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

Pull block layer fixes from Jens Axboe:
 "A small collection of fixes for the current series.  This contains:

   - Two fixes for xen-blkfront, from Bob Liu.

   - A bug fix for NVMe, releasing only the specific resources we
     requested.

   - Fix for a debugfs flags entry for nbd, from Josef.

   - Plug fix from Omar, fixing up a case of code being switched between
     two functions.

   - A missing bio_put() for the new discard callers of
     submit_bio_wait(), fixing a regression causing a leak of the bio.
     From Shaun.

   - Improve dirty limit calculation precision in the writeback code,
     fixing a case where setting a limit lower than 1% of memory would
     end up being zero.  From Tejun"

* 'for-linus' of git://git.kernel.dk/linux-block:
  NVMe: Only release requested regions
  xen-blkfront: fix resume issues after a migration
  xen-blkfront: don't call talk_to_blkback when already connected to blkback
  nbd: pass the nbd pointer for flags debugfs
  block: missing bio_put following submit_bio_wait
  blk-mq: really fix plug list flushing for nomerge queues
  writeback: use higher precision calculation in domain_dirty_limits()

block/blk-lib.c

@@ -113,6 +113,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		ret = submit_bio_wait(type, bio);
 		if (ret == -EOPNOTSUPP)
 			ret = 0;
+		bio_put(bio);
 	}
 	blk_finish_plug(&plug);
 
@@ -165,8 +166,10 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 		}
 	}
 
-	if (bio)
+	if (bio) {
 		ret = submit_bio_wait(REQ_WRITE | REQ_WRITE_SAME, bio);
+		bio_put(bio);
+	}
 	return ret != -EOPNOTSUPP ? ret : 0;
 }
 EXPORT_SYMBOL(blkdev_issue_write_same);
@@ -206,8 +209,11 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 		}
 	}
 
-	if (bio)
+	if (bio) {
-		return submit_bio_wait(WRITE, bio);
+		ret = submit_bio_wait(WRITE, bio);
+		bio_put(bio);
+		return ret;
+	}
 	return 0;
 }
 

block/blk-mq.c

@@ -1262,12 +1262,9 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 	blk_queue_split(q, &bio, q->bio_split);
 
-	if (!is_flush_fua && !blk_queue_nomerges(q)) {
+	if (!is_flush_fua && !blk_queue_nomerges(q) &&
-		if (blk_attempt_plug_merge(q, bio, &request_count,
+	    blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
-					   &same_queue_rq))
+		return BLK_QC_T_NONE;
-			return BLK_QC_T_NONE;
-	} else
-		request_count = blk_plug_queued_count(q);
 
 	rq = blk_mq_map_request(q, bio, &data);
 	if (unlikely(!rq))
@@ -1358,9 +1355,11 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 
 	blk_queue_split(q, &bio, q->bio_split);
 
-	if (!is_flush_fua && !blk_queue_nomerges(q) &&
+	if (!is_flush_fua && !blk_queue_nomerges(q)) {
-	    blk_attempt_plug_merge(q, bio, &request_count, NULL))
+		if (blk_attempt_plug_merge(q, bio, &request_count, NULL))
-		return BLK_QC_T_NONE;
+			return BLK_QC_T_NONE;
+	} else
+		request_count = blk_plug_queued_count(q);
 
 	rq = blk_mq_map_request(q, bio, &data);
 	if (unlikely(!rq))

drivers/block/nbd.c

@@ -941,7 +941,7 @@ static int nbd_dev_dbg_init(struct nbd_device *nbd)
 	debugfs_create_u64("size_bytes", 0444, dir, &nbd->bytesize);
 	debugfs_create_u32("timeout", 0444, dir, &nbd->xmit_timeout);
 	debugfs_create_u32("blocksize", 0444, dir, &nbd->blksize);
-	debugfs_create_file("flags", 0444, dir, &nbd, &nbd_dbg_flags_ops);
+	debugfs_create_file("flags", 0444, dir, nbd, &nbd_dbg_flags_ops);
 
 	return 0;
 }

drivers/block/xen-blkfront.c

@@ -874,8 +874,12 @@ static int blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
 			  const struct blk_mq_queue_data *qd)
 {
 	unsigned long flags;
-	struct blkfront_ring_info *rinfo = (struct blkfront_ring_info *)hctx->driver_data;
+	int qid = hctx->queue_num;
+	struct blkfront_info *info = hctx->queue->queuedata;
+	struct blkfront_ring_info *rinfo = NULL;
 
+	BUG_ON(info->nr_rings <= qid);
+	rinfo = &info->rinfo[qid];
 	blk_mq_start_request(qd->rq);
 	spin_lock_irqsave(&rinfo->ring_lock, flags);
 	if (RING_FULL(&rinfo->ring))
@@ -901,20 +905,9 @@ out_busy:
 	return BLK_MQ_RQ_QUEUE_BUSY;
 }
 
-static int blk_mq_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
-			    unsigned int index)
-{
-	struct blkfront_info *info = (struct blkfront_info *)data;
-
-	BUG_ON(info->nr_rings <= index);
-	hctx->driver_data = &info->rinfo[index];
-	return 0;
-}
-
 static struct blk_mq_ops blkfront_mq_ops = {
 	.queue_rq = blkif_queue_rq,
 	.map_queue = blk_mq_map_queue,
-	.init_hctx = blk_mq_init_hctx,
 };
 
 static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
@@ -950,6 +943,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
 		return PTR_ERR(rq);
 	}
 
+	rq->queuedata = info;
 	queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq);
 
 	if (info->feature_discard) {
@@ -2149,6 +2143,8 @@ static int blkfront_resume(struct xenbus_device *dev)
 		return err;
 
 	err = talk_to_blkback(dev, info);
+	if (!err)
+		blk_mq_update_nr_hw_queues(&info->tag_set, info->nr_rings);
 
 	/*
 	 * We have to wait for the backend to switch to
@@ -2485,10 +2481,23 @@ static void blkback_changed(struct xenbus_device *dev,
 		break;
 
 	case XenbusStateConnected:
-		if (dev->state != XenbusStateInitialised) {
+		/*
+		 * talk_to_blkback sets state to XenbusStateInitialised
+		 * and blkfront_connect sets it to XenbusStateConnected
+		 * (if connection went OK).
+		 *
+		 * If the backend (or toolstack) decides to poke at backend
+		 * state (and re-trigger the watch by setting the state repeatedly
+		 * to XenbusStateConnected (4)) we need to deal with this.
+		 * This is allowed as this is used to communicate to the guest
+		 * that the size of disk has changed!
+		 */
+		if ((dev->state != XenbusStateInitialised) &&
+		    (dev->state != XenbusStateConnected)) {
 			if (talk_to_blkback(dev, info))
 				break;
 		}
+
 		blkfront_connect(info);
 		break;
 

drivers/nvme/host/pci.c

@@ -1679,9 +1679,14 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 
 static void nvme_dev_unmap(struct nvme_dev *dev)
 {
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
+	int bars;
+
 	if (dev->bar)
 		iounmap(dev->bar);
-	pci_release_regions(to_pci_dev(dev->dev));
+
+	bars = pci_select_bars(pdev, IORESOURCE_MEM);
+	pci_release_selected_regions(pdev, bars);
 }
 
 static void nvme_pci_disable(struct nvme_dev *dev)
@@ -1924,7 +1929,7 @@ static int nvme_dev_map(struct nvme_dev *dev)
 
        return 0;
   release:
-       pci_release_regions(pdev);
+       pci_release_selected_regions(pdev, bars);
        return -ENODEV;
 }
 

mm/page-writeback.c

@@ -373,8 +373,9 @@ static void domain_dirty_limits(struct dirty_throttle_control *dtc)
 	struct dirty_throttle_control *gdtc = mdtc_gdtc(dtc);
 	unsigned long bytes = vm_dirty_bytes;
 	unsigned long bg_bytes = dirty_background_bytes;
-	unsigned long ratio = vm_dirty_ratio;
+	/* convert ratios to per-PAGE_SIZE for higher precision */
-	unsigned long bg_ratio = dirty_background_ratio;
+	unsigned long ratio = (vm_dirty_ratio * PAGE_SIZE) / 100;
+	unsigned long bg_ratio = (dirty_background_ratio * PAGE_SIZE) / 100;
 	unsigned long thresh;
 	unsigned long bg_thresh;
 	struct task_struct *tsk;
@@ -386,26 +387,28 @@ static void domain_dirty_limits(struct dirty_throttle_control *dtc)
 		/*
 		 * The byte settings can't be applied directly to memcg
 		 * domains.  Convert them to ratios by scaling against
-		 * globally available memory.
+		 * globally available memory.  As the ratios are in
+		 * per-PAGE_SIZE, they can be obtained by dividing bytes by
+		 * number of pages.
 		 */
 		if (bytes)
-			ratio = min(DIV_ROUND_UP(bytes, PAGE_SIZE) * 100 /
+			ratio = min(DIV_ROUND_UP(bytes, global_avail),
-				    global_avail, 100UL);
+				    PAGE_SIZE);
 		if (bg_bytes)
-			bg_ratio = min(DIV_ROUND_UP(bg_bytes, PAGE_SIZE) * 100 /
+			bg_ratio = min(DIV_ROUND_UP(bg_bytes, global_avail),
-				       global_avail, 100UL);
+				       PAGE_SIZE);
 		bytes = bg_bytes = 0;
 	}
 
 	if (bytes)
 		thresh = DIV_ROUND_UP(bytes, PAGE_SIZE);
 	else
-		thresh = (ratio * available_memory) / 100;
+		thresh = (ratio * available_memory) / PAGE_SIZE;
 
 	if (bg_bytes)
 		bg_thresh = DIV_ROUND_UP(bg_bytes, PAGE_SIZE);
 	else
-		bg_thresh = (bg_ratio * available_memory) / 100;
+		bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE;
 
 	if (bg_thresh >= thresh)
 		bg_thresh = thresh / 2;