diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox')
67 files changed, 2635 insertions, 933 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 8d751383530b..94ead263081f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -3009,7 +3009,7 @@ int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u8 *mac) return -EPERM; } - s_info->mac = mlx4_mac_to_u64(mac); + s_info->mac = ether_addr_to_u64(mac); mlx4_info(dev, "default mac on vf %d port %d to %llX will take effect only after vf restart\n", vf, port, s_info->mac); return 0; @@ -3195,7 +3195,7 @@ int mlx4_set_vf_spoofchk(struct mlx4_dev *dev, int port, int vf, bool setting) port = mlx4_slaves_closest_port(dev, slave, port); s_info = &priv->mfunc.master.vf_admin[slave].vport[port]; - mlx4_u64_to_mac(mac, s_info->mac); + u64_to_ether_addr(s_info->mac, mac); if (setting && !is_valid_ether_addr(mac)) { mlx4_info(dev, "Illegal MAC with spoofchk\n"); return -EPERM; diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c index f7053a74e6a8..4d4f9cf9facb 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/cq.c @@ -314,7 +314,8 @@ static int mlx4_init_user_cqes(void *buf, int entries, int cqe_size) buf += PAGE_SIZE; } } else { - err = copy_to_user((void __user *)buf, init_ents, entries * cqe_size) ? + err = copy_to_user((void __user *)buf, init_ents, + array_size(entries, cqe_size)) ? -EFAULT : 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index ef518b1040f7..66c8ae29bc7a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -197,6 +197,8 @@ static const char main_strings[][ETH_GSTRING_LEN] = { /* xdp statistics */ "rx_xdp_drop", + "rx_xdp_redirect", + "rx_xdp_redirect_fail", "rx_xdp_tx", "rx_xdp_tx_full", @@ -428,6 +430,8 @@ static void mlx4_en_get_ethtool_stats(struct net_device *dev, data[index++] = priv->rx_ring[i]->bytes; data[index++] = priv->rx_ring[i]->dropped; data[index++] = priv->rx_ring[i]->xdp_drop; + data[index++] = priv->rx_ring[i]->xdp_redirect; + data[index++] = priv->rx_ring[i]->xdp_redirect_fail; data[index++] = priv->rx_ring[i]->xdp_tx; data[index++] = priv->rx_ring[i]->xdp_tx_full; } @@ -520,6 +524,10 @@ static void mlx4_en_get_strings(struct net_device *dev, sprintf(data + (index++) * ETH_GSTRING_LEN, "rx%d_xdp_drop", i); sprintf(data + (index++) * ETH_GSTRING_LEN, + "rx%d_xdp_redirect", i); + sprintf(data + (index++) * ETH_GSTRING_LEN, + "rx%d_xdp_redirect_fail", i); + sprintf(data + (index++) * ETH_GSTRING_LEN, "rx%d_xdp_tx", i); sprintf(data + (index++) * ETH_GSTRING_LEN, "rx%d_xdp_tx_full", i); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 8af7f2827322..3f6d5c384637 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -527,18 +527,17 @@ static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev, 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; - } - memset(&dst_mac[ETH_ALEN], 0, 2); + 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, unsigned char *addr, +static int mlx4_en_tunnel_steer_add(struct mlx4_en_priv *priv, + const unsigned char *addr, int qpn, u64 *reg_id) { int err; @@ -559,7 +558,7 @@ static int mlx4_en_tunnel_steer_add(struct mlx4_en_priv *priv, unsigned char *ad 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; @@ -611,7 +610,8 @@ 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; @@ -644,7 +644,7 @@ static int mlx4_en_get_qp(struct mlx4_en_priv *priv) int index = 0; int err = 0; int *qpn = &priv->base_qpn; - u64 mac = mlx4_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); @@ -683,7 +683,7 @@ static void mlx4_en_put_qp(struct mlx4_en_priv *priv) int qpn = priv->base_qpn; if (dev->caps.steering_mode == MLX4_STEERING_MODE_A0) { - u64 mac = mlx4_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); @@ -701,14 +701,14 @@ 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_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_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) { @@ -797,7 +797,7 @@ static int mlx4_en_set_mac(struct net_device *dev, void *addr) if (err) goto out; - memcpy(dev->dev_addr, saddr->sa_data, ETH_ALEN); + eth_hw_addr_set(dev, saddr->sa_data); mlx4_en_update_user_mac(priv, new_mac); out: mutex_unlock(&mdev->state_lock); @@ -1076,7 +1076,7 @@ static void mlx4_en_do_multicast(struct mlx4_en_priv *priv, mlx4_en_cache_mclist(dev); netif_addr_unlock_bh(dev); list_for_each_entry(mclist, &priv->mc_list, list) { - mcast_addr = mlx4_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); } @@ -1169,7 +1169,7 @@ static void mlx4_en_do_uc_filter(struct mlx4_en_priv *priv, found = true; if (!found) { - mac = mlx4_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); @@ -1212,7 +1212,7 @@ static void mlx4_en_do_uc_filter(struct mlx4_en_priv *priv, priv->flags |= MLX4_EN_FLAG_FORCE_PROMISC; break; } - mac = mlx4_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) { @@ -1348,7 +1348,7 @@ static void mlx4_en_delete_rss_steer_rules(struct mlx4_en_priv *priv) for (i = 0; i < MLX4_EN_MAC_HASH_SIZE; ++i) { bucket = &priv->mac_hash[i]; hlist_for_each_entry_safe(entry, tmp, bucket, hlist) { - mac = mlx4_mac_to_u64(entry->mac); + 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, @@ -3267,7 +3267,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, /* 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)) { en_err(priv, "Port: %d, invalid mac burned: %pM, quitting\n", priv->port, dev->dev_addr); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c index 0158b88bea5b..532997eba698 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_port.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c @@ -244,6 +244,8 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) priv->port_stats.rx_chksum_complete = 0; priv->port_stats.rx_alloc_pages = 0; priv->xdp_stats.rx_xdp_drop = 0; + priv->xdp_stats.rx_xdp_redirect = 0; + priv->xdp_stats.rx_xdp_redirect_fail = 0; priv->xdp_stats.rx_xdp_tx = 0; priv->xdp_stats.rx_xdp_tx_full = 0; for (i = 0; i < priv->rx_ring_num; i++) { @@ -255,6 +257,8 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) priv->port_stats.rx_chksum_complete += READ_ONCE(ring->csum_complete); priv->port_stats.rx_alloc_pages += READ_ONCE(ring->rx_alloc_pages); priv->xdp_stats.rx_xdp_drop += READ_ONCE(ring->xdp_drop); + priv->xdp_stats.rx_xdp_redirect += READ_ONCE(ring->xdp_redirect); + priv->xdp_stats.rx_xdp_redirect_fail += READ_ONCE(ring->xdp_redirect_fail); priv->xdp_stats.rx_xdp_tx += READ_ONCE(ring->xdp_tx); priv->xdp_stats.rx_xdp_tx_full += READ_ONCE(ring->xdp_tx_full); } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 7f6d3b82c29b..650e6a1844ae 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -669,6 +669,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud struct bpf_prog *xdp_prog; int cq_ring = cq->ring; bool doorbell_pending; + bool xdp_redir_flush; struct mlx4_cqe *cqe; struct xdp_buff xdp; int polled = 0; @@ -682,6 +683,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud xdp_prog = rcu_dereference_bh(ring->xdp_prog); xdp_init_buff(&xdp, priv->frag_info[0].frag_stride, &ring->xdp_rxq); doorbell_pending = false; + xdp_redir_flush = false; /* We assume a 1:1 mapping between CQEs and Rx descriptors, so Rx * descriptor offset can be deduced from the CQE index instead of @@ -790,6 +792,16 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud switch (act) { case XDP_PASS: break; + case XDP_REDIRECT: + if (likely(!xdp_do_redirect(dev, &xdp, xdp_prog))) { + ring->xdp_redirect++; + xdp_redir_flush = true; + frags[0].page = NULL; + goto next; + } + ring->xdp_redirect_fail++; + trace_xdp_exception(dev, xdp_prog, act); + goto xdp_drop_no_cnt; case XDP_TX: if (likely(!mlx4_en_xmit_frame(ring, frags, priv, length, cq_ring, @@ -897,6 +909,9 @@ next: break; } + if (xdp_redir_flush) + xdp_do_flush(); + if (likely(polled)) { if (doorbell_pending) { priv->tx_cq[TX_XDP][cq_ring]->xdp_busy = true; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index c56b9dba4c71..817f4154b86d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -130,6 +130,7 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv, ring->bf_enabled = !!(priv->pflags & MLX4_EN_PRIV_FLAGS_BLUEFLAME); } + ring->doorbell_address = ring->bf.uar->map + MLX4_SEND_DOORBELL; ring->hwtstamp_tx_type = priv->hwtstamp_config.tx_type; ring->queue_index = queue_index; @@ -753,8 +754,7 @@ void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring) #else iowrite32be( #endif - (__force u32)ring->doorbell_qpn, - ring->bf.uar->map + MLX4_SEND_DOORBELL); + (__force u32)ring->doorbell_qpn, ring->doorbell_address); } static void mlx4_en_tx_write_desc(struct mlx4_en_tx_ring *ring, diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index dc4ac1a2b6b6..42c96c9d7fb1 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -3105,7 +3105,7 @@ void mlx4_replace_zero_macs(struct mlx4_dev *dev) dev->caps.port_type[i] == MLX4_PORT_TYPE_ETH) { eth_random_addr(mac_addr); dev->port_random_macs |= 1 << i; - dev->caps.def_mac[i] = mlx4_mac_to_u64(mac_addr); + dev->caps.def_mac[i] = ether_addr_to_u64(mac_addr); } } EXPORT_SYMBOL_GPL(mlx4_replace_zero_macs); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 5a6b0fcaf7f8..9541f3a920c8 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -4015,9 +4015,6 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) mutex_init(&dev->persist->interface_state_mutex); mutex_init(&dev->persist->pci_status_mutex); - ret = devlink_register(devlink); - if (ret) - goto err_persist_free; ret = devlink_params_register(devlink, mlx4_devlink_params, ARRAY_SIZE(mlx4_devlink_params)); if (ret) @@ -4027,17 +4024,15 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) if (ret) goto err_params_unregister; - devlink_params_publish(devlink); - devlink_reload_enable(devlink); pci_save_state(pdev); + devlink_register(devlink); + devlink_reload_enable(devlink); return 0; err_params_unregister: devlink_params_unregister(devlink, mlx4_devlink_params, ARRAY_SIZE(mlx4_devlink_params)); err_devlink_unregister: - devlink_unregister(devlink); -err_persist_free: kfree(dev->persist); err_devlink_free: devlink_free(devlink); @@ -4141,6 +4136,7 @@ static void mlx4_remove_one(struct pci_dev *pdev) int active_vfs = 0; devlink_reload_disable(devlink); + devlink_unregister(devlink); if (mlx4_is_slave(dev)) persist->interface_state |= MLX4_INTERFACE_STATE_NOWAIT; @@ -4176,7 +4172,6 @@ static void mlx4_remove_one(struct pci_dev *pdev) mlx4_pci_disable_device(dev); devlink_params_unregister(devlink, mlx4_devlink_params, ARRAY_SIZE(mlx4_devlink_params)); - devlink_unregister(devlink); kfree(dev->persist); devlink_free(devlink); } diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c index f1b4ad9c66d2..f1716a83a4d3 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c @@ -1046,7 +1046,7 @@ int mlx4_flow_detach(struct mlx4_dev *dev, u64 reg_id) } EXPORT_SYMBOL_GPL(mlx4_flow_detach); -int mlx4_tunnel_steer_add(struct mlx4_dev *dev, unsigned char *addr, +int mlx4_tunnel_steer_add(struct mlx4_dev *dev, const unsigned char *addr, int port, int qpn, u16 prio, u64 *reg_id) { int err; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 6bf558c5ec10..e132ff4c82f2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -283,6 +283,7 @@ struct mlx4_en_tx_ring { struct mlx4_bf bf; /* Following part should be mostly read */ + void __iomem *doorbell_address; __be32 doorbell_qpn; __be32 mr_key; u32 size; /* number of TXBBs */ @@ -340,6 +341,8 @@ struct mlx4_en_rx_ring { unsigned long csum_complete; unsigned long rx_alloc_pages; unsigned long xdp_drop; + unsigned long xdp_redirect; + unsigned long xdp_redirect_fail; unsigned long xdp_tx; unsigned long xdp_tx_full; unsigned long dropped; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h index 7b51ae8cf759..e9cd4bb6f83d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h @@ -42,9 +42,11 @@ struct mlx4_en_port_stats { struct mlx4_en_xdp_stats { unsigned long rx_xdp_drop; + unsigned long rx_xdp_redirect; + unsigned long rx_xdp_redirect_fail; unsigned long rx_xdp_tx; unsigned long rx_xdp_tx_full; -#define NUM_XDP_STATS 3 +#define NUM_XDP_STATS 5 }; struct mlx4_en_phy_stats { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index db5dfff585c9..4dc3a822907a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -2058,7 +2058,7 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev) return -EINVAL; } - cmd->stats = kvzalloc(MLX5_CMD_OP_MAX * sizeof(*cmd->stats), GFP_KERNEL); + cmd->stats = kvcalloc(MLX5_CMD_OP_MAX, sizeof(*cmd->stats), GFP_KERNEL); if (!cmd->stats) return -ENOMEM; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index dcf9f27ba2ef..b9a6cea03951 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -136,6 +136,7 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change, struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_priv(devlink); + struct pci_dev *pdev = dev->pdev; bool sf_dev_allocated; sf_dev_allocated = mlx5_sf_dev_allocated(dev); @@ -153,6 +154,10 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change, return -EOPNOTSUPP; } + if (pci_num_vf(pdev)) { + NL_SET_ERR_MSG_MOD(extack, "reload while VFs are present is unfavorable"); + } + switch (action) { case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: mlx5_unload_one(dev); @@ -625,7 +630,6 @@ static int mlx5_devlink_eth_param_register(struct devlink *devlink) devlink_param_driverinit_value_set(devlink, DEVLINK_PARAM_GENERIC_ID_ENABLE_ETH, value); - devlink_param_publish(devlink, &enable_eth_param); return 0; } @@ -636,7 +640,6 @@ static void mlx5_devlink_eth_param_unregister(struct devlink *devlink) if (!mlx5_eth_supported(dev)) return; - devlink_param_unpublish(devlink, &enable_eth_param); devlink_param_unregister(devlink, &enable_eth_param); } @@ -672,7 +675,6 @@ static int mlx5_devlink_rdma_param_register(struct devlink *devlink) devlink_param_driverinit_value_set(devlink, DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA, value); - devlink_param_publish(devlink, &enable_rdma_param); return 0; } @@ -681,7 +683,6 @@ static void mlx5_devlink_rdma_param_unregister(struct devlink *devlink) if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND)) return; - devlink_param_unpublish(devlink, &enable_rdma_param); devlink_param_unregister(devlink, &enable_rdma_param); } @@ -706,7 +707,6 @@ static int mlx5_devlink_vnet_param_register(struct devlink *devlink) devlink_param_driverinit_value_set(devlink, DEVLINK_PARAM_GENERIC_ID_ENABLE_VNET, value); - devlink_param_publish(devlink, &enable_rdma_param); return 0; } @@ -717,7 +717,6 @@ static void mlx5_devlink_vnet_param_unregister(struct devlink *devlink) if (!mlx5_vnet_supported(dev)) return; - devlink_param_unpublish(devlink, &enable_vnet_param); devlink_param_unregister(devlink, &enable_vnet_param); } @@ -799,16 +798,12 @@ int mlx5_devlink_register(struct devlink *devlink) { int err; - err = devlink_register(devlink); - if (err) - return err; - err = devlink_params_register(devlink, mlx5_devlink_params, ARRAY_SIZE(mlx5_devlink_params)); if (err) - goto params_reg_err; + return err; + mlx5_devlink_set_params_init_values(devlink); - devlink_params_publish(devlink); err = mlx5_devlink_auxdev_params_register(devlink); if (err) @@ -825,8 +820,6 @@ traps_reg_err: auxdev_reg_err: devlink_params_unregister(devlink, mlx5_devlink_params, ARRAY_SIZE(mlx5_devlink_params)); -params_reg_err: - devlink_unregister(devlink); return err; } @@ -834,8 +827,6 @@ void mlx5_devlink_unregister(struct devlink *devlink) { mlx5_devlink_traps_unregister(devlink); mlx5_devlink_auxdev_params_unregister(devlink); - devlink_params_unpublish(devlink); devlink_params_unregister(devlink, mlx5_devlink_params, ARRAY_SIZE(mlx5_devlink_params)); - devlink_unregister(devlink); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 03a7a4ce5cd5..a3a4fece0cac 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -220,8 +220,6 @@ struct mlx5e_umr_wqe { struct mlx5_mtt inline_mtts[0]; }; -extern const char mlx5e_self_tests[][ETH_GSTRING_LEN]; - enum mlx5e_priv_flag { MLX5E_PFLAG_RX_CQE_BASED_MODER, MLX5E_PFLAG_TX_CQE_BASED_MODER, @@ -253,6 +251,9 @@ struct mlx5e_params { u16 mode; u8 num_tc; struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE]; + struct { + struct mlx5e_mqprio_rl *rl; + } channel; } mqprio; bool rx_cqe_compress_def; bool tunneled_offload_en; @@ -879,6 +880,7 @@ struct mlx5e_priv { #endif struct mlx5e_scratchpad scratchpad; struct mlx5e_htb htb; + struct mlx5e_mqprio_rl *mqprio_rl; }; struct mlx5e_rx_handlers { @@ -918,6 +920,7 @@ void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s) void mlx5e_init_l2_addr(struct mlx5e_priv *priv); int mlx5e_self_test_num(struct mlx5e_priv *priv); +int mlx5e_self_test_fill_strings(struct mlx5e_priv *priv, u8 *data); void mlx5e_self_test(struct net_device *ndev, struct ethtool_test *etest, u64 *buf); void mlx5e_set_rx_mode_work(struct work_struct *work); @@ -1003,7 +1006,8 @@ int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn, struct mlx5e_modify_sq_param *p); int mlx5e_open_txqsq(struct mlx5e_channel *c, u32 tisn, int txq_ix, struct mlx5e_params *params, struct mlx5e_sq_param *param, - struct mlx5e_txqsq *sq, int tc, u16 qos_queue_group_id, u16 qos_qid); + struct mlx5e_txqsq *sq, int tc, u16 qos_queue_group_id, + struct mlx5e_sq_stats *sq_stats); void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq); void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq); void mlx5e_free_txqsq(struct mlx5e_txqsq *sq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c index e8a8d78e3e4d..50977f01a050 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c @@ -7,6 +7,21 @@ #define BYTES_IN_MBIT 125000 +int mlx5e_qos_bytes_rate_check(struct mlx5_core_dev *mdev, u64 nbytes) +{ + if (nbytes < BYTES_IN_MBIT) { + qos_warn(mdev, "Input rate (%llu Bytes/sec) below minimum supported (%u Bytes/sec)\n", + nbytes, BYTES_IN_MBIT); + return -EINVAL; + } + return 0; +} + +static u32 mlx5e_qos_bytes2mbits(struct mlx5_core_dev *mdev, u64 nbytes) +{ + return div_u64(nbytes, BYTES_IN_MBIT); +} + int mlx5e_qos_max_leaf_nodes(struct mlx5_core_dev *mdev) { return min(MLX5E_QOS_MAX_LEAF_NODES, mlx5_qos_max_leaf_nodes(mdev)); @@ -238,7 +253,8 @@ static int mlx5e_open_qos_sq(struct mlx5e_priv *priv, struct mlx5e_channels *chs if (err) goto err_free_sq; err = mlx5e_open_txqsq(c, priv->tisn[c->lag_port][0], txq_ix, params, - ¶m_sq, sq, 0, node->hw_id, node->qid); + ¶m_sq, sq, 0, node->hw_id, + priv->htb.qos_sq_stats[node->qid]); if (err) goto err_close_cq; @@ -979,3 +995,87 @@ int mlx5e_htb_node_modify(struct mlx5e_priv *priv, u16 classid, u64 rate, u64 ce return err; } + +struct mlx5e_mqprio_rl { + struct mlx5_core_dev *mdev; + u32 root_id; + u32 *leaves_id; + u8 num_tc; +}; + +struct mlx5e_mqprio_rl *mlx5e_mqprio_rl_alloc(void) +{ + return kvzalloc(sizeof(struct mlx5e_mqprio_rl), GFP_KERNEL); +} + +void mlx5e_mqprio_rl_free(struct mlx5e_mqprio_rl *rl) +{ + kvfree(rl); +} + +int mlx5e_mqprio_rl_init(struct mlx5e_mqprio_rl *rl, struct mlx5_core_dev *mdev, u8 num_tc, + u64 max_rate[]) +{ + int err; + int tc; + + if (!mlx5_qos_is_supported(mdev)) { + qos_warn(mdev, "Missing QoS capabilities. Try disabling SRIOV or use a supported device."); + return -EOPNOTSUPP; + } + if (num_tc > mlx5e_qos_max_leaf_nodes(mdev)) + return -EINVAL; + + rl->mdev = mdev; + rl->num_tc = num_tc; + rl->leaves_id = kvcalloc(num_tc, sizeof(*rl->leaves_id), GFP_KERNEL); + if (!rl->leaves_id) + return -ENOMEM; + + err = mlx5_qos_create_root_node(mdev, &rl->root_id); + if (err) + goto err_free_leaves; + + qos_dbg(mdev, "Root created, id %#x\n", rl->root_id); + + for (tc = 0; tc < num_tc; tc++) { + u32 max_average_bw; + + max_average_bw = mlx5e_qos_bytes2mbits(mdev, max_rate[tc]); + err = mlx5_qos_create_leaf_node(mdev, rl->root_id, 0, max_average_bw, + &rl->leaves_id[tc]); + if (err) + goto err_destroy_leaves; + + qos_dbg(mdev, "Leaf[%d] created, id %#x, max average bw %u Mbits/sec\n", + tc, rl->leaves_id[tc], max_average_bw); + } + return 0; + +err_destroy_leaves: + while (--tc >= 0) + mlx5_qos_destroy_node(mdev, rl->leaves_id[tc]); + mlx5_qos_destroy_node(mdev, rl->root_id); +err_free_leaves: + kvfree(rl->leaves_id); + return err; +} + +void mlx5e_mqprio_rl_cleanup(struct mlx5e_mqprio_rl *rl) +{ + int tc; + + for (tc = 0; tc < rl->num_tc; tc++) + mlx5_qos_destroy_node(rl->mdev, rl->leaves_id[tc]); + mlx5_qos_destroy_node(rl->mdev, rl->root_id); + kvfree(rl->leaves_id); +} + +int mlx5e_mqprio_rl_get_node_hw_id(struct mlx5e_mqprio_rl *rl, int tc, u32 *hw_id) +{ + if (tc >= rl->num_tc) + return -EINVAL; + + *hw_id = rl->leaves_id[tc]; + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.h b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.h index 757682b7c0e0..b7558907ba20 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.h @@ -12,6 +12,7 @@ struct mlx5e_priv; struct mlx5e_channels; struct mlx5e_channel; +int mlx5e_qos_bytes_rate_check(struct mlx5_core_dev *mdev, u64 nbytes); int mlx5e_qos_max_leaf_nodes(struct mlx5_core_dev *mdev); int mlx5e_qos_cur_leaf_nodes(struct mlx5e_priv *priv); @@ -41,4 +42,12 @@ int mlx5e_htb_leaf_del_last(struct mlx5e_priv *priv, u16 classid, bool force, int mlx5e_htb_node_modify(struct mlx5e_priv *priv, u16 classid, u64 rate, u64 ceil, struct netlink_ext_ack *extack); +/* MQPRIO TX rate limit */ +struct mlx5e_mqprio_rl; +struct mlx5e_mqprio_rl *mlx5e_mqprio_rl_alloc(void); +void mlx5e_mqprio_rl_free(struct mlx5e_mqprio_rl *rl); +int mlx5e_mqprio_rl_init(struct mlx5e_mqprio_rl *rl, struct mlx5_core_dev *mdev, u8 num_tc, + u64 max_rate[]); +void mlx5e_mqprio_rl_cleanup(struct mlx5e_mqprio_rl *rl); +int mlx5e_mqprio_rl_get_node_hw_id(struct mlx5e_mqprio_rl *rl, int tc, u32 *hw_id); #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index de03684528bb..398c6761eeb3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -3,6 +3,7 @@ #include <net/dst_metadata.h> #include <linux/netdevice.h> +#include <linux/if_macvlan.h> #include <linux/list.h> #include <linux/rculist.h> #include <linux/rtnetlink.h> @@ -409,6 +410,13 @@ static void mlx5e_rep_indr_block_unbind(void *cb_priv) static LIST_HEAD(mlx5e_block_cb_list); +static bool mlx5e_rep_macvlan_mode_supported(const struct net_device *dev) +{ + struct macvlan_dev *macvlan = netdev_priv(dev); + + return macvlan->mode == MACVLAN_MODE_PASSTHRU; +} + static int mlx5e_rep_indr_setup_block(struct net_device *netdev, struct Qdisc *sch, struct mlx5e_rep_priv *rpriv, @@ -422,8 +430,14 @@ mlx5e_rep_indr_setup_block(struct net_device *netdev, struct Qdisc *sch, struct flow_block_cb *block_cb; if (!mlx5e_tc_tun_device_to_offload(priv, netdev) && - !(is_vlan_dev(netdev) && vlan_dev_real_dev(netdev) == rpriv->netdev)) - return -EOPNOTSUPP; + !(is_vlan_dev(netdev) && vlan_dev_real_dev(netdev) == rpriv->netdev)) { + if (!(netif_is_macvlan(netdev) && macvlan_dev_real_dev(netdev) == rpriv->netdev)) + return -EOPNOTSUPP; + if (!mlx5e_rep_macvlan_mode_supported(netdev)) { + netdev_warn(netdev, "Offloading ingress filter is supported only with macvlan passthru mode"); + return -EOPNOTSUPP; + } + } if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) return -EOPNOTSUPP; @@ -647,9 +661,7 @@ static void mlx5e_restore_skb_sample(struct mlx5e_priv *priv, struct sk_buff *sk "Failed to restore tunnel info for sampled packet\n"); return; } -#if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) mlx5e_tc_sample_skb(skb, mapped_obj); -#endif /* CONFIG_MLX5_TC_SAMPLE */ mlx5_rep_tc_post_napi_receive(tc_priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c index 625cd49ef96c..b8b481b335cf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c @@ -391,7 +391,7 @@ int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss, return 0; } -static void mlx5e_rss_apply(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns) +static int mlx5e_rss_apply(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns) { int err; @@ -399,6 +399,7 @@ static void mlx5e_rss_apply(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_r if (err) mlx5e_rss_warn(rss->mdev, "Failed to redirect RQT %#x to channels: err = %d\n", mlx5e_rqt_get_rqtn(&rss->rqt), err); + return err; } void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns) @@ -490,6 +491,14 @@ int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir, { bool changed_indir = false; bool changed_hash = false; + struct mlx5e_rss *old_rss; + int err = 0; + + old_rss = mlx5e_rss_alloc(); + if (!old_rss) + return -ENOMEM; + + *old_rss = *rss; if (hfunc && *hfunc != rss->hash.hfunc) { switch (*hfunc) { @@ -497,7 +506,8 @@ int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir, case ETH_RSS_HASH_TOP: break; default: - return -EINVAL; + err = -EINVAL; + goto out; } changed_hash = true; changed_indir = true; @@ -520,13 +530,20 @@ int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir, rss->indir.table[i] = indir[i]; } - if (changed_indir && rss->enabled) - mlx5e_rss_apply(rss, rqns, num_rqns); + if (changed_indir && rss->enabled) { + err = mlx5e_rss_apply(rss, rqns, num_rqns); + if (err) { + *rss = *old_rss; + goto out; + } + } if (changed_hash) mlx5e_rss_update_tirs(rss); - return 0; +out: + mlx5e_rss_free(old_rss); + return err; } struct mlx5e_rss_params_hash mlx5e_rss_get_hash(struct mlx5e_rss *rss) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c index 6552ecee3f9b..d1d7e4b9f7ad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c @@ -602,7 +602,7 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, } sample_flow->pre_attr = pre_attr; - return sample_flow->post_rule; + return sample_flow->pre_rule; err_pre_offload_rule: kfree(pre_attr); @@ -613,7 +613,7 @@ err_sample_restore: err_obj_id: sampler_put(tc_psample, sample_flow->sampler); err_sampler: - if (!post_act_handle) + if (sample_flow->post_rule) del_post_rule(esw, sample_flow, attr); err_post_rule: if (post_act_handle) @@ -628,9 +628,7 @@ mlx5e_tc_sample_unoffload(struct mlx5e_tc_psample *tc_psample, struct mlx5_flow_handle *rule, struct mlx5_flow_attr *attr) { - struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; struct mlx5e_sample_flow *sample_flow; - struct mlx5_vport_tbl_attr tbl_attr; struct mlx5_eswitch *esw; if (IS_ERR_OR_NULL(tc_psample)) @@ -650,23 +648,14 @@ mlx5e_tc_sample_unoffload(struct mlx5e_tc_psample *tc_psample, */ sample_flow = attr->sample_attr->sample_flow; mlx5_eswitch_del_offloaded_rule(esw, sample_flow->pre_rule, sample_flow->pre_attr); - if (!sample_flow->post_act_handle) - mlx5_eswitch_del_offloaded_rule(esw, sample_flow->post_rule, - sample_flow->post_attr); sample_restore_put(tc_psample, sample_flow->restore); mapping_remove(esw->offloads.reg_c0_obj_pool, attr->sample_attr->restore_obj_id); sampler_put(tc_psample, sample_flow->sampler); - if (sample_flow->post_act_handle) { + if (sample_flow->post_act_handle) mlx5e_tc_post_act_del(tc_psample->post_act, sample_flow->post_act_handle); - } else { - tbl_attr.chain = attr->chain; - tbl_attr.prio = attr->prio; - tbl_attr.vport = esw_attr->in_rep->vport; - tbl_attr.vport_ns = &mlx5_esw_vport_tbl_sample_ns; - mlx5_esw_vporttbl_put(esw, &tbl_attr); - kfree(sample_flow->post_attr); - } + else + del_post_rule(esw, sample_flow, attr); kfree(sample_flow->pre_attr); kfree(sample_flow); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.h index db0146df9b30..9ef8a49d7801 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.h @@ -19,6 +19,8 @@ struct mlx5e_sample_attr { struct mlx5e_sample_flow *sample_flow; }; +#if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) + void mlx5e_tc_sample_skb(struct sk_buff *skb, struct mlx5_mapped_obj *mapped_obj); struct mlx5_flow_handle * @@ -38,4 +40,29 @@ mlx5e_tc_sample_init(struct mlx5_eswitch *esw, struct mlx5e_post_act *post_act); void mlx5e_tc_sample_cleanup(struct mlx5e_tc_psample *tc_psample); +#else /* CONFIG_MLX5_TC_SAMPLE */ + +static inline struct mlx5_flow_handle * +mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, + struct mlx5_flow_spec *spec, + struct mlx5_flow_attr *attr, + u32 tunnel_id) +{ return ERR_PTR(-EOPNOTSUPP); } + +static inline void +mlx5e_tc_sample_unoffload(struct mlx5e_tc_psample *tc_psample, + struct mlx5_flow_handle *rule, + struct mlx5_flow_attr *attr) {} + +static inline struct mlx5e_tc_psample * +mlx5e_tc_sample_init(struct mlx5_eswitch *esw, struct mlx5e_post_act *post_act) +{ return ERR_PTR(-EOPNOTSUPP); } + +static inline void +mlx5e_tc_sample_cleanup(struct mlx5e_tc_psample *tc_psample) {} + +static inline void +mlx5e_tc_sample_skb(struct sk_buff *skb, struct mlx5_mapped_obj *mapped_obj) {} + +#endif /* CONFIG_MLX5_TC_SAMPLE */ #endif /* __MLX5_EN_TC_SAMPLE_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index 6c949abcd2e1..225748a9e52a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -2127,12 +2127,20 @@ mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains, ct_priv->post_act = post_act; mutex_init(&ct_priv->control_lock); - rhashtable_init(&ct_priv->zone_ht, &zone_params); - rhashtable_init(&ct_priv->ct_tuples_ht, &tuples_ht_params); - rhashtable_init(&ct_priv->ct_tuples_nat_ht, &tuples_nat_ht_params); + if (rhashtable_init(&ct_priv->zone_ht, &zone_params)) + goto err_ct_zone_ht; + if (rhashtable_init(&ct_priv->ct_tuples_ht, &tuples_ht_params)) + goto err_ct_tuples_ht; + if (rhashtable_init(&ct_priv->ct_tuples_nat_ht, &tuples_nat_ht_params)) + goto err_ct_tuples_nat_ht; return ct_priv; +err_ct_tuples_nat_ht: + rhashtable_destroy(&ct_priv->ct_tuples_ht); +err_ct_tuples_ht: + rhashtable_destroy(&ct_priv->zone_ht); +err_ct_zone_ht: err_ct_nat_tbl: mlx5_chains_destroy_global_table(chains, ct_priv->ct); err_ct_tbl: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index b4e986818794..cc7d7b895b80 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -118,6 +118,11 @@ static int mlx5e_route_lookup_ipv4_get(struct mlx5e_priv *priv, uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH); attr->fl.fl4.flowi4_oif = uplink_dev->ifindex; + } else { + struct mlx5e_tc_tunnel *tunnel = mlx5e_get_tc_tun(mirred_dev); + + if (tunnel && tunnel->get_remote_ifindex) + attr->fl.fl4.flowi4_oif = tunnel->get_remote_ifindex(mirred_dev); } rt = ip_route_output_key(dev_net(mirred_dev), &attr->fl.fl4); @@ -435,12 +440,15 @@ static int mlx5e_route_lookup_ipv6_get(struct mlx5e_priv *priv, struct net_device *mirred_dev, struct mlx5e_tc_tun_route_attr *attr) { + struct mlx5e_tc_tunnel *tunnel = mlx5e_get_tc_tun(mirred_dev); struct net_device *route_dev; struct net_device *out_dev; struct dst_entry *dst; struct neighbour *n; int ret; + if (tunnel && tunnel->get_remote_ifindex) + attr->fl.fl6.flowi6_oif = tunnel->get_remote_ifindex(mirred_dev); dst = ipv6_stub->ipv6_dst_lookup_flow(dev_net(mirred_dev), NULL, &attr->fl.fl6, NULL); if (IS_ERR(dst)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h index 9350ca05ce65..aa092eaeaec3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h @@ -51,6 +51,7 @@ struct mlx5e_tc_tunnel { void *headers_v); bool (*encap_info_equal)(struct mlx5e_encap_key *a, struct mlx5e_encap_key *b); + int (*get_remote_ifindex)(struct net_device *mirred_dev); }; extern struct mlx5e_tc_tunnel vxlan_tunnel; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c index 4267f3a1059e..fd07c4cbfd1d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c @@ -141,6 +141,14 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv, return 0; } +static int mlx5e_tc_tun_get_remote_ifindex(struct net_device *mirred_dev) +{ + const struct vxlan_dev *vxlan = netdev_priv(mirred_dev); + const struct vxlan_rdst *dst = &vxlan->default_dst; + + return dst->remote_ifindex; +} + struct mlx5e_tc_tunnel vxlan_tunnel = { .tunnel_type = MLX5E_TC_TUNNEL_TYPE_VXLAN, .match_level = MLX5_MATCH_L4, @@ -151,4 +159,5 @@ struct mlx5e_tc_tunnel vxlan_tunnel = { .parse_udp_ports = mlx5e_tc_tun_parse_udp_ports_vxlan, .parse_tunnel = mlx5e_tc_tun_parse_vxlan, .encap_info_equal = mlx5e_tc_tun_encap_info_equal_generic, + .get_remote_ifindex = mlx5e_tc_tun_get_remote_ifindex, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 9d451b8ee467..7a97e0e21fd7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -267,9 +267,7 @@ void mlx5e_ethtool_get_strings(struct mlx5e_priv *priv, u32 stringset, u8 *data) break; case ETH_SS_TEST: - for (i = 0; i < mlx5e_self_test_num(priv); i++) - strcpy(data + i * ETH_GSTRING_LEN, - mlx5e_self_tests[i]); + mlx5e_self_test_fill_strings(priv, data); break; case ETH_SS_STATS: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 0c5197f9cea3..e81e5505207c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -930,9 +930,10 @@ static int mlx5e_alloc_xdpsq_fifo(struct mlx5e_xdpsq *sq, int numa) struct mlx5e_xdp_info_fifo *xdpi_fifo = &sq->db.xdpi_fifo; int wq_sz = mlx5_wq_cyc_get_size(&sq->wq); int dsegs_per_wq = wq_sz * MLX5_SEND_WQEBB_NUM_DS; + size_t size; - xdpi_fifo->xi = kvzalloc_node(sizeof(*xdpi_fifo->xi) * dsegs_per_wq, - GFP_KERNEL, numa); + size = array_size(sizeof(*xdpi_fifo->xi), dsegs_per_wq); + xdpi_fifo->xi = kvzalloc_node(size, GFP_KERNEL, numa); if (!xdpi_fifo->xi) return -ENOMEM; @@ -946,10 +947,11 @@ static int mlx5e_alloc_xdpsq_fifo(struct mlx5e_xdpsq *sq, int numa) static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa) { int wq_sz = mlx5_wq_cyc_get_size(&sq->wq); + size_t size; int err; - sq->db.wqe_info = kvzalloc_node(sizeof(*sq->db.wqe_info) * wq_sz, - GFP_KERNEL, numa); + size = array_size(sizeof(*sq->db.wqe_info), wq_sz); + sq->db.wqe_info = kvzalloc_node(size, GFP_KERNEL, numa); if (!sq->db.wqe_info) return -ENOMEM; @@ -1298,7 +1300,8 @@ static int mlx5e_set_sq_maxrate(struct net_device *dev, int mlx5e_open_txqsq(struct mlx5e_channel *c, u32 tisn, int txq_ix, struct mlx5e_params *params, struct mlx5e_sq_param *param, - struct mlx5e_txqsq *sq, int tc, u16 qos_queue_group_id, u16 qos_qid) + struct mlx5e_txqsq *sq, int tc, u16 qos_queue_group_id, + struct mlx5e_sq_stats *sq_stats) { struct mlx5e_create_sq_param csp = {}; u32 tx_rate; @@ -1308,10 +1311,7 @@ int mlx5e_open_txqsq(struct mlx5e_channel *c, u32 tisn, int txq_ix, if (err) return err; - if (qos_queue_group_id) - sq->stats = c->priv->htb.qos_sq_stats[qos_qid]; - else - sq->stats = &c->priv->channel_stats[c->ix].sq[tc]; + sq->stats = sq_stats; csp.tisn = tisn; csp.tis_lst_sz = 1; @@ -1705,6 +1705,36 @@ static void mlx5e_close_tx_cqs(struct mlx5e_channel *c) mlx5e_close_cq(&c->sq[tc].cq); } +static int mlx5e_mqprio_txq_to_tc(struct netdev_tc_txq *tc_to_txq, unsigned int txq) +{ + int tc; + + for (tc = 0; tc < TC_MAX_QUEUE; tc++) + if (txq - tc_to_txq[tc].offset < tc_to_txq[tc].count) + return tc; + + WARN(1, "Unexpected TCs configuration. No match found for txq %u", txq); + return -ENOENT; +} + +static int mlx5e_txq_get_qos_node_hw_id(struct mlx5e_params *params, int txq_ix, + u32 *hw_id) +{ + int tc; + + if (params->mqprio.mode != TC_MQPRIO_MODE_CHANNEL || + !params->mqprio.channel.rl) { + *hw_id = 0; + return 0; + } + + tc = mlx5e_mqprio_txq_to_tc(params->mqprio.tc_to_txq, txq_ix); + if (tc < 0) + return tc; + + return mlx5e_mqprio_rl_get_node_hw_id(params->mqprio.channel.rl, tc, hw_id); +} + static int mlx5e_open_sqs(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_channel_param *cparam) @@ -1713,9 +1743,16 @@ static int mlx5e_open_sqs(struct mlx5e_channel *c, for (tc = 0; tc < mlx5e_get_dcb_num_tc(params); tc++) { int txq_ix = c->ix + tc * params->num_channels; + u32 qos_queue_group_id; + + err = mlx5e_txq_get_qos_node_hw_id(params, txq_ix, &qos_queue_group_id); + if (err) + goto err_close_sqs; err = mlx5e_open_txqsq(c, c->priv->tisn[c->lag_port][tc], txq_ix, - params, &cparam->txq_sq, &c->sq[tc], tc, 0, 0); + params, &cparam->txq_sq, &c->sq[tc], tc, + qos_queue_group_id, + &c->priv->channel_stats[c->ix].sq[tc]); if (err) goto err_close_sqs; } @@ -2340,6 +2377,13 @@ static int mlx5e_update_netdev_queues(struct mlx5e_priv *priv) netdev_warn(netdev, "netif_set_real_num_rx_queues failed, %d\n", err); goto err_txqs; } + if (priv->mqprio_rl != priv->channels.params.mqprio.channel.rl) { + if (priv->mqprio_rl) { + mlx5e_mqprio_rl_cleanup(priv->mqprio_rl); + mlx5e_mqprio_rl_free(priv->mqprio_rl); + } + priv->mqprio_rl = priv->channels.params.mqprio.channel.rl; + } return 0; @@ -2901,15 +2945,18 @@ static void mlx5e_params_mqprio_dcb_set(struct mlx5e_params *params, u8 num_tc) { params->mqprio.mode = TC_MQPRIO_MODE_DCB; params->mqprio.num_tc = num_tc; + params->mqprio.channel.rl = NULL; mlx5e_mqprio_build_default_tc_to_txq(params->mqprio.tc_to_txq, num_tc, params->num_channels); } static void mlx5e_params_mqprio_channel_set(struct mlx5e_params *params, - struct tc_mqprio_qopt *qopt) + struct tc_mqprio_qopt *qopt, + struct mlx5e_mqprio_rl *rl) { params->mqprio.mode = TC_MQPRIO_MODE_CHANNEL; params->mqprio.num_tc = qopt->num_tc; + params->mqprio.channel.rl = rl; mlx5e_mqprio_build_tc_to_txq(params->mqprio.tc_to_txq, qopt); } @@ -2969,9 +3016,13 @@ static int mlx5e_mqprio_channel_validate(struct mlx5e_priv *priv, netdev_err(netdev, "Min tx rate is not supported\n"); return -EINVAL; } + if (mqprio->max_rate[i]) { - netdev_err(netdev, "Max tx rate is not supported\n"); - return -EINVAL; + int err; + + err = mlx5e_qos_bytes_rate_check(priv->mdev, mqprio->max_rate[i]); + if (err) + return err; } if (mqprio->qopt.offset[i] != agg_count) { @@ -2990,11 +3041,22 @@ static int mlx5e_mqprio_channel_validate(struct mlx5e_priv *priv, return 0; } +static bool mlx5e_mqprio_rate_limit(struct tc_mqprio_qopt_offload *mqprio) +{ + int tc; + + for (tc = 0; tc < mqprio->qopt.num_tc; tc++) + if (mqprio->max_rate[tc]) + return true; + return false; +} + static int mlx5e_setup_tc_mqprio_channel(struct mlx5e_priv *priv, struct tc_mqprio_qopt_offload *mqprio) { mlx5e_fp_preactivate preactivate; struct mlx5e_params new_params; + struct mlx5e_mqprio_rl *rl; bool nch_changed; int err; @@ -3002,13 +3064,32 @@ static int mlx5e_setup_tc_mqprio_channel(struct mlx5e_priv *priv, if (err) return err; + rl = NULL; + if (mlx5e_mqprio_rate_limit(mqprio)) { + rl = mlx5e_mqprio_rl_alloc(); + if (!rl) + return -ENOMEM; + err = mlx5e_mqprio_rl_init(rl, priv->mdev, mqprio->qopt.num_tc, + mqprio->max_rate); + if (err) { + mlx5e_mqprio_rl_free(rl); + return err; + } + } + new_params = priv->channels.params; - mlx5e_params_mqprio_channel_set(&new_params, &mqprio->qopt); + mlx5e_params_mqprio_channel_set(&new_params, &mqprio->qopt, rl); nch_changed = mlx5e_get_dcb_num_tc(&priv->channels.params) > 1; preactivate = nch_changed ? mlx5e_num_channels_changed_ctx : mlx5e_update_netdev_queues_ctx; - return mlx5e_safe_switch_params(priv, &new_params, preactivate, NULL, true); + err = mlx5e_safe_switch_params(priv, &new_params, preactivate, NULL, true); + if (err && rl) { + mlx5e_mqprio_rl_cleanup(rl); + mlx5e_mqprio_rl_free(rl); + } + + return err; } static int mlx5e_setup_tc_mqprio(struct mlx5e_priv *priv, @@ -3226,7 +3307,7 @@ static int mlx5e_set_mac(struct net_device *netdev, void *addr) return -EADDRNOTAVAIL; netif_addr_lock_bh(netdev); - ether_addr_copy(netdev->dev_addr, saddr->sa_data); + eth_hw_addr_set(netdev, saddr->sa_data); netif_addr_unlock_bh(netdev); mlx5e_nic_set_rx_mode(priv); @@ -4808,6 +4889,11 @@ void mlx5e_priv_cleanup(struct mlx5e_priv *priv) kfree(priv->htb.qos_sq_stats[i]); kvfree(priv->htb.qos_sq_stats); + if (priv->mqprio_rl) { + mlx5e_mqprio_rl_cleanup(priv->mqprio_rl); + mlx5e_mqprio_rl_free(priv->mqprio_rl); + } + memset(priv, 0, sizeof(*priv)); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c index ce8ab1f01876..8c9163d2c646 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c @@ -35,30 +35,7 @@ #include <net/udp.h> #include "en.h" #include "en/port.h" - -enum { - MLX5E_ST_LINK_STATE, - MLX5E_ST_LINK_SPEED, - MLX5E_ST_HEALTH_INFO, -#ifdef CONFIG_INET - MLX5E_ST_LOOPBACK, -#endif - MLX5E_ST_NUM, -}; - -const char mlx5e_self_tests[MLX5E_ST_NUM][ETH_GSTRING_LEN] = { - "Link Test", - "Speed Test", - "Health Test", -#ifdef CONFIG_INET - "Loopback Test", -#endif -}; - -int mlx5e_self_test_num(struct mlx5e_priv *priv) -{ - return ARRAY_SIZE(mlx5e_self_tests); -} +#include "eswitch.h" static int mlx5e_test_health_info(struct mlx5e_priv *priv) { @@ -265,6 +242,14 @@ static void mlx5e_test_loopback_cleanup(struct mlx5e_priv *priv, mlx5e_refresh_tirs(priv, false, false); } +static int mlx5e_cond_loopback(struct mlx5e_priv *priv) +{ + if (is_mdev_switchdev_mode(priv->mdev)) + return -EOPNOTSUPP; + + return 0; +} + #define MLX5E_LB_VERIFY_TIMEOUT (msecs_to_jiffies(200)) static int mlx5e_test_loopback(struct mlx5e_priv *priv) { @@ -313,37 +298,47 @@ out: } #endif -static int (*mlx5e_st_func[MLX5E_ST_NUM])(struct mlx5e_priv *) = { - mlx5e_test_link_state, - mlx5e_test_link_speed, - mlx5e_test_health_info, +typedef int (*mlx5e_st_func)(struct mlx5e_priv *); + +struct mlx5e_st { + char name[ETH_GSTRING_LEN]; + mlx5e_st_func st_func; + mlx5e_st_func cond_func; +}; + +static struct mlx5e_st mlx5e_sts[] = { + { "Link Test", mlx5e_test_link_state }, + { "Speed Test", mlx5e_test_link_speed }, + { "Health Test", mlx5e_test_health_info }, #ifdef CONFIG_INET - mlx5e_test_loopback, + { "Loopback Test", mlx5e_test_loopback, mlx5e_cond_loopback }, #endif }; +#define MLX5E_ST_NUM ARRAY_SIZE(mlx5e_sts) + void mlx5e_self_test(struct net_device *ndev, struct ethtool_test *etest, u64 *buf) { struct mlx5e_priv *priv = netdev_priv(ndev); - int i; - - memset(buf, 0, sizeof(u64) * MLX5E_ST_NUM); + int i, count = 0; mutex_lock(&priv->state_lock); netdev_info(ndev, "Self test begin..\n"); for (i = 0; i < MLX5E_ST_NUM; i++) { - netdev_info(ndev, "\t[%d] %s start..\n", - i, mlx5e_self_tests[i]); - buf[i] = mlx5e_st_func[i](priv); - netdev_info(ndev, "\t[%d] %s end: result(%lld)\n", - i, mlx5e_self_tests[i], buf[i]); + struct mlx5e_st st = mlx5e_sts[i]; + + if (st.cond_func && st.cond_func(priv)) + continue; + netdev_info(ndev, "\t[%d] %s start..\n", i, st.name); + buf[count] = st.st_func(priv); + netdev_info(ndev, "\t[%d] %s end: result(%lld)\n", i, st.name, buf[count]); } mutex_unlock(&priv->state_lock); - for (i = 0; i < MLX5E_ST_NUM; i++) { + for (i = 0; i < count; i++) { if (buf[i]) { etest->flags |= ETH_TEST_FL_FAILED; break; @@ -352,3 +347,24 @@ void mlx5e_self_test(struct net_device *ndev, struct ethtool_test *etest, netdev_info(ndev, "Self test out: status flags(0x%x)\n", etest->flags); } + +int mlx5e_self_test_fill_strings(struct mlx5e_priv *priv, u8 *data) +{ + int i, count = 0; + + for (i = 0; i < MLX5E_ST_NUM; i++) { + struct mlx5e_st st = mlx5e_sts[i]; + + if (st.cond_func && st.cond_func(priv)) + continue; + if (data) + strcpy(data + count * ETH_GSTRING_LEN, st.name); + count++; + } + return count; +} + +int mlx5e_self_test_num(struct mlx5e_priv *priv) +{ + return mlx5e_self_test_fill_strings(priv, NULL); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index ba8164792016..d92ee2f37c22 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -39,6 +39,7 @@ #include <linux/rhashtable.h> #include <linux/refcount.h> #include <linux/completion.h> +#include <linux/if_macvlan.h> #include <net/tc_act/tc_pedit.h> #include <net/tc_act/tc_csum.h> #include <net/psample.h> @@ -246,7 +247,6 @@ get_ct_priv(struct mlx5e_priv *priv) return priv->fs.tc.ct; } -#if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) static struct mlx5e_tc_psample * get_sample_priv(struct mlx5e_priv *priv) { @@ -263,7 +263,6 @@ get_sample_priv(struct mlx5e_priv *priv) return NULL; } -#endif struct mlx5_flow_handle * mlx5_tc_rule_insert(struct mlx5e_priv *priv, @@ -1146,11 +1145,9 @@ mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw, rule = mlx5_tc_ct_flow_offload(get_ct_priv(flow->priv), flow, spec, attr, mod_hdr_acts); -#if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) } else if (flow_flag_test(flow, SAMPLE)) { rule = mlx5e_tc_sample_offload(get_sample_priv(flow->priv), spec, attr, mlx5e_tc_get_flow_tun_id(flow)); -#endif } else { rule = mlx5_eswitch_add_offloaded_rule(esw, spec, attr); } @@ -1186,12 +1183,10 @@ void mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw, return; } -#if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) if (flow_flag_test(flow, SAMPLE)) { mlx5e_tc_sample_unoffload(get_sample_priv(flow->priv), flow->rule[0], attr); return; } -#endif if (attr->esw_attr->split_count) mlx5_eswitch_del_fwd_rule(esw, flow->rule[1], attr); @@ -1688,8 +1683,8 @@ enc_opts_is_dont_care_or_full_match(struct mlx5e_priv *priv, if (opt->opt_class != htons(U16_MAX) || opt->type != U8_MAX) { - NL_SET_ERR_MSG(extack, - "Partial match of tunnel options in chain > 0 isn't supported"); + NL_SET_ERR_MSG_MOD(extack, + "Partial match of tunnel options in chain > 0 isn't supported"); netdev_warn(priv->netdev, "Partial match of tunnel options in chain > 0 isn't supported"); return -EOPNOTSUPP; @@ -1905,8 +1900,8 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, if ((needs_mapping || sets_mapping) && !mlx5_eswitch_reg_c1_loopback_enabled(esw)) { - NL_SET_ERR_MSG(extack, - "Chains on tunnel devices isn't supported without register loopback support"); + NL_SET_ERR_MSG_MOD(extack, + "Chains on tunnel devices isn't supported without register loopback support"); netdev_warn(priv->netdev, "Chains on tunnel devices isn't supported without register loopback support"); return -EOPNOTSUPP; @@ -2910,8 +2905,7 @@ out_err: } static int -parse_pedit_to_reformat(struct mlx5e_priv *priv, - const struct flow_action_entry *act, +parse_pedit_to_reformat(const struct flow_action_entry *act, struct mlx5e_tc_flow_parse_attr *parse_attr, struct netlink_ext_ack *extack) { @@ -2943,7 +2937,7 @@ static int parse_tc_pedit_action(struct mlx5e_priv *priv, struct netlink_ext_ack *extack) { if (flow && flow_flag_test(flow, L3_TO_L2_DECAP)) - return parse_pedit_to_reformat(priv, act, parse_attr, extack); + return parse_pedit_to_reformat(act, parse_attr, extack); return parse_pedit_to_modify_hdr(priv, act, namespace, parse_attr, hdrs, extack); @@ -3025,10 +3019,10 @@ struct ipv6_hoplimit_word { __u8 hop_limit; }; -static int is_action_keys_supported(const struct flow_action_entry *act, - bool ct_flow, bool *modify_ip_header, - bool *modify_tuple, - struct netlink_ext_ack *extack) +static bool +is_action_keys_supported(const struct flow_action_entry *act, bool ct_flow, + bool *modify_ip_header, bool *modify_tuple, + struct netlink_ext_ack *extack) { u32 mask, offset; u8 htype; @@ -3056,7 +3050,7 @@ static int is_action_keys_supported(const struct flow_action_entry *act, if (ct_flow && *modify_tuple) { NL_SET_ERR_MSG_MOD(extack, "can't offload re-write of ipv4 address with action ct"); - return -EOPNOTSUPP; + return false; } } else if (htype == FLOW_ACT_MANGLE_HDR_TYPE_IP6) { struct ipv6_hoplimit_word *hoplimit_word = @@ -3074,7 +3068,7 @@ static int is_action_keys_supported(const struct flow_action_entry *act, if (ct_flow && *modify_tuple) { NL_SET_ERR_MSG_MOD(extack, "can't offload re-write of ipv6 address with action ct"); - return -EOPNOTSUPP; + return false; } } else if (htype == FLOW_ACT_MANGLE_HDR_TYPE_TCP || htype == FLOW_ACT_MANGLE_HDR_TYPE_UDP) { @@ -3082,11 +3076,11 @@ static int is_action_keys_supported(const struct flow_action_entry *act, if (ct_flow) { NL_SET_ERR_MSG_MOD(extack, "can't offload re-write of transport header ports with action ct"); - return -EOPNOTSUPP; + return false; } } - return 0; + return true; } static bool modify_tuple_supported(bool modify_tuple, bool ct_clear, @@ -3133,7 +3127,7 @@ static bool modify_header_match_supported(struct mlx5e_priv *priv, void *headers_v; u16 ethertype; u8 ip_proto; - int i, err; + int i; headers_c = get_match_headers_criteria(actions, spec); headers_v = get_match_headers_value(actions, spec); @@ -3151,11 +3145,10 @@ static bool modify_header_match_supported(struct mlx5e_priv *priv, act->id != FLOW_ACTION_ADD) continue; - err = is_action_keys_supported(act, ct_flow, - &modify_ip_header, - &modify_tuple, extack); - if (err) - return err; + if (!is_action_keys_supported(act, ct_flow, + &modify_ip_header, + &modify_tuple, extack)) + return false; } if (!modify_tuple_supported(modify_tuple, ct_clear, ct_flow, extack, @@ -3176,37 +3169,65 @@ out_ok: return true; } -static bool actions_match_supported(struct mlx5e_priv *priv, - struct flow_action *flow_action, - struct mlx5e_tc_flow_parse_attr *parse_attr, - struct mlx5e_tc_flow *flow, - struct netlink_ext_ack *extack) +static bool +actions_match_supported_fdb(struct mlx5e_priv *priv, + struct mlx5e_tc_flow_parse_attr *parse_attr, + struct mlx5e_tc_flow *flow, + struct netlink_ext_ack *extack) { - bool ct_flow = false, ct_clear = false; - u32 actions; + struct mlx5_esw_flow_attr *esw_attr = flow->attr->esw_attr; + bool ct_flow, ct_clear; - ct_clear = flow->attr->ct_attr.ct_action & - TCA_CT_ACT_CLEAR; + ct_clear = flow->attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR; ct_flow = flow_flag_test(flow, CT) && !ct_clear; - actions = flow->attr->action; - if (mlx5e_is_eswitch_flow(flow)) { - if (flow->attr->esw_attr->split_count && ct_flow && - !MLX5_CAP_GEN(flow->attr->esw_attr->in_mdev, reg_c_preserve)) { - /* All registers used by ct are cleared when using - * split rules. - */ - NL_SET_ERR_MSG_MOD(extack, - "Can't offload mirroring with action ct"); - return false; - } + if (esw_attr->split_count && ct_flow && + !MLX5_CAP_GEN(esw_attr->in_mdev, reg_c_preserve)) { + /* All registers used by ct are cleared when using + * split rules. + */ + NL_SET_ERR_MSG_MOD(extack, "Can't offload mirroring with action ct"); + return false; } - if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) - return modify_header_match_supported(priv, &parse_attr->spec, - flow_action, actions, - ct_flow, ct_clear, - extack); + if (esw_attr->split_count > 0 && !mlx5_esw_has_fwd_fdb(priv->mdev)) { + NL_SET_ERR_MSG_MOD(extack, + "current firmware doesn't support split rule for port mirroring"); + netdev_warn_once(priv->netdev, + "current firmware doesn't support split rule for port mirroring\n"); + return false; + } + + return true; +} + +static bool +actions_match_supported(struct mlx5e_priv *priv, + struct flow_action *flow_action, + struct mlx5e_tc_flow_parse_attr *parse_attr, + struct mlx5e_tc_flow *flow, + struct netlink_ext_ack *extack) +{ + u32 actions = flow->attr->action; + bool ct_flow, ct_clear; + + ct_clear = flow->attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR; + ct_flow = flow_flag_test(flow, CT) && !ct_clear; + + if (!(actions & + (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) { + NL_SET_ERR_MSG_MOD(extack, "Rule must have at least one forward/drop action"); + return false; + } + + if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR && + !modify_header_match_supported(priv, &parse_attr->spec, flow_action, + actions, ct_flow, ct_clear, extack)) + return false; + + if (mlx5e_is_eswitch_flow(flow) && + !actions_match_supported_fdb(priv, parse_attr, flow, extack)) + return false; return true; } @@ -3355,11 +3376,51 @@ static int validate_goto_chain(struct mlx5e_priv *priv, return 0; } -static int parse_tc_nic_actions(struct mlx5e_priv *priv, - struct flow_action *flow_action, +static int +actions_prepare_mod_hdr_actions(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, + struct pedit_headers_action *hdrs, struct netlink_ext_ack *extack) { + struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr; + enum mlx5_flow_namespace_type ns_type; + int err; + + if (!hdrs[TCA_PEDIT_KEY_EX_CMD_SET].pedits && + !hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits) + return 0; + + ns_type = get_flow_name_space(flow); + + err = alloc_tc_pedit_action(priv, ns_type, parse_attr, hdrs, + &attr->action, extack); + if (err) + return err; + + /* In case all pedit actions are skipped, remove the MOD_HDR flag. */ + if (parse_attr->mod_hdr_acts.num_actions > 0) + return 0; + + attr->action &= ~MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; + dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts); + + if (ns_type != MLX5_FLOW_NAMESPACE_FDB) + return 0; + + if (!((attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) || + (attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH))) + attr->esw_attr->split_count = 0; + + return 0; +} + +static int +parse_tc_nic_actions(struct mlx5e_priv *priv, + struct flow_action *flow_action, + struct mlx5e_tc_flow *flow, + struct netlink_ext_ack *extack) +{ struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; struct pedit_headers_action hdrs[2] = {}; @@ -3451,7 +3512,8 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, if (err) return err; - action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; + action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_COUNT; attr->dest_chain = act->chain_index; break; case FLOW_ACTION_CT: @@ -3467,33 +3529,16 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, } } - if (hdrs[TCA_PEDIT_KEY_EX_CMD_SET].pedits || - hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits) { - err = alloc_tc_pedit_action(priv, MLX5_FLOW_NAMESPACE_KERNEL, - parse_attr, hdrs, &action, extack); - if (err) - return err; - /* in case all pedit actions are skipped, remove the MOD_HDR - * flag. - */ - if (parse_attr->mod_hdr_acts.num_actions == 0) { - action &= ~MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; - dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts); - } - } - attr->action = action; - if (attr->dest_chain) { - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) { - NL_SET_ERR_MSG(extack, "Mirroring goto chain rules isn't supported"); - return -EOPNOTSUPP; - } - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + if (attr->dest_chain && parse_attr->mirred_ifindex[0]) { + NL_SET_ERR_MSG(extack, "Mirroring goto chain rules isn't supported"); + return -EOPNOTSUPP; } - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + err = actions_prepare_mod_hdr_actions(priv, flow, attr, hdrs, extack); + if (err) + return err; if (!actions_match_supported(priv, flow_action, parse_attr, flow, extack)) return -EOPNOTSUPP; @@ -3765,6 +3810,11 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, flow_action_for_each(i, act, flow_action) { switch (act->id) { + case FLOW_ACTION_ACCEPT: + action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_COUNT; + attr->flags |= MLX5_ESW_ATTR_FLAG_ACCEPT; + break; case FLOW_ACTION_DROP: action |= MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; @@ -3914,6 +3964,9 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, return err; } + if (netif_is_macvlan(out_dev)) + out_dev = macvlan_dev_real_dev(out_dev); + err = verify_uplink_forwarding(priv, flow, out_dev, extack); if (err) return err; @@ -3998,7 +4051,8 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, if (err) return err; - action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; + action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_COUNT; attr->dest_chain = act->chain_index; break; case FLOW_ACTION_CT: @@ -4045,60 +4099,26 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, return err; } - if (hdrs[TCA_PEDIT_KEY_EX_CMD_SET].pedits || - hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits) { - err = alloc_tc_pedit_action(priv, MLX5_FLOW_NAMESPACE_FDB, - parse_attr, hdrs, &action, extack); - if (err) - return err; - /* in case all pedit actions are skipped, remove the MOD_HDR - * flag. we might have set split_count either by pedit or - * pop/push. if there is no pop/push either, reset it too. - */ - if (parse_attr->mod_hdr_acts.num_actions == 0) { - action &= ~MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; - dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts); - if (!((action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) || - (action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH))) - esw_attr->split_count = 0; - } - } - attr->action = action; - if (!actions_match_supported(priv, flow_action, parse_attr, flow, extack)) - return -EOPNOTSUPP; - - if (attr->dest_chain) { - if (decap) { - /* It can be supported if we'll create a mapping for - * the tunnel device only (without tunnel), and set - * this tunnel id with this decap flow. - * - * On restore (miss), we'll just set this saved tunnel - * device. - */ - - NL_SET_ERR_MSG(extack, - "Decap with goto isn't supported"); - netdev_warn(priv->netdev, - "Decap with goto isn't supported"); - return -EOPNOTSUPP; - } - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - } + err = actions_prepare_mod_hdr_actions(priv, flow, attr, hdrs, extack); + if (err) + return err; - if (!(attr->action & - (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) { - NL_SET_ERR_MSG_MOD(extack, - "Rule must have at least one forward/drop action"); + if (!actions_match_supported(priv, flow_action, parse_attr, flow, extack)) return -EOPNOTSUPP; - } - if (esw_attr->split_count > 0 && !mlx5_esw_has_fwd_fdb(priv->mdev)) { - NL_SET_ERR_MSG_MOD(extack, - "current firmware doesn't support split rule for port mirroring"); - netdev_warn_once(priv->netdev, "current firmware doesn't support split rule for port mirroring\n"); + if (attr->dest_chain && decap) { + /* It can be supported if we'll create a mapping for + * the tunnel device only (without tunnel), and set + * this tunnel id with this decap flow. + * + * On restore (miss), we'll just set this saved tunnel + * device. + */ + + NL_SET_ERR_MSG(extack, "Decap with goto isn't supported"); + netdev_warn(priv->netdev, "Decap with goto isn't supported"); return -EOPNOTSUPP; } @@ -5006,9 +5026,7 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht) MLX5_FLOW_NAMESPACE_FDB, uplink_priv->post_act); -#if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) uplink_priv->tc_psample = mlx5e_tc_sample_init(esw, uplink_priv->post_act); -#endif mapping_id = mlx5_query_nic_system_image_guid(esw->dev); @@ -5022,9 +5040,11 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht) } uplink_priv->tunnel_mapping = mapping; - /* 0xFFF is reserved for stack devices slow path table mark */ + /* Two last values are reserved for stack devices slow path table mark + * and bridge ingress push mark. + */ mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_TUNNEL_ENC_OPTS, - sz_enc_opts, ENC_OPTS_BITS_MASK - 1, true); + sz_enc_opts, ENC_OPTS_BITS_MASK - 2, true); if (IS_ERR(mapping)) { err = PTR_ERR(mapping); goto err_enc_opts_mapping; @@ -5052,9 +5072,7 @@ err_ht_init: err_enc_opts_mapping: mapping_destroy(uplink_priv->tunnel_mapping); err_tun_mapping: -#if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) mlx5e_tc_sample_cleanup(uplink_priv->tc_psample); -#endif mlx5_tc_ct_clean(uplink_priv->ct_priv); netdev_warn(priv->netdev, "Failed to initialize tc (eswitch), err: %d", err); @@ -5074,9 +5092,7 @@ void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht) mapping_destroy(uplink_priv->tunnel_enc_opts_mapping); mapping_destroy(uplink_priv->tunnel_mapping); -#if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) mlx5e_tc_sample_cleanup(uplink_priv->tc_psample); -#endif mlx5_tc_ct_clean(uplink_priv->ct_priv); mlx5e_tc_post_act_destroy(uplink_priv->post_act); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 605c8ecc3610..792e0d6aa861 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -632,6 +632,7 @@ static int create_async_eqs(struct mlx5_core_dev *dev) mlx5_eq_notifier_register(dev, &table->cq_err_nb); param = (struct mlx5_eq_param) { + .irq_index = MLX5_IRQ_EQ_CTRL, .nent = MLX5_NUM_CMD_EQE, .mask[0] = 1ull << MLX5_EVENT_TYPE_CMD, }; @@ -644,6 +645,7 @@ static int create_async_eqs(struct mlx5_core_dev *dev) mlx5_cmd_allowed_opcode(dev, CMD_ALLOWED_OPCODE_ALL); param = (struct mlx5_eq_param) { + .irq_index = MLX5_IRQ_EQ_CTRL, .nent = MLX5_NUM_ASYNC_EQE, }; @@ -653,6 +655,7 @@ static int create_async_eqs(struct mlx5_core_dev *dev) goto err2; param = (struct mlx5_eq_param) { + .irq_index = MLX5_IRQ_EQ_CTRL, .nent = /* TODO: sriov max_vf + */ 1, .mask[0] = 1ull << MLX5_EVENT_TYPE_PAGE_REQUEST, }; @@ -806,8 +809,8 @@ static int create_comp_eqs(struct mlx5_core_dev *dev) ncomp_eqs = table->num_comp_eqs; nent = MLX5_COMP_EQ_SIZE; for (i = 0; i < ncomp_eqs; i++) { - int vecidx = i + MLX5_IRQ_VEC_COMP_BASE; struct mlx5_eq_param param = {}; + int vecidx = i; eq = kzalloc(sizeof(*eq), GFP_KERNEL); if (!eq) { @@ -953,9 +956,7 @@ static int set_rmap(struct mlx5_core_dev *mdev) goto err_out; } - vecidx = MLX5_IRQ_VEC_COMP_BASE; - for (; vecidx < eq_table->num_comp_eqs + MLX5_IRQ_VEC_COMP_BASE; - vecidx++) { + for (vecidx = 0; vecidx < eq_table->num_comp_eqs; vecidx++) { err = irq_cpu_rmap_add(eq_table->rmap, pci_irq_vector(mdev->pdev, vecidx)); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index 7e221038df8d..ed72246d1d83 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -28,7 +28,10 @@ #define MLX5_ESW_BRIDGE_EGRESS_TABLE_VLAN_GRP_IDX_TO (MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE / 2 - 1) #define MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_FROM \ (MLX5_ESW_BRIDGE_EGRESS_TABLE_VLAN_GRP_IDX_TO + 1) -#define MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_TO (MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE - 1) +#define MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_TO (MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE - 2) +#define MLX5_ESW_BRIDGE_EGRESS_TABLE_MISS_GRP_IDX_FROM \ + (MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_TO + 1) +#define MLX5_ESW_BRIDGE_EGRESS_TABLE_MISS_GRP_IDX_TO (MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE - 1) #define MLX5_ESW_BRIDGE_SKIP_TABLE_SIZE 0 @@ -61,6 +64,9 @@ struct mlx5_esw_bridge { struct mlx5_flow_table *egress_ft; struct mlx5_flow_group *egress_vlan_fg; struct mlx5_flow_group *egress_mac_fg; + struct mlx5_flow_group *egress_miss_fg; + struct mlx5_pkt_reformat *egress_miss_pkt_reformat; + struct mlx5_flow_handle *egress_miss_handle; unsigned long ageing_time; u32 flags; }; @@ -86,6 +92,26 @@ mlx5_esw_bridge_fdb_del_notify(struct mlx5_esw_bridge_fdb_entry *entry) SWITCHDEV_FDB_DEL_TO_BRIDGE); } +static bool mlx5_esw_bridge_pkt_reformat_vlan_pop_supported(struct mlx5_eswitch *esw) +{ + return BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat_remove)) && + MLX5_CAP_GEN_2(esw->dev, max_reformat_remove_size) >= sizeof(struct vlan_hdr) && + MLX5_CAP_GEN_2(esw->dev, max_reformat_remove_offset) >= + offsetof(struct vlan_ethhdr, h_vlan_proto); +} + +static struct mlx5_pkt_reformat * +mlx5_esw_bridge_pkt_reformat_vlan_pop_create(struct mlx5_eswitch *esw) +{ + struct mlx5_pkt_reformat_params reformat_params = {}; + + reformat_params.type = MLX5_REFORMAT_TYPE_REMOVE_HDR; + reformat_params.param_0 = MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START; + reformat_params.param_1 = offsetof(struct vlan_ethhdr, h_vlan_proto); + reformat_params.size = sizeof(struct vlan_hdr); + return mlx5_packet_reformat_alloc(esw->dev, &reformat_params, MLX5_FLOW_NAMESPACE_FDB); +} + static struct mlx5_flow_table * mlx5_esw_bridge_table_create(int max_fte, u32 level, struct mlx5_eswitch *esw) { @@ -287,43 +313,74 @@ mlx5_esw_bridge_egress_mac_fg_create(struct mlx5_eswitch *esw, struct mlx5_flow_ return fg; } +static struct mlx5_flow_group * +mlx5_esw_bridge_egress_miss_fg_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *egress_ft) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *fg; + u32 *in, *match; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return ERR_PTR(-ENOMEM); + + MLX5_SET(create_flow_group_in, in, match_criteria_enable, MLX5_MATCH_MISC_PARAMETERS_2); + match = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); + + MLX5_SET(fte_match_param, match, misc_parameters_2.metadata_reg_c_1, ESW_TUN_MASK); + + MLX5_SET(create_flow_group_in, in, start_flow_index, + MLX5_ESW_BRIDGE_EGRESS_TABLE_MISS_GRP_IDX_FROM); + MLX5_SET(create_flow_group_in, in, end_flow_index, + MLX5_ESW_BRIDGE_EGRESS_TABLE_MISS_GRP_IDX_TO); + + fg = mlx5_create_flow_group(egress_ft, in); + if (IS_ERR(fg)) + esw_warn(esw->dev, + "Failed to create bridge egress table miss flow group (err=%ld)\n", + PTR_ERR(fg)); + kvfree(in); + return fg; +} + static int mlx5_esw_bridge_ingress_table_init(struct mlx5_esw_bridge_offloads *br_offloads) { struct mlx5_flow_group *mac_fg, *filter_fg, *vlan_fg; struct mlx5_flow_table *ingress_ft, *skip_ft; + struct mlx5_eswitch *esw = br_offloads->esw; int err; - if (!mlx5_eswitch_vport_match_metadata_enabled(br_offloads->esw)) + if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) return -EOPNOTSUPP; ingress_ft = mlx5_esw_bridge_table_create(MLX5_ESW_BRIDGE_INGRESS_TABLE_SIZE, MLX5_ESW_BRIDGE_LEVEL_INGRESS_TABLE, - br_offloads->esw); + esw); if (IS_ERR(ingress_ft)) return PTR_ERR(ingress_ft); skip_ft = mlx5_esw_bridge_table_create(MLX5_ESW_BRIDGE_SKIP_TABLE_SIZE, MLX5_ESW_BRIDGE_LEVEL_SKIP_TABLE, - br_offloads->esw); + esw); if (IS_ERR(skip_ft)) { err = PTR_ERR(skip_ft); goto err_skip_tbl; } - vlan_fg = mlx5_esw_bridge_ingress_vlan_fg_create(br_offloads->esw, ingress_ft); + vlan_fg = mlx5_esw_bridge_ingress_vlan_fg_create(esw, ingress_ft); if (IS_ERR(vlan_fg)) { err = PTR_ERR(vlan_fg); goto err_vlan_fg; } - filter_fg = mlx5_esw_bridge_ingress_filter_fg_create(br_offloads->esw, ingress_ft); + filter_fg = mlx5_esw_bridge_ingress_filter_fg_create(esw, ingress_ft); if (IS_ERR(filter_fg)) { err = PTR_ERR(filter_fg); goto err_filter_fg; } - mac_fg = mlx5_esw_bridge_ingress_mac_fg_create(br_offloads->esw, ingress_ft); + mac_fg = mlx5_esw_bridge_ingress_mac_fg_create(esw, ingress_ft); if (IS_ERR(mac_fg)) { err = PTR_ERR(mac_fg); goto err_mac_fg; @@ -362,35 +419,82 @@ mlx5_esw_bridge_ingress_table_cleanup(struct mlx5_esw_bridge_offloads *br_offloa br_offloads->ingress_ft = NULL; } +static struct mlx5_flow_handle * +mlx5_esw_bridge_egress_miss_flow_create(struct mlx5_flow_table *egress_ft, + struct mlx5_flow_table *skip_ft, + struct mlx5_pkt_reformat *pkt_reformat); + static int mlx5_esw_bridge_egress_table_init(struct mlx5_esw_bridge_offloads *br_offloads, struct mlx5_esw_bridge *bridge) { - struct mlx5_flow_group *mac_fg, *vlan_fg; + struct mlx5_flow_group *miss_fg = NULL, *mac_fg, *vlan_fg; + struct mlx5_pkt_reformat *miss_pkt_reformat = NULL; + struct mlx5_flow_handle *miss_handle = NULL; + struct mlx5_eswitch *esw = br_offloads->esw; struct mlx5_flow_table *egress_ft; int err; egress_ft = mlx5_esw_bridge_table_create(MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE, MLX5_ESW_BRIDGE_LEVEL_EGRESS_TABLE, - br_offloads->esw); + esw); if (IS_ERR(egress_ft)) return PTR_ERR(egress_ft); - vlan_fg = mlx5_esw_bridge_egress_vlan_fg_create(br_offloads->esw, egress_ft); + vlan_fg = mlx5_esw_bridge_egress_vlan_fg_create(esw, egress_ft); if (IS_ERR(vlan_fg)) { err = PTR_ERR(vlan_fg); goto err_vlan_fg; } - mac_fg = mlx5_esw_bridge_egress_mac_fg_create(br_offloads->esw, egress_ft); + mac_fg = mlx5_esw_bridge_egress_mac_fg_create(esw, egress_ft); if (IS_ERR(mac_fg)) { err = PTR_ERR(mac_fg); goto err_mac_fg; } + if (mlx5_esw_bridge_pkt_reformat_vlan_pop_supported(esw)) { + miss_fg = mlx5_esw_bridge_egress_miss_fg_create(esw, egress_ft); + if (IS_ERR(miss_fg)) { + esw_warn(esw->dev, "Failed to create miss flow group (err=%ld)\n", + PTR_ERR(miss_fg)); + miss_fg = NULL; + goto skip_miss_flow; + } + + miss_pkt_reformat = mlx5_esw_bridge_pkt_reformat_vlan_pop_create(esw); + if (IS_ERR(miss_pkt_reformat)) { + esw_warn(esw->dev, + "Failed to alloc packet reformat REMOVE_HEADER (err=%ld)\n", + PTR_ERR(miss_pkt_reformat)); + miss_pkt_reformat = NULL; + mlx5_destroy_flow_group(miss_fg); + miss_fg = NULL; + goto skip_miss_flow; + } + + miss_handle = mlx5_esw_bridge_egress_miss_flow_create(egress_ft, + br_offloads->skip_ft, + miss_pkt_reformat); + if (IS_ERR(miss_handle)) { + esw_warn(esw->dev, "Failed to create miss flow (err=%ld)\n", + PTR_ERR(miss_handle)); + miss_handle = NULL; + mlx5_packet_reformat_dealloc(esw->dev, miss_pkt_reformat); + miss_pkt_reformat = NULL; + mlx5_destroy_flow_group(miss_fg); + miss_fg = NULL; + goto skip_miss_flow; + } + } +skip_miss_flow: + bridge->egress_ft = egress_ft; bridge->egress_vlan_fg = vlan_fg; bridge->egress_mac_fg = mac_fg; + bridge->egress_miss_fg = miss_fg; + bridge->egress_miss_pkt_reformat = miss_pkt_reformat; + bridge->egress_miss_handle = miss_handle; return 0; err_mac_fg: @@ -403,6 +507,13 @@ err_vlan_fg: static void mlx5_esw_bridge_egress_table_cleanup(struct mlx5_esw_bridge *bridge) { + if (bridge->egress_miss_handle) + mlx5_del_flow_rules(bridge->egress_miss_handle); + if (bridge->egress_miss_pkt_reformat) + mlx5_packet_reformat_dealloc(bridge->br_offloads->esw->dev, + bridge->egress_miss_pkt_reformat); + if (bridge->egress_miss_fg) + mlx5_destroy_flow_group(bridge->egress_miss_fg); mlx5_destroy_flow_group(bridge->egress_mac_fg); mlx5_destroy_flow_group(bridge->egress_vlan_fg); mlx5_destroy_flow_table(bridge->egress_ft); @@ -443,8 +554,10 @@ mlx5_esw_bridge_ingress_flow_with_esw_create(u16 vport_num, const unsigned char mlx5_eswitch_get_vport_metadata_for_match(esw, vport_num)); if (vlan && vlan->pkt_reformat_push) { - flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; + flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT | + MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; flow_act.pkt_reformat = vlan->pkt_reformat_push; + flow_act.modify_hdr = vlan->pkt_mod_hdr_push_mark; } else if (vlan) { MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria, outer_headers.cvlan_tag); @@ -599,6 +712,41 @@ mlx5_esw_bridge_egress_flow_create(u16 vport_num, u16 esw_owner_vhca_id, const u return handle; } +static struct mlx5_flow_handle * +mlx5_esw_bridge_egress_miss_flow_create(struct mlx5_flow_table *egress_ft, + struct mlx5_flow_table *skip_ft, + struct mlx5_pkt_reformat *pkt_reformat) +{ + struct mlx5_flow_destination dest = { + .type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE, + .ft = skip_ft, + }; + struct mlx5_flow_act flow_act = { + .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT, + .flags = FLOW_ACT_NO_APPEND, + .pkt_reformat = pkt_reformat, + }; + struct mlx5_flow_spec *rule_spec; + struct mlx5_flow_handle *handle; + + rule_spec = kvzalloc(sizeof(*rule_spec), GFP_KERNEL); + if (!rule_spec) + return ERR_PTR(-ENOMEM); + + rule_spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2; + + MLX5_SET(fte_match_param, rule_spec->match_criteria, + misc_parameters_2.metadata_reg_c_1, ESW_TUN_MASK); + MLX5_SET(fte_match_param, rule_spec->match_value, misc_parameters_2.metadata_reg_c_1, + ESW_TUN_BRIDGE_INGRESS_PUSH_VLAN_MARK); + + handle = mlx5_add_flow_rules(egress_ft, rule_spec, &flow_act, &dest, 1); + + kvfree(rule_spec); + return handle; +} + static struct mlx5_esw_bridge *mlx5_esw_bridge_create(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads) { @@ -798,24 +946,14 @@ mlx5_esw_bridge_vlan_push_cleanup(struct mlx5_esw_bridge_vlan *vlan, struct mlx5 static int mlx5_esw_bridge_vlan_pop_create(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_eswitch *esw) { - struct mlx5_pkt_reformat_params reformat_params = {}; struct mlx5_pkt_reformat *pkt_reformat; - if (!BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat_remove)) || - MLX5_CAP_GEN_2(esw->dev, max_reformat_remove_size) < sizeof(struct vlan_hdr) || - MLX5_CAP_GEN_2(esw->dev, max_reformat_remove_offset) < - offsetof(struct vlan_ethhdr, h_vlan_proto)) { + if (!mlx5_esw_bridge_pkt_reformat_vlan_pop_supported(esw)) { esw_warn(esw->dev, "Packet reformat REMOVE_HEADER is not supported\n"); return -EOPNOTSUPP; } - reformat_params.type = MLX5_REFORMAT_TYPE_REMOVE_HDR; - reformat_params.param_0 = MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START; - reformat_params.param_1 = offsetof(struct vlan_ethhdr, h_vlan_proto); - reformat_params.size = sizeof(struct vlan_hdr); - pkt_reformat = mlx5_packet_reformat_alloc(esw->dev, - &reformat_params, - MLX5_FLOW_NAMESPACE_FDB); + pkt_reformat = mlx5_esw_bridge_pkt_reformat_vlan_pop_create(esw); if (IS_ERR(pkt_reformat)) { esw_warn(esw->dev, "Failed to alloc packet reformat REMOVE_HEADER (err=%ld)\n", PTR_ERR(pkt_reformat)); @@ -833,6 +971,33 @@ mlx5_esw_bridge_vlan_pop_cleanup(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_ vlan->pkt_reformat_pop = NULL; } +static int +mlx5_esw_bridge_vlan_push_mark_create(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_eswitch *esw) +{ + u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {}; + struct mlx5_modify_hdr *pkt_mod_hdr; + + MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET); + MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_C_1); + MLX5_SET(set_action_in, action, offset, 8); + MLX5_SET(set_action_in, action, length, ESW_TUN_OPTS_BITS + ESW_TUN_ID_BITS); + MLX5_SET(set_action_in, action, data, ESW_TUN_BRIDGE_INGRESS_PUSH_VLAN); + + pkt_mod_hdr = mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_FDB, 1, action); + if (IS_ERR(pkt_mod_hdr)) + return PTR_ERR(pkt_mod_hdr); + + vlan->pkt_mod_hdr_push_mark = pkt_mod_hdr; + return 0; +} + +static void +mlx5_esw_bridge_vlan_push_mark_cleanup(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_eswitch *esw) +{ + mlx5_modify_header_dealloc(esw->dev, vlan->pkt_mod_hdr_push_mark); + vlan->pkt_mod_hdr_push_mark = NULL; +} + static struct mlx5_esw_bridge_vlan * mlx5_esw_bridge_vlan_create(u16 vid, u16 flags, struct mlx5_esw_bridge_port *port, struct mlx5_eswitch *esw) @@ -852,6 +1017,10 @@ mlx5_esw_bridge_vlan_create(u16 vid, u16 flags, struct mlx5_esw_bridge_port *por err = mlx5_esw_bridge_vlan_push_create(vlan, esw); if (err) goto err_vlan_push; + + err = mlx5_esw_bridge_vlan_push_mark_create(vlan, esw); + if (err) + goto err_vlan_push_mark; } if (flags & BRIDGE_VLAN_INFO_UNTAGGED) { err = mlx5_esw_bridge_vlan_pop_create(vlan, esw); @@ -870,6 +1039,9 @@ err_xa_insert: if (vlan->pkt_reformat_pop) mlx5_esw_bridge_vlan_pop_cleanup(vlan, esw); err_vlan_pop: + if (vlan->pkt_mod_hdr_push_mark) + mlx5_esw_bridge_vlan_push_mark_cleanup(vlan, esw); +err_vlan_push_mark: if (vlan->pkt_reformat_push) mlx5_esw_bridge_vlan_push_cleanup(vlan, esw); err_vlan_push: @@ -886,6 +1058,7 @@ static void mlx5_esw_bridge_vlan_erase(struct mlx5_esw_bridge_port *port, static void mlx5_esw_bridge_vlan_flush(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_esw_bridge *bridge) { + struct mlx5_eswitch *esw = bridge->br_offloads->esw; struct mlx5_esw_bridge_fdb_entry *entry, *tmp; list_for_each_entry_safe(entry, tmp, &vlan->fdb_list, vlan_list) { @@ -894,9 +1067,11 @@ static void mlx5_esw_bridge_vlan_flush(struct mlx5_esw_bridge_vlan *vlan, } if (vlan->pkt_reformat_pop) - mlx5_esw_bridge_vlan_pop_cleanup(vlan, bridge->br_offloads->esw); + mlx5_esw_bridge_vlan_pop_cleanup(vlan, esw); + if (vlan->pkt_mod_hdr_push_mark) + mlx5_esw_bridge_vlan_push_mark_cleanup(vlan, esw); if (vlan->pkt_reformat_push) - mlx5_esw_bridge_vlan_push_cleanup(vlan, bridge->br_offloads->esw); + mlx5_esw_bridge_vlan_push_cleanup(vlan, esw); } static void mlx5_esw_bridge_vlan_cleanup(struct mlx5_esw_bridge_port *port, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h index 52964a82d6a6..878311fe950a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h @@ -49,6 +49,7 @@ struct mlx5_esw_bridge_vlan { struct list_head fdb_list; struct mlx5_pkt_reformat *pkt_reformat_push; struct mlx5_pkt_reformat *pkt_reformat_pop; + struct mlx5_modify_hdr *pkt_mod_hdr_push_mark; }; struct mlx5_esw_bridge_port { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 2c7444101bb9..7461aafb321e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -447,8 +447,16 @@ enum { MLX5_ESW_ATTR_FLAG_NO_IN_PORT = BIT(2), MLX5_ESW_ATTR_FLAG_SRC_REWRITE = BIT(3), MLX5_ESW_ATTR_FLAG_SAMPLE = BIT(4), + MLX5_ESW_ATTR_FLAG_ACCEPT = BIT(5), }; +/* Returns true if any of the flags that require skipping further TC/NF processing are set. */ +static inline bool +mlx5_esw_attr_flags_skip(u32 attr_flags) +{ + return attr_flags & (MLX5_ESW_ATTR_FLAG_SLOW_PATH | MLX5_ESW_ATTR_FLAG_ACCEPT); +} + struct mlx5_esw_flow_attr { struct mlx5_eswitch_rep *in_rep; struct mlx5_core_dev *in_mdev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 0d461e38add3..ca7e31a1a431 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -440,7 +440,7 @@ esw_setup_dests(struct mlx5_flow_destination *dest, } else if (attr->dest_ft) { esw_setup_ft_dest(dest, flow_act, esw, attr, spec, *i); (*i)++; - } else if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH) { + } else if (mlx5_esw_attr_flags_skip(attr->flags)) { esw_setup_slow_path_dest(dest, flow_act, chains, *i); (*i)++; } else if (attr->dest_chain) { @@ -467,7 +467,7 @@ esw_cleanup_dests(struct mlx5_eswitch *esw, if (attr->dest_ft) { esw_cleanup_decap_indir(esw, attr); - } else if (!(attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH)) { + } else if (!mlx5_esw_attr_flags_skip(attr->flags)) { if (attr->dest_chain) esw_cleanup_chain_dest(chains, attr->dest_chain, 1, 0); else if (esw_is_indir_table(esw, attr)) @@ -678,7 +678,7 @@ __mlx5_eswitch_del_rule(struct mlx5_eswitch *esw, mlx5_del_flow_rules(rule); - if (!(attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH)) { + if (!mlx5_esw_attr_flags_skip(attr->flags)) { /* unref the term table */ for (i = 0; i < MLX5_MAX_FLOW_FWD_VPORTS; i++) { if (esw_attr->dests[i].termtbl) @@ -1009,7 +1009,7 @@ mlx5_eswitch_add_send_to_vport_meta_rules(struct mlx5_eswitch *esw) u16 vport_num; num_vfs = esw->esw_funcs.num_vfs; - flows = kvzalloc(num_vfs * sizeof(*flows), GFP_KERNEL); + flows = kvcalloc(num_vfs, sizeof(*flows), GFP_KERNEL); if (!flows) return -ENOMEM; @@ -1188,7 +1188,7 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, peer_miss_rules_setup(esw, peer_dev, spec, &dest); - flows = kvzalloc(nvports * sizeof(*flows), GFP_KERNEL); + flows = kvcalloc(nvports, sizeof(*flows), GFP_KERNEL); if (!flows) { err = -ENOMEM; goto alloc_flows_err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c index b45954905845..879d78e46e47 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c @@ -219,7 +219,7 @@ mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw, if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, termination_table) || !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ignore_flow_level) || - attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH || + mlx5_esw_attr_flags_skip(attr->flags) || !mlx5_eswitch_offload_is_uplink_port(esw, spec)) return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index 18e5aec14641..f542a36be62c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -497,8 +497,7 @@ static struct mlx5_fc_bulk *mlx5_fc_bulk_create(struct mlx5_core_dev *dev) alloc_bitmask = MLX5_CAP_GEN(dev, flow_counter_bulk_alloc); bulk_len = alloc_bitmask > 0 ? MLX5_FC_BULK_NUM_FCS(alloc_bitmask) : 1; - bulk = kvzalloc(sizeof(*bulk) + bulk_len * sizeof(struct mlx5_fc), - GFP_KERNEL); + bulk = kvzalloc(struct_size(bulk, fcs, bulk_len), GFP_KERNEL); if (!bulk) goto err_alloc_bulk; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 79482824c64f..5893fdd5aedb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1112,8 +1112,9 @@ static int mlx5_load(struct mlx5_core_dev *dev) err = mlx5_fw_tracer_init(dev->tracer); if (err) { - mlx5_core_err(dev, "Failed to init FW tracer\n"); - goto err_fw_tracer; + mlx5_core_err(dev, "Failed to init FW tracer %d\n", err); + mlx5_fw_tracer_destroy(dev->tracer); + dev->tracer = NULL; } mlx5_fw_reset_events_start(dev); @@ -1121,8 +1122,9 @@ static int mlx5_load(struct mlx5_core_dev *dev) err = mlx5_rsc_dump_init(dev); if (err) { - mlx5_core_err(dev, "Failed to init Resource dump\n"); - goto err_rsc_dump; + mlx5_core_err(dev, "Failed to init Resource dump %d\n", err); + mlx5_rsc_dump_destroy(dev); + dev->rsc_dump = NULL; } err = mlx5_fpga_device_start(dev); @@ -1192,11 +1194,9 @@ err_tls_start: mlx5_fpga_device_stop(dev); err_fpga_start: mlx5_rsc_dump_cleanup(dev); -err_rsc_dump: mlx5_hv_vhca_cleanup(dev->hv_vhca); mlx5_fw_reset_events_stop(dev); mlx5_fw_tracer_cleanup(dev->tracer); -err_fw_tracer: mlx5_eq_table_destroy(dev); err_eq_table: mlx5_irq_table_destroy(dev); @@ -1537,6 +1537,7 @@ static int probe_one(struct pci_dev *pdev, const struct pci_device_id *id) dev_err(&pdev->dev, "mlx5_crdump_enable failed with error code %d\n", err); pci_save_state(pdev); + devlink_register(devlink); if (!mlx5_core_is_mp_slave(dev)) devlink_reload_enable(devlink); return 0; @@ -1559,6 +1560,7 @@ static void remove_one(struct pci_dev *pdev) struct devlink *devlink = priv_to_devlink(dev); devlink_reload_disable(devlink); + devlink_unregister(devlink); mlx5_crdump_disable(dev); mlx5_drain_health_wq(dev); mlx5_uninit_one(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h index abd024173c42..8116815663a7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h @@ -8,8 +8,6 @@ #define MLX5_COMP_EQS_PER_SF 8 -#define MLX5_IRQ_EQ_CTRL (0) - struct mlx5_irq; int mlx5_irq_table_init(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 763c83a02380..830444f927d4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -194,15 +194,25 @@ static void irq_sf_set_name(struct mlx5_irq_pool *pool, char *name, int vecidx) snprintf(name, MLX5_MAX_IRQ_NAME, "%s%d", pool->name, vecidx); } -static void irq_set_name(char *name, int vecidx) +static void irq_set_name(struct mlx5_irq_pool *pool, char *name, int vecidx) { - if (vecidx == 0) { + if (!pool->xa_num_irqs.max) { + /* in case we only have a single irq for the device */ + snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_combined%d", vecidx); + return; + } + + if (vecidx == pool->xa_num_irqs.max) { snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_async%d", vecidx); return; } - snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", - vecidx - MLX5_IRQ_VEC_COMP_BASE); + snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", vecidx); +} + +static bool irq_pool_is_sf_pool(struct mlx5_irq_pool *pool) +{ + return !strncmp("mlx5_sf", pool->name, strlen("mlx5_sf")); } static struct mlx5_irq *irq_request(struct mlx5_irq_pool *pool, int i) @@ -216,8 +226,8 @@ static struct mlx5_irq *irq_request(struct mlx5_irq_pool *pool, int i) if (!irq) return ERR_PTR(-ENOMEM); irq->irqn = pci_irq_vector(dev->pdev, i); - if (!pool->name[0]) - irq_set_name(name, i); + if (!irq_pool_is_sf_pool(pool)) + irq_set_name(pool, name, i); else irq_sf_set_name(pool, name, i); ATOMIC_INIT_NOTIFIER_HEAD(&irq->nh); @@ -386,6 +396,9 @@ irq_pool_request_vector(struct mlx5_irq_pool *pool, int vecidx, if (IS_ERR(irq) || !affinity) goto unlock; cpumask_copy(irq->mask, affinity); + if (!irq_pool_is_sf_pool(pool) && !pool->xa_num_irqs.max && + cpumask_empty(irq->mask)) + cpumask_set_cpu(0, irq->mask); irq_set_affinity_hint(irq->irqn, irq->mask); unlock: mutex_unlock(&pool->lock); @@ -440,6 +453,7 @@ struct mlx5_irq *mlx5_irq_request(struct mlx5_core_dev *dev, u16 vecidx, } pf_irq: pool = irq_table->pf_pool; + vecidx = (vecidx == MLX5_IRQ_EQ_CTRL) ? pool->xa_num_irqs.max : vecidx; irq = irq_pool_request_vector(pool, vecidx, affinity); out: if (IS_ERR(irq)) @@ -577,6 +591,8 @@ void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev) int mlx5_irq_table_get_num_comp(struct mlx5_irq_table *table) { + if (!table->pf_pool->xa_num_irqs.max) + return 1; return table->pf_pool->xa_num_irqs.max - table->pf_pool->xa_num_irqs.min; } @@ -592,19 +608,15 @@ int mlx5_irq_table_create(struct mlx5_core_dev *dev) if (mlx5_core_is_sf(dev)) return 0; - pf_vec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() + - MLX5_IRQ_VEC_COMP_BASE; + pf_vec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() + 1; pf_vec = min_t(int, pf_vec, num_eqs); - if (pf_vec <= MLX5_IRQ_VEC_COMP_BASE) - return -ENOMEM; total_vec = pf_vec; if (mlx5_sf_max_functions(dev)) total_vec += MLX5_IRQ_CTRL_SF_MAX + MLX5_COMP_EQS_PER_SF * mlx5_sf_max_functions(dev); - total_vec = pci_alloc_irq_vectors(dev->pdev, MLX5_IRQ_VEC_COMP_BASE + 1, - total_vec, PCI_IRQ_MSIX); + total_vec = pci_alloc_irq_vectors(dev->pdev, 1, total_vec, PCI_IRQ_MSIX); if (total_vec < 0) return total_vec; pf_vec = min(pf_vec, total_vec); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c index 052f48068dc1..3cf272fa2164 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c @@ -46,6 +46,7 @@ static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxilia mlx5_core_warn(mdev, "mlx5_init_one err=%d\n", err); goto init_one_err; } + devlink_register(devlink); devlink_reload_enable(devlink); return 0; @@ -65,6 +66,7 @@ static void mlx5_sf_dev_remove(struct auxiliary_device *adev) devlink = priv_to_devlink(sf_dev->mdev); devlink_reload_disable(devlink); + devlink_unregister(devlink); mlx5_uninit_one(sf_dev->mdev); iounmap(sf_dev->mdev->iseg); mlx5_mdev_uninit(sf_dev->mdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index a5b9f65db23c..50630112c8ff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -39,6 +39,7 @@ static const char * const action_type_to_str[] = { [DR_ACTION_TYP_VPORT] = "DR_ACTION_TYP_VPORT", [DR_ACTION_TYP_POP_VLAN] = "DR_ACTION_TYP_POP_VLAN", [DR_ACTION_TYP_PUSH_VLAN] = "DR_ACTION_TYP_PUSH_VLAN", + [DR_ACTION_TYP_SAMPLER] = "DR_ACTION_TYP_SAMPLER", [DR_ACTION_TYP_INSERT_HDR] = "DR_ACTION_TYP_INSERT_HDR", [DR_ACTION_TYP_REMOVE_HDR] = "DR_ACTION_TYP_REMOVE_HDR", [DR_ACTION_TYP_MAX] = "DR_ACTION_UNKNOWN", @@ -513,9 +514,9 @@ static int dr_action_handle_cs_recalc(struct mlx5dr_domain *dmn, /* If destination is vport we will get the FW flow table * that recalculates the CS and forwards to the vport. */ - ret = mlx5dr_domain_cache_get_recalc_cs_ft_addr(dest_action->vport->dmn, - dest_action->vport->caps->num, - final_icm_addr); + ret = mlx5dr_domain_get_recalc_cs_ft_addr(dest_action->vport->dmn, + dest_action->vport->caps->num, + final_icm_addr); if (ret) { mlx5dr_err(dmn, "Failed to get FW cs recalc flow table\n"); return ret; @@ -632,7 +633,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, return -EOPNOTSUPP; case DR_ACTION_TYP_CTR: attr.ctr_id = action->ctr->ctr_id + - action->ctr->offeset; + action->ctr->offset; break; case DR_ACTION_TYP_TAG: attr.flow_tag = action->flow_tag->flow_tag; @@ -669,7 +670,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, attr.hit_gvmi = action->vport->caps->vhca_gvmi; dest_action = action; if (rx_rule) { - if (action->vport->caps->num == WIRE_PORT) { + if (action->vport->caps->num == MLX5_VPORT_UPLINK) { mlx5dr_dbg(dmn, "Device doesn't support Loopback on WIRE vport\n"); return -EOPNOTSUPP; } @@ -1747,7 +1748,7 @@ dec_ref: struct mlx5dr_action * mlx5dr_action_create_dest_vport(struct mlx5dr_domain *dmn, - u32 vport, u8 vhca_id_valid, + u16 vport, u8 vhca_id_valid, u16 vhca_id) { struct mlx5dr_cmd_vport_cap *vport_cap; @@ -1767,9 +1768,11 @@ mlx5dr_action_create_dest_vport(struct mlx5dr_domain *dmn, return NULL; } - vport_cap = mlx5dr_get_vport_cap(&vport_dmn->info.caps, vport); + vport_cap = mlx5dr_domain_get_vport_cap(vport_dmn, vport); if (!vport_cap) { - mlx5dr_dbg(dmn, "Failed to get vport %d caps\n", vport); + mlx5dr_err(dmn, + "Failed to get vport 0x%x caps - vport is disabled or invalid\n", + vport); return NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c index 56307283bf9b..1d8febed0d76 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c @@ -195,6 +195,8 @@ int mlx5dr_cmd_query_device(struct mlx5_core_dev *mdev, caps->roce_min_src_udp = MLX5_CAP_ROCE(mdev, r_roce_min_src_udp_port); + caps->is_ecpf = mlx5_core_is_ecpf_esw_manager(mdev); + return 0; } @@ -272,7 +274,7 @@ int mlx5dr_cmd_set_fte_modify_and_vport(struct mlx5_core_dev *mdev, u32 table_id, u32 group_id, u32 modify_header_id, - u32 vport_id) + u16 vport) { u32 out[MLX5_ST_SZ_DW(set_fte_out)] = {}; void *in_flow_context; @@ -303,7 +305,7 @@ int mlx5dr_cmd_set_fte_modify_and_vport(struct mlx5_core_dev *mdev, in_dests = MLX5_ADDR_OF(flow_context, in_flow_context, destination); MLX5_SET(dest_format_struct, in_dests, destination_type, MLX5_FLOW_DESTINATION_TYPE_VPORT); - MLX5_SET(dest_format_struct, in_dests, destination_id, vport_id); + MLX5_SET(dest_format_struct, in_dests, destination_id, vport); err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out)); kvfree(in); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c index 0fe159809ba1..49089cbe897c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c @@ -9,48 +9,45 @@ ((dmn)->info.caps.dmn_type##_sw_owner_v2 && \ (dmn)->info.caps.sw_format_ver <= MLX5_STEERING_FORMAT_CONNECTX_6DX)) -static int dr_domain_init_cache(struct mlx5dr_domain *dmn) +static void dr_domain_init_csum_recalc_fts(struct mlx5dr_domain *dmn) { /* Per vport cached FW FT for checksum recalculation, this - * recalculation is needed due to a HW bug. + * recalculation is needed due to a HW bug in STEv0. */ - dmn->cache.recalc_cs_ft = kcalloc(dmn->info.caps.num_vports, - sizeof(dmn->cache.recalc_cs_ft[0]), - GFP_KERNEL); - if (!dmn->cache.recalc_cs_ft) - return -ENOMEM; - - return 0; + xa_init(&dmn->csum_fts_xa); } -static void dr_domain_uninit_cache(struct mlx5dr_domain *dmn) +static void dr_domain_uninit_csum_recalc_fts(struct mlx5dr_domain *dmn) { - int i; - - for (i = 0; i < dmn->info.caps.num_vports; i++) { - if (!dmn->cache.recalc_cs_ft[i]) - continue; + struct mlx5dr_fw_recalc_cs_ft *recalc_cs_ft; + unsigned long i; - mlx5dr_fw_destroy_recalc_cs_ft(dmn, dmn->cache.recalc_cs_ft[i]); + xa_for_each(&dmn->csum_fts_xa, i, recalc_cs_ft) { + if (recalc_cs_ft) + mlx5dr_fw_destroy_recalc_cs_ft(dmn, recalc_cs_ft); } - kfree(dmn->cache.recalc_cs_ft); + xa_destroy(&dmn->csum_fts_xa); } -int mlx5dr_domain_cache_get_recalc_cs_ft_addr(struct mlx5dr_domain *dmn, - u32 vport_num, - u64 *rx_icm_addr) +int mlx5dr_domain_get_recalc_cs_ft_addr(struct mlx5dr_domain *dmn, + u16 vport_num, + u64 *rx_icm_addr) { struct mlx5dr_fw_recalc_cs_ft *recalc_cs_ft; + int ret; - recalc_cs_ft = dmn->cache.recalc_cs_ft[vport_num]; + recalc_cs_ft = xa_load(&dmn->csum_fts_xa, vport_num); if (!recalc_cs_ft) { - /* Table not in cache, need to allocate a new one */ + /* Table hasn't been created yet */ recalc_cs_ft = mlx5dr_fw_create_recalc_cs_ft(dmn, vport_num); if (!recalc_cs_ft) return -EINVAL; - dmn->cache.recalc_cs_ft[vport_num] = recalc_cs_ft; + ret = xa_err(xa_store(&dmn->csum_fts_xa, vport_num, + recalc_cs_ft, GFP_KERNEL)); + if (ret) + return ret; } *rx_icm_addr = recalc_cs_ft->rx_icm_addr; @@ -124,18 +121,39 @@ static void dr_domain_uninit_resources(struct mlx5dr_domain *dmn) mlx5_core_dealloc_pd(dmn->mdev, dmn->pdn); } +static void dr_domain_fill_uplink_caps(struct mlx5dr_domain *dmn, + struct mlx5dr_cmd_vport_cap *uplink_vport) +{ + struct mlx5dr_esw_caps *esw_caps = &dmn->info.caps.esw_caps; + + uplink_vport->num = MLX5_VPORT_UPLINK; + uplink_vport->icm_address_rx = esw_caps->uplink_icm_address_rx; + uplink_vport->icm_address_tx = esw_caps->uplink_icm_address_tx; + uplink_vport->vport_gvmi = 0; + uplink_vport->vhca_gvmi = dmn->info.caps.gvmi; +} + static int dr_domain_query_vport(struct mlx5dr_domain *dmn, - bool other_vport, - u16 vport_number) + u16 vport_number, + struct mlx5dr_cmd_vport_cap *vport_caps) { - struct mlx5dr_cmd_vport_cap *vport_caps; + u16 cmd_vport = vport_number; + bool other_vport = true; int ret; - vport_caps = &dmn->info.caps.vports_caps[vport_number]; + if (vport_number == MLX5_VPORT_UPLINK) { + dr_domain_fill_uplink_caps(dmn, vport_caps); + return 0; + } + + if (dmn->info.caps.is_ecpf && vport_number == MLX5_VPORT_ECPF) { + other_vport = false; + cmd_vport = 0; + } ret = mlx5dr_cmd_query_esw_vport_context(dmn->mdev, other_vport, - vport_number, + cmd_vport, &vport_caps->icm_address_rx, &vport_caps->icm_address_tx); if (ret) @@ -143,7 +161,7 @@ static int dr_domain_query_vport(struct mlx5dr_domain *dmn, ret = mlx5dr_cmd_query_gvmi(dmn->mdev, other_vport, - vport_number, + cmd_vport, &vport_caps->vport_gvmi); if (ret) return ret; @@ -154,27 +172,82 @@ static int dr_domain_query_vport(struct mlx5dr_domain *dmn, return 0; } -static int dr_domain_query_vports(struct mlx5dr_domain *dmn) +static int dr_domain_query_esw_mngr(struct mlx5dr_domain *dmn) { - struct mlx5dr_esw_caps *esw_caps = &dmn->info.caps.esw_caps; - struct mlx5dr_cmd_vport_cap *wire_vport; - int vport; + return dr_domain_query_vport(dmn, + dmn->info.caps.is_ecpf ? MLX5_VPORT_ECPF : 0, + &dmn->info.caps.vports.esw_manager_caps); +} + +static struct mlx5dr_cmd_vport_cap * +dr_domain_add_vport_cap(struct mlx5dr_domain *dmn, u16 vport) +{ + struct mlx5dr_cmd_caps *caps = &dmn->info.caps; + struct mlx5dr_cmd_vport_cap *vport_caps; int ret; - /* Query vports (except wire vport) */ - for (vport = 0; vport < dmn->info.caps.num_esw_ports - 1; vport++) { - ret = dr_domain_query_vport(dmn, !!vport, vport); - if (ret) - return ret; + vport_caps = kvzalloc(sizeof(*vport_caps), GFP_KERNEL); + if (!vport_caps) + return NULL; + + ret = dr_domain_query_vport(dmn, vport, vport_caps); + if (ret) { + kvfree(vport_caps); + return NULL; } - /* Last vport is the wire port */ - wire_vport = &dmn->info.caps.vports_caps[vport]; - wire_vport->num = WIRE_PORT; - wire_vport->icm_address_rx = esw_caps->uplink_icm_address_rx; - wire_vport->icm_address_tx = esw_caps->uplink_icm_address_tx; - wire_vport->vport_gvmi = 0; - wire_vport->vhca_gvmi = dmn->info.caps.gvmi; + ret = xa_insert(&caps->vports.vports_caps_xa, vport, + vport_caps, GFP_KERNEL); + if (ret) { + mlx5dr_dbg(dmn, "Couldn't insert new vport into xarray (%d)\n", ret); + kvfree(vport_caps); + return ERR_PTR(ret); + } + + return vport_caps; +} + +struct mlx5dr_cmd_vport_cap * +mlx5dr_domain_get_vport_cap(struct mlx5dr_domain *dmn, u16 vport) +{ + struct mlx5dr_cmd_caps *caps = &dmn->info.caps; + struct mlx5dr_cmd_vport_cap *vport_caps; + + if ((caps->is_ecpf && vport == MLX5_VPORT_ECPF) || + (!caps->is_ecpf && vport == 0)) + return &caps->vports.esw_manager_caps; + +vport_load: + vport_caps = xa_load(&caps->vports.vports_caps_xa, vport); + if (vport_caps) + return vport_caps; + + vport_caps = dr_domain_add_vport_cap(dmn, vport); + if (PTR_ERR(vport_caps) == -EBUSY) + /* caps were already stored by another thread */ + goto vport_load; + + return vport_caps; +} + +static void dr_domain_clear_vports(struct mlx5dr_domain *dmn) +{ + struct mlx5dr_cmd_vport_cap *vport_caps; + unsigned long i; + + xa_for_each(&dmn->info.caps.vports.vports_caps_xa, i, vport_caps) { + vport_caps = xa_erase(&dmn->info.caps.vports.vports_caps_xa, i); + kvfree(vport_caps); + } +} + +static int dr_domain_query_uplink(struct mlx5dr_domain *dmn) +{ + struct mlx5dr_cmd_vport_cap *vport_caps; + + vport_caps = mlx5dr_domain_get_vport_cap(dmn, MLX5_VPORT_UPLINK); + if (!vport_caps) + return -EINVAL; return 0; } @@ -196,25 +269,29 @@ static int dr_domain_query_fdb_caps(struct mlx5_core_dev *mdev, dmn->info.caps.esw_rx_drop_address = dmn->info.caps.esw_caps.drop_icm_address_rx; dmn->info.caps.esw_tx_drop_address = dmn->info.caps.esw_caps.drop_icm_address_tx; - dmn->info.caps.vports_caps = kcalloc(dmn->info.caps.num_esw_ports, - sizeof(dmn->info.caps.vports_caps[0]), - GFP_KERNEL); - if (!dmn->info.caps.vports_caps) - return -ENOMEM; + xa_init(&dmn->info.caps.vports.vports_caps_xa); - ret = dr_domain_query_vports(dmn); + /* Query eswitch manager and uplink vports only. Rest of the + * vports (vport 0, VFs and SFs) will be queried dynamically. + */ + + ret = dr_domain_query_esw_mngr(dmn); if (ret) { - mlx5dr_err(dmn, "Failed to query vports caps (err: %d)", ret); - goto free_vports_caps; + mlx5dr_err(dmn, "Failed to query eswitch manager vport caps (err: %d)", ret); + goto free_vports_caps_xa; } - dmn->info.caps.num_vports = dmn->info.caps.num_esw_ports - 1; + ret = dr_domain_query_uplink(dmn); + if (ret) { + mlx5dr_err(dmn, "Failed to query uplink vport caps (err: %d)", ret); + goto free_vports_caps_xa; + } return 0; -free_vports_caps: - kfree(dmn->info.caps.vports_caps); - dmn->info.caps.vports_caps = NULL; +free_vports_caps_xa: + xa_destroy(&dmn->info.caps.vports.vports_caps_xa); + return ret; } @@ -229,8 +306,6 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev, return -EOPNOTSUPP; } - dmn->info.caps.num_esw_ports = mlx5_eswitch_get_total_vports(mdev); - ret = mlx5dr_cmd_query_device(mdev, &dmn->info.caps); if (ret) return ret; @@ -267,11 +342,7 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev, dmn->info.rx.type = DR_DOMAIN_NIC_TYPE_RX; dmn->info.tx.type = DR_DOMAIN_NIC_TYPE_TX; - vport_cap = mlx5dr_get_vport_cap(&dmn->info.caps, 0); - if (!vport_cap) { - mlx5dr_err(dmn, "Failed to get esw manager vport\n"); - return -ENOENT; - } + vport_cap = &dmn->info.caps.vports.esw_manager_caps; dmn->info.supp_sw_steering = true; dmn->info.tx.default_icm_addr = vport_cap->icm_address_tx; @@ -290,7 +361,8 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev, static void dr_domain_caps_uninit(struct mlx5dr_domain *dmn) { - kfree(dmn->info.caps.vports_caps); + dr_domain_clear_vports(dmn); + xa_destroy(&dmn->info.caps.vports.vports_caps_xa); } struct mlx5dr_domain * @@ -333,16 +405,10 @@ mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type) goto uninit_caps; } - ret = dr_domain_init_cache(dmn); - if (ret) { - mlx5dr_err(dmn, "Failed initialize domain cache\n"); - goto uninit_resourses; - } + dr_domain_init_csum_recalc_fts(dmn); return dmn; -uninit_resourses: - dr_domain_uninit_resources(dmn); uninit_caps: dr_domain_caps_uninit(dmn); free_domain: @@ -381,7 +447,7 @@ int mlx5dr_domain_destroy(struct mlx5dr_domain *dmn) /* make sure resources are not used by the hardware */ mlx5dr_cmd_sync_steering(dmn->mdev); - dr_domain_uninit_cache(dmn); + dr_domain_uninit_csum_recalc_fts(dmn); dr_domain_uninit_resources(dmn); dr_domain_caps_uninit(dmn); mutex_destroy(&dmn->info.tx.mutex); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c index 0d6f86eb248b..68a4c32d5f34 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c @@ -5,7 +5,7 @@ #include "dr_types.h" struct mlx5dr_fw_recalc_cs_ft * -mlx5dr_fw_create_recalc_cs_ft(struct mlx5dr_domain *dmn, u32 vport_num) +mlx5dr_fw_create_recalc_cs_ft(struct mlx5dr_domain *dmn, u16 vport_num) { struct mlx5dr_cmd_create_flow_table_attr ft_attr = {}; struct mlx5dr_fw_recalc_cs_ft *recalc_cs_ft; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index aca80efc28fa..323ea138ad99 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -1042,10 +1042,10 @@ static bool dr_rule_skip(enum mlx5dr_domain_type domain, return false; if (mask->misc.source_port) { - if (rx && value->misc.source_port != WIRE_PORT) + if (rx && value->misc.source_port != MLX5_VPORT_UPLINK) return true; - if (!rx && value->misc.source_port == WIRE_PORT) + if (!rx && value->misc.source_port == MLX5_VPORT_UPLINK) return true; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c index 9c704bce3c12..b0649c2877dd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c @@ -1645,7 +1645,7 @@ dr_ste_v0_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value, struct mlx5dr_match_misc *misc = &value->misc; struct mlx5dr_cmd_vport_cap *vport_cap; struct mlx5dr_domain *dmn = sb->dmn; - struct mlx5dr_cmd_caps *caps; + struct mlx5dr_domain *vport_dmn; u8 *bit_mask = sb->bit_mask; bool source_gvmi_set; @@ -1654,23 +1654,24 @@ dr_ste_v0_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value, if (sb->vhca_id_valid) { /* Find port GVMI based on the eswitch_owner_vhca_id */ if (misc->source_eswitch_owner_vhca_id == dmn->info.caps.gvmi) - caps = &dmn->info.caps; + vport_dmn = dmn; else if (dmn->peer_dmn && (misc->source_eswitch_owner_vhca_id == dmn->peer_dmn->info.caps.gvmi)) - caps = &dmn->peer_dmn->info.caps; + vport_dmn = dmn->peer_dmn; else return -EINVAL; misc->source_eswitch_owner_vhca_id = 0; } else { - caps = &dmn->info.caps; + vport_dmn = dmn; } source_gvmi_set = MLX5_GET(ste_src_gvmi_qp, bit_mask, source_gvmi); if (source_gvmi_set) { - vport_cap = mlx5dr_get_vport_cap(caps, misc->source_port); + vport_cap = mlx5dr_domain_get_vport_cap(vport_dmn, + misc->source_port); if (!vport_cap) { - mlx5dr_err(dmn, "Vport 0x%x is invalid\n", + mlx5dr_err(dmn, "Vport 0x%x is disabled or invalid\n", misc->source_port); return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c index b2481c99da79..cb9cf67b0a02 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c @@ -586,9 +586,11 @@ static void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn, } else if (action_type_set[DR_ACTION_TYP_L2_TO_TNL_L3]) { u8 *d_action; - dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi); - action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action); - action_sz = DR_STE_ACTION_TRIPLE_SZ; + if (action_sz < DR_STE_ACTION_TRIPLE_SZ) { + dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi); + action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action); + action_sz = DR_STE_ACTION_TRIPLE_SZ; + } d_action = action + DR_STE_ACTION_SINGLE_SZ; dr_ste_v1_set_encap_l3(last_ste, @@ -1776,7 +1778,7 @@ static int dr_ste_v1_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value, struct mlx5dr_match_misc *misc = &value->misc; struct mlx5dr_cmd_vport_cap *vport_cap; struct mlx5dr_domain *dmn = sb->dmn; - struct mlx5dr_cmd_caps *caps; + struct mlx5dr_domain *vport_dmn; u8 *bit_mask = sb->bit_mask; DR_STE_SET_TAG(src_gvmi_qp_v1, tag, source_qp, misc, source_sqn); @@ -1784,22 +1786,22 @@ static int dr_ste_v1_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value, if (sb->vhca_id_valid) { /* Find port GVMI based on the eswitch_owner_vhca_id */ if (misc->source_eswitch_owner_vhca_id == dmn->info.caps.gvmi) - caps = &dmn->info.caps; + vport_dmn = dmn; else if (dmn->peer_dmn && (misc->source_eswitch_owner_vhca_id == dmn->peer_dmn->info.caps.gvmi)) - caps = &dmn->peer_dmn->info.caps; + vport_dmn = dmn->peer_dmn; else return -EINVAL; - misc->source_eswitch_owner_vhca_id = 0; + misc->source_eswitch_owner_vhca_id = 0; } else { - caps = &dmn->info.caps; + vport_dmn = dmn; } if (!MLX5_GET(ste_src_gvmi_qp_v1, bit_mask, source_gvmi)) return 0; - vport_cap = mlx5dr_get_vport_cap(caps, misc->source_port); + vport_cap = mlx5dr_domain_get_vport_cap(vport_dmn, misc->source_port); if (!vport_cap) { mlx5dr_err(dmn, "Vport 0x%x is disabled or invalid\n", misc->source_port); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index b20e8aabb861..73fed94af09a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -4,7 +4,7 @@ #ifndef _DR_TYPES_ #define _DR_TYPES_ -#include <linux/mlx5/driver.h> +#include <linux/mlx5/vport.h> #include <linux/refcount.h> #include "fs_core.h" #include "wq.h" @@ -14,7 +14,6 @@ #define DR_RULE_MAX_STES 18 #define DR_ACTION_MAX_STES 5 -#define WIRE_PORT 0xFFFF #define DR_STE_SVLAN 0x1 #define DR_STE_CVLAN 0x2 #define DR_SZ_MATCH_PARAM (MLX5_ST_SZ_DW_MATCH_PARAM * 4) @@ -752,9 +751,9 @@ struct mlx5dr_esw_caps { struct mlx5dr_cmd_vport_cap { u16 vport_gvmi; u16 vhca_gvmi; + u16 num; u64 icm_address_rx; u64 icm_address_tx; - u32 num; }; struct mlx5dr_roce_cap { @@ -763,6 +762,11 @@ struct mlx5dr_roce_cap { u8 fl_rc_qp_when_roce_enabled:1; }; +struct mlx5dr_vports { + struct mlx5dr_cmd_vport_cap esw_manager_caps; + struct xarray vports_caps_xa; +}; + struct mlx5dr_cmd_caps { u16 gvmi; u64 nic_rx_drop_address; @@ -786,7 +790,6 @@ struct mlx5dr_cmd_caps { u8 flex_parser_id_gtpu_first_ext_dw_0; u8 max_ft_level; u16 roce_min_src_udp; - u8 num_esw_ports; u8 sw_format_ver; bool eswitch_manager; bool rx_sw_owner; @@ -795,11 +798,11 @@ struct mlx5dr_cmd_caps { u8 rx_sw_owner_v2:1; u8 tx_sw_owner_v2:1; u8 fdb_sw_owner_v2:1; - u32 num_vports; struct mlx5dr_esw_caps esw_caps; - struct mlx5dr_cmd_vport_cap *vports_caps; + struct mlx5dr_vports vports; bool prio_tag_required; struct mlx5dr_roce_cap roce_caps; + u8 is_ecpf:1; u8 isolate_vl_tc:1; }; @@ -826,10 +829,6 @@ struct mlx5dr_domain_info { struct mlx5dr_cmd_caps caps; }; -struct mlx5dr_domain_cache { - struct mlx5dr_fw_recalc_cs_ft **recalc_cs_ft; -}; - struct mlx5dr_domain { struct mlx5dr_domain *peer_dmn; struct mlx5_core_dev *mdev; @@ -841,7 +840,7 @@ struct mlx5dr_domain { struct mlx5dr_icm_pool *action_icm_pool; struct mlx5dr_send_ring *send_ring; struct mlx5dr_domain_info info; - struct mlx5dr_domain_cache cache; + struct xarray csum_fts_xa; struct mlx5dr_ste_ctx *ste_ctx; }; @@ -942,7 +941,7 @@ struct mlx5dr_action_dest_tbl { struct mlx5dr_action_ctr { u32 ctr_id; - u32 offeset; + u32 offset; }; struct mlx5dr_action_vport { @@ -1102,18 +1101,8 @@ mlx5dr_ste_htbl_may_grow(struct mlx5dr_ste_htbl *htbl) return true; } -static inline struct mlx5dr_cmd_vport_cap * -mlx5dr_get_vport_cap(struct mlx5dr_cmd_caps *caps, u32 vport) -{ - if (!caps->vports_caps || - (vport >= caps->num_vports && vport != WIRE_PORT)) - return NULL; - - if (vport == WIRE_PORT) - vport = caps->num_vports; - - return &caps->vports_caps[vport]; -} +struct mlx5dr_cmd_vport_cap * +mlx5dr_domain_get_vport_cap(struct mlx5dr_domain *dmn, u16 vport); struct mlx5dr_cmd_query_flow_table_details { u8 status; @@ -1154,7 +1143,7 @@ int mlx5dr_cmd_set_fte_modify_and_vport(struct mlx5_core_dev *mdev, u32 table_id, u32 group_id, u32 modify_header_id, - u32 vport_id); + u16 vport_id); int mlx5dr_cmd_del_flow_table_entry(struct mlx5_core_dev *mdev, u32 table_type, u32 table_id); @@ -1372,12 +1361,12 @@ struct mlx5dr_fw_recalc_cs_ft { }; struct mlx5dr_fw_recalc_cs_ft * -mlx5dr_fw_create_recalc_cs_ft(struct mlx5dr_domain *dmn, u32 vport_num); +mlx5dr_fw_create_recalc_cs_ft(struct mlx5dr_domain *dmn, u16 vport_num); void mlx5dr_fw_destroy_recalc_cs_ft(struct mlx5dr_domain *dmn, struct mlx5dr_fw_recalc_cs_ft *recalc_cs_ft); -int mlx5dr_domain_cache_get_recalc_cs_ft_addr(struct mlx5dr_domain *dmn, - u32 vport_num, - u64 *rx_icm_addr); +int mlx5dr_domain_get_recalc_cs_ft_addr(struct mlx5dr_domain *dmn, + u16 vport_num, + u64 *rx_icm_addr); int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn, struct mlx5dr_cmd_flow_destination_hw_info *dest, int num_dest, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index 7e58f4e594b7..230e920e3845 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -222,7 +222,7 @@ static bool contain_vport_reformat_action(struct mlx5_flow_rule *dst) dst->dest_attr.vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID; } -#define MLX5_FLOW_CONTEXT_ACTION_MAX 20 +#define MLX5_FLOW_CONTEXT_ACTION_MAX 32 static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *ft, struct mlx5_flow_group *group, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index c5a8b1601999..c7c93131b762 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -89,7 +89,7 @@ mlx5dr_action_create_dest_flow_fw_table(struct mlx5dr_domain *domain, struct mlx5dr_action * mlx5dr_action_create_dest_vport(struct mlx5dr_domain *domain, - u32 vport, u8 vhca_id_valid, + u16 vport, u8 vhca_id_valid, u16 vhca_id); struct mlx5dr_action * diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c index 6704f5c1aa32..b990782c1eb1 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c @@ -75,7 +75,7 @@ static void mlxbf_gige_initial_mac(struct mlxbf_gige *priv) u64_to_ether_addr(local_mac, mac); if (is_valid_ether_addr(mac)) { - ether_addr_copy(priv->netdev->dev_addr, mac); + eth_hw_addr_set(priv->netdev, mac); } else { /* Provide a random MAC if for some reason the device has * not been configured with a valid MAC address already. diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index f080fab3de2b..9e831e8b607a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -90,7 +90,6 @@ struct mlxsw_core { struct devlink_health_reporter *fw_fatal; } health; struct mlxsw_env *env; - bool is_initialized; /* Denotes if core was already initialized. */ unsigned long driver_priv[]; /* driver_priv has to be always the last item */ }; @@ -1975,12 +1974,6 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, goto err_emad_init; if (!reload) { - err = devlink_register(devlink); - if (err) - goto err_devlink_register; - } - - if (!reload) { err = mlxsw_core_params_register(mlxsw_core); if (err) goto err_register_params; @@ -1995,12 +1988,6 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, if (err) goto err_health_init; - if (mlxsw_driver->init) { - err = mlxsw_driver->init(mlxsw_core, mlxsw_bus_info, extack); - if (err) - goto err_driver_init; - } - err = mlxsw_hwmon_init(mlxsw_core, mlxsw_bus_info, &mlxsw_core->hwmon); if (err) goto err_hwmon_init; @@ -2014,31 +2001,32 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, if (err) goto err_env_init; - mlxsw_core->is_initialized = true; - devlink_params_publish(devlink); + if (mlxsw_driver->init) { + err = mlxsw_driver->init(mlxsw_core, mlxsw_bus_info, extack); + if (err) + goto err_driver_init; + } - if (!reload) + if (!reload) { + devlink_register(devlink); devlink_reload_enable(devlink); + } return 0; +err_driver_init: + mlxsw_env_fini(mlxsw_core->env); err_env_init: mlxsw_thermal_fini(mlxsw_core->thermal); err_thermal_init: mlxsw_hwmon_fini(mlxsw_core->hwmon); err_hwmon_init: - if (mlxsw_core->driver->fini) - mlxsw_core->driver->fini(mlxsw_core); -err_driver_init: mlxsw_core_health_fini(mlxsw_core); err_health_init: err_fw_rev_validate: if (!reload) mlxsw_core_params_unregister(mlxsw_core); err_register_params: - if (!reload) - devlink_unregister(devlink); -err_devlink_register: mlxsw_emad_fini(mlxsw_core); err_emad_init: kfree(mlxsw_core->lag.mapping); @@ -2087,8 +2075,10 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, { struct devlink *devlink = priv_to_devlink(mlxsw_core); - if (!reload) + if (!reload) { devlink_reload_disable(devlink); + devlink_unregister(devlink); + } if (devlink_is_reload_failed(devlink)) { if (!reload) /* Only the parts that were not de-initialized in the @@ -2099,18 +2089,14 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, return; } - devlink_params_unpublish(devlink); - mlxsw_core->is_initialized = false; + if (mlxsw_core->driver->fini) + mlxsw_core->driver->fini(mlxsw_core); mlxsw_env_fini(mlxsw_core->env); mlxsw_thermal_fini(mlxsw_core->thermal); mlxsw_hwmon_fini(mlxsw_core->hwmon); - if (mlxsw_core->driver->fini) - mlxsw_core->driver->fini(mlxsw_core); mlxsw_core_health_fini(mlxsw_core); if (!reload) mlxsw_core_params_unregister(mlxsw_core); - if (!reload) - devlink_unregister(devlink); mlxsw_emad_fini(mlxsw_core); kfree(mlxsw_core->lag.mapping); mlxsw_ports_fini(mlxsw_core, reload); @@ -2124,7 +2110,6 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, reload_fail_deinit: mlxsw_core_params_unregister(mlxsw_core); - devlink_unregister(devlink); devlink_resources_unregister(devlink, NULL); devlink_free(devlink); } @@ -2939,49 +2924,6 @@ struct mlxsw_env *mlxsw_core_env(const struct mlxsw_core *mlxsw_core) return mlxsw_core->env; } -bool mlxsw_core_is_initialized(const struct mlxsw_core *mlxsw_core) -{ - return mlxsw_core->is_initialized; -} - -int mlxsw_core_module_max_width(struct mlxsw_core *mlxsw_core, u8 module) -{ - enum mlxsw_reg_pmtm_module_type module_type; - char pmtm_pl[MLXSW_REG_PMTM_LEN]; - int err; - - mlxsw_reg_pmtm_pack(pmtm_pl, module); - err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(pmtm), pmtm_pl); - if (err) - return err; - mlxsw_reg_pmtm_unpack(pmtm_pl, &module_type); - - /* Here we need to get the module width according to the module type. */ - - switch (module_type) { - case MLXSW_REG_PMTM_MODULE_TYPE_C2C8X: - case MLXSW_REG_PMTM_MODULE_TYPE_QSFP_DD: - case MLXSW_REG_PMTM_MODULE_TYPE_OSFP: - return 8; - case MLXSW_REG_PMTM_MODULE_TYPE_C2C4X: - case MLXSW_REG_PMTM_MODULE_TYPE_BP_4X: - case MLXSW_REG_PMTM_MODULE_TYPE_QSFP: - return 4; - case MLXSW_REG_PMTM_MODULE_TYPE_C2C2X: - case MLXSW_REG_PMTM_MODULE_TYPE_BP_2X: - case MLXSW_REG_PMTM_MODULE_TYPE_SFP_DD: - case MLXSW_REG_PMTM_MODULE_TYPE_DSFP: - return 2; - case MLXSW_REG_PMTM_MODULE_TYPE_C2C1X: - case MLXSW_REG_PMTM_MODULE_TYPE_BP_1X: - case MLXSW_REG_PMTM_MODULE_TYPE_SFP: - return 1; - default: - return -EINVAL; - } -} -EXPORT_SYMBOL(mlxsw_core_module_max_width); - static void mlxsw_core_buf_dump_dbg(struct mlxsw_core *mlxsw_core, const char *buf, size_t size) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index 80712dc803d0..12023a550007 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -249,8 +249,6 @@ mlxsw_core_port_devlink_port_get(struct mlxsw_core *mlxsw_core, u8 local_port); bool mlxsw_core_port_is_xm(const struct mlxsw_core *mlxsw_core, u8 local_port); struct mlxsw_env *mlxsw_core_env(const struct mlxsw_core *mlxsw_core); -bool mlxsw_core_is_initialized(const struct mlxsw_core *mlxsw_core); -int mlxsw_core_module_max_width(struct mlxsw_core *mlxsw_core, u8 module); int mlxsw_core_schedule_dw(struct delayed_work *dwork, unsigned long delay); bool mlxsw_core_schedule_work(struct work_struct *work); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c index 3713c45cfa1e..6dd4ae2f45f4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_env.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c @@ -5,6 +5,7 @@ #include <linux/err.h> #include <linux/ethtool.h> #include <linux/sfp.h> +#include <linux/mutex.h> #include "core.h" #include "core_env.h" @@ -14,12 +15,15 @@ struct mlxsw_env_module_info { u64 module_overheat_counter; bool is_overheat; + int num_ports_mapped; + int num_ports_up; + enum ethtool_module_power_mode_policy power_mode_policy; }; struct mlxsw_env { struct mlxsw_core *core; u8 module_count; - spinlock_t module_info_lock; /* Protects 'module_info'. */ + struct mutex module_info_lock; /* Protects 'module_info'. */ struct mlxsw_env_module_info module_info[]; }; @@ -389,6 +393,205 @@ mlxsw_env_get_module_eeprom_by_page(struct mlxsw_core *mlxsw_core, u8 module, } EXPORT_SYMBOL(mlxsw_env_get_module_eeprom_by_page); +static int mlxsw_env_module_reset(struct mlxsw_core *mlxsw_core, u8 module) +{ + char pmaos_pl[MLXSW_REG_PMAOS_LEN]; + + mlxsw_reg_pmaos_pack(pmaos_pl, module); + mlxsw_reg_pmaos_rst_set(pmaos_pl, true); + + return mlxsw_reg_write(mlxsw_core, MLXSW_REG(pmaos), pmaos_pl); +} + +int mlxsw_env_reset_module(struct net_device *netdev, + struct mlxsw_core *mlxsw_core, u8 module, u32 *flags) +{ + struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core); + u32 req = *flags; + int err; + + if (!(req & ETH_RESET_PHY) && + !(req & (ETH_RESET_PHY << ETH_RESET_SHARED_SHIFT))) + return 0; + + if (WARN_ON_ONCE(module >= mlxsw_env->module_count)) + return -EINVAL; + + mutex_lock(&mlxsw_env->module_info_lock); + + if (mlxsw_env->module_info[module].num_ports_up) { + netdev_err(netdev, "Cannot reset module when ports using it are administratively up\n"); + err = -EINVAL; + goto out; + } + + if (mlxsw_env->module_info[module].num_ports_mapped > 1 && + !(req & (ETH_RESET_PHY << ETH_RESET_SHARED_SHIFT))) { + netdev_err(netdev, "Cannot reset module without \"phy-shared\" flag when shared by multiple ports\n"); + err = -EINVAL; + goto out; + } + + err = mlxsw_env_module_reset(mlxsw_core, module); + if (err) { + netdev_err(netdev, "Failed to reset module\n"); + goto out; + } + + *flags &= ~(ETH_RESET_PHY | (ETH_RESET_PHY << ETH_RESET_SHARED_SHIFT)); + +out: + mutex_unlock(&mlxsw_env->module_info_lock); + return err; +} +EXPORT_SYMBOL(mlxsw_env_reset_module); + +int +mlxsw_env_get_module_power_mode(struct mlxsw_core *mlxsw_core, u8 module, + struct ethtool_module_power_mode_params *params, + struct netlink_ext_ack *extack) +{ + struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core); + char mcion_pl[MLXSW_REG_MCION_LEN]; + u32 status_bits; + int err; + + if (WARN_ON_ONCE(module >= mlxsw_env->module_count)) + return -EINVAL; + + mutex_lock(&mlxsw_env->module_info_lock); + + params->policy = mlxsw_env->module_info[module].power_mode_policy; + + mlxsw_reg_mcion_pack(mcion_pl, module); + err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mcion), mcion_pl); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to retrieve module's power mode"); + goto out; + } + + status_bits = mlxsw_reg_mcion_module_status_bits_get(mcion_pl); + if (!(status_bits & MLXSW_REG_MCION_MODULE_STATUS_BITS_PRESENT_MASK)) + goto out; + + if (status_bits & MLXSW_REG_MCION_MODULE_STATUS_BITS_LOW_POWER_MASK) + params->mode = ETHTOOL_MODULE_POWER_MODE_LOW; + else + params->mode = ETHTOOL_MODULE_POWER_MODE_HIGH; + +out: + mutex_unlock(&mlxsw_env->module_info_lock); + return err; +} +EXPORT_SYMBOL(mlxsw_env_get_module_power_mode); + +static int mlxsw_env_module_enable_set(struct mlxsw_core *mlxsw_core, + u8 module, bool enable) +{ + enum mlxsw_reg_pmaos_admin_status admin_status; + char pmaos_pl[MLXSW_REG_PMAOS_LEN]; + + mlxsw_reg_pmaos_pack(pmaos_pl, module); + admin_status = enable ? MLXSW_REG_PMAOS_ADMIN_STATUS_ENABLED : + MLXSW_REG_PMAOS_ADMIN_STATUS_DISABLED; + mlxsw_reg_pmaos_admin_status_set(pmaos_pl, admin_status); + mlxsw_reg_pmaos_ase_set(pmaos_pl, true); + + return mlxsw_reg_write(mlxsw_core, MLXSW_REG(pmaos), pmaos_pl); +} + +static int mlxsw_env_module_low_power_set(struct mlxsw_core *mlxsw_core, + u8 module, bool low_power) +{ + u16 eeprom_override_mask, eeprom_override; + char pmmp_pl[MLXSW_REG_PMMP_LEN]; + + mlxsw_reg_pmmp_pack(pmmp_pl, module); + mlxsw_reg_pmmp_sticky_set(pmmp_pl, true); + /* Mask all the bits except low power mode. */ + eeprom_override_mask = ~MLXSW_REG_PMMP_EEPROM_OVERRIDE_LOW_POWER_MASK; + mlxsw_reg_pmmp_eeprom_override_mask_set(pmmp_pl, eeprom_override_mask); + eeprom_override = low_power ? MLXSW_REG_PMMP_EEPROM_OVERRIDE_LOW_POWER_MASK : + 0; + mlxsw_reg_pmmp_eeprom_override_set(pmmp_pl, eeprom_override); + + return mlxsw_reg_write(mlxsw_core, MLXSW_REG(pmmp), pmmp_pl); +} + +static int __mlxsw_env_set_module_power_mode(struct mlxsw_core *mlxsw_core, + u8 module, bool low_power, + struct netlink_ext_ack *extack) +{ + int err; + + err = mlxsw_env_module_enable_set(mlxsw_core, module, false); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to disable module"); + return err; + } + + err = mlxsw_env_module_low_power_set(mlxsw_core, module, low_power); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to set module's power mode"); + goto err_module_low_power_set; + } + + err = mlxsw_env_module_enable_set(mlxsw_core, module, true); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to enable module"); + goto err_module_enable_set; + } + + return 0; + +err_module_enable_set: + mlxsw_env_module_low_power_set(mlxsw_core, module, !low_power); +err_module_low_power_set: + mlxsw_env_module_enable_set(mlxsw_core, module, true); + return err; +} + +int +mlxsw_env_set_module_power_mode(struct mlxsw_core *mlxsw_core, u8 module, + enum ethtool_module_power_mode_policy policy, + struct netlink_ext_ack *extack) +{ + struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core); + bool low_power; + int err = 0; + + if (WARN_ON_ONCE(module >= mlxsw_env->module_count)) + return -EINVAL; + + if (policy != ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH && + policy != ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported power mode policy"); + return -EOPNOTSUPP; + } + + mutex_lock(&mlxsw_env->module_info_lock); + + if (mlxsw_env->module_info[module].power_mode_policy == policy) + goto out; + + /* If any ports are up, we are already in high power mode. */ + if (mlxsw_env->module_info[module].num_ports_up) + goto out_set_policy; + + low_power = policy == ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO; + err = __mlxsw_env_set_module_power_mode(mlxsw_core, module, low_power, + extack); + if (err) + goto out; + +out_set_policy: + mlxsw_env->module_info[module].power_mode_policy = policy; +out: + mutex_unlock(&mlxsw_env->module_info_lock); + return err; +} +EXPORT_SYMBOL(mlxsw_env_set_module_power_mode); + static int mlxsw_env_module_has_temp_sensor(struct mlxsw_core *mlxsw_core, u8 module, bool *p_has_temp_sensor) @@ -482,22 +685,32 @@ static int mlxsw_env_module_temp_event_enable(struct mlxsw_core *mlxsw_core, return 0; } -static void mlxsw_env_mtwe_event_func(const struct mlxsw_reg_info *reg, - char *mtwe_pl, void *priv) +struct mlxsw_env_module_temp_warn_event { + struct mlxsw_env *mlxsw_env; + char mtwe_pl[MLXSW_REG_MTWE_LEN]; + struct work_struct work; +}; + +static void mlxsw_env_mtwe_event_work(struct work_struct *work) { - struct mlxsw_env *mlxsw_env = priv; + struct mlxsw_env_module_temp_warn_event *event; + struct mlxsw_env *mlxsw_env; int i, sensor_warning; bool is_overheat; + event = container_of(work, struct mlxsw_env_module_temp_warn_event, + work); + mlxsw_env = event->mlxsw_env; + for (i = 0; i < mlxsw_env->module_count; i++) { /* 64-127 of sensor_index are mapped to the port modules * sequentially (module 0 is mapped to sensor_index 64, * module 1 to sensor_index 65 and so on) */ sensor_warning = - mlxsw_reg_mtwe_sensor_warning_get(mtwe_pl, + mlxsw_reg_mtwe_sensor_warning_get(event->mtwe_pl, i + MLXSW_REG_MTMP_MODULE_INDEX_MIN); - spin_lock(&mlxsw_env->module_info_lock); + mutex_lock(&mlxsw_env->module_info_lock); is_overheat = mlxsw_env->module_info[i].is_overheat; @@ -507,13 +720,13 @@ static void mlxsw_env_mtwe_event_func(const struct mlxsw_reg_info *reg, * warning OR current state in "no warning" and MTWE * does not report warning. */ - spin_unlock(&mlxsw_env->module_info_lock); + mutex_unlock(&mlxsw_env->module_info_lock); continue; } else if (is_overheat && !sensor_warning) { /* MTWE reports "no warning", turn is_overheat off. */ mlxsw_env->module_info[i].is_overheat = false; - spin_unlock(&mlxsw_env->module_info_lock); + mutex_unlock(&mlxsw_env->module_info_lock); } else { /* Current state is "no warning" and MTWE reports * "warning", increase the counter and turn is_overheat @@ -521,13 +734,32 @@ static void mlxsw_env_mtwe_event_func(const struct mlxsw_reg_info *reg, */ mlxsw_env->module_info[i].is_overheat = true; mlxsw_env->module_info[i].module_overheat_counter++; - spin_unlock(&mlxsw_env->module_info_lock); + mutex_unlock(&mlxsw_env->module_info_lock); } } + + kfree(event); +} + +static void +mlxsw_env_mtwe_listener_func(const struct mlxsw_reg_info *reg, char *mtwe_pl, + void *priv) +{ + struct mlxsw_env_module_temp_warn_event *event; + struct mlxsw_env *mlxsw_env = priv; + + event = kmalloc(sizeof(*event), GFP_ATOMIC); + if (!event) + return; + + event->mlxsw_env = mlxsw_env; + memcpy(event->mtwe_pl, mtwe_pl, MLXSW_REG_MTWE_LEN); + INIT_WORK(&event->work, mlxsw_env_mtwe_event_work); + mlxsw_core_schedule_work(&event->work); } static const struct mlxsw_listener mlxsw_env_temp_warn_listener = - MLXSW_EVENTL(mlxsw_env_mtwe_event_func, MTWE, MTWE); + MLXSW_EVENTL(mlxsw_env_mtwe_listener_func, MTWE, MTWE); static int mlxsw_env_temp_warn_event_register(struct mlxsw_core *mlxsw_core) { @@ -568,9 +800,9 @@ static void mlxsw_env_pmpe_event_work(struct work_struct *work) work); mlxsw_env = event->mlxsw_env; - spin_lock_bh(&mlxsw_env->module_info_lock); + mutex_lock(&mlxsw_env->module_info_lock); mlxsw_env->module_info[event->module].is_overheat = false; - spin_unlock_bh(&mlxsw_env->module_info_lock); + mutex_unlock(&mlxsw_env->module_info_lock); err = mlxsw_env_module_has_temp_sensor(mlxsw_env->core, event->module, &has_temp_sensor); @@ -652,8 +884,10 @@ mlxsw_env_module_oper_state_event_enable(struct mlxsw_core *mlxsw_core, for (i = 0; i < module_count; i++) { char pmaos_pl[MLXSW_REG_PMAOS_LEN]; - mlxsw_reg_pmaos_pack(pmaos_pl, i, - MLXSW_REG_PMAOS_E_GENERATE_EVENT); + mlxsw_reg_pmaos_pack(pmaos_pl, i); + mlxsw_reg_pmaos_e_set(pmaos_pl, + MLXSW_REG_PMAOS_E_GENERATE_EVENT); + mlxsw_reg_pmaos_ee_set(pmaos_pl, true); err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(pmaos), pmaos_pl); if (err) return err; @@ -667,29 +901,110 @@ mlxsw_env_module_overheat_counter_get(struct mlxsw_core *mlxsw_core, u8 module, { struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core); - /* Prevent switch driver from accessing uninitialized data. */ - if (!mlxsw_core_is_initialized(mlxsw_core)) { - *p_counter = 0; - return 0; - } - if (WARN_ON_ONCE(module >= mlxsw_env->module_count)) return -EINVAL; - spin_lock_bh(&mlxsw_env->module_info_lock); + mutex_lock(&mlxsw_env->module_info_lock); *p_counter = mlxsw_env->module_info[module].module_overheat_counter; - spin_unlock_bh(&mlxsw_env->module_info_lock); + mutex_unlock(&mlxsw_env->module_info_lock); return 0; } EXPORT_SYMBOL(mlxsw_env_module_overheat_counter_get); +void mlxsw_env_module_port_map(struct mlxsw_core *mlxsw_core, u8 module) +{ + struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core); + + if (WARN_ON_ONCE(module >= mlxsw_env->module_count)) + return; + + mutex_lock(&mlxsw_env->module_info_lock); + mlxsw_env->module_info[module].num_ports_mapped++; + mutex_unlock(&mlxsw_env->module_info_lock); +} +EXPORT_SYMBOL(mlxsw_env_module_port_map); + +void mlxsw_env_module_port_unmap(struct mlxsw_core *mlxsw_core, u8 module) +{ + struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core); + + if (WARN_ON_ONCE(module >= mlxsw_env->module_count)) + return; + + mutex_lock(&mlxsw_env->module_info_lock); + mlxsw_env->module_info[module].num_ports_mapped--; + mutex_unlock(&mlxsw_env->module_info_lock); +} +EXPORT_SYMBOL(mlxsw_env_module_port_unmap); + +int mlxsw_env_module_port_up(struct mlxsw_core *mlxsw_core, u8 module) +{ + struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core); + int err = 0; + + if (WARN_ON_ONCE(module >= mlxsw_env->module_count)) + return -EINVAL; + + mutex_lock(&mlxsw_env->module_info_lock); + + if (mlxsw_env->module_info[module].power_mode_policy != + ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO) + goto out_inc; + + if (mlxsw_env->module_info[module].num_ports_up != 0) + goto out_inc; + + /* Transition to high power mode following first port using the module + * being put administratively up. + */ + err = __mlxsw_env_set_module_power_mode(mlxsw_core, module, false, + NULL); + if (err) + goto out_unlock; + +out_inc: + mlxsw_env->module_info[module].num_ports_up++; +out_unlock: + mutex_unlock(&mlxsw_env->module_info_lock); + return err; +} +EXPORT_SYMBOL(mlxsw_env_module_port_up); + +void mlxsw_env_module_port_down(struct mlxsw_core *mlxsw_core, u8 module) +{ + struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core); + + if (WARN_ON_ONCE(module >= mlxsw_env->module_count)) + return; + + mutex_lock(&mlxsw_env->module_info_lock); + + mlxsw_env->module_info[module].num_ports_up--; + + if (mlxsw_env->module_info[module].power_mode_policy != + ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO) + goto out_unlock; + + if (mlxsw_env->module_info[module].num_ports_up != 0) + goto out_unlock; + + /* Transition to low power mode following last port using the module + * being put administratively down. + */ + __mlxsw_env_set_module_power_mode(mlxsw_core, module, true, NULL); + +out_unlock: + mutex_unlock(&mlxsw_env->module_info_lock); +} +EXPORT_SYMBOL(mlxsw_env_module_port_down); + int mlxsw_env_init(struct mlxsw_core *mlxsw_core, struct mlxsw_env **p_env) { char mgpir_pl[MLXSW_REG_MGPIR_LEN]; struct mlxsw_env *env; u8 module_count; - int err; + int i, err; mlxsw_reg_mgpir_pack(mgpir_pl); err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mgpir), mgpir_pl); @@ -702,7 +1017,14 @@ int mlxsw_env_init(struct mlxsw_core *mlxsw_core, struct mlxsw_env **p_env) if (!env) return -ENOMEM; - spin_lock_init(&env->module_info_lock); + /* Firmware defaults to high power mode policy where modules are + * transitioned to high power mode following plug-in. + */ + for (i = 0; i < module_count; i++) + env->module_info[i].power_mode_policy = + ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH; + + mutex_init(&env->module_info_lock); env->core = mlxsw_core; env->module_count = module_count; *p_env = env; @@ -732,6 +1054,7 @@ err_oper_state_event_enable: err_module_plug_event_register: mlxsw_env_temp_warn_event_unregister(env); err_temp_warn_event_register: + mutex_destroy(&env->module_info_lock); kfree(env); return err; } @@ -742,5 +1065,6 @@ void mlxsw_env_fini(struct mlxsw_env *env) /* Make sure there is no more event work scheduled. */ mlxsw_core_flush_owq(); mlxsw_env_temp_warn_event_unregister(env); + mutex_destroy(&env->module_info_lock); kfree(env); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.h b/drivers/net/ethernet/mellanox/mlxsw/core_env.h index 0bf5bd0f8a7e..da121b1a84b4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_env.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.h @@ -24,9 +24,32 @@ mlxsw_env_get_module_eeprom_by_page(struct mlxsw_core *mlxsw_core, u8 module, const struct ethtool_module_eeprom *page, struct netlink_ext_ack *extack); +int mlxsw_env_reset_module(struct net_device *netdev, + struct mlxsw_core *mlxsw_core, u8 module, + u32 *flags); + +int +mlxsw_env_get_module_power_mode(struct mlxsw_core *mlxsw_core, u8 module, + struct ethtool_module_power_mode_params *params, + struct netlink_ext_ack *extack); + +int +mlxsw_env_set_module_power_mode(struct mlxsw_core *mlxsw_core, u8 module, + enum ethtool_module_power_mode_policy policy, + struct netlink_ext_ack *extack); + int mlxsw_env_module_overheat_counter_get(struct mlxsw_core *mlxsw_core, u8 module, u64 *p_counter); + +void mlxsw_env_module_port_map(struct mlxsw_core *mlxsw_core, u8 module); + +void mlxsw_env_module_port_unmap(struct mlxsw_core *mlxsw_core, u8 module); + +int mlxsw_env_module_port_up(struct mlxsw_core *mlxsw_core, u8 module); + +void mlxsw_env_module_port_down(struct mlxsw_core *mlxsw_core, u8 module); + int mlxsw_env_init(struct mlxsw_core *core, struct mlxsw_env **p_env); void mlxsw_env_fini(struct mlxsw_env *env); diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c index d9d56c44e994..e0892f259adf 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c @@ -54,8 +54,20 @@ static int mlxsw_m_base_mac_get(struct mlxsw_m *mlxsw_m) return 0; } -static int mlxsw_m_port_dummy_open_stop(struct net_device *dev) +static int mlxsw_m_port_open(struct net_device *dev) { + struct mlxsw_m_port *mlxsw_m_port = netdev_priv(dev); + struct mlxsw_m *mlxsw_m = mlxsw_m_port->mlxsw_m; + + return mlxsw_env_module_port_up(mlxsw_m->core, mlxsw_m_port->module); +} + +static int mlxsw_m_port_stop(struct net_device *dev) +{ + struct mlxsw_m_port *mlxsw_m_port = netdev_priv(dev); + struct mlxsw_m *mlxsw_m = mlxsw_m_port->mlxsw_m; + + mlxsw_env_module_port_down(mlxsw_m->core, mlxsw_m_port->module); return 0; } @@ -70,8 +82,8 @@ mlxsw_m_port_get_devlink_port(struct net_device *dev) } static const struct net_device_ops mlxsw_m_port_netdev_ops = { - .ndo_open = mlxsw_m_port_dummy_open_stop, - .ndo_stop = mlxsw_m_port_dummy_open_stop, + .ndo_open = mlxsw_m_port_open, + .ndo_stop = mlxsw_m_port_stop, .ndo_get_devlink_port = mlxsw_m_port_get_devlink_port, }; @@ -124,11 +136,47 @@ mlxsw_m_get_module_eeprom_by_page(struct net_device *netdev, page, extack); } +static int mlxsw_m_reset(struct net_device *netdev, u32 *flags) +{ + struct mlxsw_m_port *mlxsw_m_port = netdev_priv(netdev); + struct mlxsw_core *core = mlxsw_m_port->mlxsw_m->core; + + return mlxsw_env_reset_module(netdev, core, mlxsw_m_port->module, + flags); +} + +static int +mlxsw_m_get_module_power_mode(struct net_device *netdev, + struct ethtool_module_power_mode_params *params, + struct netlink_ext_ack *extack) +{ + struct mlxsw_m_port *mlxsw_m_port = netdev_priv(netdev); + struct mlxsw_core *core = mlxsw_m_port->mlxsw_m->core; + + return mlxsw_env_get_module_power_mode(core, mlxsw_m_port->module, + params, extack); +} + +static int +mlxsw_m_set_module_power_mode(struct net_device *netdev, + const struct ethtool_module_power_mode_params *params, + struct netlink_ext_ack *extack) +{ + struct mlxsw_m_port *mlxsw_m_port = netdev_priv(netdev); + struct mlxsw_core *core = mlxsw_m_port->mlxsw_m->core; + + return mlxsw_env_set_module_power_mode(core, mlxsw_m_port->module, + params->policy, extack); +} + static const struct ethtool_ops mlxsw_m_port_ethtool_ops = { .get_drvinfo = mlxsw_m_module_get_drvinfo, .get_module_info = mlxsw_m_get_module_info, .get_module_eeprom = mlxsw_m_get_module_eeprom, .get_module_eeprom_by_page = mlxsw_m_get_module_eeprom_by_page, + .reset = mlxsw_m_reset, + .get_module_power_mode = mlxsw_m_get_module_power_mode, + .set_module_power_mode = mlxsw_m_set_module_power_mode, }; static int @@ -266,6 +314,7 @@ static int mlxsw_m_port_module_map(struct mlxsw_m *mlxsw_m, u8 local_port, if (WARN_ON_ONCE(module >= max_ports)) return -EINVAL; + mlxsw_env_module_port_map(mlxsw_m->core, module); mlxsw_m->module_to_port[module] = ++mlxsw_m->max_ports; return 0; @@ -274,6 +323,7 @@ static int mlxsw_m_port_module_map(struct mlxsw_m *mlxsw_m, u8 local_port, static void mlxsw_m_port_module_unmap(struct mlxsw_m *mlxsw_m, u8 module) { mlxsw_m->module_to_port[module] = -1; + mlxsw_env_module_port_unmap(mlxsw_m->core, module); } static int mlxsw_m_ports_create(struct mlxsw_m *mlxsw_m) diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 6fbda6ebd590..ed6c3356e4eb 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -5681,6 +5681,14 @@ static inline void mlxsw_reg_pspa_pack(char *payload, u8 swid, u8 local_port) MLXSW_REG_DEFINE(pmaos, MLXSW_REG_PMAOS_ID, MLXSW_REG_PMAOS_LEN); +/* reg_pmaos_rst + * Module reset toggle. + * Note: Setting reset while module is plugged-in will result in transition to + * "initializing" operational state. + * Access: OP + */ +MLXSW_ITEM32(reg, pmaos, rst, 0x00, 31, 1); + /* reg_pmaos_slot_index * Slot index. * Access: Index @@ -5693,6 +5701,24 @@ MLXSW_ITEM32(reg, pmaos, slot_index, 0x00, 24, 4); */ MLXSW_ITEM32(reg, pmaos, module, 0x00, 16, 8); +enum mlxsw_reg_pmaos_admin_status { + MLXSW_REG_PMAOS_ADMIN_STATUS_ENABLED = 1, + MLXSW_REG_PMAOS_ADMIN_STATUS_DISABLED = 2, + /* If the module is active and then unplugged, or experienced an error + * event, the operational status should go to "disabled" and can only + * be enabled upon explicit enable command. + */ + MLXSW_REG_PMAOS_ADMIN_STATUS_ENABLED_ONCE = 3, +}; + +/* reg_pmaos_admin_status + * Module administrative state (the desired state of the module). + * Note: To disable a module, all ports associated with the port must be + * administatively down first. + * Access: RW + */ +MLXSW_ITEM32(reg, pmaos, admin_status, 0x00, 8, 4); + /* reg_pmaos_ase * Admin state update enable. * If this bit is set, admin state will be updated based on admin_state field. @@ -5721,13 +5747,10 @@ enum mlxsw_reg_pmaos_e { */ MLXSW_ITEM32(reg, pmaos, e, 0x04, 0, 2); -static inline void mlxsw_reg_pmaos_pack(char *payload, u8 module, - enum mlxsw_reg_pmaos_e e) +static inline void mlxsw_reg_pmaos_pack(char *payload, u8 module) { MLXSW_REG_ZERO(pmaos, payload); mlxsw_reg_pmaos_module_set(payload, module); - mlxsw_reg_pmaos_e_set(payload, e); - mlxsw_reg_pmaos_ee_set(payload, true); } /* PPLR - Port Physical Loopback Register @@ -5766,6 +5789,69 @@ static inline void mlxsw_reg_pplr_pack(char *payload, u8 local_port, MLXSW_REG_PPLR_LB_TYPE_BIT_PHY_LOCAL : 0); } +/* PMTDB - Port Module To local DataBase Register + * ---------------------------------------------- + * The PMTDB register allows to query the possible module<->local port + * mapping than can be used in PMLP. It does not represent the actual/current + * mapping of the local to module. Actual mapping is only defined by PMLP. + */ +#define MLXSW_REG_PMTDB_ID 0x501A +#define MLXSW_REG_PMTDB_LEN 0x40 + +MLXSW_REG_DEFINE(pmtdb, MLXSW_REG_PMTDB_ID, MLXSW_REG_PMTDB_LEN); + +/* reg_pmtdb_slot_index + * Slot index (0: Main board). + * Access: Index + */ +MLXSW_ITEM32(reg, pmtdb, slot_index, 0x00, 24, 4); + +/* reg_pmtdb_module + * Module number. + * Access: Index + */ +MLXSW_ITEM32(reg, pmtdb, module, 0x00, 16, 8); + +/* reg_pmtdb_ports_width + * Port's width + * Access: Index + */ +MLXSW_ITEM32(reg, pmtdb, ports_width, 0x00, 12, 4); + +/* reg_pmtdb_num_ports + * Number of ports in a single module (split/breakout) + * Access: Index + */ +MLXSW_ITEM32(reg, pmtdb, num_ports, 0x00, 8, 4); + +enum mlxsw_reg_pmtdb_status { + MLXSW_REG_PMTDB_STATUS_SUCCESS, +}; + +/* reg_pmtdb_status + * Status + * Access: RO + */ +MLXSW_ITEM32(reg, pmtdb, status, 0x00, 0, 4); + +/* reg_pmtdb_port_num + * The local_port value which can be assigned to the module. + * In case of more than one port, port<x> represent the /<x> port of + * the module. + * Access: RO + */ +MLXSW_ITEM16_INDEXED(reg, pmtdb, port_num, 0x04, 0, 8, 0x02, 0x00, false); + +static inline void mlxsw_reg_pmtdb_pack(char *payload, u8 slot_index, u8 module, + u8 ports_width, u8 num_ports) +{ + MLXSW_REG_ZERO(pmtdb, payload); + mlxsw_reg_pmtdb_slot_index_set(payload, slot_index); + mlxsw_reg_pmtdb_module_set(payload, module); + mlxsw_reg_pmtdb_ports_width_set(payload, ports_width); + mlxsw_reg_pmtdb_num_ports_set(payload, num_ports); +} + /* PMPE - Port Module Plug/Unplug Event Register * --------------------------------------------- * This register reports any operational status change of a module. @@ -5860,67 +5946,100 @@ static inline void mlxsw_reg_pddr_pack(char *payload, u8 local_port, mlxsw_reg_pddr_page_select_set(payload, page_select); } -/* PMTM - Port Module Type Mapping Register - * ---------------------------------------- - * The PMTM allows query or configuration of module types. +/* PMMP - Port Module Memory Map Properties Register + * ------------------------------------------------- + * The PMMP register allows to override the module memory map advertisement. + * The register can only be set when the module is disabled by PMAOS register. */ -#define MLXSW_REG_PMTM_ID 0x5067 -#define MLXSW_REG_PMTM_LEN 0x10 +#define MLXSW_REG_PMMP_ID 0x5044 +#define MLXSW_REG_PMMP_LEN 0x2C -MLXSW_REG_DEFINE(pmtm, MLXSW_REG_PMTM_ID, MLXSW_REG_PMTM_LEN); +MLXSW_REG_DEFINE(pmmp, MLXSW_REG_PMMP_ID, MLXSW_REG_PMMP_LEN); -/* reg_pmtm_module +/* reg_pmmp_module * Module number. * Access: Index */ -MLXSW_ITEM32(reg, pmtm, module, 0x00, 16, 8); +MLXSW_ITEM32(reg, pmmp, module, 0x00, 16, 8); + +/* reg_pmmp_sticky + * When set, will keep eeprom_override values after plug-out event. + * Access: OP + */ +MLXSW_ITEM32(reg, pmmp, sticky, 0x00, 0, 1); + +/* reg_pmmp_eeprom_override_mask + * Write mask bit (negative polarity). + * 0 - Allow write + * 1 - Ignore write + * On write, indicates which of the bits from eeprom_override field are + * updated. + * Access: WO + */ +MLXSW_ITEM32(reg, pmmp, eeprom_override_mask, 0x04, 16, 16); -enum mlxsw_reg_pmtm_module_type { - /* Backplane with 4 lanes */ - MLXSW_REG_PMTM_MODULE_TYPE_BP_4X, - /* QSFP */ - MLXSW_REG_PMTM_MODULE_TYPE_QSFP, - /* SFP */ - MLXSW_REG_PMTM_MODULE_TYPE_SFP, - /* Backplane with single lane */ - MLXSW_REG_PMTM_MODULE_TYPE_BP_1X = 4, - /* Backplane with two lane */ - MLXSW_REG_PMTM_MODULE_TYPE_BP_2X = 8, - /* Chip2Chip4x */ - MLXSW_REG_PMTM_MODULE_TYPE_C2C4X = 10, - /* Chip2Chip2x */ - MLXSW_REG_PMTM_MODULE_TYPE_C2C2X, - /* Chip2Chip1x */ - MLXSW_REG_PMTM_MODULE_TYPE_C2C1X, - /* QSFP-DD */ - MLXSW_REG_PMTM_MODULE_TYPE_QSFP_DD = 14, - /* OSFP */ - MLXSW_REG_PMTM_MODULE_TYPE_OSFP, - /* SFP-DD */ - MLXSW_REG_PMTM_MODULE_TYPE_SFP_DD, - /* DSFP */ - MLXSW_REG_PMTM_MODULE_TYPE_DSFP, - /* Chip2Chip8x */ - MLXSW_REG_PMTM_MODULE_TYPE_C2C8X, +enum { + /* Set module to low power mode */ + MLXSW_REG_PMMP_EEPROM_OVERRIDE_LOW_POWER_MASK = BIT(8), }; -/* reg_pmtm_module_type - * Module type. +/* reg_pmmp_eeprom_override + * Override / ignore EEPROM advertisement properties bitmask * Access: RW */ -MLXSW_ITEM32(reg, pmtm, module_type, 0x04, 0, 4); +MLXSW_ITEM32(reg, pmmp, eeprom_override, 0x04, 0, 16); -static inline void mlxsw_reg_pmtm_pack(char *payload, u8 module) +static inline void mlxsw_reg_pmmp_pack(char *payload, u8 module) { - MLXSW_REG_ZERO(pmtm, payload); - mlxsw_reg_pmtm_module_set(payload, module); + MLXSW_REG_ZERO(pmmp, payload); + mlxsw_reg_pmmp_module_set(payload, module); } -static inline void -mlxsw_reg_pmtm_unpack(char *payload, - enum mlxsw_reg_pmtm_module_type *module_type) +/* PLLP - Port Local port to Label Port mapping Register + * ----------------------------------------------------- + * The PLLP register returns the mapping from Local Port into Label Port. + */ +#define MLXSW_REG_PLLP_ID 0x504A +#define MLXSW_REG_PLLP_LEN 0x10 + +MLXSW_REG_DEFINE(pllp, MLXSW_REG_PLLP_ID, MLXSW_REG_PLLP_LEN); + +/* reg_pllp_local_port + * Local port number. + * Access: Index + */ +MLXSW_ITEM32(reg, pllp, local_port, 0x00, 16, 8); + +/* reg_pllp_label_port + * Front panel label of the port. + * Access: RO + */ +MLXSW_ITEM32(reg, pllp, label_port, 0x00, 0, 8); + +/* reg_pllp_split_num + * Label split mapping for local_port. + * Access: RO + */ +MLXSW_ITEM32(reg, pllp, split_num, 0x04, 0, 4); + +/* reg_pllp_slot_index + * Slot index (0: Main board). + * Access: RO + */ +MLXSW_ITEM32(reg, pllp, slot_index, 0x08, 0, 4); + +static inline void mlxsw_reg_pllp_pack(char *payload, u8 local_port) { - *module_type = mlxsw_reg_pmtm_module_type_get(payload); + MLXSW_REG_ZERO(pllp, payload); + mlxsw_reg_pllp_local_port_set(payload, local_port); +} + +static inline void mlxsw_reg_pllp_unpack(char *payload, u8 *label_port, + u8 *split_num, u8 *slot_index) +{ + *label_port = mlxsw_reg_pllp_label_port_get(payload); + *split_num = mlxsw_reg_pllp_split_num_get(payload); + *slot_index = mlxsw_reg_pllp_slot_index_get(payload); } /* HTGT - Host Trap Group Table @@ -6664,6 +6783,23 @@ mlxsw_reg_ritr_loopback_ipip4_pack(char *payload, mlxsw_reg_ritr_loopback_ipip_usip4_set(payload, usip); } +static inline void +mlxsw_reg_ritr_loopback_ipip6_pack(char *payload, + enum mlxsw_reg_ritr_loopback_ipip_type ipip_type, + enum mlxsw_reg_ritr_loopback_ipip_options options, + u16 uvr_id, u16 underlay_rif, + const struct in6_addr *usip, u32 gre_key) +{ + enum mlxsw_reg_ritr_loopback_protocol protocol = + MLXSW_REG_RITR_LOOPBACK_PROTOCOL_IPIP_IPV6; + + mlxsw_reg_ritr_loopback_protocol_set(payload, protocol); + mlxsw_reg_ritr_loopback_ipip_common_pack(payload, ipip_type, options, + uvr_id, underlay_rif, gre_key); + mlxsw_reg_ritr_loopback_ipip_usip6_memcpy_to(payload, + (const char *)usip); +} + /* RTAR - Router TCAM Allocation Register * -------------------------------------- * This register is used for allocation of regions in the TCAM table. @@ -6932,6 +7068,12 @@ static inline void mlxsw_reg_ratr_ipip4_entry_pack(char *payload, u32 ipv4_udip) mlxsw_reg_ratr_ipip_ipv4_udip_set(payload, ipv4_udip); } +static inline void mlxsw_reg_ratr_ipip6_entry_pack(char *payload, u32 ipv6_ptr) +{ + mlxsw_reg_ratr_ipip_type_set(payload, MLXSW_REG_RATR_IPIP_TYPE_IPV6); + mlxsw_reg_ratr_ipip_ipv6_ptr_set(payload, ipv6_ptr); +} + static inline void mlxsw_reg_ratr_counter_pack(char *payload, u64 counter_index, bool counter_enable) { @@ -8117,19 +8259,71 @@ static inline void mlxsw_reg_rtdp_pack(char *payload, } static inline void -mlxsw_reg_rtdp_ipip4_pack(char *payload, u16 irif, - enum mlxsw_reg_rtdp_ipip_sip_check sip_check, - unsigned int type_check, bool gre_key_check, - u32 ipv4_usip, u32 expected_gre_key) +mlxsw_reg_rtdp_ipip_pack(char *payload, u16 irif, + enum mlxsw_reg_rtdp_ipip_sip_check sip_check, + unsigned int type_check, bool gre_key_check, + u32 expected_gre_key) { mlxsw_reg_rtdp_ipip_irif_set(payload, irif); mlxsw_reg_rtdp_ipip_sip_check_set(payload, sip_check); mlxsw_reg_rtdp_ipip_type_check_set(payload, type_check); mlxsw_reg_rtdp_ipip_gre_key_check_set(payload, gre_key_check); - mlxsw_reg_rtdp_ipip_ipv4_usip_set(payload, ipv4_usip); mlxsw_reg_rtdp_ipip_expected_gre_key_set(payload, expected_gre_key); } +static inline void +mlxsw_reg_rtdp_ipip4_pack(char *payload, u16 irif, + enum mlxsw_reg_rtdp_ipip_sip_check sip_check, + unsigned int type_check, bool gre_key_check, + u32 ipv4_usip, u32 expected_gre_key) +{ + mlxsw_reg_rtdp_ipip_pack(payload, irif, sip_check, type_check, + gre_key_check, expected_gre_key); + mlxsw_reg_rtdp_ipip_ipv4_usip_set(payload, ipv4_usip); +} + +static inline void +mlxsw_reg_rtdp_ipip6_pack(char *payload, u16 irif, + enum mlxsw_reg_rtdp_ipip_sip_check sip_check, + unsigned int type_check, bool gre_key_check, + u32 ipv6_usip_ptr, u32 expected_gre_key) +{ + mlxsw_reg_rtdp_ipip_pack(payload, irif, sip_check, type_check, + gre_key_check, expected_gre_key); + mlxsw_reg_rtdp_ipip_ipv6_usip_ptr_set(payload, ipv6_usip_ptr); +} + +/* RIPS - Router IP version Six Register + * ------------------------------------- + * The RIPS register is used to store IPv6 addresses for use by the NVE and + * IPinIP + */ +#define MLXSW_REG_RIPS_ID 0x8021 +#define MLXSW_REG_RIPS_LEN 0x14 + +MLXSW_REG_DEFINE(rips, MLXSW_REG_RIPS_ID, MLXSW_REG_RIPS_LEN); + +/* reg_rips_index + * Index to IPv6 address. + * For Spectrum, the index is to the KVD linear. + * Access: Index + */ +MLXSW_ITEM32(reg, rips, index, 0x00, 0, 24); + +/* reg_rips_ipv6 + * IPv6 address + * Access: RW + */ +MLXSW_ITEM_BUF(reg, rips, ipv6, 0x04, 16); + +static inline void mlxsw_reg_rips_pack(char *payload, u32 index, + const struct in6_addr *ipv6) +{ + MLXSW_REG_ZERO(rips, payload); + mlxsw_reg_rips_index_set(payload, index); + mlxsw_reg_rips_ipv6_memcpy_to(payload, (const char *)ipv6); +} + /* RATRAD - Router Adjacency Table Activity Dump Register * ------------------------------------------------------ * The RATRAD register is used to dump and optionally clear activity bits of @@ -10208,6 +10402,39 @@ static inline void mlxsw_reg_mlcr_pack(char *payload, u8 local_port, MLXSW_REG_MLCR_DURATION_MAX : 0); } +/* MCION - Management Cable IO and Notifications Register + * ------------------------------------------------------ + * The MCION register is used to query transceiver modules' IO pins and other + * notifications. + */ +#define MLXSW_REG_MCION_ID 0x9052 +#define MLXSW_REG_MCION_LEN 0x18 + +MLXSW_REG_DEFINE(mcion, MLXSW_REG_MCION_ID, MLXSW_REG_MCION_LEN); + +/* reg_mcion_module + * Module number. + * Access: Index + */ +MLXSW_ITEM32(reg, mcion, module, 0x00, 16, 8); + +enum { + MLXSW_REG_MCION_MODULE_STATUS_BITS_PRESENT_MASK = BIT(0), + MLXSW_REG_MCION_MODULE_STATUS_BITS_LOW_POWER_MASK = BIT(8), +}; + +/* reg_mcion_module_status_bits + * Module IO status as defined by SFF. + * Access: RO + */ +MLXSW_ITEM32(reg, mcion, module_status_bits, 0x04, 0, 16); + +static inline void mlxsw_reg_mcion_pack(char *payload, u8 module) +{ + MLXSW_REG_ZERO(mcion, payload); + mlxsw_reg_mcion_module_set(payload, module); +} + /* MTPPS - Management Pulse Per Second Register * -------------------------------------------- * This register provides the device PPS capabilities, configure the PPS in and @@ -12200,9 +12427,11 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = { MLXSW_REG(pspa), MLXSW_REG(pmaos), MLXSW_REG(pplr), + MLXSW_REG(pmtdb), MLXSW_REG(pmpe), MLXSW_REG(pddr), - MLXSW_REG(pmtm), + MLXSW_REG(pmmp), + MLXSW_REG(pllp), MLXSW_REG(htgt), MLXSW_REG(hpkt), MLXSW_REG(rgcr), @@ -12210,6 +12439,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = { MLXSW_REG(rtar), MLXSW_REG(ratr), MLXSW_REG(rtdp), + MLXSW_REG(rips), MLXSW_REG(ratrad), MLXSW_REG(rdpm), MLXSW_REG(ricnt), @@ -12249,6 +12479,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = { MLXSW_REG(mgir), MLXSW_REG(mrsr), MLXSW_REG(mlcr), + MLXSW_REG(mcion), MLXSW_REG(mtpps), MLXSW_REG(mtutc), MLXSW_REG(mpsc), diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h index a56c9e19a390..a1512be77867 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/resources.h +++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h @@ -25,9 +25,6 @@ enum mlxsw_res_id { MLXSW_RES_ID_MAX_SYSTEM_PORT, MLXSW_RES_ID_MAX_LAG, MLXSW_RES_ID_MAX_LAG_MEMBERS, - MLXSW_RES_ID_LOCAL_PORTS_IN_1X, - MLXSW_RES_ID_LOCAL_PORTS_IN_2X, - MLXSW_RES_ID_LOCAL_PORTS_IN_4X, MLXSW_RES_ID_GUARANTEED_SHARED_BUFFER, MLXSW_RES_ID_CELL_SIZE, MLXSW_RES_ID_MAX_HEADROOM_SIZE, @@ -84,9 +81,6 @@ static u16 mlxsw_res_ids[] = { [MLXSW_RES_ID_MAX_SYSTEM_PORT] = 0x2502, [MLXSW_RES_ID_MAX_LAG] = 0x2520, [MLXSW_RES_ID_MAX_LAG_MEMBERS] = 0x2521, - [MLXSW_RES_ID_LOCAL_PORTS_IN_1X] = 0x2610, - [MLXSW_RES_ID_LOCAL_PORTS_IN_2X] = 0x2611, - [MLXSW_RES_ID_LOCAL_PORTS_IN_4X] = 0x2612, [MLXSW_RES_ID_GUARANTEED_SHARED_BUFFER] = 0x2805, /* Bytes */ [MLXSW_RES_ID_CELL_SIZE] = 0x2803, /* Bytes */ [MLXSW_RES_ID_MAX_HEADROOM_SIZE] = 0x2811, /* Bytes */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 250c5a24264d..d366786ce0f8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -47,7 +47,7 @@ #define MLXSW_SP1_FWREV_MAJOR 13 #define MLXSW_SP1_FWREV_MINOR 2008 -#define MLXSW_SP1_FWREV_SUBMINOR 2406 +#define MLXSW_SP1_FWREV_SUBMINOR 3326 #define MLXSW_SP1_FWREV_CAN_RESET_MINOR 1702 static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = { @@ -64,7 +64,7 @@ static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = { #define MLXSW_SP2_FWREV_MAJOR 29 #define MLXSW_SP2_FWREV_MINOR 2008 -#define MLXSW_SP2_FWREV_SUBMINOR 2406 +#define MLXSW_SP2_FWREV_SUBMINOR 3326 static const struct mlxsw_fw_rev mlxsw_sp2_fw_rev = { .major = MLXSW_SP2_FWREV_MAJOR, @@ -79,7 +79,7 @@ static const struct mlxsw_fw_rev mlxsw_sp2_fw_rev = { #define MLXSW_SP3_FWREV_MAJOR 30 #define MLXSW_SP3_FWREV_MINOR 2008 -#define MLXSW_SP3_FWREV_SUBMINOR 2406 +#define MLXSW_SP3_FWREV_SUBMINOR 3326 static const struct mlxsw_fw_rev mlxsw_sp3_fw_rev = { .major = MLXSW_SP3_FWREV_MAJOR, @@ -351,12 +351,12 @@ static int mlxsw_sp_port_mtu_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 mtu) return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pmtu), pmtu_pl); } -static int mlxsw_sp_port_swid_set(struct mlxsw_sp_port *mlxsw_sp_port, u8 swid) +static int mlxsw_sp_port_swid_set(struct mlxsw_sp *mlxsw_sp, + u8 local_port, u8 swid) { - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; char pspa_pl[MLXSW_REG_PSPA_LEN]; - mlxsw_reg_pspa_pack(pspa_pl, swid, mlxsw_sp_port->local_port); + mlxsw_reg_pspa_pack(pspa_pl, swid, local_port); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pspa), pspa_pl); } @@ -529,55 +529,80 @@ mlxsw_sp_port_module_info_get(struct mlxsw_sp *mlxsw_sp, u8 local_port, port_mapping->module = module; port_mapping->width = width; + port_mapping->module_width = width; port_mapping->lane = mlxsw_reg_pmlp_tx_lane_get(pmlp_pl, 0); return 0; } -static int mlxsw_sp_port_module_map(struct mlxsw_sp_port *mlxsw_sp_port) +static int +mlxsw_sp_port_module_map(struct mlxsw_sp *mlxsw_sp, u8 local_port, + const struct mlxsw_sp_port_mapping *port_mapping) { - struct mlxsw_sp_port_mapping *port_mapping = &mlxsw_sp_port->mapping; - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; char pmlp_pl[MLXSW_REG_PMLP_LEN]; - int i; + int i, err; + + mlxsw_env_module_port_map(mlxsw_sp->core, port_mapping->module); - mlxsw_reg_pmlp_pack(pmlp_pl, mlxsw_sp_port->local_port); + mlxsw_reg_pmlp_pack(pmlp_pl, local_port); mlxsw_reg_pmlp_width_set(pmlp_pl, port_mapping->width); for (i = 0; i < port_mapping->width; i++) { mlxsw_reg_pmlp_module_set(pmlp_pl, i, port_mapping->module); mlxsw_reg_pmlp_tx_lane_set(pmlp_pl, i, port_mapping->lane + i); /* Rx & Tx */ } - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pmlp), pmlp_pl); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pmlp), pmlp_pl); + if (err) + goto err_pmlp_write; + return 0; + +err_pmlp_write: + mlxsw_env_module_port_unmap(mlxsw_sp->core, port_mapping->module); + return err; } -static int mlxsw_sp_port_module_unmap(struct mlxsw_sp_port *mlxsw_sp_port) +static void mlxsw_sp_port_module_unmap(struct mlxsw_sp *mlxsw_sp, u8 local_port, + u8 module) { - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; char pmlp_pl[MLXSW_REG_PMLP_LEN]; - mlxsw_reg_pmlp_pack(pmlp_pl, mlxsw_sp_port->local_port); + mlxsw_reg_pmlp_pack(pmlp_pl, local_port); mlxsw_reg_pmlp_width_set(pmlp_pl, 0); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pmlp), pmlp_pl); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pmlp), pmlp_pl); + mlxsw_env_module_port_unmap(mlxsw_sp->core, module); } static int mlxsw_sp_port_open(struct net_device *dev) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; int err; - err = mlxsw_sp_port_admin_status_set(mlxsw_sp_port, true); + err = mlxsw_env_module_port_up(mlxsw_sp->core, + mlxsw_sp_port->mapping.module); if (err) return err; + err = mlxsw_sp_port_admin_status_set(mlxsw_sp_port, true); + if (err) + goto err_port_admin_status_set; netif_start_queue(dev); return 0; + +err_port_admin_status_set: + mlxsw_env_module_port_down(mlxsw_sp->core, + mlxsw_sp_port->mapping.module); + return err; } static int mlxsw_sp_port_stop(struct net_device *dev) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; netif_stop_queue(dev); - return mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false); + mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false); + mlxsw_env_module_port_down(mlxsw_sp->core, + mlxsw_sp_port->mapping.module); + return 0; } static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb, @@ -649,7 +674,7 @@ static int mlxsw_sp_port_set_mac_address(struct net_device *dev, void *p) err = mlxsw_sp_port_dev_addr_set(mlxsw_sp_port, addr->sa_data); if (err) return err; - memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); + eth_hw_addr_set(dev, addr->sa_data); return 0; } @@ -1442,29 +1467,68 @@ mlxsw_sp_port_vlan_classification_set(struct mlxsw_sp_port *mlxsw_sp_port, return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spvc), spvc_pl); } +static int mlxsw_sp_port_label_info_get(struct mlxsw_sp *mlxsw_sp, + u8 local_port, u8 *port_number, + u8 *split_port_subnumber, + u8 *slot_index) +{ + char pllp_pl[MLXSW_REG_PLLP_LEN]; + int err; + + mlxsw_reg_pllp_pack(pllp_pl, local_port); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(pllp), pllp_pl); + if (err) + return err; + mlxsw_reg_pllp_unpack(pllp_pl, port_number, + split_port_subnumber, slot_index); + return 0; +} + static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, - u8 split_base_local_port, + bool split, struct mlxsw_sp_port_mapping *port_mapping) { struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; - bool split = !!split_base_local_port; struct mlxsw_sp_port *mlxsw_sp_port; u32 lanes = port_mapping->width; + u8 split_port_subnumber; struct net_device *dev; + u8 port_number; + u8 slot_index; bool splittable; int err; + err = mlxsw_sp_port_module_map(mlxsw_sp, local_port, port_mapping); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to map module\n", + local_port); + return err; + } + + err = mlxsw_sp_port_swid_set(mlxsw_sp, local_port, 0); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set SWID\n", + local_port); + goto err_port_swid_set; + } + + err = mlxsw_sp_port_label_info_get(mlxsw_sp, local_port, &port_number, + &split_port_subnumber, &slot_index); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to get port label information\n", + local_port); + goto err_port_label_info_get; + } + splittable = lanes > 1 && !split; err = mlxsw_core_port_init(mlxsw_sp->core, local_port, - port_mapping->module + 1, split, - port_mapping->lane / lanes, - splittable, lanes, - mlxsw_sp->base_mac, + port_number, split, split_port_subnumber, + splittable, lanes, mlxsw_sp->base_mac, sizeof(mlxsw_sp->base_mac)); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to init core port\n", local_port); - return err; + goto err_core_port_init; } dev = alloc_etherdev(sizeof(struct mlxsw_sp_port)); @@ -1480,7 +1544,6 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, mlxsw_sp_port->local_port = local_port; mlxsw_sp_port->pvid = MLXSW_SP_DEFAULT_VID; mlxsw_sp_port->split = split; - mlxsw_sp_port->split_base_local_port = split_base_local_port; mlxsw_sp_port->mapping = *port_mapping; mlxsw_sp_port->link.autoneg = 1; INIT_LIST_HEAD(&mlxsw_sp_port->vlans_list); @@ -1498,20 +1561,6 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, dev->netdev_ops = &mlxsw_sp_port_netdev_ops; dev->ethtool_ops = &mlxsw_sp_port_ethtool_ops; - err = mlxsw_sp_port_module_map(mlxsw_sp_port); - if (err) { - dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to map module\n", - mlxsw_sp_port->local_port); - goto err_port_module_map; - } - - err = mlxsw_sp_port_swid_set(mlxsw_sp_port, 0); - if (err) { - dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set SWID\n", - mlxsw_sp_port->local_port); - goto err_port_swid_set; - } - err = mlxsw_sp_port_dev_addr_init(mlxsw_sp_port); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Port %d: Unable to init port mac address\n", @@ -1712,21 +1761,24 @@ err_max_speed_get: err_port_speed_by_width_set: err_port_system_port_mapping_set: err_dev_addr_init: - mlxsw_sp_port_swid_set(mlxsw_sp_port, MLXSW_PORT_SWID_DISABLED_PORT); -err_port_swid_set: - mlxsw_sp_port_module_unmap(mlxsw_sp_port); -err_port_module_map: free_percpu(mlxsw_sp_port->pcpu_stats); err_alloc_stats: free_netdev(dev); err_alloc_etherdev: mlxsw_core_port_fini(mlxsw_sp->core, local_port); +err_core_port_init: +err_port_label_info_get: + mlxsw_sp_port_swid_set(mlxsw_sp, local_port, + MLXSW_PORT_SWID_DISABLED_PORT); +err_port_swid_set: + mlxsw_sp_port_module_unmap(mlxsw_sp, local_port, port_mapping->module); return err; } static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port) { struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp->ports[local_port]; + u8 module = mlxsw_sp_port->mapping.module; cancel_delayed_work_sync(&mlxsw_sp_port->periodic_hw_stats.update_dw); cancel_delayed_work_sync(&mlxsw_sp_port->ptp.shaper_dw); @@ -1742,12 +1794,13 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port) mlxsw_sp_port_dcb_fini(mlxsw_sp_port); mlxsw_sp_port_tc_mc_mode_set(mlxsw_sp_port, false); mlxsw_sp_port_buffers_fini(mlxsw_sp_port); - mlxsw_sp_port_swid_set(mlxsw_sp_port, MLXSW_PORT_SWID_DISABLED_PORT); - mlxsw_sp_port_module_unmap(mlxsw_sp_port); free_percpu(mlxsw_sp_port->pcpu_stats); WARN_ON_ONCE(!list_empty(&mlxsw_sp_port->vlans_list)); free_netdev(mlxsw_sp_port->dev); mlxsw_core_port_fini(mlxsw_sp->core, local_port); + mlxsw_sp_port_swid_set(mlxsw_sp, local_port, + MLXSW_PORT_SWID_DISABLED_PORT); + mlxsw_sp_port_module_unmap(mlxsw_sp, local_port, module); } static int mlxsw_sp_cpu_port_create(struct mlxsw_sp *mlxsw_sp) @@ -1789,8 +1842,15 @@ static void mlxsw_sp_cpu_port_remove(struct mlxsw_sp *mlxsw_sp) kfree(mlxsw_sp_port); } +static bool mlxsw_sp_local_port_valid(u8 local_port) +{ + return local_port != MLXSW_PORT_CPU_PORT; +} + static bool mlxsw_sp_port_created(struct mlxsw_sp *mlxsw_sp, u8 local_port) { + if (!mlxsw_sp_local_port_valid(local_port)) + return false; return mlxsw_sp->ports[local_port] != NULL; } @@ -1827,7 +1887,7 @@ static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp) port_mapping = mlxsw_sp->port_mapping[i]; if (!port_mapping) continue; - err = mlxsw_sp_port_create(mlxsw_sp, i, 0, port_mapping); + err = mlxsw_sp_port_create(mlxsw_sp, i, false, port_mapping); if (err) goto err_port_create; } @@ -1894,17 +1954,10 @@ static void mlxsw_sp_port_module_info_fini(struct mlxsw_sp *mlxsw_sp) kfree(mlxsw_sp->port_mapping); } -static u8 mlxsw_sp_cluster_base_port_get(u8 local_port, unsigned int max_width) -{ - u8 offset = (local_port - 1) % max_width; - - return local_port - offset; -} - static int -mlxsw_sp_port_split_create(struct mlxsw_sp *mlxsw_sp, u8 base_port, +mlxsw_sp_port_split_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_port_mapping *port_mapping, - unsigned int count, u8 offset) + unsigned int count, const char *pmtdb_pl) { struct mlxsw_sp_port_mapping split_port_mapping; int err, i; @@ -1912,8 +1965,13 @@ mlxsw_sp_port_split_create(struct mlxsw_sp *mlxsw_sp, u8 base_port, split_port_mapping = *port_mapping; split_port_mapping.width /= count; for (i = 0; i < count; i++) { - err = mlxsw_sp_port_create(mlxsw_sp, base_port + i * offset, - base_port, &split_port_mapping); + u8 s_local_port = mlxsw_reg_pmtdb_port_num_get(pmtdb_pl, i); + + if (!mlxsw_sp_local_port_valid(s_local_port)) + continue; + + err = mlxsw_sp_port_create(mlxsw_sp, s_local_port, + true, &split_port_mapping); if (err) goto err_port_create; split_port_mapping.lane += split_port_mapping.width; @@ -1922,49 +1980,34 @@ mlxsw_sp_port_split_create(struct mlxsw_sp *mlxsw_sp, u8 base_port, return 0; err_port_create: - for (i--; i >= 0; i--) - if (mlxsw_sp_port_created(mlxsw_sp, base_port + i * offset)) - mlxsw_sp_port_remove(mlxsw_sp, base_port + i * offset); + for (i--; i >= 0; i--) { + u8 s_local_port = mlxsw_reg_pmtdb_port_num_get(pmtdb_pl, i); + + if (mlxsw_sp_port_created(mlxsw_sp, s_local_port)) + mlxsw_sp_port_remove(mlxsw_sp, s_local_port); + } return err; } static void mlxsw_sp_port_unsplit_create(struct mlxsw_sp *mlxsw_sp, - u8 base_port, - unsigned int count, u8 offset) + unsigned int count, + const char *pmtdb_pl) { struct mlxsw_sp_port_mapping *port_mapping; int i; /* Go over original unsplit ports in the gap and recreate them. */ - for (i = 0; i < count * offset; i++) { - port_mapping = mlxsw_sp->port_mapping[base_port + i]; - if (!port_mapping) + for (i = 0; i < count; i++) { + u8 local_port = mlxsw_reg_pmtdb_port_num_get(pmtdb_pl, i); + + port_mapping = mlxsw_sp->port_mapping[local_port]; + if (!port_mapping || !mlxsw_sp_local_port_valid(local_port)) continue; - mlxsw_sp_port_create(mlxsw_sp, base_port + i, 0, port_mapping); + mlxsw_sp_port_create(mlxsw_sp, local_port, + false, port_mapping); } } -static int mlxsw_sp_local_ports_offset(struct mlxsw_core *mlxsw_core, - unsigned int count, - unsigned int max_width) -{ - enum mlxsw_res_id local_ports_in_x_res_id; - int split_width = max_width / count; - - if (split_width == 1) - local_ports_in_x_res_id = MLXSW_RES_ID_LOCAL_PORTS_IN_1X; - else if (split_width == 2) - local_ports_in_x_res_id = MLXSW_RES_ID_LOCAL_PORTS_IN_2X; - else if (split_width == 4) - local_ports_in_x_res_id = MLXSW_RES_ID_LOCAL_PORTS_IN_4X; - else - return -EINVAL; - - if (!mlxsw_core_res_valid(mlxsw_core, local_ports_in_x_res_id)) - return -EINVAL; - return mlxsw_core_res_get(mlxsw_core, local_ports_in_x_res_id); -} - static struct mlxsw_sp_port * mlxsw_sp_port_get_by_local_port(struct mlxsw_sp *mlxsw_sp, u8 local_port) { @@ -1980,9 +2023,8 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); struct mlxsw_sp_port_mapping port_mapping; struct mlxsw_sp_port *mlxsw_sp_port; - int max_width; - u8 base_port; - int offset; + enum mlxsw_reg_pmtdb_status status; + char pmtdb_pl[MLXSW_REG_PMTDB_LEN]; int i; int err; @@ -1994,57 +2036,37 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, return -EINVAL; } - max_width = mlxsw_core_module_max_width(mlxsw_core, - mlxsw_sp_port->mapping.module); - if (max_width < 0) { - netdev_err(mlxsw_sp_port->dev, "Cannot get max width of port module\n"); - NL_SET_ERR_MSG_MOD(extack, "Cannot get max width of port module"); - return max_width; + if (mlxsw_sp_port->split) { + NL_SET_ERR_MSG_MOD(extack, "Port is already split"); + return -EINVAL; } - /* Split port with non-max cannot be split. */ - if (mlxsw_sp_port->mapping.width != max_width) { - netdev_err(mlxsw_sp_port->dev, "Port cannot be split\n"); - NL_SET_ERR_MSG_MOD(extack, "Port cannot be split"); - return -EINVAL; + mlxsw_reg_pmtdb_pack(pmtdb_pl, 0, mlxsw_sp_port->mapping.module, + mlxsw_sp_port->mapping.module_width / count, + count); + err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(pmtdb), pmtdb_pl); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to query split info"); + return err; } - offset = mlxsw_sp_local_ports_offset(mlxsw_core, count, max_width); - if (offset < 0) { - netdev_err(mlxsw_sp_port->dev, "Cannot obtain local port offset\n"); - NL_SET_ERR_MSG_MOD(extack, "Cannot obtain local port offset"); + status = mlxsw_reg_pmtdb_status_get(pmtdb_pl); + if (status != MLXSW_REG_PMTDB_STATUS_SUCCESS) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported split configuration"); return -EINVAL; } - /* Only in case max split is being done, the local port and - * base port may differ. - */ - base_port = count == max_width ? - mlxsw_sp_cluster_base_port_get(local_port, max_width) : - local_port; + port_mapping = mlxsw_sp_port->mapping; - for (i = 0; i < count * offset; i++) { - /* Expect base port to exist and also the one in the middle in - * case of maximal split count. - */ - if (i == 0 || (count == max_width && i == count / 2)) - continue; + for (i = 0; i < count; i++) { + u8 s_local_port = mlxsw_reg_pmtdb_port_num_get(pmtdb_pl, i); - if (mlxsw_sp_port_created(mlxsw_sp, base_port + i)) { - netdev_err(mlxsw_sp_port->dev, "Invalid split configuration\n"); - NL_SET_ERR_MSG_MOD(extack, "Invalid split configuration"); - return -EINVAL; - } + if (mlxsw_sp_port_created(mlxsw_sp, s_local_port)) + mlxsw_sp_port_remove(mlxsw_sp, s_local_port); } - port_mapping = mlxsw_sp_port->mapping; - - for (i = 0; i < count; i++) - if (mlxsw_sp_port_created(mlxsw_sp, base_port + i * offset)) - mlxsw_sp_port_remove(mlxsw_sp, base_port + i * offset); - - err = mlxsw_sp_port_split_create(mlxsw_sp, base_port, &port_mapping, - count, offset); + err = mlxsw_sp_port_split_create(mlxsw_sp, &port_mapping, + count, pmtdb_pl); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to create split ports\n"); goto err_port_split_create; @@ -2053,7 +2075,7 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, return 0; err_port_split_create: - mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count, offset); + mlxsw_sp_port_unsplit_create(mlxsw_sp, count, pmtdb_pl); return err; } @@ -2062,11 +2084,10 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port, { struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); struct mlxsw_sp_port *mlxsw_sp_port; + char pmtdb_pl[MLXSW_REG_PMTDB_LEN]; unsigned int count; - int max_width; - u8 base_port; - int offset; int i; + int err; mlxsw_sp_port = mlxsw_sp_port_get_by_local_port(mlxsw_sp, local_port); if (!mlxsw_sp_port) { @@ -2077,35 +2098,30 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port, } if (!mlxsw_sp_port->split) { - netdev_err(mlxsw_sp_port->dev, "Port was not split\n"); NL_SET_ERR_MSG_MOD(extack, "Port was not split"); return -EINVAL; } - max_width = mlxsw_core_module_max_width(mlxsw_core, - mlxsw_sp_port->mapping.module); - if (max_width < 0) { - netdev_err(mlxsw_sp_port->dev, "Cannot get max width of port module\n"); - NL_SET_ERR_MSG_MOD(extack, "Cannot get max width of port module"); - return max_width; - } + count = mlxsw_sp_port->mapping.module_width / + mlxsw_sp_port->mapping.width; - count = max_width / mlxsw_sp_port->mapping.width; - - offset = mlxsw_sp_local_ports_offset(mlxsw_core, count, max_width); - if (WARN_ON(offset < 0)) { - netdev_err(mlxsw_sp_port->dev, "Cannot obtain local port offset\n"); - NL_SET_ERR_MSG_MOD(extack, "Cannot obtain local port offset"); - return -EINVAL; + mlxsw_reg_pmtdb_pack(pmtdb_pl, 0, mlxsw_sp_port->mapping.module, + mlxsw_sp_port->mapping.module_width / count, + count); + err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(pmtdb), pmtdb_pl); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to query split info"); + return err; } - base_port = mlxsw_sp_port->split_base_local_port; + for (i = 0; i < count; i++) { + u8 s_local_port = mlxsw_reg_pmtdb_port_num_get(pmtdb_pl, i); - for (i = 0; i < count; i++) - if (mlxsw_sp_port_created(mlxsw_sp, base_port + i * offset)) - mlxsw_sp_port_remove(mlxsw_sp, base_port + i * offset); + if (mlxsw_sp_port_created(mlxsw_sp, s_local_port)) + mlxsw_sp_port_remove(mlxsw_sp, s_local_port); + } - mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count, offset); + mlxsw_sp_port_unsplit_create(mlxsw_sp, count, pmtdb_pl); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 3a43cba6d23c..0ebbd9b04b89 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -144,7 +144,8 @@ struct mlxsw_sp_mall_entry; struct mlxsw_sp_port_mapping { u8 module; - u8 width; + u8 width; /* Number of lanes used by the port */ + u8 module_width; /* Number of lanes in the module (static) */ u8 lane; }; @@ -345,7 +346,6 @@ struct mlxsw_sp_port { u16 egr_types; struct mlxsw_sp_ptp_port_stats stats; } ptp; - u8 split_base_local_port; int max_mtu; u32 max_speed; struct mlxsw_sp_hdroom *hdroom; @@ -747,6 +747,7 @@ enum mlxsw_sp_kvdl_entry_type { MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET, MLXSW_SP_KVDL_ENTRY_TYPE_PBS, MLXSW_SP_KVDL_ENTRY_TYPE_MCRIGR, + MLXSW_SP_KVDL_ENTRY_TYPE_IPV6_ADDRESS, MLXSW_SP_KVDL_ENTRY_TYPE_TNUMT, }; @@ -758,6 +759,7 @@ mlxsw_sp_kvdl_entry_size(enum mlxsw_sp_kvdl_entry_type type) case MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET: case MLXSW_SP_KVDL_ENTRY_TYPE_PBS: case MLXSW_SP_KVDL_ENTRY_TYPE_MCRIGR: + case MLXSW_SP_KVDL_ENTRY_TYPE_IPV6_ADDRESS: case MLXSW_SP_KVDL_ENTRY_TYPE_TNUMT: default: return 1; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c index 3a73d654017f..10ae1115de6c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c @@ -35,6 +35,7 @@ static const struct mlxsw_sp2_kvdl_part_info mlxsw_sp2_kvdl_parts_info[] = { MAX_KVD_ACTION_SETS), MLXSW_SP2_KVDL_PART_INFO(PBS, 0x24, KVD_SIZE, KVD_SIZE), MLXSW_SP2_KVDL_PART_INFO(MCRIGR, 0x26, KVD_SIZE, KVD_SIZE), + MLXSW_SP2_KVDL_PART_INFO(IPV6_ADDRESS, 0x28, KVD_SIZE, KVD_SIZE), MLXSW_SP2_KVDL_PART_INFO(TNUMT, 0x29, KVD_SIZE, KVD_SIZE), }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 9de160e740b2..d78cf5a7220a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -1583,7 +1583,7 @@ int mlxsw_sp_sb_occ_snapshot(struct mlxsw_core *mlxsw_core, { struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); struct mlxsw_sp_sb_sr_occ_query_cb_ctx cb_ctx; - unsigned long cb_priv; + unsigned long cb_priv = 0; LIST_HEAD(bulk_list); char *sbsr_pl; u8 masked_count; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c index 267590a0eee7..84d4460f3dcd 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c @@ -96,6 +96,9 @@ mlxsw_sp_link_ext_state_opcode_map[] = { {1032, ETHTOOL_LINK_EXT_STATE_POWER_BUDGET_EXCEEDED, 0}, {1030, ETHTOOL_LINK_EXT_STATE_OVERHEAT, 0}, + + {1042, ETHTOOL_LINK_EXT_STATE_MODULE, + ETHTOOL_LINK_EXT_SUBSTATE_MODULE_CMIS_NOT_READY}, }; static void @@ -124,6 +127,10 @@ mlxsw_sp_port_set_link_ext_state(struct mlxsw_sp_ethtool_link_ext_state_opcode_m link_ext_state_info->cable_issue = link_ext_state_mapping.link_ext_substate; break; + case ETHTOOL_LINK_EXT_STATE_MODULE: + link_ext_state_info->module = + link_ext_state_mapping.link_ext_substate; + break; default: break; } @@ -1197,6 +1204,41 @@ mlxsw_sp_get_rmon_stats(struct net_device *dev, *ranges = mlxsw_rmon_ranges; } +static int mlxsw_sp_reset(struct net_device *dev, u32 *flags) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + u8 module = mlxsw_sp_port->mapping.module; + + return mlxsw_env_reset_module(dev, mlxsw_sp->core, module, flags); +} + +static int +mlxsw_sp_get_module_power_mode(struct net_device *dev, + struct ethtool_module_power_mode_params *params, + struct netlink_ext_ack *extack) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + u8 module = mlxsw_sp_port->mapping.module; + + return mlxsw_env_get_module_power_mode(mlxsw_sp->core, module, params, + extack); +} + +static int +mlxsw_sp_set_module_power_mode(struct net_device *dev, + const struct ethtool_module_power_mode_params *params, + struct netlink_ext_ack *extack) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + u8 module = mlxsw_sp_port->mapping.module; + + return mlxsw_env_set_module_power_mode(mlxsw_sp->core, module, + params->policy, extack); +} + const struct ethtool_ops mlxsw_sp_port_ethtool_ops = { .cap_link_lanes_supported = true, .get_drvinfo = mlxsw_sp_port_get_drvinfo, @@ -1218,6 +1260,9 @@ const struct ethtool_ops mlxsw_sp_port_ethtool_ops = { .get_eth_mac_stats = mlxsw_sp_get_eth_mac_stats, .get_eth_ctrl_stats = mlxsw_sp_get_eth_ctrl_stats, .get_rmon_stats = mlxsw_sp_get_rmon_stats, + .reset = mlxsw_sp_reset, + .get_module_power_mode = mlxsw_sp_get_module_power_mode, + .set_module_power_mode = mlxsw_sp_set_module_power_mode, }; struct mlxsw_sp1_port_link_mode { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c index 5facabd86882..ad3926de88f2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c @@ -24,50 +24,72 @@ mlxsw_sp_ipip_netdev_parms6(const struct net_device *ol_dev) return tun->parms; } -static bool mlxsw_sp_ipip_parms4_has_ikey(struct ip_tunnel_parm parms) +static bool mlxsw_sp_ipip_parms4_has_ikey(const struct ip_tunnel_parm *parms) { - return !!(parms.i_flags & TUNNEL_KEY); + return !!(parms->i_flags & TUNNEL_KEY); } -static bool mlxsw_sp_ipip_parms4_has_okey(struct ip_tunnel_parm parms) +static bool mlxsw_sp_ipip_parms6_has_ikey(const struct __ip6_tnl_parm *parms) { - return !!(parms.o_flags & TUNNEL_KEY); + return !!(parms->i_flags & TUNNEL_KEY); } -static u32 mlxsw_sp_ipip_parms4_ikey(struct ip_tunnel_parm parms) +static bool mlxsw_sp_ipip_parms4_has_okey(const struct ip_tunnel_parm *parms) +{ + return !!(parms->o_flags & TUNNEL_KEY); +} + +static bool mlxsw_sp_ipip_parms6_has_okey(const struct __ip6_tnl_parm *parms) +{ + return !!(parms->o_flags & TUNNEL_KEY); +} + +static u32 mlxsw_sp_ipip_parms4_ikey(const struct ip_tunnel_parm *parms) { return mlxsw_sp_ipip_parms4_has_ikey(parms) ? - be32_to_cpu(parms.i_key) : 0; + be32_to_cpu(parms->i_key) : 0; } -static u32 mlxsw_sp_ipip_parms4_okey(struct ip_tunnel_parm parms) +static u32 mlxsw_sp_ipip_parms6_ikey(const struct __ip6_tnl_parm *parms) +{ + return mlxsw_sp_ipip_parms6_has_ikey(parms) ? + be32_to_cpu(parms->i_key) : 0; +} + +static u32 mlxsw_sp_ipip_parms4_okey(const struct ip_tunnel_parm *parms) { return mlxsw_sp_ipip_parms4_has_okey(parms) ? - be32_to_cpu(parms.o_key) : 0; + be32_to_cpu(parms->o_key) : 0; +} + +static u32 mlxsw_sp_ipip_parms6_okey(const struct __ip6_tnl_parm *parms) +{ + return mlxsw_sp_ipip_parms6_has_okey(parms) ? + be32_to_cpu(parms->o_key) : 0; } static union mlxsw_sp_l3addr -mlxsw_sp_ipip_parms4_saddr(struct ip_tunnel_parm parms) +mlxsw_sp_ipip_parms4_saddr(const struct ip_tunnel_parm *parms) { - return (union mlxsw_sp_l3addr) { .addr4 = parms.iph.saddr }; + return (union mlxsw_sp_l3addr) { .addr4 = parms->iph.saddr }; } static union mlxsw_sp_l3addr -mlxsw_sp_ipip_parms6_saddr(struct __ip6_tnl_parm parms) +mlxsw_sp_ipip_parms6_saddr(const struct __ip6_tnl_parm *parms) { - return (union mlxsw_sp_l3addr) { .addr6 = parms.laddr }; + return (union mlxsw_sp_l3addr) { .addr6 = parms->laddr }; } static union mlxsw_sp_l3addr -mlxsw_sp_ipip_parms4_daddr(struct ip_tunnel_parm parms) +mlxsw_sp_ipip_parms4_daddr(const struct ip_tunnel_parm *parms) { - return (union mlxsw_sp_l3addr) { .addr4 = parms.iph.daddr }; + return (union mlxsw_sp_l3addr) { .addr4 = parms->iph.daddr }; } static union mlxsw_sp_l3addr -mlxsw_sp_ipip_parms6_daddr(struct __ip6_tnl_parm parms) +mlxsw_sp_ipip_parms6_daddr(const struct __ip6_tnl_parm *parms) { - return (union mlxsw_sp_l3addr) { .addr6 = parms.raddr }; + return (union mlxsw_sp_l3addr) { .addr6 = parms->raddr }; } union mlxsw_sp_l3addr @@ -80,10 +102,10 @@ mlxsw_sp_ipip_netdev_saddr(enum mlxsw_sp_l3proto proto, switch (proto) { case MLXSW_SP_L3_PROTO_IPV4: parms4 = mlxsw_sp_ipip_netdev_parms4(ol_dev); - return mlxsw_sp_ipip_parms4_saddr(parms4); + return mlxsw_sp_ipip_parms4_saddr(&parms4); case MLXSW_SP_L3_PROTO_IPV6: parms6 = mlxsw_sp_ipip_netdev_parms6(ol_dev); - return mlxsw_sp_ipip_parms6_saddr(parms6); + return mlxsw_sp_ipip_parms6_saddr(&parms6); } WARN_ON(1); @@ -95,7 +117,7 @@ static __be32 mlxsw_sp_ipip_netdev_daddr4(const struct net_device *ol_dev) struct ip_tunnel_parm parms4 = mlxsw_sp_ipip_netdev_parms4(ol_dev); - return mlxsw_sp_ipip_parms4_daddr(parms4).addr4; + return mlxsw_sp_ipip_parms4_daddr(&parms4).addr4; } static union mlxsw_sp_l3addr @@ -108,10 +130,10 @@ mlxsw_sp_ipip_netdev_daddr(enum mlxsw_sp_l3proto proto, switch (proto) { case MLXSW_SP_L3_PROTO_IPV4: parms4 = mlxsw_sp_ipip_netdev_parms4(ol_dev); - return mlxsw_sp_ipip_parms4_daddr(parms4); + return mlxsw_sp_ipip_parms4_daddr(&parms4); case MLXSW_SP_L3_PROTO_IPV6: parms6 = mlxsw_sp_ipip_netdev_parms6(ol_dev); - return mlxsw_sp_ipip_parms6_daddr(parms6); + return mlxsw_sp_ipip_parms6_daddr(&parms6); } WARN_ON(1); @@ -125,6 +147,21 @@ bool mlxsw_sp_l3addr_is_zero(union mlxsw_sp_l3addr addr) return !memcmp(&addr, &naddr, sizeof(naddr)); } +static struct mlxsw_sp_ipip_parms +mlxsw_sp_ipip_netdev_parms_init_gre4(const struct net_device *ol_dev) +{ + struct ip_tunnel_parm parms = mlxsw_sp_ipip_netdev_parms4(ol_dev); + + return (struct mlxsw_sp_ipip_parms) { + .proto = MLXSW_SP_L3_PROTO_IPV4, + .saddr = mlxsw_sp_ipip_parms4_saddr(&parms), + .daddr = mlxsw_sp_ipip_parms4_daddr(&parms), + .link = parms.link, + .ikey = mlxsw_sp_ipip_parms4_ikey(&parms), + .okey = mlxsw_sp_ipip_parms4_okey(&parms), + }; +} + static int mlxsw_sp_ipip_nexthop_update_gre4(struct mlxsw_sp *mlxsw_sp, u32 adj_index, struct mlxsw_sp_ipip_entry *ipip_entry, @@ -158,8 +195,8 @@ mlxsw_sp_ipip_decap_config_gre4(struct mlxsw_sp *mlxsw_sp, u32 ikey; parms = mlxsw_sp_ipip_netdev_parms4(ipip_entry->ol_dev); - has_ikey = mlxsw_sp_ipip_parms4_has_ikey(parms); - ikey = mlxsw_sp_ipip_parms4_ikey(parms); + has_ikey = mlxsw_sp_ipip_parms4_has_ikey(&parms); + ikey = mlxsw_sp_ipip_parms4_ikey(&parms); mlxsw_reg_rtdp_pack(rtdp_pl, MLXSW_REG_RTDP_TYPE_IPIP, tunnel_index); mlxsw_reg_rtdp_egress_router_interface_set(rtdp_pl, ul_rif_id); @@ -218,12 +255,12 @@ mlxsw_sp_ipip_ol_loopback_config_gre4(struct mlxsw_sp *mlxsw_sp, struct ip_tunnel_parm parms = mlxsw_sp_ipip_netdev_parms4(ol_dev); enum mlxsw_reg_ritr_loopback_ipip_type lb_ipipt; - lb_ipipt = mlxsw_sp_ipip_parms4_has_okey(parms) ? + lb_ipipt = mlxsw_sp_ipip_parms4_has_okey(&parms) ? MLXSW_REG_RITR_LOOPBACK_IPIP_TYPE_IP_IN_GRE_KEY_IN_IP : MLXSW_REG_RITR_LOOPBACK_IPIP_TYPE_IP_IN_GRE_IN_IP; return (struct mlxsw_sp_rif_ipip_lb_config){ .lb_ipipt = lb_ipipt, - .okey = mlxsw_sp_ipip_parms4_okey(parms), + .okey = mlxsw_sp_ipip_parms4_okey(&parms), .ul_protocol = MLXSW_SP_L3_PROTO_IPV4, .saddr = mlxsw_sp_ipip_netdev_saddr(MLXSW_SP_L3_PROTO_IPV4, ol_dev), @@ -231,48 +268,39 @@ mlxsw_sp_ipip_ol_loopback_config_gre4(struct mlxsw_sp *mlxsw_sp, } static int -mlxsw_sp_ipip_ol_netdev_change_gre4(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_ipip_entry *ipip_entry, - struct netlink_ext_ack *extack) +mlxsw_sp_ipip_ol_netdev_change_gre(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry, + const struct mlxsw_sp_ipip_parms *new_parms, + struct netlink_ext_ack *extack) { - union mlxsw_sp_l3addr old_saddr, new_saddr; - union mlxsw_sp_l3addr old_daddr, new_daddr; - struct ip_tunnel_parm new_parms; + const struct mlxsw_sp_ipip_parms *old_parms = &ipip_entry->parms; bool update_tunnel = false; bool update_decap = false; bool update_nhs = false; int err = 0; - new_parms = mlxsw_sp_ipip_netdev_parms4(ipip_entry->ol_dev); - - new_saddr = mlxsw_sp_ipip_parms4_saddr(new_parms); - old_saddr = mlxsw_sp_ipip_parms4_saddr(ipip_entry->parms4); - new_daddr = mlxsw_sp_ipip_parms4_daddr(new_parms); - old_daddr = mlxsw_sp_ipip_parms4_daddr(ipip_entry->parms4); - - if (!mlxsw_sp_l3addr_eq(&new_saddr, &old_saddr)) { + if (!mlxsw_sp_l3addr_eq(&new_parms->saddr, &old_parms->saddr)) { u16 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(ipip_entry->ol_dev); /* Since the local address has changed, if there is another * tunnel with a matching saddr, both need to be demoted. */ if (mlxsw_sp_ipip_demote_tunnel_by_saddr(mlxsw_sp, - MLXSW_SP_L3_PROTO_IPV4, - new_saddr, ul_tb_id, + new_parms->proto, + new_parms->saddr, + ul_tb_id, ipip_entry)) { mlxsw_sp_ipip_entry_demote_tunnel(mlxsw_sp, ipip_entry); return 0; } update_tunnel = true; - } else if ((mlxsw_sp_ipip_parms4_okey(ipip_entry->parms4) != - mlxsw_sp_ipip_parms4_okey(new_parms)) || - ipip_entry->parms4.link != new_parms.link) { + } else if (old_parms->okey != new_parms->okey || + old_parms->link != new_parms->link) { update_tunnel = true; - } else if (!mlxsw_sp_l3addr_eq(&new_daddr, &old_daddr)) { + } else if (!mlxsw_sp_l3addr_eq(&new_parms->daddr, &old_parms->daddr)) { update_nhs = true; - } else if (mlxsw_sp_ipip_parms4_ikey(ipip_entry->parms4) != - mlxsw_sp_ipip_parms4_ikey(new_parms)) { + } else if (old_parms->ikey != new_parms->ikey) { update_decap = true; } @@ -288,23 +316,308 @@ mlxsw_sp_ipip_ol_netdev_change_gre4(struct mlxsw_sp *mlxsw_sp, err = __mlxsw_sp_ipip_entry_update_tunnel(mlxsw_sp, ipip_entry, false, false, false, extack); + if (err) + return err; - ipip_entry->parms4 = new_parms; - return err; + ipip_entry->parms = *new_parms; + return 0; +} + +static int +mlxsw_sp_ipip_ol_netdev_change_gre4(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry, + struct netlink_ext_ack *extack) +{ + struct mlxsw_sp_ipip_parms new_parms; + + new_parms = mlxsw_sp_ipip_netdev_parms_init_gre4(ipip_entry->ol_dev); + return mlxsw_sp_ipip_ol_netdev_change_gre(mlxsw_sp, ipip_entry, + &new_parms, extack); +} + +static int +mlxsw_sp_ipip_rem_addr_set_gre4(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry) +{ + return 0; +} + +static void +mlxsw_sp_ipip_rem_addr_unset_gre4(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_ipip_entry *ipip_entry) +{ } static const struct mlxsw_sp_ipip_ops mlxsw_sp_ipip_gre4_ops = { .dev_type = ARPHRD_IPGRE, .ul_proto = MLXSW_SP_L3_PROTO_IPV4, + .inc_parsing_depth = false, + .parms_init = mlxsw_sp_ipip_netdev_parms_init_gre4, .nexthop_update = mlxsw_sp_ipip_nexthop_update_gre4, .decap_config = mlxsw_sp_ipip_decap_config_gre4, .can_offload = mlxsw_sp_ipip_can_offload_gre4, .ol_loopback_config = mlxsw_sp_ipip_ol_loopback_config_gre4, .ol_netdev_change = mlxsw_sp_ipip_ol_netdev_change_gre4, + .rem_ip_addr_set = mlxsw_sp_ipip_rem_addr_set_gre4, + .rem_ip_addr_unset = mlxsw_sp_ipip_rem_addr_unset_gre4, }; -const struct mlxsw_sp_ipip_ops *mlxsw_sp_ipip_ops_arr[] = { +static struct mlxsw_sp_ipip_parms +mlxsw_sp1_ipip_netdev_parms_init_gre6(const struct net_device *ol_dev) +{ + struct mlxsw_sp_ipip_parms parms = {0}; + + WARN_ON_ONCE(1); + return parms; +} + +static int +mlxsw_sp1_ipip_nexthop_update_gre6(struct mlxsw_sp *mlxsw_sp, u32 adj_index, + struct mlxsw_sp_ipip_entry *ipip_entry, + bool force, char *ratr_pl) +{ + WARN_ON_ONCE(1); + return -EINVAL; +} + +static int +mlxsw_sp1_ipip_decap_config_gre6(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry, + u32 tunnel_index) +{ + WARN_ON_ONCE(1); + return -EINVAL; +} + +static bool mlxsw_sp1_ipip_can_offload_gre6(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *ol_dev) +{ + return false; +} + +static struct mlxsw_sp_rif_ipip_lb_config +mlxsw_sp1_ipip_ol_loopback_config_gre6(struct mlxsw_sp *mlxsw_sp, + const struct net_device *ol_dev) +{ + struct mlxsw_sp_rif_ipip_lb_config config = {0}; + + WARN_ON_ONCE(1); + return config; +} + +static int +mlxsw_sp1_ipip_ol_netdev_change_gre6(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry, + struct netlink_ext_ack *extack) +{ + WARN_ON_ONCE(1); + return -EINVAL; +} + +static int +mlxsw_sp1_ipip_rem_addr_set_gre6(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry) +{ + WARN_ON_ONCE(1); + return -EINVAL; +} + +static void +mlxsw_sp1_ipip_rem_addr_unset_gre6(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_ipip_entry *ipip_entry) +{ + WARN_ON_ONCE(1); +} + +static const struct mlxsw_sp_ipip_ops mlxsw_sp1_ipip_gre6_ops = { + .dev_type = ARPHRD_IP6GRE, + .ul_proto = MLXSW_SP_L3_PROTO_IPV6, + .inc_parsing_depth = true, + .parms_init = mlxsw_sp1_ipip_netdev_parms_init_gre6, + .nexthop_update = mlxsw_sp1_ipip_nexthop_update_gre6, + .decap_config = mlxsw_sp1_ipip_decap_config_gre6, + .can_offload = mlxsw_sp1_ipip_can_offload_gre6, + .ol_loopback_config = mlxsw_sp1_ipip_ol_loopback_config_gre6, + .ol_netdev_change = mlxsw_sp1_ipip_ol_netdev_change_gre6, + .rem_ip_addr_set = mlxsw_sp1_ipip_rem_addr_set_gre6, + .rem_ip_addr_unset = mlxsw_sp1_ipip_rem_addr_unset_gre6, +}; + +const struct mlxsw_sp_ipip_ops *mlxsw_sp1_ipip_ops_arr[] = { [MLXSW_SP_IPIP_TYPE_GRE4] = &mlxsw_sp_ipip_gre4_ops, + [MLXSW_SP_IPIP_TYPE_GRE6] = &mlxsw_sp1_ipip_gre6_ops, +}; + +static struct mlxsw_sp_ipip_parms +mlxsw_sp2_ipip_netdev_parms_init_gre6(const struct net_device *ol_dev) +{ + struct __ip6_tnl_parm parms = mlxsw_sp_ipip_netdev_parms6(ol_dev); + + return (struct mlxsw_sp_ipip_parms) { + .proto = MLXSW_SP_L3_PROTO_IPV6, + .saddr = mlxsw_sp_ipip_parms6_saddr(&parms), + .daddr = mlxsw_sp_ipip_parms6_daddr(&parms), + .link = parms.link, + .ikey = mlxsw_sp_ipip_parms6_ikey(&parms), + .okey = mlxsw_sp_ipip_parms6_okey(&parms), + }; +} + +static int +mlxsw_sp2_ipip_nexthop_update_gre6(struct mlxsw_sp *mlxsw_sp, u32 adj_index, + struct mlxsw_sp_ipip_entry *ipip_entry, + bool force, char *ratr_pl) +{ + u16 rif_index = mlxsw_sp_ipip_lb_rif_index(ipip_entry->ol_lb); + enum mlxsw_reg_ratr_op op; + + op = force ? MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY : + MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY_ON_ACTIVITY; + mlxsw_reg_ratr_pack(ratr_pl, op, true, MLXSW_REG_RATR_TYPE_IPIP, + adj_index, rif_index); + mlxsw_reg_ratr_ipip6_entry_pack(ratr_pl, + ipip_entry->dip_kvdl_index); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ratr), ratr_pl); +} + +static int +mlxsw_sp2_ipip_decap_config_gre6(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry, + u32 tunnel_index) +{ + u16 rif_index = mlxsw_sp_ipip_lb_rif_index(ipip_entry->ol_lb); + u16 ul_rif_id = mlxsw_sp_ipip_lb_ul_rif_id(ipip_entry->ol_lb); + char rtdp_pl[MLXSW_REG_RTDP_LEN]; + struct __ip6_tnl_parm parms; + unsigned int type_check; + bool has_ikey; + u32 ikey; + + parms = mlxsw_sp_ipip_netdev_parms6(ipip_entry->ol_dev); + has_ikey = mlxsw_sp_ipip_parms6_has_ikey(&parms); + ikey = mlxsw_sp_ipip_parms6_ikey(&parms); + + mlxsw_reg_rtdp_pack(rtdp_pl, MLXSW_REG_RTDP_TYPE_IPIP, tunnel_index); + mlxsw_reg_rtdp_egress_router_interface_set(rtdp_pl, ul_rif_id); + + type_check = has_ikey ? + MLXSW_REG_RTDP_IPIP_TYPE_CHECK_ALLOW_GRE_KEY : + MLXSW_REG_RTDP_IPIP_TYPE_CHECK_ALLOW_GRE; + + /* Linux demuxes tunnels based on packet SIP (which must match tunnel + * remote IP). Thus configure decap so that it filters out packets that + * are not IPv6 or have the wrong SIP. IPIP_DECAP_ERROR trap is + * generated for packets that fail this criterion. Linux then handles + * such packets in slow path and generates ICMP destination unreachable. + */ + mlxsw_reg_rtdp_ipip6_pack(rtdp_pl, rif_index, + MLXSW_REG_RTDP_IPIP_SIP_CHECK_FILTER_IPV6, + type_check, has_ikey, + ipip_entry->dip_kvdl_index, ikey); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtdp), rtdp_pl); +} + +static bool mlxsw_sp2_ipip_can_offload_gre6(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *ol_dev) +{ + struct __ip6_tnl_parm tparm = mlxsw_sp_ipip_netdev_parms6(ol_dev); + bool inherit_tos = tparm.flags & IP6_TNL_F_USE_ORIG_TCLASS; + bool inherit_ttl = tparm.hop_limit == 0; + __be16 okflags = TUNNEL_KEY; /* We can't offload any other features. */ + + return (tparm.i_flags & ~okflags) == 0 && + (tparm.o_flags & ~okflags) == 0 && + inherit_ttl && inherit_tos && + mlxsw_sp_ipip_tunnel_complete(MLXSW_SP_L3_PROTO_IPV6, ol_dev); +} + +static struct mlxsw_sp_rif_ipip_lb_config +mlxsw_sp2_ipip_ol_loopback_config_gre6(struct mlxsw_sp *mlxsw_sp, + const struct net_device *ol_dev) +{ + struct __ip6_tnl_parm parms = mlxsw_sp_ipip_netdev_parms6(ol_dev); + enum mlxsw_reg_ritr_loopback_ipip_type lb_ipipt; + + lb_ipipt = mlxsw_sp_ipip_parms6_has_okey(&parms) ? + MLXSW_REG_RITR_LOOPBACK_IPIP_TYPE_IP_IN_GRE_KEY_IN_IP : + MLXSW_REG_RITR_LOOPBACK_IPIP_TYPE_IP_IN_GRE_IN_IP; + return (struct mlxsw_sp_rif_ipip_lb_config){ + .lb_ipipt = lb_ipipt, + .okey = mlxsw_sp_ipip_parms6_okey(&parms), + .ul_protocol = MLXSW_SP_L3_PROTO_IPV6, + .saddr = mlxsw_sp_ipip_netdev_saddr(MLXSW_SP_L3_PROTO_IPV6, + ol_dev), + }; +} + +static int +mlxsw_sp2_ipip_ol_netdev_change_gre6(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry, + struct netlink_ext_ack *extack) +{ + struct mlxsw_sp_ipip_parms new_parms; + + new_parms = mlxsw_sp2_ipip_netdev_parms_init_gre6(ipip_entry->ol_dev); + return mlxsw_sp_ipip_ol_netdev_change_gre(mlxsw_sp, ipip_entry, + &new_parms, extack); +} + +static int +mlxsw_sp2_ipip_rem_addr_set_gre6(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry) +{ + char rips_pl[MLXSW_REG_RIPS_LEN]; + struct __ip6_tnl_parm parms6; + int err; + + err = mlxsw_sp_kvdl_alloc(mlxsw_sp, + MLXSW_SP_KVDL_ENTRY_TYPE_IPV6_ADDRESS, 1, + &ipip_entry->dip_kvdl_index); + if (err) + return err; + + parms6 = mlxsw_sp_ipip_netdev_parms6(ipip_entry->ol_dev); + mlxsw_reg_rips_pack(rips_pl, ipip_entry->dip_kvdl_index, + &parms6.raddr); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rips), rips_pl); + if (err) + goto err_rips_write; + + return 0; + +err_rips_write: + mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_IPV6_ADDRESS, 1, + ipip_entry->dip_kvdl_index); + return err; +} + +static void +mlxsw_sp2_ipip_rem_addr_unset_gre6(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_ipip_entry *ipip_entry) +{ + mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_IPV6_ADDRESS, 1, + ipip_entry->dip_kvdl_index); +} + +static const struct mlxsw_sp_ipip_ops mlxsw_sp2_ipip_gre6_ops = { + .dev_type = ARPHRD_IP6GRE, + .ul_proto = MLXSW_SP_L3_PROTO_IPV6, + .inc_parsing_depth = true, + .parms_init = mlxsw_sp2_ipip_netdev_parms_init_gre6, + .nexthop_update = mlxsw_sp2_ipip_nexthop_update_gre6, + .decap_config = mlxsw_sp2_ipip_decap_config_gre6, + .can_offload = mlxsw_sp2_ipip_can_offload_gre6, + .ol_loopback_config = mlxsw_sp2_ipip_ol_loopback_config_gre6, + .ol_netdev_change = mlxsw_sp2_ipip_ol_netdev_change_gre6, + .rem_ip_addr_set = mlxsw_sp2_ipip_rem_addr_set_gre6, + .rem_ip_addr_unset = mlxsw_sp2_ipip_rem_addr_unset_gre6, +}; + +const struct mlxsw_sp_ipip_ops *mlxsw_sp2_ipip_ops_arr[] = { + [MLXSW_SP_IPIP_TYPE_GRE4] = &mlxsw_sp_ipip_gre4_ops, + [MLXSW_SP_IPIP_TYPE_GRE6] = &mlxsw_sp2_ipip_gre6_ops, }; static int mlxsw_sp_ipip_ecn_encap_init_one(struct mlxsw_sp *mlxsw_sp, @@ -363,3 +676,22 @@ int mlxsw_sp_ipip_ecn_decap_init(struct mlxsw_sp *mlxsw_sp) return 0; } + +struct net_device * +mlxsw_sp_ipip_netdev_ul_dev_get(const struct net_device *ol_dev) +{ + struct net *net = dev_net(ol_dev); + struct ip_tunnel *tun4; + struct ip6_tnl *tun6; + + switch (ol_dev->type) { + case ARPHRD_IPGRE: + tun4 = netdev_priv(ol_dev); + return dev_get_by_index_rcu(net, tun4->parms.link); + case ARPHRD_IP6GRE: + tun6 = netdev_priv(ol_dev); + return dev_get_by_index_rcu(net, tun6->parms.link); + default: + return NULL; + } +} diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h index f0837b42d1d6..8cc259dcc8d0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h @@ -7,6 +7,7 @@ #include "spectrum_router.h" #include <net/ip_fib.h> #include <linux/if_tunnel.h> +#include <net/ip6_tunnel.h> struct ip_tunnel_parm mlxsw_sp_ipip_netdev_parms4(const struct net_device *ol_dev); @@ -21,23 +22,36 @@ bool mlxsw_sp_l3addr_is_zero(union mlxsw_sp_l3addr addr); enum mlxsw_sp_ipip_type { MLXSW_SP_IPIP_TYPE_GRE4, + MLXSW_SP_IPIP_TYPE_GRE6, MLXSW_SP_IPIP_TYPE_MAX, }; +struct mlxsw_sp_ipip_parms { + enum mlxsw_sp_l3proto proto; + union mlxsw_sp_l3addr saddr; + union mlxsw_sp_l3addr daddr; + int link; + u32 ikey; + u32 okey; +}; + struct mlxsw_sp_ipip_entry { enum mlxsw_sp_ipip_type ipipt; struct net_device *ol_dev; /* Overlay. */ struct mlxsw_sp_rif_ipip_lb *ol_lb; struct mlxsw_sp_fib_entry *decap_fib_entry; struct list_head ipip_list_node; - union { - struct ip_tunnel_parm parms4; - }; + struct mlxsw_sp_ipip_parms parms; + u32 dip_kvdl_index; }; struct mlxsw_sp_ipip_ops { int dev_type; enum mlxsw_sp_l3proto ul_proto; /* Underlay. */ + bool inc_parsing_depth; + + struct mlxsw_sp_ipip_parms + (*parms_init)(const struct net_device *ol_dev); int (*nexthop_update)(struct mlxsw_sp *mlxsw_sp, u32 adj_index, struct mlxsw_sp_ipip_entry *ipip_entry, @@ -58,8 +72,13 @@ struct mlxsw_sp_ipip_ops { int (*ol_netdev_change)(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_ipip_entry *ipip_entry, struct netlink_ext_ack *extack); + int (*rem_ip_addr_set)(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry); + void (*rem_ip_addr_unset)(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_ipip_entry *ipip_entry); }; -extern const struct mlxsw_sp_ipip_ops *mlxsw_sp_ipip_ops_arr[]; +extern const struct mlxsw_sp_ipip_ops *mlxsw_sp1_ipip_ops_arr[]; +extern const struct mlxsw_sp_ipip_ops *mlxsw_sp2_ipip_ops_arr[]; #endif /* _MLXSW_IPIP_H_*/ diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 19bb3ca0515e..1e141b5944cd 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -115,6 +115,7 @@ struct mlxsw_sp_rif_ops { struct mlxsw_sp_router_ops { int (*init)(struct mlxsw_sp *mlxsw_sp); + int (*ipips_init)(struct mlxsw_sp *mlxsw_sp); }; static struct mlxsw_sp_rif * @@ -1055,22 +1056,13 @@ static void mlxsw_sp_vrs_fini(struct mlxsw_sp *mlxsw_sp) kfree(mlxsw_sp->router->vrs); } -static struct net_device * -__mlxsw_sp_ipip_netdev_ul_dev_get(const struct net_device *ol_dev) -{ - struct ip_tunnel *tun = netdev_priv(ol_dev); - struct net *net = dev_net(ol_dev); - - return dev_get_by_index_rcu(net, tun->parms.link); -} - u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev) { struct net_device *d; u32 tb_id; rcu_read_lock(); - d = __mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev); + d = mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev); if (d) tb_id = l3mdev_fib_table(d) ? : RT_TABLE_MAIN; else @@ -1116,6 +1108,7 @@ mlxsw_sp_ipip_entry_alloc(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_ipip_ops *ipip_ops; struct mlxsw_sp_ipip_entry *ipip_entry; struct mlxsw_sp_ipip_entry *ret = NULL; + int err; ipip_ops = mlxsw_sp->router->ipip_ops_arr[ipipt]; ipip_entry = kzalloc(sizeof(*ipip_entry), GFP_KERNEL); @@ -1131,26 +1124,30 @@ mlxsw_sp_ipip_entry_alloc(struct mlxsw_sp *mlxsw_sp, ipip_entry->ipipt = ipipt; ipip_entry->ol_dev = ol_dev; + ipip_entry->parms = ipip_ops->parms_init(ol_dev); - switch (ipip_ops->ul_proto) { - case MLXSW_SP_L3_PROTO_IPV4: - ipip_entry->parms4 = mlxsw_sp_ipip_netdev_parms4(ol_dev); - break; - case MLXSW_SP_L3_PROTO_IPV6: - WARN_ON(1); - break; + err = ipip_ops->rem_ip_addr_set(mlxsw_sp, ipip_entry); + if (err) { + ret = ERR_PTR(err); + goto err_rem_ip_addr_set; } return ipip_entry; +err_rem_ip_addr_set: + mlxsw_sp_rif_destroy(&ipip_entry->ol_lb->common); err_ol_ipip_lb_create: kfree(ipip_entry); return ret; } -static void -mlxsw_sp_ipip_entry_dealloc(struct mlxsw_sp_ipip_entry *ipip_entry) +static void mlxsw_sp_ipip_entry_dealloc(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry) { + const struct mlxsw_sp_ipip_ops *ipip_ops = + mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt]; + + ipip_ops->rem_ip_addr_unset(mlxsw_sp, ipip_entry); mlxsw_sp_rif_destroy(&ipip_entry->ol_lb->common); kfree(ipip_entry); } @@ -1174,6 +1171,32 @@ mlxsw_sp_ipip_entry_saddr_matches(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_l3addr_eq(&tun_saddr, &saddr); } +static int mlxsw_sp_ipip_decap_parsing_depth_inc(struct mlxsw_sp *mlxsw_sp, + enum mlxsw_sp_ipip_type ipipt) +{ + const struct mlxsw_sp_ipip_ops *ipip_ops; + + ipip_ops = mlxsw_sp->router->ipip_ops_arr[ipipt]; + + /* Not all tunnels require to increase the default pasing depth + * (96 bytes). + */ + if (ipip_ops->inc_parsing_depth) + return mlxsw_sp_parsing_depth_inc(mlxsw_sp); + + return 0; +} + +static void mlxsw_sp_ipip_decap_parsing_depth_dec(struct mlxsw_sp *mlxsw_sp, + enum mlxsw_sp_ipip_type ipipt) +{ + const struct mlxsw_sp_ipip_ops *ipip_ops = + mlxsw_sp->router->ipip_ops_arr[ipipt]; + + if (ipip_ops->inc_parsing_depth) + mlxsw_sp_parsing_depth_dec(mlxsw_sp); +} + static int mlxsw_sp_fib_entry_decap_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry, @@ -1187,18 +1210,32 @@ mlxsw_sp_fib_entry_decap_init(struct mlxsw_sp *mlxsw_sp, if (err) return err; + err = mlxsw_sp_ipip_decap_parsing_depth_inc(mlxsw_sp, + ipip_entry->ipipt); + if (err) + goto err_parsing_depth_inc; + ipip_entry->decap_fib_entry = fib_entry; fib_entry->decap.ipip_entry = ipip_entry; fib_entry->decap.tunnel_index = tunnel_index; + return 0; + +err_parsing_depth_inc: + mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, + fib_entry->decap.tunnel_index); + return err; } static void mlxsw_sp_fib_entry_decap_fini(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry) { + enum mlxsw_sp_ipip_type ipipt = fib_entry->decap.ipip_entry->ipipt; + /* Unlink this node from the IPIP entry that it's the decap entry of. */ fib_entry->decap.ipip_entry->decap_fib_entry = NULL; fib_entry->decap.ipip_entry = NULL; + mlxsw_sp_ipip_decap_parsing_depth_dec(mlxsw_sp, ipipt); mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, fib_entry->decap.tunnel_index); } @@ -1309,6 +1346,11 @@ mlxsw_sp_ipip_entry_find_decap(struct mlxsw_sp *mlxsw_sp, saddr_len = 4; saddr_prefix_len = 32; break; + case MLXSW_SP_L3_PROTO_IPV6: + saddrp = &saddr.addr6; + saddr_len = 16; + saddr_prefix_len = 128; + break; default: WARN_ON(1); return NULL; @@ -1345,7 +1387,7 @@ mlxsw_sp_ipip_entry_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_ipip_entry *ipip_entry) { list_del(&ipip_entry->ipip_list_node); - mlxsw_sp_ipip_entry_dealloc(ipip_entry); + mlxsw_sp_ipip_entry_dealloc(mlxsw_sp, ipip_entry); } static bool @@ -1450,7 +1492,7 @@ mlxsw_sp_ipip_entry_find_by_ul_dev(const struct mlxsw_sp *mlxsw_sp, struct net_device *ipip_ul_dev; rcu_read_lock(); - ipip_ul_dev = __mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev); + ipip_ul_dev = mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev); rcu_read_unlock(); if (ipip_ul_dev == ul_dev) @@ -1536,23 +1578,34 @@ mlxsw_sp_rif_ipip_lb_op(struct mlxsw_sp_rif_ipip_lb *lb_rif, u16 ul_vr_id, u16 ul_rif_id, bool enable) { struct mlxsw_sp_rif_ipip_lb_config lb_cf = lb_rif->lb_config; + enum mlxsw_reg_ritr_loopback_ipip_options ipip_options; struct mlxsw_sp_rif *rif = &lb_rif->common; struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; char ritr_pl[MLXSW_REG_RITR_LEN]; + struct in6_addr *saddr6; u32 saddr4; + ipip_options = MLXSW_REG_RITR_LOOPBACK_IPIP_OPTIONS_GRE_KEY_PRESET; switch (lb_cf.ul_protocol) { case MLXSW_SP_L3_PROTO_IPV4: saddr4 = be32_to_cpu(lb_cf.saddr.addr4); mlxsw_reg_ritr_pack(ritr_pl, enable, MLXSW_REG_RITR_LOOPBACK_IF, rif->rif_index, rif->vr_id, rif->dev->mtu); mlxsw_reg_ritr_loopback_ipip4_pack(ritr_pl, lb_cf.lb_ipipt, - MLXSW_REG_RITR_LOOPBACK_IPIP_OPTIONS_GRE_KEY_PRESET, - ul_vr_id, ul_rif_id, saddr4, lb_cf.okey); + ipip_options, ul_vr_id, + ul_rif_id, saddr4, + lb_cf.okey); break; case MLXSW_SP_L3_PROTO_IPV6: - return -EAFNOSUPPORT; + saddr6 = &lb_cf.saddr.addr6; + mlxsw_reg_ritr_pack(ritr_pl, enable, MLXSW_REG_RITR_LOOPBACK_IF, + rif->rif_index, rif->vr_id, rif->dev->mtu); + mlxsw_reg_ritr_loopback_ipip6_pack(ritr_pl, lb_cf.lb_ipipt, + ipip_options, ul_vr_id, + ul_rif_id, saddr6, + lb_cf.okey); + break; } return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); @@ -1827,7 +1880,7 @@ static void mlxsw_sp_ipip_demote_tunnel_by_ul_netdev(struct mlxsw_sp *mlxsw_sp, struct net_device *ipip_ul_dev; rcu_read_lock(); - ipip_ul_dev = __mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev); + ipip_ul_dev = mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev); rcu_read_unlock(); if (ipip_ul_dev == ul_dev) mlxsw_sp_ipip_entry_demote_tunnel(mlxsw_sp, ipip_entry); @@ -4152,7 +4205,7 @@ static bool mlxsw_sp_ipip_netdev_ul_up(struct net_device *ol_dev) bool is_up; rcu_read_lock(); - ul_dev = __mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev); + ul_dev = mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev); is_up = ul_dev ? (ul_dev->flags & IFF_UP) : true; rcu_read_unlock(); @@ -4376,6 +4429,66 @@ static void mlxsw_sp_nexthop_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, } } +static int mlxsw_sp_adj_trap_entry_init(struct mlxsw_sp *mlxsw_sp) +{ + enum mlxsw_reg_ratr_trap_action trap_action; + char ratr_pl[MLXSW_REG_RATR_LEN]; + int err; + + err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, + &mlxsw_sp->router->adj_trap_index); + if (err) + return err; + + trap_action = MLXSW_REG_RATR_TRAP_ACTION_TRAP; + mlxsw_reg_ratr_pack(ratr_pl, MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY, true, + MLXSW_REG_RATR_TYPE_ETHERNET, + mlxsw_sp->router->adj_trap_index, + mlxsw_sp->router->lb_rif_index); + mlxsw_reg_ratr_trap_action_set(ratr_pl, trap_action); + mlxsw_reg_ratr_trap_id_set(ratr_pl, MLXSW_TRAP_ID_RTR_EGRESS0); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ratr), ratr_pl); + if (err) + goto err_ratr_write; + + return 0; + +err_ratr_write: + mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, + mlxsw_sp->router->adj_trap_index); + return err; +} + +static void mlxsw_sp_adj_trap_entry_fini(struct mlxsw_sp *mlxsw_sp) +{ + mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, + mlxsw_sp->router->adj_trap_index); +} + +static int mlxsw_sp_nexthop_group_inc(struct mlxsw_sp *mlxsw_sp) +{ + int err; + + if (refcount_inc_not_zero(&mlxsw_sp->router->num_groups)) + return 0; + + err = mlxsw_sp_adj_trap_entry_init(mlxsw_sp); + if (err) + return err; + + refcount_set(&mlxsw_sp->router->num_groups, 1); + + return 0; +} + +static void mlxsw_sp_nexthop_group_dec(struct mlxsw_sp *mlxsw_sp) +{ + if (!refcount_dec_and_test(&mlxsw_sp->router->num_groups)) + return; + + mlxsw_sp_adj_trap_entry_fini(mlxsw_sp); +} + static void mlxsw_sp_nh_grp_activity_get(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_nexthop_group *nh_grp, @@ -4790,6 +4903,9 @@ mlxsw_sp_nexthop_obj_group_info_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_nexthop_obj_init; } + err = mlxsw_sp_nexthop_group_inc(mlxsw_sp); + if (err) + goto err_group_inc; err = mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp); if (err) { NL_SET_ERR_MSG_MOD(info->extack, "Failed to write adjacency entries to the device"); @@ -4808,6 +4924,8 @@ mlxsw_sp_nexthop_obj_group_info_init(struct mlxsw_sp *mlxsw_sp, return 0; err_group_refresh: + mlxsw_sp_nexthop_group_dec(mlxsw_sp); +err_group_inc: i = nhgi->count; err_nexthop_obj_init: for (i--; i >= 0; i--) { @@ -4832,6 +4950,7 @@ mlxsw_sp_nexthop_obj_group_info_fini(struct mlxsw_sp *mlxsw_sp, cancel_delayed_work(&router->nh_grp_activity_dw); } + mlxsw_sp_nexthop_group_dec(mlxsw_sp); for (i = nhgi->count - 1; i >= 0; i--) { struct mlxsw_sp_nexthop *nh = &nhgi->nexthops[i]; @@ -5223,6 +5342,9 @@ mlxsw_sp_nexthop4_group_info_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_nexthop4_init; } + err = mlxsw_sp_nexthop_group_inc(mlxsw_sp); + if (err) + goto err_group_inc; err = mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp); if (err) goto err_group_refresh; @@ -5230,6 +5352,8 @@ mlxsw_sp_nexthop4_group_info_init(struct mlxsw_sp *mlxsw_sp, return 0; err_group_refresh: + mlxsw_sp_nexthop_group_dec(mlxsw_sp); +err_group_inc: i = nhgi->count; err_nexthop4_init: for (i--; i >= 0; i--) { @@ -5247,6 +5371,7 @@ mlxsw_sp_nexthop4_group_info_fini(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group_info *nhgi = nh_grp->nhgi; int i; + mlxsw_sp_nexthop_group_dec(mlxsw_sp); for (i = nhgi->count - 1; i >= 0; i--) { struct mlxsw_sp_nexthop *nh = &nhgi->nexthops[i]; @@ -5725,41 +5850,6 @@ static int mlxsw_sp_fib_entry_commit(struct mlxsw_sp *mlxsw_sp, return err; } -static int mlxsw_sp_adj_discard_write(struct mlxsw_sp *mlxsw_sp) -{ - enum mlxsw_reg_ratr_trap_action trap_action; - char ratr_pl[MLXSW_REG_RATR_LEN]; - int err; - - if (mlxsw_sp->router->adj_discard_index_valid) - return 0; - - err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, - &mlxsw_sp->router->adj_discard_index); - if (err) - return err; - - trap_action = MLXSW_REG_RATR_TRAP_ACTION_TRAP; - mlxsw_reg_ratr_pack(ratr_pl, MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY, true, - MLXSW_REG_RATR_TYPE_ETHERNET, - mlxsw_sp->router->adj_discard_index, - mlxsw_sp->router->lb_rif_index); - mlxsw_reg_ratr_trap_action_set(ratr_pl, trap_action); - mlxsw_reg_ratr_trap_id_set(ratr_pl, MLXSW_TRAP_ID_RTR_EGRESS0); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ratr), ratr_pl); - if (err) - goto err_ratr_write; - - mlxsw_sp->router->adj_discard_index_valid = true; - - return 0; - -err_ratr_write: - mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, - mlxsw_sp->router->adj_discard_index); - return err; -} - static int mlxsw_sp_fib_entry_op_remote(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry, @@ -5772,7 +5862,6 @@ static int mlxsw_sp_fib_entry_op_remote(struct mlxsw_sp *mlxsw_sp, u16 trap_id = 0; u32 adjacency_index = 0; u16 ecmp_size = 0; - int err; /* In case the nexthop group adjacency index is valid, use it * with provided ECMP size. Otherwise, setup trap and pass @@ -5783,11 +5872,8 @@ static int mlxsw_sp_fib_entry_op_remote(struct mlxsw_sp *mlxsw_sp, adjacency_index = nhgi->adj_index; ecmp_size = nhgi->ecmp_size; } else if (!nhgi->adj_index_valid && nhgi->count && nhgi->nh_rif) { - err = mlxsw_sp_adj_discard_write(mlxsw_sp); - if (err) - return err; trap_action = MLXSW_REG_RALUE_TRAP_ACTION_NOP; - adjacency_index = mlxsw_sp->router->adj_discard_index; + adjacency_index = mlxsw_sp->router->adj_trap_index; ecmp_size = 1; } else { trap_action = MLXSW_REG_RALUE_TRAP_ACTION_TRAP; @@ -6036,8 +6122,8 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp, } static void -mlxsw_sp_fib4_entry_type_unset(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry *fib_entry) +mlxsw_sp_fib_entry_type_unset(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry) { switch (fib_entry->type) { case MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP: @@ -6048,6 +6134,13 @@ mlxsw_sp_fib4_entry_type_unset(struct mlxsw_sp *mlxsw_sp, } } +static void +mlxsw_sp_fib4_entry_type_unset(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib4_entry *fib4_entry) +{ + mlxsw_sp_fib_entry_type_unset(mlxsw_sp, &fib4_entry->common); +} + static struct mlxsw_sp_fib4_entry * mlxsw_sp_fib4_entry_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_node *fib_node, @@ -6108,7 +6201,7 @@ static void mlxsw_sp_fib4_entry_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_node *fib_node = fib4_entry->common.fib_node; fib_info_put(fib4_entry->fi); - mlxsw_sp_fib4_entry_type_unset(mlxsw_sp, &fib4_entry->common); + mlxsw_sp_fib4_entry_type_unset(mlxsw_sp, fib4_entry); mlxsw_sp_nexthop_group_vr_unlink(fib4_entry->common.nh_group, fib_node->fib); mlxsw_sp_nexthop4_group_put(mlxsw_sp, &fib4_entry->common); @@ -6641,6 +6734,9 @@ mlxsw_sp_nexthop6_group_info_init(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_rt6 = list_next_entry(mlxsw_sp_rt6, list); } nh_grp->nhgi = nhgi; + err = mlxsw_sp_nexthop_group_inc(mlxsw_sp); + if (err) + goto err_group_inc; err = mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp); if (err) goto err_group_refresh; @@ -6648,6 +6744,8 @@ mlxsw_sp_nexthop6_group_info_init(struct mlxsw_sp *mlxsw_sp, return 0; err_group_refresh: + mlxsw_sp_nexthop_group_dec(mlxsw_sp); +err_group_inc: i = nhgi->count; err_nexthop6_init: for (i--; i >= 0; i--) { @@ -6665,6 +6763,7 @@ mlxsw_sp_nexthop6_group_info_fini(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group_info *nhgi = nh_grp->nhgi; int i; + mlxsw_sp_nexthop_group_dec(mlxsw_sp); for (i = nhgi->count - 1; i >= 0; i--) { struct mlxsw_sp_nexthop *nh = &nhgi->nexthops[i]; @@ -6888,11 +6987,38 @@ mlxsw_sp_fib6_entry_nexthop_del(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_nexthop6_group_update(mlxsw_sp, op_ctx, fib6_entry); } -static void mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry *fib_entry, - const struct fib6_info *rt) +static int +mlxsw_sp_fib6_entry_type_set_local(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry, + const struct fib6_info *rt) { - if (rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) + struct mlxsw_sp_nexthop_group_info *nhgi = fib_entry->nh_group->nhgi; + union mlxsw_sp_l3addr dip = { .addr6 = rt->fib6_dst.addr }; + int ifindex = nhgi->nexthops[0].ifindex; + struct mlxsw_sp_ipip_entry *ipip_entry; + + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP; + ipip_entry = mlxsw_sp_ipip_entry_find_by_decap(mlxsw_sp, ifindex, + MLXSW_SP_L3_PROTO_IPV6, + dip); + + if (ipip_entry && ipip_entry->ol_dev->flags & IFF_UP) { + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP; + return mlxsw_sp_fib_entry_decap_init(mlxsw_sp, fib_entry, + ipip_entry); + } + + return 0; +} + +static int mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry, + const struct fib6_info *rt) +{ + if (rt->fib6_flags & RTF_LOCAL) + return mlxsw_sp_fib6_entry_type_set_local(mlxsw_sp, fib_entry, + rt); + if (rt->fib6_flags & RTF_ANYCAST) fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP; else if (rt->fib6_type == RTN_BLACKHOLE) fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE; @@ -6902,6 +7028,8 @@ static void mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp *mlxsw_sp, fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE; else fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL; + + return 0; } static void @@ -6959,12 +7087,16 @@ mlxsw_sp_fib6_entry_create(struct mlxsw_sp *mlxsw_sp, if (err) goto err_nexthop_group_vr_link; - mlxsw_sp_fib6_entry_type_set(mlxsw_sp, fib_entry, rt_arr[0]); + err = mlxsw_sp_fib6_entry_type_set(mlxsw_sp, fib_entry, rt_arr[0]); + if (err) + goto err_fib6_entry_type_set; fib_entry->fib_node = fib_node; return fib6_entry; +err_fib6_entry_type_set: + mlxsw_sp_nexthop_group_vr_unlink(fib_entry->nh_group, fib_node->fib); err_nexthop_group_vr_link: mlxsw_sp_nexthop6_group_put(mlxsw_sp, fib_entry); err_nexthop6_group_get: @@ -6983,11 +7115,19 @@ err_fib_entry_priv_create: return ERR_PTR(err); } +static void +mlxsw_sp_fib6_entry_type_unset(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib6_entry *fib6_entry) +{ + mlxsw_sp_fib_entry_type_unset(mlxsw_sp, &fib6_entry->common); +} + static void mlxsw_sp_fib6_entry_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib6_entry *fib6_entry) { struct mlxsw_sp_fib_node *fib_node = fib6_entry->common.fib_node; + mlxsw_sp_fib6_entry_type_unset(mlxsw_sp, fib6_entry); mlxsw_sp_nexthop_group_vr_unlink(fib6_entry->common.nh_group, fib_node->fib); mlxsw_sp_nexthop6_group_put(mlxsw_sp, &fib6_entry->common); @@ -7340,16 +7480,6 @@ static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp) continue; mlxsw_sp_vr_fib_flush(mlxsw_sp, vr, MLXSW_SP_L3_PROTO_IPV6); } - - /* After flushing all the routes, it is not possible anyone is still - * using the adjacency index that is discarding packets, so free it in - * case it was allocated. - */ - if (!mlxsw_sp->router->adj_discard_index_valid) - return; - mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, - mlxsw_sp->router->adj_discard_index); - mlxsw_sp->router->adj_discard_index_valid = false; } struct mlxsw_sp_fib6_event { @@ -9447,7 +9577,6 @@ static int mlxsw_sp_ipips_init(struct mlxsw_sp *mlxsw_sp) { int err; - mlxsw_sp->router->ipip_ops_arr = mlxsw_sp_ipip_ops_arr; INIT_LIST_HEAD(&mlxsw_sp->router->ipip_list); err = mlxsw_sp_ipip_ecn_encap_init(mlxsw_sp); @@ -9460,6 +9589,18 @@ static int mlxsw_sp_ipips_init(struct mlxsw_sp *mlxsw_sp) return mlxsw_sp_ipip_config_tigcr(mlxsw_sp); } +static int mlxsw_sp1_ipips_init(struct mlxsw_sp *mlxsw_sp) +{ + mlxsw_sp->router->ipip_ops_arr = mlxsw_sp1_ipip_ops_arr; + return mlxsw_sp_ipips_init(mlxsw_sp); +} + +static int mlxsw_sp2_ipips_init(struct mlxsw_sp *mlxsw_sp) +{ + mlxsw_sp->router->ipip_ops_arr = mlxsw_sp2_ipip_ops_arr; + return mlxsw_sp_ipips_init(mlxsw_sp); +} + static void mlxsw_sp_ipips_fini(struct mlxsw_sp *mlxsw_sp) { WARN_ON(!list_empty(&mlxsw_sp->router->ipip_list)); @@ -9874,6 +10015,7 @@ static int mlxsw_sp1_router_init(struct mlxsw_sp *mlxsw_sp) const struct mlxsw_sp_router_ops mlxsw_sp1_router_ops = { .init = mlxsw_sp1_router_init, + .ipips_init = mlxsw_sp1_ipips_init, }; static int mlxsw_sp2_router_init(struct mlxsw_sp *mlxsw_sp) @@ -9889,6 +10031,7 @@ static int mlxsw_sp2_router_init(struct mlxsw_sp *mlxsw_sp) const struct mlxsw_sp_router_ops mlxsw_sp2_router_ops = { .init = mlxsw_sp2_router_init, + .ipips_init = mlxsw_sp2_ipips_init, }; int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, @@ -9934,7 +10077,7 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_rifs_init; - err = mlxsw_sp_ipips_init(mlxsw_sp); + err = mlxsw_sp->router_ops->ipips_init(mlxsw_sp); if (err) goto err_ipips_init; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h index 25d3eae63501..1d0d28f8ff05 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h @@ -65,8 +65,6 @@ struct mlxsw_sp_router { struct notifier_block inet6addr_nb; const struct mlxsw_sp_rif_ops **rif_ops_arr; const struct mlxsw_sp_ipip_ops **ipip_ops_arr; - u32 adj_discard_index; - bool adj_discard_index_valid; struct mlxsw_sp_router_nve_decap nve_decap_config; struct mutex lock; /* Protects shared router resources */ struct work_struct fib_event_work; @@ -82,6 +80,8 @@ struct mlxsw_sp_router { struct delayed_work nh_grp_activity_dw; struct list_head nh_res_grp_list; bool inc_parsing_depth; + refcount_t num_groups; + u32 adj_trap_index; }; struct mlxsw_sp_fib_entry_priv { @@ -226,6 +226,8 @@ static inline bool mlxsw_sp_l3addr_eq(const union mlxsw_sp_l3addr *addr1, int mlxsw_sp_ipip_ecn_encap_init(struct mlxsw_sp *mlxsw_sp); int mlxsw_sp_ipip_ecn_decap_init(struct mlxsw_sp *mlxsw_sp); +struct net_device * +mlxsw_sp_ipip_netdev_ul_dev_get(const struct net_device *ol_dev); extern const struct mlxsw_sp_router_ll_ops mlxsw_sp_router_ll_xm_ops; |