Merge tag 'ntb-4.3' of git://github.com/jonmason/ntb

Pull NTB fixes from Jon Mason:
 "NTB bug and documentation fixes, new device IDs, performance
  improvements, and adding a mailing list to MAINTAINERS for NTB"

* tag 'ntb-4.3' of git://github.com/jonmason/ntb:
  NTB: Fix range check on memory window index
  NTB: Improve index handling in B2B MW workaround
  NTB: Fix documentation for ntb_peer_db_clear.
  NTB: Fix documentation for ntb_link_is_up
  NTB: Use unique DMA channels for TX and RX
  NTB: Remove dma_sync_wait from ntb_async_rx
  NTB: Clean up QP stats info
  NTB: Make the transport list in order of discovery
  NTB: Add PCI Device IDs for Broadwell Xeon
  NTB: Add flow control to the ntb_netdev
  NTB: Add list to MAINTAINERS

7 files changed, 210 insertions, 47 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 310da42..030d8724 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7396,6 +7396,7 @@ NTB DRIVER CORE
 M:	Jon Mason <jdmason@kudzu.us>
 M:	Dave Jiang <dave.jiang@intel.com>
 M:	Allen Hubbe <Allen.Hubbe@emc.com>
+L:	linux-ntb@googlegroups.com
 S:	Supported
 W:	https://github.com/jonmason/ntb/wiki
 T:	git git://github.com/jonmason/ntb.git
@@ -7407,6 +7408,7 @@ F:	include/linux/ntb_transport.h
 NTB INTEL DRIVER
 M:	Jon Mason <jdmason@kudzu.us>
 M:	Dave Jiang <dave.jiang@intel.com>
+L:	linux-ntb@googlegroups.com
 S:	Supported
 W:	https://github.com/jonmason/ntb/wiki
 T:	git git://github.com/jonmason/ntb.git
diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c
index d8757bf..a9acf71 100644
--- a/drivers/net/ntb_netdev.c
+++ b/drivers/net/ntb_netdev.c
@@ -61,11 +61,21 @@ MODULE_VERSION(NTB_NETDEV_VER);
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Intel Corporation");
 
+/* Time in usecs for tx resource reaper */
+static unsigned int tx_time = 1;
+
+/* Number of descriptors to free before resuming tx */
+static unsigned int tx_start = 10;
+
+/* Number of descriptors still available before stop upper layer tx */
+static unsigned int tx_stop = 5;
+
 struct ntb_netdev {
 	struct list_head list;
 	struct pci_dev *pdev;
 	struct net_device *ndev;
 	struct ntb_transport_qp *qp;
+	struct timer_list tx_timer;
 };
 
 #define	NTB_TX_TIMEOUT_MS	1000
@@ -136,11 +146,42 @@ enqueue_again:
 	}
 }
 
+static int __ntb_netdev_maybe_stop_tx(struct net_device *netdev,
+				      struct ntb_transport_qp *qp, int size)
+{
+	struct ntb_netdev *dev = netdev_priv(netdev);
+
+	netif_stop_queue(netdev);
+	/* Make sure to see the latest value of ntb_transport_tx_free_entry()
+	 * since the queue was last started.
+	 */
+	smp_mb();
+
+	if (likely(ntb_transport_tx_free_entry(qp) < size)) {
+		mod_timer(&dev->tx_timer, jiffies + usecs_to_jiffies(tx_time));
+		return -EBUSY;
+	}
+
+	netif_start_queue(netdev);
+	return 0;
+}
+
+static int ntb_netdev_maybe_stop_tx(struct net_device *ndev,
+				    struct ntb_transport_qp *qp, int size)
+{
+	if (netif_queue_stopped(ndev) ||
+	    (ntb_transport_tx_free_entry(qp) >= size))
+		return 0;
+
+	return __ntb_netdev_maybe_stop_tx(ndev, qp, size);
+}
+
 static void ntb_netdev_tx_handler(struct ntb_transport_qp *qp, void *qp_data,
 				  void *data, int len)
 {
 	struct net_device *ndev = qp_data;
 	struct sk_buff *skb;
+	struct ntb_netdev *dev = netdev_priv(ndev);
 
 	skb = data;
 	if (!skb || !ndev)
@@ -155,6 +196,15 @@ static void ntb_netdev_tx_handler(struct ntb_transport_qp *qp, void *qp_data,
 	}
 
 	dev_kfree_skb(skb);
+
+	if (ntb_transport_tx_free_entry(dev->qp) >= tx_start) {
+		/* Make sure anybody stopping the queue after this sees the new
+		 * value of ntb_transport_tx_free_entry()
+		 */
+		smp_mb();
+		if (netif_queue_stopped(ndev))
+			netif_wake_queue(ndev);
+	}
 }
 
 static netdev_tx_t ntb_netdev_start_xmit(struct sk_buff *skb,
@@ -163,10 +213,15 @@ static netdev_tx_t ntb_netdev_start_xmit(struct sk_buff *skb,
 	struct ntb_netdev *dev = netdev_priv(ndev);
 	int rc;
 
+	ntb_netdev_maybe_stop_tx(ndev, dev->qp, tx_stop);
+
 	rc = ntb_transport_tx_enqueue(dev->qp, skb, skb->data, skb->len);
 	if (rc)
 		goto err;
 
+	/* check for next submit */
+	ntb_netdev_maybe_stop_tx(ndev, dev->qp, tx_stop);
+
 	return NETDEV_TX_OK;
 
 err:
@@ -175,6 +230,23 @@ err:
 	return NETDEV_TX_BUSY;
 }
 
+static void ntb_netdev_tx_timer(unsigned long data)
+{
+	struct net_device *ndev = (struct net_device *)data;
+	struct ntb_netdev *dev = netdev_priv(ndev);
+
+	if (ntb_transport_tx_free_entry(dev->qp) < tx_stop) {
+		mod_timer(&dev->tx_timer, jiffies + msecs_to_jiffies(tx_time));
+	} else {
+		/* Make sure anybody stopping the queue after this sees the new
+		 * value of ntb_transport_tx_free_entry()
+		 */
+		smp_mb();
+		if (netif_queue_stopped(ndev))
+			netif_wake_queue(ndev);
+	}
+}
+
 static int ntb_netdev_open(struct net_device *ndev)
 {
 	struct ntb_netdev *dev = netdev_priv(ndev);
@@ -197,8 +269,11 @@ static int ntb_netdev_open(struct net_device *ndev)
 		}
 	}
 
+	setup_timer(&dev->tx_timer, ntb_netdev_tx_timer, (unsigned long)ndev);
+
 	netif_carrier_off(ndev);
 	ntb_transport_link_up(dev->qp);
+	netif_start_queue(ndev);
 
 	return 0;
 
@@ -219,6 +294,8 @@ static int ntb_netdev_close(struct net_device *ndev)
 	while ((skb = ntb_transport_rx_remove(dev->qp, &len)))
 		dev_kfree_skb(skb);
 
+	del_timer_sync(&dev->tx_timer);
+
 	return 0;
 }
 
diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.c b/drivers/ntb/hw/intel/ntb_hw_intel.c
index 87751cf..865a3e3 100644
--- a/drivers/ntb/hw/intel/ntb_hw_intel.c
+++ b/drivers/ntb/hw/intel/ntb_hw_intel.c
@@ -190,14 +190,17 @@ static inline int pdev_is_xeon(struct pci_dev *pdev)
 	case PCI_DEVICE_ID_INTEL_NTB_SS_SNB:
 	case PCI_DEVICE_ID_INTEL_NTB_SS_IVT:
 	case PCI_DEVICE_ID_INTEL_NTB_SS_HSX:
+	case PCI_DEVICE_ID_INTEL_NTB_SS_BDX:
 	case PCI_DEVICE_ID_INTEL_NTB_PS_JSF:
 	case PCI_DEVICE_ID_INTEL_NTB_PS_SNB:
 	case PCI_DEVICE_ID_INTEL_NTB_PS_IVT:
 	case PCI_DEVICE_ID_INTEL_NTB_PS_HSX:
+	case PCI_DEVICE_ID_INTEL_NTB_PS_BDX:
 	case PCI_DEVICE_ID_INTEL_NTB_B2B_JSF:
 	case PCI_DEVICE_ID_INTEL_NTB_B2B_SNB:
 	case PCI_DEVICE_ID_INTEL_NTB_B2B_IVT:
 	case PCI_DEVICE_ID_INTEL_NTB_B2B_HSX:
+	case PCI_DEVICE_ID_INTEL_NTB_B2B_BDX:
 		return 1;
 	}
 	return 0;
@@ -237,7 +240,7 @@ static inline int ndev_ignore_unsafe(struct intel_ntb_dev *ndev,
 
 static int ndev_mw_to_bar(struct intel_ntb_dev *ndev, int idx)
 {
-	if (idx < 0 || idx > ndev->mw_count)
+	if (idx < 0 || idx >= ndev->mw_count)
 		return -EINVAL;
 	return ndev->reg->mw_bar[idx];
 }
@@ -572,10 +575,13 @@ static ssize_t ndev_debugfs_read(struct file *filp, char __user *ubuf,
 			 "Connection Topology -\t%s\n",
 			 ntb_topo_string(ndev->ntb.topo));
 
-	off += scnprintf(buf + off, buf_size - off,
-			 "B2B Offset -\t\t%#lx\n", ndev->b2b_off);
-	off += scnprintf(buf + off, buf_size - off,
-			 "B2B MW Idx -\t\t%d\n", ndev->b2b_idx);
+	if (ndev->b2b_idx != UINT_MAX) {
+		off += scnprintf(buf + off, buf_size - off,
+				 "B2B MW Idx -\t\t%u\n", ndev->b2b_idx);
+		off += scnprintf(buf + off, buf_size - off,
+				 "B2B Offset -\t\t%#lx\n", ndev->b2b_off);
+	}
+
 	off += scnprintf(buf + off, buf_size - off,
 			 "BAR4 Split -\t\t%s\n",
 			 ndev->bar4_split ? "yes" : "no");
@@ -1484,7 +1490,7 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev,
 	pdev = ndev_pdev(ndev);
 	mmio = ndev->self_mmio;
 
-	if (ndev->b2b_idx >= ndev->mw_count) {
+	if (ndev->b2b_idx == UINT_MAX) {
 		dev_dbg(ndev_dev(ndev), "not using b2b mw\n");
 		b2b_bar = 0;
 		ndev->b2b_off = 0;
@@ -1776,6 +1782,13 @@ static int xeon_init_ntb(struct intel_ntb_dev *ndev)
 			else
 				ndev->b2b_idx = b2b_mw_idx;
 
+			if (ndev->b2b_idx >= ndev->mw_count) {
+				dev_dbg(ndev_dev(ndev),
+					"b2b_mw_idx %d invalid for mw_count %u\n",
+					b2b_mw_idx, ndev->mw_count);
+				return -EINVAL;
+			}
+
 			dev_dbg(ndev_dev(ndev),
 				"setting up b2b mw idx %d means %d\n",
 				b2b_mw_idx, ndev->b2b_idx);
@@ -1843,6 +1856,9 @@ static int xeon_init_dev(struct intel_ntb_dev *ndev)
 	case PCI_DEVICE_ID_INTEL_NTB_SS_HSX:
 	case PCI_DEVICE_ID_INTEL_NTB_PS_HSX:
 	case PCI_DEVICE_ID_INTEL_NTB_B2B_HSX:
+	case PCI_DEVICE_ID_INTEL_NTB_SS_BDX:
+	case PCI_DEVICE_ID_INTEL_NTB_PS_BDX:
+	case PCI_DEVICE_ID_INTEL_NTB_B2B_BDX:
 		ndev->hwerr_flags |= NTB_HWERR_SDOORBELL_LOCKUP;
 		break;
 	}
@@ -1857,6 +1873,9 @@ static int xeon_init_dev(struct intel_ntb_dev *ndev)
 	case PCI_DEVICE_ID_INTEL_NTB_SS_HSX:
 	case PCI_DEVICE_ID_INTEL_NTB_PS_HSX:
 	case PCI_DEVICE_ID_INTEL_NTB_B2B_HSX:
+	case PCI_DEVICE_ID_INTEL_NTB_SS_BDX:
+	case PCI_DEVICE_ID_INTEL_NTB_PS_BDX:
+	case PCI_DEVICE_ID_INTEL_NTB_B2B_BDX:
 		ndev->hwerr_flags |= NTB_HWERR_SB01BASE_LOCKUP;
 		break;
 	}
@@ -1878,6 +1897,9 @@ static int xeon_init_dev(struct intel_ntb_dev *ndev)
 	case PCI_DEVICE_ID_INTEL_NTB_SS_HSX:
 	case PCI_DEVICE_ID_INTEL_NTB_PS_HSX:
 	case PCI_DEVICE_ID_INTEL_NTB_B2B_HSX:
+	case PCI_DEVICE_ID_INTEL_NTB_SS_BDX:
+	case PCI_DEVICE_ID_INTEL_NTB_PS_BDX:
+	case PCI_DEVICE_ID_INTEL_NTB_B2B_BDX:
 		ndev->hwerr_flags |= NTB_HWERR_B2BDOORBELL_BIT14;
 		break;
 	}
@@ -1996,7 +2018,7 @@ static inline void ndev_init_struct(struct intel_ntb_dev *ndev,
 	ndev->ntb.ops = &intel_ntb_ops;
 
 	ndev->b2b_off = 0;
-	ndev->b2b_idx = INT_MAX;
+	ndev->b2b_idx = UINT_MAX;
 
 	ndev->bar4_split = 0;
 
@@ -2234,14 +2256,17 @@ static const struct pci_device_id intel_ntb_pci_tbl[] = {
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_B2B_SNB)},
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_B2B_IVT)},
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_B2B_HSX)},
+	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_B2B_BDX)},
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_PS_JSF)},
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_PS_SNB)},
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_PS_IVT)},
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_PS_HSX)},
+	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_PS_BDX)},
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_SS_JSF)},
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_SS_SNB)},
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_SS_IVT)},
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_SS_HSX)},
+	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_SS_BDX)},
 	{0}
 };
 MODULE_DEVICE_TABLE(pci, intel_ntb_pci_tbl);
diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.h b/drivers/ntb/hw/intel/ntb_hw_intel.h
index 7ddaf38..ea0612f7 100644
--- a/drivers/ntb/hw/intel/ntb_hw_intel.h
+++ b/drivers/ntb/hw/intel/ntb_hw_intel.h
@@ -67,6 +67,9 @@
 #define PCI_DEVICE_ID_INTEL_NTB_PS_HSX	0x2F0E
 #define PCI_DEVICE_ID_INTEL_NTB_SS_HSX	0x2F0F
 #define PCI_DEVICE_ID_INTEL_NTB_B2B_BWD	0x0C4E
+#define PCI_DEVICE_ID_INTEL_NTB_B2B_BDX	0x6F0D
+#define PCI_DEVICE_ID_INTEL_NTB_PS_BDX	0x6F0E
+#define PCI_DEVICE_ID_INTEL_NTB_SS_BDX	0x6F0F
 
 /* Intel Xeon hardware */
 
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index 1c6386d..6e3ee90 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -119,7 +119,8 @@ struct ntb_transport_qp {
 	struct ntb_transport_ctx *transport;
 	struct ntb_dev *ndev;
 	void *cb_data;
-	struct dma_chan *dma_chan;
+	struct dma_chan *tx_dma_chan;
+	struct dma_chan *rx_dma_chan;
 
 	bool client_ready;
 	bool link_is_up;
@@ -297,7 +298,7 @@ static LIST_HEAD(ntb_transport_list);
 
 static int ntb_bus_init(struct ntb_transport_ctx *nt)
 {
-	list_add(&nt->entry, &ntb_transport_list);
+	list_add_tail(&nt->entry, &ntb_transport_list);
 	return 0;
 }
 
@@ -452,7 +453,7 @@ static ssize_t debugfs_read(struct file *filp, char __user *ubuf, size_t count,
 
 	out_offset = 0;
 	out_offset += snprintf(buf + out_offset, out_count - out_offset,
-			       "NTB QP stats\n");
+			       "\nNTB QP stats:\n\n");
 	out_offset += snprintf(buf + out_offset, out_count - out_offset,
 			       "rx_bytes - \t%llu\n", qp->rx_bytes);
 	out_offset += snprintf(buf + out_offset, out_count - out_offset,
@@ -470,11 +471,11 @@ static ssize_t debugfs_read(struct file *filp, char __user *ubuf, size_t count,
 	out_offset += snprintf(buf + out_offset, out_count - out_offset,
 			       "rx_err_ver - \t%llu\n", qp->rx_err_ver);
 	out_offset += snprintf(buf + out_offset, out_count - out_offset,
-			       "rx_buff - \t%p\n", qp->rx_buff);
+			       "rx_buff - \t0x%p\n", qp->rx_buff);
 	out_offset += snprintf(buf + out_offset, out_count - out_offset,
 			       "rx_index - \t%u\n", qp->rx_index);
 	out_offset += snprintf(buf + out_offset, out_count - out_offset,
-			       "rx_max_entry - \t%u\n", qp->rx_max_entry);
+			       "rx_max_entry - \t%u\n\n", qp->rx_max_entry);
 
 	out_offset += snprintf(buf + out_offset, out_count - out_offset,
 			       "tx_bytes - \t%llu\n", qp->tx_bytes);
@@ -489,15 +490,32 @@ static ssize_t debugfs_read(struct file *filp, char __user *ubuf, size_t count,
 	out_offset += snprintf(buf + out_offset, out_count - out_offset,
 			       "tx_err_no_buf - %llu\n", qp->tx_err_no_buf);
 	out_offset += snprintf(buf + out_offset, out_count - out_offset,
-			       "tx_mw - \t%p\n", qp->tx_mw);
+			       "tx_mw - \t0x%p\n", qp->tx_mw);
 	out_offset += snprintf(buf + out_offset, out_count - out_offset,
-			       "tx_index - \t%u\n", qp->tx_index);
+			       "tx_index (H) - \t%u\n", qp->tx_index);
+	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+			       "RRI (T) - \t%u\n",
+			       qp->remote_rx_info->entry);
 	out_offset += snprintf(buf + out_offset, out_count - out_offset,
 			       "tx_max_entry - \t%u\n", qp->tx_max_entry);
+	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+			       "free tx - \t%u\n",
+			       ntb_transport_tx_free_entry(qp));
 
 	out_offset += snprintf(buf + out_offset, out_count - out_offset,
-			       "\nQP Link %s\n",
+			       "\n");
+	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+			       "Using TX DMA - \t%s\n",
+			       qp->tx_dma_chan ? "Yes" : "No");
+	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+			       "Using RX DMA - \t%s\n",
+			       qp->rx_dma_chan ? "Yes" : "No");
+	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+			       "QP Link - \t%s\n",
 			       qp->link_is_up ? "Up" : "Down");
+	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+			       "\n");
+
 	if (out_offset > out_count)
 		out_offset = out_count;
 
@@ -535,6 +553,7 @@ static struct ntb_queue_entry *ntb_list_rm(spinlock_t *lock,
 	}
 	entry = list_first_entry(list, struct ntb_queue_entry, entry);
 	list_del(&entry->entry);
+
 out:
 	spin_unlock_irqrestore(lock, flags);
 
@@ -1206,7 +1225,7 @@ static void ntb_async_rx(struct ntb_queue_entry *entry, void *offset)
 {
 	struct dma_async_tx_descriptor *txd;
 	struct ntb_transport_qp *qp = entry->qp;
-	struct dma_chan *chan = qp->dma_chan;
+	struct dma_chan *chan = qp->rx_dma_chan;
 	struct dma_device *device;
 	size_t pay_off, buff_off, len;
 	struct dmaengine_unmap_data *unmap;
@@ -1219,18 +1238,18 @@ static void ntb_async_rx(struct ntb_queue_entry *entry, void *offset)
 		goto err;
 
 	if (len < copy_bytes)
-		goto err_wait;
+		goto err;
 
 	device = chan->device;
 	pay_off = (size_t)offset & ~PAGE_MASK;
 	buff_off = (size_t)buf & ~PAGE_MASK;
 
 	if (!is_dma_copy_aligned(device, pay_off, buff_off, len))
-		goto err_wait;
+		goto err;
 
 	unmap = dmaengine_get_unmap_data(device->dev, 2, GFP_NOWAIT);
 	if (!unmap)
-		goto err_wait;
+		goto err;
 
 	unmap->len = len;
 	unmap->addr[0] = dma_map_page(device->dev, virt_to_page(offset),
@@ -1273,12 +1292,6 @@ err_set_unmap:
 	dmaengine_unmap_put(unmap);
 err_get_unmap:
 	dmaengine_unmap_put(unmap);
-err_wait:
-	/* If the callbacks come out of order, the writing of the index to the
-	 * last completed will be out of order.  This may result in the
-	 * receive stalling forever.
-	 */
-	dma_sync_wait(chan, qp->last_cookie);
 err:
 	ntb_memcpy_rx(entry, offset);
 	qp->rx_memcpy++;
@@ -1373,8 +1386,8 @@ static void ntb_transport_rxc_db(unsigned long data)
 			break;
 	}
 
-	if (i && qp->dma_chan)
-		dma_async_issue_pending(qp->dma_chan);
+	if (i && qp->rx_dma_chan)
+		dma_async_issue_pending(qp->rx_dma_chan);
 
 	if (i == qp->rx_max_entry) {
 		/* there is more work to do */
@@ -1441,7 +1454,7 @@ static void ntb_async_tx(struct ntb_transport_qp *qp,
 {
 	struct ntb_payload_header __iomem *hdr;
 	struct dma_async_tx_descriptor *txd;
-	struct dma_chan *chan = qp->dma_chan;
+	struct dma_chan *chan = qp->tx_dma_chan;
 	struct dma_device *device;
 	size_t dest_off, buff_off;
 	struct dmaengine_unmap_data *unmap;
@@ -1634,14 +1647,27 @@ ntb_transport_create_queue(void *data, struct device *client_dev,
 	dma_cap_set(DMA_MEMCPY, dma_mask);
 
 	if (use_dma) {
-		qp->dma_chan = dma_request_channel(dma_mask, ntb_dma_filter_fn,
-						   (void *)(unsigned long)node);
-		if (!qp->dma_chan)
-			dev_info(&pdev->dev, "Unable to allocate DMA channel\n");
+		qp->tx_dma_chan =
+			dma_request_channel(dma_mask, ntb_dma_filter_fn,
+					    (void *)(unsigned long)node);
+		if (!qp->tx_dma_chan)
+			dev_info(&pdev->dev, "Unable to allocate TX DMA channel\n");
+
+		qp->rx_dma_chan =
+			dma_request_channel(dma_mask, ntb_dma_filter_fn,
+					    (void *)(unsigned long)node);
+		if (!qp->rx_dma_chan)
+			dev_info(&pdev->dev, "Unable to allocate RX DMA channel\n");
 	} else {
-		qp->dma_chan = NULL;
+		qp->tx_dma_chan = NULL;
+		qp->rx_dma_chan = NULL;
 	}
-	dev_dbg(&pdev->dev, "Using %s memcpy\n", qp->dma_chan ? "DMA" : "CPU");
+
+	dev_dbg(&pdev->dev, "Using %s memcpy for TX\n",
+		qp->tx_dma_chan ? "DMA" : "CPU");
+
+	dev_dbg(&pdev->dev, "Using %s memcpy for RX\n",
+		qp->rx_dma_chan ? "DMA" : "CPU");
 
 	for (i = 0; i < NTB_QP_DEF_NUM_ENTRIES; i++) {
 		entry = kzalloc_node(sizeof(*entry), GFP_ATOMIC, node);
@@ -1676,8 +1702,10 @@ err2:
 err1:
 	while ((entry = ntb_list_rm(&qp->ntb_rx_q_lock, &qp->rx_free_q)))
 		kfree(entry);
-	if (qp->dma_chan)
-		dma_release_channel(qp->dma_chan);
+	if (qp->tx_dma_chan)
+		dma_release_channel(qp->tx_dma_chan);
+	if (qp->rx_dma_chan)
+		dma_release_channel(qp->rx_dma_chan);
 	nt->qp_bitmap_free |= qp_bit;
 err:
 	return NULL;
@@ -1701,12 +1729,27 @@ void ntb_transport_free_queue(struct ntb_transport_qp *qp)
 
 	pdev = qp->ndev->pdev;
 
-	if (qp->dma_chan) {
-		struct dma_chan *chan = qp->dma_chan;
+	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
+		 * processed by the CPU instead of the DAM engine
+		 */
+		qp->tx_dma_chan = NULL;
+
+		/* Try to be nice and wait for any queued DMA engine
+		 * transactions to process before smashing it with a rock
+		 */
+		dma_sync_wait(chan, qp->last_cookie);
+		dmaengine_terminate_all(chan);
+		dma_release_channel(chan);
+	}
+
+	if (qp->rx_dma_chan) {
+		struct dma_chan *chan = qp->rx_dma_chan;
 		/* Putting the dma_chan to NULL will force any new traffic to be
 		 * processed by the CPU instead of the DAM engine
 		 */
-		qp->dma_chan = NULL;
+		qp->rx_dma_chan = NULL;
 
 		/* Try to be nice and wait for any queued DMA engine
 		 * transactions to process before smashing it with a rock
@@ -1843,7 +1886,7 @@ int ntb_transport_tx_enqueue(struct ntb_transport_qp *qp, void *cb, void *data,
 	entry = ntb_list_rm(&qp->ntb_tx_free_q_lock, &qp->tx_free_q);
 	if (!entry) {
 		qp->tx_err_no_buf++;
-		return -ENOMEM;
+		return -EBUSY;
 	}
 
 	entry->cb_data = cb;
@@ -1954,21 +1997,34 @@ EXPORT_SYMBOL_GPL(ntb_transport_qp_num);
 unsigned int ntb_transport_max_size(struct ntb_transport_qp *qp)
 {
 	unsigned int max;
+	unsigned int copy_align;
 
 	if (!qp)
 		return 0;
 
-	if (!qp->dma_chan)
+	if (!qp->tx_dma_chan && !qp->rx_dma_chan)
 		return qp->tx_max_frame - sizeof(struct ntb_payload_header);
 
+	copy_align = max(qp->tx_dma_chan->device->copy_align,
+			 qp->rx_dma_chan->device->copy_align);
+
 	/* If DMA engine usage is possible, try to find the max size for that */
 	max = qp->tx_max_frame - sizeof(struct ntb_payload_header);
-	max -= max % (1 << qp->dma_chan->device->copy_align);
+	max -= max % (1 << copy_align);
 
 	return max;
 }
 EXPORT_SYMBOL_GPL(ntb_transport_max_size);
 
+unsigned int ntb_transport_tx_free_entry(struct ntb_transport_qp *qp)
+{
+	unsigned int head = qp->tx_index;
+	unsigned int tail = qp->remote_rx_info->entry;
+
+	return tail > head ? tail - head : qp->tx_max_entry + tail - head;
+}
+EXPORT_SYMBOL_GPL(ntb_transport_tx_free_entry);
+
 static void ntb_transport_doorbell_callback(void *data, int vector)
 {
 	struct ntb_transport_ctx *nt = data;
diff --git a/include/linux/ntb.h b/include/linux/ntb.h
index b02f72b..f798e2a 100644
--- a/include/linux/ntb.h
+++ b/include/linux/ntb.h
@@ -522,10 +522,9 @@ static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int idx)
  * @speed:	OUT - The link speed expressed as PCIe generation number.
  * @width:	OUT - The link width expressed as the number of PCIe lanes.
  *
- * Set the translation of a memory window.  The peer may access local memory
- * through the window starting at the address, up to the size.  The address
- * must be aligned to the alignment specified by ntb_mw_get_range().  The size
- * must be aligned to the size alignment specified by ntb_mw_get_range().
+ * Get the current state of the ntb link.  It is recommended to query the link
+ * state once after every link event.  It is safe to query the link state in
+ * the context of the link event callback.
  *
  * Return: One if the link is up, zero if the link is down, otherwise a
  *		negative value indicating the error number.
@@ -795,7 +794,7 @@ static inline int ntb_peer_db_set(struct ntb_dev *ntb, u64 db_bits)
 }
 
 /**
- * ntb_peer_db_clear() - clear bits in the local doorbell register
+ * ntb_peer_db_clear() - clear bits in the peer doorbell register
  * @ntb:	NTB device context.
  * @db_bits:	Doorbell bits to clear.
  *
diff --git a/include/linux/ntb_transport.h b/include/linux/ntb_transport.h
index 2862861..7243eb9 100644
--- a/include/linux/ntb_transport.h
+++ b/include/linux/ntb_transport.h
@@ -83,3 +83,4 @@ void *ntb_transport_rx_remove(struct ntb_transport_qp *qp, unsigned int *len);
 void ntb_transport_link_up(struct ntb_transport_qp *qp);
 void ntb_transport_link_down(struct ntb_transport_qp *qp);
 bool ntb_transport_link_query(struct ntb_transport_qp *qp);
+unsigned int ntb_transport_tx_free_entry(struct ntb_transport_qp *qp);