mm: put readahead pages in cache earlier

When populating the page cache for readahead, mappings that use
->readpages must populate the page cache themselves as the pages are
passed on a linked list which would normally be used for the page
cache's LRU.  For mappings that use ->readpage or the upcoming
->readahead method, we can put the pages into the page cache as soon as
they're allocated, which solves a race between readahead and direct IO.
It also lets us remove the gfp argument from read_pages().

Use the new readahead_page() API to implement the repeated calls to
->readpage(), just like most filesystems will.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: William Kucharski <william.kucharski@oracle.com>
Cc: Chao Yu <yuchao0@huawei.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Darrick J. Wong <darrick.wong@oracle.com>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Eric Biggers <ebiggers@google.com>
Cc: Gao Xiang <gaoxiang25@huawei.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Cc: Miklos Szeredi <mszeredi@redhat.com>
Link: http://lkml.kernel.org/r/20200414150233.24495-11-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/readahead.c

@@ -114,14 +114,14 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages,
 EXPORT_SYMBOL(read_cache_pages);
 
 static void read_pages(struct readahead_control *rac, struct list_head *pages,
-		gfp_t gfp)
+		bool skip_page)
 {
 	const struct address_space_operations *aops = rac->mapping->a_ops;
+	struct page *page;
 	struct blk_plug plug;
-	unsigned page_idx;
 
 	if (!readahead_count(rac))
-		return;
+		goto out;
 
 	blk_start_plug(&plug);
 
@@ -130,23 +130,23 @@ static void read_pages(struct readahead_control *rac, struct list_head *pages,
 				readahead_count(rac));
 		/* Clean up the remaining pages */
 		put_pages_list(pages);
-		goto out;
+		rac->_index += rac->_nr_pages;
-	}
+		rac->_nr_pages = 0;
-
+	} else {
-	for (page_idx = 0; page_idx < readahead_count(rac); page_idx++) {
+		while ((page = readahead_page(rac))) {
-		struct page *page = lru_to_page(pages);
-		list_del(&page->lru);
-		if (!add_to_page_cache_lru(page, rac->mapping, page->index,
-				gfp))
 			aops->readpage(rac->file, page);
-		put_page(page);
+			put_page(page);
+		}
 	}
 
-out:
 	blk_finish_plug(&plug);
 
 	BUG_ON(!list_empty(pages));
-	rac->_nr_pages = 0;
+	BUG_ON(readahead_count(rac));
+
+out:
+	if (skip_page)
+		rac->_index++;
 }
 
 /*
@@ -168,6 +168,7 @@ void __do_page_cache_readahead(struct address_space *mapping,
 	struct readahead_control rac = {
 		.mapping = mapping,
 		.file = filp,
+		._index = index,
 	};
 	unsigned long i;
 
@@ -183,6 +184,8 @@ void __do_page_cache_readahead(struct address_space *mapping,
 		if (index + i > end_index)
 			break;
 
+		BUG_ON(index + i != rac._index + rac._nr_pages);
+
 		page = xa_load(&mapping->i_pages, index + i);
 		if (page && !xa_is_value(page)) {
 			/*
@@ -190,15 +193,22 @@ void __do_page_cache_readahead(struct address_space *mapping,
 			 * contiguous pages before continuing with the next
 			 * batch.
 			 */
-			read_pages(&rac, &page_pool, gfp_mask);
+			read_pages(&rac, &page_pool, true);
 			continue;
 		}
 
 		page = __page_cache_alloc(gfp_mask);
 		if (!page)
 			break;
-		page->index = index + i;
+		if (mapping->a_ops->readpages) {
-		list_add(&page->lru, &page_pool);
+			page->index = index + i;
+			list_add(&page->lru, &page_pool);
+		} else if (add_to_page_cache_lru(page, mapping, index + i,
+					gfp_mask) < 0) {
+			put_page(page);
+			read_pages(&rac, &page_pool, true);
+			continue;
+		}
 		if (i == nr_to_read - lookahead_size)
 			SetPageReadahead(page);
 		rac._nr_pages++;
@@ -209,7 +219,7 @@ void __do_page_cache_readahead(struct address_space *mapping,
 	 * uptodate then the caller will launch readpage again, and
 	 * will then handle the error.
 	 */
-	read_pages(&rac, &page_pool, gfp_mask);
+	read_pages(&rac, &page_pool, false);
 }
 
 /*