mpage: mpage_readpages() should submit IO as read-ahead

a_ops->readpages() is only ever used for read-ahead, yet we don't flag
the IO being submitted as such.  Fix that up.  Any file system that uses
mpage_readpages() as its ->readpages() implementation will now get this
right.

Since we're passing in whether the IO is read-ahead or not, we don't
need to pass in the 'gfp' separately, as it is dependent on the IO being
read-ahead.  Kill off that member.

Add some documentation notes on ->readpages() being purely for
read-ahead.

Link: http://lkml.kernel.org/r/20180621010725.17813-3-axboe@kernel.dk
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Chris Mason <clm@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 28 insertions, 10 deletions

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 8f931d699287..b7c9b58acf3e 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1421,6 +1421,11 @@ out:
 /*
  * This function was originally taken from fs/mpage.c, and customized for f2fs.
  * Major change was from block_size == page_size in f2fs by default.
+ *
+ * Note that the aops->readpages() function is ONLY used for read-ahead. If
+ * this function ever deviates from doing just read-ahead, it should either
+ * use ->readpage() or do the necessary surgery to decouple ->readpages()
+ * readom read-ahead.
  */
 static int f2fs_mpage_readpages(struct address_space *mapping,
 			struct list_head *pages, struct page *page,
diff --git a/fs/mpage.c b/fs/mpage.c
index 6dc90e456abf..c820dc9bebab 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -137,11 +137,11 @@ struct mpage_readpage_args {
 	struct bio *bio;
 	struct page *page;
 	unsigned int nr_pages;
+	bool is_readahead;
 	sector_t last_block_in_bio;
 	struct buffer_head map_bh;
 	unsigned long first_logical_block;
 	get_block_t *get_block;
-	gfp_t gfp;
 };
 
 /*
@@ -170,8 +170,18 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args)
 	struct block_device *bdev = NULL;
 	int length;
 	int fully_mapped = 1;
+	int op_flags;
 	unsigned nblocks;
 	unsigned relative_block;
+	gfp_t gfp;
+
+	if (args->is_readahead) {
+		op_flags = REQ_RAHEAD;
+		gfp = readahead_gfp_mask(page->mapping);
+	} else {
+		op_flags = 0;
+		gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL);
+	}
 
 	if (page_has_buffers(page))
 		goto confused;
@@ -284,7 +294,7 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args)
 	 * This page will go to BIO.  Do we need to send this BIO off first?
 	 */
 	if (args->bio && (args->last_block_in_bio != blocks[0] - 1))
-		args->bio = mpage_bio_submit(REQ_OP_READ, 0, args->bio);
+		args->bio = mpage_bio_submit(REQ_OP_READ, op_flags, args->bio);
 
 alloc_new:
 	if (args->bio == NULL) {
@@ -296,14 +306,14 @@ alloc_new:
 		args->bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
 					min_t(int, args->nr_pages,
 					      BIO_MAX_PAGES),
-					args->gfp);
+					gfp);
 		if (args->bio == NULL)
 			goto confused;
 	}
 
 	length = first_hole << blkbits;
 	if (bio_add_page(args->bio, page, length, 0) < length) {
-		args->bio = mpage_bio_submit(REQ_OP_READ, 0, args->bio);
+		args->bio = mpage_bio_submit(REQ_OP_READ, op_flags, args->bio);
 		goto alloc_new;
 	}
 
@@ -311,7 +321,7 @@ alloc_new:
 	nblocks = map_bh->b_size >> blkbits;
 	if ((buffer_boundary(map_bh) && relative_block == nblocks) ||
 	    (first_hole != blocks_per_page))
-		args->bio = mpage_bio_submit(REQ_OP_READ, 0, args->bio);
+		args->bio = mpage_bio_submit(REQ_OP_READ, op_flags, args->bio);
 	else
 		args->last_block_in_bio = blocks[blocks_per_page - 1];
 out:
@@ -319,7 +329,7 @@ out:
 
 confused:
 	if (args->bio)
-		args->bio = mpage_bio_submit(REQ_OP_READ, 0, args->bio);
+		args->bio = mpage_bio_submit(REQ_OP_READ, op_flags, args->bio);
 	if (!PageUptodate(page))
 		block_read_full_page(page, args->get_block);
 	else
@@ -377,7 +387,7 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages,
 {
 	struct mpage_readpage_args args = {
 		.get_block = get_block,
-		.gfp = readahead_gfp_mask(mapping),
+		.is_readahead = true,
 	};
 	unsigned page_idx;
 
@@ -388,7 +398,7 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages,
 		list_del(&page->lru);
 		if (!add_to_page_cache_lru(page, mapping,
 					page->index,
-					args.gfp)) {
+					readahead_gfp_mask(mapping))) {
 			args.page = page;
 			args.nr_pages = nr_pages - page_idx;
 			args.bio = do_mpage_readpage(&args);
@@ -397,7 +407,7 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages,
 	}
 	BUG_ON(!list_empty(pages));
 	if (args.bio)
-		mpage_bio_submit(REQ_OP_READ, 0, args.bio);
+		mpage_bio_submit(REQ_OP_READ, REQ_RAHEAD, args.bio);
 	return 0;
 }
 EXPORT_SYMBOL(mpage_readpages);
@@ -411,7 +421,6 @@ int mpage_readpage(struct page *page, get_block_t get_block)
 		.page = page,
 		.nr_pages = 1,
 		.get_block = get_block,
-		.gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL),
 	};
 
 	args.bio = do_mpage_readpage(&args);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 9d319f1f66f6..a9242f336f02 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -344,6 +344,10 @@ struct address_space_operations {
 	/* Set a page dirty.  Return true if this dirtied it */
 	int (*set_page_dirty)(struct page *page);
 
+	/*
+	 * Reads in the requested pages. Unlike ->readpage(), this is
+	 * PURELY used for read-ahead!.
+	 */
 	int (*readpages)(struct file *filp, struct address_space *mapping,
 			struct list_head *pages, unsigned nr_pages);