Merge branch 'mlx4'

Amir Vadai says:

====================
net/mlx4: Mellanox driver update 07-11-2013

This patchset contains some enhancements and bug fixes for the mlx4_* drivers.
Patchset was applied and tested against commit: "9bb8ca8 virtio-net: switch to
use XPS to choose txq"
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

22 files changed, 383 insertions, 228 deletions

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 7567437dbd3..6a0a0d29660 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -526,7 +526,6 @@ static int mlx4_ib_modify_device(struct ib_device *ibdev, int mask,
 	if (IS_ERR(mailbox))
 		return 0;
 
-	memset(mailbox->buf, 0, 256);
 	memcpy(mailbox->buf, props->node_desc, 64);
 	mlx4_cmd(to_mdev(ibdev)->dev, mailbox->dma, 1, 0,
 		 MLX4_CMD_SET_NODE, MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
@@ -547,8 +546,6 @@ static int mlx4_SET_PORT(struct mlx4_ib_dev *dev, u8 port, int reset_qkey_viols,
 	if (IS_ERR(mailbox))
 		return PTR_ERR(mailbox);
 
-	memset(mailbox->buf, 0, 256);
-
 	if (dev->dev->flags & MLX4_FLAG_OLD_PORT_CMDS) {
 		*(u8 *) mailbox->buf	     = !!reset_qkey_viols << 6;
 		((__be32 *) mailbox->buf)[2] = cpu_to_be32(cap_mask);
@@ -879,8 +876,6 @@ static int __mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_att
 	struct mlx4_ib_dev *mdev = to_mdev(qp->device);
 	struct mlx4_cmd_mailbox *mailbox;
 	struct mlx4_net_trans_rule_hw_ctrl *ctrl;
-	size_t rule_size = sizeof(struct mlx4_net_trans_rule_hw_ctrl) +
-			   (sizeof(struct _rule_hw) * flow_attr->num_of_specs);
 
 	static const u16 __mlx4_domain[] = {
 		[IB_FLOW_DOMAIN_USER] = MLX4_DOMAIN_UVERBS,
@@ -905,7 +900,6 @@ static int __mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_att
 	mailbox = mlx4_alloc_cmd_mailbox(mdev->dev);
 	if (IS_ERR(mailbox))
 		return PTR_ERR(mailbox);
-	memset(mailbox->buf, 0, rule_size);
 	ctrl = mailbox->buf;
 
 	ctrl->prio = cpu_to_be16(__mlx4_domain[domain] |
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 65d41b76fa2..1e9970d2f0f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -1539,11 +1539,6 @@ out:
 	return ret;
 }
 
-static int calculate_transition(u16 oper_vlan, u16 admin_vlan)
-{
-	return (2 * (oper_vlan == MLX4_VGT) + (admin_vlan == MLX4_VGT));
-}
-
 static int mlx4_master_immediate_activate_vlan_qos(struct mlx4_priv *priv,
 					    int slave, int port)
 {
@@ -1553,7 +1548,6 @@ static int mlx4_master_immediate_activate_vlan_qos(struct mlx4_priv *priv,
 	struct mlx4_dev *dev = &(priv->dev);
 	int err;
 	int admin_vlan_ix = NO_INDX;
-	enum mlx4_vlan_transition vlan_trans;
 
 	vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port];
 	vp_admin = &priv->mfunc.master.vf_admin[slave].vport[port];
@@ -1563,12 +1557,8 @@ static int mlx4_master_immediate_activate_vlan_qos(struct mlx4_priv *priv,
 	    vp_oper->state.link_state == vp_admin->link_state)
 		return 0;
 
-	vlan_trans = calculate_transition(vp_oper->state.default_vlan,
-					  vp_admin->default_vlan);
-
 	if (!(priv->mfunc.master.slave_state[slave].active &&
-	      dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_UPDATE_QP &&
-	      vlan_trans == MLX4_VLAN_TRANSITION_VST_VST)) {
+	      dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_UPDATE_QP)) {
 		/* even if the UPDATE_QP command isn't supported, we still want
 		 * to set this VF link according to the admin directive
 		 */
@@ -1586,15 +1576,19 @@ static int mlx4_master_immediate_activate_vlan_qos(struct mlx4_priv *priv,
 		return -ENOMEM;
 
 	if (vp_oper->state.default_vlan != vp_admin->default_vlan) {
-		err = __mlx4_register_vlan(&priv->dev, port,
-					   vp_admin->default_vlan,
-					   &admin_vlan_ix);
-		if (err) {
-			kfree(work);
-			mlx4_warn((&priv->dev),
-				  "No vlan resources slave %d, port %d\n",
-				  slave, port);
-			return err;
+		if (MLX4_VGT != vp_admin->default_vlan) {
+			err = __mlx4_register_vlan(&priv->dev, port,
+						   vp_admin->default_vlan,
+						   &admin_vlan_ix);
+			if (err) {
+				kfree(work);
+				mlx4_warn((&priv->dev),
+					  "No vlan resources slave %d, port %d\n",
+					  slave, port);
+				return err;
+			}
+		} else {
+			admin_vlan_ix = NO_INDX;
 		}
 		work->flags |= MLX4_VF_IMMED_VLAN_FLAG_VLAN;
 		mlx4_dbg((&(priv->dev)),
@@ -2199,6 +2193,8 @@ struct mlx4_cmd_mailbox *mlx4_alloc_cmd_mailbox(struct mlx4_dev *dev)
 		return ERR_PTR(-ENOMEM);
 	}
 
+	memset(mailbox->buf, 0, MLX4_MAILBOX_SIZE);
+
 	return mailbox;
 }
 EXPORT_SYMBOL_GPL(mlx4_alloc_cmd_mailbox);
diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c
index 004e4231af6..22fcbe78311 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cq.c
@@ -128,8 +128,6 @@ int mlx4_cq_modify(struct mlx4_dev *dev, struct mlx4_cq *cq,
 		return PTR_ERR(mailbox);
 
 	cq_context = mailbox->buf;
-	memset(cq_context, 0, sizeof *cq_context);
-
 	cq_context->cq_max_count = cpu_to_be16(count);
 	cq_context->cq_period    = cpu_to_be16(period);
 
@@ -153,8 +151,6 @@ int mlx4_cq_resize(struct mlx4_dev *dev, struct mlx4_cq *cq,
 		return PTR_ERR(mailbox);
 
 	cq_context = mailbox->buf;
-	memset(cq_context, 0, sizeof *cq_context);
-
 	cq_context->logsize_usrpage = cpu_to_be32(ilog2(entries) << 24);
 	cq_context->log_page_size   = mtt->page_shift - 12;
 	mtt_addr = mlx4_mtt_addr(dev, mtt);
@@ -274,8 +270,6 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
 	}
 
 	cq_context = mailbox->buf;
-	memset(cq_context, 0, sizeof *cq_context);
-
 	cq_context->flags	    = cpu_to_be32(!!collapsed << 18);
 	if (timestamp_en)
 		cq_context->flags  |= cpu_to_be32(1 << 19);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 3e2d5047cdb..3a098cc4d34 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -44,12 +44,23 @@ static void mlx4_en_cq_event(struct mlx4_cq *cq, enum mlx4_event event)
 
 
 int mlx4_en_create_cq(struct mlx4_en_priv *priv,
-		      struct mlx4_en_cq *cq,
-		      int entries, int ring, enum cq_type mode)
+		      struct mlx4_en_cq **pcq,
+		      int entries, int ring, enum cq_type mode,
+		      int node)
 {
 	struct mlx4_en_dev *mdev = priv->mdev;
+	struct mlx4_en_cq *cq;
 	int err;
 
+	cq = kzalloc_node(sizeof(*cq), GFP_KERNEL, node);
+	if (!cq) {
+		cq = kzalloc(sizeof(*cq), GFP_KERNEL);
+		if (!cq) {
+			en_err(priv, "Failed to allocate CQ structure\n");
+			return -ENOMEM;
+		}
+	}
+
 	cq->size = entries;
 	cq->buf_size = cq->size * mdev->dev->caps.cqe_size;
 
@@ -57,17 +68,30 @@ int mlx4_en_create_cq(struct mlx4_en_priv *priv,
 	cq->is_tx = mode;
 	spin_lock_init(&cq->lock);
 
+	/* Allocate HW buffers on provided NUMA node.
+	 * dev->numa_node is used in mtt range allocation flow.
+	 */
+	set_dev_node(&mdev->dev->pdev->dev, node);
 	err = mlx4_alloc_hwq_res(mdev->dev, &cq->wqres,
 				cq->buf_size, 2 * PAGE_SIZE);
+	set_dev_node(&mdev->dev->pdev->dev, mdev->dev->numa_node);
 	if (err)
-		return err;
+		goto err_cq;
 
 	err = mlx4_en_map_buffer(&cq->wqres.buf);
 	if (err)
-		mlx4_free_hwq_res(mdev->dev, &cq->wqres, cq->buf_size);
-	else
-		cq->buf = (struct mlx4_cqe *) cq->wqres.buf.direct.buf;
+		goto err_res;
 
+	cq->buf = (struct mlx4_cqe *)cq->wqres.buf.direct.buf;
+	*pcq = cq;
+
+	return 0;
+
+err_res:
+	mlx4_free_hwq_res(mdev->dev, &cq->wqres, cq->buf_size);
+err_cq:
+	kfree(cq);
+	*pcq = NULL;
 	return err;
 }
 
@@ -117,12 +141,12 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 		struct mlx4_en_cq *rx_cq;
 
 		cq_idx = cq_idx % priv->rx_ring_num;
-		rx_cq = &priv->rx_cq[cq_idx];
+		rx_cq = priv->rx_cq[cq_idx];
 		cq->vector = rx_cq->vector;
 	}
 
 	if (!cq->is_tx)
-		cq->size = priv->rx_ring[cq->ring].actual_size;
+		cq->size = priv->rx_ring[cq->ring]->actual_size;
 
 	if ((cq->is_tx && priv->hwtstamp_config.tx_type) ||
 	    (!cq->is_tx && priv->hwtstamp_config.rx_filter))
@@ -146,9 +170,10 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 	return 0;
 }
 
-void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
+void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq)
 {
 	struct mlx4_en_dev *mdev = priv->mdev;
+	struct mlx4_en_cq *cq = *pcq;
 
 	mlx4_en_unmap_buffer(&cq->wqres.buf);
 	mlx4_free_hwq_res(mdev->dev, &cq->wqres, cq->buf_size);
@@ -157,6 +182,8 @@ void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
 	cq->vector = 0;
 	cq->buf_size = 0;
 	cq->buf = NULL;
+	kfree(cq);
+	*pcq = NULL;
 }
 
 void mlx4_en_deactivate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 0c750985f47..0596f9f85a0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -51,10 +51,10 @@ static int mlx4_en_moderation_update(struct mlx4_en_priv *priv)
 	int err = 0;
 
 	for (i = 0; i < priv->tx_ring_num; i++) {
-		priv->tx_cq[i].moder_cnt = priv->tx_frames;
-		priv->tx_cq[i].moder_time = priv->tx_usecs;
+		priv->tx_cq[i]->moder_cnt = priv->tx_frames;
+		priv->tx_cq[i]->moder_time = priv->tx_usecs;
 		if (priv->port_up) {
-			err = mlx4_en_set_cq_moder(priv, &priv->tx_cq[i]);
+			err = mlx4_en_set_cq_moder(priv, priv->tx_cq[i]);
 			if (err)
 				return err;
 		}
@@ -64,11 +64,11 @@ static int mlx4_en_moderation_update(struct mlx4_en_priv *priv)
 		return 0;
 
 	for (i = 0; i < priv->rx_ring_num; i++) {
-		priv->rx_cq[i].moder_cnt = priv->rx_frames;
-		priv->rx_cq[i].moder_time = priv->rx_usecs;
+		priv->rx_cq[i]->moder_cnt = priv->rx_frames;
+		priv->rx_cq[i]->moder_time = priv->rx_usecs;
 		priv->last_moder_time[i] = MLX4_EN_AUTO_CONF;
 		if (priv->port_up) {
-			err = mlx4_en_set_cq_moder(priv, &priv->rx_cq[i]);
+			err = mlx4_en_set_cq_moder(priv, priv->rx_cq[i]);
 			if (err)
 				return err;
 		}
@@ -274,16 +274,16 @@ static void mlx4_en_get_ethtool_stats(struct net_device *dev,
 		}
 	}
 	for (i = 0; i < priv->tx_ring_num; i++) {
-		data[index++] = priv->tx_ring[i].packets;
-		data[index++] = priv->tx_ring[i].bytes;
+		data[index++] = priv->tx_ring[i]->packets;
+		data[index++] = priv->tx_ring[i]->bytes;
 	}
 	for (i = 0; i < priv->rx_ring_num; i++) {
-		data[index++] = priv->rx_ring[i].packets;
-		data[index++] = priv->rx_ring[i].bytes;
+		data[index++] = priv->rx_ring[i]->packets;
+		data[index++] = priv->rx_ring[i]->bytes;
 #ifdef CONFIG_NET_RX_BUSY_POLL
-		data[index++] = priv->rx_ring[i].yields;
-		data[index++] = priv->rx_ring[i].misses;
-		data[index++] = priv->rx_ring[i].cleaned;
+		data[index++] = priv->rx_ring[i]->yields;
+		data[index++] = priv->rx_ring[i]->misses;
+		data[index++] = priv->rx_ring[i]->cleaned;
 #endif
 	}
 	spin_unlock_bh(&priv->stats_lock);
@@ -510,9 +510,9 @@ static int mlx4_en_set_ringparam(struct net_device *dev,
 	tx_size = max_t(u32, tx_size, MLX4_EN_MIN_TX_SIZE);
 	tx_size = min_t(u32, tx_size, MLX4_EN_MAX_TX_SIZE);
 
-	if (rx_size == (priv->port_up ? priv->rx_ring[0].actual_size :
-					priv->rx_ring[0].size) &&
-	    tx_size == priv->tx_ring[0].size)
+	if (rx_size == (priv->port_up ? priv->rx_ring[0]->actual_size :
+					priv->rx_ring[0]->size) &&
+	    tx_size == priv->tx_ring[0]->size)
 		return 0;
 
 	mutex_lock(&mdev->state_lock);
@@ -553,8 +553,8 @@ static void mlx4_en_get_ringparam(struct net_device *dev,
 	param->rx_max_pending = MLX4_EN_MAX_RX_SIZE;
 	param->tx_max_pending = MLX4_EN_MAX_TX_SIZE;
 	param->rx_pending = priv->port_up ?
-		priv->rx_ring[0].actual_size : priv->rx_ring[0].size;
-	param->tx_pending = priv->tx_ring[0].size;
+		priv->rx_ring[0]->actual_size : priv->rx_ring[0]->size;
+	param->tx_pending = priv->tx_ring[0]->size;
 }
 
 static u32 mlx4_en_get_rxfh_indir_size(struct net_device *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index b5554121aca..e72d8a112a6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -75,7 +75,7 @@ static int mlx4_en_low_latency_recv(struct napi_struct *napi)
 	struct mlx4_en_cq *cq = container_of(napi, struct mlx4_en_cq, napi);
 	struct net_device *dev = cq->dev;
 	struct mlx4_en_priv *priv = netdev_priv(dev);
-	struct mlx4_en_rx_ring *rx_ring = &priv->rx_ring[cq->ring];
+	struct mlx4_en_rx_ring *rx_ring = priv->rx_ring[cq->ring];
 	int done;
 
 	if (!priv->port_up)
@@ -102,6 +102,7 @@ struct mlx4_en_filter {
 	struct list_head next;
 	struct work_struct work;
 
+	u8     ip_proto;
 	__be32 src_ip;
 	__be32 dst_ip;
 	__be16 src_port;
@@ -120,14 +121,26 @@ struct mlx4_en_filter {
 
 static void mlx4_en_filter_rfs_expire(struct mlx4_en_priv *priv);
 
+static enum mlx4_net_trans_rule_id mlx4_ip_proto_to_trans_rule_id(u8 ip_proto)
+{
+	switch (ip_proto) {
+	case IPPROTO_UDP:
+		return MLX4_NET_TRANS_RULE_ID_UDP;
+	case IPPROTO_TCP:
+		return MLX4_NET_TRANS_RULE_ID_TCP;
+	default:
+		return -EPROTONOSUPPORT;
+	}
+};
+
 static void mlx4_en_filter_work(struct work_struct *work)
 {
 	struct mlx4_en_filter *filter = container_of(work,
 						     struct mlx4_en_filter,
 						     work);
 	struct mlx4_en_priv *priv = filter->priv;
-	struct mlx4_spec_list spec_tcp = {
-		.id = MLX4_NET_TRANS_RULE_ID_TCP,
+	struct mlx4_spec_list spec_tcp_udp = {
+		.id = mlx4_ip_proto_to_trans_rule_id(filter->ip_proto),
 		{
 			.tcp_udp = {
 				.dst_port = filter->dst_port,
@@ -163,9 +176,14 @@ static void mlx4_en_filter_work(struct work_struct *work)
 	int rc;
 	__be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16);
 
+	if (spec_tcp_udp.id < 0) {
+		en_warn(priv, "RFS: ignoring unsupported ip protocol (%d)\n",
+			filter->ip_proto);
+		goto ignore;
+	}
 	list_add_tail(&spec_eth.list, &rule.list);
 	list_add_tail(&spec_ip.list, &rule.list);
-	list_add_tail(&spec_tcp.list, &rule.list);
+	list_add_tail(&spec_tcp_udp.list, &rule.list);
 
 	rule.qpn = priv->rss_map.qps[filter->rxq_index].qpn;
 	memcpy(spec_eth.eth.dst_mac, priv->dev->dev_addr, ETH_ALEN);
@@ -183,6 +201,7 @@ static void mlx4_en_filter_work(struct work_struct *work)
 	if (rc)
 		en_err(priv, "Error attaching flow. err = %d\n", rc);
 
+ignore:
 	mlx4_en_filter_rfs_expire(priv);
 
 	filter->activated = 1;
@@ -206,8 +225,8 @@ filter_hash_bucket(struct mlx4_en_priv *priv, __be32 src_ip, __be32 dst_ip,
 
 static struct mlx4_en_filter *
 mlx4_en_filter_alloc(struct mlx4_en_priv *priv, int rxq_index, __be32 src_ip,
-		     __be32 dst_ip, __be16 src_port, __be16 dst_port,
-		     u32 flow_id)
+		     __be32 dst_ip, u8 ip_proto, __be16 src_port,
+		     __be16 dst_port, u32 flow_id)
 {
 	struct mlx4_en_filter *filter = NULL;
 
@@ -221,6 +240,7 @@ mlx4_en_filter_alloc(struct mlx4_en_priv *priv, int rxq_index, __be32 src_ip,
 
 	filter->src_ip = src_ip;
 	filter->dst_ip = dst_ip;
+	filter->ip_proto = ip_proto;
 	filter->src_port = src_port;
 	filter->dst_port = dst_port;
 
@@ -252,7 +272,7 @@ static void mlx4_en_filter_free(struct mlx4_en_filter *filter)
 
 static inline struct mlx4_en_filter *
 mlx4_en_filter_find(struct mlx4_en_priv *priv, __be32 src_ip, __be32 dst_ip,
-		    __be16 src_port, __be16 dst_port)
+		    u8 ip_proto, __be16 src_port, __be16 dst_port)
 {
 	struct mlx4_en_filter *filter;
 	struct mlx4_en_filter *ret = NULL;
@@ -263,6 +283,7 @@ mlx4_en_filter_find(struct mlx4_en_priv *priv, __be32 src_ip, __be32 dst_ip,
 			     filter_chain) {
 		if (filter->src_ip == src_ip &&
 		    filter->dst_ip == dst_ip &&
+		    filter->ip_proto == ip_proto &&
 		    filter->src_port == src_port &&
 		    filter->dst_port == dst_port) {
 			ret = filter;
@@ -281,6 +302,7 @@ mlx4_en_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
 	struct mlx4_en_filter *filter;
 	const struct iphdr *ip;
 	const __be16 *ports;
+	u8 ip_proto;
 	__be32 src_ip;
 	__be32 dst_ip;
 	__be16 src_port;
@@ -295,18 +317,19 @@ mlx4_en_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
 	if (ip_is_fragment(ip))
 		return -EPROTONOSUPPORT;
 
+	if ((ip->protocol != IPPROTO_TCP) && (ip->protocol != IPPROTO_UDP))
+		return -EPROTONOSUPPORT;
 	ports = (const __be16 *)(skb->data + nhoff + 4 * ip->ihl);
 
+	ip_proto = ip->protocol;
 	src_ip = ip->saddr;
 	dst_ip = ip->daddr;
 	src_port = ports[0];
 	dst_port = ports[1];
 
-	if (ip->protocol != IPPROTO_TCP)
-		return -EPROTONOSUPPORT;
-
 	spin_lock_bh(&priv->filters_lock);
-	filter = mlx4_en_filter_find(priv, src_ip, dst_ip, src_port, dst_port);
+	filter = mlx4_en_filter_find(priv, src_ip, dst_ip, ip_proto,
+				     src_port, dst_port);
 	if (filter) {
 		if (filter->rxq_index == rxq_index)
 			goto out;
@@ -314,7 +337,7 @@ mlx4_en_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
 		filter->rxq_index = rxq_index;
 	} else {
 		filter = mlx4_en_filter_alloc(priv, rxq_index,
-					      src_ip, dst_ip,
+					      src_ip, dst_ip, ip_proto,
 					      src_port, dst_port, flow_id);
 		if (!filter) {
 			ret = -ENOMEM;
@@ -332,8 +355,7 @@ err:
 	return ret;
 }
 
-void mlx4_en_cleanup_filters(struct mlx4_en_priv *priv,
-			     struct mlx4_en_rx_ring *rx_ring)
+void mlx4_en_cleanup_filters(struct mlx4_en_priv *priv)
 {
 	struct mlx4_en_filter *filter, *tmp;
 	LIST_HEAD(del_list);
@@ -1219,7 +1241,7 @@ static void mlx4_en_netpoll(struct net_device *dev)
 	int i;
 
 	for (i = 0; i < priv->rx_ring_num; i++) {
-		cq = &priv->rx_cq[i];
+		cq = priv->rx_cq[i];
 		spin_lock_irqsave(&cq->lock, flags);
 		napi_synchronize(&cq->napi);
 		mlx4_en_process_rx_cq(dev, cq, 0);
@@ -1241,8 +1263,8 @@ static void mlx4_en_tx_timeout(struct net_device *dev)
 		if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, i)))
 			continue;
 		en_warn(priv, "TX timeout on queue: %d, QP: 0x%x, CQ: 0x%x, Cons: 0x%x, Prod: 0x%x\n",
-			i, priv->tx_ring[i].qpn, priv->tx_ring[i].cqn,
-			priv->tx_ring[i].cons, priv->tx_ring[i].prod);
+			i, priv->tx_ring[i]->qpn, priv->tx_ring[i]->cqn,
+			priv->tx_ring[i]->cons, priv->tx_ring[i]->prod);
 	}
 
 	priv->port_stats.tx_timeout++;
@@ -1282,7 +1304,7 @@ static void mlx4_en_set_default_moderation(struct mlx4_en_priv *priv)
 
 	/* Setup cq moderation params */
 	for (i = 0; i < priv->rx_ring_num; i++) {
-		cq = &priv->rx_cq[i];
+		cq = priv->rx_cq[i];
 		cq->moder_cnt = priv->rx_frames;
 		cq->moder_time = priv->rx_usecs;
 		priv->last_moder_time[i] = MLX4_EN_AUTO_CONF;
@@ -1291,7 +1313,7 @@ static void mlx4_en_set_default_moderation(struct mlx4_en_priv *priv)
 	}
 
 	for (i = 0; i < priv->tx_ring_num; i++) {
-		cq = &priv->tx_cq[i];
+		cq = priv->tx_cq[i];
 		cq->moder_cnt = priv->tx_frames;
 		cq->moder_time = priv->tx_usecs;
 	}
@@ -1325,8 +1347,8 @@ static void mlx4_en_auto_moderation(struct mlx4_en_priv *priv)
 
 	for (ring = 0; ring < priv->rx_ring_num; ring++) {
 		spin_lock_bh(&priv->stats_lock);
-		rx_packets = priv->rx_ring[ring].packets;
-		rx_bytes = priv->rx_ring[ring].bytes;
+		rx_packets = priv->rx_ring[ring]->packets;
+		rx_bytes = priv->rx_ring[ring]->bytes;
 		spin_unlock_bh(&priv->stats_lock);
 
 		rx_pkt_diff = ((unsigned long) (rx_packets -
@@ -1355,7 +1377,7 @@ static void mlx4_en_auto_moderation(struct mlx4_en_priv *priv)
 
 		if (moder_time != priv->last_moder_time[ring]) {
 			priv->last_moder_time[ring] = moder_time;
-			cq = &priv->rx_cq[ring];
+			cq = priv->rx_cq[ring];
 			cq->moder_time = moder_time;
 			cq->moder_cnt = priv->rx_frames;
 			err = mlx4_en_set_cq_moder(priv, cq);
@@ -1478,7 +1500,7 @@ int mlx4_en_start_port(struct net_device *dev)
 		return err;
 	}
 	for (i = 0; i < priv->rx_ring_num; i++) {
-		cq = &priv->rx_cq[i];
+		cq = priv->rx_cq[i];
 
 		mlx4_en_cq_init_lock(cq);
 
@@ -1496,7 +1518,7 @@ int mlx4_en_start_port(struct net_device *dev)
 			goto cq_err;
 		}
 		mlx4_en_arm_cq(priv, cq);
-		priv->rx_ring[i].cqn = cq->mcq.cqn;
+		priv->rx_ring[i]->cqn = cq->mcq.cqn;
 		++rx_index;
 	}
 
@@ -1522,7 +1544,7 @@ int mlx4_en_start_port(struct net_device *dev)
 	/* Configure tx cq's and rings */
 	for (i = 0; i < priv->tx_ring_num; i++) {
 		/* Configure cq */
-		cq = &priv->tx_cq[i];
+		cq = priv->tx_cq[i];
 		err = mlx4_en_activate_cq(priv, cq, i);
 		if (err) {
 			en_err(priv, "Failed allocating Tx CQ\n");
@@ -1538,7 +1560,7 @@ int mlx4_en_start_port(struct net_device *dev)
 		cq->buf->wqe_index = cpu_to_be16(0xffff);
 
 		/* Configure ring */
-		tx_ring = &priv->tx_ring[i];
+		tx_ring = priv->tx_ring[i];
 		err = mlx4_en_activate_tx_ring(priv, tx_ring, cq->mcq.cqn,
 			i / priv->num_tx_rings_p_up);
 		if (err) {
@@ -1608,8 +1630,8 @@ int mlx4_en_start_port(struct net_device *dev)
 
 tx_err:
 	while (tx_index--) {
-		mlx4_en_deactivate_tx_ring(priv, &priv->tx_ring[tx_index]);
-		mlx4_en_deactivate_cq(priv, &priv->tx_cq[tx_index]);
+		mlx4_en_deactivate_tx_ring(priv, priv->tx_ring[tx_index]);
+		mlx4_en_deactivate_cq(priv, priv->tx_cq[tx_index]);
 	}
 	mlx4_en_destroy_drop_qp(priv);
 rss_err:
@@ -1618,9 +1640,9 @@ mac_err:
 	mlx4_en_put_qp(priv);
 cq_err:
 	while (rx_index--)
-		mlx4_en_deactivate_cq(priv, &priv->rx_cq[rx_index]);
+		mlx4_en_deactivate_cq(priv, priv->rx_cq[rx_index]);
 	for (i = 0; i < priv->rx_ring_num; i++)
-		mlx4_en_deactivate_rx_ring(priv, &priv->rx_ring[i]);
+		mlx4_en_deactivate_rx_ring(priv, priv->rx_ring[i]);
 
 	return err; /* need to close devices */
 }
@@ -1716,13 +1738,13 @@ void mlx4_en_stop_port(struct net_device *dev, int detach)
 
 	/* Free TX Rings */
 	for (i = 0; i < priv->tx_ring_num; i++) {
-		mlx4_en_deactivate_tx_ring(priv, &priv->tx_ring[i]);
-		mlx4_en_deactivate_cq(priv, &priv->tx_cq[i]);
+		mlx4_en_deactivate_tx_ring(priv, priv->tx_ring[i]);
+		mlx4_en_deactivate_cq(priv, priv->tx_cq[i]);
 	}
 	msleep(10);
 
 	for (i = 0; i < priv->tx_ring_num; i++)
-		mlx4_en_free_tx_buf(dev, &priv->tx_ring[i]);
+		mlx4_en_free_tx_buf(dev, priv->tx_ring[i]);
 
 	/* Free RSS qps */
 	mlx4_en_release_rss_steer(priv);
@@ -1734,7 +1756,7 @@ void mlx4_en_stop_port(struct net_device *dev, int detach)
 
 	/* Free RX Rings */
 	for (i = 0; i < priv->rx_ring_num; i++) {
-		struct mlx4_en_cq *cq = &priv->rx_cq[i];
+		struct mlx4_en_cq *cq = priv->rx_cq[i];
 
 		local_bh_disable();
 		while (!mlx4_en_cq_lock_napi(cq)) {
@@ -1745,7 +1767,7 @@ void mlx4_en_stop_port(struct net_device *dev, int detach)
 
 		while (test_bit(NAPI_STATE_SCHED, &cq->napi.state))
 			msleep(1);
-		mlx4_en_deactivate_rx_ring(priv, &priv->rx_ring[i]);
+		mlx4_en_deactivate_rx_ring(priv, priv->rx_ring[i]);
 		mlx4_en_deactivate_cq(priv, cq);
 	}
 }
@@ -1783,15 +1805,15 @@ static void mlx4_en_clear_stats(struct net_device *dev)
 	memset(&priv->port_stats, 0, sizeof(priv->port_stats));
 
 	for (i = 0; i < priv->tx_ring_num; i++) {
-		priv->tx_ring[i].bytes = 0;
-		priv->tx_ring[i].packets = 0;
-		priv->tx_ring[i].tx_csum = 0;
+		priv->tx_ring[i]->bytes = 0;
+		priv->tx_ring[i]->packets = 0;
+		priv->tx_ring[i]->tx_csum = 0;
 	}
 	for (i = 0; i < priv->rx_ring_num; i++) {
-		priv->rx_ring[i].bytes = 0;
-		priv->rx_ring[i].packets = 0;
-		priv->rx_ring[i].csum_ok = 0;
-		priv->rx_ring[i].csum_none = 0;
+		priv->rx_ring[i]->bytes = 0;
+		priv->rx_ring[i]->packets = 0;
+		priv->rx_ring[i]->csum_ok = 0;
+		priv->rx_ring[i]->csum_none = 0;
 	}
 }
 
@@ -1848,17 +1870,17 @@ void mlx4_en_free_resources(struct mlx4_en_priv *priv)
 #endif
 
 	for (i = 0; i < priv->tx_ring_num; i++) {
-		if (priv->tx_ring[i].tx_info)
+		if (priv->tx_ring && priv->tx_ring[i])
 			mlx4_en_destroy_tx_ring(priv, &priv->tx_ring[i]);
-		if (priv->tx_cq[i].buf)
+		if (priv->tx_cq && priv->tx_cq[i])
 			mlx4_en_destroy_cq(priv, &priv->tx_cq[i]);
 	}
 
 	for (i = 0; i < priv->rx_ring_num; i++) {
-		if (priv->rx_ring[i].rx_info)
+		if (priv->rx_ring[i])
 			mlx4_en_destroy_rx_ring(priv, &priv->rx_ring[i],
 				priv->prof->rx_ring_size, priv->stride);
-		if (priv->rx_cq[i].buf)
+		if (priv->rx_cq[i])
 			mlx4_en_destroy_cq(priv, &priv->rx_cq[i]);
 	}
 
@@ -1873,6 +1895,7 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
 	struct mlx4_en_port_profile *prof = priv->prof;
 	int i;
 	int err;
+	int node;
 
 	err = mlx4_qp_reserve_range(priv->mdev->dev, priv->tx_ring_num, 256, &priv->base_tx_qpn);
 	if (err) {
@@ -1882,23 +1905,26 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
 
 	/* Create tx Rings */
 	for (i = 0; i < priv->tx_ring_num; i++) {
+		node = cpu_to_node(i % num_online_cpus());
 		if (mlx4_en_create_cq(priv, &priv->tx_cq[i],
-				      prof->tx_ring_size, i, TX))
+				      prof->tx_ring_size, i, TX, node))
 			goto err;
 
 		if (mlx4_en_create_tx_ring(priv, &priv->tx_ring[i], priv->base_tx_qpn + i,
-					   prof->tx_ring_size, TXBB_SIZE))
+					   prof->tx_ring_size, TXBB_SIZE, node))
 			goto err;
 	}
 
 	/* Create rx Rings */
 	for (i = 0; i < priv->rx_ring_num; i++) {
+		node = cpu_to_node(i % num_online_cpus());
 		if (mlx4_en_create_cq(priv, &priv->rx_cq[i],
-				      prof->rx_ring_size, i, RX))
+				      prof->rx_ring_size, i, RX, node))
 			goto err;
 
 		if (mlx4_en_create_rx_ring(priv, &priv->rx_ring[i],
-					   prof->rx_ring_size, priv->stride))
+					   prof->rx_ring_size, priv->stride,
+					   node))
 			goto err;
 	}
 
@@ -1914,6 +1940,20 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
 
 err:
 	en_err(priv, "Failed to allocate NIC resources\n");
+	for (i = 0; i < priv->rx_ring_num; i++) {
+		if (priv->rx_ring[i])
+			mlx4_en_destroy_rx_ring(priv, &priv->rx_ring[i],
+						prof->rx_ring_size,
+						priv->stride);
+		if (priv->rx_cq[i])
+			mlx4_en_destroy_cq(priv, &priv->rx_cq[i]);
+	}
+	for (i = 0; i < priv->tx_ring_num; i++) {
+		if (priv->tx_ring[i])
+			mlx4_en_destroy_tx_ring(priv, &priv->tx_ring[i]);
+		if (priv->tx_cq[i])
+			mlx4_en_destroy_cq(priv, &priv->tx_cq[i]);
+	}
 	return -ENOMEM;
 }
 
@@ -2207,13 +2247,13 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	priv->num_tx_rings_p_up = mdev->profile.num_tx_rings_p_up;
 	priv->tx_ring_num = prof->tx_ring_num;
 
-	priv->tx_ring = kzalloc(sizeof(struct mlx4_en_tx_ring) * MAX_TX_RINGS,
+	priv->tx_ring = kzalloc(sizeof(struct mlx4_en_tx_ring *) * MAX_TX_RINGS,
 				GFP_KERNEL);
 	if (!priv->tx_ring) {
 		err = -ENOMEM;
 		goto out;
 	}
-	priv->tx_cq = kzalloc(sizeof(struct mlx4_en_cq) * MAX_TX_RINGS,
+	priv->tx_cq = kzalloc(sizeof(struct mlx4_en_cq *) * MAX_TX_RINGS,
 			      GFP_KERNEL);
 	if (!priv->tx_cq) {
 		err = -ENOMEM;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c
index 331791467a2..dae1a1f4ae5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c
@@ -56,7 +56,6 @@ int mlx4_SET_VLAN_FLTR(struct mlx4_dev *dev, struct mlx4_en_priv *priv)
 		return PTR_ERR(mailbox);
 
 	filter = mailbox->buf;
-	memset(filter, 0, sizeof(*filter));
 	for (i = VLAN_FLTR_SIZE - 1; i >= 0; i--) {
 		entry = 0;
 		for (j = 0; j < 32; j++)
@@ -81,7 +80,6 @@ int mlx4_en_QUERY_PORT(struct mlx4_en_dev *mdev, u8 port)
 	mailbox = mlx4_alloc_cmd_mailbox(mdev->dev);
 	if (IS_ERR(mailbox))
 		return PTR_ERR(mailbox);
-	memset(mailbox->buf, 0, sizeof(*qport_context));
 	err = mlx4_cmd_box(mdev->dev, 0, mailbox->dma, port, 0,
 			   MLX4_CMD_QUERY_PORT, MLX4_CMD_TIME_CLASS_B,
 			   MLX4_CMD_WRAPPED);
@@ -127,7 +125,6 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 	mailbox = mlx4_alloc_cmd_mailbox(mdev->dev);
 	if (IS_ERR(mailbox))
 		return PTR_ERR(mailbox);
-	memset(mailbox->buf, 0, sizeof(*mlx4_en_stats));
 	err = mlx4_cmd_box(mdev->dev, 0, mailbox->dma, in_mod, 0,
 			   MLX4_CMD_DUMP_ETH_STATS, MLX4_CMD_TIME_CLASS_B,
 			   MLX4_CMD_WRAPPED);
@@ -143,18 +140,18 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 	priv->port_stats.rx_chksum_good = 0;
 	priv->port_stats.rx_chksum_none = 0;
 	for (i = 0; i < priv->rx_ring_num; i++) {
-		stats->rx_packets += priv->rx_ring[i].packets;
-		stats->rx_bytes += priv->rx_ring[i].bytes;
-		priv->port_stats.rx_chksum_good += priv->rx_ring[i].csum_ok;
-		priv->port_stats.rx_chksum_none += priv->rx_ring[i].csum_none;
+		stats->rx_packets += priv->rx_ring[i]->packets;
+		stats->rx_bytes += priv->rx_ring[i]->bytes;
+		priv->port_stats.rx_chksum_good += priv->rx_ring[i]->csum_ok;
+		priv->port_stats.rx_chksum_none += priv->rx_ring[i]->csum_none;
 	}
 	stats->tx_packets = 0;
 	stats->tx_bytes = 0;
 	priv->port_stats.tx_chksum_offload = 0;
 	for (i = 0; i < priv->tx_ring_num; i++) {
-		stats->tx_packets += priv->tx_ring[i].packets;
-		stats->tx_bytes += priv->tx_ring[i].bytes;
-		priv->port_stats.tx_chksum_offload += priv->tx_ring[i].tx_csum;
+		stats->tx_packets += priv->tx_ring[i]->packets;
+		stats->tx_bytes += priv->tx_ring[i]->bytes;
+		priv->port_stats.tx_chksum_offload += priv->tx_ring[i]->tx_csum;
 	}
 
 	stats->rx_errors = be64_to_cpu(mlx4_en_stats->PCS) +
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index afe2efa69c8..07a1d0fbae4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -264,7 +264,7 @@ stat