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, 24 insertions, 11 deletions

diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index aafb44224c89..3f9c3f4ac44c 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -15,6 +15,18 @@
 
 static void blk_mq_sysfs_release(struct kobject *kobj)
 {
+	struct blk_mq_ctxs *ctxs = container_of(kobj, struct blk_mq_ctxs, kobj);
+
+	free_percpu(ctxs->queue_ctx);
+	kfree(ctxs);
+}
+
+static void blk_mq_ctx_sysfs_release(struct kobject *kobj)
+{
+	struct blk_mq_ctx *ctx = container_of(kobj, struct blk_mq_ctx, kobj);
+
+	/* ctx->ctxs won't be released until all ctx are freed */
+	kobject_put(&ctx->ctxs->kobj);
 }
 
 static void blk_mq_hw_sysfs_release(struct kobject *kobj)
@@ -203,7 +215,7 @@ static struct kobj_type blk_mq_ktype = {
 static struct kobj_type blk_mq_ctx_ktype = {
 	.sysfs_ops	= &blk_mq_sysfs_ops,
 	.default_attrs	= default_ctx_attrs,
-	.release	= blk_mq_sysfs_release,
+	.release	= blk_mq_ctx_sysfs_release,
 };
 
 static struct kobj_type blk_mq_hw_ktype = {
@@ -235,7 +247,7 @@ static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx)
 	if (!hctx->nr_ctx)
 		return 0;
 
-	ret = kobject_add(&hctx->kobj, &q->mq_kobj, "%u", hctx->queue_num);
+	ret = kobject_add(&hctx->kobj, q->mq_kobj, "%u", hctx->queue_num);
 	if (ret)
 		return ret;
 
@@ -258,8 +270,8 @@ void blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
 	queue_for_each_hw_ctx(q, hctx, i)
 		blk_mq_unregister_hctx(hctx);
 
-	kobject_uevent(&q->mq_kobj, KOBJ_REMOVE);
-	kobject_del(&q->mq_kobj);
+	kobject_uevent(q->mq_kobj, KOBJ_REMOVE);
+	kobject_del(q->mq_kobj);
 	kobject_put(&dev->kobj);
 
 	q->mq_sysfs_init_done = false;
@@ -279,7 +291,7 @@ void blk_mq_sysfs_deinit(struct request_queue *q)
 		ctx = per_cpu_ptr(q->queue_ctx, cpu);
 		kobject_put(&ctx->kobj);
 	}
-	kobject_put(&q->mq_kobj);
+	kobject_put(q->mq_kobj);
 }
 
 void blk_mq_sysfs_init(struct request_queue *q)
@@ -287,10 +299,12 @@ void blk_mq_sysfs_init(struct request_queue *q)
 	struct blk_mq_ctx *ctx;
 	int cpu;
 
-	kobject_init(&q->mq_kobj, &blk_mq_ktype);
+	kobject_init(q->mq_kobj, &blk_mq_ktype);
 
 	for_each_possible_cpu(cpu) {
 		ctx = per_cpu_ptr(q->queue_ctx, cpu);
+
+		kobject_get(q->mq_kobj);
 		kobject_init(&ctx->kobj, &blk_mq_ctx_ktype);
 	}
 }
@@ -303,11 +317,11 @@ int __blk_mq_register_dev(struct device *dev, struct request_queue *q)
 	WARN_ON_ONCE(!q->kobj.parent);
 	lockdep_assert_held(&q->sysfs_lock);
 
-	ret = kobject_add(&q->mq_kobj, kobject_get(&dev->kobj), "%s", "mq");
+	ret = kobject_add(q->mq_kobj, kobject_get(&dev->kobj), "%s", "mq");
 	if (ret < 0)
 		goto out;
 
-	kobject_uevent(&q->mq_kobj, KOBJ_ADD);
+	kobject_uevent(q->mq_kobj, KOBJ_ADD);
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		ret = blk_mq_register_hctx(hctx);
@@ -324,8 +338,8 @@ unreg:
 	while (--i >= 0)
 		blk_mq_unregister_hctx(q->queue_hw_ctx[i]);
 
-	kobject_uevent(&q->mq_kobj, KOBJ_REMOVE);
-	kobject_del(&q->mq_kobj);
+	kobject_uevent(q->mq_kobj, KOBJ_REMOVE);
+	kobject_del(q->mq_kobj);
 	kobject_put(&dev->kobj);
 	return ret;
 }
@@ -340,7 +354,6 @@ int blk_mq_register_dev(struct device *dev, struct request_queue *q)
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(blk_mq_register_dev);
 
 void blk_mq_sysfs_unregister(struct request_queue *q)
 {