diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.c b/drivers/ntb/hw/amd/ntb_hw_amd.c
index 588803a..6ccba0d 100644
--- a/drivers/ntb/hw/amd/ntb_hw_amd.c
+++ b/drivers/ntb/hw/amd/ntb_hw_amd.c
@@ -357,20 +357,6 @@
 	return 0;
 }
 
-static int amd_ntb_peer_db_addr(struct ntb_dev *ntb,
-				phys_addr_t *db_addr,
-				resource_size_t *db_size)
-{
-	struct amd_ntb_dev *ndev = ntb_ndev(ntb);
-
-	if (db_addr)
-		*db_addr = (phys_addr_t)(ndev->peer_mmio + AMD_DBREQ_OFFSET);
-	if (db_size)
-		*db_size = sizeof(u32);
-
-	return 0;
-}
-
 static int amd_ntb_peer_db_set(struct ntb_dev *ntb, u64 db_bits)
 {
 	struct amd_ntb_dev *ndev = ntb_ndev(ntb);
@@ -415,20 +401,6 @@
 	return 0;
 }
 
-static int amd_ntb_peer_spad_addr(struct ntb_dev *ntb, int idx,
-				  phys_addr_t *spad_addr)
-{
-	struct amd_ntb_dev *ndev = ntb_ndev(ntb);
-
-	if (idx < 0 || idx >= ndev->spad_count)
-		return -EINVAL;
-
-	if (spad_addr)
-		*spad_addr = (phys_addr_t)(ndev->self_mmio + AMD_SPAD_OFFSET +
-					   ndev->peer_spad + (idx << 2));
-	return 0;
-}
-
 static u32 amd_ntb_peer_spad_read(struct ntb_dev *ntb, int idx)
 {
 	struct amd_ntb_dev *ndev = ntb_ndev(ntb);
@@ -472,12 +444,10 @@
 	.db_clear		= amd_ntb_db_clear,
 	.db_set_mask		= amd_ntb_db_set_mask,
 	.db_clear_mask		= amd_ntb_db_clear_mask,
-	.peer_db_addr		= amd_ntb_peer_db_addr,
 	.peer_db_set		= amd_ntb_peer_db_set,
 	.spad_count		= amd_ntb_spad_count,
 	.spad_read		= amd_ntb_spad_read,
 	.spad_write		= amd_ntb_spad_write,
-	.peer_spad_addr		= amd_ntb_peer_spad_addr,
 	.peer_spad_read		= amd_ntb_peer_spad_read,
 	.peer_spad_write	= amd_ntb_peer_spad_write,
 };
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index ec4775f..2ef9d91 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -124,6 +124,7 @@
 
 	bool client_ready;
 	bool link_is_up;
+	bool active;
 
 	u8 qp_num;	/* Only 64 QP's are allowed.  0-63 */
 	u64 qp_bit;
@@ -719,6 +720,7 @@
 static void ntb_qp_link_down_reset(struct ntb_transport_qp *qp)
 {
 	qp->link_is_up = false;
+	qp->active = false;
 
 	qp->tx_index = 0;
 	qp->rx_index = 0;
@@ -827,7 +829,7 @@
 	struct pci_dev *pdev = ndev->pdev;
 	resource_size_t size;
 	u32 val;
-	int rc, i, spad;
+	int rc = 0, i, spad;
 
 	/* send the local info, in the opposite order of the way we read it */
 	for (i = 0; i < nt->mw_count; i++) {
@@ -897,6 +899,13 @@
 out1:
 	for (i = 0; i < nt->mw_count; i++)
 		ntb_free_mw(nt, i);
+
+	/* if there's an actual failure, we should just bail */
+	if (rc < 0) {
+		ntb_link_disable(ndev);
+		return;
+	}
+
 out:
 	if (ntb_link_is_up(ndev, NULL, NULL) == 1)
 		schedule_delayed_work(&nt->link_work,
@@ -926,11 +935,13 @@
 	if (val & BIT(qp->qp_num)) {
 		dev_info(&pdev->dev, "qp %d: Link Up\n", qp->qp_num);
 		qp->link_is_up = true;
+		qp->active = true;
 
 		if (qp->event_handler)
 			qp->event_handler(qp->cb_data, qp->link_is_up);
 
-		tasklet_schedule(&qp->rxc_db_work);
+		if (qp->active)
+			tasklet_schedule(&qp->rxc_db_work);
 	} else if (nt->link_is_up)
 		schedule_delayed_work(&qp->link_work,
 				      msecs_to_jiffies(NTB_LINK_DOWN_TIMEOUT));
@@ -1411,7 +1422,8 @@
 
 	if (i == qp->rx_max_entry) {
 		/* there is more work to do */
-		tasklet_schedule(&qp->rxc_db_work);
+		if (qp->active)
+			tasklet_schedule(&qp->rxc_db_work);
 	} else if (ntb_db_read(qp->ndev) & BIT_ULL(qp->qp_num)) {
 		/* the doorbell bit is set: clear it */
 		ntb_db_clear(qp->ndev, BIT_ULL(qp->qp_num));
@@ -1422,7 +1434,8 @@
 		 * ntb_process_rxc and clearing the doorbell bit:
 		 * there might be some more work to do.
 		 */
-		tasklet_schedule(&qp->rxc_db_work);
+		if (qp->active)
+			tasklet_schedule(&qp->rxc_db_work);
 	}
 }
 
@@ -1760,6 +1773,8 @@
 
 	pdev = qp->ndev->pdev;
 
+	qp->active = false;
+
 	if (qp->tx_dma_chan) {
 		struct dma_chan *chan = qp->tx_dma_chan;
 		/* Putting the dma_chan to NULL will force any new traffic to be
@@ -1793,7 +1808,7 @@
 	qp_bit = BIT_ULL(qp->qp_num);
 
 	ntb_db_set_mask(qp->ndev, qp_bit);
-	tasklet_disable(&qp->rxc_db_work);
+	tasklet_kill(&qp->rxc_db_work);
 
 	cancel_delayed_work_sync(&qp->link_work);
 
@@ -1886,7 +1901,8 @@
 
 	ntb_list_add(&qp->ntb_rx_q_lock, &entry->entry, &qp->rx_pend_q);
 
-	tasklet_schedule(&qp->rxc_db_work);
+	if (qp->active)
+		tasklet_schedule(&qp->rxc_db_work);
 
 	return 0;
 }
@@ -2069,7 +2085,8 @@
 		qp_num = __ffs(db_bits);
 		qp = &nt->qp_vec[qp_num];
 
-		tasklet_schedule(&qp->rxc_db_work);
+		if (qp->active)
+			tasklet_schedule(&qp->rxc_db_work);
 
 		db_bits &= ~BIT_ULL(qp_num);
 	}
diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c
index c8a37ba..8dfce9c 100644
--- a/drivers/ntb/test/ntb_perf.c
+++ b/drivers/ntb/test/ntb_perf.c
@@ -178,7 +178,7 @@
 	atomic_dec(&pctx->dma_sync);
 }
 
-static ssize_t perf_copy(struct pthr_ctx *pctx, char *dst,
+static ssize_t perf_copy(struct pthr_ctx *pctx, char __iomem *dst,
 			 char *src, size_t size)
 {
 	struct perf_ctx *perf = pctx->perf;
@@ -189,7 +189,8 @@
 	dma_cookie_t cookie;
 	size_t src_off, dst_off;
 	struct perf_mw *mw = &perf->mw;
-	u64 vbase, dst_vaddr;
+	void __iomem *vbase;
+	void __iomem *dst_vaddr;
 	dma_addr_t dst_phys;
 	int retries = 0;
 
@@ -204,14 +205,14 @@
 	}
 
 	device = chan->device;
-	src_off = (size_t)src & ~PAGE_MASK;
-	dst_off = (size_t)dst & ~PAGE_MASK;
+	src_off = (uintptr_t)src & ~PAGE_MASK;
+	dst_off = (uintptr_t __force)dst & ~PAGE_MASK;
 
 	if (!is_dma_copy_aligned(device, src_off, dst_off, size))
 		return -ENODEV;
 
-	vbase = (u64)(u64 *)mw->vbase;
-	dst_vaddr = (u64)(u64 *)dst;
+	vbase = mw->vbase;
+	dst_vaddr = dst;
 	dst_phys = mw->phys_addr + (dst_vaddr - vbase);
 
 	unmap = dmaengine_get_unmap_data(device->dev, 1, GFP_NOWAIT);
@@ -261,13 +262,13 @@
 	return 0;
 }
 
-static int perf_move_data(struct pthr_ctx *pctx, char *dst, char *src,
+static int perf_move_data(struct pthr_ctx *pctx, char __iomem *dst, char *src,
 			  u64 buf_size, u64 win_size, u64 total)
 {
 	int chunks, total_chunks, i;
 	int copied_chunks = 0;
 	u64 copied = 0, result;
-	char *tmp = dst;
+	char __iomem *tmp = dst;
 	u64 perf, diff_us;
 	ktime_t kstart, kstop, kdiff;
 
@@ -324,7 +325,7 @@
 	struct perf_ctx *perf = pctx->perf;
 	struct pci_dev *pdev = perf->ntb->pdev;
 	struct perf_mw *mw = &perf->mw;
-	char *dst;
+	char __iomem *dst;
 	u64 win_size, buf_size, total;
 	void *src;
 	int rc, node, i;
@@ -364,7 +365,7 @@
 	if (buf_size > MAX_TEST_SIZE)
 		buf_size = MAX_TEST_SIZE;
 
-	dst = (char *)mw->vbase;
+	dst = (char __iomem *)mw->vbase;
 
 	atomic_inc(&perf->tsync);
 	while (atomic_read(&perf->tsync) != perf->perf_threads)
@@ -424,6 +425,7 @@
 {
 	struct perf_mw *mw = &perf->mw;
 	size_t xlat_size, buf_size;
+	int rc;
 
 	if (!size)
 		return -EINVAL;
@@ -447,6 +449,13 @@
 		mw->buf_size = 0;
 	}
 
+	rc = ntb_mw_set_trans(perf->ntb, 0, mw->dma_addr, mw->xlat_size);
+	if (rc) {
+		dev_err(&perf->ntb->dev, "Unable to set mw0 translation\n");
+		perf_free_mw(perf);
+		return -EIO;
+	}
+
 	return 0;
 }
 
@@ -541,6 +550,8 @@
 		return 0;
 
 	buf = kmalloc(64, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
 	out_offset = snprintf(buf, 64, "%d\n", perf->run);
 	ret = simple_read_from_buffer(ubuf, count, offp, buf, out_offset);
 	kfree(buf);
@@ -548,6 +559,21 @@
 	return ret;
 }
 
+static void threads_cleanup(struct perf_ctx *perf)
+{
+	struct pthr_ctx *pctx;
+	int i;
+
+	perf->run = false;
+	for (i = 0; i < MAX_THREADS; i++) {
+		pctx = &perf->pthr_ctx[i];
+		if (pctx->thread) {
+			kthread_stop(pctx->thread);
+			pctx->thread = NULL;
+		}
+	}
+}
+
 static ssize_t debugfs_run_write(struct file *filp, const char __user *ubuf,
 				 size_t count, loff_t *offp)
 {
@@ -563,17 +589,9 @@
 	if (atomic_read(&perf->tsync) == 0)
 		perf->run = false;
 
-	if (perf->run) {
-		/* lets stop the threads */
-		perf->run = false;
-		for (i = 0; i < MAX_THREADS; i++) {
-			if (perf->pthr_ctx[i].thread) {
-				kthread_stop(perf->pthr_ctx[i].thread);
-				perf->pthr_ctx[i].thread = NULL;
-			} else
-				break;
-		}
-	} else {
+	if (perf->run)
+		threads_cleanup(perf);
+	else {
 		perf->run = true;
 
 		if (perf->perf_threads > MAX_THREADS) {
@@ -604,17 +622,11 @@
 				kthread_create_on_node(ntb_perf_thread,
 						       (void *)pctx,
 						       node, "ntb_perf %d", i);
-			if (pctx->thread)
+			if (IS_ERR(pctx->thread)) {
+				pctx->thread = NULL;
+				goto err;
+			} else
 				wake_up_process(pctx->thread);
-			else {
-				perf->run = false;
-				for (i = 0; i < MAX_THREADS; i++) {
-					if (pctx->thread) {
-						kthread_stop(pctx->thread);
-						pctx->thread = NULL;
-					}
-				}
-			}
 
 			if (perf->run == false)
 				return -ENXIO;
@@ -623,6 +635,10 @@
 	}
 
 	return count;
+
+err:
+	threads_cleanup(perf);
+	return -ENXIO;
 }
 
 static const struct file_operations ntb_perf_debugfs_run = {
diff --git a/include/linux/ntb.h b/include/linux/ntb.h
index f798e2a..6f47562 100644
--- a/include/linux/ntb.h
+++ b/include/linux/ntb.h
@@ -284,7 +284,7 @@
 		/* ops->db_read_mask			&& */
 		ops->db_set_mask			&&
 		ops->db_clear_mask			&&
-		ops->peer_db_addr			&&
+		/* ops->peer_db_addr			&& */
 		/* ops->peer_db_read			&& */
 		ops->peer_db_set			&&
 		/* ops->peer_db_clear			&& */
@@ -295,7 +295,7 @@
 		ops->spad_count				&&
 		ops->spad_read				&&
 		ops->spad_write				&&
-		ops->peer_spad_addr			&&
+		/* ops->peer_spad_addr			&& */
 		/* ops->peer_spad_read			&& */
 		ops->peer_spad_write			&&
 		1;
@@ -757,6 +757,9 @@
 				   phys_addr_t *db_addr,
 				   resource_size_t *db_size)
 {
+	if (!ntb->ops->peer_db_addr)
+		return -EINVAL;
+
 	return ntb->ops->peer_db_addr(ntb, db_addr, db_size);
 }
 
@@ -948,6 +951,9 @@
 static inline int ntb_peer_spad_addr(struct ntb_dev *ntb, int idx,
 				     phys_addr_t *spad_addr)
 {
+	if (!ntb->ops->peer_spad_addr)
+		return -EINVAL;
+
 	return ntb->ops->peer_spad_addr(ntb, idx, spad_addr);
 }