diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx5/core')
80 files changed, 2304 insertions, 1203 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index f8f0a712c943..4957412ff1f6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -156,15 +156,18 @@ static u8 alloc_token(struct mlx5_cmd *cmd) return token; } -static int cmd_alloc_index(struct mlx5_cmd *cmd) +static int cmd_alloc_index(struct mlx5_cmd *cmd, struct mlx5_cmd_work_ent *ent) { unsigned long flags; int ret; spin_lock_irqsave(&cmd->alloc_lock, flags); ret = find_first_bit(&cmd->vars.bitmask, cmd->vars.max_reg_cmds); - if (ret < cmd->vars.max_reg_cmds) + if (ret < cmd->vars.max_reg_cmds) { clear_bit(ret, &cmd->vars.bitmask); + ent->idx = ret; + cmd->ent_arr[ent->idx] = ent; + } spin_unlock_irqrestore(&cmd->alloc_lock, flags); return ret < cmd->vars.max_reg_cmds ? ret : -ENOMEM; @@ -979,7 +982,7 @@ static void cmd_work_handler(struct work_struct *work) sem = ent->page_queue ? &cmd->vars.pages_sem : &cmd->vars.sem; down(sem); if (!ent->page_queue) { - alloc_ret = cmd_alloc_index(cmd); + alloc_ret = cmd_alloc_index(cmd, ent); if (alloc_ret < 0) { mlx5_core_err_rl(dev, "failed to allocate command entry\n"); if (ent->callback) { @@ -994,15 +997,14 @@ static void cmd_work_handler(struct work_struct *work) up(sem); return; } - ent->idx = alloc_ret; } else { ent->idx = cmd->vars.max_reg_cmds; spin_lock_irqsave(&cmd->alloc_lock, flags); clear_bit(ent->idx, &cmd->vars.bitmask); + cmd->ent_arr[ent->idx] = ent; spin_unlock_irqrestore(&cmd->alloc_lock, flags); } - cmd->ent_arr[ent->idx] = ent; lay = get_inst(cmd, ent->idx); ent->lay = lay; memset(lay, 0, sizeof(*lay)); @@ -1921,6 +1923,7 @@ static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, { const char *namep = mlx5_command_str(opcode); struct mlx5_cmd_stats *stats; + unsigned long flags; if (!err || !(strcmp(namep, "unknown command opcode"))) return; @@ -1928,7 +1931,7 @@ static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, stats = xa_load(&dev->cmd.stats, opcode); if (!stats) return; - spin_lock_irq(&stats->lock); + spin_lock_irqsave(&stats->lock, flags); stats->failed++; if (err < 0) stats->last_failed_errno = -err; @@ -1937,7 +1940,7 @@ static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, stats->last_failed_mbox_status = status; stats->last_failed_syndrome = syndrome; } - spin_unlock_irq(&stats->lock); + spin_unlock_irqrestore(&stats->lock, flags); } /* preserve -EREMOTEIO for outbox.status != OK, otherwise return err as is */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index cf0477f53dc4..47e7c2639774 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -210,7 +210,7 @@ static bool is_dpll_supported(struct mlx5_core_dev *dev) return false; if (!MLX5_CAP_MCAM_REG2(dev, synce_registers)) { - mlx5_core_warn(dev, "Missing SyncE capability\n"); + mlx5_core_dbg(dev, "Missing SyncE capability\n"); return false; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index 3e064234f6fe..98d4306929f3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -157,6 +157,12 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change, return -EOPNOTSUPP; } + if (action == DEVLINK_RELOAD_ACTION_FW_ACTIVATE && + !dev->priv.fw_reset) { + NL_SET_ERR_MSG_MOD(extack, "FW activate is unsupported for this function"); + return -EOPNOTSUPP; + } + if (mlx5_core_is_pf(dev) && pci_num_vf(pdev)) NL_SET_ERR_MSG_MOD(extack, "reload while VFs are present is unfavorable"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/crdump.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/crdump.c index 28d02749d3c4..7659ad21e6e5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/crdump.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/crdump.c @@ -55,7 +55,10 @@ int mlx5_crdump_collect(struct mlx5_core_dev *dev, u32 *cr_data) ret = mlx5_vsc_sem_set_space(dev, MLX5_SEMAPHORE_SW_RESET, MLX5_VSC_LOCK); if (ret) { - mlx5_core_warn(dev, "Failed to lock SW reset semaphore\n"); + if (ret == -EBUSY) + mlx5_core_info(dev, "SW reset semaphore is already in use\n"); + else + mlx5_core_warn(dev, "Failed to lock SW reset semaphore\n"); goto unlock_gw; } 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 76d27d2ee40c..080e7eab52c7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -718,7 +718,7 @@ static void mlx5_fw_tracer_handle_traces(struct work_struct *work) while (block_timestamp > tracer->last_timestamp) { /* Check block override if it's not the first block */ - if (!tracer->last_timestamp) { + if (tracer->last_timestamp) { u64 *ts_event; /* To avoid block override be the HW in case of buffer * wraparound, the time stamp of the previous block diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c index 2cd81bb32c66..904e08de852e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c @@ -36,11 +36,18 @@ static int mlx5_dpll_clock_id_get(struct mlx5_core_dev *mdev, u64 *clock_id) return 0; } +struct mlx5_dpll_synce_status { + enum mlx5_msees_admin_status admin_status; + enum mlx5_msees_oper_status oper_status; + bool ho_acq; + bool oper_freq_measure; + enum mlx5_msees_failure_reason failure_reason; + s32 frequency_diff; +}; + static int mlx5_dpll_synce_status_get(struct mlx5_core_dev *mdev, - enum mlx5_msees_admin_status *admin_status, - enum mlx5_msees_oper_status *oper_status, - bool *ho_acq) + struct mlx5_dpll_synce_status *synce_status) { u32 out[MLX5_ST_SZ_DW(msees_reg)] = {}; u32 in[MLX5_ST_SZ_DW(msees_reg)] = {}; @@ -50,11 +57,12 @@ mlx5_dpll_synce_status_get(struct mlx5_core_dev *mdev, MLX5_REG_MSEES, 0, 0); if (err) return err; - if (admin_status) - *admin_status = MLX5_GET(msees_reg, out, admin_status); - *oper_status = MLX5_GET(msees_reg, out, oper_status); - if (ho_acq) - *ho_acq = MLX5_GET(msees_reg, out, ho_acq); + synce_status->admin_status = MLX5_GET(msees_reg, out, admin_status); + synce_status->oper_status = MLX5_GET(msees_reg, out, oper_status); + synce_status->ho_acq = MLX5_GET(msees_reg, out, ho_acq); + synce_status->oper_freq_measure = MLX5_GET(msees_reg, out, oper_freq_measure); + synce_status->failure_reason = MLX5_GET(msees_reg, out, failure_reason); + synce_status->frequency_diff = MLX5_GET(msees_reg, out, frequency_diff); return 0; } @@ -67,21 +75,23 @@ mlx5_dpll_synce_status_set(struct mlx5_core_dev *mdev, MLX5_SET(msees_reg, in, field_select, MLX5_MSEES_FIELD_SELECT_ENABLE | + MLX5_MSEES_FIELD_SELECT_ADMIN_FREQ_MEASURE | MLX5_MSEES_FIELD_SELECT_ADMIN_STATUS); MLX5_SET(msees_reg, in, admin_status, admin_status); + MLX5_SET(msees_reg, in, admin_freq_measure, true); return mlx5_core_access_reg(mdev, in, sizeof(in), out, sizeof(out), MLX5_REG_MSEES, 0, 1); } static enum dpll_lock_status -mlx5_dpll_lock_status_get(enum mlx5_msees_oper_status oper_status, bool ho_acq) +mlx5_dpll_lock_status_get(struct mlx5_dpll_synce_status *synce_status) { - switch (oper_status) { + switch (synce_status->oper_status) { case MLX5_MSEES_OPER_STATUS_SELF_TRACK: fallthrough; case MLX5_MSEES_OPER_STATUS_OTHER_TRACK: - return ho_acq ? DPLL_LOCK_STATUS_LOCKED_HO_ACQ : - DPLL_LOCK_STATUS_LOCKED; + return synce_status->ho_acq ? DPLL_LOCK_STATUS_LOCKED_HO_ACQ : + DPLL_LOCK_STATUS_LOCKED; case MLX5_MSEES_OPER_STATUS_HOLDOVER: fallthrough; case MLX5_MSEES_OPER_STATUS_FAIL_HOLDOVER: @@ -91,32 +101,60 @@ mlx5_dpll_lock_status_get(enum mlx5_msees_oper_status oper_status, bool ho_acq) } } +static enum dpll_lock_status_error +mlx5_dpll_lock_status_error_get(struct mlx5_dpll_synce_status *synce_status) +{ + switch (synce_status->oper_status) { + case MLX5_MSEES_OPER_STATUS_FAIL_HOLDOVER: + fallthrough; + case MLX5_MSEES_OPER_STATUS_FAIL_FREE_RUNNING: + switch (synce_status->failure_reason) { + case MLX5_MSEES_FAILURE_REASON_PORT_DOWN: + return DPLL_LOCK_STATUS_ERROR_MEDIA_DOWN; + case MLX5_MSEES_FAILURE_REASON_TOO_HIGH_FREQUENCY_DIFF: + return DPLL_LOCK_STATUS_ERROR_FRACTIONAL_FREQUENCY_OFFSET_TOO_HIGH; + default: + return DPLL_LOCK_STATUS_ERROR_UNDEFINED; + } + default: + return DPLL_LOCK_STATUS_ERROR_NONE; + } +} + static enum dpll_pin_state -mlx5_dpll_pin_state_get(enum mlx5_msees_admin_status admin_status, - enum mlx5_msees_oper_status oper_status) +mlx5_dpll_pin_state_get(struct mlx5_dpll_synce_status *synce_status) { - return (admin_status == MLX5_MSEES_ADMIN_STATUS_TRACK && - (oper_status == MLX5_MSEES_OPER_STATUS_SELF_TRACK || - oper_status == MLX5_MSEES_OPER_STATUS_OTHER_TRACK)) ? + return (synce_status->admin_status == MLX5_MSEES_ADMIN_STATUS_TRACK && + (synce_status->oper_status == MLX5_MSEES_OPER_STATUS_SELF_TRACK || + synce_status->oper_status == MLX5_MSEES_OPER_STATUS_OTHER_TRACK)) ? DPLL_PIN_STATE_CONNECTED : DPLL_PIN_STATE_DISCONNECTED; } -static int mlx5_dpll_device_lock_status_get(const struct dpll_device *dpll, - void *priv, - enum dpll_lock_status *status, - struct netlink_ext_ack *extack) +static int +mlx5_dpll_pin_ffo_get(struct mlx5_dpll_synce_status *synce_status, + s64 *ffo) { - enum mlx5_msees_oper_status oper_status; + if (!synce_status->oper_freq_measure) + return -ENODATA; + *ffo = synce_status->frequency_diff; + return 0; +} + +static int +mlx5_dpll_device_lock_status_get(const struct dpll_device *dpll, void *priv, + enum dpll_lock_status *status, + enum dpll_lock_status_error *status_error, + struct netlink_ext_ack *extack) +{ + struct mlx5_dpll_synce_status synce_status; struct mlx5_dpll *mdpll = priv; - bool ho_acq; int err; - err = mlx5_dpll_synce_status_get(mdpll->mdev, NULL, - &oper_status, &ho_acq); + err = mlx5_dpll_synce_status_get(mdpll->mdev, &synce_status); if (err) return err; - - *status = mlx5_dpll_lock_status_get(oper_status, ho_acq); + *status = mlx5_dpll_lock_status_get(&synce_status); + *status_error = mlx5_dpll_lock_status_error_get(&synce_status); return 0; } @@ -128,18 +166,9 @@ static int mlx5_dpll_device_mode_get(const struct dpll_device *dpll, return 0; } -static bool mlx5_dpll_device_mode_supported(const struct dpll_device *dpll, - void *priv, - enum dpll_mode mode, - struct netlink_ext_ack *extack) -{ - return mode == DPLL_MODE_MANUAL; -} - static const struct dpll_device_ops mlx5_dpll_device_ops = { .lock_status_get = mlx5_dpll_device_lock_status_get, .mode_get = mlx5_dpll_device_mode_get, - .mode_supported = mlx5_dpll_device_mode_supported, }; static int mlx5_dpll_pin_direction_get(const struct dpll_pin *pin, @@ -160,16 +189,14 @@ static int mlx5_dpll_state_on_dpll_get(const struct dpll_pin *pin, enum dpll_pin_state *state, struct netlink_ext_ack *extack) { - enum mlx5_msees_admin_status admin_status; - enum mlx5_msees_oper_status oper_status; + struct mlx5_dpll_synce_status synce_status; struct mlx5_dpll *mdpll = pin_priv; int err; - err = mlx5_dpll_synce_status_get(mdpll->mdev, &admin_status, - &oper_status, NULL); + err = mlx5_dpll_synce_status_get(mdpll->mdev, &synce_status); if (err) return err; - *state = mlx5_dpll_pin_state_get(admin_status, oper_status); + *state = mlx5_dpll_pin_state_get(&synce_status); return 0; } @@ -188,10 +215,25 @@ static int mlx5_dpll_state_on_dpll_set(const struct dpll_pin *pin, MLX5_MSEES_ADMIN_STATUS_FREE_RUNNING); } +static int mlx5_dpll_ffo_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + s64 *ffo, struct netlink_ext_ack *extack) +{ + struct mlx5_dpll_synce_status synce_status; + struct mlx5_dpll *mdpll = pin_priv; + int err; + + err = mlx5_dpll_synce_status_get(mdpll->mdev, &synce_status); + if (err) + return err; + return mlx5_dpll_pin_ffo_get(&synce_status, ffo); +} + static const struct dpll_pin_ops mlx5_dpll_pins_ops = { .direction_get = mlx5_dpll_pin_direction_get, .state_on_dpll_get = mlx5_dpll_state_on_dpll_get, .state_on_dpll_set = mlx5_dpll_state_on_dpll_set, + .ffo_get = mlx5_dpll_ffo_get, }; static const struct dpll_pin_properties mlx5_dpll_pin_properties = { @@ -211,19 +253,16 @@ static void mlx5_dpll_periodic_work(struct work_struct *work) { struct mlx5_dpll *mdpll = container_of(work, struct mlx5_dpll, work.work); - enum mlx5_msees_admin_status admin_status; - enum mlx5_msees_oper_status oper_status; + struct mlx5_dpll_synce_status synce_status; enum dpll_lock_status lock_status; enum dpll_pin_state pin_state; - bool ho_acq; int err; - err = mlx5_dpll_synce_status_get(mdpll->mdev, &admin_status, - &oper_status, &ho_acq); + err = mlx5_dpll_synce_status_get(mdpll->mdev, &synce_status); if (err) goto err_out; - lock_status = mlx5_dpll_lock_status_get(oper_status, ho_acq); - pin_state = mlx5_dpll_pin_state_get(admin_status, oper_status); + lock_status = mlx5_dpll_lock_status_get(&synce_status); + pin_state = mlx5_dpll_pin_state_get(&synce_status); if (!mdpll->last.valid) goto invalid_out; @@ -246,7 +285,7 @@ static void mlx5_dpll_netdev_dpll_pin_set(struct mlx5_dpll *mdpll, { if (mdpll->tracking_netdev) return; - netdev_dpll_pin_set(netdev, mdpll->dpll_pin); + dpll_netdev_pin_set(netdev, mdpll->dpll_pin); mdpll->tracking_netdev = netdev; } @@ -254,7 +293,7 @@ static void mlx5_dpll_netdev_dpll_pin_clear(struct mlx5_dpll *mdpll) { if (!mdpll->tracking_netdev) return; - netdev_dpll_pin_clear(mdpll->tracking_netdev); + dpll_netdev_pin_clear(mdpll->tracking_netdev); mdpll->tracking_netdev = NULL; } @@ -374,7 +413,7 @@ static void mlx5_dpll_remove(struct auxiliary_device *adev) struct mlx5_dpll *mdpll = auxiliary_get_drvdata(adev); struct mlx5_core_dev *mdev = mdpll->mdev; - cancel_delayed_work(&mdpll->work); + cancel_delayed_work_sync(&mdpll->work); mlx5_dpll_mdev_netdev_untrack(mdpll, mdev); destroy_workqueue(mdpll->wq); dpll_pin_unregister(mdpll->dpll, mdpll->dpll_pin, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index b2a5da9739d2..55c6ace0acd5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -72,7 +72,6 @@ struct page_pool; #define MLX5E_HW2SW_MTU(params, hwmtu) ((hwmtu) - ((params)->hard_mtu)) #define MLX5E_SW2HW_MTU(params, swmtu) ((swmtu) + ((params)->hard_mtu)) -#define MLX5E_MAX_NUM_TC 8 #define MLX5E_MAX_NUM_MQPRIO_CH_TC TC_QOPT_MAX_QUEUE #define MLX5_RX_HEADROOM NET_SKB_PAD @@ -364,7 +363,7 @@ struct mlx5e_cq { /* control */ struct net_device *netdev; struct mlx5_core_dev *mdev; - struct mlx5e_priv *priv; + struct workqueue_struct *workqueue; struct mlx5_wq_ctrl wq_ctrl; } ____cacheline_aligned_in_smp; @@ -484,10 +483,12 @@ struct mlx5e_xdp_info_fifo { struct mlx5e_xdpsq; struct mlx5e_xmit_data; +struct xsk_tx_metadata; typedef int (*mlx5e_fp_xmit_xdp_frame_check)(struct mlx5e_xdpsq *); typedef bool (*mlx5e_fp_xmit_xdp_frame)(struct mlx5e_xdpsq *, struct mlx5e_xmit_data *, - int); + int, + struct xsk_tx_metadata *); struct mlx5e_xdpsq { /* data path */ @@ -756,7 +757,7 @@ struct mlx5e_channel { /* data path */ struct mlx5e_rq rq; struct mlx5e_xdpsq rq_xdpsq; - struct mlx5e_txqsq sq[MLX5E_MAX_NUM_TC]; + struct mlx5e_txqsq sq[MLX5_MAX_NUM_TC]; struct mlx5e_icosq icosq; /* internal control operations */ struct mlx5e_txqsq __rcu * __rcu *qos_sqs; bool xdp; @@ -806,7 +807,7 @@ struct mlx5e_channels { struct mlx5e_channel_stats { struct mlx5e_ch_stats ch; - struct mlx5e_sq_stats sq[MLX5E_MAX_NUM_TC]; + struct mlx5e_sq_stats sq[MLX5_MAX_NUM_TC]; struct mlx5e_rq_stats rq; struct mlx5e_rq_stats xskrq; struct mlx5e_xdpsq_stats rq_xdpsq; @@ -816,8 +817,8 @@ struct mlx5e_channel_stats { struct mlx5e_ptp_stats { struct mlx5e_ch_stats ch; - struct mlx5e_sq_stats sq[MLX5E_MAX_NUM_TC]; - struct mlx5e_ptp_cq_stats cq[MLX5E_MAX_NUM_TC]; + struct mlx5e_sq_stats sq[MLX5_MAX_NUM_TC]; + struct mlx5e_ptp_cq_stats cq[MLX5_MAX_NUM_TC]; struct mlx5e_rq_stats rq; } ____cacheline_aligned_in_smp; @@ -826,6 +827,7 @@ enum { MLX5E_STATE_DESTROYING, MLX5E_STATE_XDP_TX_ENABLED, MLX5E_STATE_XDP_ACTIVE, + MLX5E_STATE_CHANNELS_ACTIVE, }; struct mlx5e_modify_sq_param { @@ -884,7 +886,6 @@ struct mlx5e_priv { struct mlx5e_rq drop_rq; struct mlx5e_channels channels; - u32 tisn[MLX5_MAX_PORTS][MLX5E_MAX_NUM_TC]; struct mlx5e_rx_res *rx_res; u32 *tx_rates; @@ -982,6 +983,8 @@ struct mlx5e_profile { void (*update_stats)(struct mlx5e_priv *priv); void (*update_carrier)(struct mlx5e_priv *priv); int (*max_nch_limit)(struct mlx5_core_dev *mdev); + u32 (*get_tisn)(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv, + u8 lag_port, u8 tc); unsigned int (*stats_grps_num)(struct mlx5e_priv *priv); mlx5e_stats_grp_t *stats_grps; const struct mlx5e_rx_handlers *rx_handlers; @@ -989,6 +992,11 @@ struct mlx5e_profile { u32 features; }; +u32 mlx5e_profile_get_tisn(struct mlx5_core_dev *mdev, + struct mlx5e_priv *priv, + const struct mlx5e_profile *profile, + u8 lag_port, u8 tc); + #define mlx5e_profile_feature_cap(profile, feature) \ ((profile)->features & BIT(MLX5E_PROFILE_FEATURE_##feature)) @@ -1036,6 +1044,8 @@ int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params, void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq); struct mlx5e_create_cq_param { + struct net_device *netdev; + struct workqueue_struct *wq; struct napi_struct *napi; struct mlx5e_ch_stats *ch_stats; int node; @@ -1043,7 +1053,7 @@ struct mlx5e_create_cq_param { }; struct mlx5e_cq_param; -int mlx5e_open_cq(struct mlx5e_priv *priv, struct dim_cq_moder moder, +int mlx5e_open_cq(struct mlx5_core_dev *mdev, struct dim_cq_moder moder, struct mlx5e_cq_param *param, struct mlx5e_create_cq_param *ccp, struct mlx5e_cq *cq); void mlx5e_close_cq(struct mlx5e_cq *cq); @@ -1114,7 +1124,7 @@ static inline bool mlx5_tx_swp_supported(struct mlx5_core_dev *mdev) extern const struct ethtool_ops mlx5e_ethtool_ops; int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, u32 *mkey); -int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev); +int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises); void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev); int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb, bool enable_mc_lb); @@ -1130,8 +1140,6 @@ void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq); int mlx5e_create_tis(struct mlx5_core_dev *mdev, void *in, u32 *tisn); void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn); -int mlx5e_create_tises(struct mlx5e_priv *priv); -void mlx5e_destroy_tises(struct mlx5e_priv *priv); int mlx5e_update_nic_rx(struct mlx5e_priv *priv); void mlx5e_update_carrier(struct mlx5e_priv *priv); int mlx5e_close(struct net_device *netdev); @@ -1173,9 +1181,9 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, struct ethtool_link_ksettings *link_ksettings); int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, const struct ethtool_link_ksettings *link_ksettings); -int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc); -int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, const u8 *key, - const u8 hfunc); +int mlx5e_get_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh); +int mlx5e_set_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh, + struct netlink_ext_ack *extack); u32 mlx5e_ethtool_get_rxfh_key_size(struct mlx5e_priv *priv); u32 mlx5e_ethtool_get_rxfh_indir_size(struct mlx5e_priv *priv); int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c index be83ad9db82a..671adbad0a40 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c @@ -154,6 +154,7 @@ static int fs_udp_create_groups(struct mlx5e_flow_table *ft, enum fs_udp_type ty in = kvzalloc(inlen, GFP_KERNEL); if (!in || !ft->g) { kfree(ft->g); + ft->g = NULL; kvfree(in); return -ENOMEM; } @@ -435,6 +436,7 @@ static int fs_any_create_groups(struct mlx5e_flow_table *ft) in = kvzalloc(inlen, GFP_KERNEL); if (!in || !ft->g) { kfree(ft->g); + ft->g = NULL; kvfree(in); return -ENOMEM; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c index 254c84739046..40c8df111754 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c @@ -36,7 +36,7 @@ int mlx5e_monitor_counter_supported(struct mlx5e_priv *priv) return true; } -void mlx5e_monitor_counter_arm(struct mlx5e_priv *priv) +static void mlx5e_monitor_counter_arm(struct mlx5e_priv *priv) { u32 in[MLX5_ST_SZ_DW(arm_monitor_counter_in)] = {}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.h index e1ac4b3d22fb..6beba7f075c1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.h @@ -7,6 +7,5 @@ int mlx5e_monitor_counter_supported(struct mlx5e_priv *priv); void mlx5e_monitor_counter_init(struct mlx5e_priv *priv); void mlx5e_monitor_counter_cleanup(struct mlx5e_priv *priv); -void mlx5e_monitor_counter_arm(struct mlx5e_priv *priv); #endif /* __MLX5_MONITOR_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index e097f336e1c4..5757f4f10c12 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -240,11 +240,14 @@ static u32 mlx5e_rx_get_linear_sz_xsk(struct mlx5e_params *params, return xsk->headroom + hw_mtu; } -static u32 mlx5e_rx_get_linear_sz_skb(struct mlx5e_params *params, bool xsk) +static u32 mlx5e_rx_get_linear_sz_skb(struct mlx5e_params *params, bool no_head_tail_room) { - /* SKBs built on XDP_PASS on XSK RQs don't have headroom. */ - u16 headroom = xsk ? 0 : mlx5e_get_linear_rq_headroom(params, NULL); u32 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); + u16 headroom; + + if (no_head_tail_room) + return SKB_DATA_ALIGN(hw_mtu); + headroom = mlx5e_get_linear_rq_headroom(params, NULL); return MLX5_SKB_FRAG_SZ(headroom + hw_mtu); } @@ -254,6 +257,7 @@ static u32 mlx5e_rx_get_linear_stride_sz(struct mlx5_core_dev *mdev, struct mlx5e_xsk_param *xsk, bool mpwqe) { + bool no_head_tail_room; u32 sz; /* XSK frames are mapped as individual pages, because frames may come in @@ -262,7 +266,13 @@ static u32 mlx5e_rx_get_linear_stride_sz(struct mlx5_core_dev *mdev, if (xsk) return mpwqe ? 1 << mlx5e_mpwrq_page_shift(mdev, xsk) : PAGE_SIZE; - sz = roundup_pow_of_two(mlx5e_rx_get_linear_sz_skb(params, false)); + no_head_tail_room = params->xdp_prog && mpwqe && !mlx5e_rx_is_linear_skb(mdev, params, xsk); + + /* When no_head_tail_room is set, headroom and tailroom are excluded from skb calculations. + * no_head_tail_room should be set in the case of XDP with Striding RQ + * when SKB is not linear. This is because another page is allocated for the linear part. + */ + sz = roundup_pow_of_two(mlx5e_rx_get_linear_sz_skb(params, no_head_tail_room)); /* XDP in mlx5e doesn't support multiple packets per page. * Do not assume sz <= PAGE_SIZE if params->xdp_prog is set. @@ -289,7 +299,11 @@ bool mlx5e_rx_is_linear_skb(struct mlx5_core_dev *mdev, if (params->packet_merge.type != MLX5E_PACKET_MERGE_NONE) return false; - /* Both XSK and non-XSK cases allocate an SKB on XDP_PASS. Packet data + /* Call mlx5e_rx_get_linear_sz_skb with the no_head_tail_room parameter set + * to exclude headroom and tailroom from calculations. + * no_head_tail_room is true when SKB is built on XDP_PASS on XSK RQs + * since packet data buffers don't have headroom and tailroom resreved for the SKB. + * Both XSK and non-XSK cases allocate an SKB on XDP_PASS. Packet data * must fit into a CPU page. */ if (mlx5e_rx_get_linear_sz_skb(params, xsk) > PAGE_SIZE) @@ -669,6 +683,8 @@ void mlx5e_build_rq_params(struct mlx5_core_dev *mdev, void mlx5e_build_create_cq_param(struct mlx5e_create_cq_param *ccp, struct mlx5e_channel *c) { *ccp = (struct mlx5e_create_cq_param) { + .netdev = c->netdev, + .wq = c->priv->wq, .napi = &c->napi, .ch_stats = c->stats, .node = cpu_to_node(c->cpu), @@ -1062,8 +1078,8 @@ void mlx5e_build_sq_param(struct mlx5_core_dev *mdev, void *wq = MLX5_ADDR_OF(sqc, sqc, wq); bool allow_swp; - allow_swp = - mlx5_geneve_tx_allowed(mdev) || !!mlx5_ipsec_device_caps(mdev); + allow_swp = mlx5_geneve_tx_allowed(mdev) || + (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_CRYPTO); mlx5e_build_sq_param_common(mdev, param); MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size); MLX5_SET(sqc, sqc, allow_swp, allow_swp); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index bb11e644d24f..a848a7fda66b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -42,9 +42,9 @@ mlx5e_ptp_port_ts_cqe_list_add(struct mlx5e_ptp_port_ts_cqe_list *list, u8 metad WARN_ON_ONCE(tracker->inuse); tracker->inuse = true; - spin_lock(&list->tracker_list_lock); + spin_lock_bh(&list->tracker_list_lock); list_add_tail(&tracker->entry, &list->tracker_list_head); - spin_unlock(&list->tracker_list_lock); + spin_unlock_bh(&list->tracker_list_lock); } static void @@ -54,9 +54,9 @@ mlx5e_ptp_port_ts_cqe_list_remove(struct mlx5e_ptp_port_ts_cqe_list *list, u8 me WARN_ON_ONCE(!tracker->inuse); tracker->inuse = false; - spin_lock(&list->tracker_list_lock); + spin_lock_bh(&list->tracker_list_lock); list_del(&tracker->entry); - spin_unlock(&list->tracker_list_lock); + spin_unlock_bh(&list->tracker_list_lock); } void mlx5e_ptpsq_track_metadata(struct mlx5e_ptpsq *ptpsq, u8 metadata) @@ -155,7 +155,7 @@ static void mlx5e_ptpsq_mark_ts_cqes_undelivered(struct mlx5e_ptpsq *ptpsq, struct mlx5e_ptp_metadata_map *metadata_map = &ptpsq->metadata_map; struct mlx5e_ptp_port_ts_cqe_tracker *pos, *n; - spin_lock(&cqe_list->tracker_list_lock); + spin_lock_bh(&cqe_list->tracker_list_lock); list_for_each_entry_safe(pos, n, &cqe_list->tracker_list_head, entry) { struct sk_buff *skb = mlx5e_ptp_metadata_map_lookup(metadata_map, pos->metadata_id); @@ -170,13 +170,15 @@ static void mlx5e_ptpsq_mark_ts_cqes_undelivered(struct mlx5e_ptpsq *ptpsq, pos->inuse = false; list_del(&pos->entry); } - spin_unlock(&cqe_list->tracker_list_lock); + spin_unlock_bh(&cqe_list->tracker_list_lock); } #define PTP_WQE_CTR2IDX(val) ((val) & ptpsq->ts_cqe_ctr_mask) static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq, struct mlx5_cqe64 *cqe, + u8 *md_buff, + u8 *md_buff_sz, int budget) { struct mlx5e_ptp_port_ts_cqe_list *pending_cqe_list = ptpsq->ts_cqe_pending_list; @@ -211,19 +213,24 @@ static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq, mlx5e_ptpsq_mark_ts_cqes_undelivered(ptpsq, hwtstamp); out: napi_consume_skb(skb, budget); - mlx5e_ptp_metadata_fifo_push(&ptpsq->metadata_freelist, metadata_id); + md_buff[(*md_buff_sz)++] = metadata_id; if (unlikely(mlx5e_ptp_metadata_map_unhealthy(&ptpsq->metadata_map)) && !test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) queue_work(ptpsq->txqsq.priv->wq, &ptpsq->report_unhealthy_work); } -static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget) +static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int napi_budget) { struct mlx5e_ptpsq *ptpsq = container_of(cq, struct mlx5e_ptpsq, ts_cq); - struct mlx5_cqwq *cqwq = &cq->wq; + int budget = min(napi_budget, MLX5E_TX_CQ_POLL_BUDGET); + u8 metadata_buff[MLX5E_TX_CQ_POLL_BUDGET]; + u8 metadata_buff_sz = 0; + struct mlx5_cqwq *cqwq; struct mlx5_cqe64 *cqe; int work_done = 0; + cqwq = &cq->wq; + if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &ptpsq->txqsq.state))) return false; @@ -234,7 +241,8 @@ static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget) do { mlx5_cqwq_pop(cqwq); - mlx5e_ptp_handle_ts_cqe(ptpsq, cqe, budget); + mlx5e_ptp_handle_ts_cqe(ptpsq, cqe, + metadata_buff, &metadata_buff_sz, napi_budget); } while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(cqwq))); mlx5_cqwq_update_db_record(cqwq); @@ -242,6 +250,10 @@ static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget) /* ensure cq space is freed before enabling more cqes */ wmb(); + while (metadata_buff_sz > 0) + mlx5e_ptp_metadata_fifo_push(&ptpsq->metadata_freelist, + metadata_buff[--metadata_buff_sz]); + mlx5e_txqsq_wake(&ptpsq->txqsq); return work_done == budget; @@ -506,9 +518,11 @@ static int mlx5e_ptp_open_txqsqs(struct mlx5e_ptp *c, for (tc = 0; tc < num_tc; tc++) { int txq_ix = ix_base + tc; + u32 tisn; - err = mlx5e_ptp_open_txqsq(c, c->priv->tisn[c->lag_port][tc], txq_ix, - cparams, tc, &c->ptpsq[tc]); + tisn = mlx5e_profile_get_tisn(c->mdev, c->priv, c->priv->profile, + c->lag_port, tc); + err = mlx5e_ptp_open_txqsq(c, tisn, txq_ix, cparams, tc, &c->ptpsq[tc]); if (err) goto close_txqsq; } @@ -543,6 +557,8 @@ static int mlx5e_ptp_open_tx_cqs(struct mlx5e_ptp *c, num_tc = mlx5e_get_dcb_num_tc(params); + ccp.netdev = c->netdev; + ccp.wq = c->priv->wq; ccp.node = dev_to_node(mlx5_core_dma_dev(c->mdev)); ccp.ch_stats = c->stats; ccp.napi = &c->napi; @@ -553,7 +569,7 @@ static int mlx5e_ptp_open_tx_cqs(struct mlx5e_ptp *c, for (tc = 0; tc < num_tc; tc++) { struct mlx5e_cq *cq = &c->ptpsq[tc].txqsq.cq; - err = mlx5e_open_cq(c->priv, ptp_moder, cq_param, &ccp, cq); + err = mlx5e_open_cq(c->mdev, ptp_moder, cq_param, &ccp, cq); if (err) goto out_err_txqsq_cq; } @@ -562,7 +578,7 @@ static int mlx5e_ptp_open_tx_cqs(struct mlx5e_ptp *c, struct mlx5e_cq *cq = &c->ptpsq[tc].ts_cq; struct mlx5e_ptpsq *ptpsq = &c->ptpsq[tc]; - err = mlx5e_open_cq(c->priv, ptp_moder, cq_param, &ccp, cq); + err = mlx5e_open_cq(c->mdev, ptp_moder, cq_param, &ccp, cq); if (err) goto out_err_ts_cq; @@ -590,6 +606,8 @@ static int mlx5e_ptp_open_rx_cq(struct mlx5e_ptp *c, struct mlx5e_cq_param *cq_param; struct mlx5e_cq *cq = &c->rq.cq; + ccp.netdev = c->netdev; + ccp.wq = c->priv->wq; ccp.node = dev_to_node(mlx5_core_dma_dev(c->mdev)); ccp.ch_stats = c->stats; ccp.napi = &c->napi; @@ -597,7 +615,7 @@ static int mlx5e_ptp_open_rx_cq(struct mlx5e_ptp *c, cq_param = &cparams->rq_param.cqp; - return mlx5e_open_cq(c->priv, ptp_moder, cq_param, &ccp, cq); + return mlx5e_open_cq(c->mdev, ptp_moder, cq_param, &ccp, cq); } static void mlx5e_ptp_close_tx_cqs(struct mlx5e_ptp *c) @@ -917,6 +935,7 @@ void mlx5e_ptp_activate_channel(struct mlx5e_ptp *c) if (test_bit(MLX5E_PTP_STATE_RX, c->state)) { mlx5e_ptp_rx_set_fs(c->priv); mlx5e_activate_rq(&c->rq); + netif_queue_set_napi(c->netdev, c->rq.ix, NETDEV_QUEUE_TYPE_RX, &c->napi); } mlx5e_trigger_napi_sched(&c->napi); } @@ -925,8 +944,10 @@ void mlx5e_ptp_deactivate_channel(struct mlx5e_ptp *c) { int tc; - if (test_bit(MLX5E_PTP_STATE_RX, c->state)) + if (test_bit(MLX5E_PTP_STATE_RX, c->state)) { + netif_queue_set_napi(c->netdev, c->rq.ix, NETDEV_QUEUE_TYPE_RX, NULL); mlx5e_deactivate_rq(&c->rq); + } if (test_bit(MLX5E_PTP_STATE_TX, c->state)) { for (tc = 0; tc < c->num_tc; tc++) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h index 7b700d0f956a..86f1854698b4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h @@ -49,7 +49,7 @@ enum { struct mlx5e_ptp { /* data path */ - struct mlx5e_ptpsq ptpsq[MLX5E_MAX_NUM_TC]; + struct mlx5e_ptpsq ptpsq[MLX5_MAX_NUM_TC]; struct mlx5e_rq rq; struct napi_struct napi; struct device *pdev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c index 244bc15a42ab..34adf8c3f81a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c @@ -77,6 +77,7 @@ int mlx5e_open_qos_sq(struct mlx5e_priv *priv, struct mlx5e_channels *chs, struct mlx5e_params *params; struct mlx5e_channel *c; struct mlx5e_txqsq *sq; + u32 tisn; params = &chs->params; @@ -123,11 +124,13 @@ int mlx5e_open_qos_sq(struct mlx5e_priv *priv, struct mlx5e_channels *chs, memset(¶m_cq, 0, sizeof(param_cq)); mlx5e_build_sq_param(priv->mdev, params, ¶m_sq); mlx5e_build_tx_cq_param(priv->mdev, params, ¶m_cq); - err = mlx5e_open_cq(priv, params->tx_cq_moderation, ¶m_cq, &ccp, &sq->cq); + err = mlx5e_open_cq(c->mdev, params->tx_cq_moderation, ¶m_cq, &ccp, &sq->cq); if (err) goto err_free_sq; - err = mlx5e_open_txqsq(c, priv->tisn[c->lag_port][0], txq_ix, params, - ¶m_sq, sq, 0, hw_id, + + tisn = mlx5e_profile_get_tisn(c->mdev, c->priv, c->priv->profile, + c->lag_port, 0); + err = mlx5e_open_txqsq(c, tisn, txq_ix, params, ¶m_sq, sq, 0, hw_id, priv->htb_qos_sq_stats[node_qid]); if (err) goto err_close_cq; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index b12fe3c5a258..a55452c69f06 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -147,6 +147,20 @@ mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv, } } +static void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *ma) +{ + struct mlx5e_rep_priv *rpriv = priv->ppriv; + u64 dbytes; + u64 dpkts; + + dpkts = priv->stats.rep_stats.vport_rx_packets - rpriv->prev_vf_vport_stats.rx_packets; + dbytes = priv->stats.rep_stats.vport_rx_bytes - rpriv->prev_vf_vport_stats.rx_bytes; + mlx5e_stats_copy_rep_stats(&rpriv->prev_vf_vport_stats, &priv->stats.rep_stats); + flow_stats_update(&ma->stats, dbytes, dpkts, 0, jiffies, + FLOW_ACTION_HW_STATS_DELAYED); +} + static int mlx5e_rep_setup_tc_cls_matchall(struct mlx5e_priv *priv, struct tc_cls_matchall_offload *ma) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c index fea8c0a5fe89..4358798d6ce1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c @@ -492,11 +492,11 @@ static int mlx5e_rx_reporter_dump(struct devlink_health_reporter *reporter, void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq) { - char icosq_str[MLX5E_REPORTER_PER_Q_MAX_LEN] = {}; char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN]; struct mlx5e_icosq *icosq = rq->icosq; struct mlx5e_priv *priv = rq->priv; struct mlx5e_err_ctx err_ctx = {}; + char icosq_str[32] = {}; err_ctx.ctx = rq; err_ctx.recover = mlx5e_rx_reporter_timeout_recover; @@ -505,7 +505,7 @@ void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq) if (icosq) snprintf(icosq_str, sizeof(icosq_str), "ICOSQ: 0x%x, ", icosq->sqn); snprintf(err_str, sizeof(err_str), - "RX timeout on channel: %d, %sRQ: 0x%x, CQ: 0x%x", + "RX timeout on channel: %d, %s RQ: 0x%x, CQ: 0x%x", rq->ix, icosq_str, rq->rqn, rq->cq.mcq.cqn); mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c index f63402c48028..1b418095b79a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c @@ -197,7 +197,7 @@ parse_mirred_encap(struct mlx5e_tc_act_parse_state *parse_state, } esw_attr->dests[esw_attr->out_count].flags |= MLX5_ESW_DEST_ENCAP; esw_attr->out_count++; - /* attr->dests[].rep is resolved when we handle encap */ + /* attr->dests[].vport is resolved when we handle encap */ return 0; } @@ -270,7 +270,8 @@ parse_mirred(struct mlx5e_tc_act_parse_state *parse_state, out_priv = netdev_priv(out_dev); rpriv = out_priv->ppriv; - esw_attr->dests[esw_attr->out_count].rep = rpriv->rep; + esw_attr->dests[esw_attr->out_count].vport_valid = true; + esw_attr->dests[esw_attr->out_count].vport = rpriv->rep->vport; esw_attr->dests[esw_attr->out_count].mdev = out_priv->mdev; esw_attr->out_count++; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c index 368a95fa77d3..b14cd62edffc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c @@ -48,7 +48,8 @@ mlx5e_tc_act_pedit_parse_action(struct mlx5e_priv *priv, struct pedit_headers_action *hdrs, struct netlink_ext_ack *extack) { - u8 cmd = (act->id == FLOW_ACTION_MANGLE) ? 0 : 1; + u8 cmd = (act->id == FLOW_ACTION_MANGLE) ? TCA_PEDIT_KEY_EX_CMD_SET : + TCA_PEDIT_KEY_EX_CMD_ADD; u8 htype = act->mangle.htype; int err = -EOPNOTSUPP; u32 mask, val, offset; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c index 4e923a2874ae..b500cc2c9689 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c @@ -37,7 +37,7 @@ mlx5e_tc_post_act_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains, if (!MLX5_CAP_FLOWTABLE_TYPE(priv->mdev, ignore_flow_level, table_type)) { if (priv->mdev->coredev_type == MLX5_COREDEV_PF) - mlx5_core_warn(priv->mdev, "firmware level support is missing\n"); + mlx5_core_dbg(priv->mdev, "firmware flow level support is missing\n"); err = -EOPNOTSUPP; goto err_check; } @@ -83,6 +83,9 @@ mlx5e_tc_post_act_offload(struct mlx5e_post_act *post_act, struct mlx5_flow_spec *spec; int err; + if (IS_ERR(post_act)) + return PTR_ERR(post_act); + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); if (!spec) return -ENOMEM; @@ -111,6 +114,9 @@ mlx5e_tc_post_act_add(struct mlx5e_post_act *post_act, struct mlx5_flow_attr *po struct mlx5e_post_act_handle *handle; int err; + if (IS_ERR(post_act)) + return ERR_CAST(post_act); + handle = kzalloc(sizeof(*handle), GFP_KERNEL); if (!handle) return ERR_PTR(-ENOMEM); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 00a04fdd756f..8dfb57f712b0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -302,6 +302,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, e->encap_size = ipv4_encap_size; e->encap_header = encap_header; + encap_header = NULL; if (!(nud_state & NUD_VALID)) { neigh_event_send(attr.n, NULL); @@ -313,8 +314,8 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, memset(&reformat_params, 0, sizeof(reformat_params)); reformat_params.type = e->reformat_type; - reformat_params.size = ipv4_encap_size; - reformat_params.data = encap_header; + reformat_params.size = e->encap_size; + reformat_params.data = e->encap_header; e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params, MLX5_FLOW_NAMESPACE_FDB); if (IS_ERR(e->pkt_reformat)) { @@ -407,6 +408,7 @@ int mlx5e_tc_tun_update_header_ipv4(struct mlx5e_priv *priv, e->encap_size = ipv4_encap_size; kfree(e->encap_header); e->encap_header = encap_header; + encap_header = NULL; if (!(nud_state & NUD_VALID)) { neigh_event_send(attr.n, NULL); @@ -418,8 +420,8 @@ int mlx5e_tc_tun_update_header_ipv4(struct mlx5e_priv *priv, memset(&reformat_params, 0, sizeof(reformat_params)); reformat_params.type = e->reformat_type; - reformat_params.size = ipv4_encap_size; - reformat_params.data = encap_header; + reformat_params.size = e->encap_size; + reformat_params.data = e->encap_header; e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params, MLX5_FLOW_NAMESPACE_FDB); if (IS_ERR(e->pkt_reformat)) { @@ -570,6 +572,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, e->encap_size = ipv6_encap_size; e->encap_header = encap_header; + encap_header = NULL; if (!(nud_state & NUD_VALID)) { neigh_event_send(attr.n, NULL); @@ -581,8 +584,8 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, memset(&reformat_params, 0, sizeof(reformat_params)); reformat_params.type = e->reformat_type; - reformat_params.size = ipv6_encap_size; - reformat_params.data = encap_header; + reformat_params.size = e->encap_size; + reformat_params.data = e->encap_header; e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params, MLX5_FLOW_NAMESPACE_FDB); if (IS_ERR(e->pkt_reformat)) { @@ -674,6 +677,7 @@ int mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv, e->encap_size = ipv6_encap_size; kfree(e->encap_header); e->encap_header = encap_header; + encap_header = NULL; if (!(nud_state & NUD_VALID)) { neigh_event_send(attr.n, NULL); @@ -685,8 +689,8 @@ int mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv, memset(&reformat_params, 0, sizeof(reformat_params)); reformat_params.type = e->reformat_type; - reformat_params.size = ipv6_encap_size; - reformat_params.data = encap_header; + reformat_params.size = e->encap_size; + reformat_params.data = e->encap_header; e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params, MLX5_FLOW_NAMESPACE_FDB); if (IS_ERR(e->pkt_reformat)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index b10e40e1a9c1..f1d1e1542e81 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -1064,7 +1064,8 @@ int mlx5e_tc_tun_encap_dests_set(struct mlx5e_priv *priv, out_priv = netdev_priv(encap_dev); rpriv = out_priv->ppriv; - esw_attr->dests[out_index].rep = rpriv->rep; + esw_attr->dests[out_index].vport_valid = true; + esw_attr->dests[out_index].vport = rpriv->rep->vport; esw_attr->dests[out_index].mdev = out_priv->mdev; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c index 5620d9f97518..ac458a8d10e0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c @@ -68,11 +68,13 @@ static int mlx5e_open_trap_rq(struct mlx5e_priv *priv, struct mlx5e_trap *t) node = dev_to_node(mdev->device); + ccp.netdev = priv->netdev; + ccp.wq = priv->wq; ccp.node = node; ccp.ch_stats = t->stats; ccp.napi = &t->napi; ccp.ix = 0; - err = mlx5e_open_cq(priv, trap_moder, &rq_param->cqp, &ccp, &rq->cq); + err = mlx5e_open_cq(priv->mdev, trap_moder, &rq_param->cqp, &ccp, &rq->cq); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 7decc81ed33a..82b5ca1be4f3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -103,7 +103,7 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq, xdptxd->dma_addr = dma_addr; if (unlikely(!INDIRECT_CALL_2(sq->xmit_xdp_frame, mlx5e_xmit_xdp_frame_mpwqe, - mlx5e_xmit_xdp_frame, sq, xdptxd, 0))) + mlx5e_xmit_xdp_frame, sq, xdptxd, 0, NULL))) return false; /* xmit_mode == MLX5E_XDP_XMIT_MODE_FRAME */ @@ -145,7 +145,7 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq, xdptxd->dma_addr = dma_addr; if (unlikely(!INDIRECT_CALL_2(sq->xmit_xdp_frame, mlx5e_xmit_xdp_frame_mpwqe, - mlx5e_xmit_xdp_frame, sq, xdptxd, 0))) + mlx5e_xmit_xdp_frame, sq, xdptxd, 0, NULL))) return false; /* xmit_mode == MLX5E_XDP_XMIT_MODE_PAGE */ @@ -256,9 +256,55 @@ static int mlx5e_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, return 0; } +static int mlx5e_xdp_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto, + u16 *vlan_tci) +{ + const struct mlx5e_xdp_buff *_ctx = (void *)ctx; + const struct mlx5_cqe64 *cqe = _ctx->cqe; + + if (!cqe_has_vlan(cqe)) + return -ENODATA; + + *vlan_proto = htons(ETH_P_8021Q); + *vlan_tci = be16_to_cpu(cqe->vlan_info); + return 0; +} + const struct xdp_metadata_ops mlx5e_xdp_metadata_ops = { .xmo_rx_timestamp = mlx5e_xdp_rx_timestamp, .xmo_rx_hash = mlx5e_xdp_rx_hash, + .xmo_rx_vlan_tag = mlx5e_xdp_rx_vlan_tag, +}; + +struct mlx5e_xsk_tx_complete { + struct mlx5_cqe64 *cqe; + struct mlx5e_cq *cq; +}; + +static u64 mlx5e_xsk_fill_timestamp(void *_priv) +{ + struct mlx5e_xsk_tx_complete *priv = _priv; + u64 ts; + + ts = get_cqe_ts(priv->cqe); + + if (mlx5_is_real_time_rq(priv->cq->mdev) || mlx5_is_real_time_sq(priv->cq->mdev)) + return mlx5_real_time_cyc2time(&priv->cq->mdev->clock, ts); + + return mlx5_timecounter_cyc2time(&priv->cq->mdev->clock, ts); +} + +static void mlx5e_xsk_request_checksum(u16 csum_start, u16 csum_offset, void *priv) +{ + struct mlx5_wqe_eth_seg *eseg = priv; + + /* HW/FW is doing parsing, so offsets are largely ignored. */ + eseg->cs_flags |= MLX5_ETH_WQE_L3_CSUM | MLX5_ETH_WQE_L4_CSUM; +} + +const struct xsk_tx_metadata_ops mlx5e_xsk_tx_metadata_ops = { + .tmo_fill_timestamp = mlx5e_xsk_fill_timestamp, + .tmo_request_checksum = mlx5e_xsk_request_checksum, }; /* returns true if packet was consumed by xdp */ @@ -398,11 +444,11 @@ INDIRECT_CALLABLE_SCOPE int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq INDIRECT_CALLABLE_SCOPE bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, - int check_result); + int check_result, struct xsk_tx_metadata *meta); INDIRECT_CALLABLE_SCOPE bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, - int check_result) + int check_result, struct xsk_tx_metadata *meta) { struct mlx5e_tx_mpwqe *session = &sq->mpwqe; struct mlx5e_xdpsq_stats *stats = sq->stats; @@ -420,7 +466,7 @@ mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptx */ if (unlikely(sq->mpwqe.wqe)) mlx5e_xdp_mpwqe_complete(sq); - return mlx5e_xmit_xdp_frame(sq, xdptxd, 0); + return mlx5e_xmit_xdp_frame(sq, xdptxd, 0, meta); } if (!xdptxd->len) { skb_frag_t *frag = &xdptxdf->sinfo->frags[0]; @@ -450,6 +496,7 @@ mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptx * and it's safe to complete it at any time. */ mlx5e_xdp_mpwqe_session_start(sq); + xsk_tx_metadata_request(meta, &mlx5e_xsk_tx_metadata_ops, &session->wqe->eth); } mlx5e_xdp_mpwqe_add_dseg(sq, p, stats); @@ -480,7 +527,7 @@ INDIRECT_CALLABLE_SCOPE int mlx5e_xmit_xdp_frame_check(struct mlx5e_xdpsq *sq) INDIRECT_CALLABLE_SCOPE bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, - int check_result) + int check_result, struct xsk_tx_metadata *meta) { struct mlx5e_xmit_data_frags *xdptxdf = container_of(xdptxd, struct mlx5e_xmit_data_frags, xd); @@ -493,6 +540,7 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, dma_addr_t dma_addr = xdptxd->dma_addr; u32 dma_len = xdptxd->len; u16 ds_cnt, inline_hdr_sz; + unsigned int frags_size; u8 num_wqebbs = 1; int num_frags = 0; bool inline_ok; @@ -503,8 +551,9 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, inline_ok = sq->min_inline_mode == MLX5_INLINE_MODE_NONE || dma_len >= MLX5E_XDP_MIN_INLINE; + frags_size = xdptxd->has_frags ? xdptxdf->sinfo->xdp_frags_size : 0; - if (unlikely(!inline_ok || sq->hw_mtu < dma_len)) { + if (unlikely(!inline_ok || sq->hw_mtu < dma_len + frags_size)) { stats->err++; return false; } @@ -599,6 +648,8 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, sq->pc++; } + xsk_tx_metadata_request(meta, &mlx5e_xsk_tx_metadata_ops, eseg); + sq->doorbell_cseg = cseg; stats->xmit++; @@ -608,7 +659,9 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_wqe_info *wi, u32 *xsk_frames, - struct xdp_frame_bulk *bq) + struct xdp_frame_bulk *bq, + struct mlx5e_cq *cq, + struct mlx5_cqe64 *cqe) { struct mlx5e_xdp_info_fifo *xdpi_fifo = &sq->db.xdpi_fifo; u16 i; @@ -668,10 +721,24 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq, break; } - case MLX5E_XDP_XMIT_MODE_XSK: + case MLX5E_XDP_XMIT_MODE_XSK: { /* AF_XDP send */ + struct xsk_tx_metadata_compl *compl = NULL; + struct mlx5e_xsk_tx_complete priv = { + .cqe = cqe, + .cq = cq, + }; + + if (xp_tx_metadata_enabled(sq->xsk_pool)) { + xdpi = mlx5e_xdpi_fifo_pop(xdpi_fifo); + compl = &xdpi.xsk_meta; + + xsk_tx_metadata_complete(compl, &mlx5e_xsk_tx_metadata_ops, &priv); + } + (*xsk_frames)++; break; + } default: WARN_ON_ONCE(true); } @@ -720,7 +787,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) sqcc += wi->num_wqebbs; - mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, &bq); + mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, &bq, cq, cqe); } while (!last_wqe); if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) { @@ -767,7 +834,7 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq) sq->cc += wi->num_wqebbs; - mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, &bq); + mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, &bq, NULL, NULL); } xdp_flush_frame_bulk(&bq); @@ -840,7 +907,7 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, } ret = INDIRECT_CALL_2(sq->xmit_xdp_frame, mlx5e_xmit_xdp_frame_mpwqe, - mlx5e_xmit_xdp_frame, sq, xdptxd, 0); + mlx5e_xmit_xdp_frame, sq, xdptxd, 0, NULL); if (unlikely(!ret)) { int j; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h index ecfe93a479da..e054db1e10f8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h @@ -33,6 +33,7 @@ #define __MLX5_EN_XDP_H__ #include <linux/indirect_call_wrapper.h> +#include <net/xdp_sock.h> #include "en.h" #include "en/txrx.h" @@ -82,7 +83,7 @@ enum mlx5e_xdp_xmit_mode { * num, page_1, page_2, ... , page_num. * * MLX5E_XDP_XMIT_MODE_XSK: - * none. + * frame.xsk_meta. */ #define MLX5E_XDP_FIFO_ENTRIES2DS_MAX_RATIO 4 @@ -97,6 +98,7 @@ union mlx5e_xdp_info { u8 num; struct page *page; } page; + struct xsk_tx_metadata_compl xsk_meta; }; struct mlx5e_xsk_param; @@ -112,13 +114,16 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags); extern const struct xdp_metadata_ops mlx5e_xdp_metadata_ops; +extern const struct xsk_tx_metadata_ops mlx5e_xsk_tx_metadata_ops; INDIRECT_CALLABLE_DECLARE(bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, - int check_result)); + int check_result, + struct xsk_tx_metadata *meta)); INDIRECT_CALLABLE_DECLARE(bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, - int check_result)); + int check_result, + struct xsk_tx_metadata *meta)); INDIRECT_CALLABLE_DECLARE(int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq)); INDIRECT_CALLABLE_DECLARE(int mlx5e_xmit_xdp_frame_check(struct mlx5e_xdpsq *sq)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index 36826b582484..82e6abbc1734 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -127,7 +127,7 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, mlx5e_build_xsk_cparam(priv->mdev, params, xsk, priv->q_counter, cparam); - err = mlx5e_open_cq(c->priv, params->rx_cq_moderation, &cparam->rq.cqp, &ccp, + err = mlx5e_open_cq(c->mdev, params->rx_cq_moderation, &cparam->rq.cqp, &ccp, &c->xskrq.cq); if (unlikely(err)) goto err_free_cparam; @@ -136,7 +136,7 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, if (unlikely(err)) goto err_close_rx_cq; - err = mlx5e_open_cq(c->priv, params->tx_cq_moderation, &cparam->xdp_sq.cqp, &ccp, + err = mlx5e_open_cq(c->mdev, params->tx_cq_moderation, &cparam->xdp_sq.cqp, &ccp, &c->xsksq.cq); if (unlikely(err)) goto err_close_rq; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c index 597f319d4770..a59199ed590d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c @@ -55,12 +55,16 @@ static void mlx5e_xsk_tx_post_err(struct mlx5e_xdpsq *sq, nopwqe = mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc); mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, *xdpi); + if (xp_tx_metadata_enabled(sq->xsk_pool)) + mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, + (union mlx5e_xdp_info) { .xsk_meta = {} }); sq->doorbell_cseg = &nopwqe->ctrl; } bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget) { struct xsk_buff_pool *pool = sq->xsk_pool; + struct xsk_tx_metadata *meta = NULL; union mlx5e_xdp_info xdpi; bool work_done = true; bool flush = false; @@ -93,12 +97,13 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget) xdptxd.dma_addr = xsk_buff_raw_get_dma(pool, desc.addr); xdptxd.data = xsk_buff_raw_get_data(pool, desc.addr); xdptxd.len = desc.len; + meta = xsk_buff_get_metadata(pool, desc.addr); xsk_buff_raw_dma_sync_for_device(pool, xdptxd.dma_addr, xdptxd.len); ret = INDIRECT_CALL_2(sq->xmit_xdp_frame, mlx5e_xmit_xdp_frame_mpwqe, mlx5e_xmit_xdp_frame, sq, &xdptxd, - check_result); + check_result, meta); if (unlikely(!ret)) { if (sq->mpwqe.wqe) mlx5e_xdp_mpwqe_complete(sq); @@ -106,6 +111,16 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget) mlx5e_xsk_tx_post_err(sq, &xdpi); } else { mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, xdpi); + if (xp_tx_metadata_enabled(sq->xsk_pool)) { + struct xsk_tx_metadata_compl compl; + + xsk_tx_metadata_to_compl(meta, &compl); + XSK_TX_COMPL_FITS(void *); + + mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, + (union mlx5e_xdp_info) + { .xsk_meta = compl }); + } } flush = true; 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 655496598c68..c54fd01ea635 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -121,7 +121,14 @@ static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry) if (x->xso.type == XFRM_DEV_OFFLOAD_CRYPTO) esn_msb = xfrm_replay_seqhi(x, htonl(seq_bottom)); - sa_entry->esn_state.esn = esn; + if (sa_entry->esn_state.esn_msb) + sa_entry->esn_state.esn = esn; + else + /* According to RFC4303, section "3.3.3. Sequence Number Generation", + * the first packet sent using a given SA will contain a sequence + * number of 1. + */ + sa_entry->esn_state.esn = max_t(u32, esn, 1); sa_entry->esn_state.esn_msb = esn_msb; if (unlikely(overlap && seq_bottom < MLX5E_IPSEC_ESN_SCOPE_MID)) { @@ -329,15 +336,41 @@ void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry, /* iv len */ aes_gcm->icv_len = x->aead->alg_icv_len; + attrs->dir = x->xso.dir; + /* esn */ if (x->props.flags & XFRM_STATE_ESN) { attrs->replay_esn.trigger = true; attrs->replay_esn.esn = sa_entry->esn_state.esn; attrs->replay_esn.esn_msb = sa_entry->esn_state.esn_msb; attrs->replay_esn.overlap = sa_entry->esn_state.overlap; + if (attrs->dir == XFRM_DEV_OFFLOAD_OUT) + goto skip_replay_window; + + switch (x->replay_esn->replay_window) { + case 32: + attrs->replay_esn.replay_window = + MLX5_IPSEC_ASO_REPLAY_WIN_32BIT; + break; + case 64: + attrs->replay_esn.replay_window = + MLX5_IPSEC_ASO_REPLAY_WIN_64BIT; + break; + case 128: + attrs->replay_esn.replay_window = + MLX5_IPSEC_ASO_REPLAY_WIN_128BIT; + break; + case 256: + attrs->replay_esn.replay_window = + MLX5_IPSEC_ASO_REPLAY_WIN_256BIT; + break; + default: + WARN_ON(true); + return; + } } - attrs->dir = x->xso.dir; +skip_replay_window: /* spi */ attrs->spi = be32_to_cpu(x->id.spi); @@ -473,7 +506,8 @@ static int mlx5e_xfrm_validate_state(struct mlx5_core_dev *mdev, return -EINVAL; } - if (x->replay_esn && x->replay_esn->replay_window != 32 && + if (x->replay_esn && x->xso.dir == XFRM_DEV_OFFLOAD_IN && + x->replay_esn->replay_window != 32 && x->replay_esn->replay_window != 64 && x->replay_esn->replay_window != 128 && x->replay_esn->replay_window != 256) { @@ -907,9 +941,11 @@ void mlx5e_ipsec_cleanup(struct mlx5e_priv *priv) return; mlx5e_accel_ipsec_fs_cleanup(ipsec); - if (mlx5_ipsec_device_caps(priv->mdev) & MLX5_IPSEC_CAP_TUNNEL) + if (ipsec->netevent_nb.notifier_call) { unregister_netevent_notifier(&ipsec->netevent_nb); - if (mlx5_ipsec_device_caps(priv->mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD) + ipsec->netevent_nb.notifier_call = NULL; + } + if (ipsec->aso) mlx5e_ipsec_aso_cleanup(ipsec); destroy_workqueue(ipsec->wq); kfree(ipsec); @@ -948,21 +984,41 @@ static void mlx5e_xfrm_advance_esn_state(struct xfrm_state *x) queue_work(sa_entry->ipsec->wq, &work->work); } -static void mlx5e_xfrm_update_curlft(struct xfrm_state *x) +static void mlx5e_xfrm_update_stats(struct xfrm_state *x) { struct mlx5e_ipsec_sa_entry *sa_entry = to_ipsec_sa_entry(x); struct mlx5e_ipsec_rule *ipsec_rule = &sa_entry->ipsec_rule; + struct net *net = dev_net(x->xso.dev); u64 packets, bytes, lastuse; lockdep_assert(lockdep_is_held(&x->lock) || - lockdep_is_held(&dev_net(x->xso.real_dev)->xfrm.xfrm_cfg_mutex)); + lockdep_is_held(&dev_net(x->xso.real_dev)->xfrm.xfrm_cfg_mutex) || + lockdep_is_held(&dev_net(x->xso.real_dev)->xfrm.xfrm_state_lock)); if (x->xso.flags & XFRM_DEV_OFFLOAD_FLAG_ACQ) return; + if (sa_entry->attrs.dir == XFRM_DEV_OFFLOAD_IN) { + mlx5_fc_query_cached(ipsec_rule->auth.fc, &bytes, &packets, &lastuse); + x->stats.integrity_failed += packets; + XFRM_ADD_STATS(net, LINUX_MIB_XFRMINSTATEPROTOERROR, packets); + + mlx5_fc_query_cached(ipsec_rule->trailer.fc, &bytes, &packets, &lastuse); + XFRM_ADD_STATS(net, LINUX_MIB_XFRMINHDRERROR, packets); + } + + if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) + return; + mlx5_fc_query_cached(ipsec_rule->fc, &bytes, &packets, &lastuse); x->curlft.packets += packets; x->curlft.bytes += bytes; + + if (sa_entry->attrs.dir == XFRM_DEV_OFFLOAD_IN) { + mlx5_fc_query_cached(ipsec_rule->replay.fc, &bytes, &packets, &lastuse); + x->stats.replay += packets; + XFRM_ADD_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR, packets); + } } static int mlx5e_xfrm_validate_policy(struct mlx5_core_dev *mdev, @@ -1018,6 +1074,12 @@ static int mlx5e_xfrm_validate_policy(struct mlx5_core_dev *mdev, } } + if (x->xdo.type == XFRM_DEV_OFFLOAD_PACKET && + !(mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD)) { + NL_SET_ERR_MSG_MOD(extack, "Packet offload is not supported"); + return -EINVAL; + } + return 0; } @@ -1113,16 +1175,8 @@ static const struct xfrmdev_ops mlx5e_ipsec_xfrmdev_ops = { .xdo_dev_state_free = mlx5e_xfrm_free_state, .xdo_dev_offload_ok = mlx5e_ipsec_offload_ok, .xdo_dev_state_advance_esn = mlx5e_xfrm_advance_esn_state, -}; -static const struct xfrmdev_ops mlx5e_ipsec_packet_xfrmdev_ops = { - .xdo_dev_state_add = mlx5e_xfrm_add_state, - .xdo_dev_state_delete = mlx5e_xfrm_del_state, - .xdo_dev_state_free = mlx5e_xfrm_free_state, - .xdo_dev_offload_ok = mlx5e_ipsec_offload_ok, - .xdo_dev_state_advance_esn = mlx5e_xfrm_advance_esn_state, - - .xdo_dev_state_update_curlft = mlx5e_xfrm_update_curlft, + .xdo_dev_state_update_stats = mlx5e_xfrm_update_stats, .xdo_dev_policy_add = mlx5e_xfrm_add_policy, .xdo_dev_policy_delete = mlx5e_xfrm_del_policy, .xdo_dev_policy_free = mlx5e_xfrm_free_policy, @@ -1138,11 +1192,7 @@ void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv) mlx5_core_info(mdev, "mlx5e: IPSec ESP acceleration enabled\n"); - if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD) - netdev->xfrmdev_ops = &mlx5e_ipsec_packet_xfrmdev_ops; - else - netdev->xfrmdev_ops = &mlx5e_ipsec_xfrmdev_ops; - + netdev->xfrmdev_ops = &mlx5e_ipsec_xfrmdev_ops; netdev->features |= NETIF_F_HW_ESP; netdev->hw_enc_features |= NETIF_F_HW_ESP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h index 8f4a37bceaf4..7d943e93cf6d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h @@ -137,7 +137,6 @@ struct mlx5e_ipsec_hw_stats { struct mlx5e_ipsec_sw_stats { atomic64_t ipsec_rx_drop_sp_alloc; atomic64_t ipsec_rx_drop_sadb_miss; - atomic64_t ipsec_rx_drop_syndrome; atomic64_t ipsec_tx_drop_bundle; atomic64_t ipsec_tx_drop_no_state; atomic64_t ipsec_tx_drop_not_ip; @@ -189,11 +188,19 @@ struct mlx5e_ipsec_ft { u32 refcnt; }; +struct mlx5e_ipsec_drop { + struct mlx5_flow_handle *rule; + struct mlx5_fc *fc; +}; + struct mlx5e_ipsec_rule { struct mlx5_flow_handle *rule; struct mlx5_modify_hdr *modify_hdr; struct mlx5_pkt_reformat *pkt_reformat; struct mlx5_fc *fc; + struct mlx5e_ipsec_drop replay; + struct mlx5e_ipsec_drop auth; + struct mlx5e_ipsec_drop trailer; }; struct mlx5e_ipsec_miss { @@ -201,19 +208,6 @@ struct mlx5e_ipsec_miss { struct mlx5_flow_handle *rule; }; -struct mlx5e_ipsec_rx { - struct mlx5e_ipsec_ft ft; - struct mlx5e_ipsec_miss pol; - struct mlx5e_ipsec_miss sa; - struct mlx5e_ipsec_rule status; - struct mlx5e_ipsec_miss status_drop; - struct mlx5_fc *status_drop_cnt; - struct mlx5e_ipsec_fc *fc; - struct mlx5_fs_chains *chains; - u8 allow_tunnel_mode : 1; - struct xarray ipsec_obj_id_map; -}; - struct mlx5e_ipsec_tx_create_attr { int prio; int pol_level; @@ -248,6 +242,7 @@ struct mlx5e_ipsec { struct mlx5_ipsec_fs *roce; u8 is_uplink_rep: 1; struct mlx5e_ipsec_mpv_work mpv_work; + struct xarray ipsec_obj_id_map; }; struct mlx5e_ipsec_esn_state { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index f41c976dc33f..41a2543a52cd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -32,6 +32,22 @@ struct mlx5e_ipsec_tx { u8 allow_tunnel_mode : 1; }; +struct mlx5e_ipsec_status_checks { + struct mlx5_flow_group *drop_all_group; + struct mlx5e_ipsec_drop all; +}; + +struct mlx5e_ipsec_rx { + struct mlx5e_ipsec_ft ft; + struct mlx5e_ipsec_miss pol; + struct mlx5e_ipsec_miss sa; + struct mlx5e_ipsec_rule status; + struct mlx5e_ipsec_status_checks status_drops; + struct mlx5e_ipsec_fc *fc; + struct mlx5_fs_chains *chains; + u8 allow_tunnel_mode : 1; +}; + /* IPsec RX flow steering */ static enum mlx5_traffic_types family2tt(u32 family) { @@ -128,14 +144,37 @@ static struct mlx5_flow_table *ipsec_ft_create(struct mlx5_flow_namespace *ns, return mlx5_create_auto_grouped_flow_table(ns, &ft_attr); } -static int ipsec_status_rule(struct mlx5_core_dev *mdev, - struct mlx5e_ipsec_rx *rx, - struct mlx5_flow_destination *dest) +static void ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx) +{ + mlx5_del_flow_rules(rx->status_drops.all.rule); + mlx5_fc_destroy(ipsec->mdev, rx->status_drops.all.fc); + mlx5_destroy_flow_group(rx->status_drops.drop_all_group); +} + +static void ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx) { - u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {}; + mlx5_del_flow_rules(rx->status.rule); + + if (rx != ipsec->rx_esw) + return; + +#ifdef CONFIG_MLX5_ESWITCH + mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch), 0, 1, 0); +#endif +} + +static int rx_add_rule_drop_auth_trailer(struct mlx5e_ipsec_sa_entry *sa_entry, + struct mlx5e_ipsec_rx *rx) +{ + struct mlx5e_ipsec *ipsec = sa_entry->ipsec; + struct mlx5_flow_table *ft = rx->ft.status; + struct mlx5_core_dev *mdev = ipsec->mdev; + struct mlx5_flow_destination dest = {}; struct mlx5_flow_act flow_act = {}; - struct mlx5_modify_hdr *modify_hdr; - struct mlx5_flow_handle *fte; + struct mlx5_flow_handle *rule; + struct mlx5_fc *flow_counter; struct mlx5_flow_spec *spec; int err; @@ -143,48 +182,273 @@ static int ipsec_status_rule(struct mlx5_core_dev *mdev, if (!spec) return -ENOMEM; - /* Action to copy 7 bit ipsec_syndrome to regB[24:30] */ - MLX5_SET(copy_action_in, action, action_type, MLX5_ACTION_TYPE_COPY); - MLX5_SET(copy_action_in, action, src_field, MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME); - MLX5_SET(copy_action_in, action, src_offset, 0); - MLX5_SET(copy_action_in, action, length, 7); - MLX5_SET(copy_action_in, action, dst_field, MLX5_ACTION_IN_FIELD_METADATA_REG_B); - MLX5_SET(copy_action_in, action, dst_offset, 24); + flow_counter = mlx5_fc_create(mdev, true); + if (IS_ERR(flow_counter)) { + err = PTR_ERR(flow_counter); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule counter, err=%d\n", err); + goto err_cnt; + } + sa_entry->ipsec_rule.auth.fc = flow_counter; - modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_KERNEL, - 1, action); + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; + flow_act.flags = FLOW_ACT_NO_APPEND; + dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dest.counter_id = mlx5_fc_id(flow_counter); + if (rx == ipsec->rx_esw) + spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; - if (IS_ERR(modify_hdr)) { - err = PTR_ERR(modify_hdr); + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.ipsec_syndrome); + MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.ipsec_syndrome, 1); + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_2); + MLX5_SET(fte_match_param, spec->match_value, + misc_parameters_2.metadata_reg_c_2, + sa_entry->ipsec_obj_id | BIT(31)); + spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2; + rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); mlx5_core_err(mdev, - "fail to alloc ipsec copy modify_header_id err=%d\n", err); - goto out_spec; + "Failed to add ipsec rx status drop rule, err=%d\n", err); + goto err_rule; } + sa_entry->ipsec_rule.auth.rule = rule; - /* create fte */ - flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | - MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + flow_counter = mlx5_fc_create(mdev, true); + if (IS_ERR(flow_counter)) { + err = PTR_ERR(flow_counter); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule counter, err=%d\n", err); + goto err_cnt_2; + } + sa_entry->ipsec_rule.trailer.fc = flow_counter; + + dest.counter_id = mlx5_fc_id(flow_counter); + MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.ipsec_syndrome, 2); + rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule, err=%d\n", err); + goto err_rule_2; + } + sa_entry->ipsec_rule.trailer.rule = rule; + + kvfree(spec); + return 0; + +err_rule_2: + mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.trailer.fc); +err_cnt_2: + mlx5_del_flow_rules(sa_entry->ipsec_rule.auth.rule); +err_rule: + mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.auth.fc); +err_cnt: + kvfree(spec); + return err; +} + +static int rx_add_rule_drop_replay(struct mlx5e_ipsec_sa_entry *sa_entry, struct mlx5e_ipsec_rx *rx) +{ + struct mlx5e_ipsec *ipsec = sa_entry->ipsec; + struct mlx5_flow_table *ft = rx->ft.status; + struct mlx5_core_dev *mdev = ipsec->mdev; + struct mlx5_flow_destination dest = {}; + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *rule; + struct mlx5_fc *flow_counter; + struct mlx5_flow_spec *spec; + int err; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) + return -ENOMEM; + + flow_counter = mlx5_fc_create(mdev, true); + if (IS_ERR(flow_counter)) { + err = PTR_ERR(flow_counter); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule counter, err=%d\n", err); + goto err_cnt; + } + + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; + flow_act.flags = FLOW_ACT_NO_APPEND; + dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dest.counter_id = mlx5_fc_id(flow_counter); + if (rx == ipsec->rx_esw) + spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; + + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_4); + MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_c_4, 1); + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_2); + MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_c_2, + sa_entry->ipsec_obj_id | BIT(31)); + spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2; + rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule, err=%d\n", err); + goto err_rule; + } + + sa_entry->ipsec_rule.replay.rule = rule; + sa_entry->ipsec_rule.replay.fc = flow_counter; + + kvfree(spec); + return 0; + +err_rule: + mlx5_fc_destroy(mdev, flow_counter); +err_cnt: + kvfree(spec); + return err; +} + +static int ipsec_rx_status_drop_all_create(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_table *ft = rx->ft.status; + struct mlx5_core_dev *mdev = ipsec->mdev; + struct mlx5_flow_destination dest = {}; + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *rule; + struct mlx5_fc *flow_counter; + struct mlx5_flow_spec *spec; + struct mlx5_flow_group *g; + u32 *flow_group_in; + int err = 0; + + flow_group_in = kvzalloc(inlen, GFP_KERNEL); + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!flow_group_in || !spec) { + err = -ENOMEM; + goto err_out; + } + + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ft->max_fte - 1); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ft->max_fte - 1); + g = mlx5_create_flow_group(ft, flow_group_in); + if (IS_ERR(g)) { + err = PTR_ERR(g); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop flow group, err=%d\n", err); + goto err_out; + } + + flow_counter = mlx5_fc_create(mdev, false); + if (IS_ERR(flow_counter)) { + err = PTR_ERR(flow_counter); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule counter, err=%d\n", err); + goto err_cnt; + } + + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; + dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dest.counter_id = mlx5_fc_id(flow_counter); + if (rx == ipsec->rx_esw) + spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; + rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule, err=%d\n", err); + goto err_rule; + } + + rx->status_drops.drop_all_group = g; + rx->status_drops.all.rule = rule; + rx->status_drops.all.fc = flow_counter; + + kvfree(flow_group_in); + kvfree(spec); + return 0; + +err_rule: + mlx5_fc_destroy(mdev, flow_counter); +err_cnt: + mlx5_destroy_flow_group(g); +err_out: + kvfree(flow_group_in); + kvfree(spec); + return err; +} + +static int ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx, + struct mlx5_flow_destination *dest) +{ + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *rule; + struct mlx5_flow_spec *spec; + int err; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) + return -ENOMEM; + + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + misc_parameters_2.ipsec_syndrome); + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + misc_parameters_2.metadata_reg_c_4); + MLX5_SET(fte_match_param, spec->match_value, + misc_parameters_2.ipsec_syndrome, 0); + MLX5_SET(fte_match_param, spec->match_value, + misc_parameters_2.metadata_reg_c_4, 0); + if (rx == ipsec->rx_esw) + spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; + spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2; + flow_act.flags = FLOW_ACT_NO_APPEND; + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_COUNT; - flow_act.modify_hdr = modify_hdr; - fte = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2); - if (IS_ERR(fte)) { - err = PTR_ERR(fte); - mlx5_core_err(mdev, "fail to add ipsec rx err copy rule err=%d\n", err); - goto out; + rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + mlx5_core_warn(ipsec->mdev, + "Failed to add ipsec rx status pass rule, err=%d\n", err); + goto err_rule; } + rx->status.rule = rule; kvfree(spec); - rx->status.rule = fte; - rx->status.modify_hdr = modify_hdr; return 0; -out: - mlx5_modify_header_dealloc(mdev, modify_hdr); -out_spec: +err_rule: kvfree(spec); return err; } +static void mlx5_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx) +{ + ipsec_rx_status_pass_destroy(ipsec, rx); + ipsec_rx_status_drop_destroy(ipsec, rx); +} + +static int mlx5_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx, + struct mlx5_flow_destination *dest) +{ + int err; + + err = ipsec_rx_status_drop_all_create(ipsec, rx); + if (err) + return err; + + err = ipsec_rx_status_pass_create(ipsec, rx, dest); + if (err) + goto err_pass_create; + + return 0; + +err_pass_create: + ipsec_rx_status_drop_destroy(ipsec, rx); + return err; +} + static int ipsec_miss_create(struct mlx5_core_dev *mdev, struct mlx5_flow_table *ft, struct mlx5e_ipsec_miss *miss, @@ -333,12 +597,7 @@ static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec, mlx5_destroy_flow_table(rx->ft.sa); if (rx->allow_tunnel_mode) mlx5_eswitch_unblock_encap(mdev); - if (rx == ipsec->rx_esw) { - mlx5_esw_ipsec_rx_status_destroy(ipsec, rx); - } else { - mlx5_del_flow_rules(rx->status.rule); - mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr); - } + mlx5_ipsec_rx_status_destroy(ipsec, rx); mlx5_destroy_flow_table(rx->ft.status); mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family, mdev); @@ -419,7 +678,7 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec, if (err) return err; - ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 1, 0); + ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 3, 0); if (IS_ERR(ft)) { err = PTR_ERR(ft); goto err_fs_ft_status; @@ -428,10 +687,7 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec, dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; dest[1].counter_id = mlx5_fc_id(rx->fc->cnt); - if (rx == ipsec->rx_esw) - err = mlx5_esw_ipsec_rx_status_create(ipsec, rx, dest); - else - err = ipsec_status_rule(mdev, rx, dest); + err = mlx5_ipsec_rx_status_create(ipsec, rx, dest); if (err) goto err_add; @@ -956,13 +1212,22 @@ static void setup_fte_esp(struct mlx5_flow_spec *spec) MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_protocol, IPPROTO_ESP); } -static void setup_fte_spi(struct mlx5_flow_spec *spec, u32 spi) +static void setup_fte_spi(struct mlx5_flow_spec *spec, u32 spi, bool encap) { /* SPI number */ spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters.outer_esp_spi); - MLX5_SET(fte_match_param, spec->match_value, misc_parameters.outer_esp_spi, spi); + if (encap) { + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + misc_parameters.inner_esp_spi); + MLX5_SET(fte_match_param, spec->match_value, + misc_parameters.inner_esp_spi, spi); + } else { + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + misc_parameters.outer_esp_spi); + MLX5_SET(fte_match_param, spec->match_value, + misc_parameters.outer_esp_spi, spi); + } } static void setup_fte_no_frags(struct mlx5_flow_spec *spec) @@ -1052,29 +1317,48 @@ static int setup_modify_header(struct mlx5e_ipsec *ipsec, int type, u32 val, u8 struct mlx5_flow_act *flow_act) { enum mlx5_flow_namespace_type ns_type = ipsec_fs_get_ns(ipsec, type, dir); - u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {}; + u8 action[3][MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {}; struct mlx5_core_dev *mdev = ipsec->mdev; struct mlx5_modify_hdr *modify_hdr; + u8 num_of_actions = 1; - MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET); + MLX5_SET(set_action_in, action[0], action_type, MLX5_ACTION_TYPE_SET); switch (dir) { case XFRM_DEV_OFFLOAD_IN: - MLX5_SET(set_action_in, action, field, + MLX5_SET(set_action_in, action[0], field, MLX5_ACTION_IN_FIELD_METADATA_REG_B); + + num_of_actions++; + MLX5_SET(set_action_in, action[1], action_type, MLX5_ACTION_TYPE_SET); + MLX5_SET(set_action_in, action[1], field, MLX5_ACTION_IN_FIELD_METADATA_REG_C_2); + MLX5_SET(set_action_in, action[1], data, val); + MLX5_SET(set_action_in, action[1], offset, 0); + MLX5_SET(set_action_in, action[1], length, 32); + + if (type == XFRM_DEV_OFFLOAD_CRYPTO) { + num_of_actions++; + MLX5_SET(set_action_in, action[2], action_type, + MLX5_ACTION_TYPE_SET); + MLX5_SET(set_action_in, action[2], field, + MLX5_ACTION_IN_FIELD_METADATA_REG_C_4); + MLX5_SET(set_action_in, action[2], data, 0); + MLX5_SET(set_action_in, action[2], offset, 0); + MLX5_SET(set_action_in, action[2], length, 32); + } break; case XFRM_DEV_OFFLOAD_OUT: - MLX5_SET(set_action_in, action, field, + MLX5_SET(set_action_in, action[0], field, MLX5_ACTION_IN_FIELD_METADATA_REG_C_4); break; default: return -EINVAL; } - MLX5_SET(set_action_in, action, data, val); - MLX5_SET(set_action_in, action, offset, 0); - MLX5_SET(set_action_in, action, length, 32); + MLX5_SET(set_action_in, action[0], data, val); + MLX5_SET(set_action_in, action[0], offset, 0); + MLX5_SET(set_action_in, action[0], length, 32); - modify_hdr = mlx5_modify_header_alloc(mdev, ns_type, 1, action); + modify_hdr = mlx5_modify_header_alloc(mdev, ns_type, num_of_actions, action); if (IS_ERR(modify_hdr)) { mlx5_core_err(mdev, "Failed to allocate modify_header %ld\n", PTR_ERR(modify_hdr)); @@ -1321,8 +1605,9 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) else setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6); - setup_fte_spi(spec, attrs->spi); - setup_fte_esp(spec); + setup_fte_spi(spec, attrs->spi, attrs->encap); + if (!attrs->encap) + setup_fte_esp(spec); setup_fte_no_frags(spec); setup_fte_upper_proto_match(spec, &attrs->upspec); @@ -1372,6 +1657,15 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) mlx5_core_err(mdev, "fail to add RX ipsec rule err=%d\n", err); goto err_add_flow; } + if (attrs->type == XFRM_DEV_OFFLOAD_PACKET) + err = rx_add_rule_drop_replay(sa_entry, rx); + if (err) + goto err_add_replay; + + err = rx_add_rule_drop_auth_trailer(sa_entry, rx); + if (err) + goto err_drop_reason; + kvfree(spec); sa_entry->ipsec_rule.rule = rule; @@ -1380,6 +1674,13 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) sa_entry->ipsec_rule.pkt_reformat = flow_act.pkt_reformat; return 0; +err_drop_reason: + if (sa_entry->ipsec_rule.replay.rule) { + mlx5_del_flow_rules(sa_entry->ipsec_rule.replay.rule); + mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.replay.fc); + } +err_add_replay: + mlx5_del_flow_rules(rule); err_add_flow: mlx5_fc_destroy(mdev, counter); err_add_cnt: @@ -1428,7 +1729,7 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) switch (attrs->type) { case XFRM_DEV_OFFLOAD_CRYPTO: - setup_fte_spi(spec, attrs->spi); + setup_fte_spi(spec, attrs->spi, false); setup_fte_esp(spec); setup_fte_reg_a(spec); break; @@ -1809,8 +2110,11 @@ static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev) struct mlx5_eswitch *esw = mdev->priv.eswitch; int err = 0; - if (esw) - down_write(&esw->mode_lock); + if (esw) { + err = mlx5_esw_lock(esw); + if (err) + return err; + } if (mdev->num_block_ipsec) { err = -EBUSY; @@ -1821,7 +2125,7 @@ static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev) unlock: if (esw) - up_write(&esw->mode_lock); + mlx5_esw_unlock(esw); return err; } @@ -1838,7 +2142,7 @@ static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev) static void mlx5e_ipsec_unblock_tc_offload(struct mlx5_core_dev *mdev) { - mdev->num_block_tc++; + mdev->num_block_tc--; } int mlx5e_accel_ipsec_fs_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) @@ -1887,6 +2191,17 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry) if (ipsec_rule->modify_hdr) mlx5_modify_header_dealloc(mdev, ipsec_rule->modify_hdr); + + mlx5_del_flow_rules(ipsec_rule->trailer.rule); + mlx5_fc_destroy(mdev, ipsec_rule->trailer.fc); + + mlx5_del_flow_rules(ipsec_rule->auth.rule); + mlx5_fc_destroy(mdev, ipsec_rule->auth.fc); + + if (ipsec_rule->replay.rule) { + mlx5_del_flow_rules(ipsec_rule->replay.rule); + mlx5_fc_destroy(mdev, ipsec_rule->replay.fc); + } mlx5_esw_ipsec_rx_id_mapping_remove(sa_entry); rx_ft_put(sa_entry->ipsec, sa_entry->attrs.family, sa_entry->attrs.type); } @@ -1957,7 +2272,7 @@ void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_ipsec *ipsec) kfree(ipsec->rx_ipv6); if (ipsec->is_uplink_rep) { - xa_destroy(&ipsec->rx_esw->ipsec_obj_id_map); + xa_destroy(&ipsec->ipsec_obj_id_map); mutex_destroy(&ipsec->tx_esw->ft.mutex); WARN_ON(ipsec->tx_esw->ft.refcnt); @@ -2020,7 +2335,7 @@ int mlx5e_accel_ipsec_fs_init(struct mlx5e_ipsec *ipsec, mutex_init(&ipsec->tx_esw->ft.mutex); mutex_init(&ipsec->rx_esw->ft.mutex); ipsec->tx_esw->ns = ns_esw; - xa_init_flags(&ipsec->rx_esw->ipsec_obj_id_map, XA_FLAGS_ALLOC1); + xa_init_flags(&ipsec->ipsec_obj_id_map, XA_FLAGS_ALLOC1); } else if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_ROCE) { ipsec->roce = mlx5_ipsec_fs_roce_init(mdev, devcom); } else { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c index a91f772dc981..6e00afe4671b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c @@ -6,6 +6,8 @@ #include "ipsec.h" #include "lib/crypto.h" #include "lib/ipsec_fs_roce.h" +#include "fs_core.h" +#include "eswitch.h" enum { MLX5_IPSEC_ASO_REMOVE_FLOW_PKT_CNT_OFFSET, @@ -38,7 +40,10 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev) MLX5_CAP_ETH(mdev, insert_trailer) && MLX5_CAP_ETH(mdev, swp)) caps |= MLX5_IPSEC_CAP_CRYPTO; - if (MLX5_CAP_IPSEC(mdev, ipsec_full_offload)) { + if (MLX5_CAP_IPSEC(mdev, ipsec_full_offload) && + (mdev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_DMFS || + (mdev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS && + is_mdev_legacy_mode(mdev)))) { if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev, reformat_add_esp_trasport) && MLX5_CAP_FLOWTABLE_NIC_RX(mdev, @@ -95,7 +100,7 @@ static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn, if (attrs->dir == XFRM_DEV_OFFLOAD_IN) { MLX5_SET(ipsec_aso, aso_ctx, window_sz, - attrs->replay_esn.replay_window / 64); + attrs->replay_esn.replay_window); MLX5_SET(ipsec_aso, aso_ctx, mode, MLX5_IPSEC_ASO_REPLAY_PROTECTION); } @@ -559,6 +564,7 @@ void mlx5e_ipsec_aso_cleanup(struct mlx5e_ipsec *ipsec) dma_unmap_single(pdev, aso->dma_addr, sizeof(aso->ctx), DMA_BIDIRECTIONAL); kfree(aso); + ipsec->aso = NULL; } static void mlx5e_ipsec_aso_copy(struct mlx5_wqe_aso_ctrl_seg *ctrl, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c index 51a144246ea6..727fa7c18523 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c @@ -304,12 +304,6 @@ drop: return false; } -enum { - MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_DECRYPTED, - MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_AUTH_FAILED, - MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_BAD_TRAILER, -}; - void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb, u32 ipsec_meta_data) @@ -343,20 +337,7 @@ void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev, xo = xfrm_offload(skb); xo->flags = CRYPTO_DONE; - - switch (MLX5_IPSEC_METADATA_SYNDROM(ipsec_meta_data)) { - case MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_DECRYPTED: - xo->status = CRYPTO_SUCCESS; - break; - case MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_AUTH_FAILED: - xo->status = CRYPTO_TUNNEL_ESP_AUTH_FAILED; - break; - case MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_BAD_TRAILER: - xo->status = CRYPTO_INVALID_PACKET_SYNTAX; - break; - default: - atomic64_inc(&ipsec->sw_stats.ipsec_rx_drop_syndrome); - } + xo->status = CRYPTO_SUCCESS; } int mlx5_esw_ipsec_rx_make_metadata(struct mlx5e_priv *priv, u32 id, u32 *metadata) @@ -374,8 +355,6 @@ int mlx5_esw_ipsec_rx_make_metadata(struct mlx5e_priv *priv, u32 id, u32 *metada return err; } - *metadata = MLX5_IPSEC_METADATA_CREATE(ipsec_obj_id, - MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_DECRYPTED); - + *metadata = ipsec_obj_id; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h index 2ed99772f168..82064614846f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h @@ -43,7 +43,6 @@ #define MLX5_IPSEC_METADATA_MARKER(metadata) (((metadata) >> 31) & 0x1) #define MLX5_IPSEC_METADATA_SYNDROM(metadata) (((metadata) >> 24) & GENMASK(5, 0)) #define MLX5_IPSEC_METADATA_HANDLE(metadata) ((metadata) & GENMASK(23, 0)) -#define MLX5_IPSEC_METADATA_CREATE(id, syndrome) ((id) | ((syndrome) << 24)) struct mlx5e_accel_tx_ipsec_state { struct xfrm_offload *xo; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c index e0e36a09721c..dd36b04e30a0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c @@ -51,7 +51,6 @@ static const struct counter_desc mlx5e_ipsec_hw_stats_desc[] = { static const struct counter_desc mlx5e_ipsec_sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_ipsec_sw_stats, ipsec_rx_drop_sp_alloc) }, { MLX5E_DECLARE_STAT(struct mlx5e_ipsec_sw_stats, ipsec_rx_drop_sadb_miss) }, - { MLX5E_DECLARE_STAT(struct mlx5e_ipsec_sw_stats, ipsec_rx_drop_syndrome) }, { MLX5E_DECLARE_STAT(struct mlx5e_ipsec_sw_stats, ipsec_tx_drop_bundle) }, { MLX5E_DECLARE_STAT(struct mlx5e_ipsec_sw_stats, ipsec_tx_drop_no_state) }, { MLX5E_DECLARE_STAT(struct mlx5e_ipsec_sw_stats, ipsec_tx_drop_not_ip) }, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index d4ebd8743114..b2cabd6ab86c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -310,9 +310,9 @@ static void mlx5e_macsec_destroy_object(struct mlx5_core_dev *mdev, u32 macsec_o mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); } -static void mlx5e_macsec_cleanup_sa(struct mlx5e_macsec *macsec, - struct mlx5e_macsec_sa *sa, - bool is_tx, struct net_device *netdev, u32 fs_id) +static void mlx5e_macsec_cleanup_sa_fs(struct mlx5e_macsec *macsec, + struct mlx5e_macsec_sa *sa, bool is_tx, + struct net_device *netdev, u32 fs_id) { int action = (is_tx) ? MLX5_ACCEL_MACSEC_ACTION_ENCRYPT : MLX5_ACCEL_MACSEC_ACTION_DECRYPT; @@ -322,20 +322,49 @@ static void mlx5e_macsec_cleanup_sa(struct mlx5e_macsec *macsec, mlx5_macsec_fs_del_rule(macsec->mdev->macsec_fs, sa->macsec_rule, action, netdev, fs_id); - mlx5e_macsec_destroy_object(macsec->mdev, sa->macsec_obj_id); sa->macsec_rule = NULL; } +static void mlx5e_macsec_cleanup_sa(struct mlx5e_macsec *macsec, + struct mlx5e_macsec_sa *sa, bool is_tx, + struct net_device *netdev, u32 fs_id) +{ + mlx5e_macsec_cleanup_sa_fs(macsec, sa, is_tx, netdev, fs_id); + mlx5e_macsec_destroy_object(macsec->mdev, sa->macsec_obj_id); +} + +static int mlx5e_macsec_init_sa_fs(struct macsec_context *ctx, + struct mlx5e_macsec_sa *sa, bool encrypt, + bool is_tx, u32 *fs_id) +{ + struct mlx5e_priv *priv = macsec_netdev_priv(ctx->netdev); + struct mlx5_macsec_fs *macsec_fs = priv->mdev->macsec_fs; + struct mlx5_macsec_rule_attrs rule_attrs; + union mlx5_macsec_rule *macsec_rule; + + rule_attrs.macsec_obj_id = sa->macsec_obj_id; + rule_attrs.sci = sa->sci; + rule_attrs.assoc_num = sa->assoc_num; + rule_attrs.action = (is_tx) ? MLX5_ACCEL_MACSEC_ACTION_ENCRYPT : + MLX5_ACCEL_MACSEC_ACTION_DECRYPT; + + macsec_rule = mlx5_macsec_fs_add_rule(macsec_fs, ctx, &rule_attrs, fs_id); + if (!macsec_rule) + return -ENOMEM; + + sa->macsec_rule = macsec_rule; + + return 0; +} + static int mlx5e_macsec_init_sa(struct macsec_context *ctx, struct mlx5e_macsec_sa *sa, bool encrypt, bool is_tx, u32 *fs_id) { struct mlx5e_priv *priv = macsec_netdev_priv(ctx->netdev); struct mlx5e_macsec *macsec = priv->macsec; - struct mlx5_macsec_rule_attrs rule_attrs; struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_macsec_obj_attrs obj_attrs; - union mlx5_macsec_rule *macsec_rule; int err; obj_attrs.next_pn = sa->next_pn; @@ -357,20 +386,12 @@ static int mlx5e_macsec_init_sa(struct macsec_context *ctx, if (err) return err; - rule_attrs.macsec_obj_id = sa->macsec_obj_id; - rule_attrs.sci = sa->sci; - rule_attrs.assoc_num = sa->assoc_num; - rule_attrs.action = (is_tx) ? MLX5_ACCEL_MACSEC_ACTION_ENCRYPT : - MLX5_ACCEL_MACSEC_ACTION_DECRYPT; - - macsec_rule = mlx5_macsec_fs_add_rule(mdev->macsec_fs, ctx, &rule_attrs, fs_id); - if (!macsec_rule) { - err = -ENOMEM; - goto destroy_macsec_object; + if (sa->active) { + err = mlx5e_macsec_init_sa_fs(ctx, sa, encrypt, is_tx, fs_id); + if (err) + goto destroy_macsec_object; } - sa->macsec_rule = macsec_rule; - return 0; destroy_macsec_object: @@ -526,9 +547,7 @@ static int mlx5e_macsec_add_txsa(struct macsec_context *ctx) goto destroy_sa; macsec_device->tx_sa[assoc_num] = tx_sa; - if (!secy->operational || - assoc_num != tx_sc->encoding_sa || - !tx_sa->active) + if (!secy->operational) goto out; err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true, NULL); @@ -595,7 +614,7 @@ static int mlx5e_macsec_upd_txsa(struct macsec_context *ctx) goto out; if (ctx_tx_sa->active) { - err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true, NULL); + err = mlx5e_macsec_init_sa_fs(ctx, tx_sa, tx_sc->encrypt, true, NULL); if (err) goto out; } else { @@ -604,7 +623,7 @@ static int mlx5e_macsec_upd_txsa(struct macsec_context *ctx) goto out; } - mlx5e_macsec_cleanup_sa(macsec, tx_sa, true, ctx->secy->netdev, 0); + mlx5e_macsec_cleanup_sa_fs(macsec, tx_sa, true, ctx->secy->netdev, 0); } out: mutex_unlock(&macsec->lock); @@ -1030,8 +1049,9 @@ static int mlx5e_macsec_del_rxsa(struct macsec_context *ctx) goto out; } - mlx5e_macsec_cleanup_sa(macsec, rx_sa, false, ctx->secy->netdev, - rx_sc->sc_xarray_element->fs_id); + if (rx_sa->active) + mlx5e_macsec_cleanup_sa(macsec, rx_sa, false, ctx->secy->netdev, + rx_sc->sc_xarray_element->fs_id); mlx5_destroy_encryption_key(macsec->mdev, rx_sa->enc_key_id); kfree(rx_sa); rx_sc->rx_sa[assoc_num] = NULL; @@ -1112,8 +1132,8 @@ static int macsec_upd_secy_hw_address(struct macsec_context *ctx, if (!rx_sa || !rx_sa->macsec_rule) continue; - mlx5e_macsec_cleanup_sa(macsec, rx_sa, false, ctx->secy->netdev, - rx_sc->sc_xarray_element->fs_id); + mlx5e_macsec_cleanup_sa_fs(macsec, rx_sa, false, ctx->secy->netdev, + rx_sc->sc_xarray_element->fs_id); } } @@ -1124,8 +1144,8 @@ static int macsec_upd_secy_hw_address(struct macsec_context *ctx, continue; if (rx_sa->active) { - err = mlx5e_macsec_init_sa(ctx, rx_sa, true, false, - &rx_sc->sc_xarray_element->fs_id); + err = mlx5e_macsec_init_sa_fs(ctx, rx_sa, true, false, + &rx_sc->sc_xarray_element->fs_id); if (err) goto out; } @@ -1178,7 +1198,7 @@ static int mlx5e_macsec_upd_secy(struct macsec_context *ctx) if (!tx_sa) continue; - mlx5e_macsec_cleanup_sa(macsec, tx_sa, true, ctx->secy->netdev, 0); + mlx5e_macsec_cleanup_sa_fs(macsec, tx_sa, true, ctx->secy->netdev, 0); } for (i = 0; i < MACSEC_NUM_AN; ++i) { @@ -1187,7 +1207,7 @@ static int mlx5e_macsec_upd_secy(struct macsec_context *ctx) continue; if (tx_sa->assoc_num == tx_sc->encoding_sa && tx_sa->active) { - err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true, NULL); + err = mlx5e_macsec_init_sa_fs(ctx, tx_sa, tx_sc->encrypt, true, NULL); if (err) goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index bb7f86c993e5..c7f542d0b8f0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -34,6 +34,7 @@ #include <linux/mlx5/fs.h> #include <linux/ip.h> #include <linux/ipv6.h> +#include <net/rps.h> #include "en.h" #define ARFS_HASH_SHIFT BITS_PER_BYTE @@ -254,11 +255,13 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft, ft->g = kcalloc(MLX5E_ARFS_NUM_GROUPS, sizeof(*ft->g), GFP_KERNEL); - in = kvzalloc(inlen, GFP_KERNEL); - if (!in || !ft->g) { - kfree(ft->g); - kvfree(in); + if (!ft->g) return -ENOMEM; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) { + err = -ENOMEM; + goto err_free_g; } mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); @@ -278,7 +281,7 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft, break; default: err = -EINVAL; - goto out; + goto err_free_in; } switch (type) { @@ -300,7 +303,7 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft, break; default: err = -EINVAL; - goto out; + goto err_free_in; } MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); @@ -309,7 +312,7 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft, MLX5_SET_CFG(in, end_flow_index, ix - 1); ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); if (IS_ERR(ft->g[ft->num_groups])) - goto err; + goto err_clean_group; ft->num_groups++; memset(in, 0, inlen); @@ -318,18 +321,20 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft, MLX5_SET_CFG(in, end_flow_index, ix - 1); ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); if (IS_ERR(ft->g[ft->num_groups])) - goto err; + goto err_clean_group; ft->num_groups++; kvfree(in); return 0; -err: +err_clean_group: err = PTR_ERR(ft->g[ft->num_groups]); ft->g[ft->num_groups] = NULL; -out: +err_free_in: kvfree(in); - +err_free_g: + kfree(ft->g); + ft->g = NULL; return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 41c396e76457..6ed3a32b7e22 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -74,7 +74,73 @@ int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, u32 *mkey) return err; } -int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev) +int mlx5e_create_tis(struct mlx5_core_dev *mdev, void *in, u32 *tisn) +{ + void *tisc = MLX5_ADDR_OF(create_tis_in, in, ctx); + + MLX5_SET(tisc, tisc, transport_domain, mdev->mlx5e_res.hw_objs.td.tdn); + + if (mlx5_lag_is_lacp_owner(mdev)) + MLX5_SET(tisc, tisc, strict_lag_tx_port_affinity, 1); + + return mlx5_core_create_tis(mdev, in, tisn); +} + +void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn) +{ + mlx5_core_destroy_tis(mdev, tisn); +} + +static void mlx5e_destroy_tises(struct mlx5_core_dev *mdev, u32 tisn[MLX5_MAX_PORTS][MLX5_MAX_NUM_TC]) +{ + int tc, i; + + for (i = 0; i < mlx5e_get_num_lag_ports(mdev); i++) + for (tc = 0; tc < MLX5_MAX_NUM_TC; tc++) + mlx5e_destroy_tis(mdev, tisn[i][tc]); +} + +static bool mlx5_lag_should_assign_affinity(struct mlx5_core_dev *mdev) +{ + return MLX5_CAP_GEN(mdev, lag_tx_port_affinity) && mlx5e_get_num_lag_ports(mdev) > 1; +} + +static int mlx5e_create_tises(struct mlx5_core_dev *mdev, u32 tisn[MLX5_MAX_PORTS][MLX5_MAX_NUM_TC]) +{ + int tc, i; + int err; + + for (i = 0; i < mlx5e_get_num_lag_ports(mdev); i++) { + for (tc = 0; tc < MLX5_MAX_NUM_TC; tc++) { + u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {}; + void *tisc; + + tisc = MLX5_ADDR_OF(create_tis_in, in, ctx); + + MLX5_SET(tisc, tisc, prio, tc << 1); + + if (mlx5_lag_should_assign_affinity(mdev)) + MLX5_SET(tisc, tisc, lag_tx_port_affinity, i + 1); + + err = mlx5e_create_tis(mdev, in, &tisn[i][tc]); + if (err) + goto err_close_tises; + } + } + + return 0; + +err_close_tises: + for (; i >= 0; i--) { + for (tc--; tc >= 0; tc--) + mlx5e_destroy_tis(mdev, tisn[i][tc]); + tc = MLX5_MAX_NUM_TC; + } + + return err; +} + +int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises) { struct mlx5e_hw_objs *res = &mdev->mlx5e_res.hw_objs; int err; @@ -103,6 +169,15 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev) goto err_destroy_mkey; } + if (create_tises) { + err = mlx5e_create_tises(mdev, res->tisn); + if (err) { + mlx5_core_err(mdev, "alloc tises failed, %d\n", err); + goto err_destroy_bfreg; + } + res->tisn_valid = true; + } + INIT_LIST_HEAD(&res->td.tirs_list); mutex_init(&res->td.list_lock); @@ -115,6 +190,8 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev) return 0; +err_destroy_bfreg: + mlx5_free_bfreg(mdev, &res->bfreg); err_destroy_mkey: mlx5_core_destroy_mkey(mdev, res->mkey); err_dealloc_transport_domain: @@ -130,6 +207,8 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev) mlx5_crypto_dek_cleanup(mdev->mlx5e_res.dek_priv); mdev->mlx5e_res.dek_priv = NULL; + if (res->tisn_valid) + mlx5e_destroy_tises(mdev, res->tisn); mlx5_free_bfreg(mdev, &res->bfreg); mlx5_core_destroy_mkey(mdev, res->mkey); mlx5_core_dealloc_transport_domain(mdev, res->td.tdn); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 215261a69255..cc51ce16df14 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -43,12 +43,17 @@ void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv, struct ethtool_drvinfo *drvinfo) { struct mlx5_core_dev *mdev = priv->mdev; + int count; strscpy(drvinfo->driver, KBUILD_MODNAME, sizeof(drvinfo->driver)); - snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), - "%d.%d.%04d (%.16s)", - fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev), - mdev->board_id); + count = snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), + "%d.%d.%04d (%.16s)", fw_rev_maj(mdev), + fw_rev_min(mdev), fw_rev_sub(mdev), mdev->board_id); + if (count >= sizeof(drvinfo->fw_version)) + snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), + "%d.%d.%04d", fw_rev_maj(mdev), + fw_rev_min(mdev), fw_rev_sub(mdev)); + strscpy(drvinfo->bus_info, dev_name(mdev->device), sizeof(drvinfo->bus_info)); } @@ -1257,27 +1262,29 @@ static u32 mlx5e_get_rxfh_indir_size(struct net_device *netdev) return mlx5e_ethtool_get_rxfh_indir_size(priv); } -static int mlx5e_get_rxfh_context(struct net_device *dev, u32 *indir, - u8 *key, u8 *hfunc, u32 rss_context) +int mlx5e_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh) { - struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5e_priv *priv = netdev_priv(netdev); + u32 rss_context = rxfh->rss_context; int err; mutex_lock(&priv->state_lock); - err = mlx5e_rx_res_rss_get_rxfh(priv->rx_res, rss_context, indir, key, hfunc); + err = mlx5e_rx_res_rss_get_rxfh(priv->rx_res, rss_context, + rxfh->indir, rxfh->key, &rxfh->hfunc); mutex_unlock(&priv->state_lock); return err; } -static int mlx5e_set_rxfh_context(struct net_device *dev, const u32 *indir, - const u8 *key, const u8 hfunc, - u32 *rss_context, bool delete) +int mlx5e_set_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = netdev_priv(dev); + u32 *rss_context = &rxfh->rss_context; + u8 hfunc = rxfh->hfunc; int err; mutex_lock(&priv->state_lock); - if (delete) { + if (*rss_context && rxfh->rss_delete) { err = mlx5e_rx_res_rss_destroy(priv->rx_res, *rss_context); goto unlock; } @@ -1290,7 +1297,8 @@ static int mlx5e_set_rxfh_context(struct net_device *dev, const u32 *indir, goto unlock; } - err = mlx5e_rx_res_rss_set_rxfh(priv->rx_res, *rss_context, indir, key, + err = mlx5e_rx_res_rss_set_rxfh(priv->rx_res, *rss_context, + rxfh->indir, rxfh->key, hfunc == ETH_RSS_HASH_NO_CHANGE ? NULL : &hfunc); unlock: @@ -1298,25 +1306,6 @@ unlock: return err; } -int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, - u8 *hfunc) -{ - return mlx5e_get_rxfh_context(netdev, indir, key, hfunc, 0); -} - -int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, - const u8 *key, const u8 hfunc) -{ - struct mlx5e_priv *priv = netdev_priv(dev); - int err; - - mutex_lock(&priv->state_lock); - err = mlx5e_rx_res_rss_set_rxfh(priv->rx_res, 0, indir, key, - hfunc == ETH_RSS_HASH_NO_CHANGE ? NULL : &hfunc); - mutex_unlock(&priv->state_lock); - return err; -} - #define MLX5E_PFC_PREVEN_AUTO_TOUT_MSEC 100 #define MLX5E_PFC_PREVEN_TOUT_MAX_MSEC 8000 #define MLX5E_PFC_PREVEN_MINOR_PRECENT 85 @@ -2393,6 +2382,7 @@ static void mlx5e_get_rmon_stats(struct net_device *netdev, } const struct ethtool_ops mlx5e_ethtool_ops = { + .cap_rss_ctx_supported = true, .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_MAX_FRAMES | ETHTOOL_COALESCE_USE_ADAPTIVE | @@ -2415,8 +2405,6 @@ const struct ethtool_ops mlx5e_ethtool_ops = { .get_rxfh_indir_size = mlx5e_get_rxfh_indir_size, .get_rxfh = mlx5e_get_rxfh, .set_rxfh = mlx5e_set_rxfh, - .get_rxfh_context = mlx5e_get_rxfh_context, - .set_rxfh_context = mlx5e_set_rxfh_context, .get_rxnfc = mlx5e_get_rxnfc, .set_rxnfc = mlx5e_set_rxnfc, .get_tunable = mlx5e_get_tunable, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index ea58c6917433..be809556b2e1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -902,6 +902,7 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params, pp_params.nid = node; pp_params.dev = rq->pdev; pp_params.napi = rq->cq.napi; + pp_params.netdev = rq->netdev; pp_params.dma_dir = rq->buff.map_dir; pp_params.max_len = PAGE_SIZE; @@ -1351,6 +1352,17 @@ void mlx5e_close_rq(struct mlx5e_rq *rq) mlx5e_free_rq(rq); } +u32 mlx5e_profile_get_tisn(struct mlx5_core_dev *mdev, + struct mlx5e_priv *priv, + const struct mlx5e_profile *profile, + u8 lag_port, u8 tc) +{ + if (profile->get_tisn) + return profile->get_tisn(mdev, priv, lag_port, tc); + + return mdev->mlx5e_res.hw_objs.tisn[lag_port][tc]; +} + static void mlx5e_free_xdpsq_db(struct mlx5e_xdpsq *sq) { kvfree(sq->db.xdpi_fifo.xi); @@ -1794,6 +1806,7 @@ void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq) set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); netdev_tx_reset_queue(sq->txq); netif_tx_start_queue(sq->txq); + netif_queue_set_napi(sq->netdev, sq->txq_ix, NETDEV_QUEUE_TYPE_TX, sq->cq.napi); } void mlx5e_tx_disable_queue(struct netdev_queue *txq) @@ -1807,6 +1820,7 @@ void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq) { struct mlx5_wq_cyc *wq = &sq->wq; + netif_queue_set_napi(sq->netdev, sq->txq_ix, NETDEV_QUEUE_TYPE_TX, NULL); clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); synchronize_net(); /* Sync with NAPI to prevent netif_tx_wake_queue. */ @@ -1919,7 +1933,8 @@ int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params, return err; csp.tis_lst_sz = 1; - csp.tisn = c->priv->tisn[c->lag_port][0]; /* tc = 0 */ + csp.tisn = mlx5e_profile_get_tisn(c->mdev, c->priv, c->priv->profile, + c->lag_port, 0); /* tc = 0 */ csp.cqn = sq->cq.mcq.cqn; csp.wq_ctrl = &sq->wq_ctrl; csp.min_inline_mode = sq->min_inline_mode; @@ -1981,11 +1996,12 @@ void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq) mlx5e_free_xdpsq(sq); } -static int mlx5e_alloc_cq_common(struct mlx5e_priv *priv, +static int mlx5e_alloc_cq_common(struct mlx5_core_dev *mdev, + struct net_device *netdev, + struct workqueue_struct *workqueue, struct mlx5e_cq_param *param, struct mlx5e_cq *cq) { - struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_core_cq *mcq = &cq->mcq; int err; u32 i; @@ -2012,13 +2028,13 @@ static int mlx5e_alloc_cq_common(struct mlx5e_priv *priv, } cq->mdev = mdev; - cq->netdev = priv->netdev; - cq->priv = priv; + cq->netdev = netdev; + cq->workqueue = workqueue; return 0; } -static int mlx5e_alloc_cq(struct mlx5e_priv *priv, +static int mlx5e_alloc_cq(struct mlx5_core_dev *mdev, struct mlx5e_cq_param *param, struct mlx5e_create_cq_param *ccp, struct mlx5e_cq *cq) @@ -2029,7 +2045,7 @@ static int mlx5e_alloc_cq(struct mlx5e_priv *priv, param->wq.db_numa_node = ccp->node; param->eq_ix = ccp->ix; - err = mlx5e_alloc_cq_common(priv, param, cq); + err = mlx5e_alloc_cq_common(mdev, ccp->netdev, ccp->wq, param, cq); cq->napi = ccp->napi; cq->ch_stats = ccp->ch_stats; @@ -2095,14 +2111,13 @@ static void mlx5e_destroy_cq(struct mlx5e_cq *cq) mlx5_core_destroy_cq(cq->mdev, &cq->mcq); } -int mlx5e_open_cq(struct mlx5e_priv *priv, struct dim_cq_moder moder, +int mlx5e_open_cq(struct mlx5_core_dev *mdev, struct dim_cq_moder moder, struct mlx5e_cq_param *param, struct mlx5e_create_cq_param *ccp, struct mlx5e_cq *cq) { - struct mlx5_core_dev *mdev = priv->mdev; int err; - err = mlx5e_alloc_cq(priv, param, ccp, cq); + err = mlx5e_alloc_cq(mdev, param, ccp, cq); if (err) return err; @@ -2135,7 +2150,7 @@ static int mlx5e_open_tx_cqs(struct mlx5e_channel *c, int tc; for (tc = 0; tc < c->num_tc; tc++) { - err = mlx5e_open_cq(c->priv, params->tx_cq_moderation, &cparam->txq_sq.cqp, + err = mlx5e_open_cq(c->mdev, params->tx_cq_moderation, &cparam->txq_sq.cqp, ccp, &c->sq[tc].cq); if (err) goto err_close_tx_cqs; @@ -2203,12 +2218,15 @@ static int mlx5e_open_sqs(struct mlx5e_channel *c, for (tc = 0; tc < mlx5e_get_dcb_num_tc(params); tc++) { int txq_ix = c->ix + tc * params->num_channels; u32 qos_queue_group_id; + u32 tisn; + tisn = mlx5e_profile_get_tisn(c->mdev, c->priv, c->priv->profile, + c->lag_port, tc); err = mlx5e_txq_get_qos_node_hw_id(params, txq_ix, &qos_queue_group_id); if (err) goto err_close_sqs; - err = mlx5e_open_txqsq(c, c->priv->tisn[c->lag_port][tc], txq_ix, + err = mlx5e_open_txqsq(c, tisn, txq_ix, params, &cparam->txq_sq, &c->sq[tc], tc, qos_queue_group_id, &c->priv->channel_stats[c->ix]->sq[tc]); @@ -2336,12 +2354,12 @@ static int mlx5e_open_queues(struct mlx5e_channel *c, mlx5e_build_create_cq_param(&ccp, c); - err = mlx5e_open_cq(c->priv, icocq_moder, &cparam->async_icosq.cqp, &ccp, + err = mlx5e_open_cq(c->mdev, icocq_moder, &cparam->async_icosq.cqp, &ccp, &c->async_icosq.cq); if (err) return err; - err = mlx5e_open_cq(c->priv, icocq_moder, &cparam->icosq.cqp, &ccp, + err = mlx5e_open_cq(c->mdev, icocq_moder, &cparam->icosq.cqp, &ccp, &c->icosq.cq); if (err) goto err_close_async_icosq_cq; @@ -2350,17 +2368,17 @@ static int mlx5e_open_queues(struct mlx5e_channel *c, if (err) goto err_close_icosq_cq; - err = mlx5e_open_cq(c->priv, params->tx_cq_moderation, &cparam->xdp_sq.cqp, &ccp, + err = mlx5e_open_cq(c->mdev, params->tx_cq_moderation, &cparam->xdp_sq.cqp, &ccp, &c->xdpsq.cq); if (err) goto err_close_tx_cqs; - err = mlx5e_open_cq(c->priv, params->rx_cq_moderation, &cparam->rq.cqp, &ccp, + err = mlx5e_open_cq(c->mdev, params->rx_cq_moderation, &cparam->rq.cqp, &ccp, &c->rq.cq); if (err) goto err_close_xdp_tx_cqs; - err = c->xdp ? mlx5e_open_cq(c->priv, params->tx_cq_moderation, &cparam->xdp_sq.cqp, + err = c->xdp ? mlx5e_open_cq(c->mdev, params->tx_cq_moderation, &cparam->xdp_sq.cqp, &ccp, &c->rq_xdpsq.cq) : 0; if (err) goto err_close_rx_cq; @@ -2544,6 +2562,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, c->lag_port = mlx5e_enumerate_lag_port(priv->mdev, ix); netif_napi_add(netdev, &c->napi, mlx5e_napi_poll); + netif_napi_set_irq(&c->napi, irq); err = mlx5e_open_queues(c, params, cparam); if (unlikely(err)) @@ -2586,12 +2605,16 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c) mlx5e_activate_xsk(c); else mlx5e_activate_rq(&c->rq); + + netif_queue_set_napi(c->netdev, c->ix, NETDEV_QUEUE_TYPE_RX, &c->napi); } static void mlx5e_deactivate_channel(struct mlx5e_channel *c) { int tc; + netif_queue_set_napi(c->netdev, c->ix, NETDEV_QUEUE_TYPE_RX, NULL); + if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)) mlx5e_deactivate_xsk(c); else @@ -2731,6 +2754,7 @@ void mlx5e_close_channels(struct mlx5e_channels *chs) { int i; + ASSERT_RTNL(); if (chs->ptp) { mlx5e_ptp_close(chs->ptp); chs->ptp = NULL; @@ -3012,17 +3036,29 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) if (mlx5e_is_vport_rep(priv)) mlx5e_rep_activate_channels(priv); + set_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state); + mlx5e_wait_channels_min_rx_wqes(&priv->channels); if (priv->rx_res) mlx5e_rx_res_channels_activate(priv->rx_res, &priv->channels); } +static void mlx5e_cancel_tx_timeout_work(struct mlx5e_priv *priv) +{ + WARN_ON_ONCE(test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state)); + if (current_work() != &priv->tx_timeout_work) + cancel_work_sync(&priv->tx_timeout_work); +} + void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv) { if (priv->rx_res) mlx5e_rx_res_channels_deactivate(priv->rx_res); + clear_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state); + mlx5e_cancel_tx_timeout_work(priv); + if (mlx5e_is_vport_rep(priv)) mlx5e_rep_deactivate_channels(priv); @@ -3294,7 +3330,7 @@ static int mlx5e_alloc_drop_cq(struct mlx5e_priv *priv, param->wq.buf_numa_node = dev_to_node(mlx5_core_dma_dev(mdev)); param->wq.db_numa_node = dev_to_node(mlx5_core_dma_dev(mdev)); - return mlx5e_alloc_cq_common(priv, param, cq); + return mlx5e_alloc_cq_common(priv->mdev, priv->netdev, priv->wq, param, cq); } int mlx5e_open_drop_rq(struct mlx5e_priv *priv, @@ -3350,75 +3386,6 @@ void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq) mlx5e_free_cq(&drop_rq->cq); } -int mlx5e_create_tis(struct mlx5_core_dev *mdev, void *in, u32 *tisn) -{ - void *tisc = MLX5_ADDR_OF(create_tis_in, in, ctx); - - MLX5_SET(tisc, tisc, transport_domain, mdev->mlx5e_res.hw_objs.td.tdn); - - if (MLX5_GET(tisc, tisc, tls_en)) - MLX5_SET(tisc, tisc, pd, mdev->mlx5e_res.hw_objs.pdn); - - if (mlx5_lag_is_lacp_owner(mdev)) - MLX5_SET(tisc, tisc, strict_lag_tx_port_affinity, 1); - - return mlx5_core_create_tis(mdev, in, tisn); -} - -void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn) -{ - mlx5_core_destroy_tis(mdev, tisn); -} - -void mlx5e_destroy_tises(struct mlx5e_priv *priv) -{ - int tc, i; - - for (i = 0; i < mlx5e_get_num_lag_ports(priv->mdev); i++) - for (tc = 0; tc < priv->profile->max_tc; tc++) - mlx5e_destroy_tis(priv->mdev, priv->tisn[i][tc]); -} - -static bool mlx5e_lag_should_assign_affinity(struct mlx5_core_dev *mdev) -{ - return MLX5_CAP_GEN(mdev, lag_tx_port_affinity) && mlx5e_get_num_lag_ports(mdev) > 1; -} - -int mlx5e_create_tises(struct mlx5e_priv *priv) -{ - int tc, i; - int err; - - for (i = 0; i < mlx5e_get_num_lag_ports(priv->mdev); i++) { - for (tc = 0; tc < priv->profile->max_tc; tc++) { - u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {}; - void *tisc; - - tisc = MLX5_ADDR_OF(create_tis_in, in, ctx); - - MLX5_SET(tisc, tisc, prio, tc << 1); - - if (mlx5e_lag_should_assign_affinity(priv->mdev)) - MLX5_SET(tisc, tisc, lag_tx_port_affinity, i + 1); - - err = mlx5e_create_tis(priv->mdev, in, &priv->tisn[i][tc]); - if (err) - goto err_close_tises; - } - } - - return 0; - -err_close_tises: - for (; i >= 0; i--) { - for (tc--; tc >= 0; tc--) - mlx5e_destroy_tis(priv->mdev, priv->tisn[i][tc]); - tc = priv->profile->max_tc; - } - - return err; -} - static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv) { if (priv->mqprio_rl) { @@ -3427,7 +3394,6 @@ static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv) priv->mqprio_rl = NULL; } mlx5e_accel_cleanup_tx(priv); - mlx5e_destroy_tises(priv); } static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd) @@ -3529,7 +3495,7 @@ static int mlx5e_setup_tc_mqprio_dcb(struct mlx5e_priv *priv, mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; - if (tc && tc != MLX5E_MAX_NUM_TC) + if (tc && tc != MLX5_MAX_NUM_TC) return -EINVAL; new_params = priv->channels.params; @@ -4801,8 +4767,17 @@ static void mlx5e_tx_timeout_work(struct work_struct *work) struct net_device *netdev = priv->netdev; int i; - rtnl_lock(); - mutex_lock(&priv->state_lock); + /* Take rtnl_lock to ensure no change in netdev->real_num_tx_queues + * through this flow. However, channel closing flows have to wait for + * this work to finish while holding rtnl lock too. So either get the + * lock or find that channels are being closed for other reason and + * this work is not relevant anymore. + */ + while (!rtnl_trylock()) { + if (!test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state)) + return; + msleep(20); + } if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) goto unlock; @@ -4821,7 +4796,6 @@ static void mlx5e_tx_timeout_work(struct work_struct *work) } unlock: - mutex_unlock(&priv->state_lock); rtnl_unlock(); } @@ -5164,6 +5138,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->netdev_ops = &mlx5e_netdev_ops; netdev->xdp_metadata_ops = &mlx5e_xdp_metadata_ops; + netdev->xsk_tx_metadata_ops = &mlx5e_xsk_tx_metadata_ops; mlx5e_dcbnl_build_netdev(netdev); @@ -5244,7 +5219,6 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->gso_partial_features |= NETIF_F_GSO_UDP_L4; netdev->hw_features |= NETIF_F_GSO_UDP_L4; - netdev->features |= NETIF_F_GSO_UDP_L4; mlx5_query_port_fcs(mdev, &fcs_supported, &fcs_enabled); @@ -5484,23 +5458,13 @@ static int mlx5e_init_nic_tx(struct mlx5e_priv *priv) { int err; - err = mlx5e_create_tises(priv); - if (err) { - mlx5_core_warn(priv->mdev, "create tises failed, %d\n", err); - return err; - } - err = mlx5e_accel_init_tx(priv); if (err) - goto err_destroy_tises; + return err; mlx5e_set_mqprio_rl(priv); mlx5e_dcbnl_initialize(priv); return 0; - -err_destroy_tises: - mlx5e_destroy_tises(priv); - return err; } static void mlx5e_nic_enable(struct mlx5e_priv *priv) @@ -5595,7 +5559,7 @@ static const struct mlx5e_profile mlx5e_nic_profile = { .update_stats = mlx5e_stats_update_ndo_stats, .update_carrier = mlx5e_update_carrier, .rx_handlers = &mlx5e_rx_handlers_nic, - .max_tc = MLX5E_MAX_NUM_TC, + .max_tc = MLX5_MAX_NUM_TC, .stats_grps = mlx5e_nic_stats_grps, .stats_grps_num = mlx5e_nic_stats_grps_num, .features = BIT(MLX5E_PROFILE_FEATURE_PTP_RX) | @@ -6035,7 +5999,7 @@ static int mlx5e_resume(struct auxiliary_device *adev) if (netif_device_present(netdev)) return 0; - err = mlx5e_create_mdev_resources(mdev); + err = mlx5e_create_mdev_resources(mdev, true); if (err) return err; @@ -6048,7 +6012,7 @@ static int mlx5e_resume(struct auxiliary_device *adev) return 0; } -static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state) +static int _mlx5e_suspend(struct auxiliary_device *adev) { struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); struct mlx5e_priv *priv = mlx5e_dev->priv; @@ -6066,15 +6030,18 @@ static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state) return 0; } -static int mlx5e_probe(struct auxiliary_device *adev, - const struct auxiliary_device_id *id) +static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state) +{ + return _mlx5e_suspend(adev); +} + +static int _mlx5e_probe(struct auxiliary_device *adev) { struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); const struct mlx5e_profile *profile = &mlx5e_nic_profile; struct mlx5_core_dev *mdev = edev->mdev; struct mlx5e_dev *mlx5e_dev; struct net_device *netdev; - pm_message_t state = {}; struct mlx5e_priv *priv; int err; @@ -6129,7 +6096,7 @@ static int mlx5e_probe(struct auxiliary_device *adev, return 0; err_resume: - mlx5e_suspend(adev, state); + _mlx5e_suspend(adev); err_profile_cleanup: profile->cleanup(priv); err_destroy_netdev: @@ -6141,16 +6108,21 @@ err_devlink_unregister: return err; } +static int mlx5e_probe(struct auxiliary_device *adev, + const struct auxiliary_device_id *id) +{ + return _mlx5e_probe(adev); +} + static void mlx5e_remove(struct auxiliary_device *adev) { struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); struct mlx5e_priv *priv = mlx5e_dev->priv; - pm_message_t state = {}; mlx5_core_uplink_netdev_set(priv->mdev, NULL); mlx5e_dcbnl_delete_app(priv); unregister_netdev(priv->netdev); - mlx5e_suspend(adev, state); + _mlx5e_suspend(adev); priv->profile->cleanup(priv); mlx5e_destroy_netdev(priv); mlx5e_devlink_port_unregister(mlx5e_dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 693e55b010d9..05527418fa64 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -71,13 +71,17 @@ static void mlx5e_rep_get_drvinfo(struct net_device *dev, { struct mlx5e_priv *priv = netdev_priv(dev); struct mlx5_core_dev *mdev = priv->mdev; + int count; strscpy(drvinfo->driver, mlx5e_rep_driver_name, sizeof(drvinfo->driver)); - snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), - "%d.%d.%04d (%.16s)", - fw_rev_maj(mdev), fw_rev_min(mdev), - fw_rev_sub(mdev), mdev->board_id); + count = snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), + "%d.%d.%04d (%.16s)", fw_rev_maj(mdev), + fw_rev_min(mdev), fw_rev_sub(mdev), mdev->board_id); + if (count >= sizeof(drvinfo->fw_version)) + snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), + "%d.%d.%04d", fw_rev_maj(mdev), + fw_rev_min(mdev), fw_rev_sub(mdev)); } static const struct counter_desc sw_rep_stats_desc[] = { @@ -108,8 +112,18 @@ static const struct counter_desc vport_rep_stats_desc[] = { tx_vport_rdma_multicast_bytes) }, }; +static const struct counter_desc vport_rep_loopback_stats_desc[] = { + { MLX5E_DECLARE_STAT(struct mlx5e_rep_stats, + vport_loopback_packets) }, + { MLX5E_DECLARE_STAT(struct mlx5e_rep_stats, + vport_loopback_bytes) }, +}; + #define NUM_VPORT_REP_SW_COUNTERS ARRAY_SIZE(sw_rep_stats_desc) #define NUM_VPORT_REP_HW_COUNTERS ARRAY_SIZE(vport_rep_stats_desc) +#define NUM_VPORT_REP_LOOPBACK_COUNTERS(dev) \ + (MLX5_CAP_GEN(dev, vport_counter_local_loopback) ? \ + ARRAY_SIZE(vport_rep_loopback_stats_desc) : 0) static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(sw_rep) { @@ -153,7 +167,8 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(sw_rep) static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(vport_rep) { - return NUM_VPORT_REP_HW_COUNTERS; + return NUM_VPORT_REP_HW_COUNTERS + + NUM_VPORT_REP_LOOPBACK_COUNTERS(priv->mdev); } static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(vport_rep) @@ -162,6 +177,9 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(vport_rep) for (i = 0; i < NUM_VPORT_REP_HW_COUNTERS; i++) strcpy(data + (idx++) * ETH_GSTRING_LEN, vport_rep_stats_desc[i].format); + for (i = 0; i < NUM_VPORT_REP_LOOPBACK_COUNTERS(priv->mdev); i++) + strcpy(data + (idx++) * ETH_GSTRING_LEN, + vport_rep_loopback_stats_desc[i].format); return idx; } @@ -172,6 +190,9 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(vport_rep) for (i = 0; i < NUM_VPORT_REP_HW_COUNTERS; i++) data[idx++] = MLX5E_READ_CTR64_CPU(&priv->stats.rep_stats, vport_rep_stats_desc, i); + for (i = 0; i < NUM_VPORT_REP_LOOPBACK_COUNTERS(priv->mdev); i++) + data[idx++] = MLX5E_READ_CTR64_CPU(&priv->stats.rep_stats, + vport_rep_loopback_stats_desc, i); return idx; } @@ -243,6 +264,13 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(vport_rep) rep_stats->tx_vport_rdma_multicast_bytes = MLX5_GET_CTR(out, received_ib_multicast.octets); + if (MLX5_CAP_GEN(priv->mdev, vport_counter_local_loopback)) { + rep_stats->vport_loopback_packets = + MLX5_GET_CTR(out, local_loopback.packets); + rep_stats->vport_loopback_bytes = + MLX5_GET_CTR(out, local_loopback.octets); + } + out: kvfree(out); } @@ -1152,12 +1180,6 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv) struct mlx5e_rep_priv *rpriv = priv->ppriv; int err; - err = mlx5e_create_tises(priv); - if (err) { - mlx5_core_warn(priv->mdev, "create tises failed, %d\n", err); - return err; - } - err = mlx5e_rep_neigh_init(rpriv); if (err) goto err_neigh_init; @@ -1180,7 +1202,6 @@ err_ht_init: err_init_tx: mlx5e_rep_neigh_cleanup(rpriv); err_neigh_init: - mlx5e_destroy_tises(priv); return err; } @@ -1194,7 +1215,6 @@ static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv) mlx5e_cleanup_uplink_rep_tx(rpriv); mlx5e_rep_neigh_cleanup(rpriv); - mlx5e_destroy_tises(priv); } static void mlx5e_rep_enable(struct mlx5e_priv *priv) @@ -1424,7 +1444,7 @@ static const struct mlx5e_profile mlx5e_uplink_rep_profile = { .update_stats = mlx5e_stats_update_ndo_stats, .update_carrier = mlx5e_update_carrier, .rx_handlers = &mlx5e_rx_handlers_rep, - .max_tc = MLX5E_MAX_NUM_TC, + .max_tc = MLX5_MAX_NUM_TC, .stats_grps = mlx5e_ul_rep_stats_grps, .stats_grps_num = mlx5e_ul_rep_stats_grps_num, }; @@ -1493,7 +1513,7 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch, rpriv->rep->vport); - if (dl_port) { + if (!IS_ERR(dl_port)) { SET_NETDEV_DEVLINK_PORT(netdev, dl_port); mlx5e_rep_vnic_reporter_create(priv, dl_port); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 8d9743a5e42c..d601b5faaed5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -298,8 +298,8 @@ static void mlx5e_page_release_fragmented(struct mlx5e_rq *rq, u16 drain_count = MLX5E_PAGECNT_BIAS_MAX - frag_page->frags; struct page *page = frag_page->page; - if (page_pool_defrag_page(page, drain_count) == 0) - page_pool_put_defragged_page(rq->page_pool, page, -1, true); + if (page_pool_unref_page(page, drain_count) == 0) + page_pool_put_unrefed_page(rq->page_pool, page, -1, true); } static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq, @@ -1039,7 +1039,7 @@ int mlx5e_poll_ico_cq(struct mlx5e_cq *cq) (struct mlx5_err_cqe *)cqe); mlx5_wq_cyc_wqe_dump(&sq->wq, ci, wi->num_wqebbs); if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) - queue_work(cq->priv->wq, &sq->recover_work); + queue_work(cq->workqueue, &sq->recover_work); break; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 477c547dcc04..12b3607afecd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -476,6 +476,8 @@ struct mlx5e_rep_stats { u64 tx_vport_rdma_multicast_packets; u64 rx_vport_rdma_multicast_bytes; u64 tx_vport_rdma_multicast_bytes; + u64 vport_loopback_packets; + u64 vport_loopback_bytes; }; struct mlx5e_stats { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 9a5a5c2c7da9..9fb2c057bd78 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -444,6 +444,9 @@ mlx5e_tc_add_flow_meter(struct mlx5e_priv *priv, struct mlx5e_flow_meter_handle *meter; enum mlx5e_post_meter_type type; + if (IS_ERR(post_act)) + return PTR_ERR(post_act); + meter = mlx5e_tc_meter_replace(priv->mdev, &attr->meter_attr.params); if (IS_ERR(meter)) { mlx5_core_err(priv->mdev, "Failed to get flow meter\n"); @@ -758,7 +761,7 @@ static int mlx5e_hairpin_create_indirect_rqt(struct mlx5e_hairpin *hp) err = mlx5e_rss_params_indir_init(&indir, mdev, mlx5e_rqt_size(mdev, hp->num_channels), - mlx5e_rqt_size(mdev, priv->max_nch)); + mlx5e_rqt_size(mdev, hp->num_channels)); if (err) return err; @@ -2011,9 +2014,10 @@ static void mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow, list_for_each_entry_safe(peer_flow, tmp, &flow->peer_flows, peer_flows) { if (peer_index != mlx5_get_dev_index(peer_flow->priv->mdev)) continue; + + list_del(&peer_flow->peer_flows); if (refcount_dec_and_test(&peer_flow->refcnt)) { mlx5e_tc_del_fdb_flow(peer_flow->priv, peer_flow); - list_del(&peer_flow->peer_flows); kfree(peer_flow); } } @@ -3147,7 +3151,7 @@ static struct mlx5_fields fields[] = { OFFLOAD(DIPV6_31_0, 32, U32_MAX, ip6.daddr.s6_addr32[3], 0, dst_ipv4_dst_ipv6.ipv6_layout.ipv6[12]), OFFLOAD(IPV6_HOPLIMIT, 8, U8_MAX, ip6.hop_limit, 0, ttl_hoplimit), - OFFLOAD(IP_DSCP, 16, 0xc00f, ip6, 0, ip_dscp), + OFFLOAD(IP_DSCP, 16, 0x0fc0, ip6, 0, ip_dscp), OFFLOAD(TCP_SPORT, 16, U16_MAX, tcp.source, 0, tcp_sport), OFFLOAD(TCP_DPORT, 16, U16_MAX, tcp.dest, 0, tcp_dport), @@ -3158,21 +3162,31 @@ static struct mlx5_fields fields[] = { OFFLOAD(UDP_DPORT, 16, U16_MAX, udp.dest, 0, udp_dport), }; -static unsigned long mask_to_le(unsigned long mask, int size) +static u32 mask_field_get(void *mask, struct mlx5_fields *f) { - __be32 mask_be32; - __be16 mask_be16; - - if (size == 32) { - mask_be32 = (__force __be32)(mask); - mask = (__force unsigned long)cpu_to_le32(be32_to_cpu(mask_be32)); - } else if (size == 16) { - mask_be32 = (__force __be32)(mask); - mask_be16 = *(__be16 *)&mask_be32; - mask = (__force unsigned long)cpu_to_le16(be16_to_cpu(mask_be16)); + switch (f->field_bsize) { + case 32: + return be32_to_cpu(*(__be32 *)mask) & f->field_mask; + case 16: + return be16_to_cpu(*(__be16 *)mask) & (u16)f->field_mask; + default: + return *(u8 *)mask & (u8)f->field_mask; } +} - return mask; +static void mask_field_clear(void *mask, struct mlx5_fields *f) +{ + switch (f->field_bsize) { + case 32: + *(__be32 *)mask &= ~cpu_to_be32(f->field_mask); + break; + case 16: + *(__be16 *)mask &= ~cpu_to_be16((u16)f->field_mask); + break; + default: + *(u8 *)mask &= ~(u8)f->field_mask; + break; + } } static int offload_pedit_fields(struct mlx5e_priv *priv, @@ -3184,35 +3198,32 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, struct pedit_headers *set_masks, *add_masks, *set_vals, *add_vals; struct pedit_headers_action *hdrs = parse_attr->hdrs; void *headers_c, *headers_v, *action, *vals_p; - u32 *s_masks_p, *a_masks_p, s_mask, a_mask; struct mlx5e_tc_mod_hdr_acts *mod_acts; - unsigned long mask, field_mask; + void *s_masks_p, *a_masks_p; int i, first, last, next_z; struct mlx5_fields *f; + unsigned long mask; + u32 s_mask, a_mask; u8 cmd; mod_acts = &parse_attr->mod_hdr_acts; headers_c = mlx5e_get_match_headers_criteria(*action_flags, &parse_attr->spec); headers_v = mlx5e_get_match_headers_value(*action_flags, &parse_attr->spec); - set_masks = &hdrs[0].masks; - add_masks = &hdrs[1].masks; - set_vals = &hdrs[0].vals; - add_vals = &hdrs[1].vals; + set_masks = &hdrs[TCA_PEDIT_KEY_EX_CMD_SET].masks; + add_masks = &hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].masks; + set_vals = &hdrs[TCA_PEDIT_KEY_EX_CMD_SET].vals; + add_vals = &hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].vals; for (i = 0; i < ARRAY_SIZE(fields); i++) { bool skip; f = &fields[i]; - /* avoid seeing bits set from previous iterations */ - s_mask = 0; - a_mask = 0; - s_masks_p = (void *)set_masks + f->offset; a_masks_p = (void *)add_masks + f->offset; - s_mask = *s_masks_p & f->field_mask; - a_mask = *a_masks_p & f->field_mask; + s_mask = mask_field_get(s_masks_p, f); + a_mask = mask_field_get(a_masks_p, f); if (!s_mask && !a_mask) /* nothing to offload here */ continue; @@ -3239,22 +3250,20 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, match_mask, f->field_bsize)) skip = true; /* clear to denote we consumed this field */ - *s_masks_p &= ~f->field_mask; + mask_field_clear(s_masks_p, f); } else { cmd = MLX5_ACTION_TYPE_ADD; mask = a_mask; vals_p = (void *)add_vals + f->offset; /* add 0 is no change */ - if ((*(u32 *)vals_p & f->field_mask) == 0) + if (!mask_field_get(vals_p, f)) skip = true; /* clear to denote we consumed this field */ - *a_masks_p &= ~f->field_mask; + mask_field_clear(a_masks_p, f); } if (skip) continue; - mask = mask_to_le(mask, f->field_bsize); - first = find_first_bit(&mask, f->field_bsize); next_z = find_next_zero_bit(&mask, f->field_bsize, first); last = find_last_bit(&mask, f->field_bsize); @@ -3281,10 +3290,9 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, MLX5_SET(set_action_in, action, field, f->field); if (cmd == MLX5_ACTION_TYPE_SET) { + unsigned long field_mask = f->field_mask; int start; - field_mask = mask_to_le(f->field_mask, f->field_bsize); - /* if field is bit sized it can start not from first bit */ start = find_first_bit(&field_mask, f->field_bsize); @@ -3735,6 +3743,20 @@ out_free: } static int +set_branch_dest_ft(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr) +{ + struct mlx5e_post_act *post_act = get_post_action(priv); + + if (IS_ERR(post_act)) + return PTR_ERR(post_act); + + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + attr->dest_ft = mlx5e_tc_post_act_get_ft(post_act); + + return 0; +} + +static int alloc_branch_attr(struct mlx5e_tc_flow *flow, struct mlx5e_tc_act_branch_ctrl *cond, struct mlx5_flow_attr **cond_attr, @@ -3757,8 +3779,9 @@ alloc_branch_attr(struct mlx5e_tc_flow *flow, break; case FLOW_ACTION_ACCEPT: case FLOW_ACTION_PIPE: - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - attr->dest_ft = mlx5e_tc_post_act_get_ft(get_post_action(flow->priv)); + err = set_branch_dest_ft(flow->priv, attr); + if (err) + goto out_err; break; case FLOW_ACTION_JUMP: if (*jump_count) { @@ -3767,8 +3790,9 @@ alloc_branch_attr(struct mlx5e_tc_flow *flow, goto out_err; } *jump_count = cond->extval; - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - attr->dest_ft = mlx5e_tc_post_act_get_ft(get_post_action(flow->priv)); + err = set_branch_dest_ft(flow->priv, attr); + if (err) + goto out_err; break; default: err = -EOPNOTSUPP; @@ -5007,22 +5031,6 @@ int mlx5e_tc_delete_matchall(struct mlx5e_priv *priv, return apply_police_params(priv, 0, extack); } -void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv, - struct tc_cls_matchall_offload *ma) -{ - struct mlx5e_rep_priv *rpriv = priv->ppriv; - struct rtnl_link_stats64 cur_stats; - u64 dbytes; - u64 dpkts; - - mlx5e_stats_copy_rep_stats(&cur_stats, &priv->stats.rep_stats); - dpkts = cur_stats.rx_packets - rpriv->prev_vf_vport_stats.rx_packets; - dbytes = cur_stats.rx_bytes - rpriv->prev_vf_vport_stats.rx_bytes; - rpriv->prev_vf_vport_stats = cur_stats; - flow_stats_update(&ma->stats, dbytes, dpkts, 0, jiffies, - FLOW_ACTION_HW_STATS_DELAYED); -} - static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv) { @@ -5715,8 +5723,10 @@ int mlx5e_tc_action_miss_mapping_get(struct mlx5e_priv *priv, struct mlx5_flow_a esw = priv->mdev->priv.eswitch; attr->act_id_restore_rule = esw_add_restore_rule(esw, *act_miss_mapping); - if (IS_ERR(attr->act_id_restore_rule)) + if (IS_ERR(attr->act_id_restore_rule)) { + err = PTR_ERR(attr->act_id_restore_rule); goto err_rule; + } return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index adb39e30f90f..c24bda56b2b5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -203,8 +203,6 @@ int mlx5e_tc_configure_matchall(struct mlx5e_priv *priv, struct tc_cls_matchall_offload *f); int mlx5e_tc_delete_matchall(struct mlx5e_priv *priv, struct tc_cls_matchall_offload *f); -void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv, - struct tc_cls_matchall_offload *ma); struct mlx5e_encap_entry; void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index d41435c22ce5..2fa076b23fbe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -399,9 +399,11 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb, u8 metadata_index = be32_to_cpu(eseg->flow_table_metadata); mlx5e_skb_cb_hwtstamp_init(skb); - mlx5e_ptpsq_track_metadata(sq->ptpsq, metadata_index); mlx5e_ptp_metadata_map_put(&sq->ptpsq->metadata_map, skb, metadata_index); + /* ensure skb is put on metadata_map before tracking the index */ + wmb(); + mlx5e_ptpsq_track_metadata(sq->ptpsq, metadata_index); if (!netif_tx_queue_stopped(sq->txq) && mlx5e_ptpsq_metadata_freelist_empty(sq->ptpsq)) { netif_tx_stop_queue(sq->txq); @@ -494,10 +496,10 @@ mlx5e_sq_xmit_wqe(struct mlx5e_txqsq *sq, struct sk_buff *skb, err_drop: stats->dropped++; - dev_kfree_skb_any(skb); if (unlikely(sq->ptpsq && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))) mlx5e_ptp_metadata_fifo_push(&sq->ptpsq->metadata_freelist, be32_to_cpu(eseg->flow_table_metadata)); + dev_kfree_skb_any(skb); mlx5e_tx_flush(sq); } @@ -861,7 +863,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) mlx5e_dump_error_cqe(&sq->cq, sq->sqn, (struct mlx5_err_cqe *)cqe); mlx5_wq_cyc_wqe_dump(&sq->wq, ci, wi->num_wqebbs); - queue_work(cq->priv->wq, &sq->recover_work); + queue_work(cq->workqueue, &sq->recover_work); } stats->cqe_err++; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index ea0405e0a43f..40a6cb052a2d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -885,11 +885,14 @@ static void comp_irq_release_sf(struct mlx5_core_dev *dev, u16 vecidx) { struct mlx5_eq_table *table = dev->priv.eq_table; struct mlx5_irq *irq; + int cpu; irq = xa_load(&table->comp_irqs, vecidx); if (!irq) return; + cpu = cpumask_first(mlx5_irq_get_affinity_mask(irq)); + cpumask_clear_cpu(cpu, &table->used_cpus); xa_erase(&table->comp_irqs, vecidx); mlx5_irq_affinity_irq_release(dev, irq); } @@ -897,16 +900,26 @@ static void comp_irq_release_sf(struct mlx5_core_dev *dev, u16 vecidx) static int comp_irq_request_sf(struct mlx5_core_dev *dev, u16 vecidx) { struct mlx5_eq_table *table = dev->priv.eq_table; + struct mlx5_irq_pool *pool = mlx5_irq_pool_get(dev); + struct irq_affinity_desc af_desc = {}; struct mlx5_irq *irq; - irq = mlx5_irq_affinity_irq_request_auto(dev, &table->used_cpus, vecidx); - if (IS_ERR(irq)) { - /* In case SF irq pool does not exist, fallback to the PF irqs*/ - if (PTR_ERR(irq) == -ENOENT) - return comp_irq_request_pci(dev, vecidx); + /* In case SF irq pool does not exist, fallback to the PF irqs*/ + if (!mlx5_irq_pool_is_sf_pool(pool)) + return comp_irq_request_pci(dev, vecidx); + af_desc.is_managed = 1; + cpumask_copy(&af_desc.mask, cpu_online_mask); + cpumask_andnot(&af_desc.mask, &af_desc.mask, &table->used_cpus); + irq = mlx5_irq_affinity_request(pool, &af_desc); + if (IS_ERR(irq)) return PTR_ERR(irq); - } + + cpumask_or(&table->used_cpus, &table->used_cpus, mlx5_irq_get_affinity_mask(irq)); + mlx5_core_dbg(pool->dev, "IRQ %u mapped to cpu %*pbl, %u EQs on this irq\n", + pci_irq_vector(dev->pdev, mlx5_irq_get_index(irq)), + cpumask_pr_args(mlx5_irq_get_affinity_mask(irq)), + mlx5_irq_read_locked(irq) / MLX5_EQ_REFS_PER_IRQ); return xa_err(xa_store(&table->comp_irqs, vecidx, irq, GFP_KERNEL)); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c index a7ed87e9d842..22dd30cf8033 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c @@ -83,6 +83,7 @@ mlx5_esw_bridge_mdb_flow_create(u16 esw_owner_vhca_id, struct mlx5_esw_bridge_md i++; } + rule_spec->flow_context.flags |= FLOW_CONTEXT_UPLINK_HAIRPIN_EN; rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; dmac_v = MLX5_ADDR_OF(fte_match_param, rule_spec->match_value, outer_headers.dmac_47_16); ether_addr_copy(dmac_v, entry->key.addr); @@ -587,6 +588,7 @@ mlx5_esw_bridge_mcast_vlan_flow_create(u16 vlan_proto, struct mlx5_esw_bridge_po if (!rule_spec) return ERR_PTR(-ENOMEM); + rule_spec->flow_context.flags |= FLOW_CONTEXT_UPLINK_HAIRPIN_EN; rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; @@ -662,6 +664,7 @@ mlx5_esw_bridge_mcast_fwd_flow_create(struct mlx5_esw_bridge_port *port) dest.vport.flags = MLX5_FLOW_DEST_VPORT_VHCA_ID; dest.vport.vhca_id = port->esw_owner_vhca_id; } + rule_spec->flow_context.flags |= FLOW_CONTEXT_UPLINK_HAIRPIN_EN; handle = mlx5_add_flow_rules(port->mcast.ft, rule_spec, &flow_act, &dest, 1); kvfree(rule_spec); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c index 095f31f380fa..5a0047bdcb51 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c @@ -21,158 +21,6 @@ enum { MLX5_ESW_IPSEC_TX_ESP_FT_CNT_LEVEL, }; -static void esw_ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx) -{ - mlx5_del_flow_rules(rx->status_drop.rule); - mlx5_destroy_flow_group(rx->status_drop.group); - mlx5_fc_destroy(ipsec->mdev, rx->status_drop_cnt); -} - -static void esw_ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx) -{ - mlx5_del_flow_rules(rx->status.rule); - mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch), 0, 1, 0); -} - -static int esw_ipsec_rx_status_drop_create(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx) -{ - int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); - struct mlx5_flow_table *ft = rx->ft.status; - struct mlx5_core_dev *mdev = ipsec->mdev; - struct mlx5_flow_destination dest = {}; - struct mlx5_flow_act flow_act = {}; - struct mlx5_flow_handle *rule; - struct mlx5_fc *flow_counter; - struct mlx5_flow_spec *spec; - struct mlx5_flow_group *g; - u32 *flow_group_in; - int err = 0; - - flow_group_in = kvzalloc(inlen, GFP_KERNEL); - spec = kvzalloc(sizeof(*spec), GFP_KERNEL); - if (!flow_group_in || !spec) { - err = -ENOMEM; - goto err_out; - } - - MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ft->max_fte - 1); - MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ft->max_fte - 1); - g = mlx5_create_flow_group(ft, flow_group_in); - if (IS_ERR(g)) { - err = PTR_ERR(g); - mlx5_core_err(mdev, - "Failed to add ipsec rx status drop flow group, err=%d\n", err); - goto err_out; - } - - flow_counter = mlx5_fc_create(mdev, false); - if (IS_ERR(flow_counter)) { - err = PTR_ERR(flow_counter); - mlx5_core_err(mdev, - "Failed to add ipsec rx status drop rule counter, err=%d\n", err); - goto err_cnt; - } - - flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; - dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest.counter_id = mlx5_fc_id(flow_counter); - spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; - rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); - if (IS_ERR(rule)) { - err = PTR_ERR(rule); - mlx5_core_err(mdev, - "Failed to add ipsec rx status drop rule, err=%d\n", err); - goto err_rule; - } - - rx->status_drop.group = g; - rx->status_drop.rule = rule; - rx->status_drop_cnt = flow_counter; - - kvfree(flow_group_in); - kvfree(spec); - return 0; - -err_rule: - mlx5_fc_destroy(mdev, flow_counter); -err_cnt: - mlx5_destroy_flow_group(g); -err_out: - kvfree(flow_group_in); - kvfree(spec); - return err; -} - -static int esw_ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx, - struct mlx5_flow_destination *dest) -{ - struct mlx5_flow_act flow_act = {}; - struct mlx5_flow_handle *rule; - struct mlx5_flow_spec *spec; - int err; - - spec = kvzalloc(sizeof(*spec), GFP_KERNEL); - if (!spec) - return -ENOMEM; - - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, - misc_parameters_2.ipsec_syndrome); - MLX5_SET(fte_match_param, spec->match_value, - misc_parameters_2.ipsec_syndrome, 0); - spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; - spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2; - flow_act.flags = FLOW_ACT_NO_APPEND; - flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_COUNT; - rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2); - if (IS_ERR(rule)) { - err = PTR_ERR(rule); - mlx5_core_warn(ipsec->mdev, - "Failed to add ipsec rx status pass rule, err=%d\n", err); - goto err_rule; - } - - rx->status.rule = rule; - kvfree(spec); - return 0; - -err_rule: - kvfree(spec); - return err; -} - -void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx) -{ - esw_ipsec_rx_status_pass_destroy(ipsec, rx); - esw_ipsec_rx_status_drop_destroy(ipsec, rx); -} - -int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx, - struct mlx5_flow_destination *dest) -{ - int err; - - err = esw_ipsec_rx_status_drop_create(ipsec, rx); - if (err) - return err; - - err = esw_ipsec_rx_status_pass_create(ipsec, rx, dest); - if (err) - goto err_pass_create; - - return 0; - -err_pass_create: - esw_ipsec_rx_status_drop_destroy(ipsec, rx); - return err; -} - void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx_create_attr *attr) { @@ -202,7 +50,7 @@ int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry, u32 mapped_id; int err; - err = xa_alloc_bh(&ipsec->rx_esw->ipsec_obj_id_map, &mapped_id, + err = xa_alloc_bh(&ipsec->ipsec_obj_id_map, &mapped_id, xa_mk_value(sa_entry->ipsec_obj_id), XA_LIMIT(1, ESW_IPSEC_RX_MAPPED_ID_MASK), 0); if (err) @@ -233,7 +81,7 @@ int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry, return 0; err_header_alloc: - xa_erase_bh(&ipsec->rx_esw->ipsec_obj_id_map, mapped_id); + xa_erase_bh(&ipsec->ipsec_obj_id_map, mapped_id); return err; } @@ -242,7 +90,7 @@ void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry) struct mlx5e_ipsec *ipsec = sa_entry->ipsec; if (sa_entry->rx_mapped_id) - xa_erase_bh(&ipsec->rx_esw->ipsec_obj_id_map, + xa_erase_bh(&ipsec->ipsec_obj_id_map, sa_entry->rx_mapped_id); } @@ -252,7 +100,7 @@ int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id, struct mlx5e_ipsec *ipsec = priv->ipsec; void *val; - val = xa_load(&ipsec->rx_esw->ipsec_obj_id_map, id); + val = xa_load(&ipsec->ipsec_obj_id_map, id); if (!val) return -ENOENT; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h index 0c90f7a8b0d3..ac9c65b89166 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h @@ -8,11 +8,6 @@ struct mlx5e_ipsec; struct mlx5e_ipsec_sa_entry; #ifdef CONFIG_MLX5_ESWITCH -void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx); -int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx, - struct mlx5_flow_destination *dest); void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx_create_attr *attr); int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec, @@ -26,16 +21,6 @@ void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx_create_attr *attr); void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev); #else -static inline void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx) {} - -static inline int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx, - struct mlx5_flow_destination *dest) -{ - return -EINVAL; -} - static inline void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx_create_attr *attr) {} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 8d0b915a3121..3047d7015c52 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1463,7 +1463,7 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int num_vfs) { int err; - lockdep_assert_held(&esw->mode_lock); + devl_assert_locked(priv_to_devlink(esw->dev)); if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) { esw_warn(esw->dev, "FDB is not supported, aborting ...\n"); @@ -1531,7 +1531,6 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) if (toggle_lag) mlx5_lag_disable_change(esw->dev); - down_write(&esw->mode_lock); if (!mlx5_esw_is_fdb_created(esw)) { ret = mlx5_eswitch_enable_locked(esw, num_vfs); } else { @@ -1554,8 +1553,6 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) } } - up_write(&esw->mode_lock); - if (toggle_lag) mlx5_lag_enable_change(esw->dev); @@ -1569,12 +1566,11 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf) return; devl_assert_locked(priv_to_devlink(esw->dev)); - down_write(&esw->mode_lock); /* If driver is unloaded, this function is called twice by remove_one() * and mlx5_unload(). Prevent the second call. */ if (!esw->esw_funcs.num_vfs && !esw->esw_funcs.num_ec_vfs && !clear_vf) - goto unlock; + return; esw_info(esw->dev, "Unload vfs: mode(%s), nvfs(%d), necvfs(%d), active vports(%d)\n", esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS", @@ -1603,9 +1599,6 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf) esw->esw_funcs.num_vfs = 0; else esw->esw_funcs.num_ec_vfs = 0; - -unlock: - up_write(&esw->mode_lock); } /* Free resources for corresponding eswitch mode. It is called by devlink @@ -1647,10 +1640,8 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw) devl_assert_locked(priv_to_devlink(esw->dev)); mlx5_lag_disable_change(esw->dev); - down_write(&esw->mode_lock); mlx5_eswitch_disable_locked(esw); esw->mode = MLX5_ESWITCH_LEGACY; - up_write(&esw->mode_lock); mlx5_lag_enable_change(esw->dev); } @@ -2254,8 +2245,13 @@ bool mlx5_esw_hold(struct mlx5_core_dev *mdev) if (!mlx5_esw_allowed(esw)) return true; - if (down_read_trylock(&esw->mode_lock) != 0) + if (down_read_trylock(&esw->mode_lock) != 0) { + if (esw->eswitch_operation_in_progress) { + up_read(&esw->mode_lock); + return false; + } return true; + } return false; } @@ -2312,7 +2308,8 @@ int mlx5_esw_try_lock(struct mlx5_eswitch *esw) if (down_write_trylock(&esw->mode_lock) == 0) return -EINVAL; - if (atomic64_read(&esw->user_count) > 0) { + if (esw->eswitch_operation_in_progress || + atomic64_read(&esw->user_count) > 0) { up_write(&esw->mode_lock); return -EBUSY; } @@ -2320,6 +2317,18 @@ int mlx5_esw_try_lock(struct mlx5_eswitch *esw) return esw->mode; } +int mlx5_esw_lock(struct mlx5_eswitch *esw) +{ + down_write(&esw->mode_lock); + + if (esw->eswitch_operation_in_progress) { + up_write(&esw->mode_lock); + return -EBUSY; + } + + return 0; +} + /** * mlx5_esw_unlock() - Release write lock on esw mode lock * @esw: eswitch device. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 37ab66e7b403..349e28a6dd8d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -383,6 +383,7 @@ struct mlx5_eswitch { struct xarray paired; struct mlx5_devcom_comp_dev *devcom; u16 enabled_ipsec_vf_count; + bool eswitch_operation_in_progress; }; void esw_offloads_disable(struct mlx5_eswitch *esw); @@ -525,7 +526,8 @@ struct mlx5_esw_flow_attr { u8 total_vlan; struct { u32 flags; - struct mlx5_eswitch_rep *rep; + bool vport_valid; + u16 vport; struct mlx5_pkt_reformat *pkt_reformat; struct mlx5_core_dev *mdev; struct mlx5_termtbl_handle *termtbl; @@ -616,13 +618,6 @@ static inline bool mlx5_esw_allowed(const struct mlx5_eswitch *esw) return esw && MLX5_ESWITCH_MANAGER(esw->dev); } -/* The returned number is valid only when the dev is eswitch manager. */ -static inline u16 mlx5_eswitch_manager_vport(struct mlx5_core_dev *dev) -{ - return mlx5_core_is_ecpf_esw_manager(dev) ? - MLX5_VPORT_ECPF : MLX5_VPORT_PF; -} - static inline bool mlx5_esw_is_manager_vport(const struct mlx5_eswitch *esw, u16 vport_num) { @@ -827,6 +822,7 @@ void mlx5_esw_release(struct mlx5_core_dev *dev); void mlx5_esw_get(struct mlx5_core_dev *dev); void mlx5_esw_put(struct mlx5_core_dev *dev); int mlx5_esw_try_lock(struct mlx5_eswitch *esw); +int mlx5_esw_lock(struct mlx5_eswitch *esw); void mlx5_esw_unlock(struct mlx5_eswitch *esw); void esw_vport_change_handle_locked(struct mlx5_vport *vport); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index b296ac52a439..baaae628b0a0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -287,10 +287,9 @@ static void esw_put_dest_tables_loop(struct mlx5_eswitch *esw, struct mlx5_flow_ for (i = from; i < to; i++) if (esw_attr->dests[i].flags & MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE) mlx5_chains_put_table(chains, 0, 1, 0); - else if (mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].rep->vport, + else if (mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].vport, esw_attr->dests[i].mdev)) - mlx5_esw_indir_table_put(esw, esw_attr->dests[i].rep->vport, - false); + mlx5_esw_indir_table_put(esw, esw_attr->dests[i].vport, false); } static bool @@ -358,8 +357,8 @@ esw_is_indir_table(struct mlx5_eswitch *esw, struct mlx5_flow_attr *attr) * this criteria. */ for (i = esw_attr->split_count; i < esw_attr->out_count; i++) { - if (esw_attr->dests[i].rep && - mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].rep->vport, + if (esw_attr->dests[i].vport_valid && + mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].vport, esw_attr->dests[i].mdev)) { result = true; } else { @@ -388,7 +387,7 @@ esw_setup_indir_table(struct mlx5_flow_destination *dest, dest[*i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; dest[*i].ft = mlx5_esw_indir_table_get(esw, attr, - esw_attr->dests[j].rep->vport, false); + esw_attr->dests[j].vport, false); if (IS_ERR(dest[*i].ft)) { err = PTR_ERR(dest[*i].ft); goto err_indir_tbl_get; @@ -432,11 +431,11 @@ static bool esw_setup_uplink_fwd_ipsec_needed(struct mlx5_eswitch *esw, int attr_idx) { if (esw->offloads.ft_ipsec_tx_pol && - esw_attr->dests[attr_idx].rep && - esw_attr->dests[attr_idx].rep->vport == MLX5_VPORT_UPLINK && + esw_attr->dests[attr_idx].vport_valid && + esw_attr->dests[attr_idx].vport == MLX5_VPORT_UPLINK && /* To be aligned with software, encryption is needed only for tunnel device */ (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP_VALID) && - esw_attr->dests[attr_idx].rep != esw_attr->in_rep && + esw_attr->dests[attr_idx].vport != esw_attr->in_rep->vport && esw_same_vhca_id(esw_attr->dests[attr_idx].mdev, esw->dev)) return true; @@ -469,7 +468,7 @@ esw_setup_dest_fwd_vport(struct mlx5_flow_destination *dest, struct mlx5_flow_ac int attr_idx, int dest_idx, bool pkt_reformat) { dest[dest_idx].type = MLX5_FLOW_DESTINATION_TYPE_VPORT; - dest[dest_idx].vport.num = esw_attr->dests[attr_idx].rep->vport; + dest[dest_idx].vport.num = esw_attr->dests[attr_idx].vport; if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) { dest[dest_idx].vport.vhca_id = MLX5_CAP_GEN(esw_attr->dests[attr_idx].mdev, vhca_id); @@ -536,21 +535,26 @@ esw_src_port_rewrite_supported(struct mlx5_eswitch *esw) } static bool -esw_dests_to_vf_pf_vports(struct mlx5_flow_destination *dests, int max_dest) +esw_dests_to_int_external(struct mlx5_flow_destination *dests, int max_dest) { - bool vf_dest = false, pf_dest = false; + bool internal_dest = false, external_dest = false; int i; for (i = 0; i < max_dest; i++) { - if (dests[i].type != MLX5_FLOW_DESTINATION_TYPE_VPORT) + if (dests[i].type != MLX5_FLOW_DESTINATION_TYPE_VPORT && + dests[i].type != MLX5_FLOW_DESTINATION_TYPE_UPLINK) continue; - if (dests[i].vport.num == MLX5_VPORT_UPLINK) - pf_dest = true; + /* Uplink dest is external, but considered as internal + * if there is reformat because firmware uses LB+hairpin to support it. + */ + if (dests[i].vport.num == MLX5_VPORT_UPLINK && + !(dests[i].vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID)) + external_dest = true; else - vf_dest = true; + internal_dest = true; - if (vf_dest && pf_dest) + if (internal_dest && external_dest) return true; } @@ -696,9 +700,9 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, /* Header rewrite with combined wire+loopback in FDB is not allowed */ if ((flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) && - esw_dests_to_vf_pf_vports(dest, i)) { + esw_dests_to_int_external(dest, i)) { esw_warn(esw->dev, - "FDB: Header rewrite with forwarding to both PF and VF is not allowed\n"); + "FDB: Header rewrite with forwarding to both internal and external dests is not allowed\n"); rule = ERR_PTR(-EINVAL); goto err_esw_get; } @@ -984,7 +988,8 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw, dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - if (rep->vport == MLX5_VPORT_UPLINK && on_esw->offloads.ft_ipsec_tx_pol) { + if (rep->vport == MLX5_VPORT_UPLINK && + on_esw == from_esw && on_esw->offloads.ft_ipsec_tx_pol) { dest.ft = on_esw->offloads.ft_ipsec_tx_pol; flow_act.flags = FLOW_ACT_IGNORE_FLOW_LEVEL; dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; @@ -1176,9 +1181,9 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, struct mlx5_flow_handle *flow; struct mlx5_flow_spec *spec; struct mlx5_vport *vport; + int err, pfindex; unsigned long i; void *misc; - int err; if (!MLX5_VPORT_MANAGER(esw->dev) && !mlx5_core_is_ecpf_esw_manager(esw->dev)) return 0; @@ -1254,7 +1259,15 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, flows[vport->index] = flow; } } - esw->fdb_table.offloads.peer_miss_rules[mlx5_get_dev_index(peer_dev)] = flows; + + pfindex = mlx5_get_dev_index(peer_dev); + if (pfindex >= MLX5_MAX_PORTS) { + esw_warn(esw->dev, "Peer dev index(%d) is over the max num defined(%d)\n", + pfindex, MLX5_MAX_PORTS); + err = -EINVAL; + goto add_ec_vf_flow_err; + } + esw->fdb_table.offloads.peer_miss_rules[pfindex] = flows; kvfree(spec); return 0; @@ -3650,18 +3663,6 @@ static int esw_inline_mode_to_devlink(u8 mlx5_mode, u8 *mode) return 0; } -static bool esw_offloads_devlink_ns_eq_netdev_ns(struct devlink *devlink) -{ - struct net *devl_net, *netdev_net; - struct mlx5_eswitch *esw; - - esw = mlx5_devlink_eswitch_nocheck_get(devlink); - netdev_net = dev_net(esw->dev->mlx5e_res.uplink_netdev); - devl_net = devlink_net(devlink); - - return net_eq(devl_net, netdev_net); -} - int mlx5_eswitch_block_mode(struct mlx5_core_dev *dev) { struct mlx5_eswitch *esw = dev->priv.eswitch; @@ -3706,13 +3707,6 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, if (esw_mode_from_devlink(mode, &mlx5_mode)) return -EINVAL; - if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV && - !esw_offloads_devlink_ns_eq_netdev_ns(devlink)) { - NL_SET_ERR_MSG_MOD(extack, - "Can't change E-Switch mode to switchdev when netdev net namespace has diverged from the devlink's."); - return -EPERM; - } - mlx5_lag_disable_change(esw->dev); err = mlx5_esw_try_lock(esw); if (err < 0) { @@ -3732,13 +3726,16 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, goto unlock; } + esw->eswitch_operation_in_progress = true; + up_write(&esw->mode_lock); + mlx5_eswitch_disable_locked(esw); if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) { if (mlx5_devlink_trap_get_num_active(esw->dev)) { NL_SET_ERR_MSG_MOD(extack, "Can't change mode while devlink traps are active"); err = -EOPNOTSUPP; - goto unlock; + goto skip; } err = esw_offloads_start(esw, extack); } else if (mode == DEVLINK_ESWITCH_MODE_LEGACY) { @@ -3748,6 +3745,9 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, err = -EINVAL; } +skip: + down_write(&esw->mode_lock); + esw->eswitch_operation_in_progress = false; unlock: mlx5_esw_unlock(esw); enable_lag: @@ -3758,16 +3758,12 @@ enable_lag: int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode) { struct mlx5_eswitch *esw; - int err; esw = mlx5_devlink_eswitch_get(devlink); if (IS_ERR(esw)) return PTR_ERR(esw); - down_read(&esw->mode_lock); - err = esw_mode_to_devlink(esw->mode, mode); - up_read(&esw->mode_lock); - return err; + return esw_mode_to_devlink(esw->mode, mode); } static int mlx5_esw_vports_inline_set(struct mlx5_eswitch *esw, u8 mlx5_mode, @@ -3861,11 +3857,15 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode, if (err) goto out; + esw->eswitch_operation_in_progress = true; + up_write(&esw->mode_lock); + err = mlx5_esw_vports_inline_set(esw, mlx5_mode, extack); - if (err) - goto out; + if (!err) + esw->offloads.inline_mode = mlx5_mode; - esw->offloads.inline_mode = mlx5_mode; + down_write(&esw->mode_lock); + esw->eswitch_operation_in_progress = false; up_write(&esw->mode_lock); return 0; @@ -3877,16 +3877,12 @@ out: int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode) { struct mlx5_eswitch *esw; - int err; esw = mlx5_devlink_eswitch_get(devlink); if (IS_ERR(esw)) return PTR_ERR(esw); - down_read(&esw->mode_lock); - err = esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode); - up_read(&esw->mode_lock); - return err; + return esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode); } bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev) @@ -3968,6 +3964,9 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, goto unlock; } + esw->eswitch_operation_in_progress = true; + up_write(&esw->mode_lock); + esw_destroy_offloads_fdb_tables(esw); esw->offloads.encap = encap; @@ -3981,6 +3980,9 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, (void)esw_create_offloads_fdb_tables(esw); } + down_write(&esw->mode_lock); + esw->eswitch_operation_in_progress = false; + unlock: up_write(&esw->mode_lock); return err; @@ -3995,9 +3997,7 @@ int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, if (IS_ERR(esw)) return PTR_ERR(esw); - down_read(&esw->mode_lock); *encap = esw->offloads.encap; - up_read(&esw->mode_lock); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c index edd910258314..40bdc677f051 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c @@ -233,8 +233,8 @@ mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw, /* hairpin */ for (i = esw_attr->split_count; i < esw_attr->out_count; i++) - if (!esw_attr->dest_int_port && esw_attr->dests[i].rep && - esw_attr->dests[i].rep->vport == MLX5_VPORT_UPLINK) + if (!esw_attr->dest_int_port && esw_attr->dests[i].vport_valid && + esw_attr->dests[i].vport == MLX5_VPORT_UPLINK) return true; return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index a4b925331661..9b8599c200e2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -566,6 +566,8 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, fte->flow_context.flow_tag); MLX5_SET(flow_context, in_flow_context, flow_source, fte->flow_context.flow_source); + MLX5_SET(flow_context, in_flow_context, uplink_hairpin_en, + !!(fte->flow_context.flags & FLOW_CONTEXT_UPLINK_HAIRPIN_EN)); MLX5_SET(flow_context, in_flow_context, extended_destination, extended_dest); @@ -1144,3 +1146,37 @@ const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type typ return mlx5_fs_cmd_get_stub_cmds(); } } + +int mlx5_fs_cmd_set_l2table_entry_silent(struct mlx5_core_dev *dev, u8 silent_mode) +{ + u32 in[MLX5_ST_SZ_DW(set_l2_table_entry_in)] = {}; + + if (silent_mode && !MLX5_CAP_GEN(dev, silent_mode)) + return -EOPNOTSUPP; + + MLX5_SET(set_l2_table_entry_in, in, opcode, MLX5_CMD_OP_SET_L2_TABLE_ENTRY); + MLX5_SET(set_l2_table_entry_in, in, silent_mode_valid, 1); + MLX5_SET(set_l2_table_entry_in, in, silent_mode, silent_mode); + + return mlx5_cmd_exec_in(dev, set_l2_table_entry, in); +} + +int mlx5_fs_cmd_set_tx_flow_table_root(struct mlx5_core_dev *dev, u32 ft_id, bool disconnect) +{ + u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {}; + u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)] = {}; + + if (disconnect && MLX5_CAP_FLOWTABLE_NIC_TX(dev, reset_root_to_default)) + return -EOPNOTSUPP; + + MLX5_SET(set_flow_table_root_in, in, opcode, + MLX5_CMD_OP_SET_FLOW_TABLE_ROOT); + MLX5_SET(set_flow_table_root_in, in, table_type, + FS_FT_NIC_TX); + if (disconnect) + MLX5_SET(set_flow_table_root_in, in, op_mod, 1); + else + MLX5_SET(set_flow_table_root_in, in, table_id, ft_id); + + return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index 7790ae5531e1..53e0e5137d3f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -122,4 +122,6 @@ int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len, const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type type); const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void); +int mlx5_fs_cmd_set_l2table_entry_silent(struct mlx5_core_dev *dev, u8 silent_mode); +int mlx5_fs_cmd_set_tx_flow_table_root(struct mlx5_core_dev *dev, u32 ft_id, bool disconnect); #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 4aed1768b85f..78eb6b7097e1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -181,7 +181,7 @@ struct mlx5_flow_rule { struct mlx5_flow_handle { int num_rules; - struct mlx5_flow_rule *rule[]; + struct mlx5_flow_rule *rule[] __counted_by(num_rules); }; /* Type of children is mlx5_flow_group */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index 17fe30a4c06c..0c26d707eed2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -539,7 +539,7 @@ struct mlx5_fc_bulk { u32 base_id; int bulk_len; unsigned long *bitmask; - struct mlx5_fc fcs[]; + struct mlx5_fc fcs[] __counted_by(bulk_len); }; static void mlx5_fc_init(struct mlx5_fc *counter, struct mlx5_fc_bulk *bulk, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index 58f4c0d0fafa..e7faf7e73ca4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -366,18 +366,18 @@ int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev) return -EIO; } - mlx5_set_nic_state(dev, MLX5_NIC_IFC_DISABLED); + mlx5_set_nic_state(dev, MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED); /* Loop until device state turns to disable */ end = jiffies + msecs_to_jiffies(delay_ms); do { - if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED) + if (mlx5_get_nic_state(dev) == MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED) break; cond_resched(); } while (!time_after(jiffies, end)); - if (mlx5_get_nic_state(dev) != MLX5_NIC_IFC_DISABLED) { + if (mlx5_get_nic_state(dev) != MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED) { dev_err(&dev->pdev->dev, "NIC IFC still %d after %lums.\n", mlx5_get_nic_state(dev), delay_ms); return -EIO; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index b568988e92e3..2911aa34a5be 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -325,6 +325,48 @@ static void mlx5_fw_live_patch_event(struct work_struct *work) mlx5_core_err(dev, "Failed to reload FW tracer\n"); } +#if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE) +static int mlx5_check_hotplug_interrupt(struct mlx5_core_dev *dev) +{ + struct pci_dev *bridge = dev->pdev->bus->self; + u16 reg16; + int err; + + if (!bridge) + return -EOPNOTSUPP; + + err = pcie_capability_read_word(bridge, PCI_EXP_SLTCTL, ®16); + if (err) + return err; + + if ((reg16 & PCI_EXP_SLTCTL_HPIE) && (reg16 & PCI_EXP_SLTCTL_DLLSCE)) { + mlx5_core_warn(dev, "FW reset is not supported as HotPlug is enabled\n"); + return -EOPNOTSUPP; + } + + return 0; +} +#endif + +static const struct pci_device_id mgt_ifc_device_ids[] = { + { PCI_VDEVICE(MELLANOX, 0xc2d2) }, /* BlueField1 MGT interface device ID */ + { PCI_VDEVICE(MELLANOX, 0xc2d3) }, /* BlueField2 MGT interface device ID */ + { PCI_VDEVICE(MELLANOX, 0xc2d4) }, /* BlueField3-Lx MGT interface device ID */ + { PCI_VDEVICE(MELLANOX, 0xc2d5) }, /* BlueField3 MGT interface device ID */ + { PCI_VDEVICE(MELLANOX, 0xc2d6) }, /* BlueField4 MGT interface device ID */ +}; + +static bool mlx5_is_mgt_ifc_pci_device(struct mlx5_core_dev *dev, u16 dev_id) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(mgt_ifc_device_ids); ++i) + if (mgt_ifc_device_ids[i].device == dev_id) + return true; + + return false; +} + static int mlx5_check_dev_ids(struct mlx5_core_dev *dev, u16 dev_id) { struct pci_bus *bridge_bus = dev->pdev->bus; @@ -339,10 +381,15 @@ static int mlx5_check_dev_ids(struct mlx5_core_dev *dev, u16 dev_id) err = pci_read_config_word(sdev, PCI_DEVICE_ID, &sdev_id); if (err) return pcibios_err_to_errno(err); - if (sdev_id != dev_id) { - mlx5_core_warn(dev, "unrecognized dev_id (0x%x)\n", sdev_id); - return -EPERM; - } + + if (sdev_id == dev_id) + continue; + + if (mlx5_is_mgt_ifc_pci_device(dev, sdev_id)) + continue; + + mlx5_core_warn(dev, "unrecognized dev_id (0x%x)\n", sdev_id); + return -EPERM; } return 0; } @@ -357,6 +404,12 @@ static bool mlx5_is_reset_now_capable(struct mlx5_core_dev *dev) return false; } +#if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE) + err = mlx5_check_hotplug_interrupt(dev); + if (err) + return false; +#endif + err = pci_read_config_word(dev->pdev, PCI_DEVICE_ID, &dev_id); if (err) return false; @@ -650,19 +703,30 @@ void mlx5_fw_reset_events_start(struct mlx5_core_dev *dev) { struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + if (!fw_reset) + return; + MLX5_NB_INIT(&fw_reset->nb, fw_reset_event_notifier, GENERAL_EVENT); mlx5_eq_notifier_register(dev, &fw_reset->nb); } void mlx5_fw_reset_events_stop(struct mlx5_core_dev *dev) { - mlx5_eq_notifier_unregister(dev, &dev->priv.fw_reset->nb); + struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + + if (!fw_reset) + return; + + mlx5_eq_notifier_unregister(dev, &fw_reset->nb); } void mlx5_drain_fw_reset(struct mlx5_core_dev *dev) { struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + if (!fw_reset) + return; + set_bit(MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS, &fw_reset->reset_flags); cancel_work_sync(&fw_reset->fw_live_patch_work); cancel_work_sync(&fw_reset->reset_request_work); @@ -680,9 +744,13 @@ static const struct devlink_param mlx5_fw_reset_devlink_params[] = { int mlx5_fw_reset_init(struct mlx5_core_dev *dev) { - struct mlx5_fw_reset *fw_reset = kzalloc(sizeof(*fw_reset), GFP_KERNEL); + struct mlx5_fw_reset *fw_reset; int err; + if (!MLX5_CAP_MCAM_REG(dev, mfrl)) + return 0; + + fw_reset = kzalloc(sizeof(*fw_reset), GFP_KERNEL); if (!fw_reset) return -ENOMEM; fw_reset->wq = create_singlethread_workqueue("mlx5_fw_reset_events"); @@ -718,6 +786,9 @@ void mlx5_fw_reset_cleanup(struct mlx5_core_dev *dev) { struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + if (!fw_reset) + return; + devl_params_unregister(priv_to_devlink(dev), mlx5_fw_reset_devlink_params, ARRAY_SIZE(mlx5_fw_reset_devlink_params)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 8ff6dc9bc803..ad38e31822df 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -116,9 +116,9 @@ u32 mlx5_health_check_fatal_sensors(struct mlx5_core_dev *dev) return MLX5_SENSOR_PCI_COMM_ERR; if (pci_channel_offline(dev->pdev)) return MLX5_SENSOR_PCI_ERR; - if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED) + if (mlx5_get_nic_state(dev) == MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED) return MLX5_SENSOR_NIC_DISABLED; - if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_SW_RESET) + if (mlx5_get_nic_state(dev) == MLX5_INITIAL_SEG_NIC_INTERFACE_SW_RESET) return MLX5_SENSOR_NIC_SW_RESET; if (sensor_fw_synd_rfr(dev)) return MLX5_SENSOR_FW_SYND_RFR; @@ -185,7 +185,7 @@ static bool reset_fw_if_needed(struct mlx5_core_dev *dev) /* Write the NIC interface field to initiate the reset, the command * interface address also resides here, don't overwrite it. */ - mlx5_set_nic_state(dev, MLX5_NIC_IFC_SW_RESET); + mlx5_set_nic_state(dev, MLX5_INITIAL_SEG_NIC_INTERFACE_SW_RESET); return true; } @@ -246,13 +246,13 @@ recover_from_sw_reset: /* Recover from SW reset */ end = jiffies + msecs_to_jiffies(delay_ms); do { - if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED) + if (mlx5_get_nic_state(dev) == MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED) break; msleep(20); } while (!time_after(jiffies, end)); - if (mlx5_get_nic_state(dev) != MLX5_NIC_IFC_DISABLED) { + if (mlx5_get_nic_state(dev) != MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED) { dev_err(&dev->pdev->dev, "NIC IFC still %d after %lums.\n", mlx5_get_nic_state(dev), delay_ms); } @@ -272,26 +272,26 @@ static void mlx5_handle_bad_state(struct mlx5_core_dev *dev) u8 nic_interface = mlx5_get_nic_state(dev); switch (nic_interface) { - case MLX5_NIC_IFC_FULL: + case MLX5_INITIAL_SEG_NIC_INTERFACE_FULL_DRIVER: mlx5_core_warn(dev, "Expected to see disabled NIC but it is full driver\n"); break; - case MLX5_NIC_IFC_DISABLED: + case MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED: mlx5_core_warn(dev, "starting teardown\n"); break; - case MLX5_NIC_IFC_NO_DRAM_NIC: + case MLX5_INITIAL_SEG_NIC_INTERFACE_NO_DRAM_NIC: mlx5_core_warn(dev, "Expected to see disabled NIC but it is no dram nic\n"); break; - case MLX5_NIC_IFC_SW_RESET: + case MLX5_INITIAL_SEG_NIC_INTERFACE_SW_RESET: /* The IFC mode field is 3 bits, so it will read 0x7 in 2 cases: * 1. PCI has been disabled (ie. PCI-AER, PF driver unloaded * and this is a VF), this is not recoverable by SW reset. * Logging of this is handled elsewhere. * 2. FW reset has been issued by another function, driver can * be reloaded to recover after the mode switches to - * MLX5_NIC_IFC_DISABLED. + * MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED. */ if (dev->priv.health.fatal_error != MLX5_SENSOR_PCI_COMM_ERR) mlx5_core_warn(dev, "NIC SW reset in progress\n"); @@ -452,10 +452,10 @@ mlx5_fw_reporter_diagnose(struct devlink_health_reporter *reporter, struct health_buffer __iomem *h = health->health; u8 synd = ioread8(&h->synd); + devlink_fmsg_u8_pair_put(fmsg, "Syndrome", synd); if (!synd) return 0; - devlink_fmsg_u8_pair_put(fmsg, "Syndrome", synd); devlink_fmsg_string_pair_put(fmsg, "Description", hsynd_str(synd)); return 0; @@ -555,12 +555,17 @@ static void mlx5_fw_reporter_err_work(struct work_struct *work) &fw_reporter_ctx); } -static const struct devlink_health_reporter_ops mlx5_fw_reporter_ops = { +static const struct devlink_health_reporter_ops mlx5_fw_reporter_pf_ops = { .name = "fw", .diagnose = mlx5_fw_reporter_diagnose, .dump = mlx5_fw_reporter_dump, }; +static const struct devlink_health_reporter_ops mlx5_fw_reporter_ops = { + .name = "fw", + .diagnose = mlx5_fw_reporter_diagnose, +}; + static int mlx5_fw_fatal_reporter_recover(struct devlink_health_reporter *reporter, void *priv_ctx, @@ -646,12 +651,17 @@ static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work) } } -static const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_ops = { +static const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_pf_ops = { .name = "fw_fatal", .recover = mlx5_fw_fatal_reporter_recover, .dump = mlx5_fw_fatal_reporter_dump, }; +static const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_ops = { + .name = "fw_fatal", + .recover = mlx5_fw_fatal_reporter_recover, +}; + #define MLX5_FW_REPORTER_ECPF_GRACEFUL_PERIOD 180000 #define MLX5_FW_REPORTER_PF_GRACEFUL_PERIOD 60000 #define MLX5_FW_REPORTER_VF_GRACEFUL_PERIOD 30000 @@ -659,10 +669,14 @@ static const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_ops = { void mlx5_fw_reporters_create(struct mlx5_core_dev *dev) { + const struct devlink_health_reporter_ops *fw_fatal_ops; struct mlx5_core_health *health = &dev->priv.health; + const struct devlink_health_reporter_ops *fw_ops; struct devlink *devlink = priv_to_devlink(dev); u64 grace_period; + fw_fatal_ops = &mlx5_fw_fatal_reporter_pf_ops; + fw_ops = &mlx5_fw_reporter_pf_ops; if (mlx5_core_is_ecpf(dev)) { grace_period = MLX5_FW_REPORTER_ECPF_GRACEFUL_PERIOD; } else if (mlx5_core_is_pf(dev)) { @@ -670,18 +684,19 @@ void mlx5_fw_reporters_create(struct mlx5_core_dev *dev) } else { /* VF or SF */ grace_period = MLX5_FW_REPORTER_DEFAULT_GRACEFUL_PERIOD; + fw_fatal_ops = &mlx5_fw_fatal_reporter_ops; + fw_ops = &mlx5_fw_reporter_ops; } health->fw_reporter = - devl_health_reporter_create(devlink, &mlx5_fw_reporter_ops, - 0, dev); + devl_health_reporter_create(devlink, fw_ops, 0, dev); if (IS_ERR(health->fw_reporter)) mlx5_core_warn(dev, "Failed to create fw reporter, err = %ld\n", PTR_ERR(health->fw_reporter)); health->fw_fatal_reporter = devl_health_reporter_create(devlink, - &mlx5_fw_fatal_reporter_ops, + fw_fatal_ops, grace_period, dev); if (IS_ERR(health->fw_fatal_reporter)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 2bf77a5251b4..d77be1b4dd9c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -339,7 +339,7 @@ static int mlx5i_init_tx(struct mlx5e_priv *priv) return err; } - err = mlx5i_create_tis(priv->mdev, ipriv->qpn, &priv->tisn[0][0]); + err = mlx5i_create_tis(priv->mdev, ipriv->qpn, &ipriv->tisn); if (err) { mlx5_core_warn(priv->mdev, "create tis failed, %d\n", err); goto err_destroy_underlay_qp; @@ -356,7 +356,7 @@ static void mlx5i_cleanup_tx(struct mlx5e_priv *priv) { struct mlx5i_priv *ipriv = priv->ppriv; - mlx5e_destroy_tis(priv->mdev, priv->tisn[0][0]); + mlx5e_destroy_tis(priv->mdev, ipriv->tisn); mlx5i_destroy_underlay_qp(priv->mdev, ipriv->qpn); } @@ -483,6 +483,18 @@ static unsigned int mlx5i_stats_grps_num(struct mlx5e_priv *priv) return ARRAY_SIZE(mlx5i_stats_grps); } +u32 mlx5i_get_tisn(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv, u8 lag_port, u8 tc) +{ + struct mlx5i_priv *ipriv = priv->ppriv; + + if (WARN(lag_port || tc, + "IPoIB unexpected non-zero value: lag_port (%u), tc (%u)\n", + lag_port, tc)) + return 0; + + return ipriv->tisn; +} + static const struct mlx5e_profile mlx5i_nic_profile = { .init = mlx5i_init, .cleanup = mlx5i_cleanup, @@ -499,6 +511,7 @@ static const struct mlx5e_profile mlx5i_nic_profile = { .max_tc = MLX5I_MAX_NUM_TC, .stats_grps = mlx5i_stats_grps, .stats_grps_num = mlx5i_stats_grps_num, + .get_tisn = mlx5i_get_tisn, }; /* mlx5i netdev NDos */ @@ -770,7 +783,7 @@ static int mlx5_rdma_setup_rn(struct ib_device *ibdev, u32 port_num, } /* This should only be called once per mdev */ - err = mlx5e_create_mdev_resources(mdev); + err = mlx5e_create_mdev_resources(mdev, false); if (err) goto destroy_ht; } @@ -829,7 +842,7 @@ int mlx5_rdma_rn_get_params(struct mlx5_core_dev *mdev, *params = (struct rdma_netdev_alloc_params){ .sizeof_priv = sizeof(struct mlx5i_priv) + sizeof(struct mlx5e_priv), - .txqs = nch * MLX5E_MAX_NUM_TC, + .txqs = nch * MLX5_MAX_NUM_TC, .rxqs = nch, .param = mdev, .initialize_rdma_netdev = mlx5_rdma_setup_rn, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h index f3f2af972020..2ab6437a1c49 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h @@ -53,6 +53,7 @@ extern const struct mlx5e_rx_handlers mlx5i_rx_handlers; struct mlx5i_priv { struct rdma_netdev rn; /* keep this first */ u32 qpn; + u32 tisn; bool sub_interface; u32 num_sub_interfaces; u32 qkey; @@ -63,6 +64,7 @@ struct mlx5i_priv { }; int mlx5i_create_tis(struct mlx5_core_dev *mdev, u32 underlay_qpn, u32 *tisn); +u32 mlx5i_get_tisn(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv, u8 lag_port, u8 tc); /* Underlay QP create/destroy functions */ int mlx5i_create_underlay_qp(struct mlx5e_priv *priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c index 03e681297937..f87471306f6b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c @@ -218,7 +218,7 @@ static int mlx5i_pkey_open(struct net_device *netdev) goto err_unint_underlay_qp; } - err = mlx5i_create_tis(mdev, ipriv->qpn, &epriv->tisn[0][0]); + err = mlx5i_create_tis(mdev, ipriv->qpn, &ipriv->tisn); if (err) { mlx5_core_warn(mdev, "create child tis failed, %d\n", err); goto err_remove_rx_uderlay_qp; @@ -240,7 +240,7 @@ static int mlx5i_pkey_open(struct net_device *netdev) err_close_channels: mlx5e_close_channels(&epriv->channels); err_clear_state_opened_flag: - mlx5e_destroy_tis(mdev, epriv->tisn[0][0]); + mlx5e_destroy_tis(mdev, ipriv->tisn); err_remove_rx_uderlay_qp: mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qpn); err_unint_underlay_qp: @@ -269,7 +269,7 @@ static int mlx5i_pkey_close(struct net_device *netdev) mlx5i_uninit_underlay_qp(priv); mlx5e_deactivate_priv_channels(priv); mlx5e_close_channels(&priv->channels); - mlx5e_destroy_tis(mdev, priv->tisn[0][0]); + mlx5e_destroy_tis(mdev, ipriv->tisn); unlock: mutex_unlock(&priv->state_lock); return 0; @@ -361,6 +361,7 @@ static const struct mlx5e_profile mlx5i_pkey_nic_profile = { .update_stats = NULL, .rx_handlers = &mlx5i_rx_handlers, .max_tc = MLX5I_MAX_NUM_TC, + .get_tisn = mlx5i_get_tisn, }; const struct mlx5e_profile *mlx5i_pkey_get_profile(void) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c index 047d5fed5f89..612e666ec263 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c @@ -168,45 +168,3 @@ void mlx5_irq_affinity_irq_release(struct mlx5_core_dev *dev, struct mlx5_irq *i if (pool->irqs_per_cpu) cpu_put(pool, cpu); } - -/** - * mlx5_irq_affinity_irq_request_auto - request one IRQ for mlx5 device. - * @dev: mlx5 device that is requesting the IRQ. - * @used_cpus: cpumask of bounded cpus by the device - * @vecidx: vector index to request an IRQ for. - * - * Each IRQ is bounded to at most 1 CPU. - * This function is requesting an IRQ according to the default assignment. - * The default assignment policy is: - * - request the least loaded IRQ which is not bound to any - * CPU of the previous IRQs requested. - * - * On success, this function updates used_cpus mask and returns an irq pointer. - * In case of an error, an appropriate error pointer is returned. - */ -struct mlx5_irq *mlx5_irq_affinity_irq_request_auto(struct mlx5_core_dev *dev, - struct cpumask *used_cpus, u16 vecidx) -{ - struct mlx5_irq_pool *pool = mlx5_irq_pool_get(dev); - struct irq_affinity_desc af_desc = {}; - struct mlx5_irq *irq; - - if (!mlx5_irq_pool_is_sf_pool(pool)) - return ERR_PTR(-ENOENT); - - af_desc.is_managed = 1; - cpumask_copy(&af_desc.mask, cpu_online_mask); - cpumask_andnot(&af_desc.mask, &af_desc.mask, used_cpus); - irq = mlx5_irq_affinity_request(pool, &af_desc); - - if (IS_ERR(irq)) - return irq; - - cpumask_or(used_cpus, used_cpus, mlx5_irq_get_affinity_mask(irq)); - mlx5_core_dbg(pool->dev, "IRQ %u mapped to cpu %*pbl, %u EQs on this irq\n", - pci_irq_vector(dev->pdev, mlx5_irq_get_index(irq)), - cpumask_pr_args(mlx5_irq_get_affinity_mask(irq)), - mlx5_irq_read_locked(irq) / MLX5_EQ_REFS_PER_IRQ); - - return irq; -} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c index 40c7be124041..58bd749b5e4d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c @@ -98,7 +98,7 @@ static int create_aso_cq(struct mlx5_aso_cq *cq, void *cqc_data) mlx5_fill_page_frag_array(&cq->wq_ctrl.buf, (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas)); - MLX5_SET(cqc, cqc, cq_period_mode, DIM_CQ_PERIOD_MODE_START_FROM_EQE); + MLX5_SET(cqc, cqc, cq_period_mode, MLX5_CQ_PERIOD_MODE_START_FROM_EQE); MLX5_SET(cqc, cqc, c_eqn_or_apu_element, eqn); MLX5_SET(cqc, cqc, uar_page, mdev->priv.uar->index); MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.buf.page_shift - diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index aa29f09e8356..0361741632a6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -266,9 +266,6 @@ static int mlx5_ptp_settime_real_time(struct mlx5_core_dev *mdev, { u32 in[MLX5_ST_SZ_DW(mtutc_reg)] = {}; - if (!mlx5_modify_mtutc_allowed(mdev)) - return 0; - if (ts->tv_sec < 0 || ts->tv_sec > U32_MAX || ts->tv_nsec < 0 || ts->tv_nsec > NSEC_PER_SEC) return -EINVAL; @@ -286,12 +283,15 @@ static int mlx5_ptp_settime(struct ptp_clock_info *ptp, const struct timespec64 struct mlx5_timer *timer = &clock->timer; struct mlx5_core_dev *mdev; unsigned long flags; - int err; mdev = container_of(clock, struct mlx5_core_dev, clock); - err = mlx5_ptp_settime_real_time(mdev, ts); - if (err) - return err; + + if (mlx5_modify_mtutc_allowed(mdev)) { + int err = mlx5_ptp_settime_real_time(mdev, ts); + + if (err) + return err; + } write_seqlock_irqsave(&clock->lock, flags); timecounter_init(&timer->tc, &timer->cycles, timespec64_to_ns(ts)); @@ -341,9 +341,6 @@ static int mlx5_ptp_adjtime_real_time(struct mlx5_core_dev *mdev, s64 delta) { u32 in[MLX5_ST_SZ_DW(mtutc_reg)] = {}; - if (!mlx5_modify_mtutc_allowed(mdev)) - return 0; - /* HW time adjustment range is checked. If out of range, settime instead */ if (!mlx5_is_mtutc_time_adj_cap(mdev, delta)) { struct timespec64 ts; @@ -367,13 +364,16 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) struct mlx5_timer *timer = &clock->timer; struct mlx5_core_dev *mdev; unsigned long flags; - int err; mdev = container_of(clock, struct mlx5_core_dev, clock); - err = mlx5_ptp_adjtime_real_time(mdev, delta); - if (err) - return err; + if (mlx5_modify_mtutc_allowed(mdev)) { + int err = mlx5_ptp_adjtime_real_time(mdev, delta); + + if (err) + return err; + } + write_seqlock_irqsave(&clock->lock, flags); timecounter_adjtime(&timer->tc, delta); mlx5_update_clock_info_page(mdev); @@ -384,22 +384,26 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) static int mlx5_ptp_adjphase(struct ptp_clock_info *ptp, s32 delta) { - return mlx5_ptp_adjtime(ptp, delta); + struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info); + struct mlx5_core_dev *mdev; + + mdev = container_of(clock, struct mlx5_core_dev, clock); + + return mlx5_ptp_adjtime_real_time(mdev, delta); } static int mlx5_ptp_freq_adj_real_time(struct mlx5_core_dev *mdev, long scaled_ppm) { u32 in[MLX5_ST_SZ_DW(mtutc_reg)] = {}; - if (!mlx5_modify_mtutc_allowed(mdev)) - return 0; - MLX5_SET(mtutc_reg, in, operation, MLX5_MTUTC_OPERATION_ADJUST_FREQ_UTC); - if (MLX5_CAP_MCAM_FEATURE(mdev, mtutc_freq_adj_units)) { + if (MLX5_CAP_MCAM_FEATURE(mdev, mtutc_freq_adj_units) && + scaled_ppm <= S32_MAX && scaled_ppm >= S32_MIN) { + /* HW scaled_ppm support on mlx5 devices only supports a 32-bit value */ MLX5_SET(mtutc_reg, in, freq_adj_units, MLX5_MTUTC_FREQ_ADJ_UNITS_SCALED_PPM); - MLX5_SET(mtutc_reg, in, freq_adjustment, scaled_ppm); + MLX5_SET(mtutc_reg, in, freq_adjustment, (s32)scaled_ppm); } else { MLX5_SET(mtutc_reg, in, freq_adj_units, MLX5_MTUTC_FREQ_ADJ_UNITS_PPB); MLX5_SET(mtutc_reg, in, freq_adjustment, scaled_ppm_to_ppb(scaled_ppm)); @@ -415,13 +419,15 @@ static int mlx5_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) struct mlx5_core_dev *mdev; unsigned long flags; u32 mult; - int err; mdev = container_of(clock, struct mlx5_core_dev, clock); - err = mlx5_ptp_freq_adj_real_time(mdev, scaled_ppm); - if (err) - return err; + if (mlx5_modify_mtutc_allowed(mdev)) { + int err = mlx5_ptp_freq_adj_real_time(mdev, scaled_ppm); + + if (err) + return err; + } mult = (u32)adjust_by_scaled_ppm(timer->nominal_c_mult, scaled_ppm); @@ -999,14 +1005,38 @@ static void mlx5_init_clock_info(struct mlx5_core_dev *mdev) info->frac = timer->tc.frac; } +static void mlx5_init_timer_max_freq_adjustment(struct mlx5_core_dev *mdev) +{ + struct mlx5_clock *clock = &mdev->clock; + u32 out[MLX5_ST_SZ_DW(mtutc_reg)] = {}; + u32 in[MLX5_ST_SZ_DW(mtutc_reg)] = {}; + u8 log_max_freq_adjustment = 0; + int err; + + err = mlx5_core_access_reg(mdev, in, sizeof(in), out, sizeof(out), + MLX5_REG_MTUTC, 0, 0); + if (!err) + log_max_freq_adjustment = + MLX5_GET(mtutc_reg, out, log_max_freq_adjustment); + + if (log_max_freq_adjustment) + clock->ptp_info.max_adj = + min(S32_MAX, 1 << log_max_freq_adjustment); +} + static void mlx5_init_timer_clock(struct mlx5_core_dev *mdev) { struct mlx5_clock *clock = &mdev->clock; + /* Configure the PHC */ + clock->ptp_info = mlx5_ptp_clock_info; + + if (MLX5_CAP_MCAM_REG(mdev, mtutc)) + mlx5_init_timer_max_freq_adjustment(mdev); + mlx5_timecounter_init(mdev); mlx5_init_clock_info(mdev); mlx5_init_overflow_period(clock); - clock->ptp_info = mlx5_ptp_clock_info; if (mlx5_real_time_mode(mdev)) { struct timespec64 ts; @@ -1037,11 +1067,10 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev) } seqlock_init(&clock->lock); - mlx5_init_timer_clock(mdev); INIT_WORK(&clock->pps_info.out_work, mlx5_pps_out); - /* Configure the PHC */ - clock->ptp_info = mlx5_ptp_clock_info; + /* Initialize the device clock */ + mlx5_init_timer_clock(mdev); /* Initialize 1PPS data structures */ mlx5_init_pps(mdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c index e8e50563e956..e7d59cfa8708 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c @@ -256,6 +256,13 @@ void mlx5_devcom_unregister_component(struct mlx5_devcom_comp_dev *devcom) devcom_free_comp_dev(devcom); } +int mlx5_devcom_comp_get_size(struct mlx5_devcom_comp_dev *devcom) +{ + struct mlx5_devcom_comp *comp = devcom->comp; + + return kref_read(&comp->ref); +} + int mlx5_devcom_send_event(struct mlx5_devcom_comp_dev *devcom, int event, int rollback_event, void *event_data) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h index fc23bbef87b4..ec32b686f586 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h @@ -31,6 +31,7 @@ void mlx5_devcom_unregister_component(struct mlx5_devcom_comp_dev *devcom); int mlx5_devcom_send_event(struct mlx5_devcom_comp_dev *devcom, int event, int rollback_event, void *event_data); +int mlx5_devcom_comp_get_size(struct mlx5_devcom_comp_dev *devcom); void mlx5_devcom_comp_set_ready(struct mlx5_devcom_comp_dev *devcom, bool ready); bool mlx5_devcom_comp_is_ready(struct mlx5_devcom_comp_dev *devcom); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c index 9482e51ac82a..7c5516b0a844 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c @@ -13,11 +13,13 @@ struct mlx5_dm { unsigned long *steering_sw_icm_alloc_blocks; unsigned long *header_modify_sw_icm_alloc_blocks; unsigned long *header_modify_pattern_sw_icm_alloc_blocks; + unsigned long *header_encap_sw_icm_alloc_blocks; }; struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev) { u64 header_modify_pattern_icm_blocks = 0; + u64 header_sw_encap_icm_blocks = 0; u64 header_modify_icm_blocks = 0; u64 steering_icm_blocks = 0; struct mlx5_dm *dm; @@ -54,6 +56,17 @@ struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev) goto err_modify_hdr; } + if (MLX5_CAP_DEV_MEM(dev, log_indirect_encap_sw_icm_size)) { + header_sw_encap_icm_blocks = + BIT(MLX5_CAP_DEV_MEM(dev, log_indirect_encap_sw_icm_size) - + MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)); + + dm->header_encap_sw_icm_alloc_blocks = + bitmap_zalloc(header_sw_encap_icm_blocks, GFP_KERNEL); + if (!dm->header_encap_sw_icm_alloc_blocks) + goto err_pattern; + } + support_v2 = MLX5_CAP_FLOWTABLE_NIC_RX(dev, sw_owner_v2) && MLX5_CAP_FLOWTABLE_NIC_TX(dev, sw_owner_v2) && MLX5_CAP64_DEV_MEM(dev, header_modify_pattern_sw_icm_start_address); @@ -66,11 +79,14 @@ struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev) dm->header_modify_pattern_sw_icm_alloc_blocks = bitmap_zalloc(header_modify_pattern_icm_blocks, GFP_KERNEL); if (!dm->header_modify_pattern_sw_icm_alloc_blocks) - goto err_pattern; + goto err_sw_encap; } return dm; +err_sw_encap: + bitmap_free(dm->header_encap_sw_icm_alloc_blocks); + err_pattern: bitmap_free(dm->header_modify_sw_icm_alloc_blocks); @@ -105,6 +121,14 @@ void mlx5_dm_cleanup(struct mlx5_core_dev *dev) bitmap_free(dm->header_modify_sw_icm_alloc_blocks); } + if (dm->header_encap_sw_icm_alloc_blocks) { + WARN_ON(!bitmap_empty(dm->header_encap_sw_icm_alloc_blocks, + BIT(MLX5_CAP_DEV_MEM(dev, + log_indirect_encap_sw_icm_size) - + MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)))); + bitmap_free(dm->header_encap_sw_icm_alloc_blocks); + } + if (dm->header_modify_pattern_sw_icm_alloc_blocks) { WARN_ON(!bitmap_empty(dm->header_modify_pattern_sw_icm_alloc_blocks, BIT(MLX5_CAP_DEV_MEM(dev, @@ -164,6 +188,13 @@ int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, log_header_modify_pattern_sw_icm_size); block_map = dm->header_modify_pattern_sw_icm_alloc_blocks; break; + case MLX5_SW_ICM_TYPE_SW_ENCAP: + icm_start_addr = MLX5_CAP64_DEV_MEM(dev, + indirect_encap_sw_icm_start_address); + log_icm_size = MLX5_CAP_DEV_MEM(dev, + log_indirect_encap_sw_icm_size); + block_map = dm->header_encap_sw_icm_alloc_blocks; + break; default: return -EINVAL; } @@ -242,6 +273,11 @@ int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type header_modify_pattern_sw_icm_start_address); block_map = dm->header_modify_pattern_sw_icm_alloc_blocks; break; + case MLX5_SW_ICM_TYPE_SW_ENCAP: + icm_start_addr = MLX5_CAP64_DEV_MEM(dev, + indirect_encap_sw_icm_start_address); + block_map = dm->header_encap_sw_icm_alloc_blocks; + break; default: return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index a17152c1cbb2..c2593625c09a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -187,31 +187,36 @@ static struct mlx5_profile profile[] = { }; static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili, - u32 warn_time_mili) + u32 warn_time_mili, const char *init_state) { unsigned long warn = jiffies + msecs_to_jiffies(warn_time_mili); unsigned long end = jiffies + msecs_to_jiffies(max_wait_mili); u32 fw_initializing; - int err = 0; do { fw_initializing = ioread32be(&dev->iseg->initializing); if (!(fw_initializing >> 31)) break; - if (time_after(jiffies, end) || - test_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state)) { - err = -EBUSY; - break; + if (time_after(jiffies, end)) { + mlx5_core_err(dev, "Firmware over %u MS in %s state, aborting\n", + max_wait_mili, init_state); + return -ETIMEDOUT; + } + if (test_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state)) { + mlx5_core_warn(dev, "device is being removed, stop waiting for FW %s\n", + init_state); + return -ENODEV; } if (warn_time_mili && time_after(jiffies, warn)) { - mlx5_core_warn(dev, "Waiting for FW initialization, timeout abort in %ds (0x%x)\n", - jiffies_to_msecs(end - warn) / 1000, fw_initializing); + mlx5_core_warn(dev, "Waiting for FW %s, timeout abort in %ds (0x%x)\n", + init_state, jiffies_to_msecs(end - warn) / 1000, + fw_initializing); warn = jiffies + msecs_to_jiffies(warn_time_mili); } msleep(mlx5_tout_ms(dev, FW_PRE_INIT_WAIT)); } while (true); - return err; + return 0; } static void mlx5_set_driver_version(struct mlx5_core_dev *dev) @@ -219,7 +224,6 @@ static void mlx5_set_driver_version(struct mlx5_core_dev *dev) int driver_ver_sz = MLX5_FLD_SZ_BYTES(set_driver_version_in, driver_version); u8 in[MLX5_ST_SZ_BYTES(set_driver_version_in)] = {}; - int remaining_size = driver_ver_sz; char *string; if (!MLX5_CAP_GEN(dev, driver_version)) @@ -227,22 +231,9 @@ static void mlx5_set_driver_version(struct mlx5_core_dev *dev) string = MLX5_ADDR_OF(set_driver_version_in, in, driver_version); - strncpy(string, "Linux", remaining_size); - - remaining_size = max_t(int, 0, driver_ver_sz - strlen(string)); - strncat(string, ",", remaining_size); - - remaining_size = max_t(int, 0, driver_ver_sz - strlen(string)); - strncat(string, KBUILD_MODNAME, remaining_size); - - remaining_size = max_t(int, 0, driver_ver_sz - strlen(string)); - strncat(string, ",", remaining_size); - - remaining_size = max_t(int, 0, driver_ver_sz - strlen(string)); - - snprintf(string + strlen(string), remaining_size, "%u.%u.%u", - LINUX_VERSION_MAJOR, LINUX_VERSION_PATCHLEVEL, - LINUX_VERSION_SUBLEVEL); + snprintf(string, driver_ver_sz, "Linux,%s,%u.%u.%u", + KBUILD_MODNAME, LINUX_VERSION_MAJOR, + LINUX_VERSION_PATCHLEVEL, LINUX_VERSION_SUBLEVEL); /*Send the command*/ MLX5_SET(set_driver_version_in, in, opcode, @@ -1165,12 +1156,10 @@ static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeou /* wait for firmware to accept initialization segments configurations */ err = wait_fw_init(dev, timeout, - mlx5_tout_ms(dev, FW_PRE_INIT_WARN_MESSAGE_INTERVAL)); - if (err) { - mlx5_core_err(dev, "Firmware over %llu MS in pre-initializing state, aborting\n", - timeout); + mlx5_tout_ms(dev, FW_PRE_INIT_WARN_MESSAGE_INTERVAL), + "pre-initializing"); + if (err) return err; - } err = mlx5_cmd_enable(dev); if (err) { @@ -1180,12 +1169,9 @@ static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeou mlx5_tout_query_iseg(dev); - err = wait_fw_init(dev, mlx5_tout_ms(dev, FW_INIT), 0); - if (err) { - mlx5_core_err(dev, "Firmware over %llu MS in initializing state, aborting\n", - mlx5_tout_ms(dev, FW_INIT)); + err = wait_fw_init(dev, mlx5_tout_ms(dev, FW_INIT), 0, "initializing"); + if (err) goto err_cmd_cleanup; - } dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev); mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_UP); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 6b14e347d914..58732f44940f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -243,6 +243,7 @@ int mlx5_query_mcam_reg(struct mlx5_core_dev *dev, u32 *mcap, u8 feature_group, u8 access_reg_group); int mlx5_query_qcam_reg(struct mlx5_core_dev *mdev, u32 *qcam, u8 feature_group, u8 access_reg_group); +int mlx5_query_mpir_reg(struct mlx5_core_dev *dev, u32 *mpir); void mlx5_lag_add_netdev(struct mlx5_core_dev *dev, struct net_device *netdev); void mlx5_lag_remove_netdev(struct mlx5_core_dev *dev, struct net_device *netdev); @@ -311,13 +312,6 @@ static inline int mlx5_rescan_drivers(struct mlx5_core_dev *dev) return ret; } -enum { - MLX5_NIC_IFC_FULL = 0, - MLX5_NIC_IFC_DISABLED = 1, - MLX5_NIC_IFC_NO_DRAM_NIC = 2, - MLX5_NIC_IFC_SW_RESET = 7 -}; - u8 mlx5_get_nic_state(struct mlx5_core_dev *dev); void mlx5_set_nic_state(struct mlx5_core_dev *dev, u8 state); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 653648216730..4dcf995cb1a2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -28,7 +28,7 @@ struct mlx5_irq { struct atomic_notifier_head nh; cpumask_var_t mask; - char name[MLX5_MAX_IRQ_NAME]; + char name[MLX5_MAX_IRQ_FORMATTED_NAME]; struct mlx5_irq_pool *pool; int refcount; struct msi_map map; @@ -292,8 +292,8 @@ struct mlx5_irq *mlx5_irq_alloc(struct mlx5_irq_pool *pool, int i, else irq_sf_set_name(pool, name, i); ATOMIC_INIT_NOTIFIER_HEAD(&irq->nh); - snprintf(irq->name, MLX5_MAX_IRQ_NAME, - "%s@pci:%s", name, pci_name(dev->pdev)); + snprintf(irq->name, MLX5_MAX_IRQ_FORMATTED_NAME, + MLX5_IRQ_NAME_FORMAT_STR, name, pci_name(dev->pdev)); err = request_irq(irq->map.virq, irq_int_handler, 0, irq->name, &irq->nh); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h index d3a77a0ab848..c4d377f8df30 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h @@ -7,6 +7,9 @@ #include <linux/mlx5/driver.h> #define MLX5_MAX_IRQ_NAME (32) +#define MLX5_IRQ_NAME_FORMAT_STR ("%s@pci:%s") +#define MLX5_MAX_IRQ_FORMATTED_NAME \ + (MLX5_MAX_IRQ_NAME + sizeof(MLX5_IRQ_NAME_FORMAT_STR)) /* max irq_index is 2047, so four chars */ #define MLX5_MAX_IRQ_IDX_CHARS (4) #define MLX5_EQ_REFS_PER_IRQ (2) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 7d8c732818f2..7fba1c46e2ac 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -1206,3 +1206,13 @@ int mlx5_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed) *speed = max_speed; return 0; } + +int mlx5_query_mpir_reg(struct mlx5_core_dev *dev, u32 *mpir) +{ + u32 in[MLX5_ST_SZ_DW(mpir_reg)] = {}; + int sz = MLX5_ST_SZ_BYTES(mpir_reg); + + MLX5_SET(mpir_reg, in, local_port, 1); + + return mlx5_core_access_reg(dev, in, sz, mpir, sz, MLX5_REG_MPIR, 0, 0); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c index c93492b67788..99219ea52c4b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c @@ -74,7 +74,8 @@ static void mlx5_sf_dev_release(struct device *device) kfree(sf_dev); } -static void mlx5_sf_dev_remove(struct mlx5_core_dev *dev, struct mlx5_sf_dev *sf_dev) +static void mlx5_sf_dev_remove_aux(struct mlx5_core_dev *dev, + struct mlx5_sf_dev *sf_dev) { int id; @@ -138,7 +139,7 @@ static void mlx5_sf_dev_add(struct mlx5_core_dev *dev, u16 sf_index, u16 fn_id, return; xa_err: - mlx5_sf_dev_remove(dev, sf_dev); + mlx5_sf_dev_remove_aux(dev, sf_dev); add_err: mlx5_core_err(dev, "SF DEV: fail device add for index=%d sfnum=%d err=%d\n", sf_index, sfnum, err); @@ -149,7 +150,7 @@ static void mlx5_sf_dev_del(struct mlx5_core_dev *dev, struct mlx5_sf_dev *sf_de struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table; xa_erase(&table->devices, sf_index); - mlx5_sf_dev_remove(dev, sf_dev); + mlx5_sf_dev_remove_aux(dev, sf_dev); } static int @@ -367,7 +368,7 @@ static void mlx5_sf_dev_destroy_all(struct mlx5_sf_dev_table *table) xa_for_each(&table->devices, index, sf_dev) { xa_erase(&table->devices, index); - mlx5_sf_dev_remove(table->dev, sf_dev); + mlx5_sf_dev_remove_aux(table->dev, sf_dev); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c index 169c2c68ed5c..bc863e1f062e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c @@ -95,24 +95,29 @@ mdev_err: static void mlx5_sf_dev_remove(struct auxiliary_device *adev) { struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev); - struct devlink *devlink = priv_to_devlink(sf_dev->mdev); + struct mlx5_core_dev *mdev = sf_dev->mdev; + struct devlink *devlink; - mlx5_drain_health_wq(sf_dev->mdev); + devlink = priv_to_devlink(mdev); + set_bit(MLX5_BREAK_FW_WAIT, &mdev->intf_state); + mlx5_drain_health_wq(mdev); devlink_unregister(devlink); - if (mlx5_dev_is_lightweight(sf_dev->mdev)) - mlx5_uninit_one_light(sf_dev->mdev); + if (mlx5_dev_is_lightweight(mdev)) + mlx5_uninit_one_light(mdev); else - mlx5_uninit_one(sf_dev->mdev); - iounmap(sf_dev->mdev->iseg); - mlx5_mdev_uninit(sf_dev->mdev); + mlx5_uninit_one(mdev); + iounmap(mdev->iseg); + mlx5_mdev_uninit(mdev); mlx5_devlink_free(devlink); } static void mlx5_sf_dev_shutdown(struct auxiliary_device *adev) { struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev); + struct mlx5_core_dev *mdev = sf_dev->mdev; - mlx5_unload_one(sf_dev->mdev, false); + set_bit(MLX5_BREAK_FW_WAIT, &mdev->intf_state); + mlx5_unload_one(mdev, false); } static const struct auxiliary_device_id mlx5_sf_dev_id_table[] = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index 6ea88a581804..2ebb61ef3ea9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -57,7 +57,8 @@ static const char *dr_action_id_to_str(enum mlx5dr_action_type action_id) static bool mlx5dr_action_supp_fwd_fdb_multi_ft(struct mlx5_core_dev *dev) { - return (MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_any_table_limit_regc) || + return (MLX5_CAP_GEN(dev, steering_format_version) < MLX5_STEERING_FORMAT_CONNECTX_6DX || + MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_any_table_limit_regc) || MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_any_table)); } @@ -787,6 +788,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, switch (action_type) { case DR_ACTION_TYP_DROP: attr.final_icm_addr = nic_dmn->drop_icm_addr; + attr.hit_gvmi = nic_dmn->drop_icm_addr >> 48; break; case DR_ACTION_TYP_FT: dest_action = action; @@ -872,11 +874,17 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, action->sampler->tx_icm_addr; break; case DR_ACTION_TYP_VPORT: - attr.hit_gvmi = action->vport->caps->vhca_gvmi; - dest_action = action; - attr.final_icm_addr = rx_rule ? - action->vport->caps->icm_address_rx : - action->vport->caps->icm_address_tx; + if (unlikely(rx_rule && action->vport->caps->num == MLX5_VPORT_UPLINK)) { + /* can't go to uplink on RX rule - dropping instead */ + attr.final_icm_addr = nic_dmn->drop_icm_addr; + attr.hit_gvmi = nic_dmn->drop_icm_addr >> 48; + } else { + attr.hit_gvmi = action->vport->caps->vhca_gvmi; + dest_action = action; + attr.final_icm_addr = rx_rule ? + action->vport->caps->icm_address_rx : + action->vport->caps->icm_address_tx; + } break; case DR_ACTION_TYP_POP_VLAN: if (!rx_rule && !(dmn->ste_ctx->actions_caps & @@ -1169,7 +1177,6 @@ mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn, bool ignore_flow_level, u32 flow_source) { - struct mlx5dr_cmd_flow_destination_hw_info tmp_hw_dest; struct mlx5dr_cmd_flow_destination_hw_info *hw_dests; struct mlx5dr_action **ref_actions; struct mlx5dr_action *action; @@ -1248,11 +1255,8 @@ mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn, * one that done in the TX. * So, if one of the ft target is wire, put it at the end of the dest list. */ - if (is_ft_wire && num_dst_ft > 1) { - tmp_hw_dest = hw_dests[last_dest]; - hw_dests[last_dest] = hw_dests[num_of_dests - 1]; - hw_dests[num_of_dests - 1] = tmp_hw_dest; - } + if (is_ft_wire && num_dst_ft > 1) + swap(hw_dests[last_dest], hw_dests[num_of_dests - 1]); action = dr_action_create_generic(DR_ACTION_TYP_FT); if (!action) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c index 7e36e1062139..64f4cc284aea 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c @@ -54,6 +54,107 @@ enum dr_dump_rec_type { DR_DUMP_REC_TYPE_ACTION_MATCH_RANGE = 3425, }; +static struct mlx5dr_dbg_dump_buff * +mlx5dr_dbg_dump_data_init_new_buff(struct mlx5dr_dbg_dump_data *dump_data) +{ + struct mlx5dr_dbg_dump_buff *new_buff; + + new_buff = kzalloc(sizeof(*new_buff), GFP_KERNEL); + if (!new_buff) + return NULL; + + new_buff->buff = kvzalloc(MLX5DR_DEBUG_DUMP_BUFF_SIZE, GFP_KERNEL); + if (!new_buff->buff) { + kfree(new_buff); + return NULL; + } + + INIT_LIST_HEAD(&new_buff->node); + list_add_tail(&new_buff->node, &dump_data->buff_list); + + return new_buff; +} + +static struct mlx5dr_dbg_dump_data * +mlx5dr_dbg_create_dump_data(void) +{ + struct mlx5dr_dbg_dump_data *dump_data; + + dump_data = kzalloc(sizeof(*dump_data), GFP_KERNEL); + if (!dump_data) + return NULL; + + INIT_LIST_HEAD(&dump_data->buff_list); + + if (!mlx5dr_dbg_dump_data_init_new_buff(dump_data)) { + kfree(dump_data); + return NULL; + } + + return dump_data; +} + +static void +mlx5dr_dbg_destroy_dump_data(struct mlx5dr_dbg_dump_data *dump_data) +{ + struct mlx5dr_dbg_dump_buff *dump_buff, *tmp_buff; + + if (!dump_data) + return; + + list_for_each_entry_safe(dump_buff, tmp_buff, &dump_data->buff_list, node) { + kvfree(dump_buff->buff); + list_del(&dump_buff->node); + kfree(dump_buff); + } + + kfree(dump_data); +} + +static int +mlx5dr_dbg_dump_data_print(struct seq_file *file, char *str, u32 size) +{ + struct mlx5dr_domain *dmn = file->private; + struct mlx5dr_dbg_dump_data *dump_data; + struct mlx5dr_dbg_dump_buff *buff; + u32 buff_capacity, write_size; + int remain_size, ret; + + if (size >= MLX5DR_DEBUG_DUMP_BUFF_SIZE) + return -EINVAL; + + dump_data = dmn->dump_info.dump_data; + buff = list_last_entry(&dump_data->buff_list, + struct mlx5dr_dbg_dump_buff, node); + + buff_capacity = (MLX5DR_DEBUG_DUMP_BUFF_SIZE - 1) - buff->index; + remain_size = buff_capacity - size; + write_size = (remain_size > 0) ? size : buff_capacity; + + if (likely(write_size)) { + ret = snprintf(buff->buff + buff->index, write_size + 1, "%s", str); + if (ret < 0) + return ret; + + buff->index += write_size; + } + + if (remain_size < 0) { + remain_size *= -1; + buff = mlx5dr_dbg_dump_data_init_new_buff(dump_data); + if (!buff) + return -ENOMEM; + + ret = snprintf(buff->buff, remain_size + 1, "%s", str + write_size); + if (ret < 0) + return ret; + + buff->index += remain_size; + } + + return 0; +} + void mlx5dr_dbg_tbl_add(struct mlx5dr_table *tbl) { mutex_lock(&tbl->dmn->dump_info.dbg_mutex); @@ -109,36 +210,68 @@ dr_dump_rule_action_mem(struct seq_file *file, const u64 rule_id, { struct mlx5dr_action *action = action_mem->action; const u64 action_id = DR_DBG_PTR_TO_ID(action); + char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH]; u64 hit_tbl_ptr, miss_tbl_ptr; u32 hit_tbl_id, miss_tbl_id; + int ret; switch (action->action_type) { case DR_ACTION_TYP_DROP: - seq_printf(file, "%d,0x%llx,0x%llx\n", - DR_DUMP_REC_TYPE_ACTION_DROP, action_id, rule_id); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx\n", + DR_DUMP_REC_TYPE_ACTION_DROP, action_id, + rule_id); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; break; case DR_ACTION_TYP_FT: if (action->dest_tbl->is_fw_tbl) - seq_printf(file, "%d,0x%llx,0x%llx,0x%x,0x%x\n", - DR_DUMP_REC_TYPE_ACTION_FT, action_id, - rule_id, action->dest_tbl->fw_tbl.id, - -1); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx,0x%x,0x%x\n", + DR_DUMP_REC_TYPE_ACTION_FT, action_id, + rule_id, action->dest_tbl->fw_tbl.id, + -1); else - seq_printf(file, "%d,0x%llx,0x%llx,0x%x,0x%llx\n", - DR_DUMP_REC_TYPE_ACTION_FT, action_id, - rule_id, action->dest_tbl->tbl->table_id, - DR_DBG_PTR_TO_ID(action->dest_tbl->tbl)); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx,0x%x,0x%llx\n", + DR_DUMP_REC_TYPE_ACTION_FT, action_id, + rule_id, action->dest_tbl->tbl->table_id, + DR_DBG_PTR_TO_ID(action->dest_tbl->tbl)); + + if (ret < 0) + return ret; + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; break; case DR_ACTION_TYP_CTR: - seq_printf(file, "%d,0x%llx,0x%llx,0x%x\n", - DR_DUMP_REC_TYPE_ACTION_CTR, action_id, rule_id, - action->ctr->ctr_id + action->ctr->offset); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx,0x%x\n", + DR_DUMP_REC_TYPE_ACTION_CTR, action_id, rule_id, + action->ctr->ctr_id + action->ctr->offset); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; break; case DR_ACTION_TYP_TAG: - seq_printf(file, "%d,0x%llx,0x%llx,0x%x\n", - DR_DUMP_REC_TYPE_ACTION_TAG, action_id, rule_id, - action->flow_tag->flow_tag); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx,0x%x\n", + DR_DUMP_REC_TYPE_ACTION_TAG, action_id, rule_id, + action->flow_tag->flow_tag); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; break; case DR_ACTION_TYP_MODIFY_HDR: { @@ -150,83 +283,171 @@ dr_dump_rule_action_mem(struct seq_file *file, const u64 rule_id, ptrn_arg = !action->rewrite->single_action_opt && ptrn && arg; - seq_printf(file, "%d,0x%llx,0x%llx,0x%x,%d,0x%x,0x%x,0x%x", - DR_DUMP_REC_TYPE_ACTION_MODIFY_HDR, action_id, - rule_id, action->rewrite->index, - action->rewrite->single_action_opt, - ptrn_arg ? action->rewrite->num_of_actions : 0, - ptrn_arg ? ptrn->index : 0, - ptrn_arg ? mlx5dr_arg_get_obj_id(arg) : 0); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx,0x%x,%d,0x%x,0x%x,0x%x", + DR_DUMP_REC_TYPE_ACTION_MODIFY_HDR, action_id, + rule_id, action->rewrite->index, + action->rewrite->single_action_opt, + ptrn_arg ? action->rewrite->num_of_actions : 0, + ptrn_arg ? ptrn->index : 0, + ptrn_arg ? mlx5dr_arg_get_obj_id(arg) : 0); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; if (ptrn_arg) { for (i = 0; i < action->rewrite->num_of_actions; i++) { - seq_printf(file, ",0x%016llx", - be64_to_cpu(((__be64 *)rewrite_data)[i])); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + ",0x%016llx", + be64_to_cpu(((__be64 *)rewrite_data)[i])); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; } } - seq_puts(file, "\n"); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, "\n"); + if (ret < 0) + return ret; + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; break; } case DR_ACTION_TYP_VPORT: - seq_printf(file, "%d,0x%llx,0x%llx,0x%x\n", - DR_DUMP_REC_TYPE_ACTION_VPORT, action_id, rule_id, - action->vport->caps->num); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx,0x%x\n", + DR_DUMP_REC_TYPE_ACTION_VPORT, action_id, rule_id, + action->vport->caps->num); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; break; case DR_ACTION_TYP_TNL_L2_TO_L2: - seq_printf(file, "%d,0x%llx,0x%llx\n", - DR_DUMP_REC_TYPE_ACTION_DECAP_L2, action_id, - rule_id); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx\n", + DR_DUMP_REC_TYPE_ACTION_DECAP_L2, action_id, + rule_id); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; break; case DR_ACTION_TYP_TNL_L3_TO_L2: - seq_printf(file, "%d,0x%llx,0x%llx,0x%x\n", - DR_DUMP_REC_TYPE_ACTION_DECAP_L3, action_id, - rule_id, - (action->rewrite->ptrn && action->rewrite->arg) ? - mlx5dr_arg_get_obj_id(action->rewrite->arg) : - action->rewrite->index); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx,0x%x\n", + DR_DUMP_REC_TYPE_ACTION_DECAP_L3, action_id, + rule_id, + (action->rewrite->ptrn && action->rewrite->arg) ? + mlx5dr_arg_get_obj_id(action->rewrite->arg) : + action->rewrite->index); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; break; case DR_ACTION_TYP_L2_TO_TNL_L2: - seq_printf(file, "%d,0x%llx,0x%llx,0x%x\n", - DR_DUMP_REC_TYPE_ACTION_ENCAP_L2, action_id, - rule_id, action->reformat->id); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx,0x%x\n", + DR_DUMP_REC_TYPE_ACTION_ENCAP_L2, action_id, + rule_id, action->reformat->id); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; break; case DR_ACTION_TYP_L2_TO_TNL_L3: - seq_printf(file, "%d,0x%llx,0x%llx,0x%x\n", - DR_DUMP_REC_TYPE_ACTION_ENCAP_L3, action_id, - rule_id, action->reformat->id); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx,0x%x\n", + DR_DUMP_REC_TYPE_ACTION_ENCAP_L3, action_id, + rule_id, action->reformat->id); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; break; case DR_ACTION_TYP_POP_VLAN: - seq_printf(file, "%d,0x%llx,0x%llx\n", - DR_DUMP_REC_TYPE_ACTION_POP_VLAN, action_id, - rule_id); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx\n", + DR_DUMP_REC_TYPE_ACTION_POP_VLAN, action_id, + rule_id); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; break; case DR_ACTION_TYP_PUSH_VLAN: - seq_printf(file, "%d,0x%llx,0x%llx,0x%x\n", - DR_DUMP_REC_TYPE_ACTION_PUSH_VLAN, action_id, - rule_id, action->push_vlan->vlan_hdr); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx,0x%x\n", + DR_DUMP_REC_TYPE_ACTION_PUSH_VLAN, action_id, + rule_id, action->push_vlan->vlan_hdr); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; break; case DR_ACTION_TYP_INSERT_HDR: - seq_printf(file, "%d,0x%llx,0x%llx,0x%x,0x%x,0x%x\n", - DR_DUMP_REC_TYPE_ACTION_INSERT_HDR, action_id, - rule_id, action->reformat->id, - action->reformat->param_0, - action->reformat->param_1); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx,0x%x,0x%x,0x%x\n", + DR_DUMP_REC_TYPE_ACTION_INSERT_HDR, action_id, + rule_id, action->reformat->id, + action->reformat->param_0, + action->reformat->param_1); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; break; case DR_ACTION_TYP_REMOVE_HDR: - seq_printf(file, "%d,0x%llx,0x%llx,0x%x,0x%x,0x%x\n", - DR_DUMP_REC_TYPE_ACTION_REMOVE_HDR, action_id, - rule_id, action->reformat->id, - action->reformat->param_0, - action->reformat->param_1); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx,0x%x,0x%x,0x%x\n", + DR_DUMP_REC_TYPE_ACTION_REMOVE_HDR, action_id, + rule_id, action->reformat->id, + action->reformat->param_0, + action->reformat->param_1); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; break; case DR_ACTION_TYP_SAMPLER: - seq_printf(file, - "%d,0x%llx,0x%llx,0x%x,0x%x,0x%x,0x%llx,0x%llx\n", - DR_DUMP_REC_TYPE_ACTION_SAMPLER, action_id, rule_id, - 0, 0, action->sampler->sampler_id, - action->sampler->rx_icm_addr, - action->sampler->tx_icm_addr); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx,0x%x,0x%x,0x%x,0x%llx,0x%llx\n", + DR_DUMP_REC_TYPE_ACTION_SAMPLER, action_id, + rule_id, 0, 0, action->sampler->sampler_id, + action->sampler->rx_icm_addr, + action->sampler->tx_icm_addr); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; break; case DR_ACTION_TYP_RANGE: if (action->range->hit_tbl_action->dest_tbl->is_fw_tbl) { @@ -247,10 +468,17 @@ dr_dump_rule_action_mem(struct seq_file *file, const u64 rule_id, DR_DBG_PTR_TO_ID(action->range->miss_tbl_action->dest_tbl->tbl); } - seq_printf(file, "%d,0x%llx,0x%llx,0x%x,0x%llx,0x%x,0x%llx,0x%x\n", - DR_DUMP_REC_TYPE_ACTION_MATCH_RANGE, action_id, rule_id, - hit_tbl_id, hit_tbl_ptr, miss_tbl_id, miss_tbl_ptr, - action->range->definer_id); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx,0x%x,0x%llx,0x%x,0x%llx,0x%x\n", + DR_DUMP_REC_TYPE_ACTION_MATCH_RANGE, action_id, + rule_id, hit_tbl_id, hit_tbl_ptr, miss_tbl_id, + miss_tbl_ptr, action->range->definer_id); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; break; default: return 0; @@ -263,8 +491,10 @@ static int dr_dump_rule_mem(struct seq_file *file, struct mlx5dr_ste *ste, bool is_rx, const u64 rule_id, u8 format_ver) { + char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH]; char hw_ste_dump[DR_HEX_SIZE]; u32 mem_rec_type; + int ret; if (format_ver == MLX5_STEERING_FORMAT_CONNECTX_5) { mem_rec_type = is_rx ? DR_DUMP_REC_TYPE_RULE_RX_ENTRY_V0 : @@ -277,9 +507,16 @@ dr_dump_rule_mem(struct seq_file *file, struct mlx5dr_ste *ste, dr_dump_hex_print(hw_ste_dump, (char *)mlx5dr_ste_get_hw_ste(ste), DR_STE_SIZE_REDUCED); - seq_printf(file, "%d,0x%llx,0x%llx,%s\n", mem_rec_type, - dr_dump_icm_to_idx(mlx5dr_ste_get_icm_addr(ste)), rule_id, - hw_ste_dump); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx,%s\n", mem_rec_type, + dr_dump_icm_to_idx(mlx5dr_ste_get_icm_addr(ste)), + rule_id, hw_ste_dump); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; return 0; } @@ -309,6 +546,7 @@ static int dr_dump_rule(struct seq_file *file, struct mlx5dr_rule *rule) { struct mlx5dr_rule_action_member *action_mem; const u64 rule_id = DR_DBG_PTR_TO_ID(rule); + char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH]; struct mlx5dr_rule_rx_tx *rx = &rule->rx; struct mlx5dr_rule_rx_tx *tx = &rule->tx; u8 format_ver; @@ -316,8 +554,15 @@ static int dr_dump_rule(struct seq_file *file, struct mlx5dr_rule *rule) format_ver = rule->matcher->tbl->dmn->info.caps.sw_format_ver; - seq_printf(file, "%d,0x%llx,0x%llx\n", DR_DUMP_REC_TYPE_RULE, rule_id, - DR_DBG_PTR_TO_ID(rule->matcher)); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx\n", DR_DUMP_REC_TYPE_RULE, + rule_id, DR_DBG_PTR_TO_ID(rule->matcher)); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; if (rx->nic_matcher) { ret = dr_dump_rule_rx_tx(file, rx, true, rule_id, format_ver); @@ -344,46 +589,94 @@ static int dr_dump_matcher_mask(struct seq_file *file, struct mlx5dr_match_param *mask, u8 criteria, const u64 matcher_id) { + char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH]; char dump[DR_HEX_SIZE]; + int ret; - seq_printf(file, "%d,0x%llx,", DR_DUMP_REC_TYPE_MATCHER_MASK, - matcher_id); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, "%d,0x%llx,", + DR_DUMP_REC_TYPE_MATCHER_MASK, matcher_id); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; if (criteria & DR_MATCHER_CRITERIA_OUTER) { dr_dump_hex_print(dump, (char *)&mask->outer, sizeof(mask->outer)); - seq_printf(file, "%s,", dump); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%s,", dump); } else { - seq_puts(file, ","); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, ","); } + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; + if (criteria & DR_MATCHER_CRITERIA_INNER) { dr_dump_hex_print(dump, (char *)&mask->inner, sizeof(mask->inner)); - seq_printf(file, "%s,", dump); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%s,", dump); } else { - seq_puts(file, ","); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, ","); } + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; + if (criteria & DR_MATCHER_CRITERIA_MISC) { dr_dump_hex_print(dump, (char *)&mask->misc, sizeof(mask->misc)); - seq_printf(file, "%s,", dump); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%s,", dump); } else { - seq_puts(file, ","); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, ","); } + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; + if (criteria & DR_MATCHER_CRITERIA_MISC2) { dr_dump_hex_print(dump, (char *)&mask->misc2, sizeof(mask->misc2)); - seq_printf(file, "%s,", dump); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%s,", dump); } else { - seq_puts(file, ","); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, ","); } + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; + if (criteria & DR_MATCHER_CRITERIA_MISC3) { dr_dump_hex_print(dump, (char *)&mask->misc3, sizeof(mask->misc3)); - seq_printf(file, "%s\n", dump); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%s\n", dump); } else { - seq_puts(file, ",\n"); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, ",\n"); } + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; + return 0; } @@ -391,9 +684,19 @@ static int dr_dump_matcher_builder(struct seq_file *file, struct mlx5dr_ste_build *builder, u32 index, bool is_rx, const u64 matcher_id) { - seq_printf(file, "%d,0x%llx,%d,%d,0x%x\n", - DR_DUMP_REC_TYPE_MATCHER_BUILDER, matcher_id, index, is_rx, - builder->lu_type); + char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH]; + int ret; + + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,%d,%d,0x%x\n", + DR_DUMP_REC_TYPE_MATCHER_BUILDER, matcher_id, index, + is_rx, builder->lu_type); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; return 0; } @@ -403,6 +706,7 @@ dr_dump_matcher_rx_tx(struct seq_file *file, bool is_rx, struct mlx5dr_matcher_rx_tx *matcher_rx_tx, const u64 matcher_id) { + char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH]; enum dr_dump_rec_type rec_type; u64 s_icm_addr, e_icm_addr; int i, ret; @@ -412,11 +716,19 @@ dr_dump_matcher_rx_tx(struct seq_file *file, bool is_rx, s_icm_addr = mlx5dr_icm_pool_get_chunk_icm_addr(matcher_rx_tx->s_htbl->chunk); e_icm_addr = mlx5dr_icm_pool_get_chunk_icm_addr(matcher_rx_tx->e_anchor->chunk); - seq_printf(file, "%d,0x%llx,0x%llx,%d,0x%llx,0x%llx\n", - rec_type, DR_DBG_PTR_TO_ID(matcher_rx_tx), - matcher_id, matcher_rx_tx->num_of_builders, - dr_dump_icm_to_idx(s_icm_addr), - dr_dump_icm_to_idx(e_icm_addr)); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx,%d,0x%llx,0x%llx\n", + rec_type, DR_DBG_PTR_TO_ID(matcher_rx_tx), + matcher_id, matcher_rx_tx->num_of_builders, + dr_dump_icm_to_idx(s_icm_addr), + dr_dump_icm_to_idx(e_icm_addr)); + + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; for (i = 0; i < matcher_rx_tx->num_of_builders; i++) { ret = dr_dump_matcher_builder(file, @@ -434,13 +746,22 @@ dr_dump_matcher(struct seq_file *file, struct mlx5dr_matcher *matcher) { struct mlx5dr_matcher_rx_tx *rx = &matcher->rx; struct mlx5dr_matcher_rx_tx *tx = &matcher->tx; + char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH]; u64 matcher_id; int ret; matcher_id = DR_DBG_PTR_TO_ID(matcher); - seq_printf(file, "%d,0x%llx,0x%llx,%d\n", DR_DUMP_REC_TYPE_MATCHER, - matcher_id, DR_DBG_PTR_TO_ID(matcher->tbl), matcher->prio); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx,%d\n", DR_DUMP_REC_TYPE_MATCHER, + matcher_id, DR_DBG_PTR_TO_ID(matcher->tbl), + matcher->prio); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; ret = dr_dump_matcher_mask(file, &matcher->mask, matcher->match_criteria, matcher_id); @@ -486,15 +807,24 @@ dr_dump_table_rx_tx(struct seq_file *file, bool is_rx, struct mlx5dr_table_rx_tx *table_rx_tx, const u64 table_id) { + char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH]; enum dr_dump_rec_type rec_type; u64 s_icm_addr; + int ret; rec_type = is_rx ? DR_DUMP_REC_TYPE_TABLE_RX : DR_DUMP_REC_TYPE_TABLE_TX; s_icm_addr = mlx5dr_icm_pool_get_chunk_icm_addr(table_rx_tx->s_anchor->chunk); - seq_printf(file, "%d,0x%llx,0x%llx\n", rec_type, table_id, - dr_dump_icm_to_idx(s_icm_addr)); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx\n", rec_type, table_id, + dr_dump_icm_to_idx(s_icm_addr)); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; return 0; } @@ -503,11 +833,19 @@ static int dr_dump_table(struct seq_file *file, struct mlx5dr_table *table) { struct mlx5dr_table_rx_tx *rx = &table->rx; struct mlx5dr_table_rx_tx *tx = &table->tx; + char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH]; int ret; - seq_printf(file, "%d,0x%llx,0x%llx,%d,%d\n", DR_DUMP_REC_TYPE_TABLE, - DR_DBG_PTR_TO_ID(table), DR_DBG_PTR_TO_ID(table->dmn), - table->table_type, table->level); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx,%d,%d\n", DR_DUMP_REC_TYPE_TABLE, + DR_DBG_PTR_TO_ID(table), DR_DBG_PTR_TO_ID(table->dmn), + table->table_type, table->level); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; if (rx->nic_dmn) { ret = dr_dump_table_rx_tx(file, true, rx, @@ -546,46 +884,86 @@ static int dr_dump_send_ring(struct seq_file *file, struct mlx5dr_send_ring *ring, const u64 domain_id) { - seq_printf(file, "%d,0x%llx,0x%llx,0x%x,0x%x\n", - DR_DUMP_REC_TYPE_DOMAIN_SEND_RING, DR_DBG_PTR_TO_ID(ring), - domain_id, ring->cq->mcq.cqn, ring->qp->qpn); + char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH]; + int ret; + + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%llx,0x%x,0x%x\n", + DR_DUMP_REC_TYPE_DOMAIN_SEND_RING, + DR_DBG_PTR_TO_ID(ring), domain_id, + ring->cq->mcq.cqn, ring->qp->qpn); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; + return 0; } -static int +static noinline_for_stack int dr_dump_domain_info_flex_parser(struct seq_file *file, const char *flex_parser_name, const u8 flex_parser_value, const u64 domain_id) { - seq_printf(file, "%d,0x%llx,%s,0x%x\n", - DR_DUMP_REC_TYPE_DOMAIN_INFO_FLEX_PARSER, domain_id, - flex_parser_name, flex_parser_value); + char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH]; + int ret; + + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,%s,0x%x\n", + DR_DUMP_REC_TYPE_DOMAIN_INFO_FLEX_PARSER, domain_id, + flex_parser_name, flex_parser_value); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; + return 0; } -static int +static noinline_for_stack int dr_dump_domain_info_caps(struct seq_file *file, struct mlx5dr_cmd_caps *caps, const u64 domain_id) { + char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH]; struct mlx5dr_cmd_vport_cap *vport_caps; unsigned long i, vports_num; + int ret; xa_for_each(&caps->vports.vports_caps_xa, vports_num, vport_caps) ; /* count the number of vports in xarray */ - seq_printf(file, "%d,0x%llx,0x%x,0x%llx,0x%llx,0x%x,%lu,%d\n", - DR_DUMP_REC_TYPE_DOMAIN_INFO_CAPS, domain_id, caps->gvmi, - caps->nic_rx_drop_address, caps->nic_tx_drop_address, - caps->flex_protocols, vports_num, caps->eswitch_manager); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,0x%x,0x%llx,0x%llx,0x%x,%lu,%d\n", + DR_DUMP_REC_TYPE_DOMAIN_INFO_CAPS, domain_id, caps->gvmi, + caps->nic_rx_drop_address, caps->nic_tx_drop_address, + caps->flex_protocols, vports_num, caps->eswitch_manager); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; xa_for_each(&caps->vports.vports_caps_xa, i, vport_caps) { vport_caps = xa_load(&caps->vports.vports_caps_xa, i); - seq_printf(file, "%d,0x%llx,%lu,0x%x,0x%llx,0x%llx\n", - DR_DUMP_REC_TYPE_DOMAIN_INFO_VPORT, domain_id, i, - vport_caps->vport_gvmi, vport_caps->icm_address_rx, - vport_caps->icm_address_tx); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,%lu,0x%x,0x%llx,0x%llx\n", + DR_DUMP_REC_TYPE_DOMAIN_INFO_VPORT, + domain_id, i, vport_caps->vport_gvmi, + vport_caps->icm_address_rx, + vport_caps->icm_address_tx); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; } return 0; } @@ -627,24 +1005,32 @@ dr_dump_domain_info(struct seq_file *file, struct mlx5dr_domain_info *info, return 0; } -static int +static noinline_for_stack int dr_dump_domain(struct seq_file *file, struct mlx5dr_domain *dmn) { + char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH]; u64 domain_id = DR_DBG_PTR_TO_ID(dmn); int ret; - seq_printf(file, "%d,0x%llx,%d,0%x,%d,%u.%u.%u,%s,%d,%u,%u,%u\n", - DR_DUMP_REC_TYPE_DOMAIN, - domain_id, dmn->type, dmn->info.caps.gvmi, - dmn->info.supp_sw_steering, - /* package version */ - LINUX_VERSION_MAJOR, LINUX_VERSION_PATCHLEVEL, - LINUX_VERSION_SUBLEVEL, - pci_name(dmn->mdev->pdev), - 0, /* domain flags */ - dmn->num_buddies[DR_ICM_TYPE_STE], - dmn->num_buddies[DR_ICM_TYPE_MODIFY_ACTION], - dmn->num_buddies[DR_ICM_TYPE_MODIFY_HDR_PTRN]); + ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, + "%d,0x%llx,%d,0%x,%d,%u.%u.%u,%s,%d,%u,%u,%u\n", + DR_DUMP_REC_TYPE_DOMAIN, + domain_id, dmn->type, dmn->info.caps.gvmi, + dmn->info.supp_sw_steering, + /* package version */ + LINUX_VERSION_MAJOR, LINUX_VERSION_PATCHLEVEL, + LINUX_VERSION_SUBLEVEL, + pci_name(dmn->mdev->pdev), + 0, /* domain flags */ + dmn->num_buddies[DR_ICM_TYPE_STE], + dmn->num_buddies[DR_ICM_TYPE_MODIFY_ACTION], + dmn->num_buddies[DR_ICM_TYPE_MODIFY_HDR_PTRN]); + if (ret < 0) + return ret; + + ret = mlx5dr_dbg_dump_data_print(file, buff, ret); + if (ret) + return ret; ret = dr_dump_domain_info(file, &dmn->info, domain_id); if (ret < 0) @@ -683,11 +1069,91 @@ unlock_mutex: return ret; } -static int dr_dump_show(struct seq_file *file, void *priv) +static void * +dr_dump_start(struct seq_file *file, loff_t *pos) { - return dr_dump_domain_all(file, file->private); + struct mlx5dr_domain *dmn = file->private; + struct mlx5dr_dbg_dump_data *dump_data; + + if (atomic_read(&dmn->dump_info.state) != MLX5DR_DEBUG_DUMP_STATE_FREE) { + mlx5_core_warn(dmn->mdev, "Dump already in progress\n"); + return ERR_PTR(-EBUSY); + } + + atomic_set(&dmn->dump_info.state, MLX5DR_DEBUG_DUMP_STATE_IN_PROGRESS); + dump_data = dmn->dump_info.dump_data; + + if (dump_data) { + return seq_list_start(&dump_data->buff_list, *pos); + } else if (*pos == 0) { + dump_data = mlx5dr_dbg_create_dump_data(); + if (!dump_data) + goto exit; + + dmn->dump_info.dump_data = dump_data; + if (dr_dump_domain_all(file, dmn)) { + mlx5dr_dbg_destroy_dump_data(dump_data); + dmn->dump_info.dump_data = NULL; + goto exit; + } + + return seq_list_start(&dump_data->buff_list, *pos); + } + +exit: + atomic_set(&dmn->dump_info.state, MLX5DR_DEBUG_DUMP_STATE_FREE); + return NULL; } -DEFINE_SHOW_ATTRIBUTE(dr_dump); + +static void * +dr_dump_next(struct seq_file *file, void *v, loff_t *pos) +{ + struct mlx5dr_domain *dmn = file->private; + struct mlx5dr_dbg_dump_data *dump_data; + + dump_data = dmn->dump_info.dump_data; + + return seq_list_next(v, &dump_data->buff_list, pos); +} + +static void +dr_dump_stop(struct seq_file *file, void *v) +{ + struct mlx5dr_domain *dmn = file->private; + struct mlx5dr_dbg_dump_data *dump_data; + + if (v && IS_ERR(v)) + return; + + if (!v) { + dump_data = dmn->dump_info.dump_data; + if (dump_data) { + mlx5dr_dbg_destroy_dump_data(dump_data); + dmn->dump_info.dump_data = NULL; + } + } + + atomic_set(&dmn->dump_info.state, MLX5DR_DEBUG_DUMP_STATE_FREE); +} + +static int +dr_dump_show(struct seq_file *file, void *v) +{ + struct mlx5dr_dbg_dump_buff *entry; + + entry = list_entry(v, struct mlx5dr_dbg_dump_buff, node); + seq_printf(file, "%s", entry->buff); + + return 0; +} + +static const struct seq_operations dr_dump_sops = { + .start = dr_dump_start, + .next = dr_dump_next, + .stop = dr_dump_stop, + .show = dr_dump_show, +}; +DEFINE_SEQ_ATTRIBUTE(dr_dump); void mlx5dr_dbg_init_dump(struct mlx5dr_domain *dmn) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.h index def6cf853eea..57c6b363b870 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.h @@ -1,10 +1,30 @@ /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ +#define MLX5DR_DEBUG_DUMP_BUFF_SIZE (64 * 1024 * 1024) +#define MLX5DR_DEBUG_DUMP_BUFF_LENGTH 512 + +enum { + MLX5DR_DEBUG_DUMP_STATE_FREE, + MLX5DR_DEBUG_DUMP_STATE_IN_PROGRESS, +}; + +struct mlx5dr_dbg_dump_buff { + char *buff; + u32 index; + struct list_head node; +}; + +struct mlx5dr_dbg_dump_data { + struct list_head buff_list; +}; + struct mlx5dr_dbg_dump_info { struct mutex dbg_mutex; /* protect dbg lists */ struct dentry *steering_debugfs; struct dentry *fdb_debugfs; + struct mlx5dr_dbg_dump_data *dump_data; + atomic_t state; }; void mlx5dr_dbg_init_dump(struct mlx5dr_domain *dmn); 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 4e8527a724f5..6fa06ba2d346 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -52,7 +52,6 @@ struct dr_qp_init_attr { u32 cqn; u32 pdn; u32 max_send_wr; - u32 max_send_sge; struct mlx5_uars_page *uar; u8 isolate_vl_tc:1; }; @@ -247,37 +246,6 @@ static int dr_poll_cq(struct mlx5dr_cq *dr_cq, int ne) return err == CQ_POLL_ERR ? err : npolled; } -static int dr_qp_get_args_update_send_wqe_size(struct dr_qp_init_attr *attr) -{ - return roundup_pow_of_two(sizeof(struct mlx5_wqe_ctrl_seg) + - sizeof(struct mlx5_wqe_flow_update_ctrl_seg) + - sizeof(struct mlx5_wqe_header_modify_argument_update_seg)); -} - -/* We calculate for specific RC QP with the required functionality */ -static int dr_qp_calc_rc_send_wqe(struct dr_qp_init_attr *attr) -{ - int update_arg_size; - int inl_size = 0; - int tot_size; - int size; - - update_arg_size = dr_qp_get_args_update_send_wqe_size(attr); - - size = sizeof(struct mlx5_wqe_ctrl_seg) + - sizeof(struct mlx5_wqe_raddr_seg); - inl_size = size + ALIGN(sizeof(struct mlx5_wqe_inline_seg) + - DR_STE_SIZE, 16); - - size += attr->max_send_sge * sizeof(struct mlx5_wqe_data_seg); - - size = max(size, update_arg_size); - - tot_size = max(size, inl_size); - - return ALIGN(tot_size, MLX5_SEND_WQE_BB); -} - static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev, struct dr_qp_init_attr *attr) { @@ -285,7 +253,6 @@ static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev, u32 temp_qpc[MLX5_ST_SZ_DW(qpc)] = {}; struct mlx5_wq_param wqp; struct mlx5dr_qp *dr_qp; - int wqe_size; int inlen; void *qpc; void *in; @@ -365,15 +332,6 @@ static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev, if (err) goto err_in; dr_qp->uar = attr->uar; - wqe_size = dr_qp_calc_rc_send_wqe(attr); - dr_qp->max_inline_data = min(wqe_size - - (sizeof(struct mlx5_wqe_ctrl_seg) + - sizeof(struct mlx5_wqe_raddr_seg) + - sizeof(struct mlx5_wqe_inline_seg)), - (2 * MLX5_SEND_WQE_BB - - (sizeof(struct mlx5_wqe_ctrl_seg) + - sizeof(struct mlx5_wqe_raddr_seg) + - sizeof(struct mlx5_wqe_inline_seg)))); return dr_qp; @@ -437,48 +395,8 @@ dr_rdma_handle_flow_access_arg_segments(struct mlx5_wqe_ctrl_seg *wq_ctrl, MLX5_SEND_WQE_DS; } -static int dr_set_data_inl_seg(struct mlx5dr_qp *dr_qp, - struct dr_data_seg *data_seg, void *wqe) -{ - int inline_header_size = sizeof(struct mlx5_wqe_ctrl_seg) + - sizeof(struct mlx5_wqe_raddr_seg) + - sizeof(struct mlx5_wqe_inline_seg); - struct mlx5_wqe_inline_seg *seg; - int left_space; - int inl = 0; - void *addr; - int len; - int idx; - - seg = wqe; - wqe += sizeof(*seg); - addr = (void *)(unsigned long)(data_seg->addr); - len = data_seg->length; - inl += len; - left_space = MLX5_SEND_WQE_BB - inline_header_size; - - if (likely(len > left_space)) { - memcpy(wqe, addr, left_space); - len -= left_space; - addr += left_space; - idx = (dr_qp->sq.pc + 1) & (dr_qp->sq.wqe_cnt - 1); - wqe = mlx5_wq_cyc_get_wqe(&dr_qp->wq.sq, idx); - } - - memcpy(wqe, addr, len); - - if (likely(inl)) { - seg->byte_count = cpu_to_be32(inl | MLX5_INLINE_SEG); - return DIV_ROUND_UP(inl + sizeof(seg->byte_count), - MLX5_SEND_WQE_DS); - } else { - return 0; - } -} - static void -dr_rdma_handle_icm_write_segments(struct mlx5dr_qp *dr_qp, - struct mlx5_wqe_ctrl_seg *wq_ctrl, +dr_rdma_handle_icm_write_segments(struct mlx5_wqe_ctrl_seg *wq_ctrl, u64 remote_addr, u32 rkey, struct dr_data_seg *data_seg, @@ -494,17 +412,15 @@ dr_rdma_handle_icm_write_segments(struct mlx5dr_qp *dr_qp, wq_raddr->reserved = 0; wq_dseg = (void *)(wq_raddr + 1); - /* WQE ctrl segment + WQE remote addr segment */ - *size = (sizeof(*wq_ctrl) + sizeof(*wq_raddr)) / MLX5_SEND_WQE_DS; - if (data_seg->send_flags & IB_SEND_INLINE) { - *size += dr_set_data_inl_seg(dr_qp, data_seg, wq_dseg); - } else { - wq_dseg->byte_count = cpu_to_be32(data_seg->length); - wq_dseg->lkey = cpu_to_be32(data_seg->lkey); - wq_dseg->addr = cpu_to_be64(data_seg->addr); - *size += sizeof(*wq_dseg) / MLX5_SEND_WQE_DS; /* WQE data segment */ - } + wq_dseg->byte_count = cpu_to_be32(data_seg->length); + wq_dseg->lkey = cpu_to_be32(data_seg->lkey); + wq_dseg->addr = cpu_to_be64(data_seg->addr); + + *size = (sizeof(*wq_ctrl) + /* WQE ctrl segment */ + sizeof(*wq_dseg) + /* WQE data segment */ + sizeof(*wq_raddr)) / /* WQE remote addr segment */ + MLX5_SEND_WQE_DS; } static void dr_set_ctrl_seg(struct mlx5_wqe_ctrl_seg *wq_ctrl, @@ -535,7 +451,7 @@ static void dr_rdma_segments(struct mlx5dr_qp *dr_qp, u64 remote_addr, switch (opcode) { case MLX5_OPCODE_RDMA_READ: case MLX5_OPCODE_RDMA_WRITE: - dr_rdma_handle_icm_write_segments(dr_qp, wq_ctrl, remote_addr, + dr_rdma_handle_icm_write_segments(wq_ctrl, remote_addr, rkey, data_seg, &size); break; case MLX5_OPCODE_FLOW_TBL_ACCESS: @@ -656,7 +572,7 @@ static void dr_fill_write_args_segs(struct mlx5dr_send_ring *send_ring, if (send_ring->pending_wqe % send_ring->signal_th == 0) send_info->write.send_flags |= IB_SEND_SIGNALED; else - send_info->write.send_flags &= ~IB_SEND_SIGNALED; + send_info->write.send_flags = 0; } static void dr_fill_write_icm_segs(struct mlx5dr_domain *dmn, @@ -680,13 +596,9 @@ static void dr_fill_write_icm_segs(struct mlx5dr_domain *dmn, } send_ring->pending_wqe++; - if (!send_info->write.lkey) - send_info->write.send_flags |= IB_SEND_INLINE; if (send_ring->pending_wqe % send_ring->signal_th == 0) send_info->write.send_flags |= IB_SEND_SIGNALED; - else - send_info->write.send_flags &= ~IB_SEND_SIGNALED; send_ring->pending_wqe++; send_info->read.length = send_info->write.length; @@ -696,9 +608,9 @@ static void dr_fill_write_icm_segs(struct mlx5dr_domain *dmn, send_info->read.lkey = send_ring->sync_mr->mkey; if (send_ring->pending_wqe % send_ring->signal_th == 0) - send_info->read.send_flags |= IB_SEND_SIGNALED; + send_info->read.send_flags = IB_SEND_SIGNALED; else - send_info->read.send_flags &= ~IB_SEND_SIGNALED; + send_info->read.send_flags = 0; } static void dr_fill_data_segs(struct mlx5dr_domain *dmn, @@ -1345,7 +1257,6 @@ int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn) dmn->send_ring->cq->qp = dmn->send_ring->qp; dmn->info.max_send_wr = QUEUE_SIZE; - init_attr.max_send_sge = 1; dmn->info.max_inline_size = min(dmn->send_ring->qp->max_inline_data, DR_STE_SIZE); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 5a31fb47ffa5..1005bb6935b6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -277,7 +277,7 @@ int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev, req_list_size = max_list_size; } - out_sz = MLX5_ST_SZ_BYTES(query_nic_vport_context_in) + + out_sz = MLX5_ST_SZ_BYTES(query_nic_vport_context_out) + req_list_size * MLX5_ST_SZ_BYTES(mac_address_layout); out = kvzalloc(out_sz, GFP_KERNEL); @@ -440,6 +440,27 @@ out: } EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_system_image_guid); +int mlx5_query_nic_vport_sd_group(struct mlx5_core_dev *mdev, u8 *sd_group) +{ + int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out); + u32 *out; + int err; + + out = kvzalloc(outlen, GFP_KERNEL); + if (!out) + return -ENOMEM; + + err = mlx5_query_nic_vport_context(mdev, 0, out); + if (err) + goto out; + + *sd_group = MLX5_GET(query_nic_vport_context_out, out, + nic_vport_context.sd_group); +out: + kvfree(out); + return err; +} + int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid) { u32 *out; |