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

Pull block layer fixes from Jens Axboe:
 "A collection of fixes for this merge window, either fixes for existing
  issues, or parts that were waiting for acks to come in. This pull
  request contains:

   - Allocation of nvme queues on the right node from Shaohua.

     This was ready long before the merge window, but waiting on an ack
     from Bjorn on the PCI bit. Now that we have that, the three patches
     can go in.

   - Two fixes for blk-mq-sched with nvmeof, which uses hctx specific
     request allocations. This caused an oops. One part from Sagi, one
     part from Omar.

   - A loop partition scan deadlock fix from Omar, fixing a regression
     in this merge window.

   - A three-patch series from Keith, closing up a hole on clearing out
     requests on shutdown/resume.

   - A stable fix for nbd from Josef, fixing a leak of sockets.

   - Two fixes for a regression in this window from Jan, fixing a
     problem with one of his earlier patches dealing with queue vs bdi
     life times.

   - A fix for a regression with virtio-blk, causing an IO stall if
     scheduling is used. From me.

   - A fix for an io context lock ordering problem. From me"

* 'for-linus' of git://git.kernel.dk/linux-block:
  block: Move bdi_unregister() to del_gendisk()
  blk-mq: ensure that bd->last is always set correctly
  block: don't call ioc_exit_icq() with the queue lock held for blk-mq
  block: Initialize bd_bdi on inode initialization
  loop: fix LO_FLAGS_PARTSCAN hang
  nvme: Complete all stuck requests
  blk-mq: Provide freeze queue timeout
  blk-mq: Export blk_mq_freeze_queue_wait
  nbd: stop leaking sockets
  blk-mq: move update of tags->rqs to __blk_mq_alloc_request()
  blk-mq: kill blk_mq_set_alloc_data()
  blk-mq: make blk_mq_alloc_request_hctx() allocate a scheduler request
  blk-mq-sched: Allocate sched reserved tags as specified in the original queue tagset
  nvme: allocate nvme_queue in correct node
  PCI: add an API to get node from vector
  blk-mq: allocate blk_mq_tags and requests in correct node

1 files changed, 31 insertions, 13 deletions

diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 6bfa396..63898d2 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -37,8 +37,8 @@ static void icq_free_icq_rcu(struct rcu_head *head)
 }
 
 /*
- * Exit an icq. Called with both ioc and q locked for sq, only ioc locked for
- * mq.
+ * Exit an icq. Called with ioc locked for blk-mq, and with both ioc
+ * and queue locked for legacy.
  */
 static void ioc_exit_icq(struct io_cq *icq)
 {
@@ -55,7 +55,10 @@ static void ioc_exit_icq(struct io_cq *icq)
 	icq->flags |= ICQ_EXITED;
 }
 
-/* Release an icq.  Called with both ioc and q locked. */
+/*
+ * Release an icq. Called with ioc locked for blk-mq, and with both ioc
+ * and queue locked for legacy.
+ */
 static void ioc_destroy_icq(struct io_cq *icq)
 {
 	struct io_context *ioc = icq->ioc;
@@ -63,7 +66,6 @@ static void ioc_destroy_icq(struct io_cq *icq)
 	struct elevator_type *et = q->elevator->type;
 
 	lockdep_assert_held(&ioc->lock);
-	lockdep_assert_held(q->queue_lock);
 
 	radix_tree_delete(&ioc->icq_tree, icq->q->id);
 	hlist_del_init(&icq->ioc_node);
@@ -223,24 +225,40 @@ void exit_io_context(struct task_struct *task)
 	put_io_context_active(ioc);
 }
 
+static void __ioc_clear_queue(struct list_head *icq_list)
+{
+	unsigned long flags;
+
+	while (!list_empty(icq_list)) {
+		struct io_cq *icq = list_entry(icq_list->next,
+					       struct io_cq, q_node);
+		struct io_context *ioc = icq->ioc;
+
+		spin_lock_irqsave(&ioc->lock, flags);
+		ioc_destroy_icq(icq);
+		spin_unlock_irqrestore(&ioc->lock, flags);
+	}
+}
+
 /**
  * ioc_clear_queue - break any ioc association with the specified queue
  * @q: request_queue being cleared
  *
- * Walk @q->icq_list and exit all io_cq's.  Must be called with @q locked.
+ * Walk @q->icq_list and exit all io_cq's.
  */
 void ioc_clear_queue(struct request_queue *q)
 {
-	lockdep_assert_held(q->queue_lock);
+	LIST_HEAD(icq_list);
 
-	while (!list_empty(&q->icq_list)) {
-		struct io_cq *icq = list_entry(q->icq_list.next,
-					       struct io_cq, q_node);
-		struct io_context *ioc = icq->ioc;
+	spin_lock_irq(q->queue_lock);
+	list_splice_init(&q->icq_list, &icq_list);
 
-		spin_lock(&ioc->lock);
-		ioc_destroy_icq(icq);
-		spin_unlock(&ioc->lock);
+	if (q->mq_ops) {
+		spin_unlock_irq(q->queue_lock);
+		__ioc_clear_queue(&icq_list);
+	} else {
+		__ioc_clear_queue(&icq_list);
+		spin_unlock_irq(q->queue_lock);
 	}
 }