btrfs: Refactor main loop in extent_readpages

extent_readpages processes all pages in the readlist in batches of 16,
this is implemented by a single for loop but thanks to an if condition
the loop does 2 things based on whether we've filled the batch or not.
Additionally due to the structure of the code there is an additional
check which deals with partial batches.

Streamline all of this by explicitly using two loops. The outter one is
used to process all pages while the inner one just fills in the batch
of 16 (currently). Due to this new structure the code guarantees that
all pages are processed in the loop hence the code to deal with any
leftovers is eliminated.

This also enable the compiler to inline __extent_readpages:

	./scripts/bloat-o-meter fs/btrfs/extent_io.o extent_io.for

	add/remove: 0/1 grow/shrink: 1/0 up/down: 660/-820 (-160)
	Function                                     old     new   delta
	extent_readpages                             476    1136    +660
	__extent_readpages                           820       -    -820
	Total: Before=44315, After=44155, chg -0.36%
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/extent_io.c

@@ -4094,42 +4094,36 @@ int extent_readpages(struct address_space *mapping, struct list_head *pages,
 		     unsigned nr_pages)
 {
 	struct bio *bio = NULL;
-	unsigned page_idx;
 	unsigned long bio_flags = 0;
 	struct page *pagepool[16];
-	struct page *page;
 	struct extent_map *em_cached = NULL;
 	struct extent_io_tree *tree = &BTRFS_I(mapping->host)->io_tree;
 	int nr = 0;
 	u64 prev_em_start = (u64)-1;
 
-	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
-		page = list_entry(pages->prev, struct page, lru);
+	while (!list_empty(pages)) {
+		for (nr = 0; nr < ARRAY_SIZE(pagepool) && !list_empty(pages);) {
+			struct page *page = list_entry(pages->prev,
+						       struct page, lru);
 
-		prefetchw(&page->flags);
-		list_del(&page->lru);
-		if (add_to_page_cache_lru(page, mapping,
-					page->index,
-					readahead_gfp_mask(mapping))) {
-			put_page(page);
-			continue;
+			prefetchw(&page->flags);
+			list_del(&page->lru);
+			if (add_to_page_cache_lru(page, mapping, page->index,
+						readahead_gfp_mask(mapping))) {
+				put_page(page);
+				continue;
+			}
+
+			pagepool[nr++] = page;
 		}
 
-		pagepool[nr++] = page;
-		if (nr < ARRAY_SIZE(pagepool))
-			continue;
 		__extent_readpages(tree, pagepool, nr, &em_cached, &bio,
-				&bio_flags, &prev_em_start);
-		nr = 0;
+				   &bio_flags, &prev_em_start);
 	}
-	if (nr)
-		__extent_readpages(tree, pagepool, nr, &em_cached, &bio,
-				&bio_flags, &prev_em_start);
 
 	if (em_cached)
 		free_extent_map(em_cached);
 
-	BUG_ON(!list_empty(pages));
 	if (bio)
 		return submit_one_bio(bio, 0, bio_flags);
 	return 0;