mm: buffered write cleanup

Quite a bit of code is used in maintaining these "cached pages" that are
probably pretty unlikely to get used. It would require a narrow race where
the page is inserted concurrently while this process is allocating a page
in order to create the spare page. Then a multi-page write into an uncached
part of the file, to make use of it.

Next, the buffered write path (and others) uses its own LRU pagevec when it
should be just using the per-CPU LRU pagevec (which will cut down on both data
and code size cacheline footprint). Also, these private LRU pagevecs are
emptied after just a very short time, in contrast with the per-CPU pagevecs
that are persistent. Net result: 7.3 times fewer lru_lock acquisitions required
to add the pages to pagecache for a bulk write (in 4K chunks).

[this gets rid of some cond_resched() calls in readahead.c and mpage.c due
 to clashes in -mm. What put them there, and why? ]

Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 8 insertions, 16 deletions

diff --git a/mm/readahead.c b/mm/readahead.c
index c5c8981469e7..229788884010 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -58,28 +58,25 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages,
 			int (*filler)(void *, struct page *), void *data)
 {
 	struct page *page;
-	struct pagevec lru_pvec;
 	int ret = 0;
 
-	pagevec_init(&lru_pvec, 0);
-
 	while (!list_empty(pages)) {
 		page = list_to_page(pages);
 		list_del(&page->lru);
-		if (add_to_page_cache(page, mapping, page->index, GFP_KERNEL)) {
+		if (add_to_page_cache_lru(page, mapping,
+					page->index, GFP_KERNEL)) {
 			page_cache_release(page);
 			continue;
 		}
+		page_cache_release(page);
+
 		ret = filler(data, page);
-		if (!pagevec_add(&lru_pvec, page))
-			__pagevec_lru_add(&lru_pvec);
-		if (ret) {
+		if (unlikely(ret)) {
 			put_pages_list(pages);
 			break;
 		}
 		task_io_account_read(PAGE_CACHE_SIZE);
 	}
-	pagevec_lru_add(&lru_pvec);
 	return ret;
 }
 
@@ -89,7 +86,6 @@ static int read_pages(struct address_space *mapping, struct file *filp,
 		struct list_head *pages, unsigned nr_pages)
 {
 	unsigned page_idx;
-	struct pagevec lru_pvec;
 	int ret;
 
 	if (mapping->a_ops->readpages) {
@@ -99,19 +95,15 @@ static int read_pages(struct address_space *mapping, struct file *filp,
 		goto out;
 	}
 
-	pagevec_init(&lru_pvec, 0);
 	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
 		struct page *page = list_to_page(pages);
 		list_del(&page->lru);
-		if (!add_to_page_cache(page, mapping,
+		if (!add_to_page_cache_lru(page, mapping,
 					page->index, GFP_KERNEL)) {
 			mapping->a_ops->readpage(filp, page);
-			if (!pagevec_add(&lru_pvec, page))
-				__pagevec_lru_add(&lru_pvec);
-		} else
-			page_cache_release(page);
+		}
+		page_cache_release(page);
 	}
-	pagevec_lru_add(&lru_pvec);
 	ret = 0;
 out:
 	return ret;