diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 4753a18..acaa8b8 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4537,6 +4537,10 @@ static void ata_fill_sg(struct ata_queued_cmd *qc)
 		 * Note h/w doesn't support 64-bit, so we unconditionally
 		 * truncate dma_addr_t to u32.
 		 */
+		if (sg_dma_address(sg) & ~DMA_BIT_MASK(32))
+			ata_dev_printk(qc->dev, KERN_WARNING,
+				       "XXX DMA address %llx is above 32bit\n",
+				       sg_dma_address(sg));
 		addr = (u32) sg_dma_address(sg);
 		sg_len = sg_dma_len(sg);
 
@@ -6628,6 +6632,10 @@ int ata_port_start(struct ata_port *ap)
 	if (rc)
 		return rc;
 
+	ata_port_printk(ap, KERN_INFO, "XXX: prd %p/%llx pad %p/%llx\n",
+			ap->prd, (unsigned long long)ap->prd_dma,
+			ap->pad, (unsigned long long)ap->pad_dma);
+
 	DPRINTK("prd alloc, virt %p, dma %llx\n", ap->prd,
 		(unsigned long long)ap->prd_dma);
 	return 0;
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index ed5dc7c..c55d2ae 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -247,6 +247,7 @@ struct nv_adma_port_priv {
 	void __iomem		*ctl_block;
 	void __iomem		*gen_block;
 	void __iomem		*notifier_clear_block;
+	u64			adma_dma_mask;
 	u8			flags;
 	int			last_issue_ncq;
 };
@@ -748,7 +749,7 @@ static int nv_adma_slave_config(struct scsi_device *sdev)
 		adma_enable = 0;
 		nv_adma_register_mode(ap);
 	} else {
-		bounce_limit = *ap->dev->dma_mask;
+		bounce_limit = pp->adma_dma_mask;
 		segment_boundary = NV_ADMA_DMA_BOUNDARY;
 		sg_tablesize = NV_ADMA_SGTBL_TOTAL_LEN;
 		adma_enable = 1;
@@ -1134,10 +1135,20 @@ static int nv_adma_port_start(struct ata_port *ap)
 	void *mem;
 	dma_addr_t mem_dma;
 	void __iomem *mmio;
+	struct pci_dev *pdev = to_pci_dev(dev);
 	u16 tmp;
 
 	VPRINTK("ENTER\n");
 
+	/* Ensure DMA mask is set to 32-bit before allocating legacy PRD and
+	   pad buffers */
+	rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+	if (rc)
+		return rc;
+	rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+	if (rc)
+		return rc;
+
 	rc = ata_port_start(ap);
 	if (rc)
 		return rc;
@@ -1153,6 +1164,15 @@ static int nv_adma_port_start(struct ata_port *ap)
 	pp->notifier_clear_block = pp->gen_block +
 	       NV_ADMA_NOTIFIER_CLEAR + (4 * ap->port_no);
 
+	/* Now that the legacy PRD and padding buffer are allocated we can
+	   safely raise the DMA mask to allocate the CPB/APRD table.
+	   These are allowed to fail since we store the value that ends up
+	   being used to set as the bounce limit in slave_config later if
+	   needed. */
+	pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+	pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+	pp->adma_dma_mask = *dev->dma_mask;
+
 	mem = dmam_alloc_coherent(dev, NV_ADMA_PORT_PRIV_DMA_SZ,
 				  &mem_dma, GFP_KERNEL);
 	if (!mem)
@@ -2418,12 +2438,6 @@ static int nv_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	hpriv->type = type;
 	host->private_data = hpriv;
 
-	/* set 64bit dma masks, may fail */
-	if (type == ADMA) {
-		if (pci_set_dma_mask(pdev, DMA_64BIT_MASK) == 0)
-			pci_set_consistent_dma_mask(pdev, DMA_64BIT_MASK);
-	}
-
 	/* request and iomap NV_MMIO_BAR */
 	rc = pcim_iomap_regions(pdev, 1 << NV_MMIO_BAR, DRV_NAME);
 	if (rc)
diff --git a/include/linux/libata.h b/include/linux/libata.h