IPoIB: Use checksum offload support if available

For HCAs that support checksum offload (ie that set IB_DEVICE_UD_IP_CSUM
in the device capabilities flags), have IPoIB set NETIF_F_IP_CSUM and
use the HCA to generate and verify IP checksums.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

4 files changed, 41 insertions, 1 deletions

diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 054fab8e27a..08930ca41a3 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -87,6 +87,7 @@ enum {
 	IPOIB_MCAST_STARTED	  = 8,
 	IPOIB_FLAG_ADMIN_CM	  = 9,
 	IPOIB_FLAG_UMCAST	  = 10,
+	IPOIB_FLAG_CSUM		  = 11,
 
 	IPOIB_MAX_BACKOFF_SECONDS = 16,
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 2490b2d79db..edf63dc0afe 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -1383,6 +1383,10 @@ static ssize_t set_mode(struct device *d, struct device_attribute *attr,
 		set_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags);
 		ipoib_warn(priv, "enabling connected mode "
 			   "will cause multicast packet drops\n");
+
+		dev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_SG);
+		priv->tx_wr.send_flags &= ~IB_SEND_IP_CSUM;
+
 		ipoib_flush_paths(dev);
 		return count;
 	}
@@ -1391,6 +1395,10 @@ static ssize_t set_mode(struct device *d, struct device_attribute *attr,
 		clear_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags);
 		dev->mtu = min(priv->mcast_mtu, dev->mtu);
 		ipoib_flush_paths(dev);
+
+		if (test_bit(IPOIB_FLAG_CSUM, &priv->flags))
+			dev->features |= NETIF_F_IP_CSUM | NETIF_F_SG;
+
 		return count;
 	}
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 08c4396cf41..d13f4fb3853 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -231,6 +231,10 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	skb->dev = dev;
 	/* XXX get correct PACKET_ type here */
 	skb->pkt_type = PACKET_HOST;
+
+	if (test_bit(IPOIB_FLAG_CSUM, &priv->flags) && likely(wc->csum_ok))
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+
 	netif_receive_skb(skb);
 
 repost:
@@ -442,6 +446,11 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb,
 		return;
 	}
 
+	if (skb->ip_summed == CHECKSUM_PARTIAL)
+		priv->tx_wr.send_flags |= IB_SEND_IP_CSUM;
+	else
+		priv->tx_wr.send_flags &= ~IB_SEND_IP_CSUM;
+
 	if (unlikely(post_send(priv, priv->tx_head & (ipoib_sendq_size - 1),
 			       address->ah, qpn,
 			       tx_req->mapping, skb_headlen(skb),
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 57282048865..329b4675aec 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1105,6 +1105,7 @@ static struct net_device *ipoib_add_port(const char *format,
 					 struct ib_device *hca, u8 port)
 {
 	struct ipoib_dev_priv *priv;
+	struct ib_device_attr *device_attr;
 	int result = -ENOMEM;
 
 	priv = ipoib_intf_alloc(format);
@@ -1120,6 +1121,28 @@ static struct net_device *ipoib_add_port(const char *format,
 		goto device_init_failed;
 	}
 
+	device_attr = kmalloc(sizeof *device_attr, GFP_KERNEL);
+	if (!device_attr) {
+		printk(KERN_WARNING "%s: allocation of %zu bytes failed\n",
+		       hca->name, sizeof *device_attr);
+		goto device_init_failed;
+	}
+
+	result = ib_query_device(hca, device_attr);
+	if (result) {
+		printk(KERN_WARNING "%s: ib_query_device failed (ret = %d)\n",
+		       hca->name, result);
+		kfree(device_attr);
+		goto device_init_failed;
+	}
+
+	if (device_attr->device_cap_flags & IB_DEVICE_UD_IP_CSUM) {
+		set_bit(IPOIB_FLAG_CSUM, &priv->flags);
+		priv->dev->features |= NETIF_F_SG | NETIF_F_IP_CSUM;
+	}
+
+	kfree(device_attr);
+
 	/*
 	 * Set the full membership bit, so that we join the right
 	 * broadcast group, etc.
@@ -1137,7 +1160,6 @@ static struct net_device *ipoib_add_port(const char *format,
 	} else
 		memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw, sizeof (union ib_gid));
 
-
 	result = ipoib_dev_init(priv->dev, hca, port);
 	if (result < 0) {
 		printk(KERN_WARNING "%s: failed to initialize port %d (ret = %d)\n",