1 files changed, 274 insertions, 406 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 90ad3006ef3a..ac3fca5a5e41 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -181,34 +181,9 @@ void extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end)
 	}
 }
 
-void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end)
-{
-	struct address_space *mapping = inode->i_mapping;
-	unsigned long index = start >> PAGE_SHIFT;
-	unsigned long end_index = end >> PAGE_SHIFT;
-	struct folio *folio;
-
-	while (index <= end_index) {
-		folio = filemap_get_folio(mapping, index);
-		filemap_dirty_folio(mapping, folio);
-		folio_account_redirty(folio);
-		index += folio_nr_pages(folio);
-		folio_put(folio);
-	}
-}
-
-/*
- * Process one page for __process_pages_contig().
- *
- * Return >0 if we hit @page == @locked_page.
- * Return 0 if we updated the page status.
- * Return -EGAIN if the we need to try again.
- * (For PAGE_LOCK case but got dirty page or page not belong to mapping)
- */
-static int process_one_page(struct btrfs_fs_info *fs_info,
-			    struct address_space *mapping,
-			    struct page *page, struct page *locked_page,
-			    unsigned long page_ops, u64 start, u64 end)
+static void process_one_page(struct btrfs_fs_info *fs_info,
+			     struct page *page, struct page *locked_page,
+			     unsigned long page_ops, u64 start, u64 end)
 {
 	u32 len;
 
@@ -224,94 +199,36 @@ static int process_one_page(struct btrfs_fs_info *fs_info,
 	if (page_ops & PAGE_END_WRITEBACK)
 		btrfs_page_clamp_clear_writeback(fs_info, page, start, len);
 
-	if (page == locked_page)
-		return 1;
-
-	if (page_ops & PAGE_LOCK) {
-		int ret;
-
-		ret = btrfs_page_start_writer_lock(fs_info, page, start, len);
-		if (ret)
-			return ret;
-		if (!PageDirty(page) || page->mapping != mapping) {
-			btrfs_page_end_writer_lock(fs_info, page, start, len);
-			return -EAGAIN;
-		}
-	}
-	if (page_ops & PAGE_UNLOCK)
+	if (page != locked_page && (page_ops & PAGE_UNLOCK))
 		btrfs_page_end_writer_lock(fs_info, page, start, len);
-	return 0;
 }
 
-static int __process_pages_contig(struct address_space *mapping,
-				  struct page *locked_page,
-				  u64 start, u64 end, unsigned long page_ops,
-				  u64 *processed_end)
+static void __process_pages_contig(struct address_space *mapping,
+				   struct page *locked_page, u64 start, u64 end,
+				   unsigned long page_ops)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(mapping->host->i_sb);
 	pgoff_t start_index = start >> PAGE_SHIFT;
 	pgoff_t end_index = end >> PAGE_SHIFT;
 	pgoff_t index = start_index;
-	unsigned long pages_processed = 0;
 	struct folio_batch fbatch;
-	int err = 0;
 	int i;
 
-	if (page_ops & PAGE_LOCK) {
-		ASSERT(page_ops == PAGE_LOCK);
-		ASSERT(processed_end && *processed_end == start);
-	}
-
 	folio_batch_init(&fbatch);
 	while (index <= end_index) {
 		int found_folios;
 
 		found_folios = filemap_get_folios_contig(mapping, &index,
 				end_index, &fbatch);
-
-		if (found_folios == 0) {
-			/*
-			 * Only if we're going to lock these pages, we can find
-			 * nothing at @index.
-			 */
-			ASSERT(page_ops & PAGE_LOCK);
-			err = -EAGAIN;
-			goto out;
-		}
-
 		for (i = 0; i < found_folios; i++) {
-			int process_ret;
 			struct folio *folio = fbatch.folios[i];
-			process_ret = process_one_page(fs_info, mapping,
-					&folio->page, locked_page, page_ops,
-					start, end);
-			if (process_ret < 0) {
-				err = -EAGAIN;
-				folio_batch_release(&fbatch);
-				goto out;
-			}
-			pages_processed += folio_nr_pages(folio);
+
+			process_one_page(fs_info, &folio->page, locked_page,
+					 page_ops, start, end);
 		}
 		folio_batch_release(&fbatch);
 		cond_resched();
 	}
-out:
-	if (err && processed_end) {
-		/*
-		 * Update @processed_end. I know this is awful since it has
-		 * two different return value patterns (inclusive vs exclusive).
-		 *
-		 * But the exclusive pattern is necessary if @start is 0, or we
-		 * underflow and check against processed_end won't work as
-		 * expected.
-		 */
-		if (pages_processed)
-			*processed_end = min(end,
-			((u64)(start_index + pages_processed) << PAGE_SHIFT) - 1);
-		else
-			*processed_end = start;
-	}
-	return err;
 }
 
 static noinline void __unlock_for_delalloc(struct inode *inode,
@@ -326,29 +243,63 @@ static noinline void __unlock_for_delalloc(struct inode *inode,
 		return;
 
 	__process_pages_contig(inode->i_mapping, locked_page, start, end,
-			       PAGE_UNLOCK, NULL);
+			       PAGE_UNLOCK);
 }
 
 static noinline int lock_delalloc_pages(struct inode *inode,
 					struct page *locked_page,
-					u64 delalloc_start,
-					u64 delalloc_end)
+					u64 start,
+					u64 end)
 {
-	unsigned long index = delalloc_start >> PAGE_SHIFT;
-	unsigned long end_index = delalloc_end >> PAGE_SHIFT;
-	u64 processed_end = delalloc_start;
-	int ret;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct address_space *mapping = inode->i_mapping;
+	pgoff_t start_index = start >> PAGE_SHIFT;
+	pgoff_t end_index = end >> PAGE_SHIFT;
+	pgoff_t index = start_index;
+	u64 processed_end = start;
+	struct folio_batch fbatch;
 
-	ASSERT(locked_page);
 	if (index == locked_page->index && index == end_index)
 		return 0;
 
-	ret = __process_pages_contig(inode->i_mapping, locked_page, delalloc_start,
-				     delalloc_end, PAGE_LOCK, &processed_end);
-	if (ret == -EAGAIN && processed_end > delalloc_start)
-		__unlock_for_delalloc(inode, locked_page, delalloc_start,
-				      processed_end);
-	return ret;
+	folio_batch_init(&fbatch);
+	while (index <= end_index) {
+		unsigned int found_folios, i;
+
+		found_folios = filemap_get_folios_contig(mapping, &index,
+				end_index, &fbatch);
+		if (found_folios == 0)
+			goto out;
+
+		for (i = 0; i < found_folios; i++) {
+			struct page *page = &fbatch.folios[i]->page;
+			u32 len = end + 1 - start;
+
+			if (page == locked_page)
+				continue;
+
+			if (btrfs_page_start_writer_lock(fs_info, page, start,
+							 len))
+				goto out;
+
+			if (!PageDirty(page) || page->mapping != mapping) {
+				btrfs_page_end_writer_lock(fs_info, page, start,
+							   len);
+				goto out;
+			}
+
+			processed_end = page_offset(page) + PAGE_SIZE - 1;
+		}
+		folio_batch_release(&fbatch);
+		cond_resched();
+	}
+
+	return 0;
+out:
+	folio_batch_release(&fbatch);
+	if (processed_end > start)
+		__unlock_for_delalloc(inode, locked_page, start, processed_end);
+	return -EAGAIN;
 }
 
 /*
@@ -467,7 +418,7 @@ void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
 	clear_extent_bit(&inode->io_tree, start, end, clear_bits, NULL);
 
 	__process_pages_contig(inode->vfs_inode.i_mapping, locked_page,
-			       start, end, page_ops, NULL);
+			       start, end, page_ops);
 }
 
 static bool btrfs_verify_page(struct page *page, u64 start)
@@ -497,31 +448,6 @@ static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len)
 		btrfs_subpage_end_reader(fs_info, page, start, len);
 }
 
-/* lots and lots of room for performance fixes in the end_bio funcs */
-
-void end_extent_writepage(struct page *page, int err, u64 start, u64 end)
-{
-	struct btrfs_inode *inode;
-	const bool uptodate = (err == 0);
-	int ret = 0;
-
-	ASSERT(page && page->mapping);
-	inode = BTRFS_I(page->mapping->host);
-	btrfs_writepage_endio_finish_ordered(inode, page, start, end, uptodate);
-
-	if (!uptodate) {
-		const struct btrfs_fs_info *fs_info = inode->root->fs_info;
-		u32 len;
-
-		ASSERT(end + 1 - start <= U32_MAX);
-		len = end + 1 - start;
-
-		btrfs_page_clear_uptodate(fs_info, page, start, len);
-		ret = err < 0 ? err : -EIO;
-		mapping_set_error(page->mapping, ret);
-	}
-}
-
 /*
  * after a writepage IO is done, we need to:
  * clear the uptodate bits on error
@@ -1243,38 +1169,45 @@ static inline void contiguous_readpages(struct page *pages[], int nr_pages,
 static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode,
 		struct page *page, struct writeback_control *wbc)
 {
-	const u64 page_end = page_offset(page) + PAGE_SIZE - 1;
-	u64 delalloc_start = page_offset(page);
+	const u64 page_start = page_offset(page);
+	const u64 page_end = page_start + PAGE_SIZE - 1;
+	u64 delalloc_start = page_start;
+	u64 delalloc_end = page_end;
 	u64 delalloc_to_write = 0;
-	/* How many pages are started by btrfs_run_delalloc_range() */
-	unsigned long nr_written = 0;
-	int ret;
-	int page_started = 0;
+	int ret = 0;
 
 	while (delalloc_start < page_end) {
-		u64 delalloc_end = page_end;
-		bool found;
-
-		found = find_lock_delalloc_range(&inode->vfs_inode, page,
-					       &delalloc_start,
-					       &delalloc_end);
-		if (!found) {
+		delalloc_end = page_end;
+		if (!find_lock_delalloc_range(&inode->vfs_inode, page,
+					      &delalloc_start, &delalloc_end)) {
 			delalloc_start = delalloc_end + 1;
 			continue;
 		}
+
 		ret = btrfs_run_delalloc_range(inode, page, delalloc_start,
-				delalloc_end, &page_started, &nr_written, wbc);
-		if (ret)
+					       delalloc_end, wbc);
+		if (ret < 0)
 			return ret;
 
-		/*
-		 * delalloc_end is already one less than the total length, so
-		 * we don't subtract one from PAGE_SIZE
-		 */
-		delalloc_to_write += (delalloc_end - delalloc_start +
-				      PAGE_SIZE) >> PAGE_SHIFT;
 		delalloc_start = delalloc_end + 1;
 	}
+
+	/*
+	 * delalloc_end is already one less than the total length, so
+	 * we don't subtract one from PAGE_SIZE
+	 */
+	delalloc_to_write +=
+		DIV_ROUND_UP(delalloc_end + 1 - page_start, PAGE_SIZE);
+
+	/*
+	 * If btrfs_run_dealloc_range() already started I/O and unlocked
+	 * the pages, we just need to account for them here.
+	 */
+	if (ret == 1) {
+		wbc->nr_to_write -= delalloc_to_write;
+		return 1;
+	}
+
 	if (wbc->nr_to_write < delalloc_to_write) {
 		int thresh = 8192;
 
@@ -1284,16 +1217,6 @@ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode,
 					 thresh);
 	}
 
-	/* Did btrfs_run_dealloc_range() already unlock and start the IO? */
-	if (page_started) {
-		/*
-		 * We've unlocked the page, so we can't update the mapping's
-		 * writeback index, just update nr_to_write.
-		 */
-		wbc->nr_to_write -= nr_written;
-		return 1;
-	}
-
 	return 0;
 }
 
@@ -1382,6 +1305,7 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
 
 	bio_ctrl->end_io_func = end_bio_extent_writepage;
 	while (cur <= end) {
+		u32 len = end - cur + 1;
 		u64 disk_bytenr;
 		u64 em_end;
 		u64 dirty_range_start = cur;
@@ -1389,8 +1313,8 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
 		u32 iosize;
 
 		if (cur >= i_size) {
-			btrfs_writepage_endio_finish_ordered(inode, page, cur,
-							     end, true);
+			btrfs_mark_ordered_io_finished(inode, page, cur, len,
+						       true);
 			/*
 			 * This range is beyond i_size, thus we don't need to
 			 * bother writing back.
@@ -1399,7 +1323,7 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
 			 * writeback the sectors with subpage dirty bits,
 			 * causing writeback without ordered extent.
 			 */
-			btrfs_page_clear_dirty(fs_info, page, cur, end + 1 - cur);
+			btrfs_page_clear_dirty(fs_info, page, cur, len);
 			break;
 		}
 
@@ -1410,7 +1334,7 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
 			continue;
 		}
 
-		em = btrfs_get_extent(inode, NULL, 0, cur, end - cur + 1);
+		em = btrfs_get_extent(inode, NULL, 0, cur, len);
 		if (IS_ERR(em)) {
 			ret = PTR_ERR_OR_ZERO(em);
 			goto out_error;
@@ -1486,7 +1410,6 @@ static int __extent_writepage(struct page *page, struct btrfs_bio_ctrl *bio_ctrl
 	struct folio *folio = page_folio(page);
 	struct inode *inode = page->mapping->host;
 	const u64 page_start = page_offset(page);
-	const u64 page_end = page_start + PAGE_SIZE - 1;
 	int ret;
 	int nr = 0;
 	size_t pg_offset;
@@ -1530,8 +1453,13 @@ done:
 		set_page_writeback(page);
 		end_page_writeback(page);
 	}
-	if (ret)
-		end_extent_writepage(page, ret, page_start, page_end);
+	if (ret) {
+		btrfs_mark_ordered_io_finished(BTRFS_I(inode), page, page_start,
+					       PAGE_SIZE, !ret);
+		btrfs_page_clear_uptodate(btrfs_sb(inode->i_sb), page,
+					  page_start, PAGE_SIZE);
+		mapping_set_error(page->mapping, ret);
+	}
 	unlock_page(page);
 	ASSERT(ret <= 0);
 	return ret;
@@ -1877,11 +1805,10 @@ static int submit_eb_subpage(struct page *page, struct writeback_control *wbc)
  * previous call.
  * Return <0 for fatal error.
  */
-static int submit_eb_page(struct page *page, struct writeback_control *wbc,
-			  struct extent_buffer **eb_context)
+static int submit_eb_page(struct page *page, struct btrfs_eb_write_context *ctx)
 {
+	struct writeback_control *wbc = ctx->wbc;
 	struct address_space *mapping = page->mapping;
-	struct btrfs_block_group *cache = NULL;
 	struct extent_buffer *eb;
 	int ret;
 
@@ -1908,7 +1835,7 @@ static int submit_eb_page(struct page *page, struct writeback_control *wbc,
 		return 0;
 	}
 
-	if (eb == *eb_context) {
+	if (eb == ctx->eb) {
 		spin_unlock(&mapping->private_lock);
 		return 0;
 	}
@@ -1917,34 +1844,25 @@ static int submit_eb_page(struct page *page, struct writeback_control *wbc,
 	if (!ret)
 		return 0;
 
-	if (!btrfs_check_meta_write_pointer(eb->fs_info, eb, &cache)) {
-		/*
-		 * If for_sync, this hole will be filled with
-		 * trasnsaction commit.
-		 */
-		if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync)
-			ret = -EAGAIN;
-		else
+	ctx->eb = eb;
+
+	ret = btrfs_check_meta_write_pointer(eb->fs_info, ctx);
+	if (ret) {
+		if (ret == -EBUSY)
 			ret = 0;
 		free_extent_buffer(eb);
 		return ret;
 	}
 
-	*eb_context = eb;
-
 	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 0;
 	}
-	if (cache) {
-		/*
-		 * Implies write in zoned mode. Mark the last eb in a block group.
-		 */
-		btrfs_schedule_zone_finish_bg(cache, eb);
-		btrfs_put_block_group(cache);
+	/* Implies write in zoned mode. */
+	if (ctx->zoned_bg) {
+		/* Mark the last eb in the block group. */
+		btrfs_schedule_zone_finish_bg(ctx->zoned_bg, eb);
+		ctx->zoned_bg->meta_write_pointer += eb->len;
 	}
 	write_one_eb(eb, wbc);
 	free_extent_buffer(eb);
@@ -1954,7 +1872,7 @@ static int submit_eb_page(struct page *page, struct writeback_control *wbc,
 int btree_write_cache_pages(struct address_space *mapping,
 				   struct writeback_control *wbc)
 {
-	struct extent_buffer *eb_context = NULL;
+	struct btrfs_eb_write_context ctx = { .wbc = wbc };
 	struct btrfs_fs_info *fs_info = BTRFS_I(mapping->host)->root->fs_info;
 	int ret = 0;
 	int done = 0;
@@ -1996,7 +1914,7 @@ retry:
 		for (i = 0; i < nr_folios; i++) {
 			struct folio *folio = fbatch.folios[i];
 
-			ret = submit_eb_page(&folio->page, wbc, &eb_context);
+			ret = submit_eb_page(&folio->page, &ctx);
 			if (ret == 0)
 				continue;
 			if (ret < 0) {
@@ -2057,6 +1975,9 @@ retry:
 		ret = 0;
 	if (!ret && BTRFS_FS_ERROR(fs_info))
 		ret = -EROFS;
+
+	if (ctx.zoned_bg)
+		btrfs_put_block_group(ctx.zoned_bg);
 	btrfs_zoned_meta_io_unlock(fs_info);
 	return ret;
 }
@@ -2150,7 +2071,7 @@ retry:
 		for (i = 0; i < nr_folios; i++) {
 			struct folio *folio = fbatch.folios[i];
 
-			done_index = folio->index + folio_nr_pages(folio);
+			done_index = folio_next_index(folio);
 			/*
 			 * At this point we hold neither the i_pages lock nor
 			 * the page lock: the page may be truncated or
@@ -2233,11 +2154,11 @@ retry:
  * already been ran (aka, ordered extent inserted) and all pages are still
  * locked.
  */
-int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
-			      struct writeback_control *wbc)
+void extent_write_locked_range(struct inode *inode, struct page *locked_page,
+			       u64 start, u64 end, struct writeback_control *wbc,
+			       bool pages_dirty)
 {
 	bool found_error = false;
-	int first_error = 0;
 	int ret = 0;
 	struct address_space *mapping = inode->i_mapping;
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
@@ -2256,18 +2177,16 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
 
 	while (cur <= end) {
 		u64 cur_end = min(round_down(cur, PAGE_SIZE) + PAGE_SIZE - 1, end);
+		u32 cur_len = cur_end + 1 - cur;
 		struct page *page;
 		int nr = 0;
 
 		page = find_get_page(mapping, cur >> PAGE_SHIFT);
-		/*
-		 * All pages in the range are locked since
-		 * btrfs_run_delalloc_range(), thus there is no way to clear
-		 * the page dirty flag.
-		 */
 		ASSERT(PageLocked(page));
-		ASSERT(PageDirty(page));
-		clear_page_dirty_for_io(page);
+		if (pages_dirty && page != locked_page) {
+			ASSERT(PageDirty(page));
+			clear_page_dirty_for_io(page);
+		}
 
 		ret = __extent_writepage_io(BTRFS_I(inode), page, &bio_ctrl,
 					    i_size, &nr);
@@ -2279,23 +2198,21 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
 			set_page_writeback(page);
 			end_page_writeback(page);
 		}
-		if (ret)
-			end_extent_writepage(page, ret, cur, cur_end);
-		btrfs_page_unlock_writer(fs_info, page, cur, cur_end + 1 - cur);
-		if (ret < 0) {
-			found_error = true;
-			first_error = ret;
+		if (ret) {
+			btrfs_mark_ordered_io_finished(BTRFS_I(inode), page,
+						       cur, cur_len, !ret);
+			btrfs_page_clear_uptodate(fs_info, page, cur, cur_len);
+			mapping_set_error(page->mapping, ret);
 		}
+		btrfs_page_unlock_writer(fs_info, page, cur, cur_len);
+		if (ret < 0)
+			found_error = true;
 next_page:
 		put_page(page);
 		cur = cur_end + 1;
 	}
 
 	submit_write_bio(&bio_ctrl, found_error ? ret : 0);
-
-	if (found_error)
-		return first_error;
-	return ret;
 }
 
 int extent_writepages(struct address_space *mapping,
@@ -3315,8 +3232,8 @@ struct extent_buffer *btrfs_clone_extent_buffer(const struct extent_buffer *src)
 			return NULL;
 		}
 		WARN_ON(PageDirty(p));
-		copy_page(page_address(p), page_address(src->pages[i]));
 	}
+	copy_extent_buffer_full(new, src);
 	set_extent_buffer_uptodate(new);
 
 	return new;
@@ -3559,6 +3476,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	struct extent_buffer *exists = NULL;
 	struct page *p;
 	struct address_space *mapping = fs_info->btree_inode->i_mapping;
+	struct btrfs_subpage *prealloc = NULL;
 	u64 lockdep_owner = owner_root;
 	int uptodate = 1;
 	int ret;
@@ -3595,36 +3513,30 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	btrfs_set_buffer_lockdep_class(lockdep_owner, eb, level);
 
 	num_pages = num_extent_pages(eb);
-	for (i = 0; i < num_pages; i++, index++) {
-		struct btrfs_subpage *prealloc = NULL;
 
+	/*
+	 * Preallocate page->private for subpage case, so that we won't
+	 * allocate memory with private_lock nor page lock hold.
+	 *
+	 * The memory will be freed by attach_extent_buffer_page() or freed
+	 * manually if we exit earlier.
+	 */
+	if (fs_info->nodesize < PAGE_SIZE) {
+		prealloc = btrfs_alloc_subpage(fs_info, BTRFS_SUBPAGE_METADATA);
+		if (IS_ERR(prealloc)) {
+			exists = ERR_CAST(prealloc);
+			goto free_eb;
+		}
+	}
+
+	for (i = 0; i < num_pages; i++, index++) {
 		p = find_or_create_page(mapping, index, GFP_NOFS|__GFP_NOFAIL);
 		if (!p) {
 			exists = ERR_PTR(-ENOMEM);
+			btrfs_free_subpage(prealloc);
 			goto free_eb;
 		}
 
-		/*
-		 * Preallocate page->private for subpage case, so that we won't
-		 * allocate memory with private_lock hold.  The memory will be
-		 * freed by attach_extent_buffer_page() or freed manually if
-		 * we exit earlier.
-		 *
-		 * Although we have ensured one subpage eb can only have one
-		 * page, but it may change in the future for 16K page size
-		 * support, so we still preallocate the memory in the loop.
-		 */
-		if (fs_info->nodesize < PAGE_SIZE) {
-			prealloc = btrfs_alloc_subpage(fs_info, BTRFS_SUBPAGE_METADATA);
-			if (IS_ERR(prealloc)) {
-				ret = PTR_ERR(prealloc);
-				unlock_page(p);
-				put_page(p);
-				exists = ERR_PTR(ret);
-				goto free_eb;
-			}
-		}
-
 		spin_lock(&mapping->private_lock);
 		exists = grab_extent_buffer(fs_info, p);
 		if (exists) {
@@ -4210,30 +4122,9 @@ static void assert_eb_page_uptodate(const struct extent_buffer *eb,
 	}
 }
 
-void write_extent_buffer_chunk_tree_uuid(const struct extent_buffer *eb,
-		const void *srcv)
-{
-	char *kaddr;
-
-	assert_eb_page_uptodate(eb, eb->pages[0]);
-	kaddr = page_address(eb->pages[0]) +
-		get_eb_offset_in_page(eb, offsetof(struct btrfs_header,
-						   chunk_tree_uuid));
-	memcpy(kaddr, srcv, BTRFS_FSID_SIZE);
-}
-
-void write_extent_buffer_fsid(const struct extent_buffer *eb, const void *srcv)
-{
-	char *kaddr;
-
-	assert_eb_page_uptodate(eb, eb->pages[0]);
-	kaddr = page_address(eb->pages[0]) +
-		get_eb_offset_in_page(eb, offsetof(struct btrfs_header, fsid));
-	memcpy(kaddr, srcv, BTRFS_FSID_SIZE);
-}
-
-void write_extent_buffer(const struct extent_buffer *eb, const void *srcv,
-			 unsigned long start, unsigned long len)
+static void __write_extent_buffer(const struct extent_buffer *eb,
+				  const void *srcv, unsigned long start,
+				  unsigned long len, bool use_memmove)
 {
 	size_t cur;
 	size_t offset;
@@ -4241,6 +4132,8 @@ void write_extent_buffer(const struct extent_buffer *eb, const void *srcv,
 	char *kaddr;
 	char *src = (char *)srcv;
 	unsigned long i = get_eb_page_index(start);
+	/* For unmapped (dummy) ebs, no need to check their uptodate status. */
+	const bool check_uptodate = !test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags);
 
 	WARN_ON(test_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags));
 
@@ -4251,11 +4144,15 @@ void write_extent_buffer(const struct extent_buffer *eb, const void *srcv,
 
 	while (len > 0) {
 		page = eb->pages[i];
-		assert_eb_page_uptodate(eb, page);
+		if (check_uptodate)
+			assert_eb_page_uptodate(eb, page);
 
 		cur = min(len, PAGE_SIZE - offset);
 		kaddr = page_address(page);
-		memcpy(kaddr + offset, src, cur);
+		if (use_memmove)
+			memmove(kaddr + offset, src, cur);
+		else
+			memcpy(kaddr + offset, src, cur);
 
 		src += cur;
 		len -= cur;
@@ -4264,55 +4161,54 @@ void write_extent_buffer(const struct extent_buffer *eb, const void *srcv,
 	}
 }
 
-void memzero_extent_buffer(const struct extent_buffer *eb, unsigned long start,
-		unsigned long len)
+void write_extent_buffer(const struct extent_buffer *eb, const void *srcv,
+			 unsigned long start, unsigned long len)
 {
-	size_t cur;
-	size_t offset;
-	struct page *page;
-	char *kaddr;
-	unsigned long i = get_eb_page_index(start);
+	return __write_extent_buffer(eb, srcv, start, len, false);
+}
 
-	if (check_eb_range(eb, start, len))
-		return;
+static void memset_extent_buffer(const struct extent_buffer *eb, int c,
+				 unsigned long start, unsigned long len)
+{
+	unsigned long cur = start;
 
-	offset = get_eb_offset_in_page(eb, start);
+	while (cur < start + len) {
+		unsigned long index = get_eb_page_index(cur);
+		unsigned int offset = get_eb_offset_in_page(eb, cur);
+		unsigned int cur_len = min(start + len - cur, PAGE_SIZE - offset);
+		struct page *page = eb->pages[index];
 
-	while (len > 0) {
-		page = eb->pages[i];
 		assert_eb_page_uptodate(eb, page);
+		memset(page_address(page) + offset, c, cur_len);
 
-		cur = min(len, PAGE_SIZE - offset);
-		kaddr = page_address(page);
-		memset(kaddr + offset, 0, cur);
-
-		len -= cur;
-		offset = 0;
-		i++;
+		cur += cur_len;
 	}
 }
 
+void memzero_extent_buffer(const struct extent_buffer *eb, unsigned long start,
+			   unsigned long len)
+{
+	if (check_eb_range(eb, start, len))
+		return;
+	return memset_extent_buffer(eb, 0, start, len);
+}
+
 void copy_extent_buffer_full(const struct extent_buffer *dst,
 			     const struct extent_buffer *src)
 {
-	int i;
-	int num_pages;
+	unsigned long cur = 0;
 
 	ASSERT(dst->len == src->len);
 
-	if (dst->fs_info->nodesize >= PAGE_SIZE) {
-		num_pages = num_extent_pages(dst);
-		for (i = 0; i < num_pages; i++)
-			copy_page(page_address(dst->pages[i]),
-				  page_address(src->pages[i]));
-	} else {
-		size_t src_offset = get_eb_offset_in_page(src, 0);
-		size_t dst_offset = get_eb_offset_in_page(dst, 0);
+	while (cur < src->len) {
+		unsigned long index = get_eb_page_index(cur);
+		unsigned long offset = get_eb_offset_in_page(src, cur);
+		unsigned long cur_len = min(src->len, PAGE_SIZE - offset);
+		void *addr = page_address(src->pages[index]) + offset;
+
+		write_extent_buffer(dst, addr, cur, cur_len);
 
-		ASSERT(src->fs_info->nodesize < PAGE_SIZE);
-		memcpy(page_address(dst->pages[0]) + dst_offset,
-		       page_address(src->pages[0]) + src_offset,
-		       src->len);
+		cur += cur_len;
 	}
 }
 
@@ -4406,6 +4302,15 @@ int extent_buffer_test_bit(const struct extent_buffer *eb, unsigned long start,
 	return 1U & (kaddr[offset] >> (nr & (BITS_PER_BYTE - 1)));
 }
 
+static u8 *extent_buffer_get_byte(const struct extent_buffer *eb, unsigned long bytenr)
+{
+	unsigned long index = get_eb_page_index(bytenr);
+
+	if (check_eb_range(eb, bytenr, 1))
+		return NULL;
+	return page_address(eb->pages[index]) + get_eb_offset_in_page(eb, bytenr);
+}
+
 /*
  * Set an area of a bitmap to 1.
  *
@@ -4417,35 +4322,28 @@ int extent_buffer_test_bit(const struct extent_buffer *eb, unsigned long start,
 void extent_buffer_bitmap_set(const struct extent_buffer *eb, unsigned long start,
 			      unsigned long pos, unsigned long len)
 {
+	unsigned int first_byte = start + BIT_BYTE(pos);
+	unsigned int last_byte = start + BIT_BYTE(pos + len - 1);
+	const bool same_byte = (first_byte == last_byte);
+	u8 mask = BITMAP_FIRST_BYTE_MASK(pos);
 	u8 *kaddr;
-	struct page *page;
-	unsigned long i;
-	size_t offset;
-	const unsigned int size = pos + len;
-	int bits_to_set = BITS_PER_BYTE - (pos % BITS_PER_BYTE);
-	u8 mask_to_set = BITMAP_FIRST_BYTE_MASK(pos);
 
-	eb_bitmap_offset(eb, start, pos, &i, &offset);
-	page = eb->pages[i];
-	assert_eb_page_uptodate(eb, page);
-	kaddr = page_address(page);
+	if (same_byte)
+		mask &= BITMAP_LAST_BYTE_MASK(pos + len);
 
-	while (len >= bits_to_set) {
-		kaddr[offset] |= mask_to_set;
-		len -= bits_to_set;
-		bits_to_set = BITS_PER_BYTE;
-		mask_to_set = ~0;
-		if (++offset >= PAGE_SIZE && len > 0) {
-			offset = 0;
-			page = eb->pages[++i];
-			assert_eb_page_uptodate(eb, page);
-			kaddr = page_address(page);
-		}
-	}
-	if (len) {
-		mask_to_set &= BITMAP_LAST_BYTE_MASK(size);
-		kaddr[offset] |= mask_to_set;
-	}
+	/* Handle the first byte. */
+	kaddr = extent_buffer_get_byte(eb, first_byte);
+	*kaddr |= mask;
+	if (same_byte)
+		return;
+
+	/* Handle the byte aligned part. */
+	ASSERT(first_byte + 1 <= last_byte);
+	memset_extent_buffer(eb, 0xff, first_byte + 1, last_byte - first_byte - 1);
+
+	/* Handle the last byte. */
+	kaddr = extent_buffer_get_byte(eb, last_byte);
+	*kaddr |= BITMAP_LAST_BYTE_MASK(pos + len);
 }
 
 
@@ -4461,35 +4359,28 @@ void extent_buffer_bitmap_clear(const struct extent_buffer *eb,
 				unsigned long start, unsigned long pos,
 				unsigned long len)
 {
+	unsigned int first_byte = start + BIT_BYTE(pos);
+	unsigned int last_byte = start + BIT_BYTE(pos + len - 1);
+	const bool same_byte = (first_byte == last_byte);
+	u8 mask = BITMAP_FIRST_BYTE_MASK(pos);
 	u8 *kaddr;
-	struct page *page;
-	unsigned long i;
-	size_t offset;
-	const unsigned int size = pos + len;
-	int bits_to_clear = BITS_PER_BYTE - (pos % BITS_PER_BYTE);
-	u8 mask_to_clear = BITMAP_FIRST_BYTE_MASK(pos);
 
-	eb_bitmap_offset(eb, start, pos, &i, &offset);
-	page = eb->pages[i];
-	assert_eb_page_uptodate(eb, page);
-	kaddr = page_address(page);
+	if (same_byte)
+		mask &= BITMAP_LAST_BYTE_MASK(pos + len);
 
-	while (len >= bits_to_clear) {
-		kaddr[offset] &= ~mask_to_clear;
-		len -= bits_to_clear;
-		bits_to_clear = BITS_PER_BYTE;
-		mask_to_clear = ~0;
-		if (++offset >= PAGE_SIZE && len > 0) {
-			offset = 0;
-			page = eb->pages[++i];
-			assert_eb_page_uptodate(eb, page);
-			kaddr = page_address(page);
-		}
-	}
-	if (len) {
-		mask_to_clear &= BITMAP_LAST_BYTE_MASK(size);
-		kaddr[offset] &= ~mask_to_clear;
-	}
+	/* Handle the first byte. */
+	kaddr = extent_buffer_get_byte(eb, first_byte);
+	*kaddr &= ~mask;
+	if (same_byte)
+		return;
+
+	/* Handle the byte aligned part. */
+	ASSERT(first_byte + 1 <= last_byte);
+	memset_extent_buffer(eb, 0, first_byte + 1, last_byte - first_byte - 1);
+
+	/* Handle the last byte. */
+	kaddr = extent_buffer_get_byte(eb, last_byte);
+	*kaddr &= ~BITMAP_LAST_BYTE_MASK(pos + len);
 }
 
 static inline bool areas_overlap(unsigned long src, unsigned long dst, unsigned long len)
@@ -4498,60 +4389,29 @@ static inline bool areas_overlap(unsigned long src, unsigned long dst, unsigned
 	return distance < len;
 }
 
-static void copy_pages(struct page *dst_page, struct page *src_page,
-		       unsigned long dst_off, unsigned long src_off,
-		       unsigned long len)
-{
-	char *dst_kaddr = page_address(dst_page);
-	char *src_kaddr;
-	int must_memmove = 0;
-
-	if (dst_page != src_page) {
-		src_kaddr = page_address(src_page);
-	} else {
-		src_kaddr = dst_kaddr;
-		if (areas_overlap(src_off, dst_off, len))
-			must_memmove = 1;
-	}
-
-	if (must_memmove)
-		memmove(dst_kaddr + dst_off, src_kaddr + src_off, len);
-	else
-		memcpy(dst_kaddr + dst_off, src_kaddr + src_off, len);
-}
-
 void memcpy_extent_buffer(const struct extent_buffer *dst,
 			  unsigned long dst_offset, unsigned long src_offset,
 			  unsigned long len)
 {
-	size_t cur;
-	size_t dst_off_in_page;
-	size_t src_off_in_page;
-	unsigned long dst_i;
-	unsigned long src_i;
+	unsigned long cur_off = 0;
 
 	if (check_eb_range(dst, dst_offset, len) ||
 	    check_eb_range(dst, src_offset, len))
 		return;
 
-	while (len > 0) {
-		dst_off_in_page = get_eb_offset_in_page(dst, dst_offset);
-		src_off_in_page = get_eb_offset_in_page(dst, src_offset);
-
-		dst_i = get_eb_page_index(dst_offset);
-		src_i = get_eb_page_index(src_offset);
-
-		cur = min(len, (unsigned long)(PAGE_SIZE -
-					       src_off_in_page));
-		cur = min_t(unsigned long, cur,
-			(unsigned long)(PAGE_SIZE - dst_off_in_page));
-
-		copy_pages(dst->pages[dst_i], dst->pages[src_i],
-			   dst_off_in_page, src_off_in_page, cur);
-
-		src_offset += cur;
-		dst_offset += cur;
-		len -= cur;
+	while (cur_off < len) {
+		unsigned long cur_src = cur_off + src_offset;
+		unsigned long pg_index = get_eb_page_index(cur_src);
+		unsigned long pg_off = get_eb_offset_in_page(dst, cur_src);
+		unsigned long cur_len = min(src_offset + len - cur_src,
+					    PAGE_SIZE - pg_off);
+		void *src_addr = page_address(dst->pages[pg_index]) + pg_off;
+		const bool use_memmove = areas_overlap(src_offset + cur_off,
+						       dst_offset + cur_off, cur_len);
+
+		__write_extent_buffer(dst, src_addr, dst_offset + cur_off, cur_len,
+				      use_memmove);
+		cur_off += cur_len;
 	}
 }
 
@@ -4559,23 +4419,26 @@ void memmove_extent_buffer(const struct extent_buffer *dst,
 			   unsigned long dst_offset, unsigned long src_offset,
 			   unsigned long len)
 {
-	size_t cur;
-	size_t dst_off_in_page;
-	size_t src_off_in_page;
 	unsigned long dst_end = dst_offset + len - 1;
 	unsigned long src_end = src_offset + len - 1;
-	unsigned long dst_i;
-	unsigned long src_i;
 
 	if (check_eb_range(dst, dst_offset, len) ||
 	    check_eb_range(dst, src_offset, len))
 		return;
+
 	if (dst_offset < src_offset) {
 		memcpy_extent_buffer(dst, dst_offset, src_offset, len);
 		return;
 	}
+
 	while (len > 0) {
-		dst_i = get_eb_page_index(dst_end);
+		unsigned long src_i;
+		size_t cur;
+		size_t dst_off_in_page;
+		size_t src_off_in_page;
+		void *src_addr;
+		bool use_memmove;
+
 		src_i = get_eb_page_index(src_end);
 
 		dst_off_in_page = get_eb_offset_in_page(dst, dst_end);
@@ -4583,9 +4446,14 @@ void memmove_extent_buffer(const struct extent_buffer *dst,
 
 		cur = min_t(unsigned long, len, src_off_in_page + 1);
 		cur = min(cur, dst_off_in_page + 1);
-		copy_pages(dst->pages[dst_i], dst->pages[src_i],
-			   dst_off_in_page - cur + 1,
-			   src_off_in_page - cur + 1, cur);
+
+		src_addr = page_address(dst->pages[src_i]) + src_off_in_page -
+					cur + 1;
+		use_memmove = areas_overlap(src_end - cur + 1, dst_end - cur + 1,
+					    cur);
+
+		__write_extent_buffer(dst, src_addr, dst_end - cur + 1, cur,
+				      use_memmove);
 
 		dst_end -= cur;
 		src_end -= cur;