Merge tag 'for-4.21/block-20181221' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "This is the main pull request for block/storage for 4.21.

  Larger than usual, it was a busy round with lots of goodies queued up.
  Most notable is the removal of the old IO stack, which has been a long
  time coming. No new features for a while, everything coming in this
  week has all been fixes for things that were previously merged.

  This contains:

   - Use atomic counters instead of semaphores for mtip32xx (Arnd)

   - Cleanup of the mtip32xx request setup (Christoph)

   - Fix for circular locking dependency in loop (Jan, Tetsuo)

   - bcache (Coly, Guoju, Shenghui)
      * Optimizations for writeback caching
      * Various fixes and improvements

   - nvme (Chaitanya, Christoph, Sagi, Jay, me, Keith)
      * host and target support for NVMe over TCP
      * Error log page support
      * Support for separate read/write/poll queues
      * Much improved polling
      * discard OOM fallback
      * Tracepoint improvements

   - lightnvm (Hans, Hua, Igor, Matias, Javier)
      * Igor added packed metadata to pblk. Now drives without metadata
        per LBA can be used as well.
      * Fix from Geert on uninitialized value on chunk metadata reads.
      * Fixes from Hans and Javier to pblk recovery and write path.
      * Fix from Hua Su to fix a race condition in the pblk recovery
        code.
      * Scan optimization added to pblk recovery from Zhoujie.
      * Small geometry cleanup from me.

   - Conversion of the last few drivers that used the legacy path to
     blk-mq (me)

   - Removal of legacy IO path in SCSI (me, Christoph)

   - Removal of legacy IO stack and schedulers (me)

   - Support for much better polling, now without interrupts at all.
     blk-mq adds support for multiple queue maps, which enables us to
     have a map per type. This in turn enables nvme to have separate
     completion queues for polling, which can then be interrupt-less.
     Also means we're ready for async polled IO, which is hopefully
     coming in the next release.

   - Killing of (now) unused block exports (Christoph)

   - Unification of the blk-rq-qos and blk-wbt wait handling (Josef)

   - Support for zoned testing with null_blk (Masato)

   - sx8 conversion to per-host tag sets (Christoph)

   - IO priority improvements (Damien)

   - mq-deadline zoned fix (Damien)

   - Ref count blkcg series (Dennis)

   - Lots of blk-mq improvements and speedups (me)

   - sbitmap scalability improvements (me)

   - Make core inflight IO accounting per-cpu (Mikulas)

   - Export timeout setting in sysfs (Weiping)

   - Cleanup the direct issue path (Jianchao)

   - Export blk-wbt internals in block debugfs for easier debugging
     (Ming)

   - Lots of other fixes and improvements"

* tag 'for-4.21/block-20181221' of git://git.kernel.dk/linux-block: (364 commits)
  kyber: use sbitmap add_wait_queue/list_del wait helpers
  sbitmap: add helpers for add/del wait queue handling
  block: save irq state in blkg_lookup_create()
  dm: don't reuse bio for flushes
  nvme-pci: trace SQ status on completions
  nvme-rdma: implement polling queue map
  nvme-fabrics: allow user to pass in nr_poll_queues
  nvme-fabrics: allow nvmf_connect_io_queue to poll
  nvme-core: optionally poll sync commands
  block: make request_to_qc_t public
  nvme-tcp: fix spelling mistake "attepmpt" -> "attempt"
  nvme-tcp: fix endianess annotations
  nvmet-tcp: fix endianess annotations
  nvme-pci: refactor nvme_poll_irqdisable to make sparse happy
  nvme-pci: only set nr_maps to 2 if poll queues are supported
  nvmet: use a macro for default error location
  nvmet: fix comparison of a u16 with -1
  blk-mq: enable IO poll if .nr_queues of type poll > 0
  blk-mq: change blk_mq_queue_busy() to blk_mq_queue_inflight()
  blk-mq: skip zero-queue maps in blk_mq_map_swqueue
  ...

6 files changed, 68 insertions, 27 deletions

diff --git a/fs/aio.c b/fs/aio.c
index 76f72509f8c5..0f99cad35ffe 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1438,17 +1438,22 @@ static int aio_prep_rw(struct kiocb *req, struct iocb *iocb)
 		ret = ioprio_check_cap(iocb->aio_reqprio);
 		if (ret) {
 			pr_debug("aio ioprio check cap error: %d\n", ret);
-			fput(req->ki_filp);
-			return ret;
+			goto out_fput;
 		}
 
 		req->ki_ioprio = iocb->aio_reqprio;
 	} else
-		req->ki_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0);
+		req->ki_ioprio = get_current_ioprio();
 
 	ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags);
 	if (unlikely(ret))
-		fput(req->ki_filp);
+		goto out_fput;
+
+	req->ki_flags &= ~IOCB_HIPRI; /* no one is going to poll for this I/O */
+	return 0;
+
+out_fput:
+	fput(req->ki_filp);
 	return ret;
 }
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index a80b4f0ee7c4..e1886cc7048f 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -181,7 +181,7 @@ static void blkdev_bio_end_io_simple(struct bio *bio)
 	struct task_struct *waiter = bio->bi_private;
 
 	WRITE_ONCE(bio->bi_private, NULL);
-	wake_up_process(waiter);
+	blk_wake_io_task(waiter);
 }
 
 static ssize_t
@@ -232,14 +232,18 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 		bio.bi_opf = dio_bio_write_op(iocb);
 		task_io_account_write(ret);
 	}
+	if (iocb->ki_flags & IOCB_HIPRI)
+		bio.bi_opf |= REQ_HIPRI;
 
 	qc = submit_bio(&bio);
 	for (;;) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
+		__set_current_state(TASK_UNINTERRUPTIBLE);
+
 		if (!READ_ONCE(bio.bi_private))
 			break;
+
 		if (!(iocb->ki_flags & IOCB_HIPRI) ||
-		    !blk_poll(bdev_get_queue(bdev), qc))
+		    !blk_poll(bdev_get_queue(bdev), qc, true))
 			io_schedule();
 	}
 	__set_current_state(TASK_RUNNING);
@@ -298,12 +302,13 @@ static void blkdev_bio_end_io(struct bio *bio)
 			}
 
 			dio->iocb->ki_complete(iocb, ret, 0);
-			bio_put(&dio->bio);
+			if (dio->multi_bio)
+				bio_put(&dio->bio);
 		} else {
 			struct task_struct *waiter = dio->waiter;
 
 			WRITE_ONCE(dio->waiter, NULL);
-			wake_up_process(waiter);
+			blk_wake_io_task(waiter);
 		}
 	}
 
@@ -328,6 +333,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 	struct blk_plug plug;
 	struct blkdev_dio *dio;
 	struct bio *bio;
+	bool is_poll = (iocb->ki_flags & IOCB_HIPRI) != 0;
 	bool is_read = (iov_iter_rw(iter) == READ), is_sync;
 	loff_t pos = iocb->ki_pos;
 	blk_qc_t qc = BLK_QC_T_NONE;
@@ -338,20 +344,27 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 		return -EINVAL;
 
 	bio = bio_alloc_bioset(GFP_KERNEL, nr_pages, &blkdev_dio_pool);
-	bio_get(bio); /* extra ref for the completion handler */
 
 	dio = container_of(bio, struct blkdev_dio, bio);
 	dio->is_sync = is_sync = is_sync_kiocb(iocb);
-	if (dio->is_sync)
+	if (dio->is_sync) {
 		dio->waiter = current;
-	else
+		bio_get(bio);
+	} else {
 		dio->iocb = iocb;
+	}
 
 	dio->size = 0;
 	dio->multi_bio = false;
 	dio->should_dirty = is_read && iter_is_iovec(iter);
 
-	blk_start_plug(&plug);
+	/*
+	 * Don't plug for HIPRI/polled IO, as those should go straight
+	 * to issue
+	 */
+	if (!is_poll)
+		blk_start_plug(&plug);
+
 	for (;;) {
 		bio_set_dev(bio, bdev);
 		bio->bi_iter.bi_sector = pos >> 9;
@@ -381,11 +394,21 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 
 		nr_pages = iov_iter_npages(iter, BIO_MAX_PAGES);
 		if (!nr_pages) {
+			if (iocb->ki_flags & IOCB_HIPRI)
+				bio->bi_opf |= REQ_HIPRI;
+
 			qc = submit_bio(bio);
 			break;
 		}
 
 		if (!dio->multi_bio) {
+			/*
+			 * AIO needs an extra reference to ensure the dio
+			 * structure which is embedded into the first bio
+			 * stays around.
+			 */
+			if (!is_sync)
+				bio_get(bio);
 			dio->multi_bio = true;
 			atomic_set(&dio->ref, 2);
 		} else {
@@ -395,18 +418,21 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 		submit_bio(bio);
 		bio = bio_alloc(GFP_KERNEL, nr_pages);
 	}
-	blk_finish_plug(&plug);
+
+	if (!is_poll)
+		blk_finish_plug(&plug);
 
 	if (!is_sync)
 		return -EIOCBQUEUED;
 
 	for (;;) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
+		__set_current_state(TASK_UNINTERRUPTIBLE);
+
 		if (!READ_ONCE(dio->waiter))
 			break;
 
 		if (!(iocb->ki_flags & IOCB_HIPRI) ||
-		    !blk_poll(bdev_get_queue(bdev), qc))
+		    !blk_poll(bdev_get_queue(bdev), qc, true))
 			io_schedule();
 	}
 	__set_current_state(TASK_RUNNING);
diff --git a/fs/buffer.c b/fs/buffer.c
index 1286c2b95498..d60d61e8ed7d 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -3060,11 +3060,6 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
 	 */
 	bio = bio_alloc(GFP_NOIO, 1);
 
-	if (wbc) {
-		wbc_init_bio(wbc, bio);
-		wbc_account_io(wbc, bh->b_page, bh->b_size);
-	}
-
 	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
 	bio_set_dev(bio, bh->b_bdev);
 	bio->bi_write_hint = write_hint;
@@ -3084,6 +3079,11 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
 		op_flags |= REQ_PRIO;
 	bio_set_op_attrs(bio, op, op_flags);
 
+	if (wbc) {
+		wbc_init_bio(wbc, bio);
+		wbc_account_io(wbc, bh->b_page, bh->b_size);
+	}
+
 	submit_bio(bio);
 	return 0;
 }
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 41a0e97252ae..dbc1a1f080ce 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -518,7 +518,7 @@ static struct bio *dio_await_one(struct dio *dio)
 		dio->waiter = current;
 		spin_unlock_irqrestore(&dio->bio_lock, flags);
 		if (!(dio->iocb->ki_flags & IOCB_HIPRI) ||
-		    !blk_poll(dio->bio_disk->queue, dio->bio_cookie))
+		    !blk_poll(dio->bio_disk->queue, dio->bio_cookie, true))
 			io_schedule();
 		/* wake up sets us TASK_RUNNING */
 		spin_lock_irqsave(&dio->bio_lock, flags);
@@ -1265,6 +1265,8 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 	} else {
 		dio->op = REQ_OP_READ;
 	}
+	if (iocb->ki_flags & IOCB_HIPRI)
+		dio->op_flags |= REQ_HIPRI;
 
 	/*
 	 * For AIO O_(D)SYNC writes we need to defer completions to a workqueue
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index db7590178dfc..2aa62d58d8dd 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -374,13 +374,13 @@ static int io_submit_init_bio(struct ext4_io_submit *io,
 	bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
 	if (!bio)
 		return -ENOMEM;
-	wbc_init_bio(io->io_wbc, bio);
 	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
 	bio_set_dev(bio, bh->b_bdev);
 	bio->bi_end_io = ext4_end_bio;
 	bio->bi_private = ext4_get_io_end(io->io_end);
 	io->io_bio = bio;
 	io->io_next_block = bh->b_blocknr;
+	wbc_init_bio(io->io_wbc, bio);
 	return 0;
 }
 
diff --git a/fs/iomap.c b/fs/iomap.c
index ce837d962d47..e87c288cd5ef 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -1543,7 +1543,7 @@ static void iomap_dio_bio_end_io(struct bio *bio)
 		if (dio->wait_for_completion) {
 			struct task_struct *waiter = dio->submit.waiter;
 			WRITE_ONCE(dio->submit.waiter, NULL);
-			wake_up_process(waiter);
+			blk_wake_io_task(waiter);
 		} else if (dio->flags & IOMAP_DIO_WRITE) {
 			struct inode *inode = file_inode(dio->iocb->ki_filp);
 
@@ -1571,6 +1571,7 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
 		unsigned len)
 {
 	struct page *page = ZERO_PAGE(0);
+	int flags = REQ_SYNC | REQ_IDLE;
 	struct bio *bio;
 
 	bio = bio_alloc(GFP_KERNEL, 1);
@@ -1579,9 +1580,12 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
 	bio->bi_private = dio;
 	bio->bi_end_io = iomap_dio_bio_end_io;
 
+	if (dio->iocb->ki_flags & IOCB_HIPRI)
+		flags |= REQ_HIPRI;
+
 	get_page(page);
 	__bio_add_page(bio, page, len, 0);
-	bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_SYNC | REQ_IDLE);
+	bio_set_op_attrs(bio, REQ_OP_WRITE, flags);
 
 	atomic_inc(&dio->ref);
 	return submit_bio(bio);
@@ -1687,6 +1691,9 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 				bio_set_pages_dirty(bio);
 		}
 
+		if (dio->iocb->ki_flags & IOCB_HIPRI)
+			bio->bi_opf |= REQ_HIPRI;
+
 		iov_iter_advance(dio->submit.iter, n);
 
 		dio->size += n;
@@ -1914,14 +1921,15 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 			return -EIOCBQUEUED;
 
 		for (;;) {
-			set_current_state(TASK_UNINTERRUPTIBLE);
+			__set_current_state(TASK_UNINTERRUPTIBLE);
+
 			if (!READ_ONCE(dio->submit.waiter))
 				break;
 
 			if (!(iocb->ki_flags & IOCB_HIPRI) ||
 			    !dio->submit.last_queue ||
 			    !blk_poll(dio->submit.last_queue,
-					 dio->submit.cookie))
+					 dio->submit.cookie, true))
 				io_schedule();
 		}
 		__set_current_state(TASK_RUNNING);