diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox')
35 files changed, 431 insertions, 375 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c index c7e939945259..53daa6ca5d83 100644 --- a/drivers/net/ethernet/mellanox/mlx4/catas.c +++ b/drivers/net/ethernet/mellanox/mlx4/catas.c @@ -158,7 +158,7 @@ static int mlx4_reset_slave(struct mlx4_dev *dev) return -ETIMEDOUT; } -static int mlx4_comm_internal_err(u32 slave_read) +int mlx4_comm_internal_err(u32 slave_read) { return (u32)COMM_CHAN_EVENT_INTERNAL_ERR == (slave_read & (u32)COMM_CHAN_EVENT_INTERNAL_ERR) ? 1 : 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c index a849da92f857..6b8635378f1f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/cq.c @@ -101,13 +101,19 @@ void mlx4_cq_completion(struct mlx4_dev *dev, u32 cqn) { struct mlx4_cq *cq; + rcu_read_lock(); cq = radix_tree_lookup(&mlx4_priv(dev)->cq_table.tree, cqn & (dev->caps.num_cqs - 1)); + rcu_read_unlock(); + if (!cq) { mlx4_dbg(dev, "Completion event for bogus CQ %08x\n", cqn); return; } + /* Acessing the CQ outside of rcu_read_lock is safe, because + * the CQ is freed only after interrupt handling is completed. + */ ++cq->arm_sn; cq->comp(cq); @@ -118,23 +124,19 @@ void mlx4_cq_event(struct mlx4_dev *dev, u32 cqn, int event_type) struct mlx4_cq_table *cq_table = &mlx4_priv(dev)->cq_table; struct mlx4_cq *cq; - spin_lock(&cq_table->lock); - + rcu_read_lock(); cq = radix_tree_lookup(&cq_table->tree, cqn & (dev->caps.num_cqs - 1)); - if (cq) - atomic_inc(&cq->refcount); - - spin_unlock(&cq_table->lock); + rcu_read_unlock(); if (!cq) { - mlx4_warn(dev, "Async event for bogus CQ %08x\n", cqn); + mlx4_dbg(dev, "Async event for bogus CQ %08x\n", cqn); return; } + /* Acessing the CQ outside of rcu_read_lock is safe, because + * the CQ is freed only after interrupt handling is completed. + */ cq->event(cq, event_type); - - if (atomic_dec_and_test(&cq->refcount)) - complete(&cq->free); } static int mlx4_SW2HW_CQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox, @@ -301,9 +303,9 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, if (err) return err; - spin_lock_irq(&cq_table->lock); + spin_lock(&cq_table->lock); err = radix_tree_insert(&cq_table->tree, cq->cqn, cq); - spin_unlock_irq(&cq_table->lock); + spin_unlock(&cq_table->lock); if (err) goto err_icm; @@ -349,9 +351,9 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, return 0; err_radix: - spin_lock_irq(&cq_table->lock); + spin_lock(&cq_table->lock); radix_tree_delete(&cq_table->tree, cq->cqn); - spin_unlock_irq(&cq_table->lock); + spin_unlock(&cq_table->lock); err_icm: mlx4_cq_free_icm(dev, cq->cqn); @@ -370,15 +372,15 @@ void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq) if (err) mlx4_warn(dev, "HW2SW_CQ failed (%d) for CQN %06x\n", err, cq->cqn); + spin_lock(&cq_table->lock); + radix_tree_delete(&cq_table->tree, cq->cqn); + spin_unlock(&cq_table->lock); + synchronize_irq(priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq->vector)].irq); if (priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq->vector)].irq != priv->eq_table.eq[MLX4_EQ_ASYNC].irq) synchronize_irq(priv->eq_table.eq[MLX4_EQ_ASYNC].irq); - spin_lock_irq(&cq_table->lock); - radix_tree_delete(&cq_table->tree, cq->cqn); - spin_unlock_irq(&cq_table->lock); - if (atomic_dec_and_test(&cq->refcount)) complete(&cq->free); wait_for_completion(&cq->free); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c index 015198c14fa8..504461a464c5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c @@ -245,13 +245,9 @@ static u32 freq_to_shift(u16 freq) { u32 freq_khz = freq * 1000; u64 max_val_cycles = freq_khz * 1000 * MLX4_EN_WRAP_AROUND_SEC; - u64 tmp_rounded = - roundup_pow_of_two(max_val_cycles) > max_val_cycles ? - roundup_pow_of_two(max_val_cycles) - 1 : UINT_MAX; - u64 max_val_cycles_rounded = is_power_of_2(max_val_cycles + 1) ? - max_val_cycles : tmp_rounded; + u64 max_val_cycles_rounded = 1ULL << fls64(max_val_cycles - 1); /* calculate max possible multiplier in order to fit in 64bit */ - u64 max_mul = div_u64(0xffffffffffffffffULL, max_val_cycles_rounded); + u64 max_mul = div64_u64(ULLONG_MAX, max_val_cycles_rounded); /* This comes from the reverse of clocksource_khz2mult */ return ilog2(div_u64(max_mul * freq_khz, 1000000)); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index d9c9f86a30df..9aa422691954 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1099,7 +1099,7 @@ static int mlx4_en_set_ringparam(struct net_device *dev, memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile)); new_prof.tx_ring_size = tx_size; new_prof.rx_ring_size = rx_size; - err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof); + err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, true); if (err) goto out; @@ -1732,8 +1732,6 @@ static void mlx4_en_get_channels(struct net_device *dev, { struct mlx4_en_priv *priv = netdev_priv(dev); - memset(channel, 0, sizeof(*channel)); - channel->max_rx = MAX_RX_RINGS; channel->max_tx = MLX4_EN_MAX_TX_RING_P_UP; @@ -1752,10 +1750,7 @@ static int mlx4_en_set_channels(struct net_device *dev, int xdp_count; int err = 0; - if (channel->other_count || channel->combined_count || - channel->tx_count > MLX4_EN_MAX_TX_RING_P_UP || - channel->rx_count > MAX_RX_RINGS || - !channel->tx_count || !channel->rx_count) + if (!channel->tx_count || !channel->rx_count) return -EINVAL; tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); @@ -1779,7 +1774,7 @@ static int mlx4_en_set_channels(struct net_device *dev, new_prof.tx_ring_num[TX_XDP] = xdp_count; new_prof.rx_ring_num = channel->rx_count; - err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof); + err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, true); if (err) goto out; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index edbe200ac2fa..3b4961a8e8e4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -1748,8 +1748,11 @@ int mlx4_en_start_port(struct net_device *dev) /* Process all completions if exist to prevent * the queues freezing if they are full */ - for (i = 0; i < priv->rx_ring_num; i++) + for (i = 0; i < priv->rx_ring_num; i++) { + local_bh_disable(); napi_schedule(&priv->rx_cq[i]->napi); + local_bh_enable(); + } netif_tx_start_all_queues(dev); netif_device_attach(dev); @@ -2039,6 +2042,8 @@ static void mlx4_en_free_resources(struct mlx4_en_priv *priv) if (priv->tx_cq[t] && priv->tx_cq[t][i]) mlx4_en_destroy_cq(priv, &priv->tx_cq[t][i]); } + kfree(priv->tx_ring[t]); + kfree(priv->tx_cq[t]); } for (i = 0; i < priv->rx_ring_num; i++) { @@ -2181,9 +2186,11 @@ static void mlx4_en_update_priv(struct mlx4_en_priv *dst, int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv, struct mlx4_en_priv *tmp, - struct mlx4_en_port_profile *prof) + struct mlx4_en_port_profile *prof, + bool carry_xdp_prog) { - int t; + struct bpf_prog *xdp_prog; + int i, t; mlx4_en_copy_priv(tmp, priv, prof); @@ -2197,6 +2204,23 @@ int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv, } return -ENOMEM; } + + /* All rx_rings has the same xdp_prog. Pick the first one. */ + xdp_prog = rcu_dereference_protected( + priv->rx_ring[0]->xdp_prog, + lockdep_is_held(&priv->mdev->state_lock)); + + if (xdp_prog && carry_xdp_prog) { + xdp_prog = bpf_prog_add(xdp_prog, tmp->rx_ring_num); + if (IS_ERR(xdp_prog)) { + mlx4_en_free_resources(tmp); + return PTR_ERR(xdp_prog); + } + for (i = 0; i < tmp->rx_ring_num; i++) + rcu_assign_pointer(tmp->rx_ring[i]->xdp_prog, + xdp_prog); + } + return 0; } @@ -2211,7 +2235,6 @@ void mlx4_en_destroy_netdev(struct net_device *dev) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; - int t; en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port); @@ -2245,11 +2268,6 @@ void mlx4_en_destroy_netdev(struct net_device *dev) mlx4_en_free_resources(priv); mutex_unlock(&mdev->state_lock); - for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) { - kfree(priv->tx_ring[t]); - kfree(priv->tx_cq[t]); - } - free_netdev(dev); } @@ -2277,7 +2295,7 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu) if (priv->tx_ring_num[TX_XDP] && !mlx4_en_check_xdp_mtu(dev, new_mtu)) - return -ENOTSUPP; + return -EOPNOTSUPP; dev->mtu = new_mtu; @@ -2752,7 +2770,7 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog) en_warn(priv, "Reducing the number of TX rings, to not exceed the max total rings number.\n"); } - err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof); + err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, false); if (err) { if (prog) bpf_prog_sub(prog, priv->rx_ring_num - 1); @@ -3496,7 +3514,7 @@ int mlx4_en_reset_config(struct net_device *dev, memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile)); memcpy(&new_prof.hwtstamp_config, &ts_config, sizeof(ts_config)); - err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof); + err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, true); if (err) goto out; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 3c37e216bbf3..cc003fdf0ed9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -445,8 +445,14 @@ int mlx4_en_activate_rx_rings(struct mlx4_en_priv *priv) ring->cqn = priv->rx_cq[ring_ind]->mcq.cqn; ring->stride = stride; - if (ring->stride <= TXBB_SIZE) + if (ring->stride <= TXBB_SIZE) { + /* Stamp first unused send wqe */ + __be32 *ptr = (__be32 *)ring->buf; + __be32 stamp = cpu_to_be32(1 << STAMP_SHIFT); + *ptr = stamp; + /* Move pointer to start of rx section */ ring->buf += TXBB_SIZE; + } ring->log_stride = ffs(ring->stride) - 1; ring->buf_size = ring->size * ring->stride; @@ -508,8 +514,11 @@ void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv) return; for (ring = 0; ring < priv->rx_ring_num; ring++) { - if (mlx4_en_is_ring_empty(priv->rx_ring[ring])) + if (mlx4_en_is_ring_empty(priv->rx_ring[ring])) { + local_bh_disable(); napi_reschedule(&priv->rx_cq[ring]->napi); + local_bh_enable(); + } } } diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index cd3638e6fe25..0509996957d9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -554,8 +554,9 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) break; case MLX4_EVENT_TYPE_SRQ_LIMIT: - mlx4_dbg(dev, "%s: MLX4_EVENT_TYPE_SRQ_LIMIT\n", - __func__); + mlx4_dbg(dev, "%s: MLX4_EVENT_TYPE_SRQ_LIMIT. srq_no=0x%x, eq 0x%x\n", + __func__, be32_to_cpu(eqe->event.srq.srqn), + eq->eqn); case MLX4_EVENT_TYPE_SRQ_CATAS_ERROR: if (mlx4_is_master(dev)) { /* forward only to slave owning the SRQ */ @@ -570,15 +571,19 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) eq->eqn, eq->cons_index, ret); break; } - mlx4_warn(dev, "%s: slave:%d, srq_no:0x%x, event: %02x(%02x)\n", - __func__, slave, - be32_to_cpu(eqe->event.srq.srqn), - eqe->type, eqe->subtype); + if (eqe->type == + MLX4_EVENT_TYPE_SRQ_CATAS_ERROR) + mlx4_warn(dev, "%s: slave:%d, srq_no:0x%x, event: %02x(%02x)\n", + __func__, slave, + be32_to_cpu(eqe->event.srq.srqn), + eqe->type, eqe->subtype); if (!ret && slave != dev->caps.function) { - mlx4_warn(dev, "%s: sending event %02x(%02x) to slave:%d\n", - __func__, eqe->type, - eqe->subtype, slave); + if (eqe->type == + MLX4_EVENT_TYPE_SRQ_CATAS_ERROR) + mlx4_warn(dev, "%s: sending event %02x(%02x) to slave:%d\n", + __func__, eqe->type, + eqe->subtype, slave); mlx4_slave_event(dev, slave, eqe); break; } diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c index 2a9dd460a95f..e1f9e7cebf8f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/icm.c +++ b/drivers/net/ethernet/mellanox/mlx4/icm.c @@ -118,8 +118,13 @@ static int mlx4_alloc_icm_coherent(struct device *dev, struct scatterlist *mem, if (!buf) return -ENOMEM; + if (offset_in_page(buf)) { + dma_free_coherent(dev, PAGE_SIZE << order, + buf, sg_dma_address(mem)); + return -ENOMEM; + } + sg_set_buf(mem, buf, PAGE_SIZE << order); - BUG_ON(mem->offset); sg_dma_len(mem) = PAGE_SIZE << order; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c index 0e8b7c44931f..8258d08acd8c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/intf.c +++ b/drivers/net/ethernet/mellanox/mlx4/intf.c @@ -222,6 +222,18 @@ void mlx4_unregister_device(struct mlx4_dev *dev) return; mlx4_stop_catas_poll(dev); + if (dev->persist->interface_state & MLX4_INTERFACE_STATE_DELETION && + mlx4_is_slave(dev)) { + /* In mlx4_remove_one on a VF */ + u32 slave_read = + swab32(readl(&mlx4_priv(dev)->mfunc.comm->slave_read)); + + if (mlx4_comm_internal_err(slave_read)) { + mlx4_dbg(dev, "%s: comm channel is down, entering error state.\n", + __func__); + mlx4_enter_error_state(dev->persist); + } + } mutex_lock(&intf_mutex); list_for_each_entry(intf, &intf_list, list) diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 5e7840a7a33b..bffa6f345f2f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -42,6 +42,7 @@ #include <linux/io-mapping.h> #include <linux/delay.h> #include <linux/kmod.h> +#include <linux/etherdevice.h> #include <net/devlink.h> #include <linux/mlx4/device.h> @@ -782,6 +783,23 @@ int mlx4_is_slave_active(struct mlx4_dev *dev, int slave) } EXPORT_SYMBOL(mlx4_is_slave_active); +void mlx4_handle_eth_header_mcast_prio(struct mlx4_net_trans_rule_hw_ctrl *ctrl, + struct _rule_hw *eth_header) +{ + if (is_multicast_ether_addr(eth_header->eth.dst_mac) || + is_broadcast_ether_addr(eth_header->eth.dst_mac)) { + struct mlx4_net_trans_rule_hw_eth *eth = + (struct mlx4_net_trans_rule_hw_eth *)eth_header; + struct _rule_hw *next_rule = (struct _rule_hw *)(eth + 1); + bool last_rule = next_rule->size == 0 && next_rule->id == 0 && + next_rule->rsvd == 0; + + if (last_rule) + ctrl->prio = cpu_to_be16(MLX4_DOMAIN_NIC); + } +} +EXPORT_SYMBOL(mlx4_handle_eth_header_mcast_prio); + static void slave_adjust_steering_mode(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap, struct mlx4_init_hca_param *hca_param) diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 88ee7d8a5923..086920b615af 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -1220,6 +1220,7 @@ void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type); void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type); void mlx4_enter_error_state(struct mlx4_dev_persistent *persist); +int mlx4_comm_internal_err(u32 slave_read); int mlx4_SENSE_PORT(struct mlx4_dev *dev, int port, enum mlx4_port_type *type); diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index ba1c6cd0cc79..cec59bc264c9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -679,7 +679,8 @@ void mlx4_en_set_stats_bitmap(struct mlx4_dev *dev, int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv, struct mlx4_en_priv *tmp, - struct mlx4_en_port_profile *prof); + struct mlx4_en_port_profile *prof, + bool carry_xdp_prog); void mlx4_en_safe_replace_resources(struct mlx4_en_priv *priv, struct mlx4_en_priv *tmp); diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index c548beaaf910..1822382212ee 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -2980,6 +2980,9 @@ int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave, put_res(dev, slave, srqn, RES_SRQ); qp->srq = srq; } + + /* Save param3 for dynamic changes from VST back to VGT */ + qp->param3 = qpc->param3; put_res(dev, slave, rcqn, RES_CQ); put_res(dev, slave, mtt_base, RES_MTT); res_end_move(dev, slave, RES_QP, qpn); @@ -3772,7 +3775,6 @@ int mlx4_INIT2RTR_QP_wrapper(struct mlx4_dev *dev, int slave, int qpn = vhcr->in_modifier & 0x7fffff; struct res_qp *qp; u8 orig_sched_queue; - __be32 orig_param3 = qpc->param3; u8 orig_vlan_control = qpc->pri_path.vlan_control; u8 orig_fvl_rx = qpc->pri_path.fvl_rx; u8 orig_pri_path_fl = qpc->pri_path.fl; @@ -3814,7 +3816,6 @@ out: */ if (!err) { qp->sched_queue = orig_sched_queue; - qp->param3 = orig_param3; qp->vlan_control = orig_vlan_control; qp->fvl_rx = orig_fvl_rx; qp->pri_path_fl = orig_pri_path_fl; @@ -4164,22 +4165,6 @@ static int validate_eth_header_mac(int slave, struct _rule_hw *eth_header, return 0; } -static void handle_eth_header_mcast_prio(struct mlx4_net_trans_rule_hw_ctrl *ctrl, - struct _rule_hw *eth_header) -{ - if (is_multicast_ether_addr(eth_header->eth.dst_mac) || - is_broadcast_ether_addr(eth_header->eth.dst_mac)) { - struct mlx4_net_trans_rule_hw_eth *eth = - (struct mlx4_net_trans_rule_hw_eth *)eth_header; - struct _rule_hw *next_rule = (struct _rule_hw *)(eth + 1); - bool last_rule = next_rule->size == 0 && next_rule->id == 0 && - next_rule->rsvd == 0; - - if (last_rule) - ctrl->prio = cpu_to_be16(MLX4_DOMAIN_NIC); - } -} - /* * In case of missing eth header, append eth header with a MAC address * assigned to the VF. @@ -4363,10 +4348,7 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave, header_id = map_hw_to_sw_id(be16_to_cpu(rule_header->id)); if (header_id == MLX4_NET_TRANS_RULE_ID_ETH) - handle_eth_header_mcast_prio(ctrl, rule_header); - - if (slave == dev->caps.function) - goto execute; + mlx4_handle_eth_header_mcast_prio(ctrl, rule_header); switch (header_id) { case MLX4_NET_TRANS_RULE_ID_ETH: @@ -4394,7 +4376,6 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave, goto err_put_qp; } -execute: err = mlx4_cmd_imm(dev, inbox->dma, &vhcr->out_param, vhcr->in_modifier, 0, MLX4_QP_FLOW_STEERING_ATTACH, MLX4_CMD_TIME_CLASS_A, @@ -4473,6 +4454,7 @@ int mlx4_QP_FLOW_STEERING_DETACH_wrapper(struct mlx4_dev *dev, int slave, struct res_qp *rqp; struct res_fs_rule *rrule; u64 mirr_reg_id; + int qpn; if (dev->caps.steering_mode != MLX4_STEERING_MODE_DEVICE_MANAGED) @@ -4489,10 +4471,11 @@ int mlx4_QP_FLOW_STEERING_DETACH_wrapper(struct mlx4_dev *dev, int slave, } mirr_reg_id = rrule->mirr_rule_id; kfree(rrule->mirr_mbox); + qpn = rrule->qpn; /* Release the rule form busy state before removal */ put_res(dev, slave, vhcr->in_param, RES_FS_RULE); - err = get_res(dev, slave, rrule->qpn, RES_QP, &rqp); + err = get_res(dev, slave, qpn, RES_QP, &rqp); if (err) return err; @@ -4517,7 +4500,7 @@ int mlx4_QP_FLOW_STEERING_DETACH_wrapper(struct mlx4_dev *dev, int slave, if (!err) atomic_dec(&rqp->ref_count); out: - put_res(dev, slave, rrule->qpn, RES_QP); + put_res(dev, slave, qpn, RES_QP); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 3797cc7c1288..caa837e5e2b9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -1728,7 +1728,7 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev) if (cmd->cmdif_rev > CMD_IF_REV) { dev_err(&dev->pdev->dev, "driver does not support command interface version. driver %d, firmware %d\n", CMD_IF_REV, cmd->cmdif_rev); - err = -ENOTSUPP; + err = -EOPNOTSUPP; goto err_free_page; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 951dbd58594d..d5ecb8f53fd4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -791,7 +791,8 @@ void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv); int mlx5e_modify_rqs_vsd(struct mlx5e_priv *priv, bool vsd); int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz, int ix); -void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv); +void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_priv *priv, void *tirc, + enum mlx5e_traffic_types tt); int mlx5e_open_locked(struct net_device *netdev); int mlx5e_close_locked(struct net_device *netdev); @@ -863,12 +864,12 @@ static inline void mlx5e_arfs_destroy_tables(struct mlx5e_priv *priv) {} static inline int mlx5e_arfs_enable(struct mlx5e_priv *priv) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline int mlx5e_arfs_disable(struct mlx5e_priv *priv) { - return -ENOTSUPP; + return -EOPNOTSUPP; } #else int mlx5e_arfs_create_tables(struct mlx5e_priv *priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 7f6c225666c1..0523ed47f597 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -89,7 +89,7 @@ static int mlx5e_dcbnl_ieee_getets(struct net_device *netdev, int i; if (!MLX5_CAP_GEN(priv->mdev, ets)) - return -ENOTSUPP; + return -EOPNOTSUPP; ets->ets_cap = mlx5_max_tc(priv->mdev) + 1; for (i = 0; i < ets->ets_cap; i++) { @@ -236,7 +236,7 @@ static int mlx5e_dcbnl_ieee_setets(struct net_device *netdev, int err; if (!MLX5_CAP_GEN(priv->mdev, ets)) - return -ENOTSUPP; + return -EOPNOTSUPP; err = mlx5e_dbcnl_validate_ets(netdev, ets); if (err) @@ -402,7 +402,7 @@ static u8 mlx5e_dcbnl_setall(struct net_device *netdev) struct mlx5_core_dev *mdev = priv->mdev; struct ieee_ets ets; struct ieee_pfc pfc; - int err = -ENOTSUPP; + int err = -EOPNOTSUPP; int i; if (!MLX5_CAP_GEN(mdev, ets)) @@ -511,6 +511,11 @@ static void mlx5e_dcbnl_getpgtccfgtx(struct net_device *netdev, struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; + if (!MLX5_CAP_GEN(priv->mdev, ets)) { + netdev_err(netdev, "%s, ets is not supported\n", __func__); + return; + } + if (priority >= CEE_DCBX_MAX_PRIO) { netdev_err(netdev, "%s, priority is out of range\n", __func__); @@ -723,6 +728,9 @@ static void mlx5e_ets_init(struct mlx5e_priv *priv) int i; struct ieee_ets ets; + if (!MLX5_CAP_GEN(priv->mdev, ets)) + return; + memset(&ets, 0, sizeof(ets)); ets.ets_cap = mlx5_max_tc(priv->mdev) + 1; for (i = 0; i < ets.ets_cap; i++) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 352462af8d51..bb67863aa361 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -171,7 +171,6 @@ static int mlx5e_get_sset_count(struct net_device *dev, int sset) return NUM_SW_COUNTERS + MLX5E_NUM_Q_CNTRS(priv) + NUM_VPORT_COUNTERS + NUM_PPORT_COUNTERS + - NUM_PCIE_COUNTERS + MLX5E_NUM_RQ_STATS(priv) + MLX5E_NUM_SQ_STATS(priv) + MLX5E_NUM_PFC_COUNTERS(priv) + @@ -219,14 +218,6 @@ static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, uint8_t *data) strcpy(data + (idx++) * ETH_GSTRING_LEN, pport_2819_stats_desc[i].format); - for (i = 0; i < NUM_PCIE_PERF_COUNTERS; i++) - strcpy(data + (idx++) * ETH_GSTRING_LEN, - pcie_perf_stats_desc[i].format); - - for (i = 0; i < NUM_PCIE_TAS_COUNTERS; i++) - strcpy(data + (idx++) * ETH_GSTRING_LEN, - pcie_tas_stats_desc[i].format); - for (prio = 0; prio < NUM_PPORT_PRIO; prio++) { for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++) sprintf(data + (idx++) * ETH_GSTRING_LEN, @@ -339,14 +330,6 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev, data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.RFC_2819_counters, pport_2819_stats_desc, i); - for (i = 0; i < NUM_PCIE_PERF_COUNTERS; i++) - data[idx++] = MLX5E_READ_CTR32_BE(&priv->stats.pcie.pcie_perf_counters, - pcie_perf_stats_desc, i); - - for (i = 0; i < NUM_PCIE_TAS_COUNTERS; i++) - data[idx++] = MLX5E_READ_CTR32_BE(&priv->stats.pcie.pcie_tas_counters, - pcie_tas_stats_desc, i); - for (prio = 0; prio < NUM_PPORT_PRIO; prio++) { for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++) data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.per_prio_counters[prio], @@ -560,7 +543,6 @@ static int mlx5e_set_channels(struct net_device *dev, struct ethtool_channels *ch) { struct mlx5e_priv *priv = netdev_priv(dev); - int ncv = mlx5e_get_max_num_channels(priv->mdev); unsigned int count = ch->combined_count; bool arfs_enabled; bool was_opened; @@ -571,16 +553,6 @@ static int mlx5e_set_channels(struct net_device *dev, __func__); return -EINVAL; } - if (ch->rx_count || ch->tx_count) { - netdev_info(dev, "%s: separate rx/tx count not supported\n", - __func__); - return -EINVAL; - } - if (count > ncv) { - netdev_info(dev, "%s: count (%d) > max (%d)\n", - __func__, count, ncv); - return -EINVAL; - } if (priv->params.num_channels == count) return 0; @@ -623,7 +595,7 @@ static int mlx5e_get_coalesce(struct net_device *netdev, struct mlx5e_priv *priv = netdev_priv(netdev); if (!MLX5_CAP_GEN(priv->mdev, cq_moderation)) - return -ENOTSUPP; + return -EOPNOTSUPP; coal->rx_coalesce_usecs = priv->params.rx_cq_moderation.usec; coal->rx_max_coalesced_frames = priv->params.rx_cq_moderation.pkts; @@ -648,7 +620,7 @@ static int mlx5e_set_coalesce(struct net_device *netdev, int i; if (!MLX5_CAP_GEN(mdev, cq_moderation)) - return -ENOTSUPP; + return -EOPNOTSUPP; mutex_lock(&priv->state_lock); @@ -1008,15 +980,18 @@ static int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, static void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen) { - struct mlx5_core_dev *mdev = priv->mdev; void *tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx); - int i; + struct mlx5_core_dev *mdev = priv->mdev; + int ctxlen = MLX5_ST_SZ_BYTES(tirc); + int tt; MLX5_SET(modify_tir_in, in, bitmask.hash, 1); - mlx5e_build_tir_ctx_hash(tirc, priv); - for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++) - mlx5_core_modify_tir(mdev, priv->indir_tir[i].tirn, in, inlen); + for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) { + memset(tirc, 0, ctxlen); + mlx5e_build_indir_tir_ctx_hash(priv, tirc, tt); + mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in, inlen); + } } static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, @@ -1024,6 +999,7 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, { struct mlx5e_priv *priv = netdev_priv(dev); int inlen = MLX5_ST_SZ_BYTES(modify_tir_in); + bool hash_changed = false; void *in; if ((hfunc != ETH_RSS_HASH_NO_CHANGE) && @@ -1045,14 +1021,21 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, 0); } - if (key) + if (hfunc != ETH_RSS_HASH_NO_CHANGE && + hfunc != priv->params.rss_hfunc) { + priv->params.rss_hfunc = hfunc; + hash_changed = true; + } + + if (key) { memcpy(priv->params.toeplitz_hash_key, key, sizeof(priv->params.toeplitz_hash_key)); + hash_changed = hash_changed || + priv->params.rss_hfunc == ETH_RSS_HASH_TOP; + } - if (hfunc != ETH_RSS_HASH_NO_CHANGE) - priv->params.rss_hfunc = hfunc; - - mlx5e_modify_tirs_hash(priv, in, inlen); + if (hash_changed) + mlx5e_modify_tirs_hash(priv, in, inlen); mutex_unlock(&priv->state_lock); @@ -1324,7 +1307,7 @@ static int mlx5e_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) u32 mlx5_wol_mode; if (!wol_supported) - return -ENOTSUPP; + return -EOPNOTSUPP; if (wol->wolopts & ~wol_supported) return -EINVAL; @@ -1454,7 +1437,7 @@ static int set_pflag_rx_cqe_based_moder(struct net_device *netdev, bool enable) if (rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE && !MLX5_CAP_GEN(mdev, cq_period_start_from_cqe)) - return -ENOTSUPP; + return -EOPNOTSUPP; if (!rx_mode_changed) return 0; @@ -1480,7 +1463,7 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev, bool reset; if (!MLX5_CAP_GEN(mdev, cqe_compression)) - return -ENOTSUPP; + return -EOPNOTSUPP; if (enable && priv->tstamp.hwtstamp_config.rx_filter != HWTSTAMP_FILTER_NONE) { netdev_err(netdev, "Can't enable cqe compression while timestamping is enabled.\n"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 1fe80de5d68f..a0e5a69402b3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -1089,7 +1089,7 @@ int mlx5e_create_flow_steering(struct mlx5e_priv *priv) MLX5_FLOW_NAMESPACE_KERNEL); if (!priv->fs.ns) - return -EINVAL; + return -EOPNOTSUPP; err = mlx5e_arfs_create_tables(priv); if (err) { 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 3691451c728c..f33f72d0237c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -92,7 +92,7 @@ static struct mlx5e_ethtool_table *get_flow_table(struct mlx5e_priv *priv, ns = mlx5_get_flow_namespace(priv->mdev, MLX5_FLOW_NAMESPACE_ETHTOOL); if (!ns) - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); table_size = min_t(u32, BIT(MLX5_CAP_FLOWTABLE(priv->mdev, flow_table_properties_nic_receive.log_max_ft_size)), @@ -247,6 +247,7 @@ static int set_flow_attrs(u32 *match_c, u32 *match_v, } if (fs->flow_type & FLOW_MAC_EXT && !is_zero_ether_addr(fs->m_ext.h_dest)) { + mask_spec(fs->m_ext.h_dest, fs->h_ext.h_dest, ETH_ALEN); ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_c, dmac_47_16), fs->m_ext.h_dest); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index cbfa38fc72c0..f14ca3385fdd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -291,36 +291,12 @@ static void mlx5e_update_q_counter(struct mlx5e_priv *priv) &qcnt->rx_out_of_buffer); } -static void mlx5e_update_pcie_counters(struct mlx5e_priv *priv) -{ - struct mlx5e_pcie_stats *pcie_stats = &priv->stats.pcie; - struct mlx5_core_dev *mdev = priv->mdev; - int sz = MLX5_ST_SZ_BYTES(mpcnt_reg); - void *out; - u32 *in; - - in = mlx5_vzalloc(sz); - if (!in) - return; - - out = pcie_stats->pcie_perf_counters; - MLX5_SET(mpcnt_reg, in, grp, MLX5_PCIE_PERFORMANCE_COUNTERS_GROUP); - mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_MPCNT, 0, 0); - - out = pcie_stats->pcie_tas_counters; - MLX5_SET(mpcnt_reg, in, grp, MLX5_PCIE_TIMERS_AND_STATES_COUNTERS_GROUP); - mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_MPCNT, 0, 0); - - kvfree(in); -} - void mlx5e_update_stats(struct mlx5e_priv *priv) { mlx5e_update_q_counter(priv); mlx5e_update_vport_counters(priv); mlx5e_update_pport_counters(priv); mlx5e_update_sw_counters(priv); - mlx5e_update_pcie_counters(priv); } void mlx5e_update_stats_work(struct work_struct *work) @@ -2046,8 +2022,23 @@ static void mlx5e_build_tir_ctx_lro(void *tirc, struct mlx5e_priv *priv) MLX5_SET(tirc, tirc, lro_timeout_period_usecs, priv->params.lro_timeout); } -void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv) +void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_priv *priv, void *tirc, + enum mlx5e_traffic_types tt) { + void *hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer); + +#define MLX5_HASH_IP (MLX5_HASH_FIELD_SEL_SRC_IP |\ + MLX5_HASH_FIELD_SEL_DST_IP) + +#define MLX5_HASH_IP_L4PORTS (MLX5_HASH_FIELD_SEL_SRC_IP |\ + MLX5_HASH_FIELD_SEL_DST_IP |\ + MLX5_HASH_FIELD_SEL_L4_SPORT |\ + MLX5_HASH_FIELD_SEL_L4_DPORT) + +#define MLX5_HASH_IP_IPSEC_SPI (MLX5_HASH_FIELD_SEL_SRC_IP |\ + MLX5_HASH_FIELD_SEL_DST_IP |\ + MLX5_HASH_FIELD_SEL_IPSEC_SPI) + MLX5_SET(tirc, tirc, rx_hash_fn, mlx5e_rx_hash_fn(priv->params.rss_hfunc)); if (priv->params.rss_hfunc == ETH_RSS_HASH_TOP) { @@ -2059,6 +2050,88 @@ void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv) MLX5_SET(tirc, tirc, rx_hash_symmetric, 1); memcpy(rss_key, priv->params.toeplitz_hash_key, len); } + + switch (tt) { + case MLX5E_TT_IPV4_TCP: + MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, + MLX5_L3_PROT_TYPE_IPV4); + MLX5_SET(rx_hash_field_select, hfso, l4_prot_type, + MLX5_L4_PROT_TYPE_TCP); + MLX5_SET(rx_hash_field_select, hfso, selected_fields, + MLX5_HASH_IP_L4PORTS); + break; + + case MLX5E_TT_IPV6_TCP: + MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, + MLX5_L3_PROT_TYPE_IPV6); + MLX5_SET(rx_hash_field_select, hfso, l4_prot_type, + MLX5_L4_PROT_TYPE_TCP); + MLX5_SET(rx_hash_field_select, hfso, selected_fields, + MLX5_HASH_IP_L4PORTS); + break; + + case MLX5E_TT_IPV4_UDP: + MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, + MLX5_L3_PROT_TYPE_IPV4); + MLX5_SET(rx_hash_field_select, hfso, l4_prot_type, + MLX5_L4_PROT_TYPE_UDP); + MLX5_SET(rx_hash_field_select, hfso, selected_fields, + MLX5_HASH_IP_L4PORTS); + break; + + case MLX5E_TT_IPV6_UDP: + MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, + MLX5_L3_PROT_TYPE_IPV6); + MLX5_SET(rx_hash_field_select, hfso, l4_prot_type, + MLX5_L4_PROT_TYPE_UDP); + MLX5_SET(rx_hash_field_select, hfso, selected_fields, + MLX5_HASH_IP_L4PORTS); + break; + + case MLX5E_TT_IPV4_IPSEC_AH: + MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, + MLX5_L3_PROT_TYPE_IPV4); + MLX5_SET(rx_hash_field_select, hfso, selected_fields, + MLX5_HASH_IP_IPSEC_SPI); + break; + + case MLX5E_TT_IPV6_IPSEC_AH: + MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, + MLX5_L3_PROT_TYPE_IPV6); + MLX5_SET(rx_hash_field_select, hfso, selected_fields, + MLX5_HASH_IP_IPSEC_SPI); + break; + + case MLX5E_TT_IPV4_IPSEC_ESP: + MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, + MLX5_L3_PROT_TYPE_IPV4); + MLX5_SET(rx_hash_field_select, hfso, selected_fields, + MLX5_HASH_IP_IPSEC_SPI); + break; + + case MLX5E_TT_IPV6_IPSEC_ESP: + MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, + MLX5_L3_PROT_TYPE_IPV6); + MLX5_SET(rx_hash_field_select, hfso, selected_fields, + MLX5_HASH_IP_IPSEC_SPI); + break; + + case MLX5E_TT_IPV4: + MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, + MLX5_L3_PROT_TYPE_IPV4); + MLX5_SET(rx_hash_field_select, hfso, selected_fields, + MLX5_HASH_IP); + break; + + case MLX5E_TT_IPV6: + MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, + MLX5_L3_PROT_TYPE_IPV6); + MLX5_SET(rx_hash_field_select, hfso, selected_fields, + MLX5_HASH_IP); + break; + default: + WARN_ONCE(true, "%s: bad traffic type!\n", __func__); + } } static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv) @@ -2428,110 +2501,13 @@ void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv) static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv, u32 *tirc, enum mlx5e_traffic_types tt) { - void *hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer); - MLX5_SET(tirc, tirc, transport_domain, priv->mdev->mlx5e_res.td.tdn); -#define MLX5_HASH_IP (MLX5_HASH_FIELD_SEL_SRC_IP |\ - MLX5_HASH_FIELD_SEL_DST_IP) - -#define MLX5_HASH_IP_L4PORTS (MLX5_HASH_FIELD_SEL_SRC_IP |\ - MLX5_HASH_FIELD_SEL_DST_IP |\ - MLX5_HASH_FIELD_SEL_L4_SPORT |\ - MLX5_HASH_FIELD_SEL_L4_DPORT) - -#define MLX5_HASH_IP_IPSEC_SPI (MLX5_HASH_FIELD_SEL_SRC_IP |\ - MLX5_HASH_FIELD_SEL_DST_IP |\ - MLX5_HASH_FIELD_SEL_IPSEC_SPI) - mlx5e_build_tir_ctx_lro(tirc, priv); MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT); MLX5_SET(tirc, tirc, indirect_table, priv->indir_rqt.rqtn); - mlx5e_build_tir_ctx_hash(tirc, priv); - - switch (tt) { - case MLX5E_TT_IPV4_TCP: - MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, - MLX5_L3_PROT_TYPE_IPV4); - MLX5_SET(rx_hash_field_select, hfso, l4_prot_type, - MLX5_L4_PROT_TYPE_TCP); - MLX5_SET(rx_hash_field_select, hfso, selected_fields, - MLX5_HASH_IP_L4PORTS); - break; - - case MLX5E_TT_IPV6_TCP: - MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, - MLX5_L3_PROT_TYPE_IPV6); - MLX5_SET(rx_hash_field_select, hfso, l4_prot_type, - MLX5_L4_PROT_TYPE_TCP); - MLX5_SET(rx_hash_field_select, hfso, selected_fields, - MLX5_HASH_IP_L4PORTS); - break; - - case MLX5E_TT_IPV4_UDP: - MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, - MLX5_L3_PROT_TYPE_IPV4); - MLX5_SET(rx_hash_field_select, hfso, l4_prot_type, - MLX5_L4_PROT_TYPE_UDP); - MLX5_SET(rx_hash_field_select, hfso, selected_fields, - MLX5_HASH_IP_L4PORTS); - break; - - case MLX5E_TT_IPV6_UDP: - MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, - MLX5_L3_PROT_TYPE_IPV6); - MLX5_SET(rx_hash_field_select, hfso, l4_prot_type, - MLX5_L4_PROT_TYPE_UDP); - MLX5_SET(rx_hash_field_select, hfso, selected_fields, - MLX5_HASH_IP_L4PORTS); - break; - - case MLX5E_TT_IPV4_IPSEC_AH: - MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, - MLX5_L3_PROT_TYPE_IPV4); - MLX5_SET(rx_hash_field_select, hfso, selected_fields, - MLX5_HASH_IP_IPSEC_SPI); - break; - - case MLX5E_TT_IPV6_IPSEC_AH: - MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, - MLX5_L3_PROT_TYPE_IPV6); - MLX5_SET(rx_hash_field_select, hfso, selected_fields, - MLX5_HASH_IP_IPSEC_SPI); - break; - - case MLX5E_TT_IPV4_IPSEC_ESP: - MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, - MLX5_L3_PROT_TYPE_IPV4); - MLX5_SET(rx_hash_field_select, hfso, selected_fields, - MLX5_HASH_IP_IPSEC_SPI); - break; - - case MLX5E_TT_IPV6_IPSEC_ESP: - MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, - MLX5_L3_PROT_TYPE_IPV6); - MLX5_SET(rx_hash_field_select, hfso, selected_fields, - MLX5_HASH_IP_IPSEC_SPI); - break; - - case MLX5E_TT_IPV4: - MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, - MLX5_L3_PROT_TYPE_IPV4); - MLX5_SET(rx_hash_field_select, hfso, selected_fields, - MLX5_HASH_IP); - break; - - case MLX5E_TT_IPV6: - MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, - MLX5_L3_PROT_TYPE_IPV6); - MLX5_SET(rx_hash_field_select, hfso, selected_fields, - MLX5_HASH_IP); - break; - default: - WARN_ONCE(true, - "mlx5e_build_indir_tir_ctx: bad traffic type!\n"); - } + mlx5e_build_indir_tir_ctx_hash(priv, tirc, tt); } static void mlx5e_build_direct_tir_ctx(struct mlx5e_priv *priv, u32 *tirc, @@ -3355,7 +3331,7 @@ static const struct net_device_ops mlx5e_netdev_ops_sriov = { static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev) { if (MLX5_CAP_GEN(mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH) - return -ENOTSUPP; + return -EOPNOTSUPP; if (!MLX5_CAP_GEN(mdev, eth_net_offloads) || !MLX5_CAP_GEN(mdev, nic_flow_table) || !MLX5_CAP_ETH(mdev, csum_cap) || @@ -3367,7 +3343,7 @@ static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev) < 3) { mlx5_core_warn(mdev, "Not creating net device, some required device capabilities are missing\n"); - return -ENOTSUPP; + return -EOPNOTSUPP; } if (!MLX5_CAP_ETH(mdev, self_lb_en_modifiable)) mlx5_core_warn(mdev, "Self loop back prevention is not supported\n"); @@ -3699,14 +3675,8 @@ static void mlx5e_nic_init(struct mlx5_core_dev *mdev, static void mlx5e_nic_cleanup(struct mlx5e_priv *priv) { - struct mlx5_core_dev *mdev = priv->mdev; - struct mlx5_eswitch *esw = mdev->priv.eswitch; - mlx5e_vxlan_cleanup(priv); - if (MLX5_CAP_GEN(mdev, vport_group_manager)) - mlx5_eswitch_unregister_vport_rep(esw, 0); - if (priv->xdp_prog) bpf_prog_put(priv->xdp_prog); } @@ -3805,14 +3775,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) mlx5_lag_add(mdev, netdev); - if (mlx5e_vxlan_allowed(mdev)) { - rtnl_lock(); - udp_tunnel_get_rx_info(netdev); - rtnl_unlock(); - } - mlx5e_enable_async_events(priv); - queue_work(priv->wq, &priv->set_rx_mode_work); if (MLX5_CAP_GEN(mdev, vport_group_manager)) { mlx5_query_nic_vport_mac_address(mdev, 0, rep.hw_id); @@ -3822,13 +3785,30 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) rep.netdev = netdev; mlx5_eswitch_register_vport_rep(esw, 0, &rep); } + + if (netdev->reg_state != NETREG_REGISTERED) + return; + + /* Device already registered: sync netdev system state */ + if (mlx5e_vxlan_allowed(mdev)) { + rtnl_lock(); + udp_tunnel_get_rx_info(netdev); + rtnl_unlock(); + } + + queue_work(priv->wq, &priv->set_rx_mode_work); } static void mlx5e_nic_disable(struct mlx5e_priv *priv) { + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5_eswitch *esw = mdev->priv.eswitch; + queue_work(priv->wq, &priv->set_rx_mode_work); + if (MLX5_CAP_GEN(mdev, vport_group_manager)) + mlx5_eswitch_unregister_vport_rep(esw, 0); mlx5e_disable_async_events(priv); - mlx5_lag_remove(priv->mdev); + mlx5_lag_remove(mdev); } static const struct mlx5e_profile mlx5e_nic_profile = { @@ -3966,10 +3946,6 @@ void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev) const struct mlx5e_profile *profile = priv->profile; set_bit(MLX5E_STATE_DESTROYING, &priv->state); - if (profile->disable) - profile->disable(priv); - - flush_workqueue(priv->wq); rtnl_lock(); if (netif_running(netdev)) @@ -3977,6 +3953,10 @@ void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev) netif_device_detach(netdev); rtnl_unlock(); + if (profile->disable) + profile->disable(priv); + flush_workqueue(priv->wq); + mlx5e_destroy_q_counter(priv); profile->cleanup_rx(priv); mlx5e_close_drop_rq(priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 0e2fb3ed1790..06d5e6fecb0a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -193,6 +193,9 @@ static inline bool mlx5e_rx_cache_put(struct mlx5e_rq *rq, return false; } + if (unlikely(page_is_pfmemalloc(dma_info->page))) + return false; + cache->page_cache[cache->tail] = *dma_info; cache->tail = tail_next; return true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c index 1fffe48a93cc..cbfac06b7ffd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c @@ -109,7 +109,6 @@ static bool mlx5e_am_on_top(struct mlx5e_rx_am *am) switch (am->tune_state) { case MLX5E_AM_PARKING_ON_TOP: case MLX5E_AM_PARKING_TIRED: - WARN_ONCE(true, "mlx5e_am_on_top: PARKING\n"); return true; case MLX5E_AM_GOING_RIGHT: return (am->steps_left > 1) && (am->steps_right == 1); @@ -123,7 +122,6 @@ static void mlx5e_am_turn(struct mlx5e_rx_am *am) switch (am->tune_state) { case MLX5E_AM_PARKING_ON_TOP: case MLX5E_AM_PARKING_TIRED: - WARN_ONCE(true, "mlx5e_am_turn: PARKING\n"); break; case MLX5E_AM_GOING_RIGHT: am->tune_state = MLX5E_AM_GOING_LEFT; @@ -144,7 +142,6 @@ static int mlx5e_am_step(struct mlx5e_rx_am *am) switch (am->tune_state) { case MLX5E_AM_PARKING_ON_TOP: case MLX5E_AM_PARKING_TIRED: - WARN_ONCE(true, "mlx5e_am_step: PARKING\n"); break; case MLX5E_AM_GOING_RIGHT: if (am->profile_ix == (MLX5E_PARAMS_AM_NUM_PROFILES - 1)) @@ -282,10 +279,8 @@ static void mlx5e_am_calc_stats(struct mlx5e_rx_am_sample *start, u32 delta_us = ktime_us_delta(end->time, start->time); unsigned int npkts = end->pkt_ctr - start->pkt_ctr; - if (!delta_us) { - WARN_ONCE(true, "mlx5e_am_calc_stats: delta_us=0\n"); + if (!delta_us) return; - } curr_stats->ppms = (npkts * USEC_PER_MSEC) / delta_us; curr_stats->epms = (MLX5E_AM_NEVENTS * USEC_PER_MSEC) / delta_us; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index f202f872f57f..ba5db1dd23a9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -39,7 +39,7 @@ #define MLX5E_READ_CTR32_CPU(ptr, dsc, i) \ (*(u32 *)((char *)ptr + dsc[i].offset)) #define MLX5E_READ_CTR32_BE(ptr, dsc, i) \ - be32_to_cpu(*(__be32 *)((char *)ptr + dsc[i].offset)) + be64_to_cpu(*(__be32 *)((char *)ptr + dsc[i].offset)) #define MLX5E_DECLARE_STAT(type, fld) #fld, offsetof(type, fld) #define MLX5E_DECLARE_RX_STAT(type, fld) "rx%d_"#fld, offsetof(type, fld) @@ -276,32 +276,6 @@ static const struct counter_desc pport_per_prio_pfc_stats_desc[] = { { "rx_%s_pause_transition", PPORT_PER_PRIO_OFF(rx_pause_transition) }, }; -#define PCIE_PERF_OFF(c) \ - MLX5_BYTE_OFF(mpcnt_reg, counter_set.pcie_perf_cntrs_grp_data_layout.c) -#define PCIE_PERF_GET(pcie_stats, c) \ - MLX5_GET(mpcnt_reg, pcie_stats->pcie_perf_counters, \ - counter_set.pcie_perf_cntrs_grp_data_layout.c) -#define PCIE_TAS_OFF(c) \ - MLX5_BYTE_OFF(mpcnt_reg, counter_set.pcie_tas_cntrs_grp_data_layout.c) -#define PCIE_TAS_GET(pcie_stats, c) \ - MLX5_GET(mpcnt_reg, pcie_stats->pcie_tas_counters, \ - counter_set.pcie_tas_cntrs_grp_data_layout.c) - -struct mlx5e_pcie_stats { - __be64 pcie_perf_counters[MLX5_ST_SZ_QW(mpcnt_reg)]; - __be64 pcie_tas_counters[MLX5_ST_SZ_QW(mpcnt_reg)]; -}; - -static const struct counter_desc pcie_perf_stats_desc[] = { - { "rx_pci_signal_integrity", PCIE_PERF_OFF(rx_errors) }, - { "tx_pci_signal_integrity", PCIE_PERF_OFF(tx_errors) }, -}; - -static const struct counter_desc pcie_tas_stats_desc[] = { - { "tx_pci_transport_nonfatal_msg", PCIE_TAS_OFF(non_fatal_err_msg_sent) }, - { "tx_pci_transport_fatal_msg", PCIE_TAS_OFF(fatal_err_msg_sent) }, -}; - struct mlx5e_rq_stats { u64 packets; u64 bytes; @@ -386,8 +360,6 @@ static const struct counter_desc sq_stats_desc[] = { #define NUM_PPORT_802_3_COUNTERS ARRAY_SIZE(pport_802_3_stats_desc) #define NUM_PPORT_2863_COUNTERS ARRAY_SIZE(pport_2863_stats_desc) #define NUM_PPORT_2819_COUNTERS ARRAY_SIZE(pport_2819_stats_desc) -#define NUM_PCIE_PERF_COUNTERS ARRAY_SIZE(pcie_perf_stats_desc) -#define NUM_PCIE_TAS_COUNTERS ARRAY_SIZE(pcie_tas_stats_desc) #define NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS \ ARRAY_SIZE(pport_per_prio_traffic_stats_desc) #define NUM_PPORT_PER_PRIO_PFC_COUNTERS \ @@ -397,7 +369,6 @@ static const struct counter_desc sq_stats_desc[] = { NUM_PPORT_2819_COUNTERS + \ NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS * \ NUM_PPORT_PRIO) -#define NUM_PCIE_COUNTERS (NUM_PCIE_PERF_COUNTERS + NUM_PCIE_TAS_COUNTERS) #define NUM_RQ_STATS ARRAY_SIZE(rq_stats_desc) #define NUM_SQ_STATS ARRAY_SIZE(sq_stats_desc) @@ -406,7 +377,6 @@ struct mlx5e_stats { struct mlx5e_qcounter_stats qcnt; struct mlx5e_vport_stats vport; struct mlx5e_pport_stats pport; - struct mlx5e_pcie_stats pcie; struct rtnl_link_stats64 vf_vport; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index f8829b517156..c5282b6aba8b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -161,15 +161,21 @@ static void mlx5e_detach_encap(struct mlx5e_priv *priv, } } +/* we get here also when setting rule to the FW failed, etc. It means that the + * flow rule itself might not exist, but some offloading related to the actions + * should be cleaned. + */ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_fc *counter = NULL; - counter = mlx5_flow_rule_counter(flow->rule); - - mlx5_del_flow_rules(flow->rule); + if (!IS_ERR(flow->rule)) { + counter = mlx5_flow_rule_counter(flow->rule); + mlx5_del_flow_rules(flow->rule); + mlx5_fc_destroy(priv->mdev, counter); + } if (esw && esw->mode == SRIOV_OFFLOADS) { mlx5_eswitch_del_vlan_action(esw, flow->attr); @@ -177,8 +183,6 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, mlx5e_detach_encap(priv, flow); } - mlx5_fc_destroy(priv->mdev, counter); - if (!mlx5e_tc_num_filters(priv) && (priv->fs.tc.t)) { mlx5_destroy_flow_table(priv->fs.tc.t); priv->fs.tc.t = NULL; @@ -225,6 +229,11 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers); + struct flow_dissector_key_control *enc_control = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ENC_CONTROL, + f->key); + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) { struct flow_dissector_key_ports *key = skb_flow_dissector_target(f->dissector, @@ -237,28 +246,34 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, /* Full udp dst port must be given */ if (memchr_inv(&mask->dst, 0xff, sizeof(mask->dst))) - return -EOPNOTSUPP; - - /* udp src port isn't supported */ - if (memchr_inv(&mask->src, 0, sizeof(mask->src))) - return -EOPNOTSUPP; + goto vxlan_match_offload_err; if (mlx5e_vxlan_lookup_port(priv, be16_to_cpu(key->dst)) && MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) parse_vxlan_attr(spec, f); - else + else { + netdev_warn(priv->netdev, + "%d isn't an offloaded vxlan udp dport\n", be16_to_cpu(key->dst)); return -EOPNOTSUPP; + } MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_dport, ntohs(mask->dst)); MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_dport, ntohs(key->dst)); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, + udp_sport, ntohs(mask->src)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, + udp_sport, ntohs(key->src)); } else { /* udp dst port must be given */ - return -EOPNOTSUPP; +vxlan_match_offload_err: + netdev_warn(priv->netdev, + "IP tunnel decap offload supported only for vxlan, must set UDP dport\n"); + return -EOPNOTSUPP; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { + if (enc_control->addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { struct flow_dissector_key_ipv4_addrs *key = skb_flow_dissector_target(f->dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, @@ -280,10 +295,10 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, MLX5_SET(fte_match_set_lyr_2_4, headers_v, dst_ipv4_dst_ipv6.ipv4_layout.ipv4, ntohl(key->dst)); - } - MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ethertype); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IP); + MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ethertype); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IP); + } /* Enforce DMAC when offloading incoming tunneled flows. * Flow counters require a match on the DMAC. @@ -346,6 +361,9 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, if (parse_tunnel_attr(priv, spec, f)) return -EOPNOTSUPP; break; + case FLOW_DISSECTOR_KEY_IPV6_ADDRS: + netdev_warn(priv->netdev, + "IPv6 tunnel decap offload isn't supported\n"); default: return -EOPNOTSUPP; } @@ -375,6 +393,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1); MLX5_SET(fte_match_set_lyr_2_4, headers_v, frag, key->flags & FLOW_DIS_IS_FRAGMENT); + + /* the HW doesn't need L3 inline to match on frag=no */ + if (key->flags & FLOW_DIS_IS_FRAGMENT) + *min_inline = MLX5_INLINE_MODE_IP; } } @@ -641,26 +663,26 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv, __be32 *saddr, int *out_ttl) { + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct rtable *rt; struct neighbour *n = NULL; int ttl; #if IS_ENABLED(CONFIG_INET) + int ret; + rt = ip_route_output_key(dev_net(mirred_dev), fl4); - if (IS_ERR(rt)) { - pr_warn("%s: no route to %pI4\n", __func__, &fl4->daddr); - return -EOPNOTSUPP; - } + ret = PTR_ERR_OR_ZERO(rt); + if (ret) + return ret; #else return -EOPNOTSUPP; #endif - - if (!switchdev_port_same_parent_id(priv->netdev, rt->dst.dev)) { - pr_warn("%s: Can't offload the flow, netdevices aren't on the same HW e-switch\n", - __func__); - ip_rt_put(rt); - return -EOPNOTSUPP; - } + /* if the egress device isn't on the same HW e-switch, we use the uplink */ + if (!switchdev_port_same_parent_id(priv->netdev, rt->dst.dev)) + *out_dev = mlx5_eswitch_get_uplink_netdev(esw); + else + *out_dev = rt->dst.dev; ttl = ip4_dst_hoplimit(&rt->dst); n = dst_neigh_lookup(&rt->dst, &fl4->daddr); @@ -671,7 +693,6 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv, *out_n = n; *saddr = fl4->saddr; *out_ttl = ttl; - *out_dev = rt->dst.dev; return 0; } @@ -718,8 +739,8 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, struct net_device **out_dev) { int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size); + struct neighbour *n = NULL; struct flowi4 fl4 = {}; - struct neighbour *n; char *encap_header; int encap_size; __be32 saddr; @@ -750,7 +771,8 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, e->out_dev = *out_dev; if (!(n->nud_state & NUD_VALID)) { - err = -ENOTSUPP; + pr_warn("%s: can't offload, neighbour to %pI4 invalid\n", __func__, &fl4.daddr); + err = -EOPNOTSUPP; goto out; } @@ -772,6 +794,8 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, err = mlx5_encap_alloc(priv->mdev, e->tunnel_type, encap_size, encap_header, &e->encap_id); out: + if (err && n) + neigh_release(n); kfree(encap_header); return err; } @@ -792,9 +816,17 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, int tunnel_type; int err; - /* udp dst port must be given */ + /* udp dst port must be set */ if (!memchr_inv(&key->tp_dst, 0, sizeof(key->tp_dst))) + goto vxlan_encap_offload_err; + + /* setting udp src port isn't supported */ + if (memchr_inv(&key->tp_src, 0, sizeof(key->tp_src))) { +vxlan_encap_offload_err: + netdev_warn(priv->netdev, + "must set udp dst port and not set udp src port\n"); return -EOPNOTSUPP; + } if (mlx5e_vxlan_lookup_port(priv, be16_to_cpu(key->tp_dst)) && MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) { @@ -802,6 +834,8 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, info.tun_id = tunnel_id_to_key32(key->tun_id); tunnel_type = MLX5_HEADER_TYPE_VXLAN; } else { + netdev_warn(priv->netdev, + "%d isn't an offloaded vxlan udp dport\n", be16_to_cpu(key->tp_dst)); return -EOPNOTSUPP; } @@ -809,6 +843,9 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, case AF_INET: info.daddr = key->u.ipv4.dst; break; + case AF_INET6: + netdev_warn(priv->netdev, + "IPv6 tunnel encap offload isn't supported\n"); default: return -EOPNOTSUPP; } @@ -986,7 +1023,7 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol, if (IS_ERR(flow->rule)) { err = PTR_ERR(flow->rule); - goto err_free; + goto err_del_rule; } err = rhashtable_insert_fast(&tc->ht, &flow->node, @@ -997,7 +1034,7 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol, goto out; err_del_rule: - mlx5_del_flow_rules(flow->rule); + mlx5e_tc_del_flow(priv, flow); err_free: kfree(flow); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index d6807c3cc461..d0c8bf014453 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -133,7 +133,7 @@ static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u32 vport, if (!MLX5_CAP_ESW(dev, vport_cvlan_strip) || !MLX5_CAP_ESW(dev, vport_cvlan_insert_if_not_exist)) - return -ENOTSUPP; + return -EOPNOTSUPP; esw_debug(dev, "Set Vport[%d] VLAN %d qos %d set=%x\n", vport, vlan, qos, set_flags); @@ -353,7 +353,7 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw, int nvports) root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB); if (!root_ns) { esw_warn(dev, "Failed to get FDB flow namespace\n"); - return -ENOMEM; + return -EOPNOTSUPP; } flow_group_in = mlx5_vzalloc(inlen); @@ -962,7 +962,7 @@ static int esw_vport_enable_egress_acl(struct mlx5_eswitch *esw, root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_EGRESS); if (!root_ns) { esw_warn(dev, "Failed to get E-Switch egress flow namespace\n"); - return -EIO; + return -EOPNOTSUPP; } flow_group_in = mlx5_vzalloc(inlen); @@ -1079,7 +1079,7 @@ static int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw, root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS); if (!root_ns) { esw_warn(dev, "Failed to get E-Switch ingress flow namespace\n"); - return -EIO; + return -EOPNOTSUPP; } flow_group_in = mlx5_vzalloc(inlen); @@ -1630,7 +1630,7 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) if (!MLX5_CAP_GEN(esw->dev, eswitch_flow_table) || !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) { esw_warn(esw->dev, "E-Switch FDB is not supported, aborting ...\n"); - return -ENOTSUPP; + return -EOPNOTSUPP; } if (!MLX5_CAP_ESW_INGRESS_ACL(esw->dev, ft_support)) @@ -1860,7 +1860,7 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw, if (!ESW_ALLOWED(esw)) return -EPERM; - if (!LEGAL_VPORT(esw, vport)) + if (!LEGAL_VPORT(esw, vport) || is_multicast_ether_addr(mac)) return -EINVAL; mutex_lock(&esw->state_lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 466e161010f7..595f7c7383b3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -166,7 +166,7 @@ static int esw_add_vlan_action_check(struct mlx5_esw_flow_attr *attr, return 0; out_notsupp: - return -ENOTSUPP; + return -EOPNOTSUPP; } int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw, @@ -424,6 +424,7 @@ static int esw_create_offloads_fdb_table(struct mlx5_eswitch *esw, int nvports) root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB); if (!root_ns) { esw_warn(dev, "Failed to get FDB flow namespace\n"); + err = -EOPNOTSUPP; goto ns_err; } @@ -535,7 +536,7 @@ static int esw_create_offloads_table(struct mlx5_eswitch *esw) ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_OFFLOADS); if (!ns) { esw_warn(esw->dev, "Failed to get offloads flow namespace\n"); - return -ENOMEM; + return -EOPNOTSUPP; } ft_offloads = mlx5_create_flow_table(ns, 0, dev->priv.sriov.num_vfs + 2, 0, 0); @@ -655,7 +656,7 @@ static int esw_offloads_start(struct mlx5_eswitch *esw) esw_warn(esw->dev, "Failed setting eswitch to offloads, err %d\n", err); err1 = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY); if (err1) - esw_warn(esw->dev, "Failed setting eswitch back to legacy, err %d\n", err); + esw_warn(esw->dev, "Failed setting eswitch back to legacy, err %d\n", err1); } if (esw->offloads.inline_mode == MLX5_INLINE_MODE_NONE) { if (mlx5_eswitch_inline_mode_get(esw, @@ -674,9 +675,14 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int nvports) int vport; int err; + /* disable PF RoCE so missed packets don't go through RoCE steering */ + mlx5_dev_list_lock(); + mlx5_remove_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); + mlx5_dev_list_unlock(); + err = esw_create_offloads_fdb_table(esw, nvports); if (err) - return err; + goto create_fdb_err; err = esw_create_offloads_table(esw); if (err) @@ -695,6 +701,7 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int nvports) if (err) goto err_reps; } + return 0; err_reps: @@ -711,6 +718,13 @@ create_fg_err: create_ft_err: esw_destroy_offloads_fdb_table(esw); + +create_fdb_err: + /* enable back PF RoCE */ + mlx5_dev_list_lock(); + mlx5_add_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); + mlx5_dev_list_unlock(); + return err; } @@ -727,6 +741,11 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw) esw_warn(esw->dev, "Failed setting eswitch back to offloads, err %d\n", err); } + /* enable back PF RoCE */ + mlx5_dev_list_lock(); + mlx5_add_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); + mlx5_dev_list_unlock(); + return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index c4478ecd8056..b53fc85a2375 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -322,7 +322,7 @@ int mlx5_cmd_update_fte(struct mlx5_core_dev *dev, flow_table_properties_nic_receive. flow_modify_en); if (!atomic_mod_cap) - return -ENOTSUPP; + return -EOPNOTSUPP; opmod = 1; return mlx5_cmd_set_fte(dev, opmod, modify_mask, ft, group_id, fte); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index a263d8904a4c..6346a8f5883b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1263,6 +1263,7 @@ static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg, nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD); handle = add_rule_fte(fte, fg, dest, dest_num, false); if (IS_ERR(handle)) { + unlock_ref_node(&fte->node); kfree(fte); goto unlock_fg; } @@ -1821,7 +1822,7 @@ static int create_anchor_flow_table(struct mlx5_flow_steering *steering) struct mlx5_flow_table *ft; ns = mlx5_get_flow_namespace(steering->dev, MLX5_FLOW_NAMESPACE_ANCHOR); - if (!ns) + if (WARN_ON(!ns)) return -EINVAL; ft = mlx5_create_flow_table(ns, ANCHOR_PRIO, ANCHOR_SIZE, ANCHOR_LEVEL, 0); if (IS_ERR(ft)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 54e5a786f191..3c315eb8d270 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -503,6 +503,13 @@ static int handle_hca_cap(struct mlx5_core_dev *dev) MLX5_SET(cmd_hca_cap, set_hca_cap, pkey_table_size, to_fw_pkey_sz(dev, 128)); + /* Check log_max_qp from HCA caps to set in current profile */ + if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < profile[prof_sel].log_max_qp) { + mlx5_core_warn(dev, "log_max_qp value in current profile is %d, changing it to HCA capability limit (%d)\n", + profile[prof_sel].log_max_qp, + MLX5_CAP_GEN_MAX(dev, log_max_qp)); + profile[prof_sel].log_max_qp = MLX5_CAP_GEN_MAX(dev, log_max_qp); + } if (prof->mask & MLX5_PROF_MASK_QP_SIZE) MLX5_SET(cmd_hca_cap, set_hca_cap, log_max_qp, prof->log_max_qp); @@ -575,7 +582,6 @@ static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i) struct mlx5_priv *priv = &mdev->priv; struct msix_entry *msix = priv->msix_arr; int irq = msix[i + MLX5_EQ_VEC_COMP_BASE].vector; - int numa_node = priv->numa_node; int err; if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) { @@ -583,7 +589,7 @@ static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i) return -ENOMEM; } - cpumask_set_cpu(cpumask_local_spread(i, numa_node), + cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node), priv->irq_info[i].mask); err = irq_set_affinity_hint(irq, priv->irq_info[i].mask); @@ -801,7 +807,7 @@ static int mlx5_core_set_issi(struct mlx5_core_dev *dev) return 0; } - return -ENOTSUPP; + return -EOPNOTSUPP; } @@ -1189,6 +1195,9 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, { int err = 0; + if (cleanup) + mlx5_drain_health_wq(dev); + mutex_lock(&dev->intf_state_mutex); if (test_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state)) { dev_warn(&dev->pdev->dev, "%s: interface is down, NOP\n", @@ -1351,7 +1360,7 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev, mlx5_enter_error_state(dev); mlx5_unload_one(dev, priv, false); - /* In case of kernel call save the pci state and drain health wq */ + /* In case of kernel call save the pci state and drain the health wq */ if (state) { pci_save_state(pdev); mlx5_drain_health_wq(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index d2ec9d232a70..fd12e0a377a5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -620,7 +620,7 @@ static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in, u32 out[MLX5_ST_SZ_DW(qtct_reg)]; if (!MLX5_CAP_GEN(mdev, ets)) - return -ENOTSUPP; + return -EOPNOTSUPP; return mlx5_core_access_reg(mdev, in, inlen, out, sizeof(out), MLX5_REG_QETCR, 0, 1); @@ -632,7 +632,7 @@ static int mlx5_query_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *out, u32 in[MLX5_ST_SZ_DW(qtct_reg)]; if (!MLX5_CAP_GEN(mdev, ets)) - return -ENOTSUPP; + return -EOPNOTSUPP; memset(in, 0, sizeof(in)); return mlx5_core_access_reg(mdev, in, sizeof(in), out, outlen, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 269e4401c342..7129c30a2ab4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -532,7 +532,7 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev, if (!MLX5_CAP_GEN(mdev, vport_group_manager)) return -EACCES; if (!MLX5_CAP_ESW(mdev, nic_vport_node_guid_modify)) - return -ENOTSUPP; + return -EOPNOTSUPP; in = mlx5_vzalloc(inlen); if (!in) diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h index d147ddd97997..0af3338bfcb4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h @@ -209,21 +209,21 @@ MLXSW_ITEM32(pci, eqe, owner, 0x0C, 0, 1); /* pci_eqe_cmd_token * Command completion event - token */ -MLXSW_ITEM32(pci, eqe, cmd_token, 0x08, 16, 16); +MLXSW_ITEM32(pci, eqe, cmd_token, 0x00, 16, 16); /* pci_eqe_cmd_status * Command completion event - status */ -MLXSW_ITEM32(pci, eqe, cmd_status, 0x08, 0, 8); +MLXSW_ITEM32(pci, eqe, cmd_status, 0x00, 0, 8); /* pci_eqe_cmd_out_param_h * Command completion event - output parameter - higher part */ -MLXSW_ITEM32(pci, eqe, cmd_out_param_h, 0x0C, 0, 32); +MLXSW_ITEM32(pci, eqe, cmd_out_param_h, 0x04, 0, 32); /* pci_eqe_cmd_out_param_l * Command completion event - output parameter - lower part */ -MLXSW_ITEM32(pci, eqe, cmd_out_param_l, 0x10, 0, 32); +MLXSW_ITEM32(pci, eqe, cmd_out_param_l, 0x08, 0, 32); #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index d768c7b6c6d6..003093abb170 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -684,6 +684,7 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb, dev_kfree_skb_any(skb_orig); return NETDEV_TX_OK; } + dev_consume_skb_any(skb_orig); } if (eth_skb_pad(skb)) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 01d0efa9c5c7..9e494a446b7e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -1172,7 +1172,8 @@ static int mlxsw_sp_nexthop_mac_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index, static int mlxsw_sp_nexthop_group_mac_update(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_nexthop_group *nh_grp) + struct mlxsw_sp_nexthop_group *nh_grp, + bool reallocate) { u32 adj_index = nh_grp->adj_index; /* base */ struct mlxsw_sp_nexthop *nh; @@ -1187,7 +1188,7 @@ mlxsw_sp_nexthop_group_mac_update(struct mlxsw_sp *mlxsw_sp, continue; } - if (nh->update) { + if (nh->update || reallocate) { err = mlxsw_sp_nexthop_mac_update(mlxsw_sp, adj_index, nh); if (err) @@ -1248,7 +1249,8 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp, /* Nothing was added or removed, so no need to reallocate. Just * update MAC on existing adjacency indexes. */ - err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp); + err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp, + false); if (err) { dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n"); goto set_trap; @@ -1276,7 +1278,7 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp, nh_grp->adj_index_valid = 1; nh_grp->adj_index = adj_index; nh_grp->ecmp_size = ecmp_size; - err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp); + err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp, true); if (err) { dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n"); goto set_trap; diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index 150ccf5192a9..2e88115e8735 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -345,6 +345,7 @@ static netdev_tx_t mlxsw_sx_port_xmit(struct sk_buff *skb, dev_kfree_skb_any(skb_orig); return NETDEV_TX_OK; } + dev_consume_skb_any(skb_orig); } mlxsw_sx_txhdr_construct(skb, &tx_info); /* TX header is consumed by HW on the way so we shouldn't count its |