diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx4/en_netdev.c')
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 2132 |
1 files changed, 1673 insertions, 459 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 5eac871399d8..81bf8908b897 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -31,14 +31,19 @@ * */ +#include <linux/bpf.h> #include <linux/etherdevice.h> +#include <linux/filter.h> #include <linux/tcp.h> #include <linux/if_vlan.h> #include <linux/delay.h> #include <linux/slab.h> #include <linux/hash.h> #include <net/ip.h> -#include <net/busy_poll.h> +#include <net/vxlan.h> +#include <net/devlink.h> +#include <net/rps.h> +#include <net/netdev_queues.h> #include <linux/mlx4/driver.h> #include <linux/mlx4/device.h> @@ -48,53 +53,110 @@ #include "mlx4_en.h" #include "en_port.h" +#define MLX4_EN_MAX_XDP_MTU ((int)(PAGE_SIZE - ETH_HLEN - (2 * VLAN_HLEN) - \ + XDP_PACKET_HEADROOM - \ + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))) + int mlx4_en_setup_tc(struct net_device *dev, u8 up) { struct mlx4_en_priv *priv = netdev_priv(dev); int i; unsigned int offset = 0; - if (up && up != MLX4_EN_NUM_UP) + if (up && up != MLX4_EN_NUM_UP_HIGH) return -EINVAL; netdev_set_num_tc(dev, up); - + netif_set_real_num_tx_queues(dev, priv->tx_ring_num[TX]); /* Partition Tx queues evenly amongst UP's */ for (i = 0; i < up; i++) { netdev_set_tc_queue(dev, i, priv->num_tx_rings_p_up, offset); offset += priv->num_tx_rings_p_up; } +#ifdef CONFIG_MLX4_EN_DCB + if (!mlx4_is_slave(priv->mdev->dev)) { + if (up) { + if (priv->dcbx_cap) + priv->flags |= MLX4_EN_FLAG_DCB_ENABLED; + } else { + priv->flags &= ~MLX4_EN_FLAG_DCB_ENABLED; + priv->cee_config.pfc_state = false; + } + } +#endif /* CONFIG_MLX4_EN_DCB */ + return 0; } -#ifdef CONFIG_NET_LL_RX_POLL -/* must be called with local_bh_disable()d */ -static int mlx4_en_low_latency_recv(struct napi_struct *napi) +int mlx4_en_alloc_tx_queue_per_tc(struct net_device *dev, u8 tc) { - 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; + struct mlx4_en_dev *mdev = priv->mdev; + struct mlx4_en_port_profile new_prof; + struct mlx4_en_priv *tmp; + int total_count; + int port_up = 0; + int err = 0; - if (!priv->port_up) - return LL_FLUSH_FAILED; + tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return -ENOMEM; - if (!mlx4_en_cq_lock_poll(cq)) - return LL_FLUSH_BUSY; + mutex_lock(&mdev->state_lock); + memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile)); + new_prof.num_up = (tc == 0) ? MLX4_EN_NUM_UP_LOW : + MLX4_EN_NUM_UP_HIGH; + new_prof.tx_ring_num[TX] = new_prof.num_tx_rings_p_up * + new_prof.num_up; + total_count = new_prof.tx_ring_num[TX] + new_prof.tx_ring_num[TX_XDP]; + if (total_count > MAX_TX_RINGS) { + err = -EINVAL; + en_err(priv, + "Total number of TX and XDP rings (%d) exceeds the maximum supported (%d)\n", + total_count, MAX_TX_RINGS); + goto out; + } + err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, true); + if (err) + goto out; - done = mlx4_en_process_rx_cq(dev, cq, 4); - if (likely(done)) - rx_ring->cleaned += done; - else - rx_ring->misses++; + if (priv->port_up) { + port_up = 1; + mlx4_en_stop_port(dev, 1); + } + + mlx4_en_safe_replace_resources(priv, tmp); + if (port_up) { + err = mlx4_en_start_port(dev); + if (err) { + en_err(priv, "Failed starting port for setup TC\n"); + goto out; + } + } + + err = mlx4_en_setup_tc(dev, tc); +out: + mutex_unlock(&mdev->state_lock); + kfree(tmp); + return err; +} + +static int __mlx4_en_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) +{ + struct tc_mqprio_qopt *mqprio = type_data; - mlx4_en_cq_unlock_poll(cq); + if (type != TC_SETUP_QDISC_MQPRIO) + return -EOPNOTSUPP; + + if (mqprio->num_tc && mqprio->num_tc != MLX4_EN_NUM_UP_HIGH) + return -EINVAL; - return done; + mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + + return mlx4_en_alloc_tx_queue_per_tc(dev, mqprio->num_tc); } -#endif /* CONFIG_NET_LL_RX_POLL */ #ifdef CONFIG_RFS_ACCEL @@ -102,6 +164,7 @@ 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 +183,29 @@ 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 MLX4_NET_TRANS_RULE_NUM; + } +}; + +/* Must not acquire state_lock, as its corresponding work_sync + * is done under it. + */ 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 +241,14 @@ 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 >= 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); @@ -183,6 +266,7 @@ 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; @@ -206,10 +290,10 @@ 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; + struct mlx4_en_filter *filter; filter = kzalloc(sizeof(struct mlx4_en_filter), GFP_ATOMIC); if (!filter) @@ -221,6 +305,7 @@ 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 +337,7 @@ 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 +348,7 @@ 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 +367,7 @@ 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; @@ -288,6 +375,9 @@ mlx4_en_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb, int nhoff = skb_network_offset(skb); int ret = 0; + if (skb->encapsulation) + return -EPROTONOSUPPORT; + if (skb->protocol != htons(ETH_P_IP)) return -EPROTONOSUPPORT; @@ -295,18 +385,19 @@ 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 +405,7 @@ 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 +423,7 @@ 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); @@ -401,14 +491,18 @@ static int mlx4_en_vlan_rx_add_vid(struct net_device *dev, mutex_lock(&mdev->state_lock); if (mdev->device_up && priv->port_up) { err = mlx4_SET_VLAN_FLTR(mdev->dev, priv); - if (err) + if (err) { en_err(priv, "Failed configuring VLAN filter\n"); + goto out; + } } - if (mlx4_register_vlan(mdev->dev, priv->port, vid, &idx)) - en_dbg(HW, priv, "failed adding vlan %d\n", vid); - mutex_unlock(&mdev->state_lock); + err = mlx4_register_vlan(mdev->dev, priv->port, vid, &idx); + if (err) + en_dbg(HW, priv, "Failed adding vlan %d\n", vid); - return 0; +out: + mutex_unlock(&mdev->state_lock); + return err; } static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev, @@ -416,8 +510,7 @@ static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev, { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; - int err; - int idx; + int err = 0; en_dbg(HW, priv, "Killing VID:%d\n", vid); @@ -425,10 +518,7 @@ static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev, /* 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_dbg(HW, 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); @@ -437,21 +527,41 @@ static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev, } mutex_unlock(&mdev->state_lock); - return 0; + return err; } -static void mlx4_en_u64_to_mac(unsigned char dst_mac[ETH_ALEN + 2], u64 src_mac) +static void mlx4_en_u64_to_mac(struct net_device *dev, u64 src_mac) { - int i; - for (i = ETH_ALEN - 1; i >= 0; --i) { - dst_mac[i] = src_mac & 0xff; - src_mac >>= 8; + u8 addr[ETH_ALEN]; + + u64_to_ether_addr(src_mac, addr); + eth_hw_addr_set(dev, addr); +} + + +static int mlx4_en_tunnel_steer_add(struct mlx4_en_priv *priv, + const 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; } - memset(&dst_mac[ETH_ALEN], 0, 2); + 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) + const unsigned char *mac, int *qpn, u64 *reg_id) { struct mlx4_en_dev *mdev = priv->mdev; struct mlx4_dev *dev = mdev->dev; @@ -503,7 +613,8 @@ static int mlx4_en_uc_steer_add(struct mlx4_en_priv *priv, } static void mlx4_en_uc_steer_release(struct mlx4_en_priv *priv, - unsigned char *mac, int qpn, u64 reg_id) + const unsigned char *mac, + int qpn, u64 reg_id) { struct mlx4_en_dev *mdev = priv->mdev; struct mlx4_dev *dev = mdev->dev; @@ -533,12 +644,10 @@ static int mlx4_en_get_qp(struct mlx4_en_priv *priv) { 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 = ether_addr_to_u64(priv->dev->dev_addr); en_dbg(DRV, priv, "Registering MAC: %pM for adding\n", priv->dev->dev_addr); @@ -550,45 +659,24 @@ static int mlx4_en_get_qp(struct mlx4_en_priv *priv) return err; } + en_info(priv, "Steering Mode %d\n", dev->caps.steering_mode); + if (dev->caps.steering_mode == MLX4_STEERING_MODE_A0) { int base_qpn = mlx4_get_base_qpn(dev, priv->port); *qpn = base_qpn + index; return 0; } - err = mlx4_qp_reserve_range(dev, 1, 1, qpn); + err = mlx4_qp_reserve_range(dev, 1, 1, qpn, MLX4_RESERVE_A0_QP, + MLX4_RES_USAGE_DRIVER); 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) @@ -596,34 +684,13 @@ static void mlx4_en_put_qp(struct mlx4_en_priv *priv) 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 = ether_addr_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); @@ -637,14 +704,14 @@ static int mlx4_en_replace_mac(struct mlx4_en_priv *priv, int qpn, 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 = ether_addr_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 = ether_addr_to_u64(prev_mac); bucket = &priv->mac_hash[prev_mac[MLX4_EN_MAC_HASH_IDX]]; hlist_for_each_entry_safe(entry, tmp, bucket, hlist) { @@ -664,6 +731,14 @@ static int mlx4_en_replace_mac(struct mlx4_en_priv *priv, int qpn, 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; } } @@ -673,33 +748,38 @@ static int mlx4_en_replace_mac(struct mlx4_en_priv *priv, int qpn, return __mlx4_replace_mac(dev, priv->port, qpn, new_mac_u64); } -u64 mlx4_en_mac_to_u64(u8 *addr) +static void mlx4_en_update_user_mac(struct mlx4_en_priv *priv, + unsigned char new_mac[ETH_ALEN + 2]) { - u64 mac = 0; - int i; + struct mlx4_en_dev *mdev = priv->mdev; + int err; - for (i = 0; i < ETH_ALEN; i++) { - mac <<= 8; - mac |= addr[i]; - } - return mac; + if (!(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_USER_MAC_EN)) + return; + + err = mlx4_SET_PORT_user_mac(mdev->dev, priv->port, new_mac); + if (err) + en_err(priv, "Failed to pass user MAC(%pM) to Firmware for port %d, with error %d\n", + new_mac, priv->port, err); } -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; } @@ -708,15 +788,21 @@ static int mlx4_en_set_mac(struct net_device *dev, void *addr) 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) + goto out; + + eth_hw_addr_set(dev, saddr->sa_data); + mlx4_en_update_user_mac(priv, new_mac); +out: mutex_unlock(&mdev->state_lock); return err; @@ -764,7 +850,7 @@ static void update_mclist_flags(struct mlx4_en_priv *priv, 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; } @@ -779,7 +865,7 @@ static void update_mclist_flags(struct mlx4_en_priv *priv, 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; @@ -865,11 +951,6 @@ static void mlx4_en_set_promisc_mode(struct mlx4_en_priv *priv, 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"); } } @@ -918,11 +999,6 @@ static void mlx4_en_clear_promisc_mode(struct mlx4_en_priv *priv, 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, @@ -998,12 +1074,13 @@ static void mlx4_en_do_multicast(struct mlx4_en_priv *priv, 1, MLX4_MCAST_CONFIG); /* Update multicast list - we cache all addresses so they won't - * change while HW is updated holding the command semaphor */ + * change while HW is updated holding the command semaphore + */ netif_addr_lock_bh(dev); 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 = ether_addr_to_u64(mclist->addr); mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, mcast_addr, 0, MLX4_MCAST_CONFIG); } @@ -1019,13 +1096,19 @@ static void mlx4_en_do_multicast(struct mlx4_en_priv *priv, memcpy(&mc_list[10], mclist->addr, ETH_ALEN); mc_list[5] = priv->port; err = mlx4_multicast_detach(mdev->dev, - &priv->rss_map.indir_qp, + priv->rss_map.indir_qp, mc_list, MLX4_PROT_ETH, mclist->reg_id); 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); @@ -1035,7 +1118,7 @@ static void mlx4_en_do_multicast(struct mlx4_en_priv *priv, /* needed for B0 steering support */ mc_list[5] = priv->port; err = mlx4_multicast_attach(mdev->dev, - &priv->rss_map.indir_qp, + priv->rss_map.indir_qp, mc_list, priv->port, 0, MLX4_PROT_ETH, @@ -1043,6 +1126,10 @@ static void mlx4_en_do_multicast(struct mlx4_en_priv *priv, 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"); } } } @@ -1081,20 +1168,21 @@ static void mlx4_en_do_uc_filter(struct mlx4_en_priv *priv, } /* 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 = ether_addr_to_u64(entry->mac); mlx4_en_uc_steer_release(priv, entry->mac, priv->base_qpn, entry->reg_id); mlx4_unregister_mac(mdev->dev, priv->port, mac); hlist_del_rcu(&entry->hlist); - kfree_rcu(entry, rcu); en_dbg(DRV, priv, "Removed MAC %pM on port:%d\n", entry->mac, priv->port); + kfree_rcu(entry, rcu); ++removed; } } @@ -1128,7 +1216,7 @@ static void mlx4_en_do_uc_filter(struct mlx4_en_priv *priv, priv->flags |= MLX4_EN_FLAG_FORCE_PROMISC; break; } - mac = mlx4_en_mac_to_u64(ha->addr); + mac = ether_addr_to_u64(ha->addr); memcpy(entry->mac, ha->addr, ETH_ALEN); err = mlx4_register_mac(mdev->dev, priv->port, mac); if (err < 0) { @@ -1188,7 +1276,6 @@ static void mlx4_en_do_set_rx_mode(struct work_struct *work) if (!netif_carrier_ok(dev)) { if (!mlx4_en_QUERY_PORT(mdev, priv->port)) { if (priv->port_state.link_state) { - priv->last_link_state = MLX4_DEV_EVENT_PORT_UP; netif_carrier_on(dev); en_dbg(LINK, priv, "Link Up\n"); } @@ -1214,62 +1301,111 @@ out: mutex_unlock(&mdev->state_lock); } -#ifdef CONFIG_NET_POLL_CONTROLLER -static void mlx4_en_netpoll(struct net_device *dev) +static int mlx4_en_set_rss_steer_rules(struct mlx4_en_priv *priv) { - struct mlx4_en_priv *priv = netdev_priv(dev); - struct mlx4_en_cq *cq; - unsigned long flags; - int i; + u64 reg_id; + int err = 0; + int *qpn = &priv->base_qpn; + struct mlx4_mac_entry *entry; - for (i = 0; i < priv->rx_ring_num; i++) { - cq = &priv->rx_cq[i]; - spin_lock_irqsave(&cq->lock, flags); - napi_synchronize(&cq->napi); - mlx4_en_process_rx_cq(dev, cq, 0); - spin_unlock_irqrestore(&cq->lock, flags); + 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; } -#endif -static void mlx4_en_tx_timeout(struct net_device *dev) +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 = ether_addr_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, unsigned int txqueue) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; - int i; + struct mlx4_en_tx_ring *tx_ring = priv->tx_ring[TX][txqueue]; 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); - } + en_warn(priv, "TX timeout on queue: %d, QP: 0x%x, CQ: 0x%x, Cons: 0x%x, Prod: 0x%x\n", + txqueue, tx_ring->qpn, tx_ring->sp_cqn, + tx_ring->cons, tx_ring->prod); priv->port_stats.tx_timeout++; - en_dbg(DRV, priv, "Scheduling watchdog\n"); - queue_work(mdev->workqueue, &priv->watchdog_task); + if (!test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state)) { + en_dbg(DRV, priv, "Scheduling port restart\n"); + queue_work(mdev->workqueue, &priv->restart_task); + } } -static struct net_device_stats *mlx4_en_get_stats(struct net_device *dev) +static void +mlx4_en_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct mlx4_en_priv *priv = netdev_priv(dev); spin_lock_bh(&priv->stats_lock); - memcpy(&priv->ret_stats, &priv->stats, sizeof(priv->stats)); + mlx4_en_fold_software_stats(dev); + netdev_stats_to_stats64(stats, &dev->stats); spin_unlock_bh(&priv->stats_lock); - - return &priv->ret_stats; } static void mlx4_en_set_default_moderation(struct mlx4_en_priv *priv) { struct mlx4_en_cq *cq; - int i; + int i, t; /* If we haven't received a specific coalescing setting * (module param), we set the moderation parameters as follows: @@ -1281,12 +1417,12 @@ static void mlx4_en_set_default_moderation(struct mlx4_en_priv *priv) priv->rx_usecs = MLX4_EN_RX_COAL_TIME; priv->tx_frames = MLX4_EN_TX_COAL_PKTS; priv->tx_usecs = MLX4_EN_TX_COAL_TIME; - en_dbg(INTR, priv, "Default coalesing params for mtu:%d - rx_frames:%d rx_usecs:%d\n", + en_dbg(INTR, priv, "Default coalescing params for mtu:%d - rx_frames:%d rx_usecs:%d\n", priv->dev->mtu, priv->rx_frames, priv->rx_usecs); /* 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; @@ -1294,10 +1430,12 @@ static void mlx4_en_set_default_moderation(struct mlx4_en_priv *priv) priv->last_moder_bytes[i] = 0; } - for (i = 0; i < priv->tx_ring_num; i++) { - cq = &priv->tx_cq[i]; - cq->moder_cnt = priv->tx_frames; - cq->moder_time = priv->tx_usecs; + for (t = 0 ; t < MLX4_EN_NUM_TX_TYPES; t++) { + for (i = 0; i < priv->tx_ring_num[t]; i++) { + cq = priv->tx_cq[t][i]; + cq->moder_cnt = priv->tx_frames; + cq->moder_time = priv->tx_usecs; + } } /* Reset auto-moderation params */ @@ -1314,6 +1452,7 @@ static void mlx4_en_set_default_moderation(struct mlx4_en_priv *priv) static void mlx4_en_auto_moderation(struct mlx4_en_priv *priv) { unsigned long period = (unsigned long) (jiffies - priv->last_moder_jiffies); + u32 pkt_rate_high, pkt_rate_low; struct mlx4_en_cq *cq; unsigned long packets; unsigned long rate; @@ -1327,39 +1466,40 @@ static void mlx4_en_auto_moderation(struct mlx4_en_priv *priv) if (!priv->adaptive_rx_coal || period < priv->sample_interval * HZ) return; + pkt_rate_low = READ_ONCE(priv->pkt_rate_low); + pkt_rate_high = READ_ONCE(priv->pkt_rate_high); + 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; - spin_unlock_bh(&priv->stats_lock); + rx_packets = READ_ONCE(priv->rx_ring[ring]->packets); + rx_bytes = READ_ONCE(priv->rx_ring[ring]->bytes); - rx_pkt_diff = ((unsigned long) (rx_packets - - priv->last_moder_packets[ring])); + rx_pkt_diff = rx_packets - priv->last_moder_packets[ring]; packets = rx_pkt_diff; rate = packets * HZ / period; - avg_pkt_size = packets ? ((unsigned long) (rx_bytes - - priv->last_moder_bytes[ring])) / packets : 0; + avg_pkt_size = packets ? (rx_bytes - + priv->last_moder_bytes[ring]) / packets : 0; /* Apply auto-moderation only when packet rate * exceeds a rate that it matters */ if (rate > (MLX4_EN_RX_RATE_THRESH / priv->rx_ring_num) && avg_pkt_size > MLX4_EN_AVG_PKT_SMALL) { - if (rate < priv->pkt_rate_low) + if (rate <= pkt_rate_low) moder_time = priv->rx_usecs_low; - else if (rate > priv->pkt_rate_high) + else if (rate >= pkt_rate_high) moder_time = priv->rx_usecs_high; else - moder_time = (rate - priv->pkt_rate_low) * + moder_time = (rate - pkt_rate_low) * (priv->rx_usecs_high - priv->rx_usecs_low) / - (priv->pkt_rate_high - priv->pkt_rate_low) + + (pkt_rate_high - pkt_rate_low) + priv->rx_usecs_low; } else { moder_time = priv->rx_usecs_low; } - if (moder_time != priv->last_moder_time[ring]) { + cq = priv->rx_cq[ring]; + if (moder_time != priv->last_moder_time[ring] || + cq->moder_cnt != priv->rx_frames) { priv->last_moder_time[ring] = moder_time; - cq = &priv->rx_cq[ring]; cq->moder_time = moder_time; cq->moder_cnt = priv->rx_frames; err = mlx4_en_set_cq_moder(priv, cq); @@ -1395,7 +1535,7 @@ static void mlx4_en_do_get_stats(struct work_struct *work) 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); @@ -1416,35 +1556,75 @@ static void mlx4_en_service_task(struct work_struct *work) 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); } mutex_unlock(&mdev->state_lock); } -static void mlx4_en_linkstate(struct work_struct *work) +static void mlx4_en_linkstate(struct mlx4_en_priv *priv) +{ + struct mlx4_en_port_state *port_state = &priv->port_state; + struct mlx4_en_dev *mdev = priv->mdev; + struct net_device *dev = priv->dev; + bool up; + + if (mlx4_en_QUERY_PORT(mdev, priv->port)) + port_state->link_state = MLX4_PORT_STATE_DEV_EVENT_PORT_DOWN; + + up = port_state->link_state == MLX4_PORT_STATE_DEV_EVENT_PORT_UP; + if (up == netif_carrier_ok(dev)) + netif_carrier_event(dev); + if (!up) { + en_info(priv, "Link Down\n"); + netif_carrier_off(dev); + } else { + en_info(priv, "Link Up\n"); + netif_carrier_on(dev); + } +} + +static void mlx4_en_linkstate_work(struct work_struct *work) { struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv, linkstate_task); struct mlx4_en_dev *mdev = priv->mdev; - int linkstate = priv->link_state; mutex_lock(&mdev->state_lock); - /* If observable port state changed set carrier state and - * report to system log */ - if (priv->last_link_state != linkstate) { - if (linkstate == MLX4_DEV_EVENT_PORT_DOWN) { - en_info(priv, "Link Down\n"); - netif_carrier_off(priv->dev); - } else { - en_info(priv, "Link Up\n"); - netif_carrier_on(priv->dev); - } - } - priv->last_link_state = linkstate; + mlx4_en_linkstate(priv); 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); +} + +static void mlx4_en_init_recycle_ring(struct mlx4_en_priv *priv, + int tx_ring_idx) +{ + struct mlx4_en_tx_ring *tx_ring = priv->tx_ring[TX_XDP][tx_ring_idx]; + int rr_index = tx_ring_idx; + + tx_ring->free_tx_desc = mlx4_en_recycle_tx_desc; + tx_ring->recycle_ring = priv->rx_ring[rr_index]; + en_dbg(DRV, priv, "Set tx_ring[%d][%d]->recycle_ring = rx_ring[%d]\n", + TX_XDP, tx_ring_idx, rr_index); +} int mlx4_en_start_port(struct net_device *dev) { @@ -1453,9 +1633,8 @@ int mlx4_en_start_port(struct net_device *dev) struct mlx4_en_cq *cq; struct mlx4_en_tx_ring *tx_ring; int rx_index = 0; - int tx_index = 0; int err = 0; - int i; + int i, t; int j; u8 mc_list[16] = {0}; @@ -1471,7 +1650,7 @@ int mlx4_en_start_port(struct net_device *dev) sizeof(struct ethtool_flow_id) * MAX_NUM_OF_FS_RULES); /* Calculate Rx buf size */ - dev->mtu = min(dev->mtu, priv->max_mtu); + WRITE_ONCE(dev->mtu, min(dev->mtu, priv->max_mtu)); mlx4_en_calc_rx_buf(dev); en_dbg(DRV, priv, "Rx buf size:%d\n", priv->rx_skb_size); @@ -1482,25 +1661,38 @@ 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); + 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; } @@ -1513,6 +1705,9 @@ int mlx4_en_start_port(struct net_device *dev) } 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"); @@ -1524,41 +1719,56 @@ int mlx4_en_start_port(struct net_device *dev) goto rss_err; /* Configure tx cq's and rings */ - for (i = 0; i < priv->tx_ring_num; i++) { - /* Configure cq */ - cq = &priv->tx_cq[i]; - err = mlx4_en_activate_cq(priv, cq, i); - if (err) { - en_err(priv, "Failed allocating Tx CQ\n"); - goto tx_err; - } - err = mlx4_en_set_cq_moder(priv, cq); - if (err) { - en_err(priv, "Failed setting cq moderation parameters"); - mlx4_en_deactivate_cq(priv, cq); - goto tx_err; - } - en_dbg(DRV, priv, "Resetting index of collapsed CQ:%d to -1\n", i); - cq->buf->wqe_index = cpu_to_be16(0xffff); + for (t = 0 ; t < MLX4_EN_NUM_TX_TYPES; t++) { + u8 num_tx_rings_p_up = t == TX ? + priv->num_tx_rings_p_up : priv->tx_ring_num[t]; + + for (i = 0; i < priv->tx_ring_num[t]; i++) { + /* Configure cq */ + cq = priv->tx_cq[t][i]; + err = mlx4_en_activate_cq(priv, cq, i); + if (err) { + en_err(priv, "Failed allocating Tx CQ\n"); + goto tx_err; + } + err = mlx4_en_set_cq_moder(priv, cq); + if (err) { + en_err(priv, "Failed setting cq moderation parameters\n"); + mlx4_en_deactivate_cq(priv, cq); + goto tx_err; + } + en_dbg(DRV, priv, + "Resetting index of collapsed CQ:%d to -1\n", i); + cq->buf->wqe_index = cpu_to_be16(0xffff); + + /* Configure ring */ + tx_ring = priv->tx_ring[t][i]; + err = mlx4_en_activate_tx_ring(priv, tx_ring, + cq->mcq.cqn, + i / num_tx_rings_p_up); + if (err) { + en_err(priv, "Failed allocating Tx ring\n"); + mlx4_en_deactivate_cq(priv, cq); + goto tx_err; + } + clear_bit(MLX4_EN_TX_RING_STATE_RECOVERING, &tx_ring->state); + if (t != TX_XDP) { + tx_ring->tx_queue = netdev_get_tx_queue(dev, i); + tx_ring->recycle_ring = NULL; - /* Configure ring */ - 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) { - en_err(priv, "Failed allocating Tx ring\n"); - mlx4_en_deactivate_cq(priv, cq); - goto tx_err; - } - tx_ring->tx_queue = netdev_get_tx_queue(dev, i); + /* Arm CQ for TX completions */ + mlx4_en_arm_cq(priv, cq); - /* Arm CQ for TX completions */ - mlx4_en_arm_cq(priv, cq); + } else { + mlx4_en_init_tx_xdp_ring_descs(priv, tx_ring); + mlx4_en_init_recycle_ring(priv, i); + /* XDP TX CQ should never be armed */ + } - /* Set initial ownership of all Tx TXBBs to SW (1) */ - for (j = 0; j < tx_ring->buf_size; j += STAMP_STRIDE) - *((u32 *) (tx_ring->buf + j)) = 0xffffffff; - ++tx_index; + /* Set initial ownership of all Tx TXBBs to SW (1) */ + for (j = 0; j < tx_ring->buf_size; j += STAMP_STRIDE) + *((u32 *)(tx_ring->buf + j)) = 0xffffffff; + } } /* Configure port */ @@ -1573,6 +1783,14 @@ int mlx4_en_start_port(struct net_device *dev) priv->port, err); goto tx_err; } + + err = mlx4_SET_PORT_user_mtu(mdev->dev, priv->port, dev->mtu); + if (err) { + en_err(priv, "Failed to pass user MTU(%d) to Firmware for port %d, with error %d\n", + dev->mtu, priv->port, err); + goto tx_err; + } + /* Set default qp number */ err = mlx4_SET_PORT_qpn_calc(mdev->dev, priv->port, priv->base_qpn, 0); if (err) { @@ -1580,6 +1798,15 @@ int mlx4_en_start_port(struct net_device *dev) 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); @@ -1588,10 +1815,15 @@ int mlx4_en_start_port(struct net_device *dev) goto tx_err; } - /* Attach rx QP to bradcast address */ - memset(&mc_list[10], 0xff, ETH_ALEN); + /* 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 broadcast address */ + 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, + if (mlx4_multicast_attach(mdev->dev, priv->rss_map.indir_qp, mc_list, priv->port, 0, MLX4_PROT_ETH, &priv->broadcast_id)) mlx4_warn(mdev, "Failed Attaching Broadcast\n"); @@ -1602,18 +1834,39 @@ int mlx4_en_start_port(struct net_device *dev) /* Schedule multicast task to populate multicast list */ queue_work(mdev->workqueue, &priv->rx_mode_task); - mlx4_set_stats_bitmap(mdev->dev, &priv->stats_bitmap); + if (priv->mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) + udp_tunnel_nic_reset_ntf(dev); priv->port_up = true; + + /* Process all completions if exist to prevent + * the queues freezing if they are full + */ + for (i = 0; i < priv->rx_ring_num; i++) { + local_bh_disable(); + napi_schedule(&priv->rx_cq[i]->napi); + local_bh_enable(); + } + + clear_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state); netif_tx_start_all_queues(dev); netif_device_attach(dev); return 0; 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]); + if (t == MLX4_EN_NUM_TX_TYPES) { + t--; + i = priv->tx_ring_num[t]; + } + while (t >= 0) { + while (i--) { + mlx4_en_deactivate_tx_ring(priv, priv->tx_ring[t][i]); + mlx4_en_deactivate_cq(priv, priv->tx_cq[t][i]); + } + if (!t--) + break; + i = priv->tx_ring_num[t]; } mlx4_en_destroy_drop_qp(priv); rss_err: @@ -1621,10 +1874,12 @@ rss_err: 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 */ } @@ -1636,7 +1891,7 @@ void mlx4_en_stop_port(struct net_device *dev, int detach) struct mlx4_en_dev *mdev = priv->mdev; struct mlx4_en_mc_list *mclist, *tmp; struct ethtool_flow_id *flow, *tmp_flow; - int i; + int i, t; u8 mc_list[16] = {0}; if (!priv->port_up) { @@ -1656,8 +1911,13 @@ void mlx4_en_stop_port(struct net_device *dev, int detach) netif_tx_disable(dev); + spin_lock_bh(&priv->stats_lock); + mlx4_en_fold_software_stats(dev); /* Set port as not active */ priv->port_up = false; + spin_unlock_bh(&priv->stats_lock); + + priv->counter_index = MLX4_SINK_COUNTER_INDEX(mdev->dev); /* Promsicuous mode */ if (mdev->dev->caps.steering_mode == @@ -1686,15 +1946,17 @@ void mlx4_en_stop_port(struct net_device *dev, int detach) } /* 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_multicast_detach(mdev->dev, priv->rss_map.indir_qp, mc_list, MLX4_PROT_ETH, priv->broadcast_id); list_for_each_entry(mclist, &priv->curr_list, list) { memcpy(&mc_list[10], mclist->addr, ETH_ALEN); mc_list[5] = priv->port; - mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp, + 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) { @@ -1719,50 +1981,51 @@ void mlx4_en_stop_port(struct net_device *dev, int detach) mlx4_en_destroy_drop_qp(priv); /* 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]); + for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) { + for (i = 0; i < priv->tx_ring_num[t]; i++) { + mlx4_en_deactivate_tx_ring(priv, priv->tx_ring[t][i]); + mlx4_en_deactivate_cq(priv, priv->tx_cq[t][i]); + } } msleep(10); - for (i = 0; i < priv->tx_ring_num; i++) - mlx4_en_free_tx_buf(dev, &priv->tx_ring[i]); + for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) + for (i = 0; i < priv->tx_ring_num[t]; i++) + mlx4_en_free_tx_buf(dev, priv->tx_ring[t][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++) { - struct mlx4_en_cq *cq = &priv->rx_cq[i]; - - local_bh_disable(); - while (!mlx4_en_cq_lock_napi(cq)) { - pr_info("CQ %d locked\n", i); - mdelay(1); - } - local_bh_enable(); + struct mlx4_en_cq *cq = priv->rx_cq[i]; - while (test_bit(NAPI_STATE_SCHED, &cq->napi.state)) - msleep(1); - mlx4_en_deactivate_rx_ring(priv, &priv->rx_ring[i]); + 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) { struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv, - watchdog_task); + restart_task); struct mlx4_en_dev *mdev = priv->mdev; struct net_device *dev = priv->dev; en_dbg(DRV, priv, "Watchdog task called for port %d\n", priv->port); + rtnl_lock(); mutex_lock(&mdev->state_lock); if (priv->port_up) { mlx4_en_stop_port(dev, 1); @@ -1770,32 +2033,48 @@ static void mlx4_en_restart(struct work_struct *work) en_err(priv, "Failed restarting port %d\n", priv->port); } mutex_unlock(&mdev->state_lock); + rtnl_unlock(); } static void mlx4_en_clear_stats(struct net_device *dev) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; + struct mlx4_en_tx_ring **tx_ring; int i; - if (mlx4_en_DUMP_ETH_STATS(mdev, priv->port, 1)) - en_dbg(HW, priv, "Failed dumping statistics\n"); + if (!mlx4_is_slave(mdev->dev)) + if (mlx4_en_DUMP_ETH_STATS(mdev, priv->port, 1)) + en_dbg(HW, priv, "Failed dumping statistics\n"); - memset(&priv->stats, 0, sizeof(priv->stats)); - memset(&priv->pstats, 0, sizeof(priv->pstats)); memset(&priv->pkstats, 0, sizeof(priv->pkstats)); 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; + 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)); + + tx_ring = priv->tx_ring[TX]; + for (i = 0; i < priv->tx_ring_num[TX]; i++) { + tx_ring[i]->bytes = 0; + tx_ring[i]->packets = 0; + tx_ring[i]->tx_csum = 0; + tx_ring[i]->tx_dropped = 0; + tx_ring[i]->queue_stopped = 0; + tx_ring[i]->wake_queue = 0; + tx_ring[i]->tso_packets = 0; + tx_ring[i]->xmit_more = 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; + priv->rx_ring[i]->alloc_fail = 0; } } @@ -1817,9 +2096,11 @@ static int mlx4_en_open(struct net_device *dev) mlx4_en_clear_stats(dev); err = mlx4_en_start_port(dev); - if (err) + if (err) { en_err(priv, "Failed starting port:%d\n", priv->port); - + goto out; + } + mlx4_en_linkstate(priv); out: mutex_unlock(&mdev->state_lock); return err; @@ -1842,86 +2123,216 @@ static int mlx4_en_close(struct net_device *dev) return 0; } -void mlx4_en_free_resources(struct mlx4_en_priv *priv) +static void mlx4_en_free_resources(struct mlx4_en_priv *priv) { - int i; + int i, t; #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) - mlx4_en_destroy_tx_ring(priv, &priv->tx_ring[i]); - if (priv->tx_cq[i].buf) - mlx4_en_destroy_cq(priv, &priv->tx_cq[i]); + for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) { + for (i = 0; i < priv->tx_ring_num[t]; i++) { + if (priv->tx_ring[t] && priv->tx_ring[t][i]) + mlx4_en_destroy_tx_ring(priv, + &priv->tx_ring[t][i]); + if (priv->tx_cq[t] && priv->tx_cq[t][i]) + mlx4_en_destroy_cq(priv, &priv->tx_cq[t][i]); + } + kfree(priv->tx_ring[t]); + kfree(priv->tx_cq[t]); } 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) +static 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 i, t; + int node; /* Create tx Rings */ - for (i = 0; i < priv->tx_ring_num; i++) { - if (mlx4_en_create_cq(priv, &priv->tx_cq[i], - prof->tx_ring_size, i, TX)) - goto err; - - if (mlx4_en_create_tx_ring(priv, &priv->tx_ring[i], priv->base_tx_qpn + i, - prof->tx_ring_size, TXBB_SIZE)) - goto err; + for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) { + for (i = 0; i < priv->tx_ring_num[t]; i++) { + node = cpu_to_node(i % num_online_cpus()); + if (mlx4_en_create_cq(priv, &priv->tx_cq[t][i], + prof->tx_ring_size, i, t, node)) + goto err; + + if (mlx4_en_create_tx_ring(priv, &priv->tx_ring[t][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, i)) 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 (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) { + for (i = 0; i < priv->tx_ring_num[t]; i++) { + if (priv->tx_ring[t][i]) + mlx4_en_destroy_tx_ring(priv, + &priv->tx_ring[t][i]); + if (priv->tx_cq[t][i]) + mlx4_en_destroy_cq(priv, &priv->tx_cq[t][i]); + } + } return -ENOMEM; } +static int mlx4_en_copy_priv(struct mlx4_en_priv *dst, + struct mlx4_en_priv *src, + struct mlx4_en_port_profile *prof) +{ + int t; + + memcpy(&dst->hwtstamp_config, &prof->hwtstamp_config, + sizeof(dst->hwtstamp_config)); + dst->num_tx_rings_p_up = prof->num_tx_rings_p_up; + dst->rx_ring_num = prof->rx_ring_num; + dst->flags = prof->flags; + dst->mdev = src->mdev; + dst->port = src->port; + dst->dev = src->dev; + dst->prof = prof; + dst->stride = roundup_pow_of_two(sizeof(struct mlx4_en_rx_desc) + + DS_SIZE * MLX4_EN_MAX_RX_FRAGS); + + for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) { + dst->tx_ring_num[t] = prof->tx_ring_num[t]; + if (!dst->tx_ring_num[t]) + continue; + + dst->tx_ring[t] = kcalloc(MAX_TX_RINGS, + sizeof(struct mlx4_en_tx_ring *), + GFP_KERNEL); + if (!dst->tx_ring[t]) + goto err_free_tx; + + dst->tx_cq[t] = kcalloc(MAX_TX_RINGS, + sizeof(struct mlx4_en_cq *), + GFP_KERNEL); + if (!dst->tx_cq[t]) { + kfree(dst->tx_ring[t]); + goto err_free_tx; + } + } + + return 0; + +err_free_tx: + while (t--) { + kfree(dst->tx_ring[t]); + kfree(dst->tx_cq[t]); + } + return -ENOMEM; +} + +static void mlx4_en_update_priv(struct mlx4_en_priv *dst, + struct mlx4_en_priv *src) +{ + int t; + memcpy(dst->rx_ring, src->rx_ring, + sizeof(struct mlx4_en_rx_ring *) * src->rx_ring_num); + memcpy(dst->rx_cq, src->rx_cq, + sizeof(struct mlx4_en_cq *) * src->rx_ring_num); + memcpy(&dst->hwtstamp_config, &src->hwtstamp_config, + sizeof(dst->hwtstamp_config)); + for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) { + dst->tx_ring_num[t] = src->tx_ring_num[t]; + dst->tx_ring[t] = src->tx_ring[t]; + dst->tx_cq[t] = src->tx_cq[t]; + } + dst->num_tx_rings_p_up = src->num_tx_rings_p_up; + dst->rx_ring_num = src->rx_ring_num; + memcpy(dst->prof, src->prof, sizeof(struct mlx4_en_port_profile)); +} + +int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv, + struct mlx4_en_priv *tmp, + struct mlx4_en_port_profile *prof, + bool carry_xdp_prog) +{ + struct bpf_prog *xdp_prog; + int i, t, ret; + + ret = mlx4_en_copy_priv(tmp, priv, prof); + if (ret) { + en_warn(priv, "%s: mlx4_en_copy_priv() failed, return\n", + __func__); + return ret; + } + + if (mlx4_en_alloc_resources(tmp)) { + en_warn(priv, + "%s: Resource allocation failed, using previous configuration\n", + __func__); + for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) { + kfree(tmp->tx_ring[t]); + kfree(tmp->tx_cq[t]); + } + return -ENOMEM; + } + + /* All rx_rings has the same xdp_prog. Pick the first one. */ + xdp_prog = rcu_dereference_protected( + priv->rx_ring[0]->xdp_prog, + lockdep_is_held(&priv->mdev->state_lock)); + + if (xdp_prog && carry_xdp_prog) { + bpf_prog_add(xdp_prog, tmp->rx_ring_num); + for (i = 0; i < tmp->rx_ring_num; i++) + rcu_assign_pointer(tmp->rx_ring[i]->xdp_prog, + xdp_prog); + } + + return 0; +} + +void mlx4_en_safe_replace_resources(struct mlx4_en_priv *priv, + struct mlx4_en_priv *tmp) +{ + mlx4_en_free_resources(priv); + mlx4_en_update_priv(priv, tmp); +} + void mlx4_en_destroy_netdev(struct net_device *dev) { struct mlx4_en_priv *priv = netdev_priv(dev); @@ -1941,19 +2352,37 @@ void mlx4_en_destroy_netdev(struct net_device *dev) /* 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; - mutex_unlock(&mdev->state_lock); + mdev->upper[priv->port] = NULL; - mlx4_en_free_resources(priv); +#ifdef CONFIG_RFS_ACCEL + mlx4_en_cleanup_filters(priv); +#endif - kfree(priv->tx_ring); - kfree(priv->tx_cq); + mlx4_en_free_resources(priv); + mutex_unlock(&mdev->state_lock); free_netdev(dev); } +static bool mlx4_en_check_xdp_mtu(struct net_device *dev, int mtu) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + + if (mtu > MLX4_EN_MAX_XDP_MTU) { + en_err(priv, "mtu:%d > max:%d when XDP prog is attached\n", + mtu, MLX4_EN_MAX_XDP_MTU); + return false; + } + + return true; +} + static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu) { struct mlx4_en_priv *priv = netdev_priv(dev); @@ -1963,16 +2392,16 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu) en_dbg(DRV, priv, "Change MTU called - current:%d new:%d\n", dev->mtu, new_mtu); - if ((new_mtu < MLX4_EN_MIN_MTU) || (new_mtu > priv->max_mtu)) { - en_err(priv, "Bad MTU size:%d.\n", new_mtu); - return -EPERM; - } - dev->mtu = new_mtu; + if (priv->tx_ring_num[TX_XDP] && + !mlx4_en_check_xdp_mtu(dev, new_mtu)) + return -EOPNOTSUPP; + + WRITE_ONCE(dev->mtu, new_mtu); if (netif_running(dev)) { mutex_lock(&mdev->state_lock); if (!mdev->device_up) { - /* NIC is probably restarting - let watchdog task reset + /* NIC is probably restarting - let restart task reset * the port */ en_dbg(DRV, priv, "Change MTU called with card down!?\n"); } else { @@ -1981,7 +2410,9 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu) if (err) { en_err(priv, "Failed restarting port:%d\n", priv->port); - queue_work(mdev->workqueue, &priv->watchdog_task); + if (!test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, + &priv->state)) + queue_work(mdev->workqueue, &priv->restart_task); } } mutex_unlock(&mdev->state_lock); @@ -1989,25 +2420,22 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu) 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 kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; - struct hwtstamp_config config; - - if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) - return -EFAULT; - - /* reserved for future extensions */ - if (config.flags) - return -EINVAL; /* device doesn't support time stamping */ - if (!(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)) + if (!(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)) { + NL_SET_ERR_MSG_MOD(extack, + "device doesn't support time stamping"); return -EINVAL; + } /* TX HW timestamp */ - switch (config.tx_type) { + switch (config->tx_type) { case HWTSTAMP_TX_OFF: case HWTSTAMP_TX_ON: break; @@ -2016,7 +2444,7 @@ static int mlx4_en_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr) } /* RX HW timestamp */ - switch (config.rx_filter) { + switch (config->rx_filter) { case HWTSTAMP_FILTER_NONE: break; case HWTSTAMP_FILTER_ALL: @@ -2033,66 +2461,129 @@ static int mlx4_en_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr) case HWTSTAMP_FILTER_PTP_V2_EVENT: case HWTSTAMP_FILTER_PTP_V2_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: - config.rx_filter = HWTSTAMP_FILTER_ALL; + case HWTSTAMP_FILTER_NTP_ALL: + config->rx_filter = HWTSTAMP_FILTER_ALL; break; default: return -ERANGE; } - if (mlx4_en_timestamp_config(dev, config.tx_type, config.rx_filter)) { - config.tx_type = HWTSTAMP_TX_OFF; - config.rx_filter = HWTSTAMP_FILTER_NONE; + if (mlx4_en_reset_config(dev, config, dev->features)) { + config->tx_type = HWTSTAMP_TX_OFF; + config->rx_filter = HWTSTAMP_FILTER_NONE; } - return copy_to_user(ifr->ifr_data, &config, - sizeof(config)) ? -EFAULT : 0; + return 0; } -static int mlx4_en_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +static int mlx4_en_hwtstamp_get(struct net_device *dev, + struct kernel_hwtstamp_config *config) { - switch (cmd) { - case SIOCSHWTSTAMP: - return mlx4_en_hwtstamp_ioctl(dev, ifr); - default: - return -EOPNOTSUPP; - } + struct mlx4_en_priv *priv = netdev_priv(dev); + + *config = priv->hwtstamp_config; + return 0; +} + +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); - if (!is_valid_ether_addr(mac)) - return -EINVAL; + return mlx4_set_vf_mac(mdev->dev, en_priv->port, queue, mac); +} + +static int mlx4_en_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos, + __be16 vlan_proto) +{ + struct mlx4_en_priv *en_priv = netdev_priv(dev); + struct mlx4_en_dev *mdev = en_priv->mdev; - return mlx4_set_vf_mac(mdev->dev, en_priv->port, queue, mac_u64); + return mlx4_set_vf_vlan(mdev->dev, en_priv->port, vf, vlan, qos, + vlan_proto); } -static int mlx4_en_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 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_vlan(mdev->dev, en_priv->port, vf, vlan, qos); + 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) @@ -2118,31 +2609,245 @@ static int mlx4_en_set_vf_link_state(struct net_device *dev, int vf, int link_st 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; +} + +static int mlx4_udp_tunnel_sync(struct net_device *dev, unsigned int table) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + struct udp_tunnel_info ti; + int ret; + + udp_tunnel_nic_get_port(dev, table, 0, &ti); + priv->vxlan_port = ti.port; + + ret = mlx4_config_vxlan_port(priv->mdev->dev, priv->vxlan_port); + if (ret) + return ret; + + return mlx4_SET_PORT_VXLAN(priv->mdev->dev, priv->port, + VXLAN_STEER_BY_OUTER_MAC, + !!priv->vxlan_port); +} + +static const struct udp_tunnel_nic_info mlx4_udp_tunnels = { + .sync_table = mlx4_udp_tunnel_sync, + .flags = UDP_TUNNEL_NIC_INFO_IPV4_ONLY, + .tables = { + { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, }, + }, +}; + +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); + features = vxlan_features_check(skb, features); + + /* The ConnectX-3 doesn't support outer IPv6 checksums but it does + * support inner IPv6 checksums and segmentation so we need to + * strip that feature if this is an IPv6 encapsulated frame. + */ + if (skb->encapsulation && + (skb->ip_summed == CHECKSUM_PARTIAL)) { + struct mlx4_en_priv *priv = netdev_priv(dev); + + if (!priv->vxlan_port || + (ip_hdr(skb)->version != 4) || + (udp_hdr(skb)->dest != priv->vxlan_port)) + features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); + } + + return features; +} + +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[TX][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 int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + struct mlx4_en_dev *mdev = priv->mdev; + struct mlx4_en_port_profile new_prof; + struct bpf_prog *old_prog; + struct mlx4_en_priv *tmp; + int tx_changed = 0; + int xdp_ring_num; + int port_up = 0; + int err; + int i; + + xdp_ring_num = prog ? priv->rx_ring_num : 0; + + /* No need to reconfigure buffers when simply swapping the + * program for a new one. + */ + if (priv->tx_ring_num[TX_XDP] == xdp_ring_num) { + if (prog) + bpf_prog_add(prog, priv->rx_ring_num - 1); + + mutex_lock(&mdev->state_lock); + for (i = 0; i < priv->rx_ring_num; i++) { + old_prog = rcu_dereference_protected( + priv->rx_ring[i]->xdp_prog, + lockdep_is_held(&mdev->state_lock)); + rcu_assign_pointer(priv->rx_ring[i]->xdp_prog, prog); + if (old_prog) + bpf_prog_put(old_prog); + } + mutex_unlock(&mdev->state_lock); + return 0; + } + + if (!mlx4_en_check_xdp_mtu(dev, dev->mtu)) + return -EOPNOTSUPP; + + tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return -ENOMEM; + + if (prog) + bpf_prog_add(prog, priv->rx_ring_num - 1); + + mutex_lock(&mdev->state_lock); + memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile)); + new_prof.tx_ring_num[TX_XDP] = xdp_ring_num; + + if (priv->tx_ring_num[TX] + xdp_ring_num > MAX_TX_RINGS) { + tx_changed = 1; + new_prof.tx_ring_num[TX] = + MAX_TX_RINGS - ALIGN(xdp_ring_num, priv->prof->num_up); + en_warn(priv, "Reducing the number of TX rings, to not exceed the max total rings number.\n"); + } + + err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, false); + if (err) { + if (prog) + bpf_prog_sub(prog, priv->rx_ring_num - 1); + goto unlock_out; + } + + if (priv->port_up) { + port_up = 1; + mlx4_en_stop_port(dev, 1); + } + + mlx4_en_safe_replace_resources(priv, tmp); + if (tx_changed) + netif_set_real_num_tx_queues(dev, priv->tx_ring_num[TX]); + + for (i = 0; i < priv->rx_ring_num; i++) { + old_prog = rcu_dereference_protected( + priv->rx_ring[i]->xdp_prog, + lockdep_is_held(&mdev->state_lock)); + rcu_assign_pointer(priv->rx_ring[i]->xdp_prog, prog); + if (old_prog) + bpf_prog_put(old_prog); + } + + if (port_up) { + err = mlx4_en_start_port(dev); + if (err) { + en_err(priv, "Failed starting port %d for XDP change\n", + priv->port); + if (!test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state)) + queue_work(mdev->workqueue, &priv->restart_task); + } + } + +unlock_out: + mutex_unlock(&mdev->state_lock); + kfree(tmp); + return err; +} + +static int mlx4_xdp(struct net_device *dev, struct netdev_bpf *xdp) +{ + switch (xdp->command) { + case XDP_SETUP_PROG: + return mlx4_xdp_set(dev, xdp->prog); + default: + return -EINVAL; + } +} + static const struct net_device_ops mlx4_netdev_ops = { .ndo_open = mlx4_en_open, .ndo_stop = mlx4_en_close, .ndo_start_xmit = mlx4_en_xmit, .ndo_select_queue = mlx4_en_select_queue, - .ndo_get_stats = mlx4_en_get_stats, + .ndo_get_stats64 = mlx4_en_get_stats64, .ndo_set_rx_mode = mlx4_en_set_rx_mode, .ndo_set_mac_address = mlx4_en_set_mac, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = mlx4_en_change_mtu, - .ndo_do_ioctl = mlx4_en_ioctl, .ndo_tx_timeout = mlx4_en_tx_timeout, .ndo_vlan_rx_add_vid = mlx4_en_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = mlx4_en_vlan_rx_kill_vid, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = mlx4_en_netpoll, -#endif .ndo_set_features = mlx4_en_set_features, - .ndo_setup_tc = mlx4_en_setup_tc, + .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_LL_RX_POLL - .ndo_busy_poll = mlx4_en_low_latency_recv, -#endif + .ndo_get_phys_port_id = mlx4_en_get_phys_port_id, + .ndo_features_check = mlx4_en_features_check, + .ndo_set_tx_maxrate = mlx4_en_set_tx_maxrate, + .ndo_bpf = mlx4_xdp, + .ndo_hwtstamp_get = mlx4_en_hwtstamp_get, + .ndo_hwtstamp_set = mlx4_en_hwtstamp_set, }; static const struct net_device_ops mlx4_netdev_ops_master = { @@ -2150,7 +2855,7 @@ static const struct net_device_ops mlx4_netdev_ops_master = { .ndo_stop = mlx4_en_close, .ndo_start_xmit = mlx4_en_xmit, .ndo_select_queue = mlx4_en_select_queue, - .ndo_get_stats = mlx4_en_get_stats, + .ndo_get_stats64 = mlx4_en_get_stats64, .ndo_set_rx_mode = mlx4_en_set_rx_mode, .ndo_set_mac_address = mlx4_en_set_mac, .ndo_validate_addr = eth_validate_addr, @@ -2160,17 +2865,300 @@ static const struct net_device_ops mlx4_netdev_ops_master = { .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_setup_tc = mlx4_en_setup_tc, + .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, + .ndo_features_check = mlx4_en_features_check, + .ndo_set_tx_maxrate = mlx4_en_set_tx_maxrate, + .ndo_bpf = mlx4_xdp, +}; + +static const struct xdp_metadata_ops mlx4_xdp_metadata_ops = { + .xmo_rx_timestamp = mlx4_en_xdp_rx_timestamp, + .xmo_rx_hash = mlx4_en_xdp_rx_hash, +}; + +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; + 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, netdev_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; + + 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_queue_bond_work(dev, 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); + last_i += NUM_PKT_STATS; + + bitmap_set(stats_bitmap->bitmap, last_i, NUM_XDP_STATS); + last_i += NUM_XDP_STATS; + + if (!mlx4_is_slave(dev)) + bitmap_set(stats_bitmap->bitmap, last_i, NUM_PHY_STATS); + last_i += NUM_PHY_STATS; +} + +static void mlx4_get_queue_stats_rx(struct net_device *dev, int i, + struct netdev_queue_stats_rx *stats) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + const struct mlx4_en_rx_ring *ring; + + spin_lock_bh(&priv->stats_lock); + + if (!priv->port_up || mlx4_is_master(priv->mdev->dev)) + goto out_unlock; + + ring = priv->rx_ring[i]; + stats->packets = READ_ONCE(ring->packets); + stats->bytes = READ_ONCE(ring->bytes); + stats->alloc_fail = READ_ONCE(ring->alloc_fail); + +out_unlock: + spin_unlock_bh(&priv->stats_lock); +} + +static void mlx4_get_queue_stats_tx(struct net_device *dev, int i, + struct netdev_queue_stats_tx *stats) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + const struct mlx4_en_tx_ring *ring; + + spin_lock_bh(&priv->stats_lock); + + if (!priv->port_up || mlx4_is_master(priv->mdev->dev)) + goto out_unlock; + + ring = priv->tx_ring[TX][i]; + stats->packets = READ_ONCE(ring->packets); + stats->bytes = READ_ONCE(ring->bytes); + +out_unlock: + spin_unlock_bh(&priv->stats_lock); +} + +static void mlx4_get_base_stats(struct net_device *dev, + struct netdev_queue_stats_rx *rx, + struct netdev_queue_stats_tx *tx) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + + spin_lock_bh(&priv->stats_lock); + + if (!priv->port_up || mlx4_is_master(priv->mdev->dev)) + goto out_unlock; + + if (priv->rx_ring_num) { + rx->packets = 0; + rx->bytes = 0; + rx->alloc_fail = 0; + } + + if (priv->tx_ring_num[TX]) { + tx->packets = 0; + tx->bytes = 0; + } + +out_unlock: + spin_unlock_bh(&priv->stats_lock); +} + +static const struct netdev_stat_ops mlx4_stat_ops = { + .get_queue_stats_rx = mlx4_get_queue_stats_rx, + .get_queue_stats_tx = mlx4_get_queue_stats_tx, + .get_base_stats = mlx4_get_base_stats, }; int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, @@ -2178,20 +3166,19 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, { struct net_device *dev; struct mlx4_en_priv *priv; - int i; + int i, t; int err; - u64 mac_u64; dev = alloc_etherdev_mqs(sizeof(struct mlx4_en_priv), MAX_TX_RINGS, MAX_RX_RINGS); if (dev == NULL) return -ENOMEM; - netif_set_real_num_tx_queues(dev, prof->tx_ring_num); + netif_set_real_num_tx_queues(dev, prof->tx_ring_num[TX]); 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 @@ -2199,6 +3186,18 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, 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->restart_task, mlx4_en_restart); + INIT_WORK(&priv->linkstate_task, mlx4_en_linkstate_work); + INIT_DELAYED_WORK(&priv->stats_task, mlx4_en_do_get_stats); + INIT_DELAYED_WORK(&priv->service_task, mlx4_en_service_task); +#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; @@ -2206,36 +3205,56 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, 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->num_tx_rings_p_up = mdev->profile.max_num_tx_rings_p_up; + 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, - GFP_KERNEL); - if (!priv->tx_ring) { - err = -ENOMEM; - goto out; - } - priv->tx_cq = kzalloc(sizeof(struct mlx4_en_cq) * MAX_TX_RINGS, - GFP_KERNEL); - if (!priv->tx_cq) { - err = -ENOMEM; - goto out; + for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) { + priv->tx_ring_num[t] = prof->tx_ring_num[t]; + if (!priv->tx_ring_num[t]) + continue; + + priv->tx_ring[t] = kcalloc(MAX_TX_RINGS, + sizeof(struct mlx4_en_tx_ring *), + GFP_KERNEL); + if (!priv->tx_ring[t]) { + err = -ENOMEM; + goto out; + } + priv->tx_cq[t] = kcalloc(MAX_TX_RINGS, + sizeof(struct mlx4_en_cq *), + GFP_KERNEL); + if (!priv->tx_cq[t]) { + err = -ENOMEM; + goto out; + } } 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) { + u8 prio; + + for (prio = 0; prio < IEEE_8021QAZ_MAX_TCS; ++prio) { + priv->ets.prio_tc[prio] = prio; + priv->ets.tc_tsa[prio] = IEEE_8021QAZ_TSA_VENDOR; + } + + priv->dcbx_cap = DCB_CAP_DCBX_VER_CEE | DCB_CAP_DCBX_HOST | + DCB_CAP_DCBX_VER_IEEE; + priv->flags |= MLX4_EN_DCB_ENABLED; + priv->cee_config.pfc_state = false; + + for (i = 0; i < MLX4_EN_NUM_UP_HIGH; i++) + priv->cee_config.dcb_pfc[i] = pfc_disabled; + + 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"); @@ -2250,24 +3269,28 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, /* 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]); + mlx4_en_u64_to_mac(dev, 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, quitting\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); @@ -2275,11 +3298,6 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, 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; @@ -2287,7 +3305,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, /* Allocate page for receive rings */ err = mlx4_alloc_hwq_res(mdev->dev, &priv->res, - MLX4_EN_PAGE_SIZE, MLX4_EN_PAGE_SIZE); + MLX4_EN_PAGE_SIZE); if (err) { en_err(priv, "Failed to allocate page for rx qps\n"); goto out; @@ -2301,11 +3319,13 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, dev->netdev_ops = &mlx4_netdev_ops_master; else dev->netdev_ops = &mlx4_netdev_ops; + dev->xdp_metadata_ops = &mlx4_xdp_metadata_ops; dev->watchdog_timeo = MLX4_EN_WATCHDOG_TIMEOUT; - netif_set_real_num_tx_queues(dev, priv->tx_ring_num); + netif_set_real_num_tx_queues(dev, priv->tx_ring_num[TX]); netif_set_real_num_rx_queues(dev, priv->rx_ring_num); - SET_ETHTOOL_OPS(dev, &mlx4_en_ethtool_ops); + dev->stat_ops = &mlx4_stat_ops; + dev->ethtool_ops = &mlx4_en_ethtool_ops; /* * Set driver features @@ -2314,34 +3334,109 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, if (mdev->LSO_support) dev->hw_features |= NETIF_F_TSO | NETIF_F_TSO6; + if (mdev->dev->caps.tunnel_offload_mode == + MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) { + dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM | + NETIF_F_GSO_PARTIAL; + dev->features |= NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM | + NETIF_F_GSO_PARTIAL; + dev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM; + dev->hw_enc_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | + NETIF_F_RXCSUM | + NETIF_F_TSO | NETIF_F_TSO6 | + NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM | + NETIF_F_GSO_PARTIAL; + + dev->udp_tunnel_nic_info = &mlx4_udp_tunnels; + } + dev->vlan_features = dev->hw_features; dev->hw_features |= NETIF_F_RXCSUM | NETIF_F_RXHASH; 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)) { + bool vlan_offload_disabled; + 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; + } + err = mlx4_get_is_vlan_offload_disabled(mdev->dev, port, + &vlan_offload_disabled); + if (!err && vlan_offload_disabled) { + dev->hw_features &= ~(NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_STAG_TX | + NETIF_F_HW_VLAN_STAG_RX); + dev->features &= ~(NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_STAG_TX | + NETIF_F_HW_VLAN_STAG_RX); + } + } 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; + } + + dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT; + + /* MTU range: 68 - hw-specific max */ + dev->min_mtu = ETH_MIN_MTU; + dev->max_mtu = priv->max_mtu; + + /* supports LSOv2 packets. */ + netif_set_tso_max_size(dev, GSO_MAX_SIZE); + mdev->pndev[port] = dev; + mdev->upper[port] = NULL; netif_carrier_off(dev); mlx4_en_set_default_moderation(priv); - err = register_netdev(dev); - if (err) { - en_err(priv, "Netdev registration failed for port %d\n", port); - goto out; - } - priv->registered = 1; - - en_warn(priv, "Using %d TX rings\n", prof->tx_ring_num); + en_warn(priv, "Using %d TX rings\n", prof->tx_ring_num[TX]); en_warn(priv, "Using %d RX rings\n", prof->rx_ring_num); mlx4_en_update_loopback_state(priv->dev, priv->dev->features); @@ -2353,11 +3448,20 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, 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); @@ -2367,9 +3471,28 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, } 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); + + SET_NETDEV_DEVLINK_PORT(dev, + mlx4_get_devlink_port(mdev->dev, priv->port)); + err = register_netdev(dev); + if (err) { + en_err(priv, "Netdev registration failed for port %d\n", port); + goto out; + } + + priv->registered = 1; return 0; @@ -2378,3 +3501,94 @@ out: return err; } +int mlx4_en_reset_config(struct net_device *dev, + struct kernel_hwtstamp_config *ts_config, + netdev_features_t features) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + struct mlx4_en_dev *mdev = priv->mdev; + struct mlx4_en_port_profile new_prof; + struct mlx4_en_priv *tmp; + 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; + } + + tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return -ENOMEM; + + mutex_lock(&mdev->state_lock); + + memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile)); + memcpy(&new_prof.hwtstamp_config, ts_config, sizeof(*ts_config)); + + err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, true); + if (err) + goto out; + + if (priv->port_up) { + port_up = 1; + mlx4_en_stop_port(dev, 1); + } + + mlx4_en_safe_replace_resources(priv, tmp); + + 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; + } + + if (port_up) { + err = mlx4_en_start_port(dev); + if (err) + en_err(priv, "Failed starting port\n"); + } + + if (!err) + err = mlx4_en_moderation_update(priv); +out: + mutex_unlock(&mdev->state_lock); + kfree(tmp); + if (!err) + netdev_features_change(dev); + return err; +} |