Merge tag 'for-linus-2019-08-17' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "A collection of fixes that should go into this series. This contains:

   - Revert of the REQ_NOWAIT_INLINE and associated dio changes. There
     were still corner cases there, and even though I had a solution for
     it, it's too involved for this stage. (me)

   - Set of NVMe fixes (via Sagi)

   - io_uring fix for fixed buffers (Anthony)

   - io_uring defer issue fix (Jackie)

   - Regression fix for queue sync at exit time (zhengbin)

   - xen blk-back memory leak fix (Wenwen)"

* tag 'for-linus-2019-08-17' of git://git.kernel.dk/linux-block:
  io_uring: fix an issue when IOSQE_IO_LINK is inserted into defer list
  block: remove REQ_NOWAIT_INLINE
  io_uring: fix manual setup of iov_iter for fixed buffers
  xen/blkback: fix memory leaks
  blk-mq: move cancel of requeue_work to the front of blk_exit_queue
  nvme-pci: Fix async probe remove race
  nvme: fix controller removal race with scan work
  nvme-rdma: fix possible use-after-free in connect error flow
  nvme: fix a possible deadlock when passthru commands sent to a multipath device
  nvme-core: Fix extra device_put() call on error path
  nvmet-file: fix nvmet_file_flush() always returning an error
  nvmet-loop: Flush nvme_delete_wq when removing the port
  nvmet: Fix use-after-free bug when a port is removed
  nvme-multipath: revalidate nvme_ns_head gendisk in nvme_validate_ns

2 files changed, 15 insertions, 54 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index eb657ab94060..677cb364d33f 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -345,24 +345,15 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 	struct bio *bio;
 	bool is_poll = (iocb->ki_flags & IOCB_HIPRI) != 0;
 	bool is_read = (iov_iter_rw(iter) == READ), is_sync;
-	bool nowait = (iocb->ki_flags & IOCB_NOWAIT) != 0;
 	loff_t pos = iocb->ki_pos;
 	blk_qc_t qc = BLK_QC_T_NONE;
-	gfp_t gfp;
-	int ret;
+	int ret = 0;
 
 	if ((pos | iov_iter_alignment(iter)) &
 	    (bdev_logical_block_size(bdev) - 1))
 		return -EINVAL;
 
-	if (nowait)
-		gfp = GFP_NOWAIT;
-	else
-		gfp = GFP_KERNEL;
-
-	bio = bio_alloc_bioset(gfp, nr_pages, &blkdev_dio_pool);
-	if (!bio)
-		return -EAGAIN;
+	bio = bio_alloc_bioset(GFP_KERNEL, nr_pages, &blkdev_dio_pool);
 
 	dio = container_of(bio, struct blkdev_dio, bio);
 	dio->is_sync = is_sync = is_sync_kiocb(iocb);
@@ -384,7 +375,6 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 	if (!is_poll)
 		blk_start_plug(&plug);
 
-	ret = 0;
 	for (;;) {
 		bio_set_dev(bio, bdev);
 		bio->bi_iter.bi_sector = pos >> 9;
@@ -409,14 +399,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 			task_io_account_write(bio->bi_iter.bi_size);
 		}
 
-		/*
-		 * Tell underlying layer to not block for resource shortage.
-		 * And if we would have blocked, return error inline instead
-		 * of through the bio->bi_end_io() callback.
-		 */
-		if (nowait)
-			bio->bi_opf |= (REQ_NOWAIT | REQ_NOWAIT_INLINE);
-
+		dio->size += bio->bi_iter.bi_size;
 		pos += bio->bi_iter.bi_size;
 
 		nr_pages = iov_iter_npages(iter, BIO_MAX_PAGES);
@@ -428,13 +411,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 				polled = true;
 			}
 
-			dio->size += bio->bi_iter.bi_size;
 			qc = submit_bio(bio);
-			if (qc == BLK_QC_T_EAGAIN) {
-				dio->size -= bio->bi_iter.bi_size;
-				ret = -EAGAIN;
-				goto error;
-			}
 
 			if (polled)
 				WRITE_ONCE(iocb->ki_cookie, qc);
@@ -455,19 +432,8 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 			atomic_inc(&dio->ref);
 		}
 
-		dio->size += bio->bi_iter.bi_size;
-		qc = submit_bio(bio);
-		if (qc == BLK_QC_T_EAGAIN) {
-			dio->size -= bio->bi_iter.bi_size;
-			ret = -EAGAIN;
-			goto error;
-		}
-
-		bio = bio_alloc(gfp, nr_pages);
-		if (!bio) {
-			ret = -EAGAIN;
-			goto error;
-		}
+		submit_bio(bio);
+		bio = bio_alloc(GFP_KERNEL, nr_pages);
 	}
 
 	if (!is_poll)
@@ -487,7 +453,6 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 	}
 	__set_current_state(TASK_RUNNING);
 
-out:
 	if (!ret)
 		ret = blk_status_to_errno(dio->bio.bi_status);
 	if (likely(!ret))
@@ -495,10 +460,6 @@ out:
 
 	bio_put(&dio->bio);
 	return ret;
-error:
-	if (!is_poll)
-		blk_finish_plug(&plug);
-	goto out;
 }
 
 static ssize_t
diff --git a/fs/io_uring.c b/fs/io_uring.c
index d542f1cf4428..24bbe3cb7ad4 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1097,10 +1097,8 @@ static int io_import_fixed(struct io_ring_ctx *ctx, int rw,
 
 			iter->bvec = bvec + seg_skip;
 			iter->nr_segs -= seg_skip;
-			iter->count -= (seg_skip << PAGE_SHIFT);
+			iter->count -= bvec->bv_len + offset;
 			iter->iov_offset = offset & ~PAGE_MASK;
-			if (iter->iov_offset)
-				iter->count -= iter->iov_offset;
 		}
 	}
 
@@ -2025,6 +2023,15 @@ static int io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 {
 	int ret;
 
+	ret = io_req_defer(ctx, req, s->sqe);
+	if (ret) {
+		if (ret != -EIOCBQUEUED) {
+			io_free_req(req);
+			io_cqring_add_event(ctx, s->sqe->user_data, ret);
+		}
+		return 0;
+	}
+
 	ret = __io_submit_sqe(ctx, req, s, true);
 	if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
 		struct io_uring_sqe *sqe_copy;
@@ -2097,13 +2104,6 @@ err:
 		return;
 	}
 
-	ret = io_req_defer(ctx, req, s->sqe);
-	if (ret) {
-		if (ret != -EIOCBQUEUED)
-			goto err_req;
-		return;
-	}
-
 	/*
 	 * If we already have a head request, queue this one for async
 	 * submittal once the head completes. If we don't have a head but