3 files changed, 48 insertions, 84 deletions

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 89e21961d1ad..a1ed7620fbac 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -59,24 +59,19 @@ iomap_page_create(struct inode *inode, struct page *page)
 	 * migrate_page_move_mapping() assumes that pages with private data have
 	 * their count elevated by 1.
 	 */
-	get_page(page);
-	set_page_private(page, (unsigned long)iop);
-	SetPagePrivate(page);
+	attach_page_private(page, iop);
 	return iop;
 }
 
 static void
 iomap_page_release(struct page *page)
 {
-	struct iomap_page *iop = to_iomap_page(page);
+	struct iomap_page *iop = detach_page_private(page);
 
 	if (!iop)
 		return;
 	WARN_ON_ONCE(atomic_read(&iop->read_count));
 	WARN_ON_ONCE(atomic_read(&iop->write_count));
-	ClearPagePrivate(page);
-	set_page_private(page, 0);
-	put_page(page);
 	kfree(iop);
 }
 
@@ -214,9 +209,8 @@ iomap_read_end_io(struct bio *bio)
 struct iomap_readpage_ctx {
 	struct page		*cur_page;
 	bool			cur_page_in_bio;
-	bool			is_readahead;
 	struct bio		*bio;
-	struct list_head	*pages;
+	struct readahead_control *rac;
 };
 
 static void
@@ -308,7 +302,7 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		if (ctx->bio)
 			submit_bio(ctx->bio);
 
-		if (ctx->is_readahead) /* same as readahead_gfp_mask */
+		if (ctx->rac) /* same as readahead_gfp_mask */
 			gfp |= __GFP_NORETRY | __GFP_NOWARN;
 		ctx->bio = bio_alloc(gfp, min(BIO_MAX_PAGES, nr_vecs));
 		/*
@@ -319,7 +313,7 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		if (!ctx->bio)
 			ctx->bio = bio_alloc(orig_gfp, 1);
 		ctx->bio->bi_opf = REQ_OP_READ;
-		if (ctx->is_readahead)
+		if (ctx->rac)
 			ctx->bio->bi_opf |= REQ_RAHEAD;
 		ctx->bio->bi_iter.bi_sector = sector;
 		bio_set_dev(ctx->bio, iomap->bdev);
@@ -367,7 +361,7 @@ 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.
 	 */
@@ -375,36 +369,8 @@ iomap_readpage(struct page *page, const struct iomap_ops *ops)
 }
 EXPORT_SYMBOL_GPL(iomap_readpage);
 
-static struct page *
-iomap_next_page(struct inode *inode, struct list_head *pages, loff_t pos,
-		loff_t length, loff_t *done)
-{
-	while (!list_empty(pages)) {
-		struct page *page = lru_to_page(pages);
-
-		if (page_offset(page) >= (u64)pos + length)
-			break;
-
-		list_del(&page->lru);
-		if (!add_to_page_cache_lru(page, inode->i_mapping, page->index,
-				GFP_NOFS))
-			return page;
-
-		/*
-		 * If we already have a page in the page cache at index we are
-		 * done.  Upper layers don't care if it is uptodate after the
-		 * readpages call itself as every page gets checked again once
-		 * actually needed.
-		 */
-		*done += PAGE_SIZE;
-		put_page(page);
-	}
-
-	return NULL;
-}
-
 static loff_t
-iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length,
+iomap_readahead_actor(struct inode *inode, loff_t pos, loff_t length,
 		void *data, struct iomap *iomap, struct iomap *srcmap)
 {
 	struct iomap_readpage_ctx *ctx = data;
@@ -418,10 +384,7 @@ iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length,
 			ctx->cur_page = NULL;
 		}
 		if (!ctx->cur_page) {
-			ctx->cur_page = iomap_next_page(inode, ctx->pages,
-					pos, length, &done);
-			if (!ctx->cur_page)
-				break;
+			ctx->cur_page = readahead_page(ctx->rac);
 			ctx->cur_page_in_bio = false;
 		}
 		ret = iomap_readpage_actor(inode, pos + done, length - done,
@@ -431,32 +394,43 @@ iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length,
 	return done;
 }
 
-int
-iomap_readpages(struct address_space *mapping, struct list_head *pages,
-		unsigned nr_pages, const struct iomap_ops *ops)
+/**
+ * iomap_readahead - Attempt to read pages from a file.
+ * @rac: Describes the pages to be read.
+ * @ops: The operations vector for the filesystem.
+ *
+ * This function is for filesystems to call to implement their readahead
+ * address_space operation.
+ *
+ * Context: The @ops callbacks may submit I/O (eg to read the addresses of
+ * blocks from disc), and may wait for it.  The caller may be trying to
+ * access a different page, and so sleeping excessively should be avoided.
+ * It may allocate memory, but should avoid costly allocations.  This
+ * function is called with memalloc_nofs set, so allocations will not cause
+ * the filesystem to be reentered.
+ */
+void iomap_readahead(struct readahead_control *rac, const struct iomap_ops *ops)
 {
+	struct inode *inode = rac->mapping->host;
+	loff_t pos = readahead_pos(rac);
+	loff_t length = readahead_length(rac);
 	struct iomap_readpage_ctx ctx = {
-		.pages		= pages,
-		.is_readahead	= true,
+		.rac	= rac,
 	};
-	loff_t pos = page_offset(list_entry(pages->prev, struct page, lru));
-	loff_t last = page_offset(list_entry(pages->next, struct page, lru));
-	loff_t length = last - pos + PAGE_SIZE, ret = 0;
 
-	trace_iomap_readpages(mapping->host, nr_pages);
+	trace_iomap_readahead(inode, readahead_count(rac));
 
 	while (length > 0) {
-		ret = iomap_apply(mapping->host, pos, length, 0, ops,
-				&ctx, iomap_readpages_actor);
+		loff_t ret = iomap_apply(inode, pos, length, 0, ops,
+				&ctx, iomap_readahead_actor);
 		if (ret <= 0) {
 			WARN_ON_ONCE(ret == 0);
-			goto done;
+			break;
 		}
 		pos += ret;
 		length -= ret;
 	}
-	ret = 0;
-done:
+
 	if (ctx.bio)
 		submit_bio(ctx.bio);
 	if (ctx.cur_page) {
@@ -464,15 +438,8 @@ done:
 			unlock_page(ctx.cur_page);
 		put_page(ctx.cur_page);
 	}
-
-	/*
-	 * Check that we didn't lose a page due to the arcance calling
-	 * conventions..
-	 */
-	WARN_ON_ONCE(!ret && !list_empty(ctx.pages));
-	return ret;
 }
-EXPORT_SYMBOL_GPL(iomap_readpages);
+EXPORT_SYMBOL_GPL(iomap_readahead);
 
 /*
  * iomap_is_partially_uptodate checks whether blocks within a page are
@@ -554,14 +521,8 @@ iomap_migrate_page(struct address_space *mapping, struct page *newpage,
 	if (ret != MIGRATEPAGE_SUCCESS)
 		return ret;
 
-	if (page_has_private(page)) {
-		ClearPagePrivate(page);
-		get_page(newpage);
-		set_page_private(newpage, page_private(page));
-		set_page_private(page, 0);
-		put_page(page);
-		SetPagePrivate(newpage);
-	}
+	if (page_has_private(page))
+		attach_page_private(newpage, detach_page_private(page));
 
 	if (mode != MIGRATE_SYNC_NO_COPY)
 		migrate_page_copy(newpage, page);
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 20dde5aadcdd..ec7b78e6feca 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -59,7 +59,7 @@ int iomap_dio_iopoll(struct kiocb *kiocb, bool spin)
 EXPORT_SYMBOL_GPL(iomap_dio_iopoll);
 
 static void iomap_dio_submit_bio(struct iomap_dio *dio, struct iomap *iomap,
-		struct bio *bio)
+		struct bio *bio, loff_t pos)
 {
 	atomic_inc(&dio->ref);
 
@@ -67,7 +67,12 @@ static void iomap_dio_submit_bio(struct iomap_dio *dio, struct iomap *iomap,
 		bio_set_polled(bio, dio->iocb);
 
 	dio->submit.last_queue = bdev_get_queue(iomap->bdev);
-	dio->submit.cookie = submit_bio(bio);
+	if (dio->dops && dio->dops->submit_io)
+		dio->submit.cookie = dio->dops->submit_io(
+				file_inode(dio->iocb->ki_filp),
+				iomap, bio, pos);
+	else
+		dio->submit.cookie = submit_bio(bio);
 }
 
 static ssize_t iomap_dio_complete(struct iomap_dio *dio)
@@ -191,7 +196,7 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
 	get_page(page);
 	__bio_add_page(bio, page, len, 0);
 	bio_set_op_attrs(bio, REQ_OP_WRITE, flags);
-	iomap_dio_submit_bio(dio, iomap, bio);
+	iomap_dio_submit_bio(dio, iomap, bio, pos);
 }
 
 static loff_t
@@ -299,11 +304,11 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 		}
 
 		dio->size += n;
-		pos += n;
 		copied += n;
 
 		nr_pages = iov_iter_npages(dio->submit.iter, BIO_MAX_PAGES);
-		iomap_dio_submit_bio(dio, iomap, bio);
+		iomap_dio_submit_bio(dio, iomap, bio, pos);
+		pos += n;
 	} while (nr_pages);
 
 	/*
@@ -411,8 +416,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	struct blk_plug plug;
 	struct iomap_dio *dio;
 
-	lockdep_assert_held(&inode->i_rwsem);
-
 	if (!count)
 		return 0;
 
@@ -561,7 +564,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 			    !dio->submit.last_queue ||
 			    !blk_poll(dio->submit.last_queue,
 					 dio->submit.cookie, true))
-				io_schedule();
+				blk_io_schedule();
 		}
 		__set_current_state(TASK_RUNNING);
 	}
diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h
index 4df19c66f597..5693a39d52fb 100644
--- a/fs/iomap/trace.h
+++ b/fs/iomap/trace.h
@@ -39,7 +39,7 @@ DEFINE_EVENT(iomap_readpage_class, name,	\
 	TP_PROTO(struct inode *inode, int nr_pages), \
 	TP_ARGS(inode, nr_pages))
 DEFINE_READPAGE_EVENT(iomap_readpage);
-DEFINE_READPAGE_EVENT(iomap_readpages);
+DEFINE_READPAGE_EVENT(iomap_readahead);
 
 DECLARE_EVENT_CLASS(iomap_range_class,
 	TP_PROTO(struct inode *inode, unsigned long off, unsigned int len),