diff options
Diffstat (limited to 'drivers/net/ethernet/intel')
48 files changed, 1866 insertions, 285 deletions
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index c1d155690341..eae1b42e48db 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -241,6 +241,7 @@ config I40E tristate "Intel(R) Ethernet Controller XL710 Family support" imply PTP_1588_CLOCK depends on PCI + select AUXILIARY_BUS help This driver supports Intel(R) Ethernet Controller XL710 Family of devices. For more information on how to identify your adapter, go @@ -294,6 +295,7 @@ config ICE tristate "Intel(R) Ethernet Connection E800 Series Support" default n depends on PCI_MSI + select AUXILIARY_BUS select DIMLIB select NET_DEVLINK select PLDMFW diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index f8d78af76d7d..1b0958bd24f6 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -1395,7 +1395,7 @@ static int e100_phy_check_without_mii(struct nic *nic) u8 phy_type; int without_mii; - phy_type = (nic->eeprom[eeprom_phy_iface] >> 8) & 0x0f; + phy_type = (le16_to_cpu(nic->eeprom[eeprom_phy_iface]) >> 8) & 0x0f; switch (phy_type) { case NoSuchPhy: /* Non-MII PHY; UNTESTED! */ @@ -1515,7 +1515,7 @@ static int e100_phy_init(struct nic *nic) mdio_write(netdev, nic->mii.phy_id, MII_BMCR, bmcr); } else if ((nic->mac >= mac_82550_D102) || ((nic->flags & ich) && (mdio_read(netdev, nic->mii.phy_id, MII_TPISTATUS) & 0x8000) && - (nic->eeprom[eeprom_cnfg_mdix] & eeprom_mdix_enabled))) { + (le16_to_cpu(nic->eeprom[eeprom_cnfg_mdix]) & eeprom_mdix_enabled))) { /* enable/disable MDI/MDI-X auto-switching. */ mdio_write(netdev, nic->mii.phy_id, MII_NCONFIG, nic->mii.force_media ? 0 : NCONFIG_AUTO_SWITCH); @@ -2269,9 +2269,9 @@ static int e100_asf(struct nic *nic) { /* ASF can be enabled from eeprom */ return (nic->pdev->device >= 0x1050) && (nic->pdev->device <= 0x1057) && - (nic->eeprom[eeprom_config_asf] & eeprom_asf) && - !(nic->eeprom[eeprom_config_asf] & eeprom_gcl) && - ((nic->eeprom[eeprom_smbus_addr] & 0xFF) != 0xFE); + (le16_to_cpu(nic->eeprom[eeprom_config_asf]) & eeprom_asf) && + !(le16_to_cpu(nic->eeprom[eeprom_config_asf]) & eeprom_gcl) && + ((le16_to_cpu(nic->eeprom[eeprom_smbus_addr]) & 0xFF) != 0xFE); } static int e100_up(struct nic *nic) @@ -2926,7 +2926,7 @@ static int e100_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Wol magic packet can be enabled from eeprom */ if ((nic->mac >= mac_82558_D101_A4) && - (nic->eeprom[eeprom_id] & eeprom_id_wol)) { + (le16_to_cpu(nic->eeprom[eeprom_id]) & eeprom_id_wol)) { nic->flags |= wol_magic; device_set_wakeup_enable(&pdev->dev, true); } diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c index f976e9daa3d8..3c51ee94fa00 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c +++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c @@ -513,7 +513,7 @@ static int e1000_set_eeprom(struct net_device *netdev, memcpy(ptr, bytes, eeprom->len); for (i = 0; i < last_word - first_word + 1; i++) - eeprom_buff[i] = cpu_to_le16(eeprom_buff[i]); + cpu_to_le16s(&eeprom_buff[i]); ret_val = e1000_write_eeprom(hw, first_word, last_word - first_word + 1, eeprom_buff); diff --git a/drivers/net/ethernet/intel/e1000/e1000_hw.c b/drivers/net/ethernet/intel/e1000/e1000_hw.c index 19cf36360933..1042e79a1397 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_hw.c +++ b/drivers/net/ethernet/intel/e1000/e1000_hw.c @@ -2522,7 +2522,7 @@ s32 e1000_check_for_link(struct e1000_hw *hw) * turn it on. For compatibility with a TBI link * partner, we will store bad packets. Some * frames have an additional byte on the end and - * will look like CRC errors to to the hardware. + * will look like CRC errors to the hardware. */ if (!hw->tbi_compatibility_on) { hw->tbi_compatibility_on = true; @@ -2723,7 +2723,7 @@ static void e1000_shift_out_mdi_bits(struct e1000_hw *hw, u32 data, u16 count) * e1000_shift_in_mdi_bits - Shifts data bits in from the PHY * @hw: Struct containing variables accessed by shared code * - * Bits are shifted in in MSB to LSB order. + * Bits are shifted in MSB to LSB order. */ static u16 e1000_shift_in_mdi_bits(struct e1000_hw *hw) { diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 042de276e632..c2a109126c27 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -5245,7 +5245,7 @@ static pci_ers_result_t e1000_io_error_detected(struct pci_dev *pdev, if (!test_and_set_bit(__E1000_DISABLED, &adapter->flags)) pci_disable_device(pdev); - /* Request a slot slot reset. */ + /* Request a slot reset. */ return PCI_ERS_RESULT_NEED_RESET; } diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 590ad110d383..cf7b3887da1d 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -4639,7 +4639,7 @@ static s32 e1000_id_led_init_pchlan(struct e1000_hw *hw) * @hw: pointer to the HW structure * * ICH8 use the PCI Express bus, but does not contain a PCI Express Capability - * register, so the the bus width is hard coded. + * register, so the bus width is hard coded. **/ static s32 e1000_get_bus_info_ich8lan(struct e1000_hw *hw) { diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 88e9035b75cf..5435606149b0 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -7118,7 +7118,7 @@ static pci_ers_result_t e1000_io_error_detected(struct pci_dev *pdev, pci_disable_device(pdev); - /* Request a slot slot reset. */ + /* Request a slot reset. */ return PCI_ERS_RESULT_NEED_RESET; } diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c index 1db35b2c7750..0f0efee5fc8e 100644 --- a/drivers/net/ethernet/intel/e1000e/phy.c +++ b/drivers/net/ethernet/intel/e1000e/phy.c @@ -2978,7 +2978,7 @@ static u32 e1000_get_phy_addr_for_hv_page(u32 page) * @data: pointer to the data to be read or written * @read: determines if operation is read or write * - * Reads the PHY register at offset and stores the retreived information + * Reads the PHY register at offset and stores the retrieved information * in data. Assumes semaphore already acquired. Note that the procedure * to access these regs uses the address port and data port to read/write. * These accesses done with PHY address 2 and without using pages. diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 9e3103fae723..dbcae92bb18d 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -1370,7 +1370,6 @@ static irqreturn_t fm10k_msix_mbx_pf(int __always_unused irq, void *data) struct fm10k_hw *hw = &interface->hw; struct fm10k_mbx_info *mbx = &hw->mbx; u32 eicr; - s32 err = 0; /* unmask any set bits related to this interrupt */ eicr = fm10k_read_reg(hw, FM10K_EICR); @@ -1386,15 +1385,16 @@ static irqreturn_t fm10k_msix_mbx_pf(int __always_unused irq, void *data) /* service mailboxes */ if (fm10k_mbx_trylock(interface)) { - err = mbx->ops.process(hw, mbx); + s32 err = mbx->ops.process(hw, mbx); + + if (err == FM10K_ERR_RESET_REQUESTED) + set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); + /* handle VFLRE events */ fm10k_iov_event(interface); fm10k_mbx_unlock(interface); } - if (err == FM10K_ERR_RESET_REQUESTED) - set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); - /* if switch toggled state we should reset GLORTs */ if (eicr & FM10K_EICR_SWITCHNOTREADY) { /* force link down for at least 4 seconds */ diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 85d3dd3a3339..b9417dc0007c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -870,6 +870,8 @@ struct i40e_netdev_priv { struct i40e_vsi *vsi; }; +extern struct ida i40e_client_ida; + /* struct that defines an interrupt vector */ struct i40e_q_vector { struct i40e_vsi *vsi; diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c index 32f3facbed1a..e07ed065d3a4 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.c +++ b/drivers/net/ethernet/intel/i40e/i40e_client.c @@ -12,6 +12,7 @@ static const char i40e_client_interface_version_str[] = I40E_CLIENT_VERSION_STR; static struct i40e_client *registered_client; static LIST_HEAD(i40e_devices); static DEFINE_MUTEX(i40e_device_mutex); +DEFINE_IDA(i40e_client_ida); static int i40e_client_virtchnl_send(struct i40e_info *ldev, struct i40e_client *client, @@ -275,6 +276,57 @@ void i40e_client_update_msix_info(struct i40e_pf *pf) cdev->lan_info.msix_entries = &pf->msix_entries[pf->iwarp_base_vector]; } +static void i40e_auxiliary_dev_release(struct device *dev) +{ + struct i40e_auxiliary_device *i40e_aux_dev = + container_of(dev, struct i40e_auxiliary_device, aux_dev.dev); + + ida_free(&i40e_client_ida, i40e_aux_dev->aux_dev.id); + kfree(i40e_aux_dev); +} + +static int i40e_register_auxiliary_dev(struct i40e_info *ldev, const char *name) +{ + struct i40e_auxiliary_device *i40e_aux_dev; + struct pci_dev *pdev = ldev->pcidev; + struct auxiliary_device *aux_dev; + int ret; + + i40e_aux_dev = kzalloc(sizeof(*i40e_aux_dev), GFP_KERNEL); + if (!i40e_aux_dev) + return -ENOMEM; + + i40e_aux_dev->ldev = ldev; + + aux_dev = &i40e_aux_dev->aux_dev; + aux_dev->name = name; + aux_dev->dev.parent = &pdev->dev; + aux_dev->dev.release = i40e_auxiliary_dev_release; + ldev->aux_dev = aux_dev; + + ret = ida_alloc(&i40e_client_ida, GFP_KERNEL); + if (ret < 0) { + kfree(i40e_aux_dev); + return ret; + } + aux_dev->id = ret; + + ret = auxiliary_device_init(aux_dev); + if (ret < 0) { + ida_free(&i40e_client_ida, aux_dev->id); + kfree(i40e_aux_dev); + return ret; + } + + ret = auxiliary_device_add(aux_dev); + if (ret) { + auxiliary_device_uninit(aux_dev); + return ret; + } + + return ret; +} + /** * i40e_client_add_instance - add a client instance struct to the instance list * @pf: pointer to the board struct @@ -286,9 +338,6 @@ static void i40e_client_add_instance(struct i40e_pf *pf) struct netdev_hw_addr *mac = NULL; struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; - if (!registered_client || pf->cinst) - return; - cdev = kzalloc(sizeof(*cdev), GFP_KERNEL); if (!cdev) return; @@ -308,11 +357,8 @@ static void i40e_client_add_instance(struct i40e_pf *pf) cdev->lan_info.fw_build = pf->hw.aq.fw_build; set_bit(__I40E_CLIENT_INSTANCE_NONE, &cdev->state); - if (i40e_client_get_params(vsi, &cdev->lan_info.params)) { - kfree(cdev); - cdev = NULL; - return; - } + if (i40e_client_get_params(vsi, &cdev->lan_info.params)) + goto free_cdev; mac = list_first_entry(&cdev->lan_info.netdev->dev_addrs.list, struct netdev_hw_addr, list); @@ -324,7 +370,17 @@ static void i40e_client_add_instance(struct i40e_pf *pf) cdev->client = registered_client; pf->cinst = cdev; - i40e_client_update_msix_info(pf); + cdev->lan_info.msix_count = pf->num_iwarp_msix; + cdev->lan_info.msix_entries = &pf->msix_entries[pf->iwarp_base_vector]; + + if (i40e_register_auxiliary_dev(&cdev->lan_info, "iwarp")) + goto free_cdev; + + return; + +free_cdev: + kfree(cdev); + pf->cinst = NULL; } /** @@ -345,7 +401,7 @@ void i40e_client_del_instance(struct i40e_pf *pf) **/ void i40e_client_subtask(struct i40e_pf *pf) { - struct i40e_client *client = registered_client; + struct i40e_client *client; struct i40e_client_instance *cdev; struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; int ret = 0; @@ -359,9 +415,11 @@ void i40e_client_subtask(struct i40e_pf *pf) test_bit(__I40E_CONFIG_BUSY, pf->state)) return; - if (!client || !cdev) + if (!cdev || !cdev->client) return; + client = cdev->client; + /* Here we handle client opens. If the client is down, and * the netdev is registered, then open the client. */ @@ -423,16 +481,8 @@ int i40e_lan_add_device(struct i40e_pf *pf) pf->hw.pf_id, pf->hw.bus.bus_id, pf->hw.bus.device, pf->hw.bus.func); - /* If a client has already been registered, we need to add an instance - * of it to our new LAN device. - */ - if (registered_client) - i40e_client_add_instance(pf); + i40e_client_add_instance(pf); - /* Since in some cases register may have happened before a device gets - * added, we can schedule a subtask to go initiate the clients if - * they can be launched at probe time. - */ set_bit(__I40E_CLIENT_SERVICE_REQUESTED, pf->state); i40e_service_event_schedule(pf); @@ -449,9 +499,13 @@ out: **/ int i40e_lan_del_device(struct i40e_pf *pf) { + struct auxiliary_device *aux_dev = pf->cinst->lan_info.aux_dev; struct i40e_device *ldev, *tmp; int ret = -ENODEV; + auxiliary_device_delete(aux_dev); + auxiliary_device_uninit(aux_dev); + /* First, remove any client instance. */ i40e_client_del_instance(pf); @@ -579,7 +633,7 @@ static int i40e_client_setup_qvlist(struct i40e_info *ldev, u32 v_idx, i, reg_idx, reg; ldev->qvlist_info = kzalloc(struct_size(ldev->qvlist_info, qv_info, - qvlist_info->num_vectors - 1), GFP_KERNEL); + qvlist_info->num_vectors), GFP_KERNEL); if (!ldev->qvlist_info) return -ENOMEM; ldev->qvlist_info->num_vectors = qvlist_info->num_vectors; @@ -732,6 +786,42 @@ static int i40e_client_update_vsi_ctxt(struct i40e_info *ldev, return err; } +void i40e_client_device_register(struct i40e_info *ldev, struct i40e_client *client) +{ + struct i40e_pf *pf = ldev->pf; + + pf->cinst->client = client; + set_bit(__I40E_CLIENT_SERVICE_REQUESTED, pf->state); + i40e_service_event_schedule(pf); +} +EXPORT_SYMBOL_GPL(i40e_client_device_register); + +void i40e_client_device_unregister(struct i40e_info *ldev) +{ + struct i40e_pf *pf = ldev->pf; + struct i40e_client_instance *cdev = pf->cinst; + + if (!cdev) + return; + + while (test_and_set_bit(__I40E_SERVICE_SCHED, pf->state)) + usleep_range(500, 1000); + + if (test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) { + cdev->client->ops->close(&cdev->lan_info, cdev->client, false); + clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state); + i40e_client_release_qvlist(&cdev->lan_info); + } + + pf->cinst->client = NULL; + clear_bit(__I40E_SERVICE_SCHED, pf->state); +} +EXPORT_SYMBOL_GPL(i40e_client_device_unregister); + +/* Retain these legacy global registration/unregistration calls till i40iw is + * removed from the kernel. The irdma unified driver does not use these + * exported symbols. + */ /** * i40e_register_client - Register a i40e client driver with the L2 driver * @client: pointer to the i40e_client struct diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 704e474879c5..9db1968fc491 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -16270,6 +16270,7 @@ static void __exit i40e_exit_module(void) { pci_unregister_driver(&i40e_driver); destroy_workqueue(i40e_wq); + ida_destroy(&i40e_client_ida); i40e_dbg_exit(); } module_exit(i40e_exit_module); diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index 07fe857e9e3a..dfb64fb504a2 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -22,6 +22,7 @@ ice-y := ice_main.o \ ice_ethtool_fdir.o \ ice_flex_pipe.o \ ice_flow.o \ + ice_idc.o \ ice_devlink.o \ ice_fw_update.o \ ice_lag.o \ diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 2924c67567b8..ea1ab7ca82c4 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -34,6 +34,7 @@ #include <linux/if_bridge.h> #include <linux/ctype.h> #include <linux/bpf.h> +#include <linux/auxiliary_bus.h> #include <linux/avf/virtchnl.h> #include <linux/cpu_rmap.h> #include <linux/dim.h> @@ -55,6 +56,7 @@ #include "ice_switch.h" #include "ice_common.h" #include "ice_sched.h" +#include "ice_idc_int.h" #include "ice_virtchnl_pf.h" #include "ice_sriov.h" #include "ice_fdir.h" @@ -78,6 +80,8 @@ #define ICE_MIN_LAN_OICR_MSIX 1 #define ICE_MIN_MSIX (ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_LAN_OICR_MSIX) #define ICE_FDIR_MSIX 2 +#define ICE_RDMA_NUM_AEQ_MSIX 4 +#define ICE_MIN_RDMA_MSIX 2 #define ICE_NO_VSI 0xffff #define ICE_VSI_MAP_CONTIG 0 #define ICE_VSI_MAP_SCATTER 1 @@ -88,8 +92,9 @@ #define ICE_MAX_LG_RSS_QS 256 #define ICE_RES_VALID_BIT 0x8000 #define ICE_RES_MISC_VEC_ID (ICE_RES_VALID_BIT - 1) +#define ICE_RES_RDMA_VEC_ID (ICE_RES_MISC_VEC_ID - 1) /* All VF control VSIs share the same IRQ, so assign a unique ID for them */ -#define ICE_RES_VF_CTRL_VEC_ID (ICE_RES_MISC_VEC_ID - 1) +#define ICE_RES_VF_CTRL_VEC_ID (ICE_RES_RDMA_VEC_ID - 1) #define ICE_INVAL_Q_INDEX 0xffff #define ICE_INVAL_VFID 256 @@ -203,9 +208,9 @@ enum ice_pf_state { ICE_NEEDS_RESTART, ICE_PREPARED_FOR_RESET, /* set by driver when prepared */ ICE_RESET_OICR_RECV, /* set by driver after rcv reset OICR */ - ICE_PFR_REQ, /* set by driver and peers */ - ICE_CORER_REQ, /* set by driver and peers */ - ICE_GLOBR_REQ, /* set by driver and peers */ + ICE_PFR_REQ, /* set by driver */ + ICE_CORER_REQ, /* set by driver */ + ICE_GLOBR_REQ, /* set by driver */ ICE_CORER_RECV, /* set by OICR handler */ ICE_GLOBR_RECV, /* set by OICR handler */ ICE_EMPR_RECV, /* set by OICR handler */ @@ -332,6 +337,7 @@ struct ice_vsi { u16 req_rxq; /* User requested Rx queues */ u16 num_rx_desc; u16 num_tx_desc; + u16 qset_handle[ICE_MAX_TRAFFIC_CLASS]; struct ice_tc_cfg tc_cfg; struct bpf_prog *xdp_prog; struct ice_ring **xdp_rings; /* XDP ring array */ @@ -374,12 +380,14 @@ struct ice_q_vector { enum ice_pf_flags { ICE_FLAG_FLTR_SYNC, + ICE_FLAG_RDMA_ENA, ICE_FLAG_RSS_ENA, ICE_FLAG_SRIOV_ENA, ICE_FLAG_SRIOV_CAPABLE, ICE_FLAG_DCB_CAPABLE, ICE_FLAG_DCB_ENA, ICE_FLAG_FD_ENA, + ICE_FLAG_AUX_ENA, ICE_FLAG_ADV_FEATURES, ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, ICE_FLAG_TOTAL_PORT_SHUTDOWN_ENA, @@ -440,6 +448,8 @@ struct ice_pf { struct mutex sw_mutex; /* lock for protecting VSI alloc flow */ struct mutex tc_mutex; /* lock to protect TC changes */ u32 msg_enable; + u16 num_rdma_msix; /* Total MSIX vectors for RDMA driver */ + u16 rdma_base_vector; /* spinlock to protect the AdminQ wait list */ spinlock_t aq_wait_lock; @@ -472,6 +482,8 @@ struct ice_pf { unsigned long tx_timeout_last_recovery; u32 tx_timeout_recovery_level; char int_name[ICE_INT_NAME_STR_LEN]; + struct auxiliary_device *adev; + int aux_idx; u32 sw_int_count; __le64 nvm_phy_type_lo; /* NVM PHY type low */ @@ -638,6 +650,9 @@ int ice_get_rss_key(struct ice_vsi *vsi, u8 *seed); void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size); int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset); void ice_print_link_msg(struct ice_vsi *vsi, bool isup); +int ice_plug_aux_dev(struct ice_pf *pf); +void ice_unplug_aux_dev(struct ice_pf *pf); +int ice_init_rdma(struct ice_pf *pf); const char *ice_stat_str(enum ice_status stat_err); const char *ice_aq_str(enum ice_aq_err aq_err); bool ice_is_wol_supported(struct ice_hw *hw); @@ -662,4 +677,25 @@ int ice_open_internal(struct net_device *netdev); int ice_stop(struct net_device *netdev); void ice_service_task_schedule(struct ice_pf *pf); +/** + * ice_set_rdma_cap - enable RDMA support + * @pf: PF struct + */ +static inline void ice_set_rdma_cap(struct ice_pf *pf) +{ + if (pf->hw.func_caps.common_cap.rdma && pf->num_rdma_msix) { + set_bit(ICE_FLAG_RDMA_ENA, pf->flags); + ice_plug_aux_dev(pf); + } +} + +/** + * ice_clear_rdma_cap - disable RDMA support + * @pf: PF struct + */ +static inline void ice_clear_rdma_cap(struct ice_pf *pf) +{ + ice_unplug_aux_dev(pf); + clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); +} #endif /* _ICE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 5cdfe406af84..ff11a618bef7 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -115,6 +115,7 @@ struct ice_aqc_list_caps_elem { #define ICE_AQC_CAPS_PENDING_OROM_VER 0x004B #define ICE_AQC_CAPS_NET_VER 0x004C #define ICE_AQC_CAPS_PENDING_NET_VER 0x004D +#define ICE_AQC_CAPS_RDMA 0x0051 #define ICE_AQC_CAPS_NVM_MGMT 0x0080 u8 major_ver; @@ -1684,6 +1685,36 @@ struct ice_aqc_dis_txq_item { __le16 q_id[]; } __packed; +/* Add Tx RDMA Queue Set (indirect 0x0C33) */ +struct ice_aqc_add_rdma_qset { + u8 num_qset_grps; + u8 reserved[7]; + __le32 addr_high; + __le32 addr_low; +}; + +/* This is the descriptor of each Qset entry for the Add Tx RDMA Queue Set + * command (0x0C33). Only used within struct ice_aqc_add_rdma_qset. + */ +struct ice_aqc_add_tx_rdma_qset_entry { + __le16 tx_qset_id; + u8 rsvd[2]; + __le32 qset_teid; + struct ice_aqc_txsched_elem info; +}; + +/* The format of the command buffer for Add Tx RDMA Queue Set(0x0C33) + * is an array of the following structs. Please note that the length of + * each struct ice_aqc_add_rdma_qset is variable due to the variable + * number of queues in each group! + */ +struct ice_aqc_add_rdma_qset_data { + __le32 parent_teid; + __le16 num_qsets; + u8 rsvd[2]; + struct ice_aqc_add_tx_rdma_qset_entry rdma_qsets[]; +}; + /* Configure Firmware Logging Command (indirect 0xFF09) * Logging Information Read Response (indirect 0xFF10) * Note: The 0xFF10 command has no input parameters. @@ -1880,6 +1911,7 @@ struct ice_aq_desc { struct ice_aqc_get_set_rss_key get_set_rss_key; struct ice_aqc_add_txqs add_txqs; struct ice_aqc_dis_txqs dis_txqs; + struct ice_aqc_add_rdma_qset add_rdma_qset; struct ice_aqc_add_get_update_free_vsi vsi_cmd; struct ice_aqc_add_update_free_vsi_resp add_update_free_vsi_res; struct ice_aqc_fw_logging fw_logging; @@ -2028,6 +2060,7 @@ enum ice_adminq_opc { /* Tx queue handling commands/events */ ice_aqc_opc_add_txqs = 0x0C30, ice_aqc_opc_dis_txqs = 0x0C31, + ice_aqc_opc_add_rdma_qset = 0x0C33, /* package commands */ ice_aqc_opc_download_pkg = 0x0C40, diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index e93b1e40f627..b8cc737ea261 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -2,6 +2,7 @@ /* Copyright (c) 2018, Intel Corporation. */ #include "ice_common.h" +#include "ice_lib.h" #include "ice_sched.h" #include "ice_adminq_cmd.h" #include "ice_flow.h" @@ -1062,7 +1063,8 @@ enum ice_status ice_check_reset(struct ice_hw *hw) GLNVM_ULD_POR_DONE_1_M |\ GLNVM_ULD_PCIER_DONE_2_M) - uld_mask = ICE_RESET_DONE_MASK; + uld_mask = ICE_RESET_DONE_MASK | (hw->func_caps.common_cap.rdma ? + GLNVM_ULD_PE_DONE_M : 0); /* Device is Active; check Global Reset processes are done */ for (cnt = 0; cnt < ICE_PF_RESET_WAIT_COUNT; cnt++) { @@ -1938,6 +1940,10 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps, ice_debug(hw, ICE_DBG_INIT, "%s: nvm_unified_update = %d\n", prefix, caps->nvm_unified_update); break; + case ICE_AQC_CAPS_RDMA: + caps->rdma = (number == 1); + ice_debug(hw, ICE_DBG_INIT, "%s: rdma = %d\n", prefix, caps->rdma); + break; case ICE_AQC_CAPS_MAX_MTU: caps->max_mtu = number; ice_debug(hw, ICE_DBG_INIT, "%s: max_mtu = %d\n", @@ -1971,6 +1977,16 @@ ice_recalc_port_limited_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps) caps->maxtc = 4; ice_debug(hw, ICE_DBG_INIT, "reducing maxtc to %d (based on #ports)\n", caps->maxtc); + if (caps->rdma) { + ice_debug(hw, ICE_DBG_INIT, "forcing RDMA off\n"); + caps->rdma = 0; + } + + /* print message only when processing device capabilities + * during initialization. + */ + if (caps == &hw->dev_caps.common_cap) + dev_info(ice_hw_to_dev(hw), "RDMA functionality is not available with the current device configuration.\n"); } } @@ -3635,6 +3651,52 @@ do_aq: return status; } +/** + * ice_aq_add_rdma_qsets + * @hw: pointer to the hardware structure + * @num_qset_grps: Number of RDMA Qset groups + * @qset_list: list of Qset groups to be added + * @buf_size: size of buffer for indirect command + * @cd: pointer to command details structure or NULL + * + * Add Tx RDMA Qsets (0x0C33) + */ +static int +ice_aq_add_rdma_qsets(struct ice_hw *hw, u8 num_qset_grps, + struct ice_aqc_add_rdma_qset_data *qset_list, + u16 buf_size, struct ice_sq_cd *cd) +{ + struct ice_aqc_add_rdma_qset_data *list; + struct ice_aqc_add_rdma_qset *cmd; + struct ice_aq_desc desc; + u16 i, sum_size = 0; + + cmd = &desc.params.add_rdma_qset; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_rdma_qset); + + if (num_qset_grps > ICE_LAN_TXQ_MAX_QGRPS) + return -EINVAL; + + for (i = 0, list = qset_list; i < num_qset_grps; i++) { + u16 num_qsets = le16_to_cpu(list->num_qsets); + + sum_size += struct_size(list, rdma_qsets, num_qsets); + list = (struct ice_aqc_add_rdma_qset_data *)(list->rdma_qsets + + num_qsets); + } + + if (buf_size != sum_size) + return -EINVAL; + + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + cmd->num_qset_grps = num_qset_grps; + + return ice_status_to_errno(ice_aq_send_cmd(hw, &desc, qset_list, + buf_size, cd)); +} + /* End of FW Admin Queue command wrappers */ /** @@ -4133,6 +4195,162 @@ ice_cfg_vsi_lan(struct ice_port_info *pi, u16 vsi_handle, u8 tc_bitmap, } /** + * ice_cfg_vsi_rdma - configure the VSI RDMA queues + * @pi: port information structure + * @vsi_handle: software VSI handle + * @tc_bitmap: TC bitmap + * @max_rdmaqs: max RDMA queues array per TC + * + * This function adds/updates the VSI RDMA queues per TC. + */ +int +ice_cfg_vsi_rdma(struct ice_port_info *pi, u16 vsi_handle, u16 tc_bitmap, + u16 *max_rdmaqs) +{ + return ice_status_to_errno(ice_cfg_vsi_qs(pi, vsi_handle, tc_bitmap, + max_rdmaqs, + ICE_SCHED_NODE_OWNER_RDMA)); +} + +/** + * ice_ena_vsi_rdma_qset + * @pi: port information structure + * @vsi_handle: software VSI handle + * @tc: TC number + * @rdma_qset: pointer to RDMA Qset + * @num_qsets: number of RDMA Qsets + * @qset_teid: pointer to Qset node TEIDs + * + * This function adds RDMA Qset + */ +int +ice_ena_vsi_rdma_qset(struct ice_port_info *pi, u16 vsi_handle, u8 tc, + u16 *rdma_qset, u16 num_qsets, u32 *qset_teid) +{ + struct ice_aqc_txsched_elem_data node = { 0 }; + struct ice_aqc_add_rdma_qset_data *buf; + struct ice_sched_node *parent; + enum ice_status status; + struct ice_hw *hw; + u16 i, buf_size; + int ret; + + if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY) + return -EIO; + hw = pi->hw; + + if (!ice_is_vsi_valid(hw, vsi_handle)) + return -EINVAL; + + buf_size = struct_size(buf, rdma_qsets, num_qsets); + buf = kzalloc(buf_size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + mutex_lock(&pi->sched_lock); + + parent = ice_sched_get_free_qparent(pi, vsi_handle, tc, + ICE_SCHED_NODE_OWNER_RDMA); + if (!parent) { + ret = -EINVAL; + goto rdma_error_exit; + } + buf->parent_teid = parent->info.node_teid; + node.parent_teid = parent->info.node_teid; + + buf->num_qsets = cpu_to_le16(num_qsets); + for (i = 0; i < num_qsets; i++) { + buf->rdma_qsets[i].tx_qset_id = cpu_to_le16(rdma_qset[i]); + buf->rdma_qsets[i].info.valid_sections = + ICE_AQC_ELEM_VALID_GENERIC | ICE_AQC_ELEM_VALID_CIR | + ICE_AQC_ELEM_VALID_EIR; + buf->rdma_qsets[i].info.generic = 0; + buf->rdma_qsets[i].info.cir_bw.bw_profile_idx = + cpu_to_le16(ICE_SCHED_DFLT_RL_PROF_ID); + buf->rdma_qsets[i].info.cir_bw.bw_alloc = + cpu_to_le16(ICE_SCHED_DFLT_BW_WT); + buf->rdma_qsets[i].info.eir_bw.bw_profile_idx = + cpu_to_le16(ICE_SCHED_DFLT_RL_PROF_ID); + buf->rdma_qsets[i].info.eir_bw.bw_alloc = + cpu_to_le16(ICE_SCHED_DFLT_BW_WT); + } + ret = ice_aq_add_rdma_qsets(hw, 1, buf, buf_size, NULL); + if (ret) { + ice_debug(hw, ICE_DBG_RDMA, "add RDMA qset failed\n"); + goto rdma_error_exit; + } + node.data.elem_type = ICE_AQC_ELEM_TYPE_LEAF; + for (i = 0; i < num_qsets; i++) { + node.node_teid = buf->rdma_qsets[i].qset_teid; + status = ice_sched_add_node(pi, hw->num_tx_sched_layers - 1, + &node); + if (status) { + ret = ice_status_to_errno(status); + break; + } + qset_teid[i] = le32_to_cpu(node.node_teid); + } +rdma_error_exit: + mutex_unlock(&pi->sched_lock); + kfree(buf); + return ret; +} + +/** + * ice_dis_vsi_rdma_qset - free RDMA resources + * @pi: port_info struct + * @count: number of RDMA Qsets to free + * @qset_teid: TEID of Qset node + * @q_id: list of queue IDs being disabled + */ +int +ice_dis_vsi_rdma_qset(struct ice_port_info *pi, u16 count, u32 *qset_teid, + u16 *q_id) +{ + struct ice_aqc_dis_txq_item *qg_list; + enum ice_status status = 0; + struct ice_hw *hw; + u16 qg_size; + int i; + + if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY) + return -EIO; + + hw = pi->hw; + + qg_size = struct_size(qg_list, q_id, 1); + qg_list = kzalloc(qg_size, GFP_KERNEL); + if (!qg_list) + return -ENOMEM; + + mutex_lock(&pi->sched_lock); + + for (i = 0; i < count; i++) { + struct ice_sched_node *node; + + node = ice_sched_find_node_by_teid(pi->root, qset_teid[i]); + if (!node) + continue; + + qg_list->parent_teid = node->info.parent_teid; + qg_list->num_qs = 1; + qg_list->q_id[0] = + cpu_to_le16(q_id[i] | + ICE_AQC_Q_DIS_BUF_ELEM_TYPE_RDMA_QSET); + + status = ice_aq_dis_lan_txq(hw, 1, qg_list, qg_size, + ICE_NO_RESET, 0, NULL); + if (status) + break; + + ice_free_sched_node(pi, node); + } + + mutex_unlock(&pi->sched_lock); + kfree(qg_list); + return ice_status_to_errno(status); +} + +/** * ice_replay_pre_init - replay pre initialization * @hw: pointer to the HW struct * diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 7a9d2dfb21a2..0fdda597fbc8 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -147,6 +147,15 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr, u16 mem_addr, u8 page, u8 set_page, u8 *data, u8 length, bool write, struct ice_sq_cd *cd); +int +ice_cfg_vsi_rdma(struct ice_port_info *pi, u16 vsi_handle, u16 tc_bitmap, + u16 *max_rdmaqs); +int +ice_ena_vsi_rdma_qset(struct ice_port_info *pi, u16 vsi_handle, u8 tc, + u16 *rdma_qset, u16 num_qsets, u32 *qset_teid); +int +ice_dis_vsi_rdma_qset(struct ice_port_info *pi, u16 count, u32 *qset_teid, + u16 *q_id); enum ice_status ice_dis_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_queues, u16 *q_handle, u16 *q_ids, u32 *q_teids, diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index df02cffdf209..857dc62da7a8 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -275,6 +275,7 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked) struct ice_dcbx_cfg *old_cfg, *curr_cfg; struct device *dev = ice_pf_to_dev(pf); int ret = ICE_DCB_NO_HW_CHG; + struct iidc_event *event; struct ice_vsi *pf_vsi; curr_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; @@ -313,6 +314,15 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked) goto free_cfg; } + /* Notify AUX drivers about impending change to TCs */ + event = kzalloc(sizeof(*event), GFP_KERNEL); + if (!event) + return -ENOMEM; + + set_bit(IIDC_EVENT_BEFORE_TC_CHANGE, event->type); + ice_send_event_to_aux(pf, event); + kfree(event); + /* avoid race conditions by holding the lock while disabling and * re-enabling the VSI */ @@ -640,6 +650,7 @@ static int ice_dcb_noncontig_cfg(struct ice_pf *pf) void ice_pf_dcb_recfg(struct ice_pf *pf) { struct ice_dcbx_cfg *dcbcfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; + struct iidc_event *event; u8 tc_map = 0; int v, ret; @@ -675,6 +686,14 @@ void ice_pf_dcb_recfg(struct ice_pf *pf) if (vsi->type == ICE_VSI_PF) ice_dcbnl_set_all(vsi); } + /* Notify the AUX drivers that TC change is finished */ + event = kzalloc(sizeof(*event), GFP_KERNEL); + if (!event) + return; + + set_bit(IIDC_EVENT_AFTER_TC_CHANGE, event->type); + ice_send_event_to_aux(pf, event); + kfree(event); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index 9b8300d4a267..5386285c39e7 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -111,8 +111,6 @@ #define VPGEN_VFRSTAT_VFRD_M BIT(0) #define VPGEN_VFRTRIG(_VF) (0x00090000 + ((_VF) * 4)) #define VPGEN_VFRTRIG_VFSWR_M BIT(0) -#define PFHMC_ERRORDATA 0x00520500 -#define PFHMC_ERRORINFO 0x00520400 #define GLINT_CTL 0x0016CC54 #define GLINT_CTL_DIS_AUTOMASK_M BIT(0) #define GLINT_CTL_ITR_GRAN_200_S 16 @@ -161,6 +159,7 @@ #define PFINT_OICR_GRST_M BIT(20) #define PFINT_OICR_PCI_EXCEPTION_M BIT(21) #define PFINT_OICR_HMC_ERR_M BIT(26) +#define PFINT_OICR_PE_PUSH_M BIT(27) #define PFINT_OICR_PE_CRITERR_M BIT(28) #define PFINT_OICR_VFLR_M BIT(29) #define PFINT_OICR_SWINT_M BIT(31) diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c new file mode 100644 index 000000000000..1f2afdf6cd48 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_idc.c @@ -0,0 +1,334 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2021, Intel Corporation. */ + +/* Inter-Driver Communication */ +#include "ice.h" +#include "ice_lib.h" +#include "ice_dcb_lib.h" + +/** + * ice_get_auxiliary_drv - retrieve iidc_auxiliary_drv struct + * @pf: pointer to PF struct + * + * This function has to be called with a device_lock on the + * pf->adev.dev to avoid race conditions. + */ +static struct iidc_auxiliary_drv *ice_get_auxiliary_drv(struct ice_pf *pf) +{ + struct auxiliary_device *adev; + + adev = pf->adev; + if (!adev || !adev->dev.driver) + return NULL; + + return container_of(adev->dev.driver, struct iidc_auxiliary_drv, + adrv.driver); +} + +/** + * ice_send_event_to_aux - send event to RDMA AUX driver + * @pf: pointer to PF struct + * @event: event struct + */ +void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_event *event) +{ + struct iidc_auxiliary_drv *iadrv; + + if (!pf->adev) + return; + + device_lock(&pf->adev->dev); + iadrv = ice_get_auxiliary_drv(pf); + if (iadrv && iadrv->event_handler) + iadrv->event_handler(pf, event); + device_unlock(&pf->adev->dev); +} + +/** + * ice_find_vsi - Find the VSI from VSI ID + * @pf: The PF pointer to search in + * @vsi_num: The VSI ID to search for + */ +static struct ice_vsi *ice_find_vsi(struct ice_pf *pf, u16 vsi_num) +{ + int i; + + ice_for_each_vsi(pf, i) + if (pf->vsi[i] && pf->vsi[i]->vsi_num == vsi_num) + return pf->vsi[i]; + return NULL; +} + +/** + * ice_add_rdma_qset - Add Leaf Node for RDMA Qset + * @pf: PF struct + * @qset: Resource to be allocated + */ +int ice_add_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset) +{ + u16 max_rdmaqs[ICE_MAX_TRAFFIC_CLASS]; + struct ice_vsi *vsi; + struct device *dev; + u32 qset_teid; + u16 qs_handle; + int status; + int i; + + if (WARN_ON(!pf || !qset)) + return -EINVAL; + + dev = ice_pf_to_dev(pf); + + if (!test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) + return -EINVAL; + + vsi = ice_get_main_vsi(pf); + if (!vsi) { + dev_err(dev, "RDMA QSet invalid VSI\n"); + return -EINVAL; + } + + ice_for_each_traffic_class(i) + max_rdmaqs[i] = 0; + + max_rdmaqs[qset->tc]++; + qs_handle = qset->qs_handle; + + status = ice_cfg_vsi_rdma(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, + max_rdmaqs); + if (status) { + dev_err(dev, "Failed VSI RDMA Qset config\n"); + return status; + } + + status = ice_ena_vsi_rdma_qset(vsi->port_info, vsi->idx, qset->tc, + &qs_handle, 1, &qset_teid); + if (status) { + dev_err(dev, "Failed VSI RDMA Qset enable\n"); + return status; + } + vsi->qset_handle[qset->tc] = qset->qs_handle; + qset->teid = qset_teid; + + return 0; +} +EXPORT_SYMBOL_GPL(ice_add_rdma_qset); + +/** + * ice_del_rdma_qset - Delete leaf node for RDMA Qset + * @pf: PF struct + * @qset: Resource to be freed + */ +int ice_del_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset) +{ + struct ice_vsi *vsi; + u32 teid; + u16 q_id; + + if (WARN_ON(!pf || !qset)) + return -EINVAL; + + vsi = ice_find_vsi(pf, qset->vport_id); + if (!vsi) { + dev_err(ice_pf_to_dev(pf), "RDMA Invalid VSI\n"); + return -EINVAL; + } + + q_id = qset->qs_handle; + teid = qset->teid; + + vsi->qset_handle[qset->tc] = 0; + + return ice_dis_vsi_rdma_qset(vsi->port_info, 1, &teid, &q_id); +} +EXPORT_SYMBOL_GPL(ice_del_rdma_qset); + +/** + * ice_rdma_request_reset - accept request from RDMA to perform a reset + * @pf: struct for PF + * @reset_type: type of reset + */ +int ice_rdma_request_reset(struct ice_pf *pf, enum iidc_reset_type reset_type) +{ + enum ice_reset_req reset; + + if (WARN_ON(!pf)) + return -EINVAL; + + switch (reset_type) { + case IIDC_PFR: + reset = ICE_RESET_PFR; + break; + case IIDC_CORER: + reset = ICE_RESET_CORER; + break; + case IIDC_GLOBR: + reset = ICE_RESET_GLOBR; + break; + default: + dev_err(ice_pf_to_dev(pf), "incorrect reset request\n"); + return -EINVAL; + } + + return ice_schedule_reset(pf, reset); +} +EXPORT_SYMBOL_GPL(ice_rdma_request_reset); + +/** + * ice_rdma_update_vsi_filter - update main VSI filters for RDMA + * @pf: pointer to struct for PF + * @vsi_id: VSI HW idx to update filter on + * @enable: bool whether to enable or disable filters + */ +int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable) +{ + struct ice_vsi *vsi; + int status; + + if (WARN_ON(!pf)) + return -EINVAL; + + vsi = ice_find_vsi(pf, vsi_id); + if (!vsi) + return -EINVAL; + + status = ice_cfg_rdma_fltr(&pf->hw, vsi->idx, enable); + if (status) { + dev_err(ice_pf_to_dev(pf), "Failed to %sable RDMA filtering\n", + enable ? "en" : "dis"); + } else { + if (enable) + vsi->info.q_opt_flags |= ICE_AQ_VSI_Q_OPT_PE_FLTR_EN; + else + vsi->info.q_opt_flags &= ~ICE_AQ_VSI_Q_OPT_PE_FLTR_EN; + } + + return status; +} +EXPORT_SYMBOL_GPL(ice_rdma_update_vsi_filter); + +/** + * ice_get_qos_params - parse QoS params for RDMA consumption + * @pf: pointer to PF struct + * @qos: set of QoS values + */ +void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos) +{ + struct ice_dcbx_cfg *dcbx_cfg; + unsigned int i; + u32 up2tc; + + dcbx_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; + up2tc = rd32(&pf->hw, PRTDCB_TUP2TC); + + qos->num_tc = ice_dcb_get_num_tc(dcbx_cfg); + for (i = 0; i < IIDC_MAX_USER_PRIORITY; i++) + qos->up2tc[i] = (up2tc >> (i * 3)) & 0x7; + + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) + qos->tc_info[i].rel_bw = dcbx_cfg->etscfg.tcbwtable[i]; +} +EXPORT_SYMBOL_GPL(ice_get_qos_params); + +/** + * ice_reserve_rdma_qvector - Reserve vector resources for RDMA driver + * @pf: board private structure to initialize + */ +static int ice_reserve_rdma_qvector(struct ice_pf *pf) +{ + if (test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) { + int index; + + index = ice_get_res(pf, pf->irq_tracker, pf->num_rdma_msix, + ICE_RES_RDMA_VEC_ID); + if (index < 0) + return index; + pf->num_avail_sw_msix -= pf->num_rdma_msix; + pf->rdma_base_vector = (u16)index; + } + return 0; +} + +/** + * ice_adev_release - function to be mapped to AUX dev's release op + * @dev: pointer to device to free + */ +static void ice_adev_release(struct device *dev) +{ + struct iidc_auxiliary_dev *iadev; + + iadev = container_of(dev, struct iidc_auxiliary_dev, adev.dev); + kfree(iadev); +} + +/** + * ice_plug_aux_dev - allocate and register AUX device + * @pf: pointer to pf struct + */ +int ice_plug_aux_dev(struct ice_pf *pf) +{ + struct iidc_auxiliary_dev *iadev; + struct auxiliary_device *adev; + int ret; + + iadev = kzalloc(sizeof(*iadev), GFP_KERNEL); + if (!iadev) + return -ENOMEM; + + adev = &iadev->adev; + pf->adev = adev; + iadev->pf = pf; + + adev->id = pf->aux_idx; + adev->dev.release = ice_adev_release; + adev->dev.parent = &pf->pdev->dev; + adev->name = IIDC_RDMA_ROCE_NAME; + + ret = auxiliary_device_init(adev); + if (ret) { + pf->adev = NULL; + kfree(iadev); + return ret; + } + + ret = auxiliary_device_add(adev); + if (ret) { + pf->adev = NULL; + auxiliary_device_uninit(adev); + return ret; + } + + return 0; +} + +/* ice_unplug_aux_dev - unregister and free AUX device + * @pf: pointer to pf struct + */ +void ice_unplug_aux_dev(struct ice_pf *pf) +{ + if (!pf->adev) + return; + + auxiliary_device_delete(pf->adev); + auxiliary_device_uninit(pf->adev); + pf->adev = NULL; +} + +/** + * ice_init_rdma - initializes PF for RDMA use + * @pf: ptr to ice_pf + */ +int ice_init_rdma(struct ice_pf *pf) +{ + struct device *dev = &pf->pdev->dev; + int ret; + + /* Reserve vector resources */ + ret = ice_reserve_rdma_qvector(pf); + if (ret < 0) { + dev_err(dev, "failed to reserve vectors for RDMA\n"); + return ret; + } + + return ice_plug_aux_dev(pf); +} diff --git a/drivers/net/ethernet/intel/ice/ice_idc_int.h b/drivers/net/ethernet/intel/ice/ice_idc_int.h new file mode 100644 index 000000000000..b7796b8aecbd --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_idc_int.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2021, Intel Corporation. */ + +#ifndef _ICE_IDC_INT_H_ +#define _ICE_IDC_INT_H_ + +#include <linux/net/intel/iidc.h> +#include "ice.h" + +struct ice_pf; + +void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_event *event); + +#endif /* !_ICE_IDC_INT_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index 4599fc3b4ed8..37c18c66b5c7 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -172,6 +172,7 @@ ice_lag_link(struct ice_lag *lag, struct netdev_notifier_changeupper_info *info) } ice_clear_sriov_cap(pf); + ice_clear_rdma_cap(pf); lag->bonded = true; lag->role = ICE_LAG_UNSET; @@ -222,6 +223,7 @@ ice_lag_unlink(struct ice_lag *lag, } ice_set_sriov_cap(pf); + ice_set_rdma_cap(pf); lag->bonded = false; lag->role = ICE_LAG_NONE; } diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index d70ee573fde5..89bb573e5bcd 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -629,6 +629,17 @@ bool ice_is_safe_mode(struct ice_pf *pf) } /** + * ice_is_aux_ena + * @pf: pointer to the PF struct + * + * returns true if AUX devices/drivers are supported, false otherwise + */ +bool ice_is_aux_ena(struct ice_pf *pf) +{ + return test_bit(ICE_FLAG_AUX_ENA, pf->flags); +} + +/** * ice_vsi_clean_rss_flow_fld - Delete RSS configuration * @vsi: the VSI being cleaned up * diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index 511c2316c40c..5ec857f71459 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -102,7 +102,7 @@ enum ice_status ice_vsi_cfg_mac_fltr(struct ice_vsi *vsi, const u8 *macaddr, bool set); bool ice_is_safe_mode(struct ice_pf *pf); - +bool ice_is_aux_ena(struct ice_pf *pf); bool ice_is_dflt_vsi_in_use(struct ice_sw *sw); bool ice_is_vsi_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 4ee85a217c6f..254cfc14d6b4 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -35,6 +35,8 @@ MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all), hw debug_mask (0x8XXXX MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all)"); #endif /* !CONFIG_DYNAMIC_DEBUG */ +static DEFINE_IDA(ice_aux_ida); + static struct workqueue_struct *ice_wq; static const struct net_device_ops ice_netdev_safe_mode_ops; static const struct net_device_ops ice_netdev_ops; @@ -454,6 +456,8 @@ ice_prepare_for_reset(struct ice_pf *pf) if (test_bit(ICE_PREPARED_FOR_RESET, pf->state)) return; + ice_unplug_aux_dev(pf); + /* Notify VFs of impending reset */ if (ice_check_sq_alive(hw, &hw->mailboxq)) ice_vc_notify_reset(pf); @@ -2118,6 +2122,8 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset) return -EBUSY; } + ice_unplug_aux_dev(pf); + switch (reset) { case ICE_RESET_PFR: set_bit(ICE_PFR_REQ, pf->state); @@ -2608,6 +2614,7 @@ static void ice_ena_misc_vector(struct ice_pf *pf) PFINT_OICR_PCI_EXCEPTION_M | PFINT_OICR_VFLR_M | PFINT_OICR_HMC_ERR_M | + PFINT_OICR_PE_PUSH_M | PFINT_OICR_PE_CRITERR_M); wr32(hw, PFINT_OICR_ENA, val); @@ -2678,8 +2685,6 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) /* If a reset cycle isn't already in progress, we set a bit in * pf->state so that the service task can start a reset/rebuild. - * We also make note of which reset happened so that peer - * devices/drivers can be informed. */ if (!test_and_set_bit(ICE_RESET_OICR_RECV, pf->state)) { if (reset == ICE_RESET_CORER) @@ -2706,11 +2711,19 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) } } - if (oicr & PFINT_OICR_HMC_ERR_M) { - ena_mask &= ~PFINT_OICR_HMC_ERR_M; - dev_dbg(dev, "HMC Error interrupt - info 0x%x, data 0x%x\n", - rd32(hw, PFHMC_ERRORINFO), - rd32(hw, PFHMC_ERRORDATA)); +#define ICE_AUX_CRIT_ERR (PFINT_OICR_PE_CRITERR_M | PFINT_OICR_HMC_ERR_M | PFINT_OICR_PE_PUSH_M) + if (oicr & ICE_AUX_CRIT_ERR) { + struct iidc_event *event; + + ena_mask &= ~ICE_AUX_CRIT_ERR; + event = kzalloc(sizeof(*event), GFP_KERNEL); + if (event) { + set_bit(IIDC_EVENT_CRIT_ERR, event->type); + /* report the entire OICR value to AUX driver */ + event->reg = oicr; + ice_send_event_to_aux(pf, event); + kfree(event); + } } /* Report any remaining unexpected interrupts */ @@ -2720,8 +2733,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) /* If a critical error is pending there is no choice but to * reset the device. */ - if (oicr & (PFINT_OICR_PE_CRITERR_M | - PFINT_OICR_PCI_EXCEPTION_M | + if (oicr & (PFINT_OICR_PCI_EXCEPTION_M | PFINT_OICR_ECC_ERR_M)) { set_bit(ICE_PFR_REQ, pf->state); ice_service_task_schedule(pf); @@ -3276,6 +3288,12 @@ static void ice_set_pf_caps(struct ice_pf *pf) { struct ice_hw_func_caps *func_caps = &pf->hw.func_caps; + clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); + clear_bit(ICE_FLAG_AUX_ENA, pf->flags); + if (func_caps->common_cap.rdma) { + set_bit(ICE_FLAG_RDMA_ENA, pf->flags); + set_bit(ICE_FLAG_AUX_ENA, pf->flags); + } clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags); if (func_caps->common_cap.dcb) set_bit(ICE_FLAG_DCB_CAPABLE, pf->flags); @@ -3355,11 +3373,12 @@ static int ice_init_pf(struct ice_pf *pf) */ static int ice_ena_msix_range(struct ice_pf *pf) { - int v_left, v_actual, v_other, v_budget = 0; + int num_cpus, v_left, v_actual, v_other, v_budget = 0; struct device *dev = ice_pf_to_dev(pf); int needed, err, i; v_left = pf->hw.func_caps.common_cap.num_msix_vectors; + num_cpus = num_online_cpus(); /* reserve for LAN miscellaneous handler */ needed = ICE_MIN_LAN_OICR_MSIX; @@ -3381,13 +3400,23 @@ static int ice_ena_msix_range(struct ice_pf *pf) v_other = v_budget; /* reserve vectors for LAN traffic */ - needed = min_t(int, num_online_cpus(), v_left); + needed = num_cpus; if (v_left < needed) goto no_hw_vecs_left_err; pf->num_lan_msix = needed; v_budget += needed; v_left -= needed; + /* reserve vectors for RDMA auxiliary driver */ + if (test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) { + needed = num_cpus + ICE_RDMA_NUM_AEQ_MSIX; + if (v_left < needed) + goto no_hw_vecs_left_err; + pf->num_rdma_msix = needed; + v_budget += needed; + v_left -= needed; + } + pf->msix_entries = devm_kcalloc(dev, v_budget, sizeof(*pf->msix_entries), GFP_KERNEL); if (!pf->msix_entries) { @@ -3417,16 +3446,46 @@ static int ice_ena_msix_range(struct ice_pf *pf) err = -ERANGE; goto msix_err; } else { - int v_traffic = v_actual - v_other; + int v_remain = v_actual - v_other; + int v_rdma = 0, v_min_rdma = 0; + + if (test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) { + /* Need at least 1 interrupt in addition to + * AEQ MSIX + */ + v_rdma = ICE_RDMA_NUM_AEQ_MSIX + 1; + v_min_rdma = ICE_MIN_RDMA_MSIX; + } if (v_actual == ICE_MIN_MSIX || - v_traffic < ICE_MIN_LAN_TXRX_MSIX) + v_remain < ICE_MIN_LAN_TXRX_MSIX + v_min_rdma) { + dev_warn(dev, "Not enough MSI-X vectors to support RDMA.\n"); + clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); + + pf->num_rdma_msix = 0; pf->num_lan_msix = ICE_MIN_LAN_TXRX_MSIX; - else - pf->num_lan_msix = v_traffic; + } else if ((v_remain < ICE_MIN_LAN_TXRX_MSIX + v_rdma) || + (v_remain - v_rdma < v_rdma)) { + /* Support minimum RDMA and give remaining + * vectors to LAN MSIX + */ + pf->num_rdma_msix = v_min_rdma; + pf->num_lan_msix = v_remain - v_min_rdma; + } else { + /* Split remaining MSIX with RDMA after + * accounting for AEQ MSIX + */ + pf->num_rdma_msix = (v_remain - ICE_RDMA_NUM_AEQ_MSIX) / 2 + + ICE_RDMA_NUM_AEQ_MSIX; + pf->num_lan_msix = v_remain - pf->num_rdma_msix; + } dev_notice(dev, "Enabled %d MSI-X vectors for LAN traffic.\n", pf->num_lan_msix); + + if (test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) + dev_notice(dev, "Enabled %d MSI-X vectors for RDMA.\n", + pf->num_rdma_msix); } } @@ -3441,6 +3500,7 @@ no_hw_vecs_left_err: needed, v_left); err = -ERANGE; exit_err: + pf->num_rdma_msix = 0; pf->num_lan_msix = 0; return err; } @@ -4268,8 +4328,29 @@ probe_done: /* ready to go, so clear down state bit */ clear_bit(ICE_DOWN, pf->state); + if (ice_is_aux_ena(pf)) { + pf->aux_idx = ida_alloc(&ice_aux_ida, GFP_KERNEL); + if (pf->aux_idx < 0) { + dev_err(dev, "Failed to allocate device ID for AUX driver\n"); + err = -ENOMEM; + goto err_netdev_reg; + } + + err = ice_init_rdma(pf); + if (err) { + dev_err(dev, "Failed to initialize RDMA: %d\n", err); + err = -EIO; + goto err_init_aux_unroll; + } + } else { + dev_warn(dev, "RDMA is not supported on this device\n"); + } + return 0; +err_init_aux_unroll: + pf->adev = NULL; + ida_free(&ice_aux_ida, pf->aux_idx); err_netdev_reg: err_send_version_unroll: ice_vsi_release_all(pf); @@ -4379,10 +4460,12 @@ static void ice_remove(struct pci_dev *pdev) ice_free_vfs(pf); } - set_bit(ICE_DOWN, pf->state); ice_service_task_stop(pf); ice_aq_cancel_waiting_tasks(pf); + ice_unplug_aux_dev(pf); + ida_free(&ice_aux_ida, pf->aux_idx); + set_bit(ICE_DOWN, pf->state); mutex_destroy(&(&pf->hw)->fdir_fltr_lock); ice_deinit_lag(pf); @@ -4538,6 +4621,8 @@ static int __maybe_unused ice_suspend(struct device *dev) */ disabled = ice_service_task_stop(pf); + ice_unplug_aux_dev(pf); + /* Already suspended?, then there is nothing to do */ if (test_and_set_bit(ICE_SUSPENDED, pf->state)) { if (!disabled) @@ -6208,6 +6293,8 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) /* if we get here, reset flow is successful */ clear_bit(ICE_RESET_FAILED, pf->state); + + ice_plug_aux_dev(pf); return; err_vsi_rebuild: @@ -6246,7 +6333,9 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; + struct iidc_event *event; u8 count = 0; + int err = 0; if (new_mtu == (int)netdev->mtu) { netdev_warn(netdev, "MTU is already %u\n", netdev->mtu); @@ -6279,27 +6368,38 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) return -EBUSY; } + event = kzalloc(sizeof(*event), GFP_KERNEL); + if (!event) + return -ENOMEM; + + set_bit(IIDC_EVENT_BEFORE_MTU_CHANGE, event->type); + ice_send_event_to_aux(pf, event); + clear_bit(IIDC_EVENT_BEFORE_MTU_CHANGE, event->type); + netdev->mtu = (unsigned int)new_mtu; /* if VSI is up, bring it down and then back up */ if (!test_and_set_bit(ICE_VSI_DOWN, vsi->state)) { - int err; - err = ice_down(vsi); if (err) { netdev_err(netdev, "change MTU if_down err %d\n", err); - return err; + goto event_after; } err = ice_up(vsi); if (err) { netdev_err(netdev, "change MTU if_up err %d\n", err); - return err; + goto event_after; } } netdev_dbg(netdev, "changed MTU to %d\n", new_mtu); - return 0; +event_after: + set_bit(IIDC_EVENT_AFTER_MTU_CHANGE, event->type); + ice_send_event_to_aux(pf, event); + kfree(event); + + return err; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index 2f097637e405..a17e24e54cf3 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -596,6 +596,50 @@ ice_alloc_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs) } /** + * ice_alloc_rdma_q_ctx - allocate RDMA queue contexts for the given VSI and TC + * @hw: pointer to the HW struct + * @vsi_handle: VSI handle + * @tc: TC number + * @new_numqs: number of queues + */ +static enum ice_status +ice_alloc_rdma_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs) +{ + struct ice_vsi_ctx *vsi_ctx; + struct ice_q_ctx *q_ctx; + + vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle); + if (!vsi_ctx) + return ICE_ERR_PARAM; + /* allocate RDMA queue contexts */ + if (!vsi_ctx->rdma_q_ctx[tc]) { + vsi_ctx->rdma_q_ctx[tc] = devm_kcalloc(ice_hw_to_dev(hw), + new_numqs, + sizeof(*q_ctx), + GFP_KERNEL); + if (!vsi_ctx->rdma_q_ctx[tc]) + return ICE_ERR_NO_MEMORY; + vsi_ctx->num_rdma_q_entries[tc] = new_numqs; + return 0; + } + /* num queues are increased, update the queue contexts */ + if (new_numqs > vsi_ctx->num_rdma_q_entries[tc]) { + u16 prev_num = vsi_ctx->num_rdma_q_entries[tc]; + + q_ctx = devm_kcalloc(ice_hw_to_dev(hw), new_numqs, + sizeof(*q_ctx), GFP_KERNEL); + if (!q_ctx) + return ICE_ERR_NO_MEMORY; + memcpy(q_ctx, vsi_ctx->rdma_q_ctx[tc], + prev_num * sizeof(*q_ctx)); + devm_kfree(ice_hw_to_dev(hw), vsi_ctx->rdma_q_ctx[tc]); + vsi_ctx->rdma_q_ctx[tc] = q_ctx; + vsi_ctx->num_rdma_q_entries[tc] = new_numqs; + } + return 0; +} + +/** * ice_aq_rl_profile - performs a rate limiting task * @hw: pointer to the HW struct * @opcode: opcode for add, query, or remove profile(s) @@ -1774,13 +1818,22 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle, if (!vsi_ctx) return ICE_ERR_PARAM; - prev_numqs = vsi_ctx->sched.max_lanq[tc]; + if (owner == ICE_SCHED_NODE_OWNER_LAN) + prev_numqs = vsi_ctx->sched.max_lanq[tc]; + else + prev_numqs = vsi_ctx->sched.max_rdmaq[tc]; /* num queues are not changed or less than the previous number */ if (new_numqs <= prev_numqs) return status; - status = ice_alloc_lan_q_ctx(hw, vsi_handle, tc, new_numqs); - if (status) - return status; + if (owner == ICE_SCHED_NODE_OWNER_LAN) { + status = ice_alloc_lan_q_ctx(hw, vsi_handle, tc, new_numqs); + if (status) + return status; + } else { + status = ice_alloc_rdma_q_ctx(hw, vsi_handle, tc, new_numqs); + if (status) + return status; + } if (new_numqs) ice_sched_calc_vsi_child_nodes(hw, new_numqs, new_num_nodes); @@ -1795,7 +1848,10 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle, new_num_nodes, owner); if (status) return status; - vsi_ctx->sched.max_lanq[tc] = new_numqs; + if (owner == ICE_SCHED_NODE_OWNER_LAN) + vsi_ctx->sched.max_lanq[tc] = new_numqs; + else + vsi_ctx->sched.max_rdmaq[tc] = new_numqs; return 0; } @@ -1861,6 +1917,7 @@ ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs, * recreate the child nodes all the time in these cases. */ vsi_ctx->sched.max_lanq[tc] = 0; + vsi_ctx->sched.max_rdmaq[tc] = 0; } /* update the VSI child nodes */ @@ -1990,6 +2047,8 @@ ice_sched_rm_vsi_cfg(struct ice_port_info *pi, u16 vsi_handle, u8 owner) } if (owner == ICE_SCHED_NODE_OWNER_LAN) vsi_ctx->sched.max_lanq[i] = 0; + else + vsi_ctx->sched.max_rdmaq[i] = 0; } status = 0; diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 357d3073d814..3b6c1420aa7b 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2018, Intel Corporation. */ +#include "ice_lib.h" #include "ice_switch.h" #define ICE_ETH_DA_OFFSET 0 @@ -302,6 +303,10 @@ static void ice_clear_vsi_q_ctx(struct ice_hw *hw, u16 vsi_handle) devm_kfree(ice_hw_to_dev(hw), vsi->lan_q_ctx[i]); vsi->lan_q_ctx[i] = NULL; } + if (vsi->rdma_q_ctx[i]) { + devm_kfree(ice_hw_to_dev(hw), vsi->rdma_q_ctx[i]); + vsi->rdma_q_ctx[i] = NULL; + } } } @@ -423,6 +428,29 @@ ice_update_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, } /** + * ice_cfg_rdma_fltr - enable/disable RDMA filtering on VSI + * @hw: pointer to HW struct + * @vsi_handle: VSI SW index + * @enable: boolean for enable/disable + */ +int +ice_cfg_rdma_fltr(struct ice_hw *hw, u16 vsi_handle, bool enable) +{ + struct ice_vsi_ctx *ctx; + + ctx = ice_get_vsi_ctx(hw, vsi_handle); + if (!ctx) + return -EIO; + + if (enable) + ctx->info.q_opt_flags |= ICE_AQ_VSI_Q_OPT_PE_FLTR_EN; + else + ctx->info.q_opt_flags &= ~ICE_AQ_VSI_Q_OPT_PE_FLTR_EN; + + return ice_status_to_errno(ice_update_vsi(hw, vsi_handle, ctx, NULL)); +} + +/** * ice_aq_alloc_free_vsi_list * @hw: pointer to the HW struct * @vsi_list_id: VSI list ID returned or used for lookup diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index 8b4f9d35c860..6bb7358ff67b 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -26,6 +26,8 @@ struct ice_vsi_ctx { u8 vf_num; u16 num_lan_q_entries[ICE_MAX_TRAFFIC_CLASS]; struct ice_q_ctx *lan_q_ctx[ICE_MAX_TRAFFIC_CLASS]; + u16 num_rdma_q_entries[ICE_MAX_TRAFFIC_CLASS]; + struct ice_q_ctx *rdma_q_ctx[ICE_MAX_TRAFFIC_CLASS]; }; enum ice_sw_fwd_act_type { @@ -223,6 +225,8 @@ enum ice_status ice_add_eth_mac(struct ice_hw *hw, struct list_head *em_list); enum ice_status ice_remove_eth_mac(struct ice_hw *hw, struct list_head *em_list); +int +ice_cfg_rdma_fltr(struct ice_hw *hw, u16 vsi_handle, bool enable); void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_handle); enum ice_status ice_add_vlan(struct ice_hw *hw, struct list_head *m_list); diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 4474dd6a7ba1..c580b87c76ee 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -45,6 +45,7 @@ static inline u32 ice_round_to_num(u32 N, u32 R) #define ICE_DBG_FLOW BIT_ULL(9) #define ICE_DBG_SW BIT_ULL(13) #define ICE_DBG_SCHED BIT_ULL(14) +#define ICE_DBG_RDMA BIT_ULL(15) #define ICE_DBG_PKG BIT_ULL(16) #define ICE_DBG_RES BIT_ULL(17) #define ICE_DBG_AQ_MSG BIT_ULL(24) @@ -262,6 +263,7 @@ struct ice_hw_common_caps { u8 rss_table_entry_width; /* RSS Entry width in bits */ u8 dcb; + u8 rdma; bool nvm_update_pending_nvm; bool nvm_update_pending_orom; @@ -440,6 +442,7 @@ struct ice_sched_node { u8 tc_num; u8 owner; #define ICE_SCHED_NODE_OWNER_LAN 0 +#define ICE_SCHED_NODE_OWNER_RDMA 2 }; /* Access Macros for Tx Sched Elements data */ @@ -511,6 +514,7 @@ struct ice_sched_vsi_info { struct ice_sched_node *ag_node[ICE_MAX_TRAFFIC_CLASS]; struct list_head list_entry; u16 max_lanq[ICE_MAX_TRAFFIC_CLASS]; + u16 max_rdmaq[ICE_MAX_TRAFFIC_CLASS]; }; /* driver defines the policy */ diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c index 50863fd87d53..cbe92fd23a70 100644 --- a/drivers/net/ethernet/intel/igb/e1000_82575.c +++ b/drivers/net/ethernet/intel/igb/e1000_82575.c @@ -2756,6 +2756,7 @@ out: return ret_val; } +#ifdef CONFIG_IGB_HWMON static const u8 e1000_emc_temp_data[4] = { E1000_EMC_INTERNAL_DATA, E1000_EMC_DIODE1_DATA, @@ -2769,7 +2770,6 @@ static const u8 e1000_emc_therm_limit[4] = { E1000_EMC_DIODE3_THERM_LIMIT }; -#ifdef CONFIG_IGB_HWMON /** * igb_get_thermal_sensor_data_generic - Gathers thermal sensor data * @hw: pointer to hardware structure diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 7545da216d8b..636a1b1fb7e1 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -831,7 +831,7 @@ static int igb_set_eeprom(struct net_device *netdev, memcpy(ptr, bytes, eeprom->len); for (i = 0; i < last_word - first_word + 1; i++) - eeprom_buff[i] = cpu_to_le16(eeprom_buff[i]); + cpu_to_le16s(&eeprom_buff[i]); ret_val = hw->nvm.ops.write(hw, first_word, last_word - first_word + 1, eeprom_buff); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index b2a042f825ff..5db303d64d14 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -356,7 +356,7 @@ static void igb_dump(struct igb_adapter *adapter) struct igb_reg_info *reginfo; struct igb_ring *tx_ring; union e1000_adv_tx_desc *tx_desc; - struct my_u0 { u64 a; u64 b; } *u0; + struct my_u0 { __le64 a; __le64 b; } *u0; struct igb_ring *rx_ring; union e1000_adv_rx_desc *rx_desc; u32 staterr; @@ -2643,7 +2643,8 @@ static int igb_parse_cls_flower(struct igb_adapter *adapter, } input->filter.match_flags |= IGB_FILTER_FLAG_VLAN_TCI; - input->filter.vlan_tci = match.key->vlan_priority; + input->filter.vlan_tci = + (__force __be16)match.key->vlan_priority; } } @@ -6275,12 +6276,12 @@ int igb_xmit_xdp_ring(struct igb_adapter *adapter, cmd_type |= len | IGB_TXD_DCMD; tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); - olinfo_status = cpu_to_le32(len << E1000_ADVTXD_PAYLEN_SHIFT); + olinfo_status = len << E1000_ADVTXD_PAYLEN_SHIFT; /* 82575 requires a unique index per ring */ if (test_bit(IGB_RING_FLAG_TX_CTX_IDX, &tx_ring->flags)) olinfo_status |= tx_ring->reg_idx << 4; - tx_desc->read.olinfo_status = olinfo_status; + tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); netdev_tx_sent_queue(txring_txq(tx_ring), tx_buffer->bytecount); @@ -8592,7 +8593,7 @@ static void igb_process_skb_fields(struct igb_ring *rx_ring, if (igb_test_staterr(rx_desc, E1000_RXDEXT_STATERR_LB) && test_bit(IGB_RING_FLAG_RX_LB_VLAN_BSWAP, &rx_ring->flags)) - vid = be16_to_cpu(rx_desc->wb.upper.vlan); + vid = be16_to_cpu((__force __be16)rx_desc->wb.upper.vlan); else vid = le16_to_cpu(rx_desc->wb.upper.vlan); diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index d68cd4466a54..0011b15e678c 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -1131,12 +1131,12 @@ static int igb_ptp_set_timestamp_mode(struct igb_adapter *adapter, | E1000_FTQF_MASK); /* mask all inputs */ ftqf &= ~E1000_FTQF_MASK_PROTO_BP; /* enable protocol check */ - wr32(E1000_IMIR(3), htons(PTP_EV_PORT)); + wr32(E1000_IMIR(3), (__force unsigned int)htons(PTP_EV_PORT)); wr32(E1000_IMIREXT(3), (E1000_IMIREXT_SIZE_BP | E1000_IMIREXT_CTRL_BP)); if (hw->mac.type == e1000_82576) { /* enable source port check */ - wr32(E1000_SPQF(3), htons(PTP_EV_PORT)); + wr32(E1000_SPQF(3), (__force unsigned int)htons(PTP_EV_PORT)); ftqf &= ~E1000_FTQF_MASK_SOURCE_PORT_BP; } wr32(E1000_FTQF(3), ftqf); diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index fb3fbcb13331..1bbe9862a758 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -83,14 +83,14 @@ static int igbvf_desc_unused(struct igbvf_ring *ring) static void igbvf_receive_skb(struct igbvf_adapter *adapter, struct net_device *netdev, struct sk_buff *skb, - u32 status, u16 vlan) + u32 status, __le16 vlan) { u16 vid; if (status & E1000_RXD_STAT_VP) { if ((adapter->flags & IGBVF_FLAG_RX_LB_VLAN_BSWAP) && (status & E1000_RXDEXT_STATERR_LB)) - vid = be16_to_cpu(vlan) & E1000_RXD_SPC_VLAN_MASK; + vid = be16_to_cpu((__force __be16)vlan) & E1000_RXD_SPC_VLAN_MASK; else vid = le16_to_cpu(vlan) & E1000_RXD_SPC_VLAN_MASK; if (test_bit(vid, adapter->active_vlans)) @@ -2056,7 +2056,7 @@ static int igbvf_tso(struct igbvf_ring *tx_ring, /* remove payload length from inner checksum */ paylen = skb->len - l4_offset; - csum_replace_by_diff(&l4.tcp->check, htonl(paylen)); + csum_replace_by_diff(&l4.tcp->check, (__force __wsum)htonl(paylen)); /* MSS L4LEN IDX */ mss_l4len_idx = (*hdr_len - l4_offset) << E1000_ADVTXD_L4LEN_SHIFT; diff --git a/drivers/net/ethernet/intel/igbvf/vf.h b/drivers/net/ethernet/intel/igbvf/vf.h index c71b0d7dbcee..ba9bb3132d5d 100644 --- a/drivers/net/ethernet/intel/igbvf/vf.h +++ b/drivers/net/ethernet/intel/igbvf/vf.h @@ -35,31 +35,31 @@ struct e1000_hw; /* Receive Descriptor - Advanced */ union e1000_adv_rx_desc { struct { - u64 pkt_addr; /* Packet buffer address */ - u64 hdr_addr; /* Header buffer address */ + __le64 pkt_addr; /* Packet buffer address */ + __le64 hdr_addr; /* Header buffer address */ } read; struct { struct { union { - u32 data; + __le32 data; struct { - u16 pkt_info; /* RSS/Packet type */ + __le16 pkt_info; /* RSS/Packet type */ /* Split Header, hdr buffer length */ - u16 hdr_info; + __le16 hdr_info; } hs_rss; } lo_dword; union { - u32 rss; /* RSS Hash */ + __le32 rss; /* RSS Hash */ struct { - u16 ip_id; /* IP id */ - u16 csum; /* Packet Checksum */ + __le16 ip_id; /* IP id */ + __le16 csum; /* Packet Checksum */ } csum_ip; } hi_dword; } lower; struct { - u32 status_error; /* ext status/error */ - u16 length; /* Packet length */ - u16 vlan; /* VLAN tag */ + __le32 status_error; /* ext status/error */ + __le16 length; /* Packet length */ + __le16 vlan; /* VLAN tag */ } upper; } wb; /* writeback */ }; @@ -70,14 +70,14 @@ union e1000_adv_rx_desc { /* Transmit Descriptor - Advanced */ union e1000_adv_tx_desc { struct { - u64 buffer_addr; /* Address of descriptor's data buf */ - u32 cmd_type_len; - u32 olinfo_status; + __le64 buffer_addr; /* Address of descriptor's data buf */ + __le32 cmd_type_len; + __le32 olinfo_status; } read; struct { - u64 rsvd; /* Reserved */ - u32 nxtseq_seed; - u32 status; + __le64 rsvd; /* Reserved */ + __le32 nxtseq_seed; + __le32 status; } wb; }; @@ -94,10 +94,10 @@ union e1000_adv_tx_desc { /* Context descriptors */ struct e1000_adv_tx_context_desc { - u32 vlan_macip_lens; - u32 seqnum_seed; - u32 type_tucmd_mlhl; - u32 mss_l4len_idx; + __le32 vlan_macip_lens; + __le32 seqnum_seed; + __le32 type_tucmd_mlhl; + __le32 mss_l4len_idx; }; #define E1000_ADVTXD_MACLEN_SHIFT 9 /* Adv ctxt desc mac len shift */ diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 25871351730b..9e0bbb2e55e3 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -118,6 +118,7 @@ struct igc_ring { }; struct xdp_rxq_info xdp_rxq; + struct xsk_buff_pool *xsk_pool; } ____cacheline_internodealigned_in_smp; /* Board specific private data structure */ @@ -255,6 +256,11 @@ bool igc_has_link(struct igc_adapter *adapter); void igc_reset(struct igc_adapter *adapter); int igc_set_spd_dplx(struct igc_adapter *adapter, u32 spd, u8 dplx); void igc_update_stats(struct igc_adapter *adapter); +void igc_disable_rx_ring(struct igc_ring *ring); +void igc_enable_rx_ring(struct igc_ring *ring); +void igc_disable_tx_ring(struct igc_ring *ring); +void igc_enable_tx_ring(struct igc_ring *ring); +int igc_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags); /* igc_dump declarations */ void igc_rings_dump(struct igc_adapter *adapter); @@ -366,6 +372,7 @@ extern char igc_driver_name[]; /* VLAN info */ #define IGC_TX_FLAGS_VLAN_MASK 0xffff0000 +#define IGC_TX_FLAGS_VLAN_SHIFT 16 /* igc_test_staterr - tests bits within Rx descriptor status and error fields */ static inline __le32 igc_test_staterr(union igc_adv_rx_desc *rx_desc, @@ -390,8 +397,6 @@ enum igc_tx_flags { /* olinfo flags */ IGC_TX_FLAGS_IPV4 = 0x10, IGC_TX_FLAGS_CSUM = 0x20, - - IGC_TX_FLAGS_XDP = 0x100, }; enum igc_boards { @@ -408,12 +413,19 @@ enum igc_boards { #define TXD_USE_COUNT(S) DIV_ROUND_UP((S), IGC_MAX_DATA_PER_TXD) #define DESC_NEEDED (MAX_SKB_FRAGS + 4) +enum igc_tx_buffer_type { + IGC_TX_BUFFER_TYPE_SKB, + IGC_TX_BUFFER_TYPE_XDP, + IGC_TX_BUFFER_TYPE_XSK, +}; + /* wrapper around a pointer to a socket buffer, * so a DMA handle can be stored along with the buffer */ struct igc_tx_buffer { union igc_adv_tx_desc *next_to_watch; unsigned long time_stamp; + enum igc_tx_buffer_type type; union { struct sk_buff *skb; struct xdp_frame *xdpf; @@ -428,14 +440,19 @@ struct igc_tx_buffer { }; struct igc_rx_buffer { - dma_addr_t dma; - struct page *page; + union { + struct { + dma_addr_t dma; + struct page *page; #if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536) - __u32 page_offset; + __u32 page_offset; #else - __u16 page_offset; + __u16 page_offset; #endif - __u16 pagecnt_bias; + __u16 pagecnt_bias; + }; + struct xdp_buff *xdp; + }; }; struct igc_q_vector { @@ -521,7 +538,8 @@ enum igc_ring_flags_t { IGC_RING_FLAG_RX_SCTP_CSUM, IGC_RING_FLAG_RX_LB_VLAN_BSWAP, IGC_RING_FLAG_TX_CTX_IDX, - IGC_RING_FLAG_TX_DETECT_HANG + IGC_RING_FLAG_TX_DETECT_HANG, + IGC_RING_FLAG_AF_XDP_ZC, }; #define ring_uses_large_buffer(ring) \ diff --git a/drivers/net/ethernet/intel/igc/igc_base.h b/drivers/net/ethernet/intel/igc/igc_base.h index ea627ce52525..ce530f5fd7bd 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.h +++ b/drivers/net/ethernet/intel/igc/igc_base.h @@ -78,9 +78,11 @@ union igc_adv_rx_desc { /* Additional Transmit Descriptor Control definitions */ #define IGC_TXDCTL_QUEUE_ENABLE 0x02000000 /* Ena specific Tx Queue */ +#define IGC_TXDCTL_SWFLUSH 0x04000000 /* Transmit Software Flush */ /* Additional Receive Descriptor Control definitions */ #define IGC_RXDCTL_QUEUE_ENABLE 0x02000000 /* Ena specific Rx Queue */ +#define IGC_RXDCTL_SWFLUSH 0x04000000 /* Receive Software Flush */ /* SRRCTL bit definitions */ #define IGC_SRRCTL_BSIZEPKT_SHIFT 10 /* Shift _right_ */ diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index 0103dda32f39..c3a5a5518790 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -94,12 +94,13 @@ #define IGC_CTRL_SLU 0x00000040 /* Set link up (Force Link) */ #define IGC_CTRL_FRCSPD 0x00000800 /* Force Speed */ #define IGC_CTRL_FRCDPX 0x00001000 /* Force Duplex */ +#define IGC_CTRL_VME 0x40000000 /* IEEE VLAN mode enable */ #define IGC_CTRL_RFCE 0x08000000 /* Receive Flow Control enable */ #define IGC_CTRL_TFCE 0x10000000 /* Transmit flow control enable */ -#define IGC_CTRL_SDP0_DIR 0x00400000 /* SDP0 Data direction */ -#define IGC_CTRL_SDP1_DIR 0x00800000 /* SDP1 Data direction */ +#define IGC_CTRL_SDP0_DIR 0x00400000 /* SDP0 Data direction */ +#define IGC_CTRL_SDP1_DIR 0x00800000 /* SDP1 Data direction */ /* As per the EAS the maximum supported size is 9.5KB (9728 bytes) */ #define MAX_JUMBO_FRAME_SIZE 0x2600 @@ -128,7 +129,6 @@ #define NWAY_LPAR_ASM_DIR 0x0800 /* LP Asymmetric Pause Direction bit */ /* 1000BASE-T Control Register */ -#define CR_1000T_ASYM_PAUSE 0x0080 /* Advertise asymmetric pause bit */ #define CR_1000T_HD_CAPS 0x0100 /* Advertise 1000T HD capability */ #define CR_1000T_FD_CAPS 0x0200 /* Advertise 1000T FD capability */ @@ -323,6 +323,9 @@ #define IGC_RXD_STAT_IXSM 0x04 /* Ignore checksum */ #define IGC_RXD_STAT_UDPCS 0x10 /* UDP xsum calculated */ #define IGC_RXD_STAT_TCPCS 0x20 /* TCP xsum calculated */ +#define IGC_RXD_STAT_VP 0x08 /* IEEE VLAN Packet */ + +#define IGC_RXDEXT_STATERR_LB 0x00040000 /* Advanced Receive Descriptor bit definitions */ #define IGC_RXDADV_STAT_TSIP 0x08000 /* timestamp in packet */ diff --git a/drivers/net/ethernet/intel/igc/igc_dump.c b/drivers/net/ethernet/intel/igc/igc_dump.c index 495bed47ed0a..c09c95cc5f70 100644 --- a/drivers/net/ethernet/intel/igc/igc_dump.c +++ b/drivers/net/ethernet/intel/igc/igc_dump.c @@ -112,7 +112,7 @@ static void igc_regdump(struct igc_hw *hw, struct igc_reg_info *reginfo) void igc_rings_dump(struct igc_adapter *adapter) { struct net_device *netdev = adapter->netdev; - struct my_u0 { u64 a; u64 b; } *u0; + struct my_u0 { __le64 a; __le64 b; } *u0; union igc_adv_tx_desc *tx_desc; union igc_adv_rx_desc *rx_desc; struct igc_ring *tx_ring; diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index 9722449d7633..fa4171860623 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -554,7 +554,7 @@ static int igc_ethtool_set_eeprom(struct net_device *netdev, memcpy(ptr, bytes, eeprom->len); for (i = 0; i < last_word - first_word + 1; i++) - eeprom_buff[i] = cpu_to_le16(eeprom_buff[i]); + cpu_to_le16s(&eeprom_buff[i]); ret_val = hw->nvm.ops.write(hw, first_word, last_word - first_word + 1, eeprom_buff); @@ -765,35 +765,22 @@ static void igc_ethtool_get_strings(struct net_device *netdev, u32 stringset, IGC_TEST_LEN * ETH_GSTRING_LEN); break; case ETH_SS_STATS: - for (i = 0; i < IGC_GLOBAL_STATS_LEN; i++) { - memcpy(p, igc_gstrings_stats[i].stat_string, - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } - for (i = 0; i < IGC_NETDEV_STATS_LEN; i++) { - memcpy(p, igc_gstrings_net_stats[i].stat_string, - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } + for (i = 0; i < IGC_GLOBAL_STATS_LEN; i++) + ethtool_sprintf(&p, igc_gstrings_stats[i].stat_string); + for (i = 0; i < IGC_NETDEV_STATS_LEN; i++) + ethtool_sprintf(&p, + igc_gstrings_net_stats[i].stat_string); for (i = 0; i < adapter->num_tx_queues; i++) { - sprintf(p, "tx_queue_%u_packets", i); - p += ETH_GSTRING_LEN; - sprintf(p, "tx_queue_%u_bytes", i); - p += ETH_GSTRING_LEN; - sprintf(p, "tx_queue_%u_restart", i); - p += ETH_GSTRING_LEN; + ethtool_sprintf(&p, "tx_queue_%u_packets", i); + ethtool_sprintf(&p, "tx_queue_%u_bytes", i); + ethtool_sprintf(&p, "tx_queue_%u_restart", i); } for (i = 0; i < adapter->num_rx_queues; i++) { - sprintf(p, "rx_queue_%u_packets", i); - p += ETH_GSTRING_LEN; - sprintf(p, "rx_queue_%u_bytes", i); - p += ETH_GSTRING_LEN; - sprintf(p, "rx_queue_%u_drops", i); - p += ETH_GSTRING_LEN; - sprintf(p, "rx_queue_%u_csum_err", i); - p += ETH_GSTRING_LEN; - sprintf(p, "rx_queue_%u_alloc_failed", i); - p += ETH_GSTRING_LEN; + ethtool_sprintf(&p, "rx_queue_%u_packets", i); + ethtool_sprintf(&p, "rx_queue_%u_bytes", i); + ethtool_sprintf(&p, "rx_queue_%u_drops", i); + ethtool_sprintf(&p, "rx_queue_%u_csum_err", i); + ethtool_sprintf(&p, "rx_queue_%u_alloc_failed", i); } /* BUG_ON(p - data != IGC_STATS_LEN * ETH_GSTRING_LEN); */ break; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index f1adf154ec4a..3f6b6d4543a8 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -11,7 +11,7 @@ #include <linux/pm_runtime.h> #include <net/pkt_sched.h> #include <linux/bpf_trace.h> - +#include <net/xdp_sock_drv.h> #include <net/ipv6.h> #include "igc.h" @@ -111,6 +111,9 @@ void igc_reset(struct igc_adapter *adapter) if (!netif_running(adapter->netdev)) igc_power_down_phy_copper_base(&adapter->hw); + /* Enable HW to recognize an 802.1Q VLAN Ethernet packet */ + wr32(IGC_VET, ETH_P_8021Q); + /* Re-enable PTP, where applicable. */ igc_ptp_reset(adapter); @@ -171,6 +174,14 @@ static void igc_get_hw_control(struct igc_adapter *adapter) ctrl_ext | IGC_CTRL_EXT_DRV_LOAD); } +static void igc_unmap_tx_buffer(struct device *dev, struct igc_tx_buffer *buf) +{ + dma_unmap_single(dev, dma_unmap_addr(buf, dma), + dma_unmap_len(buf, len), DMA_TO_DEVICE); + + dma_unmap_len_set(buf, len, 0); +} + /** * igc_clean_tx_ring - Free Tx Buffers * @tx_ring: ring to be cleaned @@ -179,20 +190,27 @@ static void igc_clean_tx_ring(struct igc_ring *tx_ring) { u16 i = tx_ring->next_to_clean; struct igc_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i]; + u32 xsk_frames = 0; while (i != tx_ring->next_to_use) { union igc_adv_tx_desc *eop_desc, *tx_desc; - if (tx_buffer->tx_flags & IGC_TX_FLAGS_XDP) + switch (tx_buffer->type) { + case IGC_TX_BUFFER_TYPE_XSK: + xsk_frames++; + break; + case IGC_TX_BUFFER_TYPE_XDP: xdp_return_frame(tx_buffer->xdpf); - else + igc_unmap_tx_buffer(tx_ring->dev, tx_buffer); + break; + case IGC_TX_BUFFER_TYPE_SKB: dev_kfree_skb_any(tx_buffer->skb); - - /* unmap skb header data */ - dma_unmap_single(tx_ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); + igc_unmap_tx_buffer(tx_ring->dev, tx_buffer); + break; + default: + netdev_warn_once(tx_ring->netdev, "Unknown Tx buffer type\n"); + break; + } /* check for eop_desc to determine the end of the packet */ eop_desc = tx_buffer->next_to_watch; @@ -211,10 +229,7 @@ static void igc_clean_tx_ring(struct igc_ring *tx_ring) /* unmap any remaining paged data */ if (dma_unmap_len(tx_buffer, len)) - dma_unmap_page(tx_ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); + igc_unmap_tx_buffer(tx_ring->dev, tx_buffer); } /* move us one more past the eop_desc for start of next pkt */ @@ -226,6 +241,9 @@ static void igc_clean_tx_ring(struct igc_ring *tx_ring) } } + if (tx_ring->xsk_pool && xsk_frames) + xsk_tx_completed(tx_ring->xsk_pool, xsk_frames); + /* reset BQL for queue */ netdev_tx_reset_queue(txring_txq(tx_ring)); @@ -346,11 +364,7 @@ static int igc_setup_all_tx_resources(struct igc_adapter *adapter) return err; } -/** - * igc_clean_rx_ring - Free Rx Buffers per Queue - * @rx_ring: ring to free buffers from - */ -static void igc_clean_rx_ring(struct igc_ring *rx_ring) +static void igc_clean_rx_ring_page_shared(struct igc_ring *rx_ring) { u16 i = rx_ring->next_to_clean; @@ -383,12 +397,39 @@ static void igc_clean_rx_ring(struct igc_ring *rx_ring) if (i == rx_ring->count) i = 0; } +} + +static void igc_clean_rx_ring_xsk_pool(struct igc_ring *ring) +{ + struct igc_rx_buffer *bi; + u16 i; + + for (i = 0; i < ring->count; i++) { + bi = &ring->rx_buffer_info[i]; + if (!bi->xdp) + continue; + + xsk_buff_free(bi->xdp); + bi->xdp = NULL; + } +} - clear_ring_uses_large_buffer(rx_ring); +/** + * igc_clean_rx_ring - Free Rx Buffers per Queue + * @ring: ring to free buffers from + */ +static void igc_clean_rx_ring(struct igc_ring *ring) +{ + if (ring->xsk_pool) + igc_clean_rx_ring_xsk_pool(ring); + else + igc_clean_rx_ring_page_shared(ring); - rx_ring->next_to_alloc = 0; - rx_ring->next_to_clean = 0; - rx_ring->next_to_use = 0; + clear_ring_uses_large_buffer(ring); + + ring->next_to_alloc = 0; + ring->next_to_clean = 0; + ring->next_to_use = 0; } /** @@ -414,7 +455,7 @@ void igc_free_rx_resources(struct igc_ring *rx_ring) { igc_clean_rx_ring(rx_ring); - igc_xdp_unregister_rxq_info(rx_ring); + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); vfree(rx_ring->rx_buffer_info); rx_ring->rx_buffer_info = NULL; @@ -453,11 +494,16 @@ int igc_setup_rx_resources(struct igc_ring *rx_ring) { struct net_device *ndev = rx_ring->netdev; struct device *dev = rx_ring->dev; + u8 index = rx_ring->queue_index; int size, desc_len, res; - res = igc_xdp_register_rxq_info(rx_ring); - if (res < 0) + res = xdp_rxq_info_reg(&rx_ring->xdp_rxq, ndev, index, + rx_ring->q_vector->napi.napi_id); + if (res < 0) { + netdev_err(ndev, "Failed to register xdp_rxq index %u\n", + index); return res; + } size = sizeof(struct igc_rx_buffer) * rx_ring->count; rx_ring->rx_buffer_info = vzalloc(size); @@ -483,7 +529,7 @@ int igc_setup_rx_resources(struct igc_ring *rx_ring) return 0; err: - igc_xdp_unregister_rxq_info(rx_ring); + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); vfree(rx_ring->rx_buffer_info); rx_ring->rx_buffer_info = NULL; netdev_err(ndev, "Unable to allocate memory for Rx descriptor ring\n"); @@ -515,9 +561,14 @@ static int igc_setup_all_rx_resources(struct igc_adapter *adapter) return err; } -static bool igc_xdp_is_enabled(struct igc_adapter *adapter) +static struct xsk_buff_pool *igc_get_xsk_pool(struct igc_adapter *adapter, + struct igc_ring *ring) { - return !!adapter->xdp_prog; + if (!igc_xdp_is_enabled(adapter) || + !test_bit(IGC_RING_FLAG_AF_XDP_ZC, &ring->flags)) + return NULL; + + return xsk_get_pool_from_qid(ring->netdev, ring->queue_index); } /** @@ -535,6 +586,20 @@ static void igc_configure_rx_ring(struct igc_adapter *adapter, int reg_idx = ring->reg_idx; u32 srrctl = 0, rxdctl = 0; u64 rdba = ring->dma; + u32 buf_size; + + xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); + ring->xsk_pool = igc_get_xsk_pool(adapter, ring); + if (ring->xsk_pool) { + WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_XSK_BUFF_POOL, + NULL)); + xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq); + } else { + WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_PAGE_SHARED, + NULL)); + } if (igc_xdp_is_enabled(adapter)) set_ring_uses_large_buffer(ring); @@ -558,12 +623,15 @@ static void igc_configure_rx_ring(struct igc_adapter *adapter, ring->next_to_clean = 0; ring->next_to_use = 0; - /* set descriptor configuration */ - srrctl = IGC_RX_HDR_LEN << IGC_SRRCTL_BSIZEHDRSIZE_SHIFT; - if (ring_uses_large_buffer(ring)) - srrctl |= IGC_RXBUFFER_3072 >> IGC_SRRCTL_BSIZEPKT_SHIFT; + if (ring->xsk_pool) + buf_size = xsk_pool_get_rx_frame_size(ring->xsk_pool); + else if (ring_uses_large_buffer(ring)) + buf_size = IGC_RXBUFFER_3072; else - srrctl |= IGC_RXBUFFER_2048 >> IGC_SRRCTL_BSIZEPKT_SHIFT; + buf_size = IGC_RXBUFFER_2048; + + srrctl = IGC_RX_HDR_LEN << IGC_SRRCTL_BSIZEHDRSIZE_SHIFT; + srrctl |= buf_size >> IGC_SRRCTL_BSIZEPKT_SHIFT; srrctl |= IGC_SRRCTL_DESCTYPE_ADV_ONEBUF; wr32(IGC_SRRCTL(reg_idx), srrctl); @@ -618,6 +686,8 @@ static void igc_configure_tx_ring(struct igc_adapter *adapter, u64 tdba = ring->dma; u32 txdctl = 0; + ring->xsk_pool = igc_get_xsk_pool(adapter, ring); + /* disable the queue */ wr32(IGC_TXDCTL(reg_idx), 0); wrfl(); @@ -1055,13 +1125,17 @@ static inline int igc_maybe_stop_tx(struct igc_ring *tx_ring, const u16 size) ((u32)((_input) & (_flag)) * ((_result) / (_flag))) : \ ((u32)((_input) & (_flag)) / ((_flag) / (_result)))) -static u32 igc_tx_cmd_type(u32 tx_flags) +static u32 igc_tx_cmd_type(struct sk_buff *skb, u32 tx_flags) { /* set type for advanced descriptor with frame checksum insertion */ u32 cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT | IGC_ADVTXD_DCMD_IFCS; + /* set HW vlan bit if vlan is present */ + cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_VLAN, + IGC_ADVTXD_DCMD_VLE); + /* set segmentation bits for TSO */ cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSO, (IGC_ADVTXD_DCMD_TSE)); @@ -1070,6 +1144,9 @@ static u32 igc_tx_cmd_type(u32 tx_flags) cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSTAMP, (IGC_ADVTXD_MAC_TSTAMP)); + /* insert frame checksum */ + cmd_type ^= IGC_SET_FLAG(skb->no_fcs, 1, IGC_ADVTXD_DCMD_IFCS); + return cmd_type; } @@ -1104,8 +1181,9 @@ static int igc_tx_map(struct igc_ring *tx_ring, u16 i = tx_ring->next_to_use; unsigned int data_len, size; dma_addr_t dma; - u32 cmd_type = igc_tx_cmd_type(tx_flags); + u32 cmd_type; + cmd_type = igc_tx_cmd_type(skb, tx_flags); tx_desc = IGC_TX_DESC(tx_ring, i); igc_tx_olinfo_status(tx_ring, tx_desc, tx_flags, skb->len - hdr_len); @@ -1211,11 +1289,7 @@ dma_error: /* clear dma mappings for failed tx_buffer_info map */ while (tx_buffer != first) { if (dma_unmap_len(tx_buffer, len)) - dma_unmap_page(tx_ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); - dma_unmap_len_set(tx_buffer, len, 0); + igc_unmap_tx_buffer(tx_ring->dev, tx_buffer); if (i-- == 0) i += tx_ring->count; @@ -1223,11 +1297,7 @@ dma_error: } if (dma_unmap_len(tx_buffer, len)) - dma_unmap_single(tx_ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); - dma_unmap_len_set(tx_buffer, len, 0); + igc_unmap_tx_buffer(tx_ring->dev, tx_buffer); dev_kfree_skb_any(tx_buffer->skb); tx_buffer->skb = NULL; @@ -1359,6 +1429,7 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, /* record the location of the first descriptor for this packet */ first = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + first->type = IGC_TX_BUFFER_TYPE_SKB; first->skb = skb; first->bytecount = skb->len; first->gso_segs = 1; @@ -1383,6 +1454,11 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, } } + if (skb_vlan_tag_present(skb)) { + tx_flags |= IGC_TX_FLAGS_VLAN; + tx_flags |= (skb_vlan_tag_get(skb) << IGC_TX_FLAGS_VLAN_SHIFT); + } + /* record initial flags and protocol */ first->tx_flags = tx_flags; first->protocol = protocol; @@ -1482,6 +1558,25 @@ static inline void igc_rx_hash(struct igc_ring *ring, PKT_HASH_TYPE_L3); } +static void igc_rx_vlan(struct igc_ring *rx_ring, + union igc_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + struct net_device *dev = rx_ring->netdev; + u16 vid; + + if ((dev->features & NETIF_F_HW_VLAN_CTAG_RX) && + igc_test_staterr(rx_desc, IGC_RXD_STAT_VP)) { + if (igc_test_staterr(rx_desc, IGC_RXDEXT_STATERR_LB) && + test_bit(IGC_RING_FLAG_RX_LB_VLAN_BSWAP, &rx_ring->flags)) + vid = be16_to_cpu((__force __be16)rx_desc->wb.upper.vlan); + else + vid = le16_to_cpu(rx_desc->wb.upper.vlan); + + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid); + } +} + /** * igc_process_skb_fields - Populate skb header fields from Rx descriptor * @rx_ring: rx descriptor ring packet is being transacted on @@ -1500,11 +1595,37 @@ static void igc_process_skb_fields(struct igc_ring *rx_ring, igc_rx_checksum(rx_ring, rx_desc, skb); + igc_rx_vlan(rx_ring, rx_desc, skb); + skb_record_rx_queue(skb, rx_ring->queue_index); skb->protocol = eth_type_trans(skb, rx_ring->netdev); } +static void igc_vlan_mode(struct net_device *netdev, netdev_features_t features) +{ + bool enable = !!(features & NETIF_F_HW_VLAN_CTAG_RX); + struct igc_adapter *adapter = netdev_priv(netdev); + struct igc_hw *hw = &adapter->hw; + u32 ctrl; + + ctrl = rd32(IGC_CTRL); + + if (enable) { + /* enable VLAN tag insert/strip */ + ctrl |= IGC_CTRL_VME; + } else { + /* disable VLAN tag insert/strip */ + ctrl &= ~IGC_CTRL_VME; + } + wr32(IGC_CTRL, ctrl); +} + +static void igc_restore_vlan(struct igc_adapter *adapter) +{ + igc_vlan_mode(adapter->netdev, adapter->netdev->features); +} + static struct igc_rx_buffer *igc_get_rx_buffer(struct igc_ring *rx_ring, const unsigned int size, int *rx_buffer_pgcnt) @@ -1930,6 +2051,63 @@ static void igc_alloc_rx_buffers(struct igc_ring *rx_ring, u16 cleaned_count) } } +static bool igc_alloc_rx_buffers_zc(struct igc_ring *ring, u16 count) +{ + union igc_adv_rx_desc *desc; + u16 i = ring->next_to_use; + struct igc_rx_buffer *bi; + dma_addr_t dma; + bool ok = true; + + if (!count) + return ok; + + desc = IGC_RX_DESC(ring, i); + bi = &ring->rx_buffer_info[i]; + i -= ring->count; + + do { + bi->xdp = xsk_buff_alloc(ring->xsk_pool); + if (!bi->xdp) { + ok = false; + break; + } + + dma = xsk_buff_xdp_get_dma(bi->xdp); + desc->read.pkt_addr = cpu_to_le64(dma); + + desc++; + bi++; + i++; + if (unlikely(!i)) { + desc = IGC_RX_DESC(ring, 0); + bi = ring->rx_buffer_info; + i -= ring->count; + } + + /* Clear the length for the next_to_use descriptor. */ + desc->wb.upper.length = 0; + + count--; + } while (count); + + i += ring->count; + + if (ring->next_to_use != i) { + ring->next_to_use = i; + + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. (Only + * applicable for weak-ordered memory model archs, + * such as IA-64). + */ + wmb(); + writel(i, ring->tail); + } + + return ok; +} + static int igc_xdp_init_tx_buffer(struct igc_tx_buffer *buffer, struct xdp_frame *xdpf, struct igc_ring *ring) @@ -1942,8 +2120,8 @@ static int igc_xdp_init_tx_buffer(struct igc_tx_buffer *buffer, return -ENOMEM; } + buffer->type = IGC_TX_BUFFER_TYPE_XDP; buffer->xdpf = xdpf; - buffer->tx_flags = IGC_TX_FLAGS_XDP; buffer->protocol = 0; buffer->bytecount = xdpf->len; buffer->gso_segs = 1; @@ -2025,35 +2203,24 @@ static int igc_xdp_xmit_back(struct igc_adapter *adapter, struct xdp_buff *xdp) return res; } -static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter, - struct xdp_buff *xdp) +/* This function assumes rcu_read_lock() is held by the caller. */ +static int __igc_xdp_run_prog(struct igc_adapter *adapter, + struct bpf_prog *prog, + struct xdp_buff *xdp) { - struct bpf_prog *prog; - int res; - u32 act; + u32 act = bpf_prog_run_xdp(prog, xdp); - rcu_read_lock(); - - prog = READ_ONCE(adapter->xdp_prog); - if (!prog) { - res = IGC_XDP_PASS; - goto unlock; - } - - act = bpf_prog_run_xdp(prog, xdp); switch (act) { case XDP_PASS: - res = IGC_XDP_PASS; - break; + return IGC_XDP_PASS; case XDP_TX: if (igc_xdp_xmit_back(adapter, xdp) < 0) goto out_failure; - res = IGC_XDP_TX; - break; + return IGC_XDP_TX; case XDP_REDIRECT: if (xdp_do_redirect(adapter->netdev, xdp, prog) < 0) goto out_failure; - res = IGC_XDP_REDIRECT; + return IGC_XDP_REDIRECT; break; default: bpf_warn_invalid_xdp_action(act); @@ -2063,9 +2230,25 @@ out_failure: trace_xdp_exception(adapter->netdev, prog, act); fallthrough; case XDP_DROP: - res = IGC_XDP_CONSUMED; - break; + return IGC_XDP_CONSUMED; } +} + +static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter, + struct xdp_buff *xdp) +{ + struct bpf_prog *prog; + int res; + + rcu_read_lock(); + + prog = READ_ONCE(adapter->xdp_prog); + if (!prog) { + res = IGC_XDP_PASS; + goto unlock; + } + + res = __igc_xdp_run_prog(adapter, prog, xdp); unlock: rcu_read_unlock(); @@ -2102,6 +2285,20 @@ static void igc_finalize_xdp(struct igc_adapter *adapter, int status) xdp_do_flush(); } +static void igc_update_rx_stats(struct igc_q_vector *q_vector, + unsigned int packets, unsigned int bytes) +{ + struct igc_ring *ring = q_vector->rx.ring; + + u64_stats_update_begin(&ring->rx_syncp); + ring->rx_stats.packets += packets; + ring->rx_stats.bytes += bytes; + u64_stats_update_end(&ring->rx_syncp); + + q_vector->rx.total_packets += packets; + q_vector->rx.total_bytes += bytes; +} + static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) { unsigned int total_bytes = 0, total_packets = 0; @@ -2150,12 +2347,9 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) } if (!skb) { - xdp.data = pktbuf + pkt_offset; - xdp.data_end = xdp.data + size; - xdp.data_hard_start = pktbuf - igc_rx_offset(rx_ring); - xdp_set_data_meta_invalid(&xdp); - xdp.frame_sz = truesize; - xdp.rxq = &rx_ring->xdp_rxq; + xdp_init_buff(&xdp, truesize, &rx_ring->xdp_rxq); + xdp_prepare_buff(&xdp, pktbuf - igc_rx_offset(rx_ring), + igc_rx_offset(rx_ring) + pkt_offset, size, false); skb = igc_xdp_run_prog(adapter, &xdp); } @@ -2225,12 +2419,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) /* place incomplete frames back on ring for completion */ rx_ring->skb = skb; - u64_stats_update_begin(&rx_ring->rx_syncp); - rx_ring->rx_stats.packets += total_packets; - rx_ring->rx_stats.bytes += total_bytes; - u64_stats_update_end(&rx_ring->rx_syncp); - q_vector->rx.total_packets += total_packets; - q_vector->rx.total_bytes += total_bytes; + igc_update_rx_stats(q_vector, total_packets, total_bytes); if (cleaned_count) igc_alloc_rx_buffers(rx_ring, cleaned_count); @@ -2238,6 +2427,221 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) return total_packets; } +static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring, + struct xdp_buff *xdp) +{ + unsigned int metasize = xdp->data - xdp->data_meta; + unsigned int datasize = xdp->data_end - xdp->data; + unsigned int totalsize = metasize + datasize; + struct sk_buff *skb; + + skb = __napi_alloc_skb(&ring->q_vector->napi, + xdp->data_end - xdp->data_hard_start, + GFP_ATOMIC | __GFP_NOWARN); + if (unlikely(!skb)) + return NULL; + + skb_reserve(skb, xdp->data_meta - xdp->data_hard_start); + memcpy(__skb_put(skb, totalsize), xdp->data_meta, totalsize); + if (metasize) + skb_metadata_set(skb, metasize); + + return skb; +} + +static void igc_dispatch_skb_zc(struct igc_q_vector *q_vector, + union igc_adv_rx_desc *desc, + struct xdp_buff *xdp, + ktime_t timestamp) +{ + struct igc_ring *ring = q_vector->rx.ring; + struct sk_buff *skb; + + skb = igc_construct_skb_zc(ring, xdp); + if (!skb) { + ring->rx_stats.alloc_failed++; + return; + } + + if (timestamp) + skb_hwtstamps(skb)->hwtstamp = timestamp; + + if (igc_cleanup_headers(ring, desc, skb)) + return; + + igc_process_skb_fields(ring, desc, skb); + napi_gro_receive(&q_vector->napi, skb); +} + +static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget) +{ + struct igc_adapter *adapter = q_vector->adapter; + struct igc_ring *ring = q_vector->rx.ring; + u16 cleaned_count = igc_desc_unused(ring); + int total_bytes = 0, total_packets = 0; + u16 ntc = ring->next_to_clean; + struct bpf_prog *prog; + bool failure = false; + int xdp_status = 0; + + rcu_read_lock(); + + prog = READ_ONCE(adapter->xdp_prog); + + while (likely(total_packets < budget)) { + union igc_adv_rx_desc *desc; + struct igc_rx_buffer *bi; + ktime_t timestamp = 0; + unsigned int size; + int res; + + desc = IGC_RX_DESC(ring, ntc); + size = le16_to_cpu(desc->wb.upper.length); + if (!size) + break; + + /* This memory barrier is needed to keep us from reading + * any other fields out of the rx_desc until we know the + * descriptor has been written back + */ + dma_rmb(); + + bi = &ring->rx_buffer_info[ntc]; + + if (igc_test_staterr(desc, IGC_RXDADV_STAT_TSIP)) { + timestamp = igc_ptp_rx_pktstamp(q_vector->adapter, + bi->xdp->data); + + bi->xdp->data += IGC_TS_HDR_LEN; + + /* HW timestamp has been copied into local variable. Metadata + * length when XDP program is called should be 0. + */ + bi->xdp->data_meta += IGC_TS_HDR_LEN; + size -= IGC_TS_HDR_LEN; + } + + bi->xdp->data_end = bi->xdp->data + size; + xsk_buff_dma_sync_for_cpu(bi->xdp, ring->xsk_pool); + + res = __igc_xdp_run_prog(adapter, prog, bi->xdp); + switch (res) { + case IGC_XDP_PASS: + igc_dispatch_skb_zc(q_vector, desc, bi->xdp, timestamp); + fallthrough; + case IGC_XDP_CONSUMED: + xsk_buff_free(bi->xdp); + break; + case IGC_XDP_TX: + case IGC_XDP_REDIRECT: + xdp_status |= res; + break; + } + + bi->xdp = NULL; + total_bytes += size; + total_packets++; + cleaned_count++; + ntc++; + if (ntc == ring->count) + ntc = 0; + } + + ring->next_to_clean = ntc; + rcu_read_unlock(); + + if (cleaned_count >= IGC_RX_BUFFER_WRITE) + failure = !igc_alloc_rx_buffers_zc(ring, cleaned_count); + + if (xdp_status) + igc_finalize_xdp(adapter, xdp_status); + + igc_update_rx_stats(q_vector, total_packets, total_bytes); + + if (xsk_uses_need_wakeup(ring->xsk_pool)) { + if (failure || ring->next_to_clean == ring->next_to_use) + xsk_set_rx_need_wakeup(ring->xsk_pool); + else + xsk_clear_rx_need_wakeup(ring->xsk_pool); + return total_packets; + } + + return failure ? budget : total_packets; +} + +static void igc_update_tx_stats(struct igc_q_vector *q_vector, + unsigned int packets, unsigned int bytes) +{ + struct igc_ring *ring = q_vector->tx.ring; + + u64_stats_update_begin(&ring->tx_syncp); + ring->tx_stats.bytes += bytes; + ring->tx_stats.packets += packets; + u64_stats_update_end(&ring->tx_syncp); + + q_vector->tx.total_bytes += bytes; + q_vector->tx.total_packets += packets; +} + +static void igc_xdp_xmit_zc(struct igc_ring *ring) +{ + struct xsk_buff_pool *pool = ring->xsk_pool; + struct netdev_queue *nq = txring_txq(ring); + union igc_adv_tx_desc *tx_desc = NULL; + int cpu = smp_processor_id(); + u16 ntu = ring->next_to_use; + struct xdp_desc xdp_desc; + u16 budget; + + if (!netif_carrier_ok(ring->netdev)) + return; + + __netif_tx_lock(nq, cpu); + + budget = igc_desc_unused(ring); + + while (xsk_tx_peek_desc(pool, &xdp_desc) && budget--) { + u32 cmd_type, olinfo_status; + struct igc_tx_buffer *bi; + dma_addr_t dma; + + cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT | + IGC_ADVTXD_DCMD_IFCS | IGC_TXD_DCMD | + xdp_desc.len; + olinfo_status = xdp_desc.len << IGC_ADVTXD_PAYLEN_SHIFT; + + dma = xsk_buff_raw_get_dma(pool, xdp_desc.addr); + xsk_buff_raw_dma_sync_for_device(pool, dma, xdp_desc.len); + + tx_desc = IGC_TX_DESC(ring, ntu); + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); + tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); + tx_desc->read.buffer_addr = cpu_to_le64(dma); + + bi = &ring->tx_buffer_info[ntu]; + bi->type = IGC_TX_BUFFER_TYPE_XSK; + bi->protocol = 0; + bi->bytecount = xdp_desc.len; + bi->gso_segs = 1; + bi->time_stamp = jiffies; + bi->next_to_watch = tx_desc; + + netdev_tx_sent_queue(txring_txq(ring), xdp_desc.len); + + ntu++; + if (ntu == ring->count) + ntu = 0; + } + + ring->next_to_use = ntu; + if (tx_desc) { + igc_flush_tx_descriptors(ring); + xsk_tx_release(pool); + } + + __netif_tx_unlock(nq); +} + /** * igc_clean_tx_irq - Reclaim resources after transmit completes * @q_vector: pointer to q_vector containing needed info @@ -2254,6 +2658,7 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget) unsigned int i = tx_ring->next_to_clean; struct igc_tx_buffer *tx_buffer; union igc_adv_tx_desc *tx_desc; + u32 xsk_frames = 0; if (test_bit(__IGC_DOWN, &adapter->state)) return true; @@ -2283,19 +2688,22 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget) total_bytes += tx_buffer->bytecount; total_packets += tx_buffer->gso_segs; - if (tx_buffer->tx_flags & IGC_TX_FLAGS_XDP) + switch (tx_buffer->type) { + case IGC_TX_BUFFER_TYPE_XSK: + xsk_frames++; + break; + case IGC_TX_BUFFER_TYPE_XDP: xdp_return_frame(tx_buffer->xdpf); - else + igc_unmap_tx_buffer(tx_ring->dev, tx_buffer); + break; + case IGC_TX_BUFFER_TYPE_SKB: napi_consume_skb(tx_buffer->skb, napi_budget); - - /* unmap skb header data */ - dma_unmap_single(tx_ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); - - /* clear tx_buffer data */ - dma_unmap_len_set(tx_buffer, len, 0); + igc_unmap_tx_buffer(tx_ring->dev, tx_buffer); + break; + default: + netdev_warn_once(tx_ring->netdev, "Unknown Tx buffer type\n"); + break; + } /* clear last DMA location and unmap remaining buffers */ while (tx_desc != eop_desc) { @@ -2309,13 +2717,8 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget) } /* unmap any remaining paged data */ - if (dma_unmap_len(tx_buffer, len)) { - dma_unmap_page(tx_ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); - dma_unmap_len_set(tx_buffer, len, 0); - } + if (dma_unmap_len(tx_buffer, len)) + igc_unmap_tx_buffer(tx_ring->dev, tx_buffer); } /* move us one more past the eop_desc for start of next pkt */ @@ -2340,12 +2743,16 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget) i += tx_ring->count; tx_ring->next_to_clean = i; - u64_stats_update_begin(&tx_ring->tx_syncp); - tx_ring->tx_stats.bytes += total_bytes; - tx_ring->tx_stats.packets += total_packets; - u64_stats_update_end(&tx_ring->tx_syncp); - q_vector->tx.total_bytes += total_bytes; - q_vector->tx.total_packets += total_packets; + + igc_update_tx_stats(q_vector, total_packets, total_bytes); + + if (tx_ring->xsk_pool) { + if (xsk_frames) + xsk_tx_completed(tx_ring->xsk_pool, xsk_frames); + if (xsk_uses_need_wakeup(tx_ring->xsk_pool)) + xsk_set_tx_need_wakeup(tx_ring->xsk_pool); + igc_xdp_xmit_zc(tx_ring); + } if (test_bit(IGC_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags)) { struct igc_hw *hw = &adapter->hw; @@ -2906,6 +3313,8 @@ static void igc_configure(struct igc_adapter *adapter) igc_get_hw_control(adapter); igc_set_rx_mode(netdev); + igc_restore_vlan(adapter); + igc_setup_tctl(adapter); igc_setup_mrqc(adapter); igc_setup_rctl(adapter); @@ -2925,7 +3334,10 @@ static void igc_configure(struct igc_adapter *adapter) for (i = 0; i < adapter->num_rx_queues; i++) { struct igc_ring *ring = adapter->rx_ring[i]; - igc_alloc_rx_buffers(ring, igc_desc_unused(ring)); + if (ring->xsk_pool) + igc_alloc_rx_buffers_zc(ring, igc_desc_unused(ring)); + else + igc_alloc_rx_buffers(ring, igc_desc_unused(ring)); } } @@ -3540,14 +3952,17 @@ static int igc_poll(struct napi_struct *napi, int budget) struct igc_q_vector *q_vector = container_of(napi, struct igc_q_vector, napi); + struct igc_ring *rx_ring = q_vector->rx.ring; bool clean_complete = true; int work_done = 0; if (q_vector->tx.ring) clean_complete = igc_clean_tx_irq(q_vector, budget); - if (q_vector->rx.ring) { - int cleaned = igc_clean_rx_irq(q_vector, budget); + if (rx_ring) { + int cleaned = rx_ring->xsk_pool ? + igc_clean_rx_irq_zc(q_vector, budget) : + igc_clean_rx_irq(q_vector, budget); work_done += cleaned; if (cleaned >= budget) @@ -4199,6 +4614,9 @@ static int igc_set_features(struct net_device *netdev, netdev_features_t changed = netdev->features ^ features; struct igc_adapter *adapter = netdev_priv(netdev); + if (changed & NETIF_F_HW_VLAN_CTAG_RX) + igc_vlan_mode(netdev, features); + /* Add VLAN support */ if (!(changed & (NETIF_F_RXALL | NETIF_F_NTUPLE))) return 0; @@ -5185,6 +5603,9 @@ static int igc_bpf(struct net_device *dev, struct netdev_bpf *bpf) switch (bpf->command) { case XDP_SETUP_PROG: return igc_xdp_set_prog(adapter, bpf->prog, bpf->extack); + case XDP_SETUP_XSK_POOL: + return igc_xdp_setup_pool(adapter, bpf->xsk.pool, + bpf->xsk.queue_id); default: return -EOPNOTSUPP; } @@ -5230,6 +5651,43 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, return num_frames - drops; } +static void igc_trigger_rxtxq_interrupt(struct igc_adapter *adapter, + struct igc_q_vector *q_vector) +{ + struct igc_hw *hw = &adapter->hw; + u32 eics = 0; + + eics |= q_vector->eims_value; + wr32(IGC_EICS, eics); +} + +int igc_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) +{ + struct igc_adapter *adapter = netdev_priv(dev); + struct igc_q_vector *q_vector; + struct igc_ring *ring; + + if (test_bit(__IGC_DOWN, &adapter->state)) + return -ENETDOWN; + + if (!igc_xdp_is_enabled(adapter)) + return -ENXIO; + + if (queue_id >= adapter->num_rx_queues) + return -EINVAL; + + ring = adapter->rx_ring[queue_id]; + + if (!ring->xsk_pool) + return -ENXIO; + + q_vector = adapter->q_vector[queue_id]; + if (!napi_if_scheduled_mark_missed(&q_vector->napi)) + igc_trigger_rxtxq_interrupt(adapter, q_vector); + + return 0; +} + static const struct net_device_ops igc_netdev_ops = { .ndo_open = igc_open, .ndo_stop = igc_close, @@ -5245,6 +5703,7 @@ static const struct net_device_ops igc_netdev_ops = { .ndo_setup_tc = igc_setup_tc, .ndo_bpf = igc_bpf, .ndo_xdp_xmit = igc_xdp_xmit, + .ndo_xsk_wakeup = igc_xsk_wakeup, }; /* PCIe configuration access */ @@ -5484,11 +5943,15 @@ static int igc_probe(struct pci_dev *pdev, /* copy netdev features into list of user selectable features */ netdev->hw_features |= NETIF_F_NTUPLE; + netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX; + netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX; netdev->hw_features |= netdev->features; if (pci_using_dac) netdev->features |= NETIF_F_HIGHDMA; + netdev->vlan_features |= netdev->features; + /* MTU range: 68 - 9216 */ netdev->min_mtu = ETH_MIN_MTU; netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE; @@ -5997,6 +6460,61 @@ struct net_device *igc_get_hw_dev(struct igc_hw *hw) return adapter->netdev; } +static void igc_disable_rx_ring_hw(struct igc_ring *ring) +{ + struct igc_hw *hw = &ring->q_vector->adapter->hw; + u8 idx = ring->reg_idx; + u32 rxdctl; + + rxdctl = rd32(IGC_RXDCTL(idx)); + rxdctl &= ~IGC_RXDCTL_QUEUE_ENABLE; + rxdctl |= IGC_RXDCTL_SWFLUSH; + wr32(IGC_RXDCTL(idx), rxdctl); +} + +void igc_disable_rx_ring(struct igc_ring *ring) +{ + igc_disable_rx_ring_hw(ring); + igc_clean_rx_ring(ring); +} + +void igc_enable_rx_ring(struct igc_ring *ring) +{ + struct igc_adapter *adapter = ring->q_vector->adapter; + + igc_configure_rx_ring(adapter, ring); + + if (ring->xsk_pool) + igc_alloc_rx_buffers_zc(ring, igc_desc_unused(ring)); + else + igc_alloc_rx_buffers(ring, igc_desc_unused(ring)); +} + +static void igc_disable_tx_ring_hw(struct igc_ring *ring) +{ + struct igc_hw *hw = &ring->q_vector->adapter->hw; + u8 idx = ring->reg_idx; + u32 txdctl; + + txdctl = rd32(IGC_TXDCTL(idx)); + txdctl &= ~IGC_TXDCTL_QUEUE_ENABLE; + txdctl |= IGC_TXDCTL_SWFLUSH; + wr32(IGC_TXDCTL(idx), txdctl); +} + +void igc_disable_tx_ring(struct igc_ring *ring) +{ + igc_disable_tx_ring_hw(ring); + igc_clean_tx_ring(ring); +} + +void igc_enable_tx_ring(struct igc_ring *ring) +{ + struct igc_adapter *adapter = ring->q_vector->adapter; + + igc_configure_tx_ring(adapter, ring); +} + /** * igc_init_module - Driver Registration Routine * diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h index cc174853554b..0f82990567d9 100644 --- a/drivers/net/ethernet/intel/igc/igc_regs.h +++ b/drivers/net/ethernet/intel/igc/igc_regs.h @@ -10,8 +10,8 @@ #define IGC_EECD 0x00010 /* EEPROM/Flash Control - RW */ #define IGC_CTRL_EXT 0x00018 /* Extended Device Control - RW */ #define IGC_MDIC 0x00020 /* MDI Control - RW */ -#define IGC_MDICNFG 0x00E04 /* MDC/MDIO Configuration - RW */ #define IGC_CONNSW 0x00034 /* Copper/Fiber switch control - RW */ +#define IGC_VET 0x00038 /* VLAN Ether Type - RW */ #define IGC_I225_PHPM 0x00E14 /* I225 PHY Power Management */ #define IGC_GPHY_VERSION 0x0001E /* I225 gPHY Firmware Version */ diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.c b/drivers/net/ethernet/intel/igc/igc_xdp.c index 11133c4619bb..a8cf5374be47 100644 --- a/drivers/net/ethernet/intel/igc/igc_xdp.c +++ b/drivers/net/ethernet/intel/igc/igc_xdp.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020, Intel Corporation. */ +#include <net/xdp_sock_drv.h> + #include "igc.h" #include "igc_xdp.h" @@ -32,29 +34,112 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, return 0; } -int igc_xdp_register_rxq_info(struct igc_ring *ring) +static int igc_xdp_enable_pool(struct igc_adapter *adapter, + struct xsk_buff_pool *pool, u16 queue_id) { - struct net_device *dev = ring->netdev; + struct net_device *ndev = adapter->netdev; + struct device *dev = &adapter->pdev->dev; + struct igc_ring *rx_ring, *tx_ring; + struct napi_struct *napi; + bool needs_reset; + u32 frame_size; int err; - err = xdp_rxq_info_reg(&ring->xdp_rxq, dev, ring->queue_index, 0); - if (err) { - netdev_err(dev, "Failed to register xdp rxq info\n"); - return err; + if (queue_id >= adapter->num_rx_queues || + queue_id >= adapter->num_tx_queues) + return -EINVAL; + + frame_size = xsk_pool_get_rx_frame_size(pool); + if (frame_size < ETH_FRAME_LEN + VLAN_HLEN * 2) { + /* When XDP is enabled, the driver doesn't support frames that + * span over multiple buffers. To avoid that, we check if xsk + * frame size is big enough to fit the max ethernet frame size + * + vlan double tagging. + */ + return -EOPNOTSUPP; } - err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_SHARED, - NULL); + err = xsk_pool_dma_map(pool, dev, IGC_RX_DMA_ATTR); if (err) { - netdev_err(dev, "Failed to register xdp rxq mem model\n"); - xdp_rxq_info_unreg(&ring->xdp_rxq); + netdev_err(ndev, "Failed to map xsk pool\n"); return err; } + needs_reset = netif_running(adapter->netdev) && igc_xdp_is_enabled(adapter); + + rx_ring = adapter->rx_ring[queue_id]; + tx_ring = adapter->tx_ring[queue_id]; + /* Rx and Tx rings share the same napi context. */ + napi = &rx_ring->q_vector->napi; + + if (needs_reset) { + igc_disable_rx_ring(rx_ring); + igc_disable_tx_ring(tx_ring); + napi_disable(napi); + } + + set_bit(IGC_RING_FLAG_AF_XDP_ZC, &rx_ring->flags); + set_bit(IGC_RING_FLAG_AF_XDP_ZC, &tx_ring->flags); + + if (needs_reset) { + napi_enable(napi); + igc_enable_rx_ring(rx_ring); + igc_enable_tx_ring(tx_ring); + + err = igc_xsk_wakeup(ndev, queue_id, XDP_WAKEUP_RX); + if (err) { + xsk_pool_dma_unmap(pool, IGC_RX_DMA_ATTR); + return err; + } + } + + return 0; +} + +static int igc_xdp_disable_pool(struct igc_adapter *adapter, u16 queue_id) +{ + struct igc_ring *rx_ring, *tx_ring; + struct xsk_buff_pool *pool; + struct napi_struct *napi; + bool needs_reset; + + if (queue_id >= adapter->num_rx_queues || + queue_id >= adapter->num_tx_queues) + return -EINVAL; + + pool = xsk_get_pool_from_qid(adapter->netdev, queue_id); + if (!pool) + return -EINVAL; + + needs_reset = netif_running(adapter->netdev) && igc_xdp_is_enabled(adapter); + + rx_ring = adapter->rx_ring[queue_id]; + tx_ring = adapter->tx_ring[queue_id]; + /* Rx and Tx rings share the same napi context. */ + napi = &rx_ring->q_vector->napi; + + if (needs_reset) { + igc_disable_rx_ring(rx_ring); + igc_disable_tx_ring(tx_ring); + napi_disable(napi); + } + + xsk_pool_dma_unmap(pool, IGC_RX_DMA_ATTR); + clear_bit(IGC_RING_FLAG_AF_XDP_ZC, &rx_ring->flags); + clear_bit(IGC_RING_FLAG_AF_XDP_ZC, &tx_ring->flags); + + if (needs_reset) { + napi_enable(napi); + igc_enable_rx_ring(rx_ring); + igc_enable_tx_ring(tx_ring); + } + return 0; } -void igc_xdp_unregister_rxq_info(struct igc_ring *ring) +int igc_xdp_setup_pool(struct igc_adapter *adapter, struct xsk_buff_pool *pool, + u16 queue_id) { - xdp_rxq_info_unreg(&ring->xdp_rxq); + return pool ? igc_xdp_enable_pool(adapter, pool, queue_id) : + igc_xdp_disable_pool(adapter, queue_id); } diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.h b/drivers/net/ethernet/intel/igc/igc_xdp.h index cfecb515b718..a74e5487d199 100644 --- a/drivers/net/ethernet/intel/igc/igc_xdp.h +++ b/drivers/net/ethernet/intel/igc/igc_xdp.h @@ -6,8 +6,12 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, struct netlink_ext_ack *extack); +int igc_xdp_setup_pool(struct igc_adapter *adapter, struct xsk_buff_pool *pool, + u16 queue_id); -int igc_xdp_register_rxq_info(struct igc_ring *ring); -void igc_xdp_unregister_rxq_info(struct igc_ring *ring); +static inline bool igc_xdp_is_enabled(struct igc_adapter *adapter) +{ + return !!adapter->xdp_prog; +} #endif /* _IGC_XDP_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c index e324e42fab2d..58ea959a4482 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c @@ -1514,8 +1514,7 @@ static u32 ixgbe_get_fdirtcpm_82599(union ixgbe_atr_input *input_mask) #define IXGBE_WRITE_REG_BE32(a, reg, value) \ IXGBE_WRITE_REG((a), (reg), IXGBE_STORE_AS_BE32(ntohl(value))) -#define IXGBE_STORE_AS_BE16(_value) \ - ntohs(((u16)(_value) >> 8) | ((u16)(_value) << 8)) +#define IXGBE_STORE_AS_BE16(_value) __swab16(ntohs((_value))) s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, union ixgbe_atr_input *input_mask) @@ -1651,13 +1650,13 @@ s32 ixgbe_fdir_write_perfect_filter_82599(struct ixgbe_hw *hw, IXGBE_WRITE_REG_BE32(hw, IXGBE_FDIRIPDA, input->formatted.dst_ip[0]); /* record source and destination port (little-endian)*/ - fdirport = ntohs(input->formatted.dst_port); + fdirport = be16_to_cpu(input->formatted.dst_port); fdirport <<= IXGBE_FDIRPORT_DESTINATION_SHIFT; - fdirport |= ntohs(input->formatted.src_port); + fdirport |= be16_to_cpu(input->formatted.src_port); IXGBE_WRITE_REG(hw, IXGBE_FDIRPORT, fdirport); /* record vlan (little-endian) and flex_bytes(big-endian) */ - fdirvlan = IXGBE_STORE_AS_BE16((__force u16)input->formatted.flex_bytes); + fdirvlan = IXGBE_STORE_AS_BE16(input->formatted.flex_bytes); fdirvlan <<= IXGBE_FDIRVLAN_FLEX_SHIFT; fdirvlan |= ntohs(input->formatted.vlan_id); IXGBE_WRITE_REG(hw, IXGBE_FDIRVLAN, fdirvlan); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 03ccbe6b66d2..e90b5047e695 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -3678,10 +3678,8 @@ s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer, bool return_data) { u32 hdr_size = sizeof(struct ixgbe_hic_hdr); - union { - struct ixgbe_hic_hdr hdr; - u32 u32arr[1]; - } *bp = buffer; + struct ixgbe_hic_hdr *hdr = buffer; + u32 *u32arr = buffer; u16 buf_len, dword_len; s32 status; u32 bi; @@ -3707,12 +3705,12 @@ s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer, /* first pull in the header so we know the buffer length */ for (bi = 0; bi < dword_len; bi++) { - bp->u32arr[bi] = IXGBE_READ_REG_ARRAY(hw, IXGBE_FLEX_MNG, bi); - le32_to_cpus(&bp->u32arr[bi]); + u32arr[bi] = IXGBE_READ_REG_ARRAY(hw, IXGBE_FLEX_MNG, bi); + le32_to_cpus(&u32arr[bi]); } /* If there is any thing in data position pull it in */ - buf_len = bp->hdr.buf_len; + buf_len = hdr->buf_len; if (!buf_len) goto rel_out; @@ -3727,8 +3725,8 @@ s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer, /* Pull in the rest of the buffer (bi is where we left off) */ for (; bi <= dword_len; bi++) { - bp->u32arr[bi] = IXGBE_READ_REG_ARRAY(hw, IXGBE_FLEX_MNG, bi); - le32_to_cpus(&bp->u32arr[bi]); + u32arr[bi] = IXGBE_READ_REG_ARRAY(hw, IXGBE_FLEX_MNG, bi); + le32_to_cpus(&u32arr[bi]); } rel_out: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c index 54d47265a7ac..e596e1a9fc75 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c @@ -511,14 +511,14 @@ static int ixgbe_ipsec_check_mgmt_ip(struct xfrm_state *xs) continue; reg = IXGBE_READ_REG(hw, MIPAF_ARR(3, i)); - if (reg == xs->id.daddr.a4) + if (reg == (__force u32)xs->id.daddr.a4) return 1; } } if ((bmcipval & BMCIP_MASK) == BMCIP_V4) { reg = IXGBE_READ_REG(hw, IXGBE_BMCIP(3)); - if (reg == xs->id.daddr.a4) + if (reg == (__force u32)xs->id.daddr.a4) return 1; } @@ -533,7 +533,7 @@ static int ixgbe_ipsec_check_mgmt_ip(struct xfrm_state *xs) for (j = 0; j < 4; j++) { reg = IXGBE_READ_REG(hw, MIPAF_ARR(i, j)); - if (reg != xs->id.daddr.a6[j]) + if (reg != (__force u32)xs->id.daddr.a6[j]) break; } if (j == 4) /* did we match all 4 words? */ @@ -543,7 +543,7 @@ static int ixgbe_ipsec_check_mgmt_ip(struct xfrm_state *xs) if ((bmcipval & BMCIP_MASK) == BMCIP_V6) { for (j = 0; j < 4; j++) { reg = IXGBE_READ_REG(hw, IXGBE_BMCIP(j)); - if (reg != xs->id.daddr.a6[j]) + if (reg != (__force u32)xs->id.daddr.a6[j]) break; } if (j == 4) /* did we match all 4 words? */ diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 0e733cc15c58..dc56931fc1dc 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -3817,7 +3817,7 @@ static int ixgbevf_tso(struct ixgbevf_ring *tx_ring, /* remove payload length from inner checksum */ paylen = skb->len - l4_offset; - csum_replace_by_diff(&l4.tcp->check, htonl(paylen)); + csum_replace_by_diff(&l4.tcp->check, (__force __wsum)htonl(paylen)); /* update gso size and bytecount with header size */ first->gso_segs = skb_shinfo(skb)->gso_segs; |