ibmvnic: Enable TSO support

This patch enables TSO support. It includes additional
buffers reserved exclusively for large packets. Throughput
is greatly increased with TSO enabled, from about 1 Gb/s to
9 Gb/s on our test systems.

Signed-off-by: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index b508877397e1427991ddf6833e72b8827a83d177..aedb81c230a6332ded5f6d637ae7b137580a99a5 100644 (file)
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/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) {
@@ -1201,10 +1217,21 @@ 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];
-       offset = index * adapter->req_mtu;
-       dst = tx_pool->long_term_buff.buff + offset;
-       memset(dst, 0, adapter->req_mtu);
-       data_dma_addr = tx_pool->long_term_buff.addr + offset;
+
+       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);
+               data_dma_addr = tx_pool->long_term_buff.addr + offset;
+       }
 
        if (skb_shinfo(skb)->nr_frags) {
                int cur, i;
@@ -1245,7 +1272,10 @@ 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);
-       tx_crq.v1.dma_reg = cpu_to_be16(tx_pool->long_term_buff.map_id);
+       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);
 
@@ -1270,6 +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) ||
@@ -2960,10 +2995,10 @@ 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;
 
@@ -2979,6 +3014,11 @@ 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;
+
        memset(&crq, 0, sizeof(crq));
        crq.control_ip_offload.first = IBMVNIC_CRQ_CMD;
        crq.control_ip_offload.cmd = CONTROL_IP_OFFLOAD;

diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index d02257ccc377820f1d05cc455224ade1985f103d..7aa347a21e782558b1c4240b69acf9e89f916723 100644 (file)
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/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 {