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, 47 insertions, 28 deletions

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 7f11ef559be6..48d07939fee4 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -285,12 +285,12 @@ static noinline void end_compressed_writeback(const struct compressed_bio *cb)
 	unsigned long index = cb->start >> PAGE_SHIFT;
 	unsigned long end_index = (cb->start + cb->len - 1) >> PAGE_SHIFT;
 	struct folio_batch fbatch;
-	const int error = blk_status_to_errno(cb->bbio.bio.bi_status);
 	int i;
 	int ret;
 
-	if (error)
-		mapping_set_error(inode->i_mapping, error);
+	ret = blk_status_to_errno(cb->bbio.bio.bi_status);
+	if (ret)
+		mapping_set_error(inode->i_mapping, ret);
 
 	folio_batch_init(&fbatch);
 	while (index <= end_index) {
@@ -499,9 +499,9 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 		}
 
 		page_end = (pg_index << PAGE_SHIFT) + folio_size(folio) - 1;
-		lock_extent(tree, cur, page_end, NULL);
+		btrfs_lock_extent(tree, cur, page_end, NULL);
 		read_lock(&em_tree->lock);
-		em = lookup_extent_mapping(em_tree, cur, page_end + 1 - cur);
+		em = btrfs_lookup_extent_mapping(em_tree, cur, page_end + 1 - cur);
 		read_unlock(&em_tree->lock);
 
 		/*
@@ -510,20 +510,20 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 		 * to this compressed extent on disk.
 		 */
 		if (!em || cur < em->start ||
-		    (cur + fs_info->sectorsize > extent_map_end(em)) ||
-		    (extent_map_block_start(em) >> SECTOR_SHIFT) !=
+		    (cur + fs_info->sectorsize > btrfs_extent_map_end(em)) ||
+		    (btrfs_extent_map_block_start(em) >> SECTOR_SHIFT) !=
 		    orig_bio->bi_iter.bi_sector) {
-			free_extent_map(em);
-			unlock_extent(tree, cur, page_end, NULL);
+			btrfs_free_extent_map(em);
+			btrfs_unlock_extent(tree, cur, page_end, NULL);
 			folio_unlock(folio);
 			folio_put(folio);
 			break;
 		}
 		add_size = min(em->start + em->len, page_end + 1) - cur;
-		free_extent_map(em);
-		unlock_extent(tree, cur, page_end, NULL);
+		btrfs_free_extent_map(em);
+		btrfs_unlock_extent(tree, cur, page_end, NULL);
 
-		if (folio->index == end_index) {
+		if (folio_contains(folio, end_index)) {
 			size_t zero_offset = offset_in_folio(folio, isize);
 
 			if (zero_offset) {
@@ -576,19 +576,19 @@ void btrfs_submit_compressed_read(struct btrfs_bio *bbio)
 	struct extent_map *em;
 	unsigned long pflags;
 	int memstall = 0;
-	blk_status_t ret;
-	int ret2;
+	blk_status_t status;
+	int ret;
 
 	/* we need the actual starting offset of this extent in the file */
 	read_lock(&em_tree->lock);
-	em = lookup_extent_mapping(em_tree, file_offset, fs_info->sectorsize);
+	em = btrfs_lookup_extent_mapping(em_tree, file_offset, fs_info->sectorsize);
 	read_unlock(&em_tree->lock);
 	if (!em) {
-		ret = BLK_STS_IOERR;
+		status = BLK_STS_IOERR;
 		goto out;
 	}
 
-	ASSERT(extent_map_is_compressed(em));
+	ASSERT(btrfs_extent_map_is_compressed(em));
 	compressed_len = em->disk_num_bytes;
 
 	cb = alloc_compressed_bio(inode, file_offset, REQ_OP_READ,
@@ -600,21 +600,21 @@ void btrfs_submit_compressed_read(struct btrfs_bio *bbio)
 
 	cb->len = bbio->bio.bi_iter.bi_size;
 	cb->compressed_len = compressed_len;
-	cb->compress_type = extent_map_compression(em);
+	cb->compress_type = btrfs_extent_map_compression(em);
 	cb->orig_bbio = bbio;
 
-	free_extent_map(em);
+	btrfs_free_extent_map(em);
 
 	cb->nr_folios = DIV_ROUND_UP(compressed_len, PAGE_SIZE);
 	cb->compressed_folios = kcalloc(cb->nr_folios, sizeof(struct folio *), GFP_NOFS);
 	if (!cb->compressed_folios) {
-		ret = BLK_STS_RESOURCE;
+		status = BLK_STS_RESOURCE;
 		goto out_free_bio;
 	}
 
-	ret2 = btrfs_alloc_folio_array(cb->nr_folios, cb->compressed_folios);
-	if (ret2) {
-		ret = BLK_STS_RESOURCE;
+	ret = btrfs_alloc_folio_array(cb->nr_folios, cb->compressed_folios);
+	if (ret) {
+		status = BLK_STS_RESOURCE;
 		goto out_free_compressed_pages;
 	}
 
@@ -637,7 +637,7 @@ out_free_compressed_pages:
 out_free_bio:
 	bio_put(&cb->bbio.bio);
 out:
-	btrfs_bio_end_io(bbio, ret);
+	btrfs_bio_end_io(bbio, status);
 }
 
 /*
@@ -1138,6 +1138,22 @@ void __cold btrfs_exit_compress(void)
 }
 
 /*
+ * The bvec is a single page bvec from a bio that contains folios from a filemap.
+ *
+ * Since the folio may be a large one, and if the bv_page is not a head page of
+ * a large folio, then page->index is unreliable.
+ *
+ * Thus we need this helper to grab the proper file offset.
+ */
+static u64 file_offset_from_bvec(const struct bio_vec *bvec)
+{
+	const struct page *page = bvec->bv_page;
+	const struct folio *folio = page_folio(page);
+
+	return (page_pgoff(folio, page) << PAGE_SHIFT) + bvec->bv_offset;
+}
+
+/*
  * Copy decompressed data from working buffer to pages.
  *
  * @buf:		The decompressed data buffer
@@ -1182,13 +1198,14 @@ int btrfs_decompress_buf2page(const char *buf, u32 buf_len,
 		u32 copy_start;
 		/* Offset inside the full decompressed extent */
 		u32 bvec_offset;
+		void *kaddr;
 
 		bvec = bio_iter_iovec(orig_bio, orig_bio->bi_iter);
 		/*
 		 * cb->start may underflow, but subtracting that value can still
 		 * give us correct offset inside the full decompressed extent.
 		 */
-		bvec_offset = page_offset(bvec.bv_page) + bvec.bv_offset - cb->start;
+		bvec_offset = file_offset_from_bvec(&bvec) - cb->start;
 
 		/* Haven't reached the bvec range, exit */
 		if (decompressed + buf_len <= bvec_offset)
@@ -1204,10 +1221,12 @@ int btrfs_decompress_buf2page(const char *buf, u32 buf_len,
 		 * @buf + @buf_len.
 		 */
 		ASSERT(copy_start - decompressed < buf_len);
-		memcpy_to_page(bvec.bv_page, bvec.bv_offset,
-			       buf + copy_start - decompressed, copy_len);
-		cur_offset += copy_len;
 
+		kaddr = bvec_kmap_local(&bvec);
+		memcpy(kaddr, buf + copy_start - decompressed, copy_len);
+		kunmap_local(kaddr);
+
+		cur_offset += copy_len;
 		bio_advance(orig_bio, copy_len);
 		/* Finished the bio */
 		if (!orig_bio->bi_iter.bi_size)