[PATCH] swap: use direct_IO for swap_readpage

[Omar Sandoval]

Signed-off-by: Omar Sandoval <osandov@xxxxxxxxxxx>
---
 fs/direct-io.c |  8 +++++---
 mm/page_io.c   | 37 ++++++++++++++++++++++++++++++-------
 2 files changed, 35 insertions(+), 10 deletions(-)

diff --git a/fs/direct-io.c b/fs/direct-io.c
index e181b6b..e542ce4 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -120,6 +120,7 @@ struct dio {
 	spinlock_t bio_lock;		/* protects BIO fields below */
 	int page_errors;		/* errno from get_user_pages() */
 	int is_async;			/* is IO async ? */
+	int should_dirty;		/* should we mark read pages dirty? */
 	bool defer_completion;		/* defer AIO completion to workqueue? */
 	int io_error;			/* IO error in completion path */
 	unsigned long refcount;		/* direct_io_worker() and bios */
@@ -392,7 +393,7 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio)
 	dio->refcount++;
 	spin_unlock_irqrestore(&dio->bio_lock, flags);
 
-	if (dio->is_async && dio->rw == READ)
+	if (dio->is_async && dio->rw == READ && dio->should_dirty)
 		bio_set_pages_dirty(bio);
 
 	if (sdio->submit_io)
@@ -463,13 +464,13 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio)
 	if (!uptodate)
 		dio->io_error = -EIO;
 
-	if (dio->is_async && dio->rw == READ) {
+	if (dio->is_async && dio->rw == READ && dio->should_dirty) {
 		bio_check_pages_dirty(bio);	/* transfers ownership */
 	} else {
 		bio_for_each_segment_all(bvec, bio, i) {
 			struct page *page = bvec->bv_page;
 
-			if (dio->rw == READ && !PageCompound(page))
+			if (dio->rw == READ && !PageCompound(page) && dio->should_dirty)
 				set_page_dirty_lock(page);
 			page_cache_release(page);
 		}
@@ -1177,6 +1178,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 
 	dio->inode = inode;
 	dio->rw = rw;
+	dio->should_dirty = !(iter->type & ITER_BVEC);
 
 	/*
 	 * For AIO O_(D)SYNC writes we need to defer completions to a workqueue
diff --git a/mm/page_io.c b/mm/page_io.c
index 955db8b..b9b84b2 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -266,8 +266,8 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 		struct address_space *mapping = swap_file->f_mapping;
 		struct bio_vec bv = {
 			.bv_page = page,
-			.bv_len  = PAGE_SIZE,
-			.bv_offset = 0
+			.bv_len = PAGE_SIZE,
+			.bv_offset = 0,
 		};
 		struct iov_iter from = {
 			.type = ITER_BVEC | WRITE,
@@ -283,8 +283,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 
 		set_page_writeback(page);
 		unlock_page(page);
-		ret = mapping->a_ops->direct_IO(ITER_BVEC | WRITE,
-						&kiocb, &from,
+		ret = mapping->a_ops->direct_IO(WRITE, &kiocb, &from,
 						kiocb.ki_pos);
 		if (ret == PAGE_SIZE) {
 			count_vm_event(PSWPOUT);
@@ -303,7 +302,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 			set_page_dirty(page);
 			ClearPageReclaim(page);
 			pr_err_ratelimited("Write error on dio swapfile (%Lu)\n",
-				page_file_offset(page));
+					   page_file_offset(page));
 		}
 		end_page_writeback(page);
 		return ret;
@@ -348,12 +347,36 @@ int swap_readpage(struct page *page)
 	}
 
 	if (sis->flags & SWP_FILE) {
+		struct kiocb kiocb;
 		struct file *swap_file = sis->swap_file;
 		struct address_space *mapping = swap_file->f_mapping;
+		struct bio_vec bv = {
+			.bv_page = page,
+			.bv_len = PAGE_SIZE,
+			.bv_offset = 0,
+		};
+		struct iov_iter to = {
+			.type = ITER_BVEC | READ,
+			.count = PAGE_SIZE,
+			.iov_offset = 0,
+			.nr_segs = 1,
+		};
+		to.bvec = &bv;	/* older gcc versions are broken */
+
+		init_sync_kiocb(&kiocb, swap_file);
+		kiocb.ki_pos = page_file_offset(page);
+		kiocb.ki_nbytes = PAGE_SIZE;
 
-		ret = mapping->a_ops->readpage(swap_file, page);
-		if (!ret)
+		ret = mapping->a_ops->direct_IO(READ, &kiocb, &to,
+						kiocb.ki_pos);
+		if (ret == PAGE_SIZE) {
+			SetPageUptodate(page);
 			count_vm_event(PSWPIN);
+			ret = 0;
+		} else {
+			PageError(page); /* XXX: maybe? */
+		}
+		unlock_page(page);
 		return ret;
 	}
 
-- 
2.1.3


--HlL+5n6rz5pIUxbD--
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/