nvme: Fix PRP Offset Invalid

When large writes take place I saw a Samsung EVO 970+ return a status
value of 0x13, PRP Offset Invalid.  I tracked this down to the
improper handling of PRP entries.  The blocks the PRP entries are
placed in cannot cross a page boundary and thus should be allocated
on page boundaries.  This is how the Linux kernel driver works.

With this patch, the PRP pool is allocated on a page boundary and
other than the very first allocation, the pool size is a multiple of
the page size.  Each page can hold (4096 / 8) - 1 entries since the
last entry must point to the next page in the pool.

Signed-off-by: Aaron Williams <awilliams@marvell.com>
Reviewed-by: Bin Meng <bmeng.cn@gmail.com>

drivers/nvme/nvme.c

@@ -73,6 +73,9 @@ static int nvme_setup_prps(struct nvme_dev *dev, u64 *prp2,
 	u64 *prp_pool;
 	int length = total_len;
 	int i, nprps;
+	u32 prps_per_page = (page_size >> 3) - 1;
+	u32 num_pages;
+
 	length -= (page_size - offset);
 
 	if (length <= 0) {
@@ -89,15 +92,20 @@ static int nvme_setup_prps(struct nvme_dev *dev, u64 *prp2,
 	}
 
 	nprps = DIV_ROUND_UP(length, page_size);
+	num_pages = DIV_ROUND_UP(nprps, prps_per_page);
 
 	if (nprps > dev->prp_entry_num) {
 		free(dev->prp_pool);
-		dev->prp_pool = malloc(nprps << 3);
+		/*
+		 * Always increase in increments of pages.  It doesn't waste
+		 * much memory and reduces the number of allocations.
+		 */
+		dev->prp_pool = memalign(page_size, num_pages * page_size);
 		if (!dev->prp_pool) {
 			printf("Error: malloc prp_pool fail\n");
 			return -ENOMEM;
 		}
-		dev->prp_entry_num = nprps;
+		dev->prp_entry_num = prps_per_page * num_pages;
 	}
 
 	prp_pool = dev->prp_pool;
@@ -788,14 +796,6 @@ static int nvme_probe(struct udevice *udev)
 	}
 	memset(ndev->queues, 0, NVME_Q_NUM * sizeof(struct nvme_queue *));
 
-	ndev->prp_pool = malloc(MAX_PRP_POOL);
-	if (!ndev->prp_pool) {
-		ret = -ENOMEM;
-		printf("Error: %s: Out of memory!\n", udev->name);
-		goto free_nvme;
-	}
-	ndev->prp_entry_num = MAX_PRP_POOL >> 3;
-
 	ndev->cap = nvme_readq(&ndev->bar->cap);
 	ndev->q_depth = min_t(int, NVME_CAP_MQES(ndev->cap) + 1, NVME_Q_DEPTH);
 	ndev->db_stride = 1 << NVME_CAP_STRIDE(ndev->cap);
@@ -805,6 +805,15 @@ static int nvme_probe(struct udevice *udev)
 	if (ret)
 		goto free_queue;
 
+	/* Allocate after the page size is known */
+	ndev->prp_pool = memalign(ndev->page_size, MAX_PRP_POOL);
+	if (!ndev->prp_pool) {
+		ret = -ENOMEM;
+		printf("Error: %s: Out of memory!\n", udev->name);
+		goto free_nvme;
+	}
+	ndev->prp_entry_num = MAX_PRP_POOL >> 3;
+
 	ret = nvme_setup_io_queues(ndev);
 	if (ret)
 		goto free_queue;