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

Pull more block layer fixes from Jens Axboe:
 "I wasn't going to send off a new pull before next week, but the blk
  flush fix from Jan from the other day introduced a regression.  It's
  rare enough not to have hit during testing, since it requires both a
  device that rejects the first flush, and bad timing while it does
  that.  But since someone did hit it, let's get the revert into 4.4-rc3
  so we don't have a released rc with that known issue.

  Apart from that revert, three other fixes:

   - From Christoph, a fix for a missing unmap in NVMe request
     preparation.

   - An NVMe fix from Nishanth that fixes data corruption on powerpc.

   - Also from Christoph, fix a list_del() attempt on blk-mq that didn't
     have a matching list_add() at timer start"

* 'for-linus' of git://git.kernel.dk/linux-block:
  Revert "blk-flush: Queue through IO scheduler when flush not required"
  block: fix blk_abort_request for blk-mq drivers
  nvme: add missing unmaps in nvme_queue_rq
  NVMe: default to 4k device page size

block/blk-flush.c

@@ -422,7 +422,7 @@ void blk_insert_flush(struct request *rq)
 		if (q->mq_ops) {
 			blk_mq_insert_request(rq, false, false, true);
 		} else
-			q->elevator->type->ops.elevator_add_req_fn(q, rq);
+			list_add_tail(&rq->queuelist, &q->queue_head);
 		return;
 	}
 

block/blk-timeout.c

@@ -158,11 +158,13 @@ void blk_abort_request(struct request *req)
 {
 	if (blk_mark_rq_complete(req))
 		return;
-	blk_delete_timer(req);
-	if (req->q->mq_ops)
+
+	if (req->q->mq_ops) {
 		blk_mq_rq_timed_out(req, false);
-	else
+	} else {
+		blk_delete_timer(req);
 		blk_rq_timed_out(req);
+	}
 }
 EXPORT_SYMBOL_GPL(blk_abort_request);
 

drivers/nvme/host/pci.c

@@ -896,21 +896,30 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 			goto retry_cmd;
 		}
 		if (blk_integrity_rq(req)) {
-			if (blk_rq_count_integrity_sg(req->q, req->bio) != 1)
+			if (blk_rq_count_integrity_sg(req->q, req->bio) != 1) {
+				dma_unmap_sg(dev->dev, iod->sg, iod->nents,
+						dma_dir);
 				goto error_cmd;
+			}
 
 			sg_init_table(iod->meta_sg, 1);
 			if (blk_rq_map_integrity_sg(
-					req->q, req->bio, iod->meta_sg) != 1)
+					req->q, req->bio, iod->meta_sg) != 1) {
+				dma_unmap_sg(dev->dev, iod->sg, iod->nents,
+						dma_dir);
 				goto error_cmd;
+			}
 
 			if (rq_data_dir(req))
 				nvme_dif_remap(req, nvme_dif_prep);
 
-			if (!dma_map_sg(nvmeq->q_dmadev, iod->meta_sg, 1, dma_dir))
+			if (!dma_map_sg(nvmeq->q_dmadev, iod->meta_sg, 1, dma_dir)) {
+				dma_unmap_sg(dev->dev, iod->sg, iod->nents,
+						dma_dir);
 				goto error_cmd;
 			}
 		}
+	}
 
 	nvme_set_info(cmd, iod, req_completion);
 	spin_lock_irq(&nvmeq->q_lock);
@@ -1728,9 +1737,13 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 	u32 aqa;
 	u64 cap = lo_hi_readq(&dev->bar->cap);
 	struct nvme_queue *nvmeq;
-	unsigned page_shift = PAGE_SHIFT;
+	/*
+	 * default to a 4K page size, with the intention to update this
+	 * path in the future to accomodate architectures with differing
+	 * kernel and IO page sizes.
+	 */
+	unsigned page_shift = 12;
 	unsigned dev_page_min = NVME_CAP_MPSMIN(cap) + 12;
-	unsigned dev_page_max = NVME_CAP_MPSMAX(cap) + 12;
 
 	if (page_shift < dev_page_min) {
 		dev_err(dev->dev,
@@ -1739,13 +1752,6 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 				1 << page_shift);
 		return -ENODEV;
 	}
-	if (page_shift > dev_page_max) {
-		dev_info(dev->dev,
-				"Device maximum page size (%u) smaller than "
-				"host (%u); enabling work-around\n",
-				1 << dev_page_max, 1 << page_shift);
-		page_shift = dev_page_max;
-	}
 
 	dev->subsystem = readl(&dev->bar->vs) >= NVME_VS(1, 1) ?
 						NVME_CAP_NSSRC(cap) : 0;