--- zzzz-none-000/linux-3.10.107/drivers/net/ethernet/mellanox/mlx4/en_netdev.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/drivers/net/ethernet/mellanox/mlx4/en_netdev.c 2021-02-04 17:41:59.000000000 +0000 @@ -38,6 +38,8 @@ #include #include #include +#include +#include #include #include @@ -67,12 +69,41 @@ return 0; } +#ifdef CONFIG_NET_RX_BUSY_POLL +/* must be called with local_bh_disable()d */ +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]; + int done; + + if (!priv->port_up) + return LL_FLUSH_FAILED; + + if (!mlx4_en_cq_lock_poll(cq)) + return LL_FLUSH_BUSY; + + done = mlx4_en_process_rx_cq(dev, cq, 4); + if (likely(done)) + rx_ring->cleaned += done; + else + rx_ring->misses++; + + mlx4_en_cq_unlock_poll(cq); + + return done; +} +#endif /* CONFIG_NET_RX_BUSY_POLL */ + #ifdef CONFIG_RFS_ACCEL struct mlx4_en_filter { struct list_head next; struct work_struct work; + u8 ip_proto; __be32 src_ip; __be32 dst_ip; __be16 src_port; @@ -91,14 +122,26 @@ 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 MLX4_NET_TRANS_RULE_NUM; + } +}; + 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, @@ -134,9 +177,14 @@ int rc; __be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16); + if (spec_tcp_udp.id >= MLX4_NET_TRANS_RULE_NUM) { + 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); @@ -154,6 +202,7 @@ if (rc) en_err(priv, "Error attaching flow. err = %d\n", rc); +ignore: mlx4_en_filter_rfs_expire(priv); filter->activated = 1; @@ -177,8 +226,8 @@ 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; @@ -192,6 +241,7 @@ 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; @@ -223,7 +273,7 @@ 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; @@ -234,6 +284,7 @@ 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; @@ -252,6 +303,7 @@ struct mlx4_en_filter *filter; const struct iphdr *ip; const __be16 *ports; + u8 ip_proto; __be32 src_ip; __be32 dst_ip; __be16 src_port; @@ -266,18 +318,19 @@ 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; @@ -285,7 +338,7 @@ 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; @@ -303,8 +356,7 @@ 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); @@ -376,7 +428,7 @@ en_err(priv, "Failed configuring VLAN filter\n"); } if (mlx4_register_vlan(mdev->dev, priv->port, vid, &idx)) - en_err(priv, "failed adding vlan %d\n", vid); + en_dbg(HW, priv, "failed adding vlan %d\n", vid); mutex_unlock(&mdev->state_lock); return 0; @@ -388,7 +440,6 @@ struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; int err; - int idx; en_dbg(HW, priv, "Killing VID:%d\n", vid); @@ -396,10 +447,7 @@ /* Remove VID from port VLAN filter */ mutex_lock(&mdev->state_lock); - if (!mlx4_find_cached_vlan(mdev->dev, priv->port, vid, &idx)) - mlx4_unregister_vlan(mdev->dev, priv->port, idx); - else - en_err(priv, "could not find vid %d in cache\n", vid); + mlx4_unregister_vlan(mdev->dev, priv->port, vid); if (mdev->device_up && priv->port_up) { err = mlx4_SET_VLAN_FLTR(mdev->dev, priv); @@ -421,6 +469,27 @@ memset(&dst_mac[ETH_ALEN], 0, 2); } + +static int mlx4_en_tunnel_steer_add(struct mlx4_en_priv *priv, unsigned char *addr, + int qpn, u64 *reg_id) +{ + int err; + + if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN || + priv->mdev->dev->caps.dmfs_high_steer_mode == MLX4_STEERING_DMFS_A0_STATIC) + return 0; /* do nothing */ + + err = mlx4_tunnel_steer_add(priv->mdev->dev, addr, priv->port, qpn, + MLX4_DOMAIN_NIC, reg_id); + if (err) { + en_err(priv, "failed to add vxlan steering rule, err %d\n", err); + return err; + } + en_dbg(DRV, priv, "added vxlan steering rule, mac %pM reg_id %llx\n", addr, *reg_id); + return 0; +} + + static int mlx4_en_uc_steer_add(struct mlx4_en_priv *priv, unsigned char *mac, int *qpn, u64 *reg_id) { @@ -504,12 +573,10 @@ { struct mlx4_en_dev *mdev = priv->mdev; struct mlx4_dev *dev = mdev->dev; - struct mlx4_mac_entry *entry; int index = 0; int err = 0; - u64 reg_id; int *qpn = &priv->base_qpn; - u64 mac = mlx4_en_mac_to_u64(priv->dev->dev_addr); + u64 mac = mlx4_mac_to_u64(priv->dev->dev_addr); en_dbg(DRV, priv, "Registering MAC: %pM for adding\n", priv->dev->dev_addr); @@ -527,39 +594,15 @@ return 0; } - err = mlx4_qp_reserve_range(dev, 1, 1, qpn); + err = mlx4_qp_reserve_range(dev, 1, 1, qpn, MLX4_RESERVE_A0_QP); en_dbg(DRV, priv, "Reserved qp %d\n", *qpn); if (err) { en_err(priv, "Failed to reserve qp for mac registration\n"); - goto qp_err; - } - - err = mlx4_en_uc_steer_add(priv, priv->dev->dev_addr, qpn, ®_id); - if (err) - goto steer_err; - - entry = kmalloc(sizeof(*entry), GFP_KERNEL); - if (!entry) { - err = -ENOMEM; - goto alloc_err; + mlx4_unregister_mac(dev, priv->port, mac); + return err; } - memcpy(entry->mac, priv->dev->dev_addr, sizeof(entry->mac)); - entry->reg_id = reg_id; - - hlist_add_head_rcu(&entry->hlist, - &priv->mac_hash[entry->mac[MLX4_EN_MAC_HASH_IDX]]); return 0; - -alloc_err: - mlx4_en_uc_steer_release(priv, priv->dev->dev_addr, *qpn, reg_id); - -steer_err: - mlx4_qp_release_range(dev, *qpn, 1); - -qp_err: - mlx4_unregister_mac(dev, priv->port, mac); - return err; } static void mlx4_en_put_qp(struct mlx4_en_priv *priv) @@ -567,34 +610,13 @@ struct mlx4_en_dev *mdev = priv->mdev; struct mlx4_dev *dev = mdev->dev; int qpn = priv->base_qpn; - u64 mac; if (dev->caps.steering_mode == MLX4_STEERING_MODE_A0) { - mac = mlx4_en_mac_to_u64(priv->dev->dev_addr); + u64 mac = mlx4_mac_to_u64(priv->dev->dev_addr); en_dbg(DRV, priv, "Registering MAC: %pM for deleting\n", priv->dev->dev_addr); mlx4_unregister_mac(dev, priv->port, mac); } else { - struct mlx4_mac_entry *entry; - struct hlist_node *tmp; - struct hlist_head *bucket; - unsigned int i; - - for (i = 0; i < MLX4_EN_MAC_HASH_SIZE; ++i) { - bucket = &priv->mac_hash[i]; - hlist_for_each_entry_safe(entry, tmp, bucket, hlist) { - mac = mlx4_en_mac_to_u64(entry->mac); - en_dbg(DRV, priv, "Registering MAC: %pM for deleting\n", - entry->mac); - mlx4_en_uc_steer_release(priv, entry->mac, - qpn, entry->reg_id); - - mlx4_unregister_mac(dev, priv->port, mac); - hlist_del_rcu(&entry->hlist); - kfree_rcu(entry, rcu); - } - } - en_dbg(DRV, priv, "Releasing qp: port %d, qpn %d\n", priv->port, qpn); mlx4_qp_release_range(dev, qpn, 1); @@ -608,14 +630,14 @@ struct mlx4_en_dev *mdev = priv->mdev; struct mlx4_dev *dev = mdev->dev; int err = 0; - u64 new_mac_u64 = mlx4_en_mac_to_u64(new_mac); + u64 new_mac_u64 = mlx4_mac_to_u64(new_mac); if (dev->caps.steering_mode != MLX4_STEERING_MODE_A0) { struct hlist_head *bucket; unsigned int mac_hash; struct mlx4_mac_entry *entry; struct hlist_node *tmp; - u64 prev_mac_u64 = mlx4_en_mac_to_u64(prev_mac); + u64 prev_mac_u64 = mlx4_mac_to_u64(prev_mac); bucket = &priv->mac_hash[prev_mac[MLX4_EN_MAC_HASH_IDX]]; hlist_for_each_entry_safe(entry, tmp, bucket, hlist) { @@ -635,6 +657,14 @@ err = mlx4_en_uc_steer_add(priv, new_mac, &qpn, &entry->reg_id); + if (err) + return err; + if (priv->tunnel_reg_id) { + mlx4_flow_detach(priv->mdev->dev, priv->tunnel_reg_id); + priv->tunnel_reg_id = 0; + } + err = mlx4_en_tunnel_steer_add(priv, new_mac, qpn, + &priv->tunnel_reg_id); return err; } } @@ -644,33 +674,23 @@ return __mlx4_replace_mac(dev, priv->port, qpn, new_mac_u64); } -u64 mlx4_en_mac_to_u64(u8 *addr) -{ - u64 mac = 0; - int i; - - for (i = 0; i < ETH_ALEN; i++) { - mac <<= 8; - mac |= addr[i]; - } - return mac; -} - -static int mlx4_en_do_set_mac(struct mlx4_en_priv *priv) +static int mlx4_en_do_set_mac(struct mlx4_en_priv *priv, + unsigned char new_mac[ETH_ALEN + 2]) { int err = 0; if (priv->port_up) { /* Remove old MAC and insert the new one */ err = mlx4_en_replace_mac(priv, priv->base_qpn, - priv->dev->dev_addr, priv->prev_mac); + new_mac, priv->current_mac); if (err) en_err(priv, "Failed changing HW MAC address\n"); - memcpy(priv->prev_mac, priv->dev->dev_addr, - sizeof(priv->prev_mac)); } else en_dbg(HW, priv, "Port is down while registering mac, exiting...\n"); + if (!err) + memcpy(priv->current_mac, new_mac, sizeof(priv->current_mac)); + return err; } @@ -679,15 +699,17 @@ struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; struct sockaddr *saddr = addr; + unsigned char new_mac[ETH_ALEN + 2]; int err; if (!is_valid_ether_addr(saddr->sa_data)) return -EADDRNOTAVAIL; - memcpy(dev->dev_addr, saddr->sa_data, ETH_ALEN); - mutex_lock(&mdev->state_lock); - err = mlx4_en_do_set_mac(priv); + memcpy(new_mac, saddr->sa_data, ETH_ALEN); + err = mlx4_en_do_set_mac(priv, new_mac); + if (!err) + memcpy(dev->dev_addr, saddr->sa_data, ETH_ALEN); mutex_unlock(&mdev->state_lock); return err; @@ -735,7 +757,7 @@ list_for_each_entry(dst_tmp, dst, list) { found = false; list_for_each_entry(src_tmp, src, list) { - if (!memcmp(dst_tmp->addr, src_tmp->addr, ETH_ALEN)) { + if (ether_addr_equal(dst_tmp->addr, src_tmp->addr)) { found = true; break; } @@ -750,7 +772,7 @@ list_for_each_entry(src_tmp, src, list) { found = false; list_for_each_entry(dst_tmp, dst, list) { - if (!memcmp(dst_tmp->addr, src_tmp->addr, ETH_ALEN)) { + if (ether_addr_equal(dst_tmp->addr, src_tmp->addr)) { dst_tmp->action = MCLIST_NONE; found = true; break; @@ -836,11 +858,6 @@ 0, MLX4_MCAST_DISABLE); if (err) en_err(priv, "Failed disabling multicast filter\n"); - - /* Disable port VLAN filter */ - err = mlx4_SET_VLAN_FLTR(mdev->dev, priv); - if (err) - en_err(priv, "Failed disabling VLAN filter\n"); } } @@ -889,11 +906,6 @@ en_err(priv, "Failed disabling promiscuous mode\n"); break; } - - /* Enable port VLAN filter */ - err = mlx4_SET_VLAN_FLTR(mdev->dev, priv); - if (err) - en_err(priv, "Failed enabling VLAN filter\n"); } static void mlx4_en_do_multicast(struct mlx4_en_priv *priv, @@ -974,7 +986,7 @@ mlx4_en_cache_mclist(dev); netif_addr_unlock_bh(dev); list_for_each_entry(mclist, &priv->mc_list, list) { - mcast_addr = mlx4_en_mac_to_u64(mclist->addr); + mcast_addr = mlx4_mac_to_u64(mclist->addr); mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, mcast_addr, 0, MLX4_MCAST_CONFIG); } @@ -997,6 +1009,12 @@ if (err) en_err(priv, "Fail to detach multicast address\n"); + if (mclist->tunnel_reg_id) { + err = mlx4_flow_detach(priv->mdev->dev, mclist->tunnel_reg_id); + if (err) + en_err(priv, "Failed to detach multicast address\n"); + } + /* remove from list */ list_del(&mclist->list); kfree(mclist); @@ -1014,6 +1032,10 @@ if (err) en_err(priv, "Fail to attach multicast address\n"); + err = mlx4_en_tunnel_steer_add(priv, &mc_list[10], priv->base_qpn, + &mclist->tunnel_reg_id); + if (err) + en_err(priv, "Failed to attach multicast address\n"); } } } @@ -1052,11 +1074,12 @@ } /* MAC address of the port is not in uc list */ - if (ether_addr_equal_64bits(entry->mac, dev->dev_addr)) + if (ether_addr_equal_64bits(entry->mac, + priv->current_mac)) found = true; if (!found) { - mac = mlx4_en_mac_to_u64(entry->mac); + mac = mlx4_mac_to_u64(entry->mac); mlx4_en_uc_steer_release(priv, entry->mac, priv->base_qpn, entry->reg_id); @@ -1099,7 +1122,7 @@ priv->flags |= MLX4_EN_FLAG_FORCE_PROMISC; break; } - mac = mlx4_en_mac_to_u64(ha->addr); + mac = mlx4_mac_to_u64(ha->addr); memcpy(entry->mac, ha->addr, ETH_ALEN); err = mlx4_register_mac(mdev->dev, priv->port, mac); if (err < 0) { @@ -1193,20 +1216,98 @@ int i; for (i = 0; i < priv->rx_ring_num; i++) { - cq = &priv->rx_cq[i]; + cq = priv->rx_cq[i]; napi_schedule(&cq->napi); } } #endif +static int mlx4_en_set_rss_steer_rules(struct mlx4_en_priv *priv) +{ + u64 reg_id; + int err = 0; + int *qpn = &priv->base_qpn; + struct mlx4_mac_entry *entry; + + err = mlx4_en_uc_steer_add(priv, priv->dev->dev_addr, qpn, ®_id); + if (err) + return err; + + err = mlx4_en_tunnel_steer_add(priv, priv->dev->dev_addr, *qpn, + &priv->tunnel_reg_id); + if (err) + goto tunnel_err; + + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) { + err = -ENOMEM; + goto alloc_err; + } + + memcpy(entry->mac, priv->dev->dev_addr, sizeof(entry->mac)); + memcpy(priv->current_mac, entry->mac, sizeof(priv->current_mac)); + entry->reg_id = reg_id; + hlist_add_head_rcu(&entry->hlist, + &priv->mac_hash[entry->mac[MLX4_EN_MAC_HASH_IDX]]); + + return 0; + +alloc_err: + if (priv->tunnel_reg_id) + mlx4_flow_detach(priv->mdev->dev, priv->tunnel_reg_id); + +tunnel_err: + mlx4_en_uc_steer_release(priv, priv->dev->dev_addr, *qpn, reg_id); + return err; +} + +static void mlx4_en_delete_rss_steer_rules(struct mlx4_en_priv *priv) +{ + u64 mac; + unsigned int i; + int qpn = priv->base_qpn; + struct hlist_head *bucket; + struct hlist_node *tmp; + struct mlx4_mac_entry *entry; + + for (i = 0; i < MLX4_EN_MAC_HASH_SIZE; ++i) { + bucket = &priv->mac_hash[i]; + hlist_for_each_entry_safe(entry, tmp, bucket, hlist) { + mac = mlx4_mac_to_u64(entry->mac); + en_dbg(DRV, priv, "Registering MAC:%pM for deleting\n", + entry->mac); + mlx4_en_uc_steer_release(priv, entry->mac, + qpn, entry->reg_id); + + mlx4_unregister_mac(priv->mdev->dev, priv->port, mac); + hlist_del_rcu(&entry->hlist); + kfree_rcu(entry, rcu); + } + } + + if (priv->tunnel_reg_id) { + mlx4_flow_detach(priv->mdev->dev, priv->tunnel_reg_id); + priv->tunnel_reg_id = 0; + } +} + static void mlx4_en_tx_timeout(struct net_device *dev) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; + int i; if (netif_msg_timer(priv)) en_warn(priv, "Tx timeout called on port:%d\n", priv->port); + for (i = 0; i < priv->tx_ring_num; i++) { + 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); + } + priv->port_stats.tx_timeout++; en_dbg(DRV, priv, "Scheduling watchdog\n"); queue_work(mdev->workqueue, &priv->watchdog_task); @@ -1244,7 +1345,7 @@ /* 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; @@ -1253,7 +1354,7 @@ } 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; } @@ -1287,8 +1388,8 @@ 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 - @@ -1317,7 +1418,7 @@ 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); @@ -1342,17 +1443,18 @@ mutex_lock(&mdev->state_lock); if (mdev->device_up) { - err = mlx4_en_DUMP_ETH_STATS(mdev, priv->port, 0); - if (err) - en_dbg(HW, priv, "Could not update stats\n"); + if (priv->port_up) { + err = mlx4_en_DUMP_ETH_STATS(mdev, priv->port, 0); + if (err) + en_dbg(HW, priv, "Could not update stats\n"); - if (priv->port_up) mlx4_en_auto_moderation(priv); + } queue_delayed_work(mdev->workqueue, &priv->stats_task, STATS_DELAY); } if (mdev->mac_removed[MLX4_MAX_PORTS + 1 - priv->port]) { - mlx4_en_do_set_mac(priv); + mlx4_en_do_set_mac(priv, priv->current_mac); mdev->mac_removed[MLX4_MAX_PORTS + 1 - priv->port] = 0; } mutex_unlock(&mdev->state_lock); @@ -1373,6 +1475,7 @@ if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) mlx4_en_ptp_overflow_check(mdev); + mlx4_en_recover_from_oom(priv); queue_delayed_work(mdev->workqueue, &priv->service_task, SERVICE_TASK_DELAY); } @@ -1402,6 +1505,23 @@ mutex_unlock(&mdev->state_lock); } +static int mlx4_en_init_affinity_hint(struct mlx4_en_priv *priv, int ring_idx) +{ + struct mlx4_en_rx_ring *ring = priv->rx_ring[ring_idx]; + int numa_node = priv->mdev->dev->numa_node; + + if (!zalloc_cpumask_var(&ring->affinity_mask, GFP_KERNEL)) + return -ENOMEM; + + cpumask_set_cpu(cpumask_local_spread(ring_idx, numa_node), + ring->affinity_mask); + return 0; +} + +static void mlx4_en_free_affinity_hint(struct mlx4_en_priv *priv, int ring_idx) +{ + free_cpumask_var(priv->rx_ring[ring_idx]->affinity_mask); +} int mlx4_en_start_port(struct net_device *dev) { @@ -1439,23 +1559,40 @@ 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); + + err = mlx4_en_init_affinity_hint(priv, i); + if (err) { + en_err(priv, "Failed preparing IRQ affinity hint\n"); + goto cq_err; + } err = mlx4_en_activate_cq(priv, cq, i); if (err) { en_err(priv, "Failed activating Rx CQ\n"); + mlx4_en_free_affinity_hint(priv, i); goto cq_err; } - for (j = 0; j < cq->size; j++) - cq->buf[j].owner_sr_opcode = MLX4_CQE_OWNER_MASK; + + for (j = 0; j < cq->size; j++) { + struct mlx4_cqe *cqe = NULL; + + cqe = mlx4_en_get_cqe(cq->buf, j, priv->cqe_size) + + priv->cqe_factor; + cqe->owner_sr_opcode = MLX4_CQE_OWNER_MASK; + } + err = mlx4_en_set_cq_moder(priv, cq); if (err) { - en_err(priv, "Failed setting cq moderation parameters"); + en_err(priv, "Failed setting cq moderation parameters\n"); mlx4_en_deactivate_cq(priv, cq); + mlx4_en_free_affinity_hint(priv, i); 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; } @@ -1468,6 +1605,9 @@ } mdev->mac_removed[priv->port] = 0; + priv->counter_index = + mlx4_get_default_counter_index(mdev->dev, priv->port); + err = mlx4_en_config_rss_steer(priv); if (err) { en_err(priv, "Failed configuring rss steering\n"); @@ -1481,7 +1621,7 @@ /* 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"); @@ -1489,7 +1629,7 @@ } err = mlx4_en_set_cq_moder(priv, cq); if (err) { - en_err(priv, "Failed setting cq moderation parameters"); + en_err(priv, "Failed setting cq moderation parameters\n"); mlx4_en_deactivate_cq(priv, cq); goto tx_err; } @@ -1497,7 +1637,7 @@ 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) { @@ -1535,6 +1675,15 @@ goto tx_err; } + if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) { + err = mlx4_SET_PORT_VXLAN(mdev->dev, priv->port, VXLAN_STEER_BY_OUTER_MAC, 1); + if (err) { + en_err(priv, "Failed setting port L2 tunnel configuration, err %d\n", + err); + goto tx_err; + } + } + /* Init port */ en_dbg(HW, priv, "Initializing port\n"); err = mlx4_INIT_PORT(mdev->dev, priv->port); @@ -1543,8 +1692,13 @@ goto tx_err; } + /* Set Unicast and VXLAN steering rules */ + if (mdev->dev->caps.steering_mode != MLX4_STEERING_MODE_A0 && + mlx4_en_set_rss_steer_rules(priv)) + mlx4_warn(mdev, "Failed setting steering rules\n"); + /* Attach rx QP to bradcast address */ - memset(&mc_list[10], 0xff, ETH_ALEN); + eth_broadcast_addr(&mc_list[10]); mc_list[5] = priv->port; /* needed for B0 steering support */ if (mlx4_multicast_attach(mdev->dev, &priv->rss_map.indir_qp, mc_list, priv->port, 0, MLX4_PROT_ETH, @@ -1557,8 +1711,10 @@ /* Schedule multicast task to populate multicast list */ queue_work(mdev->workqueue, &priv->rx_mode_task); - mlx4_set_stats_bitmap(mdev->dev, &priv->stats_bitmap); - +#ifdef CONFIG_MLX4_EN_VXLAN + if (priv->mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) + vxlan_get_rx_port(dev); +#endif priv->port_up = true; netif_tx_start_all_queues(dev); netif_device_attach(dev); @@ -1567,8 +1723,8 @@ 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: @@ -1576,10 +1732,12 @@ mac_err: mlx4_en_put_qp(priv); cq_err: - while (rx_index--) - mlx4_en_deactivate_cq(priv, &priv->rx_cq[rx_index]); + while (rx_index--) { + mlx4_en_deactivate_cq(priv, priv->rx_cq[rx_index]); + mlx4_en_free_affinity_hint(priv, 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 */ } @@ -1599,6 +1757,9 @@ return; } + /* close port*/ + mlx4_CLOSE_PORT(mdev->dev, priv->port); + /* Synchronize with tx routine */ netif_tx_lock_bh(dev); if (detach) @@ -1610,6 +1771,7 @@ /* Set port as not active */ priv->port_up = false; + priv->counter_index = MLX4_SINK_COUNTER_INDEX(mdev->dev); /* Promsicuous mode */ if (mdev->dev->caps.steering_mode == @@ -1638,7 +1800,7 @@ } /* Detach All multicasts */ - memset(&mc_list[10], 0xff, ETH_ALEN); + eth_broadcast_addr(&mc_list[10]); mc_list[5] = priv->port; /* needed for B0 steering support */ mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp, mc_list, MLX4_PROT_ETH, priv->broadcast_id); @@ -1647,6 +1809,8 @@ mc_list[5] = priv->port; mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp, mc_list, MLX4_PROT_ETH, mclist->reg_id); + if (mclist->tunnel_reg_id) + mlx4_flow_detach(mdev->dev, mclist->tunnel_reg_id); } mlx4_en_clear_list(dev); list_for_each_entry_safe(mclist, tmp, &priv->curr_list, list) { @@ -1672,32 +1836,42 @@ /* 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]); + + if (mdev->dev->caps.steering_mode != MLX4_STEERING_MODE_A0) + mlx4_en_delete_rss_steer_rules(priv); /* Free RSS qps */ mlx4_en_release_rss_steer(priv); /* Unregister Mac address for the port */ mlx4_en_put_qp(priv); - if (!(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAGS2_REASSIGN_MAC_EN)) + if (!(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_REASSIGN_MAC_EN)) mdev->mac_removed[priv->port] = 1; /* Free RX Rings */ for (i = 0; i < priv->rx_ring_num; i++) { - mlx4_en_deactivate_rx_ring(priv, &priv->rx_ring[i]); - while (test_bit(NAPI_STATE_SCHED, &priv->rx_cq[i].napi.state)) - msleep(1); - mlx4_en_deactivate_cq(priv, &priv->rx_cq[i]); - } + struct mlx4_en_cq *cq = priv->rx_cq[i]; - /* close port*/ - mlx4_CLOSE_PORT(mdev->dev, priv->port); + local_bh_disable(); + while (!mlx4_en_cq_lock_napi(cq)) { + pr_info("CQ %d locked\n", i); + mdelay(1); + } + local_bh_enable(); + + napi_synchronize(&cq->napi); + mlx4_en_deactivate_rx_ring(priv, priv->rx_ring[i]); + mlx4_en_deactivate_cq(priv, cq); + + mlx4_en_free_affinity_hint(priv, i); + } } static void mlx4_en_restart(struct work_struct *work) @@ -1731,17 +1905,25 @@ memset(&priv->pstats, 0, sizeof(priv->pstats)); memset(&priv->pkstats, 0, sizeof(priv->pkstats)); memset(&priv->port_stats, 0, sizeof(priv->port_stats)); + memset(&priv->rx_flowstats, 0, sizeof(priv->rx_flowstats)); + memset(&priv->tx_flowstats, 0, sizeof(priv->tx_flowstats)); + memset(&priv->rx_priority_flowstats, 0, + sizeof(priv->rx_priority_flowstats)); + memset(&priv->tx_priority_flowstats, 0, + sizeof(priv->tx_priority_flowstats)); + memset(&priv->pf_stats, 0, sizeof(priv->pf_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; + priv->rx_ring[i]->csum_complete = 0; } } @@ -1793,77 +1975,80 @@ int i; #ifdef CONFIG_RFS_ACCEL - free_irq_cpu_rmap(priv->dev->rx_cpu_rmap); priv->dev->rx_cpu_rmap = NULL; #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]); } - if (priv->base_tx_qpn) { - mlx4_qp_release_range(priv->mdev->dev, priv->base_tx_qpn, priv->tx_ring_num); - priv->base_tx_qpn = 0; - } } int mlx4_en_alloc_resources(struct mlx4_en_priv *priv) { struct mlx4_en_port_profile *prof = priv->prof; int i; - int err; - - err = mlx4_qp_reserve_range(priv->mdev->dev, priv->tx_ring_num, 256, &priv->base_tx_qpn); - if (err) { - en_err(priv, "failed reserving range for TX rings\n"); - return err; - } + int node; /* 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)) + if (mlx4_en_create_tx_ring(priv, &priv->tx_ring[i], + prof->tx_ring_size, TXBB_SIZE, + node, i)) 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; } #ifdef CONFIG_RFS_ACCEL - if (priv->mdev->dev->caps.comp_pool) { - priv->dev->rx_cpu_rmap = alloc_irq_cpu_rmap(priv->mdev->dev->caps.comp_pool); - if (!priv->dev->rx_cpu_rmap) - goto err; - } + priv->dev->rx_cpu_rmap = mlx4_get_cpu_rmap(priv->mdev->dev, priv->port); #endif return 0; 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; } @@ -1887,9 +2072,13 @@ /* flush any pending task for this netdev */ flush_workqueue(mdev->workqueue); + if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) + mlx4_en_remove_timestamp(mdev); + /* Detach the netdev so tasks would not attempt to access it */ mutex_lock(&mdev->state_lock); mdev->pndev[priv->port] = NULL; + mdev->upper[priv->port] = NULL; mutex_unlock(&mdev->state_lock); mlx4_en_free_resources(priv); @@ -1935,7 +2124,7 @@ return 0; } -static int mlx4_en_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr) +static int mlx4_en_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; @@ -1985,7 +2174,7 @@ return -ERANGE; } - if (mlx4_en_timestamp_config(dev, config.tx_type, config.rx_filter)) { + if (mlx4_en_reset_config(dev, config, dev->features)) { config.tx_type = HWTSTAMP_TX_OFF; config.rx_filter = HWTSTAMP_FILTER_NONE; } @@ -1994,38 +2183,104 @@ sizeof(config)) ? -EFAULT : 0; } +static int mlx4_en_hwtstamp_get(struct net_device *dev, struct ifreq *ifr) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + + return copy_to_user(ifr->ifr_data, &priv->hwtstamp_config, + sizeof(priv->hwtstamp_config)) ? -EFAULT : 0; +} + static int mlx4_en_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { switch (cmd) { case SIOCSHWTSTAMP: - return mlx4_en_hwtstamp_ioctl(dev, ifr); + return mlx4_en_hwtstamp_set(dev, ifr); + case SIOCGHWTSTAMP: + return mlx4_en_hwtstamp_get(dev, ifr); default: return -EOPNOTSUPP; } } +static netdev_features_t mlx4_en_fix_features(struct net_device *netdev, + netdev_features_t features) +{ + struct mlx4_en_priv *en_priv = netdev_priv(netdev); + struct mlx4_en_dev *mdev = en_priv->mdev; + + /* Since there is no support for separate RX C-TAG/S-TAG vlan accel + * enable/disable make sure S-TAG flag is always in same state as + * C-TAG. + */ + if (features & NETIF_F_HW_VLAN_CTAG_RX && + !(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_SKIP_OUTER_VLAN)) + features |= NETIF_F_HW_VLAN_STAG_RX; + else + features &= ~NETIF_F_HW_VLAN_STAG_RX; + + return features; +} + static int mlx4_en_set_features(struct net_device *netdev, netdev_features_t features) { struct mlx4_en_priv *priv = netdev_priv(netdev); + bool reset = false; + int ret = 0; - if (features & NETIF_F_LOOPBACK) - priv->ctrl_flags |= cpu_to_be32(MLX4_WQE_CTRL_FORCE_LOOPBACK); - else - priv->ctrl_flags &= - cpu_to_be32(~MLX4_WQE_CTRL_FORCE_LOOPBACK); + if (DEV_FEATURE_CHANGED(netdev, features, NETIF_F_RXFCS)) { + en_info(priv, "Turn %s RX-FCS\n", + (features & NETIF_F_RXFCS) ? "ON" : "OFF"); + reset = true; + } - mlx4_en_update_loopback_state(netdev, features); + if (DEV_FEATURE_CHANGED(netdev, features, NETIF_F_RXALL)) { + u8 ignore_fcs_value = (features & NETIF_F_RXALL) ? 1 : 0; - return 0; + en_info(priv, "Turn %s RX-ALL\n", + ignore_fcs_value ? "ON" : "OFF"); + ret = mlx4_SET_PORT_fcs_check(priv->mdev->dev, + priv->port, ignore_fcs_value); + if (ret) + return ret; + } + + if (DEV_FEATURE_CHANGED(netdev, features, NETIF_F_HW_VLAN_CTAG_RX)) { + en_info(priv, "Turn %s RX vlan strip offload\n", + (features & NETIF_F_HW_VLAN_CTAG_RX) ? "ON" : "OFF"); + reset = true; + } + if (DEV_FEATURE_CHANGED(netdev, features, NETIF_F_HW_VLAN_CTAG_TX)) + en_info(priv, "Turn %s TX vlan strip offload\n", + (features & NETIF_F_HW_VLAN_CTAG_TX) ? "ON" : "OFF"); + + if (DEV_FEATURE_CHANGED(netdev, features, NETIF_F_HW_VLAN_STAG_TX)) + en_info(priv, "Turn %s TX S-VLAN strip offload\n", + (features & NETIF_F_HW_VLAN_STAG_TX) ? "ON" : "OFF"); + + if (DEV_FEATURE_CHANGED(netdev, features, NETIF_F_LOOPBACK)) { + en_info(priv, "Turn %s loopback\n", + (features & NETIF_F_LOOPBACK) ? "ON" : "OFF"); + mlx4_en_update_loopback_state(netdev, features); + } + + if (reset) { + ret = mlx4_en_reset_config(netdev, priv->hwtstamp_config, + features); + if (ret) + return ret; + } + + return 0; } static int mlx4_en_set_vf_mac(struct net_device *dev, int queue, u8 *mac) { struct mlx4_en_priv *en_priv = netdev_priv(dev); struct mlx4_en_dev *mdev = en_priv->mdev; - u64 mac_u64 = mlx4_en_mac_to_u64(mac); + u64 mac_u64 = mlx4_mac_to_u64(mac); if (is_multicast_ether_addr(mac)) return -EINVAL; @@ -2041,6 +2296,16 @@ return mlx4_set_vf_vlan(mdev->dev, en_priv->port, vf, vlan, qos); } +static int mlx4_en_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate, + int max_tx_rate) +{ + struct mlx4_en_priv *en_priv = netdev_priv(dev); + struct mlx4_en_dev *mdev = en_priv->mdev; + + return mlx4_set_vf_rate(mdev->dev, en_priv->port, vf, min_tx_rate, + max_tx_rate); +} + static int mlx4_en_set_vf_spoofchk(struct net_device *dev, int vf, bool setting) { struct mlx4_en_priv *en_priv = netdev_priv(dev); @@ -2057,6 +2322,164 @@ return mlx4_get_vf_config(mdev->dev, en_priv->port, vf, ivf); } +static int mlx4_en_set_vf_link_state(struct net_device *dev, int vf, int link_state) +{ + struct mlx4_en_priv *en_priv = netdev_priv(dev); + struct mlx4_en_dev *mdev = en_priv->mdev; + + return mlx4_set_vf_link_state(mdev->dev, en_priv->port, vf, link_state); +} + +static int mlx4_en_get_vf_stats(struct net_device *dev, int vf, + struct ifla_vf_stats *vf_stats) +{ + struct mlx4_en_priv *en_priv = netdev_priv(dev); + struct mlx4_en_dev *mdev = en_priv->mdev; + + return mlx4_get_vf_stats(mdev->dev, en_priv->port, vf, vf_stats); +} + +#define PORT_ID_BYTE_LEN 8 +static int mlx4_en_get_phys_port_id(struct net_device *dev, + struct netdev_phys_item_id *ppid) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + struct mlx4_dev *mdev = priv->mdev->dev; + int i; + u64 phys_port_id = mdev->caps.phys_port_id[priv->port]; + + if (!phys_port_id) + return -EOPNOTSUPP; + + ppid->id_len = sizeof(phys_port_id); + for (i = PORT_ID_BYTE_LEN - 1; i >= 0; --i) { + ppid->id[i] = phys_port_id & 0xff; + phys_port_id >>= 8; + } + return 0; +} + +#ifdef CONFIG_MLX4_EN_VXLAN +static void mlx4_en_add_vxlan_offloads(struct work_struct *work) +{ + int ret; + struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv, + vxlan_add_task); + + ret = mlx4_config_vxlan_port(priv->mdev->dev, priv->vxlan_port); + if (ret) + goto out; + + ret = mlx4_SET_PORT_VXLAN(priv->mdev->dev, priv->port, + VXLAN_STEER_BY_OUTER_MAC, 1); +out: + if (ret) { + en_err(priv, "failed setting L2 tunnel configuration ret %d\n", ret); + return; + } + + /* set offloads */ + priv->dev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_RXCSUM | + NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL; +} + +static void mlx4_en_del_vxlan_offloads(struct work_struct *work) +{ + int ret; + struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv, + vxlan_del_task); + /* unset offloads */ + priv->dev->hw_enc_features &= ~(NETIF_F_IP_CSUM | NETIF_F_RXCSUM | + NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL); + + ret = mlx4_SET_PORT_VXLAN(priv->mdev->dev, priv->port, + VXLAN_STEER_BY_OUTER_MAC, 0); + if (ret) + en_err(priv, "failed setting L2 tunnel configuration ret %d\n", ret); + + priv->vxlan_port = 0; +} + +static void mlx4_en_add_vxlan_port(struct net_device *dev, + sa_family_t sa_family, __be16 port) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + __be16 current_port; + + if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) + return; + + if (sa_family == AF_INET6) + return; + + current_port = priv->vxlan_port; + if (current_port && current_port != port) { + en_warn(priv, "vxlan port %d configured, can't add port %d\n", + ntohs(current_port), ntohs(port)); + return; + } + + priv->vxlan_port = port; + queue_work(priv->mdev->workqueue, &priv->vxlan_add_task); +} + +static void mlx4_en_del_vxlan_port(struct net_device *dev, + sa_family_t sa_family, __be16 port) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + __be16 current_port; + + if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) + return; + + if (sa_family == AF_INET6) + return; + + current_port = priv->vxlan_port; + if (current_port != port) { + en_dbg(DRV, priv, "vxlan port %d isn't configured, ignoring\n", ntohs(port)); + return; + } + + queue_work(priv->mdev->workqueue, &priv->vxlan_del_task); +} + +static netdev_features_t mlx4_en_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) +{ + features = vlan_features_check(skb, features); + return vxlan_features_check(skb, features); +} +#endif + +static int mlx4_en_set_tx_maxrate(struct net_device *dev, int queue_index, u32 maxrate) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + struct mlx4_en_tx_ring *tx_ring = priv->tx_ring[queue_index]; + struct mlx4_update_qp_params params; + int err; + + if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_QP_RATE_LIMIT)) + return -EOPNOTSUPP; + + /* rate provided to us in Mbs, check if it fits into 12 bits, if not use Gbs */ + if (maxrate >> 12) { + params.rate_unit = MLX4_QP_RATE_LIMIT_GBS; + params.rate_val = maxrate / 1000; + } else if (maxrate) { + params.rate_unit = MLX4_QP_RATE_LIMIT_MBS; + params.rate_val = maxrate; + } else { /* zero serves to revoke the QP rate-limitation */ + params.rate_unit = 0; + params.rate_val = 0; + } + + err = mlx4_update_qp(priv->mdev->dev, tx_ring->qpn, MLX4_UPDATE_QP_RATE_LIMIT, + ¶ms); + return err; +} + static const struct net_device_ops mlx4_netdev_ops = { .ndo_open = mlx4_en_open, .ndo_stop = mlx4_en_close, @@ -2075,10 +2498,21 @@ .ndo_poll_controller = mlx4_en_netpoll, #endif .ndo_set_features = mlx4_en_set_features, + .ndo_fix_features = mlx4_en_fix_features, .ndo_setup_tc = mlx4_en_setup_tc, #ifdef CONFIG_RFS_ACCEL .ndo_rx_flow_steer = mlx4_en_filter_rfs, #endif +#ifdef CONFIG_NET_RX_BUSY_POLL + .ndo_busy_poll = mlx4_en_low_latency_recv, +#endif + .ndo_get_phys_port_id = mlx4_en_get_phys_port_id, +#ifdef CONFIG_MLX4_EN_VXLAN + .ndo_add_vxlan_port = mlx4_en_add_vxlan_port, + .ndo_del_vxlan_port = mlx4_en_del_vxlan_port, + .ndo_features_check = mlx4_en_features_check, +#endif + .ndo_set_tx_maxrate = mlx4_en_set_tx_maxrate, }; static const struct net_device_ops mlx4_netdev_ops_master = { @@ -2096,18 +2530,284 @@ .ndo_vlan_rx_kill_vid = mlx4_en_vlan_rx_kill_vid, .ndo_set_vf_mac = mlx4_en_set_vf_mac, .ndo_set_vf_vlan = mlx4_en_set_vf_vlan, + .ndo_set_vf_rate = mlx4_en_set_vf_rate, .ndo_set_vf_spoofchk = mlx4_en_set_vf_spoofchk, + .ndo_set_vf_link_state = mlx4_en_set_vf_link_state, + .ndo_get_vf_stats = mlx4_en_get_vf_stats, .ndo_get_vf_config = mlx4_en_get_vf_config, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = mlx4_en_netpoll, #endif .ndo_set_features = mlx4_en_set_features, + .ndo_fix_features = mlx4_en_fix_features, .ndo_setup_tc = mlx4_en_setup_tc, #ifdef CONFIG_RFS_ACCEL .ndo_rx_flow_steer = mlx4_en_filter_rfs, #endif + .ndo_get_phys_port_id = mlx4_en_get_phys_port_id, +#ifdef CONFIG_MLX4_EN_VXLAN + .ndo_add_vxlan_port = mlx4_en_add_vxlan_port, + .ndo_del_vxlan_port = mlx4_en_del_vxlan_port, + .ndo_features_check = mlx4_en_features_check, +#endif + .ndo_set_tx_maxrate = mlx4_en_set_tx_maxrate, }; +struct mlx4_en_bond { + struct work_struct work; + struct mlx4_en_priv *priv; + int is_bonded; + struct mlx4_port_map port_map; +}; + +static void mlx4_en_bond_work(struct work_struct *work) +{ + struct mlx4_en_bond *bond = container_of(work, + struct mlx4_en_bond, + work); + int err = 0; + struct mlx4_dev *dev = bond->priv->mdev->dev; + + if (bond->is_bonded) { + if (!mlx4_is_bonded(dev)) { + err = mlx4_bond(dev); + if (err) + en_err(bond->priv, "Fail to bond device\n"); + } + if (!err) { + err = mlx4_port_map_set(dev, &bond->port_map); + if (err) + en_err(bond->priv, "Fail to set port map [%d][%d]: %d\n", + bond->port_map.port1, + bond->port_map.port2, + err); + } + } else if (mlx4_is_bonded(dev)) { + err = mlx4_unbond(dev); + if (err) + en_err(bond->priv, "Fail to unbond device\n"); + } + dev_put(bond->priv->dev); + kfree(bond); +} + +static int mlx4_en_queue_bond_work(struct mlx4_en_priv *priv, int is_bonded, + u8 v2p_p1, u8 v2p_p2) +{ + struct mlx4_en_bond *bond = NULL; + + bond = kzalloc(sizeof(*bond), GFP_ATOMIC); + if (!bond) + return -ENOMEM; + + INIT_WORK(&bond->work, mlx4_en_bond_work); + bond->priv = priv; + bond->is_bonded = is_bonded; + bond->port_map.port1 = v2p_p1; + bond->port_map.port2 = v2p_p2; + dev_hold(priv->dev); + queue_work(priv->mdev->workqueue, &bond->work); + return 0; +} + +int mlx4_en_netdev_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct net_device *ndev = netdev_notifier_info_to_dev(ptr); + u8 port = 0; + struct mlx4_en_dev *mdev; + struct mlx4_dev *dev; + int i, num_eth_ports = 0; + bool do_bond = true; + struct mlx4_en_priv *priv; + u8 v2p_port1 = 0; + u8 v2p_port2 = 0; + + if (!net_eq(dev_net(ndev), &init_net)) + return NOTIFY_DONE; + + mdev = container_of(this, struct mlx4_en_dev, nb); + dev = mdev->dev; + + /* Go into this mode only when two network devices set on two ports + * of the same mlx4 device are slaves of the same bonding master + */ + mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) { + ++num_eth_ports; + if (!port && (mdev->pndev[i] == ndev)) + port = i; + mdev->upper[i] = mdev->pndev[i] ? + netdev_master_upper_dev_get(mdev->pndev[i]) : NULL; + /* condition not met: network device is a slave */ + if (!mdev->upper[i]) + do_bond = false; + if (num_eth_ports < 2) + continue; + /* condition not met: same master */ + if (mdev->upper[i] != mdev->upper[i-1]) + do_bond = false; + } + /* condition not met: 2 salves */ + do_bond = (num_eth_ports == 2) ? do_bond : false; + + /* handle only events that come with enough info */ + if ((do_bond && (event != NETDEV_BONDING_INFO)) || !port) + return NOTIFY_DONE; + + priv = netdev_priv(ndev); + if (do_bond) { + struct netdev_notifier_bonding_info *notifier_info = ptr; + struct netdev_bonding_info *bonding_info = + ¬ifier_info->bonding_info; + + /* required mode 1, 2 or 4 */ + if ((bonding_info->master.bond_mode != BOND_MODE_ACTIVEBACKUP) && + (bonding_info->master.bond_mode != BOND_MODE_XOR) && + (bonding_info->master.bond_mode != BOND_MODE_8023AD)) + do_bond = false; + + /* require exactly 2 slaves */ + if (bonding_info->master.num_slaves != 2) + do_bond = false; + + /* calc v2p */ + if (do_bond) { + if (bonding_info->master.bond_mode == + BOND_MODE_ACTIVEBACKUP) { + /* in active-backup mode virtual ports are + * mapped to the physical port of the active + * slave */ + if (bonding_info->slave.state == + BOND_STATE_BACKUP) { + if (port == 1) { + v2p_port1 = 2; + v2p_port2 = 2; + } else { + v2p_port1 = 1; + v2p_port2 = 1; + } + } else { /* BOND_STATE_ACTIVE */ + if (port == 1) { + v2p_port1 = 1; + v2p_port2 = 1; + } else { + v2p_port1 = 2; + v2p_port2 = 2; + } + } + } else { /* Active-Active */ + /* in active-active mode a virtual port is + * mapped to the native physical port if and only + * if the physical port is up */ + __s8 link = bonding_info->slave.link; + + if (port == 1) + v2p_port2 = 2; + else + v2p_port1 = 1; + if ((link == BOND_LINK_UP) || + (link == BOND_LINK_FAIL)) { + if (port == 1) + v2p_port1 = 1; + else + v2p_port2 = 2; + } else { /* BOND_LINK_DOWN || BOND_LINK_BACK */ + if (port == 1) + v2p_port1 = 2; + else + v2p_port2 = 1; + } + } + } + } + + mlx4_en_queue_bond_work(priv, do_bond, + v2p_port1, v2p_port2); + + return NOTIFY_DONE; +} + +void mlx4_en_update_pfc_stats_bitmap(struct mlx4_dev *dev, + struct mlx4_en_stats_bitmap *stats_bitmap, + u8 rx_ppp, u8 rx_pause, + u8 tx_ppp, u8 tx_pause) +{ + int last_i = NUM_MAIN_STATS + NUM_PORT_STATS + NUM_PF_STATS; + + if (!mlx4_is_slave(dev) && + (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_FLOWSTATS_EN)) { + mutex_lock(&stats_bitmap->mutex); + bitmap_clear(stats_bitmap->bitmap, last_i, NUM_FLOW_STATS); + + if (rx_ppp) + bitmap_set(stats_bitmap->bitmap, last_i, + NUM_FLOW_PRIORITY_STATS_RX); + last_i += NUM_FLOW_PRIORITY_STATS_RX; + + if (rx_pause && !(rx_ppp)) + bitmap_set(stats_bitmap->bitmap, last_i, + NUM_FLOW_STATS_RX); + last_i += NUM_FLOW_STATS_RX; + + if (tx_ppp) + bitmap_set(stats_bitmap->bitmap, last_i, + NUM_FLOW_PRIORITY_STATS_TX); + last_i += NUM_FLOW_PRIORITY_STATS_TX; + + if (tx_pause && !(tx_ppp)) + bitmap_set(stats_bitmap->bitmap, last_i, + NUM_FLOW_STATS_TX); + last_i += NUM_FLOW_STATS_TX; + + mutex_unlock(&stats_bitmap->mutex); + } +} + +void mlx4_en_set_stats_bitmap(struct mlx4_dev *dev, + struct mlx4_en_stats_bitmap *stats_bitmap, + u8 rx_ppp, u8 rx_pause, + u8 tx_ppp, u8 tx_pause) +{ + int last_i = 0; + + mutex_init(&stats_bitmap->mutex); + bitmap_zero(stats_bitmap->bitmap, NUM_ALL_STATS); + + if (mlx4_is_slave(dev)) { + bitmap_set(stats_bitmap->bitmap, last_i + + MLX4_FIND_NETDEV_STAT(rx_packets), 1); + bitmap_set(stats_bitmap->bitmap, last_i + + MLX4_FIND_NETDEV_STAT(tx_packets), 1); + bitmap_set(stats_bitmap->bitmap, last_i + + MLX4_FIND_NETDEV_STAT(rx_bytes), 1); + bitmap_set(stats_bitmap->bitmap, last_i + + MLX4_FIND_NETDEV_STAT(tx_bytes), 1); + bitmap_set(stats_bitmap->bitmap, last_i + + MLX4_FIND_NETDEV_STAT(rx_dropped), 1); + bitmap_set(stats_bitmap->bitmap, last_i + + MLX4_FIND_NETDEV_STAT(tx_dropped), 1); + } else { + bitmap_set(stats_bitmap->bitmap, last_i, NUM_MAIN_STATS); + } + last_i += NUM_MAIN_STATS; + + bitmap_set(stats_bitmap->bitmap, last_i, NUM_PORT_STATS); + last_i += NUM_PORT_STATS; + + if (mlx4_is_master(dev)) + bitmap_set(stats_bitmap->bitmap, last_i, + NUM_PF_STATS); + last_i += NUM_PF_STATS; + + mlx4_en_update_pfc_stats_bitmap(dev, stats_bitmap, + rx_ppp, rx_pause, + tx_ppp, tx_pause); + last_i += NUM_FLOW_STATS; + + if (!mlx4_is_slave(dev)) + bitmap_set(stats_bitmap->bitmap, last_i, NUM_PKT_STATS); +} + int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, struct mlx4_en_port_profile *prof) { @@ -2115,7 +2815,6 @@ struct mlx4_en_priv *priv; int i; int err; - u64 mac_u64; dev = alloc_etherdev_mqs(sizeof(struct mlx4_en_priv), MAX_TX_RINGS, MAX_RX_RINGS); @@ -2125,8 +2824,8 @@ netif_set_real_num_tx_queues(dev, prof->tx_ring_num); netif_set_real_num_rx_queues(dev, prof->rx_ring_num); - SET_NETDEV_DEV(dev, &mdev->dev->pdev->dev); - dev->dev_id = port - 1; + SET_NETDEV_DEV(dev, &mdev->dev->persist->pdev->dev); + dev->dev_port = port - 1; /* * Initialize driver private data @@ -2134,6 +2833,22 @@ priv = netdev_priv(dev); memset(priv, 0, sizeof(struct mlx4_en_priv)); + priv->counter_index = MLX4_SINK_COUNTER_INDEX(mdev->dev); + spin_lock_init(&priv->stats_lock); + INIT_WORK(&priv->rx_mode_task, mlx4_en_do_set_rx_mode); + INIT_WORK(&priv->watchdog_task, mlx4_en_restart); + INIT_WORK(&priv->linkstate_task, mlx4_en_linkstate); + INIT_DELAYED_WORK(&priv->stats_task, mlx4_en_do_get_stats); + INIT_DELAYED_WORK(&priv->service_task, mlx4_en_service_task); +#ifdef CONFIG_MLX4_EN_VXLAN + INIT_WORK(&priv->vxlan_add_task, mlx4_en_add_vxlan_offloads); + INIT_WORK(&priv->vxlan_del_task, mlx4_en_del_vxlan_offloads); +#endif +#ifdef CONFIG_RFS_ACCEL + INIT_LIST_HEAD(&priv->filters); + spin_lock_init(&priv->filters_lock); +#endif + priv->dev = dev; priv->mdev = mdev; priv->ddev = &mdev->pdev->dev; @@ -2141,18 +2856,21 @@ priv->port = port; priv->port_up = false; priv->flags = prof->flags; + priv->pflags = MLX4_EN_PRIV_FLAGS_BLUEFLAME; priv->ctrl_flags = cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE | MLX4_WQE_CTRL_SOLICITED); priv->num_tx_rings_p_up = mdev->profile.num_tx_rings_p_up; priv->tx_ring_num = prof->tx_ring_num; + priv->tx_work_limit = MLX4_EN_DEFAULT_TX_WORK; + netdev_rss_key_fill(priv->rss_key, sizeof(priv->rss_key)); - 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; @@ -2160,17 +2878,12 @@ } priv->rx_ring_num = prof->rx_ring_num; priv->cqe_factor = (mdev->dev->caps.cqe_size == 64) ? 1 : 0; + priv->cqe_size = mdev->dev->caps.cqe_size; priv->mac_index = -1; priv->msg_enable = MLX4_EN_MSG_LEVEL; - spin_lock_init(&priv->stats_lock); - INIT_WORK(&priv->rx_mode_task, mlx4_en_do_set_rx_mode); - INIT_WORK(&priv->watchdog_task, mlx4_en_restart); - INIT_WORK(&priv->linkstate_task, mlx4_en_linkstate); - INIT_DELAYED_WORK(&priv->stats_task, mlx4_en_do_get_stats); - INIT_DELAYED_WORK(&priv->service_task, mlx4_en_service_task); #ifdef CONFIG_MLX4_EN_DCB if (!mlx4_is_slave(priv->mdev->dev)) { - if (mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_SET_ETH_SCHED) { + if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ETS_CFG) { dev->dcbnl_ops = &mlx4_en_dcbnl_ops; } else { en_info(priv, "enabling only PFC DCB ops\n"); @@ -2185,24 +2898,28 @@ /* Query for default mac and max mtu */ priv->max_mtu = mdev->dev->caps.eth_mtu_cap[priv->port]; + if (mdev->dev->caps.rx_checksum_flags_port[priv->port] & + MLX4_RX_CSUM_MODE_VAL_NON_TCP_UDP) + priv->flags |= MLX4_EN_FLAG_RX_CSUM_NON_TCP_UDP; + /* Set default MAC */ dev->addr_len = ETH_ALEN; mlx4_en_u64_to_mac(dev->dev_addr, mdev->dev->caps.def_mac[priv->port]); if (!is_valid_ether_addr(dev->dev_addr)) { - if (mlx4_is_slave(priv->mdev->dev)) { - eth_hw_addr_random(dev); - en_warn(priv, "Assigned random MAC address %pM\n", dev->dev_addr); - mac_u64 = mlx4_en_mac_to_u64(dev->dev_addr); - mdev->dev->caps.def_mac[priv->port] = mac_u64; - } else { - en_err(priv, "Port: %d, invalid mac burned: %pM, quiting\n", - priv->port, dev->dev_addr); - err = -EINVAL; - goto out; - } + en_err(priv, "Port: %d, invalid mac burned: %pM, quiting\n", + priv->port, dev->dev_addr); + err = -EINVAL; + goto out; + } else if (mlx4_is_slave(priv->mdev->dev) && + (priv->mdev->dev->port_random_macs & 1 << priv->port)) { + /* Random MAC was assigned in mlx4_slave_cap + * in mlx4_core module + */ + dev->addr_assign_type |= NET_ADDR_RANDOM; + en_warn(priv, "Assigned random MAC address %pM\n", dev->dev_addr); } - memcpy(priv->prev_mac, dev->dev_addr, sizeof(priv->prev_mac)); + memcpy(priv->current_mac, dev->dev_addr, sizeof(priv->current_mac)); priv->stride = roundup_pow_of_two(sizeof(struct mlx4_en_rx_desc) + DS_SIZE * MLX4_EN_MAX_RX_FRAGS); @@ -2210,11 +2927,6 @@ if (err) goto out; -#ifdef CONFIG_RFS_ACCEL - INIT_LIST_HEAD(&priv->filters); - spin_lock_init(&priv->filters_lock); -#endif - /* Initialize time stamping config */ priv->hwtstamp_config.flags = 0; priv->hwtstamp_config.tx_type = HWTSTAMP_TX_OFF; @@ -2240,7 +2952,7 @@ netif_set_real_num_tx_queues(dev, priv->tx_ring_num); netif_set_real_num_rx_queues(dev, priv->rx_ring_num); - SET_ETHTOOL_OPS(dev, &mlx4_en_ethtool_ops); + dev->ethtool_ops = &mlx4_en_ethtool_ops; /* * Set driver features @@ -2255,24 +2967,65 @@ dev->features = dev->hw_features | NETIF_F_HIGHDMA | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER; - dev->hw_features |= NETIF_F_LOOPBACK; + dev->hw_features |= NETIF_F_LOOPBACK | + NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; + + if (!(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_SKIP_OUTER_VLAN)) { + dev->features |= NETIF_F_HW_VLAN_STAG_RX | + NETIF_F_HW_VLAN_STAG_FILTER; + dev->hw_features |= NETIF_F_HW_VLAN_STAG_RX; + } + + if (mlx4_is_slave(mdev->dev)) { + int phv; + + err = get_phv_bit(mdev->dev, port, &phv); + if (!err && phv) { + dev->hw_features |= NETIF_F_HW_VLAN_STAG_TX; + priv->pflags |= MLX4_EN_PRIV_FLAGS_PHV; + } + } else { + if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PHV_EN && + !(mdev->dev->caps.flags2 & + MLX4_DEV_CAP_FLAG2_SKIP_OUTER_VLAN)) + dev->hw_features |= NETIF_F_HW_VLAN_STAG_TX; + } + + if (mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_FCS_KEEP) + dev->hw_features |= NETIF_F_RXFCS; + + if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_IGNORE_FCS) + dev->hw_features |= NETIF_F_RXALL; if (mdev->dev->caps.steering_mode == - MLX4_STEERING_MODE_DEVICE_MANAGED) + MLX4_STEERING_MODE_DEVICE_MANAGED && + mdev->dev->caps.dmfs_high_steer_mode != MLX4_STEERING_DMFS_A0_STATIC) dev->hw_features |= NETIF_F_NTUPLE; if (mdev->dev->caps.steering_mode != MLX4_STEERING_MODE_A0) dev->priv_flags |= IFF_UNICAST_FLT; + /* Setting a default hash function value */ + if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_TOP) { + priv->rss_hash_fn = ETH_RSS_HASH_TOP; + } else if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_XOR) { + priv->rss_hash_fn = ETH_RSS_HASH_XOR; + } else { + en_warn(priv, + "No RSS hash capabilities exposed, using Toeplitz\n"); + priv->rss_hash_fn = ETH_RSS_HASH_TOP; + } + + if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) { + dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; + dev->features |= NETIF_F_GSO_UDP_TUNNEL; + } + mdev->pndev[port] = dev; + mdev->upper[port] = NULL; netif_carrier_off(dev); - err = register_netdev(dev); - if (err) { - en_err(priv, "Netdev registration failed for port %d\n", port); - goto out; - } - priv->registered = 1; + mlx4_en_set_default_moderation(priv); en_warn(priv, "Using %d TX rings\n", prof->tx_ring_num); en_warn(priv, "Using %d RX rings\n", prof->rx_ring_num); @@ -2286,11 +3039,20 @@ prof->tx_pause, prof->tx_ppp, prof->rx_pause, prof->rx_ppp); if (err) { - en_err(priv, "Failed setting port general configurations " - "for port %d, with error %d\n", priv->port, err); + en_err(priv, "Failed setting port general configurations for port %d, with error %d\n", + priv->port, err); goto out; } + if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) { + err = mlx4_SET_PORT_VXLAN(mdev->dev, priv->port, VXLAN_STEER_BY_OUTER_MAC, 1); + if (err) { + en_err(priv, "Failed setting port L2 tunnel configuration, err %d\n", + err); + goto out; + } + } + /* Init port */ en_warn(priv, "Initializing port\n"); err = mlx4_INIT_PORT(mdev->dev, priv->port); @@ -2298,12 +3060,28 @@ en_err(priv, "Failed Initializing port\n"); goto out; } - mlx4_en_set_default_moderation(priv); queue_delayed_work(mdev->workqueue, &priv->stats_task, STATS_DELAY); + /* Initialize time stamp mechanism */ if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) - queue_delayed_work(mdev->workqueue, &priv->service_task, - SERVICE_TASK_DELAY); + mlx4_en_init_timestamp(mdev); + + queue_delayed_work(mdev->workqueue, &priv->service_task, + SERVICE_TASK_DELAY); + + mlx4_en_set_stats_bitmap(mdev->dev, &priv->stats_bitmap, + mdev->profile.prof[priv->port].rx_ppp, + mdev->profile.prof[priv->port].rx_pause, + mdev->profile.prof[priv->port].tx_ppp, + mdev->profile.prof[priv->port].tx_pause); + + err = register_netdev(dev); + if (err) { + en_err(priv, "Netdev registration failed for port %d\n", port); + goto out; + } + + priv->registered = 1; return 0; @@ -2312,3 +3090,87 @@ return err; } +int mlx4_en_reset_config(struct net_device *dev, + struct hwtstamp_config ts_config, + netdev_features_t features) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + struct mlx4_en_dev *mdev = priv->mdev; + int port_up = 0; + int err = 0; + + if (priv->hwtstamp_config.tx_type == ts_config.tx_type && + priv->hwtstamp_config.rx_filter == ts_config.rx_filter && + !DEV_FEATURE_CHANGED(dev, features, NETIF_F_HW_VLAN_CTAG_RX) && + !DEV_FEATURE_CHANGED(dev, features, NETIF_F_RXFCS)) + return 0; /* Nothing to change */ + + if (DEV_FEATURE_CHANGED(dev, features, NETIF_F_HW_VLAN_CTAG_RX) && + (features & NETIF_F_HW_VLAN_CTAG_RX) && + (priv->hwtstamp_config.rx_filter != HWTSTAMP_FILTER_NONE)) { + en_warn(priv, "Can't turn ON rx vlan offload while time-stamping rx filter is ON\n"); + return -EINVAL; + } + + mutex_lock(&mdev->state_lock); + if (priv->port_up) { + port_up = 1; + mlx4_en_stop_port(dev, 1); + } + + mlx4_en_free_resources(priv); + + en_warn(priv, "Changing device configuration rx filter(%x) rx vlan(%x)\n", + ts_config.rx_filter, !!(features & NETIF_F_HW_VLAN_CTAG_RX)); + + priv->hwtstamp_config.tx_type = ts_config.tx_type; + priv->hwtstamp_config.rx_filter = ts_config.rx_filter; + + if (DEV_FEATURE_CHANGED(dev, features, NETIF_F_HW_VLAN_CTAG_RX)) { + if (features & NETIF_F_HW_VLAN_CTAG_RX) + dev->features |= NETIF_F_HW_VLAN_CTAG_RX; + else + dev->features &= ~NETIF_F_HW_VLAN_CTAG_RX; + } else if (ts_config.rx_filter == HWTSTAMP_FILTER_NONE) { + /* RX time-stamping is OFF, update the RX vlan offload + * to the latest wanted state + */ + if (dev->wanted_features & NETIF_F_HW_VLAN_CTAG_RX) + dev->features |= NETIF_F_HW_VLAN_CTAG_RX; + else + dev->features &= ~NETIF_F_HW_VLAN_CTAG_RX; + } + + if (DEV_FEATURE_CHANGED(dev, features, NETIF_F_RXFCS)) { + if (features & NETIF_F_RXFCS) + dev->features |= NETIF_F_RXFCS; + else + dev->features &= ~NETIF_F_RXFCS; + } + + /* RX vlan offload and RX time-stamping can't co-exist ! + * Regardless of the caller's choice, + * Turn Off RX vlan offload in case of time-stamping is ON + */ + if (ts_config.rx_filter != HWTSTAMP_FILTER_NONE) { + if (dev->features & NETIF_F_HW_VLAN_CTAG_RX) + en_warn(priv, "Turning off RX vlan offload since RX time-stamping is ON\n"); + dev->features &= ~NETIF_F_HW_VLAN_CTAG_RX; + } + + err = mlx4_en_alloc_resources(priv); + if (err) { + en_err(priv, "Failed reallocating port resources\n"); + goto out; + } + if (port_up) { + err = mlx4_en_start_port(dev); + if (err) + en_err(priv, "Failed starting port\n"); + } + +out: + mutex_unlock(&mdev->state_lock); + netdev_features_change(dev); + return err; +}