Merge tag 'for-6.11-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "The highlights are new logic behind background block group reclaim,
  automatic removal of qgroup after removing a subvolume and new
  'rescue=' mount options.

  The rest is optimizations, cleanups and refactoring.

  User visible features:

   - dynamic block group reclaim:
      - tunable framework to avoid situations where eager data
        allocations prevent creating new metadata chunks due to lack of
        unallocated space
      - reuse sysfs knob bg_reclaim_threshold (otherwise used only in
        zoned mode) for a fixed value threshold
      - new on/off sysfs knob "dynamic_reclaim" calculating the value
        based on heuristics, aiming to keep spare working space for
        relocating chunks but not to needlessly relocate partially
        utilized block groups or reclaim newly allocated ones
      - stats are exported in sysfs per block group type, files
        "reclaim_*"
      - this may increase IO load at unexpected times but the corner
        case of no allocatable block groups is known to be worse

   - automatically remove qgroup of deleted subvolumes:
      - adjust qgroup removal conditions, make sure all related
        subvolume data are already removed, or return EBUSY, also take
        into account setting of sysfs drop_subtree_threshold
      - also works in squota mode

   - mount option updates: new modes of 'rescue=' that allow to mount
     images (read-only) that could have been partially converted by user
     space tools
      - ignoremetacsums  - invalid metadata checksums are ignored
      - ignoresuperflags - super block flags that track conversion in
                           progress (like UUID or checksums)

  Core:

   - size of struct btrfs_inode is now below 1024 (on a release config),
     improved memory packing and other secondary effects

   - switch tracking of open inodes from rb-tree to xarray, minor
     performance improvement

   - reduce number of empty transaction commits when there are no dirty
     data/metadata

   - memory allocation optimizations (reduced numbers, reordering out of
     critical sections)

   - extent map structure optimizations and refactoring, more sanity
     checks

   - more subpage in zoned mode preparations or fixes

   - general snapshot code cleanups, improvements and documentation

   - tree-checker updates: more file extent ram_bytes fixes, continued

   - raid-stripe-tree update (not backward compatible):
      - remove extent encoding field from the structure, can be inferred
        from other information
      - requires btrfs-progs 6.9.1 or newer

   - cleanups and refactoring
      - error message updates
      - error handling improvements
      - return type and parameter cleanups and improvements"

* tag 'for-6.11-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (152 commits)
  btrfs: fix extent map use-after-free when adding pages to compressed bio
  btrfs: fix bitmap leak when loading free space cache on duplicate entry
  btrfs: remove the BUG_ON() inside extent_range_clear_dirty_for_io()
  btrfs: move extent_range_clear_dirty_for_io() into inode.c
  btrfs: enhance compression error messages
  btrfs: fix data race when accessing the last_trans field of a root
  btrfs: rename the extra_gfp parameter of btrfs_alloc_page_array()
  btrfs: remove the extra_gfp parameter from btrfs_alloc_folio_array()
  btrfs: introduce new "rescue=ignoresuperflags" mount option
  btrfs: introduce new "rescue=ignoremetacsums" mount option
  btrfs: output the unrecognized super block flags as hex
  btrfs: remove unused Opt enums
  btrfs: tree-checker: add extra ram_bytes and disk_num_bytes check
  btrfs: fix the ram_bytes assignment for truncated ordered extents
  btrfs: make validate_extent_map() catch ram_bytes mismatch
  btrfs: ignore incorrect btrfs_file_extent_item::ram_bytes
  btrfs: cleanup the bytenr usage inside btrfs_extent_item_to_extent_map()
  btrfs: fix typo in error message in btrfs_validate_super()
  btrfs: move the direct IO code into its own file
  btrfs: pass a btrfs_inode to btrfs_set_prop()
  ...

1 files changed, 53 insertions, 21 deletions

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 0bce1d45e252..f0cf8ce26f01 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -151,7 +151,7 @@ static struct inode *btrfs_iget_logging(u64 objectid, struct btrfs_root *root)
 	 * attempt a transaction commit, resulting in a deadlock.
 	 */
 	nofs_flag = memalloc_nofs_save();
-	inode = btrfs_iget(root->fs_info->sb, objectid, root);
+	inode = btrfs_iget(objectid, root);
 	memalloc_nofs_restore(nofs_flag);
 
 	return inode;
@@ -1644,7 +1644,8 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
 		if (ret)
 			goto out;
 	}
-	BTRFS_I(inode)->index_cnt = (u64)-1;
+	if (S_ISDIR(inode->i_mode))
+		BTRFS_I(inode)->index_cnt = (u64)-1;
 
 	if (inode->i_nlink == 0) {
 		if (S_ISDIR(inode->i_mode)) {
@@ -2839,7 +2840,7 @@ static void wait_for_writer(struct btrfs_root *root)
 	finish_wait(&root->log_writer_wait, &wait);
 }
 
-void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx, struct inode *inode)
+void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx, struct btrfs_inode *inode)
 {
 	ctx->log_ret = 0;
 	ctx->log_transid = 0;
@@ -2858,7 +2859,7 @@ void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx, struct inode *inode)
 
 void btrfs_init_log_ctx_scratch_eb(struct btrfs_log_ctx *ctx)
 {
-	struct btrfs_inode *inode = BTRFS_I(ctx->inode);
+	struct btrfs_inode *inode = ctx->inode;
 
 	if (!test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags) &&
 	    !test_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags))
@@ -2876,7 +2877,7 @@ void btrfs_release_log_ctx_extents(struct btrfs_log_ctx *ctx)
 	struct btrfs_ordered_extent *ordered;
 	struct btrfs_ordered_extent *tmp;
 
-	ASSERT(inode_is_locked(ctx->inode));
+	ASSERT(inode_is_locked(&ctx->inode->vfs_inode));
 
 	list_for_each_entry_safe(ordered, tmp, &ctx->ordered_extents, log_list) {
 		list_del_init(&ordered->log_list);
@@ -4253,8 +4254,10 @@ static int log_inode_item(struct btrfs_trans_handle *trans,
 			  struct btrfs_inode *inode, bool inode_item_dropped)
 {
 	struct btrfs_inode_item *inode_item;
+	struct btrfs_key key;
 	int ret;
 
+	btrfs_get_inode_key(inode, &key);
 	/*
 	 * If we are doing a fast fsync and the inode was logged before in the
 	 * current transaction, then we know the inode was previously logged and
@@ -4266,7 +4269,7 @@ static int log_inode_item(struct btrfs_trans_handle *trans,
 	 * already exists can also result in unnecessarily splitting a leaf.
 	 */
 	if (!inode_item_dropped && inode->logged_trans == trans->transid) {
-		ret = btrfs_search_slot(trans, log, &inode->location, path, 0, 1);
+		ret = btrfs_search_slot(trans, log, &key, path, 0, 1);
 		ASSERT(ret <= 0);
 		if (ret > 0)
 			ret = -ENOENT;
@@ -4280,7 +4283,7 @@ static int log_inode_item(struct btrfs_trans_handle *trans,
 		 * the inode, we set BTRFS_INODE_NEEDS_FULL_SYNC on its runtime
 		 * flags and set ->logged_trans to 0.
 		 */
-		ret = btrfs_insert_empty_item(trans, log, path, &inode->location,
+		ret = btrfs_insert_empty_item(trans, log, path, &key,
 					      sizeof(*inode_item));
 		ASSERT(ret != -EEXIST);
 	}
@@ -4594,6 +4597,7 @@ static int log_extent_csums(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_ordered_extent *ordered;
 	struct btrfs_root *csum_root;
+	u64 block_start;
 	u64 csum_offset;
 	u64 csum_len;
 	u64 mod_start = em->start;
@@ -4603,7 +4607,7 @@ static int log_extent_csums(struct btrfs_trans_handle *trans,
 
 	if (inode->flags & BTRFS_INODE_NODATASUM ||
 	    (em->flags & EXTENT_FLAG_PREALLOC) ||
-	    em->block_start == EXTENT_MAP_HOLE)
+	    em->disk_bytenr == EXTENT_MAP_HOLE)
 		return 0;
 
 	list_for_each_entry(ordered, &ctx->ordered_extents, log_list) {
@@ -4667,17 +4671,18 @@ static int log_extent_csums(struct btrfs_trans_handle *trans,
 	/* If we're compressed we have to save the entire range of csums. */
 	if (extent_map_is_compressed(em)) {
 		csum_offset = 0;
-		csum_len = max(em->block_len, em->orig_block_len);
+		csum_len = em->disk_num_bytes;
 	} else {
 		csum_offset = mod_start - em->start;
 		csum_len = mod_len;
 	}
 
 	/* block start is already adjusted for the file extent offset. */
-	csum_root = btrfs_csum_root(trans->fs_info, em->block_start);
-	ret = btrfs_lookup_csums_list(csum_root, em->block_start + csum_offset,
-				      em->block_start + csum_offset +
-				      csum_len - 1, &ordered_sums, false);
+	block_start = extent_map_block_start(em);
+	csum_root = btrfs_csum_root(trans->fs_info, block_start);
+	ret = btrfs_lookup_csums_list(csum_root, block_start + csum_offset,
+				      block_start + csum_offset + csum_len - 1,
+				      &ordered_sums, false);
 	if (ret < 0)
 		return ret;
 	ret = 0;
@@ -4707,7 +4712,8 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 	struct extent_buffer *leaf;
 	struct btrfs_key key;
 	enum btrfs_compression_type compress_type;
-	u64 extent_offset = em->start - em->orig_start;
+	u64 extent_offset = em->offset;
+	u64 block_start = extent_map_block_start(em);
 	u64 block_len;
 	int ret;
 
@@ -4717,14 +4723,13 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 	else
 		btrfs_set_stack_file_extent_type(&fi, BTRFS_FILE_EXTENT_REG);
 
-	block_len = max(em->block_len, em->orig_block_len);
+	block_len = em->disk_num_bytes;
 	compress_type = extent_map_compression(em);
 	if (compress_type != BTRFS_COMPRESS_NONE) {
-		btrfs_set_stack_file_extent_disk_bytenr(&fi, em->block_start);
+		btrfs_set_stack_file_extent_disk_bytenr(&fi, block_start);
 		btrfs_set_stack_file_extent_disk_num_bytes(&fi, block_len);
-	} else if (em->block_start < EXTENT_MAP_LAST_BYTE) {
-		btrfs_set_stack_file_extent_disk_bytenr(&fi, em->block_start -
-							extent_offset);
+	} else if (em->disk_bytenr < EXTENT_MAP_LAST_BYTE) {
+		btrfs_set_stack_file_extent_disk_bytenr(&fi, block_start - extent_offset);
 		btrfs_set_stack_file_extent_disk_num_bytes(&fi, block_len);
 	}
 
@@ -5927,7 +5932,7 @@ again:
 			if (ret < 0) {
 				return ret;
 			} else if (ret > 0 &&
-				   other_ino != btrfs_ino(BTRFS_I(ctx->inode))) {
+				   other_ino != btrfs_ino(ctx->inode)) {
 				if (ins_nr > 0) {
 					ins_nr++;
 				} else {
@@ -7074,6 +7079,15 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 	}
 
 	/*
+	 * If we're logging an inode from a subvolume created in the current
+	 * transaction we must force a commit since the root is not persisted.
+	 */
+	if (btrfs_root_generation(&root->root_item) == trans->transid) {
+		ret = BTRFS_LOG_FORCE_COMMIT;
+		goto end_no_trans;
+	}
+
+	/*
 	 * Skip already logged inodes or inodes corresponding to tmpfiles
 	 * (since logging them is pointless, a link count of 0 means they
 	 * will never be accessible).
@@ -7454,6 +7468,24 @@ void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans,
 }
 
 /*
+ * Call this when creating a subvolume in a directory.
+ * Because we don't commit a transaction when creating a subvolume, we can't
+ * allow the directory pointing to the subvolume to be logged with an entry that
+ * points to an unpersisted root if we are still in the transaction used to
+ * create the subvolume, so make any attempt to log the directory to result in a
+ * full log sync.
+ * Also we don't need to worry with renames, since btrfs_rename() marks the log
+ * for full commit when renaming a subvolume.
+ */
+void btrfs_record_new_subvolume(const struct btrfs_trans_handle *trans,
+				struct btrfs_inode *dir)
+{
+	mutex_lock(&dir->log_mutex);
+	dir->last_unlink_trans = trans->transid;
+	mutex_unlock(&dir->log_mutex);
+}
+
+/*
  * Update the log after adding a new name for an inode.
  *
  * @trans:              Transaction handle.
@@ -7585,7 +7617,7 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans,
 			goto out;
 	}
 
-	btrfs_init_log_ctx(&ctx, &inode->vfs_inode);
+	btrfs_init_log_ctx(&ctx, inode);
 	ctx.logging_new_name = true;
 	btrfs_init_log_ctx_scratch_eb(&ctx);
 	/*