fs: convert mpage_readpages to mpage_readahead

Implement the new readahead aop and convert all callers (block_dev,
exfat, ext2, fat, gfs2, hpfs, isofs, jfs, nilfs2, ocfs2, omfs, qnx6,
reiserfs & udf).

The callers are all trivial except for GFS2 & OCFS2.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Junxiao Bi <junxiao.bi@oracle.com> # ocfs2
Reviewed-by: Joseph Qi <joseph.qi@linux.alibaba.com> # ocfs2
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
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: Eric Biggers <ebiggers@google.com>
Cc: Gao Xiang <gaoxiang25@huawei.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
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/20200414150233.24495-17-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

fs/block_dev.c

@@ -614,10 +614,9 @@ static int blkdev_readpage(struct file * file, struct page * page)
 	return block_read_full_page(page, blkdev_get_block);
 }
 
-static int blkdev_readpages(struct file *file, struct address_space *mapping,
+static void blkdev_readahead(struct readahead_control *rac)
-			struct list_head *pages, unsigned nr_pages)
 {
-	return mpage_readpages(mapping, pages, nr_pages, blkdev_get_block);
+	mpage_readahead(rac, blkdev_get_block);
 }
 
 static int blkdev_write_begin(struct file *file, struct address_space *mapping,
@@ -2085,7 +2084,7 @@ static int blkdev_writepages(struct address_space *mapping,
 
 static const struct address_space_operations def_blk_aops = {
 	.readpage	= blkdev_readpage,
-	.readpages	= blkdev_readpages,
+	.readahead	= blkdev_readahead,
 	.writepage	= blkdev_writepage,
 	.write_begin	= blkdev_write_begin,
 	.write_end	= blkdev_write_end,

fs/exfat/inode.c

@@ -372,10 +372,9 @@ static int exfat_readpage(struct file *file, struct page *page)
 	return mpage_readpage(page, exfat_get_block);
 }
 
-static int exfat_readpages(struct file *file, struct address_space *mapping,
+static void exfat_readahead(struct readahead_control *rac)
-		struct list_head *pages, unsigned int nr_pages)
 {
-	return mpage_readpages(mapping, pages, nr_pages, exfat_get_block);
+	mpage_readahead(rac, exfat_get_block);
 }
 
 static int exfat_writepage(struct page *page, struct writeback_control *wbc)
@@ -502,7 +501,7 @@ int exfat_block_truncate_page(struct inode *inode, loff_t from)
 
 static const struct address_space_operations exfat_aops = {
 	.readpage	= exfat_readpage,
-	.readpages	= exfat_readpages,
+	.readahead	= exfat_readahead,
 	.writepage	= exfat_writepage,
 	.writepages	= exfat_writepages,
 	.write_begin	= exfat_write_begin,

fs/ext2/inode.c

@@ -877,11 +877,9 @@ static int ext2_readpage(struct file *file, struct page *page)
 	return mpage_readpage(page, ext2_get_block);
 }
 
-static int
+static void ext2_readahead(struct readahead_control *rac)
-ext2_readpages(struct file *file, struct address_space *mapping,
-		struct list_head *pages, unsigned nr_pages)
 {
-	return mpage_readpages(mapping, pages, nr_pages, ext2_get_block);
+	mpage_readahead(rac, ext2_get_block);
 }
 
 static int
@@ -967,7 +965,7 @@ ext2_dax_writepages(struct address_space *mapping, struct writeback_control *wbc
 
 const struct address_space_operations ext2_aops = {
 	.readpage		= ext2_readpage,
-	.readpages		= ext2_readpages,
+	.readahead		= ext2_readahead,
 	.writepage		= ext2_writepage,
 	.write_begin		= ext2_write_begin,
 	.write_end		= ext2_write_end,
@@ -981,7 +979,7 @@ const struct address_space_operations ext2_aops = {
 
 const struct address_space_operations ext2_nobh_aops = {
 	.readpage		= ext2_readpage,
-	.readpages		= ext2_readpages,
+	.readahead		= ext2_readahead,
 	.writepage		= ext2_nobh_writepage,
 	.write_begin		= ext2_nobh_write_begin,
 	.write_end		= nobh_write_end,

fs/fat/inode.c

@@ -210,10 +210,9 @@ static int fat_readpage(struct file *file, struct page *page)
 	return mpage_readpage(page, fat_get_block);
 }
 
-static int fat_readpages(struct file *file, struct address_space *mapping,
+static void fat_readahead(struct readahead_control *rac)
-			 struct list_head *pages, unsigned nr_pages)
 {
-	return mpage_readpages(mapping, pages, nr_pages, fat_get_block);
+	mpage_readahead(rac, fat_get_block);
 }
 
 static void fat_write_failed(struct address_space *mapping, loff_t to)
@@ -344,7 +343,7 @@ int fat_block_truncate_page(struct inode *inode, loff_t from)
 
 static const struct address_space_operations fat_aops = {
 	.readpage	= fat_readpage,
-	.readpages	= fat_readpages,
+	.readahead	= fat_readahead,
 	.writepage	= fat_writepage,
 	.writepages	= fat_writepages,
 	.write_begin	= fat_write_begin,

fs/gfs2/aops.c

@@ -577,7 +577,7 @@ int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos,
 }
 
 /**
- * gfs2_readpages - Read a bunch of pages at once
+ * gfs2_readahead - Read a bunch of pages at once
  * @file: The file to read from
  * @mapping: Address space info
  * @pages: List of pages to read
@@ -590,31 +590,24 @@ int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos,
  *    obviously not something we'd want to do on too regular a basis.
  *    Any I/O we ignore at this time will be done via readpage later.
  * 2. We don't handle stuffed files here we let readpage do the honours.
- * 3. mpage_readpages() does most of the heavy lifting in the common case.
+ * 3. mpage_readahead() does most of the heavy lifting in the common case.
  * 4. gfs2_block_map() is relied upon to set BH_Boundary in the right places.
  */
 
-static int gfs2_readpages(struct file *file, struct address_space *mapping,
+static void gfs2_readahead(struct readahead_control *rac)
-			  struct list_head *pages, unsigned nr_pages)
 {
-	struct inode *inode = mapping->host;
+	struct inode *inode = rac->mapping->host;
 	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct gfs2_holder gh;
-	int ret;
 
 	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
-	ret = gfs2_glock_nq(&gh);
+	if (gfs2_glock_nq(&gh))
-	if (unlikely(ret))
 		goto out_uninit;
 	if (!gfs2_is_stuffed(ip))
-		ret = mpage_readpages(mapping, pages, nr_pages, gfs2_block_map);
+		mpage_readahead(rac, gfs2_block_map);
 	gfs2_glock_dq(&gh);
 out_uninit:
 	gfs2_holder_uninit(&gh);
-	if (unlikely(gfs2_withdrawn(sdp)))
-		ret = -EIO;
-	return ret;
 }
 
 /**
@@ -833,7 +826,7 @@ static const struct address_space_operations gfs2_aops = {
 	.writepage = gfs2_writepage,
 	.writepages = gfs2_writepages,
 	.readpage = gfs2_readpage,
-	.readpages = gfs2_readpages,
+	.readahead = gfs2_readahead,
 	.bmap = gfs2_bmap,
 	.invalidatepage = gfs2_invalidatepage,
 	.releasepage = gfs2_releasepage,
@@ -847,7 +840,7 @@ static const struct address_space_operations gfs2_jdata_aops = {
 	.writepage = gfs2_jdata_writepage,
 	.writepages = gfs2_jdata_writepages,
 	.readpage = gfs2_readpage,
-	.readpages = gfs2_readpages,
+	.readahead = gfs2_readahead,
 	.set_page_dirty = jdata_set_page_dirty,
 	.bmap = gfs2_bmap,
 	.invalidatepage = gfs2_invalidatepage,

fs/hpfs/file.c

@@ -125,10 +125,9 @@ static int hpfs_writepage(struct page *page, struct writeback_control *wbc)
 	return block_write_full_page(page, hpfs_get_block, wbc);
 }
 
-static int hpfs_readpages(struct file *file, struct address_space *mapping,
+static void hpfs_readahead(struct readahead_control *rac)
-			  struct list_head *pages, unsigned nr_pages)
 {
-	return mpage_readpages(mapping, pages, nr_pages, hpfs_get_block);
+	mpage_readahead(rac, hpfs_get_block);
 }
 
 static int hpfs_writepages(struct address_space *mapping,
@@ -198,7 +197,7 @@ static int hpfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 const struct address_space_operations hpfs_aops = {
 	.readpage = hpfs_readpage,
 	.writepage = hpfs_writepage,
-	.readpages = hpfs_readpages,
+	.readahead = hpfs_readahead,
 	.writepages = hpfs_writepages,
 	.write_begin = hpfs_write_begin,
 	.write_end = hpfs_write_end,

fs/iomap/buffered-io.c

@@ -367,7 +367,7 @@ iomap_readpage(struct page *page, const struct iomap_ops *ops)
 	}
 
 	/*
-	 * Just like mpage_readpages and block_read_full_page we always
+	 * Just like mpage_readahead and block_read_full_page we always
 	 * return 0 and just mark the page as PageError on errors.  This
 	 * should be cleaned up all through the stack eventually.
 	 */

fs/isofs/inode.c

@@ -1185,10 +1185,9 @@ static int isofs_readpage(struct file *file, struct page *page)
 	return mpage_readpage(page, isofs_get_block);
 }
 
-static int isofs_readpages(struct file *file, struct address_space *mapping,
+static void isofs_readahead(struct readahead_control *rac)
-			struct list_head *pages, unsigned nr_pages)
 {
-	return mpage_readpages(mapping, pages, nr_pages, isofs_get_block);
+	mpage_readahead(rac, isofs_get_block);
 }
 
 static sector_t _isofs_bmap(struct address_space *mapping, sector_t block)
@@ -1198,7 +1197,7 @@ static sector_t _isofs_bmap(struct address_space *mapping, sector_t block)
 
 static const struct address_space_operations isofs_aops = {
 	.readpage = isofs_readpage,
-	.readpages = isofs_readpages,
+	.readahead = isofs_readahead,
 	.bmap = _isofs_bmap
 };
 

fs/jfs/inode.c

@@ -296,10 +296,9 @@ static int jfs_readpage(struct file *file, struct page *page)
 	return mpage_readpage(page, jfs_get_block);
 }
 
-static int jfs_readpages(struct file *file, struct address_space *mapping,
+static void jfs_readahead(struct readahead_control *rac)
-		struct list_head *pages, unsigned nr_pages)
 {
-	return mpage_readpages(mapping, pages, nr_pages, jfs_get_block);
+	mpage_readahead(rac, jfs_get_block);
 }
 
 static void jfs_write_failed(struct address_space *mapping, loff_t to)
@@ -358,7 +357,7 @@ static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 
 const struct address_space_operations jfs_aops = {
 	.readpage	= jfs_readpage,
-	.readpages	= jfs_readpages,
+	.readahead	= jfs_readahead,
 	.writepage	= jfs_writepage,
 	.writepages	= jfs_writepages,
 	.write_begin	= jfs_write_begin,

fs/mpage.c

@@ -91,7 +91,7 @@ mpage_alloc(struct block_device *bdev,
 }
 
 /*
- * support function for mpage_readpages.  The fs supplied get_block might
+ * support function for mpage_readahead.  The fs supplied get_block might
  * return an up to date buffer.  This is used to map that buffer into
  * the page, which allows readpage to avoid triggering a duplicate call
  * to get_block.
@@ -338,13 +338,8 @@ confused:
 }
 
 /**
- * mpage_readpages - populate an address space with some pages & start reads against them
+ * mpage_readahead - start reads against pages
- * @mapping: the address_space
+ * @rac: Describes which pages to read.
- * @pages: The address of a list_head which contains the target pages.  These
- *   pages have their ->index populated and are otherwise uninitialised.
- *   The page at @pages->prev has the lowest file offset, and reads should be
- *   issued in @pages->prev to @pages->next order.
- * @nr_pages: The number of pages at *@pages
  * @get_block: The filesystem's block mapper function.
  *
  * This function walks the pages and the blocks within each page, building and
@@ -381,36 +376,25 @@ confused:
  *
  * This all causes the disk requests to be issued in the correct order.
  */
-int
+void mpage_readahead(struct readahead_control *rac, get_block_t get_block)
-mpage_readpages(struct address_space *mapping, struct list_head *pages,
-				unsigned nr_pages, get_block_t get_block)
 {
+	struct page *page;
 	struct mpage_readpage_args args = {
 		.get_block = get_block,
 		.is_readahead = true,
 	};
-	unsigned page_idx;
-
-	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
-		struct page *page = lru_to_page(pages);
 
+	while ((page = readahead_page(rac))) {
 		prefetchw(&page->flags);
-		list_del(&page->lru);
-		if (!add_to_page_cache_lru(page, mapping,
-					page->index,
-					readahead_gfp_mask(mapping))) {
 		args.page = page;
-			args.nr_pages = nr_pages - page_idx;
+		args.nr_pages = readahead_count(rac);
 		args.bio = do_mpage_readpage(&args);
-		}
 		put_page(page);
 	}
-	BUG_ON(!list_empty(pages));
 	if (args.bio)
 		mpage_bio_submit(REQ_OP_READ, REQ_RAHEAD, args.bio);
-	return 0;
 }
-EXPORT_SYMBOL(mpage_readpages);
+EXPORT_SYMBOL(mpage_readahead);
 
 /*
  * This isn't called much at all
@@ -563,7 +547,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
 		 * Page has buffers, but they are all unmapped. The page was
 		 * created by pagein or read over a hole which was handled by
 		 * block_read_full_page().  If this address_space is also
-		 * using mpage_readpages then this can rarely happen.
+		 * using mpage_readahead then this can rarely happen.
 		 */
 		goto confused;
 	}

fs/nilfs2/inode.c

@@ -145,18 +145,9 @@ static int nilfs_readpage(struct file *file, struct page *page)
 	return mpage_readpage(page, nilfs_get_block);
 }
 
-/**
+static void nilfs_readahead(struct readahead_control *rac)
- * nilfs_readpages() - implement readpages() method of nilfs_aops {}
- * address_space_operations.
- * @file - file struct of the file to be read
- * @mapping - address_space struct used for reading multiple pages
- * @pages - the pages to be read
- * @nr_pages - number of pages to be read
- */
-static int nilfs_readpages(struct file *file, struct address_space *mapping,
-			   struct list_head *pages, unsigned int nr_pages)
 {
-	return mpage_readpages(mapping, pages, nr_pages, nilfs_get_block);
+	mpage_readahead(rac, nilfs_get_block);
 }
 
 static int nilfs_writepages(struct address_space *mapping,
@@ -308,7 +299,7 @@ const struct address_space_operations nilfs_aops = {
 	.readpage		= nilfs_readpage,
 	.writepages		= nilfs_writepages,
 	.set_page_dirty		= nilfs_set_page_dirty,
-	.readpages		= nilfs_readpages,
+	.readahead		= nilfs_readahead,
 	.write_begin		= nilfs_write_begin,
 	.write_end		= nilfs_write_end,
 	/* .releasepage		= nilfs_releasepage, */

fs/ocfs2/aops.c

@@ -350,14 +350,11 @@ out:
  * grow out to a tree. If need be, detecting boundary extents could
  * trivially be added in a future version of ocfs2_get_block().
  */
-static int ocfs2_readpages(struct file *filp, struct address_space *mapping,
+static void ocfs2_readahead(struct readahead_control *rac)
-			   struct list_head *pages, unsigned nr_pages)
 {
-	int ret, err = -EIO;
+	int ret;
-	struct inode *inode = mapping->host;
+	struct inode *inode = rac->mapping->host;
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
-	loff_t start;
-	struct page *last;
 
 	/*
 	 * Use the nonblocking flag for the dlm code to avoid page
@@ -365,36 +362,31 @@ static int ocfs2_readpages(struct file *filp, struct address_space *mapping,
 	 */
 	ret = ocfs2_inode_lock_full(inode, NULL, 0, OCFS2_LOCK_NONBLOCK);
 	if (ret)
-		return err;
+		return;
 
-	if (down_read_trylock(&oi->ip_alloc_sem) == 0) {
+	if (down_read_trylock(&oi->ip_alloc_sem) == 0)
-		ocfs2_inode_unlock(inode, 0);
+		goto out_unlock;
-		return err;
-	}
 
 	/*
 	 * Don't bother with inline-data. There isn't anything
 	 * to read-ahead in that case anyway...
 	 */
 	if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL)
-		goto out_unlock;
+		goto out_up;
 
 	/*
 	 * Check whether a remote node truncated this file - we just
 	 * drop out in that case as it's not worth handling here.
 	 */
-	last = lru_to_page(pages);
+	if (readahead_pos(rac) >= i_size_read(inode))
-	start = (loff_t)last->index << PAGE_SHIFT;
+		goto out_up;
-	if (start >= i_size_read(inode))
-		goto out_unlock;
 
-	err = mpage_readpages(mapping, pages, nr_pages, ocfs2_get_block);
+	mpage_readahead(rac, ocfs2_get_block);
 
-out_unlock:
+out_up:
 	up_read(&oi->ip_alloc_sem);
+out_unlock:
 	ocfs2_inode_unlock(inode, 0);
-
-	return err;
 }
 
 /* Note: Because we don't support holes, our allocation has
@@ -2474,7 +2466,7 @@ static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 
 const struct address_space_operations ocfs2_aops = {
 	.readpage		= ocfs2_readpage,
-	.readpages		= ocfs2_readpages,
+	.readahead		= ocfs2_readahead,
 	.writepage		= ocfs2_writepage,
 	.write_begin		= ocfs2_write_begin,
 	.write_end		= ocfs2_write_end,

fs/omfs/file.c

@@ -289,10 +289,9 @@ static int omfs_readpage(struct file *file, struct page *page)
 	return block_read_full_page(page, omfs_get_block);
 }
 
-static int omfs_readpages(struct file *file, struct address_space *mapping,
+static void omfs_readahead(struct readahead_control *rac)
-		struct list_head *pages, unsigned nr_pages)
 {
-	return mpage_readpages(mapping, pages, nr_pages, omfs_get_block);
+	mpage_readahead(rac, omfs_get_block);
 }
 
 static int omfs_writepage(struct page *page, struct writeback_control *wbc)
@@ -373,7 +372,7 @@ const struct inode_operations omfs_file_inops = {
 
 const struct address_space_operations omfs_aops = {
 	.readpage = omfs_readpage,
-	.readpages = omfs_readpages,
+	.readahead = omfs_readahead,
 	.writepage = omfs_writepage,
 	.writepages = omfs_writepages,
 	.write_begin = omfs_write_begin,

fs/qnx6/inode.c

@@ -99,10 +99,9 @@ static int qnx6_readpage(struct file *file, struct page *page)
 	return mpage_readpage(page, qnx6_get_block);
 }
 
-static int qnx6_readpages(struct file *file, struct address_space *mapping,
+static void qnx6_readahead(struct readahead_control *rac)
-		   struct list_head *pages, unsigned nr_pages)
 {
-	return mpage_readpages(mapping, pages, nr_pages, qnx6_get_block);
+	mpage_readahead(rac, qnx6_get_block);
 }
 
 /*
@@ -499,7 +498,7 @@ static sector_t qnx6_bmap(struct address_space *mapping, sector_t block)
 }
 static const struct address_space_operations qnx6_aops = {
 	.readpage	= qnx6_readpage,
-	.readpages	= qnx6_readpages,
+	.readahead	= qnx6_readahead,
 	.bmap		= qnx6_bmap
 };
 

fs/reiserfs/inode.c

@@ -1160,11 +1160,9 @@ failure:
 	return retval;
 }
 
-static int
+static void reiserfs_readahead(struct readahead_control *rac)
-reiserfs_readpages(struct file *file, struct address_space *mapping,
-		   struct list_head *pages, unsigned nr_pages)
 {
-	return mpage_readpages(mapping, pages, nr_pages, reiserfs_get_block);
+	mpage_readahead(rac, reiserfs_get_block);
 }
 
 /*
@@ -3434,7 +3432,7 @@ out:
 const struct address_space_operations reiserfs_address_space_operations = {
 	.writepage = reiserfs_writepage,
 	.readpage = reiserfs_readpage,
-	.readpages = reiserfs_readpages,
+	.readahead = reiserfs_readahead,
 	.releasepage = reiserfs_releasepage,
 	.invalidatepage = reiserfs_invalidatepage,
 	.write_begin = reiserfs_write_begin,

fs/udf/inode.c

@@ -195,10 +195,9 @@ static int udf_readpage(struct file *file, struct page *page)
 	return mpage_readpage(page, udf_get_block);
 }
 
-static int udf_readpages(struct file *file, struct address_space *mapping,
+static void udf_readahead(struct readahead_control *rac)
-			struct list_head *pages, unsigned nr_pages)
 {
-	return mpage_readpages(mapping, pages, nr_pages, udf_get_block);
+	mpage_readahead(rac, udf_get_block);
 }
 
 static int udf_write_begin(struct file *file, struct address_space *mapping,
@@ -234,7 +233,7 @@ static sector_t udf_bmap(struct address_space *mapping, sector_t block)
 
 const struct address_space_operations udf_aops = {
 	.readpage	= udf_readpage,
-	.readpages	= udf_readpages,
+	.readahead	= udf_readahead,
 	.writepage	= udf_writepage,
 	.writepages	= udf_writepages,
 	.write_begin	= udf_write_begin,

include/linux/mpage.h

@@ -13,9 +13,9 @@
 #ifdef CONFIG_BLOCK
 
 struct writeback_control;
+struct readahead_control;
 
-int mpage_readpages(struct address_space *mapping, struct list_head *pages,
+void mpage_readahead(struct readahead_control *, get_block_t get_block);
-				unsigned nr_pages, get_block_t get_block);
 int mpage_readpage(struct page *page, get_block_t get_block);
 int mpage_writepages(struct address_space *mapping,
 		struct writeback_control *wbc, get_block_t get_block);

mm/migrate.c

@@ -1032,7 +1032,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 		 * to the LRU. Later, when the IO completes the pages are
 		 * marked uptodate and unlocked. However, the queueing
 		 * could be merging multiple pages for one bio (e.g.
-		 * mpage_readpages). If an allocation happens for the
+		 * mpage_readahead). If an allocation happens for the
 		 * second or third page, the process can end up locking
 		 * the same page twice and deadlocking. Rather than
 		 * trying to be clever about what pages can be locked,