Merge tag 'for-6.16-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "Apart from numerous cleanups, there are some performance improvements
  and one minor mount option update. There's one more radix-tree
  conversion (one remaining), and continued work towards enabling large
  folios (almost finished).

  Performance:

   - extent buffer conversion to xarray gains throughput and runtime
     improvements on metadata heavy operations doing writeback (sample
     test shows +50% throughput, -33% runtime)

   - extent io tree cleanups lead to performance improvements by
     avoiding unnecessary searches or repeated searches

   - more efficient extent unpinning when committing transaction
     (estimated run time improvement 3-5%)

  User visible changes:

   - remove standalone mount option 'nologreplay', deprecated in 5.9,
     replacement is 'rescue=nologreplay'

   - in scrub, update reporting, add back device stats message after
     detected errors (accidentally removed during recent refactoring)

  Core:

   - convert extent buffer radix tree to xarray

   - in subpage mode, move block perfect compression out of experimental
     build

   - in zoned mode, introduce sub block groups to allow managing special
     block groups, like the one for relocation or tree-log, to handle
     some corner cases of ENOSPC

   - in scrub, simplify bitmaps for block tracking status

   - continued preparations for large folios:
       - remove assertions for folio order 0
       - add support where missing: compression, buffered write, defrag,
         hole punching, subpage, send

   - fix fsync of files with no hard links not persisting deletion

   - reject tree blocks which are not nodesize aligned, a precaution
     from 4.9 times

   - move transaction abort calls closer to the error sites

   - remove usage of some struct bio_vec internals

   - simplifications in extent map

   - extent IO cleanups and optimizations

   - error handling improvements

   - enhanced ASSERT() macro with optional format strings

   - cleanups:
       - remove unused code
       - naming unifications, dropped __, added prefix
       - merge similar functions
       - use common helpers for various data structures"

* tag 'for-6.16-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (198 commits)
  btrfs: move misplaced comment of btrfs_path::keep_locks
  btrfs: remove standalone "nologreplay" mount option
  btrfs: use a single variable to track return value at btrfs_page_mkwrite()
  btrfs: don't return VM_FAULT_SIGBUS on failure to set delalloc for mmap write
  btrfs: simplify early error checking in btrfs_page_mkwrite()
  btrfs: pass true to btrfs_delalloc_release_space() at btrfs_page_mkwrite()
  btrfs: fix wrong start offset for delalloc space release during mmap write
  btrfs: fix harmless race getting delayed ref head count when running delayed refs
  btrfs: log error codes during failures when writing super blocks
  btrfs: simplify error return logic when getting folio at prepare_one_folio()
  btrfs: return real error from __filemap_get_folio() calls
  btrfs: remove superfluous return value check at btrfs_dio_iomap_begin()
  btrfs: fix invalid data space release when truncating block in NOCOW mode
  btrfs: update Kconfig option descriptions
  btrfs: update list of features built under experimental config
  btrfs: send: remove btrfs_debug() calls
  btrfs: use boolean for delalloc argument to btrfs_free_reserved_extent()
  btrfs: use boolean for delalloc argument to btrfs_free_reserved_bytes()
  btrfs: fold error checks when allocating ordered extent and update comments
  btrfs: check we grabbed inode reference when allocating an ordered extent
  ...

1 files changed, 42 insertions, 31 deletions

diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 03c945711003c..9212ce110cdee 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -153,25 +153,30 @@ static struct btrfs_ordered_extent *alloc_ordered_extent(
 	struct btrfs_ordered_extent *entry;
 	int ret;
 	u64 qgroup_rsv = 0;
+	const bool is_nocow = (flags &
+	       ((1U << BTRFS_ORDERED_NOCOW) | (1U << BTRFS_ORDERED_PREALLOC)));
 
-	if (flags &
-	    ((1 << BTRFS_ORDERED_NOCOW) | (1 << BTRFS_ORDERED_PREALLOC))) {
-		/* For nocow write, we can release the qgroup rsv right now */
+	/*
+	 * For a NOCOW write we can free the qgroup reserve right now. For a COW
+	 * one we transfer the reserved space from the inode's iotree into the
+	 * ordered extent by calling btrfs_qgroup_release_data() and tracking
+	 * the qgroup reserved amount in the ordered extent, so that later after
+	 * completing the ordered extent, when running the data delayed ref it
+	 * creates, we free the reserved data with btrfs_qgroup_free_refroot().
+	 */
+	if (is_nocow)
 		ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes, &qgroup_rsv);
-		if (ret < 0)
-			return ERR_PTR(ret);
-	} else {
-		/*
-		 * The ordered extent has reserved qgroup space, release now
-		 * and pass the reserved number for qgroup_record to free.
-		 */
+	else
 		ret = btrfs_qgroup_release_data(inode, file_offset, num_bytes, &qgroup_rsv);
-		if (ret < 0)
-			return ERR_PTR(ret);
-	}
+
+	if (ret < 0)
+		return ERR_PTR(ret);
+
 	entry = kmem_cache_zalloc(btrfs_ordered_extent_cache, GFP_NOFS);
-	if (!entry)
-		return ERR_PTR(-ENOMEM);
+	if (!entry) {
+		entry = ERR_PTR(-ENOMEM);
+		goto out;
+	}
 
 	entry->file_offset = file_offset;
 	entry->num_bytes = num_bytes;
@@ -180,7 +185,12 @@ static struct btrfs_ordered_extent *alloc_ordered_extent(
 	entry->disk_num_bytes = disk_num_bytes;
 	entry->offset = offset;
 	entry->bytes_left = num_bytes;
-	entry->inode = BTRFS_I(igrab(&inode->vfs_inode));
+	if (WARN_ON_ONCE(!igrab(&inode->vfs_inode))) {
+		kmem_cache_free(btrfs_ordered_extent_cache, entry);
+		entry = ERR_PTR(-ESTALE);
+		goto out;
+	}
+	entry->inode = inode;
 	entry->compress_type = compress_type;
 	entry->truncated_len = (u64)-1;
 	entry->qgroup_rsv = qgroup_rsv;
@@ -203,6 +213,12 @@ static struct btrfs_ordered_extent *alloc_ordered_extent(
 	btrfs_mod_outstanding_extents(inode, 1);
 	spin_unlock(&inode->lock);
 
+out:
+	if (IS_ERR(entry) && !is_nocow)
+		btrfs_qgroup_free_refroot(inode->root->fs_info,
+					  btrfs_root_id(inode->root),
+					  qgroup_rsv, BTRFS_QGROUP_RSV_DATA);
+
 	return entry;
 }
 
@@ -253,7 +269,7 @@ static void insert_ordered_extent(struct btrfs_ordered_extent *entry)
  * @disk_bytenr:     Offset of extent on disk.
  * @disk_num_bytes:  Size of extent on disk.
  * @offset:          Offset into unencoded data where file data starts.
- * @flags:           Flags specifying type of extent (1 << BTRFS_ORDERED_*).
+ * @flags:           Flags specifying type of extent (1U << BTRFS_ORDERED_*).
  * @compress_type:   Compression algorithm used for data.
  *
  * Most of these parameters correspond to &struct btrfs_file_extent_item. The
@@ -607,23 +623,18 @@ out:
  */
 void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry)
 {
-	struct list_head *cur;
-	struct btrfs_ordered_sum *sum;
-
 	trace_btrfs_ordered_extent_put(entry->inode, entry);
 
 	if (refcount_dec_and_test(&entry->refs)) {
+		struct btrfs_ordered_sum *sum;
+		struct btrfs_ordered_sum *tmp;
+
 		ASSERT(list_empty(&entry->root_extent_list));
 		ASSERT(list_empty(&entry->log_list));
 		ASSERT(RB_EMPTY_NODE(&entry->rb_node));
-		if (entry->inode)
-			btrfs_add_delayed_iput(entry->inode);
-		while (!list_empty(&entry->list)) {
-			cur = entry->list.next;
-			sum = list_entry(cur, struct btrfs_ordered_sum, list);
-			list_del(&sum->list);
+		btrfs_add_delayed_iput(entry->inode);
+		list_for_each_entry_safe(sum, tmp, &entry->list, list)
 			kvfree(sum);
-		}
 		kmem_cache_free(btrfs_ordered_extent_cache, entry);
 	}
 }
@@ -1173,7 +1184,7 @@ void btrfs_lock_and_flush_ordered_range(struct btrfs_inode *inode, u64 start,
 		cachedp = cached_state;
 
 	while (1) {
-		lock_extent(&inode->io_tree, start, end, cachedp);
+		btrfs_lock_extent(&inode->io_tree, start, end, cachedp);
 		ordered = btrfs_lookup_ordered_range(inode, start,
 						     end - start + 1);
 		if (!ordered) {
@@ -1186,7 +1197,7 @@ void btrfs_lock_and_flush_ordered_range(struct btrfs_inode *inode, u64 start,
 				refcount_dec(&cache->refs);
 			break;
 		}
-		unlock_extent(&inode->io_tree, start, end, cachedp);
+		btrfs_unlock_extent(&inode->io_tree, start, end, cachedp);
 		btrfs_start_ordered_extent(ordered);
 		btrfs_put_ordered_extent(ordered);
 	}
@@ -1204,7 +1215,7 @@ bool btrfs_try_lock_ordered_range(struct btrfs_inode *inode, u64 start, u64 end,
 {
 	struct btrfs_ordered_extent *ordered;
 
-	if (!try_lock_extent(&inode->io_tree, start, end, cached_state))
+	if (!btrfs_try_lock_extent(&inode->io_tree, start, end, cached_state))
 		return false;
 
 	ordered = btrfs_lookup_ordered_range(inode, start, end - start + 1);
@@ -1212,7 +1223,7 @@ bool btrfs_try_lock_ordered_range(struct btrfs_inode *inode, u64 start, u64 end,
 		return true;
 
 	btrfs_put_ordered_extent(ordered);
-	unlock_extent(&inode->io_tree, start, end, cached_state);
+	btrfs_unlock_extent(&inode->io_tree, start, end, cached_state);
 
 	return false;
 }