Merge tag 'block-5.9-2020-09-04' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "A bit larger than usual this week, mostly due to the NVMe fixes
  arriving late for -rc3 and hence didn't make last weeks pull request.

   - NVMe:
        - instance leak and io boundary fixes from Keith
        - fc locking fix from Christophe
        - various tcp/rdma reset during traffic fixes from Sagi
        - pci use-after-free fix from Tong
        - tcp target null deref fix from Ziye

   - Locking fix for partition removal (Christoph)

   - Ensure bdi->io_pages is always set (me)

   - Fixup for hd struct reference (Ming)

   - Fix for zero length bvecs (Ming)

   - Two small blk-iocost fixes (Tejun)"

* tag 'block-5.9-2020-09-04' of git://git.kernel.dk/linux-block:
  block: allow for_each_bvec to support zero len bvec
  blk-stat: make q->stats->lock irqsafe
  blk-iocost: ioc_pd_free() shouldn't assume irq disabled
  block: fix locking in bdev_del_partition
  block: release disk reference in hd_struct_free_work
  block: ensure bdi->io_pages is always initialized
  nvme-pci: cancel nvme device request before disabling
  nvme: only use power of two io boundaries
  nvme: fix controller instance leak
  nvmet-fc: Fix a missed _irqsave version of spin_lock in 'nvmet_fc_fod_op_done()'
  nvme: Fix NULL dereference for pci nvme controllers
  nvme-rdma: fix reset hang if controller died in the middle of a reset
  nvme-rdma: fix timeout handler
  nvme-rdma: serialize controller teardown sequences
  nvme-tcp: fix reset hang if controller died in the middle of a reset
  nvme-tcp: fix timeout handler
  nvme-tcp: serialize controller teardown sequences
  nvme: have nvme_wait_freeze_timeout return if it timed out
  nvme-fabrics: don't check state NVME_CTRL_NEW for request acceptance
  nvmet-tcp: Fix NULL dereference when a connect data comes in h2cdata pdu

4 files changed, 37 insertions, 23 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index d9d632639bd1..10c08ac50697 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -539,6 +539,7 @@ struct request_queue *blk_alloc_queue(int node_id)
 		goto fail_stats;
 
 	q->backing_dev_info->ra_pages = VM_READAHEAD_PAGES;
+	q->backing_dev_info->io_pages = VM_READAHEAD_PAGES;
 	q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK;
 	q->node = node_id;
 
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 413e0b5c8e6b..d37b55db2409 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -2092,14 +2092,15 @@ static void ioc_pd_free(struct blkg_policy_data *pd)
 {
 	struct ioc_gq *iocg = pd_to_iocg(pd);
 	struct ioc *ioc = iocg->ioc;
+	unsigned long flags;
 
 	if (ioc) {
-		spin_lock(&ioc->lock);
+		spin_lock_irqsave(&ioc->lock, flags);
 		if (!list_empty(&iocg->active_list)) {
 			propagate_active_weight(iocg, 0, 0);
 			list_del_init(&iocg->active_list);
 		}
-		spin_unlock(&ioc->lock);
+		spin_unlock_irqrestore(&ioc->lock, flags);
 
 		hrtimer_cancel(&iocg->waitq_timer);
 		hrtimer_cancel(&iocg->delay_timer);
diff --git a/block/blk-stat.c b/block/blk-stat.c
index 7da302ff88d0..ae3dd1fb8e61 100644
--- a/block/blk-stat.c
+++ b/block/blk-stat.c
@@ -137,6 +137,7 @@ void blk_stat_add_callback(struct request_queue *q,
 			   struct blk_stat_callback *cb)
 {
 	unsigned int bucket;
+	unsigned long flags;
 	int cpu;
 
 	for_each_possible_cpu(cpu) {
@@ -147,20 +148,22 @@ void blk_stat_add_callback(struct request_queue *q,
 			blk_rq_stat_init(&cpu_stat[bucket]);
 	}
 
-	spin_lock(&q->stats->lock);
+	spin_lock_irqsave(&q->stats->lock, flags);
 	list_add_tail_rcu(&cb->list, &q->stats->callbacks);
 	blk_queue_flag_set(QUEUE_FLAG_STATS, q);
-	spin_unlock(&q->stats->lock);
+	spin_unlock_irqrestore(&q->stats->lock, flags);
 }
 
 void blk_stat_remove_callback(struct request_queue *q,
 			      struct blk_stat_callback *cb)
 {
-	spin_lock(&q->stats->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->stats->lock, flags);
 	list_del_rcu(&cb->list);
 	if (list_empty(&q->stats->callbacks) && !q->stats->enable_accounting)
 		blk_queue_flag_clear(QUEUE_FLAG_STATS, q);
-	spin_unlock(&q->stats->lock);
+	spin_unlock_irqrestore(&q->stats->lock, flags);
 
 	del_timer_sync(&cb->timer);
 }
@@ -183,10 +186,12 @@ void blk_stat_free_callback(struct blk_stat_callback *cb)
 
 void blk_stat_enable_accounting(struct request_queue *q)
 {
-	spin_lock(&q->stats->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->stats->lock, flags);
 	q->stats->enable_accounting = true;
 	blk_queue_flag_set(QUEUE_FLAG_STATS, q);
-	spin_unlock(&q->stats->lock);
+	spin_unlock_irqrestore(&q->stats->lock, flags);
 }
 EXPORT_SYMBOL_GPL(blk_stat_enable_accounting);
 
diff --git a/block/partitions/core.c b/block/partitions/core.c
index e62a98a8eeb7..5b4869c08fb3 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -278,6 +278,15 @@ static void hd_struct_free_work(struct work_struct *work)
 {
 	struct hd_struct *part =
 		container_of(to_rcu_work(work), struct hd_struct, rcu_work);
+	struct gendisk *disk = part_to_disk(part);
+
+	/*
+	 * Release the disk reference acquired in delete_partition here.
+	 * We can't release it in hd_struct_free because the final put_device
+	 * needs process context and thus can't be run directly from a
+	 * percpu_ref ->release handler.
+	 */
+	put_device(disk_to_dev(disk));
 
 	part->start_sect = 0;
 	part->nr_sects = 0;
@@ -293,7 +302,6 @@ static void hd_struct_free(struct percpu_ref *ref)
 		rcu_dereference_protected(disk->part_tbl, 1);
 
 	rcu_assign_pointer(ptbl->last_lookup, NULL);
-	put_device(disk_to_dev(disk));
 
 	INIT_RCU_WORK(&part->rcu_work, hd_struct_free_work);
 	queue_rcu_work(system_wq, &part->rcu_work);
@@ -524,19 +532,20 @@ int bdev_add_partition(struct block_device *bdev, int partno,
 int bdev_del_partition(struct block_device *bdev, int partno)
 {
 	struct block_device *bdevp;
-	struct hd_struct *part;
-	int ret = 0;
+	struct hd_struct *part = NULL;
+	int ret;
 
-	part = disk_get_part(bdev->bd_disk, partno);
-	if (!part)
-		return -ENXIO;
-
-	ret = -ENOMEM;
-	bdevp = bdget(part_devt(part));
+	bdevp = bdget_disk(bdev->bd_disk, partno);
 	if (!bdevp)
-		goto out_put_part;
+		return -ENOMEM;
 
 	mutex_lock(&bdevp->bd_mutex);
+	mutex_lock_nested(&bdev->bd_mutex, 1);
+
+	ret = -ENXIO;
+	part = disk_get_part(bdev->bd_disk, partno);
+	if (!part)
+		goto out_unlock;
 
 	ret = -EBUSY;
 	if (bdevp->bd_openers)
@@ -545,16 +554,14 @@ int bdev_del_partition(struct block_device *bdev, int partno)
 	sync_blockdev(bdevp);
 	invalidate_bdev(bdevp);
 
-	mutex_lock_nested(&bdev->bd_mutex, 1);
 	delete_partition(bdev->bd_disk, part);
-	mutex_unlock(&bdev->bd_mutex);
-
 	ret = 0;
 out_unlock:
+	mutex_unlock(&bdev->bd_mutex);
 	mutex_unlock(&bdevp->bd_mutex);
 	bdput(bdevp);
-out_put_part:
-	disk_put_part(part);
+	if (part)
+		disk_put_part(part);
 	return ret;
 }