diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx5/core/en_main.c')
-rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 346 |
1 files changed, 165 insertions, 181 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 93e50ccd44c3..b5fdbd3190d9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -35,6 +35,7 @@ #include <linux/mlx5/fs.h> #include <net/vxlan.h> #include <linux/bpf.h> +#include <linux/if_bridge.h> #include <net/page_pool.h> #include "eswitch.h" #include "en.h" @@ -51,6 +52,7 @@ #include "en/xdp.h" #include "lib/eq.h" #include "en/monitor_stats.h" +#include "en/reporter.h" struct mlx5e_rq_param { u32 rqc[MLX5_ST_SZ_DW(rqc)]; @@ -171,8 +173,7 @@ static u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev, if (mlx5e_rx_mpwqe_is_linear_skb(mdev, params)) return order_base_2(mlx5e_rx_get_linear_frag_sz(params)); - return MLX5E_MPWQE_STRIDE_SZ(mdev, - MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)); + return MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev); } static u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev, @@ -1160,7 +1161,7 @@ static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa) return 0; } -static void mlx5e_sq_recover(struct work_struct *work); +static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work); static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, int txq_ix, struct mlx5e_params *params, @@ -1182,7 +1183,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, sq->uar_map = mdev->mlx5e_res.bfreg.map; sq->min_inline_mode = params->tx_min_inline_mode; sq->stats = &c->priv->channel_stats[c->ix].sq[tc]; - INIT_WORK(&sq->recover.recover_work, mlx5e_sq_recover); + INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work); if (MLX5_IPSEC_DEV(c->priv->mdev)) set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state); if (mlx5_accel_is_tls_device(c->priv->mdev)) @@ -1270,15 +1271,8 @@ static int mlx5e_create_sq(struct mlx5_core_dev *mdev, return err; } -struct mlx5e_modify_sq_param { - int curr_state; - int next_state; - bool rl_update; - int rl_index; -}; - -static int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn, - struct mlx5e_modify_sq_param *p) +int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn, + struct mlx5e_modify_sq_param *p) { void *in; void *sqc; @@ -1376,17 +1370,7 @@ err_free_txqsq: return err; } -static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq) -{ - WARN_ONCE(sq->cc != sq->pc, - "SQ 0x%x: cc (0x%x) != pc (0x%x)\n", - sq->sqn, sq->cc, sq->pc); - sq->cc = 0; - sq->dma_fifo_cc = 0; - sq->pc = 0; -} - -static void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq) +void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq) { sq->txq = netdev_get_tx_queue(sq->channel->netdev, sq->txq_ix); clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state); @@ -1395,7 +1379,7 @@ static void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq) netif_tx_start_queue(sq->txq); } -static inline void netif_tx_disable_queue(struct netdev_queue *txq) +void mlx5e_tx_disable_queue(struct netdev_queue *txq) { __netif_tx_lock_bh(txq); netif_tx_stop_queue(txq); @@ -1411,7 +1395,7 @@ static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq) /* prevent netif_tx_wake_queue */ napi_synchronize(&c->napi); - netif_tx_disable_queue(sq->txq); + mlx5e_tx_disable_queue(sq->txq); /* last doorbell out, godspeed .. */ if (mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1)) { @@ -1431,6 +1415,7 @@ static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq) struct mlx5_rate_limit rl = {0}; cancel_work_sync(&sq->dim.work); + cancel_work_sync(&sq->recover_work); mlx5e_destroy_sq(mdev, sq->sqn); if (sq->rate_limit) { rl.rate = sq->rate_limit; @@ -1440,105 +1425,12 @@ static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq) mlx5e_free_txqsq(sq); } -static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq) -{ - unsigned long exp_time = jiffies + msecs_to_jiffies(2000); - - while (time_before(jiffies, exp_time)) { - if (sq->cc == sq->pc) - return 0; - - msleep(20); - } - - netdev_err(sq->channel->netdev, - "Wait for SQ 0x%x flush timeout (sq cc = 0x%x, sq pc = 0x%x)\n", - sq->sqn, sq->cc, sq->pc); - - return -ETIMEDOUT; -} - -static int mlx5e_sq_to_ready(struct mlx5e_txqsq *sq, int curr_state) -{ - struct mlx5_core_dev *mdev = sq->channel->mdev; - struct net_device *dev = sq->channel->netdev; - struct mlx5e_modify_sq_param msp = {0}; - int err; - - msp.curr_state = curr_state; - msp.next_state = MLX5_SQC_STATE_RST; - - err = mlx5e_modify_sq(mdev, sq->sqn, &msp); - if (err) { - netdev_err(dev, "Failed to move sq 0x%x to reset\n", sq->sqn); - return err; - } - - memset(&msp, 0, sizeof(msp)); - msp.curr_state = MLX5_SQC_STATE_RST; - msp.next_state = MLX5_SQC_STATE_RDY; - - err = mlx5e_modify_sq(mdev, sq->sqn, &msp); - if (err) { - netdev_err(dev, "Failed to move sq 0x%x to ready\n", sq->sqn); - return err; - } - - return 0; -} - -static void mlx5e_sq_recover(struct work_struct *work) +static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work) { - struct mlx5e_txqsq_recover *recover = - container_of(work, struct mlx5e_txqsq_recover, - recover_work); - struct mlx5e_txqsq *sq = container_of(recover, struct mlx5e_txqsq, - recover); - struct mlx5_core_dev *mdev = sq->channel->mdev; - struct net_device *dev = sq->channel->netdev; - u8 state; - int err; - - err = mlx5_core_query_sq_state(mdev, sq->sqn, &state); - if (err) { - netdev_err(dev, "Failed to query SQ 0x%x state. err = %d\n", - sq->sqn, err); - return; - } - - if (state != MLX5_RQC_STATE_ERR) { - netdev_err(dev, "SQ 0x%x not in ERROR state\n", sq->sqn); - return; - } - - netif_tx_disable_queue(sq->txq); + struct mlx5e_txqsq *sq = container_of(recover_work, struct mlx5e_txqsq, + recover_work); - if (mlx5e_wait_for_sq_flush(sq)) - return; - - /* If the interval between two consecutive recovers per SQ is too - * short, don't recover to avoid infinite loop of ERR_CQE -> recover. - * If we reached this state, there is probably a bug that needs to be - * fixed. let's keep the queue close and let tx timeout cleanup. - */ - if (jiffies_to_msecs(jiffies - recover->last_recover) < - MLX5E_SQ_RECOVER_MIN_INTERVAL) { - netdev_err(dev, "Recover SQ 0x%x canceled, too many error CQEs\n", - sq->sqn); - return; - } - - /* At this point, no new packets will arrive from the stack as TXQ is - * marked with QUEUE_STATE_DRV_XOFF. In addition, NAPI cleared all - * pending WQEs. SQ can safely reset the SQ. - */ - if (mlx5e_sq_to_ready(sq, state)) - return; - - mlx5e_reset_txqsq_cc_pc(sq); - sq->stats->recover++; - recover->last_recover = jiffies; - mlx5e_activate_txqsq(sq); + mlx5e_tx_reporter_err_cqe(sq); } static int mlx5e_open_icosq(struct mlx5e_channel *c, @@ -1950,6 +1842,29 @@ static int mlx5e_set_tx_maxrate(struct net_device *dev, int index, u32 rate) return err; } +static int mlx5e_alloc_xps_cpumask(struct mlx5e_channel *c, + struct mlx5e_params *params) +{ + int num_comp_vectors = mlx5_comp_vectors_count(c->mdev); + int irq; + + if (!zalloc_cpumask_var(&c->xps_cpumask, GFP_KERNEL)) + return -ENOMEM; + + for (irq = c->ix; irq < num_comp_vectors; irq += params->num_channels) { + int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(c->mdev, irq)); + + cpumask_set_cpu(cpu, c->xps_cpumask); + } + + return 0; +} + +static void mlx5e_free_xps_cpumask(struct mlx5e_channel *c) +{ + free_cpumask_var(c->xps_cpumask); +} + static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, struct mlx5e_params *params, struct mlx5e_channel_param *cparam, @@ -1982,9 +1897,12 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, c->num_tc = params->num_tc; c->xdp = !!params->xdp_prog; c->stats = &priv->channel_stats[ix].ch; - c->irq_desc = irq_to_desc(irq); + err = mlx5e_alloc_xps_cpumask(c, params); + if (err) + goto err_free_channel; + netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64); err = mlx5e_open_cq(c, icocq_moder, &cparam->icosq_cq, &c->icosq.cq); @@ -2067,6 +1985,9 @@ err_close_icosq_cq: err_napi_del: netif_napi_del(&c->napi); + mlx5e_free_xps_cpumask(c); + +err_free_channel: kvfree(c); return err; @@ -2079,7 +2000,7 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c) for (tc = 0; tc < c->num_tc; tc++) mlx5e_activate_txqsq(&c->sq[tc]); mlx5e_activate_rq(&c->rq); - netif_set_xps_queue(c->netdev, get_cpu_mask(c->cpu), c->ix); + netif_set_xps_queue(c->netdev, c->xps_cpumask, c->ix); } static void mlx5e_deactivate_channel(struct mlx5e_channel *c) @@ -2107,6 +2028,7 @@ static void mlx5e_close_channel(struct mlx5e_channel *c) mlx5e_close_tx_cqs(c); mlx5e_close_cq(&c->icosq.cq); netif_napi_del(&c->napi); + mlx5e_free_xps_cpumask(c); kvfree(c); } @@ -2380,6 +2302,10 @@ int mlx5e_open_channels(struct mlx5e_priv *priv, goto err_close_channels; } + if (!IS_ERR_OR_NULL(priv->tx_reporter)) + devlink_health_reporter_state_update(priv->tx_reporter, + DEVLINK_HEALTH_REPORTER_STATE_HEALTHY); + kvfree(cparam); return 0; @@ -2964,13 +2890,14 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv) mlx5e_deactivate_channels(&priv->channels); } -void mlx5e_switch_priv_channels(struct mlx5e_priv *priv, - struct mlx5e_channels *new_chs, - mlx5e_fp_hw_modify hw_modify) +static void mlx5e_switch_priv_channels(struct mlx5e_priv *priv, + struct mlx5e_channels *new_chs, + mlx5e_fp_hw_modify hw_modify) { struct net_device *netdev = priv->netdev; int new_num_txqs; int carrier_ok; + new_num_txqs = new_chs->num * new_chs->params.num_tc; carrier_ok = netif_carrier_ok(netdev); @@ -2996,6 +2923,20 @@ void mlx5e_switch_priv_channels(struct mlx5e_priv *priv, netif_carrier_on(netdev); } +int mlx5e_safe_switch_channels(struct mlx5e_priv *priv, + struct mlx5e_channels *new_chs, + mlx5e_fp_hw_modify hw_modify) +{ + int err; + + err = mlx5e_open_channels(priv, new_chs); + if (err) + return err; + + mlx5e_switch_priv_channels(priv, new_chs, hw_modify); + return 0; +} + void mlx5e_timestamp_init(struct mlx5e_priv *priv) { priv->tstamp.tx_type = HWTSTAMP_TX_OFF; @@ -3209,6 +3150,7 @@ static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv) { int tc; + mlx5e_tx_reporter_destroy(priv); for (tc = 0; tc < priv->profile->max_tc; tc++) mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]); } @@ -3411,13 +3353,12 @@ static int mlx5e_setup_tc_mqprio(struct net_device *netdev, goto out; } - err = mlx5e_open_channels(priv, &new_channels); + err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); if (err) goto out; priv->max_opened_tc = max_t(u8, priv->max_opened_tc, new_channels.params.num_tc); - mlx5e_switch_priv_channels(priv, &new_channels, NULL); out: mutex_unlock(&priv->state_lock); return err; @@ -3494,11 +3435,32 @@ static int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type, } } +void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s) +{ + int i; + + for (i = 0; i < mlx5e_get_netdev_max_channels(priv->netdev); i++) { + struct mlx5e_channel_stats *channel_stats = &priv->channel_stats[i]; + struct mlx5e_rq_stats *rq_stats = &channel_stats->rq; + int j; + + s->rx_packets += rq_stats->packets; + s->rx_bytes += rq_stats->bytes; + + for (j = 0; j < priv->max_opened_tc; j++) { + struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j]; + + s->tx_packets += sq_stats->packets; + s->tx_bytes += sq_stats->bytes; + s->tx_dropped += sq_stats->dropped; + } + } +} + void mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct mlx5e_priv *priv = netdev_priv(dev); - struct mlx5e_sw_stats *sstats = &priv->stats.sw; struct mlx5e_vport_stats *vstats = &priv->stats.vport; struct mlx5e_pport_stats *pstats = &priv->stats.pport; @@ -3513,12 +3475,7 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->tx_packets = PPORT_802_3_GET(pstats, a_frames_transmitted_ok); stats->tx_bytes = PPORT_802_3_GET(pstats, a_octets_transmitted_ok); } else { - mlx5e_grp_sw_update_stats(priv); - stats->rx_packets = sstats->rx_packets; - stats->rx_bytes = sstats->rx_bytes; - stats->tx_packets = sstats->tx_packets; - stats->tx_bytes = sstats->tx_bytes; - stats->tx_dropped = sstats->tx_queue_dropped; + mlx5e_fold_sw_stats64(priv, stats); } stats->rx_dropped = priv->stats.qcnt.rx_out_of_buffer; @@ -3611,11 +3568,7 @@ static int set_feature_lro(struct net_device *netdev, bool enable) goto out; } - err = mlx5e_open_channels(priv, &new_channels); - if (err) - goto out; - - mlx5e_switch_priv_channels(priv, &new_channels, mlx5e_modify_tirs_lro); + err = mlx5e_safe_switch_channels(priv, &new_channels, mlx5e_modify_tirs_lro); out: mutex_unlock(&priv->state_lock); return err; @@ -3833,11 +3786,10 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, goto out; } - err = mlx5e_open_channels(priv, &new_channels); + err = mlx5e_safe_switch_channels(priv, &new_channels, set_mtu_cb); if (err) goto out; - mlx5e_switch_priv_channels(priv, &new_channels, set_mtu_cb); netdev->mtu = new_channels.params.sw_mtu; out: @@ -4180,31 +4132,13 @@ netdev_features_t mlx5e_features_check(struct sk_buff *skb, return features; } -static bool mlx5e_tx_timeout_eq_recover(struct net_device *dev, - struct mlx5e_txqsq *sq) -{ - struct mlx5_eq_comp *eq = sq->cq.mcq.eq; - u32 eqe_count; - - netdev_err(dev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n", - eq->core.eqn, eq->core.cons_index, eq->core.irqn); - - eqe_count = mlx5_eq_poll_irq_disabled(eq); - if (!eqe_count) - return false; - - netdev_err(dev, "Recover %d eqes on EQ 0x%x\n", eqe_count, eq->core.eqn); - sq->channel->stats->eq_rearm++; - return true; -} - static void mlx5e_tx_timeout_work(struct work_struct *work) { struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv, tx_timeout_work); - struct net_device *dev = priv->netdev; - bool reopen_channels = false; - int i, err; + bool report_failed = false; + int err; + int i; rtnl_lock(); mutex_lock(&priv->state_lock); @@ -4213,31 +4147,22 @@ static void mlx5e_tx_timeout_work(struct work_struct *work) goto unlock; for (i = 0; i < priv->channels.num * priv->channels.params.num_tc; i++) { - struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, i); + struct netdev_queue *dev_queue = + netdev_get_tx_queue(priv->netdev, i); struct mlx5e_txqsq *sq = priv->txq2sq[i]; if (!netif_xmit_stopped(dev_queue)) continue; - netdev_err(dev, - "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u\n", - i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc, - jiffies_to_usecs(jiffies - dev_queue->trans_start)); - - /* If we recover a lost interrupt, most likely TX timeout will - * be resolved, skip reopening channels - */ - if (!mlx5e_tx_timeout_eq_recover(dev, sq)) { - clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); - reopen_channels = true; - } + if (mlx5e_tx_reporter_timeout(sq)) + report_failed = true; } - if (!reopen_channels) + if (!report_failed) goto unlock; - mlx5e_close_locked(dev); - err = mlx5e_open_locked(dev); + mlx5e_close_locked(priv->netdev); + err = mlx5e_open_locked(priv->netdev); if (err) netdev_err(priv->netdev, "mlx5e_open_locked failed recovering from a tx_timeout, err(%d).\n", @@ -4385,6 +4310,61 @@ static int mlx5e_xdp(struct net_device *dev, struct netdev_bpf *xdp) } } +#ifdef CONFIG_MLX5_ESWITCH +static int mlx5e_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, + struct net_device *dev, u32 filter_mask, + int nlflags) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5_core_dev *mdev = priv->mdev; + u8 mode, setting; + int err; + + err = mlx5_eswitch_get_vepa(mdev->priv.eswitch, &setting); + if (err) + return err; + mode = setting ? BRIDGE_MODE_VEPA : BRIDGE_MODE_VEB; + return ndo_dflt_bridge_getlink(skb, pid, seq, dev, + mode, + 0, 0, nlflags, filter_mask, NULL); +} + +static int mlx5e_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, + u16 flags, struct netlink_ext_ack *extack) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5_core_dev *mdev = priv->mdev; + struct nlattr *attr, *br_spec; + u16 mode = BRIDGE_MODE_UNDEF; + u8 setting; + int rem; + + br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + if (!br_spec) + return -EINVAL; + + nla_for_each_nested(attr, br_spec, rem) { + if (nla_type(attr) != IFLA_BRIDGE_MODE) + continue; + + if (nla_len(attr) < sizeof(mode)) + return -EINVAL; + + mode = nla_get_u16(attr); + if (mode > BRIDGE_MODE_VEPA) + return -EINVAL; + + break; + } + + if (mode == BRIDGE_MODE_UNDEF) + return -EINVAL; + + setting = (mode == BRIDGE_MODE_VEPA) ? 1 : 0; + return mlx5_eswitch_set_vepa(mdev->priv.eswitch, setting); +} +#endif + const struct net_device_ops mlx5e_netdev_ops = { .ndo_open = mlx5e_open, .ndo_stop = mlx5e_close, @@ -4411,6 +4391,9 @@ const struct net_device_ops mlx5e_netdev_ops = { .ndo_rx_flow_steer = mlx5e_rx_flow_steer, #endif #ifdef CONFIG_MLX5_ESWITCH + .ndo_bridge_setlink = mlx5e_bridge_setlink, + .ndo_bridge_getlink = mlx5e_bridge_getlink, + /* SRIOV E-Switch NDOs */ .ndo_set_vf_mac = mlx5e_set_vf_mac, .ndo_set_vf_vlan = mlx5e_set_vf_vlan, @@ -4910,6 +4893,7 @@ static int mlx5e_init_nic_tx(struct mlx5e_priv *priv) #ifdef CONFIG_MLX5_CORE_EN_DCB mlx5e_dcbnl_initialize(priv); #endif + mlx5e_tx_reporter_create(priv); return 0; } |