diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox')
28 files changed, 362 insertions, 235 deletions
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/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 7b8c8187543a..03a7a4ce5cd5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -252,6 +252,7 @@ struct mlx5e_params { struct { u16 mode; u8 num_tc; + struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE]; } mqprio; bool rx_cqe_compress_def; bool tunneled_offload_en; @@ -845,6 +846,7 @@ 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; @@ -1100,12 +1102,6 @@ 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 +1110,13 @@ 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/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index 41684a6c44e9..a88a1a48229f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -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/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/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index ee688dec67a9..3a86f66d1295 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) 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/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/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index b4e986818794..4a13ef561587 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.h" +#include "lag_mp.h" struct mlx5e_tc_tun_route_attr { struct net_device *out_dev; 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_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 306fb5d6a36d..9d451b8ee467 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -2036,6 +2036,17 @@ 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 diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index c06b4b938ae7..d226cc5ab1d1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -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_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 3fd515e7bf30..41ef6eb70a58 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2264,7 +2264,7 @@ 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 +2282,8 @@ 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 +2312,24 @@ 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); @@ -2350,11 +2352,14 @@ 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 +2866,58 @@ 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; + 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) +{ + params->mqprio.mode = TC_MQPRIO_MODE_CHANNEL; + params->mqprio.num_tc = qopt->num_tc; + 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 +2931,7 @@ 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 +2945,17 @@ 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; @@ -2917,8 +2981,8 @@ 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; } @@ -2926,25 +2990,12 @@ 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) -{ - 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); - - return 0; -} - 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; + bool nch_changed; int err; err = mlx5e_mqprio_channel_validate(priv, mqprio); @@ -2952,12 +3003,12 @@ static int mlx5e_setup_tc_mqprio_channel(struct mlx5e_priv *priv, 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); - return err; + nch_changed = mlx5e_get_dcb_num_tc(&priv->channels.params) > 1; + preactivate = nch_changed ? mlx5e_num_channels_changed_ctx : + mlx5e_update_netdev_queues_ctx; + return mlx5e_safe_switch_params(priv, &new_params, preactivate, NULL, true); } static int mlx5e_setup_tc_mqprio(struct mlx5e_priv *priv, @@ -3065,7 +3116,7 @@ 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; @@ -3274,20 +3325,67 @@ 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; } @@ -4186,13 +4284,11 @@ 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. @@ -4482,6 +4578,12 @@ 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); @@ -4499,6 +4601,7 @@ 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) @@ -4682,8 +4785,35 @@ 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 +4821,8 @@ 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)) @@ -4734,7 +4866,8 @@ 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) { struct net_device *netdev; int err; @@ -4745,7 +4878,7 @@ 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 +4920,7 @@ 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 +4928,18 @@ 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 +5004,7 @@ 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 +5030,12 @@ 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 +5131,7 @@ 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..0684ac6699b2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -596,7 +596,6 @@ 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 +618,11 @@ 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 +648,6 @@ 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; } @@ -1169,7 +1172,7 @@ 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_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 3c65fd0bcf31..29a6586ef28d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1001,14 +1001,9 @@ 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); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index e4f5b6395148..e1dd17019030 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) { @@ -450,7 +451,7 @@ 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; @@ -2076,7 +2077,7 @@ 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 +2120,7 @@ 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 +2134,7 @@ 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 +2176,7 @@ 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_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index ba8164792016..129ff7e0d65c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -67,6 +67,8 @@ #include "lib/fs_chains.h" #include "diag/en_tc_tracepoint.h" #include <asm/div64.h> +#include "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) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index c63d78eda606..188994d091c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -213,19 +213,18 @@ 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) { + struct xfrm_offload *xo = xfrm_offload(skb); + eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM; - if (skb->encapsulation) { - eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_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++; - } else { - sq->stats->csum_partial++; } } @@ -234,6 +233,11 @@ 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_eseg_meta(eseg))) { + 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 +253,6 @@ 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/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/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/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 67571e5040d6..269ebb53eda6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -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; @@ -711,7 +711,7 @@ 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.c index ca5690b0a7ab..d2105c1635c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -442,6 +442,10 @@ 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); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c index f239b352a58a..21fdaf708f1f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c @@ -9,20 +9,23 @@ #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..dea199e79bed 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) {} +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/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/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index c79a10b3454d..763c83a02380 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 @@ -633,8 +633,9 @@ 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/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/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 13b0259f7ea6..fcace73eae40 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); |