Merge branch 'ibmvnic-next'

Thomas Falcon says:

====================
ibmvnic: Enable SG and TSO feature support

This patch set is fairly straightforward. The first patch enables
scatter-gather support in the ibmvnic driver. The following patch
then enables the TCP Segmentation offload feature. The final patch
allows users to enable or disable net device features using ethtool.

Enabling SG and TSO grants a large increase in throughput with TX
speed increasing from 1Gb/s to 9Gb/s in our initial test runs.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/ibm/ibmvnic.c

@@ -553,6 +553,10 @@ static int reset_tx_pools(struct ibmvnic_adapter *adapter)
 		if (rc)
 			return rc;
 
+		rc = reset_long_term_buff(adapter, &tx_pool->tso_ltb);
+		if (rc)
+			return rc;
+
 		memset(tx_pool->tx_buff, 0,
 		       adapter->req_tx_entries_per_subcrq *
 		       sizeof(struct ibmvnic_tx_buff));
@@ -562,6 +566,7 @@ static int reset_tx_pools(struct ibmvnic_adapter *adapter)
 
 		tx_pool->consumer_index = 0;
 		tx_pool->producer_index = 0;
+		tx_pool->tso_index = 0;
 	}
 
 	return 0;
@@ -581,6 +586,7 @@ static void release_tx_pools(struct ibmvnic_adapter *adapter)
 		tx_pool = &adapter->tx_pool[i];
 		kfree(tx_pool->tx_buff);
 		free_long_term_buff(adapter, &tx_pool->long_term_buff);
+		free_long_term_buff(adapter, &tx_pool->tso_ltb);
 		kfree(tx_pool->free_map);
 	}
 
@@ -625,6 +631,16 @@ static int init_tx_pools(struct net_device *netdev)
 			return -1;
 		}
 
+		/* alloc TSO ltb */
+		if (alloc_long_term_buff(adapter, &tx_pool->tso_ltb,
+					 IBMVNIC_TSO_BUFS *
+					 IBMVNIC_TSO_BUF_SZ)) {
+			release_tx_pools(adapter);
+			return -1;
+		}
+
+		tx_pool->tso_index = 0;
+
 		tx_pool->free_map = kcalloc(adapter->req_tx_entries_per_subcrq,
 					    sizeof(int), GFP_KERNEL);
 		if (!tx_pool->free_map) {
@@ -1201,11 +1217,41 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 		be32_to_cpu(adapter->login_rsp_buf->off_txsubm_subcrqs));
 
 	index = tx_pool->free_map[tx_pool->consumer_index];
+
+	if (skb_is_gso(skb)) {
+		offset = tx_pool->tso_index * IBMVNIC_TSO_BUF_SZ;
+		dst = tx_pool->tso_ltb.buff + offset;
+		memset(dst, 0, IBMVNIC_TSO_BUF_SZ);
+		data_dma_addr = tx_pool->tso_ltb.addr + offset;
+		tx_pool->tso_index++;
+		if (tx_pool->tso_index == IBMVNIC_TSO_BUFS)
+			tx_pool->tso_index = 0;
+	} else {
 		offset = index * adapter->req_mtu;
 		dst = tx_pool->long_term_buff.buff + offset;
 		memset(dst, 0, adapter->req_mtu);
-	skb_copy_from_linear_data(skb, dst, skb->len);
 		data_dma_addr = tx_pool->long_term_buff.addr + offset;
+	}
+
+	if (skb_shinfo(skb)->nr_frags) {
+		int cur, i;
+
+		/* Copy the head */
+		skb_copy_from_linear_data(skb, dst, skb_headlen(skb));
+		cur = skb_headlen(skb);
+
+		/* Copy the frags */
+		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+			const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+			memcpy(dst + cur,
+			       page_address(skb_frag_page(frag)) +
+			       frag->page_offset, skb_frag_size(frag));
+			cur += skb_frag_size(frag);
+		}
+	} else {
+		skb_copy_from_linear_data(skb, dst, skb->len);
+	}
 
 	tx_pool->consumer_index =
 	    (tx_pool->consumer_index + 1) %
@@ -1226,6 +1272,9 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	tx_crq.v1.n_sge = 1;
 	tx_crq.v1.flags1 = IBMVNIC_TX_COMP_NEEDED;
 	tx_crq.v1.correlator = cpu_to_be32(index);
+	if (skb_is_gso(skb))
+		tx_crq.v1.dma_reg = cpu_to_be16(tx_pool->tso_ltb.map_id);
+	else
 		tx_crq.v1.dma_reg = cpu_to_be16(tx_pool->long_term_buff.map_id);
 	tx_crq.v1.sge_len = cpu_to_be32(skb->len);
 	tx_crq.v1.ioba = cpu_to_be64(data_dma_addr);
@@ -1251,6 +1300,11 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 		tx_crq.v1.flags1 |= IBMVNIC_TX_CHKSUM_OFFLOAD;
 		hdrs += 2;
 	}
+	if (skb_is_gso(skb)) {
+		tx_crq.v1.flags1 |= IBMVNIC_TX_LSO;
+		tx_crq.v1.mss = cpu_to_be16(skb_shinfo(skb)->gso_size);
+		hdrs += 2;
+	}
 	/* determine if l2/3/4 headers are sent to firmware */
 	if ((*hdrs >> 7) & 1 &&
 	    (skb->protocol == htons(ETH_P_IP) ||
@@ -2941,14 +2995,14 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter)
 	adapter->ip_offload_ctrl.udp_ipv4_chksum = buf->udp_ipv4_chksum;
 	adapter->ip_offload_ctrl.tcp_ipv6_chksum = buf->tcp_ipv6_chksum;
 	adapter->ip_offload_ctrl.udp_ipv6_chksum = buf->udp_ipv6_chksum;
+	adapter->ip_offload_ctrl.large_tx_ipv4 = buf->large_tx_ipv4;
+	adapter->ip_offload_ctrl.large_tx_ipv6 = buf->large_tx_ipv6;
 
-	/* large_tx/rx disabled for now, additional features needed */
-	adapter->ip_offload_ctrl.large_tx_ipv4 = 0;
-	adapter->ip_offload_ctrl.large_tx_ipv6 = 0;
+	/* large_rx disabled for now, additional features needed */
 	adapter->ip_offload_ctrl.large_rx_ipv4 = 0;
 	adapter->ip_offload_ctrl.large_rx_ipv6 = 0;
 
-	adapter->netdev->features = NETIF_F_GSO;
+	adapter->netdev->features = NETIF_F_SG | NETIF_F_GSO;
 
 	if (buf->tcp_ipv4_chksum || buf->udp_ipv4_chksum)
 		adapter->netdev->features |= NETIF_F_IP_CSUM;
@@ -2960,6 +3014,13 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter)
 	    (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)))
 		adapter->netdev->features |= NETIF_F_RXCSUM;
 
+	if (buf->large_tx_ipv4)
+		adapter->netdev->features |= NETIF_F_TSO;
+	if (buf->large_tx_ipv6)
+		adapter->netdev->features |= NETIF_F_TSO6;
+
+	adapter->netdev->hw_features |= adapter->netdev->features;
+
 	memset(&crq, 0, sizeof(crq));
 	crq.control_ip_offload.first = IBMVNIC_CRQ_CMD;
 	crq.control_ip_offload.cmd = CONTROL_IP_OFFLOAD;

drivers/net/ethernet/ibm/ibmvnic.h

@@ -39,6 +39,9 @@
 #define IBMVNIC_BUFFS_PER_POOL	100
 #define IBMVNIC_MAX_TX_QUEUES	5
 
+#define IBMVNIC_TSO_BUF_SZ	65536
+#define IBMVNIC_TSO_BUFS	64
+
 struct ibmvnic_login_buffer {
 	__be32 len;
 	__be32 version;
@@ -896,6 +899,8 @@ struct ibmvnic_tx_pool {
 	wait_queue_head_t ibmvnic_tx_comp_q;
 	struct task_struct *work_thread;
 	struct ibmvnic_long_term_buff long_term_buff;
+	struct ibmvnic_long_term_buff tso_ltb;
+	int tso_index;
 };
 
 struct ibmvnic_rx_buff {