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
  ...

1 files changed, 97 insertions, 49 deletions

diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index f3501cdaf1a65..1921298563429 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -21,7 +21,7 @@
  *
  */
 #include <linux/slab.h>
-#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
 #include <linux/delay.h>
 #include <linux/scatterlist.h>
 #include <linux/bsg-lib.h>
@@ -31,6 +31,12 @@
 
 #define uptr64(val) ((void __user *)(uintptr_t)(val))
 
+struct bsg_set {
+	struct blk_mq_tag_set	tag_set;
+	bsg_job_fn		*job_fn;
+	bsg_timeout_fn		*timeout_fn;
+};
+
 static int bsg_transport_check_proto(struct sg_io_v4 *hdr)
 {
 	if (hdr->protocol != BSG_PROTOCOL_SCSI  ||
@@ -129,7 +135,7 @@ static void bsg_teardown_job(struct kref *kref)
 	kfree(job->request_payload.sg_list);
 	kfree(job->reply_payload.sg_list);
 
-	blk_end_request_all(rq, BLK_STS_OK);
+	blk_mq_end_request(rq, BLK_STS_OK);
 }
 
 void bsg_job_put(struct bsg_job *job)
@@ -157,15 +163,15 @@ void bsg_job_done(struct bsg_job *job, int result,
 {
 	job->result = result;
 	job->reply_payload_rcv_len = reply_payload_rcv_len;
-	blk_complete_request(blk_mq_rq_from_pdu(job));
+	blk_mq_complete_request(blk_mq_rq_from_pdu(job));
 }
 EXPORT_SYMBOL_GPL(bsg_job_done);
 
 /**
- * bsg_softirq_done - softirq done routine for destroying the bsg requests
+ * bsg_complete - softirq done routine for destroying the bsg requests
  * @rq: BSG request that holds the job to be destroyed
  */
-static void bsg_softirq_done(struct request *rq)
+static void bsg_complete(struct request *rq)
 {
 	struct bsg_job *job = blk_mq_rq_to_pdu(rq);
 
@@ -224,54 +230,48 @@ failjob_rls_job:
 }
 
 /**
- * bsg_request_fn - generic handler for bsg requests
- * @q: request queue to manage
+ * bsg_queue_rq - generic handler for bsg requests
+ * @hctx: hardware queue
+ * @bd: queue data
  *
  * On error the create_bsg_job function should return a -Exyz error value
  * that will be set to ->result.
  *
  * Drivers/subsys should pass this to the queue init function.
  */
-static void bsg_request_fn(struct request_queue *q)
-	__releases(q->queue_lock)
-	__acquires(q->queue_lock)
+static blk_status_t bsg_queue_rq(struct blk_mq_hw_ctx *hctx,
+				 const struct blk_mq_queue_data *bd)
 {
+	struct request_queue *q = hctx->queue;
 	struct device *dev = q->queuedata;
-	struct request *req;
+	struct request *req = bd->rq;
+	struct bsg_set *bset =
+		container_of(q->tag_set, struct bsg_set, tag_set);
 	int ret;
 
+	blk_mq_start_request(req);
+
 	if (!get_device(dev))
-		return;
-
-	while (1) {
-		req = blk_fetch_request(q);
-		if (!req)
-			break;
-		spin_unlock_irq(q->queue_lock);
-
-		if (!bsg_prepare_job(dev, req)) {
-			blk_end_request_all(req, BLK_STS_OK);
-			spin_lock_irq(q->queue_lock);
-			continue;
-		}
-
-		ret = q->bsg_job_fn(blk_mq_rq_to_pdu(req));
-		spin_lock_irq(q->queue_lock);
-		if (ret)
-			break;
-	}
+		return BLK_STS_IOERR;
+
+	if (!bsg_prepare_job(dev, req))
+		return BLK_STS_IOERR;
+
+	ret = bset->job_fn(blk_mq_rq_to_pdu(req));
+	if (ret)
+		return BLK_STS_IOERR;
 
-	spin_unlock_irq(q->queue_lock);
 	put_device(dev);
-	spin_lock_irq(q->queue_lock);
+	return BLK_STS_OK;
 }
 
 /* called right after the request is allocated for the request_queue */
-static int bsg_init_rq(struct request_queue *q, struct request *req, gfp_t gfp)
+static int bsg_init_rq(struct blk_mq_tag_set *set, struct request *req,
+		       unsigned int hctx_idx, unsigned int numa_node)
 {
 	struct bsg_job *job = blk_mq_rq_to_pdu(req);
 
-	job->reply = kzalloc(SCSI_SENSE_BUFFERSIZE, gfp);
+	job->reply = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_KERNEL);
 	if (!job->reply)
 		return -ENOMEM;
 	return 0;
@@ -289,13 +289,47 @@ static void bsg_initialize_rq(struct request *req)
 	job->dd_data = job + 1;
 }
 
-static void bsg_exit_rq(struct request_queue *q, struct request *req)
+static void bsg_exit_rq(struct blk_mq_tag_set *set, struct request *req,
+		       unsigned int hctx_idx)
 {
 	struct bsg_job *job = blk_mq_rq_to_pdu(req);
 
 	kfree(job->reply);
 }
 
+void bsg_remove_queue(struct request_queue *q)
+{
+	if (q) {
+		struct bsg_set *bset =
+			container_of(q->tag_set, struct bsg_set, tag_set);
+
+		bsg_unregister_queue(q);
+		blk_cleanup_queue(q);
+		blk_mq_free_tag_set(&bset->tag_set);
+		kfree(bset);
+	}
+}
+EXPORT_SYMBOL_GPL(bsg_remove_queue);
+
+static enum blk_eh_timer_return bsg_timeout(struct request *rq, bool reserved)
+{
+	struct bsg_set *bset =
+		container_of(rq->q->tag_set, struct bsg_set, tag_set);
+
+	if (!bset->timeout_fn)
+		return BLK_EH_DONE;
+	return bset->timeout_fn(rq);
+}
+
+static const struct blk_mq_ops bsg_mq_ops = {
+	.queue_rq		= bsg_queue_rq,
+	.init_request		= bsg_init_rq,
+	.exit_request		= bsg_exit_rq,
+	.initialize_rq_fn	= bsg_initialize_rq,
+	.complete		= bsg_complete,
+	.timeout		= bsg_timeout,
+};
+
 /**
  * bsg_setup_queue - Create and add the bsg hooks so we can receive requests
  * @dev: device to attach bsg device to
@@ -304,28 +338,38 @@ static void bsg_exit_rq(struct request_queue *q, struct request *req)
  * @dd_job_size: size of LLD data needed for each job
  */
 struct request_queue *bsg_setup_queue(struct device *dev, const char *name,
-		bsg_job_fn *job_fn, int dd_job_size)
+		bsg_job_fn *job_fn, bsg_timeout_fn *timeout, int dd_job_size)
 {
+	struct bsg_set *bset;
+	struct blk_mq_tag_set *set;
 	struct request_queue *q;
-	int ret;
+	int ret = -ENOMEM;
 
-	q = blk_alloc_queue(GFP_KERNEL);
-	if (!q)
+	bset = kzalloc(sizeof(*bset), GFP_KERNEL);
+	if (!bset)
 		return ERR_PTR(-ENOMEM);
-	q->cmd_size = sizeof(struct bsg_job) + dd_job_size;
-	q->init_rq_fn = bsg_init_rq;
-	q->exit_rq_fn = bsg_exit_rq;
-	q->initialize_rq_fn = bsg_initialize_rq;
-	q->request_fn = bsg_request_fn;
 
-	ret = blk_init_allocated_queue(q);
-	if (ret)
-		goto out_cleanup_queue;
+	bset->job_fn = job_fn;
+	bset->timeout_fn = timeout;
+
+	set = &bset->tag_set;
+	set->ops = &bsg_mq_ops,
+	set->nr_hw_queues = 1;
+	set->queue_depth = 128;
+	set->numa_node = NUMA_NO_NODE;
+	set->cmd_size = sizeof(struct bsg_job) + dd_job_size;
+	set->flags = BLK_MQ_F_NO_SCHED | BLK_MQ_F_BLOCKING;
+	if (blk_mq_alloc_tag_set(set))
+		goto out_tag_set;
+
+	q = blk_mq_init_queue(set);
+	if (IS_ERR(q)) {
+		ret = PTR_ERR(q);
+		goto out_queue;
+	}
 
 	q->queuedata = dev;
-	q->bsg_job_fn = job_fn;
 	blk_queue_flag_set(QUEUE_FLAG_BIDI, q);
-	blk_queue_softirq_done(q, bsg_softirq_done);
 	blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT);
 
 	ret = bsg_register_queue(q, dev, name, &bsg_transport_ops);
@@ -338,6 +382,10 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name,
 	return q;
 out_cleanup_queue:
 	blk_cleanup_queue(q);
+out_queue:
+	blk_mq_free_tag_set(set);
+out_tag_set:
+	kfree(bset);
 	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(bsg_setup_queue);