diff options
Diffstat (limited to 'drivers/net/ethernet/intel')
164 files changed, 32120 insertions, 4377 deletions
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index 9bc0a9519899..06ddd7147c7f 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -225,6 +225,7 @@ config I40E depends on PTP_1588_CLOCK_OPTIONAL depends on PCI select AUXILIARY_BUS + select NET_DEVLINK help This driver supports Intel(R) Ethernet Controller XL710 Family of devices. For more information on how to identify your adapter, go @@ -284,6 +285,7 @@ config ICE select DIMLIB select NET_DEVLINK select PLDMFW + select DPLL help This driver supports Intel(R) Ethernet Connection E800 Series of devices. For more information on how to identify your adapter, go @@ -355,5 +357,17 @@ config IGC To compile this driver as a module, choose M here. The module will be called igc. +config IDPF + tristate "Intel(R) Infrastructure Data Path Function Support" + depends on PCI_MSI + select DIMLIB + select PAGE_POOL + select PAGE_POOL_STATS + help + This driver supports Intel(R) Infrastructure Data Path Function + devices. + + To compile this driver as a module, choose M here. The module + will be called idpf. endif # NET_VENDOR_INTEL diff --git a/drivers/net/ethernet/intel/Makefile b/drivers/net/ethernet/intel/Makefile index d80d04132073..dacb481ee5b1 100644 --- a/drivers/net/ethernet/intel/Makefile +++ b/drivers/net/ethernet/intel/Makefile @@ -15,3 +15,4 @@ obj-$(CONFIG_I40E) += i40e/ obj-$(CONFIG_IAVF) += iavf/ obj-$(CONFIG_FM10K) += fm10k/ obj-$(CONFIG_ICE) += ice/ +obj-$(CONFIG_IDPF) += idpf/ diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index d3fdc290937f..01f0f12035ca 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -2841,7 +2841,7 @@ static int e100_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->netdev_ops = &e100_netdev_ops; netdev->ethtool_ops = &e100_ethtool_ops; netdev->watchdog_timeo = E100_WATCHDOG_PERIOD; - strncpy(netdev->name, pci_name(pdev), sizeof(netdev->name) - 1); + strscpy(netdev->name, pci_name(pdev), sizeof(netdev->name)); nic = netdev_priv(netdev); netif_napi_add_weight(netdev, &nic->napi, e100_poll, E100_NAPI_WEIGHT); diff --git a/drivers/net/ethernet/intel/e1000/e1000.h b/drivers/net/ethernet/intel/e1000/e1000.h index 4817eb13ca6f..75f3fd1d8d6e 100644 --- a/drivers/net/ethernet/intel/e1000/e1000.h +++ b/drivers/net/ethernet/intel/e1000/e1000.h @@ -347,6 +347,5 @@ bool e1000_has_link(struct e1000_adapter *adapter); void e1000_power_up_phy(struct e1000_adapter *); void e1000_set_ethtool_ops(struct net_device *netdev); void e1000_check_options(struct e1000_adapter *adapter); -char *e1000_get_hw_dev_name(struct e1000_hw *hw); #endif /* _E1000_H_ */ diff --git a/drivers/net/ethernet/intel/e1000/e1000_hw.h b/drivers/net/ethernet/intel/e1000/e1000_hw.h index b57a04954ccf..95cdd17134e5 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_hw.h +++ b/drivers/net/ethernet/intel/e1000/e1000_hw.h @@ -343,7 +343,6 @@ struct e1000_host_mng_dhcp_cookie { }; #endif -bool e1000_check_mng_mode(struct e1000_hw *hw); s32 e1000_read_eeprom(struct e1000_hw *hw, u16 reg, u16 words, u16 * data); s32 e1000_validate_eeprom_checksum(struct e1000_hw *hw); s32 e1000_update_eeprom_checksum(struct e1000_hw *hw); @@ -352,7 +351,6 @@ s32 e1000_read_mac_addr(struct e1000_hw *hw); /* Filters (multicast, vlan, receive) */ u32 e1000_hash_mc_addr(struct e1000_hw *hw, u8 * mc_addr); -void e1000_mta_set(struct e1000_hw *hw, u32 hash_value); void e1000_rar_set(struct e1000_hw *hw, u8 * mc_addr, u32 rar_index); void e1000_write_vfta(struct e1000_hw *hw, u32 offset, u32 value); @@ -361,7 +359,6 @@ s32 e1000_setup_led(struct e1000_hw *hw); s32 e1000_cleanup_led(struct e1000_hw *hw); s32 e1000_led_on(struct e1000_hw *hw); s32 e1000_led_off(struct e1000_hw *hw); -s32 e1000_blink_led_start(struct e1000_hw *hw); /* Adaptive IFS Functions */ diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index da6e303ad99b..1d1e93686af2 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -1014,7 +1014,7 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->watchdog_timeo = 5 * HZ; netif_napi_add(netdev, &adapter->napi, e1000_clean); - strncpy(netdev->name, pci_name(pdev), sizeof(netdev->name) - 1); + strscpy(netdev->name, pci_name(pdev), sizeof(netdev->name)); adapter->bd_number = cards_found; diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index 721f86fd5802..9835e6a90d56 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -917,6 +917,7 @@ static int e1000_reg_test(struct e1000_adapter *adapter, u64 *data) case e1000_pch_mtp: case e1000_pch_lnp: case e1000_pch_ptp: + case e1000_pch_nvp: mask |= BIT(18); break; default: @@ -1585,6 +1586,7 @@ static void e1000_loopback_cleanup(struct e1000_adapter *adapter) case e1000_pch_mtp: case e1000_pch_lnp: case e1000_pch_ptp: + case e1000_pch_nvp: fext_nvm11 = er32(FEXTNVM11); fext_nvm11 &= ~E1000_FEXTNVM11_DISABLE_MULR_FIX; ew32(FEXTNVM11, fext_nvm11); diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index 29f9fae35f42..1fef6bb5a5fb 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -122,6 +122,8 @@ struct e1000_hw; #define E1000_DEV_ID_PCH_PTP_I219_V26 0x57B6 #define E1000_DEV_ID_PCH_PTP_I219_LM27 0x57B7 #define E1000_DEV_ID_PCH_PTP_I219_V27 0x57B8 +#define E1000_DEV_ID_PCH_NVL_I219_LM29 0x57B9 +#define E1000_DEV_ID_PCH_NVL_I219_V29 0x57BA #define E1000_REVISION_4 4 @@ -150,6 +152,7 @@ enum e1000_mac_type { e1000_pch_mtp, e1000_pch_lnp, e1000_pch_ptp, + e1000_pch_nvp, }; enum e1000_media_type { diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 0c7fd10312c8..39e9fc601bf5 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -323,6 +323,7 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) case e1000_pch_mtp: case e1000_pch_lnp: case e1000_pch_ptp: + case e1000_pch_nvp: if (e1000_phy_is_accessible_pchlan(hw)) break; @@ -470,6 +471,7 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw) case e1000_pch_mtp: case e1000_pch_lnp: case e1000_pch_ptp: + case e1000_pch_nvp: /* In case the PHY needs to be in mdio slow mode, * set slow mode and try to get the PHY id again. */ @@ -717,6 +719,7 @@ static s32 e1000_init_mac_params_ich8lan(struct e1000_hw *hw) case e1000_pch_mtp: case e1000_pch_lnp: case e1000_pch_ptp: + case e1000_pch_nvp: case e1000_pchlan: /* check management mode */ mac->ops.check_mng_mode = e1000_check_mng_mode_pchlan; @@ -1685,6 +1688,7 @@ static s32 e1000_get_variants_ich8lan(struct e1000_adapter *adapter) case e1000_pch_mtp: case e1000_pch_lnp: case e1000_pch_ptp: + case e1000_pch_nvp: rc = e1000_init_phy_params_pchlan(hw); break; default: @@ -2142,6 +2146,7 @@ static s32 e1000_sw_lcd_config_ich8lan(struct e1000_hw *hw) case e1000_pch_mtp: case e1000_pch_lnp: case e1000_pch_ptp: + case e1000_pch_nvp: sw_cfg_mask = E1000_FEXTNVM_SW_CONFIG_ICH8M; break; default: @@ -3188,6 +3193,7 @@ static s32 e1000_valid_nvm_bank_detect_ich8lan(struct e1000_hw *hw, u32 *bank) case e1000_pch_mtp: case e1000_pch_lnp: case e1000_pch_ptp: + case e1000_pch_nvp: bank1_offset = nvm->flash_bank_size; act_offset = E1000_ICH_NVM_SIG_WORD; @@ -4129,6 +4135,7 @@ static s32 e1000_validate_nvm_checksum_ich8lan(struct e1000_hw *hw) case e1000_pch_mtp: case e1000_pch_lnp: case e1000_pch_ptp: + case e1000_pch_nvp: word = NVM_COMPAT; valid_csum_mask = NVM_COMPAT_VALID_CSUM; break; diff --git a/drivers/net/ethernet/intel/e1000e/mac.h b/drivers/net/ethernet/intel/e1000e/mac.h index 6ab261119801..563176fd436e 100644 --- a/drivers/net/ethernet/intel/e1000e/mac.h +++ b/drivers/net/ethernet/intel/e1000e/mac.h @@ -29,8 +29,6 @@ s32 e1000e_set_fc_watermarks(struct e1000_hw *hw); s32 e1000e_setup_fiber_serdes_link(struct e1000_hw *hw); s32 e1000e_setup_led_generic(struct e1000_hw *hw); s32 e1000e_setup_link_generic(struct e1000_hw *hw); -s32 e1000e_validate_mdi_setting_generic(struct e1000_hw *hw); -s32 e1000e_validate_mdi_setting_crossover_generic(struct e1000_hw *hw); void e1000e_clear_hw_cntrs_base(struct e1000_hw *hw); void e1000_clear_vfta_generic(struct e1000_hw *hw); diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 771a3c909c45..f536c856727c 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -3545,6 +3545,7 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca) case e1000_pch_mtp: case e1000_pch_lnp: case e1000_pch_ptp: + case e1000_pch_nvp: if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) { /* Stable 24MHz frequency */ incperiod = INCPERIOD_24MHZ; @@ -4061,6 +4062,7 @@ void e1000e_reset(struct e1000_adapter *adapter) case e1000_pch_mtp: case e1000_pch_lnp: case e1000_pch_ptp: + case e1000_pch_nvp: fc->refresh_time = 0xFFFF; fc->pause_time = 0xFFFF; @@ -7021,6 +7023,8 @@ static __maybe_unused int e1000e_pm_runtime_resume(struct device *dev) struct e1000_adapter *adapter = netdev_priv(netdev); int rc; + pdev->pme_poll = true; + rc = __e1000_resume(pdev); if (rc) return rc; @@ -7682,7 +7686,7 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_pm_set_driver_flags(&pdev->dev, DPM_FLAG_SMART_PREPARE); - if (pci_dev_run_wake(pdev) && hw->mac.type != e1000_pch_cnp) + if (pci_dev_run_wake(pdev)) pm_runtime_put_noidle(&pdev->dev); return 0; @@ -7911,6 +7915,8 @@ static const struct pci_device_id e1000_pci_tbl[] = { { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V26), board_pch_mtp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM27), board_pch_mtp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V27), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_LM29), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_V29), board_pch_mtp }, { 0, 0, 0, 0, 0, 0, 0 } /* terminate list */ }; diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c index def4566a916f..02d871bc112a 100644 --- a/drivers/net/ethernet/intel/e1000e/ptp.c +++ b/drivers/net/ethernet/intel/e1000e/ptp.c @@ -288,6 +288,7 @@ void e1000e_ptp_init(struct e1000_adapter *adapter) case e1000_pch_mtp: case e1000_pch_lnp: case e1000_pch_ptp: + case e1000_pch_nvp: if ((hw->mac.type < e1000_pch_lpt) || (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)) { adapter->ptp_clock_info.max_adj = 24000000 - 1; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c index d53369e30040..13a05604dcc0 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c @@ -448,10 +448,10 @@ static void fm10k_get_drvinfo(struct net_device *dev, { struct fm10k_intfc *interface = netdev_priv(dev); - strncpy(info->driver, fm10k_driver_name, - sizeof(info->driver) - 1); - strncpy(info->bus_info, pci_name(interface->pdev), - sizeof(info->bus_info) - 1); + strscpy(info->driver, fm10k_driver_name, + sizeof(info->driver)); + strscpy(info->bus_info, pci_name(interface->pdev), + sizeof(info->bus_info)); } static void fm10k_get_pauseparam(struct net_device *dev, diff --git a/drivers/net/ethernet/intel/i40e/Makefile b/drivers/net/ethernet/intel/i40e/Makefile index 2f21b3e89fd0..cad93f323bd5 100644 --- a/drivers/net/ethernet/intel/i40e/Makefile +++ b/drivers/net/ethernet/intel/i40e/Makefile @@ -24,6 +24,7 @@ i40e-objs := i40e_main.o \ i40e_ddp.o \ i40e_client.o \ i40e_virtchnl_pf.o \ - i40e_xsk.o + i40e_xsk.o \ + i40e_devlink.o i40e-$(CONFIG_I40E_DCB) += i40e_dcb.o i40e_dcb_nl.o diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 6e310a539467..1bf424ac3145 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -4,47 +4,21 @@ #ifndef _I40E_H_ #define _I40E_H_ -#include <net/tcp.h> -#include <net/udp.h> -#include <linux/types.h> -#include <linux/errno.h> -#include <linux/module.h> #include <linux/pci.h> -#include <linux/netdevice.h> -#include <linux/ioport.h> -#include <linux/iommu.h> -#include <linux/slab.h> -#include <linux/list.h> -#include <linux/hashtable.h> -#include <linux/string.h> -#include <linux/in.h> -#include <linux/ip.h> -#include <linux/sctp.h> -#include <linux/pkt_sched.h> -#include <linux/ipv6.h> -#include <net/checksum.h> -#include <net/ip6_checksum.h> -#include <linux/ethtool.h> -#include <linux/if_vlan.h> -#include <linux/if_macvlan.h> -#include <linux/if_bridge.h> -#include <linux/clocksource.h> -#include <linux/net_tstamp.h> #include <linux/ptp_clock_kernel.h> +#include <linux/types.h> +#include <linux/avf/virtchnl.h> +#include <linux/net/intel/i40e_client.h> +#include <net/devlink.h> #include <net/pkt_cls.h> -#include <net/pkt_sched.h> -#include <net/tc_act/tc_gact.h> -#include <net/tc_act/tc_mirred.h> #include <net/udp_tunnel.h> -#include <net/xdp_sock.h> -#include <linux/bitfield.h> -#include "i40e_type.h" +#include "i40e_dcb.h" +#include "i40e_debug.h" +#include "i40e_devlink.h" +#include "i40e_io.h" #include "i40e_prototype.h" -#include <linux/net/intel/i40e_client.h> -#include <linux/avf/virtchnl.h> -#include "i40e_virtchnl_pf.h" +#include "i40e_register.h" #include "i40e_txrx.h" -#include "i40e_dcb.h" /* Useful i40e defaults */ #define I40E_MAX_VEB 16 @@ -75,23 +49,19 @@ #define I40E_QUEUE_WAIT_RETRY_LIMIT 10 #define I40E_INT_NAME_STR_LEN (IFNAMSIZ + 16) -#define I40E_NVM_VERSION_LO_SHIFT 0 -#define I40E_NVM_VERSION_LO_MASK (0xff << I40E_NVM_VERSION_LO_SHIFT) -#define I40E_NVM_VERSION_HI_SHIFT 12 -#define I40E_NVM_VERSION_HI_MASK (0xf << I40E_NVM_VERSION_HI_SHIFT) -#define I40E_OEM_VER_BUILD_MASK 0xffff -#define I40E_OEM_VER_PATCH_MASK 0xff -#define I40E_OEM_VER_BUILD_SHIFT 8 -#define I40E_OEM_VER_SHIFT 24 #define I40E_PHY_DEBUG_ALL \ (I40E_AQ_PHY_DEBUG_DISABLE_LINK_FW | \ I40E_AQ_PHY_DEBUG_DISABLE_ALL_LINK_FW) #define I40E_OEM_EETRACK_ID 0xffffffff -#define I40E_OEM_GEN_SHIFT 24 -#define I40E_OEM_SNAP_MASK 0x00ff0000 -#define I40E_OEM_SNAP_SHIFT 16 -#define I40E_OEM_RELEASE_MASK 0x0000ffff +#define I40E_NVM_VERSION_LO_MASK GENMASK(7, 0) +#define I40E_NVM_VERSION_HI_MASK GENMASK(15, 12) +#define I40E_OEM_VER_BUILD_MASK GENMASK(23, 8) +#define I40E_OEM_VER_PATCH_MASK GENMASK(7, 0) +#define I40E_OEM_VER_MASK GENMASK(31, 24) +#define I40E_OEM_GEN_MASK GENMASK(31, 24) +#define I40E_OEM_SNAP_MASK GENMASK(23, 16) +#define I40E_OEM_RELEASE_MASK GENMASK(15, 0) #define I40E_RX_DESC(R, i) \ (&(((union i40e_rx_desc *)((R)->desc))[i])) @@ -323,29 +293,6 @@ struct i40e_udp_port_config { u8 filter_index; }; -#define I40_DDP_FLASH_REGION 100 -#define I40E_PROFILE_INFO_SIZE 48 -#define I40E_MAX_PROFILE_NUM 16 -#define I40E_PROFILE_LIST_SIZE \ - (I40E_PROFILE_INFO_SIZE * I40E_MAX_PROFILE_NUM + 4) -#define I40E_DDP_PROFILE_PATH "intel/i40e/ddp/" -#define I40E_DDP_PROFILE_NAME_MAX 64 - -int i40e_ddp_load(struct net_device *netdev, const u8 *data, size_t size, - bool is_add); -int i40e_ddp_flash(struct net_device *netdev, struct ethtool_flash *flash); - -struct i40e_ddp_profile_list { - u32 p_count; - struct i40e_profile_info p_info[]; -}; - -struct i40e_ddp_old_profile_list { - struct list_head list; - size_t old_ddp_size; - u8 old_ddp_buf[]; -}; - /* macros related to FLX_PIT */ #define I40E_FLEX_SET_FSIZE(fsize) (((fsize) << \ I40E_PRTQF_FLX_PIT_FSIZE_SHIFT) & \ @@ -462,6 +409,7 @@ static inline const u8 *i40e_channel_mac(struct i40e_channel *ch) /* struct that defines the Ethernet device */ struct i40e_pf { struct pci_dev *pdev; + struct devlink_port devlink_port; struct i40e_hw hw; DECLARE_BITMAP(state, __I40E_STATE_SIZE__); struct msix_entry *msix_entries; @@ -580,7 +528,6 @@ struct i40e_pf { #define I40E_FLAG_DISABLE_FW_LLDP BIT(24) #define I40E_FLAG_RS_FEC BIT(25) #define I40E_FLAG_BASE_R_FEC BIT(26) -#define I40E_FLAG_VF_VLAN_PRUNING BIT(27) /* TOTAL_PORT_SHUTDOWN * Allows to physically disable the link on the NIC's port. * If enabled, (after link down request from the OS) @@ -603,6 +550,7 @@ struct i40e_pf { * in abilities field of i40e_aq_set_phy_config structure */ #define I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENABLED BIT(27) +#define I40E_FLAG_VF_VLAN_PRUNING BIT(28) struct i40e_client_instance *cinst; bool stat_offsets_loaded; @@ -1002,43 +950,104 @@ struct i40e_device { }; /** - * i40e_nvm_version_str - format the NVM version strings + * i40e_info_nvm_ver - format the NVM version string * @hw: ptr to the hardware info + * @buf: string buffer to store + * @len: buffer size + * + * Formats NVM version string as: + * <gen>.<snap>.<release> when eetrackid == I40E_OEM_EETRACK_ID + * <nvm_major>.<nvm_minor> otherwise **/ -static inline char *i40e_nvm_version_str(struct i40e_hw *hw) +static inline void i40e_info_nvm_ver(struct i40e_hw *hw, char *buf, size_t len) { - static char buf[32]; - u32 full_ver; + struct i40e_nvm_info *nvm = &hw->nvm; - full_ver = hw->nvm.oem_ver; - - if (hw->nvm.eetrack == I40E_OEM_EETRACK_ID) { + if (nvm->eetrack == I40E_OEM_EETRACK_ID) { + u32 full_ver = nvm->oem_ver; u8 gen, snap; u16 release; - gen = (u8)(full_ver >> I40E_OEM_GEN_SHIFT); - snap = (u8)((full_ver & I40E_OEM_SNAP_MASK) >> - I40E_OEM_SNAP_SHIFT); - release = (u16)(full_ver & I40E_OEM_RELEASE_MASK); - - snprintf(buf, sizeof(buf), "%x.%x.%x", gen, snap, release); + gen = FIELD_GET(I40E_OEM_GEN_MASK, full_ver); + snap = FIELD_GET(I40E_OEM_SNAP_MASK, full_ver); + release = FIELD_GET(I40E_OEM_RELEASE_MASK, full_ver); + snprintf(buf, len, "%x.%x.%x", gen, snap, release); } else { - u8 ver, patch; + u8 major, minor; + + major = FIELD_GET(I40E_NVM_VERSION_HI_MASK, nvm->version); + minor = FIELD_GET(I40E_NVM_VERSION_LO_MASK, nvm->version); + snprintf(buf, len, "%x.%02x", major, minor); + } +} + +/** + * i40e_info_eetrack - format the EETrackID string + * @hw: ptr to the hardware info + * @buf: string buffer to store + * @len: buffer size + * + * Returns hexadecimally formated EETrackID if it is + * different from I40E_OEM_EETRACK_ID or empty string. + **/ +static inline void i40e_info_eetrack(struct i40e_hw *hw, char *buf, size_t len) +{ + struct i40e_nvm_info *nvm = &hw->nvm; + + buf[0] = '\0'; + if (nvm->eetrack != I40E_OEM_EETRACK_ID) + snprintf(buf, len, "0x%08x", nvm->eetrack); +} + +/** + * i40e_info_civd_ver - format the NVM version strings + * @hw: ptr to the hardware info + * @buf: string buffer to store + * @len: buffer size + * + * Returns formated combo image version if adapter's EETrackID is + * different from I40E_OEM_EETRACK_ID or empty string. + **/ +static inline void i40e_info_civd_ver(struct i40e_hw *hw, char *buf, size_t len) +{ + struct i40e_nvm_info *nvm = &hw->nvm; + + buf[0] = '\0'; + if (nvm->eetrack != I40E_OEM_EETRACK_ID) { + u32 full_ver = nvm->oem_ver; + u8 major, minor; u16 build; - ver = (u8)(full_ver >> I40E_OEM_VER_SHIFT); - build = (u16)((full_ver >> I40E_OEM_VER_BUILD_SHIFT) & - I40E_OEM_VER_BUILD_MASK); - patch = (u8)(full_ver & I40E_OEM_VER_PATCH_MASK); - - snprintf(buf, sizeof(buf), - "%x.%02x 0x%x %d.%d.%d", - (hw->nvm.version & I40E_NVM_VERSION_HI_MASK) >> - I40E_NVM_VERSION_HI_SHIFT, - (hw->nvm.version & I40E_NVM_VERSION_LO_MASK) >> - I40E_NVM_VERSION_LO_SHIFT, - hw->nvm.eetrack, ver, build, patch); + major = FIELD_GET(I40E_OEM_VER_MASK, full_ver); + build = FIELD_GET(I40E_OEM_VER_BUILD_MASK, full_ver); + minor = FIELD_GET(I40E_OEM_VER_PATCH_MASK, full_ver); + snprintf(buf, len, "%d.%d.%d", major, build, minor); } +} + +/** + * i40e_nvm_version_str - format the NVM version strings + * @hw: ptr to the hardware info + * @buf: string buffer to store + * @len: buffer size + **/ +static inline char *i40e_nvm_version_str(struct i40e_hw *hw, char *buf, + size_t len) +{ + char ver[16] = " "; + + /* Get NVM version */ + i40e_info_nvm_ver(hw, buf, len); + + /* Append EETrackID if provided */ + i40e_info_eetrack(hw, &ver[1], sizeof(ver) - 1); + if (strlen(ver) > 1) + strlcat(buf, ver, len); + + /* Append combo image version if provided */ + i40e_info_civd_ver(hw, &ver[1], sizeof(ver) - 1); + if (strlen(ver) > 1) + strlcat(buf, ver, len); return buf; } @@ -1321,4 +1330,15 @@ static inline u32 i40e_is_tc_mqprio_enabled(struct i40e_pf *pf) return pf->flags & I40E_FLAG_TC_MQPRIO; } +/** + * i40e_hw_to_pf - get pf pointer from the hardware structure + * @hw: pointer to the device HW structure + **/ +static inline struct i40e_pf *i40e_hw_to_pf(struct i40e_hw *hw) +{ + return container_of(hw, struct i40e_pf, hw); +} + +struct device *i40e_hw_to_dev(struct i40e_hw *hw); + #endif /* _I40E_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index 86fac8f959bb..9ce6e633cc2f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -1,10 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ -#include "i40e_status.h" -#include "i40e_type.h" +#include <linux/delay.h> +#include "i40e_alloc.h" #include "i40e_register.h" -#include "i40e_adminq.h" #include "i40e_prototype.h" static void i40e_resume_aq(struct i40e_hw *hw); @@ -52,7 +51,6 @@ static int i40e_alloc_adminq_asq_ring(struct i40e_hw *hw) int ret_code; ret_code = i40e_allocate_dma_mem(hw, &hw->aq.asq.desc_buf, - i40e_mem_atq_ring, (hw->aq.num_asq_entries * sizeof(struct i40e_aq_desc)), I40E_ADMINQ_DESC_ALIGNMENT); @@ -79,7 +77,6 @@ static int i40e_alloc_adminq_arq_ring(struct i40e_hw *hw) int ret_code; ret_code = i40e_allocate_dma_mem(hw, &hw->aq.arq.desc_buf, - i40e_mem_arq_ring, (hw->aq.num_arq_entries * sizeof(struct i40e_aq_desc)), I40E_ADMINQ_DESC_ALIGNMENT); @@ -137,7 +134,6 @@ static int i40e_alloc_arq_bufs(struct i40e_hw *hw) for (i = 0; i < hw->aq.num_arq_entries; i++) { bi = &hw->aq.arq.r.arq_bi[i]; ret_code = i40e_allocate_dma_mem(hw, bi, - i40e_mem_arq_buf, hw->aq.arq_buf_size, I40E_ADMINQ_DESC_ALIGNMENT); if (ret_code) @@ -199,7 +195,6 @@ static int i40e_alloc_asq_bufs(struct i40e_hw *hw) for (i = 0; i < hw->aq.num_asq_entries; i++) { bi = &hw->aq.asq.r.asq_bi[i]; ret_code = i40e_allocate_dma_mem(hw, bi, - i40e_mem_asq_buf, hw->aq.asq_buf_size, I40E_ADMINQ_DESC_ALIGNMENT); if (ret_code) @@ -284,7 +279,7 @@ static int i40e_config_asq_regs(struct i40e_hw *hw) /* Check one register to verify that config was applied */ reg = rd32(hw, hw->aq.asq.bal); if (reg != lower_32_bits(hw->aq.asq.desc_buf.pa)) - ret_code = I40E_ERR_ADMIN_QUEUE_ERROR; + ret_code = -EIO; return ret_code; } @@ -316,7 +311,7 @@ static int i40e_config_arq_regs(struct i40e_hw *hw) /* Check one register to verify that config was applied */ reg = rd32(hw, hw->aq.arq.bal); if (reg != lower_32_bits(hw->aq.arq.desc_buf.pa)) - ret_code = I40E_ERR_ADMIN_QUEUE_ERROR; + ret_code = -EIO; return ret_code; } @@ -340,14 +335,14 @@ static int i40e_init_asq(struct i40e_hw *hw) if (hw->aq.asq.count > 0) { /* queue already initialized */ - ret_code = I40E_ERR_NOT_READY; + ret_code = -EBUSY; goto init_adminq_exit; } /* verify input for valid configuration */ if ((hw->aq.num_asq_entries == 0) || (hw->aq.asq_buf_size == 0)) { - ret_code = I40E_ERR_CONFIG; + ret_code = -EIO; goto init_adminq_exit; } @@ -399,14 +394,14 @@ static int i40e_init_arq(struct i40e_hw *hw) if (hw->aq.arq.count > 0) { /* queue already initialized */ - ret_code = I40E_ERR_NOT_READY; + ret_code = -EBUSY; goto init_adminq_exit; } /* verify input for valid configuration */ if ((hw->aq.num_arq_entries == 0) || (hw->aq.arq_buf_size == 0)) { - ret_code = I40E_ERR_CONFIG; + ret_code = -EIO; goto init_adminq_exit; } @@ -452,7 +447,7 @@ static int i40e_shutdown_asq(struct i40e_hw *hw) mutex_lock(&hw->aq.asq_mutex); if (hw->aq.asq.count == 0) { - ret_code = I40E_ERR_NOT_READY; + ret_code = -EBUSY; goto shutdown_asq_out; } @@ -486,7 +481,7 @@ static int i40e_shutdown_arq(struct i40e_hw *hw) mutex_lock(&hw->aq.arq_mutex); if (hw->aq.arq.count == 0) { - ret_code = I40E_ERR_NOT_READY; + ret_code = -EBUSY; goto shutdown_arq_out; } @@ -594,7 +589,7 @@ int i40e_init_adminq(struct i40e_hw *hw) (hw->aq.num_asq_entries == 0) || (hw->aq.arq_buf_size == 0) || (hw->aq.asq_buf_size == 0)) { - ret_code = I40E_ERR_CONFIG; + ret_code = -EIO; goto init_adminq_exit; } @@ -626,13 +621,13 @@ int i40e_init_adminq(struct i40e_hw *hw) &hw->aq.api_maj_ver, &hw->aq.api_min_ver, NULL); - if (ret_code != I40E_ERR_ADMIN_QUEUE_TIMEOUT) + if (ret_code != -EIO) break; retry++; msleep(100); i40e_resume_aq(hw); } while (retry < 10); - if (ret_code != I40E_SUCCESS) + if (ret_code != 0) goto init_adminq_free_arq; /* Some features were introduced in different FW API version @@ -672,7 +667,7 @@ int i40e_init_adminq(struct i40e_hw *hw) hw->flags |= I40E_HW_FLAG_802_1AD_CAPABLE; if (hw->aq.api_maj_ver > I40E_FW_API_VERSION_MAJOR) { - ret_code = I40E_ERR_FIRMWARE_API_VERSION; + ret_code = -EIO; goto init_adminq_free_arq; } @@ -799,7 +794,7 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw, if (hw->aq.asq.count == 0) { i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQTX: Admin queue not initialized.\n"); - status = I40E_ERR_QUEUE_EMPTY; + status = -EIO; goto asq_send_command_error; } @@ -809,7 +804,7 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw, if (val >= hw->aq.num_asq_entries) { i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQTX: head overrun at %d\n", val); - status = I40E_ERR_ADMIN_QUEUE_FULL; + status = -ENOSPC; goto asq_send_command_error; } @@ -840,7 +835,7 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw, I40E_DEBUG_AQ_MESSAGE, "AQTX: Invalid buffer size: %d.\n", buff_size); - status = I40E_ERR_INVALID_SIZE; + status = -EINVAL; goto asq_send_command_error; } @@ -848,7 +843,7 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw, i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQTX: Async flag not set along with postpone flag"); - status = I40E_ERR_PARAM; + status = -EINVAL; goto asq_send_command_error; } @@ -863,7 +858,7 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw, i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQTX: Error queue is full.\n"); - status = I40E_ERR_ADMIN_QUEUE_FULL; + status = -ENOSPC; goto asq_send_command_error; } @@ -940,9 +935,9 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw, if ((enum i40e_admin_queue_err)retval == I40E_AQ_RC_OK) status = 0; else if ((enum i40e_admin_queue_err)retval == I40E_AQ_RC_EBUSY) - status = I40E_ERR_NOT_READY; + status = -EBUSY; else - status = I40E_ERR_ADMIN_QUEUE_ERROR; + status = -EIO; hw->aq.asq_last_status = (enum i40e_admin_queue_err)retval; } @@ -960,11 +955,11 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw, if (rd32(hw, hw->aq.asq.len) & I40E_GL_ATQLEN_ATQCRIT_MASK) { i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQTX: AQ Critical error.\n"); - status = I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR; + status = -EIO; } else { i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQTX: Writeback timeout.\n"); - status = I40E_ERR_ADMIN_QUEUE_TIMEOUT; + status = -EIO; } } @@ -1106,7 +1101,7 @@ int i40e_clean_arq_element(struct i40e_hw *hw, if (hw->aq.arq.count == 0) { i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQRX: Admin queue not initialized.\n"); - ret_code = I40E_ERR_QUEUE_EMPTY; + ret_code = -EIO; goto clean_arq_element_err; } @@ -1114,7 +1109,7 @@ int i40e_clean_arq_element(struct i40e_hw *hw, ntu = rd32(hw, hw->aq.arq.head) & I40E_PF_ARQH_ARQH_MASK; if (ntu == ntc) { /* nothing to do - shouldn't need to update ring's values */ - ret_code = I40E_ERR_ADMIN_QUEUE_NO_WORK; + ret_code = -EALREADY; goto clean_arq_element_out; } @@ -1126,7 +1121,7 @@ int i40e_clean_arq_element(struct i40e_hw *hw, (enum i40e_admin_queue_err)le16_to_cpu(desc->retval); flags = le16_to_cpu(desc->flags); if (flags & I40E_AQ_FLAG_ERR) { - ret_code = I40E_ERR_ADMIN_QUEUE_ERROR; + ret_code = -EIO; i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQRX: Event received with error 0x%X.\n", diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.h b/drivers/net/ethernet/intel/i40e/i40e_adminq.h index ee394aacef4d..80125bea80a2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.h @@ -4,8 +4,8 @@ #ifndef _I40E_ADMINQ_H_ #define _I40E_ADMINQ_H_ -#include "i40e_osdep.h" -#include "i40e_status.h" +#include <linux/mutex.h> +#include "i40e_alloc.h" #include "i40e_adminq_cmd.h" #define I40E_ADMINQ_DESC(R, i) \ @@ -117,7 +117,7 @@ static inline int i40e_aq_rc_to_posix(int aq_ret, int aq_rc) }; /* aq_rc is invalid if AQ timed out */ - if (aq_ret == I40E_ERR_ADMIN_QUEUE_TIMEOUT) + if (aq_ret == -EIO) return -EAGAIN; if (!((u32)aq_rc < (sizeof(aq_to_posix) / sizeof((aq_to_posix)[0])))) diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 3357d65a906b..18a1c3b6d72c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -4,6 +4,8 @@ #ifndef _I40E_ADMINQ_CMD_H_ #define _I40E_ADMINQ_CMD_H_ +#include <linux/bits.h> + /* This header file defines the i40e Admin Queue commands and is shared between * i40e Firmware and Software. * diff --git a/drivers/net/ethernet/intel/i40e/i40e_alloc.h b/drivers/net/ethernet/intel/i40e/i40e_alloc.h index a6c9a9e343d1..e0dde326255d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_alloc.h +++ b/drivers/net/ethernet/intel/i40e/i40e_alloc.h @@ -4,25 +4,25 @@ #ifndef _I40E_ALLOC_H_ #define _I40E_ALLOC_H_ +#include <linux/types.h> + struct i40e_hw; -/* Memory allocation types */ -enum i40e_memory_type { - i40e_mem_arq_buf = 0, /* ARQ indirect command buffer */ - i40e_mem_asq_buf = 1, - i40e_mem_atq_buf = 2, /* ATQ indirect command buffer */ - i40e_mem_arq_ring = 3, /* ARQ descriptor ring */ - i40e_mem_atq_ring = 4, /* ATQ descriptor ring */ - i40e_mem_pd = 5, /* Page Descriptor */ - i40e_mem_bp = 6, /* Backing Page - 4KB */ - i40e_mem_bp_jumbo = 7, /* Backing Page - > 4KB */ - i40e_mem_reserved +/* memory allocation tracking */ +struct i40e_dma_mem { + void *va; + dma_addr_t pa; + u32 size; +}; + +struct i40e_virt_mem { + void *va; + u32 size; }; /* prototype for functions used for dynamic memory allocation */ int i40e_allocate_dma_mem(struct i40e_hw *hw, struct i40e_dma_mem *mem, - enum i40e_memory_type type, u64 size, u32 alignment); int i40e_free_dma_mem(struct i40e_hw *hw, struct i40e_dma_mem *mem); diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c index 639c5a1ca853..306758428aef 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.c +++ b/drivers/net/ethernet/intel/i40e/i40e_client.c @@ -6,7 +6,6 @@ #include <linux/net/intel/i40e_client.h> #include "i40e.h" -#include "i40e_prototype.h" static LIST_HEAD(i40e_devices); static DEFINE_MUTEX(i40e_device_mutex); diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index ed88e38d488b..d7e24d661724 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1,11 +1,14 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2021 Intel Corporation. */ -#include "i40e.h" -#include "i40e_type.h" -#include "i40e_adminq.h" -#include "i40e_prototype.h" #include <linux/avf/virtchnl.h> +#include <linux/delay.h> +#include <linux/etherdevice.h> +#include <linux/pci.h> +#include "i40e_adminq_cmd.h" +#include "i40e_devids.h" +#include "i40e_prototype.h" +#include "i40e_register.h" /** * i40e_set_mac_type - Sets MAC type @@ -56,7 +59,7 @@ int i40e_set_mac_type(struct i40e_hw *hw) break; } } else { - status = I40E_ERR_DEVICE_NOT_SUPPORTED; + status = -ENODEV; } hw_dbg(hw, "i40e_set_mac_type found mac: %d, returns: %d\n", @@ -660,7 +663,7 @@ int i40e_init_shared_code(struct i40e_hw *hw) case I40E_MAC_X722: break; default: - return I40E_ERR_DEVICE_NOT_SUPPORTED; + return -ENODEV; } hw->phy.get_link_info = true; @@ -780,7 +783,7 @@ int i40e_get_port_mac_addr(struct i40e_hw *hw, u8 *mac_addr) if (flags & I40E_AQC_PORT_ADDR_VALID) ether_addr_copy(mac_addr, addrs.port_mac); else - status = I40E_ERR_INVALID_MAC_ADDR; + status = -EINVAL; return status; } @@ -818,62 +821,72 @@ void i40e_pre_tx_queue_cfg(struct i40e_hw *hw, u32 queue, bool enable) } /** - * i40e_read_pba_string - Reads part number string from EEPROM + * i40e_get_pba_string - Reads part number string from EEPROM * @hw: pointer to hardware structure - * @pba_num: stores the part number string from the EEPROM - * @pba_num_size: part number string buffer length * - * Reads the part number string from the EEPROM. + * Reads the part number string from the EEPROM and stores it + * into newly allocated buffer and saves resulting pointer + * to i40e_hw->pba_id field. **/ -int i40e_read_pba_string(struct i40e_hw *hw, u8 *pba_num, - u32 pba_num_size) +void i40e_get_pba_string(struct i40e_hw *hw) { +#define I40E_NVM_PBA_FLAGS_BLK_PRESENT 0xFAFA u16 pba_word = 0; u16 pba_size = 0; u16 pba_ptr = 0; - int status = 0; - u16 i = 0; + int status; + char *ptr; + u16 i; status = i40e_read_nvm_word(hw, I40E_SR_PBA_FLAGS, &pba_word); - if (status || (pba_word != 0xFAFA)) { - hw_dbg(hw, "Failed to read PBA flags or flag is invalid.\n"); - return status; + if (status) { + hw_dbg(hw, "Failed to read PBA flags.\n"); + return; + } + if (pba_word != I40E_NVM_PBA_FLAGS_BLK_PRESENT) { + hw_dbg(hw, "PBA block is not present.\n"); + return; } status = i40e_read_nvm_word(hw, I40E_SR_PBA_BLOCK_PTR, &pba_ptr); if (status) { hw_dbg(hw, "Failed to read PBA Block pointer.\n"); - return status; + return; } status = i40e_read_nvm_word(hw, pba_ptr, &pba_size); if (status) { hw_dbg(hw, "Failed to read PBA Block size.\n"); - return status; + return; } /* Subtract one to get PBA word count (PBA Size word is included in - * total size) + * total size) and advance pointer to first PBA word. */ pba_size--; - if (pba_num_size < (((u32)pba_size * 2) + 1)) { - hw_dbg(hw, "Buffer too small for PBA data.\n"); - return I40E_ERR_PARAM; + pba_ptr++; + if (!pba_size) { + hw_dbg(hw, "PBA ID is empty.\n"); + return; } + ptr = devm_kzalloc(i40e_hw_to_dev(hw), pba_size * 2 + 1, GFP_KERNEL); + if (!ptr) + return; + hw->pba_id = ptr; + for (i = 0; i < pba_size; i++) { - status = i40e_read_nvm_word(hw, (pba_ptr + 1) + i, &pba_word); + status = i40e_read_nvm_word(hw, pba_ptr + i, &pba_word); if (status) { hw_dbg(hw, "Failed to read PBA Block word %d.\n", i); - return status; + devm_kfree(i40e_hw_to_dev(hw), hw->pba_id); + hw->pba_id = NULL; + return; } - pba_num[(i * 2)] = (pba_word >> 8) & 0xFF; - pba_num[(i * 2) + 1] = pba_word & 0xFF; + *ptr++ = (pba_word >> 8) & 0xFF; + *ptr++ = pba_word & 0xFF; } - pba_num[(pba_size * 2)] = '\0'; - - return status; } /** @@ -955,7 +968,7 @@ static int i40e_poll_globr(struct i40e_hw *hw, hw_dbg(hw, "Global reset failed.\n"); hw_dbg(hw, "I40E_GLGEN_RSTAT = 0x%x\n", reg); - return I40E_ERR_RESET_FAILED; + return -EIO; } #define I40E_PF_RESET_WAIT_COUNT_A0 200 @@ -995,7 +1008,7 @@ int i40e_pf_reset(struct i40e_hw *hw) } if (reg & I40E_GLGEN_RSTAT_DEVSTATE_MASK) { hw_dbg(hw, "Global reset polling failed to complete.\n"); - return I40E_ERR_RESET_FAILED; + return -EIO; } /* Now Wait for the FW to be ready */ @@ -1014,7 +1027,7 @@ int i40e_pf_reset(struct i40e_hw *hw) I40E_GLNVM_ULD_CONF_GLOBAL_DONE_MASK))) { hw_dbg(hw, "wait for FW Reset complete timedout\n"); hw_dbg(hw, "I40E_GLNVM_ULD = 0x%x\n", reg); - return I40E_ERR_RESET_FAILED; + return -EIO; } /* If there was a Global Reset in progress when we got here, @@ -1040,10 +1053,10 @@ int i40e_pf_reset(struct i40e_hw *hw) } if (reg2 & I40E_GLGEN_RSTAT_DEVSTATE_MASK) { if (i40e_poll_globr(hw, grst_del)) - return I40E_ERR_RESET_FAILED; + return -EIO; } else if (reg & I40E_PFGEN_CTRL_PFSWR_MASK) { hw_dbg(hw, "PF reset polling failed to complete.\n"); - return I40E_ERR_RESET_FAILED; + return -EIO; } } @@ -1082,7 +1095,7 @@ void i40e_clear_hw(struct i40e_hw *hw) I40E_PFLAN_QALLOC_FIRSTQ_SHIFT; j = (val & I40E_PFLAN_QALLOC_LASTQ_MASK) >> I40E_PFLAN_QALLOC_LASTQ_SHIFT; - if (val & I40E_PFLAN_QALLOC_VALID_MASK) + if (val & I40E_PFLAN_QALLOC_VALID_MASK && j >= base_queue) num_queues = (j - base_queue) + 1; else num_queues = 0; @@ -1092,7 +1105,7 @@ void i40e_clear_hw(struct i40e_hw *hw) I40E_PF_VT_PFALLOC_FIRSTVF_SHIFT; j = (val & I40E_PF_VT_PFALLOC_LASTVF_MASK) >> I40E_PF_VT_PFALLOC_LASTVF_SHIFT; - if (val & I40E_PF_VT_PFALLOC_VALID_MASK) + if (val & I40E_PF_VT_PFALLOC_VALID_MASK && j >= i) num_vfs = (j - i) + 1; else num_vfs = 0; @@ -1318,7 +1331,7 @@ i40e_aq_get_phy_capabilities(struct i40e_hw *hw, int status; if (!abilities) - return I40E_ERR_PARAM; + return -EINVAL; do { i40e_fill_default_direct_cmd_desc(&desc, @@ -1341,12 +1354,12 @@ i40e_aq_get_phy_capabilities(struct i40e_hw *hw, switch (hw->aq.asq_last_status) { case I40E_AQ_RC_EIO: - status = I40E_ERR_UNKNOWN_PHY; + status = -EIO; break; case I40E_AQ_RC_EAGAIN: usleep_range(1000, 2000); total_delay++; - status = I40E_ERR_TIMEOUT; + status = -EIO; break; /* also covers I40E_AQ_RC_OK */ default: @@ -1396,7 +1409,7 @@ int i40e_aq_set_phy_config(struct i40e_hw *hw, int status; if (!config) - return I40E_ERR_PARAM; + return -EINVAL; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_phy_config); @@ -2312,7 +2325,7 @@ int i40e_aq_send_driver_version(struct i40e_hw *hw, u16 len; if (dv == NULL) - return I40E_ERR_PARAM; + return -EINVAL; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_driver_version); @@ -2430,7 +2443,7 @@ int i40e_aq_add_veb(struct i40e_hw *hw, u16 uplink_seid, /* SEIDs need to either both be set or both be 0 for floating VEB */ if (!!uplink_seid != !!downlink_seid) - return I40E_ERR_PARAM; + return -EINVAL; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_add_veb); @@ -2485,7 +2498,7 @@ int i40e_aq_get_veb_parameters(struct i40e_hw *hw, int status; if (veb_seid == 0) - return I40E_ERR_PARAM; + return -EINVAL; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_get_veb_parameters); @@ -2575,7 +2588,7 @@ i40e_aq_add_macvlan(struct i40e_hw *hw, u16 seid, u16 buf_size; if (count == 0 || !mv_list || !hw) - return I40E_ERR_PARAM; + return -EINVAL; buf_size = i40e_prepare_add_macvlan(mv_list, &desc, count, seid); @@ -2608,7 +2621,7 @@ i40e_aq_add_macvlan_v2(struct i40e_hw *hw, u16 seid, u16 buf_size; if (count == 0 || !mv_list || !hw) - return I40E_ERR_PARAM; + return -EINVAL; buf_size = i40e_prepare_add_macvlan(mv_list, &desc, count, seid); @@ -2638,7 +2651,7 @@ i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 seid, int status; if (count == 0 || !mv_list || !hw) - return I40E_ERR_PARAM; + return -EINVAL; buf_size = count * sizeof(*mv_list); @@ -2685,7 +2698,7 @@ i40e_aq_remove_macvlan_v2(struct i40e_hw *hw, u16 seid, u16 buf_size; if (count == 0 || !mv_list || !hw) - return I40E_ERR_PARAM; + return -EINVAL; buf_size = count * sizeof(*mv_list); @@ -2791,7 +2804,7 @@ int i40e_aq_add_mirrorrule(struct i40e_hw *hw, u16 sw_seid, if (!(rule_type == I40E_AQC_MIRROR_RULE_TYPE_ALL_INGRESS || rule_type == I40E_AQC_MIRROR_RULE_TYPE_ALL_EGRESS)) { if (count == 0 || !mr_list) - return I40E_ERR_PARAM; + return -EINVAL; } return i40e_mirrorrule_op(hw, i40e_aqc_opc_add_mirror_rule, sw_seid, @@ -2827,7 +2840,7 @@ int i40e_aq_delete_mirrorrule(struct i40e_hw *hw, u16 sw_seid, * not matter. */ if (count == 0 || !mr_list) - return I40E_ERR_PARAM; + return -EINVAL; } return i40e_mirrorrule_op(hw, i40e_aqc_opc_delete_mirror_rule, sw_seid, @@ -2892,7 +2905,7 @@ int i40e_aq_debug_read_register(struct i40e_hw *hw, int status; if (reg_val == NULL) - return I40E_ERR_PARAM; + return -EINVAL; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_debug_read_reg); @@ -3031,7 +3044,7 @@ int i40e_aq_read_nvm(struct i40e_hw *hw, u8 module_pointer, /* In offset the highest byte must be zeroed. */ if (offset & 0xFF000000) { - status = I40E_ERR_PARAM; + status = -EINVAL; goto i40e_aq_read_nvm_exit; } @@ -3076,7 +3089,7 @@ int i40e_aq_erase_nvm(struct i40e_hw *hw, u8 module_pointer, /* In offset the highest byte must be zeroed. */ if (offset & 0xFF000000) { - status = I40E_ERR_PARAM; + status = -EINVAL; goto i40e_aq_erase_nvm_exit; } @@ -3368,7 +3381,7 @@ int i40e_aq_discover_capabilities(struct i40e_hw *hw, if (list_type_opc != i40e_aqc_opc_list_func_capabilities && list_type_opc != i40e_aqc_opc_list_dev_capabilities) { - status = I40E_ERR_PARAM; + status = -EINVAL; goto exit; } @@ -3416,7 +3429,7 @@ int i40e_aq_update_nvm(struct i40e_hw *hw, u8 module_pointer, /* In offset the highest byte must be zeroed. */ if (offset & 0xFF000000) { - status = I40E_ERR_PARAM; + status = -EINVAL; goto i40e_aq_update_nvm_exit; } @@ -3473,7 +3486,7 @@ int i40e_aq_rearrange_nvm(struct i40e_hw *hw, I40E_AQ_NVM_REARRANGE_TO_STRUCT); if (!rearrange_nvm) { - status = I40E_ERR_PARAM; + status = -EINVAL; goto i40e_aq_rearrange_nvm_exit; } @@ -3510,7 +3523,7 @@ int i40e_aq_get_lldp_mib(struct i40e_hw *hw, u8 bridge_type, int status; if (buff_size == 0 || !buff) - return I40E_ERR_PARAM; + return -EINVAL; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_get_mib); /* Indirect Command */ @@ -3558,7 +3571,7 @@ i40e_aq_set_lldp_mib(struct i40e_hw *hw, cmd = (struct i40e_aqc_lldp_set_local_mib *)&desc.params.raw; if (buff_size == 0 || !buff) - return I40E_ERR_PARAM; + return -EINVAL; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_set_local_mib); @@ -3627,7 +3640,7 @@ i40e_aq_restore_lldp(struct i40e_hw *hw, u8 *setting, bool restore, if (!(hw->flags & I40E_HW_FLAG_FW_LLDP_PERSISTENT)) { i40e_debug(hw, I40E_DEBUG_ALL, "Restore LLDP not supported by current FW version.\n"); - return I40E_ERR_DEVICE_NOT_SUPPORTED; + return -ENODEV; } i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_restore); @@ -3729,7 +3742,7 @@ i40e_aq_set_dcb_parameters(struct i40e_hw *hw, bool dcb_enable, int status; if (!(hw->flags & I40E_HW_FLAG_FW_LLDP_STOPPABLE)) - return I40E_ERR_DEVICE_NOT_SUPPORTED; + return -ENODEV; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_dcb_parameters); @@ -3760,7 +3773,7 @@ int i40e_aq_get_cee_dcb_config(struct i40e_hw *hw, int status; if (buff_size == 0 || !buff) - return I40E_ERR_PARAM; + return -EINVAL; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_get_cee_dcb_cfg); @@ -3848,7 +3861,7 @@ int i40e_aq_delete_element(struct i40e_hw *hw, u16 seid, int status; if (seid == 0) - return I40E_ERR_PARAM; + return -EINVAL; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_delete_element); @@ -3922,7 +3935,7 @@ static int i40e_aq_tx_sched_cmd(struct i40e_hw *hw, u16 seid, cmd_param_flag = false; break; default: - return I40E_ERR_PARAM; + return -EINVAL; } i40e_fill_default_direct_cmd_desc(&desc, opcode); @@ -4148,7 +4161,7 @@ i40e_validate_filter_settings(struct i40e_hw *hw, fcoe_filt_size <<= (u32)settings->fcoe_filt_num; break; default: - return I40E_ERR_PARAM; + return -EINVAL; } switch (settings->fcoe_cntx_num) { @@ -4160,7 +4173,7 @@ i40e_validate_filter_settings(struct i40e_hw *hw, fcoe_cntx_size <<= (u32)settings->fcoe_cntx_num; break; default: - return I40E_ERR_PARAM; + return -EINVAL; } /* Validate PE settings passed */ @@ -4178,7 +4191,7 @@ i40e_validate_filter_settings(struct i40e_hw *hw, case I40E_HASH_FILTER_SIZE_1M: break; default: - return I40E_ERR_PARAM; + return -EINVAL; } switch (settings->pe_cntx_num) { @@ -4194,7 +4207,7 @@ i40e_validate_filter_settings(struct i40e_hw *hw, case I40E_DMA_CNTX_SIZE_256K: break; default: - return I40E_ERR_PARAM; + return -EINVAL; } /* FCHSIZE + FCDSIZE should not be greater than PMFCOEFMAX */ @@ -4202,7 +4215,7 @@ i40e_validate_filter_settings(struct i40e_hw *hw, fcoe_fmax = (val & I40E_GLHMC_FCOEFMAX_PMFCOEFMAX_MASK) >> I40E_GLHMC_FCOEFMAX_PMFCOEFMAX_SHIFT; if (fcoe_filt_size + fcoe_cntx_size > fcoe_fmax) - return I40E_ERR_INVALID_SIZE; + return -EINVAL; return 0; } @@ -4224,7 +4237,7 @@ int i40e_set_filter_control(struct i40e_hw *hw, u32 val; if (!settings) - return I40E_ERR_PARAM; + return -EINVAL; /* Validate the input settings */ ret = i40e_validate_filter_settings(hw, settings); @@ -4306,7 +4319,7 @@ int i40e_aq_add_rem_control_packet_filter(struct i40e_hw *hw, int status; if (vsi_seid == 0) - return I40E_ERR_PARAM; + return -EINVAL; if (is_add) { i40e_fill_default_direct_cmd_desc(&desc, @@ -4381,7 +4394,7 @@ static int i40e_aq_alternate_read(struct i40e_hw *hw, int status; if (!reg_val0) - return I40E_ERR_PARAM; + return -EINVAL; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_alternate_read); cmd_resp->address0 = cpu_to_le32(reg_addr0); @@ -4517,7 +4530,7 @@ int i40e_aq_debug_dump(struct i40e_hw *hw, u8 cluster_id, int status; if (buff_size == 0 || !buff) - return I40E_ERR_PARAM; + return -EINVAL; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_debug_dump_internals); @@ -4635,7 +4648,7 @@ int i40e_read_phy_register_clause22(struct i40e_hw *hw, u16 reg, u8 phy_addr, u16 *value) { u8 port_num = (u8)hw->func_caps.mdio_port_num; - int status = I40E_ERR_TIMEOUT; + int status = -EIO; u32 command = 0; u16 retry = 1000; @@ -4680,7 +4693,7 @@ int i40e_write_phy_register_clause22(struct i40e_hw *hw, u16 reg, u8 phy_addr, u16 value) { u8 port_num = (u8)hw->func_caps.mdio_port_num; - int status = I40E_ERR_TIMEOUT; + int status = -EIO; u32 command = 0; u16 retry = 1000; @@ -4721,7 +4734,7 @@ int i40e_read_phy_register_clause45(struct i40e_hw *hw, u8 page, u16 reg, u8 phy_addr, u16 *value) { u8 port_num = hw->func_caps.mdio_port_num; - int status = I40E_ERR_TIMEOUT; + int status = -EIO; u32 command = 0; u16 retry = 1000; @@ -4755,7 +4768,7 @@ int i40e_read_phy_register_clause45(struct i40e_hw *hw, (I40E_MDIO_CLAUSE45_STCODE_MASK) | (I40E_GLGEN_MSCA_MDICMD_MASK) | (I40E_GLGEN_MSCA_MDIINPROGEN_MASK); - status = I40E_ERR_TIMEOUT; + status = -EIO; retry = 1000; wr32(hw, I40E_GLGEN_MSCA(port_num), command); do { @@ -4795,7 +4808,7 @@ int i40e_write_phy_register_clause45(struct i40e_hw *hw, u8 page, u16 reg, u8 phy_addr, u16 value) { u8 port_num = hw->func_caps.mdio_port_num; - int status = I40E_ERR_TIMEOUT; + int status = -EIO; u16 retry = 1000; u32 command = 0; @@ -4831,7 +4844,7 @@ int i40e_write_phy_register_clause45(struct i40e_hw *hw, (I40E_MDIO_CLAUSE45_STCODE_MASK) | (I40E_GLGEN_MSCA_MDICMD_MASK) | (I40E_GLGEN_MSCA_MDIINPROGEN_MASK); - status = I40E_ERR_TIMEOUT; + status = -EIO; retry = 1000; wr32(hw, I40E_GLGEN_MSCA(port_num), command); do { @@ -4880,7 +4893,7 @@ int i40e_write_phy_register(struct i40e_hw *hw, phy_addr, value); break; default: - status = I40E_ERR_UNKNOWN_PHY; + status = -EIO; break; } @@ -4919,7 +4932,7 @@ int i40e_read_phy_register(struct i40e_hw *hw, phy_addr, value); break; default: - status = I40E_ERR_UNKNOWN_PHY; + status = -EIO; break; } @@ -5109,7 +5122,7 @@ int i40e_led_get_phy(struct i40e_hw *hw, u16 *led_addr, I40E_PHY_COM_REG_PAGE, true, I40E_PHY_LED_PROV_REG_1, ®_val_aq, NULL); - if (status == I40E_SUCCESS) + if (status == 0) *val = (u16)reg_val_aq; return status; } @@ -5204,7 +5217,7 @@ int i40e_aq_rx_ctl_read_register(struct i40e_hw *hw, int status; if (!reg_val) - return I40E_ERR_PARAM; + return -EINVAL; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_rx_ctl_reg_read); @@ -5644,7 +5657,7 @@ i40e_validate_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile, if (track_id == I40E_DDP_TRACKID_INVALID) { i40e_debug(hw, I40E_DEBUG_PACKAGE, "Invalid track_id\n"); - return I40E_NOT_SUPPORTED; + return -EOPNOTSUPP; } dev_cnt = profile->device_table_count; @@ -5657,7 +5670,7 @@ i40e_validate_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile, if (dev_cnt && i == dev_cnt) { i40e_debug(hw, I40E_DEBUG_PACKAGE, "Device doesn't support DDP\n"); - return I40E_ERR_DEVICE_NOT_SUPPORTED; + return -ENODEV; } I40E_SECTION_TABLE(profile, sec_tbl); @@ -5672,14 +5685,14 @@ i40e_validate_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile, sec->section.type == SECTION_TYPE_RB_AQ) { i40e_debug(hw, I40E_DEBUG_PACKAGE, "Not a roll-back package\n"); - return I40E_NOT_SUPPORTED; + return -EOPNOTSUPP; } } else { if (sec->section.type == SECTION_TYPE_RB_AQ || sec->section.type == SECTION_TYPE_RB_MMIO) { i40e_debug(hw, I40E_DEBUG_PACKAGE, "Not an original package\n"); - return I40E_NOT_SUPPORTED; + return -EOPNOTSUPP; } } } diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c index 90638b67f8dc..68602fc375f6 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c +++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c @@ -1,9 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2021 Intel Corporation. */ -#include "i40e_adminq.h" -#include "i40e_prototype.h" +#include "i40e_alloc.h" #include "i40e_dcb.h" +#include "i40e_prototype.h" /** * i40e_get_dcbx_status @@ -17,7 +17,7 @@ int i40e_get_dcbx_status(struct i40e_hw *hw, u16 *status) u32 reg; if (!status) - return I40E_ERR_PARAM; + return -EINVAL; reg = rd32(hw, I40E_PRTDCB_GENS); *status = (u16)((reg & I40E_PRTDCB_GENS_DCBX_STATUS_MASK) >> @@ -508,7 +508,7 @@ int i40e_lldp_to_dcb_config(u8 *lldpmib, u16 type; if (!lldpmib || !dcbcfg) - return I40E_ERR_PARAM; + return -EINVAL; /* set to the start of LLDPDU */ lldpmib += ETH_HLEN; @@ -874,7 +874,7 @@ int i40e_init_dcb(struct i40e_hw *hw, bool enable_mib_change) int ret = 0; if (!hw->func_caps.dcb) - return I40E_NOT_SUPPORTED; + return -EOPNOTSUPP; /* Read LLDP NVM area */ if (hw->flags & I40E_HW_FLAG_FW_LLDP_PERSISTENT) { @@ -885,7 +885,7 @@ int i40e_init_dcb(struct i40e_hw *hw, bool enable_mib_change) else if (hw->mac.type == I40E_MAC_X722) offset = I40E_LLDP_CURRENT_STATUS_X722_OFFSET; else - return I40E_NOT_SUPPORTED; + return -EOPNOTSUPP; ret = i40e_read_nvm_module_data(hw, I40E_SR_EMP_SR_SETTINGS_PTR, @@ -897,7 +897,7 @@ int i40e_init_dcb(struct i40e_hw *hw, bool enable_mib_change) ret = i40e_read_lldp_cfg(hw, &lldp_cfg); } if (ret) - return I40E_ERR_NOT_READY; + return -EBUSY; /* Get the LLDP AdminStatus for the current port */ adminstatus = lldp_cfg.adminstatus >> (hw->port * 4); @@ -906,7 +906,7 @@ int i40e_init_dcb(struct i40e_hw *hw, bool enable_mib_change) /* LLDP agent disabled */ if (!adminstatus) { hw->dcbx_status = I40E_DCBX_STATUS_DISABLED; - return I40E_ERR_NOT_READY; + return -EBUSY; } /* Get DCBX status */ @@ -922,7 +922,7 @@ int i40e_init_dcb(struct i40e_hw *hw, bool enable_mib_change) if (ret) return ret; } else if (hw->dcbx_status == I40E_DCBX_STATUS_DISABLED) { - return I40E_ERR_NOT_READY; + return -EBUSY; } /* Configure the LLDP MIB change event */ @@ -949,7 +949,7 @@ i40e_get_fw_lldp_status(struct i40e_hw *hw, int ret; if (!lldp_status) - return I40E_ERR_PARAM; + return -EINVAL; /* Allocate buffer for the LLDPDU */ ret = i40e_allocate_virt_mem(hw, &mem, I40E_LLDPDU_SIZE); @@ -1299,7 +1299,7 @@ int i40e_dcb_config_to_lldp(u8 *lldpmib, u16 *miblen, sizeof(tlv->typelength) + length); } while (tlvid < I40E_TLV_ID_END_OF_LLDPPDU); *miblen = offset; - return I40E_SUCCESS; + return 0; } /** @@ -1957,7 +1957,7 @@ int i40e_read_lldp_cfg(struct i40e_hw *hw, u32 mem; if (!lldp_cfg) - return I40E_ERR_PARAM; + return -EINVAL; ret = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); if (ret) diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c b/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c index 195421d863ab..077a95dad32c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c +++ b/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c @@ -2,8 +2,8 @@ /* Copyright(c) 2013 - 2021 Intel Corporation. */ #ifdef CONFIG_I40E_DCB -#include "i40e.h" #include <net/dcbnl.h> +#include "i40e.h" #define I40E_DCBNL_STATUS_SUCCESS 0 #define I40E_DCBNL_STATUS_ERROR 1 diff --git a/drivers/net/ethernet/intel/i40e/i40e_ddp.c b/drivers/net/ethernet/intel/i40e/i40e_ddp.c index 7e8183762fd9..cf25bfc5dc3f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ddp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ddp.c @@ -1,9 +1,27 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ +#include <linux/firmware.h> #include "i40e.h" -#include <linux/firmware.h> +#define I40_DDP_FLASH_REGION 100 +#define I40E_PROFILE_INFO_SIZE 48 +#define I40E_MAX_PROFILE_NUM 16 +#define I40E_PROFILE_LIST_SIZE \ + (I40E_PROFILE_INFO_SIZE * I40E_MAX_PROFILE_NUM + 4) +#define I40E_DDP_PROFILE_PATH "intel/i40e/ddp/" +#define I40E_DDP_PROFILE_NAME_MAX 64 + +struct i40e_ddp_profile_list { + u32 p_count; + struct i40e_profile_info p_info[]; +}; + +struct i40e_ddp_old_profile_list { + struct list_head list; + size_t old_ddp_size; + u8 old_ddp_buf[]; +}; /** * i40e_ddp_profiles_eq - checks if DDP profiles are the equivalent @@ -220,7 +238,7 @@ static bool i40e_ddp_is_pkg_hdr_valid(struct net_device *netdev, netdev_err(netdev, "Invalid DDP profile - size is bigger than 4G"); return false; } - if (size < (sizeof(struct i40e_package_header) + + if (size < (sizeof(struct i40e_package_header) + sizeof(u32) + sizeof(struct i40e_metadata_segment) + sizeof(u32) * 2)) { netdev_err(netdev, "Invalid DDP profile - size is too small."); return false; @@ -261,8 +279,8 @@ static bool i40e_ddp_is_pkg_hdr_valid(struct net_device *netdev, * Checks correctness and loads DDP profile to the NIC. The function is * also used for rolling back previously loaded profile. **/ -int i40e_ddp_load(struct net_device *netdev, const u8 *data, size_t size, - bool is_add) +static int i40e_ddp_load(struct net_device *netdev, const u8 *data, size_t size, + bool is_add) { u8 profile_info_sec[sizeof(struct i40e_profile_section_header) + sizeof(struct i40e_profile_info)]; @@ -281,7 +299,7 @@ int i40e_ddp_load(struct net_device *netdev, const u8 *data, size_t size, if (!i40e_ddp_is_pkg_hdr_valid(netdev, pkg_hdr, size)) return -EINVAL; - if (size < (sizeof(struct i40e_package_header) + + if (size < (sizeof(struct i40e_package_header) + sizeof(u32) + sizeof(struct i40e_metadata_segment) + sizeof(u32) * 2)) { netdev_err(netdev, "Invalid DDP recipe size."); return -EINVAL; @@ -344,7 +362,7 @@ int i40e_ddp_load(struct net_device *netdev, const u8 *data, size_t size, if (is_add) { status = i40e_write_profile(&pf->hw, profile_hdr, track_id); if (status) { - if (status == I40E_ERR_DEVICE_NOT_SUPPORTED) { + if (status == -ENODEV) { netdev_err(netdev, "Profile is not supported by the device."); return -EPERM; @@ -438,10 +456,9 @@ int i40e_ddp_flash(struct net_device *netdev, struct ethtool_flash *flash) char profile_name[sizeof(I40E_DDP_PROFILE_PATH) + I40E_DDP_PROFILE_NAME_MAX]; - profile_name[sizeof(profile_name) - 1] = 0; - strncpy(profile_name, I40E_DDP_PROFILE_PATH, - sizeof(profile_name) - 1); - strncat(profile_name, flash->data, I40E_DDP_PROFILE_NAME_MAX); + scnprintf(profile_name, sizeof(profile_name), "%s%s", + I40E_DDP_PROFILE_PATH, flash->data); + /* Load DDP recipe. */ status = request_firmware(&ddp_config, profile_name, &netdev->dev); diff --git a/drivers/net/ethernet/intel/i40e/i40e_debug.h b/drivers/net/ethernet/intel/i40e/i40e_debug.h new file mode 100644 index 000000000000..27ebc72d8bfe --- /dev/null +++ b/drivers/net/ethernet/intel/i40e/i40e_debug.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2023 Intel Corporation. */ + +#ifndef _I40E_DEBUG_H_ +#define _I40E_DEBUG_H_ + +#include <linux/dev_printk.h> + +/* debug masks - set these bits in hw->debug_mask to control output */ +enum i40e_debug_mask { + I40E_DEBUG_INIT = 0x00000001, + I40E_DEBUG_RELEASE = 0x00000002, + + I40E_DEBUG_LINK = 0x00000010, + I40E_DEBUG_PHY = 0x00000020, + I40E_DEBUG_HMC = 0x00000040, + I40E_DEBUG_NVM = 0x00000080, + I40E_DEBUG_LAN = 0x00000100, + I40E_DEBUG_FLOW = 0x00000200, + I40E_DEBUG_DCB = 0x00000400, + I40E_DEBUG_DIAG = 0x00000800, + I40E_DEBUG_FD = 0x00001000, + I40E_DEBUG_PACKAGE = 0x00002000, + I40E_DEBUG_IWARP = 0x00F00000, + I40E_DEBUG_AQ_MESSAGE = 0x01000000, + I40E_DEBUG_AQ_DESCRIPTOR = 0x02000000, + I40E_DEBUG_AQ_DESC_BUFFER = 0x04000000, + I40E_DEBUG_AQ_COMMAND = 0x06000000, + I40E_DEBUG_AQ = 0x0F000000, + + I40E_DEBUG_USER = 0xF0000000, + + I40E_DEBUG_ALL = 0xFFFFFFFF +}; + +struct i40e_hw; +struct device *i40e_hw_to_dev(struct i40e_hw *hw); + +#define hw_dbg(hw, S, A...) dev_dbg(i40e_hw_to_dev(hw), S, ##A) + +#define i40e_debug(h, m, s, ...) \ +do { \ + if (((m) & (h)->debug_mask)) \ + dev_info(i40e_hw_to_dev(hw), s, ##__VA_ARGS__); \ +} while (0) + +#endif /* _I40E_DEBUG_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 62497f5565c5..999c9708def5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -5,8 +5,9 @@ #include <linux/fs.h> #include <linux/debugfs.h> - +#include <linux/if_bridge.h> #include "i40e.h" +#include "i40e_virtchnl_pf.h" static struct dentry *i40e_dbg_root; @@ -1309,7 +1310,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp, ret = i40e_asq_send_command(&pf->hw, desc, NULL, 0, NULL); if (!ret) { dev_info(&pf->pdev->dev, "AQ command sent Status : Success\n"); - } else if (ret == I40E_ERR_ADMIN_QUEUE_ERROR) { + } else if (ret == -EIO) { dev_info(&pf->pdev->dev, "AQ command send failed Opcode %x AQ Error: %d\n", desc->opcode, pf->hw.aq.asq_last_status); @@ -1370,7 +1371,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp, buffer_len, NULL); if (!ret) { dev_info(&pf->pdev->dev, "AQ command sent Status : Success\n"); - } else if (ret == I40E_ERR_ADMIN_QUEUE_ERROR) { + } else if (ret == -EIO) { dev_info(&pf->pdev->dev, "AQ command send failed Opcode %x AQ Error: %d\n", desc->opcode, pf->hw.aq.asq_last_status); diff --git a/drivers/net/ethernet/intel/i40e/i40e_devlink.c b/drivers/net/ethernet/intel/i40e/i40e_devlink.c new file mode 100644 index 000000000000..cc4e9e2addb7 --- /dev/null +++ b/drivers/net/ethernet/intel/i40e/i40e_devlink.c @@ -0,0 +1,235 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2023 Intel Corporation. */ + +#include <net/devlink.h> +#include "i40e.h" +#include "i40e_devlink.h" + +static void i40e_info_get_dsn(struct i40e_pf *pf, char *buf, size_t len) +{ + u8 dsn[8]; + + put_unaligned_be64(pci_get_dsn(pf->pdev), dsn); + + snprintf(buf, len, "%8phD", dsn); +} + +static void i40e_info_fw_mgmt(struct i40e_hw *hw, char *buf, size_t len) +{ + struct i40e_adminq_info *aq = &hw->aq; + + snprintf(buf, len, "%u.%u", aq->fw_maj_ver, aq->fw_min_ver); +} + +static void i40e_info_fw_mgmt_build(struct i40e_hw *hw, char *buf, size_t len) +{ + struct i40e_adminq_info *aq = &hw->aq; + + snprintf(buf, len, "%05d", aq->fw_build); +} + +static void i40e_info_fw_api(struct i40e_hw *hw, char *buf, size_t len) +{ + struct i40e_adminq_info *aq = &hw->aq; + + snprintf(buf, len, "%u.%u", aq->api_maj_ver, aq->api_min_ver); +} + +static void i40e_info_pba(struct i40e_hw *hw, char *buf, size_t len) +{ + buf[0] = '\0'; + if (hw->pba_id) + strscpy(buf, hw->pba_id, len); +} + +enum i40e_devlink_version_type { + I40E_DL_VERSION_FIXED, + I40E_DL_VERSION_RUNNING, +}; + +static int i40e_devlink_info_put(struct devlink_info_req *req, + enum i40e_devlink_version_type type, + const char *key, const char *value) +{ + if (!strlen(value)) + return 0; + + switch (type) { + case I40E_DL_VERSION_FIXED: + return devlink_info_version_fixed_put(req, key, value); + case I40E_DL_VERSION_RUNNING: + return devlink_info_version_running_put(req, key, value); + } + return 0; +} + +static int i40e_devlink_info_get(struct devlink *dl, + struct devlink_info_req *req, + struct netlink_ext_ack *extack) +{ + struct i40e_pf *pf = devlink_priv(dl); + struct i40e_hw *hw = &pf->hw; + char buf[32]; + int err; + + i40e_info_get_dsn(pf, buf, sizeof(buf)); + err = devlink_info_serial_number_put(req, buf); + if (err) + return err; + + i40e_info_fw_mgmt(hw, buf, sizeof(buf)); + err = i40e_devlink_info_put(req, I40E_DL_VERSION_RUNNING, + DEVLINK_INFO_VERSION_GENERIC_FW_MGMT, buf); + if (err) + return err; + + i40e_info_fw_mgmt_build(hw, buf, sizeof(buf)); + err = i40e_devlink_info_put(req, I40E_DL_VERSION_RUNNING, + "fw.mgmt.build", buf); + if (err) + return err; + + i40e_info_fw_api(hw, buf, sizeof(buf)); + err = i40e_devlink_info_put(req, I40E_DL_VERSION_RUNNING, + DEVLINK_INFO_VERSION_GENERIC_FW_MGMT_API, + buf); + if (err) + return err; + + i40e_info_nvm_ver(hw, buf, sizeof(buf)); + err = i40e_devlink_info_put(req, I40E_DL_VERSION_RUNNING, + "fw.psid.api", buf); + if (err) + return err; + + i40e_info_eetrack(hw, buf, sizeof(buf)); + err = i40e_devlink_info_put(req, I40E_DL_VERSION_RUNNING, + DEVLINK_INFO_VERSION_GENERIC_FW_BUNDLE_ID, + buf); + if (err) + return err; + + i40e_info_civd_ver(hw, buf, sizeof(buf)); + err = i40e_devlink_info_put(req, I40E_DL_VERSION_RUNNING, + DEVLINK_INFO_VERSION_GENERIC_FW_UNDI, buf); + if (err) + return err; + + i40e_info_pba(hw, buf, sizeof(buf)); + err = i40e_devlink_info_put(req, I40E_DL_VERSION_FIXED, + DEVLINK_INFO_VERSION_GENERIC_BOARD_ID, buf); + + return err; +} + +static const struct devlink_ops i40e_devlink_ops = { + .info_get = i40e_devlink_info_get, +}; + +/** + * i40e_alloc_pf - Allocate devlink and return i40e_pf structure pointer + * @dev: the device to allocate for + * + * Allocate a devlink instance for this device and return the private + * area as the i40e_pf structure. + **/ +struct i40e_pf *i40e_alloc_pf(struct device *dev) +{ + struct devlink *devlink; + + devlink = devlink_alloc(&i40e_devlink_ops, sizeof(struct i40e_pf), dev); + if (!devlink) + return NULL; + + return devlink_priv(devlink); +} + +/** + * i40e_free_pf - Free i40e_pf structure and associated devlink + * @pf: the PF structure + * + * Free i40e_pf structure and devlink allocated by devlink_alloc. + **/ +void i40e_free_pf(struct i40e_pf *pf) +{ + struct devlink *devlink = priv_to_devlink(pf); + + devlink_free(devlink); +} + +/** + * i40e_devlink_register - Register devlink interface for this PF + * @pf: the PF to register the devlink for. + * + * Register the devlink instance associated with this physical function. + **/ +void i40e_devlink_register(struct i40e_pf *pf) +{ + devlink_register(priv_to_devlink(pf)); +} + +/** + * i40e_devlink_unregister - Unregister devlink resources for this PF. + * @pf: the PF structure to cleanup + * + * Releases resources used by devlink and cleans up associated memory. + **/ +void i40e_devlink_unregister(struct i40e_pf *pf) +{ + devlink_unregister(priv_to_devlink(pf)); +} + +/** + * i40e_devlink_set_switch_id - Set unique switch id based on pci dsn + * @pf: the PF to create a devlink port for + * @ppid: struct with switch id information + */ +static void i40e_devlink_set_switch_id(struct i40e_pf *pf, + struct netdev_phys_item_id *ppid) +{ + u64 id = pci_get_dsn(pf->pdev); + + ppid->id_len = sizeof(id); + put_unaligned_be64(id, &ppid->id); +} + +/** + * i40e_devlink_create_port - Create a devlink port for this PF + * @pf: the PF to create a port for + * + * Create and register a devlink_port for this PF. Note that although each + * physical function is connected to a separate devlink instance, the port + * will still be numbered according to the physical function id. + * + * Return: zero on success or an error code on failure. + **/ +int i40e_devlink_create_port(struct i40e_pf *pf) +{ + struct devlink *devlink = priv_to_devlink(pf); + struct devlink_port_attrs attrs = {}; + struct device *dev = &pf->pdev->dev; + int err; + + attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; + attrs.phys.port_number = pf->hw.pf_id; + i40e_devlink_set_switch_id(pf, &attrs.switch_id); + devlink_port_attrs_set(&pf->devlink_port, &attrs); + err = devlink_port_register(devlink, &pf->devlink_port, pf->hw.pf_id); + if (err) { + dev_err(dev, "devlink_port_register failed: %d\n", err); + return err; + } + + return 0; +} + +/** + * i40e_devlink_destroy_port - Destroy the devlink_port for this PF + * @pf: the PF to cleanup + * + * Unregisters the devlink_port structure associated with this PF. + **/ +void i40e_devlink_destroy_port(struct i40e_pf *pf) +{ + devlink_port_unregister(&pf->devlink_port); +} diff --git a/drivers/net/ethernet/intel/i40e/i40e_devlink.h b/drivers/net/ethernet/intel/i40e/i40e_devlink.h new file mode 100644 index 000000000000..469fb3d2ee25 --- /dev/null +++ b/drivers/net/ethernet/intel/i40e/i40e_devlink.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2023, Intel Corporation. */ + +#ifndef _I40E_DEVLINK_H_ +#define _I40E_DEVLINK_H_ + +#include <linux/device.h> + +struct i40e_pf; + +struct i40e_pf *i40e_alloc_pf(struct device *dev); +void i40e_free_pf(struct i40e_pf *pf); +void i40e_devlink_register(struct i40e_pf *pf); +void i40e_devlink_unregister(struct i40e_pf *pf); +int i40e_devlink_create_port(struct i40e_pf *pf); +void i40e_devlink_destroy_port(struct i40e_pf *pf); + +#endif /* _I40E_DEVLINK_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_diag.c b/drivers/net/ethernet/intel/i40e/i40e_diag.c index 97fe1787a8f4..b1ad7c4259b9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_diag.c +++ b/drivers/net/ethernet/intel/i40e/i40e_diag.c @@ -28,7 +28,7 @@ static int i40e_diag_reg_pattern_test(struct i40e_hw *hw, i40e_debug(hw, I40E_DEBUG_DIAG, "%s: reg pattern test failed - reg 0x%08x pat 0x%08x val 0x%08x\n", __func__, reg, pat, val); - return I40E_ERR_DIAG_TEST_FAILED; + return -EIO; } } @@ -38,7 +38,7 @@ static int i40e_diag_reg_pattern_test(struct i40e_hw *hw, i40e_debug(hw, I40E_DEBUG_DIAG, "%s: reg restore test failed - reg 0x%08x orig_val 0x%08x val 0x%08x\n", __func__, reg, orig_val, val); - return I40E_ERR_DIAG_TEST_FAILED; + return -EIO; } return 0; @@ -127,5 +127,5 @@ int i40e_diag_eeprom_test(struct i40e_hw *hw) BIT(I40E_SR_CONTROL_WORD_1_SHIFT))) return i40e_validate_nvm_checksum(hw, NULL); else - return I40E_ERR_DIAG_TEST_FAILED; + return -EIO; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_diag.h b/drivers/net/ethernet/intel/i40e/i40e_diag.h index c3ce5f35211f..ece3a6b9a5c6 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_diag.h +++ b/drivers/net/ethernet/intel/i40e/i40e_diag.h @@ -4,7 +4,10 @@ #ifndef _I40E_DIAG_H_ #define _I40E_DIAG_H_ -#include "i40e_type.h" +#include "i40e_adminq_cmd.h" + +/* forward-declare the HW struct for the compiler */ +struct i40e_hw; enum i40e_lb_mode { I40E_LB_MODE_NONE = 0x0, diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index afc4fa8c66af..fd7163128c4d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -3,9 +3,10 @@ /* ethtool support for i40e */ -#include "i40e.h" +#include "i40e_devids.h" #include "i40e_diag.h" #include "i40e_txrx_common.h" +#include "i40e_virtchnl_pf.h" /* ethtool statistics helpers */ @@ -245,6 +246,7 @@ static const struct i40e_stats i40e_gstrings_net_stats[] = { I40E_NETDEV_STAT(rx_errors), I40E_NETDEV_STAT(tx_errors), I40E_NETDEV_STAT(rx_dropped), + I40E_NETDEV_STAT(rx_missed_errors), I40E_NETDEV_STAT(tx_dropped), I40E_NETDEV_STAT(collisions), I40E_NETDEV_STAT(rx_length_errors), @@ -321,7 +323,7 @@ static const struct i40e_stats i40e_gstrings_stats[] = { I40E_PF_STAT("port.rx_broadcast", stats.eth.rx_broadcast), I40E_PF_STAT("port.tx_broadcast", stats.eth.tx_broadcast), I40E_PF_STAT("port.tx_errors", stats.eth.tx_errors), - I40E_PF_STAT("port.rx_dropped", stats.eth.rx_discards), + I40E_PF_STAT("port.rx_discards", stats.eth.rx_discards), I40E_PF_STAT("port.tx_dropped_link_down", stats.tx_dropped_link_down), I40E_PF_STAT("port.rx_crc_errors", stats.crc_errors), I40E_PF_STAT("port.illegal_bytes", stats.illegal_bytes), @@ -2004,8 +2006,8 @@ static void i40e_get_drvinfo(struct net_device *netdev, struct i40e_pf *pf = vsi->back; strscpy(drvinfo->driver, i40e_driver_name, sizeof(drvinfo->driver)); - strscpy(drvinfo->fw_version, i40e_nvm_version_str(&pf->hw), - sizeof(drvinfo->fw_version)); + i40e_nvm_version_str(&pf->hw, drvinfo->fw_version, + sizeof(drvinfo->fw_version)); strscpy(drvinfo->bus_info, pci_name(pf->pdev), sizeof(drvinfo->bus_info)); drvinfo->n_priv_flags = I40E_PRIV_FLAGS_STR_LEN; @@ -2512,11 +2514,13 @@ static void i40e_get_priv_flag_strings(struct net_device *netdev, u8 *data) u8 *p = data; for (i = 0; i < I40E_PRIV_FLAGS_STR_LEN; i++) - ethtool_sprintf(&p, i40e_gstrings_priv_flags[i].flag_string); + ethtool_sprintf(&p, "%s", + i40e_gstrings_priv_flags[i].flag_string); if (pf->hw.pf_id != 0) return; for (i = 0; i < I40E_GL_PRIV_FLAGS_STR_LEN; i++) - ethtool_sprintf(&p, i40e_gl_gstrings_priv_flags[i].flag_string); + ethtool_sprintf(&p, "%s", + i40e_gl_gstrings_priv_flags[i].flag_string); } static void i40e_get_strings(struct net_device *netdev, u32 stringset, @@ -5699,8 +5703,8 @@ static int i40e_set_eee(struct net_device *netdev, struct ethtool_eee *edata) struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; struct i40e_hw *hw = &pf->hw; - int status = I40E_SUCCESS; __le16 eee_capability; + int status = 0; /* Deny parameters we don't support */ if (i40e_is_eee_param_supported(netdev, edata)) diff --git a/drivers/net/ethernet/intel/i40e/i40e_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_hmc.c index 46f7950a0049..1742624ca62e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_hmc.c +++ b/drivers/net/ethernet/intel/i40e/i40e_hmc.c @@ -1,11 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ -#include "i40e.h" -#include "i40e_osdep.h" -#include "i40e_register.h" -#include "i40e_status.h" #include "i40e_alloc.h" +#include "i40e_debug.h" #include "i40e_hmc.h" #include "i40e_type.h" @@ -23,37 +20,33 @@ int i40e_add_sd_table_entry(struct i40e_hw *hw, enum i40e_sd_entry_type type, u64 direct_mode_sz) { - enum i40e_memory_type mem_type __attribute__((unused)); struct i40e_hmc_sd_entry *sd_entry; bool dma_mem_alloc_done = false; - int ret_code = I40E_SUCCESS; struct i40e_dma_mem mem; + int ret_code = 0; u64 alloc_len; if (NULL == hmc_info->sd_table.sd_entry) { - ret_code = I40E_ERR_BAD_PTR; + ret_code = -EINVAL; hw_dbg(hw, "i40e_add_sd_table_entry: bad sd_entry\n"); goto exit; } if (sd_index >= hmc_info->sd_table.sd_cnt) { - ret_code = I40E_ERR_INVALID_SD_INDEX; + ret_code = -EINVAL; hw_dbg(hw, "i40e_add_sd_table_entry: bad sd_index\n"); goto exit; } sd_entry = &hmc_info->sd_table.sd_entry[sd_index]; if (!sd_entry->valid) { - if (I40E_SD_TYPE_PAGED == type) { - mem_type = i40e_mem_pd; + if (type == I40E_SD_TYPE_PAGED) alloc_len = I40E_HMC_PAGED_BP_SIZE; - } else { - mem_type = i40e_mem_bp_jumbo; + else alloc_len = direct_mode_sz; - } /* allocate a 4K pd page or 2M backing page */ - ret_code = i40e_allocate_dma_mem(hw, &mem, mem_type, alloc_len, + ret_code = i40e_allocate_dma_mem(hw, &mem, alloc_len, I40E_HMC_PD_BP_BUF_ALIGNMENT); if (ret_code) goto exit; @@ -121,7 +114,7 @@ int i40e_add_pd_table_entry(struct i40e_hw *hw, u64 *pd_addr; if (pd_index / I40E_HMC_PD_CNT_IN_SD >= hmc_info->sd_table.sd_cnt) { - ret_code = I40E_ERR_INVALID_PAGE_DESC_INDEX; + ret_code = -EINVAL; hw_dbg(hw, "i40e_add_pd_table_entry: bad pd_index\n"); goto exit; } @@ -141,7 +134,7 @@ int i40e_add_pd_table_entry(struct i40e_hw *hw, page = rsrc_pg; } else { /* allocate a 4K backing page */ - ret_code = i40e_allocate_dma_mem(hw, page, i40e_mem_bp, + ret_code = i40e_allocate_dma_mem(hw, page, I40E_HMC_PAGED_BP_SIZE, I40E_HMC_PD_BP_BUF_ALIGNMENT); if (ret_code) @@ -200,13 +193,13 @@ int i40e_remove_pd_bp(struct i40e_hw *hw, sd_idx = idx / I40E_HMC_PD_CNT_IN_SD; rel_pd_idx = idx % I40E_HMC_PD_CNT_IN_SD; if (sd_idx >= hmc_info->sd_table.sd_cnt) { - ret_code = I40E_ERR_INVALID_PAGE_DESC_INDEX; + ret_code = -EINVAL; hw_dbg(hw, "i40e_remove_pd_bp: bad idx\n"); goto exit; } sd_entry = &hmc_info->sd_table.sd_entry[sd_idx]; if (I40E_SD_TYPE_PAGED != sd_entry->entry_type) { - ret_code = I40E_ERR_INVALID_SD_TYPE; + ret_code = -EINVAL; hw_dbg(hw, "i40e_remove_pd_bp: wrong sd_entry type\n"); goto exit; } @@ -251,7 +244,7 @@ int i40e_prep_remove_sd_bp(struct i40e_hmc_info *hmc_info, sd_entry = &hmc_info->sd_table.sd_entry[idx]; I40E_DEC_BP_REFCNT(&sd_entry->u.bp); if (sd_entry->u.bp.ref_cnt) { - ret_code = I40E_ERR_NOT_READY; + ret_code = -EBUSY; goto exit; } I40E_DEC_SD_REFCNT(&hmc_info->sd_table); @@ -276,7 +269,7 @@ int i40e_remove_sd_bp_new(struct i40e_hw *hw, struct i40e_hmc_sd_entry *sd_entry; if (!is_pf) - return I40E_NOT_SUPPORTED; + return -EOPNOTSUPP; /* get the entry and decrease its ref counter */ sd_entry = &hmc_info->sd_table.sd_entry[idx]; @@ -299,7 +292,7 @@ int i40e_prep_remove_pd_page(struct i40e_hmc_info *hmc_info, sd_entry = &hmc_info->sd_table.sd_entry[idx]; if (sd_entry->u.pd_table.ref_cnt) { - ret_code = I40E_ERR_NOT_READY; + ret_code = -EBUSY; goto exit; } @@ -325,7 +318,7 @@ int i40e_remove_pd_page_new(struct i40e_hw *hw, struct i40e_hmc_sd_entry *sd_entry; if (!is_pf) - return I40E_NOT_SUPPORTED; + return -EOPNOTSUPP; sd_entry = &hmc_info->sd_table.sd_entry[idx]; I40E_CLEAR_PF_SD_ENTRY(hw, idx, I40E_SD_TYPE_PAGED); diff --git a/drivers/net/ethernet/intel/i40e/i40e_hmc.h b/drivers/net/ethernet/intel/i40e/i40e_hmc.h index 9960da07a573..480e3a883cc7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_hmc.h +++ b/drivers/net/ethernet/intel/i40e/i40e_hmc.h @@ -4,6 +4,10 @@ #ifndef _I40E_HMC_H_ #define _I40E_HMC_H_ +#include "i40e_alloc.h" +#include "i40e_io.h" +#include "i40e_register.h" + #define I40E_HMC_MAX_BP_COUNT 512 /* forward-declare the HW struct for the compiler */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_io.h b/drivers/net/ethernet/intel/i40e/i40e_io.h new file mode 100644 index 000000000000..2a2ed9a1d476 --- /dev/null +++ b/drivers/net/ethernet/intel/i40e/i40e_io.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2023 Intel Corporation. */ + +#ifndef _I40E_IO_H_ +#define _I40E_IO_H_ + +/* get readq/writeq support for 32 bit kernels, use the low-first version */ +#include <linux/io-64-nonatomic-lo-hi.h> + +#define wr32(a, reg, value) writel((value), ((a)->hw_addr + (reg))) +#define rd32(a, reg) readl((a)->hw_addr + (reg)) + +#define rd64(a, reg) readq((a)->hw_addr + (reg)) +#define i40e_flush(a) readl((a)->hw_addr + I40E_GLGEN_STAT) + +#endif /* _I40E_IO_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c index 40c101f286d1..beaaf5c309d5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c +++ b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c @@ -1,13 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ -#include "i40e.h" -#include "i40e_osdep.h" -#include "i40e_register.h" -#include "i40e_type.h" -#include "i40e_hmc.h" +#include "i40e_alloc.h" +#include "i40e_debug.h" #include "i40e_lan_hmc.h" -#include "i40e_prototype.h" +#include "i40e_type.h" /* lan specific interface functions */ @@ -111,7 +108,7 @@ int i40e_init_lan_hmc(struct i40e_hw *hw, u32 txq_num, /* validate values requested by driver don't exceed HMC capacity */ if (txq_num > obj->max_cnt) { - ret_code = I40E_ERR_INVALID_HMC_OBJ_COUNT; + ret_code = -EINVAL; hw_dbg(hw, "i40e_init_lan_hmc: Tx context: asks for 0x%x but max allowed is 0x%x, returns error %d\n", txq_num, obj->max_cnt, ret_code); goto init_lan_hmc_out; @@ -134,7 +131,7 @@ int i40e_init_lan_hmc(struct i40e_hw *hw, u32 txq_num, /* validate values requested by driver don't exceed HMC capacity */ if (rxq_num > obj->max_cnt) { - ret_code = I40E_ERR_INVALID_HMC_OBJ_COUNT; + ret_code = -EINVAL; hw_dbg(hw, "i40e_init_lan_hmc: Rx context: asks for 0x%x but max allowed is 0x%x, returns error %d\n", rxq_num, obj->max_cnt, ret_code); goto init_lan_hmc_out; @@ -157,7 +154,7 @@ int i40e_init_lan_hmc(struct i40e_hw *hw, u32 txq_num, /* validate values requested by driver don't exceed HMC capacity */ if (fcoe_cntx_num > obj->max_cnt) { - ret_code = I40E_ERR_INVALID_HMC_OBJ_COUNT; + ret_code = -EINVAL; hw_dbg(hw, "i40e_init_lan_hmc: FCoE context: asks for 0x%x but max allowed is 0x%x, returns error %d\n", fcoe_cntx_num, obj->max_cnt, ret_code); goto init_lan_hmc_out; @@ -180,7 +177,7 @@ int i40e_init_lan_hmc(struct i40e_hw *hw, u32 txq_num, /* validate values requested by driver don't exceed HMC capacity */ if (fcoe_filt_num > obj->max_cnt) { - ret_code = I40E_ERR_INVALID_HMC_OBJ_COUNT; + ret_code = -EINVAL; hw_dbg(hw, "i40e_init_lan_hmc: FCoE filter: asks for 0x%x but max allowed is 0x%x, returns error %d\n", fcoe_filt_num, obj->max_cnt, ret_code); goto init_lan_hmc_out; @@ -289,30 +286,30 @@ static int i40e_create_lan_hmc_object(struct i40e_hw *hw, u32 i, j; if (NULL == info) { - ret_code = I40E_ERR_BAD_PTR; + ret_code = -EINVAL; hw_dbg(hw, "i40e_create_lan_hmc_object: bad info ptr\n"); goto exit; } if (NULL == info->hmc_info) { - ret_code = I40E_ERR_BAD_PTR; + ret_code = -EINVAL; hw_dbg(hw, "i40e_create_lan_hmc_object: bad hmc_info ptr\n"); goto exit; } if (I40E_HMC_INFO_SIGNATURE != info->hmc_info->signature) { - ret_code = I40E_ERR_BAD_PTR; + ret_code = -EINVAL; hw_dbg(hw, "i40e_create_lan_hmc_object: bad signature\n"); goto exit; } if (info->start_idx >= info->hmc_info->hmc_obj[info->rsrc_type].cnt) { - ret_code = I40E_ERR_INVALID_HMC_OBJ_INDEX; + ret_code = -EINVAL; hw_dbg(hw, "i40e_create_lan_hmc_object: returns error %d\n", ret_code); goto exit; } if ((info->start_idx + info->count) > info->hmc_info->hmc_obj[info->rsrc_type].cnt) { - ret_code = I40E_ERR_INVALID_HMC_OBJ_COUNT; + ret_code = -EINVAL; hw_dbg(hw, "i40e_create_lan_hmc_object: returns error %d\n", ret_code); goto exit; @@ -324,8 +321,8 @@ static int i40e_create_lan_hmc_object(struct i40e_hw *hw, &sd_idx, &sd_lmt); if (sd_idx >= info->hmc_info->sd_table.sd_cnt || sd_lmt > info->hmc_info->sd_table.sd_cnt) { - ret_code = I40E_ERR_INVALID_SD_INDEX; - goto exit; + ret_code = -EINVAL; + goto exit; } /* find pd index */ I40E_FIND_PD_INDEX_LIMIT(info->hmc_info, info->rsrc_type, @@ -393,7 +390,7 @@ static int i40e_create_lan_hmc_object(struct i40e_hw *hw, j, sd_entry->entry_type); break; default: - ret_code = I40E_ERR_INVALID_SD_TYPE; + ret_code = -EINVAL; goto exit; } } @@ -417,7 +414,7 @@ exit_sd_error: i40e_remove_sd_bp(hw, info->hmc_info, (j - 1)); break; default: - ret_code = I40E_ERR_INVALID_SD_TYPE; + ret_code = -EINVAL; break; } j--; @@ -474,7 +471,7 @@ try_type_paged: break; default: /* unsupported type */ - ret_code = I40E_ERR_INVALID_SD_TYPE; + ret_code = -EINVAL; hw_dbg(hw, "i40e_configure_lan_hmc: Unknown SD type: %d\n", ret_code); goto configure_lan_hmc_out; @@ -530,34 +527,34 @@ static int i40e_delete_lan_hmc_object(struct i40e_hw *hw, u32 i, j; if (NULL == info) { - ret_code = I40E_ERR_BAD_PTR; + ret_code = -EINVAL; hw_dbg(hw, "i40e_delete_hmc_object: bad info ptr\n"); goto exit; } if (NULL == info->hmc_info) { - ret_code = I40E_ERR_BAD_PTR; + ret_code = -EINVAL; hw_dbg(hw, "i40e_delete_hmc_object: bad info->hmc_info ptr\n"); goto exit; } if (I40E_HMC_INFO_SIGNATURE != info->hmc_info->signature) { - ret_code = I40E_ERR_BAD_PTR; + ret_code = -EINVAL; hw_dbg(hw, "i40e_delete_hmc_object: bad hmc_info->signature\n"); goto exit; } if (NULL == info->hmc_info->sd_table.sd_entry) { - ret_code = I40E_ERR_BAD_PTR; + ret_code = -EINVAL; hw_dbg(hw, "i40e_delete_hmc_object: bad sd_entry\n"); goto exit; } if (NULL == info->hmc_info->hmc_obj) { - ret_code = I40E_ERR_BAD_PTR; + ret_code = -EINVAL; hw_dbg(hw, "i40e_delete_hmc_object: bad hmc_info->hmc_obj\n"); goto exit; } if (info->start_idx >= info->hmc_info->hmc_obj[info->rsrc_type].cnt) { - ret_code = I40E_ERR_INVALID_HMC_OBJ_INDEX; + ret_code = -EINVAL; hw_dbg(hw, "i40e_delete_hmc_object: returns error %d\n", ret_code); goto exit; @@ -565,7 +562,7 @@ static int i40e_delete_lan_hmc_object(struct i40e_hw *hw, if ((info->start_idx + info->count) > info->hmc_info->hmc_obj[info->rsrc_type].cnt) { - ret_code = I40E_ERR_INVALID_HMC_OBJ_COUNT; + ret_code = -EINVAL; hw_dbg(hw, "i40e_delete_hmc_object: returns error %d\n", ret_code); goto exit; @@ -599,7 +596,7 @@ static int i40e_delete_lan_hmc_object(struct i40e_hw *hw, &sd_idx, &sd_lmt); if (sd_idx >= info->hmc_info->sd_table.sd_cnt || sd_lmt > info->hmc_info->sd_table.sd_cnt) { - ret_code = I40E_ERR_INVALID_SD_INDEX; + ret_code = -EINVAL; goto exit; } @@ -987,29 +984,29 @@ int i40e_hmc_get_object_va(struct i40e_hw *hw, u8 **object_base, int ret_code = 0; if (NULL == hmc_info) { - ret_code = I40E_ERR_BAD_PTR; + ret_code = -EINVAL; hw_dbg(hw, "i40e_hmc_get_object_va: bad hmc_info ptr\n"); goto exit; } if (NULL == hmc_info->hmc_obj) { - ret_code = I40E_ERR_BAD_PTR; + ret_code = -EINVAL; hw_dbg(hw, "i40e_hmc_get_object_va: bad hmc_info->hmc_obj ptr\n"); goto exit; } if (NULL == object_base) { - ret_code = I40E_ERR_BAD_PTR; + ret_code = -EINVAL; hw_dbg(hw, "i40e_hmc_get_object_va: bad object_base ptr\n"); goto exit; } if (I40E_HMC_INFO_SIGNATURE != hmc_info->signature) { - ret_code = I40E_ERR_BAD_PTR; + ret_code = -EINVAL; hw_dbg(hw, "i40e_hmc_get_object_va: bad hmc_info->signature\n"); goto exit; } if (obj_idx >= hmc_info->hmc_obj[rsrc_type].cnt) { hw_dbg(hw, "i40e_hmc_get_object_va: returns error %d\n", ret_code); - ret_code = I40E_ERR_INVALID_HMC_OBJ_INDEX; + ret_code = -EINVAL; goto exit; } /* find sd index and limit */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.h b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.h index 9f960404c2b3..305a276953b0 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.h +++ b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.h @@ -4,6 +4,8 @@ #ifndef _I40E_LAN_HMC_H_ #define _I40E_LAN_HMC_H_ +#include "i40e_hmc.h" + /* forward-declare the HW struct for the compiler */ struct i40e_hw; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index a86bfa3bba74..1ab8dbe2d880 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1,19 +1,22 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2021 Intel Corporation. */ -#include <linux/etherdevice.h> -#include <linux/of_net.h> -#include <linux/pci.h> -#include <linux/bpf.h> #include <generated/utsrelease.h> #include <linux/crash_dump.h> +#include <linux/if_bridge.h> +#include <linux/if_macvlan.h> +#include <linux/module.h> +#include <net/pkt_cls.h> +#include <net/xdp_sock_drv.h> /* Local includes */ #include "i40e.h" +#include "i40e_devids.h" #include "i40e_diag.h" +#include "i40e_lan_hmc.h" +#include "i40e_virtchnl_pf.h" #include "i40e_xsk.h" -#include <net/udp_tunnel.h> -#include <net/xdp_sock_drv.h> + /* All i40e tracepoints are defined by the include below, which * must be included exactly once across the whole kernel with * CREATE_TRACE_POINTS defined @@ -120,16 +123,27 @@ static void netdev_hw_addr_refcnt(struct i40e_mac_filter *f, } /** - * i40e_allocate_dma_mem_d - OS specific memory alloc for shared code + * i40e_hw_to_dev - get device pointer from the hardware structure + * @hw: pointer to the device HW structure + **/ +struct device *i40e_hw_to_dev(struct i40e_hw *hw) +{ + struct i40e_pf *pf = i40e_hw_to_pf(hw); + + return &pf->pdev->dev; +} + +/** + * i40e_allocate_dma_mem - OS specific memory alloc for shared code * @hw: pointer to the HW structure * @mem: ptr to mem struct to fill out * @size: size of memory requested * @alignment: what to align the allocation to **/ -int i40e_allocate_dma_mem_d(struct i40e_hw *hw, struct i40e_dma_mem *mem, - u64 size, u32 alignment) +int i40e_allocate_dma_mem(struct i40e_hw *hw, struct i40e_dma_mem *mem, + u64 size, u32 alignment) { - struct i40e_pf *pf = (struct i40e_pf *)hw->back; + struct i40e_pf *pf = i40e_hw_to_pf(hw); mem->size = ALIGN(size, alignment); mem->va = dma_alloc_coherent(&pf->pdev->dev, mem->size, &mem->pa, @@ -141,13 +155,13 @@ int i40e_allocate_dma_mem_d(struct i40e_hw *hw, struct i40e_dma_mem *mem, } /** - * i40e_free_dma_mem_d - OS specific memory free for shared code + * i40e_free_dma_mem - OS specific memory free for shared code * @hw: pointer to the HW structure * @mem: ptr to mem struct to free **/ -int i40e_free_dma_mem_d(struct i40e_hw *hw, struct i40e_dma_mem *mem) +int i40e_free_dma_mem(struct i40e_hw *hw, struct i40e_dma_mem *mem) { - struct i40e_pf *pf = (struct i40e_pf *)hw->back; + struct i40e_pf *pf = i40e_hw_to_pf(hw); dma_free_coherent(&pf->pdev->dev, mem->size, mem->va, mem->pa); mem->va = NULL; @@ -158,13 +172,13 @@ int i40e_free_dma_mem_d(struct i40e_hw *hw, struct i40e_dma_mem *mem) } /** - * i40e_allocate_virt_mem_d - OS specific memory alloc for shared code + * i40e_allocate_virt_mem - OS specific memory alloc for shared code * @hw: pointer to the HW structure * @mem: ptr to mem struct to fill out * @size: size of memory requested **/ -int i40e_allocate_virt_mem_d(struct i40e_hw *hw, struct i40e_virt_mem *mem, - u32 size) +int i40e_allocate_virt_mem(struct i40e_hw *hw, struct i40e_virt_mem *mem, + u32 size) { mem->size = size; mem->va = kzalloc(size, GFP_KERNEL); @@ -176,11 +190,11 @@ int i40e_allocate_virt_mem_d(struct i40e_hw *hw, struct i40e_virt_mem *mem, } /** - * i40e_free_virt_mem_d - OS specific memory free for shared code + * i40e_free_virt_mem - OS specific memory free for shared code * @hw: pointer to the HW structure * @mem: ptr to mem struct to free **/ -int i40e_free_virt_mem_d(struct i40e_hw *hw, struct i40e_virt_mem *mem) +int i40e_free_virt_mem(struct i40e_hw *hw, struct i40e_virt_mem *mem) { /* it's ok to kfree a NULL pointer */ kfree(mem->va); @@ -489,6 +503,7 @@ static void i40e_get_netdev_stats_struct(struct net_device *netdev, stats->tx_dropped = vsi_stats->tx_dropped; stats->rx_errors = vsi_stats->rx_errors; stats->rx_dropped = vsi_stats->rx_dropped; + stats->rx_missed_errors = vsi_stats->rx_missed_errors; stats->rx_crc_errors = vsi_stats->rx_crc_errors; stats->rx_length_errors = vsi_stats->rx_length_errors; } @@ -680,17 +695,13 @@ i40e_stats_update_rx_discards(struct i40e_vsi *vsi, struct i40e_hw *hw, struct i40e_eth_stats *stat_offset, struct i40e_eth_stats *stat) { - u64 rx_rdpc, rx_rxerr; - i40e_stat_update32(hw, I40E_GLV_RDPC(stat_idx), offset_loaded, - &stat_offset->rx_discards, &rx_rdpc); + &stat_offset->rx_discards, &stat->rx_discards); i40e_stat_update64(hw, I40E_GL_RXERR1H(i40e_compute_pci_to_hw_id(vsi, hw)), I40E_GL_RXERR1L(i40e_compute_pci_to_hw_id(vsi, hw)), offset_loaded, &stat_offset->rx_discards_other, - &rx_rxerr); - - stat->rx_discards = rx_rdpc + rx_rxerr; + &stat->rx_discards_other); } /** @@ -712,9 +723,6 @@ void i40e_update_eth_stats(struct i40e_vsi *vsi) i40e_stat_update32(hw, I40E_GLV_TEPC(stat_idx), vsi->stat_offsets_loaded, &oes->tx_errors, &es->tx_errors); - i40e_stat_update32(hw, I40E_GLV_RDPC(stat_idx), - vsi->stat_offsets_loaded, - &oes->rx_discards, &es->rx_discards); i40e_stat_update32(hw, I40E_GLV_RUPP(stat_idx), vsi->stat_offsets_loaded, &oes->rx_unknown_protocol, &es->rx_unknown_protocol); @@ -971,8 +979,10 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) ns->tx_errors = es->tx_errors; ons->multicast = oes->rx_multicast; ns->multicast = es->rx_multicast; - ons->rx_dropped = oes->rx_discards; - ns->rx_dropped = es->rx_discards; + ons->rx_dropped = oes->rx_discards_other; + ns->rx_dropped = es->rx_discards_other; + ons->rx_missed_errors = oes->rx_discards; + ns->rx_missed_errors = es->rx_discards; ons->tx_dropped = oes->tx_discards; ns->tx_dropped = es->tx_discards; @@ -3586,11 +3596,6 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) if (ring->xsk_pool) { ring->rx_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool); - /* For AF_XDP ZC, we disallow packets to span on - * multiple buffers, thus letting us skip that - * handling in the fast-path. - */ - chain_len = 1; ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_XSK_BUFF_POOL, NULL); @@ -5715,7 +5720,7 @@ int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset) int ret; if (!vsi) - return I40E_ERR_PARAM; + return -EINVAL; pf = vsi->back; hw = &pf->hw; @@ -7159,7 +7164,7 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf) */ if (pf->hw_features & I40E_HW_NO_DCB_SUPPORT) { dev_info(&pf->pdev->dev, "DCB is not supported.\n"); - err = I40E_NOT_SUPPORTED; + err = -EOPNOTSUPP; goto out; } if (pf->flags & I40E_FLAG_DISABLE_FW_LLDP) { @@ -7469,7 +7474,7 @@ static int i40e_force_link_state(struct i40e_pf *pf, bool is_up) if (pf->flags & I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENABLED) non_zero_phy_type = true; else if (is_up && abilities.phy_type != 0 && abilities.link_speed != 0) - return I40E_SUCCESS; + return 0; /* To force link we need to set bits for all supported PHY types, * but there are now more than 32, so we need to split the bitmap @@ -7520,7 +7525,7 @@ static int i40e_force_link_state(struct i40e_pf *pf, bool is_up) i40e_aq_set_link_restart_an(hw, is_up, NULL); - return I40E_SUCCESS; + return 0; } /** @@ -8367,7 +8372,7 @@ int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, }; if (filter->flags >= ARRAY_SIZE(flag_table)) - return I40E_ERR_CONFIG; + return -EIO; memset(&cld_filter, 0, sizeof(cld_filter)); @@ -8531,15 +8536,15 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi, u8 field_flags = 0; if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_VLAN) | - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_PORTS) | - BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) { - dev_err(&pf->pdev->dev, "Unsupported key used: 0x%x\n", + ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID))) { + dev_err(&pf->pdev->dev, "Unsupported key used: 0x%llx\n", dissector->used_keys); return -EOPNOTSUPP; } @@ -8581,7 +8586,7 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi, } else { dev_err(&pf->pdev->dev, "Bad ether dest mask %pM\n", match.mask->dst); - return I40E_ERR_CONFIG; + return -EIO; } } @@ -8591,7 +8596,7 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi, } else { dev_err(&pf->pdev->dev, "Bad ether src mask %pM\n", match.mask->src); - return I40E_ERR_CONFIG; + return -EIO; } } ether_addr_copy(filter->dst_mac, match.key->dst); @@ -8609,7 +8614,7 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi, } else { dev_err(&pf->pdev->dev, "Bad vlan mask 0x%04x\n", match.mask->vlan_id); - return I40E_ERR_CONFIG; + return -EIO; } } @@ -8633,7 +8638,7 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi, } else { dev_err(&pf->pdev->dev, "Bad ip dst mask %pI4b\n", &match.mask->dst); - return I40E_ERR_CONFIG; + return -EIO; } } @@ -8643,13 +8648,13 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi, } else { dev_err(&pf->pdev->dev, "Bad ip src mask %pI4b\n", &match.mask->src); - return I40E_ERR_CONFIG; + return -EIO; } } if (field_flags & I40E_CLOUD_FIELD_TEN_ID) { dev_err(&pf->pdev->dev, "Tenant id not allowed for ip filter\n"); - return I40E_ERR_CONFIG; + return -EIO; } filter->dst_ipv4 = match.key->dst; filter->src_ipv4 = match.key->src; @@ -8667,7 +8672,7 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi, ipv6_addr_loopback(&match.key->src)) { dev_err(&pf->pdev->dev, "Bad ipv6, addr is LOOPBACK\n"); - return I40E_ERR_CONFIG; + return -EIO; } if (!ipv6_addr_any(&match.mask->dst) || !ipv6_addr_any(&match.mask->src)) @@ -8689,7 +8694,7 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi, } else { dev_err(&pf->pdev->dev, "Bad src port mask 0x%04x\n", be16_to_cpu(match.mask->src)); - return I40E_ERR_CONFIG; + return -EIO; } } @@ -8699,7 +8704,7 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi, } else { dev_err(&pf->pdev->dev, "Bad dst port mask 0x%04x\n", be16_to_cpu(match.mask->dst)); - return I40E_ERR_CONFIG; + return -EIO; } } @@ -9907,11 +9912,11 @@ static void i40e_link_event(struct i40e_pf *pf) status = i40e_get_link_status(&pf->hw, &new_link); /* On success, disable temp link polling */ - if (status == I40E_SUCCESS) { + if (status == 0) { clear_bit(__I40E_TEMP_LINK_POLLING, pf->state); } else { /* Enable link polling temporarily until i40e_get_link_status - * returns I40E_SUCCESS + * returns 0 */ set_bit(__I40E_TEMP_LINK_POLLING, pf->state); dev_dbg(&pf->pdev->dev, "couldn't get link state, status: %d\n", @@ -10165,7 +10170,7 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf) do { ret = i40e_clean_arq_element(hw, &event, &pending); - if (ret == I40E_ERR_ADMIN_QUEUE_NO_WORK) + if (ret == -EALREADY) break; else if (ret) { dev_info(&pf->pdev->dev, "ARQ event error %d\n", ret); @@ -10793,7 +10798,9 @@ static void i40e_get_oem_version(struct i40e_hw *hw) &gen_snap); i40e_read_nvm_word(hw, block_offset + I40E_NVM_OEM_RELEASE_OFFSET, &release); - hw->nvm.oem_ver = (gen_snap << I40E_OEM_SNAP_SHIFT) | release; + hw->nvm.oem_ver = + FIELD_PREP(I40E_OEM_GEN_MASK | I40E_OEM_SNAP_MASK, gen_snap) | + FIELD_PREP(I40E_OEM_RELEASE_MASK, release); hw->nvm.eetrack = I40E_OEM_EETRACK_ID; } @@ -12575,7 +12582,7 @@ int i40e_commit_partition_bw_setting(struct i40e_pf *pf) dev_info(&pf->pdev->dev, "Commit BW only works on partition 1! This is partition %d", pf->hw.partition_id); - ret = I40E_NOT_SUPPORTED; + ret = -EOPNOTSUPP; goto bw_commit_out; } @@ -12657,10 +12664,10 @@ static bool i40e_is_total_port_shutdown_enabled(struct i40e_pf *pf) #define I40E_LINK_BEHAVIOR_WORD_LENGTH 0x1 #define I40E_LINK_BEHAVIOR_OS_FORCED_ENABLED BIT(0) #define I40E_LINK_BEHAVIOR_PORT_BIT_LENGTH 4 - int read_status = I40E_SUCCESS; u16 sr_emp_sr_settings_ptr = 0; u16 features_enable = 0; u16 link_behavior = 0; + int read_status = 0; bool ret = false; read_status = i40e_read_nvm_word(&pf->hw, @@ -13823,6 +13830,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_XSK_ZEROCOPY | NETDEV_XDP_ACT_RX_SG; + netdev->xdp_zc_max_segs = I40E_MAX_BUFFER_TXD; } else { /* Relate the VSI_VMDQ name to the VSI_MAIN name. Note that we * are still limited by IFNAMSIZ, but we're adding 'v%d\0' to @@ -14205,6 +14213,7 @@ int i40e_vsi_release(struct i40e_vsi *vsi) } set_bit(__I40E_VSI_RELEASING, vsi->state); uplink_seid = vsi->uplink_seid; + if (vsi->type != I40E_VSI_SRIOV) { if (vsi->netdev_registered) { vsi->netdev_registered = false; @@ -14218,6 +14227,9 @@ int i40e_vsi_release(struct i40e_vsi *vsi) i40e_vsi_disable_irq(vsi); } + if (vsi->type == I40E_VSI_MAIN) + i40e_devlink_destroy_port(pf); + spin_lock_bh(&vsi->mac_filter_hash_lock); /* clear the sync flag on all filters */ @@ -14398,6 +14410,8 @@ err_rings: free_netdev(vsi->netdev); vsi->netdev = NULL; } + if (vsi->type == I40E_VSI_MAIN) + i40e_devlink_destroy_port(pf); i40e_aq_delete_element(&pf->hw, vsi->seid, NULL); err_vsi: i40e_vsi_clear(vsi); @@ -14538,9 +14552,15 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type, ret = i40e_netif_set_realnum_tx_rx_queues(vsi); if (ret) goto err_netdev; + if (vsi->type == I40E_VSI_MAIN) { + ret = i40e_devlink_create_port(pf); + if (ret) + goto err_netdev; + SET_NETDEV_DEVLINK_PORT(vsi->netdev, &pf->devlink_port); + } ret = register_netdev(vsi->netdev); if (ret) - goto err_netdev; + goto err_dl_port; vsi->netdev_registered = true; netif_carrier_off(vsi->netdev); #ifdef CONFIG_I40E_DCB @@ -14583,6 +14603,9 @@ err_msix: free_netdev(vsi->netdev); vsi->netdev = NULL; } +err_dl_port: + if (vsi->type == I40E_VSI_MAIN) + i40e_devlink_destroy_port(pf); err_netdev: i40e_aq_delete_element(&pf->hw, vsi->seid, NULL); err_vsi: @@ -15467,12 +15490,12 @@ static int i40e_pf_loop_reset(struct i40e_pf *pf) int ret; ret = i40e_pf_reset(hw); - while (ret != I40E_SUCCESS && time_before(jiffies, time_end)) { + while (ret != 0 && time_before(jiffies, time_end)) { usleep_range(10000, 20000); ret = i40e_pf_reset(hw); } - if (ret == I40E_SUCCESS) + if (ret == 0) pf->pfr_count++; else dev_info(&pf->pdev->dev, "PF reset failed: %d\n", ret); @@ -15515,10 +15538,10 @@ static int i40e_handle_resets(struct i40e_pf *pf) const int pfr = i40e_pf_loop_reset(pf); const bool is_empr = i40e_check_fw_empr(pf); - if (is_empr || pfr != I40E_SUCCESS) + if (is_empr || pfr != 0) dev_crit(&pf->pdev->dev, "Entering recovery mode due to repeated FW resets. This may take several minutes. Refer to the Intel(R) Ethernet Adapters and Devices User Guide.\n"); - return is_empr ? I40E_ERR_RESET_FAILED : pfr; + return is_empr ? -EIO : pfr; } /** @@ -15613,7 +15636,7 @@ err_switch_setup: iounmap(hw->hw_addr); pci_release_mem_regions(pf->pdev); pci_disable_device(pf->pdev); - kfree(pf); + i40e_free_pf(pf); return err; } @@ -15627,10 +15650,10 @@ err_switch_setup: **/ static inline void i40e_set_subsystem_device_id(struct i40e_hw *hw) { - struct pci_dev *pdev = ((struct i40e_pf *)hw->back)->pdev; + struct i40e_pf *pf = i40e_hw_to_pf(hw); - hw->subsystem_device_id = pdev->subsystem_device ? - pdev->subsystem_device : + hw->subsystem_device_id = pf->pdev->subsystem_device ? + pf->pdev->subsystem_device : (ushort)(rd32(hw, I40E_PFPCI_SUBSYSID) & USHRT_MAX); } @@ -15655,6 +15678,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct i40e_hw *hw; static u16 pfs_found; u16 wol_nvm_bits; + char nvm_ver[32]; u16 link_status; #ifdef CONFIG_I40E_DCB int status; @@ -15690,7 +15714,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * the Admin Queue structures and then querying for the * device's current profile information. */ - pf = kzalloc(sizeof(*pf), GFP_KERNEL); + pf = i40e_alloc_pf(&pdev->dev); if (!pf) { err = -ENOMEM; goto err_pf_alloc; @@ -15700,7 +15724,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) set_bit(__I40E_DOWN, pf->state); hw = &pf->hw; - hw->back = pf; pf->ioremap_len = min_t(int, pci_resource_len(pdev, 0), I40E_MAX_CSR_SPACE); @@ -15811,7 +15834,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = i40e_init_adminq(hw); if (err) { - if (err == I40E_ERR_FIRMWARE_API_VERSION) + if (err == -EIO) dev_info(&pdev->dev, "The driver for the device stopped because the NVM image v%u.%u is newer than expected v%u.%u. You must install the most recent version of the network driver.\n", hw->aq.api_maj_ver, @@ -15825,13 +15848,15 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_pf_reset; } i40e_get_oem_version(hw); + i40e_get_pba_string(hw); /* provide nvm, fw, api versions, vendor:device id, subsys vendor:device id */ + i40e_nvm_version_str(hw, nvm_ver, sizeof(nvm_ver)); dev_info(&pdev->dev, "fw %d.%d.%05d api %d.%d nvm %s [%04x:%04x] [%04x:%04x]\n", hw->aq.fw_maj_ver, hw->aq.fw_min_ver, hw->aq.fw_build, - hw->aq.api_maj_ver, hw->aq.api_min_ver, - i40e_nvm_version_str(hw), hw->vendor_id, hw->device_id, - hw->subsystem_vendor_id, hw->subsystem_device_id); + hw->aq.api_maj_ver, hw->aq.api_min_ver, nvm_ver, + hw->vendor_id, hw->device_id, hw->subsystem_vendor_id, + hw->subsystem_device_id); if (hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR && hw->aq.api_min_ver > I40E_FW_MINOR_VERSION(hw)) @@ -16199,7 +16224,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) I40E_PRTGL_SAH_MFS_MASK) >> I40E_PRTGL_SAH_MFS_SHIFT; if (val < MAX_FRAME_SIZE_DEFAULT) dev_warn(&pdev->dev, "MFS for port %x has been set below the default: %x\n", - i, val); + pf->hw.port, val); /* Add a filter to drop all Flow control frames from any VSI from being * transmitted. By doing so we stop a malicious VF from sending out @@ -16218,6 +16243,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* print a string summarizing features */ i40e_print_features(pf); + i40e_devlink_register(pf); + return 0; /* Unwind what we've done if something failed in the setup */ @@ -16238,7 +16265,7 @@ err_adminq_setup: err_pf_reset: iounmap(hw->hw_addr); err_ioremap: - kfree(pf); + i40e_free_pf(pf); err_pf_alloc: pci_release_mem_regions(pdev); err_pci_reg: @@ -16263,6 +16290,8 @@ static void i40e_remove(struct pci_dev *pdev) int ret_code; int i; + i40e_devlink_unregister(pf); + i40e_dbg_pf_exit(pf); i40e_ptp_stop(pf); @@ -16324,11 +16353,15 @@ static void i40e_remove(struct pci_dev *pdev) i40e_switch_branch_release(pf->veb[i]); } - /* Now we can shutdown the PF's VSI, just before we kill + /* Now we can shutdown the PF's VSIs, just before we kill * adminq and hmc. */ - if (pf->vsi[pf->lan_vsi]) - i40e_vsi_release(pf->vsi[pf->lan_vsi]); + for (i = pf->num_alloc_vsi; i--;) + if (pf->vsi[i]) { + i40e_vsi_close(pf->vsi[i]); + i40e_vsi_release(pf->vsi[i]); + pf->vsi[i] = NULL; + } i40e_cloud_filter_exit(pf); @@ -16384,7 +16417,7 @@ unmap: kfree(pf->vsi); iounmap(hw->hw_addr); - kfree(pf); + i40e_free_pf(pf); pci_release_mem_regions(pdev); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c index f99c1f7fec40..77cdbfc19d47 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c +++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ +#include <linux/delay.h> +#include "i40e_alloc.h" #include "i40e_prototype.h" /** @@ -37,7 +39,7 @@ int i40e_init_nvm(struct i40e_hw *hw) nvm->blank_nvm_mode = false; } else { /* Blank programming mode */ nvm->blank_nvm_mode = true; - ret_code = I40E_ERR_NVM_BLANK_MODE; + ret_code = -EIO; i40e_debug(hw, I40E_DEBUG_NVM, "NVM init error: unsupported blank mode.\n"); } @@ -111,8 +113,8 @@ i40e_i40e_acquire_nvm_exit: **/ void i40e_release_nvm(struct i40e_hw *hw) { - int ret_code = I40E_SUCCESS; u32 total_delay = 0; + int ret_code = 0; if (hw->nvm.blank_nvm_mode) return; @@ -122,7 +124,7 @@ void i40e_release_nvm(struct i40e_hw *hw) /* there are some rare cases when trying to release the resource * results in an admin Q timeout, so handle them correctly */ - while ((ret_code == I40E_ERR_ADMIN_QUEUE_TIMEOUT) && + while ((ret_code == -EIO) && (total_delay < hw->aq.asq_cmd_timeout)) { usleep_range(1000, 2000); ret_code = i40e_aq_release_resource(hw, @@ -140,7 +142,7 @@ void i40e_release_nvm(struct i40e_hw *hw) **/ static int i40e_poll_sr_srctl_done_bit(struct i40e_hw *hw) { - int ret_code = I40E_ERR_TIMEOUT; + int ret_code = -EIO; u32 srctl, wait_cnt; /* Poll the I40E_GLNVM_SRCTL until the done bit is set */ @@ -152,7 +154,7 @@ static int i40e_poll_sr_srctl_done_bit(struct i40e_hw *hw) } udelay(5); } - if (ret_code == I40E_ERR_TIMEOUT) + if (ret_code == -EIO) i40e_debug(hw, I40E_DEBUG_NVM, "Done bit in GLNVM_SRCTL not set"); return ret_code; } @@ -168,14 +170,14 @@ static int i40e_poll_sr_srctl_done_bit(struct i40e_hw *hw) static int i40e_read_nvm_word_srctl(struct i40e_hw *hw, u16 offset, u16 *data) { - int ret_code = I40E_ERR_TIMEOUT; + int ret_code = -EIO; u32 sr_reg; if (offset >= hw->nvm.sr_size) { i40e_debug(hw, I40E_DEBUG_NVM, "NVM read error: offset %d beyond Shadow RAM limit %d\n", offset, hw->nvm.sr_size); - ret_code = I40E_ERR_PARAM; + ret_code = -EINVAL; goto read_nvm_exit; } @@ -222,7 +224,7 @@ static int i40e_read_nvm_aq(struct i40e_hw *hw, bool last_command) { struct i40e_asq_cmd_details cmd_details; - int ret_code = I40E_ERR_NVM; + int ret_code = -EIO; memset(&cmd_details, 0, sizeof(cmd_details)); cmd_details.wb_desc = &hw->nvm_wb_desc; @@ -267,7 +269,7 @@ static int i40e_read_nvm_aq(struct i40e_hw *hw, static int i40e_read_nvm_word_aq(struct i40e_hw *hw, u16 offset, u16 *data) { - int ret_code = I40E_ERR_TIMEOUT; + int ret_code = -EIO; ret_code = i40e_read_nvm_aq(hw, 0x0, offset, 1, data, true); *data = le16_to_cpu(*(__le16 *)data); @@ -348,7 +350,7 @@ int i40e_read_nvm_module_data(struct i40e_hw *hw, i40e_debug(hw, I40E_DEBUG_ALL, "Reading nvm word failed.Error code: %d.\n", status); - return I40E_ERR_NVM; + return -EIO; } } #define I40E_NVM_INVALID_PTR_VAL 0x7FFF @@ -358,7 +360,7 @@ int i40e_read_nvm_module_data(struct i40e_hw *hw, if (ptr_value == I40E_NVM_INVALID_PTR_VAL || ptr_value == I40E_NVM_INVALID_VAL) { i40e_debug(hw, I40E_DEBUG_ALL, "Pointer not initialized.\n"); - return I40E_ERR_BAD_PTR; + return -EINVAL; } /* Check whether the module is in SR mapped area or outside */ @@ -367,7 +369,7 @@ int i40e_read_nvm_module_data(struct i40e_hw *hw, i40e_debug(hw, I40E_DEBUG_ALL, "Reading nvm data failed. Pointer points outside of the Shared RAM mapped area.\n"); - return I40E_ERR_PARAM; + return -EINVAL; } else { /* Read from the Shadow RAM */ @@ -377,7 +379,7 @@ int i40e_read_nvm_module_data(struct i40e_hw *hw, i40e_debug(hw, I40E_DEBUG_ALL, "Reading nvm word failed.Error code: %d.\n", status); - return I40E_ERR_NVM; + return -EIO; } offset = ptr_value + module_offset + specific_ptr + @@ -549,7 +551,7 @@ static int i40e_write_nvm_aq(struct i40e_hw *hw, u8 module_pointer, bool last_command) { struct i40e_asq_cmd_details cmd_details; - int ret_code = I40E_ERR_NVM; + int ret_code = -EIO; memset(&cmd_details, 0, sizeof(cmd_details)); cmd_details.wb_desc = &hw->nvm_wb_desc; @@ -614,7 +616,7 @@ static int i40e_calc_nvm_checksum(struct i40e_hw *hw, /* read pointer to VPD area */ ret_code = __i40e_read_nvm_word(hw, I40E_SR_VPD_PTR, &vpd_module); if (ret_code) { - ret_code = I40E_ERR_NVM_CHECKSUM; + ret_code = -EIO; goto i40e_calc_nvm_checksum_exit; } @@ -622,7 +624,7 @@ static int i40e_calc_nvm_checksum(struct i40e_hw *hw, ret_code = __i40e_read_nvm_word(hw, I40E_SR_PCIE_ALT_AUTO_LOAD_PTR, &pcie_alt_module); if (ret_code) { - ret_code = I40E_ERR_NVM_CHECKSUM; + ret_code = -EIO; goto i40e_calc_nvm_checksum_exit; } @@ -636,7 +638,7 @@ static int i40e_calc_nvm_checksum(struct i40e_hw *hw, ret_code = __i40e_read_nvm_buffer(hw, i, &words, data); if (ret_code) { - ret_code = I40E_ERR_NVM_CHECKSUM; + ret_code = -EIO; goto i40e_calc_nvm_checksum_exit; } } @@ -724,7 +726,7 @@ int i40e_validate_nvm_checksum(struct i40e_hw *hw, * calculated checksum */ if (checksum_local != checksum_sr) - ret_code = I40E_ERR_NVM_CHECKSUM; + ret_code = -EIO; /* If the user cares, return the calculated checksum */ if (checksum) @@ -839,7 +841,7 @@ int i40e_nvmupd_command(struct i40e_hw *hw, if (upd_cmd == I40E_NVMUPD_STATUS) { if (!cmd->data_size) { *perrno = -EFAULT; - return I40E_ERR_BUF_TOO_SHORT; + return -EINVAL; } bytes[0] = hw->nvmupd_state; @@ -896,7 +898,7 @@ int i40e_nvmupd_command(struct i40e_hw *hw, break; } - status = I40E_ERR_NOT_READY; + status = -EBUSY; *perrno = -EBUSY; break; @@ -904,7 +906,7 @@ int i40e_nvmupd_command(struct i40e_hw *hw, /* invalid state, should never happen */ i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: no such state %d\n", hw->nvmupd_state); - status = I40E_NOT_SUPPORTED; + status = -EOPNOTSUPP; *perrno = -ESRCH; break; } @@ -1045,7 +1047,7 @@ static int i40e_nvmupd_state_init(struct i40e_hw *hw, i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: bad cmd %s in init state\n", i40e_nvm_update_state_str[upd_cmd]); - status = I40E_ERR_NVM; + status = -EIO; *perrno = -ESRCH; break; } @@ -1087,7 +1089,7 @@ static int i40e_nvmupd_state_reading(struct i40e_hw *hw, i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: bad cmd %s in reading state.\n", i40e_nvm_update_state_str[upd_cmd]); - status = I40E_NOT_SUPPORTED; + status = -EOPNOTSUPP; *perrno = -ESRCH; break; } @@ -1174,7 +1176,7 @@ retry: i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: bad cmd %s in writing state.\n", i40e_nvm_update_state_str[upd_cmd]); - status = I40E_NOT_SUPPORTED; + status = -EOPNOTSUPP; *perrno = -ESRCH; break; } @@ -1398,7 +1400,7 @@ static int i40e_nvmupd_exec_aq(struct i40e_hw *hw, "NVMUPD: not enough aq desc bytes for exec, size %d < %d\n", cmd->data_size, aq_desc_len); *perrno = -EINVAL; - return I40E_ERR_PARAM; + return -EINVAL; } aq_desc = (struct i40e_aq_desc *)bytes; @@ -1473,7 +1475,7 @@ static int i40e_nvmupd_get_aq_result(struct i40e_hw *hw, i40e_debug(hw, I40E_DEBUG_NVM, "%s: offset too big %d > %d\n", __func__, cmd->offset, aq_total_len); *perrno = -EINVAL; - return I40E_ERR_PARAM; + return -EINVAL; } /* check copylength range */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_osdep.h b/drivers/net/ethernet/intel/i40e/i40e_osdep.h deleted file mode 100644 index 2bd4de03dafa..000000000000 --- a/drivers/net/ethernet/intel/i40e/i40e_osdep.h +++ /dev/null @@ -1,59 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#ifndef _I40E_OSDEP_H_ -#define _I40E_OSDEP_H_ - -#include <linux/types.h> -#include <linux/if_ether.h> -#include <linux/if_vlan.h> -#include <linux/tcp.h> -#include <linux/pci.h> -#include <linux/highuid.h> - -/* get readq/writeq support for 32 bit kernels, use the low-first version */ -#include <linux/io-64-nonatomic-lo-hi.h> - -/* File to be the magic between shared code and - * actual OS primitives - */ - -#define hw_dbg(hw, S, A...) \ -do { \ - dev_dbg(&((struct i40e_pf *)hw->back)->pdev->dev, S, ##A); \ -} while (0) - -#define wr32(a, reg, value) writel((value), ((a)->hw_addr + (reg))) -#define rd32(a, reg) readl((a)->hw_addr + (reg)) - -#define rd64(a, reg) readq((a)->hw_addr + (reg)) -#define i40e_flush(a) readl((a)->hw_addr + I40E_GLGEN_STAT) - -/* memory allocation tracking */ -struct i40e_dma_mem { - void *va; - dma_addr_t pa; - u32 size; -}; - -#define i40e_allocate_dma_mem(h, m, unused, s, a) \ - i40e_allocate_dma_mem_d(h, m, s, a) -#define i40e_free_dma_mem(h, m) i40e_free_dma_mem_d(h, m) - -struct i40e_virt_mem { - void *va; - u32 size; -}; - -#define i40e_allocate_virt_mem(h, m, s) i40e_allocate_virt_mem_d(h, m, s) -#define i40e_free_virt_mem(h, m) i40e_free_virt_mem_d(h, m) - -#define i40e_debug(h, m, s, ...) \ -do { \ - if (((m) & (h)->debug_mask)) \ - pr_info("i40e %02x:%02x.%x " s, \ - (h)->bus.bus_id, (h)->bus.device, \ - (h)->bus.func, ##__VA_ARGS__); \ -} while (0) - -#endif /* _I40E_OSDEP_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index fe845987d99a..001162042050 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -4,9 +4,10 @@ #ifndef _I40E_PROTOTYPE_H_ #define _I40E_PROTOTYPE_H_ -#include "i40e_type.h" -#include "i40e_alloc.h" +#include <linux/ethtool.h> #include <linux/avf/virtchnl.h> +#include "i40e_debug.h" +#include "i40e_type.h" /* Prototypes for shared code functions that are not in * the standard function pointer structures. These are @@ -18,7 +19,6 @@ /* adminq functions */ int i40e_init_adminq(struct i40e_hw *hw); void i40e_shutdown_adminq(struct i40e_hw *hw); -void i40e_adminq_init_ring_data(struct i40e_hw *hw); int i40e_clean_arq_element(struct i40e_hw *hw, struct i40e_arq_event_info *e, u16 *events_pending); @@ -51,7 +51,6 @@ i40e_asq_send_command_atomic_v2(struct i40e_hw *hw, void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc, void *buffer, u16 buf_len); -void i40e_idle_aq(struct i40e_hw *hw); bool i40e_check_asq_alive(struct i40e_hw *hw); int i40e_aq_queue_shutdown(struct i40e_hw *hw, bool unloading); const char *i40e_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err); @@ -117,9 +116,6 @@ int i40e_aq_set_link_restart_an(struct i40e_hw *hw, int i40e_aq_get_link_info(struct i40e_hw *hw, bool enable_lse, struct i40e_link_status *link, struct i40e_asq_cmd_details *cmd_details); -int i40e_aq_set_local_advt_reg(struct i40e_hw *hw, - u64 advt_reg, - struct i40e_asq_cmd_details *cmd_details); int i40e_aq_send_driver_version(struct i40e_hw *hw, struct i40e_driver_version *dv, struct i40e_asq_cmd_details *cmd_details); @@ -269,9 +265,6 @@ int i40e_aq_config_vsi_bw_limit(struct i40e_hw *hw, struct i40e_asq_cmd_details *cmd_details); int i40e_aq_dcb_updated(struct i40e_hw *hw, struct i40e_asq_cmd_details *cmd_details); -int i40e_aq_config_switch_comp_bw_limit(struct i40e_hw *hw, - u16 seid, u16 credit, u8 max_bw, - struct i40e_asq_cmd_details *cmd_details); int i40e_aq_config_vsi_tc_bw(struct i40e_hw *hw, u16 seid, struct i40e_aqc_configure_vsi_tc_bw_data *bw_data, struct i40e_asq_cmd_details *cmd_details); @@ -348,9 +341,7 @@ i40e_aq_configure_partition_bw(struct i40e_hw *hw, struct i40e_aqc_configure_partition_bw_data *bw_data, struct i40e_asq_cmd_details *cmd_details); int i40e_get_port_mac_addr(struct i40e_hw *hw, u8 *mac_addr); -int i40e_read_pba_string(struct i40e_hw *hw, u8 *pba_num, - u32 pba_num_size); -int i40e_validate_mac_addr(u8 *mac_addr); +void i40e_get_pba_string(struct i40e_hw *hw); void i40e_pre_tx_queue_cfg(struct i40e_hw *hw, u32 queue, bool enable); /* prototype for functions used for NVM access */ int i40e_init_nvm(struct i40e_hw *hw); @@ -425,14 +416,6 @@ i40e_virtchnl_link_speed(enum i40e_aq_link_speed link_speed) /* prototype for functions used for SW locks */ /* i40e_common for VF drivers*/ -void i40e_vf_parse_hw_config(struct i40e_hw *hw, - struct virtchnl_vf_resource *msg); -int i40e_vf_reset(struct i40e_hw *hw); -int i40e_aq_send_msg_to_pf(struct i40e_hw *hw, - enum virtchnl_ops v_opcode, - int v_retval, - u8 *msg, u16 msglen, - struct i40e_asq_cmd_details *cmd_details); int i40e_set_filter_control(struct i40e_hw *hw, struct i40e_filter_control_settings *settings); int i40e_aq_add_rem_control_packet_filter(struct i40e_hw *hw, @@ -514,4 +497,8 @@ int i40e_add_pinfo_to_list(struct i40e_hw *hw, struct i40e_profile_segment *profile, u8 *profile_info_sec, u32 track_id); + +/* i40e_ddp */ +int i40e_ddp_flash(struct net_device *netdev, struct ethtool_flash *flash); + #endif /* _I40E_PROTOTYPE_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index c37abbb3cd06..20b77398f060 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -1,9 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ -#include "i40e.h" #include <linux/ptp_classify.h> #include <linux/posix-clock.h> +#include "i40e.h" +#include "i40e_devids.h" /* The XL710 timesync is very much like Intel's 82599 design when it comes to * the fundamental clock design. However, the clock operations are much simpler @@ -1132,7 +1133,7 @@ int i40e_ptp_alloc_pins(struct i40e_pf *pf) if (!pf->ptp_pins) { dev_warn(&pf->pdev->dev, "Cannot allocate memory for PTP pins structure.\n"); - return -I40E_ERR_NO_MEMORY; + return -ENOMEM; } pf->ptp_pins->sdp3_2 = off; diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h index 7339003aa17c..f6671ac79735 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_register.h +++ b/drivers/net/ethernet/intel/i40e/i40e_register.h @@ -4,6 +4,9 @@ #ifndef _I40E_REGISTER_H_ #define _I40E_REGISTER_H_ +/* I40E_MASK is a macro used on 32 bit registers */ +#define I40E_MASK(mask, shift) ((u32)(mask) << (shift)) + #define I40E_GL_ATQLEN_ATQCRIT_SHIFT 30 #define I40E_GL_ATQLEN_ATQCRIT_MASK I40E_MASK(0x1, I40E_GL_ATQLEN_ATQCRIT_SHIFT) #define I40E_PF_ARQBAH 0x00080180 /* Reset: EMPR */ @@ -202,7 +205,9 @@ #define I40E_GLGEN_MSCA_DEVADD_SHIFT 16 #define I40E_GLGEN_MSCA_PHYADD_SHIFT 21 #define I40E_GLGEN_MSCA_OPCODE_SHIFT 26 +#define I40E_GLGEN_MSCA_OPCODE_MASK(_i) I40E_MASK(_i, I40E_GLGEN_MSCA_OPCODE_SHIFT) #define I40E_GLGEN_MSCA_STCODE_SHIFT 28 +#define I40E_GLGEN_MSCA_STCODE_MASK(_i) I40E_MASK(_i, I40E_GLGEN_MSCA_STCODE_SHIFT) #define I40E_GLGEN_MSCA_MDICMD_SHIFT 30 #define I40E_GLGEN_MSCA_MDICMD_MASK I40E_MASK(0x1, I40E_GLGEN_MSCA_MDICMD_SHIFT) #define I40E_GLGEN_MSCA_MDIINPROGEN_SHIFT 31 diff --git a/drivers/net/ethernet/intel/i40e/i40e_status.h b/drivers/net/ethernet/intel/i40e/i40e_status.h deleted file mode 100644 index 4d2782e76038..000000000000 --- a/drivers/net/ethernet/intel/i40e/i40e_status.h +++ /dev/null @@ -1,43 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#ifndef _I40E_STATUS_H_ -#define _I40E_STATUS_H_ - -/* Error Codes */ -enum i40e_status_code { - I40E_SUCCESS = 0, - I40E_ERR_NVM = -1, - I40E_ERR_NVM_CHECKSUM = -2, - I40E_ERR_CONFIG = -4, - I40E_ERR_PARAM = -5, - I40E_ERR_UNKNOWN_PHY = -7, - I40E_ERR_INVALID_MAC_ADDR = -10, - I40E_ERR_DEVICE_NOT_SUPPORTED = -11, - I40E_ERR_RESET_FAILED = -15, - I40E_ERR_NO_AVAILABLE_VSI = -17, - I40E_ERR_NO_MEMORY = -18, - I40E_ERR_BAD_PTR = -19, - I40E_ERR_INVALID_SIZE = -26, - I40E_ERR_QUEUE_EMPTY = -32, - I40E_ERR_TIMEOUT = -37, - I40E_ERR_INVALID_SD_INDEX = -45, - I40E_ERR_INVALID_PAGE_DESC_INDEX = -46, - I40E_ERR_INVALID_SD_TYPE = -47, - I40E_ERR_INVALID_HMC_OBJ_INDEX = -49, - I40E_ERR_INVALID_HMC_OBJ_COUNT = -50, - I40E_ERR_ADMIN_QUEUE_ERROR = -53, - I40E_ERR_ADMIN_QUEUE_TIMEOUT = -54, - I40E_ERR_BUF_TOO_SHORT = -55, - I40E_ERR_ADMIN_QUEUE_FULL = -56, - I40E_ERR_ADMIN_QUEUE_NO_WORK = -57, - I40E_ERR_NVM_BLANK_MODE = -59, - I40E_ERR_NOT_IMPLEMENTED = -60, - I40E_ERR_DIAG_TEST_FAILED = -62, - I40E_ERR_NOT_READY = -63, - I40E_NOT_SUPPORTED = -64, - I40E_ERR_FIRMWARE_API_VERSION = -65, - I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR = -66, -}; - -#endif /* _I40E_STATUS_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 8b8bf4880faa..dd410b15000f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1,14 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ -#include <linux/prefetch.h> #include <linux/bpf_trace.h> +#include <linux/prefetch.h> +#include <linux/sctp.h> #include <net/mpls.h> #include <net/xdp.h> -#include "i40e.h" -#include "i40e_trace.h" -#include "i40e_prototype.h" #include "i40e_txrx_common.h" +#include "i40e_trace.h" #include "i40e_xsk.h" #define I40E_TXD_CMD (I40E_TX_DESC_CMD_EOP | I40E_TX_DESC_CMD_RS) @@ -2284,8 +2283,8 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, * If the buffer is an EOP buffer, this function exits returning false, * otherwise return true indicating that this is in fact a non-EOP buffer. */ -static bool i40e_is_non_eop(struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc) +bool i40e_is_non_eop(struct i40e_ring *rx_ring, + union i40e_rx_desc *rx_desc) { /* if we are the last buffer then there is nothing else to do */ #define I40E_RXD_EOF BIT(I40E_RX_DESC_STATUS_EOF_SHIFT) @@ -2405,7 +2404,7 @@ void i40e_update_rx_stats(struct i40e_ring *rx_ring, void i40e_finalize_xdp_rx(struct i40e_ring *rx_ring, unsigned int xdp_res) { if (xdp_res & I40E_XDP_REDIR) - xdp_do_flush_map(); + xdp_do_flush(); if (xdp_res & I40E_XDP_TX) { struct i40e_ring *xdp_ring = @@ -2544,7 +2543,14 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget, rx_buffer = i40e_rx_bi(rx_ring, ntp); i40e_inc_ntp(rx_ring); i40e_reuse_rx_page(rx_ring, rx_buffer); - cleaned_count++; + /* Update ntc and bump cleaned count if not in the + * middle of mb packet. + */ + if (rx_ring->next_to_clean == ntp) { + rx_ring->next_to_clean = + rx_ring->next_to_process; + cleaned_count++; + } continue; } @@ -2847,7 +2853,7 @@ tx_only: return budget; } - if (vsi->back->flags & I40E_TXR_FLAGS_WB_ON_ITR) + if (q_vector->tx.ring[0].flags & I40E_TXR_FLAGS_WB_ON_ITR) q_vector->arm_wb_state = false; /* Exit the polling mode, but don't re-enable interrupts if stack might diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 8c3d24012c54..421fe5675584 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -5,6 +5,7 @@ #define _I40E_TXRX_H_ #include <net/xdp.h> +#include "i40e_type.h" /* Interrupt Throttling and Rate Limiting Goodies */ #define I40E_DEFAULT_IRQ_WORK 256 @@ -473,6 +474,8 @@ int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size); bool __i40e_chk_linearize(struct sk_buff *skb); int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags); +bool i40e_is_non_eop(struct i40e_ring *rx_ring, + union i40e_rx_desc *rx_desc); /** * i40e_get_head - Retrieve head from head writeback diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h index 8c5118c8baaf..e26807fd2123 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h @@ -4,6 +4,8 @@ #ifndef I40E_TXRX_COMMON_ #define I40E_TXRX_COMMON_ +#include "i40e.h" + int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp, struct i40e_ring *xdp_ring); void i40e_clean_programming_status(struct i40e_ring *rx_ring, u64 qword0_raw, u64 qword1); diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index 388c3d36d96a..f95bc2a4a838 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -4,16 +4,9 @@ #ifndef _I40E_TYPE_H_ #define _I40E_TYPE_H_ -#include "i40e_status.h" -#include "i40e_osdep.h" -#include "i40e_register.h" +#include <uapi/linux/if_ether.h> #include "i40e_adminq.h" #include "i40e_hmc.h" -#include "i40e_lan_hmc.h" -#include "i40e_devids.h" - -/* I40E_MASK is a macro used on 32 bit registers */ -#define I40E_MASK(mask, shift) ((u32)(mask) << (shift)) #define I40E_MAX_VSI_QP 16 #define I40E_MAX_VF_VSI 4 @@ -44,48 +37,14 @@ typedef void (*I40E_ADMINQ_CALLBACK)(struct i40e_hw *, struct i40e_aq_desc *); #define I40E_QTX_CTL_VM_QUEUE 0x1 #define I40E_QTX_CTL_PF_QUEUE 0x2 -/* debug masks - set these bits in hw->debug_mask to control output */ -enum i40e_debug_mask { - I40E_DEBUG_INIT = 0x00000001, - I40E_DEBUG_RELEASE = 0x00000002, - - I40E_DEBUG_LINK = 0x00000010, - I40E_DEBUG_PHY = 0x00000020, - I40E_DEBUG_HMC = 0x00000040, - I40E_DEBUG_NVM = 0x00000080, - I40E_DEBUG_LAN = 0x00000100, - I40E_DEBUG_FLOW = 0x00000200, - I40E_DEBUG_DCB = 0x00000400, - I40E_DEBUG_DIAG = 0x00000800, - I40E_DEBUG_FD = 0x00001000, - I40E_DEBUG_PACKAGE = 0x00002000, - I40E_DEBUG_IWARP = 0x00F00000, - I40E_DEBUG_AQ_MESSAGE = 0x01000000, - I40E_DEBUG_AQ_DESCRIPTOR = 0x02000000, - I40E_DEBUG_AQ_DESC_BUFFER = 0x04000000, - I40E_DEBUG_AQ_COMMAND = 0x06000000, - I40E_DEBUG_AQ = 0x0F000000, - - I40E_DEBUG_USER = 0xF0000000, - - I40E_DEBUG_ALL = 0xFFFFFFFF -}; - -#define I40E_MDIO_CLAUSE22_STCODE_MASK I40E_MASK(1, \ - I40E_GLGEN_MSCA_STCODE_SHIFT) -#define I40E_MDIO_CLAUSE22_OPCODE_WRITE_MASK I40E_MASK(1, \ - I40E_GLGEN_MSCA_OPCODE_SHIFT) -#define I40E_MDIO_CLAUSE22_OPCODE_READ_MASK I40E_MASK(2, \ - I40E_GLGEN_MSCA_OPCODE_SHIFT) - -#define I40E_MDIO_CLAUSE45_STCODE_MASK I40E_MASK(0, \ - I40E_GLGEN_MSCA_STCODE_SHIFT) -#define I40E_MDIO_CLAUSE45_OPCODE_ADDRESS_MASK I40E_MASK(0, \ - I40E_GLGEN_MSCA_OPCODE_SHIFT) -#define I40E_MDIO_CLAUSE45_OPCODE_WRITE_MASK I40E_MASK(1, \ - I40E_GLGEN_MSCA_OPCODE_SHIFT) -#define I40E_MDIO_CLAUSE45_OPCODE_READ_MASK I40E_MASK(3, \ - I40E_GLGEN_MSCA_OPCODE_SHIFT) +#define I40E_MDIO_CLAUSE22_STCODE_MASK I40E_GLGEN_MSCA_STCODE_MASK(1) +#define I40E_MDIO_CLAUSE22_OPCODE_WRITE_MASK I40E_GLGEN_MSCA_OPCODE_MASK(1) +#define I40E_MDIO_CLAUSE22_OPCODE_READ_MASK I40E_GLGEN_MSCA_OPCODE_MASK(2) + +#define I40E_MDIO_CLAUSE45_STCODE_MASK I40E_GLGEN_MSCA_STCODE_MASK(0) +#define I40E_MDIO_CLAUSE45_OPCODE_ADDRESS_MASK I40E_GLGEN_MSCA_OPCODE_MASK(0) +#define I40E_MDIO_CLAUSE45_OPCODE_WRITE_MASK I40E_GLGEN_MSCA_OPCODE_MASK(1) +#define I40E_MDIO_CLAUSE45_OPCODE_READ_MASK I40E_GLGEN_MSCA_OPCODE_MASK(3) #define I40E_PHY_COM_REG_PAGE 0x1E #define I40E_PHY_LED_LINK_MODE_MASK 0xF0 @@ -526,7 +485,6 @@ struct i40e_dcbx_config { /* Port hardware description */ struct i40e_hw { u8 __iomem *hw_addr; - void *back; /* subsystem structs */ struct i40e_phy_info phy; @@ -535,6 +493,9 @@ struct i40e_hw { struct i40e_nvm_info nvm; struct i40e_fc_info fc; + /* PBA ID */ + const char *pba_id; + /* pci info */ u16 device_id; u16 vendor_id; @@ -1456,7 +1417,7 @@ struct i40e_ddp_version { struct i40e_package_header { struct i40e_ddp_version version; u32 segment_count; - u32 segment_offset[1]; + u32 segment_offset[]; }; /* Generic segment header */ @@ -1487,12 +1448,12 @@ struct i40e_profile_segment { struct i40e_ddp_version version; char name[I40E_DDP_NAME_SIZE]; u32 device_table_count; - struct i40e_device_id_entry device_table[1]; + struct i40e_device_id_entry device_table[]; }; struct i40e_section_table { u32 section_count; - u32 section_offset[1]; + u32 section_offset[]; }; struct i40e_profile_section_header { @@ -1524,7 +1485,7 @@ struct i40e_profile_aq_section { u16 flags; u8 param[16]; u16 datalen; - u8 data[1]; + u8 data[]; }; struct i40e_profile_info { diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index be59ba3774e1..3f99eb198245 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -2,6 +2,8 @@ /* Copyright(c) 2013 - 2018 Intel Corporation. */ #include "i40e.h" +#include "i40e_lan_hmc.h" +#include "i40e_virtchnl_pf.h" /*********************notification routines***********************/ @@ -506,6 +508,7 @@ i40e_config_rdma_qvlist(struct i40e_vf *vf, struct virtchnl_rdma_qv_info *qv_info; u32 v_idx, i, reg_idx, reg; u32 next_q_idx, next_q_type; + size_t size; u32 msix_vf; int ret = 0; @@ -521,9 +524,9 @@ i40e_config_rdma_qvlist(struct i40e_vf *vf, } kfree(vf->qvlist_info); - vf->qvlist_info = kzalloc(struct_size(vf->qvlist_info, qv_info, - qvlist_info->num_vectors - 1), - GFP_KERNEL); + size = virtchnl_struct_size(vf->qvlist_info, qv_info, + qvlist_info->num_vectors); + vf->qvlist_info = kzalloc(size, GFP_KERNEL); if (!vf->qvlist_info) { ret = -ENOMEM; goto err_out; @@ -1346,14 +1349,14 @@ static int i40e_config_vf_promiscuous_mode(struct i40e_vf *vf, bool alluni) { struct i40e_pf *pf = vf->pf; - int aq_ret = I40E_SUCCESS; struct i40e_vsi *vsi; + int aq_ret = 0; u16 num_vlans; s16 *vl; vsi = i40e_find_vsi_from_id(pf, vsi_id); if (!i40e_vc_isvalid_vsi_id(vf, vsi_id) || !vsi) - return I40E_ERR_PARAM; + return -EINVAL; if (vf->port_vlan_id) { aq_ret = i40e_set_vsi_promisc(vf, vsi->seid, allmulti, @@ -1363,7 +1366,7 @@ static int i40e_config_vf_promiscuous_mode(struct i40e_vf *vf, i40e_get_vlan_list_sync(vsi, &num_vlans, &vl); if (!vl) - return I40E_ERR_NO_MEMORY; + return -ENOMEM; aq_ret = i40e_set_vsi_promisc(vf, vsi->seid, allmulti, alluni, vl, num_vlans); @@ -2037,7 +2040,7 @@ static int i40e_vc_get_version_msg(struct i40e_vf *vf, u8 *msg) if (VF_IS_V10(&vf->vf_ver)) info.minor = VIRTCHNL_VERSION_MINOR_NO_VF_CAPS; return i40e_vc_send_msg_to_vf(vf, VIRTCHNL_OP_VERSION, - I40E_SUCCESS, (u8 *)&info, + 0, (u8 *)&info, sizeof(struct virtchnl_version_info)); } @@ -2099,14 +2102,14 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) int ret; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_INIT)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err; } - len = struct_size(vfres, vsi_res, num_vsis); + len = virtchnl_struct_size(vfres, vsi_res, num_vsis); vfres = kzalloc(len, GFP_KERNEL); if (!vfres) { - aq_ret = I40E_ERR_NO_MEMORY; + aq_ret = -ENOMEM; len = 0; goto err; } @@ -2159,7 +2162,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) dev_err(&pf->pdev->dev, "VF %d requested polling mode: this feature is supported only when the device is running in single function per port (SFP) mode\n", vf->vf_id); - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err; } vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RX_POLLING; @@ -2227,7 +2230,7 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, u8 *msg) int aq_ret = 0; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err_out; } if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps)) { @@ -2243,12 +2246,12 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, u8 *msg) } if (info->flags > I40E_MAX_VF_PROMISC_FLAGS) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err_out; } if (!i40e_vc_isvalid_vsi_id(vf, info->vsi_id)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err_out; } @@ -2315,17 +2318,17 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg) int aq_ret = 0; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } if (!i40e_vc_isvalid_vsi_id(vf, qci->vsi_id)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } if (qci->num_queue_pairs > I40E_MAX_VF_QUEUES) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } @@ -2333,7 +2336,7 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg) for (i = 0; i < vf->num_tc; i++) num_qps_all += vf->ch[i].num_qps; if (num_qps_all != qci->num_queue_pairs) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } } @@ -2346,7 +2349,7 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg) if (!vf->adq_enabled) { if (!i40e_vc_isvalid_queue_id(vf, vsi_id, qpi->txq.queue_id)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } @@ -2355,14 +2358,14 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg) if (qpi->txq.vsi_id != qci->vsi_id || qpi->rxq.vsi_id != qci->vsi_id || qpi->rxq.queue_id != vsi_queue_id) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } } if (vf->adq_enabled) { if (idx >= ARRAY_SIZE(vf->ch)) { - aq_ret = I40E_ERR_NO_AVAILABLE_VSI; + aq_ret = -ENODEV; goto error_param; } vsi_id = vf->ch[idx].vsi_id; @@ -2372,7 +2375,7 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg) &qpi->rxq) || i40e_config_vsi_tx_queue(vf, vsi_id, vsi_queue_id, &qpi->txq)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } @@ -2383,7 +2386,7 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg) */ if (vf->adq_enabled) { if (idx >= ARRAY_SIZE(vf->ch)) { - aq_ret = I40E_ERR_NO_AVAILABLE_VSI; + aq_ret = -ENODEV; goto error_param; } if (j == (vf->ch[idx].num_qps - 1)) { @@ -2406,7 +2409,7 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg) vsi->num_queue_pairs = vf->ch[i].num_qps; if (i40e_update_adq_vsi_queues(vsi, i)) { - aq_ret = I40E_ERR_CONFIG; + aq_ret = -EIO; goto error_param; } } @@ -2464,13 +2467,13 @@ static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg) int i; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } if (irqmap_info->num_vectors > vf->pf->hw.func_caps.num_msix_vectors_vf) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } @@ -2479,18 +2482,18 @@ static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg) /* validate msg params */ if (!i40e_vc_isvalid_vector_id(vf, map->vector_id) || !i40e_vc_isvalid_vsi_id(vf, map->vsi_id)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } vsi_id = map->vsi_id; if (i40e_validate_queue_map(vf, vsi_id, map->rxq_map)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } if (i40e_validate_queue_map(vf, vsi_id, map->txq_map)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } @@ -2579,29 +2582,29 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg) int i; if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } if (!i40e_vc_isvalid_vsi_id(vf, vqs->vsi_id)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } if (!i40e_vc_validate_vqs_bitmaps(vqs)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } /* Use the queue bit map sent by the VF */ if (i40e_ctrl_vf_rx_rings(pf->vsi[vf->lan_vsi_idx], vqs->rx_queues, true)) { - aq_ret = I40E_ERR_TIMEOUT; + aq_ret = -EIO; goto error_param; } if (i40e_ctrl_vf_tx_rings(pf->vsi[vf->lan_vsi_idx], vqs->tx_queues, true)) { - aq_ret = I40E_ERR_TIMEOUT; + aq_ret = -EIO; goto error_param; } @@ -2610,7 +2613,7 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg) /* zero belongs to LAN VSI */ for (i = 1; i < vf->num_tc; i++) { if (i40e_vsi_start_rings(pf->vsi[vf->ch[i].vsi_idx])) - aq_ret = I40E_ERR_TIMEOUT; + aq_ret = -EIO; } } @@ -2636,29 +2639,29 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg) int aq_ret = 0; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } if (!i40e_vc_isvalid_vsi_id(vf, vqs->vsi_id)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } if (!i40e_vc_validate_vqs_bitmaps(vqs)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } /* Use the queue bit map sent by the VF */ if (i40e_ctrl_vf_tx_rings(pf->vsi[vf->lan_vsi_idx], vqs->tx_queues, false)) { - aq_ret = I40E_ERR_TIMEOUT; + aq_ret = -EIO; goto error_param; } if (i40e_ctrl_vf_rx_rings(pf->vsi[vf->lan_vsi_idx], vqs->rx_queues, false)) { - aq_ret = I40E_ERR_TIMEOUT; + aq_ret = -EIO; goto error_param; } error_param: @@ -2790,18 +2793,18 @@ static int i40e_vc_get_stats_msg(struct i40e_vf *vf, u8 *msg) memset(&stats, 0, sizeof(struct i40e_eth_stats)); if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } if (!i40e_vc_isvalid_vsi_id(vf, vqs->vsi_id)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } vsi = pf->vsi[vf->lan_vsi_idx]; if (!vsi) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } i40e_update_eth_stats(vsi); @@ -2862,7 +2865,7 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf, is_zero_ether_addr(addr)) { dev_err(&pf->pdev->dev, "invalid VF MAC addr %pM\n", addr); - return I40E_ERR_INVALID_MAC_ADDR; + return -EINVAL; } /* If the host VMM administrator has set the VF MAC address @@ -2998,7 +3001,7 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg) if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) || !i40e_vc_isvalid_vsi_id(vf, al->vsi_id)) { - ret = I40E_ERR_PARAM; + ret = -EINVAL; goto error_param; } @@ -3027,7 +3030,7 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg) dev_err(&pf->pdev->dev, "Unable to add MAC filter %pM for VF %d\n", al->list[i].addr, vf->vf_id); - ret = I40E_ERR_PARAM; + ret = -EINVAL; spin_unlock_bh(&vsi->mac_filter_hash_lock); goto error_param; } @@ -3067,7 +3070,7 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) || !i40e_vc_isvalid_vsi_id(vf, al->vsi_id)) { - ret = I40E_ERR_PARAM; + ret = -EINVAL; goto error_param; } @@ -3076,7 +3079,7 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) is_zero_ether_addr(al->list[i].addr)) { dev_err(&pf->pdev->dev, "Invalid MAC addr %pM for VF %d\n", al->list[i].addr, vf->vf_id); - ret = I40E_ERR_INVALID_MAC_ADDR; + ret = -EINVAL; goto error_param; } if (ether_addr_equal(al->list[i].addr, vf->default_lan_addr.addr)) @@ -3088,7 +3091,7 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) /* delete addresses from the list */ for (i = 0; i < al->num_elements; i++) if (i40e_del_mac_filter(vsi, al->list[i].addr)) { - ret = I40E_ERR_INVALID_MAC_ADDR; + ret = -EINVAL; spin_unlock_bh(&vsi->mac_filter_hash_lock); goto error_param; } @@ -3149,13 +3152,13 @@ static int i40e_vc_add_vlan_msg(struct i40e_vf *vf, u8 *msg) } if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || !i40e_vc_isvalid_vsi_id(vf, vfl->vsi_id)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } for (i = 0; i < vfl->num_elements; i++) { if (vfl->vlan_id[i] > I40E_MAX_VLANID) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; dev_err(&pf->pdev->dev, "invalid VF VLAN id %d\n", vfl->vlan_id[i]); goto error_param; @@ -3163,7 +3166,7 @@ static int i40e_vc_add_vlan_msg(struct i40e_vf *vf, u8 *msg) } vsi = pf->vsi[vf->lan_vsi_idx]; if (vsi->info.pvid) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } @@ -3214,13 +3217,13 @@ static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg) if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) || !i40e_vc_isvalid_vsi_id(vf, vfl->vsi_id)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } for (i = 0; i < vfl->num_elements; i++) { if (vfl->vlan_id[i] > I40E_MAX_VLANID) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } } @@ -3228,7 +3231,7 @@ static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg) vsi = pf->vsi[vf->lan_vsi_idx]; if (vsi->info.pvid) { if (vfl->num_elements > 1 || vfl->vlan_id[0]) - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } @@ -3269,7 +3272,7 @@ static int i40e_vc_rdma_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || !test_bit(I40E_VF_STATE_RDMAENA, &vf->vf_states)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } @@ -3298,13 +3301,13 @@ static int i40e_vc_rdma_qvmap_msg(struct i40e_vf *vf, u8 *msg, bool config) if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || !test_bit(I40E_VF_STATE_RDMAENA, &vf->vf_states)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto error_param; } if (config) { if (i40e_config_rdma_qvlist(vf, qvlist_info)) - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; } else { i40e_release_rdma_qvlist(vf); } @@ -3335,7 +3338,7 @@ static int i40e_vc_config_rss_key(struct i40e_vf *vf, u8 *msg) if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) || !i40e_vc_isvalid_vsi_id(vf, vrk->vsi_id) || vrk->key_len != I40E_HKEY_ARRAY_SIZE) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err; } @@ -3366,13 +3369,13 @@ static int i40e_vc_config_rss_lut(struct i40e_vf *vf, u8 *msg) if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) || !i40e_vc_isvalid_vsi_id(vf, vrl->vsi_id) || vrl->lut_entries != I40E_VF_HLUT_ARRAY_SIZE) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err; } for (i = 0; i < vrl->lut_entries; i++) if (vrl->lut[i] >= vf->num_queue_pairs) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err; } @@ -3399,14 +3402,14 @@ static int i40e_vc_get_rss_hena(struct i40e_vf *vf, u8 *msg) int len = 0; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err; } len = sizeof(struct virtchnl_rss_hena); vrh = kzalloc(len, GFP_KERNEL); if (!vrh) { - aq_ret = I40E_ERR_NO_MEMORY; + aq_ret = -ENOMEM; len = 0; goto err; } @@ -3435,7 +3438,7 @@ static int i40e_vc_set_rss_hena(struct i40e_vf *vf, u8 *msg) int aq_ret = 0; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err; } i40e_write_rx_ctl(hw, I40E_VFQF_HENA1(0, vf->vf_id), (u32)vrh->hena); @@ -3460,7 +3463,7 @@ static int i40e_vc_enable_vlan_stripping(struct i40e_vf *vf, u8 *msg) int aq_ret = 0; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err; } @@ -3486,7 +3489,7 @@ static int i40e_vc_disable_vlan_stripping(struct i40e_vf *vf, u8 *msg) int aq_ret = 0; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err; } @@ -3574,7 +3577,7 @@ static int i40e_validate_cloud_filter(struct i40e_vf *vf, dev_err(&pf->pdev->dev, "VF %d not trusted, make VF trusted to add advanced mode ADq cloud filters\n", vf->vf_id); - return I40E_ERR_CONFIG; + return -EIO; } } @@ -3627,9 +3630,9 @@ static int i40e_validate_cloud_filter(struct i40e_vf *vf, } } - return I40E_SUCCESS; + return 0; err: - return I40E_ERR_CONFIG; + return -EIO; } /** @@ -3713,7 +3716,7 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg) int i, ret; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err; } @@ -3721,7 +3724,7 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg) dev_info(&pf->pdev->dev, "VF %d: ADq not enabled, can't apply cloud filter\n", vf->vf_id); - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err; } @@ -3729,7 +3732,7 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg) dev_info(&pf->pdev->dev, "VF %d: Invalid input, can't apply cloud filter\n", vf->vf_id); - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err; } @@ -3841,10 +3844,10 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg) struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi = NULL; int aq_ret = 0; - int i, ret; + int i; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err_out; } @@ -3852,7 +3855,7 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg) dev_info(&pf->pdev->dev, "VF %d: ADq is not enabled, can't apply cloud filter\n", vf->vf_id); - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err_out; } @@ -3860,13 +3863,15 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg) dev_info(&pf->pdev->dev, "VF %d: Invalid input/s, can't apply cloud filter\n", vf->vf_id); - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err_out; } cfilter = kzalloc(sizeof(*cfilter), GFP_KERNEL); - if (!cfilter) - return -ENOMEM; + if (!cfilter) { + aq_ret = -ENOMEM; + goto err_out; + } /* parse destination mac address */ for (i = 0; i < ETH_ALEN; i++) @@ -3914,13 +3919,13 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg) /* Adding cloud filter programmed as TC filter */ if (tcf.dst_port) - ret = i40e_add_del_cloud_filter_big_buf(vsi, cfilter, true); + aq_ret = i40e_add_del_cloud_filter_big_buf(vsi, cfilter, true); else - ret = i40e_add_del_cloud_filter(vsi, cfilter, true); - if (ret) { + aq_ret = i40e_add_del_cloud_filter(vsi, cfilter, true); + if (aq_ret) { dev_err(&pf->pdev->dev, "VF %d: Failed to add cloud filter, err %pe aq_err %s\n", - vf->vf_id, ERR_PTR(ret), + vf->vf_id, ERR_PTR(aq_ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); goto err_free; } @@ -3953,7 +3958,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg) u64 speed = 0; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err; } @@ -3961,7 +3966,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg) if (vf->spoofchk) { dev_err(&pf->pdev->dev, "Spoof check is ON, turn it OFF to enable ADq\n"); - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err; } @@ -3969,7 +3974,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg) dev_err(&pf->pdev->dev, "VF %d attempting to enable ADq, but hasn't properly negotiated that capability\n", vf->vf_id); - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err; } @@ -3978,7 +3983,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg) dev_err(&pf->pdev->dev, "VF %d trying to set %u TCs, valid range 1-%u TCs per VF\n", vf->vf_id, tci->num_tc, I40E_MAX_VF_VSI); - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err; } @@ -3990,7 +3995,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg) "VF %d: TC %d trying to set %u queues, valid range 1-%u queues per TC\n", vf->vf_id, i, tci->list[i].count, I40E_DEFAULT_QUEUES_PER_VF); - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err; } @@ -4001,7 +4006,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg) dev_err(&pf->pdev->dev, "No queues left to allocate to VF %d\n", vf->vf_id); - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err; } else { /* we need to allocate max VF queues to enable ADq so as to @@ -4016,7 +4021,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg) if (speed == SPEED_UNKNOWN) { dev_err(&pf->pdev->dev, "Cannot detect link speed\n"); - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err; } @@ -4029,7 +4034,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg) "Invalid max tx rate %llu specified for VF %d.", tci->list[i].max_tx_rate, vf->vf_id); - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err; } else { vf->ch[i].max_tx_rate = @@ -4045,7 +4050,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg) /* reset the VF in order to allocate resources */ i40e_vc_reset_vf(vf, true); - return I40E_SUCCESS; + return 0; /* send the response to the VF */ err: @@ -4064,7 +4069,7 @@ static int i40e_vc_del_qch_msg(struct i40e_vf *vf, u8 *msg) int aq_ret = 0; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; goto err; } @@ -4079,13 +4084,13 @@ static int i40e_vc_del_qch_msg(struct i40e_vf *vf, u8 *msg) } else { dev_info(&pf->pdev->dev, "VF %d trying to delete queue channels but ADq isn't enabled\n", vf->vf_id); - aq_ret = I40E_ERR_PARAM; + aq_ret = -EINVAL; } /* reset the VF in order to allocate resources */ i40e_vc_reset_vf(vf, true); - return I40E_SUCCESS; + return 0; err: return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DISABLE_CHANNELS, @@ -4119,21 +4124,16 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode, /* Check if VF is disabled. */ if (test_bit(I40E_VF_STATE_DISABLED, &vf->vf_states)) - return I40E_ERR_PARAM; + return -EINVAL; /* perform basic checks on the msg */ ret = virtchnl_vc_validate_vf_msg(&vf->vf_ver, v_opcode, msg, msglen); if (ret) { - i40e_vc_send_resp_to_vf(vf, v_opcode, I40E_ERR_PARAM); + i40e_vc_send_resp_to_vf(vf, v_opcode, -EINVAL); dev_err(&pf->pdev->dev, "Invalid message from VF %d, opcode %d, len %d\n", local_vf_id, v_opcode, msglen); - switch (ret) { - case VIRTCHNL_STATUS_ERR_PARAM: - return -EPERM; - default: - return -EINVAL; - } + return ret; } switch (v_opcode) { @@ -4226,7 +4226,7 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode, dev_err(&pf->pdev->dev, "Unsupported opcode %d from VF %d\n", v_opcode, local_vf_id); ret = i40e_vc_send_resp_to_vf(vf, v_opcode, - I40E_ERR_NOT_IMPLEMENTED); + -EOPNOTSUPP); break; } @@ -4305,6 +4305,38 @@ err_out: } /** + * i40e_check_vf_init_timeout + * @vf: the virtual function + * + * Check that the VF's initialization was successfully done and if not + * wait up to 300ms for its finish. + * + * Returns true when VF is initialized, false on timeout + **/ +static bool i40e_check_vf_init_timeout(struct i40e_vf *vf) +{ + int i; + + /* When the VF is resetting wait until it is done. + * It can take up to 200 milliseconds, but wait for + * up to 300 milliseconds to be safe. + */ + for (i = 0; i < 15; i++) { + if (test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) + return true; + msleep(20); + } + + if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { + dev_err(&vf->pf->pdev->dev, + "VF %d still in reset. Try again.\n", vf->vf_id); + return false; + } + + return true; +} + +/** * i40e_ndo_set_vf_mac * @netdev: network interface device structure * @vf_id: VF identifier @@ -4322,7 +4354,6 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) int ret = 0; struct hlist_node *h; int bkt; - u8 i; if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) { dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n"); @@ -4335,21 +4366,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) goto error_param; vf = &pf->vf[vf_id]; - - /* When the VF is resetting wait until it is done. - * It can take up to 200 milliseconds, - * but wait for up to 300 milliseconds to be safe. - * Acquire the VSI pointer only after the VF has been - * properly initialized. - */ - for (i = 0; i < 15; i++) { - if (test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) - break; - msleep(20); - } - if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { - dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n", - vf_id); + if (!i40e_check_vf_init_timeout(vf)) { ret = -EAGAIN; goto error_param; } @@ -4451,22 +4468,18 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, } vf = &pf->vf[vf_id]; - vsi = pf->vsi[vf->lan_vsi_idx]; - if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { - dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n", - vf_id); + if (!i40e_check_vf_init_timeout(vf)) { ret = -EAGAIN; goto error_pvid; } + vsi = pf->vsi[vf->lan_vsi_idx]; if (le16_to_cpu(vsi->info.pvid) == vlanprio) /* duplicate request, so just return success */ goto error_pvid; i40e_vlan_stripping_enable(vsi); - i40e_vc_reset_vf(vf, true); - /* During reset the VF got a new VSI, so refresh a pointer. */ - vsi = pf->vsi[vf->lan_vsi_idx]; + /* Locked once because multiple functions below iterate list */ spin_lock_bh(&vsi->mac_filter_hash_lock); @@ -4552,6 +4565,10 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, */ vf->port_vlan_id = le16_to_cpu(vsi->info.pvid); + i40e_vc_reset_vf(vf, true); + /* During reset the VF got a new VSI, so refresh a pointer. */ + vsi = pf->vsi[vf->lan_vsi_idx]; + ret = i40e_config_vf_promiscuous_mode(vf, vsi->id, allmulti, alluni); if (ret) { dev_err(&pf->pdev->dev, "Unable to config vf promiscuous mode\n"); @@ -4601,13 +4618,11 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, } vf = &pf->vf[vf_id]; - vsi = pf->vsi[vf->lan_vsi_idx]; - if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { - dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n", - vf_id); + if (!i40e_check_vf_init_timeout(vf)) { ret = -EAGAIN; goto error; } + vsi = pf->vsi[vf->lan_vsi_idx]; ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate); if (ret) @@ -4774,9 +4789,7 @@ int i40e_ndo_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool enable) } vf = &(pf->vf[vf_id]); - if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { - dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n", - vf_id); + if (!i40e_check_vf_init_timeout(vf)) { ret = -EAGAIN; goto out; } @@ -4907,7 +4920,7 @@ int i40e_get_vf_stats(struct net_device *netdev, int vf_id, vf_stats->tx_bytes = stats->tx_bytes; vf_stats->broadcast = stats->rx_broadcast; vf_stats->multicast = stats->rx_multicast; - vf_stats->rx_dropped = stats->rx_discards; + vf_stats->rx_dropped = stats->rx_discards + stats->rx_discards_other; vf_stats->tx_dropped = stats->tx_discards; return 0; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 895b8feb2567..2ee0f8a23248 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -4,7 +4,9 @@ #ifndef _I40E_VIRTCHNL_PF_H_ #define _I40E_VIRTCHNL_PF_H_ -#include "i40e.h" +#include <linux/avf/virtchnl.h> +#include <linux/netdevice.h> +#include "i40e_type.h" #define I40E_MAX_VLANID 4095 diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 05ec1181471e..e99fa854d17f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -2,11 +2,7 @@ /* Copyright(c) 2018 Intel Corporation. */ #include <linux/bpf_trace.h> -#include <linux/stringify.h> #include <net/xdp_sock_drv.h> -#include <net/xdp.h> - -#include "i40e.h" #include "i40e_txrx_common.h" #include "i40e_xsk.h" @@ -294,8 +290,14 @@ static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring, { unsigned int totalsize = xdp->data_end - xdp->data_meta; unsigned int metasize = xdp->data - xdp->data_meta; + struct skb_shared_info *sinfo = NULL; struct sk_buff *skb; + u32 nr_frags = 0; + if (unlikely(xdp_buff_has_frags(xdp))) { + sinfo = xdp_get_shared_info_from_buff(xdp); + nr_frags = sinfo->nr_frags; + } net_prefetch(xdp->data_meta); /* allocate a skb to store the frags */ @@ -312,6 +314,28 @@ static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring, __skb_pull(skb, metasize); } + if (likely(!xdp_buff_has_frags(xdp))) + goto out; + + for (int i = 0; i < nr_frags; i++) { + struct skb_shared_info *skinfo = skb_shinfo(skb); + skb_frag_t *frag = &sinfo->frags[i]; + struct page *page; + void *addr; + + page = dev_alloc_page(); + if (!page) { + dev_kfree_skb(skb); + return NULL; + } + addr = page_to_virt(page); + + memcpy(addr, skb_frag_page(frag), skb_frag_size(frag)); + + __skb_fill_page_desc_noacc(skinfo, skinfo->nr_frags++, + addr, 0, skb_frag_size(frag)); + } + out: xsk_buff_free(xdp); return skb; @@ -322,14 +346,13 @@ static void i40e_handle_xdp_result_zc(struct i40e_ring *rx_ring, union i40e_rx_desc *rx_desc, unsigned int *rx_packets, unsigned int *rx_bytes, - unsigned int size, unsigned int xdp_res, bool *failure) { struct sk_buff *skb; *rx_packets = 1; - *rx_bytes = size; + *rx_bytes = xdp_get_buff_len(xdp_buff); if (likely(xdp_res == I40E_XDP_REDIR) || xdp_res == I40E_XDP_TX) return; @@ -363,7 +386,6 @@ static void i40e_handle_xdp_result_zc(struct i40e_ring *rx_ring, return; } - *rx_bytes = skb->len; i40e_process_skb_fields(rx_ring, rx_desc, skb); napi_gro_receive(&rx_ring->q_vector->napi, skb); return; @@ -374,6 +396,31 @@ static void i40e_handle_xdp_result_zc(struct i40e_ring *rx_ring, WARN_ON_ONCE(1); } +static int +i40e_add_xsk_frag(struct i40e_ring *rx_ring, struct xdp_buff *first, + struct xdp_buff *xdp, const unsigned int size) +{ + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(first); + + if (!xdp_buff_has_frags(first)) { + sinfo->nr_frags = 0; + sinfo->xdp_frags_size = 0; + xdp_buff_set_frags_flag(first); + } + + if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) { + xsk_buff_free(first); + return -ENOMEM; + } + + __skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, + virt_to_page(xdp->data_hard_start), 0, size); + sinfo->xdp_frags_size += size; + xsk_buff_add_frag(xdp); + + return 0; +} + /** * i40e_clean_rx_irq_zc - Consumes Rx packets from the hardware ring * @rx_ring: Rx ring @@ -384,12 +431,17 @@ static void i40e_handle_xdp_result_zc(struct i40e_ring *rx_ring, int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) { unsigned int total_rx_bytes = 0, total_rx_packets = 0; + u16 next_to_process = rx_ring->next_to_process; u16 next_to_clean = rx_ring->next_to_clean; - u16 count_mask = rx_ring->count - 1; unsigned int xdp_res, xdp_xmit = 0; + struct xdp_buff *first = NULL; + u32 count = rx_ring->count; struct bpf_prog *xdp_prog; + u32 entries_to_alloc; bool failure = false; - u16 cleaned_count; + + if (next_to_process != next_to_clean) + first = *i40e_rx_bi(rx_ring, next_to_clean); /* NB! xdp_prog will always be !NULL, due to the fact that * this path is enabled by setting an XDP program. @@ -404,7 +456,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) unsigned int size; u64 qword; - rx_desc = I40E_RX_DESC(rx_ring, next_to_clean); + rx_desc = I40E_RX_DESC(rx_ring, next_to_process); qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); /* This memory barrier is needed to keep us from reading @@ -417,9 +469,10 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) i40e_clean_programming_status(rx_ring, rx_desc->raw.qword[0], qword); - bi = *i40e_rx_bi(rx_ring, next_to_clean); + bi = *i40e_rx_bi(rx_ring, next_to_process); xsk_buff_free(bi); - next_to_clean = (next_to_clean + 1) & count_mask; + if (++next_to_process == count) + next_to_process = 0; continue; } @@ -428,26 +481,40 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) if (!size) break; - bi = *i40e_rx_bi(rx_ring, next_to_clean); + bi = *i40e_rx_bi(rx_ring, next_to_process); xsk_buff_set_size(bi, size); xsk_buff_dma_sync_for_cpu(bi, rx_ring->xsk_pool); - xdp_res = i40e_run_xdp_zc(rx_ring, bi, xdp_prog); - i40e_handle_xdp_result_zc(rx_ring, bi, rx_desc, &rx_packets, - &rx_bytes, size, xdp_res, &failure); + if (!first) + first = bi; + else if (i40e_add_xsk_frag(rx_ring, first, bi, size)) + break; + + if (++next_to_process == count) + next_to_process = 0; + + if (i40e_is_non_eop(rx_ring, rx_desc)) + continue; + + xdp_res = i40e_run_xdp_zc(rx_ring, first, xdp_prog); + i40e_handle_xdp_result_zc(rx_ring, first, rx_desc, &rx_packets, + &rx_bytes, xdp_res, &failure); + first->flags = 0; + next_to_clean = next_to_process; if (failure) break; total_rx_packets += rx_packets; total_rx_bytes += rx_bytes; xdp_xmit |= xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR); - next_to_clean = (next_to_clean + 1) & count_mask; + first = NULL; } rx_ring->next_to_clean = next_to_clean; - cleaned_count = (next_to_clean - rx_ring->next_to_use - 1) & count_mask; + rx_ring->next_to_process = next_to_process; - if (cleaned_count >= I40E_RX_BUFFER_WRITE) - failure |= !i40e_alloc_rx_buffers_zc(rx_ring, cleaned_count); + entries_to_alloc = I40E_DESC_UNUSED(rx_ring); + if (entries_to_alloc >= I40E_RX_BUFFER_WRITE) + failure |= !i40e_alloc_rx_buffers_zc(rx_ring, entries_to_alloc); i40e_finalize_xdp_rx(rx_ring, xdp_xmit); i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets); @@ -466,6 +533,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) static void i40e_xmit_pkt(struct i40e_ring *xdp_ring, struct xdp_desc *desc, unsigned int *total_bytes) { + u32 cmd = I40E_TX_DESC_CMD_ICRC | xsk_is_eop_desc(desc); struct i40e_tx_desc *tx_desc; dma_addr_t dma; @@ -474,8 +542,7 @@ static void i40e_xmit_pkt(struct i40e_ring *xdp_ring, struct xdp_desc *desc, tx_desc = I40E_TX_DESC(xdp_ring, xdp_ring->next_to_use++); tx_desc->buffer_addr = cpu_to_le64(dma); - tx_desc->cmd_type_offset_bsz = build_ctob(I40E_TX_DESC_CMD_ICRC | I40E_TX_DESC_CMD_EOP, - 0, desc->len, 0); + tx_desc->cmd_type_offset_bsz = build_ctob(cmd, 0, desc->len, 0); *total_bytes += desc->len; } @@ -489,14 +556,14 @@ static void i40e_xmit_pkt_batch(struct i40e_ring *xdp_ring, struct xdp_desc *des u32 i; loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) { + u32 cmd = I40E_TX_DESC_CMD_ICRC | xsk_is_eop_desc(&desc[i]); + dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc[i].addr); xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc[i].len); tx_desc = I40E_TX_DESC(xdp_ring, ntu++); tx_desc->buffer_addr = cpu_to_le64(dma); - tx_desc->cmd_type_offset_bsz = build_ctob(I40E_TX_DESC_CMD_ICRC | - I40E_TX_DESC_CMD_EOP, - 0, desc[i].len, 0); + tx_desc->cmd_type_offset_bsz = build_ctob(cmd, 0, desc[i].len, 0); *total_bytes += desc[i].len; } @@ -683,14 +750,16 @@ int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring) { - u16 count_mask = rx_ring->count - 1; u16 ntc = rx_ring->next_to_clean; u16 ntu = rx_ring->next_to_use; - for ( ; ntc != ntu; ntc = (ntc + 1) & count_mask) { + while (ntc != ntu) { struct xdp_buff *rx_bi = *i40e_rx_bi(rx_ring, ntc); xsk_buff_free(rx_bi); + ntc++; + if (ntc >= rx_ring->count) + ntc = 0; } } diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h index 821df248f8be..ef156fad52f2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h @@ -4,6 +4,8 @@ #ifndef _I40E_XSK_H_ #define _I40E_XSK_H_ +#include <linux/types.h> + /* This value should match the pragma in the loop_unrolled_for * macro. Why 4? It is strictly empirical. It seems to be a good * compromise between the advantage of having simultaneous outstanding @@ -20,7 +22,9 @@ #define loop_unrolled_for for #endif +struct i40e_ring; struct i40e_vsi; +struct net_device; struct xsk_buff_pool; int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair); diff --git a/drivers/net/ethernet/intel/iavf/Makefile b/drivers/net/ethernet/intel/iavf/Makefile index 9c3e45c54d01..2d154a4e2fd7 100644 --- a/drivers/net/ethernet/intel/iavf/Makefile +++ b/drivers/net/ethernet/intel/iavf/Makefile @@ -13,4 +13,4 @@ obj-$(CONFIG_IAVF) += iavf.o iavf-objs := iavf_main.o iavf_ethtool.o iavf_virtchnl.o iavf_fdir.o \ iavf_adv_rss.o \ - iavf_txrx.o iavf_common.o iavf_adminq.o iavf_client.o + iavf_txrx.o iavf_common.o iavf_adminq.o diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 8cbdebc5b698..63b45c61cc4a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -63,7 +63,6 @@ struct iavf_vsi { DECLARE_BITMAP(state, __IAVF_VSI_STATE_SIZE__); int base_vector; u16 qs_handle; - void *priv; /* client driver data reference. */ }; /* How many Rx Buffers do we bundle into one write to the hardware ? */ @@ -92,9 +91,9 @@ struct iavf_vsi { #define IAVF_MBPS_DIVISOR 125000 /* divisor to convert to Mbps */ #define IAVF_MBPS_QUANTA 50 -#define IAVF_VIRTCHNL_VF_RESOURCE_SIZE (sizeof(struct virtchnl_vf_resource) + \ - (IAVF_MAX_VF_VSI * \ - sizeof(struct virtchnl_vsi_resource))) +#define IAVF_VIRTCHNL_VF_RESOURCE_SIZE \ + virtchnl_struct_size((struct virtchnl_vf_resource *)NULL, \ + vsi_res, IAVF_MAX_VF_VSI) /* MAX_MSIX_Q_VECTORS of these are allocated, * but we only use one per queue-specific vector. @@ -256,7 +255,6 @@ struct iavf_adapter { struct work_struct reset_task; struct work_struct adminq_task; struct work_struct finish_config; - struct delayed_work client_task; wait_queue_head_t down_waitqueue; wait_queue_head_t reset_waitqueue; wait_queue_head_t vc_waitqueue; @@ -265,7 +263,6 @@ struct iavf_adapter { int num_vlan_filters; struct list_head mac_filter_list; struct mutex crit_lock; - struct mutex client_lock; /* Lock to protect accesses to MAC and VLAN lists */ spinlock_t mac_vlan_list_lock; char misc_vector_name[IFNAMSIZ + 9]; @@ -282,10 +279,6 @@ struct iavf_adapter { u64 hw_csum_rx_error; u32 rx_desc_count; int num_msix_vectors; - int num_rdma_msix; - int rdma_base_vector; - u32 client_pending; - struct iavf_client_instance *cinst; struct msix_entry *msix_entries; u32 flags; @@ -294,17 +287,12 @@ struct iavf_adapter { #define IAVF_FLAG_RESET_PENDING BIT(4) #define IAVF_FLAG_RESET_NEEDED BIT(5) #define IAVF_FLAG_WB_ON_ITR_CAPABLE BIT(6) -#define IAVF_FLAG_SERVICE_CLIENT_REQUESTED BIT(9) -#define IAVF_FLAG_CLIENT_NEEDS_OPEN BIT(10) -#define IAVF_FLAG_CLIENT_NEEDS_CLOSE BIT(11) -#define IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS BIT(12) -#define IAVF_FLAG_PROMISC_ON BIT(13) -#define IAVF_FLAG_ALLMULTI_ON BIT(14) #define IAVF_FLAG_LEGACY_RX BIT(15) #define IAVF_FLAG_REINIT_ITR_NEEDED BIT(16) #define IAVF_FLAG_QUEUES_DISABLED BIT(17) #define IAVF_FLAG_SETUP_NETDEV_FEATURES BIT(18) #define IAVF_FLAG_REINIT_MSIX_NEEDED BIT(20) +#define IAVF_FLAG_FDIR_ENABLED BIT(21) /* duplicates for common code */ #define IAVF_FLAG_DCB_ENABLED 0 /* flags for admin queue service task */ @@ -325,10 +313,7 @@ struct iavf_adapter { #define IAVF_FLAG_AQ_SET_HENA BIT_ULL(12) #define IAVF_FLAG_AQ_SET_RSS_KEY BIT_ULL(13) #define IAVF_FLAG_AQ_SET_RSS_LUT BIT_ULL(14) -#define IAVF_FLAG_AQ_REQUEST_PROMISC BIT_ULL(15) -#define IAVF_FLAG_AQ_RELEASE_PROMISC BIT_ULL(16) -#define IAVF_FLAG_AQ_REQUEST_ALLMULTI BIT_ULL(17) -#define IAVF_FLAG_AQ_RELEASE_ALLMULTI BIT_ULL(18) +#define IAVF_FLAG_AQ_CONFIGURE_PROMISC_MODE BIT_ULL(15) #define IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING BIT_ULL(19) #define IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING BIT_ULL(20) #define IAVF_FLAG_AQ_ENABLE_CHANNELS BIT_ULL(21) @@ -365,6 +350,12 @@ struct iavf_adapter { (IAVF_EXTENDED_CAP_SEND_VLAN_V2 | \ IAVF_EXTENDED_CAP_RECV_VLAN_V2) + /* Lock to prevent possible clobbering of + * current_netdev_promisc_flags + */ + spinlock_t current_netdev_promisc_flags_lock; + netdev_features_t current_netdev_promisc_flags; + /* OS defined structs */ struct net_device *netdev; struct pci_dev *pdev; @@ -376,7 +367,6 @@ struct iavf_adapter { unsigned long crit_section; struct delayed_work watchdog_task; - bool netdev_registered; bool link_up; enum virtchnl_link_speed link_speed; /* This is only populated if the VIRTCHNL_VF_CAP_ADV_LINK_SPEED is set @@ -388,11 +378,6 @@ struct iavf_adapter { u32 link_speed_mbps; enum virtchnl_ops current_op; -#define CLIENT_ALLOWED(_a) ((_a)->vf_res ? \ - (_a)->vf_res->vf_cap_flags & \ - VIRTCHNL_VF_OFFLOAD_RDMA : \ - 0) -#define CLIENT_ENABLED(_a) ((_a)->cinst) /* RSS by the PF should be preferred over RSS via other methods. */ #define RSS_PF(_a) ((_a)->vf_res->vf_cap_flags & \ VIRTCHNL_VF_OFFLOAD_RSS_PF) @@ -405,6 +390,8 @@ struct iavf_adapter { VIRTCHNL_VF_OFFLOAD_VLAN) #define VLAN_V2_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \ VIRTCHNL_VF_OFFLOAD_VLAN_V2) +#define CRC_OFFLOAD_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \ + VIRTCHNL_VF_OFFLOAD_CRC) #define VLAN_V2_FILTERING_ALLOWED(_a) \ (VLAN_V2_ALLOWED((_a)) && \ ((_a)->vlan_v2_caps.filtering.filtering_support.outer || \ @@ -458,12 +445,6 @@ struct iavf_adapter { /* Ethtool Private Flags */ -/* lan device, used by client interface */ -struct iavf_device { - struct list_head list; - struct iavf_adapter *vf; -}; - /* needed by iavf_ethtool.c */ extern char iavf_driver_name[]; @@ -521,7 +502,7 @@ void iavf_down(struct iavf_adapter *adapter); int iavf_process_config(struct iavf_adapter *adapter); int iavf_parse_vf_resource_msg(struct iavf_adapter *adapter); void iavf_schedule_reset(struct iavf_adapter *adapter, u64 flags); -void iavf_schedule_request_stats(struct iavf_adapter *adapter); +void iavf_schedule_aq_request(struct iavf_adapter *adapter, u64 flags); void iavf_schedule_finish_config(struct iavf_adapter *adapter); void iavf_reset(struct iavf_adapter *adapter); void iavf_set_ethtool_ops(struct net_device *netdev); @@ -551,7 +532,8 @@ void iavf_add_ether_addrs(struct iavf_adapter *adapter); void iavf_del_ether_addrs(struct iavf_adapter *adapter); void iavf_add_vlans(struct iavf_adapter *adapter); void iavf_del_vlans(struct iavf_adapter *adapter); -void iavf_set_promiscuous(struct iavf_adapter *adapter, int flags); +void iavf_set_promiscuous(struct iavf_adapter *adapter); +bool iavf_promiscuous_mode_changed(struct iavf_adapter *adapter); void iavf_request_stats(struct iavf_adapter *adapter); int iavf_request_reset(struct iavf_adapter *adapter); void iavf_get_hena(struct iavf_adapter *adapter); @@ -566,11 +548,6 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, int iavf_config_rss(struct iavf_adapter *adapter); int iavf_lan_add_device(struct iavf_adapter *adapter); int iavf_lan_del_device(struct iavf_adapter *adapter); -void iavf_client_subtask(struct iavf_adapter *adapter); -void iavf_notify_client_message(struct iavf_vsi *vsi, u8 *msg, u16 len); -void iavf_notify_client_l2_params(struct iavf_vsi *vsi); -void iavf_notify_client_open(struct iavf_vsi *vsi); -void iavf_notify_client_close(struct iavf_vsi *vsi, bool reset); void iavf_enable_channels(struct iavf_adapter *adapter); void iavf_disable_channels(struct iavf_adapter *adapter); void iavf_add_cloud_filter(struct iavf_adapter *adapter); diff --git a/drivers/net/ethernet/intel/iavf/iavf_client.c b/drivers/net/ethernet/intel/iavf/iavf_client.c deleted file mode 100644 index 93c903c02c64..000000000000 --- a/drivers/net/ethernet/intel/iavf/iavf_client.c +++ /dev/null @@ -1,578 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#include <linux/list.h> -#include <linux/errno.h> - -#include "iavf.h" -#include "iavf_prototype.h" -#include "iavf_client.h" - -static -const char iavf_client_interface_version_str[] = IAVF_CLIENT_VERSION_STR; -static struct iavf_client *vf_registered_client; -static LIST_HEAD(iavf_devices); -static DEFINE_MUTEX(iavf_device_mutex); - -static u32 iavf_client_virtchnl_send(struct iavf_info *ldev, - struct iavf_client *client, - u8 *msg, u16 len); - -static int iavf_client_setup_qvlist(struct iavf_info *ldev, - struct iavf_client *client, - struct iavf_qvlist_info *qvlist_info); - -static struct iavf_ops iavf_lan_ops = { - .virtchnl_send = iavf_client_virtchnl_send, - .setup_qvlist = iavf_client_setup_qvlist, -}; - -/** - * iavf_client_get_params - retrieve relevant client parameters - * @vsi: VSI with parameters - * @params: client param struct - **/ -static -void iavf_client_get_params(struct iavf_vsi *vsi, struct iavf_params *params) -{ - int i; - - memset(params, 0, sizeof(struct iavf_params)); - params->mtu = vsi->netdev->mtu; - params->link_up = vsi->back->link_up; - - for (i = 0; i < IAVF_MAX_USER_PRIORITY; i++) { - params->qos.prio_qos[i].tc = 0; - params->qos.prio_qos[i].qs_handle = vsi->qs_handle; - } -} - -/** - * iavf_notify_client_message - call the client message receive callback - * @vsi: the VSI associated with this client - * @msg: message buffer - * @len: length of message - * - * If there is a client to this VSI, call the client - **/ -void iavf_notify_client_message(struct iavf_vsi *vsi, u8 *msg, u16 len) -{ - struct iavf_client_instance *cinst; - - if (!vsi) - return; - - cinst = vsi->back->cinst; - if (!cinst || !cinst->client || !cinst->client->ops || - !cinst->client->ops->virtchnl_receive) { - dev_dbg(&vsi->back->pdev->dev, - "Cannot locate client instance virtchnl_receive function\n"); - return; - } - cinst->client->ops->virtchnl_receive(&cinst->lan_info, cinst->client, - msg, len); -} - -/** - * iavf_notify_client_l2_params - call the client notify callback - * @vsi: the VSI with l2 param changes - * - * If there is a client to this VSI, call the client - **/ -void iavf_notify_client_l2_params(struct iavf_vsi *vsi) -{ - struct iavf_client_instance *cinst; - struct iavf_params params; - - if (!vsi) - return; - - cinst = vsi->back->cinst; - - if (!cinst || !cinst->client || !cinst->client->ops || - !cinst->client->ops->l2_param_change) { - dev_dbg(&vsi->back->pdev->dev, - "Cannot locate client instance l2_param_change function\n"); - return; - } - iavf_client_get_params(vsi, ¶ms); - cinst->lan_info.params = params; - cinst->client->ops->l2_param_change(&cinst->lan_info, cinst->client, - ¶ms); -} - -/** - * iavf_notify_client_open - call the client open callback - * @vsi: the VSI with netdev opened - * - * If there is a client to this netdev, call the client with open - **/ -void iavf_notify_client_open(struct iavf_vsi *vsi) -{ - struct iavf_adapter *adapter = vsi->back; - struct iavf_client_instance *cinst = adapter->cinst; - int ret; - - if (!cinst || !cinst->client || !cinst->client->ops || - !cinst->client->ops->open) { - dev_dbg(&vsi->back->pdev->dev, - "Cannot locate client instance open function\n"); - return; - } - if (!(test_bit(__IAVF_CLIENT_INSTANCE_OPENED, &cinst->state))) { - ret = cinst->client->ops->open(&cinst->lan_info, cinst->client); - if (!ret) - set_bit(__IAVF_CLIENT_INSTANCE_OPENED, &cinst->state); - } -} - -/** - * iavf_client_release_qvlist - send a message to the PF to release rdma qv map - * @ldev: pointer to L2 context. - * - * Return 0 on success or < 0 on error - **/ -static int iavf_client_release_qvlist(struct iavf_info *ldev) -{ - struct iavf_adapter *adapter = ldev->vf; - enum iavf_status err; - - if (adapter->aq_required) - return -EAGAIN; - - err = iavf_aq_send_msg_to_pf(&adapter->hw, - VIRTCHNL_OP_RELEASE_RDMA_IRQ_MAP, - IAVF_SUCCESS, NULL, 0, NULL); - - if (err) - dev_err(&adapter->pdev->dev, - "Unable to send RDMA vector release message to PF, error %d, aq status %d\n", - err, adapter->hw.aq.asq_last_status); - - return err; -} - -/** - * iavf_notify_client_close - call the client close callback - * @vsi: the VSI with netdev closed - * @reset: true when close called due to reset pending - * - * If there is a client to this netdev, call the client with close - **/ -void iavf_notify_client_close(struct iavf_vsi *vsi, bool reset) -{ - struct iavf_adapter *adapter = vsi->back; - struct iavf_client_instance *cinst = adapter->cinst; - - if (!cinst || !cinst->client || !cinst->client->ops || - !cinst->client->ops->close) { - dev_dbg(&vsi->back->pdev->dev, - "Cannot locate client instance close function\n"); - return; - } - cinst->client->ops->close(&cinst->lan_info, cinst->client, reset); - iavf_client_release_qvlist(&cinst->lan_info); - clear_bit(__IAVF_CLIENT_INSTANCE_OPENED, &cinst->state); -} - -/** - * iavf_client_add_instance - add a client instance to the instance list - * @adapter: pointer to the board struct - * - * Returns cinst ptr on success, NULL on failure - **/ -static struct iavf_client_instance * -iavf_client_add_instance(struct iavf_adapter *adapter) -{ - struct iavf_client_instance *cinst = NULL; - struct iavf_vsi *vsi = &adapter->vsi; - struct netdev_hw_addr *mac = NULL; - struct iavf_params params; - - if (!vf_registered_client) - goto out; - - if (adapter->cinst) { - cinst = adapter->cinst; - goto out; - } - - cinst = kzalloc(sizeof(*cinst), GFP_KERNEL); - if (!cinst) - goto out; - - cinst->lan_info.vf = (void *)adapter; - cinst->lan_info.netdev = vsi->netdev; - cinst->lan_info.pcidev = adapter->pdev; - cinst->lan_info.fid = 0; - cinst->lan_info.ftype = IAVF_CLIENT_FTYPE_VF; - cinst->lan_info.hw_addr = adapter->hw.hw_addr; - cinst->lan_info.ops = &iavf_lan_ops; - cinst->lan_info.version.major = IAVF_CLIENT_VERSION_MAJOR; - cinst->lan_info.version.minor = IAVF_CLIENT_VERSION_MINOR; - cinst->lan_info.version.build = IAVF_CLIENT_VERSION_BUILD; - iavf_client_get_params(vsi, ¶ms); - cinst->lan_info.params = params; - set_bit(__IAVF_CLIENT_INSTANCE_NONE, &cinst->state); - - cinst->lan_info.msix_count = adapter->num_rdma_msix; - cinst->lan_info.msix_entries = - &adapter->msix_entries[adapter->rdma_base_vector]; - - mac = list_first_entry(&cinst->lan_info.netdev->dev_addrs.list, - struct netdev_hw_addr, list); - if (mac) - ether_addr_copy(cinst->lan_info.lanmac, mac->addr); - else - dev_err(&adapter->pdev->dev, "MAC address list is empty!\n"); - - cinst->client = vf_registered_client; - adapter->cinst = cinst; -out: - return cinst; -} - -/** - * iavf_client_del_instance - removes a client instance from the list - * @adapter: pointer to the board struct - * - **/ -static -void iavf_client_del_instance(struct iavf_adapter *adapter) -{ - kfree(adapter->cinst); - adapter->cinst = NULL; -} - -/** - * iavf_client_subtask - client maintenance work - * @adapter: board private structure - **/ -void iavf_client_subtask(struct iavf_adapter *adapter) -{ - struct iavf_client *client = vf_registered_client; - struct iavf_client_instance *cinst; - int ret = 0; - - if (adapter->state < __IAVF_DOWN) - return; - - /* first check client is registered */ - if (!client) - return; - - /* Add the client instance to the instance list */ - cinst = iavf_client_add_instance(adapter); - if (!cinst) - return; - - dev_info(&adapter->pdev->dev, "Added instance of Client %s\n", - client->name); - - if (!test_bit(__IAVF_CLIENT_INSTANCE_OPENED, &cinst->state)) { - /* Send an Open request to the client */ - - if (client->ops && client->ops->open) - ret = client->ops->open(&cinst->lan_info, client); - if (!ret) - set_bit(__IAVF_CLIENT_INSTANCE_OPENED, - &cinst->state); - else - /* remove client instance */ - iavf_client_del_instance(adapter); - } -} - -/** - * iavf_lan_add_device - add a lan device struct to the list of lan devices - * @adapter: pointer to the board struct - * - * Returns 0 on success or none 0 on error - **/ -int iavf_lan_add_device(struct iavf_adapter *adapter) -{ - struct iavf_device *ldev; - int ret = 0; - - mutex_lock(&iavf_device_mutex); - list_for_each_entry(ldev, &iavf_devices, list) { - if (ldev->vf == adapter) { - ret = -EEXIST; - goto out; - } - } - ldev = kzalloc(sizeof(*ldev), GFP_KERNEL); - if (!ldev) { - ret = -ENOMEM; - goto out; - } - ldev->vf = adapter; - INIT_LIST_HEAD(&ldev->list); - list_add(&ldev->list, &iavf_devices); - dev_info(&adapter->pdev->dev, "Added LAN device bus=0x%02x dev=0x%02x func=0x%02x\n", - adapter->hw.bus.bus_id, adapter->hw.bus.device, - adapter->hw.bus.func); - - /* Since in some cases register may have happened before a device gets - * added, we can schedule a subtask to go initiate the clients. - */ - adapter->flags |= IAVF_FLAG_SERVICE_CLIENT_REQUESTED; - -out: - mutex_unlock(&iavf_device_mutex); - return ret; -} - -/** - * iavf_lan_del_device - removes a lan device from the device list - * @adapter: pointer to the board struct - * - * Returns 0 on success or non-0 on error - **/ -int iavf_lan_del_device(struct iavf_adapter *adapter) -{ - struct iavf_device *ldev, *tmp; - int ret = -ENODEV; - - mutex_lock(&iavf_device_mutex); - list_for_each_entry_safe(ldev, tmp, &iavf_devices, list) { - if (ldev->vf == adapter) { - dev_info(&adapter->pdev->dev, - "Deleted LAN device bus=0x%02x dev=0x%02x func=0x%02x\n", - adapter->hw.bus.bus_id, adapter->hw.bus.device, - adapter->hw.bus.func); - list_del(&ldev->list); - kfree(ldev); - ret = 0; - break; - } - } - - mutex_unlock(&iavf_device_mutex); - return ret; -} - -/** - * iavf_client_release - release client specific resources - * @client: pointer to the registered client - * - **/ -static void iavf_client_release(struct iavf_client *client) -{ - struct iavf_client_instance *cinst; - struct iavf_device *ldev; - struct iavf_adapter *adapter; - - mutex_lock(&iavf_device_mutex); - list_for_each_entry(ldev, &iavf_devices, list) { - adapter = ldev->vf; - cinst = adapter->cinst; - if (!cinst) - continue; - if (test_bit(__IAVF_CLIENT_INSTANCE_OPENED, &cinst->state)) { - if (client->ops && client->ops->close) - client->ops->close(&cinst->lan_info, client, - false); - iavf_client_release_qvlist(&cinst->lan_info); - clear_bit(__IAVF_CLIENT_INSTANCE_OPENED, &cinst->state); - - dev_warn(&adapter->pdev->dev, - "Client %s instance closed\n", client->name); - } - /* delete the client instance */ - iavf_client_del_instance(adapter); - dev_info(&adapter->pdev->dev, "Deleted client instance of Client %s\n", - client->name); - } - mutex_unlock(&iavf_device_mutex); -} - -/** - * iavf_client_prepare - prepare client specific resources - * @client: pointer to the registered client - * - **/ -static void iavf_client_prepare(struct iavf_client *client) -{ - struct iavf_device *ldev; - struct iavf_adapter *adapter; - - mutex_lock(&iavf_device_mutex); - list_for_each_entry(ldev, &iavf_devices, list) { - adapter = ldev->vf; - /* Signal the watchdog to service the client */ - adapter->flags |= IAVF_FLAG_SERVICE_CLIENT_REQUESTED; - } - mutex_unlock(&iavf_device_mutex); -} - -/** - * iavf_client_virtchnl_send - send a message to the PF instance - * @ldev: pointer to L2 context. - * @client: Client pointer. - * @msg: pointer to message buffer - * @len: message length - * - * Return 0 on success or < 0 on error - **/ -static u32 iavf_client_virtchnl_send(struct iavf_info *ldev, - struct iavf_client *client, - u8 *msg, u16 len) -{ - struct iavf_adapter *adapter = ldev->vf; - enum iavf_status err; - - if (adapter->aq_required) - return -EAGAIN; - - err = iavf_aq_send_msg_to_pf(&adapter->hw, VIRTCHNL_OP_RDMA, - IAVF_SUCCESS, msg, len, NULL); - if (err) - dev_err(&adapter->pdev->dev, "Unable to send RDMA message to PF, error %d, aq status %d\n", - err, adapter->hw.aq.asq_last_status); - - return err; -} - -/** - * iavf_client_setup_qvlist - send a message to the PF to setup rdma qv map - * @ldev: pointer to L2 context. - * @client: Client pointer. - * @qvlist_info: queue and vector list - * - * Return 0 on success or < 0 on error - **/ -static int iavf_client_setup_qvlist(struct iavf_info *ldev, - struct iavf_client *client, - struct iavf_qvlist_info *qvlist_info) -{ - struct virtchnl_rdma_qvlist_info *v_qvlist_info; - struct iavf_adapter *adapter = ldev->vf; - struct iavf_qv_info *qv_info; - enum iavf_status err; - u32 v_idx, i; - size_t msg_size; - - if (adapter->aq_required) - return -EAGAIN; - - /* A quick check on whether the vectors belong to the client */ - for (i = 0; i < qvlist_info->num_vectors; i++) { - qv_info = &qvlist_info->qv_info[i]; - if (!qv_info) - continue; - v_idx = qv_info->v_idx; - if ((v_idx >= - (adapter->rdma_base_vector + adapter->num_rdma_msix)) || - (v_idx < adapter->rdma_base_vector)) - return -EINVAL; - } - - v_qvlist_info = (struct virtchnl_rdma_qvlist_info *)qvlist_info; - msg_size = struct_size(v_qvlist_info, qv_info, - v_qvlist_info->num_vectors - 1); - - adapter->client_pending |= BIT(VIRTCHNL_OP_CONFIG_RDMA_IRQ_MAP); - err = iavf_aq_send_msg_to_pf(&adapter->hw, - VIRTCHNL_OP_CONFIG_RDMA_IRQ_MAP, IAVF_SUCCESS, - (u8 *)v_qvlist_info, msg_size, NULL); - - if (err) { - dev_err(&adapter->pdev->dev, - "Unable to send RDMA vector config message to PF, error %d, aq status %d\n", - err, adapter->hw.aq.asq_last_status); - goto out; - } - - err = -EBUSY; - for (i = 0; i < 5; i++) { - msleep(100); - if (!(adapter->client_pending & - BIT(VIRTCHNL_OP_CONFIG_RDMA_IRQ_MAP))) { - err = 0; - break; - } - } -out: - return err; -} - -/** - * iavf_register_client - Register a iavf client driver with the L2 driver - * @client: pointer to the iavf_client struct - * - * Returns 0 on success or non-0 on error - **/ -int iavf_register_client(struct iavf_client *client) -{ - int ret = 0; - - if (!client) { - ret = -EIO; - goto out; - } - - if (strlen(client->name) == 0) { - pr_info("iavf: Failed to register client with no name\n"); - ret = -EIO; - goto out; - } - - if (vf_registered_client) { - pr_info("iavf: Client %s has already been registered!\n", - client->name); - ret = -EEXIST; - goto out; - } - - if ((client->version.major != IAVF_CLIENT_VERSION_MAJOR) || - (client->version.minor != IAVF_CLIENT_VERSION_MINOR)) { - pr_info("iavf: Failed to register client %s due to mismatched client interface version\n", - client->name); - pr_info("Client is using version: %02d.%02d.%02d while LAN driver supports %s\n", - client->version.major, client->version.minor, - client->version.build, - iavf_client_interface_version_str); - ret = -EIO; - goto out; - } - - vf_registered_client = client; - - iavf_client_prepare(client); - - pr_info("iavf: Registered client %s with return code %d\n", - client->name, ret); -out: - return ret; -} -EXPORT_SYMBOL(iavf_register_client); - -/** - * iavf_unregister_client - Unregister a iavf client driver with the L2 driver - * @client: pointer to the iavf_client struct - * - * Returns 0 on success or non-0 on error - **/ -int iavf_unregister_client(struct iavf_client *client) -{ - int ret = 0; - - /* When a unregister request comes through we would have to send - * a close for each of the client instances that were opened. - * client_release function is called to handle this. - */ - iavf_client_release(client); - - if (vf_registered_client != client) { - pr_info("iavf: Client %s has not been registered\n", - client->name); - ret = -ENODEV; - goto out; - } - vf_registered_client = NULL; - pr_info("iavf: Unregistered client %s\n", client->name); -out: - return ret; -} -EXPORT_SYMBOL(iavf_unregister_client); diff --git a/drivers/net/ethernet/intel/iavf/iavf_client.h b/drivers/net/ethernet/intel/iavf/iavf_client.h deleted file mode 100644 index c5d51d7dc7cc..000000000000 --- a/drivers/net/ethernet/intel/iavf/iavf_client.h +++ /dev/null @@ -1,169 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#ifndef _IAVF_CLIENT_H_ -#define _IAVF_CLIENT_H_ - -#define IAVF_CLIENT_STR_LENGTH 10 - -/* Client interface version should be updated anytime there is a change in the - * existing APIs or data structures. - */ -#define IAVF_CLIENT_VERSION_MAJOR 0 -#define IAVF_CLIENT_VERSION_MINOR 01 -#define IAVF_CLIENT_VERSION_BUILD 00 -#define IAVF_CLIENT_VERSION_STR \ - __stringify(IAVF_CLIENT_VERSION_MAJOR) "." \ - __stringify(IAVF_CLIENT_VERSION_MINOR) "." \ - __stringify(IAVF_CLIENT_VERSION_BUILD) - -struct iavf_client_version { - u8 major; - u8 minor; - u8 build; - u8 rsvd; -}; - -enum iavf_client_state { - __IAVF_CLIENT_NULL, - __IAVF_CLIENT_REGISTERED -}; - -enum iavf_client_instance_state { - __IAVF_CLIENT_INSTANCE_NONE, - __IAVF_CLIENT_INSTANCE_OPENED, -}; - -struct iavf_ops; -struct iavf_client; - -/* HW does not define a type value for AEQ; only for RX/TX and CEQ. - * In order for us to keep the interface simple, SW will define a - * unique type value for AEQ. - */ -#define IAVF_QUEUE_TYPE_PE_AEQ 0x80 -#define IAVF_QUEUE_INVALID_IDX 0xFFFF - -struct iavf_qv_info { - u32 v_idx; /* msix_vector */ - u16 ceq_idx; - u16 aeq_idx; - u8 itr_idx; -}; - -struct iavf_qvlist_info { - u32 num_vectors; - struct iavf_qv_info qv_info[1]; -}; - -#define IAVF_CLIENT_MSIX_ALL 0xFFFFFFFF - -/* set of LAN parameters useful for clients managed by LAN */ - -/* Struct to hold per priority info */ -struct iavf_prio_qos_params { - u16 qs_handle; /* qs handle for prio */ - u8 tc; /* TC mapped to prio */ - u8 reserved; -}; - -#define IAVF_CLIENT_MAX_USER_PRIORITY 8 -/* Struct to hold Client QoS */ -struct iavf_qos_params { - struct iavf_prio_qos_params prio_qos[IAVF_CLIENT_MAX_USER_PRIORITY]; -}; - -struct iavf_params { - struct iavf_qos_params qos; - u16 mtu; - u16 link_up; /* boolean */ -}; - -/* Structure to hold LAN device info for a client device */ -struct iavf_info { - struct iavf_client_version version; - u8 lanmac[6]; - struct net_device *netdev; - struct pci_dev *pcidev; - u8 __iomem *hw_addr; - u8 fid; /* function id, PF id or VF id */ -#define IAVF_CLIENT_FTYPE_PF 0 -#define IAVF_CLIENT_FTYPE_VF 1 - u8 ftype; /* function type, PF or VF */ - void *vf; /* cast to iavf_adapter */ - - /* All L2 params that could change during the life span of the device - * and needs to be communicated to the client when they change - */ - struct iavf_params params; - struct iavf_ops *ops; - - u16 msix_count; /* number of msix vectors*/ - /* Array down below will be dynamically allocated based on msix_count */ - struct msix_entry *msix_entries; - u16 itr_index; /* Which ITR index the PE driver is suppose to use */ -}; - -struct iavf_ops { - /* setup_q_vector_list enables queues with a particular vector */ - int (*setup_qvlist)(struct iavf_info *ldev, struct iavf_client *client, - struct iavf_qvlist_info *qv_info); - - u32 (*virtchnl_send)(struct iavf_info *ldev, struct iavf_client *client, - u8 *msg, u16 len); - - /* If the PE Engine is unresponsive, RDMA driver can request a reset.*/ - void (*request_reset)(struct iavf_info *ldev, - struct iavf_client *client); -}; - -struct iavf_client_ops { - /* Should be called from register_client() or whenever the driver is - * ready to create a specific client instance. - */ - int (*open)(struct iavf_info *ldev, struct iavf_client *client); - - /* Should be closed when netdev is unavailable or when unregister - * call comes in. If the close happens due to a reset, set the reset - * bit to true. - */ - void (*close)(struct iavf_info *ldev, struct iavf_client *client, - bool reset); - - /* called when some l2 managed parameters changes - mss */ - void (*l2_param_change)(struct iavf_info *ldev, - struct iavf_client *client, - struct iavf_params *params); - - /* called when a message is received from the PF */ - int (*virtchnl_receive)(struct iavf_info *ldev, - struct iavf_client *client, - u8 *msg, u16 len); -}; - -/* Client device */ -struct iavf_client_instance { - struct list_head list; - struct iavf_info lan_info; - struct iavf_client *client; - unsigned long state; -}; - -struct iavf_client { - struct list_head list; /* list of registered clients */ - char name[IAVF_CLIENT_STR_LENGTH]; - struct iavf_client_version version; - unsigned long state; /* client state */ - atomic_t ref_cnt; /* Count of all the client devices of this kind */ - u32 flags; -#define IAVF_CLIENT_FLAGS_LAUNCH_ON_PROBE BIT(0) -#define IAVF_TX_FLAGS_NOTIFY_OTHER_EVENTS BIT(2) - u8 type; -#define IAVF_CLIENT_RDMA 0 - struct iavf_client_ops *ops; /* client ops provided by the client */ -}; - -/* used by clients */ -int iavf_register_client(struct iavf_client *client); -int iavf_unregister_client(struct iavf_client *client); -#endif /* _IAVF_CLIENT_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_common.c b/drivers/net/ethernet/intel/iavf/iavf_common.c index 1afd761d8052..8091e6feca01 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_common.c +++ b/drivers/net/ethernet/intel/iavf/iavf_common.c @@ -7,38 +7,6 @@ #include <linux/avf/virtchnl.h> /** - * iavf_set_mac_type - Sets MAC type - * @hw: pointer to the HW structure - * - * This function sets the mac type of the adapter based on the - * vendor ID and device ID stored in the hw structure. - **/ -enum iavf_status iavf_set_mac_type(struct iavf_hw *hw) -{ - enum iavf_status status = 0; - - if (hw->vendor_id == PCI_VENDOR_ID_INTEL) { - switch (hw->device_id) { - case IAVF_DEV_ID_X722_VF: - hw->mac.type = IAVF_MAC_X722_VF; - break; - case IAVF_DEV_ID_VF: - case IAVF_DEV_ID_VF_HV: - case IAVF_DEV_ID_ADAPTIVE_VF: - hw->mac.type = IAVF_MAC_VF; - break; - default: - hw->mac.type = IAVF_MAC_GENERIC; - break; - } - } else { - status = IAVF_ERR_DEVICE_NOT_SUPPORTED; - } - - return status; -} - -/** * iavf_aq_str - convert AQ err code to a string * @hw: pointer to the HW structure * @aq_err: the AQ error code to convert diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index a34303ad057d..dc499fe7734e 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -362,7 +362,7 @@ static void iavf_get_ethtool_stats(struct net_device *netdev, unsigned int i; /* Explicitly request stats refresh */ - iavf_schedule_request_stats(adapter); + iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_REQUEST_STATS); iavf_add_ethtool_stats(&data, adapter, iavf_gstrings_stats); @@ -395,11 +395,9 @@ static void iavf_get_priv_flag_strings(struct net_device *netdev, u8 *data) { unsigned int i; - for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++) { - snprintf(data, ETH_GSTRING_LEN, "%s", - iavf_gstrings_priv_flags[i].flag_string); - data += ETH_GSTRING_LEN; - } + for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++) + ethtool_sprintf(&data, "%s", + iavf_gstrings_priv_flags[i].flag_string); } /** @@ -829,18 +827,10 @@ static int __iavf_set_coalesce(struct net_device *netdev, struct iavf_adapter *adapter = netdev_priv(netdev); int i; - if (ec->rx_coalesce_usecs == 0) { - if (ec->use_adaptive_rx_coalesce) - netif_info(adapter, drv, netdev, "rx-usecs=0, need to disable adaptive-rx for a complete disable\n"); - } else if ((ec->rx_coalesce_usecs < IAVF_MIN_ITR) || - (ec->rx_coalesce_usecs > IAVF_MAX_ITR)) { + if (ec->rx_coalesce_usecs > IAVF_MAX_ITR) { netif_info(adapter, drv, netdev, "Invalid value, rx-usecs range is 0-8160\n"); return -EINVAL; - } else if (ec->tx_coalesce_usecs == 0) { - if (ec->use_adaptive_tx_coalesce) - netif_info(adapter, drv, netdev, "tx-usecs=0, need to disable adaptive-tx for a complete disable\n"); - } else if ((ec->tx_coalesce_usecs < IAVF_MIN_ITR) || - (ec->tx_coalesce_usecs > IAVF_MAX_ITR)) { + } else if (ec->tx_coalesce_usecs > IAVF_MAX_ITR) { netif_info(adapter, drv, netdev, "Invalid value, tx-usecs range is 0-8160\n"); return -EINVAL; } @@ -1071,7 +1061,7 @@ iavf_get_ethtool_fdir_entry(struct iavf_adapter *adapter, struct iavf_fdir_fltr *rule = NULL; int ret = 0; - if (!FDIR_FLTR_SUPPORT(adapter)) + if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) return -EOPNOTSUPP; spin_lock_bh(&adapter->fdir_fltr_lock); @@ -1213,7 +1203,7 @@ iavf_get_fdir_fltr_ids(struct iavf_adapter *adapter, struct ethtool_rxnfc *cmd, unsigned int cnt = 0; int val = 0; - if (!FDIR_FLTR_SUPPORT(adapter)) + if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) return -EOPNOTSUPP; cmd->data = IAVF_MAX_FDIR_FILTERS; @@ -1405,7 +1395,7 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx int count = 50; int err; - if (!FDIR_FLTR_SUPPORT(adapter)) + if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) return -EOPNOTSUPP; if (fsp->flow_type & FLOW_MAC_EXT) @@ -1446,12 +1436,16 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx spin_lock_bh(&adapter->fdir_fltr_lock); iavf_fdir_list_add_fltr(adapter, fltr); adapter->fdir_active_fltr++; - fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST; - adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER; + if (adapter->link_up) { + fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER; + } else { + fltr->state = IAVF_FDIR_FLTR_INACTIVE; + } spin_unlock_bh(&adapter->fdir_fltr_lock); - mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); - + if (adapter->link_up) + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); ret: if (err && fltr) kfree(fltr); @@ -1473,7 +1467,7 @@ static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx struct iavf_fdir_fltr *fltr = NULL; int err = 0; - if (!FDIR_FLTR_SUPPORT(adapter)) + if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) return -EOPNOTSUPP; spin_lock_bh(&adapter->fdir_fltr_lock); @@ -1482,6 +1476,11 @@ static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx if (fltr->state == IAVF_FDIR_FLTR_ACTIVE) { fltr->state = IAVF_FDIR_FLTR_DEL_REQUEST; adapter->aq_required |= IAVF_FLAG_AQ_DEL_FDIR_FILTER; + } else if (fltr->state == IAVF_FDIR_FLTR_INACTIVE) { + list_del(&fltr->list); + kfree(fltr); + adapter->fdir_active_fltr--; + fltr = NULL; } else { err = -EBUSY; } @@ -1790,7 +1789,7 @@ static int iavf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, ret = 0; break; case ETHTOOL_GRXCLSRLCNT: - if (!FDIR_FLTR_SUPPORT(adapter)) + if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) break; spin_lock_bh(&adapter->fdir_fltr_lock); cmd->rule_cnt = adapter->fdir_active_fltr; diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.h b/drivers/net/ethernet/intel/iavf/iavf_fdir.h index 9eb9f73f6adf..d31bd923ba8c 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.h +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.h @@ -6,12 +6,25 @@ struct iavf_adapter; -/* State of Flow Director filter */ +/* State of Flow Director filter + * + * *_REQUEST states are used to mark filter to be sent to PF driver to perform + * an action (either add or delete filter). *_PENDING states are an indication + * that request was sent to PF and the driver is waiting for response. + * + * Both DELETE and DISABLE states are being used to delete a filter in PF. + * The difference is that after a successful response filter in DEL_PENDING + * state is being deleted from VF driver as well and filter in DIS_PENDING state + * is being changed to INACTIVE state. + */ enum iavf_fdir_fltr_state_t { IAVF_FDIR_FLTR_ADD_REQUEST, /* User requests to add filter */ IAVF_FDIR_FLTR_ADD_PENDING, /* Filter pending add by the PF */ IAVF_FDIR_FLTR_DEL_REQUEST, /* User requests to delete filter */ IAVF_FDIR_FLTR_DEL_PENDING, /* Filter pending delete by the PF */ + IAVF_FDIR_FLTR_DIS_REQUEST, /* Filter scheduled to be disabled */ + IAVF_FDIR_FLTR_DIS_PENDING, /* Filter pending disable by the PF */ + IAVF_FDIR_FLTR_INACTIVE, /* Filter inactive on link down */ IAVF_FDIR_FLTR_ACTIVE, /* Filter is active */ }; diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 9610ca770349..e8d5b889addc 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -3,7 +3,6 @@ #include "iavf.h" #include "iavf_prototype.h" -#include "iavf_client.h" /* All iavf tracepoints are defined by the include below, which must * be included exactly once across the whole kernel with * CREATE_TRACE_POINTS defined @@ -278,27 +277,6 @@ void iavf_free_virt_mem(struct iavf_hw *hw, struct iavf_virt_mem *mem) } /** - * iavf_lock_timeout - try to lock mutex but give up after timeout - * @lock: mutex that should be locked - * @msecs: timeout in msecs - * - * Returns 0 on success, negative on failure - **/ -static int iavf_lock_timeout(struct mutex *lock, unsigned int msecs) -{ - unsigned int wait, delay = 10; - - for (wait = 0; wait < msecs; wait += delay) { - if (mutex_trylock(lock)) - return 0; - - msleep(delay); - } - - return -1; -} - -/** * iavf_schedule_reset - Set the flags and schedule a reset event * @adapter: board private structure * @flags: IAVF_FLAG_RESET_PENDING or IAVF_FLAG_RESET_NEEDED @@ -314,15 +292,13 @@ void iavf_schedule_reset(struct iavf_adapter *adapter, u64 flags) } /** - * iavf_schedule_request_stats - Set the flags and schedule statistics request + * iavf_schedule_aq_request - Set the flags and schedule aq request * @adapter: board private structure - * - * Sets IAVF_FLAG_AQ_REQUEST_STATS flag so iavf_watchdog_task() will explicitly - * request and refresh ethtool stats + * @flags: requested aq flags **/ -void iavf_schedule_request_stats(struct iavf_adapter *adapter) +void iavf_schedule_aq_request(struct iavf_adapter *adapter, u64 flags) { - adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_STATS; + adapter->aq_required |= flags; mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); } @@ -823,7 +799,7 @@ iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter, list_add_tail(&f->list, &adapter->vlan_filter_list); f->state = IAVF_VLAN_ADD; adapter->num_vlan_filters++; - adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; + iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_VLAN_FILTER); } clearout: @@ -845,7 +821,7 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan) f = iavf_find_vlan(adapter, vlan); if (f) { f->state = IAVF_VLAN_REMOVE; - adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER; + iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_VLAN_FILTER); } spin_unlock_bh(&adapter->mac_vlan_list_lock); @@ -1189,6 +1165,16 @@ static int iavf_addr_unsync(struct net_device *netdev, const u8 *addr) } /** + * iavf_promiscuous_mode_changed - check if promiscuous mode bits changed + * @adapter: device specific adapter + */ +bool iavf_promiscuous_mode_changed(struct iavf_adapter *adapter) +{ + return (adapter->current_netdev_promisc_flags ^ adapter->netdev->flags) & + (IFF_PROMISC | IFF_ALLMULTI); +} + +/** * iavf_set_rx_mode - NDO callback to set the netdev filters * @netdev: network interface device structure **/ @@ -1201,19 +1187,10 @@ static void iavf_set_rx_mode(struct net_device *netdev) __dev_mc_sync(netdev, iavf_addr_sync, iavf_addr_unsync); spin_unlock_bh(&adapter->mac_vlan_list_lock); - if (netdev->flags & IFF_PROMISC && - !(adapter->flags & IAVF_FLAG_PROMISC_ON)) - adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_PROMISC; - else if (!(netdev->flags & IFF_PROMISC) && - adapter->flags & IAVF_FLAG_PROMISC_ON) - adapter->aq_required |= IAVF_FLAG_AQ_RELEASE_PROMISC; - - if (netdev->flags & IFF_ALLMULTI && - !(adapter->flags & IAVF_FLAG_ALLMULTI_ON)) - adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_ALLMULTI; - else if (!(netdev->flags & IFF_ALLMULTI) && - adapter->flags & IAVF_FLAG_ALLMULTI_ON) - adapter->aq_required |= IAVF_FLAG_AQ_RELEASE_ALLMULTI; + spin_lock_bh(&adapter->current_netdev_promisc_flags_lock); + if (iavf_promiscuous_mode_changed(adapter)) + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_PROMISC_MODE; + spin_unlock_bh(&adapter->current_netdev_promisc_flags_lock); } /** @@ -1277,7 +1254,7 @@ static void iavf_configure(struct iavf_adapter *adapter) * iavf_up_complete - Finish the last steps of bringing up a connection * @adapter: board private structure * - * Expects to be called while holding the __IAVF_IN_CRITICAL_TASK bit lock. + * Expects to be called while holding crit_lock. **/ static void iavf_up_complete(struct iavf_adapter *adapter) { @@ -1287,8 +1264,6 @@ static void iavf_up_complete(struct iavf_adapter *adapter) iavf_napi_enable_all(adapter); adapter->aq_required |= IAVF_FLAG_AQ_ENABLE_QUEUES; - if (CLIENT_ENABLED(adapter)) - adapter->flags |= IAVF_FLAG_CLIENT_NEEDS_OPEN; mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); } @@ -1357,18 +1332,20 @@ static void iavf_clear_cloud_filters(struct iavf_adapter *adapter) **/ static void iavf_clear_fdir_filters(struct iavf_adapter *adapter) { - struct iavf_fdir_fltr *fdir, *fdirtmp; + struct iavf_fdir_fltr *fdir; /* remove all Flow Director filters */ spin_lock_bh(&adapter->fdir_fltr_lock); - list_for_each_entry_safe(fdir, fdirtmp, &adapter->fdir_list_head, - list) { + list_for_each_entry(fdir, &adapter->fdir_list_head, list) { if (fdir->state == IAVF_FDIR_FLTR_ADD_REQUEST) { - list_del(&fdir->list); - kfree(fdir); - adapter->fdir_active_fltr--; - } else { - fdir->state = IAVF_FDIR_FLTR_DEL_REQUEST; + /* Cancel a request, keep filter as inactive */ + fdir->state = IAVF_FDIR_FLTR_INACTIVE; + } else if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING || + fdir->state == IAVF_FDIR_FLTR_ACTIVE) { + /* Disable filters which are active or have a pending + * request to PF to be added + */ + fdir->state = IAVF_FDIR_FLTR_DIS_REQUEST; } } spin_unlock_bh(&adapter->fdir_fltr_lock); @@ -1401,7 +1378,7 @@ static void iavf_clear_adv_rss_conf(struct iavf_adapter *adapter) * iavf_down - Shutdown the connection processing * @adapter: board private structure * - * Expects to be called while holding the __IAVF_IN_CRITICAL_TASK bit lock. + * Expects to be called while holding crit_lock. **/ void iavf_down(struct iavf_adapter *adapter) { @@ -1421,7 +1398,10 @@ void iavf_down(struct iavf_adapter *adapter) iavf_clear_fdir_filters(adapter); iavf_clear_adv_rss_conf(adapter); - if (!(adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)) { + if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) + return; + + if (!test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) { /* cancel any current operation */ adapter->current_op = VIRTCHNL_OP_UNKNOWN; /* Schedule operations to close down the HW. Don't wait @@ -1438,9 +1418,9 @@ void iavf_down(struct iavf_adapter *adapter) adapter->aq_required |= IAVF_FLAG_AQ_DEL_FDIR_FILTER; if (!list_empty(&adapter->adv_rss_list_head)) adapter->aq_required |= IAVF_FLAG_AQ_DEL_ADV_RSS_CFG; - adapter->aq_required |= IAVF_FLAG_AQ_DISABLE_QUEUES; } + adapter->aq_required |= IAVF_FLAG_AQ_DISABLE_QUEUES; mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); } @@ -1953,6 +1933,17 @@ err_alloc_queues: } /** + * iavf_free_interrupt_scheme - Undo what iavf_init_interrupt_scheme does + * @adapter: board private structure + **/ +static void iavf_free_interrupt_scheme(struct iavf_adapter *adapter) +{ + iavf_free_q_vectors(adapter); + iavf_reset_interrupt_capability(adapter); + iavf_free_queues(adapter); +} + +/** * iavf_free_rss - Free memory used by RSS structs * @adapter: board private structure **/ @@ -1980,11 +1971,9 @@ static int iavf_reinit_interrupt_scheme(struct iavf_adapter *adapter, bool runni if (running) iavf_free_traffic_irqs(adapter); iavf_free_misc_irq(adapter); - iavf_reset_interrupt_capability(adapter); - iavf_free_q_vectors(adapter); - iavf_free_queues(adapter); + iavf_free_interrupt_scheme(adapter); - err = iavf_init_interrupt_scheme(adapter); + err = iavf_init_interrupt_scheme(adapter); if (err) goto err; @@ -2019,7 +2008,7 @@ static void iavf_finish_config(struct work_struct *work) mutex_lock(&adapter->crit_lock); if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES) && - adapter->netdev_registered && + adapter->netdev->reg_state == NETREG_REGISTERED && !test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) { netdev_update_features(adapter->netdev); adapter->flags &= ~IAVF_FLAG_SETUP_NETDEV_FEATURES; @@ -2027,7 +2016,7 @@ static void iavf_finish_config(struct work_struct *work) switch (adapter->state) { case __IAVF_DOWN: - if (!adapter->netdev_registered) { + if (adapter->netdev->reg_state != NETREG_REGISTERED) { err = register_netdevice(adapter->netdev); if (err) { dev_err(&adapter->pdev->dev, "Unable to register netdev (%d)\n", @@ -2041,7 +2030,6 @@ static void iavf_finish_config(struct work_struct *work) __IAVF_INIT_CONFIG_ADAPTER); goto out; } - adapter->netdev_registered = true; } /* Set the real number of queues when reset occurs while @@ -2163,19 +2151,8 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter) return 0; } - if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_PROMISC) { - iavf_set_promiscuous(adapter, FLAG_VF_UNICAST_PROMISC | - FLAG_VF_MULTICAST_PROMISC); - return 0; - } - - if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_ALLMULTI) { - iavf_set_promiscuous(adapter, FLAG_VF_MULTICAST_PROMISC); - return 0; - } - if ((adapter->aq_required & IAVF_FLAG_AQ_RELEASE_PROMISC) || - (adapter->aq_required & IAVF_FLAG_AQ_RELEASE_ALLMULTI)) { - iavf_set_promiscuous(adapter, 0); + if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_PROMISC_MODE) { + iavf_set_promiscuous(adapter); return 0; } @@ -2367,11 +2344,6 @@ static void iavf_startup(struct iavf_adapter *adapter) /* driver loaded, probe complete */ adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; adapter->flags &= ~IAVF_FLAG_RESET_PENDING; - status = iavf_set_mac_type(hw); - if (status) { - dev_err(&pdev->dev, "Failed to set MAC type (%d)\n", status); - goto err; - } ret = iavf_check_reset_complete(hw); if (ret) { @@ -2712,12 +2684,6 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) adapter->link_up = false; netif_tx_stop_all_queues(netdev); - if (CLIENT_ALLOWED(adapter)) { - err = iavf_lan_add_device(adapter); - if (err) - dev_info(&pdev->dev, "Failed to add VF to client API service list: %d\n", - err); - } dev_info(&pdev->dev, "MAC address: %pM\n", adapter->hw.mac.addr); if (netdev->features & NETIF_F_GRO) dev_info(&pdev->dev, "GRO is enabled\n"); @@ -2914,7 +2880,6 @@ static void iavf_watchdog_task(struct work_struct *work) return; } - schedule_delayed_work(&adapter->client_task, msecs_to_jiffies(5)); mutex_unlock(&adapter->crit_lock); restart_watchdog: if (adapter->state >= __IAVF_DOWN) @@ -2983,9 +2948,7 @@ static void iavf_disable_vf(struct iavf_adapter *adapter) spin_unlock_bh(&adapter->cloud_filter_list_lock); iavf_free_misc_irq(adapter); - iavf_reset_interrupt_capability(adapter); - iavf_free_q_vectors(adapter); - iavf_free_queues(adapter); + iavf_free_interrupt_scheme(adapter); memset(adapter->vf_res, 0, IAVF_VIRTCHNL_VF_RESOURCE_SIZE); iavf_shutdown_adminq(&adapter->hw); adapter->flags &= ~IAVF_FLAG_RESET_PENDING; @@ -3027,16 +2990,6 @@ static void iavf_reset_task(struct work_struct *work) return; } - while (!mutex_trylock(&adapter->client_lock)) - usleep_range(500, 1000); - if (CLIENT_ENABLED(adapter)) { - adapter->flags &= ~(IAVF_FLAG_CLIENT_NEEDS_OPEN | - IAVF_FLAG_CLIENT_NEEDS_CLOSE | - IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS | - IAVF_FLAG_SERVICE_CLIENT_REQUESTED); - cancel_delayed_work_sync(&adapter->client_task); - iavf_notify_client_close(&adapter->vsi, true); - } iavf_misc_irq_disable(adapter); if (adapter->flags & IAVF_FLAG_RESET_NEEDED) { adapter->flags &= ~IAVF_FLAG_RESET_NEEDED; @@ -3080,7 +3033,6 @@ static void iavf_reset_task(struct work_struct *work) dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n", reg_val); iavf_disable_vf(adapter); - mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); return; /* Do not attempt to reinit. It's dead, Jim. */ } @@ -3219,7 +3171,6 @@ continue_reset: adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; wake_up(&adapter->reset_waitqueue); - mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); return; @@ -3230,7 +3181,6 @@ reset_err: } iavf_disable_vf(adapter); - mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); } @@ -3330,48 +3280,6 @@ out: } /** - * iavf_client_task - worker thread to perform client work - * @work: pointer to work_struct containing our data - * - * This task handles client interactions. Because client calls can be - * reentrant, we can't handle them in the watchdog. - **/ -static void iavf_client_task(struct work_struct *work) -{ - struct iavf_adapter *adapter = - container_of(work, struct iavf_adapter, client_task.work); - - /* If we can't get the client bit, just give up. We'll be rescheduled - * later. - */ - - if (!mutex_trylock(&adapter->client_lock)) - return; - - if (adapter->flags & IAVF_FLAG_SERVICE_CLIENT_REQUESTED) { - iavf_client_subtask(adapter); - adapter->flags &= ~IAVF_FLAG_SERVICE_CLIENT_REQUESTED; - goto out; - } - if (adapter->flags & IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS) { - iavf_notify_client_l2_params(&adapter->vsi); - adapter->flags &= ~IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS; - goto out; - } - if (adapter->flags & IAVF_FLAG_CLIENT_NEEDS_CLOSE) { - iavf_notify_client_close(&adapter->vsi, false); - adapter->flags &= ~IAVF_FLAG_CLIENT_NEEDS_CLOSE; - goto out; - } - if (adapter->flags & IAVF_FLAG_CLIENT_NEEDS_OPEN) { - iavf_notify_client_open(&adapter->vsi); - adapter->flags &= ~IAVF_FLAG_CLIENT_NEEDS_OPEN; - } -out: - mutex_unlock(&adapter->client_lock); -} - -/** * iavf_free_all_tx_resources - Free Tx Resources for All Queues * @adapter: board private structure * @@ -3744,15 +3652,15 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter, struct virtchnl_filter *vf = &filter->f; if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_VLAN) | - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_PORTS) | - BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) { - dev_err(&adapter->pdev->dev, "Unsupported key used: 0x%x\n", + ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID))) { + dev_err(&adapter->pdev->dev, "Unsupported key used: 0x%llx\n", dissector->used_keys); return -EOPNOTSUPP; } @@ -4186,6 +4094,33 @@ static int iavf_setup_tc(struct net_device *netdev, enum tc_setup_type type, } /** + * iavf_restore_fdir_filters + * @adapter: board private structure + * + * Restore existing FDIR filters when VF netdev comes back up. + **/ +static void iavf_restore_fdir_filters(struct iavf_adapter *adapter) +{ + struct iavf_fdir_fltr *f; + + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry(f, &adapter->fdir_list_head, list) { + if (f->state == IAVF_FDIR_FLTR_DIS_REQUEST) { + /* Cancel a request, keep filter as active */ + f->state = IAVF_FDIR_FLTR_ACTIVE; + } else if (f->state == IAVF_FDIR_FLTR_DIS_PENDING || + f->state == IAVF_FDIR_FLTR_INACTIVE) { + /* Add filters which are inactive or have a pending + * request to PF to be deleted + */ + f->state = IAVF_FDIR_FLTR_ADD_REQUEST; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER; + } + } + spin_unlock_bh(&adapter->fdir_fltr_lock); +} + +/** * iavf_open - Called when a network interface is made active * @netdev: network interface device structure * @@ -4252,8 +4187,9 @@ static int iavf_open(struct net_device *netdev) spin_unlock_bh(&adapter->mac_vlan_list_lock); - /* Restore VLAN filters that were removed with IFF_DOWN */ + /* Restore filters that were removed with IFF_DOWN */ iavf_restore_filters(adapter); + iavf_restore_fdir_filters(adapter); iavf_configure(adapter); @@ -4303,8 +4239,6 @@ static int iavf_close(struct net_device *netdev) } set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); - if (CLIENT_ENABLED(adapter)) - adapter->flags |= IAVF_FLAG_CLIENT_NEEDS_CLOSE; /* We cannot send IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS before * IAVF_FLAG_AQ_DISABLE_QUEUES because in such case there is rtnl * deadlock with adminq_task() until iavf_close timeouts. We must send @@ -4373,10 +4307,6 @@ static int iavf_change_mtu(struct net_device *netdev, int new_mtu) netdev_dbg(netdev, "changing MTU from %d to %d\n", netdev->mtu, new_mtu); netdev->mtu = new_mtu; - if (CLIENT_ENABLED(adapter)) { - iavf_notify_client_l2_params(&adapter->vsi); - adapter->flags |= IAVF_FLAG_SERVICE_CLIENT_REQUESTED; - } if (netif_running(netdev)) { iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); @@ -4390,6 +4320,49 @@ static int iavf_change_mtu(struct net_device *netdev, int new_mtu) return ret; } +/** + * iavf_disable_fdir - disable Flow Director and clear existing filters + * @adapter: board private structure + **/ +static void iavf_disable_fdir(struct iavf_adapter *adapter) +{ + struct iavf_fdir_fltr *fdir, *fdirtmp; + bool del_filters = false; + + adapter->flags &= ~IAVF_FLAG_FDIR_ENABLED; + + /* remove all Flow Director filters */ + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry_safe(fdir, fdirtmp, &adapter->fdir_list_head, + list) { + if (fdir->state == IAVF_FDIR_FLTR_ADD_REQUEST || + fdir->state == IAVF_FDIR_FLTR_INACTIVE) { + /* Delete filters not registered in PF */ + list_del(&fdir->list); + kfree(fdir); + adapter->fdir_active_fltr--; + } else if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING || + fdir->state == IAVF_FDIR_FLTR_DIS_REQUEST || + fdir->state == IAVF_FDIR_FLTR_ACTIVE) { + /* Filters registered in PF, schedule their deletion */ + fdir->state = IAVF_FDIR_FLTR_DEL_REQUEST; + del_filters = true; + } else if (fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) { + /* Request to delete filter already sent to PF, change + * state to DEL_PENDING to delete filter after PF's + * response, not set as INACTIVE + */ + fdir->state = IAVF_FDIR_FLTR_DEL_PENDING; + } + } + spin_unlock_bh(&adapter->fdir_fltr_lock); + + if (del_filters) { + adapter->aq_required |= IAVF_FLAG_AQ_DEL_FDIR_FILTER; + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); + } +} + #define NETIF_VLAN_OFFLOAD_FEATURES (NETIF_F_HW_VLAN_CTAG_RX | \ NETIF_F_HW_VLAN_CTAG_TX | \ NETIF_F_HW_VLAN_STAG_RX | \ @@ -4411,6 +4384,16 @@ static int iavf_set_features(struct net_device *netdev, (features & NETIF_VLAN_OFFLOAD_FEATURES)) iavf_set_vlan_offload_features(adapter, netdev->features, features); + if (CRC_OFFLOAD_ALLOWED(adapter) && + ((netdev->features & NETIF_F_RXFCS) ^ (features & NETIF_F_RXFCS))) + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); + + if ((netdev->features & NETIF_F_NTUPLE) ^ (features & NETIF_F_NTUPLE)) { + if (features & NETIF_F_NTUPLE) + adapter->flags |= IAVF_FLAG_FDIR_ENABLED; + else + iavf_disable_fdir(adapter); + } return 0; } @@ -4532,6 +4515,9 @@ iavf_get_netdev_vlan_hw_features(struct iavf_adapter *adapter) } } + if (CRC_OFFLOAD_ALLOWED(adapter)) + hw_features |= NETIF_F_RXFCS; + return hw_features; } @@ -4696,6 +4682,55 @@ iavf_fix_netdev_vlan_features(struct iavf_adapter *adapter, } /** + * iavf_fix_strip_features - fix NETDEV CRC and VLAN strip features + * @adapter: board private structure + * @requested_features: stack requested NETDEV features + * + * Returns fixed-up features bits + **/ +static netdev_features_t +iavf_fix_strip_features(struct iavf_adapter *adapter, + netdev_features_t requested_features) +{ + struct net_device *netdev = adapter->netdev; + bool crc_offload_req, is_vlan_strip; + netdev_features_t vlan_strip; + int num_non_zero_vlan; + + crc_offload_req = CRC_OFFLOAD_ALLOWED(adapter) && + (requested_features & NETIF_F_RXFCS); + num_non_zero_vlan = iavf_get_num_vlans_added(adapter); + vlan_strip = (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX); + is_vlan_strip = requested_features & vlan_strip; + + if (!crc_offload_req) + return requested_features; + + if (!num_non_zero_vlan && (netdev->features & vlan_strip) && + !(netdev->features & NETIF_F_RXFCS) && is_vlan_strip) { + requested_features &= ~vlan_strip; + netdev_info(netdev, "Disabling VLAN stripping as FCS/CRC stripping is also disabled and there is no VLAN configured\n"); + return requested_features; + } + + if ((netdev->features & NETIF_F_RXFCS) && is_vlan_strip) { + requested_features &= ~vlan_strip; + if (!(netdev->features & vlan_strip)) + netdev_info(netdev, "To enable VLAN stripping, first need to enable FCS/CRC stripping"); + + return requested_features; + } + + if (num_non_zero_vlan && is_vlan_strip && + !(netdev->features & NETIF_F_RXFCS)) { + requested_features &= ~NETIF_F_RXFCS; + netdev_info(netdev, "To disable FCS/CRC stripping, first need to disable VLAN stripping"); + } + + return requested_features; +} + +/** * iavf_fix_features - fix up the netdev feature bits * @netdev: our net device * @features: desired feature bits @@ -4707,7 +4742,12 @@ static netdev_features_t iavf_fix_features(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); - return iavf_fix_netdev_vlan_features(adapter, features); + features = iavf_fix_netdev_vlan_features(adapter, features); + + if (!FDIR_FLTR_SUPPORT(adapter)) + features &= ~NETIF_F_NTUPLE; + + return iavf_fix_strip_features(adapter, features); } static const struct net_device_ops iavf_netdev_ops = { @@ -4744,7 +4784,7 @@ static int iavf_check_reset_complete(struct iavf_hw *hw) if ((rstat == VIRTCHNL_VFR_VFACTIVE) || (rstat == VIRTCHNL_VFR_COMPLETED)) return 0; - usleep_range(10, 20); + msleep(IAVF_RESET_WAIT_MS); } return -EBUSY; } @@ -4824,6 +4864,12 @@ int iavf_process_config(struct iavf_adapter *adapter) if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN) netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + if (FDIR_FLTR_SUPPORT(adapter)) { + netdev->hw_features |= NETIF_F_NTUPLE; + netdev->features |= NETIF_F_NTUPLE; + adapter->flags |= IAVF_FLAG_FDIR_ENABLED; + } + netdev->priv_flags |= IFF_UNICAST_FLT; /* Do not turn on offloads when they are requested to be turned off. @@ -4848,34 +4894,6 @@ int iavf_process_config(struct iavf_adapter *adapter) } /** - * iavf_shutdown - Shutdown the device in preparation for a reboot - * @pdev: pci device structure - **/ -static void iavf_shutdown(struct pci_dev *pdev) -{ - struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev); - struct net_device *netdev = adapter->netdev; - - netif_device_detach(netdev); - - if (netif_running(netdev)) - iavf_close(netdev); - - if (iavf_lock_timeout(&adapter->crit_lock, 5000)) - dev_warn(&adapter->pdev->dev, "%s: failed to acquire crit_lock\n", __func__); - /* Prevent the watchdog from running. */ - iavf_change_state(adapter, __IAVF_REMOVE); - adapter->aq_required = 0; - mutex_unlock(&adapter->crit_lock); - -#ifdef CONFIG_PM - pci_save_state(pdev); - -#endif - pci_disable_device(pdev); -} - -/** * iavf_probe - Device Initialization Routine * @pdev: PCI device information struct * @ent: entry in iavf_pci_tbl @@ -4963,7 +4981,6 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * and destroy them only once in remove */ mutex_init(&adapter->crit_lock); - mutex_init(&adapter->client_lock); mutex_init(&hw->aq.asq_mutex); mutex_init(&hw->aq.arq_mutex); @@ -4971,6 +4988,7 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) spin_lock_init(&adapter->cloud_filter_list_lock); spin_lock_init(&adapter->fdir_fltr_lock); spin_lock_init(&adapter->adv_rss_lock); + spin_lock_init(&adapter->current_netdev_promisc_flags_lock); INIT_LIST_HEAD(&adapter->mac_filter_list); INIT_LIST_HEAD(&adapter->vlan_filter_list); @@ -4982,9 +5000,6 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&adapter->adminq_task, iavf_adminq_task); INIT_WORK(&adapter->finish_config, iavf_finish_config); INIT_DELAYED_WORK(&adapter->watchdog_task, iavf_watchdog_task); - INIT_DELAYED_WORK(&adapter->client_task, iavf_client_task); - queue_delayed_work(adapter->wq, &adapter->watchdog_task, - msecs_to_jiffies(5 * (pdev->devfn & 0x07))); /* Setup the wait queue for indicating transition to down status */ init_waitqueue_head(&adapter->down_waitqueue); @@ -4995,6 +5010,9 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Setup the wait queue for indicating virtchannel events */ init_waitqueue_head(&adapter->vc_waitqueue); + queue_delayed_work(adapter->wq, &adapter->watchdog_task, + msecs_to_jiffies(5 * (pdev->devfn & 0x07))); + /* Initialization goes on in the work. Do not add more of it below. */ return 0; err_ioremap: @@ -5022,8 +5040,7 @@ static int __maybe_unused iavf_suspend(struct device *dev_d) netif_device_detach(netdev); - while (!mutex_trylock(&adapter->crit_lock)) - usleep_range(500, 1000); + mutex_lock(&adapter->crit_lock); if (netif_running(netdev)) { rtnl_lock(); @@ -5086,17 +5103,21 @@ static int __maybe_unused iavf_resume(struct device *dev_d) **/ static void iavf_remove(struct pci_dev *pdev) { - struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev); struct iavf_fdir_fltr *fdir, *fdirtmp; struct iavf_vlan_filter *vlf, *vlftmp; struct iavf_cloud_filter *cf, *cftmp; struct iavf_adv_rss *rss, *rsstmp; struct iavf_mac_filter *f, *ftmp; + struct iavf_adapter *adapter; struct net_device *netdev; struct iavf_hw *hw; - int err; - netdev = adapter->netdev; + /* Don't proceed with remove if netdev is already freed */ + netdev = pci_get_drvdata(pdev); + if (!netdev) + return; + + adapter = iavf_pdev_to_adapter(pdev); hw = &adapter->hw; if (test_and_set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) @@ -5125,19 +5146,8 @@ static void iavf_remove(struct pci_dev *pdev) cancel_delayed_work_sync(&adapter->watchdog_task); cancel_work_sync(&adapter->finish_config); - rtnl_lock(); - if (adapter->netdev_registered) { - unregister_netdevice(netdev); - adapter->netdev_registered = false; - } - rtnl_unlock(); - - if (CLIENT_ALLOWED(adapter)) { - err = iavf_lan_del_device(adapter); - if (err) - dev_warn(&pdev->dev, "Failed to delete client device: %d\n", - err); - } + if (netdev->reg_state == NETREG_REGISTERED) + unregister_netdev(netdev); mutex_lock(&adapter->crit_lock); dev_info(&adapter->pdev->dev, "Removing device\n"); @@ -5156,7 +5166,6 @@ static void iavf_remove(struct pci_dev *pdev) cancel_work_sync(&adapter->reset_task); cancel_delayed_work_sync(&adapter->watchdog_task); cancel_work_sync(&adapter->adminq_task); - cancel_delayed_work_sync(&adapter->client_task); adapter->aq_required = 0; adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; @@ -5164,9 +5173,7 @@ static void iavf_remove(struct pci_dev *pdev) iavf_free_all_tx_resources(adapter); iavf_free_all_rx_resources(adapter); iavf_free_misc_irq(adapter); - - iavf_reset_interrupt_capability(adapter); - iavf_free_q_vectors(adapter); + iavf_free_interrupt_scheme(adapter); iavf_free_rss(adapter); @@ -5176,13 +5183,11 @@ static void iavf_remove(struct pci_dev *pdev) /* destroy the locks only once, here */ mutex_destroy(&hw->aq.arq_mutex); mutex_destroy(&hw->aq.asq_mutex); - mutex_destroy(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); mutex_destroy(&adapter->crit_lock); iounmap(hw->hw_addr); pci_release_regions(pdev); - iavf_free_queues(adapter); kfree(adapter->vf_res); spin_lock_bh(&adapter->mac_vlan_list_lock); /* If we got removed before an up/down sequence, we've got a filter @@ -5224,11 +5229,25 @@ static void iavf_remove(struct pci_dev *pdev) destroy_workqueue(adapter->wq); + pci_set_drvdata(pdev, NULL); + free_netdev(netdev); pci_disable_device(pdev); } +/** + * iavf_shutdown - Shutdown the device in preparation for a reboot + * @pdev: pci device structure + **/ +static void iavf_shutdown(struct pci_dev *pdev) +{ + iavf_remove(pdev); + + if (system_state == SYSTEM_POWER_OFF) + pci_set_power_state(pdev, PCI_D3hot); +} + static SIMPLE_DEV_PM_OPS(iavf_pm_ops, iavf_suspend, iavf_resume); static struct pci_driver iavf_driver = { diff --git a/drivers/net/ethernet/intel/iavf/iavf_prototype.h b/drivers/net/ethernet/intel/iavf/iavf_prototype.h index 940cb4203fbe..4a48e6171405 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_prototype.h +++ b/drivers/net/ethernet/intel/iavf/iavf_prototype.h @@ -45,8 +45,6 @@ enum iavf_status iavf_aq_set_rss_lut(struct iavf_hw *hw, u16 seid, enum iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 seid, struct iavf_aqc_get_set_rss_key_data *key); -enum iavf_status iavf_set_mac_type(struct iavf_hw *hw); - extern struct iavf_rx_ptype_decoded iavf_ptype_lookup[]; static inline struct iavf_rx_ptype_decoded decode_rx_desc_ptype(u8 ptype) diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index 8c5f6096b002..d64c4997136b 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -7,8 +7,8 @@ #include "iavf_trace.h" #include "iavf_prototype.h" -static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size, - u32 td_tag) +static __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size, + u32 td_tag) { return cpu_to_le64(IAVF_TX_DESC_DTYPE_DATA | ((u64)td_cmd << IAVF_TXD_QW1_CMD_SHIFT) | @@ -370,8 +370,8 @@ static void iavf_enable_wb_on_itr(struct iavf_vsi *vsi, q_vector->arm_wb_state = true; } -static inline bool iavf_container_is_rx(struct iavf_q_vector *q_vector, - struct iavf_ring_container *rc) +static bool iavf_container_is_rx(struct iavf_q_vector *q_vector, + struct iavf_ring_container *rc) { return &q_vector->rx == rc; } @@ -806,7 +806,7 @@ err: * @rx_ring: ring to bump * @val: new head index **/ -static inline void iavf_release_rx_desc(struct iavf_ring *rx_ring, u32 val) +static void iavf_release_rx_desc(struct iavf_ring *rx_ring, u32 val) { rx_ring->next_to_use = val; @@ -828,7 +828,7 @@ static inline void iavf_release_rx_desc(struct iavf_ring *rx_ring, u32 val) * * Returns the offset value for ring into the data buffer. */ -static inline unsigned int iavf_rx_offset(struct iavf_ring *rx_ring) +static unsigned int iavf_rx_offset(struct iavf_ring *rx_ring) { return ring_uses_build_skb(rx_ring) ? IAVF_SKB_PAD : 0; } @@ -977,9 +977,9 @@ no_buffers: * @skb: skb currently being received and modified * @rx_desc: the receive descriptor **/ -static inline void iavf_rx_checksum(struct iavf_vsi *vsi, - struct sk_buff *skb, - union iavf_rx_desc *rx_desc) +static void iavf_rx_checksum(struct iavf_vsi *vsi, + struct sk_buff *skb, + union iavf_rx_desc *rx_desc) { struct iavf_rx_ptype_decoded decoded; u32 rx_error, rx_status; @@ -1061,7 +1061,7 @@ checksum_fail: * * Returns a hash type to be used by skb_set_hash **/ -static inline int iavf_ptype_to_htype(u8 ptype) +static int iavf_ptype_to_htype(u8 ptype) { struct iavf_rx_ptype_decoded decoded = decode_rx_desc_ptype(ptype); @@ -1085,10 +1085,10 @@ static inline int iavf_ptype_to_htype(u8 ptype) * @skb: skb currently being received and modified * @rx_ptype: Rx packet type **/ -static inline void iavf_rx_hash(struct iavf_ring *ring, - union iavf_rx_desc *rx_desc, - struct sk_buff *skb, - u8 rx_ptype) +static void iavf_rx_hash(struct iavf_ring *ring, + union iavf_rx_desc *rx_desc, + struct sk_buff *skb, + u8 rx_ptype) { u32 hash; const __le64 rss_mask = @@ -1115,10 +1115,10 @@ static inline void iavf_rx_hash(struct iavf_ring *ring, * order to populate the hash, checksum, VLAN, protocol, and * other fields within the skb. **/ -static inline -void iavf_process_skb_fields(struct iavf_ring *rx_ring, - union iavf_rx_desc *rx_desc, struct sk_buff *skb, - u8 rx_ptype) +static void +iavf_process_skb_fields(struct iavf_ring *rx_ring, + union iavf_rx_desc *rx_desc, struct sk_buff *skb, + u8 rx_ptype) { iavf_rx_hash(rx_ring, rx_desc, skb, rx_ptype); @@ -1662,8 +1662,8 @@ static inline u32 iavf_buildreg_itr(const int type, u16 itr) * @q_vector: q_vector for which itr is being updated and interrupt enabled * **/ -static inline void iavf_update_enable_itr(struct iavf_vsi *vsi, - struct iavf_q_vector *q_vector) +static void iavf_update_enable_itr(struct iavf_vsi *vsi, + struct iavf_q_vector *q_vector) { struct iavf_hw *hw = &vsi->back->hw; u32 intval; @@ -2275,9 +2275,9 @@ int __iavf_maybe_stop_tx(struct iavf_ring *tx_ring, int size) * @td_cmd: the command field in the descriptor * @td_offset: offset for checksum or crc **/ -static inline void iavf_tx_map(struct iavf_ring *tx_ring, struct sk_buff *skb, - struct iavf_tx_buffer *first, u32 tx_flags, - const u8 hdr_len, u32 td_cmd, u32 td_offset) +static void iavf_tx_map(struct iavf_ring *tx_ring, struct sk_buff *skb, + struct iavf_tx_buffer *first, u32 tx_flags, + const u8 hdr_len, u32 td_cmd, u32 td_offset) { unsigned int data_len = skb->data_len; unsigned int size = skb_headlen(skb); diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h index 7e6ee32d19b6..10ba36602c0c 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h @@ -15,7 +15,6 @@ */ #define IAVF_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ #define IAVF_ITR_MASK 0x1FFE /* mask for ITR register value */ -#define IAVF_MIN_ITR 2 /* reg uses 2 usec resolution */ #define IAVF_ITR_100K 10 /* all values below must be even */ #define IAVF_ITR_50K 20 #define IAVF_ITR_20K 50 diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h index 9f1f523807c4..2b6a207fa441 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_type.h +++ b/drivers/net/ethernet/intel/iavf/iavf_type.h @@ -69,15 +69,6 @@ enum iavf_debug_mask { * the Firmware and AdminQ are intended to insulate the driver from most of the * future changes, but these structures will also do part of the job. */ -enum iavf_mac_type { - IAVF_MAC_UNKNOWN = 0, - IAVF_MAC_XL710, - IAVF_MAC_VF, - IAVF_MAC_X722, - IAVF_MAC_X722_VF, - IAVF_MAC_GENERIC, -}; - enum iavf_vsi_type { IAVF_VSI_MAIN = 0, IAVF_VSI_VMDQ1 = 1, @@ -110,11 +101,8 @@ struct iavf_hw_capabilities { }; struct iavf_mac_info { - enum iavf_mac_type type; u8 addr[ETH_ALEN]; u8 perm_addr[ETH_ALEN]; - u8 san_addr[ETH_ALEN]; - u16 max_fcoeq; }; /* PCI bus types */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index be3c007ce90a..2d9366be0ec5 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -3,7 +3,6 @@ #include "iavf.h" #include "iavf_prototype.h" -#include "iavf_client.h" /** * iavf_send_pf_msg @@ -142,6 +141,7 @@ int iavf_send_vf_config_msg(struct iavf_adapter *adapter) VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 | VIRTCHNL_VF_OFFLOAD_ENCAP | VIRTCHNL_VF_OFFLOAD_VLAN_V2 | + VIRTCHNL_VF_OFFLOAD_CRC | VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM | VIRTCHNL_VF_OFFLOAD_REQ_QUEUES | VIRTCHNL_VF_OFFLOAD_ADQ | @@ -215,8 +215,7 @@ int iavf_get_vf_config(struct iavf_adapter *adapter) u16 len; int err; - len = sizeof(struct virtchnl_vf_resource) + - IAVF_MAX_VF_VSI * sizeof(struct virtchnl_vsi_resource); + len = IAVF_VIRTCHNL_VF_RESOURCE_SIZE; event.buf_len = len; event.msg_buf = kzalloc(len, GFP_KERNEL); if (!event.msg_buf) @@ -284,7 +283,7 @@ void iavf_configure_queues(struct iavf_adapter *adapter) return; } adapter->current_op = VIRTCHNL_OP_CONFIG_VSI_QUEUES; - len = struct_size(vqci, qpair, pairs); + len = virtchnl_struct_size(vqci, qpair, pairs); vqci = kzalloc(len, GFP_KERNEL); if (!vqci) return; @@ -313,6 +312,9 @@ void iavf_configure_queues(struct iavf_adapter *adapter) vqpi->rxq.databuffer_size = ALIGN(adapter->rx_rings[i].rx_buf_len, BIT_ULL(IAVF_RXQ_CTX_DBUFF_SHIFT)); + if (CRC_OFFLOAD_ALLOWED(adapter)) + vqpi->rxq.crc_disable = !!(adapter->netdev->features & + NETIF_F_RXFCS); vqpi++; } @@ -397,7 +399,7 @@ void iavf_map_queues(struct iavf_adapter *adapter) q_vectors = adapter->num_msix_vectors - NONQ_VECS; - len = struct_size(vimi, vecmap, adapter->num_msix_vectors); + len = virtchnl_struct_size(vimi, vecmap, adapter->num_msix_vectors); vimi = kzalloc(len, GFP_KERNEL); if (!vimi) return; @@ -476,13 +478,11 @@ void iavf_add_ether_addrs(struct iavf_adapter *adapter) } adapter->current_op = VIRTCHNL_OP_ADD_ETH_ADDR; - len = struct_size(veal, list, count); + len = virtchnl_struct_size(veal, list, count); if (len > IAVF_MAX_AQ_BUF_SIZE) { dev_warn(&adapter->pdev->dev, "Too many add MAC changes in one request\n"); - count = (IAVF_MAX_AQ_BUF_SIZE - - sizeof(struct virtchnl_ether_addr_list)) / - sizeof(struct virtchnl_ether_addr); - len = struct_size(veal, list, count); + while (len > IAVF_MAX_AQ_BUF_SIZE) + len = virtchnl_struct_size(veal, list, --count); more = true; } @@ -547,13 +547,11 @@ void iavf_del_ether_addrs(struct iavf_adapter *adapter) } adapter->current_op = VIRTCHNL_OP_DEL_ETH_ADDR; - len = struct_size(veal, list, count); + len = virtchnl_struct_size(veal, list, count); if (len > IAVF_MAX_AQ_BUF_SIZE) { dev_warn(&adapter->pdev->dev, "Too many delete MAC changes in one request\n"); - count = (IAVF_MAX_AQ_BUF_SIZE - - sizeof(struct virtchnl_ether_addr_list)) / - sizeof(struct virtchnl_ether_addr); - len = struct_size(veal, list, count); + while (len > IAVF_MAX_AQ_BUF_SIZE) + len = virtchnl_struct_size(veal, list, --count); more = true; } veal = kzalloc(len, GFP_ATOMIC); @@ -687,12 +685,12 @@ void iavf_add_vlans(struct iavf_adapter *adapter) adapter->current_op = VIRTCHNL_OP_ADD_VLAN; - len = sizeof(*vvfl) + (count * sizeof(u16)); + len = virtchnl_struct_size(vvfl, vlan_id, count); if (len > IAVF_MAX_AQ_BUF_SIZE) { dev_warn(&adapter->pdev->dev, "Too many add VLAN changes in one request\n"); - count = (IAVF_MAX_AQ_BUF_SIZE - sizeof(*vvfl)) / - sizeof(u16); - len = sizeof(*vvfl) + (count * sizeof(u16)); + while (len > IAVF_MAX_AQ_BUF_SIZE) + len = virtchnl_struct_size(vvfl, vlan_id, + --count); more = true; } vvfl = kzalloc(len, GFP_ATOMIC); @@ -732,15 +730,12 @@ void iavf_add_vlans(struct iavf_adapter *adapter) more = true; } - len = sizeof(*vvfl_v2) + ((count - 1) * - sizeof(struct virtchnl_vlan_filter)); + len = virtchnl_struct_size(vvfl_v2, filters, count); if (len > IAVF_MAX_AQ_BUF_SIZE) { dev_warn(&adapter->pdev->dev, "Too many add VLAN changes in one request\n"); - count = (IAVF_MAX_AQ_BUF_SIZE - sizeof(*vvfl_v2)) / - sizeof(struct virtchnl_vlan_filter); - len = sizeof(*vvfl_v2) + - ((count - 1) * - sizeof(struct virtchnl_vlan_filter)); + while (len > IAVF_MAX_AQ_BUF_SIZE) + len = virtchnl_struct_size(vvfl_v2, filters, + --count); more = true; } @@ -838,12 +833,12 @@ void iavf_del_vlans(struct iavf_adapter *adapter) adapter->current_op = VIRTCHNL_OP_DEL_VLAN; - len = sizeof(*vvfl) + (count * sizeof(u16)); + len = virtchnl_struct_size(vvfl, vlan_id, count); if (len > IAVF_MAX_AQ_BUF_SIZE) { dev_warn(&adapter->pdev->dev, "Too many delete VLAN changes in one request\n"); - count = (IAVF_MAX_AQ_BUF_SIZE - sizeof(*vvfl)) / - sizeof(u16); - len = sizeof(*vvfl) + (count * sizeof(u16)); + while (len > IAVF_MAX_AQ_BUF_SIZE) + len = virtchnl_struct_size(vvfl, vlan_id, + --count); more = true; } vvfl = kzalloc(len, GFP_ATOMIC); @@ -884,16 +879,12 @@ void iavf_del_vlans(struct iavf_adapter *adapter) adapter->current_op = VIRTCHNL_OP_DEL_VLAN_V2; - len = sizeof(*vvfl_v2) + - ((count - 1) * sizeof(struct virtchnl_vlan_filter)); + len = virtchnl_struct_size(vvfl_v2, filters, count); if (len > IAVF_MAX_AQ_BUF_SIZE) { dev_warn(&adapter->pdev->dev, "Too many add VLAN changes in one request\n"); - count = (IAVF_MAX_AQ_BUF_SIZE - - sizeof(*vvfl_v2)) / - sizeof(struct virtchnl_vlan_filter); - len = sizeof(*vvfl_v2) + - ((count - 1) * - sizeof(struct virtchnl_vlan_filter)); + while (len > IAVF_MAX_AQ_BUF_SIZE) + len = virtchnl_struct_size(vvfl_v2, filters, + --count); more = true; } @@ -948,14 +939,14 @@ void iavf_del_vlans(struct iavf_adapter *adapter) /** * iavf_set_promiscuous * @adapter: adapter structure - * @flags: bitmask to control unicast/multicast promiscuous. * * Request that the PF enable promiscuous mode for our VSI. **/ -void iavf_set_promiscuous(struct iavf_adapter *adapter, int flags) +void iavf_set_promiscuous(struct iavf_adapter *adapter) { + struct net_device *netdev = adapter->netdev; struct virtchnl_promisc_info vpi; - int promisc_all; + unsigned int flags; if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { /* bail because we already have a command pending */ @@ -964,36 +955,57 @@ void iavf_set_promiscuous(struct iavf_adapter *adapter, int flags) return; } - promisc_all = FLAG_VF_UNICAST_PROMISC | - FLAG_VF_MULTICAST_PROMISC; - if ((flags & promisc_all) == promisc_all) { - adapter->flags |= IAVF_FLAG_PROMISC_ON; - adapter->aq_required &= ~IAVF_FLAG_AQ_REQUEST_PROMISC; - dev_info(&adapter->pdev->dev, "Entering promiscuous mode\n"); - } + /* prevent changes to promiscuous flags */ + spin_lock_bh(&adapter->current_netdev_promisc_flags_lock); - if (flags & FLAG_VF_MULTICAST_PROMISC) { - adapter->flags |= IAVF_FLAG_ALLMULTI_ON; - adapter->aq_required &= ~IAVF_FLAG_AQ_REQUEST_ALLMULTI; - dev_info(&adapter->pdev->dev, "%s is entering multicast promiscuous mode\n", - adapter->netdev->name); + /* sanity check to prevent duplicate AQ calls */ + if (!iavf_promiscuous_mode_changed(adapter)) { + adapter->aq_required &= ~IAVF_FLAG_AQ_CONFIGURE_PROMISC_MODE; + dev_dbg(&adapter->pdev->dev, "No change in promiscuous mode\n"); + /* allow changes to promiscuous flags */ + spin_unlock_bh(&adapter->current_netdev_promisc_flags_lock); + return; } - if (!flags) { - if (adapter->flags & IAVF_FLAG_PROMISC_ON) { - adapter->flags &= ~IAVF_FLAG_PROMISC_ON; - adapter->aq_required &= ~IAVF_FLAG_AQ_RELEASE_PROMISC; - dev_info(&adapter->pdev->dev, "Leaving promiscuous mode\n"); - } + /* there are 2 bits, but only 3 states */ + if (!(netdev->flags & IFF_PROMISC) && + netdev->flags & IFF_ALLMULTI) { + /* State 1 - only multicast promiscuous mode enabled + * - !IFF_PROMISC && IFF_ALLMULTI + */ + flags = FLAG_VF_MULTICAST_PROMISC; + adapter->current_netdev_promisc_flags |= IFF_ALLMULTI; + adapter->current_netdev_promisc_flags &= ~IFF_PROMISC; + dev_info(&adapter->pdev->dev, "Entering multicast promiscuous mode\n"); + } else if (!(netdev->flags & IFF_PROMISC) && + !(netdev->flags & IFF_ALLMULTI)) { + /* State 2 - unicast/multicast promiscuous mode disabled + * - !IFF_PROMISC && !IFF_ALLMULTI + */ + flags = 0; + adapter->current_netdev_promisc_flags &= + ~(IFF_PROMISC | IFF_ALLMULTI); + dev_info(&adapter->pdev->dev, "Leaving promiscuous mode\n"); + } else { + /* State 3 - unicast/multicast promiscuous mode enabled + * - IFF_PROMISC && IFF_ALLMULTI + * - IFF_PROMISC && !IFF_ALLMULTI + */ + flags = FLAG_VF_UNICAST_PROMISC | FLAG_VF_MULTICAST_PROMISC; + adapter->current_netdev_promisc_flags |= IFF_PROMISC; + if (netdev->flags & IFF_ALLMULTI) + adapter->current_netdev_promisc_flags |= IFF_ALLMULTI; + else + adapter->current_netdev_promisc_flags &= ~IFF_ALLMULTI; - if (adapter->flags & IAVF_FLAG_ALLMULTI_ON) { - adapter->flags &= ~IAVF_FLAG_ALLMULTI_ON; - adapter->aq_required &= ~IAVF_FLAG_AQ_RELEASE_ALLMULTI; - dev_info(&adapter->pdev->dev, "%s is leaving multicast promiscuous mode\n", - adapter->netdev->name); - } + dev_info(&adapter->pdev->dev, "Entering promiscuous mode\n"); } + adapter->aq_required &= ~IAVF_FLAG_AQ_CONFIGURE_PROMISC_MODE; + + /* allow changes to promiscuous flags */ + spin_unlock_bh(&adapter->current_netdev_promisc_flags_lock); + adapter->current_op = VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE; vpi.vsi_id = adapter->vsi_res->vsi_id; vpi.flags = flags; @@ -1085,8 +1097,7 @@ void iavf_set_rss_key(struct iavf_adapter *adapter) adapter->current_op); return; } - len = sizeof(struct virtchnl_rss_key) + - (adapter->rss_key_size * sizeof(u8)) - 1; + len = virtchnl_struct_size(vrk, key, adapter->rss_key_size); vrk = kzalloc(len, GFP_KERNEL); if (!vrk) return; @@ -1117,8 +1128,7 @@ void iavf_set_rss_lut(struct iavf_adapter *adapter) adapter->current_op); return; } - len = sizeof(struct virtchnl_rss_lut) + - (adapter->rss_lut_size * sizeof(u8)) - 1; + len = virtchnl_struct_size(vrl, lut, adapter->rss_lut_size); vrl = kzalloc(len, GFP_KERNEL); if (!vrl) return; @@ -1367,8 +1377,6 @@ void iavf_disable_vlan_insertion_v2(struct iavf_adapter *adapter, u16 tpid) VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2); } -#define IAVF_MAX_SPEED_STRLEN 13 - /** * iavf_print_link_message - print link up or down * @adapter: adapter structure @@ -1386,10 +1394,6 @@ static void iavf_print_link_message(struct iavf_adapter *adapter) return; } - speed = kzalloc(IAVF_MAX_SPEED_STRLEN, GFP_KERNEL); - if (!speed) - return; - if (ADV_LINK_SUPPORT(adapter)) { link_speed_mbps = adapter->link_speed_mbps; goto print_link_msg; @@ -1427,17 +1431,17 @@ static void iavf_print_link_message(struct iavf_adapter *adapter) print_link_msg: if (link_speed_mbps > SPEED_1000) { - if (link_speed_mbps == SPEED_2500) - snprintf(speed, IAVF_MAX_SPEED_STRLEN, "2.5 Gbps"); - else + if (link_speed_mbps == SPEED_2500) { + speed = kasprintf(GFP_KERNEL, "%s", "2.5 Gbps"); + } else { /* convert to Gbps inline */ - snprintf(speed, IAVF_MAX_SPEED_STRLEN, "%d %s", - link_speed_mbps / 1000, "Gbps"); + speed = kasprintf(GFP_KERNEL, "%d Gbps", + link_speed_mbps / 1000); + } } else if (link_speed_mbps == SPEED_UNKNOWN) { - snprintf(speed, IAVF_MAX_SPEED_STRLEN, "%s", "Unknown Mbps"); + speed = kasprintf(GFP_KERNEL, "%s", "Unknown Mbps"); } else { - snprintf(speed, IAVF_MAX_SPEED_STRLEN, "%d %s", - link_speed_mbps, "Mbps"); + speed = kasprintf(GFP_KERNEL, "%d Mbps", link_speed_mbps); } netdev_info(netdev, "NIC Link is Up Speed is %s Full Duplex\n", speed); @@ -1499,7 +1503,7 @@ void iavf_enable_channels(struct iavf_adapter *adapter) return; } - len = struct_size(vti, list, adapter->num_tc - 1); + len = virtchnl_struct_size(vti, list, adapter->num_tc); vti = kzalloc(len, GFP_KERNEL); if (!vti) return; @@ -1731,8 +1735,8 @@ void iavf_add_fdir_filter(struct iavf_adapter *adapter) **/ void iavf_del_fdir_filter(struct iavf_adapter *adapter) { + struct virtchnl_fdir_del f = {}; struct iavf_fdir_fltr *fdir; - struct virtchnl_fdir_del f; bool process_fltr = false; int len; @@ -1749,11 +1753,16 @@ void iavf_del_fdir_filter(struct iavf_adapter *adapter) list_for_each_entry(fdir, &adapter->fdir_list_head, list) { if (fdir->state == IAVF_FDIR_FLTR_DEL_REQUEST) { process_fltr = true; - memset(&f, 0, len); f.vsi_id = fdir->vc_add_msg.vsi_id; f.flow_id = fdir->flow_id; fdir->state = IAVF_FDIR_FLTR_DEL_PENDING; break; + } else if (fdir->state == IAVF_FDIR_FLTR_DIS_REQUEST) { + process_fltr = true; + f.vsi_id = fdir->vc_add_msg.vsi_id; + f.flow_id = fdir->flow_id; + fdir->state = IAVF_FDIR_FLTR_DIS_PENDING; + break; } } spin_unlock_bh(&adapter->fdir_fltr_lock); @@ -1898,6 +1907,48 @@ static void iavf_netdev_features_vlan_strip_set(struct net_device *netdev, } /** + * iavf_activate_fdir_filters - Reactivate all FDIR filters after a reset + * @adapter: private adapter structure + * + * Called after a reset to re-add all FDIR filters and delete some of them + * if they were pending to be deleted. + */ +static void iavf_activate_fdir_filters(struct iavf_adapter *adapter) +{ + struct iavf_fdir_fltr *f, *ftmp; + bool add_filters = false; + + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry_safe(f, ftmp, &adapter->fdir_list_head, list) { + if (f->state == IAVF_FDIR_FLTR_ADD_REQUEST || + f->state == IAVF_FDIR_FLTR_ADD_PENDING || + f->state == IAVF_FDIR_FLTR_ACTIVE) { + /* All filters and requests have been removed in PF, + * restore them + */ + f->state = IAVF_FDIR_FLTR_ADD_REQUEST; + add_filters = true; + } else if (f->state == IAVF_FDIR_FLTR_DIS_REQUEST || + f->state == IAVF_FDIR_FLTR_DIS_PENDING) { + /* Link down state, leave filters as inactive */ + f->state = IAVF_FDIR_FLTR_INACTIVE; + } else if (f->state == IAVF_FDIR_FLTR_DEL_REQUEST || + f->state == IAVF_FDIR_FLTR_DEL_PENDING) { + /* Delete filters that were pending to be deleted, the + * list on PF is already cleared after a reset + */ + list_del(&f->list); + kfree(f); + adapter->fdir_active_fltr--; + } + } + spin_unlock_bh(&adapter->fdir_fltr_lock); + + if (add_filters) + adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER; +} + +/** * iavf_virtchnl_completion * @adapter: adapter structure * @v_opcode: opcode sent by PF @@ -2074,7 +2125,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, spin_lock_bh(&adapter->fdir_fltr_lock); list_for_each_entry(fdir, &adapter->fdir_list_head, list) { - if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING) { + if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING || + fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) { fdir->state = IAVF_FDIR_FLTR_ACTIVE; dev_info(&adapter->pdev->dev, "Failed to del Flow Director filter, error %s\n", iavf_stat_str(&adapter->hw, @@ -2175,9 +2227,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, } break; case VIRTCHNL_OP_GET_VF_RESOURCES: { - u16 len = sizeof(struct virtchnl_vf_resource) + - IAVF_MAX_VF_VSI * - sizeof(struct virtchnl_vsi_resource); + u16 len = IAVF_VIRTCHNL_VF_RESOURCE_SIZE; + memcpy(adapter->vf_res, msg, min(msglen, len)); iavf_validate_num_queues(adapter); iavf_vf_parse_hw_config(&adapter->hw, adapter->vf_res); @@ -2211,6 +2262,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, spin_unlock_bh(&adapter->mac_vlan_list_lock); + iavf_activate_fdir_filters(adapter); + iavf_parse_vf_resource_msg(adapter); /* negotiated VIRTCHNL_VF_OFFLOAD_VLAN_V2, so wait for the @@ -2305,19 +2358,6 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, if (v_opcode != adapter->current_op) return; break; - case VIRTCHNL_OP_RDMA: - /* Gobble zero-length replies from the PF. They indicate that - * a previous message was received OK, and the client doesn't - * care about that. - */ - if (msglen && CLIENT_ENABLED(adapter)) - iavf_notify_client_message(&adapter->vsi, msg, msglen); - break; - - case VIRTCHNL_OP_CONFIG_RDMA_IRQ_MAP: - adapter->client_pending &= - ~(BIT(VIRTCHNL_OP_CONFIG_RDMA_IRQ_MAP)); - break; case VIRTCHNL_OP_GET_RSS_HENA_CAPS: { struct virtchnl_rss_hena *vrh = (struct virtchnl_rss_hena *)msg; @@ -2400,7 +2440,9 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, list_for_each_entry_safe(fdir, fdir_tmp, &adapter->fdir_list_head, list) { if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING) { - if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS) { + if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS || + del_fltr->status == + VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST) { dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is deleted\n", fdir->loc); list_del(&fdir->list); @@ -2412,6 +2454,17 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, del_fltr->status); iavf_print_fdir_fltr(adapter, fdir); } + } else if (fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) { + if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS || + del_fltr->status == + VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST) { + fdir->state = IAVF_FDIR_FLTR_INACTIVE; + } else { + fdir->state = IAVF_FDIR_FLTR_ACTIVE; + dev_info(&adapter->pdev->dev, "Failed to disable Flow Director filter with status: %d\n", + del_fltr->status); + iavf_print_fdir_fltr(adapter, fdir); + } } } spin_unlock_bh(&adapter->fdir_fltr_lock); diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index 817977e3039d..0679907980f7 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -43,9 +43,9 @@ ice-$(CONFIG_PCI_IOV) += \ ice_vf_mbx.o \ ice_vf_vsi_vlan_ops.o \ ice_vf_lib.o -ice-$(CONFIG_PTP_1588_CLOCK) += ice_ptp.o ice_ptp_hw.o +ice-$(CONFIG_PTP_1588_CLOCK) += ice_ptp.o ice_ptp_hw.o ice_dpll.o ice-$(CONFIG_DCB) += ice_dcb.o ice_dcb_nl.o ice_dcb_lib.o ice-$(CONFIG_RFS_ACCEL) += ice_arfs.o ice-$(CONFIG_XDP_SOCKETS) += ice_xsk.o -ice-$(CONFIG_ICE_SWITCHDEV) += ice_eswitch.o +ice-$(CONFIG_ICE_SWITCHDEV) += ice_eswitch.o ice_eswitch_br.o ice-$(CONFIG_GNSS) += ice_gnss.o diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 4ba3d99439a0..351e0d36df44 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -76,6 +76,7 @@ #include "ice_vsi_vlan_ops.h" #include "ice_gnss.h" #include "ice_irq.h" +#include "ice_dpll.h" #define ICE_BAR0 0 #define ICE_REQ_DESC_MULTIPLE 32 @@ -195,11 +196,16 @@ #define ice_pf_to_dev(pf) (&((pf)->pdev->dev)) +#define ice_pf_src_tmr_owned(pf) ((pf)->hw.func_caps.ts_func_info.src_tmr_owned) + enum ice_feature { ICE_F_DSCP, - ICE_F_PTP_EXTTS, + ICE_F_PHY_RCLK, ICE_F_SMA_CTRL, + ICE_F_CGU, ICE_F_GNSS, + ICE_F_ROCE_LAG, + ICE_F_SRIOV_LAG, ICE_F_MAX }; @@ -370,6 +376,7 @@ struct ice_vsi { u16 rx_buf_len; struct ice_aqc_vsi_props info; /* VSI properties */ + struct ice_vsi_vlan_info vlan_info; /* vlan config to be restored */ /* VSI stats */ struct rtnl_link_stats64 net_stats; @@ -505,6 +512,7 @@ enum ice_pf_flags { ICE_FLAG_UNPLUG_AUX_DEV, ICE_FLAG_MTU_CHANGED, ICE_FLAG_GNSS, /* GNSS successfully initialized */ + ICE_FLAG_DPLL, /* SyncE/PTP dplls initialized */ ICE_PF_FLAGS_NBITS /* must be last */ }; @@ -517,6 +525,7 @@ enum ice_misc_thread_tasks { struct ice_switchdev_info { struct ice_vsi *control_vsi; struct ice_vsi *uplink_vsi; + struct ice_esw_br_offloads *br_offloads; bool is_running; }; @@ -545,6 +554,8 @@ struct ice_pf { * MSIX vectors allowed on this PF. */ u16 sriov_base_vector; + unsigned long *sriov_irq_bm; /* bitmap to track irq usage */ + u16 sriov_irq_size; /* size of the irq_bm bitmap */ u16 ctrl_vsi_idx; /* control VSI index in pf->vsi array */ @@ -567,6 +578,7 @@ struct ice_pf { struct mutex sw_mutex; /* lock for protecting VSI alloc flow */ struct mutex tc_mutex; /* lock to protect TC changes */ struct mutex adev_mutex; /* lock to protect aux device access */ + struct mutex lag_mutex; /* protect ice_lag struct in PF */ u32 msg_enable; struct ice_ptp ptp; struct gnss_serial *gnss_serial; @@ -626,6 +638,7 @@ struct ice_pf { struct ice_lag *lag; /* Link Aggregation information */ struct ice_switchdev_info switchdev; + struct ice_esw_br_port *br_port; #define ICE_INVALID_AGG_NODE_ID 0 #define ICE_PF_AGG_NODE_ID_START 1 @@ -634,8 +647,11 @@ struct ice_pf { #define ICE_VF_AGG_NODE_ID_START 65 #define ICE_MAX_VF_AGG_NODES 32 struct ice_agg_node vf_agg_node[ICE_MAX_VF_AGG_NODES]; + struct ice_dplls dplls; }; +extern struct workqueue_struct *ice_lag_wq; + struct ice_netdev_priv { struct ice_vsi *vsi; struct ice_repr *repr; @@ -660,6 +676,18 @@ static inline bool ice_vector_ch_enabled(struct ice_q_vector *qv) } /** + * ice_ptp_pf_handles_tx_interrupt - Check if PF handles Tx interrupt + * @pf: Board private structure + * + * Return true if this PF should respond to the Tx timestamp interrupt + * indication in the miscellaneous OICR interrupt handler. + */ +static inline bool ice_ptp_pf_handles_tx_interrupt(struct ice_pf *pf) +{ + return pf->ptp.tx_interrupt_mode != ICE_PTP_TX_INTERRUPT_NONE; +} + +/** * ice_irq_dynamic_ena - Enable default interrupt generation settings * @hw: pointer to HW struct * @vsi: pointer to VSI struct, can be NULL @@ -853,7 +881,7 @@ static inline bool ice_is_adq_active(struct ice_pf *pf) return false; } -bool netif_is_ice(struct net_device *dev); +bool netif_is_ice(const struct net_device *dev); int ice_vsi_setup_tx_rings(struct ice_vsi *vsi); int ice_vsi_setup_rx_rings(struct ice_vsi *vsi); int ice_vsi_open_ctrl(struct ice_vsi *vsi); @@ -909,14 +937,32 @@ void ice_fdir_release_flows(struct ice_hw *hw); void ice_fdir_replay_flows(struct ice_hw *hw); void ice_fdir_replay_fltrs(struct ice_pf *pf); int ice_fdir_create_dflt_rules(struct ice_pf *pf); -int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, - struct ice_rq_event_info *event); + +enum ice_aq_task_state { + ICE_AQ_TASK_NOT_PREPARED, + ICE_AQ_TASK_WAITING, + ICE_AQ_TASK_COMPLETE, + ICE_AQ_TASK_CANCELED, +}; + +struct ice_aq_task { + struct hlist_node entry; + struct ice_rq_event_info event; + enum ice_aq_task_state state; + u16 opcode; +}; + +void ice_aq_prep_for_event(struct ice_pf *pf, struct ice_aq_task *task, + u16 opcode); +int ice_aq_wait_for_event(struct ice_pf *pf, struct ice_aq_task *task, + unsigned long timeout); int ice_open(struct net_device *netdev); int ice_open_internal(struct net_device *netdev); int ice_stop(struct net_device *netdev); void ice_service_task_schedule(struct ice_pf *pf); int ice_load(struct ice_pf *pf); void ice_unload(struct ice_pf *pf); +void ice_adv_lnk_speed_maps_init(void); /** * ice_set_rdma_cap - enable RDMA support diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 63d3e1dcbba5..d7fdb7ba7268 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -120,6 +120,9 @@ struct ice_aqc_list_caps_elem { #define ICE_AQC_CAPS_PCIE_RESET_AVOIDANCE 0x0076 #define ICE_AQC_CAPS_POST_UPDATE_RESET_RESTRICT 0x0077 #define ICE_AQC_CAPS_NVM_MGMT 0x0080 +#define ICE_AQC_CAPS_FW_LAG_SUPPORT 0x0092 +#define ICE_AQC_BIT_ROCEV2_LAG 0x01 +#define ICE_AQC_BIT_SRIOV_LAG 0x02 u8 major_ver; u8 minor_ver; @@ -232,6 +235,8 @@ struct ice_aqc_set_port_params { #define ICE_AQC_SET_P_PARAMS_DOUBLE_VLAN_ENA BIT(2) __le16 bad_frame_vsi; __le16 swid; +#define ICE_AQC_PORT_SWID_VALID BIT(15) +#define ICE_AQC_PORT_SWID_M 0xFF u8 reserved[10]; }; @@ -241,10 +246,12 @@ struct ice_aqc_set_port_params { * Allocate Resources command (indirect 0x0208) * Free Resources command (indirect 0x0209) * Get Allocated Resource Descriptors Command (indirect 0x020A) + * Share Resource command (indirect 0x020B) */ #define ICE_AQC_RES_TYPE_VSI_LIST_REP 0x03 #define ICE_AQC_RES_TYPE_VSI_LIST_PRUNE 0x04 #define ICE_AQC_RES_TYPE_RECIPE 0x05 +#define ICE_AQC_RES_TYPE_SWID 0x07 #define ICE_AQC_RES_TYPE_FDIR_COUNTER_BLOCK 0x21 #define ICE_AQC_RES_TYPE_FDIR_GUARANTEED_ENTRIES 0x22 #define ICE_AQC_RES_TYPE_FDIR_SHARED_ENTRIES 0x23 @@ -264,6 +271,7 @@ struct ice_aqc_set_port_params { /* Allocate Resources command (indirect 0x0208) * Free Resources command (indirect 0x0209) + * Share Resource command (indirect 0x020B) */ struct ice_aqc_alloc_free_res_cmd { __le16 num_entries; /* Number of Resource entries */ @@ -818,7 +826,11 @@ struct ice_aqc_txsched_move_grp_info_hdr { __le32 src_parent_teid; __le32 dest_parent_teid; __le16 num_elems; - __le16 reserved; + u8 mode; +#define ICE_AQC_MOVE_ELEM_MODE_SAME_PF 0x0 +#define ICE_AQC_MOVE_ELEM_MODE_GIVE_OWN 0x1 +#define ICE_AQC_MOVE_ELEM_MODE_KEEP_OWN 0x2 + u8 reserved; }; struct ice_aqc_move_elem { @@ -1087,7 +1099,15 @@ struct ice_aqc_get_phy_caps { #define ICE_PHY_TYPE_HIGH_100G_CAUI2 BIT_ULL(2) #define ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC BIT_ULL(3) #define ICE_PHY_TYPE_HIGH_100G_AUI2 BIT_ULL(4) -#define ICE_PHY_TYPE_HIGH_MAX_INDEX 4 +#define ICE_PHY_TYPE_HIGH_200G_CR4_PAM4 BIT_ULL(5) +#define ICE_PHY_TYPE_HIGH_200G_SR4 BIT_ULL(6) +#define ICE_PHY_TYPE_HIGH_200G_FR4 BIT_ULL(7) +#define ICE_PHY_TYPE_HIGH_200G_LR4 BIT_ULL(8) +#define ICE_PHY_TYPE_HIGH_200G_DR4 BIT_ULL(9) +#define ICE_PHY_TYPE_HIGH_200G_KR4_PAM4 BIT_ULL(10) +#define ICE_PHY_TYPE_HIGH_200G_AUI4_AOC_ACC BIT_ULL(11) +#define ICE_PHY_TYPE_HIGH_200G_AUI4 BIT_ULL(12) +#define ICE_PHY_TYPE_HIGH_MAX_INDEX 12 struct ice_aqc_get_phy_caps_data { __le64 phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */ @@ -1307,11 +1327,41 @@ struct ice_aqc_get_link_status_data { #define ICE_AQ_LINK_SPEED_40GB BIT(8) #define ICE_AQ_LINK_SPEED_50GB BIT(9) #define ICE_AQ_LINK_SPEED_100GB BIT(10) +#define ICE_AQ_LINK_SPEED_200GB BIT(11) #define ICE_AQ_LINK_SPEED_UNKNOWN BIT(15) - __le32 reserved3; /* Aligns next field to 8-byte boundary */ - __le64 phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */ - __le64 phy_type_high; /* Use values from ICE_PHY_TYPE_HIGH_* */ -}; + /* Aligns next field to 8-byte boundary */ + __le16 reserved3; + u8 ext_fec_status; + /* RS 272 FEC enabled */ +#define ICE_AQ_LINK_RS_272_FEC_EN BIT(0) + u8 reserved4; + /* Use values from ICE_PHY_TYPE_LOW_* */ + __le64 phy_type_low; + /* Use values from ICE_PHY_TYPE_HIGH_* */ + __le64 phy_type_high; +#define ICE_AQC_LS_DATA_SIZE_V1 \ + offsetofend(struct ice_aqc_get_link_status_data, phy_type_high) + /* Get link status v2 link partner data */ + __le64 lp_phy_type_low; + __le64 lp_phy_type_high; + u8 lp_fec_adv; +#define ICE_AQ_LINK_LP_10G_KR_FEC_CAP BIT(0) +#define ICE_AQ_LINK_LP_25G_KR_FEC_CAP BIT(1) +#define ICE_AQ_LINK_LP_RS_528_FEC_CAP BIT(2) +#define ICE_AQ_LINK_LP_50G_KR_272_FEC_CAP BIT(3) +#define ICE_AQ_LINK_LP_100G_KR_272_FEC_CAP BIT(4) +#define ICE_AQ_LINK_LP_200G_KR_272_FEC_CAP BIT(5) + u8 lp_fec_req; +#define ICE_AQ_LINK_LP_10G_KR_FEC_REQ BIT(0) +#define ICE_AQ_LINK_LP_25G_KR_FEC_REQ BIT(1) +#define ICE_AQ_LINK_LP_RS_528_FEC_REQ BIT(2) +#define ICE_AQ_LINK_LP_KR_272_FEC_REQ BIT(3) + u8 lp_flowcontrol; +#define ICE_AQ_LINK_LP_PAUSE_ADV BIT(0) +#define ICE_AQ_LINK_LP_ASM_DIR_ADV BIT(1) +#define ICE_AQC_LS_DATA_SIZE_V2 \ + offsetofend(struct ice_aqc_get_link_status_data, lp_flowcontrol) +} __packed; /* Set event mask command (direct 0x0613) */ struct ice_aqc_set_event_mask { @@ -1339,6 +1389,30 @@ struct ice_aqc_set_mac_lb { u8 reserved[15]; }; +/* Set PHY recovered clock output (direct 0x0630) */ +struct ice_aqc_set_phy_rec_clk_out { + u8 phy_output; + u8 port_num; +#define ICE_AQC_SET_PHY_REC_CLK_OUT_CURR_PORT 0xFF + u8 flags; +#define ICE_AQC_SET_PHY_REC_CLK_OUT_OUT_EN BIT(0) + u8 rsvd; + __le32 freq; + u8 rsvd2[6]; + __le16 node_handle; +}; + +/* Get PHY recovered clock output (direct 0x0631) */ +struct ice_aqc_get_phy_rec_clk_out { + u8 phy_output; + u8 port_num; +#define ICE_AQC_GET_PHY_REC_CLK_OUT_CURR_PORT 0xFF + u8 flags; +#define ICE_AQC_GET_PHY_REC_CLK_OUT_OUT_EN BIT(0) + u8 rsvd[11]; + __le16 node_handle; +}; + struct ice_aqc_link_topo_params { u8 lport_num; u8 lport_num_valid; @@ -1355,6 +1429,9 @@ struct ice_aqc_link_topo_params { #define ICE_AQC_LINK_TOPO_NODE_TYPE_CAGE 6 #define ICE_AQC_LINK_TOPO_NODE_TYPE_MEZZ 7 #define ICE_AQC_LINK_TOPO_NODE_TYPE_ID_EEPROM 8 +#define ICE_AQC_LINK_TOPO_NODE_TYPE_CLK_CTRL 9 +#define ICE_AQC_LINK_TOPO_NODE_TYPE_CLK_MUX 10 +#define ICE_AQC_LINK_TOPO_NODE_TYPE_GPS 11 #define ICE_AQC_LINK_TOPO_NODE_CTX_S 4 #define ICE_AQC_LINK_TOPO_NODE_CTX_M \ (0xF << ICE_AQC_LINK_TOPO_NODE_CTX_S) @@ -1391,7 +1468,13 @@ struct ice_aqc_link_topo_addr { struct ice_aqc_get_link_topo { struct ice_aqc_link_topo_addr addr; u8 node_part_num; -#define ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575 0x21 +#define ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575 0x21 +#define ICE_AQC_GET_LINK_TOPO_NODE_NR_ZL30632_80032 0x24 +#define ICE_AQC_GET_LINK_TOPO_NODE_NR_SI5383_5384 0x25 +#define ICE_AQC_GET_LINK_TOPO_NODE_NR_E822_PHY 0x30 +#define ICE_AQC_GET_LINK_TOPO_NODE_NR_C827 0x31 +#define ICE_AQC_GET_LINK_TOPO_NODE_NR_GEN_CLK_MUX 0x47 +#define ICE_AQC_GET_LINK_TOPO_NODE_NR_GEN_GPS 0x48 u8 rsvd[9]; }; @@ -1781,11 +1864,10 @@ struct ice_aqc_lldp_filter_ctrl { u8 reserved2[12]; }; +#define ICE_AQC_RSS_VSI_VALID BIT(15) + /* Get/Set RSS key (indirect 0x0B04/0x0B02) */ struct ice_aqc_get_set_rss_key { -#define ICE_AQC_GSET_RSS_KEY_VSI_VALID BIT(15) -#define ICE_AQC_GSET_RSS_KEY_VSI_ID_S 0 -#define ICE_AQC_GSET_RSS_KEY_VSI_ID_M (0x3FF << ICE_AQC_GSET_RSS_KEY_VSI_ID_S) __le16 vsi_id; u8 reserved[6]; __le32 addr_high; @@ -1803,35 +1885,33 @@ struct ice_aqc_get_set_rss_keys { u8 extended_hash_key[ICE_AQC_GET_SET_RSS_KEY_DATA_HASH_KEY_SIZE]; }; -/* Get/Set RSS LUT (indirect 0x0B05/0x0B03) */ -struct ice_aqc_get_set_rss_lut { -#define ICE_AQC_GSET_RSS_LUT_VSI_VALID BIT(15) -#define ICE_AQC_GSET_RSS_LUT_VSI_ID_S 0 -#define ICE_AQC_GSET_RSS_LUT_VSI_ID_M (0x3FF << ICE_AQC_GSET_RSS_LUT_VSI_ID_S) - __le16 vsi_id; -#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_S 0 -#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_M \ - (0x3 << ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_S) - -#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI 0 -#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF 1 -#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_GLOBAL 2 +enum ice_lut_type { + ICE_LUT_VSI = 0, + ICE_LUT_PF = 1, + ICE_LUT_GLOBAL = 2, +}; -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S 2 -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_M \ - (0x3 << ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S) +enum ice_lut_size { + ICE_LUT_VSI_SIZE = 64, + ICE_LUT_GLOBAL_SIZE = 512, + ICE_LUT_PF_SIZE = 2048, +}; -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_128 128 -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_128_FLAG 0 -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_512 512 -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_512_FLAG 1 -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K 2048 -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K_FLAG 2 +/* enum ice_aqc_lut_flags combines constants used to fill + * &ice_aqc_get_set_rss_lut ::flags, which is an amalgamation of global LUT ID, + * LUT size and LUT type, last of which does not need neither shift nor mask. + */ +enum ice_aqc_lut_flags { + ICE_AQC_LUT_SIZE_SMALL = 0, /* size = 64 or 128 */ + ICE_AQC_LUT_SIZE_512 = BIT(2), + ICE_AQC_LUT_SIZE_2K = BIT(3), -#define ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_S 4 -#define ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_M \ - (0xF << ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_S) + ICE_AQC_LUT_GLOBAL_IDX = GENMASK(7, 4), +}; +/* Get/Set RSS LUT (indirect 0x0B05/0x0B03) */ +struct ice_aqc_get_set_rss_lut { + __le16 vsi_id; __le16 flags; __le32 reserved; __le32 addr_high; @@ -1923,6 +2003,42 @@ struct ice_aqc_dis_txq_item { __le16 q_id[]; } __packed; +/* Move/Reconfigure Tx queue (indirect 0x0C32) */ +struct ice_aqc_cfg_txqs { + u8 cmd_type; +#define ICE_AQC_Q_CFG_MOVE_NODE 0x1 +#define ICE_AQC_Q_CFG_TC_CHNG 0x2 +#define ICE_AQC_Q_CFG_MOVE_TC_CHNG 0x3 +#define ICE_AQC_Q_CFG_SUBSEQ_CALL BIT(2) +#define ICE_AQC_Q_CFG_FLUSH BIT(3) + u8 num_qs; + u8 port_num_chng; +#define ICE_AQC_Q_CFG_SRC_PRT_M 0x7 +#define ICE_AQC_Q_CFG_DST_PRT_S 3 +#define ICE_AQC_Q_CFG_DST_PRT_M (0x7 << ICE_AQC_Q_CFG_DST_PRT_S) + u8 time_out; +#define ICE_AQC_Q_CFG_TIMEOUT_S 2 +#define ICE_AQC_Q_CFG_TIMEOUT_M (0x1F << ICE_AQC_Q_CFG_TIMEOUT_S) + __le32 blocked_cgds; + __le32 addr_high; + __le32 addr_low; +}; + +/* Per Q struct for Move/Reconfigure Tx LAN Queues (indirect 0x0C32) */ +struct ice_aqc_cfg_txq_perq { + __le16 q_handle; + u8 tc; + u8 rsvd; + __le32 q_teid; +}; + +/* The buffer for Move/Reconfigure Tx LAN Queues (indirect 0x0C32) */ +struct ice_aqc_cfg_txqs_buf { + __le32 src_parent_teid; + __le32 dst_parent_teid; + struct ice_aqc_cfg_txq_perq queue_info[]; +}; + /* Add Tx RDMA Queue Set (indirect 0x0C33) */ struct ice_aqc_add_rdma_qset { u8 num_qset_grps; @@ -2079,6 +2195,193 @@ struct ice_aqc_get_pkg_info_resp { struct ice_aqc_get_pkg_info pkg_info[]; }; +/* Get CGU abilities command response data structure (indirect 0x0C61) */ +struct ice_aqc_get_cgu_abilities { + u8 num_inputs; + u8 num_outputs; + u8 pps_dpll_idx; + u8 eec_dpll_idx; + __le32 max_in_freq; + __le32 max_in_phase_adj; + __le32 max_out_freq; + __le32 max_out_phase_adj; + u8 cgu_part_num; + u8 rsvd[3]; +}; + +/* Set CGU input config (direct 0x0C62) */ +struct ice_aqc_set_cgu_input_config { + u8 input_idx; + u8 flags1; +#define ICE_AQC_SET_CGU_IN_CFG_FLG1_UPDATE_FREQ BIT(6) +#define ICE_AQC_SET_CGU_IN_CFG_FLG1_UPDATE_DELAY BIT(7) + u8 flags2; +#define ICE_AQC_SET_CGU_IN_CFG_FLG2_INPUT_EN BIT(5) +#define ICE_AQC_SET_CGU_IN_CFG_FLG2_ESYNC_EN BIT(6) + u8 rsvd; + __le32 freq; + __le32 phase_delay; + u8 rsvd2[2]; + __le16 node_handle; +}; + +/* Get CGU input config response descriptor structure (direct 0x0C63) */ +struct ice_aqc_get_cgu_input_config { + u8 input_idx; + u8 status; +#define ICE_AQC_GET_CGU_IN_CFG_STATUS_LOS BIT(0) +#define ICE_AQC_GET_CGU_IN_CFG_STATUS_SCM_FAIL BIT(1) +#define ICE_AQC_GET_CGU_IN_CFG_STATUS_CFM_FAIL BIT(2) +#define ICE_AQC_GET_CGU_IN_CFG_STATUS_GST_FAIL BIT(3) +#define ICE_AQC_GET_CGU_IN_CFG_STATUS_PFM_FAIL BIT(4) +#define ICE_AQC_GET_CGU_IN_CFG_STATUS_ESYNC_FAIL BIT(6) +#define ICE_AQC_GET_CGU_IN_CFG_STATUS_ESYNC_CAP BIT(7) + u8 type; +#define ICE_AQC_GET_CGU_IN_CFG_TYPE_READ_ONLY BIT(0) +#define ICE_AQC_GET_CGU_IN_CFG_TYPE_GPS BIT(4) +#define ICE_AQC_GET_CGU_IN_CFG_TYPE_EXTERNAL BIT(5) +#define ICE_AQC_GET_CGU_IN_CFG_TYPE_PHY BIT(6) + u8 flags1; +#define ICE_AQC_GET_CGU_IN_CFG_FLG1_PHASE_DELAY_SUPP BIT(0) +#define ICE_AQC_GET_CGU_IN_CFG_FLG1_1PPS_SUPP BIT(2) +#define ICE_AQC_GET_CGU_IN_CFG_FLG1_10MHZ_SUPP BIT(3) +#define ICE_AQC_GET_CGU_IN_CFG_FLG1_ANYFREQ BIT(7) + __le32 freq; + __le32 phase_delay; + u8 flags2; +#define ICE_AQC_GET_CGU_IN_CFG_FLG2_INPUT_EN BIT(5) +#define ICE_AQC_GET_CGU_IN_CFG_FLG2_ESYNC_EN BIT(6) + u8 rsvd[1]; + __le16 node_handle; +}; + +/* Set CGU output config (direct 0x0C64) */ +struct ice_aqc_set_cgu_output_config { + u8 output_idx; + u8 flags; +#define ICE_AQC_SET_CGU_OUT_CFG_OUT_EN BIT(0) +#define ICE_AQC_SET_CGU_OUT_CFG_ESYNC_EN BIT(1) +#define ICE_AQC_SET_CGU_OUT_CFG_UPDATE_FREQ BIT(2) +#define ICE_AQC_SET_CGU_OUT_CFG_UPDATE_PHASE BIT(3) +#define ICE_AQC_SET_CGU_OUT_CFG_UPDATE_SRC_SEL BIT(4) + u8 src_sel; +#define ICE_AQC_SET_CGU_OUT_CFG_DPLL_SRC_SEL ICE_M(0x1F, 0) + u8 rsvd; + __le32 freq; + __le32 phase_delay; + u8 rsvd2[2]; + __le16 node_handle; +}; + +/* Get CGU output config (direct 0x0C65) */ +struct ice_aqc_get_cgu_output_config { + u8 output_idx; + u8 flags; +#define ICE_AQC_GET_CGU_OUT_CFG_OUT_EN BIT(0) +#define ICE_AQC_GET_CGU_OUT_CFG_ESYNC_EN BIT(1) +#define ICE_AQC_GET_CGU_OUT_CFG_ESYNC_ABILITY BIT(2) + u8 src_sel; +#define ICE_AQC_GET_CGU_OUT_CFG_DPLL_SRC_SEL_SHIFT 0 +#define ICE_AQC_GET_CGU_OUT_CFG_DPLL_SRC_SEL \ + ICE_M(0x1F, ICE_AQC_GET_CGU_OUT_CFG_DPLL_SRC_SEL_SHIFT) +#define ICE_AQC_GET_CGU_OUT_CFG_DPLL_MODE_SHIFT 5 +#define ICE_AQC_GET_CGU_OUT_CFG_DPLL_MODE \ + ICE_M(0x7, ICE_AQC_GET_CGU_OUT_CFG_DPLL_MODE_SHIFT) + u8 rsvd; + __le32 freq; + __le32 src_freq; + u8 rsvd2[2]; + __le16 node_handle; +}; + +/* Get CGU DPLL status (direct 0x0C66) */ +struct ice_aqc_get_cgu_dpll_status { + u8 dpll_num; + u8 ref_state; +#define ICE_AQC_GET_CGU_DPLL_STATUS_REF_SW_LOS BIT(0) +#define ICE_AQC_GET_CGU_DPLL_STATUS_REF_SW_SCM BIT(1) +#define ICE_AQC_GET_CGU_DPLL_STATUS_REF_SW_CFM BIT(2) +#define ICE_AQC_GET_CGU_DPLL_STATUS_REF_SW_GST BIT(3) +#define ICE_AQC_GET_CGU_DPLL_STATUS_REF_SW_PFM BIT(4) +#define ICE_AQC_GET_CGU_DPLL_STATUS_FAST_LOCK_EN BIT(5) +#define ICE_AQC_GET_CGU_DPLL_STATUS_REF_SW_ESYNC BIT(6) + u8 dpll_state; +#define ICE_AQC_GET_CGU_DPLL_STATUS_STATE_LOCK BIT(0) +#define ICE_AQC_GET_CGU_DPLL_STATUS_STATE_HO BIT(1) +#define ICE_AQC_GET_CGU_DPLL_STATUS_STATE_HO_READY BIT(2) +#define ICE_AQC_GET_CGU_DPLL_STATUS_STATE_FLHIT BIT(5) +#define ICE_AQC_GET_CGU_DPLL_STATUS_STATE_PSLHIT BIT(7) + u8 config; +#define ICE_AQC_GET_CGU_DPLL_CONFIG_CLK_REF_SEL ICE_M(0x1F, 0) +#define ICE_AQC_GET_CGU_DPLL_CONFIG_MODE_SHIFT 5 +#define ICE_AQC_GET_CGU_DPLL_CONFIG_MODE \ + ICE_M(0x7, ICE_AQC_GET_CGU_DPLL_CONFIG_MODE_SHIFT) +#define ICE_AQC_GET_CGU_DPLL_CONFIG_MODE_FREERUN 0 +#define ICE_AQC_GET_CGU_DPLL_CONFIG_MODE_AUTOMATIC \ + ICE_M(0x3, ICE_AQC_GET_CGU_DPLL_CONFIG_MODE_SHIFT) + __le32 phase_offset_h; + __le32 phase_offset_l; + u8 eec_mode; +#define ICE_AQC_GET_CGU_DPLL_STATUS_EEC_MODE_1 0xA +#define ICE_AQC_GET_CGU_DPLL_STATUS_EEC_MODE_2 0xB +#define ICE_AQC_GET_CGU_DPLL_STATUS_EEC_MODE_UNKNOWN 0xF + u8 rsvd[1]; + __le16 node_handle; +}; + +/* Set CGU DPLL config (direct 0x0C67) */ +struct ice_aqc_set_cgu_dpll_config { + u8 dpll_num; + u8 ref_state; +#define ICE_AQC_SET_CGU_DPLL_CONFIG_REF_SW_LOS BIT(0) +#define ICE_AQC_SET_CGU_DPLL_CONFIG_REF_SW_SCM BIT(1) +#define ICE_AQC_SET_CGU_DPLL_CONFIG_REF_SW_CFM BIT(2) +#define ICE_AQC_SET_CGU_DPLL_CONFIG_REF_SW_GST BIT(3) +#define ICE_AQC_SET_CGU_DPLL_CONFIG_REF_SW_PFM BIT(4) +#define ICE_AQC_SET_CGU_DPLL_CONFIG_REF_FLOCK_EN BIT(5) +#define ICE_AQC_SET_CGU_DPLL_CONFIG_REF_SW_ESYNC BIT(6) + u8 rsvd; + u8 config; +#define ICE_AQC_SET_CGU_DPLL_CONFIG_CLK_REF_SEL ICE_M(0x1F, 0) +#define ICE_AQC_SET_CGU_DPLL_CONFIG_MODE_SHIFT 5 +#define ICE_AQC_SET_CGU_DPLL_CONFIG_MODE \ + ICE_M(0x7, ICE_AQC_SET_CGU_DPLL_CONFIG_MODE_SHIFT) +#define ICE_AQC_SET_CGU_DPLL_CONFIG_MODE_FREERUN 0 +#define ICE_AQC_SET_CGU_DPLL_CONFIG_MODE_AUTOMATIC \ + ICE_M(0x3, ICE_AQC_SET_CGU_DPLL_CONFIG_MODE_SHIFT) + u8 rsvd2[8]; + u8 eec_mode; + u8 rsvd3[1]; + __le16 node_handle; +}; + +/* Set CGU reference priority (direct 0x0C68) */ +struct ice_aqc_set_cgu_ref_prio { + u8 dpll_num; + u8 ref_idx; + u8 ref_priority; + u8 rsvd[11]; + __le16 node_handle; +}; + +/* Get CGU reference priority (direct 0x0C69) */ +struct ice_aqc_get_cgu_ref_prio { + u8 dpll_num; + u8 ref_idx; + u8 ref_priority; /* Valid only in response */ + u8 rsvd[13]; +}; + +/* Get CGU info (direct 0x0C6A) */ +struct ice_aqc_get_cgu_info { + __le32 cgu_id; + __le32 cgu_cfg_ver; + __le32 cgu_fw_ver; + u8 node_part_num; + u8 dev_rev; + __le16 node_handle; +}; + /* Driver Shared Parameters (direct, 0x0C90) */ struct ice_aqc_driver_shared_params { u8 set_or_get_op; @@ -2093,16 +2396,6 @@ struct ice_aqc_driver_shared_params { __le32 addr_low; }; -enum ice_aqc_driver_params { - /* OS clock index for PTP timer Domain 0 */ - ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR0 = 0, - /* OS clock index for PTP timer Domain 1 */ - ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR1, - - /* Add new parameters above */ - ICE_AQC_DRIVER_PARAM_MAX = 16, -}; - /* Lan Queue Overflow Event (direct, 0x1001) */ struct ice_aqc_event_lan_overflow { __le32 prtdcb_ruptq; @@ -2148,6 +2441,8 @@ struct ice_aq_desc { struct ice_aqc_get_phy_caps get_phy; struct ice_aqc_set_phy_cfg set_phy; struct ice_aqc_restart_an restart_an; + struct ice_aqc_set_phy_rec_clk_out set_phy_rec_clk_out; + struct ice_aqc_get_phy_rec_clk_out get_phy_rec_clk_out; struct ice_aqc_gpio read_write_gpio; struct ice_aqc_sff_eeprom read_write_sff_param; struct ice_aqc_set_port_id_led set_port_id_led; @@ -2181,12 +2476,22 @@ struct ice_aq_desc { struct ice_aqc_neigh_dev_req neigh_dev; struct ice_aqc_add_txqs add_txqs; struct ice_aqc_dis_txqs dis_txqs; + struct ice_aqc_cfg_txqs cfg_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; struct ice_aqc_get_clear_fw_log get_clear_fw_log; struct ice_aqc_download_pkg download_pkg; + struct ice_aqc_set_cgu_input_config set_cgu_input_config; + struct ice_aqc_get_cgu_input_config get_cgu_input_config; + struct ice_aqc_set_cgu_output_config set_cgu_output_config; + struct ice_aqc_get_cgu_output_config get_cgu_output_config; + struct ice_aqc_get_cgu_dpll_status get_cgu_dpll_status; + struct ice_aqc_set_cgu_dpll_config set_cgu_dpll_config; + struct ice_aqc_set_cgu_ref_prio set_cgu_ref_prio; + struct ice_aqc_get_cgu_ref_prio get_cgu_ref_prio; + struct ice_aqc_get_cgu_info get_cgu_info; struct ice_aqc_driver_shared_params drv_shared_params; struct ice_aqc_set_mac_lb set_mac_lb; struct ice_aqc_alloc_free_res_cmd sw_res_ctrl; @@ -2263,6 +2568,7 @@ enum ice_adminq_opc { /* Alloc/Free/Get Resources */ ice_aqc_opc_alloc_res = 0x0208, ice_aqc_opc_free_res = 0x0209, + ice_aqc_opc_share_res = 0x020B, ice_aqc_opc_set_vlan_mode_parameters = 0x020C, ice_aqc_opc_get_vlan_mode_parameters = 0x020D, @@ -2310,6 +2616,8 @@ enum ice_adminq_opc { ice_aqc_opc_get_link_status = 0x0607, ice_aqc_opc_set_event_mask = 0x0613, ice_aqc_opc_set_mac_lb = 0x0620, + ice_aqc_opc_set_phy_rec_clk_out = 0x0630, + ice_aqc_opc_get_phy_rec_clk_out = 0x0631, ice_aqc_opc_get_link_topo = 0x06E0, ice_aqc_opc_read_i2c = 0x06E2, ice_aqc_opc_write_i2c = 0x06E3, @@ -2356,6 +2664,7 @@ enum ice_adminq_opc { /* Tx queue handling commands/events */ ice_aqc_opc_add_txqs = 0x0C30, ice_aqc_opc_dis_txqs = 0x0C31, + ice_aqc_opc_cfg_txqs = 0x0C32, ice_aqc_opc_add_rdma_qset = 0x0C33, /* package commands */ @@ -2364,6 +2673,18 @@ enum ice_adminq_opc { ice_aqc_opc_update_pkg = 0x0C42, ice_aqc_opc_get_pkg_info_list = 0x0C43, + /* 1588/SyncE commands/events */ + ice_aqc_opc_get_cgu_abilities = 0x0C61, + ice_aqc_opc_set_cgu_input_config = 0x0C62, + ice_aqc_opc_get_cgu_input_config = 0x0C63, + ice_aqc_opc_set_cgu_output_config = 0x0C64, + ice_aqc_opc_get_cgu_output_config = 0x0C65, + ice_aqc_opc_get_cgu_dpll_status = 0x0C66, + ice_aqc_opc_set_cgu_dpll_config = 0x0C67, + ice_aqc_opc_set_cgu_ref_prio = 0x0C68, + ice_aqc_opc_get_cgu_ref_prio = 0x0C69, + ice_aqc_opc_get_cgu_info = 0x0C6A, + ice_aqc_opc_driver_shared_params = 0x0C90, /* Standalone Commands/Events */ diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 074bf9403cd1..7fa43827a3f0 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -408,7 +408,6 @@ static unsigned int ice_rx_offset(struct ice_rx_ring *rx_ring) */ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) { - int chain_len = ICE_MAX_CHAINED_RX_BUFS; struct ice_vsi *vsi = ring->vsi; u32 rxdid = ICE_RXDID_FLEX_NIC; struct ice_rlan_ctx rlan_ctx; @@ -473,17 +472,11 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) */ rlan_ctx.showiv = 0; - /* For AF_XDP ZC, we disallow packets to span on - * multiple buffers, thus letting us skip that - * handling in the fast-path. - */ - if (ring->xsk_pool) - chain_len = 1; /* Max packet size for this queue - must not be set to a larger value * than 5 x DBUF */ rlan_ctx.rxmax = min_t(u32, vsi->max_frame, - chain_len * ring->rx_buf_len); + ICE_MAX_CHAINED_RX_BUFS * ring->rx_buf_len); /* Rx queue threshold in units of 64 */ rlan_ctx.lrxqthresh = 1; diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index e16d4c83ed5f..9a6c25f98632 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1,12 +1,14 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (c) 2018, Intel Corporation. */ +/* Copyright (c) 2018-2023, Intel Corporation. */ #include "ice_common.h" #include "ice_sched.h" #include "ice_adminq_cmd.h" #include "ice_flow.h" +#include "ice_ptp_hw.h" #define ICE_PF_RESET_WAIT_COUNT 300 +#define ICE_MAX_NETLIST_SIZE 10 static const char * const ice_link_mode_str_low[] = { [0] = "100BASE_TX", @@ -152,6 +154,12 @@ static int ice_set_mac_type(struct ice_hw *hw) case ICE_DEV_ID_E823L_SFP: hw->mac_type = ICE_MAC_GENERIC; break; + case ICE_DEV_ID_E830_BACKPLANE: + case ICE_DEV_ID_E830_QSFP56: + case ICE_DEV_ID_E830_SFP: + case ICE_DEV_ID_E830_SFP_DD: + hw->mac_type = ICE_MAC_E830; + break; default: hw->mac_type = ICE_MAC_UNKNOWN; break; @@ -435,6 +443,80 @@ ice_aq_get_link_topo_handle(struct ice_port_info *pi, u8 node_type, } /** + * ice_aq_get_netlist_node + * @hw: pointer to the hw struct + * @cmd: get_link_topo AQ structure + * @node_part_number: output node part number if node found + * @node_handle: output node handle parameter if node found + * + * Get netlist node handle. + */ +int +ice_aq_get_netlist_node(struct ice_hw *hw, struct ice_aqc_get_link_topo *cmd, + u8 *node_part_number, u16 *node_handle) +{ + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo); + desc.params.get_link_topo = *cmd; + + if (ice_aq_send_cmd(hw, &desc, NULL, 0, NULL)) + return -EINTR; + + if (node_handle) + *node_handle = + le16_to_cpu(desc.params.get_link_topo.addr.handle); + if (node_part_number) + *node_part_number = desc.params.get_link_topo.node_part_num; + + return 0; +} + +/** + * ice_find_netlist_node + * @hw: pointer to the hw struct + * @node_type_ctx: type of netlist node to look for + * @node_part_number: node part number to look for + * @node_handle: output parameter if node found - optional + * + * Scan the netlist for a node handle of the given node type and part number. + * + * If node_handle is non-NULL it will be modified on function exit. It is only + * valid if the function returns zero, and should be ignored on any non-zero + * return value. + * + * Returns: 0 if the node is found, -ENOENT if no handle was found, and + * a negative error code on failure to access the AQ. + */ +static int ice_find_netlist_node(struct ice_hw *hw, u8 node_type_ctx, + u8 node_part_number, u16 *node_handle) +{ + u8 idx; + + for (idx = 0; idx < ICE_MAX_NETLIST_SIZE; idx++) { + struct ice_aqc_get_link_topo cmd = {}; + u8 rec_node_part_number; + int status; + + cmd.addr.topo_params.node_type_ctx = + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M, + node_type_ctx); + cmd.addr.topo_params.index = idx; + + status = ice_aq_get_netlist_node(hw, &cmd, + &rec_node_part_number, + node_handle); + if (status) + return status; + + if (rec_node_part_number == node_part_number) + return 0; + } + + return -ENOENT; +} + +/** * ice_is_media_cage_present * @pi: port information structure * @@ -570,6 +652,24 @@ static enum ice_media_type ice_get_media_type(struct ice_port_info *pi) } /** + * ice_get_link_status_datalen + * @hw: pointer to the HW struct + * + * Returns datalength for the Get Link Status AQ command, which is bigger for + * newer adapter families handled by ice driver. + */ +static u16 ice_get_link_status_datalen(struct ice_hw *hw) +{ + switch (hw->mac_type) { + case ICE_MAC_E830: + return ICE_AQC_LS_DATA_SIZE_V2; + case ICE_MAC_E810: + default: + return ICE_AQC_LS_DATA_SIZE_V1; + } +} + +/** * ice_aq_get_link_info * @pi: port information structure * @ena_lse: enable/disable LinkStatusEvent reporting @@ -607,8 +707,8 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse, resp->cmd_flags = cpu_to_le16(cmd_flags); resp->lport_num = pi->lport; - status = ice_aq_send_cmd(hw, &desc, &link_data, sizeof(link_data), cd); - + status = ice_aq_send_cmd(hw, &desc, &link_data, + ice_get_link_status_datalen(hw), cd); if (status) return status; @@ -683,8 +783,7 @@ static void ice_fill_tx_timer_and_fc_thresh(struct ice_hw *hw, struct ice_aqc_set_mac_cfg *cmd) { - u16 fc_thres_val, tx_timer_val; - u32 val; + u32 val, fc_thres_m; /* We read back the transmit timer and FC threshold value of * LFC. Thus, we will use index = @@ -693,19 +792,32 @@ ice_fill_tx_timer_and_fc_thresh(struct ice_hw *hw, * Also, because we are operating on transmit timer and FC * threshold of LFC, we don't turn on any bit in tx_tmr_priority */ -#define IDX_OF_LFC PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_MAX_INDEX - - /* Retrieve the transmit timer */ - val = rd32(hw, PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA(IDX_OF_LFC)); - tx_timer_val = val & - PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_HSEC_CTL_TX_PAUSE_QUANTA_M; - cmd->tx_tmr_value = cpu_to_le16(tx_timer_val); - - /* Retrieve the FC threshold */ - val = rd32(hw, PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER(IDX_OF_LFC)); - fc_thres_val = val & PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_M; - - cmd->fc_refresh_threshold = cpu_to_le16(fc_thres_val); +#define E800_IDX_OF_LFC E800_PRTMAC_HSEC_CTL_TX_PS_QNT_MAX +#define E800_REFRESH_TMR E800_PRTMAC_HSEC_CTL_TX_PS_RFSH_TMR + + if (hw->mac_type == ICE_MAC_E830) { + /* Retrieve the transmit timer */ + val = rd32(hw, E830_PRTMAC_CL01_PS_QNT); + cmd->tx_tmr_value = + le16_encode_bits(val, E830_PRTMAC_CL01_PS_QNT_CL0_M); + + /* Retrieve the fc threshold */ + val = rd32(hw, E830_PRTMAC_CL01_QNT_THR); + fc_thres_m = E830_PRTMAC_CL01_QNT_THR_CL0_M; + } else { + /* Retrieve the transmit timer */ + val = rd32(hw, + E800_PRTMAC_HSEC_CTL_TX_PS_QNT(E800_IDX_OF_LFC)); + cmd->tx_tmr_value = + le16_encode_bits(val, + E800_PRTMAC_HSEC_CTL_TX_PS_QNT_M); + + /* Retrieve the fc threshold */ + val = rd32(hw, + E800_REFRESH_TMR(E800_IDX_OF_LFC)); + fc_thres_m = E800_PRTMAC_HSEC_CTL_TX_PS_RFSH_TMR_M; + } + cmd->fc_refresh_threshold = le16_encode_bits(val, fc_thres_m); } /** @@ -1999,37 +2111,31 @@ void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res) /** * ice_aq_alloc_free_res - command to allocate/free resources * @hw: pointer to the HW struct - * @num_entries: number of resource entries in buffer * @buf: Indirect buffer to hold data parameters and response * @buf_size: size of buffer for indirect commands * @opc: pass in the command opcode - * @cd: pointer to command details structure or NULL * * Helper function to allocate/free resources using the admin queue commands */ -int -ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries, - struct ice_aqc_alloc_free_res_elem *buf, u16 buf_size, - enum ice_adminq_opc opc, struct ice_sq_cd *cd) +int ice_aq_alloc_free_res(struct ice_hw *hw, + struct ice_aqc_alloc_free_res_elem *buf, u16 buf_size, + enum ice_adminq_opc opc) { struct ice_aqc_alloc_free_res_cmd *cmd; struct ice_aq_desc desc; cmd = &desc.params.sw_res_ctrl; - if (!buf) - return -EINVAL; - - if (buf_size < flex_array_size(buf, elem, num_entries)) + if (!buf || buf_size < flex_array_size(buf, elem, 1)) return -EINVAL; ice_fill_dflt_direct_cmd_desc(&desc, opc); desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); - cmd->num_entries = cpu_to_le16(num_entries); + cmd->num_entries = cpu_to_le16(1); - return ice_aq_send_cmd(hw, &desc, buf, buf_size, cd); + return ice_aq_send_cmd(hw, &desc, buf, buf_size, NULL); } /** @@ -2059,8 +2165,7 @@ ice_alloc_hw_res(struct ice_hw *hw, u16 type, u16 num, bool btm, u16 *res) if (btm) buf->res_type |= cpu_to_le16(ICE_AQC_RES_TYPE_FLAG_SCAN_BOTTOM); - status = ice_aq_alloc_free_res(hw, 1, buf, buf_len, - ice_aqc_opc_alloc_res, NULL); + status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_alloc_res); if (status) goto ice_alloc_res_exit; @@ -2094,8 +2199,7 @@ int ice_free_hw_res(struct ice_hw *hw, u16 type, u16 num, u16 *res) buf->res_type = cpu_to_le16(type); memcpy(buf->elem, res, sizeof(*buf->elem) * num); - status = ice_aq_alloc_free_res(hw, num, buf, buf_len, - ice_aqc_opc_free_res, NULL); + status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_free_res); if (status) ice_debug(hw, ICE_DBG_SW, "CQ CMD Buffer:\n"); @@ -2241,6 +2345,14 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps, "%s: reset_restrict_support = %d\n", prefix, caps->reset_restrict_support); break; + case ICE_AQC_CAPS_FW_LAG_SUPPORT: + caps->roce_lag = !!(number & ICE_AQC_BIT_ROCEV2_LAG); + ice_debug(hw, ICE_DBG_INIT, "%s: roce_lag = %u\n", + prefix, caps->roce_lag); + caps->sriov_lag = !!(number & ICE_AQC_BIT_SRIOV_LAG); + ice_debug(hw, ICE_DBG_INIT, "%s: sriov_lag = %u\n", + prefix, caps->sriov_lag); + break; default: /* Not one of the recognized common capabilities */ found = false; @@ -2388,16 +2500,21 @@ ice_parse_1588_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p, static void ice_parse_fdir_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p) { - u32 reg_val, val; + u32 reg_val, gsize, bsize; reg_val = rd32(hw, GLQF_FD_SIZE); - val = (reg_val & GLQF_FD_SIZE_FD_GSIZE_M) >> - GLQF_FD_SIZE_FD_GSIZE_S; - func_p->fd_fltr_guar = - ice_get_num_per_func(hw, val); - val = (reg_val & GLQF_FD_SIZE_FD_BSIZE_M) >> - GLQF_FD_SIZE_FD_BSIZE_S; - func_p->fd_fltr_best_effort = val; + switch (hw->mac_type) { + case ICE_MAC_E830: + gsize = FIELD_GET(E830_GLQF_FD_SIZE_FD_GSIZE_M, reg_val); + bsize = FIELD_GET(E830_GLQF_FD_SIZE_FD_BSIZE_M, reg_val); + break; + case ICE_MAC_E810: + default: + gsize = FIELD_GET(E800_GLQF_FD_SIZE_FD_GSIZE_M, reg_val); + bsize = FIELD_GET(E800_GLQF_FD_SIZE_FD_BSIZE_M, reg_val); + } + func_p->fd_fltr_guar = ice_get_num_per_func(hw, gsize); + func_p->fd_fltr_best_effort = bsize; ice_debug(hw, ICE_DBG_INIT, "func caps: fd_fltr_guar = %d\n", func_p->fd_fltr_guar); @@ -2654,6 +2771,116 @@ ice_parse_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, } /** + * ice_is_pf_c827 - check if pf contains c827 phy + * @hw: pointer to the hw struct + */ +bool ice_is_pf_c827(struct ice_hw *hw) +{ + struct ice_aqc_get_link_topo cmd = {}; + u8 node_part_number; + u16 node_handle; + int status; + + if (hw->mac_type != ICE_MAC_E810) + return false; + + if (hw->device_id != ICE_DEV_ID_E810C_QSFP) + return true; + + cmd.addr.topo_params.node_type_ctx = + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M, ICE_AQC_LINK_TOPO_NODE_TYPE_PHY) | + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, ICE_AQC_LINK_TOPO_NODE_CTX_PORT); + cmd.addr.topo_params.index = 0; + + status = ice_aq_get_netlist_node(hw, &cmd, &node_part_number, + &node_handle); + + if (status || node_part_number != ICE_AQC_GET_LINK_TOPO_NODE_NR_C827) + return false; + + if (node_handle == E810C_QSFP_C827_0_HANDLE || node_handle == E810C_QSFP_C827_1_HANDLE) + return true; + + return false; +} + +/** + * ice_is_phy_rclk_in_netlist + * @hw: pointer to the hw struct + * + * Check if the PHY Recovered Clock device is present in the netlist + */ +bool ice_is_phy_rclk_in_netlist(struct ice_hw *hw) +{ + if (ice_find_netlist_node(hw, ICE_AQC_LINK_TOPO_NODE_TYPE_CLK_CTRL, + ICE_AQC_GET_LINK_TOPO_NODE_NR_C827, NULL) && + ice_find_netlist_node(hw, ICE_AQC_LINK_TOPO_NODE_TYPE_CLK_CTRL, + ICE_AQC_GET_LINK_TOPO_NODE_NR_E822_PHY, NULL)) + return false; + + return true; +} + +/** + * ice_is_clock_mux_in_netlist + * @hw: pointer to the hw struct + * + * Check if the Clock Multiplexer device is present in the netlist + */ +bool ice_is_clock_mux_in_netlist(struct ice_hw *hw) +{ + if (ice_find_netlist_node(hw, ICE_AQC_LINK_TOPO_NODE_TYPE_CLK_MUX, + ICE_AQC_GET_LINK_TOPO_NODE_NR_GEN_CLK_MUX, + NULL)) + return false; + + return true; +} + +/** + * ice_is_cgu_in_netlist - check for CGU presence + * @hw: pointer to the hw struct + * + * Check if the Clock Generation Unit (CGU) device is present in the netlist. + * Save the CGU part number in the hw structure for later use. + * Return: + * * true - cgu is present + * * false - cgu is not present + */ +bool ice_is_cgu_in_netlist(struct ice_hw *hw) +{ + if (!ice_find_netlist_node(hw, ICE_AQC_LINK_TOPO_NODE_TYPE_CLK_CTRL, + ICE_AQC_GET_LINK_TOPO_NODE_NR_ZL30632_80032, + NULL)) { + hw->cgu_part_number = ICE_AQC_GET_LINK_TOPO_NODE_NR_ZL30632_80032; + return true; + } else if (!ice_find_netlist_node(hw, + ICE_AQC_LINK_TOPO_NODE_TYPE_CLK_CTRL, + ICE_AQC_GET_LINK_TOPO_NODE_NR_SI5383_5384, + NULL)) { + hw->cgu_part_number = ICE_AQC_GET_LINK_TOPO_NODE_NR_SI5383_5384; + return true; + } + + return false; +} + +/** + * ice_is_gps_in_netlist + * @hw: pointer to the hw struct + * + * Check if the GPS generic device is present in the netlist + */ +bool ice_is_gps_in_netlist(struct ice_hw *hw) +{ + if (ice_find_netlist_node(hw, ICE_AQC_LINK_TOPO_NODE_TYPE_GPS, + ICE_AQC_GET_LINK_TOPO_NODE_NR_GEN_GPS, NULL)) + return false; + + return true; +} + +/** * ice_aq_list_caps - query function/device capabilities * @hw: pointer to the HW struct * @buf: a buffer to hold the capabilities @@ -3869,6 +4096,34 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr, return status; } +static enum ice_lut_size ice_lut_type_to_size(enum ice_lut_type type) +{ + switch (type) { + case ICE_LUT_VSI: + return ICE_LUT_VSI_SIZE; + case ICE_LUT_GLOBAL: + return ICE_LUT_GLOBAL_SIZE; + case ICE_LUT_PF: + return ICE_LUT_PF_SIZE; + } + WARN_ONCE(1, "incorrect type passed"); + return ICE_LUT_VSI_SIZE; +} + +static enum ice_aqc_lut_flags ice_lut_size_to_flag(enum ice_lut_size size) +{ + switch (size) { + case ICE_LUT_VSI_SIZE: + return ICE_AQC_LUT_SIZE_SMALL; + case ICE_LUT_GLOBAL_SIZE: + return ICE_AQC_LUT_SIZE_512; + case ICE_LUT_PF_SIZE: + return ICE_AQC_LUT_SIZE_2K; + } + WARN_ONCE(1, "incorrect size passed"); + return 0; +} + /** * __ice_aq_get_set_rss_lut * @hw: pointer to the hardware structure @@ -3878,95 +4133,44 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr, * Internal function to get (0x0B05) or set (0x0B03) RSS look up table */ static int -__ice_aq_get_set_rss_lut(struct ice_hw *hw, struct ice_aq_get_set_rss_lut_params *params, bool set) -{ - u16 flags = 0, vsi_id, lut_type, lut_size, glob_lut_idx, vsi_handle; - struct ice_aqc_get_set_rss_lut *cmd_resp; +__ice_aq_get_set_rss_lut(struct ice_hw *hw, + struct ice_aq_get_set_rss_lut_params *params, bool set) +{ + u16 opcode, vsi_id, vsi_handle = params->vsi_handle, glob_lut_idx = 0; + enum ice_lut_type lut_type = params->lut_type; + struct ice_aqc_get_set_rss_lut *desc_params; + enum ice_aqc_lut_flags flags; + enum ice_lut_size lut_size; struct ice_aq_desc desc; - int status; - u8 *lut; - - if (!params) - return -EINVAL; + u8 *lut = params->lut; - vsi_handle = params->vsi_handle; - lut = params->lut; - if (!ice_is_vsi_valid(hw, vsi_handle) || !lut) + if (!lut || !ice_is_vsi_valid(hw, vsi_handle)) return -EINVAL; - lut_size = params->lut_size; - lut_type = params->lut_type; - glob_lut_idx = params->global_lut_id; - vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); - - cmd_resp = &desc.params.get_set_rss_lut; + lut_size = ice_lut_type_to_size(lut_type); + if (lut_size > params->lut_size) + return -EINVAL; + else if (set && lut_size != params->lut_size) + return -EINVAL; - if (set) { - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_rss_lut); + opcode = set ? ice_aqc_opc_set_rss_lut : ice_aqc_opc_get_rss_lut; + ice_fill_dflt_direct_cmd_desc(&desc, opcode); + if (set) desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); - } else { - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_rss_lut); - } - cmd_resp->vsi_id = cpu_to_le16(((vsi_id << - ICE_AQC_GSET_RSS_LUT_VSI_ID_S) & - ICE_AQC_GSET_RSS_LUT_VSI_ID_M) | - ICE_AQC_GSET_RSS_LUT_VSI_VALID); - - switch (lut_type) { - case ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI: - case ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF: - case ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_GLOBAL: - flags |= ((lut_type << ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_S) & - ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_M); - break; - default: - status = -EINVAL; - goto ice_aq_get_set_rss_lut_exit; - } + desc_params = &desc.params.get_set_rss_lut; + vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); + desc_params->vsi_id = cpu_to_le16(vsi_id | ICE_AQC_RSS_VSI_VALID); - if (lut_type == ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_GLOBAL) { - flags |= ((glob_lut_idx << ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_S) & - ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_M); + if (lut_type == ICE_LUT_GLOBAL) + glob_lut_idx = FIELD_PREP(ICE_AQC_LUT_GLOBAL_IDX, + params->global_lut_id); - if (!set) - goto ice_aq_get_set_rss_lut_send; - } else if (lut_type == ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF) { - if (!set) - goto ice_aq_get_set_rss_lut_send; - } else { - goto ice_aq_get_set_rss_lut_send; - } + flags = lut_type | glob_lut_idx | ice_lut_size_to_flag(lut_size); + desc_params->flags = cpu_to_le16(flags); - /* LUT size is only valid for Global and PF table types */ - switch (lut_size) { - case ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_128: - break; - case ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_512: - flags |= (ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_512_FLAG << - ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S) & - ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_M; - break; - case ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K: - if (lut_type == ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF) { - flags |= (ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K_FLAG << - ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S) & - ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_M; - break; - } - fallthrough; - default: - status = -EINVAL; - goto ice_aq_get_set_rss_lut_exit; - } - -ice_aq_get_set_rss_lut_send: - cmd_resp->flags = cpu_to_le16(flags); - status = ice_aq_send_cmd(hw, &desc, lut, lut_size, NULL); - -ice_aq_get_set_rss_lut_exit: - return status; + return ice_aq_send_cmd(hw, &desc, lut, lut_size, NULL); } /** @@ -4008,12 +4212,10 @@ static int __ice_aq_get_set_rss_key(struct ice_hw *hw, u16 vsi_id, struct ice_aqc_get_set_rss_keys *key, bool set) { - struct ice_aqc_get_set_rss_key *cmd_resp; + struct ice_aqc_get_set_rss_key *desc_params; u16 key_size = sizeof(*key); struct ice_aq_desc desc; - cmd_resp = &desc.params.get_set_rss_key; - if (set) { ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_rss_key); desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); @@ -4021,10 +4223,8 @@ __ice_aq_get_set_rss_key(struct ice_hw *hw, u16 vsi_id, ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_rss_key); } - cmd_resp->vsi_id = cpu_to_le16(((vsi_id << - ICE_AQC_GSET_RSS_KEY_VSI_ID_S) & - ICE_AQC_GSET_RSS_KEY_VSI_ID_M) | - ICE_AQC_GSET_RSS_KEY_VSI_VALID); + desc_params = &desc.params.get_set_rss_key; + desc_params->vsi_id = cpu_to_le16(vsi_id | ICE_AQC_RSS_VSI_VALID); return ice_aq_send_cmd(hw, &desc, key, key_size, NULL); } @@ -4222,6 +4422,53 @@ do_aq: } /** + * ice_aq_cfg_lan_txq + * @hw: pointer to the hardware structure + * @buf: buffer for command + * @buf_size: size of buffer in bytes + * @num_qs: number of queues being configured + * @oldport: origination lport + * @newport: destination lport + * @cd: pointer to command details structure or NULL + * + * Move/Configure LAN Tx queue (0x0C32) + * + * There is a better AQ command to use for moving nodes, so only coding + * this one for configuring the node. + */ +int +ice_aq_cfg_lan_txq(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *buf, + u16 buf_size, u16 num_qs, u8 oldport, u8 newport, + struct ice_sq_cd *cd) +{ + struct ice_aqc_cfg_txqs *cmd; + struct ice_aq_desc desc; + int status; + + cmd = &desc.params.cfg_txqs; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_cfg_txqs); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + if (!buf) + return -EINVAL; + + cmd->cmd_type = ICE_AQC_Q_CFG_TC_CHNG; + cmd->num_qs = num_qs; + cmd->port_num_chng = (oldport & ICE_AQC_Q_CFG_SRC_PRT_M); + cmd->port_num_chng |= (newport << ICE_AQC_Q_CFG_DST_PRT_S) & + ICE_AQC_Q_CFG_DST_PRT_M; + cmd->time_out = (5 << ICE_AQC_Q_CFG_TIMEOUT_S) & + ICE_AQC_Q_CFG_TIMEOUT_M; + cmd->blocked_cgds = 0; + + status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd); + if (status) + ice_debug(hw, ICE_DBG_SCHED, "Failed to reconfigure nodes %d\n", + hw->adminq.sq_last_status); + return status; +} + +/** * ice_aq_add_rdma_qsets * @hw: pointer to the hardware structure * @num_qset_grps: Number of RDMA Qset groups @@ -4644,11 +4891,11 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_queues, enum ice_disq_rst_src rst_src, u16 vmvf_num, struct ice_sq_cd *cd) { - struct ice_aqc_dis_txq_item *qg_list; + DEFINE_FLEX(struct ice_aqc_dis_txq_item, qg_list, q_id, 1); + u16 i, buf_size = __struct_size(qg_list); struct ice_q_ctx *q_ctx; int status = -ENOENT; struct ice_hw *hw; - u16 i, buf_size; if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY) return -EIO; @@ -4666,11 +4913,6 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_queues, return -EIO; } - buf_size = struct_size(qg_list, q_id, 1); - qg_list = kzalloc(buf_size, GFP_KERNEL); - if (!qg_list) - return -ENOMEM; - mutex_lock(&pi->sched_lock); for (i = 0; i < num_queues; i++) { @@ -4700,9 +4942,9 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_queues, break; ice_free_sched_node(pi, node); q_ctx->q_handle = ICE_INVAL_Q_HANDLE; + q_ctx->q_teid = ICE_INVAL_TEID; } mutex_unlock(&pi->sched_lock); - kfree(qg_list); return status; } @@ -4871,10 +5113,10 @@ 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; + DEFINE_FLEX(struct ice_aqc_dis_txq_item, qg_list, q_id, 1); + u16 qg_size = __struct_size(qg_list); struct ice_hw *hw; int status = 0; - u16 qg_size; int i; if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY) @@ -4882,11 +5124,6 @@ ice_dis_vsi_rdma_qset(struct ice_port_info *pi, u16 count, u32 *qset_teid, 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++) { @@ -4911,7 +5148,395 @@ ice_dis_vsi_rdma_qset(struct ice_port_info *pi, u16 count, u32 *qset_teid, } mutex_unlock(&pi->sched_lock); - kfree(qg_list); + return status; +} + +/** + * ice_aq_get_cgu_abilities - get cgu abilities + * @hw: pointer to the HW struct + * @abilities: CGU abilities + * + * Get CGU abilities (0x0C61) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_get_cgu_abilities(struct ice_hw *hw, + struct ice_aqc_get_cgu_abilities *abilities) +{ + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_abilities); + return ice_aq_send_cmd(hw, &desc, abilities, sizeof(*abilities), NULL); +} + +/** + * ice_aq_set_input_pin_cfg - set input pin config + * @hw: pointer to the HW struct + * @input_idx: Input index + * @flags1: Input flags + * @flags2: Input flags + * @freq: Frequency in Hz + * @phase_delay: Delay in ps + * + * Set CGU input config (0x0C62) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_set_input_pin_cfg(struct ice_hw *hw, u8 input_idx, u8 flags1, u8 flags2, + u32 freq, s32 phase_delay) +{ + struct ice_aqc_set_cgu_input_config *cmd; + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_cgu_input_config); + cmd = &desc.params.set_cgu_input_config; + cmd->input_idx = input_idx; + cmd->flags1 = flags1; + cmd->flags2 = flags2; + cmd->freq = cpu_to_le32(freq); + cmd->phase_delay = cpu_to_le32(phase_delay); + + return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); +} + +/** + * ice_aq_get_input_pin_cfg - get input pin config + * @hw: pointer to the HW struct + * @input_idx: Input index + * @status: Pin status + * @type: Pin type + * @flags1: Input flags + * @flags2: Input flags + * @freq: Frequency in Hz + * @phase_delay: Delay in ps + * + * Get CGU input config (0x0C63) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_get_input_pin_cfg(struct ice_hw *hw, u8 input_idx, u8 *status, u8 *type, + u8 *flags1, u8 *flags2, u32 *freq, s32 *phase_delay) +{ + struct ice_aqc_get_cgu_input_config *cmd; + struct ice_aq_desc desc; + int ret; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_input_config); + cmd = &desc.params.get_cgu_input_config; + cmd->input_idx = input_idx; + + ret = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (!ret) { + if (status) + *status = cmd->status; + if (type) + *type = cmd->type; + if (flags1) + *flags1 = cmd->flags1; + if (flags2) + *flags2 = cmd->flags2; + if (freq) + *freq = le32_to_cpu(cmd->freq); + if (phase_delay) + *phase_delay = le32_to_cpu(cmd->phase_delay); + } + + return ret; +} + +/** + * ice_aq_set_output_pin_cfg - set output pin config + * @hw: pointer to the HW struct + * @output_idx: Output index + * @flags: Output flags + * @src_sel: Index of DPLL block + * @freq: Output frequency + * @phase_delay: Output phase compensation + * + * Set CGU output config (0x0C64) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_set_output_pin_cfg(struct ice_hw *hw, u8 output_idx, u8 flags, + u8 src_sel, u32 freq, s32 phase_delay) +{ + struct ice_aqc_set_cgu_output_config *cmd; + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_cgu_output_config); + cmd = &desc.params.set_cgu_output_config; + cmd->output_idx = output_idx; + cmd->flags = flags; + cmd->src_sel = src_sel; + cmd->freq = cpu_to_le32(freq); + cmd->phase_delay = cpu_to_le32(phase_delay); + + return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); +} + +/** + * ice_aq_get_output_pin_cfg - get output pin config + * @hw: pointer to the HW struct + * @output_idx: Output index + * @flags: Output flags + * @src_sel: Internal DPLL source + * @freq: Output frequency + * @src_freq: Source frequency + * + * Get CGU output config (0x0C65) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_get_output_pin_cfg(struct ice_hw *hw, u8 output_idx, u8 *flags, + u8 *src_sel, u32 *freq, u32 *src_freq) +{ + struct ice_aqc_get_cgu_output_config *cmd; + struct ice_aq_desc desc; + int ret; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_output_config); + cmd = &desc.params.get_cgu_output_config; + cmd->output_idx = output_idx; + + ret = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (!ret) { + if (flags) + *flags = cmd->flags; + if (src_sel) + *src_sel = cmd->src_sel; + if (freq) + *freq = le32_to_cpu(cmd->freq); + if (src_freq) + *src_freq = le32_to_cpu(cmd->src_freq); + } + + return ret; +} + +/** + * ice_aq_get_cgu_dpll_status - get dpll status + * @hw: pointer to the HW struct + * @dpll_num: DPLL index + * @ref_state: Reference clock state + * @config: current DPLL config + * @dpll_state: current DPLL state + * @phase_offset: Phase offset in ns + * @eec_mode: EEC_mode + * + * Get CGU DPLL status (0x0C66) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_get_cgu_dpll_status(struct ice_hw *hw, u8 dpll_num, u8 *ref_state, + u8 *dpll_state, u8 *config, s64 *phase_offset, + u8 *eec_mode) +{ + struct ice_aqc_get_cgu_dpll_status *cmd; + const s64 nsec_per_psec = 1000LL; + struct ice_aq_desc desc; + int status; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_dpll_status); + cmd = &desc.params.get_cgu_dpll_status; + cmd->dpll_num = dpll_num; + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (!status) { + *ref_state = cmd->ref_state; + *dpll_state = cmd->dpll_state; + *config = cmd->config; + *phase_offset = le32_to_cpu(cmd->phase_offset_h); + *phase_offset <<= 32; + *phase_offset += le32_to_cpu(cmd->phase_offset_l); + *phase_offset = div64_s64(sign_extend64(*phase_offset, 47), + nsec_per_psec); + *eec_mode = cmd->eec_mode; + } + + return status; +} + +/** + * ice_aq_set_cgu_dpll_config - set dpll config + * @hw: pointer to the HW struct + * @dpll_num: DPLL index + * @ref_state: Reference clock state + * @config: DPLL config + * @eec_mode: EEC mode + * + * Set CGU DPLL config (0x0C67) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_set_cgu_dpll_config(struct ice_hw *hw, u8 dpll_num, u8 ref_state, + u8 config, u8 eec_mode) +{ + struct ice_aqc_set_cgu_dpll_config *cmd; + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_cgu_dpll_config); + cmd = &desc.params.set_cgu_dpll_config; + cmd->dpll_num = dpll_num; + cmd->ref_state = ref_state; + cmd->config = config; + cmd->eec_mode = eec_mode; + + return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); +} + +/** + * ice_aq_set_cgu_ref_prio - set input reference priority + * @hw: pointer to the HW struct + * @dpll_num: DPLL index + * @ref_idx: Reference pin index + * @ref_priority: Reference input priority + * + * Set CGU reference priority (0x0C68) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_set_cgu_ref_prio(struct ice_hw *hw, u8 dpll_num, u8 ref_idx, + u8 ref_priority) +{ + struct ice_aqc_set_cgu_ref_prio *cmd; + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_cgu_ref_prio); + cmd = &desc.params.set_cgu_ref_prio; + cmd->dpll_num = dpll_num; + cmd->ref_idx = ref_idx; + cmd->ref_priority = ref_priority; + + return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); +} + +/** + * ice_aq_get_cgu_ref_prio - get input reference priority + * @hw: pointer to the HW struct + * @dpll_num: DPLL index + * @ref_idx: Reference pin index + * @ref_prio: Reference input priority + * + * Get CGU reference priority (0x0C69) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_get_cgu_ref_prio(struct ice_hw *hw, u8 dpll_num, u8 ref_idx, + u8 *ref_prio) +{ + struct ice_aqc_get_cgu_ref_prio *cmd; + struct ice_aq_desc desc; + int status; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_ref_prio); + cmd = &desc.params.get_cgu_ref_prio; + cmd->dpll_num = dpll_num; + cmd->ref_idx = ref_idx; + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (!status) + *ref_prio = cmd->ref_priority; + + return status; +} + +/** + * ice_aq_get_cgu_info - get cgu info + * @hw: pointer to the HW struct + * @cgu_id: CGU ID + * @cgu_cfg_ver: CGU config version + * @cgu_fw_ver: CGU firmware version + * + * Get CGU info (0x0C6A) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_get_cgu_info(struct ice_hw *hw, u32 *cgu_id, u32 *cgu_cfg_ver, + u32 *cgu_fw_ver) +{ + struct ice_aqc_get_cgu_info *cmd; + struct ice_aq_desc desc; + int status; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_info); + cmd = &desc.params.get_cgu_info; + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (!status) { + *cgu_id = le32_to_cpu(cmd->cgu_id); + *cgu_cfg_ver = le32_to_cpu(cmd->cgu_cfg_ver); + *cgu_fw_ver = le32_to_cpu(cmd->cgu_fw_ver); + } + + return status; +} + +/** + * ice_aq_set_phy_rec_clk_out - set RCLK phy out + * @hw: pointer to the HW struct + * @phy_output: PHY reference clock output pin + * @enable: GPIO state to be applied + * @freq: PHY output frequency + * + * Set phy recovered clock as reference (0x0630) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_set_phy_rec_clk_out(struct ice_hw *hw, u8 phy_output, bool enable, + u32 *freq) +{ + struct ice_aqc_set_phy_rec_clk_out *cmd; + struct ice_aq_desc desc; + int status; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_phy_rec_clk_out); + cmd = &desc.params.set_phy_rec_clk_out; + cmd->phy_output = phy_output; + cmd->port_num = ICE_AQC_SET_PHY_REC_CLK_OUT_CURR_PORT; + cmd->flags = enable & ICE_AQC_SET_PHY_REC_CLK_OUT_OUT_EN; + cmd->freq = cpu_to_le32(*freq); + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (!status) + *freq = le32_to_cpu(cmd->freq); + + return status; +} + +/** + * ice_aq_get_phy_rec_clk_out - get phy recovered signal info + * @hw: pointer to the HW struct + * @phy_output: PHY reference clock output pin + * @port_num: Port number + * @flags: PHY flags + * @node_handle: PHY output frequency + * + * Get PHY recovered clock output info (0x0631) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_get_phy_rec_clk_out(struct ice_hw *hw, u8 *phy_output, u8 *port_num, + u8 *flags, u16 *node_handle) +{ + struct ice_aqc_get_phy_rec_clk_out *cmd; + struct ice_aq_desc desc; + int status; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_phy_rec_clk_out); + cmd = &desc.params.get_phy_rec_clk_out; + cmd->phy_output = *phy_output; + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (!status) { + *phy_output = cmd->phy_output; + if (port_num) + *port_num = cmd->port_num; + if (flags) + *flags = cmd->flags; + if (node_handle) + *node_handle = le16_to_cpu(cmd->node_handle); + } + return status; } @@ -5185,81 +5810,6 @@ ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, } /** - * ice_aq_set_driver_param - Set driver parameter to share via firmware - * @hw: pointer to the HW struct - * @idx: parameter index to set - * @value: the value to set the parameter to - * @cd: pointer to command details structure or NULL - * - * Set the value of one of the software defined parameters. All PFs connected - * to this device can read the value using ice_aq_get_driver_param. - * - * Note that firmware provides no synchronization or locking, and will not - * save the parameter value during a device reset. It is expected that - * a single PF will write the parameter value, while all other PFs will only - * read it. - */ -int -ice_aq_set_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx, - u32 value, struct ice_sq_cd *cd) -{ - struct ice_aqc_driver_shared_params *cmd; - struct ice_aq_desc desc; - - if (idx >= ICE_AQC_DRIVER_PARAM_MAX) - return -EIO; - - cmd = &desc.params.drv_shared_params; - - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_driver_shared_params); - - cmd->set_or_get_op = ICE_AQC_DRIVER_PARAM_SET; - cmd->param_indx = idx; - cmd->param_val = cpu_to_le32(value); - - return ice_aq_send_cmd(hw, &desc, NULL, 0, cd); -} - -/** - * ice_aq_get_driver_param - Get driver parameter shared via firmware - * @hw: pointer to the HW struct - * @idx: parameter index to set - * @value: storage to return the shared parameter - * @cd: pointer to command details structure or NULL - * - * Get the value of one of the software defined parameters. - * - * Note that firmware provides no synchronization or locking. It is expected - * that only a single PF will write a given parameter. - */ -int -ice_aq_get_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx, - u32 *value, struct ice_sq_cd *cd) -{ - struct ice_aqc_driver_shared_params *cmd; - struct ice_aq_desc desc; - int status; - - if (idx >= ICE_AQC_DRIVER_PARAM_MAX) - return -EIO; - - cmd = &desc.params.drv_shared_params; - - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_driver_shared_params); - - cmd->set_or_get_op = ICE_AQC_DRIVER_PARAM_GET; - cmd->param_indx = idx; - - status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd); - if (status) - return status; - - *value = le32_to_cpu(cmd->param_val); - - return 0; -} - -/** * ice_aq_set_gpio * @hw: pointer to the hw struct * @gpio_ctrl_handle: GPIO controller node handle @@ -5560,6 +6110,7 @@ static const u32 ice_aq_to_link_speed[] = { SPEED_40000, SPEED_50000, SPEED_100000, /* BIT(10) */ + SPEED_200000, }; /** diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 81961a7d6598..31fdcac33986 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -38,10 +38,9 @@ int ice_alloc_hw_res(struct ice_hw *hw, u16 type, u16 num, bool btm, u16 *res); int ice_free_hw_res(struct ice_hw *hw, u16 type, u16 num, u16 *res); -int -ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries, - struct ice_aqc_alloc_free_res_elem *buf, u16 buf_size, - enum ice_adminq_opc opc, struct ice_sq_cd *cd); +int ice_aq_alloc_free_res(struct ice_hw *hw, + struct ice_aqc_alloc_free_res_elem *buf, u16 buf_size, + enum ice_adminq_opc opc); bool ice_is_sbq_supported(struct ice_hw *hw); struct ice_ctl_q_info *ice_get_sbq(struct ice_hw *hw); int @@ -93,6 +92,14 @@ int ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode, struct ice_aqc_get_phy_caps_data *caps, struct ice_sq_cd *cd); +bool ice_is_pf_c827(struct ice_hw *hw); +bool ice_is_phy_rclk_in_netlist(struct ice_hw *hw); +bool ice_is_clock_mux_in_netlist(struct ice_hw *hw); +bool ice_is_cgu_in_netlist(struct ice_hw *hw); +bool ice_is_gps_in_netlist(struct ice_hw *hw); +int +ice_aq_get_netlist_node(struct ice_hw *hw, struct ice_aqc_get_link_topo *cmd, + u8 *node_part_number, u16 *node_handle); int ice_aq_list_caps(struct ice_hw *hw, void *buf, u16 buf_size, u32 *cap_count, enum ice_adminq_opc opc, struct ice_sq_cd *cd); @@ -186,12 +193,54 @@ int ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 q_handle, u8 num_qgrps, struct ice_aqc_add_tx_qgrp *buf, u16 buf_size, struct ice_sq_cd *cd); +int +ice_aq_cfg_lan_txq(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *buf, + u16 buf_size, u16 num_qs, u8 oldport, u8 newport, + struct ice_sq_cd *cd); int ice_replay_vsi(struct ice_hw *hw, u16 vsi_handle); void ice_replay_post(struct ice_hw *hw); void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf); struct ice_q_ctx * ice_get_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 q_handle); int ice_sbq_rw_reg(struct ice_hw *hw, struct ice_sbq_msg_input *in); +int +ice_aq_get_cgu_abilities(struct ice_hw *hw, + struct ice_aqc_get_cgu_abilities *abilities); +int +ice_aq_set_input_pin_cfg(struct ice_hw *hw, u8 input_idx, u8 flags1, u8 flags2, + u32 freq, s32 phase_delay); +int +ice_aq_get_input_pin_cfg(struct ice_hw *hw, u8 input_idx, u8 *status, u8 *type, + u8 *flags1, u8 *flags2, u32 *freq, s32 *phase_delay); +int +ice_aq_set_output_pin_cfg(struct ice_hw *hw, u8 output_idx, u8 flags, + u8 src_sel, u32 freq, s32 phase_delay); +int +ice_aq_get_output_pin_cfg(struct ice_hw *hw, u8 output_idx, u8 *flags, + u8 *src_sel, u32 *freq, u32 *src_freq); +int +ice_aq_get_cgu_dpll_status(struct ice_hw *hw, u8 dpll_num, u8 *ref_state, + u8 *dpll_state, u8 *config, s64 *phase_offset, + u8 *eec_mode); +int +ice_aq_set_cgu_dpll_config(struct ice_hw *hw, u8 dpll_num, u8 ref_state, + u8 config, u8 eec_mode); +int +ice_aq_set_cgu_ref_prio(struct ice_hw *hw, u8 dpll_num, u8 ref_idx, + u8 ref_priority); +int +ice_aq_get_cgu_ref_prio(struct ice_hw *hw, u8 dpll_num, u8 ref_idx, + u8 *ref_prio); +int +ice_aq_get_cgu_info(struct ice_hw *hw, u32 *cgu_id, u32 *cgu_cfg_ver, + u32 *cgu_fw_ver); + +int +ice_aq_set_phy_rec_clk_out(struct ice_hw *hw, u8 phy_output, bool enable, + u32 *freq); +int +ice_aq_get_phy_rec_clk_out(struct ice_hw *hw, u8 *phy_output, u8 *port_num, + u8 *flags, u16 *node_handle); void ice_stat_update40(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat); @@ -204,12 +253,6 @@ int ice_sched_query_elem(struct ice_hw *hw, u32 node_teid, struct ice_aqc_txsched_elem_data *buf); int -ice_aq_set_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx, - u32 value, struct ice_sq_cd *cd); -int -ice_aq_get_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx, - u32 *value, struct ice_sq_cd *cd); -int ice_aq_set_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx, bool value, struct ice_sq_cd *cd); int diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c index 3eb01731e496..e1fbc6de452d 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c @@ -70,6 +70,11 @@ static int ice_dcbnl_setets(struct net_device *netdev, struct ieee_ets *ets) !(pf->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) return -EINVAL; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return -EINVAL; + } + new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; mutex_lock(&pf->tc_mutex); @@ -170,6 +175,11 @@ static u8 ice_dcbnl_setdcbx(struct net_device *netdev, u8 mode) if (mode == pf->dcbx_cap) return ICE_DCB_NO_HW_CHG; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return ICE_DCB_NO_HW_CHG; + } + qos_cfg = &pf->hw.port_info->qos_cfg; /* DSCP configuration is not DCBx negotiated */ @@ -261,6 +271,11 @@ static int ice_dcbnl_setpfc(struct net_device *netdev, struct ieee_pfc *pfc) !(pf->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) return -EINVAL; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return -EINVAL; + } + mutex_lock(&pf->tc_mutex); new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; @@ -323,6 +338,11 @@ static void ice_dcbnl_set_pfc_cfg(struct net_device *netdev, int prio, u8 set) if (prio >= ICE_MAX_USER_PRIORITY) return; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return; + } + new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; new_cfg->pfc.pfccap = pf->hw.func_caps.common_cap.maxtc; @@ -379,6 +399,11 @@ static u8 ice_dcbnl_setstate(struct net_device *netdev, u8 state) !(pf->dcbx_cap & DCB_CAP_DCBX_VER_CEE)) return ICE_DCB_NO_HW_CHG; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return ICE_DCB_NO_HW_CHG; + } + /* Nothing to do */ if (!!state == test_bit(ICE_FLAG_DCB_ENA, pf->flags)) return ICE_DCB_NO_HW_CHG; @@ -451,6 +476,11 @@ ice_dcbnl_set_pg_tc_cfg_tx(struct net_device *netdev, int tc, if (tc >= ICE_MAX_TRAFFIC_CLASS) return; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return; + } + new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; /* prio_type, bwg_id and bw_pct per UP are not supported */ @@ -505,6 +535,11 @@ ice_dcbnl_set_pg_bwg_cfg_tx(struct net_device *netdev, int pgid, u8 bw_pct) if (pgid >= ICE_MAX_TRAFFIC_CLASS) return; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return; + } + new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; new_cfg->etscfg.tcbwtable[pgid] = bw_pct; @@ -725,6 +760,11 @@ static int ice_dcbnl_setapp(struct net_device *netdev, struct dcb_app *app) return -EINVAL; } + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return -EINVAL; + } + max_tc = pf->hw.func_caps.common_cap.maxtc; if (app->priority >= max_tc) { netdev_err(netdev, "TC %d out of range, max TC %d\n", @@ -836,6 +876,11 @@ static int ice_dcbnl_delapp(struct net_device *netdev, struct dcb_app *app) return -EINVAL; } + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return -EINVAL; + } + mutex_lock(&pf->tc_mutex); old_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; @@ -937,6 +982,11 @@ static u8 ice_dcbnl_cee_set_all(struct net_device *netdev) !(pf->dcbx_cap & DCB_CAP_DCBX_VER_CEE)) return ICE_DCB_NO_HW_CHG; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return ICE_DCB_NO_HW_CHG; + } + new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; mutex_lock(&pf->tc_mutex); diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c index d71ed210f9c4..8b7504a9df31 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.c +++ b/drivers/net/ethernet/intel/ice/ice_ddp.c @@ -30,7 +30,7 @@ static const struct ice_tunnel_type_scan tnls[] = { * Verifies various attributes of the package file, including length, format * version, and the requirement of at least one segment. */ -enum ice_ddp_state ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len) +static enum ice_ddp_state ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len) { u32 seg_count; u32 i; @@ -118,7 +118,7 @@ static enum ice_ddp_state ice_chk_pkg_version(struct ice_pkg_ver *pkg_ver) * * This helper function validates a buffer's header. */ -struct ice_buf_hdr *ice_pkg_val_buf(struct ice_buf *buf) +static struct ice_buf_hdr *ice_pkg_val_buf(struct ice_buf *buf) { struct ice_buf_hdr *hdr; u16 section_count; @@ -1153,23 +1153,168 @@ static void ice_release_global_cfg_lock(struct ice_hw *hw) } /** - * ice_dwnld_cfg_bufs + * ice_aq_download_pkg + * @hw: pointer to the hardware structure + * @pkg_buf: the package buffer to transfer + * @buf_size: the size of the package buffer + * @last_buf: last buffer indicator + * @error_offset: returns error offset + * @error_info: returns error information + * @cd: pointer to command details structure or NULL + * + * Download Package (0x0C40) + */ +static int +ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, + u16 buf_size, bool last_buf, u32 *error_offset, + u32 *error_info, struct ice_sq_cd *cd) +{ + struct ice_aqc_download_pkg *cmd; + struct ice_aq_desc desc; + int status; + + if (error_offset) + *error_offset = 0; + if (error_info) + *error_info = 0; + + cmd = &desc.params.download_pkg; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_download_pkg); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + if (last_buf) + cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF; + + status = ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd); + if (status == -EIO) { + /* Read error from buffer only when the FW returned an error */ + struct ice_aqc_download_pkg_resp *resp; + + resp = (struct ice_aqc_download_pkg_resp *)pkg_buf; + if (error_offset) + *error_offset = le32_to_cpu(resp->error_offset); + if (error_info) + *error_info = le32_to_cpu(resp->error_info); + } + + return status; +} + +/** + * ice_get_pkg_seg_by_idx + * @pkg_hdr: pointer to the package header to be searched + * @idx: index of segment + */ +static struct ice_generic_seg_hdr * +ice_get_pkg_seg_by_idx(struct ice_pkg_hdr *pkg_hdr, u32 idx) +{ + if (idx < le32_to_cpu(pkg_hdr->seg_count)) + return (struct ice_generic_seg_hdr *) + ((u8 *)pkg_hdr + + le32_to_cpu(pkg_hdr->seg_offset[idx])); + + return NULL; +} + +/** + * ice_is_signing_seg_at_idx - determine if segment is a signing segment + * @pkg_hdr: pointer to package header + * @idx: segment index + */ +static bool ice_is_signing_seg_at_idx(struct ice_pkg_hdr *pkg_hdr, u32 idx) +{ + struct ice_generic_seg_hdr *seg; + + seg = ice_get_pkg_seg_by_idx(pkg_hdr, idx); + if (!seg) + return false; + + return le32_to_cpu(seg->seg_type) == SEGMENT_TYPE_SIGNING; +} + +/** + * ice_is_signing_seg_type_at_idx + * @pkg_hdr: pointer to package header + * @idx: segment index + * @seg_id: segment id that is expected + * @sign_type: signing type + * + * Determine if a segment is a signing segment of the correct type + */ +static bool +ice_is_signing_seg_type_at_idx(struct ice_pkg_hdr *pkg_hdr, u32 idx, + u32 seg_id, u32 sign_type) +{ + struct ice_sign_seg *seg; + + if (!ice_is_signing_seg_at_idx(pkg_hdr, idx)) + return false; + + seg = (struct ice_sign_seg *)ice_get_pkg_seg_by_idx(pkg_hdr, idx); + + if (seg && le32_to_cpu(seg->seg_id) == seg_id && + le32_to_cpu(seg->sign_type) == sign_type) + return true; + + return false; +} + +/** + * ice_is_buffer_metadata - determine if package buffer is a metadata buffer + * @buf: pointer to buffer header + */ +static bool ice_is_buffer_metadata(struct ice_buf_hdr *buf) +{ + if (le32_to_cpu(buf->section_entry[0].type) & ICE_METADATA_BUF) + return true; + + return false; +} + +/** + * ice_is_last_download_buffer + * @buf: pointer to current buffer header + * @idx: index of the buffer in the current sequence + * @count: the buffer count in the current sequence + * + * Note: this routine should only be called if the buffer is not the last buffer + */ +static bool +ice_is_last_download_buffer(struct ice_buf_hdr *buf, u32 idx, u32 count) +{ + struct ice_buf *next_buf; + + if ((idx + 1) == count) + return true; + + /* A set metadata flag in the next buffer will signal that the current + * buffer will be the last buffer downloaded + */ + next_buf = ((struct ice_buf *)buf) + 1; + + return ice_is_buffer_metadata((struct ice_buf_hdr *)next_buf); +} + +/** + * ice_dwnld_cfg_bufs_no_lock * @hw: pointer to the hardware structure * @bufs: pointer to an array of buffers - * @count: the number of buffers in the array + * @start: buffer index of first buffer to download + * @count: the number of buffers to download + * @indicate_last: if true, then set last buffer flag on last buffer download * - * Obtains global config lock and downloads the package configuration buffers - * to the firmware. Metadata buffers are skipped, and the first metadata buffer - * found indicates that the rest of the buffers are all metadata buffers. + * Downloads package configuration buffers to the firmware. Metadata buffers + * are skipped, and the first metadata buffer found indicates that the rest + * of the buffers are all metadata buffers. */ -static enum ice_ddp_state ice_dwnld_cfg_bufs(struct ice_hw *hw, - struct ice_buf *bufs, u32 count) +static enum ice_ddp_state +ice_dwnld_cfg_bufs_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 start, + u32 count, bool indicate_last) { enum ice_ddp_state state = ICE_DDP_PKG_SUCCESS; struct ice_buf_hdr *bh; enum ice_aq_err err; u32 offset, info, i; - int status; if (!bufs || !count) return ICE_DDP_PKG_ERR; @@ -1178,43 +1323,25 @@ static enum ice_ddp_state ice_dwnld_cfg_bufs(struct ice_hw *hw, * then there are no buffers to be downloaded, and the operation is * considered a success. */ - bh = (struct ice_buf_hdr *)bufs; + bh = (struct ice_buf_hdr *)(bufs + start); if (le32_to_cpu(bh->section_entry[0].type) & ICE_METADATA_BUF) return ICE_DDP_PKG_SUCCESS; - status = ice_acquire_global_cfg_lock(hw, ICE_RES_WRITE); - if (status) { - if (status == -EALREADY) - return ICE_DDP_PKG_ALREADY_LOADED; - return ice_map_aq_err_to_ddp_state(hw->adminq.sq_last_status); - } - for (i = 0; i < count; i++) { - bool last = ((i + 1) == count); - - if (!last) { - /* check next buffer for metadata flag */ - bh = (struct ice_buf_hdr *)(bufs + i + 1); + bool last = false; + int status; - /* A set metadata flag in the next buffer will signal - * that the current buffer will be the last buffer - * downloaded - */ - if (le16_to_cpu(bh->section_count)) - if (le32_to_cpu(bh->section_entry[0].type) & - ICE_METADATA_BUF) - last = true; - } + bh = (struct ice_buf_hdr *)(bufs + start + i); - bh = (struct ice_buf_hdr *)(bufs + i); + if (indicate_last) + last = ice_is_last_download_buffer(bh, i, count); status = ice_aq_download_pkg(hw, bh, ICE_PKG_BUF_SIZE, last, &offset, &info, NULL); /* Save AQ status from download package */ if (status) { - ice_debug(hw, ICE_DBG_PKG, - "Pkg download failed: err %d off %d inf %d\n", + ice_debug(hw, ICE_DBG_PKG, "Pkg download failed: err %d off %d inf %d\n", status, offset, info); err = hw->adminq.sq_last_status; state = ice_map_aq_err_to_ddp_state(err); @@ -1225,50 +1352,231 @@ static enum ice_ddp_state ice_dwnld_cfg_bufs(struct ice_hw *hw, break; } - if (!status) { - status = ice_set_vlan_mode(hw); - if (status) - ice_debug(hw, ICE_DBG_PKG, - "Failed to set VLAN mode: err %d\n", status); + return state; +} + +/** + * ice_download_pkg_sig_seg - download a signature segment + * @hw: pointer to the hardware structure + * @seg: pointer to signature segment + */ +static enum ice_ddp_state +ice_download_pkg_sig_seg(struct ice_hw *hw, struct ice_sign_seg *seg) +{ + return ice_dwnld_cfg_bufs_no_lock(hw, seg->buf_tbl.buf_array, 0, + le32_to_cpu(seg->buf_tbl.buf_count), + false); +} + +/** + * ice_download_pkg_config_seg - download a config segment + * @hw: pointer to the hardware structure + * @pkg_hdr: pointer to package header + * @idx: segment index + * @start: starting buffer + * @count: buffer count + * + * Note: idx must reference a ICE segment + */ +static enum ice_ddp_state +ice_download_pkg_config_seg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr, + u32 idx, u32 start, u32 count) +{ + struct ice_buf_table *bufs; + struct ice_seg *seg; + u32 buf_count; + + seg = (struct ice_seg *)ice_get_pkg_seg_by_idx(pkg_hdr, idx); + if (!seg) + return ICE_DDP_PKG_ERR; + + bufs = ice_find_buf_table(seg); + buf_count = le32_to_cpu(bufs->buf_count); + + if (start >= buf_count || start + count > buf_count) + return ICE_DDP_PKG_ERR; + + return ice_dwnld_cfg_bufs_no_lock(hw, bufs->buf_array, start, count, + true); +} + +/** + * ice_dwnld_sign_and_cfg_segs - download a signing segment and config segment + * @hw: pointer to the hardware structure + * @pkg_hdr: pointer to package header + * @idx: segment index (must be a signature segment) + * + * Note: idx must reference a signature segment + */ +static enum ice_ddp_state +ice_dwnld_sign_and_cfg_segs(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr, + u32 idx) +{ + enum ice_ddp_state state; + struct ice_sign_seg *seg; + u32 conf_idx; + u32 start; + u32 count; + + seg = (struct ice_sign_seg *)ice_get_pkg_seg_by_idx(pkg_hdr, idx); + if (!seg) { + state = ICE_DDP_PKG_ERR; + goto exit; } + conf_idx = le32_to_cpu(seg->signed_seg_idx); + start = le32_to_cpu(seg->signed_buf_start); + count = le32_to_cpu(seg->signed_buf_count); + + state = ice_download_pkg_sig_seg(hw, seg); + if (state) + goto exit; + + state = ice_download_pkg_config_seg(hw, pkg_hdr, conf_idx, start, + count); + +exit: + return state; +} + +/** + * ice_match_signing_seg - determine if a matching signing segment exists + * @pkg_hdr: pointer to package header + * @seg_id: segment id that is expected + * @sign_type: signing type + */ +static bool +ice_match_signing_seg(struct ice_pkg_hdr *pkg_hdr, u32 seg_id, u32 sign_type) +{ + u32 i; + + for (i = 0; i < le32_to_cpu(pkg_hdr->seg_count); i++) { + if (ice_is_signing_seg_type_at_idx(pkg_hdr, i, seg_id, + sign_type)) + return true; + } + + return false; +} + +/** + * ice_post_dwnld_pkg_actions - perform post download package actions + * @hw: pointer to the hardware structure + */ +static enum ice_ddp_state +ice_post_dwnld_pkg_actions(struct ice_hw *hw) +{ + int status; + + status = ice_set_vlan_mode(hw); + if (status) { + ice_debug(hw, ICE_DBG_PKG, "Failed to set VLAN mode: err %d\n", + status); + return ICE_DDP_PKG_ERR; + } + + return ICE_DDP_PKG_SUCCESS; +} + +/** + * ice_download_pkg_with_sig_seg + * @hw: pointer to the hardware structure + * @pkg_hdr: pointer to package header + * + * Handles the download of a complete package. + */ +static enum ice_ddp_state +ice_download_pkg_with_sig_seg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr) +{ + enum ice_aq_err aq_err = hw->adminq.sq_last_status; + enum ice_ddp_state state = ICE_DDP_PKG_ERR; + int status; + u32 i; + + ice_debug(hw, ICE_DBG_INIT, "Segment ID %d\n", hw->pkg_seg_id); + ice_debug(hw, ICE_DBG_INIT, "Signature type %d\n", hw->pkg_sign_type); + + status = ice_acquire_global_cfg_lock(hw, ICE_RES_WRITE); + if (status) { + if (status == -EALREADY) + state = ICE_DDP_PKG_ALREADY_LOADED; + else + state = ice_map_aq_err_to_ddp_state(aq_err); + return state; + } + + for (i = 0; i < le32_to_cpu(pkg_hdr->seg_count); i++) { + if (!ice_is_signing_seg_type_at_idx(pkg_hdr, i, hw->pkg_seg_id, + hw->pkg_sign_type)) + continue; + + state = ice_dwnld_sign_and_cfg_segs(hw, pkg_hdr, i); + if (state) + break; + } + + if (!state) + state = ice_post_dwnld_pkg_actions(hw); + ice_release_global_cfg_lock(hw); return state; } /** - * ice_aq_get_pkg_info_list + * ice_dwnld_cfg_bufs * @hw: pointer to the hardware structure - * @pkg_info: the buffer which will receive the information list - * @buf_size: the size of the pkg_info information buffer - * @cd: pointer to command details structure or NULL + * @bufs: pointer to an array of buffers + * @count: the number of buffers in the array * - * Get Package Info List (0x0C43) + * Obtains global config lock and downloads the package configuration buffers + * to the firmware. */ -static int ice_aq_get_pkg_info_list(struct ice_hw *hw, - struct ice_aqc_get_pkg_info_resp *pkg_info, - u16 buf_size, struct ice_sq_cd *cd) +static enum ice_ddp_state +ice_dwnld_cfg_bufs(struct ice_hw *hw, struct ice_buf *bufs, u32 count) { - struct ice_aq_desc desc; + enum ice_ddp_state state; + struct ice_buf_hdr *bh; + int status; - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_pkg_info_list); + if (!bufs || !count) + return ICE_DDP_PKG_ERR; - return ice_aq_send_cmd(hw, &desc, pkg_info, buf_size, cd); + /* If the first buffer's first section has its metadata bit set + * then there are no buffers to be downloaded, and the operation is + * considered a success. + */ + bh = (struct ice_buf_hdr *)bufs; + if (le32_to_cpu(bh->section_entry[0].type) & ICE_METADATA_BUF) + return ICE_DDP_PKG_SUCCESS; + + status = ice_acquire_global_cfg_lock(hw, ICE_RES_WRITE); + if (status) { + if (status == -EALREADY) + return ICE_DDP_PKG_ALREADY_LOADED; + return ice_map_aq_err_to_ddp_state(hw->adminq.sq_last_status); + } + + state = ice_dwnld_cfg_bufs_no_lock(hw, bufs, 0, count, true); + if (!state) + state = ice_post_dwnld_pkg_actions(hw); + + ice_release_global_cfg_lock(hw); + + return state; } /** - * ice_download_pkg + * ice_download_pkg_without_sig_seg * @hw: pointer to the hardware structure * @ice_seg: pointer to the segment of the package to be downloaded * - * Handles the download of a complete package. + * Handles the download of a complete package without signature segment. */ -static enum ice_ddp_state ice_download_pkg(struct ice_hw *hw, - struct ice_seg *ice_seg) +static enum ice_ddp_state +ice_download_pkg_without_sig_seg(struct ice_hw *hw, struct ice_seg *ice_seg) { struct ice_buf_table *ice_buf_tbl; - int status; ice_debug(hw, ICE_DBG_PKG, "Segment format version: %d.%d.%d.%d\n", ice_seg->hdr.seg_format_ver.major, @@ -1285,79 +1593,52 @@ static enum ice_ddp_state ice_download_pkg(struct ice_hw *hw, ice_debug(hw, ICE_DBG_PKG, "Seg buf count: %d\n", le32_to_cpu(ice_buf_tbl->buf_count)); - status = ice_dwnld_cfg_bufs(hw, ice_buf_tbl->buf_array, - le32_to_cpu(ice_buf_tbl->buf_count)); - - ice_post_pkg_dwnld_vlan_mode_cfg(hw); - - return status; + return ice_dwnld_cfg_bufs(hw, ice_buf_tbl->buf_array, + le32_to_cpu(ice_buf_tbl->buf_count)); } /** - * ice_aq_download_pkg + * ice_download_pkg * @hw: pointer to the hardware structure - * @pkg_buf: the package buffer to transfer - * @buf_size: the size of the package buffer - * @last_buf: last buffer indicator - * @error_offset: returns error offset - * @error_info: returns error information - * @cd: pointer to command details structure or NULL + * @pkg_hdr: pointer to package header + * @ice_seg: pointer to the segment of the package to be downloaded * - * Download Package (0x0C40) + * Handles the download of a complete package. */ -int ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, - u16 buf_size, bool last_buf, u32 *error_offset, - u32 *error_info, struct ice_sq_cd *cd) +static enum ice_ddp_state +ice_download_pkg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr, + struct ice_seg *ice_seg) { - struct ice_aqc_download_pkg *cmd; - struct ice_aq_desc desc; - int status; - - if (error_offset) - *error_offset = 0; - if (error_info) - *error_info = 0; - - cmd = &desc.params.download_pkg; - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_download_pkg); - desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); - - if (last_buf) - cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF; + enum ice_ddp_state state; - status = ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd); - if (status == -EIO) { - /* Read error from buffer only when the FW returned an error */ - struct ice_aqc_download_pkg_resp *resp; + if (hw->pkg_has_signing_seg) + state = ice_download_pkg_with_sig_seg(hw, pkg_hdr); + else + state = ice_download_pkg_without_sig_seg(hw, ice_seg); - resp = (struct ice_aqc_download_pkg_resp *)pkg_buf; - if (error_offset) - *error_offset = le32_to_cpu(resp->error_offset); - if (error_info) - *error_info = le32_to_cpu(resp->error_info); - } + ice_post_pkg_dwnld_vlan_mode_cfg(hw); - return status; + return state; } /** - * ice_aq_upload_section + * ice_aq_get_pkg_info_list * @hw: pointer to the hardware structure - * @pkg_buf: the package buffer which will receive the section - * @buf_size: the size of the package buffer + * @pkg_info: the buffer which will receive the information list + * @buf_size: the size of the pkg_info information buffer * @cd: pointer to command details structure or NULL * - * Upload Section (0x0C41) + * Get Package Info List (0x0C43) */ -int ice_aq_upload_section(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, - u16 buf_size, struct ice_sq_cd *cd) +static int ice_aq_get_pkg_info_list(struct ice_hw *hw, + struct ice_aqc_get_pkg_info_resp *pkg_info, + u16 buf_size, struct ice_sq_cd *cd) { struct ice_aq_desc desc; - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_upload_section); - desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_pkg_info_list); - return ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd); + return ice_aq_send_cmd(hw, &desc, pkg_info, buf_size, cd); } /** @@ -1408,6 +1689,26 @@ static int ice_aq_update_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, } /** + * ice_aq_upload_section + * @hw: pointer to the hardware structure + * @pkg_buf: the package buffer which will receive the section + * @buf_size: the size of the package buffer + * @cd: pointer to command details structure or NULL + * + * Upload Section (0x0C41) + */ +int ice_aq_upload_section(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, + u16 buf_size, struct ice_sq_cd *cd) +{ + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_upload_section); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + return ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd); +} + +/** * ice_update_pkg_no_lock * @hw: pointer to the hardware structure * @bufs: pointer to an array of buffers @@ -1470,8 +1771,9 @@ int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count) * success it returns a pointer to the segment header, otherwise it will * return NULL. */ -struct ice_generic_seg_hdr *ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type, - struct ice_pkg_hdr *pkg_hdr) +static struct ice_generic_seg_hdr * +ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type, + struct ice_pkg_hdr *pkg_hdr) { u32 i; @@ -1496,6 +1798,73 @@ struct ice_generic_seg_hdr *ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type, } /** + * ice_has_signing_seg - determine if package has a signing segment + * @hw: pointer to the hardware structure + * @pkg_hdr: pointer to the driver's package hdr + */ +static bool ice_has_signing_seg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr) +{ + struct ice_generic_seg_hdr *seg_hdr; + + seg_hdr = (struct ice_generic_seg_hdr *) + ice_find_seg_in_pkg(hw, SEGMENT_TYPE_SIGNING, pkg_hdr); + + return seg_hdr ? true : false; +} + +/** + * ice_get_pkg_segment_id - get correct package segment id, based on device + * @mac_type: MAC type of the device + */ +static u32 ice_get_pkg_segment_id(enum ice_mac_type mac_type) +{ + u32 seg_id; + + switch (mac_type) { + case ICE_MAC_E830: + seg_id = SEGMENT_TYPE_ICE_E830; + break; + case ICE_MAC_GENERIC: + default: + seg_id = SEGMENT_TYPE_ICE_E810; + break; + } + + return seg_id; +} + +/** + * ice_get_pkg_sign_type - get package segment sign type, based on device + * @mac_type: MAC type of the device + */ +static u32 ice_get_pkg_sign_type(enum ice_mac_type mac_type) +{ + u32 sign_type; + + switch (mac_type) { + case ICE_MAC_E830: + sign_type = SEGMENT_SIGN_TYPE_RSA3K_SBB; + break; + case ICE_MAC_GENERIC: + default: + sign_type = SEGMENT_SIGN_TYPE_RSA2K; + break; + } + + return sign_type; +} + +/** + * ice_get_signing_req - get correct package requirements, based on device + * @hw: pointer to the hardware structure + */ +static void ice_get_signing_req(struct ice_hw *hw) +{ + hw->pkg_seg_id = ice_get_pkg_segment_id(hw->mac_type); + hw->pkg_sign_type = ice_get_pkg_sign_type(hw->mac_type); +} + +/** * ice_init_pkg_info * @hw: pointer to the hardware structure * @pkg_hdr: pointer to the driver's package hdr @@ -1510,7 +1879,14 @@ static enum ice_ddp_state ice_init_pkg_info(struct ice_hw *hw, if (!pkg_hdr) return ICE_DDP_PKG_ERR; - seg_hdr = ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE, pkg_hdr); + hw->pkg_has_signing_seg = ice_has_signing_seg(hw, pkg_hdr); + ice_get_signing_req(hw); + + ice_debug(hw, ICE_DBG_INIT, "Pkg using segment id: 0x%08X\n", + hw->pkg_seg_id); + + seg_hdr = (struct ice_generic_seg_hdr *) + ice_find_seg_in_pkg(hw, hw->pkg_seg_id, pkg_hdr); if (seg_hdr) { struct ice_meta_sect *meta; struct ice_pkg_enum state; @@ -1558,21 +1934,14 @@ static enum ice_ddp_state ice_init_pkg_info(struct ice_hw *hw, */ static enum ice_ddp_state ice_get_pkg_info(struct ice_hw *hw) { - enum ice_ddp_state state = ICE_DDP_PKG_SUCCESS; - struct ice_aqc_get_pkg_info_resp *pkg_info; - u16 size; + DEFINE_FLEX(struct ice_aqc_get_pkg_info_resp, pkg_info, pkg_info, + ICE_PKG_CNT); + u16 size = __struct_size(pkg_info); u32 i; - size = struct_size(pkg_info, pkg_info, ICE_PKG_CNT); - pkg_info = kzalloc(size, GFP_KERNEL); - if (!pkg_info) + if (ice_aq_get_pkg_info_list(hw, pkg_info, size, NULL)) return ICE_DDP_PKG_ERR; - if (ice_aq_get_pkg_info_list(hw, pkg_info, size, NULL)) { - state = ICE_DDP_PKG_ERR; - goto init_pkg_free_alloc; - } - for (i = 0; i < le32_to_cpu(pkg_info->count); i++) { #define ICE_PKG_FLAG_COUNT 4 char flags[ICE_PKG_FLAG_COUNT + 1] = { 0 }; @@ -1602,10 +1971,7 @@ static enum ice_ddp_state ice_get_pkg_info(struct ice_hw *hw) pkg_info->pkg_info[i].name, flags); } -init_pkg_free_alloc: - kfree(pkg_info); - - return state; + return ICE_DDP_PKG_SUCCESS; } /** @@ -1620,9 +1986,10 @@ static enum ice_ddp_state ice_chk_pkg_compat(struct ice_hw *hw, struct ice_pkg_hdr *ospkg, struct ice_seg **seg) { - struct ice_aqc_get_pkg_info_resp *pkg; + DEFINE_FLEX(struct ice_aqc_get_pkg_info_resp, pkg, pkg_info, + ICE_PKG_CNT); + u16 size = __struct_size(pkg); enum ice_ddp_state state; - u16 size; u32 i; /* Check package version compatibility */ @@ -1633,7 +2000,7 @@ static enum ice_ddp_state ice_chk_pkg_compat(struct ice_hw *hw, } /* find ICE segment in given package */ - *seg = (struct ice_seg *)ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE, + *seg = (struct ice_seg *)ice_find_seg_in_pkg(hw, hw->pkg_seg_id, ospkg); if (!*seg) { ice_debug(hw, ICE_DBG_INIT, "no ice segment in package.\n"); @@ -1641,15 +2008,8 @@ static enum ice_ddp_state ice_chk_pkg_compat(struct ice_hw *hw, } /* Check if FW is compatible with the OS package */ - size = struct_size(pkg, pkg_info, ICE_PKG_CNT); - pkg = kzalloc(size, GFP_KERNEL); - if (!pkg) - return ICE_DDP_PKG_ERR; - - if (ice_aq_get_pkg_info_list(hw, pkg, size, NULL)) { - state = ICE_DDP_PKG_LOAD_ERROR; - goto fw_ddp_compat_free_alloc; - } + if (ice_aq_get_pkg_info_list(hw, pkg, size, NULL)) + return ICE_DDP_PKG_LOAD_ERROR; for (i = 0; i < le32_to_cpu(pkg->count); i++) { /* loop till we find the NVM package */ @@ -1666,8 +2026,7 @@ static enum ice_ddp_state ice_chk_pkg_compat(struct ice_hw *hw, /* done processing NVM package so break */ break; } -fw_ddp_compat_free_alloc: - kfree(pkg); + return state; } @@ -1807,6 +2166,11 @@ enum ice_ddp_state ice_init_pkg(struct ice_hw *hw, u8 *buf, u32 len) if (state) return state; + /* must be a matching segment */ + if (hw->pkg_has_signing_seg && + !ice_match_signing_seg(pkg, hw->pkg_seg_id, hw->pkg_sign_type)) + return ICE_DDP_PKG_ERR; + /* before downloading the package, check package version for * compatibility with driver */ @@ -1816,7 +2180,7 @@ enum ice_ddp_state ice_init_pkg(struct ice_hw *hw, u8 *buf, u32 len) /* initialize package hints and then download package */ ice_init_pkg_hints(hw, seg); - state = ice_download_pkg(hw, seg); + state = ice_download_pkg(hw, pkg, seg); if (state == ICE_DDP_PKG_ALREADY_LOADED) { ice_debug(hw, ICE_DBG_INIT, "package previously loaded - no work.\n"); diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.h b/drivers/net/ethernet/intel/ice/ice_ddp.h index 41acfe26df1c..ff66c2ffb1a2 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.h +++ b/drivers/net/ethernet/intel/ice/ice_ddp.h @@ -98,10 +98,21 @@ struct ice_pkg_hdr { __le32 seg_offset[]; }; +/* Package signing algorithm types */ +#define SEGMENT_SIGN_TYPE_INVALID 0x00000000 +#define SEGMENT_SIGN_TYPE_RSA2K 0x00000001 +#define SEGMENT_SIGN_TYPE_RSA3K 0x00000002 +#define SEGMENT_SIGN_TYPE_RSA3K_SBB 0x00000003 /* Secure Boot Block */ +#define SEGMENT_SIGN_TYPE_RSA3K_E825 0x00000005 + /* generic segment */ struct ice_generic_seg_hdr { -#define SEGMENT_TYPE_METADATA 0x00000001 -#define SEGMENT_TYPE_ICE 0x00000010 +#define SEGMENT_TYPE_INVALID 0x00000000 +#define SEGMENT_TYPE_METADATA 0x00000001 +#define SEGMENT_TYPE_ICE_E810 0x00000010 +#define SEGMENT_TYPE_SIGNING 0x00001001 +#define SEGMENT_TYPE_ICE_RUN_TIME_CFG 0x00000020 +#define SEGMENT_TYPE_ICE_E830 0x00000017 __le32 seg_type; struct ice_pkg_ver seg_format_ver; __le32 seg_size; @@ -163,6 +174,18 @@ struct ice_global_metadata_seg { #define ICE_MIN_S_SZ 1 #define ICE_MAX_S_SZ 4084 +struct ice_sign_seg { + struct ice_generic_seg_hdr hdr; + __le32 seg_id; + __le32 sign_type; + __le32 signed_seg_idx; + __le32 signed_buf_start; + __le32 signed_buf_count; +#define ICE_SIGN_SEG_RESERVED_COUNT 44 + u8 reserved[ICE_SIGN_SEG_RESERVED_COUNT]; + struct ice_buf_table buf_tbl; +}; + /* section information */ struct ice_section_entry { __le32 type; @@ -416,21 +439,13 @@ struct ice_pkg_enum { void *(*handler)(u32 sect_type, void *section, u32 index, u32 *offset); }; -int ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, - u16 buf_size, bool last_buf, u32 *error_offset, - u32 *error_info, struct ice_sq_cd *cd); int ice_aq_upload_section(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, u16 buf_size, struct ice_sq_cd *cd); void *ice_pkg_buf_alloc_section(struct ice_buf_build *bld, u32 type, u16 size); -enum ice_ddp_state ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len); - struct ice_buf_build *ice_pkg_buf_alloc(struct ice_hw *hw); -struct ice_generic_seg_hdr *ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type, - struct ice_pkg_hdr *pkg_hdr); - int ice_update_pkg_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 count); int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count); @@ -439,6 +454,4 @@ u16 ice_pkg_buf_get_active_sections(struct ice_buf_build *bld); void *ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state, u32 sect_type); -struct ice_buf_hdr *ice_pkg_val_buf(struct ice_buf *buf); - #endif diff --git a/drivers/net/ethernet/intel/ice/ice_devids.h b/drivers/net/ethernet/intel/ice/ice_devids.h index 6d560d1c74a4..a2d384dbfc76 100644 --- a/drivers/net/ethernet/intel/ice/ice_devids.h +++ b/drivers/net/ethernet/intel/ice/ice_devids.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (c) 2018, Intel Corporation. */ +/* Copyright (c) 2018-2023, Intel Corporation. */ #ifndef _ICE_DEVIDS_H_ #define _ICE_DEVIDS_H_ @@ -16,6 +16,14 @@ #define ICE_DEV_ID_E823L_1GBE 0x124F /* Intel(R) Ethernet Connection E823-L for QSFP */ #define ICE_DEV_ID_E823L_QSFP 0x151D +/* Intel(R) Ethernet Controller E830-C for backplane */ +#define ICE_DEV_ID_E830_BACKPLANE 0x12D1 +/* Intel(R) Ethernet Controller E830-C for QSFP */ +#define ICE_DEV_ID_E830_QSFP56 0x12D2 +/* Intel(R) Ethernet Controller E830-C for SFP */ +#define ICE_DEV_ID_E830_SFP 0x12D3 +/* Intel(R) Ethernet Controller E830-C for SFP-DD */ +#define ICE_DEV_ID_E830_SFP_DD 0x12D4 /* Intel(R) Ethernet Controller E810-C for backplane */ #define ICE_DEV_ID_E810C_BACKPLANE 0x1591 /* Intel(R) Ethernet Controller E810-C for QSFP */ diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c new file mode 100644 index 000000000000..86b180cb32a0 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -0,0 +1,2117 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2022, Intel Corporation. */ + +#include "ice.h" +#include "ice_lib.h" +#include "ice_trace.h" +#include <linux/dpll.h> + +#define ICE_CGU_STATE_ACQ_ERR_THRESHOLD 50 +#define ICE_DPLL_PIN_IDX_INVALID 0xff +#define ICE_DPLL_RCLK_NUM_PER_PF 1 + +/** + * enum ice_dpll_pin_type - enumerate ice pin types: + * @ICE_DPLL_PIN_INVALID: invalid pin type + * @ICE_DPLL_PIN_TYPE_INPUT: input pin + * @ICE_DPLL_PIN_TYPE_OUTPUT: output pin + * @ICE_DPLL_PIN_TYPE_RCLK_INPUT: recovery clock input pin + */ +enum ice_dpll_pin_type { + ICE_DPLL_PIN_INVALID, + ICE_DPLL_PIN_TYPE_INPUT, + ICE_DPLL_PIN_TYPE_OUTPUT, + ICE_DPLL_PIN_TYPE_RCLK_INPUT, +}; + +static const char * const pin_type_name[] = { + [ICE_DPLL_PIN_TYPE_INPUT] = "input", + [ICE_DPLL_PIN_TYPE_OUTPUT] = "output", + [ICE_DPLL_PIN_TYPE_RCLK_INPUT] = "rclk-input", +}; + +/** + * ice_dpll_pin_freq_set - set pin's frequency + * @pf: private board structure + * @pin: pointer to a pin + * @pin_type: type of pin being configured + * @freq: frequency to be set + * @extack: error reporting + * + * Set requested frequency on a pin. + * + * Context: Called under pf->dplls.lock + * Return: + * * 0 - success + * * negative - error on AQ or wrong pin type given + */ +static int +ice_dpll_pin_freq_set(struct ice_pf *pf, struct ice_dpll_pin *pin, + enum ice_dpll_pin_type pin_type, const u32 freq, + struct netlink_ext_ack *extack) +{ + u8 flags; + int ret; + + switch (pin_type) { + case ICE_DPLL_PIN_TYPE_INPUT: + flags = ICE_AQC_SET_CGU_IN_CFG_FLG1_UPDATE_FREQ; + ret = ice_aq_set_input_pin_cfg(&pf->hw, pin->idx, flags, + pin->flags[0], freq, 0); + break; + case ICE_DPLL_PIN_TYPE_OUTPUT: + flags = ICE_AQC_SET_CGU_OUT_CFG_UPDATE_FREQ; + ret = ice_aq_set_output_pin_cfg(&pf->hw, pin->idx, flags, + 0, freq, 0); + break; + default: + return -EINVAL; + } + if (ret) { + NL_SET_ERR_MSG_FMT(extack, + "err:%d %s failed to set pin freq:%u on pin:%u\n", + ret, + ice_aq_str(pf->hw.adminq.sq_last_status), + freq, pin->idx); + return ret; + } + pin->freq = freq; + + return 0; +} + +/** + * ice_dpll_frequency_set - wrapper for pin callback for set frequency + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: pointer to dpll + * @dpll_priv: private data pointer passed on dpll registration + * @frequency: frequency to be set + * @extack: error reporting + * @pin_type: type of pin being configured + * + * Wraps internal set frequency command on a pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error pin not found or couldn't set in hw + */ +static int +ice_dpll_frequency_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + const u32 frequency, + struct netlink_ext_ack *extack, + enum ice_dpll_pin_type pin_type) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + int ret; + + mutex_lock(&pf->dplls.lock); + ret = ice_dpll_pin_freq_set(pf, p, pin_type, frequency, extack); + mutex_unlock(&pf->dplls.lock); + + return ret; +} + +/** + * ice_dpll_input_frequency_set - input pin callback for set frequency + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: pointer to dpll + * @dpll_priv: private data pointer passed on dpll registration + * @frequency: frequency to be set + * @extack: error reporting + * + * Wraps internal set frequency command on a pin. + * + * Context: Calls a function which acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error pin not found or couldn't set in hw + */ +static int +ice_dpll_input_frequency_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u64 frequency, struct netlink_ext_ack *extack) +{ + return ice_dpll_frequency_set(pin, pin_priv, dpll, dpll_priv, frequency, + extack, ICE_DPLL_PIN_TYPE_INPUT); +} + +/** + * ice_dpll_output_frequency_set - output pin callback for set frequency + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: pointer to dpll + * @dpll_priv: private data pointer passed on dpll registration + * @frequency: frequency to be set + * @extack: error reporting + * + * Wraps internal set frequency command on a pin. + * + * Context: Calls a function which acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error pin not found or couldn't set in hw + */ +static int +ice_dpll_output_frequency_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u64 frequency, struct netlink_ext_ack *extack) +{ + return ice_dpll_frequency_set(pin, pin_priv, dpll, dpll_priv, frequency, + extack, ICE_DPLL_PIN_TYPE_OUTPUT); +} + +/** + * ice_dpll_frequency_get - wrapper for pin callback for get frequency + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: pointer to dpll + * @dpll_priv: private data pointer passed on dpll registration + * @frequency: on success holds pin's frequency + * @extack: error reporting + * @pin_type: type of pin being configured + * + * Wraps internal get frequency command of a pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error pin not found or couldn't get from hw + */ +static int +ice_dpll_frequency_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u64 *frequency, struct netlink_ext_ack *extack, + enum ice_dpll_pin_type pin_type) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + + mutex_lock(&pf->dplls.lock); + *frequency = p->freq; + mutex_unlock(&pf->dplls.lock); + + return 0; +} + +/** + * ice_dpll_input_frequency_get - input pin callback for get frequency + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: pointer to dpll + * @dpll_priv: private data pointer passed on dpll registration + * @frequency: on success holds pin's frequency + * @extack: error reporting + * + * Wraps internal get frequency command of a input pin. + * + * Context: Calls a function which acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error pin not found or couldn't get from hw + */ +static int +ice_dpll_input_frequency_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u64 *frequency, struct netlink_ext_ack *extack) +{ + return ice_dpll_frequency_get(pin, pin_priv, dpll, dpll_priv, frequency, + extack, ICE_DPLL_PIN_TYPE_INPUT); +} + +/** + * ice_dpll_output_frequency_get - output pin callback for get frequency + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: pointer to dpll + * @dpll_priv: private data pointer passed on dpll registration + * @frequency: on success holds pin's frequency + * @extack: error reporting + * + * Wraps internal get frequency command of a pin. + * + * Context: Calls a function which acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error pin not found or couldn't get from hw + */ +static int +ice_dpll_output_frequency_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u64 *frequency, struct netlink_ext_ack *extack) +{ + return ice_dpll_frequency_get(pin, pin_priv, dpll, dpll_priv, frequency, + extack, ICE_DPLL_PIN_TYPE_OUTPUT); +} + +/** + * ice_dpll_pin_enable - enable a pin on dplls + * @hw: board private hw structure + * @pin: pointer to a pin + * @pin_type: type of pin being enabled + * @extack: error reporting + * + * Enable a pin on both dplls. Store current state in pin->flags. + * + * Context: Called under pf->dplls.lock + * Return: + * * 0 - OK + * * negative - error + */ +static int +ice_dpll_pin_enable(struct ice_hw *hw, struct ice_dpll_pin *pin, + enum ice_dpll_pin_type pin_type, + struct netlink_ext_ack *extack) +{ + u8 flags = 0; + int ret; + + switch (pin_type) { + case ICE_DPLL_PIN_TYPE_INPUT: + if (pin->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_ESYNC_EN) + flags |= ICE_AQC_SET_CGU_IN_CFG_FLG2_ESYNC_EN; + flags |= ICE_AQC_SET_CGU_IN_CFG_FLG2_INPUT_EN; + ret = ice_aq_set_input_pin_cfg(hw, pin->idx, 0, flags, 0, 0); + break; + case ICE_DPLL_PIN_TYPE_OUTPUT: + if (pin->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_EN) + flags |= ICE_AQC_SET_CGU_OUT_CFG_ESYNC_EN; + flags |= ICE_AQC_SET_CGU_OUT_CFG_OUT_EN; + ret = ice_aq_set_output_pin_cfg(hw, pin->idx, flags, 0, 0, 0); + break; + default: + return -EINVAL; + } + if (ret) + NL_SET_ERR_MSG_FMT(extack, + "err:%d %s failed to enable %s pin:%u\n", + ret, ice_aq_str(hw->adminq.sq_last_status), + pin_type_name[pin_type], pin->idx); + + return ret; +} + +/** + * ice_dpll_pin_disable - disable a pin on dplls + * @hw: board private hw structure + * @pin: pointer to a pin + * @pin_type: type of pin being disabled + * @extack: error reporting + * + * Disable a pin on both dplls. Store current state in pin->flags. + * + * Context: Called under pf->dplls.lock + * Return: + * * 0 - OK + * * negative - error + */ +static int +ice_dpll_pin_disable(struct ice_hw *hw, struct ice_dpll_pin *pin, + enum ice_dpll_pin_type pin_type, + struct netlink_ext_ack *extack) +{ + u8 flags = 0; + int ret; + + switch (pin_type) { + case ICE_DPLL_PIN_TYPE_INPUT: + if (pin->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_ESYNC_EN) + flags |= ICE_AQC_SET_CGU_IN_CFG_FLG2_ESYNC_EN; + ret = ice_aq_set_input_pin_cfg(hw, pin->idx, 0, flags, 0, 0); + break; + case ICE_DPLL_PIN_TYPE_OUTPUT: + if (pin->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_EN) + flags |= ICE_AQC_SET_CGU_OUT_CFG_ESYNC_EN; + ret = ice_aq_set_output_pin_cfg(hw, pin->idx, flags, 0, 0, 0); + break; + default: + return -EINVAL; + } + if (ret) + NL_SET_ERR_MSG_FMT(extack, + "err:%d %s failed to disable %s pin:%u\n", + ret, ice_aq_str(hw->adminq.sq_last_status), + pin_type_name[pin_type], pin->idx); + + return ret; +} + +/** + * ice_dpll_pin_state_update - update pin's state + * @pf: private board struct + * @pin: structure with pin attributes to be updated + * @pin_type: type of pin being updated + * @extack: error reporting + * + * Determine pin current state and frequency, then update struct + * holding the pin info. For input pin states are separated for each + * dpll, for rclk pins states are separated for each parent. + * + * Context: Called under pf->dplls.lock + * Return: + * * 0 - OK + * * negative - error + */ +static int +ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin, + enum ice_dpll_pin_type pin_type, + struct netlink_ext_ack *extack) +{ + u8 parent, port_num = ICE_AQC_SET_PHY_REC_CLK_OUT_CURR_PORT; + int ret; + + switch (pin_type) { + case ICE_DPLL_PIN_TYPE_INPUT: + ret = ice_aq_get_input_pin_cfg(&pf->hw, pin->idx, NULL, NULL, + NULL, &pin->flags[0], + &pin->freq, NULL); + if (ret) + goto err; + if (ICE_AQC_GET_CGU_IN_CFG_FLG2_INPUT_EN & pin->flags[0]) { + if (pin->pin) { + pin->state[pf->dplls.eec.dpll_idx] = + pin->pin == pf->dplls.eec.active_input ? + DPLL_PIN_STATE_CONNECTED : + DPLL_PIN_STATE_SELECTABLE; + pin->state[pf->dplls.pps.dpll_idx] = + pin->pin == pf->dplls.pps.active_input ? + DPLL_PIN_STATE_CONNECTED : + DPLL_PIN_STATE_SELECTABLE; + } else { + pin->state[pf->dplls.eec.dpll_idx] = + DPLL_PIN_STATE_SELECTABLE; + pin->state[pf->dplls.pps.dpll_idx] = + DPLL_PIN_STATE_SELECTABLE; + } + } else { + pin->state[pf->dplls.eec.dpll_idx] = + DPLL_PIN_STATE_DISCONNECTED; + pin->state[pf->dplls.pps.dpll_idx] = + DPLL_PIN_STATE_DISCONNECTED; + } + break; + case ICE_DPLL_PIN_TYPE_OUTPUT: + ret = ice_aq_get_output_pin_cfg(&pf->hw, pin->idx, + &pin->flags[0], NULL, + &pin->freq, NULL); + if (ret) + goto err; + if (ICE_AQC_SET_CGU_OUT_CFG_OUT_EN & pin->flags[0]) + pin->state[0] = DPLL_PIN_STATE_CONNECTED; + else + pin->state[0] = DPLL_PIN_STATE_DISCONNECTED; + break; + case ICE_DPLL_PIN_TYPE_RCLK_INPUT: + for (parent = 0; parent < pf->dplls.rclk.num_parents; + parent++) { + u8 p = parent; + + ret = ice_aq_get_phy_rec_clk_out(&pf->hw, &p, + &port_num, + &pin->flags[parent], + NULL); + if (ret) + goto err; + if (ICE_AQC_GET_PHY_REC_CLK_OUT_OUT_EN & + pin->flags[parent]) + pin->state[parent] = DPLL_PIN_STATE_CONNECTED; + else + pin->state[parent] = + DPLL_PIN_STATE_DISCONNECTED; + } + break; + default: + return -EINVAL; + } + + return 0; +err: + if (extack) + NL_SET_ERR_MSG_FMT(extack, + "err:%d %s failed to update %s pin:%u\n", + ret, + ice_aq_str(pf->hw.adminq.sq_last_status), + pin_type_name[pin_type], pin->idx); + else + dev_err_ratelimited(ice_pf_to_dev(pf), + "err:%d %s failed to update %s pin:%u\n", + ret, + ice_aq_str(pf->hw.adminq.sq_last_status), + pin_type_name[pin_type], pin->idx); + return ret; +} + +/** + * ice_dpll_hw_input_prio_set - set input priority value in hardware + * @pf: board private structure + * @dpll: ice dpll pointer + * @pin: ice pin pointer + * @prio: priority value being set on a dpll + * @extack: error reporting + * + * Internal wrapper for setting the priority in the hardware. + * + * Context: Called under pf->dplls.lock + * Return: + * * 0 - success + * * negative - failure + */ +static int +ice_dpll_hw_input_prio_set(struct ice_pf *pf, struct ice_dpll *dpll, + struct ice_dpll_pin *pin, const u32 prio, + struct netlink_ext_ack *extack) +{ + int ret; + + ret = ice_aq_set_cgu_ref_prio(&pf->hw, dpll->dpll_idx, pin->idx, + (u8)prio); + if (ret) + NL_SET_ERR_MSG_FMT(extack, + "err:%d %s failed to set pin prio:%u on pin:%u\n", + ret, + ice_aq_str(pf->hw.adminq.sq_last_status), + prio, pin->idx); + else + dpll->input_prio[pin->idx] = prio; + + return ret; +} + +/** + * ice_dpll_lock_status_get - get dpll lock status callback + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @status: on success holds dpll's lock status + * @extack: error reporting + * + * Dpll subsystem callback, provides dpll's lock status. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - failure + */ +static int +ice_dpll_lock_status_get(const struct dpll_device *dpll, void *dpll_priv, + enum dpll_lock_status *status, + struct netlink_ext_ack *extack) +{ + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + + mutex_lock(&pf->dplls.lock); + *status = d->dpll_state; + mutex_unlock(&pf->dplls.lock); + + return 0; +} + +/** + * ice_dpll_mode_supported - check if dpll's working mode is supported + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @mode: mode to be checked for support + * @extack: error reporting + * + * Dpll subsystem callback. Provides information if working mode is supported + * by dpll. + * + * Return: + * * true - mode is supported + * * false - mode is not supported + */ +static bool ice_dpll_mode_supported(const struct dpll_device *dpll, + void *dpll_priv, + enum dpll_mode mode, + struct netlink_ext_ack *extack) +{ + if (mode == DPLL_MODE_AUTOMATIC) + return true; + + return false; +} + +/** + * ice_dpll_mode_get - get dpll's working mode + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @mode: on success holds current working mode of dpll + * @extack: error reporting + * + * Dpll subsystem callback. Provides working mode of dpll. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - failure + */ +static int ice_dpll_mode_get(const struct dpll_device *dpll, void *dpll_priv, + enum dpll_mode *mode, + struct netlink_ext_ack *extack) +{ + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + + mutex_lock(&pf->dplls.lock); + *mode = d->mode; + mutex_unlock(&pf->dplls.lock); + + return 0; +} + +/** + * ice_dpll_pin_state_set - set pin's state on dpll + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @enable: if pin shalll be enabled + * @extack: error reporting + * @pin_type: type of a pin + * + * Set pin state on a pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - OK or no change required + * * negative - error + */ +static int +ice_dpll_pin_state_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + bool enable, struct netlink_ext_ack *extack, + enum ice_dpll_pin_type pin_type) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + int ret; + + mutex_lock(&pf->dplls.lock); + if (enable) + ret = ice_dpll_pin_enable(&pf->hw, p, pin_type, extack); + else + ret = ice_dpll_pin_disable(&pf->hw, p, pin_type, extack); + if (!ret) + ret = ice_dpll_pin_state_update(pf, p, pin_type, extack); + mutex_unlock(&pf->dplls.lock); + + return ret; +} + +/** + * ice_dpll_output_state_set - enable/disable output pin on dpll device + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: dpll being configured + * @dpll_priv: private data pointer passed on dpll registration + * @state: state of pin to be set + * @extack: error reporting + * + * Dpll subsystem callback. Set given state on output type pin. + * + * Context: Calls a function which acquires pf->dplls.lock + * Return: + * * 0 - successfully enabled mode + * * negative - failed to enable mode + */ +static int +ice_dpll_output_state_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + enum dpll_pin_state state, + struct netlink_ext_ack *extack) +{ + bool enable = state == DPLL_PIN_STATE_CONNECTED; + + return ice_dpll_pin_state_set(pin, pin_priv, dpll, dpll_priv, enable, + extack, ICE_DPLL_PIN_TYPE_OUTPUT); +} + +/** + * ice_dpll_input_state_set - enable/disable input pin on dpll levice + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: dpll being configured + * @dpll_priv: private data pointer passed on dpll registration + * @state: state of pin to be set + * @extack: error reporting + * + * Dpll subsystem callback. Enables given mode on input type pin. + * + * Context: Calls a function which acquires pf->dplls.lock + * Return: + * * 0 - successfully enabled mode + * * negative - failed to enable mode + */ +static int +ice_dpll_input_state_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + enum dpll_pin_state state, + struct netlink_ext_ack *extack) +{ + bool enable = state == DPLL_PIN_STATE_SELECTABLE; + + return ice_dpll_pin_state_set(pin, pin_priv, dpll, dpll_priv, enable, + extack, ICE_DPLL_PIN_TYPE_INPUT); +} + +/** + * ice_dpll_pin_state_get - set pin's state on dpll + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @state: on success holds state of the pin + * @extack: error reporting + * @pin_type: type of questioned pin + * + * Determine pin state set it on a pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - failed to get state + */ +static int +ice_dpll_pin_state_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + enum dpll_pin_state *state, + struct netlink_ext_ack *extack, + enum ice_dpll_pin_type pin_type) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + int ret; + + mutex_lock(&pf->dplls.lock); + ret = ice_dpll_pin_state_update(pf, p, pin_type, extack); + if (ret) + goto unlock; + if (pin_type == ICE_DPLL_PIN_TYPE_INPUT) + *state = p->state[d->dpll_idx]; + else if (pin_type == ICE_DPLL_PIN_TYPE_OUTPUT) + *state = p->state[0]; + ret = 0; +unlock: + mutex_unlock(&pf->dplls.lock); + + return ret; +} + +/** + * ice_dpll_output_state_get - get output pin state on dpll device + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @state: on success holds state of the pin + * @extack: error reporting + * + * Dpll subsystem callback. Check state of a pin. + * + * Context: Calls a function which acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - failed to get state + */ +static int +ice_dpll_output_state_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + enum dpll_pin_state *state, + struct netlink_ext_ack *extack) +{ + return ice_dpll_pin_state_get(pin, pin_priv, dpll, dpll_priv, state, + extack, ICE_DPLL_PIN_TYPE_OUTPUT); +} + +/** + * ice_dpll_input_state_get - get input pin state on dpll device + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @state: on success holds state of the pin + * @extack: error reporting + * + * Dpll subsystem callback. Check state of a input pin. + * + * Context: Calls a function which acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - failed to get state + */ +static int +ice_dpll_input_state_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + enum dpll_pin_state *state, + struct netlink_ext_ack *extack) +{ + return ice_dpll_pin_state_get(pin, pin_priv, dpll, dpll_priv, state, + extack, ICE_DPLL_PIN_TYPE_INPUT); +} + +/** + * ice_dpll_input_prio_get - get dpll's input prio + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @prio: on success - returns input priority on dpll + * @extack: error reporting + * + * Dpll subsystem callback. Handler for getting priority of a input pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - failure + */ +static int +ice_dpll_input_prio_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u32 *prio, struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + + mutex_lock(&pf->dplls.lock); + *prio = d->input_prio[p->idx]; + mutex_unlock(&pf->dplls.lock); + + return 0; +} + +/** + * ice_dpll_input_prio_set - set dpll input prio + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @prio: input priority to be set on dpll + * @extack: error reporting + * + * Dpll subsystem callback. Handler for setting priority of a input pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - failure + */ +static int +ice_dpll_input_prio_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u32 prio, struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + int ret; + + mutex_lock(&pf->dplls.lock); + ret = ice_dpll_hw_input_prio_set(pf, d, p, prio, extack); + mutex_unlock(&pf->dplls.lock); + + return ret; +} + +/** + * ice_dpll_input_direction - callback for get input pin direction + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @direction: holds input pin direction + * @extack: error reporting + * + * Dpll subsystem callback. Handler for getting direction of a input pin. + * + * Return: + * * 0 - success + */ +static int +ice_dpll_input_direction(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + enum dpll_pin_direction *direction, + struct netlink_ext_ack *extack) +{ + *direction = DPLL_PIN_DIRECTION_INPUT; + + return 0; +} + +/** + * ice_dpll_output_direction - callback for get output pin direction + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @direction: holds output pin direction + * @extack: error reporting + * + * Dpll subsystem callback. Handler for getting direction of an output pin. + * + * Return: + * * 0 - success + */ +static int +ice_dpll_output_direction(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + enum dpll_pin_direction *direction, + struct netlink_ext_ack *extack) +{ + *direction = DPLL_PIN_DIRECTION_OUTPUT; + + return 0; +} + +/** + * ice_dpll_pin_phase_adjust_get - callback for get pin phase adjust value + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @phase_adjust: on success holds pin phase_adjust value + * @extack: error reporting + * + * Dpll subsystem callback. Handler for getting phase adjust value of a pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_pin_phase_adjust_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + s32 *phase_adjust, + struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_pf *pf = p->pf; + + mutex_lock(&pf->dplls.lock); + *phase_adjust = p->phase_adjust; + mutex_unlock(&pf->dplls.lock); + + return 0; +} + +/** + * ice_dpll_pin_phase_adjust_set - helper for setting a pin phase adjust value + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @phase_adjust: phase_adjust to be set + * @extack: error reporting + * @type: type of a pin + * + * Helper for dpll subsystem callback. Handler for setting phase adjust value + * of a pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_pin_phase_adjust_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + s32 phase_adjust, + struct netlink_ext_ack *extack, + enum ice_dpll_pin_type type) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + u8 flag, flags_en = 0; + int ret; + + mutex_lock(&pf->dplls.lock); + switch (type) { + case ICE_DPLL_PIN_TYPE_INPUT: + flag = ICE_AQC_SET_CGU_IN_CFG_FLG1_UPDATE_DELAY; + if (p->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_ESYNC_EN) + flags_en |= ICE_AQC_SET_CGU_IN_CFG_FLG2_ESYNC_EN; + if (p->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_INPUT_EN) + flags_en |= ICE_AQC_SET_CGU_IN_CFG_FLG2_INPUT_EN; + ret = ice_aq_set_input_pin_cfg(&pf->hw, p->idx, flag, flags_en, + 0, phase_adjust); + break; + case ICE_DPLL_PIN_TYPE_OUTPUT: + flag = ICE_AQC_SET_CGU_OUT_CFG_UPDATE_PHASE; + if (p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_OUT_EN) + flag |= ICE_AQC_SET_CGU_OUT_CFG_OUT_EN; + if (p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_EN) + flag |= ICE_AQC_SET_CGU_OUT_CFG_ESYNC_EN; + ret = ice_aq_set_output_pin_cfg(&pf->hw, p->idx, flag, 0, 0, + phase_adjust); + break; + default: + ret = -EINVAL; + } + if (!ret) + p->phase_adjust = phase_adjust; + mutex_unlock(&pf->dplls.lock); + if (ret) + NL_SET_ERR_MSG_FMT(extack, + "err:%d %s failed to set pin phase_adjust:%d for pin:%u on dpll:%u\n", + ret, + ice_aq_str(pf->hw.adminq.sq_last_status), + phase_adjust, p->idx, d->dpll_idx); + + return ret; +} + +/** + * ice_dpll_input_phase_adjust_set - callback for set input pin phase adjust + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @phase_adjust: phase_adjust to be set + * @extack: error reporting + * + * Dpll subsystem callback. Wraps a handler for setting phase adjust on input + * pin. + * + * Context: Calls a function which acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_input_phase_adjust_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + s32 phase_adjust, + struct netlink_ext_ack *extack) +{ + return ice_dpll_pin_phase_adjust_set(pin, pin_priv, dpll, dpll_priv, + phase_adjust, extack, + ICE_DPLL_PIN_TYPE_INPUT); +} + +/** + * ice_dpll_output_phase_adjust_set - callback for set output pin phase adjust + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @phase_adjust: phase_adjust to be set + * @extack: error reporting + * + * Dpll subsystem callback. Wraps a handler for setting phase adjust on output + * pin. + * + * Context: Calls a function which acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_output_phase_adjust_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + s32 phase_adjust, + struct netlink_ext_ack *extack) +{ + return ice_dpll_pin_phase_adjust_set(pin, pin_priv, dpll, dpll_priv, + phase_adjust, extack, + ICE_DPLL_PIN_TYPE_OUTPUT); +} + +#define ICE_DPLL_PHASE_OFFSET_DIVIDER 100 +#define ICE_DPLL_PHASE_OFFSET_FACTOR \ + (DPLL_PHASE_OFFSET_DIVIDER / ICE_DPLL_PHASE_OFFSET_DIVIDER) +/** + * ice_dpll_phase_offset_get - callback for get dpll phase shift value + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @phase_offset: on success holds pin phase_offset value + * @extack: error reporting + * + * Dpll subsystem callback. Handler for getting phase shift value between + * dpll's input and output. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_phase_offset_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + s64 *phase_offset, struct netlink_ext_ack *extack) +{ + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + + mutex_lock(&pf->dplls.lock); + if (d->active_input == pin) + *phase_offset = d->phase_offset * ICE_DPLL_PHASE_OFFSET_FACTOR; + else + *phase_offset = 0; + mutex_unlock(&pf->dplls.lock); + + return 0; +} + +/** + * ice_dpll_rclk_state_on_pin_set - set a state on rclk pin + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @parent_pin: pin parent pointer + * @parent_pin_priv: parent private data pointer passed on pin registration + * @state: state to be set on pin + * @extack: error reporting + * + * Dpll subsystem callback, set a state of a rclk pin on a parent pin + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - failure + */ +static int +ice_dpll_rclk_state_on_pin_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_pin *parent_pin, + void *parent_pin_priv, + enum dpll_pin_state state, + struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv, *parent = parent_pin_priv; + bool enable = state == DPLL_PIN_STATE_CONNECTED; + struct ice_pf *pf = p->pf; + int ret = -EINVAL; + u32 hw_idx; + + mutex_lock(&pf->dplls.lock); + hw_idx = parent->idx - pf->dplls.base_rclk_idx; + if (hw_idx >= pf->dplls.num_inputs) + goto unlock; + + if ((enable && p->state[hw_idx] == DPLL_PIN_STATE_CONNECTED) || + (!enable && p->state[hw_idx] == DPLL_PIN_STATE_DISCONNECTED)) { + NL_SET_ERR_MSG_FMT(extack, + "pin:%u state:%u on parent:%u already set", + p->idx, state, parent->idx); + goto unlock; + } + ret = ice_aq_set_phy_rec_clk_out(&pf->hw, hw_idx, enable, + &p->freq); + if (ret) + NL_SET_ERR_MSG_FMT(extack, + "err:%d %s failed to set pin state:%u for pin:%u on parent:%u\n", + ret, + ice_aq_str(pf->hw.adminq.sq_last_status), + state, p->idx, parent->idx); +unlock: + mutex_unlock(&pf->dplls.lock); + + return ret; +} + +/** + * ice_dpll_rclk_state_on_pin_get - get a state of rclk pin + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @parent_pin: pin parent pointer + * @parent_pin_priv: pin parent priv data pointer passed on pin registration + * @state: on success holds pin state on parent pin + * @extack: error reporting + * + * dpll subsystem callback, get a state of a recovered clock pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - failure + */ +static int +ice_dpll_rclk_state_on_pin_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_pin *parent_pin, + void *parent_pin_priv, + enum dpll_pin_state *state, + struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv, *parent = parent_pin_priv; + struct ice_pf *pf = p->pf; + int ret = -EINVAL; + u32 hw_idx; + + mutex_lock(&pf->dplls.lock); + hw_idx = parent->idx - pf->dplls.base_rclk_idx; + if (hw_idx >= pf->dplls.num_inputs) + goto unlock; + + ret = ice_dpll_pin_state_update(pf, p, ICE_DPLL_PIN_TYPE_RCLK_INPUT, + extack); + if (ret) + goto unlock; + + *state = p->state[hw_idx]; + ret = 0; +unlock: + mutex_unlock(&pf->dplls.lock); + + return ret; +} + +static const struct dpll_pin_ops ice_dpll_rclk_ops = { + .state_on_pin_set = ice_dpll_rclk_state_on_pin_set, + .state_on_pin_get = ice_dpll_rclk_state_on_pin_get, + .direction_get = ice_dpll_input_direction, +}; + +static const struct dpll_pin_ops ice_dpll_input_ops = { + .frequency_get = ice_dpll_input_frequency_get, + .frequency_set = ice_dpll_input_frequency_set, + .state_on_dpll_get = ice_dpll_input_state_get, + .state_on_dpll_set = ice_dpll_input_state_set, + .prio_get = ice_dpll_input_prio_get, + .prio_set = ice_dpll_input_prio_set, + .direction_get = ice_dpll_input_direction, + .phase_adjust_get = ice_dpll_pin_phase_adjust_get, + .phase_adjust_set = ice_dpll_input_phase_adjust_set, + .phase_offset_get = ice_dpll_phase_offset_get, +}; + +static const struct dpll_pin_ops ice_dpll_output_ops = { + .frequency_get = ice_dpll_output_frequency_get, + .frequency_set = ice_dpll_output_frequency_set, + .state_on_dpll_get = ice_dpll_output_state_get, + .state_on_dpll_set = ice_dpll_output_state_set, + .direction_get = ice_dpll_output_direction, + .phase_adjust_get = ice_dpll_pin_phase_adjust_get, + .phase_adjust_set = ice_dpll_output_phase_adjust_set, +}; + +static const struct dpll_device_ops ice_dpll_ops = { + .lock_status_get = ice_dpll_lock_status_get, + .mode_supported = ice_dpll_mode_supported, + .mode_get = ice_dpll_mode_get, +}; + +/** + * ice_generate_clock_id - generates unique clock_id for registering dpll. + * @pf: board private structure + * + * Generates unique (per board) clock_id for allocation and search of dpll + * devices in Linux dpll subsystem. + * + * Return: generated clock id for the board + */ +static u64 ice_generate_clock_id(struct ice_pf *pf) +{ + return pci_get_dsn(pf->pdev); +} + +/** + * ice_dpll_notify_changes - notify dpll subsystem about changes + * @d: pointer do dpll + * + * Once change detected appropriate event is submitted to the dpll subsystem. + */ +static void ice_dpll_notify_changes(struct ice_dpll *d) +{ + bool pin_notified = false; + + if (d->prev_dpll_state != d->dpll_state) { + d->prev_dpll_state = d->dpll_state; + dpll_device_change_ntf(d->dpll); + } + if (d->prev_input != d->active_input) { + if (d->prev_input) + dpll_pin_change_ntf(d->prev_input); + d->prev_input = d->active_input; + if (d->active_input) { + dpll_pin_change_ntf(d->active_input); + pin_notified = true; + } + } + if (d->prev_phase_offset != d->phase_offset) { + d->prev_phase_offset = d->phase_offset; + if (!pin_notified && d->active_input) + dpll_pin_change_ntf(d->active_input); + } +} + +/** + * ice_dpll_update_state - update dpll state + * @pf: pf private structure + * @d: pointer to queried dpll device + * @init: if function called on initialization of ice dpll + * + * Poll current state of dpll from hw and update ice_dpll struct. + * + * Context: Called by kworker under pf->dplls.lock + * Return: + * * 0 - success + * * negative - AQ failure + */ +static int +ice_dpll_update_state(struct ice_pf *pf, struct ice_dpll *d, bool init) +{ + struct ice_dpll_pin *p = NULL; + int ret; + + ret = ice_get_cgu_state(&pf->hw, d->dpll_idx, d->prev_dpll_state, + &d->input_idx, &d->ref_state, &d->eec_mode, + &d->phase_offset, &d->dpll_state); + + dev_dbg(ice_pf_to_dev(pf), + "update dpll=%d, prev_src_idx:%u, src_idx:%u, state:%d, prev:%d mode:%d\n", + d->dpll_idx, d->prev_input_idx, d->input_idx, + d->dpll_state, d->prev_dpll_state, d->mode); + if (ret) { + dev_err(ice_pf_to_dev(pf), + "update dpll=%d state failed, ret=%d %s\n", + d->dpll_idx, ret, + ice_aq_str(pf->hw.adminq.sq_last_status)); + return ret; + } + if (init) { + if (d->dpll_state == DPLL_LOCK_STATUS_LOCKED || + d->dpll_state == DPLL_LOCK_STATUS_LOCKED_HO_ACQ) + d->active_input = pf->dplls.inputs[d->input_idx].pin; + p = &pf->dplls.inputs[d->input_idx]; + return ice_dpll_pin_state_update(pf, p, + ICE_DPLL_PIN_TYPE_INPUT, NULL); + } + if (d->dpll_state == DPLL_LOCK_STATUS_HOLDOVER || + d->dpll_state == DPLL_LOCK_STATUS_UNLOCKED) { + d->active_input = NULL; + if (d->input_idx != ICE_DPLL_PIN_IDX_INVALID) + p = &pf->dplls.inputs[d->input_idx]; + d->prev_input_idx = ICE_DPLL_PIN_IDX_INVALID; + d->input_idx = ICE_DPLL_PIN_IDX_INVALID; + if (!p) + return 0; + ret = ice_dpll_pin_state_update(pf, p, + ICE_DPLL_PIN_TYPE_INPUT, NULL); + } else if (d->input_idx != d->prev_input_idx) { + if (d->prev_input_idx != ICE_DPLL_PIN_IDX_INVALID) { + p = &pf->dplls.inputs[d->prev_input_idx]; + ice_dpll_pin_state_update(pf, p, + ICE_DPLL_PIN_TYPE_INPUT, + NULL); + } + if (d->input_idx != ICE_DPLL_PIN_IDX_INVALID) { + p = &pf->dplls.inputs[d->input_idx]; + d->active_input = p->pin; + ice_dpll_pin_state_update(pf, p, + ICE_DPLL_PIN_TYPE_INPUT, + NULL); + } + d->prev_input_idx = d->input_idx; + } + + return ret; +} + +/** + * ice_dpll_periodic_work - DPLLs periodic worker + * @work: pointer to kthread_work structure + * + * DPLLs periodic worker is responsible for polling state of dpll. + * Context: Holds pf->dplls.lock + */ +static void ice_dpll_periodic_work(struct kthread_work *work) +{ + struct ice_dplls *d = container_of(work, struct ice_dplls, work.work); + struct ice_pf *pf = container_of(d, struct ice_pf, dplls); + struct ice_dpll *de = &pf->dplls.eec; + struct ice_dpll *dp = &pf->dplls.pps; + int ret; + + mutex_lock(&pf->dplls.lock); + ret = ice_dpll_update_state(pf, de, false); + if (!ret) + ret = ice_dpll_update_state(pf, dp, false); + if (ret) { + d->cgu_state_acq_err_num++; + /* stop rescheduling this worker */ + if (d->cgu_state_acq_err_num > + ICE_CGU_STATE_ACQ_ERR_THRESHOLD) { + dev_err(ice_pf_to_dev(pf), + "EEC/PPS DPLLs periodic work disabled\n"); + mutex_unlock(&pf->dplls.lock); + return; + } + } + mutex_unlock(&pf->dplls.lock); + ice_dpll_notify_changes(de); + ice_dpll_notify_changes(dp); + + /* Run twice a second or reschedule if update failed */ + kthread_queue_delayed_work(d->kworker, &d->work, + ret ? msecs_to_jiffies(10) : + msecs_to_jiffies(500)); +} + +/** + * ice_dpll_release_pins - release pins resources from dpll subsystem + * @pins: pointer to pins array + * @count: number of pins + * + * Release resources of given pins array in the dpll subsystem. + */ +static void ice_dpll_release_pins(struct ice_dpll_pin *pins, int count) +{ + int i; + + for (i = 0; i < count; i++) + dpll_pin_put(pins[i].pin); +} + +/** + * ice_dpll_get_pins - get pins from dpll subsystem + * @pf: board private structure + * @pins: pointer to pins array + * @start_idx: get starts from this pin idx value + * @count: number of pins + * @clock_id: clock_id of dpll device + * + * Get pins - allocate - in dpll subsystem, store them in pin field of given + * pins array. + * + * Return: + * * 0 - success + * * negative - allocation failure reason + */ +static int +ice_dpll_get_pins(struct ice_pf *pf, struct ice_dpll_pin *pins, + int start_idx, int count, u64 clock_id) +{ + int i, ret; + + for (i = 0; i < count; i++) { + pins[i].pin = dpll_pin_get(clock_id, i + start_idx, THIS_MODULE, + &pins[i].prop); + if (IS_ERR(pins[i].pin)) { + ret = PTR_ERR(pins[i].pin); + goto release_pins; + } + } + + return 0; + +release_pins: + while (--i >= 0) + dpll_pin_put(pins[i].pin); + return ret; +} + +/** + * ice_dpll_unregister_pins - unregister pins from a dpll + * @dpll: dpll device pointer + * @pins: pointer to pins array + * @ops: callback ops registered with the pins + * @count: number of pins + * + * Unregister pins of a given array of pins from given dpll device registered in + * dpll subsystem. + */ +static void +ice_dpll_unregister_pins(struct dpll_device *dpll, struct ice_dpll_pin *pins, + const struct dpll_pin_ops *ops, int count) +{ + int i; + + for (i = 0; i < count; i++) + dpll_pin_unregister(dpll, pins[i].pin, ops, &pins[i]); +} + +/** + * ice_dpll_register_pins - register pins with a dpll + * @dpll: dpll pointer to register pins with + * @pins: pointer to pins array + * @ops: callback ops registered with the pins + * @count: number of pins + * + * Register pins of a given array with given dpll in dpll subsystem. + * + * Return: + * * 0 - success + * * negative - registration failure reason + */ +static int +ice_dpll_register_pins(struct dpll_device *dpll, struct ice_dpll_pin *pins, + const struct dpll_pin_ops *ops, int count) +{ + int ret, i; + + for (i = 0; i < count; i++) { + ret = dpll_pin_register(dpll, pins[i].pin, ops, &pins[i]); + if (ret) + goto unregister_pins; + } + + return 0; + +unregister_pins: + while (--i >= 0) + dpll_pin_unregister(dpll, pins[i].pin, ops, &pins[i]); + return ret; +} + +/** + * ice_dpll_deinit_direct_pins - deinitialize direct pins + * @cgu: if cgu is present and controlled by this NIC + * @pins: pointer to pins array + * @count: number of pins + * @ops: callback ops registered with the pins + * @first: dpll device pointer + * @second: dpll device pointer + * + * If cgu is owned unregister pins from given dplls. + * Release pins resources to the dpll subsystem. + */ +static void +ice_dpll_deinit_direct_pins(bool cgu, struct ice_dpll_pin *pins, int count, + const struct dpll_pin_ops *ops, + struct dpll_device *first, + struct dpll_device *second) +{ + if (cgu) { + ice_dpll_unregister_pins(first, pins, ops, count); + ice_dpll_unregister_pins(second, pins, ops, count); + } + ice_dpll_release_pins(pins, count); +} + +/** + * ice_dpll_init_direct_pins - initialize direct pins + * @pf: board private structure + * @cgu: if cgu is present and controlled by this NIC + * @pins: pointer to pins array + * @start_idx: on which index shall allocation start in dpll subsystem + * @count: number of pins + * @ops: callback ops registered with the pins + * @first: dpll device pointer + * @second: dpll device pointer + * + * Allocate directly connected pins of a given array in dpll subsystem. + * If cgu is owned register allocated pins with given dplls. + * + * Return: + * * 0 - success + * * negative - registration failure reason + */ +static int +ice_dpll_init_direct_pins(struct ice_pf *pf, bool cgu, + struct ice_dpll_pin *pins, int start_idx, int count, + const struct dpll_pin_ops *ops, + struct dpll_device *first, struct dpll_device *second) +{ + int ret; + + ret = ice_dpll_get_pins(pf, pins, start_idx, count, pf->dplls.clock_id); + if (ret) + return ret; + if (cgu) { + ret = ice_dpll_register_pins(first, pins, ops, count); + if (ret) + goto release_pins; + ret = ice_dpll_register_pins(second, pins, ops, count); + if (ret) + goto unregister_first; + } + + return 0; + +unregister_first: + ice_dpll_unregister_pins(first, pins, ops, count); +release_pins: + ice_dpll_release_pins(pins, count); + return ret; +} + +/** + * ice_dpll_deinit_rclk_pin - release rclk pin resources + * @pf: board private structure + * + * Deregister rclk pin from parent pins and release resources in dpll subsystem. + */ +static void ice_dpll_deinit_rclk_pin(struct ice_pf *pf) +{ + struct ice_dpll_pin *rclk = &pf->dplls.rclk; + struct ice_vsi *vsi = ice_get_main_vsi(pf); + struct dpll_pin *parent; + int i; + + for (i = 0; i < rclk->num_parents; i++) { + parent = pf->dplls.inputs[rclk->parent_idx[i]].pin; + if (!parent) + continue; + dpll_pin_on_pin_unregister(parent, rclk->pin, + &ice_dpll_rclk_ops, rclk); + } + if (WARN_ON_ONCE(!vsi || !vsi->netdev)) + return; + netdev_dpll_pin_clear(vsi->netdev); + dpll_pin_put(rclk->pin); +} + +/** + * ice_dpll_init_rclk_pins - initialize recovered clock pin + * @pf: board private structure + * @pin: pin to register + * @start_idx: on which index shall allocation start in dpll subsystem + * @ops: callback ops registered with the pins + * + * Allocate resource for recovered clock pin in dpll subsystem. Register the + * pin with the parents it has in the info. Register pin with the pf's main vsi + * netdev. + * + * Return: + * * 0 - success + * * negative - registration failure reason + */ +static int +ice_dpll_init_rclk_pins(struct ice_pf *pf, struct ice_dpll_pin *pin, + int start_idx, const struct dpll_pin_ops *ops) +{ + struct ice_vsi *vsi = ice_get_main_vsi(pf); + struct dpll_pin *parent; + int ret, i; + + ret = ice_dpll_get_pins(pf, pin, start_idx, ICE_DPLL_RCLK_NUM_PER_PF, + pf->dplls.clock_id); + if (ret) + return ret; + for (i = 0; i < pf->dplls.rclk.num_parents; i++) { + parent = pf->dplls.inputs[pf->dplls.rclk.parent_idx[i]].pin; + if (!parent) { + ret = -ENODEV; + goto unregister_pins; + } + ret = dpll_pin_on_pin_register(parent, pf->dplls.rclk.pin, + ops, &pf->dplls.rclk); + if (ret) + goto unregister_pins; + } + if (WARN_ON((!vsi || !vsi->netdev))) + return -EINVAL; + netdev_dpll_pin_set(vsi->netdev, pf->dplls.rclk.pin); + + return 0; + +unregister_pins: + while (i) { + parent = pf->dplls.inputs[pf->dplls.rclk.parent_idx[--i]].pin; + dpll_pin_on_pin_unregister(parent, pf->dplls.rclk.pin, + &ice_dpll_rclk_ops, &pf->dplls.rclk); + } + ice_dpll_release_pins(pin, ICE_DPLL_RCLK_NUM_PER_PF); + return ret; +} + +/** + * ice_dpll_deinit_pins - deinitialize direct pins + * @pf: board private structure + * @cgu: if cgu is controlled by this pf + * + * If cgu is owned unregister directly connected pins from the dplls. + * Release resources of directly connected pins from the dpll subsystem. + */ +static void ice_dpll_deinit_pins(struct ice_pf *pf, bool cgu) +{ + struct ice_dpll_pin *outputs = pf->dplls.outputs; + struct ice_dpll_pin *inputs = pf->dplls.inputs; + int num_outputs = pf->dplls.num_outputs; + int num_inputs = pf->dplls.num_inputs; + struct ice_dplls *d = &pf->dplls; + struct ice_dpll *de = &d->eec; + struct ice_dpll *dp = &d->pps; + + ice_dpll_deinit_rclk_pin(pf); + if (cgu) { + ice_dpll_unregister_pins(dp->dpll, inputs, &ice_dpll_input_ops, + num_inputs); + ice_dpll_unregister_pins(de->dpll, inputs, &ice_dpll_input_ops, + num_inputs); + } + ice_dpll_release_pins(inputs, num_inputs); + if (cgu) { + ice_dpll_unregister_pins(dp->dpll, outputs, + &ice_dpll_output_ops, num_outputs); + ice_dpll_unregister_pins(de->dpll, outputs, + &ice_dpll_output_ops, num_outputs); + ice_dpll_release_pins(outputs, num_outputs); + } +} + +/** + * ice_dpll_init_pins - init pins and register pins with a dplls + * @pf: board private structure + * @cgu: if cgu is present and controlled by this NIC + * + * Initialize directly connected pf's pins within pf's dplls in a Linux dpll + * subsystem. + * + * Return: + * * 0 - success + * * negative - initialization failure reason + */ +static int ice_dpll_init_pins(struct ice_pf *pf, bool cgu) +{ + u32 rclk_idx; + int ret; + + ret = ice_dpll_init_direct_pins(pf, cgu, pf->dplls.inputs, 0, + pf->dplls.num_inputs, + &ice_dpll_input_ops, + pf->dplls.eec.dpll, pf->dplls.pps.dpll); + if (ret) + return ret; + if (cgu) { + ret = ice_dpll_init_direct_pins(pf, cgu, pf->dplls.outputs, + pf->dplls.num_inputs, + pf->dplls.num_outputs, + &ice_dpll_output_ops, + pf->dplls.eec.dpll, + pf->dplls.pps.dpll); + if (ret) + goto deinit_inputs; + } + rclk_idx = pf->dplls.num_inputs + pf->dplls.num_outputs + pf->hw.pf_id; + ret = ice_dpll_init_rclk_pins(pf, &pf->dplls.rclk, rclk_idx, + &ice_dpll_rclk_ops); + if (ret) + goto deinit_outputs; + + return 0; +deinit_outputs: + ice_dpll_deinit_direct_pins(cgu, pf->dplls.outputs, + pf->dplls.num_outputs, + &ice_dpll_output_ops, pf->dplls.pps.dpll, + pf->dplls.eec.dpll); +deinit_inputs: + ice_dpll_deinit_direct_pins(cgu, pf->dplls.inputs, pf->dplls.num_inputs, + &ice_dpll_input_ops, pf->dplls.pps.dpll, + pf->dplls.eec.dpll); + return ret; +} + +/** + * ice_dpll_deinit_dpll - deinitialize dpll device + * @pf: board private structure + * @d: pointer to ice_dpll + * @cgu: if cgu is present and controlled by this NIC + * + * If cgu is owned unregister the dpll from dpll subsystem. + * Release resources of dpll device from dpll subsystem. + */ +static void +ice_dpll_deinit_dpll(struct ice_pf *pf, struct ice_dpll *d, bool cgu) +{ + if (cgu) + dpll_device_unregister(d->dpll, &ice_dpll_ops, d); + dpll_device_put(d->dpll); +} + +/** + * ice_dpll_init_dpll - initialize dpll device in dpll subsystem + * @pf: board private structure + * @d: dpll to be initialized + * @cgu: if cgu is present and controlled by this NIC + * @type: type of dpll being initialized + * + * Allocate dpll instance for this board in dpll subsystem, if cgu is controlled + * by this NIC, register dpll with the callback ops. + * + * Return: + * * 0 - success + * * negative - initialization failure reason + */ +static int +ice_dpll_init_dpll(struct ice_pf *pf, struct ice_dpll *d, bool cgu, + enum dpll_type type) +{ + u64 clock_id = pf->dplls.clock_id; + int ret; + + d->dpll = dpll_device_get(clock_id, d->dpll_idx, THIS_MODULE); + if (IS_ERR(d->dpll)) { + ret = PTR_ERR(d->dpll); + dev_err(ice_pf_to_dev(pf), + "dpll_device_get failed (%p) err=%d\n", d, ret); + return ret; + } + d->pf = pf; + if (cgu) { + ice_dpll_update_state(pf, d, true); + ret = dpll_device_register(d->dpll, type, &ice_dpll_ops, d); + if (ret) { + dpll_device_put(d->dpll); + return ret; + } + } + + return 0; +} + +/** + * ice_dpll_deinit_worker - deinitialize dpll kworker + * @pf: board private structure + * + * Stop dpll's kworker, release it's resources. + */ +static void ice_dpll_deinit_worker(struct ice_pf *pf) +{ + struct ice_dplls *d = &pf->dplls; + + kthread_cancel_delayed_work_sync(&d->work); + kthread_destroy_worker(d->kworker); +} + +/** + * ice_dpll_init_worker - Initialize DPLLs periodic worker + * @pf: board private structure + * + * Create and start DPLLs periodic worker. + * + * Context: Shall be called after pf->dplls.lock is initialized. + * Return: + * * 0 - success + * * negative - create worker failure + */ +static int ice_dpll_init_worker(struct ice_pf *pf) +{ + struct ice_dplls *d = &pf->dplls; + struct kthread_worker *kworker; + + kthread_init_delayed_work(&d->work, ice_dpll_periodic_work); + kworker = kthread_create_worker(0, "ice-dplls-%s", + dev_name(ice_pf_to_dev(pf))); + if (IS_ERR(kworker)) + return PTR_ERR(kworker); + d->kworker = kworker; + d->cgu_state_acq_err_num = 0; + kthread_queue_delayed_work(d->kworker, &d->work, 0); + + return 0; +} + +/** + * ice_dpll_init_info_direct_pins - initializes direct pins info + * @pf: board private structure + * @pin_type: type of pins being initialized + * + * Init information for directly connected pins, cache them in pf's pins + * structures. + * + * Return: + * * 0 - success + * * negative - init failure reason + */ +static int +ice_dpll_init_info_direct_pins(struct ice_pf *pf, + enum ice_dpll_pin_type pin_type) +{ + struct ice_dpll *de = &pf->dplls.eec, *dp = &pf->dplls.pps; + int num_pins, i, ret = -EINVAL; + struct ice_hw *hw = &pf->hw; + struct ice_dpll_pin *pins; + unsigned long caps; + u8 freq_supp_num; + bool input; + + switch (pin_type) { + case ICE_DPLL_PIN_TYPE_INPUT: + pins = pf->dplls.inputs; + num_pins = pf->dplls.num_inputs; + input = true; + break; + case ICE_DPLL_PIN_TYPE_OUTPUT: + pins = pf->dplls.outputs; + num_pins = pf->dplls.num_outputs; + input = false; + break; + default: + return -EINVAL; + } + + for (i = 0; i < num_pins; i++) { + caps = 0; + pins[i].idx = i; + pins[i].prop.board_label = ice_cgu_get_pin_name(hw, i, input); + pins[i].prop.type = ice_cgu_get_pin_type(hw, i, input); + if (input) { + ret = ice_aq_get_cgu_ref_prio(hw, de->dpll_idx, i, + &de->input_prio[i]); + if (ret) + return ret; + ret = ice_aq_get_cgu_ref_prio(hw, dp->dpll_idx, i, + &dp->input_prio[i]); + if (ret) + return ret; + caps |= (DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE | + DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE); + pins[i].prop.phase_range.min = + pf->dplls.input_phase_adj_max; + pins[i].prop.phase_range.max = + -pf->dplls.input_phase_adj_max; + } else { + pins[i].prop.phase_range.min = + pf->dplls.output_phase_adj_max; + pins[i].prop.phase_range.max = + -pf->dplls.output_phase_adj_max; + ret = ice_cgu_get_output_pin_state_caps(hw, i, &caps); + if (ret) + return ret; + } + pins[i].prop.capabilities = caps; + ret = ice_dpll_pin_state_update(pf, &pins[i], pin_type, NULL); + if (ret) + return ret; + pins[i].prop.freq_supported = + ice_cgu_get_pin_freq_supp(hw, i, input, &freq_supp_num); + pins[i].prop.freq_supported_num = freq_supp_num; + pins[i].pf = pf; + } + + return ret; +} + +/** + * ice_dpll_init_info_rclk_pin - initializes rclk pin information + * @pf: board private structure + * + * Init information for rclk pin, cache them in pf->dplls.rclk. + * + * Return: + * * 0 - success + * * negative - init failure reason + */ +static int ice_dpll_init_info_rclk_pin(struct ice_pf *pf) +{ + struct ice_dpll_pin *pin = &pf->dplls.rclk; + + pin->prop.type = DPLL_PIN_TYPE_SYNCE_ETH_PORT; + pin->prop.capabilities |= DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE; + pin->pf = pf; + + return ice_dpll_pin_state_update(pf, pin, + ICE_DPLL_PIN_TYPE_RCLK_INPUT, NULL); +} + +/** + * ice_dpll_init_pins_info - init pins info wrapper + * @pf: board private structure + * @pin_type: type of pins being initialized + * + * Wraps functions for pin initialization. + * + * Return: + * * 0 - success + * * negative - init failure reason + */ +static int +ice_dpll_init_pins_info(struct ice_pf *pf, enum ice_dpll_pin_type pin_type) +{ + switch (pin_type) { + case ICE_DPLL_PIN_TYPE_INPUT: + case ICE_DPLL_PIN_TYPE_OUTPUT: + return ice_dpll_init_info_direct_pins(pf, pin_type); + case ICE_DPLL_PIN_TYPE_RCLK_INPUT: + return ice_dpll_init_info_rclk_pin(pf); + default: + return -EINVAL; + } +} + +/** + * ice_dpll_deinit_info - release memory allocated for pins info + * @pf: board private structure + * + * Release memory allocated for pins by ice_dpll_init_info function. + */ +static void ice_dpll_deinit_info(struct ice_pf *pf) +{ + kfree(pf->dplls.inputs); + kfree(pf->dplls.outputs); + kfree(pf->dplls.eec.input_prio); + kfree(pf->dplls.pps.input_prio); +} + +/** + * ice_dpll_init_info - prepare pf's dpll information structure + * @pf: board private structure + * @cgu: if cgu is present and controlled by this NIC + * + * Acquire (from HW) and set basic dpll information (on pf->dplls struct). + * + * Return: + * * 0 - success + * * negative - init failure reason + */ +static int ice_dpll_init_info(struct ice_pf *pf, bool cgu) +{ + struct ice_aqc_get_cgu_abilities abilities; + struct ice_dpll *de = &pf->dplls.eec; + struct ice_dpll *dp = &pf->dplls.pps; + struct ice_dplls *d = &pf->dplls; + struct ice_hw *hw = &pf->hw; + int ret, alloc_size, i; + + d->clock_id = ice_generate_clock_id(pf); + ret = ice_aq_get_cgu_abilities(hw, &abilities); + if (ret) { + dev_err(ice_pf_to_dev(pf), + "err:%d %s failed to read cgu abilities\n", + ret, ice_aq_str(hw->adminq.sq_last_status)); + return ret; + } + + de->dpll_idx = abilities.eec_dpll_idx; + dp->dpll_idx = abilities.pps_dpll_idx; + d->num_inputs = abilities.num_inputs; + d->num_outputs = abilities.num_outputs; + d->input_phase_adj_max = le32_to_cpu(abilities.max_in_phase_adj); + d->output_phase_adj_max = le32_to_cpu(abilities.max_out_phase_adj); + + alloc_size = sizeof(*d->inputs) * d->num_inputs; + d->inputs = kzalloc(alloc_size, GFP_KERNEL); + if (!d->inputs) + return -ENOMEM; + + alloc_size = sizeof(*de->input_prio) * d->num_inputs; + de->input_prio = kzalloc(alloc_size, GFP_KERNEL); + if (!de->input_prio) + return -ENOMEM; + + dp->input_prio = kzalloc(alloc_size, GFP_KERNEL); + if (!dp->input_prio) + return -ENOMEM; + + ret = ice_dpll_init_pins_info(pf, ICE_DPLL_PIN_TYPE_INPUT); + if (ret) + goto deinit_info; + + if (cgu) { + alloc_size = sizeof(*d->outputs) * d->num_outputs; + d->outputs = kzalloc(alloc_size, GFP_KERNEL); + if (!d->outputs) { + ret = -ENOMEM; + goto deinit_info; + } + + ret = ice_dpll_init_pins_info(pf, ICE_DPLL_PIN_TYPE_OUTPUT); + if (ret) + goto deinit_info; + } + + ret = ice_get_cgu_rclk_pin_info(&pf->hw, &d->base_rclk_idx, + &pf->dplls.rclk.num_parents); + if (ret) + return ret; + for (i = 0; i < pf->dplls.rclk.num_parents; i++) + pf->dplls.rclk.parent_idx[i] = d->base_rclk_idx + i; + ret = ice_dpll_init_pins_info(pf, ICE_DPLL_PIN_TYPE_RCLK_INPUT); + if (ret) + return ret; + de->mode = DPLL_MODE_AUTOMATIC; + dp->mode = DPLL_MODE_AUTOMATIC; + + dev_dbg(ice_pf_to_dev(pf), + "%s - success, inputs:%u, outputs:%u rclk-parents:%u\n", + __func__, d->num_inputs, d->num_outputs, d->rclk.num_parents); + + return 0; + +deinit_info: + dev_err(ice_pf_to_dev(pf), + "%s - fail: d->inputs:%p, de->input_prio:%p, dp->input_prio:%p, d->outputs:%p\n", + __func__, d->inputs, de->input_prio, + dp->input_prio, d->outputs); + ice_dpll_deinit_info(pf); + return ret; +} + +/** + * ice_dpll_deinit - Disable the driver/HW support for dpll subsystem + * the dpll device. + * @pf: board private structure + * + * Handles the cleanup work required after dpll initialization, freeing + * resources and unregistering the dpll, pin and all resources used for + * handling them. + * + * Context: Destroys pf->dplls.lock mutex. Call only if ICE_FLAG_DPLL was set. + */ +void ice_dpll_deinit(struct ice_pf *pf) +{ + bool cgu = ice_is_feature_supported(pf, ICE_F_CGU); + + clear_bit(ICE_FLAG_DPLL, pf->flags); + if (cgu) + ice_dpll_deinit_worker(pf); + + ice_dpll_deinit_pins(pf, cgu); + ice_dpll_deinit_dpll(pf, &pf->dplls.pps, cgu); + ice_dpll_deinit_dpll(pf, &pf->dplls.eec, cgu); + ice_dpll_deinit_info(pf); + mutex_destroy(&pf->dplls.lock); +} + +/** + * ice_dpll_init - initialize support for dpll subsystem + * @pf: board private structure + * + * Set up the device dplls, register them and pins connected within Linux dpll + * subsystem. Allow userspace to obtain state of DPLL and handling of DPLL + * configuration requests. + * + * Context: Initializes pf->dplls.lock mutex. + */ +void ice_dpll_init(struct ice_pf *pf) +{ + bool cgu = ice_is_feature_supported(pf, ICE_F_CGU); + struct ice_dplls *d = &pf->dplls; + int err = 0; + + err = ice_dpll_init_info(pf, cgu); + if (err) + goto err_exit; + err = ice_dpll_init_dpll(pf, &pf->dplls.eec, cgu, DPLL_TYPE_EEC); + if (err) + goto deinit_info; + err = ice_dpll_init_dpll(pf, &pf->dplls.pps, cgu, DPLL_TYPE_PPS); + if (err) + goto deinit_eec; + err = ice_dpll_init_pins(pf, cgu); + if (err) + goto deinit_pps; + mutex_init(&d->lock); + if (cgu) { + err = ice_dpll_init_worker(pf); + if (err) + goto deinit_pins; + } + set_bit(ICE_FLAG_DPLL, pf->flags); + + return; + +deinit_pins: + ice_dpll_deinit_pins(pf, cgu); +deinit_pps: + ice_dpll_deinit_dpll(pf, &pf->dplls.pps, cgu); +deinit_eec: + ice_dpll_deinit_dpll(pf, &pf->dplls.eec, cgu); +deinit_info: + ice_dpll_deinit_info(pf); +err_exit: + mutex_destroy(&d->lock); + dev_warn(ice_pf_to_dev(pf), "DPLLs init failure err:%d\n", err); +} diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.h b/drivers/net/ethernet/intel/ice/ice_dpll.h new file mode 100644 index 000000000000..93172e93995b --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_dpll.h @@ -0,0 +1,113 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2022, Intel Corporation. */ + +#ifndef _ICE_DPLL_H_ +#define _ICE_DPLL_H_ + +#include "ice.h" + +#define ICE_DPLL_RCLK_NUM_MAX 4 + +/** ice_dpll_pin - store info about pins + * @pin: dpll pin structure + * @pf: pointer to pf, which has registered the dpll_pin + * @idx: ice pin private idx + * @num_parents: hols number of parent pins + * @parent_idx: hold indexes of parent pins + * @flags: pin flags returned from HW + * @state: state of a pin + * @prop: pin properties + * @freq: current frequency of a pin + * @phase_adjust: current phase adjust value + */ +struct ice_dpll_pin { + struct dpll_pin *pin; + struct ice_pf *pf; + u8 idx; + u8 num_parents; + u8 parent_idx[ICE_DPLL_RCLK_NUM_MAX]; + u8 flags[ICE_DPLL_RCLK_NUM_MAX]; + u8 state[ICE_DPLL_RCLK_NUM_MAX]; + struct dpll_pin_properties prop; + u32 freq; + s32 phase_adjust; +}; + +/** ice_dpll - store info required for DPLL control + * @dpll: pointer to dpll dev + * @pf: pointer to pf, which has registered the dpll_device + * @dpll_idx: index of dpll on the NIC + * @input_idx: currently selected input index + * @prev_input_idx: previously selected input index + * @ref_state: state of dpll reference signals + * @eec_mode: eec_mode dpll is configured for + * @phase_offset: phase offset of active pin vs dpll signal + * @prev_phase_offset: previous phase offset of active pin vs dpll signal + * @input_prio: priorities of each input + * @dpll_state: current dpll sync state + * @prev_dpll_state: last dpll sync state + * @active_input: pointer to active input pin + * @prev_input: pointer to previous active input pin + */ +struct ice_dpll { + struct dpll_device *dpll; + struct ice_pf *pf; + u8 dpll_idx; + u8 input_idx; + u8 prev_input_idx; + u8 ref_state; + u8 eec_mode; + s64 phase_offset; + s64 prev_phase_offset; + u8 *input_prio; + enum dpll_lock_status dpll_state; + enum dpll_lock_status prev_dpll_state; + enum dpll_mode mode; + struct dpll_pin *active_input; + struct dpll_pin *prev_input; +}; + +/** ice_dplls - store info required for CCU (clock controlling unit) + * @kworker: periodic worker + * @work: periodic work + * @lock: locks access to configuration of a dpll + * @eec: pointer to EEC dpll dev + * @pps: pointer to PPS dpll dev + * @inputs: input pins pointer + * @outputs: output pins pointer + * @rclk: recovered pins pointer + * @num_inputs: number of input pins available on dpll + * @num_outputs: number of output pins available on dpll + * @cgu_state_acq_err_num: number of errors returned during periodic work + * @base_rclk_idx: idx of first pin used for clock revocery pins + * @clock_id: clock_id of dplls + * @input_phase_adj_max: max phase adjust value for an input pins + * @output_phase_adj_max: max phase adjust value for an output pins + */ +struct ice_dplls { + struct kthread_worker *kworker; + struct kthread_delayed_work work; + struct mutex lock; + struct ice_dpll eec; + struct ice_dpll pps; + struct ice_dpll_pin *inputs; + struct ice_dpll_pin *outputs; + struct ice_dpll_pin rclk; + u8 num_inputs; + u8 num_outputs; + int cgu_state_acq_err_num; + u8 base_rclk_idx; + u64 clock_id; + s32 input_phase_adj_max; + s32 output_phase_adj_max; +}; + +#if IS_ENABLED(CONFIG_PTP_1588_CLOCK) +void ice_dpll_init(struct ice_pf *pf); +void ice_dpll_deinit(struct ice_pf *pf); +#else +static inline void ice_dpll_init(struct ice_pf *pf) { } +static inline void ice_dpll_deinit(struct ice_pf *pf) { } +#endif + +#endif diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index 8f232c41a89e..a655d499abfa 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -4,6 +4,7 @@ #include "ice.h" #include "ice_lib.h" #include "ice_eswitch.h" +#include "ice_eswitch_br.h" #include "ice_fltr.h" #include "ice_repr.h" #include "ice_devlink.h" @@ -83,10 +84,6 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) struct ice_vsi_vlan_ops *vlan_ops; bool rule_added = false; - vlan_ops = ice_get_compat_vsi_vlan_ops(ctrl_vsi); - if (vlan_ops->dis_stripping(ctrl_vsi)) - return -ENODEV; - ice_remove_vsi_fltr(&pf->hw, uplink_vsi->idx); netif_addr_lock_bh(uplink_netdev); @@ -103,17 +100,28 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) rule_added = true; } + vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi); + if (vlan_ops->dis_rx_filtering(uplink_vsi)) + goto err_dis_rx; + if (ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_set_allow_override)) goto err_override_uplink; if (ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_set_allow_override)) goto err_override_control; + if (ice_vsi_update_local_lb(uplink_vsi, true)) + goto err_override_local_lb; + return 0; +err_override_local_lb: + ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_clear_allow_override); err_override_control: ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override); err_override_uplink: + vlan_ops->ena_rx_filtering(uplink_vsi); +err_dis_rx: if (rule_added) ice_clear_dflt_vsi(uplink_vsi); err_def_rx: @@ -306,6 +314,9 @@ void ice_eswitch_update_repr(struct ice_vsi *vsi) repr->src_vsi = vsi; repr->dst->u.port_info.port_id = vsi->vsi_num; + if (repr->br_port) + repr->br_port->vsi = vsi; + ret = ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof); if (ret) { ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr, ICE_FWD_TO_VSI); @@ -331,6 +342,9 @@ ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev) np = netdev_priv(netdev); vsi = np->vsi; + if (!vsi || !ice_is_switchdev_running(vsi->back)) + return NETDEV_TX_BUSY; + if (ice_is_reset_in_progress(vsi->back->state) || test_bit(ICE_VF_DIS, vsi->back->state)) return NETDEV_TX_BUSY; @@ -378,9 +392,14 @@ static void ice_eswitch_release_env(struct ice_pf *pf) { struct ice_vsi *uplink_vsi = pf->switchdev.uplink_vsi; struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; + struct ice_vsi_vlan_ops *vlan_ops; + vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi); + + ice_vsi_update_local_lb(uplink_vsi, false); ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_clear_allow_override); ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override); + vlan_ops->ena_rx_filtering(uplink_vsi); ice_clear_dflt_vsi(uplink_vsi); ice_fltr_add_mac_and_broadcast(uplink_vsi, uplink_vsi->port_info->mac.perm_addr, @@ -455,16 +474,24 @@ static void ice_eswitch_napi_disable(struct ice_pf *pf) */ static int ice_eswitch_enable_switchdev(struct ice_pf *pf) { - struct ice_vsi *ctrl_vsi; + struct ice_vsi *ctrl_vsi, *uplink_vsi; + + uplink_vsi = ice_get_main_vsi(pf); + if (!uplink_vsi) + return -ENODEV; + + if (netif_is_any_bridge_port(uplink_vsi->netdev)) { + dev_err(ice_pf_to_dev(pf), + "Uplink port cannot be a bridge port\n"); + return -EINVAL; + } pf->switchdev.control_vsi = ice_eswitch_vsi_setup(pf, pf->hw.port_info); if (!pf->switchdev.control_vsi) return -ENODEV; ctrl_vsi = pf->switchdev.control_vsi; - pf->switchdev.uplink_vsi = ice_get_main_vsi(pf); - if (!pf->switchdev.uplink_vsi) - goto err_vsi; + pf->switchdev.uplink_vsi = uplink_vsi; if (ice_eswitch_setup_env(pf)) goto err_vsi; @@ -480,10 +507,15 @@ static int ice_eswitch_enable_switchdev(struct ice_pf *pf) if (ice_vsi_open(ctrl_vsi)) goto err_setup_reprs; + if (ice_eswitch_br_offloads_init(pf)) + goto err_br_offloads; + ice_eswitch_napi_enable(pf); return 0; +err_br_offloads: + ice_vsi_close(ctrl_vsi); err_setup_reprs: ice_repr_rem_from_all_vfs(pf); err_repr_add: @@ -502,8 +534,8 @@ static void ice_eswitch_disable_switchdev(struct ice_pf *pf) struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; ice_eswitch_napi_disable(pf); + ice_eswitch_br_offloads_deinit(pf); ice_eswitch_release_env(pf); - ice_rem_adv_rule_for_vsi(&pf->hw, ctrl_vsi->idx); ice_eswitch_release_reprs(pf, ctrl_vsi); ice_vsi_release(ctrl_vsi); ice_repr_rem_from_all_vfs(pf); diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c new file mode 100644 index 000000000000..6ae0269bdf73 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c @@ -0,0 +1,1346 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023, Intel Corporation. */ + +#include "ice.h" +#include "ice_eswitch_br.h" +#include "ice_repr.h" +#include "ice_switch.h" +#include "ice_vlan.h" +#include "ice_vf_vsi_vlan_ops.h" +#include "ice_trace.h" + +#define ICE_ESW_BRIDGE_UPDATE_INTERVAL msecs_to_jiffies(1000) + +static const struct rhashtable_params ice_fdb_ht_params = { + .key_offset = offsetof(struct ice_esw_br_fdb_entry, data), + .key_len = sizeof(struct ice_esw_br_fdb_data), + .head_offset = offsetof(struct ice_esw_br_fdb_entry, ht_node), + .automatic_shrinking = true, +}; + +static bool ice_eswitch_br_is_dev_valid(const struct net_device *dev) +{ + /* Accept only PF netdev, PRs and LAG */ + return ice_is_port_repr_netdev(dev) || netif_is_ice(dev) || + netif_is_lag_master(dev); +} + +static struct net_device * +ice_eswitch_br_get_uplink_from_lag(struct net_device *lag_dev) +{ + struct net_device *lower; + struct list_head *iter; + + netdev_for_each_lower_dev(lag_dev, lower, iter) { + if (netif_is_ice(lower)) + return lower; + } + + return NULL; +} + +static struct ice_esw_br_port * +ice_eswitch_br_netdev_to_port(struct net_device *dev) +{ + if (ice_is_port_repr_netdev(dev)) { + struct ice_repr *repr = ice_netdev_to_repr(dev); + + return repr->br_port; + } else if (netif_is_ice(dev) || netif_is_lag_master(dev)) { + struct net_device *ice_dev; + struct ice_pf *pf; + + if (netif_is_lag_master(dev)) + ice_dev = ice_eswitch_br_get_uplink_from_lag(dev); + else + ice_dev = dev; + + if (!ice_dev) + return NULL; + + pf = ice_netdev_to_pf(ice_dev); + + return pf->br_port; + } + + return NULL; +} + +static void +ice_eswitch_br_ingress_rule_setup(struct ice_adv_rule_info *rule_info, + u8 pf_id, u16 vf_vsi_idx) +{ + rule_info->sw_act.vsi_handle = vf_vsi_idx; + rule_info->sw_act.flag |= ICE_FLTR_RX; + rule_info->sw_act.src = pf_id; + rule_info->priority = 2; +} + +static void +ice_eswitch_br_egress_rule_setup(struct ice_adv_rule_info *rule_info, + u16 pf_vsi_idx) +{ + rule_info->sw_act.vsi_handle = pf_vsi_idx; + rule_info->sw_act.flag |= ICE_FLTR_TX; + rule_info->flags_info.act = ICE_SINGLE_ACT_LAN_ENABLE; + rule_info->flags_info.act_valid = true; + rule_info->priority = 2; +} + +static int +ice_eswitch_br_rule_delete(struct ice_hw *hw, struct ice_rule_query_data *rule) +{ + int err; + + if (!rule) + return -EINVAL; + + err = ice_rem_adv_rule_by_id(hw, rule); + kfree(rule); + + return err; +} + +static u16 +ice_eswitch_br_get_lkups_cnt(u16 vid) +{ + return ice_eswitch_br_is_vid_valid(vid) ? 2 : 1; +} + +static void +ice_eswitch_br_add_vlan_lkup(struct ice_adv_lkup_elem *list, u16 vid) +{ + if (ice_eswitch_br_is_vid_valid(vid)) { + list[1].type = ICE_VLAN_OFOS; + list[1].h_u.vlan_hdr.vlan = cpu_to_be16(vid & VLAN_VID_MASK); + list[1].m_u.vlan_hdr.vlan = cpu_to_be16(0xFFFF); + } +} + +static struct ice_rule_query_data * +ice_eswitch_br_fwd_rule_create(struct ice_hw *hw, int vsi_idx, int port_type, + const unsigned char *mac, u16 vid) +{ + struct ice_adv_rule_info rule_info = { 0 }; + struct ice_rule_query_data *rule; + struct ice_adv_lkup_elem *list; + u16 lkups_cnt; + int err; + + lkups_cnt = ice_eswitch_br_get_lkups_cnt(vid); + + rule = kzalloc(sizeof(*rule), GFP_KERNEL); + if (!rule) + return ERR_PTR(-ENOMEM); + + list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC); + if (!list) { + err = -ENOMEM; + goto err_list_alloc; + } + + switch (port_type) { + case ICE_ESWITCH_BR_UPLINK_PORT: + ice_eswitch_br_egress_rule_setup(&rule_info, vsi_idx); + break; + case ICE_ESWITCH_BR_VF_REPR_PORT: + ice_eswitch_br_ingress_rule_setup(&rule_info, hw->pf_id, + vsi_idx); + break; + default: + err = -EINVAL; + goto err_add_rule; + } + + list[0].type = ICE_MAC_OFOS; + ether_addr_copy(list[0].h_u.eth_hdr.dst_addr, mac); + eth_broadcast_addr(list[0].m_u.eth_hdr.dst_addr); + + ice_eswitch_br_add_vlan_lkup(list, vid); + + rule_info.need_pass_l2 = true; + + rule_info.sw_act.fltr_act = ICE_FWD_TO_VSI; + + err = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, rule); + if (err) + goto err_add_rule; + + kfree(list); + + return rule; + +err_add_rule: + kfree(list); +err_list_alloc: + kfree(rule); + + return ERR_PTR(err); +} + +static struct ice_rule_query_data * +ice_eswitch_br_guard_rule_create(struct ice_hw *hw, u16 vsi_idx, + const unsigned char *mac, u16 vid) +{ + struct ice_adv_rule_info rule_info = { 0 }; + struct ice_rule_query_data *rule; + struct ice_adv_lkup_elem *list; + int err = -ENOMEM; + u16 lkups_cnt; + + lkups_cnt = ice_eswitch_br_get_lkups_cnt(vid); + + rule = kzalloc(sizeof(*rule), GFP_KERNEL); + if (!rule) + goto err_exit; + + list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC); + if (!list) + goto err_list_alloc; + + list[0].type = ICE_MAC_OFOS; + ether_addr_copy(list[0].h_u.eth_hdr.src_addr, mac); + eth_broadcast_addr(list[0].m_u.eth_hdr.src_addr); + + ice_eswitch_br_add_vlan_lkup(list, vid); + + rule_info.allow_pass_l2 = true; + rule_info.sw_act.vsi_handle = vsi_idx; + rule_info.sw_act.fltr_act = ICE_NOP; + rule_info.priority = 2; + + err = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, rule); + if (err) + goto err_add_rule; + + kfree(list); + + return rule; + +err_add_rule: + kfree(list); +err_list_alloc: + kfree(rule); +err_exit: + return ERR_PTR(err); +} + +static struct ice_esw_br_flow * +ice_eswitch_br_flow_create(struct device *dev, struct ice_hw *hw, int vsi_idx, + int port_type, const unsigned char *mac, u16 vid) +{ + struct ice_rule_query_data *fwd_rule, *guard_rule; + struct ice_esw_br_flow *flow; + int err; + + flow = kzalloc(sizeof(*flow), GFP_KERNEL); + if (!flow) + return ERR_PTR(-ENOMEM); + + fwd_rule = ice_eswitch_br_fwd_rule_create(hw, vsi_idx, port_type, mac, + vid); + err = PTR_ERR_OR_ZERO(fwd_rule); + if (err) { + dev_err(dev, "Failed to create eswitch bridge %sgress forward rule, err: %d\n", + port_type == ICE_ESWITCH_BR_UPLINK_PORT ? "e" : "in", + err); + goto err_fwd_rule; + } + + guard_rule = ice_eswitch_br_guard_rule_create(hw, vsi_idx, mac, vid); + err = PTR_ERR_OR_ZERO(guard_rule); + if (err) { + dev_err(dev, "Failed to create eswitch bridge %sgress guard rule, err: %d\n", + port_type == ICE_ESWITCH_BR_UPLINK_PORT ? "e" : "in", + err); + goto err_guard_rule; + } + + flow->fwd_rule = fwd_rule; + flow->guard_rule = guard_rule; + + return flow; + +err_guard_rule: + ice_eswitch_br_rule_delete(hw, fwd_rule); +err_fwd_rule: + kfree(flow); + + return ERR_PTR(err); +} + +static struct ice_esw_br_fdb_entry * +ice_eswitch_br_fdb_find(struct ice_esw_br *bridge, const unsigned char *mac, + u16 vid) +{ + struct ice_esw_br_fdb_data data = { + .vid = vid, + }; + + ether_addr_copy(data.addr, mac); + return rhashtable_lookup_fast(&bridge->fdb_ht, &data, + ice_fdb_ht_params); +} + +static void +ice_eswitch_br_flow_delete(struct ice_pf *pf, struct ice_esw_br_flow *flow) +{ + struct device *dev = ice_pf_to_dev(pf); + int err; + + err = ice_eswitch_br_rule_delete(&pf->hw, flow->fwd_rule); + if (err) + dev_err(dev, "Failed to delete FDB forward rule, err: %d\n", + err); + + err = ice_eswitch_br_rule_delete(&pf->hw, flow->guard_rule); + if (err) + dev_err(dev, "Failed to delete FDB guard rule, err: %d\n", + err); + + kfree(flow); +} + +static struct ice_esw_br_vlan * +ice_esw_br_port_vlan_lookup(struct ice_esw_br *bridge, u16 vsi_idx, u16 vid) +{ + struct ice_pf *pf = bridge->br_offloads->pf; + struct device *dev = ice_pf_to_dev(pf); + struct ice_esw_br_port *port; + struct ice_esw_br_vlan *vlan; + + port = xa_load(&bridge->ports, vsi_idx); + if (!port) { + dev_info(dev, "Bridge port lookup failed (vsi=%u)\n", vsi_idx); + return ERR_PTR(-EINVAL); + } + + vlan = xa_load(&port->vlans, vid); + if (!vlan) { + dev_info(dev, "Bridge port vlan metadata lookup failed (vsi=%u)\n", + vsi_idx); + return ERR_PTR(-EINVAL); + } + + return vlan; +} + +static void +ice_eswitch_br_fdb_entry_delete(struct ice_esw_br *bridge, + struct ice_esw_br_fdb_entry *fdb_entry) +{ + struct ice_pf *pf = bridge->br_offloads->pf; + + rhashtable_remove_fast(&bridge->fdb_ht, &fdb_entry->ht_node, + ice_fdb_ht_params); + list_del(&fdb_entry->list); + + ice_eswitch_br_flow_delete(pf, fdb_entry->flow); + + kfree(fdb_entry); +} + +static void +ice_eswitch_br_fdb_offload_notify(struct net_device *dev, + const unsigned char *mac, u16 vid, + unsigned long val) +{ + struct switchdev_notifier_fdb_info fdb_info = { + .addr = mac, + .vid = vid, + .offloaded = true, + }; + + call_switchdev_notifiers(val, dev, &fdb_info.info, NULL); +} + +static void +ice_eswitch_br_fdb_entry_notify_and_cleanup(struct ice_esw_br *bridge, + struct ice_esw_br_fdb_entry *entry) +{ + if (!(entry->flags & ICE_ESWITCH_BR_FDB_ADDED_BY_USER)) + ice_eswitch_br_fdb_offload_notify(entry->dev, entry->data.addr, + entry->data.vid, + SWITCHDEV_FDB_DEL_TO_BRIDGE); + ice_eswitch_br_fdb_entry_delete(bridge, entry); +} + +static void +ice_eswitch_br_fdb_entry_find_and_delete(struct ice_esw_br *bridge, + const unsigned char *mac, u16 vid) +{ + struct ice_pf *pf = bridge->br_offloads->pf; + struct ice_esw_br_fdb_entry *fdb_entry; + struct device *dev = ice_pf_to_dev(pf); + + fdb_entry = ice_eswitch_br_fdb_find(bridge, mac, vid); + if (!fdb_entry) { + dev_err(dev, "FDB entry with mac: %pM and vid: %u not found\n", + mac, vid); + return; + } + + trace_ice_eswitch_br_fdb_entry_find_and_delete(fdb_entry); + ice_eswitch_br_fdb_entry_notify_and_cleanup(bridge, fdb_entry); +} + +static void +ice_eswitch_br_fdb_entry_create(struct net_device *netdev, + struct ice_esw_br_port *br_port, + bool added_by_user, + const unsigned char *mac, u16 vid) +{ + struct ice_esw_br *bridge = br_port->bridge; + struct ice_pf *pf = bridge->br_offloads->pf; + struct device *dev = ice_pf_to_dev(pf); + struct ice_esw_br_fdb_entry *fdb_entry; + struct ice_esw_br_flow *flow; + struct ice_esw_br_vlan *vlan; + struct ice_hw *hw = &pf->hw; + unsigned long event; + int err; + + /* untagged filtering is not yet supported */ + if (!(bridge->flags & ICE_ESWITCH_BR_VLAN_FILTERING) && vid) + return; + + if ((bridge->flags & ICE_ESWITCH_BR_VLAN_FILTERING)) { + vlan = ice_esw_br_port_vlan_lookup(bridge, br_port->vsi_idx, + vid); + if (IS_ERR(vlan)) { + dev_err(dev, "Failed to find vlan lookup, err: %ld\n", + PTR_ERR(vlan)); + return; + } + } + + fdb_entry = ice_eswitch_br_fdb_find(bridge, mac, vid); + if (fdb_entry) + ice_eswitch_br_fdb_entry_notify_and_cleanup(bridge, fdb_entry); + + fdb_entry = kzalloc(sizeof(*fdb_entry), GFP_KERNEL); + if (!fdb_entry) { + err = -ENOMEM; + goto err_exit; + } + + flow = ice_eswitch_br_flow_create(dev, hw, br_port->vsi_idx, + br_port->type, mac, vid); + if (IS_ERR(flow)) { + err = PTR_ERR(flow); + goto err_add_flow; + } + + ether_addr_copy(fdb_entry->data.addr, mac); + fdb_entry->data.vid = vid; + fdb_entry->br_port = br_port; + fdb_entry->flow = flow; + fdb_entry->dev = netdev; + fdb_entry->last_use = jiffies; + event = SWITCHDEV_FDB_ADD_TO_BRIDGE; + + if (added_by_user) { + fdb_entry->flags |= ICE_ESWITCH_BR_FDB_ADDED_BY_USER; + event = SWITCHDEV_FDB_OFFLOADED; + } + + err = rhashtable_insert_fast(&bridge->fdb_ht, &fdb_entry->ht_node, + ice_fdb_ht_params); + if (err) + goto err_fdb_insert; + + list_add(&fdb_entry->list, &bridge->fdb_list); + trace_ice_eswitch_br_fdb_entry_create(fdb_entry); + + ice_eswitch_br_fdb_offload_notify(netdev, mac, vid, event); + + return; + +err_fdb_insert: + ice_eswitch_br_flow_delete(pf, flow); +err_add_flow: + kfree(fdb_entry); +err_exit: + dev_err(dev, "Failed to create fdb entry, err: %d\n", err); +} + +static void +ice_eswitch_br_fdb_work_dealloc(struct ice_esw_br_fdb_work *fdb_work) +{ + kfree(fdb_work->fdb_info.addr); + kfree(fdb_work); +} + +static void +ice_eswitch_br_fdb_event_work(struct work_struct *work) +{ + struct ice_esw_br_fdb_work *fdb_work = ice_work_to_fdb_work(work); + bool added_by_user = fdb_work->fdb_info.added_by_user; + const unsigned char *mac = fdb_work->fdb_info.addr; + u16 vid = fdb_work->fdb_info.vid; + struct ice_esw_br_port *br_port; + + rtnl_lock(); + + br_port = ice_eswitch_br_netdev_to_port(fdb_work->dev); + if (!br_port) + goto err_exit; + + switch (fdb_work->event) { + case SWITCHDEV_FDB_ADD_TO_DEVICE: + ice_eswitch_br_fdb_entry_create(fdb_work->dev, br_port, + added_by_user, mac, vid); + break; + case SWITCHDEV_FDB_DEL_TO_DEVICE: + ice_eswitch_br_fdb_entry_find_and_delete(br_port->bridge, + mac, vid); + break; + default: + goto err_exit; + } + +err_exit: + rtnl_unlock(); + dev_put(fdb_work->dev); + ice_eswitch_br_fdb_work_dealloc(fdb_work); +} + +static struct ice_esw_br_fdb_work * +ice_eswitch_br_fdb_work_alloc(struct switchdev_notifier_fdb_info *fdb_info, + struct net_device *dev, + unsigned long event) +{ + struct ice_esw_br_fdb_work *work; + unsigned char *mac; + + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) + return ERR_PTR(-ENOMEM); + + INIT_WORK(&work->work, ice_eswitch_br_fdb_event_work); + memcpy(&work->fdb_info, fdb_info, sizeof(work->fdb_info)); + + mac = kzalloc(ETH_ALEN, GFP_ATOMIC); + if (!mac) { + kfree(work); + return ERR_PTR(-ENOMEM); + } + + ether_addr_copy(mac, fdb_info->addr); + work->fdb_info.addr = mac; + work->event = event; + work->dev = dev; + + return work; +} + +static int +ice_eswitch_br_switchdev_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct net_device *dev = switchdev_notifier_info_to_dev(ptr); + struct switchdev_notifier_fdb_info *fdb_info; + struct switchdev_notifier_info *info = ptr; + struct ice_esw_br_offloads *br_offloads; + struct ice_esw_br_fdb_work *work; + struct netlink_ext_ack *extack; + struct net_device *upper; + + br_offloads = ice_nb_to_br_offloads(nb, switchdev_nb); + extack = switchdev_notifier_info_to_extack(ptr); + + upper = netdev_master_upper_dev_get_rcu(dev); + if (!upper) + return NOTIFY_DONE; + + if (!netif_is_bridge_master(upper)) + return NOTIFY_DONE; + + if (!ice_eswitch_br_is_dev_valid(dev)) + return NOTIFY_DONE; + + if (!ice_eswitch_br_netdev_to_port(dev)) + return NOTIFY_DONE; + + switch (event) { + case SWITCHDEV_FDB_ADD_TO_DEVICE: + case SWITCHDEV_FDB_DEL_TO_DEVICE: + fdb_info = container_of(info, typeof(*fdb_info), info); + + work = ice_eswitch_br_fdb_work_alloc(fdb_info, dev, event); + if (IS_ERR(work)) { + NL_SET_ERR_MSG_MOD(extack, "Failed to init switchdev fdb work"); + return notifier_from_errno(PTR_ERR(work)); + } + dev_hold(dev); + + queue_work(br_offloads->wq, &work->work); + break; + default: + break; + } + return NOTIFY_DONE; +} + +static void ice_eswitch_br_fdb_flush(struct ice_esw_br *bridge) +{ + struct ice_esw_br_fdb_entry *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) + ice_eswitch_br_fdb_entry_notify_and_cleanup(bridge, entry); +} + +static void +ice_eswitch_br_vlan_filtering_set(struct ice_esw_br *bridge, bool enable) +{ + if (enable == !!(bridge->flags & ICE_ESWITCH_BR_VLAN_FILTERING)) + return; + + ice_eswitch_br_fdb_flush(bridge); + if (enable) + bridge->flags |= ICE_ESWITCH_BR_VLAN_FILTERING; + else + bridge->flags &= ~ICE_ESWITCH_BR_VLAN_FILTERING; +} + +static void +ice_eswitch_br_clear_pvid(struct ice_esw_br_port *port) +{ + struct ice_vlan port_vlan = ICE_VLAN(ETH_P_8021Q, port->pvid, 0); + struct ice_vsi_vlan_ops *vlan_ops; + + vlan_ops = ice_get_compat_vsi_vlan_ops(port->vsi); + + vlan_ops->del_vlan(port->vsi, &port_vlan); + vlan_ops->clear_port_vlan(port->vsi); + + ice_vf_vsi_disable_port_vlan(port->vsi); + + port->pvid = 0; +} + +static void +ice_eswitch_br_vlan_cleanup(struct ice_esw_br_port *port, + struct ice_esw_br_vlan *vlan) +{ + struct ice_esw_br_fdb_entry *fdb_entry, *tmp; + struct ice_esw_br *bridge = port->bridge; + + trace_ice_eswitch_br_vlan_cleanup(vlan); + + list_for_each_entry_safe(fdb_entry, tmp, &bridge->fdb_list, list) { + if (vlan->vid == fdb_entry->data.vid) + ice_eswitch_br_fdb_entry_delete(bridge, fdb_entry); + } + + xa_erase(&port->vlans, vlan->vid); + if (port->pvid == vlan->vid) + ice_eswitch_br_clear_pvid(port); + kfree(vlan); +} + +static void ice_eswitch_br_port_vlans_flush(struct ice_esw_br_port *port) +{ + struct ice_esw_br_vlan *vlan; + unsigned long index; + + xa_for_each(&port->vlans, index, vlan) + ice_eswitch_br_vlan_cleanup(port, vlan); +} + +static int +ice_eswitch_br_set_pvid(struct ice_esw_br_port *port, + struct ice_esw_br_vlan *vlan) +{ + struct ice_vlan port_vlan = ICE_VLAN(ETH_P_8021Q, vlan->vid, 0); + struct device *dev = ice_pf_to_dev(port->vsi->back); + struct ice_vsi_vlan_ops *vlan_ops; + int err; + + if (port->pvid == vlan->vid || vlan->vid == 1) + return 0; + + /* Setting port vlan on uplink isn't supported by hw */ + if (port->type == ICE_ESWITCH_BR_UPLINK_PORT) + return -EOPNOTSUPP; + + if (port->pvid) { + dev_info(dev, + "Port VLAN (vsi=%u, vid=%u) already exists on the port, remove it before adding new one\n", + port->vsi_idx, port->pvid); + return -EEXIST; + } + + ice_vf_vsi_enable_port_vlan(port->vsi); + + vlan_ops = ice_get_compat_vsi_vlan_ops(port->vsi); + err = vlan_ops->set_port_vlan(port->vsi, &port_vlan); + if (err) + return err; + + err = vlan_ops->add_vlan(port->vsi, &port_vlan); + if (err) + return err; + + ice_eswitch_br_port_vlans_flush(port); + port->pvid = vlan->vid; + + return 0; +} + +static struct ice_esw_br_vlan * +ice_eswitch_br_vlan_create(u16 vid, u16 flags, struct ice_esw_br_port *port) +{ + struct device *dev = ice_pf_to_dev(port->vsi->back); + struct ice_esw_br_vlan *vlan; + int err; + + vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); + if (!vlan) + return ERR_PTR(-ENOMEM); + + vlan->vid = vid; + vlan->flags = flags; + if ((flags & BRIDGE_VLAN_INFO_PVID) && + (flags & BRIDGE_VLAN_INFO_UNTAGGED)) { + err = ice_eswitch_br_set_pvid(port, vlan); + if (err) + goto err_set_pvid; + } else if ((flags & BRIDGE_VLAN_INFO_PVID) || + (flags & BRIDGE_VLAN_INFO_UNTAGGED)) { + dev_info(dev, "VLAN push and pop are supported only simultaneously\n"); + err = -EOPNOTSUPP; + goto err_set_pvid; + } + + err = xa_insert(&port->vlans, vlan->vid, vlan, GFP_KERNEL); + if (err) + goto err_insert; + + trace_ice_eswitch_br_vlan_create(vlan); + + return vlan; + +err_insert: + if (port->pvid) + ice_eswitch_br_clear_pvid(port); +err_set_pvid: + kfree(vlan); + return ERR_PTR(err); +} + +static int +ice_eswitch_br_port_vlan_add(struct ice_esw_br *bridge, u16 vsi_idx, u16 vid, + u16 flags, struct netlink_ext_ack *extack) +{ + struct ice_esw_br_port *port; + struct ice_esw_br_vlan *vlan; + + port = xa_load(&bridge->ports, vsi_idx); + if (!port) + return -EINVAL; + + if (port->pvid) { + dev_info(ice_pf_to_dev(port->vsi->back), + "Port VLAN (vsi=%u, vid=%d) exists on the port, remove it to add trunk VLANs\n", + port->vsi_idx, port->pvid); + return -EEXIST; + } + + vlan = xa_load(&port->vlans, vid); + if (vlan) { + if (vlan->flags == flags) + return 0; + + ice_eswitch_br_vlan_cleanup(port, vlan); + } + + vlan = ice_eswitch_br_vlan_create(vid, flags, port); + if (IS_ERR(vlan)) { + NL_SET_ERR_MSG_FMT_MOD(extack, "Failed to create VLAN entry, vid: %u, vsi: %u", + vid, vsi_idx); + return PTR_ERR(vlan); + } + + return 0; +} + +static void +ice_eswitch_br_port_vlan_del(struct ice_esw_br *bridge, u16 vsi_idx, u16 vid) +{ + struct ice_esw_br_port *port; + struct ice_esw_br_vlan *vlan; + + port = xa_load(&bridge->ports, vsi_idx); + if (!port) + return; + + vlan = xa_load(&port->vlans, vid); + if (!vlan) + return; + + ice_eswitch_br_vlan_cleanup(port, vlan); +} + +static int +ice_eswitch_br_port_obj_add(struct net_device *netdev, const void *ctx, + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack) +{ + struct ice_esw_br_port *br_port = ice_eswitch_br_netdev_to_port(netdev); + struct switchdev_obj_port_vlan *vlan; + int err; + + if (!br_port) + return -EINVAL; + + switch (obj->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); + err = ice_eswitch_br_port_vlan_add(br_port->bridge, + br_port->vsi_idx, vlan->vid, + vlan->flags, extack); + return err; + default: + return -EOPNOTSUPP; + } +} + +static int +ice_eswitch_br_port_obj_del(struct net_device *netdev, const void *ctx, + const struct switchdev_obj *obj) +{ + struct ice_esw_br_port *br_port = ice_eswitch_br_netdev_to_port(netdev); + struct switchdev_obj_port_vlan *vlan; + + if (!br_port) + return -EINVAL; + + switch (obj->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); + ice_eswitch_br_port_vlan_del(br_port->bridge, br_port->vsi_idx, + vlan->vid); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int +ice_eswitch_br_port_obj_attr_set(struct net_device *netdev, const void *ctx, + const struct switchdev_attr *attr, + struct netlink_ext_ack *extack) +{ + struct ice_esw_br_port *br_port = ice_eswitch_br_netdev_to_port(netdev); + + if (!br_port) + return -EINVAL; + + switch (attr->id) { + case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: + ice_eswitch_br_vlan_filtering_set(br_port->bridge, + attr->u.vlan_filtering); + return 0; + case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME: + br_port->bridge->ageing_time = + clock_t_to_jiffies(attr->u.ageing_time); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int +ice_eswitch_br_event_blocking(struct notifier_block *nb, unsigned long event, + void *ptr) +{ + struct net_device *dev = switchdev_notifier_info_to_dev(ptr); + int err; + + switch (event) { + case SWITCHDEV_PORT_OBJ_ADD: + err = switchdev_handle_port_obj_add(dev, ptr, + ice_eswitch_br_is_dev_valid, + ice_eswitch_br_port_obj_add); + break; + case SWITCHDEV_PORT_OBJ_DEL: + err = switchdev_handle_port_obj_del(dev, ptr, + ice_eswitch_br_is_dev_valid, + ice_eswitch_br_port_obj_del); + break; + case SWITCHDEV_PORT_ATTR_SET: + err = switchdev_handle_port_attr_set(dev, ptr, + ice_eswitch_br_is_dev_valid, + ice_eswitch_br_port_obj_attr_set); + break; + default: + err = 0; + } + + return notifier_from_errno(err); +} + +static void +ice_eswitch_br_port_deinit(struct ice_esw_br *bridge, + struct ice_esw_br_port *br_port) +{ + struct ice_esw_br_fdb_entry *fdb_entry, *tmp; + struct ice_vsi *vsi = br_port->vsi; + + list_for_each_entry_safe(fdb_entry, tmp, &bridge->fdb_list, list) { + if (br_port == fdb_entry->br_port) + ice_eswitch_br_fdb_entry_delete(bridge, fdb_entry); + } + + if (br_port->type == ICE_ESWITCH_BR_UPLINK_PORT && vsi->back) + vsi->back->br_port = NULL; + else if (vsi->vf && vsi->vf->repr) + vsi->vf->repr->br_port = NULL; + + xa_erase(&bridge->ports, br_port->vsi_idx); + ice_eswitch_br_port_vlans_flush(br_port); + kfree(br_port); +} + +static struct ice_esw_br_port * +ice_eswitch_br_port_init(struct ice_esw_br *bridge) +{ + struct ice_esw_br_port *br_port; + + br_port = kzalloc(sizeof(*br_port), GFP_KERNEL); + if (!br_port) + return ERR_PTR(-ENOMEM); + + xa_init(&br_port->vlans); + + br_port->bridge = bridge; + + return br_port; +} + +static int +ice_eswitch_br_vf_repr_port_init(struct ice_esw_br *bridge, + struct ice_repr *repr) +{ + struct ice_esw_br_port *br_port; + int err; + + br_port = ice_eswitch_br_port_init(bridge); + if (IS_ERR(br_port)) + return PTR_ERR(br_port); + + br_port->vsi = repr->src_vsi; + br_port->vsi_idx = br_port->vsi->idx; + br_port->type = ICE_ESWITCH_BR_VF_REPR_PORT; + repr->br_port = br_port; + + err = xa_insert(&bridge->ports, br_port->vsi_idx, br_port, GFP_KERNEL); + if (err) { + ice_eswitch_br_port_deinit(bridge, br_port); + return err; + } + + return 0; +} + +static int +ice_eswitch_br_uplink_port_init(struct ice_esw_br *bridge, struct ice_pf *pf) +{ + struct ice_vsi *vsi = pf->switchdev.uplink_vsi; + struct ice_esw_br_port *br_port; + int err; + + br_port = ice_eswitch_br_port_init(bridge); + if (IS_ERR(br_port)) + return PTR_ERR(br_port); + + br_port->vsi = vsi; + br_port->vsi_idx = br_port->vsi->idx; + br_port->type = ICE_ESWITCH_BR_UPLINK_PORT; + pf->br_port = br_port; + + err = xa_insert(&bridge->ports, br_port->vsi_idx, br_port, GFP_KERNEL); + if (err) { + ice_eswitch_br_port_deinit(bridge, br_port); + return err; + } + + return 0; +} + +static void +ice_eswitch_br_ports_flush(struct ice_esw_br *bridge) +{ + struct ice_esw_br_port *port; + unsigned long i; + + xa_for_each(&bridge->ports, i, port) + ice_eswitch_br_port_deinit(bridge, port); +} + +static void +ice_eswitch_br_deinit(struct ice_esw_br_offloads *br_offloads, + struct ice_esw_br *bridge) +{ + if (!bridge) + return; + + /* Cleanup all the ports that were added asynchronously + * through NETDEV_CHANGEUPPER event. + */ + ice_eswitch_br_ports_flush(bridge); + WARN_ON(!xa_empty(&bridge->ports)); + xa_destroy(&bridge->ports); + rhashtable_destroy(&bridge->fdb_ht); + + br_offloads->bridge = NULL; + kfree(bridge); +} + +static struct ice_esw_br * +ice_eswitch_br_init(struct ice_esw_br_offloads *br_offloads, int ifindex) +{ + struct ice_esw_br *bridge; + int err; + + bridge = kzalloc(sizeof(*bridge), GFP_KERNEL); + if (!bridge) + return ERR_PTR(-ENOMEM); + + err = rhashtable_init(&bridge->fdb_ht, &ice_fdb_ht_params); + if (err) { + kfree(bridge); + return ERR_PTR(err); + } + + INIT_LIST_HEAD(&bridge->fdb_list); + bridge->br_offloads = br_offloads; + bridge->ifindex = ifindex; + bridge->ageing_time = clock_t_to_jiffies(BR_DEFAULT_AGEING_TIME); + xa_init(&bridge->ports); + br_offloads->bridge = bridge; + + return bridge; +} + +static struct ice_esw_br * +ice_eswitch_br_get(struct ice_esw_br_offloads *br_offloads, int ifindex, + struct netlink_ext_ack *extack) +{ + struct ice_esw_br *bridge = br_offloads->bridge; + + if (bridge) { + if (bridge->ifindex != ifindex) { + NL_SET_ERR_MSG_MOD(extack, + "Only one bridge is supported per eswitch"); + return ERR_PTR(-EOPNOTSUPP); + } + return bridge; + } + + /* Create the bridge if it doesn't exist yet */ + bridge = ice_eswitch_br_init(br_offloads, ifindex); + if (IS_ERR(bridge)) + NL_SET_ERR_MSG_MOD(extack, "Failed to init the bridge"); + + return bridge; +} + +static void +ice_eswitch_br_verify_deinit(struct ice_esw_br_offloads *br_offloads, + struct ice_esw_br *bridge) +{ + /* Remove the bridge if it exists and there are no ports left */ + if (!bridge || !xa_empty(&bridge->ports)) + return; + + ice_eswitch_br_deinit(br_offloads, bridge); +} + +static int +ice_eswitch_br_port_unlink(struct ice_esw_br_offloads *br_offloads, + struct net_device *dev, int ifindex, + struct netlink_ext_ack *extack) +{ + struct ice_esw_br_port *br_port = ice_eswitch_br_netdev_to_port(dev); + struct ice_esw_br *bridge; + + if (!br_port) { + NL_SET_ERR_MSG_MOD(extack, + "Port representor is not attached to any bridge"); + return -EINVAL; + } + + if (br_port->bridge->ifindex != ifindex) { + NL_SET_ERR_MSG_MOD(extack, + "Port representor is attached to another bridge"); + return -EINVAL; + } + + bridge = br_port->bridge; + + trace_ice_eswitch_br_port_unlink(br_port); + ice_eswitch_br_port_deinit(br_port->bridge, br_port); + ice_eswitch_br_verify_deinit(br_offloads, bridge); + + return 0; +} + +static int +ice_eswitch_br_port_link(struct ice_esw_br_offloads *br_offloads, + struct net_device *dev, int ifindex, + struct netlink_ext_ack *extack) +{ + struct ice_esw_br *bridge; + int err; + + if (ice_eswitch_br_netdev_to_port(dev)) { + NL_SET_ERR_MSG_MOD(extack, + "Port is already attached to the bridge"); + return -EINVAL; + } + + bridge = ice_eswitch_br_get(br_offloads, ifindex, extack); + if (IS_ERR(bridge)) + return PTR_ERR(bridge); + + if (ice_is_port_repr_netdev(dev)) { + struct ice_repr *repr = ice_netdev_to_repr(dev); + + err = ice_eswitch_br_vf_repr_port_init(bridge, repr); + trace_ice_eswitch_br_port_link(repr->br_port); + } else { + struct net_device *ice_dev; + struct ice_pf *pf; + + if (netif_is_lag_master(dev)) + ice_dev = ice_eswitch_br_get_uplink_from_lag(dev); + else + ice_dev = dev; + + if (!ice_dev) + return 0; + + pf = ice_netdev_to_pf(ice_dev); + + err = ice_eswitch_br_uplink_port_init(bridge, pf); + trace_ice_eswitch_br_port_link(pf->br_port); + } + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to init bridge port"); + goto err_port_init; + } + + return 0; + +err_port_init: + ice_eswitch_br_verify_deinit(br_offloads, bridge); + return err; +} + +static int +ice_eswitch_br_port_changeupper(struct notifier_block *nb, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_changeupper_info *info = ptr; + struct ice_esw_br_offloads *br_offloads; + struct netlink_ext_ack *extack; + struct net_device *upper; + + br_offloads = ice_nb_to_br_offloads(nb, netdev_nb); + + if (!ice_eswitch_br_is_dev_valid(dev)) + return 0; + + upper = info->upper_dev; + if (!netif_is_bridge_master(upper)) + return 0; + + extack = netdev_notifier_info_to_extack(&info->info); + + if (info->linking) + return ice_eswitch_br_port_link(br_offloads, dev, + upper->ifindex, extack); + else + return ice_eswitch_br_port_unlink(br_offloads, dev, + upper->ifindex, extack); +} + +static int +ice_eswitch_br_port_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + int err = 0; + + switch (event) { + case NETDEV_CHANGEUPPER: + err = ice_eswitch_br_port_changeupper(nb, ptr); + break; + } + + return notifier_from_errno(err); +} + +static void +ice_eswitch_br_offloads_dealloc(struct ice_pf *pf) +{ + struct ice_esw_br_offloads *br_offloads = pf->switchdev.br_offloads; + + ASSERT_RTNL(); + + if (!br_offloads) + return; + + ice_eswitch_br_deinit(br_offloads, br_offloads->bridge); + + pf->switchdev.br_offloads = NULL; + kfree(br_offloads); +} + +static struct ice_esw_br_offloads * +ice_eswitch_br_offloads_alloc(struct ice_pf *pf) +{ + struct ice_esw_br_offloads *br_offloads; + + ASSERT_RTNL(); + + if (pf->switchdev.br_offloads) + return ERR_PTR(-EEXIST); + + br_offloads = kzalloc(sizeof(*br_offloads), GFP_KERNEL); + if (!br_offloads) + return ERR_PTR(-ENOMEM); + + pf->switchdev.br_offloads = br_offloads; + br_offloads->pf = pf; + + return br_offloads; +} + +void +ice_eswitch_br_offloads_deinit(struct ice_pf *pf) +{ + struct ice_esw_br_offloads *br_offloads; + + br_offloads = pf->switchdev.br_offloads; + if (!br_offloads) + return; + + cancel_delayed_work_sync(&br_offloads->update_work); + unregister_netdevice_notifier(&br_offloads->netdev_nb); + unregister_switchdev_blocking_notifier(&br_offloads->switchdev_blk); + unregister_switchdev_notifier(&br_offloads->switchdev_nb); + destroy_workqueue(br_offloads->wq); + /* Although notifier block is unregistered just before, + * so we don't get any new events, some events might be + * already in progress. Hold the rtnl lock and wait for + * them to finished. + */ + rtnl_lock(); + ice_eswitch_br_offloads_dealloc(pf); + rtnl_unlock(); +} + +static void ice_eswitch_br_update(struct ice_esw_br_offloads *br_offloads) +{ + struct ice_esw_br *bridge = br_offloads->bridge; + struct ice_esw_br_fdb_entry *entry, *tmp; + + if (!bridge) + return; + + rtnl_lock(); + list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) { + if (entry->flags & ICE_ESWITCH_BR_FDB_ADDED_BY_USER) + continue; + + if (time_is_after_eq_jiffies(entry->last_use + + bridge->ageing_time)) + continue; + + ice_eswitch_br_fdb_entry_notify_and_cleanup(bridge, entry); + } + rtnl_unlock(); +} + +static void ice_eswitch_br_update_work(struct work_struct *work) +{ + struct ice_esw_br_offloads *br_offloads; + + br_offloads = ice_work_to_br_offloads(work); + + ice_eswitch_br_update(br_offloads); + + queue_delayed_work(br_offloads->wq, &br_offloads->update_work, + ICE_ESW_BRIDGE_UPDATE_INTERVAL); +} + +int +ice_eswitch_br_offloads_init(struct ice_pf *pf) +{ + struct ice_esw_br_offloads *br_offloads; + struct device *dev = ice_pf_to_dev(pf); + int err; + + rtnl_lock(); + br_offloads = ice_eswitch_br_offloads_alloc(pf); + rtnl_unlock(); + if (IS_ERR(br_offloads)) { + dev_err(dev, "Failed to init eswitch bridge\n"); + return PTR_ERR(br_offloads); + } + + br_offloads->wq = alloc_ordered_workqueue("ice_bridge_wq", 0); + if (!br_offloads->wq) { + err = -ENOMEM; + dev_err(dev, "Failed to allocate bridge workqueue\n"); + goto err_alloc_wq; + } + + br_offloads->switchdev_nb.notifier_call = + ice_eswitch_br_switchdev_event; + err = register_switchdev_notifier(&br_offloads->switchdev_nb); + if (err) { + dev_err(dev, + "Failed to register switchdev notifier\n"); + goto err_reg_switchdev_nb; + } + + br_offloads->switchdev_blk.notifier_call = + ice_eswitch_br_event_blocking; + err = register_switchdev_blocking_notifier(&br_offloads->switchdev_blk); + if (err) { + dev_err(dev, + "Failed to register bridge blocking switchdev notifier\n"); + goto err_reg_switchdev_blk; + } + + br_offloads->netdev_nb.notifier_call = ice_eswitch_br_port_event; + err = register_netdevice_notifier(&br_offloads->netdev_nb); + if (err) { + dev_err(dev, + "Failed to register bridge port event notifier\n"); + goto err_reg_netdev_nb; + } + + INIT_DELAYED_WORK(&br_offloads->update_work, + ice_eswitch_br_update_work); + queue_delayed_work(br_offloads->wq, &br_offloads->update_work, + ICE_ESW_BRIDGE_UPDATE_INTERVAL); + + return 0; + +err_reg_netdev_nb: + unregister_switchdev_blocking_notifier(&br_offloads->switchdev_blk); +err_reg_switchdev_blk: + unregister_switchdev_notifier(&br_offloads->switchdev_nb); +err_reg_switchdev_nb: + destroy_workqueue(br_offloads->wq); +err_alloc_wq: + rtnl_lock(); + ice_eswitch_br_offloads_dealloc(pf); + rtnl_unlock(); + + return err; +} diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.h b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h new file mode 100644 index 000000000000..85a8fadb2928 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h @@ -0,0 +1,120 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2023, Intel Corporation. */ + +#ifndef _ICE_ESWITCH_BR_H_ +#define _ICE_ESWITCH_BR_H_ + +#include <linux/rhashtable.h> +#include <linux/workqueue.h> + +struct ice_esw_br_fdb_data { + unsigned char addr[ETH_ALEN]; + u16 vid; +}; + +struct ice_esw_br_flow { + struct ice_rule_query_data *fwd_rule; + struct ice_rule_query_data *guard_rule; +}; + +enum { + ICE_ESWITCH_BR_FDB_ADDED_BY_USER = BIT(0), +}; + +struct ice_esw_br_fdb_entry { + struct ice_esw_br_fdb_data data; + struct rhash_head ht_node; + struct list_head list; + + int flags; + + struct net_device *dev; + struct ice_esw_br_port *br_port; + struct ice_esw_br_flow *flow; + + unsigned long last_use; +}; + +enum ice_esw_br_port_type { + ICE_ESWITCH_BR_UPLINK_PORT = 0, + ICE_ESWITCH_BR_VF_REPR_PORT = 1, +}; + +struct ice_esw_br_port { + struct ice_esw_br *bridge; + struct ice_vsi *vsi; + enum ice_esw_br_port_type type; + u16 vsi_idx; + u16 pvid; + struct xarray vlans; +}; + +enum { + ICE_ESWITCH_BR_VLAN_FILTERING = BIT(0), +}; + +struct ice_esw_br { + struct ice_esw_br_offloads *br_offloads; + struct xarray ports; + + struct rhashtable fdb_ht; + struct list_head fdb_list; + + int ifindex; + u32 flags; + unsigned long ageing_time; +}; + +struct ice_esw_br_offloads { + struct ice_pf *pf; + struct ice_esw_br *bridge; + struct notifier_block netdev_nb; + struct notifier_block switchdev_blk; + struct notifier_block switchdev_nb; + + struct workqueue_struct *wq; + struct delayed_work update_work; +}; + +struct ice_esw_br_fdb_work { + struct work_struct work; + struct switchdev_notifier_fdb_info fdb_info; + struct net_device *dev; + unsigned long event; +}; + +struct ice_esw_br_vlan { + u16 vid; + u16 flags; +}; + +#define ice_nb_to_br_offloads(nb, nb_name) \ + container_of(nb, \ + struct ice_esw_br_offloads, \ + nb_name) + +#define ice_work_to_br_offloads(w) \ + container_of(w, \ + struct ice_esw_br_offloads, \ + update_work.work) + +#define ice_work_to_fdb_work(w) \ + container_of(w, \ + struct ice_esw_br_fdb_work, \ + work) + +static inline bool ice_eswitch_br_is_vid_valid(u16 vid) +{ + /* In trunk VLAN mode, for untagged traffic the bridge sends requests + * to offload VLAN 1 with pvid and untagged flags set. Since these + * flags are not supported, add a MAC filter instead. + */ + return vid > 1; +} + +void +ice_eswitch_br_offloads_deinit(struct ice_pf *pf); +int +ice_eswitch_br_offloads_init(struct ice_pf *pf); + +#endif /* _ICE_ESWITCH_BR_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index ad4d4702129f..bde9bc74f928 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -345,6 +345,88 @@ static const struct ice_priv_flag ice_gstrings_priv_flags[] = { #define ICE_PRIV_FLAG_ARRAY_SIZE ARRAY_SIZE(ice_gstrings_priv_flags) +static const u32 ice_adv_lnk_speed_100[] __initconst = { + ETHTOOL_LINK_MODE_100baseT_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_1000[] __initconst = { + ETHTOOL_LINK_MODE_1000baseX_Full_BIT, + ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_2500[] __initconst = { + ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + ETHTOOL_LINK_MODE_2500baseX_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_5000[] __initconst = { + ETHTOOL_LINK_MODE_5000baseT_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_10000[] __initconst = { + ETHTOOL_LINK_MODE_10000baseT_Full_BIT, + ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, + ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, + ETHTOOL_LINK_MODE_10000baseLR_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_25000[] __initconst = { + ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, + ETHTOOL_LINK_MODE_25000baseSR_Full_BIT, + ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_40000[] __initconst = { + ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT, + ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT, + ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT, + ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_50000[] __initconst = { + ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT, + ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT, + ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_100000[] __initconst = { + ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, + ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT, + ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT, + ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, + ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT, + ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT, + ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_200000[] __initconst = { + ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT, + ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT, + ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT, + ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT, + ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT, +}; + +static struct ethtool_forced_speed_map ice_adv_lnk_speed_maps[] __ro_after_init = { + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 100), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 1000), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 2500), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 5000), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 10000), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 25000), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 40000), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 50000), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 100000), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 200000), +}; + +void __init ice_adv_lnk_speed_maps_init(void) +{ + ethtool_forced_speed_maps_init(ice_adv_lnk_speed_maps, + ARRAY_SIZE(ice_adv_lnk_speed_maps)); +} + static void __ice_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo, struct ice_vsi *vsi) @@ -1060,7 +1142,7 @@ __ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data, switch (stringset) { case ETH_SS_STATS: for (i = 0; i < ICE_VSI_STATS_LEN; i++) - ethtool_sprintf(&p, + ethtool_sprintf(&p, "%s", ice_gstrings_vsi_stats[i].stat_string); if (ice_is_port_repr_netdev(netdev)) @@ -1080,7 +1162,7 @@ __ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data, return; for (i = 0; i < ICE_PF_STATS_LEN; i++) - ethtool_sprintf(&p, + ethtool_sprintf(&p, "%s", ice_gstrings_pf_stats[i].stat_string); for (i = 0; i < ICE_MAX_USER_PRIORITY; i++) { @@ -1097,7 +1179,8 @@ __ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data, break; case ETH_SS_PRIV_FLAGS: for (i = 0; i < ICE_PRIV_FLAG_ARRAY_SIZE; i++) - ethtool_sprintf(&p, ice_gstrings_priv_flags[i].name); + ethtool_sprintf(&p, "%s", + ice_gstrings_priv_flags[i].name); break; default: break; @@ -1638,6 +1721,15 @@ ice_get_ethtool_stats(struct net_device *netdev, ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC | \ ICE_PHY_TYPE_HIGH_100G_AUI2) +#define ICE_PHY_TYPE_HIGH_MASK_200G (ICE_PHY_TYPE_HIGH_200G_CR4_PAM4 | \ + ICE_PHY_TYPE_HIGH_200G_SR4 | \ + ICE_PHY_TYPE_HIGH_200G_FR4 | \ + ICE_PHY_TYPE_HIGH_200G_LR4 | \ + ICE_PHY_TYPE_HIGH_200G_DR4 | \ + ICE_PHY_TYPE_HIGH_200G_KR4_PAM4 | \ + ICE_PHY_TYPE_HIGH_200G_AUI4_AOC_ACC | \ + ICE_PHY_TYPE_HIGH_200G_AUI4) + /** * ice_mask_min_supported_speeds * @hw: pointer to the HW structure @@ -1652,8 +1744,9 @@ ice_mask_min_supported_speeds(struct ice_hw *hw, u64 phy_types_high, u64 *phy_types_low) { /* if QSFP connection with 100G speed, minimum supported speed is 25G */ - if (*phy_types_low & ICE_PHY_TYPE_LOW_MASK_100G || - phy_types_high & ICE_PHY_TYPE_HIGH_MASK_100G) + if ((*phy_types_low & ICE_PHY_TYPE_LOW_MASK_100G) || + (phy_types_high & ICE_PHY_TYPE_HIGH_MASK_100G) || + (phy_types_high & ICE_PHY_TYPE_HIGH_MASK_200G)) *phy_types_low &= ~ICE_PHY_TYPE_LOW_MASK_MIN_25G; else if (!ice_is_100m_speed_supported(hw)) *phy_types_low &= ~ICE_PHY_TYPE_LOW_MASK_MIN_1G; @@ -1757,14 +1850,14 @@ ice_phy_type_to_ethtool(struct net_device *netdev, linkmode_zero(ks->link_modes.supported); linkmode_zero(ks->link_modes.advertising); - for (i = 0; i < BITS_PER_TYPE(u64); i++) { + for (i = 0; i < ARRAY_SIZE(phy_type_low_lkup); i++) { if (phy_types_low & BIT_ULL(i)) ice_linkmode_set_bit(&phy_type_low_lkup[i], ks, req_speeds, advert_phy_type_lo, i); } - for (i = 0; i < BITS_PER_TYPE(u64); i++) { + for (i = 0; i < ARRAY_SIZE(phy_type_high_lkup); i++) { if (phy_types_high & BIT_ULL(i)) ice_linkmode_set_bit(&phy_type_high_lkup[i], ks, req_speeds, advert_phy_type_hi, @@ -1796,6 +1889,9 @@ ice_get_settings_link_up(struct ethtool_link_ksettings *ks, ice_phy_type_to_ethtool(netdev, ks); switch (link_info->link_speed) { + case ICE_AQ_LINK_SPEED_200GB: + ks->base.speed = SPEED_200000; + break; case ICE_AQ_LINK_SPEED_100GB: ks->base.speed = SPEED_100000; break; @@ -2008,79 +2104,69 @@ done: } /** + * ice_speed_to_aq_link - Get AQ link speed by Ethtool forced speed + * @speed: ethtool forced speed + */ +static u16 ice_speed_to_aq_link(int speed) +{ + int aq_speed; + + switch (speed) { + case SPEED_10: + aq_speed = ICE_AQ_LINK_SPEED_10MB; + break; + case SPEED_100: + aq_speed = ICE_AQ_LINK_SPEED_100MB; + break; + case SPEED_1000: + aq_speed = ICE_AQ_LINK_SPEED_1000MB; + break; + case SPEED_2500: + aq_speed = ICE_AQ_LINK_SPEED_2500MB; + break; + case SPEED_5000: + aq_speed = ICE_AQ_LINK_SPEED_5GB; + break; + case SPEED_10000: + aq_speed = ICE_AQ_LINK_SPEED_10GB; + break; + case SPEED_20000: + aq_speed = ICE_AQ_LINK_SPEED_20GB; + break; + case SPEED_25000: + aq_speed = ICE_AQ_LINK_SPEED_25GB; + break; + case SPEED_40000: + aq_speed = ICE_AQ_LINK_SPEED_40GB; + break; + case SPEED_50000: + aq_speed = ICE_AQ_LINK_SPEED_50GB; + break; + case SPEED_100000: + aq_speed = ICE_AQ_LINK_SPEED_100GB; + break; + default: + aq_speed = ICE_AQ_LINK_SPEED_UNKNOWN; + break; + } + return aq_speed; +} + +/** * ice_ksettings_find_adv_link_speed - Find advertising link speed * @ks: ethtool ksettings */ static u16 ice_ksettings_find_adv_link_speed(const struct ethtool_link_ksettings *ks) { + const struct ethtool_forced_speed_map *map; u16 adv_link_speed = 0; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, - 100baseT_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_100MB; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, - 1000baseX_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 1000baseT_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 1000baseKX_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_1000MB; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, - 2500baseT_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 2500baseX_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_2500MB; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, - 5000baseT_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_5GB; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, - 10000baseT_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 10000baseKR_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 10000baseSR_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 10000baseLR_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_10GB; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, - 25000baseCR_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 25000baseSR_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 25000baseKR_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_25GB; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, - 40000baseCR4_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 40000baseSR4_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 40000baseLR4_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 40000baseKR4_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_40GB; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, - 50000baseCR2_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 50000baseKR2_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 50000baseSR2_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_50GB; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, - 100000baseCR4_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 100000baseSR4_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 100000baseLR4_ER4_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 100000baseKR4_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 100000baseCR2_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 100000baseSR2_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 100000baseKR2_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_100GB; + for (u32 i = 0; i < ARRAY_SIZE(ice_adv_lnk_speed_maps); i++) { + map = ice_adv_lnk_speed_maps + i; + if (linkmode_intersects(ks->link_modes.advertising, map->caps)) + adv_link_speed |= ice_speed_to_aq_link(map->speed); + } return adv_link_speed; } @@ -3285,7 +3371,7 @@ ice_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) SOF_TIMESTAMPING_RX_HARDWARE | SOF_TIMESTAMPING_RAW_HARDWARE; - info->phc_index = ice_get_ptp_clock_index(pf); + info->phc_index = ice_ptp_clock_index(pf); info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON); diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.h b/drivers/net/ethernet/intel/ice/ice_ethtool.h index b403ee79cd5e..b88e3da06f13 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.h +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.h @@ -100,6 +100,14 @@ phy_type_high_lkup[] = { [2] = ICE_PHY_TYPE(100GB, 100000baseCR2_Full), [3] = ICE_PHY_TYPE(100GB, 100000baseSR2_Full), [4] = ICE_PHY_TYPE(100GB, 100000baseCR2_Full), + [5] = ICE_PHY_TYPE(200GB, 200000baseCR4_Full), + [6] = ICE_PHY_TYPE(200GB, 200000baseSR4_Full), + [7] = ICE_PHY_TYPE(200GB, 200000baseLR4_ER4_FR4_Full), + [8] = ICE_PHY_TYPE(200GB, 200000baseLR4_ER4_FR4_Full), + [9] = ICE_PHY_TYPE(200GB, 200000baseDR4_Full), + [10] = ICE_PHY_TYPE(200GB, 200000baseKR4_Full), + [11] = ICE_PHY_TYPE(200GB, 200000baseSR4_Full), + [12] = ICE_PHY_TYPE(200GB, 200000baseCR4_Full), }; #endif /* !_ICE_ETHTOOL_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c index 8c6e13f87b7d..d151e5bacfec 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2018-2020, Intel Corporation. */ +/* Copyright (C) 2018-2023, Intel Corporation. */ /* flow director ethtool support for ice */ @@ -540,16 +540,24 @@ static int ice_fdir_num_avail_fltr(struct ice_hw *hw, struct ice_vsi *vsi) /* total guaranteed filters assigned to this VSI */ num_guar = vsi->num_gfltr; - /* minus the guaranteed filters programed by this VSI */ - num_guar -= (rd32(hw, VSIQF_FD_CNT(vsi_num)) & - VSIQF_FD_CNT_FD_GCNT_M) >> VSIQF_FD_CNT_FD_GCNT_S; - /* total global best effort filters */ num_be = hw->func_caps.fd_fltr_best_effort; - /* minus the global best effort filters programmed */ - num_be -= (rd32(hw, GLQF_FD_CNT) & GLQF_FD_CNT_FD_BCNT_M) >> - GLQF_FD_CNT_FD_BCNT_S; + /* Subtract the number of programmed filters from the global values */ + switch (hw->mac_type) { + case ICE_MAC_E830: + num_guar -= FIELD_GET(E830_VSIQF_FD_CNT_FD_GCNT_M, + rd32(hw, VSIQF_FD_CNT(vsi_num))); + num_be -= FIELD_GET(E830_GLQF_FD_CNT_FD_BCNT_M, + rd32(hw, GLQF_FD_CNT)); + break; + case ICE_MAC_E810: + default: + num_guar -= FIELD_GET(E800_VSIQF_FD_CNT_FD_GCNT_M, + rd32(hw, VSIQF_FD_CNT(vsi_num))); + num_be -= FIELD_GET(E800_GLQF_FD_CNT_FD_BCNT_M, + rd32(hw, GLQF_FD_CNT)); + } return num_guar + num_be; } diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c index 85cca572c22a..fb8b925aaf8b 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.c +++ b/drivers/net/ethernet/intel/ice/ice_flow.c @@ -1318,7 +1318,6 @@ ice_flow_rem_entry_sync(struct ice_hw *hw, enum ice_block __always_unused blk, list_del(&entry->l_entry); - devm_kfree(ice_hw_to_dev(hw), entry->entry); devm_kfree(ice_hw_to_dev(hw), entry); return 0; @@ -1645,10 +1644,8 @@ ice_flow_add_entry(struct ice_hw *hw, enum ice_block blk, u64 prof_id, *entry_h = ICE_FLOW_ENTRY_HNDL(e); out: - if (status && e) { - devm_kfree(ice_hw_to_dev(hw), e->entry); + if (status) devm_kfree(ice_hw_to_dev(hw), e); - } return status; } diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h index b465d27d9b80..96923ef0a5a8 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.h +++ b/drivers/net/ethernet/intel/ice/ice_flow.h @@ -350,11 +350,8 @@ struct ice_flow_entry { u64 id; struct ice_flow_prof *prof; - /* Flow entry's content */ - void *entry; enum ice_flow_priority priority; u16 vsi_handle; - u16 entry_sz; }; #define ICE_FLOW_ENTRY_HNDL(e) ((u64)(uintptr_t)e) diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c index 3dc5662d62a6..319a2d6fe26c 100644 --- a/drivers/net/ethernet/intel/ice/ice_fw_update.c +++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c @@ -293,16 +293,17 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, { u16 completion_module, completion_retval; struct device *dev = ice_pf_to_dev(pf); - struct ice_rq_event_info event; + struct ice_aq_task task = {}; struct ice_hw *hw = &pf->hw; + struct ice_aq_desc *desc; u32 completion_offset; int err; - memset(&event, 0, sizeof(event)); - dev_dbg(dev, "Writing block of %u bytes for module 0x%02x at offset %u\n", block_size, module, offset); + ice_aq_prep_for_event(pf, &task, ice_aqc_opc_nvm_write); + err = ice_aq_update_nvm(hw, module, offset, block_size, block, last_cmd, 0, NULL); if (err) { @@ -319,7 +320,7 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, * is conservative and is intended to prevent failure to update when * firmware is slow to respond. */ - err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_write, 15 * HZ, &event); + err = ice_aq_wait_for_event(pf, &task, 15 * HZ); if (err) { dev_err(dev, "Timed out while trying to flash module 0x%02x with block of size %u at offset %u, err %d\n", module, block_size, offset, err); @@ -327,11 +328,12 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, return -EIO; } - completion_module = le16_to_cpu(event.desc.params.nvm.module_typeid); - completion_retval = le16_to_cpu(event.desc.retval); + desc = &task.event.desc; + completion_module = le16_to_cpu(desc->params.nvm.module_typeid); + completion_retval = le16_to_cpu(desc->retval); - completion_offset = le16_to_cpu(event.desc.params.nvm.offset_low); - completion_offset |= event.desc.params.nvm.offset_high << 16; + completion_offset = le16_to_cpu(desc->params.nvm.offset_low); + completion_offset |= desc->params.nvm.offset_high << 16; if (completion_module != module) { dev_err(dev, "Unexpected module_typeid in write completion: got 0x%x, expected 0x%x\n", @@ -363,8 +365,8 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, */ if (reset_level && last_cmd && module == ICE_SR_1ST_NVM_BANK_PTR) { if (hw->dev_caps.common_cap.pcie_reset_avoidance) { - *reset_level = (event.desc.params.nvm.cmd_flags & - ICE_AQC_NVM_RESET_LVL_M); + *reset_level = desc->params.nvm.cmd_flags & + ICE_AQC_NVM_RESET_LVL_M; dev_dbg(dev, "Firmware reported required reset level as %u\n", *reset_level); } else { @@ -479,19 +481,20 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component, { u16 completion_module, completion_retval; struct device *dev = ice_pf_to_dev(pf); - struct ice_rq_event_info event; + struct ice_aq_task task = {}; struct ice_hw *hw = &pf->hw; + struct ice_aq_desc *desc; struct devlink *devlink; int err; dev_dbg(dev, "Beginning erase of flash component '%s', module 0x%02x\n", component, module); - memset(&event, 0, sizeof(event)); - devlink = priv_to_devlink(pf); devlink_flash_update_timeout_notify(devlink, "Erasing", component, ICE_FW_ERASE_TIMEOUT); + ice_aq_prep_for_event(pf, &task, ice_aqc_opc_nvm_erase); + err = ice_aq_erase_nvm(hw, module, NULL); if (err) { dev_err(dev, "Failed to erase %s (module 0x%02x), err %d aq_err %s\n", @@ -502,7 +505,7 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component, goto out_notify_devlink; } - err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_erase, ICE_FW_ERASE_TIMEOUT * HZ, &event); + err = ice_aq_wait_for_event(pf, &task, ICE_FW_ERASE_TIMEOUT * HZ); if (err) { dev_err(dev, "Timed out waiting for firmware to respond with erase completion for %s (module 0x%02x), err %d\n", component, module, err); @@ -510,8 +513,9 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component, goto out_notify_devlink; } - completion_module = le16_to_cpu(event.desc.params.nvm.module_typeid); - completion_retval = le16_to_cpu(event.desc.retval); + desc = &task.event.desc; + completion_module = le16_to_cpu(desc->params.nvm.module_typeid); + completion_retval = le16_to_cpu(desc->retval); if (completion_module != module) { dev_err(dev, "Unexpected module_typeid in erase completion for %s: got 0x%x, expected 0x%x\n", @@ -560,13 +564,13 @@ ice_switch_flash_banks(struct ice_pf *pf, u8 activate_flags, u8 *emp_reset_available, struct netlink_ext_ack *extack) { struct device *dev = ice_pf_to_dev(pf); - struct ice_rq_event_info event; + struct ice_aq_task task = {}; struct ice_hw *hw = &pf->hw; u16 completion_retval; u8 response_flags; int err; - memset(&event, 0, sizeof(event)); + ice_aq_prep_for_event(pf, &task, ice_aqc_opc_nvm_write_activate); err = ice_nvm_write_activate(hw, activate_flags, &response_flags); if (err) { @@ -592,8 +596,7 @@ ice_switch_flash_banks(struct ice_pf *pf, u8 activate_flags, } } - err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_write_activate, 30 * HZ, - &event); + err = ice_aq_wait_for_event(pf, &task, 30 * HZ); if (err) { dev_err(dev, "Timed out waiting for firmware to switch active flash banks, err %d\n", err); @@ -601,7 +604,7 @@ ice_switch_flash_banks(struct ice_pf *pf, u8 activate_flags, return err; } - completion_retval = le16_to_cpu(event.desc.retval); + completion_retval = le16_to_cpu(task.event.desc.retval); if (completion_retval) { dev_err(dev, "Firmware failed to switch active flash banks aq_err %s\n", ice_aq_str((enum ice_aq_err)completion_retval)); diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c index 75c9de675f20..c8ea1af51ad3 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.c +++ b/drivers/net/ethernet/intel/ice/ice_gnss.c @@ -389,6 +389,9 @@ bool ice_gnss_is_gps_present(struct ice_hw *hw) if (!hw->func_caps.ts_func_info.src_tmr_owned) return false; + if (!ice_is_gps_in_netlist(hw)) + return false; + #if IS_ENABLED(CONFIG_PTP_1588_CLOCK) if (ice_is_e810t(hw)) { int err; diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index a92dc9a16035..86936b758ade 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (c) 2018, Intel Corporation. */ +/* Copyright (c) 2018-2023, Intel Corporation. */ /* Machine-generated file */ @@ -231,6 +231,7 @@ #define PFINT_SB_CTL 0x0016B600 #define PFINT_SB_CTL_MSIX_INDX_M ICE_M(0x7FF, 0) #define PFINT_SB_CTL_CAUSE_ENA_M BIT(30) +#define PFINT_TSYN_MSK 0x0016C980 #define QINT_RQCTL(_QRX) (0x00150000 + ((_QRX) * 4)) #define QINT_RQCTL_MSIX_INDX_S 0 #define QINT_RQCTL_MSIX_INDX_M ICE_M(0x7FF, 0) @@ -284,11 +285,11 @@ #define VPLAN_TX_QBASE_VFNUMQ_M ICE_M(0xFF, 16) #define VPLAN_TXQ_MAPENA(_VF) (0x00073800 + ((_VF) * 4)) #define VPLAN_TXQ_MAPENA_TX_ENA_M BIT(0) -#define PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA(_i) (0x001E36E0 + ((_i) * 32)) -#define PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_MAX_INDEX 8 -#define PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_HSEC_CTL_TX_PAUSE_QUANTA_M ICE_M(0xFFFF, 0) -#define PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER(_i) (0x001E3800 + ((_i) * 32)) -#define PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_M ICE_M(0xFFFF, 0) +#define E800_PRTMAC_HSEC_CTL_TX_PS_QNT(_i) (0x001E36E0 + ((_i) * 32)) +#define E800_PRTMAC_HSEC_CTL_TX_PS_QNT_MAX 8 +#define E800_PRTMAC_HSEC_CTL_TX_PS_QNT_M GENMASK(15, 0) +#define E800_PRTMAC_HSEC_CTL_TX_PS_RFSH_TMR(_i) (0x001E3800 + ((_i) * 32)) +#define E800_PRTMAC_HSEC_CTL_TX_PS_RFSH_TMR_M GENMASK(15, 0) #define GL_MDCK_TX_TDPU 0x00049348 #define GL_MDCK_TX_TDPU_RCU_ANTISPOOF_ITR_DIS_M BIT(1) #define GL_MDET_RX 0x00294C00 @@ -311,7 +312,11 @@ #define GL_MDET_TX_PQM_MAL_TYPE_S 26 #define GL_MDET_TX_PQM_MAL_TYPE_M ICE_M(0x1F, 26) #define GL_MDET_TX_PQM_VALID_M BIT(31) -#define GL_MDET_TX_TCLAN 0x000FC068 +#define GL_MDET_TX_TCLAN_BY_MAC(hw) \ + ((hw)->mac_type == ICE_MAC_E830 ? E830_GL_MDET_TX_TCLAN : \ + E800_GL_MDET_TX_TCLAN) +#define E800_GL_MDET_TX_TCLAN 0x000FC068 +#define E830_GL_MDET_TX_TCLAN 0x000FCCC0 #define GL_MDET_TX_TCLAN_QNUM_S 0 #define GL_MDET_TX_TCLAN_QNUM_M ICE_M(0x7FFF, 0) #define GL_MDET_TX_TCLAN_VF_NUM_S 15 @@ -325,7 +330,11 @@ #define PF_MDET_RX_VALID_M BIT(0) #define PF_MDET_TX_PQM 0x002D2C80 #define PF_MDET_TX_PQM_VALID_M BIT(0) -#define PF_MDET_TX_TCLAN 0x000FC000 +#define PF_MDET_TX_TCLAN_BY_MAC(hw) \ + ((hw)->mac_type == ICE_MAC_E830 ? E830_PF_MDET_TX_TCLAN : \ + E800_PF_MDET_TX_TCLAN) +#define E800_PF_MDET_TX_TCLAN 0x000FC000 +#define E830_PF_MDET_TX_TCLAN 0x000FCC00 #define PF_MDET_TX_TCLAN_VALID_M BIT(0) #define VP_MDET_RX(_VF) (0x00294400 + ((_VF) * 4)) #define VP_MDET_RX_VALID_M BIT(0) @@ -335,6 +344,10 @@ #define VP_MDET_TX_TCLAN_VALID_M BIT(0) #define VP_MDET_TX_TDPU(_VF) (0x00040000 + ((_VF) * 4)) #define VP_MDET_TX_TDPU_VALID_M BIT(0) +#define E800_GL_MNG_FWSM_FW_MODES_M GENMASK(2, 0) +#define E830_GL_MNG_FWSM_FW_MODES_M GENMASK(1, 0) +#define GL_MNG_FWSM 0x000B6134 +#define GL_MNG_FWSM_FW_LOADING_M BIT(30) #define GLNVM_FLA 0x000B6108 #define GLNVM_FLA_LOCKED_M BIT(6) #define GLNVM_GENS 0x000B6100 @@ -361,13 +374,18 @@ #define GL_PWR_MODE_CTL_CAR_MAX_BW_S 30 #define GL_PWR_MODE_CTL_CAR_MAX_BW_M ICE_M(0x3, 30) #define GLQF_FD_CNT 0x00460018 +#define E800_GLQF_FD_CNT_FD_GCNT_M GENMASK(14, 0) +#define E830_GLQF_FD_CNT_FD_GCNT_M GENMASK(15, 0) #define GLQF_FD_CNT_FD_BCNT_S 16 -#define GLQF_FD_CNT_FD_BCNT_M ICE_M(0x7FFF, 16) +#define E800_GLQF_FD_CNT_FD_BCNT_M GENMASK(30, 16) +#define E830_GLQF_FD_CNT_FD_BCNT_M GENMASK(31, 16) #define GLQF_FD_SIZE 0x00460010 #define GLQF_FD_SIZE_FD_GSIZE_S 0 -#define GLQF_FD_SIZE_FD_GSIZE_M ICE_M(0x7FFF, 0) +#define E800_GLQF_FD_SIZE_FD_GSIZE_M GENMASK(14, 0) +#define E830_GLQF_FD_SIZE_FD_GSIZE_M GENMASK(15, 0) #define GLQF_FD_SIZE_FD_BSIZE_S 16 -#define GLQF_FD_SIZE_FD_BSIZE_M ICE_M(0x7FFF, 16) +#define E800_GLQF_FD_SIZE_FD_BSIZE_M GENMASK(30, 16) +#define E830_GLQF_FD_SIZE_FD_BSIZE_M GENMASK(31, 16) #define GLQF_FDINSET(_i, _j) (0x00412000 + ((_i) * 4 + (_j) * 512)) #define GLQF_FDMASK(_i) (0x00410800 + ((_i) * 4)) #define GLQF_FDMASK_MAX_INDEX 31 @@ -386,6 +404,10 @@ #define GLQF_HMASK_SEL(_i) (0x00410000 + ((_i) * 4)) #define GLQF_HMASK_SEL_MAX_INDEX 127 #define GLQF_HMASK_SEL_MASK_SEL_S 0 +#define E800_PFQF_FD_CNT_FD_GCNT_M GENMASK(14, 0) +#define E830_PFQF_FD_CNT_FD_GCNT_M GENMASK(15, 0) +#define E800_PFQF_FD_CNT_FD_BCNT_M GENMASK(30, 16) +#define E830_PFQF_FD_CNT_FD_BCNT_M GENMASK(31, 16) #define PFQF_FD_ENA 0x0043A000 #define PFQF_FD_ENA_FD_ENA_M BIT(0) #define PFQF_FD_SIZE 0x00460100 @@ -476,6 +498,7 @@ #define GLTSYN_SYNC_DLAY 0x00088818 #define GLTSYN_TGT_H_0(_i) (0x00088930 + ((_i) * 4)) #define GLTSYN_TGT_L_0(_i) (0x00088928 + ((_i) * 4)) +#define GLTSYN_TIME_0(_i) (0x000888C8 + ((_i) * 4)) #define GLTSYN_TIME_H(_i) (0x000888D8 + ((_i) * 4)) #define GLTSYN_TIME_L(_i) (0x000888D0 + ((_i) * 4)) #define PFHH_SEM 0x000A4200 /* Reset Source: PFR */ @@ -484,12 +507,13 @@ #define PFTSYN_SEM_BUSY_M BIT(0) #define VSIQF_FD_CNT(_VSI) (0x00464000 + ((_VSI) * 4)) #define VSIQF_FD_CNT_FD_GCNT_S 0 -#define VSIQF_FD_CNT_FD_GCNT_M ICE_M(0x3FFF, 0) +#define E800_VSIQF_FD_CNT_FD_GCNT_M GENMASK(13, 0) +#define E830_VSIQF_FD_CNT_FD_GCNT_M GENMASK(15, 0) #define VSIQF_FD_CNT_FD_BCNT_S 16 -#define VSIQF_FD_CNT_FD_BCNT_M ICE_M(0x3FFF, 16) +#define E800_VSIQF_FD_CNT_FD_BCNT_M GENMASK(29, 16) +#define E830_VSIQF_FD_CNT_FD_BCNT_M GENMASK(31, 16) #define VSIQF_FD_SIZE(_VSI) (0x00462000 + ((_VSI) * 4)) #define VSIQF_HKEY_MAX_INDEX 12 -#define VSIQF_HLUT_MAX_INDEX 15 #define PFPM_APM 0x000B8080 #define PFPM_APM_APME_M BIT(0) #define PFPM_WUFC 0x0009DC00 @@ -499,6 +523,10 @@ #define PFPM_WUS_MAG_M BIT(1) #define PFPM_WUS_MNG_M BIT(3) #define PFPM_WUS_FW_RST_WK_M BIT(31) +#define E830_PRTMAC_CL01_PS_QNT 0x001E32A0 +#define E830_PRTMAC_CL01_PS_QNT_CL0_M GENMASK(15, 0) +#define E830_PRTMAC_CL01_QNT_THR 0x001E3320 +#define E830_PRTMAC_CL01_QNT_THR_CL0_M GENMASK(15, 0) #define VFINT_DYN_CTLN(_i) (0x00003800 + ((_i) * 4)) #define VFINT_DYN_CTLN_CLEARPBA_M BIT(1) diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index 5a7753bda324..b47cd43ae871 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -4,8 +4,27 @@ /* Link Aggregation code */ #include "ice.h" +#include "ice_lib.h" #include "ice_lag.h" +#define ICE_LAG_RES_SHARED BIT(14) +#define ICE_LAG_RES_VALID BIT(15) + +#define LACP_TRAIN_PKT_LEN 16 +static const u8 lacp_train_pkt[LACP_TRAIN_PKT_LEN] = { 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, + 0x88, 0x09, 0, 0 }; + +#define ICE_RECIPE_LEN 64 +static const u8 ice_dflt_vsi_rcp[ICE_RECIPE_LEN] = { + 0x05, 0, 0, 0, 0x20, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0x85, 0, 0x01, 0, 0, 0, 0xff, 0xff, 0x08, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0x30 }; +static const u8 ice_lport_rcp[ICE_RECIPE_LEN] = { + 0x05, 0, 0, 0, 0x20, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0x85, 0, 0x16, 0, 0, 0, 0xff, 0xff, 0x07, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0x30 }; + /** * ice_lag_set_primary - set PF LAG state as Primary * @lag: LAG info struct @@ -47,16 +66,257 @@ static void ice_lag_set_backup(struct ice_lag *lag) } /** + * netif_is_same_ice - determine if netdev is on the same ice NIC as local PF + * @pf: local PF struct + * @netdev: netdev we are evaluating + */ +static bool netif_is_same_ice(struct ice_pf *pf, struct net_device *netdev) +{ + struct ice_netdev_priv *np; + struct ice_pf *test_pf; + struct ice_vsi *vsi; + + if (!netif_is_ice(netdev)) + return false; + + np = netdev_priv(netdev); + if (!np) + return false; + + vsi = np->vsi; + if (!vsi) + return false; + + test_pf = vsi->back; + if (!test_pf) + return false; + + if (pf->pdev->bus != test_pf->pdev->bus || + pf->pdev->slot != test_pf->pdev->slot) + return false; + + return true; +} + +/** + * ice_netdev_to_lag - return pointer to associated lag struct from netdev + * @netdev: pointer to net_device struct to query + */ +static struct ice_lag *ice_netdev_to_lag(struct net_device *netdev) +{ + struct ice_netdev_priv *np; + struct ice_vsi *vsi; + + if (!netif_is_ice(netdev)) + return NULL; + + np = netdev_priv(netdev); + if (!np) + return NULL; + + vsi = np->vsi; + if (!vsi) + return NULL; + + return vsi->back->lag; +} + +/** + * ice_lag_find_hw_by_lport - return an hw struct from bond members lport + * @lag: lag struct + * @lport: lport value to search for + */ +static struct ice_hw * +ice_lag_find_hw_by_lport(struct ice_lag *lag, u8 lport) +{ + struct ice_lag_netdev_list *entry; + struct net_device *tmp_netdev; + struct ice_netdev_priv *np; + struct ice_hw *hw; + + list_for_each_entry(entry, lag->netdev_head, node) { + tmp_netdev = entry->netdev; + if (!tmp_netdev || !netif_is_ice(tmp_netdev)) + continue; + + np = netdev_priv(tmp_netdev); + if (!np || !np->vsi) + continue; + + hw = &np->vsi->back->hw; + if (hw->port_info->lport == lport) + return hw; + } + + return NULL; +} + +/** + * ice_lag_find_primary - returns pointer to primary interfaces lag struct + * @lag: local interfaces lag struct + */ +static struct ice_lag *ice_lag_find_primary(struct ice_lag *lag) +{ + struct ice_lag *primary_lag = NULL; + struct list_head *tmp; + + list_for_each(tmp, lag->netdev_head) { + struct ice_lag_netdev_list *entry; + struct ice_lag *tmp_lag; + + entry = list_entry(tmp, struct ice_lag_netdev_list, node); + tmp_lag = ice_netdev_to_lag(entry->netdev); + if (tmp_lag && tmp_lag->primary) { + primary_lag = tmp_lag; + break; + } + } + + return primary_lag; +} + +/** + * ice_lag_cfg_fltr - Add/Remove rule for LAG + * @lag: lag struct for local interface + * @act: rule action + * @recipe_id: recipe id for the new rule + * @rule_idx: pointer to rule index + * @add: boolean on whether we are adding filters + */ +static int +ice_lag_cfg_fltr(struct ice_lag *lag, u32 act, u16 recipe_id, u16 *rule_idx, + bool add) +{ + struct ice_sw_rule_lkup_rx_tx *s_rule; + u16 s_rule_sz, vsi_num; + struct ice_hw *hw; + u8 *eth_hdr; + u32 opc; + int err; + + hw = &lag->pf->hw; + vsi_num = ice_get_hw_vsi_num(hw, 0); + + s_rule_sz = ICE_SW_RULE_RX_TX_ETH_HDR_SIZE(s_rule); + s_rule = kzalloc(s_rule_sz, GFP_KERNEL); + if (!s_rule) { + dev_err(ice_pf_to_dev(lag->pf), "error allocating rule for LAG\n"); + return -ENOMEM; + } + + if (add) { + eth_hdr = s_rule->hdr_data; + ice_fill_eth_hdr(eth_hdr); + + act |= (vsi_num << ICE_SINGLE_ACT_VSI_ID_S) & + ICE_SINGLE_ACT_VSI_ID_M; + + s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX); + s_rule->recipe_id = cpu_to_le16(recipe_id); + s_rule->src = cpu_to_le16(hw->port_info->lport); + s_rule->act = cpu_to_le32(act); + s_rule->hdr_len = cpu_to_le16(DUMMY_ETH_HDR_LEN); + opc = ice_aqc_opc_add_sw_rules; + } else { + s_rule->index = cpu_to_le16(*rule_idx); + opc = ice_aqc_opc_remove_sw_rules; + } + + err = ice_aq_sw_rules(&lag->pf->hw, s_rule, s_rule_sz, 1, opc, NULL); + if (err) + goto dflt_fltr_free; + + if (add) + *rule_idx = le16_to_cpu(s_rule->index); + else + *rule_idx = 0; + +dflt_fltr_free: + kfree(s_rule); + return err; +} + +/** + * ice_lag_cfg_dflt_fltr - Add/Remove default VSI rule for LAG + * @lag: lag struct for local interface + * @add: boolean on whether to add filter + */ +static int +ice_lag_cfg_dflt_fltr(struct ice_lag *lag, bool add) +{ + u32 act = ICE_SINGLE_ACT_VSI_FORWARDING | + ICE_SINGLE_ACT_VALID_BIT | ICE_SINGLE_ACT_LAN_ENABLE; + + return ice_lag_cfg_fltr(lag, act, lag->pf_recipe, + &lag->pf_rule_id, add); +} + +/** + * ice_lag_cfg_drop_fltr - Add/Remove lport drop rule + * @lag: lag struct for local interface + * @add: boolean on whether to add filter + */ +static int +ice_lag_cfg_drop_fltr(struct ice_lag *lag, bool add) +{ + u32 act = ICE_SINGLE_ACT_VSI_FORWARDING | + ICE_SINGLE_ACT_VALID_BIT | + ICE_SINGLE_ACT_DROP; + + return ice_lag_cfg_fltr(lag, act, lag->lport_recipe, + &lag->lport_rule_idx, add); +} + +/** + * ice_lag_cfg_pf_fltrs - set filters up for new active port + * @lag: local interfaces lag struct + * @ptr: opaque data containing notifier event + */ +static void +ice_lag_cfg_pf_fltrs(struct ice_lag *lag, void *ptr) +{ + struct netdev_notifier_bonding_info *info; + struct netdev_bonding_info *bonding_info; + struct net_device *event_netdev; + struct device *dev; + + event_netdev = netdev_notifier_info_to_dev(ptr); + /* not for this netdev */ + if (event_netdev != lag->netdev) + return; + + info = (struct netdev_notifier_bonding_info *)ptr; + bonding_info = &info->bonding_info; + dev = ice_pf_to_dev(lag->pf); + + /* interface not active - remove old default VSI rule */ + if (bonding_info->slave.state && lag->pf_rule_id) { + if (ice_lag_cfg_dflt_fltr(lag, false)) + dev_err(dev, "Error removing old default VSI filter\n"); + if (ice_lag_cfg_drop_fltr(lag, true)) + dev_err(dev, "Error adding new drop filter\n"); + return; + } + + /* interface becoming active - add new default VSI rule */ + if (!bonding_info->slave.state && !lag->pf_rule_id) { + if (ice_lag_cfg_dflt_fltr(lag, true)) + dev_err(dev, "Error adding new default VSI filter\n"); + if (lag->lport_rule_idx && ice_lag_cfg_drop_fltr(lag, false)) + dev_err(dev, "Error removing old drop filter\n"); + } +} + +/** * ice_display_lag_info - print LAG info * @lag: LAG info struct */ static void ice_display_lag_info(struct ice_lag *lag) { - const char *name, *peer, *upper, *role, *bonded, *primary; + const char *name, *upper, *role, *bonded, *primary; struct device *dev = &lag->pf->pdev->dev; name = lag->netdev ? netdev_name(lag->netdev) : "unset"; - peer = lag->peer_netdev ? netdev_name(lag->peer_netdev) : "unset"; upper = lag->upper_netdev ? netdev_name(lag->upper_netdev) : "unset"; primary = lag->primary ? "TRUE" : "FALSE"; bonded = lag->bonded ? "BONDED" : "UNBONDED"; @@ -78,8 +338,445 @@ static void ice_display_lag_info(struct ice_lag *lag) role = "ERROR"; } - dev_dbg(dev, "%s %s, peer:%s, upper:%s, role:%s, primary:%s\n", name, - bonded, peer, upper, role, primary); + dev_dbg(dev, "%s %s, upper:%s, role:%s, primary:%s\n", name, bonded, + upper, role, primary); +} + +/** + * ice_lag_qbuf_recfg - generate a buffer of queues for a reconfigure command + * @hw: HW struct that contains the queue contexts + * @qbuf: pointer to buffer to populate + * @vsi_num: index of the VSI in PF space + * @numq: number of queues to search for + * @tc: traffic class that contains the queues + * + * function returns the number of valid queues in buffer + */ +static u16 +ice_lag_qbuf_recfg(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *qbuf, + u16 vsi_num, u16 numq, u8 tc) +{ + struct ice_q_ctx *q_ctx; + u16 qid, count = 0; + struct ice_pf *pf; + int i; + + pf = hw->back; + for (i = 0; i < numq; i++) { + q_ctx = ice_get_lan_q_ctx(hw, vsi_num, tc, i); + if (!q_ctx) { + dev_dbg(ice_hw_to_dev(hw), "%s queue %d NO Q CONTEXT\n", + __func__, i); + continue; + } + if (q_ctx->q_teid == ICE_INVAL_TEID) { + dev_dbg(ice_hw_to_dev(hw), "%s queue %d INVAL TEID\n", + __func__, i); + continue; + } + if (q_ctx->q_handle == ICE_INVAL_Q_HANDLE) { + dev_dbg(ice_hw_to_dev(hw), "%s queue %d INVAL Q HANDLE\n", + __func__, i); + continue; + } + + qid = pf->vsi[vsi_num]->txq_map[q_ctx->q_handle]; + qbuf->queue_info[count].q_handle = cpu_to_le16(qid); + qbuf->queue_info[count].tc = tc; + qbuf->queue_info[count].q_teid = cpu_to_le32(q_ctx->q_teid); + count++; + } + + return count; +} + +/** + * ice_lag_get_sched_parent - locate or create a sched node parent + * @hw: HW struct for getting parent in + * @tc: traffic class on parent/node + */ +static struct ice_sched_node * +ice_lag_get_sched_parent(struct ice_hw *hw, u8 tc) +{ + struct ice_sched_node *tc_node, *aggnode, *parent = NULL; + u16 num_nodes[ICE_AQC_TOPO_MAX_LEVEL_NUM] = { 0 }; + struct ice_port_info *pi = hw->port_info; + struct device *dev; + u8 aggl, vsil; + int n; + + dev = ice_hw_to_dev(hw); + + tc_node = ice_sched_get_tc_node(pi, tc); + if (!tc_node) { + dev_warn(dev, "Failure to find TC node for LAG move\n"); + return parent; + } + + aggnode = ice_sched_get_agg_node(pi, tc_node, ICE_DFLT_AGG_ID); + if (!aggnode) { + dev_warn(dev, "Failure to find aggregate node for LAG move\n"); + return parent; + } + + aggl = ice_sched_get_agg_layer(hw); + vsil = ice_sched_get_vsi_layer(hw); + + for (n = aggl + 1; n < vsil; n++) + num_nodes[n] = 1; + + for (n = 0; n < aggnode->num_children; n++) { + parent = ice_sched_get_free_vsi_parent(hw, aggnode->children[n], + num_nodes); + if (parent) + return parent; + } + + /* if free parent not found - add one */ + parent = aggnode; + for (n = aggl + 1; n < vsil; n++) { + u16 num_nodes_added; + u32 first_teid; + int err; + + err = ice_sched_add_nodes_to_layer(pi, tc_node, parent, n, + num_nodes[n], &first_teid, + &num_nodes_added); + if (err || num_nodes[n] != num_nodes_added) + return NULL; + + if (num_nodes_added) + parent = ice_sched_find_node_by_teid(tc_node, + first_teid); + else + parent = parent->children[0]; + if (!parent) { + dev_warn(dev, "Failure to add new parent for LAG move\n"); + return parent; + } + } + + return parent; +} + +/** + * ice_lag_move_vf_node_tc - move scheduling nodes for one VF on one TC + * @lag: lag info struct + * @oldport: lport of previous nodes location + * @newport: lport of destination nodes location + * @vsi_num: array index of VSI in PF space + * @tc: traffic class to move + */ +static void +ice_lag_move_vf_node_tc(struct ice_lag *lag, u8 oldport, u8 newport, + u16 vsi_num, u8 tc) +{ + DEFINE_FLEX(struct ice_aqc_move_elem, buf, teid, 1); + struct device *dev = ice_pf_to_dev(lag->pf); + u16 numq, valq, num_moved, qbuf_size; + u16 buf_size = __struct_size(buf); + struct ice_aqc_cfg_txqs_buf *qbuf; + struct ice_sched_node *n_prt; + struct ice_hw *new_hw = NULL; + __le32 teid, parent_teid; + struct ice_vsi_ctx *ctx; + u32 tmp_teid; + + ctx = ice_get_vsi_ctx(&lag->pf->hw, vsi_num); + if (!ctx) { + dev_warn(dev, "Unable to locate VSI context for LAG failover\n"); + return; + } + + /* check to see if this VF is enabled on this TC */ + if (!ctx->sched.vsi_node[tc]) + return; + + /* locate HW struct for destination port */ + new_hw = ice_lag_find_hw_by_lport(lag, newport); + if (!new_hw) { + dev_warn(dev, "Unable to locate HW struct for LAG node destination\n"); + return; + } + + numq = ctx->num_lan_q_entries[tc]; + teid = ctx->sched.vsi_node[tc]->info.node_teid; + tmp_teid = le32_to_cpu(teid); + parent_teid = ctx->sched.vsi_node[tc]->info.parent_teid; + /* if no teid assigned or numq == 0, then this TC is not active */ + if (!tmp_teid || !numq) + return; + + /* suspend VSI subtree for Traffic Class "tc" on + * this VF's VSI + */ + if (ice_sched_suspend_resume_elems(&lag->pf->hw, 1, &tmp_teid, true)) + dev_dbg(dev, "Problem suspending traffic for LAG node move\n"); + + /* reconfigure all VF's queues on this Traffic Class + * to new port + */ + qbuf_size = struct_size(qbuf, queue_info, numq); + qbuf = kzalloc(qbuf_size, GFP_KERNEL); + if (!qbuf) { + dev_warn(dev, "Failure allocating memory for VF queue recfg buffer\n"); + goto resume_traffic; + } + + /* add the per queue info for the reconfigure command buffer */ + valq = ice_lag_qbuf_recfg(&lag->pf->hw, qbuf, vsi_num, numq, tc); + if (!valq) { + dev_dbg(dev, "No valid queues found for LAG failover\n"); + goto qbuf_none; + } + + if (ice_aq_cfg_lan_txq(&lag->pf->hw, qbuf, qbuf_size, valq, oldport, + newport, NULL)) { + dev_warn(dev, "Failure to configure queues for LAG failover\n"); + goto qbuf_err; + } + +qbuf_none: + kfree(qbuf); + + /* find new parent in destination port's tree for VF VSI node on this + * Traffic Class + */ + n_prt = ice_lag_get_sched_parent(new_hw, tc); + if (!n_prt) + goto resume_traffic; + + /* Move Vf's VSI node for this TC to newport's scheduler tree */ + buf->hdr.src_parent_teid = parent_teid; + buf->hdr.dest_parent_teid = n_prt->info.node_teid; + buf->hdr.num_elems = cpu_to_le16(1); + buf->hdr.mode = ICE_AQC_MOVE_ELEM_MODE_KEEP_OWN; + buf->teid[0] = teid; + + if (ice_aq_move_sched_elems(&lag->pf->hw, buf, buf_size, &num_moved)) + dev_warn(dev, "Failure to move VF nodes for failover\n"); + else + ice_sched_update_parent(n_prt, ctx->sched.vsi_node[tc]); + + goto resume_traffic; + +qbuf_err: + kfree(qbuf); + +resume_traffic: + /* restart traffic for VSI node */ + if (ice_sched_suspend_resume_elems(&lag->pf->hw, 1, &tmp_teid, false)) + dev_dbg(dev, "Problem restarting traffic for LAG node move\n"); +} + +/** + * ice_lag_build_netdev_list - populate the lag struct's netdev list + * @lag: local lag struct + * @ndlist: pointer to netdev list to populate + */ +static void ice_lag_build_netdev_list(struct ice_lag *lag, + struct ice_lag_netdev_list *ndlist) +{ + struct ice_lag_netdev_list *nl; + struct net_device *tmp_nd; + + INIT_LIST_HEAD(&ndlist->node); + rcu_read_lock(); + for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) { + nl = kzalloc(sizeof(*nl), GFP_ATOMIC); + if (!nl) + break; + + nl->netdev = tmp_nd; + list_add(&nl->node, &ndlist->node); + } + rcu_read_unlock(); + lag->netdev_head = &ndlist->node; +} + +/** + * ice_lag_destroy_netdev_list - free lag struct's netdev list + * @lag: pointer to local lag struct + * @ndlist: pointer to lag struct netdev list + */ +static void ice_lag_destroy_netdev_list(struct ice_lag *lag, + struct ice_lag_netdev_list *ndlist) +{ + struct ice_lag_netdev_list *entry, *n; + + rcu_read_lock(); + list_for_each_entry_safe(entry, n, &ndlist->node, node) { + list_del(&entry->node); + kfree(entry); + } + rcu_read_unlock(); + lag->netdev_head = NULL; +} + +/** + * ice_lag_move_single_vf_nodes - Move Tx scheduling nodes for single VF + * @lag: primary interface LAG struct + * @oldport: lport of previous interface + * @newport: lport of destination interface + * @vsi_num: SW index of VF's VSI + */ +static void +ice_lag_move_single_vf_nodes(struct ice_lag *lag, u8 oldport, u8 newport, + u16 vsi_num) +{ + u8 tc; + + ice_for_each_traffic_class(tc) + ice_lag_move_vf_node_tc(lag, oldport, newport, vsi_num, tc); +} + +/** + * ice_lag_move_new_vf_nodes - Move Tx scheduling nodes for a VF if required + * @vf: the VF to move Tx nodes for + * + * Called just after configuring new VF queues. Check whether the VF Tx + * scheduling nodes need to be updated to fail over to the active port. If so, + * move them now. + */ +void ice_lag_move_new_vf_nodes(struct ice_vf *vf) +{ + struct ice_lag_netdev_list ndlist; + u8 pri_port, act_port; + struct ice_lag *lag; + struct ice_vsi *vsi; + struct ice_pf *pf; + + vsi = ice_get_vf_vsi(vf); + + if (WARN_ON(!vsi)) + return; + + if (WARN_ON(vsi->type != ICE_VSI_VF)) + return; + + pf = vf->pf; + lag = pf->lag; + + mutex_lock(&pf->lag_mutex); + if (!lag->bonded) + goto new_vf_unlock; + + pri_port = pf->hw.port_info->lport; + act_port = lag->active_port; + + if (lag->upper_netdev) + ice_lag_build_netdev_list(lag, &ndlist); + + if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG) && + lag->bonded && lag->primary && pri_port != act_port && + !list_empty(lag->netdev_head)) + ice_lag_move_single_vf_nodes(lag, pri_port, act_port, vsi->idx); + + ice_lag_destroy_netdev_list(lag, &ndlist); + +new_vf_unlock: + mutex_unlock(&pf->lag_mutex); +} + +/** + * ice_lag_move_vf_nodes - move Tx scheduling nodes for all VFs to new port + * @lag: lag info struct + * @oldport: lport of previous interface + * @newport: lport of destination interface + */ +static void ice_lag_move_vf_nodes(struct ice_lag *lag, u8 oldport, u8 newport) +{ + struct ice_pf *pf; + int i; + + if (!lag->primary) + return; + + pf = lag->pf; + ice_for_each_vsi(pf, i) + if (pf->vsi[i] && (pf->vsi[i]->type == ICE_VSI_VF || + pf->vsi[i]->type == ICE_VSI_SWITCHDEV_CTRL)) + ice_lag_move_single_vf_nodes(lag, oldport, newport, i); +} + +/** + * ice_lag_move_vf_nodes_cfg - move vf nodes outside LAG netdev event context + * @lag: local lag struct + * @src_prt: lport value for source port + * @dst_prt: lport value for destination port + * + * This function is used to move nodes during an out-of-netdev-event situation, + * primarily when the driver needs to reconfigure or recreate resources. + * + * Must be called while holding the lag_mutex to avoid lag events from + * processing while out-of-sync moves are happening. Also, paired moves, + * such as used in a reset flow, should both be called under the same mutex + * lock to avoid changes between start of reset and end of reset. + */ +void ice_lag_move_vf_nodes_cfg(struct ice_lag *lag, u8 src_prt, u8 dst_prt) +{ + struct ice_lag_netdev_list ndlist; + + ice_lag_build_netdev_list(lag, &ndlist); + ice_lag_move_vf_nodes(lag, src_prt, dst_prt); + ice_lag_destroy_netdev_list(lag, &ndlist); +} + +#define ICE_LAG_SRIOV_CP_RECIPE 10 +#define ICE_LAG_SRIOV_TRAIN_PKT_LEN 16 + +/** + * ice_lag_cfg_cp_fltr - configure filter for control packets + * @lag: local interface's lag struct + * @add: add or remove rule + */ +static void +ice_lag_cfg_cp_fltr(struct ice_lag *lag, bool add) +{ + struct ice_sw_rule_lkup_rx_tx *s_rule = NULL; + struct ice_vsi *vsi; + u16 buf_len, opc; + + vsi = lag->pf->vsi[0]; + + buf_len = ICE_SW_RULE_RX_TX_HDR_SIZE(s_rule, + ICE_LAG_SRIOV_TRAIN_PKT_LEN); + s_rule = kzalloc(buf_len, GFP_KERNEL); + if (!s_rule) { + netdev_warn(lag->netdev, "-ENOMEM error configuring CP filter\n"); + return; + } + + if (add) { + s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX); + s_rule->recipe_id = cpu_to_le16(ICE_LAG_SRIOV_CP_RECIPE); + s_rule->src = cpu_to_le16(vsi->port_info->lport); + s_rule->act = cpu_to_le32(ICE_FWD_TO_VSI | + ICE_SINGLE_ACT_LAN_ENABLE | + ICE_SINGLE_ACT_VALID_BIT | + ((vsi->vsi_num << + ICE_SINGLE_ACT_VSI_ID_S) & + ICE_SINGLE_ACT_VSI_ID_M)); + s_rule->hdr_len = cpu_to_le16(ICE_LAG_SRIOV_TRAIN_PKT_LEN); + memcpy(s_rule->hdr_data, lacp_train_pkt, LACP_TRAIN_PKT_LEN); + opc = ice_aqc_opc_add_sw_rules; + } else { + opc = ice_aqc_opc_remove_sw_rules; + s_rule->index = cpu_to_le16(lag->cp_rule_idx); + } + if (ice_aq_sw_rules(&lag->pf->hw, s_rule, buf_len, 1, opc, NULL)) { + netdev_warn(lag->netdev, "Error %s CP rule for fail-over\n", + add ? "ADDING" : "REMOVING"); + goto cp_free; + } + + if (add) + lag->cp_rule_idx = le16_to_cpu(s_rule->index); + else + lag->cp_rule_idx = 0; + +cp_free: + kfree(s_rule); } /** @@ -124,117 +821,422 @@ lag_out: } /** + * ice_lag_reclaim_vf_tc - move scheduling nodes back to primary interface + * @lag: primary interface lag struct + * @src_hw: HW struct current node location + * @vsi_num: VSI index in PF space + * @tc: traffic class to move + */ +static void +ice_lag_reclaim_vf_tc(struct ice_lag *lag, struct ice_hw *src_hw, u16 vsi_num, + u8 tc) +{ + DEFINE_FLEX(struct ice_aqc_move_elem, buf, teid, 1); + struct device *dev = ice_pf_to_dev(lag->pf); + u16 numq, valq, num_moved, qbuf_size; + u16 buf_size = __struct_size(buf); + struct ice_aqc_cfg_txqs_buf *qbuf; + struct ice_sched_node *n_prt; + __le32 teid, parent_teid; + struct ice_vsi_ctx *ctx; + struct ice_hw *hw; + u32 tmp_teid; + + hw = &lag->pf->hw; + ctx = ice_get_vsi_ctx(hw, vsi_num); + if (!ctx) { + dev_warn(dev, "Unable to locate VSI context for LAG reclaim\n"); + return; + } + + /* check to see if this VF is enabled on this TC */ + if (!ctx->sched.vsi_node[tc]) + return; + + numq = ctx->num_lan_q_entries[tc]; + teid = ctx->sched.vsi_node[tc]->info.node_teid; + tmp_teid = le32_to_cpu(teid); + parent_teid = ctx->sched.vsi_node[tc]->info.parent_teid; + + /* if !teid or !numq, then this TC is not active */ + if (!tmp_teid || !numq) + return; + + /* suspend traffic */ + if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, true)) + dev_dbg(dev, "Problem suspending traffic for LAG node move\n"); + + /* reconfig queues for new port */ + qbuf_size = struct_size(qbuf, queue_info, numq); + qbuf = kzalloc(qbuf_size, GFP_KERNEL); + if (!qbuf) { + dev_warn(dev, "Failure allocating memory for VF queue recfg buffer\n"); + goto resume_reclaim; + } + + /* add the per queue info for the reconfigure command buffer */ + valq = ice_lag_qbuf_recfg(hw, qbuf, vsi_num, numq, tc); + if (!valq) { + dev_dbg(dev, "No valid queues found for LAG reclaim\n"); + goto reclaim_none; + } + + if (ice_aq_cfg_lan_txq(hw, qbuf, qbuf_size, numq, + src_hw->port_info->lport, hw->port_info->lport, + NULL)) { + dev_warn(dev, "Failure to configure queues for LAG failover\n"); + goto reclaim_qerr; + } + +reclaim_none: + kfree(qbuf); + + /* find parent in primary tree */ + n_prt = ice_lag_get_sched_parent(hw, tc); + if (!n_prt) + goto resume_reclaim; + + /* Move node to new parent */ + buf->hdr.src_parent_teid = parent_teid; + buf->hdr.dest_parent_teid = n_prt->info.node_teid; + buf->hdr.num_elems = cpu_to_le16(1); + buf->hdr.mode = ICE_AQC_MOVE_ELEM_MODE_KEEP_OWN; + buf->teid[0] = teid; + + if (ice_aq_move_sched_elems(&lag->pf->hw, buf, buf_size, &num_moved)) + dev_warn(dev, "Failure to move VF nodes for LAG reclaim\n"); + else + ice_sched_update_parent(n_prt, ctx->sched.vsi_node[tc]); + + goto resume_reclaim; + +reclaim_qerr: + kfree(qbuf); + +resume_reclaim: + /* restart traffic */ + if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, false)) + dev_warn(dev, "Problem restarting traffic for LAG node reclaim\n"); +} + +/** + * ice_lag_reclaim_vf_nodes - When interface leaving bond primary reclaims nodes + * @lag: primary interface lag struct + * @src_hw: HW struct for current node location + */ +static void +ice_lag_reclaim_vf_nodes(struct ice_lag *lag, struct ice_hw *src_hw) +{ + struct ice_pf *pf; + int i, tc; + + if (!lag->primary || !src_hw) + return; + + pf = lag->pf; + ice_for_each_vsi(pf, i) + if (pf->vsi[i] && (pf->vsi[i]->type == ICE_VSI_VF || + pf->vsi[i]->type == ICE_VSI_SWITCHDEV_CTRL)) + ice_for_each_traffic_class(tc) + ice_lag_reclaim_vf_tc(lag, src_hw, i, tc); +} + +/** * ice_lag_link - handle LAG link event * @lag: LAG info struct - * @info: info from the netdev notifier */ -static void -ice_lag_link(struct ice_lag *lag, struct netdev_notifier_changeupper_info *info) +static void ice_lag_link(struct ice_lag *lag) { - struct net_device *netdev_tmp, *upper = info->upper_dev; struct ice_pf *pf = lag->pf; - int peers = 0; if (lag->bonded) dev_warn(ice_pf_to_dev(pf), "%s Already part of a bond\n", netdev_name(lag->netdev)); - rcu_read_lock(); - for_each_netdev_in_bond_rcu(upper, netdev_tmp) - peers++; - rcu_read_unlock(); - - if (lag->upper_netdev != upper) { - dev_hold(upper); - lag->upper_netdev = upper; - } - - ice_clear_rdma_cap(pf); - lag->bonded = true; lag->role = ICE_LAG_UNSET; - - /* if this is the first element in an LAG mark as primary */ - lag->primary = !!(peers == 1); + netdev_info(lag->netdev, "Shared SR-IOV resources in bond are active\n"); } /** * ice_lag_unlink - handle unlink event * @lag: LAG info struct - * @info: info from netdev notification */ -static void -ice_lag_unlink(struct ice_lag *lag, - struct netdev_notifier_changeupper_info *info) +static void ice_lag_unlink(struct ice_lag *lag) { - struct net_device *netdev_tmp, *upper = info->upper_dev; + u8 pri_port, act_port, loc_port; struct ice_pf *pf = lag->pf; - bool found = false; if (!lag->bonded) { netdev_dbg(lag->netdev, "bonding unlink event on non-LAG netdev\n"); return; } - /* determine if we are in the new LAG config or not */ - rcu_read_lock(); - for_each_netdev_in_bond_rcu(upper, netdev_tmp) { - if (netdev_tmp == lag->netdev) { - found = true; - break; + if (lag->primary) { + act_port = lag->active_port; + pri_port = lag->pf->hw.port_info->lport; + if (act_port != pri_port && act_port != ICE_LAG_INVALID_PORT) + ice_lag_move_vf_nodes(lag, act_port, pri_port); + lag->primary = false; + lag->active_port = ICE_LAG_INVALID_PORT; + } else { + struct ice_lag *primary_lag; + + primary_lag = ice_lag_find_primary(lag); + if (primary_lag) { + act_port = primary_lag->active_port; + pri_port = primary_lag->pf->hw.port_info->lport; + loc_port = pf->hw.port_info->lport; + if (act_port == loc_port && + act_port != ICE_LAG_INVALID_PORT) { + ice_lag_reclaim_vf_nodes(primary_lag, + &lag->pf->hw); + primary_lag->active_port = ICE_LAG_INVALID_PORT; + } } } - rcu_read_unlock(); - if (found) + lag->bonded = false; + lag->role = ICE_LAG_NONE; + lag->upper_netdev = NULL; +} + +/** + * ice_lag_link_unlink - helper function to call lag_link/unlink + * @lag: lag info struct + * @ptr: opaque pointer data + */ +static void ice_lag_link_unlink(struct ice_lag *lag, void *ptr) +{ + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_changeupper_info *info = ptr; + + if (netdev != lag->netdev) return; - if (lag->upper_netdev) { - dev_put(lag->upper_netdev); - lag->upper_netdev = NULL; + if (info->linking) + ice_lag_link(lag); + else + ice_lag_unlink(lag); +} + +/** + * ice_lag_set_swid - set the SWID on secondary interface + * @primary_swid: primary interface's SWID + * @local_lag: local interfaces LAG struct + * @link: Is this a linking activity + * + * If link is false, then primary_swid should be expected to not be valid + * This function should never be called in interrupt context. + */ +static void +ice_lag_set_swid(u16 primary_swid, struct ice_lag *local_lag, + bool link) +{ + struct ice_aqc_alloc_free_res_elem *buf; + struct ice_aqc_set_port_params *cmd; + struct ice_aq_desc desc; + u16 buf_len, swid; + int status, i; + + buf_len = struct_size(buf, elem, 1); + buf = kzalloc(buf_len, GFP_KERNEL); + if (!buf) { + dev_err(ice_pf_to_dev(local_lag->pf), "-ENOMEM error setting SWID\n"); + return; } - lag->peer_netdev = NULL; - ice_set_rdma_cap(pf); - lag->bonded = false; - lag->role = ICE_LAG_NONE; + buf->num_elems = cpu_to_le16(1); + buf->res_type = cpu_to_le16(ICE_AQC_RES_TYPE_SWID); + /* if unlinnking need to free the shared resource */ + if (!link && local_lag->bond_swid) { + buf->elem[0].e.sw_resp = cpu_to_le16(local_lag->bond_swid); + status = ice_aq_alloc_free_res(&local_lag->pf->hw, buf, + buf_len, ice_aqc_opc_free_res); + if (status) + dev_err(ice_pf_to_dev(local_lag->pf), "Error freeing SWID during LAG unlink\n"); + local_lag->bond_swid = 0; + } + + if (link) { + buf->res_type |= cpu_to_le16(ICE_LAG_RES_SHARED | + ICE_LAG_RES_VALID); + /* store the primary's SWID in case it leaves bond first */ + local_lag->bond_swid = primary_swid; + buf->elem[0].e.sw_resp = cpu_to_le16(local_lag->bond_swid); + } else { + buf->elem[0].e.sw_resp = + cpu_to_le16(local_lag->pf->hw.port_info->sw_id); + } + + status = ice_aq_alloc_free_res(&local_lag->pf->hw, buf, buf_len, + ice_aqc_opc_alloc_res); + if (status) + dev_err(ice_pf_to_dev(local_lag->pf), "Error subscribing to SWID 0x%04X\n", + local_lag->bond_swid); + + kfree(buf); + + /* Configure port param SWID to correct value */ + if (link) + swid = primary_swid; + else + swid = local_lag->pf->hw.port_info->sw_id; + + cmd = &desc.params.set_port_params; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_port_params); + + cmd->swid = cpu_to_le16(ICE_AQC_PORT_SWID_VALID | swid); + /* If this is happening in reset context, it is possible that the + * primary interface has not finished setting its SWID to SHARED + * yet. Allow retries to account for this timing issue between + * interfaces. + */ + for (i = 0; i < ICE_LAG_RESET_RETRIES; i++) { + status = ice_aq_send_cmd(&local_lag->pf->hw, &desc, NULL, 0, + NULL); + if (!status) + break; + + usleep_range(1000, 2000); + } + + if (status) + dev_err(ice_pf_to_dev(local_lag->pf), "Error setting SWID in port params %d\n", + status); } /** - * ice_lag_unregister - handle netdev unregister events - * @lag: LAG info struct - * @netdev: netdev reporting the event + * ice_lag_primary_swid - set/clear the SHARED attrib of primary's SWID + * @lag: primary interface's lag struct + * @link: is this a linking activity + * + * Implement setting primary SWID as shared using 0x020B */ -static void ice_lag_unregister(struct ice_lag *lag, struct net_device *netdev) +static void ice_lag_primary_swid(struct ice_lag *lag, bool link) { - struct ice_pf *pf = lag->pf; + struct ice_hw *hw; + u16 swid; - /* check to see if this event is for this netdev - * check that we are in an aggregate - */ - if (netdev != lag->netdev || !lag->bonded) + hw = &lag->pf->hw; + swid = hw->port_info->sw_id; + + if (ice_share_res(hw, ICE_AQC_RES_TYPE_SWID, link, swid)) + dev_warn(ice_pf_to_dev(lag->pf), "Failure to set primary interface shared status\n"); +} + +/** + * ice_lag_add_prune_list - Adds event_pf's VSI to primary's prune list + * @lag: lag info struct + * @event_pf: PF struct for VSI we are adding to primary's prune list + */ +static void ice_lag_add_prune_list(struct ice_lag *lag, struct ice_pf *event_pf) +{ + u16 num_vsi, rule_buf_sz, vsi_list_id, event_vsi_num, prim_vsi_idx; + struct ice_sw_rule_vsi_list *s_rule = NULL; + struct device *dev; + + num_vsi = 1; + + dev = ice_pf_to_dev(lag->pf); + event_vsi_num = event_pf->vsi[0]->vsi_num; + prim_vsi_idx = lag->pf->vsi[0]->idx; + + if (!ice_find_vsi_list_entry(&lag->pf->hw, ICE_SW_LKUP_VLAN, + prim_vsi_idx, &vsi_list_id)) { + dev_warn(dev, "Could not locate prune list when setting up SRIOV LAG\n"); return; + } - if (lag->upper_netdev) { - dev_put(lag->upper_netdev); - lag->upper_netdev = NULL; - ice_set_rdma_cap(pf); + rule_buf_sz = (u16)ICE_SW_RULE_VSI_LIST_SIZE(s_rule, num_vsi); + s_rule = kzalloc(rule_buf_sz, GFP_KERNEL); + if (!s_rule) { + dev_warn(dev, "Error allocating space for prune list when configuring SRIOV LAG\n"); + return; } - /* perform some cleanup in case we come back */ - lag->bonded = false; - lag->role = ICE_LAG_NONE; + + s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_PRUNE_LIST_SET); + s_rule->index = cpu_to_le16(vsi_list_id); + s_rule->number_vsi = cpu_to_le16(num_vsi); + s_rule->vsi[0] = cpu_to_le16(event_vsi_num); + + if (ice_aq_sw_rules(&event_pf->hw, s_rule, rule_buf_sz, 1, + ice_aqc_opc_update_sw_rules, NULL)) + dev_warn(dev, "Error adding VSI prune list\n"); + kfree(s_rule); +} + +/** + * ice_lag_del_prune_list - Remove secondary's vsi from primary's prune list + * @lag: primary interface's ice_lag struct + * @event_pf: PF struct for unlinking interface + */ +static void ice_lag_del_prune_list(struct ice_lag *lag, struct ice_pf *event_pf) +{ + u16 num_vsi, vsi_num, vsi_idx, rule_buf_sz, vsi_list_id; + struct ice_sw_rule_vsi_list *s_rule = NULL; + struct device *dev; + + num_vsi = 1; + + dev = ice_pf_to_dev(lag->pf); + vsi_num = event_pf->vsi[0]->vsi_num; + vsi_idx = lag->pf->vsi[0]->idx; + + if (!ice_find_vsi_list_entry(&lag->pf->hw, ICE_SW_LKUP_VLAN, + vsi_idx, &vsi_list_id)) { + dev_warn(dev, "Could not locate prune list when unwinding SRIOV LAG\n"); + return; + } + + rule_buf_sz = (u16)ICE_SW_RULE_VSI_LIST_SIZE(s_rule, num_vsi); + s_rule = kzalloc(rule_buf_sz, GFP_KERNEL); + if (!s_rule) { + dev_warn(dev, "Error allocating prune list when unwinding SRIOV LAG\n"); + return; + } + + s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_PRUNE_LIST_CLEAR); + s_rule->index = cpu_to_le16(vsi_list_id); + s_rule->number_vsi = cpu_to_le16(num_vsi); + s_rule->vsi[0] = cpu_to_le16(vsi_num); + + if (ice_aq_sw_rules(&event_pf->hw, (struct ice_aqc_sw_rules *)s_rule, + rule_buf_sz, 1, ice_aqc_opc_update_sw_rules, NULL)) + dev_warn(dev, "Error clearing VSI prune list\n"); + + kfree(s_rule); +} + +/** + * ice_lag_init_feature_support_flag - Check for NVM support for LAG + * @pf: PF struct + */ +static void ice_lag_init_feature_support_flag(struct ice_pf *pf) +{ + struct ice_hw_common_caps *caps; + + caps = &pf->hw.dev_caps.common_cap; + if (caps->roce_lag) + ice_set_feature_support(pf, ICE_F_ROCE_LAG); + else + ice_clear_feature_support(pf, ICE_F_ROCE_LAG); + + if (caps->sriov_lag) + ice_set_feature_support(pf, ICE_F_SRIOV_LAG); + else + ice_clear_feature_support(pf, ICE_F_SRIOV_LAG); } /** * ice_lag_changeupper_event - handle LAG changeupper event * @lag: LAG info struct * @ptr: opaque pointer data - * - * ptr is to be cast into netdev_notifier_changeupper_info */ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr) { struct netdev_notifier_changeupper_info *info; + struct ice_lag *primary_lag; struct net_device *netdev; info = ptr; @@ -244,44 +1246,437 @@ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr) if (netdev != lag->netdev) return; - if (!info->upper_dev) { - netdev_dbg(netdev, "changeupper rcvd, but no upper defined\n"); + primary_lag = ice_lag_find_primary(lag); + if (info->linking) { + lag->upper_netdev = info->upper_dev; + /* If there is not already a primary interface in the LAG, + * then mark this one as primary. + */ + if (!primary_lag) { + lag->primary = true; + /* Configure primary's SWID to be shared */ + ice_lag_primary_swid(lag, true); + primary_lag = lag; + } else { + u16 swid; + + swid = primary_lag->pf->hw.port_info->sw_id; + ice_lag_set_swid(swid, lag, true); + ice_lag_add_prune_list(primary_lag, lag->pf); + ice_lag_cfg_drop_fltr(lag, true); + } + /* add filter for primary control packets */ + ice_lag_cfg_cp_fltr(lag, true); + } else { + if (!primary_lag && lag->primary) + primary_lag = lag; + + if (!lag->primary) { + ice_lag_set_swid(0, lag, false); + } else { + if (primary_lag && lag->primary) { + ice_lag_primary_swid(lag, false); + ice_lag_del_prune_list(primary_lag, lag->pf); + } + } + /* remove filter for control packets */ + ice_lag_cfg_cp_fltr(lag, false); + } +} + +/** + * ice_lag_monitor_link - monitor interfaces entering/leaving the aggregate + * @lag: lag info struct + * @ptr: opaque data containing notifier event + * + * This function only operates after a primary has been set. + */ +static void ice_lag_monitor_link(struct ice_lag *lag, void *ptr) +{ + struct netdev_notifier_changeupper_info *info; + struct ice_hw *prim_hw, *active_hw; + struct net_device *event_netdev; + struct ice_pf *pf; + u8 prim_port; + + if (!lag->primary) return; + + event_netdev = netdev_notifier_info_to_dev(ptr); + if (!netif_is_same_ice(lag->pf, event_netdev)) + return; + + pf = lag->pf; + prim_hw = &pf->hw; + prim_port = prim_hw->port_info->lport; + + info = (struct netdev_notifier_changeupper_info *)ptr; + if (info->upper_dev != lag->upper_netdev) + return; + + if (!info->linking) { + /* Since there are only two interfaces allowed in SRIOV+LAG, if + * one port is leaving, then nodes need to be on primary + * interface. + */ + if (prim_port != lag->active_port && + lag->active_port != ICE_LAG_INVALID_PORT) { + active_hw = ice_lag_find_hw_by_lport(lag, + lag->active_port); + ice_lag_reclaim_vf_nodes(lag, active_hw); + lag->active_port = ICE_LAG_INVALID_PORT; + } } +} + +/** + * ice_lag_monitor_active - main PF keep track of which port is active + * @lag: lag info struct + * @ptr: opaque data containing notifier event + * + * This function is for the primary PF to monitor changes in which port is + * active and handle changes for SRIOV VF functionality + */ +static void ice_lag_monitor_active(struct ice_lag *lag, void *ptr) +{ + struct net_device *event_netdev, *event_upper; + struct netdev_notifier_bonding_info *info; + struct netdev_bonding_info *bonding_info; + struct ice_netdev_priv *event_np; + struct ice_pf *pf, *event_pf; + u8 prim_port, event_port; + + if (!lag->primary) + return; - netdev_dbg(netdev, "bonding %s\n", info->linking ? "LINK" : "UNLINK"); + pf = lag->pf; + if (!pf) + return; - if (!netif_is_lag_master(info->upper_dev)) { - netdev_dbg(netdev, "changeupper rcvd, but not primary. bail\n"); + event_netdev = netdev_notifier_info_to_dev(ptr); + rcu_read_lock(); + event_upper = netdev_master_upper_dev_get_rcu(event_netdev); + rcu_read_unlock(); + if (!netif_is_ice(event_netdev) || event_upper != lag->upper_netdev) return; + + event_np = netdev_priv(event_netdev); + event_pf = event_np->vsi->back; + event_port = event_pf->hw.port_info->lport; + prim_port = pf->hw.port_info->lport; + + info = (struct netdev_notifier_bonding_info *)ptr; + bonding_info = &info->bonding_info; + + if (!bonding_info->slave.state) { + /* if no port is currently active, then nodes and filters exist + * on primary port, check if we need to move them + */ + if (lag->active_port == ICE_LAG_INVALID_PORT) { + if (event_port != prim_port) + ice_lag_move_vf_nodes(lag, prim_port, + event_port); + lag->active_port = event_port; + return; + } + + /* active port is already set and is current event port */ + if (lag->active_port == event_port) + return; + /* new active port */ + ice_lag_move_vf_nodes(lag, lag->active_port, event_port); + lag->active_port = event_port; + } else { + /* port not set as currently active (e.g. new active port + * has already claimed the nodes and filters + */ + if (lag->active_port != event_port) + return; + /* This is the case when neither port is active (both link down) + * Link down on the bond - set active port to invalid and move + * nodes and filters back to primary if not already there + */ + if (event_port != prim_port) + ice_lag_move_vf_nodes(lag, event_port, prim_port); + lag->active_port = ICE_LAG_INVALID_PORT; } +} - if (info->linking) - ice_lag_link(lag, info); - else - ice_lag_unlink(lag, info); +/** + * ice_lag_chk_comp - evaluate bonded interface for feature support + * @lag: lag info struct + * @ptr: opaque data for netdev event info + */ +static bool +ice_lag_chk_comp(struct ice_lag *lag, void *ptr) +{ + struct net_device *event_netdev, *event_upper; + struct netdev_notifier_bonding_info *info; + struct netdev_bonding_info *bonding_info; + struct list_head *tmp; + struct device *dev; + int count = 0; - ice_display_lag_info(lag); + if (!lag->primary) + return true; + + event_netdev = netdev_notifier_info_to_dev(ptr); + rcu_read_lock(); + event_upper = netdev_master_upper_dev_get_rcu(event_netdev); + rcu_read_unlock(); + if (event_upper != lag->upper_netdev) + return true; + + dev = ice_pf_to_dev(lag->pf); + + /* only supporting switchdev mode for SRIOV VF LAG. + * primary interface has to be in switchdev mode + */ + if (!ice_is_switchdev_running(lag->pf)) { + dev_info(dev, "Primary interface not in switchdev mode - VF LAG disabled\n"); + return false; + } + + info = (struct netdev_notifier_bonding_info *)ptr; + bonding_info = &info->bonding_info; + lag->bond_mode = bonding_info->master.bond_mode; + if (lag->bond_mode != BOND_MODE_ACTIVEBACKUP) { + dev_info(dev, "Bond Mode not ACTIVE-BACKUP - VF LAG disabled\n"); + return false; + } + + list_for_each(tmp, lag->netdev_head) { + struct ice_dcbx_cfg *dcb_cfg, *peer_dcb_cfg; + struct ice_lag_netdev_list *entry; + struct ice_netdev_priv *peer_np; + struct net_device *peer_netdev; + struct ice_vsi *vsi, *peer_vsi; + struct ice_pf *peer_pf; + + entry = list_entry(tmp, struct ice_lag_netdev_list, node); + peer_netdev = entry->netdev; + if (!netif_is_ice(peer_netdev)) { + dev_info(dev, "Found %s non-ice netdev in LAG - VF LAG disabled\n", + netdev_name(peer_netdev)); + return false; + } + + count++; + if (count > 2) { + dev_info(dev, "Found more than two netdevs in LAG - VF LAG disabled\n"); + return false; + } + + peer_np = netdev_priv(peer_netdev); + vsi = ice_get_main_vsi(lag->pf); + peer_vsi = peer_np->vsi; + if (lag->pf->pdev->bus != peer_vsi->back->pdev->bus || + lag->pf->pdev->slot != peer_vsi->back->pdev->slot) { + dev_info(dev, "Found %s on different device in LAG - VF LAG disabled\n", + netdev_name(peer_netdev)); + return false; + } + + dcb_cfg = &vsi->port_info->qos_cfg.local_dcbx_cfg; + peer_dcb_cfg = &peer_vsi->port_info->qos_cfg.local_dcbx_cfg; + if (memcmp(dcb_cfg, peer_dcb_cfg, + sizeof(struct ice_dcbx_cfg))) { + dev_info(dev, "Found %s with different DCB in LAG - VF LAG disabled\n", + netdev_name(peer_netdev)); + return false; + } + + peer_pf = peer_vsi->back; + if (test_bit(ICE_FLAG_FW_LLDP_AGENT, peer_pf->flags)) { + dev_warn(dev, "Found %s with FW LLDP agent active - VF LAG disabled\n", + netdev_name(peer_netdev)); + return false; + } + } + + return true; } /** - * ice_lag_changelower_event - handle LAG changelower event + * ice_lag_unregister - handle netdev unregister events * @lag: LAG info struct - * @ptr: opaque data pointer + * @event_netdev: netdev struct for target of notifier event + */ +static void +ice_lag_unregister(struct ice_lag *lag, struct net_device *event_netdev) +{ + struct ice_netdev_priv *np; + struct ice_pf *event_pf; + struct ice_lag *p_lag; + + p_lag = ice_lag_find_primary(lag); + np = netdev_priv(event_netdev); + event_pf = np->vsi->back; + + if (p_lag) { + if (p_lag->active_port != p_lag->pf->hw.port_info->lport && + p_lag->active_port != ICE_LAG_INVALID_PORT) { + struct ice_hw *active_hw; + + active_hw = ice_lag_find_hw_by_lport(lag, + p_lag->active_port); + if (active_hw) + ice_lag_reclaim_vf_nodes(p_lag, active_hw); + lag->active_port = ICE_LAG_INVALID_PORT; + } + } + + /* primary processing for primary */ + if (lag->primary && lag->netdev == event_netdev) + ice_lag_primary_swid(lag, false); + + /* primary processing for secondary */ + if (lag->primary && lag->netdev != event_netdev) + ice_lag_del_prune_list(lag, event_pf); + + /* secondary processing for secondary */ + if (!lag->primary && lag->netdev == event_netdev) + ice_lag_set_swid(0, lag, false); +} + +/** + * ice_lag_monitor_rdma - set and clear rdma functionality + * @lag: pointer to lag struct + * @ptr: opaque data for netdev event info + */ +static void +ice_lag_monitor_rdma(struct ice_lag *lag, void *ptr) +{ + struct netdev_notifier_changeupper_info *info; + struct net_device *netdev; + + info = ptr; + netdev = netdev_notifier_info_to_dev(ptr); + + if (netdev != lag->netdev) + return; + + if (info->linking) + ice_clear_rdma_cap(lag->pf); + else + ice_set_rdma_cap(lag->pf); +} + +/** + * ice_lag_chk_disabled_bond - monitor interfaces entering/leaving disabled bond + * @lag: lag info struct + * @ptr: opaque data containing event * - * ptr to be cast to netdev_notifier_changelowerstate_info + * as interfaces enter a bond - determine if the bond is currently + * SRIOV LAG compliant and flag if not. As interfaces leave the + * bond, reset their compliant status. */ -static void ice_lag_changelower_event(struct ice_lag *lag, void *ptr) +static void ice_lag_chk_disabled_bond(struct ice_lag *lag, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_changeupper_info *info = ptr; + struct ice_lag *prim_lag; if (netdev != lag->netdev) return; - netdev_dbg(netdev, "bonding info\n"); + if (info->linking) { + prim_lag = ice_lag_find_primary(lag); + if (prim_lag && + !ice_is_feature_supported(prim_lag->pf, ICE_F_SRIOV_LAG)) { + ice_clear_feature_support(lag->pf, ICE_F_SRIOV_LAG); + netdev_info(netdev, "Interface added to non-compliant SRIOV LAG aggregate\n"); + } + } else { + ice_lag_init_feature_support_flag(lag->pf); + } +} + +/** + * ice_lag_disable_sriov_bond - set members of bond as not supporting SRIOV LAG + * @lag: primary interfaces lag struct + */ +static void ice_lag_disable_sriov_bond(struct ice_lag *lag) +{ + struct ice_netdev_priv *np; + struct ice_pf *pf; + + np = netdev_priv(lag->netdev); + pf = np->vsi->back; + ice_clear_feature_support(pf, ICE_F_SRIOV_LAG); +} + +/** + * ice_lag_process_event - process a task assigned to the lag_wq + * @work: pointer to work_struct + */ +static void ice_lag_process_event(struct work_struct *work) +{ + struct netdev_notifier_changeupper_info *info; + struct ice_lag_work *lag_work; + struct net_device *netdev; + struct list_head *tmp, *n; + struct ice_pf *pf; + + lag_work = container_of(work, struct ice_lag_work, lag_task); + pf = lag_work->lag->pf; + + mutex_lock(&pf->lag_mutex); + lag_work->lag->netdev_head = &lag_work->netdev_list.node; + + switch (lag_work->event) { + case NETDEV_CHANGEUPPER: + info = &lag_work->info.changeupper_info; + ice_lag_chk_disabled_bond(lag_work->lag, info); + if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) { + ice_lag_monitor_link(lag_work->lag, info); + ice_lag_changeupper_event(lag_work->lag, info); + ice_lag_link_unlink(lag_work->lag, info); + } + ice_lag_monitor_rdma(lag_work->lag, info); + break; + case NETDEV_BONDING_INFO: + if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) { + if (!ice_lag_chk_comp(lag_work->lag, + &lag_work->info.bonding_info)) { + netdev = lag_work->info.bonding_info.info.dev; + ice_lag_disable_sriov_bond(lag_work->lag); + ice_lag_unregister(lag_work->lag, netdev); + goto lag_cleanup; + } + ice_lag_monitor_active(lag_work->lag, + &lag_work->info.bonding_info); + ice_lag_cfg_pf_fltrs(lag_work->lag, + &lag_work->info.bonding_info); + } + ice_lag_info_event(lag_work->lag, &lag_work->info.bonding_info); + break; + case NETDEV_UNREGISTER: + if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) { + netdev = lag_work->info.bonding_info.info.dev; + if ((netdev == lag_work->lag->netdev || + lag_work->lag->primary) && lag_work->lag->bonded) + ice_lag_unregister(lag_work->lag, netdev); + } + break; + default: + break; + } + +lag_cleanup: + /* cleanup resources allocated for this work item */ + list_for_each_safe(tmp, n, &lag_work->netdev_list.node) { + struct ice_lag_netdev_list *entry; + + entry = list_entry(tmp, struct ice_lag_netdev_list, node); + list_del(&entry->node); + kfree(entry); + } + lag_work->lag->netdev_head = NULL; + + mutex_unlock(&pf->lag_mutex); - if (!netif_is_lag_port(netdev)) - netdev_dbg(netdev, "CHANGELOWER rcvd, but netdev not in LAG. Bail\n"); + kfree(lag_work); } /** @@ -295,34 +1690,79 @@ ice_lag_event_handler(struct notifier_block *notif_blk, unsigned long event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct net_device *upper_netdev; + struct ice_lag_work *lag_work; struct ice_lag *lag; - lag = container_of(notif_blk, struct ice_lag, notif_block); + if (!netif_is_ice(netdev)) + return NOTIFY_DONE; + + if (event != NETDEV_CHANGEUPPER && event != NETDEV_BONDING_INFO && + event != NETDEV_UNREGISTER) + return NOTIFY_DONE; + + if (!(netdev->priv_flags & IFF_BONDING)) + return NOTIFY_DONE; + lag = container_of(notif_blk, struct ice_lag, notif_block); if (!lag->netdev) return NOTIFY_DONE; - /* Check that the netdev is in the working namespace */ if (!net_eq(dev_net(netdev), &init_net)) return NOTIFY_DONE; + /* This memory will be freed at the end of ice_lag_process_event */ + lag_work = kzalloc(sizeof(*lag_work), GFP_KERNEL); + if (!lag_work) + return -ENOMEM; + + lag_work->event_netdev = netdev; + lag_work->lag = lag; + lag_work->event = event; + if (event == NETDEV_CHANGEUPPER) { + struct netdev_notifier_changeupper_info *info; + + info = ptr; + upper_netdev = info->upper_dev; + } else { + upper_netdev = netdev_master_upper_dev_get(netdev); + } + + INIT_LIST_HEAD(&lag_work->netdev_list.node); + if (upper_netdev) { + struct ice_lag_netdev_list *nd_list; + struct net_device *tmp_nd; + + rcu_read_lock(); + for_each_netdev_in_bond_rcu(upper_netdev, tmp_nd) { + nd_list = kzalloc(sizeof(*nd_list), GFP_ATOMIC); + if (!nd_list) + break; + + nd_list->netdev = tmp_nd; + list_add(&nd_list->node, &lag_work->netdev_list.node); + } + rcu_read_unlock(); + } + switch (event) { case NETDEV_CHANGEUPPER: - ice_lag_changeupper_event(lag, ptr); - break; - case NETDEV_CHANGELOWERSTATE: - ice_lag_changelower_event(lag, ptr); + lag_work->info.changeupper_info = + *((struct netdev_notifier_changeupper_info *)ptr); break; case NETDEV_BONDING_INFO: - ice_lag_info_event(lag, ptr); - break; - case NETDEV_UNREGISTER: - ice_lag_unregister(lag, netdev); + lag_work->info.bonding_info = + *((struct netdev_notifier_bonding_info *)ptr); break; default: + lag_work->info.notifier_info = + *((struct netdev_notifier_info *)ptr); break; } + INIT_WORK(&lag_work->lag_task, ice_lag_process_event); + queue_work(ice_lag_wq, &lag_work->lag_task); + return NOTIFY_DONE; } @@ -366,6 +1806,166 @@ static void ice_unregister_lag_handler(struct ice_lag *lag) } /** + * ice_create_lag_recipe + * @hw: pointer to HW struct + * @rid: pointer to u16 to pass back recipe index + * @base_recipe: recipe to base the new recipe on + * @prio: priority for new recipe + * + * function returns 0 on error + */ +static int ice_create_lag_recipe(struct ice_hw *hw, u16 *rid, + const u8 *base_recipe, u8 prio) +{ + struct ice_aqc_recipe_data_elem *new_rcp; + int err; + + err = ice_alloc_recipe(hw, rid); + if (err) + return err; + + new_rcp = kzalloc(ICE_RECIPE_LEN * ICE_MAX_NUM_RECIPES, GFP_KERNEL); + if (!new_rcp) + return -ENOMEM; + + memcpy(new_rcp, base_recipe, ICE_RECIPE_LEN); + new_rcp->content.act_ctrl_fwd_priority = prio; + new_rcp->content.rid = *rid | ICE_AQ_RECIPE_ID_IS_ROOT; + new_rcp->recipe_indx = *rid; + bitmap_zero((unsigned long *)new_rcp->recipe_bitmap, + ICE_MAX_NUM_RECIPES); + set_bit(*rid, (unsigned long *)new_rcp->recipe_bitmap); + + err = ice_aq_add_recipe(hw, new_rcp, 1, NULL); + if (err) + *rid = 0; + + kfree(new_rcp); + return err; +} + +/** + * ice_lag_move_vf_nodes_tc_sync - move a VF's nodes for a tc during reset + * @lag: primary interfaces lag struct + * @dest_hw: HW struct for destination's interface + * @vsi_num: VSI index in PF space + * @tc: traffic class to move + */ +static void +ice_lag_move_vf_nodes_tc_sync(struct ice_lag *lag, struct ice_hw *dest_hw, + u16 vsi_num, u8 tc) +{ + DEFINE_FLEX(struct ice_aqc_move_elem, buf, teid, 1); + struct device *dev = ice_pf_to_dev(lag->pf); + u16 numq, valq, num_moved, qbuf_size; + u16 buf_size = __struct_size(buf); + struct ice_aqc_cfg_txqs_buf *qbuf; + struct ice_sched_node *n_prt; + __le32 teid, parent_teid; + struct ice_vsi_ctx *ctx; + struct ice_hw *hw; + u32 tmp_teid; + + hw = &lag->pf->hw; + ctx = ice_get_vsi_ctx(hw, vsi_num); + if (!ctx) { + dev_warn(dev, "LAG rebuild failed after reset due to VSI Context failure\n"); + return; + } + + if (!ctx->sched.vsi_node[tc]) + return; + + numq = ctx->num_lan_q_entries[tc]; + teid = ctx->sched.vsi_node[tc]->info.node_teid; + tmp_teid = le32_to_cpu(teid); + parent_teid = ctx->sched.vsi_node[tc]->info.parent_teid; + + if (!tmp_teid || !numq) + return; + + if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, true)) + dev_dbg(dev, "Problem suspending traffic during reset rebuild\n"); + + /* reconfig queues for new port */ + qbuf_size = struct_size(qbuf, queue_info, numq); + qbuf = kzalloc(qbuf_size, GFP_KERNEL); + if (!qbuf) { + dev_warn(dev, "Failure allocating VF queue recfg buffer for reset rebuild\n"); + goto resume_sync; + } + + /* add the per queue info for the reconfigure command buffer */ + valq = ice_lag_qbuf_recfg(hw, qbuf, vsi_num, numq, tc); + if (!valq) { + dev_warn(dev, "Failure to reconfig queues for LAG reset rebuild\n"); + goto sync_none; + } + + if (ice_aq_cfg_lan_txq(hw, qbuf, qbuf_size, numq, hw->port_info->lport, + dest_hw->port_info->lport, NULL)) { + dev_warn(dev, "Failure to configure queues for LAG reset rebuild\n"); + goto sync_qerr; + } + +sync_none: + kfree(qbuf); + + /* find parent in destination tree */ + n_prt = ice_lag_get_sched_parent(dest_hw, tc); + if (!n_prt) + goto resume_sync; + + /* Move node to new parent */ + buf->hdr.src_parent_teid = parent_teid; + buf->hdr.dest_parent_teid = n_prt->info.node_teid; + buf->hdr.num_elems = cpu_to_le16(1); + buf->hdr.mode = ICE_AQC_MOVE_ELEM_MODE_KEEP_OWN; + buf->teid[0] = teid; + + if (ice_aq_move_sched_elems(&lag->pf->hw, buf, buf_size, &num_moved)) + dev_warn(dev, "Failure to move VF nodes for LAG reset rebuild\n"); + else + ice_sched_update_parent(n_prt, ctx->sched.vsi_node[tc]); + + goto resume_sync; + +sync_qerr: + kfree(qbuf); + +resume_sync: + if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, false)) + dev_warn(dev, "Problem restarting traffic for LAG node reset rebuild\n"); +} + +/** + * ice_lag_move_vf_nodes_sync - move vf nodes to active interface + * @lag: primary interfaces lag struct + * @dest_hw: lport value for currently active port + * + * This function is used in a reset context, outside of event handling, + * to move the VF nodes to the secondary interface when that interface + * is the active interface during a reset rebuild + */ +static void +ice_lag_move_vf_nodes_sync(struct ice_lag *lag, struct ice_hw *dest_hw) +{ + struct ice_pf *pf; + int i, tc; + + if (!lag->primary || !dest_hw) + return; + + pf = lag->pf; + ice_for_each_vsi(pf, i) + if (pf->vsi[i] && (pf->vsi[i]->type == ICE_VSI_VF || + pf->vsi[i]->type == ICE_VSI_SWITCHDEV_CTRL)) + ice_for_each_traffic_class(tc) + ice_lag_move_vf_nodes_tc_sync(lag, dest_hw, i, + tc); +} + +/** * ice_init_lag - initialize support for LAG * @pf: PF struct * @@ -377,7 +1977,12 @@ int ice_init_lag(struct ice_pf *pf) struct device *dev = ice_pf_to_dev(pf); struct ice_lag *lag; struct ice_vsi *vsi; - int err; + u64 recipe_bits = 0; + int n, err; + + ice_lag_init_feature_support_flag(pf); + if (!ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) + return 0; pf->lag = kzalloc(sizeof(*lag), GFP_KERNEL); if (!pf->lag) @@ -394,8 +1999,8 @@ int ice_init_lag(struct ice_pf *pf) lag->pf = pf; lag->netdev = vsi->netdev; lag->role = ICE_LAG_NONE; + lag->active_port = ICE_LAG_INVALID_PORT; lag->bonded = false; - lag->peer_netdev = NULL; lag->upper_netdev = NULL; lag->notif_block.notifier_call = NULL; @@ -405,11 +2010,39 @@ int ice_init_lag(struct ice_pf *pf) goto lag_error; } + err = ice_create_lag_recipe(&pf->hw, &lag->pf_recipe, + ice_dflt_vsi_rcp, 1); + if (err) + goto lag_error; + + err = ice_create_lag_recipe(&pf->hw, &lag->lport_recipe, + ice_lport_rcp, 3); + if (err) + goto free_rcp_res; + + /* associate recipes to profiles */ + for (n = 0; n < ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER; n++) { + err = ice_aq_get_recipe_to_profile(&pf->hw, n, + (u8 *)&recipe_bits, NULL); + if (err) + continue; + + if (recipe_bits & BIT(ICE_SW_LKUP_DFLT)) { + recipe_bits |= BIT(lag->pf_recipe) | + BIT(lag->lport_recipe); + ice_aq_map_recipe_to_profile(&pf->hw, n, + (u8 *)&recipe_bits, NULL); + } + } + ice_display_lag_info(lag); dev_dbg(dev, "INIT LAG complete\n"); return 0; +free_rcp_res: + ice_free_hw_res(&pf->hw, ICE_AQC_RES_TYPE_RECIPE, 1, + &pf->lag->pf_recipe); lag_error: kfree(lag); pf->lag = NULL; @@ -435,11 +2068,107 @@ void ice_deinit_lag(struct ice_pf *pf) if (lag->pf) ice_unregister_lag_handler(lag); - dev_put(lag->upper_netdev); + flush_workqueue(ice_lag_wq); - dev_put(lag->peer_netdev); + ice_free_hw_res(&pf->hw, ICE_AQC_RES_TYPE_RECIPE, 1, + &pf->lag->pf_recipe); + ice_free_hw_res(&pf->hw, ICE_AQC_RES_TYPE_RECIPE, 1, + &pf->lag->lport_recipe); kfree(lag); pf->lag = NULL; } + +/** + * ice_lag_rebuild - rebuild lag resources after reset + * @pf: pointer to local pf struct + * + * PF resets are promoted to CORER resets when interface in an aggregate. This + * means that we need to rebuild the PF resources for the interface. Since + * this will happen outside the normal event processing, need to acquire the lag + * lock. + * + * This function will also evaluate the VF resources if this is the primary + * interface. + */ +void ice_lag_rebuild(struct ice_pf *pf) +{ + struct ice_lag_netdev_list ndlist; + struct ice_lag *lag, *prim_lag; + u8 act_port, loc_port; + + if (!pf->lag || !pf->lag->bonded) + return; + + mutex_lock(&pf->lag_mutex); + + lag = pf->lag; + if (lag->primary) { + prim_lag = lag; + } else { + ice_lag_build_netdev_list(lag, &ndlist); + prim_lag = ice_lag_find_primary(lag); + } + + if (!prim_lag) { + dev_dbg(ice_pf_to_dev(pf), "No primary interface in aggregate, can't rebuild\n"); + goto lag_rebuild_out; + } + + act_port = prim_lag->active_port; + loc_port = lag->pf->hw.port_info->lport; + + /* configure SWID for this port */ + if (lag->primary) { + ice_lag_primary_swid(lag, true); + } else { + ice_lag_set_swid(prim_lag->pf->hw.port_info->sw_id, lag, true); + ice_lag_add_prune_list(prim_lag, pf); + if (act_port == loc_port) + ice_lag_move_vf_nodes_sync(prim_lag, &pf->hw); + } + + ice_lag_cfg_cp_fltr(lag, true); + + if (lag->pf_rule_id) + if (ice_lag_cfg_dflt_fltr(lag, true)) + dev_err(ice_pf_to_dev(pf), "Error adding default VSI rule in rebuild\n"); + + ice_clear_rdma_cap(pf); +lag_rebuild_out: + ice_lag_destroy_netdev_list(lag, &ndlist); + mutex_unlock(&pf->lag_mutex); +} + +/** + * ice_lag_is_switchdev_running + * @pf: pointer to PF structure + * + * Check if switchdev is running on any of the interfaces connected to lag. + */ +bool ice_lag_is_switchdev_running(struct ice_pf *pf) +{ + struct ice_lag *lag = pf->lag; + struct net_device *tmp_nd; + + if (!ice_is_feature_supported(pf, ICE_F_SRIOV_LAG) || !lag) + return false; + + rcu_read_lock(); + for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) { + struct ice_netdev_priv *priv = netdev_priv(tmp_nd); + + if (!netif_is_ice(tmp_nd) || !priv || !priv->vsi || + !priv->vsi->back) + continue; + + if (ice_is_switchdev_running(priv->vsi->back)) { + rcu_read_unlock(); + return true; + } + } + rcu_read_unlock(); + + return false; +} diff --git a/drivers/net/ethernet/intel/ice/ice_lag.h b/drivers/net/ethernet/intel/ice/ice_lag.h index 2c373676c42f..ede833dfa658 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.h +++ b/drivers/net/ethernet/intel/ice/ice_lag.h @@ -14,20 +14,56 @@ enum ice_lag_role { ICE_LAG_UNSET }; +#define ICE_LAG_INVALID_PORT 0xFF + +#define ICE_LAG_RESET_RETRIES 5 + struct ice_pf; +struct ice_vf; + +struct ice_lag_netdev_list { + struct list_head node; + struct net_device *netdev; +}; /* LAG info struct */ struct ice_lag { struct ice_pf *pf; /* backlink to PF struct */ struct net_device *netdev; /* this PF's netdev */ - struct net_device *peer_netdev; struct net_device *upper_netdev; /* upper bonding netdev */ + struct list_head *netdev_head; struct notifier_block notif_block; + s32 bond_mode; + u16 bond_swid; /* swid for primary interface */ + u8 active_port; /* lport value for the current active port */ u8 bonded:1; /* currently bonded */ u8 primary:1; /* this is primary */ + u16 pf_recipe; + u16 lport_recipe; + u16 pf_rule_id; + u16 cp_rule_idx; + u16 lport_rule_idx; u8 role; }; +/* LAG workqueue struct */ +struct ice_lag_work { + struct work_struct lag_task; + struct ice_lag_netdev_list netdev_list; + struct ice_lag *lag; + unsigned long event; + struct net_device *event_netdev; + union { + struct netdev_notifier_changeupper_info changeupper_info; + struct netdev_notifier_bonding_info bonding_info; + struct netdev_notifier_info notifier_info; + } info; +}; + +void ice_lag_move_new_vf_nodes(struct ice_vf *vf); int ice_init_lag(struct ice_pf *pf); void ice_deinit_lag(struct ice_pf *pf); +void ice_lag_rebuild(struct ice_pf *pf); +bool ice_lag_is_switchdev_running(struct ice_pf *pf); +void ice_lag_move_vf_nodes_cfg(struct ice_lag *lag, u8 src_prt, u8 dst_prt); #endif /* _ICE_LAG_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 0054d7e64ec3..1bad6e17f9be 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -229,7 +229,7 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi) * of queues vectors, subtract 1 (ICE_NONQ_VECS_VF) from the * original vector count */ - vsi->num_q_vectors = pf->vfs.num_msix_per - ICE_NONQ_VECS_VF; + vsi->num_q_vectors = vf->num_msix - ICE_NONQ_VECS_VF; break; case ICE_VSI_CTRL: vsi->alloc_txq = 1; @@ -907,6 +907,7 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi) { struct ice_hw_common_caps *cap; struct ice_pf *pf = vsi->back; + u16 max_rss_size; if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) { vsi->rss_size = 1; @@ -914,32 +915,31 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi) } cap = &pf->hw.func_caps.common_cap; + max_rss_size = BIT(cap->rss_table_entry_width); switch (vsi->type) { case ICE_VSI_CHNL: case ICE_VSI_PF: /* PF VSI will inherit RSS instance of PF */ vsi->rss_table_size = (u16)cap->rss_table_size; if (vsi->type == ICE_VSI_CHNL) - vsi->rss_size = min_t(u16, vsi->num_rxq, - BIT(cap->rss_table_entry_width)); + vsi->rss_size = min_t(u16, vsi->num_rxq, max_rss_size); else vsi->rss_size = min_t(u16, num_online_cpus(), - BIT(cap->rss_table_entry_width)); - vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF; + max_rss_size); + vsi->rss_lut_type = ICE_LUT_PF; break; case ICE_VSI_SWITCHDEV_CTRL: - vsi->rss_table_size = ICE_VSIQF_HLUT_ARRAY_SIZE; - vsi->rss_size = min_t(u16, num_online_cpus(), - BIT(cap->rss_table_entry_width)); - vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI; + vsi->rss_table_size = ICE_LUT_VSI_SIZE; + vsi->rss_size = min_t(u16, num_online_cpus(), max_rss_size); + vsi->rss_lut_type = ICE_LUT_VSI; break; case ICE_VSI_VF: /* VF VSI will get a small RSS table. * For VSI_LUT, LUT size should be set to 64 bytes. */ - vsi->rss_table_size = ICE_VSIQF_HLUT_ARRAY_SIZE; + vsi->rss_table_size = ICE_LUT_VSI_SIZE; vsi->rss_size = ICE_MAX_RSS_QS_PER_VF; - vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI; + vsi->rss_lut_type = ICE_LUT_VSI; break; case ICE_VSI_LB: break; @@ -1201,8 +1201,7 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) ctxt->info.q_opt_rss = ((lut_type << ICE_AQ_VSI_Q_OPT_RSS_LUT_S) & ICE_AQ_VSI_Q_OPT_RSS_LUT_M) | - ((hash_type << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) & - ICE_AQ_VSI_Q_OPT_RSS_HASH_M); + (hash_type & ICE_AQ_VSI_Q_OPT_RSS_HASH_M); } static void @@ -1228,6 +1227,17 @@ ice_chnl_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) } /** + * ice_vsi_is_vlan_pruning_ena - check if VLAN pruning is enabled or not + * @vsi: VSI to check whether or not VLAN pruning is enabled. + * + * returns true if Rx VLAN pruning is enabled and false otherwise. + */ +static bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi) +{ + return vsi->info.sw_flags2 & ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; +} + +/** * ice_vsi_init - Create and initialize a VSI * @vsi: the VSI being configured * @vsi_flags: VSI configuration flags @@ -1685,6 +1695,27 @@ static void ice_vsi_set_rss_flow_fld(struct ice_vsi *vsi) } /** + * ice_vsi_cfg_frame_size - setup max frame size and Rx buffer length + * @vsi: VSI + */ +static void ice_vsi_cfg_frame_size(struct ice_vsi *vsi) +{ + if (!vsi->netdev || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) { + vsi->max_frame = ICE_MAX_FRAME_LEGACY_RX; + vsi->rx_buf_len = ICE_RXBUF_1664; +#if (PAGE_SIZE < 8192) + } else if (!ICE_2K_TOO_SMALL_WITH_PADDING && + (vsi->netdev->mtu <= ETH_DATA_LEN)) { + vsi->max_frame = ICE_RXBUF_1536 - NET_IP_ALIGN; + vsi->rx_buf_len = ICE_RXBUF_1536 - NET_IP_ALIGN; +#endif + } else { + vsi->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX; + vsi->rx_buf_len = ICE_RXBUF_3072; + } +} + +/** * ice_pf_state_is_nominal - checks the PF for nominal state * @pf: pointer to PF to check * @@ -1759,27 +1790,6 @@ void ice_update_eth_stats(struct ice_vsi *vsi) } /** - * ice_vsi_cfg_frame_size - setup max frame size and Rx buffer length - * @vsi: VSI - */ -void ice_vsi_cfg_frame_size(struct ice_vsi *vsi) -{ - if (!vsi->netdev || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) { - vsi->max_frame = ICE_MAX_FRAME_LEGACY_RX; - vsi->rx_buf_len = ICE_RXBUF_1664; -#if (PAGE_SIZE < 8192) - } else if (!ICE_2K_TOO_SMALL_WITH_PADDING && - (vsi->netdev->mtu <= ETH_DATA_LEN)) { - vsi->max_frame = ICE_RXBUF_1536 - NET_IP_ALIGN; - vsi->rx_buf_len = ICE_RXBUF_1536 - NET_IP_ALIGN; -#endif - } else { - vsi->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX; - vsi->rx_buf_len = ICE_RXBUF_3072; - } -} - -/** * ice_write_qrxflxp_cntxt - write/configure QRXFLXP_CNTXT register * @hw: HW pointer * @pf_q: index of the Rx queue in the PF's queue space @@ -1821,21 +1831,14 @@ int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx) int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_tx_ring **tx_rings, u16 q_idx) { - struct ice_aqc_add_tx_qgrp *qg_buf; - int err; + DEFINE_FLEX(struct ice_aqc_add_tx_qgrp, qg_buf, txqs, 1); if (q_idx >= vsi->alloc_txq || !tx_rings || !tx_rings[q_idx]) return -EINVAL; - qg_buf = kzalloc(struct_size(qg_buf, txqs, 1), GFP_KERNEL); - if (!qg_buf) - return -ENOMEM; - qg_buf->num_txqs = 1; - err = ice_vsi_cfg_txq(vsi, tx_rings[q_idx], qg_buf); - kfree(qg_buf); - return err; + return ice_vsi_cfg_txq(vsi, tx_rings[q_idx], qg_buf); } /** @@ -1877,24 +1880,18 @@ setup_rings: static int ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_tx_ring **rings, u16 count) { - struct ice_aqc_add_tx_qgrp *qg_buf; - u16 q_idx = 0; + DEFINE_FLEX(struct ice_aqc_add_tx_qgrp, qg_buf, txqs, 1); int err = 0; - - qg_buf = kzalloc(struct_size(qg_buf, txqs, 1), GFP_KERNEL); - if (!qg_buf) - return -ENOMEM; + u16 q_idx; qg_buf->num_txqs = 1; for (q_idx = 0; q_idx < count; q_idx++) { err = ice_vsi_cfg_txq(vsi, rings[q_idx], qg_buf); if (err) - goto err_cfg_txqs; + break; } -err_cfg_txqs: - kfree(qg_buf); return err; } @@ -2185,20 +2182,6 @@ bool ice_vsi_is_rx_queue_active(struct ice_vsi *vsi) return false; } -/** - * ice_vsi_is_vlan_pruning_ena - check if VLAN pruning is enabled or not - * @vsi: VSI to check whether or not VLAN pruning is enabled. - * - * returns true if Rx VLAN pruning is enabled and false otherwise. - */ -bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi) -{ - if (!vsi) - return false; - - return (vsi->info.sw_flags2 & ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA); -} - static void ice_vsi_set_tc_cfg(struct ice_vsi *vsi) { if (!test_bit(ICE_FLAG_DCB_ENA, vsi->back->flags)) { @@ -2388,6 +2371,9 @@ static int ice_vsi_cfg_tc_lan(struct ice_pf *pf, struct ice_vsi *vsi) } else { max_txqs[i] = vsi->alloc_txq; } + + if (vsi->type == ICE_VSI_PF) + max_txqs[i] += vsi->num_xdp_txq; } dev_dbg(dev, "vsi->tc_cfg.ena_tc = %d\n", vsi->tc_cfg.ena_tc); @@ -2637,10 +2623,6 @@ void ice_vsi_decfg(struct ice_vsi *vsi) if (vsi->type == ICE_VSI_VF && vsi->agg_node && vsi->agg_node->valid) vsi->agg_node->num_vsis--; - if (vsi->agg_node) { - vsi->agg_node->valid = false; - vsi->agg_node->agg_id = 0; - } } /** @@ -2944,21 +2926,6 @@ void ice_vsi_dis_irq(struct ice_vsi *vsi) } /** - * ice_napi_del - Remove NAPI handler for the VSI - * @vsi: VSI for which NAPI handler is to be removed - */ -void ice_napi_del(struct ice_vsi *vsi) -{ - int v_idx; - - if (!vsi->netdev) - return; - - ice_for_each_q_vector(vsi, v_idx) - netif_napi_del(&vsi->q_vectors[v_idx]->napi); -} - -/** * ice_vsi_release - Delete a VSI and free its resources * @vsi: the VSI being removed * @@ -3593,6 +3560,12 @@ int ice_set_dflt_vsi(struct ice_vsi *vsi) dev = ice_pf_to_dev(vsi->back); + if (ice_lag_is_switchdev_running(vsi->back)) { + dev_dbg(dev, "VSI %d passed is a part of LAG containing interfaces in switchdev mode, nothing to do\n", + vsi->vsi_num); + return 0; + } + /* the VSI passed in is already the default VSI */ if (ice_is_vsi_dflt_vsi(vsi)) { dev_dbg(dev, "VSI %d passed in is already the default forwarding VSI, nothing to do\n", @@ -3970,7 +3943,7 @@ bool ice_is_feature_supported(struct ice_pf *pf, enum ice_feature f) * @pf: pointer to the struct ice_pf instance * @f: feature enum to set */ -static void ice_set_feature_support(struct ice_pf *pf, enum ice_feature f) +void ice_set_feature_support(struct ice_pf *pf, enum ice_feature f) { if (f < 0 || f >= ICE_F_MAX) return; @@ -4003,13 +3976,21 @@ void ice_init_feature_support(struct ice_pf *pf) case ICE_DEV_ID_E810C_BACKPLANE: case ICE_DEV_ID_E810C_QSFP: case ICE_DEV_ID_E810C_SFP: + case ICE_DEV_ID_E810_XXV_BACKPLANE: + case ICE_DEV_ID_E810_XXV_QSFP: + case ICE_DEV_ID_E810_XXV_SFP: ice_set_feature_support(pf, ICE_F_DSCP); - ice_set_feature_support(pf, ICE_F_PTP_EXTTS); - if (ice_is_e810t(&pf->hw)) { + if (ice_is_phy_rclk_in_netlist(&pf->hw)) + ice_set_feature_support(pf, ICE_F_PHY_RCLK); + /* If we don't own the timer - don't enable other caps */ + if (!ice_pf_src_tmr_owned(pf)) + break; + if (ice_is_cgu_in_netlist(&pf->hw)) + ice_set_feature_support(pf, ICE_F_CGU); + if (ice_is_clock_mux_in_netlist(&pf->hw)) ice_set_feature_support(pf, ICE_F_SMA_CTRL); - if (ice_gnss_is_gps_present(&pf->hw)) - ice_set_feature_support(pf, ICE_F_GNSS); - } + if (ice_gnss_is_gps_present(&pf->hw)) + ice_set_feature_support(pf, ICE_F_GNSS); break; default: break; @@ -4076,3 +4057,28 @@ void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx) { ctx->info.sec_flags &= ~ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD; } + +/** + * ice_vsi_update_local_lb - update sw block in VSI with local loopback bit + * @vsi: pointer to VSI structure + * @set: set or unset the bit + */ +int +ice_vsi_update_local_lb(struct ice_vsi *vsi, bool set) +{ + struct ice_vsi_ctx ctx = { + .info = vsi->info, + }; + + ctx.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID); + if (set) + ctx.info.sw_flags |= ICE_AQ_VSI_SW_FLAG_LOCAL_LB; + else + ctx.info.sw_flags &= ~ICE_AQ_VSI_SW_FLAG_LOCAL_LB; + + if (ice_update_vsi(&vsi->back->hw, vsi->idx, &ctx, NULL)) + return -ENODEV; + + vsi->info = ctx.info; + return 0; +} diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index e985766e6bb5..f24f5d1e6f9c 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -76,8 +76,6 @@ int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi); int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi); -bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi); - void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create); int ice_set_link(struct ice_vsi *vsi, bool ena); @@ -93,8 +91,6 @@ void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc); struct ice_vsi * ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params); -void ice_napi_del(struct ice_vsi *vsi); - int ice_vsi_release(struct ice_vsi *vsi); void ice_vsi_close(struct ice_vsi *vsi); @@ -130,7 +126,6 @@ void ice_update_tx_ring_stats(struct ice_tx_ring *ring, u64 pkts, u64 bytes); void ice_update_rx_ring_stats(struct ice_rx_ring *ring, u64 pkts, u64 bytes); -void ice_vsi_cfg_frame_size(struct ice_vsi *vsi); void ice_write_intrl(struct ice_q_vector *q_vector, u8 intrl); void ice_write_itr(struct ice_ring_container *rc, u16 itr); void ice_set_q_vector_intrl(struct ice_q_vector *q_vector); @@ -157,11 +152,13 @@ void ice_vsi_ctx_clear_antispoof(struct ice_vsi_ctx *ctx); void ice_vsi_ctx_set_allow_override(struct ice_vsi_ctx *ctx); void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx); +int ice_vsi_update_local_lb(struct ice_vsi *vsi, bool set); int ice_vsi_add_vlan_zero(struct ice_vsi *vsi); int ice_vsi_del_vlan_zero(struct ice_vsi *vsi); bool ice_vsi_has_non_zero_vlans(struct ice_vsi *vsi); u16 ice_vsi_num_non_zero_vlans(struct ice_vsi *vsi); bool ice_is_feature_supported(struct ice_pf *pf, enum ice_feature f); +void ice_set_feature_support(struct ice_pf *pf, enum ice_feature f); void ice_clear_feature_support(struct ice_pf *pf, enum ice_feature f); void ice_init_feature_support(struct ice_pf *pf); bool ice_vsi_is_rx_queue_active(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 b40dfe6ae321..fb9c93f37e84 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -1,11 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (c) 2018, Intel Corporation. */ +/* Copyright (c) 2018-2023, Intel Corporation. */ /* Intel(R) Ethernet Connection E800 Series Linux Driver */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <generated/utsrelease.h> +#include <linux/crash_dump.h> #include "ice.h" #include "ice_base.h" #include "ice_lib.h" @@ -64,6 +65,7 @@ struct device *ice_hw_to_dev(struct ice_hw *hw) } static struct workqueue_struct *ice_wq; +struct workqueue_struct *ice_lag_wq; static const struct net_device_ops ice_netdev_safe_mode_ops; static const struct net_device_ops ice_netdev_ops; @@ -80,7 +82,7 @@ ice_indr_setup_tc_cb(struct net_device *netdev, struct Qdisc *sch, void *data, void (*cleanup)(struct flow_block_cb *block_cb)); -bool netif_is_ice(struct net_device *dev) +bool netif_is_ice(const struct net_device *dev) { return dev && (dev->netdev_ops == &ice_netdev_ops); } @@ -635,6 +637,11 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type) dev_dbg(dev, "reset_type 0x%x requested\n", reset_type); + if (pf->lag && pf->lag->bonded && reset_type == ICE_RESET_PFR) { + dev_dbg(dev, "PFR on a bonded interface, promoting to CORER\n"); + reset_type = ICE_RESET_CORER; + } + ice_prepare_for_reset(pf, reset_type); /* trigger the reset */ @@ -718,8 +725,13 @@ static void ice_reset_subtask(struct ice_pf *pf) } /* No pending resets to finish processing. Check for new resets */ - if (test_bit(ICE_PFR_REQ, pf->state)) + if (test_bit(ICE_PFR_REQ, pf->state)) { reset_type = ICE_RESET_PFR; + if (pf->lag && pf->lag->bonded) { + dev_dbg(ice_pf_to_dev(pf), "PFR on a bonded interface, promoting to CORER\n"); + reset_type = ICE_RESET_CORER; + } + } if (test_bit(ICE_CORER_REQ, pf->state)) reset_type = ICE_RESET_CORER; if (test_bit(ICE_GLOBR_REQ, pf->state)) @@ -1239,64 +1251,63 @@ ice_handle_link_event(struct ice_pf *pf, struct ice_rq_event_info *event) return status; } -enum ice_aq_task_state { - ICE_AQ_TASK_WAITING = 0, - ICE_AQ_TASK_COMPLETE, - ICE_AQ_TASK_CANCELED, -}; - -struct ice_aq_task { - struct hlist_node entry; +/** + * ice_aq_prep_for_event - Prepare to wait for an AdminQ event from firmware + * @pf: pointer to the PF private structure + * @task: intermediate helper storage and identifier for waiting + * @opcode: the opcode to wait for + * + * Prepares to wait for a specific AdminQ completion event on the ARQ for + * a given PF. Actual wait would be done by a call to ice_aq_wait_for_event(). + * + * Calls are separated to allow caller registering for event before sending + * the command, which mitigates a race between registering and FW responding. + * + * To obtain only the descriptor contents, pass an task->event with null + * msg_buf. If the complete data buffer is desired, allocate the + * task->event.msg_buf with enough space ahead of time. + */ +void ice_aq_prep_for_event(struct ice_pf *pf, struct ice_aq_task *task, + u16 opcode) +{ + INIT_HLIST_NODE(&task->entry); + task->opcode = opcode; + task->state = ICE_AQ_TASK_WAITING; - u16 opcode; - struct ice_rq_event_info *event; - enum ice_aq_task_state state; -}; + spin_lock_bh(&pf->aq_wait_lock); + hlist_add_head(&task->entry, &pf->aq_wait_list); + spin_unlock_bh(&pf->aq_wait_lock); +} /** * ice_aq_wait_for_event - Wait for an AdminQ event from firmware * @pf: pointer to the PF private structure - * @opcode: the opcode to wait for + * @task: ptr prepared by ice_aq_prep_for_event() * @timeout: how long to wait, in jiffies - * @event: storage for the event info * * Waits for a specific AdminQ completion event on the ARQ for a given PF. The * current thread will be put to sleep until the specified event occurs or * until the given timeout is reached. * - * To obtain only the descriptor contents, pass an event without an allocated - * msg_buf. If the complete data buffer is desired, allocate the - * event->msg_buf with enough space ahead of time. - * * Returns: zero on success, or a negative error code on failure. */ -int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, - struct ice_rq_event_info *event) +int ice_aq_wait_for_event(struct ice_pf *pf, struct ice_aq_task *task, + unsigned long timeout) { + enum ice_aq_task_state *state = &task->state; struct device *dev = ice_pf_to_dev(pf); - struct ice_aq_task *task; - unsigned long start; + unsigned long start = jiffies; long ret; int err; - task = kzalloc(sizeof(*task), GFP_KERNEL); - if (!task) - return -ENOMEM; - - INIT_HLIST_NODE(&task->entry); - task->opcode = opcode; - task->event = event; - task->state = ICE_AQ_TASK_WAITING; - - spin_lock_bh(&pf->aq_wait_lock); - hlist_add_head(&task->entry, &pf->aq_wait_list); - spin_unlock_bh(&pf->aq_wait_lock); - - start = jiffies; - - ret = wait_event_interruptible_timeout(pf->aq_wait_queue, task->state, + ret = wait_event_interruptible_timeout(pf->aq_wait_queue, + *state != ICE_AQ_TASK_WAITING, timeout); - switch (task->state) { + switch (*state) { + case ICE_AQ_TASK_NOT_PREPARED: + WARN(1, "call to %s without ice_aq_prep_for_event()", __func__); + err = -EINVAL; + break; case ICE_AQ_TASK_WAITING: err = ret < 0 ? ret : -ETIMEDOUT; break; @@ -1307,7 +1318,7 @@ int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, err = ret < 0 ? ret : 0; break; default: - WARN(1, "Unexpected AdminQ wait task state %u", task->state); + WARN(1, "Unexpected AdminQ wait task state %u", *state); err = -EINVAL; break; } @@ -1315,12 +1326,11 @@ int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, dev_dbg(dev, "Waited %u msecs (max %u msecs) for firmware response to op 0x%04x\n", jiffies_to_msecs(jiffies - start), jiffies_to_msecs(timeout), - opcode); + task->opcode); spin_lock_bh(&pf->aq_wait_lock); hlist_del(&task->entry); spin_unlock_bh(&pf->aq_wait_lock); - kfree(task); return err; } @@ -1346,23 +1356,26 @@ int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, static void ice_aq_check_events(struct ice_pf *pf, u16 opcode, struct ice_rq_event_info *event) { + struct ice_rq_event_info *task_ev; struct ice_aq_task *task; bool found = false; spin_lock_bh(&pf->aq_wait_lock); hlist_for_each_entry(task, &pf->aq_wait_list, entry) { - if (task->state || task->opcode != opcode) + if (task->state != ICE_AQ_TASK_WAITING) + continue; + if (task->opcode != opcode) continue; - memcpy(&task->event->desc, &event->desc, sizeof(event->desc)); - task->event->msg_len = event->msg_len; + task_ev = &task->event; + memcpy(&task_ev->desc, &event->desc, sizeof(event->desc)); + task_ev->msg_len = event->msg_len; /* Only copy the data buffer if a destination was set */ - if (task->event->msg_buf && - task->event->buf_len > event->buf_len) { - memcpy(task->event->msg_buf, event->msg_buf, + if (task_ev->msg_buf && task_ev->buf_len >= event->buf_len) { + memcpy(task_ev->msg_buf, event->msg_buf, event->buf_len); - task->event->buf_len = event->buf_len; + task_ev->buf_len = event->buf_len; } task->state = ICE_AQ_TASK_COMPLETE; @@ -1746,7 +1759,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf) wr32(hw, GL_MDET_TX_PQM, 0xffffffff); } - reg = rd32(hw, GL_MDET_TX_TCLAN); + reg = rd32(hw, GL_MDET_TX_TCLAN_BY_MAC(hw)); if (reg & GL_MDET_TX_TCLAN_VALID_M) { u8 pf_num = (reg & GL_MDET_TX_TCLAN_PF_NUM_M) >> GL_MDET_TX_TCLAN_PF_NUM_S; @@ -1760,7 +1773,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf) if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n", event, queue, pf_num, vf_num); - wr32(hw, GL_MDET_TX_TCLAN, 0xffffffff); + wr32(hw, GL_MDET_TX_TCLAN_BY_MAC(hw), U32_MAX); } reg = rd32(hw, GL_MDET_RX); @@ -1788,9 +1801,9 @@ static void ice_handle_mdd_event(struct ice_pf *pf) dev_info(dev, "Malicious Driver Detection event TX_PQM detected on PF\n"); } - reg = rd32(hw, PF_MDET_TX_TCLAN); + reg = rd32(hw, PF_MDET_TX_TCLAN_BY_MAC(hw)); if (reg & PF_MDET_TX_TCLAN_VALID_M) { - wr32(hw, PF_MDET_TX_TCLAN, 0xFFFF); + wr32(hw, PF_MDET_TX_TCLAN_BY_MAC(hw), 0xffff); if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event TX_TCLAN detected on PF\n"); } @@ -3137,7 +3150,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) if (oicr & PFINT_OICR_TSYN_TX_M) { ena_mask &= ~PFINT_OICR_TSYN_TX_M; - if (!hw->reset_ongoing) + if (!hw->reset_ongoing && ice_ptp_pf_handles_tx_interrupt(pf)) set_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread); } @@ -3147,7 +3160,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) ena_mask &= ~PFINT_OICR_TSYN_EVNT_M; - if (hw->func_caps.ts_func_info.src_tmr_owned) { + if (ice_pf_src_tmr_owned(pf)) { /* Save EVENTs from GLTSYN register */ pf->ptp.ext_ts_irq |= gltsyn_stat & (GLTSYN_STAT_EVENT0_M | @@ -3392,6 +3405,7 @@ static void ice_set_ops(struct ice_vsi *vsi) netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_XSK_ZEROCOPY | NETDEV_XDP_ACT_RX_SG; + netdev->xdp_zc_max_segs = ICE_MAX_BUF_TXD; } /** @@ -3794,6 +3808,7 @@ u16 ice_get_avail_rxq_count(struct ice_pf *pf) static void ice_deinit_pf(struct ice_pf *pf) { ice_service_task_stop(pf); + mutex_destroy(&pf->lag_mutex); mutex_destroy(&pf->adev_mutex); mutex_destroy(&pf->sw_mutex); mutex_destroy(&pf->tc_mutex); @@ -3856,7 +3871,8 @@ static void ice_set_pf_caps(struct ice_pf *pf) } clear_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags); - if (func_caps->common_cap.ieee_1588) + if (func_caps->common_cap.ieee_1588 && + !(pf->hw.mac_type == ICE_MAC_E830)) set_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags); pf->max_pf_txqs = func_caps->common_cap.num_txq; @@ -3874,6 +3890,7 @@ static int ice_init_pf(struct ice_pf *pf) mutex_init(&pf->sw_mutex); mutex_init(&pf->tc_mutex); mutex_init(&pf->adev_mutex); + mutex_init(&pf->lag_mutex); INIT_HLIST_HEAD(&pf->aq_wait_list); spin_lock_init(&pf->aq_wait_lock); @@ -4506,6 +4523,31 @@ static void ice_deinit_eth(struct ice_pf *pf) ice_decfg_netdev(vsi); } +/** + * ice_wait_for_fw - wait for full FW readiness + * @hw: pointer to the hardware structure + * @timeout: milliseconds that can elapse before timing out + */ +static int ice_wait_for_fw(struct ice_hw *hw, u32 timeout) +{ + int fw_loading; + u32 elapsed = 0; + + while (elapsed <= timeout) { + fw_loading = rd32(hw, GL_MNG_FWSM) & GL_MNG_FWSM_FW_LOADING_M; + + /* firmware was not yet loaded, we have to wait more */ + if (fw_loading) { + elapsed += 100; + msleep(100); + continue; + } + return 0; + } + + return -ETIMEDOUT; +} + static int ice_init_dev(struct ice_pf *pf) { struct device *dev = ice_pf_to_dev(pf); @@ -4518,6 +4560,18 @@ static int ice_init_dev(struct ice_pf *pf) return err; } + /* Some cards require longer initialization times + * due to necessity of loading FW from an external source. + * This can take even half a minute. + */ + if (ice_is_pf_c827(hw)) { + err = ice_wait_for_fw(hw, 30000); + if (err) { + dev_err(dev, "ice_wait_for_fw timed out"); + return err; + } + } + ice_init_feature_support(pf); ice_request_fw(pf); @@ -4613,6 +4667,10 @@ static void ice_init_features(struct ice_pf *pf) if (ice_is_feature_supported(pf, ICE_F_GNSS)) ice_gnss_init(pf); + if (ice_is_feature_supported(pf, ICE_F_CGU) || + ice_is_feature_supported(pf, ICE_F_PHY_RCLK)) + ice_dpll_init(pf); + /* Note: Flow director init failure is non-fatal to load */ if (ice_init_fdir(pf)) dev_err(dev, "could not initialize flow director\n"); @@ -4631,6 +4689,9 @@ static void ice_init_features(struct ice_pf *pf) static void ice_deinit_features(struct ice_pf *pf) { + if (ice_is_safe_mode(pf)) + return; + ice_deinit_lag(pf); if (test_bit(ICE_FLAG_DCB_CAPABLE, pf->flags)) ice_cfg_lldp_mib_change(&pf->hw, false); @@ -4639,6 +4700,8 @@ static void ice_deinit_features(struct ice_pf *pf) ice_gnss_exit(pf); if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) ice_ptp_release(pf); + if (test_bit(ICE_FLAG_DPLL, pf->flags)) + ice_dpll_deinit(pf); } static void ice_init_wakeup(struct ice_pf *pf) @@ -4962,6 +5025,20 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) return -EINVAL; } + /* when under a kdump kernel initiate a reset before enabling the + * device in order to clear out any pending DMA transactions. These + * transactions can cause some systems to machine check when doing + * the pcim_enable_device() below. + */ + if (is_kdump_kernel()) { + pci_save_state(pdev); + pci_clear_master(pdev); + err = pcie_flr(pdev); + if (err) + return err; + pci_restore_state(pdev); + } + /* this driver uses devres, see * Documentation/driver-api/driver-model/devres.rst */ @@ -5465,7 +5542,7 @@ static void ice_pci_err_resume(struct pci_dev *pdev) return; } - ice_restore_all_vfs_msi_state(pdev); + ice_restore_all_vfs_msi_state(pf); ice_do_reset(pf, ICE_RESET_PFR); ice_service_task_restart(pf); @@ -5508,34 +5585,38 @@ static void ice_pci_err_reset_done(struct pci_dev *pdev) * Class, Class Mask, private data (not used) } */ static const struct pci_device_id ice_pci_tbl[] = { - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_BACKPLANE), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_QSFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_SFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_BACKPLANE), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_QSFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_SFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_BACKPLANE), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_QSFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_SFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_10G_BASE_T), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_SGMII), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_BACKPLANE), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_QSFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_SFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_10G_BASE_T), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_SGMII), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_BACKPLANE), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_SFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_10G_BASE_T), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_SGMII), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_BACKPLANE), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_SFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_10G_BASE_T), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_1GBE), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_QSFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822_SI_DFLT), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_BACKPLANE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_QSFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_SFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_BACKPLANE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_QSFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_SFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_BACKPLANE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_QSFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_SFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_10G_BASE_T) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_SGMII) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_BACKPLANE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_QSFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_SFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_10G_BASE_T) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_SGMII) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_BACKPLANE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_SFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_10G_BASE_T) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_SGMII) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_BACKPLANE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_SFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_10G_BASE_T) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_1GBE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_QSFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822_SI_DFLT) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_BACKPLANE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_QSFP56) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_SFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_SFP_DD) }, /* required last entry */ - { 0, } + {} }; MODULE_DEVICE_TABLE(pci, ice_pci_tbl); @@ -5559,6 +5640,8 @@ static struct pci_driver ice_driver = { #endif /* CONFIG_PM */ .shutdown = ice_shutdown, .sriov_configure = ice_sriov_configure, + .sriov_get_vf_total_msix = ice_sriov_get_vf_total_msix, + .sriov_set_msix_vec_count = ice_sriov_set_msix_vec_count, .err_handler = &ice_pci_err_handler }; @@ -5570,23 +5653,37 @@ static struct pci_driver ice_driver = { */ static int __init ice_module_init(void) { - int status; + int status = -ENOMEM; pr_info("%s\n", ice_driver_string); pr_info("%s\n", ice_copyright); + ice_adv_lnk_speed_maps_init(); + ice_wq = alloc_workqueue("%s", 0, 0, KBUILD_MODNAME); if (!ice_wq) { pr_err("Failed to create workqueue\n"); - return -ENOMEM; + return status; + } + + ice_lag_wq = alloc_ordered_workqueue("ice_lag_wq", 0); + if (!ice_lag_wq) { + pr_err("Failed to create LAG workqueue\n"); + goto err_dest_wq; } status = pci_register_driver(&ice_driver); if (status) { pr_err("failed to register PCI driver, err %d\n", status); - destroy_workqueue(ice_wq); + goto err_dest_lag_wq; } + return 0; + +err_dest_lag_wq: + destroy_workqueue(ice_lag_wq); +err_dest_wq: + destroy_workqueue(ice_wq); return status; } module_init(ice_module_init); @@ -5601,6 +5698,7 @@ static void __exit ice_module_exit(void) { pci_unregister_driver(&ice_driver); destroy_workqueue(ice_wq); + destroy_workqueue(ice_lag_wq); pr_info("module unloaded\n"); } module_exit(ice_module_exit); @@ -5703,7 +5801,7 @@ static void ice_set_rx_mode(struct net_device *netdev) struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; - if (!vsi) + if (!vsi || ice_is_switchdev_running(vsi->back)) return; /* Set the flags to synchronize filters @@ -6255,7 +6353,7 @@ static void ice_tx_dim_work(struct work_struct *work) u16 itr; dim = container_of(work, struct dim, work); - rc = (struct ice_ring_container *)dim->priv; + rc = dim->priv; WARN_ON(dim->profile_ix >= ARRAY_SIZE(tx_profile)); @@ -6275,7 +6373,7 @@ static void ice_rx_dim_work(struct work_struct *work) u16 itr; dim = container_of(work, struct dim, work); - rc = (struct ice_ring_container *)dim->priv; + rc = dim->priv; WARN_ON(dim->profile_ix >= ARRAY_SIZE(rx_profile)); @@ -7303,10 +7401,6 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) goto err_vsi_rebuild; } - /* configure PTP timestamping after VSI rebuild */ - if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) - ice_ptp_cfg_timestamp(pf, false); - err = ice_vsi_rebuild_by_type(pf, ICE_VSI_SWITCHDEV_CTRL); if (err) { dev_err(dev, "Switchdev CTRL VSI rebuild failed: %d\n", err); @@ -7356,6 +7450,11 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) clear_bit(ICE_RESET_FAILED, pf->state); ice_plug_aux_dev(pf); + if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) + ice_lag_rebuild(pf); + + /* Restore timestamp mode settings after VSI rebuild */ + ice_ptp_restore_timestamp_mode(pf); return; err_vsi_rebuild: diff --git a/drivers/net/ethernet/intel/ice/ice_protocol_type.h b/drivers/net/ethernet/intel/ice/ice_protocol_type.h index 6a9364761165..f6f27361c3cf 100644 --- a/drivers/net/ethernet/intel/ice/ice_protocol_type.h +++ b/drivers/net/ethernet/intel/ice/ice_protocol_type.h @@ -287,6 +287,7 @@ struct ice_nvgre_hdr { * M = EVLAN (0x8100) - Outer L2 header has EVLAN (ethernet type 0x8100) * N = EVLAN (0x9100) - Outer L2 header has EVLAN (ethernet type 0x9100) */ +#define ICE_PKT_FROM_NETWORK BIT(3) #define ICE_PKT_VLAN_STAG BIT(12) #define ICE_PKT_VLAN_ITAG BIT(13) #define ICE_PKT_VLAN_EVLAN (BIT(14) | BIT(15)) @@ -392,10 +393,10 @@ enum ice_hw_metadata_offset { }; enum ice_pkt_flags { - ICE_PKT_FLAGS_VLAN = 0, - ICE_PKT_FLAGS_TUNNEL = 1, - ICE_PKT_FLAGS_TCP = 2, - ICE_PKT_FLAGS_ERROR = 3, + ICE_PKT_FLAGS_MDID20 = 0, + ICE_PKT_FLAGS_MDID21 = 1, + ICE_PKT_FLAGS_MDID22 = 2, + ICE_PKT_FLAGS_MDID23 = 3, }; struct ice_hw_metadata { diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index 81d96a40d5a7..71f405f8a6fe 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -39,8 +39,8 @@ ice_get_sma_config_e810t(struct ice_hw *hw, struct ptp_pin_desc *ptp_pins) /* initialize with defaults */ for (i = 0; i < NUM_PTP_PINS_E810T; i++) { - snprintf(ptp_pins[i].name, sizeof(ptp_pins[i].name), - "%s", ice_pin_desc_e810t[i].name); + strscpy(ptp_pins[i].name, ice_pin_desc_e810t[i].name, + sizeof(ptp_pins[i].name)); ptp_pins[i].index = ice_pin_desc_e810t[i].index; ptp_pins[i].func = ice_pin_desc_e810t[i].func; ptp_pins[i].chan = ice_pin_desc_e810t[i].chan; @@ -256,36 +256,42 @@ ice_verify_pin_e810t(struct ptp_clock_info *info, unsigned int pin, } /** - * ice_set_tx_tstamp - Enable or disable Tx timestamping - * @pf: The PF pointer to search in - * @on: bool value for whether timestamps are enabled or disabled + * ice_ptp_cfg_tx_interrupt - Configure Tx timestamp interrupt for the device + * @pf: Board private structure + * + * Program the device to respond appropriately to the Tx timestamp interrupt + * cause. */ -static void ice_set_tx_tstamp(struct ice_pf *pf, bool on) +static void ice_ptp_cfg_tx_interrupt(struct ice_pf *pf) { - struct ice_vsi *vsi; + struct ice_hw *hw = &pf->hw; + bool enable; u32 val; - u16 i; - - vsi = ice_get_main_vsi(pf); - if (!vsi) - return; - /* Set the timestamp enable flag for all the Tx rings */ - ice_for_each_txq(vsi, i) { - if (!vsi->tx_rings[i]) - continue; - vsi->tx_rings[i]->ptp_tx = on; + switch (pf->ptp.tx_interrupt_mode) { + case ICE_PTP_TX_INTERRUPT_ALL: + /* React to interrupts across all quads. */ + wr32(hw, PFINT_TSYN_MSK + (0x4 * hw->pf_id), (u32)0x1f); + enable = true; + break; + case ICE_PTP_TX_INTERRUPT_NONE: + /* Do not react to interrupts on any quad. */ + wr32(hw, PFINT_TSYN_MSK + (0x4 * hw->pf_id), (u32)0x0); + enable = false; + break; + case ICE_PTP_TX_INTERRUPT_SELF: + default: + enable = pf->ptp.tstamp_config.tx_type == HWTSTAMP_TX_ON; + break; } /* Configure the Tx timestamp interrupt */ - val = rd32(&pf->hw, PFINT_OICR_ENA); - if (on) + val = rd32(hw, PFINT_OICR_ENA); + if (enable) val |= PFINT_OICR_TSYN_TX_M; else val &= ~PFINT_OICR_TSYN_TX_M; - wr32(&pf->hw, PFINT_OICR_ENA, val); - - pf->ptp.tstamp_config.tx_type = on ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; + wr32(hw, PFINT_OICR_ENA, val); } /** @@ -299,7 +305,7 @@ static void ice_set_rx_tstamp(struct ice_pf *pf, bool on) u16 i; vsi = ice_get_main_vsi(pf); - if (!vsi) + if (!vsi || !vsi->rx_rings) return; /* Set the timestamp flag for all the Rx rings */ @@ -308,148 +314,50 @@ static void ice_set_rx_tstamp(struct ice_pf *pf, bool on) continue; vsi->rx_rings[i]->ptp_rx = on; } - - pf->ptp.tstamp_config.rx_filter = on ? HWTSTAMP_FILTER_ALL : - HWTSTAMP_FILTER_NONE; } /** - * ice_ptp_cfg_timestamp - Configure timestamp for init/deinit + * ice_ptp_disable_timestamp_mode - Disable current timestamp mode * @pf: Board private structure - * @ena: bool value to enable or disable time stamp - * - * This function will configure timestamping during PTP initialization - * and deinitialization - */ -void ice_ptp_cfg_timestamp(struct ice_pf *pf, bool ena) -{ - ice_set_tx_tstamp(pf, ena); - ice_set_rx_tstamp(pf, ena); -} - -/** - * ice_get_ptp_clock_index - Get the PTP clock index - * @pf: the PF pointer - * - * Determine the clock index of the PTP clock associated with this device. If - * this is the PF controlling the clock, just use the local access to the - * clock device pointer. - * - * Otherwise, read from the driver shared parameters to determine the clock - * index value. - * - * Returns: the index of the PTP clock associated with this device, or -1 if - * there is no associated clock. - */ -int ice_get_ptp_clock_index(struct ice_pf *pf) -{ - struct device *dev = ice_pf_to_dev(pf); - enum ice_aqc_driver_params param_idx; - struct ice_hw *hw = &pf->hw; - u8 tmr_idx; - u32 value; - int err; - - /* Use the ptp_clock structure if we're the main PF */ - if (pf->ptp.clock) - return ptp_clock_index(pf->ptp.clock); - - tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc; - if (!tmr_idx) - param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR0; - else - param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR1; - - err = ice_aq_get_driver_param(hw, param_idx, &value, NULL); - if (err) { - dev_err(dev, "Failed to read PTP clock index parameter, err %d aq_err %s\n", - err, ice_aq_str(hw->adminq.sq_last_status)); - return -1; - } - - /* The PTP clock index is an integer, and will be between 0 and - * INT_MAX. The highest bit of the driver shared parameter is used to - * indicate whether or not the currently stored clock index is valid. - */ - if (!(value & PTP_SHARED_CLK_IDX_VALID)) - return -1; - - return value & ~PTP_SHARED_CLK_IDX_VALID; -} - -/** - * ice_set_ptp_clock_index - Set the PTP clock index - * @pf: the PF pointer - * - * Set the PTP clock index for this device into the shared driver parameters, - * so that other PFs associated with this device can read it. * - * If the PF is unable to store the clock index, it will log an error, but - * will continue operating PTP. + * Called during preparation for reset to temporarily disable timestamping on + * the device. Called during remove to disable timestamping while cleaning up + * driver resources. */ -static void ice_set_ptp_clock_index(struct ice_pf *pf) +static void ice_ptp_disable_timestamp_mode(struct ice_pf *pf) { - struct device *dev = ice_pf_to_dev(pf); - enum ice_aqc_driver_params param_idx; struct ice_hw *hw = &pf->hw; - u8 tmr_idx; - u32 value; - int err; - - if (!pf->ptp.clock) - return; - - tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc; - if (!tmr_idx) - param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR0; - else - param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR1; + u32 val; - value = (u32)ptp_clock_index(pf->ptp.clock); - if (value > INT_MAX) { - dev_err(dev, "PTP Clock index is too large to store\n"); - return; - } - value |= PTP_SHARED_CLK_IDX_VALID; + val = rd32(hw, PFINT_OICR_ENA); + val &= ~PFINT_OICR_TSYN_TX_M; + wr32(hw, PFINT_OICR_ENA, val); - err = ice_aq_set_driver_param(hw, param_idx, value, NULL); - if (err) { - dev_err(dev, "Failed to set PTP clock index parameter, err %d aq_err %s\n", - err, ice_aq_str(hw->adminq.sq_last_status)); - } + ice_set_rx_tstamp(pf, false); } /** - * ice_clear_ptp_clock_index - Clear the PTP clock index - * @pf: the PF pointer + * ice_ptp_restore_timestamp_mode - Restore timestamp configuration + * @pf: Board private structure * - * Clear the PTP clock index for this device. Must be called when - * unregistering the PTP clock, in order to ensure other PFs stop reporting - * a clock object that no longer exists. + * Called at the end of rebuild to restore timestamp configuration after + * a device reset. */ -static void ice_clear_ptp_clock_index(struct ice_pf *pf) +void ice_ptp_restore_timestamp_mode(struct ice_pf *pf) { - struct device *dev = ice_pf_to_dev(pf); - enum ice_aqc_driver_params param_idx; struct ice_hw *hw = &pf->hw; - u8 tmr_idx; - int err; + bool enable_rx; - /* Do not clear the index if we don't own the timer */ - if (!hw->func_caps.ts_func_info.src_tmr_owned) - return; + ice_ptp_cfg_tx_interrupt(pf); - tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc; - if (!tmr_idx) - param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR0; - else - param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR1; + enable_rx = pf->ptp.tstamp_config.rx_filter == HWTSTAMP_FILTER_ALL; + ice_set_rx_tstamp(pf, enable_rx); - err = ice_aq_set_driver_param(hw, param_idx, 0, NULL); - if (err) { - dev_dbg(dev, "Failed to clear PTP clock index parameter, err %d aq_err %s\n", - err, ice_aq_str(hw->adminq.sq_last_status)); - } + /* Trigger an immediate software interrupt to ensure that timestamps + * which occurred during reset are handled now. + */ + wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M); + ice_flush(hw); } /** @@ -674,9 +582,6 @@ static void ice_ptp_process_tx_tstamp(struct ice_ptp_tx *tx) int err; u8 idx; - if (!tx->init) - return; - ptp_port = container_of(tx, struct ice_ptp_port, tx); pf = ptp_port_to_pf(ptp_port); hw = &pf->hw; @@ -775,6 +680,39 @@ skip_ts_read: } /** + * ice_ptp_tx_tstamp_owner - Process Tx timestamps for all ports on the device + * @pf: Board private structure + */ +static enum ice_tx_tstamp_work ice_ptp_tx_tstamp_owner(struct ice_pf *pf) +{ + struct ice_ptp_port *port; + unsigned int i; + + mutex_lock(&pf->ptp.ports_owner.lock); + list_for_each_entry(port, &pf->ptp.ports_owner.ports, list_member) { + struct ice_ptp_tx *tx = &port->tx; + + if (!tx || !tx->init) + continue; + + ice_ptp_process_tx_tstamp(tx); + } + mutex_unlock(&pf->ptp.ports_owner.lock); + + for (i = 0; i < ICE_MAX_QUAD; i++) { + u64 tstamp_ready; + int err; + + /* Read the Tx ready status first */ + err = ice_get_phy_tx_tstamp_ready(&pf->hw, i, &tstamp_ready); + if (err || tstamp_ready) + return ICE_TX_TSTAMP_WORK_PENDING; + } + + return ICE_TX_TSTAMP_WORK_DONE; +} + +/** * ice_ptp_tx_tstamp - Process Tx timestamps for this function. * @tx: Tx tracking structure to initialize * @@ -1366,6 +1304,7 @@ out_unlock: void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) { struct ice_ptp_port *ptp_port; + struct ice_hw *hw = &pf->hw; if (!test_bit(ICE_FLAG_PTP, pf->flags)) return; @@ -1380,11 +1319,16 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) /* Update cached link status for this port immediately */ ptp_port->link_up = linkup; - /* E810 devices do not need to reconfigure the PHY */ - if (ice_is_e810(&pf->hw)) + switch (hw->phy_model) { + case ICE_PHY_E810: + /* Do not reconfigure E810 PHY */ return; - - ice_ptp_port_phy_restart(ptp_port); + case ICE_PHY_E822: + ice_ptp_port_phy_restart(ptp_port); + return; + default: + dev_warn(ice_pf_to_dev(pf), "%s: Unknown PHY type\n", __func__); + } } /** @@ -1441,6 +1385,24 @@ static void ice_ptp_reset_phy_timestamping(struct ice_pf *pf) } /** + * ice_ptp_restart_all_phy - Restart all PHYs to recalibrate timestamping + * @pf: Board private structure + */ +static void ice_ptp_restart_all_phy(struct ice_pf *pf) +{ + struct list_head *entry; + + list_for_each(entry, &pf->ptp.ports_owner.ports) { + struct ice_ptp_port *port = list_entry(entry, + struct ice_ptp_port, + list_member); + + if (port->link_up) + ice_ptp_port_phy_restart(port); + } +} + +/** * ice_ptp_adjfine - Adjust clock increment rate * @info: the driver's PTP info structure * @scaled_ppm: Parts per million with 16-bit fractional field @@ -1877,9 +1839,9 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts) /* Reenable periodic outputs */ ice_ptp_enable_all_clkout(pf); - /* Recalibrate and re-enable timestamp block */ - if (pf->ptp.port.link_up) - ice_ptp_port_phy_restart(&pf->ptp.port); + /* Recalibrate and re-enable timestamp blocks for E822/E823 */ + if (hw->phy_model == ICE_PHY_E822) + ice_ptp_restart_all_phy(pf); exit: if (err) { dev_err(ice_pf_to_dev(pf), "PTP failed to set time %d\n", err); @@ -1976,21 +1938,32 @@ ice_ptp_get_syncdevicetime(ktime_t *device, u32 hh_lock, hh_art_ctl; int i; - /* Get the HW lock */ - hh_lock = rd32(hw, PFHH_SEM + (PFTSYN_SEM_BYTES * hw->pf_id)); +#define MAX_HH_HW_LOCK_TRIES 5 +#define MAX_HH_CTL_LOCK_TRIES 100 + + for (i = 0; i < MAX_HH_HW_LOCK_TRIES; i++) { + /* Get the HW lock */ + hh_lock = rd32(hw, PFHH_SEM + (PFTSYN_SEM_BYTES * hw->pf_id)); + if (hh_lock & PFHH_SEM_BUSY_M) { + usleep_range(10000, 15000); + continue; + } + break; + } if (hh_lock & PFHH_SEM_BUSY_M) { dev_err(ice_pf_to_dev(pf), "PTP failed to get hh lock\n"); - return -EFAULT; + return -EBUSY; } + /* Program cmd to master timer */ + ice_ptp_src_cmd(hw, ICE_PTP_READ_TIME); + /* Start the ART and device clock sync sequence */ hh_art_ctl = rd32(hw, GLHH_ART_CTL); hh_art_ctl = hh_art_ctl | GLHH_ART_CTL_ACTIVE_M; wr32(hw, GLHH_ART_CTL, hh_art_ctl); -#define MAX_HH_LOCK_TRIES 100 - - for (i = 0; i < MAX_HH_LOCK_TRIES; i++) { + for (i = 0; i < MAX_HH_CTL_LOCK_TRIES; i++) { /* Wait for sync to complete */ hh_art_ctl = rd32(hw, GLHH_ART_CTL); if (hh_art_ctl & GLHH_ART_CTL_ACTIVE_M) { @@ -2014,19 +1987,23 @@ ice_ptp_get_syncdevicetime(ktime_t *device, break; } } + + /* Clear the master timer */ + ice_ptp_src_cmd(hw, ICE_PTP_NOP); + /* Release HW lock */ hh_lock = rd32(hw, PFHH_SEM + (PFTSYN_SEM_BYTES * hw->pf_id)); hh_lock = hh_lock & ~PFHH_SEM_BUSY_M; wr32(hw, PFHH_SEM + (PFTSYN_SEM_BYTES * hw->pf_id), hh_lock); - if (i == MAX_HH_LOCK_TRIES) + if (i == MAX_HH_CTL_LOCK_TRIES) return -ETIMEDOUT; return 0; } /** - * ice_ptp_getcrosststamp_e822 - Capture a device cross timestamp + * ice_ptp_getcrosststamp_e82x - Capture a device cross timestamp * @info: the driver's PTP info structure * @cts: The memory to fill the cross timestamp info * @@ -2034,14 +2011,14 @@ ice_ptp_get_syncdevicetime(ktime_t *device, * clock. Fill the cross timestamp information and report it back to the * caller. * - * This is only valid for E822 devices which have support for generating the - * cross timestamp via PCIe PTM. + * This is only valid for E822 and E823 devices which have support for + * generating the cross timestamp via PCIe PTM. * * In order to correctly correlate the ART timestamp back to the TSC time, the * CPU must have X86_FEATURE_TSC_KNOWN_FREQ. */ static int -ice_ptp_getcrosststamp_e822(struct ptp_clock_info *info, +ice_ptp_getcrosststamp_e82x(struct ptp_clock_info *info, struct system_device_crosststamp *cts) { struct ice_pf *pf = ptp_info_to_pf(info); @@ -2081,10 +2058,10 @@ ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config) { switch (config->tx_type) { case HWTSTAMP_TX_OFF: - ice_set_tx_tstamp(pf, false); + pf->ptp.tstamp_config.tx_type = HWTSTAMP_TX_OFF; break; case HWTSTAMP_TX_ON: - ice_set_tx_tstamp(pf, true); + pf->ptp.tstamp_config.tx_type = HWTSTAMP_TX_ON; break; default: return -ERANGE; @@ -2092,7 +2069,7 @@ ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config) switch (config->rx_filter) { case HWTSTAMP_FILTER_NONE: - ice_set_rx_tstamp(pf, false); + pf->ptp.tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; break; case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: @@ -2108,12 +2085,15 @@ ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config) case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: case HWTSTAMP_FILTER_NTP_ALL: case HWTSTAMP_FILTER_ALL: - ice_set_rx_tstamp(pf, true); + pf->ptp.tstamp_config.rx_filter = HWTSTAMP_FILTER_ALL; break; default: return -ERANGE; } + /* Immediately update the device timestamping mode */ + ice_ptp_restore_timestamp_mode(pf); + return 0; } @@ -2246,18 +2226,20 @@ ice_ptp_setup_sma_pins_e810t(struct ice_pf *pf, struct ptp_clock_info *info) static void ice_ptp_setup_pins_e810(struct ice_pf *pf, struct ptp_clock_info *info) { - info->n_per_out = N_PER_OUT_E810; - - if (ice_is_feature_supported(pf, ICE_F_PTP_EXTTS)) - info->n_ext_ts = N_EXT_TS_E810; - if (ice_is_feature_supported(pf, ICE_F_SMA_CTRL)) { info->n_ext_ts = N_EXT_TS_E810; + info->n_per_out = N_PER_OUT_E810T; info->n_pins = NUM_PTP_PINS_E810T; info->verify = ice_verify_pin_e810t; /* Complete setup of the SMA pins */ ice_ptp_setup_sma_pins_e810t(pf, info); + } else if (ice_is_e810t(&pf->hw)) { + info->n_ext_ts = N_EXT_TS_NO_SMA_E810T; + info->n_per_out = N_PER_OUT_NO_SMA_E810T; + } else { + info->n_per_out = N_PER_OUT_E810; + info->n_ext_ts = N_EXT_TS_E810; } } @@ -2275,22 +2257,22 @@ ice_ptp_setup_pins_e823(struct ice_pf *pf, struct ptp_clock_info *info) } /** - * ice_ptp_set_funcs_e822 - Set specialized functions for E822 support + * ice_ptp_set_funcs_e82x - Set specialized functions for E82x support * @pf: Board private structure * @info: PTP info to fill * - * Assign functions to the PTP capabiltiies structure for E822 devices. + * Assign functions to the PTP capabiltiies structure for E82x devices. * Functions which operate across all device families should be set directly - * in ice_ptp_set_caps. Only add functions here which are distinct for E822 + * in ice_ptp_set_caps. Only add functions here which are distinct for E82x * devices. */ static void -ice_ptp_set_funcs_e822(struct ice_pf *pf, struct ptp_clock_info *info) +ice_ptp_set_funcs_e82x(struct ice_pf *pf, struct ptp_clock_info *info) { #ifdef CONFIG_ICE_HWTS if (boot_cpu_has(X86_FEATURE_ART) && boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) - info->getcrosststamp = ice_ptp_getcrosststamp_e822; + info->getcrosststamp = ice_ptp_getcrosststamp_e82x; #endif /* CONFIG_ICE_HWTS */ } @@ -2324,6 +2306,8 @@ ice_ptp_set_funcs_e810(struct ice_pf *pf, struct ptp_clock_info *info) static void ice_ptp_set_funcs_e823(struct ice_pf *pf, struct ptp_clock_info *info) { + ice_ptp_set_funcs_e82x(pf, info); + info->enable = ice_ptp_gpio_enable_e823; ice_ptp_setup_pins_e823(pf, info); } @@ -2351,7 +2335,7 @@ static void ice_ptp_set_caps(struct ice_pf *pf) else if (ice_is_e823(&pf->hw)) ice_ptp_set_funcs_e823(pf, info); else - ice_ptp_set_funcs_e822(pf, info); + ice_ptp_set_funcs_e82x(pf, info); } /** @@ -2366,7 +2350,6 @@ static void ice_ptp_set_caps(struct ice_pf *pf) static long ice_ptp_create_clock(struct ice_pf *pf) { struct ptp_clock_info *info; - struct ptp_clock *clock; struct device *dev; /* No need to create a clock device if we already have one */ @@ -2379,11 +2362,11 @@ static long ice_ptp_create_clock(struct ice_pf *pf) dev = ice_pf_to_dev(pf); /* Attempt to register the clock before enabling the hardware. */ - clock = ptp_clock_register(info, dev); - if (IS_ERR(clock)) - return PTR_ERR(clock); - - pf->ptp.clock = clock; + pf->ptp.clock = ptp_clock_register(info, dev); + if (IS_ERR(pf->ptp.clock)) { + dev_err(ice_pf_to_dev(pf), "Failed to register PTP clock device"); + return PTR_ERR(pf->ptp.clock); + } return 0; } @@ -2440,7 +2423,21 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) */ enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf) { - return ice_ptp_tx_tstamp(&pf->ptp.port.tx); + switch (pf->ptp.tx_interrupt_mode) { + case ICE_PTP_TX_INTERRUPT_NONE: + /* This device has the clock owner handle timestamps for it */ + return ICE_TX_TSTAMP_WORK_DONE; + case ICE_PTP_TX_INTERRUPT_SELF: + /* This device handles its own timestamps */ + return ice_ptp_tx_tstamp(&pf->ptp.port.tx); + case ICE_PTP_TX_INTERRUPT_ALL: + /* This device handles timestamps for all ports */ + return ice_ptp_tx_tstamp_owner(pf); + default: + WARN_ONCE(1, "Unexpected Tx timestamp interrupt mode %u\n", + pf->ptp.tx_interrupt_mode); + return ICE_TX_TSTAMP_WORK_DONE; + } } static void ice_ptp_periodic_work(struct kthread_work *work) @@ -2474,7 +2471,7 @@ void ice_ptp_reset(struct ice_pf *pf) if (test_bit(ICE_PFR_REQ, pf->state)) goto pfr; - if (!hw->func_caps.ts_func_info.src_tmr_owned) + if (!ice_pf_src_tmr_owned(pf)) goto reset_ts; err = ice_ptp_init_phc(hw); @@ -2550,6 +2547,209 @@ err: } /** + * ice_ptp_aux_dev_to_aux_pf - Get auxiliary PF handle for the auxiliary device + * @aux_dev: auxiliary device to get the auxiliary PF for + */ +static struct ice_pf * +ice_ptp_aux_dev_to_aux_pf(struct auxiliary_device *aux_dev) +{ + struct ice_ptp_port *aux_port; + struct ice_ptp *aux_ptp; + + aux_port = container_of(aux_dev, struct ice_ptp_port, aux_dev); + aux_ptp = container_of(aux_port, struct ice_ptp, port); + + return container_of(aux_ptp, struct ice_pf, ptp); +} + +/** + * ice_ptp_aux_dev_to_owner_pf - Get PF handle for the auxiliary device + * @aux_dev: auxiliary device to get the PF for + */ +static struct ice_pf * +ice_ptp_aux_dev_to_owner_pf(struct auxiliary_device *aux_dev) +{ + struct ice_ptp_port_owner *ports_owner; + struct auxiliary_driver *aux_drv; + struct ice_ptp *owner_ptp; + + if (!aux_dev->dev.driver) + return NULL; + + aux_drv = to_auxiliary_drv(aux_dev->dev.driver); + ports_owner = container_of(aux_drv, struct ice_ptp_port_owner, + aux_driver); + owner_ptp = container_of(ports_owner, struct ice_ptp, ports_owner); + return container_of(owner_ptp, struct ice_pf, ptp); +} + +/** + * ice_ptp_auxbus_probe - Probe auxiliary devices + * @aux_dev: PF's auxiliary device + * @id: Auxiliary device ID + */ +static int ice_ptp_auxbus_probe(struct auxiliary_device *aux_dev, + const struct auxiliary_device_id *id) +{ + struct ice_pf *owner_pf = ice_ptp_aux_dev_to_owner_pf(aux_dev); + struct ice_pf *aux_pf = ice_ptp_aux_dev_to_aux_pf(aux_dev); + + if (WARN_ON(!owner_pf)) + return -ENODEV; + + INIT_LIST_HEAD(&aux_pf->ptp.port.list_member); + mutex_lock(&owner_pf->ptp.ports_owner.lock); + list_add(&aux_pf->ptp.port.list_member, + &owner_pf->ptp.ports_owner.ports); + mutex_unlock(&owner_pf->ptp.ports_owner.lock); + + return 0; +} + +/** + * ice_ptp_auxbus_remove - Remove auxiliary devices from the bus + * @aux_dev: PF's auxiliary device + */ +static void ice_ptp_auxbus_remove(struct auxiliary_device *aux_dev) +{ + struct ice_pf *owner_pf = ice_ptp_aux_dev_to_owner_pf(aux_dev); + struct ice_pf *aux_pf = ice_ptp_aux_dev_to_aux_pf(aux_dev); + + mutex_lock(&owner_pf->ptp.ports_owner.lock); + list_del(&aux_pf->ptp.port.list_member); + mutex_unlock(&owner_pf->ptp.ports_owner.lock); +} + +/** + * ice_ptp_auxbus_shutdown + * @aux_dev: PF's auxiliary device + */ +static void ice_ptp_auxbus_shutdown(struct auxiliary_device *aux_dev) +{ + /* Doing nothing here, but handle to auxbus driver must be satisfied */ +} + +/** + * ice_ptp_auxbus_suspend + * @aux_dev: PF's auxiliary device + * @state: power management state indicator + */ +static int +ice_ptp_auxbus_suspend(struct auxiliary_device *aux_dev, pm_message_t state) +{ + /* Doing nothing here, but handle to auxbus driver must be satisfied */ + return 0; +} + +/** + * ice_ptp_auxbus_resume + * @aux_dev: PF's auxiliary device + */ +static int ice_ptp_auxbus_resume(struct auxiliary_device *aux_dev) +{ + /* Doing nothing here, but handle to auxbus driver must be satisfied */ + return 0; +} + +/** + * ice_ptp_auxbus_create_id_table - Create auxiliary device ID table + * @pf: Board private structure + * @name: auxiliary bus driver name + */ +static struct auxiliary_device_id * +ice_ptp_auxbus_create_id_table(struct ice_pf *pf, const char *name) +{ + struct auxiliary_device_id *ids; + + /* Second id left empty to terminate the array */ + ids = devm_kcalloc(ice_pf_to_dev(pf), 2, + sizeof(struct auxiliary_device_id), GFP_KERNEL); + if (!ids) + return NULL; + + snprintf(ids[0].name, sizeof(ids[0].name), "ice.%s", name); + + return ids; +} + +/** + * ice_ptp_register_auxbus_driver - Register PTP auxiliary bus driver + * @pf: Board private structure + */ +static int ice_ptp_register_auxbus_driver(struct ice_pf *pf) +{ + struct auxiliary_driver *aux_driver; + struct ice_ptp *ptp; + struct device *dev; + char *name; + int err; + + ptp = &pf->ptp; + dev = ice_pf_to_dev(pf); + aux_driver = &ptp->ports_owner.aux_driver; + INIT_LIST_HEAD(&ptp->ports_owner.ports); + mutex_init(&ptp->ports_owner.lock); + name = devm_kasprintf(dev, GFP_KERNEL, "ptp_aux_dev_%u_%u_clk%u", + pf->pdev->bus->number, PCI_SLOT(pf->pdev->devfn), + ice_get_ptp_src_clock_index(&pf->hw)); + + aux_driver->name = name; + aux_driver->shutdown = ice_ptp_auxbus_shutdown; + aux_driver->suspend = ice_ptp_auxbus_suspend; + aux_driver->remove = ice_ptp_auxbus_remove; + aux_driver->resume = ice_ptp_auxbus_resume; + aux_driver->probe = ice_ptp_auxbus_probe; + aux_driver->id_table = ice_ptp_auxbus_create_id_table(pf, name); + if (!aux_driver->id_table) + return -ENOMEM; + + err = auxiliary_driver_register(aux_driver); + if (err) { + devm_kfree(dev, aux_driver->id_table); + dev_err(dev, "Failed registering aux_driver, name <%s>\n", + name); + } + + return err; +} + +/** + * ice_ptp_unregister_auxbus_driver - Unregister PTP auxiliary bus driver + * @pf: Board private structure + */ +static void ice_ptp_unregister_auxbus_driver(struct ice_pf *pf) +{ + struct auxiliary_driver *aux_driver = &pf->ptp.ports_owner.aux_driver; + + auxiliary_driver_unregister(aux_driver); + devm_kfree(ice_pf_to_dev(pf), aux_driver->id_table); + + mutex_destroy(&pf->ptp.ports_owner.lock); +} + +/** + * ice_ptp_clock_index - Get the PTP clock index for this device + * @pf: Board private structure + * + * Returns: the PTP clock index associated with this PF, or -1 if no PTP clock + * is associated. + */ +int ice_ptp_clock_index(struct ice_pf *pf) +{ + struct auxiliary_device *aux_dev; + struct ice_pf *owner_pf; + struct ptp_clock *clock; + + aux_dev = &pf->ptp.port.aux_dev; + owner_pf = ice_ptp_aux_dev_to_owner_pf(aux_dev); + if (!owner_pf) + return -1; + clock = owner_pf->ptp.clock; + + return clock ? ptp_clock_index(clock) : -1; +} + +/** * ice_ptp_prepare_for_reset - Prepare PTP for reset * @pf: Board private structure */ @@ -2561,7 +2761,7 @@ void ice_ptp_prepare_for_reset(struct ice_pf *pf) clear_bit(ICE_FLAG_PTP, pf->flags); /* Disable timestamping for both Tx and Rx */ - ice_ptp_cfg_timestamp(pf, false); + ice_ptp_disable_timestamp_mode(pf); kthread_cancel_delayed_work_sync(&ptp->work); @@ -2639,11 +2839,15 @@ static int ice_ptp_init_owner(struct ice_pf *pf) if (err) goto err_clk; - /* Store the PTP clock index for other PFs */ - ice_set_ptp_clock_index(pf); + err = ice_ptp_register_auxbus_driver(pf); + if (err) { + dev_err(ice_pf_to_dev(pf), "Failed to register PTP auxbus driver"); + goto err_aux; + } return 0; - +err_aux: + ptp_clock_unregister(pf->ptp.clock); err_clk: pf->ptp.clock = NULL; err_exit: @@ -2685,14 +2889,117 @@ static int ice_ptp_init_work(struct ice_pf *pf, struct ice_ptp *ptp) */ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port) { + struct ice_hw *hw = &pf->hw; + mutex_init(&ptp_port->ps_lock); - if (ice_is_e810(&pf->hw)) + switch (hw->phy_model) { + case ICE_PHY_E810: return ice_ptp_init_tx_e810(pf, &ptp_port->tx); + case ICE_PHY_E822: + kthread_init_delayed_work(&ptp_port->ov_work, + ice_ptp_wait_for_offsets); + + return ice_ptp_init_tx_e822(pf, &ptp_port->tx, + ptp_port->port_num); + default: + return -ENODEV; + } +} - kthread_init_delayed_work(&ptp_port->ov_work, - ice_ptp_wait_for_offsets); - return ice_ptp_init_tx_e822(pf, &ptp_port->tx, ptp_port->port_num); +/** + * ice_ptp_release_auxbus_device + * @dev: device that utilizes the auxbus + */ +static void ice_ptp_release_auxbus_device(struct device *dev) +{ + /* Doing nothing here, but handle to auxbux device must be satisfied */ +} + +/** + * ice_ptp_create_auxbus_device - Create PTP auxiliary bus device + * @pf: Board private structure + */ +static int ice_ptp_create_auxbus_device(struct ice_pf *pf) +{ + struct auxiliary_device *aux_dev; + struct ice_ptp *ptp; + struct device *dev; + char *name; + int err; + u32 id; + + ptp = &pf->ptp; + id = ptp->port.port_num; + dev = ice_pf_to_dev(pf); + + aux_dev = &ptp->port.aux_dev; + + name = devm_kasprintf(dev, GFP_KERNEL, "ptp_aux_dev_%u_%u_clk%u", + pf->pdev->bus->number, PCI_SLOT(pf->pdev->devfn), + ice_get_ptp_src_clock_index(&pf->hw)); + + aux_dev->name = name; + aux_dev->id = id; + aux_dev->dev.release = ice_ptp_release_auxbus_device; + aux_dev->dev.parent = dev; + + err = auxiliary_device_init(aux_dev); + if (err) + goto aux_err; + + err = auxiliary_device_add(aux_dev); + if (err) { + auxiliary_device_uninit(aux_dev); + goto aux_err; + } + + return 0; +aux_err: + dev_err(dev, "Failed to create PTP auxiliary bus device <%s>\n", name); + devm_kfree(dev, name); + return err; +} + +/** + * ice_ptp_remove_auxbus_device - Remove PTP auxiliary bus device + * @pf: Board private structure + */ +static void ice_ptp_remove_auxbus_device(struct ice_pf *pf) +{ + struct auxiliary_device *aux_dev = &pf->ptp.port.aux_dev; + + auxiliary_device_delete(aux_dev); + auxiliary_device_uninit(aux_dev); + + memset(aux_dev, 0, sizeof(*aux_dev)); +} + +/** + * ice_ptp_init_tx_interrupt_mode - Initialize device Tx interrupt mode + * @pf: Board private structure + * + * Initialize the Tx timestamp interrupt mode for this device. For most device + * types, each PF processes the interrupt and manages its own timestamps. For + * E822-based devices, only the clock owner processes the timestamps. Other + * PFs disable the interrupt and do not process their own timestamps. + */ +static void ice_ptp_init_tx_interrupt_mode(struct ice_pf *pf) +{ + switch (pf->hw.phy_model) { + case ICE_PHY_E822: + /* E822 based PHY has the clock owner process the interrupt + * for all ports. + */ + if (ice_pf_src_tmr_owned(pf)) + pf->ptp.tx_interrupt_mode = ICE_PTP_TX_INTERRUPT_ALL; + else + pf->ptp.tx_interrupt_mode = ICE_PTP_TX_INTERRUPT_NONE; + break; + default: + /* other PHY types handle their own Tx interrupt */ + pf->ptp.tx_interrupt_mode = ICE_PTP_TX_INTERRUPT_SELF; + } } /** @@ -2713,10 +3020,14 @@ void ice_ptp_init(struct ice_pf *pf) struct ice_hw *hw = &pf->hw; int err; + ice_ptp_init_phy_model(hw); + + ice_ptp_init_tx_interrupt_mode(pf); + /* If this function owns the clock hardware, it must allocate and * configure the PTP clock device to represent it. */ - if (hw->func_caps.ts_func_info.src_tmr_owned) { + if (ice_pf_src_tmr_owned(pf)) { err = ice_ptp_init_owner(pf); if (err) goto err; @@ -2730,11 +3041,18 @@ void ice_ptp_init(struct ice_pf *pf) /* Start the PHY timestamping block */ ice_ptp_reset_phy_timestamping(pf); + /* Configure initial Tx interrupt settings */ + ice_ptp_cfg_tx_interrupt(pf); + set_bit(ICE_FLAG_PTP, pf->flags); err = ice_ptp_init_work(pf, ptp); if (err) goto err; + err = ice_ptp_create_auxbus_device(pf); + if (err) + goto err; + dev_info(ice_pf_to_dev(pf), "PTP init successful\n"); return; @@ -2761,7 +3079,9 @@ void ice_ptp_release(struct ice_pf *pf) return; /* Disable timestamping for both Tx and Rx */ - ice_ptp_cfg_timestamp(pf, false); + ice_ptp_disable_timestamp_mode(pf); + + ice_ptp_remove_auxbus_device(pf); ice_ptp_release_tx_tracker(pf, &pf->ptp.port.tx); @@ -2782,9 +3102,10 @@ void ice_ptp_release(struct ice_pf *pf) /* Disable periodic outputs */ ice_ptp_disable_all_clkout(pf); - ice_clear_ptp_clock_index(pf); ptp_clock_unregister(pf->ptp.clock); pf->ptp.clock = NULL; + ice_ptp_unregister_auxbus_driver(pf); + dev_info(ice_pf_to_dev(pf), "Removed PTP clock\n"); } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index 995a57019ba7..06a330867fc9 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -157,7 +157,9 @@ struct ice_ptp_tx { * ready for PTP functionality. It is used to track the port initialization * and determine when the port's PHY offset is valid. * + * @list_member: list member structure of auxiliary device * @tx: Tx timestamp tracking for this port + * @aux_dev: auxiliary device associated with this port * @ov_work: delayed work task for tracking when PHY offset is valid * @ps_lock: mutex used to protect the overall PTP PHY start procedure * @link_up: indicates whether the link is up @@ -165,7 +167,9 @@ struct ice_ptp_tx { * @port_num: the port number this structure represents */ struct ice_ptp_port { + struct list_head list_member; struct ice_ptp_tx tx; + struct auxiliary_device aux_dev; struct kthread_delayed_work ov_work; struct mutex ps_lock; /* protects overall PTP PHY start procedure */ bool link_up; @@ -173,11 +177,35 @@ struct ice_ptp_port { u8 port_num; }; +enum ice_ptp_tx_interrupt { + ICE_PTP_TX_INTERRUPT_NONE = 0, + ICE_PTP_TX_INTERRUPT_SELF, + ICE_PTP_TX_INTERRUPT_ALL, +}; + +/** + * struct ice_ptp_port_owner - data used to handle the PTP clock owner info + * + * This structure contains data necessary for the PTP clock owner to correctly + * handle the timestamping feature for all attached ports. + * + * @aux_driver: the structure carring the auxiliary driver information + * @ports: list of porst handled by this port owner + * @lock: protect access to ports list + */ +struct ice_ptp_port_owner { + struct auxiliary_driver aux_driver; + struct list_head ports; + struct mutex lock; +}; + #define GLTSYN_TGT_H_IDX_MAX 4 /** * struct ice_ptp - data used for integrating with CONFIG_PTP_1588_CLOCK + * @tx_interrupt_mode: the TX interrupt mode for the PTP clock * @port: data for the PHY port initialization procedure + * @ports_owner: data for the auxiliary driver owner * @work: delayed work function for periodic tasks * @cached_phc_time: a cached copy of the PHC time for timestamp extension * @cached_phc_jiffies: jiffies when cached_phc_time was last updated @@ -197,7 +225,9 @@ struct ice_ptp_port { * @late_cached_phc_updates: number of times cached PHC update is late */ struct ice_ptp { + enum ice_ptp_tx_interrupt tx_interrupt_mode; struct ice_ptp_port port; + struct ice_ptp_port_owner ports_owner; struct kthread_delayed_work work; u64 cached_phc_time; unsigned long cached_phc_jiffies; @@ -258,11 +288,11 @@ struct ice_ptp { #define ETH_GLTSYN_ENA(_i) (0x03000348 + ((_i) * 4)) #if IS_ENABLED(CONFIG_PTP_1588_CLOCK) +int ice_ptp_clock_index(struct ice_pf *pf); struct ice_pf; int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr); int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr); -void ice_ptp_cfg_timestamp(struct ice_pf *pf, bool ena); -int ice_get_ptp_clock_index(struct ice_pf *pf); +void ice_ptp_restore_timestamp_mode(struct ice_pf *pf); void ice_ptp_extts_event(struct ice_pf *pf); s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb); @@ -287,12 +317,7 @@ static inline int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr) return -EOPNOTSUPP; } -static inline void ice_ptp_cfg_timestamp(struct ice_pf *pf, bool ena) { } -static inline int ice_get_ptp_clock_index(struct ice_pf *pf) -{ - return -1; -} - +static inline void ice_ptp_restore_timestamp_mode(struct ice_pf *pf) { } static inline void ice_ptp_extts_event(struct ice_pf *pf) { } static inline s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) @@ -314,5 +339,10 @@ static inline void ice_ptp_release(struct ice_pf *pf) { } static inline void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) { } + +static inline int ice_ptp_clock_index(struct ice_pf *pf) +{ + return -1; +} #endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ #endif /* _ICE_PTP_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index a38614d21ea8..a00b55e14aac 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -7,6 +7,132 @@ #include "ice_ptp_consts.h" #include "ice_cgu_regs.h" +static struct dpll_pin_frequency ice_cgu_pin_freq_common[] = { + DPLL_PIN_FREQUENCY_1PPS, + DPLL_PIN_FREQUENCY_10MHZ, +}; + +static struct dpll_pin_frequency ice_cgu_pin_freq_1_hz[] = { + DPLL_PIN_FREQUENCY_1PPS, +}; + +static struct dpll_pin_frequency ice_cgu_pin_freq_10_mhz[] = { + DPLL_PIN_FREQUENCY_10MHZ, +}; + +static const struct ice_cgu_pin_desc ice_e810t_sfp_cgu_inputs[] = { + { "CVL-SDP22", ZL_REF0P, DPLL_PIN_TYPE_INT_OSCILLATOR, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "CVL-SDP20", ZL_REF0N, DPLL_PIN_TYPE_INT_OSCILLATOR, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "C827_0-RCLKA", ZL_REF1P, DPLL_PIN_TYPE_MUX, 0, }, + { "C827_0-RCLKB", ZL_REF1N, DPLL_PIN_TYPE_MUX, 0, }, + { "SMA1", ZL_REF3P, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "SMA2/U.FL2", ZL_REF3N, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "GNSS-1PPS", ZL_REF4P, DPLL_PIN_TYPE_GNSS, + ARRAY_SIZE(ice_cgu_pin_freq_1_hz), ice_cgu_pin_freq_1_hz }, + { "OCXO", ZL_REF4N, DPLL_PIN_TYPE_INT_OSCILLATOR, 0, }, +}; + +static const struct ice_cgu_pin_desc ice_e810t_qsfp_cgu_inputs[] = { + { "CVL-SDP22", ZL_REF0P, DPLL_PIN_TYPE_INT_OSCILLATOR, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "CVL-SDP20", ZL_REF0N, DPLL_PIN_TYPE_INT_OSCILLATOR, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "C827_0-RCLKA", ZL_REF1P, DPLL_PIN_TYPE_MUX, }, + { "C827_0-RCLKB", ZL_REF1N, DPLL_PIN_TYPE_MUX, }, + { "C827_1-RCLKA", ZL_REF2P, DPLL_PIN_TYPE_MUX, }, + { "C827_1-RCLKB", ZL_REF2N, DPLL_PIN_TYPE_MUX, }, + { "SMA1", ZL_REF3P, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "SMA2/U.FL2", ZL_REF3N, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "GNSS-1PPS", ZL_REF4P, DPLL_PIN_TYPE_GNSS, + ARRAY_SIZE(ice_cgu_pin_freq_1_hz), ice_cgu_pin_freq_1_hz }, + { "OCXO", ZL_REF4N, DPLL_PIN_TYPE_INT_OSCILLATOR, }, +}; + +static const struct ice_cgu_pin_desc ice_e810t_sfp_cgu_outputs[] = { + { "REF-SMA1", ZL_OUT0, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "REF-SMA2/U.FL2", ZL_OUT1, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "PHY-CLK", ZL_OUT2, DPLL_PIN_TYPE_SYNCE_ETH_PORT, }, + { "MAC-CLK", ZL_OUT3, DPLL_PIN_TYPE_SYNCE_ETH_PORT, }, + { "CVL-SDP21", ZL_OUT4, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_1_hz), ice_cgu_pin_freq_1_hz }, + { "CVL-SDP23", ZL_OUT5, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_1_hz), ice_cgu_pin_freq_1_hz }, +}; + +static const struct ice_cgu_pin_desc ice_e810t_qsfp_cgu_outputs[] = { + { "REF-SMA1", ZL_OUT0, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "REF-SMA2/U.FL2", ZL_OUT1, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "PHY-CLK", ZL_OUT2, DPLL_PIN_TYPE_SYNCE_ETH_PORT, 0 }, + { "PHY2-CLK", ZL_OUT3, DPLL_PIN_TYPE_SYNCE_ETH_PORT, 0 }, + { "MAC-CLK", ZL_OUT4, DPLL_PIN_TYPE_SYNCE_ETH_PORT, 0 }, + { "CVL-SDP21", ZL_OUT5, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_1_hz), ice_cgu_pin_freq_1_hz }, + { "CVL-SDP23", ZL_OUT6, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_1_hz), ice_cgu_pin_freq_1_hz }, +}; + +static const struct ice_cgu_pin_desc ice_e823_si_cgu_inputs[] = { + { "NONE", SI_REF0P, 0, 0 }, + { "NONE", SI_REF0N, 0, 0 }, + { "SYNCE0_DP", SI_REF1P, DPLL_PIN_TYPE_MUX, 0 }, + { "SYNCE0_DN", SI_REF1N, DPLL_PIN_TYPE_MUX, 0 }, + { "EXT_CLK_SYNC", SI_REF2P, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "NONE", SI_REF2N, 0, 0 }, + { "EXT_PPS_OUT", SI_REF3, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "INT_PPS_OUT", SI_REF4, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, +}; + +static const struct ice_cgu_pin_desc ice_e823_si_cgu_outputs[] = { + { "1588-TIME_SYNC", SI_OUT0, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "PHY-CLK", SI_OUT1, DPLL_PIN_TYPE_SYNCE_ETH_PORT, 0 }, + { "10MHZ-SMA2", SI_OUT2, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_10_mhz), ice_cgu_pin_freq_10_mhz }, + { "PPS-SMA1", SI_OUT3, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, +}; + +static const struct ice_cgu_pin_desc ice_e823_zl_cgu_inputs[] = { + { "NONE", ZL_REF0P, 0, 0 }, + { "INT_PPS_OUT", ZL_REF0N, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_1_hz), ice_cgu_pin_freq_1_hz }, + { "SYNCE0_DP", ZL_REF1P, DPLL_PIN_TYPE_MUX, 0 }, + { "SYNCE0_DN", ZL_REF1N, DPLL_PIN_TYPE_MUX, 0 }, + { "NONE", ZL_REF2P, 0, 0 }, + { "NONE", ZL_REF2N, 0, 0 }, + { "EXT_CLK_SYNC", ZL_REF3P, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "NONE", ZL_REF3N, 0, 0 }, + { "EXT_PPS_OUT", ZL_REF4P, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_1_hz), ice_cgu_pin_freq_1_hz }, + { "OCXO", ZL_REF4N, DPLL_PIN_TYPE_INT_OSCILLATOR, 0 }, +}; + +static const struct ice_cgu_pin_desc ice_e823_zl_cgu_outputs[] = { + { "PPS-SMA1", ZL_OUT0, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_1_hz), ice_cgu_pin_freq_1_hz }, + { "10MHZ-SMA2", ZL_OUT1, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_10_mhz), ice_cgu_pin_freq_10_mhz }, + { "PHY-CLK", ZL_OUT2, DPLL_PIN_TYPE_SYNCE_ETH_PORT, 0 }, + { "1588-TIME_REF", ZL_OUT3, DPLL_PIN_TYPE_SYNCE_ETH_PORT, 0 }, + { "CPK-TIME_SYNC", ZL_OUT4, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "NONE", ZL_OUT5, 0, 0 }, +}; + /* Low level functions for interacting with and managing the device clock used * for the Precision Time Protocol. * @@ -107,7 +233,7 @@ static u64 ice_ptp_read_src_incval(struct ice_hw *hw) * * Prepare the source timer for an upcoming timer sync command. */ -static void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) +void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) { u32 cmd_val; u8 tmr_idx; @@ -116,21 +242,23 @@ static void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) cmd_val = tmr_idx << SEL_CPK_SRC; switch (cmd) { - case INIT_TIME: + case ICE_PTP_INIT_TIME: cmd_val |= GLTSYN_CMD_INIT_TIME; break; - case INIT_INCVAL: + case ICE_PTP_INIT_INCVAL: cmd_val |= GLTSYN_CMD_INIT_INCVAL; break; - case ADJ_TIME: + case ICE_PTP_ADJ_TIME: cmd_val |= GLTSYN_CMD_ADJ_TIME; break; - case ADJ_TIME_AT_TIME: + case ICE_PTP_ADJ_TIME_AT_TIME: cmd_val |= GLTSYN_CMD_ADJ_INIT_TIME; break; - case READ_TIME: + case ICE_PTP_READ_TIME: cmd_val |= GLTSYN_CMD_READ_TIME; break; + case ICE_PTP_NOP: + break; } wr32(hw, GLTSYN_CMD, cmd_val); @@ -166,9 +294,9 @@ ice_fill_phy_msg_e822(struct ice_sbq_msg_input *msg, u8 port, u16 offset) { int phy_port, phy, quadtype; - phy_port = port % ICE_PORTS_PER_PHY; - phy = port / ICE_PORTS_PER_PHY; - quadtype = (port / ICE_PORTS_PER_QUAD) % ICE_NUM_QUAD_TYPE; + phy_port = port % ICE_PORTS_PER_PHY_E822; + phy = port / ICE_PORTS_PER_PHY_E822; + quadtype = (port / ICE_PORTS_PER_QUAD) % ICE_QUADS_PER_PHY_E822; if (quadtype == 0) { msg->msg_addr_low = P_Q0_L(P_0_BASE + offset, phy_port); @@ -293,7 +421,7 @@ static bool ice_is_40b_phy_reg_e822(u16 low_addr, u16 *high_addr) * * Read a PHY register for the given port over the device sideband queue. */ -int +static int ice_read_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 *val) { struct ice_sbq_msg_input msg = {0}; @@ -370,7 +498,7 @@ ice_read_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 *val) * * Write a PHY register for the given port over the device sideband queue. */ -int +static int ice_write_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 val) { struct ice_sbq_msg_input msg = {0}; @@ -493,20 +621,25 @@ ice_write_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 val) * Fill a message buffer for accessing a register in a quad shared between * multiple PHYs. */ -static void +static int ice_fill_quad_msg_e822(struct ice_sbq_msg_input *msg, u8 quad, u16 offset) { u32 addr; + if (quad >= ICE_MAX_QUAD) + return -EINVAL; + msg->dest_dev = rmn_0; - if ((quad % ICE_NUM_QUAD_TYPE) == 0) + if ((quad % ICE_QUADS_PER_PHY_E822) == 0) addr = Q_0_BASE + offset; else addr = Q_1_BASE + offset; msg->msg_addr_low = lower_16_bits(addr); msg->msg_addr_high = upper_16_bits(addr); + + return 0; } /** @@ -525,10 +658,10 @@ ice_read_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 *val) struct ice_sbq_msg_input msg = {0}; int err; - if (quad >= ICE_MAX_QUAD) - return -EINVAL; + err = ice_fill_quad_msg_e822(&msg, quad, offset); + if (err) + return err; - ice_fill_quad_msg_e822(&msg, quad, offset); msg.opcode = ice_sbq_msg_rd; err = ice_sbq_rw_reg(hw, &msg); @@ -559,10 +692,10 @@ ice_write_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 val) struct ice_sbq_msg_input msg = {0}; int err; - if (quad >= ICE_MAX_QUAD) - return -EINVAL; + err = ice_fill_quad_msg_e822(&msg, quad, offset); + if (err) + return err; - ice_fill_quad_msg_e822(&msg, quad, offset); msg.opcode = ice_sbq_msg_wr; msg.data = val; @@ -626,29 +759,32 @@ ice_read_phy_tstamp_e822(struct ice_hw *hw, u8 quad, u8 idx, u64 *tstamp) * @quad: the quad to read from * @idx: the timestamp index to reset * - * Clear a timestamp, resetting its valid bit, from the PHY quad block that is - * shared between the internal PHYs on the E822 devices. + * Read the timestamp out of the quad to clear its timestamp status bit from + * the PHY quad block that is shared between the internal PHYs of the E822 + * devices. + * + * Note that unlike E810, software cannot directly write to the quad memory + * bank registers. E822 relies on the ice_get_phy_tx_tstamp_ready() function + * to determine which timestamps are valid. Reading a timestamp auto-clears + * the valid bit. + * + * To directly clear the contents of the timestamp block entirely, discarding + * all timestamp data at once, software should instead use + * ice_ptp_reset_ts_memory_quad_e822(). + * + * This function should only be called on an idx whose bit is set according to + * ice_get_phy_tx_tstamp_ready(). */ static int ice_clear_phy_tstamp_e822(struct ice_hw *hw, u8 quad, u8 idx) { - u16 lo_addr, hi_addr; + u64 unused_tstamp; int err; - lo_addr = (u16)TS_L(Q_REG_TX_MEMORY_BANK_START, idx); - hi_addr = (u16)TS_H(Q_REG_TX_MEMORY_BANK_START, idx); - - err = ice_write_quad_reg_e822(hw, quad, lo_addr, 0); + err = ice_read_phy_tstamp_e822(hw, quad, idx, &unused_tstamp); if (err) { - ice_debug(hw, ICE_DBG_PTP, "Failed to clear low PTP timestamp register, err %d\n", - err); - return err; - } - - err = ice_write_quad_reg_e822(hw, quad, hi_addr, 0); - if (err) { - ice_debug(hw, ICE_DBG_PTP, "Failed to clear high PTP timestamp register, err %d\n", - err); + ice_debug(hw, ICE_DBG_PTP, "Failed to read the timestamp register for quad %u, idx %u, err %d\n", + quad, idx, err); return err; } @@ -1023,7 +1159,7 @@ static int ice_ptp_init_phc_e822(struct ice_hw *hw) * @time: Time to initialize the PHY port clocks to * * Program the PHY port registers with a new initial time value. The port - * clock will be initialized once the driver issues an INIT_TIME sync + * clock will be initialized once the driver issues an ICE_PTP_INIT_TIME sync * command. The time value is the upper 32 bits of the PHY timer, usually in * units of nominal nanoseconds. */ @@ -1072,14 +1208,14 @@ exit_err: * * Program the port for an atomic adjustment by writing the Tx and Rx timer * registers. The atomic adjustment won't be completed until the driver issues - * an ADJ_TIME command. + * an ICE_PTP_ADJ_TIME command. * * Note that time is not in units of nanoseconds. It is in clock time * including the lower sub-nanosecond portion of the port timer. * * Negative adjustments are supported using 2s complement arithmetic. */ -int +static int ice_ptp_prep_port_adj_e822(struct ice_hw *hw, u8 port, s64 time) { u32 l_time, u_time; @@ -1125,7 +1261,7 @@ exit_err: * * Prepare the PHY ports for an atomic time adjustment by programming the PHY * Tx and Rx port registers. The actual adjustment is completed by issuing an - * ADJ_TIME or ADJ_TIME_AT_TIME sync command. + * ICE_PTP_ADJ_TIME or ICE_PTP_ADJ_TIME_AT_TIME sync command. */ static int ice_ptp_prep_phy_adj_e822(struct ice_hw *hw, s32 adj) @@ -1160,7 +1296,7 @@ ice_ptp_prep_phy_adj_e822(struct ice_hw *hw, s32 adj) * * Prepare each of the PHY ports for a new increment value by programming the * port's TIMETUS registers. The new increment value will be updated after - * issuing an INIT_INCVAL command. + * issuing an ICE_PTP_INIT_INCVAL command. */ static int ice_ptp_prep_phy_incval_e822(struct ice_hw *hw, u64 incval) @@ -1226,18 +1362,18 @@ ice_ptp_read_port_capture(struct ice_hw *hw, u8 port, u64 *tx_ts, u64 *rx_ts) } /** - * ice_ptp_one_port_cmd - Prepare a single PHY port for a timer command + * ice_ptp_write_port_cmd_e822 - Prepare a single PHY port for a timer command * @hw: pointer to HW struct * @port: Port to which cmd has to be sent * @cmd: Command to be sent to the port * * Prepare the requested port for an upcoming timer sync command. * - * Note there is no equivalent of this operation on E810, as that device - * always handles all external PHYs internally. + * Do not use this function directly. If you want to configure exactly one + * port, use ice_ptp_one_port_cmd() instead. */ static int -ice_ptp_one_port_cmd(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd) +ice_ptp_write_port_cmd_e822(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd) { u32 cmd_val, val; u8 tmr_idx; @@ -1246,21 +1382,23 @@ ice_ptp_one_port_cmd(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd) tmr_idx = ice_get_ptp_src_clock_index(hw); cmd_val = tmr_idx << SEL_PHY_SRC; switch (cmd) { - case INIT_TIME: + case ICE_PTP_INIT_TIME: cmd_val |= PHY_CMD_INIT_TIME; break; - case INIT_INCVAL: + case ICE_PTP_INIT_INCVAL: cmd_val |= PHY_CMD_INIT_INCVAL; break; - case ADJ_TIME: + case ICE_PTP_ADJ_TIME: cmd_val |= PHY_CMD_ADJ_TIME; break; - case READ_TIME: + case ICE_PTP_READ_TIME: cmd_val |= PHY_CMD_READ_TIME; break; - case ADJ_TIME_AT_TIME: + case ICE_PTP_ADJ_TIME_AT_TIME: cmd_val |= PHY_CMD_ADJ_TIME_AT_TIME; break; + case ICE_PTP_NOP: + break; } /* Tx case */ @@ -1307,6 +1445,39 @@ ice_ptp_one_port_cmd(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd) } /** + * ice_ptp_one_port_cmd - Prepare one port for a timer command + * @hw: pointer to the HW struct + * @configured_port: the port to configure with configured_cmd + * @configured_cmd: timer command to prepare on the configured_port + * + * Prepare the configured_port for the configured_cmd, and prepare all other + * ports for ICE_PTP_NOP. This causes the configured_port to execute the + * desired command while all other ports perform no operation. + */ +static int +ice_ptp_one_port_cmd(struct ice_hw *hw, u8 configured_port, + enum ice_ptp_tmr_cmd configured_cmd) +{ + u8 port; + + for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) { + enum ice_ptp_tmr_cmd cmd; + int err; + + if (port == configured_port) + cmd = configured_cmd; + else + cmd = ICE_PTP_NOP; + + err = ice_ptp_write_port_cmd_e822(hw, port, cmd); + if (err) + return err; + } + + return 0; +} + +/** * ice_ptp_port_cmd_e822 - Prepare all ports for a timer command * @hw: pointer to the HW struct * @cmd: timer command to prepare @@ -1322,7 +1493,7 @@ ice_ptp_port_cmd_e822(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) { int err; - err = ice_ptp_one_port_cmd(hw, port, cmd); + err = ice_ptp_write_port_cmd_e822(hw, port, cmd); if (err) return err; } @@ -2159,8 +2330,8 @@ int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port) * @phy_time: on return, the 64bit PHY timer value * @phc_time: on return, the lower 64bits of PHC time * - * Issue a READ_TIME timer command to simultaneously capture the PHY and PHC - * timer values. + * Issue a ICE_PTP_READ_TIME timer command to simultaneously capture the PHY + * and PHC timer values. */ static int ice_read_phy_and_phc_time_e822(struct ice_hw *hw, u8 port, u64 *phy_time, @@ -2173,15 +2344,15 @@ ice_read_phy_and_phc_time_e822(struct ice_hw *hw, u8 port, u64 *phy_time, tmr_idx = ice_get_ptp_src_clock_index(hw); - /* Prepare the PHC timer for a READ_TIME capture command */ - ice_ptp_src_cmd(hw, READ_TIME); + /* Prepare the PHC timer for a ICE_PTP_READ_TIME capture command */ + ice_ptp_src_cmd(hw, ICE_PTP_READ_TIME); - /* Prepare the PHY timer for a READ_TIME capture command */ - err = ice_ptp_one_port_cmd(hw, port, READ_TIME); + /* Prepare the PHY timer for a ICE_PTP_READ_TIME capture command */ + err = ice_ptp_one_port_cmd(hw, port, ICE_PTP_READ_TIME); if (err) return err; - /* Issue the sync to start the READ_TIME capture */ + /* Issue the sync to start the ICE_PTP_READ_TIME capture */ ice_ptp_exec_tmr_cmd(hw); /* Read the captured PHC time from the shadow time registers */ @@ -2215,10 +2386,11 @@ ice_read_phy_and_phc_time_e822(struct ice_hw *hw, u8 port, u64 *phy_time, * @port: the PHY port to synchronize * * Perform an adjustment to ensure that the PHY and PHC timers are in sync. - * This is done by issuing a READ_TIME command which triggers a simultaneous - * read of the PHY timer and PHC timer. Then we use the difference to - * calculate an appropriate 2s complement addition to add to the PHY timer in - * order to ensure it reads the same value as the primary PHC timer. + * This is done by issuing a ICE_PTP_READ_TIME command which triggers a + * simultaneous read of the PHY timer and PHC timer. Then we use the + * difference to calculate an appropriate 2s complement addition to add + * to the PHY timer in order to ensure it reads the same value as the + * primary PHC timer. */ static int ice_sync_phy_timer_e822(struct ice_hw *hw, u8 port) { @@ -2248,10 +2420,13 @@ static int ice_sync_phy_timer_e822(struct ice_hw *hw, u8 port) if (err) goto err_unlock; - err = ice_ptp_one_port_cmd(hw, port, ADJ_TIME); + err = ice_ptp_one_port_cmd(hw, port, ICE_PTP_ADJ_TIME); if (err) goto err_unlock; + /* Do not perform any action on the main timer */ + ice_ptp_src_cmd(hw, ICE_PTP_NOP); + /* Issue the sync to activate the time adjustment */ ice_ptp_exec_tmr_cmd(hw); @@ -2368,10 +2543,13 @@ int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port) if (err) return err; - err = ice_ptp_one_port_cmd(hw, port, INIT_INCVAL); + err = ice_ptp_one_port_cmd(hw, port, ICE_PTP_INIT_INCVAL); if (err) return err; + /* Do not perform any action on the main timer */ + ice_ptp_src_cmd(hw, ICE_PTP_NOP); + ice_ptp_exec_tmr_cmd(hw); err = ice_read_phy_reg_e822(hw, port, P_REG_PS, &val); @@ -2393,7 +2571,7 @@ int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port) if (err) return err; - err = ice_ptp_one_port_cmd(hw, port, INIT_INCVAL); + err = ice_ptp_one_port_cmd(hw, port, ICE_PTP_INIT_INCVAL); if (err) return err; @@ -2642,28 +2820,39 @@ ice_read_phy_tstamp_e810(struct ice_hw *hw, u8 lport, u8 idx, u64 *tstamp) * @lport: the lport to read from * @idx: the timestamp index to reset * - * Clear a timestamp, resetting its valid bit, from the timestamp block of the - * external PHY on the E810 device. + * Read the timestamp and then forcibly overwrite its value to clear the valid + * bit from the timestamp block of the external PHY on the E810 device. + * + * This function should only be called on an idx whose bit is set according to + * ice_get_phy_tx_tstamp_ready(). */ static int ice_clear_phy_tstamp_e810(struct ice_hw *hw, u8 lport, u8 idx) { u32 lo_addr, hi_addr; + u64 unused_tstamp; int err; + err = ice_read_phy_tstamp_e810(hw, lport, idx, &unused_tstamp); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read the timestamp register for lport %u, idx %u, err %d\n", + lport, idx, err); + return err; + } + lo_addr = TS_EXT(LOW_TX_MEMORY_BANK_START, lport, idx); hi_addr = TS_EXT(HIGH_TX_MEMORY_BANK_START, lport, idx); err = ice_write_phy_reg_e810(hw, lo_addr, 0); if (err) { - ice_debug(hw, ICE_DBG_PTP, "Failed to clear low PTP timestamp register, err %d\n", - err); + ice_debug(hw, ICE_DBG_PTP, "Failed to clear low PTP timestamp register for lport %u, idx %u, err %d\n", + lport, idx, err); return err; } err = ice_write_phy_reg_e810(hw, hi_addr, 0); if (err) { - ice_debug(hw, ICE_DBG_PTP, "Failed to clear high PTP timestamp register, err %d\n", - err); + ice_debug(hw, ICE_DBG_PTP, "Failed to clear high PTP timestamp register for lport %u, idx %u, err %d\n", + lport, idx, err); return err; } @@ -2714,7 +2903,7 @@ static int ice_ptp_init_phc_e810(struct ice_hw *hw) * * Program the PHY port ETH_GLTSYN_SHTIME registers in preparation setting the * initial clock time. The time will not actually be programmed until the - * driver issues an INIT_TIME command. + * driver issues an ICE_PTP_INIT_TIME command. * * The time value is the upper 32 bits of the PHY timer, usually in units of * nominal nanoseconds. @@ -2749,7 +2938,7 @@ static int ice_ptp_prep_phy_time_e810(struct ice_hw *hw, u32 time) * * Prepare the PHY port for an atomic adjustment by programming the PHY * ETH_GLTSYN_SHADJ_L and ETH_GLTSYN_SHADJ_H registers. The actual adjustment - * is completed by issuing an ADJ_TIME sync command. + * is completed by issuing an ICE_PTP_ADJ_TIME sync command. * * The adjustment value only contains the portion used for the upper 32bits of * the PHY timer, usually in units of nominal nanoseconds. Negative @@ -2789,7 +2978,7 @@ static int ice_ptp_prep_phy_adj_e810(struct ice_hw *hw, s32 adj) * * Prepare the PHY port for a new increment value by programming the PHY * ETH_GLTSYN_SHADJ_L and ETH_GLTSYN_SHADJ_H registers. The actual change is - * completed by issuing an INIT_INCVAL command. + * completed by issuing an ICE_PTP_INIT_INCVAL command. */ static int ice_ptp_prep_phy_incval_e810(struct ice_hw *hw, u64 incval) { @@ -2832,21 +3021,23 @@ static int ice_ptp_port_cmd_e810(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) int err; switch (cmd) { - case INIT_TIME: + case ICE_PTP_INIT_TIME: cmd_val = GLTSYN_CMD_INIT_TIME; break; - case INIT_INCVAL: + case ICE_PTP_INIT_INCVAL: cmd_val = GLTSYN_CMD_INIT_INCVAL; break; - case ADJ_TIME: + case ICE_PTP_ADJ_TIME: cmd_val = GLTSYN_CMD_ADJ_TIME; break; - case READ_TIME: + case ICE_PTP_READ_TIME: cmd_val = GLTSYN_CMD_READ_TIME; break; - case ADJ_TIME_AT_TIME: + case ICE_PTP_ADJ_TIME_AT_TIME: cmd_val = GLTSYN_CMD_ADJ_INIT_TIME; break; + case ICE_PTP_NOP: + return 0; } /* Read, modify, write */ @@ -2869,6 +3060,185 @@ static int ice_ptp_port_cmd_e810(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) return 0; } +/** + * ice_get_phy_tx_tstamp_ready_e810 - Read Tx memory status register + * @hw: pointer to the HW struct + * @port: the PHY port to read + * @tstamp_ready: contents of the Tx memory status register + * + * E810 devices do not use a Tx memory status register. Instead simply + * indicate that all timestamps are currently ready. + */ +static int +ice_get_phy_tx_tstamp_ready_e810(struct ice_hw *hw, u8 port, u64 *tstamp_ready) +{ + *tstamp_ready = 0xFFFFFFFFFFFFFFFF; + return 0; +} + +/* E810T SMA functions + * + * The following functions operate specifically on E810T hardware and are used + * to access the extended GPIOs available. + */ + +/** + * ice_get_pca9575_handle + * @hw: pointer to the hw struct + * @pca9575_handle: GPIO controller's handle + * + * Find and return the GPIO controller's handle in the netlist. + * When found - the value will be cached in the hw structure and following calls + * will return cached value + */ +static int +ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle) +{ + struct ice_aqc_get_link_topo *cmd; + struct ice_aq_desc desc; + int status; + u8 idx; + + /* If handle was read previously return cached value */ + if (hw->io_expander_handle) { + *pca9575_handle = hw->io_expander_handle; + return 0; + } + + /* If handle was not detected read it from the netlist */ + cmd = &desc.params.get_link_topo; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo); + + /* Set node type to GPIO controller */ + cmd->addr.topo_params.node_type_ctx = + (ICE_AQC_LINK_TOPO_NODE_TYPE_M & + ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL); + +#define SW_PCA9575_SFP_TOPO_IDX 2 +#define SW_PCA9575_QSFP_TOPO_IDX 1 + + /* Check if the SW IO expander controlling SMA exists in the netlist. */ + if (hw->device_id == ICE_DEV_ID_E810C_SFP) + idx = SW_PCA9575_SFP_TOPO_IDX; + else if (hw->device_id == ICE_DEV_ID_E810C_QSFP) + idx = SW_PCA9575_QSFP_TOPO_IDX; + else + return -EOPNOTSUPP; + + cmd->addr.topo_params.index = idx; + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (status) + return -EOPNOTSUPP; + + /* Verify if we found the right IO expander type */ + if (desc.params.get_link_topo.node_part_num != + ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575) + return -EOPNOTSUPP; + + /* If present save the handle and return it */ + hw->io_expander_handle = + le16_to_cpu(desc.params.get_link_topo.addr.handle); + *pca9575_handle = hw->io_expander_handle; + + return 0; +} + +/** + * ice_read_sma_ctrl_e810t + * @hw: pointer to the hw struct + * @data: pointer to data to be read from the GPIO controller + * + * Read the SMA controller state. It is connected to pins 3-7 of Port 1 of the + * PCA9575 expander, so only bits 3-7 in data are valid. + */ +int ice_read_sma_ctrl_e810t(struct ice_hw *hw, u8 *data) +{ + int status; + u16 handle; + u8 i; + + status = ice_get_pca9575_handle(hw, &handle); + if (status) + return status; + + *data = 0; + + for (i = ICE_SMA_MIN_BIT_E810T; i <= ICE_SMA_MAX_BIT_E810T; i++) { + bool pin; + + status = ice_aq_get_gpio(hw, handle, i + ICE_PCA9575_P1_OFFSET, + &pin, NULL); + if (status) + break; + *data |= (u8)(!pin) << i; + } + + return status; +} + +/** + * ice_write_sma_ctrl_e810t + * @hw: pointer to the hw struct + * @data: data to be written to the GPIO controller + * + * Write the data to the SMA controller. It is connected to pins 3-7 of Port 1 + * of the PCA9575 expander, so only bits 3-7 in data are valid. + */ +int ice_write_sma_ctrl_e810t(struct ice_hw *hw, u8 data) +{ + int status; + u16 handle; + u8 i; + + status = ice_get_pca9575_handle(hw, &handle); + if (status) + return status; + + for (i = ICE_SMA_MIN_BIT_E810T; i <= ICE_SMA_MAX_BIT_E810T; i++) { + bool pin; + + pin = !(data & (1 << i)); + status = ice_aq_set_gpio(hw, handle, i + ICE_PCA9575_P1_OFFSET, + pin, NULL); + if (status) + break; + } + + return status; +} + +/** + * ice_read_pca9575_reg_e810t + * @hw: pointer to the hw struct + * @offset: GPIO controller register offset + * @data: pointer to data to be read from the GPIO controller + * + * Read the register from the GPIO controller + */ +int ice_read_pca9575_reg_e810t(struct ice_hw *hw, u8 offset, u8 *data) +{ + struct ice_aqc_link_topo_addr link_topo; + __le16 addr; + u16 handle; + int err; + + memset(&link_topo, 0, sizeof(link_topo)); + + err = ice_get_pca9575_handle(hw, &handle); + if (err) + return err; + + link_topo.handle = cpu_to_le16(handle); + link_topo.topo_params.node_type_ctx = + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, + ICE_AQC_LINK_TOPO_NODE_CTX_PROVIDED); + + addr = cpu_to_le16((u16)offset); + + return ice_aq_read_i2c(hw, link_topo, 0, addr, 1, data, NULL); +} + /* Device agnostic functions * * The following functions implement shared behavior common to both E822 and @@ -2926,6 +3296,21 @@ void ice_ptp_unlock(struct ice_hw *hw) } /** + * ice_ptp_init_phy_model - Initialize hw->phy_model based on device type + * @hw: pointer to the HW structure + * + * Determine the PHY model for the device, and initialize hw->phy_model + * for use by other functions. + */ +void ice_ptp_init_phy_model(struct ice_hw *hw) +{ + if (ice_is_e810(hw)) + hw->phy_model = ICE_PHY_E810; + else + hw->phy_model = ICE_PHY_E822; +} + +/** * ice_ptp_tmr_cmd - Prepare and trigger a timer sync command * @hw: pointer to HW struct * @cmd: the command to issue @@ -2943,10 +3328,17 @@ static int ice_ptp_tmr_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) ice_ptp_src_cmd(hw, cmd); /* Next, prepare the ports */ - if (ice_is_e810(hw)) + switch (hw->phy_model) { + case ICE_PHY_E810: err = ice_ptp_port_cmd_e810(hw, cmd); - else + break; + case ICE_PHY_E822: err = ice_ptp_port_cmd_e822(hw, cmd); + break; + default: + err = -EOPNOTSUPP; + } + if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to prepare PHY ports for timer command %u, err %d\n", cmd, err); @@ -2988,14 +3380,21 @@ int ice_ptp_init_time(struct ice_hw *hw, u64 time) /* PHY timers */ /* Fill Rx and Tx ports and send msg to PHY */ - if (ice_is_e810(hw)) + switch (hw->phy_model) { + case ICE_PHY_E810: err = ice_ptp_prep_phy_time_e810(hw, time & 0xFFFFFFFF); - else + break; + case ICE_PHY_E822: err = ice_ptp_prep_phy_time_e822(hw, time & 0xFFFFFFFF); + break; + default: + err = -EOPNOTSUPP; + } + if (err) return err; - return ice_ptp_tmr_cmd(hw, INIT_TIME); + return ice_ptp_tmr_cmd(hw, ICE_PTP_INIT_TIME); } /** @@ -3008,8 +3407,8 @@ int ice_ptp_init_time(struct ice_hw *hw, u64 time) * * 1) Write the increment value to the source timer shadow registers * 2) Write the increment value to the PHY timer shadow registers - * 3) Issue an INIT_INCVAL timer command to synchronously switch both the - * source and port timers to the new increment value at the next clock + * 3) Issue an ICE_PTP_INIT_INCVAL timer command to synchronously switch both + * the source and port timers to the new increment value at the next clock * cycle. */ int ice_ptp_write_incval(struct ice_hw *hw, u64 incval) @@ -3023,14 +3422,21 @@ int ice_ptp_write_incval(struct ice_hw *hw, u64 incval) wr32(hw, GLTSYN_SHADJ_L(tmr_idx), lower_32_bits(incval)); wr32(hw, GLTSYN_SHADJ_H(tmr_idx), upper_32_bits(incval)); - if (ice_is_e810(hw)) + switch (hw->phy_model) { + case ICE_PHY_E810: err = ice_ptp_prep_phy_incval_e810(hw, incval); - else + break; + case ICE_PHY_E822: err = ice_ptp_prep_phy_incval_e822(hw, incval); + break; + default: + err = -EOPNOTSUPP; + } + if (err) return err; - return ice_ptp_tmr_cmd(hw, INIT_INCVAL); + return ice_ptp_tmr_cmd(hw, ICE_PTP_INIT_INCVAL); } /** @@ -3064,8 +3470,8 @@ int ice_ptp_write_incval_locked(struct ice_hw *hw, u64 incval) * * 1) Write the adjustment to the source timer shadow registers * 2) Write the adjustment to the PHY timer shadow registers - * 3) Issue an ADJ_TIME timer command to synchronously apply the adjustment to - * both the source and port timers at the next clock cycle. + * 3) Issue an ICE_PTP_ADJ_TIME timer command to synchronously apply the + * adjustment to both the source and port timers at the next clock cycle. */ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj) { @@ -3075,21 +3481,28 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj) tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; /* Write the desired clock adjustment into the GLTSYN_SHADJ register. - * For an ADJ_TIME command, this set of registers represents the value - * to add to the clock time. It supports subtraction by interpreting - * the value as a 2's complement integer. + * For an ICE_PTP_ADJ_TIME command, this set of registers represents + * the value to add to the clock time. It supports subtraction by + * interpreting the value as a 2's complement integer. */ wr32(hw, GLTSYN_SHADJ_L(tmr_idx), 0); wr32(hw, GLTSYN_SHADJ_H(tmr_idx), adj); - if (ice_is_e810(hw)) + switch (hw->phy_model) { + case ICE_PHY_E810: err = ice_ptp_prep_phy_adj_e810(hw, adj); - else + break; + case ICE_PHY_E822: err = ice_ptp_prep_phy_adj_e822(hw, adj); + break; + default: + err = -EOPNOTSUPP; + } + if (err) return err; - return ice_ptp_tmr_cmd(hw, ADJ_TIME); + return ice_ptp_tmr_cmd(hw, ICE_PTP_ADJ_TIME); } /** @@ -3105,10 +3518,14 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj) */ int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp) { - if (ice_is_e810(hw)) + switch (hw->phy_model) { + case ICE_PHY_E810: return ice_read_phy_tstamp_e810(hw, block, idx, tstamp); - else + case ICE_PHY_E822: return ice_read_phy_tstamp_e822(hw, block, idx, tstamp); + default: + return -EOPNOTSUPP; + } } /** @@ -3117,267 +3534,484 @@ int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp) * @block: the block to read from * @idx: the timestamp index to reset * - * Clear a timestamp, resetting its valid bit, from the timestamp block. For - * E822 devices, the block is the quad to clear from. For E810 devices, the - * block is the logical port to clear from. + * Clear a timestamp from the timestamp block, discarding its value without + * returning it. This resets the memory status bit for the timestamp index + * allowing it to be reused for another timestamp in the future. + * + * For E822 devices, the block number is the PHY quad to clear from. For E810 + * devices, the block number is the logical port to clear from. + * + * This function must only be called on a timestamp index whose valid bit is + * set according to ice_get_phy_tx_tstamp_ready(). */ int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx) { - if (ice_is_e810(hw)) + switch (hw->phy_model) { + case ICE_PHY_E810: return ice_clear_phy_tstamp_e810(hw, block, idx); - else + case ICE_PHY_E822: return ice_clear_phy_tstamp_e822(hw, block, idx); + default: + return -EOPNOTSUPP; + } } /** - * ice_get_phy_tx_tstamp_ready_e810 - Read Tx memory status register - * @hw: pointer to the HW struct - * @port: the PHY port to read - * @tstamp_ready: contents of the Tx memory status register - * - * E810 devices do not use a Tx memory status register. Instead simply - * indicate that all timestamps are currently ready. - */ -static int -ice_get_phy_tx_tstamp_ready_e810(struct ice_hw *hw, u8 port, u64 *tstamp_ready) -{ - *tstamp_ready = 0xFFFFFFFFFFFFFFFF; - return 0; -} - -/* E810T SMA functions - * - * The following functions operate specifically on E810T hardware and are used - * to access the extended GPIOs available. - */ - -/** - * ice_get_pca9575_handle + * ice_get_pf_c827_idx - find and return the C827 index for the current pf * @hw: pointer to the hw struct - * @pca9575_handle: GPIO controller's handle - * - * Find and return the GPIO controller's handle in the netlist. - * When found - the value will be cached in the hw structure and following calls - * will return cached value + * @idx: index of the found C827 PHY + * Return: + * * 0 - success + * * negative - failure */ -static int -ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle) +static int ice_get_pf_c827_idx(struct ice_hw *hw, u8 *idx) { - struct ice_aqc_get_link_topo *cmd; - struct ice_aq_desc desc; + struct ice_aqc_get_link_topo cmd; + u8 node_part_number; + u16 node_handle; int status; - u8 idx; + u8 ctx; - /* If handle was read previously return cached value */ - if (hw->io_expander_handle) { - *pca9575_handle = hw->io_expander_handle; + if (hw->mac_type != ICE_MAC_E810) + return -ENODEV; + + if (hw->device_id != ICE_DEV_ID_E810C_QSFP) { + *idx = C827_0; return 0; } - /* If handle was not detected read it from the netlist */ - cmd = &desc.params.get_link_topo; - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo); + memset(&cmd, 0, sizeof(cmd)); - /* Set node type to GPIO controller */ - cmd->addr.topo_params.node_type_ctx = - (ICE_AQC_LINK_TOPO_NODE_TYPE_M & - ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL); + ctx = ICE_AQC_LINK_TOPO_NODE_TYPE_PHY << ICE_AQC_LINK_TOPO_NODE_TYPE_S; + ctx |= ICE_AQC_LINK_TOPO_NODE_CTX_PORT << ICE_AQC_LINK_TOPO_NODE_CTX_S; + cmd.addr.topo_params.node_type_ctx = ctx; -#define SW_PCA9575_SFP_TOPO_IDX 2 -#define SW_PCA9575_QSFP_TOPO_IDX 1 + status = ice_aq_get_netlist_node(hw, &cmd, &node_part_number, + &node_handle); + if (status || node_part_number != ICE_AQC_GET_LINK_TOPO_NODE_NR_C827) + return -ENOENT; - /* Check if the SW IO expander controlling SMA exists in the netlist. */ - if (hw->device_id == ICE_DEV_ID_E810C_SFP) - idx = SW_PCA9575_SFP_TOPO_IDX; - else if (hw->device_id == ICE_DEV_ID_E810C_QSFP) - idx = SW_PCA9575_QSFP_TOPO_IDX; + if (node_handle == E810C_QSFP_C827_0_HANDLE) + *idx = C827_0; + else if (node_handle == E810C_QSFP_C827_1_HANDLE) + *idx = C827_1; else - return -EOPNOTSUPP; + return -EIO; - cmd->addr.topo_params.index = idx; + return 0; +} - status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); - if (status) - return -EOPNOTSUPP; +/** + * ice_ptp_reset_ts_memory - Reset timestamp memory for all blocks + * @hw: pointer to the HW struct + */ +void ice_ptp_reset_ts_memory(struct ice_hw *hw) +{ + switch (hw->phy_model) { + case ICE_PHY_E822: + ice_ptp_reset_ts_memory_e822(hw); + break; + case ICE_PHY_E810: + default: + return; + } +} - /* Verify if we found the right IO expander type */ - if (desc.params.get_link_topo.node_part_num != - ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575) - return -EOPNOTSUPP; +/** + * ice_ptp_init_phc - Initialize PTP hardware clock + * @hw: pointer to the HW struct + * + * Perform the steps required to initialize the PTP hardware clock. + */ +int ice_ptp_init_phc(struct ice_hw *hw) +{ + u8 src_idx = hw->func_caps.ts_func_info.tmr_index_owned; - /* If present save the handle and return it */ - hw->io_expander_handle = - le16_to_cpu(desc.params.get_link_topo.addr.handle); - *pca9575_handle = hw->io_expander_handle; + /* Enable source clocks */ + wr32(hw, GLTSYN_ENA(src_idx), GLTSYN_ENA_TSYN_ENA_M); - return 0; + /* Clear event err indications for auxiliary pins */ + (void)rd32(hw, GLTSYN_STAT(src_idx)); + + switch (hw->phy_model) { + case ICE_PHY_E810: + return ice_ptp_init_phc_e810(hw); + case ICE_PHY_E822: + return ice_ptp_init_phc_e822(hw); + default: + return -EOPNOTSUPP; + } } /** - * ice_read_sma_ctrl_e810t + * ice_get_phy_tx_tstamp_ready - Read PHY Tx memory status indication + * @hw: pointer to the HW struct + * @block: the timestamp block to check + * @tstamp_ready: storage for the PHY Tx memory status information + * + * Check the PHY for Tx timestamp memory status. This reports a 64 bit value + * which indicates which timestamps in the block may be captured. A set bit + * means the timestamp can be read. An unset bit means the timestamp is not + * ready and software should avoid reading the register. + */ +int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready) +{ + switch (hw->phy_model) { + case ICE_PHY_E810: + return ice_get_phy_tx_tstamp_ready_e810(hw, block, + tstamp_ready); + case ICE_PHY_E822: + return ice_get_phy_tx_tstamp_ready_e822(hw, block, + tstamp_ready); + break; + default: + return -EOPNOTSUPP; + } +} + +/** + * ice_cgu_get_pin_desc_e823 - get pin description array * @hw: pointer to the hw struct - * @data: pointer to data to be read from the GPIO controller + * @input: if request is done against input or output pin + * @size: number of inputs/outputs * - * Read the SMA controller state. It is connected to pins 3-7 of Port 1 of the - * PCA9575 expander, so only bits 3-7 in data are valid. + * Return: pointer to pin description array associated to given hw. */ -int ice_read_sma_ctrl_e810t(struct ice_hw *hw, u8 *data) +static const struct ice_cgu_pin_desc * +ice_cgu_get_pin_desc_e823(struct ice_hw *hw, bool input, int *size) { - int status; - u16 handle; - u8 i; + static const struct ice_cgu_pin_desc *t; - status = ice_get_pca9575_handle(hw, &handle); - if (status) - return status; + if (hw->cgu_part_number == + ICE_AQC_GET_LINK_TOPO_NODE_NR_ZL30632_80032) { + if (input) { + t = ice_e823_zl_cgu_inputs; + *size = ARRAY_SIZE(ice_e823_zl_cgu_inputs); + } else { + t = ice_e823_zl_cgu_outputs; + *size = ARRAY_SIZE(ice_e823_zl_cgu_outputs); + } + } else if (hw->cgu_part_number == + ICE_AQC_GET_LINK_TOPO_NODE_NR_SI5383_5384) { + if (input) { + t = ice_e823_si_cgu_inputs; + *size = ARRAY_SIZE(ice_e823_si_cgu_inputs); + } else { + t = ice_e823_si_cgu_outputs; + *size = ARRAY_SIZE(ice_e823_si_cgu_outputs); + } + } else { + t = NULL; + *size = 0; + } - *data = 0; + return t; +} - for (i = ICE_SMA_MIN_BIT_E810T; i <= ICE_SMA_MAX_BIT_E810T; i++) { - bool pin; +/** + * ice_cgu_get_pin_desc - get pin description array + * @hw: pointer to the hw struct + * @input: if request is done against input or output pins + * @size: size of array returned by function + * + * Return: pointer to pin description array associated to given hw. + */ +static const struct ice_cgu_pin_desc * +ice_cgu_get_pin_desc(struct ice_hw *hw, bool input, int *size) +{ + const struct ice_cgu_pin_desc *t = NULL; - status = ice_aq_get_gpio(hw, handle, i + ICE_PCA9575_P1_OFFSET, - &pin, NULL); - if (status) - break; - *data |= (u8)(!pin) << i; + switch (hw->device_id) { + case ICE_DEV_ID_E810C_SFP: + if (input) { + t = ice_e810t_sfp_cgu_inputs; + *size = ARRAY_SIZE(ice_e810t_sfp_cgu_inputs); + } else { + t = ice_e810t_sfp_cgu_outputs; + *size = ARRAY_SIZE(ice_e810t_sfp_cgu_outputs); + } + break; + case ICE_DEV_ID_E810C_QSFP: + if (input) { + t = ice_e810t_qsfp_cgu_inputs; + *size = ARRAY_SIZE(ice_e810t_qsfp_cgu_inputs); + } else { + t = ice_e810t_qsfp_cgu_outputs; + *size = ARRAY_SIZE(ice_e810t_qsfp_cgu_outputs); + } + break; + case ICE_DEV_ID_E823L_10G_BASE_T: + case ICE_DEV_ID_E823L_1GBE: + case ICE_DEV_ID_E823L_BACKPLANE: + case ICE_DEV_ID_E823L_QSFP: + case ICE_DEV_ID_E823L_SFP: + case ICE_DEV_ID_E823C_10G_BASE_T: + case ICE_DEV_ID_E823C_BACKPLANE: + case ICE_DEV_ID_E823C_QSFP: + case ICE_DEV_ID_E823C_SFP: + case ICE_DEV_ID_E823C_SGMII: + t = ice_cgu_get_pin_desc_e823(hw, input, size); + break; + default: + break; } - return status; + return t; } /** - * ice_write_sma_ctrl_e810t + * ice_cgu_get_pin_type - get pin's type * @hw: pointer to the hw struct - * @data: data to be written to the GPIO controller + * @pin: pin index + * @input: if request is done against input or output pin * - * Write the data to the SMA controller. It is connected to pins 3-7 of Port 1 - * of the PCA9575 expander, so only bits 3-7 in data are valid. + * Return: type of a pin. */ -int ice_write_sma_ctrl_e810t(struct ice_hw *hw, u8 data) +enum dpll_pin_type ice_cgu_get_pin_type(struct ice_hw *hw, u8 pin, bool input) { - int status; - u16 handle; - u8 i; + const struct ice_cgu_pin_desc *t; + int t_size; - status = ice_get_pca9575_handle(hw, &handle); - if (status) - return status; + t = ice_cgu_get_pin_desc(hw, input, &t_size); - for (i = ICE_SMA_MIN_BIT_E810T; i <= ICE_SMA_MAX_BIT_E810T; i++) { - bool pin; + if (!t) + return 0; - pin = !(data & (1 << i)); - status = ice_aq_set_gpio(hw, handle, i + ICE_PCA9575_P1_OFFSET, - pin, NULL); - if (status) - break; - } + if (pin >= t_size) + return 0; - return status; + return t[pin].type; } /** - * ice_read_pca9575_reg_e810t + * ice_cgu_get_pin_freq_supp - get pin's supported frequency * @hw: pointer to the hw struct - * @offset: GPIO controller register offset - * @data: pointer to data to be read from the GPIO controller + * @pin: pin index + * @input: if request is done against input or output pin + * @num: output number of supported frequencies * - * Read the register from the GPIO controller + * Get frequency supported number and array of supported frequencies. + * + * Return: array of supported frequencies for given pin. */ -int ice_read_pca9575_reg_e810t(struct ice_hw *hw, u8 offset, u8 *data) +struct dpll_pin_frequency * +ice_cgu_get_pin_freq_supp(struct ice_hw *hw, u8 pin, bool input, u8 *num) { - struct ice_aqc_link_topo_addr link_topo; - __le16 addr; - u16 handle; - int err; + const struct ice_cgu_pin_desc *t; + int t_size; - memset(&link_topo, 0, sizeof(link_topo)); - - err = ice_get_pca9575_handle(hw, &handle); - if (err) - return err; + *num = 0; + t = ice_cgu_get_pin_desc(hw, input, &t_size); + if (!t) + return NULL; + if (pin >= t_size) + return NULL; + *num = t[pin].freq_supp_num; - link_topo.handle = cpu_to_le16(handle); - link_topo.topo_params.node_type_ctx = - FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, - ICE_AQC_LINK_TOPO_NODE_CTX_PROVIDED); - - addr = cpu_to_le16((u16)offset); - - return ice_aq_read_i2c(hw, link_topo, 0, addr, 1, data, NULL); + return t[pin].freq_supp; } /** - * ice_is_pca9575_present + * ice_cgu_get_pin_name - get pin's name * @hw: pointer to the hw struct + * @pin: pin index + * @input: if request is done against input or output pin * - * Check if the SW IO expander is present in the netlist + * Return: + * * null terminated char array with name + * * NULL in case of failure */ -bool ice_is_pca9575_present(struct ice_hw *hw) +const char *ice_cgu_get_pin_name(struct ice_hw *hw, u8 pin, bool input) { - u16 handle = 0; - int status; + const struct ice_cgu_pin_desc *t; + int t_size; - if (!ice_is_e810t(hw)) - return false; + t = ice_cgu_get_pin_desc(hw, input, &t_size); - status = ice_get_pca9575_handle(hw, &handle); + if (!t) + return NULL; - return !status && handle; + if (pin >= t_size) + return NULL; + + return t[pin].name; } /** - * ice_ptp_reset_ts_memory - Reset timestamp memory for all blocks - * @hw: pointer to the HW struct - */ -void ice_ptp_reset_ts_memory(struct ice_hw *hw) -{ - if (ice_is_e810(hw)) - return; + * ice_get_cgu_state - get the state of the DPLL + * @hw: pointer to the hw struct + * @dpll_idx: Index of internal DPLL unit + * @last_dpll_state: last known state of DPLL + * @pin: pointer to a buffer for returning currently active pin + * @ref_state: reference clock state + * @eec_mode: eec mode of the DPLL + * @phase_offset: pointer to a buffer for returning phase offset + * @dpll_state: state of the DPLL (output) + * + * This function will read the state of the DPLL(dpll_idx). Non-null + * 'pin', 'ref_state', 'eec_mode' and 'phase_offset' parameters are used to + * retrieve currently active pin, state, mode and phase_offset respectively. + * + * Return: state of the DPLL + */ +int ice_get_cgu_state(struct ice_hw *hw, u8 dpll_idx, + enum dpll_lock_status last_dpll_state, u8 *pin, + u8 *ref_state, u8 *eec_mode, s64 *phase_offset, + enum dpll_lock_status *dpll_state) +{ + u8 hw_ref_state, hw_dpll_state, hw_eec_mode, hw_config; + s64 hw_phase_offset; + int status; + + status = ice_aq_get_cgu_dpll_status(hw, dpll_idx, &hw_ref_state, + &hw_dpll_state, &hw_config, + &hw_phase_offset, &hw_eec_mode); + if (status) + return status; + + if (pin) + /* current ref pin in dpll_state_refsel_status_X register */ + *pin = hw_config & ICE_AQC_GET_CGU_DPLL_CONFIG_CLK_REF_SEL; + if (phase_offset) + *phase_offset = hw_phase_offset; + if (ref_state) + *ref_state = hw_ref_state; + if (eec_mode) + *eec_mode = hw_eec_mode; + if (!dpll_state) + return 0; - ice_ptp_reset_ts_memory_e822(hw); + /* According to ZL DPLL documentation, once state reach LOCKED_HO_ACQ + * it would never return to FREERUN. This aligns to ITU-T G.781 + * Recommendation. We cannot report HOLDOVER as HO memory is cleared + * while switching to another reference. + * Only for situations where previous state was either: "LOCKED without + * HO_ACQ" or "HOLDOVER" we actually back to FREERUN. + */ + if (hw_dpll_state & ICE_AQC_GET_CGU_DPLL_STATUS_STATE_LOCK) { + if (hw_dpll_state & ICE_AQC_GET_CGU_DPLL_STATUS_STATE_HO_READY) + *dpll_state = DPLL_LOCK_STATUS_LOCKED_HO_ACQ; + else + *dpll_state = DPLL_LOCK_STATUS_LOCKED; + } else if (last_dpll_state == DPLL_LOCK_STATUS_LOCKED_HO_ACQ || + last_dpll_state == DPLL_LOCK_STATUS_HOLDOVER) { + *dpll_state = DPLL_LOCK_STATUS_HOLDOVER; + } else { + *dpll_state = DPLL_LOCK_STATUS_UNLOCKED; + } + + return 0; } /** - * ice_ptp_init_phc - Initialize PTP hardware clock - * @hw: pointer to the HW struct + * ice_get_cgu_rclk_pin_info - get info on available recovered clock pins + * @hw: pointer to the hw struct + * @base_idx: returns index of first recovered clock pin on device + * @pin_num: returns number of recovered clock pins available on device * - * Perform the steps required to initialize the PTP hardware clock. + * Based on hw provide caller info about recovery clock pins available on the + * board. + * + * Return: + * * 0 - success, information is valid + * * negative - failure, information is not valid */ -int ice_ptp_init_phc(struct ice_hw *hw) +int ice_get_cgu_rclk_pin_info(struct ice_hw *hw, u8 *base_idx, u8 *pin_num) { - u8 src_idx = hw->func_caps.ts_func_info.tmr_index_owned; + u8 phy_idx; + int ret; - /* Enable source clocks */ - wr32(hw, GLTSYN_ENA(src_idx), GLTSYN_ENA_TSYN_ENA_M); + switch (hw->device_id) { + case ICE_DEV_ID_E810C_SFP: + case ICE_DEV_ID_E810C_QSFP: - /* Clear event err indications for auxiliary pins */ - (void)rd32(hw, GLTSYN_STAT(src_idx)); + ret = ice_get_pf_c827_idx(hw, &phy_idx); + if (ret) + return ret; + *base_idx = E810T_CGU_INPUT_C827(phy_idx, ICE_RCLKA_PIN); + *pin_num = ICE_E810_RCLK_PINS_NUM; + ret = 0; + break; + case ICE_DEV_ID_E823L_10G_BASE_T: + case ICE_DEV_ID_E823L_1GBE: + case ICE_DEV_ID_E823L_BACKPLANE: + case ICE_DEV_ID_E823L_QSFP: + case ICE_DEV_ID_E823L_SFP: + case ICE_DEV_ID_E823C_10G_BASE_T: + case ICE_DEV_ID_E823C_BACKPLANE: + case ICE_DEV_ID_E823C_QSFP: + case ICE_DEV_ID_E823C_SFP: + case ICE_DEV_ID_E823C_SGMII: + *pin_num = ICE_E822_RCLK_PINS_NUM; + ret = 0; + if (hw->cgu_part_number == + ICE_AQC_GET_LINK_TOPO_NODE_NR_ZL30632_80032) + *base_idx = ZL_REF1P; + else if (hw->cgu_part_number == + ICE_AQC_GET_LINK_TOPO_NODE_NR_SI5383_5384) + *base_idx = SI_REF1P; + else + ret = -ENODEV; - if (ice_is_e810(hw)) - return ice_ptp_init_phc_e810(hw); - else - return ice_ptp_init_phc_e822(hw); + break; + default: + ret = -ENODEV; + break; + } + + return ret; } /** - * ice_get_phy_tx_tstamp_ready - Read PHY Tx memory status indication - * @hw: pointer to the HW struct - * @block: the timestamp block to check - * @tstamp_ready: storage for the PHY Tx memory status information + * ice_cgu_get_output_pin_state_caps - get output pin state capabilities + * @hw: pointer to the hw struct + * @pin_id: id of a pin + * @caps: capabilities to modify * - * Check the PHY for Tx timestamp memory status. This reports a 64 bit value - * which indicates which timestamps in the block may be captured. A set bit - * means the timestamp can be read. An unset bit means the timestamp is not - * ready and software should avoid reading the register. + * Return: + * * 0 - success, state capabilities were modified + * * negative - failure, capabilities were not modified */ -int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready) +int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id, + unsigned long *caps) { - if (ice_is_e810(hw)) - return ice_get_phy_tx_tstamp_ready_e810(hw, block, - tstamp_ready); + bool can_change = true; + + switch (hw->device_id) { + case ICE_DEV_ID_E810C_SFP: + if (pin_id == ZL_OUT2 || pin_id == ZL_OUT3) + can_change = false; + break; + case ICE_DEV_ID_E810C_QSFP: + if (pin_id == ZL_OUT2 || pin_id == ZL_OUT3 || pin_id == ZL_OUT4) + can_change = false; + break; + case ICE_DEV_ID_E823L_10G_BASE_T: + case ICE_DEV_ID_E823L_1GBE: + case ICE_DEV_ID_E823L_BACKPLANE: + case ICE_DEV_ID_E823L_QSFP: + case ICE_DEV_ID_E823L_SFP: + case ICE_DEV_ID_E823C_10G_BASE_T: + case ICE_DEV_ID_E823C_BACKPLANE: + case ICE_DEV_ID_E823C_QSFP: + case ICE_DEV_ID_E823C_SFP: + case ICE_DEV_ID_E823C_SGMII: + if (hw->cgu_part_number == + ICE_AQC_GET_LINK_TOPO_NODE_NR_ZL30632_80032 && + pin_id == ZL_OUT2) + can_change = false; + else if (hw->cgu_part_number == + ICE_AQC_GET_LINK_TOPO_NODE_NR_SI5383_5384 && + pin_id == SI_OUT1) + can_change = false; + break; + default: + return -EINVAL; + } + if (can_change) + *caps |= DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE; else - return ice_get_phy_tx_tstamp_ready_e822(hw, block, - tstamp_ready); + *caps &= ~DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE; + + return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h index 3b68cb91bd81..cf76701566c7 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -3,13 +3,15 @@ #ifndef _ICE_PTP_HW_H_ #define _ICE_PTP_HW_H_ +#include <linux/dpll.h> enum ice_ptp_tmr_cmd { - INIT_TIME, - INIT_INCVAL, - ADJ_TIME, - ADJ_TIME_AT_TIME, - READ_TIME + ICE_PTP_INIT_TIME, + ICE_PTP_INIT_INCVAL, + ICE_PTP_ADJ_TIME, + ICE_PTP_ADJ_TIME_AT_TIME, + ICE_PTP_READ_TIME, + ICE_PTP_NOP, }; enum ice_ptp_serdes { @@ -109,9 +111,83 @@ struct ice_cgu_pll_params_e822 { u32 post_pll_div; }; +#define E810C_QSFP_C827_0_HANDLE 2 +#define E810C_QSFP_C827_1_HANDLE 3 +enum ice_e810_c827_idx { + C827_0, + C827_1 +}; + +enum ice_phy_rclk_pins { + ICE_RCLKA_PIN = 0, /* SCL pin */ + ICE_RCLKB_PIN, /* SDA pin */ +}; + +#define ICE_E810_RCLK_PINS_NUM (ICE_RCLKB_PIN + 1) +#define ICE_E822_RCLK_PINS_NUM (ICE_RCLKA_PIN + 1) +#define E810T_CGU_INPUT_C827(_phy, _pin) ((_phy) * ICE_E810_RCLK_PINS_NUM + \ + (_pin) + ZL_REF1P) + +enum ice_zl_cgu_in_pins { + ZL_REF0P = 0, + ZL_REF0N, + ZL_REF1P, + ZL_REF1N, + ZL_REF2P, + ZL_REF2N, + ZL_REF3P, + ZL_REF3N, + ZL_REF4P, + ZL_REF4N, + NUM_ZL_CGU_INPUT_PINS +}; + +enum ice_zl_cgu_out_pins { + ZL_OUT0 = 0, + ZL_OUT1, + ZL_OUT2, + ZL_OUT3, + ZL_OUT4, + ZL_OUT5, + ZL_OUT6, + NUM_ZL_CGU_OUTPUT_PINS +}; + +enum ice_si_cgu_in_pins { + SI_REF0P = 0, + SI_REF0N, + SI_REF1P, + SI_REF1N, + SI_REF2P, + SI_REF2N, + SI_REF3, + SI_REF4, + NUM_SI_CGU_INPUT_PINS +}; + +enum ice_si_cgu_out_pins { + SI_OUT0 = 0, + SI_OUT1, + SI_OUT2, + SI_OUT3, + SI_OUT4, + NUM_SI_CGU_OUTPUT_PINS +}; + +struct ice_cgu_pin_desc { + char *name; + u8 index; + enum dpll_pin_type type; + u32 freq_supp_num; + struct dpll_pin_frequency *freq_supp; +}; + extern const struct ice_cgu_pll_params_e822 e822_cgu_params[NUM_ICE_TIME_REF_FREQ]; +#define E810C_QSFP_C827_0_HANDLE 2 +#define E810C_QSFP_C827_1_HANDLE 3 + /* Table of constants related to possible TIME_REF sources */ extern const struct ice_time_ref_info_e822 e822_time_ref[NUM_ICE_TIME_REF_FREQ]; @@ -127,6 +203,7 @@ extern const struct ice_vernier_info_e822 e822_vernier[NUM_ICE_PTP_LNK_SPD]; u8 ice_get_ptp_src_clock_index(struct ice_hw *hw); bool ice_ptp_lock(struct ice_hw *hw); void ice_ptp_unlock(struct ice_hw *hw); +void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd); int ice_ptp_init_time(struct ice_hw *hw, u64 time); int ice_ptp_write_incval(struct ice_hw *hw, u64 incval); int ice_ptp_write_incval_locked(struct ice_hw *hw, u64 incval); @@ -138,11 +215,8 @@ int ice_ptp_init_phc(struct ice_hw *hw); int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready); /* E822 family functions */ -int ice_read_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 *val); -int ice_write_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 val); int ice_read_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 *val); int ice_write_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 val); -int ice_ptp_prep_port_adj_e822(struct ice_hw *hw, u8 port, s64 time); void ice_ptp_reset_ts_memory_quad_e822(struct ice_hw *hw, u8 quad); /** @@ -197,6 +271,19 @@ int ice_read_sma_ctrl_e810t(struct ice_hw *hw, u8 *data); int ice_write_sma_ctrl_e810t(struct ice_hw *hw, u8 data); int ice_read_pca9575_reg_e810t(struct ice_hw *hw, u8 offset, u8 *data); bool ice_is_pca9575_present(struct ice_hw *hw); +enum dpll_pin_type ice_cgu_get_pin_type(struct ice_hw *hw, u8 pin, bool input); +struct dpll_pin_frequency * +ice_cgu_get_pin_freq_supp(struct ice_hw *hw, u8 pin, bool input, u8 *num); +const char *ice_cgu_get_pin_name(struct ice_hw *hw, u8 pin, bool input); +int ice_get_cgu_state(struct ice_hw *hw, u8 dpll_idx, + enum dpll_lock_status last_dpll_state, u8 *pin, + u8 *ref_state, u8 *eec_mode, s64 *phase_offset, + enum dpll_lock_status *dpll_state); +int ice_get_cgu_rclk_pin_info(struct ice_hw *hw, u8 *base_idx, u8 *pin_num); + +void ice_ptp_init_phy_model(struct ice_hw *hw); +int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id, + unsigned long *caps); #define PFTSYN_SEM_BYTES 4 diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c index e30e12321abd..c686ac0935eb 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.c +++ b/drivers/net/ethernet/intel/ice/ice_repr.c @@ -254,7 +254,7 @@ static const struct net_device_ops ice_repr_netdev_ops = { * ice_is_port_repr_netdev - Check if a given netdevice is a port representor netdev * @netdev: pointer to netdev */ -bool ice_is_port_repr_netdev(struct net_device *netdev) +bool ice_is_port_repr_netdev(const struct net_device *netdev) { return netdev && (netdev->netdev_ops == &ice_repr_netdev_ops); } diff --git a/drivers/net/ethernet/intel/ice/ice_repr.h b/drivers/net/ethernet/intel/ice/ice_repr.h index 9c2a6f496b3b..e1ee2d2c1d2d 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.h +++ b/drivers/net/ethernet/intel/ice/ice_repr.h @@ -12,6 +12,7 @@ struct ice_repr { struct ice_q_vector *q_vector; struct net_device *netdev; struct metadata_dst *dst; + struct ice_esw_br_port *br_port; #ifdef CONFIG_ICE_SWITCHDEV /* info about slow path rule */ struct ice_rule_query_data sp_rule; @@ -27,5 +28,5 @@ void ice_repr_stop_tx_queues(struct ice_repr *repr); void ice_repr_set_traffic_vsi(struct ice_repr *repr, struct ice_vsi *vsi); struct ice_repr *ice_netdev_to_repr(struct net_device *netdev); -bool ice_is_port_repr_netdev(struct net_device *netdev); +bool ice_is_port_repr_netdev(const struct net_device *netdev); #endif diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index b664d60fd037..2f4a621254e8 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -229,29 +229,22 @@ ice_aq_delete_sched_elems(struct ice_hw *hw, u16 grps_req, * ice_sched_remove_elems - remove nodes from HW * @hw: pointer to the HW struct * @parent: pointer to the parent node - * @num_nodes: number of nodes - * @node_teids: array of node teids to be deleted + * @node_teid: node teid to be deleted * * This function remove nodes from HW */ static int ice_sched_remove_elems(struct ice_hw *hw, struct ice_sched_node *parent, - u16 num_nodes, u32 *node_teids) + u32 node_teid) { - struct ice_aqc_delete_elem *buf; - u16 i, num_groups_removed = 0; - u16 buf_size; + DEFINE_FLEX(struct ice_aqc_delete_elem, buf, teid, 1); + u16 buf_size = __struct_size(buf); + u16 num_groups_removed = 0; int status; - buf_size = struct_size(buf, teid, num_nodes); - buf = devm_kzalloc(ice_hw_to_dev(hw), buf_size, GFP_KERNEL); - if (!buf) - return -ENOMEM; - buf->hdr.parent_teid = parent->info.node_teid; - buf->hdr.num_elems = cpu_to_le16(num_nodes); - for (i = 0; i < num_nodes; i++) - buf->teid[i] = cpu_to_le32(node_teids[i]); + buf->hdr.num_elems = cpu_to_le16(1); + buf->teid[0] = cpu_to_le32(node_teid); status = ice_aq_delete_sched_elems(hw, 1, buf, buf_size, &num_groups_removed, NULL); @@ -259,7 +252,6 @@ ice_sched_remove_elems(struct ice_hw *hw, struct ice_sched_node *parent, ice_debug(hw, ICE_DBG_SCHED, "remove node failed FW error %d\n", hw->adminq.sq_last_status); - devm_kfree(ice_hw_to_dev(hw), buf); return status; } @@ -326,7 +318,7 @@ void ice_free_sched_node(struct ice_port_info *pi, struct ice_sched_node *node) node->info.data.elem_type != ICE_AQC_ELEM_TYPE_LEAF) { u32 teid = le32_to_cpu(node->info.node_teid); - ice_sched_remove_elems(hw, node->parent, 1, &teid); + ice_sched_remove_elems(hw, node->parent, teid); } parent = node->parent; /* root has no parent */ @@ -437,24 +429,20 @@ ice_aq_cfg_sched_elems(struct ice_hw *hw, u16 elems_req, } /** - * ice_aq_move_sched_elems - move scheduler elements + * ice_aq_move_sched_elems - move scheduler element (just 1 group) * @hw: pointer to the HW struct - * @grps_req: number of groups to move * @buf: pointer to buffer * @buf_size: buffer size in bytes * @grps_movd: returns total number of groups moved - * @cd: pointer to command details structure or NULL * * Move scheduling elements (0x0408) */ -static int -ice_aq_move_sched_elems(struct ice_hw *hw, u16 grps_req, - struct ice_aqc_move_elem *buf, u16 buf_size, - u16 *grps_movd, struct ice_sq_cd *cd) +int +ice_aq_move_sched_elems(struct ice_hw *hw, struct ice_aqc_move_elem *buf, + u16 buf_size, u16 *grps_movd) { return ice_aqc_send_sched_elem_cmd(hw, ice_aqc_opc_move_sched_elems, - grps_req, (void *)buf, buf_size, - grps_movd, cd); + 1, buf, buf_size, grps_movd, NULL); } /** @@ -526,7 +514,7 @@ ice_aq_query_sched_res(struct ice_hw *hw, u16 buf_size, * * This function suspends or resumes HW nodes */ -static int +int ice_sched_suspend_resume_elems(struct ice_hw *hw, u8 num_nodes, u32 *node_teids, bool suspend) { @@ -569,18 +557,24 @@ ice_alloc_lan_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; + u16 idx; vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle); if (!vsi_ctx) return -EINVAL; /* allocate LAN queue contexts */ if (!vsi_ctx->lan_q_ctx[tc]) { - vsi_ctx->lan_q_ctx[tc] = devm_kcalloc(ice_hw_to_dev(hw), - new_numqs, - sizeof(*q_ctx), - GFP_KERNEL); - if (!vsi_ctx->lan_q_ctx[tc]) + q_ctx = devm_kcalloc(ice_hw_to_dev(hw), new_numqs, + sizeof(*q_ctx), GFP_KERNEL); + if (!q_ctx) return -ENOMEM; + + for (idx = 0; idx < new_numqs; idx++) { + q_ctx[idx].q_handle = ICE_INVAL_Q_HANDLE; + q_ctx[idx].q_teid = ICE_INVAL_TEID; + } + + vsi_ctx->lan_q_ctx[tc] = q_ctx; vsi_ctx->num_lan_q_entries[tc] = new_numqs; return 0; } @@ -592,9 +586,16 @@ ice_alloc_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs) sizeof(*q_ctx), GFP_KERNEL); if (!q_ctx) return -ENOMEM; + memcpy(q_ctx, vsi_ctx->lan_q_ctx[tc], prev_num * sizeof(*q_ctx)); devm_kfree(ice_hw_to_dev(hw), vsi_ctx->lan_q_ctx[tc]); + + for (idx = prev_num; idx < new_numqs; idx++) { + q_ctx[idx].q_handle = ICE_INVAL_Q_HANDLE; + q_ctx[idx].q_teid = ICE_INVAL_TEID; + } + vsi_ctx->lan_q_ctx[tc] = q_ctx; vsi_ctx->num_lan_q_entries[tc] = new_numqs; } @@ -1044,7 +1045,7 @@ ice_sched_add_nodes_to_hw_layer(struct ice_port_info *pi, * * This function add nodes to a given layer. */ -static int +int ice_sched_add_nodes_to_layer(struct ice_port_info *pi, struct ice_sched_node *tc_node, struct ice_sched_node *parent, u8 layer, @@ -1119,7 +1120,7 @@ static u8 ice_sched_get_qgrp_layer(struct ice_hw *hw) * * This function returns the current VSI layer number */ -static u8 ice_sched_get_vsi_layer(struct ice_hw *hw) +u8 ice_sched_get_vsi_layer(struct ice_hw *hw) { /* Num Layers VSI layer * 9 6 @@ -1142,7 +1143,7 @@ static u8 ice_sched_get_vsi_layer(struct ice_hw *hw) * * This function returns the current aggregator layer number */ -static u8 ice_sched_get_agg_layer(struct ice_hw *hw) +u8 ice_sched_get_agg_layer(struct ice_hw *hw) { /* Num Layers aggregator layer * 9 4 @@ -1180,7 +1181,7 @@ static void ice_rm_dflt_leaf_node(struct ice_port_info *pi) int status; /* remove the default leaf node */ - status = ice_sched_remove_elems(pi->hw, node->parent, 1, &teid); + status = ice_sched_remove_elems(pi->hw, node->parent, teid); if (!status) ice_free_sched_node(pi, node); } @@ -1577,7 +1578,7 @@ ice_sched_get_vsi_node(struct ice_port_info *pi, struct ice_sched_node *tc_node, * This function retrieves an aggregator node for a given aggregator ID from * a given TC branch */ -static struct ice_sched_node * +struct ice_sched_node * ice_sched_get_agg_node(struct ice_port_info *pi, struct ice_sched_node *tc_node, u32 agg_id) { @@ -2139,7 +2140,7 @@ ice_get_agg_info(struct ice_hw *hw, u32 agg_id) * This function walks through the aggregator subtree to find a free parent * node */ -static struct ice_sched_node * +struct ice_sched_node * ice_sched_get_free_vsi_parent(struct ice_hw *hw, struct ice_sched_node *node, u16 *num_nodes) { @@ -2219,12 +2220,12 @@ int ice_sched_move_nodes(struct ice_port_info *pi, struct ice_sched_node *parent, u16 num_items, u32 *list) { - struct ice_aqc_move_elem *buf; + DEFINE_FLEX(struct ice_aqc_move_elem, buf, teid, 1); + u16 buf_len = __struct_size(buf); struct ice_sched_node *node; u16 i, grps_movd = 0; struct ice_hw *hw; int status = 0; - u16 buf_len; hw = pi->hw; @@ -2236,35 +2237,27 @@ ice_sched_move_nodes(struct ice_port_info *pi, struct ice_sched_node *parent, hw->max_children[parent->tx_sched_layer]) return -ENOSPC; - buf_len = struct_size(buf, teid, 1); - buf = kzalloc(buf_len, GFP_KERNEL); - if (!buf) - return -ENOMEM; - for (i = 0; i < num_items; i++) { node = ice_sched_find_node_by_teid(pi->root, list[i]); if (!node) { status = -EINVAL; - goto move_err_exit; + break; } buf->hdr.src_parent_teid = node->info.parent_teid; buf->hdr.dest_parent_teid = parent->info.node_teid; buf->teid[0] = node->info.node_teid; buf->hdr.num_elems = cpu_to_le16(1); - status = ice_aq_move_sched_elems(hw, 1, buf, buf_len, - &grps_movd, NULL); + status = ice_aq_move_sched_elems(hw, buf, buf_len, &grps_movd); if (status && grps_movd != 1) { status = -EIO; - goto move_err_exit; + break; } /* update the SW DB */ ice_sched_update_parent(parent, node); } -move_err_exit: - kfree(buf); return status; } @@ -3958,7 +3951,7 @@ ice_sched_get_node_by_id_type(struct ice_port_info *pi, u32 id, * This function sets BW limit of VSI or Aggregator scheduling node * based on TC information from passed in argument BW. */ -int +static int ice_sched_set_node_bw_lmt_per_tc(struct ice_port_info *pi, u32 id, enum ice_agg_type agg_type, u8 tc, enum ice_rl_type rl_type, u32 bw) diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h index 9c100747445a..1aef05ea5a57 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.h +++ b/drivers/net/ethernet/intel/ice/ice_sched.h @@ -141,13 +141,28 @@ ice_cfg_vsi_bw_lmt_per_tc(struct ice_port_info *pi, u16 vsi_handle, u8 tc, int ice_cfg_vsi_bw_dflt_lmt_per_tc(struct ice_port_info *pi, u16 vsi_handle, u8 tc, enum ice_rl_type rl_type); -int -ice_sched_set_node_bw_lmt_per_tc(struct ice_port_info *pi, u32 id, - enum ice_agg_type agg_type, u8 tc, - enum ice_rl_type rl_type, u32 bw); int ice_cfg_rl_burst_size(struct ice_hw *hw, u32 bytes); +int +ice_sched_suspend_resume_elems(struct ice_hw *hw, u8 num_nodes, u32 *node_teids, + bool suspend); +struct ice_sched_node * +ice_sched_get_agg_node(struct ice_port_info *pi, struct ice_sched_node *tc_node, + u32 agg_id); +u8 ice_sched_get_agg_layer(struct ice_hw *hw); +u8 ice_sched_get_vsi_layer(struct ice_hw *hw); +struct ice_sched_node * +ice_sched_get_free_vsi_parent(struct ice_hw *hw, struct ice_sched_node *node, + u16 *num_nodes); +int +ice_sched_add_nodes_to_layer(struct ice_port_info *pi, + struct ice_sched_node *tc_node, + struct ice_sched_node *parent, u8 layer, + u16 num_nodes, u32 *first_node_teid, + u16 *num_nodes_added); void ice_sched_replay_agg_vsi_preinit(struct ice_hw *hw); void ice_sched_replay_agg(struct ice_hw *hw); +int ice_aq_move_sched_elems(struct ice_hw *hw, struct ice_aqc_move_elem *buf, + u16 buf_size, u16 *grps_movd); int ice_replay_vsi_agg(struct ice_hw *hw, u16 vsi_handle); int ice_sched_replay_q_bw(struct ice_port_info *pi, struct ice_q_ctx *q_ctx); #endif /* _ICE_SCHED_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index 31314e7540f8..e1494f24f661 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -64,7 +64,7 @@ static void ice_free_vf_res(struct ice_vf *vf) vf->num_mac = 0; } - last_vector_idx = vf->first_vector_idx + pf->vfs.num_msix_per - 1; + last_vector_idx = vf->first_vector_idx + vf->num_msix - 1; /* clear VF MDD event information */ memset(&vf->mdd_tx_events, 0, sizeof(vf->mdd_tx_events)); @@ -102,7 +102,7 @@ static void ice_dis_vf_mappings(struct ice_vf *vf) wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), 0); first = vf->first_vector_idx; - last = first + pf->vfs.num_msix_per - 1; + last = first + vf->num_msix - 1; for (v = first; v <= last; v++) { u32 reg; @@ -138,6 +138,8 @@ static int ice_sriov_free_msix_res(struct ice_pf *pf) if (!pf) return -EINVAL; + bitmap_free(pf->sriov_irq_bm); + pf->sriov_irq_size = 0; pf->sriov_base_vector = 0; return 0; @@ -244,22 +246,6 @@ static struct ice_vsi *ice_vf_vsi_setup(struct ice_vf *vf) return vsi; } -/** - * ice_calc_vf_first_vector_idx - Calculate MSIX vector index in the PF space - * @pf: pointer to PF structure - * @vf: pointer to VF that the first MSIX vector index is being calculated for - * - * This returns the first MSIX vector index in PF space that is used by this VF. - * This index is used when accessing PF relative registers such as - * GLINT_VECT2FUNC and GLINT_DYN_CTL. - * This will always be the OICR index in the AVF driver so any functionality - * using vf->first_vector_idx for queue configuration will have to increment by - * 1 to avoid meddling with the OICR index. - */ -static int ice_calc_vf_first_vector_idx(struct ice_pf *pf, struct ice_vf *vf) -{ - return pf->sriov_base_vector + vf->vf_id * pf->vfs.num_msix_per; -} /** * ice_ena_vf_msix_mappings - enable VF MSIX mappings in hardware @@ -280,12 +266,12 @@ static void ice_ena_vf_msix_mappings(struct ice_vf *vf) hw = &pf->hw; pf_based_first_msix = vf->first_vector_idx; - pf_based_last_msix = (pf_based_first_msix + pf->vfs.num_msix_per) - 1; + pf_based_last_msix = (pf_based_first_msix + vf->num_msix) - 1; device_based_first_msix = pf_based_first_msix + pf->hw.func_caps.common_cap.msix_vector_first_id; device_based_last_msix = - (device_based_first_msix + pf->vfs.num_msix_per) - 1; + (device_based_first_msix + vf->num_msix) - 1; device_based_vf_id = vf->vf_id + hw->func_caps.vf_base_id; reg = (((device_based_first_msix << VPINT_ALLOC_FIRST_S) & @@ -388,16 +374,11 @@ static void ice_ena_vf_mappings(struct ice_vf *vf) */ int ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector) { - struct ice_pf *pf; - if (!vf || !q_vector) return -EINVAL; - pf = vf->pf; - /* always add one to account for the OICR being the first MSIX */ - return pf->sriov_base_vector + pf->vfs.num_msix_per * vf->vf_id + - q_vector->v_idx + 1; + return vf->first_vector_idx + q_vector->v_idx + 1; } /** @@ -527,6 +508,52 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs) } /** + * ice_sriov_get_irqs - get irqs for SR-IOV usacase + * @pf: pointer to PF structure + * @needed: number of irqs to get + * + * This returns the first MSI-X vector index in PF space that is used by this + * VF. This index is used when accessing PF relative registers such as + * GLINT_VECT2FUNC and GLINT_DYN_CTL. + * This will always be the OICR index in the AVF driver so any functionality + * using vf->first_vector_idx for queue configuration_id: id of VF which will + * use this irqs + * + * Only SRIOV specific vectors are tracked in sriov_irq_bm. SRIOV vectors are + * allocated from the end of global irq index. First bit in sriov_irq_bm means + * last irq index etc. It simplifies extension of SRIOV vectors. + * They will be always located from sriov_base_vector to the last irq + * index. While increasing/decreasing sriov_base_vector can be moved. + */ +static int ice_sriov_get_irqs(struct ice_pf *pf, u16 needed) +{ + int res = bitmap_find_next_zero_area(pf->sriov_irq_bm, + pf->sriov_irq_size, 0, needed, 0); + /* conversion from number in bitmap to global irq index */ + int index = pf->sriov_irq_size - res - needed; + + if (res >= pf->sriov_irq_size || index < pf->sriov_base_vector) + return -ENOENT; + + bitmap_set(pf->sriov_irq_bm, res, needed); + return index; +} + +/** + * ice_sriov_free_irqs - free irqs used by the VF + * @pf: pointer to PF structure + * @vf: pointer to VF structure + */ +static void ice_sriov_free_irqs(struct ice_pf *pf, struct ice_vf *vf) +{ + /* Move back from first vector index to first index in bitmap */ + int bm_i = pf->sriov_irq_size - vf->first_vector_idx - vf->num_msix; + + bitmap_clear(pf->sriov_irq_bm, bm_i, vf->num_msix); + vf->first_vector_idx = 0; +} + +/** * ice_init_vf_vsi_res - initialize/setup VF VSI resources * @vf: VF to initialize/setup the VSI for * @@ -539,7 +566,9 @@ static int ice_init_vf_vsi_res(struct ice_vf *vf) struct ice_vsi *vsi; int err; - vf->first_vector_idx = ice_calc_vf_first_vector_idx(pf, vf); + vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix); + if (vf->first_vector_idx < 0) + return -ENOMEM; vsi = ice_vf_vsi_setup(vf); if (!vsi) @@ -789,14 +818,19 @@ static const struct ice_vf_ops ice_sriov_vf_ops = { */ static int ice_create_vf_entries(struct ice_pf *pf, u16 num_vfs) { + struct pci_dev *pdev = pf->pdev; struct ice_vfs *vfs = &pf->vfs; + struct pci_dev *vfdev = NULL; struct ice_vf *vf; - u16 vf_id; - int err; + u16 vf_pdev_id; + int err, pos; lockdep_assert_held(&vfs->table_lock); - for (vf_id = 0; vf_id < num_vfs; vf_id++) { + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV); + pci_read_config_word(pdev, pos + PCI_SRIOV_VF_DID, &vf_pdev_id); + + for (u16 vf_id = 0; vf_id < num_vfs; vf_id++) { vf = kzalloc(sizeof(*vf), GFP_KERNEL); if (!vf) { err = -ENOMEM; @@ -812,11 +846,28 @@ static int ice_create_vf_entries(struct ice_pf *pf, u16 num_vfs) ice_initialize_vf_entry(vf); + do { + vfdev = pci_get_device(pdev->vendor, vf_pdev_id, vfdev); + } while (vfdev && vfdev->physfn != pdev); + vf->vfdev = vfdev; vf->vf_sw_id = pf->first_sw; + pci_dev_get(vfdev); + + /* set default number of MSI-X */ + vf->num_msix = pf->vfs.num_msix_per; + vf->num_vf_qs = pf->vfs.num_qps_per; + ice_vc_set_default_allowlist(vf); + hash_add_rcu(vfs->table, &vf->entry, vf_id); } + /* Decrement of refcount done by pci_get_device() inside the loop does + * not touch the last iteration's vfdev, so it has to be done manually + * to balance pci_dev_get() added within the loop. + */ + pci_dev_put(vfdev); + return 0; err_free_entries: @@ -831,10 +882,16 @@ err_free_entries: */ static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs) { + int total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors; struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; int ret; + pf->sriov_irq_bm = bitmap_zalloc(total_vectors, GFP_KERNEL); + if (!pf->sriov_irq_bm) + return -ENOMEM; + pf->sriov_irq_size = total_vectors; + /* Disable global interrupt 0 so we don't try to handle the VFLR. */ wr32(hw, GLINT_DYN_CTL(pf->oicr_irq.index), ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S); @@ -893,6 +950,7 @@ err_unroll_intr: /* rearm interrupts here */ ice_irq_dynamic_ena(hw, NULL, NULL); clear_bit(ICE_OICR_INTR_DIS, pf->state); + bitmap_free(pf->sriov_irq_bm); return ret; } @@ -957,6 +1015,175 @@ static int ice_check_sriov_allowed(struct ice_pf *pf) } /** + * ice_sriov_get_vf_total_msix - return number of MSI-X used by VFs + * @pdev: pointer to pci_dev struct + * + * The function is called via sysfs ops + */ +u32 ice_sriov_get_vf_total_msix(struct pci_dev *pdev) +{ + struct ice_pf *pf = pci_get_drvdata(pdev); + + return pf->sriov_irq_size - ice_get_max_used_msix_vector(pf); +} + +static int ice_sriov_move_base_vector(struct ice_pf *pf, int move) +{ + if (pf->sriov_base_vector - move < ice_get_max_used_msix_vector(pf)) + return -ENOMEM; + + pf->sriov_base_vector -= move; + return 0; +} + +static void ice_sriov_remap_vectors(struct ice_pf *pf, u16 restricted_id) +{ + u16 vf_ids[ICE_MAX_SRIOV_VFS]; + struct ice_vf *tmp_vf; + int to_remap = 0, bkt; + + /* For better irqs usage try to remap irqs of VFs + * that aren't running yet + */ + ice_for_each_vf(pf, bkt, tmp_vf) { + /* skip VF which is changing the number of MSI-X */ + if (restricted_id == tmp_vf->vf_id || + test_bit(ICE_VF_STATE_ACTIVE, tmp_vf->vf_states)) + continue; + + ice_dis_vf_mappings(tmp_vf); + ice_sriov_free_irqs(pf, tmp_vf); + + vf_ids[to_remap] = tmp_vf->vf_id; + to_remap += 1; + } + + for (int i = 0; i < to_remap; i++) { + tmp_vf = ice_get_vf_by_id(pf, vf_ids[i]); + if (!tmp_vf) + continue; + + tmp_vf->first_vector_idx = + ice_sriov_get_irqs(pf, tmp_vf->num_msix); + /* there is no need to rebuild VSI as we are only changing the + * vector indexes not amount of MSI-X or queues + */ + ice_ena_vf_mappings(tmp_vf); + ice_put_vf(tmp_vf); + } +} + +/** + * ice_sriov_set_msix_vec_count + * @vf_dev: pointer to pci_dev struct of VF device + * @msix_vec_count: new value for MSI-X amount on this VF + * + * Set requested MSI-X, queues and registers for @vf_dev. + * + * First do some sanity checks like if there are any VFs, if the new value + * is correct etc. Then disable old mapping (MSI-X and queues registers), change + * MSI-X and queues, rebuild VSI and enable new mapping. + * + * If it is possible (driver not binded to VF) try to remap also other VFs to + * linearize irqs register usage. + */ +int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count) +{ + struct pci_dev *pdev = pci_physfn(vf_dev); + struct ice_pf *pf = pci_get_drvdata(pdev); + u16 prev_msix, prev_queues, queues; + bool needs_rebuild = false; + struct ice_vf *vf; + int id; + + if (!ice_get_num_vfs(pf)) + return -ENOENT; + + if (!msix_vec_count) + return 0; + + queues = msix_vec_count; + /* add 1 MSI-X for OICR */ + msix_vec_count += 1; + + if (queues > min(ice_get_avail_txq_count(pf), + ice_get_avail_rxq_count(pf))) + return -EINVAL; + + if (msix_vec_count < ICE_MIN_INTR_PER_VF) + return -EINVAL; + + /* Transition of PCI VF function number to function_id */ + for (id = 0; id < pci_num_vf(pdev); id++) { + if (vf_dev->devfn == pci_iov_virtfn_devfn(pdev, id)) + break; + } + + if (id == pci_num_vf(pdev)) + return -ENOENT; + + vf = ice_get_vf_by_id(pf, id); + + if (!vf) + return -ENOENT; + + prev_msix = vf->num_msix; + prev_queues = vf->num_vf_qs; + + if (ice_sriov_move_base_vector(pf, msix_vec_count - prev_msix)) { + ice_put_vf(vf); + return -ENOSPC; + } + + ice_dis_vf_mappings(vf); + ice_sriov_free_irqs(pf, vf); + + /* Remap all VFs beside the one is now configured */ + ice_sriov_remap_vectors(pf, vf->vf_id); + + vf->num_msix = msix_vec_count; + vf->num_vf_qs = queues; + vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix); + if (vf->first_vector_idx < 0) + goto unroll; + + ice_vf_vsi_release(vf); + if (vf->vf_ops->create_vsi(vf)) { + /* Try to rebuild with previous values */ + needs_rebuild = true; + goto unroll; + } + + dev_info(ice_pf_to_dev(pf), + "Changing VF %d resources to %d vectors and %d queues\n", + vf->vf_id, vf->num_msix, vf->num_vf_qs); + + ice_ena_vf_mappings(vf); + ice_put_vf(vf); + + return 0; + +unroll: + dev_info(ice_pf_to_dev(pf), + "Can't set %d vectors on VF %d, falling back to %d\n", + vf->num_msix, vf->vf_id, prev_msix); + + vf->num_msix = prev_msix; + vf->num_vf_qs = prev_queues; + vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix); + if (vf->first_vector_idx < 0) + return -EINVAL; + + if (needs_rebuild) + vf->vf_ops->create_vsi(vf); + + ice_ena_vf_mappings(vf); + ice_put_vf(vf); + + return -EINVAL; +} + +/** * ice_sriov_configure - Enable or change number of VFs via sysfs * @pdev: pointer to a pci_dev structure * @num_vfs: number of VFs to allocate or 0 to free VFs @@ -1709,31 +1936,16 @@ void ice_print_vfs_mdd_events(struct ice_pf *pf) /** * ice_restore_all_vfs_msi_state - restore VF MSI state after PF FLR - * @pdev: pointer to a pci_dev structure + * @pf: pointer to the PF structure * * Called when recovering from a PF FLR to restore interrupt capability to * the VFs. */ -void ice_restore_all_vfs_msi_state(struct pci_dev *pdev) +void ice_restore_all_vfs_msi_state(struct ice_pf *pf) { - u16 vf_id; - int pos; - - if (!pci_num_vf(pdev)) - return; + struct ice_vf *vf; + u32 bkt; - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV); - if (pos) { - struct pci_dev *vfdev; - - pci_read_config_word(pdev, pos + PCI_SRIOV_VF_DID, - &vf_id); - vfdev = pci_get_device(pdev->vendor, vf_id, NULL); - while (vfdev) { - if (vfdev->is_virtfn && vfdev->physfn == pdev) - pci_restore_msi_state(vfdev); - vfdev = pci_get_device(pdev->vendor, vf_id, - vfdev); - } - } + ice_for_each_vf(pf, bkt, vf) + pci_restore_msi_state(vf->vfdev); } diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.h b/drivers/net/ethernet/intel/ice/ice_sriov.h index 346cb2666f3a..8488df38b586 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.h +++ b/drivers/net/ethernet/intel/ice/ice_sriov.h @@ -33,7 +33,7 @@ int ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi); void ice_free_vfs(struct ice_pf *pf); -void ice_restore_all_vfs_msi_state(struct pci_dev *pdev); +void ice_restore_all_vfs_msi_state(struct ice_pf *pf); int ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, @@ -60,6 +60,8 @@ void ice_print_vfs_mdd_events(struct ice_pf *pf); void ice_print_vf_rx_mdd_event(struct ice_vf *vf); bool ice_vc_validate_pattern(struct ice_vf *vf, struct virtchnl_proto_hdrs *proto); +u32 ice_sriov_get_vf_total_msix(struct pci_dev *pdev); +int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count); #else /* CONFIG_PCI_IOV */ static inline void ice_process_vflr_event(struct ice_pf *pf) { } static inline void ice_free_vfs(struct ice_pf *pf) { } @@ -67,7 +69,7 @@ static inline void ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event) { } static inline void ice_print_vfs_mdd_events(struct ice_pf *pf) { } static inline void ice_print_vf_rx_mdd_event(struct ice_vf *vf) { } -static inline void ice_restore_all_vfs_msi_state(struct pci_dev *pdev) { } +static inline void ice_restore_all_vfs_msi_state(struct ice_pf *pf) { } static inline int ice_sriov_configure(struct pci_dev __always_unused *pdev, @@ -142,5 +144,16 @@ ice_get_vf_stats(struct net_device __always_unused *netdev, { return -EOPNOTSUPP; } + +static inline u32 ice_sriov_get_vf_total_msix(struct pci_dev *pdev) +{ + return 0; +} + +static inline int +ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_PCI_IOV */ #endif /* _ICE_SRIOV_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 6db4ca7978cb..ee19f3aa3d19 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -20,12 +20,11 @@ * byte 0 = 0x2: to identify it as locally administered DA MAC * byte 6 = 0x2: to identify it as locally administered SA MAC * byte 12 = 0x81 & byte 13 = 0x00: - * In case of VLAN filter first two bytes defines ether type (0x8100) - * and remaining two bytes are placeholder for programming a given VLAN ID - * In case of Ether type filter it is treated as header without VLAN tag - * and byte 12 and 13 is used to program a given Ether type instead + * In case of VLAN filter first two bytes defines ether type (0x8100) + * and remaining two bytes are placeholder for programming a given VLAN ID + * In case of Ether type filter it is treated as header without VLAN tag + * and byte 12 and 13 is used to program a given Ether type instead */ -#define DUMMY_ETH_HDR_LEN 16 static const u8 dummy_eth_header[DUMMY_ETH_HDR_LEN] = { 0x2, 0, 0, 0, 0, 0, 0x2, 0, 0, 0, 0, 0, 0x81, 0, 0, 0}; @@ -1369,14 +1368,6 @@ static const struct ice_dummy_pkt_profile ice_dummy_pkt_profiles[] = { ICE_PKT_PROFILE(tcp, 0), }; -#define ICE_SW_RULE_RX_TX_HDR_SIZE(s, l) struct_size((s), hdr_data, (l)) -#define ICE_SW_RULE_RX_TX_ETH_HDR_SIZE(s) \ - ICE_SW_RULE_RX_TX_HDR_SIZE((s), DUMMY_ETH_HDR_LEN) -#define ICE_SW_RULE_RX_TX_NO_HDR_SIZE(s) \ - ICE_SW_RULE_RX_TX_HDR_SIZE((s), 0) -#define ICE_SW_RULE_LG_ACT_SIZE(s, n) struct_size((s), act, (n)) -#define ICE_SW_RULE_VSI_LIST_SIZE(s, n) struct_size((s), vsi, (n)) - /* this is a recipe to profile association bitmap */ static DECLARE_BITMAP(recipe_to_profile[ICE_MAX_NUM_RECIPES], ICE_MAX_NUM_PROFILES); @@ -1821,15 +1812,11 @@ ice_aq_alloc_free_vsi_list(struct ice_hw *hw, u16 *vsi_list_id, enum ice_sw_lkup_type lkup_type, enum ice_adminq_opc opc) { - struct ice_aqc_alloc_free_res_elem *sw_buf; + DEFINE_FLEX(struct ice_aqc_alloc_free_res_elem, sw_buf, elem, 1); + u16 buf_len = __struct_size(sw_buf); struct ice_aqc_res_elem *vsi_ele; - u16 buf_len; int status; - buf_len = struct_size(sw_buf, elem, 1); - sw_buf = devm_kzalloc(ice_hw_to_dev(hw), buf_len, GFP_KERNEL); - if (!sw_buf) - return -ENOMEM; sw_buf->num_elems = cpu_to_le16(1); if (lkup_type == ICE_SW_LKUP_MAC || @@ -1841,28 +1828,30 @@ ice_aq_alloc_free_vsi_list(struct ice_hw *hw, u16 *vsi_list_id, lkup_type == ICE_SW_LKUP_DFLT) { sw_buf->res_type = cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_REP); } else if (lkup_type == ICE_SW_LKUP_VLAN) { - sw_buf->res_type = - cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_PRUNE); + if (opc == ice_aqc_opc_alloc_res) + sw_buf->res_type = + cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_PRUNE | + ICE_AQC_RES_TYPE_FLAG_SHARED); + else + sw_buf->res_type = + cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_PRUNE); } else { - status = -EINVAL; - goto ice_aq_alloc_free_vsi_list_exit; + return -EINVAL; } if (opc == ice_aqc_opc_free_res) sw_buf->elem[0].e.sw_resp = cpu_to_le16(*vsi_list_id); - status = ice_aq_alloc_free_res(hw, 1, sw_buf, buf_len, opc, NULL); + status = ice_aq_alloc_free_res(hw, sw_buf, buf_len, opc); if (status) - goto ice_aq_alloc_free_vsi_list_exit; + return status; if (opc == ice_aqc_opc_alloc_res) { vsi_ele = &sw_buf->elem[0]; *vsi_list_id = le16_to_cpu(vsi_ele->e.sw_resp); } -ice_aq_alloc_free_vsi_list_exit: - devm_kfree(ice_hw_to_dev(hw), sw_buf); - return status; + return 0; } /** @@ -1910,7 +1899,7 @@ ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz, * * Add(0x0290) */ -static int +int ice_aq_add_recipe(struct ice_hw *hw, struct ice_aqc_recipe_data_elem *s_recipe_list, u16 num_recipes, struct ice_sq_cd *cd) @@ -1947,7 +1936,7 @@ ice_aq_add_recipe(struct ice_hw *hw, * The caller must supply enough space in s_recipe_list to hold all possible * recipes and *num_recipes must equal ICE_MAX_NUM_RECIPES. */ -static int +int ice_aq_get_recipe(struct ice_hw *hw, struct ice_aqc_recipe_data_elem *s_recipe_list, u16 *num_recipes, u16 recipe_root, struct ice_sq_cd *cd) @@ -2040,7 +2029,7 @@ error_out: * @cd: pointer to command details structure or NULL * Recipe to profile association (0x0291) */ -static int +int ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, struct ice_sq_cd *cd) { @@ -2066,7 +2055,7 @@ ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, * @cd: pointer to command details structure or NULL * Associate profile ID with given recipe (0x0293) */ -static int +int ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, struct ice_sq_cd *cd) { @@ -2090,26 +2079,20 @@ ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, * @hw: pointer to the hardware structure * @rid: recipe ID returned as response to AQ call */ -static int ice_alloc_recipe(struct ice_hw *hw, u16 *rid) +int ice_alloc_recipe(struct ice_hw *hw, u16 *rid) { - struct ice_aqc_alloc_free_res_elem *sw_buf; - u16 buf_len; + DEFINE_FLEX(struct ice_aqc_alloc_free_res_elem, sw_buf, elem, 1); + u16 buf_len = __struct_size(sw_buf); int status; - buf_len = struct_size(sw_buf, elem, 1); - sw_buf = kzalloc(buf_len, GFP_KERNEL); - if (!sw_buf) - return -ENOMEM; - sw_buf->num_elems = cpu_to_le16(1); sw_buf->res_type = cpu_to_le16((ICE_AQC_RES_TYPE_RECIPE << ICE_AQC_RES_TYPE_S) | ICE_AQC_RES_TYPE_FLAG_SHARED); - status = ice_aq_alloc_free_res(hw, 1, sw_buf, buf_len, - ice_aqc_opc_alloc_res, NULL); + status = ice_aq_alloc_free_res(hw, sw_buf, buf_len, + ice_aqc_opc_alloc_res); if (!status) *rid = le16_to_cpu(sw_buf->elem[0].e.sw_resp); - kfree(sw_buf); return status; } @@ -2272,6 +2255,10 @@ ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid, /* Propagate some data to the recipe database */ recps[idx].is_root = !!is_root; recps[idx].priority = root_bufs.content.act_ctrl_fwd_priority; + recps[idx].need_pass_l2 = root_bufs.content.act_ctrl & + ICE_AQ_RECIPE_ACT_NEED_PASS_L2; + recps[idx].allow_pass_l2 = root_bufs.content.act_ctrl & + ICE_AQ_RECIPE_ACT_ALLOW_PASS_L2; bitmap_zero(recps[idx].res_idxs, ICE_MAX_FV_WORDS); if (root_bufs.content.result_indx & ICE_AQ_RECIPE_RESULT_EN) { recps[idx].chain_idx = root_bufs.content.result_indx & @@ -2460,6 +2447,15 @@ static void ice_fill_sw_info(struct ice_hw *hw, struct ice_fltr_info *fi) } /** + * ice_fill_eth_hdr - helper to copy dummy_eth_hdr into supplied buffer + * @eth_hdr: pointer to buffer to populate + */ +void ice_fill_eth_hdr(u8 *eth_hdr) +{ + memcpy(eth_hdr, dummy_eth_header, DUMMY_ETH_HDR_LEN); +} + +/** * ice_fill_sw_rule - Helper function to fill switch rule structure * @hw: pointer to the hardware structure * @f_info: entry containing packet forwarding information @@ -3118,7 +3114,7 @@ ice_find_rule_entry(struct ice_hw *hw, u8 recp_id, struct ice_fltr_info *f_info) * handle element. This can be extended further to search VSI list with more * than 1 vsi_count. Returns pointer to VSI list entry if found. */ -static struct ice_vsi_list_map_info * +struct ice_vsi_list_map_info * ice_find_vsi_list_entry(struct ice_hw *hw, u8 recp_id, u16 vsi_handle, u16 *vsi_list_id) { @@ -3129,7 +3125,7 @@ ice_find_vsi_list_entry(struct ice_hw *hw, u8 recp_id, u16 vsi_handle, list_head = &sw->recp_list[recp_id].filt_rules; list_for_each_entry(list_itr, list_head, list_entry) { - if (list_itr->vsi_count == 1 && list_itr->vsi_list_info) { + if (list_itr->vsi_list_info) { map_info = list_itr->vsi_list_info; if (test_bit(vsi_handle, map_info->vsi_map)) { *vsi_list_id = map_info->vsi_list_id; @@ -3400,54 +3396,6 @@ exit: } /** - * ice_mac_fltr_exist - does this MAC filter exist for given VSI - * @hw: pointer to the hardware structure - * @mac: MAC address to be checked (for MAC filter) - * @vsi_handle: check MAC filter for this VSI - */ -bool ice_mac_fltr_exist(struct ice_hw *hw, u8 *mac, u16 vsi_handle) -{ - struct ice_fltr_mgmt_list_entry *entry; - struct list_head *rule_head; - struct ice_switch_info *sw; - struct mutex *rule_lock; /* Lock to protect filter rule list */ - u16 hw_vsi_id; - - if (!ice_is_vsi_valid(hw, vsi_handle)) - return false; - - hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); - sw = hw->switch_info; - rule_head = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rules; - if (!rule_head) - return false; - - rule_lock = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rule_lock; - mutex_lock(rule_lock); - list_for_each_entry(entry, rule_head, list_entry) { - struct ice_fltr_info *f_info = &entry->fltr_info; - u8 *mac_addr = &f_info->l_data.mac.mac_addr[0]; - - if (is_zero_ether_addr(mac_addr)) - continue; - - if (f_info->flag != ICE_FLTR_TX || - f_info->src_id != ICE_SRC_ID_VSI || - f_info->lkup_type != ICE_SW_LKUP_MAC || - f_info->fltr_act != ICE_FWD_TO_VSI || - hw_vsi_id != f_info->fwd_id.hw_vsi_id) - continue; - - if (ether_addr_equal(mac, mac_addr)) { - mutex_unlock(rule_lock); - return true; - } - } - mutex_unlock(rule_lock); - return false; -} - -/** * ice_vlan_fltr_exist - does this VLAN filter exist for given VSI * @hw: pointer to the hardware structure * @vlan_id: VLAN ID @@ -4473,29 +4421,19 @@ int ice_alloc_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, u16 *counter_id) { - struct ice_aqc_alloc_free_res_elem *buf; - u16 buf_len; + DEFINE_FLEX(struct ice_aqc_alloc_free_res_elem, buf, elem, 1); + u16 buf_len = __struct_size(buf); int status; - /* Allocate resource */ - buf_len = struct_size(buf, elem, 1); - buf = kzalloc(buf_len, GFP_KERNEL); - if (!buf) - return -ENOMEM; - buf->num_elems = cpu_to_le16(num_items); buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) & ICE_AQC_RES_TYPE_M) | alloc_shared); - status = ice_aq_alloc_free_res(hw, 1, buf, buf_len, - ice_aqc_opc_alloc_res, NULL); + status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_alloc_res); if (status) - goto exit; + return status; *counter_id = le16_to_cpu(buf->elem[0].e.sw_resp); - -exit: - kfree(buf); return status; } @@ -4511,27 +4449,19 @@ int ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, u16 counter_id) { - struct ice_aqc_alloc_free_res_elem *buf; - u16 buf_len; + DEFINE_FLEX(struct ice_aqc_alloc_free_res_elem, buf, elem, 1); + u16 buf_len = __struct_size(buf); int status; - /* Free resource */ - buf_len = struct_size(buf, elem, 1); - buf = kzalloc(buf_len, GFP_KERNEL); - if (!buf) - return -ENOMEM; - buf->num_elems = cpu_to_le16(num_items); buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) & ICE_AQC_RES_TYPE_M) | alloc_shared); buf->elem[0].e.sw_resp = cpu_to_le16(counter_id); - status = ice_aq_alloc_free_res(hw, 1, buf, buf_len, - ice_aqc_opc_free_res, NULL); + status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_free_res); if (status) ice_debug(hw, ICE_DBG_SW, "counter resource could not be freed\n"); - kfree(buf); return status; } @@ -4540,6 +4470,39 @@ ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, .offs = {__VA_ARGS__}, \ } +/** + * ice_share_res - set a resource as shared or dedicated + * @hw: hw struct of original owner of resource + * @type: resource type + * @shared: is the resource being set to shared + * @res_id: resource id (descriptor) + */ +int ice_share_res(struct ice_hw *hw, u16 type, u8 shared, u16 res_id) +{ + DEFINE_FLEX(struct ice_aqc_alloc_free_res_elem, buf, elem, 1); + u16 buf_len = __struct_size(buf); + int status; + + buf->num_elems = cpu_to_le16(1); + if (shared) + buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) & + ICE_AQC_RES_TYPE_M) | + ICE_AQC_RES_TYPE_FLAG_SHARED); + else + buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) & + ICE_AQC_RES_TYPE_M) & + ~ICE_AQC_RES_TYPE_FLAG_SHARED); + + buf->elem[0].e.sw_resp = cpu_to_le16(res_id); + status = ice_aq_alloc_free_res(hw, buf, buf_len, + ice_aqc_opc_share_res); + if (status) + ice_debug(hw, ICE_DBG_SW, "Could not set resource type %u id %u to %s\n", + type, res_id, shared ? "SHARED" : "DEDICATED"); + + return status; +} + /* This is mapping table entry that maps every word within a given protocol * structure to the real byte offset as per the specification of that * protocol header. @@ -4613,13 +4576,13 @@ static struct ice_protocol_entry ice_prot_id_tbl[ICE_PROTOCOL_LAST] = { * ice_find_recp - find a recipe * @hw: pointer to the hardware structure * @lkup_exts: extension sequence to match - * @tun_type: type of recipe tunnel + * @rinfo: information regarding the rule e.g. priority and action info * * Returns index of matching recipe, or ICE_MAX_NUM_RECIPES if not found. */ static u16 ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts, - enum ice_sw_tunnel_type tun_type) + const struct ice_adv_rule_info *rinfo) { bool refresh_required = true; struct ice_sw_recipe *recp; @@ -4680,9 +4643,12 @@ ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts, } /* If for "i"th recipe the found was never set to false * then it means we found our match - * Also tun type of recipe needs to be checked + * Also tun type and *_pass_l2 of recipe needs to be + * checked */ - if (found && recp[i].tun_type == tun_type) + if (found && recp[i].tun_type == rinfo->tun_type && + recp[i].need_pass_l2 == rinfo->need_pass_l2 && + recp[i].allow_pass_l2 == rinfo->allow_pass_l2) return i; /* Return the recipe ID */ } } @@ -4952,6 +4918,7 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, unsigned long *profiles) { DECLARE_BITMAP(result_idx_bm, ICE_MAX_FV_WORDS); + struct ice_aqc_recipe_content *content; struct ice_aqc_recipe_data_elem *tmp; struct ice_aqc_recipe_data_elem *buf; struct ice_recp_grp_entry *entry; @@ -5012,6 +4979,8 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, if (status) goto err_unroll; + content = &buf[recps].content; + /* Clear the result index of the located recipe, as this will be * updated, if needed, later in the recipe creation process. */ @@ -5022,26 +4991,24 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, /* if the recipe is a non-root recipe RID should be programmed * as 0 for the rules to be applied correctly. */ - buf[recps].content.rid = 0; - memset(&buf[recps].content.lkup_indx, 0, - sizeof(buf[recps].content.lkup_indx)); + content->rid = 0; + memset(&content->lkup_indx, 0, + sizeof(content->lkup_indx)); /* All recipes use look-up index 0 to match switch ID. */ - buf[recps].content.lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX; - buf[recps].content.mask[0] = - cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK); + content->lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX; + content->mask[0] = cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK); /* Setup lkup_indx 1..4 to INVALID/ignore and set the mask * to be 0 */ for (i = 1; i <= ICE_NUM_WORDS_RECIPE; i++) { - buf[recps].content.lkup_indx[i] = 0x80; - buf[recps].content.mask[i] = 0; + content->lkup_indx[i] = 0x80; + content->mask[i] = 0; } for (i = 0; i < entry->r_group.n_val_pairs; i++) { - buf[recps].content.lkup_indx[i + 1] = entry->fv_idx[i]; - buf[recps].content.mask[i + 1] = - cpu_to_le16(entry->fv_mask[i]); + content->lkup_indx[i + 1] = entry->fv_idx[i]; + content->mask[i + 1] = cpu_to_le16(entry->fv_mask[i]); } if (rm->n_grp_count > 1) { @@ -5055,7 +5022,7 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, } entry->chain_idx = chain_idx; - buf[recps].content.result_indx = + content->result_indx = ICE_AQ_RECIPE_RESULT_EN | ((chain_idx << ICE_AQ_RECIPE_RESULT_DATA_S) & ICE_AQ_RECIPE_RESULT_DATA_M); @@ -5069,7 +5036,13 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, ICE_MAX_NUM_RECIPES); set_bit(buf[recps].recipe_indx, (unsigned long *)buf[recps].recipe_bitmap); - buf[recps].content.act_ctrl_fwd_priority = rm->priority; + content->act_ctrl_fwd_priority = rm->priority; + + if (rm->need_pass_l2) + content->act_ctrl |= ICE_AQ_RECIPE_ACT_NEED_PASS_L2; + + if (rm->allow_pass_l2) + content->act_ctrl |= ICE_AQ_RECIPE_ACT_ALLOW_PASS_L2; recps++; } @@ -5107,9 +5080,11 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, if (status) goto err_unroll; + content = &buf[recps].content; + buf[recps].recipe_indx = (u8)rid; - buf[recps].content.rid = (u8)rid; - buf[recps].content.rid |= ICE_AQ_RECIPE_ID_IS_ROOT; + content->rid = (u8)rid; + content->rid |= ICE_AQ_RECIPE_ID_IS_ROOT; /* the new entry created should also be part of rg_list to * make sure we have complete recipe */ @@ -5121,16 +5096,13 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, goto err_unroll; } last_chain_entry->rid = rid; - memset(&buf[recps].content.lkup_indx, 0, - sizeof(buf[recps].content.lkup_indx)); + memset(&content->lkup_indx, 0, sizeof(content->lkup_indx)); /* All recipes use look-up index 0 to match switch ID. */ - buf[recps].content.lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX; - buf[recps].content.mask[0] = - cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK); + content->lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX; + content->mask[0] = cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK); for (i = 1; i <= ICE_NUM_WORDS_RECIPE; i++) { - buf[recps].content.lkup_indx[i] = - ICE_AQ_RECIPE_LKUP_IGNORE; - buf[recps].content.mask[i] = 0; + content->lkup_indx[i] = ICE_AQ_RECIPE_LKUP_IGNORE; + content->mask[i] = 0; } i = 1; @@ -5142,8 +5114,8 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, last_chain_entry->chain_idx = ICE_INVAL_CHAIN_IND; list_for_each_entry(entry, &rm->rg_list, l_entry) { last_chain_entry->fv_idx[i] = entry->chain_idx; - buf[recps].content.lkup_indx[i] = entry->chain_idx; - buf[recps].content.mask[i++] = cpu_to_le16(0xFFFF); + content->lkup_indx[i] = entry->chain_idx; + content->mask[i++] = cpu_to_le16(0xFFFF); set_bit(entry->rid, rm->r_bitmap); } list_add(&last_chain_entry->l_entry, &rm->rg_list); @@ -5155,7 +5127,7 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, status = -EINVAL; goto err_unroll; } - buf[recps].content.act_ctrl_fwd_priority = rm->priority; + content->act_ctrl_fwd_priority = rm->priority; recps++; rm->root_rid = (u8)rid; @@ -5220,6 +5192,8 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, recp->priority = buf[buf_idx].content.act_ctrl_fwd_priority; recp->n_grp_count = rm->n_grp_count; recp->tun_type = rm->tun_type; + recp->need_pass_l2 = rm->need_pass_l2; + recp->allow_pass_l2 = rm->allow_pass_l2; recp->recp_created = true; } rm->root_buf = buf; @@ -5388,6 +5362,9 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, /* set the recipe priority if specified */ rm->priority = (u8)rinfo->priority; + rm->need_pass_l2 = rinfo->need_pass_l2; + rm->allow_pass_l2 = rinfo->allow_pass_l2; + /* Find offsets from the field vector. Pick the first one for all the * recipes. */ @@ -5403,7 +5380,7 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, } /* Look for a recipe which matches our requested fv / mask list */ - *rid = ice_find_recp(hw, lkup_exts, rinfo->tun_type); + *rid = ice_find_recp(hw, lkup_exts, rinfo); if (*rid < ICE_MAX_NUM_RECIPES) /* Success if found a recipe that match the existing criteria */ goto err_unroll; @@ -5839,7 +5816,9 @@ static bool ice_rules_equal(const struct ice_adv_rule_info *first, return first->sw_act.flag == second->sw_act.flag && first->tun_type == second->tun_type && first->vlan_type == second->vlan_type && - first->src_vsi == second->src_vsi; + first->src_vsi == second->src_vsi && + first->need_pass_l2 == second->need_pass_l2 && + first->allow_pass_l2 == second->allow_pass_l2; } /** @@ -5994,14 +5973,21 @@ ice_adv_add_update_vsi_list(struct ice_hw *hw, void ice_rule_add_tunnel_metadata(struct ice_adv_lkup_elem *lkup) { lkup->type = ICE_HW_METADATA; - lkup->m_u.metadata.flags[ICE_PKT_FLAGS_TUNNEL] = + lkup->m_u.metadata.flags[ICE_PKT_FLAGS_MDID21] |= cpu_to_be16(ICE_PKT_TUNNEL_MASK); } +void ice_rule_add_direction_metadata(struct ice_adv_lkup_elem *lkup) +{ + lkup->type = ICE_HW_METADATA; + lkup->m_u.metadata.flags[ICE_PKT_FLAGS_MDID20] |= + cpu_to_be16(ICE_PKT_FROM_NETWORK); +} + void ice_rule_add_vlan_metadata(struct ice_adv_lkup_elem *lkup) { lkup->type = ICE_HW_METADATA; - lkup->m_u.metadata.flags[ICE_PKT_FLAGS_VLAN] = + lkup->m_u.metadata.flags[ICE_PKT_FLAGS_MDID20] |= cpu_to_be16(ICE_PKT_VLAN_MASK); } @@ -6078,7 +6064,8 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, if (!(rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI || rinfo->sw_act.fltr_act == ICE_FWD_TO_Q || rinfo->sw_act.fltr_act == ICE_FWD_TO_QGRP || - rinfo->sw_act.fltr_act == ICE_DROP_PACKET)) { + rinfo->sw_act.fltr_act == ICE_DROP_PACKET || + rinfo->sw_act.fltr_act == ICE_NOP)) { status = -EIO; goto free_pkt_profile; } @@ -6089,7 +6076,8 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, goto free_pkt_profile; } - if (rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI) + if (rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI || + rinfo->sw_act.fltr_act == ICE_NOP) rinfo->sw_act.fwd_id.hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); @@ -6159,6 +6147,11 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_DROP | ICE_SINGLE_ACT_VALID_BIT; break; + case ICE_NOP: + act |= FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M, + rinfo->sw_act.fwd_id.hw_vsi_id); + act &= ~ICE_SINGLE_ACT_VALID_BIT; + break; default: status = -EIO; goto err_ice_add_adv_rule; @@ -6439,7 +6432,7 @@ ice_rem_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, return -EIO; } - rid = ice_find_recp(hw, &lkup_exts, rinfo->tun_type); + rid = ice_find_recp(hw, &lkup_exts, rinfo); /* If did not find a recipe that match the existing criteria */ if (rid == ICE_MAX_NUM_RECIPES) return -EINVAL; @@ -6533,59 +6526,6 @@ ice_rem_adv_rule_by_id(struct ice_hw *hw, } /** - * ice_rem_adv_rule_for_vsi - removes existing advanced switch rules for a - * given VSI handle - * @hw: pointer to the hardware structure - * @vsi_handle: VSI handle for which we are supposed to remove all the rules. - * - * This function is used to remove all the rules for a given VSI and as soon - * as removing a rule fails, it will return immediately with the error code, - * else it will return success. - */ -int ice_rem_adv_rule_for_vsi(struct ice_hw *hw, u16 vsi_handle) -{ - struct ice_adv_fltr_mgmt_list_entry *list_itr, *tmp_entry; - struct ice_vsi_list_map_info *map_info; - struct ice_adv_rule_info rinfo; - struct list_head *list_head; - struct ice_switch_info *sw; - int status; - u8 rid; - - sw = hw->switch_info; - for (rid = 0; rid < ICE_MAX_NUM_RECIPES; rid++) { - if (!sw->recp_list[rid].recp_created) - continue; - if (!sw->recp_list[rid].adv_rule) - continue; - - list_head = &sw->recp_list[rid].filt_rules; - list_for_each_entry_safe(list_itr, tmp_entry, list_head, - list_entry) { - rinfo = list_itr->rule_info; - - if (rinfo.sw_act.fltr_act == ICE_FWD_TO_VSI_LIST) { - map_info = list_itr->vsi_list_info; - if (!map_info) - continue; - - if (!test_bit(vsi_handle, map_info->vsi_map)) - continue; - } else if (rinfo.sw_act.vsi_handle != vsi_handle) { - continue; - } - - rinfo.sw_act.vsi_handle = vsi_handle; - status = ice_rem_adv_rule(hw, list_itr->lkups, - list_itr->lkups_cnt, &rinfo); - if (status) - return status; - } - } - return 0; -} - -/** * ice_replay_vsi_adv_rule - Replay advanced rule for requested VSI * @hw: pointer to the hardware structure * @vsi_handle: driver VSI handle diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index c84b56fe84a5..db7e501b7e0a 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -22,6 +22,16 @@ #define ICE_PROFID_IPV6_GTPU_TEID 46 #define ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER 70 +#define ICE_SW_RULE_VSI_LIST_SIZE(s, n) struct_size((s), vsi, (n)) +#define ICE_SW_RULE_RX_TX_HDR_SIZE(s, l) struct_size((s), hdr_data, (l)) +#define ICE_SW_RULE_RX_TX_ETH_HDR_SIZE(s) \ + ICE_SW_RULE_RX_TX_HDR_SIZE((s), DUMMY_ETH_HDR_LEN) +#define ICE_SW_RULE_RX_TX_NO_HDR_SIZE(s) \ + ICE_SW_RULE_RX_TX_HDR_SIZE((s), 0) +#define ICE_SW_RULE_LG_ACT_SIZE(s, n) struct_size((s), act, (n)) + +#define DUMMY_ETH_HDR_LEN 16 + /* VSI context structure for add/get/update/free operations */ struct ice_vsi_ctx { u16 vsi_num; @@ -191,6 +201,8 @@ struct ice_adv_rule_info { u16 vlan_type; u16 fltr_rule_id; u32 priority; + u16 need_pass_l2:1; + u16 allow_pass_l2:1; u16 src_vsi; struct ice_sw_act_ctrl sw_act; struct ice_adv_rule_flags_info flags_info; @@ -254,6 +266,9 @@ struct ice_sw_recipe { */ u8 priority; + u8 need_pass_l2:1; + u8 allow_pass_l2:1; + struct list_head rg_list; /* AQ buffer associated with this recipe */ @@ -340,9 +355,11 @@ ice_alloc_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, int ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, u16 counter_id); +int ice_share_res(struct ice_hw *hw, u16 type, u8 shared, u16 res_id); /* Switch/bridge related commands */ void ice_rule_add_tunnel_metadata(struct ice_adv_lkup_elem *lkup); +void ice_rule_add_direction_metadata(struct ice_adv_lkup_elem *lkup); void ice_rule_add_vlan_metadata(struct ice_adv_lkup_elem *lkup); void ice_rule_add_src_vsi_metadata(struct ice_adv_lkup_elem *lkup); int @@ -354,7 +371,6 @@ int ice_add_vlan(struct ice_hw *hw, struct list_head *m_list); int ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list); int ice_add_mac(struct ice_hw *hw, struct list_head *m_lst); int ice_remove_mac(struct ice_hw *hw, struct list_head *m_lst); -bool ice_mac_fltr_exist(struct ice_hw *hw, u8 *mac, u16 vsi_handle); bool ice_vlan_fltr_exist(struct ice_hw *hw, u16 vlan_id, u16 vsi_handle); int ice_add_eth_mac(struct ice_hw *hw, struct list_head *em_list); int ice_remove_eth_mac(struct ice_hw *hw, struct list_head *em_list); @@ -379,7 +395,6 @@ int ice_set_vlan_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, bool rm_vlan_promisc); -int ice_rem_adv_rule_for_vsi(struct ice_hw *hw, u16 vsi_handle); int ice_rem_adv_rule_by_id(struct ice_hw *hw, struct ice_rule_query_data *remove_entry); @@ -389,6 +404,7 @@ u16 ice_get_hw_vsi_num(struct ice_hw *hw, u16 vsi_handle); int ice_replay_vsi_all_fltr(struct ice_hw *hw, u16 vsi_handle); void ice_rm_all_sw_replay_rule_info(struct ice_hw *hw); +void ice_fill_eth_hdr(u8 *eth_hdr); int ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz, @@ -397,4 +413,21 @@ int ice_update_recipe_lkup_idx(struct ice_hw *hw, struct ice_update_recipe_lkup_idx_params *params); void ice_change_proto_id_to_dvm(void); +struct ice_vsi_list_map_info * +ice_find_vsi_list_entry(struct ice_hw *hw, u8 recp_id, u16 vsi_handle, + u16 *vsi_list_id); +int ice_alloc_recipe(struct ice_hw *hw, u16 *rid); +int ice_aq_get_recipe(struct ice_hw *hw, + struct ice_aqc_recipe_data_elem *s_recipe_list, + u16 *num_recipes, u16 recipe_root, struct ice_sq_cd *cd); +int ice_aq_add_recipe(struct ice_hw *hw, + struct ice_aqc_recipe_data_elem *s_recipe_list, + u16 num_recipes, struct ice_sq_cd *cd); +int +ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, + struct ice_sq_cd *cd); +int +ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, + struct ice_sq_cd *cd); + #endif /* _ICE_SWITCH_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index 4a34ef5f58d3..dd03cb69ad26 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -7,6 +7,8 @@ #include "ice_lib.h" #include "ice_protocol_type.h" +#define ICE_TC_METADATA_LKUP_IDX 0 + /** * ice_tc_count_lkups - determine lookup count for switch filter * @flags: TC-flower flags @@ -19,7 +21,13 @@ static int ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, struct ice_tc_flower_fltr *fltr) { - int lkups_cnt = 0; + int lkups_cnt = 1; /* 0th lookup is metadata */ + + /* Always add metadata as the 0th lookup. Included elements: + * - Direction flag (always present) + * - ICE_TC_FLWR_FIELD_VLAN_TPID (present if specified) + * - Tunnel flag (present if tunnel) + */ if (flags & ICE_TC_FLWR_FIELD_TENANT_ID) lkups_cnt++; @@ -54,10 +62,6 @@ ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, if (flags & (ICE_TC_FLWR_FIELD_VLAN | ICE_TC_FLWR_FIELD_VLAN_PRIO)) lkups_cnt++; - /* is VLAN TPID specified */ - if (flags & ICE_TC_FLWR_FIELD_VLAN_TPID) - lkups_cnt++; - /* is CVLAN specified? */ if (flags & (ICE_TC_FLWR_FIELD_CVLAN | ICE_TC_FLWR_FIELD_CVLAN_PRIO)) lkups_cnt++; @@ -84,10 +88,6 @@ ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, ICE_TC_FLWR_FIELD_SRC_L4_PORT)) lkups_cnt++; - /* matching for tunneled packets in metadata */ - if (fltr->tunnel_type != TNL_LAST) - lkups_cnt++; - return lkups_cnt; } @@ -176,10 +176,9 @@ static u16 ice_check_supported_vlan_tpid(u16 vlan_tpid) static int ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr, - struct ice_adv_lkup_elem *list) + struct ice_adv_lkup_elem *list, int i) { struct ice_tc_flower_lyr_2_4_hdrs *hdr = &fltr->outer_headers; - int i = 0; if (flags & ICE_TC_FLWR_FIELD_TENANT_ID) { u32 tenant_id; @@ -329,8 +328,7 @@ ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr, } /* always fill matching on tunneled packets in metadata */ - ice_rule_add_tunnel_metadata(&list[i]); - i++; + ice_rule_add_tunnel_metadata(&list[ICE_TC_METADATA_LKUP_IDX]); return i; } @@ -358,13 +356,16 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers = &tc_fltr->outer_headers; bool inner = false; u16 vlan_tpid = 0; - int i = 0; + int i = 1; /* 0th lookup is metadata */ rule_info->vlan_type = vlan_tpid; + /* Always add direction metadata */ + ice_rule_add_direction_metadata(&list[ICE_TC_METADATA_LKUP_IDX]); + rule_info->tun_type = ice_sw_type_from_tunnel(tc_fltr->tunnel_type); if (tc_fltr->tunnel_type != TNL_LAST) { - i = ice_tc_fill_tunnel_outer(flags, tc_fltr, list); + i = ice_tc_fill_tunnel_outer(flags, tc_fltr, list, i); headers = &tc_fltr->inner_headers; inner = true; @@ -431,8 +432,7 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags, rule_info->vlan_type = ice_check_supported_vlan_tpid(vlan_tpid); - ice_rule_add_vlan_metadata(&list[i]); - i++; + ice_rule_add_vlan_metadata(&list[ICE_TC_METADATA_LKUP_IDX]); } if (flags & (ICE_TC_FLWR_FIELD_CVLAN | ICE_TC_FLWR_FIELD_CVLAN_PRIO)) { @@ -630,32 +630,83 @@ bool ice_is_tunnel_supported(struct net_device *dev) return ice_tc_tun_get_type(dev) != TNL_LAST; } -static int -ice_eswitch_tc_parse_action(struct ice_tc_flower_fltr *fltr, - struct flow_action_entry *act) +static bool ice_tc_is_dev_uplink(struct net_device *dev) +{ + return netif_is_ice(dev) || ice_is_tunnel_supported(dev); +} + +static int ice_tc_setup_redirect_action(struct net_device *filter_dev, + struct ice_tc_flower_fltr *fltr, + struct net_device *target_dev) { struct ice_repr *repr; + fltr->action.fltr_act = ICE_FWD_TO_VSI; + + if (ice_is_port_repr_netdev(filter_dev) && + ice_is_port_repr_netdev(target_dev)) { + repr = ice_netdev_to_repr(target_dev); + + fltr->dest_vsi = repr->src_vsi; + fltr->direction = ICE_ESWITCH_FLTR_EGRESS; + } else if (ice_is_port_repr_netdev(filter_dev) && + ice_tc_is_dev_uplink(target_dev)) { + repr = ice_netdev_to_repr(filter_dev); + + fltr->dest_vsi = repr->src_vsi->back->switchdev.uplink_vsi; + fltr->direction = ICE_ESWITCH_FLTR_EGRESS; + } else if (ice_tc_is_dev_uplink(filter_dev) && + ice_is_port_repr_netdev(target_dev)) { + repr = ice_netdev_to_repr(target_dev); + + fltr->dest_vsi = repr->src_vsi; + fltr->direction = ICE_ESWITCH_FLTR_INGRESS; + } else { + NL_SET_ERR_MSG_MOD(fltr->extack, + "Unsupported netdevice in switchdev mode"); + return -EINVAL; + } + + return 0; +} + +static int +ice_tc_setup_drop_action(struct net_device *filter_dev, + struct ice_tc_flower_fltr *fltr) +{ + fltr->action.fltr_act = ICE_DROP_PACKET; + + if (ice_is_port_repr_netdev(filter_dev)) { + fltr->direction = ICE_ESWITCH_FLTR_EGRESS; + } else if (ice_tc_is_dev_uplink(filter_dev)) { + fltr->direction = ICE_ESWITCH_FLTR_INGRESS; + } else { + NL_SET_ERR_MSG_MOD(fltr->extack, + "Unsupported netdevice in switchdev mode"); + return -EINVAL; + } + + return 0; +} + +static int ice_eswitch_tc_parse_action(struct net_device *filter_dev, + struct ice_tc_flower_fltr *fltr, + struct flow_action_entry *act) +{ + int err; + switch (act->id) { case FLOW_ACTION_DROP: - fltr->action.fltr_act = ICE_DROP_PACKET; + err = ice_tc_setup_drop_action(filter_dev, fltr); + if (err) + return err; + break; case FLOW_ACTION_REDIRECT: - fltr->action.fltr_act = ICE_FWD_TO_VSI; - - if (ice_is_port_repr_netdev(act->dev)) { - repr = ice_netdev_to_repr(act->dev); - - fltr->dest_vsi = repr->src_vsi; - fltr->direction = ICE_ESWITCH_FLTR_INGRESS; - } else if (netif_is_ice(act->dev) || - ice_is_tunnel_supported(act->dev)) { - fltr->direction = ICE_ESWITCH_FLTR_EGRESS; - } else { - NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported netdevice in switchdev mode"); - return -EINVAL; - } + err = ice_tc_setup_redirect_action(filter_dev, fltr, act->dev); + if (err) + return err; break; @@ -696,10 +747,6 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) goto exit; } - /* egress traffic is always redirect to uplink */ - if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS) - fltr->dest_vsi = vsi->back->switchdev.uplink_vsi; - rule_info.sw_act.fltr_act = fltr->action.fltr_act; if (fltr->action.fltr_act != ICE_DROP_PACKET) rule_info.sw_act.vsi_handle = fltr->dest_vsi->idx; @@ -713,13 +760,21 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) rule_info.flags_info.act_valid = true; if (fltr->direction == ICE_ESWITCH_FLTR_INGRESS) { + /* Uplink to VF */ rule_info.sw_act.flag |= ICE_FLTR_RX; rule_info.sw_act.src = hw->pf_id; rule_info.flags_info.act = ICE_SINGLE_ACT_LB_ENABLE; - } else { + } else if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS && + fltr->dest_vsi == vsi->back->switchdev.uplink_vsi) { + /* VF to Uplink */ rule_info.sw_act.flag |= ICE_FLTR_TX; rule_info.sw_act.src = vsi->idx; rule_info.flags_info.act = ICE_SINGLE_ACT_LAN_ENABLE; + } else { + /* VF to VF */ + rule_info.sw_act.flag |= ICE_FLTR_TX; + rule_info.sw_act.src = vsi->idx; + rule_info.flags_info.act = ICE_SINGLE_ACT_LB_ENABLE; } /* specify the cookie as filter_rule_id */ @@ -1343,24 +1398,24 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, dissector = rule->match.dissector; if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_VLAN) | - BIT(FLOW_DISSECTOR_KEY_CVLAN) | - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | - BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) | - BIT(FLOW_DISSECTOR_KEY_ENC_OPTS) | - BIT(FLOW_DISSECTOR_KEY_IP) | - BIT(FLOW_DISSECTOR_KEY_ENC_IP) | - BIT(FLOW_DISSECTOR_KEY_PORTS) | - BIT(FLOW_DISSECTOR_KEY_PPPOE) | - BIT(FLOW_DISSECTOR_KEY_L2TPV3))) { + ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_CVLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_OPTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IP) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP) | + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_PPPOE) | + BIT_ULL(FLOW_DISSECTOR_KEY_L2TPV3))) { NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported key used"); return -EOPNOTSUPP; } @@ -1382,10 +1437,10 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, */ headers = &fltr->inner_headers; } else if (dissector->used_keys & - (BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | - BIT(FLOW_DISSECTOR_KEY_ENC_PORTS))) { + (BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS))) { NL_SET_ERR_MSG_MOD(fltr->extack, "Tunnel key used, but device isn't a tunnel"); return -EOPNOTSUPP; } else { @@ -1745,16 +1800,17 @@ ice_tc_parse_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr, /** * ice_parse_tc_flower_actions - Parse the actions for a TC filter + * @filter_dev: Pointer to device on which filter is being added * @vsi: Pointer to VSI * @cls_flower: Pointer to TC flower offload structure * @fltr: Pointer to TC flower filter structure * * Parse the actions for a TC filter */ -static int -ice_parse_tc_flower_actions(struct ice_vsi *vsi, - struct flow_cls_offload *cls_flower, - struct ice_tc_flower_fltr *fltr) +static int ice_parse_tc_flower_actions(struct net_device *filter_dev, + struct ice_vsi *vsi, + struct flow_cls_offload *cls_flower, + struct ice_tc_flower_fltr *fltr) { struct flow_rule *rule = flow_cls_offload_flow_rule(cls_flower); struct flow_action *flow_action = &rule->action; @@ -1769,7 +1825,7 @@ ice_parse_tc_flower_actions(struct ice_vsi *vsi, flow_action_for_each(i, act, flow_action) { if (ice_is_eswitch_mode_switchdev(vsi->back)) - err = ice_eswitch_tc_parse_action(fltr, act); + err = ice_eswitch_tc_parse_action(filter_dev, fltr, act); else err = ice_tc_parse_action(vsi, fltr, act); if (err) @@ -1856,7 +1912,7 @@ ice_add_tc_fltr(struct net_device *netdev, struct ice_vsi *vsi, if (err < 0) goto err; - err = ice_parse_tc_flower_actions(vsi, f, fltr); + err = ice_parse_tc_flower_actions(netdev, vsi, f, fltr); if (err < 0) goto err; diff --git a/drivers/net/ethernet/intel/ice/ice_trace.h b/drivers/net/ethernet/intel/ice/ice_trace.h index ae98d5a8ff60..b2f5c9fe0149 100644 --- a/drivers/net/ethernet/intel/ice/ice_trace.h +++ b/drivers/net/ethernet/intel/ice/ice_trace.h @@ -21,6 +21,7 @@ #define _ICE_TRACE_H_ #include <linux/tracepoint.h> +#include "ice_eswitch_br.h" /* ice_trace() macro enables shared code to refer to trace points * like: @@ -240,6 +241,95 @@ DEFINE_TX_TSTAMP_OP_EVENT(ice_tx_tstamp_fw_req); DEFINE_TX_TSTAMP_OP_EVENT(ice_tx_tstamp_fw_done); DEFINE_TX_TSTAMP_OP_EVENT(ice_tx_tstamp_complete); +DECLARE_EVENT_CLASS(ice_esw_br_fdb_template, + TP_PROTO(struct ice_esw_br_fdb_entry *fdb), + TP_ARGS(fdb), + TP_STRUCT__entry(__array(char, dev_name, IFNAMSIZ) + __array(unsigned char, addr, ETH_ALEN) + __field(u16, vid) + __field(int, flags)), + TP_fast_assign(strscpy(__entry->dev_name, + netdev_name(fdb->dev), + IFNAMSIZ); + memcpy(__entry->addr, fdb->data.addr, ETH_ALEN); + __entry->vid = fdb->data.vid; + __entry->flags = fdb->flags;), + TP_printk("net_device=%s addr=%pM vid=%u flags=%x", + __entry->dev_name, + __entry->addr, + __entry->vid, + __entry->flags) +); + +DEFINE_EVENT(ice_esw_br_fdb_template, + ice_eswitch_br_fdb_entry_create, + TP_PROTO(struct ice_esw_br_fdb_entry *fdb), + TP_ARGS(fdb) +); + +DEFINE_EVENT(ice_esw_br_fdb_template, + ice_eswitch_br_fdb_entry_find_and_delete, + TP_PROTO(struct ice_esw_br_fdb_entry *fdb), + TP_ARGS(fdb) +); + +DECLARE_EVENT_CLASS(ice_esw_br_vlan_template, + TP_PROTO(struct ice_esw_br_vlan *vlan), + TP_ARGS(vlan), + TP_STRUCT__entry(__field(u16, vid) + __field(u16, flags)), + TP_fast_assign(__entry->vid = vlan->vid; + __entry->flags = vlan->flags;), + TP_printk("vid=%u flags=%x", + __entry->vid, + __entry->flags) +); + +DEFINE_EVENT(ice_esw_br_vlan_template, + ice_eswitch_br_vlan_create, + TP_PROTO(struct ice_esw_br_vlan *vlan), + TP_ARGS(vlan) +); + +DEFINE_EVENT(ice_esw_br_vlan_template, + ice_eswitch_br_vlan_cleanup, + TP_PROTO(struct ice_esw_br_vlan *vlan), + TP_ARGS(vlan) +); + +#define ICE_ESW_BR_PORT_NAME_L 16 + +DECLARE_EVENT_CLASS(ice_esw_br_port_template, + TP_PROTO(struct ice_esw_br_port *port), + TP_ARGS(port), + TP_STRUCT__entry(__field(u16, vport_num) + __array(char, port_type, ICE_ESW_BR_PORT_NAME_L)), + TP_fast_assign(__entry->vport_num = port->vsi_idx; + if (port->type == ICE_ESWITCH_BR_UPLINK_PORT) + strscpy(__entry->port_type, + "Uplink", + ICE_ESW_BR_PORT_NAME_L); + else + strscpy(__entry->port_type, + "VF Representor", + ICE_ESW_BR_PORT_NAME_L);), + TP_printk("vport_num=%u port type=%s", + __entry->vport_num, + __entry->port_type) +); + +DEFINE_EVENT(ice_esw_br_port_template, + ice_eswitch_br_port_link, + TP_PROTO(struct ice_esw_br_port *port), + TP_ARGS(port) +); + +DEFINE_EVENT(ice_esw_br_port_template, + ice_eswitch_br_port_unlink, + TP_PROTO(struct ice_esw_br_port *port), + TP_ARGS(port) +); + /* End tracepoints */ #endif /* _ICE_TRACE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 52d0a126eb61..9e97ea863068 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -2306,9 +2306,6 @@ ice_tstamp(struct ice_tx_ring *tx_ring, struct sk_buff *skb, if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))) return; - if (!tx_ring->ptp_tx) - return; - /* Tx timestamps cannot be sampled when doing TSO */ if (first->tx_flags & ICE_TX_FLAGS_TSO) return; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 166413fc33f4..daf7b9dbb143 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -380,7 +380,6 @@ struct ice_tx_ring { #define ICE_TX_FLAGS_RING_VLAN_L2TAG2 BIT(2) u8 flags; u8 dcb_tc; /* Traffic class of ring */ - u8 ptp_tx; } ____cacheline_internodealigned_in_smp; static inline bool ice_ring_uses_build_skb(struct ice_rx_ring *ring) diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index c8322fb6f2b3..7e06373e14d9 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -450,7 +450,7 @@ void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res, struct ice_tx_buf *tx_buf = &xdp_ring->tx_buf[first_idx]; if (xdp_res & ICE_XDP_REDIR) - xdp_do_flush_map(); + xdp_do_flush(); if (xdp_res & ICE_XDP_TX) { if (static_branch_unlikely(&ice_xdp_locking_key)) diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index a09556e57803..a18ca0ff879f 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (c) 2018, Intel Corporation. */ +/* Copyright (c) 2018-2023, Intel Corporation. */ #ifndef _ICE_TYPE_H_ #define _ICE_TYPE_H_ @@ -129,6 +129,7 @@ enum ice_set_fc_aq_failures { enum ice_mac_type { ICE_MAC_UNKNOWN = 0, ICE_MAC_E810, + ICE_MAC_E830, ICE_MAC_GENERIC, }; @@ -277,6 +278,8 @@ struct ice_hw_common_caps { u8 dcb; u8 ieee_1588; u8 rdma; + u8 roce_lag; + u8 sriov_lag; bool nvm_update_pending_nvm; bool nvm_update_pending_orom; @@ -820,6 +823,13 @@ struct ice_mbx_data { u16 async_watermark_val; }; +/* PHY model */ +enum ice_phy_model { + ICE_PHY_UNSUP = -1, + ICE_PHY_E810 = 1, + ICE_PHY_E822, +}; + /* Port hardware description */ struct ice_hw { u8 __iomem *hw_addr; @@ -841,6 +851,7 @@ struct ice_hw { u8 revision_id; u8 pf_id; /* device profile info */ + enum ice_phy_model phy_model; u16 max_burst_size; /* driver sets this value */ @@ -899,17 +910,20 @@ struct ice_hw { /* INTRL granularity in 1 us */ u8 intrl_gran; -#define ICE_PHY_PER_NAC 1 -#define ICE_MAX_QUAD 2 -#define ICE_NUM_QUAD_TYPE 2 -#define ICE_PORTS_PER_QUAD 4 -#define ICE_PHY_0_LAST_QUAD 1 -#define ICE_PORTS_PER_PHY 8 -#define ICE_NUM_EXTERNAL_PORTS ICE_PORTS_PER_PHY +#define ICE_PHY_PER_NAC_E822 1 +#define ICE_MAX_QUAD 2 +#define ICE_QUADS_PER_PHY_E822 2 +#define ICE_PORTS_PER_PHY_E822 8 +#define ICE_PORTS_PER_QUAD 4 +#define ICE_PORTS_PER_PHY_E810 4 +#define ICE_NUM_EXTERNAL_PORTS (ICE_MAX_QUAD * ICE_PORTS_PER_QUAD) /* Active package version (currently active) */ struct ice_pkg_ver active_pkg_ver; + u32 pkg_seg_id; + u32 pkg_sign_type; u32 active_track_id; + u8 pkg_has_signing_seg:1; u8 active_pkg_name[ICE_PKG_NAME_SIZE]; u8 active_pkg_in_nvm; @@ -963,6 +977,7 @@ struct ice_hw { DECLARE_BITMAP(hw_ptype, ICE_FLOW_PTYPE_MAX); u8 dvm_ena; u16 io_expander_handle; + u8 cgu_part_number; }; /* Statistics collected by each port, VSI, VEB, and S-channel */ @@ -1033,14 +1048,15 @@ enum ice_sw_fwd_act_type { ICE_FWD_TO_Q, ICE_FWD_TO_QGRP, ICE_DROP_PACKET, + ICE_NOP, ICE_INVAL_ACT }; struct ice_aq_get_set_rss_lut_params { - u16 vsi_handle; /* software VSI handle */ - u16 lut_size; /* size of the LUT buffer */ - u8 lut_type; /* type of the LUT (i.e. VSI, PF, Global) */ u8 *lut; /* input RSS LUT for set and output RSS LUT for get */ + enum ice_lut_size lut_size; /* size of the LUT buffer */ + enum ice_lut_type lut_type; /* type of the LUT (i.e. VSI, PF, Global) */ + u16 vsi_handle; /* software VSI handle */ u8 global_lut_id; /* only valid when lut_type is global */ }; @@ -1142,9 +1158,6 @@ struct ice_aq_get_set_rss_lut_params { #define ICE_SR_WORDS_IN_1KB 512 -/* Hash redirection LUT for VSI - maximum array size */ -#define ICE_VSIQF_HLUT_ARRAY_SIZE ((VSIQF_HLUT_MAX_INDEX + 1) * 4) - /* AQ API version for LLDP_FILTER_CONTROL */ #define ICE_FW_API_LLDP_FLTR_MAJ 1 #define ICE_FW_API_LLDP_FLTR_MIN 7 diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index ea3310be8354..b7ae09952156 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -56,6 +56,8 @@ static void ice_release_vf(struct kref *ref) { struct ice_vf *vf = container_of(ref, struct ice_vf, refcnt); + pci_dev_put(vf->vfdev); + vf->vf_ops->free(vf); } @@ -304,6 +306,237 @@ static int ice_vf_rebuild_vsi(struct ice_vf *vf) } /** + * ice_vf_rebuild_host_vlan_cfg - add VLAN 0 filter or rebuild the Port VLAN + * @vf: VF to add MAC filters for + * @vsi: Pointer to VSI + * + * Called after a VF VSI has been re-added/rebuilt during reset. The PF driver + * always re-adds either a VLAN 0 or port VLAN based filter after reset. + */ +static int ice_vf_rebuild_host_vlan_cfg(struct ice_vf *vf, struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + struct device *dev = ice_pf_to_dev(vf->pf); + int err; + + if (ice_vf_is_port_vlan_ena(vf)) { + err = vlan_ops->set_port_vlan(vsi, &vf->port_vlan_info); + if (err) { + dev_err(dev, "failed to configure port VLAN via VSI parameters for VF %u, error %d\n", + vf->vf_id, err); + return err; + } + + err = vlan_ops->add_vlan(vsi, &vf->port_vlan_info); + } else { + err = ice_vsi_add_vlan_zero(vsi); + } + + if (err) { + dev_err(dev, "failed to add VLAN %u filter for VF %u during VF rebuild, error %d\n", + ice_vf_is_port_vlan_ena(vf) ? + ice_vf_get_port_vlan_id(vf) : 0, vf->vf_id, err); + return err; + } + + err = vlan_ops->ena_rx_filtering(vsi); + if (err) + dev_warn(dev, "failed to enable Rx VLAN filtering for VF %d VSI %d during VF rebuild, error %d\n", + vf->vf_id, vsi->idx, err); + + return 0; +} + +/** + * ice_vf_rebuild_host_tx_rate_cfg - re-apply the Tx rate limiting configuration + * @vf: VF to re-apply the configuration for + * + * Called after a VF VSI has been re-added/rebuild during reset. The PF driver + * needs to re-apply the host configured Tx rate limiting configuration. + */ +static int ice_vf_rebuild_host_tx_rate_cfg(struct ice_vf *vf) +{ + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + int err; + + if (WARN_ON(!vsi)) + return -EINVAL; + + if (vf->min_tx_rate) { + err = ice_set_min_bw_limit(vsi, (u64)vf->min_tx_rate * 1000); + if (err) { + dev_err(dev, "failed to set min Tx rate to %d Mbps for VF %u, error %d\n", + vf->min_tx_rate, vf->vf_id, err); + return err; + } + } + + if (vf->max_tx_rate) { + err = ice_set_max_bw_limit(vsi, (u64)vf->max_tx_rate * 1000); + if (err) { + dev_err(dev, "failed to set max Tx rate to %d Mbps for VF %u, error %d\n", + vf->max_tx_rate, vf->vf_id, err); + return err; + } + } + + return 0; +} + +/** + * ice_vf_set_host_trust_cfg - set trust setting based on pre-reset value + * @vf: VF to configure trust setting for + */ +static void ice_vf_set_host_trust_cfg(struct ice_vf *vf) +{ + assign_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps, vf->trusted); +} + +/** + * ice_vf_rebuild_host_mac_cfg - add broadcast and the VF's perm_addr/LAA + * @vf: VF to add MAC filters for + * + * Called after a VF VSI has been re-added/rebuilt during reset. The PF driver + * always re-adds a broadcast filter and the VF's perm_addr/LAA after reset. + */ +static int ice_vf_rebuild_host_mac_cfg(struct ice_vf *vf) +{ + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + u8 broadcast[ETH_ALEN]; + int status; + + if (WARN_ON(!vsi)) + return -EINVAL; + + if (ice_is_eswitch_mode_switchdev(vf->pf)) + return 0; + + eth_broadcast_addr(broadcast); + status = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI); + if (status) { + dev_err(dev, "failed to add broadcast MAC filter for VF %u, error %d\n", + vf->vf_id, status); + return status; + } + + vf->num_mac++; + + if (is_valid_ether_addr(vf->hw_lan_addr)) { + status = ice_fltr_add_mac(vsi, vf->hw_lan_addr, + ICE_FWD_TO_VSI); + if (status) { + dev_err(dev, "failed to add default unicast MAC filter %pM for VF %u, error %d\n", + &vf->hw_lan_addr[0], vf->vf_id, + status); + return status; + } + vf->num_mac++; + + ether_addr_copy(vf->dev_lan_addr, vf->hw_lan_addr); + } + + return 0; +} + +/** + * ice_vf_rebuild_aggregator_node_cfg - rebuild aggregator node config + * @vsi: Pointer to VSI + * + * This function moves VSI into corresponding scheduler aggregator node + * based on cached value of "aggregator node info" per VSI + */ +static void ice_vf_rebuild_aggregator_node_cfg(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + struct device *dev; + int status; + + if (!vsi->agg_node) + return; + + dev = ice_pf_to_dev(pf); + if (vsi->agg_node->num_vsis == ICE_MAX_VSIS_IN_AGG_NODE) { + dev_dbg(dev, + "agg_id %u already has reached max_num_vsis %u\n", + vsi->agg_node->agg_id, vsi->agg_node->num_vsis); + return; + } + + status = ice_move_vsi_to_agg(pf->hw.port_info, vsi->agg_node->agg_id, + vsi->idx, vsi->tc_cfg.ena_tc); + if (status) + dev_dbg(dev, "unable to move VSI idx %u into aggregator %u node", + vsi->idx, vsi->agg_node->agg_id); + else + vsi->agg_node->num_vsis++; +} + +/** + * ice_vf_rebuild_host_cfg - host admin configuration is persistent across reset + * @vf: VF to rebuild host configuration on + */ +static void ice_vf_rebuild_host_cfg(struct ice_vf *vf) +{ + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + + if (WARN_ON(!vsi)) + return; + + ice_vf_set_host_trust_cfg(vf); + + if (ice_vf_rebuild_host_mac_cfg(vf)) + dev_err(dev, "failed to rebuild default MAC configuration for VF %d\n", + vf->vf_id); + + if (ice_vf_rebuild_host_vlan_cfg(vf, vsi)) + dev_err(dev, "failed to rebuild VLAN configuration for VF %u\n", + vf->vf_id); + + if (ice_vf_rebuild_host_tx_rate_cfg(vf)) + dev_err(dev, "failed to rebuild Tx rate limiting configuration for VF %u\n", + vf->vf_id); + + if (ice_vsi_apply_spoofchk(vsi, vf->spoofchk)) + dev_err(dev, "failed to rebuild spoofchk configuration for VF %d\n", + vf->vf_id); + + /* rebuild aggregator node config for main VF VSI */ + ice_vf_rebuild_aggregator_node_cfg(vsi); +} + +/** + * ice_set_vf_state_qs_dis - Set VF queues state to disabled + * @vf: pointer to the VF structure + */ +static void ice_set_vf_state_qs_dis(struct ice_vf *vf) +{ + /* Clear Rx/Tx enabled queues flag */ + bitmap_zero(vf->txq_ena, ICE_MAX_RSS_QS_PER_VF); + bitmap_zero(vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF); + clear_bit(ICE_VF_STATE_QS_ENA, vf->vf_states); +} + +/** + * ice_vf_set_initialized - VF is ready for VIRTCHNL communication + * @vf: VF to set in initialized state + * + * After this function the VF will be ready to receive/handle the + * VIRTCHNL_OP_GET_VF_RESOURCES message + */ +static void ice_vf_set_initialized(struct ice_vf *vf) +{ + ice_set_vf_state_qs_dis(vf); + clear_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states); + clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states); + clear_bit(ICE_VF_STATE_DIS, vf->vf_states); + set_bit(ICE_VF_STATE_INIT, vf->vf_states); + memset(&vf->vlan_v2_caps, 0, sizeof(vf->vlan_v2_caps)); +} + +/** * ice_vf_post_vsi_rebuild - Reset tasks that occur after VSI rebuild * @vf: the VF being reset * @@ -596,12 +829,16 @@ static void ice_notify_vf_reset(struct ice_vf *vf) int ice_reset_vf(struct ice_vf *vf, u32 flags) { struct ice_pf *pf = vf->pf; + struct ice_lag *lag; struct ice_vsi *vsi; + u8 act_prt, pri_prt; struct device *dev; int err = 0; bool rsd; dev = ice_pf_to_dev(pf); + act_prt = ICE_LAG_INVALID_PORT; + pri_prt = pf->hw.port_info->lport; if (flags & ICE_VF_RESET_NOTIFY) ice_notify_vf_reset(vf); @@ -612,6 +849,17 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) return 0; } + lag = pf->lag; + mutex_lock(&pf->lag_mutex); + if (lag && lag->bonded && lag->primary) { + act_prt = lag->active_port; + if (act_prt != pri_prt && act_prt != ICE_LAG_INVALID_PORT && + lag->upper_netdev) + ice_lag_move_vf_nodes_cfg(lag, act_prt, pri_prt); + else + act_prt = ICE_LAG_INVALID_PORT; + } + if (flags & ICE_VF_RESET_LOCK) mutex_lock(&vf->cfg_lock); else @@ -704,19 +952,12 @@ out_unlock: if (flags & ICE_VF_RESET_LOCK) mutex_unlock(&vf->cfg_lock); - return err; -} + if (lag && lag->bonded && lag->primary && + act_prt != ICE_LAG_INVALID_PORT) + ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt); + mutex_unlock(&pf->lag_mutex); -/** - * ice_set_vf_state_qs_dis - Set VF queues state to disabled - * @vf: pointer to the VF structure - */ -static void ice_set_vf_state_qs_dis(struct ice_vf *vf) -{ - /* Clear Rx/Tx enabled queues flag */ - bitmap_zero(vf->txq_ena, ICE_MAX_RSS_QS_PER_VF); - bitmap_zero(vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF); - clear_bit(ICE_VF_STATE_QS_ENA, vf->vf_states); + return err; } /** @@ -960,211 +1201,6 @@ bool ice_is_vf_link_up(struct ice_vf *vf) } /** - * ice_vf_set_host_trust_cfg - set trust setting based on pre-reset value - * @vf: VF to configure trust setting for - */ -static void ice_vf_set_host_trust_cfg(struct ice_vf *vf) -{ - if (vf->trusted) - set_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps); - else - clear_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps); -} - -/** - * ice_vf_rebuild_host_mac_cfg - add broadcast and the VF's perm_addr/LAA - * @vf: VF to add MAC filters for - * - * Called after a VF VSI has been re-added/rebuilt during reset. The PF driver - * always re-adds a broadcast filter and the VF's perm_addr/LAA after reset. - */ -static int ice_vf_rebuild_host_mac_cfg(struct ice_vf *vf) -{ - struct device *dev = ice_pf_to_dev(vf->pf); - struct ice_vsi *vsi = ice_get_vf_vsi(vf); - u8 broadcast[ETH_ALEN]; - int status; - - if (WARN_ON(!vsi)) - return -EINVAL; - - if (ice_is_eswitch_mode_switchdev(vf->pf)) - return 0; - - eth_broadcast_addr(broadcast); - status = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI); - if (status) { - dev_err(dev, "failed to add broadcast MAC filter for VF %u, error %d\n", - vf->vf_id, status); - return status; - } - - vf->num_mac++; - - if (is_valid_ether_addr(vf->hw_lan_addr)) { - status = ice_fltr_add_mac(vsi, vf->hw_lan_addr, - ICE_FWD_TO_VSI); - if (status) { - dev_err(dev, "failed to add default unicast MAC filter %pM for VF %u, error %d\n", - &vf->hw_lan_addr[0], vf->vf_id, - status); - return status; - } - vf->num_mac++; - - ether_addr_copy(vf->dev_lan_addr, vf->hw_lan_addr); - } - - return 0; -} - -/** - * ice_vf_rebuild_host_vlan_cfg - add VLAN 0 filter or rebuild the Port VLAN - * @vf: VF to add MAC filters for - * @vsi: Pointer to VSI - * - * Called after a VF VSI has been re-added/rebuilt during reset. The PF driver - * always re-adds either a VLAN 0 or port VLAN based filter after reset. - */ -static int ice_vf_rebuild_host_vlan_cfg(struct ice_vf *vf, struct ice_vsi *vsi) -{ - struct ice_vsi_vlan_ops *vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); - struct device *dev = ice_pf_to_dev(vf->pf); - int err; - - if (ice_vf_is_port_vlan_ena(vf)) { - err = vlan_ops->set_port_vlan(vsi, &vf->port_vlan_info); - if (err) { - dev_err(dev, "failed to configure port VLAN via VSI parameters for VF %u, error %d\n", - vf->vf_id, err); - return err; - } - - err = vlan_ops->add_vlan(vsi, &vf->port_vlan_info); - } else { - err = ice_vsi_add_vlan_zero(vsi); - } - - if (err) { - dev_err(dev, "failed to add VLAN %u filter for VF %u during VF rebuild, error %d\n", - ice_vf_is_port_vlan_ena(vf) ? - ice_vf_get_port_vlan_id(vf) : 0, vf->vf_id, err); - return err; - } - - err = vlan_ops->ena_rx_filtering(vsi); - if (err) - dev_warn(dev, "failed to enable Rx VLAN filtering for VF %d VSI %d during VF rebuild, error %d\n", - vf->vf_id, vsi->idx, err); - - return 0; -} - -/** - * ice_vf_rebuild_host_tx_rate_cfg - re-apply the Tx rate limiting configuration - * @vf: VF to re-apply the configuration for - * - * Called after a VF VSI has been re-added/rebuild during reset. The PF driver - * needs to re-apply the host configured Tx rate limiting configuration. - */ -static int ice_vf_rebuild_host_tx_rate_cfg(struct ice_vf *vf) -{ - struct device *dev = ice_pf_to_dev(vf->pf); - struct ice_vsi *vsi = ice_get_vf_vsi(vf); - int err; - - if (WARN_ON(!vsi)) - return -EINVAL; - - if (vf->min_tx_rate) { - err = ice_set_min_bw_limit(vsi, (u64)vf->min_tx_rate * 1000); - if (err) { - dev_err(dev, "failed to set min Tx rate to %d Mbps for VF %u, error %d\n", - vf->min_tx_rate, vf->vf_id, err); - return err; - } - } - - if (vf->max_tx_rate) { - err = ice_set_max_bw_limit(vsi, (u64)vf->max_tx_rate * 1000); - if (err) { - dev_err(dev, "failed to set max Tx rate to %d Mbps for VF %u, error %d\n", - vf->max_tx_rate, vf->vf_id, err); - return err; - } - } - - return 0; -} - -/** - * ice_vf_rebuild_aggregator_node_cfg - rebuild aggregator node config - * @vsi: Pointer to VSI - * - * This function moves VSI into corresponding scheduler aggregator node - * based on cached value of "aggregator node info" per VSI - */ -static void ice_vf_rebuild_aggregator_node_cfg(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - struct device *dev; - int status; - - if (!vsi->agg_node) - return; - - dev = ice_pf_to_dev(pf); - if (vsi->agg_node->num_vsis == ICE_MAX_VSIS_IN_AGG_NODE) { - dev_dbg(dev, - "agg_id %u already has reached max_num_vsis %u\n", - vsi->agg_node->agg_id, vsi->agg_node->num_vsis); - return; - } - - status = ice_move_vsi_to_agg(pf->hw.port_info, vsi->agg_node->agg_id, - vsi->idx, vsi->tc_cfg.ena_tc); - if (status) - dev_dbg(dev, "unable to move VSI idx %u into aggregator %u node", - vsi->idx, vsi->agg_node->agg_id); - else - vsi->agg_node->num_vsis++; -} - -/** - * ice_vf_rebuild_host_cfg - host admin configuration is persistent across reset - * @vf: VF to rebuild host configuration on - */ -void ice_vf_rebuild_host_cfg(struct ice_vf *vf) -{ - struct device *dev = ice_pf_to_dev(vf->pf); - struct ice_vsi *vsi = ice_get_vf_vsi(vf); - - if (WARN_ON(!vsi)) - return; - - ice_vf_set_host_trust_cfg(vf); - - if (ice_vf_rebuild_host_mac_cfg(vf)) - dev_err(dev, "failed to rebuild default MAC configuration for VF %d\n", - vf->vf_id); - - if (ice_vf_rebuild_host_vlan_cfg(vf, vsi)) - dev_err(dev, "failed to rebuild VLAN configuration for VF %u\n", - vf->vf_id); - - if (ice_vf_rebuild_host_tx_rate_cfg(vf)) - dev_err(dev, "failed to rebuild Tx rate limiting configuration for VF %u\n", - vf->vf_id); - - if (ice_vsi_apply_spoofchk(vsi, vf->spoofchk)) - dev_err(dev, "failed to rebuild spoofchk configuration for VF %d\n", - vf->vf_id); - - /* rebuild aggregator node config for main VF VSI */ - ice_vf_rebuild_aggregator_node_cfg(vsi); -} - -/** * ice_vf_ctrl_invalidate_vsi - invalidate ctrl_vsi_idx to remove VSI access * @vf: VF that control VSI is being invalidated on */ @@ -1293,23 +1329,6 @@ void ice_vf_vsi_release(struct ice_vf *vf) } /** - * ice_vf_set_initialized - VF is ready for VIRTCHNL communication - * @vf: VF to set in initialized state - * - * After this function the VF will be ready to receive/handle the - * VIRTCHNL_OP_GET_VF_RESOURCES message - */ -void ice_vf_set_initialized(struct ice_vf *vf) -{ - ice_set_vf_state_qs_dis(vf); - clear_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states); - clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states); - clear_bit(ICE_VF_STATE_DIS, vf->vf_states); - set_bit(ICE_VF_STATE_INIT, vf->vf_states); - memset(&vf->vlan_v2_caps, 0, sizeof(vf->vlan_v2_caps)); -} - -/** * ice_get_vf_ctrl_vsi - Get first VF control VSI pointer * @pf: the PF private structure * @vsi: pointer to the VSI diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h index 48fea6fa0362..93c774f2f437 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -72,7 +72,7 @@ struct ice_vfs { struct mutex table_lock; /* Lock for protecting the hash table */ u16 num_supported; /* max supported VFs on this PF */ u16 num_qps_per; /* number of queue pairs per VF */ - u16 num_msix_per; /* number of MSI-X vectors per VF */ + u16 num_msix_per; /* default MSI-X vectors per VF */ unsigned long last_printed_mdd_jiffies; /* MDD message rate limit */ }; @@ -82,7 +82,7 @@ struct ice_vf { struct rcu_head rcu; struct kref refcnt; struct ice_pf *pf; - + struct pci_dev *vfdev; /* Used during virtchnl message handling and NDO ops against the VF * that will trigger a VFR */ @@ -123,6 +123,9 @@ struct ice_vf { u8 num_req_qs; /* num of queue pairs requested by VF */ u16 num_mac; u16 num_vf_qs; /* num of queue configured per VF */ + u8 vlan_strip_ena; /* Outer and Inner VLAN strip enable */ +#define ICE_INNER_VLAN_STRIP_ENA BIT(0) +#define ICE_OUTER_VLAN_STRIP_ENA BIT(1) struct ice_mdd_vf_events mdd_rx_events; struct ice_mdd_vf_events mdd_tx_events; DECLARE_BITMAP(opcodes_allowlist, VIRTCHNL_OP_MAX); @@ -133,6 +136,8 @@ struct ice_vf { /* devlink port data */ struct devlink_port devlink_port; + + u16 num_msix; /* num of MSI-X configured on this VF */ }; /* Flags for controlling behavior of ice_reset_vf */ diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h index 6f3293b793b5..0c7e77c0a09f 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h @@ -32,13 +32,11 @@ int ice_vsi_apply_spoofchk(struct ice_vsi *vsi, bool enable); bool ice_is_vf_trusted(struct ice_vf *vf); bool ice_vf_has_no_qs_ena(struct ice_vf *vf); bool ice_is_vf_link_up(struct ice_vf *vf); -void ice_vf_rebuild_host_cfg(struct ice_vf *vf); void ice_vf_ctrl_invalidate_vsi(struct ice_vf *vf); void ice_vf_ctrl_vsi_release(struct ice_vf *vf); struct ice_vsi *ice_vf_ctrl_vsi_setup(struct ice_vf *vf); int ice_vf_init_host_cfg(struct ice_vf *vf, struct ice_vsi *vsi); void ice_vf_invalidate_vsi(struct ice_vf *vf); void ice_vf_vsi_release(struct ice_vf *vf); -void ice_vf_set_initialized(struct ice_vf *vf); #endif /* _ICE_VF_LIB_PRIVATE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c index b1ffb81893d4..80dc4bcdd3a4 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c @@ -21,6 +21,105 @@ noop_vlan(struct ice_vsi __always_unused *vsi) return 0; } +static void ice_port_vlan_on(struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops; + struct ice_pf *pf = vsi->back; + + if (ice_is_dvm_ena(&pf->hw)) { + vlan_ops = &vsi->outer_vlan_ops; + + /* setup outer VLAN ops */ + vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan; + vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan; + + /* setup inner VLAN ops */ + vlan_ops = &vsi->inner_vlan_ops; + vlan_ops->add_vlan = noop_vlan_arg; + vlan_ops->del_vlan = noop_vlan_arg; + vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; + vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; + vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; + vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; + } else { + vlan_ops = &vsi->inner_vlan_ops; + + vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan; + vlan_ops->clear_port_vlan = ice_vsi_clear_inner_port_vlan; + } + + /* all Rx traffic should be in the domain of the assigned port VLAN, + * so prevent disabling Rx VLAN filtering + */ + vlan_ops->dis_rx_filtering = noop_vlan; + + vlan_ops->ena_rx_filtering = ice_vsi_ena_rx_vlan_filtering; +} + +static void ice_port_vlan_off(struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops; + struct ice_pf *pf = vsi->back; + + /* setup inner VLAN ops */ + vlan_ops = &vsi->inner_vlan_ops; + + vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; + vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; + vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; + vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; + + if (ice_is_dvm_ena(&pf->hw)) { + vlan_ops = &vsi->outer_vlan_ops; + + vlan_ops->del_vlan = ice_vsi_del_vlan; + vlan_ops->ena_stripping = ice_vsi_ena_outer_stripping; + vlan_ops->dis_stripping = ice_vsi_dis_outer_stripping; + vlan_ops->ena_insertion = ice_vsi_ena_outer_insertion; + vlan_ops->dis_insertion = ice_vsi_dis_outer_insertion; + } else { + vlan_ops->del_vlan = ice_vsi_del_vlan; + } + + vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; + + if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) + vlan_ops->ena_rx_filtering = noop_vlan; + else + vlan_ops->ena_rx_filtering = + ice_vsi_ena_rx_vlan_filtering; +} + +/** + * ice_vf_vsi_enable_port_vlan - Set VSI VLAN ops to support port VLAN + * @vsi: VF's VSI being configured + * + * The function won't create port VLAN, it only allows to create port VLAN + * using VLAN ops on the VF VSI. + */ +void ice_vf_vsi_enable_port_vlan(struct ice_vsi *vsi) +{ + if (WARN_ON_ONCE(!vsi->vf)) + return; + + ice_port_vlan_on(vsi); +} + +/** + * ice_vf_vsi_disable_port_vlan - Clear VSI support for creating port VLAN + * @vsi: VF's VSI being configured + * + * The function should be called after removing port VLAN on VSI + * (using VLAN ops) + */ +void ice_vf_vsi_disable_port_vlan(struct ice_vsi *vsi) +{ + if (WARN_ON_ONCE(!vsi->vf)) + return; + + ice_port_vlan_off(vsi); +} + /** * ice_vf_vsi_init_vlan_ops - Initialize default VSI VLAN ops for VF VSI * @vsi: VF's VSI being configured @@ -39,91 +138,17 @@ void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) if (WARN_ON(!vf)) return; - if (ice_is_dvm_ena(&pf->hw)) { - vlan_ops = &vsi->outer_vlan_ops; + if (ice_vf_is_port_vlan_ena(vf)) + ice_port_vlan_on(vsi); + else + ice_port_vlan_off(vsi); - /* outer VLAN ops regardless of port VLAN config */ - vlan_ops->add_vlan = ice_vsi_add_vlan; - vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering; - vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering; - - if (ice_vf_is_port_vlan_ena(vf)) { - /* setup outer VLAN ops */ - vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan; - /* all Rx traffic should be in the domain of the - * assigned port VLAN, so prevent disabling Rx VLAN - * filtering - */ - vlan_ops->dis_rx_filtering = noop_vlan; - vlan_ops->ena_rx_filtering = - ice_vsi_ena_rx_vlan_filtering; - - /* setup inner VLAN ops */ - vlan_ops = &vsi->inner_vlan_ops; - vlan_ops->add_vlan = noop_vlan_arg; - vlan_ops->del_vlan = noop_vlan_arg; - vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; - vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; - vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; - vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; - } else { - vlan_ops->dis_rx_filtering = - ice_vsi_dis_rx_vlan_filtering; - - if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) - vlan_ops->ena_rx_filtering = noop_vlan; - else - vlan_ops->ena_rx_filtering = - ice_vsi_ena_rx_vlan_filtering; - - vlan_ops->del_vlan = ice_vsi_del_vlan; - vlan_ops->ena_stripping = ice_vsi_ena_outer_stripping; - vlan_ops->dis_stripping = ice_vsi_dis_outer_stripping; - vlan_ops->ena_insertion = ice_vsi_ena_outer_insertion; - vlan_ops->dis_insertion = ice_vsi_dis_outer_insertion; - - /* setup inner VLAN ops */ - vlan_ops = &vsi->inner_vlan_ops; - - vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; - vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; - vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; - vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; - } - } else { - vlan_ops = &vsi->inner_vlan_ops; + vlan_ops = ice_is_dvm_ena(&pf->hw) ? + &vsi->outer_vlan_ops : &vsi->inner_vlan_ops; - /* inner VLAN ops regardless of port VLAN config */ - vlan_ops->add_vlan = ice_vsi_add_vlan; - vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; - vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering; - vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering; - - if (ice_vf_is_port_vlan_ena(vf)) { - vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan; - vlan_ops->ena_rx_filtering = - ice_vsi_ena_rx_vlan_filtering; - /* all Rx traffic should be in the domain of the - * assigned port VLAN, so prevent disabling Rx VLAN - * filtering - */ - vlan_ops->dis_rx_filtering = noop_vlan; - } else { - vlan_ops->dis_rx_filtering = - ice_vsi_dis_rx_vlan_filtering; - if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) - vlan_ops->ena_rx_filtering = noop_vlan; - else - vlan_ops->ena_rx_filtering = - ice_vsi_ena_rx_vlan_filtering; - - vlan_ops->del_vlan = ice_vsi_del_vlan; - vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; - vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; - vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; - vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; - } - } + vlan_ops->add_vlan = ice_vsi_add_vlan; + vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering; + vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h index 875a4e615f39..df8aa09df3e3 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h @@ -13,7 +13,11 @@ void ice_vf_vsi_cfg_svm_legacy_vlan_mode(struct ice_vsi *vsi); #ifdef CONFIG_PCI_IOV void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi); +void ice_vf_vsi_enable_port_vlan(struct ice_vsi *vsi); +void ice_vf_vsi_disable_port_vlan(struct ice_vsi *vsi); #else static inline void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) { } +static inline void ice_vf_vsi_enable_port_vlan(struct ice_vsi *vsi) { } +static inline void ice_vf_vsi_disable_port_vlan(struct ice_vsi *vsi) { } #endif /* CONFIG_PCI_IOV */ #endif /* _ICE_PF_VSI_VLAN_OPS_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index dcf628b1fccd..1c7b4ded948b 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -428,7 +428,7 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) goto err; } - len = sizeof(struct virtchnl_vf_resource); + len = virtchnl_struct_size(vfres, vsi_res, 0); vfres = kzalloc(len, GFP_KERNEL); if (!vfres) { @@ -486,6 +486,9 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_REQ_QUEUES) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_REQ_QUEUES; + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_CRC) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_CRC; + if (vf->driver_caps & VIRTCHNL_VF_CAP_ADV_LINK_SPEED) vfres->vf_cap_flags |= VIRTCHNL_VF_CAP_ADV_LINK_SPEED; @@ -498,9 +501,9 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vfres->num_vsis = 1; /* Tx and Rx queue are equal for VF */ vfres->num_queue_pairs = vsi->num_txq; - vfres->max_vectors = vf->pf->vfs.num_msix_per; + vfres->max_vectors = vf->num_msix; vfres->rss_key_size = ICE_VSIQF_HKEY_ARRAY_SIZE; - vfres->rss_lut_size = ICE_VSIQF_HLUT_ARRAY_SIZE; + vfres->rss_lut_size = ICE_LUT_VSI_SIZE; vfres->max_mtu = ice_vc_get_max_frame_size(vf); vfres->vsi_res[0].vsi_id = vf->lan_vsi_num; @@ -962,7 +965,7 @@ static int ice_vc_config_rss_lut(struct ice_vf *vf, u8 *msg) goto error_param; } - if (vrl->lut_entries != ICE_VSIQF_HLUT_ARRAY_SIZE) { + if (vrl->lut_entries != ICE_LUT_VSI_SIZE) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -978,7 +981,7 @@ static int ice_vc_config_rss_lut(struct ice_vf *vf, u8 *msg) goto error_param; } - if (ice_set_rss_lut(vsi, vrl->lut, ICE_VSIQF_HLUT_ARRAY_SIZE)) + if (ice_set_rss_lut(vsi, vrl->lut, ICE_LUT_VSI_SIZE)) v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR; error_param: return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_LUT, v_ret, @@ -1520,7 +1523,6 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg) u16 num_q_vectors_mapped, vsi_id, vector_id; struct virtchnl_irq_map_info *irqmap_info; struct virtchnl_vector_map *map; - struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; int i; @@ -1532,7 +1534,7 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg) * there is actually at least a single VF queue vector mapped */ if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) || - pf->vfs.num_msix_per < num_q_vectors_mapped || + vf->num_msix < num_q_vectors_mapped || !num_q_vectors_mapped) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; @@ -1554,7 +1556,7 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg) /* vector_id is always 0-based for each VF, and can never be * larger than or equal to the max allowed interrupts per VF */ - if (!(vector_id < pf->vfs.num_msix_per) || + if (!(vector_id < vf->num_msix) || !ice_vc_isvalid_vsi_id(vf, vsi_id) || (!vector_id && (map->rxq_map || map->txq_map))) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; @@ -1600,9 +1602,24 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) (struct virtchnl_vsi_queue_config_info *)msg; struct virtchnl_queue_pair_info *qpi; struct ice_pf *pf = vf->pf; + struct ice_lag *lag; struct ice_vsi *vsi; + u8 act_prt, pri_prt; int i = -1, q_idx; + lag = pf->lag; + mutex_lock(&pf->lag_mutex); + act_prt = ICE_LAG_INVALID_PORT; + pri_prt = pf->hw.port_info->lport; + if (lag && lag->bonded && lag->primary) { + act_prt = lag->active_port; + if (act_prt != pri_prt && act_prt != ICE_LAG_INVALID_PORT && + lag->upper_netdev) + ice_lag_move_vf_nodes_cfg(lag, act_prt, pri_prt); + else + act_prt = ICE_LAG_INVALID_PORT; + } + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) goto error_param; @@ -1621,6 +1638,15 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) } for (i = 0; i < qci->num_queue_pairs; i++) { + if (!qci->qpair[i].rxq.crc_disable) + continue; + + if (!(vf->driver_caps & VIRTCHNL_VF_OFFLOAD_CRC) || + vf->vlan_strip_ena) + goto error_param; + } + + for (i = 0; i < qci->num_queue_pairs; i++) { qpi = &qci->qpair[i]; if (qpi->txq.vsi_id != qci->vsi_id || qpi->rxq.vsi_id != qci->vsi_id || @@ -1666,6 +1692,13 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) vsi->rx_rings[i]->dma = qpi->rxq.dma_ring_addr; vsi->rx_rings[i]->count = qpi->rxq.ring_len; + if (qpi->rxq.crc_disable) + vsi->rx_rings[q_idx]->flags |= + ICE_RX_FLAGS_CRC_STRIP_DIS; + else + vsi->rx_rings[q_idx]->flags &= + ~ICE_RX_FLAGS_CRC_STRIP_DIS; + if (qpi->rxq.databuffer_size != 0 && (qpi->rxq.databuffer_size > ((16 * 1024) - 128) || qpi->rxq.databuffer_size < 1024)) @@ -1710,6 +1743,11 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) } } + if (lag && lag->bonded && lag->primary && + act_prt != ICE_LAG_INVALID_PORT) + ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt); + mutex_unlock(&pf->lag_mutex); + /* send the response to the VF */ return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES, VIRTCHNL_STATUS_SUCCESS, NULL, 0); @@ -1724,6 +1762,13 @@ error_param: vf->vf_id, i); } + if (lag && lag->bonded && lag->primary && + act_prt != ICE_LAG_INVALID_PORT) + ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt); + mutex_unlock(&pf->lag_mutex); + + ice_lag_move_new_vf_nodes(vf); + /* send the response to the VF */ return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES, VIRTCHNL_STATUS_ERR_PARAM, NULL, 0); @@ -2409,6 +2454,21 @@ static int ice_vc_remove_vlan_msg(struct ice_vf *vf, u8 *msg) } /** + * ice_vsi_is_rxq_crc_strip_dis - check if Rx queue CRC strip is disabled or not + * @vsi: pointer to the VF VSI info + */ +static bool ice_vsi_is_rxq_crc_strip_dis(struct ice_vsi *vsi) +{ + unsigned int i; + + ice_for_each_alloc_rxq(vsi, i) + if (vsi->rx_rings[i]->flags & ICE_RX_FLAGS_CRC_STRIP_DIS) + return true; + + return false; +} + +/** * ice_vc_ena_vlan_stripping * @vf: pointer to the VF info * @@ -2437,6 +2497,8 @@ static int ice_vc_ena_vlan_stripping(struct ice_vf *vf) if (vsi->inner_vlan_ops.ena_stripping(vsi, ETH_P_8021Q)) v_ret = VIRTCHNL_STATUS_ERR_PARAM; + else + vf->vlan_strip_ena |= ICE_INNER_VLAN_STRIP_ENA; error_param: return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING, @@ -2472,6 +2534,8 @@ static int ice_vc_dis_vlan_stripping(struct ice_vf *vf) if (vsi->inner_vlan_ops.dis_stripping(vsi)) v_ret = VIRTCHNL_STATUS_ERR_PARAM; + else + vf->vlan_strip_ena &= ~ICE_INNER_VLAN_STRIP_ENA; error_param: return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING, @@ -2615,12 +2679,14 @@ static int ice_vc_query_rxdid(struct ice_vf *vf) goto err; } - /* Read flexiflag registers to determine whether the - * corresponding RXDID is configured and supported or not. - * Since Legacy 16byte descriptor format is not supported, - * start from Legacy 32byte descriptor. + /* RXDIDs supported by DDP package can be read from the register + * to get the supported RXDID bitmap. But the legacy 32byte RXDID + * is not listed in DDP package, add it in the bitmap manually. + * Legacy 16byte descriptor is not supported. */ - for (i = ICE_RXDID_LEGACY_1; i < ICE_FLEX_DESC_RXDID_MAX_NUM; i++) { + rxdid->supported_rxdids |= BIT(ICE_RXDID_LEGACY_1); + + for (i = ICE_RXDID_FLEX_NIC; i < ICE_FLEX_DESC_RXDID_MAX_NUM; i++) { regval = rd32(hw, GLFLXP_RXDID_FLAGS(i, 0)); if ((regval >> GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S) & GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M) @@ -2647,6 +2713,8 @@ static int ice_vf_init_vlan_stripping(struct ice_vf *vf) { struct ice_vsi *vsi = ice_get_vf_vsi(vf); + vf->vlan_strip_ena = 0; + if (!vsi) return -EINVAL; @@ -2656,10 +2724,16 @@ static int ice_vf_init_vlan_stripping(struct ice_vf *vf) if (ice_vf_is_port_vlan_ena(vf) && !ice_is_dvm_ena(&vsi->back->hw)) return 0; - if (ice_vf_vlan_offload_ena(vf->driver_caps)) - return vsi->inner_vlan_ops.ena_stripping(vsi, ETH_P_8021Q); - else - return vsi->inner_vlan_ops.dis_stripping(vsi); + if (ice_vf_vlan_offload_ena(vf->driver_caps)) { + int err; + + err = vsi->inner_vlan_ops.ena_stripping(vsi, ETH_P_8021Q); + if (!err) + vf->vlan_strip_ena |= ICE_INNER_VLAN_STRIP_ENA; + return err; + } + + return vsi->inner_vlan_ops.dis_stripping(vsi); } static u16 ice_vc_get_max_vlan_fltrs(struct ice_vf *vf) @@ -3433,6 +3507,11 @@ static int ice_vc_ena_vlan_stripping_v2_msg(struct ice_vf *vf, u8 *msg) goto out; } + if (ice_vsi_is_rxq_crc_strip_dis(vsi)) { + v_ret = VIRTCHNL_STATUS_ERR_NOT_SUPPORTED; + goto out; + } + ethertype_setting = strip_msg->outer_ethertype_setting; if (ethertype_setting) { if (ice_vc_ena_vlan_offload(vsi, @@ -3453,6 +3532,8 @@ static int ice_vc_ena_vlan_stripping_v2_msg(struct ice_vf *vf, u8 *msg) * enabled, is extracted in L2TAG1. */ ice_vsi_update_l2tsel(vsi, l2tsel); + + vf->vlan_strip_ena |= ICE_OUTER_VLAN_STRIP_ENA; } } @@ -3464,6 +3545,9 @@ static int ice_vc_ena_vlan_stripping_v2_msg(struct ice_vf *vf, u8 *msg) goto out; } + if (ethertype_setting) + vf->vlan_strip_ena |= ICE_INNER_VLAN_STRIP_ENA; + out: return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2, v_ret, NULL, 0); @@ -3525,6 +3609,8 @@ static int ice_vc_dis_vlan_stripping_v2_msg(struct ice_vf *vf, u8 *msg) * in L2TAG1. */ ice_vsi_update_l2tsel(vsi, l2tsel); + + vf->vlan_strip_ena &= ~ICE_OUTER_VLAN_STRIP_ENA; } } @@ -3534,6 +3620,9 @@ static int ice_vc_dis_vlan_stripping_v2_msg(struct ice_vf *vf, u8 *msg) goto out; } + if (ethertype_setting) + vf->vlan_strip_ena &= ~ICE_INNER_VLAN_STRIP_ENA; + out: return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2, v_ret, NULL, 0); diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c index daa6a1e894cf..24b23b7ef04a 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2021, Intel Corporation. */ +/* Copyright (C) 2021-2023, Intel Corporation. */ #include "ice.h" #include "ice_base.h" @@ -1422,8 +1422,8 @@ ice_vc_fdir_irq_handler(struct ice_vsi *ctrl_vsi, */ static void ice_vf_fdir_dump_info(struct ice_vf *vf) { + u32 fd_size, fd_cnt, fd_size_g, fd_cnt_g, fd_size_b, fd_cnt_b; struct ice_vsi *vf_vsi; - u32 fd_size, fd_cnt; struct device *dev; struct ice_pf *pf; struct ice_hw *hw; @@ -1442,12 +1442,25 @@ static void ice_vf_fdir_dump_info(struct ice_vf *vf) fd_size = rd32(hw, VSIQF_FD_SIZE(vsi_num)); fd_cnt = rd32(hw, VSIQF_FD_CNT(vsi_num)); - dev_dbg(dev, "VF %d: space allocated: guar:0x%x, be:0x%x, space consumed: guar:0x%x, be:0x%x\n", - vf->vf_id, - (fd_size & VSIQF_FD_CNT_FD_GCNT_M) >> VSIQF_FD_CNT_FD_GCNT_S, - (fd_size & VSIQF_FD_CNT_FD_BCNT_M) >> VSIQF_FD_CNT_FD_BCNT_S, - (fd_cnt & VSIQF_FD_CNT_FD_GCNT_M) >> VSIQF_FD_CNT_FD_GCNT_S, - (fd_cnt & VSIQF_FD_CNT_FD_BCNT_M) >> VSIQF_FD_CNT_FD_BCNT_S); + switch (hw->mac_type) { + case ICE_MAC_E830: + fd_size_g = FIELD_GET(E830_VSIQF_FD_CNT_FD_GCNT_M, fd_size); + fd_size_b = FIELD_GET(E830_VSIQF_FD_CNT_FD_BCNT_M, fd_size); + fd_cnt_g = FIELD_GET(E830_VSIQF_FD_CNT_FD_GCNT_M, fd_cnt); + fd_cnt_b = FIELD_GET(E830_VSIQF_FD_CNT_FD_BCNT_M, fd_cnt); + break; + case ICE_MAC_E810: + default: + fd_size_g = FIELD_GET(E800_VSIQF_FD_CNT_FD_GCNT_M, fd_size); + fd_size_b = FIELD_GET(E800_VSIQF_FD_CNT_FD_BCNT_M, fd_size); + fd_cnt_g = FIELD_GET(E800_VSIQF_FD_CNT_FD_GCNT_M, fd_cnt); + fd_cnt_b = FIELD_GET(E800_VSIQF_FD_CNT_FD_BCNT_M, fd_cnt); + } + + dev_dbg(dev, "VF %d: Size in the FD table: guaranteed:0x%x, best effort:0x%x\n", + vf->vf_id, fd_size_g, fd_size_b); + dev_dbg(dev, "VF %d: Filter counter in the FD table: guaranteed:0x%x, best effort:0x%x\n", + vf->vf_id, fd_cnt_g, fd_cnt_b); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c index 5b4a0abb4607..76266e709a39 100644 --- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c @@ -202,6 +202,24 @@ int ice_vsi_dis_inner_insertion(struct ice_vsi *vsi) return ice_vsi_manage_vlan_insertion(vsi); } +static void +ice_save_vlan_info(struct ice_aqc_vsi_props *info, + struct ice_vsi_vlan_info *vlan) +{ + vlan->sw_flags2 = info->sw_flags2; + vlan->inner_vlan_flags = info->inner_vlan_flags; + vlan->outer_vlan_flags = info->outer_vlan_flags; +} + +static void +ice_restore_vlan_info(struct ice_aqc_vsi_props *info, + struct ice_vsi_vlan_info *vlan) +{ + info->sw_flags2 = vlan->sw_flags2; + info->inner_vlan_flags = vlan->inner_vlan_flags; + info->outer_vlan_flags = vlan->outer_vlan_flags; +} + /** * __ice_vsi_set_inner_port_vlan - set port VLAN VSI context settings to enable a port VLAN * @vsi: the VSI to update @@ -218,6 +236,7 @@ static int __ice_vsi_set_inner_port_vlan(struct ice_vsi *vsi, u16 pvid_info) if (!ctxt) return -ENOMEM; + ice_save_vlan_info(&vsi->info, &vsi->vlan_info); ctxt->info = vsi->info; info = &ctxt->info; info->inner_vlan_flags = ICE_AQ_VSI_INNER_VLAN_TX_MODE_ACCEPTUNTAGGED | @@ -259,6 +278,33 @@ int ice_vsi_set_inner_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) return __ice_vsi_set_inner_port_vlan(vsi, port_vlan_info); } +int ice_vsi_clear_inner_port_vlan(struct ice_vsi *vsi) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_aqc_vsi_props *info; + struct ice_vsi_ctx *ctxt; + int ret; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ice_restore_vlan_info(&vsi->info, &vsi->vlan_info); + vsi->info.port_based_inner_vlan = 0; + ctxt->info = vsi->info; + info = &ctxt->info; + info->valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID | + ICE_AQ_VSI_PROP_SW_VALID); + + ret = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (ret) + dev_err(ice_hw_to_dev(hw), "update VSI for port VLAN failed, err %d aq_err %s\n", + ret, ice_aq_str(hw->adminq.sq_last_status)); + + kfree(ctxt); + return ret; +} + /** * ice_cfg_vlan_pruning - enable or disable VLAN pruning on the VSI * @vsi: VSI to enable or disable VLAN pruning on @@ -647,6 +693,7 @@ __ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, u16 vlan_info, u16 tpid) if (!ctxt) return -ENOMEM; + ice_save_vlan_info(&vsi->info, &vsi->vlan_info); ctxt->info = vsi->info; ctxt->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; @@ -689,9 +736,6 @@ __ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, u16 vlan_info, u16 tpid) * used if DVM is supported. Also, this function should never be called directly * as it should be part of ice_vsi_vlan_ops if it's needed. * - * This function does not support clearing the port VLAN as there is currently - * no use case for this. - * * Use the ice_vlan structure passed in to set this VSI in a port VLAN. */ int ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) @@ -705,3 +749,37 @@ int ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) return __ice_vsi_set_outer_port_vlan(vsi, port_vlan_info, vlan->tpid); } + +/** + * ice_vsi_clear_outer_port_vlan - clear outer port vlan + * @vsi: VSI to configure + * + * The function is restoring previously set vlan config (saved in + * vsi->vlan_info). Setting happens in port vlan configuration. + */ +int ice_vsi_clear_outer_port_vlan(struct ice_vsi *vsi) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx *ctxt; + int err; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ice_restore_vlan_info(&vsi->info, &vsi->vlan_info); + vsi->info.port_based_outer_vlan = 0; + ctxt->info = vsi->info; + + ctxt->info.valid_sections = + cpu_to_le16(ICE_AQ_VSI_PROP_OUTER_TAG_VALID | + ICE_AQ_VSI_PROP_SW_VALID); + + err = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (err) + dev_err(ice_pf_to_dev(vsi->back), "update VSI for clearing outer port based VLAN failed, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); + + kfree(ctxt); + return err; +} diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h index f459909490ec..f0d84d11bd5b 100644 --- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h @@ -7,6 +7,12 @@ #include <linux/types.h> #include "ice_vlan.h" +struct ice_vsi_vlan_info { + u8 sw_flags2; + u8 inner_vlan_flags; + u8 outer_vlan_flags; +}; + struct ice_vsi; int ice_vsi_add_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan); @@ -17,6 +23,7 @@ int ice_vsi_dis_inner_stripping(struct ice_vsi *vsi); int ice_vsi_ena_inner_insertion(struct ice_vsi *vsi, u16 tpid); int ice_vsi_dis_inner_insertion(struct ice_vsi *vsi); int ice_vsi_set_inner_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan); +int ice_vsi_clear_inner_port_vlan(struct ice_vsi *vsi); int ice_vsi_ena_rx_vlan_filtering(struct ice_vsi *vsi); int ice_vsi_dis_rx_vlan_filtering(struct ice_vsi *vsi); @@ -28,5 +35,6 @@ int ice_vsi_dis_outer_stripping(struct ice_vsi *vsi); int ice_vsi_ena_outer_insertion(struct ice_vsi *vsi, u16 tpid); int ice_vsi_dis_outer_insertion(struct ice_vsi *vsi); int ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan); +int ice_vsi_clear_outer_port_vlan(struct ice_vsi *vsi); #endif /* _ICE_VSI_VLAN_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h index 5b47568f6256..b2d2330dedcb 100644 --- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h @@ -21,6 +21,7 @@ struct ice_vsi_vlan_ops { int (*ena_tx_filtering)(struct ice_vsi *vsi); int (*dis_tx_filtering)(struct ice_vsi *vsi); int (*set_port_vlan)(struct ice_vsi *vsi, struct ice_vlan *vlan); + int (*clear_port_vlan)(struct ice_vsi *vsi); }; void ice_vsi_init_vlan_ops(struct ice_vsi *vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index a7fe2b4ce655..99954508184f 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -217,21 +217,16 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) */ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) { - struct ice_aqc_add_tx_qgrp *qg_buf; + DEFINE_FLEX(struct ice_aqc_add_tx_qgrp, qg_buf, txqs, 1); + u16 size = __struct_size(qg_buf); struct ice_q_vector *q_vector; struct ice_tx_ring *tx_ring; struct ice_rx_ring *rx_ring; - u16 size; int err; if (q_idx >= vsi->num_rxq || q_idx >= vsi->num_txq) return -EINVAL; - size = struct_size(qg_buf, txqs, 1); - qg_buf = kzalloc(size, GFP_KERNEL); - if (!qg_buf) - return -ENOMEM; - qg_buf->num_txqs = 1; tx_ring = vsi->tx_rings[q_idx]; @@ -240,7 +235,7 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) err = ice_vsi_cfg_txq(vsi, tx_ring, qg_buf); if (err) - goto free_buf; + return err; if (ice_is_xdp_ena_vsi(vsi)) { struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx]; @@ -249,29 +244,28 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) qg_buf->num_txqs = 1; err = ice_vsi_cfg_txq(vsi, xdp_ring, qg_buf); if (err) - goto free_buf; + return err; ice_set_ring_xdp(xdp_ring); ice_tx_xsk_pool(vsi, q_idx); } err = ice_vsi_cfg_rxq(rx_ring); if (err) - goto free_buf; + return err; ice_qvec_cfg_msix(vsi, q_vector); err = ice_vsi_ctrl_one_rx_ring(vsi, true, q_idx, true); if (err) - goto free_buf; + return err; clear_bit(ICE_CFG_BUSY, vsi->state); ice_qvec_toggle_napi(vsi, q_vector, true); ice_qvec_ena_irq(vsi, q_vector); netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); -free_buf: - kfree(qg_buf); - return err; + + return 0; } /** @@ -546,19 +540,6 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) } /** - * ice_bump_ntc - Bump the next_to_clean counter of an Rx ring - * @rx_ring: Rx ring - */ -static void ice_bump_ntc(struct ice_rx_ring *rx_ring) -{ - int ntc = rx_ring->next_to_clean + 1; - - ntc = (ntc < rx_ring->count) ? ntc : 0; - rx_ring->next_to_clean = ntc; - prefetch(ICE_RX_DESC(rx_ring, ntc)); -} - -/** * ice_construct_skb_zc - Create an sk_buff from zero-copy buffer * @rx_ring: Rx ring * @xdp: Pointer to XDP buffer @@ -572,8 +553,14 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) { unsigned int totalsize = xdp->data_end - xdp->data_meta; unsigned int metasize = xdp->data - xdp->data_meta; + struct skb_shared_info *sinfo = NULL; struct sk_buff *skb; + u32 nr_frags = 0; + if (unlikely(xdp_buff_has_frags(xdp))) { + sinfo = xdp_get_shared_info_from_buff(xdp); + nr_frags = sinfo->nr_frags; + } net_prefetch(xdp->data_meta); skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize, @@ -589,6 +576,29 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) __skb_pull(skb, metasize); } + if (likely(!xdp_buff_has_frags(xdp))) + goto out; + + for (int i = 0; i < nr_frags; i++) { + struct skb_shared_info *skinfo = skb_shinfo(skb); + skb_frag_t *frag = &sinfo->frags[i]; + struct page *page; + void *addr; + + page = dev_alloc_page(); + if (!page) { + dev_kfree_skb(skb); + return NULL; + } + addr = page_to_virt(page); + + memcpy(addr, skb_frag_page(frag), skb_frag_size(frag)); + + __skb_fill_page_desc_noacc(skinfo, skinfo->nr_frags++, + addr, 0, skb_frag_size(frag)); + } + +out: xsk_buff_free(xdp); return skb; } @@ -597,7 +607,7 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ * @xdp_ring: XDP Tx ring */ -static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring) +static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring) { u16 ntc = xdp_ring->next_to_clean; struct ice_tx_desc *tx_desc; @@ -619,7 +629,7 @@ static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring) } if (!completed_frames) - return; + return 0; if (likely(!xdp_ring->xdp_tx_active)) { xsk_frames = completed_frames; @@ -649,6 +659,8 @@ skip: xdp_ring->next_to_clean -= cnt; if (xsk_frames) xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames); + + return completed_frames; } /** @@ -666,37 +678,72 @@ skip: static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring) { + struct skb_shared_info *sinfo = NULL; u32 size = xdp->data_end - xdp->data; u32 ntu = xdp_ring->next_to_use; struct ice_tx_desc *tx_desc; struct ice_tx_buf *tx_buf; - dma_addr_t dma; - - if (ICE_DESC_UNUSED(xdp_ring) < ICE_RING_QUARTER(xdp_ring)) { - ice_clean_xdp_irq_zc(xdp_ring); - if (!ICE_DESC_UNUSED(xdp_ring)) { - xdp_ring->ring_stats->tx_stats.tx_busy++; - return ICE_XDP_CONSUMED; - } + struct xdp_buff *head; + u32 nr_frags = 0; + u32 free_space; + u32 frag = 0; + + free_space = ICE_DESC_UNUSED(xdp_ring); + if (free_space < ICE_RING_QUARTER(xdp_ring)) + free_space += ice_clean_xdp_irq_zc(xdp_ring); + + if (unlikely(!free_space)) + goto busy; + + if (unlikely(xdp_buff_has_frags(xdp))) { + sinfo = xdp_get_shared_info_from_buff(xdp); + nr_frags = sinfo->nr_frags; + if (free_space < nr_frags + 1) + goto busy; } - dma = xsk_buff_xdp_get_dma(xdp); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size); - - tx_buf = &xdp_ring->tx_buf[ntu]; - tx_buf->xdp = xdp; - tx_buf->type = ICE_TX_BUF_XSK_TX; tx_desc = ICE_TX_DESC(xdp_ring, ntu); - tx_desc->buf_addr = cpu_to_le64(dma); - tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP, - 0, size, 0); - xdp_ring->xdp_tx_active++; + tx_buf = &xdp_ring->tx_buf[ntu]; + head = xdp; + + for (;;) { + dma_addr_t dma; + + dma = xsk_buff_xdp_get_dma(xdp); + xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size); + + tx_buf->xdp = xdp; + tx_buf->type = ICE_TX_BUF_XSK_TX; + tx_desc->buf_addr = cpu_to_le64(dma); + tx_desc->cmd_type_offset_bsz = ice_build_ctob(0, 0, size, 0); + /* account for each xdp_buff from xsk_buff_pool */ + xdp_ring->xdp_tx_active++; + + if (++ntu == xdp_ring->count) + ntu = 0; + + if (frag == nr_frags) + break; + + tx_desc = ICE_TX_DESC(xdp_ring, ntu); + tx_buf = &xdp_ring->tx_buf[ntu]; + + xdp = xsk_buff_get_frag(head); + size = skb_frag_size(&sinfo->frags[frag]); + frag++; + } - if (++ntu == xdp_ring->count) - ntu = 0; xdp_ring->next_to_use = ntu; + /* update last descriptor from a frame with EOP */ + tx_desc->cmd_type_offset_bsz |= + cpu_to_le64(ICE_TX_DESC_CMD_EOP << ICE_TXD_QW1_CMD_S); return ICE_XDP_TX; + +busy: + xdp_ring->ring_stats->tx_stats.tx_busy++; + + return ICE_XDP_CONSUMED; } /** @@ -752,6 +799,34 @@ out_failure: return result; } +static int +ice_add_xsk_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *first, + struct xdp_buff *xdp, const unsigned int size) +{ + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(first); + + if (!size) + return 0; + + if (!xdp_buff_has_frags(first)) { + sinfo->nr_frags = 0; + sinfo->xdp_frags_size = 0; + xdp_buff_set_frags_flag(first); + } + + if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) { + xsk_buff_free(first); + return -ENOMEM; + } + + __skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, + virt_to_page(xdp->data_hard_start), 0, size); + sinfo->xdp_frags_size += size; + xsk_buff_add_frag(xdp); + + return 0; +} + /** * ice_clean_rx_irq_zc - consumes packets from the hardware ring * @rx_ring: AF_XDP Rx ring @@ -762,9 +837,14 @@ out_failure: int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) { unsigned int total_rx_bytes = 0, total_rx_packets = 0; + struct xsk_buff_pool *xsk_pool = rx_ring->xsk_pool; + u32 ntc = rx_ring->next_to_clean; + u32 ntu = rx_ring->next_to_use; + struct xdp_buff *first = NULL; struct ice_tx_ring *xdp_ring; unsigned int xdp_xmit = 0; struct bpf_prog *xdp_prog; + u32 cnt = rx_ring->count; bool failure = false; int entries_to_alloc; @@ -774,6 +854,9 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) xdp_prog = READ_ONCE(rx_ring->xdp_prog); xdp_ring = rx_ring->xdp_ring; + if (ntc != rx_ring->first_desc) + first = *ice_xdp_buf(rx_ring, rx_ring->first_desc); + while (likely(total_rx_packets < (unsigned int)budget)) { union ice_32b_rx_flex_desc *rx_desc; unsigned int size, xdp_res = 0; @@ -783,7 +866,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) u16 vlan_tag = 0; u16 rx_ptype; - rx_desc = ICE_RX_DESC(rx_ring, rx_ring->next_to_clean); + rx_desc = ICE_RX_DESC(rx_ring, ntc); stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S); if (!ice_test_staterr(rx_desc->wb.status_error0, stat_err_bits)) @@ -795,51 +878,61 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) */ dma_rmb(); - if (unlikely(rx_ring->next_to_clean == rx_ring->next_to_use)) + if (unlikely(ntc == ntu)) break; - xdp = *ice_xdp_buf(rx_ring, rx_ring->next_to_clean); + xdp = *ice_xdp_buf(rx_ring, ntc); size = le16_to_cpu(rx_desc->wb.pkt_len) & ICE_RX_FLX_DESC_PKT_LEN_M; - if (!size) { - xdp->data = NULL; - xdp->data_end = NULL; - xdp->data_hard_start = NULL; - xdp->data_meta = NULL; - goto construct_skb; - } xsk_buff_set_size(xdp, size); - xsk_buff_dma_sync_for_cpu(xdp, rx_ring->xsk_pool); + xsk_buff_dma_sync_for_cpu(xdp, xsk_pool); - xdp_res = ice_run_xdp_zc(rx_ring, xdp, xdp_prog, xdp_ring); + if (!first) { + first = xdp; + xdp_buff_clear_frags_flag(first); + } else if (ice_add_xsk_frag(rx_ring, first, xdp, size)) { + break; + } + + if (++ntc == cnt) + ntc = 0; + + if (ice_is_non_eop(rx_ring, rx_desc)) + continue; + + xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring); if (likely(xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))) { xdp_xmit |= xdp_res; } else if (xdp_res == ICE_XDP_EXIT) { failure = true; + first = NULL; + rx_ring->first_desc = ntc; break; } else if (xdp_res == ICE_XDP_CONSUMED) { - xsk_buff_free(xdp); + xsk_buff_free(first); } else if (xdp_res == ICE_XDP_PASS) { goto construct_skb; } - total_rx_bytes += size; + total_rx_bytes += xdp_get_buff_len(first); total_rx_packets++; - ice_bump_ntc(rx_ring); + first = NULL; + rx_ring->first_desc = ntc; continue; construct_skb: /* XDP_PASS path */ - skb = ice_construct_skb_zc(rx_ring, xdp); + skb = ice_construct_skb_zc(rx_ring, first); if (!skb) { rx_ring->ring_stats->rx_stats.alloc_buf_failed++; break; } - ice_bump_ntc(rx_ring); + first = NULL; + rx_ring->first_desc = ntc; if (eth_skb_pad(skb)) { skb = NULL; @@ -858,18 +951,22 @@ construct_skb: ice_receive_skb(rx_ring, skb, vlan_tag); } - entries_to_alloc = ICE_DESC_UNUSED(rx_ring); + rx_ring->next_to_clean = ntc; + entries_to_alloc = ICE_RX_DESC_UNUSED(rx_ring); if (entries_to_alloc > ICE_RING_QUARTER(rx_ring)) failure |= !ice_alloc_rx_bufs_zc(rx_ring, entries_to_alloc); ice_finalize_xdp_rx(xdp_ring, xdp_xmit, 0); ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes); - if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) { - if (failure || rx_ring->next_to_clean == rx_ring->next_to_use) - xsk_set_rx_need_wakeup(rx_ring->xsk_pool); + if (xsk_uses_need_wakeup(xsk_pool)) { + /* ntu could have changed when allocating entries above, so + * use rx_ring value instead of stack based one + */ + if (failure || ntc == rx_ring->next_to_use) + xsk_set_rx_need_wakeup(xsk_pool); else - xsk_clear_rx_need_wakeup(rx_ring->xsk_pool); + xsk_clear_rx_need_wakeup(xsk_pool); return (int)total_rx_packets; } @@ -894,7 +991,7 @@ static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc, tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_to_use++); tx_desc->buf_addr = cpu_to_le64(dma); - tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP, + tx_desc->cmd_type_offset_bsz = ice_build_ctob(xsk_is_eop_desc(desc), 0, desc->len, 0); *total_bytes += desc->len; @@ -921,7 +1018,7 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de tx_desc = ICE_TX_DESC(xdp_ring, ntu++); tx_desc->buf_addr = cpu_to_le64(dma); - tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP, + tx_desc->cmd_type_offset_bsz = ice_build_ctob(xsk_is_eop_desc(&descs[i]), 0, descs[i].len, 0); *total_bytes += descs[i].len; diff --git a/drivers/net/ethernet/intel/idpf/Makefile b/drivers/net/ethernet/intel/idpf/Makefile new file mode 100644 index 000000000000..6844ead2f3ac --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/Makefile @@ -0,0 +1,18 @@ +# SPDX-License-Identifier: GPL-2.0-only +# Copyright (C) 2023 Intel Corporation + +# Makefile for Intel(R) Infrastructure Data Path Function Linux Driver + +obj-$(CONFIG_IDPF) += idpf.o + +idpf-y := \ + idpf_controlq.o \ + idpf_controlq_setup.o \ + idpf_dev.o \ + idpf_ethtool.o \ + idpf_lib.o \ + idpf_main.o \ + idpf_singleq_txrx.o \ + idpf_txrx.o \ + idpf_virtchnl.o \ + idpf_vf_dev.o diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h new file mode 100644 index 000000000000..bee73353b56a --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/idpf.h @@ -0,0 +1,968 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2023 Intel Corporation */ + +#ifndef _IDPF_H_ +#define _IDPF_H_ + +/* Forward declaration */ +struct idpf_adapter; +struct idpf_vport; +struct idpf_vport_max_q; + +#include <net/pkt_sched.h> +#include <linux/aer.h> +#include <linux/etherdevice.h> +#include <linux/pci.h> +#include <linux/bitfield.h> +#include <linux/sctp.h> +#include <linux/ethtool.h> +#include <net/gro.h> +#include <linux/dim.h> + +#include "virtchnl2.h" +#include "idpf_lan_txrx.h" +#include "idpf_txrx.h" +#include "idpf_controlq.h" + +#define GETMAXVAL(num_bits) GENMASK((num_bits) - 1, 0) + +#define IDPF_NO_FREE_SLOT 0xffff + +/* Default Mailbox settings */ +#define IDPF_NUM_FILTERS_PER_MSG 20 +#define IDPF_NUM_DFLT_MBX_Q 2 /* includes both TX and RX */ +#define IDPF_DFLT_MBX_Q_LEN 64 +#define IDPF_DFLT_MBX_ID -1 +/* maximum number of times to try before resetting mailbox */ +#define IDPF_MB_MAX_ERR 20 +#define IDPF_NUM_CHUNKS_PER_MSG(struct_sz, chunk_sz) \ + ((IDPF_CTLQ_MAX_BUF_LEN - (struct_sz)) / (chunk_sz)) +#define IDPF_WAIT_FOR_EVENT_TIMEO_MIN 2000 +#define IDPF_WAIT_FOR_EVENT_TIMEO 60000 + +#define IDPF_MAX_WAIT 500 + +/* available message levels */ +#define IDPF_AVAIL_NETIF_M (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK) + +#define IDPF_DIM_PROFILE_SLOTS 5 + +#define IDPF_VIRTCHNL_VERSION_MAJOR VIRTCHNL2_VERSION_MAJOR_2 +#define IDPF_VIRTCHNL_VERSION_MINOR VIRTCHNL2_VERSION_MINOR_0 + +/** + * struct idpf_mac_filter + * @list: list member field + * @macaddr: MAC address + * @remove: filter should be removed (virtchnl) + * @add: filter should be added (virtchnl) + */ +struct idpf_mac_filter { + struct list_head list; + u8 macaddr[ETH_ALEN]; + bool remove; + bool add; +}; + +/** + * enum idpf_state - State machine to handle bring up + * @__IDPF_STARTUP: Start the state machine + * @__IDPF_VER_CHECK: Negotiate virtchnl version + * @__IDPF_GET_CAPS: Negotiate capabilities + * @__IDPF_INIT_SW: Init based on given capabilities + * @__IDPF_STATE_LAST: Must be last, used to determine size + */ +enum idpf_state { + __IDPF_STARTUP, + __IDPF_VER_CHECK, + __IDPF_GET_CAPS, + __IDPF_INIT_SW, + __IDPF_STATE_LAST, +}; + +/** + * enum idpf_flags - Hard reset causes. + * @IDPF_HR_FUNC_RESET: Hard reset when TxRx timeout + * @IDPF_HR_DRV_LOAD: Set on driver load for a clean HW + * @IDPF_HR_RESET_IN_PROG: Reset in progress + * @IDPF_REMOVE_IN_PROG: Driver remove in progress + * @IDPF_MB_INTR_MODE: Mailbox in interrupt mode + * @IDPF_FLAGS_NBITS: Must be last + */ +enum idpf_flags { + IDPF_HR_FUNC_RESET, + IDPF_HR_DRV_LOAD, + IDPF_HR_RESET_IN_PROG, + IDPF_REMOVE_IN_PROG, + IDPF_MB_INTR_MODE, + IDPF_FLAGS_NBITS, +}; + +/** + * enum idpf_cap_field - Offsets into capabilities struct for specific caps + * @IDPF_BASE_CAPS: generic base capabilities + * @IDPF_CSUM_CAPS: checksum offload capabilities + * @IDPF_SEG_CAPS: segmentation offload capabilities + * @IDPF_RSS_CAPS: RSS offload capabilities + * @IDPF_HSPLIT_CAPS: Header split capabilities + * @IDPF_RSC_CAPS: RSC offload capabilities + * @IDPF_OTHER_CAPS: miscellaneous offloads + * + * Used when checking for a specific capability flag since different capability + * sets are not mutually exclusive numerically, the caller must specify which + * type of capability they are checking for. + */ +enum idpf_cap_field { + IDPF_BASE_CAPS = -1, + IDPF_CSUM_CAPS = offsetof(struct virtchnl2_get_capabilities, + csum_caps), + IDPF_SEG_CAPS = offsetof(struct virtchnl2_get_capabilities, + seg_caps), + IDPF_RSS_CAPS = offsetof(struct virtchnl2_get_capabilities, + rss_caps), + IDPF_HSPLIT_CAPS = offsetof(struct virtchnl2_get_capabilities, + hsplit_caps), + IDPF_RSC_CAPS = offsetof(struct virtchnl2_get_capabilities, + rsc_caps), + IDPF_OTHER_CAPS = offsetof(struct virtchnl2_get_capabilities, + other_caps), +}; + +/** + * enum idpf_vport_state - Current vport state + * @__IDPF_VPORT_DOWN: Vport is down + * @__IDPF_VPORT_UP: Vport is up + * @__IDPF_VPORT_STATE_LAST: Must be last, number of states + */ +enum idpf_vport_state { + __IDPF_VPORT_DOWN, + __IDPF_VPORT_UP, + __IDPF_VPORT_STATE_LAST, +}; + +/** + * struct idpf_netdev_priv - Struct to store vport back pointer + * @adapter: Adapter back pointer + * @vport: Vport back pointer + * @vport_id: Vport identifier + * @vport_idx: Relative vport index + * @state: See enum idpf_vport_state + * @netstats: Packet and byte stats + * @stats_lock: Lock to protect stats update + */ +struct idpf_netdev_priv { + struct idpf_adapter *adapter; + struct idpf_vport *vport; + u32 vport_id; + u16 vport_idx; + enum idpf_vport_state state; + struct rtnl_link_stats64 netstats; + spinlock_t stats_lock; +}; + +/** + * struct idpf_reset_reg - Reset register offsets/masks + * @rstat: Reset status register + * @rstat_m: Reset status mask + */ +struct idpf_reset_reg { + void __iomem *rstat; + u32 rstat_m; +}; + +/** + * struct idpf_vport_max_q - Queue limits + * @max_rxq: Maximum number of RX queues supported + * @max_txq: Maixmum number of TX queues supported + * @max_bufq: In splitq, maximum number of buffer queues supported + * @max_complq: In splitq, maximum number of completion queues supported + */ +struct idpf_vport_max_q { + u16 max_rxq; + u16 max_txq; + u16 max_bufq; + u16 max_complq; +}; + +/** + * struct idpf_reg_ops - Device specific register operation function pointers + * @ctlq_reg_init: Mailbox control queue register initialization + * @intr_reg_init: Traffic interrupt register initialization + * @mb_intr_reg_init: Mailbox interrupt register initialization + * @reset_reg_init: Reset register initialization + * @trigger_reset: Trigger a reset to occur + */ +struct idpf_reg_ops { + void (*ctlq_reg_init)(struct idpf_ctlq_create_info *cq); + int (*intr_reg_init)(struct idpf_vport *vport); + void (*mb_intr_reg_init)(struct idpf_adapter *adapter); + void (*reset_reg_init)(struct idpf_adapter *adapter); + void (*trigger_reset)(struct idpf_adapter *adapter, + enum idpf_flags trig_cause); +}; + +/** + * struct idpf_dev_ops - Device specific operations + * @reg_ops: Register operations + */ +struct idpf_dev_ops { + struct idpf_reg_ops reg_ops; +}; + +/* These macros allow us to generate an enum and a matching char * array of + * stringified enums that are always in sync. Checkpatch issues a bogus warning + * about this being a complex macro; but it's wrong, these are never used as a + * statement and instead only used to define the enum and array. + */ +#define IDPF_FOREACH_VPORT_VC_STATE(STATE) \ + STATE(IDPF_VC_CREATE_VPORT) \ + STATE(IDPF_VC_CREATE_VPORT_ERR) \ + STATE(IDPF_VC_ENA_VPORT) \ + STATE(IDPF_VC_ENA_VPORT_ERR) \ + STATE(IDPF_VC_DIS_VPORT) \ + STATE(IDPF_VC_DIS_VPORT_ERR) \ + STATE(IDPF_VC_DESTROY_VPORT) \ + STATE(IDPF_VC_DESTROY_VPORT_ERR) \ + STATE(IDPF_VC_CONFIG_TXQ) \ + STATE(IDPF_VC_CONFIG_TXQ_ERR) \ + STATE(IDPF_VC_CONFIG_RXQ) \ + STATE(IDPF_VC_CONFIG_RXQ_ERR) \ + STATE(IDPF_VC_ENA_QUEUES) \ + STATE(IDPF_VC_ENA_QUEUES_ERR) \ + STATE(IDPF_VC_DIS_QUEUES) \ + STATE(IDPF_VC_DIS_QUEUES_ERR) \ + STATE(IDPF_VC_MAP_IRQ) \ + STATE(IDPF_VC_MAP_IRQ_ERR) \ + STATE(IDPF_VC_UNMAP_IRQ) \ + STATE(IDPF_VC_UNMAP_IRQ_ERR) \ + STATE(IDPF_VC_ADD_QUEUES) \ + STATE(IDPF_VC_ADD_QUEUES_ERR) \ + STATE(IDPF_VC_DEL_QUEUES) \ + STATE(IDPF_VC_DEL_QUEUES_ERR) \ + STATE(IDPF_VC_ALLOC_VECTORS) \ + STATE(IDPF_VC_ALLOC_VECTORS_ERR) \ + STATE(IDPF_VC_DEALLOC_VECTORS) \ + STATE(IDPF_VC_DEALLOC_VECTORS_ERR) \ + STATE(IDPF_VC_SET_SRIOV_VFS) \ + STATE(IDPF_VC_SET_SRIOV_VFS_ERR) \ + STATE(IDPF_VC_GET_RSS_LUT) \ + STATE(IDPF_VC_GET_RSS_LUT_ERR) \ + STATE(IDPF_VC_SET_RSS_LUT) \ + STATE(IDPF_VC_SET_RSS_LUT_ERR) \ + STATE(IDPF_VC_GET_RSS_KEY) \ + STATE(IDPF_VC_GET_RSS_KEY_ERR) \ + STATE(IDPF_VC_SET_RSS_KEY) \ + STATE(IDPF_VC_SET_RSS_KEY_ERR) \ + STATE(IDPF_VC_GET_STATS) \ + STATE(IDPF_VC_GET_STATS_ERR) \ + STATE(IDPF_VC_ADD_MAC_ADDR) \ + STATE(IDPF_VC_ADD_MAC_ADDR_ERR) \ + STATE(IDPF_VC_DEL_MAC_ADDR) \ + STATE(IDPF_VC_DEL_MAC_ADDR_ERR) \ + STATE(IDPF_VC_GET_PTYPE_INFO) \ + STATE(IDPF_VC_GET_PTYPE_INFO_ERR) \ + STATE(IDPF_VC_LOOPBACK_STATE) \ + STATE(IDPF_VC_LOOPBACK_STATE_ERR) \ + STATE(IDPF_VC_NBITS) + +#define IDPF_GEN_ENUM(ENUM) ENUM, +#define IDPF_GEN_STRING(STRING) #STRING, + +enum idpf_vport_vc_state { + IDPF_FOREACH_VPORT_VC_STATE(IDPF_GEN_ENUM) +}; + +extern const char * const idpf_vport_vc_state_str[]; + +/** + * enum idpf_vport_reset_cause - Vport soft reset causes + * @IDPF_SR_Q_CHANGE: Soft reset queue change + * @IDPF_SR_Q_DESC_CHANGE: Soft reset descriptor change + * @IDPF_SR_MTU_CHANGE: Soft reset MTU change + * @IDPF_SR_RSC_CHANGE: Soft reset RSC change + */ +enum idpf_vport_reset_cause { + IDPF_SR_Q_CHANGE, + IDPF_SR_Q_DESC_CHANGE, + IDPF_SR_MTU_CHANGE, + IDPF_SR_RSC_CHANGE, +}; + +/** + * enum idpf_vport_flags - Vport flags + * @IDPF_VPORT_DEL_QUEUES: To send delete queues message + * @IDPF_VPORT_SW_MARKER: Indicate TX pipe drain software marker packets + * processing is done + * @IDPF_VPORT_FLAGS_NBITS: Must be last + */ +enum idpf_vport_flags { + IDPF_VPORT_DEL_QUEUES, + IDPF_VPORT_SW_MARKER, + IDPF_VPORT_FLAGS_NBITS, +}; + +struct idpf_port_stats { + struct u64_stats_sync stats_sync; + u64_stats_t rx_hw_csum_err; + u64_stats_t rx_hsplit; + u64_stats_t rx_hsplit_hbo; + u64_stats_t rx_bad_descs; + u64_stats_t tx_linearize; + u64_stats_t tx_busy; + u64_stats_t tx_drops; + u64_stats_t tx_dma_map_errs; + struct virtchnl2_vport_stats vport_stats; +}; + +/** + * struct idpf_vport - Handle for netdevices and queue resources + * @num_txq: Number of allocated TX queues + * @num_complq: Number of allocated completion queues + * @txq_desc_count: TX queue descriptor count + * @complq_desc_count: Completion queue descriptor count + * @compln_clean_budget: Work budget for completion clean + * @num_txq_grp: Number of TX queue groups + * @txq_grps: Array of TX queue groups + * @txq_model: Split queue or single queue queuing model + * @txqs: Used only in hotpath to get to the right queue very fast + * @crc_enable: Enable CRC insertion offload + * @num_rxq: Number of allocated RX queues + * @num_bufq: Number of allocated buffer queues + * @rxq_desc_count: RX queue descriptor count. *MUST* have enough descriptors + * to complete all buffer descriptors for all buffer queues in + * the worst case. + * @num_bufqs_per_qgrp: Buffer queues per RX queue in a given grouping + * @bufq_desc_count: Buffer queue descriptor count + * @bufq_size: Size of buffers in ring (e.g. 2K, 4K, etc) + * @num_rxq_grp: Number of RX queues in a group + * @rxq_grps: Total number of RX groups. Number of groups * number of RX per + * group will yield total number of RX queues. + * @rxq_model: Splitq queue or single queue queuing model + * @rx_ptype_lkup: Lookup table for ptypes on RX + * @adapter: back pointer to associated adapter + * @netdev: Associated net_device. Each vport should have one and only one + * associated netdev. + * @flags: See enum idpf_vport_flags + * @vport_type: Default SRIOV, SIOV, etc. + * @vport_id: Device given vport identifier + * @idx: Software index in adapter vports struct + * @default_vport: Use this vport if one isn't specified + * @base_rxd: True if the driver should use base descriptors instead of flex + * @num_q_vectors: Number of IRQ vectors allocated + * @q_vectors: Array of queue vectors + * @q_vector_idxs: Starting index of queue vectors + * @max_mtu: device given max possible MTU + * @default_mac_addr: device will give a default MAC to use + * @rx_itr_profile: RX profiles for Dynamic Interrupt Moderation + * @tx_itr_profile: TX profiles for Dynamic Interrupt Moderation + * @port_stats: per port csum, header split, and other offload stats + * @link_up: True if link is up + * @link_speed_mbps: Link speed in mbps + * @vc_msg: Virtchnl message buffer + * @vc_state: Virtchnl message state + * @vchnl_wq: Wait queue for virtchnl messages + * @sw_marker_wq: workqueue for marker packets + * @vc_buf_lock: Lock to protect virtchnl buffer + */ +struct idpf_vport { + u16 num_txq; + u16 num_complq; + u32 txq_desc_count; + u32 complq_desc_count; + u32 compln_clean_budget; + u16 num_txq_grp; + struct idpf_txq_group *txq_grps; + u32 txq_model; + struct idpf_queue **txqs; + bool crc_enable; + + u16 num_rxq; + u16 num_bufq; + u32 rxq_desc_count; + u8 num_bufqs_per_qgrp; + u32 bufq_desc_count[IDPF_MAX_BUFQS_PER_RXQ_GRP]; + u32 bufq_size[IDPF_MAX_BUFQS_PER_RXQ_GRP]; + u16 num_rxq_grp; + struct idpf_rxq_group *rxq_grps; + u32 rxq_model; + struct idpf_rx_ptype_decoded rx_ptype_lkup[IDPF_RX_MAX_PTYPE]; + + struct idpf_adapter *adapter; + struct net_device *netdev; + DECLARE_BITMAP(flags, IDPF_VPORT_FLAGS_NBITS); + u16 vport_type; + u32 vport_id; + u16 idx; + bool default_vport; + bool base_rxd; + + u16 num_q_vectors; + struct idpf_q_vector *q_vectors; + u16 *q_vector_idxs; + u16 max_mtu; + u8 default_mac_addr[ETH_ALEN]; + u16 rx_itr_profile[IDPF_DIM_PROFILE_SLOTS]; + u16 tx_itr_profile[IDPF_DIM_PROFILE_SLOTS]; + struct idpf_port_stats port_stats; + + bool link_up; + u32 link_speed_mbps; + + char vc_msg[IDPF_CTLQ_MAX_BUF_LEN]; + DECLARE_BITMAP(vc_state, IDPF_VC_NBITS); + + wait_queue_head_t vchnl_wq; + wait_queue_head_t sw_marker_wq; + struct mutex vc_buf_lock; +}; + +/** + * enum idpf_user_flags + * @__IDPF_PROMISC_UC: Unicast promiscuous mode + * @__IDPF_PROMISC_MC: Multicast promiscuous mode + * @__IDPF_USER_FLAGS_NBITS: Must be last + */ +enum idpf_user_flags { + __IDPF_PROMISC_UC = 32, + __IDPF_PROMISC_MC, + + __IDPF_USER_FLAGS_NBITS, +}; + +/** + * struct idpf_rss_data - Associated RSS data + * @rss_key_size: Size of RSS hash key + * @rss_key: RSS hash key + * @rss_lut_size: Size of RSS lookup table + * @rss_lut: RSS lookup table + * @cached_lut: Used to restore previously init RSS lut + */ +struct idpf_rss_data { + u16 rss_key_size; + u8 *rss_key; + u16 rss_lut_size; + u32 *rss_lut; + u32 *cached_lut; +}; + +/** + * struct idpf_vport_user_config_data - User defined configuration values for + * each vport. + * @rss_data: See struct idpf_rss_data + * @num_req_tx_qs: Number of user requested TX queues through ethtool + * @num_req_rx_qs: Number of user requested RX queues through ethtool + * @num_req_txq_desc: Number of user requested TX queue descriptors through + * ethtool + * @num_req_rxq_desc: Number of user requested RX queue descriptors through + * ethtool + * @user_flags: User toggled config flags + * @mac_filter_list: List of MAC filters + * + * Used to restore configuration after a reset as the vport will get wiped. + */ +struct idpf_vport_user_config_data { + struct idpf_rss_data rss_data; + u16 num_req_tx_qs; + u16 num_req_rx_qs; + u32 num_req_txq_desc; + u32 num_req_rxq_desc; + DECLARE_BITMAP(user_flags, __IDPF_USER_FLAGS_NBITS); + struct list_head mac_filter_list; +}; + +/** + * enum idpf_vport_config_flags - Vport config flags + * @IDPF_VPORT_REG_NETDEV: Register netdev + * @IDPF_VPORT_UP_REQUESTED: Set if interface up is requested on core reset + * @IDPF_VPORT_ADD_MAC_REQ: Asynchronous add ether address in flight + * @IDPF_VPORT_DEL_MAC_REQ: Asynchronous delete ether address in flight + * @IDPF_VPORT_CONFIG_FLAGS_NBITS: Must be last + */ +enum idpf_vport_config_flags { + IDPF_VPORT_REG_NETDEV, + IDPF_VPORT_UP_REQUESTED, + IDPF_VPORT_ADD_MAC_REQ, + IDPF_VPORT_DEL_MAC_REQ, + IDPF_VPORT_CONFIG_FLAGS_NBITS, +}; + +/** + * struct idpf_avail_queue_info + * @avail_rxq: Available RX queues + * @avail_txq: Available TX queues + * @avail_bufq: Available buffer queues + * @avail_complq: Available completion queues + * + * Maintain total queues available after allocating max queues to each vport. + */ +struct idpf_avail_queue_info { + u16 avail_rxq; + u16 avail_txq; + u16 avail_bufq; + u16 avail_complq; +}; + +/** + * struct idpf_vector_info - Utility structure to pass function arguments as a + * structure + * @num_req_vecs: Vectors required based on the number of queues updated by the + * user via ethtool + * @num_curr_vecs: Current number of vectors, must be >= @num_req_vecs + * @index: Relative starting index for vectors + * @default_vport: Vectors are for default vport + */ +struct idpf_vector_info { + u16 num_req_vecs; + u16 num_curr_vecs; + u16 index; + bool default_vport; +}; + +/** + * struct idpf_vector_lifo - Stack to maintain vector indexes used for vector + * distribution algorithm + * @top: Points to stack top i.e. next available vector index + * @base: Always points to start of the free pool + * @size: Total size of the vector stack + * @vec_idx: Array to store all the vector indexes + * + * Vector stack maintains all the relative vector indexes at the *adapter* + * level. This stack is divided into 2 parts, first one is called as 'default + * pool' and other one is called 'free pool'. Vector distribution algorithm + * gives priority to default vports in a way that at least IDPF_MIN_Q_VEC + * vectors are allocated per default vport and the relative vector indexes for + * those are maintained in default pool. Free pool contains all the unallocated + * vector indexes which can be allocated on-demand basis. Mailbox vector index + * is maintained in the default pool of the stack. + */ +struct idpf_vector_lifo { + u16 top; + u16 base; + u16 size; + u16 *vec_idx; +}; + +/** + * struct idpf_vport_config - Vport configuration data + * @user_config: see struct idpf_vport_user_config_data + * @max_q: Maximum possible queues + * @req_qs_chunks: Queue chunk data for requested queues + * @mac_filter_list_lock: Lock to protect mac filters + * @flags: See enum idpf_vport_config_flags + */ +struct idpf_vport_config { + struct idpf_vport_user_config_data user_config; + struct idpf_vport_max_q max_q; + void *req_qs_chunks; + spinlock_t mac_filter_list_lock; + DECLARE_BITMAP(flags, IDPF_VPORT_CONFIG_FLAGS_NBITS); +}; + +/** + * struct idpf_adapter - Device data struct generated on probe + * @pdev: PCI device struct given on probe + * @virt_ver_maj: Virtchnl version major + * @virt_ver_min: Virtchnl version minor + * @msg_enable: Debug message level enabled + * @mb_wait_count: Number of times mailbox was attempted initialization + * @state: Init state machine + * @flags: See enum idpf_flags + * @reset_reg: See struct idpf_reset_reg + * @hw: Device access data + * @num_req_msix: Requested number of MSIX vectors + * @num_avail_msix: Available number of MSIX vectors + * @num_msix_entries: Number of entries in MSIX table + * @msix_entries: MSIX table + * @req_vec_chunks: Requested vector chunk data + * @mb_vector: Mailbox vector data + * @vector_stack: Stack to store the msix vector indexes + * @irq_mb_handler: Handler for hard interrupt for mailbox + * @tx_timeout_count: Number of TX timeouts that have occurred + * @avail_queues: Device given queue limits + * @vports: Array to store vports created by the driver + * @netdevs: Associated Vport netdevs + * @vport_params_reqd: Vport params requested + * @vport_params_recvd: Vport params received + * @vport_ids: Array of device given vport identifiers + * @vport_config: Vport config parameters + * @max_vports: Maximum vports that can be allocated + * @num_alloc_vports: Current number of vports allocated + * @next_vport: Next free slot in pf->vport[] - 0-based! + * @init_task: Initialization task + * @init_wq: Workqueue for initialization task + * @serv_task: Periodically recurring maintenance task + * @serv_wq: Workqueue for service task + * @mbx_task: Task to handle mailbox interrupts + * @mbx_wq: Workqueue for mailbox responses + * @vc_event_task: Task to handle out of band virtchnl event notifications + * @vc_event_wq: Workqueue for virtchnl events + * @stats_task: Periodic statistics retrieval task + * @stats_wq: Workqueue for statistics task + * @caps: Negotiated capabilities with device + * @vchnl_wq: Wait queue for virtchnl messages + * @vc_state: Virtchnl message state + * @vc_msg: Virtchnl message buffer + * @dev_ops: See idpf_dev_ops + * @num_vfs: Number of allocated VFs through sysfs. PF does not directly talk + * to VFs but is used to initialize them + * @crc_enable: Enable CRC insertion offload + * @req_tx_splitq: TX split or single queue model to request + * @req_rx_splitq: RX split or single queue model to request + * @vport_ctrl_lock: Lock to protect the vport control flow + * @vector_lock: Lock to protect vector distribution + * @queue_lock: Lock to protect queue distribution + * @vc_buf_lock: Lock to protect virtchnl buffer + */ +struct idpf_adapter { + struct pci_dev *pdev; + u32 virt_ver_maj; + u32 virt_ver_min; + + u32 msg_enable; + u32 mb_wait_count; + enum idpf_state state; + DECLARE_BITMAP(flags, IDPF_FLAGS_NBITS); + struct idpf_reset_reg reset_reg; + struct idpf_hw hw; + u16 num_req_msix; + u16 num_avail_msix; + u16 num_msix_entries; + struct msix_entry *msix_entries; + struct virtchnl2_alloc_vectors *req_vec_chunks; + struct idpf_q_vector mb_vector; + struct idpf_vector_lifo vector_stack; + irqreturn_t (*irq_mb_handler)(int irq, void *data); + + u32 tx_timeout_count; + struct idpf_avail_queue_info avail_queues; + struct idpf_vport **vports; + struct net_device **netdevs; + struct virtchnl2_create_vport **vport_params_reqd; + struct virtchnl2_create_vport **vport_params_recvd; + u32 *vport_ids; + + struct idpf_vport_config **vport_config; + u16 max_vports; + u16 num_alloc_vports; + u16 next_vport; + + struct delayed_work init_task; + struct workqueue_struct *init_wq; + struct delayed_work serv_task; + struct workqueue_struct *serv_wq; + struct delayed_work mbx_task; + struct workqueue_struct *mbx_wq; + struct delayed_work vc_event_task; + struct workqueue_struct *vc_event_wq; + struct delayed_work stats_task; + struct workqueue_struct *stats_wq; + struct virtchnl2_get_capabilities caps; + + wait_queue_head_t vchnl_wq; + DECLARE_BITMAP(vc_state, IDPF_VC_NBITS); + char vc_msg[IDPF_CTLQ_MAX_BUF_LEN]; + struct idpf_dev_ops dev_ops; + int num_vfs; + bool crc_enable; + bool req_tx_splitq; + bool req_rx_splitq; + + struct mutex vport_ctrl_lock; + struct mutex vector_lock; + struct mutex queue_lock; + struct mutex vc_buf_lock; +}; + +/** + * idpf_is_queue_model_split - check if queue model is split + * @q_model: queue model single or split + * + * Returns true if queue model is split else false + */ +static inline int idpf_is_queue_model_split(u16 q_model) +{ + return q_model == VIRTCHNL2_QUEUE_MODEL_SPLIT; +} + +#define idpf_is_cap_ena(adapter, field, flag) \ + idpf_is_capability_ena(adapter, false, field, flag) +#define idpf_is_cap_ena_all(adapter, field, flag) \ + idpf_is_capability_ena(adapter, true, field, flag) + +bool idpf_is_capability_ena(struct idpf_adapter *adapter, bool all, + enum idpf_cap_field field, u64 flag); + +#define IDPF_CAP_RSS (\ + VIRTCHNL2_CAP_RSS_IPV4_TCP |\ + VIRTCHNL2_CAP_RSS_IPV4_TCP |\ + VIRTCHNL2_CAP_RSS_IPV4_UDP |\ + VIRTCHNL2_CAP_RSS_IPV4_SCTP |\ + VIRTCHNL2_CAP_RSS_IPV4_OTHER |\ + VIRTCHNL2_CAP_RSS_IPV6_TCP |\ + VIRTCHNL2_CAP_RSS_IPV6_TCP |\ + VIRTCHNL2_CAP_RSS_IPV6_UDP |\ + VIRTCHNL2_CAP_RSS_IPV6_SCTP |\ + VIRTCHNL2_CAP_RSS_IPV6_OTHER) + +#define IDPF_CAP_RSC (\ + VIRTCHNL2_CAP_RSC_IPV4_TCP |\ + VIRTCHNL2_CAP_RSC_IPV6_TCP) + +#define IDPF_CAP_HSPLIT (\ + VIRTCHNL2_CAP_RX_HSPLIT_AT_L4V4 |\ + VIRTCHNL2_CAP_RX_HSPLIT_AT_L4V6) + +#define IDPF_CAP_RX_CSUM_L4V4 (\ + VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_TCP |\ + VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_UDP) + +#define IDPF_CAP_RX_CSUM_L4V6 (\ + VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_TCP |\ + VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_UDP) + +#define IDPF_CAP_RX_CSUM (\ + VIRTCHNL2_CAP_RX_CSUM_L3_IPV4 |\ + VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_TCP |\ + VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_UDP |\ + VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_TCP |\ + VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_UDP) + +#define IDPF_CAP_SCTP_CSUM (\ + VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_SCTP |\ + VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_SCTP |\ + VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_SCTP |\ + VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_SCTP) + +#define IDPF_CAP_TUNNEL_TX_CSUM (\ + VIRTCHNL2_CAP_TX_CSUM_L3_SINGLE_TUNNEL |\ + VIRTCHNL2_CAP_TX_CSUM_L4_SINGLE_TUNNEL) + +/** + * idpf_get_reserved_vecs - Get reserved vectors + * @adapter: private data struct + */ +static inline u16 idpf_get_reserved_vecs(struct idpf_adapter *adapter) +{ + return le16_to_cpu(adapter->caps.num_allocated_vectors); +} + +/** + * idpf_get_default_vports - Get default number of vports + * @adapter: private data struct + */ +static inline u16 idpf_get_default_vports(struct idpf_adapter *adapter) +{ + return le16_to_cpu(adapter->caps.default_num_vports); +} + +/** + * idpf_get_max_vports - Get max number of vports + * @adapter: private data struct + */ +static inline u16 idpf_get_max_vports(struct idpf_adapter *adapter) +{ + return le16_to_cpu(adapter->caps.max_vports); +} + +/** + * idpf_get_max_tx_bufs - Get max scatter-gather buffers supported by the device + * @adapter: private data struct + */ +static inline unsigned int idpf_get_max_tx_bufs(struct idpf_adapter *adapter) +{ + return adapter->caps.max_sg_bufs_per_tx_pkt; +} + +/** + * idpf_get_min_tx_pkt_len - Get min packet length supported by the device + * @adapter: private data struct + */ +static inline u8 idpf_get_min_tx_pkt_len(struct idpf_adapter *adapter) +{ + u8 pkt_len = adapter->caps.min_sso_packet_len; + + return pkt_len ? pkt_len : IDPF_TX_MIN_PKT_LEN; +} + +/** + * idpf_get_reg_addr - Get BAR0 register address + * @adapter: private data struct + * @reg_offset: register offset value + * + * Based on the register offset, return the actual BAR0 register address + */ +static inline void __iomem *idpf_get_reg_addr(struct idpf_adapter *adapter, + resource_size_t reg_offset) +{ + return (void __iomem *)(adapter->hw.hw_addr + reg_offset); +} + +/** + * idpf_is_reset_detected - check if we were reset at some point + * @adapter: driver specific private structure + * + * Returns true if we are either in reset currently or were previously reset. + */ +static inline bool idpf_is_reset_detected(struct idpf_adapter *adapter) +{ + if (!adapter->hw.arq) + return true; + + return !(readl(idpf_get_reg_addr(adapter, adapter->hw.arq->reg.len)) & + adapter->hw.arq->reg.len_mask); +} + +/** + * idpf_is_reset_in_prog - check if reset is in progress + * @adapter: driver specific private structure + * + * Returns true if hard reset is in progress, false otherwise + */ +static inline bool idpf_is_reset_in_prog(struct idpf_adapter *adapter) +{ + return (test_bit(IDPF_HR_RESET_IN_PROG, adapter->flags) || + test_bit(IDPF_HR_FUNC_RESET, adapter->flags) || + test_bit(IDPF_HR_DRV_LOAD, adapter->flags)); +} + +/** + * idpf_netdev_to_vport - get a vport handle from a netdev + * @netdev: network interface device structure + */ +static inline struct idpf_vport *idpf_netdev_to_vport(struct net_device *netdev) +{ + struct idpf_netdev_priv *np = netdev_priv(netdev); + + return np->vport; +} + +/** + * idpf_netdev_to_adapter - Get adapter handle from a netdev + * @netdev: Network interface device structure + */ +static inline struct idpf_adapter *idpf_netdev_to_adapter(struct net_device *netdev) +{ + struct idpf_netdev_priv *np = netdev_priv(netdev); + + return np->adapter; +} + +/** + * idpf_is_feature_ena - Determine if a particular feature is enabled + * @vport: Vport to check + * @feature: Netdev flag to check + * + * Returns true or false if a particular feature is enabled. + */ +static inline bool idpf_is_feature_ena(const struct idpf_vport *vport, + netdev_features_t feature) +{ + return vport->netdev->features & feature; +} + +/** + * idpf_get_max_tx_hdr_size -- get the size of tx header + * @adapter: Driver specific private structure + */ +static inline u16 idpf_get_max_tx_hdr_size(struct idpf_adapter *adapter) +{ + return le16_to_cpu(adapter->caps.max_tx_hdr_size); +} + +/** + * idpf_vport_ctrl_lock - Acquire the vport control lock + * @netdev: Network interface device structure + * + * This lock should be used by non-datapath code to protect against vport + * destruction. + */ +static inline void idpf_vport_ctrl_lock(struct net_device *netdev) +{ + struct idpf_netdev_priv *np = netdev_priv(netdev); + + mutex_lock(&np->adapter->vport_ctrl_lock); +} + +/** + * idpf_vport_ctrl_unlock - Release the vport control lock + * @netdev: Network interface device structure + */ +static inline void idpf_vport_ctrl_unlock(struct net_device *netdev) +{ + struct idpf_netdev_priv *np = netdev_priv(netdev); + + mutex_unlock(&np->adapter->vport_ctrl_lock); +} + +void idpf_statistics_task(struct work_struct *work); +void idpf_init_task(struct work_struct *work); +void idpf_service_task(struct work_struct *work); +void idpf_mbx_task(struct work_struct *work); +void idpf_vc_event_task(struct work_struct *work); +void idpf_dev_ops_init(struct idpf_adapter *adapter); +void idpf_vf_dev_ops_init(struct idpf_adapter *adapter); +int idpf_vport_adjust_qs(struct idpf_vport *vport); +int idpf_init_dflt_mbx(struct idpf_adapter *adapter); +void idpf_deinit_dflt_mbx(struct idpf_adapter *adapter); +int idpf_vc_core_init(struct idpf_adapter *adapter); +void idpf_vc_core_deinit(struct idpf_adapter *adapter); +int idpf_intr_req(struct idpf_adapter *adapter); +void idpf_intr_rel(struct idpf_adapter *adapter); +int idpf_get_reg_intr_vecs(struct idpf_vport *vport, + struct idpf_vec_regs *reg_vals); +u16 idpf_get_max_tx_hdr_size(struct idpf_adapter *adapter); +int idpf_send_delete_queues_msg(struct idpf_vport *vport); +int idpf_send_add_queues_msg(const struct idpf_vport *vport, u16 num_tx_q, + u16 num_complq, u16 num_rx_q, u16 num_rx_bufq); +int idpf_initiate_soft_reset(struct idpf_vport *vport, + enum idpf_vport_reset_cause reset_cause); +int idpf_send_enable_vport_msg(struct idpf_vport *vport); +int idpf_send_disable_vport_msg(struct idpf_vport *vport); +int idpf_send_destroy_vport_msg(struct idpf_vport *vport); +int idpf_send_get_rx_ptype_msg(struct idpf_vport *vport); +int idpf_send_ena_dis_loopback_msg(struct idpf_vport *vport); +int idpf_send_get_set_rss_key_msg(struct idpf_vport *vport, bool get); +int idpf_send_get_set_rss_lut_msg(struct idpf_vport *vport, bool get); +int idpf_send_dealloc_vectors_msg(struct idpf_adapter *adapter); +int idpf_send_alloc_vectors_msg(struct idpf_adapter *adapter, u16 num_vectors); +void idpf_deinit_task(struct idpf_adapter *adapter); +int idpf_req_rel_vector_indexes(struct idpf_adapter *adapter, + u16 *q_vector_idxs, + struct idpf_vector_info *vec_info); +int idpf_vport_alloc_vec_indexes(struct idpf_vport *vport); +int idpf_send_get_stats_msg(struct idpf_vport *vport); +int idpf_get_vec_ids(struct idpf_adapter *adapter, + u16 *vecids, int num_vecids, + struct virtchnl2_vector_chunks *chunks); +int idpf_recv_mb_msg(struct idpf_adapter *adapter, u32 op, + void *msg, int msg_size); +int idpf_send_mb_msg(struct idpf_adapter *adapter, u32 op, + u16 msg_size, u8 *msg); +void idpf_set_ethtool_ops(struct net_device *netdev); +int idpf_vport_alloc_max_qs(struct idpf_adapter *adapter, + struct idpf_vport_max_q *max_q); +void idpf_vport_dealloc_max_qs(struct idpf_adapter *adapter, + struct idpf_vport_max_q *max_q); +int idpf_add_del_mac_filters(struct idpf_vport *vport, + struct idpf_netdev_priv *np, + bool add, bool async); +int idpf_set_promiscuous(struct idpf_adapter *adapter, + struct idpf_vport_user_config_data *config_data, + u32 vport_id); +int idpf_send_disable_queues_msg(struct idpf_vport *vport); +void idpf_vport_init(struct idpf_vport *vport, struct idpf_vport_max_q *max_q); +u32 idpf_get_vport_id(struct idpf_vport *vport); +int idpf_vport_queue_ids_init(struct idpf_vport *vport); +int idpf_queue_reg_init(struct idpf_vport *vport); +int idpf_send_config_queues_msg(struct idpf_vport *vport); +int idpf_send_enable_queues_msg(struct idpf_vport *vport); +int idpf_send_create_vport_msg(struct idpf_adapter *adapter, + struct idpf_vport_max_q *max_q); +int idpf_check_supported_desc_ids(struct idpf_vport *vport); +void idpf_vport_intr_write_itr(struct idpf_q_vector *q_vector, + u16 itr, bool tx); +int idpf_send_map_unmap_queue_vector_msg(struct idpf_vport *vport, bool map); +int idpf_send_set_sriov_vfs_msg(struct idpf_adapter *adapter, u16 num_vfs); +int idpf_sriov_configure(struct pci_dev *pdev, int num_vfs); + +#endif /* !_IDPF_H_ */ diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq.c b/drivers/net/ethernet/intel/idpf/idpf_controlq.c new file mode 100644 index 000000000000..c7f43d2fcd13 --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/idpf_controlq.c @@ -0,0 +1,621 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2023 Intel Corporation */ + +#include "idpf_controlq.h" + +/** + * idpf_ctlq_setup_regs - initialize control queue registers + * @cq: pointer to the specific control queue + * @q_create_info: structs containing info for each queue to be initialized + */ +static void idpf_ctlq_setup_regs(struct idpf_ctlq_info *cq, + struct idpf_ctlq_create_info *q_create_info) +{ + /* set control queue registers in our local struct */ + cq->reg.head = q_create_info->reg.head; + cq->reg.tail = q_create_info->reg.tail; + cq->reg.len = q_create_info->reg.len; + cq->reg.bah = q_create_info->reg.bah; + cq->reg.bal = q_create_info->reg.bal; + cq->reg.len_mask = q_create_info->reg.len_mask; + cq->reg.len_ena_mask = q_create_info->reg.len_ena_mask; + cq->reg.head_mask = q_create_info->reg.head_mask; +} + +/** + * idpf_ctlq_init_regs - Initialize control queue registers + * @hw: pointer to hw struct + * @cq: pointer to the specific Control queue + * @is_rxq: true if receive control queue, false otherwise + * + * Initialize registers. The caller is expected to have already initialized the + * descriptor ring memory and buffer memory + */ +static void idpf_ctlq_init_regs(struct idpf_hw *hw, struct idpf_ctlq_info *cq, + bool is_rxq) +{ + /* Update tail to post pre-allocated buffers for rx queues */ + if (is_rxq) + wr32(hw, cq->reg.tail, (u32)(cq->ring_size - 1)); + + /* For non-Mailbox control queues only TAIL need to be set */ + if (cq->q_id != -1) + return; + + /* Clear Head for both send or receive */ + wr32(hw, cq->reg.head, 0); + + /* set starting point */ + wr32(hw, cq->reg.bal, lower_32_bits(cq->desc_ring.pa)); + wr32(hw, cq->reg.bah, upper_32_bits(cq->desc_ring.pa)); + wr32(hw, cq->reg.len, (cq->ring_size | cq->reg.len_ena_mask)); +} + +/** + * idpf_ctlq_init_rxq_bufs - populate receive queue descriptors with buf + * @cq: pointer to the specific Control queue + * + * Record the address of the receive queue DMA buffers in the descriptors. + * The buffers must have been previously allocated. + */ +static void idpf_ctlq_init_rxq_bufs(struct idpf_ctlq_info *cq) +{ + int i; + + for (i = 0; i < cq->ring_size; i++) { + struct idpf_ctlq_desc *desc = IDPF_CTLQ_DESC(cq, i); + struct idpf_dma_mem *bi = cq->bi.rx_buff[i]; + + /* No buffer to post to descriptor, continue */ + if (!bi) + continue; + + desc->flags = + cpu_to_le16(IDPF_CTLQ_FLAG_BUF | IDPF_CTLQ_FLAG_RD); + desc->opcode = 0; + desc->datalen = cpu_to_le16(bi->size); + desc->ret_val = 0; + desc->v_opcode_dtype = 0; + desc->v_retval = 0; + desc->params.indirect.addr_high = + cpu_to_le32(upper_32_bits(bi->pa)); + desc->params.indirect.addr_low = + cpu_to_le32(lower_32_bits(bi->pa)); + desc->params.indirect.param0 = 0; + desc->params.indirect.sw_cookie = 0; + desc->params.indirect.v_flags = 0; + } +} + +/** + * idpf_ctlq_shutdown - shutdown the CQ + * @hw: pointer to hw struct + * @cq: pointer to the specific Control queue + * + * The main shutdown routine for any controq queue + */ +static void idpf_ctlq_shutdown(struct idpf_hw *hw, struct idpf_ctlq_info *cq) +{ + mutex_lock(&cq->cq_lock); + + /* free ring buffers and the ring itself */ + idpf_ctlq_dealloc_ring_res(hw, cq); + + /* Set ring_size to 0 to indicate uninitialized queue */ + cq->ring_size = 0; + + mutex_unlock(&cq->cq_lock); + mutex_destroy(&cq->cq_lock); +} + +/** + * idpf_ctlq_add - add one control queue + * @hw: pointer to hardware struct + * @qinfo: info for queue to be created + * @cq_out: (output) double pointer to control queue to be created + * + * Allocate and initialize a control queue and add it to the control queue list. + * The cq parameter will be allocated/initialized and passed back to the caller + * if no errors occur. + * + * Note: idpf_ctlq_init must be called prior to any calls to idpf_ctlq_add + */ +int idpf_ctlq_add(struct idpf_hw *hw, + struct idpf_ctlq_create_info *qinfo, + struct idpf_ctlq_info **cq_out) +{ + struct idpf_ctlq_info *cq; + bool is_rxq = false; + int err; + + cq = kzalloc(sizeof(*cq), GFP_KERNEL); + if (!cq) + return -ENOMEM; + + cq->cq_type = qinfo->type; + cq->q_id = qinfo->id; + cq->buf_size = qinfo->buf_size; + cq->ring_size = qinfo->len; + + cq->next_to_use = 0; + cq->next_to_clean = 0; + cq->next_to_post = cq->ring_size - 1; + + switch (qinfo->type) { + case IDPF_CTLQ_TYPE_MAILBOX_RX: + is_rxq = true; + fallthrough; + case IDPF_CTLQ_TYPE_MAILBOX_TX: + err = idpf_ctlq_alloc_ring_res(hw, cq); + break; + default: + err = -EBADR; + break; + } + + if (err) + goto init_free_q; + + if (is_rxq) { + idpf_ctlq_init_rxq_bufs(cq); + } else { + /* Allocate the array of msg pointers for TX queues */ + cq->bi.tx_msg = kcalloc(qinfo->len, + sizeof(struct idpf_ctlq_msg *), + GFP_KERNEL); + if (!cq->bi.tx_msg) { + err = -ENOMEM; + goto init_dealloc_q_mem; + } + } + + idpf_ctlq_setup_regs(cq, qinfo); + + idpf_ctlq_init_regs(hw, cq, is_rxq); + + mutex_init(&cq->cq_lock); + + list_add(&cq->cq_list, &hw->cq_list_head); + + *cq_out = cq; + + return 0; + +init_dealloc_q_mem: + /* free ring buffers and the ring itself */ + idpf_ctlq_dealloc_ring_res(hw, cq); +init_free_q: + kfree(cq); + + return err; +} + +/** + * idpf_ctlq_remove - deallocate and remove specified control queue + * @hw: pointer to hardware struct + * @cq: pointer to control queue to be removed + */ +void idpf_ctlq_remove(struct idpf_hw *hw, + struct idpf_ctlq_info *cq) +{ + list_del(&cq->cq_list); + idpf_ctlq_shutdown(hw, cq); + kfree(cq); +} + +/** + * idpf_ctlq_init - main initialization routine for all control queues + * @hw: pointer to hardware struct + * @num_q: number of queues to initialize + * @q_info: array of structs containing info for each queue to be initialized + * + * This initializes any number and any type of control queues. This is an all + * or nothing routine; if one fails, all previously allocated queues will be + * destroyed. This must be called prior to using the individual add/remove + * APIs. + */ +int idpf_ctlq_init(struct idpf_hw *hw, u8 num_q, + struct idpf_ctlq_create_info *q_info) +{ + struct idpf_ctlq_info *cq, *tmp; + int err; + int i; + + INIT_LIST_HEAD(&hw->cq_list_head); + + for (i = 0; i < num_q; i++) { + struct idpf_ctlq_create_info *qinfo = q_info + i; + + err = idpf_ctlq_add(hw, qinfo, &cq); + if (err) + goto init_destroy_qs; + } + + return 0; + +init_destroy_qs: + list_for_each_entry_safe(cq, tmp, &hw->cq_list_head, cq_list) + idpf_ctlq_remove(hw, cq); + + return err; +} + +/** + * idpf_ctlq_deinit - destroy all control queues + * @hw: pointer to hw struct + */ +void idpf_ctlq_deinit(struct idpf_hw *hw) +{ + struct idpf_ctlq_info *cq, *tmp; + + list_for_each_entry_safe(cq, tmp, &hw->cq_list_head, cq_list) + idpf_ctlq_remove(hw, cq); +} + +/** + * idpf_ctlq_send - send command to Control Queue (CTQ) + * @hw: pointer to hw struct + * @cq: handle to control queue struct to send on + * @num_q_msg: number of messages to send on control queue + * @q_msg: pointer to array of queue messages to be sent + * + * The caller is expected to allocate DMAable buffers and pass them to the + * send routine via the q_msg struct / control queue specific data struct. + * The control queue will hold a reference to each send message until + * the completion for that message has been cleaned. + */ +int idpf_ctlq_send(struct idpf_hw *hw, struct idpf_ctlq_info *cq, + u16 num_q_msg, struct idpf_ctlq_msg q_msg[]) +{ + struct idpf_ctlq_desc *desc; + int num_desc_avail; + int err = 0; + int i; + + mutex_lock(&cq->cq_lock); + + /* Ensure there are enough descriptors to send all messages */ + num_desc_avail = IDPF_CTLQ_DESC_UNUSED(cq); + if (num_desc_avail == 0 || num_desc_avail < num_q_msg) { + err = -ENOSPC; + goto err_unlock; + } + + for (i = 0; i < num_q_msg; i++) { + struct idpf_ctlq_msg *msg = &q_msg[i]; + + desc = IDPF_CTLQ_DESC(cq, cq->next_to_use); + + desc->opcode = cpu_to_le16(msg->opcode); + desc->pfid_vfid = cpu_to_le16(msg->func_id); + + desc->v_opcode_dtype = cpu_to_le32(msg->cookie.mbx.chnl_opcode); + desc->v_retval = cpu_to_le32(msg->cookie.mbx.chnl_retval); + + desc->flags = cpu_to_le16((msg->host_id & IDPF_HOST_ID_MASK) << + IDPF_CTLQ_FLAG_HOST_ID_S); + if (msg->data_len) { + struct idpf_dma_mem *buff = msg->ctx.indirect.payload; + + desc->datalen |= cpu_to_le16(msg->data_len); + desc->flags |= cpu_to_le16(IDPF_CTLQ_FLAG_BUF); + desc->flags |= cpu_to_le16(IDPF_CTLQ_FLAG_RD); + + /* Update the address values in the desc with the pa + * value for respective buffer + */ + desc->params.indirect.addr_high = + cpu_to_le32(upper_32_bits(buff->pa)); + desc->params.indirect.addr_low = + cpu_to_le32(lower_32_bits(buff->pa)); + + memcpy(&desc->params, msg->ctx.indirect.context, + IDPF_INDIRECT_CTX_SIZE); + } else { + memcpy(&desc->params, msg->ctx.direct, + IDPF_DIRECT_CTX_SIZE); + } + + /* Store buffer info */ + cq->bi.tx_msg[cq->next_to_use] = msg; + + (cq->next_to_use)++; + if (cq->next_to_use == cq->ring_size) + cq->next_to_use = 0; + } + + /* Force memory write to complete before letting hardware + * know that there are new descriptors to fetch. + */ + dma_wmb(); + + wr32(hw, cq->reg.tail, cq->next_to_use); + +err_unlock: + mutex_unlock(&cq->cq_lock); + + return err; +} + +/** + * idpf_ctlq_clean_sq - reclaim send descriptors on HW write back for the + * requested queue + * @cq: pointer to the specific Control queue + * @clean_count: (input|output) number of descriptors to clean as input, and + * number of descriptors actually cleaned as output + * @msg_status: (output) pointer to msg pointer array to be populated; needs + * to be allocated by caller + * + * Returns an array of message pointers associated with the cleaned + * descriptors. The pointers are to the original ctlq_msgs sent on the cleaned + * descriptors. The status will be returned for each; any messages that failed + * to send will have a non-zero status. The caller is expected to free original + * ctlq_msgs and free or reuse the DMA buffers. + */ +int idpf_ctlq_clean_sq(struct idpf_ctlq_info *cq, u16 *clean_count, + struct idpf_ctlq_msg *msg_status[]) +{ + struct idpf_ctlq_desc *desc; + u16 i, num_to_clean; + u16 ntc, desc_err; + + if (*clean_count == 0) + return 0; + if (*clean_count > cq->ring_size) + return -EBADR; + + mutex_lock(&cq->cq_lock); + + ntc = cq->next_to_clean; + + num_to_clean = *clean_count; + + for (i = 0; i < num_to_clean; i++) { + /* Fetch next descriptor and check if marked as done */ + desc = IDPF_CTLQ_DESC(cq, ntc); + if (!(le16_to_cpu(desc->flags) & IDPF_CTLQ_FLAG_DD)) + break; + + /* strip off FW internal code */ + desc_err = le16_to_cpu(desc->ret_val) & 0xff; + + msg_status[i] = cq->bi.tx_msg[ntc]; + msg_status[i]->status = desc_err; + + cq->bi.tx_msg[ntc] = NULL; + + /* Zero out any stale data */ + memset(desc, 0, sizeof(*desc)); + + ntc++; + if (ntc == cq->ring_size) + ntc = 0; + } + + cq->next_to_clean = ntc; + + mutex_unlock(&cq->cq_lock); + + /* Return number of descriptors actually cleaned */ + *clean_count = i; + + return 0; +} + +/** + * idpf_ctlq_post_rx_buffs - post buffers to descriptor ring + * @hw: pointer to hw struct + * @cq: pointer to control queue handle + * @buff_count: (input|output) input is number of buffers caller is trying to + * return; output is number of buffers that were not posted + * @buffs: array of pointers to dma mem structs to be given to hardware + * + * Caller uses this function to return DMA buffers to the descriptor ring after + * consuming them; buff_count will be the number of buffers. + * + * Note: this function needs to be called after a receive call even + * if there are no DMA buffers to be returned, i.e. buff_count = 0, + * buffs = NULL to support direct commands + */ +int idpf_ctlq_post_rx_buffs(struct idpf_hw *hw, struct idpf_ctlq_info *cq, + u16 *buff_count, struct idpf_dma_mem **buffs) +{ + struct idpf_ctlq_desc *desc; + u16 ntp = cq->next_to_post; + bool buffs_avail = false; + u16 tbp = ntp + 1; + int i = 0; + + if (*buff_count > cq->ring_size) + return -EBADR; + + if (*buff_count > 0) + buffs_avail = true; + + mutex_lock(&cq->cq_lock); + + if (tbp >= cq->ring_size) + tbp = 0; + + if (tbp == cq->next_to_clean) + /* Nothing to do */ + goto post_buffs_out; + + /* Post buffers for as many as provided or up until the last one used */ + while (ntp != cq->next_to_clean) { + desc = IDPF_CTLQ_DESC(cq, ntp); + + if (cq->bi.rx_buff[ntp]) + goto fill_desc; + if (!buffs_avail) { + /* If the caller hasn't given us any buffers or + * there are none left, search the ring itself + * for an available buffer to move to this + * entry starting at the next entry in the ring + */ + tbp = ntp + 1; + + /* Wrap ring if necessary */ + if (tbp >= cq->ring_size) + tbp = 0; + + while (tbp != cq->next_to_clean) { + if (cq->bi.rx_buff[tbp]) { + cq->bi.rx_buff[ntp] = + cq->bi.rx_buff[tbp]; + cq->bi.rx_buff[tbp] = NULL; + + /* Found a buffer, no need to + * search anymore + */ + break; + } + + /* Wrap ring if necessary */ + tbp++; + if (tbp >= cq->ring_size) + tbp = 0; + } + + if (tbp == cq->next_to_clean) + goto post_buffs_out; + } else { + /* Give back pointer to DMA buffer */ + cq->bi.rx_buff[ntp] = buffs[i]; + i++; + + if (i >= *buff_count) + buffs_avail = false; + } + +fill_desc: + desc->flags = + cpu_to_le16(IDPF_CTLQ_FLAG_BUF | IDPF_CTLQ_FLAG_RD); + + /* Post buffers to descriptor */ + desc->datalen = cpu_to_le16(cq->bi.rx_buff[ntp]->size); + desc->params.indirect.addr_high = + cpu_to_le32(upper_32_bits(cq->bi.rx_buff[ntp]->pa)); + desc->params.indirect.addr_low = + cpu_to_le32(lower_32_bits(cq->bi.rx_buff[ntp]->pa)); + + ntp++; + if (ntp == cq->ring_size) + ntp = 0; + } + +post_buffs_out: + /* Only update tail if buffers were actually posted */ + if (cq->next_to_post != ntp) { + if (ntp) + /* Update next_to_post to ntp - 1 since current ntp + * will not have a buffer + */ + cq->next_to_post = ntp - 1; + else + /* Wrap to end of end ring since current ntp is 0 */ + cq->next_to_post = cq->ring_size - 1; + + wr32(hw, cq->reg.tail, cq->next_to_post); + } + + mutex_unlock(&cq->cq_lock); + + /* return the number of buffers that were not posted */ + *buff_count = *buff_count - i; + + return 0; +} + +/** + * idpf_ctlq_recv - receive control queue message call back + * @cq: pointer to control queue handle to receive on + * @num_q_msg: (input|output) input number of messages that should be received; + * output number of messages actually received + * @q_msg: (output) array of received control queue messages on this q; + * needs to be pre-allocated by caller for as many messages as requested + * + * Called by interrupt handler or polling mechanism. Caller is expected + * to free buffers + */ +int idpf_ctlq_recv(struct idpf_ctlq_info *cq, u16 *num_q_msg, + struct idpf_ctlq_msg *q_msg) +{ + u16 num_to_clean, ntc, flags; + struct idpf_ctlq_desc *desc; + int err = 0; + u16 i; + + if (*num_q_msg == 0) + return 0; + else if (*num_q_msg > cq->ring_size) + return -EBADR; + + /* take the lock before we start messing with the ring */ + mutex_lock(&cq->cq_lock); + + ntc = cq->next_to_clean; + + num_to_clean = *num_q_msg; + + for (i = 0; i < num_to_clean; i++) { + /* Fetch next descriptor and check if marked as done */ + desc = IDPF_CTLQ_DESC(cq, ntc); + flags = le16_to_cpu(desc->flags); + + if (!(flags & IDPF_CTLQ_FLAG_DD)) + break; + + q_msg[i].vmvf_type = (flags & + (IDPF_CTLQ_FLAG_FTYPE_VM | + IDPF_CTLQ_FLAG_FTYPE_PF)) >> + IDPF_CTLQ_FLAG_FTYPE_S; + + if (flags & IDPF_CTLQ_FLAG_ERR) + err = -EBADMSG; + + q_msg[i].cookie.mbx.chnl_opcode = + le32_to_cpu(desc->v_opcode_dtype); + q_msg[i].cookie.mbx.chnl_retval = + le32_to_cpu(desc->v_retval); + + q_msg[i].opcode = le16_to_cpu(desc->opcode); + q_msg[i].data_len = le16_to_cpu(desc->datalen); + q_msg[i].status = le16_to_cpu(desc->ret_val); + + if (desc->datalen) { + memcpy(q_msg[i].ctx.indirect.context, + &desc->params.indirect, IDPF_INDIRECT_CTX_SIZE); + + /* Assign pointer to dma buffer to ctlq_msg array + * to be given to upper layer + */ + q_msg[i].ctx.indirect.payload = cq->bi.rx_buff[ntc]; + + /* Zero out pointer to DMA buffer info; + * will be repopulated by post buffers API + */ + cq->bi.rx_buff[ntc] = NULL; + } else { + memcpy(q_msg[i].ctx.direct, desc->params.raw, + IDPF_DIRECT_CTX_SIZE); + } + + /* Zero out stale data in descriptor */ + memset(desc, 0, sizeof(struct idpf_ctlq_desc)); + + ntc++; + if (ntc == cq->ring_size) + ntc = 0; + } + + cq->next_to_clean = ntc; + + mutex_unlock(&cq->cq_lock); + + *num_q_msg = i; + if (*num_q_msg == 0) + err = -ENOMSG; + + return err; +} diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq.h b/drivers/net/ethernet/intel/idpf/idpf_controlq.h new file mode 100644 index 000000000000..c1aba09e9856 --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/idpf_controlq.h @@ -0,0 +1,130 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2023 Intel Corporation */ + +#ifndef _IDPF_CONTROLQ_H_ +#define _IDPF_CONTROLQ_H_ + +#include <linux/slab.h> + +#include "idpf_controlq_api.h" + +/* Maximum buffer length for all control queue types */ +#define IDPF_CTLQ_MAX_BUF_LEN 4096 + +#define IDPF_CTLQ_DESC(R, i) \ + (&(((struct idpf_ctlq_desc *)((R)->desc_ring.va))[i])) + +#define IDPF_CTLQ_DESC_UNUSED(R) \ + ((u16)((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->ring_size) + \ + (R)->next_to_clean - (R)->next_to_use - 1)) + +/* Control Queue default settings */ +#define IDPF_CTRL_SQ_CMD_TIMEOUT 250 /* msecs */ + +struct idpf_ctlq_desc { + /* Control queue descriptor flags */ + __le16 flags; + /* Control queue message opcode */ + __le16 opcode; + __le16 datalen; /* 0 for direct commands */ + union { + __le16 ret_val; + __le16 pfid_vfid; +#define IDPF_CTLQ_DESC_VF_ID_S 0 +#define IDPF_CTLQ_DESC_VF_ID_M (0x7FF << IDPF_CTLQ_DESC_VF_ID_S) +#define IDPF_CTLQ_DESC_PF_ID_S 11 +#define IDPF_CTLQ_DESC_PF_ID_M (0x1F << IDPF_CTLQ_DESC_PF_ID_S) + }; + + /* Virtchnl message opcode and virtchnl descriptor type + * v_opcode=[27:0], v_dtype=[31:28] + */ + __le32 v_opcode_dtype; + /* Virtchnl return value */ + __le32 v_retval; + union { + struct { + __le32 param0; + __le32 param1; + __le32 param2; + __le32 param3; + } direct; + struct { + __le32 param0; + __le16 sw_cookie; + /* Virtchnl flags */ + __le16 v_flags; + __le32 addr_high; + __le32 addr_low; + } indirect; + u8 raw[16]; + } params; +}; + +/* Flags sub-structure + * |0 |1 |2 |3 |4 |5 |6 |7 |8 |9 |10 |11 |12 |13 |14 |15 | + * |DD |CMP|ERR| * RSV * |FTYPE | *RSV* |RD |VFC|BUF| HOST_ID | + */ +/* command flags and offsets */ +#define IDPF_CTLQ_FLAG_DD_S 0 +#define IDPF_CTLQ_FLAG_CMP_S 1 +#define IDPF_CTLQ_FLAG_ERR_S 2 +#define IDPF_CTLQ_FLAG_FTYPE_S 6 +#define IDPF_CTLQ_FLAG_RD_S 10 +#define IDPF_CTLQ_FLAG_VFC_S 11 +#define IDPF_CTLQ_FLAG_BUF_S 12 +#define IDPF_CTLQ_FLAG_HOST_ID_S 13 + +#define IDPF_CTLQ_FLAG_DD BIT(IDPF_CTLQ_FLAG_DD_S) /* 0x1 */ +#define IDPF_CTLQ_FLAG_CMP BIT(IDPF_CTLQ_FLAG_CMP_S) /* 0x2 */ +#define IDPF_CTLQ_FLAG_ERR BIT(IDPF_CTLQ_FLAG_ERR_S) /* 0x4 */ +#define IDPF_CTLQ_FLAG_FTYPE_VM BIT(IDPF_CTLQ_FLAG_FTYPE_S) /* 0x40 */ +#define IDPF_CTLQ_FLAG_FTYPE_PF BIT(IDPF_CTLQ_FLAG_FTYPE_S + 1) /* 0x80 */ +#define IDPF_CTLQ_FLAG_RD BIT(IDPF_CTLQ_FLAG_RD_S) /* 0x400 */ +#define IDPF_CTLQ_FLAG_VFC BIT(IDPF_CTLQ_FLAG_VFC_S) /* 0x800 */ +#define IDPF_CTLQ_FLAG_BUF BIT(IDPF_CTLQ_FLAG_BUF_S) /* 0x1000 */ + +/* Host ID is a special field that has 3b and not a 1b flag */ +#define IDPF_CTLQ_FLAG_HOST_ID_M MAKE_MASK(0x7000UL, IDPF_CTLQ_FLAG_HOST_ID_S) + +struct idpf_mbxq_desc { + u8 pad[8]; /* CTLQ flags/opcode/len/retval fields */ + u32 chnl_opcode; /* avoid confusion with desc->opcode */ + u32 chnl_retval; /* ditto for desc->retval */ + u32 pf_vf_id; /* used by CP when sending to PF */ +}; + +/* Define the driver hardware struct to replace other control structs as needed + * Align to ctlq_hw_info + */ +struct idpf_hw { + void __iomem *hw_addr; + resource_size_t hw_addr_len; + + struct idpf_adapter *back; + + /* control queue - send and receive */ + struct idpf_ctlq_info *asq; + struct idpf_ctlq_info *arq; + + /* pci info */ + u16 device_id; + u16 vendor_id; + u16 subsystem_device_id; + u16 subsystem_vendor_id; + u8 revision_id; + bool adapter_stopped; + + struct list_head cq_list_head; +}; + +int idpf_ctlq_alloc_ring_res(struct idpf_hw *hw, + struct idpf_ctlq_info *cq); + +void idpf_ctlq_dealloc_ring_res(struct idpf_hw *hw, struct idpf_ctlq_info *cq); + +/* prototype for functions used for dynamic memory allocation */ +void *idpf_alloc_dma_mem(struct idpf_hw *hw, struct idpf_dma_mem *mem, + u64 size); +void idpf_free_dma_mem(struct idpf_hw *hw, struct idpf_dma_mem *mem); +#endif /* _IDPF_CONTROLQ_H_ */ diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h b/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h new file mode 100644 index 000000000000..8dee098bbfb0 --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h @@ -0,0 +1,169 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2023 Intel Corporation */ + +#ifndef _IDPF_CONTROLQ_API_H_ +#define _IDPF_CONTROLQ_API_H_ + +#include "idpf_mem.h" + +struct idpf_hw; + +/* Used for queue init, response and events */ +enum idpf_ctlq_type { + IDPF_CTLQ_TYPE_MAILBOX_TX = 0, + IDPF_CTLQ_TYPE_MAILBOX_RX = 1, + IDPF_CTLQ_TYPE_CONFIG_TX = 2, + IDPF_CTLQ_TYPE_CONFIG_RX = 3, + IDPF_CTLQ_TYPE_EVENT_RX = 4, + IDPF_CTLQ_TYPE_RDMA_TX = 5, + IDPF_CTLQ_TYPE_RDMA_RX = 6, + IDPF_CTLQ_TYPE_RDMA_COMPL = 7 +}; + +/* Generic Control Queue Structures */ +struct idpf_ctlq_reg { + /* used for queue tracking */ + u32 head; + u32 tail; + /* Below applies only to default mb (if present) */ + u32 len; + u32 bah; + u32 bal; + u32 len_mask; + u32 len_ena_mask; + u32 head_mask; +}; + +/* Generic queue msg structure */ +struct idpf_ctlq_msg { + u8 vmvf_type; /* represents the source of the message on recv */ +#define IDPF_VMVF_TYPE_VF 0 +#define IDPF_VMVF_TYPE_VM 1 +#define IDPF_VMVF_TYPE_PF 2 + u8 host_id; + /* 3b field used only when sending a message to CP - to be used in + * combination with target func_id to route the message + */ +#define IDPF_HOST_ID_MASK 0x7 + + u16 opcode; + u16 data_len; /* data_len = 0 when no payload is attached */ + union { + u16 func_id; /* when sending a message */ + u16 status; /* when receiving a message */ + }; + union { + struct { + u32 chnl_opcode; + u32 chnl_retval; + } mbx; + } cookie; + union { +#define IDPF_DIRECT_CTX_SIZE 16 +#define IDPF_INDIRECT_CTX_SIZE 8 + /* 16 bytes of context can be provided or 8 bytes of context + * plus the address of a DMA buffer + */ + u8 direct[IDPF_DIRECT_CTX_SIZE]; + struct { + u8 context[IDPF_INDIRECT_CTX_SIZE]; + struct idpf_dma_mem *payload; + } indirect; + } ctx; +}; + +/* Generic queue info structures */ +/* MB, CONFIG and EVENT q do not have extended info */ +struct idpf_ctlq_create_info { + enum idpf_ctlq_type type; + int id; /* absolute queue offset passed as input + * -1 for default mailbox if present + */ + u16 len; /* Queue length passed as input */ + u16 buf_size; /* buffer size passed as input */ + u64 base_address; /* output, HPA of the Queue start */ + struct idpf_ctlq_reg reg; /* registers accessed by ctlqs */ + + int ext_info_size; + void *ext_info; /* Specific to q type */ +}; + +/* Control Queue information */ +struct idpf_ctlq_info { + struct list_head cq_list; + + enum idpf_ctlq_type cq_type; + int q_id; + struct mutex cq_lock; /* control queue lock */ + /* used for interrupt processing */ + u16 next_to_use; + u16 next_to_clean; + u16 next_to_post; /* starting descriptor to post buffers + * to after recev + */ + + struct idpf_dma_mem desc_ring; /* descriptor ring memory + * idpf_dma_mem is defined in OSdep.h + */ + union { + struct idpf_dma_mem **rx_buff; + struct idpf_ctlq_msg **tx_msg; + } bi; + + u16 buf_size; /* queue buffer size */ + u16 ring_size; /* Number of descriptors */ + struct idpf_ctlq_reg reg; /* registers accessed by ctlqs */ +}; + +/** + * enum idpf_mbx_opc - PF/VF mailbox commands + * @idpf_mbq_opc_send_msg_to_cp: used by PF or VF to send a message to its CP + */ +enum idpf_mbx_opc { + idpf_mbq_opc_send_msg_to_cp = 0x0801, +}; + +/* API supported for control queue management */ +/* Will init all required q including default mb. "q_info" is an array of + * create_info structs equal to the number of control queues to be created. + */ +int idpf_ctlq_init(struct idpf_hw *hw, u8 num_q, + struct idpf_ctlq_create_info *q_info); + +/* Allocate and initialize a single control queue, which will be added to the + * control queue list; returns a handle to the created control queue + */ +int idpf_ctlq_add(struct idpf_hw *hw, + struct idpf_ctlq_create_info *qinfo, + struct idpf_ctlq_info **cq); + +/* Deinitialize and deallocate a single control queue */ +void idpf_ctlq_remove(struct idpf_hw *hw, + struct idpf_ctlq_info *cq); + +/* Sends messages to HW and will also free the buffer*/ +int idpf_ctlq_send(struct idpf_hw *hw, + struct idpf_ctlq_info *cq, + u16 num_q_msg, + struct idpf_ctlq_msg q_msg[]); + +/* Receives messages and called by interrupt handler/polling + * initiated by app/process. Also caller is supposed to free the buffers + */ +int idpf_ctlq_recv(struct idpf_ctlq_info *cq, u16 *num_q_msg, + struct idpf_ctlq_msg *q_msg); + +/* Reclaims send descriptors on HW write back */ +int idpf_ctlq_clean_sq(struct idpf_ctlq_info *cq, u16 *clean_count, + struct idpf_ctlq_msg *msg_status[]); + +/* Indicate RX buffers are done being processed */ +int idpf_ctlq_post_rx_buffs(struct idpf_hw *hw, + struct idpf_ctlq_info *cq, + u16 *buff_count, + struct idpf_dma_mem **buffs); + +/* Will destroy all q including the default mb */ +void idpf_ctlq_deinit(struct idpf_hw *hw); + +#endif /* _IDPF_CONTROLQ_API_H_ */ diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq_setup.c b/drivers/net/ethernet/intel/idpf/idpf_controlq_setup.c new file mode 100644 index 000000000000..a942a6385d06 --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/idpf_controlq_setup.c @@ -0,0 +1,171 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2023 Intel Corporation */ + +#include "idpf_controlq.h" + +/** + * idpf_ctlq_alloc_desc_ring - Allocate Control Queue (CQ) rings + * @hw: pointer to hw struct + * @cq: pointer to the specific Control queue + */ +static int idpf_ctlq_alloc_desc_ring(struct idpf_hw *hw, + struct idpf_ctlq_info *cq) +{ + size_t size = cq->ring_size * sizeof(struct idpf_ctlq_desc); + + cq->desc_ring.va = idpf_alloc_dma_mem(hw, &cq->desc_ring, size); + if (!cq->desc_ring.va) + return -ENOMEM; + + return 0; +} + +/** + * idpf_ctlq_alloc_bufs - Allocate Control Queue (CQ) buffers + * @hw: pointer to hw struct + * @cq: pointer to the specific Control queue + * + * Allocate the buffer head for all control queues, and if it's a receive + * queue, allocate DMA buffers + */ +static int idpf_ctlq_alloc_bufs(struct idpf_hw *hw, + struct idpf_ctlq_info *cq) +{ + int i; + + /* Do not allocate DMA buffers for transmit queues */ + if (cq->cq_type == IDPF_CTLQ_TYPE_MAILBOX_TX) + return 0; + + /* We'll be allocating the buffer info memory first, then we can + * allocate the mapped buffers for the event processing + */ + cq->bi.rx_buff = kcalloc(cq->ring_size, sizeof(struct idpf_dma_mem *), + GFP_KERNEL); + if (!cq->bi.rx_buff) + return -ENOMEM; + + /* allocate the mapped buffers (except for the last one) */ + for (i = 0; i < cq->ring_size - 1; i++) { + struct idpf_dma_mem *bi; + int num = 1; /* number of idpf_dma_mem to be allocated */ + + cq->bi.rx_buff[i] = kcalloc(num, sizeof(struct idpf_dma_mem), + GFP_KERNEL); + if (!cq->bi.rx_buff[i]) + goto unwind_alloc_cq_bufs; + + bi = cq->bi.rx_buff[i]; + + bi->va = idpf_alloc_dma_mem(hw, bi, cq->buf_size); + if (!bi->va) { + /* unwind will not free the failed entry */ + kfree(cq->bi.rx_buff[i]); + goto unwind_alloc_cq_bufs; + } + } + + return 0; + +unwind_alloc_cq_bufs: + /* don't try to free the one that failed... */ + i--; + for (; i >= 0; i--) { + idpf_free_dma_mem(hw, cq->bi.rx_buff[i]); + kfree(cq->bi.rx_buff[i]); + } + kfree(cq->bi.rx_buff); + + return -ENOMEM; +} + +/** + * idpf_ctlq_free_desc_ring - Free Control Queue (CQ) rings + * @hw: pointer to hw struct + * @cq: pointer to the specific Control queue + * + * This assumes the posted send buffers have already been cleaned + * and de-allocated + */ +static void idpf_ctlq_free_desc_ring(struct idpf_hw *hw, + struct idpf_ctlq_info *cq) +{ + idpf_free_dma_mem(hw, &cq->desc_ring); +} + +/** + * idpf_ctlq_free_bufs - Free CQ buffer info elements + * @hw: pointer to hw struct + * @cq: pointer to the specific Control queue + * + * Free the DMA buffers for RX queues, and DMA buffer header for both RX and TX + * queues. The upper layers are expected to manage freeing of TX DMA buffers + */ +static void idpf_ctlq_free_bufs(struct idpf_hw *hw, struct idpf_ctlq_info *cq) +{ + void *bi; + + if (cq->cq_type == IDPF_CTLQ_TYPE_MAILBOX_RX) { + int i; + + /* free DMA buffers for rx queues*/ + for (i = 0; i < cq->ring_size; i++) { + if (cq->bi.rx_buff[i]) { + idpf_free_dma_mem(hw, cq->bi.rx_buff[i]); + kfree(cq->bi.rx_buff[i]); + } + } + + bi = (void *)cq->bi.rx_buff; + } else { + bi = (void *)cq->bi.tx_msg; + } + + /* free the buffer header */ + kfree(bi); +} + +/** + * idpf_ctlq_dealloc_ring_res - Free memory allocated for control queue + * @hw: pointer to hw struct + * @cq: pointer to the specific Control queue + * + * Free the memory used by the ring, buffers and other related structures + */ +void idpf_ctlq_dealloc_ring_res(struct idpf_hw *hw, struct idpf_ctlq_info *cq) +{ + /* free ring buffers and the ring itself */ + idpf_ctlq_free_bufs(hw, cq); + idpf_ctlq_free_desc_ring(hw, cq); +} + +/** + * idpf_ctlq_alloc_ring_res - allocate memory for descriptor ring and bufs + * @hw: pointer to hw struct + * @cq: pointer to control queue struct + * + * Do *NOT* hold cq_lock when calling this as the memory allocation routines + * called are not going to be atomic context safe + */ +int idpf_ctlq_alloc_ring_res(struct idpf_hw *hw, struct idpf_ctlq_info *cq) +{ + int err; + + /* allocate the ring memory */ + err = idpf_ctlq_alloc_desc_ring(hw, cq); + if (err) + return err; + + /* allocate buffers in the rings */ + err = idpf_ctlq_alloc_bufs(hw, cq); + if (err) + goto idpf_init_cq_free_ring; + + /* success! */ + return 0; + +idpf_init_cq_free_ring: + idpf_free_dma_mem(hw, &cq->desc_ring); + + return err; +} diff --git a/drivers/net/ethernet/intel/idpf/idpf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_dev.c new file mode 100644 index 000000000000..34ad1ac46b78 --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/idpf_dev.c @@ -0,0 +1,165 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2023 Intel Corporation */ + +#include "idpf.h" +#include "idpf_lan_pf_regs.h" + +#define IDPF_PF_ITR_IDX_SPACING 0x4 + +/** + * idpf_ctlq_reg_init - initialize default mailbox registers + * @cq: pointer to the array of create control queues + */ +static void idpf_ctlq_reg_init(struct idpf_ctlq_create_info *cq) +{ + int i; + + for (i = 0; i < IDPF_NUM_DFLT_MBX_Q; i++) { + struct idpf_ctlq_create_info *ccq = cq + i; + + switch (ccq->type) { + case IDPF_CTLQ_TYPE_MAILBOX_TX: + /* set head and tail registers in our local struct */ + ccq->reg.head = PF_FW_ATQH; + ccq->reg.tail = PF_FW_ATQT; + ccq->reg.len = PF_FW_ATQLEN; + ccq->reg.bah = PF_FW_ATQBAH; + ccq->reg.bal = PF_FW_ATQBAL; + ccq->reg.len_mask = PF_FW_ATQLEN_ATQLEN_M; + ccq->reg.len_ena_mask = PF_FW_ATQLEN_ATQENABLE_M; + ccq->reg.head_mask = PF_FW_ATQH_ATQH_M; + break; + case IDPF_CTLQ_TYPE_MAILBOX_RX: + /* set head and tail registers in our local struct */ + ccq->reg.head = PF_FW_ARQH; + ccq->reg.tail = PF_FW_ARQT; + ccq->reg.len = PF_FW_ARQLEN; + ccq->reg.bah = PF_FW_ARQBAH; + ccq->reg.bal = PF_FW_ARQBAL; + ccq->reg.len_mask = PF_FW_ARQLEN_ARQLEN_M; + ccq->reg.len_ena_mask = PF_FW_ARQLEN_ARQENABLE_M; + ccq->reg.head_mask = PF_FW_ARQH_ARQH_M; + break; + default: + break; + } + } +} + +/** + * idpf_mb_intr_reg_init - Initialize mailbox interrupt register + * @adapter: adapter structure + */ +static void idpf_mb_intr_reg_init(struct idpf_adapter *adapter) +{ + struct idpf_intr_reg *intr = &adapter->mb_vector.intr_reg; + u32 dyn_ctl = le32_to_cpu(adapter->caps.mailbox_dyn_ctl); + + intr->dyn_ctl = idpf_get_reg_addr(adapter, dyn_ctl); + intr->dyn_ctl_intena_m = PF_GLINT_DYN_CTL_INTENA_M; + intr->dyn_ctl_itridx_m = PF_GLINT_DYN_CTL_ITR_INDX_M; + intr->icr_ena = idpf_get_reg_addr(adapter, PF_INT_DIR_OICR_ENA); + intr->icr_ena_ctlq_m = PF_INT_DIR_OICR_ENA_M; +} + +/** + * idpf_intr_reg_init - Initialize interrupt registers + * @vport: virtual port structure + */ +static int idpf_intr_reg_init(struct idpf_vport *vport) +{ + struct idpf_adapter *adapter = vport->adapter; + int num_vecs = vport->num_q_vectors; + struct idpf_vec_regs *reg_vals; + int num_regs, i, err = 0; + u32 rx_itr, tx_itr; + u16 total_vecs; + + total_vecs = idpf_get_reserved_vecs(vport->adapter); + reg_vals = kcalloc(total_vecs, sizeof(struct idpf_vec_regs), + GFP_KERNEL); + if (!reg_vals) + return -ENOMEM; + + num_regs = idpf_get_reg_intr_vecs(vport, reg_vals); + if (num_regs < num_vecs) { + err = -EINVAL; + goto free_reg_vals; + } + + for (i = 0; i < num_vecs; i++) { + struct idpf_q_vector *q_vector = &vport->q_vectors[i]; + u16 vec_id = vport->q_vector_idxs[i] - IDPF_MBX_Q_VEC; + struct idpf_intr_reg *intr = &q_vector->intr_reg; + u32 spacing; + + intr->dyn_ctl = idpf_get_reg_addr(adapter, + reg_vals[vec_id].dyn_ctl_reg); + intr->dyn_ctl_intena_m = PF_GLINT_DYN_CTL_INTENA_M; + intr->dyn_ctl_itridx_s = PF_GLINT_DYN_CTL_ITR_INDX_S; + intr->dyn_ctl_intrvl_s = PF_GLINT_DYN_CTL_INTERVAL_S; + + spacing = IDPF_ITR_IDX_SPACING(reg_vals[vec_id].itrn_index_spacing, + IDPF_PF_ITR_IDX_SPACING); + rx_itr = PF_GLINT_ITR_ADDR(VIRTCHNL2_ITR_IDX_0, + reg_vals[vec_id].itrn_reg, + spacing); + tx_itr = PF_GLINT_ITR_ADDR(VIRTCHNL2_ITR_IDX_1, + reg_vals[vec_id].itrn_reg, + spacing); + intr->rx_itr = idpf_get_reg_addr(adapter, rx_itr); + intr->tx_itr = idpf_get_reg_addr(adapter, tx_itr); + } + +free_reg_vals: + kfree(reg_vals); + + return err; +} + +/** + * idpf_reset_reg_init - Initialize reset registers + * @adapter: Driver specific private structure + */ +static void idpf_reset_reg_init(struct idpf_adapter *adapter) +{ + adapter->reset_reg.rstat = idpf_get_reg_addr(adapter, PFGEN_RSTAT); + adapter->reset_reg.rstat_m = PFGEN_RSTAT_PFR_STATE_M; +} + +/** + * idpf_trigger_reset - trigger reset + * @adapter: Driver specific private structure + * @trig_cause: Reason to trigger a reset + */ +static void idpf_trigger_reset(struct idpf_adapter *adapter, + enum idpf_flags __always_unused trig_cause) +{ + u32 reset_reg; + + reset_reg = readl(idpf_get_reg_addr(adapter, PFGEN_CTRL)); + writel(reset_reg | PFGEN_CTRL_PFSWR, + idpf_get_reg_addr(adapter, PFGEN_CTRL)); +} + +/** + * idpf_reg_ops_init - Initialize register API function pointers + * @adapter: Driver specific private structure + */ +static void idpf_reg_ops_init(struct idpf_adapter *adapter) +{ + adapter->dev_ops.reg_ops.ctlq_reg_init = idpf_ctlq_reg_init; + adapter->dev_ops.reg_ops.intr_reg_init = idpf_intr_reg_init; + adapter->dev_ops.reg_ops.mb_intr_reg_init = idpf_mb_intr_reg_init; + adapter->dev_ops.reg_ops.reset_reg_init = idpf_reset_reg_init; + adapter->dev_ops.reg_ops.trigger_reset = idpf_trigger_reset; +} + +/** + * idpf_dev_ops_init - Initialize device API function pointers + * @adapter: Driver specific private structure + */ +void idpf_dev_ops_init(struct idpf_adapter *adapter) +{ + idpf_reg_ops_init(adapter); +} diff --git a/drivers/net/ethernet/intel/idpf/idpf_devids.h b/drivers/net/ethernet/intel/idpf/idpf_devids.h new file mode 100644 index 000000000000..5154a52ae61c --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/idpf_devids.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2023 Intel Corporation */ + +#ifndef _IDPF_DEVIDS_H_ +#define _IDPF_DEVIDS_H_ + +#define IDPF_DEV_ID_PF 0x1452 +#define IDPF_DEV_ID_VF 0x145C + +#endif /* _IDPF_DEVIDS_H_ */ diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c new file mode 100644 index 000000000000..52ea38669f85 --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c @@ -0,0 +1,1369 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2023 Intel Corporation */ + +#include "idpf.h" + +/** + * idpf_get_rxnfc - command to get RX flow classification rules + * @netdev: network interface device structure + * @cmd: ethtool rxnfc command + * @rule_locs: pointer to store rule locations + * + * Returns Success if the command is supported. + */ +static int idpf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, + u32 __always_unused *rule_locs) +{ + struct idpf_vport *vport; + + idpf_vport_ctrl_lock(netdev); + vport = idpf_netdev_to_vport(netdev); + + switch (cmd->cmd) { + case ETHTOOL_GRXRINGS: + cmd->data = vport->num_rxq; + idpf_vport_ctrl_unlock(netdev); + + return 0; + default: + break; + } + + idpf_vport_ctrl_unlock(netdev); + + return -EOPNOTSUPP; +} + +/** + * idpf_get_rxfh_key_size - get the RSS hash key size + * @netdev: network interface device structure + * + * Returns the key size on success, error value on failure. + */ +static u32 idpf_get_rxfh_key_size(struct net_device *netdev) +{ + struct idpf_netdev_priv *np = netdev_priv(netdev); + struct idpf_vport_user_config_data *user_config; + + if (!idpf_is_cap_ena_all(np->adapter, IDPF_RSS_CAPS, IDPF_CAP_RSS)) + return -EOPNOTSUPP; + + user_config = &np->adapter->vport_config[np->vport_idx]->user_config; + + return user_config->rss_data.rss_key_size; +} + +/** + * idpf_get_rxfh_indir_size - get the rx flow hash indirection table size + * @netdev: network interface device structure + * + * Returns the table size on success, error value on failure. + */ +static u32 idpf_get_rxfh_indir_size(struct net_device *netdev) +{ + struct idpf_netdev_priv *np = netdev_priv(netdev); + struct idpf_vport_user_config_data *user_config; + + if (!idpf_is_cap_ena_all(np->adapter, IDPF_RSS_CAPS, IDPF_CAP_RSS)) + return -EOPNOTSUPP; + + user_config = &np->adapter->vport_config[np->vport_idx]->user_config; + + return user_config->rss_data.rss_lut_size; +} + +/** + * idpf_get_rxfh - get the rx flow hash indirection table + * @netdev: network interface device structure + * @indir: indirection table + * @key: hash key + * @hfunc: hash function in use + * + * Reads the indirection table directly from the hardware. Always returns 0. + */ +static int idpf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, + u8 *hfunc) +{ + struct idpf_netdev_priv *np = netdev_priv(netdev); + struct idpf_rss_data *rss_data; + struct idpf_adapter *adapter; + int err = 0; + u16 i; + + idpf_vport_ctrl_lock(netdev); + + adapter = np->adapter; + + if (!idpf_is_cap_ena_all(adapter, IDPF_RSS_CAPS, IDPF_CAP_RSS)) { + err = -EOPNOTSUPP; + goto unlock_mutex; + } + + rss_data = &adapter->vport_config[np->vport_idx]->user_config.rss_data; + if (np->state != __IDPF_VPORT_UP) + goto unlock_mutex; + + if (hfunc) + *hfunc = ETH_RSS_HASH_TOP; + + if (key) + memcpy(key, rss_data->rss_key, rss_data->rss_key_size); + + if (indir) { + for (i = 0; i < rss_data->rss_lut_size; i++) + indir[i] = rss_data->rss_lut[i]; + } + +unlock_mutex: + idpf_vport_ctrl_unlock(netdev); + + return err; +} + +/** + * idpf_set_rxfh - set the rx flow hash indirection table + * @netdev: network interface device structure + * @indir: indirection table + * @key: hash key + * @hfunc: hash function to use + * + * Returns -EINVAL if the table specifies an invalid queue id, otherwise + * returns 0 after programming the table. + */ +static int idpf_set_rxfh(struct net_device *netdev, const u32 *indir, + const u8 *key, const u8 hfunc) +{ + struct idpf_netdev_priv *np = netdev_priv(netdev); + struct idpf_rss_data *rss_data; + struct idpf_adapter *adapter; + struct idpf_vport *vport; + int err = 0; + u16 lut; + + idpf_vport_ctrl_lock(netdev); + vport = idpf_netdev_to_vport(netdev); + + adapter = vport->adapter; + + if (!idpf_is_cap_ena_all(adapter, IDPF_RSS_CAPS, IDPF_CAP_RSS)) { + err = -EOPNOTSUPP; + goto unlock_mutex; + } + + rss_data = &adapter->vport_config[vport->idx]->user_config.rss_data; + if (np->state != __IDPF_VPORT_UP) + goto unlock_mutex; + + if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) { + err = -EOPNOTSUPP; + goto unlock_mutex; + } + + if (key) + memcpy(rss_data->rss_key, key, rss_data->rss_key_size); + + if (indir) { + for (lut = 0; lut < rss_data->rss_lut_size; lut++) + rss_data->rss_lut[lut] = indir[lut]; + } + + err = idpf_config_rss(vport); + +unlock_mutex: + idpf_vport_ctrl_unlock(netdev); + + return err; +} + +/** + * idpf_get_channels: get the number of channels supported by the device + * @netdev: network interface device structure + * @ch: channel information structure + * + * Report maximum of TX and RX. Report one extra channel to match our MailBox + * Queue. + */ +static void idpf_get_channels(struct net_device *netdev, + struct ethtool_channels *ch) +{ + struct idpf_netdev_priv *np = netdev_priv(netdev); + struct idpf_vport_config *vport_config; + u16 num_txq, num_rxq; + u16 combined; + + vport_config = np->adapter->vport_config[np->vport_idx]; + + num_txq = vport_config->user_config.num_req_tx_qs; + num_rxq = vport_config->user_config.num_req_rx_qs; + + combined = min(num_txq, num_rxq); + + /* Report maximum channels */ + ch->max_combined = min_t(u16, vport_config->max_q.max_txq, + vport_config->max_q.max_rxq); + ch->max_rx = vport_config->max_q.max_rxq; + ch->max_tx = vport_config->max_q.max_txq; + + ch->max_other = IDPF_MAX_MBXQ; + ch->other_count = IDPF_MAX_MBXQ; + + ch->combined_count = combined; + ch->rx_count = num_rxq - combined; + ch->tx_count = num_txq - combined; +} + +/** + * idpf_set_channels: set the new channel count + * @netdev: network interface device structure + * @ch: channel information structure + * + * Negotiate a new number of channels with CP. Returns 0 on success, negative + * on failure. + */ +static int idpf_set_channels(struct net_device *netdev, + struct ethtool_channels *ch) +{ + struct idpf_vport_config *vport_config; + u16 combined, num_txq, num_rxq; + unsigned int num_req_tx_q; + unsigned int num_req_rx_q; + struct idpf_vport *vport; + struct device *dev; + int err = 0; + u16 idx; + + idpf_vport_ctrl_lock(netdev); + vport = idpf_netdev_to_vport(netdev); + + idx = vport->idx; + vport_config = vport->adapter->vport_config[idx]; + + num_txq = vport_config->user_config.num_req_tx_qs; + num_rxq = vport_config->user_config.num_req_rx_qs; + + combined = min(num_txq, num_rxq); + + /* these checks are for cases where user didn't specify a particular + * value on cmd line but we get non-zero value anyway via + * get_channels(); look at ethtool.c in ethtool repository (the user + * space part), particularly, do_schannels() routine + */ + if (ch->combined_count == combined) + ch->combined_count = 0; + if (ch->combined_count && ch->rx_count == num_rxq - combined) + ch->rx_count = 0; + if (ch->combined_count && ch->tx_count == num_txq - combined) + ch->tx_count = 0; + + num_req_tx_q = ch->combined_count + ch->tx_count; + num_req_rx_q = ch->combined_count + ch->rx_count; + + dev = &vport->adapter->pdev->dev; + /* It's possible to specify number of queues that exceeds max. + * Stack checks max combined_count and max [tx|rx]_count but not the + * max combined_count + [tx|rx]_count. These checks should catch that. + */ + if (num_req_tx_q > vport_config->max_q.max_txq) { + dev_info(dev, "Maximum TX queues is %d\n", + vport_config->max_q.max_txq); + err = -EINVAL; + goto unlock_mutex; + } + if (num_req_rx_q > vport_config->max_q.max_rxq) { + dev_info(dev, "Maximum RX queues is %d\n", + vport_config->max_q.max_rxq); + err = -EINVAL; + goto unlock_mutex; + } + + if (num_req_tx_q == num_txq && num_req_rx_q == num_rxq) + goto unlock_mutex; + + vport_config->user_config.num_req_tx_qs = num_req_tx_q; + vport_config->user_config.num_req_rx_qs = num_req_rx_q; + + err = idpf_initiate_soft_reset(vport, IDPF_SR_Q_CHANGE); + if (err) { + /* roll back queue change */ + vport_config->user_config.num_req_tx_qs = num_txq; + vport_config->user_config.num_req_rx_qs = num_rxq; + } + +unlock_mutex: + idpf_vport_ctrl_unlock(netdev); + + return err; +} + +/** + * idpf_get_ringparam - Get ring parameters + * @netdev: network interface device structure + * @ring: ethtool ringparam structure + * @kring: unused + * @ext_ack: unused + * + * Returns current ring parameters. TX and RX rings are reported separately, + * but the number of rings is not reported. + */ +static void idpf_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kring, + struct netlink_ext_ack *ext_ack) +{ + struct idpf_vport *vport; + + idpf_vport_ctrl_lock(netdev); + vport = idpf_netdev_to_vport(netdev); + + ring->rx_max_pending = IDPF_MAX_RXQ_DESC; + ring->tx_max_pending = IDPF_MAX_TXQ_DESC; + ring->rx_pending = vport->rxq_desc_count; + ring->tx_pending = vport->txq_desc_count; + + idpf_vport_ctrl_unlock(netdev); +} + +/** + * idpf_set_ringparam - Set ring parameters + * @netdev: network interface device structure + * @ring: ethtool ringparam structure + * @kring: unused + * @ext_ack: unused + * + * Sets ring parameters. TX and RX rings are controlled separately, but the + * number of rings is not specified, so all rings get the same settings. + */ +static int idpf_set_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kring, + struct netlink_ext_ack *ext_ack) +{ + struct idpf_vport_user_config_data *config_data; + u32 new_rx_count, new_tx_count; + struct idpf_vport *vport; + int i, err = 0; + u16 idx; + + idpf_vport_ctrl_lock(netdev); + vport = idpf_netdev_to_vport(netdev); + + idx = vport->idx; + + if (ring->tx_pending < IDPF_MIN_TXQ_DESC) { + netdev_err(netdev, "Descriptors requested (Tx: %u) is less than min supported (%u)\n", + ring->tx_pending, + IDPF_MIN_TXQ_DESC); + err = -EINVAL; + goto unlock_mutex; + } + + if (ring->rx_pending < IDPF_MIN_RXQ_DESC) { + netdev_err(netdev, "Descriptors requested (Rx: %u) is less than min supported (%u)\n", + ring->rx_pending, + IDPF_MIN_RXQ_DESC); + err = -EINVAL; + goto unlock_mutex; + } + + new_rx_count = ALIGN(ring->rx_pending, IDPF_REQ_RXQ_DESC_MULTIPLE); + if (new_rx_count != ring->rx_pending) + netdev_info(netdev, "Requested Rx descriptor count rounded up to %u\n", + new_rx_count); + + new_tx_count = ALIGN(ring->tx_pending, IDPF_REQ_DESC_MULTIPLE); + if (new_tx_count != ring->tx_pending) + netdev_info(netdev, "Requested Tx descriptor count rounded up to %u\n", + new_tx_count); + + if (new_tx_count == vport->txq_desc_count && + new_rx_count == vport->rxq_desc_count) + goto unlock_mutex; + + config_data = &vport->adapter->vport_config[idx]->user_config; + config_data->num_req_txq_desc = new_tx_count; + config_data->num_req_rxq_desc = new_rx_count; + + /* Since we adjusted the RX completion queue count, the RX buffer queue + * descriptor count needs to be adjusted as well + */ + for (i = 0; i < vport->num_bufqs_per_qgrp; i++) + vport->bufq_desc_count[i] = + IDPF_RX_BUFQ_DESC_COUNT(new_rx_count, + vport->num_bufqs_per_qgrp); + + err = idpf_initiate_soft_reset(vport, IDPF_SR_Q_DESC_CHANGE); + +unlock_mutex: + idpf_vport_ctrl_unlock(netdev); + + return err; +} + +/** + * struct idpf_stats - definition for an ethtool statistic + * @stat_string: statistic name to display in ethtool -S output + * @sizeof_stat: the sizeof() the stat, must be no greater than sizeof(u64) + * @stat_offset: offsetof() the stat from a base pointer + * + * This structure defines a statistic to be added to the ethtool stats buffer. + * It defines a statistic as offset from a common base pointer. Stats should + * be defined in constant arrays using the IDPF_STAT macro, with every element + * of the array using the same _type for calculating the sizeof_stat and + * stat_offset. + * + * The @sizeof_stat is expected to be sizeof(u8), sizeof(u16), sizeof(u32) or + * sizeof(u64). Other sizes are not expected and will produce a WARN_ONCE from + * the idpf_add_ethtool_stat() helper function. + * + * The @stat_string is interpreted as a format string, allowing formatted + * values to be inserted while looping over multiple structures for a given + * statistics array. Thus, every statistic string in an array should have the + * same type and number of format specifiers, to be formatted by variadic + * arguments to the idpf_add_stat_string() helper function. + */ +struct idpf_stats { + char stat_string[ETH_GSTRING_LEN]; + int sizeof_stat; + int stat_offset; +}; + +/* Helper macro to define an idpf_stat structure with proper size and type. + * Use this when defining constant statistics arrays. Note that @_type expects + * only a type name and is used multiple times. + */ +#define IDPF_STAT(_type, _name, _stat) { \ + .stat_string = _name, \ + .sizeof_stat = sizeof_field(_type, _stat), \ + .stat_offset = offsetof(_type, _stat) \ +} + +/* Helper macro for defining some statistics related to queues */ +#define IDPF_QUEUE_STAT(_name, _stat) \ + IDPF_STAT(struct idpf_queue, _name, _stat) + +/* Stats associated with a Tx queue */ +static const struct idpf_stats idpf_gstrings_tx_queue_stats[] = { + IDPF_QUEUE_STAT("pkts", q_stats.tx.packets), + IDPF_QUEUE_STAT("bytes", q_stats.tx.bytes), + IDPF_QUEUE_STAT("lso_pkts", q_stats.tx.lso_pkts), +}; + +/* Stats associated with an Rx queue */ +static const struct idpf_stats idpf_gstrings_rx_queue_stats[] = { + IDPF_QUEUE_STAT("pkts", q_stats.rx.packets), + IDPF_QUEUE_STAT("bytes", q_stats.rx.bytes), + IDPF_QUEUE_STAT("rx_gro_hw_pkts", q_stats.rx.rsc_pkts), +}; + +#define IDPF_TX_QUEUE_STATS_LEN ARRAY_SIZE(idpf_gstrings_tx_queue_stats) +#define IDPF_RX_QUEUE_STATS_LEN ARRAY_SIZE(idpf_gstrings_rx_queue_stats) + +#define IDPF_PORT_STAT(_name, _stat) \ + IDPF_STAT(struct idpf_vport, _name, _stat) + +static const struct idpf_stats idpf_gstrings_port_stats[] = { + IDPF_PORT_STAT("rx-csum_errors", port_stats.rx_hw_csum_err), + IDPF_PORT_STAT("rx-hsplit", port_stats.rx_hsplit), + IDPF_PORT_STAT("rx-hsplit_hbo", port_stats.rx_hsplit_hbo), + IDPF_PORT_STAT("rx-bad_descs", port_stats.rx_bad_descs), + IDPF_PORT_STAT("tx-skb_drops", port_stats.tx_drops), + IDPF_PORT_STAT("tx-dma_map_errs", port_stats.tx_dma_map_errs), + IDPF_PORT_STAT("tx-linearized_pkts", port_stats.tx_linearize), + IDPF_PORT_STAT("tx-busy_events", port_stats.tx_busy), + IDPF_PORT_STAT("rx-unicast_pkts", port_stats.vport_stats.rx_unicast), + IDPF_PORT_STAT("rx-multicast_pkts", port_stats.vport_stats.rx_multicast), + IDPF_PORT_STAT("rx-broadcast_pkts", port_stats.vport_stats.rx_broadcast), + IDPF_PORT_STAT("rx-unknown_protocol", port_stats.vport_stats.rx_unknown_protocol), + IDPF_PORT_STAT("tx-unicast_pkts", port_stats.vport_stats.tx_unicast), + IDPF_PORT_STAT("tx-multicast_pkts", port_stats.vport_stats.tx_multicast), + IDPF_PORT_STAT("tx-broadcast_pkts", port_stats.vport_stats.tx_broadcast), +}; + +#define IDPF_PORT_STATS_LEN ARRAY_SIZE(idpf_gstrings_port_stats) + +/** + * __idpf_add_qstat_strings - copy stat strings into ethtool buffer + * @p: ethtool supplied buffer + * @stats: stat definitions array + * @size: size of the stats array + * @type: stat type + * @idx: stat index + * + * Format and copy the strings described by stats into the buffer pointed at + * by p. + */ +static void __idpf_add_qstat_strings(u8 **p, const struct idpf_stats *stats, + const unsigned int size, const char *type, + unsigned int idx) +{ + unsigned int i; + + for (i = 0; i < size; i++) + ethtool_sprintf(p, "%s_q-%u_%s", + type, idx, stats[i].stat_string); +} + +/** + * idpf_add_qstat_strings - Copy queue stat strings into ethtool buffer + * @p: ethtool supplied buffer + * @stats: stat definitions array + * @type: stat type + * @idx: stat idx + * + * Format and copy the strings described by the const static stats value into + * the buffer pointed at by p. + * + * The parameter @stats is evaluated twice, so parameters with side effects + * should be avoided. Additionally, stats must be an array such that + * ARRAY_SIZE can be called on it. + */ +#define idpf_add_qstat_strings(p, stats, type, idx) \ + __idpf_add_qstat_strings(p, stats, ARRAY_SIZE(stats), type, idx) + +/** + * idpf_add_stat_strings - Copy port stat strings into ethtool buffer + * @p: ethtool buffer + * @stats: struct to copy from + * @size: size of stats array to copy from + */ +static void idpf_add_stat_strings(u8 **p, const struct idpf_stats *stats, + const unsigned int size) +{ + unsigned int i; + + for (i = 0; i < size; i++) + ethtool_sprintf(p, "%s", stats[i].stat_string); +} + +/** + * idpf_get_stat_strings - Get stat strings + * @netdev: network interface device structure + * @data: buffer for string data + * + * Builds the statistics string table + */ +static void idpf_get_stat_strings(struct net_device *netdev, u8 *data) +{ + struct idpf_netdev_priv *np = netdev_priv(netdev); + struct idpf_vport_config *vport_config; + unsigned int i; + + idpf_add_stat_strings(&data, idpf_gstrings_port_stats, + IDPF_PORT_STATS_LEN); + + vport_config = np->adapter->vport_config[np->vport_idx]; + /* It's critical that we always report a constant number of strings and + * that the strings are reported in the same order regardless of how + * many queues are actually in use. + */ + for (i = 0; i < vport_config->max_q.max_txq; i++) + idpf_add_qstat_strings(&data, idpf_gstrings_tx_queue_stats, + "tx", i); + + for (i = 0; i < vport_config->max_q.max_rxq; i++) + idpf_add_qstat_strings(&data, idpf_gstrings_rx_queue_stats, + "rx", i); + + page_pool_ethtool_stats_get_strings(data); +} + +/** + * idpf_get_strings - Get string set + * @netdev: network interface device structure + * @sset: id of string set + * @data: buffer for string data + * + * Builds string tables for various string sets + */ +static void idpf_get_strings(struct net_device *netdev, u32 sset, u8 *data) +{ + switch (sset) { + case ETH_SS_STATS: + idpf_get_stat_strings(netdev, data); + break; + default: + break; + } +} + +/** + * idpf_get_sset_count - Get length of string set + * @netdev: network interface device structure + * @sset: id of string set + * + * Reports size of various string tables. + */ +static int idpf_get_sset_count(struct net_device *netdev, int sset) +{ + struct idpf_netdev_priv *np = netdev_priv(netdev); + struct idpf_vport_config *vport_config; + u16 max_txq, max_rxq; + unsigned int size; + + if (sset != ETH_SS_STATS) + return -EINVAL; + + vport_config = np->adapter->vport_config[np->vport_idx]; + /* This size reported back here *must* be constant throughout the + * lifecycle of the netdevice, i.e. we must report the maximum length + * even for queues that don't technically exist. This is due to the + * fact that this userspace API uses three separate ioctl calls to get + * stats data but has no way to communicate back to userspace when that + * size has changed, which can typically happen as a result of changing + * number of queues. If the number/order of stats change in the middle + * of this call chain it will lead to userspace crashing/accessing bad + * data through buffer under/overflow. + */ + max_txq = vport_config->max_q.max_txq; + max_rxq = vport_config->max_q.max_rxq; + + size = IDPF_PORT_STATS_LEN + (IDPF_TX_QUEUE_STATS_LEN * max_txq) + + (IDPF_RX_QUEUE_STATS_LEN * max_rxq); + size += page_pool_ethtool_stats_get_count(); + + return size; +} + +/** + * idpf_add_one_ethtool_stat - copy the stat into the supplied buffer + * @data: location to store the stat value + * @pstat: old stat pointer to copy from + * @stat: the stat definition + * + * Copies the stat data defined by the pointer and stat structure pair into + * the memory supplied as data. If the pointer is null, data will be zero'd. + */ +static void idpf_add_one_ethtool_stat(u64 *data, void *pstat, + const struct idpf_stats *stat) +{ + char *p; + + if (!pstat) { + /* Ensure that the ethtool data buffer is zero'd for any stats + * which don't have a valid pointer. + */ + *data = 0; + return; + } + + p = (char *)pstat + stat->stat_offset; + switch (stat->sizeof_stat) { + case sizeof(u64): + *data = *((u64 *)p); + break; + case sizeof(u32): + *data = *((u32 *)p); + break; + case sizeof(u16): + *data = *((u16 *)p); + break; + case sizeof(u8): + *data = *((u8 *)p); + break; + default: + WARN_ONCE(1, "unexpected stat size for %s", + stat->stat_string); + *data = 0; + } +} + +/** + * idpf_add_queue_stats - copy queue statistics into supplied buffer + * @data: ethtool stats buffer + * @q: the queue to copy + * + * Queue statistics must be copied while protected by u64_stats_fetch_begin, + * so we can't directly use idpf_add_ethtool_stats. Assumes that queue stats + * are defined in idpf_gstrings_queue_stats. If the queue pointer is null, + * zero out the queue stat values and update the data pointer. Otherwise + * safely copy the stats from the queue into the supplied buffer and update + * the data pointer when finished. + * + * This function expects to be called while under rcu_read_lock(). + */ +static void idpf_add_queue_stats(u64 **data, struct idpf_queue *q) +{ + const struct idpf_stats *stats; + unsigned int start; + unsigned int size; + unsigned int i; + + if (q->q_type == VIRTCHNL2_QUEUE_TYPE_RX) { + size = IDPF_RX_QUEUE_STATS_LEN; + stats = idpf_gstrings_rx_queue_stats; + } else { + size = IDPF_TX_QUEUE_STATS_LEN; + stats = idpf_gstrings_tx_queue_stats; + } + + /* To avoid invalid statistics values, ensure that we keep retrying + * the copy until we get a consistent value according to + * u64_stats_fetch_retry. + */ + do { + start = u64_stats_fetch_begin(&q->stats_sync); + for (i = 0; i < size; i++) + idpf_add_one_ethtool_stat(&(*data)[i], q, &stats[i]); + } while (u64_stats_fetch_retry(&q->stats_sync, start)); + + /* Once we successfully copy the stats in, update the data pointer */ + *data += size; +} + +/** + * idpf_add_empty_queue_stats - Add stats for a non-existent queue + * @data: pointer to data buffer + * @qtype: type of data queue + * + * We must report a constant length of stats back to userspace regardless of + * how many queues are actually in use because stats collection happens over + * three separate ioctls and there's no way to notify userspace the size + * changed between those calls. This adds empty to data to the stats since we + * don't have a real queue to refer to for this stats slot. + */ +static void idpf_add_empty_queue_stats(u64 **data, u16 qtype) +{ + unsigned int i; + int stats_len; + + if (qtype == VIRTCHNL2_QUEUE_TYPE_RX) + stats_len = IDPF_RX_QUEUE_STATS_LEN; + else + stats_len = IDPF_TX_QUEUE_STATS_LEN; + + for (i = 0; i < stats_len; i++) + (*data)[i] = 0; + *data += stats_len; +} + +/** + * idpf_add_port_stats - Copy port stats into ethtool buffer + * @vport: virtual port struct + * @data: ethtool buffer to copy into + */ +static void idpf_add_port_stats(struct idpf_vport *vport, u64 **data) +{ + unsigned int size = IDPF_PORT_STATS_LEN; + unsigned int start; + unsigned int i; + + do { + start = u64_stats_fetch_begin(&vport->port_stats.stats_sync); + for (i = 0; i < size; i++) + idpf_add_one_ethtool_stat(&(*data)[i], vport, + &idpf_gstrings_port_stats[i]); + } while (u64_stats_fetch_retry(&vport->port_stats.stats_sync, start)); + + *data += size; +} + +/** + * idpf_collect_queue_stats - accumulate various per queue stats + * into port level stats + * @vport: pointer to vport struct + **/ +static void idpf_collect_queue_stats(struct idpf_vport *vport) +{ + struct idpf_port_stats *pstats = &vport->port_stats; + int i, j; + + /* zero out port stats since they're actually tracked in per + * queue stats; this is only for reporting + */ + u64_stats_update_begin(&pstats->stats_sync); + u64_stats_set(&pstats->rx_hw_csum_err, 0); + u64_stats_set(&pstats->rx_hsplit, 0); + u64_stats_set(&pstats->rx_hsplit_hbo, 0); + u64_stats_set(&pstats->rx_bad_descs, 0); + u64_stats_set(&pstats->tx_linearize, 0); + u64_stats_set(&pstats->tx_busy, 0); + u64_stats_set(&pstats->tx_drops, 0); + u64_stats_set(&pstats->tx_dma_map_errs, 0); + u64_stats_update_end(&pstats->stats_sync); + + for (i = 0; i < vport->num_rxq_grp; i++) { + struct idpf_rxq_group *rxq_grp = &vport->rxq_grps[i]; + u16 num_rxq; + + if (idpf_is_queue_model_split(vport->rxq_model)) + num_rxq = rxq_grp->splitq.num_rxq_sets; + else + num_rxq = rxq_grp->singleq.num_rxq; + + for (j = 0; j < num_rxq; j++) { + u64 hw_csum_err, hsplit, hsplit_hbo, bad_descs; + struct idpf_rx_queue_stats *stats; + struct idpf_queue *rxq; + unsigned int start; + + if (idpf_is_queue_model_split(vport->rxq_model)) + rxq = &rxq_grp->splitq.rxq_sets[j]->rxq; + else + rxq = rxq_grp->singleq.rxqs[j]; + + if (!rxq) + continue; + + do { + start = u64_stats_fetch_begin(&rxq->stats_sync); + + stats = &rxq->q_stats.rx; + hw_csum_err = u64_stats_read(&stats->hw_csum_err); + hsplit = u64_stats_read(&stats->hsplit_pkts); + hsplit_hbo = u64_stats_read(&stats->hsplit_buf_ovf); + bad_descs = u64_stats_read(&stats->bad_descs); + } while (u64_stats_fetch_retry(&rxq->stats_sync, start)); + + u64_stats_update_begin(&pstats->stats_sync); + u64_stats_add(&pstats->rx_hw_csum_err, hw_csum_err); + u64_stats_add(&pstats->rx_hsplit, hsplit); + u64_stats_add(&pstats->rx_hsplit_hbo, hsplit_hbo); + u64_stats_add(&pstats->rx_bad_descs, bad_descs); + u64_stats_update_end(&pstats->stats_sync); + } + } + + for (i = 0; i < vport->num_txq_grp; i++) { + struct idpf_txq_group *txq_grp = &vport->txq_grps[i]; + + for (j = 0; j < txq_grp->num_txq; j++) { + u64 linearize, qbusy, skb_drops, dma_map_errs; + struct idpf_queue *txq = txq_grp->txqs[j]; + struct idpf_tx_queue_stats *stats; + unsigned int start; + + if (!txq) + continue; + + do { + start = u64_stats_fetch_begin(&txq->stats_sync); + + stats = &txq->q_stats.tx; + linearize = u64_stats_read(&stats->linearize); + qbusy = u64_stats_read(&stats->q_busy); + skb_drops = u64_stats_read(&stats->skb_drops); + dma_map_errs = u64_stats_read(&stats->dma_map_errs); + } while (u64_stats_fetch_retry(&txq->stats_sync, start)); + + u64_stats_update_begin(&pstats->stats_sync); + u64_stats_add(&pstats->tx_linearize, linearize); + u64_stats_add(&pstats->tx_busy, qbusy); + u64_stats_add(&pstats->tx_drops, skb_drops); + u64_stats_add(&pstats->tx_dma_map_errs, dma_map_errs); + u64_stats_update_end(&pstats->stats_sync); + } + } +} + +/** + * idpf_get_ethtool_stats - report device statistics + * @netdev: network interface device structure + * @stats: ethtool statistics structure + * @data: pointer to data buffer + * + * All statistics are added to the data buffer as an array of u64. + */ +static void idpf_get_ethtool_stats(struct net_device *netdev, + struct ethtool_stats __always_unused *stats, + u64 *data) +{ + struct idpf_netdev_priv *np = netdev_priv(netdev); + struct idpf_vport_config *vport_config; + struct page_pool_stats pp_stats = { }; + struct idpf_vport *vport; + unsigned int total = 0; + unsigned int i, j; + bool is_splitq; + u16 qtype; + + idpf_vport_ctrl_lock(netdev); + vport = idpf_netdev_to_vport(netdev); + + if (np->state != __IDPF_VPORT_UP) { + idpf_vport_ctrl_unlock(netdev); + + return; + } + + rcu_read_lock(); + + idpf_collect_queue_stats(vport); + idpf_add_port_stats(vport, &data); + + for (i = 0; i < vport->num_txq_grp; i++) { + struct idpf_txq_group *txq_grp = &vport->txq_grps[i]; + + qtype = VIRTCHNL2_QUEUE_TYPE_TX; + + for (j = 0; j < txq_grp->num_txq; j++, total++) { + struct idpf_queue *txq = txq_grp->txqs[j]; + + if (!txq) + idpf_add_empty_queue_stats(&data, qtype); + else + idpf_add_queue_stats(&data, txq); + } + } + + vport_config = vport->adapter->vport_config[vport->idx]; + /* It is critical we provide a constant number of stats back to + * userspace regardless of how many queues are actually in use because + * there is no way to inform userspace the size has changed between + * ioctl calls. This will fill in any missing stats with zero. + */ + for (; total < vport_config->max_q.max_txq; total++) + idpf_add_empty_queue_stats(&data, VIRTCHNL2_QUEUE_TYPE_TX); + total = 0; + + is_splitq = idpf_is_queue_model_split(vport->rxq_model); + + for (i = 0; i < vport->num_rxq_grp; i++) { + struct idpf_rxq_group *rxq_grp = &vport->rxq_grps[i]; + u16 num_rxq; + + qtype = VIRTCHNL2_QUEUE_TYPE_RX; + + if (is_splitq) + num_rxq = rxq_grp->splitq.num_rxq_sets; + else + num_rxq = rxq_grp->singleq.num_rxq; + + for (j = 0; j < num_rxq; j++, total++) { + struct idpf_queue *rxq; + + if (is_splitq) + rxq = &rxq_grp->splitq.rxq_sets[j]->rxq; + else + rxq = rxq_grp->singleq.rxqs[j]; + if (!rxq) + idpf_add_empty_queue_stats(&data, qtype); + else + idpf_add_queue_stats(&data, rxq); + + /* In splitq mode, don't get page pool stats here since + * the pools are attached to the buffer queues + */ + if (is_splitq) + continue; + + if (rxq) + page_pool_get_stats(rxq->pp, &pp_stats); + } + } + + for (i = 0; i < vport->num_rxq_grp; i++) { + for (j = 0; j < vport->num_bufqs_per_qgrp; j++) { + struct idpf_queue *rxbufq = + &vport->rxq_grps[i].splitq.bufq_sets[j].bufq; + + page_pool_get_stats(rxbufq->pp, &pp_stats); + } + } + + for (; total < vport_config->max_q.max_rxq; total++) + idpf_add_empty_queue_stats(&data, VIRTCHNL2_QUEUE_TYPE_RX); + + page_pool_ethtool_stats_get(data, &pp_stats); + + rcu_read_unlock(); + + idpf_vport_ctrl_unlock(netdev); +} + +/** + * idpf_find_rxq - find rxq from q index + * @vport: virtual port associated to queue + * @q_num: q index used to find queue + * + * returns pointer to rx queue + */ +static struct idpf_queue *idpf_find_rxq(struct idpf_vport *vport, int q_num) +{ + int q_grp, q_idx; + + if (!idpf_is_queue_model_split(vport->rxq_model)) + return vport->rxq_grps->singleq.rxqs[q_num]; + + q_grp = q_num / IDPF_DFLT_SPLITQ_RXQ_PER_GROUP; + q_idx = q_num % IDPF_DFLT_SPLITQ_RXQ_PER_GROUP; + + return &vport->rxq_grps[q_grp].splitq.rxq_sets[q_idx]->rxq; +} + +/** + * idpf_find_txq - find txq from q index + * @vport: virtual port associated to queue + * @q_num: q index used to find queue + * + * returns pointer to tx queue + */ +static struct idpf_queue *idpf_find_txq(struct idpf_vport *vport, int q_num) +{ + int q_grp; + + if (!idpf_is_queue_model_split(vport->txq_model)) + return vport->txqs[q_num]; + + q_grp = q_num / IDPF_DFLT_SPLITQ_TXQ_PER_GROUP; + + return vport->txq_grps[q_grp].complq; +} + +/** + * __idpf_get_q_coalesce - get ITR values for specific queue + * @ec: ethtool structure to fill with driver's coalesce settings + * @q: quuee of Rx or Tx + */ +static void __idpf_get_q_coalesce(struct ethtool_coalesce *ec, + struct idpf_queue *q) +{ + if (q->q_type == VIRTCHNL2_QUEUE_TYPE_RX) { + ec->use_adaptive_rx_coalesce = + IDPF_ITR_IS_DYNAMIC(q->q_vector->rx_intr_mode); + ec->rx_coalesce_usecs = q->q_vector->rx_itr_value; + } else { + ec->use_adaptive_tx_coalesce = + IDPF_ITR_IS_DYNAMIC(q->q_vector->tx_intr_mode); + ec->tx_coalesce_usecs = q->q_vector->tx_itr_value; + } +} + +/** + * idpf_get_q_coalesce - get ITR values for specific queue + * @netdev: pointer to the netdev associated with this query + * @ec: coalesce settings to program the device with + * @q_num: update ITR/INTRL (coalesce) settings for this queue number/index + * + * Return 0 on success, and negative on failure + */ +static int idpf_get_q_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, + u32 q_num) +{ + struct idpf_netdev_priv *np = netdev_priv(netdev); + struct idpf_vport *vport; + int err = 0; + + idpf_vport_ctrl_lock(netdev); + vport = idpf_netdev_to_vport(netdev); + + if (np->state != __IDPF_VPORT_UP) + goto unlock_mutex; + + if (q_num >= vport->num_rxq && q_num >= vport->num_txq) { + err = -EINVAL; + goto unlock_mutex; + } + + if (q_num < vport->num_rxq) + __idpf_get_q_coalesce(ec, idpf_find_rxq(vport, q_num)); + + if (q_num < vport->num_txq) + __idpf_get_q_coalesce(ec, idpf_find_txq(vport, q_num)); + +unlock_mutex: + idpf_vport_ctrl_unlock(netdev); + + return err; +} + +/** + * idpf_get_coalesce - get ITR values as requested by user + * @netdev: pointer to the netdev associated with this query + * @ec: coalesce settings to be filled + * @kec: unused + * @extack: unused + * + * Return 0 on success, and negative on failure + */ +static int idpf_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kec, + struct netlink_ext_ack *extack) +{ + /* Return coalesce based on queue number zero */ + return idpf_get_q_coalesce(netdev, ec, 0); +} + +/** + * idpf_get_per_q_coalesce - get ITR values as requested by user + * @netdev: pointer to the netdev associated with this query + * @q_num: queue for which the itr values has to retrieved + * @ec: coalesce settings to be filled + * + * Return 0 on success, and negative on failure + */ + +static int idpf_get_per_q_coalesce(struct net_device *netdev, u32 q_num, + struct ethtool_coalesce *ec) +{ + return idpf_get_q_coalesce(netdev, ec, q_num); +} + +/** + * __idpf_set_q_coalesce - set ITR values for specific queue + * @ec: ethtool structure from user to update ITR settings + * @q: queue for which itr values has to be set + * @is_rxq: is queue type rx + * + * Returns 0 on success, negative otherwise. + */ +static int __idpf_set_q_coalesce(struct ethtool_coalesce *ec, + struct idpf_queue *q, bool is_rxq) +{ + u32 use_adaptive_coalesce, coalesce_usecs; + struct idpf_q_vector *qv = q->q_vector; + bool is_dim_ena = false; + u16 itr_val; + + if (is_rxq) { + is_dim_ena = IDPF_ITR_IS_DYNAMIC(qv->rx_intr_mode); + use_adaptive_coalesce = ec->use_adaptive_rx_coalesce; + coalesce_usecs = ec->rx_coalesce_usecs; + itr_val = qv->rx_itr_value; + } else { + is_dim_ena = IDPF_ITR_IS_DYNAMIC(qv->tx_intr_mode); + use_adaptive_coalesce = ec->use_adaptive_tx_coalesce; + coalesce_usecs = ec->tx_coalesce_usecs; + itr_val = qv->tx_itr_value; + } + if (coalesce_usecs != itr_val && use_adaptive_coalesce) { + netdev_err(q->vport->netdev, "Cannot set coalesce usecs if adaptive enabled\n"); + + return -EINVAL; + } + + if (is_dim_ena && use_adaptive_coalesce) + return 0; + + if (coalesce_usecs > IDPF_ITR_MAX) { + netdev_err(q->vport->netdev, + "Invalid value, %d-usecs range is 0-%d\n", + coalesce_usecs, IDPF_ITR_MAX); + + return -EINVAL; + } + + if (coalesce_usecs % 2) { + coalesce_usecs--; + netdev_info(q->vport->netdev, + "HW only supports even ITR values, ITR rounded to %d\n", + coalesce_usecs); + } + + if (is_rxq) { + qv->rx_itr_value = coalesce_usecs; + if (use_adaptive_coalesce) { + qv->rx_intr_mode = IDPF_ITR_DYNAMIC; + } else { + qv->rx_intr_mode = !IDPF_ITR_DYNAMIC; + idpf_vport_intr_write_itr(qv, qv->rx_itr_value, + false); + } + } else { + qv->tx_itr_value = coalesce_usecs; + if (use_adaptive_coalesce) { + qv->tx_intr_mode = IDPF_ITR_DYNAMIC; + } else { + qv->tx_intr_mode = !IDPF_ITR_DYNAMIC; + idpf_vport_intr_write_itr(qv, qv->tx_itr_value, true); + } + } + + /* Update of static/dynamic itr will be taken care when interrupt is + * fired + */ + return 0; +} + +/** + * idpf_set_q_coalesce - set ITR values for specific queue + * @vport: vport associated to the queue that need updating + * @ec: coalesce settings to program the device with + * @q_num: update ITR/INTRL (coalesce) settings for this queue number/index + * @is_rxq: is queue type rx + * + * Return 0 on success, and negative on failure + */ +static int idpf_set_q_coalesce(struct idpf_vport *vport, + struct ethtool_coalesce *ec, + int q_num, bool is_rxq) +{ + struct idpf_queue *q; + + q = is_rxq ? idpf_find_rxq(vport, q_num) : idpf_find_txq(vport, q_num); + + if (q && __idpf_set_q_coalesce(ec, q, is_rxq)) + return -EINVAL; + + return 0; +} + +/** + * idpf_set_coalesce - set ITR values as requested by user + * @netdev: pointer to the netdev associated with this query + * @ec: coalesce settings to program the device with + * @kec: unused + * @extack: unused + * + * Return 0 on success, and negative on failure + */ +static int idpf_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kec, + struct netlink_ext_ack *extack) +{ + struct idpf_netdev_priv *np = netdev_priv(netdev); + struct idpf_vport *vport; + int i, err = 0; + + idpf_vport_ctrl_lock(netdev); + vport = idpf_netdev_to_vport(netdev); + + if (np->state != __IDPF_VPORT_UP) + goto unlock_mutex; + + for (i = 0; i < vport->num_txq; i++) { + err = idpf_set_q_coalesce(vport, ec, i, false); + if (err) + goto unlock_mutex; + } + + for (i = 0; i < vport->num_rxq; i++) { + err = idpf_set_q_coalesce(vport, ec, i, true); + if (err) + goto unlock_mutex; + } + +unlock_mutex: + idpf_vport_ctrl_unlock(netdev); + + return err; +} + +/** + * idpf_set_per_q_coalesce - set ITR values as requested by user + * @netdev: pointer to the netdev associated with this query + * @q_num: queue for which the itr values has to be set + * @ec: coalesce settings to program the device with + * + * Return 0 on success, and negative on failure + */ +static int idpf_set_per_q_coalesce(struct net_device *netdev, u32 q_num, + struct ethtool_coalesce *ec) +{ + struct idpf_vport *vport; + int err; + + idpf_vport_ctrl_lock(netdev); + vport = idpf_netdev_to_vport(netdev); + + err = idpf_set_q_coalesce(vport, ec, q_num, false); + if (err) { + idpf_vport_ctrl_unlock(netdev); + + return err; + } + + err = idpf_set_q_coalesce(vport, ec, q_num, true); + + idpf_vport_ctrl_unlock(netdev); + + return err; +} + +/** + * idpf_get_msglevel - Get debug message level + * @netdev: network interface device structure + * + * Returns current debug message level. + */ +static u32 idpf_get_msglevel(struct net_device *netdev) +{ + struct idpf_adapter *adapter = idpf_netdev_to_adapter(netdev); + + return adapter->msg_enable; +} + +/** + * idpf_set_msglevel - Set debug message level + * @netdev: network interface device structure + * @data: message level + * + * Set current debug message level. Higher values cause the driver to + * be noisier. + */ +static void idpf_set_msglevel(struct net_device *netdev, u32 data) +{ + struct idpf_adapter *adapter = idpf_netdev_to_adapter(netdev); + + adapter->msg_enable = data; +} + +/** + * idpf_get_link_ksettings - Get Link Speed and Duplex settings + * @netdev: network interface device structure + * @cmd: ethtool command + * + * Reports speed/duplex settings. + **/ +static int idpf_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) +{ + struct idpf_vport *vport; + + idpf_vport_ctrl_lock(netdev); + vport = idpf_netdev_to_vport(netdev); + + ethtool_link_ksettings_zero_link_mode(cmd, supported); + cmd->base.autoneg = AUTONEG_DISABLE; + cmd->base.port = PORT_NONE; + if (vport->link_up) { + cmd->base.duplex = DUPLEX_FULL; + cmd->base.speed = vport->link_speed_mbps; + } else { + cmd->base.duplex = DUPLEX_UNKNOWN; + cmd->base.speed = SPEED_UNKNOWN; + } + + idpf_vport_ctrl_unlock(netdev); + + return 0; +} + +static const struct ethtool_ops idpf_ethtool_ops = { + .supported_coalesce_params = ETHTOOL_COALESCE_USECS | + ETHTOOL_COALESCE_USE_ADAPTIVE, + .get_msglevel = idpf_get_msglevel, + .set_msglevel = idpf_set_msglevel, + .get_link = ethtool_op_get_link, + .get_coalesce = idpf_get_coalesce, + .set_coalesce = idpf_set_coalesce, + .get_per_queue_coalesce = idpf_get_per_q_coalesce, + .set_per_queue_coalesce = idpf_set_per_q_coalesce, + .get_ethtool_stats = idpf_get_ethtool_stats, + .get_strings = idpf_get_strings, + .get_sset_count = idpf_get_sset_count, + .get_channels = idpf_get_channels, + .get_rxnfc = idpf_get_rxnfc, + .get_rxfh_key_size = idpf_get_rxfh_key_size, + .get_rxfh_indir_size = idpf_get_rxfh_indir_size, + .get_rxfh = idpf_get_rxfh, + .set_rxfh = idpf_set_rxfh, + .set_channels = idpf_set_channels, + .get_ringparam = idpf_get_ringparam, + .set_ringparam = idpf_set_ringparam, + .get_link_ksettings = idpf_get_link_ksettings, +}; + +/** + * idpf_set_ethtool_ops - Initialize ethtool ops struct + * @netdev: network interface device structure + * + * Sets ethtool ops struct in our netdev so that ethtool can call + * our functions. + */ +void idpf_set_ethtool_ops(struct net_device *netdev) +{ + netdev->ethtool_ops = &idpf_ethtool_ops; +} diff --git a/drivers/net/ethernet/intel/idpf/idpf_lan_pf_regs.h b/drivers/net/ethernet/intel/idpf/idpf_lan_pf_regs.h new file mode 100644 index 000000000000..24edb8a6ec2e --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/idpf_lan_pf_regs.h @@ -0,0 +1,124 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2023 Intel Corporation */ + +#ifndef _IDPF_LAN_PF_REGS_H_ +#define _IDPF_LAN_PF_REGS_H_ + +/* Receive queues */ +#define PF_QRX_BASE 0x00000000 +#define PF_QRX_TAIL(_QRX) (PF_QRX_BASE + (((_QRX) * 0x1000))) +#define PF_QRX_BUFFQ_BASE 0x03000000 +#define PF_QRX_BUFFQ_TAIL(_QRX) (PF_QRX_BUFFQ_BASE + (((_QRX) * 0x1000))) + +/* Transmit queues */ +#define PF_QTX_BASE 0x05000000 +#define PF_QTX_COMM_DBELL(_DBQM) (PF_QTX_BASE + ((_DBQM) * 0x1000)) + +/* Control(PF Mailbox) Queue */ +#define PF_FW_BASE 0x08400000 + +#define PF_FW_ARQBAL (PF_FW_BASE) +#define PF_FW_ARQBAH (PF_FW_BASE + 0x4) +#define PF_FW_ARQLEN (PF_FW_BASE + 0x8) +#define PF_FW_ARQLEN_ARQLEN_S 0 +#define PF_FW_ARQLEN_ARQLEN_M GENMASK(12, 0) +#define PF_FW_ARQLEN_ARQVFE_S 28 +#define PF_FW_ARQLEN_ARQVFE_M BIT(PF_FW_ARQLEN_ARQVFE_S) +#define PF_FW_ARQLEN_ARQOVFL_S 29 +#define PF_FW_ARQLEN_ARQOVFL_M BIT(PF_FW_ARQLEN_ARQOVFL_S) +#define PF_FW_ARQLEN_ARQCRIT_S 30 +#define PF_FW_ARQLEN_ARQCRIT_M BIT(PF_FW_ARQLEN_ARQCRIT_S) +#define PF_FW_ARQLEN_ARQENABLE_S 31 +#define PF_FW_ARQLEN_ARQENABLE_M BIT(PF_FW_ARQLEN_ARQENABLE_S) +#define PF_FW_ARQH (PF_FW_BASE + 0xC) +#define PF_FW_ARQH_ARQH_S 0 +#define PF_FW_ARQH_ARQH_M GENMASK(12, 0) +#define PF_FW_ARQT (PF_FW_BASE + 0x10) + +#define PF_FW_ATQBAL (PF_FW_BASE + 0x14) +#define PF_FW_ATQBAH (PF_FW_BASE + 0x18) +#define PF_FW_ATQLEN (PF_FW_BASE + 0x1C) +#define PF_FW_ATQLEN_ATQLEN_S 0 +#define PF_FW_ATQLEN_ATQLEN_M GENMASK(9, 0) +#define PF_FW_ATQLEN_ATQVFE_S 28 +#define PF_FW_ATQLEN_ATQVFE_M BIT(PF_FW_ATQLEN_ATQVFE_S) +#define PF_FW_ATQLEN_ATQOVFL_S 29 +#define PF_FW_ATQLEN_ATQOVFL_M BIT(PF_FW_ATQLEN_ATQOVFL_S) +#define PF_FW_ATQLEN_ATQCRIT_S 30 +#define PF_FW_ATQLEN_ATQCRIT_M BIT(PF_FW_ATQLEN_ATQCRIT_S) +#define PF_FW_ATQLEN_ATQENABLE_S 31 +#define PF_FW_ATQLEN_ATQENABLE_M BIT(PF_FW_ATQLEN_ATQENABLE_S) +#define PF_FW_ATQH (PF_FW_BASE + 0x20) +#define PF_FW_ATQH_ATQH_S 0 +#define PF_FW_ATQH_ATQH_M GENMASK(9, 0) +#define PF_FW_ATQT (PF_FW_BASE + 0x24) + +/* Interrupts */ +#define PF_GLINT_BASE 0x08900000 +#define PF_GLINT_DYN_CTL(_INT) (PF_GLINT_BASE + ((_INT) * 0x1000)) +#define PF_GLINT_DYN_CTL_INTENA_S 0 +#define PF_GLINT_DYN_CTL_INTENA_M BIT(PF_GLINT_DYN_CTL_INTENA_S) +#define PF_GLINT_DYN_CTL_CLEARPBA_S 1 +#define PF_GLINT_DYN_CTL_CLEARPBA_M BIT(PF_GLINT_DYN_CTL_CLEARPBA_S) +#define PF_GLINT_DYN_CTL_SWINT_TRIG_S 2 +#define PF_GLINT_DYN_CTL_SWINT_TRIG_M BIT(PF_GLINT_DYN_CTL_SWINT_TRIG_S) +#define PF_GLINT_DYN_CTL_ITR_INDX_S 3 +#define PF_GLINT_DYN_CTL_ITR_INDX_M GENMASK(4, 3) +#define PF_GLINT_DYN_CTL_INTERVAL_S 5 +#define PF_GLINT_DYN_CTL_INTERVAL_M BIT(PF_GLINT_DYN_CTL_INTERVAL_S) +#define PF_GLINT_DYN_CTL_SW_ITR_INDX_ENA_S 24 +#define PF_GLINT_DYN_CTL_SW_ITR_INDX_ENA_M BIT(PF_GLINT_DYN_CTL_SW_ITR_INDX_ENA_S) +#define PF_GLINT_DYN_CTL_SW_ITR_INDX_S 25 +#define PF_GLINT_DYN_CTL_SW_ITR_INDX_M BIT(PF_GLINT_DYN_CTL_SW_ITR_INDX_S) +#define PF_GLINT_DYN_CTL_WB_ON_ITR_S 30 +#define PF_GLINT_DYN_CTL_WB_ON_ITR_M BIT(PF_GLINT_DYN_CTL_WB_ON_ITR_S) +#define PF_GLINT_DYN_CTL_INTENA_MSK_S 31 +#define PF_GLINT_DYN_CTL_INTENA_MSK_M BIT(PF_GLINT_DYN_CTL_INTENA_MSK_S) +/* _ITR is ITR index, _INT is interrupt index, _itrn_indx_spacing is + * spacing b/w itrn registers of the same vector. + */ +#define PF_GLINT_ITR_ADDR(_ITR, _reg_start, _itrn_indx_spacing) \ + ((_reg_start) + ((_ITR) * (_itrn_indx_spacing))) +/* For PF, itrn_indx_spacing is 4 and itrn_reg_spacing is 0x1000 */ +#define PF_GLINT_ITR(_ITR, _INT) \ + (PF_GLINT_BASE + (((_ITR) + 1) * 4) + ((_INT) * 0x1000)) +#define PF_GLINT_ITR_MAX_INDEX 2 +#define PF_GLINT_ITR_INTERVAL_S 0 +#define PF_GLINT_ITR_INTERVAL_M GENMASK(11, 0) + +/* Generic registers */ +#define PF_INT_DIR_OICR_ENA 0x08406000 +#define PF_INT_DIR_OICR_ENA_S 0 +#define PF_INT_DIR_OICR_ENA_M GENMASK(31, 0) +#define PF_INT_DIR_OICR 0x08406004 +#define PF_INT_DIR_OICR_TSYN_EVNT 0 +#define PF_INT_DIR_OICR_PHY_TS_0 BIT(1) +#define PF_INT_DIR_OICR_PHY_TS_1 BIT(2) +#define PF_INT_DIR_OICR_CAUSE 0x08406008 +#define PF_INT_DIR_OICR_CAUSE_CAUSE_S 0 +#define PF_INT_DIR_OICR_CAUSE_CAUSE_M GENMASK(31, 0) +#define PF_INT_PBA_CLEAR 0x0840600C + +#define PF_FUNC_RID 0x08406010 +#define PF_FUNC_RID_FUNCTION_NUMBER_S 0 +#define PF_FUNC_RID_FUNCTION_NUMBER_M GENMASK(2, 0) +#define PF_FUNC_RID_DEVICE_NUMBER_S 3 +#define PF_FUNC_RID_DEVICE_NUMBER_M GENMASK(7, 3) +#define PF_FUNC_RID_BUS_NUMBER_S 8 +#define PF_FUNC_RID_BUS_NUMBER_M GENMASK(15, 8) + +/* Reset registers */ +#define PFGEN_RTRIG 0x08407000 +#define PFGEN_RTRIG_CORER_S 0 +#define PFGEN_RTRIG_CORER_M BIT(0) +#define PFGEN_RTRIG_LINKR_S 1 +#define PFGEN_RTRIG_LINKR_M BIT(1) +#define PFGEN_RTRIG_IMCR_S 2 +#define PFGEN_RTRIG_IMCR_M BIT(2) +#define PFGEN_RSTAT 0x08407008 /* PFR Status */ +#define PFGEN_RSTAT_PFR_STATE_S 0 +#define PFGEN_RSTAT_PFR_STATE_M GENMASK(1, 0) +#define PFGEN_CTRL 0x0840700C +#define PFGEN_CTRL_PFSWR BIT(0) + +#endif diff --git a/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h new file mode 100644 index 000000000000..a5752dcab888 --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h @@ -0,0 +1,293 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2023 Intel Corporation */ + +#ifndef _IDPF_LAN_TXRX_H_ +#define _IDPF_LAN_TXRX_H_ + +enum idpf_rss_hash { + IDPF_HASH_INVALID = 0, + /* Values 1 - 28 are reserved for future use */ + IDPF_HASH_NONF_UNICAST_IPV4_UDP = 29, + IDPF_HASH_NONF_MULTICAST_IPV4_UDP, + IDPF_HASH_NONF_IPV4_UDP, + IDPF_HASH_NONF_IPV4_TCP_SYN_NO_ACK, + IDPF_HASH_NONF_IPV4_TCP, + IDPF_HASH_NONF_IPV4_SCTP, + IDPF_HASH_NONF_IPV4_OTHER, + IDPF_HASH_FRAG_IPV4, + /* Values 37-38 are reserved */ + IDPF_HASH_NONF_UNICAST_IPV6_UDP = 39, + IDPF_HASH_NONF_MULTICAST_IPV6_UDP, + IDPF_HASH_NONF_IPV6_UDP, + IDPF_HASH_NONF_IPV6_TCP_SYN_NO_ACK, + IDPF_HASH_NONF_IPV6_TCP, + IDPF_HASH_NONF_IPV6_SCTP, + IDPF_HASH_NONF_IPV6_OTHER, + IDPF_HASH_FRAG_IPV6, + IDPF_HASH_NONF_RSVD47, + IDPF_HASH_NONF_FCOE_OX, + IDPF_HASH_NONF_FCOE_RX, + IDPF_HASH_NONF_FCOE_OTHER, + /* Values 51-62 are reserved */ + IDPF_HASH_L2_PAYLOAD = 63, + + IDPF_HASH_MAX +}; + +/* Supported RSS offloads */ +#define IDPF_DEFAULT_RSS_HASH \ + (BIT_ULL(IDPF_HASH_NONF_IPV4_UDP) | \ + BIT_ULL(IDPF_HASH_NONF_IPV4_SCTP) | \ + BIT_ULL(IDPF_HASH_NONF_IPV4_TCP) | \ + BIT_ULL(IDPF_HASH_NONF_IPV4_OTHER) | \ + BIT_ULL(IDPF_HASH_FRAG_IPV4) | \ + BIT_ULL(IDPF_HASH_NONF_IPV6_UDP) | \ + BIT_ULL(IDPF_HASH_NONF_IPV6_TCP) | \ + BIT_ULL(IDPF_HASH_NONF_IPV6_SCTP) | \ + BIT_ULL(IDPF_HASH_NONF_IPV6_OTHER) | \ + BIT_ULL(IDPF_HASH_FRAG_IPV6) | \ + BIT_ULL(IDPF_HASH_L2_PAYLOAD)) + +#define IDPF_DEFAULT_RSS_HASH_EXPANDED (IDPF_DEFAULT_RSS_HASH | \ + BIT_ULL(IDPF_HASH_NONF_IPV4_TCP_SYN_NO_ACK) | \ + BIT_ULL(IDPF_HASH_NONF_UNICAST_IPV4_UDP) | \ + BIT_ULL(IDPF_HASH_NONF_MULTICAST_IPV4_UDP) | \ + BIT_ULL(IDPF_HASH_NONF_IPV6_TCP_SYN_NO_ACK) | \ + BIT_ULL(IDPF_HASH_NONF_UNICAST_IPV6_UDP) | \ + BIT_ULL(IDPF_HASH_NONF_MULTICAST_IPV6_UDP)) + +/* For idpf_splitq_base_tx_compl_desc */ +#define IDPF_TXD_COMPLQ_GEN_S 15 +#define IDPF_TXD_COMPLQ_GEN_M BIT_ULL(IDPF_TXD_COMPLQ_GEN_S) +#define IDPF_TXD_COMPLQ_COMPL_TYPE_S 11 +#define IDPF_TXD_COMPLQ_COMPL_TYPE_M GENMASK_ULL(13, 11) +#define IDPF_TXD_COMPLQ_QID_S 0 +#define IDPF_TXD_COMPLQ_QID_M GENMASK_ULL(9, 0) + +/* For base mode TX descriptors */ + +#define IDPF_TXD_CTX_QW0_TUNN_L4T_CS_S 23 +#define IDPF_TXD_CTX_QW0_TUNN_L4T_CS_M BIT_ULL(IDPF_TXD_CTX_QW0_TUNN_L4T_CS_S) +#define IDPF_TXD_CTX_QW0_TUNN_DECTTL_S 19 +#define IDPF_TXD_CTX_QW0_TUNN_DECTTL_M \ + (0xFULL << IDPF_TXD_CTX_QW0_TUNN_DECTTL_S) +#define IDPF_TXD_CTX_QW0_TUNN_NATLEN_S 12 +#define IDPF_TXD_CTX_QW0_TUNN_NATLEN_M \ + (0X7FULL << IDPF_TXD_CTX_QW0_TUNN_NATLEN_S) +#define IDPF_TXD_CTX_QW0_TUNN_EIP_NOINC_S 11 +#define IDPF_TXD_CTX_QW0_TUNN_EIP_NOINC_M \ + BIT_ULL(IDPF_TXD_CTX_QW0_TUNN_EIP_NOINC_S) +#define IDPF_TXD_CTX_EIP_NOINC_IPID_CONST \ + IDPF_TXD_CTX_QW0_TUNN_EIP_NOINC_M +#define IDPF_TXD_CTX_QW0_TUNN_NATT_S 9 +#define IDPF_TXD_CTX_QW0_TUNN_NATT_M (0x3ULL << IDPF_TXD_CTX_QW0_TUNN_NATT_S) +#define IDPF_TXD_CTX_UDP_TUNNELING BIT_ULL(IDPF_TXD_CTX_QW0_TUNN_NATT_S) +#define IDPF_TXD_CTX_GRE_TUNNELING (0x2ULL << IDPF_TXD_CTX_QW0_TUNN_NATT_S) +#define IDPF_TXD_CTX_QW0_TUNN_EXT_IPLEN_S 2 +#define IDPF_TXD_CTX_QW0_TUNN_EXT_IPLEN_M \ + (0x3FULL << IDPF_TXD_CTX_QW0_TUNN_EXT_IPLEN_S) +#define IDPF_TXD_CTX_QW0_TUNN_EXT_IP_S 0 +#define IDPF_TXD_CTX_QW0_TUNN_EXT_IP_M \ + (0x3ULL << IDPF_TXD_CTX_QW0_TUNN_EXT_IP_S) + +#define IDPF_TXD_CTX_QW1_MSS_S 50 +#define IDPF_TXD_CTX_QW1_MSS_M GENMASK_ULL(63, 50) +#define IDPF_TXD_CTX_QW1_TSO_LEN_S 30 +#define IDPF_TXD_CTX_QW1_TSO_LEN_M GENMASK_ULL(47, 30) +#define IDPF_TXD_CTX_QW1_CMD_S 4 +#define IDPF_TXD_CTX_QW1_CMD_M GENMASK_ULL(15, 4) +#define IDPF_TXD_CTX_QW1_DTYPE_S 0 +#define IDPF_TXD_CTX_QW1_DTYPE_M GENMASK_ULL(3, 0) +#define IDPF_TXD_QW1_L2TAG1_S 48 +#define IDPF_TXD_QW1_L2TAG1_M GENMASK_ULL(63, 48) +#define IDPF_TXD_QW1_TX_BUF_SZ_S 34 +#define IDPF_TXD_QW1_TX_BUF_SZ_M GENMASK_ULL(47, 34) +#define IDPF_TXD_QW1_OFFSET_S 16 +#define IDPF_TXD_QW1_OFFSET_M GENMASK_ULL(33, 16) +#define IDPF_TXD_QW1_CMD_S 4 +#define IDPF_TXD_QW1_CMD_M GENMASK_ULL(15, 4) +#define IDPF_TXD_QW1_DTYPE_S 0 +#define IDPF_TXD_QW1_DTYPE_M GENMASK_ULL(3, 0) + +/* TX Completion Descriptor Completion Types */ +#define IDPF_TXD_COMPLT_ITR_FLUSH 0 +/* Descriptor completion type 1 is reserved */ +#define IDPF_TXD_COMPLT_RS 2 +/* Descriptor completion type 3 is reserved */ +#define IDPF_TXD_COMPLT_RE 4 +#define IDPF_TXD_COMPLT_SW_MARKER 5 + +enum idpf_tx_desc_dtype_value { + IDPF_TX_DESC_DTYPE_DATA = 0, + IDPF_TX_DESC_DTYPE_CTX = 1, + /* DTYPE 2 is reserved + * DTYPE 3 is free for future use + * DTYPE 4 is reserved + */ + IDPF_TX_DESC_DTYPE_FLEX_TSO_CTX = 5, + /* DTYPE 6 is reserved */ + IDPF_TX_DESC_DTYPE_FLEX_L2TAG1_L2TAG2 = 7, + /* DTYPE 8, 9 are free for future use + * DTYPE 10 is reserved + * DTYPE 11 is free for future use + */ + IDPF_TX_DESC_DTYPE_FLEX_FLOW_SCHE = 12, + /* DTYPE 13, 14 are free for future use */ + + /* DESC_DONE - HW has completed write-back of descriptor */ + IDPF_TX_DESC_DTYPE_DESC_DONE = 15, +}; + +enum idpf_tx_ctx_desc_cmd_bits { + IDPF_TX_CTX_DESC_TSO = 0x01, + IDPF_TX_CTX_DESC_TSYN = 0x02, + IDPF_TX_CTX_DESC_IL2TAG2 = 0x04, + IDPF_TX_CTX_DESC_RSVD = 0x08, + IDPF_TX_CTX_DESC_SWTCH_NOTAG = 0x00, + IDPF_TX_CTX_DESC_SWTCH_UPLINK = 0x10, + IDPF_TX_CTX_DESC_SWTCH_LOCAL = 0x20, + IDPF_TX_CTX_DESC_SWTCH_VSI = 0x30, + IDPF_TX_CTX_DESC_FILT_AU_EN = 0x40, + IDPF_TX_CTX_DESC_FILT_AU_EVICT = 0x80, + IDPF_TX_CTX_DESC_RSVD1 = 0xF00 +}; + +enum idpf_tx_desc_len_fields { + /* Note: These are predefined bit offsets */ + IDPF_TX_DESC_LEN_MACLEN_S = 0, /* 7 BITS */ + IDPF_TX_DESC_LEN_IPLEN_S = 7, /* 7 BITS */ + IDPF_TX_DESC_LEN_L4_LEN_S = 14 /* 4 BITS */ +}; + +enum idpf_tx_base_desc_cmd_bits { + IDPF_TX_DESC_CMD_EOP = BIT(0), + IDPF_TX_DESC_CMD_RS = BIT(1), + /* only on VFs else RSVD */ + IDPF_TX_DESC_CMD_ICRC = BIT(2), + IDPF_TX_DESC_CMD_IL2TAG1 = BIT(3), + IDPF_TX_DESC_CMD_RSVD1 = BIT(4), + IDPF_TX_DESC_CMD_IIPT_IPV6 = BIT(5), + IDPF_TX_DESC_CMD_IIPT_IPV4 = BIT(6), + IDPF_TX_DESC_CMD_IIPT_IPV4_CSUM = GENMASK(6, 5), + IDPF_TX_DESC_CMD_RSVD2 = BIT(7), + IDPF_TX_DESC_CMD_L4T_EOFT_TCP = BIT(8), + IDPF_TX_DESC_CMD_L4T_EOFT_SCTP = BIT(9), + IDPF_TX_DESC_CMD_L4T_EOFT_UDP = GENMASK(9, 8), + IDPF_TX_DESC_CMD_RSVD3 = BIT(10), + IDPF_TX_DESC_CMD_RSVD4 = BIT(11), +}; + +/* Transmit descriptors */ +/* splitq tx buf, singleq tx buf and singleq compl desc */ +struct idpf_base_tx_desc { + __le64 buf_addr; /* Address of descriptor's data buf */ + __le64 qw1; /* type_cmd_offset_bsz_l2tag1 */ +}; /* read used with buffer queues */ + +struct idpf_splitq_tx_compl_desc { + /* qid=[10:0] comptype=[13:11] rsvd=[14] gen=[15] */ + __le16 qid_comptype_gen; + union { + __le16 q_head; /* Queue head */ + __le16 compl_tag; /* Completion tag */ + } q_head_compl_tag; + u8 ts[3]; + u8 rsvd; /* Reserved */ +}; /* writeback used with completion queues */ + +/* Context descriptors */ +struct idpf_base_tx_ctx_desc { + struct { + __le32 tunneling_params; + __le16 l2tag2; + __le16 rsvd1; + } qw0; + __le64 qw1; /* type_cmd_tlen_mss/rt_hint */ +}; + +/* Common cmd field defines for all desc except Flex Flow Scheduler (0x0C) */ +enum idpf_tx_flex_desc_cmd_bits { + IDPF_TX_FLEX_DESC_CMD_EOP = BIT(0), + IDPF_TX_FLEX_DESC_CMD_RS = BIT(1), + IDPF_TX_FLEX_DESC_CMD_RE = BIT(2), + IDPF_TX_FLEX_DESC_CMD_IL2TAG1 = BIT(3), + IDPF_TX_FLEX_DESC_CMD_DUMMY = BIT(4), + IDPF_TX_FLEX_DESC_CMD_CS_EN = BIT(5), + IDPF_TX_FLEX_DESC_CMD_FILT_AU_EN = BIT(6), + IDPF_TX_FLEX_DESC_CMD_FILT_AU_EVICT = BIT(7), +}; + +struct idpf_flex_tx_desc { + __le64 buf_addr; /* Packet buffer address */ + struct { +#define IDPF_FLEX_TXD_QW1_DTYPE_S 0 +#define IDPF_FLEX_TXD_QW1_DTYPE_M GENMASK(4, 0) +#define IDPF_FLEX_TXD_QW1_CMD_S 5 +#define IDPF_FLEX_TXD_QW1_CMD_M GENMASK(15, 5) + __le16 cmd_dtype; + /* DTYPE=IDPF_TX_DESC_DTYPE_FLEX_L2TAG1_L2TAG2 (0x07) */ + struct { + __le16 l2tag1; + __le16 l2tag2; + } l2tags; + __le16 buf_size; + } qw1; +}; + +struct idpf_flex_tx_sched_desc { + __le64 buf_addr; /* Packet buffer address */ + + /* DTYPE = IDPF_TX_DESC_DTYPE_FLEX_FLOW_SCHE_16B (0x0C) */ + struct { + u8 cmd_dtype; +#define IDPF_TXD_FLEX_FLOW_DTYPE_M GENMASK(4, 0) +#define IDPF_TXD_FLEX_FLOW_CMD_EOP BIT(5) +#define IDPF_TXD_FLEX_FLOW_CMD_CS_EN BIT(6) +#define IDPF_TXD_FLEX_FLOW_CMD_RE BIT(7) + + /* [23:23] Horizon Overflow bit, [22:0] timestamp */ + u8 ts[3]; +#define IDPF_TXD_FLOW_SCH_HORIZON_OVERFLOW_M BIT(7) + + __le16 compl_tag; + __le16 rxr_bufsize; +#define IDPF_TXD_FLEX_FLOW_RXR BIT(14) +#define IDPF_TXD_FLEX_FLOW_BUFSIZE_M GENMASK(13, 0) + } qw1; +}; + +/* Common cmd fields for all flex context descriptors + * Note: these defines already account for the 5 bit dtype in the cmd_dtype + * field + */ +enum idpf_tx_flex_ctx_desc_cmd_bits { + IDPF_TX_FLEX_CTX_DESC_CMD_TSO = BIT(5), + IDPF_TX_FLEX_CTX_DESC_CMD_TSYN_EN = BIT(6), + IDPF_TX_FLEX_CTX_DESC_CMD_L2TAG2 = BIT(7), + IDPF_TX_FLEX_CTX_DESC_CMD_SWTCH_UPLNK = BIT(9), + IDPF_TX_FLEX_CTX_DESC_CMD_SWTCH_LOCAL = BIT(10), + IDPF_TX_FLEX_CTX_DESC_CMD_SWTCH_TARGETVSI = GENMASK(10, 9), +}; + +/* Standard flex descriptor TSO context quad word */ +struct idpf_flex_tx_tso_ctx_qw { + __le32 flex_tlen; +#define IDPF_TXD_FLEX_CTX_TLEN_M GENMASK(17, 0) +#define IDPF_TXD_FLEX_TSO_CTX_FLEX_S 24 + __le16 mss_rt; +#define IDPF_TXD_FLEX_CTX_MSS_RT_M GENMASK(13, 0) + u8 hdr_len; + u8 flex; +}; + +struct idpf_flex_tx_ctx_desc { + /* DTYPE = IDPF_TX_DESC_DTYPE_FLEX_TSO_CTX (0x05) */ + struct { + struct idpf_flex_tx_tso_ctx_qw qw0; + struct { + __le16 cmd_dtype; + u8 flex[6]; + } qw1; + } tso; +}; +#endif /* _IDPF_LAN_TXRX_H_ */ diff --git a/drivers/net/ethernet/intel/idpf/idpf_lan_vf_regs.h b/drivers/net/ethernet/intel/idpf/idpf_lan_vf_regs.h new file mode 100644 index 000000000000..3d73b6c76863 --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/idpf_lan_vf_regs.h @@ -0,0 +1,128 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2023 Intel Corporation */ + +#ifndef _IDPF_LAN_VF_REGS_H_ +#define _IDPF_LAN_VF_REGS_H_ + +/* Reset */ +#define VFGEN_RSTAT 0x00008800 +#define VFGEN_RSTAT_VFR_STATE_S 0 +#define VFGEN_RSTAT_VFR_STATE_M GENMASK(1, 0) + +/* Control(VF Mailbox) Queue */ +#define VF_BASE 0x00006000 + +#define VF_ATQBAL (VF_BASE + 0x1C00) +#define VF_ATQBAH (VF_BASE + 0x1800) +#define VF_ATQLEN (VF_BASE + 0x0800) +#define VF_ATQLEN_ATQLEN_S 0 +#define VF_ATQLEN_ATQLEN_M GENMASK(9, 0) +#define VF_ATQLEN_ATQVFE_S 28 +#define VF_ATQLEN_ATQVFE_M BIT(VF_ATQLEN_ATQVFE_S) +#define VF_ATQLEN_ATQOVFL_S 29 +#define VF_ATQLEN_ATQOVFL_M BIT(VF_ATQLEN_ATQOVFL_S) +#define VF_ATQLEN_ATQCRIT_S 30 +#define VF_ATQLEN_ATQCRIT_M BIT(VF_ATQLEN_ATQCRIT_S) +#define VF_ATQLEN_ATQENABLE_S 31 +#define VF_ATQLEN_ATQENABLE_M BIT(VF_ATQLEN_ATQENABLE_S) +#define VF_ATQH (VF_BASE + 0x0400) +#define VF_ATQH_ATQH_S 0 +#define VF_ATQH_ATQH_M GENMASK(9, 0) +#define VF_ATQT (VF_BASE + 0x2400) + +#define VF_ARQBAL (VF_BASE + 0x0C00) +#define VF_ARQBAH (VF_BASE) +#define VF_ARQLEN (VF_BASE + 0x2000) +#define VF_ARQLEN_ARQLEN_S 0 +#define VF_ARQLEN_ARQLEN_M GENMASK(9, 0) +#define VF_ARQLEN_ARQVFE_S 28 +#define VF_ARQLEN_ARQVFE_M BIT(VF_ARQLEN_ARQVFE_S) +#define VF_ARQLEN_ARQOVFL_S 29 +#define VF_ARQLEN_ARQOVFL_M BIT(VF_ARQLEN_ARQOVFL_S) +#define VF_ARQLEN_ARQCRIT_S 30 +#define VF_ARQLEN_ARQCRIT_M BIT(VF_ARQLEN_ARQCRIT_S) +#define VF_ARQLEN_ARQENABLE_S 31 +#define VF_ARQLEN_ARQENABLE_M BIT(VF_ARQLEN_ARQENABLE_S) +#define VF_ARQH (VF_BASE + 0x1400) +#define VF_ARQH_ARQH_S 0 +#define VF_ARQH_ARQH_M GENMASK(12, 0) +#define VF_ARQT (VF_BASE + 0x1000) + +/* Transmit queues */ +#define VF_QTX_TAIL_BASE 0x00000000 +#define VF_QTX_TAIL(_QTX) (VF_QTX_TAIL_BASE + (_QTX) * 0x4) +#define VF_QTX_TAIL_EXT_BASE 0x00040000 +#define VF_QTX_TAIL_EXT(_QTX) (VF_QTX_TAIL_EXT_BASE + ((_QTX) * 4)) + +/* Receive queues */ +#define VF_QRX_TAIL_BASE 0x00002000 +#define VF_QRX_TAIL(_QRX) (VF_QRX_TAIL_BASE + ((_QRX) * 4)) +#define VF_QRX_TAIL_EXT_BASE 0x00050000 +#define VF_QRX_TAIL_EXT(_QRX) (VF_QRX_TAIL_EXT_BASE + ((_QRX) * 4)) +#define VF_QRXB_TAIL_BASE 0x00060000 +#define VF_QRXB_TAIL(_QRX) (VF_QRXB_TAIL_BASE + ((_QRX) * 4)) + +/* Interrupts */ +#define VF_INT_DYN_CTL0 0x00005C00 +#define VF_INT_DYN_CTL0_INTENA_S 0 +#define VF_INT_DYN_CTL0_INTENA_M BIT(VF_INT_DYN_CTL0_INTENA_S) +#define VF_INT_DYN_CTL0_ITR_INDX_S 3 +#define VF_INT_DYN_CTL0_ITR_INDX_M GENMASK(4, 3) +#define VF_INT_DYN_CTLN(_INT) (0x00003800 + ((_INT) * 4)) +#define VF_INT_DYN_CTLN_EXT(_INT) (0x00070000 + ((_INT) * 4)) +#define VF_INT_DYN_CTLN_INTENA_S 0 +#define VF_INT_DYN_CTLN_INTENA_M BIT(VF_INT_DYN_CTLN_INTENA_S) +#define VF_INT_DYN_CTLN_CLEARPBA_S 1 +#define VF_INT_DYN_CTLN_CLEARPBA_M BIT(VF_INT_DYN_CTLN_CLEARPBA_S) +#define VF_INT_DYN_CTLN_SWINT_TRIG_S 2 +#define VF_INT_DYN_CTLN_SWINT_TRIG_M BIT(VF_INT_DYN_CTLN_SWINT_TRIG_S) +#define VF_INT_DYN_CTLN_ITR_INDX_S 3 +#define VF_INT_DYN_CTLN_ITR_INDX_M GENMASK(4, 3) +#define VF_INT_DYN_CTLN_INTERVAL_S 5 +#define VF_INT_DYN_CTLN_INTERVAL_M BIT(VF_INT_DYN_CTLN_INTERVAL_S) +#define VF_INT_DYN_CTLN_SW_ITR_INDX_ENA_S 24 +#define VF_INT_DYN_CTLN_SW_ITR_INDX_ENA_M BIT(VF_INT_DYN_CTLN_SW_ITR_INDX_ENA_S) +#define VF_INT_DYN_CTLN_SW_ITR_INDX_S 25 +#define VF_INT_DYN_CTLN_SW_ITR_INDX_M BIT(VF_INT_DYN_CTLN_SW_ITR_INDX_S) +#define VF_INT_DYN_CTLN_WB_ON_ITR_S 30 +#define VF_INT_DYN_CTLN_WB_ON_ITR_M BIT(VF_INT_DYN_CTLN_WB_ON_ITR_S) +#define VF_INT_DYN_CTLN_INTENA_MSK_S 31 +#define VF_INT_DYN_CTLN_INTENA_MSK_M BIT(VF_INT_DYN_CTLN_INTENA_MSK_S) +/* _ITR is ITR index, _INT is interrupt index, _itrn_indx_spacing is spacing + * b/w itrn registers of the same vector + */ +#define VF_INT_ITR0(_ITR) (0x00004C00 + ((_ITR) * 4)) +#define VF_INT_ITRN_ADDR(_ITR, _reg_start, _itrn_indx_spacing) \ + ((_reg_start) + ((_ITR) * (_itrn_indx_spacing))) +/* For VF with 16 vector support, itrn_reg_spacing is 0x4, itrn_indx_spacing + * is 0x40 and base register offset is 0x00002800 + */ +#define VF_INT_ITRN(_INT, _ITR) \ + (0x00002800 + ((_INT) * 4) + ((_ITR) * 0x40)) +/* For VF with 64 vector support, itrn_reg_spacing is 0x4, itrn_indx_spacing + * is 0x100 and base register offset is 0x00002C00 + */ +#define VF_INT_ITRN_64(_INT, _ITR) \ + (0x00002C00 + ((_INT) * 4) + ((_ITR) * 0x100)) +/* For VF with 2k vector support, itrn_reg_spacing is 0x4, itrn_indx_spacing + * is 0x2000 and base register offset is 0x00072000 + */ +#define VF_INT_ITRN_2K(_INT, _ITR) \ + (0x00072000 + ((_INT) * 4) + ((_ITR) * 0x2000)) +#define VF_INT_ITRN_MAX_INDEX 2 +#define VF_INT_ITRN_INTERVAL_S 0 +#define VF_INT_ITRN_INTERVAL_M GENMASK(11, 0) +#define VF_INT_PBA_CLEAR 0x00008900 + +#define VF_INT_ICR0_ENA1 0x00005000 +#define VF_INT_ICR0_ENA1_ADMINQ_S 30 +#define VF_INT_ICR0_ENA1_ADMINQ_M BIT(VF_INT_ICR0_ENA1_ADMINQ_S) +#define VF_INT_ICR0_ENA1_RSVD_S 31 +#define VF_INT_ICR01 0x00004800 +#define VF_QF_HENA(_i) (0x0000C400 + ((_i) * 4)) +#define VF_QF_HENA_MAX_INDX 1 +#define VF_QF_HKEY(_i) (0x0000CC00 + ((_i) * 4)) +#define VF_QF_HKEY_MAX_INDX 12 +#define VF_QF_HLUT(_i) (0x0000D000 + ((_i) * 4)) +#define VF_QF_HLUT_MAX_INDX 15 +#endif diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c new file mode 100644 index 000000000000..19809b0ddcd9 --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -0,0 +1,2379 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2023 Intel Corporation */ + +#include "idpf.h" + +static const struct net_device_ops idpf_netdev_ops_splitq; +static const struct net_device_ops idpf_netdev_ops_singleq; + +const char * const idpf_vport_vc_state_str[] = { + IDPF_FOREACH_VPORT_VC_STATE(IDPF_GEN_STRING) +}; + +/** + * idpf_init_vector_stack - Fill the MSIX vector stack with vector index + * @adapter: private data struct + * + * Return 0 on success, error on failure + */ +static int idpf_init_vector_stack(struct idpf_adapter *adapter) +{ + struct idpf_vector_lifo *stack; + u16 min_vec; + u32 i; + + mutex_lock(&adapter->vector_lock); + min_vec = adapter->num_msix_entries - adapter->num_avail_msix; + stack = &adapter->vector_stack; + stack->size = adapter->num_msix_entries; + /* set the base and top to point at start of the 'free pool' to + * distribute the unused vectors on-demand basis + */ + stack->base = min_vec; + stack->top = min_vec; + + stack->vec_idx = kcalloc(stack->size, sizeof(u16), GFP_KERNEL); + if (!stack->vec_idx) { + mutex_unlock(&adapter->vector_lock); + + return -ENOMEM; + } + + for (i = 0; i < stack->size; i++) + stack->vec_idx[i] = i; + + mutex_unlock(&adapter->vector_lock); + + return 0; +} + +/** + * idpf_deinit_vector_stack - zero out the MSIX vector stack + * @adapter: private data struct + */ +static void idpf_deinit_vector_stack(struct idpf_adapter *adapter) +{ + struct idpf_vector_lifo *stack; + + mutex_lock(&adapter->vector_lock); + stack = &adapter->vector_stack; + kfree(stack->vec_idx); + stack->vec_idx = NULL; + mutex_unlock(&adapter->vector_lock); +} + +/** + * idpf_mb_intr_rel_irq - Free the IRQ association with the OS + * @adapter: adapter structure + * + * This will also disable interrupt mode and queue up mailbox task. Mailbox + * task will reschedule itself if not in interrupt mode. + */ +static void idpf_mb_intr_rel_irq(struct idpf_adapter *adapter) +{ + clear_bit(IDPF_MB_INTR_MODE, adapter->flags); + free_irq(adapter->msix_entries[0].vector, adapter); + queue_delayed_work(adapter->mbx_wq, &adapter->mbx_task, 0); +} + +/** + * idpf_intr_rel - Release interrupt capabilities and free memory + * @adapter: adapter to disable interrupts on + */ +void idpf_intr_rel(struct idpf_adapter *adapter) +{ + int err; + + if (!adapter->msix_entries) + return; + + idpf_mb_intr_rel_irq(adapter); + pci_free_irq_vectors(adapter->pdev); + + err = idpf_send_dealloc_vectors_msg(adapter); + if (err) + dev_err(&adapter->pdev->dev, + "Failed to deallocate vectors: %d\n", err); + + idpf_deinit_vector_stack(adapter); + kfree(adapter->msix_entries); + adapter->msix_entries = NULL; +} + +/** + * idpf_mb_intr_clean - Interrupt handler for the mailbox + * @irq: interrupt number + * @data: pointer to the adapter structure + */ +static irqreturn_t idpf_mb_intr_clean(int __always_unused irq, void *data) +{ + struct idpf_adapter *adapter = (struct idpf_adapter *)data; + + queue_delayed_work(adapter->mbx_wq, &adapter->mbx_task, 0); + + return IRQ_HANDLED; +} + +/** + * idpf_mb_irq_enable - Enable MSIX interrupt for the mailbox + * @adapter: adapter to get the hardware address for register write + */ +static void idpf_mb_irq_enable(struct idpf_adapter *adapter) +{ + struct idpf_intr_reg *intr = &adapter->mb_vector.intr_reg; + u32 val; + + val = intr->dyn_ctl_intena_m | intr->dyn_ctl_itridx_m; + writel(val, intr->dyn_ctl); + writel(intr->icr_ena_ctlq_m, intr->icr_ena); +} + +/** + * idpf_mb_intr_req_irq - Request irq for the mailbox interrupt + * @adapter: adapter structure to pass to the mailbox irq handler + */ +static int idpf_mb_intr_req_irq(struct idpf_adapter *adapter) +{ + struct idpf_q_vector *mb_vector = &adapter->mb_vector; + int irq_num, mb_vidx = 0, err; + + irq_num = adapter->msix_entries[mb_vidx].vector; + mb_vector->name = kasprintf(GFP_KERNEL, "%s-%s-%d", + dev_driver_string(&adapter->pdev->dev), + "Mailbox", mb_vidx); + err = request_irq(irq_num, adapter->irq_mb_handler, 0, + mb_vector->name, adapter); + if (err) { + dev_err(&adapter->pdev->dev, + "IRQ request for mailbox failed, error: %d\n", err); + + return err; + } + + set_bit(IDPF_MB_INTR_MODE, adapter->flags); + + return 0; +} + +/** + * idpf_set_mb_vec_id - Set vector index for mailbox + * @adapter: adapter structure to access the vector chunks + * + * The first vector id in the requested vector chunks from the CP is for + * the mailbox + */ +static void idpf_set_mb_vec_id(struct idpf_adapter *adapter) +{ + if (adapter->req_vec_chunks) + adapter->mb_vector.v_idx = + le16_to_cpu(adapter->caps.mailbox_vector_id); + else + adapter->mb_vector.v_idx = 0; +} + +/** + * idpf_mb_intr_init - Initialize the mailbox interrupt + * @adapter: adapter structure to store the mailbox vector + */ +static int idpf_mb_intr_init(struct idpf_adapter *adapter) +{ + adapter->dev_ops.reg_ops.mb_intr_reg_init(adapter); + adapter->irq_mb_handler = idpf_mb_intr_clean; + + return idpf_mb_intr_req_irq(adapter); +} + +/** + * idpf_vector_lifo_push - push MSIX vector index onto stack + * @adapter: private data struct + * @vec_idx: vector index to store + */ +static int idpf_vector_lifo_push(struct idpf_adapter *adapter, u16 vec_idx) +{ + struct idpf_vector_lifo *stack = &adapter->vector_stack; + + lockdep_assert_held(&adapter->vector_lock); + + if (stack->top == stack->base) { + dev_err(&adapter->pdev->dev, "Exceeded the vector stack limit: %d\n", + stack->top); + return -EINVAL; + } + + stack->vec_idx[--stack->top] = vec_idx; + + return 0; +} + +/** + * idpf_vector_lifo_pop - pop MSIX vector index from stack + * @adapter: private data struct + */ +static int idpf_vector_lifo_pop(struct idpf_adapter *adapter) +{ + struct idpf_vector_lifo *stack = &adapter->vector_stack; + + lockdep_assert_held(&adapter->vector_lock); + + if (stack->top == stack->size) { + dev_err(&adapter->pdev->dev, "No interrupt vectors are available to distribute!\n"); + + return -EINVAL; + } + + return stack->vec_idx[stack->top++]; +} + +/** + * idpf_vector_stash - Store the vector indexes onto the stack + * @adapter: private data struct + * @q_vector_idxs: vector index array + * @vec_info: info related to the number of vectors + * + * This function is a no-op if there are no vectors indexes to be stashed + */ +static void idpf_vector_stash(struct idpf_adapter *adapter, u16 *q_vector_idxs, + struct idpf_vector_info *vec_info) +{ + int i, base = 0; + u16 vec_idx; + + lockdep_assert_held(&adapter->vector_lock); + + if (!vec_info->num_curr_vecs) + return; + + /* For default vports, no need to stash vector allocated from the + * default pool onto the stack + */ + if (vec_info->default_vport) + base = IDPF_MIN_Q_VEC; + + for (i = vec_info->num_curr_vecs - 1; i >= base ; i--) { + vec_idx = q_vector_idxs[i]; + idpf_vector_lifo_push(adapter, vec_idx); + adapter->num_avail_msix++; + } +} + +/** + * idpf_req_rel_vector_indexes - Request or release MSIX vector indexes + * @adapter: driver specific private structure + * @q_vector_idxs: vector index array + * @vec_info: info related to the number of vectors + * + * This is the core function to distribute the MSIX vectors acquired from the + * OS. It expects the caller to pass the number of vectors required and + * also previously allocated. First, it stashes previously allocated vector + * indexes on to the stack and then figures out if it can allocate requested + * vectors. It can wait on acquiring the mutex lock. If the caller passes 0 as + * requested vectors, then this function just stashes the already allocated + * vectors and returns 0. + * + * Returns actual number of vectors allocated on success, error value on failure + * If 0 is returned, implies the stack has no vectors to allocate which is also + * a failure case for the caller + */ +int idpf_req_rel_vector_indexes(struct idpf_adapter *adapter, + u16 *q_vector_idxs, + struct idpf_vector_info *vec_info) +{ + u16 num_req_vecs, num_alloc_vecs = 0, max_vecs; + struct idpf_vector_lifo *stack; + int i, j, vecid; + + mutex_lock(&adapter->vector_lock); + stack = &adapter->vector_stack; + num_req_vecs = vec_info->num_req_vecs; + + /* Stash interrupt vector indexes onto the stack if required */ + idpf_vector_stash(adapter, q_vector_idxs, vec_info); + + if (!num_req_vecs) + goto rel_lock; + + if (vec_info->default_vport) { + /* As IDPF_MIN_Q_VEC per default vport is put aside in the + * default pool of the stack, use them for default vports + */ + j = vec_info->index * IDPF_MIN_Q_VEC + IDPF_MBX_Q_VEC; + for (i = 0; i < IDPF_MIN_Q_VEC; i++) { + q_vector_idxs[num_alloc_vecs++] = stack->vec_idx[j++]; + num_req_vecs--; + } + } + + /* Find if stack has enough vector to allocate */ + max_vecs = min(adapter->num_avail_msix, num_req_vecs); + + for (j = 0; j < max_vecs; j++) { + vecid = idpf_vector_lifo_pop(adapter); + q_vector_idxs[num_alloc_vecs++] = vecid; + } + adapter->num_avail_msix -= max_vecs; + +rel_lock: + mutex_unlock(&adapter->vector_lock); + + return num_alloc_vecs; +} + +/** + * idpf_intr_req - Request interrupt capabilities + * @adapter: adapter to enable interrupts on + * + * Returns 0 on success, negative on failure + */ +int idpf_intr_req(struct idpf_adapter *adapter) +{ + u16 default_vports = idpf_get_default_vports(adapter); + int num_q_vecs, total_vecs, num_vec_ids; + int min_vectors, v_actual, err; + unsigned int vector; + u16 *vecids; + + total_vecs = idpf_get_reserved_vecs(adapter); + num_q_vecs = total_vecs - IDPF_MBX_Q_VEC; + + err = idpf_send_alloc_vectors_msg(adapter, num_q_vecs); + if (err) { + dev_err(&adapter->pdev->dev, + "Failed to allocate %d vectors: %d\n", num_q_vecs, err); + + return -EAGAIN; + } + + min_vectors = IDPF_MBX_Q_VEC + IDPF_MIN_Q_VEC * default_vports; + v_actual = pci_alloc_irq_vectors(adapter->pdev, min_vectors, + total_vecs, PCI_IRQ_MSIX); + if (v_actual < min_vectors) { + dev_err(&adapter->pdev->dev, "Failed to allocate MSIX vectors: %d\n", + v_actual); + err = -EAGAIN; + goto send_dealloc_vecs; + } + + adapter->msix_entries = kcalloc(v_actual, sizeof(struct msix_entry), + GFP_KERNEL); + + if (!adapter->msix_entries) { + err = -ENOMEM; + goto free_irq; + } + + idpf_set_mb_vec_id(adapter); + + vecids = kcalloc(total_vecs, sizeof(u16), GFP_KERNEL); + if (!vecids) { + err = -ENOMEM; + goto free_msix; + } + + if (adapter->req_vec_chunks) { + struct virtchnl2_vector_chunks *vchunks; + struct virtchnl2_alloc_vectors *ac; + + ac = adapter->req_vec_chunks; + vchunks = &ac->vchunks; + + num_vec_ids = idpf_get_vec_ids(adapter, vecids, total_vecs, + vchunks); + if (num_vec_ids < v_actual) { + err = -EINVAL; + goto free_vecids; + } + } else { + int i; + + for (i = 0; i < v_actual; i++) + vecids[i] = i; + } + + for (vector = 0; vector < v_actual; vector++) { + adapter->msix_entries[vector].entry = vecids[vector]; + adapter->msix_entries[vector].vector = + pci_irq_vector(adapter->pdev, vector); + } + + adapter->num_req_msix = total_vecs; + adapter->num_msix_entries = v_actual; + /* 'num_avail_msix' is used to distribute excess vectors to the vports + * after considering the minimum vectors required per each default + * vport + */ + adapter->num_avail_msix = v_actual - min_vectors; + + /* Fill MSIX vector lifo stack with vector indexes */ + err = idpf_init_vector_stack(adapter); + if (err) + goto free_vecids; + + err = idpf_mb_intr_init(adapter); + if (err) + goto deinit_vec_stack; + idpf_mb_irq_enable(adapter); + kfree(vecids); + + return 0; + +deinit_vec_stack: + idpf_deinit_vector_stack(adapter); +free_vecids: + kfree(vecids); +free_msix: + kfree(adapter->msix_entries); + adapter->msix_entries = NULL; +free_irq: + pci_free_irq_vectors(adapter->pdev); +send_dealloc_vecs: + idpf_send_dealloc_vectors_msg(adapter); + + return err; +} + +/** + * idpf_find_mac_filter - Search filter list for specific mac filter + * @vconfig: Vport config structure + * @macaddr: The MAC address + * + * Returns ptr to the filter object or NULL. Must be called while holding the + * mac_filter_list_lock. + **/ +static struct idpf_mac_filter *idpf_find_mac_filter(struct idpf_vport_config *vconfig, + const u8 *macaddr) +{ + struct idpf_mac_filter *f; + + if (!macaddr) + return NULL; + + list_for_each_entry(f, &vconfig->user_config.mac_filter_list, list) { + if (ether_addr_equal(macaddr, f->macaddr)) + return f; + } + + return NULL; +} + +/** + * __idpf_del_mac_filter - Delete a MAC filter from the filter list + * @vport_config: Vport config structure + * @macaddr: The MAC address + * + * Returns 0 on success, error value on failure + **/ +static int __idpf_del_mac_filter(struct idpf_vport_config *vport_config, + const u8 *macaddr) +{ + struct idpf_mac_filter *f; + + spin_lock_bh(&vport_config->mac_filter_list_lock); + f = idpf_find_mac_filter(vport_config, macaddr); + if (f) { + list_del(&f->list); + kfree(f); + } + spin_unlock_bh(&vport_config->mac_filter_list_lock); + + return 0; +} + +/** + * idpf_del_mac_filter - Delete a MAC filter from the filter list + * @vport: Main vport structure + * @np: Netdev private structure + * @macaddr: The MAC address + * @async: Don't wait for return message + * + * Removes filter from list and if interface is up, tells hardware about the + * removed filter. + **/ +static int idpf_del_mac_filter(struct idpf_vport *vport, + struct idpf_netdev_priv *np, + const u8 *macaddr, bool async) +{ + struct idpf_vport_config *vport_config; + struct idpf_mac_filter *f; + + vport_config = np->adapter->vport_config[np->vport_idx]; + + spin_lock_bh(&vport_config->mac_filter_list_lock); + f = idpf_find_mac_filter(vport_config, macaddr); + if (f) { + f->remove = true; + } else { + spin_unlock_bh(&vport_config->mac_filter_list_lock); + + return -EINVAL; + } + spin_unlock_bh(&vport_config->mac_filter_list_lock); + + if (np->state == __IDPF_VPORT_UP) { + int err; + + err = idpf_add_del_mac_filters(vport, np, false, async); + if (err) + return err; + } + + return __idpf_del_mac_filter(vport_config, macaddr); +} + +/** + * __idpf_add_mac_filter - Add mac filter helper function + * @vport_config: Vport config structure + * @macaddr: Address to add + * + * Takes mac_filter_list_lock spinlock to add new filter to list. + */ +static int __idpf_add_mac_filter(struct idpf_vport_config *vport_config, + const u8 *macaddr) +{ + struct idpf_mac_filter *f; + + spin_lock_bh(&vport_config->mac_filter_list_lock); + + f = idpf_find_mac_filter(vport_config, macaddr); + if (f) { + f->remove = false; + spin_unlock_bh(&vport_config->mac_filter_list_lock); + + return 0; + } + + f = kzalloc(sizeof(*f), GFP_ATOMIC); + if (!f) { + spin_unlock_bh(&vport_config->mac_filter_list_lock); + + return -ENOMEM; + } + + ether_addr_copy(f->macaddr, macaddr); + list_add_tail(&f->list, &vport_config->user_config.mac_filter_list); + f->add = true; + + spin_unlock_bh(&vport_config->mac_filter_list_lock); + + return 0; +} + +/** + * idpf_add_mac_filter - Add a mac filter to the filter list + * @vport: Main vport structure + * @np: Netdev private structure + * @macaddr: The MAC address + * @async: Don't wait for return message + * + * Returns 0 on success or error on failure. If interface is up, we'll also + * send the virtchnl message to tell hardware about the filter. + **/ +static int idpf_add_mac_filter(struct idpf_vport *vport, + struct idpf_netdev_priv *np, + const u8 *macaddr, bool async) +{ + struct idpf_vport_config *vport_config; + int err; + + vport_config = np->adapter->vport_config[np->vport_idx]; + err = __idpf_add_mac_filter(vport_config, macaddr); + if (err) + return err; + + if (np->state == __IDPF_VPORT_UP) + err = idpf_add_del_mac_filters(vport, np, true, async); + + return err; +} + +/** + * idpf_del_all_mac_filters - Delete all MAC filters in list + * @vport: main vport struct + * + * Takes mac_filter_list_lock spinlock. Deletes all filters + */ +static void idpf_del_all_mac_filters(struct idpf_vport *vport) +{ + struct idpf_vport_config *vport_config; + struct idpf_mac_filter *f, *ftmp; + + vport_config = vport->adapter->vport_config[vport->idx]; + spin_lock_bh(&vport_config->mac_filter_list_lock); + + list_for_each_entry_safe(f, ftmp, &vport_config->user_config.mac_filter_list, + list) { + list_del(&f->list); + kfree(f); + } + + spin_unlock_bh(&vport_config->mac_filter_list_lock); +} + +/** + * idpf_restore_mac_filters - Re-add all MAC filters in list + * @vport: main vport struct + * + * Takes mac_filter_list_lock spinlock. Sets add field to true for filters to + * resync filters back to HW. + */ +static void idpf_restore_mac_filters(struct idpf_vport *vport) +{ + struct idpf_vport_config *vport_config; + struct idpf_mac_filter *f; + + vport_config = vport->adapter->vport_config[vport->idx]; + spin_lock_bh(&vport_config->mac_filter_list_lock); + + list_for_each_entry(f, &vport_config->user_config.mac_filter_list, list) + f->add = true; + + spin_unlock_bh(&vport_config->mac_filter_list_lock); + + idpf_add_del_mac_filters(vport, netdev_priv(vport->netdev), + true, false); +} + +/** + * idpf_remove_mac_filters - Remove all MAC filters in list + * @vport: main vport struct + * + * Takes mac_filter_list_lock spinlock. Sets remove field to true for filters + * to remove filters in HW. + */ +static void idpf_remove_mac_filters(struct idpf_vport *vport) +{ + struct idpf_vport_config *vport_config; + struct idpf_mac_filter *f; + + vport_config = vport->adapter->vport_config[vport->idx]; + spin_lock_bh(&vport_config->mac_filter_list_lock); + + list_for_each_entry(f, &vport_config->user_config.mac_filter_list, list) + f->remove = true; + + spin_unlock_bh(&vport_config->mac_filter_list_lock); + + idpf_add_del_mac_filters(vport, netdev_priv(vport->netdev), + false, false); +} + +/** + * idpf_deinit_mac_addr - deinitialize mac address for vport + * @vport: main vport structure + */ +static void idpf_deinit_mac_addr(struct idpf_vport *vport) +{ + struct idpf_vport_config *vport_config; + struct idpf_mac_filter *f; + + vport_config = vport->adapter->vport_config[vport->idx]; + + spin_lock_bh(&vport_config->mac_filter_list_lock); + + f = idpf_find_mac_filter(vport_config, vport->default_mac_addr); + if (f) { + list_del(&f->list); + kfree(f); + } + + spin_unlock_bh(&vport_config->mac_filter_list_lock); +} + +/** + * idpf_init_mac_addr - initialize mac address for vport + * @vport: main vport structure + * @netdev: pointer to netdev struct associated with this vport + */ +static int idpf_init_mac_addr(struct idpf_vport *vport, + struct net_device *netdev) +{ + struct idpf_netdev_priv *np = netdev_priv(netdev); + struct idpf_adapter *adapter = vport->adapter; + int err; + + if (is_valid_ether_addr(vport->default_mac_addr)) { + eth_hw_addr_set(netdev, vport->default_mac_addr); + ether_addr_copy(netdev->perm_addr, vport->default_mac_addr); + + return idpf_add_mac_filter(vport, np, vport->default_mac_addr, + false); + } + + if (!idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, + VIRTCHNL2_CAP_MACFILTER)) { + dev_err(&adapter->pdev->dev, + "MAC address is not provided and capability is not set\n"); + + return -EINVAL; + } + + eth_hw_addr_random(netdev); + err = idpf_add_mac_filter(vport, np, netdev->dev_addr, false); + if (err) + return err; + + dev_info(&adapter->pdev->dev, "Invalid MAC address %pM, using random %pM\n", + vport->default_mac_addr, netdev->dev_addr); + ether_addr_copy(vport->default_mac_addr, netdev->dev_addr); + + return 0; +} + +/** + * idpf_cfg_netdev - Allocate, configure and register a netdev + * @vport: main vport structure + * + * Returns 0 on success, negative value on failure. + */ +static int idpf_cfg_netdev(struct idpf_vport *vport) +{ + struct idpf_adapter *adapter = vport->adapter; + struct idpf_vport_config *vport_config; + netdev_features_t dflt_features; + netdev_features_t offloads = 0; + struct idpf_netdev_priv *np; + struct net_device *netdev; + u16 idx = vport->idx; + int err; + + vport_config = adapter->vport_config[idx]; + + /* It's possible we already have a netdev allocated and registered for + * this vport + */ + if (test_bit(IDPF_VPORT_REG_NETDEV, vport_config->flags)) { + netdev = adapter->netdevs[idx]; + np = netdev_priv(netdev); + np->vport = vport; + np->vport_idx = vport->idx; + np->vport_id = vport->vport_id; + vport->netdev = netdev; + + return idpf_init_mac_addr(vport, netdev); + } + + netdev = alloc_etherdev_mqs(sizeof(struct idpf_netdev_priv), + vport_config->max_q.max_txq, + vport_config->max_q.max_rxq); + if (!netdev) + return -ENOMEM; + + vport->netdev = netdev; + np = netdev_priv(netdev); + np->vport = vport; + np->adapter = adapter; + np->vport_idx = vport->idx; + np->vport_id = vport->vport_id; + + spin_lock_init(&np->stats_lock); + + err = idpf_init_mac_addr(vport, netdev); + if (err) { + free_netdev(vport->netdev); + vport->netdev = NULL; + + return err; + } + + /* assign netdev_ops */ + if (idpf_is_queue_model_split(vport->txq_model)) + netdev->netdev_ops = &idpf_netdev_ops_splitq; + else + netdev->netdev_ops = &idpf_netdev_ops_singleq; + + /* setup watchdog timeout value to be 5 second */ + netdev->watchdog_timeo = 5 * HZ; + + /* configure default MTU size */ + netdev->min_mtu = ETH_MIN_MTU; + netdev->max_mtu = vport->max_mtu; + + dflt_features = NETIF_F_SG | + NETIF_F_HIGHDMA; + + if (idpf_is_cap_ena_all(adapter, IDPF_RSS_CAPS, IDPF_CAP_RSS)) + dflt_features |= NETIF_F_RXHASH; + if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_RX_CSUM_L4V4)) + dflt_features |= NETIF_F_IP_CSUM; + if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_RX_CSUM_L4V6)) + dflt_features |= NETIF_F_IPV6_CSUM; + if (idpf_is_cap_ena(adapter, IDPF_CSUM_CAPS, IDPF_CAP_RX_CSUM)) + dflt_features |= NETIF_F_RXCSUM; + if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_SCTP_CSUM)) + dflt_features |= NETIF_F_SCTP_CRC; + + if (idpf_is_cap_ena(adapter, IDPF_SEG_CAPS, VIRTCHNL2_CAP_SEG_IPV4_TCP)) + dflt_features |= NETIF_F_TSO; + if (idpf_is_cap_ena(adapter, IDPF_SEG_CAPS, VIRTCHNL2_CAP_SEG_IPV6_TCP)) + dflt_features |= NETIF_F_TSO6; + if (idpf_is_cap_ena_all(adapter, IDPF_SEG_CAPS, + VIRTCHNL2_CAP_SEG_IPV4_UDP | + VIRTCHNL2_CAP_SEG_IPV6_UDP)) + dflt_features |= NETIF_F_GSO_UDP_L4; + if (idpf_is_cap_ena_all(adapter, IDPF_RSC_CAPS, IDPF_CAP_RSC)) + offloads |= NETIF_F_GRO_HW; + /* advertise to stack only if offloads for encapsulated packets is + * supported + */ + if (idpf_is_cap_ena(vport->adapter, IDPF_SEG_CAPS, + VIRTCHNL2_CAP_SEG_TX_SINGLE_TUNNEL)) { + offloads |= NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_GRE | + NETIF_F_GSO_GRE_CSUM | + NETIF_F_GSO_PARTIAL | + NETIF_F_GSO_UDP_TUNNEL_CSUM | + NETIF_F_GSO_IPXIP4 | + NETIF_F_GSO_IPXIP6 | + 0; + + if (!idpf_is_cap_ena_all(vport->adapter, IDPF_CSUM_CAPS, + IDPF_CAP_TUNNEL_TX_CSUM)) + netdev->gso_partial_features |= + NETIF_F_GSO_UDP_TUNNEL_CSUM; + + netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM; + offloads |= NETIF_F_TSO_MANGLEID; + } + if (idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_LOOPBACK)) + offloads |= NETIF_F_LOOPBACK; + + netdev->features |= dflt_features; + netdev->hw_features |= dflt_features | offloads; + netdev->hw_enc_features |= dflt_features | offloads; + idpf_set_ethtool_ops(netdev); + SET_NETDEV_DEV(netdev, &adapter->pdev->dev); + + /* carrier off on init to avoid Tx hangs */ + netif_carrier_off(netdev); + + /* make sure transmit queues start off as stopped */ + netif_tx_stop_all_queues(netdev); + + /* The vport can be arbitrarily released so we need to also track + * netdevs in the adapter struct + */ + adapter->netdevs[idx] = netdev; + + return 0; +} + +/** + * idpf_get_free_slot - get the next non-NULL location index in array + * @adapter: adapter in which to look for a free vport slot + */ +static int idpf_get_free_slot(struct idpf_adapter *adapter) +{ + unsigned int i; + + for (i = 0; i < adapter->max_vports; i++) { + if (!adapter->vports[i]) + return i; + } + + return IDPF_NO_FREE_SLOT; +} + +/** + * idpf_remove_features - Turn off feature configs + * @vport: virtual port structure + */ +static void idpf_remove_features(struct idpf_vport *vport) +{ + struct idpf_adapter *adapter = vport->adapter; + + if (idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_MACFILTER)) + idpf_remove_mac_filters(vport); +} + +/** + * idpf_vport_stop - Disable a vport + * @vport: vport to disable + */ +static void idpf_vport_stop(struct idpf_vport *vport) +{ + struct idpf_netdev_priv *np = netdev_priv(vport->netdev); + + if (np->state <= __IDPF_VPORT_DOWN) + return; + + netif_carrier_off(vport->netdev); + netif_tx_disable(vport->netdev); + + idpf_send_disable_vport_msg(vport); + idpf_send_disable_queues_msg(vport); + idpf_send_map_unmap_queue_vector_msg(vport, false); + /* Normally we ask for queues in create_vport, but if the number of + * initially requested queues have changed, for example via ethtool + * set channels, we do delete queues and then add the queues back + * instead of deleting and reallocating the vport. + */ + if (test_and_clear_bit(IDPF_VPORT_DEL_QUEUES, vport->flags)) + idpf_send_delete_queues_msg(vport); + + idpf_remove_features(vport); + + vport->link_up = false; + idpf_vport_intr_deinit(vport); + idpf_vport_intr_rel(vport); + idpf_vport_queues_rel(vport); + np->state = __IDPF_VPORT_DOWN; +} + +/** + * idpf_stop - Disables a network interface + * @netdev: network interface device structure + * + * The stop entry point is called when an interface is de-activated by the OS, + * and the netdevice enters the DOWN state. The hardware is still under the + * driver's control, but the netdev interface is disabled. + * + * Returns success only - not allowed to fail + */ +static int idpf_stop(struct net_device *netdev) +{ + struct idpf_netdev_priv *np = netdev_priv(netdev); + struct idpf_vport *vport; + + if (test_bit(IDPF_REMOVE_IN_PROG, np->adapter->flags)) + return 0; + + idpf_vport_ctrl_lock(netdev); + vport = idpf_netdev_to_vport(netdev); + + idpf_vport_stop(vport); + + idpf_vport_ctrl_unlock(netdev); + + return 0; +} + +/** + * idpf_decfg_netdev - Unregister the netdev + * @vport: vport for which netdev to be unregistered + */ +static void idpf_decfg_netdev(struct idpf_vport *vport) +{ + struct idpf_adapter *adapter = vport->adapter; + + unregister_netdev(vport->netdev); + free_netdev(vport->netdev); + vport->netdev = NULL; + + adapter->netdevs[vport->idx] = NULL; +} + +/** + * idpf_vport_rel - Delete a vport and free its resources + * @vport: the vport being removed + */ +static void idpf_vport_rel(struct idpf_vport *vport) +{ + struct idpf_adapter *adapter = vport->adapter; + struct idpf_vport_config *vport_config; + struct idpf_vector_info vec_info; + struct idpf_rss_data *rss_data; + struct idpf_vport_max_q max_q; + u16 idx = vport->idx; + int i; + + vport_config = adapter->vport_config[vport->idx]; + idpf_deinit_rss(vport); + rss_data = &vport_config->user_config.rss_data; + kfree(rss_data->rss_key); + rss_data->rss_key = NULL; + + idpf_send_destroy_vport_msg(vport); + + /* Set all bits as we dont know on which vc_state the vport vhnl_wq + * is waiting on and wakeup the virtchnl workqueue even if it is + * waiting for the response as we are going down + */ + for (i = 0; i < IDPF_VC_NBITS; i++) + set_bit(i, vport->vc_state); + wake_up(&vport->vchnl_wq); + + mutex_destroy(&vport->vc_buf_lock); + + /* Clear all the bits */ + for (i = 0; i < IDPF_VC_NBITS; i++) + clear_bit(i, vport->vc_state); + + /* Release all max queues allocated to the adapter's pool */ + max_q.max_rxq = vport_config->max_q.max_rxq; + max_q.max_txq = vport_config->max_q.max_txq; + max_q.max_bufq = vport_config->max_q.max_bufq; + max_q.max_complq = vport_config->max_q.max_complq; + idpf_vport_dealloc_max_qs(adapter, &max_q); + + /* Release all the allocated vectors on the stack */ + vec_info.num_req_vecs = 0; + vec_info.num_curr_vecs = vport->num_q_vectors; + vec_info.default_vport = vport->default_vport; + + idpf_req_rel_vector_indexes(adapter, vport->q_vector_idxs, &vec_info); + + kfree(vport->q_vector_idxs); + vport->q_vector_idxs = NULL; + + kfree(adapter->vport_params_recvd[idx]); + adapter->vport_params_recvd[idx] = NULL; + kfree(adapter->vport_params_reqd[idx]); + adapter->vport_params_reqd[idx] = NULL; + if (adapter->vport_config[idx]) { + kfree(adapter->vport_config[idx]->req_qs_chunks); + adapter->vport_config[idx]->req_qs_chunks = NULL; + } + kfree(vport); + adapter->num_alloc_vports--; +} + +/** + * idpf_vport_dealloc - cleanup and release a given vport + * @vport: pointer to idpf vport structure + * + * returns nothing + */ +static void idpf_vport_dealloc(struct idpf_vport *vport) +{ + struct idpf_adapter *adapter = vport->adapter; + unsigned int i = vport->idx; + + idpf_deinit_mac_addr(vport); + idpf_vport_stop(vport); + + if (!test_bit(IDPF_HR_RESET_IN_PROG, adapter->flags)) + idpf_decfg_netdev(vport); + if (test_bit(IDPF_REMOVE_IN_PROG, adapter->flags)) + idpf_del_all_mac_filters(vport); + + if (adapter->netdevs[i]) { + struct idpf_netdev_priv *np = netdev_priv(adapter->netdevs[i]); + + np->vport = NULL; + } + + idpf_vport_rel(vport); + + adapter->vports[i] = NULL; + adapter->next_vport = idpf_get_free_slot(adapter); +} + +/** + * idpf_vport_alloc - Allocates the next available struct vport in the adapter + * @adapter: board private structure + * @max_q: vport max queue info + * + * returns a pointer to a vport on success, NULL on failure. + */ +static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter, + struct idpf_vport_max_q *max_q) +{ + struct idpf_rss_data *rss_data; + u16 idx = adapter->next_vport; + struct idpf_vport *vport; + u16 num_max_q; + + if (idx == IDPF_NO_FREE_SLOT) + return NULL; + + vport = kzalloc(sizeof(*vport), GFP_KERNEL); + if (!vport) + return vport; + + if (!adapter->vport_config[idx]) { + struct idpf_vport_config *vport_config; + + vport_config = kzalloc(sizeof(*vport_config), GFP_KERNEL); + if (!vport_config) { + kfree(vport); + + return NULL; + } + + adapter->vport_config[idx] = vport_config; + } + + vport->idx = idx; + vport->adapter = adapter; + vport->compln_clean_budget = IDPF_TX_COMPLQ_CLEAN_BUDGET; + vport->default_vport = adapter->num_alloc_vports < + idpf_get_default_vports(adapter); + + num_max_q = max(max_q->max_txq, max_q->max_rxq); + vport->q_vector_idxs = kcalloc(num_max_q, sizeof(u16), GFP_KERNEL); + if (!vport->q_vector_idxs) { + kfree(vport); + + return NULL; + } + idpf_vport_init(vport, max_q); + + /* This alloc is done separate from the LUT because it's not strictly + * dependent on how many queues we have. If we change number of queues + * and soft reset we'll need a new LUT but the key can remain the same + * for as long as the vport exists. + */ + rss_data = &adapter->vport_config[idx]->user_config.rss_data; + rss_data->rss_key = kzalloc(rss_data->rss_key_size, GFP_KERNEL); + if (!rss_data->rss_key) { + kfree(vport); + + return NULL; + } + /* Initialize default rss key */ + netdev_rss_key_fill((void *)rss_data->rss_key, rss_data->rss_key_size); + + /* fill vport slot in the adapter struct */ + adapter->vports[idx] = vport; + adapter->vport_ids[idx] = idpf_get_vport_id(vport); + + adapter->num_alloc_vports++; + /* prepare adapter->next_vport for next use */ + adapter->next_vport = idpf_get_free_slot(adapter); + + return vport; +} + +/** + * idpf_get_stats64 - get statistics for network device structure + * @netdev: network interface device structure + * @stats: main device statistics structure + */ +static void idpf_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats) +{ + struct idpf_netdev_priv *np = netdev_priv(netdev); + + spin_lock_bh(&np->stats_lock); + *stats = np->netstats; + spin_unlock_bh(&np->stats_lock); +} + +/** + * idpf_statistics_task - Delayed task to get statistics over mailbox + * @work: work_struct handle to our data + */ +void idpf_statistics_task(struct work_struct *work) +{ + struct idpf_adapter *adapter; + int i; + + adapter = container_of(work, struct idpf_adapter, stats_task.work); + + for (i = 0; i < adapter->max_vports; i++) { + struct idpf_vport *vport = adapter->vports[i]; + + if (vport && !test_bit(IDPF_HR_RESET_IN_PROG, adapter->flags)) + idpf_send_get_stats_msg(vport); + } + + queue_delayed_work(adapter->stats_wq, &adapter->stats_task, + msecs_to_jiffies(10000)); +} + +/** + * idpf_mbx_task - Delayed task to handle mailbox responses + * @work: work_struct handle + */ +void idpf_mbx_task(struct work_struct *work) +{ + struct idpf_adapter *adapter; + + adapter = container_of(work, struct idpf_adapter, mbx_task.work); + + if (test_bit(IDPF_MB_INTR_MODE, adapter->flags)) + idpf_mb_irq_enable(adapter); + else + queue_delayed_work(adapter->mbx_wq, &adapter->mbx_task, + msecs_to_jiffies(300)); + + idpf_recv_mb_msg(adapter, VIRTCHNL2_OP_UNKNOWN, NULL, 0); +} + +/** + * idpf_service_task - Delayed task for handling mailbox responses + * @work: work_struct handle to our data + * + */ +void idpf_service_task(struct work_struct *work) +{ + struct idpf_adapter *adapter; + + adapter = container_of(work, struct idpf_adapter, serv_task.work); + + if (idpf_is_reset_detected(adapter) && + !idpf_is_reset_in_prog(adapter) && + !test_bit(IDPF_REMOVE_IN_PROG, adapter->flags)) { + dev_info(&adapter->pdev->dev, "HW reset detected\n"); + set_bit(IDPF_HR_FUNC_RESET, adapter->flags); + queue_delayed_work(adapter->vc_event_wq, + &adapter->vc_event_task, + msecs_to_jiffies(10)); + } + + queue_delayed_work(adapter->serv_wq, &adapter->serv_task, + msecs_to_jiffies(300)); +} + +/** + * idpf_restore_features - Restore feature configs + * @vport: virtual port structure + */ +static void idpf_restore_features(struct idpf_vport *vport) +{ + struct idpf_adapter *adapter = vport->adapter; + + if (idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_MACFILTER)) + idpf_restore_mac_filters(vport); +} + +/** + * idpf_set_real_num_queues - set number of queues for netdev + * @vport: virtual port structure + * + * Returns 0 on success, negative on failure. + */ +static int idpf_set_real_num_queues(struct idpf_vport *vport) +{ + int err; + + err = netif_set_real_num_rx_queues(vport->netdev, vport->num_rxq); + if (err) + return err; + + return netif_set_real_num_tx_queues(vport->netdev, vport->num_txq); +} + +/** + * idpf_up_complete - Complete interface up sequence + * @vport: virtual port structure + * + * Returns 0 on success, negative on failure. + */ +static int idpf_up_complete(struct idpf_vport *vport) +{ + struct idpf_netdev_priv *np = netdev_priv(vport->netdev); + + if (vport->link_up && !netif_carrier_ok(vport->netdev)) { + netif_carrier_on(vport->netdev); + netif_tx_start_all_queues(vport->netdev); + } + + np->state = __IDPF_VPORT_UP; + + return 0; +} + +/** + * idpf_rx_init_buf_tail - Write initial buffer ring tail value + * @vport: virtual port struct + */ +static void idpf_rx_init_buf_tail(struct idpf_vport *vport) +{ + int i, j; + + for (i = 0; i < vport->num_rxq_grp; i++) { + struct idpf_rxq_group *grp = &vport->rxq_grps[i]; + + if (idpf_is_queue_model_split(vport->rxq_model)) { + for (j = 0; j < vport->num_bufqs_per_qgrp; j++) { + struct idpf_queue *q = + &grp->splitq.bufq_sets[j].bufq; + + writel(q->next_to_alloc, q->tail); + } + } else { + for (j = 0; j < grp->singleq.num_rxq; j++) { + struct idpf_queue *q = + grp->singleq.rxqs[j]; + + writel(q->next_to_alloc, q->tail); + } + } + } +} + +/** + * idpf_vport_open - Bring up a vport + * @vport: vport to bring up + * @alloc_res: allocate queue resources + */ +static int idpf_vport_open(struct idpf_vport *vport, bool alloc_res) +{ + struct idpf_netdev_priv *np = netdev_priv(vport->netdev); + struct idpf_adapter *adapter = vport->adapter; + struct idpf_vport_config *vport_config; + int err; + + if (np->state != __IDPF_VPORT_DOWN) + return -EBUSY; + + /* we do not allow interface up just yet */ + netif_carrier_off(vport->netdev); + + if (alloc_res) { + err = idpf_vport_queues_alloc(vport); + if (err) + return err; + } + + err = idpf_vport_intr_alloc(vport); + if (err) { + dev_err(&adapter->pdev->dev, "Failed to allocate interrupts for vport %u: %d\n", + vport->vport_id, err); + goto queues_rel; + } + + err = idpf_vport_queue_ids_init(vport); + if (err) { + dev_err(&adapter->pdev->dev, "Failed to initialize queue ids for vport %u: %d\n", + vport->vport_id, err); + goto intr_rel; + } + + err = idpf_vport_intr_init(vport); + if (err) { + dev_err(&adapter->pdev->dev, "Failed to initialize interrupts for vport %u: %d\n", + vport->vport_id, err); + goto intr_rel; + } + + err = idpf_rx_bufs_init_all(vport); + if (err) { + dev_err(&adapter->pdev->dev, "Failed to initialize RX buffers for vport %u: %d\n", + vport->vport_id, err); + goto intr_rel; + } + + err = idpf_queue_reg_init(vport); + if (err) { + dev_err(&adapter->pdev->dev, "Failed to initialize queue registers for vport %u: %d\n", + vport->vport_id, err); + goto intr_rel; + } + + idpf_rx_init_buf_tail(vport); + + err = idpf_send_config_queues_msg(vport); + if (err) { + dev_err(&adapter->pdev->dev, "Failed to configure queues for vport %u, %d\n", + vport->vport_id, err); + goto intr_deinit; + } + + err = idpf_send_map_unmap_queue_vector_msg(vport, true); + if (err) { + dev_err(&adapter->pdev->dev, "Failed to map queue vectors for vport %u: %d\n", + vport->vport_id, err); + goto intr_deinit; + } + + err = idpf_send_enable_queues_msg(vport); + if (err) { + dev_err(&adapter->pdev->dev, "Failed to enable queues for vport %u: %d\n", + vport->vport_id, err); + goto unmap_queue_vectors; + } + + err = idpf_send_enable_vport_msg(vport); + if (err) { + dev_err(&adapter->pdev->dev, "Failed to enable vport %u: %d\n", + vport->vport_id, err); + err = -EAGAIN; + goto disable_queues; + } + + idpf_restore_features(vport); + + vport_config = adapter->vport_config[vport->idx]; + if (vport_config->user_config.rss_data.rss_lut) + err = idpf_config_rss(vport); + else + err = idpf_init_rss(vport); + if (err) { + dev_err(&adapter->pdev->dev, "Failed to initialize RSS for vport %u: %d\n", + vport->vport_id, err); + goto disable_vport; + } + + err = idpf_up_complete(vport); + if (err) { + dev_err(&adapter->pdev->dev, "Failed to complete interface up for vport %u: %d\n", + vport->vport_id, err); + goto deinit_rss; + } + + return 0; + +deinit_rss: + idpf_deinit_rss(vport); +disable_vport: + idpf_send_disable_vport_msg(vport); +disable_queues: + idpf_send_disable_queues_msg(vport); +unmap_queue_vectors: + idpf_send_map_unmap_queue_vector_msg(vport, false); +intr_deinit: + idpf_vport_intr_deinit(vport); +intr_rel: + idpf_vport_intr_rel(vport); +queues_rel: + idpf_vport_queues_rel(vport); + + return err; +} + +/** + * idpf_init_task - Delayed initialization task + * @work: work_struct handle to our data + * + * Init task finishes up pending work started in probe. Due to the asynchronous + * nature in which the device communicates with hardware, we may have to wait + * several milliseconds to get a response. Instead of busy polling in probe, + * pulling it out into a delayed work task prevents us from bogging down the + * whole system waiting for a response from hardware. + */ +void idpf_init_task(struct work_struct *work) +{ + struct idpf_vport_config *vport_config; + struct idpf_vport_max_q max_q; + struct idpf_adapter *adapter; + struct idpf_netdev_priv *np; + struct idpf_vport *vport; + u16 num_default_vports; + struct pci_dev *pdev; + bool default_vport; + int index, err; + + adapter = container_of(work, struct idpf_adapter, init_task.work); + + num_default_vports = idpf_get_default_vports(adapter); + if (adapter->num_alloc_vports < num_default_vports) + default_vport = true; + else + default_vport = false; + + err = idpf_vport_alloc_max_qs(adapter, &max_q); + if (err) + goto unwind_vports; + + err = idpf_send_create_vport_msg(adapter, &max_q); + if (err) { + idpf_vport_dealloc_max_qs(adapter, &max_q); + goto unwind_vports; + } + + pdev = adapter->pdev; + vport = idpf_vport_alloc(adapter, &max_q); + if (!vport) { + err = -EFAULT; + dev_err(&pdev->dev, "failed to allocate vport: %d\n", + err); + idpf_vport_dealloc_max_qs(adapter, &max_q); + goto unwind_vports; + } + + index = vport->idx; + vport_config = adapter->vport_config[index]; + + init_waitqueue_head(&vport->sw_marker_wq); + init_waitqueue_head(&vport->vchnl_wq); + + mutex_init(&vport->vc_buf_lock); + spin_lock_init(&vport_config->mac_filter_list_lock); + + INIT_LIST_HEAD(&vport_config->user_config.mac_filter_list); + + err = idpf_check_supported_desc_ids(vport); + if (err) { + dev_err(&pdev->dev, "failed to get required descriptor ids\n"); + goto cfg_netdev_err; + } + + if (idpf_cfg_netdev(vport)) + goto cfg_netdev_err; + + err = idpf_send_get_rx_ptype_msg(vport); + if (err) + goto handle_err; + + /* Once state is put into DOWN, driver is ready for dev_open */ + np = netdev_priv(vport->netdev); + np->state = __IDPF_VPORT_DOWN; + if (test_and_clear_bit(IDPF_VPORT_UP_REQUESTED, vport_config->flags)) + idpf_vport_open(vport, true); + + /* Spawn and return 'idpf_init_task' work queue until all the + * default vports are created + */ + if (adapter->num_alloc_vports < num_default_vports) { + queue_delayed_work(adapter->init_wq, &adapter->init_task, + msecs_to_jiffies(5 * (adapter->pdev->devfn & 0x07))); + + return; + } + + for (index = 0; index < adapter->max_vports; index++) { + if (adapter->netdevs[index] && + !test_bit(IDPF_VPORT_REG_NETDEV, + adapter->vport_config[index]->flags)) { + register_netdev(adapter->netdevs[index]); + set_bit(IDPF_VPORT_REG_NETDEV, + adapter->vport_config[index]->flags); + } + } + + /* As all the required vports are created, clear the reset flag + * unconditionally here in case we were in reset and the link was down. + */ + clear_bit(IDPF_HR_RESET_IN_PROG, adapter->flags); + /* Start the statistics task now */ + queue_delayed_work(adapter->stats_wq, &adapter->stats_task, + msecs_to_jiffies(10 * (pdev->devfn & 0x07))); + + return; + +handle_err: + idpf_decfg_netdev(vport); +cfg_netdev_err: + idpf_vport_rel(vport); + adapter->vports[index] = NULL; +unwind_vports: + if (default_vport) { + for (index = 0; index < adapter->max_vports; index++) { + if (adapter->vports[index]) + idpf_vport_dealloc(adapter->vports[index]); + } + } + clear_bit(IDPF_HR_RESET_IN_PROG, adapter->flags); +} + +/** + * idpf_sriov_ena - Enable or change number of VFs + * @adapter: private data struct + * @num_vfs: number of VFs to allocate + */ +static int idpf_sriov_ena(struct idpf_adapter *adapter, int num_vfs) +{ + struct device *dev = &adapter->pdev->dev; + int err; + + err = idpf_send_set_sriov_vfs_msg(adapter, num_vfs); + if (err) { + dev_err(dev, "Failed to allocate VFs: %d\n", err); + + return err; + } + + err = pci_enable_sriov(adapter->pdev, num_vfs); + if (err) { + idpf_send_set_sriov_vfs_msg(adapter, 0); + dev_err(dev, "Failed to enable SR-IOV: %d\n", err); + + return err; + } + + adapter->num_vfs = num_vfs; + + return num_vfs; +} + +/** + * idpf_sriov_configure - Configure the requested VFs + * @pdev: pointer to a pci_dev structure + * @num_vfs: number of vfs to allocate + * + * Enable or change the number of VFs. Called when the user updates the number + * of VFs in sysfs. + **/ +int idpf_sriov_configure(struct pci_dev *pdev, int num_vfs) +{ + struct idpf_adapter *adapter = pci_get_drvdata(pdev); + + if (!idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_SRIOV)) { + dev_info(&pdev->dev, "SR-IOV is not supported on this device\n"); + + return -EOPNOTSUPP; + } + + if (num_vfs) + return idpf_sriov_ena(adapter, num_vfs); + + if (pci_vfs_assigned(pdev)) { + dev_warn(&pdev->dev, "Unable to free VFs because some are assigned to VMs\n"); + + return -EBUSY; + } + + pci_disable_sriov(adapter->pdev); + idpf_send_set_sriov_vfs_msg(adapter, 0); + adapter->num_vfs = 0; + + return 0; +} + +/** + * idpf_deinit_task - Device deinit routine + * @adapter: Driver specific private structure + * + * Extended remove logic which will be used for + * hard reset as well + */ +void idpf_deinit_task(struct idpf_adapter *adapter) +{ + unsigned int i; + + /* Wait until the init_task is done else this thread might release + * the resources first and the other thread might end up in a bad state + */ + cancel_delayed_work_sync(&adapter->init_task); + + if (!adapter->vports) + return; + + cancel_delayed_work_sync(&adapter->stats_task); + + for (i = 0; i < adapter->max_vports; i++) { + if (adapter->vports[i]) + idpf_vport_dealloc(adapter->vports[i]); + } +} + +/** + * idpf_check_reset_complete - check that reset is complete + * @hw: pointer to hw struct + * @reset_reg: struct with reset registers + * + * Returns 0 if device is ready to use, or -EBUSY if it's in reset. + **/ +static int idpf_check_reset_complete(struct idpf_hw *hw, + struct idpf_reset_reg *reset_reg) +{ + struct idpf_adapter *adapter = hw->back; + int i; + + for (i = 0; i < 2000; i++) { + u32 reg_val = readl(reset_reg->rstat); + + /* 0xFFFFFFFF might be read if other side hasn't cleared the + * register for us yet and 0xFFFFFFFF is not a valid value for + * the register, so treat that as invalid. + */ + if (reg_val != 0xFFFFFFFF && (reg_val & reset_reg->rstat_m)) + return 0; + + usleep_range(5000, 10000); + } + + dev_warn(&adapter->pdev->dev, "Device reset timeout!\n"); + /* Clear the reset flag unconditionally here since the reset + * technically isn't in progress anymore from the driver's perspective + */ + clear_bit(IDPF_HR_RESET_IN_PROG, adapter->flags); + + return -EBUSY; +} + +/** + * idpf_set_vport_state - Set the vport state to be after the reset + * @adapter: Driver specific private structure + */ +static void idpf_set_vport_state(struct idpf_adapter *adapter) +{ + u16 i; + + for (i = 0; i < adapter->max_vports; i++) { + struct idpf_netdev_priv *np; + + if (!adapter->netdevs[i]) + continue; + + np = netdev_priv(adapter->netdevs[i]); + if (np->state == __IDPF_VPORT_UP) + set_bit(IDPF_VPORT_UP_REQUESTED, + adapter->vport_config[i]->flags); + } +} + +/** + * idpf_init_hard_reset - Initiate a hardware reset + * @adapter: Driver specific private structure + * + * Deallocate the vports and all the resources associated with them and + * reallocate. Also reinitialize the mailbox. Return 0 on success, + * negative on failure. + */ +static int idpf_init_hard_reset(struct idpf_adapter *adapter) +{ + struct idpf_reg_ops *reg_ops = &adapter->dev_ops.reg_ops; + struct device *dev = &adapter->pdev->dev; + struct net_device *netdev; + int err; + u16 i; + + mutex_lock(&adapter->vport_ctrl_lock); + + dev_info(dev, "Device HW Reset initiated\n"); + + /* Avoid TX hangs on reset */ + for (i = 0; i < adapter->max_vports; i++) { + netdev = adapter->netdevs[i]; + if (!netdev) + continue; + + netif_carrier_off(netdev); + netif_tx_disable(netdev); + } + + /* Prepare for reset */ + if (test_and_clear_bit(IDPF_HR_DRV_LOAD, adapter->flags)) { + reg_ops->trigger_reset(adapter, IDPF_HR_DRV_LOAD); + } else if (test_and_clear_bit(IDPF_HR_FUNC_RESET, adapter->flags)) { + bool is_reset = idpf_is_reset_detected(adapter); + + idpf_set_vport_state(adapter); + idpf_vc_core_deinit(adapter); + if (!is_reset) + reg_ops->trigger_reset(adapter, IDPF_HR_FUNC_RESET); + idpf_deinit_dflt_mbx(adapter); + } else { + dev_err(dev, "Unhandled hard reset cause\n"); + err = -EBADRQC; + goto unlock_mutex; + } + + /* Wait for reset to complete */ + err = idpf_check_reset_complete(&adapter->hw, &adapter->reset_reg); + if (err) { + dev_err(dev, "The driver was unable to contact the device's firmware. Check that the FW is running. Driver state= 0x%x\n", + adapter->state); + goto unlock_mutex; + } + + /* Reset is complete and so start building the driver resources again */ + err = idpf_init_dflt_mbx(adapter); + if (err) { + dev_err(dev, "Failed to initialize default mailbox: %d\n", err); + goto unlock_mutex; + } + + /* Initialize the state machine, also allocate memory and request + * resources + */ + err = idpf_vc_core_init(adapter); + if (err) { + idpf_deinit_dflt_mbx(adapter); + goto unlock_mutex; + } + + /* Wait till all the vports are initialized to release the reset lock, + * else user space callbacks may access uninitialized vports + */ + while (test_bit(IDPF_HR_RESET_IN_PROG, adapter->flags)) + msleep(100); + +unlock_mutex: + mutex_unlock(&adapter->vport_ctrl_lock); + + return err; +} + +/** + * idpf_vc_event_task - Handle virtchannel event logic + * @work: work queue struct + */ +void idpf_vc_event_task(struct work_struct *work) +{ + struct idpf_adapter *adapter; + + adapter = container_of(work, struct idpf_adapter, vc_event_task.work); + + if (test_bit(IDPF_REMOVE_IN_PROG, adapter->flags)) + return; + + if (test_bit(IDPF_HR_FUNC_RESET, adapter->flags) || + test_bit(IDPF_HR_DRV_LOAD, adapter->flags)) { + set_bit(IDPF_HR_RESET_IN_PROG, adapter->flags); + idpf_init_hard_reset(adapter); + } +} + +/** + * idpf_initiate_soft_reset - Initiate a software reset + * @vport: virtual port data struct + * @reset_cause: reason for the soft reset + * + * Soft reset only reallocs vport queue resources. Returns 0 on success, + * negative on failure. + */ +int idpf_initiate_soft_reset(struct idpf_vport *vport, + enum idpf_vport_reset_cause reset_cause) +{ + struct idpf_netdev_priv *np = netdev_priv(vport->netdev); + enum idpf_vport_state current_state = np->state; + struct idpf_adapter *adapter = vport->adapter; + struct idpf_vport *new_vport; + int err, i; + + /* If the system is low on memory, we can end up in bad state if we + * free all the memory for queue resources and try to allocate them + * again. Instead, we can pre-allocate the new resources before doing + * anything and bailing if the alloc fails. + * + * Make a clone of the existing vport to mimic its current + * configuration, then modify the new structure with any requested + * changes. Once the allocation of the new resources is done, stop the + * existing vport and copy the configuration to the main vport. If an + * error occurred, the existing vport will be untouched. + * + */ + new_vport = kzalloc(sizeof(*vport), GFP_KERNEL); + if (!new_vport) + return -ENOMEM; + + /* This purposely avoids copying the end of the struct because it + * contains wait_queues and mutexes and other stuff we don't want to + * mess with. Nothing below should use those variables from new_vport + * and should instead always refer to them in vport if they need to. + */ + memcpy(new_vport, vport, offsetof(struct idpf_vport, vc_state)); + + /* Adjust resource parameters prior to reallocating resources */ + switch (reset_cause) { + case IDPF_SR_Q_CHANGE: + err = idpf_vport_adjust_qs(new_vport); + if (err) + goto free_vport; + break; + case IDPF_SR_Q_DESC_CHANGE: + /* Update queue parameters before allocating resources */ + idpf_vport_calc_num_q_desc(new_vport); + break; + case IDPF_SR_MTU_CHANGE: + case IDPF_SR_RSC_CHANGE: + break; + default: + dev_err(&adapter->pdev->dev, "Unhandled soft reset cause\n"); + err = -EINVAL; + goto free_vport; + } + + err = idpf_vport_queues_alloc(new_vport); + if (err) + goto free_vport; + if (current_state <= __IDPF_VPORT_DOWN) { + idpf_send_delete_queues_msg(vport); + } else { + set_bit(IDPF_VPORT_DEL_QUEUES, vport->flags); + idpf_vport_stop(vport); + } + + idpf_deinit_rss(vport); + /* We're passing in vport here because we need its wait_queue + * to send a message and it should be getting all the vport + * config data out of the adapter but we need to be careful not + * to add code to add_queues to change the vport config within + * vport itself as it will be wiped with a memcpy later. + */ + err = idpf_send_add_queues_msg(vport, new_vport->num_txq, + new_vport->num_complq, + new_vport->num_rxq, + new_vport->num_bufq); + if (err) + goto err_reset; + + /* Same comment as above regarding avoiding copying the wait_queues and + * mutexes applies here. We do not want to mess with those if possible. + */ + memcpy(vport, new_vport, offsetof(struct idpf_vport, vc_state)); + + /* Since idpf_vport_queues_alloc was called with new_port, the queue + * back pointers are currently pointing to the local new_vport. Reset + * the backpointers to the original vport here + */ + for (i = 0; i < vport->num_txq_grp; i++) { + struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i]; + int j; + + tx_qgrp->vport = vport; + for (j = 0; j < tx_qgrp->num_txq; j++) + tx_qgrp->txqs[j]->vport = vport; + + if (idpf_is_queue_model_split(vport->txq_model)) + tx_qgrp->complq->vport = vport; + } + + for (i = 0; i < vport->num_rxq_grp; i++) { + struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i]; + struct idpf_queue *q; + u16 num_rxq; + int j; + + rx_qgrp->vport = vport; + for (j = 0; j < vport->num_bufqs_per_qgrp; j++) + rx_qgrp->splitq.bufq_sets[j].bufq.vport = vport; + + if (idpf_is_queue_model_split(vport->rxq_model)) + num_rxq = rx_qgrp->splitq.num_rxq_sets; + else + num_rxq = rx_qgrp->singleq.num_rxq; + + for (j = 0; j < num_rxq; j++) { + if (idpf_is_queue_model_split(vport->rxq_model)) + q = &rx_qgrp->splitq.rxq_sets[j]->rxq; + else + q = rx_qgrp->singleq.rxqs[j]; + q->vport = vport; + } + } + + if (reset_cause == IDPF_SR_Q_CHANGE) + idpf_vport_alloc_vec_indexes(vport); + + err = idpf_set_real_num_queues(vport); + if (err) + goto err_reset; + + if (current_state == __IDPF_VPORT_UP) + err = idpf_vport_open(vport, false); + + kfree(new_vport); + + return err; + +err_reset: + idpf_vport_queues_rel(new_vport); +free_vport: + kfree(new_vport); + + return err; +} + +/** + * idpf_addr_sync - Callback for dev_(mc|uc)_sync to add address + * @netdev: the netdevice + * @addr: address to add + * + * Called by __dev_(mc|uc)_sync when an address needs to be added. We call + * __dev_(uc|mc)_sync from .set_rx_mode. Kernel takes addr_list_lock spinlock + * meaning we cannot sleep in this context. Due to this, we have to add the + * filter and send the virtchnl message asynchronously without waiting for the + * response from the other side. We won't know whether or not the operation + * actually succeeded until we get the message back. Returns 0 on success, + * negative on failure. + */ +static int idpf_addr_sync(struct net_device *netdev, const u8 *addr) +{ + struct idpf_netdev_priv *np = netdev_priv(netdev); + + return idpf_add_mac_filter(np->vport, np, addr, true); +} + +/** + * idpf_addr_unsync - Callback for dev_(mc|uc)_sync to remove address + * @netdev: the netdevice + * @addr: address to add + * + * Called by __dev_(mc|uc)_sync when an address needs to be added. We call + * __dev_(uc|mc)_sync from .set_rx_mode. Kernel takes addr_list_lock spinlock + * meaning we cannot sleep in this context. Due to this we have to delete the + * filter and send the virtchnl message asynchronously without waiting for the + * return from the other side. We won't know whether or not the operation + * actually succeeded until we get the message back. Returns 0 on success, + * negative on failure. + */ +static int idpf_addr_unsync(struct net_device *netdev, const u8 *addr) +{ + struct idpf_netdev_priv *np = netdev_priv(netdev); + + /* Under some circumstances, we might receive a request to delete + * our own device address from our uc list. Because we store the + * device address in the VSI's MAC filter list, we need to ignore + * such requests and not delete our device address from this list. + */ + if (ether_addr_equal(addr, netdev->dev_addr)) + return 0; + + idpf_del_mac_filter(np->vport, np, addr, true); + + return 0; +} + +/** + * idpf_set_rx_mode - NDO callback to set the netdev filters + * @netdev: network interface device structure + * + * Stack takes addr_list_lock spinlock before calling our .set_rx_mode. We + * cannot sleep in this context. + */ +static void idpf_set_rx_mode(struct net_device *netdev) +{ + struct idpf_netdev_priv *np = netdev_priv(netdev); + struct idpf_vport_user_config_data *config_data; + struct idpf_adapter *adapter; + bool changed = false; + struct device *dev; + int err; + + adapter = np->adapter; + dev = &adapter->pdev->dev; + + if (idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_MACFILTER)) { + __dev_uc_sync(netdev, idpf_addr_sync, idpf_addr_unsync); + __dev_mc_sync(netdev, idpf_addr_sync, idpf_addr_unsync); + } + + if (!idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_PROMISC)) + return; + + config_data = &adapter->vport_config[np->vport_idx]->user_config; + /* IFF_PROMISC enables both unicast and multicast promiscuous, + * while IFF_ALLMULTI only enables multicast such that: + * + * promisc + allmulti = unicast | multicast + * promisc + !allmulti = unicast | multicast + * !promisc + allmulti = multicast + */ + if ((netdev->flags & IFF_PROMISC) && + !test_and_set_bit(__IDPF_PROMISC_UC, config_data->user_flags)) { + changed = true; + dev_info(&adapter->pdev->dev, "Entering promiscuous mode\n"); + if (!test_and_set_bit(__IDPF_PROMISC_MC, adapter->flags)) + dev_info(dev, "Entering multicast promiscuous mode\n"); + } + + if (!(netdev->flags & IFF_PROMISC) && + test_and_clear_bit(__IDPF_PROMISC_UC, config_data->user_flags)) { + changed = true; + dev_info(dev, "Leaving promiscuous mode\n"); + } + + if (netdev->flags & IFF_ALLMULTI && + !test_and_set_bit(__IDPF_PROMISC_MC, config_data->user_flags)) { + changed = true; + dev_info(dev, "Entering multicast promiscuous mode\n"); + } + + if (!(netdev->flags & (IFF_ALLMULTI | IFF_PROMISC)) && + test_and_clear_bit(__IDPF_PROMISC_MC, config_data->user_flags)) { + changed = true; + dev_info(dev, "Leaving multicast promiscuous mode\n"); + } + + if (!changed) + return; + + err = idpf_set_promiscuous(adapter, config_data, np->vport_id); + if (err) + dev_err(dev, "Failed to set promiscuous mode: %d\n", err); +} + +/** + * idpf_vport_manage_rss_lut - disable/enable RSS + * @vport: the vport being changed + * + * In the event of disable request for RSS, this function will zero out RSS + * LUT, while in the event of enable request for RSS, it will reconfigure RSS + * LUT with the default LUT configuration. + */ +static int idpf_vport_manage_rss_lut(struct idpf_vport *vport) +{ + bool ena = idpf_is_feature_ena(vport, NETIF_F_RXHASH); + struct idpf_rss_data *rss_data; + u16 idx = vport->idx; + int lut_size; + + rss_data = &vport->adapter->vport_config[idx]->user_config.rss_data; + lut_size = rss_data->rss_lut_size * sizeof(u32); + + if (ena) { + /* This will contain the default or user configured LUT */ + memcpy(rss_data->rss_lut, rss_data->cached_lut, lut_size); + } else { + /* Save a copy of the current LUT to be restored later if + * requested. + */ + memcpy(rss_data->cached_lut, rss_data->rss_lut, lut_size); + + /* Zero out the current LUT to disable */ + memset(rss_data->rss_lut, 0, lut_size); + } + + return idpf_config_rss(vport); +} + +/** + * idpf_set_features - set the netdev feature flags + * @netdev: ptr to the netdev being adjusted + * @features: the feature set that the stack is suggesting + */ +static int idpf_set_features(struct net_device *netdev, + netdev_features_t features) +{ + netdev_features_t changed = netdev->features ^ features; + struct idpf_adapter *adapter; + struct idpf_vport *vport; + int err = 0; + + idpf_vport_ctrl_lock(netdev); + vport = idpf_netdev_to_vport(netdev); + + adapter = vport->adapter; + + if (idpf_is_reset_in_prog(adapter)) { + dev_err(&adapter->pdev->dev, "Device is resetting, changing netdev features temporarily unavailable.\n"); + err = -EBUSY; + goto unlock_mutex; + } + + if (changed & NETIF_F_RXHASH) { + netdev->features ^= NETIF_F_RXHASH; + err = idpf_vport_manage_rss_lut(vport); + if (err) + goto unlock_mutex; + } + + if (changed & NETIF_F_GRO_HW) { + netdev->features ^= NETIF_F_GRO_HW; + err = idpf_initiate_soft_reset(vport, IDPF_SR_RSC_CHANGE); + if (err) + goto unlock_mutex; + } + + if (changed & NETIF_F_LOOPBACK) { + netdev->features ^= NETIF_F_LOOPBACK; + err = idpf_send_ena_dis_loopback_msg(vport); + } + +unlock_mutex: + idpf_vport_ctrl_unlock(netdev); + + return err; +} + +/** + * idpf_open - Called when a network interface becomes active + * @netdev: network interface device structure + * + * The open entry point is called when a network interface is made + * active by the system (IFF_UP). At this point all resources needed + * for transmit and receive operations are allocated, the interrupt + * handler is registered with the OS, the netdev watchdog is enabled, + * and the stack is notified that the interface is ready. + * + * Returns 0 on success, negative value on failure + */ +static int idpf_open(struct net_device *netdev) +{ + struct idpf_vport *vport; + int err; + + idpf_vport_ctrl_lock(netdev); + vport = idpf_netdev_to_vport(netdev); + + err = idpf_vport_open(vport, true); + + idpf_vport_ctrl_unlock(netdev); + + return err; +} + +/** + * idpf_change_mtu - NDO callback to change the MTU + * @netdev: network interface device structure + * @new_mtu: new value for maximum frame size + * + * Returns 0 on success, negative on failure + */ +static int idpf_change_mtu(struct net_device *netdev, int new_mtu) +{ + struct idpf_vport *vport; + int err; + + idpf_vport_ctrl_lock(netdev); + vport = idpf_netdev_to_vport(netdev); + + netdev->mtu = new_mtu; + + err = idpf_initiate_soft_reset(vport, IDPF_SR_MTU_CHANGE); + + idpf_vport_ctrl_unlock(netdev); + + return err; +} + +/** + * idpf_features_check - Validate packet conforms to limits + * @skb: skb buffer + * @netdev: This port's netdev + * @features: Offload features that the stack believes apply + */ +static netdev_features_t idpf_features_check(struct sk_buff *skb, + struct net_device *netdev, + netdev_features_t features) +{ + struct idpf_vport *vport = idpf_netdev_to_vport(netdev); + struct idpf_adapter *adapter = vport->adapter; + size_t len; + + /* No point in doing any of this if neither checksum nor GSO are + * being requested for this frame. We can rule out both by just + * checking for CHECKSUM_PARTIAL + */ + if (skb->ip_summed != CHECKSUM_PARTIAL) + return features; + + /* We cannot support GSO if the MSS is going to be less than + * 88 bytes. If it is then we need to drop support for GSO. + */ + if (skb_is_gso(skb) && + (skb_shinfo(skb)->gso_size < IDPF_TX_TSO_MIN_MSS)) + features &= ~NETIF_F_GSO_MASK; + + /* Ensure MACLEN is <= 126 bytes (63 words) and not an odd size */ + len = skb_network_offset(skb); + if (unlikely(len & ~(126))) + goto unsupported; + + len = skb_network_header_len(skb); + if (unlikely(len > idpf_get_max_tx_hdr_size(adapter))) + goto unsupported; + + if (!skb->encapsulation) + return features; + + /* L4TUNLEN can support 127 words */ + len = skb_inner_network_header(skb) - skb_transport_header(skb); + if (unlikely(len & ~(127 * 2))) + goto unsupported; + + /* IPLEN can support at most 127 dwords */ + len = skb_inner_network_header_len(skb); + if (unlikely(len > idpf_get_max_tx_hdr_size(adapter))) + goto unsupported; + + /* No need to validate L4LEN as TCP is the only protocol with a + * a flexible value and we support all possible values supported + * by TCP, which is at most 15 dwords + */ + + return features; + +unsupported: + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); +} + +/** + * idpf_set_mac - NDO callback to set port mac address + * @netdev: network interface device structure + * @p: pointer to an address structure + * + * Returns 0 on success, negative on failure + **/ +static int idpf_set_mac(struct net_device *netdev, void *p) +{ + struct idpf_netdev_priv *np = netdev_priv(netdev); + struct idpf_vport_config *vport_config; + struct sockaddr *addr = p; + struct idpf_vport *vport; + int err = 0; + + idpf_vport_ctrl_lock(netdev); + vport = idpf_netdev_to_vport(netdev); + + if (!idpf_is_cap_ena(vport->adapter, IDPF_OTHER_CAPS, + VIRTCHNL2_CAP_MACFILTER)) { + dev_info(&vport->adapter->pdev->dev, "Setting MAC address is not supported\n"); + err = -EOPNOTSUPP; + goto unlock_mutex; + } + + if (!is_valid_ether_addr(addr->sa_data)) { + dev_info(&vport->adapter->pdev->dev, "Invalid MAC address: %pM\n", + addr->sa_data); + err = -EADDRNOTAVAIL; + goto unlock_mutex; + } + + if (ether_addr_equal(netdev->dev_addr, addr->sa_data)) + goto unlock_mutex; + + vport_config = vport->adapter->vport_config[vport->idx]; + err = idpf_add_mac_filter(vport, np, addr->sa_data, false); + if (err) { + __idpf_del_mac_filter(vport_config, addr->sa_data); + goto unlock_mutex; + } + + if (is_valid_ether_addr(vport->default_mac_addr)) + idpf_del_mac_filter(vport, np, vport->default_mac_addr, false); + + ether_addr_copy(vport->default_mac_addr, addr->sa_data); + eth_hw_addr_set(netdev, addr->sa_data); + +unlock_mutex: + idpf_vport_ctrl_unlock(netdev); + + return err; +} + +/** + * idpf_alloc_dma_mem - Allocate dma memory + * @hw: pointer to hw struct + * @mem: pointer to dma_mem struct + * @size: size of the memory to allocate + */ +void *idpf_alloc_dma_mem(struct idpf_hw *hw, struct idpf_dma_mem *mem, u64 size) +{ + struct idpf_adapter *adapter = hw->back; + size_t sz = ALIGN(size, 4096); + + mem->va = dma_alloc_coherent(&adapter->pdev->dev, sz, + &mem->pa, GFP_KERNEL); + mem->size = sz; + + return mem->va; +} + +/** + * idpf_free_dma_mem - Free the allocated dma memory + * @hw: pointer to hw struct + * @mem: pointer to dma_mem struct + */ +void idpf_free_dma_mem(struct idpf_hw *hw, struct idpf_dma_mem *mem) +{ + struct idpf_adapter *adapter = hw->back; + + dma_free_coherent(&adapter->pdev->dev, mem->size, + mem->va, mem->pa); + mem->size = 0; + mem->va = NULL; + mem->pa = 0; +} + +static const struct net_device_ops idpf_netdev_ops_splitq = { + .ndo_open = idpf_open, + .ndo_stop = idpf_stop, + .ndo_start_xmit = idpf_tx_splitq_start, + .ndo_features_check = idpf_features_check, + .ndo_set_rx_mode = idpf_set_rx_mode, + .ndo_validate_addr = eth_validate_addr, + .ndo_set_mac_address = idpf_set_mac, + .ndo_change_mtu = idpf_change_mtu, + .ndo_get_stats64 = idpf_get_stats64, + .ndo_set_features = idpf_set_features, + .ndo_tx_timeout = idpf_tx_timeout, +}; + +static const struct net_device_ops idpf_netdev_ops_singleq = { + .ndo_open = idpf_open, + .ndo_stop = idpf_stop, + .ndo_start_xmit = idpf_tx_singleq_start, + .ndo_features_check = idpf_features_check, + .ndo_set_rx_mode = idpf_set_rx_mode, + .ndo_validate_addr = eth_validate_addr, + .ndo_set_mac_address = idpf_set_mac, + .ndo_change_mtu = idpf_change_mtu, + .ndo_get_stats64 = idpf_get_stats64, + .ndo_set_features = idpf_set_features, + .ndo_tx_timeout = idpf_tx_timeout, +}; diff --git a/drivers/net/ethernet/intel/idpf/idpf_main.c b/drivers/net/ethernet/intel/idpf/idpf_main.c new file mode 100644 index 000000000000..e1febc74cefd --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/idpf_main.c @@ -0,0 +1,279 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2023 Intel Corporation */ + +#include "idpf.h" +#include "idpf_devids.h" + +#define DRV_SUMMARY "Intel(R) Infrastructure Data Path Function Linux Driver" + +MODULE_DESCRIPTION(DRV_SUMMARY); +MODULE_LICENSE("GPL"); + +/** + * idpf_remove - Device removal routine + * @pdev: PCI device information struct + */ +static void idpf_remove(struct pci_dev *pdev) +{ + struct idpf_adapter *adapter = pci_get_drvdata(pdev); + int i; + + set_bit(IDPF_REMOVE_IN_PROG, adapter->flags); + + /* Wait until vc_event_task is done to consider if any hard reset is + * in progress else we may go ahead and release the resources but the + * thread doing the hard reset might continue the init path and + * end up in bad state. + */ + cancel_delayed_work_sync(&adapter->vc_event_task); + if (adapter->num_vfs) + idpf_sriov_configure(pdev, 0); + + idpf_vc_core_deinit(adapter); + /* Be a good citizen and leave the device clean on exit */ + adapter->dev_ops.reg_ops.trigger_reset(adapter, IDPF_HR_FUNC_RESET); + idpf_deinit_dflt_mbx(adapter); + + if (!adapter->netdevs) + goto destroy_wqs; + + /* There are some cases where it's possible to still have netdevs + * registered with the stack at this point, e.g. if the driver detected + * a HW reset and rmmod is called before it fully recovers. Unregister + * any stale netdevs here. + */ + for (i = 0; i < adapter->max_vports; i++) { + if (!adapter->netdevs[i]) + continue; + if (adapter->netdevs[i]->reg_state != NETREG_UNINITIALIZED) + unregister_netdev(adapter->netdevs[i]); + free_netdev(adapter->netdevs[i]); + adapter->netdevs[i] = NULL; + } + +destroy_wqs: + destroy_workqueue(adapter->init_wq); + destroy_workqueue(adapter->serv_wq); + destroy_workqueue(adapter->mbx_wq); + destroy_workqueue(adapter->stats_wq); + destroy_workqueue(adapter->vc_event_wq); + + for (i = 0; i < adapter->max_vports; i++) { + kfree(adapter->vport_config[i]); + adapter->vport_config[i] = NULL; + } + kfree(adapter->vport_config); + adapter->vport_config = NULL; + kfree(adapter->netdevs); + adapter->netdevs = NULL; + + mutex_destroy(&adapter->vport_ctrl_lock); + mutex_destroy(&adapter->vector_lock); + mutex_destroy(&adapter->queue_lock); + mutex_destroy(&adapter->vc_buf_lock); + + pci_set_drvdata(pdev, NULL); + kfree(adapter); +} + +/** + * idpf_shutdown - PCI callback for shutting down device + * @pdev: PCI device information struct + */ +static void idpf_shutdown(struct pci_dev *pdev) +{ + idpf_remove(pdev); + + if (system_state == SYSTEM_POWER_OFF) + pci_set_power_state(pdev, PCI_D3hot); +} + +/** + * idpf_cfg_hw - Initialize HW struct + * @adapter: adapter to setup hw struct for + * + * Returns 0 on success, negative on failure + */ +static int idpf_cfg_hw(struct idpf_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + struct idpf_hw *hw = &adapter->hw; + + hw->hw_addr = pcim_iomap_table(pdev)[0]; + if (!hw->hw_addr) { + pci_err(pdev, "failed to allocate PCI iomap table\n"); + + return -ENOMEM; + } + + hw->back = adapter; + + return 0; +} + +/** + * idpf_probe - Device initialization routine + * @pdev: PCI device information struct + * @ent: entry in idpf_pci_tbl + * + * Returns 0 on success, negative on failure + */ +static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) +{ + struct device *dev = &pdev->dev; + struct idpf_adapter *adapter; + int err; + + adapter = kzalloc(sizeof(*adapter), GFP_KERNEL); + if (!adapter) + return -ENOMEM; + + adapter->req_tx_splitq = true; + adapter->req_rx_splitq = true; + + switch (ent->device) { + case IDPF_DEV_ID_PF: + idpf_dev_ops_init(adapter); + break; + case IDPF_DEV_ID_VF: + idpf_vf_dev_ops_init(adapter); + adapter->crc_enable = true; + break; + default: + err = -ENODEV; + dev_err(&pdev->dev, "Unexpected dev ID 0x%x in idpf probe\n", + ent->device); + goto err_free; + } + + adapter->pdev = pdev; + err = pcim_enable_device(pdev); + if (err) + goto err_free; + + err = pcim_iomap_regions(pdev, BIT(0), pci_name(pdev)); + if (err) { + pci_err(pdev, "pcim_iomap_regions failed %pe\n", ERR_PTR(err)); + + goto err_free; + } + + /* set up for high or low dma */ + err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); + if (err) { + pci_err(pdev, "DMA configuration failed: %pe\n", ERR_PTR(err)); + + goto err_free; + } + + pci_set_master(pdev); + pci_set_drvdata(pdev, adapter); + + adapter->init_wq = alloc_workqueue("%s-%s-init", 0, 0, + dev_driver_string(dev), + dev_name(dev)); + if (!adapter->init_wq) { + dev_err(dev, "Failed to allocate init workqueue\n"); + err = -ENOMEM; + goto err_free; + } + + adapter->serv_wq = alloc_workqueue("%s-%s-service", 0, 0, + dev_driver_string(dev), + dev_name(dev)); + if (!adapter->serv_wq) { + dev_err(dev, "Failed to allocate service workqueue\n"); + err = -ENOMEM; + goto err_serv_wq_alloc; + } + + adapter->mbx_wq = alloc_workqueue("%s-%s-mbx", 0, 0, + dev_driver_string(dev), + dev_name(dev)); + if (!adapter->mbx_wq) { + dev_err(dev, "Failed to allocate mailbox workqueue\n"); + err = -ENOMEM; + goto err_mbx_wq_alloc; + } + + adapter->stats_wq = alloc_workqueue("%s-%s-stats", 0, 0, + dev_driver_string(dev), + dev_name(dev)); + if (!adapter->stats_wq) { + dev_err(dev, "Failed to allocate workqueue\n"); + err = -ENOMEM; + goto err_stats_wq_alloc; + } + + adapter->vc_event_wq = alloc_workqueue("%s-%s-vc_event", 0, 0, + dev_driver_string(dev), + dev_name(dev)); + if (!adapter->vc_event_wq) { + dev_err(dev, "Failed to allocate virtchnl event workqueue\n"); + err = -ENOMEM; + goto err_vc_event_wq_alloc; + } + + /* setup msglvl */ + adapter->msg_enable = netif_msg_init(-1, IDPF_AVAIL_NETIF_M); + + err = idpf_cfg_hw(adapter); + if (err) { + dev_err(dev, "Failed to configure HW structure for adapter: %d\n", + err); + goto err_cfg_hw; + } + + mutex_init(&adapter->vport_ctrl_lock); + mutex_init(&adapter->vector_lock); + mutex_init(&adapter->queue_lock); + mutex_init(&adapter->vc_buf_lock); + + init_waitqueue_head(&adapter->vchnl_wq); + + INIT_DELAYED_WORK(&adapter->init_task, idpf_init_task); + INIT_DELAYED_WORK(&adapter->serv_task, idpf_service_task); + INIT_DELAYED_WORK(&adapter->mbx_task, idpf_mbx_task); + INIT_DELAYED_WORK(&adapter->stats_task, idpf_statistics_task); + INIT_DELAYED_WORK(&adapter->vc_event_task, idpf_vc_event_task); + + adapter->dev_ops.reg_ops.reset_reg_init(adapter); + set_bit(IDPF_HR_DRV_LOAD, adapter->flags); + queue_delayed_work(adapter->vc_event_wq, &adapter->vc_event_task, + msecs_to_jiffies(10 * (pdev->devfn & 0x07))); + + return 0; + +err_cfg_hw: + destroy_workqueue(adapter->vc_event_wq); +err_vc_event_wq_alloc: + destroy_workqueue(adapter->stats_wq); +err_stats_wq_alloc: + destroy_workqueue(adapter->mbx_wq); +err_mbx_wq_alloc: + destroy_workqueue(adapter->serv_wq); +err_serv_wq_alloc: + destroy_workqueue(adapter->init_wq); +err_free: + kfree(adapter); + return err; +} + +/* idpf_pci_tbl - PCI Dev idpf ID Table + */ +static const struct pci_device_id idpf_pci_tbl[] = { + { PCI_VDEVICE(INTEL, IDPF_DEV_ID_PF)}, + { PCI_VDEVICE(INTEL, IDPF_DEV_ID_VF)}, + { /* Sentinel */ } +}; +MODULE_DEVICE_TABLE(pci, idpf_pci_tbl); + +static struct pci_driver idpf_driver = { + .name = KBUILD_MODNAME, + .id_table = idpf_pci_tbl, + .probe = idpf_probe, + .sriov_configure = idpf_sriov_configure, + .remove = idpf_remove, + .shutdown = idpf_shutdown, +}; +module_pci_driver(idpf_driver); diff --git a/drivers/net/ethernet/intel/idpf/idpf_mem.h b/drivers/net/ethernet/intel/idpf/idpf_mem.h new file mode 100644 index 000000000000..b21a04fccf0f --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/idpf_mem.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2023 Intel Corporation */ + +#ifndef _IDPF_MEM_H_ +#define _IDPF_MEM_H_ + +#include <linux/io.h> + +struct idpf_dma_mem { + void *va; + dma_addr_t pa; + size_t size; +}; + +#define wr32(a, reg, value) writel((value), ((a)->hw_addr + (reg))) +#define rd32(a, reg) readl((a)->hw_addr + (reg)) +#define wr64(a, reg, value) writeq((value), ((a)->hw_addr + (reg))) +#define rd64(a, reg) readq((a)->hw_addr + (reg)) + +#endif /* _IDPF_MEM_H_ */ diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c new file mode 100644 index 000000000000..81288a17da2a --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c @@ -0,0 +1,1183 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2023 Intel Corporation */ + +#include "idpf.h" + +/** + * idpf_tx_singleq_csum - Enable tx checksum offloads + * @skb: pointer to skb + * @off: pointer to struct that holds offload parameters + * + * Returns 0 or error (negative) if checksum offload cannot be executed, 1 + * otherwise. + */ +static int idpf_tx_singleq_csum(struct sk_buff *skb, + struct idpf_tx_offload_params *off) +{ + u32 l4_len, l3_len, l2_len; + union { + struct iphdr *v4; + struct ipv6hdr *v6; + unsigned char *hdr; + } ip; + union { + struct tcphdr *tcp; + unsigned char *hdr; + } l4; + u32 offset, cmd = 0; + u8 l4_proto = 0; + __be16 frag_off; + bool is_tso; + + if (skb->ip_summed != CHECKSUM_PARTIAL) + return 0; + + ip.hdr = skb_network_header(skb); + l4.hdr = skb_transport_header(skb); + + /* compute outer L2 header size */ + l2_len = ip.hdr - skb->data; + offset = FIELD_PREP(0x3F << IDPF_TX_DESC_LEN_MACLEN_S, l2_len / 2); + is_tso = !!(off->tx_flags & IDPF_TX_FLAGS_TSO); + if (skb->encapsulation) { + u32 tunnel = 0; + + /* define outer network header type */ + if (off->tx_flags & IDPF_TX_FLAGS_IPV4) { + /* The stack computes the IP header already, the only + * time we need the hardware to recompute it is in the + * case of TSO. + */ + tunnel |= is_tso ? + IDPF_TX_CTX_EXT_IP_IPV4 : + IDPF_TX_CTX_EXT_IP_IPV4_NO_CSUM; + + l4_proto = ip.v4->protocol; + } else if (off->tx_flags & IDPF_TX_FLAGS_IPV6) { + tunnel |= IDPF_TX_CTX_EXT_IP_IPV6; + + l4_proto = ip.v6->nexthdr; + if (ipv6_ext_hdr(l4_proto)) + ipv6_skip_exthdr(skb, skb_network_offset(skb) + + sizeof(*ip.v6), + &l4_proto, &frag_off); + } + + /* define outer transport */ + switch (l4_proto) { + case IPPROTO_UDP: + tunnel |= IDPF_TXD_CTX_UDP_TUNNELING; + break; + case IPPROTO_GRE: + tunnel |= IDPF_TXD_CTX_GRE_TUNNELING; + break; + case IPPROTO_IPIP: + case IPPROTO_IPV6: + l4.hdr = skb_inner_network_header(skb); + break; + default: + if (is_tso) + return -1; + + skb_checksum_help(skb); + + return 0; + } + off->tx_flags |= IDPF_TX_FLAGS_TUNNEL; + + /* compute outer L3 header size */ + tunnel |= FIELD_PREP(IDPF_TXD_CTX_QW0_TUNN_EXT_IPLEN_M, + (l4.hdr - ip.hdr) / 4); + + /* switch IP header pointer from outer to inner header */ + ip.hdr = skb_inner_network_header(skb); + + /* compute tunnel header size */ + tunnel |= FIELD_PREP(IDPF_TXD_CTX_QW0_TUNN_NATLEN_M, + (ip.hdr - l4.hdr) / 2); + + /* indicate if we need to offload outer UDP header */ + if (is_tso && + !(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) && + (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM)) + tunnel |= IDPF_TXD_CTX_QW0_TUNN_L4T_CS_M; + + /* record tunnel offload values */ + off->cd_tunneling |= tunnel; + + /* switch L4 header pointer from outer to inner */ + l4.hdr = skb_inner_transport_header(skb); + l4_proto = 0; + + /* reset type as we transition from outer to inner headers */ + off->tx_flags &= ~(IDPF_TX_FLAGS_IPV4 | IDPF_TX_FLAGS_IPV6); + if (ip.v4->version == 4) + off->tx_flags |= IDPF_TX_FLAGS_IPV4; + if (ip.v6->version == 6) + off->tx_flags |= IDPF_TX_FLAGS_IPV6; + } + + /* Enable IP checksum offloads */ + if (off->tx_flags & IDPF_TX_FLAGS_IPV4) { + l4_proto = ip.v4->protocol; + /* See comment above regarding need for HW to recompute IP + * header checksum in the case of TSO. + */ + if (is_tso) + cmd |= IDPF_TX_DESC_CMD_IIPT_IPV4_CSUM; + else + cmd |= IDPF_TX_DESC_CMD_IIPT_IPV4; + + } else if (off->tx_flags & IDPF_TX_FLAGS_IPV6) { + cmd |= IDPF_TX_DESC_CMD_IIPT_IPV6; + l4_proto = ip.v6->nexthdr; + if (ipv6_ext_hdr(l4_proto)) + ipv6_skip_exthdr(skb, skb_network_offset(skb) + + sizeof(*ip.v6), &l4_proto, + &frag_off); + } else { + return -1; + } + + /* compute inner L3 header size */ + l3_len = l4.hdr - ip.hdr; + offset |= (l3_len / 4) << IDPF_TX_DESC_LEN_IPLEN_S; + + /* Enable L4 checksum offloads */ + switch (l4_proto) { + case IPPROTO_TCP: + /* enable checksum offloads */ + cmd |= IDPF_TX_DESC_CMD_L4T_EOFT_TCP; + l4_len = l4.tcp->doff; + break; + case IPPROTO_UDP: + /* enable UDP checksum offload */ + cmd |= IDPF_TX_DESC_CMD_L4T_EOFT_UDP; + l4_len = sizeof(struct udphdr) >> 2; + break; + case IPPROTO_SCTP: + /* enable SCTP checksum offload */ + cmd |= IDPF_TX_DESC_CMD_L4T_EOFT_SCTP; + l4_len = sizeof(struct sctphdr) >> 2; + break; + default: + if (is_tso) + return -1; + + skb_checksum_help(skb); + + return 0; + } + + offset |= l4_len << IDPF_TX_DESC_LEN_L4_LEN_S; + off->td_cmd |= cmd; + off->hdr_offsets |= offset; + + return 1; +} + +/** + * idpf_tx_singleq_map - Build the Tx base descriptor + * @tx_q: queue to send buffer on + * @first: first buffer info buffer to use + * @offloads: pointer to struct that holds offload parameters + * + * This function loops over the skb data pointed to by *first + * and gets a physical address for each memory location and programs + * it and the length into the transmit base mode descriptor. + */ +static void idpf_tx_singleq_map(struct idpf_queue *tx_q, + struct idpf_tx_buf *first, + struct idpf_tx_offload_params *offloads) +{ + u32 offsets = offloads->hdr_offsets; + struct idpf_tx_buf *tx_buf = first; + struct idpf_base_tx_desc *tx_desc; + struct sk_buff *skb = first->skb; + u64 td_cmd = offloads->td_cmd; + unsigned int data_len, size; + u16 i = tx_q->next_to_use; + struct netdev_queue *nq; + skb_frag_t *frag; + dma_addr_t dma; + u64 td_tag = 0; + + data_len = skb->data_len; + size = skb_headlen(skb); + + tx_desc = IDPF_BASE_TX_DESC(tx_q, i); + + dma = dma_map_single(tx_q->dev, skb->data, size, DMA_TO_DEVICE); + + /* write each descriptor with CRC bit */ + if (tx_q->vport->crc_enable) + td_cmd |= IDPF_TX_DESC_CMD_ICRC; + + for (frag = &skb_shinfo(skb)->frags[0];; frag++) { + unsigned int max_data = IDPF_TX_MAX_DESC_DATA_ALIGNED; + + if (dma_mapping_error(tx_q->dev, dma)) + return idpf_tx_dma_map_error(tx_q, skb, first, i); + + /* record length, and DMA address */ + dma_unmap_len_set(tx_buf, len, size); + dma_unmap_addr_set(tx_buf, dma, dma); + + /* align size to end of page */ + max_data += -dma & (IDPF_TX_MAX_READ_REQ_SIZE - 1); + tx_desc->buf_addr = cpu_to_le64(dma); + + /* account for data chunks larger than the hardware + * can handle + */ + while (unlikely(size > IDPF_TX_MAX_DESC_DATA)) { + tx_desc->qw1 = idpf_tx_singleq_build_ctob(td_cmd, + offsets, + max_data, + td_tag); + tx_desc++; + i++; + + if (i == tx_q->desc_count) { + tx_desc = IDPF_BASE_TX_DESC(tx_q, 0); + i = 0; + } + + dma += max_data; + size -= max_data; + + max_data = IDPF_TX_MAX_DESC_DATA_ALIGNED; + tx_desc->buf_addr = cpu_to_le64(dma); + } + + if (!data_len) + break; + + tx_desc->qw1 = idpf_tx_singleq_build_ctob(td_cmd, offsets, + size, td_tag); + tx_desc++; + i++; + + if (i == tx_q->desc_count) { + tx_desc = IDPF_BASE_TX_DESC(tx_q, 0); + i = 0; + } + + size = skb_frag_size(frag); + data_len -= size; + + dma = skb_frag_dma_map(tx_q->dev, frag, 0, size, + DMA_TO_DEVICE); + + tx_buf = &tx_q->tx_buf[i]; + } + + skb_tx_timestamp(first->skb); + + /* write last descriptor with RS and EOP bits */ + td_cmd |= (u64)(IDPF_TX_DESC_CMD_EOP | IDPF_TX_DESC_CMD_RS); + + tx_desc->qw1 = idpf_tx_singleq_build_ctob(td_cmd, offsets, + size, td_tag); + + IDPF_SINGLEQ_BUMP_RING_IDX(tx_q, i); + + /* set next_to_watch value indicating a packet is present */ + first->next_to_watch = tx_desc; + + nq = netdev_get_tx_queue(tx_q->vport->netdev, tx_q->idx); + netdev_tx_sent_queue(nq, first->bytecount); + + idpf_tx_buf_hw_update(tx_q, i, netdev_xmit_more()); +} + +/** + * idpf_tx_singleq_get_ctx_desc - grab next desc and update buffer ring + * @txq: queue to put context descriptor on + * + * Since the TX buffer rings mimics the descriptor ring, update the tx buffer + * ring entry to reflect that this index is a context descriptor + */ +static struct idpf_base_tx_ctx_desc * +idpf_tx_singleq_get_ctx_desc(struct idpf_queue *txq) +{ + struct idpf_base_tx_ctx_desc *ctx_desc; + int ntu = txq->next_to_use; + + memset(&txq->tx_buf[ntu], 0, sizeof(struct idpf_tx_buf)); + txq->tx_buf[ntu].ctx_entry = true; + + ctx_desc = IDPF_BASE_TX_CTX_DESC(txq, ntu); + + IDPF_SINGLEQ_BUMP_RING_IDX(txq, ntu); + txq->next_to_use = ntu; + + return ctx_desc; +} + +/** + * idpf_tx_singleq_build_ctx_desc - populate context descriptor + * @txq: queue to send buffer on + * @offload: offload parameter structure + **/ +static void idpf_tx_singleq_build_ctx_desc(struct idpf_queue *txq, + struct idpf_tx_offload_params *offload) +{ + struct idpf_base_tx_ctx_desc *desc = idpf_tx_singleq_get_ctx_desc(txq); + u64 qw1 = (u64)IDPF_TX_DESC_DTYPE_CTX; + + if (offload->tso_segs) { + qw1 |= IDPF_TX_CTX_DESC_TSO << IDPF_TXD_CTX_QW1_CMD_S; + qw1 |= ((u64)offload->tso_len << IDPF_TXD_CTX_QW1_TSO_LEN_S) & + IDPF_TXD_CTX_QW1_TSO_LEN_M; + qw1 |= ((u64)offload->mss << IDPF_TXD_CTX_QW1_MSS_S) & + IDPF_TXD_CTX_QW1_MSS_M; + + u64_stats_update_begin(&txq->stats_sync); + u64_stats_inc(&txq->q_stats.tx.lso_pkts); + u64_stats_update_end(&txq->stats_sync); + } + + desc->qw0.tunneling_params = cpu_to_le32(offload->cd_tunneling); + + desc->qw0.l2tag2 = 0; + desc->qw0.rsvd1 = 0; + desc->qw1 = cpu_to_le64(qw1); +} + +/** + * idpf_tx_singleq_frame - Sends buffer on Tx ring using base descriptors + * @skb: send buffer + * @tx_q: queue to send buffer on + * + * Returns NETDEV_TX_OK if sent, else an error code + */ +static netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb, + struct idpf_queue *tx_q) +{ + struct idpf_tx_offload_params offload = { }; + struct idpf_tx_buf *first; + unsigned int count; + __be16 protocol; + int csum, tso; + + count = idpf_tx_desc_count_required(tx_q, skb); + if (unlikely(!count)) + return idpf_tx_drop_skb(tx_q, skb); + + if (idpf_tx_maybe_stop_common(tx_q, + count + IDPF_TX_DESCS_PER_CACHE_LINE + + IDPF_TX_DESCS_FOR_CTX)) { + idpf_tx_buf_hw_update(tx_q, tx_q->next_to_use, false); + + return NETDEV_TX_BUSY; + } + + protocol = vlan_get_protocol(skb); + if (protocol == htons(ETH_P_IP)) + offload.tx_flags |= IDPF_TX_FLAGS_IPV4; + else if (protocol == htons(ETH_P_IPV6)) + offload.tx_flags |= IDPF_TX_FLAGS_IPV6; + + tso = idpf_tso(skb, &offload); + if (tso < 0) + goto out_drop; + + csum = idpf_tx_singleq_csum(skb, &offload); + if (csum < 0) + goto out_drop; + + if (tso || offload.cd_tunneling) + idpf_tx_singleq_build_ctx_desc(tx_q, &offload); + + /* record the location of the first descriptor for this packet */ + first = &tx_q->tx_buf[tx_q->next_to_use]; + first->skb = skb; + + if (tso) { + first->gso_segs = offload.tso_segs; + first->bytecount = skb->len + ((first->gso_segs - 1) * offload.tso_hdr_len); + } else { + first->bytecount = max_t(unsigned int, skb->len, ETH_ZLEN); + first->gso_segs = 1; + } + idpf_tx_singleq_map(tx_q, first, &offload); + + return NETDEV_TX_OK; + +out_drop: + return idpf_tx_drop_skb(tx_q, skb); +} + +/** + * idpf_tx_singleq_start - Selects the right Tx queue to send buffer + * @skb: send buffer + * @netdev: network interface device structure + * + * Returns NETDEV_TX_OK if sent, else an error code + */ +netdev_tx_t idpf_tx_singleq_start(struct sk_buff *skb, + struct net_device *netdev) +{ + struct idpf_vport *vport = idpf_netdev_to_vport(netdev); + struct idpf_queue *tx_q; + + tx_q = vport->txqs[skb_get_queue_mapping(skb)]; + + /* hardware can't handle really short frames, hardware padding works + * beyond this point + */ + if (skb_put_padto(skb, IDPF_TX_MIN_PKT_LEN)) { + idpf_tx_buf_hw_update(tx_q, tx_q->next_to_use, false); + + return NETDEV_TX_OK; + } + + return idpf_tx_singleq_frame(skb, tx_q); +} + +/** + * idpf_tx_singleq_clean - Reclaim resources from queue + * @tx_q: Tx queue to clean + * @napi_budget: Used to determine if we are in netpoll + * @cleaned: returns number of packets cleaned + * + */ +static bool idpf_tx_singleq_clean(struct idpf_queue *tx_q, int napi_budget, + int *cleaned) +{ + unsigned int budget = tx_q->vport->compln_clean_budget; + unsigned int total_bytes = 0, total_pkts = 0; + struct idpf_base_tx_desc *tx_desc; + s16 ntc = tx_q->next_to_clean; + struct idpf_netdev_priv *np; + struct idpf_tx_buf *tx_buf; + struct idpf_vport *vport; + struct netdev_queue *nq; + bool dont_wake; + + tx_desc = IDPF_BASE_TX_DESC(tx_q, ntc); + tx_buf = &tx_q->tx_buf[ntc]; + ntc -= tx_q->desc_count; + + do { + struct idpf_base_tx_desc *eop_desc; + + /* If this entry in the ring was used as a context descriptor, + * it's corresponding entry in the buffer ring will indicate as + * such. We can skip this descriptor since there is no buffer + * to clean. + */ + if (tx_buf->ctx_entry) { + /* Clear this flag here to avoid stale flag values when + * this buffer is used for actual data in the future. + * There are cases where the tx_buf struct / the flags + * field will not be cleared before being reused. + */ + tx_buf->ctx_entry = false; + goto fetch_next_txq_desc; + } + + /* if next_to_watch is not set then no work pending */ + eop_desc = (struct idpf_base_tx_desc *)tx_buf->next_to_watch; + if (!eop_desc) + break; + + /* prevent any other reads prior to eop_desc */ + smp_rmb(); + + /* if the descriptor isn't done, no work yet to do */ + if (!(eop_desc->qw1 & + cpu_to_le64(IDPF_TX_DESC_DTYPE_DESC_DONE))) + break; + + /* clear next_to_watch to prevent false hangs */ + tx_buf->next_to_watch = NULL; + + /* update the statistics for this packet */ + total_bytes += tx_buf->bytecount; + total_pkts += tx_buf->gso_segs; + + napi_consume_skb(tx_buf->skb, napi_budget); + + /* unmap skb header data */ + dma_unmap_single(tx_q->dev, + dma_unmap_addr(tx_buf, dma), + dma_unmap_len(tx_buf, len), + DMA_TO_DEVICE); + + /* clear tx_buf data */ + tx_buf->skb = NULL; + dma_unmap_len_set(tx_buf, len, 0); + + /* unmap remaining buffers */ + while (tx_desc != eop_desc) { + tx_buf++; + tx_desc++; + ntc++; + if (unlikely(!ntc)) { + ntc -= tx_q->desc_count; + tx_buf = tx_q->tx_buf; + tx_desc = IDPF_BASE_TX_DESC(tx_q, 0); + } + + /* unmap any remaining paged data */ + if (dma_unmap_len(tx_buf, len)) { + dma_unmap_page(tx_q->dev, + dma_unmap_addr(tx_buf, dma), + dma_unmap_len(tx_buf, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buf, len, 0); + } + } + + /* update budget only if we did something */ + budget--; + +fetch_next_txq_desc: + tx_buf++; + tx_desc++; + ntc++; + if (unlikely(!ntc)) { + ntc -= tx_q->desc_count; + tx_buf = tx_q->tx_buf; + tx_desc = IDPF_BASE_TX_DESC(tx_q, 0); + } + } while (likely(budget)); + + ntc += tx_q->desc_count; + tx_q->next_to_clean = ntc; + + *cleaned += total_pkts; + + u64_stats_update_begin(&tx_q->stats_sync); + u64_stats_add(&tx_q->q_stats.tx.packets, total_pkts); + u64_stats_add(&tx_q->q_stats.tx.bytes, total_bytes); + u64_stats_update_end(&tx_q->stats_sync); + + vport = tx_q->vport; + np = netdev_priv(vport->netdev); + nq = netdev_get_tx_queue(vport->netdev, tx_q->idx); + + dont_wake = np->state != __IDPF_VPORT_UP || + !netif_carrier_ok(vport->netdev); + __netif_txq_completed_wake(nq, total_pkts, total_bytes, + IDPF_DESC_UNUSED(tx_q), IDPF_TX_WAKE_THRESH, + dont_wake); + + return !!budget; +} + +/** + * idpf_tx_singleq_clean_all - Clean all Tx queues + * @q_vec: queue vector + * @budget: Used to determine if we are in netpoll + * @cleaned: returns number of packets cleaned + * + * Returns false if clean is not complete else returns true + */ +static bool idpf_tx_singleq_clean_all(struct idpf_q_vector *q_vec, int budget, + int *cleaned) +{ + u16 num_txq = q_vec->num_txq; + bool clean_complete = true; + int i, budget_per_q; + + budget_per_q = num_txq ? max(budget / num_txq, 1) : 0; + for (i = 0; i < num_txq; i++) { + struct idpf_queue *q; + + q = q_vec->tx[i]; + clean_complete &= idpf_tx_singleq_clean(q, budget_per_q, + cleaned); + } + + return clean_complete; +} + +/** + * idpf_rx_singleq_test_staterr - tests bits in Rx descriptor + * status and error fields + * @rx_desc: pointer to receive descriptor (in le64 format) + * @stat_err_bits: value to mask + * + * This function does some fast chicanery in order to return the + * value of the mask which is really only used for boolean tests. + * The status_error_ptype_len doesn't need to be shifted because it begins + * at offset zero. + */ +static bool idpf_rx_singleq_test_staterr(const union virtchnl2_rx_desc *rx_desc, + const u64 stat_err_bits) +{ + return !!(rx_desc->base_wb.qword1.status_error_ptype_len & + cpu_to_le64(stat_err_bits)); +} + +/** + * idpf_rx_singleq_is_non_eop - process handling of non-EOP buffers + * @rxq: Rx ring being processed + * @rx_desc: Rx descriptor for current buffer + * @skb: Current socket buffer containing buffer in progress + * @ntc: next to clean + */ +static bool idpf_rx_singleq_is_non_eop(struct idpf_queue *rxq, + union virtchnl2_rx_desc *rx_desc, + struct sk_buff *skb, u16 ntc) +{ + /* if we are the last buffer then there is nothing else to do */ + if (likely(idpf_rx_singleq_test_staterr(rx_desc, IDPF_RXD_EOF_SINGLEQ))) + return false; + + return true; +} + +/** + * idpf_rx_singleq_csum - Indicate in skb if checksum is good + * @rxq: Rx ring being processed + * @skb: skb currently being received and modified + * @csum_bits: checksum bits from descriptor + * @ptype: the packet type decoded by hardware + * + * skb->protocol must be set before this function is called + */ +static void idpf_rx_singleq_csum(struct idpf_queue *rxq, struct sk_buff *skb, + struct idpf_rx_csum_decoded *csum_bits, + u16 ptype) +{ + struct idpf_rx_ptype_decoded decoded; + bool ipv4, ipv6; + + /* check if Rx checksum is enabled */ + if (unlikely(!(rxq->vport->netdev->features & NETIF_F_RXCSUM))) + return; + + /* check if HW has decoded the packet and checksum */ + if (unlikely(!(csum_bits->l3l4p))) + return; + + decoded = rxq->vport->rx_ptype_lkup[ptype]; + if (unlikely(!(decoded.known && decoded.outer_ip))) + return; + + ipv4 = IDPF_RX_PTYPE_TO_IPV(&decoded, IDPF_RX_PTYPE_OUTER_IPV4); + ipv6 = IDPF_RX_PTYPE_TO_IPV(&decoded, IDPF_RX_PTYPE_OUTER_IPV6); + + /* Check if there were any checksum errors */ + if (unlikely(ipv4 && (csum_bits->ipe || csum_bits->eipe))) + goto checksum_fail; + + /* Device could not do any checksum offload for certain extension + * headers as indicated by setting IPV6EXADD bit + */ + if (unlikely(ipv6 && csum_bits->ipv6exadd)) + return; + + /* check for L4 errors and handle packets that were not able to be + * checksummed due to arrival speed + */ + if (unlikely(csum_bits->l4e)) + goto checksum_fail; + + if (unlikely(csum_bits->nat && csum_bits->eudpe)) + goto checksum_fail; + + /* Handle packets that were not able to be checksummed due to arrival + * speed, in this case the stack can compute the csum. + */ + if (unlikely(csum_bits->pprs)) + return; + + /* If there is an outer header present that might contain a checksum + * we need to bump the checksum level by 1 to reflect the fact that + * we are indicating we validated the inner checksum. + */ + if (decoded.tunnel_type >= IDPF_RX_PTYPE_TUNNEL_IP_GRENAT) + skb->csum_level = 1; + + /* Only report checksum unnecessary for ICMP, TCP, UDP, or SCTP */ + switch (decoded.inner_prot) { + case IDPF_RX_PTYPE_INNER_PROT_ICMP: + case IDPF_RX_PTYPE_INNER_PROT_TCP: + case IDPF_RX_PTYPE_INNER_PROT_UDP: + case IDPF_RX_PTYPE_INNER_PROT_SCTP: + skb->ip_summed = CHECKSUM_UNNECESSARY; + return; + default: + return; + } + +checksum_fail: + u64_stats_update_begin(&rxq->stats_sync); + u64_stats_inc(&rxq->q_stats.rx.hw_csum_err); + u64_stats_update_end(&rxq->stats_sync); +} + +/** + * idpf_rx_singleq_base_csum - Indicate in skb if hw indicated a good cksum + * @rx_q: Rx completion queue + * @skb: skb currently being received and modified + * @rx_desc: the receive descriptor + * @ptype: Rx packet type + * + * This function only operates on the VIRTCHNL2_RXDID_1_32B_BASE_M base 32byte + * descriptor writeback format. + **/ +static void idpf_rx_singleq_base_csum(struct idpf_queue *rx_q, + struct sk_buff *skb, + union virtchnl2_rx_desc *rx_desc, + u16 ptype) +{ + struct idpf_rx_csum_decoded csum_bits; + u32 rx_error, rx_status; + u64 qword; + + qword = le64_to_cpu(rx_desc->base_wb.qword1.status_error_ptype_len); + + rx_status = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_STATUS_M, qword); + rx_error = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_ERROR_M, qword); + + csum_bits.ipe = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_ERROR_IPE_M, rx_error); + csum_bits.eipe = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_ERROR_EIPE_M, + rx_error); + csum_bits.l4e = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_ERROR_L4E_M, rx_error); + csum_bits.pprs = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_ERROR_PPRS_M, + rx_error); + csum_bits.l3l4p = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_STATUS_L3L4P_M, + rx_status); + csum_bits.ipv6exadd = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_STATUS_IPV6EXADD_M, + rx_status); + csum_bits.nat = 0; + csum_bits.eudpe = 0; + + idpf_rx_singleq_csum(rx_q, skb, &csum_bits, ptype); +} + +/** + * idpf_rx_singleq_flex_csum - Indicate in skb if hw indicated a good cksum + * @rx_q: Rx completion queue + * @skb: skb currently being received and modified + * @rx_desc: the receive descriptor + * @ptype: Rx packet type + * + * This function only operates on the VIRTCHNL2_RXDID_2_FLEX_SQ_NIC flexible + * descriptor writeback format. + **/ +static void idpf_rx_singleq_flex_csum(struct idpf_queue *rx_q, + struct sk_buff *skb, + union virtchnl2_rx_desc *rx_desc, + u16 ptype) +{ + struct idpf_rx_csum_decoded csum_bits; + u16 rx_status0, rx_status1; + + rx_status0 = le16_to_cpu(rx_desc->flex_nic_wb.status_error0); + rx_status1 = le16_to_cpu(rx_desc->flex_nic_wb.status_error1); + + csum_bits.ipe = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_STATUS0_XSUM_IPE_M, + rx_status0); + csum_bits.eipe = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_STATUS0_XSUM_EIPE_M, + rx_status0); + csum_bits.l4e = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_STATUS0_XSUM_L4E_M, + rx_status0); + csum_bits.eudpe = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_STATUS0_XSUM_EUDPE_M, + rx_status0); + csum_bits.l3l4p = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_STATUS0_L3L4P_M, + rx_status0); + csum_bits.ipv6exadd = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_STATUS0_IPV6EXADD_M, + rx_status0); + csum_bits.nat = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_STATUS1_NAT_M, + rx_status1); + csum_bits.pprs = 0; + + idpf_rx_singleq_csum(rx_q, skb, &csum_bits, ptype); +} + +/** + * idpf_rx_singleq_base_hash - set the hash value in the skb + * @rx_q: Rx completion queue + * @skb: skb currently being received and modified + * @rx_desc: specific descriptor + * @decoded: Decoded Rx packet type related fields + * + * This function only operates on the VIRTCHNL2_RXDID_1_32B_BASE_M base 32byte + * descriptor writeback format. + **/ +static void idpf_rx_singleq_base_hash(struct idpf_queue *rx_q, + struct sk_buff *skb, + union virtchnl2_rx_desc *rx_desc, + struct idpf_rx_ptype_decoded *decoded) +{ + u64 mask, qw1; + + if (unlikely(!(rx_q->vport->netdev->features & NETIF_F_RXHASH))) + return; + + mask = VIRTCHNL2_RX_BASE_DESC_FLTSTAT_RSS_HASH_M; + qw1 = le64_to_cpu(rx_desc->base_wb.qword1.status_error_ptype_len); + + if (FIELD_GET(mask, qw1) == mask) { + u32 hash = le32_to_cpu(rx_desc->base_wb.qword0.hi_dword.rss); + + skb_set_hash(skb, hash, idpf_ptype_to_htype(decoded)); + } +} + +/** + * idpf_rx_singleq_flex_hash - set the hash value in the skb + * @rx_q: Rx completion queue + * @skb: skb currently being received and modified + * @rx_desc: specific descriptor + * @decoded: Decoded Rx packet type related fields + * + * This function only operates on the VIRTCHNL2_RXDID_2_FLEX_SQ_NIC flexible + * descriptor writeback format. + **/ +static void idpf_rx_singleq_flex_hash(struct idpf_queue *rx_q, + struct sk_buff *skb, + union virtchnl2_rx_desc *rx_desc, + struct idpf_rx_ptype_decoded *decoded) +{ + if (unlikely(!(rx_q->vport->netdev->features & NETIF_F_RXHASH))) + return; + + if (FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_STATUS0_RSS_VALID_M, + le16_to_cpu(rx_desc->flex_nic_wb.status_error0))) + skb_set_hash(skb, le32_to_cpu(rx_desc->flex_nic_wb.rss_hash), + idpf_ptype_to_htype(decoded)); +} + +/** + * idpf_rx_singleq_process_skb_fields - Populate skb header fields from Rx + * descriptor + * @rx_q: Rx ring being processed + * @skb: pointer to current skb being populated + * @rx_desc: descriptor for skb + * @ptype: packet type + * + * This function checks the ring, descriptor, and packet information in + * order to populate the hash, checksum, VLAN, protocol, and + * other fields within the skb. + */ +static void idpf_rx_singleq_process_skb_fields(struct idpf_queue *rx_q, + struct sk_buff *skb, + union virtchnl2_rx_desc *rx_desc, + u16 ptype) +{ + struct idpf_rx_ptype_decoded decoded = + rx_q->vport->rx_ptype_lkup[ptype]; + + /* modifies the skb - consumes the enet header */ + skb->protocol = eth_type_trans(skb, rx_q->vport->netdev); + + /* Check if we're using base mode descriptor IDs */ + if (rx_q->rxdids == VIRTCHNL2_RXDID_1_32B_BASE_M) { + idpf_rx_singleq_base_hash(rx_q, skb, rx_desc, &decoded); + idpf_rx_singleq_base_csum(rx_q, skb, rx_desc, ptype); + } else { + idpf_rx_singleq_flex_hash(rx_q, skb, rx_desc, &decoded); + idpf_rx_singleq_flex_csum(rx_q, skb, rx_desc, ptype); + } +} + +/** + * idpf_rx_singleq_buf_hw_alloc_all - Replace used receive buffers + * @rx_q: queue for which the hw buffers are allocated + * @cleaned_count: number of buffers to replace + * + * Returns false if all allocations were successful, true if any fail + */ +bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_queue *rx_q, + u16 cleaned_count) +{ + struct virtchnl2_singleq_rx_buf_desc *desc; + u16 nta = rx_q->next_to_alloc; + struct idpf_rx_buf *buf; + + if (!cleaned_count) + return false; + + desc = IDPF_SINGLEQ_RX_BUF_DESC(rx_q, nta); + buf = &rx_q->rx_buf.buf[nta]; + + do { + dma_addr_t addr; + + addr = idpf_alloc_page(rx_q->pp, buf, rx_q->rx_buf_size); + if (unlikely(addr == DMA_MAPPING_ERROR)) + break; + + /* Refresh the desc even if buffer_addrs didn't change + * because each write-back erases this info. + */ + desc->pkt_addr = cpu_to_le64(addr); + desc->hdr_addr = 0; + desc++; + + buf++; + nta++; + if (unlikely(nta == rx_q->desc_count)) { + desc = IDPF_SINGLEQ_RX_BUF_DESC(rx_q, 0); + buf = rx_q->rx_buf.buf; + nta = 0; + } + + cleaned_count--; + } while (cleaned_count); + + if (rx_q->next_to_alloc != nta) { + idpf_rx_buf_hw_update(rx_q, nta); + rx_q->next_to_alloc = nta; + } + + return !!cleaned_count; +} + +/** + * idpf_rx_singleq_extract_base_fields - Extract fields from the Rx descriptor + * @rx_q: Rx descriptor queue + * @rx_desc: the descriptor to process + * @fields: storage for extracted values + * + * Decode the Rx descriptor and extract relevant information including the + * size and Rx packet type. + * + * This function only operates on the VIRTCHNL2_RXDID_1_32B_BASE_M base 32byte + * descriptor writeback format. + */ +static void idpf_rx_singleq_extract_base_fields(struct idpf_queue *rx_q, + union virtchnl2_rx_desc *rx_desc, + struct idpf_rx_extracted *fields) +{ + u64 qword; + + qword = le64_to_cpu(rx_desc->base_wb.qword1.status_error_ptype_len); + + fields->size = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_LEN_PBUF_M, qword); + fields->rx_ptype = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_PTYPE_M, qword); +} + +/** + * idpf_rx_singleq_extract_flex_fields - Extract fields from the Rx descriptor + * @rx_q: Rx descriptor queue + * @rx_desc: the descriptor to process + * @fields: storage for extracted values + * + * Decode the Rx descriptor and extract relevant information including the + * size and Rx packet type. + * + * This function only operates on the VIRTCHNL2_RXDID_2_FLEX_SQ_NIC flexible + * descriptor writeback format. + */ +static void idpf_rx_singleq_extract_flex_fields(struct idpf_queue *rx_q, + union virtchnl2_rx_desc *rx_desc, + struct idpf_rx_extracted *fields) +{ + fields->size = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PKT_LEN_M, + le16_to_cpu(rx_desc->flex_nic_wb.pkt_len)); + fields->rx_ptype = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PTYPE_M, + le16_to_cpu(rx_desc->flex_nic_wb.ptype_flex_flags0)); +} + +/** + * idpf_rx_singleq_extract_fields - Extract fields from the Rx descriptor + * @rx_q: Rx descriptor queue + * @rx_desc: the descriptor to process + * @fields: storage for extracted values + * + */ +static void idpf_rx_singleq_extract_fields(struct idpf_queue *rx_q, + union virtchnl2_rx_desc *rx_desc, + struct idpf_rx_extracted *fields) +{ + if (rx_q->rxdids == VIRTCHNL2_RXDID_1_32B_BASE_M) + idpf_rx_singleq_extract_base_fields(rx_q, rx_desc, fields); + else + idpf_rx_singleq_extract_flex_fields(rx_q, rx_desc, fields); +} + +/** + * idpf_rx_singleq_clean - Reclaim resources after receive completes + * @rx_q: rx queue to clean + * @budget: Total limit on number of packets to process + * + * Returns true if there's any budget left (e.g. the clean is finished) + */ +static int idpf_rx_singleq_clean(struct idpf_queue *rx_q, int budget) +{ + unsigned int total_rx_bytes = 0, total_rx_pkts = 0; + struct sk_buff *skb = rx_q->skb; + u16 ntc = rx_q->next_to_clean; + u16 cleaned_count = 0; + bool failure = false; + + /* Process Rx packets bounded by budget */ + while (likely(total_rx_pkts < (unsigned int)budget)) { + struct idpf_rx_extracted fields = { }; + union virtchnl2_rx_desc *rx_desc; + struct idpf_rx_buf *rx_buf; + + /* get the Rx desc from Rx queue based on 'next_to_clean' */ + rx_desc = IDPF_RX_DESC(rx_q, ntc); + + /* status_error_ptype_len will always be zero for unused + * descriptors because it's cleared in cleanup, and overlaps + * with hdr_addr which is always zero because packet split + * isn't used, if the hardware wrote DD then the length will be + * non-zero + */ +#define IDPF_RXD_DD VIRTCHNL2_RX_BASE_DESC_STATUS_DD_M + if (!idpf_rx_singleq_test_staterr(rx_desc, + IDPF_RXD_DD)) + break; + + /* This memory barrier is needed to keep us from reading + * any other fields out of the rx_desc + */ + dma_rmb(); + + idpf_rx_singleq_extract_fields(rx_q, rx_desc, &fields); + + rx_buf = &rx_q->rx_buf.buf[ntc]; + if (!fields.size) { + idpf_rx_put_page(rx_buf); + goto skip_data; + } + + idpf_rx_sync_for_cpu(rx_buf, fields.size); + skb = rx_q->skb; + if (skb) + idpf_rx_add_frag(rx_buf, skb, fields.size); + else + skb = idpf_rx_construct_skb(rx_q, rx_buf, fields.size); + + /* exit if we failed to retrieve a buffer */ + if (!skb) + break; + +skip_data: + IDPF_SINGLEQ_BUMP_RING_IDX(rx_q, ntc); + + cleaned_count++; + + /* skip if it is non EOP desc */ + if (idpf_rx_singleq_is_non_eop(rx_q, rx_desc, skb, ntc)) + continue; + +#define IDPF_RXD_ERR_S FIELD_PREP(VIRTCHNL2_RX_BASE_DESC_QW1_ERROR_M, \ + VIRTCHNL2_RX_BASE_DESC_ERROR_RXE_M) + if (unlikely(idpf_rx_singleq_test_staterr(rx_desc, + IDPF_RXD_ERR_S))) { + dev_kfree_skb_any(skb); + skb = NULL; + continue; + } + + /* pad skb if needed (to make valid ethernet frame) */ + if (eth_skb_pad(skb)) { + skb = NULL; + continue; + } + + /* probably a little skewed due to removing CRC */ + total_rx_bytes += skb->len; + + /* protocol */ + idpf_rx_singleq_process_skb_fields(rx_q, skb, + rx_desc, fields.rx_ptype); + + /* send completed skb up the stack */ + napi_gro_receive(&rx_q->q_vector->napi, skb); + skb = NULL; + + /* update budget accounting */ + total_rx_pkts++; + } + + rx_q->skb = skb; + + rx_q->next_to_clean = ntc; + + if (cleaned_count) + failure = idpf_rx_singleq_buf_hw_alloc_all(rx_q, cleaned_count); + + u64_stats_update_begin(&rx_q->stats_sync); + u64_stats_add(&rx_q->q_stats.rx.packets, total_rx_pkts); + u64_stats_add(&rx_q->q_stats.rx.bytes, total_rx_bytes); + u64_stats_update_end(&rx_q->stats_sync); + + /* guarantee a trip back through this routine if there was a failure */ + return failure ? budget : (int)total_rx_pkts; +} + +/** + * idpf_rx_singleq_clean_all - Clean all Rx queues + * @q_vec: queue vector + * @budget: Used to determine if we are in netpoll + * @cleaned: returns number of packets cleaned + * + * Returns false if clean is not complete else returns true + */ +static bool idpf_rx_singleq_clean_all(struct idpf_q_vector *q_vec, int budget, + int *cleaned) +{ + u16 num_rxq = q_vec->num_rxq; + bool clean_complete = true; + int budget_per_q, i; + + /* We attempt to distribute budget to each Rx queue fairly, but don't + * allow the budget to go below 1 because that would exit polling early. + */ + budget_per_q = num_rxq ? max(budget / num_rxq, 1) : 0; + for (i = 0; i < num_rxq; i++) { + struct idpf_queue *rxq = q_vec->rx[i]; + int pkts_cleaned_per_q; + + pkts_cleaned_per_q = idpf_rx_singleq_clean(rxq, budget_per_q); + + /* if we clean as many as budgeted, we must not be done */ + if (pkts_cleaned_per_q >= budget_per_q) + clean_complete = false; + *cleaned += pkts_cleaned_per_q; + } + + return clean_complete; +} + +/** + * idpf_vport_singleq_napi_poll - NAPI handler + * @napi: struct from which you get q_vector + * @budget: budget provided by stack + */ +int idpf_vport_singleq_napi_poll(struct napi_struct *napi, int budget) +{ + struct idpf_q_vector *q_vector = + container_of(napi, struct idpf_q_vector, napi); + bool clean_complete; + int work_done = 0; + + /* Handle case where we are called by netpoll with a budget of 0 */ + if (budget <= 0) { + idpf_tx_singleq_clean_all(q_vector, budget, &work_done); + + return budget; + } + + clean_complete = idpf_rx_singleq_clean_all(q_vector, budget, + &work_done); + clean_complete &= idpf_tx_singleq_clean_all(q_vector, budget, + &work_done); + + /* If work not completed, return budget and polling will return */ + if (!clean_complete) + return budget; + + work_done = min_t(int, work_done, budget - 1); + + /* Exit the polling mode, but don't re-enable interrupts if stack might + * poll us due to busy-polling + */ + if (likely(napi_complete_done(napi, work_done))) + idpf_vport_intr_update_itr_ena_irq(q_vector); + + return work_done; +} diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c new file mode 100644 index 000000000000..1f728a9004d9 --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -0,0 +1,4294 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2023 Intel Corporation */ + +#include "idpf.h" + +/** + * idpf_buf_lifo_push - push a buffer pointer onto stack + * @stack: pointer to stack struct + * @buf: pointer to buf to push + * + * Returns 0 on success, negative on failure + **/ +static int idpf_buf_lifo_push(struct idpf_buf_lifo *stack, + struct idpf_tx_stash *buf) +{ + if (unlikely(stack->top == stack->size)) + return -ENOSPC; + + stack->bufs[stack->top++] = buf; + + return 0; +} + +/** + * idpf_buf_lifo_pop - pop a buffer pointer from stack + * @stack: pointer to stack struct + **/ +static struct idpf_tx_stash *idpf_buf_lifo_pop(struct idpf_buf_lifo *stack) +{ + if (unlikely(!stack->top)) + return NULL; + + return stack->bufs[--stack->top]; +} + +/** + * idpf_tx_timeout - Respond to a Tx Hang + * @netdev: network interface device structure + * @txqueue: TX queue + */ +void idpf_tx_timeout(struct net_device *netdev, unsigned int txqueue) +{ + struct idpf_adapter *adapter = idpf_netdev_to_adapter(netdev); + + adapter->tx_timeout_count++; + + netdev_err(netdev, "Detected Tx timeout: Count %d, Queue %d\n", + adapter->tx_timeout_count, txqueue); + if (!idpf_is_reset_in_prog(adapter)) { + set_bit(IDPF_HR_FUNC_RESET, adapter->flags); + queue_delayed_work(adapter->vc_event_wq, + &adapter->vc_event_task, + msecs_to_jiffies(10)); + } +} + +/** + * idpf_tx_buf_rel - Release a Tx buffer + * @tx_q: the queue that owns the buffer + * @tx_buf: the buffer to free + */ +static void idpf_tx_buf_rel(struct idpf_queue *tx_q, struct idpf_tx_buf *tx_buf) +{ + if (tx_buf->skb) { + if (dma_unmap_len(tx_buf, len)) + dma_unmap_single(tx_q->dev, + dma_unmap_addr(tx_buf, dma), + dma_unmap_len(tx_buf, len), + DMA_TO_DEVICE); + dev_kfree_skb_any(tx_buf->skb); + } else if (dma_unmap_len(tx_buf, len)) { + dma_unmap_page(tx_q->dev, + dma_unmap_addr(tx_buf, dma), + dma_unmap_len(tx_buf, len), + DMA_TO_DEVICE); + } + + tx_buf->next_to_watch = NULL; + tx_buf->skb = NULL; + tx_buf->compl_tag = IDPF_SPLITQ_TX_INVAL_COMPL_TAG; + dma_unmap_len_set(tx_buf, len, 0); +} + +/** + * idpf_tx_buf_rel_all - Free any empty Tx buffers + * @txq: queue to be cleaned + */ +static void idpf_tx_buf_rel_all(struct idpf_queue *txq) +{ + u16 i; + + /* Buffers already cleared, nothing to do */ + if (!txq->tx_buf) + return; + + /* Free all the Tx buffer sk_buffs */ + for (i = 0; i < txq->desc_count; i++) + idpf_tx_buf_rel(txq, &txq->tx_buf[i]); + + kfree(txq->tx_buf); + txq->tx_buf = NULL; + + if (!txq->buf_stack.bufs) + return; + + for (i = 0; i < txq->buf_stack.size; i++) + kfree(txq->buf_stack.bufs[i]); + + kfree(txq->buf_stack.bufs); + txq->buf_stack.bufs = NULL; +} + +/** + * idpf_tx_desc_rel - Free Tx resources per queue + * @txq: Tx descriptor ring for a specific queue + * @bufq: buffer q or completion q + * + * Free all transmit software resources + */ +static void idpf_tx_desc_rel(struct idpf_queue *txq, bool bufq) +{ + if (bufq) + idpf_tx_buf_rel_all(txq); + + if (!txq->desc_ring) + return; + + dmam_free_coherent(txq->dev, txq->size, txq->desc_ring, txq->dma); + txq->desc_ring = NULL; + txq->next_to_alloc = 0; + txq->next_to_use = 0; + txq->next_to_clean = 0; +} + +/** + * idpf_tx_desc_rel_all - Free Tx Resources for All Queues + * @vport: virtual port structure + * + * Free all transmit software resources + */ +static void idpf_tx_desc_rel_all(struct idpf_vport *vport) +{ + int i, j; + + if (!vport->txq_grps) + return; + + for (i = 0; i < vport->num_txq_grp; i++) { + struct idpf_txq_group *txq_grp = &vport->txq_grps[i]; + + for (j = 0; j < txq_grp->num_txq; j++) + idpf_tx_desc_rel(txq_grp->txqs[j], true); + + if (idpf_is_queue_model_split(vport->txq_model)) + idpf_tx_desc_rel(txq_grp->complq, false); + } +} + +/** + * idpf_tx_buf_alloc_all - Allocate memory for all buffer resources + * @tx_q: queue for which the buffers are allocated + * + * Returns 0 on success, negative on failure + */ +static int idpf_tx_buf_alloc_all(struct idpf_queue *tx_q) +{ + int buf_size; + int i; + + /* Allocate book keeping buffers only. Buffers to be supplied to HW + * are allocated by kernel network stack and received as part of skb + */ + buf_size = sizeof(struct idpf_tx_buf) * tx_q->desc_count; + tx_q->tx_buf = kzalloc(buf_size, GFP_KERNEL); + if (!tx_q->tx_buf) + return -ENOMEM; + + /* Initialize tx_bufs with invalid completion tags */ + for (i = 0; i < tx_q->desc_count; i++) + tx_q->tx_buf[i].compl_tag = IDPF_SPLITQ_TX_INVAL_COMPL_TAG; + + /* Initialize tx buf stack for out-of-order completions if + * flow scheduling offload is enabled + */ + tx_q->buf_stack.bufs = + kcalloc(tx_q->desc_count, sizeof(struct idpf_tx_stash *), + GFP_KERNEL); + if (!tx_q->buf_stack.bufs) + return -ENOMEM; + + tx_q->buf_stack.size = tx_q->desc_count; + tx_q->buf_stack.top = tx_q->desc_count; + + for (i = 0; i < tx_q->desc_count; i++) { + tx_q->buf_stack.bufs[i] = kzalloc(sizeof(*tx_q->buf_stack.bufs[i]), + GFP_KERNEL); + if (!tx_q->buf_stack.bufs[i]) + return -ENOMEM; + } + + return 0; +} + +/** + * idpf_tx_desc_alloc - Allocate the Tx descriptors + * @tx_q: the tx ring to set up + * @bufq: buffer or completion queue + * + * Returns 0 on success, negative on failure + */ +static int idpf_tx_desc_alloc(struct idpf_queue *tx_q, bool bufq) +{ + struct device *dev = tx_q->dev; + u32 desc_sz; + int err; + + if (bufq) { + err = idpf_tx_buf_alloc_all(tx_q); + if (err) + goto err_alloc; + + desc_sz = sizeof(struct idpf_base_tx_desc); + } else { + desc_sz = sizeof(struct idpf_splitq_tx_compl_desc); + } + + tx_q->size = tx_q->desc_count * desc_sz; + + /* Allocate descriptors also round up to nearest 4K */ + tx_q->size = ALIGN(tx_q->size, 4096); + tx_q->desc_ring = dmam_alloc_coherent(dev, tx_q->size, &tx_q->dma, + GFP_KERNEL); + if (!tx_q->desc_ring) { + dev_err(dev, "Unable to allocate memory for the Tx descriptor ring, size=%d\n", + tx_q->size); + err = -ENOMEM; + goto err_alloc; + } + + tx_q->next_to_alloc = 0; + tx_q->next_to_use = 0; + tx_q->next_to_clean = 0; + set_bit(__IDPF_Q_GEN_CHK, tx_q->flags); + + return 0; + +err_alloc: + idpf_tx_desc_rel(tx_q, bufq); + + return err; +} + +/** + * idpf_tx_desc_alloc_all - allocate all queues Tx resources + * @vport: virtual port private structure + * + * Returns 0 on success, negative on failure + */ +static int idpf_tx_desc_alloc_all(struct idpf_vport *vport) +{ + struct device *dev = &vport->adapter->pdev->dev; + int err = 0; + int i, j; + + /* Setup buffer queues. In single queue model buffer queues and + * completion queues will be same + */ + for (i = 0; i < vport->num_txq_grp; i++) { + for (j = 0; j < vport->txq_grps[i].num_txq; j++) { + struct idpf_queue *txq = vport->txq_grps[i].txqs[j]; + u8 gen_bits = 0; + u16 bufidx_mask; + + err = idpf_tx_desc_alloc(txq, true); + if (err) { + dev_err(dev, "Allocation for Tx Queue %u failed\n", + i); + goto err_out; + } + + if (!idpf_is_queue_model_split(vport->txq_model)) + continue; + + txq->compl_tag_cur_gen = 0; + + /* Determine the number of bits in the bufid + * mask and add one to get the start of the + * generation bits + */ + bufidx_mask = txq->desc_count - 1; + while (bufidx_mask >> 1) { + txq->compl_tag_gen_s++; + bufidx_mask = bufidx_mask >> 1; + } + txq->compl_tag_gen_s++; + + gen_bits = IDPF_TX_SPLITQ_COMPL_TAG_WIDTH - + txq->compl_tag_gen_s; + txq->compl_tag_gen_max = GETMAXVAL(gen_bits); + + /* Set bufid mask based on location of first + * gen bit; it cannot simply be the descriptor + * ring size-1 since we can have size values + * where not all of those bits are set. + */ + txq->compl_tag_bufid_m = + GETMAXVAL(txq->compl_tag_gen_s); + } + + if (!idpf_is_queue_model_split(vport->txq_model)) + continue; + + /* Setup completion queues */ + err = idpf_tx_desc_alloc(vport->txq_grps[i].complq, false); + if (err) { + dev_err(dev, "Allocation for Tx Completion Queue %u failed\n", + i); + goto err_out; + } + } + +err_out: + if (err) + idpf_tx_desc_rel_all(vport); + + return err; +} + +/** + * idpf_rx_page_rel - Release an rx buffer page + * @rxq: the queue that owns the buffer + * @rx_buf: the buffer to free + */ +static void idpf_rx_page_rel(struct idpf_queue *rxq, struct idpf_rx_buf *rx_buf) +{ + if (unlikely(!rx_buf->page)) + return; + + page_pool_put_full_page(rxq->pp, rx_buf->page, false); + + rx_buf->page = NULL; + rx_buf->page_offset = 0; +} + +/** + * idpf_rx_hdr_buf_rel_all - Release header buffer memory + * @rxq: queue to use + */ +static void idpf_rx_hdr_buf_rel_all(struct idpf_queue *rxq) +{ + struct idpf_adapter *adapter = rxq->vport->adapter; + + dma_free_coherent(&adapter->pdev->dev, + rxq->desc_count * IDPF_HDR_BUF_SIZE, + rxq->rx_buf.hdr_buf_va, + rxq->rx_buf.hdr_buf_pa); + rxq->rx_buf.hdr_buf_va = NULL; +} + +/** + * idpf_rx_buf_rel_all - Free all Rx buffer resources for a queue + * @rxq: queue to be cleaned + */ +static void idpf_rx_buf_rel_all(struct idpf_queue *rxq) +{ + u16 i; + + /* queue already cleared, nothing to do */ + if (!rxq->rx_buf.buf) + return; + + /* Free all the bufs allocated and given to hw on Rx queue */ + for (i = 0; i < rxq->desc_count; i++) + idpf_rx_page_rel(rxq, &rxq->rx_buf.buf[i]); + + if (rxq->rx_hsplit_en) + idpf_rx_hdr_buf_rel_all(rxq); + + page_pool_destroy(rxq->pp); + rxq->pp = NULL; + + kfree(rxq->rx_buf.buf); + rxq->rx_buf.buf = NULL; +} + +/** + * idpf_rx_desc_rel - Free a specific Rx q resources + * @rxq: queue to clean the resources from + * @bufq: buffer q or completion q + * @q_model: single or split q model + * + * Free a specific rx queue resources + */ +static void idpf_rx_desc_rel(struct idpf_queue *rxq, bool bufq, s32 q_model) +{ + if (!rxq) + return; + + if (!bufq && idpf_is_queue_model_split(q_model) && rxq->skb) { + dev_kfree_skb_any(rxq->skb); + rxq->skb = NULL; + } + + if (bufq || !idpf_is_queue_model_split(q_model)) + idpf_rx_buf_rel_all(rxq); + + rxq->next_to_alloc = 0; + rxq->next_to_clean = 0; + rxq->next_to_use = 0; + if (!rxq->desc_ring) + return; + + dmam_free_coherent(rxq->dev, rxq->size, rxq->desc_ring, rxq->dma); + rxq->desc_ring = NULL; +} + +/** + * idpf_rx_desc_rel_all - Free Rx Resources for All Queues + * @vport: virtual port structure + * + * Free all rx queues resources + */ +static void idpf_rx_desc_rel_all(struct idpf_vport *vport) +{ + struct idpf_rxq_group *rx_qgrp; + u16 num_rxq; + int i, j; + + if (!vport->rxq_grps) + return; + + for (i = 0; i < vport->num_rxq_grp; i++) { + rx_qgrp = &vport->rxq_grps[i]; + + if (!idpf_is_queue_model_split(vport->rxq_model)) { + for (j = 0; j < rx_qgrp->singleq.num_rxq; j++) + idpf_rx_desc_rel(rx_qgrp->singleq.rxqs[j], + false, vport->rxq_model); + continue; + } + + num_rxq = rx_qgrp->splitq.num_rxq_sets; + for (j = 0; j < num_rxq; j++) + idpf_rx_desc_rel(&rx_qgrp->splitq.rxq_sets[j]->rxq, + false, vport->rxq_model); + + if (!rx_qgrp->splitq.bufq_sets) + continue; + + for (j = 0; j < vport->num_bufqs_per_qgrp; j++) { + struct idpf_bufq_set *bufq_set = + &rx_qgrp->splitq.bufq_sets[j]; + + idpf_rx_desc_rel(&bufq_set->bufq, true, + vport->rxq_model); + } + } +} + +/** + * idpf_rx_buf_hw_update - Store the new tail and head values + * @rxq: queue to bump + * @val: new head index + */ +void idpf_rx_buf_hw_update(struct idpf_queue *rxq, u32 val) +{ + rxq->next_to_use = val; + + if (unlikely(!rxq->tail)) + return; + + /* writel has an implicit memory barrier */ + writel(val, rxq->tail); +} + +/** + * idpf_rx_hdr_buf_alloc_all - Allocate memory for header buffers + * @rxq: ring to use + * + * Returns 0 on success, negative on failure. + */ +static int idpf_rx_hdr_buf_alloc_all(struct idpf_queue *rxq) +{ + struct idpf_adapter *adapter = rxq->vport->adapter; + + rxq->rx_buf.hdr_buf_va = + dma_alloc_coherent(&adapter->pdev->dev, + IDPF_HDR_BUF_SIZE * rxq->desc_count, + &rxq->rx_buf.hdr_buf_pa, + GFP_KERNEL); + if (!rxq->rx_buf.hdr_buf_va) + return -ENOMEM; + + return 0; +} + +/** + * idpf_rx_post_buf_refill - Post buffer id to refill queue + * @refillq: refill queue to post to + * @buf_id: buffer id to post + */ +static void idpf_rx_post_buf_refill(struct idpf_sw_queue *refillq, u16 buf_id) +{ + u16 nta = refillq->next_to_alloc; + + /* store the buffer ID and the SW maintained GEN bit to the refillq */ + refillq->ring[nta] = + ((buf_id << IDPF_RX_BI_BUFID_S) & IDPF_RX_BI_BUFID_M) | + (!!(test_bit(__IDPF_Q_GEN_CHK, refillq->flags)) << + IDPF_RX_BI_GEN_S); + + if (unlikely(++nta == refillq->desc_count)) { + nta = 0; + change_bit(__IDPF_Q_GEN_CHK, refillq->flags); + } + refillq->next_to_alloc = nta; +} + +/** + * idpf_rx_post_buf_desc - Post buffer to bufq descriptor ring + * @bufq: buffer queue to post to + * @buf_id: buffer id to post + * + * Returns false if buffer could not be allocated, true otherwise. + */ +static bool idpf_rx_post_buf_desc(struct idpf_queue *bufq, u16 buf_id) +{ + struct virtchnl2_splitq_rx_buf_desc *splitq_rx_desc = NULL; + u16 nta = bufq->next_to_alloc; + struct idpf_rx_buf *buf; + dma_addr_t addr; + + splitq_rx_desc = IDPF_SPLITQ_RX_BUF_DESC(bufq, nta); + buf = &bufq->rx_buf.buf[buf_id]; + + if (bufq->rx_hsplit_en) { + splitq_rx_desc->hdr_addr = + cpu_to_le64(bufq->rx_buf.hdr_buf_pa + + (u32)buf_id * IDPF_HDR_BUF_SIZE); + } + + addr = idpf_alloc_page(bufq->pp, buf, bufq->rx_buf_size); + if (unlikely(addr == DMA_MAPPING_ERROR)) + return false; + + splitq_rx_desc->pkt_addr = cpu_to_le64(addr); + splitq_rx_desc->qword0.buf_id = cpu_to_le16(buf_id); + + nta++; + if (unlikely(nta == bufq->desc_count)) + nta = 0; + bufq->next_to_alloc = nta; + + return true; +} + +/** + * idpf_rx_post_init_bufs - Post initial buffers to bufq + * @bufq: buffer queue to post working set to + * @working_set: number of buffers to put in working set + * + * Returns true if @working_set bufs were posted successfully, false otherwise. + */ +static bool idpf_rx_post_init_bufs(struct idpf_queue *bufq, u16 working_set) +{ + int i; + + for (i = 0; i < working_set; i++) { + if (!idpf_rx_post_buf_desc(bufq, i)) + return false; + } + + idpf_rx_buf_hw_update(bufq, + bufq->next_to_alloc & ~(bufq->rx_buf_stride - 1)); + + return true; +} + +/** + * idpf_rx_create_page_pool - Create a page pool + * @rxbufq: RX queue to create page pool for + * + * Returns &page_pool on success, casted -errno on failure + */ +static struct page_pool *idpf_rx_create_page_pool(struct idpf_queue *rxbufq) +{ + struct page_pool_params pp = { + .flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV, + .order = 0, + .pool_size = rxbufq->desc_count, + .nid = NUMA_NO_NODE, + .dev = rxbufq->vport->netdev->dev.parent, + .max_len = PAGE_SIZE, + .dma_dir = DMA_FROM_DEVICE, + .offset = 0, + }; + + return page_pool_create(&pp); +} + +/** + * idpf_rx_buf_alloc_all - Allocate memory for all buffer resources + * @rxbufq: queue for which the buffers are allocated; equivalent to + * rxq when operating in singleq mode + * + * Returns 0 on success, negative on failure + */ +static int idpf_rx_buf_alloc_all(struct idpf_queue *rxbufq) +{ + int err = 0; + + /* Allocate book keeping buffers */ + rxbufq->rx_buf.buf = kcalloc(rxbufq->desc_count, + sizeof(struct idpf_rx_buf), GFP_KERNEL); + if (!rxbufq->rx_buf.buf) { + err = -ENOMEM; + goto rx_buf_alloc_all_out; + } + + if (rxbufq->rx_hsplit_en) { + err = idpf_rx_hdr_buf_alloc_all(rxbufq); + if (err) + goto rx_buf_alloc_all_out; + } + + /* Allocate buffers to be given to HW. */ + if (idpf_is_queue_model_split(rxbufq->vport->rxq_model)) { + int working_set = IDPF_RX_BUFQ_WORKING_SET(rxbufq); + + if (!idpf_rx_post_init_bufs(rxbufq, working_set)) + err = -ENOMEM; + } else { + if (idpf_rx_singleq_buf_hw_alloc_all(rxbufq, + rxbufq->desc_count - 1)) + err = -ENOMEM; + } + +rx_buf_alloc_all_out: + if (err) + idpf_rx_buf_rel_all(rxbufq); + + return err; +} + +/** + * idpf_rx_bufs_init - Initialize page pool, allocate rx bufs, and post to HW + * @rxbufq: RX queue to create page pool for + * + * Returns 0 on success, negative on failure + */ +static int idpf_rx_bufs_init(struct idpf_queue *rxbufq) +{ + struct page_pool *pool; + + pool = idpf_rx_create_page_pool(rxbufq); + if (IS_ERR(pool)) + return PTR_ERR(pool); + + rxbufq->pp = pool; + + return idpf_rx_buf_alloc_all(rxbufq); +} + +/** + * idpf_rx_bufs_init_all - Initialize all RX bufs + * @vport: virtual port struct + * + * Returns 0 on success, negative on failure + */ +int idpf_rx_bufs_init_all(struct idpf_vport *vport) +{ + struct idpf_rxq_group *rx_qgrp; + struct idpf_queue *q; + int i, j, err; + + for (i = 0; i < vport->num_rxq_grp; i++) { + rx_qgrp = &vport->rxq_grps[i]; + + /* Allocate bufs for the rxq itself in singleq */ + if (!idpf_is_queue_model_split(vport->rxq_model)) { + int num_rxq = rx_qgrp->singleq.num_rxq; + + for (j = 0; j < num_rxq; j++) { + q = rx_qgrp->singleq.rxqs[j]; + err = idpf_rx_bufs_init(q); + if (err) + return err; + } + + continue; + } + + /* Otherwise, allocate bufs for the buffer queues */ + for (j = 0; j < vport->num_bufqs_per_qgrp; j++) { + q = &rx_qgrp->splitq.bufq_sets[j].bufq; + err = idpf_rx_bufs_init(q); + if (err) + return err; + } + } + + return 0; +} + +/** + * idpf_rx_desc_alloc - Allocate queue Rx resources + * @rxq: Rx queue for which the resources are setup + * @bufq: buffer or completion queue + * @q_model: single or split queue model + * + * Returns 0 on success, negative on failure + */ +static int idpf_rx_desc_alloc(struct idpf_queue *rxq, bool bufq, s32 q_model) +{ + struct device *dev = rxq->dev; + + if (bufq) + rxq->size = rxq->desc_count * + sizeof(struct virtchnl2_splitq_rx_buf_desc); + else + rxq->size = rxq->desc_count * + sizeof(union virtchnl2_rx_desc); + + /* Allocate descriptors and also round up to nearest 4K */ + rxq->size = ALIGN(rxq->size, 4096); + rxq->desc_ring = dmam_alloc_coherent(dev, rxq->size, + &rxq->dma, GFP_KERNEL); + if (!rxq->desc_ring) { + dev_err(dev, "Unable to allocate memory for the Rx descriptor ring, size=%d\n", + rxq->size); + return -ENOMEM; + } + + rxq->next_to_alloc = 0; + rxq->next_to_clean = 0; + rxq->next_to_use = 0; + set_bit(__IDPF_Q_GEN_CHK, rxq->flags); + + return 0; +} + +/** + * idpf_rx_desc_alloc_all - allocate all RX queues resources + * @vport: virtual port structure + * + * Returns 0 on success, negative on failure + */ +static int idpf_rx_desc_alloc_all(struct idpf_vport *vport) +{ + struct device *dev = &vport->adapter->pdev->dev; + struct idpf_rxq_group *rx_qgrp; + struct idpf_queue *q; + int i, j, err; + u16 num_rxq; + + for (i = 0; i < vport->num_rxq_grp; i++) { + rx_qgrp = &vport->rxq_grps[i]; + if (idpf_is_queue_model_split(vport->rxq_model)) + num_rxq = rx_qgrp->splitq.num_rxq_sets; + else + num_rxq = rx_qgrp->singleq.num_rxq; + + for (j = 0; j < num_rxq; j++) { + if (idpf_is_queue_model_split(vport->rxq_model)) + q = &rx_qgrp->splitq.rxq_sets[j]->rxq; + else + q = rx_qgrp->singleq.rxqs[j]; + err = idpf_rx_desc_alloc(q, false, vport->rxq_model); + if (err) { + dev_err(dev, "Memory allocation for Rx Queue %u failed\n", + i); + goto err_out; + } + } + + if (!idpf_is_queue_model_split(vport->rxq_model)) + continue; + + for (j = 0; j < vport->num_bufqs_per_qgrp; j++) { + q = &rx_qgrp->splitq.bufq_sets[j].bufq; + err = idpf_rx_desc_alloc(q, true, vport->rxq_model); + if (err) { + dev_err(dev, "Memory allocation for Rx Buffer Queue %u failed\n", + i); + goto err_out; + } + } + } + + return 0; + +err_out: + idpf_rx_desc_rel_all(vport); + + return err; +} + +/** + * idpf_txq_group_rel - Release all resources for txq groups + * @vport: vport to release txq groups on + */ +static void idpf_txq_group_rel(struct idpf_vport *vport) +{ + int i, j; + + if (!vport->txq_grps) + return; + + for (i = 0; i < vport->num_txq_grp; i++) { + struct idpf_txq_group *txq_grp = &vport->txq_grps[i]; + + for (j = 0; j < txq_grp->num_txq; j++) { + kfree(txq_grp->txqs[j]); + txq_grp->txqs[j] = NULL; + } + kfree(txq_grp->complq); + txq_grp->complq = NULL; + } + kfree(vport->txq_grps); + vport->txq_grps = NULL; +} + +/** + * idpf_rxq_sw_queue_rel - Release software queue resources + * @rx_qgrp: rx queue group with software queues + */ +static void idpf_rxq_sw_queue_rel(struct idpf_rxq_group *rx_qgrp) +{ + int i, j; + + for (i = 0; i < rx_qgrp->vport->num_bufqs_per_qgrp; i++) { + struct idpf_bufq_set *bufq_set = &rx_qgrp->splitq.bufq_sets[i]; + + for (j = 0; j < bufq_set->num_refillqs; j++) { + kfree(bufq_set->refillqs[j].ring); + bufq_set->refillqs[j].ring = NULL; + } + kfree(bufq_set->refillqs); + bufq_set->refillqs = NULL; + } +} + +/** + * idpf_rxq_group_rel - Release all resources for rxq groups + * @vport: vport to release rxq groups on + */ +static void idpf_rxq_group_rel(struct idpf_vport *vport) +{ + int i; + + if (!vport->rxq_grps) + return; + + for (i = 0; i < vport->num_rxq_grp; i++) { + struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i]; + u16 num_rxq; + int j; + + if (idpf_is_queue_model_split(vport->rxq_model)) { + num_rxq = rx_qgrp->splitq.num_rxq_sets; + for (j = 0; j < num_rxq; j++) { + kfree(rx_qgrp->splitq.rxq_sets[j]); + rx_qgrp->splitq.rxq_sets[j] = NULL; + } + + idpf_rxq_sw_queue_rel(rx_qgrp); + kfree(rx_qgrp->splitq.bufq_sets); + rx_qgrp->splitq.bufq_sets = NULL; + } else { + num_rxq = rx_qgrp->singleq.num_rxq; + for (j = 0; j < num_rxq; j++) { + kfree(rx_qgrp->singleq.rxqs[j]); + rx_qgrp->singleq.rxqs[j] = NULL; + } + } + } + kfree(vport->rxq_grps); + vport->rxq_grps = NULL; +} + +/** + * idpf_vport_queue_grp_rel_all - Release all queue groups + * @vport: vport to release queue groups for + */ +static void idpf_vport_queue_grp_rel_all(struct idpf_vport *vport) +{ + idpf_txq_group_rel(vport); + idpf_rxq_group_rel(vport); +} + +/** + * idpf_vport_queues_rel - Free memory for all queues + * @vport: virtual port + * + * Free the memory allocated for queues associated to a vport + */ +void idpf_vport_queues_rel(struct idpf_vport *vport) +{ + idpf_tx_desc_rel_all(vport); + idpf_rx_desc_rel_all(vport); + idpf_vport_queue_grp_rel_all(vport); + + kfree(vport->txqs); + vport->txqs = NULL; +} + +/** + * idpf_vport_init_fast_path_txqs - Initialize fast path txq array + * @vport: vport to init txqs on + * + * We get a queue index from skb->queue_mapping and we need a fast way to + * dereference the queue from queue groups. This allows us to quickly pull a + * txq based on a queue index. + * + * Returns 0 on success, negative on failure + */ +static int idpf_vport_init_fast_path_txqs(struct idpf_vport *vport) +{ + int i, j, k = 0; + + vport->txqs = kcalloc(vport->num_txq, sizeof(struct idpf_queue *), + GFP_KERNEL); + + if (!vport->txqs) + return -ENOMEM; + + for (i = 0; i < vport->num_txq_grp; i++) { + struct idpf_txq_group *tx_grp = &vport->txq_grps[i]; + + for (j = 0; j < tx_grp->num_txq; j++, k++) { + vport->txqs[k] = tx_grp->txqs[j]; + vport->txqs[k]->idx = k; + } + } + + return 0; +} + +/** + * idpf_vport_init_num_qs - Initialize number of queues + * @vport: vport to initialize queues + * @vport_msg: data to be filled into vport + */ +void idpf_vport_init_num_qs(struct idpf_vport *vport, + struct virtchnl2_create_vport *vport_msg) +{ + struct idpf_vport_user_config_data *config_data; + u16 idx = vport->idx; + + config_data = &vport->adapter->vport_config[idx]->user_config; + vport->num_txq = le16_to_cpu(vport_msg->num_tx_q); + vport->num_rxq = le16_to_cpu(vport_msg->num_rx_q); + /* number of txqs and rxqs in config data will be zeros only in the + * driver load path and we dont update them there after + */ + if (!config_data->num_req_tx_qs && !config_data->num_req_rx_qs) { + config_data->num_req_tx_qs = le16_to_cpu(vport_msg->num_tx_q); + config_data->num_req_rx_qs = le16_to_cpu(vport_msg->num_rx_q); + } + + if (idpf_is_queue_model_split(vport->txq_model)) + vport->num_complq = le16_to_cpu(vport_msg->num_tx_complq); + if (idpf_is_queue_model_split(vport->rxq_model)) + vport->num_bufq = le16_to_cpu(vport_msg->num_rx_bufq); + + /* Adjust number of buffer queues per Rx queue group. */ + if (!idpf_is_queue_model_split(vport->rxq_model)) { + vport->num_bufqs_per_qgrp = 0; + vport->bufq_size[0] = IDPF_RX_BUF_2048; + + return; + } + + vport->num_bufqs_per_qgrp = IDPF_MAX_BUFQS_PER_RXQ_GRP; + /* Bufq[0] default buffer size is 4K + * Bufq[1] default buffer size is 2K + */ + vport->bufq_size[0] = IDPF_RX_BUF_4096; + vport->bufq_size[1] = IDPF_RX_BUF_2048; +} + +/** + * idpf_vport_calc_num_q_desc - Calculate number of queue groups + * @vport: vport to calculate q groups for + */ +void idpf_vport_calc_num_q_desc(struct idpf_vport *vport) +{ + struct idpf_vport_user_config_data *config_data; + int num_bufqs = vport->num_bufqs_per_qgrp; + u32 num_req_txq_desc, num_req_rxq_desc; + u16 idx = vport->idx; + int i; + + config_data = &vport->adapter->vport_config[idx]->user_config; + num_req_txq_desc = config_data->num_req_txq_desc; + num_req_rxq_desc = config_data->num_req_rxq_desc; + + vport->complq_desc_count = 0; + if (num_req_txq_desc) { + vport->txq_desc_count = num_req_txq_desc; + if (idpf_is_queue_model_split(vport->txq_model)) { + vport->complq_desc_count = num_req_txq_desc; + if (vport->complq_desc_count < IDPF_MIN_TXQ_COMPLQ_DESC) + vport->complq_desc_count = + IDPF_MIN_TXQ_COMPLQ_DESC; + } + } else { + vport->txq_desc_count = IDPF_DFLT_TX_Q_DESC_COUNT; + if (idpf_is_queue_model_split(vport->txq_model)) + vport->complq_desc_count = + IDPF_DFLT_TX_COMPLQ_DESC_COUNT; + } + + if (num_req_rxq_desc) + vport->rxq_desc_count = num_req_rxq_desc; + else + vport->rxq_desc_count = IDPF_DFLT_RX_Q_DESC_COUNT; + + for (i = 0; i < num_bufqs; i++) { + if (!vport->bufq_desc_count[i]) + vport->bufq_desc_count[i] = + IDPF_RX_BUFQ_DESC_COUNT(vport->rxq_desc_count, + num_bufqs); + } +} + +/** + * idpf_vport_calc_total_qs - Calculate total number of queues + * @adapter: private data struct + * @vport_idx: vport idx to retrieve vport pointer + * @vport_msg: message to fill with data + * @max_q: vport max queue info + * + * Return 0 on success, error value on failure. + */ +int idpf_vport_calc_total_qs(struct idpf_adapter *adapter, u16 vport_idx, + struct virtchnl2_create_vport *vport_msg, + struct idpf_vport_max_q *max_q) +{ + int dflt_splitq_txq_grps = 0, dflt_singleq_txqs = 0; + int dflt_splitq_rxq_grps = 0, dflt_singleq_rxqs = 0; + u16 num_req_tx_qs = 0, num_req_rx_qs = 0; + struct idpf_vport_config *vport_config; + u16 num_txq_grps, num_rxq_grps; + u32 num_qs; + + vport_config = adapter->vport_config[vport_idx]; + if (vport_config) { + num_req_tx_qs = vport_config->user_config.num_req_tx_qs; + num_req_rx_qs = vport_config->user_config.num_req_rx_qs; + } else { + int num_cpus; + + /* Restrict num of queues to cpus online as a default + * configuration to give best performance. User can always + * override to a max number of queues via ethtool. + */ + num_cpus = num_online_cpus(); + + dflt_splitq_txq_grps = min_t(int, max_q->max_txq, num_cpus); + dflt_singleq_txqs = min_t(int, max_q->max_txq, num_cpus); + dflt_splitq_rxq_grps = min_t(int, max_q->max_rxq, num_cpus); + dflt_singleq_rxqs = min_t(int, max_q->max_rxq, num_cpus); + } + + if (idpf_is_queue_model_split(le16_to_cpu(vport_msg->txq_model))) { + num_txq_grps = num_req_tx_qs ? num_req_tx_qs : dflt_splitq_txq_grps; + vport_msg->num_tx_complq = cpu_to_le16(num_txq_grps * + IDPF_COMPLQ_PER_GROUP); + vport_msg->num_tx_q = cpu_to_le16(num_txq_grps * + IDPF_DFLT_SPLITQ_TXQ_PER_GROUP); + } else { + num_txq_grps = IDPF_DFLT_SINGLEQ_TX_Q_GROUPS; + num_qs = num_txq_grps * (num_req_tx_qs ? num_req_tx_qs : + dflt_singleq_txqs); + vport_msg->num_tx_q = cpu_to_le16(num_qs); + vport_msg->num_tx_complq = 0; + } + if (idpf_is_queue_model_split(le16_to_cpu(vport_msg->rxq_model))) { + num_rxq_grps = num_req_rx_qs ? num_req_rx_qs : dflt_splitq_rxq_grps; + vport_msg->num_rx_bufq = cpu_to_le16(num_rxq_grps * + IDPF_MAX_BUFQS_PER_RXQ_GRP); + vport_msg->num_rx_q = cpu_to_le16(num_rxq_grps * + IDPF_DFLT_SPLITQ_RXQ_PER_GROUP); + } else { + num_rxq_grps = IDPF_DFLT_SINGLEQ_RX_Q_GROUPS; + num_qs = num_rxq_grps * (num_req_rx_qs ? num_req_rx_qs : + dflt_singleq_rxqs); + vport_msg->num_rx_q = cpu_to_le16(num_qs); + vport_msg->num_rx_bufq = 0; + } + + return 0; +} + +/** + * idpf_vport_calc_num_q_groups - Calculate number of queue groups + * @vport: vport to calculate q groups for + */ +void idpf_vport_calc_num_q_groups(struct idpf_vport *vport) +{ + if (idpf_is_queue_model_split(vport->txq_model)) + vport->num_txq_grp = vport->num_txq; + else + vport->num_txq_grp = IDPF_DFLT_SINGLEQ_TX_Q_GROUPS; + + if (idpf_is_queue_model_split(vport->rxq_model)) + vport->num_rxq_grp = vport->num_rxq; + else + vport->num_rxq_grp = IDPF_DFLT_SINGLEQ_RX_Q_GROUPS; +} + +/** + * idpf_vport_calc_numq_per_grp - Calculate number of queues per group + * @vport: vport to calculate queues for + * @num_txq: return parameter for number of TX queues + * @num_rxq: return parameter for number of RX queues + */ +static void idpf_vport_calc_numq_per_grp(struct idpf_vport *vport, + u16 *num_txq, u16 *num_rxq) +{ + if (idpf_is_queue_model_split(vport->txq_model)) + *num_txq = IDPF_DFLT_SPLITQ_TXQ_PER_GROUP; + else + *num_txq = vport->num_txq; + + if (idpf_is_queue_model_split(vport->rxq_model)) + *num_rxq = IDPF_DFLT_SPLITQ_RXQ_PER_GROUP; + else + *num_rxq = vport->num_rxq; +} + +/** + * idpf_rxq_set_descids - set the descids supported by this queue + * @vport: virtual port data structure + * @q: rx queue for which descids are set + * + */ +static void idpf_rxq_set_descids(struct idpf_vport *vport, struct idpf_queue *q) +{ + if (vport->rxq_model == VIRTCHNL2_QUEUE_MODEL_SPLIT) { + q->rxdids = VIRTCHNL2_RXDID_2_FLEX_SPLITQ_M; + } else { + if (vport->base_rxd) + q->rxdids = VIRTCHNL2_RXDID_1_32B_BASE_M; + else + q->rxdids = VIRTCHNL2_RXDID_2_FLEX_SQ_NIC_M; + } +} + +/** + * idpf_txq_group_alloc - Allocate all txq group resources + * @vport: vport to allocate txq groups for + * @num_txq: number of txqs to allocate for each group + * + * Returns 0 on success, negative on failure + */ +static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq) +{ + bool flow_sch_en; + int err, i; + + vport->txq_grps = kcalloc(vport->num_txq_grp, + sizeof(*vport->txq_grps), GFP_KERNEL); + if (!vport->txq_grps) + return -ENOMEM; + + flow_sch_en = !idpf_is_cap_ena(vport->adapter, IDPF_OTHER_CAPS, + VIRTCHNL2_CAP_SPLITQ_QSCHED); + + for (i = 0; i < vport->num_txq_grp; i++) { + struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i]; + struct idpf_adapter *adapter = vport->adapter; + int j; + + tx_qgrp->vport = vport; + tx_qgrp->num_txq = num_txq; + + for (j = 0; j < tx_qgrp->num_txq; j++) { + tx_qgrp->txqs[j] = kzalloc(sizeof(*tx_qgrp->txqs[j]), + GFP_KERNEL); + if (!tx_qgrp->txqs[j]) { + err = -ENOMEM; + goto err_alloc; + } + } + + for (j = 0; j < tx_qgrp->num_txq; j++) { + struct idpf_queue *q = tx_qgrp->txqs[j]; + + q->dev = &adapter->pdev->dev; + q->desc_count = vport->txq_desc_count; + q->tx_max_bufs = idpf_get_max_tx_bufs(adapter); + q->tx_min_pkt_len = idpf_get_min_tx_pkt_len(adapter); + q->vport = vport; + q->txq_grp = tx_qgrp; + hash_init(q->sched_buf_hash); + + if (flow_sch_en) + set_bit(__IDPF_Q_FLOW_SCH_EN, q->flags); + } + + if (!idpf_is_queue_model_split(vport->txq_model)) + continue; + + tx_qgrp->complq = kcalloc(IDPF_COMPLQ_PER_GROUP, + sizeof(*tx_qgrp->complq), + GFP_KERNEL); + if (!tx_qgrp->complq) { + err = -ENOMEM; + goto err_alloc; + } + + tx_qgrp->complq->dev = &adapter->pdev->dev; + tx_qgrp->complq->desc_count = vport->complq_desc_count; + tx_qgrp->complq->vport = vport; + tx_qgrp->complq->txq_grp = tx_qgrp; + + if (flow_sch_en) + __set_bit(__IDPF_Q_FLOW_SCH_EN, tx_qgrp->complq->flags); + } + + return 0; + +err_alloc: + idpf_txq_group_rel(vport); + + return err; +} + +/** + * idpf_rxq_group_alloc - Allocate all rxq group resources + * @vport: vport to allocate rxq groups for + * @num_rxq: number of rxqs to allocate for each group + * + * Returns 0 on success, negative on failure + */ +static int idpf_rxq_group_alloc(struct idpf_vport *vport, u16 num_rxq) +{ + struct idpf_adapter *adapter = vport->adapter; + struct idpf_queue *q; + int i, k, err = 0; + + vport->rxq_grps = kcalloc(vport->num_rxq_grp, + sizeof(struct idpf_rxq_group), GFP_KERNEL); + if (!vport->rxq_grps) + return -ENOMEM; + + for (i = 0; i < vport->num_rxq_grp; i++) { + struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i]; + int j; + + rx_qgrp->vport = vport; + if (!idpf_is_queue_model_split(vport->rxq_model)) { + rx_qgrp->singleq.num_rxq = num_rxq; + for (j = 0; j < num_rxq; j++) { + rx_qgrp->singleq.rxqs[j] = + kzalloc(sizeof(*rx_qgrp->singleq.rxqs[j]), + GFP_KERNEL); + if (!rx_qgrp->singleq.rxqs[j]) { + err = -ENOMEM; + goto err_alloc; + } + } + goto skip_splitq_rx_init; + } + rx_qgrp->splitq.num_rxq_sets = num_rxq; + + for (j = 0; j < num_rxq; j++) { + rx_qgrp->splitq.rxq_sets[j] = + kzalloc(sizeof(struct idpf_rxq_set), + GFP_KERNEL); + if (!rx_qgrp->splitq.rxq_sets[j]) { + err = -ENOMEM; + goto err_alloc; + } + } + + rx_qgrp->splitq.bufq_sets = kcalloc(vport->num_bufqs_per_qgrp, + sizeof(struct idpf_bufq_set), + GFP_KERNEL); + if (!rx_qgrp->splitq.bufq_sets) { + err = -ENOMEM; + goto err_alloc; + } + + for (j = 0; j < vport->num_bufqs_per_qgrp; j++) { + struct idpf_bufq_set *bufq_set = + &rx_qgrp->splitq.bufq_sets[j]; + int swq_size = sizeof(struct idpf_sw_queue); + + q = &rx_qgrp->splitq.bufq_sets[j].bufq; + q->dev = &adapter->pdev->dev; + q->desc_count = vport->bufq_desc_count[j]; + q->vport = vport; + q->rxq_grp = rx_qgrp; + q->idx = j; + q->rx_buf_size = vport->bufq_size[j]; + q->rx_buffer_low_watermark = IDPF_LOW_WATERMARK; + q->rx_buf_stride = IDPF_RX_BUF_STRIDE; + if (idpf_is_cap_ena_all(adapter, IDPF_HSPLIT_CAPS, + IDPF_CAP_HSPLIT) && + idpf_is_queue_model_split(vport->rxq_model)) { + q->rx_hsplit_en = true; + q->rx_hbuf_size = IDPF_HDR_BUF_SIZE; + } + + bufq_set->num_refillqs = num_rxq; + bufq_set->refillqs = kcalloc(num_rxq, swq_size, + GFP_KERNEL); + if (!bufq_set->refillqs) { + err = -ENOMEM; + goto err_alloc; + } + for (k = 0; k < bufq_set->num_refillqs; k++) { + struct idpf_sw_queue *refillq = + &bufq_set->refillqs[k]; + + refillq->dev = &vport->adapter->pdev->dev; + refillq->desc_count = + vport->bufq_desc_count[j]; + set_bit(__IDPF_Q_GEN_CHK, refillq->flags); + set_bit(__IDPF_RFLQ_GEN_CHK, refillq->flags); + refillq->ring = kcalloc(refillq->desc_count, + sizeof(u16), + GFP_KERNEL); + if (!refillq->ring) { + err = -ENOMEM; + goto err_alloc; + } + } + } + +skip_splitq_rx_init: + for (j = 0; j < num_rxq; j++) { + if (!idpf_is_queue_model_split(vport->rxq_model)) { + q = rx_qgrp->singleq.rxqs[j]; + goto setup_rxq; + } + q = &rx_qgrp->splitq.rxq_sets[j]->rxq; + rx_qgrp->splitq.rxq_sets[j]->refillq0 = + &rx_qgrp->splitq.bufq_sets[0].refillqs[j]; + if (vport->num_bufqs_per_qgrp > IDPF_SINGLE_BUFQ_PER_RXQ_GRP) + rx_qgrp->splitq.rxq_sets[j]->refillq1 = + &rx_qgrp->splitq.bufq_sets[1].refillqs[j]; + + if (idpf_is_cap_ena_all(adapter, IDPF_HSPLIT_CAPS, + IDPF_CAP_HSPLIT) && + idpf_is_queue_model_split(vport->rxq_model)) { + q->rx_hsplit_en = true; + q->rx_hbuf_size = IDPF_HDR_BUF_SIZE; + } + +setup_rxq: + q->dev = &adapter->pdev->dev; + q->desc_count = vport->rxq_desc_count; + q->vport = vport; + q->rxq_grp = rx_qgrp; + q->idx = (i * num_rxq) + j; + /* In splitq mode, RXQ buffer size should be + * set to that of the first buffer queue + * associated with this RXQ + */ + q->rx_buf_size = vport->bufq_size[0]; + q->rx_buffer_low_watermark = IDPF_LOW_WATERMARK; + q->rx_max_pkt_size = vport->netdev->mtu + + IDPF_PACKET_HDR_PAD; + idpf_rxq_set_descids(vport, q); + } + } + +err_alloc: + if (err) + idpf_rxq_group_rel(vport); + + return err; +} + +/** + * idpf_vport_queue_grp_alloc_all - Allocate all queue groups/resources + * @vport: vport with qgrps to allocate + * + * Returns 0 on success, negative on failure + */ +static int idpf_vport_queue_grp_alloc_all(struct idpf_vport *vport) +{ + u16 num_txq, num_rxq; + int err; + + idpf_vport_calc_numq_per_grp(vport, &num_txq, &num_rxq); + + err = idpf_txq_group_alloc(vport, num_txq); + if (err) + goto err_out; + + err = idpf_rxq_group_alloc(vport, num_rxq); + if (err) + goto err_out; + + return 0; + +err_out: + idpf_vport_queue_grp_rel_all(vport); + + return err; +} + +/** + * idpf_vport_queues_alloc - Allocate memory for all queues + * @vport: virtual port + * + * Allocate memory for queues associated with a vport. Returns 0 on success, + * negative on failure. + */ +int idpf_vport_queues_alloc(struct idpf_vport *vport) +{ + int err; + + err = idpf_vport_queue_grp_alloc_all(vport); + if (err) + goto err_out; + + err = idpf_tx_desc_alloc_all(vport); + if (err) + goto err_out; + + err = idpf_rx_desc_alloc_all(vport); + if (err) + goto err_out; + + err = idpf_vport_init_fast_path_txqs(vport); + if (err) + goto err_out; + + return 0; + +err_out: + idpf_vport_queues_rel(vport); + + return err; +} + +/** + * idpf_tx_handle_sw_marker - Handle queue marker packet + * @tx_q: tx queue to handle software marker + */ +static void idpf_tx_handle_sw_marker(struct idpf_queue *tx_q) +{ + struct idpf_vport *vport = tx_q->vport; + int i; + + clear_bit(__IDPF_Q_SW_MARKER, tx_q->flags); + /* Hardware must write marker packets to all queues associated with + * completion queues. So check if all queues received marker packets + */ + for (i = 0; i < vport->num_txq; i++) + /* If we're still waiting on any other TXQ marker completions, + * just return now since we cannot wake up the marker_wq yet. + */ + if (test_bit(__IDPF_Q_SW_MARKER, vport->txqs[i]->flags)) + return; + + /* Drain complete */ + set_bit(IDPF_VPORT_SW_MARKER, vport->flags); + wake_up(&vport->sw_marker_wq); +} + +/** + * idpf_tx_splitq_clean_hdr - Clean TX buffer resources for header portion of + * packet + * @tx_q: tx queue to clean buffer from + * @tx_buf: buffer to be cleaned + * @cleaned: pointer to stats struct to track cleaned packets/bytes + * @napi_budget: Used to determine if we are in netpoll + */ +static void idpf_tx_splitq_clean_hdr(struct idpf_queue *tx_q, + struct idpf_tx_buf *tx_buf, + struct idpf_cleaned_stats *cleaned, + int napi_budget) +{ + napi_consume_skb(tx_buf->skb, napi_budget); + + if (dma_unmap_len(tx_buf, len)) { + dma_unmap_single(tx_q->dev, + dma_unmap_addr(tx_buf, dma), + dma_unmap_len(tx_buf, len), + DMA_TO_DEVICE); + + dma_unmap_len_set(tx_buf, len, 0); + } + + /* clear tx_buf data */ + tx_buf->skb = NULL; + + cleaned->bytes += tx_buf->bytecount; + cleaned->packets += tx_buf->gso_segs; +} + +/** + * idpf_tx_clean_stashed_bufs - clean bufs that were stored for + * out of order completions + * @txq: queue to clean + * @compl_tag: completion tag of packet to clean (from completion descriptor) + * @cleaned: pointer to stats struct to track cleaned packets/bytes + * @budget: Used to determine if we are in netpoll + */ +static void idpf_tx_clean_stashed_bufs(struct idpf_queue *txq, u16 compl_tag, + struct idpf_cleaned_stats *cleaned, + int budget) +{ + struct idpf_tx_stash *stash; + struct hlist_node *tmp_buf; + + /* Buffer completion */ + hash_for_each_possible_safe(txq->sched_buf_hash, stash, tmp_buf, + hlist, compl_tag) { + if (unlikely(stash->buf.compl_tag != (int)compl_tag)) + continue; + + if (stash->buf.skb) { + idpf_tx_splitq_clean_hdr(txq, &stash->buf, cleaned, + budget); + } else if (dma_unmap_len(&stash->buf, len)) { + dma_unmap_page(txq->dev, + dma_unmap_addr(&stash->buf, dma), + dma_unmap_len(&stash->buf, len), + DMA_TO_DEVICE); + dma_unmap_len_set(&stash->buf, len, 0); + } + + /* Push shadow buf back onto stack */ + idpf_buf_lifo_push(&txq->buf_stack, stash); + + hash_del(&stash->hlist); + } +} + +/** + * idpf_stash_flow_sch_buffers - store buffer parameters info to be freed at a + * later time (only relevant for flow scheduling mode) + * @txq: Tx queue to clean + * @tx_buf: buffer to store + */ +static int idpf_stash_flow_sch_buffers(struct idpf_queue *txq, + struct idpf_tx_buf *tx_buf) +{ + struct idpf_tx_stash *stash; + + if (unlikely(!dma_unmap_addr(tx_buf, dma) && + !dma_unmap_len(tx_buf, len))) + return 0; + + stash = idpf_buf_lifo_pop(&txq->buf_stack); + if (unlikely(!stash)) { + net_err_ratelimited("%s: No out-of-order TX buffers left!\n", + txq->vport->netdev->name); + + return -ENOMEM; + } + + /* Store buffer params in shadow buffer */ + stash->buf.skb = tx_buf->skb; + stash->buf.bytecount = tx_buf->bytecount; + stash->buf.gso_segs = tx_buf->gso_segs; + dma_unmap_addr_set(&stash->buf, dma, dma_unmap_addr(tx_buf, dma)); + dma_unmap_len_set(&stash->buf, len, dma_unmap_len(tx_buf, len)); + stash->buf.compl_tag = tx_buf->compl_tag; + + /* Add buffer to buf_hash table to be freed later */ + hash_add(txq->sched_buf_hash, &stash->hlist, stash->buf.compl_tag); + + memset(tx_buf, 0, sizeof(struct idpf_tx_buf)); + + /* Reinitialize buf_id portion of tag */ + tx_buf->compl_tag = IDPF_SPLITQ_TX_INVAL_COMPL_TAG; + + return 0; +} + +#define idpf_tx_splitq_clean_bump_ntc(txq, ntc, desc, buf) \ +do { \ + (ntc)++; \ + if (unlikely(!(ntc))) { \ + ntc -= (txq)->desc_count; \ + buf = (txq)->tx_buf; \ + desc = IDPF_FLEX_TX_DESC(txq, 0); \ + } else { \ + (buf)++; \ + (desc)++; \ + } \ +} while (0) + +/** + * idpf_tx_splitq_clean - Reclaim resources from buffer queue + * @tx_q: Tx queue to clean + * @end: queue index until which it should be cleaned + * @napi_budget: Used to determine if we are in netpoll + * @cleaned: pointer to stats struct to track cleaned packets/bytes + * @descs_only: true if queue is using flow-based scheduling and should + * not clean buffers at this time + * + * Cleans the queue descriptor ring. If the queue is using queue-based + * scheduling, the buffers will be cleaned as well. If the queue is using + * flow-based scheduling, only the descriptors are cleaned at this time. + * Separate packet completion events will be reported on the completion queue, + * and the buffers will be cleaned separately. The stats are not updated from + * this function when using flow-based scheduling. + */ +static void idpf_tx_splitq_clean(struct idpf_queue *tx_q, u16 end, + int napi_budget, + struct idpf_cleaned_stats *cleaned, + bool descs_only) +{ + union idpf_tx_flex_desc *next_pending_desc = NULL; + union idpf_tx_flex_desc *tx_desc; + s16 ntc = tx_q->next_to_clean; + struct idpf_tx_buf *tx_buf; + + tx_desc = IDPF_FLEX_TX_DESC(tx_q, ntc); + next_pending_desc = IDPF_FLEX_TX_DESC(tx_q, end); + tx_buf = &tx_q->tx_buf[ntc]; + ntc -= tx_q->desc_count; + + while (tx_desc != next_pending_desc) { + union idpf_tx_flex_desc *eop_desc; + + /* If this entry in the ring was used as a context descriptor, + * it's corresponding entry in the buffer ring will have an + * invalid completion tag since no buffer was used. We can + * skip this descriptor since there is no buffer to clean. + */ + if (unlikely(tx_buf->compl_tag == IDPF_SPLITQ_TX_INVAL_COMPL_TAG)) + goto fetch_next_txq_desc; + + eop_desc = (union idpf_tx_flex_desc *)tx_buf->next_to_watch; + + /* clear next_to_watch to prevent false hangs */ + tx_buf->next_to_watch = NULL; + + if (descs_only) { + if (idpf_stash_flow_sch_buffers(tx_q, tx_buf)) + goto tx_splitq_clean_out; + + while (tx_desc != eop_desc) { + idpf_tx_splitq_clean_bump_ntc(tx_q, ntc, + tx_desc, tx_buf); + + if (dma_unmap_len(tx_buf, len)) { + if (idpf_stash_flow_sch_buffers(tx_q, + tx_buf)) + goto tx_splitq_clean_out; + } + } + } else { + idpf_tx_splitq_clean_hdr(tx_q, tx_buf, cleaned, + napi_budget); + + /* unmap remaining buffers */ + while (tx_desc != eop_desc) { + idpf_tx_splitq_clean_bump_ntc(tx_q, ntc, + tx_desc, tx_buf); + + /* unmap any remaining paged data */ + if (dma_unmap_len(tx_buf, len)) { + dma_unmap_page(tx_q->dev, + dma_unmap_addr(tx_buf, dma), + dma_unmap_len(tx_buf, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buf, len, 0); + } + } + } + +fetch_next_txq_desc: + idpf_tx_splitq_clean_bump_ntc(tx_q, ntc, tx_desc, tx_buf); + } + +tx_splitq_clean_out: + ntc += tx_q->desc_count; + tx_q->next_to_clean = ntc; +} + +#define idpf_tx_clean_buf_ring_bump_ntc(txq, ntc, buf) \ +do { \ + (buf)++; \ + (ntc)++; \ + if (unlikely((ntc) == (txq)->desc_count)) { \ + buf = (txq)->tx_buf; \ + ntc = 0; \ + } \ +} while (0) + +/** + * idpf_tx_clean_buf_ring - clean flow scheduling TX queue buffers + * @txq: queue to clean + * @compl_tag: completion tag of packet to clean (from completion descriptor) + * @cleaned: pointer to stats struct to track cleaned packets/bytes + * @budget: Used to determine if we are in netpoll + * + * Cleans all buffers associated with the input completion tag either from the + * TX buffer ring or from the hash table if the buffers were previously + * stashed. Returns the byte/segment count for the cleaned packet associated + * this completion tag. + */ +static bool idpf_tx_clean_buf_ring(struct idpf_queue *txq, u16 compl_tag, + struct idpf_cleaned_stats *cleaned, + int budget) +{ + u16 idx = compl_tag & txq->compl_tag_bufid_m; + struct idpf_tx_buf *tx_buf = NULL; + u16 ntc = txq->next_to_clean; + u16 num_descs_cleaned = 0; + u16 orig_idx = idx; + + tx_buf = &txq->tx_buf[idx]; + + while (tx_buf->compl_tag == (int)compl_tag) { + if (tx_buf->skb) { + idpf_tx_splitq_clean_hdr(txq, tx_buf, cleaned, budget); + } else if (dma_unmap_len(tx_buf, len)) { + dma_unmap_page(txq->dev, + dma_unmap_addr(tx_buf, dma), + dma_unmap_len(tx_buf, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buf, len, 0); + } + + memset(tx_buf, 0, sizeof(struct idpf_tx_buf)); + tx_buf->compl_tag = IDPF_SPLITQ_TX_INVAL_COMPL_TAG; + + num_descs_cleaned++; + idpf_tx_clean_buf_ring_bump_ntc(txq, idx, tx_buf); + } + + /* If we didn't clean anything on the ring for this completion, there's + * nothing more to do. + */ + if (unlikely(!num_descs_cleaned)) + return false; + + /* Otherwise, if we did clean a packet on the ring directly, it's safe + * to assume that the descriptors starting from the original + * next_to_clean up until the previously cleaned packet can be reused. + * Therefore, we will go back in the ring and stash any buffers still + * in the ring into the hash table to be cleaned later. + */ + tx_buf = &txq->tx_buf[ntc]; + while (tx_buf != &txq->tx_buf[orig_idx]) { + idpf_stash_flow_sch_buffers(txq, tx_buf); + idpf_tx_clean_buf_ring_bump_ntc(txq, ntc, tx_buf); + } + + /* Finally, update next_to_clean to reflect the work that was just done + * on the ring, if any. If the packet was only cleaned from the hash + * table, the ring will not be impacted, therefore we should not touch + * next_to_clean. The updated idx is used here + */ + txq->next_to_clean = idx; + + return true; +} + +/** + * idpf_tx_handle_rs_completion - clean a single packet and all of its buffers + * whether on the buffer ring or in the hash table + * @txq: Tx ring to clean + * @desc: pointer to completion queue descriptor to extract completion + * information from + * @cleaned: pointer to stats struct to track cleaned packets/bytes + * @budget: Used to determine if we are in netpoll + * + * Returns bytes/packets cleaned + */ +static void idpf_tx_handle_rs_completion(struct idpf_queue *txq, + struct idpf_splitq_tx_compl_desc *desc, + struct idpf_cleaned_stats *cleaned, + int budget) +{ + u16 compl_tag; + + if (!test_bit(__IDPF_Q_FLOW_SCH_EN, txq->flags)) { + u16 head = le16_to_cpu(desc->q_head_compl_tag.q_head); + + return idpf_tx_splitq_clean(txq, head, budget, cleaned, false); + } + + compl_tag = le16_to_cpu(desc->q_head_compl_tag.compl_tag); + + /* If we didn't clean anything on the ring, this packet must be + * in the hash table. Go clean it there. + */ + if (!idpf_tx_clean_buf_ring(txq, compl_tag, cleaned, budget)) + idpf_tx_clean_stashed_bufs(txq, compl_tag, cleaned, budget); +} + +/** + * idpf_tx_clean_complq - Reclaim resources on completion queue + * @complq: Tx ring to clean + * @budget: Used to determine if we are in netpoll + * @cleaned: returns number of packets cleaned + * + * Returns true if there's any budget left (e.g. the clean is finished) + */ +static bool idpf_tx_clean_complq(struct idpf_queue *complq, int budget, + int *cleaned) +{ + struct idpf_splitq_tx_compl_desc *tx_desc; + struct idpf_vport *vport = complq->vport; + s16 ntc = complq->next_to_clean; + struct idpf_netdev_priv *np; + unsigned int complq_budget; + bool complq_ok = true; + int i; + + complq_budget = vport->compln_clean_budget; + tx_desc = IDPF_SPLITQ_TX_COMPLQ_DESC(complq, ntc); + ntc -= complq->desc_count; + + do { + struct idpf_cleaned_stats cleaned_stats = { }; + struct idpf_queue *tx_q; + int rel_tx_qid; + u16 hw_head; + u8 ctype; /* completion type */ + u16 gen; + + /* if the descriptor isn't done, no work yet to do */ + gen = (le16_to_cpu(tx_desc->qid_comptype_gen) & + IDPF_TXD_COMPLQ_GEN_M) >> IDPF_TXD_COMPLQ_GEN_S; + if (test_bit(__IDPF_Q_GEN_CHK, complq->flags) != gen) + break; + + /* Find necessary info of TX queue to clean buffers */ + rel_tx_qid = (le16_to_cpu(tx_desc->qid_comptype_gen) & + IDPF_TXD_COMPLQ_QID_M) >> IDPF_TXD_COMPLQ_QID_S; + if (rel_tx_qid >= complq->txq_grp->num_txq || + !complq->txq_grp->txqs[rel_tx_qid]) { + dev_err(&complq->vport->adapter->pdev->dev, + "TxQ not found\n"); + goto fetch_next_desc; + } + tx_q = complq->txq_grp->txqs[rel_tx_qid]; + + /* Determine completion type */ + ctype = (le16_to_cpu(tx_desc->qid_comptype_gen) & + IDPF_TXD_COMPLQ_COMPL_TYPE_M) >> + IDPF_TXD_COMPLQ_COMPL_TYPE_S; + switch (ctype) { + case IDPF_TXD_COMPLT_RE: + hw_head = le16_to_cpu(tx_desc->q_head_compl_tag.q_head); + + idpf_tx_splitq_clean(tx_q, hw_head, budget, + &cleaned_stats, true); + break; + case IDPF_TXD_COMPLT_RS: + idpf_tx_handle_rs_completion(tx_q, tx_desc, + &cleaned_stats, budget); + break; + case IDPF_TXD_COMPLT_SW_MARKER: + idpf_tx_handle_sw_marker(tx_q); + break; + default: + dev_err(&tx_q->vport->adapter->pdev->dev, + "Unknown TX completion type: %d\n", + ctype); + goto fetch_next_desc; + } + + u64_stats_update_begin(&tx_q->stats_sync); + u64_stats_add(&tx_q->q_stats.tx.packets, cleaned_stats.packets); + u64_stats_add(&tx_q->q_stats.tx.bytes, cleaned_stats.bytes); + tx_q->cleaned_pkts += cleaned_stats.packets; + tx_q->cleaned_bytes += cleaned_stats.bytes; + complq->num_completions++; + u64_stats_update_end(&tx_q->stats_sync); + +fetch_next_desc: + tx_desc++; + ntc++; + if (unlikely(!ntc)) { + ntc -= complq->desc_count; + tx_desc = IDPF_SPLITQ_TX_COMPLQ_DESC(complq, 0); + change_bit(__IDPF_Q_GEN_CHK, complq->flags); + } + + prefetch(tx_desc); + + /* update budget accounting */ + complq_budget--; + } while (likely(complq_budget)); + + /* Store the state of the complq to be used later in deciding if a + * TXQ can be started again + */ + if (unlikely(IDPF_TX_COMPLQ_PENDING(complq->txq_grp) > + IDPF_TX_COMPLQ_OVERFLOW_THRESH(complq))) + complq_ok = false; + + np = netdev_priv(complq->vport->netdev); + for (i = 0; i < complq->txq_grp->num_txq; ++i) { + struct idpf_queue *tx_q = complq->txq_grp->txqs[i]; + struct netdev_queue *nq; + bool dont_wake; + + /* We didn't clean anything on this queue, move along */ + if (!tx_q->cleaned_bytes) + continue; + + *cleaned += tx_q->cleaned_pkts; + + /* Update BQL */ + nq = netdev_get_tx_queue(tx_q->vport->netdev, tx_q->idx); + + dont_wake = !complq_ok || IDPF_TX_BUF_RSV_LOW(tx_q) || + np->state != __IDPF_VPORT_UP || + !netif_carrier_ok(tx_q->vport->netdev); + /* Check if the TXQ needs to and can be restarted */ + __netif_txq_completed_wake(nq, tx_q->cleaned_pkts, tx_q->cleaned_bytes, + IDPF_DESC_UNUSED(tx_q), IDPF_TX_WAKE_THRESH, + dont_wake); + + /* Reset cleaned stats for the next time this queue is + * cleaned + */ + tx_q->cleaned_bytes = 0; + tx_q->cleaned_pkts = 0; + } + + ntc += complq->desc_count; + complq->next_to_clean = ntc; + + return !!complq_budget; +} + +/** + * idpf_tx_splitq_build_ctb - populate command tag and size for queue + * based scheduling descriptors + * @desc: descriptor to populate + * @params: pointer to tx params struct + * @td_cmd: command to be filled in desc + * @size: size of buffer + */ +void idpf_tx_splitq_build_ctb(union idpf_tx_flex_desc *desc, + struct idpf_tx_splitq_params *params, + u16 td_cmd, u16 size) +{ + desc->q.qw1.cmd_dtype = + cpu_to_le16(params->dtype & IDPF_FLEX_TXD_QW1_DTYPE_M); + desc->q.qw1.cmd_dtype |= + cpu_to_le16((td_cmd << IDPF_FLEX_TXD_QW1_CMD_S) & + IDPF_FLEX_TXD_QW1_CMD_M); + desc->q.qw1.buf_size = cpu_to_le16((u16)size); + desc->q.qw1.l2tags.l2tag1 = cpu_to_le16(params->td_tag); +} + +/** + * idpf_tx_splitq_build_flow_desc - populate command tag and size for flow + * scheduling descriptors + * @desc: descriptor to populate + * @params: pointer to tx params struct + * @td_cmd: command to be filled in desc + * @size: size of buffer + */ +void idpf_tx_splitq_build_flow_desc(union idpf_tx_flex_desc *desc, + struct idpf_tx_splitq_params *params, + u16 td_cmd, u16 size) +{ + desc->flow.qw1.cmd_dtype = (u16)params->dtype | td_cmd; + desc->flow.qw1.rxr_bufsize = cpu_to_le16((u16)size); + desc->flow.qw1.compl_tag = cpu_to_le16(params->compl_tag); +} + +/** + * idpf_tx_maybe_stop_common - 1st level check for common Tx stop conditions + * @tx_q: the queue to be checked + * @size: number of descriptors we want to assure is available + * + * Returns 0 if stop is not needed + */ +int idpf_tx_maybe_stop_common(struct idpf_queue *tx_q, unsigned int size) +{ + struct netdev_queue *nq; + + if (likely(IDPF_DESC_UNUSED(tx_q) >= size)) + return 0; + + u64_stats_update_begin(&tx_q->stats_sync); + u64_stats_inc(&tx_q->q_stats.tx.q_busy); + u64_stats_update_end(&tx_q->stats_sync); + + nq = netdev_get_tx_queue(tx_q->vport->netdev, tx_q->idx); + + return netif_txq_maybe_stop(nq, IDPF_DESC_UNUSED(tx_q), size, size); +} + +/** + * idpf_tx_maybe_stop_splitq - 1st level check for Tx splitq stop conditions + * @tx_q: the queue to be checked + * @descs_needed: number of descriptors required for this packet + * + * Returns 0 if stop is not needed + */ +static int idpf_tx_maybe_stop_splitq(struct idpf_queue *tx_q, + unsigned int descs_needed) +{ + if (idpf_tx_maybe_stop_common(tx_q, descs_needed)) + goto splitq_stop; + + /* If there are too many outstanding completions expected on the + * completion queue, stop the TX queue to give the device some time to + * catch up + */ + if (unlikely(IDPF_TX_COMPLQ_PENDING(tx_q->txq_grp) > + IDPF_TX_COMPLQ_OVERFLOW_THRESH(tx_q->txq_grp->complq))) + goto splitq_stop; + + /* Also check for available book keeping buffers; if we are low, stop + * the queue to wait for more completions + */ + if (unlikely(IDPF_TX_BUF_RSV_LOW(tx_q))) + goto splitq_stop; + + return 0; + +splitq_stop: + u64_stats_update_begin(&tx_q->stats_sync); + u64_stats_inc(&tx_q->q_stats.tx.q_busy); + u64_stats_update_end(&tx_q->stats_sync); + netif_stop_subqueue(tx_q->vport->netdev, tx_q->idx); + + return -EBUSY; +} + +/** + * idpf_tx_buf_hw_update - Store the new tail value + * @tx_q: queue to bump + * @val: new tail index + * @xmit_more: more skb's pending + * + * The naming here is special in that 'hw' signals that this function is about + * to do a register write to update our queue status. We know this can only + * mean tail here as HW should be owning head for TX. + */ +void idpf_tx_buf_hw_update(struct idpf_queue *tx_q, u32 val, + bool xmit_more) +{ + struct netdev_queue *nq; + + nq = netdev_get_tx_queue(tx_q->vport->netdev, tx_q->idx); + tx_q->next_to_use = val; + + idpf_tx_maybe_stop_common(tx_q, IDPF_TX_DESC_NEEDED); + + /* 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(); + + /* notify HW of packet */ + if (netif_xmit_stopped(nq) || !xmit_more) + writel(val, tx_q->tail); +} + +/** + * idpf_tx_desc_count_required - calculate number of Tx descriptors needed + * @txq: queue to send buffer on + * @skb: send buffer + * + * Returns number of data descriptors needed for this skb. + */ +unsigned int idpf_tx_desc_count_required(struct idpf_queue *txq, + struct sk_buff *skb) +{ + const struct skb_shared_info *shinfo; + unsigned int count = 0, i; + + count += !!skb_headlen(skb); + + if (!skb_is_nonlinear(skb)) + return count; + + shinfo = skb_shinfo(skb); + for (i = 0; i < shinfo->nr_frags; i++) { + unsigned int size; + + size = skb_frag_size(&shinfo->frags[i]); + + /* We only need to use the idpf_size_to_txd_count check if the + * fragment is going to span multiple descriptors, + * i.e. size >= 16K. + */ + if (size >= SZ_16K) + count += idpf_size_to_txd_count(size); + else + count++; + } + + if (idpf_chk_linearize(skb, txq->tx_max_bufs, count)) { + if (__skb_linearize(skb)) + return 0; + + count = idpf_size_to_txd_count(skb->len); + u64_stats_update_begin(&txq->stats_sync); + u64_stats_inc(&txq->q_stats.tx.linearize); + u64_stats_update_end(&txq->stats_sync); + } + + return count; +} + +/** + * idpf_tx_dma_map_error - handle TX DMA map errors + * @txq: queue to send buffer on + * @skb: send buffer + * @first: original first buffer info buffer for packet + * @idx: starting point on ring to unwind + */ +void idpf_tx_dma_map_error(struct idpf_queue *txq, struct sk_buff *skb, + struct idpf_tx_buf *first, u16 idx) +{ + u64_stats_update_begin(&txq->stats_sync); + u64_stats_inc(&txq->q_stats.tx.dma_map_errs); + u64_stats_update_end(&txq->stats_sync); + + /* clear dma mappings for failed tx_buf map */ + for (;;) { + struct idpf_tx_buf *tx_buf; + + tx_buf = &txq->tx_buf[idx]; + idpf_tx_buf_rel(txq, tx_buf); + if (tx_buf == first) + break; + if (idx == 0) + idx = txq->desc_count; + idx--; + } + + if (skb_is_gso(skb)) { + union idpf_tx_flex_desc *tx_desc; + + /* If we failed a DMA mapping for a TSO packet, we will have + * used one additional descriptor for a context + * descriptor. Reset that here. + */ + tx_desc = IDPF_FLEX_TX_DESC(txq, idx); + memset(tx_desc, 0, sizeof(struct idpf_flex_tx_ctx_desc)); + if (idx == 0) + idx = txq->desc_count; + idx--; + } + + /* Update tail in case netdev_xmit_more was previously true */ + idpf_tx_buf_hw_update(txq, idx, false); +} + +/** + * idpf_tx_splitq_bump_ntu - adjust NTU and generation + * @txq: the tx ring to wrap + * @ntu: ring index to bump + */ +static unsigned int idpf_tx_splitq_bump_ntu(struct idpf_queue *txq, u16 ntu) +{ + ntu++; + + if (ntu == txq->desc_count) { + ntu = 0; + txq->compl_tag_cur_gen = IDPF_TX_ADJ_COMPL_TAG_GEN(txq); + } + + return ntu; +} + +/** + * idpf_tx_splitq_map - Build the Tx flex descriptor + * @tx_q: queue to send buffer on + * @params: pointer to splitq params struct + * @first: first buffer info buffer to use + * + * This function loops over the skb data pointed to by *first + * and gets a physical address for each memory location and programs + * it and the length into the transmit flex descriptor. + */ +static void idpf_tx_splitq_map(struct idpf_queue *tx_q, + struct idpf_tx_splitq_params *params, + struct idpf_tx_buf *first) +{ + union idpf_tx_flex_desc *tx_desc; + unsigned int data_len, size; + struct idpf_tx_buf *tx_buf; + u16 i = tx_q->next_to_use; + struct netdev_queue *nq; + struct sk_buff *skb; + skb_frag_t *frag; + u16 td_cmd = 0; + dma_addr_t dma; + + skb = first->skb; + + td_cmd = params->offload.td_cmd; + + data_len = skb->data_len; + size = skb_headlen(skb); + + tx_desc = IDPF_FLEX_TX_DESC(tx_q, i); + + dma = dma_map_single(tx_q->dev, skb->data, size, DMA_TO_DEVICE); + + tx_buf = first; + + params->compl_tag = + (tx_q->compl_tag_cur_gen << tx_q->compl_tag_gen_s) | i; + + for (frag = &skb_shinfo(skb)->frags[0];; frag++) { + unsigned int max_data = IDPF_TX_MAX_DESC_DATA_ALIGNED; + + if (dma_mapping_error(tx_q->dev, dma)) + return idpf_tx_dma_map_error(tx_q, skb, first, i); + + tx_buf->compl_tag = params->compl_tag; + + /* record length, and DMA address */ + dma_unmap_len_set(tx_buf, len, size); + dma_unmap_addr_set(tx_buf, dma, dma); + + /* buf_addr is in same location for both desc types */ + tx_desc->q.buf_addr = cpu_to_le64(dma); + + /* The stack can send us fragments that are too large for a + * single descriptor i.e. frag size > 16K-1. We will need to + * split the fragment across multiple descriptors in this case. + * To adhere to HW alignment restrictions, the fragment needs + * to be split such that the first chunk ends on a 4K boundary + * and all subsequent chunks start on a 4K boundary. We still + * want to send as much data as possible though, so our + * intermediate descriptor chunk size will be 12K. + * + * For example, consider a 32K fragment mapped to DMA addr 2600. + * ------------------------------------------------------------ + * | frag_size = 32K | + * ------------------------------------------------------------ + * |2600 |16384 |28672 + * + * 3 descriptors will be used for this fragment. The HW expects + * the descriptors to contain the following: + * ------------------------------------------------------------ + * | size = 13784 | size = 12K | size = 6696 | + * | dma = 2600 | dma = 16384 | dma = 28672 | + * ------------------------------------------------------------ + * + * We need to first adjust the max_data for the first chunk so + * that it ends on a 4K boundary. By negating the value of the + * DMA address and taking only the low order bits, we're + * effectively calculating + * 4K - (DMA addr lower order bits) = + * bytes to next boundary. + * + * Add that to our base aligned max_data (12K) and we have + * our first chunk size. In the example above, + * 13784 = 12K + (4096-2600) + * + * After guaranteeing the first chunk ends on a 4K boundary, we + * will give the intermediate descriptors 12K chunks and + * whatever is left to the final descriptor. This ensures that + * all descriptors used for the remaining chunks of the + * fragment start on a 4K boundary and we use as few + * descriptors as possible. + */ + max_data += -dma & (IDPF_TX_MAX_READ_REQ_SIZE - 1); + while (unlikely(size > IDPF_TX_MAX_DESC_DATA)) { + idpf_tx_splitq_build_desc(tx_desc, params, td_cmd, + max_data); + + tx_desc++; + i++; + + if (i == tx_q->desc_count) { + tx_desc = IDPF_FLEX_TX_DESC(tx_q, 0); + i = 0; + tx_q->compl_tag_cur_gen = + IDPF_TX_ADJ_COMPL_TAG_GEN(tx_q); + } + + /* Since this packet has a buffer that is going to span + * multiple descriptors, it's going to leave holes in + * to the TX buffer ring. To ensure these holes do not + * cause issues in the cleaning routines, we will clear + * them of any stale data and assign them the same + * completion tag as the current packet. Then when the + * packet is being cleaned, the cleaning routines will + * simply pass over these holes and finish cleaning the + * rest of the packet. + */ + memset(&tx_q->tx_buf[i], 0, sizeof(struct idpf_tx_buf)); + tx_q->tx_buf[i].compl_tag = params->compl_tag; + + /* Adjust the DMA offset and the remaining size of the + * fragment. On the first iteration of this loop, + * max_data will be >= 12K and <= 16K-1. On any + * subsequent iteration of this loop, max_data will + * always be 12K. + */ + dma += max_data; + size -= max_data; + + /* Reset max_data since remaining chunks will be 12K + * at most + */ + max_data = IDPF_TX_MAX_DESC_DATA_ALIGNED; + + /* buf_addr is in same location for both desc types */ + tx_desc->q.buf_addr = cpu_to_le64(dma); + } + + if (!data_len) + break; + + idpf_tx_splitq_build_desc(tx_desc, params, td_cmd, size); + tx_desc++; + i++; + + if (i == tx_q->desc_count) { + tx_desc = IDPF_FLEX_TX_DESC(tx_q, 0); + i = 0; + tx_q->compl_tag_cur_gen = IDPF_TX_ADJ_COMPL_TAG_GEN(tx_q); + } + + size = skb_frag_size(frag); + data_len -= size; + + dma = skb_frag_dma_map(tx_q->dev, frag, 0, size, + DMA_TO_DEVICE); + + tx_buf = &tx_q->tx_buf[i]; + } + + /* record SW timestamp if HW timestamp is not available */ + skb_tx_timestamp(skb); + + /* write last descriptor with RS and EOP bits */ + td_cmd |= params->eop_cmd; + idpf_tx_splitq_build_desc(tx_desc, params, td_cmd, size); + i = idpf_tx_splitq_bump_ntu(tx_q, i); + + /* set next_to_watch value indicating a packet is present */ + first->next_to_watch = tx_desc; + + tx_q->txq_grp->num_completions_pending++; + + /* record bytecount for BQL */ + nq = netdev_get_tx_queue(tx_q->vport->netdev, tx_q->idx); + netdev_tx_sent_queue(nq, first->bytecount); + + idpf_tx_buf_hw_update(tx_q, i, netdev_xmit_more()); +} + +/** + * idpf_tso - computes mss and TSO length to prepare for TSO + * @skb: pointer to skb + * @off: pointer to struct that holds offload parameters + * + * Returns error (negative) if TSO was requested but cannot be applied to the + * given skb, 0 if TSO does not apply to the given skb, or 1 otherwise. + */ +int idpf_tso(struct sk_buff *skb, struct idpf_tx_offload_params *off) +{ + const struct skb_shared_info *shinfo; + union { + struct iphdr *v4; + struct ipv6hdr *v6; + unsigned char *hdr; + } ip; + union { + struct tcphdr *tcp; + struct udphdr *udp; + unsigned char *hdr; + } l4; + u32 paylen, l4_start; + int err; + + if (!skb_is_gso(skb)) + return 0; + + err = skb_cow_head(skb, 0); + if (err < 0) + return err; + + shinfo = skb_shinfo(skb); + + ip.hdr = skb_network_header(skb); + l4.hdr = skb_transport_header(skb); + + /* initialize outer IP header fields */ + if (ip.v4->version == 4) { + ip.v4->tot_len = 0; + ip.v4->check = 0; + } else if (ip.v6->version == 6) { + ip.v6->payload_len = 0; + } + + l4_start = skb_transport_offset(skb); + + /* remove payload length from checksum */ + paylen = skb->len - l4_start; + + switch (shinfo->gso_type & ~SKB_GSO_DODGY) { + case SKB_GSO_TCPV4: + case SKB_GSO_TCPV6: + csum_replace_by_diff(&l4.tcp->check, + (__force __wsum)htonl(paylen)); + off->tso_hdr_len = __tcp_hdrlen(l4.tcp) + l4_start; + break; + case SKB_GSO_UDP_L4: + csum_replace_by_diff(&l4.udp->check, + (__force __wsum)htonl(paylen)); + /* compute length of segmentation header */ + off->tso_hdr_len = sizeof(struct udphdr) + l4_start; + l4.udp->len = htons(shinfo->gso_size + sizeof(struct udphdr)); + break; + default: + return -EINVAL; + } + + off->tso_len = skb->len - off->tso_hdr_len; + off->mss = shinfo->gso_size; + off->tso_segs = shinfo->gso_segs; + + off->tx_flags |= IDPF_TX_FLAGS_TSO; + + return 1; +} + +/** + * __idpf_chk_linearize - Check skb is not using too many buffers + * @skb: send buffer + * @max_bufs: maximum number of buffers + * + * For TSO we need to count the TSO header and segment payload separately. As + * such we need to check cases where we have max_bufs-1 fragments or more as we + * can potentially require max_bufs+1 DMA transactions, 1 for the TSO header, 1 + * for the segment payload in the first descriptor, and another max_buf-1 for + * the fragments. + */ +static bool __idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs) +{ + const struct skb_shared_info *shinfo = skb_shinfo(skb); + const skb_frag_t *frag, *stale; + int nr_frags, sum; + + /* no need to check if number of frags is less than max_bufs - 1 */ + nr_frags = shinfo->nr_frags; + if (nr_frags < (max_bufs - 1)) + return false; + + /* We need to walk through the list and validate that each group + * of max_bufs-2 fragments totals at least gso_size. + */ + nr_frags -= max_bufs - 2; + frag = &shinfo->frags[0]; + + /* Initialize size to the negative value of gso_size minus 1. We use + * this as the worst case scenario in which the frag ahead of us only + * provides one byte which is why we are limited to max_bufs-2 + * descriptors for a single transmit as the header and previous + * fragment are already consuming 2 descriptors. + */ + sum = 1 - shinfo->gso_size; + + /* Add size of frags 0 through 4 to create our initial sum */ + sum += skb_frag_size(frag++); + sum += skb_frag_size(frag++); + sum += skb_frag_size(frag++); + sum += skb_frag_size(frag++); + sum += skb_frag_size(frag++); + + /* Walk through fragments adding latest fragment, testing it, and + * then removing stale fragments from the sum. + */ + for (stale = &shinfo->frags[0];; stale++) { + int stale_size = skb_frag_size(stale); + + sum += skb_frag_size(frag++); + + /* The stale fragment may present us with a smaller + * descriptor than the actual fragment size. To account + * for that we need to remove all the data on the front and + * figure out what the remainder would be in the last + * descriptor associated with the fragment. + */ + if (stale_size > IDPF_TX_MAX_DESC_DATA) { + int align_pad = -(skb_frag_off(stale)) & + (IDPF_TX_MAX_READ_REQ_SIZE - 1); + + sum -= align_pad; + stale_size -= align_pad; + + do { + sum -= IDPF_TX_MAX_DESC_DATA_ALIGNED; + stale_size -= IDPF_TX_MAX_DESC_DATA_ALIGNED; + } while (stale_size > IDPF_TX_MAX_DESC_DATA); + } + + /* if sum is negative we failed to make sufficient progress */ + if (sum < 0) + return true; + + if (!nr_frags--) + break; + + sum -= stale_size; + } + + return false; +} + +/** + * idpf_chk_linearize - Check if skb exceeds max descriptors per packet + * @skb: send buffer + * @max_bufs: maximum scatter gather buffers for single packet + * @count: number of buffers this packet needs + * + * Make sure we don't exceed maximum scatter gather buffers for a single + * packet. We have to do some special checking around the boundary (max_bufs-1) + * if TSO is on since we need count the TSO header and payload separately. + * E.g.: a packet with 7 fragments can require 9 DMA transactions; 1 for TSO + * header, 1 for segment payload, and then 7 for the fragments. + */ +bool idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs, + unsigned int count) +{ + if (likely(count < max_bufs)) + return false; + if (skb_is_gso(skb)) + return __idpf_chk_linearize(skb, max_bufs); + + return count > max_bufs; +} + +/** + * idpf_tx_splitq_get_ctx_desc - grab next desc and update buffer ring + * @txq: queue to put context descriptor on + * + * Since the TX buffer rings mimics the descriptor ring, update the tx buffer + * ring entry to reflect that this index is a context descriptor + */ +static struct idpf_flex_tx_ctx_desc * +idpf_tx_splitq_get_ctx_desc(struct idpf_queue *txq) +{ + struct idpf_flex_tx_ctx_desc *desc; + int i = txq->next_to_use; + + memset(&txq->tx_buf[i], 0, sizeof(struct idpf_tx_buf)); + txq->tx_buf[i].compl_tag = IDPF_SPLITQ_TX_INVAL_COMPL_TAG; + + /* grab the next descriptor */ + desc = IDPF_FLEX_TX_CTX_DESC(txq, i); + txq->next_to_use = idpf_tx_splitq_bump_ntu(txq, i); + + return desc; +} + +/** + * idpf_tx_drop_skb - free the SKB and bump tail if necessary + * @tx_q: queue to send buffer on + * @skb: pointer to skb + */ +netdev_tx_t idpf_tx_drop_skb(struct idpf_queue *tx_q, struct sk_buff *skb) +{ + u64_stats_update_begin(&tx_q->stats_sync); + u64_stats_inc(&tx_q->q_stats.tx.skb_drops); + u64_stats_update_end(&tx_q->stats_sync); + + idpf_tx_buf_hw_update(tx_q, tx_q->next_to_use, false); + + dev_kfree_skb(skb); + + return NETDEV_TX_OK; +} + +/** + * idpf_tx_splitq_frame - Sends buffer on Tx ring using flex descriptors + * @skb: send buffer + * @tx_q: queue to send buffer on + * + * Returns NETDEV_TX_OK if sent, else an error code + */ +static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb, + struct idpf_queue *tx_q) +{ + struct idpf_tx_splitq_params tx_params = { }; + struct idpf_tx_buf *first; + unsigned int count; + int tso; + + count = idpf_tx_desc_count_required(tx_q, skb); + if (unlikely(!count)) + return idpf_tx_drop_skb(tx_q, skb); + + tso = idpf_tso(skb, &tx_params.offload); + if (unlikely(tso < 0)) + return idpf_tx_drop_skb(tx_q, skb); + + /* Check for splitq specific TX resources */ + count += (IDPF_TX_DESCS_PER_CACHE_LINE + tso); + if (idpf_tx_maybe_stop_splitq(tx_q, count)) { + idpf_tx_buf_hw_update(tx_q, tx_q->next_to_use, false); + + return NETDEV_TX_BUSY; + } + + if (tso) { + /* If tso is needed, set up context desc */ + struct idpf_flex_tx_ctx_desc *ctx_desc = + idpf_tx_splitq_get_ctx_desc(tx_q); + + ctx_desc->tso.qw1.cmd_dtype = + cpu_to_le16(IDPF_TX_DESC_DTYPE_FLEX_TSO_CTX | + IDPF_TX_FLEX_CTX_DESC_CMD_TSO); + ctx_desc->tso.qw0.flex_tlen = + cpu_to_le32(tx_params.offload.tso_len & + IDPF_TXD_FLEX_CTX_TLEN_M); + ctx_desc->tso.qw0.mss_rt = + cpu_to_le16(tx_params.offload.mss & + IDPF_TXD_FLEX_CTX_MSS_RT_M); + ctx_desc->tso.qw0.hdr_len = tx_params.offload.tso_hdr_len; + + u64_stats_update_begin(&tx_q->stats_sync); + u64_stats_inc(&tx_q->q_stats.tx.lso_pkts); + u64_stats_update_end(&tx_q->stats_sync); + } + + /* record the location of the first descriptor for this packet */ + first = &tx_q->tx_buf[tx_q->next_to_use]; + first->skb = skb; + + if (tso) { + first->gso_segs = tx_params.offload.tso_segs; + first->bytecount = skb->len + + ((first->gso_segs - 1) * tx_params.offload.tso_hdr_len); + } else { + first->gso_segs = 1; + first->bytecount = max_t(unsigned int, skb->len, ETH_ZLEN); + } + + if (test_bit(__IDPF_Q_FLOW_SCH_EN, tx_q->flags)) { + tx_params.dtype = IDPF_TX_DESC_DTYPE_FLEX_FLOW_SCHE; + tx_params.eop_cmd = IDPF_TXD_FLEX_FLOW_CMD_EOP; + /* Set the RE bit to catch any packets that may have not been + * stashed during RS completion cleaning. MIN_GAP is set to + * MIN_RING size to ensure it will be set at least once each + * time around the ring. + */ + if (!(tx_q->next_to_use % IDPF_TX_SPLITQ_RE_MIN_GAP)) { + tx_params.eop_cmd |= IDPF_TXD_FLEX_FLOW_CMD_RE; + tx_q->txq_grp->num_completions_pending++; + } + + if (skb->ip_summed == CHECKSUM_PARTIAL) + tx_params.offload.td_cmd |= IDPF_TXD_FLEX_FLOW_CMD_CS_EN; + + } else { + tx_params.dtype = IDPF_TX_DESC_DTYPE_FLEX_L2TAG1_L2TAG2; + tx_params.eop_cmd = IDPF_TXD_LAST_DESC_CMD; + + if (skb->ip_summed == CHECKSUM_PARTIAL) + tx_params.offload.td_cmd |= IDPF_TX_FLEX_DESC_CMD_CS_EN; + } + + idpf_tx_splitq_map(tx_q, &tx_params, first); + + return NETDEV_TX_OK; +} + +/** + * idpf_tx_splitq_start - Selects the right Tx queue to send buffer + * @skb: send buffer + * @netdev: network interface device structure + * + * Returns NETDEV_TX_OK if sent, else an error code + */ +netdev_tx_t idpf_tx_splitq_start(struct sk_buff *skb, + struct net_device *netdev) +{ + struct idpf_vport *vport = idpf_netdev_to_vport(netdev); + struct idpf_queue *tx_q; + + if (unlikely(skb_get_queue_mapping(skb) >= vport->num_txq)) { + dev_kfree_skb_any(skb); + + return NETDEV_TX_OK; + } + + tx_q = vport->txqs[skb_get_queue_mapping(skb)]; + + /* hardware can't handle really short frames, hardware padding works + * beyond this point + */ + if (skb_put_padto(skb, tx_q->tx_min_pkt_len)) { + idpf_tx_buf_hw_update(tx_q, tx_q->next_to_use, false); + + return NETDEV_TX_OK; + } + + return idpf_tx_splitq_frame(skb, tx_q); +} + +/** + * idpf_ptype_to_htype - get a hash type + * @decoded: Decoded Rx packet type related fields + * + * Returns appropriate hash type (such as PKT_HASH_TYPE_L2/L3/L4) to be used by + * skb_set_hash based on PTYPE as parsed by HW Rx pipeline and is part of + * Rx desc. + */ +enum pkt_hash_types idpf_ptype_to_htype(const struct idpf_rx_ptype_decoded *decoded) +{ + if (!decoded->known) + return PKT_HASH_TYPE_NONE; + if (decoded->payload_layer == IDPF_RX_PTYPE_PAYLOAD_LAYER_PAY2 && + decoded->inner_prot) + return PKT_HASH_TYPE_L4; + if (decoded->payload_layer == IDPF_RX_PTYPE_PAYLOAD_LAYER_PAY2 && + decoded->outer_ip) + return PKT_HASH_TYPE_L3; + if (decoded->outer_ip == IDPF_RX_PTYPE_OUTER_L2) + return PKT_HASH_TYPE_L2; + + return PKT_HASH_TYPE_NONE; +} + +/** + * idpf_rx_hash - set the hash value in the skb + * @rxq: Rx descriptor ring packet is being transacted on + * @skb: pointer to current skb being populated + * @rx_desc: Receive descriptor + * @decoded: Decoded Rx packet type related fields + */ +static void idpf_rx_hash(struct idpf_queue *rxq, struct sk_buff *skb, + struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc, + struct idpf_rx_ptype_decoded *decoded) +{ + u32 hash; + + if (unlikely(!idpf_is_feature_ena(rxq->vport, NETIF_F_RXHASH))) + return; + + hash = le16_to_cpu(rx_desc->hash1) | + (rx_desc->ff2_mirrid_hash2.hash2 << 16) | + (rx_desc->hash3 << 24); + + skb_set_hash(skb, hash, idpf_ptype_to_htype(decoded)); +} + +/** + * idpf_rx_csum - Indicate in skb if checksum is good + * @rxq: Rx descriptor ring packet is being transacted on + * @skb: pointer to current skb being populated + * @csum_bits: checksum fields extracted from the descriptor + * @decoded: Decoded Rx packet type related fields + * + * skb->protocol must be set before this function is called + */ +static void idpf_rx_csum(struct idpf_queue *rxq, struct sk_buff *skb, + struct idpf_rx_csum_decoded *csum_bits, + struct idpf_rx_ptype_decoded *decoded) +{ + bool ipv4, ipv6; + + /* check if Rx checksum is enabled */ + if (unlikely(!idpf_is_feature_ena(rxq->vport, NETIF_F_RXCSUM))) + return; + + /* check if HW has decoded the packet and checksum */ + if (!(csum_bits->l3l4p)) + return; + + ipv4 = IDPF_RX_PTYPE_TO_IPV(decoded, IDPF_RX_PTYPE_OUTER_IPV4); + ipv6 = IDPF_RX_PTYPE_TO_IPV(decoded, IDPF_RX_PTYPE_OUTER_IPV6); + + if (ipv4 && (csum_bits->ipe || csum_bits->eipe)) + goto checksum_fail; + + if (ipv6 && csum_bits->ipv6exadd) + return; + + /* check for L4 errors and handle packets that were not able to be + * checksummed + */ + if (csum_bits->l4e) + goto checksum_fail; + + /* Only report checksum unnecessary for ICMP, TCP, UDP, or SCTP */ + switch (decoded->inner_prot) { + case IDPF_RX_PTYPE_INNER_PROT_ICMP: + case IDPF_RX_PTYPE_INNER_PROT_TCP: + case IDPF_RX_PTYPE_INNER_PROT_UDP: + if (!csum_bits->raw_csum_inv) { + u16 csum = csum_bits->raw_csum; + + skb->csum = csum_unfold((__force __sum16)~swab16(csum)); + skb->ip_summed = CHECKSUM_COMPLETE; + } else { + skb->ip_summed = CHECKSUM_UNNECESSARY; + } + break; + case IDPF_RX_PTYPE_INNER_PROT_SCTP: + skb->ip_summed = CHECKSUM_UNNECESSARY; + break; + default: + break; + } + + return; + +checksum_fail: + u64_stats_update_begin(&rxq->stats_sync); + u64_stats_inc(&rxq->q_stats.rx.hw_csum_err); + u64_stats_update_end(&rxq->stats_sync); +} + +/** + * idpf_rx_splitq_extract_csum_bits - Extract checksum bits from descriptor + * @rx_desc: receive descriptor + * @csum: structure to extract checksum fields + * + **/ +static void idpf_rx_splitq_extract_csum_bits(struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc, + struct idpf_rx_csum_decoded *csum) +{ + u8 qword0, qword1; + + qword0 = rx_desc->status_err0_qw0; + qword1 = rx_desc->status_err0_qw1; + + csum->ipe = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_XSUM_IPE_M, + qword1); + csum->eipe = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_XSUM_EIPE_M, + qword1); + csum->l4e = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_XSUM_L4E_M, + qword1); + csum->l3l4p = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_L3L4P_M, + qword1); + csum->ipv6exadd = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_IPV6EXADD_M, + qword0); + csum->raw_csum_inv = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_RAW_CSUM_INV_M, + le16_to_cpu(rx_desc->ptype_err_fflags0)); + csum->raw_csum = le16_to_cpu(rx_desc->misc.raw_cs); +} + +/** + * idpf_rx_rsc - Set the RSC fields in the skb + * @rxq : Rx descriptor ring packet is being transacted on + * @skb : pointer to current skb being populated + * @rx_desc: Receive descriptor + * @decoded: Decoded Rx packet type related fields + * + * Return 0 on success and error code on failure + * + * Populate the skb fields with the total number of RSC segments, RSC payload + * length and packet type. + */ +static int idpf_rx_rsc(struct idpf_queue *rxq, struct sk_buff *skb, + struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc, + struct idpf_rx_ptype_decoded *decoded) +{ + u16 rsc_segments, rsc_seg_len; + bool ipv4, ipv6; + int len; + + if (unlikely(!decoded->outer_ip)) + return -EINVAL; + + rsc_seg_len = le16_to_cpu(rx_desc->misc.rscseglen); + if (unlikely(!rsc_seg_len)) + return -EINVAL; + + ipv4 = IDPF_RX_PTYPE_TO_IPV(decoded, IDPF_RX_PTYPE_OUTER_IPV4); + ipv6 = IDPF_RX_PTYPE_TO_IPV(decoded, IDPF_RX_PTYPE_OUTER_IPV6); + + if (unlikely(!(ipv4 ^ ipv6))) + return -EINVAL; + + rsc_segments = DIV_ROUND_UP(skb->data_len, rsc_seg_len); + if (unlikely(rsc_segments == 1)) + return 0; + + NAPI_GRO_CB(skb)->count = rsc_segments; + skb_shinfo(skb)->gso_size = rsc_seg_len; + + skb_reset_network_header(skb); + len = skb->len - skb_transport_offset(skb); + + if (ipv4) { + struct iphdr *ipv4h = ip_hdr(skb); + + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; + + /* Reset and set transport header offset in skb */ + skb_set_transport_header(skb, sizeof(struct iphdr)); + + /* Compute the TCP pseudo header checksum*/ + tcp_hdr(skb)->check = + ~tcp_v4_check(len, ipv4h->saddr, ipv4h->daddr, 0); + } else { + struct ipv6hdr *ipv6h = ipv6_hdr(skb); + + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; + skb_set_transport_header(skb, sizeof(struct ipv6hdr)); + tcp_hdr(skb)->check = + ~tcp_v6_check(len, &ipv6h->saddr, &ipv6h->daddr, 0); + } + + tcp_gro_complete(skb); + + u64_stats_update_begin(&rxq->stats_sync); + u64_stats_inc(&rxq->q_stats.rx.rsc_pkts); + u64_stats_update_end(&rxq->stats_sync); + + return 0; +} + +/** + * idpf_rx_process_skb_fields - Populate skb header fields from Rx descriptor + * @rxq: Rx descriptor ring packet is being transacted on + * @skb: pointer to current skb being populated + * @rx_desc: Receive descriptor + * + * This function checks the ring, descriptor, and packet information in + * order to populate the hash, checksum, protocol, and + * other fields within the skb. + */ +static int idpf_rx_process_skb_fields(struct idpf_queue *rxq, + struct sk_buff *skb, + struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc) +{ + struct idpf_rx_csum_decoded csum_bits = { }; + struct idpf_rx_ptype_decoded decoded; + u16 rx_ptype; + + rx_ptype = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_PTYPE_M, + le16_to_cpu(rx_desc->ptype_err_fflags0)); + + decoded = rxq->vport->rx_ptype_lkup[rx_ptype]; + /* If we don't know the ptype we can't do anything else with it. Just + * pass it up the stack as-is. + */ + if (!decoded.known) + return 0; + + /* process RSS/hash */ + idpf_rx_hash(rxq, skb, rx_desc, &decoded); + + skb->protocol = eth_type_trans(skb, rxq->vport->netdev); + + if (FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_RSC_M, + le16_to_cpu(rx_desc->hdrlen_flags))) + return idpf_rx_rsc(rxq, skb, rx_desc, &decoded); + + idpf_rx_splitq_extract_csum_bits(rx_desc, &csum_bits); + idpf_rx_csum(rxq, skb, &csum_bits, &decoded); + + return 0; +} + +/** + * idpf_rx_add_frag - Add contents of Rx buffer to sk_buff as a frag + * @rx_buf: buffer containing page to add + * @skb: sk_buff to place the data into + * @size: packet length from rx_desc + * + * This function will add the data contained in rx_buf->page to the skb. + * It will just attach the page as a frag to the skb. + * The function will then update the page offset. + */ +void idpf_rx_add_frag(struct idpf_rx_buf *rx_buf, struct sk_buff *skb, + unsigned int size) +{ + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buf->page, + rx_buf->page_offset, size, rx_buf->truesize); + + rx_buf->page = NULL; +} + +/** + * idpf_rx_construct_skb - Allocate skb and populate it + * @rxq: Rx descriptor queue + * @rx_buf: Rx buffer to pull data from + * @size: the length of the packet + * + * This function allocates an skb. It then populates it with the page + * data from the current receive descriptor, taking care to set up the + * skb correctly. + */ +struct sk_buff *idpf_rx_construct_skb(struct idpf_queue *rxq, + struct idpf_rx_buf *rx_buf, + unsigned int size) +{ + unsigned int headlen; + struct sk_buff *skb; + void *va; + + va = page_address(rx_buf->page) + rx_buf->page_offset; + + /* prefetch first cache line of first page */ + net_prefetch(va); + /* allocate a skb to store the frags */ + skb = __napi_alloc_skb(&rxq->q_vector->napi, IDPF_RX_HDR_SIZE, + GFP_ATOMIC); + if (unlikely(!skb)) { + idpf_rx_put_page(rx_buf); + + return NULL; + } + + skb_record_rx_queue(skb, rxq->idx); + skb_mark_for_recycle(skb); + + /* Determine available headroom for copy */ + headlen = size; + if (headlen > IDPF_RX_HDR_SIZE) + headlen = eth_get_headlen(skb->dev, va, IDPF_RX_HDR_SIZE); + + /* align pull length to size of long to optimize memcpy performance */ + memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); + + /* if we exhaust the linear part then add what is left as a frag */ + size -= headlen; + if (!size) { + idpf_rx_put_page(rx_buf); + + return skb; + } + + skb_add_rx_frag(skb, 0, rx_buf->page, rx_buf->page_offset + headlen, + size, rx_buf->truesize); + + /* Since we're giving the page to the stack, clear our reference to it. + * We'll get a new one during buffer posting. + */ + rx_buf->page = NULL; + + return skb; +} + +/** + * idpf_rx_hdr_construct_skb - Allocate skb and populate it from header buffer + * @rxq: Rx descriptor queue + * @va: Rx buffer to pull data from + * @size: the length of the packet + * + * This function allocates an skb. It then populates it with the page data from + * the current receive descriptor, taking care to set up the skb correctly. + * This specifically uses a header buffer to start building the skb. + */ +static struct sk_buff *idpf_rx_hdr_construct_skb(struct idpf_queue *rxq, + const void *va, + unsigned int size) +{ + struct sk_buff *skb; + + /* allocate a skb to store the frags */ + skb = __napi_alloc_skb(&rxq->q_vector->napi, size, GFP_ATOMIC); + if (unlikely(!skb)) + return NULL; + + skb_record_rx_queue(skb, rxq->idx); + + memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); + + /* More than likely, a payload fragment, which will use a page from + * page_pool will be added to the SKB so mark it for recycle + * preemptively. And if not, it's inconsequential. + */ + skb_mark_for_recycle(skb); + + return skb; +} + +/** + * idpf_rx_splitq_test_staterr - tests bits in Rx descriptor + * status and error fields + * @stat_err_field: field from descriptor to test bits in + * @stat_err_bits: value to mask + * + */ +static bool idpf_rx_splitq_test_staterr(const u8 stat_err_field, + const u8 stat_err_bits) +{ + return !!(stat_err_field & stat_err_bits); +} + +/** + * idpf_rx_splitq_is_eop - process handling of EOP buffers + * @rx_desc: Rx descriptor for current buffer + * + * If the buffer is an EOP buffer, this function exits returning true, + * otherwise return false indicating that this is in fact a non-EOP buffer. + */ +static bool idpf_rx_splitq_is_eop(struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc) +{ + /* if we are the last buffer then there is nothing else to do */ + return likely(idpf_rx_splitq_test_staterr(rx_desc->status_err0_qw1, + IDPF_RXD_EOF_SPLITQ)); +} + +/** + * idpf_rx_splitq_clean - Clean completed descriptors from Rx queue + * @rxq: Rx descriptor queue to retrieve receive buffer queue + * @budget: Total limit on number of packets to process + * + * This function provides a "bounce buffer" approach to Rx interrupt + * processing. The advantage to this is that on systems that have + * expensive overhead for IOMMU access this provides a means of avoiding + * it by maintaining the mapping of the page to the system. + * + * Returns amount of work completed + */ +static int idpf_rx_splitq_clean(struct idpf_queue *rxq, int budget) +{ + int total_rx_bytes = 0, total_rx_pkts = 0; + struct idpf_queue *rx_bufq = NULL; + struct sk_buff *skb = rxq->skb; + u16 ntc = rxq->next_to_clean; + + /* Process Rx packets bounded by budget */ + while (likely(total_rx_pkts < budget)) { + struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc; + struct idpf_sw_queue *refillq = NULL; + struct idpf_rxq_set *rxq_set = NULL; + struct idpf_rx_buf *rx_buf = NULL; + union virtchnl2_rx_desc *desc; + unsigned int pkt_len = 0; + unsigned int hdr_len = 0; + u16 gen_id, buf_id = 0; + /* Header buffer overflow only valid for header split */ + bool hbo = false; + int bufq_id; + u8 rxdid; + + /* get the Rx desc from Rx queue based on 'next_to_clean' */ + desc = IDPF_RX_DESC(rxq, ntc); + rx_desc = (struct virtchnl2_rx_flex_desc_adv_nic_3 *)desc; + + /* This memory barrier is needed to keep us from reading + * any other fields out of the rx_desc + */ + dma_rmb(); + + /* if the descriptor isn't done, no work yet to do */ + gen_id = le16_to_cpu(rx_desc->pktlen_gen_bufq_id); + gen_id = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_GEN_M, gen_id); + + if (test_bit(__IDPF_Q_GEN_CHK, rxq->flags) != gen_id) + break; + + rxdid = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_RXDID_M, + rx_desc->rxdid_ucast); + if (rxdid != VIRTCHNL2_RXDID_2_FLEX_SPLITQ) { + IDPF_RX_BUMP_NTC(rxq, ntc); + u64_stats_update_begin(&rxq->stats_sync); + u64_stats_inc(&rxq->q_stats.rx.bad_descs); + u64_stats_update_end(&rxq->stats_sync); + continue; + } + + pkt_len = le16_to_cpu(rx_desc->pktlen_gen_bufq_id); + pkt_len = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_LEN_PBUF_M, + pkt_len); + + hbo = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_HBO_M, + rx_desc->status_err0_qw1); + + if (unlikely(hbo)) { + /* If a header buffer overflow, occurs, i.e. header is + * too large to fit in the header split buffer, HW will + * put the entire packet, including headers, in the + * data/payload buffer. + */ + u64_stats_update_begin(&rxq->stats_sync); + u64_stats_inc(&rxq->q_stats.rx.hsplit_buf_ovf); + u64_stats_update_end(&rxq->stats_sync); + goto bypass_hsplit; + } + + hdr_len = le16_to_cpu(rx_desc->hdrlen_flags); + hdr_len = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_LEN_HDR_M, + hdr_len); + +bypass_hsplit: + bufq_id = le16_to_cpu(rx_desc->pktlen_gen_bufq_id); + bufq_id = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_BUFQ_ID_M, + bufq_id); + + rxq_set = container_of(rxq, struct idpf_rxq_set, rxq); + if (!bufq_id) + refillq = rxq_set->refillq0; + else + refillq = rxq_set->refillq1; + + /* retrieve buffer from the rxq */ + rx_bufq = &rxq->rxq_grp->splitq.bufq_sets[bufq_id].bufq; + + buf_id = le16_to_cpu(rx_desc->buf_id); + + rx_buf = &rx_bufq->rx_buf.buf[buf_id]; + + if (hdr_len) { + const void *va = (u8 *)rx_bufq->rx_buf.hdr_buf_va + + (u32)buf_id * IDPF_HDR_BUF_SIZE; + + skb = idpf_rx_hdr_construct_skb(rxq, va, hdr_len); + u64_stats_update_begin(&rxq->stats_sync); + u64_stats_inc(&rxq->q_stats.rx.hsplit_pkts); + u64_stats_update_end(&rxq->stats_sync); + } + + if (pkt_len) { + idpf_rx_sync_for_cpu(rx_buf, pkt_len); + if (skb) + idpf_rx_add_frag(rx_buf, skb, pkt_len); + else + skb = idpf_rx_construct_skb(rxq, rx_buf, + pkt_len); + } else { + idpf_rx_put_page(rx_buf); + } + + /* exit if we failed to retrieve a buffer */ + if (!skb) + break; + + idpf_rx_post_buf_refill(refillq, buf_id); + + IDPF_RX_BUMP_NTC(rxq, ntc); + /* skip if it is non EOP desc */ + if (!idpf_rx_splitq_is_eop(rx_desc)) + continue; + + /* pad skb if needed (to make valid ethernet frame) */ + if (eth_skb_pad(skb)) { + skb = NULL; + continue; + } + + /* probably a little skewed due to removing CRC */ + total_rx_bytes += skb->len; + + /* protocol */ + if (unlikely(idpf_rx_process_skb_fields(rxq, skb, rx_desc))) { + dev_kfree_skb_any(skb); + skb = NULL; + continue; + } + + /* send completed skb up the stack */ + napi_gro_receive(&rxq->q_vector->napi, skb); + skb = NULL; + + /* update budget accounting */ + total_rx_pkts++; + } + + rxq->next_to_clean = ntc; + + rxq->skb = skb; + u64_stats_update_begin(&rxq->stats_sync); + u64_stats_add(&rxq->q_stats.rx.packets, total_rx_pkts); + u64_stats_add(&rxq->q_stats.rx.bytes, total_rx_bytes); + u64_stats_update_end(&rxq->stats_sync); + + /* guarantee a trip back through this routine if there was a failure */ + return total_rx_pkts; +} + +/** + * idpf_rx_update_bufq_desc - Update buffer queue descriptor + * @bufq: Pointer to the buffer queue + * @refill_desc: SW Refill queue descriptor containing buffer ID + * @buf_desc: Buffer queue descriptor + * + * Return 0 on success and negative on failure. + */ +static int idpf_rx_update_bufq_desc(struct idpf_queue *bufq, u16 refill_desc, + struct virtchnl2_splitq_rx_buf_desc *buf_desc) +{ + struct idpf_rx_buf *buf; + dma_addr_t addr; + u16 buf_id; + + buf_id = FIELD_GET(IDPF_RX_BI_BUFID_M, refill_desc); + + buf = &bufq->rx_buf.buf[buf_id]; + + addr = idpf_alloc_page(bufq->pp, buf, bufq->rx_buf_size); + if (unlikely(addr == DMA_MAPPING_ERROR)) + return -ENOMEM; + + buf_desc->pkt_addr = cpu_to_le64(addr); + buf_desc->qword0.buf_id = cpu_to_le16(buf_id); + + if (!bufq->rx_hsplit_en) + return 0; + + buf_desc->hdr_addr = cpu_to_le64(bufq->rx_buf.hdr_buf_pa + + (u32)buf_id * IDPF_HDR_BUF_SIZE); + + return 0; +} + +/** + * idpf_rx_clean_refillq - Clean refill queue buffers + * @bufq: buffer queue to post buffers back to + * @refillq: refill queue to clean + * + * This function takes care of the buffer refill management + */ +static void idpf_rx_clean_refillq(struct idpf_queue *bufq, + struct idpf_sw_queue *refillq) +{ + struct virtchnl2_splitq_rx_buf_desc *buf_desc; + u16 bufq_nta = bufq->next_to_alloc; + u16 ntc = refillq->next_to_clean; + int cleaned = 0; + u16 gen; + + buf_desc = IDPF_SPLITQ_RX_BUF_DESC(bufq, bufq_nta); + + /* make sure we stop at ring wrap in the unlikely case ring is full */ + while (likely(cleaned < refillq->desc_count)) { + u16 refill_desc = IDPF_SPLITQ_RX_BI_DESC(refillq, ntc); + bool failure; + + gen = FIELD_GET(IDPF_RX_BI_GEN_M, refill_desc); + if (test_bit(__IDPF_RFLQ_GEN_CHK, refillq->flags) != gen) + break; + + failure = idpf_rx_update_bufq_desc(bufq, refill_desc, + buf_desc); + if (failure) + break; + + if (unlikely(++ntc == refillq->desc_count)) { + change_bit(__IDPF_RFLQ_GEN_CHK, refillq->flags); + ntc = 0; + } + + if (unlikely(++bufq_nta == bufq->desc_count)) { + buf_desc = IDPF_SPLITQ_RX_BUF_DESC(bufq, 0); + bufq_nta = 0; + } else { + buf_desc++; + } + + cleaned++; + } + + if (!cleaned) + return; + + /* We want to limit how many transactions on the bus we trigger with + * tail writes so we only do it in strides. It's also important we + * align the write to a multiple of 8 as required by HW. + */ + if (((bufq->next_to_use <= bufq_nta ? 0 : bufq->desc_count) + + bufq_nta - bufq->next_to_use) >= IDPF_RX_BUF_POST_STRIDE) + idpf_rx_buf_hw_update(bufq, ALIGN_DOWN(bufq_nta, + IDPF_RX_BUF_POST_STRIDE)); + + /* update next to alloc since we have filled the ring */ + refillq->next_to_clean = ntc; + bufq->next_to_alloc = bufq_nta; +} + +/** + * idpf_rx_clean_refillq_all - Clean all refill queues + * @bufq: buffer queue with refill queues + * + * Iterates through all refill queues assigned to the buffer queue assigned to + * this vector. Returns true if clean is complete within budget, false + * otherwise. + */ +static void idpf_rx_clean_refillq_all(struct idpf_queue *bufq) +{ + struct idpf_bufq_set *bufq_set; + int i; + + bufq_set = container_of(bufq, struct idpf_bufq_set, bufq); + for (i = 0; i < bufq_set->num_refillqs; i++) + idpf_rx_clean_refillq(bufq, &bufq_set->refillqs[i]); +} + +/** + * idpf_vport_intr_clean_queues - MSIX mode Interrupt Handler + * @irq: interrupt number + * @data: pointer to a q_vector + * + */ +static irqreturn_t idpf_vport_intr_clean_queues(int __always_unused irq, + void *data) +{ + struct idpf_q_vector *q_vector = (struct idpf_q_vector *)data; + + q_vector->total_events++; + napi_schedule(&q_vector->napi); + + return IRQ_HANDLED; +} + +/** + * idpf_vport_intr_napi_del_all - Unregister napi for all q_vectors in vport + * @vport: virtual port structure + * + */ +static void idpf_vport_intr_napi_del_all(struct idpf_vport *vport) +{ + u16 v_idx; + + for (v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) + netif_napi_del(&vport->q_vectors[v_idx].napi); +} + +/** + * idpf_vport_intr_napi_dis_all - Disable NAPI for all q_vectors in the vport + * @vport: main vport structure + */ +static void idpf_vport_intr_napi_dis_all(struct idpf_vport *vport) +{ + int v_idx; + + for (v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) + napi_disable(&vport->q_vectors[v_idx].napi); +} + +/** + * idpf_vport_intr_rel - Free memory allocated for interrupt vectors + * @vport: virtual port + * + * Free the memory allocated for interrupt vectors associated to a vport + */ +void idpf_vport_intr_rel(struct idpf_vport *vport) +{ + int i, j, v_idx; + + for (v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) { + struct idpf_q_vector *q_vector = &vport->q_vectors[v_idx]; + + kfree(q_vector->bufq); + q_vector->bufq = NULL; + kfree(q_vector->tx); + q_vector->tx = NULL; + kfree(q_vector->rx); + q_vector->rx = NULL; + } + + /* Clean up the mapping of queues to vectors */ + for (i = 0; i < vport->num_rxq_grp; i++) { + struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i]; + + if (idpf_is_queue_model_split(vport->rxq_model)) + for (j = 0; j < rx_qgrp->splitq.num_rxq_sets; j++) + rx_qgrp->splitq.rxq_sets[j]->rxq.q_vector = NULL; + else + for (j = 0; j < rx_qgrp->singleq.num_rxq; j++) + rx_qgrp->singleq.rxqs[j]->q_vector = NULL; + } + + if (idpf_is_queue_model_split(vport->txq_model)) + for (i = 0; i < vport->num_txq_grp; i++) + vport->txq_grps[i].complq->q_vector = NULL; + else + for (i = 0; i < vport->num_txq_grp; i++) + for (j = 0; j < vport->txq_grps[i].num_txq; j++) + vport->txq_grps[i].txqs[j]->q_vector = NULL; + + kfree(vport->q_vectors); + vport->q_vectors = NULL; +} + +/** + * idpf_vport_intr_rel_irq - Free the IRQ association with the OS + * @vport: main vport structure + */ +static void idpf_vport_intr_rel_irq(struct idpf_vport *vport) +{ + struct idpf_adapter *adapter = vport->adapter; + int vector; + + for (vector = 0; vector < vport->num_q_vectors; vector++) { + struct idpf_q_vector *q_vector = &vport->q_vectors[vector]; + int irq_num, vidx; + + /* free only the irqs that were actually requested */ + if (!q_vector) + continue; + + vidx = vport->q_vector_idxs[vector]; + irq_num = adapter->msix_entries[vidx].vector; + + /* clear the affinity_mask in the IRQ descriptor */ + irq_set_affinity_hint(irq_num, NULL); + free_irq(irq_num, q_vector); + } +} + +/** + * idpf_vport_intr_dis_irq_all - Disable all interrupt + * @vport: main vport structure + */ +static void idpf_vport_intr_dis_irq_all(struct idpf_vport *vport) +{ + struct idpf_q_vector *q_vector = vport->q_vectors; + int q_idx; + + for (q_idx = 0; q_idx < vport->num_q_vectors; q_idx++) + writel(0, q_vector[q_idx].intr_reg.dyn_ctl); +} + +/** + * idpf_vport_intr_buildreg_itr - Enable default interrupt generation settings + * @q_vector: pointer to q_vector + * @type: itr index + * @itr: itr value + */ +static u32 idpf_vport_intr_buildreg_itr(struct idpf_q_vector *q_vector, + const int type, u16 itr) +{ + u32 itr_val; + + itr &= IDPF_ITR_MASK; + /* Don't clear PBA because that can cause lost interrupts that + * came in while we were cleaning/polling + */ + itr_val = q_vector->intr_reg.dyn_ctl_intena_m | + (type << q_vector->intr_reg.dyn_ctl_itridx_s) | + (itr << (q_vector->intr_reg.dyn_ctl_intrvl_s - 1)); + + return itr_val; +} + +/** + * idpf_update_dim_sample - Update dim sample with packets and bytes + * @q_vector: the vector associated with the interrupt + * @dim_sample: dim sample to update + * @dim: dim instance structure + * @packets: total packets + * @bytes: total bytes + * + * Update the dim sample with the packets and bytes which are passed to this + * function. Set the dim state appropriately if the dim settings gets stale. + */ +static void idpf_update_dim_sample(struct idpf_q_vector *q_vector, + struct dim_sample *dim_sample, + struct dim *dim, u64 packets, u64 bytes) +{ + dim_update_sample(q_vector->total_events, packets, bytes, dim_sample); + dim_sample->comp_ctr = 0; + + /* if dim settings get stale, like when not updated for 1 second or + * longer, force it to start again. This addresses the frequent case + * of an idle queue being switched to by the scheduler. + */ + if (ktime_ms_delta(dim_sample->time, dim->start_sample.time) >= HZ) + dim->state = DIM_START_MEASURE; +} + +/** + * idpf_net_dim - Update net DIM algorithm + * @q_vector: the vector associated with the interrupt + * + * Create a DIM sample and notify net_dim() so that it can possibly decide + * a new ITR value based on incoming packets, bytes, and interrupts. + * + * This function is a no-op if the queue is not configured to dynamic ITR. + */ +static void idpf_net_dim(struct idpf_q_vector *q_vector) +{ + struct dim_sample dim_sample = { }; + u64 packets, bytes; + u32 i; + + if (!IDPF_ITR_IS_DYNAMIC(q_vector->tx_intr_mode)) + goto check_rx_itr; + + for (i = 0, packets = 0, bytes = 0; i < q_vector->num_txq; i++) { + struct idpf_queue *txq = q_vector->tx[i]; + unsigned int start; + + do { + start = u64_stats_fetch_begin(&txq->stats_sync); + packets += u64_stats_read(&txq->q_stats.tx.packets); + bytes += u64_stats_read(&txq->q_stats.tx.bytes); + } while (u64_stats_fetch_retry(&txq->stats_sync, start)); + } + + idpf_update_dim_sample(q_vector, &dim_sample, &q_vector->tx_dim, + packets, bytes); + net_dim(&q_vector->tx_dim, dim_sample); + +check_rx_itr: + if (!IDPF_ITR_IS_DYNAMIC(q_vector->rx_intr_mode)) + return; + + for (i = 0, packets = 0, bytes = 0; i < q_vector->num_rxq; i++) { + struct idpf_queue *rxq = q_vector->rx[i]; + unsigned int start; + + do { + start = u64_stats_fetch_begin(&rxq->stats_sync); + packets += u64_stats_read(&rxq->q_stats.rx.packets); + bytes += u64_stats_read(&rxq->q_stats.rx.bytes); + } while (u64_stats_fetch_retry(&rxq->stats_sync, start)); + } + + idpf_update_dim_sample(q_vector, &dim_sample, &q_vector->rx_dim, + packets, bytes); + net_dim(&q_vector->rx_dim, dim_sample); +} + +/** + * idpf_vport_intr_update_itr_ena_irq - Update itr and re-enable MSIX interrupt + * @q_vector: q_vector for which itr is being updated and interrupt enabled + * + * Update the net_dim() algorithm and re-enable the interrupt associated with + * this vector. + */ +void idpf_vport_intr_update_itr_ena_irq(struct idpf_q_vector *q_vector) +{ + u32 intval; + + /* net_dim() updates ITR out-of-band using a work item */ + idpf_net_dim(q_vector); + + intval = idpf_vport_intr_buildreg_itr(q_vector, + IDPF_NO_ITR_UPDATE_IDX, 0); + + writel(intval, q_vector->intr_reg.dyn_ctl); +} + +/** + * idpf_vport_intr_req_irq - get MSI-X vectors from the OS for the vport + * @vport: main vport structure + * @basename: name for the vector + */ +static int idpf_vport_intr_req_irq(struct idpf_vport *vport, char *basename) +{ + struct idpf_adapter *adapter = vport->adapter; + int vector, err, irq_num, vidx; + const char *vec_name; + + for (vector = 0; vector < vport->num_q_vectors; vector++) { + struct idpf_q_vector *q_vector = &vport->q_vectors[vector]; + + vidx = vport->q_vector_idxs[vector]; + irq_num = adapter->msix_entries[vidx].vector; + + if (q_vector->num_rxq && q_vector->num_txq) + vec_name = "TxRx"; + else if (q_vector->num_rxq) + vec_name = "Rx"; + else if (q_vector->num_txq) + vec_name = "Tx"; + else + continue; + + q_vector->name = kasprintf(GFP_KERNEL, "%s-%s-%d", + basename, vec_name, vidx); + + err = request_irq(irq_num, idpf_vport_intr_clean_queues, 0, + q_vector->name, q_vector); + if (err) { + netdev_err(vport->netdev, + "Request_irq failed, error: %d\n", err); + goto free_q_irqs; + } + /* assign the mask for this irq */ + irq_set_affinity_hint(irq_num, &q_vector->affinity_mask); + } + + return 0; + +free_q_irqs: + while (--vector >= 0) { + vidx = vport->q_vector_idxs[vector]; + irq_num = adapter->msix_entries[vidx].vector; + free_irq(irq_num, &vport->q_vectors[vector]); + } + + return err; +} + +/** + * idpf_vport_intr_write_itr - Write ITR value to the ITR register + * @q_vector: q_vector structure + * @itr: Interrupt throttling rate + * @tx: Tx or Rx ITR + */ +void idpf_vport_intr_write_itr(struct idpf_q_vector *q_vector, u16 itr, bool tx) +{ + struct idpf_intr_reg *intr_reg; + + if (tx && !q_vector->tx) + return; + else if (!tx && !q_vector->rx) + return; + + intr_reg = &q_vector->intr_reg; + writel(ITR_REG_ALIGN(itr) >> IDPF_ITR_GRAN_S, + tx ? intr_reg->tx_itr : intr_reg->rx_itr); +} + +/** + * idpf_vport_intr_ena_irq_all - Enable IRQ for the given vport + * @vport: main vport structure + */ +static void idpf_vport_intr_ena_irq_all(struct idpf_vport *vport) +{ + bool dynamic; + int q_idx; + u16 itr; + + for (q_idx = 0; q_idx < vport->num_q_vectors; q_idx++) { + struct idpf_q_vector *qv = &vport->q_vectors[q_idx]; + + /* Set the initial ITR values */ + if (qv->num_txq) { + dynamic = IDPF_ITR_IS_DYNAMIC(qv->tx_intr_mode); + itr = vport->tx_itr_profile[qv->tx_dim.profile_ix]; + idpf_vport_intr_write_itr(qv, dynamic ? + itr : qv->tx_itr_value, + true); + } + + if (qv->num_rxq) { + dynamic = IDPF_ITR_IS_DYNAMIC(qv->rx_intr_mode); + itr = vport->rx_itr_profile[qv->rx_dim.profile_ix]; + idpf_vport_intr_write_itr(qv, dynamic ? + itr : qv->rx_itr_value, + false); + } + + if (qv->num_txq || qv->num_rxq) + idpf_vport_intr_update_itr_ena_irq(qv); + } +} + +/** + * idpf_vport_intr_deinit - Release all vector associations for the vport + * @vport: main vport structure + */ +void idpf_vport_intr_deinit(struct idpf_vport *vport) +{ + idpf_vport_intr_napi_dis_all(vport); + idpf_vport_intr_napi_del_all(vport); + idpf_vport_intr_dis_irq_all(vport); + idpf_vport_intr_rel_irq(vport); +} + +/** + * idpf_tx_dim_work - Call back from the stack + * @work: work queue structure + */ +static void idpf_tx_dim_work(struct work_struct *work) +{ + struct idpf_q_vector *q_vector; + struct idpf_vport *vport; + struct dim *dim; + u16 itr; + + dim = container_of(work, struct dim, work); + q_vector = container_of(dim, struct idpf_q_vector, tx_dim); + vport = q_vector->vport; + + if (dim->profile_ix >= ARRAY_SIZE(vport->tx_itr_profile)) + dim->profile_ix = ARRAY_SIZE(vport->tx_itr_profile) - 1; + + /* look up the values in our local table */ + itr = vport->tx_itr_profile[dim->profile_ix]; + + idpf_vport_intr_write_itr(q_vector, itr, true); + + dim->state = DIM_START_MEASURE; +} + +/** + * idpf_rx_dim_work - Call back from the stack + * @work: work queue structure + */ +static void idpf_rx_dim_work(struct work_struct *work) +{ + struct idpf_q_vector *q_vector; + struct idpf_vport *vport; + struct dim *dim; + u16 itr; + + dim = container_of(work, struct dim, work); + q_vector = container_of(dim, struct idpf_q_vector, rx_dim); + vport = q_vector->vport; + + if (dim->profile_ix >= ARRAY_SIZE(vport->rx_itr_profile)) + dim->profile_ix = ARRAY_SIZE(vport->rx_itr_profile) - 1; + + /* look up the values in our local table */ + itr = vport->rx_itr_profile[dim->profile_ix]; + + idpf_vport_intr_write_itr(q_vector, itr, false); + + dim->state = DIM_START_MEASURE; +} + +/** + * idpf_init_dim - Set up dynamic interrupt moderation + * @qv: q_vector structure + */ +static void idpf_init_dim(struct idpf_q_vector *qv) +{ + INIT_WORK(&qv->tx_dim.work, idpf_tx_dim_work); + qv->tx_dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE; + qv->tx_dim.profile_ix = IDPF_DIM_DEFAULT_PROFILE_IX; + + INIT_WORK(&qv->rx_dim.work, idpf_rx_dim_work); + qv->rx_dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE; + qv->rx_dim.profile_ix = IDPF_DIM_DEFAULT_PROFILE_IX; +} + +/** + * idpf_vport_intr_napi_ena_all - Enable NAPI for all q_vectors in the vport + * @vport: main vport structure + */ +static void idpf_vport_intr_napi_ena_all(struct idpf_vport *vport) +{ + int q_idx; + + for (q_idx = 0; q_idx < vport->num_q_vectors; q_idx++) { + struct idpf_q_vector *q_vector = &vport->q_vectors[q_idx]; + + idpf_init_dim(q_vector); + napi_enable(&q_vector->napi); + } +} + +/** + * idpf_tx_splitq_clean_all- Clean completion queues + * @q_vec: queue vector + * @budget: Used to determine if we are in netpoll + * @cleaned: returns number of packets cleaned + * + * Returns false if clean is not complete else returns true + */ +static bool idpf_tx_splitq_clean_all(struct idpf_q_vector *q_vec, + int budget, int *cleaned) +{ + u16 num_txq = q_vec->num_txq; + bool clean_complete = true; + int i, budget_per_q; + + if (unlikely(!num_txq)) + return true; + + budget_per_q = DIV_ROUND_UP(budget, num_txq); + for (i = 0; i < num_txq; i++) + clean_complete &= idpf_tx_clean_complq(q_vec->tx[i], + budget_per_q, cleaned); + + return clean_complete; +} + +/** + * idpf_rx_splitq_clean_all- Clean completion queues + * @q_vec: queue vector + * @budget: Used to determine if we are in netpoll + * @cleaned: returns number of packets cleaned + * + * Returns false if clean is not complete else returns true + */ +static bool idpf_rx_splitq_clean_all(struct idpf_q_vector *q_vec, int budget, + int *cleaned) +{ + u16 num_rxq = q_vec->num_rxq; + bool clean_complete = true; + int pkts_cleaned = 0; + int i, budget_per_q; + + /* We attempt to distribute budget to each Rx queue fairly, but don't + * allow the budget to go below 1 because that would exit polling early. + */ + budget_per_q = num_rxq ? max(budget / num_rxq, 1) : 0; + for (i = 0; i < num_rxq; i++) { + struct idpf_queue *rxq = q_vec->rx[i]; + int pkts_cleaned_per_q; + + pkts_cleaned_per_q = idpf_rx_splitq_clean(rxq, budget_per_q); + /* if we clean as many as budgeted, we must not be done */ + if (pkts_cleaned_per_q >= budget_per_q) + clean_complete = false; + pkts_cleaned += pkts_cleaned_per_q; + } + *cleaned = pkts_cleaned; + + for (i = 0; i < q_vec->num_bufq; i++) + idpf_rx_clean_refillq_all(q_vec->bufq[i]); + + return clean_complete; +} + +/** + * idpf_vport_splitq_napi_poll - NAPI handler + * @napi: struct from which you get q_vector + * @budget: budget provided by stack + */ +static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget) +{ + struct idpf_q_vector *q_vector = + container_of(napi, struct idpf_q_vector, napi); + bool clean_complete; + int work_done = 0; + + /* Handle case where we are called by netpoll with a budget of 0 */ + if (unlikely(!budget)) { + idpf_tx_splitq_clean_all(q_vector, budget, &work_done); + + return 0; + } + + clean_complete = idpf_rx_splitq_clean_all(q_vector, budget, &work_done); + clean_complete &= idpf_tx_splitq_clean_all(q_vector, budget, &work_done); + + /* If work not completed, return budget and polling will return */ + if (!clean_complete) + return budget; + + work_done = min_t(int, work_done, budget - 1); + + /* Exit the polling mode, but don't re-enable interrupts if stack might + * poll us due to busy-polling + */ + if (likely(napi_complete_done(napi, work_done))) + idpf_vport_intr_update_itr_ena_irq(q_vector); + + /* Switch to poll mode in the tear-down path after sending disable + * queues virtchnl message, as the interrupts will be disabled after + * that + */ + if (unlikely(q_vector->num_txq && test_bit(__IDPF_Q_POLL_MODE, + q_vector->tx[0]->flags))) + return budget; + else + return work_done; +} + +/** + * idpf_vport_intr_map_vector_to_qs - Map vectors to queues + * @vport: virtual port + * + * Mapping for vectors to queues + */ +static void idpf_vport_intr_map_vector_to_qs(struct idpf_vport *vport) +{ + u16 num_txq_grp = vport->num_txq_grp; + int i, j, qv_idx, bufq_vidx = 0; + struct idpf_rxq_group *rx_qgrp; + struct idpf_txq_group *tx_qgrp; + struct idpf_queue *q, *bufq; + u16 q_index; + + for (i = 0, qv_idx = 0; i < vport->num_rxq_grp; i++) { + u16 num_rxq; + + rx_qgrp = &vport->rxq_grps[i]; + if (idpf_is_queue_model_split(vport->rxq_model)) + num_rxq = rx_qgrp->splitq.num_rxq_sets; + else + num_rxq = rx_qgrp->singleq.num_rxq; + + for (j = 0; j < num_rxq; j++) { + if (qv_idx >= vport->num_q_vectors) + qv_idx = 0; + + if (idpf_is_queue_model_split(vport->rxq_model)) + q = &rx_qgrp->splitq.rxq_sets[j]->rxq; + else + q = rx_qgrp->singleq.rxqs[j]; + q->q_vector = &vport->q_vectors[qv_idx]; + q_index = q->q_vector->num_rxq; + q->q_vector->rx[q_index] = q; + q->q_vector->num_rxq++; + qv_idx++; + } + + if (idpf_is_queue_model_split(vport->rxq_model)) { + for (j = 0; j < vport->num_bufqs_per_qgrp; j++) { + bufq = &rx_qgrp->splitq.bufq_sets[j].bufq; + bufq->q_vector = &vport->q_vectors[bufq_vidx]; + q_index = bufq->q_vector->num_bufq; + bufq->q_vector->bufq[q_index] = bufq; + bufq->q_vector->num_bufq++; + } + if (++bufq_vidx >= vport->num_q_vectors) + bufq_vidx = 0; + } + } + + for (i = 0, qv_idx = 0; i < num_txq_grp; i++) { + u16 num_txq; + + tx_qgrp = &vport->txq_grps[i]; + num_txq = tx_qgrp->num_txq; + + if (idpf_is_queue_model_split(vport->txq_model)) { + if (qv_idx >= vport->num_q_vectors) + qv_idx = 0; + + q = tx_qgrp->complq; + q->q_vector = &vport->q_vectors[qv_idx]; + q_index = q->q_vector->num_txq; + q->q_vector->tx[q_index] = q; + q->q_vector->num_txq++; + qv_idx++; + } else { + for (j = 0; j < num_txq; j++) { + if (qv_idx >= vport->num_q_vectors) + qv_idx = 0; + + q = tx_qgrp->txqs[j]; + q->q_vector = &vport->q_vectors[qv_idx]; + q_index = q->q_vector->num_txq; + q->q_vector->tx[q_index] = q; + q->q_vector->num_txq++; + + qv_idx++; + } + } + } +} + +/** + * idpf_vport_intr_init_vec_idx - Initialize the vector indexes + * @vport: virtual port + * + * Initialize vector indexes with values returened over mailbox + */ +static int idpf_vport_intr_init_vec_idx(struct idpf_vport *vport) +{ + struct idpf_adapter *adapter = vport->adapter; + struct virtchnl2_alloc_vectors *ac; + u16 *vecids, total_vecs; + int i; + + ac = adapter->req_vec_chunks; + if (!ac) { + for (i = 0; i < vport->num_q_vectors; i++) + vport->q_vectors[i].v_idx = vport->q_vector_idxs[i]; + + return 0; + } + + total_vecs = idpf_get_reserved_vecs(adapter); + vecids = kcalloc(total_vecs, sizeof(u16), GFP_KERNEL); + if (!vecids) + return -ENOMEM; + + idpf_get_vec_ids(adapter, vecids, total_vecs, &ac->vchunks); + + for (i = 0; i < vport->num_q_vectors; i++) + vport->q_vectors[i].v_idx = vecids[vport->q_vector_idxs[i]]; + + kfree(vecids); + + return 0; +} + +/** + * idpf_vport_intr_napi_add_all- Register napi handler for all qvectors + * @vport: virtual port structure + */ +static void idpf_vport_intr_napi_add_all(struct idpf_vport *vport) +{ + int (*napi_poll)(struct napi_struct *napi, int budget); + u16 v_idx; + + if (idpf_is_queue_model_split(vport->txq_model)) + napi_poll = idpf_vport_splitq_napi_poll; + else + napi_poll = idpf_vport_singleq_napi_poll; + + for (v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) { + struct idpf_q_vector *q_vector = &vport->q_vectors[v_idx]; + + netif_napi_add(vport->netdev, &q_vector->napi, napi_poll); + + /* only set affinity_mask if the CPU is online */ + if (cpu_online(v_idx)) + cpumask_set_cpu(v_idx, &q_vector->affinity_mask); + } +} + +/** + * idpf_vport_intr_alloc - Allocate memory for interrupt vectors + * @vport: virtual port + * + * We allocate one q_vector per queue interrupt. If allocation fails we + * return -ENOMEM. + */ +int idpf_vport_intr_alloc(struct idpf_vport *vport) +{ + u16 txqs_per_vector, rxqs_per_vector, bufqs_per_vector; + struct idpf_q_vector *q_vector; + int v_idx, err; + + vport->q_vectors = kcalloc(vport->num_q_vectors, + sizeof(struct idpf_q_vector), GFP_KERNEL); + if (!vport->q_vectors) + return -ENOMEM; + + txqs_per_vector = DIV_ROUND_UP(vport->num_txq, vport->num_q_vectors); + rxqs_per_vector = DIV_ROUND_UP(vport->num_rxq, vport->num_q_vectors); + bufqs_per_vector = vport->num_bufqs_per_qgrp * + DIV_ROUND_UP(vport->num_rxq_grp, + vport->num_q_vectors); + + for (v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) { + q_vector = &vport->q_vectors[v_idx]; + q_vector->vport = vport; + + q_vector->tx_itr_value = IDPF_ITR_TX_DEF; + q_vector->tx_intr_mode = IDPF_ITR_DYNAMIC; + q_vector->tx_itr_idx = VIRTCHNL2_ITR_IDX_1; + + q_vector->rx_itr_value = IDPF_ITR_RX_DEF; + q_vector->rx_intr_mode = IDPF_ITR_DYNAMIC; + q_vector->rx_itr_idx = VIRTCHNL2_ITR_IDX_0; + + q_vector->tx = kcalloc(txqs_per_vector, + sizeof(struct idpf_queue *), + GFP_KERNEL); + if (!q_vector->tx) { + err = -ENOMEM; + goto error; + } + + q_vector->rx = kcalloc(rxqs_per_vector, + sizeof(struct idpf_queue *), + GFP_KERNEL); + if (!q_vector->rx) { + err = -ENOMEM; + goto error; + } + + if (!idpf_is_queue_model_split(vport->rxq_model)) + continue; + + q_vector->bufq = kcalloc(bufqs_per_vector, + sizeof(struct idpf_queue *), + GFP_KERNEL); + if (!q_vector->bufq) { + err = -ENOMEM; + goto error; + } + } + + return 0; + +error: + idpf_vport_intr_rel(vport); + + return err; +} + +/** + * idpf_vport_intr_init - Setup all vectors for the given vport + * @vport: virtual port + * + * Returns 0 on success or negative on failure + */ +int idpf_vport_intr_init(struct idpf_vport *vport) +{ + char *int_name; + int err; + + err = idpf_vport_intr_init_vec_idx(vport); + if (err) + return err; + + idpf_vport_intr_map_vector_to_qs(vport); + idpf_vport_intr_napi_add_all(vport); + idpf_vport_intr_napi_ena_all(vport); + + err = vport->adapter->dev_ops.reg_ops.intr_reg_init(vport); + if (err) + goto unroll_vectors_alloc; + + int_name = kasprintf(GFP_KERNEL, "%s-%s", + dev_driver_string(&vport->adapter->pdev->dev), + vport->netdev->name); + + err = idpf_vport_intr_req_irq(vport, int_name); + if (err) + goto unroll_vectors_alloc; + + idpf_vport_intr_ena_irq_all(vport); + + return 0; + +unroll_vectors_alloc: + idpf_vport_intr_napi_dis_all(vport); + idpf_vport_intr_napi_del_all(vport); + + return err; +} + +/** + * idpf_config_rss - Send virtchnl messages to configure RSS + * @vport: virtual port + * + * Return 0 on success, negative on failure + */ +int idpf_config_rss(struct idpf_vport *vport) +{ + int err; + + err = idpf_send_get_set_rss_key_msg(vport, false); + if (err) + return err; + + return idpf_send_get_set_rss_lut_msg(vport, false); +} + +/** + * idpf_fill_dflt_rss_lut - Fill the indirection table with the default values + * @vport: virtual port structure + */ +static void idpf_fill_dflt_rss_lut(struct idpf_vport *vport) +{ + struct idpf_adapter *adapter = vport->adapter; + u16 num_active_rxq = vport->num_rxq; + struct idpf_rss_data *rss_data; + int i; + + rss_data = &adapter->vport_config[vport->idx]->user_config.rss_data; + + for (i = 0; i < rss_data->rss_lut_size; i++) { + rss_data->rss_lut[i] = i % num_active_rxq; + rss_data->cached_lut[i] = rss_data->rss_lut[i]; + } +} + +/** + * idpf_init_rss - Allocate and initialize RSS resources + * @vport: virtual port + * + * Return 0 on success, negative on failure + */ +int idpf_init_rss(struct idpf_vport *vport) +{ + struct idpf_adapter *adapter = vport->adapter; + struct idpf_rss_data *rss_data; + u32 lut_size; + + rss_data = &adapter->vport_config[vport->idx]->user_config.rss_data; + + lut_size = rss_data->rss_lut_size * sizeof(u32); + rss_data->rss_lut = kzalloc(lut_size, GFP_KERNEL); + if (!rss_data->rss_lut) + return -ENOMEM; + + rss_data->cached_lut = kzalloc(lut_size, GFP_KERNEL); + if (!rss_data->cached_lut) { + kfree(rss_data->rss_lut); + rss_data->rss_lut = NULL; + + return -ENOMEM; + } + + /* Fill the default RSS lut values */ + idpf_fill_dflt_rss_lut(vport); + + return idpf_config_rss(vport); +} + +/** + * idpf_deinit_rss - Release RSS resources + * @vport: virtual port + */ +void idpf_deinit_rss(struct idpf_vport *vport) +{ + struct idpf_adapter *adapter = vport->adapter; + struct idpf_rss_data *rss_data; + + rss_data = &adapter->vport_config[vport->idx]->user_config.rss_data; + kfree(rss_data->cached_lut); + rss_data->cached_lut = NULL; + kfree(rss_data->rss_lut); + rss_data->rss_lut = NULL; +} diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h new file mode 100644 index 000000000000..df76493faa75 --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h @@ -0,0 +1,1023 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2023 Intel Corporation */ + +#ifndef _IDPF_TXRX_H_ +#define _IDPF_TXRX_H_ + +#include <net/page_pool/helpers.h> +#include <net/tcp.h> +#include <net/netdev_queues.h> + +#define IDPF_LARGE_MAX_Q 256 +#define IDPF_MAX_Q 16 +#define IDPF_MIN_Q 2 +/* Mailbox Queue */ +#define IDPF_MAX_MBXQ 1 + +#define IDPF_MIN_TXQ_DESC 64 +#define IDPF_MIN_RXQ_DESC 64 +#define IDPF_MIN_TXQ_COMPLQ_DESC 256 +#define IDPF_MAX_QIDS 256 + +/* Number of descriptors in a queue should be a multiple of 32. RX queue + * descriptors alone should be a multiple of IDPF_REQ_RXQ_DESC_MULTIPLE + * to achieve BufQ descriptors aligned to 32 + */ +#define IDPF_REQ_DESC_MULTIPLE 32 +#define IDPF_REQ_RXQ_DESC_MULTIPLE (IDPF_MAX_BUFQS_PER_RXQ_GRP * 32) +#define IDPF_MIN_TX_DESC_NEEDED (MAX_SKB_FRAGS + 6) +#define IDPF_TX_WAKE_THRESH ((u16)IDPF_MIN_TX_DESC_NEEDED * 2) + +#define IDPF_MAX_DESCS 8160 +#define IDPF_MAX_TXQ_DESC ALIGN_DOWN(IDPF_MAX_DESCS, IDPF_REQ_DESC_MULTIPLE) +#define IDPF_MAX_RXQ_DESC ALIGN_DOWN(IDPF_MAX_DESCS, IDPF_REQ_RXQ_DESC_MULTIPLE) +#define MIN_SUPPORT_TXDID (\ + VIRTCHNL2_TXDID_FLEX_FLOW_SCHED |\ + VIRTCHNL2_TXDID_FLEX_TSO_CTX) + +#define IDPF_DFLT_SINGLEQ_TX_Q_GROUPS 1 +#define IDPF_DFLT_SINGLEQ_RX_Q_GROUPS 1 +#define IDPF_DFLT_SINGLEQ_TXQ_PER_GROUP 4 +#define IDPF_DFLT_SINGLEQ_RXQ_PER_GROUP 4 + +#define IDPF_COMPLQ_PER_GROUP 1 +#define IDPF_SINGLE_BUFQ_PER_RXQ_GRP 1 +#define IDPF_MAX_BUFQS_PER_RXQ_GRP 2 +#define IDPF_BUFQ2_ENA 1 +#define IDPF_NUMQ_PER_CHUNK 1 + +#define IDPF_DFLT_SPLITQ_TXQ_PER_GROUP 1 +#define IDPF_DFLT_SPLITQ_RXQ_PER_GROUP 1 + +/* Default vector sharing */ +#define IDPF_MBX_Q_VEC 1 +#define IDPF_MIN_Q_VEC 1 + +#define IDPF_DFLT_TX_Q_DESC_COUNT 512 +#define IDPF_DFLT_TX_COMPLQ_DESC_COUNT 512 +#define IDPF_DFLT_RX_Q_DESC_COUNT 512 + +/* IMPORTANT: We absolutely _cannot_ have more buffers in the system than a + * given RX completion queue has descriptors. This includes _ALL_ buffer + * queues. E.g.: If you have two buffer queues of 512 descriptors and buffers, + * you have a total of 1024 buffers so your RX queue _must_ have at least that + * many descriptors. This macro divides a given number of RX descriptors by + * number of buffer queues to calculate how many descriptors each buffer queue + * can have without overrunning the RX queue. + * + * If you give hardware more buffers than completion descriptors what will + * happen is that if hardware gets a chance to post more than ring wrap of + * descriptors before SW gets an interrupt and overwrites SW head, the gen bit + * in the descriptor will be wrong. Any overwritten descriptors' buffers will + * be gone forever and SW has no reasonable way to tell that this has happened. + * From SW perspective, when we finally get an interrupt, it looks like we're + * still waiting for descriptor to be done, stalling forever. + */ +#define IDPF_RX_BUFQ_DESC_COUNT(RXD, NUM_BUFQ) ((RXD) / (NUM_BUFQ)) + +#define IDPF_RX_BUFQ_WORKING_SET(rxq) ((rxq)->desc_count - 1) + +#define IDPF_RX_BUMP_NTC(rxq, ntc) \ +do { \ + if (unlikely(++(ntc) == (rxq)->desc_count)) { \ + ntc = 0; \ + change_bit(__IDPF_Q_GEN_CHK, (rxq)->flags); \ + } \ +} while (0) + +#define IDPF_SINGLEQ_BUMP_RING_IDX(q, idx) \ +do { \ + if (unlikely(++(idx) == (q)->desc_count)) \ + idx = 0; \ +} while (0) + +#define IDPF_RX_HDR_SIZE 256 +#define IDPF_RX_BUF_2048 2048 +#define IDPF_RX_BUF_4096 4096 +#define IDPF_RX_BUF_STRIDE 32 +#define IDPF_RX_BUF_POST_STRIDE 16 +#define IDPF_LOW_WATERMARK 64 +/* Size of header buffer specifically for header split */ +#define IDPF_HDR_BUF_SIZE 256 +#define IDPF_PACKET_HDR_PAD \ + (ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN * 2) +#define IDPF_TX_TSO_MIN_MSS 88 + +/* Minimum number of descriptors between 2 descriptors with the RE bit set; + * only relevant in flow scheduling mode + */ +#define IDPF_TX_SPLITQ_RE_MIN_GAP 64 + +#define IDPF_RX_BI_BUFID_S 0 +#define IDPF_RX_BI_BUFID_M GENMASK(14, 0) +#define IDPF_RX_BI_GEN_S 15 +#define IDPF_RX_BI_GEN_M BIT(IDPF_RX_BI_GEN_S) +#define IDPF_RXD_EOF_SPLITQ VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_EOF_M +#define IDPF_RXD_EOF_SINGLEQ VIRTCHNL2_RX_BASE_DESC_STATUS_EOF_M + +#define IDPF_SINGLEQ_RX_BUF_DESC(rxq, i) \ + (&(((struct virtchnl2_singleq_rx_buf_desc *)((rxq)->desc_ring))[i])) +#define IDPF_SPLITQ_RX_BUF_DESC(rxq, i) \ + (&(((struct virtchnl2_splitq_rx_buf_desc *)((rxq)->desc_ring))[i])) +#define IDPF_SPLITQ_RX_BI_DESC(rxq, i) ((((rxq)->ring))[i]) + +#define IDPF_BASE_TX_DESC(txq, i) \ + (&(((struct idpf_base_tx_desc *)((txq)->desc_ring))[i])) +#define IDPF_BASE_TX_CTX_DESC(txq, i) \ + (&(((struct idpf_base_tx_ctx_desc *)((txq)->desc_ring))[i])) +#define IDPF_SPLITQ_TX_COMPLQ_DESC(txcq, i) \ + (&(((struct idpf_splitq_tx_compl_desc *)((txcq)->desc_ring))[i])) + +#define IDPF_FLEX_TX_DESC(txq, i) \ + (&(((union idpf_tx_flex_desc *)((txq)->desc_ring))[i])) +#define IDPF_FLEX_TX_CTX_DESC(txq, i) \ + (&(((struct idpf_flex_tx_ctx_desc *)((txq)->desc_ring))[i])) + +#define IDPF_DESC_UNUSED(txq) \ + ((((txq)->next_to_clean > (txq)->next_to_use) ? 0 : (txq)->desc_count) + \ + (txq)->next_to_clean - (txq)->next_to_use - 1) + +#define IDPF_TX_BUF_RSV_UNUSED(txq) ((txq)->buf_stack.top) +#define IDPF_TX_BUF_RSV_LOW(txq) (IDPF_TX_BUF_RSV_UNUSED(txq) < \ + (txq)->desc_count >> 2) + +#define IDPF_TX_COMPLQ_OVERFLOW_THRESH(txcq) ((txcq)->desc_count >> 1) +/* Determine the absolute number of completions pending, i.e. the number of + * completions that are expected to arrive on the TX completion queue. + */ +#define IDPF_TX_COMPLQ_PENDING(txq) \ + (((txq)->num_completions_pending >= (txq)->complq->num_completions ? \ + 0 : U64_MAX) + \ + (txq)->num_completions_pending - (txq)->complq->num_completions) + +#define IDPF_TX_SPLITQ_COMPL_TAG_WIDTH 16 +#define IDPF_SPLITQ_TX_INVAL_COMPL_TAG -1 +/* Adjust the generation for the completion tag and wrap if necessary */ +#define IDPF_TX_ADJ_COMPL_TAG_GEN(txq) \ + ((++(txq)->compl_tag_cur_gen) >= (txq)->compl_tag_gen_max ? \ + 0 : (txq)->compl_tag_cur_gen) + +#define IDPF_TXD_LAST_DESC_CMD (IDPF_TX_DESC_CMD_EOP | IDPF_TX_DESC_CMD_RS) + +#define IDPF_TX_FLAGS_TSO BIT(0) +#define IDPF_TX_FLAGS_IPV4 BIT(1) +#define IDPF_TX_FLAGS_IPV6 BIT(2) +#define IDPF_TX_FLAGS_TUNNEL BIT(3) + +union idpf_tx_flex_desc { + struct idpf_flex_tx_desc q; /* queue based scheduling */ + struct idpf_flex_tx_sched_desc flow; /* flow based scheduling */ +}; + +/** + * struct idpf_tx_buf + * @next_to_watch: Next descriptor to clean + * @skb: Pointer to the skb + * @dma: DMA address + * @len: DMA length + * @bytecount: Number of bytes + * @gso_segs: Number of GSO segments + * @compl_tag: Splitq only, unique identifier for a buffer. Used to compare + * with completion tag returned in buffer completion event. + * Because the completion tag is expected to be the same in all + * data descriptors for a given packet, and a single packet can + * span multiple buffers, we need this field to track all + * buffers associated with this completion tag independently of + * the buf_id. The tag consists of a N bit buf_id and M upper + * order "generation bits". See compl_tag_bufid_m and + * compl_tag_gen_s in struct idpf_queue. We'll use a value of -1 + * to indicate the tag is not valid. + * @ctx_entry: Singleq only. Used to indicate the corresponding entry + * in the descriptor ring was used for a context descriptor and + * this buffer entry should be skipped. + */ +struct idpf_tx_buf { + void *next_to_watch; + struct sk_buff *skb; + DEFINE_DMA_UNMAP_ADDR(dma); + DEFINE_DMA_UNMAP_LEN(len); + unsigned int bytecount; + unsigned short gso_segs; + + union { + int compl_tag; + + bool ctx_entry; + }; +}; + +struct idpf_tx_stash { + struct hlist_node hlist; + struct idpf_tx_buf buf; +}; + +/** + * struct idpf_buf_lifo - LIFO for managing OOO completions + * @top: Used to know how many buffers are left + * @size: Total size of LIFO + * @bufs: Backing array + */ +struct idpf_buf_lifo { + u16 top; + u16 size; + struct idpf_tx_stash **bufs; +}; + +/** + * struct idpf_tx_offload_params - Offload parameters for a given packet + * @tx_flags: Feature flags enabled for this packet + * @hdr_offsets: Offset parameter for single queue model + * @cd_tunneling: Type of tunneling enabled for single queue model + * @tso_len: Total length of payload to segment + * @mss: Segment size + * @tso_segs: Number of segments to be sent + * @tso_hdr_len: Length of headers to be duplicated + * @td_cmd: Command field to be inserted into descriptor + */ +struct idpf_tx_offload_params { + u32 tx_flags; + + u32 hdr_offsets; + u32 cd_tunneling; + + u32 tso_len; + u16 mss; + u16 tso_segs; + u16 tso_hdr_len; + + u16 td_cmd; +}; + +/** + * struct idpf_tx_splitq_params + * @dtype: General descriptor info + * @eop_cmd: Type of EOP + * @compl_tag: Associated tag for completion + * @td_tag: Descriptor tunneling tag + * @offload: Offload parameters + */ +struct idpf_tx_splitq_params { + enum idpf_tx_desc_dtype_value dtype; + u16 eop_cmd; + union { + u16 compl_tag; + u16 td_tag; + }; + + struct idpf_tx_offload_params offload; +}; + +enum idpf_tx_ctx_desc_eipt_offload { + IDPF_TX_CTX_EXT_IP_NONE = 0x0, + IDPF_TX_CTX_EXT_IP_IPV6 = 0x1, + IDPF_TX_CTX_EXT_IP_IPV4_NO_CSUM = 0x2, + IDPF_TX_CTX_EXT_IP_IPV4 = 0x3 +}; + +/* Checksum offload bits decoded from the receive descriptor. */ +struct idpf_rx_csum_decoded { + u32 l3l4p : 1; + u32 ipe : 1; + u32 eipe : 1; + u32 eudpe : 1; + u32 ipv6exadd : 1; + u32 l4e : 1; + u32 pprs : 1; + u32 nat : 1; + u32 raw_csum_inv : 1; + u32 raw_csum : 16; +}; + +struct idpf_rx_extracted { + unsigned int size; + u16 rx_ptype; +}; + +#define IDPF_TX_COMPLQ_CLEAN_BUDGET 256 +#define IDPF_TX_MIN_PKT_LEN 17 +#define IDPF_TX_DESCS_FOR_SKB_DATA_PTR 1 +#define IDPF_TX_DESCS_PER_CACHE_LINE (L1_CACHE_BYTES / \ + sizeof(struct idpf_flex_tx_desc)) +#define IDPF_TX_DESCS_FOR_CTX 1 +/* TX descriptors needed, worst case */ +#define IDPF_TX_DESC_NEEDED (MAX_SKB_FRAGS + IDPF_TX_DESCS_FOR_CTX + \ + IDPF_TX_DESCS_PER_CACHE_LINE + \ + IDPF_TX_DESCS_FOR_SKB_DATA_PTR) + +/* The size limit for a transmit buffer in a descriptor is (16K - 1). + * In order to align with the read requests we will align the value to + * the nearest 4K which represents our maximum read request size. + */ +#define IDPF_TX_MAX_READ_REQ_SIZE SZ_4K +#define IDPF_TX_MAX_DESC_DATA (SZ_16K - 1) +#define IDPF_TX_MAX_DESC_DATA_ALIGNED \ + ALIGN_DOWN(IDPF_TX_MAX_DESC_DATA, IDPF_TX_MAX_READ_REQ_SIZE) + +#define IDPF_RX_DMA_ATTR \ + (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) +#define IDPF_RX_DESC(rxq, i) \ + (&(((union virtchnl2_rx_desc *)((rxq)->desc_ring))[i])) + +struct idpf_rx_buf { + struct page *page; + unsigned int page_offset; + u16 truesize; +}; + +#define IDPF_RX_MAX_PTYPE_PROTO_IDS 32 +#define IDPF_RX_MAX_PTYPE_SZ (sizeof(struct virtchnl2_ptype) + \ + (sizeof(u16) * IDPF_RX_MAX_PTYPE_PROTO_IDS)) +#define IDPF_RX_PTYPE_HDR_SZ sizeof(struct virtchnl2_get_ptype_info) +#define IDPF_RX_MAX_PTYPES_PER_BUF \ + DIV_ROUND_DOWN_ULL((IDPF_CTLQ_MAX_BUF_LEN - IDPF_RX_PTYPE_HDR_SZ), \ + IDPF_RX_MAX_PTYPE_SZ) + +#define IDPF_GET_PTYPE_SIZE(p) struct_size((p), proto_id, (p)->proto_id_count) + +#define IDPF_TUN_IP_GRE (\ + IDPF_PTYPE_TUNNEL_IP |\ + IDPF_PTYPE_TUNNEL_IP_GRENAT) + +#define IDPF_TUN_IP_GRE_MAC (\ + IDPF_TUN_IP_GRE |\ + IDPF_PTYPE_TUNNEL_IP_GRENAT_MAC) + +#define IDPF_RX_MAX_PTYPE 1024 +#define IDPF_RX_MAX_BASE_PTYPE 256 +#define IDPF_INVALID_PTYPE_ID 0xFFFF + +/* Packet type non-ip values */ +enum idpf_rx_ptype_l2 { + IDPF_RX_PTYPE_L2_RESERVED = 0, + IDPF_RX_PTYPE_L2_MAC_PAY2 = 1, + IDPF_RX_PTYPE_L2_TIMESYNC_PAY2 = 2, + IDPF_RX_PTYPE_L2_FIP_PAY2 = 3, + IDPF_RX_PTYPE_L2_OUI_PAY2 = 4, + IDPF_RX_PTYPE_L2_MACCNTRL_PAY2 = 5, + IDPF_RX_PTYPE_L2_LLDP_PAY2 = 6, + IDPF_RX_PTYPE_L2_ECP_PAY2 = 7, + IDPF_RX_PTYPE_L2_EVB_PAY2 = 8, + IDPF_RX_PTYPE_L2_QCN_PAY2 = 9, + IDPF_RX_PTYPE_L2_EAPOL_PAY2 = 10, + IDPF_RX_PTYPE_L2_ARP = 11, +}; + +enum idpf_rx_ptype_outer_ip { + IDPF_RX_PTYPE_OUTER_L2 = 0, + IDPF_RX_PTYPE_OUTER_IP = 1, +}; + +#define IDPF_RX_PTYPE_TO_IPV(ptype, ipv) \ + (((ptype)->outer_ip == IDPF_RX_PTYPE_OUTER_IP) && \ + ((ptype)->outer_ip_ver == (ipv))) + +enum idpf_rx_ptype_outer_ip_ver { + IDPF_RX_PTYPE_OUTER_NONE = 0, + IDPF_RX_PTYPE_OUTER_IPV4 = 1, + IDPF_RX_PTYPE_OUTER_IPV6 = 2, +}; + +enum idpf_rx_ptype_outer_fragmented { + IDPF_RX_PTYPE_NOT_FRAG = 0, + IDPF_RX_PTYPE_FRAG = 1, +}; + +enum idpf_rx_ptype_tunnel_type { + IDPF_RX_PTYPE_TUNNEL_NONE = 0, + IDPF_RX_PTYPE_TUNNEL_IP_IP = 1, + IDPF_RX_PTYPE_TUNNEL_IP_GRENAT = 2, + IDPF_RX_PTYPE_TUNNEL_IP_GRENAT_MAC = 3, + IDPF_RX_PTYPE_TUNNEL_IP_GRENAT_MAC_VLAN = 4, +}; + +enum idpf_rx_ptype_tunnel_end_prot { + IDPF_RX_PTYPE_TUNNEL_END_NONE = 0, + IDPF_RX_PTYPE_TUNNEL_END_IPV4 = 1, + IDPF_RX_PTYPE_TUNNEL_END_IPV6 = 2, +}; + +enum idpf_rx_ptype_inner_prot { + IDPF_RX_PTYPE_INNER_PROT_NONE = 0, + IDPF_RX_PTYPE_INNER_PROT_UDP = 1, + IDPF_RX_PTYPE_INNER_PROT_TCP = 2, + IDPF_RX_PTYPE_INNER_PROT_SCTP = 3, + IDPF_RX_PTYPE_INNER_PROT_ICMP = 4, + IDPF_RX_PTYPE_INNER_PROT_TIMESYNC = 5, +}; + +enum idpf_rx_ptype_payload_layer { + IDPF_RX_PTYPE_PAYLOAD_LAYER_NONE = 0, + IDPF_RX_PTYPE_PAYLOAD_LAYER_PAY2 = 1, + IDPF_RX_PTYPE_PAYLOAD_LAYER_PAY3 = 2, + IDPF_RX_PTYPE_PAYLOAD_LAYER_PAY4 = 3, +}; + +enum idpf_tunnel_state { + IDPF_PTYPE_TUNNEL_IP = BIT(0), + IDPF_PTYPE_TUNNEL_IP_GRENAT = BIT(1), + IDPF_PTYPE_TUNNEL_IP_GRENAT_MAC = BIT(2), +}; + +struct idpf_ptype_state { + bool outer_ip; + bool outer_frag; + u8 tunnel_state; +}; + +struct idpf_rx_ptype_decoded { + u32 ptype:10; + u32 known:1; + u32 outer_ip:1; + u32 outer_ip_ver:2; + u32 outer_frag:1; + u32 tunnel_type:3; + u32 tunnel_end_prot:2; + u32 tunnel_end_frag:1; + u32 inner_prot:4; + u32 payload_layer:3; +}; + +/** + * enum idpf_queue_flags_t + * @__IDPF_Q_GEN_CHK: Queues operating in splitq mode use a generation bit to + * identify new descriptor writebacks on the ring. HW sets + * the gen bit to 1 on the first writeback of any given + * descriptor. After the ring wraps, HW sets the gen bit of + * those descriptors to 0, and continues flipping + * 0->1 or 1->0 on each ring wrap. SW maintains its own + * gen bit to know what value will indicate writebacks on + * the next pass around the ring. E.g. it is initialized + * to 1 and knows that reading a gen bit of 1 in any + * descriptor on the initial pass of the ring indicates a + * writeback. It also flips on every ring wrap. + * @__IDPF_RFLQ_GEN_CHK: Refill queues are SW only, so Q_GEN acts as the HW bit + * and RFLGQ_GEN is the SW bit. + * @__IDPF_Q_FLOW_SCH_EN: Enable flow scheduling + * @__IDPF_Q_SW_MARKER: Used to indicate TX queue marker completions + * @__IDPF_Q_POLL_MODE: Enable poll mode + * @__IDPF_Q_FLAGS_NBITS: Must be last + */ +enum idpf_queue_flags_t { + __IDPF_Q_GEN_CHK, + __IDPF_RFLQ_GEN_CHK, + __IDPF_Q_FLOW_SCH_EN, + __IDPF_Q_SW_MARKER, + __IDPF_Q_POLL_MODE, + + __IDPF_Q_FLAGS_NBITS, +}; + +/** + * struct idpf_vec_regs + * @dyn_ctl_reg: Dynamic control interrupt register offset + * @itrn_reg: Interrupt Throttling Rate register offset + * @itrn_index_spacing: Register spacing between ITR registers of the same + * vector + */ +struct idpf_vec_regs { + u32 dyn_ctl_reg; + u32 itrn_reg; + u32 itrn_index_spacing; +}; + +/** + * struct idpf_intr_reg + * @dyn_ctl: Dynamic control interrupt register + * @dyn_ctl_intena_m: Mask for dyn_ctl interrupt enable + * @dyn_ctl_itridx_s: Register bit offset for ITR index + * @dyn_ctl_itridx_m: Mask for ITR index + * @dyn_ctl_intrvl_s: Register bit offset for ITR interval + * @rx_itr: RX ITR register + * @tx_itr: TX ITR register + * @icr_ena: Interrupt cause register offset + * @icr_ena_ctlq_m: Mask for ICR + */ +struct idpf_intr_reg { + void __iomem *dyn_ctl; + u32 dyn_ctl_intena_m; + u32 dyn_ctl_itridx_s; + u32 dyn_ctl_itridx_m; + u32 dyn_ctl_intrvl_s; + void __iomem *rx_itr; + void __iomem *tx_itr; + void __iomem *icr_ena; + u32 icr_ena_ctlq_m; +}; + +/** + * struct idpf_q_vector + * @vport: Vport back pointer + * @affinity_mask: CPU affinity mask + * @napi: napi handler + * @v_idx: Vector index + * @intr_reg: See struct idpf_intr_reg + * @num_txq: Number of TX queues + * @tx: Array of TX queues to service + * @tx_dim: Data for TX net_dim algorithm + * @tx_itr_value: TX interrupt throttling rate + * @tx_intr_mode: Dynamic ITR or not + * @tx_itr_idx: TX ITR index + * @num_rxq: Number of RX queues + * @rx: Array of RX queues to service + * @rx_dim: Data for RX net_dim algorithm + * @rx_itr_value: RX interrupt throttling rate + * @rx_intr_mode: Dynamic ITR or not + * @rx_itr_idx: RX ITR index + * @num_bufq: Number of buffer queues + * @bufq: Array of buffer queues to service + * @total_events: Number of interrupts processed + * @name: Queue vector name + */ +struct idpf_q_vector { + struct idpf_vport *vport; + cpumask_t affinity_mask; + struct napi_struct napi; + u16 v_idx; + struct idpf_intr_reg intr_reg; + + u16 num_txq; + struct idpf_queue **tx; + struct dim tx_dim; + u16 tx_itr_value; + bool tx_intr_mode; + u32 tx_itr_idx; + + u16 num_rxq; + struct idpf_queue **rx; + struct dim rx_dim; + u16 rx_itr_value; + bool rx_intr_mode; + u32 rx_itr_idx; + + u16 num_bufq; + struct idpf_queue **bufq; + + u16 total_events; + char *name; +}; + +struct idpf_rx_queue_stats { + u64_stats_t packets; + u64_stats_t bytes; + u64_stats_t rsc_pkts; + u64_stats_t hw_csum_err; + u64_stats_t hsplit_pkts; + u64_stats_t hsplit_buf_ovf; + u64_stats_t bad_descs; +}; + +struct idpf_tx_queue_stats { + u64_stats_t packets; + u64_stats_t bytes; + u64_stats_t lso_pkts; + u64_stats_t linearize; + u64_stats_t q_busy; + u64_stats_t skb_drops; + u64_stats_t dma_map_errs; +}; + +struct idpf_cleaned_stats { + u32 packets; + u32 bytes; +}; + +union idpf_queue_stats { + struct idpf_rx_queue_stats rx; + struct idpf_tx_queue_stats tx; +}; + +#define IDPF_ITR_DYNAMIC 1 +#define IDPF_ITR_MAX 0x1FE0 +#define IDPF_ITR_20K 0x0032 +#define IDPF_ITR_GRAN_S 1 /* Assume ITR granularity is 2us */ +#define IDPF_ITR_MASK 0x1FFE /* ITR register value alignment mask */ +#define ITR_REG_ALIGN(setting) ((setting) & IDPF_ITR_MASK) +#define IDPF_ITR_IS_DYNAMIC(itr_mode) (itr_mode) +#define IDPF_ITR_TX_DEF IDPF_ITR_20K +#define IDPF_ITR_RX_DEF IDPF_ITR_20K +/* Index used for 'No ITR' update in DYN_CTL register */ +#define IDPF_NO_ITR_UPDATE_IDX 3 +#define IDPF_ITR_IDX_SPACING(spacing, dflt) (spacing ? spacing : dflt) +#define IDPF_DIM_DEFAULT_PROFILE_IX 1 + +/** + * struct idpf_queue + * @dev: Device back pointer for DMA mapping + * @vport: Back pointer to associated vport + * @txq_grp: See struct idpf_txq_group + * @rxq_grp: See struct idpf_rxq_group + * @idx: For buffer queue, it is used as group id, either 0 or 1. On clean, + * buffer queue uses this index to determine which group of refill queues + * to clean. + * For TX queue, it is used as index to map between TX queue group and + * hot path TX pointers stored in vport. Used in both singleq/splitq. + * For RX queue, it is used to index to total RX queue across groups and + * used for skb reporting. + * @tail: Tail offset. Used for both queue models single and split. In splitq + * model relevant only for TX queue and RX queue. + * @tx_buf: See struct idpf_tx_buf + * @rx_buf: Struct with RX buffer related members + * @rx_buf.buf: See struct idpf_rx_buf + * @rx_buf.hdr_buf_pa: DMA handle + * @rx_buf.hdr_buf_va: Virtual address + * @pp: Page pool pointer + * @skb: Pointer to the skb + * @q_type: Queue type (TX, RX, TX completion, RX buffer) + * @q_id: Queue id + * @desc_count: Number of descriptors + * @next_to_use: Next descriptor to use. Relevant in both split & single txq + * and bufq. + * @next_to_clean: Next descriptor to clean. In split queue model, only + * relevant to TX completion queue and RX queue. + * @next_to_alloc: RX buffer to allocate at. Used only for RX. In splitq model + * only relevant to RX queue. + * @flags: See enum idpf_queue_flags_t + * @q_stats: See union idpf_queue_stats + * @stats_sync: See struct u64_stats_sync + * @cleaned_bytes: Splitq only, TXQ only: When a TX completion is received on + * the TX completion queue, it can be for any TXQ associated + * with that completion queue. This means we can clean up to + * N TXQs during a single call to clean the completion queue. + * cleaned_bytes|pkts tracks the clean stats per TXQ during + * that single call to clean the completion queue. By doing so, + * we can update BQL with aggregate cleaned stats for each TXQ + * only once at the end of the cleaning routine. + * @cleaned_pkts: Number of packets cleaned for the above said case + * @rx_hsplit_en: RX headsplit enable + * @rx_hbuf_size: Header buffer size + * @rx_buf_size: Buffer size + * @rx_max_pkt_size: RX max packet size + * @rx_buf_stride: RX buffer stride + * @rx_buffer_low_watermark: RX buffer low watermark + * @rxdids: Supported RX descriptor ids + * @q_vector: Backreference to associated vector + * @size: Length of descriptor ring in bytes + * @dma: Physical address of ring + * @desc_ring: Descriptor ring memory + * @tx_max_bufs: Max buffers that can be transmitted with scatter-gather + * @tx_min_pkt_len: Min supported packet length + * @num_completions: Only relevant for TX completion queue. It tracks the + * number of completions received to compare against the + * number of completions pending, as accumulated by the + * TX queues. + * @buf_stack: Stack of empty buffers to store buffer info for out of order + * buffer completions. See struct idpf_buf_lifo. + * @compl_tag_bufid_m: Completion tag buffer id mask + * @compl_tag_gen_s: Completion tag generation bit + * The format of the completion tag will change based on the TXQ + * descriptor ring size so that we can maintain roughly the same level + * of "uniqueness" across all descriptor sizes. For example, if the + * TXQ descriptor ring size is 64 (the minimum size supported), the + * completion tag will be formatted as below: + * 15 6 5 0 + * -------------------------------- + * | GEN=0-1023 |IDX = 0-63| + * -------------------------------- + * + * This gives us 64*1024 = 65536 possible unique values. Similarly, if + * the TXQ descriptor ring size is 8160 (the maximum size supported), + * the completion tag will be formatted as below: + * 15 13 12 0 + * -------------------------------- + * |GEN | IDX = 0-8159 | + * -------------------------------- + * + * This gives us 8*8160 = 65280 possible unique values. + * @compl_tag_cur_gen: Used to keep track of current completion tag generation + * @compl_tag_gen_max: To determine when compl_tag_cur_gen should be reset + * @sched_buf_hash: Hash table to stores buffers + */ +struct idpf_queue { + struct device *dev; + struct idpf_vport *vport; + union { + struct idpf_txq_group *txq_grp; + struct idpf_rxq_group *rxq_grp; + }; + u16 idx; + void __iomem *tail; + union { + struct idpf_tx_buf *tx_buf; + struct { + struct idpf_rx_buf *buf; + dma_addr_t hdr_buf_pa; + void *hdr_buf_va; + } rx_buf; + }; + struct page_pool *pp; + struct sk_buff *skb; + u16 q_type; + u32 q_id; + u16 desc_count; + + u16 next_to_use; + u16 next_to_clean; + u16 next_to_alloc; + DECLARE_BITMAP(flags, __IDPF_Q_FLAGS_NBITS); + + union idpf_queue_stats q_stats; + struct u64_stats_sync stats_sync; + + u32 cleaned_bytes; + u16 cleaned_pkts; + + bool rx_hsplit_en; + u16 rx_hbuf_size; + u16 rx_buf_size; + u16 rx_max_pkt_size; + u16 rx_buf_stride; + u8 rx_buffer_low_watermark; + u64 rxdids; + struct idpf_q_vector *q_vector; + unsigned int size; + dma_addr_t dma; + void *desc_ring; + + u16 tx_max_bufs; + u8 tx_min_pkt_len; + + u32 num_completions; + + struct idpf_buf_lifo buf_stack; + + u16 compl_tag_bufid_m; + u16 compl_tag_gen_s; + + u16 compl_tag_cur_gen; + u16 compl_tag_gen_max; + + DECLARE_HASHTABLE(sched_buf_hash, 12); +} ____cacheline_internodealigned_in_smp; + +/** + * struct idpf_sw_queue + * @next_to_clean: Next descriptor to clean + * @next_to_alloc: Buffer to allocate at + * @flags: See enum idpf_queue_flags_t + * @ring: Pointer to the ring + * @desc_count: Descriptor count + * @dev: Device back pointer for DMA mapping + * + * Software queues are used in splitq mode to manage buffers between rxq + * producer and the bufq consumer. These are required in order to maintain a + * lockless buffer management system and are strictly software only constructs. + */ +struct idpf_sw_queue { + u16 next_to_clean; + u16 next_to_alloc; + DECLARE_BITMAP(flags, __IDPF_Q_FLAGS_NBITS); + u16 *ring; + u16 desc_count; + struct device *dev; +} ____cacheline_internodealigned_in_smp; + +/** + * struct idpf_rxq_set + * @rxq: RX queue + * @refillq0: Pointer to refill queue 0 + * @refillq1: Pointer to refill queue 1 + * + * Splitq only. idpf_rxq_set associates an rxq with at an array of refillqs. + * Each rxq needs a refillq to return used buffers back to the respective bufq. + * Bufqs then clean these refillqs for buffers to give to hardware. + */ +struct idpf_rxq_set { + struct idpf_queue rxq; + struct idpf_sw_queue *refillq0; + struct idpf_sw_queue *refillq1; +}; + +/** + * struct idpf_bufq_set + * @bufq: Buffer queue + * @num_refillqs: Number of refill queues. This is always equal to num_rxq_sets + * in idpf_rxq_group. + * @refillqs: Pointer to refill queues array. + * + * Splitq only. idpf_bufq_set associates a bufq to an array of refillqs. + * In this bufq_set, there will be one refillq for each rxq in this rxq_group. + * Used buffers received by rxqs will be put on refillqs which bufqs will + * clean to return new buffers back to hardware. + * + * Buffers needed by some number of rxqs associated in this rxq_group are + * managed by at most two bufqs (depending on performance configuration). + */ +struct idpf_bufq_set { + struct idpf_queue bufq; + int num_refillqs; + struct idpf_sw_queue *refillqs; +}; + +/** + * struct idpf_rxq_group + * @vport: Vport back pointer + * @singleq: Struct with single queue related members + * @singleq.num_rxq: Number of RX queues associated + * @singleq.rxqs: Array of RX queue pointers + * @splitq: Struct with split queue related members + * @splitq.num_rxq_sets: Number of RX queue sets + * @splitq.rxq_sets: Array of RX queue sets + * @splitq.bufq_sets: Buffer queue set pointer + * + * In singleq mode, an rxq_group is simply an array of rxqs. In splitq, a + * rxq_group contains all the rxqs, bufqs and refillqs needed to + * manage buffers in splitq mode. + */ +struct idpf_rxq_group { + struct idpf_vport *vport; + + union { + struct { + u16 num_rxq; + struct idpf_queue *rxqs[IDPF_LARGE_MAX_Q]; + } singleq; + struct { + u16 num_rxq_sets; + struct idpf_rxq_set *rxq_sets[IDPF_LARGE_MAX_Q]; + struct idpf_bufq_set *bufq_sets; + } splitq; + }; +}; + +/** + * struct idpf_txq_group + * @vport: Vport back pointer + * @num_txq: Number of TX queues associated + * @txqs: Array of TX queue pointers + * @complq: Associated completion queue pointer, split queue only + * @num_completions_pending: Total number of completions pending for the + * completion queue, acculumated for all TX queues + * associated with that completion queue. + * + * Between singleq and splitq, a txq_group is largely the same except for the + * complq. In splitq a single complq is responsible for handling completions + * for some number of txqs associated in this txq_group. + */ +struct idpf_txq_group { + struct idpf_vport *vport; + + u16 num_txq; + struct idpf_queue *txqs[IDPF_LARGE_MAX_Q]; + + struct idpf_queue *complq; + + u32 num_completions_pending; +}; + +/** + * idpf_size_to_txd_count - Get number of descriptors needed for large Tx frag + * @size: transmit request size in bytes + * + * In the case where a large frag (>= 16K) needs to be split across multiple + * descriptors, we need to assume that we can have no more than 12K of data + * per descriptor due to hardware alignment restrictions (4K alignment). + */ +static inline u32 idpf_size_to_txd_count(unsigned int size) +{ + return DIV_ROUND_UP(size, IDPF_TX_MAX_DESC_DATA_ALIGNED); +} + +/** + * idpf_tx_singleq_build_ctob - populate command tag offset and size + * @td_cmd: Command to be filled in desc + * @td_offset: Offset to be filled in desc + * @size: Size of the buffer + * @td_tag: td tag to be filled + * + * Returns the 64 bit value populated with the input parameters + */ +static inline __le64 idpf_tx_singleq_build_ctob(u64 td_cmd, u64 td_offset, + unsigned int size, u64 td_tag) +{ + return cpu_to_le64(IDPF_TX_DESC_DTYPE_DATA | + (td_cmd << IDPF_TXD_QW1_CMD_S) | + (td_offset << IDPF_TXD_QW1_OFFSET_S) | + ((u64)size << IDPF_TXD_QW1_TX_BUF_SZ_S) | + (td_tag << IDPF_TXD_QW1_L2TAG1_S)); +} + +void idpf_tx_splitq_build_ctb(union idpf_tx_flex_desc *desc, + struct idpf_tx_splitq_params *params, + u16 td_cmd, u16 size); +void idpf_tx_splitq_build_flow_desc(union idpf_tx_flex_desc *desc, + struct idpf_tx_splitq_params *params, + u16 td_cmd, u16 size); +/** + * idpf_tx_splitq_build_desc - determine which type of data descriptor to build + * @desc: descriptor to populate + * @params: pointer to tx params struct + * @td_cmd: command to be filled in desc + * @size: size of buffer + */ +static inline void idpf_tx_splitq_build_desc(union idpf_tx_flex_desc *desc, + struct idpf_tx_splitq_params *params, + u16 td_cmd, u16 size) +{ + if (params->dtype == IDPF_TX_DESC_DTYPE_FLEX_L2TAG1_L2TAG2) + idpf_tx_splitq_build_ctb(desc, params, td_cmd, size); + else + idpf_tx_splitq_build_flow_desc(desc, params, td_cmd, size); +} + +/** + * idpf_alloc_page - Allocate a new RX buffer from the page pool + * @pool: page_pool to allocate from + * @buf: metadata struct to populate with page info + * @buf_size: 2K or 4K + * + * Returns &dma_addr_t to be passed to HW for Rx, %DMA_MAPPING_ERROR otherwise. + */ +static inline dma_addr_t idpf_alloc_page(struct page_pool *pool, + struct idpf_rx_buf *buf, + unsigned int buf_size) +{ + if (buf_size == IDPF_RX_BUF_2048) + buf->page = page_pool_dev_alloc_frag(pool, &buf->page_offset, + buf_size); + else + buf->page = page_pool_dev_alloc_pages(pool); + + if (!buf->page) + return DMA_MAPPING_ERROR; + + buf->truesize = buf_size; + + return page_pool_get_dma_addr(buf->page) + buf->page_offset + + pool->p.offset; +} + +/** + * idpf_rx_put_page - Return RX buffer page to pool + * @rx_buf: RX buffer metadata struct + */ +static inline void idpf_rx_put_page(struct idpf_rx_buf *rx_buf) +{ + page_pool_put_page(rx_buf->page->pp, rx_buf->page, + rx_buf->truesize, true); + rx_buf->page = NULL; +} + +/** + * idpf_rx_sync_for_cpu - Synchronize DMA buffer + * @rx_buf: RX buffer metadata struct + * @len: frame length from descriptor + */ +static inline void idpf_rx_sync_for_cpu(struct idpf_rx_buf *rx_buf, u32 len) +{ + struct page *page = rx_buf->page; + struct page_pool *pp = page->pp; + + dma_sync_single_range_for_cpu(pp->p.dev, + page_pool_get_dma_addr(page), + rx_buf->page_offset + pp->p.offset, len, + page_pool_get_dma_dir(pp)); +} + +int idpf_vport_singleq_napi_poll(struct napi_struct *napi, int budget); +void idpf_vport_init_num_qs(struct idpf_vport *vport, + struct virtchnl2_create_vport *vport_msg); +void idpf_vport_calc_num_q_desc(struct idpf_vport *vport); +int idpf_vport_calc_total_qs(struct idpf_adapter *adapter, u16 vport_index, + struct virtchnl2_create_vport *vport_msg, + struct idpf_vport_max_q *max_q); +void idpf_vport_calc_num_q_groups(struct idpf_vport *vport); +int idpf_vport_queues_alloc(struct idpf_vport *vport); +void idpf_vport_queues_rel(struct idpf_vport *vport); +void idpf_vport_intr_rel(struct idpf_vport *vport); +int idpf_vport_intr_alloc(struct idpf_vport *vport); +void idpf_vport_intr_update_itr_ena_irq(struct idpf_q_vector *q_vector); +void idpf_vport_intr_deinit(struct idpf_vport *vport); +int idpf_vport_intr_init(struct idpf_vport *vport); +enum pkt_hash_types idpf_ptype_to_htype(const struct idpf_rx_ptype_decoded *decoded); +int idpf_config_rss(struct idpf_vport *vport); +int idpf_init_rss(struct idpf_vport *vport); +void idpf_deinit_rss(struct idpf_vport *vport); +int idpf_rx_bufs_init_all(struct idpf_vport *vport); +void idpf_rx_add_frag(struct idpf_rx_buf *rx_buf, struct sk_buff *skb, + unsigned int size); +struct sk_buff *idpf_rx_construct_skb(struct idpf_queue *rxq, + struct idpf_rx_buf *rx_buf, + unsigned int size); +bool idpf_init_rx_buf_hw_alloc(struct idpf_queue *rxq, struct idpf_rx_buf *buf); +void idpf_rx_buf_hw_update(struct idpf_queue *rxq, u32 val); +void idpf_tx_buf_hw_update(struct idpf_queue *tx_q, u32 val, + bool xmit_more); +unsigned int idpf_size_to_txd_count(unsigned int size); +netdev_tx_t idpf_tx_drop_skb(struct idpf_queue *tx_q, struct sk_buff *skb); +void idpf_tx_dma_map_error(struct idpf_queue *txq, struct sk_buff *skb, + struct idpf_tx_buf *first, u16 ring_idx); +unsigned int idpf_tx_desc_count_required(struct idpf_queue *txq, + struct sk_buff *skb); +bool idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs, + unsigned int count); +int idpf_tx_maybe_stop_common(struct idpf_queue *tx_q, unsigned int size); +void idpf_tx_timeout(struct net_device *netdev, unsigned int txqueue); +netdev_tx_t idpf_tx_splitq_start(struct sk_buff *skb, + struct net_device *netdev); +netdev_tx_t idpf_tx_singleq_start(struct sk_buff *skb, + struct net_device *netdev); +bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_queue *rxq, + u16 cleaned_count); +int idpf_tso(struct sk_buff *skb, struct idpf_tx_offload_params *off); + +#endif /* !_IDPF_TXRX_H_ */ diff --git a/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c new file mode 100644 index 000000000000..8ade4e3a9fe1 --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c @@ -0,0 +1,163 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2023 Intel Corporation */ + +#include "idpf.h" +#include "idpf_lan_vf_regs.h" + +#define IDPF_VF_ITR_IDX_SPACING 0x40 + +/** + * idpf_vf_ctlq_reg_init - initialize default mailbox registers + * @cq: pointer to the array of create control queues + */ +static void idpf_vf_ctlq_reg_init(struct idpf_ctlq_create_info *cq) +{ + int i; + + for (i = 0; i < IDPF_NUM_DFLT_MBX_Q; i++) { + struct idpf_ctlq_create_info *ccq = cq + i; + + switch (ccq->type) { + case IDPF_CTLQ_TYPE_MAILBOX_TX: + /* set head and tail registers in our local struct */ + ccq->reg.head = VF_ATQH; + ccq->reg.tail = VF_ATQT; + ccq->reg.len = VF_ATQLEN; + ccq->reg.bah = VF_ATQBAH; + ccq->reg.bal = VF_ATQBAL; + ccq->reg.len_mask = VF_ATQLEN_ATQLEN_M; + ccq->reg.len_ena_mask = VF_ATQLEN_ATQENABLE_M; + ccq->reg.head_mask = VF_ATQH_ATQH_M; + break; + case IDPF_CTLQ_TYPE_MAILBOX_RX: + /* set head and tail registers in our local struct */ + ccq->reg.head = VF_ARQH; + ccq->reg.tail = VF_ARQT; + ccq->reg.len = VF_ARQLEN; + ccq->reg.bah = VF_ARQBAH; + ccq->reg.bal = VF_ARQBAL; + ccq->reg.len_mask = VF_ARQLEN_ARQLEN_M; + ccq->reg.len_ena_mask = VF_ARQLEN_ARQENABLE_M; + ccq->reg.head_mask = VF_ARQH_ARQH_M; + break; + default: + break; + } + } +} + +/** + * idpf_vf_mb_intr_reg_init - Initialize the mailbox register + * @adapter: adapter structure + */ +static void idpf_vf_mb_intr_reg_init(struct idpf_adapter *adapter) +{ + struct idpf_intr_reg *intr = &adapter->mb_vector.intr_reg; + u32 dyn_ctl = le32_to_cpu(adapter->caps.mailbox_dyn_ctl); + + intr->dyn_ctl = idpf_get_reg_addr(adapter, dyn_ctl); + intr->dyn_ctl_intena_m = VF_INT_DYN_CTL0_INTENA_M; + intr->dyn_ctl_itridx_m = VF_INT_DYN_CTL0_ITR_INDX_M; + intr->icr_ena = idpf_get_reg_addr(adapter, VF_INT_ICR0_ENA1); + intr->icr_ena_ctlq_m = VF_INT_ICR0_ENA1_ADMINQ_M; +} + +/** + * idpf_vf_intr_reg_init - Initialize interrupt registers + * @vport: virtual port structure + */ +static int idpf_vf_intr_reg_init(struct idpf_vport *vport) +{ + struct idpf_adapter *adapter = vport->adapter; + int num_vecs = vport->num_q_vectors; + struct idpf_vec_regs *reg_vals; + int num_regs, i, err = 0; + u32 rx_itr, tx_itr; + u16 total_vecs; + + total_vecs = idpf_get_reserved_vecs(vport->adapter); + reg_vals = kcalloc(total_vecs, sizeof(struct idpf_vec_regs), + GFP_KERNEL); + if (!reg_vals) + return -ENOMEM; + + num_regs = idpf_get_reg_intr_vecs(vport, reg_vals); + if (num_regs < num_vecs) { + err = -EINVAL; + goto free_reg_vals; + } + + for (i = 0; i < num_vecs; i++) { + struct idpf_q_vector *q_vector = &vport->q_vectors[i]; + u16 vec_id = vport->q_vector_idxs[i] - IDPF_MBX_Q_VEC; + struct idpf_intr_reg *intr = &q_vector->intr_reg; + u32 spacing; + + intr->dyn_ctl = idpf_get_reg_addr(adapter, + reg_vals[vec_id].dyn_ctl_reg); + intr->dyn_ctl_intena_m = VF_INT_DYN_CTLN_INTENA_M; + intr->dyn_ctl_itridx_s = VF_INT_DYN_CTLN_ITR_INDX_S; + + spacing = IDPF_ITR_IDX_SPACING(reg_vals[vec_id].itrn_index_spacing, + IDPF_VF_ITR_IDX_SPACING); + rx_itr = VF_INT_ITRN_ADDR(VIRTCHNL2_ITR_IDX_0, + reg_vals[vec_id].itrn_reg, + spacing); + tx_itr = VF_INT_ITRN_ADDR(VIRTCHNL2_ITR_IDX_1, + reg_vals[vec_id].itrn_reg, + spacing); + intr->rx_itr = idpf_get_reg_addr(adapter, rx_itr); + intr->tx_itr = idpf_get_reg_addr(adapter, tx_itr); + } + +free_reg_vals: + kfree(reg_vals); + + return err; +} + +/** + * idpf_vf_reset_reg_init - Initialize reset registers + * @adapter: Driver specific private structure + */ +static void idpf_vf_reset_reg_init(struct idpf_adapter *adapter) +{ + adapter->reset_reg.rstat = idpf_get_reg_addr(adapter, VFGEN_RSTAT); + adapter->reset_reg.rstat_m = VFGEN_RSTAT_VFR_STATE_M; +} + +/** + * idpf_vf_trigger_reset - trigger reset + * @adapter: Driver specific private structure + * @trig_cause: Reason to trigger a reset + */ +static void idpf_vf_trigger_reset(struct idpf_adapter *adapter, + enum idpf_flags trig_cause) +{ + /* Do not send VIRTCHNL2_OP_RESET_VF message on driver unload */ + if (trig_cause == IDPF_HR_FUNC_RESET && + !test_bit(IDPF_REMOVE_IN_PROG, adapter->flags)) + idpf_send_mb_msg(adapter, VIRTCHNL2_OP_RESET_VF, 0, NULL); +} + +/** + * idpf_vf_reg_ops_init - Initialize register API function pointers + * @adapter: Driver specific private structure + */ +static void idpf_vf_reg_ops_init(struct idpf_adapter *adapter) +{ + adapter->dev_ops.reg_ops.ctlq_reg_init = idpf_vf_ctlq_reg_init; + adapter->dev_ops.reg_ops.intr_reg_init = idpf_vf_intr_reg_init; + adapter->dev_ops.reg_ops.mb_intr_reg_init = idpf_vf_mb_intr_reg_init; + adapter->dev_ops.reg_ops.reset_reg_init = idpf_vf_reset_reg_init; + adapter->dev_ops.reg_ops.trigger_reset = idpf_vf_trigger_reset; +} + +/** + * idpf_vf_dev_ops_init - Initialize device API function pointers + * @adapter: Driver specific private structure + */ +void idpf_vf_dev_ops_init(struct idpf_adapter *adapter) +{ + idpf_vf_reg_ops_init(adapter); +} diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c new file mode 100644 index 000000000000..2c1b051fdc0d --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c @@ -0,0 +1,3798 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2023 Intel Corporation */ + +#include "idpf.h" + +/** + * idpf_recv_event_msg - Receive virtchnl event message + * @vport: virtual port structure + * @ctlq_msg: message to copy from + * + * Receive virtchnl event message + */ +static void idpf_recv_event_msg(struct idpf_vport *vport, + struct idpf_ctlq_msg *ctlq_msg) +{ + struct idpf_netdev_priv *np = netdev_priv(vport->netdev); + struct virtchnl2_event *v2e; + bool link_status; + u32 event; + + v2e = (struct virtchnl2_event *)ctlq_msg->ctx.indirect.payload->va; + event = le32_to_cpu(v2e->event); + + switch (event) { + case VIRTCHNL2_EVENT_LINK_CHANGE: + vport->link_speed_mbps = le32_to_cpu(v2e->link_speed); + link_status = v2e->link_status; + + if (vport->link_up == link_status) + break; + + vport->link_up = link_status; + if (np->state == __IDPF_VPORT_UP) { + if (vport->link_up) { + netif_carrier_on(vport->netdev); + netif_tx_start_all_queues(vport->netdev); + } else { + netif_tx_stop_all_queues(vport->netdev); + netif_carrier_off(vport->netdev); + } + } + break; + default: + dev_err(&vport->adapter->pdev->dev, + "Unknown event %d from PF\n", event); + break; + } +} + +/** + * idpf_mb_clean - Reclaim the send mailbox queue entries + * @adapter: Driver specific private structure + * + * Reclaim the send mailbox queue entries to be used to send further messages + * + * Returns 0 on success, negative on failure + */ +static int idpf_mb_clean(struct idpf_adapter *adapter) +{ + u16 i, num_q_msg = IDPF_DFLT_MBX_Q_LEN; + struct idpf_ctlq_msg **q_msg; + struct idpf_dma_mem *dma_mem; + int err; + + q_msg = kcalloc(num_q_msg, sizeof(struct idpf_ctlq_msg *), GFP_ATOMIC); + if (!q_msg) + return -ENOMEM; + + err = idpf_ctlq_clean_sq(adapter->hw.asq, &num_q_msg, q_msg); + if (err) + goto err_kfree; + + for (i = 0; i < num_q_msg; i++) { + if (!q_msg[i]) + continue; + dma_mem = q_msg[i]->ctx.indirect.payload; + if (dma_mem) + dma_free_coherent(&adapter->pdev->dev, dma_mem->size, + dma_mem->va, dma_mem->pa); + kfree(q_msg[i]); + kfree(dma_mem); + } + +err_kfree: + kfree(q_msg); + + return err; +} + +/** + * idpf_send_mb_msg - Send message over mailbox + * @adapter: Driver specific private structure + * @op: virtchnl opcode + * @msg_size: size of the payload + * @msg: pointer to buffer holding the payload + * + * Will prepare the control queue message and initiates the send api + * + * Returns 0 on success, negative on failure + */ +int idpf_send_mb_msg(struct idpf_adapter *adapter, u32 op, + u16 msg_size, u8 *msg) +{ + struct idpf_ctlq_msg *ctlq_msg; + struct idpf_dma_mem *dma_mem; + int err; + + /* If we are here and a reset is detected nothing much can be + * done. This thread should silently abort and expected to + * be corrected with a new run either by user or driver + * flows after reset + */ + if (idpf_is_reset_detected(adapter)) + return 0; + + err = idpf_mb_clean(adapter); + if (err) + return err; + + ctlq_msg = kzalloc(sizeof(*ctlq_msg), GFP_ATOMIC); + if (!ctlq_msg) + return -ENOMEM; + + dma_mem = kzalloc(sizeof(*dma_mem), GFP_ATOMIC); + if (!dma_mem) { + err = -ENOMEM; + goto dma_mem_error; + } + + ctlq_msg->opcode = idpf_mbq_opc_send_msg_to_cp; + ctlq_msg->func_id = 0; + ctlq_msg->data_len = msg_size; + ctlq_msg->cookie.mbx.chnl_opcode = op; + ctlq_msg->cookie.mbx.chnl_retval = 0; + dma_mem->size = IDPF_CTLQ_MAX_BUF_LEN; + dma_mem->va = dma_alloc_coherent(&adapter->pdev->dev, dma_mem->size, + &dma_mem->pa, GFP_ATOMIC); + if (!dma_mem->va) { + err = -ENOMEM; + goto dma_alloc_error; + } + memcpy(dma_mem->va, msg, msg_size); + ctlq_msg->ctx.indirect.payload = dma_mem; + + err = idpf_ctlq_send(&adapter->hw, adapter->hw.asq, 1, ctlq_msg); + if (err) + goto send_error; + + return 0; + +send_error: + dma_free_coherent(&adapter->pdev->dev, dma_mem->size, dma_mem->va, + dma_mem->pa); +dma_alloc_error: + kfree(dma_mem); +dma_mem_error: + kfree(ctlq_msg); + + return err; +} + +/** + * idpf_find_vport - Find vport pointer from control queue message + * @adapter: driver specific private structure + * @vport: address of vport pointer to copy the vport from adapters vport list + * @ctlq_msg: control queue message + * + * Return 0 on success, error value on failure. Also this function does check + * for the opcodes which expect to receive payload and return error value if + * it is not the case. + */ +static int idpf_find_vport(struct idpf_adapter *adapter, + struct idpf_vport **vport, + struct idpf_ctlq_msg *ctlq_msg) +{ + bool no_op = false, vid_found = false; + int i, err = 0; + char *vc_msg; + u32 v_id; + + vc_msg = kcalloc(IDPF_CTLQ_MAX_BUF_LEN, sizeof(char), GFP_KERNEL); + if (!vc_msg) + return -ENOMEM; + + if (ctlq_msg->data_len) { + size_t payload_size = ctlq_msg->ctx.indirect.payload->size; + + if (!payload_size) { + dev_err(&adapter->pdev->dev, "Failed to receive payload buffer\n"); + kfree(vc_msg); + + return -EINVAL; + } + + memcpy(vc_msg, ctlq_msg->ctx.indirect.payload->va, + min_t(size_t, payload_size, IDPF_CTLQ_MAX_BUF_LEN)); + } + + switch (ctlq_msg->cookie.mbx.chnl_opcode) { + case VIRTCHNL2_OP_VERSION: + case VIRTCHNL2_OP_GET_CAPS: + case VIRTCHNL2_OP_CREATE_VPORT: + case VIRTCHNL2_OP_SET_SRIOV_VFS: + case VIRTCHNL2_OP_ALLOC_VECTORS: + case VIRTCHNL2_OP_DEALLOC_VECTORS: + case VIRTCHNL2_OP_GET_PTYPE_INFO: + goto free_vc_msg; + case VIRTCHNL2_OP_ENABLE_VPORT: + case VIRTCHNL2_OP_DISABLE_VPORT: + case VIRTCHNL2_OP_DESTROY_VPORT: + v_id = le32_to_cpu(((struct virtchnl2_vport *)vc_msg)->vport_id); + break; + case VIRTCHNL2_OP_CONFIG_TX_QUEUES: + v_id = le32_to_cpu(((struct virtchnl2_config_tx_queues *)vc_msg)->vport_id); + break; + case VIRTCHNL2_OP_CONFIG_RX_QUEUES: + v_id = le32_to_cpu(((struct virtchnl2_config_rx_queues *)vc_msg)->vport_id); + break; + case VIRTCHNL2_OP_ENABLE_QUEUES: + case VIRTCHNL2_OP_DISABLE_QUEUES: + case VIRTCHNL2_OP_DEL_QUEUES: + v_id = le32_to_cpu(((struct virtchnl2_del_ena_dis_queues *)vc_msg)->vport_id); + break; + case VIRTCHNL2_OP_ADD_QUEUES: + v_id = le32_to_cpu(((struct virtchnl2_add_queues *)vc_msg)->vport_id); + break; + case VIRTCHNL2_OP_MAP_QUEUE_VECTOR: + case VIRTCHNL2_OP_UNMAP_QUEUE_VECTOR: + v_id = le32_to_cpu(((struct virtchnl2_queue_vector_maps *)vc_msg)->vport_id); + break; + case VIRTCHNL2_OP_GET_STATS: + v_id = le32_to_cpu(((struct virtchnl2_vport_stats *)vc_msg)->vport_id); + break; + case VIRTCHNL2_OP_GET_RSS_LUT: + case VIRTCHNL2_OP_SET_RSS_LUT: + v_id = le32_to_cpu(((struct virtchnl2_rss_lut *)vc_msg)->vport_id); + break; + case VIRTCHNL2_OP_GET_RSS_KEY: + case VIRTCHNL2_OP_SET_RSS_KEY: + v_id = le32_to_cpu(((struct virtchnl2_rss_key *)vc_msg)->vport_id); + break; + case VIRTCHNL2_OP_EVENT: + v_id = le32_to_cpu(((struct virtchnl2_event *)vc_msg)->vport_id); + break; + case VIRTCHNL2_OP_LOOPBACK: + v_id = le32_to_cpu(((struct virtchnl2_loopback *)vc_msg)->vport_id); + break; + case VIRTCHNL2_OP_CONFIG_PROMISCUOUS_MODE: + v_id = le32_to_cpu(((struct virtchnl2_promisc_info *)vc_msg)->vport_id); + break; + case VIRTCHNL2_OP_ADD_MAC_ADDR: + case VIRTCHNL2_OP_DEL_MAC_ADDR: + v_id = le32_to_cpu(((struct virtchnl2_mac_addr_list *)vc_msg)->vport_id); + break; + default: + no_op = true; + break; + } + + if (no_op) + goto free_vc_msg; + + for (i = 0; i < idpf_get_max_vports(adapter); i++) { + if (adapter->vport_ids[i] == v_id) { + vid_found = true; + break; + } + } + + if (vid_found) + *vport = adapter->vports[i]; + else + err = -EINVAL; + +free_vc_msg: + kfree(vc_msg); + + return err; +} + +/** + * idpf_copy_data_to_vc_buf - Copy the virtchnl response data into the buffer. + * @adapter: driver specific private structure + * @vport: virtual port structure + * @ctlq_msg: msg to copy from + * @err_enum: err bit to set on error + * + * Copies the payload from ctlq_msg into virtchnl buffer. Returns 0 on success, + * negative on failure. + */ +static int idpf_copy_data_to_vc_buf(struct idpf_adapter *adapter, + struct idpf_vport *vport, + struct idpf_ctlq_msg *ctlq_msg, + enum idpf_vport_vc_state err_enum) +{ + if (ctlq_msg->cookie.mbx.chnl_retval) { + if (vport) + set_bit(err_enum, vport->vc_state); + else + set_bit(err_enum, adapter->vc_state); + + return -EINVAL; + } + + if (vport) + memcpy(vport->vc_msg, ctlq_msg->ctx.indirect.payload->va, + min_t(int, ctlq_msg->ctx.indirect.payload->size, + IDPF_CTLQ_MAX_BUF_LEN)); + else + memcpy(adapter->vc_msg, ctlq_msg->ctx.indirect.payload->va, + min_t(int, ctlq_msg->ctx.indirect.payload->size, + IDPF_CTLQ_MAX_BUF_LEN)); + + return 0; +} + +/** + * idpf_recv_vchnl_op - helper function with common logic when handling the + * reception of VIRTCHNL OPs. + * @adapter: driver specific private structure + * @vport: virtual port structure + * @ctlq_msg: msg to copy from + * @state: state bit used on timeout check + * @err_state: err bit to set on error + */ +static void idpf_recv_vchnl_op(struct idpf_adapter *adapter, + struct idpf_vport *vport, + struct idpf_ctlq_msg *ctlq_msg, + enum idpf_vport_vc_state state, + enum idpf_vport_vc_state err_state) +{ + wait_queue_head_t *vchnl_wq; + int err; + + if (vport) + vchnl_wq = &vport->vchnl_wq; + else + vchnl_wq = &adapter->vchnl_wq; + + err = idpf_copy_data_to_vc_buf(adapter, vport, ctlq_msg, err_state); + if (wq_has_sleeper(vchnl_wq)) { + if (vport) + set_bit(state, vport->vc_state); + else + set_bit(state, adapter->vc_state); + + wake_up(vchnl_wq); + } else { + if (!err) { + dev_warn(&adapter->pdev->dev, "opcode %d received without waiting thread\n", + ctlq_msg->cookie.mbx.chnl_opcode); + } else { + /* Clear the errors since there is no sleeper to pass + * them on + */ + if (vport) + clear_bit(err_state, vport->vc_state); + else + clear_bit(err_state, adapter->vc_state); + } + } +} + +/** + * idpf_recv_mb_msg - Receive message over mailbox + * @adapter: Driver specific private structure + * @op: virtchannel operation code + * @msg: Received message holding buffer + * @msg_size: message size + * + * Will receive control queue message and posts the receive buffer. Returns 0 + * on success and negative on failure. + */ +int idpf_recv_mb_msg(struct idpf_adapter *adapter, u32 op, + void *msg, int msg_size) +{ + struct idpf_vport *vport = NULL; + struct idpf_ctlq_msg ctlq_msg; + struct idpf_dma_mem *dma_mem; + bool work_done = false; + int num_retry = 2000; + u16 num_q_msg; + int err; + + while (1) { + struct idpf_vport_config *vport_config; + int payload_size = 0; + + /* Try to get one message */ + num_q_msg = 1; + dma_mem = NULL; + err = idpf_ctlq_recv(adapter->hw.arq, &num_q_msg, &ctlq_msg); + /* If no message then decide if we have to retry based on + * opcode + */ + if (err || !num_q_msg) { + /* Increasing num_retry to consider the delayed + * responses because of large number of VF's mailbox + * messages. If the mailbox message is received from + * the other side, we come out of the sleep cycle + * immediately else we wait for more time. + */ + if (!op || !num_retry--) + break; + if (test_bit(IDPF_REMOVE_IN_PROG, adapter->flags)) { + err = -EIO; + break; + } + msleep(20); + continue; + } + + /* If we are here a message is received. Check if we are looking + * for a specific message based on opcode. If it is different + * ignore and post buffers + */ + if (op && ctlq_msg.cookie.mbx.chnl_opcode != op) + goto post_buffs; + + err = idpf_find_vport(adapter, &vport, &ctlq_msg); + if (err) + goto post_buffs; + + if (ctlq_msg.data_len) + payload_size = ctlq_msg.ctx.indirect.payload->size; + + /* All conditions are met. Either a message requested is + * received or we received a message to be processed + */ + switch (ctlq_msg.cookie.mbx.chnl_opcode) { + case VIRTCHNL2_OP_VERSION: + case VIRTCHNL2_OP_GET_CAPS: + if (ctlq_msg.cookie.mbx.chnl_retval) { + dev_err(&adapter->pdev->dev, "Failure initializing, vc op: %u retval: %u\n", + ctlq_msg.cookie.mbx.chnl_opcode, + ctlq_msg.cookie.mbx.chnl_retval); + err = -EBADMSG; + } else if (msg) { + memcpy(msg, ctlq_msg.ctx.indirect.payload->va, + min_t(int, payload_size, msg_size)); + } + work_done = true; + break; + case VIRTCHNL2_OP_CREATE_VPORT: + idpf_recv_vchnl_op(adapter, NULL, &ctlq_msg, + IDPF_VC_CREATE_VPORT, + IDPF_VC_CREATE_VPORT_ERR); + break; + case VIRTCHNL2_OP_ENABLE_VPORT: + idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, + IDPF_VC_ENA_VPORT, + IDPF_VC_ENA_VPORT_ERR); + break; + case VIRTCHNL2_OP_DISABLE_VPORT: + idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, + IDPF_VC_DIS_VPORT, + IDPF_VC_DIS_VPORT_ERR); + break; + case VIRTCHNL2_OP_DESTROY_VPORT: + idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, + IDPF_VC_DESTROY_VPORT, + IDPF_VC_DESTROY_VPORT_ERR); + break; + case VIRTCHNL2_OP_CONFIG_TX_QUEUES: + idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, + IDPF_VC_CONFIG_TXQ, + IDPF_VC_CONFIG_TXQ_ERR); + break; + case VIRTCHNL2_OP_CONFIG_RX_QUEUES: + idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, + IDPF_VC_CONFIG_RXQ, + IDPF_VC_CONFIG_RXQ_ERR); + break; + case VIRTCHNL2_OP_ENABLE_QUEUES: + idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, + IDPF_VC_ENA_QUEUES, + IDPF_VC_ENA_QUEUES_ERR); + break; + case VIRTCHNL2_OP_DISABLE_QUEUES: + idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, + IDPF_VC_DIS_QUEUES, + IDPF_VC_DIS_QUEUES_ERR); + break; + case VIRTCHNL2_OP_ADD_QUEUES: + idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, + IDPF_VC_ADD_QUEUES, + IDPF_VC_ADD_QUEUES_ERR); + break; + case VIRTCHNL2_OP_DEL_QUEUES: + idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, + IDPF_VC_DEL_QUEUES, + IDPF_VC_DEL_QUEUES_ERR); + break; + case VIRTCHNL2_OP_MAP_QUEUE_VECTOR: + idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, + IDPF_VC_MAP_IRQ, + IDPF_VC_MAP_IRQ_ERR); + break; + case VIRTCHNL2_OP_UNMAP_QUEUE_VECTOR: + idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, + IDPF_VC_UNMAP_IRQ, + IDPF_VC_UNMAP_IRQ_ERR); + break; + case VIRTCHNL2_OP_GET_STATS: + idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, + IDPF_VC_GET_STATS, + IDPF_VC_GET_STATS_ERR); + break; + case VIRTCHNL2_OP_GET_RSS_LUT: + idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, + IDPF_VC_GET_RSS_LUT, + IDPF_VC_GET_RSS_LUT_ERR); + break; + case VIRTCHNL2_OP_SET_RSS_LUT: + idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, + IDPF_VC_SET_RSS_LUT, + IDPF_VC_SET_RSS_LUT_ERR); + break; + case VIRTCHNL2_OP_GET_RSS_KEY: + idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, + IDPF_VC_GET_RSS_KEY, + IDPF_VC_GET_RSS_KEY_ERR); + break; + case VIRTCHNL2_OP_SET_RSS_KEY: + idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, + IDPF_VC_SET_RSS_KEY, + IDPF_VC_SET_RSS_KEY_ERR); + break; + case VIRTCHNL2_OP_SET_SRIOV_VFS: + idpf_recv_vchnl_op(adapter, NULL, &ctlq_msg, + IDPF_VC_SET_SRIOV_VFS, + IDPF_VC_SET_SRIOV_VFS_ERR); + break; + case VIRTCHNL2_OP_ALLOC_VECTORS: + idpf_recv_vchnl_op(adapter, NULL, &ctlq_msg, + IDPF_VC_ALLOC_VECTORS, + IDPF_VC_ALLOC_VECTORS_ERR); + break; + case VIRTCHNL2_OP_DEALLOC_VECTORS: + idpf_recv_vchnl_op(adapter, NULL, &ctlq_msg, + IDPF_VC_DEALLOC_VECTORS, + IDPF_VC_DEALLOC_VECTORS_ERR); + break; + case VIRTCHNL2_OP_GET_PTYPE_INFO: + idpf_recv_vchnl_op(adapter, NULL, &ctlq_msg, + IDPF_VC_GET_PTYPE_INFO, + IDPF_VC_GET_PTYPE_INFO_ERR); + break; + case VIRTCHNL2_OP_LOOPBACK: + idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, + IDPF_VC_LOOPBACK_STATE, + IDPF_VC_LOOPBACK_STATE_ERR); + break; + case VIRTCHNL2_OP_CONFIG_PROMISCUOUS_MODE: + /* This message can only be sent asynchronously. As + * such we'll have lost the context in which it was + * called and thus can only really report if it looks + * like an error occurred. Don't bother setting ERR bit + * or waking chnl_wq since no work queue will be waiting + * to read the message. + */ + if (ctlq_msg.cookie.mbx.chnl_retval) { + dev_err(&adapter->pdev->dev, "Failed to set promiscuous mode: %d\n", + ctlq_msg.cookie.mbx.chnl_retval); + } + break; + case VIRTCHNL2_OP_ADD_MAC_ADDR: + vport_config = adapter->vport_config[vport->idx]; + if (test_and_clear_bit(IDPF_VPORT_ADD_MAC_REQ, + vport_config->flags)) { + /* Message was sent asynchronously. We don't + * normally print errors here, instead + * prefer to handle errors in the function + * calling wait_for_event. However, if + * asynchronous, the context in which the + * message was sent is lost. We can't really do + * anything about at it this point, but we + * should at a minimum indicate that it looks + * like something went wrong. Also don't bother + * setting ERR bit or waking vchnl_wq since no + * one will be waiting to read the async + * message. + */ + if (ctlq_msg.cookie.mbx.chnl_retval) + dev_err(&adapter->pdev->dev, "Failed to add MAC address: %d\n", + ctlq_msg.cookie.mbx.chnl_retval); + break; + } + idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, + IDPF_VC_ADD_MAC_ADDR, + IDPF_VC_ADD_MAC_ADDR_ERR); + break; + case VIRTCHNL2_OP_DEL_MAC_ADDR: + vport_config = adapter->vport_config[vport->idx]; + if (test_and_clear_bit(IDPF_VPORT_DEL_MAC_REQ, + vport_config->flags)) { + /* Message was sent asynchronously like the + * VIRTCHNL2_OP_ADD_MAC_ADDR + */ + if (ctlq_msg.cookie.mbx.chnl_retval) + dev_err(&adapter->pdev->dev, "Failed to delete MAC address: %d\n", + ctlq_msg.cookie.mbx.chnl_retval); + break; + } + idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, + IDPF_VC_DEL_MAC_ADDR, + IDPF_VC_DEL_MAC_ADDR_ERR); + break; + case VIRTCHNL2_OP_EVENT: + idpf_recv_event_msg(vport, &ctlq_msg); + break; + default: + dev_warn(&adapter->pdev->dev, + "Unhandled virtchnl response %d\n", + ctlq_msg.cookie.mbx.chnl_opcode); + break; + } + +post_buffs: + if (ctlq_msg.data_len) + dma_mem = ctlq_msg.ctx.indirect.payload; + else + num_q_msg = 0; + + err = idpf_ctlq_post_rx_buffs(&adapter->hw, adapter->hw.arq, + &num_q_msg, &dma_mem); + /* If post failed clear the only buffer we supplied */ + if (err && dma_mem) + dma_free_coherent(&adapter->pdev->dev, dma_mem->size, + dma_mem->va, dma_mem->pa); + + /* Applies only if we are looking for a specific opcode */ + if (work_done) + break; + } + + return err; +} + +/** + * __idpf_wait_for_event - wrapper function for wait on virtchannel response + * @adapter: Driver private data structure + * @vport: virtual port structure + * @state: check on state upon timeout + * @err_check: check if this specific error bit is set + * @timeout: Max time to wait + * + * Checks if state is set upon expiry of timeout. Returns 0 on success, + * negative on failure. + */ +static int __idpf_wait_for_event(struct idpf_adapter *adapter, + struct idpf_vport *vport, + enum idpf_vport_vc_state state, + enum idpf_vport_vc_state err_check, + int timeout) +{ + int time_to_wait, num_waits; + wait_queue_head_t *vchnl_wq; + unsigned long *vc_state; + + time_to_wait = ((timeout <= IDPF_MAX_WAIT) ? timeout : IDPF_MAX_WAIT); + num_waits = ((timeout <= IDPF_MAX_WAIT) ? 1 : timeout / IDPF_MAX_WAIT); + + if (vport) { + vchnl_wq = &vport->vchnl_wq; + vc_state = vport->vc_state; + } else { + vchnl_wq = &adapter->vchnl_wq; + vc_state = adapter->vc_state; + } + + while (num_waits) { + int event; + + /* If we are here and a reset is detected do not wait but + * return. Reset timing is out of drivers control. So + * while we are cleaning resources as part of reset if the + * underlying HW mailbox is gone, wait on mailbox messages + * is not meaningful + */ + if (idpf_is_reset_detected(adapter)) + return 0; + + event = wait_event_timeout(*vchnl_wq, + test_and_clear_bit(state, vc_state), + msecs_to_jiffies(time_to_wait)); + if (event) { + if (test_and_clear_bit(err_check, vc_state)) { + dev_err(&adapter->pdev->dev, "VC response error %s\n", + idpf_vport_vc_state_str[err_check]); + + return -EINVAL; + } + + return 0; + } + num_waits--; + } + + /* Timeout occurred */ + dev_err(&adapter->pdev->dev, "VC timeout, state = %s\n", + idpf_vport_vc_state_str[state]); + + return -ETIMEDOUT; +} + +/** + * idpf_min_wait_for_event - wait for virtchannel response + * @adapter: Driver private data structure + * @vport: virtual port structure + * @state: check on state upon timeout + * @err_check: check if this specific error bit is set + * + * Returns 0 on success, negative on failure. + */ +static int idpf_min_wait_for_event(struct idpf_adapter *adapter, + struct idpf_vport *vport, + enum idpf_vport_vc_state state, + enum idpf_vport_vc_state err_check) +{ + return __idpf_wait_for_event(adapter, vport, state, err_check, + IDPF_WAIT_FOR_EVENT_TIMEO_MIN); +} + +/** + * idpf_wait_for_event - wait for virtchannel response + * @adapter: Driver private data structure + * @vport: virtual port structure + * @state: check on state upon timeout after 500ms + * @err_check: check if this specific error bit is set + * + * Returns 0 on success, negative on failure. + */ +static int idpf_wait_for_event(struct idpf_adapter *adapter, + struct idpf_vport *vport, + enum idpf_vport_vc_state state, + enum idpf_vport_vc_state err_check) +{ + /* Increasing the timeout in __IDPF_INIT_SW flow to consider large + * number of VF's mailbox message responses. When a message is received + * on mailbox, this thread is woken up by the idpf_recv_mb_msg before + * the timeout expires. Only in the error case i.e. if no message is + * received on mailbox, we wait for the complete timeout which is + * less likely to happen. + */ + return __idpf_wait_for_event(adapter, vport, state, err_check, + IDPF_WAIT_FOR_EVENT_TIMEO); +} + +/** + * idpf_wait_for_marker_event - wait for software marker response + * @vport: virtual port data structure + * + * Returns 0 success, negative on failure. + **/ +static int idpf_wait_for_marker_event(struct idpf_vport *vport) +{ + int event; + int i; + + for (i = 0; i < vport->num_txq; i++) + set_bit(__IDPF_Q_SW_MARKER, vport->txqs[i]->flags); + + event = wait_event_timeout(vport->sw_marker_wq, + test_and_clear_bit(IDPF_VPORT_SW_MARKER, + vport->flags), + msecs_to_jiffies(500)); + + for (i = 0; i < vport->num_txq; i++) + clear_bit(__IDPF_Q_POLL_MODE, vport->txqs[i]->flags); + + if (event) + return 0; + + dev_warn(&vport->adapter->pdev->dev, "Failed to receive marker packets\n"); + + return -ETIMEDOUT; +} + +/** + * idpf_send_ver_msg - send virtchnl version message + * @adapter: Driver specific private structure + * + * Send virtchnl version message. Returns 0 on success, negative on failure. + */ +static int idpf_send_ver_msg(struct idpf_adapter *adapter) +{ + struct virtchnl2_version_info vvi; + + if (adapter->virt_ver_maj) { + vvi.major = cpu_to_le32(adapter->virt_ver_maj); + vvi.minor = cpu_to_le32(adapter->virt_ver_min); + } else { + vvi.major = cpu_to_le32(IDPF_VIRTCHNL_VERSION_MAJOR); + vvi.minor = cpu_to_le32(IDPF_VIRTCHNL_VERSION_MINOR); + } + + return idpf_send_mb_msg(adapter, VIRTCHNL2_OP_VERSION, sizeof(vvi), + (u8 *)&vvi); +} + +/** + * idpf_recv_ver_msg - Receive virtchnl version message + * @adapter: Driver specific private structure + * + * Receive virtchnl version message. Returns 0 on success, -EAGAIN if we need + * to send version message again, otherwise negative on failure. + */ +static int idpf_recv_ver_msg(struct idpf_adapter *adapter) +{ + struct virtchnl2_version_info vvi; + u32 major, minor; + int err; + + err = idpf_recv_mb_msg(adapter, VIRTCHNL2_OP_VERSION, &vvi, + sizeof(vvi)); + if (err) + return err; + + major = le32_to_cpu(vvi.major); + minor = le32_to_cpu(vvi.minor); + + if (major > IDPF_VIRTCHNL_VERSION_MAJOR) { + dev_warn(&adapter->pdev->dev, + "Virtchnl major version (%d) greater than supported\n", + major); + + return -EINVAL; + } + + if (major == IDPF_VIRTCHNL_VERSION_MAJOR && + minor > IDPF_VIRTCHNL_VERSION_MINOR) + dev_warn(&adapter->pdev->dev, + "Virtchnl minor version (%d) didn't match\n", minor); + + /* If we have a mismatch, resend version to update receiver on what + * version we will use. + */ + if (!adapter->virt_ver_maj && + major != IDPF_VIRTCHNL_VERSION_MAJOR && + minor != IDPF_VIRTCHNL_VERSION_MINOR) + err = -EAGAIN; + + adapter->virt_ver_maj = major; + adapter->virt_ver_min = minor; + + return err; +} + +/** + * idpf_send_get_caps_msg - Send virtchnl get capabilities message + * @adapter: Driver specific private structure + * + * Send virtchl get capabilities message. Returns 0 on success, negative on + * failure. + */ +static int idpf_send_get_caps_msg(struct idpf_adapter *adapter) +{ + struct virtchnl2_get_capabilities caps = { }; + + caps.csum_caps = + cpu_to_le32(VIRTCHNL2_CAP_TX_CSUM_L3_IPV4 | + VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_TCP | + VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_UDP | + VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_SCTP | + VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_TCP | + VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_UDP | + VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_SCTP | + VIRTCHNL2_CAP_RX_CSUM_L3_IPV4 | + VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_TCP | + VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_UDP | + VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_SCTP | + VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_TCP | + VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_UDP | + VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_SCTP | + VIRTCHNL2_CAP_TX_CSUM_L3_SINGLE_TUNNEL | + VIRTCHNL2_CAP_RX_CSUM_L3_SINGLE_TUNNEL | + VIRTCHNL2_CAP_TX_CSUM_L4_SINGLE_TUNNEL | + VIRTCHNL2_CAP_RX_CSUM_L4_SINGLE_TUNNEL | + VIRTCHNL2_CAP_RX_CSUM_GENERIC); + + caps.seg_caps = + cpu_to_le32(VIRTCHNL2_CAP_SEG_IPV4_TCP | + VIRTCHNL2_CAP_SEG_IPV4_UDP | + VIRTCHNL2_CAP_SEG_IPV4_SCTP | + VIRTCHNL2_CAP_SEG_IPV6_TCP | + VIRTCHNL2_CAP_SEG_IPV6_UDP | + VIRTCHNL2_CAP_SEG_IPV6_SCTP | + VIRTCHNL2_CAP_SEG_TX_SINGLE_TUNNEL); + + caps.rss_caps = + cpu_to_le64(VIRTCHNL2_CAP_RSS_IPV4_TCP | + VIRTCHNL2_CAP_RSS_IPV4_UDP | + VIRTCHNL2_CAP_RSS_IPV4_SCTP | + VIRTCHNL2_CAP_RSS_IPV4_OTHER | + VIRTCHNL2_CAP_RSS_IPV6_TCP | + VIRTCHNL2_CAP_RSS_IPV6_UDP | + VIRTCHNL2_CAP_RSS_IPV6_SCTP | + VIRTCHNL2_CAP_RSS_IPV6_OTHER); + + caps.hsplit_caps = + cpu_to_le32(VIRTCHNL2_CAP_RX_HSPLIT_AT_L4V4 | + VIRTCHNL2_CAP_RX_HSPLIT_AT_L4V6); + + caps.rsc_caps = + cpu_to_le32(VIRTCHNL2_CAP_RSC_IPV4_TCP | + VIRTCHNL2_CAP_RSC_IPV6_TCP); + + caps.other_caps = + cpu_to_le64(VIRTCHNL2_CAP_SRIOV | + VIRTCHNL2_CAP_MACFILTER | + VIRTCHNL2_CAP_SPLITQ_QSCHED | + VIRTCHNL2_CAP_PROMISC | + VIRTCHNL2_CAP_LOOPBACK); + + return idpf_send_mb_msg(adapter, VIRTCHNL2_OP_GET_CAPS, sizeof(caps), + (u8 *)&caps); +} + +/** + * idpf_recv_get_caps_msg - Receive virtchnl get capabilities message + * @adapter: Driver specific private structure + * + * Receive virtchnl get capabilities message. Returns 0 on success, negative on + * failure. + */ +static int idpf_recv_get_caps_msg(struct idpf_adapter *adapter) +{ + return idpf_recv_mb_msg(adapter, VIRTCHNL2_OP_GET_CAPS, &adapter->caps, + sizeof(struct virtchnl2_get_capabilities)); +} + +/** + * idpf_vport_alloc_max_qs - Allocate max queues for a vport + * @adapter: Driver specific private structure + * @max_q: vport max queue structure + */ +int idpf_vport_alloc_max_qs(struct idpf_adapter *adapter, + struct idpf_vport_max_q *max_q) +{ + struct idpf_avail_queue_info *avail_queues = &adapter->avail_queues; + struct virtchnl2_get_capabilities *caps = &adapter->caps; + u16 default_vports = idpf_get_default_vports(adapter); + int max_rx_q, max_tx_q; + + mutex_lock(&adapter->queue_lock); + + max_rx_q = le16_to_cpu(caps->max_rx_q) / default_vports; + max_tx_q = le16_to_cpu(caps->max_tx_q) / default_vports; + if (adapter->num_alloc_vports < default_vports) { + max_q->max_rxq = min_t(u16, max_rx_q, IDPF_MAX_Q); + max_q->max_txq = min_t(u16, max_tx_q, IDPF_MAX_Q); + } else { + max_q->max_rxq = IDPF_MIN_Q; + max_q->max_txq = IDPF_MIN_Q; + } + max_q->max_bufq = max_q->max_rxq * IDPF_MAX_BUFQS_PER_RXQ_GRP; + max_q->max_complq = max_q->max_txq; + + if (avail_queues->avail_rxq < max_q->max_rxq || + avail_queues->avail_txq < max_q->max_txq || + avail_queues->avail_bufq < max_q->max_bufq || + avail_queues->avail_complq < max_q->max_complq) { + mutex_unlock(&adapter->queue_lock); + + return -EINVAL; + } + + avail_queues->avail_rxq -= max_q->max_rxq; + avail_queues->avail_txq -= max_q->max_txq; + avail_queues->avail_bufq -= max_q->max_bufq; + avail_queues->avail_complq -= max_q->max_complq; + + mutex_unlock(&adapter->queue_lock); + + return 0; +} + +/** + * idpf_vport_dealloc_max_qs - Deallocate max queues of a vport + * @adapter: Driver specific private structure + * @max_q: vport max queue structure + */ +void idpf_vport_dealloc_max_qs(struct idpf_adapter *adapter, + struct idpf_vport_max_q *max_q) +{ + struct idpf_avail_queue_info *avail_queues; + + mutex_lock(&adapter->queue_lock); + avail_queues = &adapter->avail_queues; + + avail_queues->avail_rxq += max_q->max_rxq; + avail_queues->avail_txq += max_q->max_txq; + avail_queues->avail_bufq += max_q->max_bufq; + avail_queues->avail_complq += max_q->max_complq; + + mutex_unlock(&adapter->queue_lock); +} + +/** + * idpf_init_avail_queues - Initialize available queues on the device + * @adapter: Driver specific private structure + */ +static void idpf_init_avail_queues(struct idpf_adapter *adapter) +{ + struct idpf_avail_queue_info *avail_queues = &adapter->avail_queues; + struct virtchnl2_get_capabilities *caps = &adapter->caps; + + avail_queues->avail_rxq = le16_to_cpu(caps->max_rx_q); + avail_queues->avail_txq = le16_to_cpu(caps->max_tx_q); + avail_queues->avail_bufq = le16_to_cpu(caps->max_rx_bufq); + avail_queues->avail_complq = le16_to_cpu(caps->max_tx_complq); +} + +/** + * idpf_get_reg_intr_vecs - Get vector queue register offset + * @vport: virtual port structure + * @reg_vals: Register offsets to store in + * + * Returns number of registers that got populated + */ +int idpf_get_reg_intr_vecs(struct idpf_vport *vport, + struct idpf_vec_regs *reg_vals) +{ + struct virtchnl2_vector_chunks *chunks; + struct idpf_vec_regs reg_val; + u16 num_vchunks, num_vec; + int num_regs = 0, i, j; + + chunks = &vport->adapter->req_vec_chunks->vchunks; + num_vchunks = le16_to_cpu(chunks->num_vchunks); + + for (j = 0; j < num_vchunks; j++) { + struct virtchnl2_vector_chunk *chunk; + u32 dynctl_reg_spacing; + u32 itrn_reg_spacing; + + chunk = &chunks->vchunks[j]; + num_vec = le16_to_cpu(chunk->num_vectors); + reg_val.dyn_ctl_reg = le32_to_cpu(chunk->dynctl_reg_start); + reg_val.itrn_reg = le32_to_cpu(chunk->itrn_reg_start); + reg_val.itrn_index_spacing = le32_to_cpu(chunk->itrn_index_spacing); + + dynctl_reg_spacing = le32_to_cpu(chunk->dynctl_reg_spacing); + itrn_reg_spacing = le32_to_cpu(chunk->itrn_reg_spacing); + + for (i = 0; i < num_vec; i++) { + reg_vals[num_regs].dyn_ctl_reg = reg_val.dyn_ctl_reg; + reg_vals[num_regs].itrn_reg = reg_val.itrn_reg; + reg_vals[num_regs].itrn_index_spacing = + reg_val.itrn_index_spacing; + + reg_val.dyn_ctl_reg += dynctl_reg_spacing; + reg_val.itrn_reg += itrn_reg_spacing; + num_regs++; + } + } + + return num_regs; +} + +/** + * idpf_vport_get_q_reg - Get the queue registers for the vport + * @reg_vals: register values needing to be set + * @num_regs: amount we expect to fill + * @q_type: queue model + * @chunks: queue regs received over mailbox + * + * This function parses the queue register offsets from the queue register + * chunk information, with a specific queue type and stores it into the array + * passed as an argument. It returns the actual number of queue registers that + * are filled. + */ +static int idpf_vport_get_q_reg(u32 *reg_vals, int num_regs, u32 q_type, + struct virtchnl2_queue_reg_chunks *chunks) +{ + u16 num_chunks = le16_to_cpu(chunks->num_chunks); + int reg_filled = 0, i; + u32 reg_val; + + while (num_chunks--) { + struct virtchnl2_queue_reg_chunk *chunk; + u16 num_q; + + chunk = &chunks->chunks[num_chunks]; + if (le32_to_cpu(chunk->type) != q_type) + continue; + + num_q = le32_to_cpu(chunk->num_queues); + reg_val = le64_to_cpu(chunk->qtail_reg_start); + for (i = 0; i < num_q && reg_filled < num_regs ; i++) { + reg_vals[reg_filled++] = reg_val; + reg_val += le32_to_cpu(chunk->qtail_reg_spacing); + } + } + + return reg_filled; +} + +/** + * __idpf_queue_reg_init - initialize queue registers + * @vport: virtual port structure + * @reg_vals: registers we are initializing + * @num_regs: how many registers there are in total + * @q_type: queue model + * + * Return number of queues that are initialized + */ +static int __idpf_queue_reg_init(struct idpf_vport *vport, u32 *reg_vals, + int num_regs, u32 q_type) +{ + struct idpf_adapter *adapter = vport->adapter; + struct idpf_queue *q; + int i, j, k = 0; + + switch (q_type) { + case VIRTCHNL2_QUEUE_TYPE_TX: + for (i = 0; i < vport->num_txq_grp; i++) { + struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i]; + + for (j = 0; j < tx_qgrp->num_txq && k < num_regs; j++, k++) + tx_qgrp->txqs[j]->tail = + idpf_get_reg_addr(adapter, reg_vals[k]); + } + break; + case VIRTCHNL2_QUEUE_TYPE_RX: + for (i = 0; i < vport->num_rxq_grp; i++) { + struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i]; + u16 num_rxq = rx_qgrp->singleq.num_rxq; + + for (j = 0; j < num_rxq && k < num_regs; j++, k++) { + q = rx_qgrp->singleq.rxqs[j]; + q->tail = idpf_get_reg_addr(adapter, + reg_vals[k]); + } + } + break; + case VIRTCHNL2_QUEUE_TYPE_RX_BUFFER: + for (i = 0; i < vport->num_rxq_grp; i++) { + struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i]; + u8 num_bufqs = vport->num_bufqs_per_qgrp; + + for (j = 0; j < num_bufqs && k < num_regs; j++, k++) { + q = &rx_qgrp->splitq.bufq_sets[j].bufq; + q->tail = idpf_get_reg_addr(adapter, + reg_vals[k]); + } + } + break; + default: + break; + } + + return k; +} + +/** + * idpf_queue_reg_init - initialize queue registers + * @vport: virtual port structure + * + * Return 0 on success, negative on failure + */ +int idpf_queue_reg_init(struct idpf_vport *vport) +{ + struct virtchnl2_create_vport *vport_params; + struct virtchnl2_queue_reg_chunks *chunks; + struct idpf_vport_config *vport_config; + u16 vport_idx = vport->idx; + int num_regs, ret = 0; + u32 *reg_vals; + + /* We may never deal with more than 256 same type of queues */ + reg_vals = kzalloc(sizeof(void *) * IDPF_LARGE_MAX_Q, GFP_KERNEL); + if (!reg_vals) + return -ENOMEM; + + vport_config = vport->adapter->vport_config[vport_idx]; + if (vport_config->req_qs_chunks) { + struct virtchnl2_add_queues *vc_aq = + (struct virtchnl2_add_queues *)vport_config->req_qs_chunks; + chunks = &vc_aq->chunks; + } else { + vport_params = vport->adapter->vport_params_recvd[vport_idx]; + chunks = &vport_params->chunks; + } + + /* Initialize Tx queue tail register address */ + num_regs = idpf_vport_get_q_reg(reg_vals, IDPF_LARGE_MAX_Q, + VIRTCHNL2_QUEUE_TYPE_TX, + chunks); + if (num_regs < vport->num_txq) { + ret = -EINVAL; + goto free_reg_vals; + } + + num_regs = __idpf_queue_reg_init(vport, reg_vals, num_regs, + VIRTCHNL2_QUEUE_TYPE_TX); + if (num_regs < vport->num_txq) { + ret = -EINVAL; + goto free_reg_vals; + } + + /* Initialize Rx/buffer queue tail register address based on Rx queue + * model + */ + if (idpf_is_queue_model_split(vport->rxq_model)) { + num_regs = idpf_vport_get_q_reg(reg_vals, IDPF_LARGE_MAX_Q, + VIRTCHNL2_QUEUE_TYPE_RX_BUFFER, + chunks); + if (num_regs < vport->num_bufq) { + ret = -EINVAL; + goto free_reg_vals; + } + + num_regs = __idpf_queue_reg_init(vport, reg_vals, num_regs, + VIRTCHNL2_QUEUE_TYPE_RX_BUFFER); + if (num_regs < vport->num_bufq) { + ret = -EINVAL; + goto free_reg_vals; + } + } else { + num_regs = idpf_vport_get_q_reg(reg_vals, IDPF_LARGE_MAX_Q, + VIRTCHNL2_QUEUE_TYPE_RX, + chunks); + if (num_regs < vport->num_rxq) { + ret = -EINVAL; + goto free_reg_vals; + } + + num_regs = __idpf_queue_reg_init(vport, reg_vals, num_regs, + VIRTCHNL2_QUEUE_TYPE_RX); + if (num_regs < vport->num_rxq) { + ret = -EINVAL; + goto free_reg_vals; + } + } + +free_reg_vals: + kfree(reg_vals); + + return ret; +} + +/** + * idpf_send_create_vport_msg - Send virtchnl create vport message + * @adapter: Driver specific private structure + * @max_q: vport max queue info + * + * send virtchnl creae vport message + * + * Returns 0 on success, negative on failure + */ +int idpf_send_create_vport_msg(struct idpf_adapter *adapter, + struct idpf_vport_max_q *max_q) +{ + struct virtchnl2_create_vport *vport_msg; + u16 idx = adapter->next_vport; + int err, buf_size; + + buf_size = sizeof(struct virtchnl2_create_vport); + if (!adapter->vport_params_reqd[idx]) { + adapter->vport_params_reqd[idx] = kzalloc(buf_size, + GFP_KERNEL); + if (!adapter->vport_params_reqd[idx]) + return -ENOMEM; + } + + vport_msg = adapter->vport_params_reqd[idx]; + vport_msg->vport_type = cpu_to_le16(VIRTCHNL2_VPORT_TYPE_DEFAULT); + vport_msg->vport_index = cpu_to_le16(idx); + + if (adapter->req_tx_splitq) + vport_msg->txq_model = cpu_to_le16(VIRTCHNL2_QUEUE_MODEL_SPLIT); + else + vport_msg->txq_model = cpu_to_le16(VIRTCHNL2_QUEUE_MODEL_SINGLE); + + if (adapter->req_rx_splitq) + vport_msg->rxq_model = cpu_to_le16(VIRTCHNL2_QUEUE_MODEL_SPLIT); + else + vport_msg->rxq_model = cpu_to_le16(VIRTCHNL2_QUEUE_MODEL_SINGLE); + + err = idpf_vport_calc_total_qs(adapter, idx, vport_msg, max_q); + if (err) { + dev_err(&adapter->pdev->dev, "Enough queues are not available"); + + return err; + } + + mutex_lock(&adapter->vc_buf_lock); + + err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_CREATE_VPORT, buf_size, + (u8 *)vport_msg); + if (err) + goto rel_lock; + + err = idpf_wait_for_event(adapter, NULL, IDPF_VC_CREATE_VPORT, + IDPF_VC_CREATE_VPORT_ERR); + if (err) { + dev_err(&adapter->pdev->dev, "Failed to receive create vport message"); + + goto rel_lock; + } + + if (!adapter->vport_params_recvd[idx]) { + adapter->vport_params_recvd[idx] = kzalloc(IDPF_CTLQ_MAX_BUF_LEN, + GFP_KERNEL); + if (!adapter->vport_params_recvd[idx]) { + err = -ENOMEM; + goto rel_lock; + } + } + + vport_msg = adapter->vport_params_recvd[idx]; + memcpy(vport_msg, adapter->vc_msg, IDPF_CTLQ_MAX_BUF_LEN); + +rel_lock: + mutex_unlock(&adapter->vc_buf_lock); + + return err; +} + +/** + * idpf_check_supported_desc_ids - Verify we have required descriptor support + * @vport: virtual port structure + * + * Return 0 on success, error on failure + */ +int idpf_check_supported_desc_ids(struct idpf_vport *vport) +{ + struct idpf_adapter *adapter = vport->adapter; + struct virtchnl2_create_vport *vport_msg; + u64 rx_desc_ids, tx_desc_ids; + + vport_msg = adapter->vport_params_recvd[vport->idx]; + + rx_desc_ids = le64_to_cpu(vport_msg->rx_desc_ids); + tx_desc_ids = le64_to_cpu(vport_msg->tx_desc_ids); + + if (vport->rxq_model == VIRTCHNL2_QUEUE_MODEL_SPLIT) { + if (!(rx_desc_ids & VIRTCHNL2_RXDID_2_FLEX_SPLITQ_M)) { + dev_info(&adapter->pdev->dev, "Minimum RX descriptor support not provided, using the default\n"); + vport_msg->rx_desc_ids = cpu_to_le64(VIRTCHNL2_RXDID_2_FLEX_SPLITQ_M); + } + } else { + if (!(rx_desc_ids & VIRTCHNL2_RXDID_2_FLEX_SQ_NIC_M)) + vport->base_rxd = true; + } + + if (vport->txq_model != VIRTCHNL2_QUEUE_MODEL_SPLIT) + return 0; + + if ((tx_desc_ids & MIN_SUPPORT_TXDID) != MIN_SUPPORT_TXDID) { + dev_info(&adapter->pdev->dev, "Minimum TX descriptor support not provided, using the default\n"); + vport_msg->tx_desc_ids = cpu_to_le64(MIN_SUPPORT_TXDID); + } + + return 0; +} + +/** + * idpf_send_destroy_vport_msg - Send virtchnl destroy vport message + * @vport: virtual port data structure + * + * Send virtchnl destroy vport message. Returns 0 on success, negative on + * failure. + */ +int idpf_send_destroy_vport_msg(struct idpf_vport *vport) +{ + struct idpf_adapter *adapter = vport->adapter; + struct virtchnl2_vport v_id; + int err; + + v_id.vport_id = cpu_to_le32(vport->vport_id); + + mutex_lock(&vport->vc_buf_lock); + + err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_DESTROY_VPORT, + sizeof(v_id), (u8 *)&v_id); + if (err) + goto rel_lock; + + err = idpf_min_wait_for_event(adapter, vport, IDPF_VC_DESTROY_VPORT, + IDPF_VC_DESTROY_VPORT_ERR); + +rel_lock: + mutex_unlock(&vport->vc_buf_lock); + + return err; +} + +/** + * idpf_send_enable_vport_msg - Send virtchnl enable vport message + * @vport: virtual port data structure + * + * Send enable vport virtchnl message. Returns 0 on success, negative on + * failure. + */ +int idpf_send_enable_vport_msg(struct idpf_vport *vport) +{ + struct idpf_adapter *adapter = vport->adapter; + struct virtchnl2_vport v_id; + int err; + + v_id.vport_id = cpu_to_le32(vport->vport_id); + + mutex_lock(&vport->vc_buf_lock); + + err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_ENABLE_VPORT, + sizeof(v_id), (u8 *)&v_id); + if (err) + goto rel_lock; + + err = idpf_wait_for_event(adapter, vport, IDPF_VC_ENA_VPORT, + IDPF_VC_ENA_VPORT_ERR); + +rel_lock: + mutex_unlock(&vport->vc_buf_lock); + + return err; +} + +/** + * idpf_send_disable_vport_msg - Send virtchnl disable vport message + * @vport: virtual port data structure + * + * Send disable vport virtchnl message. Returns 0 on success, negative on + * failure. + */ +int idpf_send_disable_vport_msg(struct idpf_vport *vport) +{ + struct idpf_adapter *adapter = vport->adapter; + struct virtchnl2_vport v_id; + int err; + + v_id.vport_id = cpu_to_le32(vport->vport_id); + + mutex_lock(&vport->vc_buf_lock); + + err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_DISABLE_VPORT, + sizeof(v_id), (u8 *)&v_id); + if (err) + goto rel_lock; + + err = idpf_min_wait_for_event(adapter, vport, IDPF_VC_DIS_VPORT, + IDPF_VC_DIS_VPORT_ERR); + +rel_lock: + mutex_unlock(&vport->vc_buf_lock); + + return err; +} + +/** + * idpf_send_config_tx_queues_msg - Send virtchnl config tx queues message + * @vport: virtual port data structure + * + * Send config tx queues virtchnl message. Returns 0 on success, negative on + * failure. + */ +static int idpf_send_config_tx_queues_msg(struct idpf_vport *vport) +{ + struct virtchnl2_config_tx_queues *ctq; + u32 config_sz, chunk_sz, buf_sz; + int totqs, num_msgs, num_chunks; + struct virtchnl2_txq_info *qi; + int err = 0, i, k = 0; + + totqs = vport->num_txq + vport->num_complq; + qi = kcalloc(totqs, sizeof(struct virtchnl2_txq_info), GFP_KERNEL); + if (!qi) + return -ENOMEM; + + /* Populate the queue info buffer with all queue context info */ + for (i = 0; i < vport->num_txq_grp; i++) { + struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i]; + int j, sched_mode; + + for (j = 0; j < tx_qgrp->num_txq; j++, k++) { + qi[k].queue_id = + cpu_to_le32(tx_qgrp->txqs[j]->q_id); + qi[k].model = + cpu_to_le16(vport->txq_model); + qi[k].type = + cpu_to_le32(tx_qgrp->txqs[j]->q_type); + qi[k].ring_len = + cpu_to_le16(tx_qgrp->txqs[j]->desc_count); + qi[k].dma_ring_addr = + cpu_to_le64(tx_qgrp->txqs[j]->dma); + if (idpf_is_queue_model_split(vport->txq_model)) { + struct idpf_queue *q = tx_qgrp->txqs[j]; + + qi[k].tx_compl_queue_id = + cpu_to_le16(tx_qgrp->complq->q_id); + qi[k].relative_queue_id = cpu_to_le16(j); + + if (test_bit(__IDPF_Q_FLOW_SCH_EN, q->flags)) + qi[k].sched_mode = + cpu_to_le16(VIRTCHNL2_TXQ_SCHED_MODE_FLOW); + else + qi[k].sched_mode = + cpu_to_le16(VIRTCHNL2_TXQ_SCHED_MODE_QUEUE); + } else { + qi[k].sched_mode = + cpu_to_le16(VIRTCHNL2_TXQ_SCHED_MODE_QUEUE); + } + } + + if (!idpf_is_queue_model_split(vport->txq_model)) + continue; + + qi[k].queue_id = cpu_to_le32(tx_qgrp->complq->q_id); + qi[k].model = cpu_to_le16(vport->txq_model); + qi[k].type = cpu_to_le32(tx_qgrp->complq->q_type); + qi[k].ring_len = cpu_to_le16(tx_qgrp->complq->desc_count); + qi[k].dma_ring_addr = cpu_to_le64(tx_qgrp->complq->dma); + + if (test_bit(__IDPF_Q_FLOW_SCH_EN, tx_qgrp->complq->flags)) + sched_mode = VIRTCHNL2_TXQ_SCHED_MODE_FLOW; + else + sched_mode = VIRTCHNL2_TXQ_SCHED_MODE_QUEUE; + qi[k].sched_mode = cpu_to_le16(sched_mode); + + k++; + } + + /* Make sure accounting agrees */ + if (k != totqs) { + err = -EINVAL; + goto error; + } + + /* Chunk up the queue contexts into multiple messages to avoid + * sending a control queue message buffer that is too large + */ + config_sz = sizeof(struct virtchnl2_config_tx_queues); + chunk_sz = sizeof(struct virtchnl2_txq_info); + + num_chunks = min_t(u32, IDPF_NUM_CHUNKS_PER_MSG(config_sz, chunk_sz), + totqs); + num_msgs = DIV_ROUND_UP(totqs, num_chunks); + + buf_sz = struct_size(ctq, qinfo, num_chunks); + ctq = kzalloc(buf_sz, GFP_KERNEL); + if (!ctq) { + err = -ENOMEM; + goto error; + } + + mutex_lock(&vport->vc_buf_lock); + + for (i = 0, k = 0; i < num_msgs; i++) { + memset(ctq, 0, buf_sz); + ctq->vport_id = cpu_to_le32(vport->vport_id); + ctq->num_qinfo = cpu_to_le16(num_chunks); + memcpy(ctq->qinfo, &qi[k], chunk_sz * num_chunks); + + err = idpf_send_mb_msg(vport->adapter, + VIRTCHNL2_OP_CONFIG_TX_QUEUES, + buf_sz, (u8 *)ctq); + if (err) + goto mbx_error; + + err = idpf_wait_for_event(vport->adapter, vport, + IDPF_VC_CONFIG_TXQ, + IDPF_VC_CONFIG_TXQ_ERR); + if (err) + goto mbx_error; + + k += num_chunks; + totqs -= num_chunks; + num_chunks = min(num_chunks, totqs); + /* Recalculate buffer size */ + buf_sz = struct_size(ctq, qinfo, num_chunks); + } + +mbx_error: + mutex_unlock(&vport->vc_buf_lock); + kfree(ctq); +error: + kfree(qi); + + return err; +} + +/** + * idpf_send_config_rx_queues_msg - Send virtchnl config rx queues message + * @vport: virtual port data structure + * + * Send config rx queues virtchnl message. Returns 0 on success, negative on + * failure. + */ +static int idpf_send_config_rx_queues_msg(struct idpf_vport *vport) +{ + struct virtchnl2_config_rx_queues *crq; + u32 config_sz, chunk_sz, buf_sz; + int totqs, num_msgs, num_chunks; + struct virtchnl2_rxq_info *qi; + int err = 0, i, k = 0; + + totqs = vport->num_rxq + vport->num_bufq; + qi = kcalloc(totqs, sizeof(struct virtchnl2_rxq_info), GFP_KERNEL); + if (!qi) + return -ENOMEM; + + /* Populate the queue info buffer with all queue context info */ + for (i = 0; i < vport->num_rxq_grp; i++) { + struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i]; + u16 num_rxq; + int j; + + if (!idpf_is_queue_model_split(vport->rxq_model)) + goto setup_rxqs; + + for (j = 0; j < vport->num_bufqs_per_qgrp; j++, k++) { + struct idpf_queue *bufq = + &rx_qgrp->splitq.bufq_sets[j].bufq; + + qi[k].queue_id = cpu_to_le32(bufq->q_id); + qi[k].model = cpu_to_le16(vport->rxq_model); + qi[k].type = cpu_to_le32(bufq->q_type); + qi[k].desc_ids = cpu_to_le64(VIRTCHNL2_RXDID_2_FLEX_SPLITQ_M); + qi[k].ring_len = cpu_to_le16(bufq->desc_count); + qi[k].dma_ring_addr = cpu_to_le64(bufq->dma); + qi[k].data_buffer_size = cpu_to_le32(bufq->rx_buf_size); + qi[k].buffer_notif_stride = bufq->rx_buf_stride; + qi[k].rx_buffer_low_watermark = + cpu_to_le16(bufq->rx_buffer_low_watermark); + if (idpf_is_feature_ena(vport, NETIF_F_GRO_HW)) + qi[k].qflags |= cpu_to_le16(VIRTCHNL2_RXQ_RSC); + } + +setup_rxqs: + if (idpf_is_queue_model_split(vport->rxq_model)) + num_rxq = rx_qgrp->splitq.num_rxq_sets; + else + num_rxq = rx_qgrp->singleq.num_rxq; + + for (j = 0; j < num_rxq; j++, k++) { + struct idpf_queue *rxq; + + if (!idpf_is_queue_model_split(vport->rxq_model)) { + rxq = rx_qgrp->singleq.rxqs[j]; + goto common_qi_fields; + } + rxq = &rx_qgrp->splitq.rxq_sets[j]->rxq; + qi[k].rx_bufq1_id = + cpu_to_le16(rxq->rxq_grp->splitq.bufq_sets[0].bufq.q_id); + if (vport->num_bufqs_per_qgrp > IDPF_SINGLE_BUFQ_PER_RXQ_GRP) { + qi[k].bufq2_ena = IDPF_BUFQ2_ENA; + qi[k].rx_bufq2_id = + cpu_to_le16(rxq->rxq_grp->splitq.bufq_sets[1].bufq.q_id); + } + qi[k].rx_buffer_low_watermark = + cpu_to_le16(rxq->rx_buffer_low_watermark); + if (idpf_is_feature_ena(vport, NETIF_F_GRO_HW)) + qi[k].qflags |= cpu_to_le16(VIRTCHNL2_RXQ_RSC); + +common_qi_fields: + if (rxq->rx_hsplit_en) { + qi[k].qflags |= + cpu_to_le16(VIRTCHNL2_RXQ_HDR_SPLIT); + qi[k].hdr_buffer_size = + cpu_to_le16(rxq->rx_hbuf_size); + } + qi[k].queue_id = cpu_to_le32(rxq->q_id); + qi[k].model = cpu_to_le16(vport->rxq_model); + qi[k].type = cpu_to_le32(rxq->q_type); + qi[k].ring_len = cpu_to_le16(rxq->desc_count); + qi[k].dma_ring_addr = cpu_to_le64(rxq->dma); + qi[k].max_pkt_size = cpu_to_le32(rxq->rx_max_pkt_size); + qi[k].data_buffer_size = cpu_to_le32(rxq->rx_buf_size); + qi[k].qflags |= + cpu_to_le16(VIRTCHNL2_RX_DESC_SIZE_32BYTE); + qi[k].desc_ids = cpu_to_le64(rxq->rxdids); + } + } + + /* Make sure accounting agrees */ + if (k != totqs) { + err = -EINVAL; + goto error; + } + + /* Chunk up the queue contexts into multiple messages to avoid + * sending a control queue message buffer that is too large + */ + config_sz = sizeof(struct virtchnl2_config_rx_queues); + chunk_sz = sizeof(struct virtchnl2_rxq_info); + + num_chunks = min_t(u32, IDPF_NUM_CHUNKS_PER_MSG(config_sz, chunk_sz), + totqs); + num_msgs = DIV_ROUND_UP(totqs, num_chunks); + + buf_sz = struct_size(crq, qinfo, num_chunks); + crq = kzalloc(buf_sz, GFP_KERNEL); + if (!crq) { + err = -ENOMEM; + goto error; + } + + mutex_lock(&vport->vc_buf_lock); + + for (i = 0, k = 0; i < num_msgs; i++) { + memset(crq, 0, buf_sz); + crq->vport_id = cpu_to_le32(vport->vport_id); + crq->num_qinfo = cpu_to_le16(num_chunks); + memcpy(crq->qinfo, &qi[k], chunk_sz * num_chunks); + + err = idpf_send_mb_msg(vport->adapter, + VIRTCHNL2_OP_CONFIG_RX_QUEUES, + buf_sz, (u8 *)crq); + if (err) + goto mbx_error; + + err = idpf_wait_for_event(vport->adapter, vport, + IDPF_VC_CONFIG_RXQ, + IDPF_VC_CONFIG_RXQ_ERR); + if (err) + goto mbx_error; + + k += num_chunks; + totqs -= num_chunks; + num_chunks = min(num_chunks, totqs); + /* Recalculate buffer size */ + buf_sz = struct_size(crq, qinfo, num_chunks); + } + +mbx_error: + mutex_unlock(&vport->vc_buf_lock); + kfree(crq); +error: + kfree(qi); + + return err; +} + +/** + * idpf_send_ena_dis_queues_msg - Send virtchnl enable or disable + * queues message + * @vport: virtual port data structure + * @vc_op: virtchnl op code to send + * + * Send enable or disable queues virtchnl message. Returns 0 on success, + * negative on failure. + */ +static int idpf_send_ena_dis_queues_msg(struct idpf_vport *vport, u32 vc_op) +{ + u32 num_msgs, num_chunks, num_txq, num_rxq, num_q; + struct idpf_adapter *adapter = vport->adapter; + struct virtchnl2_del_ena_dis_queues *eq; + struct virtchnl2_queue_chunks *qcs; + struct virtchnl2_queue_chunk *qc; + u32 config_sz, chunk_sz, buf_sz; + int i, j, k = 0, err = 0; + + /* validate virtchnl op */ + switch (vc_op) { + case VIRTCHNL2_OP_ENABLE_QUEUES: + case VIRTCHNL2_OP_DISABLE_QUEUES: + break; + default: + return -EINVAL; + } + + num_txq = vport->num_txq + vport->num_complq; + num_rxq = vport->num_rxq + vport->num_bufq; + num_q = num_txq + num_rxq; + buf_sz = sizeof(struct virtchnl2_queue_chunk) * num_q; + qc = kzalloc(buf_sz, GFP_KERNEL); + if (!qc) + return -ENOMEM; + + for (i = 0; i < vport->num_txq_grp; i++) { + struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i]; + + for (j = 0; j < tx_qgrp->num_txq; j++, k++) { + qc[k].type = cpu_to_le32(tx_qgrp->txqs[j]->q_type); + qc[k].start_queue_id = cpu_to_le32(tx_qgrp->txqs[j]->q_id); + qc[k].num_queues = cpu_to_le32(IDPF_NUMQ_PER_CHUNK); + } + } + if (vport->num_txq != k) { + err = -EINVAL; + goto error; + } + + if (!idpf_is_queue_model_split(vport->txq_model)) + goto setup_rx; + + for (i = 0; i < vport->num_txq_grp; i++, k++) { + struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i]; + + qc[k].type = cpu_to_le32(tx_qgrp->complq->q_type); + qc[k].start_queue_id = cpu_to_le32(tx_qgrp->complq->q_id); + qc[k].num_queues = cpu_to_le32(IDPF_NUMQ_PER_CHUNK); + } + if (vport->num_complq != (k - vport->num_txq)) { + err = -EINVAL; + goto error; + } + +setup_rx: + for (i = 0; i < vport->num_rxq_grp; i++) { + struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i]; + + if (idpf_is_queue_model_split(vport->rxq_model)) + num_rxq = rx_qgrp->splitq.num_rxq_sets; + else + num_rxq = rx_qgrp->singleq.num_rxq; + + for (j = 0; j < num_rxq; j++, k++) { + if (idpf_is_queue_model_split(vport->rxq_model)) { + qc[k].start_queue_id = + cpu_to_le32(rx_qgrp->splitq.rxq_sets[j]->rxq.q_id); + qc[k].type = + cpu_to_le32(rx_qgrp->splitq.rxq_sets[j]->rxq.q_type); + } else { + qc[k].start_queue_id = + cpu_to_le32(rx_qgrp->singleq.rxqs[j]->q_id); + qc[k].type = + cpu_to_le32(rx_qgrp->singleq.rxqs[j]->q_type); + } + qc[k].num_queues = cpu_to_le32(IDPF_NUMQ_PER_CHUNK); + } + } + if (vport->num_rxq != k - (vport->num_txq + vport->num_complq)) { + err = -EINVAL; + goto error; + } + + if (!idpf_is_queue_model_split(vport->rxq_model)) + goto send_msg; + + for (i = 0; i < vport->num_rxq_grp; i++) { + struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i]; + + for (j = 0; j < vport->num_bufqs_per_qgrp; j++, k++) { + struct idpf_queue *q; + + q = &rx_qgrp->splitq.bufq_sets[j].bufq; + qc[k].type = cpu_to_le32(q->q_type); + qc[k].start_queue_id = cpu_to_le32(q->q_id); + qc[k].num_queues = cpu_to_le32(IDPF_NUMQ_PER_CHUNK); + } + } + if (vport->num_bufq != k - (vport->num_txq + + vport->num_complq + + vport->num_rxq)) { + err = -EINVAL; + goto error; + } + +send_msg: + /* Chunk up the queue info into multiple messages */ + config_sz = sizeof(struct virtchnl2_del_ena_dis_queues); + chunk_sz = sizeof(struct virtchnl2_queue_chunk); + + num_chunks = min_t(u32, IDPF_NUM_CHUNKS_PER_MSG(config_sz, chunk_sz), + num_q); + num_msgs = DIV_ROUND_UP(num_q, num_chunks); + + buf_sz = struct_size(eq, chunks.chunks, num_chunks); + eq = kzalloc(buf_sz, GFP_KERNEL); + if (!eq) { + err = -ENOMEM; + goto error; + } + + mutex_lock(&vport->vc_buf_lock); + + for (i = 0, k = 0; i < num_msgs; i++) { + memset(eq, 0, buf_sz); + eq->vport_id = cpu_to_le32(vport->vport_id); + eq->chunks.num_chunks = cpu_to_le16(num_chunks); + qcs = &eq->chunks; + memcpy(qcs->chunks, &qc[k], chunk_sz * num_chunks); + + err = idpf_send_mb_msg(adapter, vc_op, buf_sz, (u8 *)eq); + if (err) + goto mbx_error; + + if (vc_op == VIRTCHNL2_OP_ENABLE_QUEUES) + err = idpf_wait_for_event(adapter, vport, + IDPF_VC_ENA_QUEUES, + IDPF_VC_ENA_QUEUES_ERR); + else + err = idpf_min_wait_for_event(adapter, vport, + IDPF_VC_DIS_QUEUES, + IDPF_VC_DIS_QUEUES_ERR); + if (err) + goto mbx_error; + + k += num_chunks; + num_q -= num_chunks; + num_chunks = min(num_chunks, num_q); + /* Recalculate buffer size */ + buf_sz = struct_size(eq, chunks.chunks, num_chunks); + } + +mbx_error: + mutex_unlock(&vport->vc_buf_lock); + kfree(eq); +error: + kfree(qc); + + return err; +} + +/** + * idpf_send_map_unmap_queue_vector_msg - Send virtchnl map or unmap queue + * vector message + * @vport: virtual port data structure + * @map: true for map and false for unmap + * + * Send map or unmap queue vector virtchnl message. Returns 0 on success, + * negative on failure. + */ +int idpf_send_map_unmap_queue_vector_msg(struct idpf_vport *vport, bool map) +{ + struct idpf_adapter *adapter = vport->adapter; + struct virtchnl2_queue_vector_maps *vqvm; + struct virtchnl2_queue_vector *vqv; + u32 config_sz, chunk_sz, buf_sz; + u32 num_msgs, num_chunks, num_q; + int i, j, k = 0, err = 0; + + num_q = vport->num_txq + vport->num_rxq; + + buf_sz = sizeof(struct virtchnl2_queue_vector) * num_q; + vqv = kzalloc(buf_sz, GFP_KERNEL); + if (!vqv) + return -ENOMEM; + + for (i = 0; i < vport->num_txq_grp; i++) { + struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i]; + + for (j = 0; j < tx_qgrp->num_txq; j++, k++) { + vqv[k].queue_type = cpu_to_le32(tx_qgrp->txqs[j]->q_type); + vqv[k].queue_id = cpu_to_le32(tx_qgrp->txqs[j]->q_id); + + if (idpf_is_queue_model_split(vport->txq_model)) { + vqv[k].vector_id = + cpu_to_le16(tx_qgrp->complq->q_vector->v_idx); + vqv[k].itr_idx = + cpu_to_le32(tx_qgrp->complq->q_vector->tx_itr_idx); + } else { + vqv[k].vector_id = + cpu_to_le16(tx_qgrp->txqs[j]->q_vector->v_idx); + vqv[k].itr_idx = + cpu_to_le32(tx_qgrp->txqs[j]->q_vector->tx_itr_idx); + } + } + } + + if (vport->num_txq != k) { + err = -EINVAL; + goto error; + } + + for (i = 0; i < vport->num_rxq_grp; i++) { + struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i]; + u16 num_rxq; + + if (idpf_is_queue_model_split(vport->rxq_model)) + num_rxq = rx_qgrp->splitq.num_rxq_sets; + else + num_rxq = rx_qgrp->singleq.num_rxq; + + for (j = 0; j < num_rxq; j++, k++) { + struct idpf_queue *rxq; + + if (idpf_is_queue_model_split(vport->rxq_model)) + rxq = &rx_qgrp->splitq.rxq_sets[j]->rxq; + else + rxq = rx_qgrp->singleq.rxqs[j]; + + vqv[k].queue_type = cpu_to_le32(rxq->q_type); + vqv[k].queue_id = cpu_to_le32(rxq->q_id); + vqv[k].vector_id = cpu_to_le16(rxq->q_vector->v_idx); + vqv[k].itr_idx = cpu_to_le32(rxq->q_vector->rx_itr_idx); + } + } + + if (idpf_is_queue_model_split(vport->txq_model)) { + if (vport->num_rxq != k - vport->num_complq) { + err = -EINVAL; + goto error; + } + } else { + if (vport->num_rxq != k - vport->num_txq) { + err = -EINVAL; + goto error; + } + } + + /* Chunk up the vector info into multiple messages */ + config_sz = sizeof(struct virtchnl2_queue_vector_maps); + chunk_sz = sizeof(struct virtchnl2_queue_vector); + + num_chunks = min_t(u32, IDPF_NUM_CHUNKS_PER_MSG(config_sz, chunk_sz), + num_q); + num_msgs = DIV_ROUND_UP(num_q, num_chunks); + + buf_sz = struct_size(vqvm, qv_maps, num_chunks); + vqvm = kzalloc(buf_sz, GFP_KERNEL); + if (!vqvm) { + err = -ENOMEM; + goto error; + } + + mutex_lock(&vport->vc_buf_lock); + + for (i = 0, k = 0; i < num_msgs; i++) { + memset(vqvm, 0, buf_sz); + vqvm->vport_id = cpu_to_le32(vport->vport_id); + vqvm->num_qv_maps = cpu_to_le16(num_chunks); + memcpy(vqvm->qv_maps, &vqv[k], chunk_sz * num_chunks); + + if (map) { + err = idpf_send_mb_msg(adapter, + VIRTCHNL2_OP_MAP_QUEUE_VECTOR, + buf_sz, (u8 *)vqvm); + if (!err) + err = idpf_wait_for_event(adapter, vport, + IDPF_VC_MAP_IRQ, + IDPF_VC_MAP_IRQ_ERR); + } else { + err = idpf_send_mb_msg(adapter, + VIRTCHNL2_OP_UNMAP_QUEUE_VECTOR, + buf_sz, (u8 *)vqvm); + if (!err) + err = + idpf_min_wait_for_event(adapter, vport, + IDPF_VC_UNMAP_IRQ, + IDPF_VC_UNMAP_IRQ_ERR); + } + if (err) + goto mbx_error; + + k += num_chunks; + num_q -= num_chunks; + num_chunks = min(num_chunks, num_q); + /* Recalculate buffer size */ + buf_sz = struct_size(vqvm, qv_maps, num_chunks); + } + +mbx_error: + mutex_unlock(&vport->vc_buf_lock); + kfree(vqvm); +error: + kfree(vqv); + + return err; +} + +/** + * idpf_send_enable_queues_msg - send enable queues virtchnl message + * @vport: Virtual port private data structure + * + * Will send enable queues virtchnl message. Returns 0 on success, negative on + * failure. + */ +int idpf_send_enable_queues_msg(struct idpf_vport *vport) +{ + return idpf_send_ena_dis_queues_msg(vport, VIRTCHNL2_OP_ENABLE_QUEUES); +} + +/** + * idpf_send_disable_queues_msg - send disable queues virtchnl message + * @vport: Virtual port private data structure + * + * Will send disable queues virtchnl message. Returns 0 on success, negative + * on failure. + */ +int idpf_send_disable_queues_msg(struct idpf_vport *vport) +{ + int err, i; + + err = idpf_send_ena_dis_queues_msg(vport, VIRTCHNL2_OP_DISABLE_QUEUES); + if (err) + return err; + + /* switch to poll mode as interrupts will be disabled after disable + * queues virtchnl message is sent + */ + for (i = 0; i < vport->num_txq; i++) + set_bit(__IDPF_Q_POLL_MODE, vport->txqs[i]->flags); + + /* schedule the napi to receive all the marker packets */ + for (i = 0; i < vport->num_q_vectors; i++) + napi_schedule(&vport->q_vectors[i].napi); + + return idpf_wait_for_marker_event(vport); +} + +/** + * idpf_convert_reg_to_queue_chunks - Copy queue chunk information to the right + * structure + * @dchunks: Destination chunks to store data to + * @schunks: Source chunks to copy data from + * @num_chunks: number of chunks to copy + */ +static void idpf_convert_reg_to_queue_chunks(struct virtchnl2_queue_chunk *dchunks, + struct virtchnl2_queue_reg_chunk *schunks, + u16 num_chunks) +{ + u16 i; + + for (i = 0; i < num_chunks; i++) { + dchunks[i].type = schunks[i].type; + dchunks[i].start_queue_id = schunks[i].start_queue_id; + dchunks[i].num_queues = schunks[i].num_queues; + } +} + +/** + * idpf_send_delete_queues_msg - send delete queues virtchnl message + * @vport: Virtual port private data structure + * + * Will send delete queues virtchnl message. Return 0 on success, negative on + * failure. + */ +int idpf_send_delete_queues_msg(struct idpf_vport *vport) +{ + struct idpf_adapter *adapter = vport->adapter; + struct virtchnl2_create_vport *vport_params; + struct virtchnl2_queue_reg_chunks *chunks; + struct virtchnl2_del_ena_dis_queues *eq; + struct idpf_vport_config *vport_config; + u16 vport_idx = vport->idx; + int buf_size, err; + u16 num_chunks; + + vport_config = adapter->vport_config[vport_idx]; + if (vport_config->req_qs_chunks) { + struct virtchnl2_add_queues *vc_aq = + (struct virtchnl2_add_queues *)vport_config->req_qs_chunks; + chunks = &vc_aq->chunks; + } else { + vport_params = adapter->vport_params_recvd[vport_idx]; + chunks = &vport_params->chunks; + } + + num_chunks = le16_to_cpu(chunks->num_chunks); + buf_size = struct_size(eq, chunks.chunks, num_chunks); + + eq = kzalloc(buf_size, GFP_KERNEL); + if (!eq) + return -ENOMEM; + + eq->vport_id = cpu_to_le32(vport->vport_id); + eq->chunks.num_chunks = cpu_to_le16(num_chunks); + + idpf_convert_reg_to_queue_chunks(eq->chunks.chunks, chunks->chunks, + num_chunks); + + mutex_lock(&vport->vc_buf_lock); + + err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_DEL_QUEUES, + buf_size, (u8 *)eq); + if (err) + goto rel_lock; + + err = idpf_min_wait_for_event(adapter, vport, IDPF_VC_DEL_QUEUES, + IDPF_VC_DEL_QUEUES_ERR); + +rel_lock: + mutex_unlock(&vport->vc_buf_lock); + kfree(eq); + + return err; +} + +/** + * idpf_send_config_queues_msg - Send config queues virtchnl message + * @vport: Virtual port private data structure + * + * Will send config queues virtchnl message. Returns 0 on success, negative on + * failure. + */ +int idpf_send_config_queues_msg(struct idpf_vport *vport) +{ + int err; + + err = idpf_send_config_tx_queues_msg(vport); + if (err) + return err; + + return idpf_send_config_rx_queues_msg(vport); +} + +/** + * idpf_send_add_queues_msg - Send virtchnl add queues message + * @vport: Virtual port private data structure + * @num_tx_q: number of transmit queues + * @num_complq: number of transmit completion queues + * @num_rx_q: number of receive queues + * @num_rx_bufq: number of receive buffer queues + * + * Returns 0 on success, negative on failure. vport _MUST_ be const here as + * we should not change any fields within vport itself in this function. + */ +int idpf_send_add_queues_msg(const struct idpf_vport *vport, u16 num_tx_q, + u16 num_complq, u16 num_rx_q, u16 num_rx_bufq) +{ + struct idpf_adapter *adapter = vport->adapter; + struct idpf_vport_config *vport_config; + struct virtchnl2_add_queues aq = { }; + struct virtchnl2_add_queues *vc_msg; + u16 vport_idx = vport->idx; + int size, err; + + vport_config = adapter->vport_config[vport_idx]; + + aq.vport_id = cpu_to_le32(vport->vport_id); + aq.num_tx_q = cpu_to_le16(num_tx_q); + aq.num_tx_complq = cpu_to_le16(num_complq); + aq.num_rx_q = cpu_to_le16(num_rx_q); + aq.num_rx_bufq = cpu_to_le16(num_rx_bufq); + + mutex_lock(&((struct idpf_vport *)vport)->vc_buf_lock); + + err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_ADD_QUEUES, + sizeof(struct virtchnl2_add_queues), (u8 *)&aq); + if (err) + goto rel_lock; + + /* We want vport to be const to prevent incidental code changes making + * changes to the vport config. We're making a special exception here + * to discard const to use the virtchnl. + */ + err = idpf_wait_for_event(adapter, (struct idpf_vport *)vport, + IDPF_VC_ADD_QUEUES, IDPF_VC_ADD_QUEUES_ERR); + if (err) + goto rel_lock; + + kfree(vport_config->req_qs_chunks); + vport_config->req_qs_chunks = NULL; + + vc_msg = (struct virtchnl2_add_queues *)vport->vc_msg; + /* compare vc_msg num queues with vport num queues */ + if (le16_to_cpu(vc_msg->num_tx_q) != num_tx_q || + le16_to_cpu(vc_msg->num_rx_q) != num_rx_q || + le16_to_cpu(vc_msg->num_tx_complq) != num_complq || + le16_to_cpu(vc_msg->num_rx_bufq) != num_rx_bufq) { + err = -EINVAL; + goto rel_lock; + } + + size = struct_size(vc_msg, chunks.chunks, + le16_to_cpu(vc_msg->chunks.num_chunks)); + vport_config->req_qs_chunks = kmemdup(vc_msg, size, GFP_KERNEL); + if (!vport_config->req_qs_chunks) { + err = -ENOMEM; + goto rel_lock; + } + +rel_lock: + mutex_unlock(&((struct idpf_vport *)vport)->vc_buf_lock); + + return err; +} + +/** + * idpf_send_alloc_vectors_msg - Send virtchnl alloc vectors message + * @adapter: Driver specific private structure + * @num_vectors: number of vectors to be allocated + * + * Returns 0 on success, negative on failure. + */ +int idpf_send_alloc_vectors_msg(struct idpf_adapter *adapter, u16 num_vectors) +{ + struct virtchnl2_alloc_vectors *alloc_vec, *rcvd_vec; + struct virtchnl2_alloc_vectors ac = { }; + u16 num_vchunks; + int size, err; + + ac.num_vectors = cpu_to_le16(num_vectors); + + mutex_lock(&adapter->vc_buf_lock); + + err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_ALLOC_VECTORS, + sizeof(ac), (u8 *)&ac); + if (err) + goto rel_lock; + + err = idpf_wait_for_event(adapter, NULL, IDPF_VC_ALLOC_VECTORS, + IDPF_VC_ALLOC_VECTORS_ERR); + if (err) + goto rel_lock; + + rcvd_vec = (struct virtchnl2_alloc_vectors *)adapter->vc_msg; + num_vchunks = le16_to_cpu(rcvd_vec->vchunks.num_vchunks); + + size = struct_size(rcvd_vec, vchunks.vchunks, num_vchunks); + if (size > sizeof(adapter->vc_msg)) { + err = -EINVAL; + goto rel_lock; + } + + kfree(adapter->req_vec_chunks); + adapter->req_vec_chunks = NULL; + adapter->req_vec_chunks = kmemdup(adapter->vc_msg, size, GFP_KERNEL); + if (!adapter->req_vec_chunks) { + err = -ENOMEM; + goto rel_lock; + } + + alloc_vec = adapter->req_vec_chunks; + if (le16_to_cpu(alloc_vec->num_vectors) < num_vectors) { + kfree(adapter->req_vec_chunks); + adapter->req_vec_chunks = NULL; + err = -EINVAL; + } + +rel_lock: + mutex_unlock(&adapter->vc_buf_lock); + + return err; +} + +/** + * idpf_send_dealloc_vectors_msg - Send virtchnl de allocate vectors message + * @adapter: Driver specific private structure + * + * Returns 0 on success, negative on failure. + */ +int idpf_send_dealloc_vectors_msg(struct idpf_adapter *adapter) +{ + struct virtchnl2_alloc_vectors *ac = adapter->req_vec_chunks; + struct virtchnl2_vector_chunks *vcs = &ac->vchunks; + int buf_size, err; + + buf_size = struct_size(vcs, vchunks, le16_to_cpu(vcs->num_vchunks)); + + mutex_lock(&adapter->vc_buf_lock); + + err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_DEALLOC_VECTORS, buf_size, + (u8 *)vcs); + if (err) + goto rel_lock; + + err = idpf_min_wait_for_event(adapter, NULL, IDPF_VC_DEALLOC_VECTORS, + IDPF_VC_DEALLOC_VECTORS_ERR); + if (err) + goto rel_lock; + + kfree(adapter->req_vec_chunks); + adapter->req_vec_chunks = NULL; + +rel_lock: + mutex_unlock(&adapter->vc_buf_lock); + + return err; +} + +/** + * idpf_get_max_vfs - Get max number of vfs supported + * @adapter: Driver specific private structure + * + * Returns max number of VFs + */ +static int idpf_get_max_vfs(struct idpf_adapter *adapter) +{ + return le16_to_cpu(adapter->caps.max_sriov_vfs); +} + +/** + * idpf_send_set_sriov_vfs_msg - Send virtchnl set sriov vfs message + * @adapter: Driver specific private structure + * @num_vfs: number of virtual functions to be created + * + * Returns 0 on success, negative on failure. + */ +int idpf_send_set_sriov_vfs_msg(struct idpf_adapter *adapter, u16 num_vfs) +{ + struct virtchnl2_sriov_vfs_info svi = { }; + int err; + + svi.num_vfs = cpu_to_le16(num_vfs); + + mutex_lock(&adapter->vc_buf_lock); + + err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_SET_SRIOV_VFS, + sizeof(svi), (u8 *)&svi); + if (err) + goto rel_lock; + + err = idpf_wait_for_event(adapter, NULL, IDPF_VC_SET_SRIOV_VFS, + IDPF_VC_SET_SRIOV_VFS_ERR); + +rel_lock: + mutex_unlock(&adapter->vc_buf_lock); + + return err; +} + +/** + * idpf_send_get_stats_msg - Send virtchnl get statistics message + * @vport: vport to get stats for + * + * Returns 0 on success, negative on failure. + */ +int idpf_send_get_stats_msg(struct idpf_vport *vport) +{ + struct idpf_netdev_priv *np = netdev_priv(vport->netdev); + struct rtnl_link_stats64 *netstats = &np->netstats; + struct idpf_adapter *adapter = vport->adapter; + struct virtchnl2_vport_stats stats_msg = { }; + struct virtchnl2_vport_stats *stats; + int err; + + /* Don't send get_stats message if the link is down */ + if (np->state <= __IDPF_VPORT_DOWN) + return 0; + + stats_msg.vport_id = cpu_to_le32(vport->vport_id); + + mutex_lock(&vport->vc_buf_lock); + + err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_GET_STATS, + sizeof(struct virtchnl2_vport_stats), + (u8 *)&stats_msg); + if (err) + goto rel_lock; + + err = idpf_wait_for_event(adapter, vport, IDPF_VC_GET_STATS, + IDPF_VC_GET_STATS_ERR); + if (err) + goto rel_lock; + + stats = (struct virtchnl2_vport_stats *)vport->vc_msg; + + spin_lock_bh(&np->stats_lock); + + netstats->rx_packets = le64_to_cpu(stats->rx_unicast) + + le64_to_cpu(stats->rx_multicast) + + le64_to_cpu(stats->rx_broadcast); + netstats->rx_bytes = le64_to_cpu(stats->rx_bytes); + netstats->rx_dropped = le64_to_cpu(stats->rx_discards); + netstats->rx_over_errors = le64_to_cpu(stats->rx_overflow_drop); + netstats->rx_length_errors = le64_to_cpu(stats->rx_invalid_frame_length); + + netstats->tx_packets = le64_to_cpu(stats->tx_unicast) + + le64_to_cpu(stats->tx_multicast) + + le64_to_cpu(stats->tx_broadcast); + netstats->tx_bytes = le64_to_cpu(stats->tx_bytes); + netstats->tx_errors = le64_to_cpu(stats->tx_errors); + netstats->tx_dropped = le64_to_cpu(stats->tx_discards); + + vport->port_stats.vport_stats = *stats; + + spin_unlock_bh(&np->stats_lock); + +rel_lock: + mutex_unlock(&vport->vc_buf_lock); + + return err; +} + +/** + * idpf_send_get_set_rss_lut_msg - Send virtchnl get or set rss lut message + * @vport: virtual port data structure + * @get: flag to set or get rss look up table + * + * Returns 0 on success, negative on failure. + */ +int idpf_send_get_set_rss_lut_msg(struct idpf_vport *vport, bool get) +{ + struct idpf_adapter *adapter = vport->adapter; + struct virtchnl2_rss_lut *recv_rl; + struct idpf_rss_data *rss_data; + struct virtchnl2_rss_lut *rl; + int buf_size, lut_buf_size; + int i, err; + + rss_data = &adapter->vport_config[vport->idx]->user_config.rss_data; + buf_size = struct_size(rl, lut, rss_data->rss_lut_size); + rl = kzalloc(buf_size, GFP_KERNEL); + if (!rl) + return -ENOMEM; + + rl->vport_id = cpu_to_le32(vport->vport_id); + mutex_lock(&vport->vc_buf_lock); + + if (!get) { + rl->lut_entries = cpu_to_le16(rss_data->rss_lut_size); + for (i = 0; i < rss_data->rss_lut_size; i++) + rl->lut[i] = cpu_to_le32(rss_data->rss_lut[i]); + + err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_SET_RSS_LUT, + buf_size, (u8 *)rl); + if (err) + goto free_mem; + + err = idpf_wait_for_event(adapter, vport, IDPF_VC_SET_RSS_LUT, + IDPF_VC_SET_RSS_LUT_ERR); + + goto free_mem; + } + + err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_GET_RSS_LUT, + buf_size, (u8 *)rl); + if (err) + goto free_mem; + + err = idpf_wait_for_event(adapter, vport, IDPF_VC_GET_RSS_LUT, + IDPF_VC_GET_RSS_LUT_ERR); + if (err) + goto free_mem; + + recv_rl = (struct virtchnl2_rss_lut *)vport->vc_msg; + if (rss_data->rss_lut_size == le16_to_cpu(recv_rl->lut_entries)) + goto do_memcpy; + + rss_data->rss_lut_size = le16_to_cpu(recv_rl->lut_entries); + kfree(rss_data->rss_lut); + + lut_buf_size = rss_data->rss_lut_size * sizeof(u32); + rss_data->rss_lut = kzalloc(lut_buf_size, GFP_KERNEL); + if (!rss_data->rss_lut) { + rss_data->rss_lut_size = 0; + err = -ENOMEM; + goto free_mem; + } + +do_memcpy: + memcpy(rss_data->rss_lut, vport->vc_msg, rss_data->rss_lut_size); +free_mem: + mutex_unlock(&vport->vc_buf_lock); + kfree(rl); + + return err; +} + +/** + * idpf_send_get_set_rss_key_msg - Send virtchnl get or set rss key message + * @vport: virtual port data structure + * @get: flag to set or get rss look up table + * + * Returns 0 on success, negative on failure + */ +int idpf_send_get_set_rss_key_msg(struct idpf_vport *vport, bool get) +{ + struct idpf_adapter *adapter = vport->adapter; + struct virtchnl2_rss_key *recv_rk; + struct idpf_rss_data *rss_data; + struct virtchnl2_rss_key *rk; + int i, buf_size, err; + + rss_data = &adapter->vport_config[vport->idx]->user_config.rss_data; + buf_size = struct_size(rk, key_flex, rss_data->rss_key_size); + rk = kzalloc(buf_size, GFP_KERNEL); + if (!rk) + return -ENOMEM; + + rk->vport_id = cpu_to_le32(vport->vport_id); + mutex_lock(&vport->vc_buf_lock); + + if (get) { + err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_GET_RSS_KEY, + buf_size, (u8 *)rk); + if (err) + goto error; + + err = idpf_wait_for_event(adapter, vport, IDPF_VC_GET_RSS_KEY, + IDPF_VC_GET_RSS_KEY_ERR); + if (err) + goto error; + + recv_rk = (struct virtchnl2_rss_key *)vport->vc_msg; + if (rss_data->rss_key_size != + le16_to_cpu(recv_rk->key_len)) { + rss_data->rss_key_size = + min_t(u16, NETDEV_RSS_KEY_LEN, + le16_to_cpu(recv_rk->key_len)); + kfree(rss_data->rss_key); + rss_data->rss_key = kzalloc(rss_data->rss_key_size, + GFP_KERNEL); + if (!rss_data->rss_key) { + rss_data->rss_key_size = 0; + err = -ENOMEM; + goto error; + } + } + memcpy(rss_data->rss_key, recv_rk->key_flex, + rss_data->rss_key_size); + } else { + rk->key_len = cpu_to_le16(rss_data->rss_key_size); + for (i = 0; i < rss_data->rss_key_size; i++) + rk->key_flex[i] = rss_data->rss_key[i]; + + err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_SET_RSS_KEY, + buf_size, (u8 *)rk); + if (err) + goto error; + + err = idpf_wait_for_event(adapter, vport, IDPF_VC_SET_RSS_KEY, + IDPF_VC_SET_RSS_KEY_ERR); + } + +error: + mutex_unlock(&vport->vc_buf_lock); + kfree(rk); + + return err; +} + +/** + * idpf_fill_ptype_lookup - Fill L3 specific fields in ptype lookup table + * @ptype: ptype lookup table + * @pstate: state machine for ptype lookup table + * @ipv4: ipv4 or ipv6 + * @frag: fragmentation allowed + * + */ +static void idpf_fill_ptype_lookup(struct idpf_rx_ptype_decoded *ptype, + struct idpf_ptype_state *pstate, + bool ipv4, bool frag) +{ + if (!pstate->outer_ip || !pstate->outer_frag) { + ptype->outer_ip = IDPF_RX_PTYPE_OUTER_IP; + pstate->outer_ip = true; + + if (ipv4) + ptype->outer_ip_ver = IDPF_RX_PTYPE_OUTER_IPV4; + else + ptype->outer_ip_ver = IDPF_RX_PTYPE_OUTER_IPV6; + + if (frag) { + ptype->outer_frag = IDPF_RX_PTYPE_FRAG; + pstate->outer_frag = true; + } + } else { + ptype->tunnel_type = IDPF_RX_PTYPE_TUNNEL_IP_IP; + pstate->tunnel_state = IDPF_PTYPE_TUNNEL_IP; + + if (ipv4) + ptype->tunnel_end_prot = + IDPF_RX_PTYPE_TUNNEL_END_IPV4; + else + ptype->tunnel_end_prot = + IDPF_RX_PTYPE_TUNNEL_END_IPV6; + + if (frag) + ptype->tunnel_end_frag = IDPF_RX_PTYPE_FRAG; + } +} + +/** + * idpf_send_get_rx_ptype_msg - Send virtchnl for ptype info + * @vport: virtual port data structure + * + * Returns 0 on success, negative on failure. + */ +int idpf_send_get_rx_ptype_msg(struct idpf_vport *vport) +{ + struct idpf_rx_ptype_decoded *ptype_lkup = vport->rx_ptype_lkup; + struct virtchnl2_get_ptype_info get_ptype_info; + int max_ptype, ptypes_recvd = 0, ptype_offset; + struct idpf_adapter *adapter = vport->adapter; + struct virtchnl2_get_ptype_info *ptype_info; + u16 next_ptype_id = 0; + int err = 0, i, j, k; + + if (idpf_is_queue_model_split(vport->rxq_model)) + max_ptype = IDPF_RX_MAX_PTYPE; + else + max_ptype = IDPF_RX_MAX_BASE_PTYPE; + + memset(vport->rx_ptype_lkup, 0, sizeof(vport->rx_ptype_lkup)); + + ptype_info = kzalloc(IDPF_CTLQ_MAX_BUF_LEN, GFP_KERNEL); + if (!ptype_info) + return -ENOMEM; + + mutex_lock(&adapter->vc_buf_lock); + + while (next_ptype_id < max_ptype) { + get_ptype_info.start_ptype_id = cpu_to_le16(next_ptype_id); + + if ((next_ptype_id + IDPF_RX_MAX_PTYPES_PER_BUF) > max_ptype) + get_ptype_info.num_ptypes = + cpu_to_le16(max_ptype - next_ptype_id); + else + get_ptype_info.num_ptypes = + cpu_to_le16(IDPF_RX_MAX_PTYPES_PER_BUF); + + err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_GET_PTYPE_INFO, + sizeof(struct virtchnl2_get_ptype_info), + (u8 *)&get_ptype_info); + if (err) + goto vc_buf_unlock; + + err = idpf_wait_for_event(adapter, NULL, IDPF_VC_GET_PTYPE_INFO, + IDPF_VC_GET_PTYPE_INFO_ERR); + if (err) + goto vc_buf_unlock; + + memcpy(ptype_info, adapter->vc_msg, IDPF_CTLQ_MAX_BUF_LEN); + + ptypes_recvd += le16_to_cpu(ptype_info->num_ptypes); + if (ptypes_recvd > max_ptype) { + err = -EINVAL; + goto vc_buf_unlock; + } + + next_ptype_id = le16_to_cpu(get_ptype_info.start_ptype_id) + + le16_to_cpu(get_ptype_info.num_ptypes); + + ptype_offset = IDPF_RX_PTYPE_HDR_SZ; + + for (i = 0; i < le16_to_cpu(ptype_info->num_ptypes); i++) { + struct idpf_ptype_state pstate = { }; + struct virtchnl2_ptype *ptype; + u16 id; + + ptype = (struct virtchnl2_ptype *) + ((u8 *)ptype_info + ptype_offset); + + ptype_offset += IDPF_GET_PTYPE_SIZE(ptype); + if (ptype_offset > IDPF_CTLQ_MAX_BUF_LEN) { + err = -EINVAL; + goto vc_buf_unlock; + } + + /* 0xFFFF indicates end of ptypes */ + if (le16_to_cpu(ptype->ptype_id_10) == + IDPF_INVALID_PTYPE_ID) { + err = 0; + goto vc_buf_unlock; + } + + if (idpf_is_queue_model_split(vport->rxq_model)) + k = le16_to_cpu(ptype->ptype_id_10); + else + k = ptype->ptype_id_8; + + if (ptype->proto_id_count) + ptype_lkup[k].known = 1; + + for (j = 0; j < ptype->proto_id_count; j++) { + id = le16_to_cpu(ptype->proto_id[j]); + switch (id) { + case VIRTCHNL2_PROTO_HDR_GRE: + if (pstate.tunnel_state == + IDPF_PTYPE_TUNNEL_IP) { + ptype_lkup[k].tunnel_type = + IDPF_RX_PTYPE_TUNNEL_IP_GRENAT; + pstate.tunnel_state |= + IDPF_PTYPE_TUNNEL_IP_GRENAT; + } + break; + case VIRTCHNL2_PROTO_HDR_MAC: + ptype_lkup[k].outer_ip = + IDPF_RX_PTYPE_OUTER_L2; + if (pstate.tunnel_state == + IDPF_TUN_IP_GRE) { + ptype_lkup[k].tunnel_type = + IDPF_RX_PTYPE_TUNNEL_IP_GRENAT_MAC; + pstate.tunnel_state |= + IDPF_PTYPE_TUNNEL_IP_GRENAT_MAC; + } + break; + case VIRTCHNL2_PROTO_HDR_IPV4: + idpf_fill_ptype_lookup(&ptype_lkup[k], + &pstate, true, + false); + break; + case VIRTCHNL2_PROTO_HDR_IPV6: + idpf_fill_ptype_lookup(&ptype_lkup[k], + &pstate, false, + false); + break; + case VIRTCHNL2_PROTO_HDR_IPV4_FRAG: + idpf_fill_ptype_lookup(&ptype_lkup[k], + &pstate, true, + true); + break; + case VIRTCHNL2_PROTO_HDR_IPV6_FRAG: + idpf_fill_ptype_lookup(&ptype_lkup[k], + &pstate, false, + true); + break; + case VIRTCHNL2_PROTO_HDR_UDP: + ptype_lkup[k].inner_prot = + IDPF_RX_PTYPE_INNER_PROT_UDP; + break; + case VIRTCHNL2_PROTO_HDR_TCP: + ptype_lkup[k].inner_prot = + IDPF_RX_PTYPE_INNER_PROT_TCP; + break; + case VIRTCHNL2_PROTO_HDR_SCTP: + ptype_lkup[k].inner_prot = + IDPF_RX_PTYPE_INNER_PROT_SCTP; + break; + case VIRTCHNL2_PROTO_HDR_ICMP: + ptype_lkup[k].inner_prot = + IDPF_RX_PTYPE_INNER_PROT_ICMP; + break; + case VIRTCHNL2_PROTO_HDR_PAY: + ptype_lkup[k].payload_layer = + IDPF_RX_PTYPE_PAYLOAD_LAYER_PAY2; + break; + case VIRTCHNL2_PROTO_HDR_ICMPV6: + case VIRTCHNL2_PROTO_HDR_IPV6_EH: + case VIRTCHNL2_PROTO_HDR_PRE_MAC: + case VIRTCHNL2_PROTO_HDR_POST_MAC: + case VIRTCHNL2_PROTO_HDR_ETHERTYPE: + case VIRTCHNL2_PROTO_HDR_SVLAN: + case VIRTCHNL2_PROTO_HDR_CVLAN: + case VIRTCHNL2_PROTO_HDR_MPLS: + case VIRTCHNL2_PROTO_HDR_MMPLS: + case VIRTCHNL2_PROTO_HDR_PTP: + case VIRTCHNL2_PROTO_HDR_CTRL: + case VIRTCHNL2_PROTO_HDR_LLDP: + case VIRTCHNL2_PROTO_HDR_ARP: + case VIRTCHNL2_PROTO_HDR_ECP: + case VIRTCHNL2_PROTO_HDR_EAPOL: + case VIRTCHNL2_PROTO_HDR_PPPOD: + case VIRTCHNL2_PROTO_HDR_PPPOE: + case VIRTCHNL2_PROTO_HDR_IGMP: + case VIRTCHNL2_PROTO_HDR_AH: + case VIRTCHNL2_PROTO_HDR_ESP: + case VIRTCHNL2_PROTO_HDR_IKE: + case VIRTCHNL2_PROTO_HDR_NATT_KEEP: + case VIRTCHNL2_PROTO_HDR_L2TPV2: + case VIRTCHNL2_PROTO_HDR_L2TPV2_CONTROL: + case VIRTCHNL2_PROTO_HDR_L2TPV3: + case VIRTCHNL2_PROTO_HDR_GTP: + case VIRTCHNL2_PROTO_HDR_GTP_EH: + case VIRTCHNL2_PROTO_HDR_GTPCV2: + case VIRTCHNL2_PROTO_HDR_GTPC_TEID: + case VIRTCHNL2_PROTO_HDR_GTPU: + case VIRTCHNL2_PROTO_HDR_GTPU_UL: + case VIRTCHNL2_PROTO_HDR_GTPU_DL: + case VIRTCHNL2_PROTO_HDR_ECPRI: + case VIRTCHNL2_PROTO_HDR_VRRP: + case VIRTCHNL2_PROTO_HDR_OSPF: + case VIRTCHNL2_PROTO_HDR_TUN: + case VIRTCHNL2_PROTO_HDR_NVGRE: + case VIRTCHNL2_PROTO_HDR_VXLAN: + case VIRTCHNL2_PROTO_HDR_VXLAN_GPE: + case VIRTCHNL2_PROTO_HDR_GENEVE: + case VIRTCHNL2_PROTO_HDR_NSH: + case VIRTCHNL2_PROTO_HDR_QUIC: + case VIRTCHNL2_PROTO_HDR_PFCP: + case VIRTCHNL2_PROTO_HDR_PFCP_NODE: + case VIRTCHNL2_PROTO_HDR_PFCP_SESSION: + case VIRTCHNL2_PROTO_HDR_RTP: + case VIRTCHNL2_PROTO_HDR_NO_PROTO: + break; + default: + break; + } + } + } + } + +vc_buf_unlock: + mutex_unlock(&adapter->vc_buf_lock); + kfree(ptype_info); + + return err; +} + +/** + * idpf_send_ena_dis_loopback_msg - Send virtchnl enable/disable loopback + * message + * @vport: virtual port data structure + * + * Returns 0 on success, negative on failure. + */ +int idpf_send_ena_dis_loopback_msg(struct idpf_vport *vport) +{ + struct virtchnl2_loopback loopback; + int err; + + loopback.vport_id = cpu_to_le32(vport->vport_id); + loopback.enable = idpf_is_feature_ena(vport, NETIF_F_LOOPBACK); + + mutex_lock(&vport->vc_buf_lock); + + err = idpf_send_mb_msg(vport->adapter, VIRTCHNL2_OP_LOOPBACK, + sizeof(loopback), (u8 *)&loopback); + if (err) + goto rel_lock; + + err = idpf_wait_for_event(vport->adapter, vport, + IDPF_VC_LOOPBACK_STATE, + IDPF_VC_LOOPBACK_STATE_ERR); + +rel_lock: + mutex_unlock(&vport->vc_buf_lock); + + return err; +} + +/** + * idpf_find_ctlq - Given a type and id, find ctlq info + * @hw: hardware struct + * @type: type of ctrlq to find + * @id: ctlq id to find + * + * Returns pointer to found ctlq info struct, NULL otherwise. + */ +static struct idpf_ctlq_info *idpf_find_ctlq(struct idpf_hw *hw, + enum idpf_ctlq_type type, int id) +{ + struct idpf_ctlq_info *cq, *tmp; + + list_for_each_entry_safe(cq, tmp, &hw->cq_list_head, cq_list) + if (cq->q_id == id && cq->cq_type == type) + return cq; + + return NULL; +} + +/** + * idpf_init_dflt_mbx - Setup default mailbox parameters and make request + * @adapter: adapter info struct + * + * Returns 0 on success, negative otherwise + */ +int idpf_init_dflt_mbx(struct idpf_adapter *adapter) +{ + struct idpf_ctlq_create_info ctlq_info[] = { + { + .type = IDPF_CTLQ_TYPE_MAILBOX_TX, + .id = IDPF_DFLT_MBX_ID, + .len = IDPF_DFLT_MBX_Q_LEN, + .buf_size = IDPF_CTLQ_MAX_BUF_LEN + }, + { + .type = IDPF_CTLQ_TYPE_MAILBOX_RX, + .id = IDPF_DFLT_MBX_ID, + .len = IDPF_DFLT_MBX_Q_LEN, + .buf_size = IDPF_CTLQ_MAX_BUF_LEN + } + }; + struct idpf_hw *hw = &adapter->hw; + int err; + + adapter->dev_ops.reg_ops.ctlq_reg_init(ctlq_info); + + err = idpf_ctlq_init(hw, IDPF_NUM_DFLT_MBX_Q, ctlq_info); + if (err) + return err; + + hw->asq = idpf_find_ctlq(hw, IDPF_CTLQ_TYPE_MAILBOX_TX, + IDPF_DFLT_MBX_ID); + hw->arq = idpf_find_ctlq(hw, IDPF_CTLQ_TYPE_MAILBOX_RX, + IDPF_DFLT_MBX_ID); + + if (!hw->asq || !hw->arq) { + idpf_ctlq_deinit(hw); + + return -ENOENT; + } + + adapter->state = __IDPF_STARTUP; + + return 0; +} + +/** + * idpf_deinit_dflt_mbx - Free up ctlqs setup + * @adapter: Driver specific private data structure + */ +void idpf_deinit_dflt_mbx(struct idpf_adapter *adapter) +{ + if (adapter->hw.arq && adapter->hw.asq) { + idpf_mb_clean(adapter); + idpf_ctlq_deinit(&adapter->hw); + } + adapter->hw.arq = NULL; + adapter->hw.asq = NULL; +} + +/** + * idpf_vport_params_buf_rel - Release memory for MailBox resources + * @adapter: Driver specific private data structure + * + * Will release memory to hold the vport parameters received on MailBox + */ +static void idpf_vport_params_buf_rel(struct idpf_adapter *adapter) +{ + kfree(adapter->vport_params_recvd); + adapter->vport_params_recvd = NULL; + kfree(adapter->vport_params_reqd); + adapter->vport_params_reqd = NULL; + kfree(adapter->vport_ids); + adapter->vport_ids = NULL; +} + +/** + * idpf_vport_params_buf_alloc - Allocate memory for MailBox resources + * @adapter: Driver specific private data structure + * + * Will alloc memory to hold the vport parameters received on MailBox + */ +static int idpf_vport_params_buf_alloc(struct idpf_adapter *adapter) +{ + u16 num_max_vports = idpf_get_max_vports(adapter); + + adapter->vport_params_reqd = kcalloc(num_max_vports, + sizeof(*adapter->vport_params_reqd), + GFP_KERNEL); + if (!adapter->vport_params_reqd) + return -ENOMEM; + + adapter->vport_params_recvd = kcalloc(num_max_vports, + sizeof(*adapter->vport_params_recvd), + GFP_KERNEL); + if (!adapter->vport_params_recvd) + goto err_mem; + + adapter->vport_ids = kcalloc(num_max_vports, sizeof(u32), GFP_KERNEL); + if (!adapter->vport_ids) + goto err_mem; + + if (adapter->vport_config) + return 0; + + adapter->vport_config = kcalloc(num_max_vports, + sizeof(*adapter->vport_config), + GFP_KERNEL); + if (!adapter->vport_config) + goto err_mem; + + return 0; + +err_mem: + idpf_vport_params_buf_rel(adapter); + + return -ENOMEM; +} + +/** + * idpf_vc_core_init - Initialize state machine and get driver specific + * resources + * @adapter: Driver specific private structure + * + * This function will initialize the state machine and request all necessary + * resources required by the device driver. Once the state machine is + * initialized, allocate memory to store vport specific information and also + * requests required interrupts. + * + * Returns 0 on success, -EAGAIN function will get called again, + * otherwise negative on failure. + */ +int idpf_vc_core_init(struct idpf_adapter *adapter) +{ + int task_delay = 30; + u16 num_max_vports; + int err = 0; + + while (adapter->state != __IDPF_INIT_SW) { + switch (adapter->state) { + case __IDPF_STARTUP: + if (idpf_send_ver_msg(adapter)) + goto init_failed; + adapter->state = __IDPF_VER_CHECK; + goto restart; + case __IDPF_VER_CHECK: + err = idpf_recv_ver_msg(adapter); + if (err == -EIO) { + return err; + } else if (err == -EAGAIN) { + adapter->state = __IDPF_STARTUP; + goto restart; + } else if (err) { + goto init_failed; + } + if (idpf_send_get_caps_msg(adapter)) + goto init_failed; + adapter->state = __IDPF_GET_CAPS; + goto restart; + case __IDPF_GET_CAPS: + if (idpf_recv_get_caps_msg(adapter)) + goto init_failed; + adapter->state = __IDPF_INIT_SW; + break; + default: + dev_err(&adapter->pdev->dev, "Device is in bad state: %d\n", + adapter->state); + goto init_failed; + } + break; +restart: + /* Give enough time before proceeding further with + * state machine + */ + msleep(task_delay); + } + + pci_sriov_set_totalvfs(adapter->pdev, idpf_get_max_vfs(adapter)); + num_max_vports = idpf_get_max_vports(adapter); + adapter->max_vports = num_max_vports; + adapter->vports = kcalloc(num_max_vports, sizeof(*adapter->vports), + GFP_KERNEL); + if (!adapter->vports) + return -ENOMEM; + + if (!adapter->netdevs) { + adapter->netdevs = kcalloc(num_max_vports, + sizeof(struct net_device *), + GFP_KERNEL); + if (!adapter->netdevs) { + err = -ENOMEM; + goto err_netdev_alloc; + } + } + + err = idpf_vport_params_buf_alloc(adapter); + if (err) { + dev_err(&adapter->pdev->dev, "Failed to alloc vport params buffer: %d\n", + err); + goto err_netdev_alloc; + } + + /* Start the mailbox task before requesting vectors. This will ensure + * vector information response from mailbox is handled + */ + queue_delayed_work(adapter->mbx_wq, &adapter->mbx_task, 0); + + queue_delayed_work(adapter->serv_wq, &adapter->serv_task, + msecs_to_jiffies(5 * (adapter->pdev->devfn & 0x07))); + + err = idpf_intr_req(adapter); + if (err) { + dev_err(&adapter->pdev->dev, "failed to enable interrupt vectors: %d\n", + err); + goto err_intr_req; + } + + idpf_init_avail_queues(adapter); + + /* Skew the delay for init tasks for each function based on fn number + * to prevent every function from making the same call simultaneously. + */ + queue_delayed_work(adapter->init_wq, &adapter->init_task, + msecs_to_jiffies(5 * (adapter->pdev->devfn & 0x07))); + + goto no_err; + +err_intr_req: + cancel_delayed_work_sync(&adapter->serv_task); + cancel_delayed_work_sync(&adapter->mbx_task); + idpf_vport_params_buf_rel(adapter); +err_netdev_alloc: + kfree(adapter->vports); + adapter->vports = NULL; +no_err: + return err; + +init_failed: + /* Don't retry if we're trying to go down, just bail. */ + if (test_bit(IDPF_REMOVE_IN_PROG, adapter->flags)) + return err; + + if (++adapter->mb_wait_count > IDPF_MB_MAX_ERR) { + dev_err(&adapter->pdev->dev, "Failed to establish mailbox communications with hardware\n"); + + return -EFAULT; + } + /* If it reached here, it is possible that mailbox queue initialization + * register writes might not have taken effect. Retry to initialize + * the mailbox again + */ + adapter->state = __IDPF_STARTUP; + idpf_deinit_dflt_mbx(adapter); + set_bit(IDPF_HR_DRV_LOAD, adapter->flags); + queue_delayed_work(adapter->vc_event_wq, &adapter->vc_event_task, + msecs_to_jiffies(task_delay)); + + return -EAGAIN; +} + +/** + * idpf_vc_core_deinit - Device deinit routine + * @adapter: Driver specific private structure + * + */ +void idpf_vc_core_deinit(struct idpf_adapter *adapter) +{ + int i; + + idpf_deinit_task(adapter); + idpf_intr_rel(adapter); + /* Set all bits as we dont know on which vc_state the vhnl_wq is + * waiting on and wakeup the virtchnl workqueue even if it is waiting + * for the response as we are going down + */ + for (i = 0; i < IDPF_VC_NBITS; i++) + set_bit(i, adapter->vc_state); + wake_up(&adapter->vchnl_wq); + + cancel_delayed_work_sync(&adapter->serv_task); + cancel_delayed_work_sync(&adapter->mbx_task); + + idpf_vport_params_buf_rel(adapter); + + /* Clear all the bits */ + for (i = 0; i < IDPF_VC_NBITS; i++) + clear_bit(i, adapter->vc_state); + + kfree(adapter->vports); + adapter->vports = NULL; +} + +/** + * idpf_vport_alloc_vec_indexes - Get relative vector indexes + * @vport: virtual port data struct + * + * This function requests the vector information required for the vport and + * stores the vector indexes received from the 'global vector distribution' + * in the vport's queue vectors array. + * + * Return 0 on success, error on failure + */ +int idpf_vport_alloc_vec_indexes(struct idpf_vport *vport) +{ + struct idpf_vector_info vec_info; + int num_alloc_vecs; + + vec_info.num_curr_vecs = vport->num_q_vectors; + vec_info.num_req_vecs = max(vport->num_txq, vport->num_rxq); + vec_info.default_vport = vport->default_vport; + vec_info.index = vport->idx; + + num_alloc_vecs = idpf_req_rel_vector_indexes(vport->adapter, + vport->q_vector_idxs, + &vec_info); + if (num_alloc_vecs <= 0) { + dev_err(&vport->adapter->pdev->dev, "Vector distribution failed: %d\n", + num_alloc_vecs); + return -EINVAL; + } + + vport->num_q_vectors = num_alloc_vecs; + + return 0; +} + +/** + * idpf_vport_init - Initialize virtual port + * @vport: virtual port to be initialized + * @max_q: vport max queue info + * + * Will initialize vport with the info received through MB earlier + */ +void idpf_vport_init(struct idpf_vport *vport, struct idpf_vport_max_q *max_q) +{ + struct idpf_adapter *adapter = vport->adapter; + struct virtchnl2_create_vport *vport_msg; + struct idpf_vport_config *vport_config; + u16 tx_itr[] = {2, 8, 64, 128, 256}; + u16 rx_itr[] = {2, 8, 32, 96, 128}; + struct idpf_rss_data *rss_data; + u16 idx = vport->idx; + + vport_config = adapter->vport_config[idx]; + rss_data = &vport_config->user_config.rss_data; + vport_msg = adapter->vport_params_recvd[idx]; + + vport_config->max_q.max_txq = max_q->max_txq; + vport_config->max_q.max_rxq = max_q->max_rxq; + vport_config->max_q.max_complq = max_q->max_complq; + vport_config->max_q.max_bufq = max_q->max_bufq; + + vport->txq_model = le16_to_cpu(vport_msg->txq_model); + vport->rxq_model = le16_to_cpu(vport_msg->rxq_model); + vport->vport_type = le16_to_cpu(vport_msg->vport_type); + vport->vport_id = le32_to_cpu(vport_msg->vport_id); + + rss_data->rss_key_size = min_t(u16, NETDEV_RSS_KEY_LEN, + le16_to_cpu(vport_msg->rss_key_size)); + rss_data->rss_lut_size = le16_to_cpu(vport_msg->rss_lut_size); + + ether_addr_copy(vport->default_mac_addr, vport_msg->default_mac_addr); + vport->max_mtu = le16_to_cpu(vport_msg->max_mtu) - IDPF_PACKET_HDR_PAD; + + /* Initialize Tx and Rx profiles for Dynamic Interrupt Moderation */ + memcpy(vport->rx_itr_profile, rx_itr, IDPF_DIM_PROFILE_SLOTS); + memcpy(vport->tx_itr_profile, tx_itr, IDPF_DIM_PROFILE_SLOTS); + + idpf_vport_init_num_qs(vport, vport_msg); + idpf_vport_calc_num_q_desc(vport); + idpf_vport_calc_num_q_groups(vport); + idpf_vport_alloc_vec_indexes(vport); + + vport->crc_enable = adapter->crc_enable; +} + +/** + * idpf_get_vec_ids - Initialize vector id from Mailbox parameters + * @adapter: adapter structure to get the mailbox vector id + * @vecids: Array of vector ids + * @num_vecids: number of vector ids + * @chunks: vector ids received over mailbox + * + * Will initialize the mailbox vector id which is received from the + * get capabilities and data queue vector ids with ids received as + * mailbox parameters. + * Returns number of ids filled + */ +int idpf_get_vec_ids(struct idpf_adapter *adapter, + u16 *vecids, int num_vecids, + struct virtchnl2_vector_chunks *chunks) +{ + u16 num_chunks = le16_to_cpu(chunks->num_vchunks); + int num_vecid_filled = 0; + int i, j; + + vecids[num_vecid_filled] = adapter->mb_vector.v_idx; + num_vecid_filled++; + + for (j = 0; j < num_chunks; j++) { + struct virtchnl2_vector_chunk *chunk; + u16 start_vecid, num_vec; + + chunk = &chunks->vchunks[j]; + num_vec = le16_to_cpu(chunk->num_vectors); + start_vecid = le16_to_cpu(chunk->start_vector_id); + + for (i = 0; i < num_vec; i++) { + if ((num_vecid_filled + i) < num_vecids) { + vecids[num_vecid_filled + i] = start_vecid; + start_vecid++; + } else { + break; + } + } + num_vecid_filled = num_vecid_filled + i; + } + + return num_vecid_filled; +} + +/** + * idpf_vport_get_queue_ids - Initialize queue id from Mailbox parameters + * @qids: Array of queue ids + * @num_qids: number of queue ids + * @q_type: queue model + * @chunks: queue ids received over mailbox + * + * Will initialize all queue ids with ids received as mailbox parameters + * Returns number of ids filled + */ +static int idpf_vport_get_queue_ids(u32 *qids, int num_qids, u16 q_type, + struct virtchnl2_queue_reg_chunks *chunks) +{ + u16 num_chunks = le16_to_cpu(chunks->num_chunks); + u32 num_q_id_filled = 0, i; + u32 start_q_id, num_q; + + while (num_chunks--) { + struct virtchnl2_queue_reg_chunk *chunk; + + chunk = &chunks->chunks[num_chunks]; + if (le32_to_cpu(chunk->type) != q_type) + continue; + + num_q = le32_to_cpu(chunk->num_queues); + start_q_id = le32_to_cpu(chunk->start_queue_id); + + for (i = 0; i < num_q; i++) { + if ((num_q_id_filled + i) < num_qids) { + qids[num_q_id_filled + i] = start_q_id; + start_q_id++; + } else { + break; + } + } + num_q_id_filled = num_q_id_filled + i; + } + + return num_q_id_filled; +} + +/** + * __idpf_vport_queue_ids_init - Initialize queue ids from Mailbox parameters + * @vport: virtual port for which the queues ids are initialized + * @qids: queue ids + * @num_qids: number of queue ids + * @q_type: type of queue + * + * Will initialize all queue ids with ids received as mailbox + * parameters. Returns number of queue ids initialized. + */ +static int __idpf_vport_queue_ids_init(struct idpf_vport *vport, + const u32 *qids, + int num_qids, + u32 q_type) +{ + struct idpf_queue *q; + int i, j, k = 0; + + switch (q_type) { + case VIRTCHNL2_QUEUE_TYPE_TX: + for (i = 0; i < vport->num_txq_grp; i++) { + struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i]; + + for (j = 0; j < tx_qgrp->num_txq && k < num_qids; j++, k++) { + tx_qgrp->txqs[j]->q_id = qids[k]; + tx_qgrp->txqs[j]->q_type = + VIRTCHNL2_QUEUE_TYPE_TX; + } + } + break; + case VIRTCHNL2_QUEUE_TYPE_RX: + for (i = 0; i < vport->num_rxq_grp; i++) { + struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i]; + u16 num_rxq; + + if (idpf_is_queue_model_split(vport->rxq_model)) + num_rxq = rx_qgrp->splitq.num_rxq_sets; + else + num_rxq = rx_qgrp->singleq.num_rxq; + + for (j = 0; j < num_rxq && k < num_qids; j++, k++) { + if (idpf_is_queue_model_split(vport->rxq_model)) + q = &rx_qgrp->splitq.rxq_sets[j]->rxq; + else + q = rx_qgrp->singleq.rxqs[j]; + q->q_id = qids[k]; + q->q_type = VIRTCHNL2_QUEUE_TYPE_RX; + } + } + break; + case VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION: + for (i = 0; i < vport->num_txq_grp && k < num_qids; i++, k++) { + struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i]; + + tx_qgrp->complq->q_id = qids[k]; + tx_qgrp->complq->q_type = + VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION; + } + break; + case VIRTCHNL2_QUEUE_TYPE_RX_BUFFER: + for (i = 0; i < vport->num_rxq_grp; i++) { + struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i]; + u8 num_bufqs = vport->num_bufqs_per_qgrp; + + for (j = 0; j < num_bufqs && k < num_qids; j++, k++) { + q = &rx_qgrp->splitq.bufq_sets[j].bufq; + q->q_id = qids[k]; + q->q_type = VIRTCHNL2_QUEUE_TYPE_RX_BUFFER; + } + } + break; + default: + break; + } + + return k; +} + +/** + * idpf_vport_queue_ids_init - Initialize queue ids from Mailbox parameters + * @vport: virtual port for which the queues ids are initialized + * + * Will initialize all queue ids with ids received as mailbox parameters. + * Returns 0 on success, negative if all the queues are not initialized. + */ +int idpf_vport_queue_ids_init(struct idpf_vport *vport) +{ + struct virtchnl2_create_vport *vport_params; + struct virtchnl2_queue_reg_chunks *chunks; + struct idpf_vport_config *vport_config; + u16 vport_idx = vport->idx; + int num_ids, err = 0; + u16 q_type; + u32 *qids; + + vport_config = vport->adapter->vport_config[vport_idx]; + if (vport_config->req_qs_chunks) { + struct virtchnl2_add_queues *vc_aq = + (struct virtchnl2_add_queues *)vport_config->req_qs_chunks; + chunks = &vc_aq->chunks; + } else { + vport_params = vport->adapter->vport_params_recvd[vport_idx]; + chunks = &vport_params->chunks; + } + + qids = kcalloc(IDPF_MAX_QIDS, sizeof(u32), GFP_KERNEL); + if (!qids) + return -ENOMEM; + + num_ids = idpf_vport_get_queue_ids(qids, IDPF_MAX_QIDS, + VIRTCHNL2_QUEUE_TYPE_TX, + chunks); + if (num_ids < vport->num_txq) { + err = -EINVAL; + goto mem_rel; + } + num_ids = __idpf_vport_queue_ids_init(vport, qids, num_ids, + VIRTCHNL2_QUEUE_TYPE_TX); + if (num_ids < vport->num_txq) { + err = -EINVAL; + goto mem_rel; + } + + num_ids = idpf_vport_get_queue_ids(qids, IDPF_MAX_QIDS, + VIRTCHNL2_QUEUE_TYPE_RX, + chunks); + if (num_ids < vport->num_rxq) { + err = -EINVAL; + goto mem_rel; + } + num_ids = __idpf_vport_queue_ids_init(vport, qids, num_ids, + VIRTCHNL2_QUEUE_TYPE_RX); + if (num_ids < vport->num_rxq) { + err = -EINVAL; + goto mem_rel; + } + + if (!idpf_is_queue_model_split(vport->txq_model)) + goto check_rxq; + + q_type = VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION; + num_ids = idpf_vport_get_queue_ids(qids, IDPF_MAX_QIDS, q_type, chunks); + if (num_ids < vport->num_complq) { + err = -EINVAL; + goto mem_rel; + } + num_ids = __idpf_vport_queue_ids_init(vport, qids, num_ids, q_type); + if (num_ids < vport->num_complq) { + err = -EINVAL; + goto mem_rel; + } + +check_rxq: + if (!idpf_is_queue_model_split(vport->rxq_model)) + goto mem_rel; + + q_type = VIRTCHNL2_QUEUE_TYPE_RX_BUFFER; + num_ids = idpf_vport_get_queue_ids(qids, IDPF_MAX_QIDS, q_type, chunks); + if (num_ids < vport->num_bufq) { + err = -EINVAL; + goto mem_rel; + } + num_ids = __idpf_vport_queue_ids_init(vport, qids, num_ids, q_type); + if (num_ids < vport->num_bufq) + err = -EINVAL; + +mem_rel: + kfree(qids); + + return err; +} + +/** + * idpf_vport_adjust_qs - Adjust to new requested queues + * @vport: virtual port data struct + * + * Renegotiate queues. Returns 0 on success, negative on failure. + */ +int idpf_vport_adjust_qs(struct idpf_vport *vport) +{ + struct virtchnl2_create_vport vport_msg; + int err; + + vport_msg.txq_model = cpu_to_le16(vport->txq_model); + vport_msg.rxq_model = cpu_to_le16(vport->rxq_model); + err = idpf_vport_calc_total_qs(vport->adapter, vport->idx, &vport_msg, + NULL); + if (err) + return err; + + idpf_vport_init_num_qs(vport, &vport_msg); + idpf_vport_calc_num_q_groups(vport); + + return 0; +} + +/** + * idpf_is_capability_ena - Default implementation of capability checking + * @adapter: Private data struct + * @all: all or one flag + * @field: caps field to check for flags + * @flag: flag to check + * + * Return true if all capabilities are supported, false otherwise + */ +bool idpf_is_capability_ena(struct idpf_adapter *adapter, bool all, + enum idpf_cap_field field, u64 flag) +{ + u8 *caps = (u8 *)&adapter->caps; + u32 *cap_field; + + if (!caps) + return false; + + if (field == IDPF_BASE_CAPS) + return false; + + cap_field = (u32 *)(caps + field); + + if (all) + return (*cap_field & flag) == flag; + else + return !!(*cap_field & flag); +} + +/** + * idpf_get_vport_id: Get vport id + * @vport: virtual port structure + * + * Return vport id from the adapter persistent data + */ +u32 idpf_get_vport_id(struct idpf_vport *vport) +{ + struct virtchnl2_create_vport *vport_msg; + + vport_msg = vport->adapter->vport_params_recvd[vport->idx]; + + return le32_to_cpu(vport_msg->vport_id); +} + +/** + * idpf_add_del_mac_filters - Add/del mac filters + * @vport: Virtual port data structure + * @np: Netdev private structure + * @add: Add or delete flag + * @async: Don't wait for return message + * + * Returns 0 on success, error on failure. + **/ +int idpf_add_del_mac_filters(struct idpf_vport *vport, + struct idpf_netdev_priv *np, + bool add, bool async) +{ + struct virtchnl2_mac_addr_list *ma_list = NULL; + struct idpf_adapter *adapter = np->adapter; + struct idpf_vport_config *vport_config; + enum idpf_vport_config_flags mac_flag; + struct pci_dev *pdev = adapter->pdev; + enum idpf_vport_vc_state vc, vc_err; + struct virtchnl2_mac_addr *mac_addr; + struct idpf_mac_filter *f, *tmp; + u32 num_msgs, total_filters = 0; + int i = 0, k, err = 0; + u32 vop; + + vport_config = adapter->vport_config[np->vport_idx]; + spin_lock_bh(&vport_config->mac_filter_list_lock); + + /* Find the number of newly added filters */ + list_for_each_entry(f, &vport_config->user_config.mac_filter_list, + list) { + if (add && f->add) + total_filters++; + else if (!add && f->remove) + total_filters++; + } + + if (!total_filters) { + spin_unlock_bh(&vport_config->mac_filter_list_lock); + + return 0; + } + + /* Fill all the new filters into virtchannel message */ + mac_addr = kcalloc(total_filters, sizeof(struct virtchnl2_mac_addr), + GFP_ATOMIC); + if (!mac_addr) { + err = -ENOMEM; + spin_unlock_bh(&vport_config->mac_filter_list_lock); + goto error; + } + + list_for_each_entry_safe(f, tmp, &vport_config->user_config.mac_filter_list, + list) { + if (add && f->add) { + ether_addr_copy(mac_addr[i].addr, f->macaddr); + i++; + f->add = false; + if (i == total_filters) + break; + } + if (!add && f->remove) { + ether_addr_copy(mac_addr[i].addr, f->macaddr); + i++; + f->remove = false; + if (i == total_filters) + break; + } + } + + spin_unlock_bh(&vport_config->mac_filter_list_lock); + + if (add) { + vop = VIRTCHNL2_OP_ADD_MAC_ADDR; + vc = IDPF_VC_ADD_MAC_ADDR; + vc_err = IDPF_VC_ADD_MAC_ADDR_ERR; + mac_flag = IDPF_VPORT_ADD_MAC_REQ; + } else { + vop = VIRTCHNL2_OP_DEL_MAC_ADDR; + vc = IDPF_VC_DEL_MAC_ADDR; + vc_err = IDPF_VC_DEL_MAC_ADDR_ERR; + mac_flag = IDPF_VPORT_DEL_MAC_REQ; + } + + /* Chunk up the filters into multiple messages to avoid + * sending a control queue message buffer that is too large + */ + num_msgs = DIV_ROUND_UP(total_filters, IDPF_NUM_FILTERS_PER_MSG); + + if (!async) + mutex_lock(&vport->vc_buf_lock); + + for (i = 0, k = 0; i < num_msgs; i++) { + u32 entries_size, buf_size, num_entries; + + num_entries = min_t(u32, total_filters, + IDPF_NUM_FILTERS_PER_MSG); + entries_size = sizeof(struct virtchnl2_mac_addr) * num_entries; + buf_size = struct_size(ma_list, mac_addr_list, num_entries); + + if (!ma_list || num_entries != IDPF_NUM_FILTERS_PER_MSG) { + kfree(ma_list); + ma_list = kzalloc(buf_size, GFP_ATOMIC); + if (!ma_list) { + err = -ENOMEM; + goto list_prep_error; + } + } else { + memset(ma_list, 0, buf_size); + } + + ma_list->vport_id = cpu_to_le32(np->vport_id); + ma_list->num_mac_addr = cpu_to_le16(num_entries); + memcpy(ma_list->mac_addr_list, &mac_addr[k], entries_size); + + if (async) + set_bit(mac_flag, vport_config->flags); + + err = idpf_send_mb_msg(adapter, vop, buf_size, (u8 *)ma_list); + if (err) + goto mbx_error; + + if (!async) { + err = idpf_wait_for_event(adapter, vport, vc, vc_err); + if (err) + goto mbx_error; + } + + k += num_entries; + total_filters -= num_entries; + } + +mbx_error: + if (!async) + mutex_unlock(&vport->vc_buf_lock); + kfree(ma_list); +list_prep_error: + kfree(mac_addr); +error: + if (err) + dev_err(&pdev->dev, "Failed to add or del mac filters %d", err); + + return err; +} + +/** + * idpf_set_promiscuous - set promiscuous and send message to mailbox + * @adapter: Driver specific private structure + * @config_data: Vport specific config data + * @vport_id: Vport identifier + * + * Request to enable promiscuous mode for the vport. Message is sent + * asynchronously and won't wait for response. Returns 0 on success, negative + * on failure; + */ +int idpf_set_promiscuous(struct idpf_adapter *adapter, + struct idpf_vport_user_config_data *config_data, + u32 vport_id) +{ + struct virtchnl2_promisc_info vpi; + u16 flags = 0; + int err; + + if (test_bit(__IDPF_PROMISC_UC, config_data->user_flags)) + flags |= VIRTCHNL2_UNICAST_PROMISC; + if (test_bit(__IDPF_PROMISC_MC, config_data->user_flags)) + flags |= VIRTCHNL2_MULTICAST_PROMISC; + + vpi.vport_id = cpu_to_le32(vport_id); + vpi.flags = cpu_to_le16(flags); + + err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_CONFIG_PROMISCUOUS_MODE, + sizeof(struct virtchnl2_promisc_info), + (u8 *)&vpi); + + return err; +} diff --git a/drivers/net/ethernet/intel/idpf/virtchnl2.h b/drivers/net/ethernet/intel/idpf/virtchnl2.h new file mode 100644 index 000000000000..07e72c72d156 --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/virtchnl2.h @@ -0,0 +1,1273 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2023 Intel Corporation */ + +#ifndef _VIRTCHNL2_H_ +#define _VIRTCHNL2_H_ + +/* All opcodes associated with virtchnl2 are prefixed with virtchnl2 or + * VIRTCHNL2. Any future opcodes, offloads/capabilities, structures, + * and defines must be prefixed with virtchnl2 or VIRTCHNL2 to avoid confusion. + * + * PF/VF uses the virtchnl2 interface defined in this header file to communicate + * with device Control Plane (CP). Driver and the CP may run on different + * platforms with different endianness. To avoid byte order discrepancies, + * all the structures in this header follow little-endian format. + * + * This is an interface definition file where existing enums and their values + * must remain unchanged over time, so we specify explicit values for all enums. + */ + +#include "virtchnl2_lan_desc.h" + +/* This macro is used to generate compilation errors if a structure + * is not exactly the correct length. + */ +#define VIRTCHNL2_CHECK_STRUCT_LEN(n, X) \ + static_assert((n) == sizeof(struct X)) + +/* New major set of opcodes introduced and so leaving room for + * old misc opcodes to be added in future. Also these opcodes may only + * be used if both the PF and VF have successfully negotiated the + * VIRTCHNL version as 2.0 during VIRTCHNL2_OP_VERSION exchange. + */ +enum virtchnl2_op { + VIRTCHNL2_OP_UNKNOWN = 0, + VIRTCHNL2_OP_VERSION = 1, + VIRTCHNL2_OP_GET_CAPS = 500, + VIRTCHNL2_OP_CREATE_VPORT = 501, + VIRTCHNL2_OP_DESTROY_VPORT = 502, + VIRTCHNL2_OP_ENABLE_VPORT = 503, + VIRTCHNL2_OP_DISABLE_VPORT = 504, + VIRTCHNL2_OP_CONFIG_TX_QUEUES = 505, + VIRTCHNL2_OP_CONFIG_RX_QUEUES = 506, + VIRTCHNL2_OP_ENABLE_QUEUES = 507, + VIRTCHNL2_OP_DISABLE_QUEUES = 508, + VIRTCHNL2_OP_ADD_QUEUES = 509, + VIRTCHNL2_OP_DEL_QUEUES = 510, + VIRTCHNL2_OP_MAP_QUEUE_VECTOR = 511, + VIRTCHNL2_OP_UNMAP_QUEUE_VECTOR = 512, + VIRTCHNL2_OP_GET_RSS_KEY = 513, + VIRTCHNL2_OP_SET_RSS_KEY = 514, + VIRTCHNL2_OP_GET_RSS_LUT = 515, + VIRTCHNL2_OP_SET_RSS_LUT = 516, + VIRTCHNL2_OP_GET_RSS_HASH = 517, + VIRTCHNL2_OP_SET_RSS_HASH = 518, + VIRTCHNL2_OP_SET_SRIOV_VFS = 519, + VIRTCHNL2_OP_ALLOC_VECTORS = 520, + VIRTCHNL2_OP_DEALLOC_VECTORS = 521, + VIRTCHNL2_OP_EVENT = 522, + VIRTCHNL2_OP_GET_STATS = 523, + VIRTCHNL2_OP_RESET_VF = 524, + VIRTCHNL2_OP_GET_EDT_CAPS = 525, + VIRTCHNL2_OP_GET_PTYPE_INFO = 526, + /* Opcode 527 and 528 are reserved for VIRTCHNL2_OP_GET_PTYPE_ID and + * VIRTCHNL2_OP_GET_PTYPE_INFO_RAW. + * Opcodes 529, 530, 531, 532 and 533 are reserved. + */ + VIRTCHNL2_OP_LOOPBACK = 534, + VIRTCHNL2_OP_ADD_MAC_ADDR = 535, + VIRTCHNL2_OP_DEL_MAC_ADDR = 536, + VIRTCHNL2_OP_CONFIG_PROMISCUOUS_MODE = 537, +}; + +/** + * enum virtchnl2_vport_type - Type of virtual port. + * @VIRTCHNL2_VPORT_TYPE_DEFAULT: Default virtual port type. + */ +enum virtchnl2_vport_type { + VIRTCHNL2_VPORT_TYPE_DEFAULT = 0, +}; + +/** + * enum virtchnl2_queue_model - Type of queue model. + * @VIRTCHNL2_QUEUE_MODEL_SINGLE: Single queue model. + * @VIRTCHNL2_QUEUE_MODEL_SPLIT: Split queue model. + * + * In the single queue model, the same transmit descriptor queue is used by + * software to post descriptors to hardware and by hardware to post completed + * descriptors to software. + * Likewise, the same receive descriptor queue is used by hardware to post + * completions to software and by software to post buffers to hardware. + * + * In the split queue model, hardware uses transmit completion queues to post + * descriptor/buffer completions to software, while software uses transmit + * descriptor queues to post descriptors to hardware. + * Likewise, hardware posts descriptor completions to the receive descriptor + * queue, while software uses receive buffer queues to post buffers to hardware. + */ +enum virtchnl2_queue_model { + VIRTCHNL2_QUEUE_MODEL_SINGLE = 0, + VIRTCHNL2_QUEUE_MODEL_SPLIT = 1, +}; + +/* Checksum offload capability flags */ +enum virtchnl2_cap_txrx_csum { + VIRTCHNL2_CAP_TX_CSUM_L3_IPV4 = BIT(0), + VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_TCP = BIT(1), + VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_UDP = BIT(2), + VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_SCTP = BIT(3), + VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_TCP = BIT(4), + VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_UDP = BIT(5), + VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_SCTP = BIT(6), + VIRTCHNL2_CAP_TX_CSUM_GENERIC = BIT(7), + VIRTCHNL2_CAP_RX_CSUM_L3_IPV4 = BIT(8), + VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_TCP = BIT(9), + VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_UDP = BIT(10), + VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_SCTP = BIT(11), + VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_TCP = BIT(12), + VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_UDP = BIT(13), + VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_SCTP = BIT(14), + VIRTCHNL2_CAP_RX_CSUM_GENERIC = BIT(15), + VIRTCHNL2_CAP_TX_CSUM_L3_SINGLE_TUNNEL = BIT(16), + VIRTCHNL2_CAP_TX_CSUM_L3_DOUBLE_TUNNEL = BIT(17), + VIRTCHNL2_CAP_RX_CSUM_L3_SINGLE_TUNNEL = BIT(18), + VIRTCHNL2_CAP_RX_CSUM_L3_DOUBLE_TUNNEL = BIT(19), + VIRTCHNL2_CAP_TX_CSUM_L4_SINGLE_TUNNEL = BIT(20), + VIRTCHNL2_CAP_TX_CSUM_L4_DOUBLE_TUNNEL = BIT(21), + VIRTCHNL2_CAP_RX_CSUM_L4_SINGLE_TUNNEL = BIT(22), + VIRTCHNL2_CAP_RX_CSUM_L4_DOUBLE_TUNNEL = BIT(23), +}; + +/* Segmentation offload capability flags */ +enum virtchnl2_cap_seg { + VIRTCHNL2_CAP_SEG_IPV4_TCP = BIT(0), + VIRTCHNL2_CAP_SEG_IPV4_UDP = BIT(1), + VIRTCHNL2_CAP_SEG_IPV4_SCTP = BIT(2), + VIRTCHNL2_CAP_SEG_IPV6_TCP = BIT(3), + VIRTCHNL2_CAP_SEG_IPV6_UDP = BIT(4), + VIRTCHNL2_CAP_SEG_IPV6_SCTP = BIT(5), + VIRTCHNL2_CAP_SEG_GENERIC = BIT(6), + VIRTCHNL2_CAP_SEG_TX_SINGLE_TUNNEL = BIT(7), + VIRTCHNL2_CAP_SEG_TX_DOUBLE_TUNNEL = BIT(8), +}; + +/* Receive Side Scaling Flow type capability flags */ +enum virtchnl2_cap_rss { + VIRTCHNL2_CAP_RSS_IPV4_TCP = BIT(0), + VIRTCHNL2_CAP_RSS_IPV4_UDP = BIT(1), + VIRTCHNL2_CAP_RSS_IPV4_SCTP = BIT(2), + VIRTCHNL2_CAP_RSS_IPV4_OTHER = BIT(3), + VIRTCHNL2_CAP_RSS_IPV6_TCP = BIT(4), + VIRTCHNL2_CAP_RSS_IPV6_UDP = BIT(5), + VIRTCHNL2_CAP_RSS_IPV6_SCTP = BIT(6), + VIRTCHNL2_CAP_RSS_IPV6_OTHER = BIT(7), + VIRTCHNL2_CAP_RSS_IPV4_AH = BIT(8), + VIRTCHNL2_CAP_RSS_IPV4_ESP = BIT(9), + VIRTCHNL2_CAP_RSS_IPV4_AH_ESP = BIT(10), + VIRTCHNL2_CAP_RSS_IPV6_AH = BIT(11), + VIRTCHNL2_CAP_RSS_IPV6_ESP = BIT(12), + VIRTCHNL2_CAP_RSS_IPV6_AH_ESP = BIT(13), +}; + +/* Header split capability flags */ +enum virtchnl2_cap_rx_hsplit_at { + /* for prepended metadata */ + VIRTCHNL2_CAP_RX_HSPLIT_AT_L2 = BIT(0), + /* all VLANs go into header buffer */ + VIRTCHNL2_CAP_RX_HSPLIT_AT_L3 = BIT(1), + VIRTCHNL2_CAP_RX_HSPLIT_AT_L4V4 = BIT(2), + VIRTCHNL2_CAP_RX_HSPLIT_AT_L4V6 = BIT(3), +}; + +/* Receive Side Coalescing offload capability flags */ +enum virtchnl2_cap_rsc { + VIRTCHNL2_CAP_RSC_IPV4_TCP = BIT(0), + VIRTCHNL2_CAP_RSC_IPV4_SCTP = BIT(1), + VIRTCHNL2_CAP_RSC_IPV6_TCP = BIT(2), + VIRTCHNL2_CAP_RSC_IPV6_SCTP = BIT(3), +}; + +/* Other capability flags */ +enum virtchnl2_cap_other { + VIRTCHNL2_CAP_RDMA = BIT_ULL(0), + VIRTCHNL2_CAP_SRIOV = BIT_ULL(1), + VIRTCHNL2_CAP_MACFILTER = BIT_ULL(2), + VIRTCHNL2_CAP_FLOW_DIRECTOR = BIT_ULL(3), + /* Queue based scheduling using split queue model */ + VIRTCHNL2_CAP_SPLITQ_QSCHED = BIT_ULL(4), + VIRTCHNL2_CAP_CRC = BIT_ULL(5), + VIRTCHNL2_CAP_ADQ = BIT_ULL(6), + VIRTCHNL2_CAP_WB_ON_ITR = BIT_ULL(7), + VIRTCHNL2_CAP_PROMISC = BIT_ULL(8), + VIRTCHNL2_CAP_LINK_SPEED = BIT_ULL(9), + VIRTCHNL2_CAP_INLINE_IPSEC = BIT_ULL(10), + VIRTCHNL2_CAP_LARGE_NUM_QUEUES = BIT_ULL(11), + VIRTCHNL2_CAP_VLAN = BIT_ULL(12), + VIRTCHNL2_CAP_PTP = BIT_ULL(13), + /* EDT: Earliest Departure Time capability used for Timing Wheel */ + VIRTCHNL2_CAP_EDT = BIT_ULL(14), + VIRTCHNL2_CAP_ADV_RSS = BIT_ULL(15), + VIRTCHNL2_CAP_FDIR = BIT_ULL(16), + VIRTCHNL2_CAP_RX_FLEX_DESC = BIT_ULL(17), + VIRTCHNL2_CAP_PTYPE = BIT_ULL(18), + VIRTCHNL2_CAP_LOOPBACK = BIT_ULL(19), + /* Other capability 20 is reserved */ + + /* this must be the last capability */ + VIRTCHNL2_CAP_OEM = BIT_ULL(63), +}; + +/* underlying device type */ +enum virtchl2_device_type { + VIRTCHNL2_MEV_DEVICE = 0, +}; + +/** + * enum virtchnl2_txq_sched_mode - Transmit Queue Scheduling Modes. + * @VIRTCHNL2_TXQ_SCHED_MODE_QUEUE: Queue mode is the legacy mode i.e. inorder + * completions where descriptors and buffers + * are completed at the same time. + * @VIRTCHNL2_TXQ_SCHED_MODE_FLOW: Flow scheduling mode allows for out of order + * packet processing where descriptors are + * cleaned in order, but buffers can be + * completed out of order. + */ +enum virtchnl2_txq_sched_mode { + VIRTCHNL2_TXQ_SCHED_MODE_QUEUE = 0, + VIRTCHNL2_TXQ_SCHED_MODE_FLOW = 1, +}; + +/** + * enum virtchnl2_rxq_flags - Receive Queue Feature flags. + * @VIRTCHNL2_RXQ_RSC: Rx queue RSC flag. + * @VIRTCHNL2_RXQ_HDR_SPLIT: Rx queue header split flag. + * @VIRTCHNL2_RXQ_IMMEDIATE_WRITE_BACK: When set, packet descriptors are flushed + * by hardware immediately after processing + * each packet. + * @VIRTCHNL2_RX_DESC_SIZE_16BYTE: Rx queue 16 byte descriptor size. + * @VIRTCHNL2_RX_DESC_SIZE_32BYTE: Rx queue 32 byte descriptor size. + */ +enum virtchnl2_rxq_flags { + VIRTCHNL2_RXQ_RSC = BIT(0), + VIRTCHNL2_RXQ_HDR_SPLIT = BIT(1), + VIRTCHNL2_RXQ_IMMEDIATE_WRITE_BACK = BIT(2), + VIRTCHNL2_RX_DESC_SIZE_16BYTE = BIT(3), + VIRTCHNL2_RX_DESC_SIZE_32BYTE = BIT(4), +}; + +/* Type of RSS algorithm */ +enum virtchnl2_rss_alg { + VIRTCHNL2_RSS_ALG_TOEPLITZ_ASYMMETRIC = 0, + VIRTCHNL2_RSS_ALG_R_ASYMMETRIC = 1, + VIRTCHNL2_RSS_ALG_TOEPLITZ_SYMMETRIC = 2, + VIRTCHNL2_RSS_ALG_XOR_SYMMETRIC = 3, +}; + +/* Type of event */ +enum virtchnl2_event_codes { + VIRTCHNL2_EVENT_UNKNOWN = 0, + VIRTCHNL2_EVENT_LINK_CHANGE = 1, + /* Event type 2, 3 are reserved */ +}; + +/* Transmit and Receive queue types are valid in legacy as well as split queue + * models. With Split Queue model, 2 additional types are introduced - + * TX_COMPLETION and RX_BUFFER. In split queue model, receive corresponds to + * the queue where hardware posts completions. + */ +enum virtchnl2_queue_type { + VIRTCHNL2_QUEUE_TYPE_TX = 0, + VIRTCHNL2_QUEUE_TYPE_RX = 1, + VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION = 2, + VIRTCHNL2_QUEUE_TYPE_RX_BUFFER = 3, + VIRTCHNL2_QUEUE_TYPE_CONFIG_TX = 4, + VIRTCHNL2_QUEUE_TYPE_CONFIG_RX = 5, + /* Queue types 6, 7, 8, 9 are reserved */ + VIRTCHNL2_QUEUE_TYPE_MBX_TX = 10, + VIRTCHNL2_QUEUE_TYPE_MBX_RX = 11, +}; + +/* Interrupt throttling rate index */ +enum virtchnl2_itr_idx { + VIRTCHNL2_ITR_IDX_0 = 0, + VIRTCHNL2_ITR_IDX_1 = 1, +}; + +/** + * enum virtchnl2_mac_addr_type - MAC address types. + * @VIRTCHNL2_MAC_ADDR_PRIMARY: PF/VF driver should set this type for the + * primary/device unicast MAC address filter for + * VIRTCHNL2_OP_ADD_MAC_ADDR and + * VIRTCHNL2_OP_DEL_MAC_ADDR. This allows for the + * underlying control plane function to accurately + * track the MAC address and for VM/function reset. + * + * @VIRTCHNL2_MAC_ADDR_EXTRA: PF/VF driver should set this type for any extra + * unicast and/or multicast filters that are being + * added/deleted via VIRTCHNL2_OP_ADD_MAC_ADDR or + * VIRTCHNL2_OP_DEL_MAC_ADDR. + */ +enum virtchnl2_mac_addr_type { + VIRTCHNL2_MAC_ADDR_PRIMARY = 1, + VIRTCHNL2_MAC_ADDR_EXTRA = 2, +}; + +/* Flags used for promiscuous mode */ +enum virtchnl2_promisc_flags { + VIRTCHNL2_UNICAST_PROMISC = BIT(0), + VIRTCHNL2_MULTICAST_PROMISC = BIT(1), +}; + +/* Protocol header type within a packet segment. A segment consists of one or + * more protocol headers that make up a logical group of protocol headers. Each + * logical group of protocol headers encapsulates or is encapsulated using/by + * tunneling or encapsulation protocols for network virtualization. + */ +enum virtchnl2_proto_hdr_type { + /* VIRTCHNL2_PROTO_HDR_ANY is a mandatory protocol id */ + VIRTCHNL2_PROTO_HDR_ANY = 0, + VIRTCHNL2_PROTO_HDR_PRE_MAC = 1, + /* VIRTCHNL2_PROTO_HDR_MAC is a mandatory protocol id */ + VIRTCHNL2_PROTO_HDR_MAC = 2, + VIRTCHNL2_PROTO_HDR_POST_MAC = 3, + VIRTCHNL2_PROTO_HDR_ETHERTYPE = 4, + VIRTCHNL2_PROTO_HDR_VLAN = 5, + VIRTCHNL2_PROTO_HDR_SVLAN = 6, + VIRTCHNL2_PROTO_HDR_CVLAN = 7, + VIRTCHNL2_PROTO_HDR_MPLS = 8, + VIRTCHNL2_PROTO_HDR_UMPLS = 9, + VIRTCHNL2_PROTO_HDR_MMPLS = 10, + VIRTCHNL2_PROTO_HDR_PTP = 11, + VIRTCHNL2_PROTO_HDR_CTRL = 12, + VIRTCHNL2_PROTO_HDR_LLDP = 13, + VIRTCHNL2_PROTO_HDR_ARP = 14, + VIRTCHNL2_PROTO_HDR_ECP = 15, + VIRTCHNL2_PROTO_HDR_EAPOL = 16, + VIRTCHNL2_PROTO_HDR_PPPOD = 17, + VIRTCHNL2_PROTO_HDR_PPPOE = 18, + /* VIRTCHNL2_PROTO_HDR_IPV4 is a mandatory protocol id */ + VIRTCHNL2_PROTO_HDR_IPV4 = 19, + /* IPv4 and IPv6 Fragment header types are only associated to + * VIRTCHNL2_PROTO_HDR_IPV4 and VIRTCHNL2_PROTO_HDR_IPV6 respectively, + * cannot be used independently. + */ + /* VIRTCHNL2_PROTO_HDR_IPV4_FRAG is a mandatory protocol id */ + VIRTCHNL2_PROTO_HDR_IPV4_FRAG = 20, + /* VIRTCHNL2_PROTO_HDR_IPV6 is a mandatory protocol id */ + VIRTCHNL2_PROTO_HDR_IPV6 = 21, + /* VIRTCHNL2_PROTO_HDR_IPV6_FRAG is a mandatory protocol id */ + VIRTCHNL2_PROTO_HDR_IPV6_FRAG = 22, + VIRTCHNL2_PROTO_HDR_IPV6_EH = 23, + /* VIRTCHNL2_PROTO_HDR_UDP is a mandatory protocol id */ + VIRTCHNL2_PROTO_HDR_UDP = 24, + /* VIRTCHNL2_PROTO_HDR_TCP is a mandatory protocol id */ + VIRTCHNL2_PROTO_HDR_TCP = 25, + /* VIRTCHNL2_PROTO_HDR_SCTP is a mandatory protocol id */ + VIRTCHNL2_PROTO_HDR_SCTP = 26, + /* VIRTCHNL2_PROTO_HDR_ICMP is a mandatory protocol id */ + VIRTCHNL2_PROTO_HDR_ICMP = 27, + /* VIRTCHNL2_PROTO_HDR_ICMPV6 is a mandatory protocol id */ + VIRTCHNL2_PROTO_HDR_ICMPV6 = 28, + VIRTCHNL2_PROTO_HDR_IGMP = 29, + VIRTCHNL2_PROTO_HDR_AH = 30, + VIRTCHNL2_PROTO_HDR_ESP = 31, + VIRTCHNL2_PROTO_HDR_IKE = 32, + VIRTCHNL2_PROTO_HDR_NATT_KEEP = 33, + /* VIRTCHNL2_PROTO_HDR_PAY is a mandatory protocol id */ + VIRTCHNL2_PROTO_HDR_PAY = 34, + VIRTCHNL2_PROTO_HDR_L2TPV2 = 35, + VIRTCHNL2_PROTO_HDR_L2TPV2_CONTROL = 36, + VIRTCHNL2_PROTO_HDR_L2TPV3 = 37, + VIRTCHNL2_PROTO_HDR_GTP = 38, + VIRTCHNL2_PROTO_HDR_GTP_EH = 39, + VIRTCHNL2_PROTO_HDR_GTPCV2 = 40, + VIRTCHNL2_PROTO_HDR_GTPC_TEID = 41, + VIRTCHNL2_PROTO_HDR_GTPU = 42, + VIRTCHNL2_PROTO_HDR_GTPU_UL = 43, + VIRTCHNL2_PROTO_HDR_GTPU_DL = 44, + VIRTCHNL2_PROTO_HDR_ECPRI = 45, + VIRTCHNL2_PROTO_HDR_VRRP = 46, + VIRTCHNL2_PROTO_HDR_OSPF = 47, + /* VIRTCHNL2_PROTO_HDR_TUN is a mandatory protocol id */ + VIRTCHNL2_PROTO_HDR_TUN = 48, + VIRTCHNL2_PROTO_HDR_GRE = 49, + VIRTCHNL2_PROTO_HDR_NVGRE = 50, + VIRTCHNL2_PROTO_HDR_VXLAN = 51, + VIRTCHNL2_PROTO_HDR_VXLAN_GPE = 52, + VIRTCHNL2_PROTO_HDR_GENEVE = 53, + VIRTCHNL2_PROTO_HDR_NSH = 54, + VIRTCHNL2_PROTO_HDR_QUIC = 55, + VIRTCHNL2_PROTO_HDR_PFCP = 56, + VIRTCHNL2_PROTO_HDR_PFCP_NODE = 57, + VIRTCHNL2_PROTO_HDR_PFCP_SESSION = 58, + VIRTCHNL2_PROTO_HDR_RTP = 59, + VIRTCHNL2_PROTO_HDR_ROCE = 60, + VIRTCHNL2_PROTO_HDR_ROCEV1 = 61, + VIRTCHNL2_PROTO_HDR_ROCEV2 = 62, + /* Protocol ids up to 32767 are reserved. + * 32768 - 65534 are used for user defined protocol ids. + * VIRTCHNL2_PROTO_HDR_NO_PROTO is a mandatory protocol id. + */ + VIRTCHNL2_PROTO_HDR_NO_PROTO = 65535, +}; + +enum virtchl2_version { + VIRTCHNL2_VERSION_MINOR_0 = 0, + VIRTCHNL2_VERSION_MAJOR_2 = 2, +}; + +/** + * struct virtchnl2_edt_caps - Get EDT granularity and time horizon. + * @tstamp_granularity_ns: Timestamp granularity in nanoseconds. + * @time_horizon_ns: Total time window in nanoseconds. + * + * Associated with VIRTCHNL2_OP_GET_EDT_CAPS. + */ +struct virtchnl2_edt_caps { + __le64 tstamp_granularity_ns; + __le64 time_horizon_ns; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_edt_caps); + +/** + * struct virtchnl2_version_info - Version information. + * @major: Major version. + * @minor: Minor version. + * + * PF/VF posts its version number to the CP. CP responds with its version number + * in the same format, along with a return code. + * If there is a major version mismatch, then the PF/VF cannot operate. + * If there is a minor version mismatch, then the PF/VF can operate but should + * add a warning to the system log. + * + * This version opcode MUST always be specified as == 1, regardless of other + * changes in the API. The CP must always respond to this message without + * error regardless of version mismatch. + * + * Associated with VIRTCHNL2_OP_VERSION. + */ +struct virtchnl2_version_info { + __le32 major; + __le32 minor; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_version_info); + +/** + * struct virtchnl2_get_capabilities - Capabilities info. + * @csum_caps: See enum virtchnl2_cap_txrx_csum. + * @seg_caps: See enum virtchnl2_cap_seg. + * @hsplit_caps: See enum virtchnl2_cap_rx_hsplit_at. + * @rsc_caps: See enum virtchnl2_cap_rsc. + * @rss_caps: See enum virtchnl2_cap_rss. + * @other_caps: See enum virtchnl2_cap_other. + * @mailbox_dyn_ctl: DYN_CTL register offset and vector id for mailbox + * provided by CP. + * @mailbox_vector_id: Mailbox vector id. + * @num_allocated_vectors: Maximum number of allocated vectors for the device. + * @max_rx_q: Maximum number of supported Rx queues. + * @max_tx_q: Maximum number of supported Tx queues. + * @max_rx_bufq: Maximum number of supported buffer queues. + * @max_tx_complq: Maximum number of supported completion queues. + * @max_sriov_vfs: The PF sends the maximum VFs it is requesting. The CP + * responds with the maximum VFs granted. + * @max_vports: Maximum number of vports that can be supported. + * @default_num_vports: Default number of vports driver should allocate on load. + * @max_tx_hdr_size: Max header length hardware can parse/checksum, in bytes. + * @max_sg_bufs_per_tx_pkt: Max number of scatter gather buffers that can be + * sent per transmit packet without needing to be + * linearized. + * @pad: Padding. + * @reserved: Reserved. + * @device_type: See enum virtchl2_device_type. + * @min_sso_packet_len: Min packet length supported by device for single + * segment offload. + * @max_hdr_buf_per_lso: Max number of header buffers that can be used for + * an LSO. + * @pad1: Padding for future extensions. + * + * Dataplane driver sends this message to CP to negotiate capabilities and + * provides a virtchnl2_get_capabilities structure with its desired + * capabilities, max_sriov_vfs and num_allocated_vectors. + * CP responds with a virtchnl2_get_capabilities structure updated + * with allowed capabilities and the other fields as below. + * If PF sets max_sriov_vfs as 0, CP will respond with max number of VFs + * that can be created by this PF. For any other value 'n', CP responds + * with max_sriov_vfs set to min(n, x) where x is the max number of VFs + * allowed by CP's policy. max_sriov_vfs is not applicable for VFs. + * If dataplane driver sets num_allocated_vectors as 0, CP will respond with 1 + * which is default vector associated with the default mailbox. For any other + * value 'n', CP responds with a value <= n based on the CP's policy of + * max number of vectors for a PF. + * CP will respond with the vector ID of mailbox allocated to the PF in + * mailbox_vector_id and the number of itr index registers in itr_idx_map. + * It also responds with default number of vports that the dataplane driver + * should comeup with in default_num_vports and maximum number of vports that + * can be supported in max_vports. + * + * Associated with VIRTCHNL2_OP_GET_CAPS. + */ +struct virtchnl2_get_capabilities { + __le32 csum_caps; + __le32 seg_caps; + __le32 hsplit_caps; + __le32 rsc_caps; + __le64 rss_caps; + __le64 other_caps; + __le32 mailbox_dyn_ctl; + __le16 mailbox_vector_id; + __le16 num_allocated_vectors; + __le16 max_rx_q; + __le16 max_tx_q; + __le16 max_rx_bufq; + __le16 max_tx_complq; + __le16 max_sriov_vfs; + __le16 max_vports; + __le16 default_num_vports; + __le16 max_tx_hdr_size; + u8 max_sg_bufs_per_tx_pkt; + u8 pad[3]; + u8 reserved[4]; + __le32 device_type; + u8 min_sso_packet_len; + u8 max_hdr_buf_per_lso; + u8 pad1[10]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(80, virtchnl2_get_capabilities); + +/** + * struct virtchnl2_queue_reg_chunk - Single queue chunk. + * @type: See enum virtchnl2_queue_type. + * @start_queue_id: Start Queue ID. + * @num_queues: Number of queues in the chunk. + * @pad: Padding. + * @qtail_reg_start: Queue tail register offset. + * @qtail_reg_spacing: Queue tail register spacing. + * @pad1: Padding for future extensions. + */ +struct virtchnl2_queue_reg_chunk { + __le32 type; + __le32 start_queue_id; + __le32 num_queues; + __le32 pad; + __le64 qtail_reg_start; + __le32 qtail_reg_spacing; + u8 pad1[4]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(32, virtchnl2_queue_reg_chunk); + +/** + * struct virtchnl2_queue_reg_chunks - Specify several chunks of contiguous + * queues. + * @num_chunks: Number of chunks. + * @pad: Padding. + * @chunks: Chunks of queue info. + */ +struct virtchnl2_queue_reg_chunks { + __le16 num_chunks; + u8 pad[6]; + struct virtchnl2_queue_reg_chunk chunks[]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_queue_reg_chunks); + +/** + * struct virtchnl2_create_vport - Create vport config info. + * @vport_type: See enum virtchnl2_vport_type. + * @txq_model: See virtchnl2_queue_model. + * @rxq_model: See virtchnl2_queue_model. + * @num_tx_q: Number of Tx queues. + * @num_tx_complq: Valid only if txq_model is split queue. + * @num_rx_q: Number of Rx queues. + * @num_rx_bufq: Valid only if rxq_model is split queue. + * @default_rx_q: Relative receive queue index to be used as default. + * @vport_index: Used to align PF and CP in case of default multiple vports, + * it is filled by the PF and CP returns the same value, to + * enable the driver to support multiple asynchronous parallel + * CREATE_VPORT requests and associate a response to a specific + * request. + * @max_mtu: Max MTU. CP populates this field on response. + * @vport_id: Vport id. CP populates this field on response. + * @default_mac_addr: Default MAC address. + * @pad: Padding. + * @rx_desc_ids: See VIRTCHNL2_RX_DESC_IDS definitions. + * @tx_desc_ids: See VIRTCHNL2_TX_DESC_IDS definitions. + * @pad1: Padding. + * @rss_algorithm: RSS algorithm. + * @rss_key_size: RSS key size. + * @rss_lut_size: RSS LUT size. + * @rx_split_pos: See enum virtchnl2_cap_rx_hsplit_at. + * @pad2: Padding. + * @chunks: Chunks of contiguous queues. + * + * PF sends this message to CP to create a vport by filling in required + * fields of virtchnl2_create_vport structure. + * CP responds with the updated virtchnl2_create_vport structure containing the + * necessary fields followed by chunks which in turn will have an array of + * num_chunks entries of virtchnl2_queue_chunk structures. + * + * Associated with VIRTCHNL2_OP_CREATE_VPORT. + */ +struct virtchnl2_create_vport { + __le16 vport_type; + __le16 txq_model; + __le16 rxq_model; + __le16 num_tx_q; + __le16 num_tx_complq; + __le16 num_rx_q; + __le16 num_rx_bufq; + __le16 default_rx_q; + __le16 vport_index; + /* CP populates the following fields on response */ + __le16 max_mtu; + __le32 vport_id; + u8 default_mac_addr[ETH_ALEN]; + __le16 pad; + __le64 rx_desc_ids; + __le64 tx_desc_ids; + u8 pad1[72]; + __le32 rss_algorithm; + __le16 rss_key_size; + __le16 rss_lut_size; + __le32 rx_split_pos; + u8 pad2[20]; + struct virtchnl2_queue_reg_chunks chunks; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(160, virtchnl2_create_vport); + +/** + * struct virtchnl2_vport - Vport ID info. + * @vport_id: Vport id. + * @pad: Padding for future extensions. + * + * PF sends this message to CP to destroy, enable or disable a vport by filling + * in the vport_id in virtchnl2_vport structure. + * CP responds with the status of the requested operation. + * + * Associated with VIRTCHNL2_OP_DESTROY_VPORT, VIRTCHNL2_OP_ENABLE_VPORT, + * VIRTCHNL2_OP_DISABLE_VPORT. + */ +struct virtchnl2_vport { + __le32 vport_id; + u8 pad[4]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_vport); + +/** + * struct virtchnl2_txq_info - Transmit queue config info + * @dma_ring_addr: DMA address. + * @type: See enum virtchnl2_queue_type. + * @queue_id: Queue ID. + * @relative_queue_id: Valid only if queue model is split and type is transmit + * queue. Used in many to one mapping of transmit queues to + * completion queue. + * @model: See enum virtchnl2_queue_model. + * @sched_mode: See enum virtchnl2_txq_sched_mode. + * @qflags: TX queue feature flags. + * @ring_len: Ring length. + * @tx_compl_queue_id: Valid only if queue model is split and type is transmit + * queue. + * @peer_type: Valid only if queue type is VIRTCHNL2_QUEUE_TYPE_MAILBOX_TX + * @peer_rx_queue_id: Valid only if queue type is CONFIG_TX and used to deliver + * messages for the respective CONFIG_TX queue. + * @pad: Padding. + * @egress_pasid: Egress PASID info. + * @egress_hdr_pasid: Egress HDR passid. + * @egress_buf_pasid: Egress buf passid. + * @pad1: Padding for future extensions. + */ +struct virtchnl2_txq_info { + __le64 dma_ring_addr; + __le32 type; + __le32 queue_id; + __le16 relative_queue_id; + __le16 model; + __le16 sched_mode; + __le16 qflags; + __le16 ring_len; + __le16 tx_compl_queue_id; + __le16 peer_type; + __le16 peer_rx_queue_id; + u8 pad[4]; + __le32 egress_pasid; + __le32 egress_hdr_pasid; + __le32 egress_buf_pasid; + u8 pad1[8]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(56, virtchnl2_txq_info); + +/** + * struct virtchnl2_config_tx_queues - TX queue config. + * @vport_id: Vport id. + * @num_qinfo: Number of virtchnl2_txq_info structs. + * @pad: Padding. + * @qinfo: Tx queues config info. + * + * PF sends this message to set up parameters for one or more transmit queues. + * This message contains an array of num_qinfo instances of virtchnl2_txq_info + * structures. CP configures requested queues and returns a status code. If + * num_qinfo specified is greater than the number of queues associated with the + * vport, an error is returned and no queues are configured. + * + * Associated with VIRTCHNL2_OP_CONFIG_TX_QUEUES. + */ +struct virtchnl2_config_tx_queues { + __le32 vport_id; + __le16 num_qinfo; + u8 pad[10]; + struct virtchnl2_txq_info qinfo[]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_config_tx_queues); + +/** + * struct virtchnl2_rxq_info - Receive queue config info. + * @desc_ids: See VIRTCHNL2_RX_DESC_IDS definitions. + * @dma_ring_addr: See VIRTCHNL2_RX_DESC_IDS definitions. + * @type: See enum virtchnl2_queue_type. + * @queue_id: Queue id. + * @model: See enum virtchnl2_queue_model. + * @hdr_buffer_size: Header buffer size. + * @data_buffer_size: Data buffer size. + * @max_pkt_size: Max packet size. + * @ring_len: Ring length. + * @buffer_notif_stride: Buffer notification stride in units of 32-descriptors. + * This field must be a power of 2. + * @pad: Padding. + * @dma_head_wb_addr: Applicable only for receive buffer queues. + * @qflags: Applicable only for receive completion queues. + * See enum virtchnl2_rxq_flags. + * @rx_buffer_low_watermark: Rx buffer low watermark. + * @rx_bufq1_id: Buffer queue index of the first buffer queue associated with + * the Rx queue. Valid only in split queue model. + * @rx_bufq2_id: Buffer queue index of the second buffer queue associated with + * the Rx queue. Valid only in split queue model. + * @bufq2_ena: It indicates if there is a second buffer, rx_bufq2_id is valid + * only if this field is set. + * @pad1: Padding. + * @ingress_pasid: Ingress PASID. + * @ingress_hdr_pasid: Ingress PASID header. + * @ingress_buf_pasid: Ingress PASID buffer. + * @pad2: Padding for future extensions. + */ +struct virtchnl2_rxq_info { + __le64 desc_ids; + __le64 dma_ring_addr; + __le32 type; + __le32 queue_id; + __le16 model; + __le16 hdr_buffer_size; + __le32 data_buffer_size; + __le32 max_pkt_size; + __le16 ring_len; + u8 buffer_notif_stride; + u8 pad; + __le64 dma_head_wb_addr; + __le16 qflags; + __le16 rx_buffer_low_watermark; + __le16 rx_bufq1_id; + __le16 rx_bufq2_id; + u8 bufq2_ena; + u8 pad1[3]; + __le32 ingress_pasid; + __le32 ingress_hdr_pasid; + __le32 ingress_buf_pasid; + u8 pad2[16]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(88, virtchnl2_rxq_info); + +/** + * struct virtchnl2_config_rx_queues - Rx queues config. + * @vport_id: Vport id. + * @num_qinfo: Number of instances. + * @pad: Padding. + * @qinfo: Rx queues config info. + * + * PF sends this message to set up parameters for one or more receive queues. + * This message contains an array of num_qinfo instances of virtchnl2_rxq_info + * structures. CP configures requested queues and returns a status code. + * If the number of queues specified is greater than the number of queues + * associated with the vport, an error is returned and no queues are configured. + * + * Associated with VIRTCHNL2_OP_CONFIG_RX_QUEUES. + */ +struct virtchnl2_config_rx_queues { + __le32 vport_id; + __le16 num_qinfo; + u8 pad[18]; + struct virtchnl2_rxq_info qinfo[]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(24, virtchnl2_config_rx_queues); + +/** + * struct virtchnl2_add_queues - data for VIRTCHNL2_OP_ADD_QUEUES. + * @vport_id: Vport id. + * @num_tx_q: Number of Tx qieues. + * @num_tx_complq: Number of Tx completion queues. + * @num_rx_q: Number of Rx queues. + * @num_rx_bufq: Number of Rx buffer queues. + * @pad: Padding. + * @chunks: Chunks of contiguous queues. + * + * PF sends this message to request additional transmit/receive queues beyond + * the ones that were assigned via CREATE_VPORT request. virtchnl2_add_queues + * structure is used to specify the number of each type of queues. + * CP responds with the same structure with the actual number of queues assigned + * followed by num_chunks of virtchnl2_queue_chunk structures. + * + * Associated with VIRTCHNL2_OP_ADD_QUEUES. + */ +struct virtchnl2_add_queues { + __le32 vport_id; + __le16 num_tx_q; + __le16 num_tx_complq; + __le16 num_rx_q; + __le16 num_rx_bufq; + u8 pad[4]; + struct virtchnl2_queue_reg_chunks chunks; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(24, virtchnl2_add_queues); + +/** + * struct virtchnl2_vector_chunk - Structure to specify a chunk of contiguous + * interrupt vectors. + * @start_vector_id: Start vector id. + * @start_evv_id: Start EVV id. + * @num_vectors: Number of vectors. + * @pad: Padding. + * @dynctl_reg_start: DYN_CTL register offset. + * @dynctl_reg_spacing: register spacing between DYN_CTL registers of 2 + * consecutive vectors. + * @itrn_reg_start: ITRN register offset. + * @itrn_reg_spacing: Register spacing between dynctl registers of 2 + * consecutive vectors. + * @itrn_index_spacing: Register spacing between itrn registers of the same + * vector where n=0..2. + * @pad1: Padding for future extensions. + * + * Register offsets and spacing provided by CP. + * Dynamic control registers are used for enabling/disabling/re-enabling + * interrupts and updating interrupt rates in the hotpath. Any changes + * to interrupt rates in the dynamic control registers will be reflected + * in the interrupt throttling rate registers. + * itrn registers are used to update interrupt rates for specific + * interrupt indices without modifying the state of the interrupt. + */ +struct virtchnl2_vector_chunk { + __le16 start_vector_id; + __le16 start_evv_id; + __le16 num_vectors; + __le16 pad; + __le32 dynctl_reg_start; + __le32 dynctl_reg_spacing; + __le32 itrn_reg_start; + __le32 itrn_reg_spacing; + __le32 itrn_index_spacing; + u8 pad1[4]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(32, virtchnl2_vector_chunk); + +/** + * struct virtchnl2_vector_chunks - chunks of contiguous interrupt vectors. + * @num_vchunks: number of vector chunks. + * @pad: Padding. + * @vchunks: Chunks of contiguous vector info. + * + * PF sends virtchnl2_vector_chunks struct to specify the vectors it is giving + * away. CP performs requested action and returns status. + * + * Associated with VIRTCHNL2_OP_DEALLOC_VECTORS. + */ +struct virtchnl2_vector_chunks { + __le16 num_vchunks; + u8 pad[14]; + struct virtchnl2_vector_chunk vchunks[]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_vector_chunks); + +/** + * struct virtchnl2_alloc_vectors - vector allocation info. + * @num_vectors: Number of vectors. + * @pad: Padding. + * @vchunks: Chunks of contiguous vector info. + * + * PF sends this message to request additional interrupt vectors beyond the + * ones that were assigned via GET_CAPS request. virtchnl2_alloc_vectors + * structure is used to specify the number of vectors requested. CP responds + * with the same structure with the actual number of vectors assigned followed + * by virtchnl2_vector_chunks structure identifying the vector ids. + * + * Associated with VIRTCHNL2_OP_ALLOC_VECTORS. + */ +struct virtchnl2_alloc_vectors { + __le16 num_vectors; + u8 pad[14]; + struct virtchnl2_vector_chunks vchunks; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(32, virtchnl2_alloc_vectors); + +/** + * struct virtchnl2_rss_lut - RSS LUT info. + * @vport_id: Vport id. + * @lut_entries_start: Start of LUT entries. + * @lut_entries: Number of LUT entrties. + * @pad: Padding. + * @lut: RSS lookup table. + * + * PF sends this message to get or set RSS lookup table. Only supported if + * both PF and CP drivers set the VIRTCHNL2_CAP_RSS bit during configuration + * negotiation. + * + * Associated with VIRTCHNL2_OP_GET_RSS_LUT and VIRTCHNL2_OP_SET_RSS_LUT. + */ +struct virtchnl2_rss_lut { + __le32 vport_id; + __le16 lut_entries_start; + __le16 lut_entries; + u8 pad[4]; + __le32 lut[]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(12, virtchnl2_rss_lut); + +/** + * struct virtchnl2_rss_hash - RSS hash info. + * @ptype_groups: Packet type groups bitmap. + * @vport_id: Vport id. + * @pad: Padding for future extensions. + * + * PF sends these messages to get and set the hash filter enable bits for RSS. + * By default, the CP sets these to all possible traffic types that the + * hardware supports. The PF can query this value if it wants to change the + * traffic types that are hashed by the hardware. + * Only supported if both PF and CP drivers set the VIRTCHNL2_CAP_RSS bit + * during configuration negotiation. + * + * Associated with VIRTCHNL2_OP_GET_RSS_HASH and VIRTCHNL2_OP_SET_RSS_HASH + */ +struct virtchnl2_rss_hash { + __le64 ptype_groups; + __le32 vport_id; + u8 pad[4]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_rss_hash); + +/** + * struct virtchnl2_sriov_vfs_info - VFs info. + * @num_vfs: Number of VFs. + * @pad: Padding for future extensions. + * + * This message is used to set number of SRIOV VFs to be created. The actual + * allocation of resources for the VFs in terms of vport, queues and interrupts + * is done by CP. When this call completes, the IDPF driver calls + * pci_enable_sriov to let the OS instantiate the SRIOV PCIE devices. + * The number of VFs set to 0 will destroy all the VFs of this function. + * + * Associated with VIRTCHNL2_OP_SET_SRIOV_VFS. + */ +struct virtchnl2_sriov_vfs_info { + __le16 num_vfs; + __le16 pad; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(4, virtchnl2_sriov_vfs_info); + +/** + * struct virtchnl2_ptype - Packet type info. + * @ptype_id_10: 10-bit packet type. + * @ptype_id_8: 8-bit packet type. + * @proto_id_count: Number of protocol ids the packet supports, maximum of 32 + * protocol ids are supported. + * @pad: Padding. + * @proto_id: proto_id_count decides the allocation of protocol id array. + * See enum virtchnl2_proto_hdr_type. + * + * Based on the descriptor type the PF supports, CP fills ptype_id_10 or + * ptype_id_8 for flex and base descriptor respectively. If ptype_id_10 value + * is set to 0xFFFF, PF should consider this ptype as dummy one and it is the + * last ptype. + */ +struct virtchnl2_ptype { + __le16 ptype_id_10; + u8 ptype_id_8; + u8 proto_id_count; + __le16 pad; + __le16 proto_id[]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(6, virtchnl2_ptype); + +/** + * struct virtchnl2_get_ptype_info - Packet type info. + * @start_ptype_id: Starting ptype ID. + * @num_ptypes: Number of packet types from start_ptype_id. + * @pad: Padding for future extensions. + * + * The total number of supported packet types is based on the descriptor type. + * For the flex descriptor, it is 1024 (10-bit ptype), and for the base + * descriptor, it is 256 (8-bit ptype). Send this message to the CP by + * populating the 'start_ptype_id' and the 'num_ptypes'. CP responds with the + * 'start_ptype_id', 'num_ptypes', and the array of ptype (virtchnl2_ptype) that + * are added at the end of the 'virtchnl2_get_ptype_info' message (Note: There + * is no specific field for the ptypes but are added at the end of the + * ptype info message. PF/VF is expected to extract the ptypes accordingly. + * Reason for doing this is because compiler doesn't allow nested flexible + * array fields). + * + * If all the ptypes don't fit into one mailbox buffer, CP splits the + * ptype info into multiple messages, where each message will have its own + * 'start_ptype_id', 'num_ptypes', and the ptype array itself. When CP is done + * updating all the ptype information extracted from the package (the number of + * ptypes extracted might be less than what PF/VF expects), it will append a + * dummy ptype (which has 'ptype_id_10' of 'struct virtchnl2_ptype' as 0xFFFF) + * to the ptype array. + * + * PF/VF is expected to receive multiple VIRTCHNL2_OP_GET_PTYPE_INFO messages. + * + * Associated with VIRTCHNL2_OP_GET_PTYPE_INFO. + */ +struct virtchnl2_get_ptype_info { + __le16 start_ptype_id; + __le16 num_ptypes; + __le32 pad; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_get_ptype_info); + +/** + * struct virtchnl2_vport_stats - Vport statistics. + * @vport_id: Vport id. + * @pad: Padding. + * @rx_bytes: Received bytes. + * @rx_unicast: Received unicast packets. + * @rx_multicast: Received multicast packets. + * @rx_broadcast: Received broadcast packets. + * @rx_discards: Discarded packets on receive. + * @rx_errors: Receive errors. + * @rx_unknown_protocol: Unlnown protocol. + * @tx_bytes: Transmitted bytes. + * @tx_unicast: Transmitted unicast packets. + * @tx_multicast: Transmitted multicast packets. + * @tx_broadcast: Transmitted broadcast packets. + * @tx_discards: Discarded packets on transmit. + * @tx_errors: Transmit errors. + * @rx_invalid_frame_length: Packets with invalid frame length. + * @rx_overflow_drop: Packets dropped on buffer overflow. + * + * PF/VF sends this message to CP to get the update stats by specifying the + * vport_id. CP responds with stats in struct virtchnl2_vport_stats. + * + * Associated with VIRTCHNL2_OP_GET_STATS. + */ +struct virtchnl2_vport_stats { + __le32 vport_id; + u8 pad[4]; + __le64 rx_bytes; + __le64 rx_unicast; + __le64 rx_multicast; + __le64 rx_broadcast; + __le64 rx_discards; + __le64 rx_errors; + __le64 rx_unknown_protocol; + __le64 tx_bytes; + __le64 tx_unicast; + __le64 tx_multicast; + __le64 tx_broadcast; + __le64 tx_discards; + __le64 tx_errors; + __le64 rx_invalid_frame_length; + __le64 rx_overflow_drop; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(128, virtchnl2_vport_stats); + +/** + * struct virtchnl2_event - Event info. + * @event: Event opcode. See enum virtchnl2_event_codes. + * @link_speed: Link_speed provided in Mbps. + * @vport_id: Vport ID. + * @link_status: Link status. + * @pad: Padding. + * @reserved: Reserved. + * + * CP sends this message to inform the PF/VF driver of events that may affect + * it. No direct response is expected from the driver, though it may generate + * other messages in response to this one. + * + * Associated with VIRTCHNL2_OP_EVENT. + */ +struct virtchnl2_event { + __le32 event; + __le32 link_speed; + __le32 vport_id; + u8 link_status; + u8 pad; + __le16 reserved; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_event); + +/** + * struct virtchnl2_rss_key - RSS key info. + * @vport_id: Vport id. + * @key_len: Length of RSS key. + * @pad: Padding. + * @key_flex: RSS hash key, packed bytes. + * PF/VF sends this message to get or set RSS key. Only supported if both + * PF/VF and CP drivers set the VIRTCHNL2_CAP_RSS bit during configuration + * negotiation. + * + * Associated with VIRTCHNL2_OP_GET_RSS_KEY and VIRTCHNL2_OP_SET_RSS_KEY. + */ +struct virtchnl2_rss_key { + __le32 vport_id; + __le16 key_len; + u8 pad; + __DECLARE_FLEX_ARRAY(u8, key_flex); +}; +VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_rss_key); + +/** + * struct virtchnl2_queue_chunk - chunk of contiguous queues + * @type: See enum virtchnl2_queue_type. + * @start_queue_id: Starting queue id. + * @num_queues: Number of queues. + * @pad: Padding for future extensions. + */ +struct virtchnl2_queue_chunk { + __le32 type; + __le32 start_queue_id; + __le32 num_queues; + u8 pad[4]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_queue_chunk); + +/* struct virtchnl2_queue_chunks - chunks of contiguous queues + * @num_chunks: Number of chunks. + * @pad: Padding. + * @chunks: Chunks of contiguous queues info. + */ +struct virtchnl2_queue_chunks { + __le16 num_chunks; + u8 pad[6]; + struct virtchnl2_queue_chunk chunks[]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_queue_chunks); + +/** + * struct virtchnl2_del_ena_dis_queues - Enable/disable queues info. + * @vport_id: Vport id. + * @pad: Padding. + * @chunks: Chunks of contiguous queues info. + * + * PF sends these messages to enable, disable or delete queues specified in + * chunks. PF sends virtchnl2_del_ena_dis_queues struct to specify the queues + * to be enabled/disabled/deleted. Also applicable to single queue receive or + * transmit. CP performs requested action and returns status. + * + * Associated with VIRTCHNL2_OP_ENABLE_QUEUES, VIRTCHNL2_OP_DISABLE_QUEUES and + * VIRTCHNL2_OP_DISABLE_QUEUES. + */ +struct virtchnl2_del_ena_dis_queues { + __le32 vport_id; + u8 pad[4]; + struct virtchnl2_queue_chunks chunks; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_del_ena_dis_queues); + +/** + * struct virtchnl2_queue_vector - Queue to vector mapping. + * @queue_id: Queue id. + * @vector_id: Vector id. + * @pad: Padding. + * @itr_idx: See enum virtchnl2_itr_idx. + * @queue_type: See enum virtchnl2_queue_type. + * @pad1: Padding for future extensions. + */ +struct virtchnl2_queue_vector { + __le32 queue_id; + __le16 vector_id; + u8 pad[2]; + __le32 itr_idx; + __le32 queue_type; + u8 pad1[8]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(24, virtchnl2_queue_vector); + +/** + * struct virtchnl2_queue_vector_maps - Map/unmap queues info. + * @vport_id: Vport id. + * @num_qv_maps: Number of queue vector maps. + * @pad: Padding. + * @qv_maps: Queue to vector maps. + * + * PF sends this message to map or unmap queues to vectors and interrupt + * throttling rate index registers. External data buffer contains + * virtchnl2_queue_vector_maps structure that contains num_qv_maps of + * virtchnl2_queue_vector structures. CP maps the requested queue vector maps + * after validating the queue and vector ids and returns a status code. + * + * Associated with VIRTCHNL2_OP_MAP_QUEUE_VECTOR and + * VIRTCHNL2_OP_UNMAP_QUEUE_VECTOR. + */ +struct virtchnl2_queue_vector_maps { + __le32 vport_id; + __le16 num_qv_maps; + u8 pad[10]; + struct virtchnl2_queue_vector qv_maps[]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_queue_vector_maps); + +/** + * struct virtchnl2_loopback - Loopback info. + * @vport_id: Vport id. + * @enable: Enable/disable. + * @pad: Padding for future extensions. + * + * PF/VF sends this message to transition to/from the loopback state. Setting + * the 'enable' to 1 enables the loopback state and setting 'enable' to 0 + * disables it. CP configures the state to loopback and returns status. + * + * Associated with VIRTCHNL2_OP_LOOPBACK. + */ +struct virtchnl2_loopback { + __le32 vport_id; + u8 enable; + u8 pad[3]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_loopback); + +/* struct virtchnl2_mac_addr - MAC address info. + * @addr: MAC address. + * @type: MAC type. See enum virtchnl2_mac_addr_type. + * @pad: Padding for future extensions. + */ +struct virtchnl2_mac_addr { + u8 addr[ETH_ALEN]; + u8 type; + u8 pad; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_mac_addr); + +/** + * struct virtchnl2_mac_addr_list - List of MAC addresses. + * @vport_id: Vport id. + * @num_mac_addr: Number of MAC addresses. + * @pad: Padding. + * @mac_addr_list: List with MAC address info. + * + * PF/VF driver uses this structure to send list of MAC addresses to be + * added/deleted to the CP where as CP performs the action and returns the + * status. + * + * Associated with VIRTCHNL2_OP_ADD_MAC_ADDR and VIRTCHNL2_OP_DEL_MAC_ADDR. + */ +struct virtchnl2_mac_addr_list { + __le32 vport_id; + __le16 num_mac_addr; + u8 pad[2]; + struct virtchnl2_mac_addr mac_addr_list[]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_mac_addr_list); + +/** + * struct virtchnl2_promisc_info - Promisc type info. + * @vport_id: Vport id. + * @flags: See enum virtchnl2_promisc_flags. + * @pad: Padding for future extensions. + * + * PF/VF sends vport id and flags to the CP where as CP performs the action + * and returns the status. + * + * Associated with VIRTCHNL2_OP_CONFIG_PROMISCUOUS_MODE. + */ +struct virtchnl2_promisc_info { + __le32 vport_id; + /* See VIRTCHNL2_PROMISC_FLAGS definitions */ + __le16 flags; + u8 pad[2]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_promisc_info); + +#endif /* _VIRTCHNL_2_H_ */ diff --git a/drivers/net/ethernet/intel/idpf/virtchnl2_lan_desc.h b/drivers/net/ethernet/intel/idpf/virtchnl2_lan_desc.h new file mode 100644 index 000000000000..f1b577f1c452 --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/virtchnl2_lan_desc.h @@ -0,0 +1,451 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2023 Intel Corporation */ + +#ifndef _VIRTCHNL2_LAN_DESC_H_ +#define _VIRTCHNL2_LAN_DESC_H_ + +#include <linux/bits.h> + +/* This is an interface definition file where existing enums and their values + * must remain unchanged over time, so we specify explicit values for all enums. + */ + +/* Transmit descriptor ID flags + */ +enum virtchnl2_tx_desc_ids { + VIRTCHNL2_TXDID_DATA = BIT(0), + VIRTCHNL2_TXDID_CTX = BIT(1), + /* TXDID bit 2 is reserved + * TXDID bit 3 is free for future use + * TXDID bit 4 is reserved + */ + VIRTCHNL2_TXDID_FLEX_TSO_CTX = BIT(5), + /* TXDID bit 6 is reserved */ + VIRTCHNL2_TXDID_FLEX_L2TAG1_L2TAG2 = BIT(7), + /* TXDID bits 8 and 9 are free for future use + * TXDID bit 10 is reserved + * TXDID bit 11 is free for future use + */ + VIRTCHNL2_TXDID_FLEX_FLOW_SCHED = BIT(12), + /* TXDID bits 13 and 14 are free for future use */ + VIRTCHNL2_TXDID_DESC_DONE = BIT(15), +}; + +/* Receive descriptor IDs */ +enum virtchnl2_rx_desc_ids { + VIRTCHNL2_RXDID_1_32B_BASE = 1, + /* FLEX_SQ_NIC and FLEX_SPLITQ share desc ids because they can be + * differentiated based on queue model; e.g. single queue model can + * only use FLEX_SQ_NIC and split queue model can only use FLEX_SPLITQ + * for DID 2. + */ + VIRTCHNL2_RXDID_2_FLEX_SPLITQ = 2, + VIRTCHNL2_RXDID_2_FLEX_SQ_NIC = VIRTCHNL2_RXDID_2_FLEX_SPLITQ, + /* 3 through 6 are reserved */ + VIRTCHNL2_RXDID_7_HW_RSVD = 7, + /* 8 through 15 are free */ +}; + +/* Receive descriptor ID bitmasks */ +#define VIRTCHNL2_RXDID_M(bit) BIT_ULL(VIRTCHNL2_RXDID_##bit) + +enum virtchnl2_rx_desc_id_bitmasks { + VIRTCHNL2_RXDID_1_32B_BASE_M = VIRTCHNL2_RXDID_M(1_32B_BASE), + VIRTCHNL2_RXDID_2_FLEX_SPLITQ_M = VIRTCHNL2_RXDID_M(2_FLEX_SPLITQ), + VIRTCHNL2_RXDID_2_FLEX_SQ_NIC_M = VIRTCHNL2_RXDID_M(2_FLEX_SQ_NIC), + VIRTCHNL2_RXDID_7_HW_RSVD_M = VIRTCHNL2_RXDID_M(7_HW_RSVD), +}; + +/* For splitq virtchnl2_rx_flex_desc_adv_nic_3 desc members */ +#define VIRTCHNL2_RX_FLEX_DESC_ADV_RXDID_M GENMASK(3, 0) +#define VIRTCHNL2_RX_FLEX_DESC_ADV_UMBCAST_M GENMASK(7, 6) +#define VIRTCHNL2_RX_FLEX_DESC_ADV_PTYPE_M GENMASK(9, 0) +#define VIRTCHNL2_RX_FLEX_DESC_ADV_RAW_CSUM_INV_S 12 +#define VIRTCHNL2_RX_FLEX_DESC_ADV_RAW_CSUM_INV_M \ + BIT_ULL(VIRTCHNL2_RX_FLEX_DESC_ADV_RAW_CSUM_INV_S) +#define VIRTCHNL2_RX_FLEX_DESC_ADV_FF0_M GENMASK(15, 13) +#define VIRTCHNL2_RX_FLEX_DESC_ADV_LEN_PBUF_M GENMASK(13, 0) +#define VIRTCHNL2_RX_FLEX_DESC_ADV_GEN_S 14 +#define VIRTCHNL2_RX_FLEX_DESC_ADV_GEN_M \ + BIT_ULL(VIRTCHNL2_RX_FLEX_DESC_ADV_GEN_S) +#define VIRTCHNL2_RX_FLEX_DESC_ADV_BUFQ_ID_S 15 +#define VIRTCHNL2_RX_FLEX_DESC_ADV_BUFQ_ID_M \ + BIT_ULL(VIRTCHNL2_RX_FLEX_DESC_ADV_BUFQ_ID_S) +#define VIRTCHNL2_RX_FLEX_DESC_ADV_LEN_HDR_M GENMASK(9, 0) +#define VIRTCHNL2_RX_FLEX_DESC_ADV_RSC_S 10 +#define VIRTCHNL2_RX_FLEX_DESC_ADV_RSC_M \ + BIT_ULL(VIRTCHNL2_RX_FLEX_DESC_ADV_RSC_S) +#define VIRTCHNL2_RX_FLEX_DESC_ADV_SPH_S 11 +#define VIRTCHNL2_RX_FLEX_DESC_ADV_SPH_M \ + BIT_ULL(VIRTCHNL2_RX_FLEX_DESC_ADV_SPH_S) +#define VIRTCHNL2_RX_FLEX_DESC_ADV_FF1_S 12 +#define VIRTCHNL2_RX_FLEX_DESC_ADV_FF1_M GENMASK(14, 12) +#define VIRTCHNL2_RX_FLEX_DESC_ADV_MISS_S 15 +#define VIRTCHNL2_RX_FLEX_DESC_ADV_MISS_M \ + BIT_ULL(VIRTCHNL2_RX_FLEX_DESC_ADV_MISS_S) + +/* Bitmasks for splitq virtchnl2_rx_flex_desc_adv_nic_3 */ +enum virtchl2_rx_flex_desc_adv_status_error_0_qw1_bits { + VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_DD_M = BIT(0), + VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_EOF_M = BIT(1), + VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_HBO_M = BIT(2), + VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_L3L4P_M = BIT(3), + VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_XSUM_IPE_M = BIT(4), + VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_XSUM_L4E_M = BIT(5), + VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_XSUM_EIPE_M = BIT(6), + VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_XSUM_EUDPE_M = BIT(7), +}; + +/* Bitmasks for splitq virtchnl2_rx_flex_desc_adv_nic_3 */ +enum virtchnl2_rx_flex_desc_adv_status_error_0_qw0_bits { + VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_LPBK_M = BIT(0), + VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_IPV6EXADD_M = BIT(1), + VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_RXE_M = BIT(2), + VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_CRCP_M = BIT(3), + VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_RSS_VALID_M = BIT(4), + VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_L2TAG1P_M = BIT(5), + VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_XTRMD0_VALID_M = BIT(6), + VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_XTRMD1_VALID_M = BIT(7), +}; + +/* Bitmasks for splitq virtchnl2_rx_flex_desc_adv_nic_3 */ +enum virtchnl2_rx_flex_desc_adv_status_error_1_bits { + VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS1_RSVD_M = GENMASK(1, 0), + VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS1_ATRAEFAIL_M = BIT(2), + VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS1_L2TAG2P_M = BIT(3), + VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS1_XTRMD2_VALID_M = BIT(4), + VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS1_XTRMD3_VALID_M = BIT(5), + VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS1_XTRMD4_VALID_M = BIT(6), + VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS1_XTRMD5_VALID_M = BIT(7), +}; + +/* For singleq (flex) virtchnl2_rx_flex_desc fields + * For virtchnl2_rx_flex_desc.ptype_flex_flags0 member + */ +#define VIRTCHNL2_RX_FLEX_DESC_PTYPE_M GENMASK(9, 0) + +/* For virtchnl2_rx_flex_desc.pkt_len member */ +#define VIRTCHNL2_RX_FLEX_DESC_PKT_LEN_M GENMASK(13, 0) + +/* Bitmasks for singleq (flex) virtchnl2_rx_flex_desc */ +enum virtchnl2_rx_flex_desc_status_error_0_bits { + VIRTCHNL2_RX_FLEX_DESC_STATUS0_DD_M = BIT(0), + VIRTCHNL2_RX_FLEX_DESC_STATUS0_EOF_M = BIT(1), + VIRTCHNL2_RX_FLEX_DESC_STATUS0_HBO_M = BIT(2), + VIRTCHNL2_RX_FLEX_DESC_STATUS0_L3L4P_M = BIT(3), + VIRTCHNL2_RX_FLEX_DESC_STATUS0_XSUM_IPE_M = BIT(4), + VIRTCHNL2_RX_FLEX_DESC_STATUS0_XSUM_L4E_M = BIT(5), + VIRTCHNL2_RX_FLEX_DESC_STATUS0_XSUM_EIPE_M = BIT(6), + VIRTCHNL2_RX_FLEX_DESC_STATUS0_XSUM_EUDPE_M = BIT(7), + VIRTCHNL2_RX_FLEX_DESC_STATUS0_LPBK_M = BIT(8), + VIRTCHNL2_RX_FLEX_DESC_STATUS0_IPV6EXADD_M = BIT(9), + VIRTCHNL2_RX_FLEX_DESC_STATUS0_RXE_M = BIT(10), + VIRTCHNL2_RX_FLEX_DESC_STATUS0_CRCP_M = BIT(11), + VIRTCHNL2_RX_FLEX_DESC_STATUS0_RSS_VALID_M = BIT(12), + VIRTCHNL2_RX_FLEX_DESC_STATUS0_L2TAG1P_M = BIT(13), + VIRTCHNL2_RX_FLEX_DESC_STATUS0_XTRMD0_VALID_M = BIT(14), + VIRTCHNL2_RX_FLEX_DESC_STATUS0_XTRMD1_VALID_M = BIT(15), +}; + +/* Bitmasks for singleq (flex) virtchnl2_rx_flex_desc */ +enum virtchnl2_rx_flex_desc_status_error_1_bits { + VIRTCHNL2_RX_FLEX_DESC_STATUS1_CPM_M = GENMASK(3, 0), + VIRTCHNL2_RX_FLEX_DESC_STATUS1_NAT_M = BIT(4), + VIRTCHNL2_RX_FLEX_DESC_STATUS1_CRYPTO_M = BIT(5), + /* [10:6] reserved */ + VIRTCHNL2_RX_FLEX_DESC_STATUS1_L2TAG2P_M = BIT(11), + VIRTCHNL2_RX_FLEX_DESC_STATUS1_XTRMD2_VALID_M = BIT(12), + VIRTCHNL2_RX_FLEX_DESC_STATUS1_XTRMD3_VALID_M = BIT(13), + VIRTCHNL2_RX_FLEX_DESC_STATUS1_XTRMD4_VALID_M = BIT(14), + VIRTCHNL2_RX_FLEX_DESC_STATUS1_XTRMD5_VALID_M = BIT(15), +}; + +/* For virtchnl2_rx_flex_desc.ts_low member */ +#define VIRTCHNL2_RX_FLEX_TSTAMP_VALID BIT(0) + +/* For singleq (non flex) virtchnl2_singleq_base_rx_desc legacy desc members */ +#define VIRTCHNL2_RX_BASE_DESC_QW1_LEN_PBUF_M GENMASK_ULL(51, 38) +#define VIRTCHNL2_RX_BASE_DESC_QW1_PTYPE_M GENMASK_ULL(37, 30) +#define VIRTCHNL2_RX_BASE_DESC_QW1_ERROR_M GENMASK_ULL(26, 19) +#define VIRTCHNL2_RX_BASE_DESC_QW1_STATUS_M GENMASK_ULL(18, 0) + +/* Bitmasks for singleq (base) virtchnl2_rx_base_desc */ +enum virtchnl2_rx_base_desc_status_bits { + VIRTCHNL2_RX_BASE_DESC_STATUS_DD_M = BIT(0), + VIRTCHNL2_RX_BASE_DESC_STATUS_EOF_M = BIT(1), + VIRTCHNL2_RX_BASE_DESC_STATUS_L2TAG1P_M = BIT(2), + VIRTCHNL2_RX_BASE_DESC_STATUS_L3L4P_M = BIT(3), + VIRTCHNL2_RX_BASE_DESC_STATUS_CRCP_M = BIT(4), + VIRTCHNL2_RX_BASE_DESC_STATUS_RSVD_M = GENMASK(7, 5), + VIRTCHNL2_RX_BASE_DESC_STATUS_EXT_UDP_0_M = BIT(8), + VIRTCHNL2_RX_BASE_DESC_STATUS_UMBCAST_M = GENMASK(10, 9), + VIRTCHNL2_RX_BASE_DESC_STATUS_FLM_M = BIT(11), + VIRTCHNL2_RX_BASE_DESC_STATUS_FLTSTAT_M = GENMASK(13, 12), + VIRTCHNL2_RX_BASE_DESC_STATUS_LPBK_M = BIT(14), + VIRTCHNL2_RX_BASE_DESC_STATUS_IPV6EXADD_M = BIT(15), + VIRTCHNL2_RX_BASE_DESC_STATUS_RSVD1_M = GENMASK(17, 16), + VIRTCHNL2_RX_BASE_DESC_STATUS_INT_UDP_0_M = BIT(18), +}; + +/* Bitmasks for singleq (base) virtchnl2_rx_base_desc */ +enum virtchnl2_rx_base_desc_error_bits { + VIRTCHNL2_RX_BASE_DESC_ERROR_RXE_M = BIT(0), + VIRTCHNL2_RX_BASE_DESC_ERROR_ATRAEFAIL_M = BIT(1), + VIRTCHNL2_RX_BASE_DESC_ERROR_HBO_M = BIT(2), + VIRTCHNL2_RX_BASE_DESC_ERROR_L3L4E_M = GENMASK(5, 3), + VIRTCHNL2_RX_BASE_DESC_ERROR_IPE_M = BIT(3), + VIRTCHNL2_RX_BASE_DESC_ERROR_L4E_M = BIT(4), + VIRTCHNL2_RX_BASE_DESC_ERROR_EIPE_M = BIT(5), + VIRTCHNL2_RX_BASE_DESC_ERROR_OVERSIZE_M = BIT(6), + VIRTCHNL2_RX_BASE_DESC_ERROR_PPRS_M = BIT(7), +}; + +/* Bitmasks for singleq (base) virtchnl2_rx_base_desc */ +#define VIRTCHNL2_RX_BASE_DESC_FLTSTAT_RSS_HASH_M GENMASK(13, 12) + +/** + * struct virtchnl2_splitq_rx_buf_desc - SplitQ RX buffer descriptor format + * @qword0: RX buffer struct. + * @qword0.buf_id: Buffer identifier. + * @qword0.rsvd0: Reserved. + * @qword0.rsvd1: Reserved. + * @pkt_addr: Packet buffer address. + * @hdr_addr: Header buffer address. + * @rsvd2: Rerserved. + * + * Receive Descriptors + * SplitQ buffer + * | 16| 0| + * ---------------------------------------------------------------- + * | RSV | Buffer ID | + * ---------------------------------------------------------------- + * | Rx packet buffer address | + * ---------------------------------------------------------------- + * | Rx header buffer address | + * ---------------------------------------------------------------- + * | RSV | + * ---------------------------------------------------------------- + * | 0| + */ +struct virtchnl2_splitq_rx_buf_desc { + struct { + __le16 buf_id; + __le16 rsvd0; + __le32 rsvd1; + } qword0; + __le64 pkt_addr; + __le64 hdr_addr; + __le64 rsvd2; +}; + +/** + * struct virtchnl2_singleq_rx_buf_desc - SingleQ RX buffer descriptor format. + * @pkt_addr: Packet buffer address. + * @hdr_addr: Header buffer address. + * @rsvd1: Reserved. + * @rsvd2: Reserved. + * + * SingleQ buffer + * | 0| + * ---------------------------------------------------------------- + * | Rx packet buffer address | + * ---------------------------------------------------------------- + * | Rx header buffer address | + * ---------------------------------------------------------------- + * | RSV | + * ---------------------------------------------------------------- + * | RSV | + * ---------------------------------------------------------------- + * | 0| + */ +struct virtchnl2_singleq_rx_buf_desc { + __le64 pkt_addr; + __le64 hdr_addr; + __le64 rsvd1; + __le64 rsvd2; +}; + +/** + * struct virtchnl2_singleq_base_rx_desc - RX descriptor writeback format. + * @qword0: First quad word struct. + * @qword0.lo_dword: Lower dual word struct. + * @qword0.lo_dword.mirroring_status: Mirrored packet status. + * @qword0.lo_dword.l2tag1: Stripped L2 tag from the received packet. + * @qword0.hi_dword: High dual word union. + * @qword0.hi_dword.rss: RSS hash. + * @qword0.hi_dword.fd_id: Flow director filter id. + * @qword1: Second quad word struct. + * @qword1.status_error_ptype_len: Status/error/PTYPE/length. + * @qword2: Third quad word struct. + * @qword2.ext_status: Extended status. + * @qword2.rsvd: Reserved. + * @qword2.l2tag2_1: Extracted L2 tag 2 from the packet. + * @qword2.l2tag2_2: Reserved. + * @qword3: Fourth quad word struct. + * @qword3.reserved: Reserved. + * @qword3.fd_id: Flow director filter id. + * + * Profile ID 0x1, SingleQ, base writeback format + */ +struct virtchnl2_singleq_base_rx_desc { + struct { + struct { + __le16 mirroring_status; + __le16 l2tag1; + } lo_dword; + union { + __le32 rss; + __le32 fd_id; + } hi_dword; + } qword0; + struct { + __le64 status_error_ptype_len; + } qword1; + struct { + __le16 ext_status; + __le16 rsvd; + __le16 l2tag2_1; + __le16 l2tag2_2; + } qword2; + struct { + __le32 reserved; + __le32 fd_id; + } qword3; +}; + +/** + * struct virtchnl2_rx_flex_desc_nic - RX descriptor writeback format. + * + * @rxdid: Descriptor builder profile id. + * @mir_id_umb_cast: umb_cast=[7:6], mirror=[5:0] + * @ptype_flex_flags0: ff0=[15:10], ptype=[9:0] + * @pkt_len: Packet length, [15:14] are reserved. + * @hdr_len_sph_flex_flags1: ff1/ext=[15:12], sph=[11], header=[10:0]. + * @status_error0: Status/Error section 0. + * @l2tag1: Stripped L2 tag from the received packet + * @rss_hash: RSS hash. + * @status_error1: Status/Error section 1. + * @flexi_flags2: Flexible flags section 2. + * @ts_low: Lower word of timestamp value. + * @l2tag2_1st: First L2TAG2. + * @l2tag2_2nd: Second L2TAG2. + * @flow_id: Flow id. + * @flex_ts: Timestamp and flexible flow id union. + * @flex_ts.ts_high: Timestamp higher word of the timestamp value. + * @flex_ts.flex.rsvd: Reserved. + * @flex_ts.flex.flow_id_ipv6: IPv6 flow id. + * + * Profile ID 0x2, SingleQ, flex writeback format + */ +struct virtchnl2_rx_flex_desc_nic { + /* Qword 0 */ + u8 rxdid; + u8 mir_id_umb_cast; + __le16 ptype_flex_flags0; + __le16 pkt_len; + __le16 hdr_len_sph_flex_flags1; + /* Qword 1 */ + __le16 status_error0; + __le16 l2tag1; + __le32 rss_hash; + /* Qword 2 */ + __le16 status_error1; + u8 flexi_flags2; + u8 ts_low; + __le16 l2tag2_1st; + __le16 l2tag2_2nd; + /* Qword 3 */ + __le32 flow_id; + union { + struct { + __le16 rsvd; + __le16 flow_id_ipv6; + } flex; + __le32 ts_high; + } flex_ts; +}; + +/** + * struct virtchnl2_rx_flex_desc_adv_nic_3 - RX descriptor writeback format. + * @rxdid_ucast: ucast=[7:6], rsvd=[5:4], profile_id=[3:0]. + * @status_err0_qw0: Status/Error section 0 in quad word 0. + * @ptype_err_fflags0: ff0=[15:12], udp_len_err=[11], ip_hdr_err=[10], + * ptype=[9:0]. + * @pktlen_gen_bufq_id: bufq_id=[15] only in splitq, gen=[14] only in splitq, + * plen=[13:0]. + * @hdrlen_flags: miss_prepend=[15], trunc_mirr=[14], int_udp_0=[13], + * ext_udp0=[12], sph=[11] only in splitq, rsc=[10] + * only in splitq, header=[9:0]. + * @status_err0_qw1: Status/Error section 0 in quad word 1. + * @status_err1: Status/Error section 1. + * @fflags1: Flexible flags section 1. + * @ts_low: Lower word of timestamp value. + * @buf_id: Buffer identifier. Only in splitq mode. + * @misc: Union. + * @misc.raw_cs: Raw checksum. + * @misc.l2tag1: Stripped L2 tag from the received packet + * @misc.rscseglen: + * @hash1: Lower bits of Rx hash value. + * @ff2_mirrid_hash2: Union. + * @ff2_mirrid_hash2.fflags2: Flexible flags section 2. + * @ff2_mirrid_hash2.mirrorid: Mirror id. + * @ff2_mirrid_hash2.rscseglen: RSC segment length. + * @hash3: Upper bits of Rx hash value. + * @l2tag2: Extracted L2 tag 2 from the packet. + * @fmd4: Flexible metadata container 4. + * @l2tag1: Stripped L2 tag from the received packet + * @fmd6: Flexible metadata container 6. + * @ts_high: Timestamp higher word of the timestamp value. + * + * Profile ID 0x2, SplitQ, flex writeback format + * + * Flex-field 0: BufferID + * Flex-field 1: Raw checksum/L2TAG1/RSC Seg Len (determined by HW) + * Flex-field 2: Hash[15:0] + * Flex-flags 2: Hash[23:16] + * Flex-field 3: L2TAG2 + * Flex-field 5: L2TAG1 + * Flex-field 7: Timestamp (upper 32 bits) + */ +struct virtchnl2_rx_flex_desc_adv_nic_3 { + /* Qword 0 */ + u8 rxdid_ucast; + u8 status_err0_qw0; + __le16 ptype_err_fflags0; + __le16 pktlen_gen_bufq_id; + __le16 hdrlen_flags; + /* Qword 1 */ + u8 status_err0_qw1; + u8 status_err1; + u8 fflags1; + u8 ts_low; + __le16 buf_id; + union { + __le16 raw_cs; + __le16 l2tag1; + __le16 rscseglen; + } misc; + /* Qword 2 */ + __le16 hash1; + union { + u8 fflags2; + u8 mirrorid; + u8 hash2; + } ff2_mirrid_hash2; + u8 hash3; + __le16 l2tag2; + __le16 fmd4; + /* Qword 3 */ + __le16 l2tag1; + __le16 fmd6; + __le32 ts_high; +}; + +/* Common union for accessing descriptor format structs */ +union virtchnl2_rx_desc { + struct virtchnl2_singleq_base_rx_desc base_wb; + struct virtchnl2_rx_flex_desc_nic flex_nic_wb; + struct virtchnl2_rx_flex_desc_adv_nic_3 flex_adv_nic_3_wb; +}; + +#endif /* _VIRTCHNL_LAN_DESC_H_ */ diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 015b78144114..a2b759531cb7 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -34,11 +34,11 @@ struct igb_adapter; /* TX/RX descriptor defines */ #define IGB_DEFAULT_TXD 256 #define IGB_DEFAULT_TX_WORK 128 -#define IGB_MIN_TXD 80 +#define IGB_MIN_TXD 64 #define IGB_MAX_TXD 4096 #define IGB_DEFAULT_RXD 256 -#define IGB_MIN_RXD 80 +#define IGB_MIN_RXD 64 #define IGB_MAX_RXD 4096 #define IGB_DEFAULT_ITR 3 /* dynamic */ diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 319ed601eaa1..16d2a55d5e17 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -2356,10 +2356,10 @@ static void igb_get_strings(struct net_device *netdev, u32 stringset, u8 *data) break; case ETH_SS_STATS: for (i = 0; i < IGB_GLOBAL_STATS_LEN; i++) - ethtool_sprintf(&p, + ethtool_sprintf(&p, "%s", igb_gstrings_stats[i].stat_string); for (i = 0; i < IGB_NETDEV_STATS_LEN; i++) - ethtool_sprintf(&p, + ethtool_sprintf(&p, "%s", igb_gstrings_net_stats[i].stat_string); for (i = 0; i < adapter->num_tx_queues; i++) { ethtool_sprintf(&p, "tx_queue_%u_packets", i); @@ -2978,11 +2978,15 @@ static int igb_add_ethtool_nfc_entry(struct igb_adapter *adapter, if (err) goto err_out_w_lock; - igb_update_ethtool_nfc_entry(adapter, input, input->sw_idx); + err = igb_update_ethtool_nfc_entry(adapter, input, input->sw_idx); + if (err) + goto err_out_input_filter; spin_unlock(&adapter->nfc_lock); return 0; +err_out_input_filter: + igb_erase_filter(adapter, input); err_out_w_lock: spin_unlock(&adapter->nfc_lock); err_out: diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 9a2561409b06..b2295caa2f0a 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2615,10 +2615,10 @@ static int igb_parse_cls_flower(struct igb_adapter *adapter, struct netlink_ext_ack *extack = f->common.extack; if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_VLAN))) { + ~(BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN))) { NL_SET_ERR_MSG_MOD(extack, "Unsupported key used, only BASIC, CONTROL, ETH_ADDRS and VLAN are supported"); return -EOPNOTSUPP; @@ -3069,6 +3069,7 @@ void igb_set_fw_version(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; struct e1000_fw_version fw; + char *lbuf; igb_get_fw_version(hw, &fw); @@ -3076,36 +3077,34 @@ void igb_set_fw_version(struct igb_adapter *adapter) case e1000_i210: case e1000_i211: if (!(igb_get_flash_presence_i210(hw))) { - snprintf(adapter->fw_version, - sizeof(adapter->fw_version), - "%2d.%2d-%d", - fw.invm_major, fw.invm_minor, - fw.invm_img_type); + lbuf = kasprintf(GFP_KERNEL, "%2d.%2d-%d", + fw.invm_major, fw.invm_minor, + fw.invm_img_type); break; } fallthrough; default: - /* if option is rom valid, display its version too */ + /* if option rom is valid, display its version too */ if (fw.or_valid) { - snprintf(adapter->fw_version, - sizeof(adapter->fw_version), - "%d.%d, 0x%08x, %d.%d.%d", - fw.eep_major, fw.eep_minor, fw.etrack_id, - fw.or_major, fw.or_build, fw.or_patch); + lbuf = kasprintf(GFP_KERNEL, "%d.%d, 0x%08x, %d.%d.%d", + fw.eep_major, fw.eep_minor, + fw.etrack_id, fw.or_major, fw.or_build, + fw.or_patch); /* no option rom */ } else if (fw.etrack_id != 0X0000) { - snprintf(adapter->fw_version, - sizeof(adapter->fw_version), - "%d.%d, 0x%08x", - fw.eep_major, fw.eep_minor, fw.etrack_id); + lbuf = kasprintf(GFP_KERNEL, "%d.%d, 0x%08x", + fw.eep_major, fw.eep_minor, + fw.etrack_id); } else { - snprintf(adapter->fw_version, - sizeof(adapter->fw_version), - "%d.%d.%d", - fw.eep_major, fw.eep_minor, fw.eep_build); + lbuf = kasprintf(GFP_KERNEL, "%d.%d.%d", fw.eep_major, + fw.eep_minor, fw.eep_build); } break; } + + /* the truncate happens here if it doesn't fit */ + strscpy(adapter->fw_version, lbuf, sizeof(adapter->fw_version)); + kfree(lbuf); } /** @@ -3264,7 +3263,7 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) igb_set_ethtool_ops(netdev); netdev->watchdog_timeo = 5 * HZ; - strncpy(netdev->name, pci_name(pdev), sizeof(netdev->name) - 1); + strscpy(netdev->name, pci_name(pdev), sizeof(netdev->name)); netdev->mem_start = pci_resource_start(pdev, 0); netdev->mem_end = pci_resource_end(pdev, 0); @@ -3827,8 +3826,11 @@ static int igb_enable_sriov(struct pci_dev *pdev, int num_vfs, bool reinit) } /* only call pci_enable_sriov() if no VFs are allocated already */ - if (!old_vfs) + if (!old_vfs) { err = pci_enable_sriov(pdev, adapter->vfs_allocated_count); + if (err) + goto err_out; + } goto out; @@ -3933,8 +3935,9 @@ static void igb_probe_vfs(struct igb_adapter *adapter) struct pci_dev *pdev = adapter->pdev; struct e1000_hw *hw = &adapter->hw; - /* Virtualization features not supported on i210 family. */ - if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211)) + /* Virtualization features not supported on i210 and 82580 family. */ + if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211) || + (hw->mac.type == e1000_82580)) return; /* Of the below we really only want the effect of getting @@ -4814,6 +4817,10 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, static void igb_set_rx_buffer_len(struct igb_adapter *adapter, struct igb_ring *rx_ring) { +#if (PAGE_SIZE < 8192) + struct e1000_hw *hw = &adapter->hw; +#endif + /* set build_skb and buffer size flags */ clear_ring_build_skb_enabled(rx_ring); clear_ring_uses_large_buffer(rx_ring); @@ -4824,10 +4831,9 @@ static void igb_set_rx_buffer_len(struct igb_adapter *adapter, set_ring_build_skb_enabled(rx_ring); #if (PAGE_SIZE < 8192) - if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB) - return; - - set_ring_uses_large_buffer(rx_ring); + if (adapter->max_frame_size > IGB_MAX_FRAME_BUILD_SKB || + rd32(E1000_RCTL) & E1000_RCTL_SBP) + set_ring_uses_large_buffer(rx_ring); #endif } @@ -7850,8 +7856,8 @@ static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf, { struct pci_dev *pdev = adapter->pdev; struct vf_data_storage *vf_data = &adapter->vf_data[vf]; - struct list_head *pos; - struct vf_mac_filter *entry = NULL; + struct vf_mac_filter *entry; + bool found = false; int ret = 0; if ((vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) && @@ -7871,8 +7877,7 @@ static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf, switch (info) { case E1000_VF_MAC_FILTER_CLR: /* remove all unicast MAC filters related to the current VF */ - list_for_each(pos, &adapter->vf_macs.l) { - entry = list_entry(pos, struct vf_mac_filter, l); + list_for_each_entry(entry, &adapter->vf_macs.l, l) { if (entry->vf == vf) { entry->vf = -1; entry->free = true; @@ -7882,13 +7887,14 @@ static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf, break; case E1000_VF_MAC_FILTER_ADD: /* try to find empty slot in the list */ - list_for_each(pos, &adapter->vf_macs.l) { - entry = list_entry(pos, struct vf_mac_filter, l); - if (entry->free) + list_for_each_entry(entry, &adapter->vf_macs.l, l) { + if (entry->free) { + found = true; break; + } } - if (entry && entry->free) { + if (found) { entry->free = false; entry->vf = vf; ether_addr_copy(entry->vf_mac, addr); diff --git a/drivers/net/ethernet/intel/igbvf/igbvf.h b/drivers/net/ethernet/intel/igbvf/igbvf.h index 57d39ee00b58..7b83678ba83a 100644 --- a/drivers/net/ethernet/intel/igbvf/igbvf.h +++ b/drivers/net/ethernet/intel/igbvf/igbvf.h @@ -39,11 +39,11 @@ enum latency_range { /* Tx/Rx descriptor defines */ #define IGBVF_DEFAULT_TXD 256 #define IGBVF_MAX_TXD 4096 -#define IGBVF_MIN_TXD 80 +#define IGBVF_MIN_TXD 64 #define IGBVF_DEFAULT_RXD 256 #define IGBVF_MAX_RXD 4096 -#define IGBVF_MIN_RXD 80 +#define IGBVF_MIN_RXD 64 #define IGBVF_MIN_ITR_USECS 10 /* 100000 irq/sec */ #define IGBVF_MAX_ITR_USECS 10000 /* 100 irq/sec */ diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 7ff2752dd763..fd712585af27 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -2785,7 +2785,7 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) igbvf_set_ethtool_ops(netdev); netdev->watchdog_timeo = 5 * HZ; - strncpy(netdev->name, pci_name(pdev), sizeof(netdev->name) - 1); + strscpy(netdev->name, pci_name(pdev), sizeof(netdev->name)); adapter->bd_number = cards_found++; diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 38901d2a4680..f48f82d5e274 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -15,6 +15,7 @@ #include <linux/net_tstamp.h> #include <linux/bitfield.h> #include <linux/hrtimer.h> +#include <net/xdp.h> #include "igc_hw.h" @@ -37,6 +38,8 @@ void igc_ethtool_set_ops(struct net_device *); #define MAX_FLEX_FILTER 32 +#define IGC_MAX_TX_TSTAMP_REGS 4 + enum igc_mac_filter_type { IGC_MAC_FILTER_TYPE_DST = 0, IGC_MAC_FILTER_TYPE_SRC @@ -69,6 +72,15 @@ struct igc_rx_packet_stats { u64 other_packets; }; +struct igc_tx_timestamp_request { + struct sk_buff *skb; /* reference to the packet being timestamped */ + unsigned long start; /* when the tstamp request started (jiffies) */ + u32 mask; /* _TSYNCTXCTL_TXTT_{X} bit for this request */ + u32 regl; /* which TXSTMPL_{X} register should be used */ + u32 regh; /* which TXSTMPH_{X} register should be used */ + u32 flags; /* flags that should be added to the tx_buffer */ +}; + struct igc_ring_container { struct igc_ring *ring; /* pointer to linked list of rings */ unsigned int total_bytes; /* total bytes processed this int */ @@ -244,9 +256,8 @@ struct igc_adapter { * ptp_tx_lock. */ spinlock_t ptp_tx_lock; - struct sk_buff *ptp_tx_skb; + struct igc_tx_timestamp_request tx_tstamp[IGC_MAX_TX_TSTAMP_REGS]; struct hwtstamp_config tstamp_config; - unsigned long ptp_tx_start; unsigned int ptp_flags; /* System time value lock */ spinlock_t tmreg_lock; @@ -368,11 +379,11 @@ static inline u32 igc_rss_type(const union igc_adv_rx_desc *rx_desc) /* TX/RX descriptor defines */ #define IGC_DEFAULT_TXD 256 #define IGC_DEFAULT_TX_WORK 128 -#define IGC_MIN_TXD 80 +#define IGC_MIN_TXD 64 #define IGC_MAX_TXD 4096 #define IGC_DEFAULT_RXD 256 -#define IGC_MIN_RXD 80 +#define IGC_MIN_RXD 64 #define IGC_MAX_RXD 4096 /* Supported Rx Buffer Sizes */ @@ -454,6 +465,10 @@ enum igc_tx_flags { /* olinfo flags */ IGC_TX_FLAGS_IPV4 = 0x10, IGC_TX_FLAGS_CSUM = 0x20, + + IGC_TX_FLAGS_TSTAMP_1 = 0x100, + IGC_TX_FLAGS_TSTAMP_2 = 0x200, + IGC_TX_FLAGS_TSTAMP_3 = 0x400, }; enum igc_boards { diff --git a/drivers/net/ethernet/intel/igc/igc_base.h b/drivers/net/ethernet/intel/igc/igc_base.h index 9f3827eda157..f7d6491d4c60 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.h +++ b/drivers/net/ethernet/intel/igc/igc_base.h @@ -34,6 +34,9 @@ struct igc_adv_tx_context_desc { /* Adv Transmit Descriptor Config Masks */ #define IGC_ADVTXD_MAC_TSTAMP 0x00080000 /* IEEE1588 Timestamp packet */ +#define IGC_ADVTXD_TSTAMP_REG_1 0x00010000 /* Select register 1 for timestamp */ +#define IGC_ADVTXD_TSTAMP_REG_2 0x00020000 /* Select register 2 for timestamp */ +#define IGC_ADVTXD_TSTAMP_REG_3 0x00030000 /* Select register 3 for timestamp */ #define IGC_ADVTXD_DTYP_CTXT 0x00200000 /* Advanced Context Descriptor */ #define IGC_ADVTXD_DTYP_DATA 0x00300000 /* Advanced Data Descriptor */ #define IGC_ADVTXD_DCMD_EOP 0x01000000 /* End of Packet */ diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index 2f780cc90883..b3037016f31d 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -454,6 +454,9 @@ /* Time Sync Transmit Control bit definitions */ #define IGC_TSYNCTXCTL_TXTT_0 0x00000001 /* Tx timestamp reg 0 valid */ +#define IGC_TSYNCTXCTL_TXTT_1 0x00000002 /* Tx timestamp reg 1 valid */ +#define IGC_TSYNCTXCTL_TXTT_2 0x00000004 /* Tx timestamp reg 2 valid */ +#define IGC_TSYNCTXCTL_TXTT_3 0x00000008 /* Tx timestamp reg 3 valid */ #define IGC_TSYNCTXCTL_ENABLED 0x00000010 /* enable Tx timestamping */ #define IGC_TSYNCTXCTL_MAX_ALLOWED_DLY_MASK 0x0000F000 /* max delay */ #define IGC_TSYNCTXCTL_SYNC_COMP_ERR 0x20000000 /* sync err */ @@ -461,6 +464,10 @@ #define IGC_TSYNCTXCTL_START_SYNC 0x80000000 /* initiate sync */ #define IGC_TSYNCTXCTL_TXSYNSIG 0x00000020 /* Sample TX tstamp in PHY sop */ +#define IGC_TSYNCTXCTL_TXTT_ANY ( \ + IGC_TSYNCTXCTL_TXTT_0 | IGC_TSYNCTXCTL_TXTT_1 | \ + IGC_TSYNCTXCTL_TXTT_2 | IGC_TSYNCTXCTL_TXTT_3) + /* Timer selection bits */ #define IGC_AUX_IO_TIMER_SEL_SYSTIM0 (0u << 30) /* Select SYSTIM0 for auxiliary time stamp */ #define IGC_AUX_IO_TIMER_SEL_SYSTIM1 (1u << 30) /* Select SYSTIM1 for auxiliary time stamp */ @@ -549,7 +556,7 @@ #define IGC_PTM_CTRL_SHRT_CYC(usec) (((usec) & 0x3f) << 2) #define IGC_PTM_CTRL_PTM_TO(usec) (((usec) & 0xff) << 8) -#define IGC_PTM_SHORT_CYC_DEFAULT 10 /* Default Short/interrupted cycle interval */ +#define IGC_PTM_SHORT_CYC_DEFAULT 1 /* Default short cycle interval */ #define IGC_PTM_CYC_TIME_DEFAULT 5 /* Default PTM cycle time */ #define IGC_PTM_TIMEOUT_DEFAULT 255 /* Default timeout for PTM errors */ diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index 93bce729be76..785eaa8e0ba8 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -773,9 +773,10 @@ static void igc_ethtool_get_strings(struct net_device *netdev, u32 stringset, break; case ETH_SS_STATS: for (i = 0; i < IGC_GLOBAL_STATS_LEN; i++) - ethtool_sprintf(&p, igc_gstrings_stats[i].stat_string); + ethtool_sprintf(&p, "%s", + igc_gstrings_stats[i].stat_string); for (i = 0; i < IGC_NETDEV_STATS_LEN; i++) - ethtool_sprintf(&p, + ethtool_sprintf(&p, "%s", igc_gstrings_net_stats[i].stat_string); for (i = 0; i < adapter->num_tx_queues; i++) { ethtool_sprintf(&p, "tx_queue_%u_packets", i); @@ -868,6 +869,18 @@ static void igc_ethtool_get_stats(struct net_device *netdev, spin_unlock(&adapter->stats64_lock); } +static int igc_ethtool_get_previous_rx_coalesce(struct igc_adapter *adapter) +{ + return (adapter->rx_itr_setting <= 3) ? + adapter->rx_itr_setting : adapter->rx_itr_setting >> 2; +} + +static int igc_ethtool_get_previous_tx_coalesce(struct igc_adapter *adapter) +{ + return (adapter->tx_itr_setting <= 3) ? + adapter->tx_itr_setting : adapter->tx_itr_setting >> 2; +} + static int igc_ethtool_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec, struct kernel_ethtool_coalesce *kernel_coal, @@ -875,17 +888,8 @@ static int igc_ethtool_get_coalesce(struct net_device *netdev, { struct igc_adapter *adapter = netdev_priv(netdev); - if (adapter->rx_itr_setting <= 3) - ec->rx_coalesce_usecs = adapter->rx_itr_setting; - else - ec->rx_coalesce_usecs = adapter->rx_itr_setting >> 2; - - if (!(adapter->flags & IGC_FLAG_QUEUE_PAIRS)) { - if (adapter->tx_itr_setting <= 3) - ec->tx_coalesce_usecs = adapter->tx_itr_setting; - else - ec->tx_coalesce_usecs = adapter->tx_itr_setting >> 2; - } + ec->rx_coalesce_usecs = igc_ethtool_get_previous_rx_coalesce(adapter); + ec->tx_coalesce_usecs = igc_ethtool_get_previous_tx_coalesce(adapter); return 0; } @@ -910,8 +914,12 @@ static int igc_ethtool_set_coalesce(struct net_device *netdev, ec->tx_coalesce_usecs == 2) return -EINVAL; - if ((adapter->flags & IGC_FLAG_QUEUE_PAIRS) && ec->tx_coalesce_usecs) + if ((adapter->flags & IGC_FLAG_QUEUE_PAIRS) && + ec->tx_coalesce_usecs != igc_ethtool_get_previous_tx_coalesce(adapter)) { + NL_SET_ERR_MSG_MOD(extack, + "Queue Pair mode enabled, both Rx and Tx coalescing controlled by rx-usecs"); return -EINVAL; + } /* If ITR is disabled, disable DMAC */ if (ec->rx_coalesce_usecs == 0) { @@ -1810,7 +1818,7 @@ igc_ethtool_set_link_ksettings(struct net_device *netdev, struct igc_adapter *adapter = netdev_priv(netdev); struct net_device *dev = adapter->netdev; struct igc_hw *hw = &adapter->hw; - u32 advertising; + u16 advertised = 0; /* When adapter in resetting mode, autoneg/speed/duplex * cannot be changed @@ -1835,18 +1843,33 @@ igc_ethtool_set_link_ksettings(struct net_device *netdev, while (test_and_set_bit(__IGC_RESETTING, &adapter->state)) usleep_range(1000, 2000); - ethtool_convert_link_mode_to_legacy_u32(&advertising, - cmd->link_modes.advertising); - /* Converting to legacy u32 drops ETHTOOL_LINK_MODE_2500baseT_Full_BIT. - * We have to check this and convert it to ADVERTISE_2500_FULL - * (aka ETHTOOL_LINK_MODE_2500baseX_Full_BIT) explicitly. - */ - if (ethtool_link_ksettings_test_link_mode(cmd, advertising, 2500baseT_Full)) - advertising |= ADVERTISE_2500_FULL; + if (ethtool_link_ksettings_test_link_mode(cmd, advertising, + 2500baseT_Full)) + advertised |= ADVERTISE_2500_FULL; + + if (ethtool_link_ksettings_test_link_mode(cmd, advertising, + 1000baseT_Full)) + advertised |= ADVERTISE_1000_FULL; + + if (ethtool_link_ksettings_test_link_mode(cmd, advertising, + 100baseT_Full)) + advertised |= ADVERTISE_100_FULL; + + if (ethtool_link_ksettings_test_link_mode(cmd, advertising, + 100baseT_Half)) + advertised |= ADVERTISE_100_HALF; + + if (ethtool_link_ksettings_test_link_mode(cmd, advertising, + 10baseT_Full)) + advertised |= ADVERTISE_10_FULL; + + if (ethtool_link_ksettings_test_link_mode(cmd, advertising, + 10baseT_Half)) + advertised |= ADVERTISE_10_HALF; if (cmd->base.autoneg == AUTONEG_ENABLE) { hw->mac.autoneg = 1; - hw->phy.autoneg_advertised = advertising; + hw->phy.autoneg_advertised = advertised; if (adapter->fc_autoneg) hw->fc.requested_mode = igc_fc_default; } else { diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 6f557e843e49..e9bb403bbacf 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -1271,10 +1271,21 @@ static u32 igc_tx_cmd_type(struct sk_buff *skb, u32 tx_flags) cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSO, (IGC_ADVTXD_DCMD_TSE)); - /* set timestamp bit if present */ + /* set timestamp bit if present, will select the register set + * based on the _TSTAMP(_X) bit. + */ cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSTAMP, (IGC_ADVTXD_MAC_TSTAMP)); + cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSTAMP_1, + (IGC_ADVTXD_TSTAMP_REG_1)); + + cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSTAMP_2, + (IGC_ADVTXD_TSTAMP_REG_2)); + + cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSTAMP_3, + (IGC_ADVTXD_TSTAMP_REG_3)); + /* insert frame checksum */ cmd_type ^= IGC_SET_FLAG(skb->no_fcs, 1, IGC_ADVTXD_DCMD_IFCS); @@ -1533,6 +1544,26 @@ static int igc_tso(struct igc_ring *tx_ring, return 1; } +static bool igc_request_tx_tstamp(struct igc_adapter *adapter, struct sk_buff *skb, u32 *flags) +{ + int i; + + for (i = 0; i < IGC_MAX_TX_TSTAMP_REGS; i++) { + struct igc_tx_timestamp_request *tstamp = &adapter->tx_tstamp[i]; + + if (tstamp->skb) + continue; + + tstamp->skb = skb_get(skb); + tstamp->start = jiffies; + *flags = tstamp->flags; + + return true; + } + + return false; +} + static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, struct igc_ring *tx_ring) { @@ -1614,14 +1645,12 @@ done: * timestamping request. */ unsigned long flags; + u32 tstamp_flags; spin_lock_irqsave(&adapter->ptp_tx_lock, flags); - if (!adapter->ptp_tx_skb) { + if (igc_request_tx_tstamp(adapter, skb, &tstamp_flags)) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; - tx_flags |= IGC_TX_FLAGS_TSTAMP; - - adapter->ptp_tx_skb = skb_get(skb); - adapter->ptp_tx_start = jiffies; + tx_flags |= IGC_TX_FLAGS_TSTAMP | tstamp_flags; } else { adapter->tx_hwtstamp_skipped++; } @@ -6162,6 +6191,26 @@ static int igc_tsn_clear_schedule(struct igc_adapter *adapter) return 0; } +static void igc_taprio_stats(struct net_device *dev, + struct tc_taprio_qopt_stats *stats) +{ + /* When Strict_End is enabled, the tx_overruns counter + * will always be zero. + */ + stats->tx_overruns = 0; +} + +static void igc_taprio_queue_stats(struct net_device *dev, + struct tc_taprio_qopt_queue_stats *queue_stats) +{ + struct tc_taprio_qopt_stats *stats = &queue_stats->stats; + + /* When Strict_End is enabled, the tx_overruns counter + * will always be zero. + */ + stats->tx_overruns = 0; +} + static int igc_save_qbv_schedule(struct igc_adapter *adapter, struct tc_taprio_qopt_offload *qopt) { @@ -6173,11 +6222,20 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, size_t n; int i; - if (qopt->cmd == TAPRIO_CMD_DESTROY) + switch (qopt->cmd) { + case TAPRIO_CMD_REPLACE: + break; + case TAPRIO_CMD_DESTROY: return igc_tsn_clear_schedule(adapter); - - if (qopt->cmd != TAPRIO_CMD_REPLACE) + case TAPRIO_CMD_STATS: + igc_taprio_stats(adapter->netdev, &qopt->stats); + return 0; + case TAPRIO_CMD_QUEUE_STATS: + igc_taprio_queue_stats(adapter->netdev, &qopt->queue_stats); + return 0; + default: return -EOPNOTSUPP; + } if (qopt->base_time < 0) return -ERANGE; @@ -6433,7 +6491,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, struct igc_ring *ring; int i, drops; - if (unlikely(test_bit(__IGC_DOWN, &adapter->state))) + if (unlikely(!netif_carrier_ok(dev))) return -ENETDOWN; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) @@ -6877,7 +6935,7 @@ static int igc_probe(struct pci_dev *pdev, */ igc_get_hw_control(adapter); - strncpy(netdev->name, "eth%d", IFNAMSIZ); + strscpy(netdev->name, "eth%d", sizeof(netdev->name)); err = register_netdev(netdev); if (err) goto err_register; diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index f0b979a70655..928f38792203 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -558,11 +558,16 @@ static void igc_ptp_enable_rx_timestamp(struct igc_adapter *adapter) static void igc_ptp_clear_tx_tstamp(struct igc_adapter *adapter) { unsigned long flags; + int i; spin_lock_irqsave(&adapter->ptp_tx_lock, flags); - dev_kfree_skb_any(adapter->ptp_tx_skb); - adapter->ptp_tx_skb = NULL; + for (i = 0; i < IGC_MAX_TX_TSTAMP_REGS; i++) { + struct igc_tx_timestamp_request *tstamp = &adapter->tx_tstamp[i]; + + dev_kfree_skb_any(tstamp->skb); + tstamp->skb = NULL; + } spin_unlock_irqrestore(&adapter->ptp_tx_lock, flags); } @@ -659,61 +664,106 @@ static int igc_ptp_set_timestamp_mode(struct igc_adapter *adapter, } /* Requires adapter->ptp_tx_lock held by caller. */ -static void igc_ptp_tx_timeout(struct igc_adapter *adapter) +static void igc_ptp_tx_timeout(struct igc_adapter *adapter, + struct igc_tx_timestamp_request *tstamp) { - struct igc_hw *hw = &adapter->hw; - - dev_kfree_skb_any(adapter->ptp_tx_skb); - adapter->ptp_tx_skb = NULL; + dev_kfree_skb_any(tstamp->skb); + tstamp->skb = NULL; adapter->tx_hwtstamp_timeouts++; - /* Clear the tx valid bit in TSYNCTXCTL register to enable interrupt. */ - rd32(IGC_TXSTMPH); + netdev_warn(adapter->netdev, "Tx timestamp timeout\n"); } void igc_ptp_tx_hang(struct igc_adapter *adapter) { + struct igc_tx_timestamp_request *tstamp; + struct igc_hw *hw = &adapter->hw; unsigned long flags; + bool found = false; + int i; spin_lock_irqsave(&adapter->ptp_tx_lock, flags); - if (!adapter->ptp_tx_skb) - goto unlock; + for (i = 0; i < IGC_MAX_TX_TSTAMP_REGS; i++) { + tstamp = &adapter->tx_tstamp[i]; + + if (!tstamp->skb) + continue; - if (time_is_after_jiffies(adapter->ptp_tx_start + IGC_PTP_TX_TIMEOUT)) - goto unlock; + if (time_is_after_jiffies(tstamp->start + IGC_PTP_TX_TIMEOUT)) + continue; - igc_ptp_tx_timeout(adapter); + igc_ptp_tx_timeout(adapter, tstamp); + found = true; + } + + if (found) { + /* Reading the high register of the first set of timestamp registers + * clears all the equivalent bits in the TSYNCTXCTL register. + */ + rd32(IGC_TXSTMPH_0); + } -unlock: spin_unlock_irqrestore(&adapter->ptp_tx_lock, flags); } +static void igc_ptp_tx_reg_to_stamp(struct igc_adapter *adapter, + struct igc_tx_timestamp_request *tstamp, u64 regval) +{ + struct skb_shared_hwtstamps shhwtstamps; + struct sk_buff *skb; + int adjust = 0; + + skb = tstamp->skb; + if (!skb) + return; + + if (igc_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval)) + return; + + switch (adapter->link_speed) { + case SPEED_10: + adjust = IGC_I225_TX_LATENCY_10; + break; + case SPEED_100: + adjust = IGC_I225_TX_LATENCY_100; + break; + case SPEED_1000: + adjust = IGC_I225_TX_LATENCY_1000; + break; + case SPEED_2500: + adjust = IGC_I225_TX_LATENCY_2500; + break; + } + + shhwtstamps.hwtstamp = + ktime_add_ns(shhwtstamps.hwtstamp, adjust); + + tstamp->skb = NULL; + + skb_tstamp_tx(skb, &shhwtstamps); + dev_kfree_skb_any(skb); +} + /** * igc_ptp_tx_hwtstamp - utility function which checks for TX time stamp * @adapter: Board private structure * - * If we were asked to do hardware stamping and such a time stamp is - * available, then it must have been for this skb here because we only - * allow only one such packet into the queue. + * Check against the ready mask for which of the timestamp register + * sets are ready to be retrieved, then retrieve that and notify the + * rest of the stack. * * Context: Expects adapter->ptp_tx_lock to be held by caller. */ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) { - struct sk_buff *skb = adapter->ptp_tx_skb; - struct skb_shared_hwtstamps shhwtstamps; struct igc_hw *hw = &adapter->hw; - u32 tsynctxctl; - int adjust = 0; u64 regval; + u32 mask; + int i; - if (WARN_ON_ONCE(!skb)) - return; - - tsynctxctl = rd32(IGC_TSYNCTXCTL); - tsynctxctl &= IGC_TSYNCTXCTL_TXTT_0; - if (tsynctxctl) { + mask = rd32(IGC_TSYNCTXCTL) & IGC_TSYNCTXCTL_TXTT_ANY; + if (mask & IGC_TSYNCTXCTL_TXTT_0) { regval = rd32(IGC_TXSTMPL); regval |= (u64)rd32(IGC_TXSTMPH) << 32; } else { @@ -742,37 +792,30 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) txstmpl_new = rd32(IGC_TXSTMPL); if (txstmpl_old == txstmpl_new) - return; + goto done; regval = txstmpl_new; regval |= (u64)rd32(IGC_TXSTMPH) << 32; } - if (igc_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval)) - return; - switch (adapter->link_speed) { - case SPEED_10: - adjust = IGC_I225_TX_LATENCY_10; - break; - case SPEED_100: - adjust = IGC_I225_TX_LATENCY_100; - break; - case SPEED_1000: - adjust = IGC_I225_TX_LATENCY_1000; - break; - case SPEED_2500: - adjust = IGC_I225_TX_LATENCY_2500; - break; - } + igc_ptp_tx_reg_to_stamp(adapter, &adapter->tx_tstamp[0], regval); - shhwtstamps.hwtstamp = - ktime_add_ns(shhwtstamps.hwtstamp, adjust); +done: + /* Now that the problematic first register was handled, we can + * use retrieve the timestamps from the other registers + * (starting from '1') with less complications. + */ + for (i = 1; i < IGC_MAX_TX_TSTAMP_REGS; i++) { + struct igc_tx_timestamp_request *tstamp = &adapter->tx_tstamp[i]; - adapter->ptp_tx_skb = NULL; + if (!(tstamp->mask & mask)) + continue; - /* Notify the stack and free the skb after we've unlocked */ - skb_tstamp_tx(skb, &shhwtstamps); - dev_kfree_skb_any(skb); + regval = rd32(tstamp->regl); + regval |= (u64)rd32(tstamp->regh) << 32; + + igc_ptp_tx_reg_to_stamp(adapter, tstamp, regval); + } } /** @@ -788,12 +831,8 @@ void igc_ptp_tx_tstamp_event(struct igc_adapter *adapter) spin_lock_irqsave(&adapter->ptp_tx_lock, flags); - if (!adapter->ptp_tx_skb) - goto unlock; - igc_ptp_tx_hwtstamp(adapter); -unlock: spin_unlock_irqrestore(&adapter->ptp_tx_lock, flags); } @@ -1006,9 +1045,34 @@ static int igc_ptp_getcrosststamp(struct ptp_clock_info *ptp, void igc_ptp_init(struct igc_adapter *adapter) { struct net_device *netdev = adapter->netdev; + struct igc_tx_timestamp_request *tstamp; struct igc_hw *hw = &adapter->hw; int i; + tstamp = &adapter->tx_tstamp[0]; + tstamp->mask = IGC_TSYNCTXCTL_TXTT_0; + tstamp->regl = IGC_TXSTMPL_0; + tstamp->regh = IGC_TXSTMPH_0; + tstamp->flags = 0; + + tstamp = &adapter->tx_tstamp[1]; + tstamp->mask = IGC_TSYNCTXCTL_TXTT_1; + tstamp->regl = IGC_TXSTMPL_1; + tstamp->regh = IGC_TXSTMPH_1; + tstamp->flags = IGC_TX_FLAGS_TSTAMP_1; + + tstamp = &adapter->tx_tstamp[2]; + tstamp->mask = IGC_TSYNCTXCTL_TXTT_2; + tstamp->regl = IGC_TXSTMPL_2; + tstamp->regh = IGC_TXSTMPH_2; + tstamp->flags = IGC_TX_FLAGS_TSTAMP_2; + + tstamp = &adapter->tx_tstamp[3]; + tstamp->mask = IGC_TSYNCTXCTL_TXTT_3; + tstamp->regl = IGC_TXSTMPL_3; + tstamp->regh = IGC_TXSTMPH_3; + tstamp->flags = IGC_TX_FLAGS_TSTAMP_3; + switch (hw->mac.type) { case igc_i225: for (i = 0; i < IGC_N_SDP; i++) { diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h index dba5a5759b1c..20e17f5fbce3 100644 --- a/drivers/net/ethernet/intel/igc/igc_regs.h +++ b/drivers/net/ethernet/intel/igc/igc_regs.h @@ -243,6 +243,18 @@ #define IGC_SYSTIMR 0x0B6F8 /* System time register Residue */ #define IGC_TIMINCA 0x0B608 /* Increment attributes register - RW */ +/* TX Timestamp Low */ +#define IGC_TXSTMPL_0 0x0B618 +#define IGC_TXSTMPL_1 0x0B698 +#define IGC_TXSTMPL_2 0x0B6B8 +#define IGC_TXSTMPL_3 0x0B6D8 + +/* TX Timestamp High */ +#define IGC_TXSTMPH_0 0x0B61C +#define IGC_TXSTMPH_1 0x0B69C +#define IGC_TXSTMPH_2 0x0B6BC +#define IGC_TXSTMPH_3 0x0B6DC + #define IGC_TXSTMPL 0x0B618 /* Tx timestamp value Low - RO */ #define IGC_TXSTMPH 0x0B61C /* Tx timestamp value High - RO */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 63d4e32df029..b6f0376e42f4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -945,8 +945,6 @@ void ixgbe_update_pf_promisc_vlvf(struct ixgbe_adapter *adapter, u32 vid); void ixgbe_clear_interrupt_scheme(struct ixgbe_adapter *adapter); netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *, struct ixgbe_adapter *, struct ixgbe_ring *); -void ixgbe_unmap_and_free_tx_resource(struct ixgbe_ring *, - struct ixgbe_tx_buffer *); void ixgbe_alloc_rx_buffers(struct ixgbe_ring *, u16); void ixgbe_write_eitr(struct ixgbe_q_vector *); int ixgbe_poll(struct napi_struct *napi, int budget); @@ -997,10 +995,6 @@ int ixgbe_setup_fcoe_ddp_resources(struct ixgbe_adapter *adapter); void ixgbe_free_fcoe_ddp_resources(struct ixgbe_adapter *adapter); int ixgbe_fcoe_enable(struct net_device *netdev); int ixgbe_fcoe_disable(struct net_device *netdev); -#ifdef CONFIG_IXGBE_DCB -u8 ixgbe_fcoe_getapp(struct ixgbe_adapter *adapter); -u8 ixgbe_fcoe_setapp(struct ixgbe_adapter *adapter, u8 up); -#endif /* CONFIG_IXGBE_DCB */ int ixgbe_fcoe_get_wwn(struct net_device *netdev, u64 *wwn, int type); int ixgbe_fcoe_get_hbainfo(struct net_device *netdev, struct netdev_fcoe_hbainfo *info); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h index 4b531e8ae38a..34761e691d52 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h @@ -8,7 +8,6 @@ #include "ixgbe.h" u16 ixgbe_get_pcie_msix_count_generic(struct ixgbe_hw *hw); -s32 ixgbe_init_ops_generic(struct ixgbe_hw *hw); s32 ixgbe_init_hw_generic(struct ixgbe_hw *hw); s32 ixgbe_start_hw_generic(struct ixgbe_hw *hw); s32 ixgbe_start_hw_gen2(struct ixgbe_hw *hw); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 0bbad4a5cc2f..4dd897806fa5 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -1413,11 +1413,11 @@ static void ixgbe_get_strings(struct net_device *netdev, u32 stringset, switch (stringset) { case ETH_SS_TEST: for (i = 0; i < IXGBE_TEST_LEN; i++) - ethtool_sprintf(&p, ixgbe_gstrings_test[i]); + ethtool_sprintf(&p, "%s", ixgbe_gstrings_test[i]); break; case ETH_SS_STATS: for (i = 0; i < IXGBE_GLOBAL_STATS_LEN; i++) - ethtool_sprintf(&p, + ethtool_sprintf(&p, "%s", ixgbe_gstrings_stats[i].stat_string); for (i = 0; i < netdev->num_tx_queues; i++) { ethtool_sprintf(&p, "tx_queue_%u_packets", i); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 8eb9839a3ca6..94bde2cad0f4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2421,7 +2421,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, } if (xdp_xmit & IXGBE_XDP_REDIR) - xdp_do_flush_map(); + xdp_do_flush(); if (xdp_xmit & IXGBE_XDP_TX) { struct ixgbe_ring *ring = ixgbe_determine_xdp_ring(adapter); @@ -10042,9 +10042,6 @@ static int ixgbe_ndo_bridge_setlink(struct net_device *dev, if (nla_type(attr) != IFLA_BRIDGE_MODE) continue; - if (nla_len(attr) < sizeof(mode)) - return -EINVAL; - mode = nla_get_u16(attr); status = ixgbe_configure_bridge_mode(adapter, mode); if (status) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index 0310af851086..9339edbd9082 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -979,6 +979,7 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter, u32 tsync_tx_ctl = IXGBE_TSYNCTXCTL_ENABLED; u32 tsync_rx_ctl = IXGBE_TSYNCRXCTL_ENABLED; u32 tsync_rx_mtrl = PTP_EV_PORT << 16; + u32 aflags = adapter->flags; bool is_l2 = false; u32 regval; @@ -996,20 +997,20 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter, case HWTSTAMP_FILTER_NONE: tsync_rx_ctl = 0; tsync_rx_mtrl = 0; - adapter->flags &= ~(IXGBE_FLAG_RX_HWTSTAMP_ENABLED | - IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); + aflags &= ~(IXGBE_FLAG_RX_HWTSTAMP_ENABLED | + IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); break; case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L4_V1; tsync_rx_mtrl |= IXGBE_RXMTRL_V1_SYNC_MSG; - adapter->flags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED | - IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); + aflags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED | + IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); break; case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L4_V1; tsync_rx_mtrl |= IXGBE_RXMTRL_V1_DELAY_REQ_MSG; - adapter->flags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED | - IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); + aflags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED | + IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); break; case HWTSTAMP_FILTER_PTP_V2_EVENT: case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: @@ -1023,8 +1024,8 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter, tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_EVENT_V2; is_l2 = true; config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; - adapter->flags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED | - IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); + aflags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED | + IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); break; case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: case HWTSTAMP_FILTER_NTP_ALL: @@ -1035,7 +1036,7 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter, if (hw->mac.type >= ixgbe_mac_X550) { tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_ALL; config->rx_filter = HWTSTAMP_FILTER_ALL; - adapter->flags |= IXGBE_FLAG_RX_HWTSTAMP_ENABLED; + aflags |= IXGBE_FLAG_RX_HWTSTAMP_ENABLED; break; } fallthrough; @@ -1046,8 +1047,6 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter, * Delay_Req messages and hardware does not support * timestamping all packets => return error */ - adapter->flags &= ~(IXGBE_FLAG_RX_HWTSTAMP_ENABLED | - IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); config->rx_filter = HWTSTAMP_FILTER_NONE; return -ERANGE; } @@ -1079,8 +1078,8 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter, IXGBE_TSYNCRXCTL_TYPE_ALL | IXGBE_TSYNCRXCTL_TSIP_UT_EN; config->rx_filter = HWTSTAMP_FILTER_ALL; - adapter->flags |= IXGBE_FLAG_RX_HWTSTAMP_ENABLED; - adapter->flags &= ~IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER; + aflags |= IXGBE_FLAG_RX_HWTSTAMP_ENABLED; + aflags &= ~IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER; is_l2 = true; break; default: @@ -1113,6 +1112,9 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter, IXGBE_WRITE_FLUSH(hw); + /* configure adapter flags only when HW is actually configured */ + adapter->flags = aflags; + /* clear TX/RX time stamp registers, just to be sure */ ixgbe_ptp_clear_tx_timestamp(adapter); IXGBE_READ_REG(hw, IXGBE_RXSTMPH); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 29cc60988071..9cfdfa8a4355 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -28,6 +28,9 @@ static inline void ixgbe_alloc_vf_macvlans(struct ixgbe_adapter *adapter, struct vf_macvlans *mv_list; int num_vf_macvlans, i; + /* Initialize list of VF macvlans */ + INIT_LIST_HEAD(&adapter->vf_mvs.l); + num_vf_macvlans = hw->mac.num_rar_entries - (IXGBE_MAX_PF_MACVLANS + 1 + num_vfs); if (!num_vf_macvlans) @@ -36,8 +39,6 @@ static inline void ixgbe_alloc_vf_macvlans(struct ixgbe_adapter *adapter, mv_list = kcalloc(num_vf_macvlans, sizeof(struct vf_macvlans), GFP_KERNEL); if (mv_list) { - /* Initialize list of VF macvlans */ - INIT_LIST_HEAD(&adapter->vf_mvs.l); for (i = 0; i < num_vf_macvlans; i++) { mv_list[i].vf = -1; mv_list[i].free = true; @@ -639,12 +640,11 @@ static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter, int vf, int index, unsigned char *mac_addr) { struct vf_macvlans *entry; - struct list_head *pos; + bool found = false; int retval = 0; if (index <= 1) { - list_for_each(pos, &adapter->vf_mvs.l) { - entry = list_entry(pos, struct vf_macvlans, l); + list_for_each_entry(entry, &adapter->vf_mvs.l, l) { if (entry->vf == vf) { entry->vf = -1; entry->free = true; @@ -662,23 +662,22 @@ static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter, if (!index) return 0; - entry = NULL; - - list_for_each(pos, &adapter->vf_mvs.l) { - entry = list_entry(pos, struct vf_macvlans, l); - if (entry->free) + list_for_each_entry(entry, &adapter->vf_mvs.l, l) { + if (entry->free) { + found = true; break; + } } /* * If we traversed the entire list and didn't find a free entry - * then we're out of space on the RAR table. Also entry may - * be NULL because the original memory allocation for the list - * failed, which is not fatal but does mean we can't support - * VF requests for MACVLAN because we couldn't allocate - * memory for the list management required. + * then we're out of space on the RAR table. It's also possible + * for the &adapter->vf_mvs.l list to be empty because the original + * memory allocation for the list failed, which is not fatal but does + * mean we can't support VF requests for MACVLAN because we couldn't + * allocate memory for the list management required. */ - if (!entry || !entry->free) + if (!found) return -ENOSPC; retval = ixgbe_add_mac_filter(adapter, mac_addr, vf); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index 1703c640a434..59798bc33298 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -351,7 +351,7 @@ construct_skb: } if (xdp_xmit & IXGBE_XDP_REDIR) - xdp_do_flush_map(); + xdp_do_flush(); if (xdp_xmit & IXGBE_XDP_TX) { struct ixgbe_ring *ring = ixgbe_determine_xdp_ring(adapter); diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h index 149c733fcc2b..130cb868774c 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h @@ -486,9 +486,6 @@ static inline int ixgbevf_ipsec_tx(struct ixgbevf_ring *tx_ring, { return 0; } #endif /* CONFIG_IXGBEVF_IPSEC */ -void ixgbe_napi_add_all(struct ixgbevf_adapter *adapter); -void ixgbe_napi_del_all(struct ixgbevf_adapter *adapter); - #define ixgbevf_hw_to_netdev(hw) \ (((struct ixgbevf_adapter *)(hw)->back)->netdev) |