diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox')
31 files changed, 397 insertions, 212 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index a1202e53710c..dd029d91bbc2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -47,7 +47,7 @@ #define EN_ETHTOOL_SHORT_MASK cpu_to_be16(0xffff) #define EN_ETHTOOL_WORD_MASK cpu_to_be32(0xffffffff) -static int mlx4_en_moderation_update(struct mlx4_en_priv *priv) +int mlx4_en_moderation_update(struct mlx4_en_priv *priv) { int i, t; int err = 0; @@ -663,7 +663,7 @@ void __init mlx4_en_init_ptys2ethtool_map(void) MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_1000BASE_T, SPEED_1000, ETHTOOL_LINK_MODE_1000baseT_Full_BIT); MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_1000BASE_CX_SGMII, SPEED_1000, - ETHTOOL_LINK_MODE_1000baseKX_Full_BIT); + ETHTOOL_LINK_MODE_1000baseX_Full_BIT); MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_1000BASE_KX, SPEED_1000, ETHTOOL_LINK_MODE_1000baseKX_Full_BIT); MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_T, SPEED_10000, @@ -675,9 +675,9 @@ void __init mlx4_en_init_ptys2ethtool_map(void) MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_KR, SPEED_10000, ETHTOOL_LINK_MODE_10000baseKR_Full_BIT); MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_CR, SPEED_10000, - ETHTOOL_LINK_MODE_10000baseKR_Full_BIT); + ETHTOOL_LINK_MODE_10000baseCR_Full_BIT); MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_SR, SPEED_10000, - ETHTOOL_LINK_MODE_10000baseKR_Full_BIT); + ETHTOOL_LINK_MODE_10000baseSR_Full_BIT); MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_20GBASE_KR2, SPEED_20000, ETHTOOL_LINK_MODE_20000baseMLD2_Full_BIT, ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT); @@ -2011,8 +2011,6 @@ static int mlx4_en_set_tunable(struct net_device *dev, return ret; } -#define MLX4_EEPROM_PAGE_LEN 256 - static int mlx4_en_get_module_info(struct net_device *dev, struct ethtool_modinfo *modinfo) { @@ -2047,7 +2045,7 @@ static int mlx4_en_get_module_info(struct net_device *dev, break; case MLX4_MODULE_ID_SFP: modinfo->type = ETH_MODULE_SFF_8472; - modinfo->eeprom_len = MLX4_EEPROM_PAGE_LEN; + modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; break; default: return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index b5eb116249dd..91334229c120 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -371,6 +371,9 @@ mlx4_en_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb, int nhoff = skb_network_offset(skb); int ret = 0; + if (skb->encapsulation) + return -EPROTONOSUPPORT; + if (skb->protocol != htons(ETH_P_IP)) return -EPROTONOSUPPORT; @@ -2278,9 +2281,14 @@ int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv, bool carry_xdp_prog) { struct bpf_prog *xdp_prog; - int i, t; + int i, t, ret; - mlx4_en_copy_priv(tmp, priv, prof); + ret = mlx4_en_copy_priv(tmp, priv, prof); + if (ret) { + en_warn(priv, "%s: mlx4_en_copy_priv() failed, return\n", + __func__); + return ret; + } if (mlx4_en_alloc_resources(tmp)) { en_warn(priv, @@ -3657,6 +3665,8 @@ int mlx4_en_reset_config(struct net_device *dev, en_err(priv, "Failed starting port\n"); } + if (!err) + err = mlx4_en_moderation_update(priv); out: mutex_unlock(&mdev->state_lock); kfree(tmp); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 605c079d4841..b0837ad94da6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -868,6 +868,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) struct mlx4_en_tx_desc *tx_desc; struct mlx4_wqe_data_seg *data; struct mlx4_en_tx_info *tx_info; + u32 __maybe_unused ring_cons; int tx_ind; int nr_txbb; int desc_size; @@ -881,7 +882,6 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) bool stop_queue; bool inline_ok; u8 data_offset; - u32 ring_cons; bool bf_ok; tx_ind = skb_get_queue_mapping(skb); diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index f6cfec81ccc3..dc4ac1a2b6b6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -823,6 +823,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) #define QUERY_DEV_CAP_MAD_DEMUX_OFFSET 0xb0 #define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_BASE_OFFSET 0xa8 #define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_RANGE_OFFSET 0xac +#define QUERY_DEV_CAP_MAP_CLOCK_TO_USER 0xc1 #define QUERY_DEV_CAP_QP_RATE_LIMIT_NUM_OFFSET 0xcc #define QUERY_DEV_CAP_QP_RATE_LIMIT_MAX_OFFSET 0xd0 #define QUERY_DEV_CAP_QP_RATE_LIMIT_MIN_OFFSET 0xd2 @@ -841,6 +842,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) if (mlx4_is_mfunc(dev)) disable_unsupported_roce_caps(outbox); + MLX4_GET(field, outbox, QUERY_DEV_CAP_MAP_CLOCK_TO_USER); + dev_cap->map_clock_to_user = field & 0x80; MLX4_GET(field, outbox, QUERY_DEV_CAP_RSVD_QP_OFFSET); dev_cap->reserved_qps = 1 << (field & 0xf); MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_QP_OFFSET); diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h index 8f020f26ebf5..cf64e54eecb0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.h +++ b/drivers/net/ethernet/mellanox/mlx4/fw.h @@ -131,6 +131,7 @@ struct mlx4_dev_cap { u32 health_buffer_addrs; struct mlx4_port_cap port_cap[MLX4_MAX_PORTS + 1]; bool wol_port[MLX4_MAX_PORTS + 1]; + bool map_clock_to_user; }; struct mlx4_func_cap { diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 942646fb2256..35882d6ded8b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -498,6 +498,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) } } + dev->caps.map_clock_to_user = dev_cap->map_clock_to_user; dev->caps.uar_page_size = PAGE_SIZE; dev->caps.num_uars = dev_cap->uar_size / PAGE_SIZE; dev->caps.local_ca_ack_delay = dev_cap->local_ca_ack_delay; @@ -1948,6 +1949,11 @@ int mlx4_get_internal_clock_params(struct mlx4_dev *dev, if (mlx4_is_slave(dev)) return -EOPNOTSUPP; + if (!dev->caps.map_clock_to_user) { + mlx4_dbg(dev, "Map clock to user is not supported.\n"); + return -EOPNOTSUPP; + } + if (!params) return -EINVAL; @@ -3520,6 +3526,7 @@ slave_start: if (!SRIOV_VALID_STATE(dev->flags)) { mlx4_err(dev, "Invalid SRIOV state\n"); + err = -EINVAL; goto err_close; } } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index a2f69c6f0c79..17a5bd4c68b2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -797,6 +797,7 @@ void mlx4_en_ptp_overflow_check(struct mlx4_en_dev *mdev); #define DEV_FEATURE_CHANGED(dev, new_features, feature) \ ((dev->features & feature) ^ (new_features & feature)) +int mlx4_en_moderation_update(struct mlx4_en_priv *priv); int mlx4_en_reset_config(struct net_device *dev, struct hwtstamp_config ts_config, netdev_features_t new_features); diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c index ba6ac31a339d..256a06b3c096 100644 --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@ -1973,6 +1973,7 @@ EXPORT_SYMBOL(mlx4_get_roce_gid_from_slave); #define I2C_ADDR_LOW 0x50 #define I2C_ADDR_HIGH 0x51 #define I2C_PAGE_SIZE 256 +#define I2C_HIGH_PAGE_SIZE 128 /* Module Info Data */ struct mlx4_cable_info { @@ -2026,6 +2027,88 @@ static inline const char *cable_info_mad_err_str(u16 mad_status) return "Unknown Error"; } +static int mlx4_get_module_id(struct mlx4_dev *dev, u8 port, u8 *module_id) +{ + struct mlx4_cmd_mailbox *inbox, *outbox; + struct mlx4_mad_ifc *inmad, *outmad; + struct mlx4_cable_info *cable_info; + int ret; + + inbox = mlx4_alloc_cmd_mailbox(dev); + if (IS_ERR(inbox)) + return PTR_ERR(inbox); + + outbox = mlx4_alloc_cmd_mailbox(dev); + if (IS_ERR(outbox)) { + mlx4_free_cmd_mailbox(dev, inbox); + return PTR_ERR(outbox); + } + + inmad = (struct mlx4_mad_ifc *)(inbox->buf); + outmad = (struct mlx4_mad_ifc *)(outbox->buf); + + inmad->method = 0x1; /* Get */ + inmad->class_version = 0x1; + inmad->mgmt_class = 0x1; + inmad->base_version = 0x1; + inmad->attr_id = cpu_to_be16(0xFF60); /* Module Info */ + + cable_info = (struct mlx4_cable_info *)inmad->data; + cable_info->dev_mem_address = 0; + cable_info->page_num = 0; + cable_info->i2c_addr = I2C_ADDR_LOW; + cable_info->size = cpu_to_be16(1); + + ret = mlx4_cmd_box(dev, inbox->dma, outbox->dma, port, 3, + MLX4_CMD_MAD_IFC, MLX4_CMD_TIME_CLASS_C, + MLX4_CMD_NATIVE); + if (ret) + goto out; + + if (be16_to_cpu(outmad->status)) { + /* Mad returned with bad status */ + ret = be16_to_cpu(outmad->status); + mlx4_warn(dev, + "MLX4_CMD_MAD_IFC Get Module ID attr(%x) port(%d) i2c_addr(%x) offset(%d) size(%d): Response Mad Status(%x) - %s\n", + 0xFF60, port, I2C_ADDR_LOW, 0, 1, ret, + cable_info_mad_err_str(ret)); + ret = -ret; + goto out; + } + cable_info = (struct mlx4_cable_info *)outmad->data; + *module_id = cable_info->data[0]; +out: + mlx4_free_cmd_mailbox(dev, inbox); + mlx4_free_cmd_mailbox(dev, outbox); + return ret; +} + +static void mlx4_sfp_eeprom_params_set(u8 *i2c_addr, u8 *page_num, u16 *offset) +{ + *i2c_addr = I2C_ADDR_LOW; + *page_num = 0; + + if (*offset < I2C_PAGE_SIZE) + return; + + *i2c_addr = I2C_ADDR_HIGH; + *offset -= I2C_PAGE_SIZE; +} + +static void mlx4_qsfp_eeprom_params_set(u8 *i2c_addr, u8 *page_num, u16 *offset) +{ + /* Offsets 0-255 belong to page 0. + * Offsets 256-639 belong to pages 01, 02, 03. + * For example, offset 400 is page 02: 1 + (400 - 256) / 128 = 2 + */ + if (*offset < I2C_PAGE_SIZE) + *page_num = 0; + else + *page_num = 1 + (*offset - I2C_PAGE_SIZE) / I2C_HIGH_PAGE_SIZE; + *i2c_addr = I2C_ADDR_LOW; + *offset -= *page_num * I2C_HIGH_PAGE_SIZE; +} + /** * mlx4_get_module_info - Read cable module eeprom data * @dev: mlx4_dev. @@ -2045,12 +2128,30 @@ int mlx4_get_module_info(struct mlx4_dev *dev, u8 port, struct mlx4_cmd_mailbox *inbox, *outbox; struct mlx4_mad_ifc *inmad, *outmad; struct mlx4_cable_info *cable_info; - u16 i2c_addr; + u8 module_id, i2c_addr, page_num; int ret; if (size > MODULE_INFO_MAX_READ) size = MODULE_INFO_MAX_READ; + ret = mlx4_get_module_id(dev, port, &module_id); + if (ret) + return ret; + + switch (module_id) { + case MLX4_MODULE_ID_SFP: + mlx4_sfp_eeprom_params_set(&i2c_addr, &page_num, &offset); + break; + case MLX4_MODULE_ID_QSFP: + case MLX4_MODULE_ID_QSFP_PLUS: + case MLX4_MODULE_ID_QSFP28: + mlx4_qsfp_eeprom_params_set(&i2c_addr, &page_num, &offset); + break; + default: + mlx4_err(dev, "Module ID not recognized: %#x\n", module_id); + return -EINVAL; + } + inbox = mlx4_alloc_cmd_mailbox(dev); if (IS_ERR(inbox)) return PTR_ERR(inbox); @@ -2076,11 +2177,9 @@ int mlx4_get_module_info(struct mlx4_dev *dev, u8 port, */ size -= offset + size - I2C_PAGE_SIZE; - i2c_addr = I2C_ADDR_LOW; - cable_info = (struct mlx4_cable_info *)inmad->data; cable_info->dev_mem_address = cpu_to_be16(offset); - cable_info->page_num = 0; + cable_info->page_num = page_num; cable_info->i2c_addr = i2c_addr; cable_info->size = cpu_to_be16(size); diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 1187ef1375e2..cb341372d5a3 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -4986,6 +4986,7 @@ static int mlx4_do_mirror_rule(struct mlx4_dev *dev, struct res_fs_rule *fs_rule if (!fs_rule->mirr_mbox) { mlx4_err(dev, "rule mirroring mailbox is null\n"); + mlx4_free_cmd_mailbox(dev, mailbox); return -EINVAL; } memcpy(mailbox->buf, fs_rule->mirr_mbox, fs_rule->mirr_mbox_size); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 76547d35cd0e..6c7b364d0bf0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -130,11 +130,8 @@ static int cmd_alloc_index(struct mlx5_cmd *cmd) static void cmd_free_index(struct mlx5_cmd *cmd, int idx) { - unsigned long flags; - - spin_lock_irqsave(&cmd->alloc_lock, flags); + lockdep_assert_held(&cmd->alloc_lock); set_bit(idx, &cmd->bitmask); - spin_unlock_irqrestore(&cmd->alloc_lock, flags); } static void cmd_ent_get(struct mlx5_cmd_work_ent *ent) @@ -144,13 +141,21 @@ static void cmd_ent_get(struct mlx5_cmd_work_ent *ent) static void cmd_ent_put(struct mlx5_cmd_work_ent *ent) { + struct mlx5_cmd *cmd = ent->cmd; + unsigned long flags; + + spin_lock_irqsave(&cmd->alloc_lock, flags); if (!refcount_dec_and_test(&ent->refcnt)) - return; + goto out; - if (ent->idx >= 0) - cmd_free_index(ent->cmd, ent->idx); + if (ent->idx >= 0) { + cmd_free_index(cmd, ent->idx); + up(ent->page_queue ? &cmd->pages_sem : &cmd->sem); + } cmd_free_ent(ent); +out: + spin_unlock_irqrestore(&cmd->alloc_lock, flags); } static struct mlx5_cmd_layout *get_inst(struct mlx5_cmd *cmd, int idx) @@ -865,7 +870,7 @@ static void cb_timeout_handler(struct work_struct *work) ent->ret = -ETIMEDOUT; mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) Async, timeout. Will cause a leak of a command resource\n", ent->idx, mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); - mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); + mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, true); out: cmd_ent_put(ent); /* for the cmd_ent_get() took on schedule delayed work */ @@ -883,25 +888,6 @@ static bool opcode_allowed(struct mlx5_cmd *cmd, u16 opcode) return cmd->allowed_opcode == opcode; } -static int cmd_alloc_index_retry(struct mlx5_cmd *cmd) -{ - unsigned long alloc_end = jiffies + msecs_to_jiffies(1000); - int idx; - -retry: - idx = cmd_alloc_index(cmd); - if (idx < 0 && time_before(jiffies, alloc_end)) { - /* Index allocation can fail on heavy load of commands. This is a temporary - * situation as the current command already holds the semaphore, meaning that - * another command completion is being handled and it is expected to release - * the entry index soon. - */ - cpu_relax(); - goto retry; - } - return idx; -} - static void cmd_work_handler(struct work_struct *work) { struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work); @@ -919,7 +905,7 @@ static void cmd_work_handler(struct work_struct *work) sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem; down(sem); if (!ent->page_queue) { - alloc_ret = cmd_alloc_index_retry(cmd); + alloc_ret = cmd_alloc_index(cmd); if (alloc_ret < 0) { mlx5_core_err(dev, "failed to allocate command entry\n"); if (ent->callback) { @@ -977,7 +963,7 @@ static void cmd_work_handler(struct work_struct *work) MLX5_SET(mbox_out, ent->out, status, status); MLX5_SET(mbox_out, ent->out, syndrome, drv_synd); - mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); + mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, true); return; } @@ -991,7 +977,7 @@ static void cmd_work_handler(struct work_struct *work) poll_timeout(ent); /* make sure we read the descriptor after ownership is SW */ rmb(); - mlx5_cmd_comp_handler(dev, 1UL << ent->idx, (ent->ret == -ETIMEDOUT)); + mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, (ent->ret == -ETIMEDOUT)); } } @@ -1051,7 +1037,7 @@ static void wait_func_handle_exec_timeout(struct mlx5_core_dev *dev, mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); ent->ret = -ETIMEDOUT; - mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); + mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, true); } static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent) @@ -1577,8 +1563,6 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force vector = vec & 0xffffffff; for (i = 0; i < (1 << cmd->log_sz); i++) { if (test_bit(i, &vector)) { - struct semaphore *sem; - ent = cmd->ent_arr[i]; /* if we already completed the command, ignore it */ @@ -1601,10 +1585,6 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) cmd_ent_put(ent); - if (ent->page_queue) - sem = &cmd->pages_sem; - else - sem = &cmd->sem; ent->ts2 = ktime_get_ns(); memcpy(ent->out->first.data, ent->lay->out, sizeof(ent->lay->out)); dump_command(dev, ent, 0); @@ -1658,7 +1638,6 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force */ complete(&ent->done); } - up(sem); } } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index eb2e57ff08a6..97359417c6e7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -1005,7 +1005,7 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer) err = mlx5_core_alloc_pd(dev, &tracer->buff.pdn); if (err) { mlx5_core_warn(dev, "FWTracer: Failed to allocate PD %d\n", err); - return err; + goto err_cancel_work; } err = mlx5_fw_tracer_create_mkey(tracer); @@ -1017,12 +1017,20 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer) MLX5_NB_INIT(&tracer->nb, fw_tracer_event, DEVICE_TRACER); mlx5_eq_notifier_register(dev, &tracer->nb); - mlx5_fw_tracer_start(tracer); - + err = mlx5_fw_tracer_start(tracer); + if (err) { + mlx5_core_warn(dev, "FWTracer: Failed to start tracer %d\n", err); + goto err_notifier_unregister; + } return 0; +err_notifier_unregister: + mlx5_eq_notifier_unregister(dev, &tracer->nb); + mlx5_core_destroy_mkey(dev, &tracer->buff.mkey); err_dealloc_pd: mlx5_core_dealloc_pd(dev, tracer->buff.pdn); +err_cancel_work: + cancel_work_sync(&tracer->read_fw_strings_work); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index d48292ccda29..9239d767443f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -234,18 +234,12 @@ struct ttc_params { void mlx5e_set_ttc_basic_params(struct mlx5e_priv *priv, struct ttc_params *ttc_params); void mlx5e_set_ttc_ft_params(struct ttc_params *ttc_params); -void mlx5e_set_inner_ttc_ft_params(struct ttc_params *ttc_params); int mlx5e_create_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params, struct mlx5e_ttc_table *ttc); void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv, struct mlx5e_ttc_table *ttc); -int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params, - struct mlx5e_ttc_table *ttc); -void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv, - struct mlx5e_ttc_table *ttc); - void mlx5e_destroy_flow_table(struct mlx5e_flow_table *ft); void mlx5e_enable_cvlan_filter(struct mlx5e_priv *priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c index 951ea26d96bc..6d27f69cc7fc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c @@ -227,6 +227,10 @@ static int mlx5e_tc_tun_parse_geneve_options(struct mlx5e_priv *priv, option_key = (struct geneve_opt *)&enc_opts.key->data[0]; option_mask = (struct geneve_opt *)&enc_opts.mask->data[0]; + if (option_mask->opt_class == 0 && option_mask->type == 0 && + !memchr_inv(option_mask->opt_data, 0, option_mask->length * 4)) + return 0; + if (option_key->length > max_tlv_option_data_len) { NL_SET_ERR_MSG_MOD(extack, "Matching on GENEVE options: unsupported option len"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index cf58c9637904..c467f5e981f6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -515,9 +515,6 @@ void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv) struct mlx5_core_dev *mdev = priv->mdev; struct net_device *netdev = priv->netdev; - if (!priv->ipsec) - return; - if (!(mlx5_accel_ipsec_device_caps(mdev) & MLX5_ACCEL_IPSEC_CAP_ESP) || !MLX5_CAP_ETH(mdev, swp)) { mlx5_core_dbg(mdev, "mlx5e: ESP and SWP offload not supported\n"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 01089c2283d7..e92cc60eade3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -700,11 +700,11 @@ static int get_fec_supported_advertised(struct mlx5_core_dev *dev, return 0; } -static void ptys2ethtool_supported_advertised_port(struct ethtool_link_ksettings *link_ksettings, - u32 eth_proto_cap, - u8 connector_type, bool ext) +static void ptys2ethtool_supported_advertised_port(struct mlx5_core_dev *mdev, + struct ethtool_link_ksettings *link_ksettings, + u32 eth_proto_cap, u8 connector_type) { - if ((!connector_type && !ext) || connector_type >= MLX5E_CONNECTOR_TYPE_NUMBER) { + if (!MLX5_CAP_PCAM_FEATURE(mdev, ptys_connector_type)) { if (eth_proto_cap & (MLX5E_PROT_MASK(MLX5E_10GBASE_CR) | MLX5E_PROT_MASK(MLX5E_10GBASE_SR) | MLX5E_PROT_MASK(MLX5E_40GBASE_CR4) @@ -836,9 +836,9 @@ static int ptys2connector_type[MLX5E_CONNECTOR_TYPE_NUMBER] = { [MLX5E_PORT_OTHER] = PORT_OTHER, }; -static u8 get_connector_port(u32 eth_proto, u8 connector_type, bool ext) +static u8 get_connector_port(struct mlx5_core_dev *mdev, u32 eth_proto, u8 connector_type) { - if ((connector_type || ext) && connector_type < MLX5E_CONNECTOR_TYPE_NUMBER) + if (MLX5_CAP_PCAM_FEATURE(mdev, ptys_connector_type)) return ptys2connector_type[connector_type]; if (eth_proto & @@ -937,11 +937,11 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, link_ksettings); eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap; - - link_ksettings->base.port = get_connector_port(eth_proto_oper, - connector_type, ext); - ptys2ethtool_supported_advertised_port(link_ksettings, eth_proto_admin, - connector_type, ext); + connector_type = connector_type < MLX5E_CONNECTOR_TYPE_NUMBER ? + connector_type : MLX5E_PORT_UNKNOWN; + link_ksettings->base.port = get_connector_port(mdev, eth_proto_oper, connector_type); + ptys2ethtool_supported_advertised_port(mdev, link_ksettings, eth_proto_admin, + connector_type); get_lp_advertising(mdev, eth_proto_lp, link_ksettings); if (an_status == MLX5_AN_COMPLETE) @@ -1683,7 +1683,7 @@ static int mlx5e_get_module_eeprom(struct net_device *netdev, if (size_read < 0) { netdev_err(priv->netdev, "%s: mlx5_query_eeprom failed:0x%x\n", __func__, size_read); - return 0; + return size_read; } i += size_read; @@ -1811,6 +1811,7 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev, { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; + int err; if (!MLX5_CAP_GEN(mdev, cqe_compression)) return -EOPNOTSUPP; @@ -1820,7 +1821,10 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev, return -EINVAL; } - mlx5e_modify_rx_cqe_compression_locked(priv, enable); + err = mlx5e_modify_rx_cqe_compression_locked(priv, enable); + if (err) + return err; + priv->channels.params.rx_cqe_compress_def = enable; return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index c4ac7a9968d1..c3b9278486a1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -1123,7 +1123,7 @@ void mlx5e_set_ttc_basic_params(struct mlx5e_priv *priv, ttc_params->inner_ttc = &priv->fs.inner_ttc; } -void mlx5e_set_inner_ttc_ft_params(struct ttc_params *ttc_params) +static void mlx5e_set_inner_ttc_ft_params(struct ttc_params *ttc_params) { struct mlx5_flow_table_attr *ft_attr = &ttc_params->ft_attr; @@ -1142,8 +1142,8 @@ void mlx5e_set_ttc_ft_params(struct ttc_params *ttc_params) ft_attr->prio = MLX5E_NIC_PRIO; } -int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params, - struct mlx5e_ttc_table *ttc) +static int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params, + struct mlx5e_ttc_table *ttc) { struct mlx5e_flow_table *ft = &ttc->ft; int err; @@ -1173,8 +1173,8 @@ err: return err; } -void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv, - struct mlx5e_ttc_table *ttc) +static void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv, + struct mlx5e_ttc_table *ttc) { if (!mlx5e_tunnel_inner_ft_supported(priv->mdev)) return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 8b8581f71e79..2465165cbea7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2365,8 +2365,9 @@ static u8 mlx5e_build_icosq_log_wq_sz(struct mlx5e_params *params, { switch (params->rq_wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: - return order_base_2(MLX5E_UMR_WQEBBS) + - mlx5e_get_rq_log_wq_sz(rqp->rqc); + return max_t(u8, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE, + order_base_2(MLX5E_UMR_WQEBBS) + + mlx5e_get_rq_log_wq_sz(rqp->rqc)); default: /* MLX5_WQ_TYPE_CYCLIC */ return MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE; } @@ -3804,20 +3805,67 @@ static int set_feature_rx_all(struct net_device *netdev, bool enable) return mlx5_set_port_fcs(mdev, !enable); } +static int mlx5e_set_rx_port_ts(struct mlx5_core_dev *mdev, bool enable) +{ + u32 in[MLX5_ST_SZ_DW(pcmr_reg)] = {}; + bool supported, curr_state; + int err; + + if (!MLX5_CAP_GEN(mdev, ports_check)) + return 0; + + err = mlx5_query_ports_check(mdev, in, sizeof(in)); + if (err) + return err; + + supported = MLX5_GET(pcmr_reg, in, rx_ts_over_crc_cap); + curr_state = MLX5_GET(pcmr_reg, in, rx_ts_over_crc); + + if (!supported || enable == curr_state) + return 0; + + MLX5_SET(pcmr_reg, in, local_port, 1); + MLX5_SET(pcmr_reg, in, rx_ts_over_crc, enable); + + return mlx5_set_ports_check(mdev, in, sizeof(in)); +} + static int set_feature_rx_fcs(struct net_device *netdev, bool enable) { struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5e_channels *chs = &priv->channels; + struct mlx5_core_dev *mdev = priv->mdev; int err; mutex_lock(&priv->state_lock); - priv->channels.params.scatter_fcs_en = enable; - err = mlx5e_modify_channels_scatter_fcs(&priv->channels, enable); - if (err) - priv->channels.params.scatter_fcs_en = !enable; + if (enable) { + err = mlx5e_set_rx_port_ts(mdev, false); + if (err) + goto out; - mutex_unlock(&priv->state_lock); + chs->params.scatter_fcs_en = true; + err = mlx5e_modify_channels_scatter_fcs(chs, true); + if (err) { + chs->params.scatter_fcs_en = false; + mlx5e_set_rx_port_ts(mdev, true); + } + } else { + chs->params.scatter_fcs_en = false; + err = mlx5e_modify_channels_scatter_fcs(chs, false); + if (err) { + chs->params.scatter_fcs_en = true; + goto out; + } + err = mlx5e_set_rx_port_ts(mdev, true); + if (err) { + mlx5_core_warn(mdev, "Failed to set RX port timestamp %d\n", err); + err = 0; + } + } +out: + mutex_unlock(&priv->state_lock); return err; } @@ -3859,12 +3907,11 @@ static int set_feature_arfs(struct net_device *netdev, bool enable) static int mlx5e_handle_feature(struct net_device *netdev, netdev_features_t *features, - netdev_features_t wanted_features, netdev_features_t feature, mlx5e_feature_handler feature_handler) { - netdev_features_t changes = wanted_features ^ netdev->features; - bool enable = !!(wanted_features & feature); + netdev_features_t changes = *features ^ netdev->features; + bool enable = !!(*features & feature); int err; if (!(changes & feature)) @@ -3872,22 +3919,22 @@ static int mlx5e_handle_feature(struct net_device *netdev, err = feature_handler(netdev, enable); if (err) { + MLX5E_SET_FEATURE(features, feature, !enable); netdev_err(netdev, "%s feature %pNF failed, err %d\n", enable ? "Enable" : "Disable", &feature, err); return err; } - MLX5E_SET_FEATURE(features, feature, enable); return 0; } int mlx5e_set_features(struct net_device *netdev, netdev_features_t features) { - netdev_features_t oper_features = netdev->features; + netdev_features_t oper_features = features; int err = 0; #define MLX5E_HANDLE_FEATURE(feature, handler) \ - mlx5e_handle_feature(netdev, &oper_features, features, feature, handler) + mlx5e_handle_feature(netdev, &oper_features, feature, handler) err |= MLX5E_HANDLE_FEATURE(NETIF_F_LRO, set_feature_lro); err |= MLX5E_HANDLE_FEATURE(NETIF_F_HW_VLAN_CTAG_FILTER, @@ -5011,6 +5058,8 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM; netdev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM; + netdev->vlan_features |= NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM; } if (mlx5e_tunnel_proto_supported(mdev, IPPROTO_GRE)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index ec117e441425..5abc15a92cfa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -57,6 +57,7 @@ #include "lib/devcom.h" #include "lib/geneve.h" #include "diag/en_tc_tracepoint.h" +#include <asm/div64.h> struct mlx5_nic_flow_attr { u32 action; @@ -443,12 +444,32 @@ static void mlx5e_detach_mod_hdr(struct mlx5e_priv *priv, static struct mlx5_core_dev *mlx5e_hairpin_get_mdev(struct net *net, int ifindex) { + struct mlx5_core_dev *mdev; struct net_device *netdev; struct mlx5e_priv *priv; - netdev = __dev_get_by_index(net, ifindex); + netdev = dev_get_by_index(net, ifindex); + if (!netdev) + return ERR_PTR(-ENODEV); + priv = netdev_priv(netdev); - return priv->mdev; + mdev = priv->mdev; + dev_put(netdev); + + /* Mirred tc action holds a refcount on the ifindex net_device (see + * net/sched/act_mirred.c:tcf_mirred_get_dev). So, it's okay to continue using mdev + * after dev_put(netdev), while we're in the context of adding a tc flow. + * + * The mdev pointer corresponds to the peer/out net_device of a hairpin. It is then + * stored in a hairpin object, which exists until all flows, that refer to it, get + * removed. + * + * On the other hand, after a hairpin object has been created, the peer net_device may + * be removed/unbound while there are still some hairpin flows that are using it. This + * case is handled by mlx5e_tc_hairpin_update_dead_peer, which is hooked to + * NETDEV_UNREGISTER event of the peer net_device. + */ + return mdev; } static int mlx5e_hairpin_create_transport(struct mlx5e_hairpin *hp) @@ -647,6 +668,10 @@ mlx5e_hairpin_create(struct mlx5e_priv *priv, struct mlx5_hairpin_params *params func_mdev = priv->mdev; peer_mdev = mlx5e_hairpin_get_mdev(dev_net(priv->netdev), peer_ifindex); + if (IS_ERR(peer_mdev)) { + err = PTR_ERR(peer_mdev); + goto create_pair_err; + } pair = mlx5_core_hairpin_create(func_mdev, peer_mdev, params); if (IS_ERR(pair)) { @@ -785,6 +810,11 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, int err; peer_mdev = mlx5e_hairpin_get_mdev(dev_net(priv->netdev), peer_ifindex); + if (IS_ERR(peer_mdev)) { + NL_SET_ERR_MSG_MOD(extack, "invalid ifindex of mirred device"); + return PTR_ERR(peer_mdev); + } + if (!MLX5_CAP_GEN(priv->mdev, hairpin) || !MLX5_CAP_GEN(peer_mdev, hairpin)) { NL_SET_ERR_MSG_MOD(extack, "hairpin is not supported"); return -EOPNOTSUPP; @@ -1837,8 +1867,8 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, BIT(FLOW_DISSECTOR_KEY_ENC_IP) | BIT(FLOW_DISSECTOR_KEY_ENC_OPTS))) { NL_SET_ERR_MSG_MOD(extack, "Unsupported key"); - netdev_warn(priv->netdev, "Unsupported key used: 0x%x\n", - dissector->used_keys); + netdev_dbg(priv->netdev, "Unsupported key used: 0x%x\n", + dissector->used_keys); return -EOPNOTSUPP; } @@ -3169,8 +3199,12 @@ static int add_vlan_push_action(struct mlx5e_priv *priv, if (err) return err; - *out_dev = dev_get_by_index_rcu(dev_net(vlan_dev), - dev_get_iflink(vlan_dev)); + rcu_read_lock(); + *out_dev = dev_get_by_index_rcu(dev_net(vlan_dev), dev_get_iflink(vlan_dev)); + rcu_read_unlock(); + if (!*out_dev) + return -ENODEV; + if (is_vlan_dev(*out_dev)) err = add_vlan_push_action(priv, attr, out_dev, action); @@ -3943,13 +3977,13 @@ errout: return err; } -static int apply_police_params(struct mlx5e_priv *priv, u32 rate, +static int apply_police_params(struct mlx5e_priv *priv, u64 rate, struct netlink_ext_ack *extack) { struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch *esw; + u32 rate_mbps = 0; u16 vport_num; - u32 rate_mbps; int err; vport_num = rpriv->rep->vport; @@ -3966,7 +4000,11 @@ static int apply_police_params(struct mlx5e_priv *priv, u32 rate, * Moreover, if rate is non zero we choose to configure to a minimum of * 1 mbit/sec. */ - rate_mbps = rate ? max_t(u32, (rate * 8 + 500000) / 1000000, 1) : 0; + if (rate) { + rate = (rate * BITS_PER_BYTE) + 500000; + rate_mbps = max_t(u32, do_div(rate, 1000000), 1); + } + err = mlx5_esw_modify_vport_rate(esw, vport_num, rate_mbps); if (err) NL_SET_ERR_MSG_MOD(extack, "failed applying action to hardware"); @@ -4070,7 +4108,7 @@ static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv, list_for_each_entry_safe(hpe, tmp, &init_wait_list, dead_peer_wait_list) { wait_for_completion(&hpe->res_ready); if (!IS_ERR_OR_NULL(hpe->hp) && hpe->peer_vhca_id == peer_vhca_id) - hpe->hp->pair->peer_gone = true; + mlx5_core_hairpin_clear_dead_peer(hpe->hp->pair); mlx5e_hairpin_put(priv, hpe); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 0a20938b4aad..30a2ee3c40a0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -926,13 +926,24 @@ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev) mutex_unlock(&table->lock); } +#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING +#define MLX5_MAX_ASYNC_EQS 4 +#else +#define MLX5_MAX_ASYNC_EQS 3 +#endif + int mlx5_eq_table_create(struct mlx5_core_dev *dev) { struct mlx5_eq_table *eq_table = dev->priv.eq_table; + int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ? + MLX5_CAP_GEN(dev, max_num_eqs) : + 1 << MLX5_CAP_GEN(dev, log_max_eq); int err; eq_table->num_comp_eqs = - mlx5_irq_get_num_comp(eq_table->irq_table); + min_t(int, + mlx5_irq_get_num_comp(eq_table->irq_table), + num_eqs - MLX5_MAX_ASYNC_EQS); err = create_async_eqs(dev); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 7cc80dc4e6d8..31c832e5256e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1977,10 +1977,6 @@ esw_check_vport_match_metadata_supported(const struct mlx5_eswitch *esw) if (!MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source)) return false; - if (mlx5_core_is_ecpf_esw_manager(esw->dev) || - mlx5_ecpf_vport_exists(esw->dev)) - return false; - return true; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 2eceb72f0f64..5baf2c666d29 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -968,17 +968,19 @@ static int connect_fwd_rules(struct mlx5_core_dev *dev, static int connect_flow_table(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft, struct fs_prio *prio) { - struct mlx5_flow_table *next_ft; + struct mlx5_flow_table *next_ft, *first_ft; int err = 0; /* Connect_prev_fts and update_root_ft_create are mutually exclusive */ - if (list_empty(&prio->node.children)) { + first_ft = list_first_entry_or_null(&prio->node.children, + struct mlx5_flow_table, node.list); + if (!first_ft || first_ft->level > ft->level) { err = connect_prev_fts(dev, ft, prio); if (err) return err; - next_ft = find_next_chained_ft(prio); + next_ft = first_ft ? first_ft : find_next_chained_ft(prio); err = connect_fwd_rules(dev, ft, next_ft); if (err) return err; @@ -1068,6 +1070,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa destroy_ft: root->cmds->destroy_flow_table(root, ft); free_ft: + rhltable_destroy(&ft->fgs_hash); kfree(ft); unlock_root: mutex_unlock(&root->chain_lock); @@ -1603,9 +1606,9 @@ static int build_match_list(struct match_list_head *match_head, curr_match = kmalloc(sizeof(*curr_match), GFP_ATOMIC); if (!curr_match) { + rcu_read_unlock(); free_match_list(match_head, ft_locked); - err = -ENOMEM; - goto out; + return -ENOMEM; } if (!tree_get_node(&g->node)) { kfree(curr_match); @@ -1614,7 +1617,6 @@ static int build_match_list(struct match_list_head *match_head, curr_match->g = g; list_add_tail(&curr_match->list, &match_head->list); } -out: rcu_read_unlock(); return err; } @@ -1696,6 +1698,7 @@ search_again_locked: if (!fte_tmp) continue; rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte_tmp); + /* No error check needed here, because insert_fte() is not called */ up_write_ref_node(&fte_tmp->node, false); tree_put_node(&fte_tmp->node, false); kmem_cache_free(steering->ftes_cache, fte); @@ -1744,6 +1747,8 @@ skip_search: up_write_ref_node(&g->node, false); rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte); up_write_ref_node(&fte->node, false); + if (IS_ERR(rule)) + tree_put_node(&fte->node, false); return rule; } rule = ERR_PTR(-ENOENT); @@ -1843,6 +1848,8 @@ search_again_locked: up_write_ref_node(&g->node, false); rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte); up_write_ref_node(&fte->node, false); + if (IS_ERR(rule)) + tree_put_node(&fte->node, false); tree_put_node(&g->node, false); return rule; @@ -1940,6 +1947,8 @@ void mlx5_del_flow_rules(struct mlx5_flow_handle *handle) fte->node.del_hw_func = NULL; up_write_ref_node(&fte->node, false); tree_put_node(&fte->node, false); + } else { + up_write_ref_node(&fte->node, false); } kfree(handle); } @@ -2020,7 +2029,7 @@ static int disconnect_flow_table(struct mlx5_flow_table *ft) node.list) == ft)) return 0; - next_ft = find_next_chained_ft(prio); + next_ft = find_next_ft(ft); err = connect_fwd_rules(dev, next_ft, ft); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 0fed2419623d..1f3d12faa2a5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -319,17 +319,6 @@ static int mlx5i_create_flow_steering(struct mlx5e_priv *priv) } mlx5e_set_ttc_basic_params(priv, &ttc_params); - mlx5e_set_inner_ttc_ft_params(&ttc_params); - for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) - ttc_params.indir_tirn[tt] = priv->inner_indir_tir[tt].tirn; - - err = mlx5e_create_inner_ttc_table(priv, &ttc_params, &priv->fs.inner_ttc); - if (err) { - netdev_err(priv->netdev, "Failed to create inner ttc table, err=%d\n", - err); - goto err_destroy_arfs_tables; - } - mlx5e_set_ttc_ft_params(&ttc_params); for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) ttc_params.indir_tirn[tt] = priv->indir_tir[tt].tirn; @@ -338,13 +327,11 @@ static int mlx5i_create_flow_steering(struct mlx5e_priv *priv) if (err) { netdev_err(priv->netdev, "Failed to create ttc table, err=%d\n", err); - goto err_destroy_inner_ttc_table; + goto err_destroy_arfs_tables; } return 0; -err_destroy_inner_ttc_table: - mlx5e_destroy_inner_ttc_table(priv, &priv->fs.inner_ttc); err_destroy_arfs_tables: mlx5e_arfs_destroy_tables(priv); @@ -354,7 +341,6 @@ err_destroy_arfs_tables: static void mlx5i_destroy_flow_steering(struct mlx5e_priv *priv) { mlx5e_destroy_ttc_table(priv, &priv->fs.ttc); - mlx5e_destroy_inner_ttc_table(priv, &priv->fs.inner_ttc); mlx5e_arfs_destroy_tables(priv); } @@ -379,7 +365,7 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv) if (err) goto err_destroy_indirect_rqts; - err = mlx5e_create_indirect_tirs(priv, true); + err = mlx5e_create_indirect_tirs(priv, false); if (err) goto err_destroy_direct_rqts; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c index 5d20d615663e..101667c6b584 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c @@ -265,10 +265,8 @@ static int mlx5_lag_fib_event(struct notifier_block *nb, fen_info = container_of(info, struct fib_entry_notifier_info, info); fi = fen_info->fi; - if (fi->nh) { - NL_SET_ERR_MSG_MOD(info->extack, "IPv4 route with nexthop objects is not supported"); - return notifier_from_errno(-EINVAL); - } + if (fi->nh) + return NOTIFY_DONE; fib_dev = fib_info_nh(fen_info->fi, 0)->fib_nh_dev; if (fib_dev != ldev->pf[0].netdev && fib_dev != ldev->pf[1].netdev) { @@ -307,6 +305,11 @@ int mlx5_lag_mp_init(struct mlx5_lag *ldev) struct lag_mp *mp = &ldev->lag_mp; int err; + /* always clear mfi, as it might become stale when a route delete event + * has been missed + */ + mp->mfi = NULL; + if (mp->fib_nb.notifier_call) return 0; @@ -328,4 +331,5 @@ void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev) unregister_fib_notifier(&mp->fib_nb); mp->fib_nb.notifier_call = NULL; + mp->mfi = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c index 8e0dddc6383f..2389239acadc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c @@ -156,6 +156,9 @@ void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev) { int err; + if (!MLX5_CAP_GEN(dev, roce)) + return; + err = mlx5_nic_vport_enable_roce(dev); if (err) { mlx5_core_err(dev, "Failed to enable RoCE: %d\n", err); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c index 56bf900eb753..dbdb6a9592f0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c @@ -2,6 +2,7 @@ /* Copyright (c) 2019 Mellanox Technologies. */ #include <linux/mlx5/eswitch.h> +#include <linux/err.h> #include "dr_types.h" static int dr_domain_init_cache(struct mlx5dr_domain *dmn) @@ -64,9 +65,9 @@ static int dr_domain_init_resources(struct mlx5dr_domain *dmn) } dmn->uar = mlx5_get_uars_page(dmn->mdev); - if (!dmn->uar) { + if (IS_ERR(dmn->uar)) { mlx5dr_err(dmn, "Couldn't allocate UAR\n"); - ret = -ENOMEM; + ret = PTR_ERR(dmn->uar); goto clean_pd; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index f012aac83b10..401564b94eb1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -603,6 +603,7 @@ static int dr_cmd_modify_qp_rtr2rts(struct mlx5_core_dev *mdev, MLX5_SET(qpc, qpc, log_ack_req_freq, 0); MLX5_SET(qpc, qpc, retry_count, attr->retry_cnt); MLX5_SET(qpc, qpc, rnr_retry, attr->rnr_retry); + MLX5_SET(qpc, qpc, primary_address_path.ack_timeout, 0x8); /* ~1ms */ return mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RTR2RTS_QP, 0, qpc, &dr_qp->mqp); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c index b1068500f1df..0b5437051a3b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c @@ -457,6 +457,15 @@ err_modify_sq: return err; } +static void mlx5_hairpin_unpair_peer_sq(struct mlx5_hairpin *hp) +{ + int i; + + for (i = 0; i < hp->num_channels; i++) + mlx5_hairpin_modify_sq(hp->peer_mdev, hp->sqn[i], MLX5_SQC_STATE_RDY, + MLX5_SQC_STATE_RST, 0, 0); +} + static void mlx5_hairpin_unpair_queues(struct mlx5_hairpin *hp) { int i; @@ -465,13 +474,9 @@ static void mlx5_hairpin_unpair_queues(struct mlx5_hairpin *hp) for (i = 0; i < hp->num_channels; i++) mlx5_hairpin_modify_rq(hp->func_mdev, hp->rqn[i], MLX5_RQC_STATE_RDY, MLX5_RQC_STATE_RST, 0, 0); - /* unset peer SQs */ - if (hp->peer_gone) - return; - for (i = 0; i < hp->num_channels; i++) - mlx5_hairpin_modify_sq(hp->peer_mdev, hp->sqn[i], MLX5_SQC_STATE_RDY, - MLX5_SQC_STATE_RST, 0, 0); + if (!hp->peer_gone) + mlx5_hairpin_unpair_peer_sq(hp); } struct mlx5_hairpin * @@ -518,3 +523,16 @@ void mlx5_core_hairpin_destroy(struct mlx5_hairpin *hp) mlx5_hairpin_destroy_queues(hp); kfree(hp); } + +void mlx5_core_hairpin_clear_dead_peer(struct mlx5_hairpin *hp) +{ + int i; + + mlx5_hairpin_unpair_peer_sq(hp); + + /* destroy peer SQ */ + for (i = 0; i < hp->num_channels; i++) + mlx5_core_destroy_sq(hp->peer_mdev, hp->sqn[i]); + + hp->peer_gone = true; +} diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c index 71c90c8a9e94..882ea12098b7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c @@ -19,22 +19,14 @@ #define MLXSW_THERMAL_ASIC_TEMP_NORM 75000 /* 75C */ #define MLXSW_THERMAL_ASIC_TEMP_HIGH 85000 /* 85C */ #define MLXSW_THERMAL_ASIC_TEMP_HOT 105000 /* 105C */ -#define MLXSW_THERMAL_ASIC_TEMP_CRIT 110000 /* 110C */ +#define MLXSW_THERMAL_ASIC_TEMP_CRIT 140000 /* 140C */ #define MLXSW_THERMAL_HYSTERESIS_TEMP 5000 /* 5C */ #define MLXSW_THERMAL_MODULE_TEMP_SHIFT (MLXSW_THERMAL_HYSTERESIS_TEMP * 2) #define MLXSW_THERMAL_ZONE_MAX_NAME 16 #define MLXSW_THERMAL_TEMP_SCORE_MAX GENMASK(31, 0) #define MLXSW_THERMAL_MAX_STATE 10 +#define MLXSW_THERMAL_MIN_STATE 2 #define MLXSW_THERMAL_MAX_DUTY 255 -/* Minimum and maximum fan allowed speed in percent: from 20% to 100%. Values - * MLXSW_THERMAL_MAX_STATE + x, where x is between 2 and 10 are used for - * setting fan speed dynamic minimum. For example, if value is set to 14 (40%) - * cooling levels vector will be set to 4, 4, 4, 4, 4, 5, 6, 7, 8, 9, 10 to - * introduce PWM speed in percent: 40, 40, 40, 40, 40, 50, 60. 70, 80, 90, 100. - */ -#define MLXSW_THERMAL_SPEED_MIN (MLXSW_THERMAL_MAX_STATE + 2) -#define MLXSW_THERMAL_SPEED_MAX (MLXSW_THERMAL_MAX_STATE * 2) -#define MLXSW_THERMAL_SPEED_MIN_LEVEL 2 /* 20% */ /* External cooling devices, allowed for binding to mlxsw thermal zones. */ static char * const mlxsw_thermal_external_allowed_cdev[] = { @@ -177,6 +169,12 @@ mlxsw_thermal_module_trips_update(struct device *dev, struct mlxsw_core *core, if (err) return err; + if (crit_temp > emerg_temp) { + dev_warn(dev, "%s : Critical threshold %d is above emergency threshold %d\n", + tz->tzdev->type, crit_temp, emerg_temp); + return 0; + } + /* According to the system thermal requirements, the thermal zones are * defined with four trip points. The critical and emergency * temperature thresholds, provided by QSFP module are set as "active" @@ -191,11 +189,8 @@ mlxsw_thermal_module_trips_update(struct device *dev, struct mlxsw_core *core, tz->trips[MLXSW_THERMAL_TEMP_TRIP_NORM].temp = crit_temp; tz->trips[MLXSW_THERMAL_TEMP_TRIP_HIGH].temp = crit_temp; tz->trips[MLXSW_THERMAL_TEMP_TRIP_HOT].temp = emerg_temp; - if (emerg_temp > crit_temp) - tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = emerg_temp + + tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = emerg_temp + MLXSW_THERMAL_MODULE_TEMP_SHIFT; - else - tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = emerg_temp; return 0; } @@ -700,49 +695,16 @@ static int mlxsw_thermal_set_cur_state(struct thermal_cooling_device *cdev, struct mlxsw_thermal *thermal = cdev->devdata; struct device *dev = thermal->bus_info->dev; char mfsc_pl[MLXSW_REG_MFSC_LEN]; - unsigned long cur_state, i; int idx; - u8 duty; int err; + if (state > MLXSW_THERMAL_MAX_STATE) + return -EINVAL; + idx = mlxsw_get_cooling_device_idx(thermal, cdev); if (idx < 0) return idx; - /* Verify if this request is for changing allowed fan dynamical - * minimum. If it is - update cooling levels accordingly and update - * state, if current state is below the newly requested minimum state. - * For example, if current state is 5, and minimal state is to be - * changed from 4 to 6, thermal->cooling_levels[0 to 5] will be changed - * all from 4 to 6. And state 5 (thermal->cooling_levels[4]) should be - * overwritten. - */ - if (state >= MLXSW_THERMAL_SPEED_MIN && - state <= MLXSW_THERMAL_SPEED_MAX) { - state -= MLXSW_THERMAL_MAX_STATE; - for (i = 0; i <= MLXSW_THERMAL_MAX_STATE; i++) - thermal->cooling_levels[i] = max(state, i); - - mlxsw_reg_mfsc_pack(mfsc_pl, idx, 0); - err = mlxsw_reg_query(thermal->core, MLXSW_REG(mfsc), mfsc_pl); - if (err) - return err; - - duty = mlxsw_reg_mfsc_pwm_duty_cycle_get(mfsc_pl); - cur_state = mlxsw_duty_to_state(duty); - - /* If current fan state is lower than requested dynamical - * minimum, increase fan speed up to dynamical minimum. - */ - if (state < cur_state) - return 0; - - state = cur_state; - } - - if (state > MLXSW_THERMAL_MAX_STATE) - return -EINVAL; - /* Normalize the state to the valid speed range. */ state = thermal->cooling_levels[state]; mlxsw_reg_mfsc_pack(mfsc_pl, idx, mlxsw_state_to_duty(state)); @@ -1037,8 +999,7 @@ int mlxsw_thermal_init(struct mlxsw_core *core, /* Initialize cooling levels per PWM state. */ for (i = 0; i < MLXSW_THERMAL_MAX_STATE; i++) - thermal->cooling_levels[i] = max(MLXSW_THERMAL_SPEED_MIN_LEVEL, - i); + thermal->cooling_levels[i] = max(MLXSW_THERMAL_MIN_STATE, i); thermal->polling_delay = bus_info->low_frequency ? MLXSW_THERMAL_SLOW_POLL_INT : diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c index 95f408d0e103..7cc4c30af1a7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/i2c.c +++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c @@ -649,6 +649,7 @@ static int mlxsw_i2c_probe(struct i2c_client *client, return 0; errout: + mutex_destroy(&mlxsw_i2c->cmd.lock); i2c_set_clientdata(client, NULL); return err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index aa4fef789084..ff331251a019 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -1876,6 +1876,7 @@ int mlxsw_pci_driver_register(struct pci_driver *pci_driver) { pci_driver->probe = mlxsw_pci_probe; pci_driver->remove = mlxsw_pci_remove; + pci_driver->shutdown = mlxsw_pci_remove; return pci_register_driver(pci_driver); } EXPORT_SYMBOL(mlxsw_pci_driver_register); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c index 336e5ecc68f8..f1874578aa14 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c @@ -524,6 +524,16 @@ mlxsw_sp_mr_route_evif_resolve(struct mlxsw_sp_mr_table *mr_table, u16 erif_index = 0; int err; + /* Add the eRIF */ + if (mlxsw_sp_mr_vif_valid(rve->mr_vif)) { + erif_index = mlxsw_sp_rif_index(rve->mr_vif->rif); + err = mr->mr_ops->route_erif_add(mlxsw_sp, + rve->mr_route->route_priv, + erif_index); + if (err) + return err; + } + /* Update the route action, as the new eVIF can be a tunnel or a pimreg * device which will require updating the action. */ @@ -533,17 +543,7 @@ mlxsw_sp_mr_route_evif_resolve(struct mlxsw_sp_mr_table *mr_table, rve->mr_route->route_priv, route_action); if (err) - return err; - } - - /* Add the eRIF */ - if (mlxsw_sp_mr_vif_valid(rve->mr_vif)) { - erif_index = mlxsw_sp_rif_index(rve->mr_vif->rif); - err = mr->mr_ops->route_erif_add(mlxsw_sp, - rve->mr_route->route_priv, - erif_index); - if (err) - goto err_route_erif_add; + goto err_route_action_update; } /* Update the minimum MTU */ @@ -561,14 +561,14 @@ mlxsw_sp_mr_route_evif_resolve(struct mlxsw_sp_mr_table *mr_table, return 0; err_route_min_mtu_update: - if (mlxsw_sp_mr_vif_valid(rve->mr_vif)) - mr->mr_ops->route_erif_del(mlxsw_sp, rve->mr_route->route_priv, - erif_index); -err_route_erif_add: if (route_action != rve->mr_route->route_action) mr->mr_ops->route_action_update(mlxsw_sp, rve->mr_route->route_priv, rve->mr_route->route_action); +err_route_action_update: + if (mlxsw_sp_mr_vif_valid(rve->mr_vif)) + mr->mr_ops->route_erif_del(mlxsw_sp, rve->mr_route->route_priv, + erif_index); return err; } |