diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox')
33 files changed, 803 insertions, 400 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c index 5f41dc92aa68..1a0c3bf86ead 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c @@ -310,6 +310,7 @@ static int mlx4_en_ets_validate(struct mlx4_en_priv *priv, struct ieee_ets *ets) } switch (ets->tc_tsa[i]) { + case IEEE_8021QAZ_TSA_VENDOR: case IEEE_8021QAZ_TSA_STRICT: break; case IEEE_8021QAZ_TSA_ETS: @@ -347,6 +348,10 @@ static int mlx4_en_config_port_scheduler(struct mlx4_en_priv *priv, /* higher TC means higher priority => lower pg */ for (i = IEEE_8021QAZ_MAX_TCS - 1; i >= 0; i--) { switch (ets->tc_tsa[i]) { + case IEEE_8021QAZ_TSA_VENDOR: + pg[i] = MLX4_EN_TC_VENDOR; + tc_tx_bw[i] = MLX4_EN_BW_MAX; + break; case IEEE_8021QAZ_TSA_STRICT: pg[i] = num_strict++; tc_tx_bw[i] = MLX4_EN_BW_MAX; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 99051a294fa6..21bc17fa3854 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -3336,6 +3336,13 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, priv->msg_enable = MLX4_EN_MSG_LEVEL; #ifdef CONFIG_MLX4_EN_DCB if (!mlx4_is_slave(priv->mdev->dev)) { + u8 prio; + + for (prio = 0; prio < IEEE_8021QAZ_MAX_TCS; ++prio) { + priv->ets.prio_tc[prio] = prio; + priv->ets.tc_tsa[prio] = IEEE_8021QAZ_TSA_VENDOR; + } + priv->dcbx_cap = DCB_CAP_DCBX_VER_CEE | DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_IEEE; priv->flags |= MLX4_EN_DCB_ENABLED; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c index e0eb695318e6..1fa4849a6f56 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_port.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c @@ -188,7 +188,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) struct net_device *dev = mdev->pndev[port]; struct mlx4_en_priv *priv = netdev_priv(dev); struct net_device_stats *stats = &dev->stats; - struct mlx4_cmd_mailbox *mailbox; + struct mlx4_cmd_mailbox *mailbox, *mailbox_priority; u64 in_mod = reset << 8 | port; int err; int i, counter_index; @@ -198,6 +198,13 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) mailbox = mlx4_alloc_cmd_mailbox(mdev->dev); if (IS_ERR(mailbox)) return PTR_ERR(mailbox); + + mailbox_priority = mlx4_alloc_cmd_mailbox(mdev->dev); + if (IS_ERR(mailbox_priority)) { + mlx4_free_cmd_mailbox(mdev->dev, mailbox); + return PTR_ERR(mailbox_priority); + } + err = mlx4_cmd_box(mdev->dev, 0, mailbox->dma, in_mod, 0, MLX4_CMD_DUMP_ETH_STATS, MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE); @@ -206,6 +213,28 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) mlx4_en_stats = mailbox->buf; + memset(&tmp_counter_stats, 0, sizeof(tmp_counter_stats)); + counter_index = mlx4_get_default_counter_index(mdev->dev, port); + err = mlx4_get_counter_stats(mdev->dev, counter_index, + &tmp_counter_stats, reset); + + /* 0xffs indicates invalid value */ + memset(mailbox_priority->buf, 0xff, + sizeof(*flowstats) * MLX4_NUM_PRIORITIES); + + if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_FLOWSTATS_EN) { + memset(mailbox_priority->buf, 0, + sizeof(*flowstats) * MLX4_NUM_PRIORITIES); + err = mlx4_cmd_box(mdev->dev, 0, mailbox_priority->dma, + in_mod | MLX4_DUMP_ETH_STATS_FLOW_CONTROL, + 0, MLX4_CMD_DUMP_ETH_STATS, + MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE); + if (err) + goto out; + } + + flowstats = mailbox_priority->buf; + spin_lock_bh(&priv->stats_lock); mlx4_en_fold_software_stats(dev); @@ -345,31 +374,6 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) priv->pkstats.tx_prio[8][0] = be64_to_cpu(mlx4_en_stats->TTOT_novlan); priv->pkstats.tx_prio[8][1] = be64_to_cpu(mlx4_en_stats->TOCT_novlan); - spin_unlock_bh(&priv->stats_lock); - - memset(&tmp_counter_stats, 0, sizeof(tmp_counter_stats)); - counter_index = mlx4_get_default_counter_index(mdev->dev, port); - err = mlx4_get_counter_stats(mdev->dev, counter_index, - &tmp_counter_stats, reset); - - /* 0xffs indicates invalid value */ - memset(mailbox->buf, 0xff, sizeof(*flowstats) * MLX4_NUM_PRIORITIES); - - if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_FLOWSTATS_EN) { - memset(mailbox->buf, 0, - sizeof(*flowstats) * MLX4_NUM_PRIORITIES); - err = mlx4_cmd_box(mdev->dev, 0, mailbox->dma, - in_mod | MLX4_DUMP_ETH_STATS_FLOW_CONTROL, - 0, MLX4_CMD_DUMP_ETH_STATS, - MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE); - if (err) - goto out; - } - - flowstats = mailbox->buf; - - spin_lock_bh(&priv->stats_lock); - if (tmp_counter_stats.counter_mode == 0) { priv->pf_stats.rx_bytes = be64_to_cpu(tmp_counter_stats.rx_bytes); priv->pf_stats.tx_bytes = be64_to_cpu(tmp_counter_stats.tx_bytes); @@ -410,6 +414,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) out: mlx4_free_cmd_mailbox(mdev->dev, mailbox); + mlx4_free_cmd_mailbox(mdev->dev, mailbox_priority); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 85e28efcda33..5f9dbc9a7f5b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -617,6 +617,10 @@ static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb, return 0; } #endif + +/* We reach this function only after checking that any of + * the (IPv4 | IPv6) bits are set in cqe->status. + */ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va, netdev_features_t dev_features) { @@ -632,13 +636,11 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va, hdr += sizeof(struct vlan_hdr); } - if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV4)) - return get_fixed_ipv4_csum(hw_checksum, skb, hdr); #if IS_ENABLED(CONFIG_IPV6) if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV6)) return get_fixed_ipv6_csum(hw_checksum, skb, hdr); #endif - return 0; + return get_fixed_ipv4_csum(hw_checksum, skb, hdr); } int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int budget) @@ -814,33 +816,33 @@ xdp_drop_no_cnt: if (likely(dev->features & NETIF_F_RXCSUM)) { if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP | MLX4_CQE_STATUS_UDP)) { - if ((cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) && - cqe->checksum == cpu_to_be16(0xffff)) { - bool l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) && - (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL)); - - ip_summed = CHECKSUM_UNNECESSARY; - hash_type = PKT_HASH_TYPE_L4; - if (l2_tunnel) - skb->csum_level = 1; - ring->csum_ok++; - } else { + bool l2_tunnel; + + if (!((cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) && + cqe->checksum == cpu_to_be16(0xffff))) goto csum_none; - } + + l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) && + (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL)); + ip_summed = CHECKSUM_UNNECESSARY; + hash_type = PKT_HASH_TYPE_L4; + if (l2_tunnel) + skb->csum_level = 1; + ring->csum_ok++; } else { - if (priv->flags & MLX4_EN_FLAG_RX_CSUM_NON_TCP_UDP && - (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV4 | - MLX4_CQE_STATUS_IPV6))) { - if (check_csum(cqe, skb, va, dev->features)) { - goto csum_none; - } else { - ip_summed = CHECKSUM_COMPLETE; - hash_type = PKT_HASH_TYPE_L3; - ring->csum_complete++; - } - } else { + if (!(priv->flags & MLX4_EN_FLAG_RX_CSUM_NON_TCP_UDP && + (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV4 | +#if IS_ENABLED(CONFIG_IPV6) + MLX4_CQE_STATUS_IPV6)))) +#else + 0)))) +#endif goto csum_none; - } + if (check_csum(cqe, skb, va, dev->features)) + goto csum_none; + ip_summed = CHECKSUM_COMPLETE; + hash_type = PKT_HASH_TYPE_L3; + ring->csum_complete++; } } else { csum_none: diff --git a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c index 88699b181946..946d9db7c8c2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c @@ -185,7 +185,7 @@ void mlx4_en_ex_selftest(struct net_device *dev, u32 *flags, u64 *buf) if (priv->mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_UC_LOOPBACK) { buf[3] = mlx4_en_test_registers(priv); - if (priv->port_up) + if (priv->port_up && dev->mtu >= MLX4_SELFTEST_LB_MIN_MTU) buf[4] = mlx4_en_test_loopback(priv); } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 1856e279a7e0..7db3d0d9bfce 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -153,6 +153,9 @@ #define SMALL_PACKET_SIZE (256 - NET_IP_ALIGN) #define HEADER_COPY_SIZE (128 - NET_IP_ALIGN) #define MLX4_LOOPBACK_TEST_PAYLOAD (HEADER_COPY_SIZE - ETH_HLEN) +#define PREAMBLE_LEN 8 +#define MLX4_SELFTEST_LB_MIN_MTU (MLX4_LOOPBACK_TEST_PAYLOAD + NET_IP_ALIGN + \ + ETH_HLEN + PREAMBLE_LEN) #define MLX4_EN_MIN_MTU 46 /* VLAN_HLEN is added twice,to support skb vlan tagged with multiple @@ -476,6 +479,7 @@ struct mlx4_en_frag_info { #define MLX4_EN_BW_MIN 1 #define MLX4_EN_BW_MAX 100 /* Utilize 100% of the line */ +#define MLX4_EN_TC_VENDOR 0 #define MLX4_EN_TC_ETS 7 enum dcb_pfc_type { diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c index c7c0764991c9..2e84f10f59ba 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mr.c +++ b/drivers/net/ethernet/mellanox/mlx4/mr.c @@ -1103,30 +1103,16 @@ EXPORT_SYMBOL_GPL(mlx4_fmr_enable); void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr, u32 *lkey, u32 *rkey) { - struct mlx4_cmd_mailbox *mailbox; - int err; - if (!fmr->maps) return; - fmr->maps = 0; + /* To unmap: it is sufficient to take back ownership from HW */ + *(u8 *)fmr->mpt = MLX4_MPT_STATUS_SW; - mailbox = mlx4_alloc_cmd_mailbox(dev); - if (IS_ERR(mailbox)) { - err = PTR_ERR(mailbox); - pr_warn("mlx4_ib: mlx4_alloc_cmd_mailbox failed (%d)\n", err); - return; - } + /* Make sure MPT status is visible */ + wmb(); - err = mlx4_HW2SW_MPT(dev, NULL, - key_to_hw_index(fmr->mr.key) & - (dev->caps.num_mpts - 1)); - mlx4_free_cmd_mailbox(dev, mailbox); - if (err) { - pr_warn("mlx4_ib: mlx4_HW2SW_MPT failed (%d)\n", err); - return; - } - fmr->mr.enabled = MLX4_MPT_EN_SW; + fmr->maps = 0; } EXPORT_SYMBOL_GPL(mlx4_fmr_unmap); @@ -1136,6 +1122,22 @@ int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr) if (fmr->maps) return -EBUSY; + if (fmr->mr.enabled == MLX4_MPT_EN_HW) { + /* In case of FMR was enabled and unmapped + * make sure to give ownership of MPT back to HW + * so HW2SW_MPT command will success. + */ + *(u8 *)fmr->mpt = MLX4_MPT_STATUS_SW; + /* Make sure MPT status is visible before changing MPT fields */ + wmb(); + fmr->mpt->length = 0; + fmr->mpt->start = 0; + /* Make sure MPT data is visible after changing MPT status */ + wmb(); + *(u8 *)fmr->mpt = MLX4_MPT_STATUS_HW; + /* make sure MPT status is visible */ + wmb(); + } ret = mlx4_mr_free(dev, &fmr->mr); if (ret) diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 04304dd894c6..606a0e0beeae 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -611,7 +611,6 @@ int mlx4_init_resource_tracker(struct mlx4_dev *dev) MLX4_MAX_PORTS; else res_alloc->guaranteed[t] = 0; - res_alloc->res_free -= res_alloc->guaranteed[t]; break; default: break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 1fffdebbc9e8..e9a1fbcc4adf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -362,7 +362,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_QUERY_VPORT_COUNTER: case MLX5_CMD_OP_ALLOC_Q_COUNTER: case MLX5_CMD_OP_QUERY_Q_COUNTER: - case MLX5_CMD_OP_SET_RATE_LIMIT: + case MLX5_CMD_OP_SET_PP_RATE_LIMIT: case MLX5_CMD_OP_QUERY_RATE_LIMIT: case MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT: case MLX5_CMD_OP_QUERY_SCHEDULING_ELEMENT: @@ -505,7 +505,7 @@ const char *mlx5_command_str(int command) MLX5_COMMAND_STR_CASE(ALLOC_Q_COUNTER); MLX5_COMMAND_STR_CASE(DEALLOC_Q_COUNTER); MLX5_COMMAND_STR_CASE(QUERY_Q_COUNTER); - MLX5_COMMAND_STR_CASE(SET_RATE_LIMIT); + MLX5_COMMAND_STR_CASE(SET_PP_RATE_LIMIT); MLX5_COMMAND_STR_CASE(QUERY_RATE_LIMIT); MLX5_COMMAND_STR_CASE(CREATE_SCHEDULING_ELEMENT); MLX5_COMMAND_STR_CASE(DESTROY_SCHEDULING_ELEMENT); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index c0872b3284cb..543060c305a0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -82,6 +82,9 @@ max_t(u32, MLX5_MPWRQ_MIN_LOG_STRIDE_SZ(mdev), req) #define MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev) MLX5_MPWRQ_LOG_STRIDE_SZ(mdev, 6) #define MLX5_MPWRQ_CQE_CMPRS_LOG_STRIDE_SZ(mdev) MLX5_MPWRQ_LOG_STRIDE_SZ(mdev, 8) +#define MLX5E_MPWQE_STRIDE_SZ(mdev, cqe_cmprs) \ + (cqe_cmprs ? MLX5_MPWRQ_CQE_CMPRS_LOG_STRIDE_SZ(mdev) : \ + MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev)) #define MLX5_MPWRQ_LOG_WQE_SZ 18 #define MLX5_MPWRQ_WQE_PAGE_ORDER (MLX5_MPWRQ_LOG_WQE_SZ - PAGE_SHIFT > 0 ? \ @@ -590,6 +593,7 @@ struct mlx5e_channel { struct mlx5_core_dev *mdev; struct hwtstamp_config *tstamp; int ix; + int cpu; }; struct mlx5e_channels { @@ -935,8 +939,9 @@ void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode); void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode); -void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev, - struct mlx5e_params *params, u8 rq_type); +void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev, + struct mlx5e_params *params, + u8 rq_type); static inline bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index c6d90b6dd80e..9bcf38f4123b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -274,6 +274,7 @@ int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets) static int mlx5e_dbcnl_validate_ets(struct net_device *netdev, struct ieee_ets *ets) { + bool have_ets_tc = false; int bw_sum = 0; int i; @@ -288,11 +289,14 @@ static int mlx5e_dbcnl_validate_ets(struct net_device *netdev, } /* Validate Bandwidth Sum */ - for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) - if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) { + have_ets_tc = true; bw_sum += ets->tc_tx_bw[i]; + } + } - if (bw_sum != 0 && bw_sum != 100) { + if (have_ets_tc && bw_sum != 100) { netdev_err(netdev, "Failed to validate ETS: BW sum is illegal\n"); return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 23425f028405..8f05efa5c829 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1523,8 +1523,10 @@ int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val new_channels.params = priv->channels.params; MLX5E_SET_PFLAG(&new_channels.params, MLX5E_PFLAG_RX_CQE_COMPRESS, new_val); - mlx5e_set_rq_type_params(priv->mdev, &new_channels.params, - new_channels.params.rq_wq_type); + new_channels.params.mpwqe_log_stride_sz = + MLX5E_MPWQE_STRIDE_SZ(priv->mdev, new_val); + new_channels.params.mpwqe_log_num_strides = + MLX5_MPWRQ_LOG_WQE_SZ - new_channels.params.mpwqe_log_stride_sz; if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { priv->channels.params = new_channels.params; @@ -1536,6 +1538,10 @@ int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val return err; mlx5e_switch_priv_channels(priv, &new_channels, NULL); + mlx5e_dbg(DRV, priv, "MLX5E: RxCqeCmprss was turned %s\n", + MLX5E_GET_PFLAG(&priv->channels.params, + MLX5E_PFLAG_RX_CQE_COMPRESS) ? "ON" : "OFF"); + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 0f5c012de52e..3aa1c90e7c86 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -71,11 +71,6 @@ struct mlx5e_channel_param { struct mlx5e_cq_param icosq_cq; }; -static int mlx5e_get_node(struct mlx5e_priv *priv, int ix) -{ - return pci_irq_get_node(priv->mdev->pdev, MLX5_EQ_VEC_COMP_BASE + ix); -} - static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev) { return MLX5_CAP_GEN(mdev, striding_rq) && @@ -83,8 +78,8 @@ static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev) MLX5_CAP_ETH(mdev, reg_umr_sq); } -void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev, - struct mlx5e_params *params, u8 rq_type) +void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev, + struct mlx5e_params *params, u8 rq_type) { params->rq_wq_type = rq_type; params->lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ; @@ -93,10 +88,8 @@ void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev, params->log_rq_size = is_kdump_kernel() ? MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW : MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE_MPW; - params->mpwqe_log_stride_sz = - MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS) ? - MLX5_MPWRQ_CQE_CMPRS_LOG_STRIDE_SZ(mdev) : - MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev); + params->mpwqe_log_stride_sz = MLX5E_MPWQE_STRIDE_SZ(mdev, + MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)); params->mpwqe_log_num_strides = MLX5_MPWRQ_LOG_WQE_SZ - params->mpwqe_log_stride_sz; break; @@ -120,13 +113,14 @@ void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev, MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)); } -static void mlx5e_set_rq_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params) +static void mlx5e_set_rq_params(struct mlx5_core_dev *mdev, + struct mlx5e_params *params) { u8 rq_type = mlx5e_check_fragmented_striding_rq_cap(mdev) && !params->xdp_prog && !MLX5_IPSEC_DEV(mdev) ? MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ : MLX5_WQ_TYPE_LINKED_LIST; - mlx5e_set_rq_type_params(mdev, params, rq_type); + mlx5e_init_rq_type_params(mdev, params, rq_type); } static void mlx5e_update_carrier(struct mlx5e_priv *priv) @@ -444,17 +438,16 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq, int wq_sz = mlx5_wq_ll_get_size(&rq->wq); int mtt_sz = mlx5e_get_wqe_mtt_sz(); int mtt_alloc = mtt_sz + MLX5_UMR_ALIGN - 1; - int node = mlx5e_get_node(c->priv, c->ix); int i; rq->mpwqe.info = kzalloc_node(wq_sz * sizeof(*rq->mpwqe.info), - GFP_KERNEL, node); + GFP_KERNEL, cpu_to_node(c->cpu)); if (!rq->mpwqe.info) goto err_out; /* We allocate more than mtt_sz as we will align the pointer */ - rq->mpwqe.mtt_no_align = kzalloc_node(mtt_alloc * wq_sz, - GFP_KERNEL, node); + rq->mpwqe.mtt_no_align = kzalloc_node(mtt_alloc * wq_sz, GFP_KERNEL, + cpu_to_node(c->cpu)); if (unlikely(!rq->mpwqe.mtt_no_align)) goto err_free_wqe_info; @@ -562,7 +555,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, int err; int i; - rqp->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix); + rqp->wq.db_numa_node = cpu_to_node(c->cpu); err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->wq, &rq->wq_ctrl); @@ -629,8 +622,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, default: /* MLX5_WQ_TYPE_LINKED_LIST */ rq->wqe.frag_info = kzalloc_node(wq_sz * sizeof(*rq->wqe.frag_info), - GFP_KERNEL, - mlx5e_get_node(c->priv, c->ix)); + GFP_KERNEL, cpu_to_node(c->cpu)); if (!rq->wqe.frag_info) { err = -ENOMEM; goto err_rq_wq_destroy; @@ -1000,13 +992,13 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c, sq->uar_map = mdev->mlx5e_res.bfreg.map; sq->min_inline_mode = params->tx_min_inline_mode; - param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix); + param->wq.db_numa_node = cpu_to_node(c->cpu); err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, &sq->wq_ctrl); if (err) return err; sq->wq.db = &sq->wq.db[MLX5_SND_DBR]; - err = mlx5e_alloc_xdpsq_db(sq, mlx5e_get_node(c->priv, c->ix)); + err = mlx5e_alloc_xdpsq_db(sq, cpu_to_node(c->cpu)); if (err) goto err_sq_wq_destroy; @@ -1053,13 +1045,13 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c, sq->channel = c; sq->uar_map = mdev->mlx5e_res.bfreg.map; - param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix); + param->wq.db_numa_node = cpu_to_node(c->cpu); err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, &sq->wq_ctrl); if (err) return err; sq->wq.db = &sq->wq.db[MLX5_SND_DBR]; - err = mlx5e_alloc_icosq_db(sq, mlx5e_get_node(c->priv, c->ix)); + err = mlx5e_alloc_icosq_db(sq, cpu_to_node(c->cpu)); if (err) goto err_sq_wq_destroy; @@ -1126,13 +1118,13 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, if (MLX5_IPSEC_DEV(c->priv->mdev)) set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state); - param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix); + param->wq.db_numa_node = cpu_to_node(c->cpu); err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, &sq->wq_ctrl); if (err) return err; sq->wq.db = &sq->wq.db[MLX5_SND_DBR]; - err = mlx5e_alloc_txqsq_db(sq, mlx5e_get_node(c->priv, c->ix)); + err = mlx5e_alloc_txqsq_db(sq, cpu_to_node(c->cpu)); if (err) goto err_sq_wq_destroy; @@ -1504,8 +1496,8 @@ static int mlx5e_alloc_cq(struct mlx5e_channel *c, struct mlx5_core_dev *mdev = c->priv->mdev; int err; - param->wq.buf_numa_node = mlx5e_get_node(c->priv, c->ix); - param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix); + param->wq.buf_numa_node = cpu_to_node(c->cpu); + param->wq.db_numa_node = cpu_to_node(c->cpu); param->eq_ix = c->ix; err = mlx5e_alloc_cq_common(mdev, param, cq); @@ -1604,6 +1596,11 @@ static void mlx5e_close_cq(struct mlx5e_cq *cq) mlx5e_free_cq(cq); } +static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix) +{ + return cpumask_first(priv->mdev->priv.irq_info[ix].mask); +} + static int mlx5e_open_tx_cqs(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_channel_param *cparam) @@ -1752,12 +1749,13 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, { struct mlx5e_cq_moder icocq_moder = {0, 0}; struct net_device *netdev = priv->netdev; + int cpu = mlx5e_get_cpu(priv, ix); struct mlx5e_channel *c; unsigned int irq; int err; int eqn; - c = kzalloc_node(sizeof(*c), GFP_KERNEL, mlx5e_get_node(priv, ix)); + c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu)); if (!c) return -ENOMEM; @@ -1765,6 +1763,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, c->mdev = priv->mdev; c->tstamp = &priv->tstamp; c->ix = ix; + c->cpu = cpu; c->pdev = &priv->mdev->pdev->dev; c->netdev = priv->netdev; c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key); @@ -1853,8 +1852,7 @@ 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, - mlx5_get_vector_affinity(c->priv->mdev, c->ix), c->ix); + netif_set_xps_queue(c->netdev, get_cpu_mask(c->cpu), c->ix); } static void mlx5e_deactivate_channel(struct mlx5e_channel *c) @@ -3679,6 +3677,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, struct sk_buff *skb, netdev_features_t features) { + unsigned int offset = 0; struct udphdr *udph; u8 proto; u16 port; @@ -3688,7 +3687,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, proto = ip_hdr(skb)->protocol; break; case htons(ETH_P_IPV6): - proto = ipv6_hdr(skb)->nexthdr; + proto = ipv6_find_hdr(skb, &offset, -1, NULL, NULL); break; default: goto out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 2c43606c26b5..c6a77f8e99a4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -190,6 +190,63 @@ int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr) return 0; } +static void mlx5e_sqs2vport_stop(struct mlx5_eswitch *esw, + struct mlx5_eswitch_rep *rep) +{ + struct mlx5e_rep_sq *rep_sq, *tmp; + struct mlx5e_rep_priv *rpriv; + + if (esw->mode != SRIOV_OFFLOADS) + return; + + rpriv = mlx5e_rep_to_rep_priv(rep); + list_for_each_entry_safe(rep_sq, tmp, &rpriv->vport_sqs_list, list) { + mlx5_eswitch_del_send_to_vport_rule(rep_sq->send_to_vport_rule); + list_del(&rep_sq->list); + kfree(rep_sq); + } +} + +static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw, + struct mlx5_eswitch_rep *rep, + u16 *sqns_array, int sqns_num) +{ + struct mlx5_flow_handle *flow_rule; + struct mlx5e_rep_priv *rpriv; + struct mlx5e_rep_sq *rep_sq; + int err; + int i; + + if (esw->mode != SRIOV_OFFLOADS) + return 0; + + rpriv = mlx5e_rep_to_rep_priv(rep); + for (i = 0; i < sqns_num; i++) { + rep_sq = kzalloc(sizeof(*rep_sq), GFP_KERNEL); + if (!rep_sq) { + err = -ENOMEM; + goto out_err; + } + + /* Add re-inject rule to the PF/representor sqs */ + flow_rule = mlx5_eswitch_add_send_to_vport_rule(esw, + rep->vport, + sqns_array[i]); + if (IS_ERR(flow_rule)) { + err = PTR_ERR(flow_rule); + kfree(rep_sq); + goto out_err; + } + rep_sq->send_to_vport_rule = flow_rule; + list_add(&rep_sq->list, &rpriv->vport_sqs_list); + } + return 0; + +out_err: + mlx5e_sqs2vport_stop(esw, rep); + return err; +} + int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; @@ -210,7 +267,7 @@ int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv) sqs[num_sqs++] = c->sq[tc].sqn; } - err = mlx5_eswitch_sqs2vport_start(esw, rep, sqs, num_sqs); + err = mlx5e_sqs2vport_start(esw, rep, sqs, num_sqs); kfree(sqs); out: @@ -225,7 +282,7 @@ void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv) struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep = rpriv->rep; - mlx5_eswitch_sqs2vport_stop(esw, rep); + mlx5e_sqs2vport_stop(esw, rep); } static void mlx5e_rep_neigh_update_init_interval(struct mlx5e_rep_priv *rpriv) @@ -238,7 +295,7 @@ static void mlx5e_rep_neigh_update_init_interval(struct mlx5e_rep_priv *rpriv) #endif unsigned long ipv4_interval = NEIGH_VAR(&arp_tbl.parms, DELAY_PROBE_TIME); - struct net_device *netdev = rpriv->rep->netdev; + struct net_device *netdev = rpriv->netdev; struct mlx5e_priv *priv = netdev_priv(netdev); rpriv->neigh_update.min_interval = min_t(unsigned long, ipv6_interval, ipv4_interval); @@ -259,7 +316,7 @@ static void mlx5e_rep_neigh_stats_work(struct work_struct *work) { struct mlx5e_rep_priv *rpriv = container_of(work, struct mlx5e_rep_priv, neigh_update.neigh_stats_work.work); - struct net_device *netdev = rpriv->rep->netdev; + struct net_device *netdev = rpriv->netdev; struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5e_neigh_hash_entry *nhe; @@ -355,7 +412,7 @@ static int mlx5e_rep_netevent_event(struct notifier_block *nb, struct mlx5e_rep_priv *rpriv = container_of(nb, struct mlx5e_rep_priv, neigh_update.netevent_nb); struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update; - struct net_device *netdev = rpriv->rep->netdev; + struct net_device *netdev = rpriv->netdev; struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5e_neigh_hash_entry *nhe = NULL; struct mlx5e_neigh m_neigh = {}; @@ -483,7 +540,7 @@ out_err: static void mlx5e_rep_neigh_cleanup(struct mlx5e_rep_priv *rpriv) { struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update; - struct mlx5e_priv *priv = netdev_priv(rpriv->rep->netdev); + struct mlx5e_priv *priv = netdev_priv(rpriv->netdev); unregister_netevent_notifier(&neigh_update->netevent_nb); @@ -904,7 +961,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) err = PTR_ERR(flow_rule); goto err_destroy_direct_tirs; } - rep->vport_rx_rule = flow_rule; + rpriv->vport_rx_rule = flow_rule; err = mlx5e_tc_init(priv); if (err) @@ -913,7 +970,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) return 0; err_del_flow_rule: - mlx5_del_flow_rules(rep->vport_rx_rule); + mlx5_del_flow_rules(rpriv->vport_rx_rule); err_destroy_direct_tirs: mlx5e_destroy_direct_tirs(priv); err_destroy_direct_rqts: @@ -924,10 +981,9 @@ err_destroy_direct_rqts: static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv) { struct mlx5e_rep_priv *rpriv = priv->ppriv; - struct mlx5_eswitch_rep *rep = rpriv->rep; mlx5e_tc_cleanup(priv); - mlx5_del_flow_rules(rep->vport_rx_rule); + mlx5_del_flow_rules(rpriv->vport_rx_rule); mlx5e_destroy_direct_tirs(priv); mlx5e_destroy_direct_rqts(priv); } @@ -967,10 +1023,10 @@ static const struct mlx5e_profile mlx5e_rep_profile = { /* e-Switch vport representors */ static int -mlx5e_nic_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep) +mlx5e_nic_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) { - struct mlx5e_priv *priv = netdev_priv(rep->netdev); - struct mlx5e_rep_priv *rpriv = priv->ppriv; + struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep); + struct mlx5e_priv *priv = netdev_priv(rpriv->netdev); int err; @@ -992,10 +1048,10 @@ err_remove_sqs: } static void -mlx5e_nic_rep_unload(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep) +mlx5e_nic_rep_unload(struct mlx5_eswitch_rep *rep) { - struct mlx5e_priv *priv = netdev_priv(rep->netdev); - struct mlx5e_rep_priv *rpriv = priv->ppriv; + struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep); + struct mlx5e_priv *priv = netdev_priv(rpriv->netdev); if (test_bit(MLX5E_STATE_OPENED, &priv->state)) mlx5e_remove_sqs_fwd_rules(priv); @@ -1008,8 +1064,9 @@ mlx5e_nic_rep_unload(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep) } static int -mlx5e_vport_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep) +mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) { + struct mlx5e_rep_priv *uplink_rpriv; struct mlx5e_rep_priv *rpriv; struct net_device *netdev; struct mlx5e_priv *upriv; @@ -1019,7 +1076,7 @@ mlx5e_vport_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep) if (!rpriv) return -ENOMEM; - netdev = mlx5e_create_netdev(esw->dev, &mlx5e_rep_profile, rpriv); + netdev = mlx5e_create_netdev(dev, &mlx5e_rep_profile, rpriv); if (!netdev) { pr_warn("Failed to create representor netdev for vport %d\n", rep->vport); @@ -1027,8 +1084,10 @@ mlx5e_vport_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep) return -EINVAL; } - rep->netdev = netdev; + rpriv->netdev = netdev; rpriv->rep = rep; + rep->rep_if[REP_ETH].priv = rpriv; + INIT_LIST_HEAD(&rpriv->vport_sqs_list); err = mlx5e_attach_netdev(netdev_priv(netdev)); if (err) { @@ -1044,7 +1103,8 @@ mlx5e_vport_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep) goto err_detach_netdev; } - upriv = netdev_priv(mlx5_eswitch_get_uplink_netdev(esw)); + uplink_rpriv = mlx5_eswitch_get_uplink_priv(dev->priv.eswitch, REP_ETH); + upriv = netdev_priv(uplink_rpriv->netdev); err = tc_setup_cb_egdev_register(netdev, mlx5e_setup_tc_block_cb, upriv); if (err) @@ -1076,16 +1136,19 @@ err_destroy_netdev: } static void -mlx5e_vport_rep_unload(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep) +mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep) { - struct net_device *netdev = rep->netdev; + struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep); + struct net_device *netdev = rpriv->netdev; struct mlx5e_priv *priv = netdev_priv(netdev); - struct mlx5e_rep_priv *rpriv = priv->ppriv; + struct mlx5e_rep_priv *uplink_rpriv; void *ppriv = priv->ppriv; struct mlx5e_priv *upriv; - unregister_netdev(rep->netdev); - upriv = netdev_priv(mlx5_eswitch_get_uplink_netdev(esw)); + unregister_netdev(netdev); + uplink_rpriv = mlx5_eswitch_get_uplink_priv(priv->mdev->priv.eswitch, + REP_ETH); + upriv = netdev_priv(uplink_rpriv->netdev); tc_setup_cb_egdev_unregister(netdev, mlx5e_setup_tc_block_cb, upriv); mlx5e_rep_neigh_cleanup(rpriv); @@ -1100,18 +1163,13 @@ static void mlx5e_rep_register_vf_vports(struct mlx5e_priv *priv) struct mlx5_eswitch *esw = mdev->priv.eswitch; int total_vfs = MLX5_TOTAL_VPORTS(mdev); int vport; - u8 mac[ETH_ALEN]; - - mlx5_query_nic_vport_mac_address(mdev, 0, mac); for (vport = 1; vport < total_vfs; vport++) { - struct mlx5_eswitch_rep rep; + struct mlx5_eswitch_rep_if rep_if = {}; - rep.load = mlx5e_vport_rep_load; - rep.unload = mlx5e_vport_rep_unload; - rep.vport = vport; - ether_addr_copy(rep.hw_id, mac); - mlx5_eswitch_register_vport_rep(esw, vport, &rep); + rep_if.load = mlx5e_vport_rep_load; + rep_if.unload = mlx5e_vport_rep_unload; + mlx5_eswitch_register_vport_rep(esw, vport, &rep_if, REP_ETH); } } @@ -1123,21 +1181,24 @@ static void mlx5e_rep_unregister_vf_vports(struct mlx5e_priv *priv) int vport; for (vport = 1; vport < total_vfs; vport++) - mlx5_eswitch_unregister_vport_rep(esw, vport); + mlx5_eswitch_unregister_vport_rep(esw, vport, REP_ETH); } void mlx5e_register_vport_reps(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_eswitch *esw = mdev->priv.eswitch; - struct mlx5_eswitch_rep rep; + struct mlx5_eswitch_rep_if rep_if; + struct mlx5e_rep_priv *rpriv; + + rpriv = priv->ppriv; + rpriv->netdev = priv->netdev; - mlx5_query_nic_vport_mac_address(mdev, 0, rep.hw_id); - rep.load = mlx5e_nic_rep_load; - rep.unload = mlx5e_nic_rep_unload; - rep.vport = FDB_UPLINK_VPORT; - rep.netdev = priv->netdev; - mlx5_eswitch_register_vport_rep(esw, 0, &rep); /* UPLINK PF vport*/ + rep_if.load = mlx5e_nic_rep_load; + rep_if.unload = mlx5e_nic_rep_unload; + rep_if.priv = rpriv; + INIT_LIST_HEAD(&rpriv->vport_sqs_list); + mlx5_eswitch_register_vport_rep(esw, 0, &rep_if, REP_ETH); /* UPLINK PF vport*/ mlx5e_rep_register_vf_vports(priv); /* VFs vports */ } @@ -1148,7 +1209,7 @@ void mlx5e_unregister_vport_reps(struct mlx5e_priv *priv) struct mlx5_eswitch *esw = mdev->priv.eswitch; mlx5e_rep_unregister_vf_vports(priv); /* VFs vports */ - mlx5_eswitch_unregister_vport_rep(esw, 0); /* UPLINK PF*/ + mlx5_eswitch_unregister_vport_rep(esw, 0, REP_ETH); /* UPLINK PF*/ } void *mlx5e_alloc_nic_rep_priv(struct mlx5_core_dev *mdev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index 5659ed9f51e6..b9b481f2833a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -56,8 +56,17 @@ struct mlx5e_neigh_update_table { struct mlx5e_rep_priv { struct mlx5_eswitch_rep *rep; struct mlx5e_neigh_update_table neigh_update; + struct net_device *netdev; + struct mlx5_flow_handle *vport_rx_rule; + struct list_head vport_sqs_list; }; +static inline +struct mlx5e_rep_priv *mlx5e_rep_to_rep_priv(struct mlx5_eswitch_rep *rep) +{ + return (struct mlx5e_rep_priv *)rep->rep_if[REP_ETH].priv; +} + struct mlx5e_neigh { struct net_device *dev; union { @@ -124,6 +133,11 @@ struct mlx5e_encap_entry { int encap_size; }; +struct mlx5e_rep_sq { + struct mlx5_flow_handle *send_to_vport_rule; + struct list_head list; +}; + void *mlx5e_alloc_nic_rep_priv(struct mlx5_core_dev *mdev); void mlx5e_register_vport_reps(struct mlx5e_priv *priv); void mlx5e_unregister_vport_reps(struct mlx5e_priv *priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 3e03d2e8f96a..25a8073f15d8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -617,7 +617,8 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, FLOW_DISSECTOR_KEY_ENC_PORTS, f->mask); struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct net_device *up_dev = mlx5_eswitch_get_uplink_netdev(esw); + struct mlx5e_rep_priv *uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); + struct net_device *up_dev = uplink_rpriv->netdev; struct mlx5e_priv *up_priv = netdev_priv(up_dev); /* Full udp dst port must be given */ @@ -1507,6 +1508,7 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv, int *out_ttl) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + struct mlx5e_rep_priv *uplink_rpriv; struct rtable *rt; struct neighbour *n = NULL; @@ -1520,9 +1522,10 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv, #else return -EOPNOTSUPP; #endif + uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); /* 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); + *out_dev = uplink_rpriv->netdev; else *out_dev = rt->dst.dev; @@ -1543,6 +1546,7 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv, struct neighbour **out_n, int *out_ttl) { + struct mlx5e_rep_priv *uplink_rpriv; struct neighbour *n = NULL; struct dst_entry *dst; @@ -1557,9 +1561,10 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv, *out_ttl = ip6_dst_hoplimit(dst); + uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); /* if the egress device isn't on the same HW e-switch, we use the uplink */ if (!switchdev_port_same_parent_id(priv->netdev, dst->dev)) - *out_dev = mlx5_eswitch_get_uplink_netdev(esw); + *out_dev = uplink_rpriv->netdev; else *out_dev = dst->dev; #else @@ -1859,7 +1864,9 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct net_device *up_dev = mlx5_eswitch_get_uplink_netdev(esw); + struct mlx5e_rep_priv *uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, + REP_ETH); + struct net_device *up_dev = uplink_rpriv->netdev; unsigned short family = ip_tunnel_info_af(tun_info); struct mlx5e_priv *up_priv = netdev_priv(up_dev); struct mlx5_esw_flow_attr *attr = flow->esw_attr; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 60771865c99c..e7e7cef2bde4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -466,7 +466,7 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr) break; case MLX5_EVENT_TYPE_CQ_ERROR: cqn = be32_to_cpu(eqe->data.cq_err.cqn) & 0xffffff; - mlx5_core_warn(dev, "CQ error on CQN 0x%x, syndrom 0x%x\n", + mlx5_core_warn(dev, "CQ error on CQN 0x%x, syndrome 0x%x\n", cqn, eqe->data.cq_err.syndrome); mlx5_cq_event(dev, cqn, eqe->type); break; @@ -775,7 +775,7 @@ err1: return err; } -int mlx5_stop_eqs(struct mlx5_core_dev *dev) +void mlx5_stop_eqs(struct mlx5_core_dev *dev) { struct mlx5_eq_table *table = &dev->priv.eq_table; int err; @@ -784,22 +784,26 @@ int mlx5_stop_eqs(struct mlx5_core_dev *dev) if (MLX5_CAP_GEN(dev, pg)) { err = mlx5_destroy_unmap_eq(dev, &table->pfault_eq); if (err) - return err; + mlx5_core_err(dev, "failed to destroy page fault eq, err(%d)\n", + err); } #endif err = mlx5_destroy_unmap_eq(dev, &table->pages_eq); if (err) - return err; + mlx5_core_err(dev, "failed to destroy pages eq, err(%d)\n", + err); - mlx5_destroy_unmap_eq(dev, &table->async_eq); + err = mlx5_destroy_unmap_eq(dev, &table->async_eq); + if (err) + mlx5_core_err(dev, "failed to destroy async eq, err(%d)\n", + err); mlx5_cmd_use_polling(dev); err = mlx5_destroy_unmap_eq(dev, &table->cmd_eq); if (err) - mlx5_cmd_use_events(dev); - - return err; + mlx5_core_err(dev, "failed to destroy command eq, err(%d)\n", + err); } int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index bbb140f517c4..7649e36653d9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -867,9 +867,10 @@ static int esw_vport_enable_egress_acl(struct mlx5_eswitch *esw, esw_debug(dev, "Create vport[%d] egress ACL log_max_size(%d)\n", vport->vport, MLX5_CAP_ESW_EGRESS_ACL(dev, log_max_ft_size)); - root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_EGRESS); + root_ns = mlx5_get_flow_vport_acl_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_EGRESS, + vport->vport); if (!root_ns) { - esw_warn(dev, "Failed to get E-Switch egress flow namespace\n"); + esw_warn(dev, "Failed to get E-Switch egress flow namespace for vport (%d)\n", vport->vport); return -EOPNOTSUPP; } @@ -984,9 +985,10 @@ static int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw, esw_debug(dev, "Create vport[%d] ingress ACL log_max_size(%d)\n", vport->vport, MLX5_CAP_ESW_INGRESS_ACL(dev, log_max_ft_size)); - root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS); + root_ns = mlx5_get_flow_vport_acl_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS, + vport->vport); if (!root_ns) { - esw_warn(dev, "Failed to get E-Switch ingress flow namespace\n"); + esw_warn(dev, "Failed to get E-Switch ingress flow namespace for vport (%d)\n", vport->vport); return -EOPNOTSUPP; } @@ -1290,7 +1292,7 @@ static int esw_create_tsar(struct mlx5_eswitch *esw) err = mlx5_create_scheduling_element_cmd(dev, SCHEDULING_HIERARCHY_E_SWITCH, - &tsar_ctx, + tsar_ctx, &esw->qos.root_tsar_id); if (err) { esw_warn(esw->dev, "E-Switch create TSAR failed (%d)\n", err); @@ -1333,20 +1335,20 @@ static int esw_vport_enable_qos(struct mlx5_eswitch *esw, int vport_num, if (vport->qos.enabled) return -EEXIST; - MLX5_SET(scheduling_context, &sched_ctx, element_type, + MLX5_SET(scheduling_context, sched_ctx, element_type, SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT); - vport_elem = MLX5_ADDR_OF(scheduling_context, &sched_ctx, + vport_elem = MLX5_ADDR_OF(scheduling_context, sched_ctx, element_attributes); MLX5_SET(vport_element, vport_elem, vport_number, vport_num); - MLX5_SET(scheduling_context, &sched_ctx, parent_element_id, + MLX5_SET(scheduling_context, sched_ctx, parent_element_id, esw->qos.root_tsar_id); - MLX5_SET(scheduling_context, &sched_ctx, max_average_bw, + MLX5_SET(scheduling_context, sched_ctx, max_average_bw, initial_max_rate); - MLX5_SET(scheduling_context, &sched_ctx, bw_share, initial_bw_share); + MLX5_SET(scheduling_context, sched_ctx, bw_share, initial_bw_share); err = mlx5_create_scheduling_element_cmd(dev, SCHEDULING_HIERARCHY_E_SWITCH, - &sched_ctx, + sched_ctx, &vport->qos.esw_tsar_ix); if (err) { esw_warn(esw->dev, "E-Switch create TSAR vport element failed (vport=%d,err=%d)\n", @@ -1392,22 +1394,22 @@ static int esw_vport_qos_config(struct mlx5_eswitch *esw, int vport_num, if (!vport->qos.enabled) return -EIO; - MLX5_SET(scheduling_context, &sched_ctx, element_type, + MLX5_SET(scheduling_context, sched_ctx, element_type, SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT); - vport_elem = MLX5_ADDR_OF(scheduling_context, &sched_ctx, + vport_elem = MLX5_ADDR_OF(scheduling_context, sched_ctx, element_attributes); MLX5_SET(vport_element, vport_elem, vport_number, vport_num); - MLX5_SET(scheduling_context, &sched_ctx, parent_element_id, + MLX5_SET(scheduling_context, sched_ctx, parent_element_id, esw->qos.root_tsar_id); - MLX5_SET(scheduling_context, &sched_ctx, max_average_bw, + MLX5_SET(scheduling_context, sched_ctx, max_average_bw, max_rate); - MLX5_SET(scheduling_context, &sched_ctx, bw_share, bw_share); + MLX5_SET(scheduling_context, sched_ctx, bw_share, bw_share); bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW; bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_BW_SHARE; err = mlx5_modify_scheduling_element_cmd(dev, SCHEDULING_HIERARCHY_E_SWITCH, - &sched_ctx, + sched_ctx, vport->qos.esw_tsar_ix, bitmask); if (err) { @@ -1644,13 +1646,9 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) goto abort; } - esw->offloads.vport_reps = - kzalloc(total_vports * sizeof(struct mlx5_eswitch_rep), - GFP_KERNEL); - if (!esw->offloads.vport_reps) { - err = -ENOMEM; + err = esw_offloads_init_reps(esw); + if (err) goto abort; - } hash_init(esw->offloads.encap_tbl); hash_init(esw->offloads.mod_hdr_tbl); @@ -1681,8 +1679,8 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) abort: if (esw->work_queue) destroy_workqueue(esw->work_queue); + esw_offloads_cleanup_reps(esw); kfree(esw->vports); - kfree(esw->offloads.vport_reps); kfree(esw); return err; } @@ -1696,7 +1694,7 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) esw->dev->priv.eswitch = NULL; destroy_workqueue(esw->work_queue); - kfree(esw->offloads.vport_reps); + esw_offloads_cleanup_reps(esw); kfree(esw->vports); kfree(esw); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 565c8b7a399a..3b481182f13a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -45,6 +45,11 @@ enum { SRIOV_OFFLOADS }; +enum { + REP_ETH, + NUM_REP_TYPES, +}; + #ifdef CONFIG_MLX5_ESWITCH #define MLX5_MAX_UC_PER_VPORT(dev) \ @@ -133,25 +138,21 @@ struct mlx5_eswitch_fdb { }; }; -struct mlx5_esw_sq { - struct mlx5_flow_handle *send_to_vport_rule; - struct list_head list; +struct mlx5_eswitch_rep; +struct mlx5_eswitch_rep_if { + int (*load)(struct mlx5_core_dev *dev, + struct mlx5_eswitch_rep *rep); + void (*unload)(struct mlx5_eswitch_rep *rep); + void *priv; + bool valid; }; struct mlx5_eswitch_rep { - int (*load)(struct mlx5_eswitch *esw, - struct mlx5_eswitch_rep *rep); - void (*unload)(struct mlx5_eswitch *esw, - struct mlx5_eswitch_rep *rep); + struct mlx5_eswitch_rep_if rep_if[NUM_REP_TYPES]; u16 vport; u8 hw_id[ETH_ALEN]; - struct net_device *netdev; - - struct mlx5_flow_handle *vport_rx_rule; - struct list_head vport_sqs_list; u16 vlan; u32 vlan_refcount; - bool valid; }; struct mlx5_esw_offload { @@ -197,6 +198,8 @@ struct mlx5_eswitch { void esw_offloads_cleanup(struct mlx5_eswitch *esw, int nvports); int esw_offloads_init(struct mlx5_eswitch *esw, int nvports); +void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw); +int esw_offloads_init_reps(struct mlx5_eswitch *esw); /* E-Switch API */ int mlx5_eswitch_init(struct mlx5_core_dev *dev); @@ -221,6 +224,10 @@ int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw, int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw, int vport, struct ifla_vf_stats *vf_stats); +struct mlx5_flow_handle * +mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, + u32 sqn); +void mlx5_eswitch_del_send_to_vport_rule(struct mlx5_flow_handle *rule); struct mlx5_flow_spec; struct mlx5_esw_flow_attr; @@ -257,12 +264,6 @@ struct mlx5_esw_flow_attr { struct mlx5e_tc_flow_parse_attr *parse_attr; }; -int mlx5_eswitch_sqs2vport_start(struct mlx5_eswitch *esw, - struct mlx5_eswitch_rep *rep, - u16 *sqns_array, int sqns_num); -void mlx5_eswitch_sqs2vport_stop(struct mlx5_eswitch *esw, - struct mlx5_eswitch_rep *rep); - int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode); int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode); int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode); @@ -272,10 +273,12 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap); int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, u8 *encap); void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw, int vport_index, - struct mlx5_eswitch_rep *rep); + struct mlx5_eswitch_rep_if *rep_if, + u8 rep_type); void mlx5_eswitch_unregister_vport_rep(struct mlx5_eswitch *esw, - int vport_index); -struct net_device *mlx5_eswitch_get_uplink_netdev(struct mlx5_eswitch *esw); + int vport_index, + u8 rep_type); +void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type); int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw, struct mlx5_esw_flow_attr *attr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 1143d80119bd..99f583a15cc3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -130,7 +130,7 @@ static int esw_set_global_vlan_pop(struct mlx5_eswitch *esw, u8 val) esw_debug(esw->dev, "%s applying global %s policy\n", __func__, val ? "pop" : "none"); for (vf_vport = 1; vf_vport < esw->enabled_vports; vf_vport++) { rep = &esw->offloads.vport_reps[vf_vport]; - if (!rep->valid) + if (!rep->rep_if[REP_ETH].valid) continue; err = __mlx5_eswitch_set_vport_vlan(esw, rep->vport, 0, 0, val); @@ -302,7 +302,7 @@ out: return err; } -static struct mlx5_flow_handle * +struct mlx5_flow_handle * mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, u32 sqn) { struct mlx5_flow_act flow_act = {0}; @@ -339,57 +339,9 @@ out: return flow_rule; } -void mlx5_eswitch_sqs2vport_stop(struct mlx5_eswitch *esw, - struct mlx5_eswitch_rep *rep) -{ - struct mlx5_esw_sq *esw_sq, *tmp; - - if (esw->mode != SRIOV_OFFLOADS) - return; - - list_for_each_entry_safe(esw_sq, tmp, &rep->vport_sqs_list, list) { - mlx5_del_flow_rules(esw_sq->send_to_vport_rule); - list_del(&esw_sq->list); - kfree(esw_sq); - } -} - -int mlx5_eswitch_sqs2vport_start(struct mlx5_eswitch *esw, - struct mlx5_eswitch_rep *rep, - u16 *sqns_array, int sqns_num) +void mlx5_eswitch_del_send_to_vport_rule(struct mlx5_flow_handle *rule) { - struct mlx5_flow_handle *flow_rule; - struct mlx5_esw_sq *esw_sq; - int err; - int i; - - if (esw->mode != SRIOV_OFFLOADS) - return 0; - - for (i = 0; i < sqns_num; i++) { - esw_sq = kzalloc(sizeof(*esw_sq), GFP_KERNEL); - if (!esw_sq) { - err = -ENOMEM; - goto out_err; - } - - /* Add re-inject rule to the PF/representor sqs */ - flow_rule = mlx5_eswitch_add_send_to_vport_rule(esw, - rep->vport, - sqns_array[i]); - if (IS_ERR(flow_rule)) { - err = PTR_ERR(flow_rule); - kfree(esw_sq); - goto out_err; - } - esw_sq->send_to_vport_rule = flow_rule; - list_add(&esw_sq->list, &rep->vport_sqs_list); - } - return 0; - -out_err: - mlx5_eswitch_sqs2vport_stop(esw, rep); - return err; + mlx5_del_flow_rules(rule); } static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw) @@ -732,12 +684,111 @@ static int esw_offloads_start(struct mlx5_eswitch *esw) return err; } -int esw_offloads_init(struct mlx5_eswitch *esw, int nvports) +void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw) +{ + kfree(esw->offloads.vport_reps); +} + +int esw_offloads_init_reps(struct mlx5_eswitch *esw) +{ + int total_vfs = MLX5_TOTAL_VPORTS(esw->dev); + struct mlx5_core_dev *dev = esw->dev; + struct mlx5_esw_offload *offloads; + struct mlx5_eswitch_rep *rep; + u8 hw_id[ETH_ALEN]; + int vport; + + esw->offloads.vport_reps = kcalloc(total_vfs, + sizeof(struct mlx5_eswitch_rep), + GFP_KERNEL); + if (!esw->offloads.vport_reps) + return -ENOMEM; + + offloads = &esw->offloads; + mlx5_query_nic_vport_mac_address(dev, 0, hw_id); + + for (vport = 0; vport < total_vfs; vport++) { + rep = &offloads->vport_reps[vport]; + + rep->vport = vport; + ether_addr_copy(rep->hw_id, hw_id); + } + + offloads->vport_reps[0].vport = FDB_UPLINK_VPORT; + + return 0; +} + +static void esw_offloads_unload_reps_type(struct mlx5_eswitch *esw, int nvports, + u8 rep_type) +{ + struct mlx5_eswitch_rep *rep; + int vport; + + for (vport = nvports - 1; vport >= 0; vport--) { + rep = &esw->offloads.vport_reps[vport]; + if (!rep->rep_if[rep_type].valid) + continue; + + rep->rep_if[rep_type].unload(rep); + } +} + +static void esw_offloads_unload_reps(struct mlx5_eswitch *esw, int nvports) +{ + u8 rep_type = NUM_REP_TYPES; + + while (rep_type-- > 0) + esw_offloads_unload_reps_type(esw, nvports, rep_type); +} + +static int esw_offloads_load_reps_type(struct mlx5_eswitch *esw, int nvports, + u8 rep_type) { struct mlx5_eswitch_rep *rep; int vport; int err; + for (vport = 0; vport < nvports; vport++) { + rep = &esw->offloads.vport_reps[vport]; + if (!rep->rep_if[rep_type].valid) + continue; + + err = rep->rep_if[rep_type].load(esw->dev, rep); + if (err) + goto err_reps; + } + + return 0; + +err_reps: + esw_offloads_unload_reps_type(esw, vport, rep_type); + return err; +} + +static int esw_offloads_load_reps(struct mlx5_eswitch *esw, int nvports) +{ + u8 rep_type = 0; + int err; + + for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) { + err = esw_offloads_load_reps_type(esw, nvports, rep_type); + if (err) + goto err_reps; + } + + return err; + +err_reps: + while (rep_type-- > 0) + esw_offloads_unload_reps_type(esw, nvports, rep_type); + return err; +} + +int esw_offloads_init(struct mlx5_eswitch *esw, int nvports) +{ + 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); @@ -755,25 +806,13 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int nvports) if (err) goto create_fg_err; - for (vport = 0; vport < nvports; vport++) { - rep = &esw->offloads.vport_reps[vport]; - if (!rep->valid) - continue; - - err = rep->load(esw, rep); - if (err) - goto err_reps; - } + err = esw_offloads_load_reps(esw, nvports); + if (err) + goto err_reps; return 0; err_reps: - for (vport--; vport >= 0; vport--) { - rep = &esw->offloads.vport_reps[vport]; - if (!rep->valid) - continue; - rep->unload(esw, rep); - } esw_destroy_vport_rx_group(esw); create_fg_err: @@ -814,16 +853,7 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw) void esw_offloads_cleanup(struct mlx5_eswitch *esw, int nvports) { - struct mlx5_eswitch_rep *rep; - int vport; - - for (vport = nvports - 1; vport >= 0; vport--) { - rep = &esw->offloads.vport_reps[vport]; - if (!rep->valid) - continue; - rep->unload(esw, rep); - } - + esw_offloads_unload_reps(esw, nvports); esw_destroy_vport_rx_group(esw); esw_destroy_offloads_table(esw); esw_destroy_offloads_fdb_tables(esw); @@ -1120,27 +1150,23 @@ int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, u8 *encap) void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw, int vport_index, - struct mlx5_eswitch_rep *__rep) + struct mlx5_eswitch_rep_if *__rep_if, + u8 rep_type) { struct mlx5_esw_offload *offloads = &esw->offloads; - struct mlx5_eswitch_rep *rep; - - rep = &offloads->vport_reps[vport_index]; + struct mlx5_eswitch_rep_if *rep_if; - memset(rep, 0, sizeof(*rep)); + rep_if = &offloads->vport_reps[vport_index].rep_if[rep_type]; - rep->load = __rep->load; - rep->unload = __rep->unload; - rep->vport = __rep->vport; - rep->netdev = __rep->netdev; - ether_addr_copy(rep->hw_id, __rep->hw_id); + rep_if->load = __rep_if->load; + rep_if->unload = __rep_if->unload; + rep_if->priv = __rep_if->priv; - INIT_LIST_HEAD(&rep->vport_sqs_list); - rep->valid = true; + rep_if->valid = true; } void mlx5_eswitch_unregister_vport_rep(struct mlx5_eswitch *esw, - int vport_index) + int vport_index, u8 rep_type) { struct mlx5_esw_offload *offloads = &esw->offloads; struct mlx5_eswitch_rep *rep; @@ -1148,17 +1174,17 @@ void mlx5_eswitch_unregister_vport_rep(struct mlx5_eswitch *esw, rep = &offloads->vport_reps[vport_index]; if (esw->mode == SRIOV_OFFLOADS && esw->vports[vport_index].enabled) - rep->unload(esw, rep); + rep->rep_if[rep_type].unload(rep); - rep->valid = false; + rep->rep_if[rep_type].valid = false; } -struct net_device *mlx5_eswitch_get_uplink_netdev(struct mlx5_eswitch *esw) +void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type) { #define UPLINK_REP_INDEX 0 struct mlx5_esw_offload *offloads = &esw->offloads; struct mlx5_eswitch_rep *rep; rep = &offloads->vport_reps[UPLINK_REP_INDEX]; - return rep->netdev; + return rep->rep_if[rep_type].priv; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c index 3c11d6e2160a..14962969c5ba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c @@ -66,6 +66,9 @@ static int mlx5_fpga_mem_read_i2c(struct mlx5_fpga_device *fdev, size_t size, u8 actual_size; int err; + if (!size) + return -EINVAL; + if (!fdev->mdev) return -ENOTCONN; @@ -95,6 +98,9 @@ static int mlx5_fpga_mem_write_i2c(struct mlx5_fpga_device *fdev, size_t size, u8 actual_size; int err; + if (!size) + return -EINVAL; + if (!fdev->mdev) return -ENOTCONN; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index c70fd663a633..cc4f6ab9374a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -174,6 +174,8 @@ static void del_hw_fte(struct fs_node *node); static void del_sw_flow_table(struct fs_node *node); static void del_sw_flow_group(struct fs_node *node); static void del_sw_fte(struct fs_node *node); +static void del_sw_prio(struct fs_node *node); +static void del_sw_ns(struct fs_node *node); /* Delete rule (destination) is special case that * requires to lock the FTE for all the deletion process. */ @@ -408,6 +410,16 @@ static inline struct mlx5_core_dev *get_dev(struct fs_node *node) return NULL; } +static void del_sw_ns(struct fs_node *node) +{ + kfree(node); +} + +static void del_sw_prio(struct fs_node *node) +{ + kfree(node); +} + static void del_hw_flow_table(struct fs_node *node) { struct mlx5_flow_table *ft; @@ -2014,16 +2026,6 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, return &steering->fdb_root_ns->ns; else return NULL; - case MLX5_FLOW_NAMESPACE_ESW_EGRESS: - if (steering->esw_egress_root_ns) - return &steering->esw_egress_root_ns->ns; - else - return NULL; - case MLX5_FLOW_NAMESPACE_ESW_INGRESS: - if (steering->esw_ingress_root_ns) - return &steering->esw_ingress_root_ns->ns; - else - return NULL; case MLX5_FLOW_NAMESPACE_SNIFFER_RX: if (steering->sniffer_rx_root_ns) return &steering->sniffer_rx_root_ns->ns; @@ -2054,6 +2056,33 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, } EXPORT_SYMBOL(mlx5_get_flow_namespace); +struct mlx5_flow_namespace *mlx5_get_flow_vport_acl_namespace(struct mlx5_core_dev *dev, + enum mlx5_flow_namespace_type type, + int vport) +{ + struct mlx5_flow_steering *steering = dev->priv.steering; + + if (!steering || vport >= MLX5_TOTAL_VPORTS(dev)) + return NULL; + + switch (type) { + case MLX5_FLOW_NAMESPACE_ESW_EGRESS: + if (steering->esw_egress_root_ns && + steering->esw_egress_root_ns[vport]) + return &steering->esw_egress_root_ns[vport]->ns; + else + return NULL; + case MLX5_FLOW_NAMESPACE_ESW_INGRESS: + if (steering->esw_ingress_root_ns && + steering->esw_ingress_root_ns[vport]) + return &steering->esw_ingress_root_ns[vport]->ns; + else + return NULL; + default: + return NULL; + } +} + static struct fs_prio *fs_create_prio(struct mlx5_flow_namespace *ns, unsigned int prio, int num_levels) { @@ -2064,7 +2093,7 @@ static struct fs_prio *fs_create_prio(struct mlx5_flow_namespace *ns, return ERR_PTR(-ENOMEM); fs_prio->node.type = FS_TYPE_PRIO; - tree_init_node(&fs_prio->node, NULL, NULL); + tree_init_node(&fs_prio->node, NULL, del_sw_prio); tree_add_node(&fs_prio->node, &ns->node); fs_prio->num_levels = num_levels; fs_prio->prio = prio; @@ -2090,7 +2119,7 @@ static struct mlx5_flow_namespace *fs_create_namespace(struct fs_prio *prio) return ERR_PTR(-ENOMEM); fs_init_namespace(ns); - tree_init_node(&ns->node, NULL, NULL); + tree_init_node(&ns->node, NULL, del_sw_ns); tree_add_node(&ns->node, &prio->node); list_add_tail(&ns->node.list, &prio->node.children); @@ -2331,13 +2360,41 @@ static void cleanup_root_ns(struct mlx5_flow_root_namespace *root_ns) clean_tree(&root_ns->ns.node); } +static void cleanup_egress_acls_root_ns(struct mlx5_core_dev *dev) +{ + struct mlx5_flow_steering *steering = dev->priv.steering; + int i; + + if (!steering->esw_egress_root_ns) + return; + + for (i = 0; i < MLX5_TOTAL_VPORTS(dev); i++) + cleanup_root_ns(steering->esw_egress_root_ns[i]); + + kfree(steering->esw_egress_root_ns); +} + +static void cleanup_ingress_acls_root_ns(struct mlx5_core_dev *dev) +{ + struct mlx5_flow_steering *steering = dev->priv.steering; + int i; + + if (!steering->esw_ingress_root_ns) + return; + + for (i = 0; i < MLX5_TOTAL_VPORTS(dev); i++) + cleanup_root_ns(steering->esw_ingress_root_ns[i]); + + kfree(steering->esw_ingress_root_ns); +} + void mlx5_cleanup_fs(struct mlx5_core_dev *dev) { struct mlx5_flow_steering *steering = dev->priv.steering; cleanup_root_ns(steering->root_ns); - cleanup_root_ns(steering->esw_egress_root_ns); - cleanup_root_ns(steering->esw_ingress_root_ns); + cleanup_egress_acls_root_ns(dev); + cleanup_ingress_acls_root_ns(dev); cleanup_root_ns(steering->fdb_root_ns); cleanup_root_ns(steering->sniffer_rx_root_ns); cleanup_root_ns(steering->sniffer_tx_root_ns); @@ -2406,34 +2463,86 @@ out_err: return PTR_ERR(prio); } -static int init_ingress_acl_root_ns(struct mlx5_flow_steering *steering) +static int init_egress_acl_root_ns(struct mlx5_flow_steering *steering, int vport) { struct fs_prio *prio; - steering->esw_egress_root_ns = create_root_ns(steering, FS_FT_ESW_EGRESS_ACL); - if (!steering->esw_egress_root_ns) + steering->esw_egress_root_ns[vport] = create_root_ns(steering, FS_FT_ESW_EGRESS_ACL); + if (!steering->esw_egress_root_ns[vport]) return -ENOMEM; /* create 1 prio*/ - prio = fs_create_prio(&steering->esw_egress_root_ns->ns, 0, - MLX5_TOTAL_VPORTS(steering->dev)); + prio = fs_create_prio(&steering->esw_egress_root_ns[vport]->ns, 0, 1); return PTR_ERR_OR_ZERO(prio); } -static int init_egress_acl_root_ns(struct mlx5_flow_steering *steering) +static int init_ingress_acl_root_ns(struct mlx5_flow_steering *steering, int vport) { struct fs_prio *prio; - steering->esw_ingress_root_ns = create_root_ns(steering, FS_FT_ESW_INGRESS_ACL); - if (!steering->esw_ingress_root_ns) + steering->esw_ingress_root_ns[vport] = create_root_ns(steering, FS_FT_ESW_INGRESS_ACL); + if (!steering->esw_ingress_root_ns[vport]) return -ENOMEM; /* create 1 prio*/ - prio = fs_create_prio(&steering->esw_ingress_root_ns->ns, 0, - MLX5_TOTAL_VPORTS(steering->dev)); + prio = fs_create_prio(&steering->esw_ingress_root_ns[vport]->ns, 0, 1); return PTR_ERR_OR_ZERO(prio); } +static int init_egress_acls_root_ns(struct mlx5_core_dev *dev) +{ + struct mlx5_flow_steering *steering = dev->priv.steering; + int err; + int i; + + steering->esw_egress_root_ns = kcalloc(MLX5_TOTAL_VPORTS(dev), + sizeof(*steering->esw_egress_root_ns), + GFP_KERNEL); + if (!steering->esw_egress_root_ns) + return -ENOMEM; + + for (i = 0; i < MLX5_TOTAL_VPORTS(dev); i++) { + err = init_egress_acl_root_ns(steering, i); + if (err) + goto cleanup_root_ns; + } + + return 0; + +cleanup_root_ns: + for (i--; i >= 0; i--) + cleanup_root_ns(steering->esw_egress_root_ns[i]); + kfree(steering->esw_egress_root_ns); + return err; +} + +static int init_ingress_acls_root_ns(struct mlx5_core_dev *dev) +{ + struct mlx5_flow_steering *steering = dev->priv.steering; + int err; + int i; + + steering->esw_ingress_root_ns = kcalloc(MLX5_TOTAL_VPORTS(dev), + sizeof(*steering->esw_ingress_root_ns), + GFP_KERNEL); + if (!steering->esw_ingress_root_ns) + return -ENOMEM; + + for (i = 0; i < MLX5_TOTAL_VPORTS(dev); i++) { + err = init_ingress_acl_root_ns(steering, i); + if (err) + goto cleanup_root_ns; + } + + return 0; + +cleanup_root_ns: + for (i--; i >= 0; i--) + cleanup_root_ns(steering->esw_ingress_root_ns[i]); + kfree(steering->esw_ingress_root_ns); + return err; +} + int mlx5_init_fs(struct mlx5_core_dev *dev) { struct mlx5_flow_steering *steering; @@ -2476,12 +2585,12 @@ int mlx5_init_fs(struct mlx5_core_dev *dev) goto err; } if (MLX5_CAP_ESW_EGRESS_ACL(dev, ft_support)) { - err = init_egress_acl_root_ns(steering); + err = init_egress_acls_root_ns(dev); if (err) goto err; } if (MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support)) { - err = init_ingress_acl_root_ns(steering); + err = init_ingress_acls_root_ns(dev); if (err) goto err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 397d24a621a4..3e571045626f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -71,8 +71,8 @@ struct mlx5_flow_steering { struct kmem_cache *ftes_cache; struct mlx5_flow_root_namespace *root_ns; struct mlx5_flow_root_namespace *fdb_root_ns; - struct mlx5_flow_root_namespace *esw_egress_root_ns; - struct mlx5_flow_root_namespace *esw_ingress_root_ns; + struct mlx5_flow_root_namespace **esw_egress_root_ns; + struct mlx5_flow_root_namespace **esw_ingress_root_ns; struct mlx5_flow_root_namespace *sniffer_tx_root_ns; struct mlx5_flow_root_namespace *sniffer_rx_root_ns; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 1a0e797ad001..21d29f7936f6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -241,7 +241,7 @@ static void print_health_info(struct mlx5_core_dev *dev) u32 fw; int i; - /* If the syndrom is 0, the device is OK and no need to print buffer */ + /* If the syndrome is 0, the device is OK and no need to print buffer */ if (!ioread8(&h->synd)) return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index d2a66dc4adc6..8812d7208e8f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -57,7 +57,7 @@ static void mlx5i_build_nic_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params) { /* Override RQ params as IPoIB supports only LINKED LIST RQ for now */ - mlx5e_set_rq_type_params(mdev, params, MLX5_WQ_TYPE_LINKED_LIST); + mlx5e_init_rq_type_params(mdev, params, MLX5_WQ_TYPE_LINKED_LIST); /* RQ size in ipoib by default is 512 */ params->log_rq_size = is_kdump_kernel() ? diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index f26f97fe4666..582b2f18010a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -137,6 +137,17 @@ int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev) } EXPORT_SYMBOL(mlx5_cmd_destroy_vport_lag); +static int mlx5_cmd_query_cong_counter(struct mlx5_core_dev *dev, + bool reset, void *out, int out_size) +{ + u32 in[MLX5_ST_SZ_DW(query_cong_statistics_in)] = { }; + + MLX5_SET(query_cong_statistics_in, in, opcode, + MLX5_CMD_OP_QUERY_CONG_STATISTICS); + MLX5_SET(query_cong_statistics_in, in, clear, reset); + return mlx5_cmd_exec(dev, in, sizeof(in), out, out_size); +} + static struct mlx5_lag *mlx5_lag_dev_get(struct mlx5_core_dev *dev) { return dev->priv.lag; @@ -633,3 +644,48 @@ bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv) /* If bonded, we do not add an IB device for PF1. */ return false; } + +int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, + u64 *values, + int num_counters, + size_t *offsets) +{ + int outlen = MLX5_ST_SZ_BYTES(query_cong_statistics_out); + struct mlx5_core_dev *mdev[MLX5_MAX_PORTS]; + struct mlx5_lag *ldev; + int num_ports; + int ret, i, j; + void *out; + + out = kvzalloc(outlen, GFP_KERNEL); + if (!out) + return -ENOMEM; + + memset(values, 0, sizeof(*values) * num_counters); + + mutex_lock(&lag_mutex); + ldev = mlx5_lag_dev_get(dev); + if (ldev && mlx5_lag_is_bonded(ldev)) { + num_ports = MLX5_MAX_PORTS; + mdev[0] = ldev->pf[0].dev; + mdev[1] = ldev->pf[1].dev; + } else { + num_ports = 1; + mdev[0] = dev; + } + + for (i = 0; i < num_ports; ++i) { + ret = mlx5_cmd_query_cong_counter(mdev[i], false, out, outlen); + if (ret) + goto unlock; + + for (j = 0; j < num_counters; ++j) + values[j] += be64_to_cpup((__be64 *)(out + offsets[j])); + } + +unlock: + mutex_unlock(&lag_mutex); + kvfree(out); + return ret; +} +EXPORT_SYMBOL(mlx5_lag_query_cong_counters); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 5f323442cc5a..8a89c7e8cd63 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -317,9 +317,6 @@ static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev) { struct mlx5_priv *priv = &dev->priv; struct mlx5_eq_table *table = &priv->eq_table; - struct irq_affinity irqdesc = { - .pre_vectors = MLX5_EQ_VEC_COMP_BASE, - }; int num_eqs = 1 << MLX5_CAP_GEN(dev, log_max_eq); int nvec; @@ -333,10 +330,9 @@ static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev) if (!priv->irq_info) goto err_free_msix; - nvec = pci_alloc_irq_vectors_affinity(dev->pdev, + nvec = pci_alloc_irq_vectors(dev->pdev, MLX5_EQ_VEC_COMP_BASE + 1, nvec, - PCI_IRQ_MSIX | PCI_IRQ_AFFINITY, - &irqdesc); + PCI_IRQ_MSIX); if (nvec < 0) return nvec; @@ -622,6 +618,63 @@ u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev) return (u64)timer_l | (u64)timer_h1 << 32; } +static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i) +{ + struct mlx5_priv *priv = &mdev->priv; + int irq = pci_irq_vector(mdev->pdev, MLX5_EQ_VEC_COMP_BASE + i); + + if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) { + mlx5_core_warn(mdev, "zalloc_cpumask_var failed"); + return -ENOMEM; + } + + cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node), + priv->irq_info[i].mask); + + if (IS_ENABLED(CONFIG_SMP) && + irq_set_affinity_hint(irq, priv->irq_info[i].mask)) + mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", irq); + + return 0; +} + +static void mlx5_irq_clear_affinity_hint(struct mlx5_core_dev *mdev, int i) +{ + struct mlx5_priv *priv = &mdev->priv; + int irq = pci_irq_vector(mdev->pdev, MLX5_EQ_VEC_COMP_BASE + i); + + irq_set_affinity_hint(irq, NULL); + free_cpumask_var(priv->irq_info[i].mask); +} + +static int mlx5_irq_set_affinity_hints(struct mlx5_core_dev *mdev) +{ + int err; + int i; + + for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++) { + err = mlx5_irq_set_affinity_hint(mdev, i); + if (err) + goto err_out; + } + + return 0; + +err_out: + for (i--; i >= 0; i--) + mlx5_irq_clear_affinity_hint(mdev, i); + + return err; +} + +static void mlx5_irq_clear_affinity_hints(struct mlx5_core_dev *mdev) +{ + int i; + + for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++) + mlx5_irq_clear_affinity_hint(mdev, i); +} + int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, unsigned int *irqn) { @@ -1097,6 +1150,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, goto err_stop_eqs; } + err = mlx5_irq_set_affinity_hints(dev); + if (err) { + dev_err(&pdev->dev, "Failed to alloc affinity hint cpumask\n"); + goto err_affinity_hints; + } + err = mlx5_init_fs(dev); if (err) { dev_err(&pdev->dev, "Failed to init flow steering\n"); @@ -1154,6 +1213,9 @@ err_sriov: mlx5_cleanup_fs(dev); err_fs: + mlx5_irq_clear_affinity_hints(dev); + +err_affinity_hints: free_comp_eqs(dev); err_stop_eqs: @@ -1222,6 +1284,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, mlx5_sriov_detach(dev); mlx5_cleanup_fs(dev); + mlx5_irq_clear_affinity_hints(dev); free_comp_eqs(dev); mlx5_stop_eqs(dev); mlx5_put_uars_page(dev, priv->uar); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c index db9e665ab104..889130edb715 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c @@ -213,8 +213,8 @@ int mlx5_core_create_qp(struct mlx5_core_dev *dev, err_cmd: memset(din, 0, sizeof(din)); memset(dout, 0, sizeof(dout)); - MLX5_SET(destroy_qp_in, in, opcode, MLX5_CMD_OP_DESTROY_QP); - MLX5_SET(destroy_qp_in, in, qpn, qp->qpn); + MLX5_SET(destroy_qp_in, din, opcode, MLX5_CMD_OP_DESTROY_QP); + MLX5_SET(destroy_qp_in, din, qpn, qp->qpn); mlx5_cmd_exec(dev, din, sizeof(din), dout, sizeof(dout)); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rl.c b/drivers/net/ethernet/mellanox/mlx5/core/rl.c index e651e4c02867..d3c33e9eea72 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/rl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/rl.c @@ -125,16 +125,16 @@ static struct mlx5_rl_entry *find_rl_entry(struct mlx5_rl_table *table, return ret_entry; } -static int mlx5_set_rate_limit_cmd(struct mlx5_core_dev *dev, +static int mlx5_set_pp_rate_limit_cmd(struct mlx5_core_dev *dev, u32 rate, u16 index) { - u32 in[MLX5_ST_SZ_DW(set_rate_limit_in)] = {0}; - u32 out[MLX5_ST_SZ_DW(set_rate_limit_out)] = {0}; + u32 in[MLX5_ST_SZ_DW(set_pp_rate_limit_in)] = {0}; + u32 out[MLX5_ST_SZ_DW(set_pp_rate_limit_out)] = {0}; - MLX5_SET(set_rate_limit_in, in, opcode, - MLX5_CMD_OP_SET_RATE_LIMIT); - MLX5_SET(set_rate_limit_in, in, rate_limit_index, index); - MLX5_SET(set_rate_limit_in, in, rate_limit, rate); + MLX5_SET(set_pp_rate_limit_in, in, opcode, + MLX5_CMD_OP_SET_PP_RATE_LIMIT); + MLX5_SET(set_pp_rate_limit_in, in, rate_limit_index, index); + MLX5_SET(set_pp_rate_limit_in, in, rate_limit, rate); return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } @@ -173,7 +173,7 @@ int mlx5_rl_add_rate(struct mlx5_core_dev *dev, u32 rate, u16 *index) entry->refcount++; } else { /* new rate limit */ - err = mlx5_set_rate_limit_cmd(dev, rate, entry->index); + err = mlx5_set_pp_rate_limit_cmd(dev, rate, entry->index); if (err) { mlx5_core_err(dev, "Failed configuring rate: %u (%d)\n", rate, err); @@ -209,7 +209,7 @@ void mlx5_rl_remove_rate(struct mlx5_core_dev *dev, u32 rate) entry->refcount--; if (!entry->refcount) { /* need to remove rate */ - mlx5_set_rate_limit_cmd(dev, 0, entry->index); + mlx5_set_pp_rate_limit_cmd(dev, 0, entry->index); entry->rate = 0; } @@ -262,8 +262,8 @@ void mlx5_cleanup_rl_table(struct mlx5_core_dev *dev) /* Clear all configured rates */ for (i = 0; i < table->max_size; i++) if (table->rl_entry[i].rate) - mlx5_set_rate_limit_cmd(dev, 0, - table->rl_entry[i].index); + mlx5_set_pp_rate_limit_cmd(dev, 0, + table->rl_entry[i].index); kfree(dev->priv.rl_table.rl_entry); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c index 07a9ba6cfc70..2f74953e4561 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c @@ -71,9 +71,9 @@ struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port) struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan; struct mlx5e_vxlan *vxlan; - spin_lock(&vxlan_db->lock); + spin_lock_bh(&vxlan_db->lock); vxlan = radix_tree_lookup(&vxlan_db->tree, port); - spin_unlock(&vxlan_db->lock); + spin_unlock_bh(&vxlan_db->lock); return vxlan; } @@ -88,8 +88,12 @@ static void mlx5e_vxlan_add_port(struct work_struct *work) struct mlx5e_vxlan *vxlan; int err; - if (mlx5e_vxlan_lookup_port(priv, port)) + mutex_lock(&priv->state_lock); + vxlan = mlx5e_vxlan_lookup_port(priv, port); + if (vxlan) { + atomic_inc(&vxlan->refcount); goto free_work; + } if (mlx5e_vxlan_core_add_port_cmd(priv->mdev, port)) goto free_work; @@ -99,10 +103,11 @@ static void mlx5e_vxlan_add_port(struct work_struct *work) goto err_delete_port; vxlan->udp_port = port; + atomic_set(&vxlan->refcount, 1); - spin_lock_irq(&vxlan_db->lock); + spin_lock_bh(&vxlan_db->lock); err = radix_tree_insert(&vxlan_db->tree, vxlan->udp_port, vxlan); - spin_unlock_irq(&vxlan_db->lock); + spin_unlock_bh(&vxlan_db->lock); if (err) goto err_free; @@ -113,35 +118,39 @@ err_free: err_delete_port: mlx5e_vxlan_core_del_port_cmd(priv->mdev, port); free_work: + mutex_unlock(&priv->state_lock); kfree(vxlan_work); } -static void __mlx5e_vxlan_core_del_port(struct mlx5e_priv *priv, u16 port) +static void mlx5e_vxlan_del_port(struct work_struct *work) { + struct mlx5e_vxlan_work *vxlan_work = + container_of(work, struct mlx5e_vxlan_work, work); + struct mlx5e_priv *priv = vxlan_work->priv; struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan; + u16 port = vxlan_work->port; struct mlx5e_vxlan *vxlan; + bool remove = false; - spin_lock_irq(&vxlan_db->lock); - vxlan = radix_tree_delete(&vxlan_db->tree, port); - spin_unlock_irq(&vxlan_db->lock); - + mutex_lock(&priv->state_lock); + spin_lock_bh(&vxlan_db->lock); + vxlan = radix_tree_lookup(&vxlan_db->tree, port); if (!vxlan) - return; - - mlx5e_vxlan_core_del_port_cmd(priv->mdev, vxlan->udp_port); - - kfree(vxlan); -} + goto out_unlock; -static void mlx5e_vxlan_del_port(struct work_struct *work) -{ - struct mlx5e_vxlan_work *vxlan_work = - container_of(work, struct mlx5e_vxlan_work, work); - struct mlx5e_priv *priv = vxlan_work->priv; - u16 port = vxlan_work->port; + if (atomic_dec_and_test(&vxlan->refcount)) { + radix_tree_delete(&vxlan_db->tree, port); + remove = true; + } - __mlx5e_vxlan_core_del_port(priv, port); +out_unlock: + spin_unlock_bh(&vxlan_db->lock); + if (remove) { + mlx5e_vxlan_core_del_port_cmd(priv->mdev, port); + kfree(vxlan); + } + mutex_unlock(&priv->state_lock); kfree(vxlan_work); } @@ -171,12 +180,11 @@ void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv) struct mlx5e_vxlan *vxlan; unsigned int port = 0; - spin_lock_irq(&vxlan_db->lock); + /* Lockless since we are the only radix-tree consumers, wq is disabled */ while (radix_tree_gang_lookup(&vxlan_db->tree, (void **)&vxlan, port, 1)) { port = vxlan->udp_port; - spin_unlock_irq(&vxlan_db->lock); - __mlx5e_vxlan_core_del_port(priv, (u16)port); - spin_lock_irq(&vxlan_db->lock); + radix_tree_delete(&vxlan_db->tree, port); + mlx5e_vxlan_core_del_port_cmd(priv->mdev, port); + kfree(vxlan); } - spin_unlock_irq(&vxlan_db->lock); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h index 5def12c048e3..5ef6ae7d568a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h @@ -36,6 +36,7 @@ #include "en.h" struct mlx5e_vxlan { + atomic_t refcount; u16 udp_port; }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 3b9c8a0437bf..d373df7b11bd 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4346,6 +4346,7 @@ static int mlxsw_sp_port_stp_set(struct mlxsw_sp_port *mlxsw_sp_port, static int mlxsw_sp_port_ovs_join(struct mlxsw_sp_port *mlxsw_sp_port) { + u16 vid = 1; int err; err = mlxsw_sp_port_vp_mode_set(mlxsw_sp_port, true); @@ -4358,8 +4359,19 @@ static int mlxsw_sp_port_ovs_join(struct mlxsw_sp_port *mlxsw_sp_port) true, false); if (err) goto err_port_vlan_set; + + for (; vid <= VLAN_N_VID - 1; vid++) { + err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_port, + vid, false); + if (err) + goto err_vid_learning_set; + } + return 0; +err_vid_learning_set: + for (vid--; vid >= 1; vid--) + mlxsw_sp_port_vid_learning_set(mlxsw_sp_port, vid, true); err_port_vlan_set: mlxsw_sp_port_stp_set(mlxsw_sp_port, false); err_port_stp_set: @@ -4369,6 +4381,12 @@ err_port_stp_set: static void mlxsw_sp_port_ovs_leave(struct mlxsw_sp_port *mlxsw_sp_port) { + u16 vid; + + for (vid = VLAN_N_VID - 1; vid >= 1; vid--) + mlxsw_sp_port_vid_learning_set(mlxsw_sp_port, + vid, true); + mlxsw_sp_port_vlan_set(mlxsw_sp_port, 2, VLAN_N_VID - 1, false, false); mlxsw_sp_port_stp_set(mlxsw_sp_port, false); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 72ef4f8025f0..be657b8533f0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -2436,25 +2436,16 @@ static void mlxsw_sp_neigh_fini(struct mlxsw_sp *mlxsw_sp) rhashtable_destroy(&mlxsw_sp->router->neigh_ht); } -static int mlxsw_sp_neigh_rif_flush(struct mlxsw_sp *mlxsw_sp, - const struct mlxsw_sp_rif *rif) -{ - char rauht_pl[MLXSW_REG_RAUHT_LEN]; - - mlxsw_reg_rauht_pack(rauht_pl, MLXSW_REG_RAUHT_OP_WRITE_DELETE_ALL, - rif->rif_index, rif->addr); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl); -} - static void mlxsw_sp_neigh_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_rif *rif) { struct mlxsw_sp_neigh_entry *neigh_entry, *tmp; - mlxsw_sp_neigh_rif_flush(mlxsw_sp, rif); list_for_each_entry_safe(neigh_entry, tmp, &rif->neigh_list, - rif_list_node) + rif_list_node) { + mlxsw_sp_neigh_entry_update(mlxsw_sp, neigh_entry, false); mlxsw_sp_neigh_entry_destroy(mlxsw_sp, neigh_entry); + } } enum mlxsw_sp_nexthop_type { |