diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox')
168 files changed, 8323 insertions, 2409 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 8d751383530b..e10b7b04b894 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -2480,7 +2480,6 @@ int mlx4_multi_func_init(struct mlx4_dev *dev) return 0; err_thread: - flush_workqueue(priv->mfunc.master.comm_wq); destroy_workqueue(priv->mfunc.master.comm_wq); err_slaves: while (i--) { @@ -2587,7 +2586,6 @@ void mlx4_multi_func_cleanup(struct mlx4_dev *dev) int i, port; if (mlx4_is_master(dev)) { - flush_workqueue(priv->mfunc.master.comm_wq); destroy_workqueue(priv->mfunc.master.comm_wq); for (i = 0; i < dev->num_slaves; i++) { for (port = 1; port <= MLX4_MAX_PORTS; port++) @@ -3009,7 +3007,7 @@ 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 +3193,7 @@ 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..066d79e4ecfc 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -39,6 +39,7 @@ #include <linux/in.h> #include <net/ip.h> #include <linux/bitmap.h> +#include <linux/mii.h> #include "mlx4_en.h" #include "en_port.h" @@ -197,6 +198,8 @@ 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 +431,8 @@ 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 +525,10 @@ 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); @@ -643,10 +652,8 @@ static unsigned long *ptys2ethtool_link_mode(struct ptys2ethtool_config *cfg, unsigned int i; \ cfg = &ptys2ethtool_map[reg_]; \ cfg->speed = speed_; \ - bitmap_zero(cfg->supported, \ - __ETHTOOL_LINK_MODE_MASK_NBITS); \ - bitmap_zero(cfg->advertised, \ - __ETHTOOL_LINK_MODE_MASK_NBITS); \ + linkmode_zero(cfg->supported); \ + linkmode_zero(cfg->advertised); \ for (i = 0 ; i < ARRAY_SIZE(modes) ; ++i) { \ __set_bit(modes[i], cfg->supported); \ __set_bit(modes[i], cfg->advertised); \ @@ -702,10 +709,8 @@ static void ptys2ethtool_update_link_modes(unsigned long *link_modes, int i; for (i = 0; i < MLX4_LINK_MODES_SZ; i++) { if (eth_proto & MLX4_PROT_MASK(i)) - bitmap_or(link_modes, link_modes, - ptys2ethtool_link_mode(&ptys2ethtool_map[i], - report), - __ETHTOOL_LINK_MODE_MASK_NBITS); + linkmode_or(link_modes, link_modes, + ptys2ethtool_link_mode(&ptys2ethtool_map[i], report)); } } @@ -716,11 +721,9 @@ static u32 ethtool2ptys_link_modes(const unsigned long *link_modes, u32 ptys_modes = 0; for (i = 0; i < MLX4_LINK_MODES_SZ; i++) { - if (bitmap_intersects( - ptys2ethtool_link_mode(&ptys2ethtool_map[i], - report), - link_modes, - __ETHTOOL_LINK_MODE_MASK_NBITS)) + ulong *map_mode = ptys2ethtool_link_mode(&ptys2ethtool_map[i], + report); + if (linkmode_intersects(map_mode, link_modes)) ptys_modes |= 1 << i; } return ptys_modes; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c index 109472d6b61f..f1259bdb1a29 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c @@ -237,7 +237,6 @@ static void mlx4_en_remove(struct mlx4_dev *dev, void *endev_ptr) if (mdev->pndev[i]) mlx4_en_destroy_netdev(mdev->pndev[i]); - flush_workqueue(mdev->workqueue); destroy_workqueue(mdev->workqueue); (void) mlx4_mr_free(dev, &mdev->mr); iounmap(mdev->uar_map); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index a2f61a87cef8..3f6d5c384637 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -372,6 +372,9 @@ mlx4_en_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb, int nhoff = skb_network_offset(skb); int ret = 0; + if (skb->encapsulation) + return -EPROTONOSUPPORT; + if (skb->protocol != htons(ETH_P_IP)) return -EPROTONOSUPPORT; @@ -524,18 +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; @@ -556,7 +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; @@ -608,7 +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; @@ -641,7 +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); @@ -680,7 +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); @@ -698,14 +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) { @@ -794,7 +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); @@ -1073,7 +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); } @@ -1166,7 +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); @@ -1209,7 +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) { @@ -1269,7 +1272,6 @@ static void mlx4_en_do_set_rx_mode(struct work_struct *work) if (!netif_carrier_ok(dev)) { if (!mlx4_en_QUERY_PORT(mdev, priv->port)) { if (priv->port_state.link_state) { - priv->last_link_state = MLX4_DEV_EVENT_PORT_UP; netif_carrier_on(dev); en_dbg(LINK, priv, "Link Up\n"); } @@ -1346,7 +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, @@ -1557,26 +1559,36 @@ static void mlx4_en_service_task(struct work_struct *work) mutex_unlock(&mdev->state_lock); } -static void mlx4_en_linkstate(struct work_struct *work) +static void mlx4_en_linkstate(struct mlx4_en_priv *priv) +{ + struct mlx4_en_port_state *port_state = &priv->port_state; + struct mlx4_en_dev *mdev = priv->mdev; + struct net_device *dev = priv->dev; + bool up; + + if (mlx4_en_QUERY_PORT(mdev, priv->port)) + port_state->link_state = MLX4_PORT_STATE_DEV_EVENT_PORT_DOWN; + + up = port_state->link_state == MLX4_PORT_STATE_DEV_EVENT_PORT_UP; + if (up == netif_carrier_ok(dev)) + netif_carrier_event(dev); + if (!up) { + en_info(priv, "Link Down\n"); + netif_carrier_off(dev); + } else { + en_info(priv, "Link Up\n"); + netif_carrier_on(dev); + } +} + +static void mlx4_en_linkstate_work(struct work_struct *work) { struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv, linkstate_task); struct mlx4_en_dev *mdev = priv->mdev; - int linkstate = priv->link_state; mutex_lock(&mdev->state_lock); - /* If observable port state changed set carrier state and - * report to system log */ - if (priv->last_link_state != linkstate) { - if (linkstate == MLX4_DEV_EVENT_PORT_DOWN) { - en_info(priv, "Link Down\n"); - netif_carrier_off(priv->dev); - } else { - en_info(priv, "Link Up\n"); - netif_carrier_on(priv->dev); - } - } - priv->last_link_state = linkstate; + mlx4_en_linkstate(priv); mutex_unlock(&mdev->state_lock); } @@ -2079,9 +2091,11 @@ static int mlx4_en_open(struct net_device *dev) mlx4_en_clear_stats(dev); err = mlx4_en_start_port(dev); - if (err) + if (err) { en_err(priv, "Failed starting port:%d\n", priv->port); - + goto out; + } + mlx4_en_linkstate(priv); out: mutex_unlock(&mdev->state_lock); return err; @@ -3168,7 +3182,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, spin_lock_init(&priv->stats_lock); INIT_WORK(&priv->rx_mode_task, mlx4_en_do_set_rx_mode); INIT_WORK(&priv->restart_task, mlx4_en_restart); - INIT_WORK(&priv->linkstate_task, mlx4_en_linkstate); + INIT_WORK(&priv->linkstate_task, mlx4_en_linkstate_work); INIT_DELAYED_WORK(&priv->stats_task, mlx4_en_do_get_stats); INIT_DELAYED_WORK(&priv->service_task, mlx4_en_service_task); #ifdef CONFIG_RFS_ACCEL @@ -3253,7 +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..b187c210d4d6 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_set_features(devlink, DEVLINK_F_RELOAD); + devlink_register(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); @@ -4140,7 +4135,7 @@ static void mlx4_remove_one(struct pci_dev *pdev) struct devlink *devlink = priv_to_devlink(priv); 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 +4171,6 @@ 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 f3d1a20201ef..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; @@ -552,7 +555,6 @@ struct mlx4_en_priv { struct mlx4_hwq_resources res; int link_state; - int last_link_state; bool port_up; int port; int registered; 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/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 63032cd6efb1..e63bb9ceb9c0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -14,10 +14,10 @@ obj-$(CONFIG_MLX5_CORE) += mlx5_core.o mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ health.o mcg.o cq.o alloc.o port.o mr.o pd.o \ transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \ - fs_counters.o fs_ft_pool.o rl.o lag.o dev.o events.o wq.o lib/gid.o \ + fs_counters.o fs_ft_pool.o rl.o lag/lag.o dev.o events.o wq.o lib/gid.o \ lib/devcom.o lib/pci_vsc.o lib/dm.o lib/fs_ttc.o diag/fs_tracepoint.o \ diag/fw_tracer.o diag/crdump.o devlink.o diag/rsc_dump.o \ - fw_reset.o qos.o + fw_reset.o qos.o lib/tout.o # # Netdev basic @@ -37,7 +37,7 @@ mlx5_core-$(CONFIG_MLX5_EN_ARFS) += en_arfs.o mlx5_core-$(CONFIG_MLX5_EN_RXNFC) += en_fs_ethtool.o mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o mlx5_core-$(CONFIG_PCI_HYPERV_INTERFACE) += en/hv_vhca_stats.o -mlx5_core-$(CONFIG_MLX5_ESWITCH) += lag_mp.o lib/geneve.o lib/port_tun.o \ +mlx5_core-$(CONFIG_MLX5_ESWITCH) += lag/mp.o lag/port_sel.o lib/geneve.o lib/port_tun.o \ en_rep.o en/rep/bond.o en/mod_hdr.o \ en/mapping.o mlx5_core-$(CONFIG_MLX5_CLS_ACT) += en_tc.o en/rep/tc.o en/rep/neigh.o \ @@ -45,7 +45,7 @@ mlx5_core-$(CONFIG_MLX5_CLS_ACT) += en_tc.o en/rep/tc.o en/rep/neigh.o \ esw/indir_table.o en/tc_tun_encap.o \ en/tc_tun_vxlan.o en/tc_tun_gre.o en/tc_tun_geneve.o \ en/tc_tun_mplsoudp.o diag/en_tc_tracepoint.o \ - en/tc/post_act.o + en/tc/post_act.o en/tc/int_port.o mlx5_core-$(CONFIG_MLX5_TC_CT) += en/tc_ct.o mlx5_core-$(CONFIG_MLX5_TC_SAMPLE) += en/tc/sample.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index db5dfff585c9..f71ec4d9d68e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -45,6 +45,7 @@ #include "mlx5_core.h" #include "lib/eq.h" +#include "lib/tout.h" enum { CMD_IF_REV = 5, @@ -225,9 +226,13 @@ static void set_signature(struct mlx5_cmd_work_ent *ent, int csum) static void poll_timeout(struct mlx5_cmd_work_ent *ent) { - unsigned long poll_end = jiffies + msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC + 1000); + struct mlx5_core_dev *dev = container_of(ent->cmd, struct mlx5_core_dev, cmd); + u64 cmd_to_ms = mlx5_tout_ms(dev, CMD); + unsigned long poll_end; u8 own; + poll_end = jiffies + msecs_to_jiffies(cmd_to_ms + 1000); + do { own = READ_ONCE(ent->lay->status_own); if (!(own & CMD_OWNER_HW)) { @@ -925,15 +930,18 @@ static void cmd_work_handler(struct work_struct *work) { struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work); struct mlx5_cmd *cmd = ent->cmd; - struct mlx5_core_dev *dev = container_of(cmd, struct mlx5_core_dev, cmd); - unsigned long cb_timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC); + bool poll_cmd = ent->polling; struct mlx5_cmd_layout *lay; + struct mlx5_core_dev *dev; + unsigned long cb_timeout; struct semaphore *sem; unsigned long flags; - bool poll_cmd = ent->polling; int alloc_ret; int cmd_mode; + dev = container_of(cmd, struct mlx5_core_dev, cmd); + cb_timeout = msecs_to_jiffies(mlx5_tout_ms(dev, CMD)); + complete(&ent->handling); sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem; down(sem); @@ -1073,7 +1081,7 @@ static void wait_func_handle_exec_timeout(struct mlx5_core_dev *dev, static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent) { - unsigned long timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC); + unsigned long timeout = msecs_to_jiffies(mlx5_tout_ms(dev, CMD)); struct mlx5_cmd *cmd = &dev->cmd; int err; @@ -2058,7 +2066,7 @@ 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/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c index cf97985628ab..02e77ffe5c3e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c @@ -155,6 +155,8 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq) u32 in[MLX5_ST_SZ_DW(destroy_cq_in)] = {}; int err; + mlx5_debug_cq_remove(dev, cq); + mlx5_eq_del_cq(mlx5_get_async_eq(dev), cq); mlx5_eq_del_cq(&cq->eq->core, cq); @@ -162,16 +164,13 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq) MLX5_SET(destroy_cq_in, in, cqn, cq->cqn); MLX5_SET(destroy_cq_in, in, uid, cq->uid); err = mlx5_cmd_exec_in(dev, destroy_cq, in); - if (err) - return err; synchronize_irq(cq->irqn); - mlx5_debug_cq_remove(dev, cq); mlx5_cq_put(cq); wait_for_completion(&cq->free); - return 0; + return err; } EXPORT_SYMBOL(mlx5_core_destroy_cq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index e8093c4e09d4..a8b84d53dfb0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -33,6 +33,7 @@ #include <linux/mlx5/driver.h> #include <linux/mlx5/eswitch.h> #include <linux/mlx5/mlx5_ifc_vdpa.h> +#include <linux/mlx5/vport.h> #include "mlx5_core.h" /* intf dev list mutex */ @@ -537,6 +538,16 @@ int mlx5_rescan_drivers_locked(struct mlx5_core_dev *dev) return add_drivers(dev); } +static bool mlx5_same_hw_devs(struct mlx5_core_dev *dev, struct mlx5_core_dev *peer_dev) +{ + u64 fsystem_guid, psystem_guid; + + fsystem_guid = mlx5_query_nic_system_image_guid(dev); + psystem_guid = mlx5_query_nic_system_image_guid(peer_dev); + + return (fsystem_guid && psystem_guid && fsystem_guid == psystem_guid); +} + static u32 mlx5_gen_pci_id(const struct mlx5_core_dev *dev) { return (u32)((pci_domain_nr(dev->pdev->bus) << 16) | @@ -556,7 +567,8 @@ static int next_phys_dev(struct device *dev, const void *data) if (mdev == curr) return 0; - if (mlx5_gen_pci_id(mdev) != mlx5_gen_pci_id(curr)) + if (!mlx5_same_hw_devs(mdev, (struct mlx5_core_dev *)curr) && + mlx5_gen_pci_id(mdev) != mlx5_gen_pci_id(curr)) return 0; return 1; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index dcf9f27ba2ef..1c98652b244a 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); @@ -449,7 +454,8 @@ static int mlx5_devlink_enable_roce_validate(struct devlink *devlink, u32 id, struct mlx5_core_dev *dev = devlink_priv(devlink); bool new_state = val.vbool; - if (new_state && !MLX5_CAP_GEN(dev, roce)) { + if (new_state && !MLX5_CAP_GEN(dev, roce) && + !MLX5_CAP_GEN(dev, roce_rw_supported)) { NL_SET_ERR_MSG_MOD(extack, "Device doesn't support RoCE"); return -EOPNOTSUPP; } @@ -625,7 +631,6 @@ 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 +641,6 @@ 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 +676,6 @@ 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 +684,6 @@ 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 +708,6 @@ 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 +718,6 @@ 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); } @@ -797,18 +797,15 @@ static void mlx5_devlink_traps_unregister(struct devlink *devlink) int mlx5_devlink_register(struct devlink *devlink) { + struct mlx5_core_dev *dev = devlink_priv(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) @@ -818,6 +815,9 @@ int mlx5_devlink_register(struct devlink *devlink) if (err) goto traps_reg_err; + if (!mlx5_core_is_mp_slave(dev)) + devlink_set_features(devlink, DEVLINK_F_RELOAD); + return 0; traps_reg_err: @@ -825,8 +825,6 @@ 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 +832,6 @@ 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/diag/fs_tracepoint.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c index 87d65f6b5310..7841ef6c193c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c @@ -235,6 +235,9 @@ const char *parse_fs_dst(struct trace_seq *p, const char *ret = trace_seq_buffer_ptr(p); switch (dst->type) { + case MLX5_FLOW_DESTINATION_TYPE_UPLINK: + trace_seq_printf(p, "uplink\n"); + break; case MLX5_FLOW_DESTINATION_TYPE_VPORT: trace_seq_printf(p, "vport=%u\n", dst->vport.num); break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index f9cf9fb31547..eae9aa9c0811 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -745,7 +745,7 @@ static int mlx5_fw_tracer_set_mtrc_conf(struct mlx5_fw_tracer *tracer) MLX5_SET(mtrc_conf, in, trace_mode, TRACE_TO_MEMORY); MLX5_SET(mtrc_conf, in, log_trace_buffer_size, ilog2(TRACER_BUFFER_PAGE_NUM)); - MLX5_SET(mtrc_conf, in, trace_mkey, tracer->buff.mkey.key); + MLX5_SET(mtrc_conf, in, trace_mkey, tracer->buff.mkey); err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out), MLX5_REG_MTRC_CONF, 0, 1); @@ -1028,7 +1028,7 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer) err_notifier_unregister: mlx5_eq_notifier_unregister(dev, &tracer->nb); - mlx5_core_destroy_mkey(dev, &tracer->buff.mkey); + mlx5_core_destroy_mkey(dev, tracer->buff.mkey); err_dealloc_pd: mlx5_core_dealloc_pd(dev, tracer->buff.pdn); err_cancel_work: @@ -1051,7 +1051,7 @@ void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer) if (tracer->owner) mlx5_fw_tracer_ownership_release(tracer); - mlx5_core_destroy_mkey(tracer->dev, &tracer->buff.mkey); + mlx5_core_destroy_mkey(tracer->dev, tracer->buff.mkey); mlx5_core_dealloc_pd(tracer->dev, tracer->buff.pdn); } @@ -1069,7 +1069,6 @@ void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer) mlx5_fw_tracer_clean_saved_traces_array(tracer); mlx5_fw_tracer_free_strings_db(tracer); mlx5_fw_tracer_destroy_log_buf(tracer); - flush_workqueue(tracer->work_queue); destroy_workqueue(tracer->work_queue); kvfree(tracer); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h index 97252a85d65e..4762b55b0b0e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h @@ -89,7 +89,7 @@ struct mlx5_fw_tracer { void *log_buf; dma_addr_t dma; u32 size; - struct mlx5_core_mkey mkey; + u32 mkey; u32 consumer_index; } buff; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c index ed4fb79b4db7..538adab6878b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c @@ -30,7 +30,7 @@ static const char *const mlx5_rsc_sgmt_name[] = { struct mlx5_rsc_dump { u32 pdn; - struct mlx5_core_mkey mkey; + u32 mkey; u16 fw_segment_type[MLX5_SGMT_TYPE_NUM]; }; @@ -89,7 +89,7 @@ static int mlx5_rsc_dump_trigger(struct mlx5_core_dev *dev, struct mlx5_rsc_dump return -ENOMEM; in_seq_num = MLX5_GET(resource_dump, cmd->cmd, seq_num); - MLX5_SET(resource_dump, cmd->cmd, mkey, rsc_dump->mkey.key); + MLX5_SET(resource_dump, cmd->cmd, mkey, rsc_dump->mkey); MLX5_SET64(resource_dump, cmd->cmd, address, dma); err = mlx5_core_access_reg(dev, cmd->cmd, sizeof(cmd->cmd), cmd->cmd, @@ -202,7 +202,7 @@ free_page: } static int mlx5_rsc_dump_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, - struct mlx5_core_mkey *mkey) + u32 *mkey) { int inlen = MLX5_ST_SZ_BYTES(create_mkey_in); void *mkc; @@ -276,7 +276,7 @@ int mlx5_rsc_dump_init(struct mlx5_core_dev *dev) return err; destroy_mkey: - mlx5_core_destroy_mkey(dev, &rsc_dump->mkey); + mlx5_core_destroy_mkey(dev, rsc_dump->mkey); free_pd: mlx5_core_dealloc_pd(dev, rsc_dump->pdn); return err; @@ -287,6 +287,6 @@ void mlx5_rsc_dump_cleanup(struct mlx5_core_dev *dev) if (IS_ERR_OR_NULL(dev->rsc_dump)) return; - mlx5_core_destroy_mkey(dev, &dev->rsc_dump->mkey); + mlx5_core_destroy_mkey(dev, dev->rsc_dump->mkey); mlx5_core_dealloc_pd(dev, dev->rsc_dump->pdn); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 7b8c8187543a..f0ac6b0d9653 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -79,6 +79,11 @@ struct page_pool; SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) #define MLX5E_RX_MAX_HEAD (256) +#define MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE (9) +#define MLX5E_SHAMPO_WQ_HEADER_PER_PAGE (PAGE_SIZE >> MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE) +#define MLX5E_SHAMPO_WQ_BASE_HEAD_ENTRY_SIZE (64) +#define MLX5E_SHAMPO_WQ_RESRV_SIZE (64 * 1024) +#define MLX5E_SHAMPO_WQ_BASE_RESRV_SIZE (4096) #define MLX5_MPWRQ_MIN_LOG_STRIDE_SZ(mdev) \ (6 + MLX5_CAP_GEN(mdev, cache_line_128byte)) /* HW restriction */ @@ -152,6 +157,25 @@ struct page_pool; #define MLX5E_UMR_WQEBBS \ (DIV_ROUND_UP(MLX5E_UMR_WQE_INLINE_SZ, MLX5_SEND_WQE_BB)) +#define MLX5E_KLM_UMR_WQE_SZ(sgl_len)\ + (sizeof(struct mlx5e_umr_wqe) +\ + (sizeof(struct mlx5_klm) * (sgl_len))) + +#define MLX5E_KLM_UMR_WQEBBS(klm_entries) \ + (DIV_ROUND_UP(MLX5E_KLM_UMR_WQE_SZ(klm_entries), MLX5_SEND_WQE_BB)) + +#define MLX5E_KLM_UMR_DS_CNT(klm_entries)\ + (DIV_ROUND_UP(MLX5E_KLM_UMR_WQE_SZ(klm_entries), MLX5_SEND_WQE_DS)) + +#define MLX5E_KLM_MAX_ENTRIES_PER_WQE(wqe_size)\ + (((wqe_size) - sizeof(struct mlx5e_umr_wqe)) / sizeof(struct mlx5_klm)) + +#define MLX5E_KLM_ENTRIES_PER_WQE(wqe_size)\ + ALIGN_DOWN(MLX5E_KLM_MAX_ENTRIES_PER_WQE(wqe_size), MLX5_UMR_KLM_ALIGNMENT) + +#define MLX5E_MAX_KLM_PER_WQE(mdev) \ + MLX5E_KLM_ENTRIES_PER_WQE(MLX5E_TX_MPW_MAX_NUM_DS << MLX5_MKEY_BSF_OCTO_SIZE) + #define MLX5E_MSG_LEVEL NETIF_MSG_LINK #define mlx5e_dbg(mlevel, priv, format, ...) \ @@ -217,11 +241,12 @@ struct mlx5e_umr_wqe { struct mlx5_wqe_ctrl_seg ctrl; struct mlx5_wqe_umr_ctrl_seg uctrl; struct mlx5_mkey_seg mkc; - struct mlx5_mtt inline_mtts[0]; + union { + struct mlx5_mtt inline_mtts[0]; + struct mlx5_klm inline_klms[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, @@ -244,6 +269,21 @@ enum mlx5e_priv_flag { #define MLX5E_GET_PFLAG(params, pflag) (!!((params)->pflags & (BIT(pflag)))) +enum packet_merge { + MLX5E_PACKET_MERGE_NONE, + MLX5E_PACKET_MERGE_LRO, + MLX5E_PACKET_MERGE_SHAMPO, +}; + +struct mlx5e_packet_merge_param { + enum packet_merge type; + u32 timeout; + struct { + u8 match_criteria_type; + u8 alignment_granularity; + } shampo; +}; + struct mlx5e_params { u8 log_sq_size; u8 rq_wq_type; @@ -252,18 +292,21 @@ struct mlx5e_params { struct { 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; struct dim_cq_moder rx_cq_moderation; struct dim_cq_moder tx_cq_moderation; - bool lro_en; + struct mlx5e_packet_merge_param packet_merge; u8 tx_min_inline_mode; bool vlan_strip_disable; bool scatter_fcs_en; bool rx_dim_enabled; bool tx_dim_enabled; - u32 lro_timeout; u32 pflags; struct bpf_prog *xdp_prog; struct mlx5e_xsk *xsk; @@ -285,7 +328,8 @@ enum { MLX5E_RQ_STATE_NO_CSUM_COMPLETE, MLX5E_RQ_STATE_CSUM_FULL, /* cqe_csum_full hw bit is set */ MLX5E_RQ_STATE_FPGA_TLS, /* FPGA TLS enabled */ - MLX5E_RQ_STATE_MINI_CQE_HW_STRIDX /* set when mini_cqe_resp_stride_index cap is used */ + MLX5E_RQ_STATE_MINI_CQE_HW_STRIDX, /* set when mini_cqe_resp_stride_index cap is used */ + MLX5E_RQ_STATE_SHAMPO, /* set when SHAMPO cap is used */ }; struct mlx5e_cq { @@ -576,6 +620,7 @@ typedef struct sk_buff * struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt); typedef bool (*mlx5e_fp_post_rx_wqes)(struct mlx5e_rq *rq); typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq*, u16); +typedef void (*mlx5e_fp_shampo_dealloc_hd)(struct mlx5e_rq*, u16, u16, bool); int mlx5e_rq_set_handlers(struct mlx5e_rq *rq, struct mlx5e_params *params, bool xsk); void mlx5e_rq_set_trap_handlers(struct mlx5e_rq *rq, struct mlx5e_params *params); @@ -597,6 +642,25 @@ struct mlx5e_rq_frags_info { u8 wqe_bulk; }; +struct mlx5e_shampo_hd { + u32 mkey; + struct mlx5e_dma_info *info; + struct page *last_page; + u16 hd_per_wq; + u16 hd_per_wqe; + unsigned long *bitmap; + u16 pi; + u16 ci; + __be32 key; + u64 last_addr; +}; + +struct mlx5e_hw_gro_data { + struct sk_buff *skb; + struct flow_keys fk; + int second_ip_id; +}; + struct mlx5e_rq { /* data path */ union { @@ -618,6 +682,7 @@ struct mlx5e_rq { u8 umr_in_progress; u8 umr_last_bulk; u8 umr_completed; + struct mlx5e_shampo_hd *shampo; } mpwqe; }; struct { @@ -637,6 +702,8 @@ struct mlx5e_rq { struct mlx5e_icosq *icosq; struct mlx5e_priv *priv; + struct mlx5e_hw_gro_data *hw_gro_data; + mlx5e_fp_handle_rx_cqe handle_rx_cqe; mlx5e_fp_post_rx_wqes post_wqes; mlx5e_fp_dealloc_wqe dealloc_wqe; @@ -664,7 +731,7 @@ struct mlx5e_rq { u8 wq_type; u32 rqn; struct mlx5_core_dev *mdev; - struct mlx5_core_mkey umr_mkey; + u32 umr_mkey; struct mlx5e_dma_info wqe_overflow; /* XDP read-mostly */ @@ -845,6 +912,7 @@ struct mlx5e_priv { struct mlx5e_channel_stats channel_stats[MLX5E_MAX_NUM_CHANNELS]; struct mlx5e_channel_stats trap_stats; struct mlx5e_ptp_stats ptp_stats; + u16 stats_nch; u16 max_nch; u8 max_opened_tc; bool tx_ptp_opened; @@ -877,11 +945,13 @@ struct mlx5e_priv { #endif struct mlx5e_scratchpad scratchpad; struct mlx5e_htb htb; + struct mlx5e_mqprio_rl *mqprio_rl; }; struct mlx5e_rx_handlers { mlx5e_fp_handle_rx_cqe handle_rx_cqe; mlx5e_fp_handle_rx_cqe handle_rx_cqe_mpwqe; + mlx5e_fp_handle_rx_cqe handle_rx_cqe_mpwqe_shampo; }; extern const struct mlx5e_rx_handlers mlx5e_rx_handlers_nic; @@ -911,11 +981,13 @@ void mlx5e_build_ptys2ethtool_map(void); bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev); +void mlx5e_shampo_dealloc_hd(struct mlx5e_rq *rq, u16 len, u16 start, bool close); void mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats); 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); @@ -1001,7 +1073,8 @@ 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); @@ -1100,12 +1173,6 @@ int mlx5e_ethtool_set_pauseparam(struct mlx5e_priv *priv, struct ethtool_pauseparam *pauseparam); /* mlx5e generic netdev management API */ -static inline unsigned int -mlx5e_calc_max_nch(struct mlx5e_priv *priv, const struct mlx5e_profile *profile) -{ - return priv->netdev->num_rx_queues / max_t(u8, profile->rq_groups, 1); -} - static inline bool mlx5e_tx_mpwqe_supported(struct mlx5_core_dev *mdev) { @@ -1114,11 +1181,13 @@ mlx5e_tx_mpwqe_supported(struct mlx5_core_dev *mdev) } int mlx5e_priv_init(struct mlx5e_priv *priv, + const struct mlx5e_profile *profile, struct net_device *netdev, struct mlx5_core_dev *mdev); void mlx5e_priv_cleanup(struct mlx5e_priv *priv); struct net_device * -mlx5e_create_netdev(struct mlx5_core_dev *mdev, unsigned int txqs, unsigned int rxqs); +mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *profile, + unsigned int txqs, unsigned int rxqs); int mlx5e_attach_netdev(struct mlx5e_priv *priv); void mlx5e_detach_netdev(struct mlx5e_priv *priv); void mlx5e_destroy_netdev(struct mlx5e_priv *priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c index 86e079310ac3..ae52e7f38306 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c @@ -24,7 +24,7 @@ int mlx5e_devlink_port_register(struct mlx5e_priv *priv) if (mlx5_core_is_pf(priv->mdev)) { attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; - attrs.phys.port_number = PCI_FUNC(priv->mdev->pdev->devfn); + attrs.phys.port_number = mlx5_get_dev_index(priv->mdev); if (MLX5_ESWITCH_MANAGER(priv->mdev)) { mlx5e_devlink_get_port_parent_id(priv->mdev, &ppid); memcpy(attrs.switch_id.id, ppid.id, ppid.id_len); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index 41684a6c44e9..678ffbb48a25 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -125,15 +125,15 @@ struct mlx5e_ethtool_steering { void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv); void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv); -int mlx5e_ethtool_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd); -int mlx5e_ethtool_get_rxnfc(struct net_device *dev, +int mlx5e_ethtool_set_rxnfc(struct mlx5e_priv *priv, struct ethtool_rxnfc *cmd); +int mlx5e_ethtool_get_rxnfc(struct mlx5e_priv *priv, struct ethtool_rxnfc *info, u32 *rule_locs); #else static inline void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv) { } static inline void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv) { } -static inline int mlx5e_ethtool_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) +static inline int mlx5e_ethtool_set_rxnfc(struct mlx5e_priv *priv, struct ethtool_rxnfc *cmd) { return -EOPNOTSUPP; } -static inline int mlx5e_ethtool_get_rxnfc(struct net_device *dev, +static inline int mlx5e_ethtool_get_rxnfc(struct mlx5e_priv *priv, struct ethtool_rxnfc *info, u32 *rule_locs) { return -EOPNOTSUPP; } #endif /* CONFIG_MLX5_EN_RXNFC */ @@ -199,6 +199,9 @@ void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv); int mlx5e_create_flow_steering(struct mlx5e_priv *priv); void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv); +int mlx5e_fs_init(struct mlx5e_priv *priv); +void mlx5e_fs_cleanup(struct mlx5e_priv *priv); + int mlx5e_add_vlan_trap(struct mlx5e_priv *priv, int trap_id, int tir_num); void mlx5e_remove_vlan_trap(struct mlx5e_priv *priv); int mlx5e_add_mac_trap(struct mlx5e_priv *priv, int trap_id, int tir_num); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h index 018262d0164b..d5b7110a4265 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h @@ -32,7 +32,6 @@ void mlx5e_reporter_rq_cqe_err(struct mlx5e_rq *rq); void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq); #define MLX5E_REPORTER_PER_Q_MAX_LEN 256 -#define MLX5E_REPORTER_FLUSH_TIMEOUT_MSEC 2000 struct mlx5e_err_ctx { int (*recover)(void *ctx); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c index ac44bbe95c5c..d290d7276b8d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c @@ -35,7 +35,7 @@ static void mlx5e_hv_vhca_fill_stats(struct mlx5e_priv *priv, void *data, { int ch, i = 0; - for (ch = 0; ch < priv->max_nch; ch++) { + for (ch = 0; ch < priv->stats_nch; ch++) { void *buf = data + i; if (WARN_ON_ONCE(buf + @@ -51,7 +51,7 @@ static void mlx5e_hv_vhca_fill_stats(struct mlx5e_priv *priv, void *data, static int mlx5e_hv_vhca_stats_buf_size(struct mlx5e_priv *priv) { return (sizeof(struct mlx5e_hv_vhca_per_ring_stats) * - priv->max_nch); + priv->stats_nch); } static void mlx5e_hv_vhca_stats_work(struct work_struct *work) @@ -100,7 +100,7 @@ static void mlx5e_hv_vhca_stats_control(struct mlx5_hv_vhca_agent *agent, sagent = &priv->stats_agent; block->version = MLX5_HV_VHCA_STATS_VERSION; - block->rings = priv->max_nch; + block->rings = priv->stats_nch; if (!block->command) { cancel_delayed_work_sync(&priv->stats_agent.work); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 3cbb596821e8..f8c29022dbb2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -87,7 +87,8 @@ bool mlx5e_rx_is_linear_skb(struct mlx5e_params *params, u32 linear_frag_sz = max(mlx5e_rx_get_linear_frag_sz(params, xsk), mlx5e_rx_get_linear_frag_sz(params, NULL)); - return !params->lro_en && linear_frag_sz <= PAGE_SIZE; + return params->packet_merge.type == MLX5E_PACKET_MERGE_NONE && + linear_frag_sz <= PAGE_SIZE; } bool mlx5e_verify_rx_mpwqe_strides(struct mlx5_core_dev *mdev, @@ -138,6 +139,27 @@ u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params, return params->log_rq_mtu_frames - log_pkts_per_wqe; } +u8 mlx5e_shampo_get_log_hd_entry_size(struct mlx5_core_dev *mdev, + struct mlx5e_params *params) +{ + return order_base_2(DIV_ROUND_UP(MLX5E_RX_MAX_HEAD, MLX5E_SHAMPO_WQ_BASE_HEAD_ENTRY_SIZE)); +} + +u8 mlx5e_shampo_get_log_rsrv_size(struct mlx5_core_dev *mdev, + struct mlx5e_params *params) +{ + return order_base_2(MLX5E_SHAMPO_WQ_RESRV_SIZE / MLX5E_SHAMPO_WQ_BASE_RESRV_SIZE); +} + +u8 mlx5e_shampo_get_log_pkt_per_rsrv(struct mlx5_core_dev *mdev, + struct mlx5e_params *params) +{ + u32 resrv_size = BIT(mlx5e_shampo_get_log_rsrv_size(mdev, params)) * + PAGE_SIZE; + + return order_base_2(DIV_ROUND_UP(resrv_size, params->sw_mtu)); +} + u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk) @@ -164,19 +186,8 @@ u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev, mlx5e_rx_is_linear_skb(params, xsk) : mlx5e_rx_mpwqe_is_linear_skb(mdev, params, xsk); - return is_linear_skb ? mlx5e_get_linear_rq_headroom(params, xsk) : 0; -} - -struct mlx5e_lro_param mlx5e_get_lro_param(struct mlx5e_params *params) -{ - struct mlx5e_lro_param lro_param; - - lro_param = (struct mlx5e_lro_param) { - .enabled = params->lro_en, - .timeout = params->lro_timeout, - }; - - return lro_param; + return is_linear_skb || params->packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO ? + mlx5e_get_linear_rq_headroom(params, xsk) : 0; } u16 mlx5e_calc_sq_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params) @@ -453,6 +464,23 @@ static void mlx5e_build_common_cq_param(struct mlx5_core_dev *mdev, MLX5_SET(cqc, cqc, cqe_sz, CQE_STRIDE_128_PAD); } +static u32 mlx5e_shampo_get_log_cq_size(struct mlx5_core_dev *mdev, + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk) +{ + int rsrv_size = BIT(mlx5e_shampo_get_log_rsrv_size(mdev, params)) * PAGE_SIZE; + u16 num_strides = BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk)); + int pkt_per_rsrv = BIT(mlx5e_shampo_get_log_pkt_per_rsrv(mdev, params)); + u8 log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk); + int wq_size = BIT(mlx5e_mpwqe_get_log_rq_size(params, xsk)); + int wqe_size = BIT(log_stride_sz) * num_strides; + + /* +1 is for the case that the pkt_per_rsrv dont consume the reservation + * so we get a filler cqe for the rest of the reservation. + */ + return order_base_2((wqe_size / rsrv_size) * wq_size * (pkt_per_rsrv + 1)); +} + static void mlx5e_build_rx_cq_param(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, @@ -464,9 +492,12 @@ static void mlx5e_build_rx_cq_param(struct mlx5_core_dev *mdev, switch (params->rq_wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: - log_cq_size = mlx5e_mpwqe_get_log_rq_size(params, xsk) + - mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk); hw_stridx = MLX5_CAP_GEN(mdev, mini_cqe_resp_stride_index); + if (params->packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO) + log_cq_size = mlx5e_shampo_get_log_cq_size(mdev, params, xsk); + else + log_cq_size = mlx5e_mpwqe_get_log_rq_size(params, xsk) + + mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk); break; default: /* MLX5_WQ_TYPE_CYCLIC */ log_cq_size = params->log_rq_mtu_frames; @@ -485,10 +516,11 @@ static void mlx5e_build_rx_cq_param(struct mlx5_core_dev *mdev, static u8 rq_end_pad_mode(struct mlx5_core_dev *mdev, struct mlx5e_params *params) { + bool lro_en = params->packet_merge.type == MLX5E_PACKET_MERGE_LRO; bool ro = pcie_relaxed_ordering_enabled(mdev->pdev) && MLX5_CAP_GEN(mdev, relaxed_ordering_write); - return ro && params->lro_en ? + return ro && lro_en ? MLX5_WQ_END_PAD_MODE_NONE : MLX5_WQ_END_PAD_MODE_ALIGN; } @@ -520,6 +552,22 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, MLX5_SET(wq, wq, log_wqe_stride_size, log_wqe_stride_size - MLX5_MPWQE_LOG_STRIDE_SZ_BASE); MLX5_SET(wq, wq, log_wq_sz, mlx5e_mpwqe_get_log_rq_size(params, xsk)); + if (params->packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO) { + MLX5_SET(wq, wq, shampo_enable, true); + MLX5_SET(wq, wq, log_reservation_size, + mlx5e_shampo_get_log_rsrv_size(mdev, params)); + MLX5_SET(wq, wq, + log_max_num_of_packets_per_reservation, + mlx5e_shampo_get_log_pkt_per_rsrv(mdev, params)); + MLX5_SET(wq, wq, log_headers_entry_size, + mlx5e_shampo_get_log_hd_entry_size(mdev, params)); + MLX5_SET(rqc, rqc, reservation_timeout, + params->packet_merge.timeout); + MLX5_SET(rqc, rqc, shampo_match_criteria_type, + params->packet_merge.shampo.match_criteria_type); + MLX5_SET(rqc, rqc, shampo_no_match_alignment_granularity, + params->packet_merge.shampo.alignment_granularity); + } break; } default: /* MLX5_WQ_TYPE_CYCLIC */ @@ -620,17 +668,80 @@ static u8 mlx5e_get_rq_log_wq_sz(void *rqc) return MLX5_GET(wq, wq, log_wq_sz); } -static u8 mlx5e_build_icosq_log_wq_sz(struct mlx5e_params *params, +/* This function calculates the maximum number of headers entries that are needed + * per WQE, the formula is based on the size of the reservations and the + * restriction we have about max packets for reservation that is equal to max + * headers per reservation. + */ +u32 mlx5e_shampo_hd_per_wqe(struct mlx5_core_dev *mdev, + struct mlx5e_params *params, + struct mlx5e_rq_param *rq_param) +{ + int resv_size = BIT(mlx5e_shampo_get_log_rsrv_size(mdev, params)) * PAGE_SIZE; + u16 num_strides = BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params, NULL)); + int pkt_per_resv = BIT(mlx5e_shampo_get_log_pkt_per_rsrv(mdev, params)); + u8 log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params, NULL); + int wqe_size = BIT(log_stride_sz) * num_strides; + u32 hd_per_wqe; + + /* Assumption: hd_per_wqe % 8 == 0. */ + hd_per_wqe = (wqe_size / resv_size) * pkt_per_resv; + mlx5_core_dbg(mdev, "%s hd_per_wqe = %d rsrv_size = %d wqe_size = %d pkt_per_resv = %d\n", + __func__, hd_per_wqe, resv_size, wqe_size, pkt_per_resv); + return hd_per_wqe; +} + +/* This function calculates the maximum number of headers entries that are needed + * for the WQ, this value is uesed to allocate the header buffer in HW, thus + * must be a pow of 2. + */ +u32 mlx5e_shampo_hd_per_wq(struct mlx5_core_dev *mdev, + struct mlx5e_params *params, + struct mlx5e_rq_param *rq_param) +{ + void *wqc = MLX5_ADDR_OF(rqc, rq_param->rqc, wq); + int wq_size = BIT(MLX5_GET(wq, wqc, log_wq_sz)); + u32 hd_per_wqe, hd_per_wq; + + hd_per_wqe = mlx5e_shampo_hd_per_wqe(mdev, params, rq_param); + hd_per_wq = roundup_pow_of_two(hd_per_wqe * wq_size); + return hd_per_wq; +} + +static u32 mlx5e_shampo_icosq_sz(struct mlx5_core_dev *mdev, + struct mlx5e_params *params, + struct mlx5e_rq_param *rq_param) +{ + int max_num_of_umr_per_wqe, max_hd_per_wqe, max_klm_per_umr, rest; + void *wqc = MLX5_ADDR_OF(rqc, rq_param->rqc, wq); + int wq_size = BIT(MLX5_GET(wq, wqc, log_wq_sz)); + u32 wqebbs; + + max_klm_per_umr = MLX5E_MAX_KLM_PER_WQE(mdev); + max_hd_per_wqe = mlx5e_shampo_hd_per_wqe(mdev, params, rq_param); + max_num_of_umr_per_wqe = max_hd_per_wqe / max_klm_per_umr; + rest = max_hd_per_wqe % max_klm_per_umr; + wqebbs = MLX5E_KLM_UMR_WQEBBS(max_klm_per_umr) * max_num_of_umr_per_wqe; + if (rest) + wqebbs += MLX5E_KLM_UMR_WQEBBS(rest); + wqebbs *= wq_size; + return wqebbs; +} + +static u8 mlx5e_build_icosq_log_wq_sz(struct mlx5_core_dev *mdev, + struct mlx5e_params *params, struct mlx5e_rq_param *rqp) { - switch (params->rq_wq_type) { - case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: - return max_t(u8, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE, - order_base_2(MLX5E_UMR_WQEBBS) + - mlx5e_get_rq_log_wq_sz(rqp->rqc)); - default: /* MLX5_WQ_TYPE_CYCLIC */ + u32 wqebbs; + + /* MLX5_WQ_TYPE_CYCLIC */ + if (params->rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) return MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE; - } + + wqebbs = MLX5E_UMR_WQEBBS * BIT(mlx5e_get_rq_log_wq_sz(rqp->rqc)); + if (params->packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO) + wqebbs += mlx5e_shampo_icosq_sz(mdev, params, rqp); + return max_t(u8, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE, order_base_2(wqebbs)); } static u8 mlx5e_build_async_icosq_log_wq_sz(struct mlx5_core_dev *mdev) @@ -697,7 +808,7 @@ int mlx5e_build_channel_param(struct mlx5_core_dev *mdev, if (err) return err; - icosq_log_wq_sz = mlx5e_build_icosq_log_wq_sz(params, &cparam->rq); + icosq_log_wq_sz = mlx5e_build_icosq_log_wq_sz(mdev, params, &cparam->rq); async_icosq_log_wq_sz = mlx5e_build_async_icosq_log_wq_sz(mdev); mlx5e_build_sq_param(mdev, params, &cparam->txq_sq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h index 879ad46d754e..433e6967692d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h @@ -11,11 +11,6 @@ struct mlx5e_xsk_param { u16 chunk_size; }; -struct mlx5e_lro_param { - bool enabled; - u32 timeout; -}; - struct mlx5e_cq_param { u32 cqc[MLX5_ST_SZ_DW(cqc)]; struct mlx5_wq_param wq; @@ -116,6 +111,18 @@ bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev, struct mlx5e_xsk_param *xsk); u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk); +u8 mlx5e_shampo_get_log_hd_entry_size(struct mlx5_core_dev *mdev, + struct mlx5e_params *params); +u8 mlx5e_shampo_get_log_rsrv_size(struct mlx5_core_dev *mdev, + struct mlx5e_params *params); +u8 mlx5e_shampo_get_log_pkt_per_rsrv(struct mlx5_core_dev *mdev, + struct mlx5e_params *params); +u32 mlx5e_shampo_hd_per_wqe(struct mlx5_core_dev *mdev, + struct mlx5e_params *params, + struct mlx5e_rq_param *rq_param); +u32 mlx5e_shampo_hd_per_wq(struct mlx5_core_dev *mdev, + struct mlx5e_params *params, + struct mlx5e_rq_param *rq_param); u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk); @@ -125,7 +132,6 @@ u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev, u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk); -struct mlx5e_lro_param mlx5e_get_lro_param(struct mlx5e_params *params); /* Build queue parameters */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index ee688dec67a9..18d542b1c5cb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -13,8 +13,6 @@ struct mlx5e_ptp_fs { bool valid; }; -#define MLX5E_PTP_CHANNEL_IX 0 - struct mlx5e_ptp_params { struct mlx5e_params params; struct mlx5e_sq_param txq_sq_param; @@ -509,6 +507,7 @@ static int mlx5e_init_ptp_rq(struct mlx5e_ptp *c, struct mlx5e_params *params, rq->mdev = mdev; rq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); rq->stats = &c->priv->ptp_stats.rq; + rq->ix = MLX5E_PTP_CHANNEL_IX; rq->ptp_cyc2time = mlx5_rq_ts_translator(mdev); err = mlx5e_rq_set_handlers(rq, params, false); if (err) @@ -683,7 +682,7 @@ int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params, c->tstamp = &priv->tstamp; c->pdev = mlx5_core_dma_dev(priv->mdev); c->netdev = priv->netdev; - c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey.key); + c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey); c->num_tc = mlx5e_get_dcb_num_tc(params); c->stats = &priv->ptp_stats.ch; c->lag_port = lag_port; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h index c96668bd701c..a71a32e00ebb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h @@ -8,6 +8,8 @@ #include "en_stats.h" #include <linux/ptp_classify.h> +#define MLX5E_PTP_CHANNEL_IX 0 + struct mlx5e_ptpsq { struct mlx5e_txqsq txqsq; struct mlx5e_cq ts_cq; 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/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c index b5ddaa82755f..c6d2f8c78db7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c @@ -475,9 +475,6 @@ void mlx5e_rep_bridge_init(struct mlx5e_priv *priv) esw_warn(mdev, "Failed to allocate bridge offloads workqueue\n"); goto err_alloc_wq; } - INIT_DELAYED_WORK(&br_offloads->update_work, mlx5_esw_bridge_update_work); - queue_delayed_work(br_offloads->wq, &br_offloads->update_work, - msecs_to_jiffies(MLX5_ESW_BRIDGE_UPDATE_INTERVAL)); br_offloads->nb.notifier_call = mlx5_esw_bridge_switchdev_event; err = register_switchdev_notifier(&br_offloads->nb); @@ -500,6 +497,9 @@ void mlx5e_rep_bridge_init(struct mlx5e_priv *priv) err); goto err_register_netdev; } + INIT_DELAYED_WORK(&br_offloads->update_work, mlx5_esw_bridge_update_work); + queue_delayed_work(br_offloads->wq, &br_offloads->update_work, + msecs_to_jiffies(MLX5_ESW_BRIDGE_UPDATE_INTERVAL)); return; err_register_netdev: @@ -523,10 +523,10 @@ void mlx5e_rep_bridge_cleanup(struct mlx5e_priv *priv) if (!br_offloads) return; + cancel_delayed_work_sync(&br_offloads->update_work); unregister_netdevice_notifier(&br_offloads->netdev_nb); unregister_switchdev_blocking_notifier(&br_offloads->nb_blk); unregister_switchdev_notifier(&br_offloads->nb); - cancel_delayed_work(&br_offloads->update_work); destroy_workqueue(br_offloads->wq); rtnl_lock(); mlx5_esw_bridge_cleanup(esw); 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..fcb0892c08a9 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> @@ -18,10 +19,13 @@ #include "en/tc_tun.h" #include "lib/port_tun.h" #include "en/tc/sample.h" +#include "en_accel/ipsec_rxtx.h" +#include "en/tc/int_port.h" struct mlx5e_rep_indr_block_priv { struct net_device *netdev; struct mlx5e_rep_priv *rpriv; + enum flow_block_binder_type binder_type; struct list_head list; }; @@ -296,14 +300,16 @@ int mlx5e_rep_tc_event_port_affinity(struct mlx5e_priv *priv) static struct mlx5e_rep_indr_block_priv * mlx5e_rep_indr_block_priv_lookup(struct mlx5e_rep_priv *rpriv, - struct net_device *netdev) + struct net_device *netdev, + enum flow_block_binder_type binder_type) { struct mlx5e_rep_indr_block_priv *cb_priv; list_for_each_entry(cb_priv, &rpriv->uplink_priv.tc_indr_block_priv_list, list) - if (cb_priv->netdev == netdev) + if (cb_priv->netdev == netdev && + cb_priv->binder_type == binder_type) return cb_priv; return NULL; @@ -341,9 +347,13 @@ mlx5e_rep_indr_offload(struct net_device *netdev, static int mlx5e_rep_indr_setup_tc_cb(enum tc_setup_type type, void *type_data, void *indr_priv) { - unsigned long flags = MLX5_TC_FLAG(EGRESS) | MLX5_TC_FLAG(ESW_OFFLOAD); + unsigned long flags = MLX5_TC_FLAG(ESW_OFFLOAD); struct mlx5e_rep_indr_block_priv *priv = indr_priv; + flags |= (priv->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) ? + MLX5_TC_FLAG(EGRESS) : + MLX5_TC_FLAG(INGRESS); + switch (type) { case TC_SETUP_CLSFLOWER: return mlx5e_rep_indr_offload(priv->netdev, type_data, priv, @@ -409,6 +419,13 @@ 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, @@ -418,14 +435,30 @@ mlx5e_rep_indr_setup_block(struct net_device *netdev, struct Qdisc *sch, void (*cleanup)(struct flow_block_cb *block_cb)) { struct mlx5e_priv *priv = netdev_priv(rpriv->netdev); + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + bool is_ovs_int_port = netif_is_ovs_master(netdev); struct mlx5e_rep_indr_block_priv *indr_priv; 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)) + !(is_vlan_dev(netdev) && vlan_dev_real_dev(netdev) == rpriv->netdev) && + !is_ovs_int_port) { + 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 && + f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) return -EOPNOTSUPP; - if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) + if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS && !is_ovs_int_port) + return -EOPNOTSUPP; + + if (is_ovs_int_port && !mlx5e_tc_int_port_supported(esw)) return -EOPNOTSUPP; f->unlocked_driver_cb = true; @@ -433,7 +466,7 @@ mlx5e_rep_indr_setup_block(struct net_device *netdev, struct Qdisc *sch, switch (f->command) { case FLOW_BLOCK_BIND: - indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev); + indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev, f->binder_type); if (indr_priv) return -EEXIST; @@ -443,6 +476,7 @@ mlx5e_rep_indr_setup_block(struct net_device *netdev, struct Qdisc *sch, indr_priv->netdev = netdev; indr_priv->rpriv = rpriv; + indr_priv->binder_type = f->binder_type; list_add(&indr_priv->list, &rpriv->uplink_priv.tc_indr_block_priv_list); @@ -460,7 +494,7 @@ mlx5e_rep_indr_setup_block(struct net_device *netdev, struct Qdisc *sch, return 0; case FLOW_BLOCK_UNBIND: - indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev); + indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev, f->binder_type); if (!indr_priv) return -ENOENT; @@ -597,8 +631,8 @@ static bool mlx5e_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb, return false; } - /* Set tun_dev so we do dev_put() after datapath */ - tc_priv->tun_dev = dev; + /* Set fwd_dev so we do dev_put() after datapath */ + tc_priv->fwd_dev = dev; skb->dev = dev; @@ -638,6 +672,12 @@ static bool mlx5e_restore_skb_chain(struct sk_buff *skb, u32 chain, u32 reg_c1, return mlx5e_restore_tunnel(priv, skb, tc_priv, tunnel_id); } +static void mlx5_rep_tc_post_napi_receive(struct mlx5e_tc_update_priv *tc_priv) +{ + if (tc_priv->fwd_dev) + dev_put(tc_priv->fwd_dev); +} + static void mlx5e_restore_skb_sample(struct mlx5e_priv *priv, struct sk_buff *skb, struct mlx5_mapped_obj *mapped_obj, struct mlx5e_tc_update_priv *tc_priv) @@ -647,25 +687,54 @@ 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); } -bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe, - struct sk_buff *skb, - struct mlx5e_tc_update_priv *tc_priv) +static bool mlx5e_restore_skb_int_port(struct mlx5e_priv *priv, struct sk_buff *skb, + struct mlx5_mapped_obj *mapped_obj, + struct mlx5e_tc_update_priv *tc_priv, + bool *forward_tx, + u32 reg_c1) +{ + u32 tunnel_id = (reg_c1 >> ESW_TUN_OFFSET) & TUNNEL_ID_MASK; + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + struct mlx5_rep_uplink_priv *uplink_priv; + struct mlx5e_rep_priv *uplink_rpriv; + + /* Tunnel restore takes precedence over int port restore */ + if (tunnel_id) + return mlx5e_restore_tunnel(priv, skb, tc_priv, tunnel_id); + + uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); + uplink_priv = &uplink_rpriv->uplink_priv; + + if (mlx5e_tc_int_port_dev_fwd(uplink_priv->int_port_priv, skb, + mapped_obj->int_port_metadata, forward_tx)) { + /* Set fwd_dev for future dev_put */ + tc_priv->fwd_dev = skb->dev; + + return true; + } + + return false; +} + +void mlx5e_rep_tc_receive(struct mlx5_cqe64 *cqe, struct mlx5e_rq *rq, + struct sk_buff *skb) { + u32 reg_c1 = be32_to_cpu(cqe->ft_metadata); + struct mlx5e_tc_update_priv tc_priv = {}; struct mlx5_mapped_obj mapped_obj; struct mlx5_eswitch *esw; + bool forward_tx = false; struct mlx5e_priv *priv; u32 reg_c0; int err; reg_c0 = (be32_to_cpu(cqe->sop_drop_qpn) & MLX5E_TC_FLOW_ID_MASK); if (!reg_c0 || reg_c0 == MLX5_FS_DEFAULT_FLOW_TAG) - return true; + goto forward; /* If reg_c0 is not equal to the default flow tag then skb->mark * is not supported and must be reset back to 0. @@ -679,26 +748,35 @@ bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe, netdev_dbg(priv->netdev, "Couldn't find mapped object for reg_c0: %d, err: %d\n", reg_c0, err); - return false; + goto free_skb; } if (mapped_obj.type == MLX5_MAPPED_OBJ_CHAIN) { - u32 reg_c1 = be32_to_cpu(cqe->ft_metadata); - - return mlx5e_restore_skb_chain(skb, mapped_obj.chain, reg_c1, tc_priv); + if (!mlx5e_restore_skb_chain(skb, mapped_obj.chain, reg_c1, &tc_priv) && + !mlx5_ipsec_is_rx_flow(cqe)) + goto free_skb; } else if (mapped_obj.type == MLX5_MAPPED_OBJ_SAMPLE) { - mlx5e_restore_skb_sample(priv, skb, &mapped_obj, tc_priv); - return false; + mlx5e_restore_skb_sample(priv, skb, &mapped_obj, &tc_priv); + goto free_skb; + } else if (mapped_obj.type == MLX5_MAPPED_OBJ_INT_PORT_METADATA) { + if (!mlx5e_restore_skb_int_port(priv, skb, &mapped_obj, &tc_priv, + &forward_tx, reg_c1)) + goto free_skb; } else { netdev_dbg(priv->netdev, "Invalid mapped object type: %d\n", mapped_obj.type); - return false; + goto free_skb; } - return true; -} +forward: + if (forward_tx) + dev_queue_xmit(skb); + else + napi_gro_receive(rq->cq.napi, skb); -void mlx5_rep_tc_post_napi_receive(struct mlx5e_tc_update_priv *tc_priv) -{ - if (tc_priv->tun_dev) - dev_put(tc_priv->tun_dev); + mlx5_rep_tc_post_napi_receive(&tc_priv); + + return; + +free_skb: + dev_kfree_skb_any(skb); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h index d0661578467b..d6c7c81690eb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h @@ -36,10 +36,8 @@ void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv, int mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data); -bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe, - struct sk_buff *skb, - struct mlx5e_tc_update_priv *tc_priv); -void mlx5_rep_tc_post_napi_receive(struct mlx5e_tc_update_priv *tc_priv); +void mlx5e_rep_tc_receive(struct mlx5_cqe64 *cqe, struct mlx5e_rq *rq, + struct sk_buff *skb); #else /* CONFIG_MLX5_CLS_ACT */ @@ -66,13 +64,9 @@ static inline int mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { return -EOPNOTSUPP; } -struct mlx5e_tc_update_priv; -static inline bool -mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe, - struct sk_buff *skb, - struct mlx5e_tc_update_priv *tc_priv) { return true; } static inline void -mlx5_rep_tc_post_napi_receive(struct mlx5e_tc_update_priv *tc_priv) {} +mlx5e_rep_tc_receive(struct mlx5_cqe64 *cqe, struct mlx5e_rq *rq, + struct sk_buff *skb) {} #endif /* CONFIG_MLX5_CLS_ACT */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c index 0eb125316fe2..74086eb556ae 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c @@ -6,6 +6,7 @@ #include "txrx.h" #include "devlink.h" #include "ptp.h" +#include "lib/tout.h" static int mlx5e_query_rq_state(struct mlx5_core_dev *dev, u32 rqn, u8 *state) { @@ -32,8 +33,10 @@ out: static int mlx5e_wait_for_icosq_flush(struct mlx5e_icosq *icosq) { - unsigned long exp_time = jiffies + - msecs_to_jiffies(MLX5E_REPORTER_FLUSH_TIMEOUT_MSEC); + struct mlx5_core_dev *dev = icosq->channel->mdev; + unsigned long exp_time; + + exp_time = jiffies + msecs_to_jiffies(mlx5_tout_ms(dev, FLUSH_ON_ERROR)); while (time_before(jiffies, exp_time)) { if (icosq->cc == icosq->pc) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index bb682fd751c9..4f4bc8726ec4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -4,11 +4,14 @@ #include "health.h" #include "en/ptp.h" #include "en/devlink.h" +#include "lib/tout.h" static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq) { - unsigned long exp_time = jiffies + - msecs_to_jiffies(MLX5E_REPORTER_FLUSH_TIMEOUT_MSEC); + struct mlx5_core_dev *dev = sq->mdev; + unsigned long exp_time; + + exp_time = jiffies + msecs_to_jiffies(mlx5_tout_ms(dev, FLUSH_ON_ERROR)); while (time_before(jiffies, exp_time)) { if (sq->cc == sq->pc) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c index 625cd49ef96c..c1cdd8c2e37a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c @@ -127,7 +127,7 @@ mlx5e_rss_get_tt_config(struct mlx5e_rss *rss, enum mlx5_traffic_types tt) static int mlx5e_rss_create_tir(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, - const struct mlx5e_lro_param *init_lro_param, + const struct mlx5e_packet_merge_param *init_pkt_merge_param, bool inner) { struct mlx5e_rss_params_traffic_type rss_tt; @@ -161,7 +161,7 @@ static int mlx5e_rss_create_tir(struct mlx5e_rss *rss, rqtn = mlx5e_rqt_get_rqtn(&rss->rqt); mlx5e_tir_builder_build_rqt(builder, rss->mdev->mlx5e_res.hw_objs.td.tdn, rqtn, rss->inner_ft_support); - mlx5e_tir_builder_build_lro(builder, init_lro_param); + mlx5e_tir_builder_build_packet_merge(builder, init_pkt_merge_param); rss_tt = mlx5e_rss_get_tt_config(rss, tt); mlx5e_tir_builder_build_rss(builder, &rss->hash, &rss_tt, inner); @@ -198,14 +198,14 @@ static void mlx5e_rss_destroy_tir(struct mlx5e_rss *rss, enum mlx5_traffic_types } static int mlx5e_rss_create_tirs(struct mlx5e_rss *rss, - const struct mlx5e_lro_param *init_lro_param, + const struct mlx5e_packet_merge_param *init_pkt_merge_param, bool inner) { enum mlx5_traffic_types tt, max_tt; int err; for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) { - err = mlx5e_rss_create_tir(rss, tt, init_lro_param, inner); + err = mlx5e_rss_create_tir(rss, tt, init_pkt_merge_param, inner); if (err) goto err_destroy_tirs; } @@ -297,7 +297,7 @@ int mlx5e_rss_init_no_tirs(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev, int mlx5e_rss_init(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev, bool inner_ft_support, u32 drop_rqn, - const struct mlx5e_lro_param *init_lro_param) + const struct mlx5e_packet_merge_param *init_pkt_merge_param) { int err; @@ -305,12 +305,12 @@ int mlx5e_rss_init(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev, if (err) goto err_out; - err = mlx5e_rss_create_tirs(rss, init_lro_param, false); + err = mlx5e_rss_create_tirs(rss, init_pkt_merge_param, false); if (err) goto err_destroy_rqt; if (inner_ft_support) { - err = mlx5e_rss_create_tirs(rss, init_lro_param, true); + err = mlx5e_rss_create_tirs(rss, init_pkt_merge_param, true); if (err) goto err_destroy_tirs; } @@ -372,7 +372,7 @@ u32 mlx5e_rss_get_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, */ int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, - const struct mlx5e_lro_param *init_lro_param, + const struct mlx5e_packet_merge_param *init_pkt_merge_param, bool inner, u32 *tirn) { struct mlx5e_tir *tir; @@ -381,7 +381,7 @@ int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss, if (!tir) { /* TIR doesn't exist, create one */ int err; - err = mlx5e_rss_create_tir(rss, tt, init_lro_param, inner); + err = mlx5e_rss_create_tir(rss, tt, init_pkt_merge_param, inner); if (err) return err; tir = rss_get_tir(rss, tt, inner); @@ -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) @@ -418,7 +419,8 @@ void mlx5e_rss_disable(struct mlx5e_rss *rss) mlx5e_rqt_get_rqtn(&rss->rqt), rss->drop_rqn, err); } -int mlx5e_rss_lro_set_param(struct mlx5e_rss *rss, struct mlx5e_lro_param *lro_param) +int mlx5e_rss_packet_merge_set_param(struct mlx5e_rss *rss, + struct mlx5e_packet_merge_param *pkt_merge_param) { struct mlx5e_tir_builder *builder; enum mlx5_traffic_types tt; @@ -428,7 +430,7 @@ int mlx5e_rss_lro_set_param(struct mlx5e_rss *rss, struct mlx5e_lro_param *lro_p if (!builder) return -ENOMEM; - mlx5e_tir_builder_build_lro(builder, lro_param); + mlx5e_tir_builder_build_packet_merge(builder, pkt_merge_param); final_err = 0; @@ -490,6 +492,14 @@ 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 +507,8 @@ 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 +531,20 @@ 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/rss.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h index d522a10dadf3..c6b216416344 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h @@ -17,7 +17,7 @@ struct mlx5e_rss *mlx5e_rss_alloc(void); void mlx5e_rss_free(struct mlx5e_rss *rss); int mlx5e_rss_init(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev, bool inner_ft_support, u32 drop_rqn, - const struct mlx5e_lro_param *init_lro_param); + const struct mlx5e_packet_merge_param *init_pkt_merge_param); int mlx5e_rss_init_no_tirs(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev, bool inner_ft_support, u32 drop_rqn); int mlx5e_rss_cleanup(struct mlx5e_rss *rss); @@ -30,13 +30,14 @@ u32 mlx5e_rss_get_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, bool inner); int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, - const struct mlx5e_lro_param *init_lro_param, + const struct mlx5e_packet_merge_param *init_pkt_merge_param, bool inner, u32 *tirn); void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns); void mlx5e_rss_disable(struct mlx5e_rss *rss); -int mlx5e_rss_lro_set_param(struct mlx5e_rss *rss, struct mlx5e_lro_param *lro_param); +int mlx5e_rss_packet_merge_set_param(struct mlx5e_rss *rss, + struct mlx5e_packet_merge_param *pkt_merge_param); int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc); int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir, const u8 *key, const u8 *hfunc, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c index 13056cb9757d..142953847996 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c @@ -34,7 +34,7 @@ struct mlx5e_rx_res { /* API for rx_res_rss_* */ static int mlx5e_rx_res_rss_init_def(struct mlx5e_rx_res *res, - const struct mlx5e_lro_param *init_lro_param, + const struct mlx5e_packet_merge_param *init_pkt_merge_param, unsigned int init_nch) { bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT; @@ -49,7 +49,7 @@ static int mlx5e_rx_res_rss_init_def(struct mlx5e_rx_res *res, return -ENOMEM; err = mlx5e_rss_init(rss, res->mdev, inner_ft_support, res->drop_rqn, - init_lro_param); + init_pkt_merge_param); if (err) goto err_rss_free; @@ -275,7 +275,7 @@ struct mlx5e_rx_res *mlx5e_rx_res_alloc(void) } static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res, - const struct mlx5e_lro_param *init_lro_param) + const struct mlx5e_packet_merge_param *init_pkt_merge_param) { bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT; struct mlx5e_tir_builder *builder; @@ -306,7 +306,7 @@ static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res, mlx5e_tir_builder_build_rqt(builder, res->mdev->mlx5e_res.hw_objs.td.tdn, mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt), inner_ft_support); - mlx5e_tir_builder_build_lro(builder, init_lro_param); + mlx5e_tir_builder_build_packet_merge(builder, init_pkt_merge_param); mlx5e_tir_builder_build_direct(builder); err = mlx5e_tir_init(&res->channels[ix].direct_tir, builder, res->mdev, true); @@ -336,7 +336,7 @@ static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res, mlx5e_tir_builder_build_rqt(builder, res->mdev->mlx5e_res.hw_objs.td.tdn, mlx5e_rqt_get_rqtn(&res->channels[ix].xsk_rqt), inner_ft_support); - mlx5e_tir_builder_build_lro(builder, init_lro_param); + mlx5e_tir_builder_build_packet_merge(builder, init_pkt_merge_param); mlx5e_tir_builder_build_direct(builder); err = mlx5e_tir_init(&res->channels[ix].xsk_tir, builder, res->mdev, true); @@ -437,7 +437,7 @@ static void mlx5e_rx_res_ptp_destroy(struct mlx5e_rx_res *res) int mlx5e_rx_res_init(struct mlx5e_rx_res *res, struct mlx5_core_dev *mdev, enum mlx5e_rx_res_features features, unsigned int max_nch, - u32 drop_rqn, const struct mlx5e_lro_param *init_lro_param, + u32 drop_rqn, const struct mlx5e_packet_merge_param *init_pkt_merge_param, unsigned int init_nch) { int err; @@ -447,11 +447,11 @@ int mlx5e_rx_res_init(struct mlx5e_rx_res *res, struct mlx5_core_dev *mdev, res->max_nch = max_nch; res->drop_rqn = drop_rqn; - err = mlx5e_rx_res_rss_init_def(res, init_lro_param, init_nch); + err = mlx5e_rx_res_rss_init_def(res, init_pkt_merge_param, init_nch); if (err) goto err_out; - err = mlx5e_rx_res_channels_init(res, init_lro_param); + err = mlx5e_rx_res_channels_init(res, init_pkt_merge_param); if (err) goto err_rss_destroy; @@ -645,7 +645,8 @@ int mlx5e_rx_res_xsk_deactivate(struct mlx5e_rx_res *res, unsigned int ix) return err; } -int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param *lro_param) +int mlx5e_rx_res_packet_merge_set_param(struct mlx5e_rx_res *res, + struct mlx5e_packet_merge_param *pkt_merge_param) { struct mlx5e_tir_builder *builder; int err, final_err; @@ -655,7 +656,7 @@ int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param if (!builder) return -ENOMEM; - mlx5e_tir_builder_build_lro(builder, lro_param); + mlx5e_tir_builder_build_packet_merge(builder, pkt_merge_param); final_err = 0; @@ -665,7 +666,7 @@ int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param if (!rss) continue; - err = mlx5e_rss_lro_set_param(rss, lro_param); + err = mlx5e_rss_packet_merge_set_param(rss, pkt_merge_param); if (err) final_err = final_err ? : err; } @@ -673,7 +674,7 @@ int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param for (ix = 0; ix < res->max_nch; ix++) { err = mlx5e_tir_modify(&res->channels[ix].direct_tir, builder); if (err) { - mlx5_core_warn(res->mdev, "Failed to update LRO state of direct TIR %#x for channel %u: err = %d\n", + mlx5_core_warn(res->mdev, "Failed to update packet merge state of direct TIR %#x for channel %u: err = %d\n", mlx5e_tir_get_tirn(&res->channels[ix].direct_tir), ix, err); if (!final_err) final_err = err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h index 4a15942d79f7..d09f7d174a51 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h @@ -25,7 +25,7 @@ enum mlx5e_rx_res_features { struct mlx5e_rx_res *mlx5e_rx_res_alloc(void); int mlx5e_rx_res_init(struct mlx5e_rx_res *res, struct mlx5_core_dev *mdev, enum mlx5e_rx_res_features features, unsigned int max_nch, - u32 drop_rqn, const struct mlx5e_lro_param *init_lro_param, + u32 drop_rqn, const struct mlx5e_packet_merge_param *init_pkt_merge_param, unsigned int init_nch); void mlx5e_rx_res_destroy(struct mlx5e_rx_res *res); void mlx5e_rx_res_free(struct mlx5e_rx_res *res); @@ -57,7 +57,8 @@ int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx, u8 mlx5e_rx_res_rss_get_hash_fields(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt); int mlx5e_rx_res_rss_set_hash_fields(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt, u8 rx_hash_fields); -int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param *lro_param); +int mlx5e_rx_res_packet_merge_set_param(struct mlx5e_rx_res *res, + struct mlx5e_packet_merge_param *pkt_merge_param); int mlx5e_rx_res_rss_init(struct mlx5e_rx_res *res, u32 *rss_idx, unsigned int init_nch); int mlx5e_rx_res_rss_destroy(struct mlx5e_rx_res *res, u32 rss_idx); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/int_port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/int_port.c new file mode 100644 index 000000000000..ca834bbcb44f --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/int_port.c @@ -0,0 +1,457 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#include <linux/mlx5/fs.h> +#include "en/mapping.h" +#include "en/tc/int_port.h" +#include "en.h" +#include "en_rep.h" +#include "en_tc.h" + +struct mlx5e_tc_int_port { + enum mlx5e_tc_int_port_type type; + int ifindex; + u32 match_metadata; + u32 mapping; + struct list_head list; + struct mlx5_flow_handle *rx_rule; + refcount_t refcnt; + struct rcu_head rcu_head; +}; + +struct mlx5e_tc_int_port_priv { + struct mlx5_core_dev *dev; + struct mutex int_ports_lock; /* Protects int ports list */ + struct list_head int_ports; /* Uses int_ports_lock */ + u16 num_ports; + bool ul_rep_rx_ready; /* Set when uplink is performing teardown */ + struct mapping_ctx *metadata_mapping; /* Metadata for source port rewrite and matching */ +}; + +bool mlx5e_tc_int_port_supported(const struct mlx5_eswitch *esw) +{ + return mlx5_eswitch_vport_match_metadata_enabled(esw) && + MLX5_CAP_GEN(esw->dev, reg_c_preserve); +} + +u32 mlx5e_tc_int_port_get_metadata(struct mlx5e_tc_int_port *int_port) +{ + return int_port->match_metadata; +} + +int mlx5e_tc_int_port_get_flow_source(struct mlx5e_tc_int_port *int_port) +{ + /* For egress forwarding we can have the case + * where the packet came from a vport and redirected + * to int port or it came from the uplink, going + * via internal port and hairpinned back to uplink + * so we set the source to any port in this case. + */ + return int_port->type == MLX5E_TC_INT_PORT_EGRESS ? + MLX5_FLOW_CONTEXT_FLOW_SOURCE_ANY_VPORT : + MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; +} + +u32 mlx5e_tc_int_port_get_metadata_for_match(struct mlx5e_tc_int_port *int_port) +{ + return int_port->match_metadata << (32 - ESW_SOURCE_PORT_METADATA_BITS); +} + +static struct mlx5_flow_handle * +mlx5e_int_port_create_rx_rule(struct mlx5_eswitch *esw, + struct mlx5e_tc_int_port *int_port, + struct mlx5_flow_destination *dest) + +{ + struct mlx5_flow_context *flow_context; + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *flow_rule; + struct mlx5_flow_spec *spec; + void *misc; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) + return ERR_PTR(-ENOMEM); + + misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters_2); + MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0, + mlx5e_tc_int_port_get_metadata_for_match(int_port)); + + misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters_2); + MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0, + mlx5_eswitch_get_vport_metadata_mask()); + + spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2; + + /* Overwrite flow tag with the int port metadata mapping + * instead of the chain mapping. + */ + flow_context = &spec->flow_context; + flow_context->flags |= FLOW_CONTEXT_HAS_TAG; + flow_context->flow_tag = int_port->mapping; + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + flow_rule = mlx5_add_flow_rules(esw->offloads.ft_offloads, spec, + &flow_act, dest, 1); + if (IS_ERR(flow_rule)) + mlx5_core_warn(esw->dev, "ft offloads: Failed to add internal vport rx rule err %ld\n", + PTR_ERR(flow_rule)); + + kvfree(spec); + + return flow_rule; +} + +static struct mlx5e_tc_int_port * +mlx5e_int_port_lookup(struct mlx5e_tc_int_port_priv *priv, + int ifindex, + enum mlx5e_tc_int_port_type type) +{ + struct mlx5e_tc_int_port *int_port; + + if (!priv->ul_rep_rx_ready) + goto not_found; + + list_for_each_entry(int_port, &priv->int_ports, list) + if (int_port->ifindex == ifindex && int_port->type == type) { + refcount_inc(&int_port->refcnt); + return int_port; + } + +not_found: + return NULL; +} + +static int mlx5e_int_port_metadata_alloc(struct mlx5e_tc_int_port_priv *priv, + int ifindex, enum mlx5e_tc_int_port_type type, + u32 *id) +{ + u32 mapped_key[2] = {type, ifindex}; + int err; + + err = mapping_add(priv->metadata_mapping, mapped_key, id); + if (err) + return err; + + /* Fill upper 4 bits of PFNUM with reserved value */ + *id |= 0xf << ESW_VPORT_BITS; + + return 0; +} + +static void mlx5e_int_port_metadata_free(struct mlx5e_tc_int_port_priv *priv, + u32 id) +{ + id &= (1 << ESW_VPORT_BITS) - 1; + mapping_remove(priv->metadata_mapping, id); +} + +/* Must be called with priv->int_ports_lock held */ +static struct mlx5e_tc_int_port * +mlx5e_int_port_add(struct mlx5e_tc_int_port_priv *priv, + int ifindex, + enum mlx5e_tc_int_port_type type) +{ + struct mlx5_eswitch *esw = priv->dev->priv.eswitch; + struct mlx5_mapped_obj mapped_obj = {}; + struct mlx5e_rep_priv *uplink_rpriv; + struct mlx5e_tc_int_port *int_port; + struct mlx5_flow_destination dest; + struct mapping_ctx *ctx; + u32 match_metadata; + u32 mapping; + int err; + + if (priv->num_ports == MLX5E_TC_MAX_INT_PORT_NUM) { + mlx5_core_dbg(priv->dev, "Cannot add a new int port, max supported %d", + MLX5E_TC_MAX_INT_PORT_NUM); + return ERR_PTR(-ENOSPC); + } + + int_port = kzalloc(sizeof(*int_port), GFP_KERNEL); + if (!int_port) + return ERR_PTR(-ENOMEM); + + err = mlx5e_int_port_metadata_alloc(priv, ifindex, type, &match_metadata); + if (err) { + mlx5_core_warn(esw->dev, "Cannot add a new internal port, metadata allocation failed for ifindex %d", + ifindex); + goto err_metadata; + } + + /* map metadata to reg_c0 object for miss handling */ + ctx = esw->offloads.reg_c0_obj_pool; + mapped_obj.type = MLX5_MAPPED_OBJ_INT_PORT_METADATA; + mapped_obj.int_port_metadata = match_metadata; + err = mapping_add(ctx, &mapped_obj, &mapping); + if (err) + goto err_map; + + int_port->type = type; + int_port->ifindex = ifindex; + int_port->match_metadata = match_metadata; + int_port->mapping = mapping; + + /* Create a match on internal vport metadata in vport table */ + uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); + + dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + dest.ft = uplink_rpriv->root_ft; + + int_port->rx_rule = mlx5e_int_port_create_rx_rule(esw, int_port, &dest); + if (IS_ERR(int_port->rx_rule)) { + err = PTR_ERR(int_port->rx_rule); + mlx5_core_warn(esw->dev, "Can't add internal port rx rule, err %d", err); + goto err_rx_rule; + } + + refcount_set(&int_port->refcnt, 1); + list_add_rcu(&int_port->list, &priv->int_ports); + priv->num_ports++; + + return int_port; + +err_rx_rule: + mapping_remove(ctx, int_port->mapping); + +err_map: + mlx5e_int_port_metadata_free(priv, match_metadata); + +err_metadata: + kfree(int_port); + + return ERR_PTR(err); +} + +/* Must be called with priv->int_ports_lock held */ +static void +mlx5e_int_port_remove(struct mlx5e_tc_int_port_priv *priv, + struct mlx5e_tc_int_port *int_port) +{ + struct mlx5_eswitch *esw = priv->dev->priv.eswitch; + struct mapping_ctx *ctx; + + ctx = esw->offloads.reg_c0_obj_pool; + + list_del_rcu(&int_port->list); + + /* The following parameters are not used by the + * rcu readers of this int_port object so it is + * safe to release them. + */ + if (int_port->rx_rule) + mlx5_del_flow_rules(int_port->rx_rule); + mapping_remove(ctx, int_port->mapping); + mlx5e_int_port_metadata_free(priv, int_port->match_metadata); + kfree_rcu(int_port); + priv->num_ports--; +} + +/* Must be called with rcu_read_lock held */ +static struct mlx5e_tc_int_port * +mlx5e_int_port_get_from_metadata(struct mlx5e_tc_int_port_priv *priv, + u32 metadata) +{ + struct mlx5e_tc_int_port *int_port; + + list_for_each_entry_rcu(int_port, &priv->int_ports, list) + if (int_port->match_metadata == metadata) + return int_port; + + return NULL; +} + +struct mlx5e_tc_int_port * +mlx5e_tc_int_port_get(struct mlx5e_tc_int_port_priv *priv, + int ifindex, + enum mlx5e_tc_int_port_type type) +{ + struct mlx5e_tc_int_port *int_port; + + if (!priv) + return ERR_PTR(-EOPNOTSUPP); + + mutex_lock(&priv->int_ports_lock); + + /* Reject request if ul rep not ready */ + if (!priv->ul_rep_rx_ready) { + int_port = ERR_PTR(-EOPNOTSUPP); + goto done; + } + + int_port = mlx5e_int_port_lookup(priv, ifindex, type); + if (int_port) + goto done; + + /* Alloc and add new int port to list */ + int_port = mlx5e_int_port_add(priv, ifindex, type); + +done: + mutex_unlock(&priv->int_ports_lock); + + return int_port; +} + +void +mlx5e_tc_int_port_put(struct mlx5e_tc_int_port_priv *priv, + struct mlx5e_tc_int_port *int_port) +{ + if (!refcount_dec_and_mutex_lock(&int_port->refcnt, &priv->int_ports_lock)) + return; + + mlx5e_int_port_remove(priv, int_port); + mutex_unlock(&priv->int_ports_lock); +} + +struct mlx5e_tc_int_port_priv * +mlx5e_tc_int_port_init(struct mlx5e_priv *priv) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + struct mlx5e_tc_int_port_priv *int_port_priv; + u64 mapping_id; + + if (!mlx5e_tc_int_port_supported(esw)) + return NULL; + + int_port_priv = kzalloc(sizeof(*int_port_priv), GFP_KERNEL); + if (!int_port_priv) + return NULL; + + mapping_id = mlx5_query_nic_system_image_guid(priv->mdev); + + int_port_priv->metadata_mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_INT_PORT, + sizeof(u32) * 2, + (1 << ESW_VPORT_BITS) - 1, true); + if (IS_ERR(int_port_priv->metadata_mapping)) { + mlx5_core_warn(priv->mdev, "Can't allocate metadata mapping of int port offload, err=%ld\n", + PTR_ERR(int_port_priv->metadata_mapping)); + goto err_mapping; + } + + int_port_priv->dev = priv->mdev; + mutex_init(&int_port_priv->int_ports_lock); + INIT_LIST_HEAD(&int_port_priv->int_ports); + + return int_port_priv; + +err_mapping: + kfree(int_port_priv); + + return NULL; +} + +void +mlx5e_tc_int_port_cleanup(struct mlx5e_tc_int_port_priv *priv) +{ + if (!priv) + return; + + mutex_destroy(&priv->int_ports_lock); + mapping_destroy(priv->metadata_mapping); + kfree(priv); +} + +/* Int port rx rules reside in ul rep rx tables. + * It is possible the ul rep will go down while there are + * still int port rules in its rx table so proper cleanup + * is required to free resources. + */ +void mlx5e_tc_int_port_init_rep_rx(struct mlx5e_priv *priv) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + struct mlx5_rep_uplink_priv *uplink_priv; + struct mlx5e_tc_int_port_priv *ppriv; + struct mlx5e_rep_priv *uplink_rpriv; + + uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); + uplink_priv = &uplink_rpriv->uplink_priv; + + ppriv = uplink_priv->int_port_priv; + + if (!ppriv) + return; + + mutex_lock(&ppriv->int_ports_lock); + ppriv->ul_rep_rx_ready = true; + mutex_unlock(&ppriv->int_ports_lock); +} + +void mlx5e_tc_int_port_cleanup_rep_rx(struct mlx5e_priv *priv) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + struct mlx5_rep_uplink_priv *uplink_priv; + struct mlx5e_tc_int_port_priv *ppriv; + struct mlx5e_rep_priv *uplink_rpriv; + struct mlx5e_tc_int_port *int_port; + + uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); + uplink_priv = &uplink_rpriv->uplink_priv; + + ppriv = uplink_priv->int_port_priv; + + if (!ppriv) + return; + + mutex_lock(&ppriv->int_ports_lock); + + ppriv->ul_rep_rx_ready = false; + + list_for_each_entry(int_port, &ppriv->int_ports, list) { + if (!IS_ERR_OR_NULL(int_port->rx_rule)) + mlx5_del_flow_rules(int_port->rx_rule); + + int_port->rx_rule = NULL; + } + + mutex_unlock(&ppriv->int_ports_lock); +} + +bool +mlx5e_tc_int_port_dev_fwd(struct mlx5e_tc_int_port_priv *priv, + struct sk_buff *skb, u32 int_vport_metadata, + bool *forward_tx) +{ + enum mlx5e_tc_int_port_type fwd_type; + struct mlx5e_tc_int_port *int_port; + struct net_device *dev; + int ifindex; + + if (!priv) + return false; + + rcu_read_lock(); + int_port = mlx5e_int_port_get_from_metadata(priv, int_vport_metadata); + if (!int_port) { + rcu_read_unlock(); + mlx5_core_dbg(priv->dev, "Unable to find int port with metadata 0x%.8x\n", + int_vport_metadata); + return false; + } + + ifindex = int_port->ifindex; + fwd_type = int_port->type; + rcu_read_unlock(); + + dev = dev_get_by_index(&init_net, ifindex); + if (!dev) { + mlx5_core_dbg(priv->dev, + "Couldn't find internal port device with ifindex: %d\n", + ifindex); + return false; + } + + skb->skb_iif = dev->ifindex; + skb->dev = dev; + + if (fwd_type == MLX5E_TC_INT_PORT_INGRESS) { + skb->pkt_type = PACKET_HOST; + skb_set_redirected(skb, true); + *forward_tx = false; + } else { + skb_reset_network_header(skb); + skb_push_rcsum(skb, skb->mac_len); + skb_set_redirected(skb, false); + *forward_tx = true; + } + + return true; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/int_port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/int_port.h new file mode 100644 index 000000000000..e72c79d308d7 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/int_port.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#ifndef __MLX5_EN_TC_INT_PORT_H__ +#define __MLX5_EN_TC_INT_PORT_H__ + +#include "en.h" + +struct mlx5e_tc_int_port; +struct mlx5e_tc_int_port_priv; + +enum mlx5e_tc_int_port_type { + MLX5E_TC_INT_PORT_INGRESS, + MLX5E_TC_INT_PORT_EGRESS, +}; + +#if IS_ENABLED(CONFIG_MLX5_CLS_ACT) +bool mlx5e_tc_int_port_supported(const struct mlx5_eswitch *esw); + +struct mlx5e_tc_int_port_priv * +mlx5e_tc_int_port_init(struct mlx5e_priv *priv); +void +mlx5e_tc_int_port_cleanup(struct mlx5e_tc_int_port_priv *priv); + +void mlx5e_tc_int_port_init_rep_rx(struct mlx5e_priv *priv); +void mlx5e_tc_int_port_cleanup_rep_rx(struct mlx5e_priv *priv); + +bool +mlx5e_tc_int_port_dev_fwd(struct mlx5e_tc_int_port_priv *priv, + struct sk_buff *skb, u32 int_vport_metadata, + bool *forward_tx); +struct mlx5e_tc_int_port * +mlx5e_tc_int_port_get(struct mlx5e_tc_int_port_priv *priv, + int ifindex, + enum mlx5e_tc_int_port_type type); +void +mlx5e_tc_int_port_put(struct mlx5e_tc_int_port_priv *priv, + struct mlx5e_tc_int_port *int_port); + +u32 mlx5e_tc_int_port_get_metadata(struct mlx5e_tc_int_port *int_port); +u32 mlx5e_tc_int_port_get_metadata_for_match(struct mlx5e_tc_int_port *int_port); +int mlx5e_tc_int_port_get_flow_source(struct mlx5e_tc_int_port *int_port); +#else /* CONFIG_MLX5_CLS_ACT */ +static inline u32 +mlx5e_tc_int_port_get_metadata_for_match(struct mlx5e_tc_int_port *int_port) +{ + return 0; +} + +static inline int +mlx5e_tc_int_port_get_flow_source(struct mlx5e_tc_int_port *int_port) +{ + return 0; +} + +static inline bool mlx5e_tc_int_port_supported(const struct mlx5_eswitch *esw) +{ + return false; +} + +static inline void mlx5e_tc_int_port_init_rep_rx(struct mlx5e_priv *priv) {} +static inline void mlx5e_tc_int_port_cleanup_rep_rx(struct mlx5e_priv *priv) {} + +#endif /* CONFIG_MLX5_CLS_ACT */ +#endif /* __MLX5_EN_TC_INT_PORT_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c index a3e43e898a56..31b4e39be2d3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c @@ -4,6 +4,7 @@ #include "en_tc.h" #include "post_act.h" #include "mlx5_core.h" +#include "fs_core.h" struct mlx5e_post_act { enum mlx5_flow_namespace_type ns_type; @@ -28,16 +29,14 @@ struct mlx5e_post_act * mlx5e_tc_post_act_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains, enum mlx5_flow_namespace_type ns_type) { + enum fs_flow_table_type table_type = ns_type == MLX5_FLOW_NAMESPACE_FDB ? + FS_FT_FDB : FS_FT_NIC_RX; struct mlx5e_post_act *post_act; int err; - if (ns_type == MLX5_FLOW_NAMESPACE_FDB && - !MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev, ignore_flow_level)) { - mlx5_core_warn(priv->mdev, "firmware level support is missing\n"); - err = -EOPNOTSUPP; - goto err_check; - } else if (!MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, ignore_flow_level)) { - mlx5_core_warn(priv->mdev, "firmware level support is missing\n"); + if (!MLX5_CAP_FLOWTABLE_TYPE(priv->mdev, ignore_flow_level, table_type)) { + if (priv->mdev->coredev_type != MLX5_COREDEV_VF) + mlx5_core_warn(priv->mdev, "firmware level support is missing\n"); err = -EOPNOTSUPP; goto err_check; } 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..df6888c4793c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c @@ -509,13 +509,6 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, if (IS_ERR_OR_NULL(tc_psample)) return ERR_PTR(-EOPNOTSUPP); - /* If slow path flag is set, eg. when the neigh is invalid for encap, - * don't offload sample action. - */ - esw = tc_psample->esw; - if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH) - return mlx5_eswitch_add_offloaded_rule(esw, spec, attr); - sample_flow = kzalloc(sizeof(*sample_flow), GFP_KERNEL); if (!sample_flow) return ERR_PTR(-ENOMEM); @@ -527,6 +520,7 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, * Only match the fte id instead of the same match in the * original flow table. */ + esw = tc_psample->esw; if (MLX5_CAP_GEN(esw->dev, reg_c_preserve) || attr->action & MLX5_FLOW_CONTEXT_ACTION_DECAP) { struct mlx5_flow_table *ft; @@ -602,7 +596,7 @@ 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 +607,7 @@ 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) @@ -628,45 +622,26 @@ 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)) return; - /* If slow path flag is set, sample action is not offloaded. - * No need to delete sample rule. - */ - esw = tc_psample->esw; - if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH) { - mlx5_eswitch_del_offloaded_rule(esw, rule, attr); - return; - } - /* The following delete order can't be changed, otherwise, * will hit fw syndromes. */ + esw = tc_psample->esw; 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..c1c6e74c79c4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -889,7 +889,7 @@ mlx5_tc_ct_counter_create(struct mlx5_tc_ct_priv *ct_priv) return ERR_PTR(-ENOMEM); counter->is_shared = false; - counter->counter = mlx5_fc_create(ct_priv->dev, true); + counter->counter = mlx5_fc_create_ex(ct_priv->dev, true); if (IS_ERR(counter->counter)) { ct_dbg("Failed to create counter for ct entry"); ret = PTR_ERR(counter->counter); @@ -2039,25 +2039,36 @@ mlx5_tc_ct_init_check_esw_support(struct mlx5_eswitch *esw, static int mlx5_tc_ct_init_check_support(struct mlx5e_priv *priv, enum mlx5_flow_namespace_type ns_type, - struct mlx5e_post_act *post_act, - const char **err_msg) + struct mlx5e_post_act *post_act) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + const char *err_msg = NULL; + int err = 0; #if !IS_ENABLED(CONFIG_NET_TC_SKB_EXT) /* cannot restore chain ID on HW miss */ - *err_msg = "tc skb extension missing"; - return -EOPNOTSUPP; + err_msg = "tc skb extension missing"; + err = -EOPNOTSUPP; + goto out_err; #endif if (IS_ERR_OR_NULL(post_act)) { - *err_msg = "tc ct offload not supported, post action is missing"; - return -EOPNOTSUPP; + /* Ignore_flow_level support isn't supported by default for VFs and so post_act + * won't be supported. Skip showing error msg. + */ + if (priv->mdev->coredev_type != MLX5_COREDEV_VF) + err_msg = "post action is missing"; + err = -EOPNOTSUPP; + goto out_err; } if (ns_type == MLX5_FLOW_NAMESPACE_FDB) - return mlx5_tc_ct_init_check_esw_support(esw, err_msg); - return 0; + err = mlx5_tc_ct_init_check_esw_support(esw, &err_msg); + +out_err: + if (err && err_msg) + netdev_dbg(priv->netdev, "tc ct offload not supported, %s\n", err_msg); + return err; } #define INIT_ERR_PREFIX "tc ct offload init failed" @@ -2070,16 +2081,13 @@ mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains, { struct mlx5_tc_ct_priv *ct_priv; struct mlx5_core_dev *dev; - const char *msg; u64 mapping_id; int err; dev = priv->mdev; - err = mlx5_tc_ct_init_check_support(priv, ns_type, post_act, &msg); - if (err) { - mlx5_core_warn(dev, "tc ct offload not supported, %s\n", msg); + err = mlx5_tc_ct_init_check_support(priv, ns_type, post_act); + if (err) goto err_support; - } ct_priv = kzalloc(sizeof(*ct_priv), GFP_KERNEL); if (!ct_priv) @@ -2127,12 +2135,21 @@ 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: + mlx5_chains_destroy_global_table(chains, ct_priv->ct_nat); 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_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h index d1599b7b944b..8f64f2c8895a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h @@ -173,4 +173,6 @@ void mlx5e_flow_put(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow); struct mlx5_fc *mlx5e_tc_get_counter(struct mlx5e_tc_flow *flow); +struct mlx5e_tc_int_port_priv * +mlx5e_get_int_port_priv(struct mlx5e_priv *priv); #endif /* __MLX5_EN_TC_PRIV_H__ */ 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..a5e450973225 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -10,6 +10,8 @@ #include "en_tc.h" #include "rep/tc.h" #include "rep/neigh.h" +#include "lag/lag.h" +#include "lag/mp.h" struct mlx5e_tc_tun_route_attr { struct net_device *out_dev; @@ -81,7 +83,8 @@ static int get_route_and_out_devs(struct mlx5e_priv *priv, */ *route_dev = dev; if (!netdev_port_same_parent_id(priv->netdev, real_dev) || - dst_is_lag_dev || is_vlan_dev(*route_dev)) + dst_is_lag_dev || is_vlan_dev(*route_dev) || + netif_is_ovs_master(*route_dev)) *out_dev = uplink_dev; else if (mlx5e_eswitch_rep(dev) && mlx5e_is_valid_eswitch_fwd_dev(priv, dev)) @@ -118,6 +121,11 @@ 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 +443,15 @@ 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)) @@ -700,6 +711,7 @@ int mlx5e_tc_tun_route_lookup(struct mlx5e_priv *priv, struct mlx5_flow_attr *flow_attr) { struct mlx5_esw_flow_attr *esw_attr = flow_attr->esw_attr; + struct mlx5e_tc_int_port *int_port; TC_TUN_ROUTE_ATTR_INIT(attr); u16 vport_num; int err = 0; @@ -724,17 +736,25 @@ int mlx5e_tc_tun_route_lookup(struct mlx5e_priv *priv, if (err) return err; - if (attr.route_dev->netdev_ops != &mlx5e_netdev_ops || - !mlx5e_tc_is_vf_tunnel(attr.out_dev, attr.route_dev)) - goto out; - - err = mlx5e_tc_query_route_vport(attr.out_dev, attr.route_dev, &vport_num); - if (err) - goto out; + if (attr.route_dev->netdev_ops == &mlx5e_netdev_ops && + mlx5e_tc_is_vf_tunnel(attr.out_dev, attr.route_dev)) { + err = mlx5e_tc_query_route_vport(attr.out_dev, attr.route_dev, &vport_num); + if (err) + goto out; - esw_attr->rx_tun_attr->vni = MLX5_GET(fte_match_param, spec->match_value, - misc_parameters.vxlan_vni); - esw_attr->rx_tun_attr->decap_vport = vport_num; + esw_attr->rx_tun_attr->vni = MLX5_GET(fte_match_param, spec->match_value, + misc_parameters.vxlan_vni); + esw_attr->rx_tun_attr->decap_vport = vport_num; + } else if (netif_is_ovs_master(attr.route_dev)) { + int_port = mlx5e_tc_int_port_get(mlx5e_get_int_port_priv(priv), + attr.route_dev->ifindex, + MLX5E_TC_INT_PORT_INGRESS); + if (IS_ERR(int_port)) { + err = PTR_ERR(int_port); + goto out; + } + esw_attr->int_port = int_port; + } out: if (flow_attr->tun_ip_version == 4) 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_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 1c44c6c345f5..660cca73c36c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -13,6 +13,30 @@ enum { MLX5E_ROUTE_ENTRY_VALID = BIT(0), }; +static int mlx5e_set_int_port_tunnel(struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr, + struct mlx5e_encap_entry *e, + int out_index) +{ + struct net_device *route_dev; + int err = 0; + + route_dev = dev_get_by_index(dev_net(e->out_dev), e->route_dev_ifindex); + + if (!route_dev || !netif_is_ovs_master(route_dev)) + goto out; + + err = mlx5e_set_fwd_to_int_port_actions(priv, attr, e->route_dev_ifindex, + MLX5E_TC_INT_PORT_EGRESS, + &attr->action, out_index); + +out: + if (route_dev) + dev_put(route_dev); + + return err; +} + struct mlx5e_route_key { int ip_version; union { @@ -809,6 +833,17 @@ attach_flow: if (err) goto out_err; + err = mlx5e_set_int_port_tunnel(priv, attr, e, out_index); + if (err == -EOPNOTSUPP) { + /* If device doesn't support int port offload, + * redirect to uplink vport. + */ + mlx5_core_dbg(priv->mdev, "attaching int port as encap dev not supported, using uplink\n"); + err = 0; + } else if (err) { + goto out_err; + } + flow->encaps[out_index].e = e; list_add(&flow->encaps[out_index].list, &e->flows); flow->encaps[out_index].index = out_index; 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/tir.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c index de936dc4bc48..da169b816665 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c @@ -70,24 +70,30 @@ void mlx5e_tir_builder_build_rqt(struct mlx5e_tir_builder *builder, u32 tdn, MLX5_SET(tirc, tirc, tunneled_offload_en, inner_ft_support); } -void mlx5e_tir_builder_build_lro(struct mlx5e_tir_builder *builder, - const struct mlx5e_lro_param *lro_param) +void mlx5e_tir_builder_build_packet_merge(struct mlx5e_tir_builder *builder, + const struct mlx5e_packet_merge_param *pkt_merge_param) { void *tirc = mlx5e_tir_builder_get_tirc(builder); const unsigned int rough_max_l2_l3_hdr_sz = 256; if (builder->modify) - MLX5_SET(modify_tir_in, builder->in, bitmask.lro, 1); - - if (!lro_param->enabled) - return; - - MLX5_SET(tirc, tirc, lro_enable_mask, - MLX5_TIRC_LRO_ENABLE_MASK_IPV4_LRO | - MLX5_TIRC_LRO_ENABLE_MASK_IPV6_LRO); - MLX5_SET(tirc, tirc, lro_max_ip_payload_size, - (MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ - rough_max_l2_l3_hdr_sz) >> 8); - MLX5_SET(tirc, tirc, lro_timeout_period_usecs, lro_param->timeout); + MLX5_SET(modify_tir_in, builder->in, bitmask.packet_merge, 1); + + switch (pkt_merge_param->type) { + case MLX5E_PACKET_MERGE_LRO: + MLX5_SET(tirc, tirc, packet_merge_mask, + MLX5_TIRC_PACKET_MERGE_MASK_IPV4_LRO | + MLX5_TIRC_PACKET_MERGE_MASK_IPV6_LRO); + MLX5_SET(tirc, tirc, lro_max_ip_payload_size, + (MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ - rough_max_l2_l3_hdr_sz) >> 8); + MLX5_SET(tirc, tirc, lro_timeout_period_usecs, pkt_merge_param->timeout); + break; + case MLX5E_PACKET_MERGE_SHAMPO: + MLX5_SET(tirc, tirc, packet_merge_mask, MLX5_TIRC_PACKET_MERGE_MASK_SHAMPO); + break; + default: + break; + } } static int mlx5e_hfunc_to_hw(u8 hfunc) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h index e45149a78ed9..857a84bcd53a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h @@ -18,7 +18,7 @@ struct mlx5e_rss_params_traffic_type { }; struct mlx5e_tir_builder; -struct mlx5e_lro_param; +struct mlx5e_packet_merge_param; struct mlx5e_tir_builder *mlx5e_tir_builder_alloc(bool modify); void mlx5e_tir_builder_free(struct mlx5e_tir_builder *builder); @@ -27,8 +27,8 @@ void mlx5e_tir_builder_clear(struct mlx5e_tir_builder *builder); void mlx5e_tir_builder_build_inline(struct mlx5e_tir_builder *builder, u32 tdn, u32 rqn); void mlx5e_tir_builder_build_rqt(struct mlx5e_tir_builder *builder, u32 tdn, u32 rqtn, bool inner_ft_support); -void mlx5e_tir_builder_build_lro(struct mlx5e_tir_builder *builder, - const struct mlx5e_lro_param *lro_param); +void mlx5e_tir_builder_build_packet_merge(struct mlx5e_tir_builder *builder, + const struct mlx5e_packet_merge_param *pkt_merge_param); void mlx5e_tir_builder_build_rss(struct mlx5e_tir_builder *builder, const struct mlx5e_rss_params_hash *rss_hash, const struct mlx5e_rss_params_traffic_type *rss_tt, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c index d54607a42740..a55b066746cb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c @@ -137,7 +137,7 @@ static struct mlx5e_trap *mlx5e_open_trap(struct mlx5e_priv *priv) t->tstamp = &priv->tstamp; t->pdev = mlx5_core_dma_dev(priv->mdev); t->netdev = priv->netdev; - t->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey.key); + t->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey); t->stats = &priv->trap_stats.ch; netif_napi_add(netdev, &t->napi, mlx5e_trap_napi_poll, 64); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index 055c3bc23733..4cdf8e5b24c2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -36,6 +36,7 @@ ktime_t mlx5e_cqe_ts_to_ns(cqe_ts_to_ns func, struct mlx5_clock *clock, u64 cqe_ enum mlx5e_icosq_wqe_type { MLX5E_ICOSQ_WQE_NOP, MLX5E_ICOSQ_WQE_UMR_RX, + MLX5E_ICOSQ_WQE_SHAMPO_HD_UMR, #ifdef CONFIG_MLX5_EN_TLS MLX5E_ICOSQ_WQE_UMR_TLS, MLX5E_ICOSQ_WQE_SET_PSV_TLS, @@ -166,6 +167,10 @@ static inline u16 mlx5e_txqsq_get_next_pi(struct mlx5e_txqsq *sq, u16 size) return pi; } +struct mlx5e_shampo_umr { + u16 len; +}; + struct mlx5e_icosq_wqe_info { u8 wqe_type; u8 num_wqebbs; @@ -175,6 +180,7 @@ struct mlx5e_icosq_wqe_info { struct { struct mlx5e_rq *rq; } umr; + struct mlx5e_shampo_umr shampo; #ifdef CONFIG_MLX5_EN_TLS struct { struct mlx5e_ktls_offload_context_rx *priv_rx; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c index 33de8f0092a6..fb5397324aa4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c @@ -141,8 +141,7 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb, * Pkt: MAC IP ESP IP L4 * * Transport Mode: - * SWP: OutL3 InL4 - * InL3 + * SWP: OutL3 OutL4 * Pkt: MAC IP ESP L4 * * Tunnel(VXLAN TCP/UDP) over Transport Mode @@ -171,31 +170,35 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb, return; if (!xo->inner_ipproto) { - eseg->swp_inner_l3_offset = skb_network_offset(skb) / 2; - eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2; - if (skb->protocol == htons(ETH_P_IPV6)) - eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6; - if (xo->proto == IPPROTO_UDP) + switch (xo->proto) { + case IPPROTO_UDP: + eseg->swp_flags |= MLX5_ETH_WQE_SWP_OUTER_L4_UDP; + fallthrough; + case IPPROTO_TCP: + /* IP | ESP | TCP */ + eseg->swp_outer_l4_offset = skb_inner_transport_offset(skb) / 2; + break; + default: + break; + } + } else { + /* Tunnel(VXLAN TCP/UDP) over Transport Mode */ + switch (xo->inner_ipproto) { + case IPPROTO_UDP: eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP; - return; - } - - /* Tunnel(VXLAN TCP/UDP) over Transport Mode */ - switch (xo->inner_ipproto) { - case IPPROTO_UDP: - eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP; - fallthrough; - case IPPROTO_TCP: - eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2; - eseg->swp_inner_l4_offset = (skb->csum_start + skb->head - skb->data) / 2; - if (skb->protocol == htons(ETH_P_IPV6)) - eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6; - break; - default: - break; + fallthrough; + case IPPROTO_TCP: + eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2; + eseg->swp_inner_l4_offset = + (skb->csum_start + skb->head - skb->data) / 2; + if (skb->protocol == htons(ETH_P_IPV6)) + eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6; + break; + default: + break; + } } - return; } void mlx5e_ipsec_set_iv_esn(struct sk_buff *skb, struct xfrm_state *x, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h index 5120a59361e6..b98db50c3418 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h @@ -127,6 +127,25 @@ out_disable: return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } +static inline bool +mlx5e_ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, + struct mlx5_wqe_eth_seg *eseg) +{ + struct xfrm_offload *xo = xfrm_offload(skb); + + if (!mlx5e_ipsec_eseg_meta(eseg)) + return false; + + eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM; + if (xo->inner_ipproto) { + eseg->cs_flags |= MLX5_ETH_WQE_L4_INNER_CSUM | MLX5_ETH_WQE_L3_INNER_CSUM; + } else if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) { + eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM; + sq->stats->csum_partial_inner++; + } + + return true; +} #else static inline void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev, @@ -143,6 +162,13 @@ static inline bool mlx5_ipsec_is_rx_flow(struct mlx5_cqe64 *cqe) { return false; static inline netdev_features_t mlx5e_ipsec_feature_check(struct sk_buff *skb, netdev_features_t features) { return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } + +static inline bool +mlx5e_ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, + struct mlx5_wqe_eth_seg *eseg) +{ + return false; +} #endif /* CONFIG_MLX5_EN_IPSEC */ #endif /* __MLX5E_IPSEC_RXTX_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 84eb7201c142..c0f409c195bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -47,7 +47,7 @@ void mlx5e_mkey_set_relaxed_ordering(struct mlx5_core_dev *mdev, void *mkc) } static int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, - struct mlx5_core_mkey *mkey) + u32 *mkey) { int inlen = MLX5_ST_SZ_BYTES(create_mkey_in); void *mkc; @@ -108,7 +108,7 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev) return 0; err_destroy_mkey: - mlx5_core_destroy_mkey(mdev, &res->mkey); + mlx5_core_destroy_mkey(mdev, res->mkey); err_dealloc_transport_domain: mlx5_core_dealloc_transport_domain(mdev, res->td.tdn); err_dealloc_pd: @@ -121,7 +121,7 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev) struct mlx5e_hw_objs *res = &mdev->mlx5e_res.hw_objs; mlx5_free_bfreg(mdev, &res->bfreg); - mlx5_core_destroy_mkey(mdev, &res->mkey); + mlx5_core_destroy_mkey(mdev, res->mkey); mlx5_core_dealloc_transport_domain(mdev, res->td.tdn); mlx5_core_dealloc_pd(mdev, res->pdn); memset(res, 0, sizeof(*res)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 306fb5d6a36d..c2ea5fad48dd 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: @@ -1902,6 +1900,11 @@ int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val return -EINVAL; } + if (priv->channels.params.packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO) { + netdev_warn(priv->netdev, "Can't set CQE compression with HW-GRO, disable it first.\n"); + return -EINVAL; + } + new_params = priv->channels.params; MLX5E_SET_PFLAG(&new_params, MLX5E_PFLAG_RX_CQE_COMPRESS, new_val); if (rx_filter) @@ -1954,8 +1957,8 @@ static int set_pflag_rx_striding_rq(struct net_device *netdev, bool enable) return -EOPNOTSUPP; if (!mlx5e_striding_rq_possible(mdev, &priv->channels.params)) return -EINVAL; - } else if (priv->channels.params.lro_en) { - netdev_warn(netdev, "Can't set legacy RQ with LRO, disable LRO first\n"); + } else if (priv->channels.params.packet_merge.type != MLX5E_PACKET_MERGE_NONE) { + netdev_warn(netdev, "Can't set legacy RQ with HW-GRO/LRO, disable them first\n"); return -EINVAL; } @@ -2036,6 +2039,17 @@ static int set_pflag_tx_port_ts(struct net_device *netdev, bool enable) } new_params = priv->channels.params; + /* Don't allow enabling TX-port-TS if MQPRIO mode channel offload is + * active, since it defines explicitly which TC accepts the packet. + * This conflicts with TX-port-TS hijacking the PTP traffic to a specific + * HW TX-queue. + */ + if (enable && new_params.mqprio.mode == TC_MQPRIO_MODE_CHANNEL) { + netdev_err(priv->netdev, + "%s: MQPRIO mode channel offload is active, cannot set the TX-port-TS\n", + __func__); + return -EINVAL; + } MLX5E_SET_PFLAG(&new_params, MLX5E_PFLAG_TX_PORT_TS, enable); /* No need to verify SQ stop room as * ptpsq.txqsq.stop_room <= generic_sq->stop_room, and both @@ -2128,12 +2142,14 @@ int mlx5e_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, return 0; } - return mlx5e_ethtool_get_rxnfc(dev, info, rule_locs); + return mlx5e_ethtool_get_rxnfc(priv, info, rule_locs); } int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) { - return mlx5e_ethtool_set_rxnfc(dev, cmd); + struct mlx5e_priv *priv = netdev_priv(dev); + + return mlx5e_ethtool_set_rxnfc(priv, cmd); } static int query_port_status_opcode(struct mlx5_core_dev *mdev, u32 *status_opcode) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index c06b4b938ae7..aeff1d972a46 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -71,12 +71,12 @@ struct mlx5e_l2_hash_node { bool mpfs; }; -static inline int mlx5e_hash_l2(u8 *addr) +static inline int mlx5e_hash_l2(const u8 *addr) { return addr[5]; } -static void mlx5e_add_l2_to_hash(struct hlist_head *hash, u8 *addr) +static void mlx5e_add_l2_to_hash(struct hlist_head *hash, const u8 *addr) { struct mlx5e_l2_hash_node *hn; int ix = mlx5e_hash_l2(addr); @@ -1186,10 +1186,6 @@ static int mlx5e_create_vlan_table(struct mlx5e_priv *priv) struct mlx5e_flow_table *ft; int err; - priv->fs.vlan = kvzalloc(sizeof(*priv->fs.vlan), GFP_KERNEL); - if (!priv->fs.vlan) - return -ENOMEM; - ft = &priv->fs.vlan->ft; ft->num_groups = 0; @@ -1198,10 +1194,8 @@ static int mlx5e_create_vlan_table(struct mlx5e_priv *priv) ft_attr.prio = MLX5E_NIC_PRIO; ft->t = mlx5_create_flow_table(priv->fs.ns, &ft_attr); - if (IS_ERR(ft->t)) { - err = PTR_ERR(ft->t); - goto err_free_t; - } + if (IS_ERR(ft->t)) + return PTR_ERR(ft->t); ft->g = kcalloc(MLX5E_NUM_VLAN_GROUPS, sizeof(*ft->g), GFP_KERNEL); if (!ft->g) { @@ -1221,9 +1215,6 @@ err_free_g: kfree(ft->g); err_destroy_vlan_table: mlx5_destroy_flow_table(ft->t); -err_free_t: - kvfree(priv->fs.vlan); - priv->fs.vlan = NULL; return err; } @@ -1232,7 +1223,6 @@ static void mlx5e_destroy_vlan_table(struct mlx5e_priv *priv) { mlx5e_del_vlan_rules(priv); mlx5e_destroy_flow_table(&priv->fs.vlan->ft); - kvfree(priv->fs.vlan); } static void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv) @@ -1351,3 +1341,17 @@ void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv) mlx5e_arfs_destroy_tables(priv); mlx5e_ethtool_cleanup_steering(priv); } + +int mlx5e_fs_init(struct mlx5e_priv *priv) +{ + priv->fs.vlan = kvzalloc(sizeof(*priv->fs.vlan), GFP_KERNEL); + if (!priv->fs.vlan) + return -ENOMEM; + return 0; +} + +void mlx5e_fs_cleanup(struct mlx5e_priv *priv) +{ + kvfree(priv->fs.vlan); + priv->fs.vlan = NULL; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index 03693fa74a70..ad0d234632a3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -411,7 +411,7 @@ static int flow_get_tirn(struct mlx5e_priv *priv, u32 rss_context, u32 *tirn) { if (fs->flow_type & FLOW_RSS) { - struct mlx5e_lro_param lro_param; + struct mlx5e_packet_merge_param pkt_merge_param; struct mlx5e_rss *rss; u32 flow_type; int err; @@ -426,8 +426,8 @@ static int flow_get_tirn(struct mlx5e_priv *priv, if (tt < 0) return -EINVAL; - lro_param = mlx5e_get_lro_param(&priv->channels.params); - err = mlx5e_rss_obtain_tirn(rss, tt, &lro_param, false, tirn); + pkt_merge_param = priv->channels.params.packet_merge; + err = mlx5e_rss_obtain_tirn(rss, tt, &pkt_merge_param, false, tirn); if (err) return err; eth_rule->rss = rss; @@ -937,9 +937,8 @@ static int mlx5e_get_rss_hash_opt(struct mlx5e_priv *priv, return 0; } -int mlx5e_ethtool_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) +int mlx5e_ethtool_set_rxnfc(struct mlx5e_priv *priv, struct ethtool_rxnfc *cmd) { - struct mlx5e_priv *priv = netdev_priv(dev); int err = 0; switch (cmd->cmd) { @@ -960,10 +959,9 @@ int mlx5e_ethtool_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) return err; } -int mlx5e_ethtool_get_rxnfc(struct net_device *dev, +int mlx5e_ethtool_get_rxnfc(struct mlx5e_priv *priv, struct ethtool_rxnfc *info, u32 *rule_locs) { - struct mlx5e_priv *priv = netdev_priv(dev); int err = 0; switch (info->cmd) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 3fd515e7bf30..65571593ec5c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -218,6 +218,45 @@ static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq, ucseg->mkey_mask = cpu_to_be64(MLX5_MKEY_MASK_FREE); } +static int mlx5e_rq_shampo_hd_alloc(struct mlx5e_rq *rq, int node) +{ + rq->mpwqe.shampo = kvzalloc_node(sizeof(*rq->mpwqe.shampo), + GFP_KERNEL, node); + if (!rq->mpwqe.shampo) + return -ENOMEM; + return 0; +} + +static void mlx5e_rq_shampo_hd_free(struct mlx5e_rq *rq) +{ + kvfree(rq->mpwqe.shampo); +} + +static int mlx5e_rq_shampo_hd_info_alloc(struct mlx5e_rq *rq, int node) +{ + struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo; + + shampo->bitmap = bitmap_zalloc_node(shampo->hd_per_wq, GFP_KERNEL, + node); + if (!shampo->bitmap) + return -ENOMEM; + + shampo->info = kvzalloc_node(array_size(shampo->hd_per_wq, + sizeof(*shampo->info)), + GFP_KERNEL, node); + if (!shampo->info) { + kvfree(shampo->bitmap); + return -ENOMEM; + } + return 0; +} + +static void mlx5e_rq_shampo_hd_info_free(struct mlx5e_rq *rq) +{ + kvfree(rq->mpwqe.shampo->bitmap); + kvfree(rq->mpwqe.shampo->info); +} + static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq, int node) { int wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq); @@ -233,10 +272,9 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq, int node) return 0; } -static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev, - u64 npages, u8 page_shift, - struct mlx5_core_mkey *umr_mkey, - dma_addr_t filler_addr) +static int mlx5e_create_umr_mtt_mkey(struct mlx5_core_dev *mdev, + u64 npages, u8 page_shift, u32 *umr_mkey, + dma_addr_t filler_addr) { struct mlx5_mtt *mtt; int inlen; @@ -284,12 +322,59 @@ static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev, return err; } +static int mlx5e_create_umr_klm_mkey(struct mlx5_core_dev *mdev, + u64 nentries, + u32 *umr_mkey) +{ + int inlen; + void *mkc; + u32 *in; + int err; + + inlen = MLX5_ST_SZ_BYTES(create_mkey_in); + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; + + mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); + + MLX5_SET(mkc, mkc, free, 1); + MLX5_SET(mkc, mkc, umr_en, 1); + MLX5_SET(mkc, mkc, lw, 1); + MLX5_SET(mkc, mkc, lr, 1); + MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_KLMS); + mlx5e_mkey_set_relaxed_ordering(mdev, mkc); + MLX5_SET(mkc, mkc, qpn, 0xffffff); + MLX5_SET(mkc, mkc, pd, mdev->mlx5e_res.hw_objs.pdn); + MLX5_SET(mkc, mkc, translations_octword_size, nentries); + MLX5_SET(mkc, mkc, length64, 1); + err = mlx5_core_create_mkey(mdev, umr_mkey, in, inlen); + + kvfree(in); + return err; +} + static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq *rq) { u64 num_mtts = MLX5E_REQUIRED_MTTS(mlx5_wq_ll_get_size(&rq->mpwqe.wq)); - return mlx5e_create_umr_mkey(mdev, num_mtts, PAGE_SHIFT, &rq->umr_mkey, - rq->wqe_overflow.addr); + return mlx5e_create_umr_mtt_mkey(mdev, num_mtts, PAGE_SHIFT, + &rq->umr_mkey, rq->wqe_overflow.addr); +} + +static int mlx5e_create_rq_hd_umr_mkey(struct mlx5_core_dev *mdev, + struct mlx5e_rq *rq) +{ + u32 max_klm_size = BIT(MLX5_CAP_GEN(mdev, log_max_klm_list_size)); + + if (max_klm_size < rq->mpwqe.shampo->hd_per_wq) { + mlx5_core_err(mdev, "max klm list size 0x%x is smaller than shampo header buffer list size 0x%x\n", + max_klm_size, rq->mpwqe.shampo->hd_per_wq); + return -EINVAL; + } + return mlx5e_create_umr_klm_mkey(mdev, rq->mpwqe.shampo->hd_per_wq, + &rq->mpwqe.shampo->mkey); } static u64 mlx5e_get_mpwqe_offset(u16 wqe_ix) @@ -403,6 +488,65 @@ static int mlx5e_init_rxq_rq(struct mlx5e_channel *c, struct mlx5e_params *param return xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq->ix, 0); } +static int mlx5_rq_shampo_alloc(struct mlx5_core_dev *mdev, + struct mlx5e_params *params, + struct mlx5e_rq_param *rqp, + struct mlx5e_rq *rq, + u32 *pool_size, + int node) +{ + void *wqc = MLX5_ADDR_OF(rqc, rqp->rqc, wq); + int wq_size; + int err; + + if (!test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state)) + return 0; + err = mlx5e_rq_shampo_hd_alloc(rq, node); + if (err) + goto out; + rq->mpwqe.shampo->hd_per_wq = + mlx5e_shampo_hd_per_wq(mdev, params, rqp); + err = mlx5e_create_rq_hd_umr_mkey(mdev, rq); + if (err) + goto err_shampo_hd; + err = mlx5e_rq_shampo_hd_info_alloc(rq, node); + if (err) + goto err_shampo_info; + rq->hw_gro_data = kvzalloc_node(sizeof(*rq->hw_gro_data), GFP_KERNEL, node); + if (!rq->hw_gro_data) { + err = -ENOMEM; + goto err_hw_gro_data; + } + rq->mpwqe.shampo->key = + cpu_to_be32(rq->mpwqe.shampo->mkey); + rq->mpwqe.shampo->hd_per_wqe = + mlx5e_shampo_hd_per_wqe(mdev, params, rqp); + wq_size = BIT(MLX5_GET(wq, wqc, log_wq_sz)); + *pool_size += (rq->mpwqe.shampo->hd_per_wqe * wq_size) / + MLX5E_SHAMPO_WQ_HEADER_PER_PAGE; + return 0; + +err_hw_gro_data: + mlx5e_rq_shampo_hd_info_free(rq); +err_shampo_info: + mlx5_core_destroy_mkey(mdev, rq->mpwqe.shampo->mkey); +err_shampo_hd: + mlx5e_rq_shampo_hd_free(rq); +out: + return err; +} + +static void mlx5e_rq_free_shampo(struct mlx5e_rq *rq) +{ + if (!test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state)) + return; + + kvfree(rq->hw_gro_data); + mlx5e_rq_shampo_hd_info_free(rq); + mlx5_core_destroy_mkey(rq->mdev, rq->mpwqe.shampo->mkey); + mlx5e_rq_shampo_hd_free(rq); +} + static int mlx5e_alloc_rq(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, struct mlx5e_rq_param *rqp, @@ -455,11 +599,16 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params, err = mlx5e_create_rq_umr_mkey(mdev, rq); if (err) goto err_rq_drop_page; - rq->mkey_be = cpu_to_be32(rq->umr_mkey.key); + rq->mkey_be = cpu_to_be32(rq->umr_mkey); err = mlx5e_rq_alloc_mpwqe_info(rq, node); if (err) goto err_rq_mkey; + + err = mlx5_rq_shampo_alloc(mdev, params, rqp, rq, &pool_size, node); + if (err) + goto err_free_by_rq_type; + break; default: /* MLX5_WQ_TYPE_CYCLIC */ err = mlx5_wq_cyc_create(mdev, &rqp->wq, rqc_wq, &rq->wqe.wq, @@ -487,7 +636,7 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params, if (err) goto err_rq_frags; - rq->mkey_be = cpu_to_be32(mdev->mlx5e_res.hw_objs.mkey.key); + rq->mkey_be = cpu_to_be32(mdev->mlx5e_res.hw_objs.mkey); } if (xsk) { @@ -512,14 +661,14 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params, if (IS_ERR(rq->page_pool)) { err = PTR_ERR(rq->page_pool); rq->page_pool = NULL; - goto err_free_by_rq_type; + goto err_free_shampo; } if (xdp_rxq_info_is_reg(&rq->xdp_rxq)) err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, MEM_TYPE_PAGE_POOL, rq->page_pool); } if (err) - goto err_free_by_rq_type; + goto err_free_shampo; for (i = 0; i < wq_sz; i++) { if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { @@ -528,8 +677,10 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params, u32 byte_count = rq->mpwqe.num_strides << rq->mpwqe.log_stride_sz; u64 dma_offset = mlx5e_get_mpwqe_offset(i); + u16 headroom = test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state) ? + 0 : rq->buff.headroom; - wqe->data[0].addr = cpu_to_be64(dma_offset + rq->buff.headroom); + wqe->data[0].addr = cpu_to_be64(dma_offset + headroom); wqe->data[0].byte_count = cpu_to_be32(byte_count); wqe->data[0].lkey = rq->mkey_be; } else { @@ -569,12 +720,14 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params, return 0; +err_free_shampo: + mlx5e_rq_free_shampo(rq); err_free_by_rq_type: switch (rq->wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: kvfree(rq->mpwqe.info); err_rq_mkey: - mlx5_core_destroy_mkey(mdev, &rq->umr_mkey); + mlx5_core_destroy_mkey(mdev, rq->umr_mkey); err_rq_drop_page: mlx5e_free_mpwqe_rq_drop_page(rq); break; @@ -607,8 +760,9 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq) switch (rq->wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: kvfree(rq->mpwqe.info); - mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey); + mlx5_core_destroy_mkey(rq->mdev, rq->umr_mkey); mlx5e_free_mpwqe_rq_drop_page(rq); + mlx5e_rq_free_shampo(rq); break; default: /* MLX5_WQ_TYPE_CYCLIC */ kvfree(rq->wqe.frags); @@ -662,6 +816,12 @@ int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param) MLX5_ADAPTER_PAGE_SHIFT); MLX5_SET64(wq, wq, dbr_addr, rq->wq_ctrl.db.dma); + if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state)) { + MLX5_SET(wq, wq, log_headers_buffer_entry_num, + order_base_2(rq->mpwqe.shampo->hd_per_wq)); + MLX5_SET(wq, wq, headers_mkey, rq->mpwqe.shampo->mkey); + } + mlx5_fill_page_frag_array(&rq->wq_ctrl.buf, (__be64 *)MLX5_ADDR_OF(wq, wq, pas)); @@ -801,6 +961,15 @@ void mlx5e_free_rx_in_progress_descs(struct mlx5e_rq *rq) head = mlx5_wq_ll_get_wqe_next_ix(wq, head); } + if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state)) { + u16 len; + + len = (rq->mpwqe.shampo->pi - rq->mpwqe.shampo->ci) & + (rq->mpwqe.shampo->hd_per_wq - 1); + mlx5e_shampo_dealloc_hd(rq, len, rq->mpwqe.shampo->ci, false); + rq->mpwqe.shampo->pi = rq->mpwqe.shampo->ci; + } + rq->mpwqe.actual_wq_head = wq->head; rq->mpwqe.umr_in_progress = 0; rq->mpwqe.umr_completed = 0; @@ -826,6 +995,10 @@ void mlx5e_free_rx_descs(struct mlx5e_rq *rq) mlx5_wq_ll_pop(wq, wqe_ix_be, &wqe->next.next_wqe_index); } + + if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state)) + mlx5e_shampo_dealloc_hd(rq, rq->mpwqe.shampo->hd_per_wq, + 0, true); } else { struct mlx5_wq_cyc *wq = &rq->wqe.wq; @@ -845,6 +1018,9 @@ int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param, struct mlx5_core_dev *mdev = rq->mdev; int err; + if (params->packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO) + __set_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state); + err = mlx5e_alloc_rq(params, xsk, param, node, rq); if (err) return err; @@ -930,9 +1106,10 @@ 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 +1123,11 @@ 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 +1476,8 @@ 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 +1487,7 @@ 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 +1881,36 @@ 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 +1919,16 @@ 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; } @@ -1991,7 +2204,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, c->cpu = cpu; c->pdev = mlx5_core_dma_dev(priv->mdev); c->netdev = priv->netdev; - c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey.key); + c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey); c->num_tc = mlx5e_get_dcb_num_tc(params); c->xdp = !!params->xdp_prog; c->stats = &priv->channel_stats[ix].ch; @@ -2185,17 +2398,14 @@ void mlx5e_close_channels(struct mlx5e_channels *chs) chs->num = 0; } -static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv) +static int mlx5e_modify_tirs_packet_merge(struct mlx5e_priv *priv) { struct mlx5e_rx_res *res = priv->rx_res; - struct mlx5e_lro_param lro_param; - lro_param = mlx5e_get_lro_param(&priv->channels.params); - - return mlx5e_rx_res_lro_set_param(res, &lro_param); + return mlx5e_rx_res_packet_merge_set_param(res, &priv->channels.params.packet_merge); } -static MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_modify_tirs_lro); +static MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_modify_tirs_packet_merge); static int mlx5e_set_mtu(struct mlx5_core_dev *mdev, struct mlx5e_params *params, u16 mtu) @@ -2264,7 +2474,7 @@ void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv) } static int mlx5e_netdev_set_tcs(struct net_device *netdev, u16 nch, u8 ntc, - struct tc_mqprio_qopt_offload *mqprio) + struct netdev_tc_txq *tc_to_txq) { int tc, err; @@ -2282,11 +2492,8 @@ static int mlx5e_netdev_set_tcs(struct net_device *netdev, u16 nch, u8 ntc, for (tc = 0; tc < ntc; tc++) { u16 count, offset; - /* For DCB mode, map netdev TCs to offset 0 - * We have our own UP to TXQ mapping for QoS - */ - count = mqprio ? mqprio->qopt.count[tc] : nch; - offset = mqprio ? mqprio->qopt.offset[tc] : 0; + count = tc_to_txq[tc].count; + offset = tc_to_txq[tc].offset; netdev_set_tc_queue(netdev, tc, count, offset); } @@ -2315,19 +2522,24 @@ int mlx5e_update_tx_netdev_queues(struct mlx5e_priv *priv) static int mlx5e_update_netdev_queues(struct mlx5e_priv *priv) { + struct netdev_tc_txq old_tc_to_txq[TC_MAX_QUEUE], *tc_to_txq; struct net_device *netdev = priv->netdev; int old_num_txqs, old_ntc; int num_rxqs, nch, ntc; int err; + int i; old_num_txqs = netdev->real_num_tx_queues; old_ntc = netdev->num_tc ? : 1; + for (i = 0; i < ARRAY_SIZE(old_tc_to_txq); i++) + old_tc_to_txq[i] = netdev->tc_to_txq[i]; nch = priv->channels.params.num_channels; - ntc = mlx5e_get_dcb_num_tc(&priv->channels.params); + ntc = priv->channels.params.mqprio.num_tc; num_rxqs = nch * priv->profile->rq_groups; + tc_to_txq = priv->channels.params.mqprio.tc_to_txq; - err = mlx5e_netdev_set_tcs(netdev, nch, ntc, NULL); + err = mlx5e_netdev_set_tcs(netdev, nch, ntc, tc_to_txq); if (err) goto err_out; err = mlx5e_update_tx_netdev_queues(priv); @@ -2338,6 +2550,13 @@ 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; @@ -2350,11 +2569,14 @@ err_txqs: WARN_ON_ONCE(netif_set_real_num_tx_queues(netdev, old_num_txqs)); err_tcs: - mlx5e_netdev_set_tcs(netdev, old_num_txqs / old_ntc, old_ntc, NULL); + WARN_ON_ONCE(mlx5e_netdev_set_tcs(netdev, old_num_txqs / old_ntc, old_ntc, + old_tc_to_txq)); err_out: return err; } +static MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_update_netdev_queues); + static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv, struct mlx5e_params *params) { @@ -2861,6 +3083,61 @@ static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd) return 0; } +static void mlx5e_mqprio_build_default_tc_to_txq(struct netdev_tc_txq *tc_to_txq, + int ntc, int nch) +{ + int tc; + + memset(tc_to_txq, 0, sizeof(*tc_to_txq) * TC_MAX_QUEUE); + + /* Map netdev TCs to offset 0. + * We have our own UP to TXQ mapping for DCB mode of QoS + */ + for (tc = 0; tc < ntc; tc++) { + tc_to_txq[tc] = (struct netdev_tc_txq) { + .count = nch, + .offset = 0, + }; + } +} + +static void mlx5e_mqprio_build_tc_to_txq(struct netdev_tc_txq *tc_to_txq, + struct tc_mqprio_qopt *qopt) +{ + int tc; + + for (tc = 0; tc < TC_MAX_QUEUE; tc++) { + tc_to_txq[tc] = (struct netdev_tc_txq) { + .count = qopt->count[tc], + .offset = qopt->offset[tc], + }; + } +} + +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 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); +} + +static void mlx5e_params_mqprio_reset(struct mlx5e_params *params) +{ + mlx5e_params_mqprio_dcb_set(params, 1); +} + static int mlx5e_setup_tc_mqprio_dcb(struct mlx5e_priv *priv, struct tc_mqprio_qopt *mqprio) { @@ -2874,8 +3151,7 @@ static int mlx5e_setup_tc_mqprio_dcb(struct mlx5e_priv *priv, return -EINVAL; new_params = priv->channels.params; - new_params.mqprio.mode = TC_MQPRIO_MODE_DCB; - new_params.mqprio.num_tc = tc ? tc : 1; + mlx5e_params_mqprio_dcb_set(&new_params, tc ? tc : 1); err = mlx5e_safe_switch_params(priv, &new_params, mlx5e_num_channels_changed_ctx, NULL, true); @@ -2889,9 +3165,17 @@ static int mlx5e_mqprio_channel_validate(struct mlx5e_priv *priv, struct tc_mqprio_qopt_offload *mqprio) { struct net_device *netdev = priv->netdev; + struct mlx5e_ptp *ptp_channel; int agg_count = 0; int i; + ptp_channel = priv->channels.ptp; + if (ptp_channel && test_bit(MLX5E_PTP_STATE_TX, ptp_channel->state)) { + netdev_err(netdev, + "Cannot activate MQPRIO mode channel since it conflicts with TX port TS\n"); + return -EINVAL; + } + if (mqprio->qopt.offset[0] != 0 || mqprio->qopt.num_tc < 1 || mqprio->qopt.num_tc > MLX5E_MAX_NUM_MQPRIO_CH_TC) return -EINVAL; @@ -2905,9 +3189,13 @@ 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) { @@ -2917,8 +3205,8 @@ static int mlx5e_mqprio_channel_validate(struct mlx5e_priv *priv, agg_count += mqprio->qopt.count[i]; } - if (priv->channels.params.num_channels < agg_count) { - netdev_err(netdev, "Num of queues (%d) exceeds available (%d)\n", + if (priv->channels.params.num_channels != agg_count) { + netdev_err(netdev, "Num of queues (%d) does not match available (%d)\n", agg_count, priv->channels.params.num_channels); return -EINVAL; } @@ -2926,36 +3214,53 @@ static int mlx5e_mqprio_channel_validate(struct mlx5e_priv *priv, return 0; } -static int mlx5e_mqprio_channel_set_tcs_ctx(struct mlx5e_priv *priv, void *ctx) +static bool mlx5e_mqprio_rate_limit(struct tc_mqprio_qopt_offload *mqprio) { - struct tc_mqprio_qopt_offload *mqprio = (struct tc_mqprio_qopt_offload *)ctx; - struct net_device *netdev = priv->netdev; - u8 num_tc; - - if (priv->channels.params.mqprio.mode != TC_MQPRIO_MODE_CHANNEL) - return -EINVAL; - - num_tc = priv->channels.params.mqprio.num_tc; - mlx5e_netdev_set_tcs(netdev, 0, num_tc, mqprio); + int tc; - return 0; + 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; err = mlx5e_mqprio_channel_validate(priv, mqprio); 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; - new_params.mqprio.mode = TC_MQPRIO_MODE_CHANNEL; - new_params.mqprio.num_tc = mqprio->qopt.num_tc; - err = mlx5e_safe_switch_params(priv, &new_params, - mlx5e_mqprio_channel_set_tcs_ctx, mqprio, true); + 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; + 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; } @@ -3065,7 +3370,7 @@ void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s) { int i; - for (i = 0; i < priv->max_nch; i++) { + for (i = 0; i < priv->stats_nch; i++) { struct mlx5e_channel_stats *channel_stats = &priv->channel_stats[i]; struct mlx5e_rq_stats *xskrq_stats = &channel_stats->xskrq; struct mlx5e_rq_stats *rq_stats = &channel_stats->rq; @@ -3175,7 +3480,7 @@ 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); @@ -3219,16 +3524,59 @@ static int set_feature_lro(struct net_device *netdev, bool enable) } new_params = *cur_params; - new_params.lro_en = enable; - if (cur_params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { - if (mlx5e_rx_mpwqe_is_linear_skb(mdev, cur_params, NULL) == - mlx5e_rx_mpwqe_is_linear_skb(mdev, &new_params, NULL)) - reset = false; + if (enable) + new_params.packet_merge.type = MLX5E_PACKET_MERGE_LRO; + else if (new_params.packet_merge.type == MLX5E_PACKET_MERGE_LRO) + new_params.packet_merge.type = MLX5E_PACKET_MERGE_NONE; + else + goto out; + + if (!(cur_params->packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO && + new_params.packet_merge.type == MLX5E_PACKET_MERGE_LRO)) { + if (cur_params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { + if (mlx5e_rx_mpwqe_is_linear_skb(mdev, cur_params, NULL) == + mlx5e_rx_mpwqe_is_linear_skb(mdev, &new_params, NULL)) + reset = false; + } + } + + err = mlx5e_safe_switch_params(priv, &new_params, + mlx5e_modify_tirs_packet_merge_ctx, NULL, reset); +out: + mutex_unlock(&priv->state_lock); + return err; +} + +static int set_feature_hw_gro(struct net_device *netdev, bool enable) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5e_params new_params; + bool reset = true; + int err = 0; + + mutex_lock(&priv->state_lock); + new_params = priv->channels.params; + + if (enable) { + if (MLX5E_GET_PFLAG(&new_params, MLX5E_PFLAG_RX_CQE_COMPRESS)) { + netdev_warn(netdev, "Can't set HW-GRO when CQE compress is active\n"); + err = -EINVAL; + goto out; + } + new_params.packet_merge.type = MLX5E_PACKET_MERGE_SHAMPO; + new_params.packet_merge.shampo.match_criteria_type = + MLX5_RQC_SHAMPO_MATCH_CRITERIA_TYPE_EXTENDED; + new_params.packet_merge.shampo.alignment_granularity = + MLX5_RQC_SHAMPO_NO_MATCH_ALIGNMENT_GRANULARITY_STRIDE; + } else if (new_params.packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO) { + new_params.packet_merge.type = MLX5E_PACKET_MERGE_NONE; + } else { + goto out; } err = mlx5e_safe_switch_params(priv, &new_params, - mlx5e_modify_tirs_lro_ctx, NULL, reset); + mlx5e_modify_tirs_packet_merge_ctx, NULL, reset); out: mutex_unlock(&priv->state_lock); return err; @@ -3274,20 +3622,67 @@ static int set_feature_rx_all(struct net_device *netdev, bool enable) return mlx5_set_port_fcs(mdev, !enable); } +static int mlx5e_set_rx_port_ts(struct mlx5_core_dev *mdev, bool enable) +{ + u32 in[MLX5_ST_SZ_DW(pcmr_reg)] = {}; + bool supported, curr_state; + int err; + + if (!MLX5_CAP_GEN(mdev, ports_check)) + return 0; + + err = mlx5_query_ports_check(mdev, in, sizeof(in)); + if (err) + return err; + + supported = MLX5_GET(pcmr_reg, in, rx_ts_over_crc_cap); + curr_state = MLX5_GET(pcmr_reg, in, rx_ts_over_crc); + + if (!supported || enable == curr_state) + return 0; + + MLX5_SET(pcmr_reg, in, local_port, 1); + MLX5_SET(pcmr_reg, in, rx_ts_over_crc, enable); + + return mlx5_set_ports_check(mdev, in, sizeof(in)); +} + static int set_feature_rx_fcs(struct net_device *netdev, bool enable) { struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5e_channels *chs = &priv->channels; + struct mlx5_core_dev *mdev = priv->mdev; int err; mutex_lock(&priv->state_lock); - priv->channels.params.scatter_fcs_en = enable; - err = mlx5e_modify_channels_scatter_fcs(&priv->channels, enable); - if (err) - priv->channels.params.scatter_fcs_en = !enable; + if (enable) { + err = mlx5e_set_rx_port_ts(mdev, false); + if (err) + goto out; - mutex_unlock(&priv->state_lock); + chs->params.scatter_fcs_en = true; + err = mlx5e_modify_channels_scatter_fcs(chs, true); + if (err) { + chs->params.scatter_fcs_en = false; + mlx5e_set_rx_port_ts(mdev, true); + } + } else { + chs->params.scatter_fcs_en = false; + err = mlx5e_modify_channels_scatter_fcs(chs, false); + if (err) { + chs->params.scatter_fcs_en = true; + goto out; + } + err = mlx5e_set_rx_port_ts(mdev, true); + if (err) { + mlx5_core_warn(mdev, "Failed to set RX port timestamp %d\n", err); + err = 0; + } + } +out: + mutex_unlock(&priv->state_lock); return err; } @@ -3360,6 +3755,7 @@ int mlx5e_set_features(struct net_device *netdev, netdev_features_t features) mlx5e_handle_feature(netdev, &oper_features, features, feature, handler) err |= MLX5E_HANDLE_FEATURE(NETIF_F_LRO, set_feature_lro); + err |= MLX5E_HANDLE_FEATURE(NETIF_F_GRO_HW, set_feature_hw_gro); err |= MLX5E_HANDLE_FEATURE(NETIF_F_HW_VLAN_CTAG_FILTER, set_feature_cvlan_filter); err |= MLX5E_HANDLE_FEATURE(NETIF_F_HW_TC, set_feature_hw_tc); @@ -3420,6 +3816,10 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev, netdev_warn(netdev, "Disabling LRO, not supported in legacy RQ\n"); features &= ~NETIF_F_LRO; } + if (features & NETIF_F_GRO_HW) { + netdev_warn(netdev, "Disabling HW-GRO, not supported in legacy RQ\n"); + features &= ~NETIF_F_GRO_HW; + } } if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)) { @@ -3508,7 +3908,7 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, goto out; } - if (params->lro_en) + if (params->packet_merge.type == MLX5E_PACKET_MERGE_LRO) reset = false; if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { @@ -3965,8 +4365,8 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog) struct net_device *netdev = priv->netdev; struct mlx5e_params new_params; - if (priv->channels.params.lro_en) { - netdev_warn(netdev, "can't set XDP while LRO is on, disable LRO first\n"); + if (priv->channels.params.packet_merge.type != MLX5E_PACKET_MERGE_NONE) { + netdev_warn(netdev, "can't set XDP while HW-GRO/LRO is on, disable them first\n"); return -EINVAL; } @@ -4186,13 +4586,11 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 struct mlx5_core_dev *mdev = priv->mdev; u8 rx_cq_period_mode; - priv->max_nch = mlx5e_calc_max_nch(priv, priv->profile); - params->sw_mtu = mtu; params->hard_mtu = MLX5E_ETH_HARD_MTU; params->num_channels = min_t(unsigned int, MLX5E_MAX_NUM_CHANNELS / 2, priv->max_nch); - params->mqprio.num_tc = 1; + mlx5e_params_mqprio_reset(params); /* Set an initial non-zero value, so that mlx5e_select_queue won't * divide by zero if called before first activating channels. @@ -4225,9 +4623,10 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { /* No XSK params: checking the availability of striding RQ in general. */ if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL)) - params->lro_en = !slow_pci_heuristic(mdev); + params->packet_merge.type = slow_pci_heuristic(mdev) ? + MLX5E_PACKET_MERGE_NONE : MLX5E_PACKET_MERGE_LRO; } - params->lro_timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT); + params->packet_merge.timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT); /* CQ moderation params */ rx_cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ? @@ -4255,13 +4654,17 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 static void mlx5e_set_netdev_dev_addr(struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); + u8 addr[ETH_ALEN]; - mlx5_query_mac_address(priv->mdev, netdev->dev_addr); - if (is_zero_ether_addr(netdev->dev_addr) && + mlx5_query_mac_address(priv->mdev, addr); + if (is_zero_ether_addr(addr) && !MLX5_CAP_GEN(priv->mdev, vport_group_manager)) { eth_hw_addr_random(netdev); mlx5_core_info(priv->mdev, "Assigned random MAC address %pM\n", netdev->dev_addr); + return; } + + eth_hw_addr_set(netdev, addr); } static int mlx5e_vxlan_set_port(struct net_device *netdev, unsigned int table, @@ -4358,6 +4761,10 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; netdev->hw_features |= NETIF_F_HW_VLAN_STAG_TX; + if (!!MLX5_CAP_GEN(mdev, shampo) && + mlx5e_check_fragmented_striding_rq_cap(mdev)) + netdev->hw_features |= NETIF_F_GRO_HW; + if (mlx5e_tunnel_any_tx_proto_supported(mdev)) { netdev->hw_enc_features |= NETIF_F_HW_CSUM; netdev->hw_enc_features |= NETIF_F_TSO; @@ -4408,6 +4815,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) if (fcs_enabled) netdev->features &= ~NETIF_F_RXALL; netdev->features &= ~NETIF_F_LRO; + netdev->features &= ~NETIF_F_GRO_HW; netdev->features &= ~NETIF_F_RXFCS; #define FT_CAP(f) MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.f) @@ -4482,6 +4890,12 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, mlx5e_timestamp_init(priv); + err = mlx5e_fs_init(priv); + if (err) { + mlx5_core_err(mdev, "FS initialization failed, %d\n", err); + return err; + } + err = mlx5e_ipsec_init(priv); if (err) mlx5_core_err(mdev, "IPSec initialization failed, %d\n", err); @@ -4499,13 +4913,13 @@ static void mlx5e_nic_cleanup(struct mlx5e_priv *priv) mlx5e_health_destroy_reporters(priv); mlx5e_tls_cleanup(priv); mlx5e_ipsec_cleanup(priv); + mlx5e_fs_cleanup(priv); } static int mlx5e_init_nic_rx(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; enum mlx5e_rx_res_features features; - struct mlx5e_lro_param lro_param; int err; priv->rx_res = mlx5e_rx_res_alloc(); @@ -4523,9 +4937,9 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv) features = MLX5E_RX_RES_FEATURE_XSK | MLX5E_RX_RES_FEATURE_PTP; if (priv->channels.params.tunneled_offload_en) features |= MLX5E_RX_RES_FEATURE_INNER_FT; - lro_param = mlx5e_get_lro_param(&priv->channels.params); err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, features, - priv->max_nch, priv->drop_rq.rqn, &lro_param, + priv->max_nch, priv->drop_rq.rqn, + &priv->channels.params.packet_merge, priv->channels.params.num_channels); if (err) goto err_close_drop_rq; @@ -4682,8 +5096,35 @@ static const struct mlx5e_profile mlx5e_nic_profile = { .rx_ptp_support = true, }; +static unsigned int +mlx5e_calc_max_nch(struct mlx5_core_dev *mdev, struct net_device *netdev, + const struct mlx5e_profile *profile) + +{ + unsigned int max_nch, tmp; + + /* core resources */ + max_nch = mlx5e_get_max_num_channels(mdev); + + /* netdev rx queues */ + tmp = netdev->num_rx_queues / max_t(u8, profile->rq_groups, 1); + max_nch = min_t(unsigned int, max_nch, tmp); + + /* netdev tx queues */ + tmp = netdev->num_tx_queues; + if (mlx5_qos_is_supported(mdev)) + tmp -= mlx5e_qos_max_leaf_nodes(mdev); + if (MLX5_CAP_GEN(mdev, ts_cqe_to_dest_cqn)) + tmp -= profile->max_tc; + tmp = tmp / profile->max_tc; + max_nch = min_t(unsigned int, max_nch, tmp); + + return max_nch; +} + /* mlx5e generic netdev management API (move to en_common.c) */ int mlx5e_priv_init(struct mlx5e_priv *priv, + const struct mlx5e_profile *profile, struct net_device *netdev, struct mlx5_core_dev *mdev) { @@ -4691,6 +5132,8 @@ int mlx5e_priv_init(struct mlx5e_priv *priv, priv->mdev = mdev; priv->netdev = netdev; priv->msglevel = MLX5E_MSG_LEVEL; + priv->max_nch = mlx5e_calc_max_nch(mdev, netdev, profile); + priv->stats_nch = priv->max_nch; priv->max_opened_tc = 1; if (!alloc_cpumask_var(&priv->scratchpad.cpumask, GFP_KERNEL)) @@ -4730,11 +5173,17 @@ 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)); } struct net_device * -mlx5e_create_netdev(struct mlx5_core_dev *mdev, unsigned int txqs, unsigned int rxqs) +mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *profile, + unsigned int txqs, unsigned int rxqs) { struct net_device *netdev; int err; @@ -4745,7 +5194,7 @@ mlx5e_create_netdev(struct mlx5_core_dev *mdev, unsigned int txqs, unsigned int return NULL; } - err = mlx5e_priv_init(netdev_priv(netdev), netdev, mdev); + err = mlx5e_priv_init(netdev_priv(netdev), profile, netdev, mdev); if (err) { mlx5_core_err(mdev, "mlx5e_priv_init failed, err=%d\n", err); goto err_free_netdev; @@ -4787,7 +5236,7 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv) clear_bit(MLX5E_STATE_DESTROYING, &priv->state); /* max number of channels may have changed */ - max_nch = mlx5e_get_max_num_channels(priv->mdev); + max_nch = mlx5e_calc_max_nch(priv->mdev, priv->netdev, profile); if (priv->channels.params.num_channels > max_nch) { mlx5_core_warn(priv->mdev, "MLX5E: Reducing number of channels to %d\n", max_nch); /* Reducing the number of channels - RXFH has to be reset, and @@ -4795,7 +5244,18 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv) */ priv->netdev->priv_flags &= ~IFF_RXFH_CONFIGURED; priv->channels.params.num_channels = max_nch; + if (priv->channels.params.mqprio.mode == TC_MQPRIO_MODE_CHANNEL) { + mlx5_core_warn(priv->mdev, "MLX5E: Disabling MQPRIO channel mode\n"); + mlx5e_params_mqprio_reset(&priv->channels.params); + } } + if (max_nch != priv->max_nch) { + mlx5_core_warn(priv->mdev, + "MLX5E: Updating max number of channels from %u to %u\n", + priv->max_nch, max_nch); + priv->max_nch = max_nch; + } + /* 1. Set the real number of queues in the kernel the first time. * 2. Set our default XPS cpumask. * 3. Build the RQT. @@ -4860,7 +5320,7 @@ mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mde struct mlx5e_priv *priv = netdev_priv(netdev); int err; - err = mlx5e_priv_init(priv, netdev, mdev); + err = mlx5e_priv_init(priv, new_profile, netdev, mdev); if (err) { mlx5_core_err(mdev, "mlx5e_priv_init failed, err=%d\n", err); return err; @@ -4886,20 +5346,12 @@ priv_cleanup: int mlx5e_netdev_change_profile(struct mlx5e_priv *priv, const struct mlx5e_profile *new_profile, void *new_ppriv) { - unsigned int new_max_nch = mlx5e_calc_max_nch(priv, new_profile); const struct mlx5e_profile *orig_profile = priv->profile; struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = priv->mdev; void *orig_ppriv = priv->ppriv; int err, rollback_err; - /* sanity */ - if (new_max_nch != priv->max_nch) { - netdev_warn(netdev, "%s: Replacing profile with different max channels\n", - __func__); - return -EINVAL; - } - /* cleanup old profile */ mlx5e_detach_netdev(priv); priv->profile->cleanup(priv); @@ -4995,7 +5447,7 @@ static int mlx5e_probe(struct auxiliary_device *adev, nch = mlx5e_get_max_num_channels(mdev); txqs = nch * profile->max_tc + ptp_txqs + qos_sqs; rxqs = nch * profile->rq_groups; - netdev = mlx5e_create_netdev(mdev, txqs, rxqs); + netdev = mlx5e_create_netdev(mdev, profile, txqs, rxqs); if (!netdev) { mlx5_core_err(mdev, "mlx5e_create_netdev failed\n"); return -ENOMEM; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index ae71a17fdb27..e58a9ec42553 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -53,6 +53,7 @@ #define CREATE_TRACE_POINTS #include "diag/en_rep_tracepoint.h" #include "en_accel/ipsec.h" +#include "en/tc/int_port.h" #define MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE \ max(0x7, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE) @@ -596,7 +597,6 @@ static void mlx5e_build_rep_params(struct net_device *netdev) MLX5_CQ_PERIOD_MODE_START_FROM_CQE : MLX5_CQ_PERIOD_MODE_START_FROM_EQE; - priv->max_nch = mlx5e_calc_max_nch(priv, priv->profile); params = &priv->channels.params; params->num_channels = MLX5E_REP_PARAMS_DEF_NUM_CHANNELS; @@ -619,6 +619,11 @@ static void mlx5e_build_rep_params(struct net_device *netdev) params->mqprio.num_tc = 1; params->tunneled_offload_en = false; + /* Set an initial non-zero value, so that mlx5e_select_queue won't + * divide by zero if called before first activating channels. + */ + priv->num_tc_x_num_ch = params->num_channels * params->mqprio.num_tc; + mlx5_query_min_inline(mdev, ¶ms->tx_min_inline_mode); } @@ -644,7 +649,6 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev, netdev->hw_features |= NETIF_F_RXCSUM; netdev->features |= netdev->hw_features; - netdev->features |= NETIF_F_VLAN_CHALLENGED; netdev->features |= NETIF_F_NETNS_LOCAL; } @@ -790,7 +794,6 @@ int mlx5e_rep_bond_update(struct mlx5e_priv *priv, bool cleanup) static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; - struct mlx5e_lro_param lro_param; int err; priv->rx_res = mlx5e_rx_res_alloc(); @@ -805,9 +808,9 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) return err; } - lro_param = mlx5e_get_lro_param(&priv->channels.params); err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, 0, - priv->max_nch, priv->drop_rq.rqn, &lro_param, + priv->max_nch, priv->drop_rq.rqn, + &priv->channels.params.packet_merge, priv->channels.params.num_channels); if (err) goto err_close_drop_rq; @@ -855,12 +858,22 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv) static int mlx5e_init_ul_rep_rx(struct mlx5e_priv *priv) { + int err; + mlx5e_create_q_counters(priv); - return mlx5e_init_rep_rx(priv); + err = mlx5e_init_rep_rx(priv); + if (err) + goto out; + + mlx5e_tc_int_port_init_rep_rx(priv); + +out: + return err; } static void mlx5e_cleanup_ul_rep_rx(struct mlx5e_priv *priv) { + mlx5e_tc_int_port_cleanup_rep_rx(priv); mlx5e_cleanup_rep_rx(priv); mlx5e_destroy_q_counters(priv); } @@ -1169,7 +1182,7 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) nch = mlx5e_get_max_num_channels(dev); txqs = nch * profile->max_tc; rxqs = nch * profile->rq_groups; - netdev = mlx5e_create_netdev(dev, txqs, rxqs); + netdev = mlx5e_create_netdev(dev, profile, txqs, rxqs); if (!netdev) { mlx5_core_warn(dev, "Failed to create representor netdev for vport %d\n", diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index 48a203a9e7d9..b01dacb6f527 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -58,6 +58,7 @@ struct mlx5e_neigh_update_table { }; struct mlx5_tc_ct_priv; +struct mlx5_tc_int_port_priv; struct mlx5e_rep_bond; struct mlx5e_tc_tun_encap; struct mlx5e_post_act; @@ -98,6 +99,9 @@ struct mlx5_rep_uplink_priv { /* tc tunneling encapsulation private data */ struct mlx5e_tc_tun_encap *encap; + + /* OVS internal port support */ + struct mlx5e_tc_int_port_priv *int_port_priv; }; struct mlx5e_rep_priv { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 3c65fd0bcf31..96967b0a2441 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -33,9 +33,12 @@ #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/tcp.h> +#include <linux/bitmap.h> #include <net/ip6_checksum.h> #include <net/page_pool.h> #include <net/inet_ecn.h> +#include <net/udp.h> +#include <net/tcp.h> #include "en.h" #include "en/txrx.h" #include "en_tc.h" @@ -62,10 +65,12 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w u16 cqe_bcnt, u32 head_offset, u32 page_idx); static void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); static void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); +static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); const struct mlx5e_rx_handlers mlx5e_rx_handlers_nic = { .handle_rx_cqe = mlx5e_handle_rx_cqe, .handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq, + .handle_rx_cqe_mpwqe_shampo = mlx5e_handle_rx_cqe_mpwrq_shampo, }; static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config) @@ -185,8 +190,9 @@ static inline u32 mlx5e_decompress_cqes_cont(struct mlx5e_rq *rq, mlx5e_read_mini_arr_slot(wq, cqd, cqcc); mlx5e_decompress_cqe_no_hash(rq, wq, cqcc); - INDIRECT_CALL_2(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq, - mlx5e_handle_rx_cqe, rq, &cqd->title); + INDIRECT_CALL_3(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq, + mlx5e_handle_rx_cqe_mpwrq_shampo, mlx5e_handle_rx_cqe, + rq, &cqd->title); } mlx5e_cqes_update_owner(wq, cqcc - wq->cc); wq->cc = cqcc; @@ -206,8 +212,9 @@ static inline u32 mlx5e_decompress_cqes_start(struct mlx5e_rq *rq, mlx5e_read_title_slot(rq, wq, cc); mlx5e_read_mini_arr_slot(wq, cqd, cc + 1); mlx5e_decompress_cqe(rq, wq, cc); - INDIRECT_CALL_2(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq, - mlx5e_handle_rx_cqe, rq, &cqd->title); + INDIRECT_CALL_3(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq, + mlx5e_handle_rx_cqe_mpwrq_shampo, mlx5e_handle_rx_cqe, + rq, &cqd->title); cqd->mini_arr_idx++; return mlx5e_decompress_cqes_cont(rq, wq, 1, budget_rem) - 1; @@ -448,13 +455,13 @@ mlx5e_add_skb_frag(struct mlx5e_rq *rq, struct sk_buff *skb, static inline void mlx5e_copy_skb_header(struct device *pdev, struct sk_buff *skb, struct mlx5e_dma_info *dma_info, - int offset_from, u32 headlen) + int offset_from, int dma_offset, u32 headlen) { const void *from = page_address(dma_info->page) + offset_from; /* Aligning len to sizeof(long) optimizes memcpy performance */ unsigned int len = ALIGN(headlen, sizeof(long)); - dma_sync_single_for_cpu(pdev, dma_info->addr + offset_from, len, + dma_sync_single_for_cpu(pdev, dma_info->addr + dma_offset, len, DMA_FROM_DEVICE); skb_copy_to_linear_data(skb, from, len); } @@ -494,6 +501,157 @@ static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq, u8 n) mlx5_wq_ll_update_db_record(wq); } +/* This function returns the size of the continuous free space inside a bitmap + * that starts from first and no longer than len including circular ones. + */ +static int bitmap_find_window(unsigned long *bitmap, int len, + int bitmap_size, int first) +{ + int next_one, count; + + next_one = find_next_bit(bitmap, bitmap_size, first); + if (next_one == bitmap_size) { + if (bitmap_size - first >= len) + return len; + next_one = find_next_bit(bitmap, bitmap_size, 0); + count = next_one + bitmap_size - first; + } else { + count = next_one - first; + } + + return min(len, count); +} + +static void build_klm_umr(struct mlx5e_icosq *sq, struct mlx5e_umr_wqe *umr_wqe, + __be32 key, u16 offset, u16 klm_len, u16 wqe_bbs) +{ + memset(umr_wqe, 0, offsetof(struct mlx5e_umr_wqe, inline_klms)); + umr_wqe->ctrl.opmod_idx_opcode = + cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) | + MLX5_OPCODE_UMR); + umr_wqe->ctrl.umr_mkey = key; + umr_wqe->ctrl.qpn_ds = cpu_to_be32((sq->sqn << MLX5_WQE_CTRL_QPN_SHIFT) + | MLX5E_KLM_UMR_DS_CNT(klm_len)); + umr_wqe->uctrl.flags = MLX5_UMR_TRANSLATION_OFFSET_EN | MLX5_UMR_INLINE; + umr_wqe->uctrl.xlt_offset = cpu_to_be16(offset); + umr_wqe->uctrl.xlt_octowords = cpu_to_be16(klm_len); + umr_wqe->uctrl.mkey_mask = cpu_to_be64(MLX5_MKEY_MASK_FREE); +} + +static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq, + struct mlx5e_icosq *sq, + u16 klm_entries, u16 index) +{ + struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo; + u16 entries, pi, i, header_offset, err, wqe_bbs, new_entries; + u32 lkey = rq->mdev->mlx5e_res.hw_objs.mkey; + struct page *page = shampo->last_page; + u64 addr = shampo->last_addr; + struct mlx5e_dma_info *dma_info; + struct mlx5e_umr_wqe *umr_wqe; + int headroom; + + headroom = rq->buff.headroom; + new_entries = klm_entries - (shampo->pi & (MLX5_UMR_KLM_ALIGNMENT - 1)); + entries = ALIGN(klm_entries, MLX5_UMR_KLM_ALIGNMENT); + wqe_bbs = MLX5E_KLM_UMR_WQEBBS(entries); + pi = mlx5e_icosq_get_next_pi(sq, wqe_bbs); + umr_wqe = mlx5_wq_cyc_get_wqe(&sq->wq, pi); + build_klm_umr(sq, umr_wqe, shampo->key, index, entries, wqe_bbs); + + for (i = 0; i < entries; i++, index++) { + dma_info = &shampo->info[index]; + if (i >= klm_entries || (index < shampo->pi && shampo->pi - index < + MLX5_UMR_KLM_ALIGNMENT)) + goto update_klm; + header_offset = (index & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)) << + MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE; + if (!(header_offset & (PAGE_SIZE - 1))) { + err = mlx5e_page_alloc(rq, dma_info); + if (unlikely(err)) + goto err_unmap; + addr = dma_info->addr; + page = dma_info->page; + } else { + dma_info->addr = addr + header_offset; + dma_info->page = page; + } + +update_klm: + umr_wqe->inline_klms[i].bcount = + cpu_to_be32(MLX5E_RX_MAX_HEAD); + umr_wqe->inline_klms[i].key = cpu_to_be32(lkey); + umr_wqe->inline_klms[i].va = + cpu_to_be64(dma_info->addr + headroom); + } + + sq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) { + .wqe_type = MLX5E_ICOSQ_WQE_SHAMPO_HD_UMR, + .num_wqebbs = wqe_bbs, + .shampo.len = new_entries, + }; + + shampo->pi = (shampo->pi + new_entries) & (shampo->hd_per_wq - 1); + shampo->last_page = page; + shampo->last_addr = addr; + sq->pc += wqe_bbs; + sq->doorbell_cseg = &umr_wqe->ctrl; + + return 0; + +err_unmap: + while (--i >= 0) { + if (--index < 0) + index = shampo->hd_per_wq - 1; + dma_info = &shampo->info[index]; + if (!(i & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1))) { + dma_info->addr = ALIGN_DOWN(dma_info->addr, PAGE_SIZE); + mlx5e_page_release(rq, dma_info, true); + } + } + rq->stats->buff_alloc_err++; + return err; +} + +static int mlx5e_alloc_rx_hd_mpwqe(struct mlx5e_rq *rq) +{ + struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo; + u16 klm_entries, num_wqe, index, entries_before; + struct mlx5e_icosq *sq = rq->icosq; + int i, err, max_klm_entries, len; + + max_klm_entries = MLX5E_MAX_KLM_PER_WQE(rq->mdev); + klm_entries = bitmap_find_window(shampo->bitmap, + shampo->hd_per_wqe, + shampo->hd_per_wq, shampo->pi); + if (!klm_entries) + return 0; + + klm_entries += (shampo->pi & (MLX5_UMR_KLM_ALIGNMENT - 1)); + index = ALIGN_DOWN(shampo->pi, MLX5_UMR_KLM_ALIGNMENT); + entries_before = shampo->hd_per_wq - index; + + if (unlikely(entries_before < klm_entries)) + num_wqe = DIV_ROUND_UP(entries_before, max_klm_entries) + + DIV_ROUND_UP(klm_entries - entries_before, max_klm_entries); + else + num_wqe = DIV_ROUND_UP(klm_entries, max_klm_entries); + + for (i = 0; i < num_wqe; i++) { + len = (klm_entries > max_klm_entries) ? max_klm_entries : + klm_entries; + if (unlikely(index + len > shampo->hd_per_wq)) + len = shampo->hd_per_wq - index; + err = mlx5e_build_shampo_hd_umr(rq, sq, len, index); + if (unlikely(err)) + return err; + index = (index + len) & (rq->mpwqe.shampo->hd_per_wq - 1); + klm_entries -= len; + } + + return 0; +} + static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) { struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix]; @@ -514,6 +672,12 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) goto err; } + if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state)) { + err = mlx5e_alloc_rx_hd_mpwqe(rq); + if (unlikely(err)) + goto err; + } + pi = mlx5e_icosq_get_next_pi(sq, MLX5E_UMR_WQEBBS); umr_wqe = mlx5_wq_cyc_get_wqe(wq, pi); memcpy(umr_wqe, &rq->mpwqe.umr_wqe, offsetof(struct mlx5e_umr_wqe, inline_mtts)); @@ -558,6 +722,44 @@ err: return err; } +/* This function is responsible to dealloc SHAMPO header buffer. + * close == true specifies that we are in the middle of closing RQ operation so + * we go over all the entries and if they are not in use we free them, + * otherwise we only go over a specific range inside the header buffer that are + * not in use. + */ +void mlx5e_shampo_dealloc_hd(struct mlx5e_rq *rq, u16 len, u16 start, bool close) +{ + struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo; + int hd_per_wq = shampo->hd_per_wq; + struct page *deleted_page = NULL; + struct mlx5e_dma_info *hd_info; + int i, index = start; + + for (i = 0; i < len; i++, index++) { + if (index == hd_per_wq) + index = 0; + + if (close && !test_bit(index, shampo->bitmap)) + continue; + + hd_info = &shampo->info[index]; + hd_info->addr = ALIGN_DOWN(hd_info->addr, PAGE_SIZE); + if (hd_info->page != deleted_page) { + deleted_page = hd_info->page; + mlx5e_page_release(rq, hd_info, false); + } + } + + if (start + len > hd_per_wq) { + len -= hd_per_wq - start; + bitmap_clear(shampo->bitmap, start, hd_per_wq - start); + start = 0; + } + + bitmap_clear(shampo->bitmap, start, len); +} + static void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) { struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix]; @@ -629,6 +831,28 @@ void mlx5e_free_icosq_descs(struct mlx5e_icosq *sq) sq->cc = sqcc; } +static void mlx5e_handle_shampo_hd_umr(struct mlx5e_shampo_umr umr, + struct mlx5e_icosq *sq) +{ + struct mlx5e_channel *c = container_of(sq, struct mlx5e_channel, icosq); + struct mlx5e_shampo_hd *shampo; + /* assume 1:1 relationship between RQ and icosq */ + struct mlx5e_rq *rq = &c->rq; + int end, from, len = umr.len; + + shampo = rq->mpwqe.shampo; + end = shampo->hd_per_wq; + from = shampo->ci; + if (from + len > shampo->hd_per_wq) { + len -= end - from; + bitmap_set(shampo->bitmap, from, end - from); + from = 0; + } + + bitmap_set(shampo->bitmap, from, len); + shampo->ci = (shampo->ci + umr.len) & (shampo->hd_per_wq - 1); +} + int mlx5e_poll_ico_cq(struct mlx5e_cq *cq) { struct mlx5e_icosq *sq = container_of(cq, struct mlx5e_icosq, cq); @@ -685,6 +909,9 @@ int mlx5e_poll_ico_cq(struct mlx5e_cq *cq) break; case MLX5E_ICOSQ_WQE_NOP: break; + case MLX5E_ICOSQ_WQE_SHAMPO_HD_UMR: + mlx5e_handle_shampo_hd_umr(wi->shampo, sq); + break; #ifdef CONFIG_MLX5_EN_TLS case MLX5E_ICOSQ_WQE_UMR_TLS: break; @@ -782,8 +1009,8 @@ static void mlx5e_lro_update_tcp_hdr(struct mlx5_cqe64 *cqe, struct tcphdr *tcp) if (tcp_ack) { tcp->ack = 1; - tcp->ack_seq = cqe->lro_ack_seq_num; - tcp->window = cqe->lro_tcp_win; + tcp->ack_seq = cqe->lro.ack_seq_num; + tcp->window = cqe->lro.tcp_win; } } @@ -809,7 +1036,7 @@ static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe, tcp = ip_p + sizeof(struct iphdr); skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; - ipv4->ttl = cqe->lro_min_ttl; + ipv4->ttl = cqe->lro.min_ttl; ipv4->tot_len = cpu_to_be16(tot_len); ipv4->check = 0; ipv4->check = ip_fast_csum((unsigned char *)ipv4, @@ -829,7 +1056,7 @@ static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe, tcp = ip_p + sizeof(struct ipv6hdr); skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; - ipv6->hop_limit = cqe->lro_min_ttl; + ipv6->hop_limit = cqe->lro.min_ttl; ipv6->payload_len = cpu_to_be16(payload_len); mlx5e_lro_update_tcp_hdr(cqe, tcp); @@ -841,6 +1068,142 @@ static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe, } } +static void *mlx5e_shampo_get_packet_hd(struct mlx5e_rq *rq, u16 header_index) +{ + struct mlx5e_dma_info *last_head = &rq->mpwqe.shampo->info[header_index]; + u16 head_offset = (last_head->addr & (PAGE_SIZE - 1)) + rq->buff.headroom; + + return page_address(last_head->page) + head_offset; +} + +static void mlx5e_shampo_update_ipv4_udp_hdr(struct mlx5e_rq *rq, struct iphdr *ipv4) +{ + int udp_off = rq->hw_gro_data->fk.control.thoff; + struct sk_buff *skb = rq->hw_gro_data->skb; + struct udphdr *uh; + + uh = (struct udphdr *)(skb->data + udp_off); + uh->len = htons(skb->len - udp_off); + + if (uh->check) + uh->check = ~udp_v4_check(skb->len - udp_off, ipv4->saddr, + ipv4->daddr, 0); + + skb->csum_start = (unsigned char *)uh - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + + skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_L4; +} + +static void mlx5e_shampo_update_ipv6_udp_hdr(struct mlx5e_rq *rq, struct ipv6hdr *ipv6) +{ + int udp_off = rq->hw_gro_data->fk.control.thoff; + struct sk_buff *skb = rq->hw_gro_data->skb; + struct udphdr *uh; + + uh = (struct udphdr *)(skb->data + udp_off); + uh->len = htons(skb->len - udp_off); + + if (uh->check) + uh->check = ~udp_v6_check(skb->len - udp_off, &ipv6->saddr, + &ipv6->daddr, 0); + + skb->csum_start = (unsigned char *)uh - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + + skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_L4; +} + +static void mlx5e_shampo_update_fin_psh_flags(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, + struct tcphdr *skb_tcp_hd) +{ + u16 header_index = be16_to_cpu(cqe->shampo.header_entry_index); + struct tcphdr *last_tcp_hd; + void *last_hd_addr; + + last_hd_addr = mlx5e_shampo_get_packet_hd(rq, header_index); + last_tcp_hd = last_hd_addr + ETH_HLEN + rq->hw_gro_data->fk.control.thoff; + tcp_flag_word(skb_tcp_hd) |= tcp_flag_word(last_tcp_hd) & (TCP_FLAG_FIN | TCP_FLAG_PSH); +} + +static void mlx5e_shampo_update_ipv4_tcp_hdr(struct mlx5e_rq *rq, struct iphdr *ipv4, + struct mlx5_cqe64 *cqe, bool match) +{ + int tcp_off = rq->hw_gro_data->fk.control.thoff; + struct sk_buff *skb = rq->hw_gro_data->skb; + struct tcphdr *tcp; + + tcp = (struct tcphdr *)(skb->data + tcp_off); + if (match) + mlx5e_shampo_update_fin_psh_flags(rq, cqe, tcp); + + tcp->check = ~tcp_v4_check(skb->len - tcp_off, ipv4->saddr, + ipv4->daddr, 0); + skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4; + if (ntohs(ipv4->id) == rq->hw_gro_data->second_ip_id) + skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_FIXEDID; + + skb->csum_start = (unsigned char *)tcp - skb->head; + skb->csum_offset = offsetof(struct tcphdr, check); + + if (tcp->cwr) + skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; +} + +static void mlx5e_shampo_update_ipv6_tcp_hdr(struct mlx5e_rq *rq, struct ipv6hdr *ipv6, + struct mlx5_cqe64 *cqe, bool match) +{ + int tcp_off = rq->hw_gro_data->fk.control.thoff; + struct sk_buff *skb = rq->hw_gro_data->skb; + struct tcphdr *tcp; + + tcp = (struct tcphdr *)(skb->data + tcp_off); + if (match) + mlx5e_shampo_update_fin_psh_flags(rq, cqe, tcp); + + tcp->check = ~tcp_v6_check(skb->len - tcp_off, &ipv6->saddr, + &ipv6->daddr, 0); + skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6; + skb->csum_start = (unsigned char *)tcp - skb->head; + skb->csum_offset = offsetof(struct tcphdr, check); + + if (tcp->cwr) + skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; +} + +static void mlx5e_shampo_update_hdr(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, bool match) +{ + bool is_ipv4 = (rq->hw_gro_data->fk.basic.n_proto == htons(ETH_P_IP)); + struct sk_buff *skb = rq->hw_gro_data->skb; + + skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; + skb->ip_summed = CHECKSUM_PARTIAL; + + if (is_ipv4) { + int nhoff = rq->hw_gro_data->fk.control.thoff - sizeof(struct iphdr); + struct iphdr *ipv4 = (struct iphdr *)(skb->data + nhoff); + __be16 newlen = htons(skb->len - nhoff); + + csum_replace2(&ipv4->check, ipv4->tot_len, newlen); + ipv4->tot_len = newlen; + + if (ipv4->protocol == IPPROTO_TCP) + mlx5e_shampo_update_ipv4_tcp_hdr(rq, ipv4, cqe, match); + else + mlx5e_shampo_update_ipv4_udp_hdr(rq, ipv4); + } else { + int nhoff = rq->hw_gro_data->fk.control.thoff - sizeof(struct ipv6hdr); + struct ipv6hdr *ipv6 = (struct ipv6hdr *)(skb->data + nhoff); + + ipv6->payload_len = htons(skb->len - nhoff - sizeof(*ipv6)); + + if (ipv6->nexthdr == IPPROTO_TCP) + mlx5e_shampo_update_ipv6_tcp_hdr(rq, ipv6, cqe, match); + else + mlx5e_shampo_update_ipv6_udp_hdr(rq, ipv6); + } +} + static inline void mlx5e_skb_set_hash(struct mlx5_cqe64 *cqe, struct sk_buff *skb) { @@ -1001,14 +1364,9 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, goto csum_unnecessary; if (likely(is_last_ethertype_ip(skb, &network_depth, &proto))) { - u8 ipproto = get_ip_proto(skb, network_depth, proto); - - if (unlikely(ipproto == IPPROTO_SCTP)) + if (unlikely(get_ip_proto(skb, network_depth, proto) == IPPROTO_SCTP)) goto csum_unnecessary; - if (unlikely(mlx5_ipsec_is_rx_flow(cqe))) - goto csum_none; - stats->csum_complete++; skb->ip_summed = CHECKSUM_COMPLETE; skb->csum = csum_unfold((__force __sum16)cqe->check_sum); @@ -1095,6 +1453,27 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, stats->mcast_packets++; } +static void mlx5e_shampo_complete_rx_cqe(struct mlx5e_rq *rq, + struct mlx5_cqe64 *cqe, + u32 cqe_bcnt, + struct sk_buff *skb) +{ + struct mlx5e_rq_stats *stats = rq->stats; + + stats->packets++; + stats->gro_packets++; + stats->bytes += cqe_bcnt; + stats->gro_bytes += cqe_bcnt; + if (NAPI_GRO_CB(skb)->count != 1) + return; + mlx5e_build_rx_skb(cqe, cqe_bcnt, rq, skb); + skb_reset_network_header(skb); + if (!skb_flow_dissect_flow_keys(skb, &rq->hw_gro_data->fk, 0)) { + napi_gro_receive(rq->cq.napi, skb); + rq->hw_gro_data->skb = NULL; + } +} + static inline void mlx5e_complete_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, u32 cqe_bcnt, @@ -1204,7 +1583,8 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, } /* copy header */ - mlx5e_copy_skb_header(rq->pdev, skb, head_wi->di, head_wi->offset, headlen); + mlx5e_copy_skb_header(rq->pdev, skb, head_wi->di, head_wi->offset, head_wi->offset, + headlen); /* skb linear part was allocated with headlen and aligned to long */ skb->tail += headlen; skb->len += headlen; @@ -1280,7 +1660,6 @@ static void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep = rpriv->rep; - struct mlx5e_tc_update_priv tc_priv = {}; struct mlx5_wq_cyc *wq = &rq->wqe.wq; struct mlx5e_wqe_frag_info *wi; struct sk_buff *skb; @@ -1316,15 +1695,7 @@ static void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) if (rep->vlan && skb_vlan_tag_present(skb)) skb_vlan_pop(skb); - if (unlikely(!mlx5_ipsec_is_rx_flow(cqe) && - !mlx5e_rep_tc_update_skb(cqe, skb, &tc_priv))) { - dev_kfree_skb_any(skb); - goto free_wqe; - } - - napi_gro_receive(rq->cq.napi, skb); - - mlx5_rep_tc_post_napi_receive(&tc_priv); + mlx5e_rep_tc_receive(cqe, rq, skb); free_wqe: mlx5e_free_rx_wqe(rq, wi, true); @@ -1341,7 +1712,6 @@ static void mlx5e_handle_rx_cqe_mpwrq_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 u32 wqe_offset = stride_ix << rq->mpwqe.log_stride_sz; u32 head_offset = wqe_offset & (PAGE_SIZE - 1); u32 page_idx = wqe_offset >> PAGE_SHIFT; - struct mlx5e_tc_update_priv tc_priv = {}; struct mlx5e_rx_wqe_ll *wqe; struct mlx5_wq_ll *wq; struct sk_buff *skb; @@ -1374,15 +1744,7 @@ static void mlx5e_handle_rx_cqe_mpwrq_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb); - if (unlikely(!mlx5_ipsec_is_rx_flow(cqe) && - !mlx5e_rep_tc_update_skb(cqe, skb, &tc_priv))) { - dev_kfree_skb_any(skb); - goto mpwrq_cqe_out; - } - - napi_gro_receive(rq->cq.napi, skb); - - mlx5_rep_tc_post_napi_receive(&tc_priv); + mlx5e_rep_tc_receive(cqe, rq, skb); mpwrq_cqe_out: if (likely(wi->consumed_strides < rq->mpwqe.num_strides)) @@ -1400,6 +1762,30 @@ const struct mlx5e_rx_handlers mlx5e_rx_handlers_rep = { }; #endif +static void +mlx5e_fill_skb_data(struct sk_buff *skb, struct mlx5e_rq *rq, struct mlx5e_dma_info *di, + u32 data_bcnt, u32 data_offset) +{ + net_prefetchw(skb->data); + + while (data_bcnt) { + u32 pg_consumed_bytes = min_t(u32, PAGE_SIZE - data_offset, data_bcnt); + unsigned int truesize; + + if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state)) + truesize = pg_consumed_bytes; + else + truesize = ALIGN(pg_consumed_bytes, BIT(rq->mpwqe.log_stride_sz)); + + mlx5e_add_skb_frag(rq, skb, di, data_offset, + pg_consumed_bytes, truesize); + + data_bcnt -= pg_consumed_bytes; + data_offset = 0; + di++; + } +} + static struct sk_buff * mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, u16 cqe_bcnt, u32 head_offset, u32 page_idx) @@ -1425,20 +1811,9 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w frag_offset -= PAGE_SIZE; } - while (byte_cnt) { - u32 pg_consumed_bytes = - min_t(u32, PAGE_SIZE - frag_offset, byte_cnt); - unsigned int truesize = - ALIGN(pg_consumed_bytes, BIT(rq->mpwqe.log_stride_sz)); - - mlx5e_add_skb_frag(rq, skb, di, frag_offset, - pg_consumed_bytes, truesize); - byte_cnt -= pg_consumed_bytes; - frag_offset = 0; - di++; - } + mlx5e_fill_skb_data(skb, rq, di, byte_cnt, frag_offset); /* copy header */ - mlx5e_copy_skb_header(rq->pdev, skb, head_di, head_offset, headlen); + mlx5e_copy_skb_header(rq->pdev, skb, head_di, head_offset, head_offset, headlen); /* skb linear part was allocated with headlen and aligned to long */ skb->tail += headlen; skb->len += headlen; @@ -1492,6 +1867,181 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, return skb; } +static void +mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, + struct mlx5_cqe64 *cqe, u16 header_index) +{ + struct mlx5e_dma_info *head = &rq->mpwqe.shampo->info[header_index]; + u16 head_offset = head->addr & (PAGE_SIZE - 1); + u16 head_size = cqe->shampo.header_size; + u16 rx_headroom = rq->buff.headroom; + struct sk_buff *skb = NULL; + void *hdr, *data; + u32 frag_size; + + hdr = page_address(head->page) + head_offset; + data = hdr + rx_headroom; + frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + head_size); + + if (likely(frag_size <= BIT(MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE))) { + /* build SKB around header */ + dma_sync_single_range_for_cpu(rq->pdev, head->addr, 0, frag_size, DMA_FROM_DEVICE); + prefetchw(hdr); + prefetch(data); + skb = mlx5e_build_linear_skb(rq, hdr, frag_size, rx_headroom, head_size); + + if (unlikely(!skb)) + return; + + /* queue up for recycling/reuse */ + page_ref_inc(head->page); + + } else { + /* allocate SKB and copy header for large header */ + rq->stats->gro_large_hds++; + skb = napi_alloc_skb(rq->cq.napi, + ALIGN(head_size, sizeof(long))); + if (unlikely(!skb)) { + rq->stats->buff_alloc_err++; + return; + } + + prefetchw(skb->data); + mlx5e_copy_skb_header(rq->pdev, skb, head, + head_offset + rx_headroom, + rx_headroom, head_size); + /* skb linear part was allocated with headlen and aligned to long */ + skb->tail += head_size; + skb->len += head_size; + } + rq->hw_gro_data->skb = skb; + NAPI_GRO_CB(skb)->count = 1; + skb_shinfo(skb)->gso_size = mpwrq_get_cqe_byte_cnt(cqe) - head_size; +} + +static void +mlx5e_shampo_align_fragment(struct sk_buff *skb, u8 log_stride_sz) +{ + skb_frag_t *last_frag = &skb_shinfo(skb)->frags[skb_shinfo(skb)->nr_frags - 1]; + unsigned int frag_size = skb_frag_size(last_frag); + unsigned int frag_truesize; + + frag_truesize = ALIGN(frag_size, BIT(log_stride_sz)); + skb->truesize += frag_truesize - frag_size; +} + +static void +mlx5e_shampo_flush_skb(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, bool match) +{ + struct sk_buff *skb = rq->hw_gro_data->skb; + struct mlx5e_rq_stats *stats = rq->stats; + + stats->gro_skbs++; + if (likely(skb_shinfo(skb)->nr_frags)) + mlx5e_shampo_align_fragment(skb, rq->mpwqe.log_stride_sz); + if (NAPI_GRO_CB(skb)->count > 1) + mlx5e_shampo_update_hdr(rq, cqe, match); + napi_gro_receive(rq->cq.napi, skb); + rq->hw_gro_data->skb = NULL; +} + +static bool +mlx5e_hw_gro_skb_has_enough_space(struct sk_buff *skb, u16 data_bcnt) +{ + int nr_frags = skb_shinfo(skb)->nr_frags; + + return PAGE_SIZE * nr_frags + data_bcnt <= GSO_MAX_SIZE; +} + +static void +mlx5e_free_rx_shampo_hd_entry(struct mlx5e_rq *rq, u16 header_index) +{ + struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo; + u64 addr = shampo->info[header_index].addr; + + if (((header_index + 1) & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)) == 0) { + shampo->info[header_index].addr = ALIGN_DOWN(addr, PAGE_SIZE); + mlx5e_page_release(rq, &shampo->info[header_index], true); + } + bitmap_clear(shampo->bitmap, header_index, 1); +} + +static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) +{ + u16 data_bcnt = mpwrq_get_cqe_byte_cnt(cqe) - cqe->shampo.header_size; + u16 header_index = be16_to_cpu(cqe->shampo.header_entry_index); + u32 wqe_offset = be32_to_cpu(cqe->shampo.data_offset); + u16 cstrides = mpwrq_get_cqe_consumed_strides(cqe); + u32 data_offset = wqe_offset & (PAGE_SIZE - 1); + u32 cqe_bcnt = mpwrq_get_cqe_byte_cnt(cqe); + u16 wqe_id = be16_to_cpu(cqe->wqe_id); + u32 page_idx = wqe_offset >> PAGE_SHIFT; + struct sk_buff **skb = &rq->hw_gro_data->skb; + bool flush = cqe->shampo.flush; + bool match = cqe->shampo.match; + struct mlx5e_rq_stats *stats = rq->stats; + struct mlx5e_rx_wqe_ll *wqe; + struct mlx5e_dma_info *di; + struct mlx5e_mpw_info *wi; + struct mlx5_wq_ll *wq; + + wi = &rq->mpwqe.info[wqe_id]; + wi->consumed_strides += cstrides; + + if (unlikely(MLX5E_RX_ERR_CQE(cqe))) { + trigger_report(rq, cqe); + stats->wqe_err++; + goto mpwrq_cqe_out; + } + + if (unlikely(mpwrq_is_filler_cqe(cqe))) { + stats->mpwqe_filler_cqes++; + stats->mpwqe_filler_strides += cstrides; + goto mpwrq_cqe_out; + } + + stats->gro_match_packets += match; + + if (*skb && (!match || !(mlx5e_hw_gro_skb_has_enough_space(*skb, data_bcnt)))) { + match = false; + mlx5e_shampo_flush_skb(rq, cqe, match); + } + + if (!*skb) { + mlx5e_skb_from_cqe_shampo(rq, wi, cqe, header_index); + if (unlikely(!*skb)) + goto free_hd_entry; + } else { + NAPI_GRO_CB(*skb)->count++; + if (NAPI_GRO_CB(*skb)->count == 2 && + rq->hw_gro_data->fk.basic.n_proto == htons(ETH_P_IP)) { + void *hd_addr = mlx5e_shampo_get_packet_hd(rq, header_index); + int nhoff = ETH_HLEN + rq->hw_gro_data->fk.control.thoff - + sizeof(struct iphdr); + struct iphdr *iph = (struct iphdr *)(hd_addr + nhoff); + + rq->hw_gro_data->second_ip_id = ntohs(iph->id); + } + } + + di = &wi->umr.dma_info[page_idx]; + mlx5e_fill_skb_data(*skb, rq, di, data_bcnt, data_offset); + + mlx5e_shampo_complete_rx_cqe(rq, cqe, cqe_bcnt, *skb); + if (flush) + mlx5e_shampo_flush_skb(rq, cqe, match); +free_hd_entry: + mlx5e_free_rx_shampo_hd_entry(rq, header_index); +mpwrq_cqe_out: + if (likely(wi->consumed_strides < rq->mpwqe.num_strides)) + return; + + wq = &rq->mpwqe.wq; + wqe = mlx5_wq_ll_get_wqe(wq, wqe_id); + mlx5e_free_rx_mpwqe(rq, wi, true); + mlx5_wq_ll_pop(wq, cqe->wqe_id, &wqe->next.next_wqe_index); +} + static void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) { u16 cstrides = mpwrq_get_cqe_consumed_strides(cqe); @@ -1584,11 +2134,15 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) mlx5_cqwq_pop(cqwq); - INDIRECT_CALL_2(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq, - mlx5e_handle_rx_cqe, rq, cqe); + INDIRECT_CALL_3(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq, + mlx5e_handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq_shampo, + rq, cqe); } while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(cqwq))); out: + if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state) && rq->hw_gro_data->skb) + mlx5e_shampo_flush_skb(rq, NULL, false); + if (rcu_access_pointer(rq->xdp_prog)) mlx5e_xdp_rx_poll_complete(rq); @@ -1789,15 +2343,24 @@ int mlx5e_rq_set_handlers(struct mlx5e_rq *rq, struct mlx5e_params *params, bool rq->post_wqes = mlx5e_post_rx_mpwqes; rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe; - rq->handle_rx_cqe = priv->profile->rx_handlers->handle_rx_cqe_mpwqe; if (mlx5_fpga_is_ipsec_device(mdev)) { netdev_err(netdev, "MPWQE RQ with Innova IPSec offload not supported\n"); return -EINVAL; } - if (!rq->handle_rx_cqe) { - netdev_err(netdev, "RX handler of MPWQE RQ is not set\n"); - return -EINVAL; + if (params->packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO) { + rq->handle_rx_cqe = priv->profile->rx_handlers->handle_rx_cqe_mpwqe_shampo; + if (!rq->handle_rx_cqe) { + netdev_err(netdev, "RX handler of SHAMPO MPWQE RQ is not set\n"); + return -EINVAL; + } + } else { + rq->handle_rx_cqe = priv->profile->rx_handlers->handle_rx_cqe_mpwqe; + if (!rq->handle_rx_cqe) { + netdev_err(netdev, "RX handler of MPWQE RQ is not set\n"); + return -EINVAL; + } } + break; default: /* MLX5_WQ_TYPE_CYCLIC */ rq->wqe.skb_from_cqe = xsk ? 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_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index e4f5b6395148..2a9bfc3ffa2e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -34,6 +34,7 @@ #include "en.h" #include "en_accel/tls.h" #include "en_accel/en_accel.h" +#include "en/ptp.h" static unsigned int stats_grps_num(struct mlx5e_priv *priv) { @@ -127,6 +128,11 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_packets) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_bytes) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_gro_packets) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_gro_bytes) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_gro_skbs) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_gro_match_packets) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_gro_large_hds) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_ecn_mark) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_removed_vlan_packets) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary) }, @@ -312,6 +318,11 @@ static void mlx5e_stats_grp_sw_update_stats_rq_stats(struct mlx5e_sw_stats *s, s->rx_bytes += rq_stats->bytes; s->rx_lro_packets += rq_stats->lro_packets; s->rx_lro_bytes += rq_stats->lro_bytes; + s->rx_gro_packets += rq_stats->gro_packets; + s->rx_gro_bytes += rq_stats->gro_bytes; + s->rx_gro_skbs += rq_stats->gro_skbs; + s->rx_gro_match_packets += rq_stats->gro_match_packets; + s->rx_gro_large_hds += rq_stats->gro_large_hds; s->rx_ecn_mark += rq_stats->ecn_mark; s->rx_removed_vlan_packets += rq_stats->removed_vlan_packets; s->rx_csum_none += rq_stats->csum_none; @@ -450,7 +461,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(sw) memset(s, 0, sizeof(*s)); - for (i = 0; i < priv->max_nch; i++) { + for (i = 0; i < priv->stats_nch; i++) { struct mlx5e_channel_stats *channel_stats = &priv->channel_stats[i]; int j; @@ -1759,6 +1770,11 @@ static const struct counter_desc rq_stats_desc[] = { { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_redirect) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_packets) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_bytes) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, gro_packets) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, gro_bytes) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, gro_skbs) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, gro_match_packets) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, gro_large_hds) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, ecn_mark) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, removed_vlan_packets) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, wqe_err) }, @@ -2076,7 +2092,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(ptp) if (priv->rx_ptp_opened) { for (i = 0; i < NUM_PTP_RQ_STATS; i++) sprintf(data + (idx++) * ETH_GSTRING_LEN, - ptp_rq_stats_desc[i].format); + ptp_rq_stats_desc[i].format, MLX5E_PTP_CHANNEL_IX); } return idx; } @@ -2119,7 +2135,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(ptp) { return; } static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(channels) { - int max_nch = priv->max_nch; + int max_nch = priv->stats_nch; return (NUM_RQ_STATS * max_nch) + (NUM_CH_STATS * max_nch) + @@ -2133,7 +2149,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(channels) static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(channels) { bool is_xsk = priv->xsk.ever_used; - int max_nch = priv->max_nch; + int max_nch = priv->stats_nch; int i, j, tc; for (i = 0; i < max_nch; i++) @@ -2175,7 +2191,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(channels) static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(channels) { bool is_xsk = priv->xsk.ever_used; - int max_nch = priv->max_nch; + int max_nch = priv->stats_nch; int i, j, tc; for (i = 0; i < max_nch; i++) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 139e59f30db0..2c1ed5b81be6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -144,6 +144,11 @@ struct mlx5e_sw_stats { u64 tx_mpwqe_pkts; u64 rx_lro_packets; u64 rx_lro_bytes; + u64 rx_gro_packets; + u64 rx_gro_bytes; + u64 rx_gro_skbs; + u64 rx_gro_match_packets; + u64 rx_gro_large_hds; u64 rx_mcast_packets; u64 rx_ecn_mark; u64 rx_removed_vlan_packets; @@ -322,6 +327,11 @@ struct mlx5e_rq_stats { u64 csum_none; u64 lro_packets; u64 lro_bytes; + u64 gro_packets; + u64 gro_bytes; + u64 gro_skbs; + u64 gro_match_packets; + u64 gro_large_hds; u64 mcast_packets; u64 ecn_mark; u64 removed_vlan_packets; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index ba8164792016..835caa1c7b74 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> @@ -59,7 +60,6 @@ #include "en/mapping.h" #include "en/tc_ct.h" #include "en/mod_hdr.h" -#include "en/tc_priv.h" #include "en/tc_tun_encap.h" #include "en/tc/sample.h" #include "lib/devcom.h" @@ -67,6 +67,8 @@ #include "lib/fs_chains.h" #include "diag/en_tc_tracepoint.h" #include <asm/div64.h> +#include "lag/lag.h" +#include "lag/mp.h" #define nic_chains(priv) ((priv)->fs.tc.chains) #define MLX5_MH_ACT_SZ MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto) @@ -229,6 +231,23 @@ mlx5e_tc_match_to_reg_set_and_get_id(struct mlx5_core_dev *mdev, return err; } +struct mlx5e_tc_int_port_priv * +mlx5e_get_int_port_priv(struct mlx5e_priv *priv) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + struct mlx5_rep_uplink_priv *uplink_priv; + struct mlx5e_rep_priv *uplink_rpriv; + + if (is_mdev_switchdev_mode(priv->mdev)) { + uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); + uplink_priv = &uplink_rpriv->uplink_priv; + + return uplink_priv->int_port_priv; + } + + return NULL; +} + static struct mlx5_tc_ct_priv * get_ct_priv(struct mlx5e_priv *priv) { @@ -246,7 +265,6 @@ 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 +281,6 @@ get_sample_priv(struct mlx5e_priv *priv) return NULL; } -#endif struct mlx5_flow_handle * mlx5_tc_rule_insert(struct mlx5e_priv *priv, @@ -1146,11 +1163,9 @@ 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 +1201,10 @@ 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); @@ -1388,6 +1401,9 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, int err = 0; int out_index; + parse_attr = attr->parse_attr; + esw_attr = attr->esw_attr; + /* We check chain range only for tc flows. * For ft flows, we checked attr->chain was originally 0 and set it to * FDB_FT_CHAIN which is outside tc range. @@ -1413,6 +1429,24 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, err = mlx5e_attach_decap_route(priv, flow); if (err) goto err_out; + + if (!attr->chain && esw_attr->int_port) { + /* If decap route device is internal port, change the + * source vport value in reg_c0 back to uplink just in + * case the rule performs goto chain > 0. If we have a miss + * on chain > 0 we want the metadata regs to hold the + * chain id so SW will resume handling of this packet + * from the proper chain. + */ + u32 metadata = mlx5_eswitch_get_vport_metadata_for_set(esw, + esw_attr->in_rep->vport); + + err = mlx5e_tc_match_to_reg_set(priv->mdev, &parse_attr->mod_hdr_acts, + MLX5_FLOW_NAMESPACE_FDB, VPORT_TO_REG, + metadata); + if (err) + return err; + } } if (flow_flag_test(flow, L3_TO_L2_DECAP)) { @@ -1421,8 +1455,31 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, goto err_out; } - parse_attr = attr->parse_attr; - esw_attr = attr->esw_attr; + if (netif_is_ovs_master(parse_attr->filter_dev)) { + struct mlx5e_tc_int_port *int_port; + + if (attr->chain) { + NL_SET_ERR_MSG_MOD(extack, + "Internal port rule is only supported on chain 0"); + return -EOPNOTSUPP; + } + + if (attr->dest_chain) { + NL_SET_ERR_MSG_MOD(extack, + "Internal port rule offload doesn't support goto action"); + return -EOPNOTSUPP; + } + + int_port = mlx5e_tc_int_port_get(mlx5e_get_int_port_priv(priv), + parse_attr->filter_dev->ifindex, + flow_flag_test(flow, EGRESS) ? + MLX5E_TC_INT_PORT_EGRESS : + MLX5E_TC_INT_PORT_INGRESS); + if (IS_ERR(int_port)) + return PTR_ERR(int_port); + + esw_attr->int_port = int_port; + } for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { struct net_device *out_dev; @@ -1445,7 +1502,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, goto err_out; if (esw_attr->dests[out_index].flags & - MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE) + MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE && + !esw_attr->dest_int_port) vf_tun = true; out_priv = netdev_priv(encap_dev); rpriv = out_priv->ppriv; @@ -1553,7 +1611,8 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { if (esw_attr->dests[out_index].flags & - MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE) + MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE && + !esw_attr->dest_int_port) vf_tun = true; if (esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP) { mlx5e_detach_encap(priv, flow, out_index); @@ -1577,6 +1636,12 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) mlx5_fc_destroy(esw_attr->counter_dev, attr->counter); + if (esw_attr->int_port) + mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(priv), esw_attr->int_port); + + if (esw_attr->dest_int_port) + mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(priv), esw_attr->dest_int_port); + if (flow_flag_test(flow, L3_TO_L2_DECAP)) mlx5e_detach_decap(priv, flow); @@ -1688,8 +1753,8 @@ 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; @@ -1896,8 +1961,10 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, bool needs_mapping, sets_mapping; int err; - if (!mlx5e_is_eswitch_flow(flow)) + if (!mlx5e_is_eswitch_flow(flow)) { + NL_SET_ERR_MSG_MOD(extack, "Match on tunnel is not supported"); return -EOPNOTSUPP; + } needs_mapping = !!flow->attr->chain; sets_mapping = flow_requires_tunnel_mapping(flow->attr->chain, f); @@ -1905,8 +1972,8 @@ 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; @@ -2269,8 +2336,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, addr_type = match.key->addr_type; /* the HW doesn't support frag first/later */ - if (match.mask->flags & FLOW_DIS_FIRST_FRAG) + if (match.mask->flags & FLOW_DIS_FIRST_FRAG) { + NL_SET_ERR_MSG_MOD(extack, "Match on frag first/later is not supported"); return -EOPNOTSUPP; + } if (match.mask->flags & FLOW_DIS_IS_FRAGMENT) { MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1); @@ -2437,8 +2506,11 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, switch (ip_proto) { case IPPROTO_ICMP: if (!(MLX5_CAP_GEN(priv->mdev, flex_parser_protocols) & - MLX5_FLEX_PROTO_ICMP)) + MLX5_FLEX_PROTO_ICMP)) { + NL_SET_ERR_MSG_MOD(extack, + "Match on Flex protocols for ICMP is not supported"); return -EOPNOTSUPP; + } MLX5_SET(fte_match_set_misc3, misc_c_3, icmp_type, match.mask->type); MLX5_SET(fte_match_set_misc3, misc_v_3, icmp_type, @@ -2450,8 +2522,11 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, break; case IPPROTO_ICMPV6: if (!(MLX5_CAP_GEN(priv->mdev, flex_parser_protocols) & - MLX5_FLEX_PROTO_ICMPV6)) + MLX5_FLEX_PROTO_ICMPV6)) { + NL_SET_ERR_MSG_MOD(extack, + "Match on Flex protocols for ICMPV6 is not supported"); return -EOPNOTSUPP; + } MLX5_SET(fte_match_set_misc3, misc_c_3, icmpv6_type, match.mask->type); MLX5_SET(fte_match_set_misc3, misc_v_3, icmpv6_type, @@ -2557,15 +2632,19 @@ static int pedit_header_offsets[] = { #define pedit_header(_ph, _htype) ((void *)(_ph) + pedit_header_offsets[_htype]) static int set_pedit_val(u8 hdr_type, u32 mask, u32 val, u32 offset, - struct pedit_headers_action *hdrs) + struct pedit_headers_action *hdrs, + struct netlink_ext_ack *extack) { u32 *curr_pmask, *curr_pval; curr_pmask = (u32 *)(pedit_header(&hdrs->masks, hdr_type) + offset); curr_pval = (u32 *)(pedit_header(&hdrs->vals, hdr_type) + offset); - if (*curr_pmask & mask) /* disallow acting twice on the same location */ + if (*curr_pmask & mask) { /* disallow acting twice on the same location */ + NL_SET_ERR_MSG_MOD(extack, + "curr_pmask and new mask same. Acting twice on same location"); goto out_err; + } *curr_pmask |= mask; *curr_pval |= (val & mask); @@ -2898,7 +2977,7 @@ parse_pedit_to_modify_hdr(struct mlx5e_priv *priv, val = act->mangle.val; offset = act->mangle.offset; - err = set_pedit_val(htype, ~mask, val, offset, &hdrs[cmd]); + err = set_pedit_val(htype, ~mask, val, offset, &hdrs[cmd], extack); if (err) goto out_err; @@ -2910,16 +2989,17 @@ 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) { u32 mask, val, offset; u32 *p; - if (act->id != FLOW_ACTION_MANGLE) + if (act->id != FLOW_ACTION_MANGLE) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported action id"); return -EOPNOTSUPP; + } if (act->mangle.htype != FLOW_ACT_MANGLE_HDR_TYPE_ETH) { NL_SET_ERR_MSG_MOD(extack, "Only Ethernet modification is supported"); @@ -2943,7 +3023,7 @@ 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 +3105,10 @@ 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 +3136,7 @@ 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 +3154,7 @@ 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 +3162,11 @@ 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 +3213,7 @@ 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 +3231,10 @@ 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 +3255,65 @@ 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 +3462,51 @@ 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] = {}; @@ -3368,12 +3515,16 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, u32 action = 0; int err, i; - if (!flow_action_has_entries(flow_action)) + if (!flow_action_has_entries(flow_action)) { + NL_SET_ERR_MSG_MOD(extack, "Flow action doesn't have any entries"); return -EINVAL; + } if (!flow_action_hw_stats_check(flow_action, extack, - FLOW_ACTION_HW_STATS_DELAYED_BIT)) + FLOW_ACTION_HW_STATS_DELAYED_BIT)) { + NL_SET_ERR_MSG_MOD(extack, "Flow action HW stats type is not supported"); return -EOPNOTSUPP; + } nic_attr = attr->nic_attr; nic_attr->flow_tag = MLX5_FS_DEFAULT_FLOW_TAG; @@ -3451,7 +3602,8 @@ 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: @@ -3462,38 +3614,22 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, flow_flag_set(flow, CT); break; default: - NL_SET_ERR_MSG_MOD(extack, "The offload action is not supported"); + NL_SET_ERR_MSG_MOD(extack, + "The offload action is not supported in NIC action"); return -EOPNOTSUPP; } } - 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; @@ -3517,19 +3653,25 @@ static bool is_merged_eswitch_vfs(struct mlx5e_priv *priv, static int parse_tc_vlan_action(struct mlx5e_priv *priv, const struct flow_action_entry *act, struct mlx5_esw_flow_attr *attr, - u32 *action) + u32 *action, + struct netlink_ext_ack *extack) { u8 vlan_idx = attr->total_vlan; - if (vlan_idx >= MLX5_FS_VLAN_DEPTH) + if (vlan_idx >= MLX5_FS_VLAN_DEPTH) { + NL_SET_ERR_MSG_MOD(extack, "Total vlans used is greater than supported"); return -EOPNOTSUPP; + } switch (act->id) { case FLOW_ACTION_VLAN_POP: if (vlan_idx) { if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, - MLX5_FS_VLAN_DEPTH)) + MLX5_FS_VLAN_DEPTH)) { + NL_SET_ERR_MSG_MOD(extack, + "vlan pop action is not supported"); return -EOPNOTSUPP; + } *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2; } else { @@ -3545,20 +3687,27 @@ static int parse_tc_vlan_action(struct mlx5e_priv *priv, if (vlan_idx) { if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, - MLX5_FS_VLAN_DEPTH)) + MLX5_FS_VLAN_DEPTH)) { + NL_SET_ERR_MSG_MOD(extack, + "vlan push action is not supported for vlan depth > 1"); return -EOPNOTSUPP; + } *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2; } else { if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, 1) && (act->vlan.proto != htons(ETH_P_8021Q) || - act->vlan.prio)) + act->vlan.prio)) { + NL_SET_ERR_MSG_MOD(extack, + "vlan push action is not supported"); return -EOPNOTSUPP; + } *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH; } break; default: + NL_SET_ERR_MSG_MOD(extack, "Unexpected action id for VLAN"); return -EINVAL; } @@ -3592,7 +3741,8 @@ static struct net_device *get_fdb_out_dev(struct net_device *uplink_dev, static int add_vlan_push_action(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr, struct net_device **out_dev, - u32 *action) + u32 *action, + struct netlink_ext_ack *extack) { struct net_device *vlan_dev = *out_dev; struct flow_action_entry vlan_act = { @@ -3603,7 +3753,7 @@ static int add_vlan_push_action(struct mlx5e_priv *priv, }; int err; - err = parse_tc_vlan_action(priv, &vlan_act, attr->esw_attr, action); + err = parse_tc_vlan_action(priv, &vlan_act, attr->esw_attr, action, extack); if (err) return err; @@ -3614,14 +3764,15 @@ static int add_vlan_push_action(struct mlx5e_priv *priv, return -ENODEV; if (is_vlan_dev(*out_dev)) - err = add_vlan_push_action(priv, attr, out_dev, action); + err = add_vlan_push_action(priv, attr, out_dev, action, extack); return err; } static int add_vlan_pop_action(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr, - u32 *action) + u32 *action, + struct netlink_ext_ack *extack) { struct flow_action_entry vlan_act = { .id = FLOW_ACTION_VLAN_POP, @@ -3631,7 +3782,7 @@ static int add_vlan_pop_action(struct mlx5e_priv *priv, nest_level = attr->parse_attr->filter_dev->lower_level - priv->netdev->lower_level; while (nest_level--) { - err = parse_tc_vlan_action(priv, &vlan_act, attr->esw_attr, action); + err = parse_tc_vlan_action(priv, &vlan_act, attr->esw_attr, action, extack); if (err) return err; } @@ -3732,6 +3883,45 @@ static int verify_uplink_forwarding(struct mlx5e_priv *priv, return 0; } +int mlx5e_set_fwd_to_int_port_actions(struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr, + int ifindex, + enum mlx5e_tc_int_port_type type, + u32 *action, + int out_index) +{ + struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; + struct mlx5e_tc_int_port_priv *int_port_priv; + struct mlx5e_tc_flow_parse_attr *parse_attr; + struct mlx5e_tc_int_port *dest_int_port; + int err; + + parse_attr = attr->parse_attr; + int_port_priv = mlx5e_get_int_port_priv(priv); + + dest_int_port = mlx5e_tc_int_port_get(int_port_priv, ifindex, type); + if (IS_ERR(dest_int_port)) + return PTR_ERR(dest_int_port); + + err = mlx5e_tc_match_to_reg_set(priv->mdev, &parse_attr->mod_hdr_acts, + MLX5_FLOW_NAMESPACE_FDB, VPORT_TO_REG, + mlx5e_tc_int_port_get_metadata(dest_int_port)); + if (err) { + mlx5e_tc_int_port_put(int_port_priv, dest_int_port); + return err; + } + + *action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; + + esw_attr->dest_int_port = dest_int_port; + esw_attr->dests[out_index].flags |= MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE; + + /* Forward to root fdb for matching against the new source vport */ + attr->dest_chain = 0; + + return 0; +} + static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct flow_action *flow_action, struct mlx5e_tc_flow *flow, @@ -3751,20 +3941,39 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, bool encap = false, decap = false; u32 action = attr->action; int err, i, if_count = 0; + bool ptype_host = false; bool mpls_push = false; - if (!flow_action_has_entries(flow_action)) + if (!flow_action_has_entries(flow_action)) { + NL_SET_ERR_MSG_MOD(extack, "Flow action doesn't have any entries"); return -EINVAL; + } if (!flow_action_hw_stats_check(flow_action, extack, - FLOW_ACTION_HW_STATS_DELAYED_BIT)) + FLOW_ACTION_HW_STATS_DELAYED_BIT)) { + NL_SET_ERR_MSG_MOD(extack, "Flow action HW stats type is not supported"); return -EOPNOTSUPP; + } esw_attr = attr->esw_attr; parse_attr = attr->parse_attr; 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_PTYPE: + if (act->ptype != PACKET_HOST) { + NL_SET_ERR_MSG_MOD(extack, + "skbedit ptype is only supported with type host"); + return -EOPNOTSUPP; + } + + ptype_host = true; + break; case FLOW_ACTION_DROP: action |= MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; @@ -3828,6 +4037,50 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, break; return -EOPNOTSUPP; + case FLOW_ACTION_REDIRECT_INGRESS: { + struct net_device *out_dev; + + out_dev = act->dev; + if (!out_dev) + return -EOPNOTSUPP; + + if (!netif_is_ovs_master(out_dev)) { + NL_SET_ERR_MSG_MOD(extack, + "redirect to ingress is supported only for OVS internal ports"); + return -EOPNOTSUPP; + } + + if (netif_is_ovs_master(parse_attr->filter_dev)) { + NL_SET_ERR_MSG_MOD(extack, + "redirect to ingress is not supported from internal port"); + return -EOPNOTSUPP; + } + + if (!ptype_host) { + NL_SET_ERR_MSG_MOD(extack, + "redirect to int port ingress requires ptype=host action"); + return -EOPNOTSUPP; + } + + if (esw_attr->out_count) { + NL_SET_ERR_MSG_MOD(extack, + "redirect to int port ingress is supported only as single destination"); + return -EOPNOTSUPP; + } + + action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_COUNT; + + err = mlx5e_set_fwd_to_int_port_actions(priv, attr, out_dev->ifindex, + MLX5E_TC_INT_PORT_INGRESS, + &action, esw_attr->out_count); + if (err) + return err; + + esw_attr->out_count++; + + break; + } case FLOW_ACTION_REDIRECT: case FLOW_ACTION_MIRRED: { struct mlx5e_priv *out_priv; @@ -3902,18 +4155,21 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, if (is_vlan_dev(out_dev)) { err = add_vlan_push_action(priv, attr, &out_dev, - &action); + &action, extack); if (err) return err; } if (is_vlan_dev(parse_attr->filter_dev)) { err = add_vlan_pop_action(priv, attr, - &action); + &action, extack); if (err) 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; @@ -3935,6 +4191,16 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, esw_attr->dests[esw_attr->out_count].rep = rpriv->rep; esw_attr->dests[esw_attr->out_count].mdev = out_priv->mdev; esw_attr->out_count++; + } else if (netif_is_ovs_master(out_dev)) { + err = mlx5e_set_fwd_to_int_port_actions(priv, attr, + out_dev->ifindex, + MLX5E_TC_INT_PORT_EGRESS, + &action, + esw_attr->out_count); + if (err) + return err; + + esw_attr->out_count++; } else if (parse_attr->filter_dev != priv->netdev) { /* All mlx5 devices are called to configure * high level device filters. Therefore, the @@ -3955,10 +4221,13 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, break; case FLOW_ACTION_TUNNEL_ENCAP: info = act->tunnel; - if (info) + if (info) { encap = true; - else + } else { + NL_SET_ERR_MSG_MOD(extack, + "Zero tunnel attributes is not supported"); return -EOPNOTSUPP; + } break; case FLOW_ACTION_VLAN_PUSH: @@ -3972,7 +4241,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, act, parse_attr, hdrs, &action, extack); } else { - err = parse_tc_vlan_action(priv, act, esw_attr, &action); + err = parse_tc_vlan_action(priv, act, esw_attr, &action, extack); } if (err) return err; @@ -3998,7 +4267,8 @@ 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: @@ -4025,11 +4295,20 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, flow_flag_set(flow, SAMPLE); break; default: - NL_SET_ERR_MSG_MOD(extack, "The offload action is not supported"); + NL_SET_ERR_MSG_MOD(extack, + "The offload action is not supported in FDB action"); return -EOPNOTSUPP; } } + /* Forward to/from internal port can only have 1 dest */ + if ((netif_is_ovs_master(parse_attr->filter_dev) || esw_attr->dest_int_port) && + esw_attr->out_count > 1) { + NL_SET_ERR_MSG_MOD(extack, + "Rules with internal port can have only one destination"); + return -EOPNOTSUPP; + } + /* always set IP version for indirect table handling */ attr->ip_version = mlx5e_tc_get_ip_version(&parse_attr->spec, true); @@ -4045,60 +4324,26 @@ 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; } @@ -4733,8 +4978,10 @@ static int scan_tc_matchall_fdb_actions(struct mlx5e_priv *priv, return -EOPNOTSUPP; } - if (!flow_action_basic_hw_stats_check(flow_action, extack)) + if (!flow_action_basic_hw_stats_check(flow_action, extack)) { + NL_SET_ERR_MSG_MOD(extack, "Flow action HW stats type is not supported"); return -EOPNOTSUPP; + } flow_action_for_each(i, act, flow_action) { switch (act->id) { @@ -5006,9 +5253,9 @@ 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->int_port_priv = mlx5e_tc_int_port_init(netdev_priv(priv->netdev)); + 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 +5269,11 @@ 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 +5301,8 @@ 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 + mlx5e_tc_int_port_cleanup(uplink_priv->int_port_priv); mlx5_tc_ct_clean(uplink_priv->ct_priv); netdev_warn(priv->netdev, "Failed to initialize tc (eswitch), err: %d", err); @@ -5074,9 +5322,8 @@ 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 + mlx5e_tc_int_port_cleanup(uplink_priv->int_port_priv); 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/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 1a4cd882f0fb..fdb222793027 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -38,6 +38,7 @@ #include "eswitch.h" #include "en/tc_ct.h" #include "en/tc_tun.h" +#include "en/tc/int_port.h" #include "en_rep.h" #define MLX5E_TC_FLOW_ID_MASK 0x0000ffff @@ -56,7 +57,7 @@ int mlx5e_tc_num_filters(struct mlx5e_priv *priv, unsigned long flags); struct mlx5e_tc_update_priv { - struct net_device *tun_dev; + struct net_device *fwd_dev; }; struct mlx5_nic_flow_attr { @@ -104,6 +105,8 @@ struct mlx5_rx_tun_attr { #define MLX5E_TC_TABLE_CHAIN_TAG_BITS 16 #define MLX5E_TC_TABLE_CHAIN_TAG_MASK GENMASK(MLX5E_TC_TABLE_CHAIN_TAG_BITS - 1, 0) +#define MLX5E_TC_MAX_INT_PORT_NUM (8) + #if IS_ENABLED(CONFIG_MLX5_CLS_ACT) struct tunnel_match_key { @@ -283,6 +286,12 @@ bool mlx5e_tc_is_vf_tunnel(struct net_device *out_dev, struct net_device *route_ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *route_dev, u16 *vport); +int mlx5e_set_fwd_to_int_port_actions(struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr, + int ifindex, + enum mlx5e_tc_int_port_type type, + u32 *action, + int out_index); #else /* CONFIG_MLX5_CLS_ACT */ static inline int mlx5e_tc_nic_init(struct mlx5e_priv *priv) { return 0; } static inline void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) {} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index c63d78eda606..7fd33b356cc8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -38,6 +38,7 @@ #include "en/txrx.h" #include "ipoib/ipoib.h" #include "en_accel/en_accel.h" +#include "en_accel/ipsec_rxtx.h" #include "en/ptp.h" static void mlx5e_dma_unmap_wqe_err(struct mlx5e_txqsq *sq, u8 num_dma) @@ -213,27 +214,14 @@ static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs) memcpy(&vhdr->h_vlan_encapsulated_proto, skb->data + cpy1_sz, cpy2_sz); } -/* If packet is not IP's CHECKSUM_PARTIAL (e.g. icmd packet), - * need to set L3 checksum flag for IPsec - */ -static void -ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, - struct mlx5_wqe_eth_seg *eseg) -{ - eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM; - if (skb->encapsulation) { - eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM; - sq->stats->csum_partial_inner++; - } else { - sq->stats->csum_partial++; - } -} - static inline void mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5e_accel_tx_state *accel, struct mlx5_wqe_eth_seg *eseg) { + if (unlikely(mlx5e_ipsec_txwqe_build_eseg_csum(sq, skb, eseg))) + return; + if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) { eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM; if (skb->encapsulation) { @@ -249,8 +237,6 @@ mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM | MLX5_ETH_WQE_L4_CSUM; sq->stats->csum_partial++; #endif - } else if (unlikely(mlx5e_ipsec_eseg_meta(eseg))) { - ipsec_txwqe_build_eseg_csum(sq, skb, eseg); } else sq->stats->csum_none++; } 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/acl/egress_lgcy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c index 0399a396d166..60a73990017c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c @@ -79,12 +79,16 @@ int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw, int dest_num = 0; int err = 0; - if (MLX5_CAP_ESW_EGRESS_ACL(esw->dev, flow_counter)) { + if (vport->egress.legacy.drop_counter) { + drop_counter = vport->egress.legacy.drop_counter; + } else if (MLX5_CAP_ESW_EGRESS_ACL(esw->dev, flow_counter)) { drop_counter = mlx5_fc_create(esw->dev, false); - if (IS_ERR(drop_counter)) + if (IS_ERR(drop_counter)) { esw_warn(esw->dev, "vport[%d] configure egress drop rule counter err(%ld)\n", vport->vport, PTR_ERR(drop_counter)); + drop_counter = NULL; + } vport->egress.legacy.drop_counter = drop_counter; } @@ -123,7 +127,7 @@ int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw, flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP; /* Attach egress drop flow counter */ - if (!IS_ERR_OR_NULL(drop_counter)) { + if (drop_counter) { flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; drop_ctr_dst.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; drop_ctr_dst.counter_id = mlx5_fc_id(drop_counter); @@ -162,7 +166,7 @@ void esw_acl_egress_lgcy_cleanup(struct mlx5_eswitch *esw, esw_acl_egress_table_destroy(vport); clean_drop_counter: - if (!IS_ERR_OR_NULL(vport->egress.legacy.drop_counter)) { + if (vport->egress.legacy.drop_counter) { mlx5_fc_destroy(esw->dev, vport->egress.legacy.drop_counter); vport->egress.legacy.drop_counter = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c index f75b86abaf1c..b1a5199260f6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c @@ -160,7 +160,9 @@ int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw, esw_acl_ingress_lgcy_rules_destroy(vport); - if (MLX5_CAP_ESW_INGRESS_ACL(esw->dev, flow_counter)) { + if (vport->ingress.legacy.drop_counter) { + counter = vport->ingress.legacy.drop_counter; + } else if (MLX5_CAP_ESW_INGRESS_ACL(esw->dev, flow_counter)) { counter = mlx5_fc_create(esw->dev, false); if (IS_ERR(counter)) { esw_warn(esw->dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index 7e221038df8d..f690f430f40f 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); @@ -564,6 +677,10 @@ mlx5_esw_bridge_egress_flow_create(u16 vport_num, u16 esw_owner_vhca_id, const u if (!rule_spec) return ERR_PTR(-ENOMEM); + if (MLX5_CAP_ESW_FLOWTABLE(bridge->br_offloads->esw->dev, flow_source) && + vport_num == MLX5_VPORT_UPLINK) + rule_spec->flow_context.flow_source = + MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT; rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; dmac_v = MLX5_ADDR_OF(fte_match_param, rule_spec->match_value, @@ -599,6 +716,41 @@ 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) { @@ -736,14 +888,20 @@ mlx5_esw_bridge_fdb_entry_cleanup(struct mlx5_esw_bridge_fdb_entry *entry, kvfree(entry); } +static void +mlx5_esw_bridge_fdb_entry_notify_and_cleanup(struct mlx5_esw_bridge_fdb_entry *entry, + struct mlx5_esw_bridge *bridge) +{ + mlx5_esw_bridge_fdb_del_notify(entry); + mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge); +} + static void mlx5_esw_bridge_fdb_flush(struct mlx5_esw_bridge *bridge) { struct mlx5_esw_bridge_fdb_entry *entry, *tmp; - list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) { - mlx5_esw_bridge_fdb_del_notify(entry); - mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge); - } + list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) + mlx5_esw_bridge_fdb_entry_notify_and_cleanup(entry, bridge); } static struct mlx5_esw_bridge_vlan * @@ -798,24 +956,14 @@ 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 +981,33 @@ 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 +1027,10 @@ 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 +1049,9 @@ 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: @@ -886,17 +1068,18 @@ 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) { - mlx5_esw_bridge_fdb_del_notify(entry); - mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge); - } + list_for_each_entry_safe(entry, tmp, &vlan->fdb_list, vlan_list) + mlx5_esw_bridge_fdb_entry_notify_and_cleanup(entry, bridge); 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, @@ -949,6 +1132,17 @@ mlx5_esw_bridge_port_vlan_lookup(u16 vid, u16 vport_num, u16 esw_owner_vhca_id, } static struct mlx5_esw_bridge_fdb_entry * +mlx5_esw_bridge_fdb_lookup(struct mlx5_esw_bridge *bridge, + const unsigned char *addr, u16 vid) +{ + struct mlx5_esw_bridge_fdb_key key = {}; + + ether_addr_copy(key.addr, addr); + key.vid = vid; + return rhashtable_lookup_fast(&bridge->fdb_ht, &key, fdb_ht_params); +} + +static struct mlx5_esw_bridge_fdb_entry * mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id, const unsigned char *addr, u16 vid, bool added_by_user, bool peer, struct mlx5_eswitch *esw, struct mlx5_esw_bridge *bridge) @@ -966,6 +1160,10 @@ mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, u16 esw_ow return ERR_CAST(vlan); } + entry = mlx5_esw_bridge_fdb_lookup(bridge, addr, vid); + if (entry) + mlx5_esw_bridge_fdb_entry_notify_and_cleanup(entry, bridge); + entry = kvzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return ERR_PTR(-ENOMEM); @@ -1265,7 +1463,6 @@ void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16 struct switchdev_notifier_fdb_info *fdb_info) { struct mlx5_esw_bridge_fdb_entry *entry; - struct mlx5_esw_bridge_fdb_key key; struct mlx5_esw_bridge_port *port; struct mlx5_esw_bridge *bridge; @@ -1274,13 +1471,11 @@ void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16 return; bridge = port->bridge; - ether_addr_copy(key.addr, fdb_info->addr); - key.vid = fdb_info->vid; - entry = rhashtable_lookup_fast(&bridge->fdb_ht, &key, fdb_ht_params); + entry = mlx5_esw_bridge_fdb_lookup(bridge, fdb_info->addr, fdb_info->vid); if (!entry) { esw_debug(br_offloads->esw->dev, "FDB entry with specified key not found (MAC=%pM,vid=%u,vport=%u)\n", - key.addr, key.vid, vport_num); + fdb_info->addr, fdb_info->vid, vport_num); return; } @@ -1322,7 +1517,6 @@ void mlx5_esw_bridge_fdb_remove(struct net_device *dev, u16 vport_num, u16 esw_o { struct mlx5_eswitch *esw = br_offloads->esw; struct mlx5_esw_bridge_fdb_entry *entry; - struct mlx5_esw_bridge_fdb_key key; struct mlx5_esw_bridge_port *port; struct mlx5_esw_bridge *bridge; @@ -1331,18 +1525,15 @@ void mlx5_esw_bridge_fdb_remove(struct net_device *dev, u16 vport_num, u16 esw_o return; bridge = port->bridge; - ether_addr_copy(key.addr, fdb_info->addr); - key.vid = fdb_info->vid; - entry = rhashtable_lookup_fast(&bridge->fdb_ht, &key, fdb_ht_params); + entry = mlx5_esw_bridge_fdb_lookup(bridge, fdb_info->addr, fdb_info->vid); if (!entry) { esw_warn(esw->dev, "FDB entry with specified key not found (MAC=%pM,vid=%u,vport=%u)\n", - key.addr, key.vid, vport_num); + fdb_info->addr, fdb_info->vid, vport_num); return; } - mlx5_esw_bridge_fdb_del_notify(entry); - mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge); + mlx5_esw_bridge_fdb_entry_notify_and_cleanup(entry, bridge); } void mlx5_esw_bridge_update(struct mlx5_esw_bridge_offloads *br_offloads) @@ -1358,13 +1549,11 @@ void mlx5_esw_bridge_update(struct mlx5_esw_bridge_offloads *br_offloads) if (entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER) continue; - if (time_after(lastuse, entry->lastuse)) { + if (time_after(lastuse, entry->lastuse)) mlx5_esw_bridge_fdb_entry_refresh(entry); - } else if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_PEER) && - time_is_before_jiffies(entry->lastuse + bridge->ageing_time)) { - mlx5_esw_bridge_fdb_del_notify(entry); - mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge); - } + else if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_PEER) && + time_is_before_jiffies(entry->lastuse + bridge->ageing_time)) + mlx5_esw_bridge_fdb_entry_notify_and_cleanup(entry, bridge); } } } 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/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c index 20af557ae30c..7f9b96d9537e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c @@ -36,7 +36,7 @@ static struct devlink_port *mlx5_esw_dl_port_alloc(struct mlx5_eswitch *esw, u16 return NULL; mlx5_esw_get_port_parent_id(dev, &ppid); - pfnum = PCI_FUNC(dev->pdev->devfn); + pfnum = mlx5_get_dev_index(dev); external = mlx5_core_is_ecpf_esw_manager(dev); if (external) controller_num = dev->priv.eswitch->offloads.host_number + 1; @@ -149,7 +149,7 @@ int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_p if (IS_ERR(vport)) return PTR_ERR(vport); - pfnum = PCI_FUNC(dev->pdev->devfn); + pfnum = mlx5_get_dev_index(dev); mlx5_esw_get_port_parent_id(dev, &ppid); memcpy(dl_port->attrs.switch_id.id, &ppid.id[0], ppid.id_len); dl_port->attrs.switch_id.id_len = ppid.id_len; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index 985e305179d1..c6cc67cb4f6a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -473,10 +473,9 @@ esw_qos_create_rate_group(struct mlx5_eswitch *esw, struct netlink_ext_ack *exta err_min_rate: list_del(&group->list); - err = mlx5_destroy_scheduling_element_cmd(esw->dev, - SCHEDULING_HIERARCHY_E_SWITCH, - group->tsar_ix); - if (err) + if (mlx5_destroy_scheduling_element_cmd(esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + group->tsar_ix)) NL_SET_ERR_MSG_MOD(extack, "E-Switch destroy TSAR for group failed"); err_sched_elem: kfree(group); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 2c7444101bb9..42f8ee2e5d9f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -51,6 +51,7 @@ enum mlx5_mapped_obj_type { MLX5_MAPPED_OBJ_CHAIN, MLX5_MAPPED_OBJ_SAMPLE, + MLX5_MAPPED_OBJ_INT_PORT_METADATA, }; struct mlx5_mapped_obj { @@ -63,6 +64,7 @@ struct mlx5_mapped_obj { u32 trunc_size; u32 tunnel_id; } sample; + u32 int_port_metadata; }; }; @@ -88,6 +90,7 @@ enum { MAPPING_TYPE_TUNNEL_ENC_OPTS, MAPPING_TYPE_LABELS, MAPPING_TYPE_ZONE, + MAPPING_TYPE_INT_PORT, }; struct vport_ingress { @@ -336,6 +339,9 @@ void mlx5_esw_match_metadata_free(struct mlx5_eswitch *esw, u32 metadata); int mlx5_esw_qos_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, u32 rate_mbps); +bool mlx5_esw_vport_match_metadata_supported(const struct mlx5_eswitch *esw); +int mlx5_esw_offloads_vport_metadata_set(struct mlx5_eswitch *esw, bool enable); + /* E-Switch API */ int mlx5_eswitch_init(struct mlx5_core_dev *dev); void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw); @@ -433,7 +439,7 @@ enum mlx5_flow_match_level { }; /* current maximum for flow based vport multicasting */ -#define MLX5_MAX_FLOW_FWD_VPORTS 2 +#define MLX5_MAX_FLOW_FWD_VPORTS 32 enum { MLX5_ESW_DEST_ENCAP = BIT(0), @@ -447,12 +453,22 @@ 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; struct mlx5_core_dev *counter_dev; + struct mlx5e_tc_int_port *dest_int_port; + struct mlx5e_tc_int_port *int_port; int split_count; int out_count; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 0d461e38add3..f4eaa5893886 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -86,12 +86,18 @@ mlx5_eswitch_set_rule_flow_source(struct mlx5_eswitch *esw, struct mlx5_flow_spec *spec, struct mlx5_esw_flow_attr *attr) { - if (MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source) && - attr && attr->in_rep) - spec->flow_context.flow_source = - attr->in_rep->vport == MLX5_VPORT_UPLINK ? - MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK : - MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT; + if (!MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source) || !attr || !attr->in_rep) + return; + + if (attr->int_port) { + spec->flow_context.flow_source = mlx5e_tc_int_port_get_flow_source(attr->int_port); + + return; + } + + spec->flow_context.flow_source = (attr->in_rep->vport == MLX5_VPORT_UPLINK) ? + MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK : + MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT; } /* Actually only the upper 16 bits of reg c0 need to be cleared, but the lower 16 bits @@ -121,6 +127,8 @@ mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw, struct mlx5_eswitch *src_esw, u16 vport) { + struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; + u32 metadata; void *misc2; void *misc; @@ -130,10 +138,16 @@ mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw, if (mlx5_eswitch_vport_match_metadata_enabled(esw)) { if (mlx5_esw_indir_table_decap_vport(attr)) vport = mlx5_esw_indir_table_decap_vport(attr); + + if (esw_attr->int_port) + metadata = + mlx5e_tc_int_port_get_metadata_for_match(esw_attr->int_port); + else + metadata = + mlx5_eswitch_get_vport_metadata_for_match(src_esw, vport); + misc2 = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters_2); - MLX5_SET(fte_match_set_misc2, misc2, metadata_reg_c_0, - mlx5_eswitch_get_vport_metadata_for_match(src_esw, - vport)); + MLX5_SET(fte_match_set_misc2, misc2, metadata_reg_c_0, metadata); misc2 = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters_2); MLX5_SET(fte_match_set_misc2, misc2, metadata_reg_c_0, @@ -290,8 +304,11 @@ esw_setup_chain_src_port_rewrite(struct mlx5_flow_destination *dest, err = esw_setup_chain_dest(dest, flow_act, chains, attr->dest_chain, 1, 0, *i); if (err) goto err_setup_chain; - flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; - flow_act->pkt_reformat = esw_attr->dests[j].pkt_reformat; + + if (esw_attr->dests[j].pkt_reformat) { + flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; + flow_act->pkt_reformat = esw_attr->dests[j].pkt_reformat; + } } return 0; @@ -315,7 +332,8 @@ esw_is_indir_table(struct mlx5_eswitch *esw, struct mlx5_flow_attr *attr) int i; for (i = esw_attr->split_count; i < esw_attr->out_count; i++) - if (mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].rep->vport, + if (esw_attr->dests[i].rep && + mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].rep->vport, esw_attr->dests[i].mdev)) return true; return false; @@ -440,7 +458,7 @@ 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 +485,7 @@ 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)) @@ -482,12 +500,12 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr) { - struct mlx5_flow_destination dest[MLX5_MAX_FLOW_FWD_VPORTS + 1] = {}; struct mlx5_flow_act flow_act = { .flags = FLOW_ACT_NO_APPEND, }; struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; struct mlx5_fs_chains *chains = esw_chains(esw); bool split = !!(esw_attr->split_count); struct mlx5_vport_tbl_attr fwd_attr; + struct mlx5_flow_destination *dest; struct mlx5_flow_handle *rule; struct mlx5_flow_table *fdb; int i = 0; @@ -495,6 +513,10 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, if (esw->mode != MLX5_ESWITCH_OFFLOADS) return ERR_PTR(-EOPNOTSUPP); + dest = kcalloc(MLX5_MAX_FLOW_FWD_VPORTS + 1, sizeof(*dest), GFP_KERNEL); + if (!dest) + return ERR_PTR(-ENOMEM); + flow_act.action = attr->action; /* if per flow vlan pop/push is emulated, don't set that into the firmware */ if (!mlx5_eswitch_vlan_actions_supported(esw->dev, 1)) @@ -574,6 +596,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, else atomic64_inc(&esw->offloads.num_flows); + kfree(dest); return rule; err_add_rule: @@ -584,6 +607,7 @@ err_add_rule: err_esw_get: esw_cleanup_dests(esw, attr); err_create_goto_table: + kfree(dest); return rule; } @@ -592,16 +616,20 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw, struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr) { - struct mlx5_flow_destination dest[MLX5_MAX_FLOW_FWD_VPORTS + 1] = {}; struct mlx5_flow_act flow_act = { .flags = FLOW_ACT_NO_APPEND, }; struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; struct mlx5_fs_chains *chains = esw_chains(esw); struct mlx5_vport_tbl_attr fwd_attr; + struct mlx5_flow_destination *dest; struct mlx5_flow_table *fast_fdb; struct mlx5_flow_table *fwd_fdb; struct mlx5_flow_handle *rule; int i, err = 0; + dest = kcalloc(MLX5_MAX_FLOW_FWD_VPORTS + 1, sizeof(*dest), GFP_KERNEL); + if (!dest) + return ERR_PTR(-ENOMEM); + fast_fdb = mlx5_chains_get_table(chains, attr->chain, attr->prio, 0); if (IS_ERR(fast_fdb)) { rule = ERR_CAST(fast_fdb); @@ -654,6 +682,7 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw, atomic64_inc(&esw->offloads.num_flows); + kfree(dest); return rule; err_chain_src_rewrite: esw_put_dest_tables_loop(esw, attr, 0, i); @@ -661,6 +690,7 @@ err_chain_src_rewrite: err_get_fwd: mlx5_chains_put_table(chains, attr->chain, attr->prio, 0); err_get_fast: + kfree(dest); return rule; } @@ -678,7 +708,7 @@ __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 +1039,7 @@ 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 +1218,7 @@ 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; @@ -1845,6 +1875,17 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw) atomic64_set(&esw->user_count, 0); } +static int esw_get_offloads_ft_size(struct mlx5_eswitch *esw) +{ + int nvports; + + nvports = esw->total_vports + MLX5_ESW_MISS_FLOWS; + if (mlx5e_tc_int_port_supported(esw)) + nvports += MLX5E_TC_MAX_INT_PORT_NUM; + + return nvports; +} + static int esw_create_offloads_table(struct mlx5_eswitch *esw) { struct mlx5_flow_table_attr ft_attr = {}; @@ -1859,7 +1900,7 @@ static int esw_create_offloads_table(struct mlx5_eswitch *esw) return -EOPNOTSUPP; } - ft_attr.max_fte = esw->total_vports + MLX5_ESW_MISS_FLOWS; + ft_attr.max_fte = esw_get_offloads_ft_size(esw); ft_attr.prio = 1; ft_offloads = mlx5_create_flow_table(ns, &ft_attr); @@ -1888,7 +1929,7 @@ static int esw_create_vport_rx_group(struct mlx5_eswitch *esw) int nvports; int err = 0; - nvports = esw->total_vports + MLX5_ESW_MISS_FLOWS; + nvports = esw_get_offloads_ft_size(esw); flow_group_in = kvzalloc(inlen, GFP_KERNEL); if (!flow_group_in) return -ENOMEM; @@ -2793,12 +2834,13 @@ bool mlx5_esw_vport_match_metadata_supported(const struct mlx5_eswitch *esw) u32 mlx5_esw_match_metadata_alloc(struct mlx5_eswitch *esw) { u32 vport_end_ida = (1 << ESW_VPORT_BITS) - 1; - u32 max_pf_num = (1 << ESW_PFNUM_BITS) - 1; + /* Reserve 0xf for internal port offload */ + u32 max_pf_num = (1 << ESW_PFNUM_BITS) - 2; u32 pf_num; int id; /* Only 4 bits of pf_num */ - pf_num = PCI_FUNC(esw->dev->pdev->devfn); + pf_num = mlx5_get_dev_index(esw->dev); if (pf_num > max_pf_num) return 0; 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..182306bbefaa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c @@ -219,8 +219,8 @@ 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_eswitch_offload_is_uplink_port(esw, spec)) + mlx5_esw_attr_flags_skip(attr->flags) || + (!mlx5_eswitch_offload_is_uplink_port(esw, spec) && !esw_attr->int_port)) return false; /* push vlan on RX */ @@ -229,7 +229,8 @@ mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw, /* hairpin */ for (i = esw_attr->split_count; i < esw_attr->out_count; i++) - if (esw_attr->dests[i].rep->vport == MLX5_VPORT_UPLINK) + if (!esw_attr->dest_int_port && esw_attr->dests[i].rep && + esw_attr->dests[i].rep->vport == MLX5_VPORT_UPLINK) return true; return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c index 306279b7f9e7..12abe991583a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c @@ -115,7 +115,7 @@ static int mlx5_fpga_conn_post_recv(struct mlx5_fpga_conn *conn, ix = conn->qp.rq.pc & (conn->qp.rq.size - 1); data = mlx5_wq_cyc_get_wqe(&conn->qp.wq.rq, ix); data->byte_count = cpu_to_be32(buf->sg[0].size); - data->lkey = cpu_to_be32(conn->fdev->conn_res.mkey.key); + data->lkey = cpu_to_be32(conn->fdev->conn_res.mkey); data->addr = cpu_to_be64(buf->sg[0].dma_addr); conn->qp.rq.pc++; @@ -155,7 +155,7 @@ static void mlx5_fpga_conn_post_send(struct mlx5_fpga_conn *conn, if (!buf->sg[sgi].data) break; data->byte_count = cpu_to_be32(buf->sg[sgi].size); - data->lkey = cpu_to_be32(conn->fdev->conn_res.mkey.key); + data->lkey = cpu_to_be32(conn->fdev->conn_res.mkey); data->addr = cpu_to_be64(buf->sg[sgi].dma_addr); data++; size++; @@ -221,7 +221,7 @@ static int mlx5_fpga_conn_post_recv_buf(struct mlx5_fpga_conn *conn) } static int mlx5_fpga_conn_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, - struct mlx5_core_mkey *mkey) + u32 *mkey) { int inlen = MLX5_ST_SZ_BYTES(create_mkey_in); void *mkc; @@ -978,7 +978,7 @@ int mlx5_fpga_conn_device_init(struct mlx5_fpga_device *fdev) mlx5_fpga_err(fdev, "create mkey failed, %d\n", err); goto err_dealloc_pd; } - mlx5_fpga_dbg(fdev, "Created mkey 0x%x\n", fdev->conn_res.mkey.key); + mlx5_fpga_dbg(fdev, "Created mkey 0x%x\n", fdev->conn_res.mkey); return 0; @@ -994,7 +994,7 @@ out: void mlx5_fpga_conn_device_cleanup(struct mlx5_fpga_device *fdev) { - mlx5_core_destroy_mkey(fdev->mdev, &fdev->conn_res.mkey); + mlx5_core_destroy_mkey(fdev->mdev, fdev->conn_res.mkey); mlx5_core_dealloc_pd(fdev->mdev, fdev->conn_res.pdn); mlx5_put_uars_page(fdev->mdev, fdev->conn_res.uar); mlx5_nic_vport_disable_roce(fdev->mdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h index 52c9dee91ea4..2a984e82ae16 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h @@ -54,7 +54,7 @@ struct mlx5_fpga_device { /* QP Connection resources */ struct { u32 pdn; - struct mlx5_core_mkey mkey; + u32 mkey; struct mlx5_uars_page *uar; } conn_res; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 7db8df64a60e..750b21124a1a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -185,6 +185,20 @@ static int mlx5_cmd_set_slave_root_fdb(struct mlx5_core_dev *master, return mlx5_cmd_exec(slave, in, sizeof(in), out, sizeof(out)); } +static int +mlx5_cmd_stub_destroy_match_definer(struct mlx5_flow_root_namespace *ns, + int definer_id) +{ + return 0; +} + +static int +mlx5_cmd_stub_create_match_definer(struct mlx5_flow_root_namespace *ns, + u16 format_id, u32 *match_mask) +{ + return 0; +} + static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *ft, u32 underlay_qpn, bool disconnect) @@ -563,8 +577,8 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE: id = dst->dest_attr.ft->id; break; + case MLX5_FLOW_DESTINATION_TYPE_UPLINK: case MLX5_FLOW_DESTINATION_TYPE_VPORT: - id = dst->dest_attr.vport.num; MLX5_SET(dest_format_struct, in_dests, destination_eswitch_owner_vhca_id_valid, !!(dst->dest_attr.vport.flags & @@ -572,6 +586,12 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, MLX5_SET(dest_format_struct, in_dests, destination_eswitch_owner_vhca_id, dst->dest_attr.vport.vhca_id); + if (type == MLX5_FLOW_DESTINATION_TYPE_UPLINK) { + /* destination_id is reserved */ + id = 0; + break; + } + id = dst->dest_attr.vport.num; if (extended_dest && dst->dest_attr.vport.pkt_reformat) { MLX5_SET(dest_format_struct, in_dests, @@ -909,6 +929,45 @@ static void mlx5_cmd_modify_header_dealloc(struct mlx5_flow_root_namespace *ns, mlx5_cmd_exec_in(dev, dealloc_modify_header_context, in); } +static int mlx5_cmd_destroy_match_definer(struct mlx5_flow_root_namespace *ns, + int definer_id) +{ + u32 in[MLX5_ST_SZ_DW(general_obj_in_cmd_hdr)] = {}; + u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)]; + + MLX5_SET(general_obj_in_cmd_hdr, in, opcode, + MLX5_CMD_OP_DESTROY_GENERAL_OBJECT); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, + MLX5_OBJ_TYPE_MATCH_DEFINER); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_id, definer_id); + + return mlx5_cmd_exec(ns->dev, in, sizeof(in), out, sizeof(out)); +} + +static int mlx5_cmd_create_match_definer(struct mlx5_flow_root_namespace *ns, + u16 format_id, u32 *match_mask) +{ + u32 out[MLX5_ST_SZ_DW(create_match_definer_out)] = {}; + u32 in[MLX5_ST_SZ_DW(create_match_definer_in)] = {}; + struct mlx5_core_dev *dev = ns->dev; + void *ptr; + int err; + + MLX5_SET(create_match_definer_in, in, general_obj_in_cmd_hdr.opcode, + MLX5_CMD_OP_CREATE_GENERAL_OBJECT); + MLX5_SET(create_match_definer_in, in, general_obj_in_cmd_hdr.obj_type, + MLX5_OBJ_TYPE_MATCH_DEFINER); + + ptr = MLX5_ADDR_OF(create_match_definer_in, in, obj_context); + MLX5_SET(match_definer, ptr, format_id, format_id); + + ptr = MLX5_ADDR_OF(match_definer, ptr, match_mask); + memcpy(ptr, match_mask, MLX5_FLD_SZ_BYTES(match_definer, match_mask)); + + err = mlx5_cmd_exec_inout(dev, create_match_definer, in, out); + return err ? err : MLX5_GET(general_obj_out_cmd_hdr, out, obj_id); +} + static const struct mlx5_flow_cmds mlx5_flow_cmds = { .create_flow_table = mlx5_cmd_create_flow_table, .destroy_flow_table = mlx5_cmd_destroy_flow_table, @@ -923,6 +982,8 @@ static const struct mlx5_flow_cmds mlx5_flow_cmds = { .packet_reformat_dealloc = mlx5_cmd_packet_reformat_dealloc, .modify_header_alloc = mlx5_cmd_modify_header_alloc, .modify_header_dealloc = mlx5_cmd_modify_header_dealloc, + .create_match_definer = mlx5_cmd_create_match_definer, + .destroy_match_definer = mlx5_cmd_destroy_match_definer, .set_peer = mlx5_cmd_stub_set_peer, .create_ns = mlx5_cmd_stub_create_ns, .destroy_ns = mlx5_cmd_stub_destroy_ns, @@ -942,6 +1003,8 @@ static const struct mlx5_flow_cmds mlx5_flow_cmd_stubs = { .packet_reformat_dealloc = mlx5_cmd_stub_packet_reformat_dealloc, .modify_header_alloc = mlx5_cmd_stub_modify_header_alloc, .modify_header_dealloc = mlx5_cmd_stub_modify_header_dealloc, + .create_match_definer = mlx5_cmd_stub_create_match_definer, + .destroy_match_definer = mlx5_cmd_stub_destroy_match_definer, .set_peer = mlx5_cmd_stub_set_peer, .create_ns = mlx5_cmd_stub_create_ns, .destroy_ns = mlx5_cmd_stub_destroy_ns, @@ -969,6 +1032,7 @@ const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type typ case FS_FT_NIC_TX: case FS_FT_RDMA_RX: case FS_FT_RDMA_TX: + case FS_FT_PORT_SEL: return mlx5_fs_cmd_get_fw_cmds(); default: return mlx5_fs_cmd_get_stub_cmds(); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index 5ecd33cdc087..220ec632d35a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -97,6 +97,10 @@ struct mlx5_flow_cmds { int (*create_ns)(struct mlx5_flow_root_namespace *ns); int (*destroy_ns)(struct mlx5_flow_root_namespace *ns); + int (*create_match_definer)(struct mlx5_flow_root_namespace *ns, + u16 format_id, u32 *match_mask); + int (*destroy_match_definer)(struct mlx5_flow_root_namespace *ns, + int definer_id); }; int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index fe501ba88bea..386ab9a2d490 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -99,6 +99,9 @@ #define LEFTOVERS_NUM_LEVELS 1 #define LEFTOVERS_NUM_PRIOS 1 +#define RDMA_RX_COUNTERS_PRIO_NUM_LEVELS 1 +#define RDMA_TX_COUNTERS_PRIO_NUM_LEVELS 1 + #define BY_PASS_PRIO_NUM_LEVELS 1 #define BY_PASS_MIN_LEVEL (ETHTOOL_MIN_LEVEL + MLX5_BY_PASS_NUM_PRIOS +\ LEFTOVERS_NUM_PRIOS) @@ -206,34 +209,63 @@ static struct init_tree_node egress_root_fs = { } }; -#define RDMA_RX_BYPASS_PRIO 0 -#define RDMA_RX_KERNEL_PRIO 1 +enum { + RDMA_RX_COUNTERS_PRIO, + RDMA_RX_BYPASS_PRIO, + RDMA_RX_KERNEL_PRIO, +}; + +#define RDMA_RX_BYPASS_MIN_LEVEL MLX5_BY_PASS_NUM_REGULAR_PRIOS +#define RDMA_RX_KERNEL_MIN_LEVEL (RDMA_RX_BYPASS_MIN_LEVEL + 1) +#define RDMA_RX_COUNTERS_MIN_LEVEL (RDMA_RX_KERNEL_MIN_LEVEL + 2) + static struct init_tree_node rdma_rx_root_fs = { .type = FS_TYPE_NAMESPACE, - .ar_size = 2, + .ar_size = 3, .children = (struct init_tree_node[]) { + [RDMA_RX_COUNTERS_PRIO] = + ADD_PRIO(0, RDMA_RX_COUNTERS_MIN_LEVEL, 0, + FS_CHAINING_CAPS, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(MLX5_RDMA_RX_NUM_COUNTERS_PRIOS, + RDMA_RX_COUNTERS_PRIO_NUM_LEVELS))), [RDMA_RX_BYPASS_PRIO] = - ADD_PRIO(0, MLX5_BY_PASS_NUM_REGULAR_PRIOS, 0, + ADD_PRIO(0, RDMA_RX_BYPASS_MIN_LEVEL, 0, FS_CHAINING_CAPS, ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, ADD_MULTIPLE_PRIO(MLX5_BY_PASS_NUM_REGULAR_PRIOS, BY_PASS_PRIO_NUM_LEVELS))), [RDMA_RX_KERNEL_PRIO] = - ADD_PRIO(0, MLX5_BY_PASS_NUM_REGULAR_PRIOS + 1, 0, + ADD_PRIO(0, RDMA_RX_KERNEL_MIN_LEVEL, 0, FS_CHAINING_CAPS, ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_SWITCH_DOMAIN, ADD_MULTIPLE_PRIO(1, 1))), } }; +enum { + RDMA_TX_COUNTERS_PRIO, + RDMA_TX_BYPASS_PRIO, +}; + +#define RDMA_TX_BYPASS_MIN_LEVEL MLX5_BY_PASS_NUM_PRIOS +#define RDMA_TX_COUNTERS_MIN_LEVEL (RDMA_TX_BYPASS_MIN_LEVEL + 1) + static struct init_tree_node rdma_tx_root_fs = { .type = FS_TYPE_NAMESPACE, - .ar_size = 1, + .ar_size = 2, .children = (struct init_tree_node[]) { - ADD_PRIO(0, MLX5_BY_PASS_NUM_PRIOS, 0, + [RDMA_TX_COUNTERS_PRIO] = + ADD_PRIO(0, RDMA_TX_COUNTERS_MIN_LEVEL, 0, + FS_CHAINING_CAPS, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(MLX5_RDMA_TX_NUM_COUNTERS_PRIOS, + RDMA_TX_COUNTERS_PRIO_NUM_LEVELS))), + [RDMA_TX_BYPASS_PRIO] = + ADD_PRIO(0, RDMA_TX_BYPASS_MIN_LEVEL, 0, FS_CHAINING_CAPS_RDMA_TX, ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, - ADD_MULTIPLE_PRIO(MLX5_BY_PASS_NUM_PRIOS, + ADD_MULTIPLE_PRIO(RDMA_TX_BYPASS_MIN_LEVEL, BY_PASS_PRIO_NUM_LEVELS))), } }; @@ -2191,6 +2223,10 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, if (steering->fdb_root_ns) return &steering->fdb_root_ns->ns; return NULL; + case MLX5_FLOW_NAMESPACE_PORT_SEL: + if (steering->port_sel_root_ns) + return &steering->port_sel_root_ns->ns; + return NULL; case MLX5_FLOW_NAMESPACE_SNIFFER_RX: if (steering->sniffer_rx_root_ns) return &steering->sniffer_rx_root_ns->ns; @@ -2215,6 +2251,12 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, prio = RDMA_RX_KERNEL_PRIO; } else if (type == MLX5_FLOW_NAMESPACE_RDMA_TX) { root_ns = steering->rdma_tx_root_ns; + } else if (type == MLX5_FLOW_NAMESPACE_RDMA_RX_COUNTERS) { + root_ns = steering->rdma_rx_root_ns; + prio = RDMA_RX_COUNTERS_PRIO; + } else if (type == MLX5_FLOW_NAMESPACE_RDMA_TX_COUNTERS) { + root_ns = steering->rdma_tx_root_ns; + prio = RDMA_TX_COUNTERS_PRIO; } else { /* Must be NIC RX */ root_ns = steering->root_ns; prio = type; @@ -2596,6 +2638,7 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev) steering->fdb_root_ns = NULL; kfree(steering->fdb_sub_ns); steering->fdb_sub_ns = NULL; + cleanup_root_ns(steering->port_sel_root_ns); cleanup_root_ns(steering->sniffer_rx_root_ns); cleanup_root_ns(steering->sniffer_tx_root_ns); cleanup_root_ns(steering->rdma_rx_root_ns); @@ -2634,6 +2677,21 @@ static int init_sniffer_rx_root_ns(struct mlx5_flow_steering *steering) return PTR_ERR_OR_ZERO(prio); } +#define PORT_SEL_NUM_LEVELS 3 +static int init_port_sel_root_ns(struct mlx5_flow_steering *steering) +{ + struct fs_prio *prio; + + steering->port_sel_root_ns = create_root_ns(steering, FS_FT_PORT_SEL); + if (!steering->port_sel_root_ns) + return -ENOMEM; + + /* Create single prio */ + prio = fs_create_prio(&steering->port_sel_root_ns->ns, 0, + PORT_SEL_NUM_LEVELS); + return PTR_ERR_OR_ZERO(prio); +} + static int init_rdma_rx_root_ns(struct mlx5_flow_steering *steering) { int err; @@ -3020,6 +3078,12 @@ int mlx5_init_fs(struct mlx5_core_dev *dev) goto err; } + if (MLX5_CAP_FLOWTABLE_PORT_SELECTION(dev, ft_support)) { + err = init_port_sel_root_ns(steering); + if (err) + goto err; + } + if (MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support) && MLX5_CAP_FLOWTABLE_RDMA_RX(dev, table_miss_action_domain)) { err = init_rdma_rx_root_ns(steering); @@ -3224,6 +3288,52 @@ void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, } EXPORT_SYMBOL(mlx5_packet_reformat_dealloc); +int mlx5_get_match_definer_id(struct mlx5_flow_definer *definer) +{ + return definer->id; +} + +struct mlx5_flow_definer * +mlx5_create_match_definer(struct mlx5_core_dev *dev, + enum mlx5_flow_namespace_type ns_type, u16 format_id, + u32 *match_mask) +{ + struct mlx5_flow_root_namespace *root; + struct mlx5_flow_definer *definer; + int id; + + root = get_root_namespace(dev, ns_type); + if (!root) + return ERR_PTR(-EOPNOTSUPP); + + definer = kzalloc(sizeof(*definer), GFP_KERNEL); + if (!definer) + return ERR_PTR(-ENOMEM); + + definer->ns_type = ns_type; + id = root->cmds->create_match_definer(root, format_id, match_mask); + if (id < 0) { + mlx5_core_warn(root->dev, "Failed to create match definer (%d)\n", id); + kfree(definer); + return ERR_PTR(id); + } + definer->id = id; + return definer; +} + +void mlx5_destroy_match_definer(struct mlx5_core_dev *dev, + struct mlx5_flow_definer *definer) +{ + struct mlx5_flow_root_namespace *root; + + root = get_root_namespace(dev, definer->ns_type); + if (WARN_ON(!root)) + return; + + root->cmds->destroy_match_definer(root, definer->id); + kfree(definer); +} + int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_root_namespace *peer_ns) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 98240badc342..7711db245c63 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -49,6 +49,11 @@ #define FDB_TC_MAX_PRIO 16 #define FDB_TC_LEVELS_PER_PRIO 2 +struct mlx5_flow_definer { + enum mlx5_flow_namespace_type ns_type; + u32 id; +}; + struct mlx5_modify_hdr { enum mlx5_flow_namespace_type ns_type; union { @@ -97,7 +102,8 @@ enum fs_flow_table_type { FS_FT_SNIFFER_TX = 0X6, FS_FT_RDMA_RX = 0X7, FS_FT_RDMA_TX = 0X8, - FS_FT_MAX_TYPE = FS_FT_RDMA_TX, + FS_FT_PORT_SEL = 0X9, + FS_FT_MAX_TYPE = FS_FT_PORT_SEL, }; enum fs_flow_table_op_mod { @@ -129,6 +135,7 @@ struct mlx5_flow_steering { struct mlx5_flow_root_namespace *rdma_rx_root_ns; struct mlx5_flow_root_namespace *rdma_tx_root_ns; struct mlx5_flow_root_namespace *egress_root_ns; + struct mlx5_flow_root_namespace *port_sel_root_ns; int esw_egress_acl_vports; int esw_ingress_acl_vports; }; @@ -341,7 +348,8 @@ struct mlx5_flow_root_namespace *find_root(struct fs_node *node); (type == FS_FT_SNIFFER_TX) ? MLX5_CAP_FLOWTABLE_SNIFFER_TX(mdev, cap) : \ (type == FS_FT_RDMA_RX) ? MLX5_CAP_FLOWTABLE_RDMA_RX(mdev, cap) : \ (type == FS_FT_RDMA_TX) ? MLX5_CAP_FLOWTABLE_RDMA_TX(mdev, cap) : \ - (BUILD_BUG_ON_ZERO(FS_FT_RDMA_TX != FS_FT_MAX_TYPE))\ + (type == FS_FT_PORT_SEL) ? MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) : \ + (BUILD_BUG_ON_ZERO(FS_FT_PORT_SEL != FS_FT_MAX_TYPE))\ ) #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index 18e5aec14641..31c99d53faf7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -40,6 +40,7 @@ #define MLX5_FC_STATS_PERIOD msecs_to_jiffies(1000) /* Max number of counters to query in bulk read is 32K */ #define MLX5_SW_MAX_COUNTERS_BULK BIT(15) +#define MLX5_SF_NUM_COUNTERS_BULK 6 #define MLX5_FC_POOL_MAX_THRESHOLD BIT(18) #define MLX5_FC_POOL_USED_BUFF_RATIO 10 @@ -146,8 +147,12 @@ static void mlx5_fc_stats_remove(struct mlx5_core_dev *dev, static int get_max_bulk_query_len(struct mlx5_core_dev *dev) { - return min_t(int, MLX5_SW_MAX_COUNTERS_BULK, - (1 << MLX5_CAP_GEN(dev, log_max_flow_counter_bulk))); + int num_counters_bulk = mlx5_core_is_sf(dev) ? + MLX5_SF_NUM_COUNTERS_BULK : + MLX5_SW_MAX_COUNTERS_BULK; + + return min_t(int, num_counters_bulk, + (1 << MLX5_CAP_GEN(dev, log_max_flow_counter_bulk))); } static void update_counter_cache(int index, u32 *bulk_raw_data, @@ -296,7 +301,7 @@ static struct mlx5_fc *mlx5_fc_acquire(struct mlx5_core_dev *dev, bool aging) return mlx5_fc_single_alloc(dev); } -struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) +struct mlx5_fc *mlx5_fc_create_ex(struct mlx5_core_dev *dev, bool aging) { struct mlx5_fc *counter = mlx5_fc_acquire(dev, aging); struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; @@ -327,8 +332,6 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) goto err_out_alloc; llist_add(&counter->addlist, &fc_stats->addlist); - - mod_delayed_work(fc_stats->wq, &fc_stats->work, 0); } return counter; @@ -337,6 +340,16 @@ err_out_alloc: mlx5_fc_release(dev, counter); return ERR_PTR(err); } + +struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) +{ + struct mlx5_fc *counter = mlx5_fc_create_ex(dev, aging); + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + + if (aging) + mod_delayed_work(fc_stats->wq, &fc_stats->work, 0); + return counter; +} EXPORT_SYMBOL(mlx5_fc_create); u32 mlx5_fc_id(struct mlx5_fc *counter) @@ -497,8 +510,7 @@ 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/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index 016d26f809a5..2d8406fab844 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -35,6 +35,7 @@ #include <linux/module.h> #include "mlx5_core.h" #include "../../mlxfw/mlxfw.h" +#include "lib/tout.h" #include "accel/tls.h" enum { @@ -148,6 +149,12 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) if (err) return err; + if (MLX5_CAP_GEN(dev, port_selection_cap)) { + err = mlx5_core_get_caps(dev, MLX5_CAP_PORT_SELECTION); + if (err) + return err; + } + if (MLX5_CAP_GEN(dev, hca_cap_2)) { err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL_2); if (err) @@ -262,6 +269,12 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) return err; } + if (MLX5_CAP_GEN(dev, shampo)) { + err = mlx5_core_get_caps(dev, MLX5_CAP_DEV_SHAMPO); + if (err) + return err; + } + return 0; } @@ -317,10 +330,9 @@ int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev) return 0; } -#define MLX5_FAST_TEARDOWN_WAIT_MS 3000 int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev) { - unsigned long end, delay_ms = MLX5_FAST_TEARDOWN_WAIT_MS; + unsigned long end, delay_ms = mlx5_tout_ms(dev, TEARDOWN); u32 out[MLX5_ST_SZ_DW(teardown_hca_out)] = {}; u32 in[MLX5_ST_SZ_DW(teardown_hca_in)] = {}; int state; @@ -618,17 +630,18 @@ static void mlx5_fsm_release(struct mlxfw_dev *mlxfw_dev, u32 fwhandle) fwhandle, 0); } -#define MLX5_FSM_REACTIVATE_TOUT 5000 /* msecs */ static int mlx5_fsm_reactivate(struct mlxfw_dev *mlxfw_dev, u8 *status) { - unsigned long exp_time = jiffies + msecs_to_jiffies(MLX5_FSM_REACTIVATE_TOUT); struct mlx5_mlxfw_dev *mlx5_mlxfw_dev = container_of(mlxfw_dev, struct mlx5_mlxfw_dev, mlxfw_dev); struct mlx5_core_dev *dev = mlx5_mlxfw_dev->mlx5_core_dev; u32 out[MLX5_ST_SZ_DW(mirc_reg)]; u32 in[MLX5_ST_SZ_DW(mirc_reg)]; + unsigned long exp_time; int err; + exp_time = jiffies + msecs_to_jiffies(mlx5_tout_ms(dev, FSM_REACTIVATE)); + if (!MLX5_CAP_MCAM_REG2(dev, mirc)) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index 106b50e42b46..0b0234f9d694 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -3,6 +3,7 @@ #include "fw_reset.h" #include "diag/fw_tracer.h" +#include "lib/tout.h" enum { MLX5_FW_RESET_FLAGS_RESET_REQUESTED, @@ -228,8 +229,6 @@ static void mlx5_sync_reset_request_event(struct work_struct *work) mlx5_core_warn(dev, "PCI Sync FW Update Reset Ack. Device reset is expected.\n"); } -#define MLX5_PCI_LINK_UP_TIMEOUT 2000 - static int mlx5_pci_link_toggle(struct mlx5_core_dev *dev) { struct pci_bus *bridge_bus = dev->pdev->bus; @@ -286,7 +285,7 @@ static int mlx5_pci_link_toggle(struct mlx5_core_dev *dev) goto restore; } - timeout = jiffies + msecs_to_jiffies(MLX5_PCI_LINK_UP_TIMEOUT); + timeout = jiffies + msecs_to_jiffies(mlx5_tout_ms(dev, PCI_TOGGLE)); do { err = pci_read_config_word(bridge, cap + PCI_EXP_LNKSTA, ®16); if (err) @@ -299,8 +298,8 @@ static int mlx5_pci_link_toggle(struct mlx5_core_dev *dev) if (reg16 & PCI_EXP_LNKSTA_DLLLA) { mlx5_core_info(dev, "PCI Link up\n"); } else { - mlx5_core_err(dev, "PCI link not ready (0x%04x) after %d ms\n", - reg16, MLX5_PCI_LINK_UP_TIMEOUT); + mlx5_core_err(dev, "PCI link not ready (0x%04x) after %llu ms\n", + reg16, mlx5_tout_ms(dev, PCI_TOGGLE)); err = -ETIMEDOUT; } @@ -395,16 +394,16 @@ static int fw_reset_event_notifier(struct notifier_block *nb, unsigned long acti return NOTIFY_OK; } -#define MLX5_FW_RESET_TIMEOUT_MSEC 5000 int mlx5_fw_reset_wait_reset_done(struct mlx5_core_dev *dev) { - unsigned long timeout = msecs_to_jiffies(MLX5_FW_RESET_TIMEOUT_MSEC); + unsigned long pci_sync_update_timeout = mlx5_tout_ms(dev, PCI_SYNC_UPDATE); + unsigned long timeout = msecs_to_jiffies(pci_sync_update_timeout); struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; int err; if (!wait_for_completion_timeout(&fw_reset->done, timeout)) { - mlx5_core_warn(dev, "FW sync reset timeout after %d seconds\n", - MLX5_FW_RESET_TIMEOUT_MSEC / 1000); + mlx5_core_warn(dev, "FW sync reset timeout after %lu seconds\n", + pci_sync_update_timeout / 1000); err = -ETIMEDOUT; goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 037e18dd4be0..64f1abc4dc36 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -36,14 +36,15 @@ #include <linux/vmalloc.h> #include <linux/hardirq.h> #include <linux/mlx5/driver.h> +#include <linux/kern_levels.h> #include "mlx5_core.h" #include "lib/eq.h" #include "lib/mlx5.h" #include "lib/pci_vsc.h" +#include "lib/tout.h" #include "diag/fw_tracer.h" enum { - MLX5_HEALTH_POLL_INTERVAL = 2 * HZ, MAX_MISSES = 3, }; @@ -74,6 +75,11 @@ enum { MLX5_SENSOR_FW_SYND_RFR = 5, }; +enum { + MLX5_SEVERITY_MASK = 0x7, + MLX5_SEVERITY_VALID_MASK = 0x8, +}; + u8 mlx5_get_nic_state(struct mlx5_core_dev *dev) { return (ioread32be(&dev->iseg->cmdq_addr_l_sz) >> 8) & 7; @@ -98,12 +104,19 @@ static bool sensor_pci_not_working(struct mlx5_core_dev *dev) return (ioread32be(&h->fw_ver) == 0xffffffff); } +static int mlx5_health_get_rfr(u8 rfr_severity) +{ + return rfr_severity >> MLX5_RFR_BIT_OFFSET; +} + static bool sensor_fw_synd_rfr(struct mlx5_core_dev *dev) { struct mlx5_core_health *health = &dev->priv.health; struct health_buffer __iomem *h = health->health; - u32 rfr = ioread32be(&h->rfr) >> MLX5_RFR_OFFSET; u8 synd = ioread8(&h->synd); + u8 rfr; + + rfr = mlx5_health_get_rfr(ioread8(&h->rfr_severity)); if (rfr && synd) mlx5_core_dbg(dev, "FW requests reset, synd: %d\n", synd); @@ -219,11 +232,9 @@ unlock: mutex_unlock(&dev->intf_state_mutex); } -#define MLX5_CRDUMP_WAIT_MS 60000 -#define MLX5_FW_RESET_WAIT_MS 1000 void mlx5_error_sw_reset(struct mlx5_core_dev *dev) { - unsigned long end, delay_ms = MLX5_FW_RESET_WAIT_MS; + unsigned long end, delay_ms = mlx5_tout_ms(dev, PCI_TOGGLE); int lock = -EBUSY; mutex_lock(&dev->intf_state_mutex); @@ -237,7 +248,7 @@ void mlx5_error_sw_reset(struct mlx5_core_dev *dev) lock = lock_sem_sw_reset(dev, true); if (lock == -EBUSY) { - delay_ms = MLX5_CRDUMP_WAIT_MS; + delay_ms = mlx5_tout_ms(dev, FULL_CRDUMP); goto recover_from_sw_reset; } /* Execute SW reset */ @@ -307,13 +318,11 @@ static void mlx5_handle_bad_state(struct mlx5_core_dev *dev) mlx5_disable_device(dev); } -/* How much time to wait until health resetting the driver (in msecs) */ -#define MLX5_RECOVERY_WAIT_MSECS 60000 int mlx5_health_wait_pci_up(struct mlx5_core_dev *dev) { unsigned long end; - end = jiffies + msecs_to_jiffies(MLX5_RECOVERY_WAIT_MSECS); + end = jiffies + msecs_to_jiffies(mlx5_tout_ms(dev, FW_RESET)); while (sensor_pci_not_working(dev)) { if (time_after(jiffies, end)) return -ETIMEDOUT; @@ -370,35 +379,69 @@ static const char *hsynd_str(u8 synd) } } +static const char *mlx5_loglevel_str(int level) +{ + switch (level) { + case LOGLEVEL_EMERG: + return "EMERGENCY"; + case LOGLEVEL_ALERT: + return "ALERT"; + case LOGLEVEL_CRIT: + return "CRITICAL"; + case LOGLEVEL_ERR: + return "ERROR"; + case LOGLEVEL_WARNING: + return "WARNING"; + case LOGLEVEL_NOTICE: + return "NOTICE"; + case LOGLEVEL_INFO: + return "INFO"; + case LOGLEVEL_DEBUG: + return "DEBUG"; + } + return "Unknown log level"; +} + +static int mlx5_health_get_severity(u8 rfr_severity) +{ + return rfr_severity & MLX5_SEVERITY_VALID_MASK ? + rfr_severity & MLX5_SEVERITY_MASK : LOGLEVEL_ERR; +} + static void print_health_info(struct mlx5_core_dev *dev) { struct mlx5_core_health *health = &dev->priv.health; struct health_buffer __iomem *h = health->health; - char fw_str[18]; - u32 fw; + u8 rfr_severity; + int severity; int i; /* If the syndrome is 0, the device is OK and no need to print buffer */ if (!ioread8(&h->synd)) return; + rfr_severity = ioread8(&h->rfr_severity); + severity = mlx5_health_get_severity(rfr_severity); + mlx5_log(dev, severity, "Health issue observed, %s, severity(%d) %s:\n", + hsynd_str(ioread8(&h->synd)), severity, mlx5_loglevel_str(severity)); + for (i = 0; i < ARRAY_SIZE(h->assert_var); i++) - mlx5_core_err(dev, "assert_var[%d] 0x%08x\n", i, - ioread32be(h->assert_var + i)); - - mlx5_core_err(dev, "assert_exit_ptr 0x%08x\n", - ioread32be(&h->assert_exit_ptr)); - mlx5_core_err(dev, "assert_callra 0x%08x\n", - ioread32be(&h->assert_callra)); - sprintf(fw_str, "%d.%d.%d", fw_rev_maj(dev), fw_rev_min(dev), fw_rev_sub(dev)); - mlx5_core_err(dev, "fw_ver %s\n", fw_str); - mlx5_core_err(dev, "hw_id 0x%08x\n", ioread32be(&h->hw_id)); - mlx5_core_err(dev, "irisc_index %d\n", ioread8(&h->irisc_index)); - mlx5_core_err(dev, "synd 0x%x: %s\n", ioread8(&h->synd), - hsynd_str(ioread8(&h->synd))); - mlx5_core_err(dev, "ext_synd 0x%04x\n", ioread16be(&h->ext_synd)); - fw = ioread32be(&h->fw_ver); - mlx5_core_err(dev, "raw fw_ver 0x%08x\n", fw); + mlx5_log(dev, severity, "assert_var[%d] 0x%08x\n", i, + ioread32be(h->assert_var + i)); + + mlx5_log(dev, severity, "assert_exit_ptr 0x%08x\n", ioread32be(&h->assert_exit_ptr)); + mlx5_log(dev, severity, "assert_callra 0x%08x\n", ioread32be(&h->assert_callra)); + mlx5_log(dev, severity, "fw_ver %d.%d.%d", fw_rev_maj(dev), fw_rev_min(dev), + fw_rev_sub(dev)); + mlx5_log(dev, severity, "time %u\n", ioread32be(&h->time)); + mlx5_log(dev, severity, "hw_id 0x%08x\n", ioread32be(&h->hw_id)); + mlx5_log(dev, severity, "rfr %d\n", mlx5_health_get_rfr(rfr_severity)); + mlx5_log(dev, severity, "severity %d (%s)\n", severity, mlx5_loglevel_str(severity)); + mlx5_log(dev, severity, "irisc_index %d\n", ioread8(&h->irisc_index)); + mlx5_log(dev, severity, "synd 0x%x: %s\n", ioread8(&h->synd), + hsynd_str(ioread8(&h->synd))); + mlx5_log(dev, severity, "ext_synd 0x%04x\n", ioread16be(&h->ext_synd)); + mlx5_log(dev, severity, "raw fw_ver 0x%08x\n", ioread32be(&h->fw_ver)); } static int @@ -447,6 +490,7 @@ mlx5_fw_reporter_heath_buffer_data_put(struct mlx5_core_dev *dev, { struct mlx5_core_health *health = &dev->priv.health; struct health_buffer __iomem *h = health->health; + u8 rfr_severity; int err; int i; @@ -479,9 +523,19 @@ mlx5_fw_reporter_heath_buffer_data_put(struct mlx5_core_dev *dev, ioread32be(&h->assert_callra)); if (err) return err; + err = devlink_fmsg_u32_pair_put(fmsg, "time", ioread32be(&h->time)); + if (err) + return err; err = devlink_fmsg_u32_pair_put(fmsg, "hw_id", ioread32be(&h->hw_id)); if (err) return err; + rfr_severity = ioread8(&h->rfr_severity); + err = devlink_fmsg_u8_pair_put(fmsg, "rfr", mlx5_health_get_rfr(rfr_severity)); + if (err) + return err; + err = devlink_fmsg_u8_pair_put(fmsg, "severity", mlx5_health_get_severity(rfr_severity)); + if (err) + return err; err = devlink_fmsg_u8_pair_put(fmsg, "irisc_index", ioread8(&h->irisc_index)); if (err) @@ -674,13 +728,13 @@ static void mlx5_fw_reporters_destroy(struct mlx5_core_dev *dev) devlink_health_reporter_destroy(health->fw_fatal_reporter); } -static unsigned long get_next_poll_jiffies(void) +static unsigned long get_next_poll_jiffies(struct mlx5_core_dev *dev) { unsigned long next; get_random_bytes(&next, sizeof(next)); next %= HZ; - next += jiffies + MLX5_HEALTH_POLL_INTERVAL; + next += jiffies + msecs_to_jiffies(mlx5_tout_ms(dev, HEALTH_POLL_INTERVAL)); return next; } @@ -698,6 +752,31 @@ void mlx5_trigger_health_work(struct mlx5_core_dev *dev) spin_unlock_irqrestore(&health->wq_lock, flags); } +#define MLX5_MSEC_PER_HOUR (MSEC_PER_SEC * 60 * 60) +static void mlx5_health_log_ts_update(struct work_struct *work) +{ + struct delayed_work *dwork = to_delayed_work(work); + u32 out[MLX5_ST_SZ_DW(mrtc_reg)] = {}; + u32 in[MLX5_ST_SZ_DW(mrtc_reg)] = {}; + struct mlx5_core_health *health; + struct mlx5_core_dev *dev; + struct mlx5_priv *priv; + u64 now_us; + + health = container_of(dwork, struct mlx5_core_health, update_fw_log_ts_work); + priv = container_of(health, struct mlx5_priv, health); + dev = container_of(priv, struct mlx5_core_dev, priv); + + now_us = ktime_to_us(ktime_get_real()); + + MLX5_SET(mrtc_reg, in, time_h, now_us >> 32); + MLX5_SET(mrtc_reg, in, time_l, now_us & 0xFFFFFFFF); + mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out), MLX5_REG_MRTC, 0, 1); + + queue_delayed_work(health->wq, &health->update_fw_log_ts_work, + msecs_to_jiffies(MLX5_MSEC_PER_HOUR)); +} + static void poll_health(struct timer_list *t) { struct mlx5_core_dev *dev = from_timer(dev, t, priv.health.timer); @@ -740,11 +819,12 @@ static void poll_health(struct timer_list *t) queue_work(health->wq, &health->report_work); out: - mod_timer(&health->timer, get_next_poll_jiffies()); + mod_timer(&health->timer, get_next_poll_jiffies(dev)); } void mlx5_start_health_poll(struct mlx5_core_dev *dev) { + u64 poll_interval_ms = mlx5_tout_ms(dev, HEALTH_POLL_INTERVAL); struct mlx5_core_health *health = &dev->priv.health; timer_setup(&health->timer, poll_health, 0); @@ -753,7 +833,7 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev) health->health = &dev->iseg->health; health->health_counter = &dev->iseg->health_counter; - health->timer.expires = round_jiffies(jiffies + MLX5_HEALTH_POLL_INTERVAL); + health->timer.expires = jiffies + msecs_to_jiffies(poll_interval_ms); add_timer(&health->timer); } @@ -779,6 +859,7 @@ void mlx5_drain_health_wq(struct mlx5_core_dev *dev) spin_lock_irqsave(&health->wq_lock, flags); set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags); spin_unlock_irqrestore(&health->wq_lock, flags); + cancel_delayed_work_sync(&health->update_fw_log_ts_work); cancel_work_sync(&health->report_work); cancel_work_sync(&health->fatal_report_work); } @@ -794,6 +875,7 @@ void mlx5_health_cleanup(struct mlx5_core_dev *dev) { struct mlx5_core_health *health = &dev->priv.health; + cancel_delayed_work_sync(&health->update_fw_log_ts_work); destroy_workqueue(health->wq); mlx5_fw_reporters_destroy(dev); } @@ -819,6 +901,9 @@ int mlx5_health_init(struct mlx5_core_dev *dev) spin_lock_init(&health->wq_lock); INIT_WORK(&health->fatal_report_work, mlx5_fw_fatal_reporter_err_work); INIT_WORK(&health->report_work, mlx5_fw_reporter_err_work); + INIT_DELAYED_WORK(&health->update_fw_log_ts_work, mlx5_health_log_ts_update); + if (mlx5_core_is_pf(dev)) + queue_delayed_work(health->wq, &health->update_fw_log_ts_work, 0); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index 0c8594c7df21..962d41418ce7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -217,6 +217,32 @@ static int mlx5i_get_link_ksettings(struct net_device *netdev, return 0; } +#ifdef CONFIG_MLX5_EN_RXNFC +static u32 mlx5i_flow_type_mask(u32 flow_type) +{ + return flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS); +} + +static int mlx5i_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) +{ + struct mlx5e_priv *priv = mlx5i_epriv(dev); + struct ethtool_rx_flow_spec *fs = &cmd->fs; + + if (mlx5i_flow_type_mask(fs->flow_type) == ETHER_FLOW) + return -EINVAL; + + return mlx5e_ethtool_set_rxnfc(priv, cmd); +} + +static int mlx5i_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, + u32 *rule_locs) +{ + struct mlx5e_priv *priv = mlx5i_epriv(dev); + + return mlx5e_ethtool_get_rxnfc(priv, info, rule_locs); +} +#endif + const struct ethtool_ops mlx5i_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_MAX_FRAMES | @@ -233,6 +259,10 @@ const struct ethtool_ops mlx5i_ethtool_ops = { .get_coalesce = mlx5i_get_coalesce, .set_coalesce = mlx5i_set_coalesce, .get_ts_info = mlx5i_get_ts_info, +#ifdef CONFIG_MLX5_EN_RXNFC + .get_rxnfc = mlx5i_get_rxnfc, + .set_rxnfc = mlx5i_set_rxnfc, +#endif .get_link_ksettings = mlx5i_get_link_ksettings, .get_link = ethtool_op_get_link, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 67571e5040d6..ea1efdecc88c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -67,7 +67,7 @@ static void mlx5i_build_nic_params(struct mlx5_core_dev *mdev, MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE : MLX5I_PARAMS_DEFAULT_LOG_RQ_SIZE; - params->lro_en = false; + params->packet_merge.type = MLX5E_PACKET_MERGE_NONE; params->hard_mtu = MLX5_IB_GRH_BYTES + MLX5_IPOIB_HARD_LEN; params->tunneled_offload_en = false; } @@ -113,7 +113,7 @@ static void mlx5i_grp_sw_update_stats(struct mlx5e_priv *priv) struct mlx5e_sw_stats s = { 0 }; int i, j; - for (i = 0; i < priv->max_nch; i++) { + for (i = 0; i < priv->stats_nch; i++) { struct mlx5e_channel_stats *channel_stats; struct mlx5e_rq_stats *rq_stats; @@ -219,7 +219,7 @@ void mlx5i_uninit_underlay_qp(struct mlx5e_priv *priv) int mlx5i_create_underlay_qp(struct mlx5e_priv *priv) { - unsigned char *dev_addr = priv->netdev->dev_addr; + const unsigned char *dev_addr = priv->netdev->dev_addr; u32 out[MLX5_ST_SZ_DW(create_qp_out)] = {}; u32 in[MLX5_ST_SZ_DW(create_qp_in)] = {}; struct mlx5i_priv *ipriv = priv->ppriv; @@ -336,6 +336,8 @@ static int mlx5i_create_flow_steering(struct mlx5e_priv *priv) goto err_destroy_arfs_tables; } + mlx5e_ethtool_init_steering(priv); + return 0; err_destroy_arfs_tables: @@ -348,12 +350,12 @@ static void mlx5i_destroy_flow_steering(struct mlx5e_priv *priv) { mlx5e_destroy_ttc_table(priv); mlx5e_arfs_destroy_tables(priv); + mlx5e_ethtool_cleanup_steering(priv); } static int mlx5i_init_rx(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; - struct mlx5e_lro_param lro_param; int err; priv->rx_res = mlx5e_rx_res_alloc(); @@ -368,9 +370,9 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv) goto err_destroy_q_counters; } - lro_param = mlx5e_get_lro_param(&priv->channels.params); err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, 0, - priv->max_nch, priv->drop_rq.rqn, &lro_param, + priv->max_nch, priv->drop_rq.rqn, + &priv->channels.params.packet_merge, priv->channels.params.num_channels); if (err) goto err_close_drop_rq; @@ -472,11 +474,13 @@ int mlx5i_dev_init(struct net_device *dev) { struct mlx5e_priv *priv = mlx5i_epriv(dev); struct mlx5i_priv *ipriv = priv->ppriv; + u8 addr_mod[3]; /* Set dev address using underlay QP */ - dev->dev_addr[1] = (ipriv->qpn >> 16) & 0xff; - dev->dev_addr[2] = (ipriv->qpn >> 8) & 0xff; - dev->dev_addr[3] = (ipriv->qpn) & 0xff; + addr_mod[0] = (ipriv->qpn >> 16) & 0xff; + addr_mod[1] = (ipriv->qpn >> 8) & 0xff; + addr_mod[2] = (ipriv->qpn) & 0xff; + dev_addr_mod(dev, 1, addr_mod, sizeof(addr_mod)); /* Add QPN to net-device mapping to HT */ mlx5i_pkey_add_qpn(dev, ipriv->qpn); @@ -711,7 +715,7 @@ static int mlx5_rdma_setup_rn(struct ib_device *ibdev, u32 port_num, goto destroy_ht; } - err = mlx5e_priv_init(epriv, netdev, mdev); + err = mlx5e_priv_init(epriv, prof, netdev, mdev); if (err) goto destroy_mdev_resources; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index ca5690b0a7ab..48d2ea690d7a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -38,7 +38,7 @@ #include "mlx5_core.h" #include "eswitch.h" #include "lag.h" -#include "lag_mp.h" +#include "mp.h" /* General purpose, use for short periods of time. * Beware of lock dependencies (preferably, no locks should be acquired @@ -47,16 +47,21 @@ static DEFINE_SPINLOCK(lag_lock); static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, u8 remap_port1, - u8 remap_port2, bool shared_fdb) + u8 remap_port2, bool shared_fdb, u8 flags) { u32 in[MLX5_ST_SZ_DW(create_lag_in)] = {}; void *lag_ctx = MLX5_ADDR_OF(create_lag_in, in, ctx); MLX5_SET(create_lag_in, in, opcode, MLX5_CMD_OP_CREATE_LAG); - MLX5_SET(lagc, lag_ctx, tx_remap_affinity_1, remap_port1); - MLX5_SET(lagc, lag_ctx, tx_remap_affinity_2, remap_port2); MLX5_SET(lagc, lag_ctx, fdb_selection_mode, shared_fdb); + if (!(flags & MLX5_LAG_FLAG_HASH_BASED)) { + MLX5_SET(lagc, lag_ctx, tx_remap_affinity_1, remap_port1); + MLX5_SET(lagc, lag_ctx, tx_remap_affinity_2, remap_port2); + } else { + MLX5_SET(lagc, lag_ctx, port_select_mode, + MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_FT); + } return mlx5_cmd_exec_in(dev, create_lag, in); } @@ -199,6 +204,15 @@ static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker, *port1 = 2; } +static int _mlx5_modify_lag(struct mlx5_lag *ldev, u8 v2p_port1, u8 v2p_port2) +{ + struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; + + if (ldev->flags & MLX5_LAG_FLAG_HASH_BASED) + return mlx5_lag_port_sel_modify(ldev, v2p_port1, v2p_port2); + return mlx5_cmd_modify_lag(dev0, v2p_port1, v2p_port2); +} + void mlx5_modify_lag(struct mlx5_lag *ldev, struct lag_tracker *tracker) { @@ -211,39 +225,56 @@ void mlx5_modify_lag(struct mlx5_lag *ldev, if (v2p_port1 != ldev->v2p_map[MLX5_LAG_P1] || v2p_port2 != ldev->v2p_map[MLX5_LAG_P2]) { + err = _mlx5_modify_lag(ldev, v2p_port1, v2p_port2); + if (err) { + mlx5_core_err(dev0, + "Failed to modify LAG (%d)\n", + err); + return; + } ldev->v2p_map[MLX5_LAG_P1] = v2p_port1; ldev->v2p_map[MLX5_LAG_P2] = v2p_port2; - mlx5_core_info(dev0, "modify lag map port 1:%d port 2:%d", ldev->v2p_map[MLX5_LAG_P1], ldev->v2p_map[MLX5_LAG_P2]); - - err = mlx5_cmd_modify_lag(dev0, v2p_port1, v2p_port2); - if (err) - mlx5_core_err(dev0, - "Failed to modify LAG (%d)\n", - err); } } +static void mlx5_lag_set_port_sel_mode(struct mlx5_lag *ldev, + struct lag_tracker *tracker, u8 *flags) +{ + bool roce_lag = !!(*flags & MLX5_LAG_FLAG_ROCE); + struct lag_func *dev0 = &ldev->pf[MLX5_LAG_P1]; + + if (roce_lag || + !MLX5_CAP_PORT_SELECTION(dev0->dev, port_select_flow_table) || + tracker->tx_type != NETDEV_LAG_TX_TYPE_HASH) + return; + *flags |= MLX5_LAG_FLAG_HASH_BASED; +} + +static char *get_str_port_sel_mode(u8 flags) +{ + if (flags & MLX5_LAG_FLAG_HASH_BASED) + return "hash"; + return "queue_affinity"; +} + static int mlx5_create_lag(struct mlx5_lag *ldev, struct lag_tracker *tracker, - bool shared_fdb) + bool shared_fdb, u8 flags) { struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev; u32 in[MLX5_ST_SZ_DW(destroy_lag_in)] = {}; int err; - mlx5_infer_tx_affinity_mapping(tracker, &ldev->v2p_map[MLX5_LAG_P1], - &ldev->v2p_map[MLX5_LAG_P2]); - - mlx5_core_info(dev0, "lag map port 1:%d port 2:%d shared_fdb:%d", + mlx5_core_info(dev0, "lag map port 1:%d port 2:%d shared_fdb:%d mode:%s", ldev->v2p_map[MLX5_LAG_P1], ldev->v2p_map[MLX5_LAG_P2], - shared_fdb); + shared_fdb, get_str_port_sel_mode(flags)); err = mlx5_cmd_create_lag(dev0, ldev->v2p_map[MLX5_LAG_P1], - ldev->v2p_map[MLX5_LAG_P2], shared_fdb); + ldev->v2p_map[MLX5_LAG_P2], shared_fdb, flags); if (err) { mlx5_core_err(dev0, "Failed to create LAG (%d)\n", @@ -279,16 +310,32 @@ int mlx5_activate_lag(struct mlx5_lag *ldev, struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; int err; - err = mlx5_create_lag(ldev, tracker, shared_fdb); + mlx5_infer_tx_affinity_mapping(tracker, &ldev->v2p_map[MLX5_LAG_P1], + &ldev->v2p_map[MLX5_LAG_P2]); + mlx5_lag_set_port_sel_mode(ldev, tracker, &flags); + if (flags & MLX5_LAG_FLAG_HASH_BASED) { + err = mlx5_lag_port_sel_create(ldev, tracker->hash_type, + ldev->v2p_map[MLX5_LAG_P1], + ldev->v2p_map[MLX5_LAG_P2]); + if (err) { + mlx5_core_err(dev0, + "Failed to create LAG port selection(%d)\n", + err); + return err; + } + } + + err = mlx5_create_lag(ldev, tracker, shared_fdb, flags); if (err) { - if (roce_lag) { + if (flags & MLX5_LAG_FLAG_HASH_BASED) + mlx5_lag_port_sel_destroy(ldev); + if (roce_lag) mlx5_core_err(dev0, "Failed to activate RoCE LAG\n"); - } else { + else mlx5_core_err(dev0, "Failed to activate VF LAG\n" "Make sure all VFs are unbound prior to VF LAG activation or deactivation\n"); - } return err; } @@ -302,6 +349,7 @@ static int mlx5_deactivate_lag(struct mlx5_lag *ldev) struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; u32 in[MLX5_ST_SZ_DW(destroy_lag_in)] = {}; bool roce_lag = __mlx5_lag_is_roce(ldev); + u8 flags = ldev->flags; int err; ldev->flags &= ~MLX5_LAG_MODE_FLAGS; @@ -324,6 +372,8 @@ static int mlx5_deactivate_lag(struct mlx5_lag *ldev) "Failed to deactivate VF LAG; driver restart required\n" "Make sure all VFs are unbound prior to VF LAG activation or deactivation\n"); } + } else if (flags & MLX5_LAG_FLAG_HASH_BASED) { + mlx5_lag_port_sel_destroy(ldev); } return err; @@ -442,6 +492,10 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) if (!mlx5_lag_is_ready(ldev)) { do_bond = false; } else { + /* VF LAG is in multipath mode, ignore bond change requests */ + if (mlx5_lag_is_multipath(dev0)) + return; + tracker = ldev->tracker; do_bond = tracker.is_bonded && mlx5_lag_check_prereq(ldev); @@ -588,8 +642,10 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev, if (!(bond_status & 0x3)) return 0; - if (lag_upper_info) + if (lag_upper_info) { tracker->tx_type = lag_upper_info->tx_type; + tracker->hash_type = lag_upper_info->hash_type; + } /* Determine bonding status: * A device is considered bonded if both its physical ports are slaves @@ -688,7 +744,7 @@ static void mlx5_ldev_add_netdev(struct mlx5_lag *ldev, struct mlx5_core_dev *dev, struct net_device *netdev) { - unsigned int fn = PCI_FUNC(dev->pdev->devfn); + unsigned int fn = mlx5_get_dev_index(dev); if (fn >= MLX5_MAX_PORTS) return; @@ -718,7 +774,7 @@ static void mlx5_ldev_remove_netdev(struct mlx5_lag *ldev, static void mlx5_ldev_add_mdev(struct mlx5_lag *ldev, struct mlx5_core_dev *dev) { - unsigned int fn = PCI_FUNC(dev->pdev->devfn); + unsigned int fn = mlx5_get_dev_index(dev); if (fn >= MLX5_MAX_PORTS) return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h index d4bae528954e..e5d231c31b54 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h @@ -5,7 +5,8 @@ #define __MLX5_LAG_H__ #include "mlx5_core.h" -#include "lag_mp.h" +#include "mp.h" +#include "port_sel.h" enum { MLX5_LAG_P1, @@ -17,10 +18,12 @@ enum { MLX5_LAG_FLAG_SRIOV = 1 << 1, MLX5_LAG_FLAG_MULTIPATH = 1 << 2, MLX5_LAG_FLAG_READY = 1 << 3, + MLX5_LAG_FLAG_HASH_BASED = 1 << 4, }; #define MLX5_LAG_MODE_FLAGS (MLX5_LAG_FLAG_ROCE | MLX5_LAG_FLAG_SRIOV |\ - MLX5_LAG_FLAG_MULTIPATH) + MLX5_LAG_FLAG_MULTIPATH | \ + MLX5_LAG_FLAG_HASH_BASED) struct lag_func { struct mlx5_core_dev *dev; @@ -32,6 +35,7 @@ struct lag_tracker { enum netdev_lag_tx_type tx_type; struct netdev_lag_lower_state_info netdev_state[MLX5_MAX_PORTS]; unsigned int is_bonded:1; + enum netdev_lag_hash hash_type; }; /* LAG data of a ConnectX card. @@ -49,6 +53,7 @@ struct mlx5_lag { struct delayed_work bond_work; struct notifier_block nb; struct lag_mp lag_mp; + struct mlx5_lag_port_sel port_sel; }; static inline struct mlx5_lag * diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c index f239b352a58a..bf4d3cbefa63 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c @@ -3,26 +3,29 @@ #include <linux/netdevice.h> #include <net/nexthop.h> -#include "lag.h" -#include "lag_mp.h" +#include "lag/lag.h" +#include "lag/mp.h" #include "mlx5_core.h" #include "eswitch.h" #include "lib/mlx5.h" +static bool __mlx5_lag_is_multipath(struct mlx5_lag *ldev) +{ + return !!(ldev->flags & MLX5_LAG_FLAG_MULTIPATH); +} + static bool mlx5_lag_multipath_check_prereq(struct mlx5_lag *ldev) { if (!mlx5_lag_is_ready(ldev)) return false; + if (__mlx5_lag_is_active(ldev) && !__mlx5_lag_is_multipath(ldev)) + return false; + return mlx5_esw_multipath_prereq(ldev->pf[MLX5_LAG_P1].dev, ldev->pf[MLX5_LAG_P2].dev); } -static bool __mlx5_lag_is_multipath(struct mlx5_lag *ldev) -{ - return !!(ldev->flags & MLX5_LAG_FLAG_MULTIPATH); -} - bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev) { struct mlx5_lag *ldev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.h index 729c839397a8..57af962cad29 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.h @@ -24,12 +24,14 @@ struct lag_mp { void mlx5_lag_mp_reset(struct mlx5_lag *ldev); int mlx5_lag_mp_init(struct mlx5_lag *ldev); void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev); +bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev); #else /* CONFIG_MLX5_ESWITCH */ static inline void mlx5_lag_mp_reset(struct mlx5_lag *ldev) {}; static inline int mlx5_lag_mp_init(struct mlx5_lag *ldev) { return 0; } static inline void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev) {} +static inline bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev) { return false; } #endif /* CONFIG_MLX5_ESWITCH */ #endif /* __MLX5_LAG_MP_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c new file mode 100644 index 000000000000..ad63dd45c8fb --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c @@ -0,0 +1,611 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. */ + +#include <linux/netdevice.h> +#include "lag.h" + +enum { + MLX5_LAG_FT_LEVEL_TTC, + MLX5_LAG_FT_LEVEL_INNER_TTC, + MLX5_LAG_FT_LEVEL_DEFINER, +}; + +static struct mlx5_flow_group * +mlx5_create_hash_flow_group(struct mlx5_flow_table *ft, + struct mlx5_flow_definer *definer) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *fg; + u32 *in; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return ERR_PTR(-ENOMEM); + + MLX5_SET(create_flow_group_in, in, match_definer_id, + mlx5_get_match_definer_id(definer)); + MLX5_SET(create_flow_group_in, in, start_flow_index, 0); + MLX5_SET(create_flow_group_in, in, end_flow_index, MLX5_MAX_PORTS - 1); + MLX5_SET(create_flow_group_in, in, group_type, + MLX5_CREATE_FLOW_GROUP_IN_GROUP_TYPE_HASH_SPLIT); + + fg = mlx5_create_flow_group(ft, in); + kvfree(in); + return fg; +} + +static int mlx5_lag_create_port_sel_table(struct mlx5_lag *ldev, + struct mlx5_lag_definer *lag_definer, + u8 port1, u8 port2) +{ + struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_flow_table_attr ft_attr = {}; + struct mlx5_flow_destination dest = {}; + MLX5_DECLARE_FLOW_ACT(flow_act); + struct mlx5_flow_namespace *ns; + int err, i; + + ft_attr.max_fte = MLX5_MAX_PORTS; + ft_attr.level = MLX5_LAG_FT_LEVEL_DEFINER; + + ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_PORT_SEL); + if (!ns) { + mlx5_core_warn(dev, "Failed to get port selection namespace\n"); + return -EOPNOTSUPP; + } + + lag_definer->ft = mlx5_create_flow_table(ns, &ft_attr); + if (IS_ERR(lag_definer->ft)) { + mlx5_core_warn(dev, "Failed to create port selection table\n"); + return PTR_ERR(lag_definer->ft); + } + + lag_definer->fg = mlx5_create_hash_flow_group(lag_definer->ft, + lag_definer->definer); + if (IS_ERR(lag_definer->fg)) { + err = PTR_ERR(lag_definer->fg); + goto destroy_ft; + } + + dest.type = MLX5_FLOW_DESTINATION_TYPE_UPLINK; + dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID; + flow_act.flags |= FLOW_ACT_NO_APPEND; + for (i = 0; i < MLX5_MAX_PORTS; i++) { + u8 affinity = i == 0 ? port1 : port2; + + dest.vport.vhca_id = MLX5_CAP_GEN(ldev->pf[affinity - 1].dev, + vhca_id); + lag_definer->rules[i] = mlx5_add_flow_rules(lag_definer->ft, + NULL, &flow_act, + &dest, 1); + if (IS_ERR(lag_definer->rules[i])) { + err = PTR_ERR(lag_definer->rules[i]); + while (i--) + mlx5_del_flow_rules(lag_definer->rules[i]); + goto destroy_fg; + } + } + + return 0; + +destroy_fg: + mlx5_destroy_flow_group(lag_definer->fg); +destroy_ft: + mlx5_destroy_flow_table(lag_definer->ft); + return err; +} + +static int mlx5_lag_set_definer_inner(u32 *match_definer_mask, + enum mlx5_traffic_types tt) +{ + int format_id; + u8 *ipv6; + + switch (tt) { + case MLX5_TT_IPV4_UDP: + case MLX5_TT_IPV4_TCP: + format_id = 23; + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_l4_sport); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_l4_dport); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_ip_src_addr); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_ip_dest_addr); + break; + case MLX5_TT_IPV4: + format_id = 23; + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_l3_type); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_dmac_47_16); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_dmac_15_0); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_smac_47_16); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_smac_15_0); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_ip_src_addr); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_ip_dest_addr); + break; + case MLX5_TT_IPV6_TCP: + case MLX5_TT_IPV6_UDP: + format_id = 31; + MLX5_SET_TO_ONES(match_definer_format_31, match_definer_mask, + inner_l4_sport); + MLX5_SET_TO_ONES(match_definer_format_31, match_definer_mask, + inner_l4_dport); + ipv6 = MLX5_ADDR_OF(match_definer_format_31, match_definer_mask, + inner_ip_dest_addr); + memset(ipv6, 0xff, 16); + ipv6 = MLX5_ADDR_OF(match_definer_format_31, match_definer_mask, + inner_ip_src_addr); + memset(ipv6, 0xff, 16); + break; + case MLX5_TT_IPV6: + format_id = 32; + ipv6 = MLX5_ADDR_OF(match_definer_format_32, match_definer_mask, + inner_ip_dest_addr); + memset(ipv6, 0xff, 16); + ipv6 = MLX5_ADDR_OF(match_definer_format_32, match_definer_mask, + inner_ip_src_addr); + memset(ipv6, 0xff, 16); + MLX5_SET_TO_ONES(match_definer_format_32, match_definer_mask, + inner_dmac_47_16); + MLX5_SET_TO_ONES(match_definer_format_32, match_definer_mask, + inner_dmac_15_0); + MLX5_SET_TO_ONES(match_definer_format_32, match_definer_mask, + inner_smac_47_16); + MLX5_SET_TO_ONES(match_definer_format_32, match_definer_mask, + inner_smac_15_0); + break; + default: + format_id = 23; + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_l3_type); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_dmac_47_16); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_dmac_15_0); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_smac_47_16); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_smac_15_0); + break; + } + + return format_id; +} + +static int mlx5_lag_set_definer(u32 *match_definer_mask, + enum mlx5_traffic_types tt, bool tunnel, + enum netdev_lag_hash hash) +{ + int format_id; + u8 *ipv6; + + if (tunnel) + return mlx5_lag_set_definer_inner(match_definer_mask, tt); + + switch (tt) { + case MLX5_TT_IPV4_UDP: + case MLX5_TT_IPV4_TCP: + format_id = 22; + MLX5_SET_TO_ONES(match_definer_format_22, match_definer_mask, + outer_l4_sport); + MLX5_SET_TO_ONES(match_definer_format_22, match_definer_mask, + outer_l4_dport); + MLX5_SET_TO_ONES(match_definer_format_22, match_definer_mask, + outer_ip_src_addr); + MLX5_SET_TO_ONES(match_definer_format_22, match_definer_mask, + outer_ip_dest_addr); + break; + case MLX5_TT_IPV4: + format_id = 22; + MLX5_SET_TO_ONES(match_definer_format_22, match_definer_mask, + outer_l3_type); + MLX5_SET_TO_ONES(match_definer_format_22, match_definer_mask, + outer_dmac_47_16); + MLX5_SET_TO_ONES(match_definer_format_22, match_definer_mask, + outer_dmac_15_0); + MLX5_SET_TO_ONES(match_definer_format_22, match_definer_mask, + outer_smac_47_16); + MLX5_SET_TO_ONES(match_definer_format_22, match_definer_mask, + outer_smac_15_0); + MLX5_SET_TO_ONES(match_definer_format_22, match_definer_mask, + outer_ip_src_addr); + MLX5_SET_TO_ONES(match_definer_format_22, match_definer_mask, + outer_ip_dest_addr); + break; + case MLX5_TT_IPV6_TCP: + case MLX5_TT_IPV6_UDP: + format_id = 29; + MLX5_SET_TO_ONES(match_definer_format_29, match_definer_mask, + outer_l4_sport); + MLX5_SET_TO_ONES(match_definer_format_29, match_definer_mask, + outer_l4_dport); + ipv6 = MLX5_ADDR_OF(match_definer_format_29, match_definer_mask, + outer_ip_dest_addr); + memset(ipv6, 0xff, 16); + ipv6 = MLX5_ADDR_OF(match_definer_format_29, match_definer_mask, + outer_ip_src_addr); + memset(ipv6, 0xff, 16); + break; + case MLX5_TT_IPV6: + format_id = 30; + ipv6 = MLX5_ADDR_OF(match_definer_format_30, match_definer_mask, + outer_ip_dest_addr); + memset(ipv6, 0xff, 16); + ipv6 = MLX5_ADDR_OF(match_definer_format_30, match_definer_mask, + outer_ip_src_addr); + memset(ipv6, 0xff, 16); + MLX5_SET_TO_ONES(match_definer_format_30, match_definer_mask, + outer_dmac_47_16); + MLX5_SET_TO_ONES(match_definer_format_30, match_definer_mask, + outer_dmac_15_0); + MLX5_SET_TO_ONES(match_definer_format_30, match_definer_mask, + outer_smac_47_16); + MLX5_SET_TO_ONES(match_definer_format_30, match_definer_mask, + outer_smac_15_0); + break; + default: + format_id = 0; + MLX5_SET_TO_ONES(match_definer_format_0, match_definer_mask, + outer_smac_47_16); + MLX5_SET_TO_ONES(match_definer_format_0, match_definer_mask, + outer_smac_15_0); + + if (hash == NETDEV_LAG_HASH_VLAN_SRCMAC) { + MLX5_SET_TO_ONES(match_definer_format_0, + match_definer_mask, + outer_first_vlan_vid); + break; + } + + MLX5_SET_TO_ONES(match_definer_format_0, match_definer_mask, + outer_ethertype); + MLX5_SET_TO_ONES(match_definer_format_0, match_definer_mask, + outer_dmac_47_16); + MLX5_SET_TO_ONES(match_definer_format_0, match_definer_mask, + outer_dmac_15_0); + break; + } + + return format_id; +} + +static struct mlx5_lag_definer * +mlx5_lag_create_definer(struct mlx5_lag *ldev, enum netdev_lag_hash hash, + enum mlx5_traffic_types tt, bool tunnel, u8 port1, + u8 port2) +{ + struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_lag_definer *lag_definer; + u32 *match_definer_mask; + int format_id, err; + + lag_definer = kzalloc(sizeof(*lag_definer), GFP_KERNEL); + if (!lag_definer) + return ERR_PTR(-ENOMEM); + + match_definer_mask = kvzalloc(MLX5_FLD_SZ_BYTES(match_definer, + match_mask), + GFP_KERNEL); + if (!match_definer_mask) { + err = -ENOMEM; + goto free_lag_definer; + } + + format_id = mlx5_lag_set_definer(match_definer_mask, tt, tunnel, hash); + lag_definer->definer = + mlx5_create_match_definer(dev, MLX5_FLOW_NAMESPACE_PORT_SEL, + format_id, match_definer_mask); + if (IS_ERR(lag_definer->definer)) { + err = PTR_ERR(lag_definer->definer); + goto free_mask; + } + + err = mlx5_lag_create_port_sel_table(ldev, lag_definer, port1, port2); + if (err) + goto destroy_match_definer; + + kvfree(match_definer_mask); + + return lag_definer; + +destroy_match_definer: + mlx5_destroy_match_definer(dev, lag_definer->definer); +free_mask: + kvfree(match_definer_mask); +free_lag_definer: + kfree(lag_definer); + return ERR_PTR(err); +} + +static void mlx5_lag_destroy_definer(struct mlx5_lag *ldev, + struct mlx5_lag_definer *lag_definer) +{ + struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev; + int i; + + for (i = 0; i < MLX5_MAX_PORTS; i++) + mlx5_del_flow_rules(lag_definer->rules[i]); + mlx5_destroy_flow_group(lag_definer->fg); + mlx5_destroy_flow_table(lag_definer->ft); + mlx5_destroy_match_definer(dev, lag_definer->definer); + kfree(lag_definer); +} + +static void mlx5_lag_destroy_definers(struct mlx5_lag *ldev) +{ + struct mlx5_lag_port_sel *port_sel = &ldev->port_sel; + int tt; + + for_each_set_bit(tt, port_sel->tt_map, MLX5_NUM_TT) { + if (port_sel->outer.definers[tt]) + mlx5_lag_destroy_definer(ldev, + port_sel->outer.definers[tt]); + if (port_sel->inner.definers[tt]) + mlx5_lag_destroy_definer(ldev, + port_sel->inner.definers[tt]); + } +} + +static int mlx5_lag_create_definers(struct mlx5_lag *ldev, + enum netdev_lag_hash hash_type, + u8 port1, u8 port2) +{ + struct mlx5_lag_port_sel *port_sel = &ldev->port_sel; + struct mlx5_lag_definer *lag_definer; + int tt, err; + + for_each_set_bit(tt, port_sel->tt_map, MLX5_NUM_TT) { + lag_definer = mlx5_lag_create_definer(ldev, hash_type, tt, + false, port1, port2); + if (IS_ERR(lag_definer)) { + err = PTR_ERR(lag_definer); + goto destroy_definers; + } + port_sel->outer.definers[tt] = lag_definer; + + if (!port_sel->tunnel) + continue; + + lag_definer = + mlx5_lag_create_definer(ldev, hash_type, tt, + true, port1, port2); + if (IS_ERR(lag_definer)) { + err = PTR_ERR(lag_definer); + goto destroy_definers; + } + port_sel->inner.definers[tt] = lag_definer; + } + + return 0; + +destroy_definers: + mlx5_lag_destroy_definers(ldev); + return err; +} + +static void set_tt_map(struct mlx5_lag_port_sel *port_sel, + enum netdev_lag_hash hash) +{ + port_sel->tunnel = false; + + switch (hash) { + case NETDEV_LAG_HASH_E34: + port_sel->tunnel = true; + fallthrough; + case NETDEV_LAG_HASH_L34: + set_bit(MLX5_TT_IPV4_TCP, port_sel->tt_map); + set_bit(MLX5_TT_IPV4_UDP, port_sel->tt_map); + set_bit(MLX5_TT_IPV6_TCP, port_sel->tt_map); + set_bit(MLX5_TT_IPV6_UDP, port_sel->tt_map); + set_bit(MLX5_TT_IPV4, port_sel->tt_map); + set_bit(MLX5_TT_IPV6, port_sel->tt_map); + set_bit(MLX5_TT_ANY, port_sel->tt_map); + break; + case NETDEV_LAG_HASH_E23: + port_sel->tunnel = true; + fallthrough; + case NETDEV_LAG_HASH_L23: + set_bit(MLX5_TT_IPV4, port_sel->tt_map); + set_bit(MLX5_TT_IPV6, port_sel->tt_map); + set_bit(MLX5_TT_ANY, port_sel->tt_map); + break; + default: + set_bit(MLX5_TT_ANY, port_sel->tt_map); + break; + } +} + +#define SET_IGNORE_DESTS_BITS(tt_map, dests) \ + do { \ + int idx; \ + \ + for_each_clear_bit(idx, tt_map, MLX5_NUM_TT) \ + set_bit(idx, dests); \ + } while (0) + +static void mlx5_lag_set_inner_ttc_params(struct mlx5_lag *ldev, + struct ttc_params *ttc_params) +{ + struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_lag_port_sel *port_sel = &ldev->port_sel; + struct mlx5_flow_table_attr *ft_attr; + int tt; + + ttc_params->ns = mlx5_get_flow_namespace(dev, + MLX5_FLOW_NAMESPACE_PORT_SEL); + ft_attr = &ttc_params->ft_attr; + ft_attr->level = MLX5_LAG_FT_LEVEL_INNER_TTC; + + for_each_set_bit(tt, port_sel->tt_map, MLX5_NUM_TT) { + ttc_params->dests[tt].type = + MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + ttc_params->dests[tt].ft = port_sel->inner.definers[tt]->ft; + } + SET_IGNORE_DESTS_BITS(port_sel->tt_map, ttc_params->ignore_dests); +} + +static void mlx5_lag_set_outer_ttc_params(struct mlx5_lag *ldev, + struct ttc_params *ttc_params) +{ + struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_lag_port_sel *port_sel = &ldev->port_sel; + struct mlx5_flow_table_attr *ft_attr; + int tt; + + ttc_params->ns = mlx5_get_flow_namespace(dev, + MLX5_FLOW_NAMESPACE_PORT_SEL); + ft_attr = &ttc_params->ft_attr; + ft_attr->level = MLX5_LAG_FT_LEVEL_TTC; + + for_each_set_bit(tt, port_sel->tt_map, MLX5_NUM_TT) { + ttc_params->dests[tt].type = + MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + ttc_params->dests[tt].ft = port_sel->outer.definers[tt]->ft; + } + SET_IGNORE_DESTS_BITS(port_sel->tt_map, ttc_params->ignore_dests); + + ttc_params->inner_ttc = port_sel->tunnel; + if (!port_sel->tunnel) + return; + + for (tt = 0; tt < MLX5_NUM_TUNNEL_TT; tt++) { + ttc_params->tunnel_dests[tt].type = + MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + ttc_params->tunnel_dests[tt].ft = + mlx5_get_ttc_flow_table(port_sel->inner.ttc); + } +} + +static int mlx5_lag_create_ttc_table(struct mlx5_lag *ldev) +{ + struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_lag_port_sel *port_sel = &ldev->port_sel; + struct ttc_params ttc_params = {}; + + mlx5_lag_set_outer_ttc_params(ldev, &ttc_params); + port_sel->outer.ttc = mlx5_create_ttc_table(dev, &ttc_params); + if (IS_ERR(port_sel->outer.ttc)) + return PTR_ERR(port_sel->outer.ttc); + + return 0; +} + +static int mlx5_lag_create_inner_ttc_table(struct mlx5_lag *ldev) +{ + struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_lag_port_sel *port_sel = &ldev->port_sel; + struct ttc_params ttc_params = {}; + + mlx5_lag_set_inner_ttc_params(ldev, &ttc_params); + port_sel->inner.ttc = mlx5_create_ttc_table(dev, &ttc_params); + if (IS_ERR(port_sel->inner.ttc)) + return PTR_ERR(port_sel->inner.ttc); + + return 0; +} + +int mlx5_lag_port_sel_create(struct mlx5_lag *ldev, + enum netdev_lag_hash hash_type, u8 port1, u8 port2) +{ + struct mlx5_lag_port_sel *port_sel = &ldev->port_sel; + int err; + + set_tt_map(port_sel, hash_type); + err = mlx5_lag_create_definers(ldev, hash_type, port1, port2); + if (err) + return err; + + if (port_sel->tunnel) { + err = mlx5_lag_create_inner_ttc_table(ldev); + if (err) + goto destroy_definers; + } + + err = mlx5_lag_create_ttc_table(ldev); + if (err) + goto destroy_inner; + + return 0; + +destroy_inner: + if (port_sel->tunnel) + mlx5_destroy_ttc_table(port_sel->inner.ttc); +destroy_definers: + mlx5_lag_destroy_definers(ldev); + return err; +} + +static int +mlx5_lag_modify_definers_destinations(struct mlx5_lag *ldev, + struct mlx5_lag_definer **definers, + u8 port1, u8 port2) +{ + struct mlx5_lag_port_sel *port_sel = &ldev->port_sel; + struct mlx5_flow_destination dest = {}; + int err; + int tt; + + dest.type = MLX5_FLOW_DESTINATION_TYPE_UPLINK; + dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID; + + for_each_set_bit(tt, port_sel->tt_map, MLX5_NUM_TT) { + struct mlx5_flow_handle **rules = definers[tt]->rules; + + if (ldev->v2p_map[MLX5_LAG_P1] != port1) { + dest.vport.vhca_id = + MLX5_CAP_GEN(ldev->pf[port1 - 1].dev, vhca_id); + err = mlx5_modify_rule_destination(rules[MLX5_LAG_P1], + &dest, NULL); + if (err) + return err; + } + + if (ldev->v2p_map[MLX5_LAG_P2] != port2) { + dest.vport.vhca_id = + MLX5_CAP_GEN(ldev->pf[port2 - 1].dev, vhca_id); + err = mlx5_modify_rule_destination(rules[MLX5_LAG_P2], + &dest, NULL); + if (err) + return err; + } + } + + return 0; +} + +int mlx5_lag_port_sel_modify(struct mlx5_lag *ldev, u8 port1, u8 port2) +{ + struct mlx5_lag_port_sel *port_sel = &ldev->port_sel; + int err; + + err = mlx5_lag_modify_definers_destinations(ldev, + port_sel->outer.definers, + port1, port2); + if (err) + return err; + + if (!port_sel->tunnel) + return 0; + + return mlx5_lag_modify_definers_destinations(ldev, + port_sel->inner.definers, + port1, port2); +} + +void mlx5_lag_port_sel_destroy(struct mlx5_lag *ldev) +{ + struct mlx5_lag_port_sel *port_sel = &ldev->port_sel; + + mlx5_destroy_ttc_table(port_sel->outer.ttc); + if (port_sel->tunnel) + mlx5_destroy_ttc_table(port_sel->inner.ttc); + mlx5_lag_destroy_definers(ldev); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.h new file mode 100644 index 000000000000..6d15b28a42fc --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. */ + +#ifndef __MLX5_LAG_FS_H__ +#define __MLX5_LAG_FS_H__ + +#include "lib/fs_ttc.h" + +struct mlx5_lag_definer { + struct mlx5_flow_definer *definer; + struct mlx5_flow_table *ft; + struct mlx5_flow_group *fg; + struct mlx5_flow_handle *rules[MLX5_MAX_PORTS]; +}; + +struct mlx5_lag_ttc { + struct mlx5_ttc_table *ttc; + struct mlx5_lag_definer *definers[MLX5_NUM_TT]; +}; + +struct mlx5_lag_port_sel { + DECLARE_BITMAP(tt_map, MLX5_NUM_TT); + bool tunnel; + struct mlx5_lag_ttc outer; + struct mlx5_lag_ttc inner; +}; + +#ifdef CONFIG_MLX5_ESWITCH + +int mlx5_lag_port_sel_modify(struct mlx5_lag *ldev, u8 port1, u8 port2); +void mlx5_lag_port_sel_destroy(struct mlx5_lag *ldev); +int mlx5_lag_port_sel_create(struct mlx5_lag *ldev, + enum netdev_lag_hash hash_type, u8 port1, + u8 port2); + +#else /* CONFIG_MLX5_ESWITCH */ +static inline int mlx5_lag_port_sel_create(struct mlx5_lag *ldev, + enum netdev_lag_hash hash_type, + u8 port1, u8 port2) +{ + return 0; +} + +static inline int mlx5_lag_port_sel_modify(struct mlx5_lag *ldev, u8 port1, + u8 port2) +{ + return 0; +} + +static inline void mlx5_lag_port_sel_destroy(struct mlx5_lag *ldev) {} +#endif /* CONFIG_MLX5_ESWITCH */ +#endif /* __MLX5_LAG_FS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index ffac8a0e7a23..91e806c1aa21 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -448,22 +448,20 @@ static u64 find_target_cycles(struct mlx5_core_dev *mdev, s64 target_ns) return cycles_now + cycles_delta; } -static u64 perout_conf_internal_timer(struct mlx5_core_dev *mdev, - s64 sec, u32 nsec) +static u64 perout_conf_internal_timer(struct mlx5_core_dev *mdev, s64 sec) { - struct timespec64 ts; + struct timespec64 ts = {}; s64 target_ns; ts.tv_sec = sec; - ts.tv_nsec = nsec; target_ns = timespec64_to_ns(&ts); return find_target_cycles(mdev, target_ns); } -static u64 perout_conf_real_time(s64 sec, u32 nsec) +static u64 perout_conf_real_time(s64 sec) { - return (u64)nsec | (u64)sec << 32; + return (u64)sec << 32; } static int mlx5_perout_configure(struct ptp_clock_info *ptp, @@ -474,6 +472,7 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp, container_of(ptp, struct mlx5_clock, ptp_info); struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev, clock); + bool rt_mode = mlx5_real_time_mode(mdev); u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0}; struct timespec64 ts; u32 field_select = 0; @@ -501,8 +500,10 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp, if (on) { bool rt_mode = mlx5_real_time_mode(mdev); - u32 nsec; - s64 sec; + s64 sec = rq->perout.start.sec; + + if (rq->perout.start.nsec) + return -EINVAL; pin_mode = MLX5_PIN_MODE_OUT; pattern = MLX5_OUT_PATTERN_PERIODIC; @@ -513,14 +514,11 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp, if ((ns >> 1) != 500000000LL) return -EINVAL; - nsec = rq->perout.start.nsec; - sec = rq->perout.start.sec; - if (rt_mode && sec > U32_MAX) return -EINVAL; - time_stamp = rt_mode ? perout_conf_real_time(sec, nsec) : - perout_conf_internal_timer(mdev, sec, nsec); + time_stamp = rt_mode ? perout_conf_real_time(sec) : + perout_conf_internal_timer(mdev, sec); field_select |= MLX5_MTPPS_FS_PIN_MODE | MLX5_MTPPS_FS_PATTERN | @@ -538,6 +536,9 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp, if (err) return err; + if (rt_mode) + return 0; + return mlx5_set_mtppse(mdev, pin, 0, MLX5_EVENT_MODE_REPETETIVE & on); } @@ -705,20 +706,14 @@ static void ts_next_sec(struct timespec64 *ts) static u64 perout_conf_next_event_timer(struct mlx5_core_dev *mdev, struct mlx5_clock *clock) { - bool rt_mode = mlx5_real_time_mode(mdev); struct timespec64 ts; s64 target_ns; - if (rt_mode) - ts = mlx5_ptp_gettimex_real_time(mdev, NULL); - else - mlx5_ptp_gettimex(&clock->ptp_info, &ts, NULL); - + mlx5_ptp_gettimex(&clock->ptp_info, &ts, NULL); ts_next_sec(&ts); target_ns = timespec64_to_ns(&ts); - return rt_mode ? perout_conf_real_time(ts.tv_sec, ts.tv_nsec) : - find_target_cycles(mdev, target_ns); + return find_target_cycles(mdev, target_ns); } static int mlx5_pps_event(struct notifier_block *nb, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c index 749d17c0057d..b63dec24747a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c @@ -247,6 +247,8 @@ static int mlx5_generate_ttc_table_rules(struct mlx5_core_dev *dev, for (tt = 0; tt < MLX5_NUM_TT; tt++) { struct mlx5_ttc_rule *rule = &rules[tt]; + if (test_bit(tt, params->ignore_dests)) + continue; rule->rule = mlx5_generate_ttc_rule(dev, ft, ¶ms->dests[tt], ttc_rules[tt].etype, ttc_rules[tt].proto); @@ -266,6 +268,8 @@ static int mlx5_generate_ttc_table_rules(struct mlx5_core_dev *dev, if (!mlx5_tunnel_proto_supported_rx(dev, ttc_tunnel_rules[tt].proto)) continue; + if (test_bit(tt, params->ignore_tunnel_dests)) + continue; trules[tt] = mlx5_generate_ttc_rule(dev, ft, ¶ms->tunnel_dests[tt], ttc_tunnel_rules[tt].etype, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h index ce95be8f8382..85fef0cd1c07 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h @@ -43,7 +43,9 @@ struct ttc_params { struct mlx5_flow_namespace *ns; struct mlx5_flow_table_attr ft_attr; struct mlx5_flow_destination dests[MLX5_NUM_TT]; + DECLARE_BITMAP(ignore_dests, MLX5_NUM_TT); bool inner_ttc; + DECLARE_BITMAP(ignore_tunnel_dests, MLX5_NUM_TUNNEL_TT); struct mlx5_flow_destination tunnel_dests[MLX5_NUM_TUNNEL_TT]; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c new file mode 100644 index 000000000000..0dd96a6b140d --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c @@ -0,0 +1,162 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#include <linux/mlx5/driver.h> +#include "lib/tout.h" + +struct mlx5_timeouts { + u64 to[MAX_TIMEOUT_TYPES]; +}; + +static const u32 tout_def_sw_val[MAX_TIMEOUT_TYPES] = { + [MLX5_TO_FW_PRE_INIT_TIMEOUT_MS] = 120000, + [MLX5_TO_FW_PRE_INIT_WARN_MESSAGE_INTERVAL_MS] = 20000, + [MLX5_TO_FW_PRE_INIT_WAIT_MS] = 2, + [MLX5_TO_FW_INIT_MS] = 2000, + [MLX5_TO_CMD_MS] = 60000, + [MLX5_TO_PCI_TOGGLE_MS] = 2000, + [MLX5_TO_HEALTH_POLL_INTERVAL_MS] = 2000, + [MLX5_TO_FULL_CRDUMP_MS] = 60000, + [MLX5_TO_FW_RESET_MS] = 60000, + [MLX5_TO_FLUSH_ON_ERROR_MS] = 2000, + [MLX5_TO_PCI_SYNC_UPDATE_MS] = 5000, + [MLX5_TO_TEARDOWN_MS] = 3000, + [MLX5_TO_FSM_REACTIVATE_MS] = 5000, + [MLX5_TO_RECLAIM_PAGES_MS] = 5000, + [MLX5_TO_RECLAIM_VFS_PAGES_MS] = 120000 +}; + +static void tout_set(struct mlx5_core_dev *dev, u64 val, enum mlx5_timeouts_types type) +{ + dev->timeouts->to[type] = val; +} + +static void tout_set_def_val(struct mlx5_core_dev *dev) +{ + int i; + + for (i = MLX5_TO_FW_PRE_INIT_TIMEOUT_MS; i < MAX_TIMEOUT_TYPES; i++) + tout_set(dev, tout_def_sw_val[i], i); +} + +int mlx5_tout_init(struct mlx5_core_dev *dev) +{ + dev->timeouts = kmalloc(sizeof(*dev->timeouts), GFP_KERNEL); + if (!dev->timeouts) + return -ENOMEM; + + tout_set_def_val(dev); + return 0; +} + +void mlx5_tout_cleanup(struct mlx5_core_dev *dev) +{ + kfree(dev->timeouts); +} + +/* Time register consists of two fields to_multiplier(time out multiplier) + * and to_value(time out value). to_value is the quantity of the time units and + * to_multiplier is the type and should be one off these four values. + * 0x0: millisecond + * 0x1: seconds + * 0x2: minutes + * 0x3: hours + * this function converts the time stored in the two register fields into + * millisecond. + */ +static u64 tout_convert_reg_field_to_ms(u32 to_mul, u32 to_val) +{ + u64 msec = to_val; + + to_mul &= 0x3; + /* convert hours/minutes/seconds to miliseconds */ + if (to_mul) + msec *= 1000 * int_pow(60, to_mul - 1); + + return msec; +} + +static u64 tout_convert_iseg_to_ms(u32 iseg_to) +{ + return tout_convert_reg_field_to_ms(iseg_to >> 29, iseg_to & 0xfffff); +} + +static bool tout_is_supported(struct mlx5_core_dev *dev) +{ + return !!ioread32be(&dev->iseg->cmd_q_init_to); +} + +void mlx5_tout_query_iseg(struct mlx5_core_dev *dev) +{ + u32 to; + + if (!tout_is_supported(dev)) + return; + + to = ioread32be(&dev->iseg->cmd_q_init_to); + tout_set(dev, tout_convert_iseg_to_ms(to), MLX5_TO_FW_INIT_MS); + + to = ioread32be(&dev->iseg->cmd_exec_to); + tout_set(dev, tout_convert_iseg_to_ms(to), MLX5_TO_CMD_MS); +} + +u64 _mlx5_tout_ms(struct mlx5_core_dev *dev, enum mlx5_timeouts_types type) +{ + return dev->timeouts->to[type]; +} + +#define MLX5_TIMEOUT_QUERY(fld, reg_out) \ + ({ \ + struct mlx5_ifc_default_timeout_bits *time_field; \ + u32 to_multi, to_value; \ + u64 to_val_ms; \ + \ + time_field = MLX5_ADDR_OF(dtor_reg, reg_out, fld); \ + to_multi = MLX5_GET(default_timeout, time_field, to_multiplier); \ + to_value = MLX5_GET(default_timeout, time_field, to_value); \ + to_val_ms = tout_convert_reg_field_to_ms(to_multi, to_value); \ + to_val_ms; \ + }) + +#define MLX5_TIMEOUT_FILL(fld, reg_out, dev, to_type, to_extra) \ + ({ \ + u64 fw_to = MLX5_TIMEOUT_QUERY(fld, reg_out); \ + tout_set(dev, fw_to + (to_extra), to_type); \ + fw_to; \ + }) + +static int tout_query_dtor(struct mlx5_core_dev *dev) +{ + u64 pcie_toggle_to_val, tear_down_to_val; + u32 out[MLX5_ST_SZ_DW(dtor_reg)] = {}; + u32 in[MLX5_ST_SZ_DW(dtor_reg)] = {}; + int err; + + err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out), MLX5_REG_DTOR, 0, 0); + if (err) + return err; + + pcie_toggle_to_val = MLX5_TIMEOUT_FILL(pcie_toggle_to, out, dev, MLX5_TO_PCI_TOGGLE_MS, 0); + MLX5_TIMEOUT_FILL(fw_reset_to, out, dev, MLX5_TO_FW_RESET_MS, pcie_toggle_to_val); + + tear_down_to_val = MLX5_TIMEOUT_FILL(tear_down_to, out, dev, MLX5_TO_TEARDOWN_MS, 0); + MLX5_TIMEOUT_FILL(pci_sync_update_to, out, dev, MLX5_TO_PCI_SYNC_UPDATE_MS, + tear_down_to_val); + + MLX5_TIMEOUT_FILL(health_poll_to, out, dev, MLX5_TO_HEALTH_POLL_INTERVAL_MS, 0); + MLX5_TIMEOUT_FILL(full_crdump_to, out, dev, MLX5_TO_FULL_CRDUMP_MS, 0); + MLX5_TIMEOUT_FILL(flush_on_err_to, out, dev, MLX5_TO_FLUSH_ON_ERROR_MS, 0); + MLX5_TIMEOUT_FILL(fsm_reactivate_to, out, dev, MLX5_TO_FSM_REACTIVATE_MS, 0); + MLX5_TIMEOUT_FILL(reclaim_pages_to, out, dev, MLX5_TO_RECLAIM_PAGES_MS, 0); + MLX5_TIMEOUT_FILL(reclaim_vfs_pages_to, out, dev, MLX5_TO_RECLAIM_VFS_PAGES_MS, 0); + + return 0; +} + +int mlx5_tout_query_dtor(struct mlx5_core_dev *dev) +{ + if (tout_is_supported(dev)) + return tout_query_dtor(dev); + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h new file mode 100644 index 000000000000..31faa5c17aa9 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#ifndef MLX5_TIMEOUTS_H +#define MLX5_TIMEOUTS_H + +enum mlx5_timeouts_types { + /* pre init timeouts (not read from FW) */ + MLX5_TO_FW_PRE_INIT_TIMEOUT_MS, + MLX5_TO_FW_PRE_INIT_WARN_MESSAGE_INTERVAL_MS, + MLX5_TO_FW_PRE_INIT_WAIT_MS, + + /* init segment timeouts */ + MLX5_TO_FW_INIT_MS, + MLX5_TO_CMD_MS, + + /* DTOR timeouts */ + MLX5_TO_PCI_TOGGLE_MS, + MLX5_TO_HEALTH_POLL_INTERVAL_MS, + MLX5_TO_FULL_CRDUMP_MS, + MLX5_TO_FW_RESET_MS, + MLX5_TO_FLUSH_ON_ERROR_MS, + MLX5_TO_PCI_SYNC_UPDATE_MS, + MLX5_TO_TEARDOWN_MS, + MLX5_TO_FSM_REACTIVATE_MS, + MLX5_TO_RECLAIM_PAGES_MS, + MLX5_TO_RECLAIM_VFS_PAGES_MS, + + MAX_TIMEOUT_TYPES +}; + +struct mlx5_core_dev; +int mlx5_tout_init(struct mlx5_core_dev *dev); +void mlx5_tout_cleanup(struct mlx5_core_dev *dev); +void mlx5_tout_query_iseg(struct mlx5_core_dev *dev); +int mlx5_tout_query_dtor(struct mlx5_core_dev *dev); +u64 _mlx5_tout_ms(struct mlx5_core_dev *dev, enum mlx5_timeouts_types type); + +#define mlx5_tout_ms(dev, type) _mlx5_tout_ms(dev, MLX5_TO_##type##_MS) + +# endif /* MLX5_TIMEOUTS_H */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 79482824c64f..a92a92a52346 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -60,6 +60,7 @@ #include "devlink.h" #include "fw_reset.h" #include "lib/mlx5.h" +#include "lib/tout.h" #include "fpga/core.h" #include "fpga/ipsec.h" #include "accel/ipsec.h" @@ -176,11 +177,6 @@ static struct mlx5_profile profile[] = { }, }; -#define FW_INIT_TIMEOUT_MILI 2000 -#define FW_INIT_WAIT_MS 2 -#define FW_PRE_INIT_TIMEOUT_MILI 120000 -#define FW_INIT_WARN_MESSAGE_INTERVAL 20000 - static int fw_initializing(struct mlx5_core_dev *dev) { return ioread32be(&dev->iseg->initializing) >> 31; @@ -193,8 +189,6 @@ static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili, unsigned long end = jiffies + msecs_to_jiffies(max_wait_mili); int err = 0; - BUILD_BUG_ON(FW_PRE_INIT_TIMEOUT_MILI < FW_INIT_WARN_MESSAGE_INTERVAL); - while (fw_initializing(dev)) { if (time_after(jiffies, end)) { err = -EBUSY; @@ -205,7 +199,7 @@ static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili, jiffies_to_msecs(end - warn) / 1000); warn = jiffies + msecs_to_jiffies(warn_time_mili); } - msleep(FW_INIT_WAIT_MS); + msleep(mlx5_tout_ms(dev, FW_PRE_INIT_WAIT)); } return err; @@ -564,15 +558,38 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) MLX5_SET(cmd_hca_cap, set_hca_cap, num_total_dynamic_vf_msix, MLX5_CAP_GEN_MAX(dev, num_total_dynamic_vf_msix)); + if (MLX5_CAP_GEN(dev, roce_rw_supported)) + MLX5_SET(cmd_hca_cap, set_hca_cap, roce, mlx5_is_roce_init_enabled(dev)); + return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE); } +/* Cached MLX5_CAP_GEN(dev, roce) can be out of sync this early in the + * boot process. + * In case RoCE cap is writable in FW and user/devlink requested to change the + * cap, we are yet to query the final state of the above cap. + * Hence, the need for this function. + * + * Returns + * True: + * 1) RoCE cap is read only in FW and already disabled + * OR: + * 2) RoCE cap is writable in FW and user/devlink requested it off. + * + * In any other case, return False. + */ +static bool is_roce_fw_disabled(struct mlx5_core_dev *dev) +{ + return (MLX5_CAP_GEN(dev, roce_rw_supported) && !mlx5_is_roce_init_enabled(dev)) || + (!MLX5_CAP_GEN(dev, roce_rw_supported) && !MLX5_CAP_GEN(dev, roce)); +} + static int handle_hca_cap_roce(struct mlx5_core_dev *dev, void *set_ctx) { void *set_hca_cap; int err; - if (!MLX5_CAP_GEN(dev, roce)) + if (is_roce_fw_disabled(dev)) return 0; err = mlx5_core_get_caps(dev, MLX5_CAP_ROCE); @@ -975,25 +992,34 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot) if (mlx5_core_is_pf(dev)) pcie_print_link_status(dev->pdev); + err = mlx5_tout_init(dev); + if (err) { + mlx5_core_err(dev, "Failed initializing timeouts, aborting\n"); + return err; + } + /* wait for firmware to accept initialization segments configurations */ - err = wait_fw_init(dev, FW_PRE_INIT_TIMEOUT_MILI, FW_INIT_WARN_MESSAGE_INTERVAL); + err = wait_fw_init(dev, mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT), + mlx5_tout_ms(dev, FW_PRE_INIT_WARN_MESSAGE_INTERVAL)); if (err) { - mlx5_core_err(dev, "Firmware over %d MS in pre-initializing state, aborting\n", - FW_PRE_INIT_TIMEOUT_MILI); - return err; + mlx5_core_err(dev, "Firmware over %llu MS in pre-initializing state, aborting\n", + mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT)); + goto err_tout_cleanup; } err = mlx5_cmd_init(dev); if (err) { mlx5_core_err(dev, "Failed initializing command interface, aborting\n"); - return err; + goto err_tout_cleanup; } - err = wait_fw_init(dev, FW_INIT_TIMEOUT_MILI, 0); + mlx5_tout_query_iseg(dev); + + err = wait_fw_init(dev, mlx5_tout_ms(dev, FW_INIT), 0); if (err) { - mlx5_core_err(dev, "Firmware over %d MS in initializing state, aborting\n", - FW_INIT_TIMEOUT_MILI); + mlx5_core_err(dev, "Firmware over %llu MS in initializing state, aborting\n", + mlx5_tout_ms(dev, FW_INIT)); goto err_cmd_cleanup; } @@ -1017,6 +1043,12 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot) goto err_disable_hca; } + err = mlx5_tout_query_dtor(dev); + if (err) { + mlx5_core_err(dev, "failed to read dtor\n"); + goto reclaim_boot_pages; + } + err = set_hca_ctrl(dev); if (err) { mlx5_core_err(dev, "set_hca_ctrl failed\n"); @@ -1062,6 +1094,8 @@ err_disable_hca: err_cmd_cleanup: mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN); mlx5_cmd_cleanup(dev); +err_tout_cleanup: + mlx5_tout_cleanup(dev); return err; } @@ -1080,6 +1114,7 @@ static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot) mlx5_core_disable_hca(dev, 0); mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN); mlx5_cmd_cleanup(dev); + mlx5_tout_cleanup(dev); return 0; } @@ -1112,8 +1147,9 @@ 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 +1157,9 @@ 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 +1229,9 @@ 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); @@ -1381,6 +1416,8 @@ static const int types[] = { MLX5_CAP_TLS, MLX5_CAP_VDPA_EMULATION, MLX5_CAP_IPSEC, + MLX5_CAP_PORT_SELECTION, + MLX5_CAP_DEV_SHAMPO, }; static void mlx5_hca_caps_free(struct mlx5_core_dev *dev) @@ -1537,8 +1574,7 @@ 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); - if (!mlx5_core_is_mp_slave(dev)) - devlink_reload_enable(devlink); + devlink_register(devlink); return 0; err_init_one: @@ -1558,7 +1594,7 @@ static void remove_one(struct pci_dev *pdev) struct mlx5_core_dev *dev = pci_get_drvdata(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_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 230eab7e3bc9..bb677329ea08 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -97,6 +97,30 @@ do { \ __func__, __LINE__, current->pid, \ ##__VA_ARGS__) +static inline void mlx5_printk(struct mlx5_core_dev *dev, int level, const char *format, ...) +{ + struct device *device = dev->device; + struct va_format vaf; + va_list args; + + if (WARN_ONCE(level < LOGLEVEL_EMERG || level > LOGLEVEL_DEBUG, + "Level %d is out of range, set to default level\n", level)) + level = LOGLEVEL_DEFAULT; + + va_start(args, format); + vaf.fmt = format; + vaf.va = &args; + + dev_printk_emit(level, device, "%s %s: %pV", dev_driver_string(device), dev_name(device), + &vaf); + va_end(args); +} + +#define mlx5_log(__dev, level, format, ...) \ + mlx5_printk(__dev, level, "%s:%d:(pid %d): " format, \ + __func__, __LINE__, current->pid, \ + ##__VA_ARGS__) + static inline struct device *mlx5_core_dma_dev(struct mlx5_core_dev *dev) { return &dev->pdev->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/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index 174f71ed5280..f099a087400e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -35,13 +35,11 @@ #include <linux/mlx5/driver.h> #include "mlx5_core.h" -int mlx5_core_create_mkey(struct mlx5_core_dev *dev, - struct mlx5_core_mkey *mkey, - u32 *in, int inlen) +int mlx5_core_create_mkey(struct mlx5_core_dev *dev, u32 *mkey, u32 *in, + int inlen) { u32 lout[MLX5_ST_SZ_DW(create_mkey_out)] = {}; u32 mkey_index; - void *mkc; int err; MLX5_SET(create_mkey_in, in, opcode, MLX5_CMD_OP_CREATE_MKEY); @@ -50,38 +48,33 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev, if (err) return err; - mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index); - mkey->iova = MLX5_GET64(mkc, mkc, start_addr); - mkey->size = MLX5_GET64(mkc, mkc, len); - mkey->key = (u32)mlx5_mkey_variant(mkey->key) | mlx5_idx_to_mkey(mkey_index); - mkey->pd = MLX5_GET(mkc, mkc, pd); - init_waitqueue_head(&mkey->wait); + *mkey = MLX5_GET(create_mkey_in, in, memory_key_mkey_entry.mkey_7_0) | + mlx5_idx_to_mkey(mkey_index); - mlx5_core_dbg(dev, "out 0x%x, mkey 0x%x\n", mkey_index, mkey->key); + mlx5_core_dbg(dev, "out 0x%x, mkey 0x%x\n", mkey_index, *mkey); return 0; } EXPORT_SYMBOL(mlx5_core_create_mkey); -int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, - struct mlx5_core_mkey *mkey) +int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, u32 mkey) { u32 in[MLX5_ST_SZ_DW(destroy_mkey_in)] = {}; MLX5_SET(destroy_mkey_in, in, opcode, MLX5_CMD_OP_DESTROY_MKEY); - MLX5_SET(destroy_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mkey->key)); + MLX5_SET(destroy_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mkey)); return mlx5_cmd_exec_in(dev, destroy_mkey, in); } EXPORT_SYMBOL(mlx5_core_destroy_mkey); -int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey, - u32 *out, int outlen) +int mlx5_core_query_mkey(struct mlx5_core_dev *dev, u32 mkey, u32 *out, + int outlen) { u32 in[MLX5_ST_SZ_DW(query_mkey_in)] = {}; memset(out, 0, outlen); MLX5_SET(query_mkey_in, in, opcode, MLX5_CMD_OP_QUERY_MKEY); - MLX5_SET(query_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mkey->key)); + MLX5_SET(query_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mkey)); return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen); } EXPORT_SYMBOL(mlx5_core_query_mkey); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index 110c0837f95b..f6b5451328fc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -38,6 +38,7 @@ #include <linux/xarray.h> #include "mlx5_core.h" #include "lib/eq.h" +#include "lib/tout.h" enum { MLX5_PAGES_CANT_GIVE = 0, @@ -65,11 +66,6 @@ struct fw_page { }; enum { - MAX_RECLAIM_TIME_MSECS = 5000, - MAX_RECLAIM_VFS_PAGES_TIME_MSECS = 2 * 1000 * 60, -}; - -enum { MLX5_MAX_RECLAIM_TIME_MILI = 5000, MLX5_NUM_4K_IN_PAGE = PAGE_SIZE / MLX5_ADAPTER_PAGE_SIZE, }; @@ -641,7 +637,8 @@ static int optimal_reclaimed_pages(void) static int mlx5_reclaim_root_pages(struct mlx5_core_dev *dev, struct rb_root *root, u16 func_id) { - unsigned long end = jiffies + msecs_to_jiffies(MAX_RECLAIM_TIME_MSECS); + u64 recl_pages_to_jiffies = msecs_to_jiffies(mlx5_tout_ms(dev, RECLAIM_PAGES)); + unsigned long end = jiffies + recl_pages_to_jiffies; while (!RB_EMPTY_ROOT(root)) { int nclaimed; @@ -656,7 +653,7 @@ static int mlx5_reclaim_root_pages(struct mlx5_core_dev *dev, } if (nclaimed) - end = jiffies + msecs_to_jiffies(MAX_RECLAIM_TIME_MSECS); + end = jiffies + recl_pages_to_jiffies; if (time_after(jiffies, end)) { mlx5_core_warn(dev, "FW did not return all pages. giving up...\n"); @@ -727,7 +724,8 @@ void mlx5_pagealloc_stop(struct mlx5_core_dev *dev) int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages) { - unsigned long end = jiffies + msecs_to_jiffies(MAX_RECLAIM_VFS_PAGES_TIME_MSECS); + u64 recl_vf_pages_to_jiffies = msecs_to_jiffies(mlx5_tout_ms(dev, RECLAIM_VFS_PAGES)); + unsigned long end = jiffies + recl_vf_pages_to_jiffies; int prev_pages = *pages; /* In case of internal error we will free the pages manually later */ @@ -743,7 +741,7 @@ int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages) return -ETIMEDOUT; } if (*pages < prev_pages) { - end = jiffies + msecs_to_jiffies(MAX_RECLAIM_VFS_PAGES_TIME_MSECS); + end = jiffies + recl_vf_pages_to_jiffies; prev_pages = *pages; } msleep(50); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index c79a10b3454d..830444f927d4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -13,8 +13,8 @@ #endif #define MLX5_MAX_IRQ_NAME (32) -/* max irq_index is 255. three chars */ -#define MLX5_MAX_IRQ_IDX_CHARS (3) +/* max irq_index is 2047, so four chars */ +#define MLX5_MAX_IRQ_IDX_CHARS (4) #define MLX5_SFS_PER_CTRL_IRQ 64 #define MLX5_IRQ_CTRL_SF_MAX 8 @@ -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); @@ -633,8 +645,9 @@ void mlx5_irq_table_destroy(struct mlx5_core_dev *dev) int mlx5_irq_table_get_sfs_vec(struct mlx5_irq_table *table) { if (table->sf_comp_pool) - return table->sf_comp_pool->xa_num_irqs.max - - table->sf_comp_pool->xa_num_irqs.min + 1; + return min_t(int, num_online_cpus(), + table->sf_comp_pool->xa_num_irqs.max - + table->sf_comp_pool->xa_num_irqs.min + 1); else return mlx5_irq_table_get_num_comp(table); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c index 871c2fbe18d3..f37db7cc32a6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c @@ -9,6 +9,8 @@ #include "sf/sf.h" #include "sf/mlx5_ifc_vhca_event.h" #include "ecpf.h" +#define CREATE_TRACE_POINTS +#include "diag/dev_tracepoint.h" struct mlx5_sf_dev_table { struct xarray devices; @@ -66,13 +68,18 @@ static void mlx5_sf_dev_release(struct device *device) kfree(sf_dev); } -static void mlx5_sf_dev_remove(struct mlx5_sf_dev *sf_dev) +static void mlx5_sf_dev_remove(struct mlx5_core_dev *dev, struct mlx5_sf_dev *sf_dev) { + int id; + + id = sf_dev->adev.id; + trace_mlx5_sf_dev_del(dev, sf_dev, id); + auxiliary_device_delete(&sf_dev->adev); auxiliary_device_uninit(&sf_dev->adev); } -static void mlx5_sf_dev_add(struct mlx5_core_dev *dev, u16 sf_index, u32 sfnum) +static void mlx5_sf_dev_add(struct mlx5_core_dev *dev, u16 sf_index, u16 fn_id, u32 sfnum) { struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table; struct mlx5_sf_dev *sf_dev; @@ -100,6 +107,7 @@ static void mlx5_sf_dev_add(struct mlx5_core_dev *dev, u16 sf_index, u32 sfnum) sf_dev->adev.dev.groups = sf_attr_groups; sf_dev->sfnum = sfnum; sf_dev->parent_mdev = dev; + sf_dev->fn_id = fn_id; if (!table->max_sfs) { mlx5_adev_idx_free(id); @@ -109,6 +117,8 @@ static void mlx5_sf_dev_add(struct mlx5_core_dev *dev, u16 sf_index, u32 sfnum) } sf_dev->bar_base_addr = table->base_address + (sf_index * table->sf_bar_length); + trace_mlx5_sf_dev_add(dev, sf_dev, id); + err = auxiliary_device_init(&sf_dev->adev); if (err) { mlx5_adev_idx_free(id); @@ -128,7 +138,7 @@ static void mlx5_sf_dev_add(struct mlx5_core_dev *dev, u16 sf_index, u32 sfnum) return; xa_err: - mlx5_sf_dev_remove(sf_dev); + mlx5_sf_dev_remove(dev, sf_dev); add_err: mlx5_core_err(dev, "SF DEV: fail device add for index=%d sfnum=%d err=%d\n", sf_index, sfnum, err); @@ -139,7 +149,7 @@ static void mlx5_sf_dev_del(struct mlx5_core_dev *dev, struct mlx5_sf_dev *sf_de struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table; xa_erase(&table->devices, sf_index); - mlx5_sf_dev_remove(sf_dev); + mlx5_sf_dev_remove(dev, sf_dev); } static int @@ -178,7 +188,8 @@ mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_ break; case MLX5_VHCA_STATE_ACTIVE: if (!sf_dev) - mlx5_sf_dev_add(table->dev, sf_index, event->sw_function_id); + mlx5_sf_dev_add(table->dev, sf_index, event->function_id, + event->sw_function_id); break; default: break; @@ -260,7 +271,7 @@ static void mlx5_sf_dev_destroy_all(struct mlx5_sf_dev_table *table) xa_for_each(&table->devices, index, sf_dev) { xa_erase(&table->devices, index); - mlx5_sf_dev_remove(sf_dev); + mlx5_sf_dev_remove(table->dev, sf_dev); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h index 149fd9e698cf..2a66a427ef15 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h @@ -16,6 +16,7 @@ struct mlx5_sf_dev { struct mlx5_core_dev *mdev; phys_addr_t bar_base_addr; u32 sfnum; + u16 fn_id; }; void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/diag/dev_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/diag/dev_tracepoint.h new file mode 100644 index 000000000000..7f7c9af5deed --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/diag/dev_tracepoint.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mlx5 + +#if !defined(_MLX5_SF_DEV_TP_) || defined(TRACE_HEADER_MULTI_READ) +#define _MLX5_SF_DEV_TP_ + +#include <linux/tracepoint.h> +#include <linux/mlx5/driver.h> +#include "../../dev/dev.h" + +DECLARE_EVENT_CLASS(mlx5_sf_dev_template, + TP_PROTO(const struct mlx5_core_dev *dev, + const struct mlx5_sf_dev *sfdev, + int aux_id), + TP_ARGS(dev, sfdev, aux_id), + TP_STRUCT__entry(__string(devname, dev_name(dev->device)) + __field(const struct mlx5_sf_dev*, sfdev) + __field(int, aux_id) + __field(u16, hw_fn_id) + __field(u32, sfnum) + ), + TP_fast_assign(__assign_str(devname, dev_name(dev->device)); + __entry->sfdev = sfdev; + __entry->aux_id = aux_id; + __entry->hw_fn_id = sfdev->fn_id; + __entry->sfnum = sfdev->sfnum; + ), + TP_printk("(%s) sfdev=%pK aux_id=%d hw_id=0x%x sfnum=%u\n", + __get_str(devname), __entry->sfdev, + __entry->aux_id, __entry->hw_fn_id, + __entry->sfnum) +); + +DEFINE_EVENT(mlx5_sf_dev_template, mlx5_sf_dev_add, + TP_PROTO(const struct mlx5_core_dev *dev, + const struct mlx5_sf_dev *sfdev, + int aux_id), + TP_ARGS(dev, sfdev, aux_id) + ); + +DEFINE_EVENT(mlx5_sf_dev_template, mlx5_sf_dev_del, + TP_PROTO(const struct mlx5_core_dev *dev, + const struct mlx5_sf_dev *sfdev, + int aux_id), + TP_ARGS(dev, sfdev, aux_id) + ); + +#endif /* _MLX5_SF_DEV_TP_ */ + +/* This part must be outside protection */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH sf/dev/diag +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE dev_tracepoint +#include <trace/define_trace.h> 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..7b4783ce213e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c @@ -46,7 +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_reload_enable(devlink); + devlink_register(devlink); return 0; init_one_err: @@ -61,10 +61,9 @@ mdev_err: static void mlx5_sf_dev_remove(struct auxiliary_device *adev) { struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev); - struct devlink *devlink; + struct devlink *devlink = priv_to_devlink(sf_dev->mdev); - 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/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c index 13891fdc607e..3be659cd91f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c @@ -8,6 +8,8 @@ #include "mlx5_ifc_vhca_event.h" #include "vhca_event.h" #include "ecpf.h" +#define CREATE_TRACE_POINTS +#include "diag/sf_tracepoint.h" struct mlx5_sf { struct devlink_port dl_port; @@ -112,6 +114,7 @@ static void mlx5_sf_free(struct mlx5_sf_table *table, struct mlx5_sf *sf) { mlx5_sf_id_erase(table, sf); mlx5_sf_hw_table_sf_free(table->dev, sf->controller, sf->id); + trace_mlx5_sf_free(table->dev, sf->port_index, sf->controller, sf->hw_fn_id); kfree(sf); } @@ -209,6 +212,7 @@ static int mlx5_sf_activate(struct mlx5_core_dev *dev, struct mlx5_sf *sf, return err; sf->hw_state = MLX5_VHCA_STATE_ACTIVE; + trace_mlx5_sf_activate(dev, sf->port_index, sf->controller, sf->hw_fn_id); return 0; } @@ -224,6 +228,7 @@ static int mlx5_sf_deactivate(struct mlx5_core_dev *dev, struct mlx5_sf *sf) return err; sf->hw_state = MLX5_VHCA_STATE_TEARDOWN_REQUEST; + trace_mlx5_sf_deactivate(dev, sf->port_index, sf->controller, sf->hw_fn_id); return 0; } @@ -293,6 +298,7 @@ static int mlx5_sf_add(struct mlx5_core_dev *dev, struct mlx5_sf_table *table, if (err) goto esw_err; *new_port_index = sf->port_index; + trace_mlx5_sf_add(dev, sf->port_index, sf->controller, sf->hw_fn_id, new_attr->sfnum); return 0; esw_err: @@ -323,7 +329,7 @@ mlx5_sf_new_check_attr(struct mlx5_core_dev *dev, const struct devlink_port_new_ NL_SET_ERR_MSG_MOD(extack, "External controller is unsupported"); return -EOPNOTSUPP; } - if (new_attr->pfnum != PCI_FUNC(dev->pdev->devfn)) { + if (new_attr->pfnum != mlx5_get_dev_index(dev)) { NL_SET_ERR_MSG_MOD(extack, "Invalid pfnum supplied"); return -EOPNOTSUPP; } @@ -442,6 +448,8 @@ static int mlx5_sf_vhca_event(struct notifier_block *nb, unsigned long opcode, v update = mlx5_sf_state_update_check(sf, event->new_vhca_state); if (update) sf->hw_state = event->new_vhca_state; + trace_mlx5_sf_update_state(table->dev, sf->port_index, sf->controller, + sf->hw_fn_id, sf->hw_state); sf_err: mutex_unlock(&table->sf_state_lock); mlx5_sf_table_put(table); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/sf_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/sf_tracepoint.h new file mode 100644 index 000000000000..8bf1cd90930d --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/sf_tracepoint.h @@ -0,0 +1,173 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mlx5 + +#if !defined(_MLX5_SF_TP_) || defined(TRACE_HEADER_MULTI_READ) +#define _MLX5_SF_TP_ + +#include <linux/tracepoint.h> +#include <linux/mlx5/driver.h> +#include "sf/vhca_event.h" + +TRACE_EVENT(mlx5_sf_add, + TP_PROTO(const struct mlx5_core_dev *dev, + unsigned int port_index, + u32 controller, + u16 hw_fn_id, + u32 sfnum), + TP_ARGS(dev, port_index, controller, hw_fn_id, sfnum), + TP_STRUCT__entry(__string(devname, dev_name(dev->device)) + __field(unsigned int, port_index) + __field(u32, controller) + __field(u16, hw_fn_id) + __field(u32, sfnum) + ), + TP_fast_assign(__assign_str(devname, dev_name(dev->device)); + __entry->port_index = port_index; + __entry->controller = controller; + __entry->hw_fn_id = hw_fn_id; + __entry->sfnum = sfnum; + ), + TP_printk("(%s) port_index=%u controller=%u hw_id=0x%x sfnum=%u\n", + __get_str(devname), __entry->port_index, __entry->controller, + __entry->hw_fn_id, __entry->sfnum) +); + +TRACE_EVENT(mlx5_sf_free, + TP_PROTO(const struct mlx5_core_dev *dev, + unsigned int port_index, + u32 controller, + u16 hw_fn_id), + TP_ARGS(dev, port_index, controller, hw_fn_id), + TP_STRUCT__entry(__string(devname, dev_name(dev->device)) + __field(unsigned int, port_index) + __field(u32, controller) + __field(u16, hw_fn_id) + ), + TP_fast_assign(__assign_str(devname, dev_name(dev->device)); + __entry->port_index = port_index; + __entry->controller = controller; + __entry->hw_fn_id = hw_fn_id; + ), + TP_printk("(%s) port_index=%u controller=%u hw_id=0x%x\n", + __get_str(devname), __entry->port_index, __entry->controller, + __entry->hw_fn_id) +); + +TRACE_EVENT(mlx5_sf_hwc_alloc, + TP_PROTO(const struct mlx5_core_dev *dev, + u32 controller, + u16 hw_fn_id, + u32 sfnum), + TP_ARGS(dev, controller, hw_fn_id, sfnum), + TP_STRUCT__entry(__string(devname, dev_name(dev->device)) + __field(u32, controller) + __field(u16, hw_fn_id) + __field(u32, sfnum) + ), + TP_fast_assign(__assign_str(devname, dev_name(dev->device)); + __entry->controller = controller; + __entry->hw_fn_id = hw_fn_id; + __entry->sfnum = sfnum; + ), + TP_printk("(%s) controller=%u hw_id=0x%x sfnum=%u\n", + __get_str(devname), __entry->controller, __entry->hw_fn_id, + __entry->sfnum) +); + +TRACE_EVENT(mlx5_sf_hwc_free, + TP_PROTO(const struct mlx5_core_dev *dev, + u16 hw_fn_id), + TP_ARGS(dev, hw_fn_id), + TP_STRUCT__entry(__string(devname, dev_name(dev->device)) + __field(u16, hw_fn_id) + ), + TP_fast_assign(__assign_str(devname, dev_name(dev->device)); + __entry->hw_fn_id = hw_fn_id; + ), + TP_printk("(%s) hw_id=0x%x\n", __get_str(devname), __entry->hw_fn_id) +); + +TRACE_EVENT(mlx5_sf_hwc_deferred_free, + TP_PROTO(const struct mlx5_core_dev *dev, + u16 hw_fn_id), + TP_ARGS(dev, hw_fn_id), + TP_STRUCT__entry(__string(devname, dev_name(dev->device)) + __field(u16, hw_fn_id) + ), + TP_fast_assign(__assign_str(devname, dev_name(dev->device)); + __entry->hw_fn_id = hw_fn_id; + ), + TP_printk("(%s) hw_id=0x%x\n", __get_str(devname), __entry->hw_fn_id) +); + +DECLARE_EVENT_CLASS(mlx5_sf_state_template, + TP_PROTO(const struct mlx5_core_dev *dev, + u32 port_index, + u32 controller, + u16 hw_fn_id), + TP_ARGS(dev, port_index, controller, hw_fn_id), + TP_STRUCT__entry(__string(devname, dev_name(dev->device)) + __field(unsigned int, port_index) + __field(u32, controller) + __field(u16, hw_fn_id)), + TP_fast_assign(__assign_str(devname, dev_name(dev->device)); + __entry->port_index = port_index; + __entry->controller = controller; + __entry->hw_fn_id = hw_fn_id; + ), + TP_printk("(%s) port_index=%u controller=%u hw_id=0x%x\n", + __get_str(devname), __entry->port_index, __entry->controller, + __entry->hw_fn_id) +); + +DEFINE_EVENT(mlx5_sf_state_template, mlx5_sf_activate, + TP_PROTO(const struct mlx5_core_dev *dev, + u32 port_index, + u32 controller, + u16 hw_fn_id), + TP_ARGS(dev, port_index, controller, hw_fn_id) + ); + +DEFINE_EVENT(mlx5_sf_state_template, mlx5_sf_deactivate, + TP_PROTO(const struct mlx5_core_dev *dev, + u32 port_index, + u32 controller, + u16 hw_fn_id), + TP_ARGS(dev, port_index, controller, hw_fn_id) + ); + +TRACE_EVENT(mlx5_sf_update_state, + TP_PROTO(const struct mlx5_core_dev *dev, + unsigned int port_index, + u32 controller, + u16 hw_fn_id, + u8 state), + TP_ARGS(dev, port_index, controller, hw_fn_id, state), + TP_STRUCT__entry(__string(devname, dev_name(dev->device)) + __field(unsigned int, port_index) + __field(u32, controller) + __field(u16, hw_fn_id) + __field(u8, state) + ), + TP_fast_assign(__assign_str(devname, dev_name(dev->device)); + __entry->port_index = port_index; + __entry->controller = controller; + __entry->hw_fn_id = hw_fn_id; + __entry->state = state; + ), + TP_printk("(%s) port_index=%u controller=%u hw_id=0x%x state=%u\n", + __get_str(devname), __entry->port_index, __entry->controller, + __entry->hw_fn_id, __entry->state) +); + +#endif /* _MLX5_SF_TP_ */ + +/* This part must be outside protection */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH sf/diag +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE sf_tracepoint +#include <trace/define_trace.h> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/vhca_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/vhca_tracepoint.h new file mode 100644 index 000000000000..fd814a190b8b --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/vhca_tracepoint.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mlx5 + +#if !defined(_MLX5_SF_VHCA_TP_) || defined(TRACE_HEADER_MULTI_READ) +#define _MLX5_SF_VHCA_TP_ + +#include <linux/tracepoint.h> +#include <linux/mlx5/driver.h> +#include "sf/vhca_event.h" + +TRACE_EVENT(mlx5_sf_vhca_event, + TP_PROTO(const struct mlx5_core_dev *dev, + const struct mlx5_vhca_state_event *event), + TP_ARGS(dev, event), + TP_STRUCT__entry(__string(devname, dev_name(dev->device)) + __field(u16, hw_fn_id) + __field(u32, sfnum) + __field(u8, vhca_state) + ), + TP_fast_assign(__assign_str(devname, dev_name(dev->device)); + __entry->hw_fn_id = event->function_id; + __entry->sfnum = event->sw_function_id; + __entry->vhca_state = event->new_vhca_state; + ), + TP_printk("(%s) hw_id=0x%x sfnum=%u vhca_state=%d\n", + __get_str(devname), __entry->hw_fn_id, + __entry->sfnum, __entry->vhca_state) +); + +#endif /* _MLX5_SF_VHCA_TP_ */ + +/* This part must be outside protection */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH sf/diag +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE vhca_tracepoint +#include <trace/define_trace.h> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c index d9c69123c1ab..252d6017387d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c @@ -8,6 +8,7 @@ #include "ecpf.h" #include "mlx5_core.h" #include "eswitch.h" +#include "diag/sf_tracepoint.h" struct mlx5_sf_hw { u32 usr_sfnum; @@ -142,6 +143,7 @@ int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 controller, u32 usr goto vhca_err; } + trace_mlx5_sf_hwc_alloc(dev, controller, hw_fn_id, usr_sfnum); mutex_unlock(&table->table_lock); return sw_id; @@ -172,6 +174,7 @@ static void mlx5_sf_hw_table_hwc_sf_free(struct mlx5_core_dev *dev, mlx5_cmd_dealloc_sf(dev, hwc->start_fn_id + idx); hwc->sfs[idx].allocated = false; hwc->sfs[idx].pending_delete = false; + trace_mlx5_sf_hwc_free(dev, hwc->start_fn_id + idx); } void mlx5_sf_hw_table_sf_deferred_free(struct mlx5_core_dev *dev, u32 controller, u16 id) @@ -195,6 +198,7 @@ void mlx5_sf_hw_table_sf_deferred_free(struct mlx5_core_dev *dev, u32 controller hwc->sfs[id].allocated = false; } else { hwc->sfs[id].pending_delete = true; + trace_mlx5_sf_hwc_deferred_free(dev, hw_fn_id); } err: mutex_unlock(&table->table_lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c index 28b14b05086f..d908fba968f0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c @@ -6,6 +6,8 @@ #include "mlx5_core.h" #include "vhca_event.h" #include "ecpf.h" +#define CREATE_TRACE_POINTS +#include "diag/vhca_tracepoint.h" struct mlx5_vhca_state_notifier { struct mlx5_core_dev *dev; @@ -82,6 +84,7 @@ mlx5_vhca_event_notify(struct mlx5_core_dev *dev, struct mlx5_vhca_state_event * vhca_state_context.vhca_state); mlx5_vhca_event_arm(dev, event->function_id); + trace_mlx5_sf_vhca_event(dev, event); blocking_notifier_call_chain(&dev->priv.vhca_state_notifier->n_head, 0, event); } 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..07936841ce99 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; } @@ -853,6 +854,7 @@ mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn, struct mlx5dr_action *action; bool reformat_req = false; u32 num_of_ref = 0; + u32 ref_act_cnt; int ret; int i; @@ -861,11 +863,14 @@ mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn, return NULL; } - hw_dests = kzalloc(sizeof(*hw_dests) * num_of_dests, GFP_KERNEL); + hw_dests = kcalloc(num_of_dests, sizeof(*hw_dests), GFP_KERNEL); if (!hw_dests) return NULL; - ref_actions = kzalloc(sizeof(*ref_actions) * num_of_dests * 2, GFP_KERNEL); + if (unlikely(check_mul_overflow(num_of_dests, 2u, &ref_act_cnt))) + goto free_hw_dests; + + ref_actions = kcalloc(ref_act_cnt, sizeof(*ref_actions), GFP_KERNEL); if (!ref_actions) goto free_hw_dests; @@ -1747,7 +1752,7 @@ 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 +1772,11 @@ 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_icm_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c index 66c24767e3b0..7f6fd9c5e371 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c @@ -24,7 +24,7 @@ struct mlx5dr_icm_dm { }; struct mlx5dr_icm_mr { - struct mlx5_core_mkey mkey; + u32 mkey; struct mlx5dr_icm_dm dm; struct mlx5dr_domain *dmn; size_t length; @@ -33,7 +33,7 @@ struct mlx5dr_icm_mr { static int dr_icm_create_dm_mkey(struct mlx5_core_dev *mdev, u32 pd, u64 length, u64 start_addr, int mode, - struct mlx5_core_mkey *mkey) + u32 *mkey) { u32 inlen = MLX5_ST_SZ_BYTES(create_mkey_in); u32 in[MLX5_ST_SZ_DW(create_mkey_in)] = {}; @@ -116,7 +116,7 @@ dr_icm_pool_mr_create(struct mlx5dr_icm_pool *pool) return icm_mr; free_mkey: - mlx5_core_destroy_mkey(mdev, &icm_mr->mkey); + mlx5_core_destroy_mkey(mdev, icm_mr->mkey); free_dm: mlx5_dm_sw_icm_dealloc(mdev, icm_mr->dm.type, icm_mr->dm.length, 0, icm_mr->dm.addr, icm_mr->dm.obj_id); @@ -130,7 +130,7 @@ static void dr_icm_pool_mr_destroy(struct mlx5dr_icm_mr *icm_mr) struct mlx5_core_dev *mdev = icm_mr->dmn->mdev; struct mlx5dr_icm_dm *dm = &icm_mr->dm; - mlx5_core_destroy_mkey(mdev, &icm_mr->mkey); + mlx5_core_destroy_mkey(mdev, icm_mr->mkey); mlx5_dm_sw_icm_dealloc(mdev, dm->type, dm->length, 0, dm->addr, dm->obj_id); kvfree(icm_mr); @@ -252,7 +252,7 @@ dr_icm_chunk_create(struct mlx5dr_icm_pool *pool, offset = mlx5dr_icm_pool_dm_type_to_entry_size(pool->icm_type) * seg; - chunk->rkey = buddy_mem_pool->icm_mr->mkey.key; + chunk->rkey = buddy_mem_pool->icm_mr->mkey; chunk->mr_addr = offset; chunk->icm_addr = (uintptr_t)buddy_mem_pool->icm_mr->icm_start_addr + offset; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c index b5409cc021d3..75c775bee351 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c @@ -875,9 +875,10 @@ uninit_nic_rx: static int dr_matcher_init(struct mlx5dr_matcher *matcher, struct mlx5dr_match_parameters *mask) { + struct mlx5dr_match_parameters consumed_mask; struct mlx5dr_table *tbl = matcher->tbl; struct mlx5dr_domain *dmn = tbl->dmn; - int ret; + int i, ret; if (matcher->match_criteria >= DR_MATCHER_CRITERIA_MAX) { mlx5dr_err(dmn, "Invalid match criteria attribute\n"); @@ -889,8 +890,16 @@ static int dr_matcher_init(struct mlx5dr_matcher *matcher, mlx5dr_err(dmn, "Invalid match size attribute\n"); return -EINVAL; } + + consumed_mask.match_buf = kzalloc(mask->match_sz, GFP_KERNEL); + if (!consumed_mask.match_buf) + return -ENOMEM; + + consumed_mask.match_sz = mask->match_sz; + memcpy(consumed_mask.match_buf, mask->match_buf, mask->match_sz); mlx5dr_ste_copy_param(matcher->match_criteria, - &matcher->mask, mask); + &matcher->mask, &consumed_mask, + true); } switch (dmn->type) { @@ -909,9 +918,22 @@ static int dr_matcher_init(struct mlx5dr_matcher *matcher, break; default: WARN_ON(true); - return -EINVAL; + ret = -EINVAL; + goto free_consumed_mask; + } + + /* Check that all mask data was consumed */ + for (i = 0; i < consumed_mask.match_sz; i++) { + if (consumed_mask.match_buf[i]) { + mlx5dr_dbg(dmn, "Match param mask contains unsupported parameters\n"); + ret = -EOPNOTSUPP; + goto free_consumed_mask; + } } + ret = 0; +free_consumed_mask: + kfree(consumed_mask.match_buf); return ret; } 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..6a390e981b09 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -917,7 +917,7 @@ static bool dr_rule_verify(struct mlx5dr_matcher *matcher, return false; } - mlx5dr_ste_copy_param(matcher->match_criteria, param, value); + mlx5dr_ste_copy_param(matcher->match_criteria, param, value, false); if (match_criteria & DR_MATCHER_CRITERIA_OUTER) { s_idx = offsetof(struct mlx5dr_match_param, outer); @@ -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_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index bfb14b4b1906..00aef47d7682 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -350,7 +350,7 @@ static void dr_fill_data_segs(struct mlx5dr_send_ring *send_ring, send_info->read.length = send_info->write.length; /* Read into the same write area */ send_info->read.addr = (uintptr_t)send_info->write.addr; - send_info->read.lkey = send_ring->mr->mkey.key; + send_info->read.lkey = send_ring->mr->mkey; if (send_ring->pending_wqe % send_ring->signal_th == 0) send_info->read.send_flags = IB_SEND_SIGNALED; @@ -388,7 +388,7 @@ static int dr_postsend_icm_data(struct mlx5dr_domain *dmn, (void *)(uintptr_t)send_info->write.addr, send_info->write.length); send_info->write.addr = (uintptr_t)send_ring->mr->dma_addr + buff_offset; - send_info->write.lkey = send_ring->mr->mkey.key; + send_info->write.lkey = send_ring->mr->mkey; } send_ring->tx_head++; @@ -848,8 +848,7 @@ static void dr_destroy_cq(struct mlx5_core_dev *mdev, struct mlx5dr_cq *cq) kfree(cq); } -static int -dr_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, struct mlx5_core_mkey *mkey) +static int dr_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, u32 *mkey) { u32 in[MLX5_ST_SZ_DW(create_mkey_in)] = {}; void *mkc; @@ -908,7 +907,7 @@ static struct mlx5dr_mr *dr_reg_mr(struct mlx5_core_dev *mdev, static void dr_dereg_mr(struct mlx5_core_dev *mdev, struct mlx5dr_mr *mr) { - mlx5_core_destroy_mkey(mdev, &mr->mkey); + mlx5_core_destroy_mkey(mdev, mr->mkey); dma_unmap_single(mlx5_core_dma_dev(mdev), mr->dma_addr, mr->size, DMA_BIDIRECTIONAL); kfree(mr); @@ -1039,7 +1038,7 @@ int mlx5dr_send_ring_force_drain(struct mlx5dr_domain *dmn) send_info.write.lkey = 0; /* Using the sync_mr in order to write/read */ send_info.remote_addr = (uintptr_t)send_ring->sync_mr->addr; - send_info.rkey = send_ring->sync_mr->mkey.key; + send_info.rkey = send_ring->sync_mr->mkey; for (i = 0; i < num_of_sends_req; i++) { ret = dr_postsend_icm_data(dmn, &send_info); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index 1cdfe4fccc7a..219a5474a8a4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -668,101 +668,116 @@ int mlx5dr_ste_build_ste_arr(struct mlx5dr_matcher *matcher, return 0; } -static void dr_ste_copy_mask_misc(char *mask, struct mlx5dr_match_misc *spec) -{ - spec->gre_c_present = MLX5_GET(fte_match_set_misc, mask, gre_c_present); - spec->gre_k_present = MLX5_GET(fte_match_set_misc, mask, gre_k_present); - spec->gre_s_present = MLX5_GET(fte_match_set_misc, mask, gre_s_present); - spec->source_vhca_port = MLX5_GET(fte_match_set_misc, mask, source_vhca_port); - spec->source_sqn = MLX5_GET(fte_match_set_misc, mask, source_sqn); - - spec->source_port = MLX5_GET(fte_match_set_misc, mask, source_port); - spec->source_eswitch_owner_vhca_id = MLX5_GET(fte_match_set_misc, mask, - source_eswitch_owner_vhca_id); - - spec->outer_second_prio = MLX5_GET(fte_match_set_misc, mask, outer_second_prio); - spec->outer_second_cfi = MLX5_GET(fte_match_set_misc, mask, outer_second_cfi); - spec->outer_second_vid = MLX5_GET(fte_match_set_misc, mask, outer_second_vid); - spec->inner_second_prio = MLX5_GET(fte_match_set_misc, mask, inner_second_prio); - spec->inner_second_cfi = MLX5_GET(fte_match_set_misc, mask, inner_second_cfi); - spec->inner_second_vid = MLX5_GET(fte_match_set_misc, mask, inner_second_vid); +#define IFC_GET_CLR(typ, p, fld, clear) ({ \ + void *__p = (p); \ + u32 __t = MLX5_GET(typ, __p, fld); \ + if (clear) \ + MLX5_SET(typ, __p, fld, 0); \ + __t; \ +}) + +#define memcpy_and_clear(to, from, len, clear) ({ \ + void *__to = (to), *__from = (from); \ + size_t __len = (len); \ + memcpy(__to, __from, __len); \ + if (clear) \ + memset(__from, 0, __len); \ +}) + +static void dr_ste_copy_mask_misc(char *mask, struct mlx5dr_match_misc *spec, bool clr) +{ + spec->gre_c_present = IFC_GET_CLR(fte_match_set_misc, mask, gre_c_present, clr); + spec->gre_k_present = IFC_GET_CLR(fte_match_set_misc, mask, gre_k_present, clr); + spec->gre_s_present = IFC_GET_CLR(fte_match_set_misc, mask, gre_s_present, clr); + spec->source_vhca_port = IFC_GET_CLR(fte_match_set_misc, mask, source_vhca_port, clr); + spec->source_sqn = IFC_GET_CLR(fte_match_set_misc, mask, source_sqn, clr); + + spec->source_port = IFC_GET_CLR(fte_match_set_misc, mask, source_port, clr); + spec->source_eswitch_owner_vhca_id = + IFC_GET_CLR(fte_match_set_misc, mask, source_eswitch_owner_vhca_id, clr); + + spec->outer_second_prio = IFC_GET_CLR(fte_match_set_misc, mask, outer_second_prio, clr); + spec->outer_second_cfi = IFC_GET_CLR(fte_match_set_misc, mask, outer_second_cfi, clr); + spec->outer_second_vid = IFC_GET_CLR(fte_match_set_misc, mask, outer_second_vid, clr); + spec->inner_second_prio = IFC_GET_CLR(fte_match_set_misc, mask, inner_second_prio, clr); + spec->inner_second_cfi = IFC_GET_CLR(fte_match_set_misc, mask, inner_second_cfi, clr); + spec->inner_second_vid = IFC_GET_CLR(fte_match_set_misc, mask, inner_second_vid, clr); spec->outer_second_cvlan_tag = - MLX5_GET(fte_match_set_misc, mask, outer_second_cvlan_tag); + IFC_GET_CLR(fte_match_set_misc, mask, outer_second_cvlan_tag, clr); spec->inner_second_cvlan_tag = - MLX5_GET(fte_match_set_misc, mask, inner_second_cvlan_tag); + IFC_GET_CLR(fte_match_set_misc, mask, inner_second_cvlan_tag, clr); spec->outer_second_svlan_tag = - MLX5_GET(fte_match_set_misc, mask, outer_second_svlan_tag); + IFC_GET_CLR(fte_match_set_misc, mask, outer_second_svlan_tag, clr); spec->inner_second_svlan_tag = - MLX5_GET(fte_match_set_misc, mask, inner_second_svlan_tag); - - spec->gre_protocol = MLX5_GET(fte_match_set_misc, mask, gre_protocol); + IFC_GET_CLR(fte_match_set_misc, mask, inner_second_svlan_tag, clr); + spec->gre_protocol = IFC_GET_CLR(fte_match_set_misc, mask, gre_protocol, clr); - spec->gre_key_h = MLX5_GET(fte_match_set_misc, mask, gre_key.nvgre.hi); - spec->gre_key_l = MLX5_GET(fte_match_set_misc, mask, gre_key.nvgre.lo); + spec->gre_key_h = IFC_GET_CLR(fte_match_set_misc, mask, gre_key.nvgre.hi, clr); + spec->gre_key_l = IFC_GET_CLR(fte_match_set_misc, mask, gre_key.nvgre.lo, clr); - spec->vxlan_vni = MLX5_GET(fte_match_set_misc, mask, vxlan_vni); + spec->vxlan_vni = IFC_GET_CLR(fte_match_set_misc, mask, vxlan_vni, clr); - spec->geneve_vni = MLX5_GET(fte_match_set_misc, mask, geneve_vni); - spec->geneve_oam = MLX5_GET(fte_match_set_misc, mask, geneve_oam); + spec->geneve_vni = IFC_GET_CLR(fte_match_set_misc, mask, geneve_vni, clr); + spec->geneve_oam = IFC_GET_CLR(fte_match_set_misc, mask, geneve_oam, clr); spec->outer_ipv6_flow_label = - MLX5_GET(fte_match_set_misc, mask, outer_ipv6_flow_label); + IFC_GET_CLR(fte_match_set_misc, mask, outer_ipv6_flow_label, clr); spec->inner_ipv6_flow_label = - MLX5_GET(fte_match_set_misc, mask, inner_ipv6_flow_label); + IFC_GET_CLR(fte_match_set_misc, mask, inner_ipv6_flow_label, clr); - spec->geneve_opt_len = MLX5_GET(fte_match_set_misc, mask, geneve_opt_len); + spec->geneve_opt_len = IFC_GET_CLR(fte_match_set_misc, mask, geneve_opt_len, clr); spec->geneve_protocol_type = - MLX5_GET(fte_match_set_misc, mask, geneve_protocol_type); + IFC_GET_CLR(fte_match_set_misc, mask, geneve_protocol_type, clr); - spec->bth_dst_qp = MLX5_GET(fte_match_set_misc, mask, bth_dst_qp); + spec->bth_dst_qp = IFC_GET_CLR(fte_match_set_misc, mask, bth_dst_qp, clr); } -static void dr_ste_copy_mask_spec(char *mask, struct mlx5dr_match_spec *spec) +static void dr_ste_copy_mask_spec(char *mask, struct mlx5dr_match_spec *spec, bool clr) { __be32 raw_ip[4]; - spec->smac_47_16 = MLX5_GET(fte_match_set_lyr_2_4, mask, smac_47_16); + spec->smac_47_16 = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, smac_47_16, clr); - spec->smac_15_0 = MLX5_GET(fte_match_set_lyr_2_4, mask, smac_15_0); - spec->ethertype = MLX5_GET(fte_match_set_lyr_2_4, mask, ethertype); + spec->smac_15_0 = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, smac_15_0, clr); + spec->ethertype = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, ethertype, clr); - spec->dmac_47_16 = MLX5_GET(fte_match_set_lyr_2_4, mask, dmac_47_16); + spec->dmac_47_16 = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, dmac_47_16, clr); - spec->dmac_15_0 = MLX5_GET(fte_match_set_lyr_2_4, mask, dmac_15_0); - spec->first_prio = MLX5_GET(fte_match_set_lyr_2_4, mask, first_prio); - spec->first_cfi = MLX5_GET(fte_match_set_lyr_2_4, mask, first_cfi); - spec->first_vid = MLX5_GET(fte_match_set_lyr_2_4, mask, first_vid); + spec->dmac_15_0 = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, dmac_15_0, clr); + spec->first_prio = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, first_prio, clr); + spec->first_cfi = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, first_cfi, clr); + spec->first_vid = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, first_vid, clr); - spec->ip_protocol = MLX5_GET(fte_match_set_lyr_2_4, mask, ip_protocol); - spec->ip_dscp = MLX5_GET(fte_match_set_lyr_2_4, mask, ip_dscp); - spec->ip_ecn = MLX5_GET(fte_match_set_lyr_2_4, mask, ip_ecn); - spec->cvlan_tag = MLX5_GET(fte_match_set_lyr_2_4, mask, cvlan_tag); - spec->svlan_tag = MLX5_GET(fte_match_set_lyr_2_4, mask, svlan_tag); - spec->frag = MLX5_GET(fte_match_set_lyr_2_4, mask, frag); - spec->ip_version = MLX5_GET(fte_match_set_lyr_2_4, mask, ip_version); - spec->tcp_flags = MLX5_GET(fte_match_set_lyr_2_4, mask, tcp_flags); - spec->tcp_sport = MLX5_GET(fte_match_set_lyr_2_4, mask, tcp_sport); - spec->tcp_dport = MLX5_GET(fte_match_set_lyr_2_4, mask, tcp_dport); + spec->ip_protocol = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, ip_protocol, clr); + spec->ip_dscp = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, ip_dscp, clr); + spec->ip_ecn = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, ip_ecn, clr); + spec->cvlan_tag = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, cvlan_tag, clr); + spec->svlan_tag = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, svlan_tag, clr); + spec->frag = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, frag, clr); + spec->ip_version = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, ip_version, clr); + spec->tcp_flags = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, tcp_flags, clr); + spec->tcp_sport = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, tcp_sport, clr); + spec->tcp_dport = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, tcp_dport, clr); - spec->ttl_hoplimit = MLX5_GET(fte_match_set_lyr_2_4, mask, ttl_hoplimit); + spec->ttl_hoplimit = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, ttl_hoplimit, clr); - spec->udp_sport = MLX5_GET(fte_match_set_lyr_2_4, mask, udp_sport); - spec->udp_dport = MLX5_GET(fte_match_set_lyr_2_4, mask, udp_dport); + spec->udp_sport = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, udp_sport, clr); + spec->udp_dport = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, udp_dport, clr); - memcpy(raw_ip, MLX5_ADDR_OF(fte_match_set_lyr_2_4, mask, - src_ipv4_src_ipv6.ipv6_layout.ipv6), - sizeof(raw_ip)); + memcpy_and_clear(raw_ip, MLX5_ADDR_OF(fte_match_set_lyr_2_4, mask, + src_ipv4_src_ipv6.ipv6_layout.ipv6), + sizeof(raw_ip), clr); spec->src_ip_127_96 = be32_to_cpu(raw_ip[0]); spec->src_ip_95_64 = be32_to_cpu(raw_ip[1]); spec->src_ip_63_32 = be32_to_cpu(raw_ip[2]); spec->src_ip_31_0 = be32_to_cpu(raw_ip[3]); - memcpy(raw_ip, MLX5_ADDR_OF(fte_match_set_lyr_2_4, mask, - dst_ipv4_dst_ipv6.ipv6_layout.ipv6), - sizeof(raw_ip)); + memcpy_and_clear(raw_ip, MLX5_ADDR_OF(fte_match_set_lyr_2_4, mask, + dst_ipv4_dst_ipv6.ipv6_layout.ipv6), + sizeof(raw_ip), clr); spec->dst_ip_127_96 = be32_to_cpu(raw_ip[0]); spec->dst_ip_95_64 = be32_to_cpu(raw_ip[1]); @@ -770,104 +785,105 @@ static void dr_ste_copy_mask_spec(char *mask, struct mlx5dr_match_spec *spec) spec->dst_ip_31_0 = be32_to_cpu(raw_ip[3]); } -static void dr_ste_copy_mask_misc2(char *mask, struct mlx5dr_match_misc2 *spec) +static void dr_ste_copy_mask_misc2(char *mask, struct mlx5dr_match_misc2 *spec, bool clr) { spec->outer_first_mpls_label = - MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls.mpls_label); + IFC_GET_CLR(fte_match_set_misc2, mask, outer_first_mpls.mpls_label, clr); spec->outer_first_mpls_exp = - MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls.mpls_exp); + IFC_GET_CLR(fte_match_set_misc2, mask, outer_first_mpls.mpls_exp, clr); spec->outer_first_mpls_s_bos = - MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls.mpls_s_bos); + IFC_GET_CLR(fte_match_set_misc2, mask, outer_first_mpls.mpls_s_bos, clr); spec->outer_first_mpls_ttl = - MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls.mpls_ttl); + IFC_GET_CLR(fte_match_set_misc2, mask, outer_first_mpls.mpls_ttl, clr); spec->inner_first_mpls_label = - MLX5_GET(fte_match_set_misc2, mask, inner_first_mpls.mpls_label); + IFC_GET_CLR(fte_match_set_misc2, mask, inner_first_mpls.mpls_label, clr); spec->inner_first_mpls_exp = - MLX5_GET(fte_match_set_misc2, mask, inner_first_mpls.mpls_exp); + IFC_GET_CLR(fte_match_set_misc2, mask, inner_first_mpls.mpls_exp, clr); spec->inner_first_mpls_s_bos = - MLX5_GET(fte_match_set_misc2, mask, inner_first_mpls.mpls_s_bos); + IFC_GET_CLR(fte_match_set_misc2, mask, inner_first_mpls.mpls_s_bos, clr); spec->inner_first_mpls_ttl = - MLX5_GET(fte_match_set_misc2, mask, inner_first_mpls.mpls_ttl); + IFC_GET_CLR(fte_match_set_misc2, mask, inner_first_mpls.mpls_ttl, clr); spec->outer_first_mpls_over_gre_label = - MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_label); + IFC_GET_CLR(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_label, clr); spec->outer_first_mpls_over_gre_exp = - MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_exp); + IFC_GET_CLR(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_exp, clr); spec->outer_first_mpls_over_gre_s_bos = - MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_s_bos); + IFC_GET_CLR(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_s_bos, clr); spec->outer_first_mpls_over_gre_ttl = - MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_ttl); + IFC_GET_CLR(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_ttl, clr); spec->outer_first_mpls_over_udp_label = - MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_label); + IFC_GET_CLR(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_label, clr); spec->outer_first_mpls_over_udp_exp = - MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_exp); + IFC_GET_CLR(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_exp, clr); spec->outer_first_mpls_over_udp_s_bos = - MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_s_bos); + IFC_GET_CLR(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_s_bos, clr); spec->outer_first_mpls_over_udp_ttl = - MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_ttl); - spec->metadata_reg_c_7 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_7); - spec->metadata_reg_c_6 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_6); - spec->metadata_reg_c_5 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_5); - spec->metadata_reg_c_4 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_4); - spec->metadata_reg_c_3 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_3); - spec->metadata_reg_c_2 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_2); - spec->metadata_reg_c_1 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_1); - spec->metadata_reg_c_0 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_0); - spec->metadata_reg_a = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_a); -} - -static void dr_ste_copy_mask_misc3(char *mask, struct mlx5dr_match_misc3 *spec) -{ - spec->inner_tcp_seq_num = MLX5_GET(fte_match_set_misc3, mask, inner_tcp_seq_num); - spec->outer_tcp_seq_num = MLX5_GET(fte_match_set_misc3, mask, outer_tcp_seq_num); - spec->inner_tcp_ack_num = MLX5_GET(fte_match_set_misc3, mask, inner_tcp_ack_num); - spec->outer_tcp_ack_num = MLX5_GET(fte_match_set_misc3, mask, outer_tcp_ack_num); + IFC_GET_CLR(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_ttl, clr); + spec->metadata_reg_c_7 = IFC_GET_CLR(fte_match_set_misc2, mask, metadata_reg_c_7, clr); + spec->metadata_reg_c_6 = IFC_GET_CLR(fte_match_set_misc2, mask, metadata_reg_c_6, clr); + spec->metadata_reg_c_5 = IFC_GET_CLR(fte_match_set_misc2, mask, metadata_reg_c_5, clr); + spec->metadata_reg_c_4 = IFC_GET_CLR(fte_match_set_misc2, mask, metadata_reg_c_4, clr); + spec->metadata_reg_c_3 = IFC_GET_CLR(fte_match_set_misc2, mask, metadata_reg_c_3, clr); + spec->metadata_reg_c_2 = IFC_GET_CLR(fte_match_set_misc2, mask, metadata_reg_c_2, clr); + spec->metadata_reg_c_1 = IFC_GET_CLR(fte_match_set_misc2, mask, metadata_reg_c_1, clr); + spec->metadata_reg_c_0 = IFC_GET_CLR(fte_match_set_misc2, mask, metadata_reg_c_0, clr); + spec->metadata_reg_a = IFC_GET_CLR(fte_match_set_misc2, mask, metadata_reg_a, clr); +} + +static void dr_ste_copy_mask_misc3(char *mask, struct mlx5dr_match_misc3 *spec, bool clr) +{ + spec->inner_tcp_seq_num = IFC_GET_CLR(fte_match_set_misc3, mask, inner_tcp_seq_num, clr); + spec->outer_tcp_seq_num = IFC_GET_CLR(fte_match_set_misc3, mask, outer_tcp_seq_num, clr); + spec->inner_tcp_ack_num = IFC_GET_CLR(fte_match_set_misc3, mask, inner_tcp_ack_num, clr); + spec->outer_tcp_ack_num = IFC_GET_CLR(fte_match_set_misc3, mask, outer_tcp_ack_num, clr); spec->outer_vxlan_gpe_vni = - MLX5_GET(fte_match_set_misc3, mask, outer_vxlan_gpe_vni); + IFC_GET_CLR(fte_match_set_misc3, mask, outer_vxlan_gpe_vni, clr); spec->outer_vxlan_gpe_next_protocol = - MLX5_GET(fte_match_set_misc3, mask, outer_vxlan_gpe_next_protocol); + IFC_GET_CLR(fte_match_set_misc3, mask, outer_vxlan_gpe_next_protocol, clr); spec->outer_vxlan_gpe_flags = - MLX5_GET(fte_match_set_misc3, mask, outer_vxlan_gpe_flags); - spec->icmpv4_header_data = MLX5_GET(fte_match_set_misc3, mask, icmp_header_data); + IFC_GET_CLR(fte_match_set_misc3, mask, outer_vxlan_gpe_flags, clr); + spec->icmpv4_header_data = IFC_GET_CLR(fte_match_set_misc3, mask, icmp_header_data, clr); spec->icmpv6_header_data = - MLX5_GET(fte_match_set_misc3, mask, icmpv6_header_data); - spec->icmpv4_type = MLX5_GET(fte_match_set_misc3, mask, icmp_type); - spec->icmpv4_code = MLX5_GET(fte_match_set_misc3, mask, icmp_code); - spec->icmpv6_type = MLX5_GET(fte_match_set_misc3, mask, icmpv6_type); - spec->icmpv6_code = MLX5_GET(fte_match_set_misc3, mask, icmpv6_code); + IFC_GET_CLR(fte_match_set_misc3, mask, icmpv6_header_data, clr); + spec->icmpv4_type = IFC_GET_CLR(fte_match_set_misc3, mask, icmp_type, clr); + spec->icmpv4_code = IFC_GET_CLR(fte_match_set_misc3, mask, icmp_code, clr); + spec->icmpv6_type = IFC_GET_CLR(fte_match_set_misc3, mask, icmpv6_type, clr); + spec->icmpv6_code = IFC_GET_CLR(fte_match_set_misc3, mask, icmpv6_code, clr); spec->geneve_tlv_option_0_data = - MLX5_GET(fte_match_set_misc3, mask, geneve_tlv_option_0_data); - spec->gtpu_msg_flags = MLX5_GET(fte_match_set_misc3, mask, gtpu_msg_flags); - spec->gtpu_msg_type = MLX5_GET(fte_match_set_misc3, mask, gtpu_msg_type); - spec->gtpu_teid = MLX5_GET(fte_match_set_misc3, mask, gtpu_teid); - spec->gtpu_dw_0 = MLX5_GET(fte_match_set_misc3, mask, gtpu_dw_0); - spec->gtpu_dw_2 = MLX5_GET(fte_match_set_misc3, mask, gtpu_dw_2); + IFC_GET_CLR(fte_match_set_misc3, mask, geneve_tlv_option_0_data, clr); + spec->gtpu_teid = IFC_GET_CLR(fte_match_set_misc3, mask, gtpu_teid, clr); + spec->gtpu_msg_flags = IFC_GET_CLR(fte_match_set_misc3, mask, gtpu_msg_flags, clr); + spec->gtpu_msg_type = IFC_GET_CLR(fte_match_set_misc3, mask, gtpu_msg_type, clr); + spec->gtpu_dw_0 = IFC_GET_CLR(fte_match_set_misc3, mask, gtpu_dw_0, clr); + spec->gtpu_dw_2 = IFC_GET_CLR(fte_match_set_misc3, mask, gtpu_dw_2, clr); spec->gtpu_first_ext_dw_0 = - MLX5_GET(fte_match_set_misc3, mask, gtpu_first_ext_dw_0); + IFC_GET_CLR(fte_match_set_misc3, mask, gtpu_first_ext_dw_0, clr); } -static void dr_ste_copy_mask_misc4(char *mask, struct mlx5dr_match_misc4 *spec) +static void dr_ste_copy_mask_misc4(char *mask, struct mlx5dr_match_misc4 *spec, bool clr) { spec->prog_sample_field_id_0 = - MLX5_GET(fte_match_set_misc4, mask, prog_sample_field_id_0); + IFC_GET_CLR(fte_match_set_misc4, mask, prog_sample_field_id_0, clr); spec->prog_sample_field_value_0 = - MLX5_GET(fte_match_set_misc4, mask, prog_sample_field_value_0); + IFC_GET_CLR(fte_match_set_misc4, mask, prog_sample_field_value_0, clr); spec->prog_sample_field_id_1 = - MLX5_GET(fte_match_set_misc4, mask, prog_sample_field_id_1); + IFC_GET_CLR(fte_match_set_misc4, mask, prog_sample_field_id_1, clr); spec->prog_sample_field_value_1 = - MLX5_GET(fte_match_set_misc4, mask, prog_sample_field_value_1); + IFC_GET_CLR(fte_match_set_misc4, mask, prog_sample_field_value_1, clr); spec->prog_sample_field_id_2 = - MLX5_GET(fte_match_set_misc4, mask, prog_sample_field_id_2); + IFC_GET_CLR(fte_match_set_misc4, mask, prog_sample_field_id_2, clr); spec->prog_sample_field_value_2 = - MLX5_GET(fte_match_set_misc4, mask, prog_sample_field_value_2); + IFC_GET_CLR(fte_match_set_misc4, mask, prog_sample_field_value_2, clr); spec->prog_sample_field_id_3 = - MLX5_GET(fte_match_set_misc4, mask, prog_sample_field_id_3); + IFC_GET_CLR(fte_match_set_misc4, mask, prog_sample_field_id_3, clr); spec->prog_sample_field_value_3 = - MLX5_GET(fte_match_set_misc4, mask, prog_sample_field_value_3); + IFC_GET_CLR(fte_match_set_misc4, mask, prog_sample_field_value_3, clr); } void mlx5dr_ste_copy_param(u8 match_criteria, struct mlx5dr_match_param *set_param, - struct mlx5dr_match_parameters *mask) + struct mlx5dr_match_parameters *mask, + bool clr) { u8 tail_param[MLX5_ST_SZ_BYTES(fte_match_set_lyr_2_4)] = {}; u8 *data = (u8 *)mask->match_buf; @@ -881,7 +897,7 @@ void mlx5dr_ste_copy_param(u8 match_criteria, } else { buff = mask->match_buf; } - dr_ste_copy_mask_spec(buff, &set_param->outer); + dr_ste_copy_mask_spec(buff, &set_param->outer, clr); } param_location = sizeof(struct mlx5dr_match_spec); @@ -894,7 +910,7 @@ void mlx5dr_ste_copy_param(u8 match_criteria, } else { buff = data + param_location; } - dr_ste_copy_mask_misc(buff, &set_param->misc); + dr_ste_copy_mask_misc(buff, &set_param->misc, clr); } param_location += sizeof(struct mlx5dr_match_misc); @@ -907,7 +923,7 @@ void mlx5dr_ste_copy_param(u8 match_criteria, } else { buff = data + param_location; } - dr_ste_copy_mask_spec(buff, &set_param->inner); + dr_ste_copy_mask_spec(buff, &set_param->inner, clr); } param_location += sizeof(struct mlx5dr_match_spec); @@ -920,7 +936,7 @@ void mlx5dr_ste_copy_param(u8 match_criteria, } else { buff = data + param_location; } - dr_ste_copy_mask_misc2(buff, &set_param->misc2); + dr_ste_copy_mask_misc2(buff, &set_param->misc2, clr); } param_location += sizeof(struct mlx5dr_match_misc2); @@ -934,7 +950,7 @@ void mlx5dr_ste_copy_param(u8 match_criteria, } else { buff = data + param_location; } - dr_ste_copy_mask_misc3(buff, &set_param->misc3); + dr_ste_copy_mask_misc3(buff, &set_param->misc3, clr); } param_location += sizeof(struct mlx5dr_match_misc3); @@ -948,7 +964,7 @@ void mlx5dr_ste_copy_param(u8 match_criteria, } else { buff = data + param_location; } - dr_ste_copy_mask_misc4(buff, &set_param->misc4); + dr_ste_copy_mask_misc4(buff, &set_param->misc4, clr); } } 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..3028b776da00 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); @@ -1241,7 +1230,8 @@ void mlx5dr_ste_set_formatted_ste(struct mlx5dr_ste_ctx *ste_ctx, struct mlx5dr_htbl_connect_info *connect_info); void mlx5dr_ste_copy_param(u8 match_criteria, struct mlx5dr_match_param *set_param, - struct mlx5dr_match_parameters *mask); + struct mlx5dr_match_parameters *mask, + bool clear); struct mlx5dr_qp { struct mlx5_core_dev *mdev; @@ -1275,7 +1265,7 @@ struct mlx5dr_cq { struct mlx5dr_mr { struct mlx5_core_dev *mdev; - struct mlx5_core_mkey mkey; + u32 mkey; dma_addr_t dma_addr; void *addr; size_t size; @@ -1372,12 +1362,12 @@ 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..2632d5ae9bc0 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, @@ -625,6 +625,19 @@ static void mlx5_cmd_dr_modify_header_dealloc(struct mlx5_flow_root_namespace *n mlx5dr_action_destroy(modify_hdr->action.dr_action); } +static int +mlx5_cmd_dr_destroy_match_definer(struct mlx5_flow_root_namespace *ns, + int definer_id) +{ + return -EOPNOTSUPP; +} + +static int mlx5_cmd_dr_create_match_definer(struct mlx5_flow_root_namespace *ns, + u16 format_id, u32 *match_mask) +{ + return -EOPNOTSUPP; +} + static int mlx5_cmd_dr_delete_fte(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *ft, struct fs_fte *fte) @@ -727,6 +740,8 @@ static const struct mlx5_flow_cmds mlx5_flow_cmds_dr = { .packet_reformat_dealloc = mlx5_cmd_dr_packet_reformat_dealloc, .modify_header_alloc = mlx5_cmd_dr_modify_header_alloc, .modify_header_dealloc = mlx5_cmd_dr_modify_header_dealloc, + .create_match_definer = mlx5_cmd_dr_create_match_definer, + .destroy_match_definer = mlx5_cmd_dr_destroy_match_definer, .set_peer = mlx5_cmd_dr_set_peer, .create_ns = mlx5_cmd_dr_create_ns, .destroy_ns = mlx5_cmd_dr_destroy_ns, 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/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c index da481a7c12f4..01e9c412977c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c @@ -36,7 +36,7 @@ #include <linux/mlx5/driver.h> #include "mlx5_core.h" -int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn) +static int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn) { u32 out[MLX5_ST_SZ_DW(alloc_uar_out)] = {}; u32 in[MLX5_ST_SZ_DW(alloc_uar_in)] = {}; @@ -44,13 +44,14 @@ int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn) MLX5_SET(alloc_uar_in, in, opcode, MLX5_CMD_OP_ALLOC_UAR); err = mlx5_cmd_exec_inout(dev, alloc_uar, in, out); - if (!err) - *uarn = MLX5_GET(alloc_uar_out, out, uar); - return err; + if (err) + return err; + + *uarn = MLX5_GET(alloc_uar_out, out, uar); + return 0; } -EXPORT_SYMBOL(mlx5_cmd_alloc_uar); -int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn) +static int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn) { u32 in[MLX5_ST_SZ_DW(dealloc_uar_in)] = {}; @@ -58,7 +59,6 @@ int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn) MLX5_SET(dealloc_uar_in, in, uar, uarn); return mlx5_cmd_exec_in(dev, dealloc_uar, in); } -EXPORT_SYMBOL(mlx5_cmd_free_uar); static int uars_per_sys_page(struct mlx5_core_dev *mdev) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 4c1440a95ad7..8846d30a380a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -421,19 +421,21 @@ int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev, { u32 *out; int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out); + int err; out = kvzalloc(outlen, GFP_KERNEL); if (!out) return -ENOMEM; - mlx5_query_nic_vport_context(mdev, 0, out); + err = mlx5_query_nic_vport_context(mdev, 0, out); + if (err) + goto out; *system_image_guid = MLX5_GET64(query_nic_vport_context_out, out, nic_vport_context.system_image_guid); - +out: kvfree(out); - - return 0; + return err; } EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_system_image_guid); @@ -1133,19 +1135,20 @@ EXPORT_SYMBOL_GPL(mlx5_nic_vport_unaffiliate_multiport); u64 mlx5_query_nic_system_image_guid(struct mlx5_core_dev *mdev) { int port_type_cap = MLX5_CAP_GEN(mdev, port_type); - u64 tmp = 0; + u64 tmp; + int err; if (mdev->sys_image_guid) return mdev->sys_image_guid; if (port_type_cap == MLX5_CAP_PORT_TYPE_ETH) - mlx5_query_nic_vport_system_image_guid(mdev, &tmp); + err = mlx5_query_nic_vport_system_image_guid(mdev, &tmp); else - mlx5_query_hca_vport_system_image_guid(mdev, &tmp); + err = mlx5_query_hca_vport_system_image_guid(mdev, &tmp); - mdev->sys_image_guid = tmp; + mdev->sys_image_guid = err ? 0 : tmp; - return tmp; + return mdev->sys_image_guid; } EXPORT_SYMBOL_GPL(mlx5_query_nic_system_image_guid); diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/Makefile b/drivers/net/ethernet/mellanox/mlxbf_gige/Makefile index e57c1375f236..a97c2bef846b 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/Makefile +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/Makefile @@ -3,7 +3,6 @@ obj-$(CONFIG_MLXBF_GIGE) += mlxbf_gige.o mlxbf_gige-y := mlxbf_gige_ethtool.o \ - mlxbf_gige_gpio.o \ mlxbf_gige_intr.o \ mlxbf_gige_main.o \ mlxbf_gige_mdio.o \ diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h index e3509e69ed1c..86826a70f9dd 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h @@ -51,11 +51,6 @@ #define MLXBF_GIGE_ERROR_INTR_IDX 0 #define MLXBF_GIGE_RECEIVE_PKT_INTR_IDX 1 #define MLXBF_GIGE_LLU_PLU_INTR_IDX 2 -#define MLXBF_GIGE_PHY_INT_N 3 - -#define MLXBF_GIGE_MDIO_DEFAULT_PHY_ADDR 0x3 - -#define MLXBF_GIGE_DEFAULT_PHY_INT_GPIO 12 struct mlxbf_gige_stats { u64 hw_access_errors; @@ -81,11 +76,7 @@ struct mlxbf_gige { struct platform_device *pdev; void __iomem *mdio_io; struct mii_bus *mdiobus; - void __iomem *gpio_io; - struct irq_domain *irqdomain; - u32 phy_int_gpio_mask; spinlock_t lock; /* for packet processing indices */ - spinlock_t gpio_lock; /* for GPIO bus access */ u16 rx_q_entries; u16 tx_q_entries; u64 *tx_wqe_base; @@ -184,7 +175,4 @@ int mlxbf_gige_poll(struct napi_struct *napi, int budget); extern const struct ethtool_ops mlxbf_gige_ethtool_ops; void mlxbf_gige_update_tx_wqe_next(struct mlxbf_gige *priv); -int mlxbf_gige_gpio_init(struct platform_device *pdev, struct mlxbf_gige *priv); -void mlxbf_gige_gpio_free(struct mlxbf_gige *priv); - #endif /* !defined(__MLXBF_GIGE_H__) */ diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_gpio.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_gpio.c deleted file mode 100644 index a8d966db5715..000000000000 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_gpio.c +++ /dev/null @@ -1,212 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only OR BSD-3-Clause - -/* Initialize and handle GPIO interrupt triggered by INT_N PHY signal. - * This GPIO interrupt triggers the PHY state machine to bring the link - * up/down. - * - * Copyright (C) 2021 NVIDIA CORPORATION & AFFILIATES - */ - -#include <linux/acpi.h> -#include <linux/bitfield.h> -#include <linux/device.h> -#include <linux/err.h> -#include <linux/gpio/driver.h> -#include <linux/interrupt.h> -#include <linux/io.h> -#include <linux/irq.h> -#include <linux/irqdomain.h> -#include <linux/irqreturn.h> -#include <linux/platform_device.h> -#include <linux/property.h> - -#include "mlxbf_gige.h" -#include "mlxbf_gige_regs.h" - -#define MLXBF_GIGE_GPIO_CAUSE_FALL_EN 0x48 -#define MLXBF_GIGE_GPIO_CAUSE_OR_CAUSE_EVTEN0 0x80 -#define MLXBF_GIGE_GPIO_CAUSE_OR_EVTEN0 0x94 -#define MLXBF_GIGE_GPIO_CAUSE_OR_CLRCAUSE 0x98 - -static void mlxbf_gige_gpio_enable(struct mlxbf_gige *priv) -{ - unsigned long flags; - u32 val; - - spin_lock_irqsave(&priv->gpio_lock, flags); - val = readl(priv->gpio_io + MLXBF_GIGE_GPIO_CAUSE_OR_CLRCAUSE); - val |= priv->phy_int_gpio_mask; - writel(val, priv->gpio_io + MLXBF_GIGE_GPIO_CAUSE_OR_CLRCAUSE); - - /* The INT_N interrupt level is active low. - * So enable cause fall bit to detect when GPIO - * state goes low. - */ - val = readl(priv->gpio_io + MLXBF_GIGE_GPIO_CAUSE_FALL_EN); - val |= priv->phy_int_gpio_mask; - writel(val, priv->gpio_io + MLXBF_GIGE_GPIO_CAUSE_FALL_EN); - - /* Enable PHY interrupt by setting the priority level */ - val = readl(priv->gpio_io + MLXBF_GIGE_GPIO_CAUSE_OR_EVTEN0); - val |= priv->phy_int_gpio_mask; - writel(val, priv->gpio_io + MLXBF_GIGE_GPIO_CAUSE_OR_EVTEN0); - spin_unlock_irqrestore(&priv->gpio_lock, flags); -} - -static void mlxbf_gige_gpio_disable(struct mlxbf_gige *priv) -{ - unsigned long flags; - u32 val; - - spin_lock_irqsave(&priv->gpio_lock, flags); - val = readl(priv->gpio_io + MLXBF_GIGE_GPIO_CAUSE_OR_EVTEN0); - val &= ~priv->phy_int_gpio_mask; - writel(val, priv->gpio_io + MLXBF_GIGE_GPIO_CAUSE_OR_EVTEN0); - spin_unlock_irqrestore(&priv->gpio_lock, flags); -} - -static irqreturn_t mlxbf_gige_gpio_handler(int irq, void *ptr) -{ - struct mlxbf_gige *priv; - u32 val; - - priv = ptr; - - /* Check if this interrupt is from PHY device. - * Return if it is not. - */ - val = readl(priv->gpio_io + MLXBF_GIGE_GPIO_CAUSE_OR_CAUSE_EVTEN0); - if (!(val & priv->phy_int_gpio_mask)) - return IRQ_NONE; - - /* Clear interrupt when done, otherwise, no further interrupt - * will be triggered. - */ - val = readl(priv->gpio_io + MLXBF_GIGE_GPIO_CAUSE_OR_CLRCAUSE); - val |= priv->phy_int_gpio_mask; - writel(val, priv->gpio_io + MLXBF_GIGE_GPIO_CAUSE_OR_CLRCAUSE); - - generic_handle_irq(priv->phy_irq); - - return IRQ_HANDLED; -} - -static void mlxbf_gige_gpio_mask(struct irq_data *irqd) -{ - struct mlxbf_gige *priv = irq_data_get_irq_chip_data(irqd); - - mlxbf_gige_gpio_disable(priv); -} - -static void mlxbf_gige_gpio_unmask(struct irq_data *irqd) -{ - struct mlxbf_gige *priv = irq_data_get_irq_chip_data(irqd); - - mlxbf_gige_gpio_enable(priv); -} - -static struct irq_chip mlxbf_gige_gpio_chip = { - .name = "mlxbf_gige_phy", - .irq_mask = mlxbf_gige_gpio_mask, - .irq_unmask = mlxbf_gige_gpio_unmask, -}; - -static int mlxbf_gige_gpio_domain_map(struct irq_domain *d, - unsigned int irq, - irq_hw_number_t hwirq) -{ - irq_set_chip_data(irq, d->host_data); - irq_set_chip_and_handler(irq, &mlxbf_gige_gpio_chip, handle_simple_irq); - irq_set_noprobe(irq); - - return 0; -} - -static const struct irq_domain_ops mlxbf_gige_gpio_domain_ops = { - .map = mlxbf_gige_gpio_domain_map, - .xlate = irq_domain_xlate_twocell, -}; - -#ifdef CONFIG_ACPI -static int mlxbf_gige_gpio_resources(struct acpi_resource *ares, - void *data) -{ - struct acpi_resource_gpio *gpio; - u32 *phy_int_gpio = data; - - if (ares->type == ACPI_RESOURCE_TYPE_GPIO) { - gpio = &ares->data.gpio; - *phy_int_gpio = gpio->pin_table[0]; - } - - return 1; -} -#endif - -void mlxbf_gige_gpio_free(struct mlxbf_gige *priv) -{ - irq_dispose_mapping(priv->phy_irq); - irq_domain_remove(priv->irqdomain); -} - -int mlxbf_gige_gpio_init(struct platform_device *pdev, - struct mlxbf_gige *priv) -{ - struct device *dev = &pdev->dev; - struct resource *res; - u32 phy_int_gpio = 0; - int ret; - - LIST_HEAD(resources); - - res = platform_get_resource(pdev, IORESOURCE_MEM, MLXBF_GIGE_RES_GPIO0); - if (!res) - return -ENODEV; - - priv->gpio_io = devm_ioremap(dev, res->start, resource_size(res)); - if (!priv->gpio_io) - return -ENOMEM; - -#ifdef CONFIG_ACPI - ret = acpi_dev_get_resources(ACPI_COMPANION(dev), - &resources, mlxbf_gige_gpio_resources, - &phy_int_gpio); - acpi_dev_free_resource_list(&resources); - if (ret < 0 || !phy_int_gpio) { - dev_err(dev, "Error retrieving the gpio phy pin"); - return -EINVAL; - } -#endif - - priv->phy_int_gpio_mask = BIT(phy_int_gpio); - - mlxbf_gige_gpio_disable(priv); - - priv->hw_phy_irq = platform_get_irq(pdev, MLXBF_GIGE_PHY_INT_N); - - priv->irqdomain = irq_domain_add_simple(NULL, 1, 0, - &mlxbf_gige_gpio_domain_ops, - priv); - if (!priv->irqdomain) { - dev_err(dev, "Failed to add IRQ domain\n"); - return -ENOMEM; - } - - priv->phy_irq = irq_create_mapping(priv->irqdomain, 0); - if (!priv->phy_irq) { - irq_domain_remove(priv->irqdomain); - priv->irqdomain = NULL; - dev_err(dev, "Error mapping PHY IRQ\n"); - return -EINVAL; - } - - ret = devm_request_irq(dev, priv->hw_phy_irq, mlxbf_gige_gpio_handler, - IRQF_ONESHOT | IRQF_SHARED, "mlxbf_gige_phy", priv); - if (ret) { - dev_err(dev, "Failed to request PHY IRQ"); - mlxbf_gige_gpio_free(priv); - return ret; - } - - return ret; -} 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..66ef0090755e 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. @@ -280,8 +280,8 @@ static int mlxbf_gige_probe(struct platform_device *pdev) void __iomem *llu_base; void __iomem *plu_base; void __iomem *base; + int addr, phy_irq; u64 control; - int addr; int err; base = devm_platform_ioremap_resource(pdev, MLXBF_GIGE_RES_MAC); @@ -316,20 +316,12 @@ static int mlxbf_gige_probe(struct platform_device *pdev) priv->pdev = pdev; spin_lock_init(&priv->lock); - spin_lock_init(&priv->gpio_lock); /* Attach MDIO device */ err = mlxbf_gige_mdio_probe(pdev, priv); if (err) return err; - err = mlxbf_gige_gpio_init(pdev, priv); - if (err) { - dev_err(&pdev->dev, "PHY IRQ initialization failed\n"); - mlxbf_gige_mdio_remove(priv); - return -ENODEV; - } - priv->base = base; priv->llu_base = llu_base; priv->plu_base = plu_base; @@ -350,6 +342,12 @@ static int mlxbf_gige_probe(struct platform_device *pdev) priv->rx_irq = platform_get_irq(pdev, MLXBF_GIGE_RECEIVE_PKT_INTR_IDX); priv->llu_plu_irq = platform_get_irq(pdev, MLXBF_GIGE_LLU_PLU_INTR_IDX); + phy_irq = acpi_dev_gpio_irq_get_by(ACPI_COMPANION(&pdev->dev), "phy-gpios", 0); + if (phy_irq < 0) { + dev_err(&pdev->dev, "Error getting PHY irq. Use polling instead"); + phy_irq = PHY_POLL; + } + phydev = phy_find_first(priv->mdiobus); if (!phydev) { err = -ENODEV; @@ -357,8 +355,8 @@ static int mlxbf_gige_probe(struct platform_device *pdev) } addr = phydev->mdio.addr; - priv->mdiobus->irq[addr] = priv->phy_irq; - phydev->irq = priv->phy_irq; + priv->mdiobus->irq[addr] = phy_irq; + phydev->irq = phy_irq; err = phy_connect_direct(netdev, phydev, mlxbf_gige_adjust_link, @@ -394,7 +392,6 @@ static int mlxbf_gige_probe(struct platform_device *pdev) return 0; out: - mlxbf_gige_gpio_free(priv); mlxbf_gige_mdio_remove(priv); return err; } @@ -405,7 +402,6 @@ static int mlxbf_gige_remove(struct platform_device *pdev) unregister_netdev(priv->netdev); phy_disconnect(priv->netdev->phydev); - mlxbf_gige_gpio_free(priv); mlxbf_gige_mdio_remove(priv); platform_set_drvdata(pdev, NULL); diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h b/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h index 7654841a05c2..e6475ea77cd1 100644 --- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h +++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h @@ -19,7 +19,7 @@ struct mlxfw_dev { static inline struct device *mlxfw_dev_dev(struct mlxfw_dev *mlxfw_dev) { - return mlxfw_dev->devlink->dev; + return devlink_to_dev(mlxfw_dev->devlink); } #define MLXFW_PRFX "mlxfw: " diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index f080fab3de2b..3fd3812b8f31 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 +2001,31 @@ __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 (!reload) - devlink_reload_enable(devlink); + if (mlxsw_driver->init) { + err = mlxsw_driver->init(mlxsw_core, mlxsw_bus_info, extack); + if (err) + goto err_driver_init; + } + if (!reload) { + devlink_set_features(devlink, DEVLINK_F_RELOAD); + devlink_register(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); @@ -2088,7 +2075,8 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, struct devlink *devlink = priv_to_devlink(mlxsw_core); 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 +2087,14 @@ 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 +2108,6 @@ 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 +2922,6 @@ 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/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c index 0998dcc9cac0..b29824448aa8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c @@ -24,16 +24,8 @@ #define MLXSW_THERMAL_ZONE_MAX_NAME 16 #define MLXSW_THERMAL_TEMP_SCORE_MAX GENMASK(31, 0) #define MLXSW_THERMAL_MAX_STATE 10 +#define MLXSW_THERMAL_MIN_STATE 2 #define MLXSW_THERMAL_MAX_DUTY 255 -/* Minimum and maximum fan allowed speed in percent: from 20% to 100%. Values - * MLXSW_THERMAL_MAX_STATE + x, where x is between 2 and 10 are used for - * setting fan speed dynamic minimum. For example, if value is set to 14 (40%) - * cooling levels vector will be set to 4, 4, 4, 4, 4, 5, 6, 7, 8, 9, 10 to - * introduce PWM speed in percent: 40, 40, 40, 40, 40, 50, 60. 70, 80, 90, 100. - */ -#define MLXSW_THERMAL_SPEED_MIN (MLXSW_THERMAL_MAX_STATE + 2) -#define MLXSW_THERMAL_SPEED_MAX (MLXSW_THERMAL_MAX_STATE * 2) -#define MLXSW_THERMAL_SPEED_MIN_LEVEL 2 /* 20% */ /* External cooling devices, allowed for binding to mlxsw thermal zones. */ static char * const mlxsw_thermal_external_allowed_cdev[] = { @@ -646,49 +638,16 @@ static int mlxsw_thermal_set_cur_state(struct thermal_cooling_device *cdev, struct mlxsw_thermal *thermal = cdev->devdata; struct device *dev = thermal->bus_info->dev; char mfsc_pl[MLXSW_REG_MFSC_LEN]; - unsigned long cur_state, i; int idx; - u8 duty; int err; + if (state > MLXSW_THERMAL_MAX_STATE) + return -EINVAL; + idx = mlxsw_get_cooling_device_idx(thermal, cdev); if (idx < 0) return idx; - /* Verify if this request is for changing allowed fan dynamical - * minimum. If it is - update cooling levels accordingly and update - * state, if current state is below the newly requested minimum state. - * For example, if current state is 5, and minimal state is to be - * changed from 4 to 6, thermal->cooling_levels[0 to 5] will be changed - * all from 4 to 6. And state 5 (thermal->cooling_levels[4]) should be - * overwritten. - */ - if (state >= MLXSW_THERMAL_SPEED_MIN && - state <= MLXSW_THERMAL_SPEED_MAX) { - state -= MLXSW_THERMAL_MAX_STATE; - for (i = 0; i <= MLXSW_THERMAL_MAX_STATE; i++) - thermal->cooling_levels[i] = max(state, i); - - mlxsw_reg_mfsc_pack(mfsc_pl, idx, 0); - err = mlxsw_reg_query(thermal->core, MLXSW_REG(mfsc), mfsc_pl); - if (err) - return err; - - duty = mlxsw_reg_mfsc_pwm_duty_cycle_get(mfsc_pl); - cur_state = mlxsw_duty_to_state(duty); - - /* If current fan state is lower than requested dynamical - * minimum, increase fan speed up to dynamical minimum. - */ - if (state < cur_state) - return 0; - - state = cur_state; - } - - if (state > MLXSW_THERMAL_MAX_STATE) - return -EINVAL; - /* Normalize the state to the valid speed range. */ state = thermal->cooling_levels[state]; mlxsw_reg_mfsc_pack(mfsc_pl, idx, mlxsw_state_to_duty(state)); @@ -998,8 +957,7 @@ int mlxsw_thermal_init(struct mlxsw_core *core, /* Initialize cooling levels per PWM state. */ for (i = 0; i < MLXSW_THERMAL_MAX_STATE; i++) - thermal->cooling_levels[i] = max(MLXSW_THERMAL_SPEED_MIN_LEVEL, - i); + thermal->cooling_levels[i] = max(MLXSW_THERMAL_MIN_STATE, i); thermal->polling_delay = bus_info->low_frequency ? MLXSW_THERMAL_SLOW_POLL_INT : diff --git a/drivers/net/ethernet/mellanox/mlxsw/item.h b/drivers/net/ethernet/mellanox/mlxsw/item.h index e92cadc98128..ab70a873a01a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/item.h +++ b/drivers/net/ethernet/mellanox/mlxsw/item.h @@ -270,11 +270,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u8 mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ +static inline u8 __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ { \ return __mlxsw_item_get8(buf, &__ITEM_NAME(_type, _cname, _iname), 0); \ } \ -static inline void mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u8 val)\ +static inline void __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u8 val) \ { \ __mlxsw_item_set8(buf, &__ITEM_NAME(_type, _cname, _iname), 0, val); \ } @@ -290,13 +292,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u8 \ +static inline u8 __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf, unsigned short index)\ { \ return __mlxsw_item_get8(buf, &__ITEM_NAME(_type, _cname, _iname), \ index); \ } \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, unsigned short index, \ u8 val) \ { \ @@ -311,11 +313,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u16 mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ +static inline u16 __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ { \ return __mlxsw_item_get16(buf, &__ITEM_NAME(_type, _cname, _iname), 0); \ } \ -static inline void mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u16 val)\ +static inline void __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u16 val) \ { \ __mlxsw_item_set16(buf, &__ITEM_NAME(_type, _cname, _iname), 0, val); \ } @@ -331,13 +335,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u16 \ +static inline u16 __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf, unsigned short index)\ { \ return __mlxsw_item_get16(buf, &__ITEM_NAME(_type, _cname, _iname), \ index); \ } \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, unsigned short index, \ u16 val) \ { \ @@ -352,11 +356,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u32 mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ +static inline u32 __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ { \ return __mlxsw_item_get32(buf, &__ITEM_NAME(_type, _cname, _iname), 0); \ } \ -static inline void mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u32 val)\ +static inline void __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u32 val) \ { \ __mlxsw_item_set32(buf, &__ITEM_NAME(_type, _cname, _iname), 0, val); \ } @@ -372,13 +378,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u32 \ +static inline u32 __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf, unsigned short index)\ { \ return __mlxsw_item_get32(buf, &__ITEM_NAME(_type, _cname, _iname), \ index); \ } \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, unsigned short index, \ u32 val) \ { \ @@ -393,11 +399,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u64 mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ +static inline u64 __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ { \ return __mlxsw_item_get64(buf, &__ITEM_NAME(_type, _cname, _iname), 0); \ } \ -static inline void mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u64 val)\ +static inline void __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u64 val) \ { \ __mlxsw_item_set64(buf, &__ITEM_NAME(_type, _cname, _iname), 0, val); \ } @@ -413,13 +421,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u64 \ +static inline u64 __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf, unsigned short index)\ { \ return __mlxsw_item_get64(buf, &__ITEM_NAME(_type, _cname, _iname), \ index); \ } \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, unsigned short index, \ u64 val) \ { \ @@ -433,19 +441,19 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bytes = _sizebytes,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_memcpy_from(const char *buf, char *dst) \ { \ __mlxsw_item_memcpy_from(buf, dst, \ &__ITEM_NAME(_type, _cname, _iname), 0); \ } \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_memcpy_to(char *buf, const char *src) \ { \ __mlxsw_item_memcpy_to(buf, src, \ &__ITEM_NAME(_type, _cname, _iname), 0); \ } \ -static inline char * \ +static inline char * __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_data(char *buf) \ { \ return __mlxsw_item_data(buf, &__ITEM_NAME(_type, _cname, _iname), 0); \ @@ -460,7 +468,7 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bytes = _sizebytes,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_memcpy_from(const char *buf, \ unsigned short index, \ char *dst) \ @@ -468,7 +476,7 @@ mlxsw_##_type##_##_cname##_##_iname##_memcpy_from(const char *buf, \ __mlxsw_item_memcpy_from(buf, dst, \ &__ITEM_NAME(_type, _cname, _iname), index); \ } \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_memcpy_to(char *buf, \ unsigned short index, \ const char *src) \ @@ -476,7 +484,7 @@ mlxsw_##_type##_##_cname##_##_iname##_memcpy_to(char *buf, \ __mlxsw_item_memcpy_to(buf, src, \ &__ITEM_NAME(_type, _cname, _iname), index); \ } \ -static inline char * \ +static inline char * __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_data(char *buf, unsigned short index) \ { \ return __mlxsw_item_data(buf, \ @@ -491,14 +499,14 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bytes = _sizebytes,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u8 \ +static inline u8 __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf, u16 index) \ { \ return __mlxsw_item_bit_array_get(buf, \ &__ITEM_NAME(_type, _cname, _iname), \ index); \ } \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u16 index, u8 val) \ { \ return __mlxsw_item_bit_array_set(buf, \ diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c index d9d56c44e994..5d4dfa5ddbb5 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 @@ -152,20 +200,16 @@ static int mlxsw_m_port_dev_addr_get(struct mlxsw_m_port *mlxsw_m_port) { struct mlxsw_m *mlxsw_m = mlxsw_m_port->mlxsw_m; - struct net_device *dev = mlxsw_m_port->dev; char ppad_pl[MLXSW_REG_PPAD_LEN]; + u8 addr[ETH_ALEN]; int err; mlxsw_reg_ppad_pack(ppad_pl, false, 0); err = mlxsw_reg_query(mlxsw_m->core, MLXSW_REG(ppad), ppad_pl); if (err) return err; - mlxsw_reg_ppad_mac_memcpy_from(ppad_pl, dev->dev_addr); - /* The last byte value in base mac address is guaranteed - * to be such it does not overflow when adding local_port - * value. - */ - dev->dev_addr[ETH_ALEN - 1] += mlxsw_m_port->module + 1; + mlxsw_reg_ppad_mac_memcpy_from(ppad_pl, addr); + eth_hw_addr_gen(mlxsw_m_port->dev, addr, mlxsw_m_port->module + 1); return 0; } @@ -266,6 +310,7 @@ 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 +319,7 @@ 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/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 13b0259f7ea6..a15c95a10bae 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -353,13 +353,10 @@ static int mlxsw_pci_rdq_skb_alloc(struct mlxsw_pci *mlxsw_pci, struct sk_buff *skb; int err; - elem_info->u.rdq.skb = NULL; skb = netdev_alloc_skb_ip_align(NULL, buf_len); if (!skb) return -ENOMEM; - /* Assume that wqe was previously zeroed. */ - err = mlxsw_pci_wqe_frag_map(mlxsw_pci, wqe, 0, skb->data, buf_len, DMA_FROM_DEVICE); if (err) @@ -597,21 +594,26 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci, struct pci_dev *pdev = mlxsw_pci->pdev; struct mlxsw_pci_queue_elem_info *elem_info; struct mlxsw_rx_info rx_info = {}; - char *wqe; + char wqe[MLXSW_PCI_WQE_SIZE]; struct sk_buff *skb; u16 byte_count; int err; elem_info = mlxsw_pci_queue_elem_info_consumer_get(q); - skb = elem_info->u.sdq.skb; - if (!skb) - return; - wqe = elem_info->elem; - mlxsw_pci_wqe_frag_unmap(mlxsw_pci, wqe, 0, DMA_FROM_DEVICE); + skb = elem_info->u.rdq.skb; + memcpy(wqe, elem_info->elem, MLXSW_PCI_WQE_SIZE); if (q->consumer_counter++ != consumer_counter_limit) dev_dbg_ratelimited(&pdev->dev, "Consumer counter does not match limit in RDQ\n"); + err = mlxsw_pci_rdq_skb_alloc(mlxsw_pci, elem_info); + if (err) { + dev_err_ratelimited(&pdev->dev, "Failed to alloc skb for RDQ\n"); + goto out; + } + + mlxsw_pci_wqe_frag_unmap(mlxsw_pci, wqe, 0, DMA_FROM_DEVICE); + if (mlxsw_pci_cqe_lag_get(cqe_v, cqe)) { rx_info.is_lag = true; rx_info.u.lag_id = mlxsw_pci_cqe_lag_id_get(cqe_v, cqe); @@ -647,10 +649,7 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci, skb_put(skb, byte_count); mlxsw_core_skb_receive(mlxsw_pci->core, skb, &rx_info); - memset(wqe, 0, q->elem_size); - err = mlxsw_pci_rdq_skb_alloc(mlxsw_pci, elem_info); - if (err) - dev_dbg_ratelimited(&pdev->dev, "Failed to alloc skb for RDQ\n"); +out: /* Everything is set up, ring doorbell to pass elem to HW */ q->producer_counter++; mlxsw_pci_queue_doorbell_producer_ring(mlxsw_pci, q); @@ -1876,7 +1875,7 @@ static void mlxsw_pci_cmd_fini(struct mlxsw_pci *mlxsw_pci) static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { - const char *driver_name = pdev->driver->name; + const char *driver_name = dev_driver_string(&pdev->dev); struct mlxsw_pci *mlxsw_pci; int err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 6fbda6ebd590..8d420eb8ade2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -4951,7 +4951,7 @@ enum mlxsw_reg_ppcnt_grp { MLXSW_REG_PPCNT_DISCARD_CNT = 0x6, MLXSW_REG_PPCNT_PRIO_CNT = 0x10, MLXSW_REG_PPCNT_TC_CNT = 0x11, - MLXSW_REG_PPCNT_TC_CONG_TC = 0x13, + MLXSW_REG_PPCNT_TC_CONG_CNT = 0x13, }; /* reg_ppcnt_grp @@ -5371,7 +5371,7 @@ MLXSW_ITEM64(reg, ppcnt, tx_pause_duration, MLXSW_ITEM64(reg, ppcnt, tx_pause_transition, MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x70, 0, 64); -/* Ethernet Per Traffic Group Counters */ +/* Ethernet Per Traffic Class Counters */ /* reg_ppcnt_tc_transmit_queue * Contains the transmit queue depth in cells of traffic class @@ -5398,6 +5398,12 @@ MLXSW_ITEM64(reg, ppcnt, tc_no_buffer_discard_uc, MLXSW_ITEM64(reg, ppcnt, wred_discard, MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x00, 0, 64); +/* reg_ppcnt_ecn_marked_tc + * Access: RO + */ +MLXSW_ITEM64(reg, ppcnt, ecn_marked_tc, + MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x08, 0, 64); + static inline void mlxsw_reg_ppcnt_pack(char *payload, u8 local_port, enum mlxsw_reg_ppcnt_grp grp, u8 prio_tc) @@ -5681,6 +5687,14 @@ 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 +5707,24 @@ 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 +5753,10 @@ 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 +5795,69 @@ 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 +5952,100 @@ 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); -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, +/* 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 { + /* 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 @@ -6401,6 +6526,12 @@ MLXSW_ITEM32(reg, ritr, mtu, 0x34, 0, 16); */ MLXSW_ITEM32(reg, ritr, if_swid, 0x08, 24, 8); +/* reg_ritr_if_mac_profile_id + * MAC msb profile ID. + * Access: RW + */ +MLXSW_ITEM32(reg, ritr, if_mac_profile_id, 0x10, 16, 4); + /* reg_ritr_if_mac * Router interface MAC address. * In Spectrum, all MAC addresses must have the same 38 MSBits. @@ -6664,6 +6795,23 @@ 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 +7080,12 @@ 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 +8271,71 @@ 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 +10414,39 @@ 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 +12439,11 @@ 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 +12451,7 @@ 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 +12491,7 @@ 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..c7fc650608eb 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, @@ -52,6 +49,7 @@ enum mlxsw_res_id { MLXSW_RES_ID_MAX_VRS, MLXSW_RES_ID_MAX_RIFS, MLXSW_RES_ID_MC_ERIF_LIST_ENTRIES, + MLXSW_RES_ID_MAX_RIF_MAC_PROFILES, MLXSW_RES_ID_MAX_LPM_TREES, MLXSW_RES_ID_MAX_NVE_MC_ENTRIES_IPV4, MLXSW_RES_ID_MAX_NVE_MC_ENTRIES_IPV6, @@ -84,9 +82,6 @@ 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 */ @@ -111,6 +106,7 @@ static u16 mlxsw_res_ids[] = { [MLXSW_RES_ID_MAX_VRS] = 0x2C01, [MLXSW_RES_ID_MAX_RIFS] = 0x2C02, [MLXSW_RES_ID_MC_ERIF_LIST_ENTRIES] = 0x2C10, + [MLXSW_RES_ID_MAX_RIF_MAC_PROFILES] = 0x2C14, [MLXSW_RES_ID_MAX_LPM_TREES] = 0x2C30, [MLXSW_RES_ID_MAX_NVE_MC_ENTRIES_IPV4] = 0x2E02, [MLXSW_RES_ID_MAX_NVE_MC_ENTRIES_IPV6] = 0x2E03, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 250c5a24264d..5925db386b1b 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, @@ -316,11 +316,11 @@ static int mlxsw_sp_port_dev_addr_set(struct mlxsw_sp_port *mlxsw_sp_port, static int mlxsw_sp_port_dev_addr_init(struct mlxsw_sp_port *mlxsw_sp_port) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - unsigned char *addr = mlxsw_sp_port->dev->dev_addr; - ether_addr_copy(addr, mlxsw_sp->base_mac); - addr[ETH_ALEN - 1] += mlxsw_sp_port->local_port; - return mlxsw_sp_port_dev_addr_set(mlxsw_sp_port, addr); + eth_hw_addr_gen(mlxsw_sp_port->dev, mlxsw_sp->base_mac, + mlxsw_sp_port->local_port); + return mlxsw_sp_port_dev_addr_set(mlxsw_sp_port, + mlxsw_sp_port->dev->dev_addr); } static int mlxsw_sp_port_max_mtu_get(struct mlxsw_sp_port *mlxsw_sp_port, int *p_max_mtu) @@ -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; } @@ -799,12 +824,16 @@ mlxsw_sp_port_get_hw_xstats(struct net_device *dev, for (i = 0; i < TC_MAX_QUEUE; i++) { err = mlxsw_sp_port_get_stats_raw(dev, - MLXSW_REG_PPCNT_TC_CONG_TC, + MLXSW_REG_PPCNT_TC_CONG_CNT, i, ppcnt_pl); - if (!err) - xstats->wred_drop[i] = - mlxsw_reg_ppcnt_wred_discard_get(ppcnt_pl); + if (err) + goto tc_cnt; + xstats->wred_drop[i] = + mlxsw_reg_ppcnt_wred_discard_get(ppcnt_pl); + xstats->tc_ecn[i] = mlxsw_reg_ppcnt_ecn_marked_tc_get(ppcnt_pl); + +tc_cnt: err = mlxsw_sp_port_get_stats_raw(dev, MLXSW_REG_PPCNT_TC_CNT, i, ppcnt_pl); if (err) @@ -1010,6 +1039,8 @@ static int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port, return mlxsw_sp_setup_tc_block_clsact(mlxsw_sp_port, f, false); case FLOW_BLOCK_BINDER_TYPE_RED_EARLY_DROP: return mlxsw_sp_setup_tc_block_qevent_early_drop(mlxsw_sp_port, f); + case FLOW_BLOCK_BINDER_TYPE_RED_MARK: + return mlxsw_sp_setup_tc_block_qevent_mark(mlxsw_sp_port, f); default: return -EOPNOTSUPP; } @@ -1442,29 +1473,68 @@ 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 +1550,6 @@ 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 +1567,6 @@ 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 +1767,24 @@ 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 +1800,13 @@ 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 +1848,15 @@ 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 +1893,7 @@ 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 +1960,10 @@ 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 +1971,13 @@ 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 +1986,34 @@ 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 +2029,8 @@ 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 +2042,37 @@ 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 +2081,7 @@ 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 +2090,10 @@ 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 +2104,30 @@ 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 = max_width / mlxsw_sp_port->mapping.width; + count = mlxsw_sp_port->mapping.module_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; } @@ -3260,6 +3282,30 @@ static int mlxsw_sp_resources_span_register(struct mlxsw_core *mlxsw_core) &span_size_params); } +static int +mlxsw_sp_resources_rif_mac_profile_register(struct mlxsw_core *mlxsw_core) +{ + struct devlink *devlink = priv_to_devlink(mlxsw_core); + struct devlink_resource_size_params size_params; + u8 max_rif_mac_profiles; + + if (!MLXSW_CORE_RES_VALID(mlxsw_core, MAX_RIF_MAC_PROFILES)) + return -EIO; + + max_rif_mac_profiles = MLXSW_CORE_RES_GET(mlxsw_core, + MAX_RIF_MAC_PROFILES); + devlink_resource_size_params_init(&size_params, max_rif_mac_profiles, + max_rif_mac_profiles, 1, + DEVLINK_RESOURCE_UNIT_ENTRY); + + return devlink_resource_register(devlink, + "rif_mac_profiles", + max_rif_mac_profiles, + MLXSW_SP_RESOURCE_RIF_MAC_PROFILES, + DEVLINK_RESOURCE_ID_PARENT_TOP, + &size_params); +} + static int mlxsw_sp1_resources_register(struct mlxsw_core *mlxsw_core) { int err; @@ -3278,10 +3324,16 @@ static int mlxsw_sp1_resources_register(struct mlxsw_core *mlxsw_core) err = mlxsw_sp_policer_resources_register(mlxsw_core); if (err) - goto err_resources_counter_register; + goto err_policer_resources_register; + + err = mlxsw_sp_resources_rif_mac_profile_register(mlxsw_core); + if (err) + goto err_resources_rif_mac_profile_register; return 0; +err_resources_rif_mac_profile_register: +err_policer_resources_register: err_resources_counter_register: err_resources_span_register: devlink_resources_unregister(priv_to_devlink(mlxsw_core), NULL); @@ -3306,10 +3358,16 @@ static int mlxsw_sp2_resources_register(struct mlxsw_core *mlxsw_core) err = mlxsw_sp_policer_resources_register(mlxsw_core); if (err) - goto err_resources_counter_register; + goto err_policer_resources_register; + + err = mlxsw_sp_resources_rif_mac_profile_register(mlxsw_core); + if (err) + goto err_resources_rif_mac_profile_register; return 0; +err_resources_rif_mac_profile_register: +err_policer_resources_register: err_resources_counter_register: err_resources_span_register: devlink_resources_unregister(priv_to_devlink(mlxsw_core), NULL); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 3a43cba6d23c..32fdd37657dd 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -67,6 +67,7 @@ enum mlxsw_sp_resource_id { MLXSW_SP_RESOURCE_COUNTERS_RIF, MLXSW_SP_RESOURCE_GLOBAL_POLICERS, MLXSW_SP_RESOURCE_SINGLE_RATE_POLICERS, + MLXSW_SP_RESOURCE_RIF_MAC_PROFILES, }; struct mlxsw_sp_port; @@ -144,7 +145,8 @@ 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; }; @@ -284,6 +286,7 @@ struct mlxsw_sp_port_vlan { /* No need an internal lock; At worse - miss a single periodic iteration */ struct mlxsw_sp_port_xstats { u64 ecn; + u64 tc_ecn[TC_MAX_QUEUE]; u64 wred_drop[TC_MAX_QUEUE]; u64 tail_drop[TC_MAX_QUEUE]; u64 backlog[TC_MAX_QUEUE]; @@ -345,7 +348,6 @@ 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 +749,7 @@ 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 +761,7 @@ 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; @@ -1193,6 +1197,8 @@ int mlxsw_sp_setup_tc_fifo(struct mlxsw_sp_port *mlxsw_sp_port, struct tc_fifo_qopt_offload *p); int mlxsw_sp_setup_tc_block_qevent_early_drop(struct mlxsw_sp_port *mlxsw_sp_port, struct flow_block_offload *f); +int mlxsw_sp_setup_tc_block_qevent_mark(struct mlxsw_sp_port *mlxsw_sp_port, + struct flow_block_offload *f); /* spectrum_fid.c */ bool mlxsw_sp_fid_is_dummy(struct mlxsw_sp *mlxsw_sp, u16 fid_index); 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_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c index ded4cf658680..4b713832fdd5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c @@ -119,7 +119,6 @@ mlxsw_sp_acl_atcam_region_12kb_init(struct mlxsw_sp_acl_atcam_region *aregion) { struct mlxsw_sp *mlxsw_sp = aregion->region->mlxsw_sp; struct mlxsw_sp_acl_atcam_region_12kb *region_12kb; - size_t alloc_size; u64 max_lkey_id; int err; @@ -131,8 +130,7 @@ mlxsw_sp_acl_atcam_region_12kb_init(struct mlxsw_sp_acl_atcam_region *aregion) if (!region_12kb) return -ENOMEM; - alloc_size = BITS_TO_LONGS(max_lkey_id) * sizeof(unsigned long); - region_12kb->used_lkey_id = kzalloc(alloc_size, GFP_KERNEL); + region_12kb->used_lkey_id = bitmap_zalloc(max_lkey_id, GFP_KERNEL); if (!region_12kb->used_lkey_id) { err = -ENOMEM; goto err_used_lkey_id_alloc; @@ -149,7 +147,7 @@ mlxsw_sp_acl_atcam_region_12kb_init(struct mlxsw_sp_acl_atcam_region *aregion) return 0; err_rhashtable_init: - kfree(region_12kb->used_lkey_id); + bitmap_free(region_12kb->used_lkey_id); err_used_lkey_id_alloc: kfree(region_12kb); return err; @@ -161,7 +159,7 @@ mlxsw_sp_acl_atcam_region_12kb_fini(struct mlxsw_sp_acl_atcam_region *aregion) struct mlxsw_sp_acl_atcam_region_12kb *region_12kb = aregion->priv; rhashtable_destroy(®ion_12kb->lkey_ht); - kfree(region_12kb->used_lkey_id); + bitmap_free(region_12kb->used_lkey_id); kfree(region_12kb); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index 7cccc41dd69c..31f7f4c3acc3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -36,7 +36,6 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, u64 max_tcam_regions; u64 max_regions; u64 max_groups; - size_t alloc_size; int err; mutex_init(&tcam->lock); @@ -52,15 +51,13 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, if (max_tcam_regions < max_regions) max_regions = max_tcam_regions; - alloc_size = sizeof(tcam->used_regions[0]) * BITS_TO_LONGS(max_regions); - tcam->used_regions = kzalloc(alloc_size, GFP_KERNEL); + tcam->used_regions = bitmap_zalloc(max_regions, GFP_KERNEL); if (!tcam->used_regions) return -ENOMEM; tcam->max_regions = max_regions; max_groups = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_GROUPS); - alloc_size = sizeof(tcam->used_groups[0]) * BITS_TO_LONGS(max_groups); - tcam->used_groups = kzalloc(alloc_size, GFP_KERNEL); + tcam->used_groups = bitmap_zalloc(max_groups, GFP_KERNEL); if (!tcam->used_groups) { err = -ENOMEM; goto err_alloc_used_groups; @@ -76,9 +73,9 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, return 0; err_tcam_init: - kfree(tcam->used_groups); + bitmap_free(tcam->used_groups); err_alloc_used_groups: - kfree(tcam->used_regions); + bitmap_free(tcam->used_regions); return err; } @@ -89,8 +86,8 @@ void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, mutex_destroy(&tcam->lock); ops->fini(mlxsw_sp, tcam->priv); - kfree(tcam->used_groups); - kfree(tcam->used_regions); + bitmap_free(tcam->used_groups); + bitmap_free(tcam->used_regions); } int mlxsw_sp_acl_tcam_priority_get(struct mlxsw_sp *mlxsw_sp, 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_cnt.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c index b65b93a2b9bc..fc2257753b9b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c @@ -122,7 +122,6 @@ int mlxsw_sp_counter_pool_init(struct mlxsw_sp *mlxsw_sp) unsigned int sub_pools_count = ARRAY_SIZE(mlxsw_sp_counter_sub_pools); struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); struct mlxsw_sp_counter_pool *pool; - unsigned int map_size; int err; pool = kzalloc(struct_size(pool, sub_pools, sub_pools_count), @@ -143,9 +142,7 @@ int mlxsw_sp_counter_pool_init(struct mlxsw_sp *mlxsw_sp) devlink_resource_occ_get_register(devlink, MLXSW_SP_RESOURCE_COUNTERS, mlxsw_sp_counter_pool_occ_get, pool); - map_size = BITS_TO_LONGS(pool->pool_size) * sizeof(unsigned long); - - pool->usage = kzalloc(map_size, GFP_KERNEL); + pool->usage = bitmap_zalloc(pool->pool_size, GFP_KERNEL); if (!pool->usage) { err = -ENOMEM; goto err_usage_alloc; @@ -158,7 +155,7 @@ int mlxsw_sp_counter_pool_init(struct mlxsw_sp *mlxsw_sp) return 0; err_sub_pools_init: - kfree(pool->usage); + bitmap_free(pool->usage); err_usage_alloc: devlink_resource_occ_get_unregister(devlink, MLXSW_SP_RESOURCE_COUNTERS); @@ -176,7 +173,7 @@ void mlxsw_sp_counter_pool_fini(struct mlxsw_sp *mlxsw_sp) WARN_ON(find_first_bit(pool->usage, pool->pool_size) != pool->pool_size); WARN_ON(atomic_read(&pool->active_entries_count)); - kfree(pool->usage); + bitmap_free(pool->usage); devlink_resource_occ_get_unregister(devlink, MLXSW_SP_RESOURCE_COUNTERS); kfree(pool); 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_qdisc.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c index 9958d503bf0e..4243d3b883ff 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c @@ -50,12 +50,24 @@ struct mlxsw_sp_qdisc_ops { struct mlxsw_sp_qdisc *(*find_class)(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, u32 parent); unsigned int num_classes; + + u8 (*get_prio_bitmap)(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, + struct mlxsw_sp_qdisc *child); + int (*get_tclass_num)(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, + struct mlxsw_sp_qdisc *child); +}; + +struct mlxsw_sp_qdisc_ets_band { + u8 prio_bitmap; + int tclass_num; +}; + +struct mlxsw_sp_qdisc_ets_data { + struct mlxsw_sp_qdisc_ets_band bands[IEEE_8021QAZ_MAX_TCS]; }; struct mlxsw_sp_qdisc { u32 handle; - int tclass_num; - u8 prio_bitmap; union { struct red_stats red; } xstats_base; @@ -67,6 +79,10 @@ struct mlxsw_sp_qdisc { u64 backlog; } stats_base; + union { + struct mlxsw_sp_qdisc_ets_data *ets_data; + }; + struct mlxsw_sp_qdisc_ops *ops; struct mlxsw_sp_qdisc *parent; struct mlxsw_sp_qdisc *qdiscs; @@ -141,8 +157,7 @@ mlxsw_sp_qdisc_walk_cb_find(struct mlxsw_sp_qdisc *qdisc, void *data) } static struct mlxsw_sp_qdisc * -mlxsw_sp_qdisc_find(struct mlxsw_sp_port *mlxsw_sp_port, u32 parent, - bool root_only) +mlxsw_sp_qdisc_find(struct mlxsw_sp_port *mlxsw_sp_port, u32 parent) { struct mlxsw_sp_qdisc_state *qdisc_state = mlxsw_sp_port->qdisc; @@ -150,8 +165,6 @@ mlxsw_sp_qdisc_find(struct mlxsw_sp_port *mlxsw_sp_port, u32 parent, return NULL; if (parent == TC_H_ROOT) return &qdisc_state->root_qdisc; - if (root_only) - return NULL; return mlxsw_sp_qdisc_walk(&qdisc_state->root_qdisc, mlxsw_sp_qdisc_walk_cb_find, &parent); } @@ -187,6 +200,32 @@ mlxsw_sp_qdisc_reduce_parent_backlog(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc) tmp->stats_base.backlog -= mlxsw_sp_qdisc->stats_base.backlog; } +static u8 mlxsw_sp_qdisc_get_prio_bitmap(struct mlxsw_sp_port *mlxsw_sp_port, + struct mlxsw_sp_qdisc *mlxsw_sp_qdisc) +{ + struct mlxsw_sp_qdisc *parent = mlxsw_sp_qdisc->parent; + + if (!parent) + return 0xff; + if (!parent->ops->get_prio_bitmap) + return mlxsw_sp_qdisc_get_prio_bitmap(mlxsw_sp_port, parent); + return parent->ops->get_prio_bitmap(parent, mlxsw_sp_qdisc); +} + +#define MLXSW_SP_PORT_DEFAULT_TCLASS 0 + +static int mlxsw_sp_qdisc_get_tclass_num(struct mlxsw_sp_port *mlxsw_sp_port, + struct mlxsw_sp_qdisc *mlxsw_sp_qdisc) +{ + struct mlxsw_sp_qdisc *parent = mlxsw_sp_qdisc->parent; + + if (!parent) + return MLXSW_SP_PORT_DEFAULT_TCLASS; + if (!parent->ops->get_tclass_num) + return mlxsw_sp_qdisc_get_tclass_num(mlxsw_sp_port, parent); + return parent->ops->get_tclass_num(parent, mlxsw_sp_qdisc); +} + static int mlxsw_sp_qdisc_destroy(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_qdisc *mlxsw_sp_qdisc) @@ -194,6 +233,7 @@ mlxsw_sp_qdisc_destroy(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_qdisc *root_qdisc = &mlxsw_sp_port->qdisc->root_qdisc; int err_hdroom = 0; int err = 0; + int i; if (!mlxsw_sp_qdisc) return 0; @@ -211,6 +251,9 @@ mlxsw_sp_qdisc_destroy(struct mlxsw_sp_port *mlxsw_sp_port, if (!mlxsw_sp_qdisc->ops) return 0; + for (i = 0; i < mlxsw_sp_qdisc->num_classes; i++) + mlxsw_sp_qdisc_destroy(mlxsw_sp_port, + &mlxsw_sp_qdisc->qdiscs[i]); mlxsw_sp_qdisc_reduce_parent_backlog(mlxsw_sp_qdisc); if (mlxsw_sp_qdisc->ops->destroy) err = mlxsw_sp_qdisc->ops->destroy(mlxsw_sp_port, @@ -226,6 +269,87 @@ mlxsw_sp_qdisc_destroy(struct mlxsw_sp_port *mlxsw_sp_port, return err_hdroom ?: err; } +struct mlxsw_sp_qdisc_tree_validate { + bool forbid_ets; + bool forbid_root_tbf; + bool forbid_tbf; + bool forbid_red; +}; + +static int +__mlxsw_sp_qdisc_tree_validate(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, + struct mlxsw_sp_qdisc_tree_validate validate); + +static int +mlxsw_sp_qdisc_tree_validate_children(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, + struct mlxsw_sp_qdisc_tree_validate validate) +{ + unsigned int i; + int err; + + for (i = 0; i < mlxsw_sp_qdisc->num_classes; i++) { + err = __mlxsw_sp_qdisc_tree_validate(&mlxsw_sp_qdisc->qdiscs[i], + validate); + if (err) + return err; + } + + return 0; +} + +static int +__mlxsw_sp_qdisc_tree_validate(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, + struct mlxsw_sp_qdisc_tree_validate validate) +{ + if (!mlxsw_sp_qdisc->ops) + return 0; + + switch (mlxsw_sp_qdisc->ops->type) { + case MLXSW_SP_QDISC_FIFO: + break; + case MLXSW_SP_QDISC_RED: + if (validate.forbid_red) + return -EINVAL; + validate.forbid_red = true; + validate.forbid_root_tbf = true; + validate.forbid_ets = true; + break; + case MLXSW_SP_QDISC_TBF: + if (validate.forbid_root_tbf) { + if (validate.forbid_tbf) + return -EINVAL; + /* This is a TC TBF. */ + validate.forbid_tbf = true; + validate.forbid_ets = true; + } else { + /* This is root TBF. */ + validate.forbid_root_tbf = true; + } + break; + case MLXSW_SP_QDISC_PRIO: + case MLXSW_SP_QDISC_ETS: + if (validate.forbid_ets) + return -EINVAL; + validate.forbid_root_tbf = true; + validate.forbid_ets = true; + break; + default: + WARN_ON(1); + return -EINVAL; + } + + return mlxsw_sp_qdisc_tree_validate_children(mlxsw_sp_qdisc, validate); +} + +static int mlxsw_sp_qdisc_tree_validate(struct mlxsw_sp_port *mlxsw_sp_port) +{ + struct mlxsw_sp_qdisc_tree_validate validate = {}; + struct mlxsw_sp_qdisc *mlxsw_sp_qdisc; + + mlxsw_sp_qdisc = &mlxsw_sp_port->qdisc->root_qdisc; + return __mlxsw_sp_qdisc_tree_validate(mlxsw_sp_qdisc, validate); +} + static int mlxsw_sp_qdisc_create(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle, struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, @@ -268,6 +392,10 @@ static int mlxsw_sp_qdisc_create(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_sp_qdisc->num_classes = ops->num_classes; mlxsw_sp_qdisc->ops = ops; mlxsw_sp_qdisc->handle = handle; + err = mlxsw_sp_qdisc_tree_validate(mlxsw_sp_port); + if (err) + goto err_replace; + err = ops->replace(mlxsw_sp_port, handle, mlxsw_sp_qdisc, params); if (err) goto err_replace; @@ -406,13 +534,17 @@ mlxsw_sp_qdisc_collect_tc_stats(struct mlxsw_sp_port *mlxsw_sp_port, u64 *p_tx_bytes, u64 *p_tx_packets, u64 *p_drops, u64 *p_backlog) { - int tclass_num = mlxsw_sp_qdisc->tclass_num; struct mlxsw_sp_port_xstats *xstats; u64 tx_bytes, tx_packets; + u8 prio_bitmap; + int tclass_num; + prio_bitmap = mlxsw_sp_qdisc_get_prio_bitmap(mlxsw_sp_port, + mlxsw_sp_qdisc); + tclass_num = mlxsw_sp_qdisc_get_tclass_num(mlxsw_sp_port, + mlxsw_sp_qdisc); xstats = &mlxsw_sp_port->periodic_hw_stats.xstats; - mlxsw_sp_qdisc_bstats_per_priority_get(xstats, - mlxsw_sp_qdisc->prio_bitmap, + mlxsw_sp_qdisc_bstats_per_priority_get(xstats, prio_bitmap, &tx_packets, &tx_bytes); *p_tx_packets += tx_packets; @@ -506,19 +638,24 @@ static void mlxsw_sp_setup_tc_qdisc_red_clean_stats(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_qdisc *mlxsw_sp_qdisc) { - int tclass_num = mlxsw_sp_qdisc->tclass_num; struct mlxsw_sp_qdisc_stats *stats_base; struct mlxsw_sp_port_xstats *xstats; struct red_stats *red_base; + u8 prio_bitmap; + int tclass_num; + prio_bitmap = mlxsw_sp_qdisc_get_prio_bitmap(mlxsw_sp_port, + mlxsw_sp_qdisc); + tclass_num = mlxsw_sp_qdisc_get_tclass_num(mlxsw_sp_port, + mlxsw_sp_qdisc); xstats = &mlxsw_sp_port->periodic_hw_stats.xstats; stats_base = &mlxsw_sp_qdisc->stats_base; red_base = &mlxsw_sp_qdisc->xstats_base.red; - mlxsw_sp_qdisc_bstats_per_priority_get(xstats, - mlxsw_sp_qdisc->prio_bitmap, + mlxsw_sp_qdisc_bstats_per_priority_get(xstats, prio_bitmap, &stats_base->tx_packets, &stats_base->tx_bytes); + red_base->prob_mark = xstats->tc_ecn[tclass_num]; red_base->prob_drop = xstats->wred_drop[tclass_num]; red_base->pdrop = mlxsw_sp_xstats_tail_drop(xstats, tclass_num); @@ -532,8 +669,10 @@ static int mlxsw_sp_qdisc_red_destroy(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_qdisc *mlxsw_sp_qdisc) { - return mlxsw_sp_tclass_congestion_disable(mlxsw_sp_port, - mlxsw_sp_qdisc->tclass_num); + int tclass_num = mlxsw_sp_qdisc_get_tclass_num(mlxsw_sp_port, + mlxsw_sp_qdisc); + + return mlxsw_sp_tclass_congestion_disable(mlxsw_sp_port, tclass_num); } static int @@ -564,15 +703,33 @@ mlxsw_sp_qdisc_red_check_params(struct mlxsw_sp_port *mlxsw_sp_port, } static int +mlxsw_sp_qdisc_future_fifo_replace(struct mlxsw_sp_port *mlxsw_sp_port, + u32 handle, unsigned int band, + struct mlxsw_sp_qdisc *child_qdisc); +static void +mlxsw_sp_qdisc_future_fifos_init(struct mlxsw_sp_port *mlxsw_sp_port, + u32 handle); + +static int mlxsw_sp_qdisc_red_replace(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle, struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, void *params) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct tc_red_qopt_offload_params *p = params; - int tclass_num = mlxsw_sp_qdisc->tclass_num; + int tclass_num; u32 min, max; u64 prob; + int err; + + err = mlxsw_sp_qdisc_future_fifo_replace(mlxsw_sp_port, handle, 0, + &mlxsw_sp_qdisc->qdiscs[0]); + if (err) + return err; + mlxsw_sp_qdisc_future_fifos_init(mlxsw_sp_port, TC_H_UNSPEC); + + tclass_num = mlxsw_sp_qdisc_get_tclass_num(mlxsw_sp_port, + mlxsw_sp_qdisc); /* calculate probability in percentage */ prob = p->probability; @@ -615,22 +772,27 @@ mlxsw_sp_qdisc_get_red_xstats(struct mlxsw_sp_port *mlxsw_sp_port, void *xstats_ptr) { struct red_stats *xstats_base = &mlxsw_sp_qdisc->xstats_base.red; - int tclass_num = mlxsw_sp_qdisc->tclass_num; struct mlxsw_sp_port_xstats *xstats; struct red_stats *res = xstats_ptr; - int early_drops, pdrops; + int early_drops, marks, pdrops; + int tclass_num; + tclass_num = mlxsw_sp_qdisc_get_tclass_num(mlxsw_sp_port, + mlxsw_sp_qdisc); xstats = &mlxsw_sp_port->periodic_hw_stats.xstats; early_drops = xstats->wred_drop[tclass_num] - xstats_base->prob_drop; + marks = xstats->tc_ecn[tclass_num] - xstats_base->prob_mark; pdrops = mlxsw_sp_xstats_tail_drop(xstats, tclass_num) - xstats_base->pdrop; res->pdrop += pdrops; res->prob_drop += early_drops; + res->prob_mark += marks; xstats_base->pdrop += pdrops; xstats_base->prob_drop += early_drops; + xstats_base->prob_mark += marks; return 0; } @@ -639,16 +801,19 @@ mlxsw_sp_qdisc_get_red_stats(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, struct tc_qopt_offload_stats *stats_ptr) { - int tclass_num = mlxsw_sp_qdisc->tclass_num; struct mlxsw_sp_qdisc_stats *stats_base; struct mlxsw_sp_port_xstats *xstats; u64 overlimits; + int tclass_num; + tclass_num = mlxsw_sp_qdisc_get_tclass_num(mlxsw_sp_port, + mlxsw_sp_qdisc); xstats = &mlxsw_sp_port->periodic_hw_stats.xstats; stats_base = &mlxsw_sp_qdisc->stats_base; mlxsw_sp_qdisc_get_tc_stats(mlxsw_sp_port, mlxsw_sp_qdisc, stats_ptr); - overlimits = xstats->wred_drop[tclass_num] - stats_base->overlimits; + overlimits = xstats->wred_drop[tclass_num] + + xstats->tc_ecn[tclass_num] - stats_base->overlimits; stats_ptr->qstats->overlimits += overlimits; stats_base->overlimits += overlimits; @@ -660,11 +825,12 @@ static struct mlxsw_sp_qdisc * mlxsw_sp_qdisc_leaf_find_class(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, u32 parent) { - return NULL; + /* RED and TBF are formally classful qdiscs, but all class references, + * including X:0, just refer to the same one class. + */ + return &mlxsw_sp_qdisc->qdiscs[0]; } -#define MLXSW_SP_PORT_DEFAULT_TCLASS 0 - static struct mlxsw_sp_qdisc_ops mlxsw_sp_qdisc_ops_red = { .type = MLXSW_SP_QDISC_RED, .check_params = mlxsw_sp_qdisc_red_check_params, @@ -675,14 +841,19 @@ static struct mlxsw_sp_qdisc_ops mlxsw_sp_qdisc_ops_red = { .get_xstats = mlxsw_sp_qdisc_get_red_xstats, .clean_stats = mlxsw_sp_setup_tc_qdisc_red_clean_stats, .find_class = mlxsw_sp_qdisc_leaf_find_class, + .num_classes = 1, }; +static int mlxsw_sp_qdisc_graft(struct mlxsw_sp_port *mlxsw_sp_port, + struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, + u8 band, u32 child_handle); + static int __mlxsw_sp_setup_tc_red(struct mlxsw_sp_port *mlxsw_sp_port, struct tc_red_qopt_offload *p) { struct mlxsw_sp_qdisc *mlxsw_sp_qdisc; - mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent, false); + mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent); if (!mlxsw_sp_qdisc) return -EOPNOTSUPP; @@ -704,6 +875,9 @@ static int __mlxsw_sp_setup_tc_red(struct mlxsw_sp_port *mlxsw_sp_port, case TC_RED_STATS: return mlxsw_sp_qdisc_get_stats(mlxsw_sp_port, mlxsw_sp_qdisc, &p->stats); + case TC_RED_GRAFT: + return mlxsw_sp_qdisc_graft(mlxsw_sp_port, mlxsw_sp_qdisc, 0, + p->child_handle); default: return -EOPNOTSUPP; } @@ -740,13 +914,34 @@ mlxsw_sp_setup_tc_qdisc_leaf_clean_stats(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_sp_qdisc->stats_base.backlog = 0; } +static enum mlxsw_reg_qeec_hr +mlxsw_sp_qdisc_tbf_hr(struct mlxsw_sp_port *mlxsw_sp_port, + struct mlxsw_sp_qdisc *mlxsw_sp_qdisc) +{ + if (mlxsw_sp_qdisc == &mlxsw_sp_port->qdisc->root_qdisc) + return MLXSW_REG_QEEC_HR_PORT; + + /* Configure subgroup shaper, so that both UC and MC traffic is subject + * to shaping. That is unlike RED, however UC queue lengths are going to + * be different than MC ones due to different pool and quota + * configurations, so the configuration is not applicable. For shaper on + * the other hand, subjecting the overall stream to the configured + * shaper makes sense. Also note that that is what we do for + * ieee_setmaxrate(). + */ + return MLXSW_REG_QEEC_HR_SUBGROUP; +} + static int mlxsw_sp_qdisc_tbf_destroy(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_qdisc *mlxsw_sp_qdisc) { - return mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port, - MLXSW_REG_QEEC_HR_SUBGROUP, - mlxsw_sp_qdisc->tclass_num, 0, + enum mlxsw_reg_qeec_hr hr = mlxsw_sp_qdisc_tbf_hr(mlxsw_sp_port, + mlxsw_sp_qdisc); + int tclass_num = mlxsw_sp_qdisc_get_tclass_num(mlxsw_sp_port, + mlxsw_sp_qdisc); + + return mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port, hr, tclass_num, 0, MLXSW_REG_QEEC_MAS_DIS, 0); } @@ -828,27 +1023,29 @@ mlxsw_sp_qdisc_tbf_replace(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle, struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, void *params) { + enum mlxsw_reg_qeec_hr hr = mlxsw_sp_qdisc_tbf_hr(mlxsw_sp_port, + mlxsw_sp_qdisc); struct tc_tbf_qopt_offload_replace_params *p = params; u64 rate_kbps = mlxsw_sp_qdisc_tbf_rate_kbps(p); + int tclass_num; u8 burst_size; int err; + err = mlxsw_sp_qdisc_future_fifo_replace(mlxsw_sp_port, handle, 0, + &mlxsw_sp_qdisc->qdiscs[0]); + if (err) + return err; + mlxsw_sp_qdisc_future_fifos_init(mlxsw_sp_port, TC_H_UNSPEC); + + tclass_num = mlxsw_sp_qdisc_get_tclass_num(mlxsw_sp_port, + mlxsw_sp_qdisc); + err = mlxsw_sp_qdisc_tbf_bs(mlxsw_sp_port, p->max_size, &burst_size); if (WARN_ON_ONCE(err)) /* check_params above was supposed to reject this value. */ return -EINVAL; - /* Configure subgroup shaper, so that both UC and MC traffic is subject - * to shaping. That is unlike RED, however UC queue lengths are going to - * be different than MC ones due to different pool and quota - * configurations, so the configuration is not applicable. For shaper on - * the other hand, subjecting the overall stream to the configured - * shaper makes sense. Also note that that is what we do for - * ieee_setmaxrate(). - */ - return mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port, - MLXSW_REG_QEEC_HR_SUBGROUP, - mlxsw_sp_qdisc->tclass_num, 0, + return mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port, hr, tclass_num, 0, rate_kbps, burst_size); } @@ -881,6 +1078,7 @@ static struct mlxsw_sp_qdisc_ops mlxsw_sp_qdisc_ops_tbf = { .get_stats = mlxsw_sp_qdisc_get_tbf_stats, .clean_stats = mlxsw_sp_setup_tc_qdisc_leaf_clean_stats, .find_class = mlxsw_sp_qdisc_leaf_find_class, + .num_classes = 1, }; static int __mlxsw_sp_setup_tc_tbf(struct mlxsw_sp_port *mlxsw_sp_port, @@ -888,7 +1086,7 @@ static int __mlxsw_sp_setup_tc_tbf(struct mlxsw_sp_port *mlxsw_sp_port, { struct mlxsw_sp_qdisc *mlxsw_sp_qdisc; - mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent, false); + mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent); if (!mlxsw_sp_qdisc) return -EOPNOTSUPP; @@ -907,6 +1105,9 @@ static int __mlxsw_sp_setup_tc_tbf(struct mlxsw_sp_port *mlxsw_sp_port, case TC_TBF_STATS: return mlxsw_sp_qdisc_get_stats(mlxsw_sp_port, mlxsw_sp_qdisc, &p->stats); + case TC_TBF_GRAFT: + return mlxsw_sp_qdisc_graft(mlxsw_sp_port, mlxsw_sp_qdisc, 0, + p->child_handle); default: return -EOPNOTSUPP; } @@ -957,6 +1158,32 @@ static struct mlxsw_sp_qdisc_ops mlxsw_sp_qdisc_ops_fifo = { .clean_stats = mlxsw_sp_setup_tc_qdisc_leaf_clean_stats, }; +static int +mlxsw_sp_qdisc_future_fifo_replace(struct mlxsw_sp_port *mlxsw_sp_port, + u32 handle, unsigned int band, + struct mlxsw_sp_qdisc *child_qdisc) +{ + struct mlxsw_sp_qdisc_state *qdisc_state = mlxsw_sp_port->qdisc; + + if (handle == qdisc_state->future_handle && + qdisc_state->future_fifos[band]) + return mlxsw_sp_qdisc_replace(mlxsw_sp_port, TC_H_UNSPEC, + child_qdisc, + &mlxsw_sp_qdisc_ops_fifo, + NULL); + return 0; +} + +static void +mlxsw_sp_qdisc_future_fifos_init(struct mlxsw_sp_port *mlxsw_sp_port, + u32 handle) +{ + struct mlxsw_sp_qdisc_state *qdisc_state = mlxsw_sp_port->qdisc; + + qdisc_state->future_handle = handle; + memset(qdisc_state->future_fifos, 0, sizeof(qdisc_state->future_fifos)); +} + static int __mlxsw_sp_setup_tc_fifo(struct mlxsw_sp_port *mlxsw_sp_port, struct tc_fifo_qopt_offload *p) { @@ -965,16 +1192,15 @@ static int __mlxsw_sp_setup_tc_fifo(struct mlxsw_sp_port *mlxsw_sp_port, unsigned int band; u32 parent_handle; - mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent, false); + mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent); if (!mlxsw_sp_qdisc && p->handle == TC_H_UNSPEC) { parent_handle = TC_H_MAJ(p->parent); if (parent_handle != qdisc_state->future_handle) { /* This notifications is for a different Qdisc than * previously. Wipe the future cache. */ - memset(qdisc_state->future_fifos, 0, - sizeof(qdisc_state->future_fifos)); - qdisc_state->future_handle = parent_handle; + mlxsw_sp_qdisc_future_fifos_init(mlxsw_sp_port, + parent_handle); } band = TC_H_MIN(p->parent) - 1; @@ -1033,11 +1259,10 @@ static int __mlxsw_sp_qdisc_ets_destroy(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_sp_port_ets_set(mlxsw_sp_port, MLXSW_REG_QEEC_HR_SUBGROUP, i, 0, false, 0); - mlxsw_sp_qdisc_destroy(mlxsw_sp_port, - &mlxsw_sp_qdisc->qdiscs[i]); - mlxsw_sp_qdisc->qdiscs[i].prio_bitmap = 0; } + kfree(mlxsw_sp_qdisc->ets_data); + mlxsw_sp_qdisc->ets_data = NULL; return 0; } @@ -1066,6 +1291,31 @@ mlxsw_sp_qdisc_prio_check_params(struct mlxsw_sp_port *mlxsw_sp_port, return __mlxsw_sp_qdisc_ets_check_params(p->bands); } +static struct mlxsw_sp_qdisc * +mlxsw_sp_qdisc_walk_cb_clean_stats(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, + void *mlxsw_sp_port) +{ + u64 backlog; + + if (mlxsw_sp_qdisc->ops) { + backlog = mlxsw_sp_qdisc->stats_base.backlog; + if (mlxsw_sp_qdisc->ops->clean_stats) + mlxsw_sp_qdisc->ops->clean_stats(mlxsw_sp_port, + mlxsw_sp_qdisc); + mlxsw_sp_qdisc->stats_base.backlog = backlog; + } + + return NULL; +} + +static void +mlxsw_sp_qdisc_tree_clean_stats(struct mlxsw_sp_port *mlxsw_sp_port, + struct mlxsw_sp_qdisc *mlxsw_sp_qdisc) +{ + mlxsw_sp_qdisc_walk(mlxsw_sp_qdisc, mlxsw_sp_qdisc_walk_cb_clean_stats, + mlxsw_sp_port); +} + static int __mlxsw_sp_qdisc_ets_replace(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, @@ -1074,69 +1324,80 @@ __mlxsw_sp_qdisc_ets_replace(struct mlxsw_sp_port *mlxsw_sp_port, const unsigned int *weights, const u8 *priomap) { - struct mlxsw_sp_qdisc_state *qdisc_state = mlxsw_sp_port->qdisc; + struct mlxsw_sp_qdisc_ets_data *ets_data = mlxsw_sp_qdisc->ets_data; + struct mlxsw_sp_qdisc_ets_band *ets_band; struct mlxsw_sp_qdisc *child_qdisc; - int tclass, i, band, backlog; - u8 old_priomap; + u8 old_priomap, new_priomap; + int i, band; int err; + if (!ets_data) { + ets_data = kzalloc(sizeof(*ets_data), GFP_KERNEL); + if (!ets_data) + return -ENOMEM; + mlxsw_sp_qdisc->ets_data = ets_data; + + for (band = 0; band < mlxsw_sp_qdisc->num_classes; band++) { + int tclass_num = MLXSW_SP_PRIO_BAND_TO_TCLASS(band); + + ets_band = &ets_data->bands[band]; + ets_band->tclass_num = tclass_num; + } + } + for (band = 0; band < nbands; band++) { - tclass = MLXSW_SP_PRIO_BAND_TO_TCLASS(band); + int tclass_num; + child_qdisc = &mlxsw_sp_qdisc->qdiscs[band]; - old_priomap = child_qdisc->prio_bitmap; - child_qdisc->prio_bitmap = 0; + ets_band = &ets_data->bands[band]; + + tclass_num = ets_band->tclass_num; + old_priomap = ets_band->prio_bitmap; + new_priomap = 0; err = mlxsw_sp_port_ets_set(mlxsw_sp_port, MLXSW_REG_QEEC_HR_SUBGROUP, - tclass, 0, !!quanta[band], + tclass_num, 0, !!quanta[band], weights[band]); if (err) return err; for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { if (priomap[i] == band) { - child_qdisc->prio_bitmap |= BIT(i); + new_priomap |= BIT(i); if (BIT(i) & old_priomap) continue; err = mlxsw_sp_port_prio_tc_set(mlxsw_sp_port, - i, tclass); + i, tclass_num); if (err) return err; } } - child_qdisc->tclass_num = tclass; + ets_band->prio_bitmap = new_priomap; - if (old_priomap != child_qdisc->prio_bitmap && - child_qdisc->ops && child_qdisc->ops->clean_stats) { - backlog = child_qdisc->stats_base.backlog; - child_qdisc->ops->clean_stats(mlxsw_sp_port, - child_qdisc); - child_qdisc->stats_base.backlog = backlog; - } + if (old_priomap != new_priomap) + mlxsw_sp_qdisc_tree_clean_stats(mlxsw_sp_port, + child_qdisc); - if (handle == qdisc_state->future_handle && - qdisc_state->future_fifos[band]) { - err = mlxsw_sp_qdisc_replace(mlxsw_sp_port, TC_H_UNSPEC, - child_qdisc, - &mlxsw_sp_qdisc_ops_fifo, - NULL); - if (err) - return err; - } + err = mlxsw_sp_qdisc_future_fifo_replace(mlxsw_sp_port, handle, + band, child_qdisc); + if (err) + return err; } for (; band < IEEE_8021QAZ_MAX_TCS; band++) { - tclass = MLXSW_SP_PRIO_BAND_TO_TCLASS(band); + ets_band = &ets_data->bands[band]; + ets_band->prio_bitmap = 0; + child_qdisc = &mlxsw_sp_qdisc->qdiscs[band]; - child_qdisc->prio_bitmap = 0; mlxsw_sp_qdisc_destroy(mlxsw_sp_port, child_qdisc); + mlxsw_sp_port_ets_set(mlxsw_sp_port, MLXSW_REG_QEEC_HR_SUBGROUP, - tclass, 0, false, 0); + ets_band->tclass_num, 0, false, 0); } - qdisc_state->future_handle = TC_H_UNSPEC; - memset(qdisc_state->future_fifos, 0, sizeof(qdisc_state->future_fifos)); + mlxsw_sp_qdisc_future_fifos_init(mlxsw_sp_port, TC_H_UNSPEC); return 0; } @@ -1238,6 +1499,31 @@ mlxsw_sp_qdisc_prio_find_class(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, return &mlxsw_sp_qdisc->qdiscs[band]; } +static struct mlxsw_sp_qdisc_ets_band * +mlxsw_sp_qdisc_ets_get_band(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, + struct mlxsw_sp_qdisc *child) +{ + unsigned int band = child - mlxsw_sp_qdisc->qdiscs; + + if (WARN_ON(band >= IEEE_8021QAZ_MAX_TCS)) + band = 0; + return &mlxsw_sp_qdisc->ets_data->bands[band]; +} + +static u8 +mlxsw_sp_qdisc_ets_get_prio_bitmap(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, + struct mlxsw_sp_qdisc *child) +{ + return mlxsw_sp_qdisc_ets_get_band(mlxsw_sp_qdisc, child)->prio_bitmap; +} + +static int +mlxsw_sp_qdisc_ets_get_tclass_num(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, + struct mlxsw_sp_qdisc *child) +{ + return mlxsw_sp_qdisc_ets_get_band(mlxsw_sp_qdisc, child)->tclass_num; +} + static struct mlxsw_sp_qdisc_ops mlxsw_sp_qdisc_ops_prio = { .type = MLXSW_SP_QDISC_PRIO, .check_params = mlxsw_sp_qdisc_prio_check_params, @@ -1248,6 +1534,8 @@ static struct mlxsw_sp_qdisc_ops mlxsw_sp_qdisc_ops_prio = { .clean_stats = mlxsw_sp_setup_tc_qdisc_prio_clean_stats, .find_class = mlxsw_sp_qdisc_prio_find_class, .num_classes = IEEE_8021QAZ_MAX_TCS, + .get_prio_bitmap = mlxsw_sp_qdisc_ets_get_prio_bitmap, + .get_tclass_num = mlxsw_sp_qdisc_ets_get_tclass_num, }; static int @@ -1299,6 +1587,8 @@ static struct mlxsw_sp_qdisc_ops mlxsw_sp_qdisc_ops_ets = { .clean_stats = mlxsw_sp_setup_tc_qdisc_prio_clean_stats, .find_class = mlxsw_sp_qdisc_prio_find_class, .num_classes = IEEE_8021QAZ_MAX_TCS, + .get_prio_bitmap = mlxsw_sp_qdisc_ets_get_prio_bitmap, + .get_tclass_num = mlxsw_sp_qdisc_ets_get_tclass_num, }; /* Linux allows linking of Qdiscs to arbitrary classes (so long as the resulting @@ -1326,10 +1616,9 @@ static struct mlxsw_sp_qdisc_ops mlxsw_sp_qdisc_ops_ets = { * grafted corresponds to the parent handle. If the two don't match, we * unoffload the child. */ -static int -__mlxsw_sp_qdisc_ets_graft(struct mlxsw_sp_port *mlxsw_sp_port, - struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, - u8 band, u32 child_handle) +static int mlxsw_sp_qdisc_graft(struct mlxsw_sp_port *mlxsw_sp_port, + struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, + u8 band, u32 child_handle) { struct mlxsw_sp_qdisc *old_qdisc; u32 parent; @@ -1362,21 +1651,12 @@ __mlxsw_sp_qdisc_ets_graft(struct mlxsw_sp_port *mlxsw_sp_port, return -EOPNOTSUPP; } -static int -mlxsw_sp_qdisc_prio_graft(struct mlxsw_sp_port *mlxsw_sp_port, - struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, - struct tc_prio_qopt_offload_graft_params *p) -{ - return __mlxsw_sp_qdisc_ets_graft(mlxsw_sp_port, mlxsw_sp_qdisc, - p->band, p->child_handle); -} - static int __mlxsw_sp_setup_tc_prio(struct mlxsw_sp_port *mlxsw_sp_port, struct tc_prio_qopt_offload *p) { struct mlxsw_sp_qdisc *mlxsw_sp_qdisc; - mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent, true); + mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent); if (!mlxsw_sp_qdisc) return -EOPNOTSUPP; @@ -1396,8 +1676,9 @@ static int __mlxsw_sp_setup_tc_prio(struct mlxsw_sp_port *mlxsw_sp_port, return mlxsw_sp_qdisc_get_stats(mlxsw_sp_port, mlxsw_sp_qdisc, &p->stats); case TC_PRIO_GRAFT: - return mlxsw_sp_qdisc_prio_graft(mlxsw_sp_port, mlxsw_sp_qdisc, - &p->graft_params); + return mlxsw_sp_qdisc_graft(mlxsw_sp_port, mlxsw_sp_qdisc, + p->graft_params.band, + p->graft_params.child_handle); default: return -EOPNOTSUPP; } @@ -1420,7 +1701,7 @@ static int __mlxsw_sp_setup_tc_ets(struct mlxsw_sp_port *mlxsw_sp_port, { struct mlxsw_sp_qdisc *mlxsw_sp_qdisc; - mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent, true); + mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent); if (!mlxsw_sp_qdisc) return -EOPNOTSUPP; @@ -1440,9 +1721,9 @@ static int __mlxsw_sp_setup_tc_ets(struct mlxsw_sp_port *mlxsw_sp_port, return mlxsw_sp_qdisc_get_stats(mlxsw_sp_port, mlxsw_sp_qdisc, &p->stats); case TC_ETS_GRAFT: - return __mlxsw_sp_qdisc_ets_graft(mlxsw_sp_port, mlxsw_sp_qdisc, - p->graft_params.band, - p->graft_params.child_handle); + return mlxsw_sp_qdisc_graft(mlxsw_sp_port, mlxsw_sp_qdisc, + p->graft_params.band, + p->graft_params.child_handle); default: return -EOPNOTSUPP; } @@ -1472,6 +1753,7 @@ struct mlxsw_sp_qevent_binding { u32 handle; int tclass_num; enum mlxsw_sp_span_trigger span_trigger; + unsigned int action_mask; }; static LIST_HEAD(mlxsw_sp_qevent_block_cb_list); @@ -1482,8 +1764,10 @@ static int mlxsw_sp_qevent_span_configure(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_span_agent_parms *agent_parms, int *p_span_id) { + enum mlxsw_sp_span_trigger span_trigger = qevent_binding->span_trigger; struct mlxsw_sp_port *mlxsw_sp_port = qevent_binding->mlxsw_sp_port; struct mlxsw_sp_span_trigger_parms trigger_parms = {}; + bool ingress; int span_id; int err; @@ -1491,18 +1775,19 @@ static int mlxsw_sp_qevent_span_configure(struct mlxsw_sp *mlxsw_sp, if (err) return err; - err = mlxsw_sp_span_analyzed_port_get(mlxsw_sp_port, true); + ingress = mlxsw_sp_span_trigger_is_ingress(span_trigger); + err = mlxsw_sp_span_analyzed_port_get(mlxsw_sp_port, ingress); if (err) goto err_analyzed_port_get; trigger_parms.span_id = span_id; trigger_parms.probability_rate = 1; - err = mlxsw_sp_span_agent_bind(mlxsw_sp, qevent_binding->span_trigger, mlxsw_sp_port, + err = mlxsw_sp_span_agent_bind(mlxsw_sp, span_trigger, mlxsw_sp_port, &trigger_parms); if (err) goto err_agent_bind; - err = mlxsw_sp_span_trigger_enable(mlxsw_sp_port, qevent_binding->span_trigger, + err = mlxsw_sp_span_trigger_enable(mlxsw_sp_port, span_trigger, qevent_binding->tclass_num); if (err) goto err_trigger_enable; @@ -1511,10 +1796,10 @@ static int mlxsw_sp_qevent_span_configure(struct mlxsw_sp *mlxsw_sp, return 0; err_trigger_enable: - mlxsw_sp_span_agent_unbind(mlxsw_sp, qevent_binding->span_trigger, mlxsw_sp_port, + mlxsw_sp_span_agent_unbind(mlxsw_sp, span_trigger, mlxsw_sp_port, &trigger_parms); err_agent_bind: - mlxsw_sp_span_analyzed_port_put(mlxsw_sp_port, true); + mlxsw_sp_span_analyzed_port_put(mlxsw_sp_port, ingress); err_analyzed_port_get: mlxsw_sp_span_agent_put(mlxsw_sp, span_id); return err; @@ -1524,16 +1809,20 @@ static void mlxsw_sp_qevent_span_deconfigure(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_qevent_binding *qevent_binding, int span_id) { + enum mlxsw_sp_span_trigger span_trigger = qevent_binding->span_trigger; struct mlxsw_sp_port *mlxsw_sp_port = qevent_binding->mlxsw_sp_port; struct mlxsw_sp_span_trigger_parms trigger_parms = { .span_id = span_id, }; + bool ingress; + + ingress = mlxsw_sp_span_trigger_is_ingress(span_trigger); - mlxsw_sp_span_trigger_disable(mlxsw_sp_port, qevent_binding->span_trigger, + mlxsw_sp_span_trigger_disable(mlxsw_sp_port, span_trigger, qevent_binding->tclass_num); - mlxsw_sp_span_agent_unbind(mlxsw_sp, qevent_binding->span_trigger, mlxsw_sp_port, + mlxsw_sp_span_agent_unbind(mlxsw_sp, span_trigger, mlxsw_sp_port, &trigger_parms); - mlxsw_sp_span_analyzed_port_put(mlxsw_sp_port, true); + mlxsw_sp_span_analyzed_port_put(mlxsw_sp_port, ingress); mlxsw_sp_span_agent_put(mlxsw_sp, span_id); } @@ -1583,10 +1872,17 @@ static void mlxsw_sp_qevent_trap_deconfigure(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_qevent_span_deconfigure(mlxsw_sp, qevent_binding, mall_entry->trap.span_id); } -static int mlxsw_sp_qevent_entry_configure(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_mall_entry *mall_entry, - struct mlxsw_sp_qevent_binding *qevent_binding) +static int +mlxsw_sp_qevent_entry_configure(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_mall_entry *mall_entry, + struct mlxsw_sp_qevent_binding *qevent_binding, + struct netlink_ext_ack *extack) { + if (!(BIT(mall_entry->type) & qevent_binding->action_mask)) { + NL_SET_ERR_MSG(extack, "Action not supported at this qevent"); + return -EOPNOTSUPP; + } + switch (mall_entry->type) { case MLXSW_SP_MALL_ACTION_TYPE_MIRROR: return mlxsw_sp_qevent_mirror_configure(mlxsw_sp, mall_entry, qevent_binding); @@ -1614,15 +1910,17 @@ static void mlxsw_sp_qevent_entry_deconfigure(struct mlxsw_sp *mlxsw_sp, } } -static int mlxsw_sp_qevent_binding_configure(struct mlxsw_sp_qevent_block *qevent_block, - struct mlxsw_sp_qevent_binding *qevent_binding) +static int +mlxsw_sp_qevent_binding_configure(struct mlxsw_sp_qevent_block *qevent_block, + struct mlxsw_sp_qevent_binding *qevent_binding, + struct netlink_ext_ack *extack) { struct mlxsw_sp_mall_entry *mall_entry; int err; list_for_each_entry(mall_entry, &qevent_block->mall_entry_list, list) { err = mlxsw_sp_qevent_entry_configure(qevent_block->mlxsw_sp, mall_entry, - qevent_binding); + qevent_binding, extack); if (err) goto err_entry_configure; } @@ -1646,13 +1944,17 @@ static void mlxsw_sp_qevent_binding_deconfigure(struct mlxsw_sp_qevent_block *qe qevent_binding); } -static int mlxsw_sp_qevent_block_configure(struct mlxsw_sp_qevent_block *qevent_block) +static int +mlxsw_sp_qevent_block_configure(struct mlxsw_sp_qevent_block *qevent_block, + struct netlink_ext_ack *extack) { struct mlxsw_sp_qevent_binding *qevent_binding; int err; list_for_each_entry(qevent_binding, &qevent_block->binding_list, list) { - err = mlxsw_sp_qevent_binding_configure(qevent_block, qevent_binding); + err = mlxsw_sp_qevent_binding_configure(qevent_block, + qevent_binding, + extack); if (err) goto err_binding_configure; } @@ -1737,7 +2039,7 @@ static int mlxsw_sp_qevent_mall_replace(struct mlxsw_sp *mlxsw_sp, list_add_tail(&mall_entry->list, &qevent_block->mall_entry_list); - err = mlxsw_sp_qevent_block_configure(qevent_block); + err = mlxsw_sp_qevent_block_configure(qevent_block, f->common.extack); if (err) goto err_block_configure; @@ -1825,7 +2127,8 @@ static void mlxsw_sp_qevent_block_release(void *cb_priv) static struct mlxsw_sp_qevent_binding * mlxsw_sp_qevent_binding_create(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle, int tclass_num, - enum mlxsw_sp_span_trigger span_trigger) + enum mlxsw_sp_span_trigger span_trigger, + unsigned int action_mask) { struct mlxsw_sp_qevent_binding *binding; @@ -1837,6 +2140,7 @@ mlxsw_sp_qevent_binding_create(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle, binding->handle = handle; binding->tclass_num = tclass_num; binding->span_trigger = span_trigger; + binding->action_mask = action_mask; return binding; } @@ -1862,9 +2166,11 @@ mlxsw_sp_qevent_binding_lookup(struct mlxsw_sp_qevent_block *block, return NULL; } -static int mlxsw_sp_setup_tc_block_qevent_bind(struct mlxsw_sp_port *mlxsw_sp_port, - struct flow_block_offload *f, - enum mlxsw_sp_span_trigger span_trigger) +static int +mlxsw_sp_setup_tc_block_qevent_bind(struct mlxsw_sp_port *mlxsw_sp_port, + struct flow_block_offload *f, + enum mlxsw_sp_span_trigger span_trigger, + unsigned int action_mask) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct mlxsw_sp_qevent_binding *qevent_binding; @@ -1872,6 +2178,7 @@ static int mlxsw_sp_setup_tc_block_qevent_bind(struct mlxsw_sp_port *mlxsw_sp_po struct flow_block_cb *block_cb; struct mlxsw_sp_qdisc *qdisc; bool register_block = false; + int tclass_num; int err; block_cb = flow_block_cb_lookup(f->block, mlxsw_sp_qevent_block_cb, mlxsw_sp); @@ -1904,14 +2211,19 @@ static int mlxsw_sp_setup_tc_block_qevent_bind(struct mlxsw_sp_port *mlxsw_sp_po goto err_binding_exists; } - qevent_binding = mlxsw_sp_qevent_binding_create(mlxsw_sp_port, f->sch->handle, - qdisc->tclass_num, span_trigger); + tclass_num = mlxsw_sp_qdisc_get_tclass_num(mlxsw_sp_port, qdisc); + qevent_binding = mlxsw_sp_qevent_binding_create(mlxsw_sp_port, + f->sch->handle, + tclass_num, + span_trigger, + action_mask); if (IS_ERR(qevent_binding)) { err = PTR_ERR(qevent_binding); goto err_binding_create; } - err = mlxsw_sp_qevent_binding_configure(qevent_block, qevent_binding); + err = mlxsw_sp_qevent_binding_configure(qevent_block, qevent_binding, + f->extack); if (err) goto err_binding_configure; @@ -1963,15 +2275,19 @@ static void mlxsw_sp_setup_tc_block_qevent_unbind(struct mlxsw_sp_port *mlxsw_sp } } -static int mlxsw_sp_setup_tc_block_qevent(struct mlxsw_sp_port *mlxsw_sp_port, - struct flow_block_offload *f, - enum mlxsw_sp_span_trigger span_trigger) +static int +mlxsw_sp_setup_tc_block_qevent(struct mlxsw_sp_port *mlxsw_sp_port, + struct flow_block_offload *f, + enum mlxsw_sp_span_trigger span_trigger, + unsigned int action_mask) { f->driver_block_list = &mlxsw_sp_qevent_block_cb_list; switch (f->command) { case FLOW_BLOCK_BIND: - return mlxsw_sp_setup_tc_block_qevent_bind(mlxsw_sp_port, f, span_trigger); + return mlxsw_sp_setup_tc_block_qevent_bind(mlxsw_sp_port, f, + span_trigger, + action_mask); case FLOW_BLOCK_UNBIND: mlxsw_sp_setup_tc_block_qevent_unbind(mlxsw_sp_port, f, span_trigger); return 0; @@ -1983,7 +2299,22 @@ static int mlxsw_sp_setup_tc_block_qevent(struct mlxsw_sp_port *mlxsw_sp_port, int mlxsw_sp_setup_tc_block_qevent_early_drop(struct mlxsw_sp_port *mlxsw_sp_port, struct flow_block_offload *f) { - return mlxsw_sp_setup_tc_block_qevent(mlxsw_sp_port, f, MLXSW_SP_SPAN_TRIGGER_EARLY_DROP); + unsigned int action_mask = BIT(MLXSW_SP_MALL_ACTION_TYPE_MIRROR) | + BIT(MLXSW_SP_MALL_ACTION_TYPE_TRAP); + + return mlxsw_sp_setup_tc_block_qevent(mlxsw_sp_port, f, + MLXSW_SP_SPAN_TRIGGER_EARLY_DROP, + action_mask); +} + +int mlxsw_sp_setup_tc_block_qevent_mark(struct mlxsw_sp_port *mlxsw_sp_port, + struct flow_block_offload *f) +{ + unsigned int action_mask = BIT(MLXSW_SP_MALL_ACTION_TYPE_MIRROR); + + return mlxsw_sp_setup_tc_block_qevent(mlxsw_sp_port, f, + MLXSW_SP_SPAN_TRIGGER_ECN, + action_mask); } int mlxsw_sp_tc_qdisc_init(struct mlxsw_sp_port *mlxsw_sp_port) @@ -1995,8 +2326,6 @@ int mlxsw_sp_tc_qdisc_init(struct mlxsw_sp_port *mlxsw_sp_port) return -ENOMEM; mutex_init(&qdisc_state->lock); - qdisc_state->root_qdisc.prio_bitmap = 0xff; - qdisc_state->root_qdisc.tclass_num = MLXSW_SP_PORT_DEFAULT_TCLASS; mlxsw_sp_port->qdisc = qdisc_state; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 19bb3ca0515e..217e3b351dfe 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -57,6 +57,7 @@ struct mlxsw_sp_rif { unsigned char addr[ETH_ALEN]; int mtu; u16 rif_index; + u8 mac_profile_id; u16 vr_id; const struct mlxsw_sp_rif_ops *ops; struct mlxsw_sp *mlxsw_sp; @@ -106,15 +107,23 @@ struct mlxsw_sp_rif_ops { void (*setup)(struct mlxsw_sp_rif *rif, const struct mlxsw_sp_rif_params *params); - int (*configure)(struct mlxsw_sp_rif *rif); + int (*configure)(struct mlxsw_sp_rif *rif, + struct netlink_ext_ack *extack); void (*deconfigure)(struct mlxsw_sp_rif *rif); struct mlxsw_sp_fid * (*fid_get)(struct mlxsw_sp_rif *rif, struct netlink_ext_ack *extack); void (*fdb_del)(struct mlxsw_sp_rif *rif, const char *mac); }; +struct mlxsw_sp_rif_mac_profile { + unsigned char mac_prefix[ETH_ALEN]; + refcount_t ref_count; + u8 id; +}; + 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 +1064,13 @@ 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 +1116,7 @@ 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 +1132,30 @@ 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 +1179,32 @@ 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 +1218,32 @@ 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 +1354,11 @@ 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 +1395,7 @@ 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 +1500,7 @@ 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 +1586,34 @@ 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 +1888,7 @@ 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 +4213,7 @@ 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 +4437,66 @@ 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 +4911,9 @@ 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 +4932,8 @@ 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 +4958,7 @@ 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 +5350,9 @@ 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 +5360,8 @@ 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 +5379,7 @@ 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 +5858,6 @@ 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 +5870,6 @@ 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 +5880,8 @@ 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 +6130,8 @@ 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 +6142,13 @@ 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 +6209,7 @@ 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 +6742,9 @@ 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 +6752,8 @@ 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 +6771,7 @@ 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 +6995,38 @@ 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 +7036,8 @@ 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 +7095,16 @@ 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 +7123,19 @@ 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 +7488,6 @@ 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 { @@ -8056,7 +8194,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, if (ops->setup) ops->setup(rif, params); - err = ops->configure(rif); + err = ops->configure(rif, extack); if (err) goto err_configure; @@ -8175,6 +8313,200 @@ static void mlxsw_sp_rif_subport_put(struct mlxsw_sp_rif *rif) mlxsw_sp_rif_destroy(rif); } +static int mlxsw_sp_rif_mac_profile_index_alloc(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_rif_mac_profile *profile, + struct netlink_ext_ack *extack) +{ + u8 max_rif_mac_profiles = mlxsw_sp->router->max_rif_mac_profile; + struct mlxsw_sp_router *router = mlxsw_sp->router; + int id; + + id = idr_alloc(&router->rif_mac_profiles_idr, profile, 0, + max_rif_mac_profiles, GFP_KERNEL); + + if (id >= 0) { + profile->id = id; + return 0; + } + + if (id == -ENOSPC) + NL_SET_ERR_MSG_MOD(extack, + "Exceeded number of supported router interface MAC profiles"); + + return id; +} + +static struct mlxsw_sp_rif_mac_profile * +mlxsw_sp_rif_mac_profile_index_free(struct mlxsw_sp *mlxsw_sp, u8 mac_profile) +{ + struct mlxsw_sp_rif_mac_profile *profile; + + profile = idr_remove(&mlxsw_sp->router->rif_mac_profiles_idr, + mac_profile); + WARN_ON(!profile); + return profile; +} + +static struct mlxsw_sp_rif_mac_profile * +mlxsw_sp_rif_mac_profile_alloc(const char *mac) +{ + struct mlxsw_sp_rif_mac_profile *profile; + + profile = kzalloc(sizeof(*profile), GFP_KERNEL); + if (!profile) + return NULL; + + ether_addr_copy(profile->mac_prefix, mac); + refcount_set(&profile->ref_count, 1); + return profile; +} + +static struct mlxsw_sp_rif_mac_profile * +mlxsw_sp_rif_mac_profile_find(const struct mlxsw_sp *mlxsw_sp, const char *mac) +{ + struct mlxsw_sp_router *router = mlxsw_sp->router; + struct mlxsw_sp_rif_mac_profile *profile; + int id; + + idr_for_each_entry(&router->rif_mac_profiles_idr, profile, id) { + if (!profile) + continue; + + if (ether_addr_equal_masked(profile->mac_prefix, mac, + mlxsw_sp->mac_mask)) + return profile; + } + + return NULL; +} + +static u64 mlxsw_sp_rif_mac_profiles_occ_get(void *priv) +{ + const struct mlxsw_sp *mlxsw_sp = priv; + + return atomic_read(&mlxsw_sp->router->rif_mac_profiles_count); +} + +static struct mlxsw_sp_rif_mac_profile * +mlxsw_sp_rif_mac_profile_create(struct mlxsw_sp *mlxsw_sp, const char *mac, + struct netlink_ext_ack *extack) +{ + struct mlxsw_sp_rif_mac_profile *profile; + int err; + + profile = mlxsw_sp_rif_mac_profile_alloc(mac); + if (!profile) + return ERR_PTR(-ENOMEM); + + err = mlxsw_sp_rif_mac_profile_index_alloc(mlxsw_sp, profile, extack); + if (err) + goto profile_index_alloc_err; + + atomic_inc(&mlxsw_sp->router->rif_mac_profiles_count); + return profile; + +profile_index_alloc_err: + kfree(profile); + return ERR_PTR(err); +} + +static void mlxsw_sp_rif_mac_profile_destroy(struct mlxsw_sp *mlxsw_sp, + u8 mac_profile) +{ + struct mlxsw_sp_rif_mac_profile *profile; + + atomic_dec(&mlxsw_sp->router->rif_mac_profiles_count); + profile = mlxsw_sp_rif_mac_profile_index_free(mlxsw_sp, mac_profile); + kfree(profile); +} + +static int mlxsw_sp_rif_mac_profile_get(struct mlxsw_sp *mlxsw_sp, + const char *mac, u8 *p_mac_profile, + struct netlink_ext_ack *extack) +{ + struct mlxsw_sp_rif_mac_profile *profile; + + profile = mlxsw_sp_rif_mac_profile_find(mlxsw_sp, mac); + if (profile) { + refcount_inc(&profile->ref_count); + goto out; + } + + profile = mlxsw_sp_rif_mac_profile_create(mlxsw_sp, mac, extack); + if (IS_ERR(profile)) + return PTR_ERR(profile); + +out: + *p_mac_profile = profile->id; + return 0; +} + +static void mlxsw_sp_rif_mac_profile_put(struct mlxsw_sp *mlxsw_sp, + u8 mac_profile) +{ + struct mlxsw_sp_rif_mac_profile *profile; + + profile = idr_find(&mlxsw_sp->router->rif_mac_profiles_idr, + mac_profile); + if (WARN_ON(!profile)) + return; + + if (!refcount_dec_and_test(&profile->ref_count)) + return; + + mlxsw_sp_rif_mac_profile_destroy(mlxsw_sp, mac_profile); +} + +static bool mlxsw_sp_rif_mac_profile_is_shared(const struct mlxsw_sp_rif *rif) +{ + struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; + struct mlxsw_sp_rif_mac_profile *profile; + + profile = idr_find(&mlxsw_sp->router->rif_mac_profiles_idr, + rif->mac_profile_id); + if (WARN_ON(!profile)) + return false; + + return refcount_read(&profile->ref_count) > 1; +} + +static int mlxsw_sp_rif_mac_profile_edit(struct mlxsw_sp_rif *rif, + const char *new_mac) +{ + struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; + struct mlxsw_sp_rif_mac_profile *profile; + + profile = idr_find(&mlxsw_sp->router->rif_mac_profiles_idr, + rif->mac_profile_id); + if (WARN_ON(!profile)) + return -EINVAL; + + ether_addr_copy(profile->mac_prefix, new_mac); + return 0; +} + +static int +mlxsw_sp_rif_mac_profile_replace(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_rif *rif, + const char *new_mac, + struct netlink_ext_ack *extack) +{ + u8 mac_profile; + int err; + + if (!mlxsw_sp_rif_mac_profile_is_shared(rif)) + return mlxsw_sp_rif_mac_profile_edit(rif, new_mac); + + err = mlxsw_sp_rif_mac_profile_get(mlxsw_sp, new_mac, + &mac_profile, extack); + if (err) + return err; + + mlxsw_sp_rif_mac_profile_put(mlxsw_sp, rif->mac_profile_id); + rif->mac_profile_id = mac_profile; + return 0; +} + static int __mlxsw_sp_port_vlan_router_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan, struct net_device *l3_dev, @@ -8523,36 +8855,6 @@ static int mlxsw_sp_inetaddr_macvlan_event(struct mlxsw_sp *mlxsw_sp, return 0; } -static int mlxsw_sp_router_port_check_rif_addr(struct mlxsw_sp *mlxsw_sp, - struct net_device *dev, - const unsigned char *dev_addr, - struct netlink_ext_ack *extack) -{ - struct mlxsw_sp_rif *rif; - int i; - - /* A RIF is not created for macvlan netdevs. Their MAC is used to - * populate the FDB - */ - if (netif_is_macvlan(dev) || netif_is_l3_master(dev)) - return 0; - - for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) { - rif = mlxsw_sp->router->rifs[i]; - if (rif && rif->ops && - rif->ops->type == MLXSW_SP_RIF_TYPE_IPIP_LB) - continue; - if (rif && rif->dev && rif->dev != dev && - !ether_addr_equal_masked(rif->dev->dev_addr, dev_addr, - mlxsw_sp->mac_mask)) { - NL_SET_ERR_MSG_MOD(extack, "All router interface MAC addresses must have the same prefix"); - return -EINVAL; - } - } - - return 0; -} - static int __mlxsw_sp_inetaddr_event(struct mlxsw_sp *mlxsw_sp, struct net_device *dev, unsigned long event, @@ -8618,11 +8920,6 @@ int mlxsw_sp_inetaddr_valid_event(struct notifier_block *unused, if (!mlxsw_sp_rif_should_config(rif, dev, event)) goto out; - err = mlxsw_sp_router_port_check_rif_addr(mlxsw_sp, dev, dev->dev_addr, - ivi->extack); - if (err) - goto out; - err = __mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, ivi->extack); out: mutex_unlock(&mlxsw_sp->router->lock); @@ -8706,11 +9003,6 @@ int mlxsw_sp_inet6addr_valid_event(struct notifier_block *unused, if (!mlxsw_sp_rif_should_config(rif, dev, event)) goto out; - err = mlxsw_sp_router_port_check_rif_addr(mlxsw_sp, dev, dev->dev_addr, - i6vi->extack); - if (err) - goto out; - err = __mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, i6vi->extack); out: mutex_unlock(&mlxsw_sp->router->lock); @@ -8718,7 +9010,7 @@ out: } static int mlxsw_sp_rif_edit(struct mlxsw_sp *mlxsw_sp, u16 rif_index, - const char *mac, int mtu) + const char *mac, int mtu, u8 mac_profile) { char ritr_pl[MLXSW_REG_RITR_LEN]; int err; @@ -8730,15 +9022,18 @@ static int mlxsw_sp_rif_edit(struct mlxsw_sp *mlxsw_sp, u16 rif_index, mlxsw_reg_ritr_mtu_set(ritr_pl, mtu); mlxsw_reg_ritr_if_mac_memcpy_to(ritr_pl, mac); + mlxsw_reg_ritr_if_mac_profile_id_set(ritr_pl, mac_profile); mlxsw_reg_ritr_op_set(ritr_pl, MLXSW_REG_RITR_RIF_CREATE); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); } static int mlxsw_sp_router_port_change_event(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_rif *rif) + struct mlxsw_sp_rif *rif, + struct netlink_ext_ack *extack) { struct net_device *dev = rif->dev; + u8 old_mac_profile; u16 fid_index; int err; @@ -8748,8 +9043,14 @@ mlxsw_sp_router_port_change_event(struct mlxsw_sp *mlxsw_sp, if (err) return err; + old_mac_profile = rif->mac_profile_id; + err = mlxsw_sp_rif_mac_profile_replace(mlxsw_sp, rif, dev->dev_addr, + extack); + if (err) + goto err_rif_mac_profile_replace; + err = mlxsw_sp_rif_edit(mlxsw_sp, rif->rif_index, dev->dev_addr, - dev->mtu); + dev->mtu, rif->mac_profile_id); if (err) goto err_rif_edit; @@ -8779,8 +9080,11 @@ mlxsw_sp_router_port_change_event(struct mlxsw_sp *mlxsw_sp, return 0; err_rif_fdb_op: - mlxsw_sp_rif_edit(mlxsw_sp, rif->rif_index, rif->addr, rif->mtu); + mlxsw_sp_rif_edit(mlxsw_sp, rif->rif_index, rif->addr, rif->mtu, + old_mac_profile); err_rif_edit: + mlxsw_sp_rif_mac_profile_replace(mlxsw_sp, rif, rif->addr, extack); +err_rif_mac_profile_replace: mlxsw_sp_rif_fdb_op(mlxsw_sp, rif->addr, fid_index, true); return err; } @@ -8788,16 +9092,34 @@ err_rif_edit: static int mlxsw_sp_router_port_pre_changeaddr_event(struct mlxsw_sp_rif *rif, struct netdev_notifier_pre_changeaddr_info *info) { + struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; + struct mlxsw_sp_rif_mac_profile *profile; struct netlink_ext_ack *extack; + u8 max_rif_mac_profiles; + u64 occ; extack = netdev_notifier_info_to_extack(&info->info); - return mlxsw_sp_router_port_check_rif_addr(rif->mlxsw_sp, rif->dev, - info->dev_addr, extack); + + profile = mlxsw_sp_rif_mac_profile_find(mlxsw_sp, info->dev_addr); + if (profile) + return 0; + + max_rif_mac_profiles = mlxsw_sp->router->max_rif_mac_profile; + occ = mlxsw_sp_rif_mac_profiles_occ_get(mlxsw_sp); + if (occ < max_rif_mac_profiles) + return 0; + + if (!mlxsw_sp_rif_mac_profile_is_shared(rif)) + return 0; + + NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported router interface MAC profiles"); + return -ENOBUFS; } int mlxsw_sp_netdevice_router_port_event(struct net_device *dev, unsigned long event, void *ptr) { + struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr); struct mlxsw_sp *mlxsw_sp; struct mlxsw_sp_rif *rif; int err = 0; @@ -8814,7 +9136,7 @@ int mlxsw_sp_netdevice_router_port_event(struct net_device *dev, switch (event) { case NETDEV_CHANGEMTU: case NETDEV_CHANGEADDR: - err = mlxsw_sp_router_port_change_event(mlxsw_sp, rif); + err = mlxsw_sp_router_port_change_event(mlxsw_sp, rif, extack); break; case NETDEV_PRE_CHANGEADDR: err = mlxsw_sp_router_port_pre_changeaddr_event(rif, ptr); @@ -8937,6 +9259,7 @@ static int mlxsw_sp_rif_subport_op(struct mlxsw_sp_rif *rif, bool enable) mlxsw_reg_ritr_pack(ritr_pl, enable, MLXSW_REG_RITR_SP_IF, rif->rif_index, rif->vr_id, rif->dev->mtu); mlxsw_reg_ritr_mac_pack(ritr_pl, rif->dev->dev_addr); + mlxsw_reg_ritr_if_mac_profile_id_set(ritr_pl, rif->mac_profile_id); mlxsw_reg_ritr_sp_if_pack(ritr_pl, rif_subport->lag, rif_subport->lag ? rif_subport->lag_id : rif_subport->system_port, @@ -8945,13 +9268,21 @@ static int mlxsw_sp_rif_subport_op(struct mlxsw_sp_rif *rif, bool enable) return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); } -static int mlxsw_sp_rif_subport_configure(struct mlxsw_sp_rif *rif) +static int mlxsw_sp_rif_subport_configure(struct mlxsw_sp_rif *rif, + struct netlink_ext_ack *extack) { + u8 mac_profile; int err; - err = mlxsw_sp_rif_subport_op(rif, true); + err = mlxsw_sp_rif_mac_profile_get(rif->mlxsw_sp, rif->addr, + &mac_profile, extack); if (err) return err; + rif->mac_profile_id = mac_profile; + + err = mlxsw_sp_rif_subport_op(rif, true); + if (err) + goto err_rif_subport_op; err = mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr, mlxsw_sp_fid_index(rif->fid), true); @@ -8963,6 +9294,8 @@ static int mlxsw_sp_rif_subport_configure(struct mlxsw_sp_rif *rif) err_rif_fdb_op: mlxsw_sp_rif_subport_op(rif, false); +err_rif_subport_op: + mlxsw_sp_rif_mac_profile_put(rif->mlxsw_sp, mac_profile); return err; } @@ -8975,6 +9308,7 @@ static void mlxsw_sp_rif_subport_deconfigure(struct mlxsw_sp_rif *rif) mlxsw_sp_fid_index(fid), false); mlxsw_sp_rif_macvlan_flush(rif); mlxsw_sp_rif_subport_op(rif, false); + mlxsw_sp_rif_mac_profile_put(rif->mlxsw_sp, rif->mac_profile_id); } static struct mlxsw_sp_fid * @@ -9003,6 +9337,7 @@ static int mlxsw_sp_rif_vlan_fid_op(struct mlxsw_sp_rif *rif, mlxsw_reg_ritr_pack(ritr_pl, enable, type, rif->rif_index, rif->vr_id, rif->dev->mtu); mlxsw_reg_ritr_mac_pack(ritr_pl, rif->dev->dev_addr); + mlxsw_reg_ritr_if_mac_profile_id_set(ritr_pl, rif->mac_profile_id); mlxsw_reg_ritr_fid_set(ritr_pl, type, vid_fid); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); @@ -9013,16 +9348,24 @@ u8 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp) return mlxsw_core_max_ports(mlxsw_sp->core) + 1; } -static int mlxsw_sp_rif_fid_configure(struct mlxsw_sp_rif *rif) +static int mlxsw_sp_rif_fid_configure(struct mlxsw_sp_rif *rif, + struct netlink_ext_ack *extack) { struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; u16 fid_index = mlxsw_sp_fid_index(rif->fid); + u8 mac_profile; int err; + err = mlxsw_sp_rif_mac_profile_get(mlxsw_sp, rif->addr, + &mac_profile, extack); + if (err) + return err; + rif->mac_profile_id = mac_profile; + err = mlxsw_sp_rif_vlan_fid_op(rif, MLXSW_REG_RITR_FID_IF, fid_index, true); if (err) - return err; + goto err_rif_vlan_fid_op; err = mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_MC, mlxsw_sp_router_port(mlxsw_sp), true); @@ -9050,6 +9393,8 @@ err_fid_bc_flood_set: mlxsw_sp_router_port(mlxsw_sp), false); err_fid_mc_flood_set: mlxsw_sp_rif_vlan_fid_op(rif, MLXSW_REG_RITR_FID_IF, fid_index, false); +err_rif_vlan_fid_op: + mlxsw_sp_rif_mac_profile_put(mlxsw_sp, mac_profile); return err; } @@ -9068,6 +9413,7 @@ static void mlxsw_sp_rif_fid_deconfigure(struct mlxsw_sp_rif *rif) mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_MC, mlxsw_sp_router_port(mlxsw_sp), false); mlxsw_sp_rif_vlan_fid_op(rif, MLXSW_REG_RITR_FID_IF, fid_index, false); + mlxsw_sp_rif_mac_profile_put(rif->mlxsw_sp, rif->mac_profile_id); } static struct mlxsw_sp_fid * @@ -9172,7 +9518,8 @@ mlxsw_sp_rif_ipip_lb_setup(struct mlxsw_sp_rif *rif, } static int -mlxsw_sp1_rif_ipip_lb_configure(struct mlxsw_sp_rif *rif) +mlxsw_sp1_rif_ipip_lb_configure(struct mlxsw_sp_rif *rif, + struct netlink_ext_ack *extack) { struct mlxsw_sp_rif_ipip_lb *lb_rif = mlxsw_sp_rif_ipip_lb_rif(rif); u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(rif->dev); @@ -9359,7 +9706,8 @@ out: } static int -mlxsw_sp2_rif_ipip_lb_configure(struct mlxsw_sp_rif *rif) +mlxsw_sp2_rif_ipip_lb_configure(struct mlxsw_sp_rif *rif, + struct netlink_ext_ack *extack) { struct mlxsw_sp_rif_ipip_lb *lb_rif = mlxsw_sp_rif_ipip_lb_rif(rif); u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(rif->dev); @@ -9414,6 +9762,13 @@ static const struct mlxsw_sp_rif_ops *mlxsw_sp2_rif_ops_arr[] = { static int mlxsw_sp_rifs_init(struct mlxsw_sp *mlxsw_sp) { u64 max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); + struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); + struct mlxsw_core *core = mlxsw_sp->core; + + if (!MLXSW_CORE_RES_VALID(core, MAX_RIF_MAC_PROFILES)) + return -EIO; + mlxsw_sp->router->max_rif_mac_profile = + MLXSW_CORE_RES_GET(core, MAX_RIF_MAC_PROFILES); mlxsw_sp->router->rifs = kcalloc(max_rifs, sizeof(struct mlxsw_sp_rif *), @@ -9421,16 +9776,28 @@ static int mlxsw_sp_rifs_init(struct mlxsw_sp *mlxsw_sp) if (!mlxsw_sp->router->rifs) return -ENOMEM; + idr_init(&mlxsw_sp->router->rif_mac_profiles_idr); + atomic_set(&mlxsw_sp->router->rif_mac_profiles_count, 0); + devlink_resource_occ_get_register(devlink, + MLXSW_SP_RESOURCE_RIF_MAC_PROFILES, + mlxsw_sp_rif_mac_profiles_occ_get, + mlxsw_sp); + return 0; } static void mlxsw_sp_rifs_fini(struct mlxsw_sp *mlxsw_sp) { + struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); int i; for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) WARN_ON_ONCE(mlxsw_sp->router->rifs[i]); + devlink_resource_occ_get_unregister(devlink, + MLXSW_SP_RESOURCE_RIF_MAC_PROFILES); + WARN_ON(!idr_is_empty(&mlxsw_sp->router->rif_mac_profiles_idr)); + idr_destroy(&mlxsw_sp->router->rif_mac_profiles_idr); kfree(mlxsw_sp->router->rifs); } @@ -9447,7 +9814,6 @@ 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 +9826,18 @@ 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 +10252,7 @@ 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 +10268,7 @@ 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 +10314,7 @@ 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..99e8371a82a5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h @@ -39,6 +39,9 @@ mlxsw_sp_fib_entry_op_ctx_clear(struct mlxsw_sp_fib_entry_op_ctx *op_ctx) struct mlxsw_sp_router { struct mlxsw_sp *mlxsw_sp; struct mlxsw_sp_rif **rifs; + struct idr rif_mac_profiles_idr; + atomic_t rif_mac_profiles_count; + u8 max_rif_mac_profile; struct mlxsw_sp_vr *vrs; struct rhashtable neigh_ht; struct rhashtable nexthop_group_ht; @@ -65,8 +68,6 @@ 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 +83,8 @@ 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 +229,8 @@ 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; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index 3398cc01e5ec..f5f819aa9a65 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -1650,6 +1650,22 @@ void mlxsw_sp_span_trigger_disable(struct mlxsw_sp_port *mlxsw_sp_port, return trigger_entry->ops->disable(trigger_entry, mlxsw_sp_port, tc); } +bool mlxsw_sp_span_trigger_is_ingress(enum mlxsw_sp_span_trigger trigger) +{ + switch (trigger) { + case MLXSW_SP_SPAN_TRIGGER_INGRESS: + case MLXSW_SP_SPAN_TRIGGER_EARLY_DROP: + case MLXSW_SP_SPAN_TRIGGER_TAIL_DROP: + return true; + case MLXSW_SP_SPAN_TRIGGER_EGRESS: + case MLXSW_SP_SPAN_TRIGGER_ECN: + return false; + } + + WARN_ON_ONCE(1); + return false; +} + static int mlxsw_sp1_span_init(struct mlxsw_sp *mlxsw_sp) { size_t arr_size = ARRAY_SIZE(mlxsw_sp1_span_entry_ops_arr); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h index efaefd1ae863..82e711afb02b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h @@ -120,6 +120,7 @@ int mlxsw_sp_span_trigger_enable(struct mlxsw_sp_port *mlxsw_sp_port, enum mlxsw_sp_span_trigger trigger, u8 tc); void mlxsw_sp_span_trigger_disable(struct mlxsw_sp_port *mlxsw_sp_port, enum mlxsw_sp_span_trigger trigger, u8 tc); +bool mlxsw_sp_span_trigger_is_ingress(enum mlxsw_sp_span_trigger trigger); extern const struct mlxsw_sp_span_ops mlxsw_sp1_span_ops; extern const struct mlxsw_sp_span_ops mlxsw_sp2_span_ops; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 22fede5cb32c..81c7e8a7fcf5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -1635,16 +1635,13 @@ mlxsw_sp_mid *__mlxsw_sp_mc_alloc(struct mlxsw_sp *mlxsw_sp, u16 fid) { struct mlxsw_sp_mid *mid; - size_t alloc_size; mid = kzalloc(sizeof(*mid), GFP_KERNEL); if (!mid) return NULL; - alloc_size = sizeof(unsigned long) * - BITS_TO_LONGS(mlxsw_core_max_ports(mlxsw_sp->core)); - - mid->ports_in_mid = kzalloc(alloc_size, GFP_KERNEL); + mid->ports_in_mid = bitmap_zalloc(mlxsw_core_max_ports(mlxsw_sp->core), + GFP_KERNEL); if (!mid->ports_in_mid) goto err_ports_in_mid_alloc; @@ -1663,7 +1660,7 @@ out: return mid; err_write_mdb_entry: - kfree(mid->ports_in_mid); + bitmap_free(mid->ports_in_mid); err_ports_in_mid_alloc: kfree(mid); return NULL; @@ -1680,7 +1677,7 @@ static int mlxsw_sp_port_remove_from_mid(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_core_max_ports(mlxsw_sp->core))) { err = mlxsw_sp_mc_remove_mdb_entry(mlxsw_sp, mid); list_del(&mid->list); - kfree(mid->ports_in_mid); + bitmap_free(mid->ports_in_mid); kfree(mid); } return err; |