1 files changed, 154 insertions, 458 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index a1adadd5d25d..5999ac3ee601 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -98,7 +98,6 @@ void btrfs_extent_buffer_leak_debug_check(struct btrfs_fs_info *fs_info)
  */
 struct btrfs_bio_ctrl {
 	struct btrfs_bio *bbio;
-	int mirror_num;
 	enum btrfs_compression_type compress_type;
 	u32 len_to_oe_boundary;
 	blk_opf_t opf;
@@ -106,15 +105,6 @@ struct btrfs_bio_ctrl {
 	struct writeback_control *wbc;
 
 	/*
-	 * This is for metadata read, to provide the extra needed verification
-	 * info.  This has to be provided for submit_one_bio(), as
-	 * submit_one_bio() can submit a bio if it ends at stripe boundary.  If
-	 * no such parent_check is provided, the metadata can hit false alert at
-	 * endio time.
-	 */
-	struct btrfs_tree_parent_check *parent_check;
-
-	/*
 	 * Tell writepage not to lock the state bits for this range, it still
 	 * does the unlocking.
 	 */
@@ -124,7 +114,6 @@ struct btrfs_bio_ctrl {
 static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl)
 {
 	struct btrfs_bio *bbio = bio_ctrl->bbio;
-	int mirror_num = bio_ctrl->mirror_num;
 
 	if (!bbio)
 		return;
@@ -132,25 +121,11 @@ static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl)
 	/* Caller should ensure the bio has at least some range added */
 	ASSERT(bbio->bio.bi_iter.bi_size);
 
-	if (!is_data_inode(&bbio->inode->vfs_inode)) {
-		if (btrfs_op(&bbio->bio) != BTRFS_MAP_WRITE) {
-			/*
-			 * For metadata read, we should have the parent_check,
-			 * and copy it to bbio for metadata verification.
-			 */
-			ASSERT(bio_ctrl->parent_check);
-			memcpy(&bbio->parent_check,
-			       bio_ctrl->parent_check,
-			       sizeof(struct btrfs_tree_parent_check));
-		}
-		bbio->bio.bi_opf |= REQ_META;
-	}
-
 	if (btrfs_op(&bbio->bio) == BTRFS_MAP_READ &&
 	    bio_ctrl->compress_type != BTRFS_COMPRESS_NONE)
-		btrfs_submit_compressed_read(bbio, mirror_num);
+		btrfs_submit_compressed_read(bbio);
 	else
-		btrfs_submit_bio(bbio, mirror_num);
+		btrfs_submit_bio(bbio, 0);
 
 	/* The bbio is owned by the end_io handler now */
 	bio_ctrl->bbio = NULL;
@@ -686,35 +661,6 @@ static void begin_page_read(struct btrfs_fs_info *fs_info, struct page *page)
 }
 
 /*
- * Find extent buffer for a givne bytenr.
- *
- * This is for end_bio_extent_readpage(), thus we can't do any unsafe locking
- * in endio context.
- */
-static struct extent_buffer *find_extent_buffer_readpage(
-		struct btrfs_fs_info *fs_info, struct page *page, u64 bytenr)
-{
-	struct extent_buffer *eb;
-
-	/*
-	 * For regular sectorsize, we can use page->private to grab extent
-	 * buffer
-	 */
-	if (fs_info->nodesize >= PAGE_SIZE) {
-		ASSERT(PagePrivate(page) && page->private);
-		return (struct extent_buffer *)page->private;
-	}
-
-	/* For subpage case, we need to lookup buffer radix tree */
-	rcu_read_lock();
-	eb = radix_tree_lookup(&fs_info->buffer_radix,
-			       bytenr >> fs_info->sectorsize_bits);
-	rcu_read_unlock();
-	ASSERT(eb);
-	return eb;
-}
-
-/*
  * after a readpage IO is done, we need to:
  * clear the uptodate bits on error
  * set the uptodate bits if things worked
@@ -735,7 +681,6 @@ static void end_bio_extent_readpage(struct btrfs_bio *bbio)
 	 * larger than UINT_MAX, u32 here is enough.
 	 */
 	u32 bio_offset = 0;
-	int mirror;
 	struct bvec_iter_all iter_all;
 
 	ASSERT(!bio_flagged(bio, BIO_CLONED));
@@ -775,11 +720,6 @@ static void end_bio_extent_readpage(struct btrfs_bio *bbio)
 		end = start + bvec->bv_len - 1;
 		len = bvec->bv_len;
 
-		mirror = bbio->mirror_num;
-		if (uptodate && !is_data_inode(inode) &&
-		    btrfs_validate_metadata_buffer(bbio, page, start, end, mirror))
-			uptodate = false;
-
 		if (likely(uptodate)) {
 			loff_t i_size = i_size_read(inode);
 			pgoff_t end_index = i_size >> PAGE_SHIFT;
@@ -800,13 +740,6 @@ static void end_bio_extent_readpage(struct btrfs_bio *bbio)
 				zero_user_segment(page, zero_start,
 						  offset_in_page(end) + 1);
 			}
-		} else if (!is_data_inode(inode)) {
-			struct extent_buffer *eb;
-
-			eb = find_extent_buffer_readpage(fs_info, page, start);
-			set_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
-			eb->read_mirror = mirror;
-			atomic_dec(&eb->io_pages);
 		}
 
 		/* Update page status and unlock. */
@@ -1681,52 +1614,26 @@ void wait_on_extent_buffer_writeback(struct extent_buffer *eb)
 		       TASK_UNINTERRUPTIBLE);
 }
 
-static void end_extent_buffer_writeback(struct extent_buffer *eb)
-{
-	clear_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags);
-	smp_mb__after_atomic();
-	wake_up_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK);
-}
-
 /*
  * Lock extent buffer status and pages for writeback.
  *
- * May try to flush write bio if we can't get the lock.
- *
- * Return  0 if the extent buffer doesn't need to be submitted.
- *           (E.g. the extent buffer is not dirty)
- * Return >0 is the extent buffer is submitted to bio.
- * Return <0 if something went wrong, no page is locked.
+ * Return %false if the extent buffer doesn't need to be submitted (e.g. the
+ * extent buffer is not dirty)
+ * Return %true is the extent buffer is submitted to bio.
  */
-static noinline_for_stack int lock_extent_buffer_for_io(struct extent_buffer *eb,
-			  struct btrfs_bio_ctrl *bio_ctrl)
+static bool lock_extent_buffer_for_io(struct extent_buffer *eb,
+				      struct writeback_control *wbc)
 {
 	struct btrfs_fs_info *fs_info = eb->fs_info;
-	int i, num_pages;
-	int flush = 0;
-	int ret = 0;
+	bool ret = false;
 
-	if (!btrfs_try_tree_write_lock(eb)) {
-		submit_write_bio(bio_ctrl, 0);
-		flush = 1;
-		btrfs_tree_lock(eb);
-	}
-
-	if (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags)) {
+	btrfs_tree_lock(eb);
+	while (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags)) {
 		btrfs_tree_unlock(eb);
-		if (bio_ctrl->wbc->sync_mode != WB_SYNC_ALL)
-			return 0;
-		if (!flush) {
-			submit_write_bio(bio_ctrl, 0);
-			flush = 1;
-		}
-		while (1) {
-			wait_on_extent_buffer_writeback(eb);
-			btrfs_tree_lock(eb);
-			if (!test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags))
-				break;
-			btrfs_tree_unlock(eb);
-		}
+		if (wbc->sync_mode != WB_SYNC_ALL)
+			return false;
+		wait_on_extent_buffer_writeback(eb);
+		btrfs_tree_lock(eb);
 	}
 
 	/*
@@ -1742,45 +1649,19 @@ static noinline_for_stack int lock_extent_buffer_for_io(struct extent_buffer *eb
 		percpu_counter_add_batch(&fs_info->dirty_metadata_bytes,
 					 -eb->len,
 					 fs_info->dirty_metadata_batch);
-		ret = 1;
+		ret = true;
 	} else {
 		spin_unlock(&eb->refs_lock);
 	}
-
 	btrfs_tree_unlock(eb);
-
-	/*
-	 * Either we don't need to submit any tree block, or we're submitting
-	 * subpage eb.
-	 * Subpage metadata doesn't use page locking at all, so we can skip
-	 * the page locking.
-	 */
-	if (!ret || fs_info->nodesize < PAGE_SIZE)
-		return ret;
-
-	num_pages = num_extent_pages(eb);
-	for (i = 0; i < num_pages; i++) {
-		struct page *p = eb->pages[i];
-
-		if (!trylock_page(p)) {
-			if (!flush) {
-				submit_write_bio(bio_ctrl, 0);
-				flush = 1;
-			}
-			lock_page(p);
-		}
-	}
-
 	return ret;
 }
 
-static void set_btree_ioerr(struct page *page, struct extent_buffer *eb)
+static void set_btree_ioerr(struct extent_buffer *eb)
 {
 	struct btrfs_fs_info *fs_info = eb->fs_info;
 
-	btrfs_page_set_error(fs_info, page, eb->start, eb->len);
-	if (test_and_set_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags))
-		return;
+	set_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags);
 
 	/*
 	 * A read may stumble upon this buffer later, make sure that it gets an
@@ -1794,7 +1675,7 @@ static void set_btree_ioerr(struct page *page, struct extent_buffer *eb)
 	 * return a 0 because we are readonly if we don't modify the err seq for
 	 * the superblock.
 	 */
-	mapping_set_error(page->mapping, -EIO);
+	mapping_set_error(eb->fs_info->btree_inode->i_mapping, -EIO);
 
 	/*
 	 * If writeback for a btree extent that doesn't belong to a log tree
@@ -1869,101 +1750,34 @@ static struct extent_buffer *find_extent_buffer_nolock(
 	return NULL;
 }
 
-/*
- * The endio function for subpage extent buffer write.
- *
- * Unlike end_bio_extent_buffer_writepage(), we only call end_page_writeback()
- * after all extent buffers in the page has finished their writeback.
- */
-static void end_bio_subpage_eb_writepage(struct btrfs_bio *bbio)
+static void extent_buffer_write_end_io(struct btrfs_bio *bbio)
 {
-	struct bio *bio = &bbio->bio;
-	struct btrfs_fs_info *fs_info;
-	struct bio_vec *bvec;
+	struct extent_buffer *eb = bbio->private;
+	struct btrfs_fs_info *fs_info = eb->fs_info;
+	bool uptodate = !bbio->bio.bi_status;
 	struct bvec_iter_all iter_all;
+	struct bio_vec *bvec;
+	u32 bio_offset = 0;
 
-	fs_info = btrfs_sb(bio_first_page_all(bio)->mapping->host->i_sb);
-	ASSERT(fs_info->nodesize < PAGE_SIZE);
+	if (!uptodate)
+		set_btree_ioerr(eb);
 
-	ASSERT(!bio_flagged(bio, BIO_CLONED));
-	bio_for_each_segment_all(bvec, bio, iter_all) {
+	bio_for_each_segment_all(bvec, &bbio->bio, iter_all) {
+		u64 start = eb->start + bio_offset;
 		struct page *page = bvec->bv_page;
-		u64 bvec_start = page_offset(page) + bvec->bv_offset;
-		u64 bvec_end = bvec_start + bvec->bv_len - 1;
-		u64 cur_bytenr = bvec_start;
-
-		ASSERT(IS_ALIGNED(bvec->bv_len, fs_info->nodesize));
-
-		/* Iterate through all extent buffers in the range */
-		while (cur_bytenr <= bvec_end) {
-			struct extent_buffer *eb;
-			int done;
+		u32 len = bvec->bv_len;
 
-			/*
-			 * Here we can't use find_extent_buffer(), as it may
-			 * try to lock eb->refs_lock, which is not safe in endio
-			 * context.
-			 */
-			eb = find_extent_buffer_nolock(fs_info, cur_bytenr);
-			ASSERT(eb);
-
-			cur_bytenr = eb->start + eb->len;
-
-			ASSERT(test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags));
-			done = atomic_dec_and_test(&eb->io_pages);
-			ASSERT(done);
-
-			if (bio->bi_status ||
-			    test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) {
-				ClearPageUptodate(page);
-				set_btree_ioerr(page, eb);
-			}
-
-			btrfs_subpage_clear_writeback(fs_info, page, eb->start,
-						      eb->len);
-			end_extent_buffer_writeback(eb);
-			/*
-			 * free_extent_buffer() will grab spinlock which is not
-			 * safe in endio context. Thus here we manually dec
-			 * the ref.
-			 */
-			atomic_dec(&eb->refs);
-		}
+		if (!uptodate)
+			btrfs_page_clear_uptodate(fs_info, page, start, len);
+		btrfs_page_clear_writeback(fs_info, page, start, len);
+		bio_offset += len;
 	}
-	bio_put(bio);
-}
-
-static void end_bio_extent_buffer_writepage(struct btrfs_bio *bbio)
-{
-	struct bio *bio = &bbio->bio;
-	struct bio_vec *bvec;
-	struct extent_buffer *eb;
-	int done;
-	struct bvec_iter_all iter_all;
-
-	ASSERT(!bio_flagged(bio, BIO_CLONED));
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		struct page *page = bvec->bv_page;
-
-		eb = (struct extent_buffer *)page->private;
-		BUG_ON(!eb);
-		done = atomic_dec_and_test(&eb->io_pages);
-
-		if (bio->bi_status ||
-		    test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) {
-			ClearPageUptodate(page);
-			set_btree_ioerr(page, eb);
-		}
-
-		end_page_writeback(page);
-
-		if (!done)
-			continue;
 
-		end_extent_buffer_writeback(eb);
-	}
+	clear_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags);
+	smp_mb__after_atomic();
+	wake_up_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK);
 
-	bio_put(bio);
+	bio_put(&bbio->bio);
 }
 
 static void prepare_eb_write(struct extent_buffer *eb)
@@ -1973,7 +1787,6 @@ static void prepare_eb_write(struct extent_buffer *eb)
 	unsigned long end;
 
 	clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags);
-	atomic_set(&eb->io_pages, num_extent_pages(eb));
 
 	/* Set btree blocks beyond nritems with 0 to avoid stale content */
 	nritems = btrfs_header_nritems(eb);
@@ -1995,63 +1808,48 @@ static void prepare_eb_write(struct extent_buffer *eb)
 	}
 }
 
-/*
- * Unlike the work in write_one_eb(), we rely completely on extent locking.
- * Page locking is only utilized at minimum to keep the VMM code happy.
- */
-static void write_one_subpage_eb(struct extent_buffer *eb,
-				 struct btrfs_bio_ctrl *bio_ctrl)
-{
-	struct btrfs_fs_info *fs_info = eb->fs_info;
-	struct page *page = eb->pages[0];
-	bool no_dirty_ebs = false;
-
-	prepare_eb_write(eb);
-
-	/* clear_page_dirty_for_io() in subpage helper needs page locked */
-	lock_page(page);
-	btrfs_subpage_set_writeback(fs_info, page, eb->start, eb->len);
-
-	/* Check if this is the last dirty bit to update nr_written */
-	no_dirty_ebs = btrfs_subpage_clear_and_test_dirty(fs_info, page,
-							  eb->start, eb->len);
-	if (no_dirty_ebs)
-		clear_page_dirty_for_io(page);
-
-	bio_ctrl->end_io_func = end_bio_subpage_eb_writepage;
-
-	submit_extent_page(bio_ctrl, eb->start, page, eb->len,
-			   eb->start - page_offset(page));
-	unlock_page(page);
-	/*
-	 * Submission finished without problem, if no range of the page is
-	 * dirty anymore, we have submitted a page.  Update nr_written in wbc.
-	 */
-	if (no_dirty_ebs)
-		bio_ctrl->wbc->nr_to_write--;
-}
-
 static noinline_for_stack void write_one_eb(struct extent_buffer *eb,
-			struct btrfs_bio_ctrl *bio_ctrl)
+					    struct writeback_control *wbc)
 {
-	u64 disk_bytenr = eb->start;
-	int i, num_pages;
+	struct btrfs_fs_info *fs_info = eb->fs_info;
+	struct btrfs_bio *bbio;
 
 	prepare_eb_write(eb);
 
-	bio_ctrl->end_io_func = end_bio_extent_buffer_writepage;
+	bbio = btrfs_bio_alloc(INLINE_EXTENT_BUFFER_PAGES,
+			       REQ_OP_WRITE | REQ_META | wbc_to_write_flags(wbc),
+			       eb->fs_info, extent_buffer_write_end_io, eb);
+	bbio->bio.bi_iter.bi_sector = eb->start >> SECTOR_SHIFT;
+	bbio->inode = BTRFS_I(eb->fs_info->btree_inode);
+	bbio->file_offset = eb->start;
+	if (fs_info->nodesize < PAGE_SIZE) {
+		struct page *p = eb->pages[0];
+
+		lock_page(p);
+		btrfs_subpage_set_writeback(fs_info, p, eb->start, eb->len);
+		if (btrfs_subpage_clear_and_test_dirty(fs_info, p, eb->start,
+						       eb->len)) {
+			clear_page_dirty_for_io(p);
+			wbc->nr_to_write--;
+		}
+		__bio_add_page(&bbio->bio, p, eb->len,
+			       eb->start - page_offset(p));
+		unlock_page(p);
+	} else {
+		int i;
 
-	num_pages = num_extent_pages(eb);
-	for (i = 0; i < num_pages; i++) {
-		struct page *p = eb->pages[i];
+		for (i = 0; i < num_extent_pages(eb); i++) {
+			struct page *p = eb->pages[i];
 
-		clear_page_dirty_for_io(p);
-		set_page_writeback(p);
-		submit_extent_page(bio_ctrl, disk_bytenr, p, PAGE_SIZE, 0);
-		disk_bytenr += PAGE_SIZE;
-		bio_ctrl->wbc->nr_to_write--;
-		unlock_page(p);
+			lock_page(p);
+			clear_page_dirty_for_io(p);
+			set_page_writeback(p);
+			__bio_add_page(&bbio->bio, p, PAGE_SIZE, 0);
+			wbc->nr_to_write--;
+			unlock_page(p);
+		}
 	}
+	btrfs_submit_bio(bbio, 0);
 }
 
 /*
@@ -2068,14 +1866,13 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb,
  * Return >=0 for the number of submitted extent buffers.
  * Return <0 for fatal error.
  */
-static int submit_eb_subpage(struct page *page, struct btrfs_bio_ctrl *bio_ctrl)
+static int submit_eb_subpage(struct page *page, struct writeback_control *wbc)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
 	int submitted = 0;
 	u64 page_start = page_offset(page);
 	int bit_start = 0;
 	int sectors_per_node = fs_info->nodesize >> fs_info->sectorsize_bits;
-	int ret;
 
 	/* Lock and write each dirty extent buffers in the range */
 	while (bit_start < fs_info->subpage_info->bitmap_nr_bits) {
@@ -2121,25 +1918,13 @@ static int submit_eb_subpage(struct page *page, struct btrfs_bio_ctrl *bio_ctrl)
 		if (!eb)
 			continue;
 
-		ret = lock_extent_buffer_for_io(eb, bio_ctrl);
-		if (ret == 0) {
-			free_extent_buffer(eb);
-			continue;
-		}
-		if (ret < 0) {
-			free_extent_buffer(eb);
-			goto cleanup;
+		if (lock_extent_buffer_for_io(eb, wbc)) {
+			write_one_eb(eb, wbc);
+			submitted++;
 		}
-		write_one_subpage_eb(eb, bio_ctrl);
 		free_extent_buffer(eb);
-		submitted++;
 	}
 	return submitted;
-
-cleanup:
-	/* We hit error, end bio for the submitted extent buffers */
-	submit_write_bio(bio_ctrl, ret);
-	return ret;
 }
 
 /*
@@ -2162,7 +1947,7 @@ cleanup:
  * previous call.
  * Return <0 for fatal error.
  */
-static int submit_eb_page(struct page *page, struct btrfs_bio_ctrl *bio_ctrl,
+static int submit_eb_page(struct page *page, struct writeback_control *wbc,
 			  struct extent_buffer **eb_context)
 {
 	struct address_space *mapping = page->mapping;
@@ -2174,7 +1959,7 @@ static int submit_eb_page(struct page *page, struct btrfs_bio_ctrl *bio_ctrl,
 		return 0;
 
 	if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE)
-		return submit_eb_subpage(page, bio_ctrl);
+		return submit_eb_subpage(page, wbc);
 
 	spin_lock(&mapping->private_lock);
 	if (!PagePrivate(page)) {
@@ -2207,8 +1992,7 @@ static int submit_eb_page(struct page *page, struct btrfs_bio_ctrl *bio_ctrl,
 		 * If for_sync, this hole will be filled with
 		 * trasnsaction commit.
 		 */
-		if (bio_ctrl->wbc->sync_mode == WB_SYNC_ALL &&
-		    !bio_ctrl->wbc->for_sync)
+		if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync)
 			ret = -EAGAIN;
 		else
 			ret = 0;
@@ -2218,13 +2002,12 @@ static int submit_eb_page(struct page *page, struct btrfs_bio_ctrl *bio_ctrl,
 
 	*eb_context = eb;
 
-	ret = lock_extent_buffer_for_io(eb, bio_ctrl);
-	if (ret <= 0) {
+	if (!lock_extent_buffer_for_io(eb, wbc)) {
 		btrfs_revert_meta_write_pointer(cache, eb);
 		if (cache)
 			btrfs_put_block_group(cache);
 		free_extent_buffer(eb);
-		return ret;
+		return 0;
 	}
 	if (cache) {
 		/*
@@ -2233,7 +2016,7 @@ static int submit_eb_page(struct page *page, struct btrfs_bio_ctrl *bio_ctrl,
 		btrfs_schedule_zone_finish_bg(cache, eb);
 		btrfs_put_block_group(cache);
 	}
-	write_one_eb(eb, bio_ctrl);
+	write_one_eb(eb, wbc);
 	free_extent_buffer(eb);
 	return 1;
 }
@@ -2242,11 +2025,6 @@ int btree_write_cache_pages(struct address_space *mapping,
 				   struct writeback_control *wbc)
 {
 	struct extent_buffer *eb_context = NULL;
-	struct btrfs_bio_ctrl bio_ctrl = {
-		.wbc = wbc,
-		.opf = REQ_OP_WRITE | wbc_to_write_flags(wbc),
-		.extent_locked = 0,
-	};
 	struct btrfs_fs_info *fs_info = BTRFS_I(mapping->host)->root->fs_info;
 	int ret = 0;
 	int done = 0;
@@ -2288,7 +2066,7 @@ retry:
 		for (i = 0; i < nr_folios; i++) {
 			struct folio *folio = fbatch.folios[i];
 
-			ret = submit_eb_page(&folio->page, &bio_ctrl, &eb_context);
+			ret = submit_eb_page(&folio->page, wbc, &eb_context);
 			if (ret == 0)
 				continue;
 			if (ret < 0) {
@@ -2349,8 +2127,6 @@ retry:
 		ret = 0;
 	if (!ret && BTRFS_FS_ERROR(fs_info))
 		ret = -EROFS;
-	submit_write_bio(&bio_ctrl, ret);
-
 	btrfs_zoned_meta_io_unlock(fs_info);
 	return ret;
 }
@@ -3421,10 +3197,9 @@ static void __free_extent_buffer(struct extent_buffer *eb)
 	kmem_cache_free(extent_buffer_cache, eb);
 }
 
-int extent_buffer_under_io(const struct extent_buffer *eb)
+static int extent_buffer_under_io(const struct extent_buffer *eb)
 {
-	return (atomic_read(&eb->io_pages) ||
-		test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags) ||
+	return (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags) ||
 		test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
 }
 
@@ -3557,11 +3332,9 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start,
 	init_rwsem(&eb->lock);
 
 	btrfs_leak_debug_add_eb(eb);
-	INIT_LIST_HEAD(&eb->release_list);
 
 	spin_lock_init(&eb->refs_lock);
 	atomic_set(&eb->refs, 1);
-	atomic_set(&eb->io_pages, 0);
 
 	ASSERT(len <= BTRFS_MAX_METADATA_BLOCKSIZE);
 
@@ -3678,9 +3451,9 @@ static void check_buffer_tree_ref(struct extent_buffer *eb)
 	 * adequately protected by the refcount, but the TREE_REF bit and
 	 * its corresponding reference are not. To protect against this
 	 * class of races, we call check_buffer_tree_ref from the codepaths
-	 * which trigger io after they set eb->io_pages. Note that once io is
-	 * initiated, TREE_REF can no longer be cleared, so that is the
-	 * moment at which any such race is best fixed.
+	 * which trigger io. Note that once io is initiated, TREE_REF can no
+	 * longer be cleared, so that is the moment at which any such race is
+	 * best fixed.
 	 */
 	refs = atomic_read(&eb->refs);
 	if (refs >= 2 && test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
@@ -4142,13 +3915,12 @@ void btrfs_clear_buffer_dirty(struct btrfs_trans_handle *trans,
 			continue;
 		lock_page(page);
 		btree_clear_page_dirty(page);
-		ClearPageError(page);
 		unlock_page(page);
 	}
 	WARN_ON(atomic_read(&eb->refs) == 0);
 }
 
-bool set_extent_buffer_dirty(struct extent_buffer *eb)
+void set_extent_buffer_dirty(struct extent_buffer *eb)
 {
 	int i;
 	int num_pages;
@@ -4183,13 +3955,14 @@ bool set_extent_buffer_dirty(struct extent_buffer *eb)
 					     eb->start, eb->len);
 		if (subpage)
 			unlock_page(eb->pages[0]);
+		percpu_counter_add_batch(&eb->fs_info->dirty_metadata_bytes,
+					 eb->len,
+					 eb->fs_info->dirty_metadata_batch);
 	}
 #ifdef CONFIG_BTRFS_DEBUG
 	for (i = 0; i < num_pages; i++)
 		ASSERT(PageDirty(eb->pages[i]));
 #endif
-
-	return was_dirty;
 }
 
 void clear_extent_buffer_uptodate(struct extent_buffer *eb)
@@ -4242,84 +4015,54 @@ void set_extent_buffer_uptodate(struct extent_buffer *eb)
 	}
 }
 
-static int read_extent_buffer_subpage(struct extent_buffer *eb, int wait,
-				      int mirror_num,
-				      struct btrfs_tree_parent_check *check)
+static void extent_buffer_read_end_io(struct btrfs_bio *bbio)
 {
+	struct extent_buffer *eb = bbio->private;
 	struct btrfs_fs_info *fs_info = eb->fs_info;
-	struct extent_io_tree *io_tree;
-	struct page *page = eb->pages[0];
-	struct extent_state *cached_state = NULL;
-	struct btrfs_bio_ctrl bio_ctrl = {
-		.opf = REQ_OP_READ,
-		.mirror_num = mirror_num,
-		.parent_check = check,
-	};
-	int ret;
+	bool uptodate = !bbio->bio.bi_status;
+	struct bvec_iter_all iter_all;
+	struct bio_vec *bvec;
+	u32 bio_offset = 0;
 
-	ASSERT(!test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags));
-	ASSERT(PagePrivate(page));
-	ASSERT(check);
-	io_tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
+	eb->read_mirror = bbio->mirror_num;
 
-	if (wait == WAIT_NONE) {
-		if (!try_lock_extent(io_tree, eb->start, eb->start + eb->len - 1,
-				     &cached_state))
-			return -EAGAIN;
-	} else {
-		ret = lock_extent(io_tree, eb->start, eb->start + eb->len - 1,
-				  &cached_state);
-		if (ret < 0)
-			return ret;
-	}
+	if (uptodate &&
+	    btrfs_validate_extent_buffer(eb, &bbio->parent_check) < 0)
+		uptodate = false;
 
-	if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags) ||
-	    PageUptodate(page) ||
-	    btrfs_subpage_test_uptodate(fs_info, page, eb->start, eb->len)) {
-		set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
-		unlock_extent(io_tree, eb->start, eb->start + eb->len - 1,
-			      &cached_state);
-		return 0;
+	if (uptodate) {
+		set_extent_buffer_uptodate(eb);
+	} else {
+		clear_extent_buffer_uptodate(eb);
+		set_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
 	}
 
-	clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
-	eb->read_mirror = 0;
-	atomic_set(&eb->io_pages, 1);
-	check_buffer_tree_ref(eb);
-	bio_ctrl.end_io_func = end_bio_extent_readpage;
+	bio_for_each_segment_all(bvec, &bbio->bio, iter_all) {
+		u64 start = eb->start + bio_offset;
+		struct page *page = bvec->bv_page;
+		u32 len = bvec->bv_len;
 
-	btrfs_subpage_clear_error(fs_info, page, eb->start, eb->len);
+		if (uptodate)
+			btrfs_page_set_uptodate(fs_info, page, start, len);
+		else
+			btrfs_page_clear_uptodate(fs_info, page, start, len);
 
-	btrfs_subpage_start_reader(fs_info, page, eb->start, eb->len);
-	submit_extent_page(&bio_ctrl, eb->start, page, eb->len,
-			   eb->start - page_offset(page));
-	submit_one_bio(&bio_ctrl);
-	if (wait != WAIT_COMPLETE) {
-		free_extent_state(cached_state);
-		return 0;
+		bio_offset += len;
 	}
 
-	wait_extent_bit(io_tree, eb->start, eb->start + eb->len - 1,
-			EXTENT_LOCKED, &cached_state);
-	if (!test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
-		return -EIO;
-	return 0;
+	clear_bit(EXTENT_BUFFER_READING, &eb->bflags);
+	smp_mb__after_atomic();
+	wake_up_bit(&eb->bflags, EXTENT_BUFFER_READING);
+	free_extent_buffer(eb);
+
+	bio_put(&bbio->bio);
 }
 
 int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num,
 			     struct btrfs_tree_parent_check *check)
 {
-	int i;
-	struct page *page;
-	int locked_pages = 0;
-	int all_uptodate = 1;
-	int num_pages;
-	unsigned long num_reads = 0;
-	struct btrfs_bio_ctrl bio_ctrl = {
-		.opf = REQ_OP_READ,
-		.mirror_num = mirror_num,
-		.parent_check = check,
-	};
+	int num_pages = num_extent_pages(eb), i;
+	struct btrfs_bio *bbio;
 
 	if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
 		return 0;
@@ -4332,87 +4075,42 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num,
 	if (unlikely(test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)))
 		return -EIO;
 
-	if (eb->fs_info->nodesize < PAGE_SIZE)
-		return read_extent_buffer_subpage(eb, wait, mirror_num, check);
-
-	num_pages = num_extent_pages(eb);
-	for (i = 0; i < num_pages; i++) {
-		page = eb->pages[i];
-		if (wait == WAIT_NONE) {
-			/*
-			 * WAIT_NONE is only utilized by readahead. If we can't
-			 * acquire the lock atomically it means either the eb
-			 * is being read out or under modification.
-			 * Either way the eb will be or has been cached,
-			 * readahead can exit safely.
-			 */
-			if (!trylock_page(page))
-				goto unlock_exit;
-		} else {
-			lock_page(page);
-		}
-		locked_pages++;
-	}
 	/*
-	 * We need to firstly lock all pages to make sure that
-	 * the uptodate bit of our pages won't be affected by
-	 * clear_extent_buffer_uptodate().
+	 * Someone else is already reading the buffer, just wait for it.
 	 */
-	for (i = 0; i < num_pages; i++) {
-		page = eb->pages[i];
-		if (!PageUptodate(page)) {
-			num_reads++;
-			all_uptodate = 0;
-		}
-	}
-
-	if (all_uptodate) {
-		set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
-		goto unlock_exit;
-	}
+	if (test_and_set_bit(EXTENT_BUFFER_READING, &eb->bflags))
+		goto done;
 
 	clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
 	eb->read_mirror = 0;
-	atomic_set(&eb->io_pages, num_reads);
-	/*
-	 * It is possible for release_folio to clear the TREE_REF bit before we
-	 * set io_pages. See check_buffer_tree_ref for a more detailed comment.
-	 */
 	check_buffer_tree_ref(eb);
-	bio_ctrl.end_io_func = end_bio_extent_readpage;
-	for (i = 0; i < num_pages; i++) {
-		page = eb->pages[i];
-
-		if (!PageUptodate(page)) {
-			ClearPageError(page);
-			submit_extent_page(&bio_ctrl, page_offset(page), page,
-					   PAGE_SIZE, 0);
-		} else {
-			unlock_page(page);
-		}
+	atomic_inc(&eb->refs);
+
+	bbio = btrfs_bio_alloc(INLINE_EXTENT_BUFFER_PAGES,
+			       REQ_OP_READ | REQ_META, eb->fs_info,
+			       extent_buffer_read_end_io, eb);
+	bbio->bio.bi_iter.bi_sector = eb->start >> SECTOR_SHIFT;
+	bbio->inode = BTRFS_I(eb->fs_info->btree_inode);
+	bbio->file_offset = eb->start;
+	memcpy(&bbio->parent_check, check, sizeof(*check));
+	if (eb->fs_info->nodesize < PAGE_SIZE) {
+		__bio_add_page(&bbio->bio, eb->pages[0], eb->len,
+			       eb->start - page_offset(eb->pages[0]));
+	} else {
+		for (i = 0; i < num_pages; i++)
+			__bio_add_page(&bbio->bio, eb->pages[i], PAGE_SIZE, 0);
 	}
+	btrfs_submit_bio(bbio, mirror_num);
 
-	submit_one_bio(&bio_ctrl);
-
-	if (wait != WAIT_COMPLETE)
-		return 0;
-
-	for (i = 0; i < num_pages; i++) {
-		page = eb->pages[i];
-		wait_on_page_locked(page);
-		if (!PageUptodate(page))
+done:
+	if (wait == WAIT_COMPLETE) {
+		wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_READING,
+			       TASK_UNINTERRUPTIBLE);
+		if (!test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
 			return -EIO;
 	}
 
 	return 0;
-
-unlock_exit:
-	while (locked_pages > 0) {
-		locked_pages--;
-		page = eb->pages[locked_pages];
-		unlock_page(page);
-	}
-	return 0;
 }
 
 static bool report_eb_range(const struct extent_buffer *eb, unsigned long start,
@@ -4561,18 +4259,16 @@ static void assert_eb_page_uptodate(const struct extent_buffer *eb,
 	 * looked up.  We don't want to complain in this case, as the page was
 	 * valid before, we just didn't write it out.  Instead we want to catch
 	 * the case where we didn't actually read the block properly, which
-	 * would have !PageUptodate && !PageError, as we clear PageError before
-	 * reading.
+	 * would have !PageUptodate && !EXTENT_BUFFER_WRITE_ERR.
 	 */
-	if (fs_info->nodesize < PAGE_SIZE) {
-		bool uptodate, error;
+	if (test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags))
+		return;
 
-		uptodate = btrfs_subpage_test_uptodate(fs_info, page,
-						       eb->start, eb->len);
-		error = btrfs_subpage_test_error(fs_info, page, eb->start, eb->len);
-		WARN_ON(!uptodate && !error);
+	if (fs_info->nodesize < PAGE_SIZE) {
+		WARN_ON(!btrfs_subpage_test_uptodate(fs_info, page,
+						     eb->start, eb->len));
 	} else {
-		WARN_ON(!PageUptodate(page) && !PageError(page));
+		WARN_ON(!PageUptodate(page));
 	}
 }