Merge tag 'for-linus-20190726' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - Several io_uring fixes/improvements:
     - Blocking fix for O_DIRECT (me)
     - Latter page slowness for registered buffers (me)
     - Fix poll hang under certain conditions (me)
     - Defer sequence check fix for wrapped rings (Zhengyuan)
     - Mismatch in async inc/dec accounting (Zhengyuan)
     - Memory ordering issue that could cause stall (Zhengyuan)
      - Track sequential defer in bytes, not pages (Zhengyuan)

 - NVMe pull request from Christoph

 - Set of hang fixes for wbt (Josef)

 - Redundant error message kill for libahci (Ding)

 - Remove unused blk_mq_sched_started_request() and related ops (Marcos)

 - drbd dynamic alloc shash descriptor to reduce stack use (Arnd)

 - blkcg ->pd_stat() non-debug print (Tejun)

 - bcache memory leak fix (Wei)

 - Comment fix (Akinobu)

 - BFQ perf regression fix (Paolo)

* tag 'for-linus-20190726' of git://git.kernel.dk/linux-block: (24 commits)
  io_uring: ensure ->list is initialized for poll commands
  Revert "nvme-pci: don't create a read hctx mapping without read queues"
  nvme: fix multipath crash when ANA is deactivated
  nvme: fix memory leak caused by incorrect subsystem free
  nvme: ignore subnqn for ADATA SX6000LNP
  drbd: dynamically allocate shash descriptor
  block: blk-mq: Remove blk_mq_sched_started_request and started_request
  bcache: fix possible memory leak in bch_cached_dev_run()
  io_uring: track io length in async_list based on bytes
  io_uring: don't use iov_iter_advance() for fixed buffers
  block: properly handle IOCB_NOWAIT for async O_DIRECT IO
  blk-mq: allow REQ_NOWAIT to return an error inline
  io_uring: add a memory barrier before atomic_read
  rq-qos: use a mb for got_token
  rq-qos: set ourself TASK_UNINTERRUPTIBLE after we schedule
  rq-qos: don't reset has_sleepers on spurious wakeups
  rq-qos: fix missed wake-ups in rq_qos_throttle
  wait: add wq_has_single_sleeper helper
  block, bfq: check also in-flight I/O in dispatch plugging
  block: fix sysfs module parameters directory path in comment
  ...

2 files changed, 114 insertions, 25 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 4707dfff991b..c2a85b587922 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -345,15 +345,24 @@ __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;
-	int ret = 0;
+	gfp_t gfp;
+	ssize_t ret;
 
 	if ((pos | iov_iter_alignment(iter)) &
 	    (bdev_logical_block_size(bdev) - 1))
 		return -EINVAL;
 
-	bio = bio_alloc_bioset(GFP_KERNEL, nr_pages, &blkdev_dio_pool);
+	if (nowait)
+		gfp = GFP_NOWAIT;
+	else
+		gfp = GFP_KERNEL;
+
+	bio = bio_alloc_bioset(gfp, nr_pages, &blkdev_dio_pool);
+	if (!bio)
+		return -EAGAIN;
 
 	dio = container_of(bio, struct blkdev_dio, bio);
 	dio->is_sync = is_sync = is_sync_kiocb(iocb);
@@ -375,7 +384,10 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 	if (!is_poll)
 		blk_start_plug(&plug);
 
+	ret = 0;
 	for (;;) {
+		int err;
+
 		bio_set_dev(bio, bdev);
 		bio->bi_iter.bi_sector = pos >> 9;
 		bio->bi_write_hint = iocb->ki_hint;
@@ -383,8 +395,10 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 		bio->bi_end_io = blkdev_bio_end_io;
 		bio->bi_ioprio = iocb->ki_ioprio;
 
-		ret = bio_iov_iter_get_pages(bio, iter);
-		if (unlikely(ret)) {
+		err = bio_iov_iter_get_pages(bio, iter);
+		if (unlikely(err)) {
+			if (!ret)
+				ret = err;
 			bio->bi_status = BLK_STS_IOERR;
 			bio_endio(bio);
 			break;
@@ -399,6 +413,14 @@ __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;
 
@@ -412,6 +434,11 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 			}
 
 			qc = submit_bio(bio);
+			if (qc == BLK_QC_T_EAGAIN) {
+				if (!ret)
+					ret = -EAGAIN;
+				goto error;
+			}
 
 			if (polled)
 				WRITE_ONCE(iocb->ki_cookie, qc);
@@ -432,8 +459,20 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 			atomic_inc(&dio->ref);
 		}
 
-		submit_bio(bio);
-		bio = bio_alloc(GFP_KERNEL, nr_pages);
+		qc = submit_bio(bio);
+		if (qc == BLK_QC_T_EAGAIN) {
+			if (!ret)
+				ret = -EAGAIN;
+			goto error;
+		}
+		ret += bio->bi_iter.bi_size;
+
+		bio = bio_alloc(gfp, nr_pages);
+		if (!bio) {
+			if (!ret)
+				ret = -EAGAIN;
+			goto error;
+		}
 	}
 
 	if (!is_poll)
@@ -453,13 +492,16 @@ __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))
-		ret = dio->size;
 
 	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 e2a66e12fbc6..012bc0efb9d3 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -202,7 +202,7 @@ struct async_list {
 
 	struct file		*file;
 	off_t			io_end;
-	size_t			io_pages;
+	size_t			io_len;
 };
 
 struct io_ring_ctx {
@@ -333,7 +333,8 @@ struct io_kiocb {
 #define REQ_F_IO_DRAIN		16	/* drain existing IO first */
 #define REQ_F_IO_DRAINED	32	/* drain done */
 #define REQ_F_LINK		64	/* linked sqes */
-#define REQ_F_FAIL_LINK		128	/* fail rest of links */
+#define REQ_F_LINK_DONE		128	/* linked sqes done */
+#define REQ_F_FAIL_LINK		256	/* fail rest of links */
 	u64			user_data;
 	u32			result;
 	u32			sequence;
@@ -429,7 +430,7 @@ static inline bool io_sequence_defer(struct io_ring_ctx *ctx,
 	if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) != REQ_F_IO_DRAIN)
 		return false;
 
-	return req->sequence > ctx->cached_cq_tail + ctx->sq_ring->dropped;
+	return req->sequence != ctx->cached_cq_tail + ctx->sq_ring->dropped;
 }
 
 static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx)
@@ -632,6 +633,7 @@ static void io_req_link_next(struct io_kiocb *req)
 			nxt->flags |= REQ_F_LINK;
 		}
 
+		nxt->flags |= REQ_F_LINK_DONE;
 		INIT_WORK(&nxt->work, io_sq_wq_submit_work);
 		queue_work(req->ctx->sqo_wq, &nxt->work);
 	}
@@ -1064,8 +1066,44 @@ static int io_import_fixed(struct io_ring_ctx *ctx, int rw,
 	 */
 	offset = buf_addr - imu->ubuf;
 	iov_iter_bvec(iter, rw, imu->bvec, imu->nr_bvecs, offset + len);
-	if (offset)
-		iov_iter_advance(iter, offset);
+
+	if (offset) {
+		/*
+		 * Don't use iov_iter_advance() here, as it's really slow for
+		 * using the latter parts of a big fixed buffer - it iterates
+		 * over each segment manually. We can cheat a bit here, because
+		 * we know that:
+		 *
+		 * 1) it's a BVEC iter, we set it up
+		 * 2) all bvecs are PAGE_SIZE in size, except potentially the
+		 *    first and last bvec
+		 *
+		 * So just find our index, and adjust the iterator afterwards.
+		 * If the offset is within the first bvec (or the whole first
+		 * bvec, just use iov_iter_advance(). This makes it easier
+		 * since we can just skip the first segment, which may not
+		 * be PAGE_SIZE aligned.
+		 */
+		const struct bio_vec *bvec = imu->bvec;
+
+		if (offset <= bvec->bv_len) {
+			iov_iter_advance(iter, offset);
+		} else {
+			unsigned long seg_skip;
+
+			/* skip first vec */
+			offset -= bvec->bv_len;
+			seg_skip = 1 + (offset >> PAGE_SHIFT);
+
+			iter->bvec = bvec + seg_skip;
+			iter->nr_segs -= seg_skip;
+			iter->count -= (seg_skip << PAGE_SHIFT);
+			iter->iov_offset = offset & ~PAGE_MASK;
+			if (iter->iov_offset)
+				iter->count -= iter->iov_offset;
+		}
+	}
+
 	return 0;
 }
 
@@ -1120,28 +1158,26 @@ static void io_async_list_note(int rw, struct io_kiocb *req, size_t len)
 	off_t io_end = kiocb->ki_pos + len;
 
 	if (filp == async_list->file && kiocb->ki_pos == async_list->io_end) {
-		unsigned long max_pages;
+		unsigned long max_bytes;
 
 		/* Use 8x RA size as a decent limiter for both reads/writes */
-		max_pages = filp->f_ra.ra_pages;
-		if (!max_pages)
-			max_pages = VM_READAHEAD_PAGES;
-		max_pages *= 8;
-
-		/* If max pages are exceeded, reset the state */
-		len >>= PAGE_SHIFT;
-		if (async_list->io_pages + len <= max_pages) {
+		max_bytes = filp->f_ra.ra_pages << (PAGE_SHIFT + 3);
+		if (!max_bytes)
+			max_bytes = VM_READAHEAD_PAGES << (PAGE_SHIFT + 3);
+
+		/* If max len are exceeded, reset the state */
+		if (async_list->io_len + len <= max_bytes) {
 			req->flags |= REQ_F_SEQ_PREV;
-			async_list->io_pages += len;
+			async_list->io_len += len;
 		} else {
 			io_end = 0;
-			async_list->io_pages = 0;
+			async_list->io_len = 0;
 		}
 	}
 
 	/* New file? Reset state. */
 	if (async_list->file != filp) {
-		async_list->io_pages = 0;
+		async_list->io_len = 0;
 		async_list->file = filp;
 	}
 	async_list->io_end = io_end;
@@ -1630,6 +1666,8 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	INIT_LIST_HEAD(&poll->wait.entry);
 	init_waitqueue_func_entry(&poll->wait, io_poll_wake);
 
+	INIT_LIST_HEAD(&req->list);
+
 	mask = vfs_poll(poll->file, &ipt.pt) & poll->events;
 
 	spin_lock_irq(&ctx->completion_lock);
@@ -1844,6 +1882,10 @@ restart:
 		/* async context always use a copy of the sqe */
 		kfree(sqe);
 
+		/* req from defer and link list needn't decrease async cnt */
+		if (req->flags & (REQ_F_IO_DRAINED | REQ_F_LINK_DONE))
+			goto out;
+
 		if (!async_list)
 			break;
 		if (!list_empty(&req_list)) {
@@ -1891,6 +1933,7 @@ restart:
 		}
 	}
 
+out:
 	if (cur_mm) {
 		set_fs(old_fs);
 		unuse_mm(cur_mm);
@@ -1917,6 +1960,10 @@ static bool io_add_to_prev_work(struct async_list *list, struct io_kiocb *req)
 	ret = true;
 	spin_lock(&list->lock);
 	list_add_tail(&req->list, &list->list);
+	/*
+	 * Ensure we see a simultaneous modification from io_sq_wq_submit_work()
+	 */
+	smp_mb();
 	if (!atomic_read(&list->cnt)) {
 		list_del_init(&req->list);
 		ret = false;