clean up and generalize swap-over-NFS

index 75c6058..7c7176f 100644
@@ -1006,11 +1006,8 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 		}
 
 		/* ... iov_iter */
-		from.type = ITER_BVEC | WRITE;
-		from.bvec = array;
-		from.nr_segs = n;
-		from.count = sd.total_len - left;
-		from.iov_offset = 0;
+		iov_iter_bvec(&from, ITER_BVEC | WRITE, array, n,
+			      sd.total_len - left);
 
 		/* ... and iocb */
 		init_sync_kiocb(&kiocb, out);

index 1c5e453..23bb5e4 100644
@@ -63,6 +63,11 @@ static inline struct iovec iov_iter_iovec(const struct iov_iter *iter)
 	};
 }
 
+static inline int iov_iter_is_bvec(const struct iov_iter *iter)
+{
+	return (iter->type & ITER_BVEC) != 0;
+}
+
 #define iov_for_each(iov, iter, start)				\
 	if (!((start).type & ITER_BVEC))			\
 	for (iter = (start);					\

@@ -90,6 +95,8 @@ void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov,
 			unsigned long nr_segs, size_t count);
 void iov_iter_kvec(struct iov_iter *i, int direction, const struct kvec *iov,
 			unsigned long nr_segs, size_t count);
+void iov_iter_bvec(struct iov_iter *i, int direction, const struct bio_vec *bv,
+		   unsigned long nr_segs, size_t count);
 ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages,
 			size_t maxsize, unsigned maxpages, size_t *start);
 ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages,

index a1599ca..c975bc4 100644
@@ -513,6 +513,18 @@ void iov_iter_kvec(struct iov_iter *i, int direction,
 }
 EXPORT_SYMBOL(iov_iter_kvec);
 
+void iov_iter_bvec(struct iov_iter *i, int direction, const struct bio_vec *bv,
+		   unsigned long nr_segs, size_t count)
+{
+	BUG_ON(!(direction & ITER_BVEC));
+	i->type = direction;
+	i->bvec = bv;
+	i->nr_segs = nr_segs;
+	i->iov_offset = 0;
+	i->count = count;
+}
+EXPORT_SYMBOL(iov_iter_bvec);
+
 unsigned long iov_iter_alignment(const struct iov_iter *i)
 {
 	unsigned long res = 0;

index 955db8b..532a39b 100644
@@ -264,18 +264,14 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 		struct kiocb kiocb;
 		struct file *swap_file = sis->swap_file;
 		struct address_space *mapping = swap_file->f_mapping;
+		struct iov_iter from;
 		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,
-			.count = PAGE_SIZE,
-			.iov_offset = 0,
-			.nr_segs = 1,
-		};
-		from.bvec = &bv;	/* older gcc versions are broken */
+
+		iov_iter_bvec(&from, ITER_BVEC | WRITE, &bv, 1, PAGE_SIZE);
 
 		init_sync_kiocb(&kiocb, swap_file);
 		kiocb.ki_pos = page_file_offset(page);

index e181b6b..c71387b 100644
@@ -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 = !iov_iter_is_bvec(iter);
 
 	/*
 	 * For AIO O_(D)SYNC writes we need to defer completions to a workqueue

index 10bf072..b6ca65c 100644
@@ -88,6 +88,7 @@ struct nfs_direct_req {
 	struct pnfs_ds_commit_info ds_cinfo;	/* Storage for cinfo */
 	struct work_struct	work;
 	int			flags;
+	int			should_dirty;	/* should we mark read pages dirty? */
 #define NFS_ODIRECT_DO_COMMIT		(1)	/* an unstable reply was received */
 #define NFS_ODIRECT_RESCHED_WRITES	(2)	/* write verification failed */
 	struct nfs_writeverf	verf;		/* unstable write verifier */

@@ -370,7 +371,8 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
 		struct nfs_page *req = nfs_list_entry(hdr->pages.next);
 		struct page *page = req->wb_page;
 
-		if (!PageCompound(page) && bytes < hdr->good_bytes)
+		if (!PageCompound(page) && bytes < hdr->good_bytes &&
+		    dreq->should_dirty)
 			set_page_dirty(page);
 		bytes += req->wb_bytes;
 		nfs_list_remove_request(req);

@@ -542,6 +544,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
 	dreq->inode = inode;
 	dreq->bytes_left = count;
 	dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
+	dreq->should_dirty = !iov_iter_is_bvec(iter);
 	l_ctx = nfs_get_lock_context(dreq->ctx);
 	if (IS_ERR(l_ctx)) {
 		result = PTR_ERR(l_ctx);

index 532a39b..61165b0 100644
@@ -263,7 +263,6 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 	if (sis->flags & SWP_FILE) {
 		struct kiocb kiocb;
 		struct file *swap_file = sis->swap_file;
-		struct address_space *mapping = swap_file->f_mapping;
 		struct iov_iter from;
 		struct bio_vec bv = {
 			.bv_page = page,

@@ -279,9 +278,7 @@ 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,
-						kiocb.ki_pos);
+		ret = swap_file->f_op->write_iter(&kiocb, &from);
 		if (ret == PAGE_SIZE) {
 			count_vm_event(PSWPOUT);
 			ret = 0;

@@ -344,12 +341,31 @@ 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 iov_iter to;
+		struct bio_vec bv = {
+			.bv_page = page,
+			.bv_len = PAGE_SIZE,
+			.bv_offset = 0,
+		};
+
+		iov_iter_bvec(&to, ITER_BVEC | READ, &bv, 1, PAGE_SIZE);
+
+		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 = swap_file->f_op->read_iter(&kiocb, &to);
+		if (ret == PAGE_SIZE) {
+			SetPageUptodate(page);
 			count_vm_event(PSWPIN);
+			ret = 0;
+		} else {
+			ClearPageUptodate(page);
+			SetPageError(page);
+		}
+		unlock_page(page);
 		return ret;
 	}
 

index 63f55cc..4e14122 100644
@@ -2379,7 +2379,16 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		name = NULL;
 		goto bad_swap;
 	}
-	swap_file = file_open_name(name, O_RDWR|O_LARGEFILE, 0);
+	swap_file = file_open_name(name, O_RDWR | O_LARGEFILE | O_DIRECT, 0);
+	if (swap_file == ERR_PTR(-EINVAL)) {
+		/*
+		 * XXX: there are several filesystems that implement ->bmap but
+		 * not ->direct_IO. It's unlikely that anyone is using a
+		 * swapfile on, e.g., the MINIX fs, but this kludge will keep us
+		 * from getting a complaint from the one person who does.
+		 */
+		swap_file = file_open_name(name, O_RDWR | O_LARGEFILE, 0);
+	}
 	if (IS_ERR(swap_file)) {
 		error = PTR_ERR(swap_file);
 		swap_file = NULL;