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

Pull block IO fixes from Jens Axboe:
 "A few fixes that I collected as post-merge.

  I was going to wait a bit with sending this out, but the O_DIRECT fix
  should really go in sooner rather than later"

* 'for-linus' of git://git.kernel.dk/linux-block:
  blk-mq: Fix failed allocation path when mapping queues
  blk-mq: Avoid memory reclaim when remapping queues
  block_dev: don't update file access position for sync direct IO
  nvme/pci: Log PCI_STATUS when the controller dies
  block_dev: don't test bdev->bd_contains when it is not stable

3 files changed, 45 insertions, 16 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index d79fdc11b1ee..4bf850e8d6b5 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1605,7 +1605,7 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 	INIT_LIST_HEAD(&tags->page_list);
 
 	tags->rqs = kzalloc_node(set->queue_depth * sizeof(struct request *),
-				 GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY,
+				 GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
 				 set->numa_node);
 	if (!tags->rqs) {
 		blk_mq_free_tags(tags);
@@ -1631,7 +1631,7 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 
 		do {
 			page = alloc_pages_node(set->numa_node,
-				GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO,
+				GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO,
 				this_order);
 			if (page)
 				break;
@@ -1652,7 +1652,7 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 		 * Allow kmemleak to scan these pages as they contain pointers
 		 * to additional allocations like via ops->init_request().
 		 */
-		kmemleak_alloc(p, order_to_size(this_order), 1, GFP_KERNEL);
+		kmemleak_alloc(p, order_to_size(this_order), 1, GFP_NOIO);
 		entries_per_page = order_to_size(this_order) / rq_size;
 		to_do = min(entries_per_page, set->queue_depth - i);
 		left -= to_do * rq_size;
@@ -1870,7 +1870,7 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
 static void blk_mq_map_swqueue(struct request_queue *q,
 			       const struct cpumask *online_mask)
 {
-	unsigned int i;
+	unsigned int i, hctx_idx;
 	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx;
 	struct blk_mq_tag_set *set = q->tag_set;
@@ -1893,6 +1893,21 @@ static void blk_mq_map_swqueue(struct request_queue *q,
 		if (!cpumask_test_cpu(i, online_mask))
 			continue;
 
+		hctx_idx = q->mq_map[i];
+		/* unmapped hw queue can be remapped after CPU topo changed */
+		if (!set->tags[hctx_idx]) {
+			set->tags[hctx_idx] = blk_mq_init_rq_map(set, hctx_idx);
+
+			/*
+			 * If tags initialization fail for some hctx,
+			 * that hctx won't be brought online.  In this
+			 * case, remap the current ctx to hctx[0] which
+			 * is guaranteed to always have tags allocated
+			 */
+			if (!set->tags[hctx_idx])
+				q->mq_map[i] = 0;
+		}
+
 		ctx = per_cpu_ptr(q->queue_ctx, i);
 		hctx = blk_mq_map_queue(q, i);
 
@@ -1909,7 +1924,11 @@ static void blk_mq_map_swqueue(struct request_queue *q,
 		 * disable it and free the request entries.
 		 */
 		if (!hctx->nr_ctx) {
-			if (set->tags[i]) {
+			/* Never unmap queue 0.  We need it as a
+			 * fallback in case of a new remap fails
+			 * allocation
+			 */
+			if (i && set->tags[i]) {
 				blk_mq_free_rq_map(set, set->tags[i], i);
 				set->tags[i] = NULL;
 			}
@@ -1917,9 +1936,6 @@ static void blk_mq_map_swqueue(struct request_queue *q,
 			continue;
 		}
 
-		/* unmapped hw queue can be remapped after CPU topo changed */
-		if (!set->tags[i])
-			set->tags[i] = blk_mq_init_rq_map(set, i);
 		hctx->tags = set->tags[i];
 		WARN_ON(!hctx->tags);
 
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index d6e6bce93d0c..2fd7dc2e8fc4 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1282,6 +1282,24 @@ static bool nvme_should_reset(struct nvme_dev *dev, u32 csts)
 	return true;
 }
 
+static void nvme_warn_reset(struct nvme_dev *dev, u32 csts)
+{
+	/* Read a config register to help see what died. */
+	u16 pci_status;
+	int result;
+
+	result = pci_read_config_word(to_pci_dev(dev->dev), PCI_STATUS,
+				      &pci_status);
+	if (result == PCIBIOS_SUCCESSFUL)
+		dev_warn(dev->dev,
+			 "controller is down; will reset: CSTS=0x%x, PCI_STATUS=0x%hx\n",
+			 csts, pci_status);
+	else
+		dev_warn(dev->dev,
+			 "controller is down; will reset: CSTS=0x%x, PCI_STATUS read failed (%d)\n",
+			 csts, result);
+}
+
 static void nvme_watchdog_timer(unsigned long data)
 {
 	struct nvme_dev *dev = (struct nvme_dev *)data;
@@ -1290,9 +1308,7 @@ static void nvme_watchdog_timer(unsigned long data)
 	/* Skip controllers under certain specific conditions. */
 	if (nvme_should_reset(dev, csts)) {
 		if (!nvme_reset(dev))
-			dev_warn(dev->dev,
-				"Failed status: 0x%x, reset controller.\n",
-				csts);
+			nvme_warn_reset(dev, csts);
 		return;
 	}
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 95acbd2ebc5d..7c4507224ed6 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -264,7 +264,6 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 
 	if (unlikely(bio.bi_error))
 		return bio.bi_error;
-	iocb->ki_pos += ret;
 	return ret;
 }
 
@@ -411,10 +410,8 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 	__set_current_state(TASK_RUNNING);
 
 	ret = dio->bio.bi_error;
-	if (likely(!ret)) {
+	if (likely(!ret))
 		ret = dio->size;
-		iocb->ki_pos += ret;
-	}
 
 	bio_put(&dio->bio);
 	return ret;
@@ -1089,7 +1086,7 @@ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole,
 		return true;	 /* already a holder */
 	else if (bdev->bd_holder != NULL)
 		return false; 	 /* held by someone else */
-	else if (bdev->bd_contains == bdev)
+	else if (whole == bdev)
 		return true;  	 /* is a whole device which isn't held */
 
 	else if (whole->bd_holder == bd_may_claim)