[ofa-general] [UPDATE][PATCH 2/3] ib/ipoib: set IPoIB-UD RX S/G parameters

Shirley Ma mashirle at us.ibm.com
Thu Jan 31 11:35:48 PST 2008


This patch sets up all IPoIB-UD RX S/G related parameters.

Signed-off-by: Shirley Ma <xma at us.ibm.com>
---

 drivers/infiniband/ulp/ipoib/ipoib.h           |   13 +++++++++++++
 drivers/infiniband/ulp/ipoib/ipoib_main.c      |   19
++++++++++++++-----
 drivers/infiniband/ulp/ipoib/ipoib_multicast.c |    3 +--
 drivers/infiniband/ulp/ipoib/ipoib_verbs.c     |   14 ++++++++++++--
 4 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h
b/drivers/infiniband/ulp/ipoib/ipoib.h
index d1d3ca2..004a80b 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -61,6 +61,10 @@ enum {
 
 	IPOIB_ENCAP_LEN		  = 4,
 
+	IPOIB_MAX_IB_MTU	  = 4096,
+	IPOIB_UD_MAX_RX_SG	  = ALIGN(IPOIB_MAX_IB_MTU + IB_GRH_BYTES + 4,
+					  PAGE_SIZE) / PAGE_SIZE,  /* padding to align IP header */
+
 	IPOIB_CM_MTU		  = 0x10000 - 0x10, /* padding to align header to 16 */
 	IPOIB_CM_BUF_SIZE	  = IPOIB_CM_MTU  + IPOIB_ENCAP_LEN,
 	IPOIB_CM_HEAD_SIZE	  = IPOIB_CM_BUF_SIZE % PAGE_SIZE,
@@ -319,6 +323,9 @@ struct ipoib_dev_priv {
 	struct dentry *mcg_dentry;
 	struct dentry *path_dentry;
 #endif
+	int max_ib_mtu;
+	struct ib_sge rx_sge[IPOIB_UD_MAX_RX_SG];
+	struct ib_recv_wr rx_wr;
 };
 
 struct ipoib_ah {
@@ -359,6 +366,12 @@ struct ipoib_neigh {
 	struct list_head    list;
 };
 
+#define IPOIB_UD_MTU(ib_mtu)		(ib_mtu - IPOIB_ENCAP_LEN)
+/* padding to align IP header */ 
+#define IPOIB_UD_BUF_SIZE(ib_mtu)	(ib_mtu + IB_GRH_BYTES + 4) 
+#define IPOIB_UD_HEAD_SIZE(ib_mtu)	(IPOIB_UD_BUF_SIZE(ib_mtu)) %
PAGE_SIZE
+#define IPOIB_UD_RX_SG(ib_mtu)		ALIGN(IPOIB_UD_BUF_SIZE(ib_mtu),
PAGE_SIZE) / PAGE_SIZE
+
 /*
  * We stash a pointer to our private neighbour information after our
  * hardware address in neigh->ha.  The ALIGN() expression here makes
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c
b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index a082466..242591f 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -194,7 +194,7 @@ static int ipoib_change_mtu(struct net_device *dev,
int new_mtu)
 		return 0;
 	}
 
-	if (new_mtu > IPOIB_PACKET_SIZE - IPOIB_ENCAP_LEN)
+	if (new_mtu > IPOIB_UD_MTU(priv->max_ib_mtu))
 		return -EINVAL;
 
 	priv->admin_mtu = new_mtu;
@@ -968,10 +968,6 @@ static void ipoib_setup(struct net_device *dev)
 	dev->tx_queue_len	 = ipoib_sendq_size * 2;
 	dev->features		 = NETIF_F_VLAN_CHALLENGED | NETIF_F_LLTX;
 
-	/* MTU will be reset when mcast join happens */
-	dev->mtu		 = IPOIB_PACKET_SIZE - IPOIB_ENCAP_LEN;
-	priv->mcast_mtu		 = priv->admin_mtu = dev->mtu;
-
 	memcpy(dev->broadcast, ipv4_bcast_addr, INFINIBAND_ALEN);
 
 	netif_carrier_off(dev);
@@ -1103,6 +1099,7 @@ static struct net_device *ipoib_add_port(const
char *format,
 					 struct ib_device *hca, u8 port)
 {
 	struct ipoib_dev_priv *priv;
+	struct ib_port_attr attr;
 	int result = -ENOMEM;
 
 	priv = ipoib_intf_alloc(format);
@@ -1111,6 +1108,18 @@ static struct net_device *ipoib_add_port(const
char *format,
 
 	SET_NETDEV_DEV(priv->dev, hca->dma_device);
 
+	if (!ib_query_port(hca, port, &attr))
+		priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu);
+	else {
+		printk(KERN_WARNING "%s: ib_query_port %d failed\n",
+		       hca->name, port);
+		goto device_init_failed;
+	}
+
+	/* MTU will be reset when mcast join happens */
+	priv->dev->mtu  = IPOIB_UD_MTU(priv->max_ib_mtu);
+	priv->mcast_mtu  = priv->admin_mtu = priv->dev->mtu;
+
 	result = ib_query_pkey(hca, port, 0, &priv->pkey);
 	if (result) {
 		printk(KERN_WARNING "%s: ib_query_pkey port %d failed (ret = %d)\n",
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 2628339..630b429 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -567,8 +567,7 @@ void ipoib_mcast_join_task(struct work_struct *work)
 		return;
 	}
 
-	priv->mcast_mtu = ib_mtu_enum_to_int(priv->broadcast->mcmember.mtu) -
-		IPOIB_ENCAP_LEN;
+	priv->mcast_mtu =
IPOIB_UD_MTU(ib_mtu_enum_to_int(priv->broadcast->mcmember.mtu));
 
 	if (!ipoib_cm_admin_enabled(dev))
 		dev->mtu = min(priv->mcast_mtu, priv->admin_mtu);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
index 433e99a..7e2d4d6 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
@@ -150,13 +150,13 @@ int ipoib_transport_dev_init(struct net_device
*dev, struct ib_device *ca)
 			.max_send_wr  = ipoib_sendq_size,
 			.max_recv_wr  = ipoib_recvq_size,
 			.max_send_sge = 1,
-			.max_recv_sge = 1
+			.max_recv_sge = IPOIB_UD_RX_SG(priv->max_ib_mtu) 
 		},
 		.sq_sig_type = IB_SIGNAL_ALL_WR,
 		.qp_type     = IB_QPT_UD
 	};
 
-	int ret, size;
+	int ret, size, i;
 
 	priv->pd = ib_alloc_pd(priv->ca);
 	if (IS_ERR(priv->pd)) {
@@ -208,6 +208,16 @@ int ipoib_transport_dev_init(struct net_device
*dev, struct ib_device *ca)
 	priv->tx_wr.num_sge	= 1;
 	priv->tx_wr.send_flags	= IB_SEND_SIGNALED;
 
+	priv->rx_sge[0].length = IPOIB_UD_HEAD_SIZE(priv->max_ib_mtu);
+	for (i = 0; i < IPOIB_UD_RX_SG(priv->max_ib_mtu) - 1; ++i) {
+		priv->rx_sge[i + 1].length = PAGE_SIZE;
+		priv->rx_sge[i].lkey = priv->mr->lkey;
+	}
+	priv->rx_sge[i + 1].lkey = priv->mr->lkey;
+	priv->rx_wr.num_sge = IPOIB_UD_RX_SG(priv->max_ib_mtu);
+	priv->rx_wr.next = NULL;
+	priv->rx_wr.sg_list = priv->rx_sge;
+
 	return 0;
 
 out_free_cq:





More information about the general mailing list