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

Pull block layer fixes from Jens Axboe:
 "A small collection of fixes that has been gathered over the last few
  weeks.  This contains:

   - A one-liner fix for NVMe, fixing a missing list_head init that
     could makes us oops on hitting recovery at load time.

   - Two small blk-mq fixes:
        - Fixup a bad goto jump on error handling.
        - Fix for oopsing if running out of reserved tags.

   - A memory leak fix for NBD.

   - Two small writeback fixes from Tejun, fixing a missing init to
     INITIAL_JIFFIES, and a possible underflow introduced recently.

   - A core merge fixup in sg gap detection, where rq->biotail was
     indexed with the count of rq->bio"

* 'for-linus' of git://git.kernel.dk/linux-block:
  writeback: fix possible underflow in write bandwidth calculation
  NVMe: Initialize device list head before starting
  Fix bug in blk_rq_merge_ok
  blkmq: Fix NULL pointer deref when all reserved tags in
  blk-mq: fix use of incorrect goto label in blk_mq_init_queue error path
  nbd: fix possible memory leak
  writeback: add missing INITIAL_JIFFIES init in global_update_bandwidth()

6 files changed, 18 insertions, 12 deletions

diff --git a/block/blk-merge.c b/block/blk-merge.c
index fc1ff3b1ea1f..fd3fee81c23c 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -592,7 +592,7 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS)) {
 		struct bio_vec *bprev;
 
-		bprev = &rq->biotail->bi_io_vec[bio->bi_vcnt - 1];
+		bprev = &rq->biotail->bi_io_vec[rq->biotail->bi_vcnt - 1];
 		if (bvec_gap_to_prev(bprev, bio->bi_io_vec[0].bv_offset))
 			return false;
 	}
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index d53a764b05ea..be3290cc0644 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -278,9 +278,11 @@ static int bt_get(struct blk_mq_alloc_data *data,
 		/*
 		 * We're out of tags on this hardware queue, kick any
 		 * pending IO submits before going to sleep waiting for
-		 * some to complete.
+		 * some to complete. Note that hctx can be NULL here for
+		 * reserved tag allocation.
 		 */
-		blk_mq_run_hw_queue(hctx, false);
+		if (hctx)
+			blk_mq_run_hw_queue(hctx, false);
 
 		/*
 		 * Retry tag allocation after running the hardware queue,
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4f4bea21052e..b7b8933ec241 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1938,7 +1938,7 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 	 */
 	if (percpu_ref_init(&q->mq_usage_counter, blk_mq_usage_counter_release,
 			    PERCPU_REF_INIT_ATOMIC, GFP_KERNEL))
-		goto err_map;
+		goto err_mq_usage;
 
 	setup_timer(&q->timeout, blk_mq_rq_timer, (unsigned long) q);
 	blk_queue_rq_timeout(q, 30000);
@@ -1981,7 +1981,7 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 	blk_mq_init_cpu_queues(q, set->nr_hw_queues);
 
 	if (blk_mq_init_hw_queues(q, set))
-		goto err_hw;
+		goto err_mq_usage;
 
 	mutex_lock(&all_q_mutex);
 	list_add_tail(&q->all_q_node, &all_q_list);
@@ -1993,7 +1993,7 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 
 	return q;
 
-err_hw:
+err_mq_usage:
 	blk_cleanup_queue(q);
 err_hctxs:
 	kfree(map);
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 4bc2a5cb9935..a98c41f72c63 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -803,10 +803,6 @@ static int __init nbd_init(void)
 		return -EINVAL;
 	}
 
-	nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL);
-	if (!nbd_dev)
-		return -ENOMEM;
-
 	part_shift = 0;
 	if (max_part > 0) {
 		part_shift = fls(max_part);
@@ -828,6 +824,10 @@ static int __init nbd_init(void)
 	if (nbds_max > 1UL << (MINORBITS - part_shift))
 		return -EINVAL;
 
+	nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL);
+	if (!nbd_dev)
+		return -ENOMEM;
+
 	for (i = 0; i < nbds_max; i++) {
 		struct gendisk *disk = alloc_disk(1 << part_shift);
 		if (!disk)
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index ceb32dd52a6c..e23be20a3417 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -3003,6 +3003,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	}
 	get_device(dev->device);
 
+	INIT_LIST_HEAD(&dev->node);
 	INIT_WORK(&dev->probe_work, nvme_async_probe);
 	schedule_work(&dev->probe_work);
 	return 0;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 45e187b2d971..644bcb665773 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -857,8 +857,11 @@ static void bdi_update_write_bandwidth(struct backing_dev_info *bdi,
 	 *                   bw * elapsed + write_bandwidth * (period - elapsed)
 	 * write_bandwidth = ---------------------------------------------------
 	 *                                          period
+	 *
+	 * @written may have decreased due to account_page_redirty().
+	 * Avoid underflowing @bw calculation.
 	 */
-	bw = written - bdi->written_stamp;
+	bw = written - min(written, bdi->written_stamp);
 	bw *= HZ;
 	if (unlikely(elapsed > period)) {
 		do_div(bw, elapsed);
@@ -922,7 +925,7 @@ static void global_update_bandwidth(unsigned long thresh,
 				    unsigned long now)
 {
 	static DEFINE_SPINLOCK(dirty_lock);
-	static unsigned long update_time;
+	static unsigned long update_time = INITIAL_JIFFIES;
 
 	/*
 	 * check locklessly first to optimize away locking for the most time