diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx5/core')
61 files changed, 2817 insertions, 1281 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index 3e371d24c462..6e4d7bb7fea2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -6,6 +6,7 @@ config MLX5_CORE tristate "Mellanox 5th generation network adapters (ConnectX series) core driver" depends on PCI + select AUXILIARY_BUS select NET_DEVLINK depends on VXLAN || !VXLAN depends on MLXFW || !MLXFW diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 2d477f9a8cb7..77961643d5a9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -25,7 +25,7 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \ en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \ en_selftest.o en/port.o en/monitor_stats.o en/health.o \ en/reporter_tx.o en/reporter_rx.o en/params.o en/xsk/pool.o \ - en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o en/devlink.o + en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o en/devlink.o en/ptp.o # # Netdev extra @@ -81,7 +81,7 @@ mlx5_core-$(CONFIG_MLX5_EN_TLS) += en_accel/tls.o en_accel/tls_rxtx.o en_accel/t mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/dr_domain.o steering/dr_table.o \ steering/dr_matcher.o steering/dr_rule.o \ - steering/dr_icm_pool.o \ + steering/dr_icm_pool.o steering/dr_buddy.o \ steering/dr_ste.o steering/dr_send.o \ steering/dr_cmd.o steering/dr_fw.o \ steering/dr_action.o steering/fs_dr.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index e49387dbef98..50c7b9ee80c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -2142,7 +2142,6 @@ dma_pool_err: kvfree(cmd->stats); return err; } -EXPORT_SYMBOL(mlx5_cmd_init); void mlx5_cmd_cleanup(struct mlx5_core_dev *dev) { @@ -2155,11 +2154,9 @@ void mlx5_cmd_cleanup(struct mlx5_core_dev *dev) dma_pool_destroy(cmd->pool); kvfree(cmd->stats); } -EXPORT_SYMBOL(mlx5_cmd_cleanup); void mlx5_cmd_set_state(struct mlx5_core_dev *dev, enum mlx5_cmdif_state cmdif_state) { dev->cmd.state = cmdif_state; } -EXPORT_SYMBOL(mlx5_cmd_set_state); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index 1972ddd12704..b051417ede67 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -31,313 +31,484 @@ */ #include <linux/mlx5/driver.h> +#include <linux/mlx5/eswitch.h> +#include <linux/mlx5/mlx5_ifc_vdpa.h> #include "mlx5_core.h" -static LIST_HEAD(intf_list); -static LIST_HEAD(mlx5_dev_list); /* intf dev list mutex */ static DEFINE_MUTEX(mlx5_intf_mutex); +static DEFINE_IDA(mlx5_adev_ida); -struct mlx5_device_context { - struct list_head list; - struct mlx5_interface *intf; - void *context; - unsigned long state; -}; +static bool is_eth_rep_supported(struct mlx5_core_dev *dev) +{ + if (!IS_ENABLED(CONFIG_MLX5_ESWITCH)) + return false; -enum { - MLX5_INTERFACE_ADDED, - MLX5_INTERFACE_ATTACHED, -}; + if (!MLX5_ESWITCH_MANAGER(dev)) + return false; + if (!is_mdev_switchdev_mode(dev)) + return false; -void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv) + return true; +} + +static bool is_eth_supported(struct mlx5_core_dev *dev) { - struct mlx5_device_context *dev_ctx; - struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv); + if (!IS_ENABLED(CONFIG_MLX5_CORE_EN)) + return false; - if (!mlx5_lag_intf_add(intf, priv)) - return; + if (is_eth_rep_supported(dev)) + return false; - dev_ctx = kzalloc(sizeof(*dev_ctx), GFP_KERNEL); - if (!dev_ctx) - return; + if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH) + return false; - dev_ctx->intf = intf; + if (!MLX5_CAP_GEN(dev, eth_net_offloads)) { + mlx5_core_warn(dev, "Missing eth_net_offloads capability\n"); + return false; + } - dev_ctx->context = intf->add(dev); - if (dev_ctx->context) { - set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state); - if (intf->attach) - set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state); + if (!MLX5_CAP_GEN(dev, nic_flow_table)) { + mlx5_core_warn(dev, "Missing nic_flow_table capability\n"); + return false; + } - spin_lock_irq(&priv->ctx_lock); - list_add_tail(&dev_ctx->list, &priv->ctx_list); - spin_unlock_irq(&priv->ctx_lock); + if (!MLX5_CAP_ETH(dev, csum_cap)) { + mlx5_core_warn(dev, "Missing csum_cap capability\n"); + return false; } - if (!dev_ctx->context) - kfree(dev_ctx); + if (!MLX5_CAP_ETH(dev, max_lso_cap)) { + mlx5_core_warn(dev, "Missing max_lso_cap capability\n"); + return false; + } + + if (!MLX5_CAP_ETH(dev, vlan_cap)) { + mlx5_core_warn(dev, "Missing vlan_cap capability\n"); + return false; + } + + if (!MLX5_CAP_ETH(dev, rss_ind_tbl_cap)) { + mlx5_core_warn(dev, "Missing rss_ind_tbl_cap capability\n"); + return false; + } + + if (MLX5_CAP_FLOWTABLE(dev, + flow_table_properties_nic_receive.max_ft_level) < 3) { + mlx5_core_warn(dev, "max_ft_level < 3\n"); + return false; + } + + if (!MLX5_CAP_ETH(dev, self_lb_en_modifiable)) + mlx5_core_warn(dev, "Self loop back prevention is not supported\n"); + if (!MLX5_CAP_GEN(dev, cq_moderation)) + mlx5_core_warn(dev, "CQ moderation is not supported\n"); + + return true; } -static struct mlx5_device_context *mlx5_get_device(struct mlx5_interface *intf, - struct mlx5_priv *priv) +static bool is_vnet_supported(struct mlx5_core_dev *dev) { - struct mlx5_device_context *dev_ctx; + if (!IS_ENABLED(CONFIG_MLX5_VDPA_NET)) + return false; - list_for_each_entry(dev_ctx, &priv->ctx_list, list) - if (dev_ctx->intf == intf) - return dev_ctx; - return NULL; + if (mlx5_core_is_pf(dev)) + return false; + + if (!(MLX5_CAP_GEN_64(dev, general_obj_types) & + MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q)) + return false; + + if (!(MLX5_CAP_DEV_VDPA_EMULATION(dev, event_mode) & + MLX5_VIRTIO_Q_EVENT_MODE_QP_MODE)) + return false; + + if (!MLX5_CAP_DEV_VDPA_EMULATION(dev, eth_frame_offload_type)) + return false; + + return true; } -void mlx5_remove_device(struct mlx5_interface *intf, struct mlx5_priv *priv) +static bool is_ib_rep_supported(struct mlx5_core_dev *dev) { - struct mlx5_device_context *dev_ctx; - struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv); + if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND)) + return false; - dev_ctx = mlx5_get_device(intf, priv); - if (!dev_ctx) - return; + if (dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_IB_ADEV) + return false; - spin_lock_irq(&priv->ctx_lock); - list_del(&dev_ctx->list); - spin_unlock_irq(&priv->ctx_lock); + if (!is_eth_rep_supported(dev)) + return false; - if (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state)) - intf->remove(dev, dev_ctx->context); + if (!MLX5_ESWITCH_MANAGER(dev)) + return false; - kfree(dev_ctx); + if (!is_mdev_switchdev_mode(dev)) + return false; + + if (mlx5_core_mp_enabled(dev)) + return false; + + return true; } -static void mlx5_attach_interface(struct mlx5_interface *intf, struct mlx5_priv *priv) +static bool is_mp_supported(struct mlx5_core_dev *dev) { - struct mlx5_device_context *dev_ctx; - struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv); - - dev_ctx = mlx5_get_device(intf, priv); - if (!dev_ctx) - return; - - if (intf->attach) { - if (test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state)) - return; - if (intf->attach(dev, dev_ctx->context)) - return; - set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state); - } else { - if (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state)) - return; - dev_ctx->context = intf->add(dev); - if (!dev_ctx->context) - return; - set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state); - } + if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND)) + return false; + + if (dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_IB_ADEV) + return false; + + if (is_ib_rep_supported(dev)) + return false; + + if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH) + return false; + + if (!mlx5_core_is_mp_slave(dev)) + return false; + + return true; } -void mlx5_attach_device(struct mlx5_core_dev *dev) +static bool is_ib_supported(struct mlx5_core_dev *dev) { - struct mlx5_priv *priv = &dev->priv; - struct mlx5_interface *intf; + if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND)) + return false; - mutex_lock(&mlx5_intf_mutex); - list_for_each_entry(intf, &intf_list, list) - mlx5_attach_interface(intf, priv); - mutex_unlock(&mlx5_intf_mutex); + if (dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_IB_ADEV) + return false; + + if (is_ib_rep_supported(dev)) + return false; + + if (is_mp_supported(dev)) + return false; + + return true; +} + +enum { + MLX5_INTERFACE_PROTOCOL_ETH_REP, + MLX5_INTERFACE_PROTOCOL_ETH, + + MLX5_INTERFACE_PROTOCOL_IB_REP, + MLX5_INTERFACE_PROTOCOL_MPIB, + MLX5_INTERFACE_PROTOCOL_IB, + + MLX5_INTERFACE_PROTOCOL_VNET, +}; + +static const struct mlx5_adev_device { + const char *suffix; + bool (*is_supported)(struct mlx5_core_dev *dev); +} mlx5_adev_devices[] = { + [MLX5_INTERFACE_PROTOCOL_VNET] = { .suffix = "vnet", + .is_supported = &is_vnet_supported }, + [MLX5_INTERFACE_PROTOCOL_IB] = { .suffix = "rdma", + .is_supported = &is_ib_supported }, + [MLX5_INTERFACE_PROTOCOL_ETH] = { .suffix = "eth", + .is_supported = &is_eth_supported }, + [MLX5_INTERFACE_PROTOCOL_ETH_REP] = { .suffix = "eth-rep", + .is_supported = &is_eth_rep_supported }, + [MLX5_INTERFACE_PROTOCOL_IB_REP] = { .suffix = "rdma-rep", + .is_supported = &is_ib_rep_supported }, + [MLX5_INTERFACE_PROTOCOL_MPIB] = { .suffix = "multiport", + .is_supported = &is_mp_supported }, +}; + +int mlx5_adev_idx_alloc(void) +{ + return ida_alloc(&mlx5_adev_ida, GFP_KERNEL); } -static void mlx5_detach_interface(struct mlx5_interface *intf, struct mlx5_priv *priv) +void mlx5_adev_idx_free(int idx) { - struct mlx5_device_context *dev_ctx; - struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv); - - dev_ctx = mlx5_get_device(intf, priv); - if (!dev_ctx) - return; - - if (intf->detach) { - if (!test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state)) - return; - intf->detach(dev, dev_ctx->context); - clear_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state); - } else { - if (!test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state)) - return; - intf->remove(dev, dev_ctx->context); - clear_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state); - } + ida_free(&mlx5_adev_ida, idx); } -void mlx5_detach_device(struct mlx5_core_dev *dev) +int mlx5_adev_init(struct mlx5_core_dev *dev) { struct mlx5_priv *priv = &dev->priv; - struct mlx5_interface *intf; - mutex_lock(&mlx5_intf_mutex); - list_for_each_entry(intf, &intf_list, list) - mlx5_detach_interface(intf, priv); - mutex_unlock(&mlx5_intf_mutex); + priv->adev = kcalloc(ARRAY_SIZE(mlx5_adev_devices), + sizeof(struct mlx5_adev *), GFP_KERNEL); + if (!priv->adev) + return -ENOMEM; + + return 0; } -bool mlx5_device_registered(struct mlx5_core_dev *dev) +void mlx5_adev_cleanup(struct mlx5_core_dev *dev) { - struct mlx5_priv *priv; - bool found = false; + struct mlx5_priv *priv = &dev->priv; - mutex_lock(&mlx5_intf_mutex); - list_for_each_entry(priv, &mlx5_dev_list, dev_list) - if (priv == &dev->priv) - found = true; - mutex_unlock(&mlx5_intf_mutex); + kfree(priv->adev); +} + +static void adev_release(struct device *dev) +{ + struct mlx5_adev *mlx5_adev = + container_of(dev, struct mlx5_adev, adev.dev); + struct mlx5_priv *priv = &mlx5_adev->mdev->priv; + int idx = mlx5_adev->idx; - return found; + kfree(mlx5_adev); + priv->adev[idx] = NULL; } -void mlx5_register_device(struct mlx5_core_dev *dev) +static struct mlx5_adev *add_adev(struct mlx5_core_dev *dev, int idx) +{ + const char *suffix = mlx5_adev_devices[idx].suffix; + struct auxiliary_device *adev; + struct mlx5_adev *madev; + int ret; + + madev = kzalloc(sizeof(*madev), GFP_KERNEL); + if (!madev) + return ERR_PTR(-ENOMEM); + + adev = &madev->adev; + adev->id = dev->priv.adev_idx; + adev->name = suffix; + adev->dev.parent = dev->device; + adev->dev.release = adev_release; + madev->mdev = dev; + madev->idx = idx; + + ret = auxiliary_device_init(adev); + if (ret) { + kfree(madev); + return ERR_PTR(ret); + } + + ret = auxiliary_device_add(adev); + if (ret) { + auxiliary_device_uninit(adev); + return ERR_PTR(ret); + } + return madev; +} + +static void del_adev(struct auxiliary_device *adev) +{ + auxiliary_device_delete(adev); + auxiliary_device_uninit(adev); +} + +int mlx5_attach_device(struct mlx5_core_dev *dev) { struct mlx5_priv *priv = &dev->priv; - struct mlx5_interface *intf; + struct auxiliary_device *adev; + struct auxiliary_driver *adrv; + int ret = 0, i; mutex_lock(&mlx5_intf_mutex); - list_add_tail(&priv->dev_list, &mlx5_dev_list); - list_for_each_entry(intf, &intf_list, list) - mlx5_add_device(intf, priv); + for (i = 0; i < ARRAY_SIZE(mlx5_adev_devices); i++) { + if (!priv->adev[i]) { + bool is_supported = false; + + if (mlx5_adev_devices[i].is_supported) + is_supported = mlx5_adev_devices[i].is_supported(dev); + + if (!is_supported) + continue; + + priv->adev[i] = add_adev(dev, i); + if (IS_ERR(priv->adev[i])) { + ret = PTR_ERR(priv->adev[i]); + priv->adev[i] = NULL; + } + } else { + adev = &priv->adev[i]->adev; + adrv = to_auxiliary_drv(adev->dev.driver); + + if (adrv->resume) + ret = adrv->resume(adev); + } + if (ret) { + mlx5_core_warn(dev, "Device[%d] (%s) failed to load\n", + i, mlx5_adev_devices[i].suffix); + + break; + } + } mutex_unlock(&mlx5_intf_mutex); + return ret; } -void mlx5_unregister_device(struct mlx5_core_dev *dev) +void mlx5_detach_device(struct mlx5_core_dev *dev) { struct mlx5_priv *priv = &dev->priv; - struct mlx5_interface *intf; + struct auxiliary_device *adev; + struct auxiliary_driver *adrv; + pm_message_t pm = {}; + int i; mutex_lock(&mlx5_intf_mutex); - list_for_each_entry_reverse(intf, &intf_list, list) - mlx5_remove_device(intf, priv); - list_del(&priv->dev_list); + for (i = ARRAY_SIZE(mlx5_adev_devices) - 1; i >= 0; i--) { + if (!priv->adev[i]) + continue; + + adev = &priv->adev[i]->adev; + adrv = to_auxiliary_drv(adev->dev.driver); + + if (adrv->suspend) { + adrv->suspend(adev, pm); + continue; + } + + del_adev(&priv->adev[i]->adev); + priv->adev[i] = NULL; + } mutex_unlock(&mlx5_intf_mutex); } -int mlx5_register_interface(struct mlx5_interface *intf) +int mlx5_register_device(struct mlx5_core_dev *dev) { - struct mlx5_priv *priv; - - if (!intf->add || !intf->remove) - return -EINVAL; + int ret; mutex_lock(&mlx5_intf_mutex); - list_add_tail(&intf->list, &intf_list); - list_for_each_entry(priv, &mlx5_dev_list, dev_list) - mlx5_add_device(intf, priv); + dev->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV; + ret = mlx5_rescan_drivers_locked(dev); mutex_unlock(&mlx5_intf_mutex); + if (ret) + mlx5_unregister_device(dev); - return 0; + return ret; } -EXPORT_SYMBOL(mlx5_register_interface); -void mlx5_unregister_interface(struct mlx5_interface *intf) +void mlx5_unregister_device(struct mlx5_core_dev *dev) { - struct mlx5_priv *priv; - mutex_lock(&mlx5_intf_mutex); - list_for_each_entry(priv, &mlx5_dev_list, dev_list) - mlx5_remove_device(intf, priv); - list_del(&intf->list); + dev->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV; + mlx5_rescan_drivers_locked(dev); mutex_unlock(&mlx5_intf_mutex); } -EXPORT_SYMBOL(mlx5_unregister_interface); -/* Must be called with intf_mutex held */ -static bool mlx5_has_added_dev_by_protocol(struct mlx5_core_dev *mdev, int protocol) +static int add_drivers(struct mlx5_core_dev *dev) { - struct mlx5_device_context *dev_ctx; - struct mlx5_interface *intf; - bool found = false; - - list_for_each_entry(intf, &intf_list, list) { - if (intf->protocol == protocol) { - dev_ctx = mlx5_get_device(intf, &mdev->priv); - if (dev_ctx && test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state)) - found = true; - break; + struct mlx5_priv *priv = &dev->priv; + int i, ret = 0; + + for (i = 0; i < ARRAY_SIZE(mlx5_adev_devices); i++) { + bool is_supported = false; + + if (priv->adev[i]) + continue; + + if (mlx5_adev_devices[i].is_supported) + is_supported = mlx5_adev_devices[i].is_supported(dev); + + if (!is_supported) + continue; + + priv->adev[i] = add_adev(dev, i); + if (IS_ERR(priv->adev[i])) { + mlx5_core_warn(dev, "Device[%d] (%s) failed to load\n", + i, mlx5_adev_devices[i].suffix); + /* We continue to rescan drivers and leave to the caller + * to make decision if to release everything or continue. + */ + ret = PTR_ERR(priv->adev[i]); + priv->adev[i] = NULL; } } - - return found; + return ret; } -void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol) +static void delete_drivers(struct mlx5_core_dev *dev) { - mutex_lock(&mlx5_intf_mutex); - if (mlx5_has_added_dev_by_protocol(mdev, protocol)) { - mlx5_remove_dev_by_protocol(mdev, protocol); - mlx5_add_dev_by_protocol(mdev, protocol); + struct mlx5_priv *priv = &dev->priv; + bool delete_all; + int i; + + delete_all = priv->flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV; + + for (i = ARRAY_SIZE(mlx5_adev_devices) - 1; i >= 0; i--) { + bool is_supported = false; + + if (!priv->adev[i]) + continue; + + if (mlx5_adev_devices[i].is_supported && !delete_all) + is_supported = mlx5_adev_devices[i].is_supported(dev); + + if (is_supported) + continue; + + del_adev(&priv->adev[i]->adev); + priv->adev[i] = NULL; } - mutex_unlock(&mlx5_intf_mutex); } -/* Must be called with intf_mutex held */ -void mlx5_add_dev_by_protocol(struct mlx5_core_dev *dev, int protocol) +/* This function is used after mlx5_core_dev is reconfigured. + */ +int mlx5_rescan_drivers_locked(struct mlx5_core_dev *dev) { - struct mlx5_interface *intf; + struct mlx5_priv *priv = &dev->priv; - list_for_each_entry(intf, &intf_list, list) - if (intf->protocol == protocol) { - mlx5_add_device(intf, &dev->priv); - break; - } -} + lockdep_assert_held(&mlx5_intf_mutex); -/* Must be called with intf_mutex held */ -void mlx5_remove_dev_by_protocol(struct mlx5_core_dev *dev, int protocol) -{ - struct mlx5_interface *intf; + delete_drivers(dev); + if (priv->flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV) + return 0; - list_for_each_entry(intf, &intf_list, list) - if (intf->protocol == protocol) { - mlx5_remove_device(intf, &dev->priv); - break; - } + return add_drivers(dev); } -static u32 mlx5_gen_pci_id(struct mlx5_core_dev *dev) +static u32 mlx5_gen_pci_id(const struct mlx5_core_dev *dev) { return (u32)((pci_domain_nr(dev->pdev->bus) << 16) | (dev->pdev->bus->number << 8) | PCI_SLOT(dev->pdev->devfn)); } -/* Must be called with intf_mutex held */ +static int next_phys_dev(struct device *dev, const void *data) +{ + struct mlx5_adev *madev = container_of(dev, struct mlx5_adev, adev.dev); + struct mlx5_core_dev *mdev = madev->mdev; + const struct mlx5_core_dev *curr = data; + + if (!mlx5_core_is_pf(mdev)) + return 0; + + if (mdev == curr) + return 0; + + if (mlx5_gen_pci_id(mdev) != mlx5_gen_pci_id(curr)) + return 0; + + return 1; +} + +/* This function is called with two flows: + * 1. During initialization of mlx5_core_dev and we don't need to lock it. + * 2. During LAG configure stage and caller holds &mlx5_intf_mutex. + */ struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev) { - struct mlx5_core_dev *res = NULL; - struct mlx5_core_dev *tmp_dev; - struct mlx5_priv *priv; - u32 pci_id; + struct auxiliary_device *adev; + struct mlx5_adev *madev; if (!mlx5_core_is_pf(dev)) return NULL; - pci_id = mlx5_gen_pci_id(dev); - list_for_each_entry(priv, &mlx5_dev_list, dev_list) { - tmp_dev = container_of(priv, struct mlx5_core_dev, priv); - if (!mlx5_core_is_pf(tmp_dev)) - continue; - - if ((dev != tmp_dev) && (mlx5_gen_pci_id(tmp_dev) == pci_id)) { - res = tmp_dev; - break; - } - } + adev = auxiliary_find_device(NULL, dev, &next_phys_dev); + if (!adev) + return NULL; - return res; + madev = container_of(adev, struct mlx5_adev, adev); + put_device(&adev->dev); + return madev->mdev; } - void mlx5_dev_list_lock(void) { mutex_lock(&mlx5_intf_mutex); } - void mlx5_dev_list_unlock(void) { mutex_unlock(&mlx5_intf_mutex); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index a28f95df2901..3261d0dc1104 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -13,17 +13,8 @@ static int mlx5_devlink_flash_update(struct devlink *devlink, struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_priv(devlink); - const struct firmware *fw; - int err; - - err = request_firmware_direct(&fw, params->file_name, &dev->pdev->dev); - if (err) - return err; - - err = mlx5_firmware_flash(dev, fw, extack); - release_firmware(fw); - return err; + return mlx5_firmware_flash(dev, params->fw, extack); } static u8 mlx5_fw_ver_major(u32 version) @@ -52,7 +43,7 @@ mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, u32 running_fw, stored_fw; int err; - err = devlink_info_driver_name_put(req, DRIVER_NAME); + err = devlink_info_driver_name_put(req, KBUILD_MODNAME); if (err) return err; @@ -221,7 +212,7 @@ static int mlx5_devlink_fs_mode_validate(struct devlink *devlink, u32 id, u8 eswitch_mode; bool smfs_cap; - eswitch_mode = mlx5_eswitch_mode(dev->priv.eswitch); + eswitch_mode = mlx5_eswitch_mode(dev); smfs_cap = mlx5_fs_dr_is_supported(dev); if (!smfs_cap) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c index a700f3c86899..87d65f6b5310 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c @@ -247,6 +247,9 @@ const char *parse_fs_dst(struct trace_seq *p, case MLX5_FLOW_DESTINATION_TYPE_TIR: trace_seq_printf(p, "tir=%u\n", dst->tir_num); break; + case MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER: + trace_seq_printf(p, "sampler_id=%u\n", dst->sampler_id); + break; case MLX5_FLOW_DESTINATION_TYPE_COUNTER: trace_seq_printf(p, "counter_id=%u\n", counter_id); break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c index 3dc9dd3f24dc..464eb3a18450 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c @@ -8,37 +8,66 @@ bool mlx5_read_embedded_cpu(struct mlx5_core_dev *dev) return (ioread32be(&dev->iseg->initializing) >> MLX5_ECPU_BIT_NUM) & 1; } -static int mlx5_peer_pf_init(struct mlx5_core_dev *dev) +static bool mlx5_ecpf_esw_admins_host_pf(const struct mlx5_core_dev *dev) { - u32 in[MLX5_ST_SZ_DW(enable_hca_in)] = {}; - int err; + /* In separate host mode, PF enables itself. + * When ECPF is eswitch manager, eswitch enables host PF after + * eswitch is setup. + */ + return mlx5_core_is_ecpf_esw_manager(dev); +} + +int mlx5_cmd_host_pf_enable_hca(struct mlx5_core_dev *dev) +{ + u32 out[MLX5_ST_SZ_DW(enable_hca_out)] = {}; + u32 in[MLX5_ST_SZ_DW(enable_hca_in)] = {}; MLX5_SET(enable_hca_in, in, opcode, MLX5_CMD_OP_ENABLE_HCA); - err = mlx5_cmd_exec_in(dev, enable_hca, in); + MLX5_SET(enable_hca_in, in, function_id, 0); + MLX5_SET(enable_hca_in, in, embedded_cpu_function, 0); + return mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out)); +} + +int mlx5_cmd_host_pf_disable_hca(struct mlx5_core_dev *dev) +{ + u32 out[MLX5_ST_SZ_DW(disable_hca_out)] = {}; + u32 in[MLX5_ST_SZ_DW(disable_hca_in)] = {}; + + MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA); + MLX5_SET(disable_hca_in, in, function_id, 0); + MLX5_SET(disable_hca_in, in, embedded_cpu_function, 0); + return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); +} + +static int mlx5_host_pf_init(struct mlx5_core_dev *dev) +{ + int err; + + if (mlx5_ecpf_esw_admins_host_pf(dev)) + return 0; + + /* ECPF shall enable HCA for host PF in the same way a PF + * does this for its VFs when ECPF is not a eswitch manager. + */ + err = mlx5_cmd_host_pf_enable_hca(dev); if (err) - mlx5_core_err(dev, "Failed to enable peer PF HCA err(%d)\n", - err); + mlx5_core_err(dev, "Failed to enable external host PF HCA err(%d)\n", err); return err; } -static void mlx5_peer_pf_cleanup(struct mlx5_core_dev *dev) +static void mlx5_host_pf_cleanup(struct mlx5_core_dev *dev) { - u32 in[MLX5_ST_SZ_DW(disable_hca_in)] = {}; int err; - MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA); - err = mlx5_cmd_exec_in(dev, disable_hca, in); + if (mlx5_ecpf_esw_admins_host_pf(dev)) + return; + + err = mlx5_cmd_host_pf_disable_hca(dev); if (err) { - mlx5_core_err(dev, "Failed to disable peer PF HCA err(%d)\n", - err); + mlx5_core_err(dev, "Failed to disable external host PF HCA err(%d)\n", err); return; } - - err = mlx5_wait_for_pages(dev, &dev->priv.peer_pf_pages); - if (err) - mlx5_core_warn(dev, "Timeout reclaiming peer PF pages err(%d)\n", - err); } int mlx5_ec_init(struct mlx5_core_dev *dev) @@ -46,16 +75,19 @@ int mlx5_ec_init(struct mlx5_core_dev *dev) if (!mlx5_core_is_ecpf(dev)) return 0; - /* ECPF shall enable HCA for peer PF in the same way a PF - * does this for its VFs. - */ - return mlx5_peer_pf_init(dev); + return mlx5_host_pf_init(dev); } void mlx5_ec_cleanup(struct mlx5_core_dev *dev) { + int err; + if (!mlx5_core_is_ecpf(dev)) return; - mlx5_peer_pf_cleanup(dev); + mlx5_host_pf_cleanup(dev); + + err = mlx5_wait_for_pages(dev, &dev->priv.host_pf_pages); + if (err) + mlx5_core_warn(dev, "Timeout reclaiming external host PF pages err(%d)\n", err); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h index d3d7a00a02ac..40b6ad76dca6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h @@ -17,6 +17,9 @@ bool mlx5_read_embedded_cpu(struct mlx5_core_dev *dev); int mlx5_ec_init(struct mlx5_core_dev *dev); void mlx5_ec_cleanup(struct mlx5_core_dev *dev); +int mlx5_cmd_host_pf_enable_hca(struct mlx5_core_dev *dev); +int mlx5_cmd_host_pf_disable_hca(struct mlx5_core_dev *dev); + #else /* CONFIG_MLX5_ESWITCH */ static inline bool diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 2f05b0f9de01..a1a81cfeb607 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -227,6 +227,7 @@ enum mlx5e_priv_flag { MLX5E_PFLAG_RX_NO_CSUM_COMPLETE, MLX5E_PFLAG_XDP_TX_MPWQE, MLX5E_PFLAG_SKB_TX_MPWQE, + MLX5E_PFLAG_TX_PORT_TS, MLX5E_NUM_PFLAGS, /* Keep last */ }; @@ -282,10 +283,12 @@ struct mlx5e_cq { u16 event_ctr; struct napi_struct *napi; struct mlx5_core_cq mcq; - struct mlx5e_channel *channel; + struct mlx5e_ch_stats *ch_stats; /* control */ + struct net_device *netdev; struct mlx5_core_dev *mdev; + struct mlx5e_priv *priv; struct mlx5_wq_ctrl wq_ctrl; } ____cacheline_aligned_in_smp; @@ -329,6 +332,15 @@ struct mlx5e_tx_mpwqe { u8 inline_on; }; +struct mlx5e_skb_fifo { + struct sk_buff **fifo; + u16 *pc; + u16 *cc; + u16 mask; +}; + +struct mlx5e_ptpsq; + struct mlx5e_txqsq { /* data path */ @@ -349,11 +361,10 @@ struct mlx5e_txqsq { /* read only */ struct mlx5_wq_cyc wq; u32 dma_fifo_mask; - u16 skb_fifo_mask; struct mlx5e_sq_stats *stats; struct { struct mlx5e_sq_dma *dma_fifo; - struct sk_buff **skb_fifo; + struct mlx5e_skb_fifo skb_fifo; struct mlx5e_tx_wqe_info *wqe_info; } db; void __iomem *uar_map; @@ -367,14 +378,17 @@ struct mlx5e_txqsq { unsigned int hw_mtu; struct hwtstamp_config *tstamp; struct mlx5_clock *clock; + struct net_device *netdev; + struct mlx5_core_dev *mdev; + struct mlx5e_priv *priv; /* control path */ struct mlx5_wq_ctrl wq_ctrl; - struct mlx5e_channel *channel; int ch_ix; int txq_ix; u32 rate_limit; struct work_struct recover_work; + struct mlx5e_ptpsq *ptpsq; } ____cacheline_aligned_in_smp; struct mlx5e_dma_info { @@ -593,7 +607,6 @@ struct mlx5e_rq { u8 map_dir; /* dma map direction */ } buff; - struct mlx5e_channel *channel; struct device *pdev; struct net_device *netdev; struct mlx5e_rq_stats *stats; @@ -602,6 +615,8 @@ struct mlx5e_rq { struct mlx5e_page_cache page_cache; struct hwtstamp_config *tstamp; struct mlx5_clock *clock; + struct mlx5e_icosq *icosq; + struct mlx5e_priv *priv; mlx5e_fp_handle_rx_cqe handle_rx_cqe; mlx5e_fp_post_rx_wqes post_wqes; @@ -681,8 +696,11 @@ struct mlx5e_channel { int cpu; }; +struct mlx5e_port_ptp; + struct mlx5e_channels { struct mlx5e_channel **c; + struct mlx5e_port_ptp *port_ptp; unsigned int num; struct mlx5e_params params; }; @@ -697,6 +715,12 @@ struct mlx5e_channel_stats { struct mlx5e_xdpsq_stats xsksq; } ____cacheline_aligned_in_smp; +struct mlx5e_port_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]; +} ____cacheline_aligned_in_smp; + enum { MLX5E_STATE_OPENED, MLX5E_STATE_DESTROYING, @@ -766,8 +790,10 @@ struct mlx5e_scratchpad { struct mlx5e_priv { /* priv data path fields - start */ - struct mlx5e_txqsq *txq2sq[MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC]; + /* +1 for port ptp ts */ + struct mlx5e_txqsq *txq2sq[(MLX5E_MAX_NUM_CHANNELS + 1) * MLX5E_MAX_NUM_TC]; int channel_tc2realtxq[MLX5E_MAX_NUM_CHANNELS][MLX5E_MAX_NUM_TC]; + int port_ptp_tc2realtxq[MLX5E_MAX_NUM_TC]; #ifdef CONFIG_MLX5_CORE_EN_DCB struct mlx5e_dcbx_dp dcbx_dp; #endif @@ -802,12 +828,15 @@ struct mlx5e_priv { struct net_device *netdev; struct mlx5e_stats stats; struct mlx5e_channel_stats channel_stats[MLX5E_MAX_NUM_CHANNELS]; + struct mlx5e_port_ptp_stats port_ptp_stats; u16 max_nch; u8 max_opened_tc; + bool port_ptp_opened; struct hwtstamp_config tstamp; u16 q_counter; u16 drop_rq_q_counter; struct notifier_block events_nb; + int num_tc_x_num_ch; struct udp_tunnel_nic_info nic_info; #ifdef CONFIG_MLX5_CORE_EN_DCB @@ -923,9 +952,17 @@ int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_xdpsq *sq, bool is_redirect); void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq); +struct mlx5e_create_cq_param { + struct napi_struct *napi; + struct mlx5e_ch_stats *ch_stats; + int node; + int ix; +}; + struct mlx5e_cq_param; -int mlx5e_open_cq(struct mlx5e_channel *c, struct dim_cq_moder moder, - struct mlx5e_cq_param *param, struct mlx5e_cq *cq); +int mlx5e_open_cq(struct mlx5e_priv *priv, 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); int mlx5e_open_locked(struct net_device *netdev); @@ -974,7 +1011,17 @@ void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq); int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn, struct mlx5e_modify_sq_param *p); void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq); +void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq); +void mlx5e_free_txqsq(struct mlx5e_txqsq *sq); void mlx5e_tx_disable_queue(struct netdev_queue *txq); +int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa); +void mlx5e_free_txqsq_db(struct mlx5e_txqsq *sq); +struct mlx5e_create_sq_param; +int mlx5e_create_sq_rdy(struct mlx5_core_dev *mdev, + struct mlx5e_sq_param *param, + struct mlx5e_create_sq_param *csp, + u32 *sqn); +void mlx5e_tx_err_cqe_work(struct work_struct *recover_work); static inline bool mlx5_tx_swp_supported(struct mlx5_core_dev *mdev) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index dc744702aee4..5749557749b0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -287,8 +287,7 @@ void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv); int mlx5e_create_flow_steering(struct mlx5e_priv *priv); void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv); -bool mlx5e_tunnel_proto_supported(struct mlx5_core_dev *mdev, u8 proto_type); -bool mlx5e_any_tunnel_proto_supported(struct mlx5_core_dev *mdev); +u8 mlx5e_get_proto_by_tunnel_type(enum mlx5e_tunnel_types tt); #endif /* __MLX5E_FLOW_STEER_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c index 69a05da0e3e3..718f8c0a4f6b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c @@ -37,13 +37,12 @@ int mlx5e_health_fmsg_named_obj_nest_end(struct devlink_fmsg *fmsg) int mlx5e_health_cq_diag_fmsg(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg) { - struct mlx5e_priv *priv = cq->channel->priv; u32 out[MLX5_ST_SZ_DW(query_cq_out)] = {}; u8 hw_status; void *cqc; int err; - err = mlx5_core_query_cq(priv->mdev, &cq->mcq, out); + err = mlx5_core_query_cq(cq->mdev, &cq->mcq, out); if (err) return err; @@ -158,10 +157,8 @@ void mlx5e_health_channels_update(struct mlx5e_priv *priv) DEVLINK_HEALTH_REPORTER_STATE_HEALTHY); } -int mlx5e_health_sq_to_ready(struct mlx5e_channel *channel, u32 sqn) +int mlx5e_health_sq_to_ready(struct mlx5_core_dev *mdev, struct net_device *dev, u32 sqn) { - struct mlx5_core_dev *mdev = channel->mdev; - struct net_device *dev = channel->netdev; struct mlx5e_modify_sq_param msp = {}; int err; @@ -206,21 +203,22 @@ out: return err; } -int mlx5e_health_channel_eq_recover(struct mlx5_eq_comp *eq, struct mlx5e_channel *channel) +int mlx5e_health_channel_eq_recover(struct net_device *dev, struct mlx5_eq_comp *eq, + struct mlx5e_ch_stats *stats) { u32 eqe_count; - netdev_err(channel->netdev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n", + netdev_err(dev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n", eq->core.eqn, eq->core.cons_index, eq->core.irqn); eqe_count = mlx5_eq_poll_irq_disabled(eq); if (!eqe_count) return -EIO; - netdev_err(channel->netdev, "Recovered %d eqes on EQ 0x%x\n", + netdev_err(dev, "Recovered %d eqes on EQ 0x%x\n", eqe_count, eq->core.eqn); - channel->stats->eq_rearm++; + stats->eq_rearm++; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h index b9aadddfd000..018262d0164b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h @@ -7,8 +7,6 @@ #include "en.h" #include "diag/rsc_dump.h" -#define MLX5E_RX_ERR_CQE(cqe) (get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND) - static inline bool cqe_syndrome_needs_recover(u8 syndrome) { return syndrome == MLX5_CQE_SYNDROME_LOCAL_QP_OP_ERR || @@ -42,8 +40,9 @@ struct mlx5e_err_ctx { void *ctx; }; -int mlx5e_health_sq_to_ready(struct mlx5e_channel *channel, u32 sqn); -int mlx5e_health_channel_eq_recover(struct mlx5_eq_comp *eq, struct mlx5e_channel *channel); +int mlx5e_health_sq_to_ready(struct mlx5_core_dev *mdev, struct net_device *dev, u32 sqn); +int mlx5e_health_channel_eq_recover(struct net_device *dev, struct mlx5_eq_comp *eq, + struct mlx5e_ch_stats *stats); int mlx5e_health_recover_channels(struct mlx5e_priv *priv); int mlx5e_health_report(struct mlx5e_priv *priv, struct devlink_health_reporter *reporter, char *err_str, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 38e4f19d69f8..43271a3856ca 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -2,6 +2,8 @@ /* Copyright (c) 2019 Mellanox Technologies. */ #include "en/params.h" +#include "en/txrx.h" +#include "en_accel/tls_rxtx.h" static inline bool mlx5e_rx_is_xdp(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk) @@ -152,3 +154,35 @@ u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev, return is_linear_skb ? mlx5e_get_linear_rq_headroom(params, xsk) : 0; } + +u16 mlx5e_calc_sq_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params) +{ + bool is_mpwqe = MLX5E_GET_PFLAG(params, MLX5E_PFLAG_SKB_TX_MPWQE); + u16 stop_room; + + stop_room = mlx5e_tls_get_stop_room(mdev, params); + stop_room += mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS); + if (is_mpwqe) + /* A MPWQE can take up to the maximum-sized WQE + all the normal + * stop room can be taken if a new packet breaks the active + * MPWQE session and allocates its WQEs right away. + */ + stop_room += mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS); + + return stop_room; +} + +int mlx5e_validate_params(struct mlx5e_priv *priv, struct mlx5e_params *params) +{ + size_t sq_size = 1 << params->log_sq_size; + u16 stop_room; + + stop_room = mlx5e_calc_sq_stop_room(priv->mdev, params); + if (stop_room >= sq_size) { + netdev_err(priv->netdev, "Stop room %hu is bigger than the SQ size %zu\n", + stop_room, sq_size); + return -EINVAL; + } + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h index a87273e801b2..807147d97a0f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h @@ -30,6 +30,7 @@ struct mlx5e_sq_param { u32 sqc[MLX5_ST_SZ_DW(sqc)]; struct mlx5_wq_param wq; bool is_mpw; + u16 stop_room; }; struct mlx5e_channel_param { @@ -40,6 +41,15 @@ struct mlx5e_channel_param { struct mlx5e_sq_param async_icosq; }; +struct mlx5e_create_sq_param { + struct mlx5_wq_ctrl *wq_ctrl; + u32 cqn; + u32 ts_cqe_to_dest_cqn; + u32 tisn; + u8 tis_lst_sz; + u8 min_inline_mode; +}; + static inline bool mlx5e_qid_get_ch_if_in_group(struct mlx5e_params *params, u16 qid, enum mlx5e_rq_group group, @@ -101,6 +111,7 @@ u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev, /* Build queue parameters */ +void mlx5e_build_create_cq_param(struct mlx5e_create_cq_param *ccp, struct mlx5e_channel *c); void mlx5e_build_rq_param(struct mlx5e_priv *priv, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, @@ -124,4 +135,7 @@ void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv, struct mlx5e_params *params, struct mlx5e_sq_param *param); +u16 mlx5e_calc_sq_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params); +int mlx5e_validate_params(struct mlx5e_priv *priv, struct mlx5e_params *params); + #endif /* __MLX5_EN_PARAMS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c new file mode 100644 index 000000000000..351118985a57 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -0,0 +1,529 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2020 Mellanox Technologies + +#include "en/ptp.h" +#include "en/txrx.h" +#include "lib/clock.h" + +struct mlx5e_skb_cb_hwtstamp { + ktime_t cqe_hwtstamp; + ktime_t port_hwtstamp; +}; + +void mlx5e_skb_cb_hwtstamp_init(struct sk_buff *skb) +{ + memset(skb->cb, 0, sizeof(struct mlx5e_skb_cb_hwtstamp)); +} + +static struct mlx5e_skb_cb_hwtstamp *mlx5e_skb_cb_get_hwts(struct sk_buff *skb) +{ + BUILD_BUG_ON(sizeof(struct mlx5e_skb_cb_hwtstamp) > sizeof(skb->cb)); + return (struct mlx5e_skb_cb_hwtstamp *)skb->cb; +} + +static void mlx5e_skb_cb_hwtstamp_tx(struct sk_buff *skb, + struct mlx5e_ptp_cq_stats *cq_stats) +{ + struct skb_shared_hwtstamps hwts = {}; + ktime_t diff; + + diff = abs(mlx5e_skb_cb_get_hwts(skb)->port_hwtstamp - + mlx5e_skb_cb_get_hwts(skb)->cqe_hwtstamp); + + /* Maximal allowed diff is 1 / 128 second */ + if (diff > (NSEC_PER_SEC >> 7)) { + cq_stats->abort++; + cq_stats->abort_abs_diff_ns += diff; + return; + } + + hwts.hwtstamp = mlx5e_skb_cb_get_hwts(skb)->port_hwtstamp; + skb_tstamp_tx(skb, &hwts); +} + +void mlx5e_skb_cb_hwtstamp_handler(struct sk_buff *skb, int hwtstamp_type, + ktime_t hwtstamp, + struct mlx5e_ptp_cq_stats *cq_stats) +{ + switch (hwtstamp_type) { + case (MLX5E_SKB_CB_CQE_HWTSTAMP): + mlx5e_skb_cb_get_hwts(skb)->cqe_hwtstamp = hwtstamp; + break; + case (MLX5E_SKB_CB_PORT_HWTSTAMP): + mlx5e_skb_cb_get_hwts(skb)->port_hwtstamp = hwtstamp; + break; + } + + /* If both CQEs arrive, check and report the port tstamp, and clear skb cb as + * skb soon to be released. + */ + if (!mlx5e_skb_cb_get_hwts(skb)->cqe_hwtstamp || + !mlx5e_skb_cb_get_hwts(skb)->port_hwtstamp) + return; + + mlx5e_skb_cb_hwtstamp_tx(skb, cq_stats); + memset(skb->cb, 0, sizeof(struct mlx5e_skb_cb_hwtstamp)); +} + +static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq, + struct mlx5_cqe64 *cqe, + int budget) +{ + struct sk_buff *skb = mlx5e_skb_fifo_pop(&ptpsq->skb_fifo); + ktime_t hwtstamp; + + if (unlikely(MLX5E_RX_ERR_CQE(cqe))) { + ptpsq->cq_stats->err_cqe++; + goto out; + } + + hwtstamp = mlx5_timecounter_cyc2time(ptpsq->txqsq.clock, get_cqe_ts(cqe)); + mlx5e_skb_cb_hwtstamp_handler(skb, MLX5E_SKB_CB_PORT_HWTSTAMP, + hwtstamp, ptpsq->cq_stats); + ptpsq->cq_stats->cqe++; + +out: + napi_consume_skb(skb, budget); +} + +static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget) +{ + struct mlx5e_ptpsq *ptpsq = container_of(cq, struct mlx5e_ptpsq, ts_cq); + struct mlx5_cqwq *cqwq = &cq->wq; + struct mlx5_cqe64 *cqe; + int work_done = 0; + + if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &ptpsq->txqsq.state))) + return false; + + cqe = mlx5_cqwq_get_cqe(cqwq); + if (!cqe) + return false; + + do { + mlx5_cqwq_pop(cqwq); + + mlx5e_ptp_handle_ts_cqe(ptpsq, cqe, budget); + } while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(cqwq))); + + mlx5_cqwq_update_db_record(cqwq); + + /* ensure cq space is freed before enabling more cqes */ + wmb(); + + return work_done == budget; +} + +static int mlx5e_ptp_napi_poll(struct napi_struct *napi, int budget) +{ + struct mlx5e_port_ptp *c = container_of(napi, struct mlx5e_port_ptp, + napi); + struct mlx5e_ch_stats *ch_stats = c->stats; + bool busy = false; + int work_done = 0; + int i; + + rcu_read_lock(); + + ch_stats->poll++; + + for (i = 0; i < c->num_tc; i++) { + busy |= mlx5e_poll_tx_cq(&c->ptpsq[i].txqsq.cq, budget); + busy |= mlx5e_ptp_poll_ts_cq(&c->ptpsq[i].ts_cq, budget); + } + + if (busy) { + work_done = budget; + goto out; + } + + if (unlikely(!napi_complete_done(napi, work_done))) + goto out; + + ch_stats->arm++; + + for (i = 0; i < c->num_tc; i++) { + mlx5e_cq_arm(&c->ptpsq[i].txqsq.cq); + mlx5e_cq_arm(&c->ptpsq[i].ts_cq); + } + +out: + rcu_read_unlock(); + + return work_done; +} + +static int mlx5e_ptp_alloc_txqsq(struct mlx5e_port_ptp *c, int txq_ix, + struct mlx5e_params *params, + struct mlx5e_sq_param *param, + struct mlx5e_txqsq *sq, int tc, + struct mlx5e_ptpsq *ptpsq) +{ + void *sqc_wq = MLX5_ADDR_OF(sqc, param->sqc, wq); + struct mlx5_core_dev *mdev = c->mdev; + struct mlx5_wq_cyc *wq = &sq->wq; + int err; + int node; + + sq->pdev = c->pdev; + sq->tstamp = c->tstamp; + sq->clock = &mdev->clock; + sq->mkey_be = c->mkey_be; + sq->netdev = c->netdev; + sq->priv = c->priv; + sq->mdev = mdev; + sq->ch_ix = c->ix; + sq->txq_ix = txq_ix; + sq->uar_map = mdev->mlx5e_res.bfreg.map; + sq->min_inline_mode = params->tx_min_inline_mode; + sq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); + sq->stats = &c->priv->port_ptp_stats.sq[tc]; + sq->ptpsq = ptpsq; + INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work); + if (!MLX5_CAP_ETH(mdev, wqe_vlan_insert)) + set_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state); + sq->stop_room = param->stop_room; + + node = dev_to_node(mlx5_core_dma_dev(mdev)); + + param->wq.db_numa_node = node; + err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, wq, &sq->wq_ctrl); + if (err) + return err; + wq->db = &wq->db[MLX5_SND_DBR]; + + err = mlx5e_alloc_txqsq_db(sq, node); + if (err) + goto err_sq_wq_destroy; + + return 0; + +err_sq_wq_destroy: + mlx5_wq_destroy(&sq->wq_ctrl); + + return err; +} + +static void mlx5e_ptp_destroy_sq(struct mlx5_core_dev *mdev, u32 sqn) +{ + mlx5_core_destroy_sq(mdev, sqn); +} + +static int mlx5e_ptp_alloc_traffic_db(struct mlx5e_ptpsq *ptpsq, int numa) +{ + int wq_sz = mlx5_wq_cyc_get_size(&ptpsq->txqsq.wq); + + ptpsq->skb_fifo.fifo = kvzalloc_node(array_size(wq_sz, sizeof(*ptpsq->skb_fifo.fifo)), + GFP_KERNEL, numa); + if (!ptpsq->skb_fifo.fifo) + return -ENOMEM; + + ptpsq->skb_fifo.pc = &ptpsq->skb_fifo_pc; + ptpsq->skb_fifo.cc = &ptpsq->skb_fifo_cc; + ptpsq->skb_fifo.mask = wq_sz - 1; + + return 0; +} + +static void mlx5e_ptp_drain_skb_fifo(struct mlx5e_skb_fifo *skb_fifo) +{ + while (*skb_fifo->pc != *skb_fifo->cc) { + struct sk_buff *skb = mlx5e_skb_fifo_pop(skb_fifo); + + dev_kfree_skb_any(skb); + } +} + +static void mlx5e_ptp_free_traffic_db(struct mlx5e_skb_fifo *skb_fifo) +{ + mlx5e_ptp_drain_skb_fifo(skb_fifo); + kvfree(skb_fifo->fifo); +} + +static int mlx5e_ptp_open_txqsq(struct mlx5e_port_ptp *c, u32 tisn, + int txq_ix, struct mlx5e_ptp_params *cparams, + int tc, struct mlx5e_ptpsq *ptpsq) +{ + struct mlx5e_sq_param *sqp = &cparams->txq_sq_param; + struct mlx5e_txqsq *txqsq = &ptpsq->txqsq; + struct mlx5e_create_sq_param csp = {}; + int err; + + err = mlx5e_ptp_alloc_txqsq(c, txq_ix, &cparams->params, sqp, + txqsq, tc, ptpsq); + if (err) + return err; + + csp.tisn = tisn; + csp.tis_lst_sz = 1; + csp.cqn = txqsq->cq.mcq.cqn; + csp.wq_ctrl = &txqsq->wq_ctrl; + csp.min_inline_mode = txqsq->min_inline_mode; + csp.ts_cqe_to_dest_cqn = ptpsq->ts_cq.mcq.cqn; + + err = mlx5e_create_sq_rdy(c->mdev, sqp, &csp, &txqsq->sqn); + if (err) + goto err_free_txqsq; + + err = mlx5e_ptp_alloc_traffic_db(ptpsq, + dev_to_node(mlx5_core_dma_dev(c->mdev))); + if (err) + goto err_free_txqsq; + + return 0; + +err_free_txqsq: + mlx5e_free_txqsq(txqsq); + + return err; +} + +static void mlx5e_ptp_close_txqsq(struct mlx5e_ptpsq *ptpsq) +{ + struct mlx5e_txqsq *sq = &ptpsq->txqsq; + struct mlx5_core_dev *mdev = sq->mdev; + + mlx5e_ptp_free_traffic_db(&ptpsq->skb_fifo); + cancel_work_sync(&sq->recover_work); + mlx5e_ptp_destroy_sq(mdev, sq->sqn); + mlx5e_free_txqsq_descs(sq); + mlx5e_free_txqsq(sq); +} + +static int mlx5e_ptp_open_txqsqs(struct mlx5e_port_ptp *c, + struct mlx5e_ptp_params *cparams) +{ + struct mlx5e_params *params = &cparams->params; + int ix_base; + int err; + int tc; + + ix_base = params->num_tc * params->num_channels; + + for (tc = 0; tc < params->num_tc; tc++) { + int txq_ix = ix_base + tc; + + err = mlx5e_ptp_open_txqsq(c, c->priv->tisn[c->lag_port][tc], txq_ix, + cparams, tc, &c->ptpsq[tc]); + if (err) + goto close_txqsq; + } + + return 0; + +close_txqsq: + for (--tc; tc >= 0; tc--) + mlx5e_ptp_close_txqsq(&c->ptpsq[tc]); + + return err; +} + +static void mlx5e_ptp_close_txqsqs(struct mlx5e_port_ptp *c) +{ + int tc; + + for (tc = 0; tc < c->num_tc; tc++) + mlx5e_ptp_close_txqsq(&c->ptpsq[tc]); +} + +static int mlx5e_ptp_open_cqs(struct mlx5e_port_ptp *c, + struct mlx5e_ptp_params *cparams) +{ + struct mlx5e_params *params = &cparams->params; + struct mlx5e_create_cq_param ccp = {}; + struct dim_cq_moder ptp_moder = {}; + struct mlx5e_cq_param *cq_param; + int err; + int tc; + + ccp.node = dev_to_node(mlx5_core_dma_dev(c->mdev)); + ccp.ch_stats = c->stats; + ccp.napi = &c->napi; + ccp.ix = c->ix; + + cq_param = &cparams->txq_sq_param.cqp; + + for (tc = 0; tc < params->num_tc; tc++) { + struct mlx5e_cq *cq = &c->ptpsq[tc].txqsq.cq; + + err = mlx5e_open_cq(c->priv, ptp_moder, cq_param, &ccp, cq); + if (err) + goto out_err_txqsq_cq; + } + + for (tc = 0; tc < params->num_tc; tc++) { + 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); + if (err) + goto out_err_ts_cq; + + ptpsq->cq_stats = &c->priv->port_ptp_stats.cq[tc]; + } + + return 0; + +out_err_ts_cq: + for (--tc; tc >= 0; tc--) + mlx5e_close_cq(&c->ptpsq[tc].ts_cq); + tc = params->num_tc; +out_err_txqsq_cq: + for (--tc; tc >= 0; tc--) + mlx5e_close_cq(&c->ptpsq[tc].txqsq.cq); + + return err; +} + +static void mlx5e_ptp_close_cqs(struct mlx5e_port_ptp *c) +{ + int tc; + + for (tc = 0; tc < c->num_tc; tc++) + mlx5e_close_cq(&c->ptpsq[tc].ts_cq); + + for (tc = 0; tc < c->num_tc; tc++) + mlx5e_close_cq(&c->ptpsq[tc].txqsq.cq); +} + +static void mlx5e_ptp_build_sq_param(struct mlx5e_priv *priv, + struct mlx5e_params *params, + struct mlx5e_sq_param *param) +{ + void *sqc = param->sqc; + void *wq; + + mlx5e_build_sq_param_common(priv, param); + + wq = MLX5_ADDR_OF(sqc, sqc, wq); + MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size); + param->stop_room = mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS); + mlx5e_build_tx_cq_param(priv, params, ¶m->cqp); +} + +static void mlx5e_ptp_build_params(struct mlx5e_port_ptp *c, + struct mlx5e_ptp_params *cparams, + struct mlx5e_params *orig) +{ + struct mlx5e_params *params = &cparams->params; + + params->tx_min_inline_mode = orig->tx_min_inline_mode; + params->num_channels = orig->num_channels; + params->hard_mtu = orig->hard_mtu; + params->sw_mtu = orig->sw_mtu; + params->num_tc = orig->num_tc; + + /* SQ */ + params->log_sq_size = orig->log_sq_size; + + mlx5e_ptp_build_sq_param(c->priv, params, &cparams->txq_sq_param); +} + +static int mlx5e_ptp_open_queues(struct mlx5e_port_ptp *c, + struct mlx5e_ptp_params *cparams) +{ + int err; + + err = mlx5e_ptp_open_cqs(c, cparams); + if (err) + return err; + + napi_enable(&c->napi); + + err = mlx5e_ptp_open_txqsqs(c, cparams); + if (err) + goto disable_napi; + + return 0; + +disable_napi: + napi_disable(&c->napi); + mlx5e_ptp_close_cqs(c); + + return err; +} + +static void mlx5e_ptp_close_queues(struct mlx5e_port_ptp *c) +{ + mlx5e_ptp_close_txqsqs(c); + napi_disable(&c->napi); + mlx5e_ptp_close_cqs(c); +} + +int mlx5e_port_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params, + u8 lag_port, struct mlx5e_port_ptp **cp) +{ + struct net_device *netdev = priv->netdev; + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5e_ptp_params *cparams; + struct mlx5e_port_ptp *c; + unsigned int irq; + int err; + int eqn; + + err = mlx5_vector2eqn(priv->mdev, 0, &eqn, &irq); + if (err) + return err; + + c = kvzalloc_node(sizeof(*c), GFP_KERNEL, dev_to_node(mlx5_core_dma_dev(mdev))); + cparams = kvzalloc(sizeof(*cparams), GFP_KERNEL); + if (!c || !cparams) + return -ENOMEM; + + c->priv = priv; + c->mdev = priv->mdev; + c->tstamp = &priv->tstamp; + c->ix = 0; + c->pdev = mlx5_core_dma_dev(priv->mdev); + c->netdev = priv->netdev; + c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key); + c->num_tc = params->num_tc; + c->stats = &priv->port_ptp_stats.ch; + c->irq_desc = irq_to_desc(irq); + c->lag_port = lag_port; + + netif_napi_add(netdev, &c->napi, mlx5e_ptp_napi_poll, 64); + + mlx5e_ptp_build_params(c, cparams, params); + + err = mlx5e_ptp_open_queues(c, cparams); + if (unlikely(err)) + goto err_napi_del; + + *cp = c; + + kvfree(cparams); + + return 0; + +err_napi_del: + netif_napi_del(&c->napi); + + kvfree(cparams); + kvfree(c); + return err; +} + +void mlx5e_port_ptp_close(struct mlx5e_port_ptp *c) +{ + mlx5e_ptp_close_queues(c); + netif_napi_del(&c->napi); + + kvfree(c); +} + +void mlx5e_ptp_activate_channel(struct mlx5e_port_ptp *c) +{ + int tc; + + for (tc = 0; tc < c->num_tc; tc++) + mlx5e_activate_txqsq(&c->ptpsq[tc].txqsq); +} + +void mlx5e_ptp_deactivate_channel(struct mlx5e_port_ptp *c) +{ + int tc; + + for (tc = 0; tc < c->num_tc; tc++) + mlx5e_deactivate_txqsq(&c->ptpsq[tc].txqsq); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h new file mode 100644 index 000000000000..28aa5ae118f4 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h @@ -0,0 +1,63 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2020 Mellanox Technologies. */ + +#ifndef __MLX5_EN_PTP_H__ +#define __MLX5_EN_PTP_H__ + +#include "en.h" +#include "en/params.h" +#include "en_stats.h" + +struct mlx5e_ptpsq { + struct mlx5e_txqsq txqsq; + struct mlx5e_cq ts_cq; + u16 skb_fifo_cc; + u16 skb_fifo_pc; + struct mlx5e_skb_fifo skb_fifo; + struct mlx5e_ptp_cq_stats *cq_stats; +}; + +struct mlx5e_port_ptp { + /* data path */ + struct mlx5e_ptpsq ptpsq[MLX5E_MAX_NUM_TC]; + struct napi_struct napi; + struct device *pdev; + struct net_device *netdev; + __be32 mkey_be; + u8 num_tc; + u8 lag_port; + + /* data path - accessed per napi poll */ + struct irq_desc *irq_desc; + struct mlx5e_ch_stats *stats; + + /* control */ + struct mlx5e_priv *priv; + struct mlx5_core_dev *mdev; + struct hwtstamp_config *tstamp; + DECLARE_BITMAP(state, MLX5E_CHANNEL_NUM_STATES); + int ix; +}; + +struct mlx5e_ptp_params { + struct mlx5e_params params; + struct mlx5e_sq_param txq_sq_param; +}; + +int mlx5e_port_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params, + u8 lag_port, struct mlx5e_port_ptp **cp); +void mlx5e_port_ptp_close(struct mlx5e_port_ptp *c); +void mlx5e_ptp_activate_channel(struct mlx5e_port_ptp *c); +void mlx5e_ptp_deactivate_channel(struct mlx5e_port_ptp *c); + +enum { + MLX5E_SKB_CB_CQE_HWTSTAMP = BIT(0), + MLX5E_SKB_CB_PORT_HWTSTAMP = BIT(1), +}; + +void mlx5e_skb_cb_hwtstamp_handler(struct sk_buff *skb, int hwtstamp_type, + ktime_t hwtstamp, + struct mlx5e_ptp_cq_stats *cq_stats); + +void mlx5e_skb_cb_hwtstamp_init(struct sk_buff *skb); +#endif /* __MLX5_EN_PTP_H__ */ 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 9913647a1faf..d80bbd17e5f8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c @@ -87,7 +87,7 @@ static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx) /* At this point, both the rq and the icosq are disabled */ - err = mlx5e_health_sq_to_ready(icosq->channel, icosq->sqn); + err = mlx5e_health_sq_to_ready(mdev, dev, icosq->sqn); if (err) goto out; @@ -146,17 +146,16 @@ out: static int mlx5e_rx_reporter_timeout_recover(void *ctx) { - struct mlx5e_icosq *icosq; struct mlx5_eq_comp *eq; struct mlx5e_rq *rq; int err; rq = ctx; - icosq = &rq->channel->icosq; eq = rq->cq.mcq.eq; - err = mlx5e_health_channel_eq_recover(eq, rq->channel); - if (err) - clear_bit(MLX5E_SQ_STATE_ENABLED, &icosq->state); + + err = mlx5e_health_channel_eq_recover(rq->netdev, eq, rq->cq.ch_stats); + if (err && rq->icosq) + clear_bit(MLX5E_SQ_STATE_ENABLED, &rq->icosq->state); return err; } @@ -233,21 +232,13 @@ static int mlx5e_reporter_icosq_diagnose(struct mlx5e_icosq *icosq, u8 hw_state, static int mlx5e_rx_reporter_build_diagnose_output(struct mlx5e_rq *rq, struct devlink_fmsg *fmsg) { - struct mlx5e_priv *priv = rq->channel->priv; - struct mlx5e_icosq *icosq; - u8 icosq_hw_state; u16 wqe_counter; int wqes_sz; u8 hw_state; u16 wq_head; int err; - icosq = &rq->channel->icosq; - err = mlx5e_query_rq_state(priv->mdev, rq->rqn, &hw_state); - if (err) - return err; - - err = mlx5_core_query_sq_state(priv->mdev, icosq->sqn, &icosq_hw_state); + err = mlx5e_query_rq_state(rq->mdev, rq->rqn, &hw_state); if (err) return err; @@ -259,7 +250,7 @@ static int mlx5e_rx_reporter_build_diagnose_output(struct mlx5e_rq *rq, if (err) return err; - err = devlink_fmsg_u32_pair_put(fmsg, "channel ix", rq->channel->ix); + err = devlink_fmsg_u32_pair_put(fmsg, "channel ix", rq->ix); if (err) return err; @@ -295,9 +286,18 @@ static int mlx5e_rx_reporter_build_diagnose_output(struct mlx5e_rq *rq, if (err) return err; - err = mlx5e_reporter_icosq_diagnose(icosq, icosq_hw_state, fmsg); - if (err) - return err; + if (rq->icosq) { + struct mlx5e_icosq *icosq = rq->icosq; + u8 icosq_hw_state; + + err = mlx5_core_query_sq_state(rq->mdev, icosq->sqn, &icosq_hw_state); + if (err) + return err; + + err = mlx5e_reporter_icosq_diagnose(icosq, icosq_hw_state, fmsg); + if (err) + return err; + } err = devlink_fmsg_obj_nest_end(fmsg); if (err) @@ -557,25 +557,29 @@ static int mlx5e_rx_reporter_dump(struct devlink_health_reporter *reporter, void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq) { - struct mlx5e_icosq *icosq = &rq->channel->icosq; - struct mlx5e_priv *priv = rq->channel->priv; + 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 = {}; err_ctx.ctx = rq; err_ctx.recover = mlx5e_rx_reporter_timeout_recover; err_ctx.dump = mlx5e_rx_reporter_dump_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, ICOSQ: 0x%x RQ: 0x%x, CQ: 0x%x", - icosq->channel->ix, icosq->sqn, rq->rqn, rq->cq.mcq.cqn); + "RX timeout on channel: %d, %sRQ: 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); } void mlx5e_reporter_rq_cqe_err(struct mlx5e_rq *rq) { - struct mlx5e_priv *priv = rq->channel->priv; char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN]; + struct mlx5e_priv *priv = rq->priv; struct mlx5e_err_ctx err_ctx = {}; err_ctx.ctx = rq; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index 8be6eaa3eeb1..d7275c84313e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -2,6 +2,7 @@ /* Copyright (c) 2019 Mellanox Technologies. */ #include "health.h" +#include "en/ptp.h" static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq) { @@ -15,7 +16,7 @@ static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq) msleep(20); } - netdev_err(sq->channel->netdev, + netdev_err(sq->netdev, "Wait for SQ 0x%x flush timeout (sq cc = 0x%x, sq pc = 0x%x)\n", sq->sqn, sq->cc, sq->pc); @@ -41,8 +42,8 @@ static int mlx5e_tx_reporter_err_cqe_recover(void *ctx) int err; sq = ctx; - mdev = sq->channel->mdev; - dev = sq->channel->netdev; + mdev = sq->mdev; + dev = sq->netdev; if (!test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) return 0; @@ -68,7 +69,7 @@ static int mlx5e_tx_reporter_err_cqe_recover(void *ctx) * pending WQEs. SQ can safely reset the SQ. */ - err = mlx5e_health_sq_to_ready(sq->channel, sq->sqn); + err = mlx5e_health_sq_to_ready(mdev, dev, sq->sqn); if (err) goto out; @@ -99,8 +100,8 @@ static int mlx5e_tx_reporter_timeout_recover(void *ctx) to_ctx = ctx; sq = to_ctx->sq; eq = sq->cq.mcq.eq; - priv = sq->channel->priv; - err = mlx5e_health_channel_eq_recover(eq, sq->channel); + priv = sq->priv; + err = mlx5e_health_channel_eq_recover(sq->netdev, eq, sq->cq.ch_stats); if (!err) { to_ctx->status = 0; /* this sq recovered */ return err; @@ -141,11 +142,11 @@ static int mlx5e_tx_reporter_recover(struct devlink_health_reporter *reporter, } static int -mlx5e_tx_reporter_build_diagnose_output(struct devlink_fmsg *fmsg, - struct mlx5e_txqsq *sq, int tc) +mlx5e_tx_reporter_build_diagnose_output_sq_common(struct devlink_fmsg *fmsg, + struct mlx5e_txqsq *sq, int tc) { - struct mlx5e_priv *priv = sq->channel->priv; bool stopped = netif_xmit_stopped(sq->txq); + struct mlx5e_priv *priv = sq->priv; u8 state; int err; @@ -153,14 +154,6 @@ mlx5e_tx_reporter_build_diagnose_output(struct devlink_fmsg *fmsg, if (err) return err; - err = devlink_fmsg_obj_nest_start(fmsg); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "channel ix", sq->ch_ix); - if (err) - return err; - err = devlink_fmsg_u32_pair_put(fmsg, "tc", tc); if (err) return err; @@ -193,7 +186,24 @@ mlx5e_tx_reporter_build_diagnose_output(struct devlink_fmsg *fmsg, if (err) return err; - err = mlx5e_health_eq_diag_fmsg(sq->cq.mcq.eq, fmsg); + return mlx5e_health_eq_diag_fmsg(sq->cq.mcq.eq, fmsg); +} + +static int +mlx5e_tx_reporter_build_diagnose_output(struct devlink_fmsg *fmsg, + struct mlx5e_txqsq *sq, int tc) +{ + int err; + + err = devlink_fmsg_obj_nest_start(fmsg); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "channel ix", sq->ch_ix); + if (err) + return err; + + err = mlx5e_tx_reporter_build_diagnose_output_sq_common(fmsg, sq, tc); if (err) return err; @@ -204,49 +214,147 @@ mlx5e_tx_reporter_build_diagnose_output(struct devlink_fmsg *fmsg, return 0; } -static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg, - struct netlink_ext_ack *extack) +static int +mlx5e_tx_reporter_build_diagnose_output_ptpsq(struct devlink_fmsg *fmsg, + struct mlx5e_ptpsq *ptpsq, int tc) { - struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); - struct mlx5e_txqsq *generic_sq = priv->txq2sq[0]; - u32 sq_stride, sq_sz; + int err; - int i, tc, err = 0; + err = devlink_fmsg_obj_nest_start(fmsg); + if (err) + return err; - mutex_lock(&priv->state_lock); + err = devlink_fmsg_string_pair_put(fmsg, "channel", "ptp"); + if (err) + return err; - if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) - goto unlock; + err = mlx5e_tx_reporter_build_diagnose_output_sq_common(fmsg, &ptpsq->txqsq, tc); + if (err) + return err; - sq_sz = mlx5_wq_cyc_get_size(&generic_sq->wq); - sq_stride = MLX5_SEND_WQE_BB; + err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "Port TS"); + if (err) + return err; - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "Common Config"); + err = mlx5e_health_cq_diag_fmsg(&ptpsq->ts_cq, fmsg); if (err) - goto unlock; + return err; + + err = mlx5e_health_fmsg_named_obj_nest_end(fmsg); + if (err) + return err; + + err = devlink_fmsg_obj_nest_end(fmsg); + if (err) + return err; + + return 0; +} + +static int +mlx5e_tx_reporter_diagnose_generic_txqsq(struct devlink_fmsg *fmsg, + struct mlx5e_txqsq *txqsq) +{ + u32 sq_stride, sq_sz; + int err; err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "SQ"); if (err) - goto unlock; + return err; + + sq_sz = mlx5_wq_cyc_get_size(&txqsq->wq); + sq_stride = MLX5_SEND_WQE_BB; err = devlink_fmsg_u64_pair_put(fmsg, "stride size", sq_stride); if (err) - goto unlock; + return err; err = devlink_fmsg_u32_pair_put(fmsg, "size", sq_sz); if (err) - goto unlock; + return err; - err = mlx5e_health_cq_common_diag_fmsg(&generic_sq->cq, fmsg); + err = mlx5e_health_cq_common_diag_fmsg(&txqsq->cq, fmsg); if (err) - goto unlock; + return err; + + return mlx5e_health_fmsg_named_obj_nest_end(fmsg); +} + +static int +mlx5e_tx_reporter_diagnose_generic_tx_port_ts(struct devlink_fmsg *fmsg, + struct mlx5e_ptpsq *ptpsq) +{ + int err; + + err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "Port TS"); + if (err) + return err; + + err = mlx5e_health_cq_common_diag_fmsg(&ptpsq->ts_cq, fmsg); + if (err) + return err; + + return mlx5e_health_fmsg_named_obj_nest_end(fmsg); +} + +static int +mlx5e_tx_reporter_diagnose_common_config(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg) +{ + struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); + struct mlx5e_txqsq *generic_sq = priv->txq2sq[0]; + struct mlx5e_ptpsq *generic_ptpsq; + int err; + + err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "Common Config"); + if (err) + return err; + + err = mlx5e_tx_reporter_diagnose_generic_txqsq(fmsg, generic_sq); + if (err) + return err; + + generic_ptpsq = priv->channels.port_ptp ? + &priv->channels.port_ptp->ptpsq[0] : + NULL; + if (!generic_ptpsq) + goto out; + + err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "PTP"); + if (err) + return err; + + err = mlx5e_tx_reporter_diagnose_generic_txqsq(fmsg, &generic_ptpsq->txqsq); + if (err) + return err; + + err = mlx5e_tx_reporter_diagnose_generic_tx_port_ts(fmsg, generic_ptpsq); + if (err) + return err; err = mlx5e_health_fmsg_named_obj_nest_end(fmsg); if (err) + return err; + +out: + return mlx5e_health_fmsg_named_obj_nest_end(fmsg); +} + +static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) +{ + struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); + struct mlx5e_port_ptp *ptp_ch = priv->channels.port_ptp; + + int i, tc, err = 0; + + mutex_lock(&priv->state_lock); + + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) goto unlock; - err = mlx5e_health_fmsg_named_obj_nest_end(fmsg); + err = mlx5e_tx_reporter_diagnose_common_config(reporter, fmsg); if (err) goto unlock; @@ -265,6 +373,19 @@ static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter, goto unlock; } } + + if (!ptp_ch) + goto close_sqs_nest; + + for (tc = 0; tc < priv->channels.params.num_tc; tc++) { + err = mlx5e_tx_reporter_build_diagnose_output_ptpsq(fmsg, + &ptp_ch->ptpsq[tc], + tc); + if (err) + goto unlock; + } + +close_sqs_nest: err = devlink_fmsg_arr_pair_nest_end(fmsg); if (err) goto unlock; @@ -338,6 +459,7 @@ static int mlx5e_tx_reporter_dump_sq(struct mlx5e_priv *priv, struct devlink_fms static int mlx5e_tx_reporter_dump_all_sqs(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg) { + struct mlx5e_port_ptp *ptp_ch = priv->channels.port_ptp; struct mlx5_rsc_key key = {}; int i, tc, err; @@ -373,6 +495,17 @@ static int mlx5e_tx_reporter_dump_all_sqs(struct mlx5e_priv *priv, return err; } } + + if (ptp_ch) { + for (tc = 0; tc < priv->channels.params.num_tc; tc++) { + struct mlx5e_txqsq *sq = &ptp_ch->ptpsq[tc].txqsq; + + err = mlx5e_health_queue_dump(priv, fmsg, sq->sqn, "PTP SQ"); + if (err) + return err; + } + } + return devlink_fmsg_arr_pair_nest_end(fmsg); } @@ -396,8 +529,8 @@ static int mlx5e_tx_reporter_dump(struct devlink_health_reporter *reporter, void mlx5e_reporter_tx_err_cqe(struct mlx5e_txqsq *sq) { - struct mlx5e_priv *priv = sq->channel->priv; char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN]; + struct mlx5e_priv *priv = sq->priv; struct mlx5e_err_ctx err_ctx = {}; err_ctx.ctx = sq; @@ -410,9 +543,9 @@ void mlx5e_reporter_tx_err_cqe(struct mlx5e_txqsq *sq) int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq) { - struct mlx5e_priv *priv = sq->channel->priv; char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN]; struct mlx5e_tx_timeout_ctx to_ctx = {}; + struct mlx5e_priv *priv = sq->priv; struct mlx5e_err_ctx err_ctx = {}; to_ctx.sq = sq; @@ -421,7 +554,7 @@ int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq) err_ctx.dump = mlx5e_tx_reporter_dump_sq; snprintf(err_str, sizeof(err_str), "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u", - sq->channel->ix, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc, + sq->ch_ix, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc, jiffies_to_usecs(jiffies - sq->txq->trans_start)); mlx5e_health_report(priv, priv->tx_reporter, err_str, &err_ctx); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index 07ee1d236ab3..7943eb30b837 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -24,6 +24,8 @@ #define INL_HDR_START_SZ (sizeof(((struct mlx5_wqe_eth_seg *)NULL)->inline_hdr.start)) +#define MLX5E_RX_ERR_CQE(cqe) (get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND) + enum mlx5e_icosq_wqe_type { MLX5E_ICOSQ_WQE_NOP, MLX5E_ICOSQ_WQE_UMR_RX, @@ -250,21 +252,24 @@ mlx5e_dma_push(struct mlx5e_txqsq *sq, dma_addr_t addr, u32 size, dma->type = map_type; } -static inline struct sk_buff **mlx5e_skb_fifo_get(struct mlx5e_txqsq *sq, u16 i) +static inline +struct sk_buff **mlx5e_skb_fifo_get(struct mlx5e_skb_fifo *fifo, u16 i) { - return &sq->db.skb_fifo[i & sq->skb_fifo_mask]; + return &fifo->fifo[i & fifo->mask]; } -static inline void mlx5e_skb_fifo_push(struct mlx5e_txqsq *sq, struct sk_buff *skb) +static inline +void mlx5e_skb_fifo_push(struct mlx5e_skb_fifo *fifo, struct sk_buff *skb) { - struct sk_buff **skb_item = mlx5e_skb_fifo_get(sq, sq->skb_fifo_pc++); + struct sk_buff **skb_item = mlx5e_skb_fifo_get(fifo, (*fifo->pc)++); *skb_item = skb; } -static inline struct sk_buff *mlx5e_skb_fifo_pop(struct mlx5e_txqsq *sq) +static inline +struct sk_buff *mlx5e_skb_fifo_pop(struct mlx5e_skb_fifo *fifo) { - return *mlx5e_skb_fifo_get(sq, sq->skb_fifo_cc++); + return *mlx5e_skb_fifo_get(fifo, (*fifo->cc)++); } static inline void @@ -308,7 +313,7 @@ static inline void mlx5e_dump_error_cqe(struct mlx5e_cq *cq, u32 qn, ci = mlx5_cqwq_ctr2ix(wq, wq->cc - 1); - netdev_err(cq->channel->netdev, + netdev_err(cq->netdev, "Error cqe on cqn 0x%x, ci 0x%x, qn 0x%x, opcode 0x%x, syndrome 0x%x, vendor syndrome 0x%x\n", cq->mcq.cqn, ci, qn, get_cqe_opcode((struct mlx5_cqe64 *)err_cqe), diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index ae90d533a350..2e3e78b0f333 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -366,7 +366,8 @@ 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, - bool recycle) + bool recycle, + struct xdp_frame_bulk *bq) { struct mlx5e_xdp_info_fifo *xdpi_fifo = &sq->db.xdpi_fifo; u16 i; @@ -379,7 +380,7 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq, /* XDP_TX from the XSK RQ and XDP_REDIRECT */ dma_unmap_single(sq->pdev, xdpi.frame.dma_addr, xdpi.frame.xdpf->len, DMA_TO_DEVICE); - xdp_return_frame(xdpi.frame.xdpf); + xdp_return_frame_bulk(xdpi.frame.xdpf, bq); break; case MLX5E_XDP_XMIT_MODE_PAGE: /* XDP_TX from the regular RQ */ @@ -397,12 +398,15 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq, bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) { + struct xdp_frame_bulk bq; struct mlx5e_xdpsq *sq; struct mlx5_cqe64 *cqe; u32 xsk_frames = 0; u16 sqcc; int i; + xdp_frame_bulk_init(&bq); + sq = container_of(cq, struct mlx5e_xdpsq, cq); if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) @@ -434,7 +438,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) sqcc += wi->num_wqebbs; - mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, true); + mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, true, &bq); } while (!last_wqe); if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) { @@ -447,6 +451,8 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) } } while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq))); + xdp_flush_frame_bulk(&bq); + if (xsk_frames) xsk_tx_completed(sq->xsk_pool, xsk_frames); @@ -463,8 +469,13 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq) { + struct xdp_frame_bulk bq; u32 xsk_frames = 0; + xdp_frame_bulk_init(&bq); + + rcu_read_lock(); /* need for xdp_return_frame_bulk */ + while (sq->cc != sq->pc) { struct mlx5e_xdp_wqe_info *wi; u16 ci; @@ -474,9 +485,12 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq) sq->cc += wi->num_wqebbs; - mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, false); + mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, false, &bq); } + xdp_flush_frame_bulk(&bq); + rcu_read_unlock(); + if (xsk_frames) xsk_tx_completed(sq->xsk_pool, xsk_frames); } 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 be3465ba38ca..d87c345878d3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -49,8 +49,11 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, struct mlx5e_channel *c) { struct mlx5e_channel_param *cparam; + struct mlx5e_create_cq_param ccp; int err; + mlx5e_build_create_cq_param(&ccp, c); + if (!mlx5e_validate_xsk_param(params, xsk, priv->mdev)) return -EINVAL; @@ -60,7 +63,8 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, mlx5e_build_xsk_cparam(priv, params, xsk, cparam); - err = mlx5e_open_cq(c, params->rx_cq_moderation, &cparam->rq.cqp, &c->xskrq.cq); + err = mlx5e_open_cq(c->priv, params->rx_cq_moderation, &cparam->rq.cqp, &ccp, + &c->xskrq.cq); if (unlikely(err)) goto err_free_cparam; @@ -68,7 +72,8 @@ 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, params->tx_cq_moderation, &cparam->xdp_sq.cqp, &c->xsksq.cq); + err = mlx5e_open_cq(c->priv, 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_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c index b140e13fdcc8..d16def68ecff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c @@ -13,20 +13,20 @@ struct mlx5e_dump_wqe { (DIV_ROUND_UP(sizeof(struct mlx5e_dump_wqe), MLX5_SEND_WQE_BB)) static u8 -mlx5e_ktls_dumps_num_wqes(struct mlx5e_txqsq *sq, unsigned int nfrags, +mlx5e_ktls_dumps_num_wqes(struct mlx5e_params *params, unsigned int nfrags, unsigned int sync_len) { /* Given the MTU and sync_len, calculates an upper bound for the * number of DUMP WQEs needed for the TX resync of a record. */ - return nfrags + DIV_ROUND_UP(sync_len, sq->hw_mtu); + return nfrags + DIV_ROUND_UP(sync_len, MLX5E_SW2HW_MTU(params, params->sw_mtu)); } -u16 mlx5e_ktls_get_stop_room(struct mlx5e_txqsq *sq) +u16 mlx5e_ktls_get_stop_room(struct mlx5e_params *params) { u16 num_dumps, stop_room = 0; - num_dumps = mlx5e_ktls_dumps_num_wqes(sq, MAX_SKB_FRAGS, TLS_MAX_PAYLOAD_SIZE); + num_dumps = mlx5e_ktls_dumps_num_wqes(params, MAX_SKB_FRAGS, TLS_MAX_PAYLOAD_SIZE); stop_room += mlx5e_stop_room_for_wqe(MLX5E_TLS_SET_STATIC_PARAMS_WQEBBS); stop_room += mlx5e_stop_room_for_wqe(MLX5E_TLS_SET_PROGRESS_PARAMS_WQEBBS); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h index 7521c9be735b..ee04e916fa21 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h @@ -14,7 +14,7 @@ struct mlx5e_accel_tx_tls_state { u32 tls_tisn; }; -u16 mlx5e_ktls_get_stop_room(struct mlx5e_txqsq *sq); +u16 mlx5e_ktls_get_stop_room(struct mlx5e_params *params); bool mlx5e_ktls_handle_tx_skb(struct tls_context *tls_ctx, struct mlx5e_txqsq *sq, struct sk_buff *skb, int datalen, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c index 6982b193ee8a..2b51d3222ca1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c @@ -276,7 +276,7 @@ bool mlx5e_tls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq, if (WARN_ON_ONCE(tls_ctx->netdev != netdev)) goto err_out; - if (mlx5_accel_is_ktls_tx(sq->channel->mdev)) + if (mlx5_accel_is_ktls_tx(sq->mdev)) return mlx5e_ktls_handle_tx_skb(tls_ctx, sq, skb, datalen, state); /* FPGA */ @@ -385,15 +385,13 @@ void mlx5e_tls_handle_rx_skb_metadata(struct mlx5e_rq *rq, struct sk_buff *skb, *cqe_bcnt -= MLX5E_METADATA_ETHER_LEN; } -u16 mlx5e_tls_get_stop_room(struct mlx5e_txqsq *sq) +u16 mlx5e_tls_get_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params) { - struct mlx5_core_dev *mdev = sq->channel->mdev; - if (!mlx5_accel_is_tls_device(mdev)) return 0; if (mlx5_accel_is_ktls_device(mdev)) - return mlx5e_ktls_get_stop_room(sq); + return mlx5e_ktls_get_stop_room(params); /* FPGA */ /* Resync SKB. */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h index 5f162ad2ee8f..9923132c9440 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h @@ -43,7 +43,7 @@ #include "en.h" #include "en/txrx.h" -u16 mlx5e_tls_get_stop_room(struct mlx5e_txqsq *sq); +u16 mlx5e_tls_get_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params); bool mlx5e_tls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5e_accel_tx_tls_state *state); @@ -71,7 +71,7 @@ mlx5e_accel_is_tls(struct mlx5_cqe64 *cqe, struct sk_buff *skb) { return false; static inline void mlx5e_tls_handle_rx_skb(struct mlx5e_rq *rq, struct sk_buff *skb, struct mlx5_cqe64 *cqe, u32 *cqe_bcnt) {} -static inline u16 mlx5e_tls_get_stop_room(struct mlx5e_txqsq *sq) +static inline u16 mlx5e_tls_get_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params) { return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index d25a56ec6876..d9076d543104 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -32,6 +32,7 @@ #include "en.h" #include "en/port.h" +#include "en/params.h" #include "en/xsk/pool.h" #include "lib/clock.h" @@ -40,9 +41,7 @@ void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv, { struct mlx5_core_dev *mdev = priv->mdev; - strlcpy(drvinfo->driver, DRIVER_NAME, sizeof(drvinfo->driver)); - strlcpy(drvinfo->version, DRIVER_VERSION, - sizeof(drvinfo->version)); + strlcpy(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), @@ -369,6 +368,10 @@ int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv, new_channels.params.log_rq_mtu_frames = log_rq_size; new_channels.params.log_sq_size = log_sq_size; + err = mlx5e_validate_params(priv, &new_channels.params); + if (err) + goto unlock; + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { priv->channels.params = new_channels.params; goto unlock; @@ -1941,6 +1944,38 @@ static int set_pflag_skb_tx_mpwqe(struct net_device *netdev, bool enable) return set_pflag_tx_mpwqe_common(netdev, MLX5E_PFLAG_SKB_TX_MPWQE, enable); } +static int set_pflag_tx_port_ts(struct net_device *netdev, bool enable) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5e_channels new_channels = {}; + int err; + + if (!MLX5_CAP_GEN(mdev, ts_cqe_to_dest_cqn)) + return -EOPNOTSUPP; + + new_channels.params = priv->channels.params; + MLX5E_SET_PFLAG(&new_channels.params, MLX5E_PFLAG_TX_PORT_TS, enable); + /* No need to verify SQ stop room as + * ptpsq.txqsq.stop_room <= generic_sq->stop_room, and both + * has the same log_sq_size. + */ + + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { + priv->channels.params = new_channels.params; + err = mlx5e_num_channels_changed(priv); + goto out; + } + + err = mlx5e_safe_switch_channels(priv, &new_channels, + mlx5e_num_channels_changed_ctx, NULL); +out: + if (!err) + priv->port_ptp_opened = true; + + return err; +} + static const struct pflag_desc mlx5e_priv_flags[MLX5E_NUM_PFLAGS] = { { "rx_cqe_moder", set_pflag_rx_cqe_based_moder }, { "tx_cqe_moder", set_pflag_tx_cqe_based_moder }, @@ -1949,6 +1984,7 @@ static const struct pflag_desc mlx5e_priv_flags[MLX5E_NUM_PFLAGS] = { { "rx_no_csum_complete", set_pflag_rx_no_csum_complete }, { "xdp_tx_mpwqe", set_pflag_xdp_tx_mpwqe }, { "skb_tx_mpwqe", set_pflag_skb_tx_mpwqe }, + { "tx_port_ts", set_pflag_tx_port_ts }, }; static int mlx5e_handle_pflag(struct net_device *netdev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 1f48f99c0997..fa8149f6eb08 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -772,25 +772,31 @@ static struct mlx5e_etype_proto ttc_tunnel_rules[] = { }; -bool mlx5e_tunnel_proto_supported(struct mlx5_core_dev *mdev, u8 proto_type) +u8 mlx5e_get_proto_by_tunnel_type(enum mlx5e_tunnel_types tt) +{ + return ttc_tunnel_rules[tt].proto; +} + +static bool mlx5e_tunnel_proto_supported_rx(struct mlx5_core_dev *mdev, u8 proto_type) { switch (proto_type) { case IPPROTO_GRE: return MLX5_CAP_ETH(mdev, tunnel_stateless_gre); case IPPROTO_IPIP: case IPPROTO_IPV6: - return MLX5_CAP_ETH(mdev, tunnel_stateless_ip_over_ip); + return (MLX5_CAP_ETH(mdev, tunnel_stateless_ip_over_ip) || + MLX5_CAP_ETH(mdev, tunnel_stateless_ip_over_ip_rx)); default: return false; } } -bool mlx5e_any_tunnel_proto_supported(struct mlx5_core_dev *mdev) +static bool mlx5e_tunnel_any_rx_proto_supported(struct mlx5_core_dev *mdev) { int tt; for (tt = 0; tt < MLX5E_NUM_TUNNEL_TT; tt++) { - if (mlx5e_tunnel_proto_supported(mdev, ttc_tunnel_rules[tt].proto)) + if (mlx5e_tunnel_proto_supported_rx(mdev, ttc_tunnel_rules[tt].proto)) return true; } return false; @@ -798,7 +804,7 @@ bool mlx5e_any_tunnel_proto_supported(struct mlx5_core_dev *mdev) bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev) { - return (mlx5e_any_tunnel_proto_supported(mdev) && + return (mlx5e_tunnel_any_rx_proto_supported(mdev) && MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ft_field_support.inner_ip_version)); } @@ -899,8 +905,8 @@ static int mlx5e_generate_ttc_table_rules(struct mlx5e_priv *priv, dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; dest.ft = params->inner_ttc->ft.t; for (tt = 0; tt < MLX5E_NUM_TUNNEL_TT; tt++) { - if (!mlx5e_tunnel_proto_supported(priv->mdev, - ttc_tunnel_rules[tt].proto)) + if (!mlx5e_tunnel_proto_supported_rx(priv->mdev, + ttc_tunnel_rules[tt].proto)) continue; trules[tt] = mlx5e_generate_ttc_rule(priv, ft, &dest, ttc_tunnel_rules[tt].etype, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index ebce97921e03..03831650f655 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -64,6 +64,7 @@ #include "en/hv_vhca_stats.h" #include "en/devlink.h" #include "lib/mlx5.h" +#include "en/ptp.h" bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev) { @@ -412,9 +413,10 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, rq->wq_type = params->rq_wq_type; rq->pdev = c->pdev; rq->netdev = c->netdev; + rq->priv = c->priv; rq->tstamp = c->tstamp; rq->clock = &mdev->clock; - rq->channel = c; + rq->icosq = &c->icosq; rq->ix = c->ix; rq->mdev = mdev; rq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); @@ -434,7 +436,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, rq_xdp_ix = rq->ix; if (xsk) rq_xdp_ix += params->num_channels * MLX5E_RQ_GROUP_XSK; - err = xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq_xdp_ix); + err = xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq_xdp_ix, 0); if (err < 0) goto err_rq_xdp_prog; @@ -613,14 +615,11 @@ err_rq_xdp_prog: static void mlx5e_free_rq(struct mlx5e_rq *rq) { - struct mlx5e_channel *c = rq->channel; - struct bpf_prog *old_prog = NULL; + struct bpf_prog *old_prog; int i; - /* drop_rq has neither channel nor xdp_prog. */ - if (c) - old_prog = rcu_dereference_protected(rq->xdp_prog, - lockdep_is_held(&c->priv->state_lock)); + old_prog = rcu_dereference_protected(rq->xdp_prog, + lockdep_is_held(&rq->priv->state_lock)); if (old_prog) bpf_prog_put(old_prog); @@ -720,9 +719,7 @@ int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state) static int mlx5e_modify_rq_scatter_fcs(struct mlx5e_rq *rq, bool enable) { - struct mlx5e_channel *c = rq->channel; - struct mlx5e_priv *priv = c->priv; - struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5_core_dev *mdev = rq->mdev; void *in; void *rqc; @@ -751,8 +748,7 @@ static int mlx5e_modify_rq_scatter_fcs(struct mlx5e_rq *rq, bool enable) static int mlx5e_modify_rq_vsd(struct mlx5e_rq *rq, bool vsd) { - struct mlx5e_channel *c = rq->channel; - struct mlx5_core_dev *mdev = c->mdev; + struct mlx5_core_dev *mdev = rq->mdev; void *in; void *rqc; int inlen; @@ -786,7 +782,6 @@ static void mlx5e_destroy_rq(struct mlx5e_rq *rq) int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time) { unsigned long exp_time = jiffies + msecs_to_jiffies(wait_time); - struct mlx5e_channel *c = rq->channel; u16 min_wqes = mlx5_min_rx_wqes(rq->wq_type, mlx5e_rqwq_get_size(rq)); @@ -797,8 +792,8 @@ int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time) msleep(20); } while (time_before(jiffies, exp_time)); - netdev_warn(c->netdev, "Failed to get min RX wqes on Channel[%d] RQN[0x%x] wq cur_sz(%d) min_rx_wqes(%d)\n", - c->ix, rq->rqn, mlx5e_rqwq_get_cur_sz(rq), min_wqes); + netdev_warn(rq->netdev, "Failed to get min RX wqes on Channel[%d] RQN[0x%x] wq cur_sz(%d) min_rx_wqes(%d)\n", + rq->ix, rq->rqn, mlx5e_rqwq_get_cur_sz(rq), min_wqes); mlx5e_reporter_rx_timeout(rq); return -ETIMEDOUT; @@ -913,7 +908,7 @@ err_free_rq: void mlx5e_activate_rq(struct mlx5e_rq *rq) { set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state); - mlx5e_trigger_irq(&rq->channel->icosq); + mlx5e_trigger_irq(rq->icosq); } void mlx5e_deactivate_rq(struct mlx5e_rq *rq) @@ -925,7 +920,7 @@ void mlx5e_deactivate_rq(struct mlx5e_rq *rq) void mlx5e_close_rq(struct mlx5e_rq *rq) { cancel_work_sync(&rq->dim.work); - cancel_work_sync(&rq->channel->icosq.recover_work); + cancel_work_sync(&rq->icosq->recover_work); cancel_work_sync(&rq->recover_work); mlx5e_destroy_rq(rq); mlx5e_free_rx_descs(rq); @@ -1089,14 +1084,14 @@ static void mlx5e_free_icosq(struct mlx5e_icosq *sq) mlx5_wq_destroy(&sq->wq_ctrl); } -static void mlx5e_free_txqsq_db(struct mlx5e_txqsq *sq) +void mlx5e_free_txqsq_db(struct mlx5e_txqsq *sq) { kvfree(sq->db.wqe_info); - kvfree(sq->db.skb_fifo); + kvfree(sq->db.skb_fifo.fifo); kvfree(sq->db.dma_fifo); } -static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa) +int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa) { int wq_sz = mlx5_wq_cyc_get_size(&sq->wq); int df_sz = wq_sz * MLX5_SEND_WQEBB_NUM_DS; @@ -1104,46 +1099,26 @@ static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa) sq->db.dma_fifo = kvzalloc_node(array_size(df_sz, sizeof(*sq->db.dma_fifo)), GFP_KERNEL, numa); - sq->db.skb_fifo = kvzalloc_node(array_size(df_sz, - sizeof(*sq->db.skb_fifo)), + sq->db.skb_fifo.fifo = kvzalloc_node(array_size(df_sz, + sizeof(*sq->db.skb_fifo.fifo)), GFP_KERNEL, numa); sq->db.wqe_info = kvzalloc_node(array_size(wq_sz, sizeof(*sq->db.wqe_info)), GFP_KERNEL, numa); - if (!sq->db.dma_fifo || !sq->db.skb_fifo || !sq->db.wqe_info) { + if (!sq->db.dma_fifo || !sq->db.skb_fifo.fifo || !sq->db.wqe_info) { mlx5e_free_txqsq_db(sq); return -ENOMEM; } sq->dma_fifo_mask = df_sz - 1; - sq->skb_fifo_mask = df_sz - 1; - - return 0; -} - -static int mlx5e_calc_sq_stop_room(struct mlx5e_txqsq *sq, u8 log_sq_size) -{ - int sq_size = 1 << log_sq_size; - sq->stop_room = mlx5e_tls_get_stop_room(sq); - sq->stop_room += mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS); - if (test_bit(MLX5E_SQ_STATE_MPWQE, &sq->state)) - /* A MPWQE can take up to the maximum-sized WQE + all the normal - * stop room can be taken if a new packet breaks the active - * MPWQE session and allocates its WQEs right away. - */ - sq->stop_room += mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS); - - if (WARN_ON(sq->stop_room >= sq_size)) { - netdev_err(sq->channel->netdev, "Stop room %hu is bigger than the SQ size %d\n", - sq->stop_room, sq_size); - return -ENOSPC; - } + sq->db.skb_fifo.pc = &sq->skb_fifo_pc; + sq->db.skb_fifo.cc = &sq->skb_fifo_cc; + sq->db.skb_fifo.mask = df_sz - 1; return 0; } -static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work); static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, int txq_ix, struct mlx5e_params *params, @@ -1160,7 +1135,9 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, sq->tstamp = c->tstamp; sq->clock = &mdev->clock; sq->mkey_be = c->mkey_be; - sq->channel = c; + sq->netdev = c->netdev; + sq->mdev = c->mdev; + sq->priv = c->priv; sq->ch_ix = c->ix; sq->txq_ix = txq_ix; sq->uar_map = mdev->mlx5e_res.bfreg.map; @@ -1176,9 +1153,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, set_bit(MLX5E_SQ_STATE_TLS, &sq->state); if (param->is_mpw) set_bit(MLX5E_SQ_STATE_MPWQE, &sq->state); - err = mlx5e_calc_sq_stop_room(sq, params->log_sq_size); - if (err) - return err; + sq->stop_room = param->stop_room; param->wq.db_numa_node = cpu_to_node(c->cpu); err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, wq, &sq->wq_ctrl); @@ -1201,20 +1176,12 @@ err_sq_wq_destroy: return err; } -static void mlx5e_free_txqsq(struct mlx5e_txqsq *sq) +void mlx5e_free_txqsq(struct mlx5e_txqsq *sq) { mlx5e_free_txqsq_db(sq); mlx5_wq_destroy(&sq->wq_ctrl); } -struct mlx5e_create_sq_param { - struct mlx5_wq_ctrl *wq_ctrl; - u32 cqn; - u32 tisn; - u8 tis_lst_sz; - u8 min_inline_mode; -}; - static int mlx5e_create_sq(struct mlx5_core_dev *mdev, struct mlx5e_sq_param *param, struct mlx5e_create_sq_param *csp, @@ -1239,6 +1206,7 @@ static int mlx5e_create_sq(struct mlx5_core_dev *mdev, MLX5_SET(sqc, sqc, tis_lst_sz, csp->tis_lst_sz); MLX5_SET(sqc, sqc, tis_num_0, csp->tisn); MLX5_SET(sqc, sqc, cqn, csp->cqn); + MLX5_SET(sqc, sqc, ts_cqe_to_dest_cqn, csp->ts_cqe_to_dest_cqn); if (MLX5_CAP_ETH(mdev, wqe_inline_mode) == MLX5_CAP_INLINE_MODE_VPORT_CONTEXT) MLX5_SET(sqc, sqc, min_wqe_inline_mode, csp->min_inline_mode); @@ -1296,10 +1264,10 @@ static void mlx5e_destroy_sq(struct mlx5_core_dev *mdev, u32 sqn) mlx5_core_destroy_sq(mdev, sqn); } -static int mlx5e_create_sq_rdy(struct mlx5_core_dev *mdev, - struct mlx5e_sq_param *param, - struct mlx5e_create_sq_param *csp, - u32 *sqn) +int mlx5e_create_sq_rdy(struct mlx5_core_dev *mdev, + struct mlx5e_sq_param *param, + struct mlx5e_create_sq_param *csp, + u32 *sqn) { struct mlx5e_modify_sq_param msp = {0}; int err; @@ -1362,7 +1330,7 @@ err_free_txqsq: void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq) { - sq->txq = netdev_get_tx_queue(sq->channel->netdev, sq->txq_ix); + sq->txq = netdev_get_tx_queue(sq->netdev, sq->txq_ix); set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); netdev_tx_reset_queue(sq->txq); netif_tx_start_queue(sq->txq); @@ -1375,7 +1343,7 @@ void mlx5e_tx_disable_queue(struct netdev_queue *txq) __netif_tx_unlock_bh(txq); } -static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq) +void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq) { struct mlx5_wq_cyc *wq = &sq->wq; @@ -1400,8 +1368,7 @@ static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq) static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq) { - struct mlx5e_channel *c = sq->channel; - struct mlx5_core_dev *mdev = c->mdev; + struct mlx5_core_dev *mdev = sq->mdev; struct mlx5_rate_limit rl = {0}; cancel_work_sync(&sq->dim.work); @@ -1415,7 +1382,7 @@ static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq) mlx5e_free_txqsq(sq); } -static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work) +void mlx5e_tx_err_cqe_work(struct work_struct *recover_work) { struct mlx5e_txqsq *sq = container_of(recover_work, struct mlx5e_txqsq, recover_work); @@ -1542,10 +1509,11 @@ void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq) mlx5e_free_xdpsq(sq); } -static int mlx5e_alloc_cq_common(struct mlx5_core_dev *mdev, +static int mlx5e_alloc_cq_common(struct mlx5e_priv *priv, struct mlx5e_cq_param *param, struct mlx5e_cq *cq) { + struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_core_cq *mcq = &cq->mcq; int eqn_not_used; unsigned int irqn; @@ -1578,25 +1546,27 @@ static int mlx5e_alloc_cq_common(struct mlx5_core_dev *mdev, } cq->mdev = mdev; + cq->netdev = priv->netdev; + cq->priv = priv; return 0; } -static int mlx5e_alloc_cq(struct mlx5e_channel *c, +static int mlx5e_alloc_cq(struct mlx5e_priv *priv, struct mlx5e_cq_param *param, + struct mlx5e_create_cq_param *ccp, struct mlx5e_cq *cq) { - struct mlx5_core_dev *mdev = c->priv->mdev; int err; - param->wq.buf_numa_node = cpu_to_node(c->cpu); - param->wq.db_numa_node = cpu_to_node(c->cpu); - param->eq_ix = c->ix; + param->wq.buf_numa_node = ccp->node; + param->wq.db_numa_node = ccp->node; + param->eq_ix = ccp->ix; - err = mlx5e_alloc_cq_common(mdev, param, cq); + err = mlx5e_alloc_cq_common(priv, param, cq); - cq->napi = &c->napi; - cq->channel = c; + cq->napi = ccp->napi; + cq->ch_stats = ccp->ch_stats; return err; } @@ -1660,13 +1630,14 @@ static void mlx5e_destroy_cq(struct mlx5e_cq *cq) mlx5_core_destroy_cq(cq->mdev, &cq->mcq); } -int mlx5e_open_cq(struct mlx5e_channel *c, struct dim_cq_moder moder, - struct mlx5e_cq_param *param, struct mlx5e_cq *cq) +int mlx5e_open_cq(struct mlx5e_priv *priv, 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 = c->mdev; + struct mlx5_core_dev *mdev = priv->mdev; int err; - err = mlx5e_alloc_cq(c, param, cq); + err = mlx5e_alloc_cq(priv, param, ccp, cq); if (err) return err; @@ -1692,14 +1663,15 @@ void mlx5e_close_cq(struct mlx5e_cq *cq) static int mlx5e_open_tx_cqs(struct mlx5e_channel *c, struct mlx5e_params *params, + struct mlx5e_create_cq_param *ccp, struct mlx5e_channel_param *cparam) { int err; int tc; for (tc = 0; tc < c->num_tc; tc++) { - err = mlx5e_open_cq(c, params->tx_cq_moderation, - &cparam->txq_sq.cqp, &c->sq[tc].cq); + err = mlx5e_open_cq(c->priv, params->tx_cq_moderation, &cparam->txq_sq.cqp, + ccp, &c->sq[tc].cq); if (err) goto err_close_tx_cqs; } @@ -1834,35 +1806,52 @@ static int mlx5e_set_tx_maxrate(struct net_device *dev, int index, u32 rate) return err; } +void mlx5e_build_create_cq_param(struct mlx5e_create_cq_param *ccp, struct mlx5e_channel *c) +{ + *ccp = (struct mlx5e_create_cq_param) { + .napi = &c->napi, + .ch_stats = c->stats, + .node = cpu_to_node(c->cpu), + .ix = c->ix, + }; +} + static int mlx5e_open_queues(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_channel_param *cparam) { struct dim_cq_moder icocq_moder = {0, 0}; + struct mlx5e_create_cq_param ccp; int err; - err = mlx5e_open_cq(c, icocq_moder, &cparam->icosq.cqp, &c->async_icosq.cq); + mlx5e_build_create_cq_param(&ccp, c); + + err = mlx5e_open_cq(c->priv, icocq_moder, &cparam->icosq.cqp, &ccp, + &c->async_icosq.cq); if (err) return err; - err = mlx5e_open_cq(c, icocq_moder, &cparam->async_icosq.cqp, &c->icosq.cq); + err = mlx5e_open_cq(c->priv, icocq_moder, &cparam->async_icosq.cqp, &ccp, + &c->icosq.cq); if (err) goto err_close_async_icosq_cq; - err = mlx5e_open_tx_cqs(c, params, cparam); + err = mlx5e_open_tx_cqs(c, params, &ccp, cparam); if (err) goto err_close_icosq_cq; - err = mlx5e_open_cq(c, params->tx_cq_moderation, &cparam->xdp_sq.cqp, &c->xdpsq.cq); + err = mlx5e_open_cq(c->priv, params->tx_cq_moderation, &cparam->xdp_sq.cqp, &ccp, + &c->xdpsq.cq); if (err) goto err_close_tx_cqs; - err = mlx5e_open_cq(c, params->rx_cq_moderation, &cparam->rq.cqp, &c->rq.cq); + err = mlx5e_open_cq(c->priv, 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, params->tx_cq_moderation, - &cparam->xdp_sq.cqp, &c->rq_xdpsq.cq) : 0; + err = c->xdp ? mlx5e_open_cq(c->priv, params->tx_cq_moderation, &cparam->xdp_sq.cqp, + &ccp, &c->rq_xdpsq.cq) : 0; if (err) goto err_close_rx_cq; @@ -2225,6 +2214,7 @@ static void mlx5e_build_sq_param(struct mlx5e_priv *priv, MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size); MLX5_SET(sqc, sqc, allow_swp, allow_swp); param->is_mpw = MLX5E_GET_PFLAG(params, MLX5E_PFLAG_SKB_TX_MPWQE); + param->stop_room = mlx5e_calc_sq_stop_room(priv->mdev, params); mlx5e_build_tx_cq_param(priv, params, ¶m->cqp); } @@ -2384,6 +2374,13 @@ int mlx5e_open_channels(struct mlx5e_priv *priv, goto err_close_channels; } + if (MLX5E_GET_PFLAG(&chs->params, MLX5E_PFLAG_TX_PORT_TS)) { + err = mlx5e_port_ptp_open(priv, &chs->params, chs->c[0]->lag_port, + &chs->port_ptp); + if (err) + goto err_close_channels; + } + mlx5e_health_channels_update(priv); kvfree(cparam); return 0; @@ -2405,6 +2402,9 @@ static void mlx5e_activate_channels(struct mlx5e_channels *chs) for (i = 0; i < chs->num; i++) mlx5e_activate_channel(chs->c[i]); + + if (chs->port_ptp) + mlx5e_ptp_activate_channel(chs->port_ptp); } #define MLX5E_RQ_WQES_TIMEOUT 20000 /* msecs */ @@ -2431,6 +2431,9 @@ static void mlx5e_deactivate_channels(struct mlx5e_channels *chs) { int i; + if (chs->port_ptp) + mlx5e_ptp_deactivate_channel(chs->port_ptp); + for (i = 0; i < chs->num; i++) mlx5e_deactivate_channel(chs->c[i]); } @@ -2439,6 +2442,9 @@ void mlx5e_close_channels(struct mlx5e_channels *chs) { int i; + if (chs->port_ptp) + mlx5e_port_ptp_close(chs->port_ptp); + for (i = 0; i < chs->num; i++) mlx5e_close_channel(chs->c[i]); @@ -2924,6 +2930,8 @@ static int mlx5e_update_netdev_queues(struct mlx5e_priv *priv) nch = priv->channels.params.num_channels; ntc = priv->channels.params.num_tc; num_txqs = nch * ntc; + if (MLX5E_GET_PFLAG(&priv->channels.params, MLX5E_PFLAG_TX_PORT_TS)) + num_txqs += ntc; num_rxqs = nch * priv->profile->rq_groups; mlx5e_netdev_set_tcs(netdev, nch, ntc); @@ -2997,14 +3005,13 @@ MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_num_channels_changed); static void mlx5e_build_txq_maps(struct mlx5e_priv *priv) { - int i, ch; + int i, ch, tc, num_tc; ch = priv->channels.num; + num_tc = priv->channels.params.num_tc; for (i = 0; i < ch; i++) { - int tc; - - for (tc = 0; tc < priv->channels.params.num_tc; tc++) { + for (tc = 0; tc < num_tc; tc++) { struct mlx5e_channel *c = priv->channels.c[i]; struct mlx5e_txqsq *sq = &c->sq[tc]; @@ -3012,10 +3019,29 @@ static void mlx5e_build_txq_maps(struct mlx5e_priv *priv) priv->channel_tc2realtxq[i][tc] = i + tc * ch; } } + + if (!priv->channels.port_ptp) + return; + + for (tc = 0; tc < num_tc; tc++) { + struct mlx5e_port_ptp *c = priv->channels.port_ptp; + struct mlx5e_txqsq *sq = &c->ptpsq[tc].txqsq; + + priv->txq2sq[sq->txq_ix] = sq; + priv->port_ptp_tc2realtxq[tc] = priv->num_tc_x_num_ch + tc; + } +} + +static void mlx5e_update_num_tc_x_num_ch(struct mlx5e_priv *priv) +{ + /* Sync with mlx5e_select_queue. */ + WRITE_ONCE(priv->num_tc_x_num_ch, + priv->channels.params.num_tc * priv->channels.num); } void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) { + mlx5e_update_num_tc_x_num_ch(priv); mlx5e_build_txq_maps(priv); mlx5e_activate_channels(&priv->channels); mlx5e_xdp_tx_enable(priv); @@ -3135,7 +3161,7 @@ static void mlx5e_modify_admin_state(struct mlx5_core_dev *mdev, mlx5_set_port_admin_status(mdev, state); - if (!MLX5_ESWITCH_MANAGER(mdev) || mlx5_eswitch_mode(esw) == MLX5_ESWITCH_OFFLOADS) + if (mlx5_eswitch_mode(mdev) != MLX5_ESWITCH_LEGACY) return; if (state == MLX5_PORT_UP) @@ -3219,6 +3245,11 @@ int mlx5e_close(struct net_device *netdev) return err; } +static void mlx5e_free_drop_rq(struct mlx5e_rq *rq) +{ + mlx5_wq_destroy(&rq->wq_ctrl); +} + static int mlx5e_alloc_drop_rq(struct mlx5_core_dev *mdev, struct mlx5e_rq *rq, struct mlx5e_rq_param *param) @@ -3242,14 +3273,16 @@ static int mlx5e_alloc_drop_rq(struct mlx5_core_dev *mdev, return 0; } -static int mlx5e_alloc_drop_cq(struct mlx5_core_dev *mdev, +static int mlx5e_alloc_drop_cq(struct mlx5e_priv *priv, struct mlx5e_cq *cq, struct mlx5e_cq_param *param) { + struct mlx5_core_dev *mdev = priv->mdev; + 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(mdev, param, cq); + return mlx5e_alloc_cq_common(priv, param, cq); } int mlx5e_open_drop_rq(struct mlx5e_priv *priv, @@ -3263,7 +3296,7 @@ int mlx5e_open_drop_rq(struct mlx5e_priv *priv, mlx5e_build_drop_rq_param(priv, &rq_param); - err = mlx5e_alloc_drop_cq(mdev, cq, &cq_param); + err = mlx5e_alloc_drop_cq(priv, cq, &cq_param); if (err) return err; @@ -3286,7 +3319,7 @@ int mlx5e_open_drop_rq(struct mlx5e_priv *priv, return 0; err_free_rq: - mlx5e_free_rq(drop_rq); + mlx5e_free_drop_rq(drop_rq); err_destroy_cq: mlx5e_destroy_cq(cq); @@ -3300,7 +3333,7 @@ err_free_cq: void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq) { mlx5e_destroy_rq(drop_rq); - mlx5e_free_rq(drop_rq); + mlx5e_free_drop_rq(drop_rq); mlx5e_destroy_cq(&drop_rq->cq); mlx5e_free_cq(&drop_rq->cq); } @@ -3999,6 +4032,9 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, new_channels.params = *params; new_channels.params.sw_mtu = new_mtu; + err = mlx5e_validate_params(priv, &new_channels.params); + if (err) + goto out; if (params->xdp_prog && !mlx5e_rx_is_linear_skb(&new_channels.params, NULL)) { @@ -4251,6 +4287,20 @@ int mlx5e_get_vf_stats(struct net_device *dev, } #endif +static bool mlx5e_tunnel_proto_supported_tx(struct mlx5_core_dev *mdev, u8 proto_type) +{ + switch (proto_type) { + case IPPROTO_GRE: + return MLX5_CAP_ETH(mdev, tunnel_stateless_gre); + case IPPROTO_IPIP: + case IPPROTO_IPV6: + return (MLX5_CAP_ETH(mdev, tunnel_stateless_ip_over_ip) || + MLX5_CAP_ETH(mdev, tunnel_stateless_ip_over_ip_tx)); + default: + return false; + } +} + static bool mlx5e_gre_tunnel_inner_proto_offload_supported(struct mlx5_core_dev *mdev, struct sk_buff *skb) { @@ -4293,7 +4343,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, break; case IPPROTO_IPIP: case IPPROTO_IPV6: - if (mlx5e_tunnel_proto_supported(priv->mdev, IPPROTO_IPIP)) + if (mlx5e_tunnel_proto_supported_tx(priv->mdev, IPPROTO_IPIP)) return features; break; case IPPROTO_UDP: @@ -4342,6 +4392,7 @@ static void mlx5e_tx_timeout_work(struct work_struct *work) { struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv, tx_timeout_work); + struct net_device *netdev = priv->netdev; int i; rtnl_lock(); @@ -4350,9 +4401,9 @@ static void mlx5e_tx_timeout_work(struct work_struct *work) if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) goto unlock; - for (i = 0; i < priv->channels.num * priv->channels.params.num_tc; i++) { + for (i = 0; i < netdev->real_num_tx_queues; i++) { struct netdev_queue *dev_queue = - netdev_get_tx_queue(priv->netdev, i); + netdev_get_tx_queue(netdev, i); struct mlx5e_txqsq *sq = priv->txq2sq[i]; if (!netif_xmit_stopped(dev_queue)) @@ -4412,7 +4463,7 @@ static void mlx5e_rq_replace_xdp_prog(struct mlx5e_rq *rq, struct bpf_prog *prog struct bpf_prog *old_prog; old_prog = rcu_replace_pointer(rq->xdp_prog, prog, - lockdep_is_held(&rq->channel->priv->state_lock)); + lockdep_is_held(&rq->priv->state_lock)); if (old_prog) bpf_prog_put(old_prog); } @@ -4597,31 +4648,6 @@ const struct net_device_ops mlx5e_netdev_ops = { .ndo_get_devlink_port = mlx5e_get_devlink_port, }; -static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev) -{ - if (MLX5_CAP_GEN(mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH) - return -EOPNOTSUPP; - if (!MLX5_CAP_GEN(mdev, eth_net_offloads) || - !MLX5_CAP_GEN(mdev, nic_flow_table) || - !MLX5_CAP_ETH(mdev, csum_cap) || - !MLX5_CAP_ETH(mdev, max_lso_cap) || - !MLX5_CAP_ETH(mdev, vlan_cap) || - !MLX5_CAP_ETH(mdev, rss_ind_tbl_cap) || - MLX5_CAP_FLOWTABLE(mdev, - flow_table_properties_nic_receive.max_ft_level) - < 3) { - mlx5_core_warn(mdev, - "Not creating net device, some required device capabilities are missing\n"); - return -EOPNOTSUPP; - } - if (!MLX5_CAP_ETH(mdev, self_lb_en_modifiable)) - mlx5_core_warn(mdev, "Self loop back prevention is not supported\n"); - if (!MLX5_CAP_GEN(mdev, cq_moderation)) - mlx5_core_warn(mdev, "CQ moderation is not supported\n"); - - return 0; -} - void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len, int num_channels) { @@ -4877,6 +4903,17 @@ void mlx5e_vxlan_set_netdev_info(struct mlx5e_priv *priv) priv->netdev->udp_tunnel_nic_info = &priv->nic_info; } +static bool mlx5e_tunnel_any_tx_proto_supported(struct mlx5_core_dev *mdev) +{ + int tt; + + for (tt = 0; tt < MLX5E_NUM_TUNNEL_TT; tt++) { + if (mlx5e_tunnel_proto_supported_tx(mdev, mlx5e_get_proto_by_tunnel_type(tt))) + return true; + } + return (mlx5_vxlan_allowed(mdev->vxlan) || mlx5_geneve_tx_allowed(mdev)); +} + static void mlx5e_build_nic_netdev(struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -4922,8 +4959,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) mlx5e_vxlan_set_netdev_info(priv); - if (mlx5_vxlan_allowed(mdev->vxlan) || mlx5_geneve_tx_allowed(mdev) || - mlx5e_any_tunnel_proto_supported(mdev)) { + if (mlx5e_tunnel_any_tx_proto_supported(mdev)) { netdev->hw_enc_features |= NETIF_F_HW_CSUM; netdev->hw_enc_features |= NETIF_F_TSO; netdev->hw_enc_features |= NETIF_F_TSO6; @@ -4940,7 +4976,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) NETIF_F_GSO_UDP_TUNNEL_CSUM; } - if (mlx5e_tunnel_proto_supported(mdev, IPPROTO_GRE)) { + if (mlx5e_tunnel_proto_supported_tx(mdev, IPPROTO_GRE)) { netdev->hw_features |= NETIF_F_GSO_GRE | NETIF_F_GSO_GRE_CSUM; netdev->hw_enc_features |= NETIF_F_GSO_GRE | @@ -4949,7 +4985,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) NETIF_F_GSO_GRE_CSUM; } - if (mlx5e_tunnel_proto_supported(mdev, IPPROTO_IPIP)) { + if (mlx5e_tunnel_proto_supported_tx(mdev, IPPROTO_IPIP)) { netdev->hw_features |= NETIF_F_GSO_IPXIP4 | NETIF_F_GSO_IPXIP6; netdev->hw_enc_features |= NETIF_F_GSO_IPXIP4 | @@ -5334,10 +5370,14 @@ struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev, void *ppriv) { struct net_device *netdev; + unsigned int ptp_txqs = 0; int err; + if (MLX5_CAP_GEN(mdev, ts_cqe_to_dest_cqn)) + ptp_txqs = profile->max_tc; + netdev = alloc_etherdev_mqs(sizeof(struct mlx5e_priv), - nch * profile->max_tc, + nch * profile->max_tc + ptp_txqs, nch * profile->rq_groups); if (!netdev) { mlx5_core_err(mdev, "alloc_etherdev_mqs() failed\n"); @@ -5441,13 +5481,12 @@ void mlx5e_destroy_netdev(struct mlx5e_priv *priv) free_netdev(netdev); } -/* mlx5e_attach and mlx5e_detach scope should be only creating/destroying - * hardware contexts and to connect it to the current netdev. - */ -static int mlx5e_attach(struct mlx5_core_dev *mdev, void *vpriv) +static int mlx5e_resume(struct auxiliary_device *adev) { - struct mlx5e_priv *priv = vpriv; + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); + struct mlx5e_priv *priv = dev_get_drvdata(&adev->dev); struct net_device *netdev = priv->netdev; + struct mlx5_core_dev *mdev = edev->mdev; int err; if (netif_device_present(netdev)) @@ -5466,109 +5505,111 @@ static int mlx5e_attach(struct mlx5_core_dev *mdev, void *vpriv) return 0; } -static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv) +static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state) { - struct mlx5e_priv *priv = vpriv; + struct mlx5e_priv *priv = dev_get_drvdata(&adev->dev); struct net_device *netdev = priv->netdev; - -#ifdef CONFIG_MLX5_ESWITCH - if (MLX5_ESWITCH_MANAGER(mdev) && vpriv == mdev) - return; -#endif + struct mlx5_core_dev *mdev = priv->mdev; if (!netif_device_present(netdev)) - return; + return -ENODEV; mlx5e_detach_netdev(priv); mlx5e_destroy_mdev_resources(mdev); + return 0; } -static void *mlx5e_add(struct mlx5_core_dev *mdev) +static int mlx5e_probe(struct auxiliary_device *adev, + const struct auxiliary_device_id *id) { + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); + struct mlx5_core_dev *mdev = edev->mdev; struct net_device *netdev; + pm_message_t state = {}; void *priv; int err; int nch; - err = mlx5e_check_required_hca_cap(mdev); - if (err) - return NULL; - -#ifdef CONFIG_MLX5_ESWITCH - if (MLX5_ESWITCH_MANAGER(mdev) && - mlx5_eswitch_mode(mdev->priv.eswitch) == MLX5_ESWITCH_OFFLOADS) { - mlx5e_rep_register_vport_reps(mdev); - return mdev; - } -#endif - nch = mlx5e_get_max_num_channels(mdev); netdev = mlx5e_create_netdev(mdev, &mlx5e_nic_profile, nch, NULL); if (!netdev) { mlx5_core_err(mdev, "mlx5e_create_netdev failed\n"); - return NULL; + return -ENOMEM; } dev_net_set(netdev, mlx5_core_net(mdev)); priv = netdev_priv(netdev); + dev_set_drvdata(&adev->dev, priv); - err = mlx5e_attach(mdev, priv); + err = mlx5e_resume(adev); if (err) { - mlx5_core_err(mdev, "mlx5e_attach failed, %d\n", err); + mlx5_core_err(mdev, "mlx5e_resume failed, %d\n", err); goto err_destroy_netdev; } err = register_netdev(netdev); if (err) { mlx5_core_err(mdev, "register_netdev failed, %d\n", err); - goto err_detach; + goto err_resume; } mlx5e_devlink_port_type_eth_set(priv); mlx5e_dcbnl_init_app(priv); - return priv; + return 0; -err_detach: - mlx5e_detach(mdev, priv); +err_resume: + mlx5e_suspend(adev, state); err_destroy_netdev: mlx5e_destroy_netdev(priv); - return NULL; + return err; } -static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv) +static void mlx5e_remove(struct auxiliary_device *adev) { - struct mlx5e_priv *priv; + struct mlx5e_priv *priv = dev_get_drvdata(&adev->dev); + pm_message_t state = {}; -#ifdef CONFIG_MLX5_ESWITCH - if (MLX5_ESWITCH_MANAGER(mdev) && vpriv == mdev) { - mlx5e_rep_unregister_vport_reps(mdev); - return; - } -#endif - priv = vpriv; mlx5e_dcbnl_delete_app(priv); unregister_netdev(priv->netdev); - mlx5e_detach(mdev, vpriv); + mlx5e_suspend(adev, state); mlx5e_destroy_netdev(priv); } -static struct mlx5_interface mlx5e_interface = { - .add = mlx5e_add, - .remove = mlx5e_remove, - .attach = mlx5e_attach, - .detach = mlx5e_detach, - .protocol = MLX5_INTERFACE_PROTOCOL_ETH, +static const struct auxiliary_device_id mlx5e_id_table[] = { + { .name = MLX5_ADEV_NAME ".eth", }, + {}, +}; + +MODULE_DEVICE_TABLE(auxiliary, mlx5e_id_table); + +static struct auxiliary_driver mlx5e_driver = { + .name = "eth", + .probe = mlx5e_probe, + .remove = mlx5e_remove, + .suspend = mlx5e_suspend, + .resume = mlx5e_resume, + .id_table = mlx5e_id_table, }; -void mlx5e_init(void) +int mlx5e_init(void) { + int ret; + mlx5e_ipsec_build_inverse_table(); mlx5e_build_ptys2ethtool_map(); - mlx5_register_interface(&mlx5e_interface); + ret = mlx5e_rep_init(); + if (ret) + return ret; + + ret = auxiliary_driver_register(&mlx5e_driver); + if (ret) + mlx5e_rep_cleanup(); + return ret; } void mlx5e_cleanup(void) { - mlx5_unregister_interface(&mlx5e_interface); + auxiliary_driver_unregister(&mlx5e_driver); + mlx5e_rep_cleanup(); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 67247c33b9fd..989c70c1eda3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -64,7 +64,6 @@ static void mlx5e_rep_get_drvinfo(struct net_device *dev, strlcpy(drvinfo->driver, mlx5e_rep_driver_name, sizeof(drvinfo->driver)); - strlcpy(drvinfo->version, UTS_RELEASE, sizeof(drvinfo->version)); snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d.%d.%04d (%.16s)", fw_rev_maj(mdev), fw_rev_min(mdev), @@ -1316,16 +1315,48 @@ static const struct mlx5_eswitch_rep_ops rep_ops = { .get_proto_dev = mlx5e_vport_rep_get_proto_dev }; -void mlx5e_rep_register_vport_reps(struct mlx5_core_dev *mdev) +static int mlx5e_rep_probe(struct auxiliary_device *adev, + const struct auxiliary_device_id *id) { - struct mlx5_eswitch *esw = mdev->priv.eswitch; + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); + struct mlx5_core_dev *mdev = edev->mdev; + struct mlx5_eswitch *esw; + esw = mdev->priv.eswitch; mlx5_eswitch_register_vport_reps(esw, &rep_ops, REP_ETH); + return 0; } -void mlx5e_rep_unregister_vport_reps(struct mlx5_core_dev *mdev) +static void mlx5e_rep_remove(struct auxiliary_device *adev) { - struct mlx5_eswitch *esw = mdev->priv.eswitch; + struct mlx5_adev *vdev = container_of(adev, struct mlx5_adev, adev); + struct mlx5_core_dev *mdev = vdev->mdev; + struct mlx5_eswitch *esw; + esw = mdev->priv.eswitch; mlx5_eswitch_unregister_vport_reps(esw, REP_ETH); } + +static const struct auxiliary_device_id mlx5e_rep_id_table[] = { + { .name = MLX5_ADEV_NAME ".eth-rep", }, + {}, +}; + +MODULE_DEVICE_TABLE(auxiliary, mlx5e_rep_id_table); + +static struct auxiliary_driver mlx5e_rep_driver = { + .name = "eth-rep", + .probe = mlx5e_rep_probe, + .remove = mlx5e_rep_remove, + .id_table = mlx5e_rep_id_table, +}; + +int mlx5e_rep_init(void) +{ + return auxiliary_driver_register(&mlx5e_rep_driver); +} + +void mlx5e_rep_cleanup(void) +{ + auxiliary_driver_unregister(&mlx5e_rep_driver); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index 8932c387d46a..988195ab1c54 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -203,8 +203,8 @@ struct mlx5e_rep_sq { struct list_head list; }; -void mlx5e_rep_register_vport_reps(struct mlx5_core_dev *mdev); -void mlx5e_rep_unregister_vport_reps(struct mlx5_core_dev *mdev); +int mlx5e_rep_init(void); +void mlx5e_rep_cleanup(void); int mlx5e_rep_bond_init(struct mlx5e_rep_priv *rpriv); void mlx5e_rep_bond_cleanup(struct mlx5e_rep_priv *rpriv); int mlx5e_rep_bond_enslave(struct mlx5_eswitch *esw, struct net_device *netdev, @@ -232,6 +232,8 @@ static inline bool mlx5e_eswitch_rep(struct net_device *netdev) static inline bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) { return false; } static inline int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv) { return 0; } static inline void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv) {} +static inline int mlx5e_rep_init(void) { return 0; }; +static inline void mlx5e_rep_cleanup(void) {}; #endif static inline bool mlx5e_is_vport_rep(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 6628a0197b4e..7f5851c61218 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -52,7 +52,6 @@ #include "en/xsk/rx.h" #include "en/health.h" #include "en/params.h" -#include "en/txrx.h" static struct sk_buff * mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, @@ -503,7 +502,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) { struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix]; struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[0]; - struct mlx5e_icosq *sq = &rq->channel->icosq; + struct mlx5e_icosq *sq = rq->icosq; struct mlx5_wq_cyc *wq = &sq->wq; struct mlx5e_umr_wqe *umr_wqe; u16 xlt_offset = ix << (MLX5E_LOG_ALIGNED_MPWQE_PPW - 1); @@ -670,13 +669,13 @@ int mlx5e_poll_ico_cq(struct mlx5e_cq *cq) sqcc += wi->num_wqebbs; if (last_wqe && unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) { - netdev_WARN_ONCE(cq->channel->netdev, + netdev_WARN_ONCE(cq->netdev, "Bad OP in ICOSQ CQE: 0x%x\n", get_cqe_opcode(cqe)); mlx5e_dump_error_cqe(&sq->cq, sq->sqn, (struct mlx5_err_cqe *)cqe); if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) - queue_work(cq->channel->priv->wq, &sq->recover_work); + queue_work(cq->priv->wq, &sq->recover_work); break; } @@ -697,7 +696,7 @@ int mlx5e_poll_ico_cq(struct mlx5e_cq *cq) break; #endif default: - netdev_WARN_ONCE(cq->channel->netdev, + netdev_WARN_ONCE(cq->netdev, "Bad WQE type in ICOSQ WQE info: 0x%x\n", wi->wqe_type); } @@ -713,9 +712,9 @@ int mlx5e_poll_ico_cq(struct mlx5e_cq *cq) INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq) { - struct mlx5e_icosq *sq = &rq->channel->icosq; struct mlx5_wq_ll *wq = &rq->mpwqe.wq; u8 umr_completed = rq->mpwqe.umr_completed; + struct mlx5e_icosq *sq = rq->icosq; int alloc_err = 0; u8 missing, i; u16 head; @@ -1218,11 +1217,12 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, static void trigger_report(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) { struct mlx5_err_cqe *err_cqe = (struct mlx5_err_cqe *)cqe; + struct mlx5e_priv *priv = rq->priv; if (cqe_syndrome_needs_recover(err_cqe->syndrome) && !test_and_set_bit(MLX5E_RQ_STATE_RECOVERING, &rq->state)) { mlx5e_dump_error_cqe(&rq->cq, rq->rqn, err_cqe); - queue_work(rq->channel->priv->wq, &rq->recover_work); + queue_work(priv->wq, &rq->recover_work); } } @@ -1771,8 +1771,9 @@ wq_free_wqe: int mlx5e_rq_set_handlers(struct mlx5e_rq *rq, struct mlx5e_params *params, bool xsk) { + struct net_device *netdev = rq->netdev; struct mlx5_core_dev *mdev = rq->mdev; - struct mlx5e_channel *c = rq->channel; + struct mlx5e_priv *priv = rq->priv; switch (rq->wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: @@ -1784,15 +1785,15 @@ int mlx5e_rq_set_handlers(struct mlx5e_rq *rq, struct mlx5e_params *params, bool rq->post_wqes = mlx5e_post_rx_mpwqes; rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe; - rq->handle_rx_cqe = c->priv->profile->rx_handlers->handle_rx_cqe_mpwqe; + rq->handle_rx_cqe = priv->profile->rx_handlers->handle_rx_cqe_mpwqe; #ifdef CONFIG_MLX5_EN_IPSEC if (MLX5_IPSEC_DEV(mdev)) { - netdev_err(c->netdev, "MPWQE RQ with IPSec offload not supported\n"); + netdev_err(netdev, "MPWQE RQ with IPSec offload not supported\n"); return -EINVAL; } #endif if (!rq->handle_rx_cqe) { - netdev_err(c->netdev, "RX handler of MPWQE RQ is not set\n"); + netdev_err(netdev, "RX handler of MPWQE RQ is not set\n"); return -EINVAL; } break; @@ -1807,13 +1808,13 @@ int mlx5e_rq_set_handlers(struct mlx5e_rq *rq, struct mlx5e_params *params, bool #ifdef CONFIG_MLX5_EN_IPSEC if ((mlx5_fpga_ipsec_device_caps(mdev) & MLX5_ACCEL_IPSEC_CAP_DEVICE) && - c->priv->ipsec) + priv->ipsec) rq->handle_rx_cqe = mlx5e_ipsec_handle_rx_cqe; else #endif - rq->handle_rx_cqe = c->priv->profile->rx_handlers->handle_rx_cqe; + rq->handle_rx_cqe = priv->profile->rx_handlers->handle_rx_cqe; if (!rq->handle_rx_cqe) { - netdev_err(c->netdev, "RX handler of RQ is not set\n"); + netdev_err(netdev, "RX handler of RQ is not set\n"); return -EINVAL; } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 78f6a6f0a7e0..2cf2042b37c7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -248,6 +248,178 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(sw) return idx; } +static void mlx5e_stats_grp_sw_update_stats_xdp_red(struct mlx5e_sw_stats *s, + struct mlx5e_xdpsq_stats *xdpsq_red_stats) +{ + s->tx_xdp_xmit += xdpsq_red_stats->xmit; + s->tx_xdp_mpwqe += xdpsq_red_stats->mpwqe; + s->tx_xdp_inlnw += xdpsq_red_stats->inlnw; + s->tx_xdp_nops += xdpsq_red_stats->nops; + s->tx_xdp_full += xdpsq_red_stats->full; + s->tx_xdp_err += xdpsq_red_stats->err; + s->tx_xdp_cqes += xdpsq_red_stats->cqes; +} + +static void mlx5e_stats_grp_sw_update_stats_xdpsq(struct mlx5e_sw_stats *s, + struct mlx5e_xdpsq_stats *xdpsq_stats) +{ + s->rx_xdp_tx_xmit += xdpsq_stats->xmit; + s->rx_xdp_tx_mpwqe += xdpsq_stats->mpwqe; + s->rx_xdp_tx_inlnw += xdpsq_stats->inlnw; + s->rx_xdp_tx_nops += xdpsq_stats->nops; + s->rx_xdp_tx_full += xdpsq_stats->full; + s->rx_xdp_tx_err += xdpsq_stats->err; + s->rx_xdp_tx_cqe += xdpsq_stats->cqes; +} + +static void mlx5e_stats_grp_sw_update_stats_xsksq(struct mlx5e_sw_stats *s, + struct mlx5e_xdpsq_stats *xsksq_stats) +{ + s->tx_xsk_xmit += xsksq_stats->xmit; + s->tx_xsk_mpwqe += xsksq_stats->mpwqe; + s->tx_xsk_inlnw += xsksq_stats->inlnw; + s->tx_xsk_full += xsksq_stats->full; + s->tx_xsk_err += xsksq_stats->err; + s->tx_xsk_cqes += xsksq_stats->cqes; +} + +static void mlx5e_stats_grp_sw_update_stats_xskrq(struct mlx5e_sw_stats *s, + struct mlx5e_rq_stats *xskrq_stats) +{ + s->rx_xsk_packets += xskrq_stats->packets; + s->rx_xsk_bytes += xskrq_stats->bytes; + s->rx_xsk_csum_complete += xskrq_stats->csum_complete; + s->rx_xsk_csum_unnecessary += xskrq_stats->csum_unnecessary; + s->rx_xsk_csum_unnecessary_inner += xskrq_stats->csum_unnecessary_inner; + s->rx_xsk_csum_none += xskrq_stats->csum_none; + s->rx_xsk_ecn_mark += xskrq_stats->ecn_mark; + s->rx_xsk_removed_vlan_packets += xskrq_stats->removed_vlan_packets; + s->rx_xsk_xdp_drop += xskrq_stats->xdp_drop; + s->rx_xsk_xdp_redirect += xskrq_stats->xdp_redirect; + s->rx_xsk_wqe_err += xskrq_stats->wqe_err; + s->rx_xsk_mpwqe_filler_cqes += xskrq_stats->mpwqe_filler_cqes; + s->rx_xsk_mpwqe_filler_strides += xskrq_stats->mpwqe_filler_strides; + s->rx_xsk_oversize_pkts_sw_drop += xskrq_stats->oversize_pkts_sw_drop; + s->rx_xsk_buff_alloc_err += xskrq_stats->buff_alloc_err; + s->rx_xsk_cqe_compress_blks += xskrq_stats->cqe_compress_blks; + s->rx_xsk_cqe_compress_pkts += xskrq_stats->cqe_compress_pkts; + s->rx_xsk_congst_umr += xskrq_stats->congst_umr; + s->rx_xsk_arfs_err += xskrq_stats->arfs_err; +} + +static void mlx5e_stats_grp_sw_update_stats_rq_stats(struct mlx5e_sw_stats *s, + struct mlx5e_rq_stats *rq_stats) +{ + s->rx_packets += rq_stats->packets; + s->rx_bytes += rq_stats->bytes; + s->rx_lro_packets += rq_stats->lro_packets; + s->rx_lro_bytes += rq_stats->lro_bytes; + s->rx_ecn_mark += rq_stats->ecn_mark; + s->rx_removed_vlan_packets += rq_stats->removed_vlan_packets; + s->rx_csum_none += rq_stats->csum_none; + s->rx_csum_complete += rq_stats->csum_complete; + s->rx_csum_complete_tail += rq_stats->csum_complete_tail; + s->rx_csum_complete_tail_slow += rq_stats->csum_complete_tail_slow; + s->rx_csum_unnecessary += rq_stats->csum_unnecessary; + s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner; + s->rx_xdp_drop += rq_stats->xdp_drop; + s->rx_xdp_redirect += rq_stats->xdp_redirect; + s->rx_wqe_err += rq_stats->wqe_err; + s->rx_mpwqe_filler_cqes += rq_stats->mpwqe_filler_cqes; + s->rx_mpwqe_filler_strides += rq_stats->mpwqe_filler_strides; + s->rx_oversize_pkts_sw_drop += rq_stats->oversize_pkts_sw_drop; + s->rx_buff_alloc_err += rq_stats->buff_alloc_err; + s->rx_cqe_compress_blks += rq_stats->cqe_compress_blks; + s->rx_cqe_compress_pkts += rq_stats->cqe_compress_pkts; + s->rx_cache_reuse += rq_stats->cache_reuse; + s->rx_cache_full += rq_stats->cache_full; + s->rx_cache_empty += rq_stats->cache_empty; + s->rx_cache_busy += rq_stats->cache_busy; + s->rx_cache_waive += rq_stats->cache_waive; + s->rx_congst_umr += rq_stats->congst_umr; + s->rx_arfs_err += rq_stats->arfs_err; + s->rx_recover += rq_stats->recover; +#ifdef CONFIG_MLX5_EN_TLS + s->rx_tls_decrypted_packets += rq_stats->tls_decrypted_packets; + s->rx_tls_decrypted_bytes += rq_stats->tls_decrypted_bytes; + s->rx_tls_ctx += rq_stats->tls_ctx; + s->rx_tls_del += rq_stats->tls_del; + s->rx_tls_resync_req_pkt += rq_stats->tls_resync_req_pkt; + s->rx_tls_resync_req_start += rq_stats->tls_resync_req_start; + s->rx_tls_resync_req_end += rq_stats->tls_resync_req_end; + s->rx_tls_resync_req_skip += rq_stats->tls_resync_req_skip; + s->rx_tls_resync_res_ok += rq_stats->tls_resync_res_ok; + s->rx_tls_resync_res_skip += rq_stats->tls_resync_res_skip; + s->rx_tls_err += rq_stats->tls_err; +#endif +} + +static void mlx5e_stats_grp_sw_update_stats_ch_stats(struct mlx5e_sw_stats *s, + struct mlx5e_ch_stats *ch_stats) +{ + s->ch_events += ch_stats->events; + s->ch_poll += ch_stats->poll; + s->ch_arm += ch_stats->arm; + s->ch_aff_change += ch_stats->aff_change; + s->ch_force_irq += ch_stats->force_irq; + s->ch_eq_rearm += ch_stats->eq_rearm; +} + +static void mlx5e_stats_grp_sw_update_stats_sq(struct mlx5e_sw_stats *s, + struct mlx5e_sq_stats *sq_stats) +{ + s->tx_packets += sq_stats->packets; + s->tx_bytes += sq_stats->bytes; + s->tx_tso_packets += sq_stats->tso_packets; + s->tx_tso_bytes += sq_stats->tso_bytes; + s->tx_tso_inner_packets += sq_stats->tso_inner_packets; + s->tx_tso_inner_bytes += sq_stats->tso_inner_bytes; + s->tx_added_vlan_packets += sq_stats->added_vlan_packets; + s->tx_nop += sq_stats->nop; + s->tx_mpwqe_blks += sq_stats->mpwqe_blks; + s->tx_mpwqe_pkts += sq_stats->mpwqe_pkts; + s->tx_queue_stopped += sq_stats->stopped; + s->tx_queue_wake += sq_stats->wake; + s->tx_queue_dropped += sq_stats->dropped; + s->tx_cqe_err += sq_stats->cqe_err; + s->tx_recover += sq_stats->recover; + s->tx_xmit_more += sq_stats->xmit_more; + s->tx_csum_partial_inner += sq_stats->csum_partial_inner; + s->tx_csum_none += sq_stats->csum_none; + s->tx_csum_partial += sq_stats->csum_partial; +#ifdef CONFIG_MLX5_EN_TLS + s->tx_tls_encrypted_packets += sq_stats->tls_encrypted_packets; + s->tx_tls_encrypted_bytes += sq_stats->tls_encrypted_bytes; + s->tx_tls_ctx += sq_stats->tls_ctx; + s->tx_tls_ooo += sq_stats->tls_ooo; + s->tx_tls_dump_bytes += sq_stats->tls_dump_bytes; + s->tx_tls_dump_packets += sq_stats->tls_dump_packets; + s->tx_tls_resync_bytes += sq_stats->tls_resync_bytes; + s->tx_tls_skip_no_sync_data += sq_stats->tls_skip_no_sync_data; + s->tx_tls_drop_no_sync_data += sq_stats->tls_drop_no_sync_data; + s->tx_tls_drop_bypass_req += sq_stats->tls_drop_bypass_req; +#endif + s->tx_cqes += sq_stats->cqes; +} + +static void mlx5e_stats_grp_sw_update_stats_ptp(struct mlx5e_priv *priv, + struct mlx5e_sw_stats *s) +{ + int i; + + if (!priv->port_ptp_opened) + return; + + mlx5e_stats_grp_sw_update_stats_ch_stats(s, &priv->port_ptp_stats.ch); + + for (i = 0; i < priv->max_opened_tc; i++) { + mlx5e_stats_grp_sw_update_stats_sq(s, &priv->port_ptp_stats.sq[i]); + + /* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=92657 */ + barrier(); + } +} + static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(sw) { struct mlx5e_sw_stats *s = &priv->stats.sw; @@ -258,144 +430,25 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(sw) for (i = 0; i < priv->max_nch; i++) { struct mlx5e_channel_stats *channel_stats = &priv->channel_stats[i]; - struct mlx5e_xdpsq_stats *xdpsq_red_stats = &channel_stats->xdpsq; - struct mlx5e_xdpsq_stats *xdpsq_stats = &channel_stats->rq_xdpsq; - struct mlx5e_xdpsq_stats *xsksq_stats = &channel_stats->xsksq; - struct mlx5e_rq_stats *xskrq_stats = &channel_stats->xskrq; - struct mlx5e_rq_stats *rq_stats = &channel_stats->rq; - struct mlx5e_ch_stats *ch_stats = &channel_stats->ch; int j; - s->rx_packets += rq_stats->packets; - s->rx_bytes += rq_stats->bytes; - s->rx_lro_packets += rq_stats->lro_packets; - s->rx_lro_bytes += rq_stats->lro_bytes; - s->rx_ecn_mark += rq_stats->ecn_mark; - s->rx_removed_vlan_packets += rq_stats->removed_vlan_packets; - s->rx_csum_none += rq_stats->csum_none; - s->rx_csum_complete += rq_stats->csum_complete; - s->rx_csum_complete_tail += rq_stats->csum_complete_tail; - s->rx_csum_complete_tail_slow += rq_stats->csum_complete_tail_slow; - s->rx_csum_unnecessary += rq_stats->csum_unnecessary; - s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner; - s->rx_xdp_drop += rq_stats->xdp_drop; - s->rx_xdp_redirect += rq_stats->xdp_redirect; - s->rx_xdp_tx_xmit += xdpsq_stats->xmit; - s->rx_xdp_tx_mpwqe += xdpsq_stats->mpwqe; - s->rx_xdp_tx_inlnw += xdpsq_stats->inlnw; - s->rx_xdp_tx_nops += xdpsq_stats->nops; - s->rx_xdp_tx_full += xdpsq_stats->full; - s->rx_xdp_tx_err += xdpsq_stats->err; - s->rx_xdp_tx_cqe += xdpsq_stats->cqes; - s->rx_wqe_err += rq_stats->wqe_err; - s->rx_mpwqe_filler_cqes += rq_stats->mpwqe_filler_cqes; - s->rx_mpwqe_filler_strides += rq_stats->mpwqe_filler_strides; - s->rx_oversize_pkts_sw_drop += rq_stats->oversize_pkts_sw_drop; - s->rx_buff_alloc_err += rq_stats->buff_alloc_err; - s->rx_cqe_compress_blks += rq_stats->cqe_compress_blks; - s->rx_cqe_compress_pkts += rq_stats->cqe_compress_pkts; - s->rx_cache_reuse += rq_stats->cache_reuse; - s->rx_cache_full += rq_stats->cache_full; - s->rx_cache_empty += rq_stats->cache_empty; - s->rx_cache_busy += rq_stats->cache_busy; - s->rx_cache_waive += rq_stats->cache_waive; - s->rx_congst_umr += rq_stats->congst_umr; - s->rx_arfs_err += rq_stats->arfs_err; - s->rx_recover += rq_stats->recover; -#ifdef CONFIG_MLX5_EN_TLS - s->rx_tls_decrypted_packets += rq_stats->tls_decrypted_packets; - s->rx_tls_decrypted_bytes += rq_stats->tls_decrypted_bytes; - s->rx_tls_ctx += rq_stats->tls_ctx; - s->rx_tls_del += rq_stats->tls_del; - s->rx_tls_resync_req_pkt += rq_stats->tls_resync_req_pkt; - s->rx_tls_resync_req_start += rq_stats->tls_resync_req_start; - s->rx_tls_resync_req_end += rq_stats->tls_resync_req_end; - s->rx_tls_resync_req_skip += rq_stats->tls_resync_req_skip; - s->rx_tls_resync_res_ok += rq_stats->tls_resync_res_ok; - s->rx_tls_resync_res_skip += rq_stats->tls_resync_res_skip; - s->rx_tls_err += rq_stats->tls_err; -#endif - s->ch_events += ch_stats->events; - s->ch_poll += ch_stats->poll; - s->ch_arm += ch_stats->arm; - s->ch_aff_change += ch_stats->aff_change; - s->ch_force_irq += ch_stats->force_irq; - s->ch_eq_rearm += ch_stats->eq_rearm; + mlx5e_stats_grp_sw_update_stats_rq_stats(s, &channel_stats->rq); + mlx5e_stats_grp_sw_update_stats_xdpsq(s, &channel_stats->rq_xdpsq); + mlx5e_stats_grp_sw_update_stats_ch_stats(s, &channel_stats->ch); /* xdp redirect */ - s->tx_xdp_xmit += xdpsq_red_stats->xmit; - s->tx_xdp_mpwqe += xdpsq_red_stats->mpwqe; - s->tx_xdp_inlnw += xdpsq_red_stats->inlnw; - s->tx_xdp_nops += xdpsq_red_stats->nops; - s->tx_xdp_full += xdpsq_red_stats->full; - s->tx_xdp_err += xdpsq_red_stats->err; - s->tx_xdp_cqes += xdpsq_red_stats->cqes; + mlx5e_stats_grp_sw_update_stats_xdp_red(s, &channel_stats->xdpsq); /* AF_XDP zero-copy */ - s->rx_xsk_packets += xskrq_stats->packets; - s->rx_xsk_bytes += xskrq_stats->bytes; - s->rx_xsk_csum_complete += xskrq_stats->csum_complete; - s->rx_xsk_csum_unnecessary += xskrq_stats->csum_unnecessary; - s->rx_xsk_csum_unnecessary_inner += xskrq_stats->csum_unnecessary_inner; - s->rx_xsk_csum_none += xskrq_stats->csum_none; - s->rx_xsk_ecn_mark += xskrq_stats->ecn_mark; - s->rx_xsk_removed_vlan_packets += xskrq_stats->removed_vlan_packets; - s->rx_xsk_xdp_drop += xskrq_stats->xdp_drop; - s->rx_xsk_xdp_redirect += xskrq_stats->xdp_redirect; - s->rx_xsk_wqe_err += xskrq_stats->wqe_err; - s->rx_xsk_mpwqe_filler_cqes += xskrq_stats->mpwqe_filler_cqes; - s->rx_xsk_mpwqe_filler_strides += xskrq_stats->mpwqe_filler_strides; - s->rx_xsk_oversize_pkts_sw_drop += xskrq_stats->oversize_pkts_sw_drop; - s->rx_xsk_buff_alloc_err += xskrq_stats->buff_alloc_err; - s->rx_xsk_cqe_compress_blks += xskrq_stats->cqe_compress_blks; - s->rx_xsk_cqe_compress_pkts += xskrq_stats->cqe_compress_pkts; - s->rx_xsk_congst_umr += xskrq_stats->congst_umr; - s->rx_xsk_arfs_err += xskrq_stats->arfs_err; - s->tx_xsk_xmit += xsksq_stats->xmit; - s->tx_xsk_mpwqe += xsksq_stats->mpwqe; - s->tx_xsk_inlnw += xsksq_stats->inlnw; - s->tx_xsk_full += xsksq_stats->full; - s->tx_xsk_err += xsksq_stats->err; - s->tx_xsk_cqes += xsksq_stats->cqes; + mlx5e_stats_grp_sw_update_stats_xskrq(s, &channel_stats->xskrq); + mlx5e_stats_grp_sw_update_stats_xsksq(s, &channel_stats->xsksq); for (j = 0; j < priv->max_opened_tc; j++) { - struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j]; - - s->tx_packets += sq_stats->packets; - s->tx_bytes += sq_stats->bytes; - s->tx_tso_packets += sq_stats->tso_packets; - s->tx_tso_bytes += sq_stats->tso_bytes; - s->tx_tso_inner_packets += sq_stats->tso_inner_packets; - s->tx_tso_inner_bytes += sq_stats->tso_inner_bytes; - s->tx_added_vlan_packets += sq_stats->added_vlan_packets; - s->tx_nop += sq_stats->nop; - s->tx_mpwqe_blks += sq_stats->mpwqe_blks; - s->tx_mpwqe_pkts += sq_stats->mpwqe_pkts; - s->tx_queue_stopped += sq_stats->stopped; - s->tx_queue_wake += sq_stats->wake; - s->tx_queue_dropped += sq_stats->dropped; - s->tx_cqe_err += sq_stats->cqe_err; - s->tx_recover += sq_stats->recover; - s->tx_xmit_more += sq_stats->xmit_more; - s->tx_csum_partial_inner += sq_stats->csum_partial_inner; - s->tx_csum_none += sq_stats->csum_none; - s->tx_csum_partial += sq_stats->csum_partial; -#ifdef CONFIG_MLX5_EN_TLS - s->tx_tls_encrypted_packets += sq_stats->tls_encrypted_packets; - s->tx_tls_encrypted_bytes += sq_stats->tls_encrypted_bytes; - s->tx_tls_ctx += sq_stats->tls_ctx; - s->tx_tls_ooo += sq_stats->tls_ooo; - s->tx_tls_dump_bytes += sq_stats->tls_dump_bytes; - s->tx_tls_dump_packets += sq_stats->tls_dump_packets; - s->tx_tls_resync_bytes += sq_stats->tls_resync_bytes; - s->tx_tls_skip_no_sync_data += sq_stats->tls_skip_no_sync_data; - s->tx_tls_drop_no_sync_data += sq_stats->tls_drop_no_sync_data; - s->tx_tls_drop_bypass_req += sq_stats->tls_drop_bypass_req; -#endif - s->tx_cqes += sq_stats->cqes; + mlx5e_stats_grp_sw_update_stats_sq(s, &channel_stats->sq[j]); /* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=92657 */ barrier(); } } + mlx5e_stats_grp_sw_update_stats_ptp(priv, s); } static const struct counter_desc q_stats_desc[] = { @@ -1656,6 +1709,37 @@ static const struct counter_desc ch_stats_desc[] = { { MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, eq_rearm) }, }; +static const struct counter_desc ptp_sq_stats_desc[] = { + { MLX5E_DECLARE_PTP_TX_STAT(struct mlx5e_sq_stats, packets) }, + { MLX5E_DECLARE_PTP_TX_STAT(struct mlx5e_sq_stats, bytes) }, + { MLX5E_DECLARE_PTP_TX_STAT(struct mlx5e_sq_stats, csum_partial) }, + { MLX5E_DECLARE_PTP_TX_STAT(struct mlx5e_sq_stats, csum_partial_inner) }, + { MLX5E_DECLARE_PTP_TX_STAT(struct mlx5e_sq_stats, added_vlan_packets) }, + { MLX5E_DECLARE_PTP_TX_STAT(struct mlx5e_sq_stats, nop) }, + { MLX5E_DECLARE_PTP_TX_STAT(struct mlx5e_sq_stats, csum_none) }, + { MLX5E_DECLARE_PTP_TX_STAT(struct mlx5e_sq_stats, stopped) }, + { MLX5E_DECLARE_PTP_TX_STAT(struct mlx5e_sq_stats, dropped) }, + { MLX5E_DECLARE_PTP_TX_STAT(struct mlx5e_sq_stats, xmit_more) }, + { MLX5E_DECLARE_PTP_TX_STAT(struct mlx5e_sq_stats, recover) }, + { MLX5E_DECLARE_PTP_TX_STAT(struct mlx5e_sq_stats, cqes) }, + { MLX5E_DECLARE_PTP_TX_STAT(struct mlx5e_sq_stats, wake) }, + { MLX5E_DECLARE_PTP_TX_STAT(struct mlx5e_sq_stats, cqe_err) }, +}; + +static const struct counter_desc ptp_ch_stats_desc[] = { + { MLX5E_DECLARE_PTP_CH_STAT(struct mlx5e_ch_stats, events) }, + { MLX5E_DECLARE_PTP_CH_STAT(struct mlx5e_ch_stats, poll) }, + { MLX5E_DECLARE_PTP_CH_STAT(struct mlx5e_ch_stats, arm) }, + { MLX5E_DECLARE_PTP_CH_STAT(struct mlx5e_ch_stats, eq_rearm) }, +}; + +static const struct counter_desc ptp_cq_stats_desc[] = { + { MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, cqe) }, + { MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, err_cqe) }, + { MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, abort) }, + { MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, abort_abs_diff_ns) }, +}; + #define NUM_RQ_STATS ARRAY_SIZE(rq_stats_desc) #define NUM_SQ_STATS ARRAY_SIZE(sq_stats_desc) #define NUM_XDPSQ_STATS ARRAY_SIZE(xdpsq_stats_desc) @@ -1663,6 +1747,69 @@ static const struct counter_desc ch_stats_desc[] = { #define NUM_XSKRQ_STATS ARRAY_SIZE(xskrq_stats_desc) #define NUM_XSKSQ_STATS ARRAY_SIZE(xsksq_stats_desc) #define NUM_CH_STATS ARRAY_SIZE(ch_stats_desc) +#define NUM_PTP_SQ_STATS ARRAY_SIZE(ptp_sq_stats_desc) +#define NUM_PTP_CH_STATS ARRAY_SIZE(ptp_ch_stats_desc) +#define NUM_PTP_CQ_STATS ARRAY_SIZE(ptp_cq_stats_desc) + +static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(ptp) +{ + return priv->port_ptp_opened ? + NUM_PTP_CH_STATS + + ((NUM_PTP_SQ_STATS + NUM_PTP_CQ_STATS) * priv->max_opened_tc) : + 0; +} + +static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(ptp) +{ + int i, tc; + + if (!priv->port_ptp_opened) + return idx; + + for (i = 0; i < NUM_PTP_CH_STATS; i++) + sprintf(data + (idx++) * ETH_GSTRING_LEN, + ptp_ch_stats_desc[i].format); + + for (tc = 0; tc < priv->max_opened_tc; tc++) + for (i = 0; i < NUM_PTP_SQ_STATS; i++) + sprintf(data + (idx++) * ETH_GSTRING_LEN, + ptp_sq_stats_desc[i].format, tc); + + for (tc = 0; tc < priv->max_opened_tc; tc++) + for (i = 0; i < NUM_PTP_CQ_STATS; i++) + sprintf(data + (idx++) * ETH_GSTRING_LEN, + ptp_cq_stats_desc[i].format, tc); + return idx; +} + +static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(ptp) +{ + int i, tc; + + if (!priv->port_ptp_opened) + return idx; + + for (i = 0; i < NUM_PTP_CH_STATS; i++) + data[idx++] = + MLX5E_READ_CTR64_CPU(&priv->port_ptp_stats.ch, + ptp_ch_stats_desc, i); + + for (tc = 0; tc < priv->max_opened_tc; tc++) + for (i = 0; i < NUM_PTP_SQ_STATS; i++) + data[idx++] = + MLX5E_READ_CTR64_CPU(&priv->port_ptp_stats.sq[tc], + ptp_sq_stats_desc, i); + + for (tc = 0; tc < priv->max_opened_tc; tc++) + for (i = 0; i < NUM_PTP_CQ_STATS; i++) + data[idx++] = + MLX5E_READ_CTR64_CPU(&priv->port_ptp_stats.cq[tc], + ptp_cq_stats_desc, i); + + return idx; +} + +static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(ptp) { return; } static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(channels) { @@ -1784,6 +1931,7 @@ MLX5E_DEFINE_STATS_GRP(channels, 0); MLX5E_DEFINE_STATS_GRP(per_port_buff_congest, 0); MLX5E_DEFINE_STATS_GRP(eth_ext, 0); static MLX5E_DEFINE_STATS_GRP(tls, 0); +static MLX5E_DEFINE_STATS_GRP(ptp, 0); /* The stats groups order is opposite to the update_stats() order calls */ mlx5e_stats_grp_t mlx5e_nic_stats_grps[] = { @@ -1806,6 +1954,7 @@ mlx5e_stats_grp_t mlx5e_nic_stats_grps[] = { &MLX5E_STATS_GRP(tls), &MLX5E_STATS_GRP(channels), &MLX5E_STATS_GRP(per_port_buff_congest), + &MLX5E_STATS_GRP(ptp), }; unsigned int mlx5e_nic_stats_grps_num(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 162daaadb0d8..e41fc11f2ce7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -51,6 +51,10 @@ #define MLX5E_DECLARE_XSKSQ_STAT(type, fld) "tx%d_xsk_"#fld, offsetof(type, fld) #define MLX5E_DECLARE_CH_STAT(type, fld) "ch%d_"#fld, offsetof(type, fld) +#define MLX5E_DECLARE_PTP_TX_STAT(type, fld) "ptp_tx%d_"#fld, offsetof(type, fld) +#define MLX5E_DECLARE_PTP_CH_STAT(type, fld) "ptp_ch_"#fld, offsetof(type, fld) +#define MLX5E_DECLARE_PTP_CQ_STAT(type, fld) "ptp_cq%d_"#fld, offsetof(type, fld) + struct counter_desc { char format[ETH_GSTRING_LEN]; size_t offset; /* Byte offset */ @@ -398,6 +402,13 @@ struct mlx5e_ch_stats { u64 eq_rearm; }; +struct mlx5e_ptp_cq_stats { + u64 cqe; + u64 err_cqe; + u64 abort; + u64 abort_abs_diff_ns; +}; + struct mlx5e_stats { struct mlx5e_sw_stats sw; struct mlx5e_qcounter_stats qcnt; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index ce710f22b1ff..4cdf834fa74a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -271,8 +271,6 @@ mlx5e_tc_match_to_reg_set(struct mlx5_core_dev *mdev, return 0; } -#define esw_offloads_mode(esw) (mlx5_eswitch_mode(esw) == MLX5_ESWITCH_OFFLOADS) - static struct mlx5_tc_ct_priv * get_ct_priv(struct mlx5e_priv *priv) { @@ -280,7 +278,7 @@ get_ct_priv(struct mlx5e_priv *priv) struct mlx5_rep_uplink_priv *uplink_priv; struct mlx5e_rep_priv *uplink_rpriv; - if (esw_offloads_mode(esw)) { + if (is_mdev_switchdev_mode(priv->mdev)) { uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); uplink_priv = &uplink_rpriv->uplink_priv; @@ -297,7 +295,7 @@ mlx5_tc_rule_insert(struct mlx5e_priv *priv, { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - if (esw_offloads_mode(esw)) + if (is_mdev_switchdev_mode(priv->mdev)) return mlx5_eswitch_add_offloaded_rule(esw, spec, attr); return mlx5e_add_offloaded_nic_rule(priv, spec, attr); @@ -310,7 +308,7 @@ mlx5_tc_rule_delete(struct mlx5e_priv *priv, { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - if (esw_offloads_mode(esw)) { + if (is_mdev_switchdev_mode(priv->mdev)) { mlx5_eswitch_del_offloaded_rule(esw, rule, attr); return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index d97203cf6a00..e47e2a0059d0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -32,6 +32,7 @@ #include <linux/tcp.h> #include <linux/if_vlan.h> +#include <linux/ptp_classify.h> #include <net/geneve.h> #include <net/dsfield.h> #include "en.h" @@ -39,6 +40,7 @@ #include "ipoib/ipoib.h" #include "en_accel/en_accel.h" #include "lib/clock.h" +#include "en/ptp.h" static void mlx5e_dma_unmap_wqe_err(struct mlx5e_txqsq *sq, u8 num_dma) { @@ -66,14 +68,73 @@ static inline int mlx5e_get_dscp_up(struct mlx5e_priv *priv, struct sk_buff *skb } #endif +static bool mlx5e_use_ptpsq(struct sk_buff *skb) +{ + struct flow_keys fk; + + if (!skb_flow_dissect_flow_keys(skb, &fk, 0)) + return false; + + if (fk.basic.n_proto == htons(ETH_P_1588)) + return true; + + if (fk.basic.n_proto != htons(ETH_P_IP) && + fk.basic.n_proto != htons(ETH_P_IPV6)) + return false; + + return (fk.basic.ip_proto == IPPROTO_UDP && + fk.ports.dst == htons(PTP_EV_PORT)); +} + +static u16 mlx5e_select_ptpsq(struct net_device *dev, struct sk_buff *skb) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + int up = 0; + + if (!netdev_get_num_tc(dev)) + goto return_txq; + +#ifdef CONFIG_MLX5_CORE_EN_DCB + if (priv->dcbx_dp.trust_state == MLX5_QPTS_TRUST_DSCP) + up = mlx5e_get_dscp_up(priv, skb); + else +#endif + if (skb_vlan_tag_present(skb)) + up = skb_vlan_tag_get_prio(skb); + +return_txq: + return priv->port_ptp_tc2realtxq[up]; +} + u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { - int txq_ix = netdev_pick_tx(dev, skb, NULL); struct mlx5e_priv *priv = netdev_priv(dev); + int txq_ix; int up = 0; int ch_ix; + if (unlikely(priv->channels.port_ptp)) { + int num_tc_x_num_ch; + + if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && + mlx5e_use_ptpsq(skb)) + return mlx5e_select_ptpsq(dev, skb); + + /* Sync with mlx5e_update_num_tc_x_num_ch - avoid refetching. */ + num_tc_x_num_ch = READ_ONCE(priv->num_tc_x_num_ch); + + txq_ix = netdev_pick_tx(dev, skb, NULL); + /* Fix netdev_pick_tx() not to choose ptp_channel txqs. + * If they are selected, switch to regular queues. + * Driver to select these queues only at mlx5e_select_ptpsq(). + */ + if (unlikely(txq_ix >= num_tc_x_num_ch)) + txq_ix %= num_tc_x_num_ch; + } else { + txq_ix = netdev_pick_tx(dev, skb, NULL); + } + if (!netdev_get_num_tc(dev)) return txq_ix; @@ -402,6 +463,12 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb, mlx5e_tx_check_stop(sq); + if (unlikely(sq->ptpsq)) { + mlx5e_skb_cb_hwtstamp_init(skb); + mlx5e_skb_fifo_push(&sq->ptpsq->skb_fifo, skb); + skb_get(skb); + } + send_doorbell = __netdev_tx_sent_queue(sq->txq, attr->num_bytes, xmit_more); if (send_doorbell) mlx5e_notify_hw(wq, sq->pc, sq->uar_map, cseg); @@ -579,7 +646,7 @@ mlx5e_sq_xmit_mpwqe(struct mlx5e_txqsq *sq, struct sk_buff *skb, goto err_unmap; mlx5e_dma_push(sq, txd.dma_addr, txd.len, MLX5E_DMA_MAP_SINGLE); - mlx5e_skb_fifo_push(sq, skb); + mlx5e_skb_fifo_push(&sq->db.skb_fifo, skb); mlx5e_tx_mpwqe_add_dseg(sq, &txd); @@ -707,7 +774,11 @@ static void mlx5e_consume_skb(struct mlx5e_txqsq *sq, struct sk_buff *skb, u64 ts = get_cqe_ts(cqe); hwts.hwtstamp = mlx5_timecounter_cyc2time(sq->clock, ts); - skb_tstamp_tx(skb, &hwts); + if (sq->ptpsq) + mlx5e_skb_cb_hwtstamp_handler(skb, MLX5E_SKB_CB_CQE_HWTSTAMP, + hwts.hwtstamp, sq->ptpsq->cq_stats); + else + skb_tstamp_tx(skb, &hwts); } napi_consume_skb(skb, napi_budget); @@ -719,7 +790,7 @@ static void mlx5e_tx_wi_consume_fifo_skbs(struct mlx5e_txqsq *sq, struct mlx5e_t int i; for (i = 0; i < wi->num_fifo_pkts; i++) { - struct sk_buff *skb = mlx5e_skb_fifo_pop(sq); + struct sk_buff *skb = mlx5e_skb_fifo_pop(&sq->db.skb_fifo); mlx5e_consume_skb(sq, skb, cqe, napi_budget); } @@ -805,8 +876,7 @@ 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->channel->priv->wq, - &sq->recover_work); + queue_work(cq->priv->wq, &sq->recover_work); } stats->cqe_err++; } @@ -840,7 +910,7 @@ static void mlx5e_tx_wi_kfree_fifo_skbs(struct mlx5e_txqsq *sq, struct mlx5e_tx_ int i; for (i = 0; i < wi->num_fifo_pkts; i++) - dev_kfree_skb_any(mlx5e_skb_fifo_pop(sq)); + dev_kfree_skb_any(mlx5e_skb_fifo_pop(&sq->db.skb_fifo)); } void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index d5868670f8a5..1ec3d62f026d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -221,14 +221,13 @@ void mlx5e_completion_event(struct mlx5_core_cq *mcq, struct mlx5_eqe *eqe) napi_schedule(cq->napi); cq->event_ctr++; - cq->channel->stats->events++; + cq->ch_stats->events++; } void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event) { struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq); - struct mlx5e_channel *c = cq->channel; - struct net_device *netdev = c->netdev; + struct net_device *netdev = cq->netdev; netdev_err(netdev, "%s: cqn=0x%.6x event=0x%.2x\n", __func__, mcq->cqn, event); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 8ebfe782f95e..fc0afa03d407 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -136,7 +136,7 @@ static int mlx5_eq_comp_int(struct notifier_block *nb, eqe = next_eqe_sw(eq); if (!eqe) - goto out; + return 0; do { struct mlx5_core_cq *cq; @@ -161,8 +161,6 @@ static int mlx5_eq_comp_int(struct notifier_block *nb, ++eq->cons_index; } while ((++num_eqes < MLX5_EQ_POLLING_BUDGET) && (eqe = next_eqe_sw(eq))); - -out: eq_update_ci(eq, 1); if (cqn != -1) @@ -189,19 +187,21 @@ u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq_comp *eq) return count_eqe; } -static void mlx5_eq_async_int_lock(struct mlx5_eq_async *eq, unsigned long *flags) +static void mlx5_eq_async_int_lock(struct mlx5_eq_async *eq, bool recovery, + unsigned long *flags) __acquires(&eq->lock) { - if (in_irq()) + if (!recovery) spin_lock(&eq->lock); else spin_lock_irqsave(&eq->lock, *flags); } -static void mlx5_eq_async_int_unlock(struct mlx5_eq_async *eq, unsigned long *flags) +static void mlx5_eq_async_int_unlock(struct mlx5_eq_async *eq, bool recovery, + unsigned long *flags) __releases(&eq->lock) { - if (in_irq()) + if (!recovery) spin_unlock(&eq->lock); else spin_unlock_irqrestore(&eq->lock, *flags); @@ -223,11 +223,13 @@ static int mlx5_eq_async_int(struct notifier_block *nb, struct mlx5_eqe *eqe; unsigned long flags; int num_eqes = 0; + bool recovery; dev = eq->dev; eqt = dev->priv.eq_table; - mlx5_eq_async_int_lock(eq_async, &flags); + recovery = action == ASYNC_EQ_RECOVER; + mlx5_eq_async_int_lock(eq_async, recovery, &flags); eqe = next_eqe_sw(eq); if (!eqe) @@ -246,12 +248,12 @@ static int mlx5_eq_async_int(struct notifier_block *nb, ++eq->cons_index; } while ((++num_eqes < MLX5_EQ_POLLING_BUDGET) && (eqe = next_eqe_sw(eq))); + eq_update_ci(eq, 1); out: - eq_update_ci(eq, 1); - mlx5_eq_async_int_unlock(eq_async, &flags); + mlx5_eq_async_int_unlock(eq_async, recovery, &flags); - return unlikely(action == ASYNC_EQ_RECOVER) ? num_eqes : 0; + return unlikely(recovery) ? num_eqes : 0; } void mlx5_cmd_eq_recover(struct mlx5_core_dev *dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c index d46f8b225ebe..2b85d4777303 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c @@ -101,7 +101,7 @@ int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw, vport->egress.acl = esw_acl_table_create(esw, vport->vport, MLX5_FLOW_NAMESPACE_ESW_EGRESS, table_size); - if (IS_ERR_OR_NULL(vport->egress.acl)) { + if (IS_ERR(vport->egress.acl)) { err = PTR_ERR(vport->egress.acl); vport->egress.acl = NULL; goto out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c index c3faae67e4d6..4c74e2690d57 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c @@ -173,7 +173,7 @@ int esw_acl_egress_ofld_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport table_size++; vport->egress.acl = esw_acl_table_create(esw, vport->vport, MLX5_FLOW_NAMESPACE_ESW_EGRESS, table_size); - if (IS_ERR_OR_NULL(vport->egress.acl)) { + if (IS_ERR(vport->egress.acl)) { err = PTR_ERR(vport->egress.acl); vport->egress.acl = NULL; return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c index 22f4c1c28006..4a369669e51e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c @@ -8,6 +8,7 @@ struct mlx5_flow_table * esw_acl_table_create(struct mlx5_eswitch *esw, u16 vport_num, int ns, int size) { + struct mlx5_flow_table_attr ft_attr = {}; struct mlx5_core_dev *dev = esw->dev; struct mlx5_flow_namespace *root_ns; struct mlx5_flow_table *acl; @@ -33,7 +34,9 @@ esw_acl_table_create(struct mlx5_eswitch *esw, u16 vport_num, int ns, int size) return ERR_PTR(-EOPNOTSUPP); } - acl = mlx5_create_vport_flow_table(root_ns, 0, size, 0, vport_num); + ft_attr.max_fte = size; + ft_attr.flags = MLX5_FLOW_TABLE_OTHER_VPORT; + acl = mlx5_create_vport_flow_table(root_ns, &ft_attr, vport_num); if (IS_ERR(acl)) { err = PTR_ERR(acl); esw_warn(dev, "vport[%d] create %s ACL table, err(%d)\n", vport_num, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c index b68976b378b8..d64fad2823e7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c @@ -180,7 +180,7 @@ int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw, vport->ingress.acl = esw_acl_table_create(esw, vport->vport, MLX5_FLOW_NAMESPACE_ESW_INGRESS, table_size); - if (IS_ERR_OR_NULL(vport->ingress.acl)) { + if (IS_ERR(vport->ingress.acl)) { err = PTR_ERR(vport->ingress.acl); vport->ingress.acl = NULL; return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c index 4e55d7225a26..548c005ea633 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c @@ -258,7 +258,7 @@ int esw_acl_ingress_ofld_setup(struct mlx5_eswitch *esw, vport->ingress.acl = esw_acl_table_create(esw, vport->vport, MLX5_FLOW_NAMESPACE_ESW_INGRESS, num_ftes); - if (IS_ERR_OR_NULL(vport->ingress.acl)) { + if (IS_ERR(vport->ingress.acl)) { err = PTR_ERR(vport->ingress.acl); vport->ingress.acl = NULL; return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index d4ee0a9c03db..da901e364656 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1474,6 +1474,26 @@ vf_err: return err; } +static int host_pf_enable_hca(struct mlx5_core_dev *dev) +{ + if (!mlx5_core_is_ecpf(dev)) + return 0; + + /* Once vport and representor are ready, take out the external host PF + * out of initializing state. Enabling HCA clears the iser->initializing + * bit and host PF driver loading can progress. + */ + return mlx5_cmd_host_pf_enable_hca(dev); +} + +static void host_pf_disable_hca(struct mlx5_core_dev *dev) +{ + if (!mlx5_core_is_ecpf(dev)) + return; + + mlx5_cmd_host_pf_disable_hca(dev); +} + /* mlx5_eswitch_enable_pf_vf_vports() enables vports of PF, ECPF and VFs * whichever are present on the eswitch. */ @@ -1488,6 +1508,11 @@ mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw, if (ret) return ret; + /* Enable external host PF HCA */ + ret = host_pf_enable_hca(esw->dev); + if (ret) + goto pf_hca_err; + /* Enable ECPF vport */ if (mlx5_ecpf_vport_exists(esw->dev)) { ret = mlx5_eswitch_load_vport(esw, MLX5_VPORT_ECPF, enabled_events); @@ -1505,8 +1530,9 @@ mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw, vf_err: if (mlx5_ecpf_vport_exists(esw->dev)) mlx5_eswitch_unload_vport(esw, MLX5_VPORT_ECPF); - ecpf_err: + host_pf_disable_hca(esw->dev); +pf_hca_err: mlx5_eswitch_unload_vport(esw, MLX5_VPORT_PF); return ret; } @@ -1521,6 +1547,7 @@ void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw) if (mlx5_ecpf_vport_exists(esw->dev)) mlx5_eswitch_unload_vport(esw, MLX5_VPORT_ECPF); + host_pf_disable_hca(esw->dev); mlx5_eswitch_unload_vport(esw, MLX5_VPORT_PF); } @@ -1614,8 +1641,7 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int mode, int num_vfs) if (mode == MLX5_ESWITCH_LEGACY) { err = esw_legacy_enable(esw); } else { - mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH); - mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); + mlx5_rescan_drivers(esw->dev); err = esw_offloads_enable(esw); } @@ -1633,10 +1659,9 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int mode, int num_vfs) abort: esw->mode = MLX5_ESWITCH_NONE; - if (mode == MLX5_ESWITCH_OFFLOADS) { - mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); - mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH); - } + if (mode == MLX5_ESWITCH_OFFLOADS) + mlx5_rescan_drivers(esw->dev); + esw_destroy_tsar(esw); return err; } @@ -1697,10 +1722,9 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw, bool clear_vf) mlx5_lag_update(esw->dev); - if (old_mode == MLX5_ESWITCH_OFFLOADS) { - mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); - mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH); - } + if (old_mode == MLX5_ESWITCH_OFFLOADS) + mlx5_rescan_drivers(esw->dev); + esw_destroy_tsar(esw); if (clear_vf) @@ -2439,8 +2463,10 @@ free_out: return err; } -u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw) +u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev) { + struct mlx5_eswitch *esw = dev->priv.eswitch; + return ESW_ALLOWED(esw) ? esw->mode : MLX5_ESWITCH_NONE; } EXPORT_SYMBOL_GPL(mlx5_eswitch_mode); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index c9c2962ad49f..2f6a0ae20650 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -484,7 +484,7 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw, } } dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; - dest[i].ft = fwd_fdb, + dest[i].ft = fwd_fdb; i++; mlx5_eswitch_set_rule_source_port(esw, spec, esw_attr); @@ -1680,7 +1680,6 @@ static int esw_create_restore_table(struct mlx5_eswitch *esw) goto out_free; } - memset(flow_group_in, 0, inlen); match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria); misc = MLX5_ADDR_OF(fte_match_param, match_criteria, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.h index 656f96be6e20..89ef592656c8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.h @@ -47,11 +47,12 @@ /** * enum mlx5_fpga_access_type - Enumerated the different methods possible for * accessing the device memory address space + * + * @MLX5_FPGA_ACCESS_TYPE_I2C: Use the slow CX-FPGA I2C bus + * @MLX5_FPGA_ACCESS_TYPE_DONTCARE: Use the fastest available method */ enum mlx5_fpga_access_type { - /** Use the slow CX-FPGA I2C bus */ MLX5_FPGA_ACCESS_TYPE_I2C = 0x0, - /** Use the fastest available method */ MLX5_FPGA_ACCESS_TYPE_DONTCARE = 0x0, }; @@ -113,6 +114,7 @@ struct mlx5_fpga_conn_attr { * subsequent receives. */ void (*recv_cb)(void *cb_arg, struct mlx5_fpga_dma_buf *buf); + /** @cb_arg: A context to be passed to recv_cb callback */ void *cb_arg; }; @@ -145,7 +147,7 @@ void mlx5_fpga_sbu_conn_destroy(struct mlx5_fpga_conn *conn); /** * mlx5_fpga_sbu_conn_sendmsg() - Queue the transmission of a packet - * @fdev: An FPGA SBU connection + * @conn: An FPGA SBU connection * @buf: The packet buffer * * Queues a packet for transmission over an FPGA SBU connection. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index babe3405132a..8e06731d3cb3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -172,10 +172,9 @@ static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns, MLX5_SET(set_flow_table_root_in, in, table_id, ft->id); MLX5_SET(set_flow_table_root_in, in, underlay_qpn, underlay_qpn); - if (ft->vport) { - MLX5_SET(set_flow_table_root_in, in, vport_number, ft->vport); - MLX5_SET(set_flow_table_root_in, in, other_vport, 1); - } + MLX5_SET(set_flow_table_root_in, in, vport_number, ft->vport); + MLX5_SET(set_flow_table_root_in, in, other_vport, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); return mlx5_cmd_exec_in(dev, set_flow_table_root, in); } @@ -199,10 +198,9 @@ static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns, MLX5_SET(create_flow_table_in, in, table_type, ft->type); MLX5_SET(create_flow_table_in, in, flow_table_context.level, ft->level); MLX5_SET(create_flow_table_in, in, flow_table_context.log_size, log_size); - if (ft->vport) { - MLX5_SET(create_flow_table_in, in, vport_number, ft->vport); - MLX5_SET(create_flow_table_in, in, other_vport, 1); - } + MLX5_SET(create_flow_table_in, in, vport_number, ft->vport); + MLX5_SET(create_flow_table_in, in, other_vport, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); MLX5_SET(create_flow_table_in, in, flow_table_context.decap_en, en_decap); @@ -252,10 +250,9 @@ static int mlx5_cmd_destroy_flow_table(struct mlx5_flow_root_namespace *ns, MLX5_CMD_OP_DESTROY_FLOW_TABLE); MLX5_SET(destroy_flow_table_in, in, table_type, ft->type); MLX5_SET(destroy_flow_table_in, in, table_id, ft->id); - if (ft->vport) { - MLX5_SET(destroy_flow_table_in, in, vport_number, ft->vport); - MLX5_SET(destroy_flow_table_in, in, other_vport, 1); - } + MLX5_SET(destroy_flow_table_in, in, vport_number, ft->vport); + MLX5_SET(destroy_flow_table_in, in, other_vport, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); return mlx5_cmd_exec_in(dev, destroy_flow_table, in); } @@ -283,11 +280,9 @@ static int mlx5_cmd_modify_flow_table(struct mlx5_flow_root_namespace *ns, flow_table_context.lag_master_next_table_id, 0); } } else { - if (ft->vport) { - MLX5_SET(modify_flow_table_in, in, vport_number, - ft->vport); - MLX5_SET(modify_flow_table_in, in, other_vport, 1); - } + MLX5_SET(modify_flow_table_in, in, vport_number, ft->vport); + MLX5_SET(modify_flow_table_in, in, other_vport, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); MLX5_SET(modify_flow_table_in, in, modify_field_select, MLX5_MODIFY_FLOW_TABLE_MISS_TABLE_ID); if (next_ft) { @@ -325,6 +320,9 @@ static int mlx5_cmd_create_flow_group(struct mlx5_flow_root_namespace *ns, MLX5_SET(create_flow_group_in, in, other_vport, 1); } + MLX5_SET(create_flow_group_in, in, vport_number, ft->vport); + MLX5_SET(create_flow_group_in, in, other_vport, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); err = mlx5_cmd_exec_inout(dev, create_flow_group, in, out); if (!err) fg->id = MLX5_GET(create_flow_group_out, out, @@ -344,11 +342,9 @@ static int mlx5_cmd_destroy_flow_group(struct mlx5_flow_root_namespace *ns, MLX5_SET(destroy_flow_group_in, in, table_type, ft->type); MLX5_SET(destroy_flow_group_in, in, table_id, ft->id); MLX5_SET(destroy_flow_group_in, in, group_id, fg->id); - if (ft->vport) { - MLX5_SET(destroy_flow_group_in, in, vport_number, ft->vport); - MLX5_SET(destroy_flow_group_in, in, other_vport, 1); - } - + MLX5_SET(destroy_flow_group_in, in, vport_number, ft->vport); + MLX5_SET(destroy_flow_group_in, in, other_vport, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); return mlx5_cmd_exec_in(dev, destroy_flow_group, in); } @@ -427,10 +423,9 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, MLX5_SET(set_fte_in, in, ignore_flow_level, !!(fte->action.flags & FLOW_ACT_IGNORE_FLOW_LEVEL)); - if (ft->vport) { - MLX5_SET(set_fte_in, in, vport_number, ft->vport); - MLX5_SET(set_fte_in, in, other_vport, 1); - } + MLX5_SET(set_fte_in, in, vport_number, ft->vport); + MLX5_SET(set_fte_in, in, other_vport, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); in_flow_context = MLX5_ADDR_OF(set_fte_in, in, flow_context); MLX5_SET(flow_context, in_flow_context, group_id, group_id); @@ -515,6 +510,9 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, dst->dest_attr.vport.pkt_reformat->id); } break; + case MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER: + id = dst->dest_attr.sampler_id; + break; default: id = dst->dest_attr.tir_num; } @@ -601,10 +599,9 @@ static int mlx5_cmd_delete_fte(struct mlx5_flow_root_namespace *ns, MLX5_SET(delete_fte_in, in, table_type, ft->type); MLX5_SET(delete_fte_in, in, table_id, ft->id); MLX5_SET(delete_fte_in, in, flow_index, fte->index); - if (ft->vport) { - MLX5_SET(delete_fte_in, in, vport_number, ft->vport); - MLX5_SET(delete_fte_in, in, other_vport, 1); - } + MLX5_SET(delete_fte_in, in, vport_number, ft->vport); + MLX5_SET(delete_fte_in, in, other_vport, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); return mlx5_cmd_exec_in(dev, delete_fte, in); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 9fdd99272e31..b899539a0786 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1152,18 +1152,13 @@ struct mlx5_flow_table *mlx5_create_flow_table(struct mlx5_flow_namespace *ns, { return __mlx5_create_flow_table(ns, ft_attr, FS_FT_OP_MOD_NORMAL, 0); } +EXPORT_SYMBOL(mlx5_create_flow_table); -struct mlx5_flow_table *mlx5_create_vport_flow_table(struct mlx5_flow_namespace *ns, - int prio, int max_fte, - u32 level, u16 vport) +struct mlx5_flow_table * +mlx5_create_vport_flow_table(struct mlx5_flow_namespace *ns, + struct mlx5_flow_table_attr *ft_attr, u16 vport) { - struct mlx5_flow_table_attr ft_attr = {}; - - ft_attr.max_fte = max_fte; - ft_attr.level = level; - ft_attr.prio = prio; - - return __mlx5_create_flow_table(ns, &ft_attr, FS_FT_OP_MOD_NORMAL, vport); + return __mlx5_create_flow_table(ns, ft_attr, FS_FT_OP_MOD_NORMAL, vport); } struct mlx5_flow_table* @@ -1243,6 +1238,7 @@ struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft, return fg; } +EXPORT_SYMBOL(mlx5_create_flow_group); static struct mlx5_flow_rule *alloc_rule(struct mlx5_flow_destination *dest) { @@ -2146,6 +2142,7 @@ void mlx5_destroy_flow_group(struct mlx5_flow_group *fg) mlx5_core_warn(get_dev(&fg->node), "Flow group %d wasn't destroyed, refcount > 1\n", fg->id); } +EXPORT_SYMBOL(mlx5_destroy_flow_group); struct mlx5_flow_namespace *mlx5_get_fdb_sub_ns(struct mlx5_core_dev *dev, int n) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index afe7f0bffb93..b24a9849c45e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -194,7 +194,7 @@ struct mlx5_ft_underlay_qp { u32 qpn; }; -#define MLX5_FTE_MATCH_PARAM_RESERVED reserved_at_a00 +#define MLX5_FTE_MATCH_PARAM_RESERVED reserved_at_c00 /* Calculate the fte_match_param length and without the reserved length. * Make sure the reserved field is the last. */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index cac8f085b16d..97d96fc38a65 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -39,7 +39,7 @@ static void mlx5i_get_drvinfo(struct net_device *dev, struct mlx5e_priv *priv = mlx5i_epriv(dev); mlx5e_ethtool_get_drvinfo(priv, drvinfo); - strlcpy(drvinfo->driver, DRIVER_NAME "[ib_ipoib]", + strlcpy(drvinfo->driver, KBUILD_MODNAME "[ib_ipoib]", sizeof(drvinfo->driver)); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index 33081b24f10a..f3d45ef082cd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -243,24 +243,30 @@ static bool mlx5_lag_check_prereq(struct mlx5_lag *ldev) #endif } -static void mlx5_lag_add_ib_devices(struct mlx5_lag *ldev) +static void mlx5_lag_add_devices(struct mlx5_lag *ldev) { int i; - for (i = 0; i < MLX5_MAX_PORTS; i++) - if (ldev->pf[i].dev) - mlx5_add_dev_by_protocol(ldev->pf[i].dev, - MLX5_INTERFACE_PROTOCOL_IB); + for (i = 0; i < MLX5_MAX_PORTS; i++) { + if (!ldev->pf[i].dev) + continue; + + ldev->pf[i].dev->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; + mlx5_rescan_drivers_locked(ldev->pf[i].dev); + } } -static void mlx5_lag_remove_ib_devices(struct mlx5_lag *ldev) +static void mlx5_lag_remove_devices(struct mlx5_lag *ldev) { int i; - for (i = 0; i < MLX5_MAX_PORTS; i++) - if (ldev->pf[i].dev) - mlx5_remove_dev_by_protocol(ldev->pf[i].dev, - MLX5_INTERFACE_PROTOCOL_IB); + for (i = 0; i < MLX5_MAX_PORTS; i++) { + if (!ldev->pf[i].dev) + continue; + + ldev->pf[i].dev->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; + mlx5_rescan_drivers_locked(ldev->pf[i].dev); + } } static void mlx5_do_bond(struct mlx5_lag *ldev) @@ -290,20 +296,21 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) #endif if (roce_lag) - mlx5_lag_remove_ib_devices(ldev); + mlx5_lag_remove_devices(ldev); err = mlx5_activate_lag(ldev, &tracker, roce_lag ? MLX5_LAG_FLAG_ROCE : MLX5_LAG_FLAG_SRIOV); if (err) { if (roce_lag) - mlx5_lag_add_ib_devices(ldev); + mlx5_lag_add_devices(ldev); return; } if (roce_lag) { - mlx5_add_dev_by_protocol(dev0, MLX5_INTERFACE_PROTOCOL_IB); + dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; + mlx5_rescan_drivers_locked(dev0); mlx5_nic_vport_enable_roce(dev1); } } else if (do_bond && __mlx5_lag_is_active(ldev)) { @@ -312,7 +319,8 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) roce_lag = __mlx5_lag_is_roce(ldev); if (roce_lag) { - mlx5_remove_dev_by_protocol(dev0, MLX5_INTERFACE_PROTOCOL_IB); + dev0->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; + mlx5_rescan_drivers_locked(dev0); mlx5_nic_vport_disable_roce(dev1); } @@ -321,7 +329,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) return; if (roce_lag) - mlx5_lag_add_ib_devices(ldev); + mlx5_lag_add_devices(ldev); } } @@ -596,6 +604,8 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev) if (err) mlx5_core_err(dev, "Failed to init multipath lag err=%d\n", err); + + return; } /* Must be called with intf_mutex held */ @@ -739,24 +749,6 @@ unlock: } EXPORT_SYMBOL(mlx5_lag_get_slave_port); -bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv) -{ - struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, - priv); - struct mlx5_lag *ldev; - - if (intf->protocol != MLX5_INTERFACE_PROTOCOL_IB) - return true; - - ldev = mlx5_lag_dev_get(dev); - if (!ldev || !__mlx5_lag_is_roce(ldev) || - ldev->pf[MLX5_LAG_P1].dev == dev) - return true; - - /* If bonded, we do not add an IB device for PF1. */ - return false; -} - int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, u64 *values, int num_counters, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 8ff207aa1479..c08315b51fd3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -50,6 +50,7 @@ #ifdef CONFIG_RFS_ACCEL #include <linux/cpu_rmap.h> #endif +#include <linux/version.h> #include <net/devlink.h> #include "mlx5_core.h" #include "lib/eq.h" @@ -76,7 +77,6 @@ MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>"); MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver"); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_VERSION(DRIVER_VERSION); unsigned int mlx5_core_debug_mask; module_param_named(debug_mask, mlx5_core_debug_mask, uint, 0644); @@ -227,13 +227,16 @@ static void mlx5_set_driver_version(struct mlx5_core_dev *dev) strncat(string, ",", remaining_size); remaining_size = max_t(int, 0, driver_ver_sz - strlen(string)); - strncat(string, DRIVER_NAME, remaining_size); + 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)); - strncat(string, DRIVER_VERSION, remaining_size); + + snprintf(string + strlen(string), remaining_size, "%u.%u.%u", + (u8)((LINUX_VERSION_CODE >> 16) & 0xff), (u8)((LINUX_VERSION_CODE >> 8) & 0xff), + (u16)(LINUX_VERSION_CODE & 0xffff)); /*Send the command*/ MLX5_SET(set_driver_version_in, in, opcode, @@ -309,7 +312,7 @@ static int request_bar(struct pci_dev *pdev) return -ENODEV; } - err = pci_request_regions(pdev, DRIVER_NAME); + err = pci_request_regions(pdev, KBUILD_MODNAME); if (err) dev_err(&pdev->dev, "Couldn't get PCI resources, aborting\n"); @@ -1126,23 +1129,23 @@ static int mlx5_load(struct mlx5_core_dev *dev) goto err_sriov; } - err = mlx5_sriov_attach(dev); - if (err) { - mlx5_core_err(dev, "sriov init failed %d\n", err); - goto err_sriov; - } - err = mlx5_ec_init(dev); if (err) { mlx5_core_err(dev, "Failed to init embedded CPU\n"); goto err_ec; } + err = mlx5_sriov_attach(dev); + if (err) { + mlx5_core_err(dev, "sriov init failed %d\n", err); + goto err_sriov; + } + return 0; -err_ec: - mlx5_sriov_detach(dev); err_sriov: + mlx5_ec_cleanup(dev); +err_ec: mlx5_cleanup_fs(dev); err_fs: mlx5_accel_tls_cleanup(dev); @@ -1168,8 +1171,8 @@ err_irq_table: static void mlx5_unload(struct mlx5_core_dev *dev) { - mlx5_ec_cleanup(dev); mlx5_sriov_detach(dev); + mlx5_ec_cleanup(dev); mlx5_cleanup_fs(dev); mlx5_accel_ipsec_cleanup(dev); mlx5_accel_tls_cleanup(dev); @@ -1219,14 +1222,21 @@ int mlx5_load_one(struct mlx5_core_dev *dev, bool boot) err = mlx5_devlink_register(priv_to_devlink(dev), dev->device); if (err) goto err_devlink_reg; - mlx5_register_device(dev); + + err = mlx5_register_device(dev); } else { - mlx5_attach_device(dev); + err = mlx5_attach_device(dev); } + if (err) + goto err_register; + mutex_unlock(&dev->intf_state_mutex); return 0; +err_register: + if (boot) + mlx5_devlink_unregister(priv_to_devlink(dev)); err_devlink_reg: clear_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state); mlx5_unload(dev); @@ -1303,8 +1313,14 @@ static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) if (err) goto err_pagealloc_init; + err = mlx5_adev_init(dev); + if (err) + goto err_adev_init; + return 0; +err_adev_init: + mlx5_pagealloc_cleanup(dev); err_pagealloc_init: mlx5_health_cleanup(dev); err_health_init: @@ -1321,6 +1337,7 @@ static void mlx5_mdev_uninit(struct mlx5_core_dev *dev) { struct mlx5_priv *priv = &dev->priv; + mlx5_adev_cleanup(dev); mlx5_pagealloc_cleanup(dev); mlx5_health_cleanup(dev); debugfs_remove_recursive(dev->priv.dbg_root); @@ -1331,7 +1348,6 @@ static void mlx5_mdev_uninit(struct mlx5_core_dev *dev) mutex_destroy(&dev->intf_state_mutex); } -#define MLX5_IB_MOD "mlx5_ib" static int init_one(struct pci_dev *pdev, const struct pci_device_id *id) { struct mlx5_core_dev *dev; @@ -1351,6 +1367,10 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id) dev->coredev_type = id->driver_data & MLX5_PCI_DEV_IS_VF ? MLX5_COREDEV_VF : MLX5_COREDEV_PF; + dev->priv.adev_idx = mlx5_adev_idx_alloc(); + if (dev->priv.adev_idx < 0) + return dev->priv.adev_idx; + err = mlx5_mdev_init(dev, prof_sel); if (err) goto mdev_init_err; @@ -1369,8 +1389,6 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id) goto err_load_one; } - request_module_nowait(MLX5_IB_MOD); - err = mlx5_crdump_enable(dev); if (err) dev_err(&pdev->dev, "mlx5_crdump_enable failed with error code %d\n", err); @@ -1384,6 +1402,7 @@ err_load_one: pci_init_err: mlx5_mdev_uninit(dev); mdev_init_err: + mlx5_adev_idx_free(dev->priv.adev_idx); mlx5_devlink_free(devlink); return err; @@ -1400,6 +1419,7 @@ static void remove_one(struct pci_dev *pdev) mlx5_unload_one(dev, true); mlx5_pci_close(dev); mlx5_mdev_uninit(dev); + mlx5_adev_idx_free(dev->priv.adev_idx); mlx5_devlink_free(devlink); } @@ -1594,6 +1614,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = { { PCI_VDEVICE(MELLANOX, 0xa2d2) }, /* BlueField integrated ConnectX-5 network controller */ { PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF}, /* BlueField integrated ConnectX-5 network controller VF */ { PCI_VDEVICE(MELLANOX, 0xa2d6) }, /* BlueField-2 integrated ConnectX-6 Dx network controller */ + { PCI_VDEVICE(MELLANOX, 0xa2dc) }, /* BlueField-3 integrated ConnectX-7 network controller */ { 0, } }; @@ -1613,7 +1634,7 @@ void mlx5_recover_device(struct mlx5_core_dev *dev) } static struct pci_driver mlx5_core_driver = { - .name = DRIVER_NAME, + .name = KBUILD_MODNAME, .id_table = mlx5_core_pci_table, .probe = init_one, .remove = remove_one, @@ -1639,6 +1660,9 @@ static int __init init(void) { int err; + WARN_ONCE(strcmp(MLX5_ADEV_NAME, KBUILD_MODNAME), + "mlx5_core name not in sync with kernel module name"); + get_random_bytes(&sw_owner_id, sizeof(sw_owner_id)); mlx5_core_verify_params(); @@ -1650,7 +1674,11 @@ static int __init init(void) goto err_debug; #ifdef CONFIG_MLX5_CORE_EN - mlx5e_init(); + err = mlx5e_init(); + if (err) { + pci_unregister_driver(&mlx5_core_driver); + goto err_debug; + } #endif return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 8cec85ab419d..0a0302ce7144 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -42,9 +42,6 @@ #include <linux/mlx5/fs.h> #include <linux/mlx5/driver.h> -#define DRIVER_NAME "mlx5_core" -#define DRIVER_VERSION "5.0-0" - extern uint mlx5_core_debug_mask; #define mlx5_core_dbg(__dev, format, ...) \ @@ -122,6 +119,10 @@ enum mlx5_semaphore_space_address { int mlx5_query_hca_caps(struct mlx5_core_dev *dev); int mlx5_query_board_id(struct mlx5_core_dev *dev); +int mlx5_cmd_init(struct mlx5_core_dev *dev); +void mlx5_cmd_cleanup(struct mlx5_core_dev *dev); +void mlx5_cmd_set_state(struct mlx5_core_dev *dev, + enum mlx5_cmdif_state cmdif_state); int mlx5_cmd_init_hca(struct mlx5_core_dev *dev, uint32_t *sw_owner_id); int mlx5_cmd_teardown_hca(struct mlx5_core_dev *dev); int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev); @@ -181,22 +182,20 @@ void mlx5_events_cleanup(struct mlx5_core_dev *dev); void mlx5_events_start(struct mlx5_core_dev *dev); void mlx5_events_stop(struct mlx5_core_dev *dev); -void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv); -void mlx5_remove_device(struct mlx5_interface *intf, struct mlx5_priv *priv); -void mlx5_attach_device(struct mlx5_core_dev *dev); +int mlx5_adev_idx_alloc(void); +void mlx5_adev_idx_free(int idx); +void mlx5_adev_cleanup(struct mlx5_core_dev *dev); +int mlx5_adev_init(struct mlx5_core_dev *dev); + +int mlx5_attach_device(struct mlx5_core_dev *dev); void mlx5_detach_device(struct mlx5_core_dev *dev); -bool mlx5_device_registered(struct mlx5_core_dev *dev); -void mlx5_register_device(struct mlx5_core_dev *dev); +int mlx5_register_device(struct mlx5_core_dev *dev); void mlx5_unregister_device(struct mlx5_core_dev *dev); -void mlx5_add_dev_by_protocol(struct mlx5_core_dev *dev, int protocol); -void mlx5_remove_dev_by_protocol(struct mlx5_core_dev *dev, int protocol); struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev); void mlx5_dev_list_lock(void); void mlx5_dev_list_unlock(void); int mlx5_dev_list_trylock(void); -bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv); - int mlx5_query_mtpps(struct mlx5_core_dev *dev, u32 *mtpps, u32 mtpps_size); int mlx5_set_mtpps(struct mlx5_core_dev *mdev, u32 *mtpps, u32 mtpps_size); int mlx5_query_mtppse(struct mlx5_core_dev *mdev, u8 pin, u8 *arm, u8 *mode); @@ -215,7 +214,7 @@ int mlx5_firmware_flash(struct mlx5_core_dev *dev, const struct firmware *fw, int mlx5_fw_version_query(struct mlx5_core_dev *dev, u32 *running_ver, u32 *stored_ver); -void mlx5e_init(void); +int mlx5e_init(void); void mlx5e_cleanup(void); static inline bool mlx5_sriov_is_enabled(struct mlx5_core_dev *dev) @@ -235,7 +234,17 @@ static inline int mlx5_lag_is_lacp_owner(struct mlx5_core_dev *dev) MLX5_CAP_GEN(dev, lag_master); } -void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol); +int mlx5_rescan_drivers_locked(struct mlx5_core_dev *dev); +static inline int mlx5_rescan_drivers(struct mlx5_core_dev *dev) +{ + int ret; + + mlx5_dev_list_lock(); + ret = mlx5_rescan_drivers_locked(dev); + mlx5_dev_list_unlock(); + return ret; +} + void mlx5_lag_update(struct mlx5_core_dev *dev); enum { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index 4d7f8a357df7..eb956ce904bc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -374,7 +374,7 @@ retry: if (func_id) dev->priv.vfs_pages += npages; else if (mlx5_core_is_ecpf(dev) && !ec_function) - dev->priv.peer_pf_pages += npages; + dev->priv.host_pf_pages += npages; mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x, err %d\n", npages, ec_function, func_id, err); @@ -416,7 +416,7 @@ static void release_all_pages(struct mlx5_core_dev *dev, u32 func_id, if (func_id) dev->priv.vfs_pages -= npages; else if (mlx5_core_is_ecpf(dev) && !ec_function) - dev->priv.peer_pf_pages -= npages; + dev->priv.host_pf_pages -= npages; mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x\n", npages, ec_function, func_id); @@ -523,7 +523,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages, if (func_id) dev->priv.vfs_pages -= num_claimed; else if (mlx5_core_is_ecpf(dev) && !ec_function) - dev->priv.peer_pf_pages -= num_claimed; + dev->priv.host_pf_pages -= num_claimed; out_free: kvfree(out); @@ -678,9 +678,9 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev) WARN(dev->priv.vfs_pages, "VFs FW pages counter is %d after reclaiming all pages\n", dev->priv.vfs_pages); - WARN(dev->priv.peer_pf_pages, - "Peer PF FW pages counter is %d after reclaiming all pages\n", - dev->priv.peer_pf_pages); + WARN(dev->priv.host_pf_pages, + "External host PF FW pages counter is %d after reclaiming all pages\n", + dev->priv.host_pf_pages); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_buddy.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_buddy.c new file mode 100644 index 000000000000..7df11a019df9 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_buddy.c @@ -0,0 +1,170 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2004 Topspin Communications. All rights reserved. + * Copyright (c) 2005 - 2008 Mellanox Technologies. All rights reserved. + * Copyright (c) 2006 - 2007 Cisco Systems, Inc. All rights reserved. + * Copyright (c) 2020 NVIDIA CORPORATION. All rights reserved. + */ + +#include "dr_types.h" + +int mlx5dr_buddy_init(struct mlx5dr_icm_buddy_mem *buddy, + unsigned int max_order) +{ + int i; + + buddy->max_order = max_order; + + INIT_LIST_HEAD(&buddy->list_node); + INIT_LIST_HEAD(&buddy->used_list); + INIT_LIST_HEAD(&buddy->hot_list); + + buddy->bitmap = kcalloc(buddy->max_order + 1, + sizeof(*buddy->bitmap), + GFP_KERNEL); + buddy->num_free = kcalloc(buddy->max_order + 1, + sizeof(*buddy->num_free), + GFP_KERNEL); + + if (!buddy->bitmap || !buddy->num_free) + goto err_free_all; + + /* Allocating max_order bitmaps, one for each order */ + + for (i = 0; i <= buddy->max_order; ++i) { + unsigned int size = 1 << (buddy->max_order - i); + + buddy->bitmap[i] = bitmap_zalloc(size, GFP_KERNEL); + if (!buddy->bitmap[i]) + goto err_out_free_each_bit_per_order; + } + + /* In the beginning, we have only one order that is available for + * use (the biggest one), so mark the first bit in both bitmaps. + */ + + bitmap_set(buddy->bitmap[buddy->max_order], 0, 1); + + buddy->num_free[buddy->max_order] = 1; + + return 0; + +err_out_free_each_bit_per_order: + for (i = 0; i <= buddy->max_order; ++i) + bitmap_free(buddy->bitmap[i]); + +err_free_all: + kfree(buddy->num_free); + kfree(buddy->bitmap); + return -ENOMEM; +} + +void mlx5dr_buddy_cleanup(struct mlx5dr_icm_buddy_mem *buddy) +{ + int i; + + list_del(&buddy->list_node); + + for (i = 0; i <= buddy->max_order; ++i) + bitmap_free(buddy->bitmap[i]); + + kfree(buddy->num_free); + kfree(buddy->bitmap); +} + +static int dr_buddy_find_free_seg(struct mlx5dr_icm_buddy_mem *buddy, + unsigned int start_order, + unsigned int *segment, + unsigned int *order) +{ + unsigned int seg, order_iter, m; + + for (order_iter = start_order; + order_iter <= buddy->max_order; ++order_iter) { + if (!buddy->num_free[order_iter]) + continue; + + m = 1 << (buddy->max_order - order_iter); + seg = find_first_bit(buddy->bitmap[order_iter], m); + + if (WARN(seg >= m, + "ICM Buddy: failed finding free mem for order %d\n", + order_iter)) + return -ENOMEM; + + break; + } + + if (order_iter > buddy->max_order) + return -ENOMEM; + + *segment = seg; + *order = order_iter; + return 0; +} + +/** + * mlx5dr_buddy_alloc_mem() - Update second level bitmap. + * @buddy: Buddy to update. + * @order: Order of the buddy to update. + * @segment: Segment number. + * + * This function finds the first area of the ICM memory managed by this buddy. + * It uses the data structures of the buddy system in order to find the first + * area of free place, starting from the current order till the maximum order + * in the system. + * + * Return: 0 when segment is set, non-zero error status otherwise. + * + * The function returns the location (segment) in the whole buddy ICM memory + * area - the index of the memory segment that is available for use. + */ +int mlx5dr_buddy_alloc_mem(struct mlx5dr_icm_buddy_mem *buddy, + unsigned int order, + unsigned int *segment) +{ + unsigned int seg, order_iter; + int err; + + err = dr_buddy_find_free_seg(buddy, order, &seg, &order_iter); + if (err) + return err; + + bitmap_clear(buddy->bitmap[order_iter], seg, 1); + --buddy->num_free[order_iter]; + + /* If we found free memory in some order that is bigger than the + * required order, we need to split every order between the required + * order and the order that we found into two parts, and mark accordingly. + */ + while (order_iter > order) { + --order_iter; + seg <<= 1; + bitmap_set(buddy->bitmap[order_iter], seg ^ 1, 1); + ++buddy->num_free[order_iter]; + } + + seg <<= order; + *segment = seg; + + return 0; +} + +void mlx5dr_buddy_free_mem(struct mlx5dr_icm_buddy_mem *buddy, + unsigned int seg, unsigned int order) +{ + seg >>= order; + + /* Whenever a segment is free, + * the mem is added to the buddy that gave it. + */ + while (test_bit(seg ^ 1, buddy->bitmap[order])) { + bitmap_clear(buddy->bitmap[order], seg ^ 1, 1); + --buddy->num_free[order]; + seg >>= 1; + ++order; + } + bitmap_set(buddy->bitmap[order], seg, 1); + + ++buddy->num_free[order]; +} + diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c index 51bbd88ff021..ba65ec406cfa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c @@ -94,12 +94,12 @@ int mlx5dr_cmd_query_device(struct mlx5_core_dev *mdev, caps->flex_protocols = MLX5_CAP_GEN(mdev, flex_parser_protocols); caps->sw_format_ver = MLX5_CAP_GEN(mdev, steering_format_version); - if (mlx5dr_matcher_supp_flex_parser_icmp_v4(caps)) { + if (caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V4_ENABLED) { caps->flex_parser_id_icmp_dw0 = MLX5_CAP_GEN(mdev, flex_parser_id_icmp_dw0); caps->flex_parser_id_icmp_dw1 = MLX5_CAP_GEN(mdev, flex_parser_id_icmp_dw1); } - if (mlx5dr_matcher_supp_flex_parser_icmp_v6(caps)) { + if (caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V6_ENABLED) { caps->flex_parser_id_icmpv6_dw0 = MLX5_CAP_GEN(mdev, flex_parser_id_icmpv6_dw0); caps->flex_parser_id_icmpv6_dw1 = diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c index cc33515b9aba..66c24767e3b0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c @@ -4,50 +4,16 @@ #include "dr_types.h" #define DR_ICM_MODIFY_HDR_ALIGN_BASE 64 -#define DR_ICM_SYNC_THRESHOLD (64 * 1024 * 1024) - -struct mlx5dr_icm_pool; - -struct mlx5dr_icm_bucket { - struct mlx5dr_icm_pool *pool; - - /* Chunks that aren't visible to HW not directly and not in cache */ - struct list_head free_list; - unsigned int free_list_count; - - /* Used chunks, HW may be accessing this memory */ - struct list_head used_list; - unsigned int used_list_count; - - /* HW may be accessing this memory but at some future, - * undetermined time, it might cease to do so. Before deciding to call - * sync_ste, this list is moved to sync_list - */ - struct list_head hot_list; - unsigned int hot_list_count; - - /* Pending sync list, entries from the hot list are moved to this list. - * sync_ste is executed and then sync_list is concatenated to the free list - */ - struct list_head sync_list; - unsigned int sync_list_count; - - u32 total_chunks; - u32 num_of_entries; - u32 entry_size; - /* protect the ICM bucket */ - struct mutex mutex; -}; +#define DR_ICM_SYNC_THRESHOLD_POOL (64 * 1024 * 1024) struct mlx5dr_icm_pool { - struct mlx5dr_icm_bucket *buckets; enum mlx5dr_icm_type icm_type; enum mlx5dr_icm_chunk_size max_log_chunk_sz; - enum mlx5dr_icm_chunk_size num_of_buckets; - struct list_head icm_mr_list; - /* protect the ICM MR list */ - struct mutex mr_mutex; struct mlx5dr_domain *dmn; + /* memory management */ + struct mutex mutex; /* protect the ICM pool and ICM buddy */ + struct list_head buddy_mem_list; + u64 hot_memory_size; }; struct mlx5dr_icm_dm { @@ -58,13 +24,11 @@ struct mlx5dr_icm_dm { }; struct mlx5dr_icm_mr { - struct mlx5dr_icm_pool *pool; struct mlx5_core_mkey mkey; struct mlx5dr_icm_dm dm; - size_t used_length; + struct mlx5dr_domain *dmn; size_t length; u64 icm_start_addr; - struct list_head mr_list; }; static int dr_icm_create_dm_mkey(struct mlx5_core_dev *mdev, @@ -107,8 +71,7 @@ dr_icm_pool_mr_create(struct mlx5dr_icm_pool *pool) if (!icm_mr) return NULL; - icm_mr->pool = pool; - INIT_LIST_HEAD(&icm_mr->mr_list); + icm_mr->dmn = pool->dmn; icm_mr->dm.length = mlx5dr_icm_pool_chunk_size_to_byte(pool->max_log_chunk_sz, pool->icm_type); @@ -150,8 +113,6 @@ dr_icm_pool_mr_create(struct mlx5dr_icm_pool *pool) goto free_mkey; } - list_add_tail(&icm_mr->mr_list, &pool->icm_mr_list); - return icm_mr; free_mkey: @@ -166,10 +127,9 @@ free_icm_mr: static void dr_icm_pool_mr_destroy(struct mlx5dr_icm_mr *icm_mr) { - struct mlx5_core_dev *mdev = icm_mr->pool->dmn->mdev; + struct mlx5_core_dev *mdev = icm_mr->dmn->mdev; struct mlx5dr_icm_dm *dm = &icm_mr->dm; - list_del(&icm_mr->mr_list); mlx5_core_destroy_mkey(mdev, &icm_mr->mkey); mlx5_dm_sw_icm_dealloc(mdev, dm->type, dm->length, 0, dm->addr, dm->obj_id); @@ -178,19 +138,17 @@ static void dr_icm_pool_mr_destroy(struct mlx5dr_icm_mr *icm_mr) static int dr_icm_chunk_ste_init(struct mlx5dr_icm_chunk *chunk) { - struct mlx5dr_icm_bucket *bucket = chunk->bucket; - - chunk->ste_arr = kvzalloc(bucket->num_of_entries * + chunk->ste_arr = kvzalloc(chunk->num_of_entries * sizeof(chunk->ste_arr[0]), GFP_KERNEL); if (!chunk->ste_arr) return -ENOMEM; - chunk->hw_ste_arr = kvzalloc(bucket->num_of_entries * + chunk->hw_ste_arr = kvzalloc(chunk->num_of_entries * DR_STE_SIZE_REDUCED, GFP_KERNEL); if (!chunk->hw_ste_arr) goto out_free_ste_arr; - chunk->miss_list = kvmalloc(bucket->num_of_entries * + chunk->miss_list = kvmalloc(chunk->num_of_entries * sizeof(chunk->miss_list[0]), GFP_KERNEL); if (!chunk->miss_list) goto out_free_hw_ste_arr; @@ -204,72 +162,6 @@ out_free_ste_arr: return -ENOMEM; } -static int dr_icm_chunks_create(struct mlx5dr_icm_bucket *bucket) -{ - size_t mr_free_size, mr_req_size, mr_row_size; - struct mlx5dr_icm_pool *pool = bucket->pool; - struct mlx5dr_icm_mr *icm_mr = NULL; - struct mlx5dr_icm_chunk *chunk; - int i, err = 0; - - mr_req_size = bucket->num_of_entries * bucket->entry_size; - mr_row_size = mlx5dr_icm_pool_chunk_size_to_byte(pool->max_log_chunk_sz, - pool->icm_type); - mutex_lock(&pool->mr_mutex); - if (!list_empty(&pool->icm_mr_list)) { - icm_mr = list_last_entry(&pool->icm_mr_list, - struct mlx5dr_icm_mr, mr_list); - - if (icm_mr) - mr_free_size = icm_mr->dm.length - icm_mr->used_length; - } - - if (!icm_mr || mr_free_size < mr_row_size) { - icm_mr = dr_icm_pool_mr_create(pool); - if (!icm_mr) { - err = -ENOMEM; - goto out_err; - } - } - - /* Create memory aligned chunks */ - for (i = 0; i < mr_row_size / mr_req_size; i++) { - chunk = kvzalloc(sizeof(*chunk), GFP_KERNEL); - if (!chunk) { - err = -ENOMEM; - goto out_err; - } - - chunk->bucket = bucket; - chunk->rkey = icm_mr->mkey.key; - /* mr start addr is zero based */ - chunk->mr_addr = icm_mr->used_length; - chunk->icm_addr = (uintptr_t)icm_mr->icm_start_addr + icm_mr->used_length; - icm_mr->used_length += mr_req_size; - chunk->num_of_entries = bucket->num_of_entries; - chunk->byte_size = chunk->num_of_entries * bucket->entry_size; - - if (pool->icm_type == DR_ICM_TYPE_STE) { - err = dr_icm_chunk_ste_init(chunk); - if (err) - goto out_free_chunk; - } - - INIT_LIST_HEAD(&chunk->chunk_list); - list_add(&chunk->chunk_list, &bucket->free_list); - bucket->free_list_count++; - bucket->total_chunks++; - } - mutex_unlock(&pool->mr_mutex); - return 0; - -out_free_chunk: - kvfree(chunk); -out_err: - mutex_unlock(&pool->mr_mutex); - return err; -} - static void dr_icm_chunk_ste_cleanup(struct mlx5dr_icm_chunk *chunk) { kvfree(chunk->miss_list); @@ -277,166 +169,199 @@ static void dr_icm_chunk_ste_cleanup(struct mlx5dr_icm_chunk *chunk) kvfree(chunk->ste_arr); } -static void dr_icm_chunk_destroy(struct mlx5dr_icm_chunk *chunk) +static enum mlx5dr_icm_type +get_chunk_icm_type(struct mlx5dr_icm_chunk *chunk) +{ + return chunk->buddy_mem->pool->icm_type; +} + +static void dr_icm_chunk_destroy(struct mlx5dr_icm_chunk *chunk, + struct mlx5dr_icm_buddy_mem *buddy) { - struct mlx5dr_icm_bucket *bucket = chunk->bucket; + enum mlx5dr_icm_type icm_type = get_chunk_icm_type(chunk); + buddy->used_memory -= chunk->byte_size; list_del(&chunk->chunk_list); - bucket->total_chunks--; - if (bucket->pool->icm_type == DR_ICM_TYPE_STE) + if (icm_type == DR_ICM_TYPE_STE) dr_icm_chunk_ste_cleanup(chunk); kvfree(chunk); } -static void dr_icm_bucket_init(struct mlx5dr_icm_pool *pool, - struct mlx5dr_icm_bucket *bucket, - enum mlx5dr_icm_chunk_size chunk_size) +static int dr_icm_buddy_create(struct mlx5dr_icm_pool *pool) { - if (pool->icm_type == DR_ICM_TYPE_STE) - bucket->entry_size = DR_STE_SIZE; - else - bucket->entry_size = DR_MODIFY_ACTION_SIZE; - - bucket->num_of_entries = mlx5dr_icm_pool_chunk_size_to_entries(chunk_size); - bucket->pool = pool; - mutex_init(&bucket->mutex); - INIT_LIST_HEAD(&bucket->free_list); - INIT_LIST_HEAD(&bucket->used_list); - INIT_LIST_HEAD(&bucket->hot_list); - INIT_LIST_HEAD(&bucket->sync_list); + struct mlx5dr_icm_buddy_mem *buddy; + struct mlx5dr_icm_mr *icm_mr; + + icm_mr = dr_icm_pool_mr_create(pool); + if (!icm_mr) + return -ENOMEM; + + buddy = kvzalloc(sizeof(*buddy), GFP_KERNEL); + if (!buddy) + goto free_mr; + + if (mlx5dr_buddy_init(buddy, pool->max_log_chunk_sz)) + goto err_free_buddy; + + buddy->icm_mr = icm_mr; + buddy->pool = pool; + + /* add it to the -start- of the list in order to search in it first */ + list_add(&buddy->list_node, &pool->buddy_mem_list); + + return 0; + +err_free_buddy: + kvfree(buddy); +free_mr: + dr_icm_pool_mr_destroy(icm_mr); + return -ENOMEM; } -static void dr_icm_bucket_cleanup(struct mlx5dr_icm_bucket *bucket) +static void dr_icm_buddy_destroy(struct mlx5dr_icm_buddy_mem *buddy) { struct mlx5dr_icm_chunk *chunk, *next; - mutex_destroy(&bucket->mutex); - list_splice_tail_init(&bucket->sync_list, &bucket->free_list); - list_splice_tail_init(&bucket->hot_list, &bucket->free_list); + list_for_each_entry_safe(chunk, next, &buddy->hot_list, chunk_list) + dr_icm_chunk_destroy(chunk, buddy); + + list_for_each_entry_safe(chunk, next, &buddy->used_list, chunk_list) + dr_icm_chunk_destroy(chunk, buddy); - list_for_each_entry_safe(chunk, next, &bucket->free_list, chunk_list) - dr_icm_chunk_destroy(chunk); + dr_icm_pool_mr_destroy(buddy->icm_mr); - WARN_ON(bucket->total_chunks != 0); + mlx5dr_buddy_cleanup(buddy); - /* Cleanup of unreturned chunks */ - list_for_each_entry_safe(chunk, next, &bucket->used_list, chunk_list) - dr_icm_chunk_destroy(chunk); + kvfree(buddy); } -static u64 dr_icm_hot_mem_size(struct mlx5dr_icm_pool *pool) +static struct mlx5dr_icm_chunk * +dr_icm_chunk_create(struct mlx5dr_icm_pool *pool, + enum mlx5dr_icm_chunk_size chunk_size, + struct mlx5dr_icm_buddy_mem *buddy_mem_pool, + unsigned int seg) { - u64 hot_size = 0; - int chunk_order; + struct mlx5dr_icm_chunk *chunk; + int offset; - for (chunk_order = 0; chunk_order < pool->num_of_buckets; chunk_order++) - hot_size += pool->buckets[chunk_order].hot_list_count * - mlx5dr_icm_pool_chunk_size_to_byte(chunk_order, pool->icm_type); + chunk = kvzalloc(sizeof(*chunk), GFP_KERNEL); + if (!chunk) + return NULL; - return hot_size; -} + offset = mlx5dr_icm_pool_dm_type_to_entry_size(pool->icm_type) * seg; + + chunk->rkey = buddy_mem_pool->icm_mr->mkey.key; + chunk->mr_addr = offset; + chunk->icm_addr = + (uintptr_t)buddy_mem_pool->icm_mr->icm_start_addr + offset; + chunk->num_of_entries = + mlx5dr_icm_pool_chunk_size_to_entries(chunk_size); + chunk->byte_size = + mlx5dr_icm_pool_chunk_size_to_byte(chunk_size, pool->icm_type); + chunk->seg = seg; + + if (pool->icm_type == DR_ICM_TYPE_STE && dr_icm_chunk_ste_init(chunk)) { + mlx5dr_err(pool->dmn, + "Failed to init ste arrays (order: %d)\n", + chunk_size); + goto out_free_chunk; + } -static bool dr_icm_reuse_hot_entries(struct mlx5dr_icm_pool *pool, - struct mlx5dr_icm_bucket *bucket) -{ - u64 bytes_for_sync; + buddy_mem_pool->used_memory += chunk->byte_size; + chunk->buddy_mem = buddy_mem_pool; + INIT_LIST_HEAD(&chunk->chunk_list); - bytes_for_sync = dr_icm_hot_mem_size(pool); - if (bytes_for_sync < DR_ICM_SYNC_THRESHOLD || !bucket->hot_list_count) - return false; + /* chunk now is part of the used_list */ + list_add_tail(&chunk->chunk_list, &buddy_mem_pool->used_list); - return true; -} + return chunk; -static void dr_icm_chill_bucket_start(struct mlx5dr_icm_bucket *bucket) -{ - list_splice_tail_init(&bucket->hot_list, &bucket->sync_list); - bucket->sync_list_count += bucket->hot_list_count; - bucket->hot_list_count = 0; +out_free_chunk: + kvfree(chunk); + return NULL; } -static void dr_icm_chill_bucket_end(struct mlx5dr_icm_bucket *bucket) +static bool dr_icm_pool_is_sync_required(struct mlx5dr_icm_pool *pool) { - list_splice_tail_init(&bucket->sync_list, &bucket->free_list); - bucket->free_list_count += bucket->sync_list_count; - bucket->sync_list_count = 0; -} + if (pool->hot_memory_size > DR_ICM_SYNC_THRESHOLD_POOL) + return true; -static void dr_icm_chill_bucket_abort(struct mlx5dr_icm_bucket *bucket) -{ - list_splice_tail_init(&bucket->sync_list, &bucket->hot_list); - bucket->hot_list_count += bucket->sync_list_count; - bucket->sync_list_count = 0; + return false; } -static void dr_icm_chill_buckets_start(struct mlx5dr_icm_pool *pool, - struct mlx5dr_icm_bucket *cb, - bool buckets[DR_CHUNK_SIZE_MAX]) +static int dr_icm_pool_sync_all_buddy_pools(struct mlx5dr_icm_pool *pool) { - struct mlx5dr_icm_bucket *bucket; - int i; - - for (i = 0; i < pool->num_of_buckets; i++) { - bucket = &pool->buckets[i]; - if (bucket == cb) { - dr_icm_chill_bucket_start(bucket); - continue; - } + struct mlx5dr_icm_buddy_mem *buddy, *tmp_buddy; + int err; - /* Freeing the mutex is done at the end of that process, after - * sync_ste was executed at dr_icm_chill_buckets_end func. - */ - if (mutex_trylock(&bucket->mutex)) { - dr_icm_chill_bucket_start(bucket); - buckets[i] = true; - } + err = mlx5dr_cmd_sync_steering(pool->dmn->mdev); + if (err) { + mlx5dr_err(pool->dmn, "Failed to sync to HW (err: %d)\n", err); + return err; } -} -static void dr_icm_chill_buckets_end(struct mlx5dr_icm_pool *pool, - struct mlx5dr_icm_bucket *cb, - bool buckets[DR_CHUNK_SIZE_MAX]) -{ - struct mlx5dr_icm_bucket *bucket; - int i; - - for (i = 0; i < pool->num_of_buckets; i++) { - bucket = &pool->buckets[i]; - if (bucket == cb) { - dr_icm_chill_bucket_end(bucket); - continue; - } + list_for_each_entry_safe(buddy, tmp_buddy, &pool->buddy_mem_list, list_node) { + struct mlx5dr_icm_chunk *chunk, *tmp_chunk; - if (!buckets[i]) - continue; + list_for_each_entry_safe(chunk, tmp_chunk, &buddy->hot_list, chunk_list) { + mlx5dr_buddy_free_mem(buddy, chunk->seg, + ilog2(chunk->num_of_entries)); + pool->hot_memory_size -= chunk->byte_size; + dr_icm_chunk_destroy(chunk, buddy); + } - dr_icm_chill_bucket_end(bucket); - mutex_unlock(&bucket->mutex); + if (!buddy->used_memory && pool->icm_type == DR_ICM_TYPE_STE) + dr_icm_buddy_destroy(buddy); } + + return 0; } -static void dr_icm_chill_buckets_abort(struct mlx5dr_icm_pool *pool, - struct mlx5dr_icm_bucket *cb, - bool buckets[DR_CHUNK_SIZE_MAX]) +static int dr_icm_handle_buddies_get_mem(struct mlx5dr_icm_pool *pool, + enum mlx5dr_icm_chunk_size chunk_size, + struct mlx5dr_icm_buddy_mem **buddy, + unsigned int *seg) { - struct mlx5dr_icm_bucket *bucket; - int i; - - for (i = 0; i < pool->num_of_buckets; i++) { - bucket = &pool->buckets[i]; - if (bucket == cb) { - dr_icm_chill_bucket_abort(bucket); - continue; - } + struct mlx5dr_icm_buddy_mem *buddy_mem_pool; + bool new_mem = false; + int err; - if (!buckets[i]) - continue; +alloc_buddy_mem: + /* find the next free place from the buddy list */ + list_for_each_entry(buddy_mem_pool, &pool->buddy_mem_list, list_node) { + err = mlx5dr_buddy_alloc_mem(buddy_mem_pool, + chunk_size, seg); + if (!err) + goto found; + + if (WARN_ON(new_mem)) { + /* We have new memory pool, first in the list */ + mlx5dr_err(pool->dmn, + "No memory for order: %d\n", + chunk_size); + goto out; + } + } - dr_icm_chill_bucket_abort(bucket); - mutex_unlock(&bucket->mutex); + /* no more available allocators in that pool, create new */ + err = dr_icm_buddy_create(pool); + if (err) { + mlx5dr_err(pool->dmn, + "Failed creating buddy for order %d\n", + chunk_size); + goto out; } + + /* mark we have new memory, first in list */ + new_mem = true; + goto alloc_buddy_mem; + +found: + *buddy = buddy_mem_pool; +out: + return err; } /* Allocate an ICM chunk, each chunk holds a piece of ICM memory and @@ -446,68 +371,48 @@ struct mlx5dr_icm_chunk * mlx5dr_icm_alloc_chunk(struct mlx5dr_icm_pool *pool, enum mlx5dr_icm_chunk_size chunk_size) { - struct mlx5dr_icm_chunk *chunk = NULL; /* Fix compilation warning */ - bool buckets[DR_CHUNK_SIZE_MAX] = {}; - struct mlx5dr_icm_bucket *bucket; - int err; + struct mlx5dr_icm_chunk *chunk = NULL; + struct mlx5dr_icm_buddy_mem *buddy; + unsigned int seg; + int ret; if (chunk_size > pool->max_log_chunk_sz) return NULL; - bucket = &pool->buckets[chunk_size]; - - mutex_lock(&bucket->mutex); - - /* Take chunk from pool if available, otherwise allocate new chunks */ - if (list_empty(&bucket->free_list)) { - if (dr_icm_reuse_hot_entries(pool, bucket)) { - dr_icm_chill_buckets_start(pool, bucket, buckets); - err = mlx5dr_cmd_sync_steering(pool->dmn->mdev); - if (err) { - dr_icm_chill_buckets_abort(pool, bucket, buckets); - mlx5dr_err(pool->dmn, "Sync_steering failed\n"); - chunk = NULL; - goto out; - } - dr_icm_chill_buckets_end(pool, bucket, buckets); - } else { - dr_icm_chunks_create(bucket); - } - } + mutex_lock(&pool->mutex); + /* find mem, get back the relevant buddy pool and seg in that mem */ + ret = dr_icm_handle_buddies_get_mem(pool, chunk_size, &buddy, &seg); + if (ret) + goto out; - if (!list_empty(&bucket->free_list)) { - chunk = list_last_entry(&bucket->free_list, - struct mlx5dr_icm_chunk, - chunk_list); - if (chunk) { - list_del_init(&chunk->chunk_list); - list_add_tail(&chunk->chunk_list, &bucket->used_list); - bucket->free_list_count--; - bucket->used_list_count++; - } - } + chunk = dr_icm_chunk_create(pool, chunk_size, buddy, seg); + if (!chunk) + goto out_err; + + goto out; + +out_err: + mlx5dr_buddy_free_mem(buddy, seg, chunk_size); out: - mutex_unlock(&bucket->mutex); + mutex_unlock(&pool->mutex); return chunk; } void mlx5dr_icm_free_chunk(struct mlx5dr_icm_chunk *chunk) { - struct mlx5dr_icm_bucket *bucket = chunk->bucket; + struct mlx5dr_icm_buddy_mem *buddy = chunk->buddy_mem; + struct mlx5dr_icm_pool *pool = buddy->pool; - if (bucket->pool->icm_type == DR_ICM_TYPE_STE) { - memset(chunk->ste_arr, 0, - bucket->num_of_entries * sizeof(chunk->ste_arr[0])); - memset(chunk->hw_ste_arr, 0, - bucket->num_of_entries * DR_STE_SIZE_REDUCED); - } + /* move the memory to the waiting list AKA "hot" */ + mutex_lock(&pool->mutex); + list_move_tail(&chunk->chunk_list, &buddy->hot_list); + pool->hot_memory_size += chunk->byte_size; + + /* Check if we have chunks that are waiting for sync-ste */ + if (dr_icm_pool_is_sync_required(pool)) + dr_icm_pool_sync_all_buddy_pools(pool); - mutex_lock(&bucket->mutex); - list_del_init(&chunk->chunk_list); - list_add_tail(&chunk->chunk_list, &bucket->hot_list); - bucket->hot_list_count++; - bucket->used_list_count--; - mutex_unlock(&bucket->mutex); + mutex_unlock(&pool->mutex); } struct mlx5dr_icm_pool *mlx5dr_icm_pool_create(struct mlx5dr_domain *dmn, @@ -515,7 +420,6 @@ struct mlx5dr_icm_pool *mlx5dr_icm_pool_create(struct mlx5dr_domain *dmn, { enum mlx5dr_icm_chunk_size max_log_chunk_sz; struct mlx5dr_icm_pool *pool; - int i; if (icm_type == DR_ICM_TYPE_STE) max_log_chunk_sz = dmn->info.max_log_sw_icm_sz; @@ -526,43 +430,24 @@ struct mlx5dr_icm_pool *mlx5dr_icm_pool_create(struct mlx5dr_domain *dmn, if (!pool) return NULL; - pool->buckets = kcalloc(max_log_chunk_sz + 1, - sizeof(pool->buckets[0]), - GFP_KERNEL); - if (!pool->buckets) - goto free_pool; - pool->dmn = dmn; pool->icm_type = icm_type; pool->max_log_chunk_sz = max_log_chunk_sz; - pool->num_of_buckets = max_log_chunk_sz + 1; - INIT_LIST_HEAD(&pool->icm_mr_list); - for (i = 0; i < pool->num_of_buckets; i++) - dr_icm_bucket_init(pool, &pool->buckets[i], i); + INIT_LIST_HEAD(&pool->buddy_mem_list); - mutex_init(&pool->mr_mutex); + mutex_init(&pool->mutex); return pool; - -free_pool: - kvfree(pool); - return NULL; } void mlx5dr_icm_pool_destroy(struct mlx5dr_icm_pool *pool) { - struct mlx5dr_icm_mr *icm_mr, *next; - int i; - - mutex_destroy(&pool->mr_mutex); - - list_for_each_entry_safe(icm_mr, next, &pool->icm_mr_list, mr_list) - dr_icm_pool_mr_destroy(icm_mr); + struct mlx5dr_icm_buddy_mem *buddy, *tmp_buddy; - for (i = 0; i < pool->num_of_buckets; i++) - dr_icm_bucket_cleanup(&pool->buckets[i]); + list_for_each_entry_safe(buddy, tmp_buddy, &pool->buddy_mem_list, list_node) + dr_icm_buddy_destroy(buddy); - kfree(pool->buckets); + mutex_destroy(&pool->mutex); kvfree(pool); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c index 7df883686d46..6527eb4df153 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c @@ -85,7 +85,7 @@ static bool dr_mask_is_ttl_set(struct mlx5dr_match_spec *spec) (_misc2)._inner_outer##_first_mpls_s_bos || \ (_misc2)._inner_outer##_first_mpls_ttl) -static bool dr_mask_is_gre_set(struct mlx5dr_match_misc *misc) +static bool dr_mask_is_tnl_gre_set(struct mlx5dr_match_misc *misc) { return (misc->gre_key_h || misc->gre_key_l || misc->gre_protocol || misc->gre_c_present || @@ -98,12 +98,12 @@ static bool dr_mask_is_gre_set(struct mlx5dr_match_misc *misc) (_misc2).outer_first_mpls_over_##gre_udp##_s_bos || \ (_misc2).outer_first_mpls_over_##gre_udp##_ttl) -#define DR_MASK_IS_FLEX_PARSER_0_SET(_misc2) ( \ +#define DR_MASK_IS_TNL_MPLS_SET(_misc2) ( \ DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET((_misc2), gre) || \ DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET((_misc2), udp)) static bool -dr_mask_is_misc3_vxlan_gpe_set(struct mlx5dr_match_misc3 *misc3) +dr_mask_is_vxlan_gpe_set(struct mlx5dr_match_misc3 *misc3) { return (misc3->outer_vxlan_gpe_vni || misc3->outer_vxlan_gpe_next_protocol || @@ -111,21 +111,20 @@ dr_mask_is_misc3_vxlan_gpe_set(struct mlx5dr_match_misc3 *misc3) } static bool -dr_matcher_supp_flex_parser_vxlan_gpe(struct mlx5dr_cmd_caps *caps) +dr_matcher_supp_vxlan_gpe(struct mlx5dr_cmd_caps *caps) { - return caps->flex_protocols & - MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED; + return caps->flex_protocols & MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED; } static bool -dr_mask_is_flex_parser_tnl_vxlan_gpe_set(struct mlx5dr_match_param *mask, - struct mlx5dr_domain *dmn) +dr_mask_is_tnl_vxlan_gpe(struct mlx5dr_match_param *mask, + struct mlx5dr_domain *dmn) { - return dr_mask_is_misc3_vxlan_gpe_set(&mask->misc3) && - dr_matcher_supp_flex_parser_vxlan_gpe(&dmn->info.caps); + return dr_mask_is_vxlan_gpe_set(&mask->misc3) && + dr_matcher_supp_vxlan_gpe(&dmn->info.caps); } -static bool dr_mask_is_misc_geneve_set(struct mlx5dr_match_misc *misc) +static bool dr_mask_is_tnl_geneve_set(struct mlx5dr_match_misc *misc) { return misc->geneve_vni || misc->geneve_oam || @@ -134,26 +133,46 @@ static bool dr_mask_is_misc_geneve_set(struct mlx5dr_match_misc *misc) } static bool -dr_matcher_supp_flex_parser_geneve(struct mlx5dr_cmd_caps *caps) +dr_matcher_supp_tnl_geneve(struct mlx5dr_cmd_caps *caps) { - return caps->flex_protocols & - MLX5_FLEX_PARSER_GENEVE_ENABLED; + return caps->flex_protocols & MLX5_FLEX_PARSER_GENEVE_ENABLED; } static bool -dr_mask_is_flex_parser_tnl_geneve_set(struct mlx5dr_match_param *mask, - struct mlx5dr_domain *dmn) +dr_mask_is_tnl_geneve(struct mlx5dr_match_param *mask, + struct mlx5dr_domain *dmn) { - return dr_mask_is_misc_geneve_set(&mask->misc) && - dr_matcher_supp_flex_parser_geneve(&dmn->info.caps); + return dr_mask_is_tnl_geneve_set(&mask->misc) && + dr_matcher_supp_tnl_geneve(&dmn->info.caps); } -static bool dr_mask_is_flex_parser_icmpv6_set(struct mlx5dr_match_misc3 *misc3) +static int dr_matcher_supp_icmp_v4(struct mlx5dr_cmd_caps *caps) +{ + return caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V4_ENABLED; +} + +static int dr_matcher_supp_icmp_v6(struct mlx5dr_cmd_caps *caps) +{ + return caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V6_ENABLED; +} + +static bool dr_mask_is_icmpv6_set(struct mlx5dr_match_misc3 *misc3) { return (misc3->icmpv6_type || misc3->icmpv6_code || misc3->icmpv6_header_data); } +static bool dr_mask_is_icmp(struct mlx5dr_match_param *mask, + struct mlx5dr_domain *dmn) +{ + if (DR_MASK_IS_ICMPV4_SET(&mask->misc3)) + return dr_matcher_supp_icmp_v4(&dmn->info.caps); + else if (dr_mask_is_icmpv6_set(&mask->misc3)) + return dr_matcher_supp_icmp_v6(&dmn->info.caps); + + return false; +} + static bool dr_mask_is_wqe_metadata_set(struct mlx5dr_match_misc2 *misc2) { return misc2->metadata_reg_a; @@ -257,7 +276,7 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, if (dr_mask_is_smac_set(&mask.outer) && dr_mask_is_dmac_set(&mask.outer)) { - mlx5dr_ste_build_eth_l2_src_des(&sb[idx++], &mask, + mlx5dr_ste_build_eth_l2_src_dst(&sb[idx++], &mask, inner, rx); } @@ -277,8 +296,8 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, inner, rx); if (DR_MASK_IS_ETH_L4_SET(mask.outer, mask.misc, outer)) - mlx5dr_ste_build_ipv6_l3_l4(&sb[idx++], &mask, - inner, rx); + mlx5dr_ste_build_eth_ipv6_l3_l4(&sb[idx++], &mask, + inner, rx); } else { if (dr_mask_is_ipv4_5_tuple_set(&mask.outer)) mlx5dr_ste_build_eth_l3_ipv4_5_tuple(&sb[idx++], &mask, @@ -289,14 +308,12 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, inner, rx); } - if (dr_mask_is_flex_parser_tnl_vxlan_gpe_set(&mask, dmn)) - mlx5dr_ste_build_flex_parser_tnl_vxlan_gpe(&sb[idx++], - &mask, - inner, rx); - else if (dr_mask_is_flex_parser_tnl_geneve_set(&mask, dmn)) - mlx5dr_ste_build_flex_parser_tnl_geneve(&sb[idx++], - &mask, - inner, rx); + if (dr_mask_is_tnl_vxlan_gpe(&mask, dmn)) + mlx5dr_ste_build_tnl_vxlan_gpe(&sb[idx++], &mask, + inner, rx); + else if (dr_mask_is_tnl_geneve(&mask, dmn)) + mlx5dr_ste_build_tnl_geneve(&sb[idx++], &mask, + inner, rx); if (DR_MASK_IS_ETH_L4_MISC_SET(mask.misc3, outer)) mlx5dr_ste_build_eth_l4_misc(&sb[idx++], &mask, inner, rx); @@ -304,22 +321,18 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, if (DR_MASK_IS_FIRST_MPLS_SET(mask.misc2, outer)) mlx5dr_ste_build_mpls(&sb[idx++], &mask, inner, rx); - if (DR_MASK_IS_FLEX_PARSER_0_SET(mask.misc2)) - mlx5dr_ste_build_flex_parser_0(&sb[idx++], &mask, - inner, rx); + if (DR_MASK_IS_TNL_MPLS_SET(mask.misc2)) + mlx5dr_ste_build_tnl_mpls(&sb[idx++], &mask, inner, rx); - if ((DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(&mask.misc3) && - mlx5dr_matcher_supp_flex_parser_icmp_v4(&dmn->info.caps)) || - (dr_mask_is_flex_parser_icmpv6_set(&mask.misc3) && - mlx5dr_matcher_supp_flex_parser_icmp_v6(&dmn->info.caps))) { - ret = mlx5dr_ste_build_flex_parser_1(&sb[idx++], - &mask, &dmn->info.caps, - inner, rx); + if (dr_mask_is_icmp(&mask, dmn)) { + ret = mlx5dr_ste_build_icmp(&sb[idx++], + &mask, &dmn->info.caps, + inner, rx); if (ret) return ret; } - if (dr_mask_is_gre_set(&mask.misc)) - mlx5dr_ste_build_gre(&sb[idx++], &mask, inner, rx); + if (dr_mask_is_tnl_gre_set(&mask.misc)) + mlx5dr_ste_build_tnl_gre(&sb[idx++], &mask, inner, rx); } /* Inner */ @@ -334,7 +347,7 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, if (dr_mask_is_smac_set(&mask.inner) && dr_mask_is_dmac_set(&mask.inner)) { - mlx5dr_ste_build_eth_l2_src_des(&sb[idx++], + mlx5dr_ste_build_eth_l2_src_dst(&sb[idx++], &mask, inner, rx); } @@ -354,8 +367,8 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, inner, rx); if (DR_MASK_IS_ETH_L4_SET(mask.inner, mask.misc, inner)) - mlx5dr_ste_build_ipv6_l3_l4(&sb[idx++], &mask, - inner, rx); + mlx5dr_ste_build_eth_ipv6_l3_l4(&sb[idx++], &mask, + inner, rx); } else { if (dr_mask_is_ipv4_5_tuple_set(&mask.inner)) mlx5dr_ste_build_eth_l3_ipv4_5_tuple(&sb[idx++], &mask, @@ -372,8 +385,8 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, if (DR_MASK_IS_FIRST_MPLS_SET(mask.misc2, inner)) mlx5dr_ste_build_mpls(&sb[idx++], &mask, inner, rx); - if (DR_MASK_IS_FLEX_PARSER_0_SET(mask.misc2)) - mlx5dr_ste_build_flex_parser_0(&sb[idx++], &mask, inner, rx); + if (DR_MASK_IS_TNL_MPLS_SET(mask.misc2)) + mlx5dr_ste_build_tnl_mpls(&sb[idx++], &mask, inner, rx); } /* Empty matcher, takes all */ if (matcher->match_criteria == DR_MATCHER_CRITERIA_EMPTY) @@ -630,7 +643,7 @@ static int dr_matcher_init(struct mlx5dr_matcher *matcher, } if (mask) { - if (mask->match_sz > sizeof(struct mlx5dr_match_param)) { + if (mask->match_sz > DR_SZ_MATCH_PARAM) { mlx5dr_err(dmn, "Invalid match size attribute\n"); return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index b3c9dc032026..6d73719db1f4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -874,8 +874,7 @@ static bool dr_rule_verify(struct mlx5dr_matcher *matcher, u32 s_idx, e_idx; if (!value_size || - (value_size > sizeof(struct mlx5dr_match_param) || - (value_size % sizeof(u32)))) { + (value_size > DR_SZ_MATCH_PARAM || (value_size % sizeof(u32)))) { mlx5dr_err(matcher->tbl->dmn, "Rule parameters length is incorrect\n"); return false; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index b01aaec75622..d275823bff2f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -1090,7 +1090,7 @@ static int dr_ste_build_eth_l2_src_des_tag(struct mlx5dr_match_param *value, return 0; } -void mlx5dr_ste_build_eth_l2_src_des(struct mlx5dr_ste_build *sb, +void mlx5dr_ste_build_eth_l2_src_dst(struct mlx5dr_ste_build *sb, struct mlx5dr_match_param *mask, bool inner, bool rx) { @@ -1594,9 +1594,9 @@ static int dr_ste_build_ipv6_l3_l4_tag(struct mlx5dr_match_param *value, return 0; } -void mlx5dr_ste_build_ipv6_l3_l4(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, - bool inner, bool rx) +void mlx5dr_ste_build_eth_ipv6_l3_l4(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) { dr_ste_build_ipv6_l3_l4_bit_mask(mask, inner, sb->bit_mask); @@ -1693,8 +1693,8 @@ static int dr_ste_build_gre_tag(struct mlx5dr_match_param *value, return 0; } -void mlx5dr_ste_build_gre(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, bool inner, bool rx) +void mlx5dr_ste_build_tnl_gre(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, bool inner, bool rx) { dr_ste_build_gre_bit_mask(mask, inner, sb->bit_mask); @@ -1771,9 +1771,9 @@ static int dr_ste_build_flex_parser_0_tag(struct mlx5dr_match_param *value, return 0; } -void mlx5dr_ste_build_flex_parser_0(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, - bool inner, bool rx) +void mlx5dr_ste_build_tnl_mpls(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) { dr_ste_build_flex_parser_0_bit_mask(mask, inner, sb->bit_mask); @@ -1792,8 +1792,8 @@ static int dr_ste_build_flex_parser_1_bit_mask(struct mlx5dr_match_param *mask, struct mlx5dr_cmd_caps *caps, u8 *bit_mask) { + bool is_ipv4_mask = DR_MASK_IS_ICMPV4_SET(&mask->misc3); struct mlx5dr_match_misc3 *misc_3_mask = &mask->misc3; - bool is_ipv4_mask = DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(misc_3_mask); u32 icmp_header_data_mask; u32 icmp_type_mask; u32 icmp_code_mask; @@ -1869,7 +1869,7 @@ static int dr_ste_build_flex_parser_1_tag(struct mlx5dr_match_param *value, u32 icmp_code; bool is_ipv4; - is_ipv4 = DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(misc_3); + is_ipv4 = DR_MASK_IS_ICMPV4_SET(misc_3); if (is_ipv4) { icmp_header_data = misc_3->icmpv4_header_data; icmp_type = misc_3->icmpv4_type; @@ -1928,10 +1928,10 @@ static int dr_ste_build_flex_parser_1_tag(struct mlx5dr_match_param *value, return 0; } -int mlx5dr_ste_build_flex_parser_1(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, - struct mlx5dr_cmd_caps *caps, - bool inner, bool rx) +int mlx5dr_ste_build_icmp(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + struct mlx5dr_cmd_caps *caps, + bool inner, bool rx) { int ret; @@ -2069,9 +2069,9 @@ dr_ste_build_flex_parser_tnl_vxlan_gpe_tag(struct mlx5dr_match_param *value, return 0; } -void mlx5dr_ste_build_flex_parser_tnl_vxlan_gpe(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, - bool inner, bool rx) +void mlx5dr_ste_build_tnl_vxlan_gpe(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) { dr_ste_build_flex_parser_tnl_vxlan_gpe_bit_mask(mask, inner, sb->bit_mask); @@ -2122,9 +2122,9 @@ dr_ste_build_flex_parser_tnl_geneve_tag(struct mlx5dr_match_param *value, return 0; } -void mlx5dr_ste_build_flex_parser_tnl_geneve(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, - bool inner, bool rx) +void mlx5dr_ste_build_tnl_geneve(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) { dr_ste_build_flex_parser_tnl_geneve_bit_mask(mask, sb->bit_mask); sb->rx = rx; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index cf62ea4f882e..51880df26724 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -17,6 +17,7 @@ #define WIRE_PORT 0xFFFF #define DR_STE_SVLAN 0x1 #define DR_STE_CVLAN 0x2 +#define DR_SZ_MATCH_PARAM (MLX5_ST_SZ_DW_MATCH_PARAM * 4) #define mlx5dr_err(dmn, arg...) mlx5_core_err((dmn)->mdev, ##arg) #define mlx5dr_info(dmn, arg...) mlx5_core_info((dmn)->mdev, ##arg) @@ -114,7 +115,7 @@ enum mlx5dr_ipv { struct mlx5dr_icm_pool; struct mlx5dr_icm_chunk; -struct mlx5dr_icm_bucket; +struct mlx5dr_icm_buddy_mem; struct mlx5dr_ste_htbl; struct mlx5dr_match_param; struct mlx5dr_cmd_caps; @@ -288,7 +289,7 @@ int mlx5dr_ste_build_ste_arr(struct mlx5dr_matcher *matcher, struct mlx5dr_matcher_rx_tx *nic_matcher, struct mlx5dr_match_param *value, u8 *ste_arr); -void mlx5dr_ste_build_eth_l2_src_des(struct mlx5dr_ste_build *builder, +void mlx5dr_ste_build_eth_l2_src_dst(struct mlx5dr_ste_build *builder, struct mlx5dr_match_param *mask, bool inner, bool rx); void mlx5dr_ste_build_eth_l3_ipv4_5_tuple(struct mlx5dr_ste_build *sb, @@ -312,31 +313,31 @@ void mlx5dr_ste_build_eth_l2_dst(struct mlx5dr_ste_build *sb, void mlx5dr_ste_build_eth_l2_tnl(struct mlx5dr_ste_build *sb, struct mlx5dr_match_param *mask, bool inner, bool rx); -void mlx5dr_ste_build_ipv6_l3_l4(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, - bool inner, bool rx); +void mlx5dr_ste_build_eth_ipv6_l3_l4(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); void mlx5dr_ste_build_eth_l4_misc(struct mlx5dr_ste_build *sb, struct mlx5dr_match_param *mask, bool inner, bool rx); -void mlx5dr_ste_build_gre(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, - bool inner, bool rx); +void mlx5dr_ste_build_tnl_gre(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); void mlx5dr_ste_build_mpls(struct mlx5dr_ste_build *sb, struct mlx5dr_match_param *mask, bool inner, bool rx); -void mlx5dr_ste_build_flex_parser_0(struct mlx5dr_ste_build *sb, +void mlx5dr_ste_build_tnl_mpls(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +int mlx5dr_ste_build_icmp(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + struct mlx5dr_cmd_caps *caps, + bool inner, bool rx); +void mlx5dr_ste_build_tnl_vxlan_gpe(struct mlx5dr_ste_build *sb, struct mlx5dr_match_param *mask, bool inner, bool rx); -int mlx5dr_ste_build_flex_parser_1(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, - struct mlx5dr_cmd_caps *caps, - bool inner, bool rx); -void mlx5dr_ste_build_flex_parser_tnl_vxlan_gpe(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, - bool inner, bool rx); -void mlx5dr_ste_build_flex_parser_tnl_geneve(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, - bool inner, bool rx); +void mlx5dr_ste_build_tnl_geneve(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); void mlx5dr_ste_build_general_purpose(struct mlx5dr_ste_build *sb, struct mlx5dr_match_param *mask, bool inner, bool rx); @@ -588,9 +589,9 @@ struct mlx5dr_match_param { struct mlx5dr_match_misc3 misc3; }; -#define DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(_misc3) ((_misc3)->icmpv4_type || \ - (_misc3)->icmpv4_code || \ - (_misc3)->icmpv4_header_data) +#define DR_MASK_IS_ICMPV4_SET(_misc3) ((_misc3)->icmpv4_type || \ + (_misc3)->icmpv4_code || \ + (_misc3)->icmpv4_header_data) struct mlx5dr_esw_caps { u64 drop_icm_address_rx; @@ -732,7 +733,6 @@ struct mlx5dr_action { struct mlx5dr_domain *dmn; struct mlx5dr_icm_chunk *chunk; u8 *data; - u32 data_size; u16 num_of_actions; u32 index; u8 allow_rx:1; @@ -805,7 +805,7 @@ void mlx5dr_rule_update_rule_member(struct mlx5dr_ste *new_ste, struct mlx5dr_ste *ste); struct mlx5dr_icm_chunk { - struct mlx5dr_icm_bucket *bucket; + struct mlx5dr_icm_buddy_mem *buddy_mem; struct list_head chunk_list; u32 rkey; u32 num_of_entries; @@ -813,6 +813,11 @@ struct mlx5dr_icm_chunk { u64 icm_addr; u64 mr_addr; + /* indicates the index of this chunk in the whole memory, + * used for deleting the chunk from the buddy + */ + unsigned int seg; + /* Memory optimisation */ struct mlx5dr_ste *ste_arr; u8 *hw_ste_arr; @@ -841,23 +846,20 @@ static inline void mlx5dr_domain_unlock(struct mlx5dr_domain *dmn) mlx5dr_domain_nic_unlock(&dmn->info.rx); } -static inline int -mlx5dr_matcher_supp_flex_parser_icmp_v4(struct mlx5dr_cmd_caps *caps) -{ - return caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V4_ENABLED; -} - -static inline int -mlx5dr_matcher_supp_flex_parser_icmp_v6(struct mlx5dr_cmd_caps *caps) -{ - return caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V6_ENABLED; -} - int mlx5dr_matcher_select_builders(struct mlx5dr_matcher *matcher, struct mlx5dr_matcher_rx_tx *nic_matcher, enum mlx5dr_ipv outer_ipv, enum mlx5dr_ipv inner_ipv); +static inline int +mlx5dr_icm_pool_dm_type_to_entry_size(enum mlx5dr_icm_type icm_type) +{ + if (icm_type == DR_ICM_TYPE_STE) + return DR_STE_SIZE; + + return DR_MODIFY_ACTION_SIZE; +} + static inline u32 mlx5dr_icm_pool_chunk_size_to_entries(enum mlx5dr_icm_chunk_size chunk_size) { @@ -871,11 +873,7 @@ mlx5dr_icm_pool_chunk_size_to_byte(enum mlx5dr_icm_chunk_size chunk_size, int num_of_entries; int entry_size; - if (icm_type == DR_ICM_TYPE_STE) - entry_size = DR_STE_SIZE; - else - entry_size = DR_MODIFY_ACTION_SIZE; - + entry_size = mlx5dr_icm_pool_dm_type_to_entry_size(icm_type); num_of_entries = mlx5dr_icm_pool_chunk_size_to_entries(chunk_size); return entry_size * num_of_entries; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index 7914fe3fc68d..4177786b8eaf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -127,4 +127,36 @@ mlx5dr_is_supported(struct mlx5_core_dev *dev) return MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner); } +/* buddy functions & structure */ + +struct mlx5dr_icm_mr; + +struct mlx5dr_icm_buddy_mem { + unsigned long **bitmap; + unsigned int *num_free; + u32 max_order; + struct list_head list_node; + struct mlx5dr_icm_mr *icm_mr; + struct mlx5dr_icm_pool *pool; + + /* This is the list of used chunks. HW may be accessing this memory */ + struct list_head used_list; + u64 used_memory; + + /* Hardware may be accessing this memory but at some future, + * undetermined time, it might cease to do so. + * sync_ste command sets them free. + */ + struct list_head hot_list; +}; + +int mlx5dr_buddy_init(struct mlx5dr_icm_buddy_mem *buddy, + unsigned int max_order); +void mlx5dr_buddy_cleanup(struct mlx5dr_icm_buddy_mem *buddy); +int mlx5dr_buddy_alloc_mem(struct mlx5dr_icm_buddy_mem *buddy, + unsigned int order, + unsigned int *segment); +void mlx5dr_buddy_free_mem(struct mlx5dr_icm_buddy_mem *buddy, + unsigned int seg, unsigned int order); + #endif /* _MLX5DR_H_ */ |