diff options
Diffstat (limited to 'drivers/net/ethernet/intel')
261 files changed, 38778 insertions, 13549 deletions
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index 639fbb12bd35..5a331c1c76cb 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -16,6 +16,9 @@ config NET_VENDOR_INTEL if NET_VENDOR_INTEL +source "drivers/net/ethernet/intel/libeth/Kconfig" +source "drivers/net/ethernet/intel/libie/Kconfig" + config E100 tristate "Intel(R) PRO/100+ support" depends on PCI @@ -41,7 +44,7 @@ config E100 config E1000 tristate "Intel(R) PRO/1000 Gigabit Ethernet support" - depends on PCI + depends on PCI && HAS_IOPORT help This driver supports Intel(R) PRO/1000 gigabit ethernet family of adapters. For more information on how to identify your adapter, go @@ -144,6 +147,8 @@ config IXGBE depends on PCI depends on PTP_1588_CLOCK_OPTIONAL select MDIO + select NET_DEVLINK + select PLDMFW select PHYLIB help This driver supports Intel(R) 10GbE PCI Express family of @@ -225,6 +230,7 @@ config I40E depends on PTP_1588_CLOCK_OPTIONAL depends on PCI select AUXILIARY_BUS + select LIBIE select NET_DEVLINK help This driver supports Intel(R) Ethernet Controller XL710 Family of @@ -253,10 +259,14 @@ config I40E_DCB # so that CONFIG_IAVF symbol will always mirror the state of CONFIG_I40EVF config IAVF tristate + select LIBIE + select NET_SHAPER + config I40EVF tristate "Intel(R) Ethernet Adaptive Virtual Function support" select IAVF depends on PCI_MSI + depends on PTP_1588_CLOCK_OPTIONAL help This driver supports virtual functions for Intel XL710, X710, X722, XXV710, and all devices advertising support for @@ -283,7 +293,9 @@ config ICE depends on GNSS || GNSS = n select AUXILIARY_BUS select DIMLIB + select LIBIE select NET_DEVLINK + select PACKING select PLDMFW select DPLL help @@ -327,7 +339,7 @@ config ICE_SWITCHDEV config ICE_HWTS bool "Support HW cross-timestamp on platforms with PTM support" default y - depends on ICE && X86 + depends on ICE && X86 && PCIE_PTM help Say Y to enable hardware supported cross-timestamping on platforms with PCIe PTM support. The cross-timestamp is available through @@ -357,6 +369,7 @@ config IGC default n depends on PCI depends on PTP_1588_CLOCK_OPTIONAL + depends on ETHTOOL_NETLINK help This driver supports Intel(R) Ethernet Controller I225-LM/I225-V family of adapters. @@ -377,17 +390,6 @@ config IGC_LEDS Optional support for controlling the NIC LED's with the netdev LED trigger. -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. +source "drivers/net/ethernet/intel/idpf/Kconfig" endif # NET_VENDOR_INTEL diff --git a/drivers/net/ethernet/intel/Makefile b/drivers/net/ethernet/intel/Makefile index dacb481ee5b1..04c844ef4964 100644 --- a/drivers/net/ethernet/intel/Makefile +++ b/drivers/net/ethernet/intel/Makefile @@ -3,6 +3,9 @@ # Makefile for the Intel network device drivers. # +obj-$(CONFIG_LIBETH) += libeth/ +obj-$(CONFIG_LIBIE) += libie/ + obj-$(CONFIG_E100) += e100.o obj-$(CONFIG_E1000) += e1000/ obj-$(CONFIG_E1000E) += e1000e/ diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 3fcb8daaa243..c0ead54ea186 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -146,7 +146,7 @@ #include <linux/string.h> #include <linux/firmware.h> #include <linux/rtnetlink.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #define DRV_NAME "e100" @@ -161,7 +161,6 @@ #define FIRMWARE_D102E "e100/d102e_ucode.bin" MODULE_DESCRIPTION(DRV_DESCRIPTION); -MODULE_AUTHOR(DRV_COPYRIGHT); MODULE_LICENSE("GPL v2"); MODULE_FIRMWARE(FIRMWARE_D101M); MODULE_FIRMWARE(FIRMWARE_D101S); @@ -2294,7 +2293,7 @@ static int e100_up(struct nic *nic) return 0; err_no_irq: - del_timer_sync(&nic->watchdog); + timer_delete_sync(&nic->watchdog); err_clean_cbs: e100_clean_cbs(nic); err_rx_clean_list: @@ -2309,7 +2308,7 @@ static void e100_down(struct nic *nic) netif_stop_queue(nic->netdev); e100_hw_reset(nic); free_irq(nic->pdev->irq, nic->netdev); - del_timer_sync(&nic->watchdog); + timer_delete_sync(&nic->watchdog); netif_carrier_off(nic->netdev); e100_clean_cbs(nic); e100_rx_clean_list(nic); @@ -3037,7 +3036,7 @@ static int __e100_power_off(struct pci_dev *pdev, bool wake) return 0; } -static int __maybe_unused e100_suspend(struct device *dev_d) +static int e100_suspend(struct device *dev_d) { bool wake; @@ -3046,7 +3045,7 @@ static int __maybe_unused e100_suspend(struct device *dev_d) return 0; } -static int __maybe_unused e100_resume(struct device *dev_d) +static int e100_resume(struct device *dev_d) { struct net_device *netdev = dev_get_drvdata(dev_d); struct nic *nic = netdev_priv(netdev); @@ -3163,7 +3162,7 @@ static const struct pci_error_handlers e100_err_handler = { .resume = e100_io_resume, }; -static SIMPLE_DEV_PM_OPS(e100_pm_ops, e100_suspend, e100_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(e100_pm_ops, e100_suspend, e100_resume); static struct pci_driver e100_driver = { .name = DRV_NAME, @@ -3172,7 +3171,7 @@ static struct pci_driver e100_driver = { .remove = e100_remove, /* Power Management hooks */ - .driver.pm = &e100_pm_ops, + .driver.pm = pm_sleep_ptr(&e100_pm_ops), .shutdown = e100_shutdown, .err_handler = &e100_err_handler, diff --git a/drivers/net/ethernet/intel/e1000/Makefile b/drivers/net/ethernet/intel/e1000/Makefile index 314c52d44b7c..79491dec47e1 100644 --- a/drivers/net/ethernet/intel/e1000/Makefile +++ b/drivers/net/ethernet/intel/e1000/Makefile @@ -7,4 +7,4 @@ obj-$(CONFIG_E1000) += e1000.o -e1000-objs := e1000_main.o e1000_hw.o e1000_ethtool.o e1000_param.o +e1000-y := e1000_main.o e1000_hw.o e1000_ethtool.o e1000_param.o diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 1d1e93686af2..3f089c3d47b2 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -149,8 +149,8 @@ static int e1000_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid); static void e1000_restore_vlan(struct e1000_adapter *adapter); -static int __maybe_unused e1000_suspend(struct device *dev); -static int __maybe_unused e1000_resume(struct device *dev); +static int e1000_suspend(struct device *dev); +static int e1000_resume(struct device *dev); static void e1000_shutdown(struct pci_dev *pdev); #ifdef CONFIG_NET_POLL_CONTROLLER @@ -175,21 +175,18 @@ static const struct pci_error_handlers e1000_err_handler = { .resume = e1000_io_resume, }; -static SIMPLE_DEV_PM_OPS(e1000_pm_ops, e1000_suspend, e1000_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(e1000_pm_ops, e1000_suspend, e1000_resume); static struct pci_driver e1000_driver = { .name = e1000_driver_name, .id_table = e1000_pci_tbl, .probe = e1000_probe, .remove = e1000_remove, - .driver = { - .pm = &e1000_pm_ops, - }, + .driver.pm = pm_sleep_ptr(&e1000_pm_ops), .shutdown = e1000_shutdown, .err_handler = &e1000_err_handler }; -MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION("Intel(R) PRO/1000 Network Driver"); MODULE_LICENSE("GPL v2"); @@ -516,6 +513,8 @@ void e1000_down(struct e1000_adapter *adapter) */ netif_carrier_off(netdev); + netif_queue_set_napi(netdev, 0, NETDEV_QUEUE_TYPE_RX, NULL); + netif_queue_set_napi(netdev, 0, NETDEV_QUEUE_TYPE_TX, NULL); napi_disable(&adapter->napi); e1000_irq_disable(adapter); @@ -1395,7 +1394,10 @@ int e1000_open(struct net_device *netdev) /* From here on the code is the same as e1000_up() */ clear_bit(__E1000_DOWN, &adapter->flags); + netif_napi_set_irq(&adapter->napi, adapter->pdev->irq); napi_enable(&adapter->napi); + netif_queue_set_napi(netdev, 0, NETDEV_QUEUE_TYPE_RX, &adapter->napi); + netif_queue_set_napi(netdev, 0, NETDEV_QUEUE_TYPE_TX, &adapter->napi); e1000_irq_enable(adapter); @@ -3507,7 +3509,9 @@ static void e1000_reset_task(struct work_struct *work) container_of(work, struct e1000_adapter, reset_task); e_err(drv, "Reset adapter\n"); + rtnl_lock(); e1000_reinit_locked(adapter); + rtnl_unlock(); } /** @@ -3571,7 +3575,7 @@ static int e1000_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; + WRITE_ONCE(netdev->mtu, new_mtu); if (netif_running(netdev)) e1000_up(adapter); @@ -5072,7 +5076,9 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool *enable_wake) usleep_range(10000, 20000); WARN_ON(test_bit(__E1000_RESETTING, &adapter->flags)); + rtnl_lock(); e1000_down(adapter); + rtnl_unlock(); } status = er32(STATUS); @@ -5135,7 +5141,7 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool *enable_wake) return 0; } -static int __maybe_unused e1000_suspend(struct device *dev) +static int e1000_suspend(struct device *dev) { int retval; struct pci_dev *pdev = to_pci_dev(dev); @@ -5147,7 +5153,7 @@ static int __maybe_unused e1000_suspend(struct device *dev) return retval; } -static int __maybe_unused e1000_resume(struct device *dev) +static int e1000_resume(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); @@ -5233,16 +5239,20 @@ static pci_ers_result_t e1000_io_error_detected(struct pci_dev *pdev, struct net_device *netdev = pci_get_drvdata(pdev); struct e1000_adapter *adapter = netdev_priv(netdev); + rtnl_lock(); netif_device_detach(netdev); - if (state == pci_channel_io_perm_failure) + if (state == pci_channel_io_perm_failure) { + rtnl_unlock(); return PCI_ERS_RESULT_DISCONNECT; + } if (netif_running(netdev)) e1000_down(adapter); if (!test_and_set_bit(__E1000_DISABLED, &adapter->flags)) pci_disable_device(pdev); + rtnl_unlock(); /* Request a slot reset. */ return PCI_ERS_RESULT_NEED_RESET; diff --git a/drivers/net/ethernet/intel/e1000e/Makefile b/drivers/net/ethernet/intel/e1000e/Makefile index 0baa15503c38..18f22b6374d5 100644 --- a/drivers/net/ethernet/intel/e1000e/Makefile +++ b/drivers/net/ethernet/intel/e1000e/Makefile @@ -10,7 +10,6 @@ subdir-ccflags-y += -I$(src) obj-$(CONFIG_E1000E) += e1000e.o -e1000e-objs := 82571.o ich8lan.o 80003es2lan.o \ - mac.o manage.o nvm.o phy.o \ - param.o ethtool.o netdev.o ptp.o - +e1000e-y := 82571.o ich8lan.o 80003es2lan.o \ + mac.o manage.o nvm.o phy.o \ + param.o ethtool.o netdev.o ptp.o diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h index 23a58cada43a..8294a7c4f122 100644 --- a/drivers/net/ethernet/intel/e1000e/defines.h +++ b/drivers/net/ethernet/intel/e1000e/defines.h @@ -679,8 +679,6 @@ /* PCI/PCI-X/PCI-EX Config space */ #define PCI_HEADER_TYPE_REGISTER 0x0E -#define PCI_HEADER_TYPE_MULTIFUNC 0x80 - #define PHY_REVISION_MASK 0xFFFFFFF0 #define MAX_PHY_REG_ADDRESS 0x1F /* 5 bit address bus (0-0x1F) */ #define MAX_PHY_MULTI_PAGE_REG 0xF @@ -805,4 +803,7 @@ /* SerDes Control */ #define E1000_GEN_POLL_TIMEOUT 640 +#define E1000_FEXTNVM12_PHYPD_CTRL_MASK 0x00C00000 +#define E1000_FEXTNVM12_PHYPD_CTRL_P1 0x00800000 + #endif /* _E1000_DEFINES_H_ */ diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index ba9c19e6994c..952898151565 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -319,7 +319,7 @@ struct e1000_adapter { u16 tx_ring_count; u16 rx_ring_count; - struct hwtstamp_config hwtstamp_config; + struct kernel_hwtstamp_config hwtstamp_config; struct delayed_work systim_overflow_work; struct sk_buff *tx_hwtstamp_skb; unsigned long tx_hwtstamp_start; diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index dc553c51d79a..9364bc2b4eb1 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -156,7 +156,7 @@ static int e1000_get_link_ksettings(struct net_device *netdev, speed = adapter->link_speed; cmd->base.duplex = adapter->link_duplex - 1; } - } else if (!pm_runtime_suspended(netdev->dev.parent)) { + } else { u32 status = er32(STATUS); if (status & E1000_STATUS_LU) { @@ -274,16 +274,13 @@ static int e1000_set_link_ksettings(struct net_device *netdev, ethtool_convert_link_mode_to_legacy_u32(&advertising, cmd->link_modes.advertising); - pm_runtime_get_sync(netdev->dev.parent); - /* When SoL/IDER sessions are active, autoneg/speed/duplex * cannot be changed */ if (hw->phy.ops.check_reset_block && hw->phy.ops.check_reset_block(hw)) { e_err("Cannot change link characteristics when SoL/IDER is active.\n"); - ret_val = -EINVAL; - goto out; + return -EINVAL; } /* MDI setting is only allowed when autoneg enabled because @@ -291,16 +288,13 @@ static int e1000_set_link_ksettings(struct net_device *netdev, * duplex is forced. */ if (cmd->base.eth_tp_mdix_ctrl) { - if (hw->phy.media_type != e1000_media_type_copper) { - ret_val = -EOPNOTSUPP; - goto out; - } + if (hw->phy.media_type != e1000_media_type_copper) + return -EOPNOTSUPP; if ((cmd->base.eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) && (cmd->base.autoneg != AUTONEG_ENABLE)) { e_err("forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n"); - ret_val = -EINVAL; - goto out; + return -EINVAL; } } @@ -347,7 +341,6 @@ static int e1000_set_link_ksettings(struct net_device *netdev, } out: - pm_runtime_put_sync(netdev->dev.parent); clear_bit(__E1000_RESETTING, &adapter->state); return ret_val; } @@ -383,8 +376,6 @@ static int e1000_set_pauseparam(struct net_device *netdev, while (test_and_set_bit(__E1000_RESETTING, &adapter->state)) usleep_range(1000, 2000); - pm_runtime_get_sync(netdev->dev.parent); - if (adapter->fc_autoneg == AUTONEG_ENABLE) { hw->fc.requested_mode = e1000_fc_default; if (netif_running(adapter->netdev)) { @@ -417,7 +408,6 @@ static int e1000_set_pauseparam(struct net_device *netdev, } out: - pm_runtime_put_sync(netdev->dev.parent); clear_bit(__E1000_RESETTING, &adapter->state); return retval; } @@ -448,8 +438,6 @@ static void e1000_get_regs(struct net_device *netdev, u32 *regs_buff = p; u16 phy_data; - pm_runtime_get_sync(netdev->dev.parent); - memset(p, 0, E1000_REGS_LEN * sizeof(u32)); regs->version = (1u << 24) | @@ -495,8 +483,6 @@ static void e1000_get_regs(struct net_device *netdev, e1e_rphy(hw, MII_STAT1000, &phy_data); regs_buff[24] = (u32)phy_data; /* phy local receiver status */ regs_buff[25] = regs_buff[24]; /* phy remote receiver status */ - - pm_runtime_put_sync(netdev->dev.parent); } static int e1000_get_eeprom_len(struct net_device *netdev) @@ -529,8 +515,6 @@ static int e1000_get_eeprom(struct net_device *netdev, if (!eeprom_buff) return -ENOMEM; - pm_runtime_get_sync(netdev->dev.parent); - if (hw->nvm.type == e1000_nvm_eeprom_spi) { ret_val = e1000_read_nvm(hw, first_word, last_word - first_word + 1, @@ -544,8 +528,6 @@ static int e1000_get_eeprom(struct net_device *netdev, } } - pm_runtime_put_sync(netdev->dev.parent); - if (ret_val) { /* a read error occurred, throw away the result */ memset(eeprom_buff, 0xff, sizeof(u16) * @@ -595,8 +577,6 @@ static int e1000_set_eeprom(struct net_device *netdev, ptr = (void *)eeprom_buff; - pm_runtime_get_sync(netdev->dev.parent); - if (eeprom->offset & 1) { /* need read/modify/write of first changed EEPROM word */ /* only the second byte of the word is being modified */ @@ -637,7 +617,6 @@ static int e1000_set_eeprom(struct net_device *netdev, ret_val = e1000e_update_nvm_checksum(hw); out: - pm_runtime_put_sync(netdev->dev.parent); kfree(eeprom_buff); return ret_val; } @@ -733,8 +712,6 @@ static int e1000_set_ringparam(struct net_device *netdev, } } - pm_runtime_get_sync(netdev->dev.parent); - e1000e_down(adapter, true); /* We can't just free everything and then setup again, because the @@ -773,7 +750,6 @@ err_setup_rx: e1000e_free_tx_resources(temp_tx); err_setup: e1000e_up(adapter); - pm_runtime_put_sync(netdev->dev.parent); free_temp: vfree(temp_tx); vfree(temp_rx); @@ -1816,8 +1792,6 @@ static void e1000_diag_test(struct net_device *netdev, u8 autoneg; bool if_running = netif_running(netdev); - pm_runtime_get_sync(netdev->dev.parent); - set_bit(__E1000_TESTING, &adapter->state); if (!if_running) { @@ -1903,8 +1877,6 @@ static void e1000_diag_test(struct net_device *netdev, } msleep_interruptible(4 * 1000); - - pm_runtime_put_sync(netdev->dev.parent); } static void e1000_get_wol(struct net_device *netdev, @@ -2046,15 +2018,11 @@ static int e1000_set_coalesce(struct net_device *netdev, adapter->itr_setting = adapter->itr & ~3; } - pm_runtime_get_sync(netdev->dev.parent); - if (adapter->itr_setting != 0) e1000e_write_itr(adapter, adapter->itr); else e1000e_write_itr(adapter, 0); - pm_runtime_put_sync(netdev->dev.parent); - return 0; } @@ -2068,9 +2036,7 @@ static int e1000_nway_reset(struct net_device *netdev) if (!adapter->hw.mac.autoneg) return -EINVAL; - pm_runtime_get_sync(netdev->dev.parent); e1000e_reinit_locked(adapter); - pm_runtime_put_sync(netdev->dev.parent); return 0; } @@ -2084,12 +2050,8 @@ static void e1000_get_ethtool_stats(struct net_device *netdev, int i; char *p = NULL; - pm_runtime_get_sync(netdev->dev.parent); - dev_get_stats(netdev, &net_stats); - pm_runtime_put_sync(netdev->dev.parent); - for (i = 0; i < E1000_GLOBAL_STATS_LEN; i++) { switch (e1000_gstrings_stats[i].type) { case NETDEV_STATS: @@ -2146,9 +2108,7 @@ static int e1000_get_rxnfc(struct net_device *netdev, struct e1000_hw *hw = &adapter->hw; u32 mrqc; - pm_runtime_get_sync(netdev->dev.parent); mrqc = er32(MRQC); - pm_runtime_put_sync(netdev->dev.parent); if (!(mrqc & E1000_MRQC_RSS_FIELD_MASK)) return 0; @@ -2211,13 +2171,9 @@ static int e1000e_get_eee(struct net_device *netdev, struct ethtool_keee *edata) return -EOPNOTSUPP; } - pm_runtime_get_sync(netdev->dev.parent); - ret_val = hw->phy.ops.acquire(hw); - if (ret_val) { - pm_runtime_put_sync(netdev->dev.parent); + if (ret_val) return -EBUSY; - } /* EEE Capability */ ret_val = e1000_read_emi_reg_locked(hw, cap_addr, &phy_data); @@ -2257,8 +2213,6 @@ release: if (ret_val) ret_val = -ENODATA; - pm_runtime_put_sync(netdev->dev.parent); - return ret_val; } @@ -2299,21 +2253,17 @@ static int e1000e_set_eee(struct net_device *netdev, struct ethtool_keee *edata) hw->dev_spec.ich8lan.eee_disable = !edata->eee_enabled; - pm_runtime_get_sync(netdev->dev.parent); - /* reset the link */ if (netif_running(netdev)) e1000e_reinit_locked(adapter); else e1000e_reset(adapter); - pm_runtime_put_sync(netdev->dev.parent); - return 0; } static int e1000e_get_ts_info(struct net_device *netdev, - struct ethtool_ts_info *info) + struct kernel_ethtool_ts_info *info) { struct e1000_adapter *adapter = netdev_priv(netdev); diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index 4b6e7536170a..fc8ed38aa095 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -108,8 +108,8 @@ struct e1000_hw; #define E1000_DEV_ID_PCH_RPL_I219_V22 0x0DC8 #define E1000_DEV_ID_PCH_MTP_I219_LM18 0x550A #define E1000_DEV_ID_PCH_MTP_I219_V18 0x550B -#define E1000_DEV_ID_PCH_MTP_I219_LM19 0x550C -#define E1000_DEV_ID_PCH_MTP_I219_V19 0x550D +#define E1000_DEV_ID_PCH_ADP_I219_LM19 0x550C +#define E1000_DEV_ID_PCH_ADP_I219_V19 0x550D #define E1000_DEV_ID_PCH_LNP_I219_LM20 0x550E #define E1000_DEV_ID_PCH_LNP_I219_V20 0x550F #define E1000_DEV_ID_PCH_LNP_I219_LM21 0x5510 diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index f9e94be36e97..364378133526 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -286,6 +286,45 @@ static void e1000_toggle_lanphypc_pch_lpt(struct e1000_hw *hw) } /** + * e1000_reconfigure_k1_exit_timeout - reconfigure K1 exit timeout to + * align to MTP and later platform requirements. + * @hw: pointer to the HW structure + * + * Context: PHY semaphore must be held by caller. + * Return: 0 on success, negative on failure + */ +static s32 e1000_reconfigure_k1_exit_timeout(struct e1000_hw *hw) +{ + u16 phy_timeout; + u32 fextnvm12; + s32 ret_val; + + if (hw->mac.type < e1000_pch_mtp) + return 0; + + /* Change Kumeran K1 power down state from P0s to P1 */ + fextnvm12 = er32(FEXTNVM12); + fextnvm12 &= ~E1000_FEXTNVM12_PHYPD_CTRL_MASK; + fextnvm12 |= E1000_FEXTNVM12_PHYPD_CTRL_P1; + ew32(FEXTNVM12, fextnvm12); + + /* Wait for the interface the settle */ + usleep_range(1000, 1100); + + /* Change K1 exit timeout */ + ret_val = e1e_rphy_locked(hw, I217_PHY_TIMEOUTS_REG, + &phy_timeout); + if (ret_val) + return ret_val; + + phy_timeout &= ~I217_PHY_TIMEOUTS_K1_EXIT_TO_MASK; + phy_timeout |= 0xF00; + + return e1e_wphy_locked(hw, I217_PHY_TIMEOUTS_REG, + phy_timeout); +} + +/** * e1000_init_phy_workarounds_pchlan - PHY initialization workarounds * @hw: pointer to the HW structure * @@ -327,15 +366,22 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) * LANPHYPC Value bit to force the interconnect to PCIe mode. */ switch (hw->mac.type) { + case e1000_pch_mtp: + case e1000_pch_lnp: + case e1000_pch_ptp: + case e1000_pch_nvp: + /* At this point the PHY might be inaccessible so don't + * propagate the failure + */ + if (e1000_reconfigure_k1_exit_timeout(hw)) + e_dbg("Failed to reconfigure K1 exit timeout\n"); + + fallthrough; case e1000_pch_lpt: case e1000_pch_spt: case e1000_pch_cnp: case e1000_pch_tgp: case e1000_pch_adp: - case e1000_pch_mtp: - case e1000_pch_lnp: - case e1000_pch_ptp: - case e1000_pch_nvp: if (e1000_phy_is_accessible_pchlan(hw)) break; @@ -419,8 +465,20 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) * the PHY is in. */ ret_val = hw->phy.ops.check_reset_block(hw); - if (ret_val) + if (ret_val) { e_err("ME blocked access to PHY after reset\n"); + goto out; + } + + if (hw->mac.type >= e1000_pch_mtp) { + ret_val = hw->phy.ops.acquire(hw); + if (ret_val) { + e_err("Failed to reconfigure K1 exit timeout\n"); + goto out; + } + ret_val = e1000_reconfigure_k1_exit_timeout(hw); + hw->phy.ops.release(hw); + } } out: @@ -1109,6 +1167,46 @@ static s32 e1000_platform_pm_pch_lpt(struct e1000_hw *hw, bool link) } /** + * e1000e_force_smbus - Force interfaces to transition to SMBUS mode. + * @hw: pointer to the HW structure + * + * Force the MAC and the PHY to SMBUS mode. Assumes semaphore already + * acquired. + * + * Return: 0 on success, negative errno on failure. + **/ +static s32 e1000e_force_smbus(struct e1000_hw *hw) +{ + u16 smb_ctrl = 0; + u32 ctrl_ext; + s32 ret_val; + + /* Switching PHY interface always returns MDI error + * so disable retry mechanism to avoid wasting time + */ + e1000e_disable_phy_retry(hw); + + /* Force SMBus mode in the PHY */ + ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &smb_ctrl); + if (ret_val) { + e1000e_enable_phy_retry(hw); + return ret_val; + } + + smb_ctrl |= CV_SMB_CTRL_FORCE_SMBUS; + e1000_write_phy_reg_hv_locked(hw, CV_SMB_CTRL, smb_ctrl); + + e1000e_enable_phy_retry(hw); + + /* Force SMBus mode in the MAC */ + ctrl_ext = er32(CTRL_EXT); + ctrl_ext |= E1000_CTRL_EXT_FORCE_SMBUS; + ew32(CTRL_EXT, ctrl_ext); + + return 0; +} + +/** * e1000_enable_ulp_lpt_lp - configure Ultra Low Power mode for LynxPoint-LP * @hw: pointer to the HW structure * @to_sx: boolean indicating a system power state transition to Sx @@ -1165,6 +1263,12 @@ s32 e1000_enable_ulp_lpt_lp(struct e1000_hw *hw, bool to_sx) if (ret_val) goto out; + ret_val = e1000e_force_smbus(hw); + if (ret_val) { + e_dbg("Failed to force SMBUS: %d\n", ret_val); + goto release; + } + /* Si workaround for ULP entry flow on i127/rev6 h/w. Enable * LPLU and disable Gig speed when entering ULP */ @@ -4842,6 +4946,18 @@ static s32 e1000_init_hw_ich8lan(struct e1000_hw *hw) u16 i; e1000_initialize_hw_bits_ich8lan(hw); + if (hw->mac.type >= e1000_pch_mtp) { + ret_val = hw->phy.ops.acquire(hw); + if (ret_val) + return ret_val; + + ret_val = e1000_reconfigure_k1_exit_timeout(hw); + hw->phy.ops.release(hw); + if (ret_val) { + e_dbg("Error failed to reconfigure K1 exit timeout\n"); + return ret_val; + } + } /* Initialize identification LED */ ret_val = mac->ops.id_led_init(hw); diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h index 2504b11c3169..5feb589a9b5f 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.h +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h @@ -219,6 +219,10 @@ #define I217_PLL_CLOCK_GATE_REG PHY_REG(772, 28) #define I217_PLL_CLOCK_GATE_MASK 0x07FF +/* PHY Timeouts */ +#define I217_PHY_TIMEOUTS_REG PHY_REG(770, 21) +#define I217_PHY_TIMEOUTS_K1_EXIT_TO_MASK 0x0FC0 + #define SW_FLAG_TIMEOUT 1000 /* SW Semaphore flag timeout in ms */ /* Inband Control */ diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c index d7df2a0ed629..44249dd91bd6 100644 --- a/drivers/net/ethernet/intel/e1000e/mac.c +++ b/drivers/net/ethernet/intel/e1000e/mac.c @@ -331,8 +331,21 @@ void e1000e_update_mc_addr_list_generic(struct e1000_hw *hw, } /* replace the entire MTA table */ - for (i = hw->mac.mta_reg_count - 1; i >= 0; i--) + for (i = hw->mac.mta_reg_count - 1; i >= 0; i--) { E1000_WRITE_REG_ARRAY(hw, E1000_MTA, i, hw->mac.mta_shadow[i]); + + if (IS_ENABLED(CONFIG_PREEMPT_RT)) { + /* + * Do not queue up too many posted writes to prevent + * increased latency for other devices on the + * interconnect. Flush after each 8th posted write, + * to keep additional execution time low while still + * preventing increased latency. + */ + if (!(i % 8) && i) + e1e_flush(); + } + } e1e_flush(); } diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 3692fce20195..e0f492a6723f 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -2928,11 +2928,8 @@ static void e1000_configure_tx(struct e1000_adapter *adapter) tx_ring->head = adapter->hw.hw_addr + E1000_TDH(0); tx_ring->tail = adapter->hw.hw_addr + E1000_TDT(0); - writel(0, tx_ring->head); if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA) e1000e_update_tdt_wa(tx_ring, 0); - else - writel(0, tx_ring->tail); /* Set the Tx Interrupt Delay register */ ew32(TIDV, adapter->tx_int_delay); @@ -3253,11 +3250,8 @@ static void e1000_configure_rx(struct e1000_adapter *adapter) rx_ring->head = adapter->hw.hw_addr + E1000_RDH(0); rx_ring->tail = adapter->hw.hw_addr + E1000_RDT(0); - writel(0, rx_ring->head); if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA) e1000e_update_rdt_wa(rx_ring, 0); - else - writel(0, rx_ring->tail); /* Enable Receive Checksum Offload for TCP and UDP */ rxcsum = er32(RXCSUM); @@ -3580,6 +3574,7 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca) * e1000e_config_hwtstamp - configure the hwtstamp registers and enable/disable * @adapter: board private structure * @config: timestamp configuration + * @extack: netlink extended ACK for error report * * Outgoing time stamping can be enabled and disabled. Play nice and * disable it when requested, although it shouldn't cause any overhead @@ -3593,7 +3588,8 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca) * exception of "all V2 events regardless of level 2 or 4". **/ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter, - struct hwtstamp_config *config) + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { struct e1000_hw *hw = &adapter->hw; u32 tsync_tx_ctl = E1000_TSYNCTXCTL_ENABLED; @@ -3604,8 +3600,10 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter, bool is_l2 = false; u32 regval; - if (!(adapter->flags & FLAG_HAS_HW_TIMESTAMP)) + if (!(adapter->flags & FLAG_HAS_HW_TIMESTAMP)) { + NL_SET_ERR_MSG(extack, "No HW timestamp support"); return -EINVAL; + } switch (config->tx_type) { case HWTSTAMP_TX_OFF: @@ -3614,6 +3612,7 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter, case HWTSTAMP_TX_ON: break; default: + NL_SET_ERR_MSG(extack, "Unsupported TX HW timestamp type"); return -ERANGE; } @@ -3687,6 +3686,7 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter, config->rx_filter = HWTSTAMP_FILTER_ALL; break; default: + NL_SET_ERR_MSG(extack, "Unsupported RX HW timestamp filter"); return -ERANGE; } @@ -3699,7 +3699,8 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter, ew32(TSYNCTXCTL, regval); if ((er32(TSYNCTXCTL) & E1000_TSYNCTXCTL_ENABLED) != (regval & E1000_TSYNCTXCTL_ENABLED)) { - e_err("Timesync Tx Control register not set as expected\n"); + NL_SET_ERR_MSG(extack, + "Timesync Tx Control register not set as expected"); return -EAGAIN; } @@ -3712,7 +3713,8 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter, E1000_TSYNCRXCTL_TYPE_MASK)) != (regval & (E1000_TSYNCRXCTL_ENABLED | E1000_TSYNCRXCTL_TYPE_MASK))) { - e_err("Timesync Rx Control register not set as expected\n"); + NL_SET_ERR_MSG(extack, + "Timesync Rx Control register not set as expected"); return -EAGAIN; } @@ -3907,6 +3909,7 @@ static void e1000e_systim_reset(struct e1000_adapter *adapter) { struct ptp_clock_info *info = &adapter->ptp_clock_info; struct e1000_hw *hw = &adapter->hw; + struct netlink_ext_ack extack = {}; unsigned long flags; u32 timinca; s32 ret_val; @@ -3938,7 +3941,12 @@ static void e1000e_systim_reset(struct e1000_adapter *adapter) spin_unlock_irqrestore(&adapter->systim_lock, flags); /* restore the previous hwtstamp configuration settings */ - e1000e_config_hwtstamp(adapter, &adapter->hwtstamp_config); + ret_val = e1000e_config_hwtstamp(adapter, &adapter->hwtstamp_config, + &extack); + if (ret_val) { + if (extack._msg) + e_err("%s\n", extack._msg); + } } /** @@ -4293,8 +4301,8 @@ void e1000e_down(struct e1000_adapter *adapter, bool reset) napi_synchronize(&adapter->napi); - del_timer_sync(&adapter->watchdog_timer); - del_timer_sync(&adapter->phy_info_timer); + timer_delete_sync(&adapter->watchdog_timer); + timer_delete_sync(&adapter->phy_info_timer); spin_lock(&adapter->stats64_lock); e1000e_update_stats(adapter); @@ -4613,6 +4621,7 @@ int e1000e_open(struct net_device *netdev) struct e1000_hw *hw = &adapter->hw; struct pci_dev *pdev = adapter->pdev; int err; + int irq; /* disallow open during test */ if (test_bit(__E1000_TESTING, &adapter->state)) @@ -4676,7 +4685,15 @@ int e1000e_open(struct net_device *netdev) /* From here on the code is the same as e1000e_up() */ clear_bit(__E1000_DOWN, &adapter->state); + if (adapter->int_mode == E1000E_INT_MODE_MSIX) + irq = adapter->msix_entries[0].vector; + else + irq = adapter->pdev->irq; + + netif_napi_set_irq(&adapter->napi, irq); napi_enable(&adapter->napi); + netif_queue_set_napi(netdev, 0, NETDEV_QUEUE_TYPE_RX, &adapter->napi); + netif_queue_set_napi(netdev, 0, NETDEV_QUEUE_TYPE_TX, &adapter->napi); e1000_irq_enable(adapter); @@ -4735,6 +4752,8 @@ int e1000e_close(struct net_device *netdev) netdev_info(netdev, "NIC Link is Down\n"); } + netif_queue_set_napi(netdev, 0, NETDEV_QUEUE_TYPE_RX, NULL); + netif_queue_set_napi(netdev, 0, NETDEV_QUEUE_TYPE_TX, NULL); napi_disable(&adapter->napi); e1000e_free_tx_resources(adapter->tx_ring); @@ -6038,7 +6057,7 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu) adapter->max_frame_size = max_frame; netdev_dbg(netdev, "changing MTU from %d to %d\n", netdev->mtu, new_mtu); - netdev->mtu = new_mtu; + WRITE_ONCE(netdev->mtu, new_mtu); pm_runtime_get_sync(netdev->dev.parent); @@ -6074,8 +6093,7 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu) return 0; } -static int e1000_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, - int cmd) +static int e1000_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) { struct e1000_adapter *adapter = netdev_priv(netdev); struct mii_ioctl_data *data = if_mii(ifr); @@ -6135,7 +6153,8 @@ static int e1000_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, /** * e1000e_hwtstamp_set - control hardware time stamping * @netdev: network interface device structure - * @ifr: interface request + * @config: timestamp configuration + * @extack: netlink extended ACK report * * Outgoing time stamping can be enabled and disabled. Play nice and * disable it when requested, although it shouldn't cause any overhead @@ -6148,20 +6167,18 @@ static int e1000_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, * specified. Matching the kind of event packet is not supported, with the * exception of "all V2 events regardless of level 2 or 4". **/ -static int e1000e_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr) +static int e1000e_hwtstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { struct e1000_adapter *adapter = netdev_priv(netdev); - struct hwtstamp_config config; int ret_val; - if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) - return -EFAULT; - - ret_val = e1000e_config_hwtstamp(adapter, &config); + ret_val = e1000e_config_hwtstamp(adapter, config, extack); if (ret_val) return ret_val; - switch (config.rx_filter) { + switch (config->rx_filter) { case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: case HWTSTAMP_FILTER_PTP_V2_SYNC: @@ -6173,38 +6190,23 @@ static int e1000e_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr) * by hardware so notify the caller the requested packets plus * some others are time stamped. */ - config.rx_filter = HWTSTAMP_FILTER_SOME; + config->rx_filter = HWTSTAMP_FILTER_SOME; break; default: break; } - return copy_to_user(ifr->ifr_data, &config, - sizeof(config)) ? -EFAULT : 0; + return 0; } -static int e1000e_hwtstamp_get(struct net_device *netdev, struct ifreq *ifr) +static int e1000e_hwtstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *kernel_config) { struct e1000_adapter *adapter = netdev_priv(netdev); - return copy_to_user(ifr->ifr_data, &adapter->hwtstamp_config, - sizeof(adapter->hwtstamp_config)) ? -EFAULT : 0; -} + *kernel_config = adapter->hwtstamp_config; -static int e1000_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) -{ - switch (cmd) { - case SIOCGMIIPHY: - case SIOCGMIIREG: - case SIOCSMIIREG: - return e1000_mii_ioctl(netdev, ifr, cmd); - case SIOCSHWTSTAMP: - return e1000e_hwtstamp_set(netdev, ifr); - case SIOCGHWTSTAMP: - return e1000e_hwtstamp_get(netdev, ifr); - default: - return -EOPNOTSUPP; - } + return 0; } static int e1000_init_phy_wakeup(struct e1000_adapter *adapter, u32 wufc) @@ -6363,49 +6365,49 @@ static void e1000e_s0ix_entry_flow(struct e1000_adapter *adapter) mac_data |= E1000_EXTCNF_CTRL_GATE_PHY_CFG; ew32(EXTCNF_CTRL, mac_data); - /* Enable the Dynamic Power Gating in the MAC */ - mac_data = er32(FEXTNVM7); - mac_data |= BIT(22); - ew32(FEXTNVM7, mac_data); - /* Disable disconnected cable conditioning for Power Gating */ mac_data = er32(DPGFR); mac_data |= BIT(2); ew32(DPGFR, mac_data); - /* Don't wake from dynamic Power Gating with clock request */ - mac_data = er32(FEXTNVM12); - mac_data |= BIT(12); - ew32(FEXTNVM12, mac_data); - - /* Ungate PGCB clock */ - mac_data = er32(FEXTNVM9); - mac_data &= ~BIT(28); - ew32(FEXTNVM9, mac_data); - - /* Enable K1 off to enable mPHY Power Gating */ - mac_data = er32(FEXTNVM6); - mac_data |= BIT(31); - ew32(FEXTNVM6, mac_data); - - /* Enable mPHY power gating for any link and speed */ - mac_data = er32(FEXTNVM8); - mac_data |= BIT(9); - ew32(FEXTNVM8, mac_data); - /* Enable the Dynamic Clock Gating in the DMA and MAC */ mac_data = er32(CTRL_EXT); mac_data |= E1000_CTRL_EXT_DMA_DYN_CLK_EN; ew32(CTRL_EXT, mac_data); - - /* No MAC DPG gating SLP_S0 in modern standby - * Switch the logic of the lanphypc to use PMC counter - */ - mac_data = er32(FEXTNVM5); - mac_data |= BIT(7); - ew32(FEXTNVM5, mac_data); } + /* Enable the Dynamic Power Gating in the MAC */ + mac_data = er32(FEXTNVM7); + mac_data |= BIT(22); + ew32(FEXTNVM7, mac_data); + + /* Don't wake from dynamic Power Gating with clock request */ + mac_data = er32(FEXTNVM12); + mac_data |= BIT(12); + ew32(FEXTNVM12, mac_data); + + /* Ungate PGCB clock */ + mac_data = er32(FEXTNVM9); + mac_data &= ~BIT(28); + ew32(FEXTNVM9, mac_data); + + /* Enable K1 off to enable mPHY Power Gating */ + mac_data = er32(FEXTNVM6); + mac_data |= BIT(31); + ew32(FEXTNVM6, mac_data); + + /* Enable mPHY power gating for any link and speed */ + mac_data = er32(FEXTNVM8); + mac_data |= BIT(9); + ew32(FEXTNVM8, mac_data); + + /* No MAC DPG gating SLP_S0 in modern standby + * Switch the logic of the lanphypc to use PMC counter + */ + mac_data = er32(FEXTNVM5); + mac_data |= BIT(7); + ew32(FEXTNVM5, mac_data); + /* Disable the time synchronization clock */ mac_data = er32(FEXTNVM7); mac_data |= BIT(31); @@ -6498,33 +6500,6 @@ static void e1000e_s0ix_exit_flow(struct e1000_adapter *adapter) } else { /* Request driver unconfigure the device from S0ix */ - /* Disable the Dynamic Power Gating in the MAC */ - mac_data = er32(FEXTNVM7); - mac_data &= 0xFFBFFFFF; - ew32(FEXTNVM7, mac_data); - - /* Disable mPHY power gating for any link and speed */ - mac_data = er32(FEXTNVM8); - mac_data &= ~BIT(9); - ew32(FEXTNVM8, mac_data); - - /* Disable K1 off */ - mac_data = er32(FEXTNVM6); - mac_data &= ~BIT(31); - ew32(FEXTNVM6, mac_data); - - /* Disable Ungate PGCB clock */ - mac_data = er32(FEXTNVM9); - mac_data |= BIT(28); - ew32(FEXTNVM9, mac_data); - - /* Cancel not waking from dynamic - * Power Gating with clock request - */ - mac_data = er32(FEXTNVM12); - mac_data &= ~BIT(12); - ew32(FEXTNVM12, mac_data); - /* Cancel disable disconnected cable conditioning * for Power Gating */ @@ -6537,13 +6512,6 @@ static void e1000e_s0ix_exit_flow(struct e1000_adapter *adapter) mac_data &= 0xFFF7FFFF; ew32(CTRL_EXT, mac_data); - /* Revert the lanphypc logic to use the internal Gbe counter - * and not the PMC counter - */ - mac_data = er32(FEXTNVM5); - mac_data &= 0xFFFFFF7F; - ew32(FEXTNVM5, mac_data); - /* Enable the periodic inband message, * Request PCIe clock in K1 page770_17[10:9] =01b */ @@ -6581,6 +6549,40 @@ static void e1000e_s0ix_exit_flow(struct e1000_adapter *adapter) mac_data &= ~BIT(31); mac_data |= BIT(0); ew32(FEXTNVM7, mac_data); + + /* Disable the Dynamic Power Gating in the MAC */ + mac_data = er32(FEXTNVM7); + mac_data &= 0xFFBFFFFF; + ew32(FEXTNVM7, mac_data); + + /* Disable mPHY power gating for any link and speed */ + mac_data = er32(FEXTNVM8); + mac_data &= ~BIT(9); + ew32(FEXTNVM8, mac_data); + + /* Disable K1 off */ + mac_data = er32(FEXTNVM6); + mac_data &= ~BIT(31); + ew32(FEXTNVM6, mac_data); + + /* Disable Ungate PGCB clock */ + mac_data = er32(FEXTNVM9); + mac_data |= BIT(28); + ew32(FEXTNVM9, mac_data); + + /* Cancel not waking from dynamic + * Power Gating with clock request + */ + mac_data = er32(FEXTNVM12); + mac_data &= ~BIT(12); + ew32(FEXTNVM12, mac_data); + + /* Revert the lanphypc logic to use the internal Gbe counter + * and not the PMC counter + */ + mac_data = er32(FEXTNVM5); + mac_data &= 0xFFFFFF7F; + ew32(FEXTNVM5, mac_data); } static int e1000e_pm_freeze(struct device *dev) @@ -6623,7 +6625,6 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) struct e1000_hw *hw = &adapter->hw; u32 ctrl, ctrl_ext, rctl, status, wufc; int retval = 0; - u16 smb_ctrl; /* Runtime suspend should only enable wakeup for link changes */ if (runtime) @@ -6672,8 +6673,10 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) if (adapter->flags2 & FLAG2_HAS_PHY_WAKEUP) { /* enable wakeup by the PHY */ retval = e1000_init_phy_wakeup(adapter, wufc); - if (retval) - return retval; + if (retval) { + e_err("Failed to enable wakeup\n"); + goto skip_phy_configurations; + } } else { /* enable wakeup by the MAC */ ew32(WUFC, wufc); @@ -6694,26 +6697,11 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) * or broadcast. */ retval = e1000_enable_ulp_lpt_lp(hw, !runtime); - if (retval) - return retval; + if (retval) { + e_err("Failed to enable ULP\n"); + goto skip_phy_configurations; + } } - - /* Force SMBUS to allow WOL */ - /* Switching PHY interface always returns MDI error - * so disable retry mechanism to avoid wasting time - */ - e1000e_disable_phy_retry(hw); - - e1e_rphy(hw, CV_SMB_CTRL, &smb_ctrl); - smb_ctrl |= CV_SMB_CTRL_FORCE_SMBUS; - e1e_wphy(hw, CV_SMB_CTRL, smb_ctrl); - - e1000e_enable_phy_retry(hw); - - /* Force SMBus mode in MAC */ - ctrl_ext = er32(CTRL_EXT); - ctrl_ext |= E1000_CTRL_EXT_FORCE_SMBUS; - ew32(CTRL_EXT, ctrl_ext); } /* Ensure that the appropriate bits are set in LPI_CTRL @@ -6744,6 +6732,7 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) hw->phy.ops.release(hw); } +skip_phy_configurations: /* Release control of h/w to f/w. If f/w is AMT enabled, this * would have already happened in close and is redundant. */ @@ -6968,13 +6957,13 @@ static int __e1000_resume(struct pci_dev *pdev) return 0; } -static __maybe_unused int e1000e_pm_prepare(struct device *dev) +static int e1000e_pm_prepare(struct device *dev) { return pm_runtime_suspended(dev) && pm_suspend_via_firmware(); } -static __maybe_unused int e1000e_pm_suspend(struct device *dev) +static int e1000e_pm_suspend(struct device *dev) { struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); struct e1000_adapter *adapter = netdev_priv(netdev); @@ -6986,18 +6975,16 @@ static __maybe_unused int e1000e_pm_suspend(struct device *dev) e1000e_pm_freeze(dev); rc = __e1000_shutdown(pdev, false); - if (rc) { - e1000e_pm_thaw(dev); - } else { + if (!rc) { /* Introduce S0ix implementation */ if (adapter->flags2 & FLAG2_ENABLE_S0IX_FLOWS) e1000e_s0ix_entry_flow(adapter); } - return rc; + return 0; } -static __maybe_unused int e1000e_pm_resume(struct device *dev) +static int e1000e_pm_resume(struct device *dev) { struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); struct e1000_adapter *adapter = netdev_priv(netdev); @@ -7031,7 +7018,7 @@ static __maybe_unused int e1000e_pm_runtime_idle(struct device *dev) return -EBUSY; } -static __maybe_unused int e1000e_pm_runtime_resume(struct device *dev) +static int e1000e_pm_runtime_resume(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); @@ -7050,7 +7037,7 @@ static __maybe_unused int e1000e_pm_runtime_resume(struct device *dev) return rc; } -static __maybe_unused int e1000e_pm_runtime_suspend(struct device *dev) +static int e1000e_pm_runtime_suspend(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); @@ -7356,9 +7343,11 @@ static const struct net_device_ops e1000e_netdev_ops = { #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = e1000_netpoll, #endif - .ndo_set_features = e1000_set_features, - .ndo_fix_features = e1000_fix_features, + .ndo_set_features = e1000_set_features, + .ndo_fix_features = e1000_fix_features, .ndo_features_check = passthru_features_check, + .ndo_hwtstamp_get = e1000e_hwtstamp_get, + .ndo_hwtstamp_set = e1000e_hwtstamp_set, }; /** @@ -7751,8 +7740,8 @@ static void e1000_remove(struct pci_dev *pdev) * from being rescheduled. */ set_bit(__E1000_DOWN, &adapter->state); - del_timer_sync(&adapter->watchdog_timer); - del_timer_sync(&adapter->phy_info_timer); + timer_delete_sync(&adapter->watchdog_timer); + timer_delete_sync(&adapter->phy_info_timer); cancel_work_sync(&adapter->reset_task); cancel_work_sync(&adapter->watchdog_task); @@ -7914,10 +7903,10 @@ static const struct pci_device_id e1000_pci_tbl[] = { { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V17), board_pch_adp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM22), board_pch_adp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V22), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM19), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V19), board_pch_adp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM18), board_pch_mtp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V18), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM19), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V19), board_pch_mtp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM20), board_pch_mtp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V20), board_pch_mtp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM21), board_pch_mtp }, @@ -7937,8 +7926,7 @@ static const struct pci_device_id e1000_pci_tbl[] = { }; MODULE_DEVICE_TABLE(pci, e1000_pci_tbl); -static const struct dev_pm_ops e1000_pm_ops = { -#ifdef CONFIG_PM_SLEEP +static const struct dev_pm_ops e1000e_pm_ops = { .prepare = e1000e_pm_prepare, .suspend = e1000e_pm_suspend, .resume = e1000e_pm_resume, @@ -7946,9 +7934,8 @@ static const struct dev_pm_ops e1000_pm_ops = { .thaw = e1000e_pm_thaw, .poweroff = e1000e_pm_suspend, .restore = e1000e_pm_resume, -#endif - SET_RUNTIME_PM_OPS(e1000e_pm_runtime_suspend, e1000e_pm_runtime_resume, - e1000e_pm_runtime_idle) + RUNTIME_PM_OPS(e1000e_pm_runtime_suspend, e1000e_pm_runtime_resume, + e1000e_pm_runtime_idle) }; /* PCI Device API Driver */ @@ -7957,9 +7944,7 @@ static struct pci_driver e1000_driver = { .id_table = e1000_pci_tbl, .probe = e1000_probe, .remove = e1000_remove, - .driver = { - .pm = &e1000_pm_ops, - }, + .driver.pm = pm_ptr(&e1000e_pm_ops), .shutdown = e1000_shutdown, .err_handler = &e1000_err_handler }; @@ -7991,7 +7976,6 @@ static void __exit e1000_exit_module(void) } module_exit(e1000_exit_module); -MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION("Intel(R) PRO/1000 Network Driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c index bbcfd529399b..89d57dd911dc 100644 --- a/drivers/net/ethernet/intel/e1000e/ptp.c +++ b/drivers/net/ethernet/intel/e1000e/ptp.c @@ -124,7 +124,8 @@ static int e1000e_phc_get_syncdevicetime(ktime_t *device, sys_cycles = er32(PLTSTMPH); sys_cycles <<= 32; sys_cycles |= er32(PLTSTMPL); - *system = convert_art_to_tsc(sys_cycles); + system->cycles = sys_cycles; + system->cs_id = CSID_X86_ART; return 0; } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index fc373472e4e1..142f07ca8bc0 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -17,7 +17,6 @@ static const char fm10k_driver_string[] = DRV_SUMMARY; static const char fm10k_copyright[] = "Copyright(c) 2013 - 2019 Intel Corporation."; -MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION(DRV_SUMMARY); MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index d748b98274e7..21267ab603ef 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -2245,7 +2245,7 @@ static void fm10k_remove(struct pci_dev *pdev) struct fm10k_intfc *interface = pci_get_drvdata(pdev); struct net_device *netdev = interface->netdev; - del_timer_sync(&interface->service_timer); + timer_delete_sync(&interface->service_timer); fm10k_stop_service_event(interface); fm10k_stop_macvlan_task(interface); @@ -2342,7 +2342,7 @@ static int fm10k_handle_resume(struct fm10k_intfc *interface) * suspend or hibernation. This function does not need to handle lower PCIe * device state as the stack takes care of that for us. **/ -static int __maybe_unused fm10k_resume(struct device *dev) +static int fm10k_resume(struct device *dev) { struct fm10k_intfc *interface = dev_get_drvdata(dev); struct net_device *netdev = interface->netdev; @@ -2369,7 +2369,7 @@ static int __maybe_unused fm10k_resume(struct device *dev) * system suspend or hibernation. This function does not need to handle lower * PCIe device state as the stack takes care of that for us. **/ -static int __maybe_unused fm10k_suspend(struct device *dev) +static int fm10k_suspend(struct device *dev) { struct fm10k_intfc *interface = dev_get_drvdata(dev); struct net_device *netdev = interface->netdev; @@ -2502,16 +2502,14 @@ static const struct pci_error_handlers fm10k_err_handler = { .reset_done = fm10k_io_reset_done, }; -static SIMPLE_DEV_PM_OPS(fm10k_pm_ops, fm10k_suspend, fm10k_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(fm10k_pm_ops, fm10k_suspend, fm10k_resume); static struct pci_driver fm10k_driver = { .name = fm10k_driver_name, .id_table = fm10k_pci_tbl, .probe = fm10k_probe, .remove = fm10k_remove, - .driver = { - .pm = &fm10k_pm_ops, - }, + .driver.pm = pm_sleep_ptr(&fm10k_pm_ops), .sriov_configure = fm10k_iov_configure, .err_handler = &fm10k_err_handler }; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c index 98861cc6df7c..b9dd7b719832 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c @@ -1180,126 +1180,6 @@ s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid) } /** - * fm10k_iov_msg_mac_vlan_pf - Message handler for MAC/VLAN request from VF - * @hw: Pointer to hardware structure - * @results: Pointer array to message, results[0] is pointer to message - * @mbx: Pointer to mailbox information structure - * - * This function is a default handler for MAC/VLAN requests from the VF. - * The assumption is that in this case it is acceptable to just directly - * hand off the message from the VF to the underlying shared code. - **/ -s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) -{ - struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx; - u8 mac[ETH_ALEN]; - u32 *result; - int err = 0; - bool set; - u16 vlan; - u32 vid; - - /* we shouldn't be updating rules on a disabled interface */ - if (!FM10K_VF_FLAG_ENABLED(vf_info)) - err = FM10K_ERR_PARAM; - - if (!err && !!results[FM10K_MAC_VLAN_MSG_VLAN]) { - result = results[FM10K_MAC_VLAN_MSG_VLAN]; - - /* record VLAN id requested */ - err = fm10k_tlv_attr_get_u32(result, &vid); - if (err) - return err; - - set = !(vid & FM10K_VLAN_CLEAR); - vid &= ~FM10K_VLAN_CLEAR; - - /* if the length field has been set, this is a multi-bit - * update request. For multi-bit requests, simply disallow - * them when the pf_vid has been set. In this case, the PF - * should have already cleared the VLAN_TABLE, and if we - * allowed them, it could allow a rogue VF to receive traffic - * on a VLAN it was not assigned. In the single-bit case, we - * need to modify requests for VLAN 0 to use the default PF or - * SW vid when assigned. - */ - - if (vid >> 16) { - /* prevent multi-bit requests when PF has - * administratively set the VLAN for this VF - */ - if (vf_info->pf_vid) - return FM10K_ERR_PARAM; - } else { - err = fm10k_iov_select_vid(vf_info, (u16)vid); - if (err < 0) - return err; - - vid = err; - } - - /* update VSI info for VF in regards to VLAN table */ - err = hw->mac.ops.update_vlan(hw, vid, vf_info->vsi, set); - } - - if (!err && !!results[FM10K_MAC_VLAN_MSG_MAC]) { - result = results[FM10K_MAC_VLAN_MSG_MAC]; - - /* record unicast MAC address requested */ - err = fm10k_tlv_attr_get_mac_vlan(result, mac, &vlan); - if (err) - return err; - - /* block attempts to set MAC for a locked device */ - if (is_valid_ether_addr(vf_info->mac) && - !ether_addr_equal(mac, vf_info->mac)) - return FM10K_ERR_PARAM; - - set = !(vlan & FM10K_VLAN_CLEAR); - vlan &= ~FM10K_VLAN_CLEAR; - - err = fm10k_iov_select_vid(vf_info, vlan); - if (err < 0) - return err; - - vlan = (u16)err; - - /* notify switch of request for new unicast address */ - err = hw->mac.ops.update_uc_addr(hw, vf_info->glort, - mac, vlan, set, 0); - } - - if (!err && !!results[FM10K_MAC_VLAN_MSG_MULTICAST]) { - result = results[FM10K_MAC_VLAN_MSG_MULTICAST]; - - /* record multicast MAC address requested */ - err = fm10k_tlv_attr_get_mac_vlan(result, mac, &vlan); - if (err) - return err; - - /* verify that the VF is allowed to request multicast */ - if (!(vf_info->vf_flags & FM10K_VF_FLAG_MULTI_ENABLED)) - return FM10K_ERR_PARAM; - - set = !(vlan & FM10K_VLAN_CLEAR); - vlan &= ~FM10K_VLAN_CLEAR; - - err = fm10k_iov_select_vid(vf_info, vlan); - if (err < 0) - return err; - - vlan = (u16)err; - - /* notify switch of request for new multicast address */ - err = hw->mac.ops.update_mc_addr(hw, vf_info->glort, - mac, vlan, set); - } - - return err; -} - -/** * fm10k_iov_supported_xcast_mode_pf - Determine best match for xcast mode * @vf_info: VF info structure containing capability flags * @mode: Requested xcast mode diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.h b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h index 8e814df709d2..ad3696893cb1 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h @@ -99,8 +99,6 @@ extern const struct fm10k_tlv_attr fm10k_err_msg_attr[]; s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid); s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *, u32 **, struct fm10k_mbx_info *); -s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *, u32 **, - struct fm10k_mbx_info *); s32 fm10k_iov_msg_lport_state_pf(struct fm10k_hw *, u32 **, struct fm10k_mbx_info *); diff --git a/drivers/net/ethernet/intel/i40e/Makefile b/drivers/net/ethernet/intel/i40e/Makefile index cad93f323bd5..9faa4339a76c 100644 --- a/drivers/net/ethernet/intel/i40e/Makefile +++ b/drivers/net/ethernet/intel/i40e/Makefile @@ -10,7 +10,7 @@ subdir-ccflags-y += -I$(src) obj-$(CONFIG_I40E) += i40e.o -i40e-objs := i40e_main.o \ +i40e-y := i40e_main.o \ i40e_ethtool.o \ i40e_adminq.o \ i40e_common.o \ diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 2fbabcdb5bb5..c67963bfe14e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -4,6 +4,7 @@ #ifndef _I40E_H_ #define _I40E_H_ +#include <linux/linkmode.h> #include <linux/pci.h> #include <linux/ptp_clock_kernel.h> #include <linux/types.h> @@ -87,6 +88,7 @@ enum i40e_state { __I40E_SERVICE_SCHED, __I40E_ADMINQ_EVENT_PENDING, __I40E_MDD_EVENT_PENDING, + __I40E_MDD_VF_PRINT_PENDING, __I40E_VFLR_EVENT_PENDING, __I40E_RESET_RECOVERY_PENDING, __I40E_TIMEOUT_RECOVERY_PENDING, @@ -190,6 +192,7 @@ enum i40e_pf_flags { */ I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENA, I40E_FLAG_VF_VLAN_PRUNING_ENA, + I40E_FLAG_MDD_AUTO_RESET_VF, I40E_PF_FLAGS_NBITS, /* must be last */ }; @@ -571,7 +574,7 @@ struct i40e_pf { int num_alloc_vfs; /* actual number of VFs allocated */ u32 vf_aq_requests; u32 arq_overflows; /* Not fatal, possibly indicative of problems */ - + struct ratelimit_state mdd_message_rate_limit; /* DCBx/DCBNL capability for PF that indicates * whether DCBx is managed by firmware or host * based agent (LLDPAD). Also, indicates what @@ -735,7 +738,7 @@ __i40e_pf_next_veb(struct i40e_pf *pf, int *idx) _i++, _veb = __i40e_pf_next_veb(_pf, &_i)) /** - * i40e_mac_to_hkey - Convert a 6-byte MAC Address to a u64 hash key + * i40e_addr_to_hkey - Convert a 6-byte MAC Address to a u64 hash key * @macaddr: the MAC Address as the base key * * Simply copies the address and returns it as a u64 for hashing @@ -754,6 +757,7 @@ enum i40e_filter_state { I40E_FILTER_ACTIVE, /* Added to switch by FW */ I40E_FILTER_FAILED, /* Rejected by FW */ I40E_FILTER_REMOVE, /* To be removed */ + I40E_FILTER_NEW_SYNC, /* New, not sent yet, is in i40e_sync_vsi_filters() */ /* There is no 'removed' state; the filter struct is freed */ }; struct i40e_mac_filter { @@ -788,7 +792,6 @@ struct i40e_veb { u16 stats_idx; /* index of VEB parent */ u8 enabled_tc; u16 bridge_mode; /* Bridge Mode (VEB/VEPA) */ - u16 flags; u16 bw_limit; u8 bw_max_quanta; bool is_abs_credits; @@ -1188,7 +1191,6 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi, struct i40e_fdir_filter *input, bool add); void i40e_fdir_check_and_reenable(struct i40e_pf *pf); u32 i40e_get_current_fd_count(struct i40e_pf *pf); -u32 i40e_get_cur_guaranteed_fd_count(struct i40e_pf *pf); u32 i40e_get_current_atr_cnt(struct i40e_pf *pf); u32 i40e_get_global_fd_count(struct i40e_pf *pf); bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features); @@ -1196,7 +1198,6 @@ void i40e_set_ethtool_ops(struct net_device *netdev); struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi, const u8 *macaddr, s16 vlan); void __i40e_del_filter(struct i40e_vsi *vsi, struct i40e_mac_filter *f); -void i40e_del_filter(struct i40e_vsi *vsi, const u8 *macaddr, s16 vlan); int i40e_sync_vsi_filters(struct i40e_vsi *vsi); struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type, u16 uplink, u32 param1); @@ -1213,7 +1214,7 @@ void i40e_vsi_stop_rings(struct i40e_vsi *vsi); void i40e_vsi_stop_rings_no_wait(struct i40e_vsi *vsi); int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi); int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count); -struct i40e_veb *i40e_veb_setup(struct i40e_pf *pf, u16 flags, u16 uplink_seid, +struct i40e_veb *i40e_veb_setup(struct i40e_pf *pf, u16 uplink_seid, u16 downlink_seid, u8 enabled_tc); void i40e_veb_release(struct i40e_veb *veb); @@ -1237,8 +1238,8 @@ static inline void i40e_dbg_exit(void) {} int i40e_lan_add_device(struct i40e_pf *pf); int i40e_lan_del_device(struct i40e_pf *pf); void i40e_client_subtask(struct i40e_pf *pf); -void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi); -void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset); +void i40e_notify_client_of_l2_param_changes(struct i40e_pf *pf); +void i40e_notify_client_of_netdev_close(struct i40e_pf *pf, bool reset); void i40e_notify_client_of_vf_enable(struct i40e_pf *pf, u32 num_vfs); void i40e_notify_client_of_vf_reset(struct i40e_pf *pf, u32 vf_id); void i40e_client_update_msix_info(struct i40e_pf *pf); @@ -1312,7 +1313,6 @@ int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset); int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi); int i40e_get_partition_bw_setting(struct i40e_pf *pf); int i40e_set_partition_bw_setting(struct i40e_pf *pf); -int i40e_commit_partition_bw_setting(struct i40e_pf *pf); void i40e_print_link_message(struct i40e_vsi *vsi, bool isup); void i40e_set_fec_in_flags(u8 fec_cfg, unsigned long *flags); @@ -1374,6 +1374,17 @@ i40e_pf_get_vsi_by_seid(struct i40e_pf *pf, u16 seid) } /** + * i40e_pf_get_main_vsi - get pointer to main VSI + * @pf: pointer to a PF + * + * Return: pointer to main VSI or NULL if it does not exist + **/ +static inline struct i40e_vsi *i40e_pf_get_main_vsi(struct i40e_pf *pf) +{ + return (pf->lan_vsi != I40E_NO_VSI) ? pf->vsi[pf->lan_vsi] : NULL; +} + +/** * i40e_pf_get_veb_by_seid - find VEB by SEID * @pf: pointer to a PF * @seid: SEID of the VSI @@ -1391,4 +1402,15 @@ i40e_pf_get_veb_by_seid(struct i40e_pf *pf, u16 seid) return NULL; } +/** + * i40e_pf_get_main_veb - get pointer to main VEB + * @pf: pointer to a PF + * + * Return: pointer to main VEB or NULL if it does not exist + **/ +static inline struct i40e_veb *i40e_pf_get_main_veb(struct i40e_pf *pf) +{ + return (pf->lan_veb != I40E_NO_VEB) ? pf->veb[pf->lan_veb] : NULL; +} + #endif /* _I40E_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index f73f5930fc58..175c1320c143 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -1016,16 +1016,6 @@ i40e_asq_send_command_atomic_v2(struct i40e_hw *hw, return status; } -int -i40e_asq_send_command_v2(struct i40e_hw *hw, struct i40e_aq_desc *desc, - void *buff, /* can be NULL */ u16 buff_size, - struct i40e_asq_cmd_details *cmd_details, - enum i40e_admin_queue_err *aq_status) -{ - return i40e_asq_send_command_atomic_v2(hw, desc, buff, buff_size, - cmd_details, true, aq_status); -} - /** * i40e_fill_default_direct_cmd_desc - AQ descriptor helper function * @desc: pointer to the temp descriptor (non DMA mem) diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.h b/drivers/net/ethernet/intel/i40e/i40e_adminq.h index ee86d2c53079..55b5bb884d73 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.h @@ -109,10 +109,6 @@ static inline int i40e_aq_rc_to_posix(int aq_ret, int aq_rc) -EFBIG, /* I40E_AQ_RC_EFBIG */ }; - /* aq_rc is invalid if AQ timed out */ - if (aq_ret == -EIO) - return -EAGAIN; - if (!((u32)aq_rc < (sizeof(aq_to_posix) / sizeof((aq_to_posix)[0])))) return -ERANGE; diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c index b32071ee84af..59263551c383 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.c +++ b/drivers/net/ethernet/intel/i40e/i40e_client.c @@ -101,25 +101,26 @@ i40e_notify_client_of_vf_msg(struct i40e_vsi *vsi, u32 vf_id, u8 *msg, u16 len) /** * i40e_notify_client_of_l2_param_changes - call the client notify callback - * @vsi: the VSI with l2 param changes + * @pf: PF device pointer * - * If there is a client to this VSI, call the client + * If there is a client, call its callback **/ -void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi) +void i40e_notify_client_of_l2_param_changes(struct i40e_pf *pf) { - struct i40e_pf *pf = vsi->back; + struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf); struct i40e_client_instance *cdev = pf->cinst; struct i40e_params params; if (!cdev || !cdev->client) return; if (!cdev->client->ops || !cdev->client->ops->l2_param_change) { - dev_dbg(&vsi->back->pdev->dev, + dev_dbg(&pf->pdev->dev, "Cannot locate client instance l2_param_change routine\n"); return; } if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) { - dev_dbg(&vsi->back->pdev->dev, "Client is not open, abort l2 param change\n"); + dev_dbg(&pf->pdev->dev, + "Client is not open, abort l2 param change\n"); return; } memset(¶ms, 0, sizeof(params)); @@ -157,20 +158,19 @@ static void i40e_client_release_qvlist(struct i40e_info *ldev) /** * i40e_notify_client_of_netdev_close - call the client close callback - * @vsi: the VSI with netdev closed + * @pf: PF device pointer * @reset: true when close called due to a reset pending * * If there is a client to this netdev, call the client with close **/ -void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset) +void i40e_notify_client_of_netdev_close(struct i40e_pf *pf, bool reset) { - struct i40e_pf *pf = vsi->back; struct i40e_client_instance *cdev = pf->cinst; if (!cdev || !cdev->client) return; if (!cdev->client->ops || !cdev->client->ops->close) { - dev_dbg(&vsi->back->pdev->dev, + dev_dbg(&pf->pdev->dev, "Cannot locate client instance close routine\n"); return; } @@ -333,9 +333,9 @@ static int i40e_register_auxiliary_dev(struct i40e_info *ldev, const char *name) **/ static void i40e_client_add_instance(struct i40e_pf *pf) { + struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf); struct i40e_client_instance *cdev = NULL; struct netdev_hw_addr *mac = NULL; - struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; cdev = kzalloc(sizeof(*cdev), GFP_KERNEL); if (!cdev) @@ -399,9 +399,9 @@ void i40e_client_del_instance(struct i40e_pf *pf) **/ void i40e_client_subtask(struct i40e_pf *pf) { - struct i40e_client *client; + struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf); struct i40e_client_instance *cdev; - struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; + struct i40e_client *client; int ret = 0; if (!test_and_clear_bit(__I40E_CLIENT_SERVICE_REQUESTED, pf->state)) @@ -665,8 +665,8 @@ static int i40e_client_update_vsi_ctxt(struct i40e_info *ldev, bool is_vf, u32 vf_id, u32 flag, u32 valid_flag) { + struct i40e_vsi *vsi = i40e_pf_get_main_vsi(ldev->pf); struct i40e_pf *pf = ldev->pf; - struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; struct i40e_vsi_context ctxt; bool update = true; int err; diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index de6ca6295742..b11c35e307ca 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -381,259 +381,6 @@ int i40e_aq_set_rss_key(struct i40e_hw *hw, return i40e_aq_get_set_rss_key(hw, vsi_id, key, true); } -/* The i40e_ptype_lookup table is used to convert from the 8-bit ptype in the - * hardware to a bit-field that can be used by SW to more easily determine the - * packet type. - * - * Macros are used to shorten the table lines and make this table human - * readable. - * - * We store the PTYPE in the top byte of the bit field - this is just so that - * we can check that the table doesn't have a row missing, as the index into - * the table should be the PTYPE. - * - * Typical work flow: - * - * IF NOT i40e_ptype_lookup[ptype].known - * THEN - * Packet is unknown - * ELSE IF i40e_ptype_lookup[ptype].outer_ip == I40E_RX_PTYPE_OUTER_IP - * Use the rest of the fields to look at the tunnels, inner protocols, etc - * ELSE - * Use the enum i40e_rx_l2_ptype to decode the packet type - * ENDIF - */ - -/* macro to make the table lines short, use explicit indexing with [PTYPE] */ -#define I40E_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\ - [PTYPE] = { \ - 1, \ - I40E_RX_PTYPE_OUTER_##OUTER_IP, \ - I40E_RX_PTYPE_OUTER_##OUTER_IP_VER, \ - I40E_RX_PTYPE_##OUTER_FRAG, \ - I40E_RX_PTYPE_TUNNEL_##T, \ - I40E_RX_PTYPE_TUNNEL_END_##TE, \ - I40E_RX_PTYPE_##TEF, \ - I40E_RX_PTYPE_INNER_PROT_##I, \ - I40E_RX_PTYPE_PAYLOAD_LAYER_##PL } - -#define I40E_PTT_UNUSED_ENTRY(PTYPE) [PTYPE] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 } - -/* shorter macros makes the table fit but are terse */ -#define I40E_RX_PTYPE_NOF I40E_RX_PTYPE_NOT_FRAG -#define I40E_RX_PTYPE_FRG I40E_RX_PTYPE_FRAG -#define I40E_RX_PTYPE_INNER_PROT_TS I40E_RX_PTYPE_INNER_PROT_TIMESYNC - -/* Lookup table mapping in the 8-bit HW PTYPE to the bit field for decoding */ -struct i40e_rx_ptype_decoded i40e_ptype_lookup[BIT(8)] = { - /* L2 Packet types */ - I40E_PTT_UNUSED_ENTRY(0), - I40E_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - I40E_PTT(2, L2, NONE, NOF, NONE, NONE, NOF, TS, PAY2), - I40E_PTT(3, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - I40E_PTT_UNUSED_ENTRY(4), - I40E_PTT_UNUSED_ENTRY(5), - I40E_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - I40E_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - I40E_PTT_UNUSED_ENTRY(8), - I40E_PTT_UNUSED_ENTRY(9), - I40E_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - I40E_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), - I40E_PTT(12, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(13, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(14, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(15, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(16, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(17, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(18, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(19, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(20, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(21, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - - /* Non Tunneled IPv4 */ - I40E_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(25), - I40E_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP, PAY4), - I40E_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4), - I40E_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4), - - /* IPv4 --> IPv4 */ - I40E_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3), - I40E_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3), - I40E_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(32), - I40E_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP, PAY4), - I40E_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), - I40E_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), - - /* IPv4 --> IPv6 */ - I40E_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3), - I40E_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3), - I40E_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(39), - I40E_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP, PAY4), - I40E_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), - I40E_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT */ - I40E_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), - - /* IPv4 --> GRE/NAT --> IPv4 */ - I40E_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), - I40E_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), - I40E_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(47), - I40E_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), - I40E_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), - I40E_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT --> IPv6 */ - I40E_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), - I40E_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), - I40E_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(54), - I40E_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), - I40E_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), - I40E_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT --> MAC */ - I40E_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), - - /* IPv4 --> GRE/NAT --> MAC --> IPv4 */ - I40E_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), - I40E_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), - I40E_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(62), - I40E_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), - I40E_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), - I40E_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT -> MAC --> IPv6 */ - I40E_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), - I40E_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), - I40E_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(69), - I40E_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), - I40E_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), - I40E_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT --> MAC/VLAN */ - I40E_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), - - /* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */ - I40E_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), - I40E_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), - I40E_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(77), - I40E_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), - I40E_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), - I40E_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), - - /* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */ - I40E_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), - I40E_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), - I40E_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(84), - I40E_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), - I40E_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), - I40E_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), - - /* Non Tunneled IPv6 */ - I40E_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(91), - I40E_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP, PAY4), - I40E_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4), - I40E_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4), - - /* IPv6 --> IPv4 */ - I40E_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3), - I40E_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3), - I40E_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(98), - I40E_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP, PAY4), - I40E_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), - I40E_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> IPv6 */ - I40E_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3), - I40E_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3), - I40E_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(105), - I40E_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP, PAY4), - I40E_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), - I40E_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT */ - I40E_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), - - /* IPv6 --> GRE/NAT -> IPv4 */ - I40E_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), - I40E_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), - I40E_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(113), - I40E_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), - I40E_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), - I40E_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> IPv6 */ - I40E_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), - I40E_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), - I40E_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(120), - I40E_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), - I40E_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), - I40E_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC */ - I40E_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), - - /* IPv6 --> GRE/NAT -> MAC -> IPv4 */ - I40E_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), - I40E_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), - I40E_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(128), - I40E_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), - I40E_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), - I40E_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC -> IPv6 */ - I40E_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), - I40E_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), - I40E_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(135), - I40E_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), - I40E_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), - I40E_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC/VLAN */ - I40E_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), - - /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */ - I40E_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), - I40E_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), - I40E_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(143), - I40E_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), - I40E_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), - I40E_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */ - I40E_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), - I40E_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), - I40E_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(150), - I40E_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), - I40E_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), - I40E_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), - - /* unused entries */ - [154 ... 255] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 } -}; - /** * i40e_init_shared_code - Initialize the shared code * @hw: pointer to hardware structure @@ -1070,10 +817,11 @@ int i40e_pf_reset(struct i40e_hw *hw) void i40e_clear_hw(struct i40e_hw *hw) { u32 num_queues, base_queue; - u32 num_pf_int; - u32 num_vf_int; + s32 num_pf_int; + s32 num_vf_int; u32 num_vfs; - u32 i, j; + s32 i; + u32 j; u32 val; u32 eol = 0x7ff; @@ -2058,37 +1806,6 @@ int i40e_aq_set_vsi_broadcast(struct i40e_hw *hw, } /** - * i40e_aq_set_vsi_vlan_promisc - control the VLAN promiscuous setting - * @hw: pointer to the hw struct - * @seid: vsi number - * @enable: set MAC L2 layer unicast promiscuous enable/disable for a given VLAN - * @cmd_details: pointer to command details structure or NULL - **/ -int i40e_aq_set_vsi_vlan_promisc(struct i40e_hw *hw, - u16 seid, bool enable, - struct i40e_asq_cmd_details *cmd_details) -{ - struct i40e_aq_desc desc; - struct i40e_aqc_set_vsi_promiscuous_modes *cmd = - (struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw; - u16 flags = 0; - int status; - - i40e_fill_default_direct_cmd_desc(&desc, - i40e_aqc_opc_set_vsi_promiscuous_modes); - if (enable) - flags |= I40E_AQC_SET_VSI_PROMISC_VLAN; - - cmd->promiscuous_flags = cpu_to_le16(flags); - cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_VLAN); - cmd->seid = cpu_to_le16(seid); - - status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); - - return status; -} - -/** * i40e_aq_get_vsi_params - get VSI configuration info * @hw: pointer to the hw struct * @vsi_ctx: pointer to a vsi context struct @@ -2689,136 +2406,6 @@ i40e_aq_remove_macvlan_v2(struct i40e_hw *hw, u16 seid, } /** - * i40e_mirrorrule_op - Internal helper function to add/delete mirror rule - * @hw: pointer to the hw struct - * @opcode: AQ opcode for add or delete mirror rule - * @sw_seid: Switch SEID (to which rule refers) - * @rule_type: Rule Type (ingress/egress/VLAN) - * @id: Destination VSI SEID or Rule ID - * @count: length of the list - * @mr_list: list of mirrored VSI SEIDs or VLAN IDs - * @cmd_details: pointer to command details structure or NULL - * @rule_id: Rule ID returned from FW - * @rules_used: Number of rules used in internal switch - * @rules_free: Number of rules free in internal switch - * - * Add/Delete a mirror rule to a specific switch. Mirror rules are supported for - * VEBs/VEPA elements only - **/ -static int i40e_mirrorrule_op(struct i40e_hw *hw, - u16 opcode, u16 sw_seid, u16 rule_type, u16 id, - u16 count, __le16 *mr_list, - struct i40e_asq_cmd_details *cmd_details, - u16 *rule_id, u16 *rules_used, u16 *rules_free) -{ - struct i40e_aq_desc desc; - struct i40e_aqc_add_delete_mirror_rule *cmd = - (struct i40e_aqc_add_delete_mirror_rule *)&desc.params.raw; - struct i40e_aqc_add_delete_mirror_rule_completion *resp = - (struct i40e_aqc_add_delete_mirror_rule_completion *)&desc.params.raw; - u16 buf_size; - int status; - - buf_size = count * sizeof(*mr_list); - - /* prep the rest of the request */ - i40e_fill_default_direct_cmd_desc(&desc, opcode); - cmd->seid = cpu_to_le16(sw_seid); - cmd->rule_type = cpu_to_le16(rule_type & - I40E_AQC_MIRROR_RULE_TYPE_MASK); - cmd->num_entries = cpu_to_le16(count); - /* Dest VSI for add, rule_id for delete */ - cmd->destination = cpu_to_le16(id); - if (mr_list) { - desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | - I40E_AQ_FLAG_RD)); - if (buf_size > I40E_AQ_LARGE_BUF) - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); - } - - status = i40e_asq_send_command(hw, &desc, mr_list, buf_size, - cmd_details); - if (!status || - hw->aq.asq_last_status == I40E_AQ_RC_ENOSPC) { - if (rule_id) - *rule_id = le16_to_cpu(resp->rule_id); - if (rules_used) - *rules_used = le16_to_cpu(resp->mirror_rules_used); - if (rules_free) - *rules_free = le16_to_cpu(resp->mirror_rules_free); - } - return status; -} - -/** - * i40e_aq_add_mirrorrule - add a mirror rule - * @hw: pointer to the hw struct - * @sw_seid: Switch SEID (to which rule refers) - * @rule_type: Rule Type (ingress/egress/VLAN) - * @dest_vsi: SEID of VSI to which packets will be mirrored - * @count: length of the list - * @mr_list: list of mirrored VSI SEIDs or VLAN IDs - * @cmd_details: pointer to command details structure or NULL - * @rule_id: Rule ID returned from FW - * @rules_used: Number of rules used in internal switch - * @rules_free: Number of rules free in internal switch - * - * Add mirror rule. Mirror rules are supported for VEBs or VEPA elements only - **/ -int i40e_aq_add_mirrorrule(struct i40e_hw *hw, u16 sw_seid, - u16 rule_type, u16 dest_vsi, u16 count, - __le16 *mr_list, - struct i40e_asq_cmd_details *cmd_details, - u16 *rule_id, u16 *rules_used, u16 *rules_free) -{ - 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 -EINVAL; - } - - return i40e_mirrorrule_op(hw, i40e_aqc_opc_add_mirror_rule, sw_seid, - rule_type, dest_vsi, count, mr_list, - cmd_details, rule_id, rules_used, rules_free); -} - -/** - * i40e_aq_delete_mirrorrule - delete a mirror rule - * @hw: pointer to the hw struct - * @sw_seid: Switch SEID (to which rule refers) - * @rule_type: Rule Type (ingress/egress/VLAN) - * @count: length of the list - * @rule_id: Rule ID that is returned in the receive desc as part of - * add_mirrorrule. - * @mr_list: list of mirrored VLAN IDs to be removed - * @cmd_details: pointer to command details structure or NULL - * @rules_used: Number of rules used in internal switch - * @rules_free: Number of rules free in internal switch - * - * Delete a mirror rule. Mirror rules are supported for VEBs/VEPA elements only - **/ -int i40e_aq_delete_mirrorrule(struct i40e_hw *hw, u16 sw_seid, - u16 rule_type, u16 rule_id, u16 count, - __le16 *mr_list, - struct i40e_asq_cmd_details *cmd_details, - u16 *rules_used, u16 *rules_free) -{ - /* Rule ID has to be valid except rule_type: INGRESS VLAN mirroring */ - if (rule_type == I40E_AQC_MIRROR_RULE_TYPE_VLAN) { - /* count and mr_list shall be valid for rule_type INGRESS VLAN - * mirroring. For other rule_type, count and rule_type should - * not matter. - */ - if (count == 0 || !mr_list) - return -EINVAL; - } - - return i40e_mirrorrule_op(hw, i40e_aqc_opc_delete_mirror_rule, sw_seid, - rule_type, rule_id, count, mr_list, - cmd_details, NULL, rules_used, rules_free); -} - -/** * i40e_aq_send_msg_to_vf * @hw: pointer to the hardware structure * @vfid: VF id to send msg @@ -3433,41 +3020,6 @@ i40e_aq_update_nvm_exit: } /** - * i40e_aq_rearrange_nvm - * @hw: pointer to the hw struct - * @rearrange_nvm: defines direction of rearrangement - * @cmd_details: pointer to command details structure or NULL - * - * Rearrange NVM structure, available only for transition FW - **/ -int i40e_aq_rearrange_nvm(struct i40e_hw *hw, - u8 rearrange_nvm, - struct i40e_asq_cmd_details *cmd_details) -{ - struct i40e_aqc_nvm_update *cmd; - struct i40e_aq_desc desc; - int status; - - cmd = (struct i40e_aqc_nvm_update *)&desc.params.raw; - - i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_nvm_update); - - rearrange_nvm &= (I40E_AQ_NVM_REARRANGE_TO_FLAT | - I40E_AQ_NVM_REARRANGE_TO_STRUCT); - - if (!rearrange_nvm) { - status = -EINVAL; - goto i40e_aq_rearrange_nvm_exit; - } - - cmd->command_flags |= rearrange_nvm; - status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); - -i40e_aq_rearrange_nvm_exit: - return status; -} - -/** * i40e_aq_get_lldp_mib * @hw: pointer to the hw struct * @bridge_type: type of bridge requested @@ -3588,44 +3140,6 @@ int i40e_aq_cfg_lldp_mib_change_event(struct i40e_hw *hw, } /** - * i40e_aq_restore_lldp - * @hw: pointer to the hw struct - * @setting: pointer to factory setting variable or NULL - * @restore: True if factory settings should be restored - * @cmd_details: pointer to command details structure or NULL - * - * Restore LLDP Agent factory settings if @restore set to True. In other case - * only returns factory setting in AQ response. - **/ -int -i40e_aq_restore_lldp(struct i40e_hw *hw, u8 *setting, bool restore, - struct i40e_asq_cmd_details *cmd_details) -{ - struct i40e_aq_desc desc; - struct i40e_aqc_lldp_restore *cmd = - (struct i40e_aqc_lldp_restore *)&desc.params.raw; - int status; - - if (!test_bit(I40E_HW_CAP_FW_LLDP_PERSISTENT, hw->caps)) { - i40e_debug(hw, I40E_DEBUG_ALL, - "Restore LLDP not supported by current FW version.\n"); - return -ENODEV; - } - - i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_restore); - - if (restore) - cmd->command |= I40E_AQ_LLDP_AGENT_RESTORE; - - status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); - - if (setting) - *setting = cmd->command & 1; - - return status; -} - -/** * i40e_aq_stop_lldp * @hw: pointer to the hw struct * @shutdown_agent: True if LLDP Agent needs to be Shutdown @@ -4823,84 +4337,6 @@ phy_write_end: } /** - * i40e_write_phy_register - * @hw: pointer to the HW structure - * @page: registers page number - * @reg: register address in the page - * @phy_addr: PHY address on MDIO interface - * @value: PHY register value - * - * Writes value to specified PHY register - **/ -int i40e_write_phy_register(struct i40e_hw *hw, - u8 page, u16 reg, u8 phy_addr, u16 value) -{ - int status; - - switch (hw->device_id) { - case I40E_DEV_ID_1G_BASE_T_X722: - status = i40e_write_phy_register_clause22(hw, reg, phy_addr, - value); - break; - case I40E_DEV_ID_1G_BASE_T_BC: - case I40E_DEV_ID_5G_BASE_T_BC: - case I40E_DEV_ID_10G_BASE_T: - case I40E_DEV_ID_10G_BASE_T4: - case I40E_DEV_ID_10G_BASE_T_BC: - case I40E_DEV_ID_10G_BASE_T_X722: - case I40E_DEV_ID_25G_B: - case I40E_DEV_ID_25G_SFP28: - status = i40e_write_phy_register_clause45(hw, page, reg, - phy_addr, value); - break; - default: - status = -EIO; - break; - } - - return status; -} - -/** - * i40e_read_phy_register - * @hw: pointer to the HW structure - * @page: registers page number - * @reg: register address in the page - * @phy_addr: PHY address on MDIO interface - * @value: PHY register value - * - * Reads specified PHY register value - **/ -int i40e_read_phy_register(struct i40e_hw *hw, - u8 page, u16 reg, u8 phy_addr, u16 *value) -{ - int status; - - switch (hw->device_id) { - case I40E_DEV_ID_1G_BASE_T_X722: - status = i40e_read_phy_register_clause22(hw, reg, phy_addr, - value); - break; - case I40E_DEV_ID_1G_BASE_T_BC: - case I40E_DEV_ID_5G_BASE_T_BC: - case I40E_DEV_ID_10G_BASE_T: - case I40E_DEV_ID_10G_BASE_T4: - case I40E_DEV_ID_10G_BASE_T_BC: - case I40E_DEV_ID_10G_BASE_T_X722: - case I40E_DEV_ID_25G_B: - case I40E_DEV_ID_25G_SFP28: - status = i40e_read_phy_register_clause45(hw, page, reg, - phy_addr, value); - break; - default: - status = -EIO; - break; - } - - return status; -} - -/** * i40e_get_phy_address * @hw: pointer to the HW structure * @dev_num: PHY port num that address we want @@ -4916,80 +4352,6 @@ u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num) } /** - * i40e_blink_phy_link_led - * @hw: pointer to the HW structure - * @time: time how long led will blinks in secs - * @interval: gap between LED on and off in msecs - * - * Blinks PHY link LED - **/ -int i40e_blink_phy_link_led(struct i40e_hw *hw, - u32 time, u32 interval) -{ - u16 led_addr = I40E_PHY_LED_PROV_REG_1; - u16 gpio_led_port; - u8 phy_addr = 0; - int status = 0; - u16 led_ctl; - u8 port_num; - u16 led_reg; - u32 i; - - i = rd32(hw, I40E_PFGEN_PORTNUM); - port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK); - phy_addr = i40e_get_phy_address(hw, port_num); - - for (gpio_led_port = 0; gpio_led_port < 3; gpio_led_port++, - led_addr++) { - status = i40e_read_phy_register_clause45(hw, - I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, - &led_reg); - if (status) - goto phy_blinking_end; - led_ctl = led_reg; - if (led_reg & I40E_PHY_LED_LINK_MODE_MASK) { - led_reg = 0; - status = i40e_write_phy_register_clause45(hw, - I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, - led_reg); - if (status) - goto phy_blinking_end; - break; - } - } - - if (time > 0 && interval > 0) { - for (i = 0; i < time * 1000; i += interval) { - status = i40e_read_phy_register_clause45(hw, - I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, &led_reg); - if (status) - goto restore_config; - if (led_reg & I40E_PHY_LED_MANUAL_ON) - led_reg = 0; - else - led_reg = I40E_PHY_LED_MANUAL_ON; - status = i40e_write_phy_register_clause45(hw, - I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, led_reg); - if (status) - goto restore_config; - msleep(interval); - } - } - -restore_config: - status = i40e_write_phy_register_clause45(hw, - I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, led_ctl); - -phy_blinking_end: - return status; -} - -/** * i40e_led_get_reg - read LED register * @hw: pointer to the HW structure * @led_addr: LED register address @@ -5522,39 +4884,6 @@ i40e_find_segment_in_package(u32 segment_type, (struct i40e_profile_section_header *)((u8 *)(profile) + (offset)) /** - * i40e_find_section_in_profile - * @section_type: the section type to search for (i.e., SECTION_TYPE_NOTE) - * @profile: pointer to the i40e segment header to be searched - * - * This function searches i40e segment for a particular section type. On - * success it returns a pointer to the section header, otherwise it will - * return NULL. - **/ -struct i40e_profile_section_header * -i40e_find_section_in_profile(u32 section_type, - struct i40e_profile_segment *profile) -{ - struct i40e_profile_section_header *sec; - struct i40e_section_table *sec_tbl; - u32 sec_off; - u32 i; - - if (profile->header.type != SEGMENT_TYPE_I40E) - return NULL; - - I40E_SECTION_TABLE(profile, sec_tbl); - - for (i = 0; i < sec_tbl->section_count; i++) { - sec_off = sec_tbl->section_offset[i]; - sec = I40E_SECTION_HEADER(profile, sec_off); - if (sec->section.type == section_type) - return sec; - } - - return NULL; -} - -/** * i40e_ddp_exec_aq_section - Execute generic AQ for DDP * @hw: pointer to the hw struct * @aq: command buffer containing all data to execute AQ @@ -5777,45 +5106,6 @@ i40e_rollback_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile, } /** - * i40e_add_pinfo_to_list - * @hw: pointer to the hardware structure - * @profile: pointer to the profile segment of the package - * @profile_info_sec: buffer for information section - * @track_id: package tracking id - * - * Register a profile to the list of loaded profiles. - */ -int -i40e_add_pinfo_to_list(struct i40e_hw *hw, - struct i40e_profile_segment *profile, - u8 *profile_info_sec, u32 track_id) -{ - struct i40e_profile_section_header *sec = NULL; - struct i40e_profile_info *pinfo; - u32 offset = 0, info = 0; - int status = 0; - - sec = (struct i40e_profile_section_header *)profile_info_sec; - sec->tbl_size = 1; - sec->data_end = sizeof(struct i40e_profile_section_header) + - sizeof(struct i40e_profile_info); - sec->section.type = SECTION_TYPE_INFO; - sec->section.offset = sizeof(struct i40e_profile_section_header); - sec->section.size = sizeof(struct i40e_profile_info); - pinfo = (struct i40e_profile_info *)(profile_info_sec + - sec->section.offset); - pinfo->track_id = track_id; - pinfo->version = profile->version; - pinfo->op = I40E_DDP_ADD_TRACKID; - memcpy(pinfo->name, profile->name, I40E_DDP_NAME_SIZE); - - status = i40e_aq_write_ddp(hw, (void *)sec, sec->data_end, - track_id, &offset, &info, NULL); - - return status; -} - -/** * i40e_aq_add_cloud_filters * @hw: pointer to the hardware structure * @seid: VSI seid to add cloud filters from diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c index 8db1eb0c1768..352e957443fd 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c +++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c @@ -1491,19 +1491,6 @@ void i40e_dcb_hw_set_num_tc(struct i40e_hw *hw, u8 num_tc) } /** - * i40e_dcb_hw_get_num_tc - * @hw: pointer to the hw struct - * - * Returns number of traffic classes configured in HW - **/ -u8 i40e_dcb_hw_get_num_tc(struct i40e_hw *hw) -{ - u32 reg = rd32(hw, I40E_PRTDCB_GENC); - - return FIELD_GET(I40E_PRTDCB_GENC_NUMTC_MASK, reg); -} - -/** * i40e_dcb_hw_rx_ets_bw_config * @hw: pointer to the hw struct * @bw_share: Bandwidth share indexed per traffic class diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.h b/drivers/net/ethernet/intel/i40e/i40e_dcb.h index d76497566e40..d5662c639c41 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_dcb.h +++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.h @@ -253,7 +253,6 @@ void i40e_dcb_hw_rx_cmd_monitor_config(struct i40e_hw *hw, void i40e_dcb_hw_pfc_config(struct i40e_hw *hw, u8 pfc_en, u8 *prio_tc); void i40e_dcb_hw_set_num_tc(struct i40e_hw *hw, u8 num_tc); -u8 i40e_dcb_hw_get_num_tc(struct i40e_hw *hw); void i40e_dcb_hw_rx_ets_bw_config(struct i40e_hw *hw, u8 *bw_share, u8 *mode, u8 *prio_type); void i40e_dcb_hw_rx_up2tc_config(struct i40e_hw *hw, u8 *prio_tc); diff --git a/drivers/net/ethernet/intel/i40e/i40e_ddp.c b/drivers/net/ethernet/intel/i40e/i40e_ddp.c index 2f53f0f53bc3..daa9f2c42f70 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ddp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ddp.c @@ -407,8 +407,9 @@ static int i40e_ddp_load(struct net_device *netdev, const u8 *data, size_t size, **/ static int i40e_ddp_restore(struct i40e_pf *pf) { + struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf); + struct net_device *netdev = vsi->netdev; struct i40e_ddp_old_profile_list *entry; - struct net_device *netdev = pf->vsi[pf->lan_vsi]->netdev; int status = 0; if (!list_empty(&pf->ddp_old_prof)) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index f9ba45f596c9..6cd9da662ae1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -53,6 +53,7 @@ static ssize_t i40e_dbg_command_read(struct file *filp, char __user *buffer, size_t count, loff_t *ppos) { struct i40e_pf *pf = filp->private_data; + struct i40e_vsi *main_vsi; int bytes_not_copied; int buf_size = 256; char *buf; @@ -68,8 +69,8 @@ static ssize_t i40e_dbg_command_read(struct file *filp, char __user *buffer, if (!buf) return -ENOSPC; - len = snprintf(buf, buf_size, "%s: %s\n", - pf->vsi[pf->lan_vsi]->netdev->name, + main_vsi = i40e_pf_get_main_vsi(pf); + len = snprintf(buf, buf_size, "%s: %s\n", main_vsi->netdev->name, i40e_dbg_command_buf); bytes_not_copied = copy_to_user(buffer, buf, len); @@ -88,6 +89,7 @@ static char *i40e_filter_state_string[] = { "ACTIVE", "FAILED", "REMOVE", + "NEW_SYNC", }; /** @@ -128,7 +130,7 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) dev_info(&pf->pdev->dev, " state[%d] = %08lx\n", i, vsi->state[i]); - if (vsi == pf->vsi[pf->lan_vsi]) + if (vsi->type == I40E_VSI_MAIN) dev_info(&pf->pdev->dev, " MAC address: %pM Port MAC: %pM\n", pf->hw.mac.addr, pf->hw.mac.port_addr); @@ -720,7 +722,7 @@ static void i40e_dbg_dump_vf(struct i40e_pf *pf, int vf_id) dev_info(&pf->pdev->dev, "vf %2d: VSI id=%d, seid=%d, qps=%d\n", vf_id, vf->lan_vsi_id, vsi->seid, vf->num_queue_pairs); dev_info(&pf->pdev->dev, " num MDD=%lld\n", - vf->num_mdd_events); + vf->mdd_tx_events.count + vf->mdd_rx_events.count); } else { dev_info(&pf->pdev->dev, "invalid VF id %d\n", vf_id); } @@ -786,7 +788,8 @@ static ssize_t i40e_dbg_command_write(struct file *filp, cnt = sscanf(&cmd_buf[7], "%i", &vsi_seid); if (cnt == 0) { /* default to PF VSI */ - vsi_seid = pf->vsi[pf->lan_vsi]->seid; + vsi = i40e_pf_get_main_vsi(pf); + vsi_seid = vsi->seid; } else if (vsi_seid < 0) { dev_info(&pf->pdev->dev, "add VSI %d: bad vsi seid\n", vsi_seid); @@ -867,7 +870,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp, goto command_write_done; } - veb = i40e_veb_setup(pf, 0, uplink_seid, vsi_seid, enabled_tc); + veb = i40e_veb_setup(pf, uplink_seid, vsi_seid, enabled_tc); if (veb) dev_info(&pf->pdev->dev, "added relay %d\n", veb->seid); else @@ -1030,7 +1033,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp, goto command_write_done; } - vsi = pf->vsi[pf->lan_vsi]; + vsi = i40e_pf_get_main_vsi(pf); switch_id = le16_to_cpu(vsi->info.switch_id) & I40E_AQ_VSI_SW_ID_MASK; @@ -1380,6 +1383,9 @@ static ssize_t i40e_dbg_command_write(struct file *filp, dev_info(&pf->pdev->dev, "FD current total filter count for this interface: %d\n", i40e_get_current_fd_count(pf)); } else if (strncmp(cmd_buf, "lldp", 4) == 0) { + /* Get main VSI */ + struct i40e_vsi *main_vsi = i40e_pf_get_main_vsi(pf); + if (strncmp(&cmd_buf[5], "stop", 4) == 0) { int ret; @@ -1391,10 +1397,9 @@ static ssize_t i40e_dbg_command_write(struct file *filp, goto command_write_done; } ret = i40e_aq_add_rem_control_packet_filter(&pf->hw, - pf->hw.mac.addr, - ETH_P_LLDP, 0, - pf->vsi[pf->lan_vsi]->seid, - 0, true, NULL, NULL); + pf->hw.mac.addr, ETH_P_LLDP, 0, + main_vsi->seid, 0, true, NULL, + NULL); if (ret) { dev_info(&pf->pdev->dev, "%s: Add Control Packet Filter AQ command failed =0x%x\n", @@ -1409,10 +1414,9 @@ static ssize_t i40e_dbg_command_write(struct file *filp, int ret; ret = i40e_aq_add_rem_control_packet_filter(&pf->hw, - pf->hw.mac.addr, - ETH_P_LLDP, 0, - pf->vsi[pf->lan_vsi]->seid, - 0, false, NULL, NULL); + pf->hw.mac.addr, ETH_P_LLDP, 0, + main_vsi->seid, 0, false, NULL, + NULL); if (ret) { dev_info(&pf->pdev->dev, "%s: Remove Control Packet Filter AQ command failed =0x%x\n", @@ -1639,6 +1643,7 @@ static ssize_t i40e_dbg_netdev_ops_read(struct file *filp, char __user *buffer, size_t count, loff_t *ppos) { struct i40e_pf *pf = filp->private_data; + struct i40e_vsi *main_vsi; int bytes_not_copied; int buf_size = 256; char *buf; @@ -1654,8 +1659,8 @@ static ssize_t i40e_dbg_netdev_ops_read(struct file *filp, char __user *buffer, if (!buf) return -ENOSPC; - len = snprintf(buf, buf_size, "%s: %s\n", - pf->vsi[pf->lan_vsi]->netdev->name, + main_vsi = i40e_pf_get_main_vsi(pf); + len = snprintf(buf, buf_size, "%s: %s\n", main_vsi->netdev->name, i40e_dbg_netdev_ops_buf); bytes_not_copied = copy_to_user(buffer, buf, len); diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 42e7e6cdaa6d..8a7a83f83ee5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -459,6 +459,8 @@ static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = { I40E_PRIV_FLAG("base-r-fec", I40E_FLAG_BASE_R_FEC, 0), I40E_PRIV_FLAG("vf-vlan-pruning", I40E_FLAG_VF_VLAN_PRUNING_ENA, 0), + I40E_PRIV_FLAG("mdd-auto-reset-vf", + I40E_FLAG_MDD_AUTO_RESET_VF, 0), }; #define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gstrings_priv_flags) @@ -1241,7 +1243,7 @@ static int i40e_set_link_ksettings(struct net_device *netdev, i40e_partition_setting_complaint(pf); return -EOPNOTSUPP; } - if (vsi != pf->vsi[pf->lan_vsi]) + if (vsi->type != I40E_VSI_MAIN) return -EOPNOTSUPP; if (hw->phy.media_type != I40E_MEDIA_TYPE_BASET && hw->phy.media_type != I40E_MEDIA_TYPE_FIBER && @@ -1710,7 +1712,7 @@ static int i40e_set_pauseparam(struct net_device *netdev, return -EOPNOTSUPP; } - if (vsi != pf->vsi[pf->lan_vsi]) + if (vsi->type != I40E_VSI_MAIN) return -EOPNOTSUPP; is_an = hw_link_info->an_info & I40E_AQ_AN_COMPLETED; @@ -2029,7 +2031,7 @@ static void i40e_get_ringparam(struct net_device *netdev, { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_pf *pf = np->vsi->back; - struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; + struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf); ring->rx_max_pending = i40e_get_max_num_descriptors(pf); ring->tx_max_pending = i40e_get_max_num_descriptors(pf); @@ -2292,7 +2294,7 @@ static int i40e_get_stats_count(struct net_device *netdev) struct i40e_pf *pf = vsi->back; int stats_len; - if (vsi == pf->vsi[pf->lan_vsi] && pf->hw.partition_id == 1) + if (vsi->type == I40E_VSI_MAIN && pf->hw.partition_id == 1) stats_len = I40E_PF_STATS_LEN; else stats_len = I40E_VSI_STATS_LEN; @@ -2422,17 +2424,14 @@ static void i40e_get_ethtool_stats(struct net_device *netdev, } rcu_read_unlock(); - if (vsi != pf->vsi[pf->lan_vsi] || pf->hw.partition_id != 1) + if (vsi->type != I40E_VSI_MAIN || pf->hw.partition_id != 1) goto check_data_pointer; - veb_stats = ((pf->lan_veb != I40E_NO_VEB) && - (pf->lan_veb < I40E_MAX_VEB) && - test_bit(I40E_FLAG_VEB_STATS_ENA, pf->flags)); + veb = i40e_pf_get_main_veb(pf); + veb_stats = veb && test_bit(I40E_FLAG_VEB_STATS_ENA, pf->flags); - if (veb_stats) { - veb = pf->veb[pf->lan_veb]; + if (veb_stats) i40e_update_veb_stats(veb); - } /* If veb stats aren't enabled, pass NULL instead of the veb so that * we initialize stats to zero and update the data pointer @@ -2495,7 +2494,7 @@ static void i40e_get_stat_strings(struct net_device *netdev, u8 *data) "rx", i); } - if (vsi != pf->vsi[pf->lan_vsi] || pf->hw.partition_id != 1) + if (vsi->type != I40E_VSI_MAIN || pf->hw.partition_id != 1) goto check_data_pointer; i40e_add_stat_strings(&data, i40e_gstrings_veb_stats); @@ -2549,7 +2548,7 @@ static void i40e_get_strings(struct net_device *netdev, u32 stringset, } static int i40e_get_ts_info(struct net_device *dev, - struct ethtool_ts_info *info) + struct kernel_ethtool_ts_info *info) { struct i40e_pf *pf = i40e_netdev_to_pf(dev); @@ -2558,16 +2557,12 @@ static int i40e_get_ts_info(struct net_device *dev, return ethtool_op_get_ts_info(dev, info); info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | - SOF_TIMESTAMPING_RX_SOFTWARE | - SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_TX_HARDWARE | SOF_TIMESTAMPING_RX_HARDWARE | SOF_TIMESTAMPING_RAW_HARDWARE; if (pf->ptp_clock) info->phc_index = ptp_clock_index(pf->ptp_clock); - else - info->phc_index = -1; info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON); @@ -2792,7 +2787,7 @@ static int i40e_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) return -EOPNOTSUPP; } - if (vsi != pf->vsi[pf->lan_vsi]) + if (vsi->type != I40E_VSI_MAIN) return -EOPNOTSUPP; /* NVM bit on means WoL disabled for the port */ @@ -3370,6 +3365,7 @@ static int i40e_get_ethtool_fdir_entry(struct i40e_pf *pf, struct i40e_rx_flow_userdef userdef = {0}; struct i40e_fdir_filter *rule = NULL; struct hlist_node *node2; + struct i40e_vsi *vsi; u64 input_set; u16 index; @@ -3493,9 +3489,8 @@ no_input_set: fsp->flow_type |= FLOW_EXT; } - if (rule->dest_vsi != pf->vsi[pf->lan_vsi]->id) { - struct i40e_vsi *vsi; - + vsi = i40e_pf_get_main_vsi(pf); + if (rule->dest_vsi != vsi->id) { vsi = i40e_find_vsi_from_id(pf, rule->dest_vsi); if (vsi && vsi->type == I40E_VSI_SRIOV) { /* VFs are zero-indexed by the driver, but ethtool @@ -5306,7 +5301,7 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) } flags_complete: - bitmap_xor(changed_flags, pf->flags, orig_flags, I40E_PF_FLAGS_NBITS); + bitmap_xor(changed_flags, new_flags, orig_flags, I40E_PF_FLAGS_NBITS); if (test_bit(I40E_FLAG_FW_LLDP_DIS, changed_flags)) reset_needed = I40E_PF_RESET_AND_REBUILD_FLAG; @@ -5644,6 +5639,26 @@ static int i40e_get_module_eeprom(struct net_device *netdev, return 0; } +static void i40e_eee_capability_to_kedata_supported(__le16 eee_capability_, + unsigned long *supported) +{ + const int eee_capability = le16_to_cpu(eee_capability_); + static const int lut[] = { + ETHTOOL_LINK_MODE_100baseT_Full_BIT, + ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + ETHTOOL_LINK_MODE_10000baseT_Full_BIT, + ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, + ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, + ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, + ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT, + }; + + linkmode_zero(supported); + for (unsigned int i = ARRAY_SIZE(lut); i--; ) + if (eee_capability & BIT(i + 1)) + linkmode_set_bit(lut[i], supported); +} + static int i40e_get_eee(struct net_device *netdev, struct ethtool_keee *edata) { struct i40e_netdev_priv *np = netdev_priv(netdev); @@ -5651,7 +5666,7 @@ static int i40e_get_eee(struct net_device *netdev, struct ethtool_keee *edata) struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; struct i40e_hw *hw = &pf->hw; - int status = 0; + int status; /* Get initial PHY capabilities */ status = i40e_aq_get_phy_capabilities(hw, false, true, &phy_cfg, NULL); @@ -5664,11 +5679,18 @@ static int i40e_get_eee(struct net_device *netdev, struct ethtool_keee *edata) if (phy_cfg.eee_capability == 0) return -EOPNOTSUPP; + i40e_eee_capability_to_kedata_supported(phy_cfg.eee_capability, + edata->supported); + linkmode_copy(edata->lp_advertised, edata->supported); + /* Get current configuration */ status = i40e_aq_get_phy_capabilities(hw, false, false, &phy_cfg, NULL); if (status) return -EAGAIN; + linkmode_zero(edata->advertised); + if (phy_cfg.eee_capability) + linkmode_copy(edata->advertised, edata->supported); edata->eee_enabled = !!phy_cfg.eee_capability; edata->tx_lpi_enabled = pf->stats.tx_lpi_status; @@ -5684,10 +5706,11 @@ static int i40e_is_eee_param_supported(struct net_device *netdev, struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; struct i40e_ethtool_not_used { - u32 value; + bool value; const char *name; } param[] = { - {edata->tx_lpi_timer, "tx-timer"}, + {!!(edata->advertised[0] & ~edata->supported[0]), "advertise"}, + {!!edata->tx_lpi_timer, "tx-timer"}, {edata->tx_lpi_enabled != pf->stats.tx_lpi_status, "tx-lpi"} }; int i; @@ -5713,7 +5736,7 @@ static int i40e_set_eee(struct net_device *netdev, struct ethtool_keee *edata) struct i40e_pf *pf = vsi->back; struct i40e_hw *hw = &pf->hw; __le16 eee_capability; - int status = 0; + int status; /* Deny parameters we don't support */ if (i40e_is_eee_param_supported(netdev, edata)) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index ffb9f9f15c52..120d68654e3f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -98,8 +98,8 @@ static int debug = -1; module_param(debug, uint, 0); MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all), Debug mask (0x8XXXXXXX)"); -MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>"); MODULE_DESCRIPTION("Intel(R) Ethernet Connection XL710 Network Driver"); +MODULE_IMPORT_NS("LIBIE"); MODULE_LICENSE("GPL v2"); static struct workqueue_struct *i40e_wq; @@ -989,7 +989,7 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) ns->tx_dropped = es->tx_discards; /* pull in a couple PF stats if this is the main vsi */ - if (vsi == pf->vsi[pf->lan_vsi]) { + if (vsi->type == I40E_VSI_MAIN) { ns->rx_crc_errors = pf->stats.crc_errors; ns->rx_errors = pf->stats.crc_errors + pf->stats.illegal_bytes; ns->rx_length_errors = pf->stats.rx_length_errors; @@ -1234,7 +1234,7 @@ void i40e_update_stats(struct i40e_vsi *vsi) { struct i40e_pf *pf = vsi->back; - if (vsi == pf->vsi[pf->lan_vsi]) + if (vsi->type == I40E_VSI_MAIN) i40e_update_pf_stats(pf); i40e_update_vsi_stats(vsi); @@ -1255,6 +1255,7 @@ int i40e_count_filters(struct i40e_vsi *vsi) hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { if (f->state == I40E_FILTER_NEW || + f->state == I40E_FILTER_NEW_SYNC || f->state == I40E_FILTER_ACTIVE) ++cnt; } @@ -1441,6 +1442,8 @@ static int i40e_correct_mac_vlan_filters(struct i40e_vsi *vsi, new->f = add_head; new->state = add_head->state; + if (add_head->state == I40E_FILTER_NEW) + add_head->state = I40E_FILTER_NEW_SYNC; /* Add the new filter to the tmp list */ hlist_add_head(&new->hlist, tmp_add_list); @@ -1550,6 +1553,8 @@ static int i40e_correct_vf_mac_vlan_filters(struct i40e_vsi *vsi, return -ENOMEM; new_mac->f = add_head; new_mac->state = add_head->state; + if (add_head->state == I40E_FILTER_NEW) + add_head->state = I40E_FILTER_NEW_SYNC; /* Add the new filter to the tmp list */ hlist_add_head(&new_mac->hlist, tmp_add_list); @@ -1661,9 +1666,8 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi, * @vsi: VSI to remove from * @f: the filter to remove from the list * - * This function should be called instead of i40e_del_filter only if you know - * the exact filter you will remove already, such as via i40e_find_filter or - * i40e_find_mac. + * This function requires you've found * the exact filter you will remove + * already, such as via i40e_find_filter or i40e_find_mac. * * NOTE: This function is expected to be called with mac_filter_hash_lock * being held. @@ -1693,29 +1697,6 @@ void __i40e_del_filter(struct i40e_vsi *vsi, struct i40e_mac_filter *f) } /** - * i40e_del_filter - Remove a MAC/VLAN filter from the VSI - * @vsi: the VSI to be searched - * @macaddr: the MAC address - * @vlan: the VLAN - * - * NOTE: This function is expected to be called with mac_filter_hash_lock - * being held. - * ANOTHER NOTE: This function MUST be called from within the context of - * the "safe" variants of any list iterators, e.g. list_for_each_entry_safe() - * instead of list_for_each_entry(). - **/ -void i40e_del_filter(struct i40e_vsi *vsi, const u8 *macaddr, s16 vlan) -{ - struct i40e_mac_filter *f; - - if (!vsi || !macaddr) - return; - - f = i40e_find_filter(vsi, macaddr, vlan); - __i40e_del_filter(vsi, f); -} - -/** * i40e_add_mac_filter - Add a MAC filter for all active VLANs * @vsi: the VSI to be searched * @macaddr: the mac address to be filtered @@ -1734,6 +1715,7 @@ struct i40e_mac_filter *i40e_add_mac_filter(struct i40e_vsi *vsi, struct hlist_node *h; int bkt; + lockdep_assert_held(&vsi->mac_filter_hash_lock); if (vsi->info.pvid) return i40e_add_filter(vsi, macaddr, le16_to_cpu(vsi->info.pvid)); @@ -2436,7 +2418,8 @@ static int i40e_aqc_broadcast_filter(struct i40e_vsi *vsi, const char *vsi_name, struct i40e_mac_filter *f) { - bool enable = f->state == I40E_FILTER_NEW; + bool enable = f->state == I40E_FILTER_NEW || + f->state == I40E_FILTER_NEW_SYNC; struct i40e_hw *hw = &vsi->back->hw; int aq_ret; @@ -2475,12 +2458,12 @@ i40e_aqc_broadcast_filter(struct i40e_vsi *vsi, const char *vsi_name, **/ static int i40e_set_promiscuous(struct i40e_pf *pf, bool promisc) { - struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; + struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf); struct i40e_hw *hw = &pf->hw; int aq_ret; if (vsi->type == I40E_VSI_MAIN && - pf->lan_veb != I40E_NO_VEB && + i40e_pf_get_main_veb(pf) && !test_bit(I40E_FLAG_MFP_ENA, pf->flags)) { /* set defport ON for Main VSI instead of true promisc * this way we will get all unicast/multicast and VLAN @@ -2610,6 +2593,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) /* Add it to the hash list */ hlist_add_head(&new->hlist, &tmp_add_list); + f->state = I40E_FILTER_NEW_SYNC; } /* Count the number of active (current and new) VLAN @@ -2761,7 +2745,8 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) spin_lock_bh(&vsi->mac_filter_hash_lock); hlist_for_each_entry_safe(new, h, &tmp_add_list, hlist) { /* Only update the state if we're still NEW */ - if (new->f->state == I40E_FILTER_NEW) + if (new->f->state == I40E_FILTER_NEW || + new->f->state == I40E_FILTER_NEW_SYNC) new->f->state = new->state; hlist_del(&new->hlist); netdev_hw_addr_refcnt(new->f, vsi->netdev, -1); @@ -2960,7 +2945,7 @@ static int i40e_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; + WRITE_ONCE(netdev->mtu, new_mtu); if (netif_running(netdev)) i40e_vsi_reinit_locked(vsi); set_bit(__I40E_CLIENT_SERVICE_REQUESTED, pf->state); @@ -4322,7 +4307,7 @@ static irqreturn_t i40e_intr(int irq, void *data) /* only q0 is used in MSI/Legacy mode, and none are used in MSIX */ if (icr0 & I40E_PFINT_ICR0_QUEUE_0_MASK) { - struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; + struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf); struct i40e_q_vector *q_vector = vsi->q_vectors[0]; /* We do not have a way to disarm Queue causes while leaving @@ -5472,7 +5457,7 @@ static u8 i40e_dcb_get_enabled_tc(struct i40e_dcbx_config *dcbcfg) **/ static u8 i40e_mqprio_get_enabled_tc(struct i40e_pf *pf) { - struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; + struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf); u8 num_tc = vsi->mqprio_qopt.qopt.num_tc; u8 enabled_tc = 1, i; @@ -5489,13 +5474,14 @@ static u8 i40e_mqprio_get_enabled_tc(struct i40e_pf *pf) **/ static u8 i40e_pf_get_num_tc(struct i40e_pf *pf) { - struct i40e_hw *hw = &pf->hw; u8 i, enabled_tc = 1; u8 num_tc = 0; - struct i40e_dcbx_config *dcbcfg = &hw->local_dcbx_config; - if (i40e_is_tc_mqprio_enabled(pf)) - return pf->vsi[pf->lan_vsi]->mqprio_qopt.qopt.num_tc; + if (i40e_is_tc_mqprio_enabled(pf)) { + struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf); + + return vsi->mqprio_qopt.qopt.num_tc; + } /* If neither MQPRIO nor DCB is enabled, then always use single TC */ if (!test_bit(I40E_FLAG_DCB_ENA, pf->flags)) @@ -5503,7 +5489,7 @@ static u8 i40e_pf_get_num_tc(struct i40e_pf *pf) /* SFP mode will be enabled for all TCs on port */ if (!test_bit(I40E_FLAG_MFP_ENA, pf->flags)) - return i40e_dcb_get_num_tc(dcbcfg); + return i40e_dcb_get_num_tc(&pf->hw.local_dcbx_config); /* MFP mode return count of enabled TCs for this PF */ if (pf->hw.func_caps.iscsi) @@ -5916,6 +5902,28 @@ out: } /** + * i40e_vsi_reconfig_tc - Reconfigure VSI Tx Scheduler for stored TC map + * @vsi: VSI to be reconfigured + * + * This reconfigures a particular VSI for TCs that are mapped to the + * TC bitmap stored previously for the VSI. + * + * Context: It is expected that the VSI queues have been quisced before + * calling this function. + * + * Return: 0 on success, negative value on failure + **/ +static int i40e_vsi_reconfig_tc(struct i40e_vsi *vsi) +{ + u8 enabled_tc; + + enabled_tc = vsi->tc_config.enabled_tc; + vsi->tc_config.enabled_tc = 0; + + return i40e_vsi_config_tc(vsi, enabled_tc); +} + +/** * i40e_get_link_speed - Returns link speed for the interface * @vsi: VSI to be configured * @@ -6477,6 +6485,7 @@ static inline int i40e_setup_hw_channel(struct i40e_pf *pf, static bool i40e_setup_channel(struct i40e_pf *pf, struct i40e_vsi *vsi, struct i40e_channel *ch) { + struct i40e_vsi *main_vsi; u8 vsi_type; u16 seid; int ret; @@ -6490,7 +6499,8 @@ static bool i40e_setup_channel(struct i40e_pf *pf, struct i40e_vsi *vsi, } /* underlying switching element */ - seid = pf->vsi[pf->lan_vsi]->uplink_seid; + main_vsi = i40e_pf_get_main_vsi(pf); + seid = main_vsi->uplink_seid; /* create channel (VSI), configure TX rings */ ret = i40e_setup_hw_channel(pf, vsi, ch, seid, vsi_type); @@ -6808,7 +6818,7 @@ static void i40e_dcb_reconfigure(struct i40e_pf *pf) /* - Enable all TCs for the LAN VSI * - For all others keep them at TC0 for now */ - if (v == pf->lan_vsi) + if (vsi->type == I40E_VSI_MAIN) tc_map = i40e_pf_get_tc_map(pf); else tc_map = I40E_DEFAULT_TRAFFIC_CLASS; @@ -7047,7 +7057,9 @@ int i40e_hw_dcb_config(struct i40e_pf *pf, struct i40e_dcbx_config *new_cfg) /* Configure Rx Packet Buffers in HW */ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { - mfs_tc[i] = pf->vsi[pf->lan_vsi]->netdev->mtu; + struct i40e_vsi *main_vsi = i40e_pf_get_main_vsi(pf); + + mfs_tc[i] = main_vsi->netdev->mtu; mfs_tc[i] += I40E_PACKET_HDR_PAD; } @@ -7237,6 +7249,26 @@ out: } #endif /* CONFIG_I40E_DCB */ +static void i40e_print_link_message_eee(struct i40e_vsi *vsi, + const char *speed, const char *fc) +{ + struct ethtool_keee kedata; + + memzero_explicit(&kedata, sizeof(kedata)); + if (vsi->netdev->ethtool_ops->get_eee) + vsi->netdev->ethtool_ops->get_eee(vsi->netdev, &kedata); + + if (!linkmode_empty(kedata.supported)) + netdev_info(vsi->netdev, + "NIC Link is Up, %sbps Full Duplex, Flow Control: %s, EEE: %s\n", + speed, fc, + kedata.eee_enabled ? "Enabled" : "Disabled"); + else + netdev_info(vsi->netdev, + "NIC Link is Up, %sbps Full Duplex, Flow Control: %s\n", + speed, fc); +} + /** * i40e_print_link_message - print link up or down * @vsi: the VSI for which link needs a message @@ -7368,9 +7400,7 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) "NIC Link is Up, %sbps Full Duplex, Requested FEC: %s, Negotiated FEC: %s, Autoneg: %s, Flow Control: %s\n", speed, req_fec, fec, an, fc); } else { - netdev_info(vsi->netdev, - "NIC Link is Up, %sbps Full Duplex, Flow Control: %s\n", - speed, fc); + i40e_print_link_message_eee(vsi, speed, fc); } } @@ -8643,6 +8673,10 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi, flow_rule_match_control(rule, &match); addr_type = match.key->addr_type; + + if (flow_rule_has_control_flags(match.mask->flags, + f->common.extack)) + return -EOPNOTSUPP; } if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { @@ -9113,7 +9147,7 @@ err_setup_rx: i40e_vsi_free_rx_resources(vsi); err_setup_tx: i40e_vsi_free_tx_resources(vsi); - if (vsi == pf->vsi[pf->lan_vsi]) + if (vsi->type == I40E_VSI_MAIN) i40e_do_reset(pf, I40E_PF_RESET_FLAG, true); return err; @@ -9571,19 +9605,6 @@ static void i40e_handle_lan_overflow_event(struct i40e_pf *pf, } /** - * i40e_get_cur_guaranteed_fd_count - Get the consumed guaranteed FD filters - * @pf: board private structure - **/ -u32 i40e_get_cur_guaranteed_fd_count(struct i40e_pf *pf) -{ - u32 val, fcnt_prog; - - val = rd32(&pf->hw, I40E_PFQF_FDSTAT); - fcnt_prog = (val & I40E_PFQF_FDSTAT_GUARANT_CNT_MASK); - return fcnt_prog; -} - -/** * i40e_get_current_fd_count - Get total FD filters programmed for this PF * @pf: board private structure **/ @@ -9804,7 +9825,7 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf) dev_warn(&pf->pdev->dev, "FD table did not flush, needs more time\n"); } else { /* replay sideband filters */ - i40e_fdir_filter_restore(pf->vsi[pf->lan_vsi]); + i40e_fdir_filter_restore(i40e_pf_get_main_vsi(pf)); if (!disable_atr && !pf->fd_tcp4_filter_cnt) clear_bit(__I40E_FD_ATR_AUTO_DISABLED, pf->state); clear_bit(__I40E_FD_FLUSH_REQUESTED, pf->state); @@ -9902,7 +9923,8 @@ static void i40e_veb_link_event(struct i40e_veb *veb, bool link_up) **/ static void i40e_link_event(struct i40e_pf *pf) { - struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; + struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf); + struct i40e_veb *veb = i40e_pf_get_main_veb(pf); u8 new_link_speed, old_link_speed; bool new_link, old_link; int status; @@ -9942,8 +9964,8 @@ static void i40e_link_event(struct i40e_pf *pf) /* Notify the base of the switch tree connected to * the link. Floating VEBs are not notified. */ - if (pf->lan_veb < I40E_MAX_VEB && pf->veb[pf->lan_veb]) - i40e_veb_link_event(pf->veb[pf->lan_veb], new_link); + if (veb) + i40e_veb_link_event(veb, new_link); else i40e_vsi_link_event(vsi, new_link); @@ -10273,7 +10295,7 @@ static void i40e_verify_eeprom(struct i40e_pf *pf) **/ static void i40e_enable_pf_switch_lb(struct i40e_pf *pf) { - struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; + struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf); struct i40e_vsi_context ctxt; int ret; @@ -10309,7 +10331,7 @@ static void i40e_enable_pf_switch_lb(struct i40e_pf *pf) **/ static void i40e_disable_pf_switch_lb(struct i40e_pf *pf) { - struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; + struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf); struct i40e_vsi_context ctxt; int ret; @@ -10385,7 +10407,7 @@ static int i40e_reconstitute_veb(struct i40e_veb *veb) if (veb->uplink_seid == pf->mac_seid) { /* Check that the LAN VSI has VEB owning flag set */ - ctl_vsi = pf->vsi[pf->lan_vsi]; + ctl_vsi = i40e_pf_get_main_vsi(pf); if (WARN_ON(ctl_vsi->veb_idx != veb->idx || !(ctl_vsi->flags & I40E_VSI_FLAG_VEB_OWNER))) { @@ -10528,7 +10550,7 @@ static int i40e_vsi_clear(struct i40e_vsi *vsi); **/ static void i40e_fdir_sb_setup(struct i40e_pf *pf) { - struct i40e_vsi *vsi; + struct i40e_vsi *main_vsi, *vsi; /* quick workaround for an NVM issue that leaves a critical register * uninitialized @@ -10553,8 +10575,8 @@ static void i40e_fdir_sb_setup(struct i40e_pf *pf) /* create a new VSI if none exists */ if (!vsi) { - vsi = i40e_vsi_setup(pf, I40E_VSI_FDIR, - pf->vsi[pf->lan_vsi]->seid, 0); + main_vsi = i40e_pf_get_main_vsi(pf); + vsi = i40e_vsi_setup(pf, I40E_VSI_FDIR, main_vsi->seid, 0); if (!vsi) { dev_info(&pf->pdev->dev, "Couldn't create FDir VSI\n"); clear_bit(I40E_FLAG_FD_SB_ENA, pf->flags); @@ -10833,7 +10855,7 @@ static int i40e_reset(struct i40e_pf *pf) static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) { const bool is_recovery_mode_reported = i40e_check_recovery_mode(pf); - struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; + struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf); struct i40e_hw *hw = &pf->hw; struct i40e_veb *veb; int ret; @@ -10842,7 +10864,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) if (test_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state) && is_recovery_mode_reported) - i40e_set_ethtool_ops(pf->vsi[pf->lan_vsi]->netdev); + i40e_set_ethtool_ops(vsi->netdev); if (test_bit(__I40E_DOWN, pf->state) && !test_bit(__I40E_RECOVERY_MODE, pf->state)) @@ -11138,6 +11160,8 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit, ret = i40e_reset(pf); if (!ret) i40e_rebuild(pf, reinit, lock_acquired); + else + dev_err(&pf->pdev->dev, "%s: i40e_reset() FAILED", __func__); } /** @@ -11156,6 +11180,67 @@ static void i40e_handle_reset_warning(struct i40e_pf *pf, bool lock_acquired) } /** + * i40e_print_vf_mdd_event - print VF Tx/Rx malicious driver detect event + * @pf: board private structure + * @vf: pointer to the VF structure + * @is_tx: true - for Tx event, false - for Rx + */ +static void i40e_print_vf_mdd_event(struct i40e_pf *pf, struct i40e_vf *vf, + bool is_tx) +{ + dev_err(&pf->pdev->dev, is_tx ? + "%lld Tx Malicious Driver Detection events detected on PF %d VF %d MAC %pm. mdd-auto-reset-vfs=%s\n" : + "%lld Rx Malicious Driver Detection events detected on PF %d VF %d MAC %pm. mdd-auto-reset-vfs=%s\n", + is_tx ? vf->mdd_tx_events.count : vf->mdd_rx_events.count, + pf->hw.pf_id, + vf->vf_id, + vf->default_lan_addr.addr, + str_on_off(test_bit(I40E_FLAG_MDD_AUTO_RESET_VF, pf->flags))); +} + +/** + * i40e_print_vfs_mdd_events - print VFs malicious driver detect event + * @pf: pointer to the PF structure + * + * Called from i40e_handle_mdd_event to rate limit and print VFs MDD events. + */ +static void i40e_print_vfs_mdd_events(struct i40e_pf *pf) +{ + unsigned int i; + + /* check that there are pending MDD events to print */ + if (!test_and_clear_bit(__I40E_MDD_VF_PRINT_PENDING, pf->state)) + return; + + if (!__ratelimit(&pf->mdd_message_rate_limit)) + return; + + for (i = 0; i < pf->num_alloc_vfs; i++) { + struct i40e_vf *vf = &pf->vf[i]; + bool is_printed = false; + + /* only print Rx MDD event message if there are new events */ + if (vf->mdd_rx_events.count != vf->mdd_rx_events.last_printed) { + vf->mdd_rx_events.last_printed = vf->mdd_rx_events.count; + i40e_print_vf_mdd_event(pf, vf, false); + is_printed = true; + } + + /* only print Tx MDD event message if there are new events */ + if (vf->mdd_tx_events.count != vf->mdd_tx_events.last_printed) { + vf->mdd_tx_events.last_printed = vf->mdd_tx_events.count; + i40e_print_vf_mdd_event(pf, vf, true); + is_printed = true; + } + + if (is_printed && !test_bit(I40E_FLAG_MDD_AUTO_RESET_VF, pf->flags)) + dev_info(&pf->pdev->dev, + "Use PF Control I/F to re-enable the VF #%d\n", + i); + } +} + +/** * i40e_handle_mdd_event * @pf: pointer to the PF structure * @@ -11169,8 +11254,13 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf) u32 reg; int i; - if (!test_bit(__I40E_MDD_EVENT_PENDING, pf->state)) + if (!test_and_clear_bit(__I40E_MDD_EVENT_PENDING, pf->state)) { + /* Since the VF MDD event logging is rate limited, check if + * there are pending MDD events. + */ + i40e_print_vfs_mdd_events(pf); return; + } /* find what triggered the MDD event */ reg = rd32(hw, I40E_GL_MDET_TX); @@ -11214,36 +11304,48 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf) /* see if one of the VFs needs its hand slapped */ for (i = 0; i < pf->num_alloc_vfs && mdd_detected; i++) { + bool is_mdd_on_tx = false; + bool is_mdd_on_rx = false; + vf = &(pf->vf[i]); reg = rd32(hw, I40E_VP_MDET_TX(i)); if (reg & I40E_VP_MDET_TX_VALID_MASK) { + set_bit(__I40E_MDD_VF_PRINT_PENDING, pf->state); wr32(hw, I40E_VP_MDET_TX(i), 0xFFFF); - vf->num_mdd_events++; - dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n", - i); - dev_info(&pf->pdev->dev, - "Use PF Control I/F to re-enable the VF\n"); + vf->mdd_tx_events.count++; set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states); + is_mdd_on_tx = true; } reg = rd32(hw, I40E_VP_MDET_RX(i)); if (reg & I40E_VP_MDET_RX_VALID_MASK) { + set_bit(__I40E_MDD_VF_PRINT_PENDING, pf->state); wr32(hw, I40E_VP_MDET_RX(i), 0xFFFF); - vf->num_mdd_events++; - dev_info(&pf->pdev->dev, "RX driver issue detected on VF %d\n", - i); - dev_info(&pf->pdev->dev, - "Use PF Control I/F to re-enable the VF\n"); + vf->mdd_rx_events.count++; set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states); + is_mdd_on_rx = true; + } + + if ((is_mdd_on_tx || is_mdd_on_rx) && + test_bit(I40E_FLAG_MDD_AUTO_RESET_VF, pf->flags)) { + /* VF MDD event counters will be cleared by + * reset, so print the event prior to reset. + */ + if (is_mdd_on_rx) + i40e_print_vf_mdd_event(pf, vf, false); + if (is_mdd_on_tx) + i40e_print_vf_mdd_event(pf, vf, true); + + i40e_vc_reset_vf(vf, true); } } - /* re-enable mdd interrupt cause */ - clear_bit(__I40E_MDD_EVENT_PENDING, pf->state); reg = rd32(hw, I40E_PFINT_ICR0_ENA); reg |= I40E_PFINT_ICR0_ENA_MAL_DETECT_MASK; wr32(hw, I40E_PFINT_ICR0_ENA, reg); i40e_flush(hw); + + i40e_print_vfs_mdd_events(pf); } /** @@ -11266,7 +11368,7 @@ static void i40e_service_task(struct work_struct *work) return; if (!test_bit(__I40E_RECOVERY_MODE, pf->state)) { - i40e_detect_recover_hung(pf->vsi[pf->lan_vsi]); + i40e_detect_recover_hung(pf); i40e_sync_filters_subtask(pf); i40e_reset_subtask(pf); i40e_handle_mdd_event(pf); @@ -11275,14 +11377,12 @@ static void i40e_service_task(struct work_struct *work) i40e_fdir_reinit_subtask(pf); if (test_and_clear_bit(__I40E_CLIENT_RESET, pf->state)) { /* Client subtask will reopen next time through. */ - i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], - true); + i40e_notify_client_of_netdev_close(pf, true); } else { i40e_client_subtask(pf); if (test_and_clear_bit(__I40E_CLIENT_L2_CHANGE, pf->state)) - i40e_notify_client_of_l2_param_changes( - pf->vsi[pf->lan_vsi]); + i40e_notify_client_of_l2_param_changes(pf); } i40e_sync_filters_subtask(pf); } else { @@ -11990,7 +12090,7 @@ static int i40e_vsi_alloc_q_vectors(struct i40e_vsi *vsi) /* if not MSIX, give the one vector only to the LAN VSI */ if (test_bit(I40E_FLAG_MSIX_ENA, pf->flags)) num_q_vectors = vsi->num_q_vectors; - else if (vsi == pf->vsi[pf->lan_vsi]) + else if (vsi->type == I40E_VSI_MAIN) num_q_vectors = 1; else return -EINVAL; @@ -12396,7 +12496,7 @@ void i40e_fill_rss_lut(struct i40e_pf *pf, u8 *lut, **/ static int i40e_pf_config_rss(struct i40e_pf *pf) { - struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; + struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf); u8 seed[I40E_HKEY_ARRAY_SIZE]; u8 *lut; struct i40e_hw *hw = &pf->hw; @@ -12468,7 +12568,7 @@ static int i40e_pf_config_rss(struct i40e_pf *pf) **/ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count) { - struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; + struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf); int new_rss_size; if (!test_bit(I40E_FLAG_RSS_ENA, pf->flags)) @@ -12555,89 +12655,6 @@ int i40e_set_partition_bw_setting(struct i40e_pf *pf) } /** - * i40e_commit_partition_bw_setting - Commit BW settings for this PF partition - * @pf: board private structure - **/ -int i40e_commit_partition_bw_setting(struct i40e_pf *pf) -{ - /* Commit temporary BW setting to permanent NVM image */ - enum i40e_admin_queue_err last_aq_status; - u16 nvm_word; - int ret; - - if (pf->hw.partition_id != 1) { - dev_info(&pf->pdev->dev, - "Commit BW only works on partition 1! This is partition %d", - pf->hw.partition_id); - ret = -EOPNOTSUPP; - goto bw_commit_out; - } - - /* Acquire NVM for read access */ - ret = i40e_acquire_nvm(&pf->hw, I40E_RESOURCE_READ); - last_aq_status = pf->hw.aq.asq_last_status; - if (ret) { - dev_info(&pf->pdev->dev, - "Cannot acquire NVM for read access, err %pe aq_err %s\n", - ERR_PTR(ret), - i40e_aq_str(&pf->hw, last_aq_status)); - goto bw_commit_out; - } - - /* Read word 0x10 of NVM - SW compatibility word 1 */ - ret = i40e_aq_read_nvm(&pf->hw, - I40E_SR_NVM_CONTROL_WORD, - 0x10, sizeof(nvm_word), &nvm_word, - false, NULL); - /* Save off last admin queue command status before releasing - * the NVM - */ - last_aq_status = pf->hw.aq.asq_last_status; - i40e_release_nvm(&pf->hw); - if (ret) { - dev_info(&pf->pdev->dev, "NVM read error, err %pe aq_err %s\n", - ERR_PTR(ret), - i40e_aq_str(&pf->hw, last_aq_status)); - goto bw_commit_out; - } - - /* Wait a bit for NVM release to complete */ - msleep(50); - - /* Acquire NVM for write access */ - ret = i40e_acquire_nvm(&pf->hw, I40E_RESOURCE_WRITE); - last_aq_status = pf->hw.aq.asq_last_status; - if (ret) { - dev_info(&pf->pdev->dev, - "Cannot acquire NVM for write access, err %pe aq_err %s\n", - ERR_PTR(ret), - i40e_aq_str(&pf->hw, last_aq_status)); - goto bw_commit_out; - } - /* Write it back out unchanged to initiate update NVM, - * which will force a write of the shadow (alt) RAM to - * the NVM - thus storing the bandwidth values permanently. - */ - ret = i40e_aq_update_nvm(&pf->hw, - I40E_SR_NVM_CONTROL_WORD, - 0x10, sizeof(nvm_word), - &nvm_word, true, 0, NULL); - /* Save off last admin queue command status before releasing - * the NVM - */ - last_aq_status = pf->hw.aq.asq_last_status; - i40e_release_nvm(&pf->hw); - if (ret) - dev_info(&pf->pdev->dev, - "BW settings NOT SAVED, err %pe aq_err %s\n", - ERR_PTR(ret), - i40e_aq_str(&pf->hw, last_aq_status)); -bw_commit_out: - - return ret; -} - -/** * i40e_is_total_port_shutdown_enabled - read NVM and return value * if total port shutdown feature is enabled for this PF * @pf: board private structure @@ -13036,12 +13053,13 @@ static int i40e_get_phys_port_id(struct net_device *netdev, * @addr: the MAC address entry being added * @vid: VLAN ID * @flags: instructions from stack about fdb operation + * @notified: whether notification was emitted * @extack: netlink extended ack, unused currently */ static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, - u16 flags, + u16 flags, bool *notified, struct netlink_ext_ack *extack) { struct i40e_netdev_priv *np = netdev_priv(dev); @@ -13107,7 +13125,7 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev, int rem; /* Only for PF VSI for now */ - if (vsi->seid != pf->vsi[pf->lan_vsi]->seid) + if (vsi->type != I40E_VSI_MAIN) return -EOPNOTSUPP; /* Find the HW bridge for PF VSI */ @@ -13117,20 +13135,16 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev, if (!br_spec) return -EINVAL; - nla_for_each_nested(attr, br_spec, rem) { - __u16 mode; + nla_for_each_nested_type(attr, IFLA_BRIDGE_MODE, br_spec, rem) { + __u16 mode = nla_get_u16(attr); - if (nla_type(attr) != IFLA_BRIDGE_MODE) - continue; - - mode = nla_get_u16(attr); if ((mode != BRIDGE_MODE_VEPA) && (mode != BRIDGE_MODE_VEB)) return -EINVAL; /* Insert a new HW bridge */ if (!veb) { - veb = i40e_veb_setup(pf, 0, vsi->uplink_seid, vsi->seid, + veb = i40e_veb_setup(pf, vsi->uplink_seid, vsi->seid, vsi->tc_config.enabled_tc); if (veb) { veb->bridge_mode = mode; @@ -13179,7 +13193,7 @@ static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct i40e_veb *veb; /* Only for PF VSI for now */ - if (vsi->seid != pf->vsi[pf->lan_vsi]->seid) + if (vsi->type != I40E_VSI_MAIN) return -EOPNOTSUPP; /* Find the HW bridge for the PF VSI */ @@ -13264,6 +13278,10 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, struct bpf_prog *prog, bool need_reset; int i; + /* VSI shall be deleted in a moment, block loading new programs */ + if (prog && test_bit(__I40E_IN_REMOVE, pf->state)) + return -EINVAL; + /* Don't allow frames that span over multiple buffers */ if (vsi->netdev->mtu > frame_size - I40E_PACKET_HDR_PAD) { NL_SET_ERR_MSG_MOD(extack, "MTU too large for linear frames and XDP prog does not support frags"); @@ -13272,14 +13290,9 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, struct bpf_prog *prog, /* When turning XDP on->off/off->on we reset and rebuild the rings. */ need_reset = (i40e_enabled_xdp_vsi(vsi) != !!prog); - if (need_reset) i40e_prep_for_reset(pf); - /* VSI shall be deleted in a moment, just return EINVAL */ - if (test_bit(__I40E_IN_REMOVE, pf->state)) - return -EINVAL; - old_prog = xchg(&vsi->xdp_prog, prog); if (need_reset) { @@ -13761,9 +13774,10 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) * the end, which is 4 bytes long, so force truncation of the * original name by IFNAMSIZ - 4 */ - snprintf(netdev->name, IFNAMSIZ, "%.*sv%%d", - IFNAMSIZ - 4, - pf->vsi[pf->lan_vsi]->netdev->name); + struct i40e_vsi *main_vsi = i40e_pf_get_main_vsi(pf); + + snprintf(netdev->name, IFNAMSIZ, "%.*sv%%d", IFNAMSIZ - 4, + main_vsi->netdev->name); eth_random_addr(mac_addr); spin_lock_bh(&vsi->mac_filter_hash_lock); @@ -14130,8 +14144,7 @@ int i40e_vsi_release(struct i40e_vsi *vsi) vsi->seid, vsi->uplink_seid); return -ENODEV; } - if (vsi == pf->vsi[pf->lan_vsi] && - !test_bit(__I40E_DOWN, pf->state)) { + if (vsi->type == I40E_VSI_MAIN && !test_bit(__I40E_DOWN, pf->state)) { dev_info(&pf->pdev->dev, "Can't remove PF VSI\n"); return -ENODEV; } @@ -14275,9 +14288,9 @@ vector_setup_out: **/ static struct i40e_vsi *i40e_vsi_reinit_setup(struct i40e_vsi *vsi) { + struct i40e_vsi *main_vsi; u16 alloc_queue_pairs; struct i40e_pf *pf; - u8 enabled_tc; int ret; if (!vsi) @@ -14309,10 +14322,10 @@ static struct i40e_vsi *i40e_vsi_reinit_setup(struct i40e_vsi *vsi) /* Update the FW view of the VSI. Force a reset of TC and queue * layout configurations. */ - enabled_tc = pf->vsi[pf->lan_vsi]->tc_config.enabled_tc; - pf->vsi[pf->lan_vsi]->tc_config.enabled_tc = 0; - pf->vsi[pf->lan_vsi]->seid = pf->main_vsi_seid; - i40e_vsi_config_tc(pf->vsi[pf->lan_vsi], enabled_tc); + main_vsi = i40e_pf_get_main_vsi(pf); + main_vsi->seid = pf->main_vsi_seid; + i40e_vsi_reconfig_tc(main_vsi); + if (vsi->type == I40E_VSI_MAIN) i40e_rm_default_mac_filter(vsi, pf->hw.mac.perm_addr); @@ -14386,13 +14399,13 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type, } if (vsi->uplink_seid == pf->mac_seid) - veb = i40e_veb_setup(pf, 0, pf->mac_seid, vsi->seid, + veb = i40e_veb_setup(pf, pf->mac_seid, vsi->seid, vsi->tc_config.enabled_tc); else if ((vsi->flags & I40E_VSI_FLAG_VEB_OWNER) == 0) - veb = i40e_veb_setup(pf, 0, vsi->uplink_seid, vsi->seid, + veb = i40e_veb_setup(pf, vsi->uplink_seid, vsi->seid, vsi->tc_config.enabled_tc); if (veb) { - if (vsi->seid != pf->vsi[pf->lan_vsi]->seid) { + if (vsi->type != I40E_VSI_MAIN) { dev_info(&vsi->back->pdev->dev, "New VSI creation error, uplink seid of LAN VSI expected.\n"); return NULL; @@ -14783,7 +14796,6 @@ static int i40e_add_veb(struct i40e_veb *veb, struct i40e_vsi *vsi) /** * i40e_veb_setup - Set up a VEB * @pf: board private structure - * @flags: VEB setup flags * @uplink_seid: the switch element to link to * @vsi_seid: the initial VSI seid * @enabled_tc: Enabled TC bit-map @@ -14796,9 +14808,8 @@ static int i40e_add_veb(struct i40e_veb *veb, struct i40e_vsi *vsi) * Returns pointer to the successfully allocated VEB sw struct on * success, otherwise returns NULL on failure. **/ -struct i40e_veb *i40e_veb_setup(struct i40e_pf *pf, u16 flags, - u16 uplink_seid, u16 vsi_seid, - u8 enabled_tc) +struct i40e_veb *i40e_veb_setup(struct i40e_pf *pf, u16 uplink_seid, + u16 vsi_seid, u8 enabled_tc) { struct i40e_vsi *vsi = NULL; struct i40e_veb *veb; @@ -14829,7 +14840,6 @@ struct i40e_veb *i40e_veb_setup(struct i40e_pf *pf, u16 flags, if (veb_idx < 0) goto err_alloc; veb = pf->veb[veb_idx]; - veb->flags = flags; veb->uplink_seid = uplink_seid; veb->enabled_tc = (enabled_tc ? enabled_tc : 0x1); @@ -14881,7 +14891,8 @@ static void i40e_setup_pf_switch_element(struct i40e_pf *pf, /* Main VEB? */ if (uplink_seid != pf->mac_seid) break; - if (pf->lan_veb >= I40E_MAX_VEB) { + veb = i40e_pf_get_main_veb(pf); + if (!veb) { int v; /* find existing or else empty VEB */ @@ -14895,12 +14906,15 @@ static void i40e_setup_pf_switch_element(struct i40e_pf *pf, pf->lan_veb = v; } } - if (pf->lan_veb >= I40E_MAX_VEB) + + /* Try to get again main VEB as pf->lan_veb may have changed */ + veb = i40e_pf_get_main_veb(pf); + if (!veb) break; - pf->veb[pf->lan_veb]->seid = seid; - pf->veb[pf->lan_veb]->uplink_seid = pf->mac_seid; - pf->veb[pf->lan_veb]->pf = pf; + veb->seid = seid; + veb->uplink_seid = pf->mac_seid; + veb->pf = pf; break; case I40E_SWITCH_ELEMENT_TYPE_VSI: if (num_reported != 1) @@ -14998,6 +15012,7 @@ int i40e_fetch_switch_configuration(struct i40e_pf *pf, bool printconfig) **/ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit, bool lock_acquired) { + struct i40e_vsi *main_vsi; u16 flags = 0; int ret; @@ -15042,22 +15057,25 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit, bool lock_acqui } /* first time setup */ - if (pf->lan_vsi == I40E_NO_VSI || reinit) { - struct i40e_vsi *vsi = NULL; + main_vsi = i40e_pf_get_main_vsi(pf); + if (!main_vsi || reinit) { + struct i40e_veb *veb; u16 uplink_seid; /* Set up the PF VSI associated with the PF's main VSI * that is already in the HW switch */ - if (pf->lan_veb < I40E_MAX_VEB && pf->veb[pf->lan_veb]) - uplink_seid = pf->veb[pf->lan_veb]->seid; + veb = i40e_pf_get_main_veb(pf); + if (veb) + uplink_seid = veb->seid; else uplink_seid = pf->mac_seid; - if (pf->lan_vsi == I40E_NO_VSI) - vsi = i40e_vsi_setup(pf, I40E_VSI_MAIN, uplink_seid, 0); + if (!main_vsi) + main_vsi = i40e_vsi_setup(pf, I40E_VSI_MAIN, + uplink_seid, 0); else if (reinit) - vsi = i40e_vsi_reinit_setup(pf->vsi[pf->lan_vsi]); - if (!vsi) { + main_vsi = i40e_vsi_reinit_setup(main_vsi); + if (!main_vsi) { dev_info(&pf->pdev->dev, "setup of MAIN VSI failed\n"); i40e_cloud_filter_exit(pf); i40e_fdir_teardown(pf); @@ -15065,13 +15083,10 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit, bool lock_acqui } } else { /* force a reset of TC and queue layout configurations */ - u8 enabled_tc = pf->vsi[pf->lan_vsi]->tc_config.enabled_tc; - - pf->vsi[pf->lan_vsi]->tc_config.enabled_tc = 0; - pf->vsi[pf->lan_vsi]->seid = pf->main_vsi_seid; - i40e_vsi_config_tc(pf->vsi[pf->lan_vsi], enabled_tc); + main_vsi->seid = pf->main_vsi_seid; + i40e_vsi_reconfig_tc(main_vsi); } - i40e_vlan_stripping_disable(pf->vsi[pf->lan_vsi]); + i40e_vlan_stripping_disable(main_vsi); i40e_fdir_sb_setup(pf); @@ -15098,7 +15113,7 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit, bool lock_acqui rtnl_lock(); /* repopulate tunnel port filters */ - udp_tunnel_nic_reset_ntf(pf->vsi[pf->lan_vsi]->netdev); + udp_tunnel_nic_reset_ntf(main_vsi->netdev); if (!lock_acquired) rtnl_unlock(); @@ -15242,6 +15257,7 @@ static int i40e_setup_pf_filter_control(struct i40e_pf *pf) #define REMAIN(__x) (INFO_STRING_LEN - (__x)) static void i40e_print_features(struct i40e_pf *pf) { + struct i40e_vsi *main_vsi = i40e_pf_get_main_vsi(pf); struct i40e_hw *hw = &pf->hw; char *buf; int i; @@ -15255,8 +15271,7 @@ static void i40e_print_features(struct i40e_pf *pf) i += scnprintf(&buf[i], REMAIN(i), " VFs: %d", pf->num_req_vfs); #endif i += scnprintf(&buf[i], REMAIN(i), " VSIs: %d QP: %d", - pf->hw.func_caps.num_vsis, - pf->vsi[pf->lan_vsi]->num_queue_pairs); + pf->hw.func_caps.num_vsis, main_vsi->num_queue_pairs); if (test_bit(I40E_FLAG_RSS_ENA, pf->flags)) i += scnprintf(&buf[i], REMAIN(i), " RSS"); if (test_bit(I40E_FLAG_FD_ATR_ENA, pf->flags)) @@ -15920,7 +15935,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_info(&pdev->dev, "setup_pf_switch failed: %d\n", err); goto err_vsis; } - INIT_LIST_HEAD(&pf->vsi[pf->lan_vsi]->ch_list); + + vsi = i40e_pf_get_main_vsi(pf); + INIT_LIST_HEAD(&vsi->ch_list); /* if FDIR VSI was set up, start it now */ vsi = i40e_find_vsi_by_type(pf, I40E_VSI_FDIR); @@ -15939,6 +15956,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) ERR_PTR(err), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + /* VF MDD event logs are rate limited to one second intervals */ + ratelimit_state_init(&pf->mdd_message_rate_limit, 1 * HZ, 1); + /* Reconfigure hardware for allowing smaller MSS in the case * of TSO, so that we avoid the MDD being fired and causing * a reset in the case of small MSS+TSO. @@ -16223,7 +16243,7 @@ static void i40e_remove(struct pci_dev *pdev) /* Client close must be called explicitly here because the timer * has been stopped. */ - i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], false); + i40e_notify_client_of_netdev_close(pf, false); i40e_fdir_teardown(pf); @@ -16304,6 +16324,139 @@ unmap: } /** + * i40e_enable_mc_magic_wake - enable multicast magic packet wake up + * using the mac_address_write admin q function + * @pf: pointer to i40e_pf struct + **/ +static void i40e_enable_mc_magic_wake(struct i40e_pf *pf) +{ + struct i40e_vsi *main_vsi = i40e_pf_get_main_vsi(pf); + struct i40e_hw *hw = &pf->hw; + u8 mac_addr[6]; + u16 flags = 0; + int ret; + + /* Get current MAC address in case it's an LAA */ + if (main_vsi && main_vsi->netdev) { + ether_addr_copy(mac_addr, main_vsi->netdev->dev_addr); + } else { + dev_err(&pf->pdev->dev, + "Failed to retrieve MAC address; using default\n"); + ether_addr_copy(mac_addr, hw->mac.addr); + } + + /* The FW expects the mac address write cmd to first be called with + * one of these flags before calling it again with the multicast + * enable flags. + */ + flags = I40E_AQC_WRITE_TYPE_LAA_WOL; + + if (hw->func_caps.flex10_enable && hw->partition_id != 1) + flags = I40E_AQC_WRITE_TYPE_LAA_ONLY; + + ret = i40e_aq_mac_address_write(hw, flags, mac_addr, NULL); + if (ret) { + dev_err(&pf->pdev->dev, + "Failed to update MAC address registers; cannot enable Multicast Magic packet wake up"); + return; + } + + flags = I40E_AQC_MC_MAG_EN + | I40E_AQC_WOL_PRESERVE_ON_PFR + | I40E_AQC_WRITE_TYPE_UPDATE_MC_MAG; + ret = i40e_aq_mac_address_write(hw, flags, mac_addr, NULL); + if (ret) + dev_err(&pf->pdev->dev, + "Failed to enable Multicast Magic Packet wake up\n"); +} + +/** + * i40e_io_suspend - suspend all IO operations + * @pf: pointer to i40e_pf struct + * + **/ +static int i40e_io_suspend(struct i40e_pf *pf) +{ + struct i40e_hw *hw = &pf->hw; + + set_bit(__I40E_DOWN, pf->state); + + /* Ensure service task will not be running */ + timer_delete_sync(&pf->service_timer); + cancel_work_sync(&pf->service_task); + + /* Client close must be called explicitly here because the timer + * has been stopped. + */ + i40e_notify_client_of_netdev_close(pf, false); + + if (test_bit(I40E_HW_CAP_WOL_MC_MAGIC_PKT_WAKE, pf->hw.caps) && + pf->wol_en) + i40e_enable_mc_magic_wake(pf); + + /* Since we're going to destroy queues during the + * i40e_clear_interrupt_scheme() we should hold the RTNL lock for this + * whole section + */ + rtnl_lock(); + + i40e_prep_for_reset(pf); + + wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0)); + wr32(hw, I40E_PFPM_WUFC, (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0)); + + /* Clear the interrupt scheme and release our IRQs so that the system + * can safely hibernate even when there are a large number of CPUs. + * Otherwise hibernation might fail when mapping all the vectors back + * to CPU0. + */ + i40e_clear_interrupt_scheme(pf); + + rtnl_unlock(); + + return 0; +} + +/** + * i40e_io_resume - resume IO operations + * @pf: pointer to i40e_pf struct + * + **/ +static int i40e_io_resume(struct i40e_pf *pf) +{ + struct device *dev = &pf->pdev->dev; + int err; + + /* We need to hold the RTNL lock prior to restoring interrupt schemes, + * since we're going to be restoring queues + */ + rtnl_lock(); + + /* We cleared the interrupt scheme when we suspended, so we need to + * restore it now to resume device functionality. + */ + err = i40e_restore_interrupt_scheme(pf); + if (err) { + dev_err(dev, "Cannot restore interrupt scheme: %d\n", + err); + } + + clear_bit(__I40E_DOWN, pf->state); + i40e_reset_and_rebuild(pf, false, true); + + rtnl_unlock(); + + /* Clear suspended state last after everything is recovered */ + clear_bit(__I40E_SUSPENDED, pf->state); + + /* Restart the service task */ + mod_timer(&pf->service_timer, + round_jiffies(jiffies + pf->service_timer_period)); + + return 0; +} + +/** * i40e_pci_error_detected - warning that something funky happened in PCI land * @pdev: PCI device information struct * @error: the type of PCI error @@ -16327,7 +16480,7 @@ static pci_ers_result_t i40e_pci_error_detected(struct pci_dev *pdev, /* shutdown all operations */ if (!test_bit(__I40E_SUSPENDED, pf->state)) - i40e_prep_for_reset(pf); + i40e_io_suspend(pf); /* Request a slot reset */ return PCI_ERS_RESULT_NEED_RESET; @@ -16349,7 +16502,8 @@ static pci_ers_result_t i40e_pci_error_slot_reset(struct pci_dev *pdev) u32 reg; dev_dbg(&pdev->dev, "%s\n", __func__); - if (pci_enable_device_mem(pdev)) { + /* enable I/O and memory of the device */ + if (pci_enable_device(pdev)) { dev_info(&pdev->dev, "Cannot re-enable PCI device after reset.\n"); result = PCI_ERS_RESULT_DISCONNECT; @@ -16412,54 +16566,7 @@ static void i40e_pci_error_resume(struct pci_dev *pdev) if (test_bit(__I40E_SUSPENDED, pf->state)) return; - i40e_handle_reset_warning(pf, false); -} - -/** - * i40e_enable_mc_magic_wake - enable multicast magic packet wake up - * using the mac_address_write admin q function - * @pf: pointer to i40e_pf struct - **/ -static void i40e_enable_mc_magic_wake(struct i40e_pf *pf) -{ - struct i40e_hw *hw = &pf->hw; - u8 mac_addr[6]; - u16 flags = 0; - int ret; - - /* Get current MAC address in case it's an LAA */ - if (pf->vsi[pf->lan_vsi] && pf->vsi[pf->lan_vsi]->netdev) { - ether_addr_copy(mac_addr, - pf->vsi[pf->lan_vsi]->netdev->dev_addr); - } else { - dev_err(&pf->pdev->dev, - "Failed to retrieve MAC address; using default\n"); - ether_addr_copy(mac_addr, hw->mac.addr); - } - - /* The FW expects the mac address write cmd to first be called with - * one of these flags before calling it again with the multicast - * enable flags. - */ - flags = I40E_AQC_WRITE_TYPE_LAA_WOL; - - if (hw->func_caps.flex10_enable && hw->partition_id != 1) - flags = I40E_AQC_WRITE_TYPE_LAA_ONLY; - - ret = i40e_aq_mac_address_write(hw, flags, mac_addr, NULL); - if (ret) { - dev_err(&pf->pdev->dev, - "Failed to update MAC address registers; cannot enable Multicast Magic packet wake up"); - return; - } - - flags = I40E_AQC_MC_MAG_EN - | I40E_AQC_WOL_PRESERVE_ON_PFR - | I40E_AQC_WRITE_TYPE_UPDATE_MC_MAG; - ret = i40e_aq_mac_address_write(hw, flags, mac_addr, NULL); - if (ret) - dev_err(&pf->pdev->dev, - "Failed to enable Multicast Magic Packet wake up\n"); + i40e_io_resume(pf); } /** @@ -16474,7 +16581,7 @@ static void i40e_shutdown(struct pci_dev *pdev) set_bit(__I40E_SUSPENDED, pf->state); set_bit(__I40E_DOWN, pf->state); - del_timer_sync(&pf->service_timer); + timer_delete_sync(&pf->service_timer); cancel_work_sync(&pf->service_task); i40e_cloud_filter_exit(pf); i40e_fdir_teardown(pf); @@ -16482,7 +16589,7 @@ static void i40e_shutdown(struct pci_dev *pdev) /* Client close must be called explicitly here because the timer * has been stopped. */ - i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], false); + i40e_notify_client_of_netdev_close(pf, false); if (test_bit(I40E_HW_CAP_WOL_MC_MAGIC_PKT_WAKE, pf->hw.caps) && pf->wol_en) @@ -16518,93 +16625,28 @@ static void i40e_shutdown(struct pci_dev *pdev) * i40e_suspend - PM callback for moving to D3 * @dev: generic device information structure **/ -static int __maybe_unused i40e_suspend(struct device *dev) +static int i40e_suspend(struct device *dev) { struct i40e_pf *pf = dev_get_drvdata(dev); - struct i40e_hw *hw = &pf->hw; /* If we're already suspended, then there is nothing to do */ if (test_and_set_bit(__I40E_SUSPENDED, pf->state)) return 0; - - set_bit(__I40E_DOWN, pf->state); - - /* Ensure service task will not be running */ - del_timer_sync(&pf->service_timer); - cancel_work_sync(&pf->service_task); - - /* Client close must be called explicitly here because the timer - * has been stopped. - */ - i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], false); - - if (test_bit(I40E_HW_CAP_WOL_MC_MAGIC_PKT_WAKE, pf->hw.caps) && - pf->wol_en) - i40e_enable_mc_magic_wake(pf); - - /* Since we're going to destroy queues during the - * i40e_clear_interrupt_scheme() we should hold the RTNL lock for this - * whole section - */ - rtnl_lock(); - - i40e_prep_for_reset(pf); - - wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0)); - wr32(hw, I40E_PFPM_WUFC, (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0)); - - /* Clear the interrupt scheme and release our IRQs so that the system - * can safely hibernate even when there are a large number of CPUs. - * Otherwise hibernation might fail when mapping all the vectors back - * to CPU0. - */ - i40e_clear_interrupt_scheme(pf); - - rtnl_unlock(); - - return 0; + return i40e_io_suspend(pf); } /** * i40e_resume - PM callback for waking up from D3 * @dev: generic device information structure **/ -static int __maybe_unused i40e_resume(struct device *dev) +static int i40e_resume(struct device *dev) { struct i40e_pf *pf = dev_get_drvdata(dev); - int err; /* If we're not suspended, then there is nothing to do */ if (!test_bit(__I40E_SUSPENDED, pf->state)) return 0; - - /* We need to hold the RTNL lock prior to restoring interrupt schemes, - * since we're going to be restoring queues - */ - rtnl_lock(); - - /* We cleared the interrupt scheme when we suspended, so we need to - * restore it now to resume device functionality. - */ - err = i40e_restore_interrupt_scheme(pf); - if (err) { - dev_err(dev, "Cannot restore interrupt scheme: %d\n", - err); - } - - clear_bit(__I40E_DOWN, pf->state); - i40e_reset_and_rebuild(pf, false, true); - - rtnl_unlock(); - - /* Clear suspended state last after everything is recovered */ - clear_bit(__I40E_SUSPENDED, pf->state); - - /* Restart the service task */ - mod_timer(&pf->service_timer, - round_jiffies(jiffies + pf->service_timer_period)); - - return 0; + return i40e_io_resume(pf); } static const struct pci_error_handlers i40e_err_handler = { @@ -16615,16 +16657,14 @@ static const struct pci_error_handlers i40e_err_handler = { .resume = i40e_pci_error_resume, }; -static SIMPLE_DEV_PM_OPS(i40e_pm_ops, i40e_suspend, i40e_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(i40e_pm_ops, i40e_suspend, i40e_resume); static struct pci_driver i40e_driver = { .name = i40e_driver_name, .id_table = i40e_pci_tbl, .probe = i40e_probe, .remove = i40e_remove, - .driver = { - .pm = &i40e_pm_ops, - }, + .driver.pm = pm_sleep_ptr(&i40e_pm_ops), .shutdown = i40e_shutdown, .err_handler = &i40e_err_handler, .sriov_configure = i40e_pci_sriov_configure, diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c index 605fd82f5d20..7f0936f4e05e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c +++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c @@ -734,37 +734,7 @@ int i40e_validate_nvm_checksum(struct i40e_hw *hw, return ret_code; } -static int i40e_nvmupd_state_init(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno); -static int i40e_nvmupd_state_reading(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno); -static int i40e_nvmupd_state_writing(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *errno); -static enum i40e_nvmupd_cmd i40e_nvmupd_validate_command(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - int *perrno); -static int i40e_nvmupd_nvm_erase(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - int *perrno); -static int i40e_nvmupd_nvm_write(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno); -static int i40e_nvmupd_nvm_read(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno); -static int i40e_nvmupd_exec_aq(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno); -static int i40e_nvmupd_get_aq_result(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno); -static int i40e_nvmupd_get_aq_event(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno); -static inline u8 i40e_nvmupd_get_module(u32 val) +static u8 i40e_nvmupd_get_module(u32 val) { return (u8)(val & I40E_NVM_MOD_PNT_MASK); } @@ -799,121 +769,408 @@ static const char * const i40e_nvm_update_state_str[] = { }; /** - * i40e_nvmupd_command - Process an NVM update command + * i40e_nvmupd_validate_command - Validate given command * @hw: pointer to hardware structure - * @cmd: pointer to nvm update command - * @bytes: pointer to the data buffer + * @cmd: pointer to nvm update command buffer * @perrno: pointer to return error code * - * Dispatches command depending on what update state is current + * Return one of the valid command types or I40E_NVMUPD_INVALID **/ -int i40e_nvmupd_command(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno) +static enum i40e_nvmupd_cmd +i40e_nvmupd_validate_command(struct i40e_hw *hw, struct i40e_nvm_access *cmd, + int *perrno) { enum i40e_nvmupd_cmd upd_cmd; - int status; - - /* assume success */ - *perrno = 0; + u8 module, transaction; - /* early check for status command and debug msgs */ - upd_cmd = i40e_nvmupd_validate_command(hw, cmd, perrno); + /* anything that doesn't match a recognized case is an error */ + upd_cmd = I40E_NVMUPD_INVALID; - i40e_debug(hw, I40E_DEBUG_NVM, "%s state %d nvm_release_on_hold %d opc 0x%04x cmd 0x%08x config 0x%08x offset 0x%08x data_size 0x%08x\n", - i40e_nvm_update_state_str[upd_cmd], - hw->nvmupd_state, - hw->nvm_release_on_done, hw->nvm_wait_opcode, - cmd->command, cmd->config, cmd->offset, cmd->data_size); + transaction = i40e_nvmupd_get_transaction(cmd->config); + module = i40e_nvmupd_get_module(cmd->config); - if (upd_cmd == I40E_NVMUPD_INVALID) { - *perrno = -EFAULT; + /* limits on data size */ + if (cmd->data_size < 1 || cmd->data_size > I40E_NVMUPD_MAX_DATA) { i40e_debug(hw, I40E_DEBUG_NVM, - "i40e_nvmupd_validate_command returns %d errno %d\n", - upd_cmd, *perrno); + "%s data_size %d\n", __func__, cmd->data_size); + *perrno = -EFAULT; + return I40E_NVMUPD_INVALID; } - /* a status request returns immediately rather than - * going into the state machine - */ - if (upd_cmd == I40E_NVMUPD_STATUS) { - if (!cmd->data_size) { - *perrno = -EFAULT; - return -EINVAL; + switch (cmd->command) { + case I40E_NVM_READ: + switch (transaction) { + case I40E_NVM_CON: + upd_cmd = I40E_NVMUPD_READ_CON; + break; + case I40E_NVM_SNT: + upd_cmd = I40E_NVMUPD_READ_SNT; + break; + case I40E_NVM_LCB: + upd_cmd = I40E_NVMUPD_READ_LCB; + break; + case I40E_NVM_SA: + upd_cmd = I40E_NVMUPD_READ_SA; + break; + case I40E_NVM_EXEC: + if (module == 0xf) + upd_cmd = I40E_NVMUPD_STATUS; + else if (module == 0) + upd_cmd = I40E_NVMUPD_GET_AQ_RESULT; + break; + case I40E_NVM_AQE: + upd_cmd = I40E_NVMUPD_GET_AQ_EVENT; + break; } + break; - bytes[0] = hw->nvmupd_state; - - if (cmd->data_size >= 4) { - bytes[1] = 0; - *((u16 *)&bytes[2]) = hw->nvm_wait_opcode; + case I40E_NVM_WRITE: + switch (transaction) { + case I40E_NVM_CON: + upd_cmd = I40E_NVMUPD_WRITE_CON; + break; + case I40E_NVM_SNT: + upd_cmd = I40E_NVMUPD_WRITE_SNT; + break; + case I40E_NVM_LCB: + upd_cmd = I40E_NVMUPD_WRITE_LCB; + break; + case I40E_NVM_SA: + upd_cmd = I40E_NVMUPD_WRITE_SA; + break; + case I40E_NVM_ERA: + upd_cmd = I40E_NVMUPD_WRITE_ERA; + break; + case I40E_NVM_CSUM: + upd_cmd = I40E_NVMUPD_CSUM_CON; + break; + case (I40E_NVM_CSUM | I40E_NVM_SA): + upd_cmd = I40E_NVMUPD_CSUM_SA; + break; + case (I40E_NVM_CSUM | I40E_NVM_LCB): + upd_cmd = I40E_NVMUPD_CSUM_LCB; + break; + case I40E_NVM_EXEC: + if (module == 0) + upd_cmd = I40E_NVMUPD_EXEC_AQ; + break; } + break; + } - /* Clear error status on read */ - if (hw->nvmupd_state == I40E_NVMUPD_STATE_ERROR) - hw->nvmupd_state = I40E_NVMUPD_STATE_INIT; + return upd_cmd; +} - return 0; +/** + * i40e_nvmupd_nvm_erase - Erase an NVM module + * @hw: pointer to hardware structure + * @cmd: pointer to nvm update command buffer + * @perrno: pointer to return error code + * + * module, offset, data_size and data are in cmd structure + **/ +static int i40e_nvmupd_nvm_erase(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + int *perrno) +{ + struct i40e_asq_cmd_details cmd_details; + u8 module, transaction; + int status = 0; + bool last; + + transaction = i40e_nvmupd_get_transaction(cmd->config); + module = i40e_nvmupd_get_module(cmd->config); + last = (transaction & I40E_NVM_LCB); + + memset(&cmd_details, 0, sizeof(cmd_details)); + cmd_details.wb_desc = &hw->nvm_wb_desc; + + status = i40e_aq_erase_nvm(hw, module, cmd->offset, (u16)cmd->data_size, + last, &cmd_details); + if (status) { + i40e_debug(hw, I40E_DEBUG_NVM, + "%s mod 0x%x off 0x%x len 0x%x\n", + __func__, module, cmd->offset, cmd->data_size); + i40e_debug(hw, I40E_DEBUG_NVM, + "%s status %d aq %d\n", + __func__, status, hw->aq.asq_last_status); + *perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status); } - /* Clear status even it is not read and log */ - if (hw->nvmupd_state == I40E_NVMUPD_STATE_ERROR) { + return status; +} + +/** + * i40e_nvmupd_nvm_write - Write NVM + * @hw: pointer to hardware structure + * @cmd: pointer to nvm update command buffer + * @bytes: pointer to the data buffer + * @perrno: pointer to return error code + * + * module, offset, data_size and data are in cmd structure + **/ +static int i40e_nvmupd_nvm_write(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno) +{ + struct i40e_asq_cmd_details cmd_details; + u8 module, transaction; + u8 preservation_flags; + int status = 0; + bool last; + + transaction = i40e_nvmupd_get_transaction(cmd->config); + module = i40e_nvmupd_get_module(cmd->config); + last = (transaction & I40E_NVM_LCB); + preservation_flags = i40e_nvmupd_get_preservation_flags(cmd->config); + + memset(&cmd_details, 0, sizeof(cmd_details)); + cmd_details.wb_desc = &hw->nvm_wb_desc; + + status = i40e_aq_update_nvm(hw, module, cmd->offset, + (u16)cmd->data_size, bytes, last, + preservation_flags, &cmd_details); + if (status) { i40e_debug(hw, I40E_DEBUG_NVM, - "Clearing I40E_NVMUPD_STATE_ERROR state without reading\n"); - hw->nvmupd_state = I40E_NVMUPD_STATE_INIT; + "%s mod 0x%x off 0x%x len 0x%x\n", + __func__, module, cmd->offset, cmd->data_size); + i40e_debug(hw, I40E_DEBUG_NVM, + "%s status %d aq %d\n", + __func__, status, hw->aq.asq_last_status); + *perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status); } - /* Acquire lock to prevent race condition where adminq_task - * can execute after i40e_nvmupd_nvm_read/write but before state - * variables (nvm_wait_opcode, nvm_release_on_done) are updated. - * - * During NVMUpdate, it is observed that lock could be held for - * ~5ms for most commands. However lock is held for ~60ms for - * NVMUPD_CSUM_LCB command. - */ - mutex_lock(&hw->aq.arq_mutex); - switch (hw->nvmupd_state) { - case I40E_NVMUPD_STATE_INIT: - status = i40e_nvmupd_state_init(hw, cmd, bytes, perrno); - break; + return status; +} - case I40E_NVMUPD_STATE_READING: - status = i40e_nvmupd_state_reading(hw, cmd, bytes, perrno); - break; +/** + * i40e_nvmupd_nvm_read - Read NVM + * @hw: pointer to hardware structure + * @cmd: pointer to nvm update command buffer + * @bytes: pointer to the data buffer + * @perrno: pointer to return error code + * + * cmd structure contains identifiers and data buffer + **/ +static int i40e_nvmupd_nvm_read(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno) +{ + struct i40e_asq_cmd_details cmd_details; + u8 module, transaction; + int status; + bool last; - case I40E_NVMUPD_STATE_WRITING: - status = i40e_nvmupd_state_writing(hw, cmd, bytes, perrno); - break; + transaction = i40e_nvmupd_get_transaction(cmd->config); + module = i40e_nvmupd_get_module(cmd->config); + last = (transaction == I40E_NVM_LCB) || (transaction == I40E_NVM_SA); - case I40E_NVMUPD_STATE_INIT_WAIT: - case I40E_NVMUPD_STATE_WRITE_WAIT: - /* if we need to stop waiting for an event, clear - * the wait info and return before doing anything else - */ - if (cmd->offset == 0xffff) { - i40e_nvmupd_clear_wait_state(hw); - status = 0; - break; + memset(&cmd_details, 0, sizeof(cmd_details)); + cmd_details.wb_desc = &hw->nvm_wb_desc; + + status = i40e_aq_read_nvm(hw, module, cmd->offset, (u16)cmd->data_size, + bytes, last, &cmd_details); + if (status) { + i40e_debug(hw, I40E_DEBUG_NVM, + "%s mod 0x%x off 0x%x len 0x%x\n", + __func__, module, cmd->offset, cmd->data_size); + i40e_debug(hw, I40E_DEBUG_NVM, + "%s status %d aq %d\n", + __func__, status, hw->aq.asq_last_status); + *perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status); + } + + return status; +} + +/** + * i40e_nvmupd_exec_aq - Run an AQ command + * @hw: pointer to hardware structure + * @cmd: pointer to nvm update command buffer + * @bytes: pointer to the data buffer + * @perrno: pointer to return error code + * + * cmd structure contains identifiers and data buffer + **/ +static int i40e_nvmupd_exec_aq(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno) +{ + struct i40e_asq_cmd_details cmd_details; + struct i40e_aq_desc *aq_desc; + u32 buff_size = 0; + u8 *buff = NULL; + u32 aq_desc_len; + u32 aq_data_len; + int status; + + i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: %s\n", __func__); + if (cmd->offset == 0xffff) + return 0; + + memset(&cmd_details, 0, sizeof(cmd_details)); + cmd_details.wb_desc = &hw->nvm_wb_desc; + + aq_desc_len = sizeof(struct i40e_aq_desc); + memset(&hw->nvm_wb_desc, 0, aq_desc_len); + + /* get the aq descriptor */ + if (cmd->data_size < aq_desc_len) { + i40e_debug(hw, I40E_DEBUG_NVM, + "NVMUPD: not enough aq desc bytes for exec, size %d < %d\n", + cmd->data_size, aq_desc_len); + *perrno = -EINVAL; + return -EINVAL; + } + aq_desc = (struct i40e_aq_desc *)bytes; + + /* if data buffer needed, make sure it's ready */ + aq_data_len = cmd->data_size - aq_desc_len; + buff_size = max_t(u32, aq_data_len, le16_to_cpu(aq_desc->datalen)); + if (buff_size) { + if (!hw->nvm_buff.va) { + status = i40e_allocate_virt_mem(hw, &hw->nvm_buff, + hw->aq.asq_buf_size); + if (status) + i40e_debug(hw, I40E_DEBUG_NVM, + "NVMUPD: i40e_allocate_virt_mem for exec buff failed, %d\n", + status); } - status = -EBUSY; - *perrno = -EBUSY; - break; + if (hw->nvm_buff.va) { + buff = hw->nvm_buff.va; + memcpy(buff, &bytes[aq_desc_len], aq_data_len); + } + } - default: - /* invalid state, should never happen */ + if (cmd->offset) + memset(&hw->nvm_aq_event_desc, 0, aq_desc_len); + + /* and away we go! */ + status = i40e_asq_send_command(hw, aq_desc, buff, + buff_size, &cmd_details); + if (status) { i40e_debug(hw, I40E_DEBUG_NVM, - "NVMUPD: no such state %d\n", hw->nvmupd_state); - status = -EOPNOTSUPP; - *perrno = -ESRCH; - break; + "%s err %pe aq_err %s\n", + __func__, ERR_PTR(status), + i40e_aq_str(hw, hw->aq.asq_last_status)); + *perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status); + return status; + } + + /* should we wait for a followup event? */ + if (cmd->offset) { + hw->nvm_wait_opcode = cmd->offset; + hw->nvmupd_state = I40E_NVMUPD_STATE_INIT_WAIT; } - mutex_unlock(&hw->aq.arq_mutex); return status; } /** + * i40e_nvmupd_get_aq_result - Get the results from the previous exec_aq + * @hw: pointer to hardware structure + * @cmd: pointer to nvm update command buffer + * @bytes: pointer to the data buffer + * @perrno: pointer to return error code + * + * cmd structure contains identifiers and data buffer + **/ +static int i40e_nvmupd_get_aq_result(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno) +{ + u32 aq_total_len; + u32 aq_desc_len; + int remainder; + u8 *buff; + + i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: %s\n", __func__); + + aq_desc_len = sizeof(struct i40e_aq_desc); + aq_total_len = aq_desc_len + le16_to_cpu(hw->nvm_wb_desc.datalen); + + /* check offset range */ + if (cmd->offset > aq_total_len) { + i40e_debug(hw, I40E_DEBUG_NVM, "%s: offset too big %d > %d\n", + __func__, cmd->offset, aq_total_len); + *perrno = -EINVAL; + return -EINVAL; + } + + /* check copylength range */ + if (cmd->data_size > (aq_total_len - cmd->offset)) { + int new_len = aq_total_len - cmd->offset; + + i40e_debug(hw, I40E_DEBUG_NVM, "%s: copy length %d too big, trimming to %d\n", + __func__, cmd->data_size, new_len); + cmd->data_size = new_len; + } + + remainder = cmd->data_size; + if (cmd->offset < aq_desc_len) { + u32 len = aq_desc_len - cmd->offset; + + len = min(len, cmd->data_size); + i40e_debug(hw, I40E_DEBUG_NVM, "%s: aq_desc bytes %d to %d\n", + __func__, cmd->offset, cmd->offset + len); + + buff = ((u8 *)&hw->nvm_wb_desc) + cmd->offset; + memcpy(bytes, buff, len); + + bytes += len; + remainder -= len; + buff = hw->nvm_buff.va; + } else { + buff = hw->nvm_buff.va + (cmd->offset - aq_desc_len); + } + + if (remainder > 0) { + int start_byte = buff - (u8 *)hw->nvm_buff.va; + + i40e_debug(hw, I40E_DEBUG_NVM, "%s: databuf bytes %d to %d\n", + __func__, start_byte, start_byte + remainder); + memcpy(bytes, buff, remainder); + } + + return 0; +} + +/** + * i40e_nvmupd_get_aq_event - Get the Admin Queue event from previous exec_aq + * @hw: pointer to hardware structure + * @cmd: pointer to nvm update command buffer + * @bytes: pointer to the data buffer + * @perrno: pointer to return error code + * + * cmd structure contains identifiers and data buffer + **/ +static int i40e_nvmupd_get_aq_event(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno) +{ + u32 aq_total_len; + u32 aq_desc_len; + + i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: %s\n", __func__); + + aq_desc_len = sizeof(struct i40e_aq_desc); + aq_total_len = aq_desc_len + le16_to_cpu(hw->nvm_aq_event_desc.datalen); + + /* check copylength range */ + if (cmd->data_size > aq_total_len) { + i40e_debug(hw, I40E_DEBUG_NVM, + "%s: copy length %d too big, trimming to %d\n", + __func__, cmd->data_size, aq_total_len); + cmd->data_size = aq_total_len; + } + + memcpy(bytes, &hw->nvm_aq_event_desc, cmd->data_size); + + return 0; +} + +/** * i40e_nvmupd_state_init - Handle NVM update state Init * @hw: pointer to hardware structure * @cmd: pointer to nvm update command buffer @@ -937,7 +1194,7 @@ static int i40e_nvmupd_state_init(struct i40e_hw *hw, status = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); if (status) { *perrno = i40e_aq_rc_to_posix(status, - hw->aq.asq_last_status); + hw->aq.asq_last_status); } else { status = i40e_nvmupd_nvm_read(hw, cmd, bytes, perrno); i40e_release_nvm(hw); @@ -948,7 +1205,7 @@ static int i40e_nvmupd_state_init(struct i40e_hw *hw, status = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); if (status) { *perrno = i40e_aq_rc_to_posix(status, - hw->aq.asq_last_status); + hw->aq.asq_last_status); } else { status = i40e_nvmupd_nvm_read(hw, cmd, bytes, perrno); if (status) @@ -962,7 +1219,7 @@ static int i40e_nvmupd_state_init(struct i40e_hw *hw, status = i40e_acquire_nvm(hw, I40E_RESOURCE_WRITE); if (status) { *perrno = i40e_aq_rc_to_posix(status, - hw->aq.asq_last_status); + hw->aq.asq_last_status); } else { status = i40e_nvmupd_nvm_erase(hw, cmd, perrno); if (status) { @@ -979,7 +1236,7 @@ static int i40e_nvmupd_state_init(struct i40e_hw *hw, status = i40e_acquire_nvm(hw, I40E_RESOURCE_WRITE); if (status) { *perrno = i40e_aq_rc_to_posix(status, - hw->aq.asq_last_status); + hw->aq.asq_last_status); } else { status = i40e_nvmupd_nvm_write(hw, cmd, bytes, perrno); if (status) { @@ -996,7 +1253,7 @@ static int i40e_nvmupd_state_init(struct i40e_hw *hw, status = i40e_acquire_nvm(hw, I40E_RESOURCE_WRITE); if (status) { *perrno = i40e_aq_rc_to_posix(status, - hw->aq.asq_last_status); + hw->aq.asq_last_status); } else { status = i40e_nvmupd_nvm_write(hw, cmd, bytes, perrno); if (status) { @@ -1012,7 +1269,7 @@ static int i40e_nvmupd_state_init(struct i40e_hw *hw, status = i40e_acquire_nvm(hw, I40E_RESOURCE_WRITE); if (status) { *perrno = i40e_aq_rc_to_posix(status, - hw->aq.asq_last_status); + hw->aq.asq_last_status); } else { status = i40e_update_nvm_checksum(hw); if (status) { @@ -1185,7 +1442,7 @@ retry: * so here we try to reacquire the semaphore then retry the write. * We only do one retry, then give up. */ - if (status && (hw->aq.asq_last_status == I40E_AQ_RC_EBUSY) && + if (status && hw->aq.asq_last_status == I40E_AQ_RC_EBUSY && !retry_attempt) { u32 old_asq_status = hw->aq.asq_last_status; int old_status = status; @@ -1215,457 +1472,168 @@ retry: } /** - * i40e_nvmupd_clear_wait_state - clear wait state on hw - * @hw: pointer to the hardware structure - **/ -void i40e_nvmupd_clear_wait_state(struct i40e_hw *hw) -{ - i40e_debug(hw, I40E_DEBUG_NVM, - "NVMUPD: clearing wait on opcode 0x%04x\n", - hw->nvm_wait_opcode); - - if (hw->nvm_release_on_done) { - i40e_release_nvm(hw); - hw->nvm_release_on_done = false; - } - hw->nvm_wait_opcode = 0; - - if (hw->aq.arq_last_status) { - hw->nvmupd_state = I40E_NVMUPD_STATE_ERROR; - return; - } - - switch (hw->nvmupd_state) { - case I40E_NVMUPD_STATE_INIT_WAIT: - hw->nvmupd_state = I40E_NVMUPD_STATE_INIT; - break; - - case I40E_NVMUPD_STATE_WRITE_WAIT: - hw->nvmupd_state = I40E_NVMUPD_STATE_WRITING; - break; - - default: - break; - } -} - -/** - * i40e_nvmupd_check_wait_event - handle NVM update operation events - * @hw: pointer to the hardware structure - * @opcode: the event that just happened - * @desc: AdminQ descriptor - **/ -void i40e_nvmupd_check_wait_event(struct i40e_hw *hw, u16 opcode, - struct i40e_aq_desc *desc) -{ - u32 aq_desc_len = sizeof(struct i40e_aq_desc); - - if (opcode == hw->nvm_wait_opcode) { - memcpy(&hw->nvm_aq_event_desc, desc, aq_desc_len); - i40e_nvmupd_clear_wait_state(hw); - } -} - -/** - * i40e_nvmupd_validate_command - Validate given command - * @hw: pointer to hardware structure - * @cmd: pointer to nvm update command buffer - * @perrno: pointer to return error code - * - * Return one of the valid command types or I40E_NVMUPD_INVALID - **/ -static enum i40e_nvmupd_cmd i40e_nvmupd_validate_command(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - int *perrno) -{ - enum i40e_nvmupd_cmd upd_cmd; - u8 module, transaction; - - /* anything that doesn't match a recognized case is an error */ - upd_cmd = I40E_NVMUPD_INVALID; - - transaction = i40e_nvmupd_get_transaction(cmd->config); - module = i40e_nvmupd_get_module(cmd->config); - - /* limits on data size */ - if ((cmd->data_size < 1) || - (cmd->data_size > I40E_NVMUPD_MAX_DATA)) { - i40e_debug(hw, I40E_DEBUG_NVM, - "i40e_nvmupd_validate_command data_size %d\n", - cmd->data_size); - *perrno = -EFAULT; - return I40E_NVMUPD_INVALID; - } - - switch (cmd->command) { - case I40E_NVM_READ: - switch (transaction) { - case I40E_NVM_CON: - upd_cmd = I40E_NVMUPD_READ_CON; - break; - case I40E_NVM_SNT: - upd_cmd = I40E_NVMUPD_READ_SNT; - break; - case I40E_NVM_LCB: - upd_cmd = I40E_NVMUPD_READ_LCB; - break; - case I40E_NVM_SA: - upd_cmd = I40E_NVMUPD_READ_SA; - break; - case I40E_NVM_EXEC: - if (module == 0xf) - upd_cmd = I40E_NVMUPD_STATUS; - else if (module == 0) - upd_cmd = I40E_NVMUPD_GET_AQ_RESULT; - break; - case I40E_NVM_AQE: - upd_cmd = I40E_NVMUPD_GET_AQ_EVENT; - break; - } - break; - - case I40E_NVM_WRITE: - switch (transaction) { - case I40E_NVM_CON: - upd_cmd = I40E_NVMUPD_WRITE_CON; - break; - case I40E_NVM_SNT: - upd_cmd = I40E_NVMUPD_WRITE_SNT; - break; - case I40E_NVM_LCB: - upd_cmd = I40E_NVMUPD_WRITE_LCB; - break; - case I40E_NVM_SA: - upd_cmd = I40E_NVMUPD_WRITE_SA; - break; - case I40E_NVM_ERA: - upd_cmd = I40E_NVMUPD_WRITE_ERA; - break; - case I40E_NVM_CSUM: - upd_cmd = I40E_NVMUPD_CSUM_CON; - break; - case (I40E_NVM_CSUM|I40E_NVM_SA): - upd_cmd = I40E_NVMUPD_CSUM_SA; - break; - case (I40E_NVM_CSUM|I40E_NVM_LCB): - upd_cmd = I40E_NVMUPD_CSUM_LCB; - break; - case I40E_NVM_EXEC: - if (module == 0) - upd_cmd = I40E_NVMUPD_EXEC_AQ; - break; - } - break; - } - - return upd_cmd; -} - -/** - * i40e_nvmupd_exec_aq - Run an AQ command + * i40e_nvmupd_command - Process an NVM update command * @hw: pointer to hardware structure - * @cmd: pointer to nvm update command buffer + * @cmd: pointer to nvm update command * @bytes: pointer to the data buffer * @perrno: pointer to return error code * - * cmd structure contains identifiers and data buffer + * Dispatches command depending on what update state is current **/ -static int i40e_nvmupd_exec_aq(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno) +int i40e_nvmupd_command(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno) { - struct i40e_asq_cmd_details cmd_details; - struct i40e_aq_desc *aq_desc; - u32 buff_size = 0; - u8 *buff = NULL; - u32 aq_desc_len; - u32 aq_data_len; + enum i40e_nvmupd_cmd upd_cmd; int status; - i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: %s\n", __func__); - if (cmd->offset == 0xffff) - return 0; + /* assume success */ + *perrno = 0; - memset(&cmd_details, 0, sizeof(cmd_details)); - cmd_details.wb_desc = &hw->nvm_wb_desc; + /* early check for status command and debug msgs */ + upd_cmd = i40e_nvmupd_validate_command(hw, cmd, perrno); - aq_desc_len = sizeof(struct i40e_aq_desc); - memset(&hw->nvm_wb_desc, 0, aq_desc_len); + i40e_debug(hw, I40E_DEBUG_NVM, "%s state %d nvm_release_on_hold %d opc 0x%04x cmd 0x%08x config 0x%08x offset 0x%08x data_size 0x%08x\n", + i40e_nvm_update_state_str[upd_cmd], + hw->nvmupd_state, + hw->nvm_release_on_done, hw->nvm_wait_opcode, + cmd->command, cmd->config, cmd->offset, cmd->data_size); - /* get the aq descriptor */ - if (cmd->data_size < aq_desc_len) { + if (upd_cmd == I40E_NVMUPD_INVALID) { + *perrno = -EFAULT; i40e_debug(hw, I40E_DEBUG_NVM, - "NVMUPD: not enough aq desc bytes for exec, size %d < %d\n", - cmd->data_size, aq_desc_len); - *perrno = -EINVAL; - return -EINVAL; + "i40e_nvmupd_validate_command returns %d errno %d\n", + upd_cmd, *perrno); } - aq_desc = (struct i40e_aq_desc *)bytes; - /* if data buffer needed, make sure it's ready */ - aq_data_len = cmd->data_size - aq_desc_len; - buff_size = max_t(u32, aq_data_len, le16_to_cpu(aq_desc->datalen)); - if (buff_size) { - if (!hw->nvm_buff.va) { - status = i40e_allocate_virt_mem(hw, &hw->nvm_buff, - hw->aq.asq_buf_size); - if (status) - i40e_debug(hw, I40E_DEBUG_NVM, - "NVMUPD: i40e_allocate_virt_mem for exec buff failed, %d\n", - status); - } - - if (hw->nvm_buff.va) { - buff = hw->nvm_buff.va; - memcpy(buff, &bytes[aq_desc_len], aq_data_len); + /* a status request returns immediately rather than + * going into the state machine + */ + if (upd_cmd == I40E_NVMUPD_STATUS) { + if (!cmd->data_size) { + *perrno = -EFAULT; + return -EINVAL; } - } - - if (cmd->offset) - memset(&hw->nvm_aq_event_desc, 0, aq_desc_len); - - /* and away we go! */ - status = i40e_asq_send_command(hw, aq_desc, buff, - buff_size, &cmd_details); - if (status) { - i40e_debug(hw, I40E_DEBUG_NVM, - "%s err %pe aq_err %s\n", - __func__, ERR_PTR(status), - i40e_aq_str(hw, hw->aq.asq_last_status)); - *perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status); - return status; - } - - /* should we wait for a followup event? */ - if (cmd->offset) { - hw->nvm_wait_opcode = cmd->offset; - hw->nvmupd_state = I40E_NVMUPD_STATE_INIT_WAIT; - } - - return status; -} -/** - * i40e_nvmupd_get_aq_result - Get the results from the previous exec_aq - * @hw: pointer to hardware structure - * @cmd: pointer to nvm update command buffer - * @bytes: pointer to the data buffer - * @perrno: pointer to return error code - * - * cmd structure contains identifiers and data buffer - **/ -static int i40e_nvmupd_get_aq_result(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno) -{ - u32 aq_total_len; - u32 aq_desc_len; - int remainder; - u8 *buff; - - i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: %s\n", __func__); - - aq_desc_len = sizeof(struct i40e_aq_desc); - aq_total_len = aq_desc_len + le16_to_cpu(hw->nvm_wb_desc.datalen); + bytes[0] = hw->nvmupd_state; - /* check offset range */ - if (cmd->offset > aq_total_len) { - i40e_debug(hw, I40E_DEBUG_NVM, "%s: offset too big %d > %d\n", - __func__, cmd->offset, aq_total_len); - *perrno = -EINVAL; - return -EINVAL; - } + if (cmd->data_size >= 4) { + bytes[1] = 0; + *((u16 *)&bytes[2]) = hw->nvm_wait_opcode; + } - /* check copylength range */ - if (cmd->data_size > (aq_total_len - cmd->offset)) { - int new_len = aq_total_len - cmd->offset; + /* Clear error status on read */ + if (hw->nvmupd_state == I40E_NVMUPD_STATE_ERROR) + hw->nvmupd_state = I40E_NVMUPD_STATE_INIT; - i40e_debug(hw, I40E_DEBUG_NVM, "%s: copy length %d too big, trimming to %d\n", - __func__, cmd->data_size, new_len); - cmd->data_size = new_len; + return 0; } - remainder = cmd->data_size; - if (cmd->offset < aq_desc_len) { - u32 len = aq_desc_len - cmd->offset; - - len = min(len, cmd->data_size); - i40e_debug(hw, I40E_DEBUG_NVM, "%s: aq_desc bytes %d to %d\n", - __func__, cmd->offset, cmd->offset + len); - - buff = ((u8 *)&hw->nvm_wb_desc) + cmd->offset; - memcpy(bytes, buff, len); - - bytes += len; - remainder -= len; - buff = hw->nvm_buff.va; - } else { - buff = hw->nvm_buff.va + (cmd->offset - aq_desc_len); + /* Clear status even it is not read and log */ + if (hw->nvmupd_state == I40E_NVMUPD_STATE_ERROR) { + i40e_debug(hw, I40E_DEBUG_NVM, + "Clearing I40E_NVMUPD_STATE_ERROR state without reading\n"); + hw->nvmupd_state = I40E_NVMUPD_STATE_INIT; } - if (remainder > 0) { - int start_byte = buff - (u8 *)hw->nvm_buff.va; - - i40e_debug(hw, I40E_DEBUG_NVM, "%s: databuf bytes %d to %d\n", - __func__, start_byte, start_byte + remainder); - memcpy(bytes, buff, remainder); - } + /* Acquire lock to prevent race condition where adminq_task + * can execute after i40e_nvmupd_nvm_read/write but before state + * variables (nvm_wait_opcode, nvm_release_on_done) are updated. + * + * During NVMUpdate, it is observed that lock could be held for + * ~5ms for most commands. However lock is held for ~60ms for + * NVMUPD_CSUM_LCB command. + */ + mutex_lock(&hw->aq.arq_mutex); + switch (hw->nvmupd_state) { + case I40E_NVMUPD_STATE_INIT: + status = i40e_nvmupd_state_init(hw, cmd, bytes, perrno); + break; - return 0; -} + case I40E_NVMUPD_STATE_READING: + status = i40e_nvmupd_state_reading(hw, cmd, bytes, perrno); + break; -/** - * i40e_nvmupd_get_aq_event - Get the Admin Queue event from previous exec_aq - * @hw: pointer to hardware structure - * @cmd: pointer to nvm update command buffer - * @bytes: pointer to the data buffer - * @perrno: pointer to return error code - * - * cmd structure contains identifiers and data buffer - **/ -static int i40e_nvmupd_get_aq_event(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno) -{ - u32 aq_total_len; - u32 aq_desc_len; + case I40E_NVMUPD_STATE_WRITING: + status = i40e_nvmupd_state_writing(hw, cmd, bytes, perrno); + break; - i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: %s\n", __func__); + case I40E_NVMUPD_STATE_INIT_WAIT: + case I40E_NVMUPD_STATE_WRITE_WAIT: + /* if we need to stop waiting for an event, clear + * the wait info and return before doing anything else + */ + if (cmd->offset == 0xffff) { + i40e_nvmupd_clear_wait_state(hw); + status = 0; + break; + } - aq_desc_len = sizeof(struct i40e_aq_desc); - aq_total_len = aq_desc_len + le16_to_cpu(hw->nvm_aq_event_desc.datalen); + status = -EBUSY; + *perrno = -EBUSY; + break; - /* check copylength range */ - if (cmd->data_size > aq_total_len) { + default: + /* invalid state, should never happen */ i40e_debug(hw, I40E_DEBUG_NVM, - "%s: copy length %d too big, trimming to %d\n", - __func__, cmd->data_size, aq_total_len); - cmd->data_size = aq_total_len; + "NVMUPD: no such state %d\n", hw->nvmupd_state); + status = -EOPNOTSUPP; + *perrno = -ESRCH; + break; } - memcpy(bytes, &hw->nvm_aq_event_desc, cmd->data_size); - - return 0; + mutex_unlock(&hw->aq.arq_mutex); + return status; } /** - * i40e_nvmupd_nvm_read - Read NVM - * @hw: pointer to hardware structure - * @cmd: pointer to nvm update command buffer - * @bytes: pointer to the data buffer - * @perrno: pointer to return error code - * - * cmd structure contains identifiers and data buffer + * i40e_nvmupd_clear_wait_state - clear wait state on hw + * @hw: pointer to the hardware structure **/ -static int i40e_nvmupd_nvm_read(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno) +void i40e_nvmupd_clear_wait_state(struct i40e_hw *hw) { - struct i40e_asq_cmd_details cmd_details; - u8 module, transaction; - int status; - bool last; - - transaction = i40e_nvmupd_get_transaction(cmd->config); - module = i40e_nvmupd_get_module(cmd->config); - last = (transaction == I40E_NVM_LCB) || (transaction == I40E_NVM_SA); - - memset(&cmd_details, 0, sizeof(cmd_details)); - cmd_details.wb_desc = &hw->nvm_wb_desc; + i40e_debug(hw, I40E_DEBUG_NVM, + "NVMUPD: clearing wait on opcode 0x%04x\n", + hw->nvm_wait_opcode); - status = i40e_aq_read_nvm(hw, module, cmd->offset, (u16)cmd->data_size, - bytes, last, &cmd_details); - if (status) { - i40e_debug(hw, I40E_DEBUG_NVM, - "i40e_nvmupd_nvm_read mod 0x%x off 0x%x len 0x%x\n", - module, cmd->offset, cmd->data_size); - i40e_debug(hw, I40E_DEBUG_NVM, - "i40e_nvmupd_nvm_read status %d aq %d\n", - status, hw->aq.asq_last_status); - *perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status); + if (hw->nvm_release_on_done) { + i40e_release_nvm(hw); + hw->nvm_release_on_done = false; } + hw->nvm_wait_opcode = 0; - return status; -} - -/** - * i40e_nvmupd_nvm_erase - Erase an NVM module - * @hw: pointer to hardware structure - * @cmd: pointer to nvm update command buffer - * @perrno: pointer to return error code - * - * module, offset, data_size and data are in cmd structure - **/ -static int i40e_nvmupd_nvm_erase(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - int *perrno) -{ - struct i40e_asq_cmd_details cmd_details; - u8 module, transaction; - int status = 0; - bool last; + if (hw->aq.arq_last_status) { + hw->nvmupd_state = I40E_NVMUPD_STATE_ERROR; + return; + } - transaction = i40e_nvmupd_get_transaction(cmd->config); - module = i40e_nvmupd_get_module(cmd->config); - last = (transaction & I40E_NVM_LCB); + switch (hw->nvmupd_state) { + case I40E_NVMUPD_STATE_INIT_WAIT: + hw->nvmupd_state = I40E_NVMUPD_STATE_INIT; + break; - memset(&cmd_details, 0, sizeof(cmd_details)); - cmd_details.wb_desc = &hw->nvm_wb_desc; + case I40E_NVMUPD_STATE_WRITE_WAIT: + hw->nvmupd_state = I40E_NVMUPD_STATE_WRITING; + break; - status = i40e_aq_erase_nvm(hw, module, cmd->offset, (u16)cmd->data_size, - last, &cmd_details); - if (status) { - i40e_debug(hw, I40E_DEBUG_NVM, - "i40e_nvmupd_nvm_erase mod 0x%x off 0x%x len 0x%x\n", - module, cmd->offset, cmd->data_size); - i40e_debug(hw, I40E_DEBUG_NVM, - "i40e_nvmupd_nvm_erase status %d aq %d\n", - status, hw->aq.asq_last_status); - *perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status); + default: + break; } - - return status; } /** - * i40e_nvmupd_nvm_write - Write NVM - * @hw: pointer to hardware structure - * @cmd: pointer to nvm update command buffer - * @bytes: pointer to the data buffer - * @perrno: pointer to return error code - * - * module, offset, data_size and data are in cmd structure + * i40e_nvmupd_check_wait_event - handle NVM update operation events + * @hw: pointer to the hardware structure + * @opcode: the event that just happened + * @desc: AdminQ descriptor **/ -static int i40e_nvmupd_nvm_write(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno) +void i40e_nvmupd_check_wait_event(struct i40e_hw *hw, u16 opcode, + struct i40e_aq_desc *desc) { - struct i40e_asq_cmd_details cmd_details; - u8 module, transaction; - u8 preservation_flags; - int status = 0; - bool last; - - transaction = i40e_nvmupd_get_transaction(cmd->config); - module = i40e_nvmupd_get_module(cmd->config); - last = (transaction & I40E_NVM_LCB); - preservation_flags = i40e_nvmupd_get_preservation_flags(cmd->config); - - memset(&cmd_details, 0, sizeof(cmd_details)); - cmd_details.wb_desc = &hw->nvm_wb_desc; + u32 aq_desc_len = sizeof(struct i40e_aq_desc); - status = i40e_aq_update_nvm(hw, module, cmd->offset, - (u16)cmd->data_size, bytes, last, - preservation_flags, &cmd_details); - if (status) { - i40e_debug(hw, I40E_DEBUG_NVM, - "i40e_nvmupd_nvm_write mod 0x%x off 0x%x len 0x%x\n", - module, cmd->offset, cmd->data_size); - i40e_debug(hw, I40E_DEBUG_NVM, - "i40e_nvmupd_nvm_write status %d aq %d\n", - status, hw->aq.asq_last_status); - *perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status); + if (opcode == hw->nvm_wait_opcode) { + memcpy(&hw->nvm_aq_event_desc, desc, aq_desc_len); + i40e_nvmupd_clear_wait_state(hw); } - - return status; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index ce1f11b8ad65..099bb8ab7d70 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -27,13 +27,6 @@ i40e_asq_send_command(struct i40e_hw *hw, struct i40e_aq_desc *desc, void *buff, /* can be NULL */ u16 buff_size, struct i40e_asq_cmd_details *cmd_details); int -i40e_asq_send_command_v2(struct i40e_hw *hw, - struct i40e_aq_desc *desc, - void *buff, /* can be NULL */ - u16 buff_size, - struct i40e_asq_cmd_details *cmd_details, - enum i40e_admin_queue_err *aq_status); -int i40e_asq_send_command_atomic(struct i40e_hw *hw, struct i40e_aq_desc *desc, void *buff, /* can be NULL */ u16 buff_size, struct i40e_asq_cmd_details *cmd_details, @@ -72,8 +65,6 @@ int i40e_led_set_phy(struct i40e_hw *hw, bool on, u16 led_addr, u32 mode); int i40e_led_get_phy(struct i40e_hw *hw, u16 *led_addr, u16 *val); -int i40e_blink_phy_link_led(struct i40e_hw *hw, - u32 time, u32 interval); /* admin send queue commands */ @@ -141,9 +132,6 @@ int i40e_aq_set_vsi_uc_promisc_on_vlan(struct i40e_hw *hw, int i40e_aq_set_vsi_bc_promisc_on_vlan(struct i40e_hw *hw, u16 seid, bool enable, u16 vid, struct i40e_asq_cmd_details *cmd_details); -int i40e_aq_set_vsi_vlan_promisc(struct i40e_hw *hw, - u16 seid, bool enable, - struct i40e_asq_cmd_details *cmd_details); int i40e_aq_get_vsi_params(struct i40e_hw *hw, struct i40e_vsi_context *vsi_ctx, struct i40e_asq_cmd_details *cmd_details); @@ -176,14 +164,6 @@ i40e_aq_remove_macvlan_v2(struct i40e_hw *hw, u16 seid, struct i40e_aqc_remove_macvlan_element_data *mv_list, u16 count, struct i40e_asq_cmd_details *cmd_details, enum i40e_admin_queue_err *aq_status); -int i40e_aq_add_mirrorrule(struct i40e_hw *hw, u16 sw_seid, - u16 rule_type, u16 dest_vsi, u16 count, __le16 *mr_list, - struct i40e_asq_cmd_details *cmd_details, - u16 *rule_id, u16 *rules_used, u16 *rules_free); -int i40e_aq_delete_mirrorrule(struct i40e_hw *hw, u16 sw_seid, - u16 rule_type, u16 rule_id, u16 count, __le16 *mr_list, - struct i40e_asq_cmd_details *cmd_details, - u16 *rules_used, u16 *rules_free); int i40e_aq_send_msg_to_vf(struct i40e_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen, @@ -220,9 +200,6 @@ int i40e_aq_update_nvm(struct i40e_hw *hw, u8 module_pointer, u32 offset, u16 length, void *data, bool last_command, u8 preservation_flags, struct i40e_asq_cmd_details *cmd_details); -int i40e_aq_rearrange_nvm(struct i40e_hw *hw, - u8 rearrange_nvm, - struct i40e_asq_cmd_details *cmd_details); int i40e_aq_get_lldp_mib(struct i40e_hw *hw, u8 bridge_type, u8 mib_type, void *buff, u16 buff_size, u16 *local_len, u16 *remote_len, @@ -234,9 +211,6 @@ i40e_aq_set_lldp_mib(struct i40e_hw *hw, int i40e_aq_cfg_lldp_mib_change_event(struct i40e_hw *hw, bool enable_update, struct i40e_asq_cmd_details *cmd_details); -int -i40e_aq_restore_lldp(struct i40e_hw *hw, u8 *setting, bool restore, - struct i40e_asq_cmd_details *cmd_details); int i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent, bool persist, struct i40e_asq_cmd_details *cmd_details); @@ -371,13 +345,6 @@ void i40e_set_pci_config_data(struct i40e_hw *hw, u16 link_status); int i40e_set_mac_type(struct i40e_hw *hw); -extern struct i40e_rx_ptype_decoded i40e_ptype_lookup[]; - -static inline struct i40e_rx_ptype_decoded decode_rx_desc_ptype(u8 ptype) -{ - return i40e_ptype_lookup[ptype]; -} - /** * i40e_virtchnl_link_speed - Convert AdminQ link_speed to virtchnl definition * @link_speed: the speed to convert @@ -465,13 +432,7 @@ int i40e_read_phy_register_clause45(struct i40e_hw *hw, u8 page, u16 reg, u8 phy_addr, u16 *value); int i40e_write_phy_register_clause45(struct i40e_hw *hw, u8 page, u16 reg, u8 phy_addr, u16 value); -int i40e_read_phy_register(struct i40e_hw *hw, u8 page, u16 reg, - u8 phy_addr, u16 *value); -int i40e_write_phy_register(struct i40e_hw *hw, u8 page, u16 reg, - u8 phy_addr, u16 value); u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num); -int i40e_blink_phy_link_led(struct i40e_hw *hw, - u32 time, u32 interval); int i40e_aq_write_ddp(struct i40e_hw *hw, void *buff, u16 buff_size, u32 track_id, u32 *error_offset, u32 *error_info, @@ -484,20 +445,12 @@ int i40e_aq_get_ddp_list(struct i40e_hw *hw, void *buff, struct i40e_generic_seg_header * i40e_find_segment_in_package(u32 segment_type, struct i40e_package_header *pkg_header); -struct i40e_profile_section_header * -i40e_find_section_in_profile(u32 section_type, - struct i40e_profile_segment *profile); int i40e_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg, u32 track_id); int i40e_rollback_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg, u32 track_id); -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); diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index e7ebcb09f23c..b72a4b5d76b9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -1472,7 +1472,8 @@ void i40e_ptp_restore_hw_time(struct i40e_pf *pf) **/ void i40e_ptp_init(struct i40e_pf *pf) { - struct net_device *netdev = pf->vsi[pf->lan_vsi]->netdev; + struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf); + struct net_device *netdev = vsi->netdev; struct i40e_hw *hw = &pf->hw; u32 pf_id; long err; @@ -1536,6 +1537,7 @@ void i40e_ptp_init(struct i40e_pf *pf) **/ void i40e_ptp_stop(struct i40e_pf *pf) { + struct i40e_vsi *main_vsi = i40e_pf_get_main_vsi(pf); struct i40e_hw *hw = &pf->hw; u32 regval; @@ -1555,7 +1557,7 @@ void i40e_ptp_stop(struct i40e_pf *pf) ptp_clock_unregister(pf->ptp_clock); pf->ptp_clock = NULL; dev_info(&pf->pdev->dev, "%s: removed PHC on %s\n", __func__, - pf->vsi[pf->lan_vsi]->netdev->name); + main_vsi->netdev->name); } if (i40e_is_ptp_pin_dev(&pf->hw)) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_trace.h b/drivers/net/ethernet/intel/i40e/i40e_trace.h index 33b4e30f5e00..759f3d1c4c8f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_trace.h +++ b/drivers/net/ethernet/intel/i40e/i40e_trace.h @@ -89,8 +89,8 @@ TRACE_EVENT(i40e_napi_poll, __entry->tx_clean_complete = tx_clean_complete; __entry->irq_num = q->irq_num; __entry->curr_cpu = get_cpu(); - __assign_str(qname, q->name); - __assign_str(dev_name, napi->dev ? napi->dev->name : NO_DEV); + __assign_str(qname); + __assign_str(dev_name); __assign_bitmask(irq_affinity, cpumask_bits(&q->affinity_mask), nr_cpumask_bits); ), @@ -132,7 +132,7 @@ DECLARE_EVENT_CLASS( __entry->ring = ring; __entry->desc = desc; __entry->buf = buf; - __assign_str(devname, ring->netdev->name); + __assign_str(devname); ), TP_printk( @@ -177,7 +177,7 @@ DECLARE_EVENT_CLASS( __entry->ring = ring; __entry->desc = desc; __entry->xdp = xdp; - __assign_str(devname, ring->netdev->name); + __assign_str(devname); ), TP_printk( @@ -219,7 +219,7 @@ DECLARE_EVENT_CLASS( TP_fast_assign( __entry->skb = skb; __entry->ring = ring; - __assign_str(devname, ring->netdev->name); + __assign_str(devname); ), TP_printk( diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 1a12b732818e..c006f716a3bd 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2,6 +2,7 @@ /* Copyright(c) 2013 - 2018 Intel Corporation. */ #include <linux/bpf_trace.h> +#include <linux/net/intel/libie/rx.h> #include <linux/prefetch.h> #include <linux/sctp.h> #include <net/mpls.h> @@ -23,7 +24,7 @@ static void i40e_fdir(struct i40e_ring *tx_ring, { struct i40e_filter_program_desc *fdir_desc; struct i40e_pf *pf = tx_ring->vsi->back; - u32 flex_ptype, dtype_cmd; + u32 flex_ptype, dtype_cmd, vsi_id; u16 i; /* grab the next descriptor */ @@ -41,8 +42,8 @@ static void i40e_fdir(struct i40e_ring *tx_ring, flex_ptype |= FIELD_PREP(I40E_TXD_FLTR_QW0_PCTYPE_MASK, fdata->pctype); /* Use LAN VSI Id if not programmed by user */ - flex_ptype |= FIELD_PREP(I40E_TXD_FLTR_QW0_DEST_VSI_MASK, - fdata->dest_vsi ? : pf->vsi[pf->lan_vsi]->id); + vsi_id = fdata->dest_vsi ? : i40e_pf_get_main_vsi(pf)->id; + flex_ptype |= FIELD_PREP(I40E_TXD_FLTR_QW0_DEST_VSI_MASK, vsi_id); dtype_cmd = I40E_TX_DESC_DTYPE_FILTER_PROG; @@ -860,13 +861,15 @@ u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw) /** * i40e_detect_recover_hung - Function to detect and recover hung_queues - * @vsi: pointer to vsi struct with tx queues + * @pf: pointer to PF struct * - * VSI has netdev and netdev has TX queues. This function is to check each of - * those TX queues if they are hung, trigger recovery by issuing SW interrupt. + * LAN VSI has netdev and netdev has TX queues. This function is to check + * each of those TX queues if they are hung, trigger recovery by issuing + * SW interrupt. **/ -void i40e_detect_recover_hung(struct i40e_vsi *vsi) +void i40e_detect_recover_hung(struct i40e_pf *pf) { + struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf); struct i40e_ring *tx_ring = NULL; struct net_device *netdev; unsigned int i; @@ -1741,38 +1744,30 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, struct sk_buff *skb, union i40e_rx_desc *rx_desc) { - struct i40e_rx_ptype_decoded decoded; + struct libeth_rx_pt decoded; u32 rx_error, rx_status; bool ipv4, ipv6; u8 ptype; u64 qword; - qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - ptype = FIELD_GET(I40E_RXD_QW1_PTYPE_MASK, qword); - rx_error = FIELD_GET(I40E_RXD_QW1_ERROR_MASK, qword); - rx_status = FIELD_GET(I40E_RXD_QW1_STATUS_MASK, qword); - decoded = decode_rx_desc_ptype(ptype); - skb->ip_summed = CHECKSUM_NONE; - skb_checksum_none_assert(skb); + qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); + ptype = FIELD_GET(I40E_RXD_QW1_PTYPE_MASK, qword); - /* Rx csum enabled and ip headers found? */ - if (!(vsi->netdev->features & NETIF_F_RXCSUM)) + decoded = libie_rx_pt_parse(ptype); + if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded)) return; + rx_error = FIELD_GET(I40E_RXD_QW1_ERROR_MASK, qword); + rx_status = FIELD_GET(I40E_RXD_QW1_STATUS_MASK, qword); + /* did the hardware decode the packet and checksum? */ if (!(rx_status & BIT(I40E_RX_DESC_STATUS_L3L4P_SHIFT))) return; - /* both known and outer_ip must be set for the below code to work */ - if (!(decoded.known && decoded.outer_ip)) - return; - - ipv4 = (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP) && - (decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV4); - ipv6 = (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP) && - (decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV6); + ipv4 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV4; + ipv6 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV6; if (ipv4 && (rx_error & (BIT(I40E_RX_DESC_ERROR_IPE_SHIFT) | @@ -1800,20 +1795,10 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, * 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 >= I40E_RX_PTYPE_TUNNEL_IP_GRENAT) + if (decoded.tunnel_type >= LIBETH_RX_PT_TUNNEL_IP_GRENAT) skb->csum_level = 1; - /* Only report checksum unnecessary for TCP, UDP, or SCTP */ - switch (decoded.inner_prot) { - case I40E_RX_PTYPE_INNER_PROT_TCP: - case I40E_RX_PTYPE_INNER_PROT_UDP: - case I40E_RX_PTYPE_INNER_PROT_SCTP: - skb->ip_summed = CHECKSUM_UNNECESSARY; - fallthrough; - default: - break; - } - + skb->ip_summed = CHECKSUM_UNNECESSARY; return; checksum_fail: @@ -1821,29 +1806,6 @@ checksum_fail: } /** - * i40e_ptype_to_htype - get a hash type - * @ptype: the ptype value from the descriptor - * - * Returns a hash type to be used by skb_set_hash - **/ -static inline int i40e_ptype_to_htype(u8 ptype) -{ - struct i40e_rx_ptype_decoded decoded = decode_rx_desc_ptype(ptype); - - if (!decoded.known) - return PKT_HASH_TYPE_NONE; - - if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP && - decoded.payload_layer == I40E_RX_PTYPE_PAYLOAD_LAYER_PAY4) - return PKT_HASH_TYPE_L4; - else if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP && - decoded.payload_layer == I40E_RX_PTYPE_PAYLOAD_LAYER_PAY3) - return PKT_HASH_TYPE_L3; - else - return PKT_HASH_TYPE_L2; -} - -/** * i40e_rx_hash - set the hash value in the skb * @ring: descriptor ring * @rx_desc: specific descriptor @@ -1855,17 +1817,19 @@ static inline void i40e_rx_hash(struct i40e_ring *ring, struct sk_buff *skb, u8 rx_ptype) { + struct libeth_rx_pt decoded; u32 hash; const __le64 rss_mask = cpu_to_le64((u64)I40E_RX_DESC_FLTSTAT_RSS_HASH << I40E_RX_DESC_STATUS_FLTSTAT_SHIFT); - if (!(ring->netdev->features & NETIF_F_RXHASH)) + decoded = libie_rx_pt_parse(rx_ptype); + if (!libeth_rx_pt_has_hash(ring->netdev, decoded)) return; if ((rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask) { hash = le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss); - skb_set_hash(skb, hash, i40e_ptype_to_htype(rx_ptype)); + libeth_rx_pt_set_hash(skb, hash, decoded); } } @@ -2144,9 +2108,7 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, */ /* allocate a skb to store the frags */ - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, - I40E_RX_HDR_SIZE, - GFP_ATOMIC | __GFP_NOWARN); + skb = napi_alloc_skb(&rx_ring->q_vector->napi, I40E_RX_HDR_SIZE); if (unlikely(!skb)) return NULL; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 2cdc7de6301c..7c26c9a2bf65 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -470,7 +470,7 @@ void i40e_free_rx_resources(struct i40e_ring *rx_ring); int i40e_napi_poll(struct napi_struct *napi, int budget); void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector); u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw); -void i40e_detect_recover_hung(struct i40e_vsi *vsi); +void i40e_detect_recover_hung(struct i40e_pf *pf); 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, diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index d9031499697e..28568e126850 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -745,94 +745,6 @@ enum i40e_rx_desc_error_l3l4e_fcoe_masks { #define I40E_RXD_QW1_PTYPE_SHIFT 30 #define I40E_RXD_QW1_PTYPE_MASK (0xFFULL << I40E_RXD_QW1_PTYPE_SHIFT) -/* Packet type non-ip values */ -enum i40e_rx_l2_ptype { - I40E_RX_PTYPE_L2_RESERVED = 0, - I40E_RX_PTYPE_L2_MAC_PAY2 = 1, - I40E_RX_PTYPE_L2_TIMESYNC_PAY2 = 2, - I40E_RX_PTYPE_L2_FIP_PAY2 = 3, - I40E_RX_PTYPE_L2_OUI_PAY2 = 4, - I40E_RX_PTYPE_L2_MACCNTRL_PAY2 = 5, - I40E_RX_PTYPE_L2_LLDP_PAY2 = 6, - I40E_RX_PTYPE_L2_ECP_PAY2 = 7, - I40E_RX_PTYPE_L2_EVB_PAY2 = 8, - I40E_RX_PTYPE_L2_QCN_PAY2 = 9, - I40E_RX_PTYPE_L2_EAPOL_PAY2 = 10, - I40E_RX_PTYPE_L2_ARP = 11, - I40E_RX_PTYPE_L2_FCOE_PAY3 = 12, - I40E_RX_PTYPE_L2_FCOE_FCDATA_PAY3 = 13, - I40E_RX_PTYPE_L2_FCOE_FCRDY_PAY3 = 14, - I40E_RX_PTYPE_L2_FCOE_FCRSP_PAY3 = 15, - I40E_RX_PTYPE_L2_FCOE_FCOTHER_PA = 16, - I40E_RX_PTYPE_L2_FCOE_VFT_PAY3 = 17, - I40E_RX_PTYPE_L2_FCOE_VFT_FCDATA = 18, - I40E_RX_PTYPE_L2_FCOE_VFT_FCRDY = 19, - I40E_RX_PTYPE_L2_FCOE_VFT_FCRSP = 20, - I40E_RX_PTYPE_L2_FCOE_VFT_FCOTHER = 21, - I40E_RX_PTYPE_GRENAT4_MAC_PAY3 = 58, - I40E_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4 = 87, - I40E_RX_PTYPE_GRENAT6_MAC_PAY3 = 124, - I40E_RX_PTYPE_GRENAT6_MACVLAN_IPV6_ICMP_PAY4 = 153 -}; - -struct i40e_rx_ptype_decoded { - u32 known:1; - u32 outer_ip:1; - u32 outer_ip_ver:1; - 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 i40e_rx_ptype_outer_ip { - I40E_RX_PTYPE_OUTER_L2 = 0, - I40E_RX_PTYPE_OUTER_IP = 1 -}; - -enum i40e_rx_ptype_outer_ip_ver { - I40E_RX_PTYPE_OUTER_NONE = 0, - I40E_RX_PTYPE_OUTER_IPV4 = 0, - I40E_RX_PTYPE_OUTER_IPV6 = 1 -}; - -enum i40e_rx_ptype_outer_fragmented { - I40E_RX_PTYPE_NOT_FRAG = 0, - I40E_RX_PTYPE_FRAG = 1 -}; - -enum i40e_rx_ptype_tunnel_type { - I40E_RX_PTYPE_TUNNEL_NONE = 0, - I40E_RX_PTYPE_TUNNEL_IP_IP = 1, - I40E_RX_PTYPE_TUNNEL_IP_GRENAT = 2, - I40E_RX_PTYPE_TUNNEL_IP_GRENAT_MAC = 3, - I40E_RX_PTYPE_TUNNEL_IP_GRENAT_MAC_VLAN = 4, -}; - -enum i40e_rx_ptype_tunnel_end_prot { - I40E_RX_PTYPE_TUNNEL_END_NONE = 0, - I40E_RX_PTYPE_TUNNEL_END_IPV4 = 1, - I40E_RX_PTYPE_TUNNEL_END_IPV6 = 2, -}; - -enum i40e_rx_ptype_inner_prot { - I40E_RX_PTYPE_INNER_PROT_NONE = 0, - I40E_RX_PTYPE_INNER_PROT_UDP = 1, - I40E_RX_PTYPE_INNER_PROT_TCP = 2, - I40E_RX_PTYPE_INNER_PROT_SCTP = 3, - I40E_RX_PTYPE_INNER_PROT_ICMP = 4, - I40E_RX_PTYPE_INNER_PROT_TIMESYNC = 5 -}; - -enum i40e_rx_ptype_payload_layer { - I40E_RX_PTYPE_PAYLOAD_LAYER_NONE = 0, - I40E_RX_PTYPE_PAYLOAD_LAYER_PAY2 = 1, - I40E_RX_PTYPE_PAYLOAD_LAYER_PAY3 = 2, - I40E_RX_PTYPE_PAYLOAD_LAYER_PAY4 = 3, -}; - #define I40E_RXD_QW1_LENGTH_PBUF_SHIFT 38 #define I40E_RXD_QW1_LENGTH_PBUF_MASK (0x3FFFULL << \ I40E_RXD_QW1_LENGTH_PBUF_SHIFT) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 232b65b9c8ea..1120f8e4bb67 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -216,7 +216,7 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf) * @notify_vf: notify vf about reset or not * Reset VF handler. **/ -static void i40e_vc_reset_vf(struct i40e_vf *vf, bool notify_vf) +void i40e_vc_reset_vf(struct i40e_vf *vf, bool notify_vf) { struct i40e_pf *pf = vf->pf; int i; @@ -795,13 +795,13 @@ error_param: static int i40e_alloc_vsi_res(struct i40e_vf *vf, u8 idx) { struct i40e_mac_filter *f = NULL; + struct i40e_vsi *main_vsi, *vsi; struct i40e_pf *pf = vf->pf; - struct i40e_vsi *vsi; u64 max_tx_rate = 0; int ret = 0; - vsi = i40e_vsi_setup(pf, I40E_VSI_SRIOV, pf->vsi[pf->lan_vsi]->seid, - vf->vf_id); + main_vsi = i40e_pf_get_main_vsi(pf); + vsi = i40e_vsi_setup(pf, I40E_VSI_SRIOV, main_vsi->seid, vf->vf_id); if (!vsi) { dev_err(&pf->pdev->dev, @@ -2213,8 +2213,10 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) vfres->vsi_res[0].qset_handle = le16_to_cpu(vsi->info.qs_handle[0]); if (!(vf->driver_caps & VIRTCHNL_VF_OFFLOAD_USO) && !vf->pf_set_mac) { + spin_lock_bh(&vsi->mac_filter_hash_lock); i40e_del_mac_filter(vsi, vf->default_lan_addr.addr); eth_zero_addr(vf->default_lan_addr.addr); + spin_unlock_bh(&vsi->mac_filter_hash_lock); } ether_addr_copy(vfres->vsi_res[0].default_mac_addr, vf->default_lan_addr.addr); @@ -3322,8 +3324,9 @@ error_param: static int i40e_vc_rdma_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) { struct i40e_pf *pf = vf->pf; - int abs_vf_id = vf->vf_id + pf->hw.func_caps.vf_base_id; + struct i40e_vsi *main_vsi; int aq_ret = 0; + int abs_vf_id; if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || !test_bit(I40E_VF_STATE_RDMAENA, &vf->vf_states)) { @@ -3331,8 +3334,9 @@ static int i40e_vc_rdma_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) goto error_param; } - i40e_notify_client_of_vf_msg(pf->vsi[pf->lan_vsi], abs_vf_id, - msg, msglen); + main_vsi = i40e_pf_get_main_vsi(pf); + abs_vf_id = vf->vf_id + pf->hw.func_caps.vf_base_id; + i40e_notify_client_of_vf_msg(main_vsi, abs_vf_id, msg, msglen); error_param: /* send the response to the VF */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 66f95e2f3146..5cf74f16f433 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -64,6 +64,12 @@ struct i40evf_channel { u64 max_tx_rate; /* bandwidth rate allocation for VSIs */ }; +struct i40e_mdd_vf_events { + u64 count; /* total count of Rx|Tx events */ + /* count number of the last printed event */ + u64 last_printed; +}; + /* VF information structure */ struct i40e_vf { struct i40e_pf *pf; @@ -92,7 +98,9 @@ struct i40e_vf { u8 num_queue_pairs; /* num of qps assigned to VF vsis */ u8 num_req_queues; /* num of requested qps */ - u64 num_mdd_events; /* num of mdd events detected */ + /* num of mdd tx and rx events detected */ + struct i40e_mdd_vf_events mdd_rx_events; + struct i40e_mdd_vf_events mdd_tx_events; unsigned long vf_caps; /* vf's adv. capabilities */ unsigned long vf_states; /* vf's runtime states */ @@ -120,6 +128,7 @@ int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs); int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen); int i40e_vc_process_vflr_event(struct i40e_pf *pf); +void i40e_vc_reset_vf(struct i40e_vf *vf, bool notify_vf); bool i40e_reset_vf(struct i40e_vf *vf, bool flr); bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr); void i40e_vc_notify_vf_reset(struct i40e_vf *vf); diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 11500003af0d..9f47388eaba5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -2,6 +2,7 @@ /* Copyright(c) 2018 Intel Corporation. */ #include <linux/bpf_trace.h> +#include <linux/unroll.h> #include <net/xdp_sock_drv.h> #include "i40e_txrx_common.h" #include "i40e_xsk.h" @@ -301,8 +302,7 @@ static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring, net_prefetch(xdp->data_meta); /* allocate a skb to store the frags */ - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize, - GFP_ATOMIC | __GFP_NOWARN); + skb = napi_alloc_skb(&rx_ring->q_vector->napi, totalsize); if (unlikely(!skb)) goto out; @@ -396,32 +396,6 @@ 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), - XDP_PACKET_HEADROOM, 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 @@ -483,12 +457,14 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) 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); + xsk_buff_dma_sync_for_cpu(bi); if (!first) first = bi; - else if (i40e_add_xsk_frag(rx_ring, first, bi, size)) + else if (!xsk_buff_add_frag(first, bi)) { + xsk_buff_free(first); break; + } if (++next_to_process == count) next_to_process = 0; @@ -554,7 +530,8 @@ static void i40e_xmit_pkt_batch(struct i40e_ring *xdp_ring, struct xdp_desc *des dma_addr_t dma; u32 i; - loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) { + unrolled_count(PKTS_PER_BATCH) + 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); diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h index ef156fad52f2..dd16351a7af8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h @@ -6,7 +6,7 @@ #include <linux/types.h> -/* This value should match the pragma in the loop_unrolled_for +/* This value should match the pragma in the unrolled_count() * macro. Why 4? It is strictly empirical. It seems to be a good * compromise between the advantage of having simultaneous outstanding * reads to the DMA array that can hide each others latency and the @@ -14,14 +14,6 @@ */ #define PKTS_PER_BATCH 4 -#ifdef __clang__ -#define loop_unrolled_for _Pragma("clang loop unroll_count(4)") for -#elif __GNUC__ >= 8 -#define loop_unrolled_for _Pragma("GCC unroll 4") for -#else -#define loop_unrolled_for for -#endif - struct i40e_ring; struct i40e_vsi; struct net_device; diff --git a/drivers/net/ethernet/intel/iavf/Makefile b/drivers/net/ethernet/intel/iavf/Makefile index 2d154a4e2fd7..e13720a728ff 100644 --- a/drivers/net/ethernet/intel/iavf/Makefile +++ b/drivers/net/ethernet/intel/iavf/Makefile @@ -11,6 +11,7 @@ subdir-ccflags-y += -I$(src) obj-$(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-y := 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-$(CONFIG_PTP_1588_CLOCK) += iavf_ptp.o diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index db8188c7ac4b..9de3e0ba3731 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -33,12 +33,15 @@ #include <net/udp.h> #include <net/tc_act/tc_gact.h> #include <net/tc_act/tc_mirred.h> +#include <net/tc_act/tc_skbedit.h> +#include <net/net_shaper.h> #include "iavf_type.h" #include <linux/avf/virtchnl.h> #include "iavf_txrx.h" #include "iavf_fdir.h" #include "iavf_adv_rss.h" +#include "iavf_types.h" #include <linux/bitmap.h> #define DEFAULT_DEBUG_LEVEL_SHIFT 3 @@ -80,7 +83,7 @@ struct iavf_vsi { #define MAXIMUM_ETHERNET_VLAN_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN) -#define IAVF_RX_DESC(R, i) (&(((union iavf_32byte_rx_desc *)((R)->desc))[i])) +#define IAVF_RX_DESC(R, i) (&(((struct iavf_rx_desc *)((R)->desc))[i])) #define IAVF_TX_DESC(R, i) (&(((struct iavf_tx_desc *)((R)->desc))[i])) #define IAVF_TX_CTXTDESC(R, i) \ (&(((struct iavf_tx_context_desc *)((R)->desc))[i])) @@ -249,6 +252,9 @@ struct iavf_cloud_filter { #define IAVF_RESET_WAIT_DETECTED_COUNT 500 #define IAVF_RESET_WAIT_COMPLETE_COUNT 2000 +#define IAVF_MAX_QOS_TC_NUM 8 +#define IAVF_DEFAULT_QUANTA_SIZE 1024 + /* board specific private data structure */ struct iavf_adapter { struct workqueue_struct *wq; @@ -266,6 +272,7 @@ struct iavf_adapter { /* Lock to protect accesses to MAC and VLAN lists */ spinlock_t mac_vlan_list_lock; char misc_vector_name[IFNAMSIZ + 9]; + u8 rxdid; int num_active_queues; int num_req_queues; @@ -287,7 +294,7 @@ 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_LEGACY_RX BIT(15) +/* BIT(15) is free, was IAVF_FLAG_LEGACY_RX */ #define IAVF_FLAG_REINIT_ITR_NEEDED BIT(16) #define IAVF_FLAG_QUEUES_DISABLED BIT(17) #define IAVF_FLAG_SETUP_NETDEV_FEATURES BIT(18) @@ -335,6 +342,20 @@ struct iavf_adapter { #define IAVF_FLAG_AQ_DISABLE_CTAG_VLAN_INSERTION BIT_ULL(36) #define IAVF_FLAG_AQ_ENABLE_STAG_VLAN_INSERTION BIT_ULL(37) #define IAVF_FLAG_AQ_DISABLE_STAG_VLAN_INSERTION BIT_ULL(38) +#define IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW BIT_ULL(39) +#define IAVF_FLAG_AQ_CFG_QUEUES_QUANTA_SIZE BIT_ULL(40) +#define IAVF_FLAG_AQ_GET_QOS_CAPS BIT_ULL(41) +#define IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS BIT_ULL(42) +#define IAVF_FLAG_AQ_GET_PTP_CAPS BIT_ULL(43) +#define IAVF_FLAG_AQ_SEND_PTP_CMD BIT_ULL(44) + + /* AQ messages that must be sent after IAVF_FLAG_AQ_GET_CONFIG, in + * order to negotiated extended capabilities. + */ +#define IAVF_FLAG_AQ_EXTENDED_CAPS \ + (IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS | \ + IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS | \ + IAVF_FLAG_AQ_GET_PTP_CAPS) /* flags for processing extended capability messages during * __IAVF_INIT_EXTENDED_CAPS. Each capability exchange requires @@ -346,10 +367,18 @@ struct iavf_adapter { u64 extended_caps; #define IAVF_EXTENDED_CAP_SEND_VLAN_V2 BIT_ULL(0) #define IAVF_EXTENDED_CAP_RECV_VLAN_V2 BIT_ULL(1) +#define IAVF_EXTENDED_CAP_SEND_RXDID BIT_ULL(2) +#define IAVF_EXTENDED_CAP_RECV_RXDID BIT_ULL(3) +#define IAVF_EXTENDED_CAP_SEND_PTP BIT_ULL(4) +#define IAVF_EXTENDED_CAP_RECV_PTP BIT_ULL(5) #define IAVF_EXTENDED_CAPS \ (IAVF_EXTENDED_CAP_SEND_VLAN_V2 | \ - IAVF_EXTENDED_CAP_RECV_VLAN_V2) + IAVF_EXTENDED_CAP_RECV_VLAN_V2 | \ + IAVF_EXTENDED_CAP_SEND_RXDID | \ + IAVF_EXTENDED_CAP_RECV_RXDID | \ + IAVF_EXTENDED_CAP_SEND_PTP | \ + IAVF_EXTENDED_CAP_RECV_PTP) /* Lock to prevent possible clobbering of * current_netdev_promisc_flags @@ -393,6 +422,8 @@ struct iavf_adapter { VIRTCHNL_VF_OFFLOAD_VLAN_V2) #define CRC_OFFLOAD_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \ VIRTCHNL_VF_OFFLOAD_CRC) +#define TC_U32_SUPPORT(_a) ((_a)->vf_res->vf_cap_flags & \ + VIRTCHNL_VF_OFFLOAD_TC_U32) #define VLAN_V2_FILTERING_ALLOWED(_a) \ (VLAN_V2_ALLOWED((_a)) && \ ((_a)->vlan_v2_caps.filtering.filtering_support.outer || \ @@ -405,14 +436,23 @@ struct iavf_adapter { VIRTCHNL_VF_OFFLOAD_FDIR_PF) #define ADV_RSS_SUPPORT(_a) ((_a)->vf_res->vf_cap_flags & \ VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF) +#define QOS_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \ + VIRTCHNL_VF_OFFLOAD_QOS) +#define IAVF_RXDID_ALLOWED(a) \ + ((a)->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) +#define IAVF_PTP_ALLOWED(a) \ + ((a)->vf_res->vf_cap_flags & VIRTCHNL_VF_CAP_PTP) struct virtchnl_vf_resource *vf_res; /* incl. all VSIs */ struct virtchnl_vsi_resource *vsi_res; /* our LAN VSI */ struct virtchnl_version_info pf_version; #define PF_IS_V11(_a) (((_a)->pf_version.major == 1) && \ ((_a)->pf_version.minor == 1)) struct virtchnl_vlan_caps vlan_v2_caps; + u64 supp_rxdids; + struct iavf_ptp ptp; u16 msg_enable; struct iavf_eth_stats current_stats; + struct virtchnl_qos_cap_list *qos_caps; struct iavf_vsi vsi; u32 aq_wait_count; /* RSS stuff */ @@ -437,6 +477,7 @@ struct iavf_adapter { #define IAVF_MAX_FDIR_FILTERS 128 /* max allowed Flow Director filters */ u16 fdir_active_fltr; + u16 raw_fdir_active_fltr; struct list_head fdir_list_head; spinlock_t fdir_fltr_lock; /* protect the Flow Director filter list */ @@ -444,6 +485,32 @@ struct iavf_adapter { spinlock_t adv_rss_lock; /* protect the RSS management list */ }; +/* Must be called with fdir_fltr_lock lock held */ +static inline bool iavf_fdir_max_reached(struct iavf_adapter *adapter) +{ + return adapter->fdir_active_fltr + adapter->raw_fdir_active_fltr >= + IAVF_MAX_FDIR_FILTERS; +} + +static inline void +iavf_inc_fdir_active_fltr(struct iavf_adapter *adapter, + struct iavf_fdir_fltr *fltr) +{ + if (iavf_is_raw_fdir(fltr)) + adapter->raw_fdir_active_fltr++; + else + adapter->fdir_active_fltr++; +} + +static inline void +iavf_dec_fdir_active_fltr(struct iavf_adapter *adapter, + struct iavf_fdir_fltr *fltr) +{ + if (iavf_is_raw_fdir(fltr)) + adapter->raw_fdir_active_fltr--; + else + adapter->fdir_active_fltr--; +} /* Ethtool Private Flags */ @@ -499,37 +566,33 @@ static inline void iavf_change_state(struct iavf_adapter *adapter, iavf_state_str(adapter->state)); } -int iavf_up(struct iavf_adapter *adapter); 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_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); -void iavf_update_stats(struct iavf_adapter *adapter); void iavf_free_all_tx_resources(struct iavf_adapter *adapter); void iavf_free_all_rx_resources(struct iavf_adapter *adapter); -void iavf_napi_add_all(struct iavf_adapter *adapter); -void iavf_napi_del_all(struct iavf_adapter *adapter); - int iavf_send_api_ver(struct iavf_adapter *adapter); int iavf_verify_api_ver(struct iavf_adapter *adapter); int iavf_send_vf_config_msg(struct iavf_adapter *adapter); int iavf_get_vf_config(struct iavf_adapter *adapter); int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter); int iavf_send_vf_offload_vlan_v2_msg(struct iavf_adapter *adapter); +int iavf_send_vf_supported_rxdids_msg(struct iavf_adapter *adapter); +int iavf_get_vf_supported_rxdids(struct iavf_adapter *adapter); +int iavf_send_vf_ptp_caps_msg(struct iavf_adapter *adapter); +int iavf_get_vf_ptp_caps(struct iavf_adapter *adapter); void iavf_set_queue_vlan_tag_loc(struct iavf_adapter *adapter); u16 iavf_get_num_vlans_added(struct iavf_adapter *adapter); void iavf_irq_enable(struct iavf_adapter *adapter, bool flush); void iavf_configure_queues(struct iavf_adapter *adapter); -void iavf_deconfigure_queues(struct iavf_adapter *adapter); void iavf_enable_queues(struct iavf_adapter *adapter); void iavf_disable_queues(struct iavf_adapter *adapter); void iavf_map_queues(struct iavf_adapter *adapter); -int iavf_request_queues(struct iavf_adapter *adapter, int num); 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); @@ -549,8 +612,9 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, enum virtchnl_ops v_opcode, enum iavf_status v_retval, u8 *msg, u16 msglen); 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_cfg_queues_bw(struct iavf_adapter *adapter); +void iavf_cfg_queues_quanta_size(struct iavf_adapter *adapter); +void iavf_get_qos_caps(struct iavf_adapter *adapter); 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_common.c b/drivers/net/ethernet/intel/iavf/iavf_common.c index 5a25233a89d5..aa751ce3425b 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_common.c +++ b/drivers/net/ethernet/intel/iavf/iavf_common.c @@ -432,259 +432,6 @@ enum iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 vsi_id, return iavf_aq_get_set_rss_key(hw, vsi_id, key, true); } -/* The iavf_ptype_lookup table is used to convert from the 8-bit ptype in the - * hardware to a bit-field that can be used by SW to more easily determine the - * packet type. - * - * Macros are used to shorten the table lines and make this table human - * readable. - * - * We store the PTYPE in the top byte of the bit field - this is just so that - * we can check that the table doesn't have a row missing, as the index into - * the table should be the PTYPE. - * - * Typical work flow: - * - * IF NOT iavf_ptype_lookup[ptype].known - * THEN - * Packet is unknown - * ELSE IF iavf_ptype_lookup[ptype].outer_ip == IAVF_RX_PTYPE_OUTER_IP - * Use the rest of the fields to look at the tunnels, inner protocols, etc - * ELSE - * Use the enum iavf_rx_l2_ptype to decode the packet type - * ENDIF - */ - -/* macro to make the table lines short, use explicit indexing with [PTYPE] */ -#define IAVF_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\ - [PTYPE] = { \ - 1, \ - IAVF_RX_PTYPE_OUTER_##OUTER_IP, \ - IAVF_RX_PTYPE_OUTER_##OUTER_IP_VER, \ - IAVF_RX_PTYPE_##OUTER_FRAG, \ - IAVF_RX_PTYPE_TUNNEL_##T, \ - IAVF_RX_PTYPE_TUNNEL_END_##TE, \ - IAVF_RX_PTYPE_##TEF, \ - IAVF_RX_PTYPE_INNER_PROT_##I, \ - IAVF_RX_PTYPE_PAYLOAD_LAYER_##PL } - -#define IAVF_PTT_UNUSED_ENTRY(PTYPE) [PTYPE] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 } - -/* shorter macros makes the table fit but are terse */ -#define IAVF_RX_PTYPE_NOF IAVF_RX_PTYPE_NOT_FRAG -#define IAVF_RX_PTYPE_FRG IAVF_RX_PTYPE_FRAG -#define IAVF_RX_PTYPE_INNER_PROT_TS IAVF_RX_PTYPE_INNER_PROT_TIMESYNC - -/* Lookup table mapping the 8-bit HW PTYPE to the bit field for decoding */ -struct iavf_rx_ptype_decoded iavf_ptype_lookup[BIT(8)] = { - /* L2 Packet types */ - IAVF_PTT_UNUSED_ENTRY(0), - IAVF_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - IAVF_PTT(2, L2, NONE, NOF, NONE, NONE, NOF, TS, PAY2), - IAVF_PTT(3, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - IAVF_PTT_UNUSED_ENTRY(4), - IAVF_PTT_UNUSED_ENTRY(5), - IAVF_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - IAVF_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - IAVF_PTT_UNUSED_ENTRY(8), - IAVF_PTT_UNUSED_ENTRY(9), - IAVF_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - IAVF_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), - IAVF_PTT(12, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(13, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(14, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(15, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(16, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(17, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(18, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(19, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(20, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(21, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - - /* Non Tunneled IPv4 */ - IAVF_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(25), - IAVF_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP, PAY4), - IAVF_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4), - IAVF_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4), - - /* IPv4 --> IPv4 */ - IAVF_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3), - IAVF_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3), - IAVF_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(32), - IAVF_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP, PAY4), - IAVF_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), - IAVF_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), - - /* IPv4 --> IPv6 */ - IAVF_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3), - IAVF_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3), - IAVF_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(39), - IAVF_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP, PAY4), - IAVF_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), - IAVF_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT */ - IAVF_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), - - /* IPv4 --> GRE/NAT --> IPv4 */ - IAVF_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), - IAVF_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), - IAVF_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(47), - IAVF_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), - IAVF_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), - IAVF_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT --> IPv6 */ - IAVF_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), - IAVF_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), - IAVF_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(54), - IAVF_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), - IAVF_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), - IAVF_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT --> MAC */ - IAVF_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), - - /* IPv4 --> GRE/NAT --> MAC --> IPv4 */ - IAVF_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), - IAVF_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), - IAVF_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(62), - IAVF_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), - IAVF_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), - IAVF_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT -> MAC --> IPv6 */ - IAVF_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), - IAVF_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), - IAVF_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(69), - IAVF_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), - IAVF_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), - IAVF_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT --> MAC/VLAN */ - IAVF_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), - - /* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */ - IAVF_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), - IAVF_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), - IAVF_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(77), - IAVF_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), - IAVF_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), - IAVF_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), - - /* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */ - IAVF_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), - IAVF_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), - IAVF_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(84), - IAVF_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), - IAVF_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), - IAVF_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), - - /* Non Tunneled IPv6 */ - IAVF_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(91), - IAVF_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP, PAY4), - IAVF_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4), - IAVF_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4), - - /* IPv6 --> IPv4 */ - IAVF_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3), - IAVF_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3), - IAVF_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(98), - IAVF_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP, PAY4), - IAVF_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), - IAVF_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> IPv6 */ - IAVF_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3), - IAVF_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3), - IAVF_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(105), - IAVF_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP, PAY4), - IAVF_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), - IAVF_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT */ - IAVF_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), - - /* IPv6 --> GRE/NAT -> IPv4 */ - IAVF_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), - IAVF_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), - IAVF_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(113), - IAVF_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), - IAVF_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), - IAVF_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> IPv6 */ - IAVF_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), - IAVF_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), - IAVF_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(120), - IAVF_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), - IAVF_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), - IAVF_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC */ - IAVF_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), - - /* IPv6 --> GRE/NAT -> MAC -> IPv4 */ - IAVF_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), - IAVF_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), - IAVF_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(128), - IAVF_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), - IAVF_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), - IAVF_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC -> IPv6 */ - IAVF_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), - IAVF_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), - IAVF_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(135), - IAVF_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), - IAVF_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), - IAVF_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC/VLAN */ - IAVF_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), - - /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */ - IAVF_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), - IAVF_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), - IAVF_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(143), - IAVF_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), - IAVF_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), - IAVF_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */ - IAVF_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), - IAVF_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), - IAVF_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(150), - IAVF_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), - IAVF_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), - IAVF_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), - - /* unused entries */ - [154 ... 255] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 } -}; - /** * iavf_aq_send_msg_to_pf * @hw: pointer to the hardware structure diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 378c3e9ddf9d..288bb5b2e72e 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -240,29 +240,6 @@ static const struct iavf_stats iavf_gstrings_stats[] = { #define IAVF_QUEUE_STATS_LEN ARRAY_SIZE(iavf_gstrings_queue_stats) -/* For now we have one and only one private flag and it is only defined - * when we have support for the SKIP_CPU_SYNC DMA attribute. Instead - * of leaving all this code sitting around empty we will strip it unless - * our one private flag is actually available. - */ -struct iavf_priv_flags { - char flag_string[ETH_GSTRING_LEN]; - u32 flag; - bool read_only; -}; - -#define IAVF_PRIV_FLAG(_name, _flag, _read_only) { \ - .flag_string = _name, \ - .flag = _flag, \ - .read_only = _read_only, \ -} - -static const struct iavf_priv_flags iavf_gstrings_priv_flags[] = { - IAVF_PRIV_FLAG("legacy-rx", IAVF_FLAG_LEGACY_RX, 0), -}; - -#define IAVF_PRIV_FLAGS_STR_LEN ARRAY_SIZE(iavf_gstrings_priv_flags) - /** * iavf_get_link_ksettings - Get Link Speed and Duplex settings * @netdev: network interface device structure @@ -342,8 +319,6 @@ static int iavf_get_sset_count(struct net_device *netdev, int sset) return IAVF_STATS_LEN + (IAVF_QUEUE_STATS_LEN * 2 * netdev->real_num_tx_queues); - else if (sset == ETH_SS_PRIV_FLAGS) - return IAVF_PRIV_FLAGS_STR_LEN; else return -EINVAL; } @@ -386,21 +361,6 @@ static void iavf_get_ethtool_stats(struct net_device *netdev, } /** - * iavf_get_priv_flag_strings - Get private flag strings - * @netdev: network interface device structure - * @data: buffer for string data - * - * Builds the private flags string table - **/ -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++) - ethtool_puts(&data, iavf_gstrings_priv_flags[i].flag_string); -} - -/** * iavf_get_stat_strings - Get stat strings * @netdev: network interface device structure * @data: buffer for string data @@ -438,109 +398,12 @@ static void iavf_get_strings(struct net_device *netdev, u32 sset, u8 *data) case ETH_SS_STATS: iavf_get_stat_strings(netdev, data); break; - case ETH_SS_PRIV_FLAGS: - iavf_get_priv_flag_strings(netdev, data); - break; default: break; } } /** - * iavf_get_priv_flags - report device private flags - * @netdev: network interface device structure - * - * The get string set count and the string set should be matched for each - * flag returned. Add new strings for each flag to the iavf_gstrings_priv_flags - * array. - * - * Returns a u32 bitmap of flags. - **/ -static u32 iavf_get_priv_flags(struct net_device *netdev) -{ - struct iavf_adapter *adapter = netdev_priv(netdev); - u32 i, ret_flags = 0; - - for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++) { - const struct iavf_priv_flags *priv_flags; - - priv_flags = &iavf_gstrings_priv_flags[i]; - - if (priv_flags->flag & adapter->flags) - ret_flags |= BIT(i); - } - - return ret_flags; -} - -/** - * iavf_set_priv_flags - set private flags - * @netdev: network interface device structure - * @flags: bit flags to be set - **/ -static int iavf_set_priv_flags(struct net_device *netdev, u32 flags) -{ - struct iavf_adapter *adapter = netdev_priv(netdev); - u32 orig_flags, new_flags, changed_flags; - int ret = 0; - u32 i; - - orig_flags = READ_ONCE(adapter->flags); - new_flags = orig_flags; - - for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++) { - const struct iavf_priv_flags *priv_flags; - - priv_flags = &iavf_gstrings_priv_flags[i]; - - if (flags & BIT(i)) - new_flags |= priv_flags->flag; - else - new_flags &= ~(priv_flags->flag); - - if (priv_flags->read_only && - ((orig_flags ^ new_flags) & ~BIT(i))) - return -EOPNOTSUPP; - } - - /* Before we finalize any flag changes, any checks which we need to - * perform to determine if the new flags will be supported should go - * here... - */ - - /* Compare and exchange the new flags into place. If we failed, that - * is if cmpxchg returns anything but the old value, this means - * something else must have modified the flags variable since we - * copied it. We'll just punt with an error and log something in the - * message buffer. - */ - if (cmpxchg(&adapter->flags, orig_flags, new_flags) != orig_flags) { - dev_warn(&adapter->pdev->dev, - "Unable to update adapter->flags as it was modified by another thread...\n"); - return -EAGAIN; - } - - changed_flags = orig_flags ^ new_flags; - - /* Process any additional changes needed as a result of flag changes. - * The changed_flags value reflects the list of bits that were changed - * in the code above. - */ - - /* issue a reset to force legacy-rx change to take effect */ - if (changed_flags & IAVF_FLAG_LEGACY_RX) { - if (netif_running(netdev)) { - iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); - ret = iavf_wait_for_reset(adapter); - if (ret) - netdev_warn(netdev, "Changing private flags timeout or interrupted waiting for reset"); - } - } - - return ret; -} - -/** * iavf_get_msglevel - Get debug message level * @netdev: network interface device structure * @@ -585,7 +448,6 @@ static void iavf_get_drvinfo(struct net_device *netdev, strscpy(drvinfo->driver, iavf_driver_name, 32); strscpy(drvinfo->fw_version, "N/A", 4); strscpy(drvinfo->bus_info, pci_name(adapter->pdev), 32); - drvinfo->n_priv_flags = IAVF_PRIV_FLAGS_STR_LEN; } /** @@ -1065,7 +927,7 @@ iavf_get_ethtool_fdir_entry(struct iavf_adapter *adapter, spin_lock_bh(&adapter->fdir_fltr_lock); - rule = iavf_find_fdir_fltr_by_loc(adapter, fsp->location); + rule = iavf_find_fdir_fltr(adapter, false, fsp->location); if (!rule) { ret = -EINVAL; goto release_lock; @@ -1210,6 +1072,9 @@ iavf_get_fdir_fltr_ids(struct iavf_adapter *adapter, struct ethtool_rxnfc *cmd, spin_lock_bh(&adapter->fdir_fltr_lock); list_for_each_entry(fltr, &adapter->fdir_list_head, list) { + if (iavf_is_raw_fdir(fltr)) + continue; + if (cnt == cmd->rule_cnt) { val = -EMSGSIZE; goto release_lock; @@ -1401,15 +1266,7 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx return -EINVAL; spin_lock_bh(&adapter->fdir_fltr_lock); - if (adapter->fdir_active_fltr >= IAVF_MAX_FDIR_FILTERS) { - spin_unlock_bh(&adapter->fdir_fltr_lock); - dev_err(&adapter->pdev->dev, - "Unable to add Flow Director filter because VF reached the limit of max allowed filters (%u)\n", - IAVF_MAX_FDIR_FILTERS); - return -ENOSPC; - } - - if (iavf_find_fdir_fltr_by_loc(adapter, fsp->location)) { + if (iavf_find_fdir_fltr(adapter, false, fsp->location)) { dev_err(&adapter->pdev->dev, "Failed to add Flow Director filter, it already exists\n"); spin_unlock_bh(&adapter->fdir_fltr_lock); return -EEXIST; @@ -1429,23 +1286,10 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx } err = iavf_add_fdir_fltr_info(adapter, fsp, fltr); - if (err) - goto ret; - - spin_lock_bh(&adapter->fdir_fltr_lock); - iavf_fdir_list_add_fltr(adapter, fltr); - adapter->fdir_active_fltr++; - - if (adapter->link_up) - fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST; - else - fltr->state = IAVF_FDIR_FLTR_INACTIVE; - spin_unlock_bh(&adapter->fdir_fltr_lock); + if (!err) + err = iavf_fdir_add_fltr(adapter, fltr); - if (adapter->link_up) - iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_FDIR_FILTER); -ret: - if (err && fltr) + if (err) kfree(fltr); mutex_unlock(&adapter->crit_lock); @@ -1462,34 +1306,11 @@ ret: static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rxnfc *cmd) { struct ethtool_rx_flow_spec *fsp = (struct ethtool_rx_flow_spec *)&cmd->fs; - struct iavf_fdir_fltr *fltr = NULL; - int err = 0; if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) return -EOPNOTSUPP; - spin_lock_bh(&adapter->fdir_fltr_lock); - fltr = iavf_find_fdir_fltr_by_loc(adapter, fsp->location); - if (fltr) { - if (fltr->state == IAVF_FDIR_FLTR_ACTIVE) { - fltr->state = IAVF_FDIR_FLTR_DEL_REQUEST; - } else if (fltr->state == IAVF_FDIR_FLTR_INACTIVE) { - list_del(&fltr->list); - kfree(fltr); - adapter->fdir_active_fltr--; - fltr = NULL; - } else { - err = -EBUSY; - } - } else if (adapter->fdir_active_fltr) { - err = -EINVAL; - } - spin_unlock_bh(&adapter->fdir_fltr_lock); - - if (fltr && fltr->state == IAVF_FDIR_FLTR_DEL_REQUEST) - iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_FDIR_FILTER); - - return err; + return iavf_fdir_del_fltr(adapter, false, fsp->location); } /** @@ -1987,7 +1808,7 @@ static int iavf_set_rxfh(struct net_device *netdev, static const struct ethtool_ops iavf_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_USE_ADAPTIVE, - .cap_rss_sym_xor_supported = true, + .supported_input_xfrm = RXH_XFRM_SYM_XOR, .get_drvinfo = iavf_get_drvinfo, .get_link = ethtool_op_get_link, .get_ringparam = iavf_get_ringparam, @@ -1995,8 +1816,6 @@ static const struct ethtool_ops iavf_ethtool_ops = { .get_strings = iavf_get_strings, .get_ethtool_stats = iavf_get_ethtool_stats, .get_sset_count = iavf_get_sset_count, - .get_priv_flags = iavf_get_priv_flags, - .set_priv_flags = iavf_set_priv_flags, .get_msglevel = iavf_get_msglevel, .set_msglevel = iavf_set_msglevel, .get_coalesce = iavf_get_coalesce, diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.c b/drivers/net/ethernet/intel/iavf/iavf_fdir.c index 2d47b0b4640e..a1b3b44cc14a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.c +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.c @@ -796,6 +796,9 @@ bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr * spin_lock_bh(&adapter->fdir_fltr_lock); list_for_each_entry(tmp, &adapter->fdir_list_head, list) { + if (iavf_is_raw_fdir(fltr)) + continue; + if (tmp->flow_type != fltr->flow_type) continue; @@ -815,33 +818,52 @@ bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr * } /** - * iavf_find_fdir_fltr_by_loc - find filter with location + * iavf_find_fdir_fltr - find FDIR filter * @adapter: pointer to the VF adapter structure - * @loc: location to find. + * @is_raw: filter type, is raw (tc u32) or not (ethtool) + * @data: data to ID the filter, type dependent * - * Returns pointer to Flow Director filter if found or null + * Returns: pointer to Flow Director filter if found or NULL. Lock must be held. */ -struct iavf_fdir_fltr *iavf_find_fdir_fltr_by_loc(struct iavf_adapter *adapter, u32 loc) +struct iavf_fdir_fltr *iavf_find_fdir_fltr(struct iavf_adapter *adapter, + bool is_raw, u32 data) { struct iavf_fdir_fltr *rule; - list_for_each_entry(rule, &adapter->fdir_list_head, list) - if (rule->loc == loc) + list_for_each_entry(rule, &adapter->fdir_list_head, list) { + if ((is_raw && rule->cls_u32_handle == data) || + (!is_raw && rule->loc == data)) return rule; + } return NULL; } /** - * iavf_fdir_list_add_fltr - add a new node to the flow director filter list + * iavf_fdir_add_fltr - add a new node to the flow director filter list * @adapter: pointer to the VF adapter structure * @fltr: filter node to add to structure + * + * Return: 0 on success or negative errno on failure. */ -void iavf_fdir_list_add_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr) +int iavf_fdir_add_fltr(struct iavf_adapter *adapter, + struct iavf_fdir_fltr *fltr) { struct iavf_fdir_fltr *rule, *parent = NULL; + spin_lock_bh(&adapter->fdir_fltr_lock); + if (iavf_fdir_max_reached(adapter)) { + spin_unlock_bh(&adapter->fdir_fltr_lock); + dev_err(&adapter->pdev->dev, + "Unable to add Flow Director filter (limit (%u) reached)\n", + IAVF_MAX_FDIR_FILTERS); + return -ENOSPC; + } + list_for_each_entry(rule, &adapter->fdir_list_head, list) { + if (iavf_is_raw_fdir(fltr)) + break; + if (rule->loc >= fltr->loc) break; parent = rule; @@ -851,4 +873,55 @@ void iavf_fdir_list_add_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr list_add(&fltr->list, &parent->list); else list_add(&fltr->list, &adapter->fdir_list_head); + + iavf_inc_fdir_active_fltr(adapter, fltr); + + if (adapter->link_up) + fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST; + else + fltr->state = IAVF_FDIR_FLTR_INACTIVE; + spin_unlock_bh(&adapter->fdir_fltr_lock); + + if (adapter->link_up) + iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_FDIR_FILTER); + + return 0; +} + +/** + * iavf_fdir_del_fltr - delete a flow director filter from the list + * @adapter: pointer to the VF adapter structure + * @is_raw: filter type, is raw (tc u32) or not (ethtool) + * @data: data to ID the filter, type dependent + * + * Return: 0 on success or negative errno on failure. + */ +int iavf_fdir_del_fltr(struct iavf_adapter *adapter, bool is_raw, u32 data) +{ + struct iavf_fdir_fltr *fltr = NULL; + int err = 0; + + spin_lock_bh(&adapter->fdir_fltr_lock); + fltr = iavf_find_fdir_fltr(adapter, is_raw, data); + + if (fltr) { + if (fltr->state == IAVF_FDIR_FLTR_ACTIVE) { + fltr->state = IAVF_FDIR_FLTR_DEL_REQUEST; + } else if (fltr->state == IAVF_FDIR_FLTR_INACTIVE) { + list_del(&fltr->list); + iavf_dec_fdir_active_fltr(adapter, fltr); + kfree(fltr); + fltr = NULL; + } else { + err = -EBUSY; + } + } else if (adapter->fdir_active_fltr) { + err = -EINVAL; + } + + if (fltr && fltr->state == IAVF_FDIR_FLTR_DEL_REQUEST) + iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_FDIR_FILTER); + + spin_unlock_bh(&adapter->fdir_fltr_lock); + return err; } diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.h b/drivers/net/ethernet/intel/iavf/iavf_fdir.h index d31bd923ba8c..e84a5351162f 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.h +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.h @@ -117,17 +117,26 @@ struct iavf_fdir_fltr { u32 flow_id; + u32 cls_u32_handle; /* for FDIR added via tc u32 */ u32 loc; /* Rule location inside the flow table */ u32 q_index; struct virtchnl_fdir_add vc_add_msg; }; +static inline bool iavf_is_raw_fdir(struct iavf_fdir_fltr *fltr) +{ + return !fltr->vc_add_msg.rule_cfg.proto_hdrs.count; +} + int iavf_validate_fdir_fltr_masks(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); int iavf_fill_fdir_add_msg(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); void iavf_print_fdir_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); -void iavf_fdir_list_add_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); -struct iavf_fdir_fltr *iavf_find_fdir_fltr_by_loc(struct iavf_adapter *adapter, u32 loc); +int iavf_fdir_add_fltr(struct iavf_adapter *adapter, + struct iavf_fdir_fltr *fltr); +int iavf_fdir_del_fltr(struct iavf_adapter *adapter, bool is_raw, u32 data); +struct iavf_fdir_fltr *iavf_find_fdir_fltr(struct iavf_adapter *adapter, + bool is_raw, u32 data); #endif /* _IAVF_FDIR_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 166832a4213a..6d7ba4d67a19 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1,7 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ +#include <linux/net/intel/libie/rx.h> +#include <net/netdev_lock.h> + #include "iavf.h" +#include "iavf_ptp.h" #include "iavf_prototype.h" /* All iavf tracepoints are defined by the include below, which must * be included exactly once across the whole kernel with @@ -43,8 +47,9 @@ static const struct pci_device_id iavf_pci_tbl[] = { MODULE_DEVICE_TABLE(pci, iavf_pci_tbl); MODULE_ALIAS("i40evf"); -MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION("Intel(R) Ethernet Adaptive Virtual Function Network Driver"); +MODULE_IMPORT_NS("LIBETH"); +MODULE_IMPORT_NS("LIBIE"); MODULE_LICENSE("GPL v2"); static const struct net_device_ops iavf_netdev_ops; @@ -707,6 +712,47 @@ static void iavf_configure_tx(struct iavf_adapter *adapter) } /** + * iavf_select_rx_desc_format - Select Rx descriptor format + * @adapter: adapter private structure + * + * Select what Rx descriptor format based on availability and enabled + * features. + * + * Return: the desired RXDID to select for a given Rx queue, as defined by + * enum virtchnl_rxdid_format. + */ +static u8 iavf_select_rx_desc_format(const struct iavf_adapter *adapter) +{ + u64 rxdids = adapter->supp_rxdids; + + /* If we did not negotiate VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC, we must + * stick with the default value of the legacy 32 byte format. + */ + if (!IAVF_RXDID_ALLOWED(adapter)) + return VIRTCHNL_RXDID_1_32B_BASE; + + /* Rx timestamping requires the use of flexible NIC descriptors */ + if (iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP)) { + if (rxdids & BIT(VIRTCHNL_RXDID_2_FLEX_SQ_NIC)) + return VIRTCHNL_RXDID_2_FLEX_SQ_NIC; + + pci_warn(adapter->pdev, + "Unable to negotiate flexible descriptor format\n"); + } + + /* Warn if the PF does not list support for the default legacy + * descriptor format. This shouldn't happen, as this is the format + * used if VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC is not supported. It is + * likely caused by a bug in the PF implementation failing to indicate + * support for the format. + */ + if (!(rxdids & VIRTCHNL_RXDID_1_32B_BASE_M)) + netdev_warn(adapter->netdev, "PF does not list support for default Rx descriptor format\n"); + + return VIRTCHNL_RXDID_1_32B_BASE; +} + +/** * iavf_configure_rx - Configure Receive Unit after Reset * @adapter: board private structure * @@ -714,39 +760,13 @@ static void iavf_configure_tx(struct iavf_adapter *adapter) **/ static void iavf_configure_rx(struct iavf_adapter *adapter) { - unsigned int rx_buf_len = IAVF_RXBUFFER_2048; struct iavf_hw *hw = &adapter->hw; - int i; - /* Legacy Rx will always default to a 2048 buffer size. */ -#if (PAGE_SIZE < 8192) - if (!(adapter->flags & IAVF_FLAG_LEGACY_RX)) { - struct net_device *netdev = adapter->netdev; + adapter->rxdid = iavf_select_rx_desc_format(adapter); - /* For jumbo frames on systems with 4K pages we have to use - * an order 1 page, so we might as well increase the size - * of our Rx buffer to make better use of the available space - */ - rx_buf_len = IAVF_RXBUFFER_3072; - - /* We use a 1536 buffer size for configurations with - * standard Ethernet mtu. On x86 this gives us enough room - * for shared info and 192 bytes of padding. - */ - if (!IAVF_2K_TOO_SMALL_WITH_PADDING && - (netdev->mtu <= ETH_DATA_LEN)) - rx_buf_len = IAVF_RXBUFFER_1536 - NET_IP_ALIGN; - } -#endif - - for (i = 0; i < adapter->num_active_queues; i++) { + for (u32 i = 0; i < adapter->num_active_queues; i++) { adapter->rx_rings[i].tail = hw->hw_addr + IAVF_QRX_TAIL1(i); - adapter->rx_rings[i].rx_buf_len = rx_buf_len; - - if (adapter->flags & IAVF_FLAG_LEGACY_RX) - clear_ring_build_skb_enabled(&adapter->rx_rings[i]); - else - set_ring_build_skb_enabled(&adapter->rx_rings[i]); + adapter->rx_rings[i].rxdid = adapter->rxdid; } } @@ -800,6 +820,11 @@ iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter, f->state = IAVF_VLAN_ADD; adapter->num_vlan_filters++; iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_VLAN_FILTER); + } else if (f->state == IAVF_VLAN_REMOVE) { + /* IAVF_VLAN_REMOVE means that VLAN wasn't yet removed. + * We can safely only change the state here. + */ + f->state = IAVF_VLAN_ACTIVE; } clearout: @@ -820,8 +845,18 @@ 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; - iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_VLAN_FILTER); + /* IAVF_ADD_VLAN means that VLAN wasn't even added yet. + * Remove it from the list. + */ + if (f->state == IAVF_VLAN_ADD) { + list_del(&f->list); + kfree(f); + adapter->num_vlan_filters--; + } else { + f->state = IAVF_VLAN_REMOVE; + iavf_schedule_aq_request(adapter, + IAVF_FLAG_AQ_DEL_VLAN_FILTER); + } } spin_unlock_bh(&adapter->mac_vlan_list_lock); @@ -1207,7 +1242,7 @@ static void iavf_napi_enable_all(struct iavf_adapter *adapter) q_vector = &adapter->q_vectors[q_idx]; napi = &q_vector->napi; - napi_enable(napi); + napi_enable_locked(napi); } } @@ -1223,7 +1258,7 @@ static void iavf_napi_disable_all(struct iavf_adapter *adapter) for (q_idx = 0; q_idx < q_vectors; q_idx++) { q_vector = &adapter->q_vectors[q_idx]; - napi_disable(&q_vector->napi); + napi_disable_locked(&q_vector->napi); } } @@ -1615,7 +1650,6 @@ static int iavf_alloc_queues(struct iavf_adapter *adapter) rx_ring = &adapter->rx_rings[i]; rx_ring->queue_index = i; rx_ring->netdev = adapter->netdev; - rx_ring->dev = &adapter->pdev->dev; rx_ring->count = adapter->rx_desc_count; rx_ring->itr_setting = IAVF_ITR_RX_DEF; } @@ -1828,8 +1862,8 @@ static int iavf_alloc_q_vectors(struct iavf_adapter *adapter) q_vector->v_idx = q_idx; q_vector->reg_idx = q_idx; cpumask_copy(&q_vector->affinity_mask, cpu_possible_mask); - netif_napi_add(adapter->netdev, &q_vector->napi, - iavf_napi_poll); + netif_napi_add_locked(adapter->netdev, &q_vector->napi, + iavf_napi_poll); } return 0; @@ -1855,7 +1889,7 @@ static void iavf_free_q_vectors(struct iavf_adapter *adapter) for (q_idx = 0; q_idx < num_q_vectors; q_idx++) { struct iavf_q_vector *q_vector = &adapter->q_vectors[q_idx]; - netif_napi_del(&q_vector->napi); + netif_napi_del_locked(&q_vector->napi); } kfree(adapter->q_vectors); adapter->q_vectors = NULL; @@ -1996,12 +2030,16 @@ err: static void iavf_finish_config(struct work_struct *work) { struct iavf_adapter *adapter; + bool locks_released = false; int pairs, err; adapter = container_of(work, struct iavf_adapter, finish_config); - /* Always take RTNL first to prevent circular lock dependency */ + /* Always take RTNL first to prevent circular lock dependency; + * The dev->lock is needed to update the queue number + */ rtnl_lock(); + netdev_lock(adapter->netdev); mutex_lock(&adapter->crit_lock); if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES) && @@ -2013,26 +2051,34 @@ static void iavf_finish_config(struct work_struct *work) switch (adapter->state) { case __IAVF_DOWN: + /* Set the real number of queues when reset occurs while + * state == __IAVF_DOWN + */ + pairs = adapter->num_active_queues; + netif_set_real_num_rx_queues(adapter->netdev, pairs); + netif_set_real_num_tx_queues(adapter->netdev, pairs); + if (adapter->netdev->reg_state != NETREG_REGISTERED) { + mutex_unlock(&adapter->crit_lock); + netdev_unlock(adapter->netdev); + locks_released = true; err = register_netdevice(adapter->netdev); if (err) { dev_err(&adapter->pdev->dev, "Unable to register netdev (%d)\n", err); /* go back and try again.*/ + mutex_lock(&adapter->crit_lock); iavf_free_rss(adapter); iavf_free_misc_irq(adapter); iavf_reset_interrupt_capability(adapter); iavf_change_state(adapter, __IAVF_INIT_CONFIG_ADAPTER); + mutex_unlock(&adapter->crit_lock); goto out; } } - - /* Set the real number of queues when reset occurs while - * state == __IAVF_DOWN - */ - fallthrough; + break; case __IAVF_RUNNING: pairs = adapter->num_active_queues; netif_set_real_num_rx_queues(adapter->netdev, pairs); @@ -2044,7 +2090,10 @@ static void iavf_finish_config(struct work_struct *work) } out: - mutex_unlock(&adapter->crit_lock); + if (!locks_released) { + mutex_unlock(&adapter->crit_lock); + netdev_unlock(adapter->netdev); + } rtnl_unlock(); } @@ -2073,6 +2122,10 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter) return iavf_send_vf_config_msg(adapter); if (adapter->aq_required & IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS) return iavf_send_vf_offload_vlan_v2_msg(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS) + return iavf_send_vf_supported_rxdids_msg(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_GET_PTP_CAPS) + return iavf_send_vf_ptp_caps_msg(adapter); if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_QUEUES) { iavf_disable_queues(adapter); return 0; @@ -2113,6 +2166,21 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter) return 0; } + if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW) { + iavf_cfg_queues_bw(adapter); + return 0; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_GET_QOS_CAPS) { + iavf_get_qos_caps(adapter); + return 0; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_CFG_QUEUES_QUANTA_SIZE) { + iavf_cfg_queues_quanta_size(adapter); + return 0; + } + if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_QUEUES) { iavf_configure_queues(adapter); return 0; @@ -2222,7 +2290,10 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter) iavf_enable_vlan_insertion_v2(adapter, ETH_P_8021AD); return 0; } - + if (adapter->aq_required & IAVF_FLAG_AQ_SEND_PTP_CMD) { + iavf_virtchnl_send_ptp_cmd(adapter); + return IAVF_SUCCESS; + } if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_STATS) { iavf_request_stats(adapter); return 0; @@ -2587,6 +2658,112 @@ err: } /** + * iavf_init_send_supported_rxdids - part of querying for supported RXDID + * formats + * @adapter: board private structure + * + * Function processes send of the request for supported RXDIDs to the PF. + * Must clear IAVF_EXTENDED_CAP_RECV_RXDID if the message is not sent, e.g. + * due to the PF not negotiating VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC. + */ +static void iavf_init_send_supported_rxdids(struct iavf_adapter *adapter) +{ + int ret; + + ret = iavf_send_vf_supported_rxdids_msg(adapter); + if (ret == -EOPNOTSUPP) { + /* PF does not support VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC. In this + * case, we did not send the capability exchange message and + * do not expect a response. + */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_RXDID; + } + + /* We sent the message, so move on to the next step */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_SEND_RXDID; +} + +/** + * iavf_init_recv_supported_rxdids - part of querying for supported RXDID + * formats + * @adapter: board private structure + * + * Function processes receipt of the supported RXDIDs message from the PF. + **/ +static void iavf_init_recv_supported_rxdids(struct iavf_adapter *adapter) +{ + int ret; + + memset(&adapter->supp_rxdids, 0, sizeof(adapter->supp_rxdids)); + + ret = iavf_get_vf_supported_rxdids(adapter); + if (ret) + goto err; + + /* We've processed the PF response to the + * VIRTCHNL_OP_GET_SUPPORTED_RXDIDS message we sent previously. + */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_RXDID; + return; + +err: + /* We didn't receive a reply. Make sure we try sending again when + * __IAVF_INIT_FAILED attempts to recover. + */ + adapter->extended_caps |= IAVF_EXTENDED_CAP_SEND_RXDID; + iavf_change_state(adapter, __IAVF_INIT_FAILED); +} + +/** + * iavf_init_send_ptp_caps - part of querying for extended PTP capabilities + * @adapter: board private structure + * + * Function processes send of the request for 1588 PTP capabilities to the PF. + * Must clear IAVF_EXTENDED_CAP_SEND_PTP if the message is not sent, e.g. + * due to the PF not negotiating VIRTCHNL_VF_PTP_CAP + */ +static void iavf_init_send_ptp_caps(struct iavf_adapter *adapter) +{ + if (iavf_send_vf_ptp_caps_msg(adapter) == -EOPNOTSUPP) { + /* PF does not support VIRTCHNL_VF_PTP_CAP. In this case, we + * did not send the capability exchange message and do not + * expect a response. + */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_PTP; + } + + /* We sent the message, so move on to the next step */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_SEND_PTP; +} + +/** + * iavf_init_recv_ptp_caps - part of querying for supported PTP capabilities + * @adapter: board private structure + * + * Function processes receipt of the PTP capabilities supported on this VF. + **/ +static void iavf_init_recv_ptp_caps(struct iavf_adapter *adapter) +{ + memset(&adapter->ptp.hw_caps, 0, sizeof(adapter->ptp.hw_caps)); + + if (iavf_get_vf_ptp_caps(adapter)) + goto err; + + /* We've processed the PF response to the VIRTCHNL_OP_1588_PTP_GET_CAPS + * message we sent previously. + */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_PTP; + return; + +err: + /* We didn't receive a reply. Make sure we try sending again when + * __IAVF_INIT_FAILED attempts to recover. + */ + adapter->extended_caps |= IAVF_EXTENDED_CAP_SEND_PTP; + iavf_change_state(adapter, __IAVF_INIT_FAILED); +} + +/** * iavf_init_process_extended_caps - Part of driver startup * @adapter: board private structure * @@ -2610,6 +2787,24 @@ static void iavf_init_process_extended_caps(struct iavf_adapter *adapter) return; } + /* Process capability exchange for RXDID formats */ + if (adapter->extended_caps & IAVF_EXTENDED_CAP_SEND_RXDID) { + iavf_init_send_supported_rxdids(adapter); + return; + } else if (adapter->extended_caps & IAVF_EXTENDED_CAP_RECV_RXDID) { + iavf_init_recv_supported_rxdids(adapter); + return; + } + + /* Process capability exchange for PTP features */ + if (adapter->extended_caps & IAVF_EXTENDED_CAP_SEND_PTP) { + iavf_init_send_ptp_caps(adapter); + return; + } else if (adapter->extended_caps & IAVF_EXTENDED_CAP_RECV_PTP) { + iavf_init_recv_ptp_caps(adapter); + return; + } + /* When we reach here, no further extended capabilities exchanges are * necessary, so we finally transition into __IAVF_INIT_CONFIG_ADAPTER */ @@ -2642,9 +2837,8 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) iavf_set_ethtool_ops(netdev); netdev->watchdog_timeo = 5 * HZ; - /* MTU range: 68 - 9710 */ netdev->min_mtu = ETH_MIN_MTU; - netdev->max_mtu = IAVF_MAX_RXBUFFER - IAVF_PACKET_HDR_PAD; + netdev->max_mtu = LIBIE_MAX_MTU; if (!is_valid_ether_addr(adapter->hw.mac.addr)) { dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n", @@ -2699,6 +2893,12 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) /* request initial VLAN offload settings */ iavf_set_vlan_offload_features(adapter, 0, netdev->features); + if (QOS_ALLOWED(adapter)) + adapter->aq_required |= IAVF_FLAG_AQ_GET_QOS_CAPS; + + /* Setup initial PTP configuration */ + iavf_ptp_init(adapter); + iavf_schedule_finish_config(adapter); return; @@ -2720,12 +2920,16 @@ static void iavf_watchdog_task(struct work_struct *work) struct iavf_adapter *adapter = container_of(work, struct iavf_adapter, watchdog_task.work); + struct net_device *netdev = adapter->netdev; struct iavf_hw *hw = &adapter->hw; u32 reg_val; + netdev_lock(netdev); if (!mutex_trylock(&adapter->crit_lock)) { - if (adapter->state == __IAVF_REMOVE) + if (adapter->state == __IAVF_REMOVE) { + netdev_unlock(netdev); return; + } goto restart_watchdog; } @@ -2737,30 +2941,35 @@ static void iavf_watchdog_task(struct work_struct *work) case __IAVF_STARTUP: iavf_startup(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(30)); return; case __IAVF_INIT_VERSION_CHECK: iavf_init_version_check(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(30)); return; case __IAVF_INIT_GET_RESOURCES: iavf_init_get_resources(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(1)); return; case __IAVF_INIT_EXTENDED_CAPS: iavf_init_process_extended_caps(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(1)); return; case __IAVF_INIT_CONFIG_ADAPTER: iavf_init_config_adapter(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(1)); return; @@ -2772,6 +2981,7 @@ static void iavf_watchdog_task(struct work_struct *work) * as it can loop forever */ mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return; } if (++adapter->aq_wait_count > IAVF_AQ_MAX_ERR) { @@ -2780,6 +2990,7 @@ static void iavf_watchdog_task(struct work_struct *work) adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED; iavf_shutdown_adminq(hw); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, (5 * HZ)); return; @@ -2787,6 +2998,7 @@ static void iavf_watchdog_task(struct work_struct *work) /* Try again from failed step*/ iavf_change_state(adapter, adapter->last_state); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, HZ); return; case __IAVF_COMM_FAILED: @@ -2799,6 +3011,7 @@ static void iavf_watchdog_task(struct work_struct *work) iavf_change_state(adapter, __IAVF_INIT_FAILED); adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return; } reg_val = rd32(hw, IAVF_VFGEN_RSTAT) & @@ -2818,12 +3031,14 @@ static void iavf_watchdog_task(struct work_struct *work) adapter->aq_required = 0; adapter->current_op = VIRTCHNL_OP_UNKNOWN; mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(10)); return; case __IAVF_RESETTING: mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, HZ * 2); return; @@ -2854,6 +3069,7 @@ static void iavf_watchdog_task(struct work_struct *work) case __IAVF_REMOVE: default: mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return; } @@ -2865,6 +3081,7 @@ static void iavf_watchdog_task(struct work_struct *work) dev_err(&adapter->pdev->dev, "Hardware reset detected\n"); iavf_schedule_reset(adapter, IAVF_FLAG_RESET_PENDING); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, HZ * 2); return; @@ -2872,6 +3089,7 @@ static void iavf_watchdog_task(struct work_struct *work) mutex_unlock(&adapter->crit_lock); restart_watchdog: + netdev_unlock(netdev); if (adapter->state >= __IAVF_DOWN) queue_work(adapter->wq, &adapter->adminq_task); if (adapter->aq_required) @@ -2948,6 +3166,30 @@ static void iavf_disable_vf(struct iavf_adapter *adapter) } /** + * iavf_reconfig_qs_bw - Call-back task to handle hardware reset + * @adapter: board private structure + * + * After a reset, the shaper parameters of queues need to be replayed again. + * Since the net_shaper object inside TX rings persists across reset, + * set the update flag for all queues so that the virtchnl message is triggered + * for all queues. + **/ +static void iavf_reconfig_qs_bw(struct iavf_adapter *adapter) +{ + int i, num = 0; + + for (i = 0; i < adapter->num_active_queues; i++) + if (adapter->tx_rings[i].q_shaper.bw_min || + adapter->tx_rings[i].q_shaper.bw_max) { + adapter->tx_rings[i].q_shaper_update = true; + num++; + } + + if (num) + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW; +} + +/** * iavf_reset_task - Call-back task to handle hardware reset * @work: pointer to work_struct * @@ -2973,10 +3215,12 @@ static void iavf_reset_task(struct work_struct *work) /* When device is being removed it doesn't make sense to run the reset * task, just return in such a case. */ + netdev_lock(netdev); if (!mutex_trylock(&adapter->crit_lock)) { if (adapter->state != __IAVF_REMOVE) queue_work(adapter->wq, &adapter->reset_task); + netdev_unlock(netdev); return; } @@ -3024,6 +3268,7 @@ static void iavf_reset_task(struct work_struct *work) reg_val); iavf_disable_vf(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return; /* Do not attempt to reinit. It's dead, Jim. */ } @@ -3079,15 +3324,18 @@ continue_reset: } adapter->aq_required |= IAVF_FLAG_AQ_GET_CONFIG; - /* always set since VIRTCHNL_OP_GET_VF_RESOURCES has not been - * sent/received yet, so VLAN_V2_ALLOWED() cannot is not reliable here, - * however the VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS won't be sent until - * VIRTCHNL_OP_GET_VF_RESOURCES and VIRTCHNL_VF_OFFLOAD_VLAN_V2 have - * been successfully sent and negotiated - */ - adapter->aq_required |= IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS; adapter->aq_required |= IAVF_FLAG_AQ_MAP_VECTORS; + /* Certain capabilities require an extended negotiation process using + * extra messages that must be processed after getting the VF + * configuration. The related checks such as VLAN_V2_ALLOWED() are not + * reliable here, since the configuration has not yet been negotiated. + * + * Always set these flags, since them related VIRTCHNL messages won't + * be sent until after VIRTCHNL_OP_GET_VF_RESOURCES. + */ + adapter->aq_required |= IAVF_FLAG_AQ_EXTENDED_CAPS; + spin_lock_bh(&adapter->mac_vlan_list_lock); /* Delete filter for the current MAC address, it could have @@ -3153,6 +3401,8 @@ continue_reset: iavf_up_complete(adapter); iavf_irq_enable(adapter, true); + + iavf_reconfig_qs_bw(adapter); } else { iavf_change_state(adapter, __IAVF_DOWN); wake_up(&adapter->down_waitqueue); @@ -3162,6 +3412,7 @@ continue_reset: wake_up(&adapter->reset_waitqueue); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return; reset_err: @@ -3172,6 +3423,7 @@ reset_err: iavf_disable_vf(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); } @@ -3785,6 +4037,10 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter, flow_rule_match_control(rule, &match); addr_type = match.key->addr_type; + + if (flow_rule_has_control_flags(match.mask->flags, + f->common.extack)) + return -EOPNOTSUPP; } if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { @@ -4038,7 +4294,7 @@ static int iavf_delete_clsflower(struct iavf_adapter *adapter, /** * iavf_setup_tc_cls_flower - flower classifier offloads - * @adapter: board private structure + * @adapter: pointer to iavf adapter structure * @cls_flower: pointer to flow_cls_offload struct with flow info */ static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter, @@ -4057,6 +4313,154 @@ static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter, } /** + * iavf_add_cls_u32 - Add U32 classifier offloads + * @adapter: pointer to iavf adapter structure + * @cls_u32: pointer to tc_cls_u32_offload struct with flow info + * + * Return: 0 on success or negative errno on failure. + */ +static int iavf_add_cls_u32(struct iavf_adapter *adapter, + struct tc_cls_u32_offload *cls_u32) +{ + struct netlink_ext_ack *extack = cls_u32->common.extack; + struct virtchnl_fdir_rule *rule_cfg; + struct virtchnl_filter_action *vact; + struct virtchnl_proto_hdrs *hdrs; + struct ethhdr *spec_h, *mask_h; + const struct tc_action *act; + struct iavf_fdir_fltr *fltr; + struct tcf_exts *exts; + unsigned int q_index; + int i, status = 0; + int off_base = 0; + + if (cls_u32->knode.link_handle) { + NL_SET_ERR_MSG_MOD(extack, "Linking not supported"); + return -EOPNOTSUPP; + } + + fltr = kzalloc(sizeof(*fltr), GFP_KERNEL); + if (!fltr) + return -ENOMEM; + + rule_cfg = &fltr->vc_add_msg.rule_cfg; + hdrs = &rule_cfg->proto_hdrs; + hdrs->count = 0; + + /* The parser lib at the PF expects the packet starting with MAC hdr */ + switch (ntohs(cls_u32->common.protocol)) { + case ETH_P_802_3: + break; + case ETH_P_IP: + spec_h = (struct ethhdr *)hdrs->raw.spec; + mask_h = (struct ethhdr *)hdrs->raw.mask; + spec_h->h_proto = htons(ETH_P_IP); + mask_h->h_proto = htons(0xFFFF); + off_base += ETH_HLEN; + break; + default: + NL_SET_ERR_MSG_MOD(extack, "Only 802_3 and ip filter protocols are supported"); + status = -EOPNOTSUPP; + goto free_alloc; + } + + for (i = 0; i < cls_u32->knode.sel->nkeys; i++) { + __be32 val, mask; + int off; + + off = off_base + cls_u32->knode.sel->keys[i].off; + val = cls_u32->knode.sel->keys[i].val; + mask = cls_u32->knode.sel->keys[i].mask; + + if (off >= sizeof(hdrs->raw.spec)) { + NL_SET_ERR_MSG_MOD(extack, "Input exceeds maximum allowed."); + status = -EINVAL; + goto free_alloc; + } + + memcpy(&hdrs->raw.spec[off], &val, sizeof(val)); + memcpy(&hdrs->raw.mask[off], &mask, sizeof(mask)); + hdrs->raw.pkt_len = off + sizeof(val); + } + + /* Only one action is allowed */ + rule_cfg->action_set.count = 1; + vact = &rule_cfg->action_set.actions[0]; + exts = cls_u32->knode.exts; + + tcf_exts_for_each_action(i, act, exts) { + /* FDIR queue */ + if (is_tcf_skbedit_rx_queue_mapping(act)) { + q_index = tcf_skbedit_rx_queue_mapping(act); + if (q_index >= adapter->num_active_queues) { + status = -EINVAL; + goto free_alloc; + } + + vact->type = VIRTCHNL_ACTION_QUEUE; + vact->act_conf.queue.index = q_index; + break; + } + + /* Drop */ + if (is_tcf_gact_shot(act)) { + vact->type = VIRTCHNL_ACTION_DROP; + break; + } + + /* Unsupported action */ + NL_SET_ERR_MSG_MOD(extack, "Unsupported action."); + status = -EOPNOTSUPP; + goto free_alloc; + } + + fltr->vc_add_msg.vsi_id = adapter->vsi.id; + fltr->cls_u32_handle = cls_u32->knode.handle; + return iavf_fdir_add_fltr(adapter, fltr); + +free_alloc: + kfree(fltr); + return status; +} + +/** + * iavf_del_cls_u32 - Delete U32 classifier offloads + * @adapter: pointer to iavf adapter structure + * @cls_u32: pointer to tc_cls_u32_offload struct with flow info + * + * Return: 0 on success or negative errno on failure. + */ +static int iavf_del_cls_u32(struct iavf_adapter *adapter, + struct tc_cls_u32_offload *cls_u32) +{ + return iavf_fdir_del_fltr(adapter, true, cls_u32->knode.handle); +} + +/** + * iavf_setup_tc_cls_u32 - U32 filter offloads + * @adapter: pointer to iavf adapter structure + * @cls_u32: pointer to tc_cls_u32_offload struct with flow info + * + * Return: 0 on success or negative errno on failure. + */ +static int iavf_setup_tc_cls_u32(struct iavf_adapter *adapter, + struct tc_cls_u32_offload *cls_u32) +{ + if (!TC_U32_SUPPORT(adapter) || !FDIR_FLTR_SUPPORT(adapter)) + return -EOPNOTSUPP; + + switch (cls_u32->command) { + case TC_CLSU32_NEW_KNODE: + case TC_CLSU32_REPLACE_KNODE: + return iavf_add_cls_u32(adapter, cls_u32); + case TC_CLSU32_DELETE_KNODE: + return iavf_del_cls_u32(adapter, cls_u32); + default: + return -EOPNOTSUPP; + } +} + +/** * iavf_setup_tc_block_cb - block callback for tc * @type: type of offload * @type_data: offload data @@ -4075,6 +4479,8 @@ static int iavf_setup_tc_block_cb(enum tc_setup_type type, void *type_data, switch (type) { case TC_SETUP_CLSFLOWER: return iavf_setup_tc_cls_flower(cb_priv, type_data); + case TC_SETUP_CLSU32: + return iavf_setup_tc_cls_u32(cb_priv, type_data); default: return -EOPNOTSUPP; } @@ -4155,6 +4561,8 @@ static int iavf_open(struct net_device *netdev) struct iavf_adapter *adapter = netdev_priv(netdev); int err; + netdev_assert_locked(netdev); + if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) { dev_err(&adapter->pdev->dev, "Unable to open device due to PF driver failure.\n"); return -EIO; @@ -4249,6 +4657,8 @@ static int iavf_close(struct net_device *netdev) u64 aq_to_restore; int status; + netdev_assert_locked(netdev); + mutex_lock(&adapter->crit_lock); if (adapter->state <= __IAVF_DOWN_PENDING) { @@ -4286,6 +4696,7 @@ static int iavf_close(struct net_device *netdev) iavf_free_traffic_irqs(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); /* We explicitly don't free resources here because the hardware is * still active and can DMA into memory. Resources are cleared in @@ -4304,6 +4715,7 @@ static int iavf_close(struct net_device *netdev) if (!status) netdev_warn(netdev, "Device resources not yet released\n"); + netdev_lock(netdev); mutex_lock(&adapter->crit_lock); adapter->aq_required |= aq_to_restore; mutex_unlock(&adapter->crit_lock); @@ -4324,7 +4736,7 @@ 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; + WRITE_ONCE(netdev->mtu, new_mtu); if (netif_running(netdev)) { iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); @@ -4357,8 +4769,8 @@ static void iavf_disable_fdir(struct iavf_adapter *adapter) fdir->state == IAVF_FDIR_FLTR_INACTIVE) { /* Delete filters not registered in PF */ list_del(&fdir->list); + iavf_dec_fdir_active_fltr(adapter, fdir); 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) { @@ -4768,6 +5180,117 @@ static netdev_features_t iavf_fix_features(struct net_device *netdev, return iavf_fix_strip_features(adapter, features); } +static int iavf_hwstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *config) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + *config = adapter->ptp.hwtstamp_config; + + return 0; +} + +static int iavf_hwstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + return iavf_ptp_set_ts_config(adapter, config, extack); +} + +static int +iavf_verify_shaper(struct net_shaper_binding *binding, + const struct net_shaper *shaper, + struct netlink_ext_ack *extack) +{ + struct iavf_adapter *adapter = netdev_priv(binding->netdev); + u64 vf_max; + + if (shaper->handle.scope == NET_SHAPER_SCOPE_QUEUE) { + vf_max = adapter->qos_caps->cap[0].shaper.peak; + if (vf_max && shaper->bw_max > vf_max) { + NL_SET_ERR_MSG_FMT(extack, "Max rate (%llu) of queue %d can't exceed max TX rate of VF (%llu kbps)", + shaper->bw_max, shaper->handle.id, + vf_max); + return -EINVAL; + } + } + return 0; +} + +static int +iavf_shaper_set(struct net_shaper_binding *binding, + const struct net_shaper *shaper, + struct netlink_ext_ack *extack) +{ + struct iavf_adapter *adapter = netdev_priv(binding->netdev); + const struct net_shaper_handle *handle = &shaper->handle; + struct iavf_ring *tx_ring; + int ret = 0; + + mutex_lock(&adapter->crit_lock); + if (handle->id >= adapter->num_active_queues) + goto unlock; + + ret = iavf_verify_shaper(binding, shaper, extack); + if (ret) + goto unlock; + + tx_ring = &adapter->tx_rings[handle->id]; + + tx_ring->q_shaper.bw_min = div_u64(shaper->bw_min, 1000); + tx_ring->q_shaper.bw_max = div_u64(shaper->bw_max, 1000); + tx_ring->q_shaper_update = true; + + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW; + +unlock: + mutex_unlock(&adapter->crit_lock); + return ret; +} + +static int iavf_shaper_del(struct net_shaper_binding *binding, + const struct net_shaper_handle *handle, + struct netlink_ext_ack *extack) +{ + struct iavf_adapter *adapter = netdev_priv(binding->netdev); + struct iavf_ring *tx_ring; + + mutex_lock(&adapter->crit_lock); + if (handle->id >= adapter->num_active_queues) + goto unlock; + + tx_ring = &adapter->tx_rings[handle->id]; + tx_ring->q_shaper.bw_min = 0; + tx_ring->q_shaper.bw_max = 0; + tx_ring->q_shaper_update = true; + + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW; + +unlock: + mutex_unlock(&adapter->crit_lock); + return 0; +} + +static void iavf_shaper_cap(struct net_shaper_binding *binding, + enum net_shaper_scope scope, + unsigned long *flags) +{ + if (scope != NET_SHAPER_SCOPE_QUEUE) + return; + + *flags = BIT(NET_SHAPER_A_CAPS_SUPPORT_BW_MIN) | + BIT(NET_SHAPER_A_CAPS_SUPPORT_BW_MAX) | + BIT(NET_SHAPER_A_CAPS_SUPPORT_METRIC_BPS); +} + +static const struct net_shaper_ops iavf_shaper_ops = { + .set = iavf_shaper_set, + .delete = iavf_shaper_del, + .capabilities = iavf_shaper_cap, +}; + static const struct net_device_ops iavf_netdev_ops = { .ndo_open = iavf_open, .ndo_stop = iavf_close, @@ -4783,6 +5306,9 @@ static const struct net_device_ops iavf_netdev_ops = { .ndo_fix_features = iavf_fix_features, .ndo_set_features = iavf_set_features, .ndo_setup_tc = iavf_setup_tc, + .net_shaper_ops = &iavf_shaper_ops, + .ndo_hwtstamp_get = iavf_hwstamp_get, + .ndo_hwtstamp_set = iavf_hwstamp_set, }; /** @@ -4868,9 +5394,11 @@ int iavf_process_config(struct iavf_adapter *adapter) /* get HW VLAN features that can be toggled */ hw_vlan_features = iavf_get_netdev_vlan_hw_features(adapter); - /* Enable cloud filter if ADQ is supported */ - if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) + /* Enable HW TC offload if ADQ or tc U32 is supported */ + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ || + TC_U32_SUPPORT(adapter)) hw_features |= NETIF_F_HW_TC; + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_USO) hw_features |= NETIF_F_GSO_UDP_L4; @@ -4927,7 +5455,7 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct net_device *netdev; struct iavf_adapter *adapter = NULL; struct iavf_hw *hw = NULL; - int err; + int err, len; err = pci_enable_device(pdev); if (err) @@ -4995,6 +5523,13 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->bus.func = PCI_FUNC(pdev->devfn); hw->bus.bus_id = pdev->bus->number; + len = struct_size(adapter->qos_caps, cap, IAVF_MAX_QOS_TC_NUM); + adapter->qos_caps = kzalloc(len, GFP_KERNEL); + if (!adapter->qos_caps) { + err = -ENOMEM; + goto err_alloc_qos_cap; + } + /* set up the locks for the AQ, do this only once in probe * and destroy them only once in remove */ @@ -5028,11 +5563,17 @@ 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); + INIT_LIST_HEAD(&adapter->ptp.aq_cmds); + init_waitqueue_head(&adapter->ptp.phc_time_waitqueue); + mutex_init(&adapter->ptp.aq_cmd_lock); + 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_alloc_qos_cap: + iounmap(hw->hw_addr); err_ioremap: destroy_workqueue(adapter->wq); err_alloc_wq: @@ -5051,13 +5592,14 @@ err_dma: * * Called when the system (VM) is entering sleep/suspend. **/ -static int __maybe_unused iavf_suspend(struct device *dev_d) +static int iavf_suspend(struct device *dev_d) { struct net_device *netdev = dev_get_drvdata(dev_d); struct iavf_adapter *adapter = netdev_priv(netdev); netif_device_detach(netdev); + netdev_lock(netdev); mutex_lock(&adapter->crit_lock); if (netif_running(netdev)) { @@ -5069,6 +5611,7 @@ static int __maybe_unused iavf_suspend(struct device *dev_d) iavf_reset_interrupt_capability(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return 0; } @@ -5079,7 +5622,7 @@ static int __maybe_unused iavf_suspend(struct device *dev_d) * * Called when the system (VM) is resumed from sleep/suspend. **/ -static int __maybe_unused iavf_resume(struct device *dev_d) +static int iavf_resume(struct device *dev_d) { struct pci_dev *pdev = to_pci_dev(dev_d); struct iavf_adapter *adapter; @@ -5167,6 +5710,7 @@ static void iavf_remove(struct pci_dev *pdev) if (netdev->reg_state == NETREG_REGISTERED) unregister_netdev(netdev); + netdev_lock(netdev); mutex_lock(&adapter->crit_lock); dev_info(&adapter->pdev->dev, "Removing device\n"); iavf_change_state(adapter, __IAVF_REMOVE); @@ -5179,6 +5723,8 @@ static void iavf_remove(struct pci_dev *pdev) msleep(50); } + iavf_ptp_release(adapter); + iavf_misc_irq_disable(adapter); /* Shut down all the garbage mashers on the detention level */ cancel_work_sync(&adapter->reset_task); @@ -5203,6 +5749,7 @@ static void iavf_remove(struct pci_dev *pdev) mutex_destroy(&hw->aq.asq_mutex); mutex_unlock(&adapter->crit_lock); mutex_destroy(&adapter->crit_lock); + netdev_unlock(netdev); iounmap(hw->hw_addr); pci_release_regions(pdev); @@ -5266,14 +5813,14 @@ static void iavf_shutdown(struct pci_dev *pdev) pci_set_power_state(pdev, PCI_D3hot); } -static SIMPLE_DEV_PM_OPS(iavf_pm_ops, iavf_suspend, iavf_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(iavf_pm_ops, iavf_suspend, iavf_resume); static struct pci_driver iavf_driver = { .name = iavf_driver_name, .id_table = iavf_pci_tbl, .probe = iavf_probe, .remove = iavf_remove, - .driver.pm = &iavf_pm_ops, + .driver.pm = pm_sleep_ptr(&iavf_pm_ops), .shutdown = iavf_shutdown, }; diff --git a/drivers/net/ethernet/intel/iavf/iavf_prototype.h b/drivers/net/ethernet/intel/iavf/iavf_prototype.h index 4a48e6171405..cac9d1a35a52 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_prototype.h +++ b/drivers/net/ethernet/intel/iavf/iavf_prototype.h @@ -18,7 +18,6 @@ /* adminq functions */ enum iavf_status iavf_init_adminq(struct iavf_hw *hw); enum iavf_status iavf_shutdown_adminq(struct iavf_hw *hw); -void iavf_adminq_init_ring_data(struct iavf_hw *hw); enum iavf_status iavf_clean_arq_element(struct iavf_hw *hw, struct iavf_arq_event_info *e, u16 *events_pending); @@ -33,8 +32,6 @@ bool iavf_asq_done(struct iavf_hw *hw); void iavf_debug_aq(struct iavf_hw *hw, enum iavf_debug_mask mask, void *desc, void *buffer, u16 buf_len); -void iavf_idle_aq(struct iavf_hw *hw); -void iavf_resume_aq(struct iavf_hw *hw); bool iavf_check_asq_alive(struct iavf_hw *hw); enum iavf_status iavf_aq_queue_shutdown(struct iavf_hw *hw, bool unloading); const char *iavf_aq_str(struct iavf_hw *hw, enum iavf_admin_queue_err aq_err); @@ -45,13 +42,6 @@ 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); -extern struct iavf_rx_ptype_decoded iavf_ptype_lookup[]; - -static inline struct iavf_rx_ptype_decoded decode_rx_desc_ptype(u8 ptype) -{ - return iavf_ptype_lookup[ptype]; -} - void iavf_vf_parse_hw_config(struct iavf_hw *hw, struct virtchnl_vf_resource *msg); enum iavf_status iavf_aq_send_msg_to_pf(struct iavf_hw *hw, diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.c b/drivers/net/ethernet/intel/iavf/iavf_ptp.c new file mode 100644 index 000000000000..b4d5eda2e84f --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.c @@ -0,0 +1,485 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2024 Intel Corporation. */ + +#include "iavf.h" +#include "iavf_ptp.h" + +#define iavf_clock_to_adapter(info) \ + container_of_const(info, struct iavf_adapter, ptp.info) + +/** + * iavf_ptp_disable_rx_tstamp - Disable timestamping in Rx rings + * @adapter: private adapter structure + * + * Disable timestamp reporting for all Rx rings. + */ +static void iavf_ptp_disable_rx_tstamp(struct iavf_adapter *adapter) +{ + for (u32 i = 0; i < adapter->num_active_queues; i++) + adapter->rx_rings[i].flags &= ~IAVF_TXRX_FLAGS_HW_TSTAMP; +} + +/** + * iavf_ptp_enable_rx_tstamp - Enable timestamping in Rx rings + * @adapter: private adapter structure + * + * Enable timestamp reporting for all Rx rings. + */ +static void iavf_ptp_enable_rx_tstamp(struct iavf_adapter *adapter) +{ + for (u32 i = 0; i < adapter->num_active_queues; i++) + adapter->rx_rings[i].flags |= IAVF_TXRX_FLAGS_HW_TSTAMP; +} + +/** + * iavf_ptp_set_timestamp_mode - Set device timestamping mode + * @adapter: private adapter structure + * @config: pointer to kernel_hwtstamp_config + * + * Set the timestamping mode requested from the userspace. + * + * Note: this function always translates Rx timestamp requests for any packet + * category into HWTSTAMP_FILTER_ALL. + * + * Return: 0 on success, negative error code otherwise. + */ +static int iavf_ptp_set_timestamp_mode(struct iavf_adapter *adapter, + struct kernel_hwtstamp_config *config) +{ + /* Reserved for future extensions. */ + if (config->flags) + return -EINVAL; + + switch (config->tx_type) { + case HWTSTAMP_TX_OFF: + break; + case HWTSTAMP_TX_ON: + return -EOPNOTSUPP; + default: + return -ERANGE; + } + + if (config->rx_filter == HWTSTAMP_FILTER_NONE) { + iavf_ptp_disable_rx_tstamp(adapter); + return 0; + } else if (config->rx_filter > HWTSTAMP_FILTER_NTP_ALL) { + return -ERANGE; + } else if (!(iavf_ptp_cap_supported(adapter, + VIRTCHNL_1588_PTP_CAP_RX_TSTAMP))) { + return -EOPNOTSUPP; + } + + config->rx_filter = HWTSTAMP_FILTER_ALL; + iavf_ptp_enable_rx_tstamp(adapter); + + return 0; +} + +/** + * iavf_ptp_set_ts_config - Set timestamping configuration + * @adapter: private adapter structure + * @config: pointer to kernel_hwtstamp_config structure + * @extack: pointer to netlink_ext_ack structure + * + * Program the requested timestamping configuration to the device. + * + * Return: 0 on success, negative error code otherwise. + */ +int iavf_ptp_set_ts_config(struct iavf_adapter *adapter, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + int err; + + err = iavf_ptp_set_timestamp_mode(adapter, config); + if (err) + return err; + + /* Save successful settings for future reference */ + adapter->ptp.hwtstamp_config = *config; + + return 0; +} + +/** + * iavf_ptp_cap_supported - Check if a PTP capability is supported + * @adapter: private adapter structure + * @cap: the capability bitmask to check + * + * Return: true if every capability set in cap is also set in the enabled + * capabilities reported by the PF, false otherwise. + */ +bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter, u32 cap) +{ + if (!IAVF_PTP_ALLOWED(adapter)) + return false; + + /* Only return true if every bit in cap is set in hw_caps.caps */ + return (adapter->ptp.hw_caps.caps & cap) == cap; +} + +/** + * iavf_allocate_ptp_cmd - Allocate a PTP command message structure + * @v_opcode: the virtchnl opcode + * @msglen: length in bytes of the associated virtchnl structure + * + * Allocates a PTP command message and pre-fills it with the provided message + * length and opcode. + * + * Return: allocated PTP command. + */ +static struct iavf_ptp_aq_cmd *iavf_allocate_ptp_cmd(enum virtchnl_ops v_opcode, + u16 msglen) +{ + struct iavf_ptp_aq_cmd *cmd; + + cmd = kzalloc(struct_size(cmd, msg, msglen), GFP_KERNEL); + if (!cmd) + return NULL; + + cmd->v_opcode = v_opcode; + cmd->msglen = msglen; + + return cmd; +} + +/** + * iavf_queue_ptp_cmd - Queue PTP command for sending over virtchnl + * @adapter: private adapter structure + * @cmd: the command structure to send + * + * Queue the given command structure into the PTP virtchnl command queue tos + * end to the PF. + */ +static void iavf_queue_ptp_cmd(struct iavf_adapter *adapter, + struct iavf_ptp_aq_cmd *cmd) +{ + mutex_lock(&adapter->ptp.aq_cmd_lock); + list_add_tail(&cmd->list, &adapter->ptp.aq_cmds); + mutex_unlock(&adapter->ptp.aq_cmd_lock); + + adapter->aq_required |= IAVF_FLAG_AQ_SEND_PTP_CMD; + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); +} + +/** + * iavf_send_phc_read - Send request to read PHC time + * @adapter: private adapter structure + * + * Send a request to obtain the PTP hardware clock time. This allocates the + * VIRTCHNL_OP_1588_PTP_GET_TIME message and queues it up to send to + * indirectly read the PHC time. + * + * This function does not wait for the reply from the PF. + * + * Return: 0 if success, error code otherwise. + */ +static int iavf_send_phc_read(struct iavf_adapter *adapter) +{ + struct iavf_ptp_aq_cmd *cmd; + + if (!adapter->ptp.clock) + return -EOPNOTSUPP; + + cmd = iavf_allocate_ptp_cmd(VIRTCHNL_OP_1588_PTP_GET_TIME, + sizeof(struct virtchnl_phc_time)); + if (!cmd) + return -ENOMEM; + + iavf_queue_ptp_cmd(adapter, cmd); + + return 0; +} + +/** + * iavf_read_phc_indirect - Indirectly read the PHC time via virtchnl + * @adapter: private adapter structure + * @ts: storage for the timestamp value + * @sts: system timestamp values before and after the read + * + * Used when the device does not have direct register access to the PHC time. + * Indirectly reads the time via the VIRTCHNL_OP_1588_PTP_GET_TIME, and waits + * for the reply from the PF. + * + * Based on some simple measurements using ftrace and phc2sys, this clock + * access method has about a ~110 usec latency even when the system is not + * under load. In order to achieve acceptable results when using phc2sys with + * the indirect clock access method, it is recommended to use more + * conservative proportional and integration constants with the P/I servo. + * + * Return: 0 if success, error code otherwise. + */ +static int iavf_read_phc_indirect(struct iavf_adapter *adapter, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + long ret; + int err; + + adapter->ptp.phc_time_ready = false; + + ptp_read_system_prets(sts); + + err = iavf_send_phc_read(adapter); + if (err) + return err; + + ret = wait_event_interruptible_timeout(adapter->ptp.phc_time_waitqueue, + adapter->ptp.phc_time_ready, + HZ); + + ptp_read_system_postts(sts); + + if (ret < 0) + return ret; + else if (!ret) + return -EBUSY; + + *ts = ns_to_timespec64(adapter->ptp.cached_phc_time); + + return 0; +} + +static int iavf_ptp_gettimex64(struct ptp_clock_info *info, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + struct iavf_adapter *adapter = iavf_clock_to_adapter(info); + + if (!adapter->ptp.clock) + return -EOPNOTSUPP; + + return iavf_read_phc_indirect(adapter, ts, sts); +} + +/** + * iavf_ptp_cache_phc_time - Cache PHC time for performing timestamp extension + * @adapter: private adapter structure + * + * Periodically cache the PHC time in order to allow for timestamp extension. + * This is required because the Tx and Rx timestamps only contain 32bits of + * nanoseconds. Timestamp extension allows calculating the corrected 64bit + * timestamp. This algorithm relies on the cached time being within ~1 second + * of the timestamp. + */ +static void iavf_ptp_cache_phc_time(struct iavf_adapter *adapter) +{ + if (!time_is_before_jiffies(adapter->ptp.cached_phc_updated + HZ)) + return; + + /* The response from virtchnl will store the time into + * cached_phc_time. + */ + iavf_send_phc_read(adapter); +} + +/** + * iavf_ptp_do_aux_work - Perform periodic work required for PTP support + * @info: PTP clock info structure + * + * Handler to take care of periodic work required for PTP operation. This + * includes the following tasks: + * + * 1) updating cached_phc_time + * + * cached_phc_time is used by the Tx and Rx timestamp flows in order to + * perform timestamp extension, by carefully comparing the timestamp + * 32bit nanosecond timestamps and determining the corrected 64bit + * timestamp value to report to userspace. This algorithm only works if + * the cached_phc_time is within ~1 second of the Tx or Rx timestamp + * event. This task periodically reads the PHC time and stores it, to + * ensure that timestamp extension operates correctly. + * + * Returns: time in jiffies until the periodic task should be re-scheduled. + */ +static long iavf_ptp_do_aux_work(struct ptp_clock_info *info) +{ + struct iavf_adapter *adapter = iavf_clock_to_adapter(info); + + iavf_ptp_cache_phc_time(adapter); + + /* Check work about twice a second */ + return msecs_to_jiffies(500); +} + +/** + * iavf_ptp_register_clock - Register a new PTP for userspace + * @adapter: private adapter structure + * + * Allocate and register a new PTP clock device if necessary. + * + * Return: 0 if success, error otherwise. + */ +static int iavf_ptp_register_clock(struct iavf_adapter *adapter) +{ + struct ptp_clock_info *ptp_info = &adapter->ptp.info; + struct device *dev = &adapter->pdev->dev; + struct ptp_clock *clock; + + snprintf(ptp_info->name, sizeof(ptp_info->name), "%s-%s-clk", + KBUILD_MODNAME, dev_name(dev)); + ptp_info->owner = THIS_MODULE; + ptp_info->gettimex64 = iavf_ptp_gettimex64; + ptp_info->do_aux_work = iavf_ptp_do_aux_work; + + clock = ptp_clock_register(ptp_info, dev); + if (IS_ERR(clock)) + return PTR_ERR(clock); + + adapter->ptp.clock = clock; + + dev_dbg(&adapter->pdev->dev, "PTP clock %s registered\n", + adapter->ptp.info.name); + + return 0; +} + +/** + * iavf_ptp_init - Initialize PTP support if capability was negotiated + * @adapter: private adapter structure + * + * Initialize PTP functionality, based on the capabilities that the PF has + * enabled for this VF. + */ +void iavf_ptp_init(struct iavf_adapter *adapter) +{ + int err; + + if (!iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_READ_PHC)) { + pci_notice(adapter->pdev, + "Device does not have PTP clock support\n"); + return; + } + + err = iavf_ptp_register_clock(adapter); + if (err) { + pci_err(adapter->pdev, + "Failed to register PTP clock device (%p)\n", + ERR_PTR(err)); + return; + } + + for (int i = 0; i < adapter->num_active_queues; i++) { + struct iavf_ring *rx_ring = &adapter->rx_rings[i]; + + rx_ring->ptp = &adapter->ptp; + } + + ptp_schedule_worker(adapter->ptp.clock, 0); +} + +/** + * iavf_ptp_release - Disable PTP support + * @adapter: private adapter structure + * + * Release all PTP resources that were previously initialized. + */ +void iavf_ptp_release(struct iavf_adapter *adapter) +{ + struct iavf_ptp_aq_cmd *cmd, *tmp; + + if (!adapter->ptp.clock) + return; + + pci_dbg(adapter->pdev, "removing PTP clock %s\n", + adapter->ptp.info.name); + ptp_clock_unregister(adapter->ptp.clock); + adapter->ptp.clock = NULL; + + /* Cancel any remaining uncompleted PTP clock commands */ + mutex_lock(&adapter->ptp.aq_cmd_lock); + list_for_each_entry_safe(cmd, tmp, &adapter->ptp.aq_cmds, list) { + list_del(&cmd->list); + kfree(cmd); + } + adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD; + mutex_unlock(&adapter->ptp.aq_cmd_lock); + + adapter->ptp.hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; + iavf_ptp_disable_rx_tstamp(adapter); +} + +/** + * iavf_ptp_process_caps - Handle change in PTP capabilities + * @adapter: private adapter structure + * + * Handle any state changes necessary due to change in PTP capabilities, such + * as after a device reset or change in configuration from the PF. + */ +void iavf_ptp_process_caps(struct iavf_adapter *adapter) +{ + bool phc = iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_READ_PHC); + + /* Check if the device gained or lost necessary access to support the + * PTP hardware clock. If so, driver must respond appropriately by + * creating or destroying the PTP clock device. + */ + if (adapter->ptp.clock && !phc) + iavf_ptp_release(adapter); + else if (!adapter->ptp.clock && phc) + iavf_ptp_init(adapter); + + /* Check if the device lost access to Rx timestamp incoming packets */ + if (!iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP)) { + adapter->ptp.hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; + iavf_ptp_disable_rx_tstamp(adapter); + } +} + +/** + * iavf_ptp_extend_32b_timestamp - Convert a 32b nanoseconds timestamp to 64b + * nanoseconds + * @cached_phc_time: recently cached copy of PHC time + * @in_tstamp: Ingress/egress 32b nanoseconds timestamp value + * + * Hardware captures timestamps which contain only 32 bits of nominal + * nanoseconds, as opposed to the 64bit timestamps that the stack expects. + * + * Extend the 32bit nanosecond timestamp using the following algorithm and + * assumptions: + * + * 1) have a recently cached copy of the PHC time + * 2) assume that the in_tstamp was captured 2^31 nanoseconds (~2.1 + * seconds) before or after the PHC time was captured. + * 3) calculate the delta between the cached time and the timestamp + * 4) if the delta is smaller than 2^31 nanoseconds, then the timestamp was + * captured after the PHC time. In this case, the full timestamp is just + * the cached PHC time plus the delta. + * 5) otherwise, if the delta is larger than 2^31 nanoseconds, then the + * timestamp was captured *before* the PHC time, i.e. because the PHC + * cache was updated after the timestamp was captured by hardware. In this + * case, the full timestamp is the cached time minus the inverse delta. + * + * This algorithm works even if the PHC time was updated after a Tx timestamp + * was requested, but before the Tx timestamp event was reported from + * hardware. + * + * This calculation primarily relies on keeping the cached PHC time up to + * date. If the timestamp was captured more than 2^31 nanoseconds after the + * PHC time, it is possible that the lower 32bits of PHC time have + * overflowed more than once, and we might generate an incorrect timestamp. + * + * This is prevented by (a) periodically updating the cached PHC time once + * a second, and (b) discarding any Tx timestamp packet if it has waited for + * a timestamp for more than one second. + * + * Return: extended timestamp (to 64b). + */ +u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time, u32 in_tstamp) +{ + u32 low = lower_32_bits(cached_phc_time); + u32 delta = in_tstamp - low; + u64 ns; + + /* Do not assume that the in_tstamp is always more recent than the + * cached PHC time. If the delta is large, it indicates that the + * in_tstamp was taken in the past, and should be converted + * forward. + */ + if (delta > S32_MAX) + ns = cached_phc_time - (low - in_tstamp); + else + ns = cached_phc_time + delta; + + return ns; +} diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.h b/drivers/net/ethernet/intel/iavf/iavf_ptp.h new file mode 100644 index 000000000000..783b8f287cd9 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2024 Intel Corporation. */ + +#ifndef _IAVF_PTP_H_ +#define _IAVF_PTP_H_ + +#include "iavf_types.h" + +/* bit indicating whether a 40bit timestamp is valid */ +#define IAVF_PTP_40B_TSTAMP_VALID BIT(24) + +#if IS_ENABLED(CONFIG_PTP_1588_CLOCK) +void iavf_ptp_init(struct iavf_adapter *adapter); +void iavf_ptp_release(struct iavf_adapter *adapter); +void iavf_ptp_process_caps(struct iavf_adapter *adapter); +bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter, u32 cap); +void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter); +int iavf_ptp_set_ts_config(struct iavf_adapter *adapter, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); +u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time, u32 in_tstamp); +#else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ +static inline void iavf_ptp_init(struct iavf_adapter *adapter) { } +static inline void iavf_ptp_release(struct iavf_adapter *adapter) { } +static inline void iavf_ptp_process_caps(struct iavf_adapter *adapter) { } +static inline bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter, + u32 cap) +{ + return false; +} + +static inline void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter) { } +static inline int iavf_ptp_set_ts_config(struct iavf_adapter *adapter, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + return -1; +} + +static inline u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time, + u32 in_tstamp) +{ + return 0; +} + +#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ +#endif /* _IAVF_PTP_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_trace.h b/drivers/net/ethernet/intel/iavf/iavf_trace.h index 82fda6f5abf0..c5e4d1823886 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_trace.h +++ b/drivers/net/ethernet/intel/iavf/iavf_trace.h @@ -83,7 +83,7 @@ DECLARE_EVENT_CLASS( __entry->ring = ring; __entry->desc = desc; __entry->buf = buf; - __assign_str(devname, ring->netdev->name); + __assign_str(devname); ), TP_printk( @@ -112,7 +112,7 @@ DECLARE_EVENT_CLASS( iavf_rx_template, TP_PROTO(struct iavf_ring *ring, - union iavf_32byte_rx_desc *desc, + struct iavf_rx_desc *desc, struct sk_buff *skb), TP_ARGS(ring, desc, skb), @@ -128,7 +128,7 @@ DECLARE_EVENT_CLASS( __entry->ring = ring; __entry->desc = desc; __entry->skb = skb; - __assign_str(devname, ring->netdev->name); + __assign_str(devname); ), TP_printk( @@ -140,7 +140,7 @@ DECLARE_EVENT_CLASS( DEFINE_EVENT( iavf_rx_template, iavf_clean_rx_irq, TP_PROTO(struct iavf_ring *ring, - union iavf_32byte_rx_desc *desc, + struct iavf_rx_desc *desc, struct sk_buff *skb), TP_ARGS(ring, desc, skb)); @@ -148,7 +148,7 @@ DEFINE_EVENT( DEFINE_EVENT( iavf_rx_template, iavf_clean_rx_irq_rx, TP_PROTO(struct iavf_ring *ring, - union iavf_32byte_rx_desc *desc, + struct iavf_rx_desc *desc, struct sk_buff *skb), TP_ARGS(ring, desc, skb)); @@ -170,7 +170,7 @@ DECLARE_EVENT_CLASS( TP_fast_assign( __entry->skb = skb; __entry->ring = ring; - __assign_str(devname, ring->netdev->name); + __assign_str(devname); ), TP_printk( diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index b71484c87a84..422312b8b54a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -2,11 +2,32 @@ /* Copyright(c) 2013 - 2018 Intel Corporation. */ #include <linux/bitfield.h> +#include <linux/net/intel/libie/rx.h> #include <linux/prefetch.h> #include "iavf.h" #include "iavf_trace.h" #include "iavf_prototype.h" +#include "iavf_ptp.h" + +/** + * iavf_is_descriptor_done - tests DD bit in Rx descriptor + * @qw1: quad word 1 from descriptor to get Descriptor Done field from + * @flex: is the descriptor flex or legacy + * + * This function tests the descriptor done bit in specified descriptor. Because + * there are two types of descriptors (legacy and flex) the parameter rx_ring + * is used to distinguish. + * + * Return: true or false based on the state of DD bit in Rx descriptor. + */ +static bool iavf_is_descriptor_done(u64 qw1, bool flex) +{ + if (flex) + return FIELD_GET(IAVF_RXD_FLEX_DD_M, qw1); + else + return FIELD_GET(IAVF_RXD_LEGACY_DD_M, qw1); +} static __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size, u32 td_tag) @@ -184,7 +205,7 @@ void iavf_detect_recover_hung(struct iavf_vsi *vsi) * pending work. */ packets = tx_ring->stats.packets & INT_MAX; - if (tx_ring->tx_stats.prev_pkt_ctr == packets) { + if (tx_ring->prev_pkt_ctr == packets) { iavf_force_wb(vsi, tx_ring->q_vector); continue; } @@ -193,7 +214,7 @@ void iavf_detect_recover_hung(struct iavf_vsi *vsi) * to iavf_get_tx_pending() */ smp_rmb(); - tx_ring->tx_stats.prev_pkt_ctr = + tx_ring->prev_pkt_ctr = iavf_get_tx_pending(tx_ring, true) ? packets : -1; } } @@ -319,7 +340,7 @@ static bool iavf_clean_tx_irq(struct iavf_vsi *vsi, ((j / WB_STRIDE) == 0) && (j > 0) && !test_bit(__IAVF_VSI_DOWN, vsi->state) && (IAVF_DESC_UNUSED(tx_ring) != tx_ring->count)) - tx_ring->arm_wb = true; + tx_ring->flags |= IAVF_TXR_FLAGS_ARM_WB; } /* notify netdev of completed buffers */ @@ -674,7 +695,7 @@ int iavf_setup_tx_descriptors(struct iavf_ring *tx_ring) tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; - tx_ring->tx_stats.prev_pkt_ctr = -1; + tx_ring->prev_pkt_ctr = -1; return 0; err: @@ -689,11 +710,8 @@ err: **/ static void iavf_clean_rx_ring(struct iavf_ring *rx_ring) { - unsigned long bi_size; - u16 i; - /* ring already cleared, nothing to do */ - if (!rx_ring->rx_bi) + if (!rx_ring->rx_fqes) return; if (rx_ring->skb) { @@ -701,41 +719,16 @@ static void iavf_clean_rx_ring(struct iavf_ring *rx_ring) rx_ring->skb = NULL; } - /* Free all the Rx ring sk_buffs */ - for (i = 0; i < rx_ring->count; i++) { - struct iavf_rx_buffer *rx_bi = &rx_ring->rx_bi[i]; + /* Free all the Rx ring buffers */ + for (u32 i = rx_ring->next_to_clean; i != rx_ring->next_to_use; ) { + const struct libeth_fqe *rx_fqes = &rx_ring->rx_fqes[i]; - if (!rx_bi->page) - continue; + page_pool_put_full_page(rx_ring->pp, rx_fqes->page, false); - /* Invalidate cache lines that may have been written to by - * device so that we avoid corrupting memory. - */ - dma_sync_single_range_for_cpu(rx_ring->dev, - rx_bi->dma, - rx_bi->page_offset, - rx_ring->rx_buf_len, - DMA_FROM_DEVICE); - - /* free resources associated with mapping */ - dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma, - iavf_rx_pg_size(rx_ring), - DMA_FROM_DEVICE, - IAVF_RX_DMA_ATTR); - - __page_frag_cache_drain(rx_bi->page, rx_bi->pagecnt_bias); - - rx_bi->page = NULL; - rx_bi->page_offset = 0; + if (unlikely(++i == rx_ring->count)) + i = 0; } - bi_size = sizeof(struct iavf_rx_buffer) * rx_ring->count; - memset(rx_ring->rx_bi, 0, bi_size); - - /* Zero out the descriptor ring */ - memset(rx_ring->desc, 0, rx_ring->size); - - rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; } @@ -748,15 +741,22 @@ static void iavf_clean_rx_ring(struct iavf_ring *rx_ring) **/ void iavf_free_rx_resources(struct iavf_ring *rx_ring) { + struct libeth_fq fq = { + .fqes = rx_ring->rx_fqes, + .pp = rx_ring->pp, + }; + iavf_clean_rx_ring(rx_ring); - kfree(rx_ring->rx_bi); - rx_ring->rx_bi = NULL; if (rx_ring->desc) { - dma_free_coherent(rx_ring->dev, rx_ring->size, + dma_free_coherent(rx_ring->pp->p.dev, rx_ring->size, rx_ring->desc, rx_ring->dma); rx_ring->desc = NULL; } + + libeth_rx_fq_destroy(&fq); + rx_ring->rx_fqes = NULL; + rx_ring->pp = NULL; } /** @@ -767,38 +767,46 @@ void iavf_free_rx_resources(struct iavf_ring *rx_ring) **/ int iavf_setup_rx_descriptors(struct iavf_ring *rx_ring) { - struct device *dev = rx_ring->dev; - int bi_size; - - /* warn if we are about to overwrite the pointer */ - WARN_ON(rx_ring->rx_bi); - bi_size = sizeof(struct iavf_rx_buffer) * rx_ring->count; - rx_ring->rx_bi = kzalloc(bi_size, GFP_KERNEL); - if (!rx_ring->rx_bi) - goto err; + struct libeth_fq fq = { + .count = rx_ring->count, + .buf_len = LIBIE_MAX_RX_BUF_LEN, + .nid = NUMA_NO_NODE, + }; + int ret; + + ret = libeth_rx_fq_create(&fq, &rx_ring->q_vector->napi); + if (ret) + return ret; + + rx_ring->pp = fq.pp; + rx_ring->rx_fqes = fq.fqes; + rx_ring->truesize = fq.truesize; + rx_ring->rx_buf_len = fq.buf_len; u64_stats_init(&rx_ring->syncp); /* Round up to nearest 4K */ - rx_ring->size = rx_ring->count * sizeof(union iavf_32byte_rx_desc); + rx_ring->size = rx_ring->count * sizeof(struct iavf_rx_desc); rx_ring->size = ALIGN(rx_ring->size, 4096); - rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size, + rx_ring->desc = dma_alloc_coherent(fq.pp->p.dev, rx_ring->size, &rx_ring->dma, GFP_KERNEL); if (!rx_ring->desc) { - dev_info(dev, "Unable to allocate memory for the Rx descriptor ring, size=%d\n", + dev_info(fq.pp->p.dev, "Unable to allocate memory for the Rx descriptor ring, size=%d\n", rx_ring->size); goto err; } - rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; return 0; + err: - kfree(rx_ring->rx_bi); - rx_ring->rx_bi = NULL; + libeth_rx_fq_destroy(&fq); + rx_ring->rx_fqes = NULL; + rx_ring->pp = NULL; + return -ENOMEM; } @@ -811,9 +819,6 @@ static void iavf_release_rx_desc(struct iavf_ring *rx_ring, u32 val) { rx_ring->next_to_use = val; - /* update next to alloc since we have filled the ring */ - rx_ring->next_to_alloc = val; - /* Force memory writes to complete before letting h/w * know there are new descriptors to fetch. (Only * applicable for weak-ordered memory model archs, @@ -824,69 +829,6 @@ static void iavf_release_rx_desc(struct iavf_ring *rx_ring, u32 val) } /** - * iavf_rx_offset - Return expected offset into page to access data - * @rx_ring: Ring we are requesting offset of - * - * Returns the offset value for ring into the data buffer. - */ -static unsigned int iavf_rx_offset(struct iavf_ring *rx_ring) -{ - return ring_uses_build_skb(rx_ring) ? IAVF_SKB_PAD : 0; -} - -/** - * iavf_alloc_mapped_page - recycle or make a new page - * @rx_ring: ring to use - * @bi: rx_buffer struct to modify - * - * Returns true if the page was successfully allocated or - * reused. - **/ -static bool iavf_alloc_mapped_page(struct iavf_ring *rx_ring, - struct iavf_rx_buffer *bi) -{ - struct page *page = bi->page; - dma_addr_t dma; - - /* since we are recycling buffers we should seldom need to alloc */ - if (likely(page)) { - rx_ring->rx_stats.page_reuse_count++; - return true; - } - - /* alloc new page for storage */ - page = dev_alloc_pages(iavf_rx_pg_order(rx_ring)); - if (unlikely(!page)) { - rx_ring->rx_stats.alloc_page_failed++; - return false; - } - - /* map page for use */ - dma = dma_map_page_attrs(rx_ring->dev, page, 0, - iavf_rx_pg_size(rx_ring), - DMA_FROM_DEVICE, - IAVF_RX_DMA_ATTR); - - /* if mapping failed free memory back to system since - * there isn't much point in holding memory we can't use - */ - if (dma_mapping_error(rx_ring->dev, dma)) { - __free_pages(page, iavf_rx_pg_order(rx_ring)); - rx_ring->rx_stats.alloc_page_failed++; - return false; - } - - bi->dma = dma; - bi->page = page; - bi->page_offset = iavf_rx_offset(rx_ring); - - /* initialize pagecnt_bias to 1 representing we fully own page */ - bi->pagecnt_bias = 1; - - return true; -} - -/** * iavf_receive_skb - Send a completed packet up the stack * @rx_ring: rx ring in play * @skb: packet to send up @@ -916,43 +858,42 @@ static void iavf_receive_skb(struct iavf_ring *rx_ring, **/ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count) { + const struct libeth_fq_fp fq = { + .pp = rx_ring->pp, + .fqes = rx_ring->rx_fqes, + .truesize = rx_ring->truesize, + .count = rx_ring->count, + }; u16 ntu = rx_ring->next_to_use; - union iavf_rx_desc *rx_desc; - struct iavf_rx_buffer *bi; + struct iavf_rx_desc *rx_desc; /* do nothing if no valid netdev defined */ if (!rx_ring->netdev || !cleaned_count) return false; rx_desc = IAVF_RX_DESC(rx_ring, ntu); - bi = &rx_ring->rx_bi[ntu]; do { - if (!iavf_alloc_mapped_page(rx_ring, bi)) - goto no_buffers; + dma_addr_t addr; - /* sync the buffer for use by the device */ - dma_sync_single_range_for_device(rx_ring->dev, bi->dma, - bi->page_offset, - rx_ring->rx_buf_len, - DMA_FROM_DEVICE); + addr = libeth_rx_alloc(&fq, ntu); + if (addr == DMA_MAPPING_ERROR) + goto no_buffers; /* Refresh the desc even if buffer_addrs didn't change * because each write-back erases this info. */ - rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset); + rx_desc->qw0 = cpu_to_le64(addr); rx_desc++; - bi++; ntu++; if (unlikely(ntu == rx_ring->count)) { rx_desc = IAVF_RX_DESC(rx_ring, 0); - bi = rx_ring->rx_bi; ntu = 0; } /* clear the status bits for the next_to_use descriptor */ - rx_desc->wb.qword1.status_error_len = 0; + rx_desc->qw1 = 0; cleaned_count--; } while (cleaned_count); @@ -966,6 +907,8 @@ no_buffers: if (rx_ring->next_to_use != ntu) iavf_release_rx_desc(rx_ring, ntu); + rx_ring->rx_stats.alloc_page_failed++; + /* make sure to come back via polling to try again after * allocation failure */ @@ -973,81 +916,46 @@ no_buffers: } /** - * iavf_rx_checksum - Indicate in skb if hw indicated a good cksum + * iavf_rx_csum - Indicate in skb if hw indicated a good checksum * @vsi: the VSI we care about * @skb: skb currently being received and modified - * @rx_desc: the receive descriptor + * @decoded_pt: decoded ptype information + * @csum_bits: decoded Rx descriptor information **/ -static void iavf_rx_checksum(struct iavf_vsi *vsi, - struct sk_buff *skb, - union iavf_rx_desc *rx_desc) +static void iavf_rx_csum(const struct iavf_vsi *vsi, struct sk_buff *skb, + struct libeth_rx_pt decoded_pt, + struct libeth_rx_csum csum_bits) { - struct iavf_rx_ptype_decoded decoded; - u32 rx_error, rx_status; bool ipv4, ipv6; - u8 ptype; - u64 qword; - - qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword); - rx_error = FIELD_GET(IAVF_RXD_QW1_ERROR_MASK, qword); - rx_status = FIELD_GET(IAVF_RXD_QW1_STATUS_MASK, qword); - decoded = decode_rx_desc_ptype(ptype); skb->ip_summed = CHECKSUM_NONE; - skb_checksum_none_assert(skb); - - /* Rx csum enabled and ip headers found? */ - if (!(vsi->netdev->features & NETIF_F_RXCSUM)) - return; - /* did the hardware decode the packet and checksum? */ - if (!(rx_status & BIT(IAVF_RX_DESC_STATUS_L3L4P_SHIFT))) - return; - - /* both known and outer_ip must be set for the below code to work */ - if (!(decoded.known && decoded.outer_ip)) + if (unlikely(!csum_bits.l3l4p)) return; - ipv4 = (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP) && - (decoded.outer_ip_ver == IAVF_RX_PTYPE_OUTER_IPV4); - ipv6 = (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP) && - (decoded.outer_ip_ver == IAVF_RX_PTYPE_OUTER_IPV6); + ipv4 = libeth_rx_pt_get_ip_ver(decoded_pt) == LIBETH_RX_PT_OUTER_IPV4; + ipv6 = libeth_rx_pt_get_ip_ver(decoded_pt) == LIBETH_RX_PT_OUTER_IPV6; - if (ipv4 && - (rx_error & (BIT(IAVF_RX_DESC_ERROR_IPE_SHIFT) | - BIT(IAVF_RX_DESC_ERROR_EIPE_SHIFT)))) + if (unlikely(ipv4 && (csum_bits.ipe || csum_bits.eipe))) goto checksum_fail; /* likely incorrect csum if alternate IP extension headers found */ - if (ipv6 && - rx_status & BIT(IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT)) - /* don't increment checksum err here, non-fatal err */ + if (unlikely(ipv6 && csum_bits.ipv6exadd)) return; /* there was some L4 error, count error and punt packet to the stack */ - if (rx_error & BIT(IAVF_RX_DESC_ERROR_L4E_SHIFT)) + if (unlikely(csum_bits.l4e)) 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 (rx_error & BIT(IAVF_RX_DESC_ERROR_PPRS_SHIFT)) + if (unlikely(csum_bits.pprs)) return; - /* Only report checksum unnecessary for TCP, UDP, or SCTP */ - switch (decoded.inner_prot) { - case IAVF_RX_PTYPE_INNER_PROT_TCP: - case IAVF_RX_PTYPE_INNER_PROT_UDP: - case IAVF_RX_PTYPE_INNER_PROT_SCTP: - skb->ip_summed = CHECKSUM_UNNECESSARY; - fallthrough; - default: - break; - } - + skb->ip_summed = CHECKSUM_UNNECESSARY; return; checksum_fail: @@ -1055,73 +963,196 @@ checksum_fail: } /** - * iavf_ptype_to_htype - get a hash type - * @ptype: the ptype value from the descriptor + * iavf_legacy_rx_csum - Indicate in skb if hw indicated a good checksum + * @vsi: the VSI we care about + * @qw1: quad word 1 + * @decoded_pt: decoded packet type * - * Returns a hash type to be used by skb_set_hash + * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte + * descriptor writeback format. + * + * Return: decoded checksum bits. **/ -static int iavf_ptype_to_htype(u8 ptype) +static struct libeth_rx_csum +iavf_legacy_rx_csum(const struct iavf_vsi *vsi, u64 qw1, + const struct libeth_rx_pt decoded_pt) { - struct iavf_rx_ptype_decoded decoded = decode_rx_desc_ptype(ptype); + struct libeth_rx_csum csum_bits = {}; - if (!decoded.known) - return PKT_HASH_TYPE_NONE; + if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded_pt)) + return csum_bits; - if (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP && - decoded.payload_layer == IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY4) - return PKT_HASH_TYPE_L4; - else if (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP && - decoded.payload_layer == IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY3) - return PKT_HASH_TYPE_L3; - else - return PKT_HASH_TYPE_L2; + csum_bits.ipe = FIELD_GET(IAVF_RXD_LEGACY_IPE_M, qw1); + csum_bits.eipe = FIELD_GET(IAVF_RXD_LEGACY_EIPE_M, qw1); + csum_bits.l4e = FIELD_GET(IAVF_RXD_LEGACY_L4E_M, qw1); + csum_bits.pprs = FIELD_GET(IAVF_RXD_LEGACY_PPRS_M, qw1); + csum_bits.l3l4p = FIELD_GET(IAVF_RXD_LEGACY_L3L4P_M, qw1); + csum_bits.ipv6exadd = FIELD_GET(IAVF_RXD_LEGACY_IPV6EXADD_M, qw1); + + return csum_bits; } /** - * iavf_rx_hash - set the hash value in the skb + * iavf_flex_rx_csum - Indicate in skb if hw indicated a good checksum + * @vsi: the VSI we care about + * @qw1: quad word 1 + * @decoded_pt: decoded packet type + * + * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible + * descriptor writeback format. + * + * Return: decoded checksum bits. + **/ +static struct libeth_rx_csum +iavf_flex_rx_csum(const struct iavf_vsi *vsi, u64 qw1, + const struct libeth_rx_pt decoded_pt) +{ + struct libeth_rx_csum csum_bits = {}; + + if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded_pt)) + return csum_bits; + + csum_bits.ipe = FIELD_GET(IAVF_RXD_FLEX_XSUM_IPE_M, qw1); + csum_bits.eipe = FIELD_GET(IAVF_RXD_FLEX_XSUM_EIPE_M, qw1); + csum_bits.l4e = FIELD_GET(IAVF_RXD_FLEX_XSUM_L4E_M, qw1); + csum_bits.eudpe = FIELD_GET(IAVF_RXD_FLEX_XSUM_EUDPE_M, qw1); + csum_bits.l3l4p = FIELD_GET(IAVF_RXD_FLEX_L3L4P_M, qw1); + csum_bits.ipv6exadd = FIELD_GET(IAVF_RXD_FLEX_IPV6EXADD_M, qw1); + csum_bits.nat = FIELD_GET(IAVF_RXD_FLEX_NAT_M, qw1); + + return csum_bits; +} + +/** + * iavf_legacy_rx_hash - set the hash value in the skb * @ring: descriptor ring - * @rx_desc: specific descriptor + * @qw0: quad word 0 + * @qw1: quad word 1 * @skb: skb currently being received and modified - * @rx_ptype: Rx packet type + * @decoded_pt: decoded packet type + * + * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte + * descriptor writeback format. **/ -static void iavf_rx_hash(struct iavf_ring *ring, - union iavf_rx_desc *rx_desc, - struct sk_buff *skb, - u8 rx_ptype) +static void iavf_legacy_rx_hash(const struct iavf_ring *ring, __le64 qw0, + __le64 qw1, struct sk_buff *skb, + const struct libeth_rx_pt decoded_pt) { + const __le64 rss_mask = cpu_to_le64(IAVF_RXD_LEGACY_FLTSTAT_M); u32 hash; - const __le64 rss_mask = - cpu_to_le64((u64)IAVF_RX_DESC_FLTSTAT_RSS_HASH << - IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT); - if (!(ring->netdev->features & NETIF_F_RXHASH)) + if (!libeth_rx_pt_has_hash(ring->netdev, decoded_pt)) return; - if ((rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask) { - hash = le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss); - skb_set_hash(skb, hash, iavf_ptype_to_htype(rx_ptype)); + if ((qw1 & rss_mask) == rss_mask) { + hash = le64_get_bits(qw0, IAVF_RXD_LEGACY_RSS_M); + libeth_rx_pt_set_hash(skb, hash, decoded_pt); } } /** + * iavf_flex_rx_hash - set the hash value in the skb + * @ring: descriptor ring + * @qw1: quad word 1 + * @skb: skb currently being received and modified + * @decoded_pt: decoded packet type + * + * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible + * descriptor writeback format. + **/ +static void iavf_flex_rx_hash(const struct iavf_ring *ring, __le64 qw1, + struct sk_buff *skb, + const struct libeth_rx_pt decoded_pt) +{ + bool rss_valid; + u32 hash; + + if (!libeth_rx_pt_has_hash(ring->netdev, decoded_pt)) + return; + + rss_valid = le64_get_bits(qw1, IAVF_RXD_FLEX_RSS_VALID_M); + if (rss_valid) { + hash = le64_get_bits(qw1, IAVF_RXD_FLEX_RSS_HASH_M); + libeth_rx_pt_set_hash(skb, hash, decoded_pt); + } +} + +/** + * iavf_flex_rx_tstamp - Capture Rx timestamp from the descriptor + * @rx_ring: descriptor ring + * @qw2: quad word 2 of descriptor + * @qw3: quad word 3 of descriptor + * @skb: skb currently being received + * + * Read the Rx timestamp value from the descriptor and pass it to the stack. + * + * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible + * descriptor writeback format. + */ +static void iavf_flex_rx_tstamp(const struct iavf_ring *rx_ring, __le64 qw2, + __le64 qw3, struct sk_buff *skb) +{ + u32 tstamp; + u64 ns; + + /* Skip processing if timestamps aren't enabled */ + if (!(rx_ring->flags & IAVF_TXRX_FLAGS_HW_TSTAMP)) + return; + + /* Check if this Rx descriptor has a valid timestamp */ + if (!le64_get_bits(qw2, IAVF_PTP_40B_TSTAMP_VALID)) + return; + + /* the ts_low field only contains the valid bit and sub-nanosecond + * precision, so we don't need to extract it. + */ + tstamp = le64_get_bits(qw3, IAVF_RXD_FLEX_QW3_TSTAMP_HIGH_M); + + ns = iavf_ptp_extend_32b_timestamp(rx_ring->ptp->cached_phc_time, + tstamp); + + *skb_hwtstamps(skb) = (struct skb_shared_hwtstamps) { + .hwtstamp = ns_to_ktime(ns), + }; +} + +/** * iavf_process_skb_fields - Populate skb header fields from Rx descriptor * @rx_ring: rx descriptor ring packet is being transacted on * @rx_desc: pointer to the EOP Rx descriptor * @skb: pointer to current skb being populated - * @rx_ptype: the packet type decoded by hardware + * @ptype: the packet type decoded by hardware + * @flex: is the descriptor flex or legacy * * 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 -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(const struct iavf_ring *rx_ring, + const struct iavf_rx_desc *rx_desc, + struct sk_buff *skb, u32 ptype, + bool flex) { - iavf_rx_hash(rx_ring, rx_desc, skb, rx_ptype); - - iavf_rx_checksum(rx_ring->vsi, skb, rx_desc); + struct libeth_rx_csum csum_bits; + struct libeth_rx_pt decoded_pt; + __le64 qw0 = rx_desc->qw0; + __le64 qw1 = rx_desc->qw1; + __le64 qw2 = rx_desc->qw2; + __le64 qw3 = rx_desc->qw3; + + decoded_pt = libie_rx_pt_parse(ptype); + + if (flex) { + iavf_flex_rx_hash(rx_ring, qw1, skb, decoded_pt); + iavf_flex_rx_tstamp(rx_ring, qw2, qw3, skb); + csum_bits = iavf_flex_rx_csum(rx_ring->vsi, le64_to_cpu(qw1), + decoded_pt); + } else { + iavf_legacy_rx_hash(rx_ring, qw0, qw1, skb, decoded_pt); + csum_bits = iavf_legacy_rx_csum(rx_ring->vsi, le64_to_cpu(qw1), + decoded_pt); + } + iavf_rx_csum(rx_ring->vsi, skb, decoded_pt, csum_bits); skb_record_rx_queue(skb, rx_ring->queue_index); @@ -1152,95 +1183,9 @@ static bool iavf_cleanup_headers(struct iavf_ring *rx_ring, struct sk_buff *skb) } /** - * iavf_reuse_rx_page - page flip buffer and store it back on the ring - * @rx_ring: rx descriptor ring to store buffers on - * @old_buff: donor buffer to have page reused - * - * Synchronizes page for reuse by the adapter - **/ -static void iavf_reuse_rx_page(struct iavf_ring *rx_ring, - struct iavf_rx_buffer *old_buff) -{ - struct iavf_rx_buffer *new_buff; - u16 nta = rx_ring->next_to_alloc; - - new_buff = &rx_ring->rx_bi[nta]; - - /* update, and store next to alloc */ - nta++; - rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; - - /* transfer page from old buffer to new buffer */ - new_buff->dma = old_buff->dma; - new_buff->page = old_buff->page; - new_buff->page_offset = old_buff->page_offset; - new_buff->pagecnt_bias = old_buff->pagecnt_bias; -} - -/** - * iavf_can_reuse_rx_page - Determine if this page can be reused by - * the adapter for another receive - * - * @rx_buffer: buffer containing the page - * - * If page is reusable, rx_buffer->page_offset is adjusted to point to - * an unused region in the page. - * - * For small pages, @truesize will be a constant value, half the size - * of the memory at page. We'll attempt to alternate between high and - * low halves of the page, with one half ready for use by the hardware - * and the other half being consumed by the stack. We use the page - * ref count to determine whether the stack has finished consuming the - * portion of this page that was passed up with a previous packet. If - * the page ref count is >1, we'll assume the "other" half page is - * still busy, and this page cannot be reused. - * - * For larger pages, @truesize will be the actual space used by the - * received packet (adjusted upward to an even multiple of the cache - * line size). This will advance through the page by the amount - * actually consumed by the received packets while there is still - * space for a buffer. Each region of larger pages will be used at - * most once, after which the page will not be reused. - * - * In either case, if the page is reusable its refcount is increased. - **/ -static bool iavf_can_reuse_rx_page(struct iavf_rx_buffer *rx_buffer) -{ - unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; - struct page *page = rx_buffer->page; - - /* Is any reuse possible? */ - if (!dev_page_is_reusable(page)) - return false; - -#if (PAGE_SIZE < 8192) - /* if we are only owner of page we can reuse it */ - if (unlikely((page_count(page) - pagecnt_bias) > 1)) - return false; -#else -#define IAVF_LAST_OFFSET \ - (SKB_WITH_OVERHEAD(PAGE_SIZE) - IAVF_RXBUFFER_2048) - if (rx_buffer->page_offset > IAVF_LAST_OFFSET) - return false; -#endif - - /* If we have drained the page fragment pool we need to update - * the pagecnt_bias and page count so that we fully restock the - * number of references the driver holds. - */ - if (unlikely(!pagecnt_bias)) { - page_ref_add(page, USHRT_MAX); - rx_buffer->pagecnt_bias = USHRT_MAX; - } - - return true; -} - -/** * iavf_add_rx_frag - Add contents of Rx buffer to sk_buff - * @rx_ring: rx descriptor ring to transact packets on - * @rx_buffer: buffer containing page to add * @skb: sk_buff to place the data into + * @rx_buffer: buffer containing page to add * @size: packet length from rx_desc * * This function will add the data contained in rx_buffer->page to the skb. @@ -1248,210 +1193,53 @@ static bool iavf_can_reuse_rx_page(struct iavf_rx_buffer *rx_buffer) * * The function will then update the page offset. **/ -static void iavf_add_rx_frag(struct iavf_ring *rx_ring, - struct iavf_rx_buffer *rx_buffer, - struct sk_buff *skb, +static void iavf_add_rx_frag(struct sk_buff *skb, + const struct libeth_fqe *rx_buffer, unsigned int size) { -#if (PAGE_SIZE < 8192) - unsigned int truesize = iavf_rx_pg_size(rx_ring) / 2; -#else - unsigned int truesize = SKB_DATA_ALIGN(size + iavf_rx_offset(rx_ring)); -#endif - - if (!size) - return; + u32 hr = rx_buffer->page->pp->p.offset; skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, - rx_buffer->page_offset, size, truesize); - - /* page is being used so we must update the page offset */ -#if (PAGE_SIZE < 8192) - rx_buffer->page_offset ^= truesize; -#else - rx_buffer->page_offset += truesize; -#endif -} - -/** - * iavf_get_rx_buffer - Fetch Rx buffer and synchronize data for use - * @rx_ring: rx descriptor ring to transact packets on - * @size: size of buffer to add to skb - * - * This function will pull an Rx buffer from the ring and synchronize it - * for use by the CPU. - */ -static struct iavf_rx_buffer *iavf_get_rx_buffer(struct iavf_ring *rx_ring, - const unsigned int size) -{ - struct iavf_rx_buffer *rx_buffer; - - rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean]; - prefetchw(rx_buffer->page); - if (!size) - return rx_buffer; - - /* we are reusing so sync this buffer for CPU use */ - dma_sync_single_range_for_cpu(rx_ring->dev, - rx_buffer->dma, - rx_buffer->page_offset, - size, - DMA_FROM_DEVICE); - - /* We have pulled a buffer for use, so decrement pagecnt_bias */ - rx_buffer->pagecnt_bias--; - - return rx_buffer; -} - -/** - * iavf_construct_skb - Allocate skb and populate it - * @rx_ring: rx descriptor ring to transact packets on - * @rx_buffer: rx buffer to pull data from - * @size: size of buffer to add to skb - * - * 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. - */ -static struct sk_buff *iavf_construct_skb(struct iavf_ring *rx_ring, - struct iavf_rx_buffer *rx_buffer, - unsigned int size) -{ - void *va; -#if (PAGE_SIZE < 8192) - unsigned int truesize = iavf_rx_pg_size(rx_ring) / 2; -#else - unsigned int truesize = SKB_DATA_ALIGN(size); -#endif - unsigned int headlen; - struct sk_buff *skb; - - if (!rx_buffer) - return NULL; - /* prefetch first cache line of first page */ - va = page_address(rx_buffer->page) + rx_buffer->page_offset; - net_prefetch(va); - - /* allocate a skb to store the frags */ - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, - IAVF_RX_HDR_SIZE, - GFP_ATOMIC | __GFP_NOWARN); - if (unlikely(!skb)) - return NULL; - - /* Determine available headroom for copy */ - headlen = size; - if (headlen > IAVF_RX_HDR_SIZE) - headlen = eth_get_headlen(skb->dev, va, IAVF_RX_HDR_SIZE); - - /* align pull length to size of long to optimize memcpy performance */ - memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); - - /* update all of the pointers */ - size -= headlen; - if (size) { - skb_add_rx_frag(skb, 0, rx_buffer->page, - rx_buffer->page_offset + headlen, - size, truesize); - - /* buffer is used by skb, update page_offset */ -#if (PAGE_SIZE < 8192) - rx_buffer->page_offset ^= truesize; -#else - rx_buffer->page_offset += truesize; -#endif - } else { - /* buffer is unused, reset bias back to rx_buffer */ - rx_buffer->pagecnt_bias++; - } - - return skb; + rx_buffer->offset + hr, size, rx_buffer->truesize); } /** * iavf_build_skb - Build skb around an existing buffer - * @rx_ring: Rx descriptor ring to transact packets on * @rx_buffer: Rx buffer to pull data from * @size: size of buffer to add to skb * * This function builds an skb around an existing Rx buffer, taking care * to set up the skb correctly and avoid any memcpy overhead. */ -static struct sk_buff *iavf_build_skb(struct iavf_ring *rx_ring, - struct iavf_rx_buffer *rx_buffer, +static struct sk_buff *iavf_build_skb(const struct libeth_fqe *rx_buffer, unsigned int size) { - void *va; -#if (PAGE_SIZE < 8192) - unsigned int truesize = iavf_rx_pg_size(rx_ring) / 2; -#else - unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + - SKB_DATA_ALIGN(IAVF_SKB_PAD + size); -#endif + u32 hr = rx_buffer->page->pp->p.offset; struct sk_buff *skb; + void *va; - if (!rx_buffer || !size) - return NULL; /* prefetch first cache line of first page */ - va = page_address(rx_buffer->page) + rx_buffer->page_offset; - net_prefetch(va); + va = page_address(rx_buffer->page) + rx_buffer->offset; + net_prefetch(va + hr); /* build an skb around the page buffer */ - skb = napi_build_skb(va - IAVF_SKB_PAD, truesize); + skb = napi_build_skb(va, rx_buffer->truesize); if (unlikely(!skb)) return NULL; + skb_mark_for_recycle(skb); + /* update pointers within the skb to store the data */ - skb_reserve(skb, IAVF_SKB_PAD); + skb_reserve(skb, hr); __skb_put(skb, size); - /* buffer is used by skb, update page_offset */ -#if (PAGE_SIZE < 8192) - rx_buffer->page_offset ^= truesize; -#else - rx_buffer->page_offset += truesize; -#endif - return skb; } /** - * iavf_put_rx_buffer - Clean up used buffer and either recycle or free - * @rx_ring: rx descriptor ring to transact packets on - * @rx_buffer: rx buffer to pull data from - * - * This function will clean up the contents of the rx_buffer. It will - * either recycle the buffer or unmap it and free the associated resources. - */ -static void iavf_put_rx_buffer(struct iavf_ring *rx_ring, - struct iavf_rx_buffer *rx_buffer) -{ - if (!rx_buffer) - return; - - if (iavf_can_reuse_rx_page(rx_buffer)) { - /* hand second half of page back to the ring */ - iavf_reuse_rx_page(rx_ring, rx_buffer); - rx_ring->rx_stats.page_reuse_count++; - } else { - /* we are not reusing the buffer so unmap it */ - dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, - iavf_rx_pg_size(rx_ring), - DMA_FROM_DEVICE, IAVF_RX_DMA_ATTR); - __page_frag_cache_drain(rx_buffer->page, - rx_buffer->pagecnt_bias); - } - - /* clear contents of buffer_info */ - rx_buffer->page = NULL; -} - -/** * iavf_is_non_eop - process handling of non-EOP buffers * @rx_ring: Rx ring being processed - * @rx_desc: Rx descriptor for current buffer - * @skb: Current socket buffer containing buffer in progress + * @fields: Rx descriptor extracted fields * * This function updates next to clean. If the buffer is an EOP buffer * this function exits returning false, otherwise it will place the @@ -1459,8 +1247,7 @@ static void iavf_put_rx_buffer(struct iavf_ring *rx_ring, * that this is in fact a non-EOP buffer. **/ static bool iavf_is_non_eop(struct iavf_ring *rx_ring, - union iavf_rx_desc *rx_desc, - struct sk_buff *skb) + struct libeth_rqe_info fields) { u32 ntc = rx_ring->next_to_clean + 1; @@ -1471,8 +1258,7 @@ static bool iavf_is_non_eop(struct iavf_ring *rx_ring, prefetch(IAVF_RX_DESC(rx_ring, ntc)); /* if we are the last buffer then there is nothing else to do */ -#define IAVF_RXD_EOF BIT(IAVF_RX_DESC_STATUS_EOF_SHIFT) - if (likely(iavf_test_staterr(rx_desc, IAVF_RXD_EOF))) + if (likely(fields.eop)) return false; rx_ring->rx_stats.non_eop_descs++; @@ -1481,6 +1267,109 @@ static bool iavf_is_non_eop(struct iavf_ring *rx_ring, } /** + * iavf_extract_legacy_rx_fields - Extract fields from the Rx descriptor + * @rx_ring: rx descriptor ring + * @rx_desc: the descriptor to process + * + * Decode the Rx descriptor and extract relevant information including the + * size, VLAN tag, Rx packet type, end of packet field and RXE field value. + * + * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte + * descriptor writeback format. + * + * Return: fields extracted from the Rx descriptor. + */ +static struct libeth_rqe_info +iavf_extract_legacy_rx_fields(const struct iavf_ring *rx_ring, + const struct iavf_rx_desc *rx_desc) +{ + u64 qw0 = le64_to_cpu(rx_desc->qw0); + u64 qw1 = le64_to_cpu(rx_desc->qw1); + u64 qw2 = le64_to_cpu(rx_desc->qw2); + struct libeth_rqe_info fields; + bool l2tag1p, l2tag2p; + + fields.eop = FIELD_GET(IAVF_RXD_LEGACY_EOP_M, qw1); + fields.len = FIELD_GET(IAVF_RXD_LEGACY_LENGTH_M, qw1); + + if (!fields.eop) + return fields; + + fields.rxe = FIELD_GET(IAVF_RXD_LEGACY_RXE_M, qw1); + fields.ptype = FIELD_GET(IAVF_RXD_LEGACY_PTYPE_M, qw1); + fields.vlan = 0; + + if (rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1) { + l2tag1p = FIELD_GET(IAVF_RXD_LEGACY_L2TAG1P_M, qw1); + if (l2tag1p) + fields.vlan = FIELD_GET(IAVF_RXD_LEGACY_L2TAG1_M, qw0); + } else if (rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2) { + l2tag2p = FIELD_GET(IAVF_RXD_LEGACY_L2TAG2P_M, qw2); + if (l2tag2p) + fields.vlan = FIELD_GET(IAVF_RXD_LEGACY_L2TAG2_M, qw2); + } + + return fields; +} + +/** + * iavf_extract_flex_rx_fields - Extract fields from the Rx descriptor + * @rx_ring: rx descriptor ring + * @rx_desc: the descriptor to process + * + * Decode the Rx descriptor and extract relevant information including the + * size, VLAN tag, Rx packet type, end of packet field and RXE field value. + * + * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible + * descriptor writeback format. + * + * Return: fields extracted from the Rx descriptor. + */ +static struct libeth_rqe_info +iavf_extract_flex_rx_fields(const struct iavf_ring *rx_ring, + const struct iavf_rx_desc *rx_desc) +{ + struct libeth_rqe_info fields = {}; + u64 qw0 = le64_to_cpu(rx_desc->qw0); + u64 qw1 = le64_to_cpu(rx_desc->qw1); + u64 qw2 = le64_to_cpu(rx_desc->qw2); + bool l2tag1p, l2tag2p; + + fields.eop = FIELD_GET(IAVF_RXD_FLEX_EOP_M, qw1); + fields.len = FIELD_GET(IAVF_RXD_FLEX_PKT_LEN_M, qw0); + + if (!fields.eop) + return fields; + + fields.rxe = FIELD_GET(IAVF_RXD_FLEX_RXE_M, qw1); + fields.ptype = FIELD_GET(IAVF_RXD_FLEX_PTYPE_M, qw0); + fields.vlan = 0; + + if (rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1) { + l2tag1p = FIELD_GET(IAVF_RXD_FLEX_L2TAG1P_M, qw1); + if (l2tag1p) + fields.vlan = FIELD_GET(IAVF_RXD_FLEX_L2TAG1_M, qw1); + } else if (rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2) { + l2tag2p = FIELD_GET(IAVF_RXD_FLEX_L2TAG2P_M, qw2); + if (l2tag2p) + fields.vlan = FIELD_GET(IAVF_RXD_FLEX_L2TAG2_2_M, qw2); + } + + return fields; +} + +static struct libeth_rqe_info +iavf_extract_rx_fields(const struct iavf_ring *rx_ring, + const struct iavf_rx_desc *rx_desc, + bool flex) +{ + if (flex) + return iavf_extract_flex_rx_fields(rx_ring, rx_desc); + else + return iavf_extract_legacy_rx_fields(rx_ring, rx_desc); +} + +/** * iavf_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf * @rx_ring: rx descriptor ring to transact packets on * @budget: Total limit on number of packets to process @@ -1494,18 +1383,17 @@ static bool iavf_is_non_eop(struct iavf_ring *rx_ring, **/ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget) { + bool flex = rx_ring->rxdid == VIRTCHNL_RXDID_2_FLEX_SQ_NIC; unsigned int total_rx_bytes = 0, total_rx_packets = 0; struct sk_buff *skb = rx_ring->skb; u16 cleaned_count = IAVF_DESC_UNUSED(rx_ring); bool failure = false; while (likely(total_rx_packets < (unsigned int)budget)) { - struct iavf_rx_buffer *rx_buffer; - union iavf_rx_desc *rx_desc; - unsigned int size; - u16 vlan_tag = 0; - u8 rx_ptype; - u64 qword; + struct libeth_rqe_info fields; + struct libeth_fqe *rx_buffer; + struct iavf_rx_desc *rx_desc; + u64 qw1; /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= IAVF_RX_BUFFER_WRITE) { @@ -1516,55 +1404,50 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget) rx_desc = IAVF_RX_DESC(rx_ring, rx_ring->next_to_clean); - /* status_error_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 - */ - qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - /* This memory barrier is needed to keep us from reading * any other fields out of the rx_desc until we have * verified the descriptor has been written back. */ dma_rmb(); -#define IAVF_RXD_DD BIT(IAVF_RX_DESC_STATUS_DD_SHIFT) - if (!iavf_test_staterr(rx_desc, IAVF_RXD_DD)) + + qw1 = le64_to_cpu(rx_desc->qw1); + /* If DD field (descriptor done) is unset then other fields are + * not valid + */ + if (!iavf_is_descriptor_done(qw1, flex)) break; - size = FIELD_GET(IAVF_RXD_QW1_LENGTH_PBUF_MASK, qword); + fields = iavf_extract_rx_fields(rx_ring, rx_desc, flex); iavf_trace(clean_rx_irq, rx_ring, rx_desc, skb); - rx_buffer = iavf_get_rx_buffer(rx_ring, size); + + rx_buffer = &rx_ring->rx_fqes[rx_ring->next_to_clean]; + if (!libeth_rx_sync_for_cpu(rx_buffer, fields.len)) + goto skip_data; /* retrieve a buffer from the ring */ if (skb) - iavf_add_rx_frag(rx_ring, rx_buffer, skb, size); - else if (ring_uses_build_skb(rx_ring)) - skb = iavf_build_skb(rx_ring, rx_buffer, size); + iavf_add_rx_frag(skb, rx_buffer, fields.len); else - skb = iavf_construct_skb(rx_ring, rx_buffer, size); + skb = iavf_build_skb(rx_buffer, fields.len); /* exit if we failed to retrieve a buffer */ if (!skb) { rx_ring->rx_stats.alloc_buff_failed++; - if (rx_buffer && size) - rx_buffer->pagecnt_bias++; break; } - iavf_put_rx_buffer(rx_ring, rx_buffer); +skip_data: cleaned_count++; - if (iavf_is_non_eop(rx_ring, rx_desc, skb)) + if (iavf_is_non_eop(rx_ring, fields) || unlikely(!skb)) continue; - /* ERR_MASK will only have valid bits if EOP set, and - * what we are doing here is actually checking - * IAVF_RX_DESC_ERROR_RXE_SHIFT, since it is the zeroth bit in - * the error field + /* RXE field in descriptor is an indication of the MAC errors + * (like CRC, alignment, oversize etc). If it is set then iavf + * should finish. */ - if (unlikely(iavf_test_staterr(rx_desc, BIT(IAVF_RXD_QW1_ERROR_SHIFT)))) { + if (unlikely(fields.rxe)) { dev_kfree_skb_any(skb); skb = NULL; continue; @@ -1578,22 +1461,11 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget) /* probably a little skewed due to removing CRC */ total_rx_bytes += skb->len; - qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - rx_ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword); - /* populate checksum, VLAN, and protocol */ - iavf_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); - - if (qword & BIT(IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT) && - rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1) - vlan_tag = le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1); - if (rx_desc->wb.qword2.ext_status & - cpu_to_le16(BIT(IAVF_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT)) && - rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2) - vlan_tag = le16_to_cpu(rx_desc->wb.qword2.l2tag2_2); + iavf_process_skb_fields(rx_ring, rx_desc, skb, fields.ptype, flex); iavf_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb); - iavf_receive_skb(rx_ring, skb, vlan_tag); + iavf_receive_skb(rx_ring, skb, fields.vlan); skb = NULL; /* update budget accounting */ @@ -1743,8 +1615,8 @@ int iavf_napi_poll(struct napi_struct *napi, int budget) clean_complete = false; continue; } - arm_wb |= ring->arm_wb; - ring->arm_wb = false; + arm_wb |= !!(ring->flags & IAVF_TXR_FLAGS_ARM_WB); + ring->flags &= ~IAVF_TXR_FLAGS_ARM_WB; } /* Handle case where we are called by netpoll with a budget of 0 */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h index 10ba36602c0c..79ad554f2d53 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h @@ -80,96 +80,6 @@ enum iavf_dyn_idx_t { BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \ BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP)) -/* Supported Rx Buffer Sizes (a multiple of 128) */ -#define IAVF_RXBUFFER_256 256 -#define IAVF_RXBUFFER_1536 1536 /* 128B aligned standard Ethernet frame */ -#define IAVF_RXBUFFER_2048 2048 -#define IAVF_RXBUFFER_3072 3072 /* Used for large frames w/ padding */ -#define IAVF_MAX_RXBUFFER 9728 /* largest size for single descriptor */ - -/* NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we - * reserve 2 more, and skb_shared_info adds an additional 384 bytes more, - * this adds up to 512 bytes of extra data meaning the smallest allocation - * we could have is 1K. - * i.e. RXBUFFER_256 --> 960 byte skb (size-1024 slab) - * i.e. RXBUFFER_512 --> 1216 byte skb (size-2048 slab) - */ -#define IAVF_RX_HDR_SIZE IAVF_RXBUFFER_256 -#define IAVF_PACKET_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2)) -#define iavf_rx_desc iavf_32byte_rx_desc - -#define IAVF_RX_DMA_ATTR \ - (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) - -/* Attempt to maximize the headroom available for incoming frames. We - * use a 2K buffer for receives and need 1536/1534 to store the data for - * the frame. This leaves us with 512 bytes of room. From that we need - * to deduct the space needed for the shared info and the padding needed - * to IP align the frame. - * - * Note: For cache line sizes 256 or larger this value is going to end - * up negative. In these cases we should fall back to the legacy - * receive path. - */ -#if (PAGE_SIZE < 8192) -#define IAVF_2K_TOO_SMALL_WITH_PADDING \ -((NET_SKB_PAD + IAVF_RXBUFFER_1536) > SKB_WITH_OVERHEAD(IAVF_RXBUFFER_2048)) - -static inline int iavf_compute_pad(int rx_buf_len) -{ - int page_size, pad_size; - - page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2); - pad_size = SKB_WITH_OVERHEAD(page_size) - rx_buf_len; - - return pad_size; -} - -static inline int iavf_skb_pad(void) -{ - int rx_buf_len; - - /* If a 2K buffer cannot handle a standard Ethernet frame then - * optimize padding for a 3K buffer instead of a 1.5K buffer. - * - * For a 3K buffer we need to add enough padding to allow for - * tailroom due to NET_IP_ALIGN possibly shifting us out of - * cache-line alignment. - */ - if (IAVF_2K_TOO_SMALL_WITH_PADDING) - rx_buf_len = IAVF_RXBUFFER_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN); - else - rx_buf_len = IAVF_RXBUFFER_1536; - - /* if needed make room for NET_IP_ALIGN */ - rx_buf_len -= NET_IP_ALIGN; - - return iavf_compute_pad(rx_buf_len); -} - -#define IAVF_SKB_PAD iavf_skb_pad() -#else -#define IAVF_2K_TOO_SMALL_WITH_PADDING false -#define IAVF_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) -#endif - -/** - * iavf_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_len doesn't need to be shifted because it begins - * at offset zero. - */ -static inline bool iavf_test_staterr(union iavf_rx_desc *rx_desc, - const u64 stat_err_bits) -{ - return !!(rx_desc->wb.qword1.status_error_len & - cpu_to_le64(stat_err_bits)); -} - /* How many Rx Buffers do we bundle into one write to the hardware ? */ #define IAVF_RX_INCREMENT(r, i) \ do { \ @@ -271,17 +181,6 @@ struct iavf_tx_buffer { u32 tx_flags; }; -struct iavf_rx_buffer { - dma_addr_t dma; - struct page *page; -#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536) - __u32 page_offset; -#else - __u16 page_offset; -#endif - __u16 pagecnt_bias; -}; - struct iavf_queue_stats { u64 packets; u64 bytes; @@ -293,7 +192,6 @@ struct iavf_tx_queue_stats { u64 tx_done_old; u64 tx_linearize; u64 tx_force_wb; - int prev_pkt_ctr; u64 tx_lost_interrupt; }; @@ -301,14 +199,6 @@ struct iavf_rx_queue_stats { u64 non_eop_descs; u64 alloc_page_failed; u64 alloc_buff_failed; - u64 page_reuse_count; - u64 realloc_count; -}; - -enum iavf_ring_state_t { - __IAVF_TX_FDIR_INIT_DONE, - __IAVF_TX_XPS_INIT_DONE, - __IAVF_RING_STATE_NBITS /* must be last */ }; /* some useful defines for virtchannel interface, which @@ -326,16 +216,19 @@ enum iavf_ring_state_t { struct iavf_ring { struct iavf_ring *next; /* pointer to next ring in q_vector */ void *desc; /* Descriptor ring memory */ - struct device *dev; /* Used for DMA mapping */ + union { + struct page_pool *pp; /* Used on Rx for buffer management */ + struct device *dev; /* Used on Tx for DMA mapping */ + }; struct net_device *netdev; /* netdev ring maps to */ union { + struct libeth_fqe *rx_fqes; struct iavf_tx_buffer *tx_bi; - struct iavf_rx_buffer *rx_bi; }; - DECLARE_BITMAP(state, __IAVF_RING_STATE_NBITS); - u16 queue_index; /* Queue number of ring */ - u8 dcb_tc; /* Traffic class of ring */ u8 __iomem *tail; + u32 truesize; + + u16 queue_index; /* Queue number of ring */ /* high bit set means dynamic, use accessors routines to read/write. * hardware only supports 2us resolution for the ITR registers. @@ -345,26 +238,21 @@ struct iavf_ring { u16 itr_setting; u16 count; /* Number of descriptors */ - u16 reg_idx; /* HW register index of the ring */ - u16 rx_buf_len; /* used in interrupt processing */ u16 next_to_use; u16 next_to_clean; - u8 atr_sample_rate; - u8 atr_count; - - bool ring_active; /* is ring online or not */ - bool arm_wb; /* do something to arm write back */ - u8 packet_stride; + u16 rxdid; /* Rx descriptor format */ u16 flags; #define IAVF_TXR_FLAGS_WB_ON_ITR BIT(0) -#define IAVF_RXR_FLAGS_BUILD_SKB_ENABLED BIT(1) +#define IAVF_TXR_FLAGS_ARM_WB BIT(1) +/* BIT(2) is free */ #define IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1 BIT(3) #define IAVF_TXR_FLAGS_VLAN_TAG_LOC_L2TAG2 BIT(4) #define IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2 BIT(5) +#define IAVF_TXRX_FLAGS_HW_TSTAMP BIT(6) /* stats structs */ struct iavf_queue_stats stats; @@ -374,6 +262,7 @@ struct iavf_ring { struct iavf_rx_queue_stats rx_stats; }; + int prev_pkt_ctr; /* For Tx stall detection */ unsigned int size; /* length of descriptor ring in bytes */ dma_addr_t dma; /* physical address of ring */ @@ -381,7 +270,6 @@ struct iavf_ring { struct iavf_q_vector *q_vector; /* Backreference to associated vector */ struct rcu_head rcu; /* to avoid race on free */ - u16 next_to_alloc; struct sk_buff *skb; /* When iavf_clean_rx_ring_irq() must * return before it sees the EOP for * the current packet, we save that skb @@ -390,22 +278,13 @@ struct iavf_ring { * iavf_clean_rx_ring_irq() is called * for this ring. */ -} ____cacheline_internodealigned_in_smp; - -static inline bool ring_uses_build_skb(struct iavf_ring *ring) -{ - return !!(ring->flags & IAVF_RXR_FLAGS_BUILD_SKB_ENABLED); -} -static inline void set_ring_build_skb_enabled(struct iavf_ring *ring) -{ - ring->flags |= IAVF_RXR_FLAGS_BUILD_SKB_ENABLED; -} + struct iavf_ptp *ptp; -static inline void clear_ring_build_skb_enabled(struct iavf_ring *ring) -{ - ring->flags &= ~IAVF_RXR_FLAGS_BUILD_SKB_ENABLED; -} + u32 rx_buf_len; + struct net_shaper q_shaper; + bool q_shaper_update; +} ____cacheline_internodealigned_in_smp; #define IAVF_ITR_ADAPTIVE_MIN_INC 0x0002 #define IAVF_ITR_ADAPTIVE_MIN_USECS 0x0002 @@ -428,17 +307,6 @@ struct iavf_ring_container { #define iavf_for_each_ring(pos, head) \ for (pos = (head).ring; pos != NULL; pos = pos->next) -static inline unsigned int iavf_rx_pg_order(struct iavf_ring *ring) -{ -#if (PAGE_SIZE < 8192) - if (ring->rx_buf_len > (PAGE_SIZE / 2)) - return 1; -#endif - return 0; -} - -#define iavf_rx_pg_size(_ring) (PAGE_SIZE << iavf_rx_pg_order(_ring)) - bool iavf_alloc_rx_buffers(struct iavf_ring *rxr, u16 cleaned_count); netdev_tx_t iavf_xmit_frame(struct sk_buff *skb, struct net_device *netdev); int iavf_setup_tx_descriptors(struct iavf_ring *tx_ring); diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h index 2b6a207fa441..f9e1319620f4 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_type.h +++ b/drivers/net/ethernet/intel/iavf/iavf_type.h @@ -10,8 +10,6 @@ #include "iavf_adminq.h" #include "iavf_devids.h" -#define IAVF_RXQ_CTX_DBUFF_SHIFT 7 - /* IAVF_MASK is a macro used on 32 bit registers */ #define IAVF_MASK(mask, shift) ((u32)(mask) << (shift)) @@ -180,110 +178,116 @@ struct iavf_hw { char err_str[16]; }; -/* RX Descriptors */ -union iavf_16byte_rx_desc { - struct { - __le64 pkt_addr; /* Packet buffer address */ - __le64 hdr_addr; /* Header buffer address */ - } read; - struct { - struct { - struct { - union { - __le16 mirroring_status; - __le16 fcoe_ctx_id; - } mirr_fcoe; - __le16 l2tag1; - } lo_dword; - union { - __le32 rss; /* RSS Hash */ - __le32 fd_id; /* Flow director filter id */ - __le32 fcoe_param; /* FCoE DDP Context id */ - } hi_dword; - } qword0; - struct { - /* ext status/error/pktype/length */ - __le64 status_error_len; - } qword1; - } wb; /* writeback */ -}; - -union iavf_32byte_rx_desc { - struct { - __le64 pkt_addr; /* Packet buffer address */ - __le64 hdr_addr; /* Header buffer address */ - /* bit 0 of hdr_buffer_addr is DD bit */ - __le64 rsvd1; - __le64 rsvd2; - } read; - struct { - struct { - struct { - union { - __le16 mirroring_status; - __le16 fcoe_ctx_id; - } mirr_fcoe; - __le16 l2tag1; - } lo_dword; - union { - __le32 rss; /* RSS Hash */ - __le32 fcoe_param; /* FCoE DDP Context id */ - /* Flow director filter id in case of - * Programming status desc WB - */ - __le32 fd_id; - } hi_dword; - } qword0; - struct { - /* status/error/pktype/length */ - __le64 status_error_len; - } qword1; - struct { - __le16 ext_status; /* extended status */ - __le16 rsvd; - __le16 l2tag2_1; - __le16 l2tag2_2; - } qword2; - struct { - union { - __le32 flex_bytes_lo; - __le32 pe_status; - } lo_dword; - union { - __le32 flex_bytes_hi; - __le32 fd_id; - } hi_dword; - } qword3; - } wb; /* writeback */ -}; - -enum iavf_rx_desc_status_bits { - /* Note: These are predefined bit offsets */ - IAVF_RX_DESC_STATUS_DD_SHIFT = 0, - IAVF_RX_DESC_STATUS_EOF_SHIFT = 1, - IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT = 2, - IAVF_RX_DESC_STATUS_L3L4P_SHIFT = 3, - IAVF_RX_DESC_STATUS_CRCP_SHIFT = 4, - IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT = 5, /* 2 BITS */ - IAVF_RX_DESC_STATUS_TSYNVALID_SHIFT = 7, - /* Note: Bit 8 is reserved in X710 and XL710 */ - IAVF_RX_DESC_STATUS_EXT_UDP_0_SHIFT = 8, - IAVF_RX_DESC_STATUS_UMBCAST_SHIFT = 9, /* 2 BITS */ - IAVF_RX_DESC_STATUS_FLM_SHIFT = 11, - IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT = 12, /* 2 BITS */ - IAVF_RX_DESC_STATUS_LPBK_SHIFT = 14, - IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT = 15, - IAVF_RX_DESC_STATUS_RESERVED_SHIFT = 16, /* 2 BITS */ - /* Note: For non-tunnel packets INT_UDP_0 is the right status for - * UDP header - */ - IAVF_RX_DESC_STATUS_INT_UDP_0_SHIFT = 18, - IAVF_RX_DESC_STATUS_LAST /* this entry must be last!!! */ -}; - -#define IAVF_RXD_QW1_STATUS_SHIFT 0 -#define IAVF_RXD_QW1_STATUS_MASK ((BIT(IAVF_RX_DESC_STATUS_LAST) - 1) \ - << IAVF_RXD_QW1_STATUS_SHIFT) +/** + * struct iavf_rx_desc - Receive descriptor (both legacy and flexible) + * @qw0: quad word 0 fields: + * Legacy: Descriptor Type; Mirror ID; L2TAG1P (S-TAG); Filter Status + * Flex: Descriptor Type; Mirror ID; UMBCAST; Packet Type; Flexible Flags + * Section 0; Packet Length; Header Length; Split Header Flag; + * Flexible Flags section 1 / Extended Status + * @qw1: quad word 1 fields: + * Legacy: Status Field; Error Field; Packet Type; Packet Length (packet, + * header, Split Header Flag) + * Flex: Status / Error 0 Field; L2TAG1P (S-TAG); Flexible Metadata + * Container #0; Flexible Metadata Container #1 + * @qw2: quad word 2 fields: + * Legacy: Extended Status; 1st L2TAG2P (C-TAG); 2nd L2TAG2P (C-TAG) + * Flex: Status / Error 1 Field; Flexible Flags section 2; Timestamp Low; + * 1st L2TAG2 (C-TAG); 2nd L2TAG2 (C-TAG) + * @qw3: quad word 3 fields: + * Legacy: FD Filter ID / Flexible Bytes + * Flex: Flexible Metadata Container #2; Flexible Metadata Container #3; + * Flexible Metadata Container #4 / Timestamp High 0; Flexible + * Metadata Container #5 / Timestamp High 1; + */ +struct iavf_rx_desc { + aligned_le64 qw0; +/* The hash signature (RSS) */ +#define IAVF_RXD_LEGACY_RSS_M GENMASK_ULL(63, 32) +/* Stripped C-TAG VLAN from the receive packet */ +#define IAVF_RXD_LEGACY_L2TAG1_M GENMASK_ULL(33, 16) +/* Packet type */ +#define IAVF_RXD_FLEX_PTYPE_M GENMASK_ULL(25, 16) +/* Packet length */ +#define IAVF_RXD_FLEX_PKT_LEN_M GENMASK_ULL(45, 32) + + aligned_le64 qw1; +/* Descriptor done indication flag. */ +#define IAVF_RXD_LEGACY_DD_M BIT(0) +/* End of packet. Set to 1 if this descriptor is the last one of the packet */ +#define IAVF_RXD_LEGACY_EOP_M BIT(1) +/* L2 TAG 1 presence indication */ +#define IAVF_RXD_LEGACY_L2TAG1P_M BIT(2) +/* Detectable L3 and L4 integrity check is processed by the HW */ +#define IAVF_RXD_LEGACY_L3L4P_M BIT(3) +/* Set when an IPv6 packet contains a Destination Options Header or a Routing + * Header. + */ +#define IAVF_RXD_LEGACY_IPV6EXADD_M BIT(15) +/* Receive MAC Errors: CRC; Alignment; Oversize; Undersizes; Length error */ +#define IAVF_RXD_LEGACY_RXE_M BIT(19) +/* Checksum reports: + * - IPE: IP checksum error + * - L4E: L4 integrity error + * - EIPE: External IP header (tunneled packets) + */ +#define IAVF_RXD_LEGACY_IPE_M BIT(22) +#define IAVF_RXD_LEGACY_L4E_M BIT(23) +#define IAVF_RXD_LEGACY_EIPE_M BIT(24) +/* Set for packets that skip checksum calculation in pre-parser */ +#define IAVF_RXD_LEGACY_PPRS_M BIT(26) +/* Indicates the content in the Filter Status field */ +#define IAVF_RXD_LEGACY_FLTSTAT_M GENMASK_ULL(13, 12) +/* Packet type */ +#define IAVF_RXD_LEGACY_PTYPE_M GENMASK_ULL(37, 30) +/* Packet length */ +#define IAVF_RXD_LEGACY_LENGTH_M GENMASK_ULL(51, 38) +/* Descriptor done indication flag */ +#define IAVF_RXD_FLEX_DD_M BIT(0) +/* End of packet. Set to 1 if this descriptor is the last one of the packet */ +#define IAVF_RXD_FLEX_EOP_M BIT(1) +/* Detectable L3 and L4 integrity check is processed by the HW */ +#define IAVF_RXD_FLEX_L3L4P_M BIT(3) +/* Checksum reports: + * - IPE: IP checksum error + * - L4E: L4 integrity error + * - EIPE: External IP header (tunneled packets) + * - EUDPE: External UDP checksum error (tunneled packets) + */ +#define IAVF_RXD_FLEX_XSUM_IPE_M BIT(4) +#define IAVF_RXD_FLEX_XSUM_L4E_M BIT(5) +#define IAVF_RXD_FLEX_XSUM_EIPE_M BIT(6) +#define IAVF_RXD_FLEX_XSUM_EUDPE_M BIT(7) +/* Set when an IPv6 packet contains a Destination Options Header or a Routing + * Header. + */ +#define IAVF_RXD_FLEX_IPV6EXADD_M BIT(9) +/* Receive MAC Errors: CRC; Alignment; Oversize; Undersizes; Length error */ +#define IAVF_RXD_FLEX_RXE_M BIT(10) +/* Indicates that the RSS/HASH result is valid */ +#define IAVF_RXD_FLEX_RSS_VALID_M BIT(12) +/* L2 TAG 1 presence indication */ +#define IAVF_RXD_FLEX_L2TAG1P_M BIT(13) +/* Stripped L2 Tag from the receive packet */ +#define IAVF_RXD_FLEX_L2TAG1_M GENMASK_ULL(31, 16) +/* The hash signature (RSS) */ +#define IAVF_RXD_FLEX_RSS_HASH_M GENMASK_ULL(63, 32) + + aligned_le64 qw2; +/* L2 Tag 2 Presence */ +#define IAVF_RXD_LEGACY_L2TAG2P_M BIT(0) +/* Stripped S-TAG VLAN from the receive packet */ +#define IAVF_RXD_LEGACY_L2TAG2_M GENMASK_ULL(63, 32) +/* Stripped S-TAG VLAN from the receive packet */ +#define IAVF_RXD_FLEX_L2TAG2_2_M GENMASK_ULL(63, 48) +/* The packet is a UDP tunneled packet */ +#define IAVF_RXD_FLEX_NAT_M BIT(4) +/* L2 Tag 2 Presence */ +#define IAVF_RXD_FLEX_L2TAG2P_M BIT(11) + aligned_le64 qw3; +#define IAVF_RXD_FLEX_QW3_TSTAMP_HIGH_M GENMASK_ULL(63, 32) +} __aligned(4 * sizeof(__le64)); +static_assert(sizeof(struct iavf_rx_desc) == 32); #define IAVF_RXD_QW1_STATUS_TSYNINDX_SHIFT IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT #define IAVF_RXD_QW1_STATUS_TSYNINDX_MASK (0x3UL << \ @@ -300,22 +304,6 @@ enum iavf_rx_desc_fltstat_values { IAVF_RX_DESC_FLTSTAT_RSS_HASH = 3, }; -#define IAVF_RXD_QW1_ERROR_SHIFT 19 -#define IAVF_RXD_QW1_ERROR_MASK (0xFFUL << IAVF_RXD_QW1_ERROR_SHIFT) - -enum iavf_rx_desc_error_bits { - /* Note: These are predefined bit offsets */ - IAVF_RX_DESC_ERROR_RXE_SHIFT = 0, - IAVF_RX_DESC_ERROR_RECIPE_SHIFT = 1, - IAVF_RX_DESC_ERROR_HBO_SHIFT = 2, - IAVF_RX_DESC_ERROR_L3L4E_SHIFT = 3, /* 3 BITS */ - IAVF_RX_DESC_ERROR_IPE_SHIFT = 3, - IAVF_RX_DESC_ERROR_L4E_SHIFT = 4, - IAVF_RX_DESC_ERROR_EIPE_SHIFT = 5, - IAVF_RX_DESC_ERROR_OVERSIZE_SHIFT = 6, - IAVF_RX_DESC_ERROR_PPRS_SHIFT = 7 -}; - enum iavf_rx_desc_error_l3l4e_fcoe_masks { IAVF_RX_DESC_ERROR_L3L4E_NONE = 0, IAVF_RX_DESC_ERROR_L3L4E_PROT = 1, @@ -324,101 +312,6 @@ enum iavf_rx_desc_error_l3l4e_fcoe_masks { IAVF_RX_DESC_ERROR_L3L4E_DMAC_WARN = 4 }; -#define IAVF_RXD_QW1_PTYPE_SHIFT 30 -#define IAVF_RXD_QW1_PTYPE_MASK (0xFFULL << IAVF_RXD_QW1_PTYPE_SHIFT) - -/* Packet type non-ip values */ -enum iavf_rx_l2_ptype { - IAVF_RX_PTYPE_L2_RESERVED = 0, - IAVF_RX_PTYPE_L2_MAC_PAY2 = 1, - IAVF_RX_PTYPE_L2_TIMESYNC_PAY2 = 2, - IAVF_RX_PTYPE_L2_FIP_PAY2 = 3, - IAVF_RX_PTYPE_L2_OUI_PAY2 = 4, - IAVF_RX_PTYPE_L2_MACCNTRL_PAY2 = 5, - IAVF_RX_PTYPE_L2_LLDP_PAY2 = 6, - IAVF_RX_PTYPE_L2_ECP_PAY2 = 7, - IAVF_RX_PTYPE_L2_EVB_PAY2 = 8, - IAVF_RX_PTYPE_L2_QCN_PAY2 = 9, - IAVF_RX_PTYPE_L2_EAPOL_PAY2 = 10, - IAVF_RX_PTYPE_L2_ARP = 11, - IAVF_RX_PTYPE_L2_FCOE_PAY3 = 12, - IAVF_RX_PTYPE_L2_FCOE_FCDATA_PAY3 = 13, - IAVF_RX_PTYPE_L2_FCOE_FCRDY_PAY3 = 14, - IAVF_RX_PTYPE_L2_FCOE_FCRSP_PAY3 = 15, - IAVF_RX_PTYPE_L2_FCOE_FCOTHER_PA = 16, - IAVF_RX_PTYPE_L2_FCOE_VFT_PAY3 = 17, - IAVF_RX_PTYPE_L2_FCOE_VFT_FCDATA = 18, - IAVF_RX_PTYPE_L2_FCOE_VFT_FCRDY = 19, - IAVF_RX_PTYPE_L2_FCOE_VFT_FCRSP = 20, - IAVF_RX_PTYPE_L2_FCOE_VFT_FCOTHER = 21, - IAVF_RX_PTYPE_GRENAT4_MAC_PAY3 = 58, - IAVF_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4 = 87, - IAVF_RX_PTYPE_GRENAT6_MAC_PAY3 = 124, - IAVF_RX_PTYPE_GRENAT6_MACVLAN_IPV6_ICMP_PAY4 = 153 -}; - -struct iavf_rx_ptype_decoded { - u32 known:1; - u32 outer_ip:1; - u32 outer_ip_ver:1; - 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 iavf_rx_ptype_outer_ip { - IAVF_RX_PTYPE_OUTER_L2 = 0, - IAVF_RX_PTYPE_OUTER_IP = 1 -}; - -enum iavf_rx_ptype_outer_ip_ver { - IAVF_RX_PTYPE_OUTER_NONE = 0, - IAVF_RX_PTYPE_OUTER_IPV4 = 0, - IAVF_RX_PTYPE_OUTER_IPV6 = 1 -}; - -enum iavf_rx_ptype_outer_fragmented { - IAVF_RX_PTYPE_NOT_FRAG = 0, - IAVF_RX_PTYPE_FRAG = 1 -}; - -enum iavf_rx_ptype_tunnel_type { - IAVF_RX_PTYPE_TUNNEL_NONE = 0, - IAVF_RX_PTYPE_TUNNEL_IP_IP = 1, - IAVF_RX_PTYPE_TUNNEL_IP_GRENAT = 2, - IAVF_RX_PTYPE_TUNNEL_IP_GRENAT_MAC = 3, - IAVF_RX_PTYPE_TUNNEL_IP_GRENAT_MAC_VLAN = 4, -}; - -enum iavf_rx_ptype_tunnel_end_prot { - IAVF_RX_PTYPE_TUNNEL_END_NONE = 0, - IAVF_RX_PTYPE_TUNNEL_END_IPV4 = 1, - IAVF_RX_PTYPE_TUNNEL_END_IPV6 = 2, -}; - -enum iavf_rx_ptype_inner_prot { - IAVF_RX_PTYPE_INNER_PROT_NONE = 0, - IAVF_RX_PTYPE_INNER_PROT_UDP = 1, - IAVF_RX_PTYPE_INNER_PROT_TCP = 2, - IAVF_RX_PTYPE_INNER_PROT_SCTP = 3, - IAVF_RX_PTYPE_INNER_PROT_ICMP = 4, - IAVF_RX_PTYPE_INNER_PROT_TIMESYNC = 5 -}; - -enum iavf_rx_ptype_payload_layer { - IAVF_RX_PTYPE_PAYLOAD_LAYER_NONE = 0, - IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY2 = 1, - IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY3 = 2, - IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY4 = 3, -}; - -#define IAVF_RXD_QW1_LENGTH_PBUF_SHIFT 38 -#define IAVF_RXD_QW1_LENGTH_PBUF_MASK (0x3FFFULL << \ - IAVF_RXD_QW1_LENGTH_PBUF_SHIFT) - #define IAVF_RXD_QW1_LENGTH_HBUF_SHIFT 52 #define IAVF_RXD_QW1_LENGTH_HBUF_MASK (0x7FFULL << \ IAVF_RXD_QW1_LENGTH_HBUF_SHIFT) @@ -437,6 +330,8 @@ enum iavf_rx_desc_ext_status_bits { IAVF_RX_DESC_EXT_STATUS_PELONGB_SHIFT = 11, }; +#define IAVF_RX_DESC_EXT_STATUS_L2TAG2P_M BIT(IAVF_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT) + enum iavf_rx_desc_pe_status_bits { /* Note: These are predefined bit offsets */ IAVF_RX_DESC_PE_STATUS_QPID_SHIFT = 0, /* 18 BITS */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_types.h b/drivers/net/ethernet/intel/iavf/iavf_types.h new file mode 100644 index 000000000000..a095855122bf --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_types.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2024 Intel Corporation. */ + +#ifndef _IAVF_TYPES_H_ +#define _IAVF_TYPES_H_ + +#include "iavf_types.h" + +#include <linux/avf/virtchnl.h> +#include <linux/ptp_clock_kernel.h> + +/* structure used to queue PTP commands for processing */ +struct iavf_ptp_aq_cmd { + struct list_head list; + enum virtchnl_ops v_opcode:16; + u16 msglen; + u8 msg[] __counted_by(msglen); +}; + +struct iavf_ptp { + wait_queue_head_t phc_time_waitqueue; + struct virtchnl_ptp_caps hw_caps; + struct ptp_clock_info info; + struct ptp_clock *clock; + struct list_head aq_cmds; + u64 cached_phc_time; + unsigned long cached_phc_updated; + /* Lock protecting access to the AQ command list */ + struct mutex aq_cmd_lock; + struct kernel_hwtstamp_config hwtstamp_config; + bool phc_time_ready:1; +}; + +#endif /* _IAVF_TYPES_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 22f2df7c460b..a6f0e5990be2 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -1,7 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ +#include <linux/net/intel/libie/rx.h> + #include "iavf.h" +#include "iavf_ptp.h" #include "iavf_prototype.h" /** @@ -140,15 +143,19 @@ int iavf_send_vf_config_msg(struct iavf_adapter *adapter) VIRTCHNL_VF_OFFLOAD_WB_ON_ITR | VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 | VIRTCHNL_VF_OFFLOAD_ENCAP | + VIRTCHNL_VF_OFFLOAD_TC_U32 | VIRTCHNL_VF_OFFLOAD_VLAN_V2 | + VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC | VIRTCHNL_VF_OFFLOAD_CRC | VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM | VIRTCHNL_VF_OFFLOAD_REQ_QUEUES | + VIRTCHNL_VF_CAP_PTP | VIRTCHNL_VF_OFFLOAD_ADQ | VIRTCHNL_VF_OFFLOAD_USO | VIRTCHNL_VF_OFFLOAD_FDIR_PF | VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF | - VIRTCHNL_VF_CAP_ADV_LINK_SPEED; + VIRTCHNL_VF_CAP_ADV_LINK_SPEED | + VIRTCHNL_VF_OFFLOAD_QOS; adapter->current_op = VIRTCHNL_OP_GET_VF_RESOURCES; adapter->aq_required &= ~IAVF_FLAG_AQ_GET_CONFIG; @@ -173,6 +180,54 @@ int iavf_send_vf_offload_vlan_v2_msg(struct iavf_adapter *adapter) NULL, 0); } +int iavf_send_vf_supported_rxdids_msg(struct iavf_adapter *adapter) +{ + adapter->aq_required &= ~IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS; + + if (!IAVF_RXDID_ALLOWED(adapter)) + return -EOPNOTSUPP; + + adapter->current_op = VIRTCHNL_OP_GET_SUPPORTED_RXDIDS; + + return iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_SUPPORTED_RXDIDS, + NULL, 0); +} + +/** + * iavf_send_vf_ptp_caps_msg - Send request for PTP capabilities + * @adapter: private adapter structure + * + * Send the VIRTCHNL_OP_1588_PTP_GET_CAPS command to the PF to request the PTP + * capabilities available to this device. This includes the following + * potential access: + * + * * READ_PHC - access to read the PTP hardware clock time + * * RX_TSTAMP - access to request Rx timestamps on all received packets + * + * The PF will reply with the same opcode a filled out copy of the + * virtchnl_ptp_caps structure which defines the specifics of which features + * are accessible to this device. + * + * Return: 0 if success, error code otherwise. + */ +int iavf_send_vf_ptp_caps_msg(struct iavf_adapter *adapter) +{ + struct virtchnl_ptp_caps hw_caps = { + .caps = VIRTCHNL_1588_PTP_CAP_READ_PHC | + VIRTCHNL_1588_PTP_CAP_RX_TSTAMP + }; + + adapter->aq_required &= ~IAVF_FLAG_AQ_GET_PTP_CAPS; + + if (!IAVF_PTP_ALLOWED(adapter)) + return -EOPNOTSUPP; + + adapter->current_op = VIRTCHNL_OP_1588_PTP_GET_CAPS; + + return iavf_send_pf_msg(adapter, VIRTCHNL_OP_1588_PTP_GET_CAPS, + (u8 *)&hw_caps, sizeof(hw_caps)); +} + /** * iavf_validate_num_queues * @adapter: adapter structure @@ -259,6 +314,40 @@ int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter) return err; } +int iavf_get_vf_supported_rxdids(struct iavf_adapter *adapter) +{ + struct iavf_arq_event_info event; + u64 rxdids; + int err; + + event.msg_buf = (u8 *)&rxdids; + event.buf_len = sizeof(rxdids); + + err = iavf_poll_virtchnl_msg(&adapter->hw, &event, + VIRTCHNL_OP_GET_SUPPORTED_RXDIDS); + if (!err) + adapter->supp_rxdids = rxdids; + + return err; +} + +int iavf_get_vf_ptp_caps(struct iavf_adapter *adapter) +{ + struct virtchnl_ptp_caps caps = {}; + struct iavf_arq_event_info event; + int err; + + event.msg_buf = (u8 *)∩︀ + event.buf_len = sizeof(caps); + + err = iavf_poll_virtchnl_msg(&adapter->hw, &event, + VIRTCHNL_OP_1588_PTP_GET_CAPS); + if (!err) + adapter->ptp.hw_caps = caps; + + return err; +} + /** * iavf_configure_queues * @adapter: adapter structure @@ -268,13 +357,14 @@ int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter) void iavf_configure_queues(struct iavf_adapter *adapter) { struct virtchnl_vsi_queue_config_info *vqci; - int i, max_frame = adapter->vf_res->max_mtu; int pairs = adapter->num_active_queues; struct virtchnl_queue_pair_info *vqpi; + u32 i, max_frame; + u8 rx_flags = 0; size_t len; - if (max_frame > IAVF_MAX_RXBUFFER || !max_frame) - max_frame = IAVF_MAX_RXBUFFER; + max_frame = LIBIE_MAX_RX_FRM_LEN(adapter->rx_rings->pp->p.offset); + max_frame = min_not_zero(adapter->vf_res->max_mtu, max_frame); if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { /* bail because we already have a command pending */ @@ -288,10 +378,8 @@ void iavf_configure_queues(struct iavf_adapter *adapter) if (!vqci) return; - /* Limit maximum frame size when jumbo frames is not enabled */ - if (!(adapter->flags & IAVF_FLAG_LEGACY_RX) && - (adapter->netdev->mtu <= ETH_DATA_LEN)) - max_frame = IAVF_RXBUFFER_1536 - NET_IP_ALIGN; + if (iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP)) + rx_flags |= VIRTCHNL_PTP_RX_TSTAMP; vqci->vsi_id = adapter->vsi_res->vsi_id; vqci->num_queue_pairs = pairs; @@ -309,12 +397,13 @@ void iavf_configure_queues(struct iavf_adapter *adapter) vqpi->rxq.ring_len = adapter->rx_rings[i].count; vqpi->rxq.dma_ring_addr = adapter->rx_rings[i].dma; vqpi->rxq.max_pkt_size = max_frame; - vqpi->rxq.databuffer_size = - ALIGN(adapter->rx_rings[i].rx_buf_len, - BIT_ULL(IAVF_RXQ_CTX_DBUFF_SHIFT)); + vqpi->rxq.databuffer_size = adapter->rx_rings[i].rx_buf_len; + if (IAVF_RXDID_ALLOWED(adapter)) + vqpi->rxq.rxdid = adapter->rxdid; if (CRC_OFFLOAD_ALLOWED(adapter)) vqpi->rxq.crc_disable = !!(adapter->netdev->features & NETIF_F_RXFCS); + vqpi->rxq.flags = rx_flags; vqpi++; } @@ -1405,6 +1494,67 @@ void iavf_disable_vlan_insertion_v2(struct iavf_adapter *adapter, u16 tpid) VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2); } +#if IS_ENABLED(CONFIG_PTP_1588_CLOCK) +/** + * iavf_virtchnl_send_ptp_cmd - Send one queued PTP command + * @adapter: adapter private structure + * + * De-queue one PTP command request and send the command message to the PF. + * Clear IAVF_FLAG_AQ_SEND_PTP_CMD if no more messages are left to send. + */ +void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter) +{ + struct iavf_ptp_aq_cmd *cmd; + int err; + + if (!adapter->ptp.clock) { + /* This shouldn't be possible to hit, since no messages should + * be queued if PTP is not initialized. + */ + pci_err(adapter->pdev, "PTP is not initialized\n"); + adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD; + return; + } + + mutex_lock(&adapter->ptp.aq_cmd_lock); + cmd = list_first_entry_or_null(&adapter->ptp.aq_cmds, + struct iavf_ptp_aq_cmd, list); + if (!cmd) { + /* no further PTP messages to send */ + adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD; + goto out_unlock; + } + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + pci_err(adapter->pdev, + "Cannot send PTP command %d, command %d pending\n", + cmd->v_opcode, adapter->current_op); + goto out_unlock; + } + + err = iavf_send_pf_msg(adapter, cmd->v_opcode, cmd->msg, cmd->msglen); + if (!err) { + /* Command was sent without errors, so we can remove it from + * the list and discard it. + */ + list_del(&cmd->list); + kfree(cmd); + } else { + /* We failed to send the command, try again next cycle */ + pci_err(adapter->pdev, "Failed to send PTP command %d\n", + cmd->v_opcode); + } + + if (list_empty(&adapter->ptp.aq_cmds)) + /* no further PTP messages to send */ + adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD; + +out_unlock: + mutex_unlock(&adapter->ptp.aq_cmd_lock); +} +#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ + /** * iavf_print_link_message - print link up or down * @adapter: adapter structure @@ -1512,6 +1662,130 @@ iavf_set_adapter_link_speed_from_vpe(struct iavf_adapter *adapter, } /** + * iavf_get_qos_caps - get qos caps support + * @adapter: iavf adapter struct instance + * + * This function requests PF for Supported QoS Caps. + */ +void iavf_get_qos_caps(struct iavf_adapter *adapter) +{ + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, + "Cannot get qos caps, command %d pending\n", + adapter->current_op); + return; + } + + adapter->current_op = VIRTCHNL_OP_GET_QOS_CAPS; + adapter->aq_required &= ~IAVF_FLAG_AQ_GET_QOS_CAPS; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_QOS_CAPS, NULL, 0); +} + +/** + * iavf_set_quanta_size - set quanta size of queue chunk + * @adapter: iavf adapter struct instance + * @quanta_size: quanta size in bytes + * @queue_index: starting index of queue chunk + * @num_queues: number of queues in the queue chunk + * + * This function requests PF to set quanta size of queue chunk + * starting at queue_index. + */ +static void +iavf_set_quanta_size(struct iavf_adapter *adapter, u16 quanta_size, + u16 queue_index, u16 num_queues) +{ + struct virtchnl_quanta_cfg quanta_cfg; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, + "Cannot set queue quanta size, command %d pending\n", + adapter->current_op); + return; + } + + adapter->current_op = VIRTCHNL_OP_CONFIG_QUANTA; + quanta_cfg.quanta_size = quanta_size; + quanta_cfg.queue_select.type = VIRTCHNL_QUEUE_TYPE_TX; + quanta_cfg.queue_select.start_queue_id = queue_index; + quanta_cfg.queue_select.num_queues = num_queues; + adapter->aq_required &= ~IAVF_FLAG_AQ_CFG_QUEUES_QUANTA_SIZE; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_QUANTA, + (u8 *)&quanta_cfg, sizeof(quanta_cfg)); +} + +/** + * iavf_cfg_queues_quanta_size - configure quanta size of queues + * @adapter: adapter structure + * + * Request that the PF configure quanta size of allocated queues. + **/ +void iavf_cfg_queues_quanta_size(struct iavf_adapter *adapter) +{ + int quanta_size = IAVF_DEFAULT_QUANTA_SIZE; + + /* Set Queue Quanta Size to default */ + iavf_set_quanta_size(adapter, quanta_size, 0, + adapter->num_active_queues); +} + +/** + * iavf_cfg_queues_bw - configure bandwidth of allocated queues + * @adapter: iavf adapter structure instance + * + * This function requests PF to configure queue bandwidth of allocated queues + */ +void iavf_cfg_queues_bw(struct iavf_adapter *adapter) +{ + struct virtchnl_queues_bw_cfg *qs_bw_cfg; + struct net_shaper *q_shaper; + int qs_to_update = 0; + int i, inx = 0; + size_t len; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, + "Cannot set tc queue bw, command %d pending\n", + adapter->current_op); + return; + } + + for (i = 0; i < adapter->num_active_queues; i++) { + if (adapter->tx_rings[i].q_shaper_update) + qs_to_update++; + } + len = struct_size(qs_bw_cfg, cfg, qs_to_update); + qs_bw_cfg = kzalloc(len, GFP_KERNEL); + if (!qs_bw_cfg) + return; + + qs_bw_cfg->vsi_id = adapter->vsi.id; + qs_bw_cfg->num_queues = qs_to_update; + + for (i = 0; i < adapter->num_active_queues; i++) { + struct iavf_ring *tx_ring = &adapter->tx_rings[i]; + + q_shaper = &tx_ring->q_shaper; + if (tx_ring->q_shaper_update) { + qs_bw_cfg->cfg[inx].queue_id = i; + qs_bw_cfg->cfg[inx].shaper.peak = q_shaper->bw_max; + qs_bw_cfg->cfg[inx].shaper.committed = q_shaper->bw_min; + qs_bw_cfg->cfg[inx].tc = 0; + inx++; + } + } + + adapter->current_op = VIRTCHNL_OP_CONFIG_QUEUE_BW; + adapter->aq_required &= ~IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_QUEUE_BW, + (u8 *)qs_bw_cfg, len); + kfree(qs_bw_cfg); +} + +/** * iavf_enable_channels * @adapter: adapter structure * @@ -1966,8 +2240,8 @@ static void iavf_activate_fdir_filters(struct iavf_adapter *adapter) * list on PF is already cleared after a reset */ list_del(&f->list); + iavf_dec_fdir_active_fltr(adapter, f); kfree(f); - adapter->fdir_active_fltr--; } } spin_unlock_bh(&adapter->fdir_fltr_lock); @@ -1977,6 +2251,37 @@ static void iavf_activate_fdir_filters(struct iavf_adapter *adapter) } /** + * iavf_virtchnl_ptp_get_time - Respond to VIRTCHNL_OP_1588_PTP_GET_TIME + * @adapter: private adapter structure + * @data: the message from the PF + * @len: length of the message from the PF + * + * Handle the VIRTCHNL_OP_1588_PTP_GET_TIME message from the PF. This message + * is sent by the PF in response to the same op as a request from the VF. + * Extract the 64bit nanoseconds time from the message and store it in + * cached_phc_time. Then, notify any thread that is waiting for the update via + * the wait queue. + */ +static void iavf_virtchnl_ptp_get_time(struct iavf_adapter *adapter, + void *data, u16 len) +{ + struct virtchnl_phc_time *msg = data; + + if (len != sizeof(*msg)) { + dev_err_once(&adapter->pdev->dev, + "Invalid VIRTCHNL_OP_1588_PTP_GET_TIME from PF. Got size %u, expected %zu\n", + len, sizeof(*msg)); + return; + } + + adapter->ptp.cached_phc_time = msg->time; + adapter->ptp.cached_phc_updated = jiffies; + adapter->ptp.phc_time_ready = true; + + wake_up(&adapter->ptp.phc_time_waitqueue); +} + +/** * iavf_virtchnl_completion * @adapter: adapter structure * @v_opcode: opcode sent by PF @@ -2140,8 +2445,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, dev_err(&adapter->pdev->dev, "%s\n", msg); list_del(&fdir->list); + iavf_dec_fdir_active_fltr(adapter, fdir); kfree(fdir); - adapter->fdir_active_fltr--; } } spin_unlock_bh(&adapter->fdir_fltr_lock); @@ -2231,6 +2536,18 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC; break; + case VIRTCHNL_OP_GET_QOS_CAPS: + dev_warn(&adapter->pdev->dev, "Failed to Get Qos CAPs, error %s\n", + iavf_stat_str(&adapter->hw, v_retval)); + break; + case VIRTCHNL_OP_CONFIG_QUANTA: + dev_warn(&adapter->pdev->dev, "Failed to Config Quanta, error %s\n", + iavf_stat_str(&adapter->hw, v_retval)); + break; + case VIRTCHNL_OP_CONFIG_QUEUE_BW: + dev_warn(&adapter->pdev->dev, "Failed to Config Queue BW, error %s\n", + iavf_stat_str(&adapter->hw, v_retval)); + break; default: dev_err(&adapter->pdev->dev, "PF returned error %d (%s) to our request %d\n", v_retval, iavf_stat_str(&adapter->hw, v_retval), @@ -2376,6 +2693,25 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, aq_required; } break; + case VIRTCHNL_OP_GET_SUPPORTED_RXDIDS: + if (msglen != sizeof(u64)) + return; + + adapter->supp_rxdids = *(u64 *)msg; + + break; + case VIRTCHNL_OP_1588_PTP_GET_CAPS: + if (msglen != sizeof(adapter->ptp.hw_caps)) + return; + + adapter->ptp.hw_caps = *(struct virtchnl_ptp_caps *)msg; + + /* process any state change needed due to new capabilities */ + iavf_ptp_process_caps(adapter); + break; + case VIRTCHNL_OP_1588_PTP_GET_TIME: + iavf_virtchnl_ptp_get_time(adapter, msg, msglen); + break; case VIRTCHNL_OP_ENABLE_QUEUES: /* enable transmits */ iavf_irq_enable(adapter, true); @@ -2456,8 +2792,12 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, list) { if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING) { if (add_fltr->status == VIRTCHNL_FDIR_SUCCESS) { - dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is added\n", - fdir->loc); + if (!iavf_is_raw_fdir(fdir)) + dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is added\n", + fdir->loc); + else + dev_info(&adapter->pdev->dev, "Flow Director filter (raw) for TC handle %x is added\n", + TC_U32_USERHTID(fdir->cls_u32_handle)); fdir->state = IAVF_FDIR_FLTR_ACTIVE; fdir->flow_id = add_fltr->flow_id; } else { @@ -2465,8 +2805,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, add_fltr->status); iavf_print_fdir_fltr(adapter, fdir); list_del(&fdir->list); + iavf_dec_fdir_active_fltr(adapter, fdir); kfree(fdir); - adapter->fdir_active_fltr--; } } } @@ -2484,11 +2824,15 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, 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); + if (!iavf_is_raw_fdir(fdir)) + dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is deleted\n", + fdir->loc); + else + dev_info(&adapter->pdev->dev, "Flow Director filter (raw) for TC handle %x is deleted\n", + TC_U32_USERHTID(fdir->cls_u32_handle)); list_del(&fdir->list); + iavf_dec_fdir_active_fltr(adapter, fdir); kfree(fdir); - adapter->fdir_active_fltr--; } else { fdir->state = IAVF_FDIR_FLTR_ACTIVE; dev_info(&adapter->pdev->dev, "Failed to delete Flow Director filter with status: %d\n", @@ -2565,6 +2909,24 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, if (!v_retval) iavf_netdev_features_vlan_strip_set(netdev, false); break; + case VIRTCHNL_OP_GET_QOS_CAPS: { + u16 len = struct_size(adapter->qos_caps, cap, + IAVF_MAX_QOS_TC_NUM); + + memcpy(adapter->qos_caps, msg, min(msglen, len)); + + adapter->aq_required |= IAVF_FLAG_AQ_CFG_QUEUES_QUANTA_SIZE; + } + break; + case VIRTCHNL_OP_CONFIG_QUANTA: + break; + case VIRTCHNL_OP_CONFIG_QUEUE_BW: { + int i; + /* shaper configuration is successful for all queues */ + for (i = 0; i < adapter->num_active_queues; i++) + adapter->tx_rings[i].q_shaper_update = false; + } + break; default: if (adapter->current_op && (v_opcode != adapter->current_op)) dev_warn(&adapter->pdev->dev, "Expected response %d from PF, received %d\n", diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index cddd82d4ca0f..9e0d9f710441 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -5,6 +5,7 @@ # Makefile for the Intel(R) Ethernet Connection E800 Series Linux Driver # +subdir-ccflags-y += -I$(src) obj-$(CONFIG_ICE) += ice.o ice-y := ice_main.o \ @@ -27,8 +28,14 @@ ice-y := ice_main.o \ ice_vlan_mode.o \ ice_flex_pipe.o \ ice_flow.o \ + ice_parser.o \ + ice_parser_rt.o \ ice_idc.o \ - ice_devlink.o \ + devlink/devlink.o \ + devlink/health.o \ + devlink/port.o \ + ice_sf_eth.o \ + ice_sf_vsi_vlan_ops.o \ ice_ddp.o \ ice_fw_update.o \ ice_lag.o \ @@ -36,7 +43,8 @@ ice-y := ice_main.o \ ice_repr.o \ ice_tc_lib.o \ ice_fwlog.o \ - ice_debugfs.o + ice_debugfs.o \ + ice_adapter.o ice-$(CONFIG_PCI_IOV) += \ ice_sriov.o \ ice_virtchnl.o \ diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c index b516e42b41f0..4af60e2f37df 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c @@ -5,12 +5,12 @@ #include "ice.h" #include "ice_lib.h" -#include "ice_devlink.h" +#include "devlink.h" +#include "port.h" #include "ice_eswitch.h" #include "ice_fw_update.h" #include "ice_dcb_lib.h" - -static int ice_active_port_option = -1; +#include "ice_sf_eth.h" /* context for devlink info version reporting */ struct ice_info_ctx { @@ -368,14 +368,18 @@ static int ice_devlink_info_get(struct devlink *devlink, } break; case ICE_VERSION_RUNNING: - err = devlink_info_version_running_put(req, key, ctx->buf); + err = devlink_info_version_running_put_ext(req, key, + ctx->buf, + DEVLINK_INFO_VERSION_TYPE_COMPONENT); if (err) { NL_SET_ERR_MSG_MOD(extack, "Unable to set running version"); goto out_free_ctx; } break; case ICE_VERSION_STORED: - err = devlink_info_version_stored_put(req, key, ctx->buf); + err = devlink_info_version_stored_put_ext(req, key, + ctx->buf, + DEVLINK_INFO_VERSION_TYPE_COMPONENT); if (err) { NL_SET_ERR_MSG_MOD(extack, "Unable to set stored version"); goto out_free_ctx; @@ -478,17 +482,17 @@ ice_devlink_reload_down(struct devlink *devlink, bool netns_change, case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: if (ice_is_eswitch_mode_switchdev(pf)) { NL_SET_ERR_MSG_MOD(extack, - "Go to legacy mode before doing reinit\n"); + "Go to legacy mode before doing reinit"); return -EOPNOTSUPP; } if (ice_is_adq_active(pf)) { NL_SET_ERR_MSG_MOD(extack, - "Turn off ADQ before doing reinit\n"); + "Turn off ADQ before doing reinit"); return -EOPNOTSUPP; } if (ice_has_vfs(pf)) { NL_SET_ERR_MSG_MOD(extack, - "Remove all VFs before doing reinit\n"); + "Remove all VFs before doing reinit"); return -EOPNOTSUPP; } ice_devlink_reinit_down(pf); @@ -526,248 +530,153 @@ ice_devlink_reload_empr_finish(struct ice_pf *pf, } /** - * ice_devlink_port_opt_speed_str - convert speed to a string - * @speed: speed value - */ -static const char *ice_devlink_port_opt_speed_str(u8 speed) -{ - switch (speed & ICE_AQC_PORT_OPT_MAX_LANE_M) { - case ICE_AQC_PORT_OPT_MAX_LANE_100M: - return "0.1"; - case ICE_AQC_PORT_OPT_MAX_LANE_1G: - return "1"; - case ICE_AQC_PORT_OPT_MAX_LANE_2500M: - return "2.5"; - case ICE_AQC_PORT_OPT_MAX_LANE_5G: - return "5"; - case ICE_AQC_PORT_OPT_MAX_LANE_10G: - return "10"; - case ICE_AQC_PORT_OPT_MAX_LANE_25G: - return "25"; - case ICE_AQC_PORT_OPT_MAX_LANE_50G: - return "50"; - case ICE_AQC_PORT_OPT_MAX_LANE_100G: - return "100"; - } - - return "-"; -} - -#define ICE_PORT_OPT_DESC_LEN 50 -/** - * ice_devlink_port_options_print - Print available port split options - * @pf: the PF to print split port options + * ice_get_tx_topo_user_sel - Read user's choice from flash + * @pf: pointer to pf structure + * @layers: value read from flash will be saved here + * + * Reads user's preference for Tx Scheduler Topology Tree from PFA TLV. * - * Prints a table with available port split options and max port speeds + * Return: zero when read was successful, negative values otherwise. */ -static void ice_devlink_port_options_print(struct ice_pf *pf) +static int ice_get_tx_topo_user_sel(struct ice_pf *pf, uint8_t *layers) { - u8 i, j, options_count, cnt, speed, pending_idx, active_idx; - struct ice_aqc_get_port_options_elem *options, *opt; - struct device *dev = ice_pf_to_dev(pf); - bool active_valid, pending_valid; - char desc[ICE_PORT_OPT_DESC_LEN]; - const char *str; - int status; + struct ice_aqc_nvm_tx_topo_user_sel usr_sel = {}; + struct ice_hw *hw = &pf->hw; + int err; - options = kcalloc(ICE_AQC_PORT_OPT_MAX * ICE_MAX_PORT_PER_PCI_DEV, - sizeof(*options), GFP_KERNEL); - if (!options) - return; + err = ice_acquire_nvm(hw, ICE_RES_READ); + if (err) + return err; - for (i = 0; i < ICE_MAX_PORT_PER_PCI_DEV; i++) { - opt = options + i * ICE_AQC_PORT_OPT_MAX; - options_count = ICE_AQC_PORT_OPT_MAX; - active_valid = 0; + err = ice_aq_read_nvm(hw, ICE_AQC_NVM_TX_TOPO_MOD_ID, 0, + sizeof(usr_sel), &usr_sel, true, true, NULL); + if (err) + goto exit_release_res; - status = ice_aq_get_port_options(&pf->hw, opt, &options_count, - i, true, &active_idx, - &active_valid, &pending_idx, - &pending_valid); - if (status) { - dev_dbg(dev, "Couldn't read port option for port %d, err %d\n", - i, status); - goto err; - } - } + if (usr_sel.data & ICE_AQC_NVM_TX_TOPO_USER_SEL) + *layers = ICE_SCHED_5_LAYERS; + else + *layers = ICE_SCHED_9_LAYERS; - dev_dbg(dev, "Available port split options and max port speeds (Gbps):\n"); - dev_dbg(dev, "Status Split Quad 0 Quad 1\n"); - dev_dbg(dev, " count L0 L1 L2 L3 L4 L5 L6 L7\n"); +exit_release_res: + ice_release_nvm(hw); - for (i = 0; i < options_count; i++) { - cnt = 0; + return err; +} - if (i == ice_active_port_option) - str = "Active"; - else if ((i == pending_idx) && pending_valid) - str = "Pending"; - else - str = ""; +/** + * ice_update_tx_topo_user_sel - Save user's preference in flash + * @pf: pointer to pf structure + * @layers: value to be saved in flash + * + * Variable "layers" defines user's preference about number of layers in Tx + * Scheduler Topology Tree. This choice should be stored in PFA TLV field + * and be picked up by driver, next time during init. + * + * Return: zero when save was successful, negative values otherwise. + */ +static int ice_update_tx_topo_user_sel(struct ice_pf *pf, int layers) +{ + struct ice_aqc_nvm_tx_topo_user_sel usr_sel = {}; + struct ice_hw *hw = &pf->hw; + int err; - cnt += snprintf(&desc[cnt], ICE_PORT_OPT_DESC_LEN - cnt, - "%-8s", str); + err = ice_acquire_nvm(hw, ICE_RES_WRITE); + if (err) + return err; - cnt += snprintf(&desc[cnt], ICE_PORT_OPT_DESC_LEN - cnt, - "%-6u", options[i].pmd); + err = ice_aq_read_nvm(hw, ICE_AQC_NVM_TX_TOPO_MOD_ID, 0, + sizeof(usr_sel), &usr_sel, true, true, NULL); + if (err) + goto exit_release_res; - for (j = 0; j < ICE_MAX_PORT_PER_PCI_DEV; ++j) { - speed = options[i + j * ICE_AQC_PORT_OPT_MAX].max_lane_speed; - str = ice_devlink_port_opt_speed_str(speed); - cnt += snprintf(&desc[cnt], ICE_PORT_OPT_DESC_LEN - cnt, - "%3s ", str); - } + if (layers == ICE_SCHED_5_LAYERS) + usr_sel.data |= ICE_AQC_NVM_TX_TOPO_USER_SEL; + else + usr_sel.data &= ~ICE_AQC_NVM_TX_TOPO_USER_SEL; - dev_dbg(dev, "%s\n", desc); - } + err = ice_write_one_nvm_block(pf, ICE_AQC_NVM_TX_TOPO_MOD_ID, 2, + sizeof(usr_sel.data), &usr_sel.data, + true, NULL, NULL); +exit_release_res: + ice_release_nvm(hw); -err: - kfree(options); + return err; } /** - * ice_devlink_aq_set_port_option - Send set port option admin queue command - * @pf: the PF to print split port options - * @option_idx: selected port option - * @extack: extended netdev ack structure + * ice_devlink_tx_sched_layers_get - Get tx_scheduling_layers parameter + * @devlink: pointer to the devlink instance + * @id: the parameter ID to set + * @ctx: context to store the parameter value * - * Sends set port option admin queue command with selected port option and - * calls NVM write activate. + * Return: zero on success and negative value on failure. */ -static int -ice_devlink_aq_set_port_option(struct ice_pf *pf, u8 option_idx, - struct netlink_ext_ack *extack) +static int ice_devlink_tx_sched_layers_get(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) { - struct device *dev = ice_pf_to_dev(pf); - int status; - - status = ice_aq_set_port_option(&pf->hw, 0, true, option_idx); - if (status) { - dev_dbg(dev, "ice_aq_set_port_option, err %d aq_err %d\n", - status, pf->hw.adminq.sq_last_status); - NL_SET_ERR_MSG_MOD(extack, "Port split request failed"); - return -EIO; - } - - status = ice_acquire_nvm(&pf->hw, ICE_RES_WRITE); - if (status) { - dev_dbg(dev, "ice_acquire_nvm failed, err %d aq_err %d\n", - status, pf->hw.adminq.sq_last_status); - NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore"); - return -EIO; - } - - status = ice_nvm_write_activate(&pf->hw, ICE_AQC_NVM_ACTIV_REQ_EMPR, NULL); - if (status) { - dev_dbg(dev, "ice_nvm_write_activate failed, err %d aq_err %d\n", - status, pf->hw.adminq.sq_last_status); - NL_SET_ERR_MSG_MOD(extack, "Port split request failed to save data"); - ice_release_nvm(&pf->hw); - return -EIO; - } + struct ice_pf *pf = devlink_priv(devlink); + int err; - ice_release_nvm(&pf->hw); + err = ice_get_tx_topo_user_sel(pf, &ctx->val.vu8); + if (err) + return err; - NL_SET_ERR_MSG_MOD(extack, "Reboot required to finish port split"); return 0; } /** - * ice_devlink_port_split - .port_split devlink handler - * @devlink: devlink instance structure - * @port: devlink port structure - * @count: number of ports to split to - * @extack: extended netdev ack structure - * - * Callback for the devlink .port_split operation. - * - * Unfortunately, the devlink expression of available options is limited - * to just a number, so search for an FW port option which supports - * the specified number. As there could be multiple FW port options with - * the same port split count, allow switching between them. When the same - * port split count request is issued again, switch to the next FW port - * option with the same port split count. + * ice_devlink_tx_sched_layers_set - Set tx_scheduling_layers parameter + * @devlink: pointer to the devlink instance + * @id: the parameter ID to set + * @ctx: context to get the parameter value + * @extack: netlink extended ACK structure * - * Return: zero on success or an error code on failure. + * Return: zero on success and negative value on failure. */ -static int -ice_devlink_port_split(struct devlink *devlink, struct devlink_port *port, - unsigned int count, struct netlink_ext_ack *extack) +static int ice_devlink_tx_sched_layers_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { - struct ice_aqc_get_port_options_elem options[ICE_AQC_PORT_OPT_MAX]; - u8 i, j, active_idx, pending_idx, new_option; struct ice_pf *pf = devlink_priv(devlink); - u8 option_count = ICE_AQC_PORT_OPT_MAX; - struct device *dev = ice_pf_to_dev(pf); - bool active_valid, pending_valid; - int status; - - status = ice_aq_get_port_options(&pf->hw, options, &option_count, - 0, true, &active_idx, &active_valid, - &pending_idx, &pending_valid); - if (status) { - dev_dbg(dev, "Couldn't read port split options, err = %d\n", - status); - NL_SET_ERR_MSG_MOD(extack, "Failed to get available port split options"); - return -EIO; - } - - new_option = ICE_AQC_PORT_OPT_MAX; - active_idx = pending_valid ? pending_idx : active_idx; - for (i = 1; i <= option_count; i++) { - /* In order to allow switching between FW port options with - * the same port split count, search for a new option starting - * from the active/pending option (with array wrap around). - */ - j = (active_idx + i) % option_count; - - if (count == options[j].pmd) { - new_option = j; - break; - } - } - - if (new_option == active_idx) { - dev_dbg(dev, "request to split: count: %u is already set and there are no other options\n", - count); - NL_SET_ERR_MSG_MOD(extack, "Requested split count is already set"); - ice_devlink_port_options_print(pf); - return -EINVAL; - } - - if (new_option == ICE_AQC_PORT_OPT_MAX) { - dev_dbg(dev, "request to split: count: %u not found\n", count); - NL_SET_ERR_MSG_MOD(extack, "Port split requested unsupported port config"); - ice_devlink_port_options_print(pf); - return -EINVAL; - } + int err; - status = ice_devlink_aq_set_port_option(pf, new_option, extack); - if (status) - return status; + err = ice_update_tx_topo_user_sel(pf, ctx->val.vu8); + if (err) + return err; - ice_devlink_port_options_print(pf); + NL_SET_ERR_MSG_MOD(extack, + "Tx scheduling layers have been changed on this device. You must do the PCI slot powercycle for the change to take effect."); return 0; } /** - * ice_devlink_port_unsplit - .port_unsplit devlink handler - * @devlink: devlink instance structure - * @port: devlink port structure - * @extack: extended netdev ack structure + * ice_devlink_tx_sched_layers_validate - Validate passed tx_scheduling_layers + * parameter value + * @devlink: unused pointer to devlink instance + * @id: the parameter ID to validate + * @val: value to validate + * @extack: netlink extended ACK structure * - * Callback for the devlink .port_unsplit operation. - * Calls ice_devlink_port_split with split count set to 1. - * There could be no FW option available with split count 1. + * Supported values are: + * - 5 - five layers Tx Scheduler Topology Tree + * - 9 - nine layers Tx Scheduler Topology Tree * - * Return: zero on success or an error code on failure. + * Return: zero when passed parameter value is supported. Negative value on + * error. */ -static int -ice_devlink_port_unsplit(struct devlink *devlink, struct devlink_port *port, - struct netlink_ext_ack *extack) +static int ice_devlink_tx_sched_layers_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) { - return ice_devlink_port_split(devlink, port, 1, extack); + if (val.vu8 != ICE_SCHED_5_LAYERS && val.vu8 != ICE_SCHED_9_LAYERS) { + NL_SET_ERR_MSG_MOD(extack, + "Wrong number of tx scheduler layers provided."); + return -EINVAL; + } + + return 0; } /** @@ -841,6 +750,7 @@ static void ice_traverse_tx_tree(struct devlink *devlink, struct ice_sched_node struct ice_sched_node *tc_node, struct ice_pf *pf) { struct devlink_rate *rate_node = NULL; + struct ice_dynamic_port *sf; struct ice_vf *vf; int i; @@ -852,6 +762,7 @@ static void ice_traverse_tx_tree(struct devlink *devlink, struct ice_sched_node /* create root node */ rate_node = devl_rate_node_create(devlink, node, node->name, NULL); } else if (node->vsi_handle && + pf->vsi[node->vsi_handle]->type == ICE_VSI_VF && pf->vsi[node->vsi_handle]->vf) { vf = pf->vsi[node->vsi_handle]->vf; if (!vf->devlink_port.devlink_rate) @@ -860,6 +771,16 @@ static void ice_traverse_tx_tree(struct devlink *devlink, struct ice_sched_node */ devl_rate_leaf_create(&vf->devlink_port, node, node->parent->rate_node); + } else if (node->vsi_handle && + pf->vsi[node->vsi_handle]->type == ICE_VSI_SF && + pf->vsi[node->vsi_handle]->sf) { + sf = pf->vsi[node->vsi_handle]->sf; + if (!sf->devlink_port.devlink_rate) + /* leaf nodes doesn't have children + * so we don't set rate_node + */ + devl_rate_leaf_create(&sf->devlink_port, node, + node->parent->rate_node); } else if (node->info.data.elem_type != ICE_AQC_ELEM_TYPE_LEAF && node->parent->rate_node) { rate_node = devl_rate_node_create(devlink, node, node->name, @@ -891,10 +812,8 @@ int ice_devlink_rate_init_tx_topology(struct devlink *devlink, struct ice_vsi *v tc_node = pi->root->children[0]; mutex_lock(&pi->sched_lock); - devl_lock(devlink); for (i = 0; i < tc_node->num_children; i++) ice_traverse_tx_tree(devlink, tc_node->children[i], tc_node, pf); - devl_unlock(devlink); mutex_unlock(&pi->sched_lock); return 0; @@ -1062,6 +981,9 @@ static int ice_devlink_rate_node_new(struct devlink_rate *rate_node, void **priv /* preallocate memory for ice_sched_node */ node = devm_kzalloc(ice_hw_to_dev(pi->hw), sizeof(*node), GFP_KERNEL); + if (!node) + return -ENOMEM; + *priv = node; return 0; @@ -1283,6 +1205,25 @@ static int ice_devlink_set_parent(struct devlink_rate *devlink_rate, return status; } +static void ice_set_min_max_msix(struct ice_pf *pf) +{ + struct devlink *devlink = priv_to_devlink(pf); + union devlink_param_value val; + int err; + + err = devl_param_driverinit_value_get(devlink, + DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN, + &val); + if (!err) + pf->msix.min = val.vu32; + + err = devl_param_driverinit_value_get(devlink, + DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX, + &val); + if (!err) + pf->msix.max = val.vu32; +} + /** * ice_devlink_reinit_up - do reinit of the given PF * @pf: pointer to the PF struct @@ -1290,18 +1231,25 @@ static int ice_devlink_set_parent(struct devlink_rate *devlink_rate, static int ice_devlink_reinit_up(struct ice_pf *pf) { struct ice_vsi *vsi = ice_get_main_vsi(pf); - struct ice_vsi_cfg_params params; int err; + err = ice_init_hw(&pf->hw); + if (err) { + dev_err(ice_pf_to_dev(pf), "ice_init_hw failed: %d\n", err); + return err; + } + + /* load MSI-X values */ + ice_set_min_max_msix(pf); + err = ice_init_dev(pf); if (err) - return err; + goto unroll_hw_init; - params = ice_vsi_to_params(vsi); - params.flags = ICE_VSI_FLAG_INIT; + vsi->flags = ICE_VSI_FLAG_INIT; rtnl_lock(); - err = ice_vsi_cfg(vsi, ¶ms); + err = ice_vsi_cfg(vsi); rtnl_unlock(); if (err) goto err_vsi_cfg; @@ -1319,6 +1267,8 @@ err_load: rtnl_unlock(); err_vsi_cfg: ice_deinit_dev(pf); +unroll_hw_init: + ice_deinit_hw(&pf->hw); return err; } @@ -1378,37 +1328,51 @@ static const struct devlink_ops ice_devlink_ops = { .rate_leaf_parent_set = ice_devlink_set_parent, .rate_node_parent_set = ice_devlink_set_parent, + + .port_new = ice_devlink_port_new, }; +static const struct devlink_ops ice_sf_devlink_ops; + static int ice_devlink_enable_roce_get(struct devlink *devlink, u32 id, struct devlink_param_gset_ctx *ctx) { struct ice_pf *pf = devlink_priv(devlink); + struct iidc_rdma_core_dev_info *cdev; + + cdev = pf->cdev_info; + if (!cdev) + return -ENODEV; - ctx->val.vbool = pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2 ? true : false; + ctx->val.vbool = !!(cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_ROCEV2); return 0; } -static int -ice_devlink_enable_roce_set(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) +static int ice_devlink_enable_roce_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct ice_pf *pf = devlink_priv(devlink); + struct iidc_rdma_core_dev_info *cdev; bool roce_ena = ctx->val.vbool; int ret; + cdev = pf->cdev_info; + if (!cdev) + return -ENODEV; + if (!roce_ena) { ice_unplug_aux_dev(pf); - pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_ROCEV2; + cdev->rdma_protocol &= ~IIDC_RDMA_PROTOCOL_ROCEV2; return 0; } - pf->rdma_mode |= IIDC_RDMA_PROTOCOL_ROCEV2; + cdev->rdma_protocol |= IIDC_RDMA_PROTOCOL_ROCEV2; ret = ice_plug_aux_dev(pf); if (ret) - pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_ROCEV2; + cdev->rdma_protocol &= ~IIDC_RDMA_PROTOCOL_ROCEV2; return ret; } @@ -1419,11 +1383,16 @@ ice_devlink_enable_roce_validate(struct devlink *devlink, u32 id, struct netlink_ext_ack *extack) { struct ice_pf *pf = devlink_priv(devlink); + struct iidc_rdma_core_dev_info *cdev; + + cdev = pf->cdev_info; + if (!cdev) + return -ENODEV; if (!test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) return -EOPNOTSUPP; - if (pf->rdma_mode & IIDC_RDMA_PROTOCOL_IWARP) { + if (cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_IWARP) { NL_SET_ERR_MSG_MOD(extack, "iWARP is currently enabled. This device cannot enable iWARP and RoCEv2 simultaneously"); return -EOPNOTSUPP; } @@ -1436,30 +1405,40 @@ ice_devlink_enable_iw_get(struct devlink *devlink, u32 id, struct devlink_param_gset_ctx *ctx) { struct ice_pf *pf = devlink_priv(devlink); + struct iidc_rdma_core_dev_info *cdev; + + cdev = pf->cdev_info; + if (!cdev) + return -ENODEV; - ctx->val.vbool = pf->rdma_mode & IIDC_RDMA_PROTOCOL_IWARP; + ctx->val.vbool = !!(cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_IWARP); return 0; } -static int -ice_devlink_enable_iw_set(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) +static int ice_devlink_enable_iw_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct ice_pf *pf = devlink_priv(devlink); + struct iidc_rdma_core_dev_info *cdev; bool iw_ena = ctx->val.vbool; int ret; + cdev = pf->cdev_info; + if (!cdev) + return -ENODEV; + if (!iw_ena) { ice_unplug_aux_dev(pf); - pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_IWARP; + cdev->rdma_protocol &= ~IIDC_RDMA_PROTOCOL_IWARP; return 0; } - pf->rdma_mode |= IIDC_RDMA_PROTOCOL_IWARP; + cdev->rdma_protocol |= IIDC_RDMA_PROTOCOL_IWARP; ret = ice_plug_aux_dev(pf); if (ret) - pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_IWARP; + cdev->rdma_protocol &= ~IIDC_RDMA_PROTOCOL_IWARP; return ret; } @@ -1474,7 +1453,7 @@ ice_devlink_enable_iw_validate(struct devlink *devlink, u32 id, if (!test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) return -EOPNOTSUPP; - if (pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2) { + if (pf->cdev_info->rdma_protocol & IIDC_RDMA_PROTOCOL_ROCEV2) { NL_SET_ERR_MSG_MOD(extack, "RoCEv2 is currently enabled. This device cannot enable iWARP and RoCEv2 simultaneously"); return -EOPNOTSUPP; } @@ -1482,260 +1461,349 @@ ice_devlink_enable_iw_validate(struct devlink *devlink, u32 id, return 0; } -static const struct devlink_param ice_devlink_params[] = { - DEVLINK_PARAM_GENERIC(ENABLE_ROCE, BIT(DEVLINK_PARAM_CMODE_RUNTIME), - ice_devlink_enable_roce_get, - ice_devlink_enable_roce_set, - ice_devlink_enable_roce_validate), - DEVLINK_PARAM_GENERIC(ENABLE_IWARP, BIT(DEVLINK_PARAM_CMODE_RUNTIME), - ice_devlink_enable_iw_get, - ice_devlink_enable_iw_set, - ice_devlink_enable_iw_validate), +#define DEVLINK_LOCAL_FWD_DISABLED_STR "disabled" +#define DEVLINK_LOCAL_FWD_ENABLED_STR "enabled" +#define DEVLINK_LOCAL_FWD_PRIORITIZED_STR "prioritized" -}; +/** + * ice_devlink_local_fwd_mode_to_str - Get string for local_fwd mode. + * @mode: local forwarding for mode used in port_info struct. + * + * Return: Mode respective string or "Invalid". + */ +static const char * +ice_devlink_local_fwd_mode_to_str(enum ice_local_fwd_mode mode) +{ + switch (mode) { + case ICE_LOCAL_FWD_MODE_ENABLED: + return DEVLINK_LOCAL_FWD_ENABLED_STR; + case ICE_LOCAL_FWD_MODE_PRIORITIZED: + return DEVLINK_LOCAL_FWD_PRIORITIZED_STR; + case ICE_LOCAL_FWD_MODE_DISABLED: + return DEVLINK_LOCAL_FWD_DISABLED_STR; + } -static void ice_devlink_free(void *devlink_ptr) -{ - devlink_free((struct devlink *)devlink_ptr); + return "Invalid"; } /** - * ice_allocate_pf - Allocate devlink and return PF structure pointer - * @dev: the device to allocate for + * ice_devlink_local_fwd_str_to_mode - Get local_fwd mode from string name. + * @mode_str: local forwarding mode string. * - * Allocate a devlink instance for this device and return the private area as - * the PF structure. The devlink memory is kept track of through devres by - * adding an action to remove it when unwinding. + * Return: Mode value or negative number if invalid. */ -struct ice_pf *ice_allocate_pf(struct device *dev) +static int ice_devlink_local_fwd_str_to_mode(const char *mode_str) { - struct devlink *devlink; - - devlink = devlink_alloc(&ice_devlink_ops, sizeof(struct ice_pf), dev); - if (!devlink) - return NULL; - - /* Add an action to teardown the devlink when unwinding the driver */ - if (devm_add_action_or_reset(dev, ice_devlink_free, devlink)) - return NULL; + if (!strcmp(mode_str, DEVLINK_LOCAL_FWD_ENABLED_STR)) + return ICE_LOCAL_FWD_MODE_ENABLED; + else if (!strcmp(mode_str, DEVLINK_LOCAL_FWD_PRIORITIZED_STR)) + return ICE_LOCAL_FWD_MODE_PRIORITIZED; + else if (!strcmp(mode_str, DEVLINK_LOCAL_FWD_DISABLED_STR)) + return ICE_LOCAL_FWD_MODE_DISABLED; - return devlink_priv(devlink); + return -EINVAL; } /** - * ice_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. + * ice_devlink_local_fwd_get - Get local_fwd parameter. + * @devlink: Pointer to the devlink instance. + * @id: The parameter ID to set. + * @ctx: Context to store the parameter value. * - * Return: zero on success or an error code on failure. + * Return: Zero. */ -void ice_devlink_register(struct ice_pf *pf) +static int ice_devlink_local_fwd_get(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) { - struct devlink *devlink = priv_to_devlink(pf); + struct ice_pf *pf = devlink_priv(devlink); + struct ice_port_info *pi; + const char *mode_str; - devlink_register(devlink); + pi = pf->hw.port_info; + mode_str = ice_devlink_local_fwd_mode_to_str(pi->local_fwd_mode); + snprintf(ctx->val.vstr, sizeof(ctx->val.vstr), "%s", mode_str); + + return 0; } /** - * ice_devlink_unregister - Unregister devlink resources for this PF. - * @pf: the PF structure to cleanup + * ice_devlink_local_fwd_set - Set local_fwd parameter. + * @devlink: Pointer to the devlink instance. + * @id: The parameter ID to set. + * @ctx: Context to get the parameter value. + * @extack: Netlink extended ACK structure. * - * Releases resources used by devlink and cleans up associated memory. + * Return: Zero. */ -void ice_devlink_unregister(struct ice_pf *pf) +static int ice_devlink_local_fwd_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { - devlink_unregister(priv_to_devlink(pf)); + int new_local_fwd_mode = ice_devlink_local_fwd_str_to_mode(ctx->val.vstr); + struct ice_pf *pf = devlink_priv(devlink); + struct device *dev = ice_pf_to_dev(pf); + struct ice_port_info *pi; + + pi = pf->hw.port_info; + if (pi->local_fwd_mode != new_local_fwd_mode) { + pi->local_fwd_mode = new_local_fwd_mode; + dev_info(dev, "Setting local_fwd to %s\n", ctx->val.vstr); + ice_schedule_reset(pf, ICE_RESET_CORER); + } + + return 0; } /** - * ice_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 + * ice_devlink_local_fwd_validate - Validate passed local_fwd parameter value. + * @devlink: Unused pointer to devlink instance. + * @id: The parameter ID to validate. + * @val: Value to validate. + * @extack: Netlink extended ACK structure. + * + * Supported values are: + * "enabled" - local_fwd is enabled, "disabled" - local_fwd is disabled + * "prioritized" - local_fwd traffic is prioritized in scheduling. + * + * Return: Zero when passed parameter value is supported. Negative value on + * error. */ -static void -ice_devlink_set_switch_id(struct ice_pf *pf, struct netdev_phys_item_id *ppid) +static int ice_devlink_local_fwd_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + if (ice_devlink_local_fwd_str_to_mode(val.vstr) < 0) { + NL_SET_ERR_MSG_MOD(extack, "Error: Requested value is not supported."); + return -EINVAL; + } + + return 0; +} + +static int +ice_devlink_msix_max_pf_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) { - struct pci_dev *pdev = pf->pdev; - u64 id; + struct ice_pf *pf = devlink_priv(devlink); - id = pci_get_dsn(pdev); + if (val.vu32 > pf->hw.func_caps.common_cap.num_msix_vectors) + return -EINVAL; - ppid->id_len = sizeof(id); - put_unaligned_be64(id, &ppid->id); + return 0; } -int ice_devlink_register_params(struct ice_pf *pf) +static int +ice_devlink_msix_min_pf_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) { - struct devlink *devlink = priv_to_devlink(pf); + if (val.vu32 < ICE_MIN_MSIX) + return -EINVAL; - return devlink_params_register(devlink, ice_devlink_params, - ARRAY_SIZE(ice_devlink_params)); + return 0; } -void ice_devlink_unregister_params(struct ice_pf *pf) +static int ice_devlink_enable_rdma_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_priv(devlink); + bool new_state = val.vbool; + + if (new_state && !test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) + return -EOPNOTSUPP; + + return 0; +} + +enum ice_param_id { + ICE_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, + ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS, + ICE_DEVLINK_PARAM_ID_LOCAL_FWD, +}; + +static const struct devlink_param ice_dvl_rdma_params[] = { + DEVLINK_PARAM_GENERIC(ENABLE_ROCE, BIT(DEVLINK_PARAM_CMODE_RUNTIME), + ice_devlink_enable_roce_get, + ice_devlink_enable_roce_set, + ice_devlink_enable_roce_validate), + DEVLINK_PARAM_GENERIC(ENABLE_IWARP, BIT(DEVLINK_PARAM_CMODE_RUNTIME), + ice_devlink_enable_iw_get, + ice_devlink_enable_iw_set, + ice_devlink_enable_iw_validate), + DEVLINK_PARAM_GENERIC(ENABLE_RDMA, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + NULL, NULL, ice_devlink_enable_rdma_validate), +}; + +static const struct devlink_param ice_dvl_msix_params[] = { + DEVLINK_PARAM_GENERIC(MSIX_VEC_PER_PF_MAX, + BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + NULL, NULL, ice_devlink_msix_max_pf_validate), + DEVLINK_PARAM_GENERIC(MSIX_VEC_PER_PF_MIN, + BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + NULL, NULL, ice_devlink_msix_min_pf_validate), +}; + +static const struct devlink_param ice_dvl_sched_params[] = { + DEVLINK_PARAM_DRIVER(ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS, + "tx_scheduling_layers", + DEVLINK_PARAM_TYPE_U8, + BIT(DEVLINK_PARAM_CMODE_PERMANENT), + ice_devlink_tx_sched_layers_get, + ice_devlink_tx_sched_layers_set, + ice_devlink_tx_sched_layers_validate), + DEVLINK_PARAM_DRIVER(ICE_DEVLINK_PARAM_ID_LOCAL_FWD, + "local_forwarding", DEVLINK_PARAM_TYPE_STRING, + BIT(DEVLINK_PARAM_CMODE_RUNTIME), + ice_devlink_local_fwd_get, + ice_devlink_local_fwd_set, + ice_devlink_local_fwd_validate), +}; + +static void ice_devlink_free(void *devlink_ptr) { - devlink_params_unregister(priv_to_devlink(pf), ice_devlink_params, - ARRAY_SIZE(ice_devlink_params)); + devlink_free((struct devlink *)devlink_ptr); } /** - * ice_devlink_set_port_split_options - Set port split options - * @pf: the PF to set port split options - * @attrs: devlink attributes + * ice_allocate_pf - Allocate devlink and return PF structure pointer + * @dev: the device to allocate for * - * Sets devlink port split options based on available FW port options + * Allocate a devlink instance for this device and return the private area as + * the PF structure. The devlink memory is kept track of through devres by + * adding an action to remove it when unwinding. */ -static void -ice_devlink_set_port_split_options(struct ice_pf *pf, - struct devlink_port_attrs *attrs) +struct ice_pf *ice_allocate_pf(struct device *dev) { - struct ice_aqc_get_port_options_elem options[ICE_AQC_PORT_OPT_MAX]; - u8 i, active_idx, pending_idx, option_count = ICE_AQC_PORT_OPT_MAX; - bool active_valid, pending_valid; - int status; + struct devlink *devlink; - status = ice_aq_get_port_options(&pf->hw, options, &option_count, - 0, true, &active_idx, &active_valid, - &pending_idx, &pending_valid); - if (status) { - dev_dbg(ice_pf_to_dev(pf), "Couldn't read port split options, err = %d\n", - status); - return; - } + devlink = devlink_alloc(&ice_devlink_ops, sizeof(struct ice_pf), dev); + if (!devlink) + return NULL; - /* find the biggest available port split count */ - for (i = 0; i < option_count; i++) - attrs->lanes = max_t(int, attrs->lanes, options[i].pmd); + /* Add an action to teardown the devlink when unwinding the driver */ + if (devm_add_action_or_reset(dev, ice_devlink_free, devlink)) + return NULL; - attrs->splittable = attrs->lanes ? 1 : 0; - ice_active_port_option = active_idx; + return devlink_priv(devlink); } -static const struct devlink_port_ops ice_devlink_port_ops = { - .port_split = ice_devlink_port_split, - .port_unsplit = ice_devlink_port_unsplit, -}; - /** - * ice_devlink_create_pf_port - Create a devlink port for this PF - * @pf: the PF to create a devlink port for + * ice_allocate_sf - Allocate devlink and return SF structure pointer + * @dev: the device to allocate for + * @pf: pointer to the PF structure * - * Create and register a devlink_port for this PF. - * This function has to be called under devl_lock. + * Allocate a devlink instance for SF. * - * Return: zero on success or an error code on failure. + * Return: ice_sf_priv pointer to allocated memory or ERR_PTR in case of error */ -int ice_devlink_create_pf_port(struct ice_pf *pf) +struct ice_sf_priv *ice_allocate_sf(struct device *dev, struct ice_pf *pf) { - struct devlink_port_attrs attrs = {}; - struct devlink_port *devlink_port; struct devlink *devlink; - struct ice_vsi *vsi; - struct device *dev; int err; - devlink = priv_to_devlink(pf); - - dev = ice_pf_to_dev(pf); - - devlink_port = &pf->devlink_port; - - vsi = ice_get_main_vsi(pf); - if (!vsi) - return -EIO; - - attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; - attrs.phys.port_number = pf->hw.bus.func; - - /* As FW supports only port split options for whole device, - * set port split options only for first PF. - */ - if (pf->hw.pf_id == 0) - ice_devlink_set_port_split_options(pf, &attrs); - - ice_devlink_set_switch_id(pf, &attrs.switch_id); - - devlink_port_attrs_set(devlink_port, &attrs); + devlink = devlink_alloc(&ice_sf_devlink_ops, sizeof(struct ice_sf_priv), + dev); + if (!devlink) + return ERR_PTR(-ENOMEM); - err = devl_port_register_with_ops(devlink, devlink_port, vsi->idx, - &ice_devlink_port_ops); + err = devl_nested_devlink_set(priv_to_devlink(pf), devlink); if (err) { - dev_err(dev, "Failed to create devlink port for PF %d, error %d\n", - pf->hw.pf_id, err); - return err; + devlink_free(devlink); + return ERR_PTR(err); } - return 0; + return devlink_priv(devlink); } /** - * ice_devlink_destroy_pf_port - Destroy the devlink_port for this PF - * @pf: the PF to cleanup + * ice_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. * - * Unregisters the devlink_port structure associated with this PF. - * This function has to be called under devl_lock. + * Return: zero on success or an error code on failure. */ -void ice_devlink_destroy_pf_port(struct ice_pf *pf) +void ice_devlink_register(struct ice_pf *pf) { - devl_port_unregister(&pf->devlink_port); + struct devlink *devlink = priv_to_devlink(pf); + + devl_register(devlink); } /** - * ice_devlink_create_vf_port - Create a devlink port for this VF - * @vf: the VF to create a port for - * - * Create and register a devlink_port for this VF. + * ice_devlink_unregister - Unregister devlink resources for this PF. + * @pf: the PF structure to cleanup * - * Return: zero on success or an error code on failure. + * Releases resources used by devlink and cleans up associated memory. */ -int ice_devlink_create_vf_port(struct ice_vf *vf) +void ice_devlink_unregister(struct ice_pf *pf) { - struct devlink_port_attrs attrs = {}; - struct devlink_port *devlink_port; - struct devlink *devlink; - struct ice_vsi *vsi; - struct device *dev; - struct ice_pf *pf; - int err; - - pf = vf->pf; - dev = ice_pf_to_dev(pf); - devlink_port = &vf->devlink_port; - - vsi = ice_get_vf_vsi(vf); - if (!vsi) - return -EINVAL; + devl_unregister(priv_to_devlink(pf)); +} - attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_VF; - attrs.pci_vf.pf = pf->hw.bus.func; - attrs.pci_vf.vf = vf->vf_id; +int ice_devlink_register_params(struct ice_pf *pf) +{ + struct devlink *devlink = priv_to_devlink(pf); + union devlink_param_value value; + struct ice_hw *hw = &pf->hw; + int status; - ice_devlink_set_switch_id(pf, &attrs.switch_id); + status = devl_params_register(devlink, ice_dvl_rdma_params, + ARRAY_SIZE(ice_dvl_rdma_params)); + if (status) + return status; - devlink_port_attrs_set(devlink_port, &attrs); - devlink = priv_to_devlink(pf); + status = devl_params_register(devlink, ice_dvl_msix_params, + ARRAY_SIZE(ice_dvl_msix_params)); + if (status) + goto unregister_rdma_params; - err = devlink_port_register(devlink, devlink_port, vsi->idx); - if (err) { - dev_err(dev, "Failed to create devlink port for VF %d, error %d\n", - vf->vf_id, err); - return err; - } + if (hw->func_caps.common_cap.tx_sched_topo_comp_mode_en) + status = devl_params_register(devlink, ice_dvl_sched_params, + ARRAY_SIZE(ice_dvl_sched_params)); + if (status) + goto unregister_msix_params; + + value.vu32 = pf->msix.max; + devl_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX, + value); + value.vu32 = pf->msix.min; + devl_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN, + value); + + value.vbool = test_bit(ICE_FLAG_RDMA_ENA, pf->flags); + devl_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA, + value); return 0; + +unregister_msix_params: + devl_params_unregister(devlink, ice_dvl_msix_params, + ARRAY_SIZE(ice_dvl_msix_params)); +unregister_rdma_params: + devl_params_unregister(devlink, ice_dvl_rdma_params, + ARRAY_SIZE(ice_dvl_rdma_params)); + return status; } -/** - * ice_devlink_destroy_vf_port - Destroy the devlink_port for this VF - * @vf: the VF to cleanup - * - * Unregisters the devlink_port structure associated with this VF. - */ -void ice_devlink_destroy_vf_port(struct ice_vf *vf) +void ice_devlink_unregister_params(struct ice_pf *pf) { - devl_rate_leaf_destroy(&vf->devlink_port); - devlink_port_unregister(&vf->devlink_port); + struct devlink *devlink = priv_to_devlink(pf); + struct ice_hw *hw = &pf->hw; + + devl_params_unregister(devlink, ice_dvl_rdma_params, + ARRAY_SIZE(ice_dvl_rdma_params)); + devl_params_unregister(devlink, ice_dvl_msix_params, + ARRAY_SIZE(ice_dvl_msix_params)); + + if (hw->func_caps.common_cap.tx_sched_topo_comp_mode_en) + devl_params_unregister(devlink, ice_dvl_sched_params, + ARRAY_SIZE(ice_dvl_sched_params)); } #define ICE_DEVLINK_READ_BLK_SIZE (1024 * 1024) @@ -1976,8 +2044,8 @@ void ice_devlink_init_regions(struct ice_pf *pf) u64 nvm_size, sram_size; nvm_size = pf->hw.flash.flash_size; - pf->nvm_region = devlink_region_create(devlink, &ice_nvm_region_ops, 1, - nvm_size); + pf->nvm_region = devl_region_create(devlink, &ice_nvm_region_ops, 1, + nvm_size); if (IS_ERR(pf->nvm_region)) { dev_err(dev, "failed to create NVM devlink region, err %ld\n", PTR_ERR(pf->nvm_region)); @@ -1985,17 +2053,17 @@ void ice_devlink_init_regions(struct ice_pf *pf) } sram_size = pf->hw.flash.sr_words * 2u; - pf->sram_region = devlink_region_create(devlink, &ice_sram_region_ops, - 1, sram_size); + pf->sram_region = devl_region_create(devlink, &ice_sram_region_ops, + 1, sram_size); if (IS_ERR(pf->sram_region)) { dev_err(dev, "failed to create shadow-ram devlink region, err %ld\n", PTR_ERR(pf->sram_region)); pf->sram_region = NULL; } - pf->devcaps_region = devlink_region_create(devlink, - &ice_devcaps_region_ops, 10, - ICE_AQ_MAX_BUF_LEN); + pf->devcaps_region = devl_region_create(devlink, + &ice_devcaps_region_ops, 10, + ICE_AQ_MAX_BUF_LEN); if (IS_ERR(pf->devcaps_region)) { dev_err(dev, "failed to create device-caps devlink region, err %ld\n", PTR_ERR(pf->devcaps_region)); @@ -2012,11 +2080,11 @@ void ice_devlink_init_regions(struct ice_pf *pf) void ice_devlink_destroy_regions(struct ice_pf *pf) { if (pf->nvm_region) - devlink_region_destroy(pf->nvm_region); + devl_region_destroy(pf->nvm_region); if (pf->sram_region) - devlink_region_destroy(pf->sram_region); + devl_region_destroy(pf->sram_region); if (pf->devcaps_region) - devlink_region_destroy(pf->devcaps_region); + devl_region_destroy(pf->devcaps_region); } diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.h b/drivers/net/ethernet/intel/ice/devlink/devlink.h index d291c0e2e17b..1af3b0763fbb 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.h +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.h @@ -5,6 +5,7 @@ #define _ICE_DEVLINK_H_ struct ice_pf *ice_allocate_pf(struct device *dev); +struct ice_sf_priv *ice_allocate_sf(struct device *dev, struct ice_pf *pf); void ice_devlink_register(struct ice_pf *pf); void ice_devlink_unregister(struct ice_pf *pf); diff --git a/drivers/net/ethernet/intel/ice/devlink/health.c b/drivers/net/ethernet/intel/ice/devlink/health.c new file mode 100644 index 000000000000..19c3d37aa768 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/devlink/health.c @@ -0,0 +1,550 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024, Intel Corporation. */ + +#include "ice.h" +#include "ice_adminq_cmd.h" /* for enum ice_aqc_health_status_elem */ +#include "health.h" + +#define ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, obj, name) \ + devlink_fmsg_put(fmsg, #name, (obj)->name) + +#define ICE_HEALTH_STATUS_DATA_SIZE 2 + +struct ice_health_status { + enum ice_aqc_health_status code; + const char *description; + const char *solution; + const char *data_label[ICE_HEALTH_STATUS_DATA_SIZE]; +}; + +/* + * In addition to the health status codes provided below, the firmware might + * generate Health Status Codes that are not pertinent to the end-user. + * For instance, Health Code 0x1002 is triggered when the command fails. + * Such codes should be disregarded by the end-user. + * The below lookup requires to be sorted by code. + */ + +static const char ice_common_port_solutions[] = + "Check your cable connection. Change or replace the module or cable. Manually set speed and duplex."; +static const char ice_port_number_label[] = "Port Number"; +static const char ice_update_nvm_solution[] = "Update to the latest NVM image."; + +static const struct ice_health_status ice_health_status_lookup[] = { + {ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_STRICT, "An unsupported module was detected.", + ice_common_port_solutions, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_MOD_TYPE, "Module type is not supported.", + "Change or replace the module or cable.", {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_MOD_QUAL, "Module is not qualified.", + ice_common_port_solutions, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_MOD_COMM, + "Device cannot communicate with the module.", + "Check your cable connection. Change or replace the module or cable. Manually set speed and duplex.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_MOD_CONFLICT, "Unresolved module conflict.", + "Manually set speed/duplex or change the port option. If the problem persists, use a cable/module that is found in the supported modules and cables list for this device.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_MOD_NOT_PRESENT, "Module is not present.", + "Check that the module is inserted correctly. If the problem persists, use a cable/module that is found in the supported modules and cables list for this device.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_INFO_MOD_UNDERUTILIZED, "Underutilized module.", + "Change or replace the module or cable. Change the port option.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_LENIENT, "An unsupported module was detected.", + ice_common_port_solutions, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_INVALID_LINK_CFG, "Invalid link configuration.", + NULL, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_PORT_ACCESS, "Port hardware access error.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_PORT_UNREACHABLE, "A port is unreachable.", + "Change the port option. Update to the latest NVM image."}, + {ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_MOD_LIMITED, "Port speed is limited due to module.", + "Change the module or configure the port option to match the current module speed. Change the port option.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_PARALLEL_FAULT, + "All configured link modes were attempted but failed to establish link. The device will restart the process to establish link.", + "Check link partner connection and configuration.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_PHY_LIMITED, + "Port speed is limited by PHY capabilities.", + "Change the module to align to port option.", {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_NETLIST_TOPO, "LOM topology netlist is corrupted.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_NETLIST, "Unrecoverable netlist error.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_TOPO_CONFLICT, "Port topology conflict.", + "Change the port option. Update to the latest NVM image."}, + {ICE_AQC_HEALTH_STATUS_ERR_LINK_HW_ACCESS, "Unrecoverable hardware access error.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_LINK_RUNTIME, "Unrecoverable runtime error.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_DNL_INIT, "Link management engine failed to initialize.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_PHY_FW_LOAD, + "Failed to load the firmware image in the external PHY.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_INFO_RECOVERY, "The device is in firmware recovery mode.", + ice_update_nvm_solution, {"Extended Error"}}, + {ICE_AQC_HEALTH_STATUS_ERR_FLASH_ACCESS, "The flash chip cannot be accessed.", + "If issue persists, call customer support.", {"Access Type"}}, + {ICE_AQC_HEALTH_STATUS_ERR_NVM_AUTH, "NVM authentication failed.", + ice_update_nvm_solution}, + {ICE_AQC_HEALTH_STATUS_ERR_OROM_AUTH, "Option ROM authentication failed.", + ice_update_nvm_solution}, + {ICE_AQC_HEALTH_STATUS_ERR_DDP_AUTH, "DDP package authentication failed.", + "Update to latest base driver and DDP package."}, + {ICE_AQC_HEALTH_STATUS_ERR_NVM_COMPAT, "NVM image is incompatible.", + ice_update_nvm_solution}, + {ICE_AQC_HEALTH_STATUS_ERR_OROM_COMPAT, "Option ROM is incompatible.", + ice_update_nvm_solution, {"Expected PCI Device ID", "Expected Module ID"}}, + {ICE_AQC_HEALTH_STATUS_ERR_DCB_MIB, + "Supplied MIB file is invalid. DCB reverted to default configuration.", + "Disable FW-LLDP and check DCBx system configuration.", + {ice_port_number_label, "MIB ID"}}, +}; + +static int ice_health_status_lookup_compare(const void *a, const void *b) +{ + return ((struct ice_health_status *)a)->code - ((struct ice_health_status *)b)->code; +} + +static const struct ice_health_status *ice_get_health_status(u16 code) +{ + struct ice_health_status key = { .code = code }; + + return bsearch(&key, ice_health_status_lookup, ARRAY_SIZE(ice_health_status_lookup), + sizeof(struct ice_health_status), ice_health_status_lookup_compare); +} + +static void ice_describe_status_code(struct devlink_fmsg *fmsg, + struct ice_aqc_health_status_elem *hse) +{ + static const char *const aux_label[] = { "Aux Data 1", "Aux Data 2" }; + const struct ice_health_status *health_code; + u32 internal_data[2]; + u16 status_code; + + status_code = le16_to_cpu(hse->health_status_code); + + devlink_fmsg_put(fmsg, "Syndrome", status_code); + if (status_code) { + internal_data[0] = le32_to_cpu(hse->internal_data1); + internal_data[1] = le32_to_cpu(hse->internal_data2); + + health_code = ice_get_health_status(status_code); + if (!health_code) + return; + + devlink_fmsg_string_pair_put(fmsg, "Description", health_code->description); + if (health_code->solution) + devlink_fmsg_string_pair_put(fmsg, "Possible Solution", + health_code->solution); + + for (size_t i = 0; i < ICE_HEALTH_STATUS_DATA_SIZE; i++) { + if (internal_data[i] != ICE_AQC_HEALTH_STATUS_UNDEFINED_DATA) + devlink_fmsg_u32_pair_put(fmsg, + health_code->data_label[i] ? + health_code->data_label[i] : + aux_label[i], + internal_data[i]); + } + } +} + +static int +ice_port_reporter_diagnose(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_health_reporter_priv(reporter); + + ice_describe_status_code(fmsg, &pf->health_reporters.port_status); + return 0; +} + +static int +ice_port_reporter_dump(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg, + void *priv_ctx, struct netlink_ext_ack __always_unused *extack) +{ + struct ice_pf *pf = devlink_health_reporter_priv(reporter); + + ice_describe_status_code(fmsg, &pf->health_reporters.port_status); + return 0; +} + +static int +ice_fw_reporter_diagnose(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_health_reporter_priv(reporter); + + ice_describe_status_code(fmsg, &pf->health_reporters.fw_status); + return 0; +} + +static int +ice_fw_reporter_dump(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg, + void *priv_ctx, struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_health_reporter_priv(reporter); + + ice_describe_status_code(fmsg, &pf->health_reporters.fw_status); + return 0; +} + +static void ice_config_health_events(struct ice_pf *pf, bool enable) +{ + u8 enable_bits = 0; + int ret; + + if (enable) + enable_bits = ICE_AQC_HEALTH_STATUS_SET_PF_SPECIFIC_MASK | + ICE_AQC_HEALTH_STATUS_SET_GLOBAL_MASK; + + ret = ice_aq_set_health_status_cfg(&pf->hw, enable_bits); + if (ret) + dev_err(ice_pf_to_dev(pf), "Failed to %s firmware health events, err %d aq_err %s\n", + str_enable_disable(enable), ret, + ice_aq_str(pf->hw.adminq.sq_last_status)); +} + +/** + * ice_process_health_status_event - Process the health status event from FW + * @pf: pointer to the PF structure + * @event: event structure containing the Health Status Event opcode + * + * Decode the Health Status Events and print the associated messages + */ +void ice_process_health_status_event(struct ice_pf *pf, struct ice_rq_event_info *event) +{ + const struct ice_aqc_health_status_elem *health_info; + u16 count; + + health_info = (struct ice_aqc_health_status_elem *)event->msg_buf; + count = le16_to_cpu(event->desc.params.get_health_status.health_status_count); + + if (count > (event->buf_len / sizeof(*health_info))) { + dev_err(ice_pf_to_dev(pf), "Received a health status event with invalid element count\n"); + return; + } + + for (size_t i = 0; i < count; i++) { + const struct ice_health_status *health_code; + u16 status_code; + + status_code = le16_to_cpu(health_info->health_status_code); + health_code = ice_get_health_status(status_code); + + if (health_code) { + switch (le16_to_cpu(health_info->event_source)) { + case ICE_AQC_HEALTH_STATUS_GLOBAL: + pf->health_reporters.fw_status = *health_info; + devlink_health_report(pf->health_reporters.fw, + "FW syndrome reported", NULL); + break; + case ICE_AQC_HEALTH_STATUS_PF: + case ICE_AQC_HEALTH_STATUS_PORT: + pf->health_reporters.port_status = *health_info; + devlink_health_report(pf->health_reporters.port, + "Port syndrome reported", NULL); + break; + default: + dev_err(ice_pf_to_dev(pf), "Health code with unknown source\n"); + } + } else { + u32 data1, data2; + u16 source; + + source = le16_to_cpu(health_info->event_source); + data1 = le32_to_cpu(health_info->internal_data1); + data2 = le32_to_cpu(health_info->internal_data2); + dev_dbg(ice_pf_to_dev(pf), + "Received internal health status code 0x%08x, source: 0x%08x, data1: 0x%08x, data2: 0x%08x", + status_code, source, data1, data2); + } + health_info++; + } +} + +/** + * ice_devlink_health_report - boilerplate to call given @reporter + * + * @reporter: devlink health reporter to call, do nothing on NULL + * @msg: message to pass up, "event name" is fine + * @priv_ctx: typically some event struct + */ +static void ice_devlink_health_report(struct devlink_health_reporter *reporter, + const char *msg, void *priv_ctx) +{ + if (!reporter) + return; + + /* We do not do auto recovering, so return value of the below function + * will always be 0, thus we do ignore it. + */ + devlink_health_report(reporter, msg, priv_ctx); +} + +struct ice_mdd_event { + enum ice_mdd_src src; + u16 vf_num; + u16 queue; + u8 pf_num; + u8 event; +}; + +static const char *ice_mdd_src_to_str(enum ice_mdd_src src) +{ + switch (src) { + case ICE_MDD_SRC_TX_PQM: + return "tx_pqm"; + case ICE_MDD_SRC_TX_TCLAN: + return "tx_tclan"; + case ICE_MDD_SRC_TX_TDPU: + return "tx_tdpu"; + case ICE_MDD_SRC_RX: + return "rx"; + default: + return "invalid"; + } +} + +static int +ice_mdd_reporter_dump(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, void *priv_ctx, + struct netlink_ext_ack *extack) +{ + struct ice_mdd_event *mdd_event = priv_ctx; + const char *src; + + if (!mdd_event) + return 0; + + src = ice_mdd_src_to_str(mdd_event->src); + + devlink_fmsg_obj_nest_start(fmsg); + devlink_fmsg_put(fmsg, "src", src); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, mdd_event, pf_num); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, mdd_event, vf_num); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, mdd_event, event); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, mdd_event, queue); + devlink_fmsg_obj_nest_end(fmsg); + + return 0; +} + +/** + * ice_report_mdd_event - Report an MDD event through devlink health + * @pf: the PF device structure + * @src: the HW block that was the source of this MDD event + * @pf_num: the pf_num on which the MDD event occurred + * @vf_num: the vf_num on which the MDD event occurred + * @event: the event type of the MDD event + * @queue: the queue on which the MDD event occurred + * + * Report an MDD event that has occurred on this PF. + */ +void ice_report_mdd_event(struct ice_pf *pf, enum ice_mdd_src src, u8 pf_num, + u16 vf_num, u8 event, u16 queue) +{ + struct ice_mdd_event ev = { + .src = src, + .pf_num = pf_num, + .vf_num = vf_num, + .event = event, + .queue = queue, + }; + + ice_devlink_health_report(pf->health_reporters.mdd, "MDD event", &ev); +} + +/** + * ice_fmsg_put_ptr - put hex value of pointer into fmsg + * + * @fmsg: devlink fmsg under construction + * @name: name to pass + * @ptr: 64 bit value to print as hex and put into fmsg + */ +static void ice_fmsg_put_ptr(struct devlink_fmsg *fmsg, const char *name, + void *ptr) +{ + char buf[sizeof(ptr) * 3]; + + sprintf(buf, "%p", ptr); + devlink_fmsg_put(fmsg, name, buf); +} + +struct ice_tx_hang_event { + u32 head; + u32 intr; + u16 vsi_num; + u16 queue; + u16 next_to_clean; + u16 next_to_use; + struct ice_tx_ring *tx_ring; +}; + +static int ice_tx_hang_reporter_dump(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, void *priv_ctx, + struct netlink_ext_ack *extack) +{ + struct ice_tx_hang_event *event = priv_ctx; + struct sk_buff *skb; + + if (!event) + return 0; + + skb = event->tx_ring->tx_buf->skb; + devlink_fmsg_obj_nest_start(fmsg); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, head); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, intr); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, vsi_num); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, queue); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, next_to_clean); + ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, next_to_use); + devlink_fmsg_put(fmsg, "irq-mapping", event->tx_ring->q_vector->name); + ice_fmsg_put_ptr(fmsg, "desc-ptr", event->tx_ring->desc); + ice_fmsg_put_ptr(fmsg, "dma-ptr", (void *)(long)event->tx_ring->dma); + ice_fmsg_put_ptr(fmsg, "skb-ptr", skb); + devlink_fmsg_binary_pair_put(fmsg, "desc", event->tx_ring->desc, + event->tx_ring->count * sizeof(struct ice_tx_desc)); + devlink_fmsg_dump_skb(fmsg, skb); + devlink_fmsg_obj_nest_end(fmsg); + + return 0; +} + +void ice_prep_tx_hang_report(struct ice_pf *pf, struct ice_tx_ring *tx_ring, + u16 vsi_num, u32 head, u32 intr) +{ + struct ice_health_tx_hang_buf *buf = &pf->health_reporters.tx_hang_buf; + + buf->tx_ring = tx_ring; + buf->vsi_num = vsi_num; + buf->head = head; + buf->intr = intr; +} + +void ice_report_tx_hang(struct ice_pf *pf) +{ + struct ice_health_tx_hang_buf *buf = &pf->health_reporters.tx_hang_buf; + struct ice_tx_ring *tx_ring = buf->tx_ring; + + struct ice_tx_hang_event ev = { + .head = buf->head, + .intr = buf->intr, + .vsi_num = buf->vsi_num, + .queue = tx_ring->q_index, + .next_to_clean = tx_ring->next_to_clean, + .next_to_use = tx_ring->next_to_use, + .tx_ring = tx_ring, + }; + + ice_devlink_health_report(pf->health_reporters.tx_hang, "Tx hang", &ev); +} + +static struct devlink_health_reporter * +ice_init_devlink_rep(struct ice_pf *pf, + const struct devlink_health_reporter_ops *ops) +{ + struct devlink *devlink = priv_to_devlink(pf); + struct devlink_health_reporter *rep; + const u64 graceful_period = 0; + + rep = devl_health_reporter_create(devlink, ops, graceful_period, pf); + if (IS_ERR(rep)) { + struct device *dev = ice_pf_to_dev(pf); + + dev_err(dev, "failed to create devlink %s health report er", + ops->name); + return NULL; + } + return rep; +} + +#define ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field) \ + ._field = ice_##_name##_reporter_##_field, + +#define ICE_DEFINE_HEALTH_REPORTER_OPS_1(_name, _field1) \ + static const struct devlink_health_reporter_ops ice_##_name##_reporter_ops = { \ + .name = #_name, \ + ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field1) \ + } + +#define ICE_DEFINE_HEALTH_REPORTER_OPS_2(_name, _field1, _field2) \ + static const struct devlink_health_reporter_ops ice_##_name##_reporter_ops = { \ + .name = #_name, \ + ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field1) \ + ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field2) \ + } + +ICE_DEFINE_HEALTH_REPORTER_OPS_1(mdd, dump); +ICE_DEFINE_HEALTH_REPORTER_OPS_1(tx_hang, dump); +ICE_DEFINE_HEALTH_REPORTER_OPS_2(fw, dump, diagnose); +ICE_DEFINE_HEALTH_REPORTER_OPS_2(port, dump, diagnose); + +/** + * ice_health_init - allocate and init all ice devlink health reporters and + * accompanied data + * + * @pf: PF struct + */ +void ice_health_init(struct ice_pf *pf) +{ + struct ice_health *reps = &pf->health_reporters; + + reps->mdd = ice_init_devlink_rep(pf, &ice_mdd_reporter_ops); + reps->tx_hang = ice_init_devlink_rep(pf, &ice_tx_hang_reporter_ops); + + if (ice_is_fw_health_report_supported(&pf->hw)) { + reps->fw = ice_init_devlink_rep(pf, &ice_fw_reporter_ops); + reps->port = ice_init_devlink_rep(pf, &ice_port_reporter_ops); + ice_config_health_events(pf, true); + } +} + +/** + * ice_deinit_devl_reporter - destroy given devlink health reporter + * @reporter: reporter to destroy + */ +static void ice_deinit_devl_reporter(struct devlink_health_reporter *reporter) +{ + if (reporter) + devl_health_reporter_destroy(reporter); +} + +/** + * ice_health_deinit - deallocate all ice devlink health reporters and + * accompanied data + * + * @pf: PF struct + */ +void ice_health_deinit(struct ice_pf *pf) +{ + ice_deinit_devl_reporter(pf->health_reporters.mdd); + ice_deinit_devl_reporter(pf->health_reporters.tx_hang); + if (ice_is_fw_health_report_supported(&pf->hw)) { + ice_deinit_devl_reporter(pf->health_reporters.fw); + ice_deinit_devl_reporter(pf->health_reporters.port); + ice_config_health_events(pf, false); + } +} + +static +void ice_health_assign_healthy_state(struct devlink_health_reporter *reporter) +{ + if (reporter) + devlink_health_reporter_state_update(reporter, + DEVLINK_HEALTH_REPORTER_STATE_HEALTHY); +} + +/** + * ice_health_clear - clear devlink health issues after a reset + * @pf: the PF device structure + * + * Mark the PF in healthy state again after a reset has completed. + */ +void ice_health_clear(struct ice_pf *pf) +{ + ice_health_assign_healthy_state(pf->health_reporters.mdd); + ice_health_assign_healthy_state(pf->health_reporters.tx_hang); +} diff --git a/drivers/net/ethernet/intel/ice/devlink/health.h b/drivers/net/ethernet/intel/ice/devlink/health.h new file mode 100644 index 000000000000..5edfc4d2adce --- /dev/null +++ b/drivers/net/ethernet/intel/ice/devlink/health.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024, Intel Corporation. */ + +#ifndef _HEALTH_H_ +#define _HEALTH_H_ + +#include <linux/types.h> + +/** + * DOC: health.h + * + * This header file stores everything that is needed for broadly understood + * devlink health mechanism for ice driver. + */ + +struct ice_aqc_health_status_elem; +struct ice_pf; +struct ice_tx_ring; +struct ice_rq_event_info; + +enum ice_mdd_src { + ICE_MDD_SRC_TX_PQM, + ICE_MDD_SRC_TX_TCLAN, + ICE_MDD_SRC_TX_TDPU, + ICE_MDD_SRC_RX, +}; + +/** + * struct ice_health - stores ice devlink health reporters and accompanied data + * @fw: devlink health reporter for FW Health Status events + * @mdd: devlink health reporter for MDD detection event + * @port: devlink health reporter for Port Health Status events + * @tx_hang: devlink health reporter for tx_hang event + * @tx_hang_buf: pre-allocated place to put info for Tx hang reporter from + * non-sleeping context + * @tx_ring: ring that the hang occurred on + * @head: descriptor head + * @intr: interrupt register value + * @vsi_num: VSI owning the queue that the hang occurred on + * @fw_status: buffer for last received FW Status event + * @port_status: buffer for last received Port Status event + */ +struct ice_health { + struct devlink_health_reporter *fw; + struct devlink_health_reporter *mdd; + struct devlink_health_reporter *port; + struct devlink_health_reporter *tx_hang; + struct_group_tagged(ice_health_tx_hang_buf, tx_hang_buf, + struct ice_tx_ring *tx_ring; + u32 head; + u32 intr; + u16 vsi_num; + ); + struct ice_aqc_health_status_elem fw_status; + struct ice_aqc_health_status_elem port_status; +}; + +void ice_process_health_status_event(struct ice_pf *pf, + struct ice_rq_event_info *event); + +void ice_health_init(struct ice_pf *pf); +void ice_health_deinit(struct ice_pf *pf); +void ice_health_clear(struct ice_pf *pf); + +void ice_prep_tx_hang_report(struct ice_pf *pf, struct ice_tx_ring *tx_ring, + u16 vsi_num, u32 head, u32 intr); +void ice_report_mdd_event(struct ice_pf *pf, enum ice_mdd_src src, u8 pf_num, + u16 vf_num, u8 event, u16 queue); +void ice_report_tx_hang(struct ice_pf *pf); + +#endif /* _HEALTH_H_ */ diff --git a/drivers/net/ethernet/intel/ice/devlink/port.c b/drivers/net/ethernet/intel/ice/devlink/port.c new file mode 100644 index 000000000000..767419a67fef --- /dev/null +++ b/drivers/net/ethernet/intel/ice/devlink/port.c @@ -0,0 +1,999 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024, Intel Corporation. */ + +#include <linux/vmalloc.h> + +#include "ice.h" +#include "devlink.h" +#include "port.h" +#include "ice_lib.h" +#include "ice_fltr.h" + +static int ice_active_port_option = -1; + +/** + * ice_devlink_port_opt_speed_str - convert speed to a string + * @speed: speed value + */ +static const char *ice_devlink_port_opt_speed_str(u8 speed) +{ + switch (speed & ICE_AQC_PORT_OPT_MAX_LANE_M) { + case ICE_AQC_PORT_OPT_MAX_LANE_100M: + return "0.1"; + case ICE_AQC_PORT_OPT_MAX_LANE_1G: + return "1"; + case ICE_AQC_PORT_OPT_MAX_LANE_2500M: + return "2.5"; + case ICE_AQC_PORT_OPT_MAX_LANE_5G: + return "5"; + case ICE_AQC_PORT_OPT_MAX_LANE_10G: + return "10"; + case ICE_AQC_PORT_OPT_MAX_LANE_25G: + return "25"; + case ICE_AQC_PORT_OPT_MAX_LANE_50G: + return "50"; + case ICE_AQC_PORT_OPT_MAX_LANE_100G: + return "100"; + } + + return "-"; +} + +#define ICE_PORT_OPT_DESC_LEN 50 +/** + * ice_devlink_port_options_print - Print available port split options + * @pf: the PF to print split port options + * + * Prints a table with available port split options and max port speeds + */ +static void ice_devlink_port_options_print(struct ice_pf *pf) +{ + u8 i, j, options_count, cnt, speed, pending_idx, active_idx; + struct ice_aqc_get_port_options_elem *options, *opt; + struct device *dev = ice_pf_to_dev(pf); + bool active_valid, pending_valid; + char desc[ICE_PORT_OPT_DESC_LEN]; + const char *str; + int status; + + options = kcalloc(ICE_AQC_PORT_OPT_MAX * ICE_MAX_PORT_PER_PCI_DEV, + sizeof(*options), GFP_KERNEL); + if (!options) + return; + + for (i = 0; i < ICE_MAX_PORT_PER_PCI_DEV; i++) { + opt = options + i * ICE_AQC_PORT_OPT_MAX; + options_count = ICE_AQC_PORT_OPT_MAX; + active_valid = 0; + + status = ice_aq_get_port_options(&pf->hw, opt, &options_count, + i, true, &active_idx, + &active_valid, &pending_idx, + &pending_valid); + if (status) { + dev_dbg(dev, "Couldn't read port option for port %d, err %d\n", + i, status); + goto err; + } + } + + dev_dbg(dev, "Available port split options and max port speeds (Gbps):\n"); + dev_dbg(dev, "Status Split Quad 0 Quad 1\n"); + dev_dbg(dev, " count L0 L1 L2 L3 L4 L5 L6 L7\n"); + + for (i = 0; i < options_count; i++) { + cnt = 0; + + if (i == ice_active_port_option) + str = "Active"; + else if ((i == pending_idx) && pending_valid) + str = "Pending"; + else + str = ""; + + cnt += snprintf(&desc[cnt], ICE_PORT_OPT_DESC_LEN - cnt, + "%-8s", str); + + cnt += snprintf(&desc[cnt], ICE_PORT_OPT_DESC_LEN - cnt, + "%-6u", options[i].pmd); + + for (j = 0; j < ICE_MAX_PORT_PER_PCI_DEV; ++j) { + speed = options[i + j * ICE_AQC_PORT_OPT_MAX].max_lane_speed; + str = ice_devlink_port_opt_speed_str(speed); + cnt += snprintf(&desc[cnt], ICE_PORT_OPT_DESC_LEN - cnt, + "%3s ", str); + } + + dev_dbg(dev, "%s\n", desc); + } + +err: + kfree(options); +} + +/** + * ice_devlink_aq_set_port_option - Send set port option admin queue command + * @pf: the PF to print split port options + * @option_idx: selected port option + * @extack: extended netdev ack structure + * + * Sends set port option admin queue command with selected port option and + * calls NVM write activate. + */ +static int +ice_devlink_aq_set_port_option(struct ice_pf *pf, u8 option_idx, + struct netlink_ext_ack *extack) +{ + struct device *dev = ice_pf_to_dev(pf); + int status; + + status = ice_aq_set_port_option(&pf->hw, 0, true, option_idx); + if (status) { + dev_dbg(dev, "ice_aq_set_port_option, err %d aq_err %d\n", + status, pf->hw.adminq.sq_last_status); + NL_SET_ERR_MSG_MOD(extack, "Port split request failed"); + return -EIO; + } + + status = ice_acquire_nvm(&pf->hw, ICE_RES_WRITE); + if (status) { + dev_dbg(dev, "ice_acquire_nvm failed, err %d aq_err %d\n", + status, pf->hw.adminq.sq_last_status); + NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore"); + return -EIO; + } + + status = ice_nvm_write_activate(&pf->hw, ICE_AQC_NVM_ACTIV_REQ_EMPR, NULL); + if (status) { + dev_dbg(dev, "ice_nvm_write_activate failed, err %d aq_err %d\n", + status, pf->hw.adminq.sq_last_status); + NL_SET_ERR_MSG_MOD(extack, "Port split request failed to save data"); + ice_release_nvm(&pf->hw); + return -EIO; + } + + ice_release_nvm(&pf->hw); + + NL_SET_ERR_MSG_MOD(extack, "Reboot required to finish port split"); + return 0; +} + +/** + * ice_devlink_port_split - .port_split devlink handler + * @devlink: devlink instance structure + * @port: devlink port structure + * @count: number of ports to split to + * @extack: extended netdev ack structure + * + * Callback for the devlink .port_split operation. + * + * Unfortunately, the devlink expression of available options is limited + * to just a number, so search for an FW port option which supports + * the specified number. As there could be multiple FW port options with + * the same port split count, allow switching between them. When the same + * port split count request is issued again, switch to the next FW port + * option with the same port split count. + * + * Return: zero on success or an error code on failure. + */ +static int +ice_devlink_port_split(struct devlink *devlink, struct devlink_port *port, + unsigned int count, struct netlink_ext_ack *extack) +{ + struct ice_aqc_get_port_options_elem options[ICE_AQC_PORT_OPT_MAX]; + u8 i, j, active_idx, pending_idx, new_option; + struct ice_pf *pf = devlink_priv(devlink); + u8 option_count = ICE_AQC_PORT_OPT_MAX; + struct device *dev = ice_pf_to_dev(pf); + bool active_valid, pending_valid; + int status; + + status = ice_aq_get_port_options(&pf->hw, options, &option_count, + 0, true, &active_idx, &active_valid, + &pending_idx, &pending_valid); + if (status) { + dev_dbg(dev, "Couldn't read port split options, err = %d\n", + status); + NL_SET_ERR_MSG_MOD(extack, "Failed to get available port split options"); + return -EIO; + } + + new_option = ICE_AQC_PORT_OPT_MAX; + active_idx = pending_valid ? pending_idx : active_idx; + for (i = 1; i <= option_count; i++) { + /* In order to allow switching between FW port options with + * the same port split count, search for a new option starting + * from the active/pending option (with array wrap around). + */ + j = (active_idx + i) % option_count; + + if (count == options[j].pmd) { + new_option = j; + break; + } + } + + if (new_option == active_idx) { + dev_dbg(dev, "request to split: count: %u is already set and there are no other options\n", + count); + NL_SET_ERR_MSG_MOD(extack, "Requested split count is already set"); + ice_devlink_port_options_print(pf); + return -EINVAL; + } + + if (new_option == ICE_AQC_PORT_OPT_MAX) { + dev_dbg(dev, "request to split: count: %u not found\n", count); + NL_SET_ERR_MSG_MOD(extack, "Port split requested unsupported port config"); + ice_devlink_port_options_print(pf); + return -EINVAL; + } + + status = ice_devlink_aq_set_port_option(pf, new_option, extack); + if (status) + return status; + + ice_devlink_port_options_print(pf); + + return 0; +} + +/** + * ice_devlink_port_unsplit - .port_unsplit devlink handler + * @devlink: devlink instance structure + * @port: devlink port structure + * @extack: extended netdev ack structure + * + * Callback for the devlink .port_unsplit operation. + * Calls ice_devlink_port_split with split count set to 1. + * There could be no FW option available with split count 1. + * + * Return: zero on success or an error code on failure. + */ +static int +ice_devlink_port_unsplit(struct devlink *devlink, struct devlink_port *port, + struct netlink_ext_ack *extack) +{ + return ice_devlink_port_split(devlink, port, 1, extack); +} + +/** + * ice_devlink_set_port_split_options - Set port split options + * @pf: the PF to set port split options + * @attrs: devlink attributes + * + * Sets devlink port split options based on available FW port options + */ +static void +ice_devlink_set_port_split_options(struct ice_pf *pf, + struct devlink_port_attrs *attrs) +{ + struct ice_aqc_get_port_options_elem options[ICE_AQC_PORT_OPT_MAX]; + u8 i, active_idx, pending_idx, option_count = ICE_AQC_PORT_OPT_MAX; + bool active_valid, pending_valid; + int status; + + status = ice_aq_get_port_options(&pf->hw, options, &option_count, + 0, true, &active_idx, &active_valid, + &pending_idx, &pending_valid); + if (status) { + dev_dbg(ice_pf_to_dev(pf), "Couldn't read port split options, err = %d\n", + status); + return; + } + + /* find the biggest available port split count */ + for (i = 0; i < option_count; i++) + attrs->lanes = max_t(int, attrs->lanes, options[i].pmd); + + attrs->splittable = attrs->lanes ? 1 : 0; + ice_active_port_option = active_idx; +} + +static const struct devlink_port_ops ice_devlink_port_ops = { + .port_split = ice_devlink_port_split, + .port_unsplit = ice_devlink_port_unsplit, +}; + +/** + * ice_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 +ice_devlink_set_switch_id(struct ice_pf *pf, struct netdev_phys_item_id *ppid) +{ + struct pci_dev *pdev = pf->pdev; + u64 id; + + id = pci_get_dsn(pdev); + + ppid->id_len = sizeof(id); + put_unaligned_be64(id, &ppid->id); +} + +/** + * ice_devlink_create_pf_port - Create a devlink port for this PF + * @pf: the PF to create a devlink port for + * + * Create and register a devlink_port for this PF. + * This function has to be called under devl_lock. + * + * Return: zero on success or an error code on failure. + */ +int ice_devlink_create_pf_port(struct ice_pf *pf) +{ + struct devlink_port_attrs attrs = {}; + struct devlink_port *devlink_port; + struct devlink *devlink; + struct ice_vsi *vsi; + struct device *dev; + int err; + + devlink = priv_to_devlink(pf); + + dev = ice_pf_to_dev(pf); + + devlink_port = &pf->devlink_port; + + vsi = ice_get_main_vsi(pf); + if (!vsi) + return -EIO; + + attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; + attrs.phys.port_number = pf->hw.pf_id; + + /* As FW supports only port split options for whole device, + * set port split options only for first PF. + */ + if (pf->hw.pf_id == 0) + ice_devlink_set_port_split_options(pf, &attrs); + + ice_devlink_set_switch_id(pf, &attrs.switch_id); + + devlink_port_attrs_set(devlink_port, &attrs); + + err = devl_port_register_with_ops(devlink, devlink_port, vsi->idx, + &ice_devlink_port_ops); + if (err) { + dev_err(dev, "Failed to create devlink port for PF %d, error %d\n", + pf->hw.pf_id, err); + return err; + } + + return 0; +} + +/** + * ice_devlink_destroy_pf_port - Destroy the devlink_port for this PF + * @pf: the PF to cleanup + * + * Unregisters the devlink_port structure associated with this PF. + * This function has to be called under devl_lock. + */ +void ice_devlink_destroy_pf_port(struct ice_pf *pf) +{ + devl_port_unregister(&pf->devlink_port); +} + +/** + * ice_devlink_port_get_vf_fn_mac - .port_fn_hw_addr_get devlink handler + * @port: devlink port structure + * @hw_addr: MAC address of the port + * @hw_addr_len: length of MAC address + * @extack: extended netdev ack structure + * + * Callback for the devlink .port_fn_hw_addr_get operation + * Return: zero on success or an error code on failure. + */ +static int ice_devlink_port_get_vf_fn_mac(struct devlink_port *port, + u8 *hw_addr, int *hw_addr_len, + struct netlink_ext_ack *extack) +{ + struct ice_vf *vf = container_of(port, struct ice_vf, devlink_port); + + ether_addr_copy(hw_addr, vf->dev_lan_addr); + *hw_addr_len = ETH_ALEN; + + return 0; +} + +/** + * ice_devlink_port_set_vf_fn_mac - .port_fn_hw_addr_set devlink handler + * @port: devlink port structure + * @hw_addr: MAC address of the port + * @hw_addr_len: length of MAC address + * @extack: extended netdev ack structure + * + * Callback for the devlink .port_fn_hw_addr_set operation + * Return: zero on success or an error code on failure. + */ +static int ice_devlink_port_set_vf_fn_mac(struct devlink_port *port, + const u8 *hw_addr, + int hw_addr_len, + struct netlink_ext_ack *extack) + +{ + struct devlink_port_attrs *attrs = &port->attrs; + struct devlink_port_pci_vf_attrs *pci_vf; + struct devlink *devlink = port->devlink; + struct ice_pf *pf; + u16 vf_id; + + pf = devlink_priv(devlink); + pci_vf = &attrs->pci_vf; + vf_id = pci_vf->vf; + + return __ice_set_vf_mac(pf, vf_id, hw_addr); +} + +static const struct devlink_port_ops ice_devlink_vf_port_ops = { + .port_fn_hw_addr_get = ice_devlink_port_get_vf_fn_mac, + .port_fn_hw_addr_set = ice_devlink_port_set_vf_fn_mac, +}; + +/** + * ice_devlink_create_vf_port - Create a devlink port for this VF + * @vf: the VF to create a port for + * + * Create and register a devlink_port for this VF. + * + * Return: zero on success or an error code on failure. + */ +int ice_devlink_create_vf_port(struct ice_vf *vf) +{ + struct devlink_port_attrs attrs = {}; + struct devlink_port *devlink_port; + struct devlink *devlink; + struct ice_vsi *vsi; + struct device *dev; + struct ice_pf *pf; + int err; + + pf = vf->pf; + dev = ice_pf_to_dev(pf); + devlink_port = &vf->devlink_port; + + vsi = ice_get_vf_vsi(vf); + if (!vsi) + return -EINVAL; + + attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_VF; + attrs.pci_vf.pf = pf->hw.pf_id; + attrs.pci_vf.vf = vf->vf_id; + + ice_devlink_set_switch_id(pf, &attrs.switch_id); + + devlink_port_attrs_set(devlink_port, &attrs); + devlink = priv_to_devlink(pf); + + err = devl_port_register_with_ops(devlink, devlink_port, vsi->idx, + &ice_devlink_vf_port_ops); + if (err) { + dev_err(dev, "Failed to create devlink port for VF %d, error %d\n", + vf->vf_id, err); + return err; + } + + return 0; +} + +/** + * ice_devlink_destroy_vf_port - Destroy the devlink_port for this VF + * @vf: the VF to cleanup + * + * Unregisters the devlink_port structure associated with this VF. + */ +void ice_devlink_destroy_vf_port(struct ice_vf *vf) +{ + devl_rate_leaf_destroy(&vf->devlink_port); + devl_port_unregister(&vf->devlink_port); +} + +/** + * ice_devlink_create_sf_dev_port - Register virtual port for a subfunction + * @sf_dev: the subfunction device to create a devlink port for + * + * Register virtual flavour devlink port for the subfunction auxiliary device + * created after activating a dynamically added devlink port. + * + * Return: zero on success or an error code on failure. + */ +int ice_devlink_create_sf_dev_port(struct ice_sf_dev *sf_dev) +{ + struct devlink_port_attrs attrs = {}; + struct ice_dynamic_port *dyn_port; + struct devlink_port *devlink_port; + struct devlink *devlink; + struct ice_vsi *vsi; + + dyn_port = sf_dev->dyn_port; + vsi = dyn_port->vsi; + + devlink_port = &sf_dev->priv->devlink_port; + + attrs.flavour = DEVLINK_PORT_FLAVOUR_VIRTUAL; + + devlink_port_attrs_set(devlink_port, &attrs); + devlink = priv_to_devlink(sf_dev->priv); + + return devl_port_register(devlink, devlink_port, vsi->idx); +} + +/** + * ice_devlink_destroy_sf_dev_port - Destroy virtual port for a subfunction + * @sf_dev: the subfunction device to create a devlink port for + * + * Unregisters the virtual port associated with this subfunction. + */ +void ice_devlink_destroy_sf_dev_port(struct ice_sf_dev *sf_dev) +{ + devl_port_unregister(&sf_dev->priv->devlink_port); +} + +/** + * ice_activate_dynamic_port - Activate a dynamic port + * @dyn_port: dynamic port instance to activate + * @extack: extack for reporting error messages + * + * Activate the dynamic port based on its flavour. + * + * Return: zero on success or an error code on failure. + */ +static int +ice_activate_dynamic_port(struct ice_dynamic_port *dyn_port, + struct netlink_ext_ack *extack) +{ + int err; + + if (dyn_port->active) + return 0; + + err = ice_sf_eth_activate(dyn_port, extack); + if (err) + return err; + + dyn_port->active = true; + + return 0; +} + +/** + * ice_deactivate_dynamic_port - Deactivate a dynamic port + * @dyn_port: dynamic port instance to deactivate + * + * Undo activation of a dynamic port. + */ +static void ice_deactivate_dynamic_port(struct ice_dynamic_port *dyn_port) +{ + if (!dyn_port->active) + return; + + ice_sf_eth_deactivate(dyn_port); + dyn_port->active = false; +} + +/** + * ice_dealloc_dynamic_port - Deallocate and remove a dynamic port + * @dyn_port: dynamic port instance to deallocate + * + * Free resources associated with a dynamically added devlink port. Will + * deactivate the port if its currently active. + */ +static void ice_dealloc_dynamic_port(struct ice_dynamic_port *dyn_port) +{ + struct devlink_port *devlink_port = &dyn_port->devlink_port; + struct ice_pf *pf = dyn_port->pf; + + ice_deactivate_dynamic_port(dyn_port); + + xa_erase(&pf->sf_nums, devlink_port->attrs.pci_sf.sf); + ice_eswitch_detach_sf(pf, dyn_port); + ice_vsi_free(dyn_port->vsi); + xa_erase(&pf->dyn_ports, dyn_port->vsi->idx); + kfree(dyn_port); +} + +/** + * ice_dealloc_all_dynamic_ports - Deallocate all dynamic devlink ports + * @pf: pointer to the pf structure + */ +void ice_dealloc_all_dynamic_ports(struct ice_pf *pf) +{ + struct ice_dynamic_port *dyn_port; + unsigned long index; + + xa_for_each(&pf->dyn_ports, index, dyn_port) + ice_dealloc_dynamic_port(dyn_port); +} + +/** + * ice_devlink_port_new_check_attr - Check that new port attributes are valid + * @pf: pointer to the PF structure + * @new_attr: the attributes for the new port + * @extack: extack for reporting error messages + * + * Check that the attributes for the new port are valid before continuing to + * allocate the devlink port. + * + * Return: zero on success or an error code on failure. + */ +static int +ice_devlink_port_new_check_attr(struct ice_pf *pf, + const struct devlink_port_new_attrs *new_attr, + struct netlink_ext_ack *extack) +{ + if (new_attr->flavour != DEVLINK_PORT_FLAVOUR_PCI_SF) { + NL_SET_ERR_MSG_MOD(extack, "Flavour other than pcisf is not supported"); + return -EOPNOTSUPP; + } + + if (new_attr->controller_valid) { + NL_SET_ERR_MSG_MOD(extack, "Setting controller is not supported"); + return -EOPNOTSUPP; + } + + if (new_attr->port_index_valid) { + NL_SET_ERR_MSG_MOD(extack, "Driver does not support user defined port index assignment"); + return -EOPNOTSUPP; + } + + if (new_attr->pfnum != pf->hw.pf_id) { + NL_SET_ERR_MSG_MOD(extack, "Incorrect pfnum supplied"); + return -EINVAL; + } + + if (!pci_msix_can_alloc_dyn(pf->pdev)) { + NL_SET_ERR_MSG_MOD(extack, "Dynamic MSIX-X interrupt allocation is not supported"); + return -EOPNOTSUPP; + } + + return 0; +} + +/** + * ice_devlink_port_del - devlink handler for port delete + * @devlink: pointer to devlink + * @port: devlink port to be deleted + * @extack: pointer to extack + * + * Deletes devlink port and deallocates all resources associated with + * created subfunction. + * + * Return: zero on success or an error code on failure. + */ +static int +ice_devlink_port_del(struct devlink *devlink, struct devlink_port *port, + struct netlink_ext_ack *extack) +{ + struct ice_dynamic_port *dyn_port; + + dyn_port = ice_devlink_port_to_dyn(port); + ice_dealloc_dynamic_port(dyn_port); + + return 0; +} + +/** + * ice_devlink_port_fn_hw_addr_set - devlink handler for mac address set + * @port: pointer to devlink port + * @hw_addr: hw address to set + * @hw_addr_len: hw address length + * @extack: extack for reporting error messages + * + * Sets mac address for the port, verifies arguments and copies address + * to the subfunction structure. + * + * Return: zero on success or an error code on failure. + */ +static int +ice_devlink_port_fn_hw_addr_set(struct devlink_port *port, const u8 *hw_addr, + int hw_addr_len, + struct netlink_ext_ack *extack) +{ + struct ice_dynamic_port *dyn_port; + + dyn_port = ice_devlink_port_to_dyn(port); + + if (dyn_port->attached) { + NL_SET_ERR_MSG_MOD(extack, + "Ethernet address can be change only in detached state"); + return -EBUSY; + } + + if (hw_addr_len != ETH_ALEN || !is_valid_ether_addr(hw_addr)) { + NL_SET_ERR_MSG_MOD(extack, "Invalid ethernet address"); + return -EADDRNOTAVAIL; + } + + ether_addr_copy(dyn_port->hw_addr, hw_addr); + + return 0; +} + +/** + * ice_devlink_port_fn_hw_addr_get - devlink handler for mac address get + * @port: pointer to devlink port + * @hw_addr: hw address to set + * @hw_addr_len: hw address length + * @extack: extack for reporting error messages + * + * Returns mac address for the port. + * + * Return: zero on success or an error code on failure. + */ +static int +ice_devlink_port_fn_hw_addr_get(struct devlink_port *port, u8 *hw_addr, + int *hw_addr_len, + struct netlink_ext_ack *extack) +{ + struct ice_dynamic_port *dyn_port; + + dyn_port = ice_devlink_port_to_dyn(port); + + ether_addr_copy(hw_addr, dyn_port->hw_addr); + *hw_addr_len = ETH_ALEN; + + return 0; +} + +/** + * ice_devlink_port_fn_state_set - devlink handler for port state set + * @port: pointer to devlink port + * @state: state to set + * @extack: extack for reporting error messages + * + * Activates or deactivates the port. + * + * Return: zero on success or an error code on failure. + */ +static int +ice_devlink_port_fn_state_set(struct devlink_port *port, + enum devlink_port_fn_state state, + struct netlink_ext_ack *extack) +{ + struct ice_dynamic_port *dyn_port; + + dyn_port = ice_devlink_port_to_dyn(port); + + switch (state) { + case DEVLINK_PORT_FN_STATE_ACTIVE: + return ice_activate_dynamic_port(dyn_port, extack); + + case DEVLINK_PORT_FN_STATE_INACTIVE: + ice_deactivate_dynamic_port(dyn_port); + break; + } + + return 0; +} + +/** + * ice_devlink_port_fn_state_get - devlink handler for port state get + * @port: pointer to devlink port + * @state: admin configured state of the port + * @opstate: current port operational state + * @extack: extack for reporting error messages + * + * Gets port state. + * + * Return: zero on success or an error code on failure. + */ +static int +ice_devlink_port_fn_state_get(struct devlink_port *port, + enum devlink_port_fn_state *state, + enum devlink_port_fn_opstate *opstate, + struct netlink_ext_ack *extack) +{ + struct ice_dynamic_port *dyn_port; + + dyn_port = ice_devlink_port_to_dyn(port); + + if (dyn_port->active) + *state = DEVLINK_PORT_FN_STATE_ACTIVE; + else + *state = DEVLINK_PORT_FN_STATE_INACTIVE; + + if (dyn_port->attached) + *opstate = DEVLINK_PORT_FN_OPSTATE_ATTACHED; + else + *opstate = DEVLINK_PORT_FN_OPSTATE_DETACHED; + + return 0; +} + +static const struct devlink_port_ops ice_devlink_port_sf_ops = { + .port_del = ice_devlink_port_del, + .port_fn_hw_addr_get = ice_devlink_port_fn_hw_addr_get, + .port_fn_hw_addr_set = ice_devlink_port_fn_hw_addr_set, + .port_fn_state_get = ice_devlink_port_fn_state_get, + .port_fn_state_set = ice_devlink_port_fn_state_set, +}; + +/** + * ice_reserve_sf_num - Reserve a subfunction number for this port + * @pf: pointer to the pf structure + * @new_attr: devlink port attributes requested + * @extack: extack for reporting error messages + * @sfnum: on success, the sf number reserved + * + * Reserve a subfunction number for this port. Only called for + * DEVLINK_PORT_FLAVOUR_PCI_SF ports. + * + * Return: zero on success or an error code on failure. + */ +static int +ice_reserve_sf_num(struct ice_pf *pf, + const struct devlink_port_new_attrs *new_attr, + struct netlink_ext_ack *extack, u32 *sfnum) +{ + int err; + + /* If user didn't request an explicit number, pick one */ + if (!new_attr->sfnum_valid) + return xa_alloc(&pf->sf_nums, sfnum, NULL, xa_limit_32b, + GFP_KERNEL); + + /* Otherwise, check and use the number provided */ + err = xa_insert(&pf->sf_nums, new_attr->sfnum, NULL, GFP_KERNEL); + if (err) { + if (err == -EBUSY) + NL_SET_ERR_MSG_MOD(extack, "Subfunction with given sfnum already exists"); + return err; + } + + *sfnum = new_attr->sfnum; + + return 0; +} + +/** + * ice_devlink_create_sf_port - Register PCI subfunction devlink port + * @dyn_port: the dynamic port instance structure for this subfunction + * + * Register PCI subfunction flavour devlink port for a dynamically added + * subfunction port. + * + * Return: zero on success or an error code on failure. + */ +int ice_devlink_create_sf_port(struct ice_dynamic_port *dyn_port) +{ + struct devlink_port_attrs attrs = {}; + struct devlink_port *devlink_port; + struct devlink *devlink; + struct ice_vsi *vsi; + struct ice_pf *pf; + + vsi = dyn_port->vsi; + pf = dyn_port->pf; + + devlink_port = &dyn_port->devlink_port; + + attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_SF; + attrs.pci_sf.pf = pf->hw.pf_id; + attrs.pci_sf.sf = dyn_port->sfnum; + + devlink_port_attrs_set(devlink_port, &attrs); + devlink = priv_to_devlink(pf); + + return devl_port_register_with_ops(devlink, devlink_port, vsi->idx, + &ice_devlink_port_sf_ops); +} + +/** + * ice_devlink_destroy_sf_port - Destroy the devlink_port for this SF + * @dyn_port: the dynamic port instance structure for this subfunction + * + * Unregisters the devlink_port structure associated with this SF. + */ +void ice_devlink_destroy_sf_port(struct ice_dynamic_port *dyn_port) +{ + devl_rate_leaf_destroy(&dyn_port->devlink_port); + devl_port_unregister(&dyn_port->devlink_port); +} + +/** + * ice_alloc_dynamic_port - Allocate new dynamic port + * @pf: pointer to the pf structure + * @new_attr: devlink port attributes requested + * @extack: extack for reporting error messages + * @devlink_port: index of newly created devlink port + * + * Allocate a new dynamic port instance and prepare it for configuration + * with devlink. + * + * Return: zero on success or an error code on failure. + */ +static int +ice_alloc_dynamic_port(struct ice_pf *pf, + const struct devlink_port_new_attrs *new_attr, + struct netlink_ext_ack *extack, + struct devlink_port **devlink_port) +{ + struct ice_dynamic_port *dyn_port; + struct ice_vsi *vsi; + u32 sfnum; + int err; + + err = ice_reserve_sf_num(pf, new_attr, extack, &sfnum); + if (err) + return err; + + dyn_port = kzalloc(sizeof(*dyn_port), GFP_KERNEL); + if (!dyn_port) { + err = -ENOMEM; + goto unroll_reserve_sf_num; + } + + vsi = ice_vsi_alloc(pf); + if (!vsi) { + NL_SET_ERR_MSG_MOD(extack, "Unable to allocate VSI"); + err = -ENOMEM; + goto unroll_dyn_port_alloc; + } + + dyn_port->vsi = vsi; + dyn_port->pf = pf; + dyn_port->sfnum = sfnum; + eth_random_addr(dyn_port->hw_addr); + + err = xa_insert(&pf->dyn_ports, vsi->idx, dyn_port, GFP_KERNEL); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Port index reservation failed"); + goto unroll_vsi_alloc; + } + + err = ice_eswitch_attach_sf(pf, dyn_port); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to attach SF to eswitch"); + goto unroll_xa_insert; + } + + *devlink_port = &dyn_port->devlink_port; + + return 0; + +unroll_xa_insert: + xa_erase(&pf->dyn_ports, vsi->idx); +unroll_vsi_alloc: + ice_vsi_free(vsi); +unroll_dyn_port_alloc: + kfree(dyn_port); +unroll_reserve_sf_num: + xa_erase(&pf->sf_nums, sfnum); + + return err; +} + +/** + * ice_devlink_port_new - devlink handler for the new port + * @devlink: pointer to devlink + * @new_attr: pointer to the port new attributes + * @extack: extack for reporting error messages + * @devlink_port: pointer to a new port + * + * Creates new devlink port, checks new port attributes and reject + * any unsupported parameters, allocates new subfunction for that port. + * + * Return: zero on success or an error code on failure. + */ +int +ice_devlink_port_new(struct devlink *devlink, + const struct devlink_port_new_attrs *new_attr, + struct netlink_ext_ack *extack, + struct devlink_port **devlink_port) +{ + struct ice_pf *pf = devlink_priv(devlink); + int err; + + err = ice_devlink_port_new_check_attr(pf, new_attr, extack); + if (err) + return err; + + if (!ice_is_eswitch_mode_switchdev(pf)) { + NL_SET_ERR_MSG_MOD(extack, + "SF ports are only supported in eswitch switchdev mode"); + return -EOPNOTSUPP; + } + + return ice_alloc_dynamic_port(pf, new_attr, extack, devlink_port); +} diff --git a/drivers/net/ethernet/intel/ice/devlink/port.h b/drivers/net/ethernet/intel/ice/devlink/port.h new file mode 100644 index 000000000000..d60efc340945 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/devlink/port.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024, Intel Corporation. */ + +#ifndef _DEVLINK_PORT_H_ +#define _DEVLINK_PORT_H_ + +#include "../ice.h" +#include "../ice_sf_eth.h" + +/** + * struct ice_dynamic_port - Track dynamically added devlink port instance + * @hw_addr: the HW address for this port + * @active: true if the port has been activated + * @attached: true it the prot is attached + * @devlink_port: the associated devlink port structure + * @pf: pointer to the PF private structure + * @vsi: the VSI associated with this port + * @repr_id: the representor ID + * @sfnum: the subfunction ID + * @sf_dev: pointer to the subfunction device + * + * An instance of a dynamically added devlink port. Each port flavour + */ +struct ice_dynamic_port { + u8 hw_addr[ETH_ALEN]; + u8 active: 1; + u8 attached: 1; + struct devlink_port devlink_port; + struct ice_pf *pf; + struct ice_vsi *vsi; + unsigned long repr_id; + u32 sfnum; + /* Flavour-specific implementation data */ + union { + struct ice_sf_dev *sf_dev; + }; +}; + +void ice_dealloc_all_dynamic_ports(struct ice_pf *pf); + +int ice_devlink_create_pf_port(struct ice_pf *pf); +void ice_devlink_destroy_pf_port(struct ice_pf *pf); +int ice_devlink_create_vf_port(struct ice_vf *vf); +void ice_devlink_destroy_vf_port(struct ice_vf *vf); +int ice_devlink_create_sf_port(struct ice_dynamic_port *dyn_port); +void ice_devlink_destroy_sf_port(struct ice_dynamic_port *dyn_port); +int ice_devlink_create_sf_dev_port(struct ice_sf_dev *sf_dev); +void ice_devlink_destroy_sf_dev_port(struct ice_sf_dev *sf_dev); + +#define ice_devlink_port_to_dyn(port) \ + container_of(port, struct ice_dynamic_port, devlink_port) + +int +ice_devlink_port_new(struct devlink *devlink, + const struct devlink_port_new_attrs *new_attr, + struct netlink_ext_ack *extack, + struct devlink_port **devlink_port); +#endif /* _DEVLINK_PORT_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 365c03d1c462..ddd0ad68185b 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -77,6 +77,8 @@ #include "ice_gnss.h" #include "ice_irq.h" #include "ice_dpll.h" +#include "ice_adapter.h" +#include "devlink/health.h" #define ICE_BAR0 0 #define ICE_REQ_DESC_MULTIPLE 32 @@ -95,9 +97,6 @@ #define ICE_MIN_LAN_OICR_MSIX 1 #define ICE_MIN_MSIX (ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_LAN_OICR_MSIX) #define ICE_FDIR_MSIX 2 -#define ICE_RDMA_NUM_AEQ_MSIX 4 -#define ICE_MIN_RDMA_MSIX 2 -#define ICE_ESWITCH_MSIX 1 #define ICE_NO_VSI 0xffff #define ICE_VSI_MAP_CONTIG 0 #define ICE_VSI_MAP_SCATTER 1 @@ -180,11 +179,9 @@ #define ice_for_each_chnl_tc(i) \ for ((i) = ICE_CHNL_START_TC; (i) < ICE_CHNL_MAX_TC; (i)++) -#define ICE_UCAST_PROMISC_BITS (ICE_PROMISC_UCAST_TX | ICE_PROMISC_UCAST_RX) +#define ICE_UCAST_PROMISC_BITS ICE_PROMISC_UCAST_RX -#define ICE_UCAST_VLAN_PROMISC_BITS (ICE_PROMISC_UCAST_TX | \ - ICE_PROMISC_UCAST_RX | \ - ICE_PROMISC_VLAN_TX | \ +#define ICE_UCAST_VLAN_PROMISC_BITS (ICE_PROMISC_UCAST_RX | \ ICE_PROMISC_VLAN_RX) #define ICE_MCAST_PROMISC_BITS (ICE_PROMISC_MCAST_TX | ICE_PROMISC_MCAST_RX) @@ -196,16 +193,16 @@ #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_PHY_RCLK, ICE_F_SMA_CTRL, ICE_F_CGU, ICE_F_GNSS, + ICE_F_GCS, ICE_F_ROCE_LAG, ICE_F_SRIOV_LAG, + ICE_F_MBX_LIMIT, ICE_F_MAX }; @@ -317,6 +314,7 @@ enum ice_vsi_state { ICE_VSI_UMAC_FLTR_CHANGED, ICE_VSI_MMAC_FLTR_CHANGED, ICE_VSI_PROMISC_CHANGED, + ICE_VSI_REBUILD_PENDING, ICE_VSI_STATE_NBITS /* must be last */ }; @@ -330,7 +328,6 @@ struct ice_vsi { struct net_device *netdev; struct ice_sw *vsw; /* switch this VSI is on */ struct ice_pf *back; /* back pointer to PF */ - struct ice_port_info *port_info; /* back pointer to port_info */ struct ice_rx_ring **rx_rings; /* Rx ring array */ struct ice_tx_ring **tx_rings; /* Tx ring array */ struct ice_q_vector **q_vectors; /* q_vector array */ @@ -348,12 +345,9 @@ struct ice_vsi { /* tell if only dynamic irq allocation is allowed */ bool irq_dyn_alloc; - enum ice_vsi_type type; u16 vsi_num; /* HW (absolute) index of this VSI */ u16 idx; /* software index in pf->vsi[] */ - struct ice_vf *vf; /* VF associated with this VSI */ - u16 num_gfltr; u16 num_bfltr; @@ -373,9 +367,6 @@ struct ice_vsi { spinlock_t arfs_lock; /* protects aRFS hash table and filter state */ atomic_t *arfs_last_fltr_id; - u16 max_frame; - u16 rx_buf_len; - struct ice_aqc_vsi_props info; /* VSI properties */ struct ice_vsi_vlan_info vlan_info; /* vlan config to be restored */ @@ -408,13 +399,12 @@ struct ice_vsi { u16 req_rxq; /* User requested Rx queues */ u16 num_rx_desc; u16 num_tx_desc; - u16 qset_handle[ICE_MAX_TRAFFIC_CLASS]; struct ice_tc_cfg tc_cfg; struct bpf_prog *xdp_prog; struct ice_tx_ring **xdp_rings; /* XDP ring array */ - unsigned long *af_xdp_zc_qps; /* tracks AF_XDP ZC enabled qps */ u16 num_xdp_txq; /* Used XDP queues */ u8 xdp_mapping_mode; /* ICE_MAP_MODE_[CONTIG|SCATTER] */ + struct mutex xdp_state_lock; struct net_device **target_netdevs; @@ -445,12 +435,23 @@ struct ice_vsi { u8 old_numtc; u16 old_ena_tc; - struct ice_channel *ch; - /* setup back reference, to which aggregator node this VSI * corresponds to */ struct ice_agg_node *agg_node; + + struct_group_tagged(ice_vsi_cfg_params, params, + struct ice_port_info *port_info; /* back pointer to port_info */ + struct ice_channel *ch; /* VSI's channel structure, may be NULL */ + union { + /* VF associated with this VSI, may be NULL */ + struct ice_vf *vf; + /* SF associated with this VSI, may be NULL */ + struct ice_dynamic_port *sf; + }; + u32 flags; /* VSI flags used for rebuild and configuration */ + enum ice_vsi_type type; /* the type of the VSI */ + ); } ____cacheline_internodealigned_in_smp; /* struct that defines an interrupt vector */ @@ -458,7 +459,7 @@ struct ice_q_vector { struct ice_vsi *vsi; u16 v_idx; /* index in the vsi->q_vector array. */ - u16 reg_idx; + u16 reg_idx; /* PF relative register index */ u8 num_ring_rx; /* total number of Rx rings in vector */ u8 num_ring_tx; /* total number of Tx rings in vector */ u8 wb_on_itr:1; /* if true, WB on ITR is enabled */ @@ -472,14 +473,12 @@ struct ice_q_vector { struct ice_ring_container rx; struct ice_ring_container tx; - cpumask_t affinity_mask; - struct irq_affinity_notify affinity_notify; - struct ice_channel *ch; char name[ICE_INT_NAME_STR_LEN]; u16 total_events; /* net_dim(): number of interrupts processed */ + u16 vf_reg_idx; /* VF relative register index */ struct msi_map irq; } ____cacheline_internodealigned_in_smp; @@ -513,6 +512,7 @@ enum ice_pf_flags { ICE_FLAG_MTU_CHANGED, ICE_FLAG_GNSS, /* GNSS successfully initialized */ ICE_FLAG_DPLL, /* SyncE/PTP dplls initialized */ + ICE_FLAG_LLDP_AQ_FLTR, ICE_PF_FLAGS_NBITS /* must be last */ }; @@ -522,17 +522,10 @@ enum ice_misc_thread_tasks { }; struct ice_eswitch { - struct ice_vsi *control_vsi; struct ice_vsi *uplink_vsi; struct ice_esw_br_offloads *br_offloads; struct xarray reprs; bool is_running; - /* struct to allow cp queues management optimization */ - struct { - int to_reach; - int value; - bool is_reaching; - } qs; }; struct ice_agg_node { @@ -542,8 +535,17 @@ struct ice_agg_node { u8 valid; }; +struct ice_pf_msix { + u32 cur; + u32 min; + u32 max; + u32 total; + u32 rest; +}; + struct ice_pf { struct pci_dev *pdev; + struct ice_adapter *adapter; struct devlink_region *nvm_region; struct devlink_region *sram_region; @@ -553,15 +555,8 @@ struct ice_pf { struct devlink_port devlink_port; /* OS reserved IRQ details */ - struct msix_entry *msix_entries; struct ice_irq_tracker irq_tracker; - /* First MSIX vector used by SR-IOV VFs. Calculated by subtracting the - * number of MSIX vectors needed for all SR-IOV VFs from the number of - * 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 */ + struct ice_virt_irq_tracker virt_irq_tracker; u16 ctrl_vsi_idx; /* control VSI index in pf->vsi array */ @@ -594,7 +589,6 @@ struct ice_pf { struct gnss_serial *gnss_serial; struct gnss_device *gnss_dev; u16 num_rdma_msix; /* Total MSIX vectors for RDMA driver */ - u16 rdma_base_vector; /* spinlock to protect the AdminQ wait list */ spinlock_t aq_wait_lock; @@ -611,7 +605,7 @@ struct ice_pf { struct msi_map ll_ts_irq; /* LL_TS interrupt MSIX vector */ u16 max_pf_txqs; /* Total Tx queues PF wide */ u16 max_pf_rxqs; /* Total Rx queues PF wide */ - u16 num_lan_msix; /* Total MSIX vectors for base driver */ + struct ice_pf_msix msix; u16 num_lan_tx; /* num LAN Tx queues setup */ u16 num_lan_rx; /* num LAN Rx queues setup */ u16 next_vsi; /* Next free slot in pf->vsi[] - 0-based! */ @@ -627,14 +621,12 @@ struct ice_pf { struct ice_hw_port_stats stats_prev; struct ice_hw hw; u8 stat_prev_loaded:1; /* has previous stats been loaded */ - u8 rdma_mode; u16 dcbx_cap; u32 tx_timeout_count; unsigned long tx_timeout_last_recovery; u32 tx_timeout_recovery_level; char int_name[ICE_INT_NAME_STR_LEN]; char int_name_ll_ts[ICE_INT_NAME_STR_LEN]; - struct auxiliary_device *adev; int aux_idx; u32 sw_int_count; /* count of tc_flower filters specific to channel (aka where filter @@ -653,6 +645,9 @@ struct ice_pf { struct ice_eswitch eswitch; struct ice_esw_br_port *br_port; + struct xarray dyn_ports; + struct xarray sf_nums; + #define ICE_INVALID_AGG_NODE_ID 0 #define ICE_PF_AGG_NODE_ID_START 1 #define ICE_MAX_PF_AGG_NODES 32 @@ -662,6 +657,10 @@ struct ice_pf { struct ice_agg_node vf_agg_node[ICE_MAX_VF_AGG_NODES]; struct ice_dplls dplls; struct device *hwmon_dev; + struct ice_health health_reporters; + struct iidc_rdma_core_dev_info *cdev_info; + + u8 num_quanta_prof_used; }; extern struct workqueue_struct *ice_lag_wq; @@ -749,21 +748,36 @@ static inline void ice_set_ring_xdp(struct ice_tx_ring *ring) } /** - * ice_xsk_pool - get XSK buffer pool bound to a ring + * ice_get_xp_from_qid - get ZC XSK buffer pool bound to a queue ID + * @vsi: pointer to VSI + * @qid: index of a queue to look at XSK buff pool presence + * + * Return: A pointer to xsk_buff_pool structure if there is a buffer pool + * attached and configured as zero-copy, NULL otherwise. + */ +static inline struct xsk_buff_pool *ice_get_xp_from_qid(struct ice_vsi *vsi, + u16 qid) +{ + struct xsk_buff_pool *pool = xsk_get_pool_from_qid(vsi->netdev, qid); + + if (!ice_is_xdp_ena_vsi(vsi)) + return NULL; + + return (pool && pool->dev) ? pool : NULL; +} + +/** + * ice_rx_xsk_pool - assign XSK buff pool to Rx ring * @ring: Rx ring to use * - * Returns a pointer to xsk_buff_pool structure if there is a buffer pool - * present, NULL otherwise. + * Sets XSK buff pool pointer on Rx ring. */ -static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring) +static inline void ice_rx_xsk_pool(struct ice_rx_ring *ring) { struct ice_vsi *vsi = ring->vsi; u16 qid = ring->q_index; - if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps)) - return NULL; - - return xsk_get_pool_from_qid(vsi->netdev, qid); + WRITE_ONCE(ring->xsk_pool, ice_get_xp_from_qid(vsi, qid)); } /** @@ -788,12 +802,7 @@ static inline void ice_tx_xsk_pool(struct ice_vsi *vsi, u16 qid) if (!ring) return; - if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps)) { - ring->xsk_pool = NULL; - return; - } - - ring->xsk_pool = xsk_get_pool_from_qid(vsi->netdev, qid); + WRITE_ONCE(ring->xsk_pool, ice_get_xp_from_qid(vsi, qid)); } /** @@ -909,6 +918,7 @@ int ice_vsi_open(struct ice_vsi *vsi); void ice_set_ethtool_ops(struct net_device *netdev); void ice_set_ethtool_repr_ops(struct net_device *netdev); void ice_set_ethtool_safe_mode_ops(struct net_device *netdev); +void ice_set_ethtool_sf_ops(struct net_device *netdev); u16 ice_get_avail_txq_count(struct ice_pf *pf); u16 ice_get_avail_rxq_count(struct ice_pf *pf); int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked); @@ -922,9 +932,17 @@ int ice_down(struct ice_vsi *vsi); int ice_down_up(struct ice_vsi *vsi); int ice_vsi_cfg_lan(struct ice_vsi *vsi); struct ice_vsi *ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi); + +enum ice_xdp_cfg { + ICE_XDP_CFG_FULL, /* Fully apply new config in .ndo_bpf() */ + ICE_XDP_CFG_PART, /* Save/use part of config in VSI rebuild */ +}; + int ice_vsi_determine_xdp_res(struct ice_vsi *vsi); -int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog); -int ice_destroy_xdp_rings(struct ice_vsi *vsi); +int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog, + enum ice_xdp_cfg cfg_type); +int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type); +void ice_map_xdp_rings(struct ice_vsi *vsi); int ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags); @@ -986,6 +1004,14 @@ void ice_unload(struct ice_pf *pf); void ice_adv_lnk_speed_maps_init(void); int ice_init_dev(struct ice_pf *pf); void ice_deinit_dev(struct ice_pf *pf); +int ice_change_mtu(struct net_device *netdev, int new_mtu); +void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue); +int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp); +void ice_set_netdev_features(struct net_device *netdev); +int ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid); +int ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid); +void ice_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats); /** * ice_set_rdma_cap - enable RDMA support @@ -1014,4 +1040,62 @@ static inline void ice_clear_rdma_cap(struct ice_pf *pf) } extern const struct xdp_metadata_ops ice_xdp_md_ops; + +/** + * ice_is_dual - Check if given config is multi-NAC + * @hw: pointer to HW structure + * + * Return: true if the device is running in mutli-NAC (Network + * Acceleration Complex) configuration variant, false otherwise + * (always false for non-E825 devices). + */ +static inline bool ice_is_dual(struct ice_hw *hw) +{ + return hw->mac_type == ICE_MAC_GENERIC_3K_E825 && + (hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_DUAL_M); +} + +/** + * ice_is_primary - Check if given device belongs to the primary complex + * @hw: pointer to HW structure + * + * Check if given PF/HW is running on primary complex in multi-NAC + * configuration. + * + * Return: true if the device is dual, false otherwise (always true + * for non-E825 devices). + */ +static inline bool ice_is_primary(struct ice_hw *hw) +{ + return hw->mac_type != ICE_MAC_GENERIC_3K_E825 || + !ice_is_dual(hw) || + (hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_PRIMARY_M); +} + +/** + * ice_pf_src_tmr_owned - Check if a primary timer is owned by PF + * @pf: pointer to PF structure + * + * Return: true if PF owns primary timer, false otherwise. + */ +static inline bool ice_pf_src_tmr_owned(struct ice_pf *pf) +{ + return pf->hw.func_caps.ts_func_info.src_tmr_owned && + ice_is_primary(&pf->hw); +} + +/** + * ice_get_primary_hw - Get pointer to primary ice_hw structure + * @pf: pointer to PF structure + * + * Return: A pointer to ice_hw structure with access to timesync + * register space. + */ +static inline struct ice_hw *ice_get_primary_hw(struct ice_pf *pf) +{ + if (!pf->adapter->ctrl_pf) + return &pf->hw; + else + return &pf->adapter->ctrl_pf->hw; +} #endif /* _ICE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.c b/drivers/net/ethernet/intel/ice/ice_adapter.c new file mode 100644 index 000000000000..66e070095d1b --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_adapter.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0-only +// SPDX-FileCopyrightText: Copyright Red Hat + +#include <linux/cleanup.h> +#include <linux/mutex.h> +#include <linux/pci.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/xarray.h> +#include "ice_adapter.h" +#include "ice.h" + +static DEFINE_XARRAY(ice_adapters); +static DEFINE_MUTEX(ice_adapters_mutex); + +static unsigned long ice_adapter_index(u64 dsn) +{ +#if BITS_PER_LONG == 64 + return dsn; +#else + return (u32)dsn ^ (u32)(dsn >> 32); +#endif +} + +static struct ice_adapter *ice_adapter_new(u64 dsn) +{ + struct ice_adapter *adapter; + + adapter = kzalloc(sizeof(*adapter), GFP_KERNEL); + if (!adapter) + return NULL; + + adapter->device_serial_number = dsn; + spin_lock_init(&adapter->ptp_gltsyn_time_lock); + refcount_set(&adapter->refcount, 1); + + mutex_init(&adapter->ports.lock); + INIT_LIST_HEAD(&adapter->ports.ports); + + return adapter; +} + +static void ice_adapter_free(struct ice_adapter *adapter) +{ + WARN_ON(!list_empty(&adapter->ports.ports)); + mutex_destroy(&adapter->ports.lock); + + kfree(adapter); +} + +/** + * ice_adapter_get - Get a shared ice_adapter structure. + * @pdev: Pointer to the pci_dev whose driver is getting the ice_adapter. + * + * Gets a pointer to a shared ice_adapter structure. Physical functions (PFs) + * of the same multi-function PCI device share one ice_adapter structure. + * The ice_adapter is reference-counted. The PF driver must use ice_adapter_put + * to release its reference. + * + * Context: Process, may sleep. + * Return: Pointer to ice_adapter on success. + * ERR_PTR() on error. -ENOMEM is the only possible error. + */ +struct ice_adapter *ice_adapter_get(struct pci_dev *pdev) +{ + u64 dsn = pci_get_dsn(pdev); + struct ice_adapter *adapter; + unsigned long index; + int err; + + index = ice_adapter_index(dsn); + scoped_guard(mutex, &ice_adapters_mutex) { + err = xa_insert(&ice_adapters, index, NULL, GFP_KERNEL); + if (err == -EBUSY) { + adapter = xa_load(&ice_adapters, index); + refcount_inc(&adapter->refcount); + WARN_ON_ONCE(adapter->device_serial_number != dsn); + return adapter; + } + if (err) + return ERR_PTR(err); + + adapter = ice_adapter_new(dsn); + if (!adapter) + return ERR_PTR(-ENOMEM); + xa_store(&ice_adapters, index, adapter, GFP_KERNEL); + } + return adapter; +} + +/** + * ice_adapter_put - Release a reference to the shared ice_adapter structure. + * @pdev: Pointer to the pci_dev whose driver is releasing the ice_adapter. + * + * Releases the reference to ice_adapter previously obtained with + * ice_adapter_get. + * + * Context: Process, may sleep. + */ +void ice_adapter_put(struct pci_dev *pdev) +{ + u64 dsn = pci_get_dsn(pdev); + struct ice_adapter *adapter; + unsigned long index; + + index = ice_adapter_index(dsn); + scoped_guard(mutex, &ice_adapters_mutex) { + adapter = xa_load(&ice_adapters, index); + if (WARN_ON(!adapter)) + return; + if (!refcount_dec_and_test(&adapter->refcount)) + return; + + WARN_ON(xa_erase(&ice_adapters, index) != adapter); + } + ice_adapter_free(adapter); +} diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.h b/drivers/net/ethernet/intel/ice/ice_adapter.h new file mode 100644 index 000000000000..ac15c0d2bc1a --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_adapter.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-FileCopyrightText: Copyright Red Hat */ + +#ifndef _ICE_ADAPTER_H_ +#define _ICE_ADAPTER_H_ + +#include <linux/types.h> +#include <linux/spinlock_types.h> +#include <linux/refcount_types.h> + +struct pci_dev; +struct ice_pf; + +/** + * struct ice_port_list - data used to store the list of adapter ports + * + * This structure contains data used to maintain a list of adapter ports + * + * @ports: list of ports + * @lock: protect access to the ports list + */ +struct ice_port_list { + struct list_head ports; + /* To synchronize the ports list operations */ + struct mutex lock; +}; + +/** + * struct ice_adapter - PCI adapter resources shared across PFs + * @ptp_gltsyn_time_lock: Spinlock protecting access to the GLTSYN_TIME + * register of the PTP clock. + * @refcount: Reference count. struct ice_pf objects hold the references. + * @ctrl_pf: Control PF of the adapter + * @ports: Ports list + * @device_serial_number: DSN cached for collision detection on 32bit systems + */ +struct ice_adapter { + refcount_t refcount; + /* For access to the GLTSYN_TIME register */ + spinlock_t ptp_gltsyn_time_lock; + + struct ice_pf *ctrl_pf; + struct ice_port_list ports; + u64 device_serial_number; +}; + +struct ice_adapter *ice_adapter_get(struct pci_dev *pdev); +void ice_adapter_put(struct pci_dev *pdev); + +#endif /* _ICE_ADAPTER_H */ diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 1f3e7a6903e5..bdee499f991a 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -12,6 +12,13 @@ #define ICE_AQC_TOPO_MAX_LEVEL_NUM 0x9 #define ICE_AQ_SET_MAC_FRAME_SIZE_MAX 9728 +#define ICE_RXQ_CTX_SIZE_DWORDS 8 +#define ICE_RXQ_CTX_SZ (ICE_RXQ_CTX_SIZE_DWORDS * sizeof(u32)) +#define ICE_TXQ_CTX_SZ 22 + +typedef struct __packed { u8 buf[ICE_RXQ_CTX_SZ]; } ice_rxq_ctx_buf_t; +typedef struct __packed { u8 buf[ICE_TXQ_CTX_SZ]; } ice_txq_ctx_buf_t; + struct ice_aqc_generic { __le32 param0; __le32 param1; @@ -121,6 +128,8 @@ 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_TX_SCHED_TOPO_COMP_MODE 0x0085 +#define ICE_AQC_CAPS_NAC_TOPOLOGY 0x0087 #define ICE_AQC_CAPS_FW_LAG_SUPPORT 0x0092 #define ICE_AQC_BIT_ROCEV2_LAG 0x01 #define ICE_AQC_BIT_SRIOV_LAG 0x02 @@ -230,6 +239,13 @@ struct ice_aqc_get_sw_cfg_resp_elem { #define ICE_AQC_GET_SW_CONF_RESP_IS_VF BIT(15) }; +/* Loopback port parameter mode values. */ +enum ice_local_fwd_mode { + ICE_LOCAL_FWD_MODE_ENABLED = 0, + ICE_LOCAL_FWD_MODE_DISABLED = 1, + ICE_LOCAL_FWD_MODE_PRIORITIZED = 2, +}; + /* Set Port parameters, (direct, 0x0203) */ struct ice_aqc_set_port_params { __le16 cmd_flags; @@ -238,7 +254,9 @@ struct ice_aqc_set_port_params { __le16 swid; #define ICE_AQC_PORT_SWID_VALID BIT(15) #define ICE_AQC_PORT_SWID_M 0xFF - u8 reserved[10]; + u8 local_fwd_mode; +#define ICE_AQC_SET_P_PARAMS_LOCAL_FWD_MODE_VALID BIT(2) + u8 reserved[9]; }; /* These resource type defines are used for all switch resource @@ -264,6 +282,8 @@ struct ice_aqc_set_port_params { #define ICE_AQC_RES_TYPE_FLAG_SHARED BIT(7) #define ICE_AQC_RES_TYPE_FLAG_SCAN_BOTTOM BIT(12) #define ICE_AQC_RES_TYPE_FLAG_IGNORE_INDEX BIT(13) +#define ICE_AQC_RES_TYPE_FLAG_SUBSCRIBE_SHARED BIT(14) +#define ICE_AQC_RES_TYPE_FLAG_SUBSCRIBE_CTL BIT(15) #define ICE_AQC_RES_TYPE_FLAG_DEDICATED 0x00 @@ -808,6 +828,23 @@ struct ice_aqc_get_topo { __le32 addr_low; }; +/* Get/Set Tx Topology (indirect 0x0418/0x0417) */ +struct ice_aqc_get_set_tx_topo { + u8 set_flags; +#define ICE_AQC_TX_TOPO_FLAGS_CORRER BIT(0) +#define ICE_AQC_TX_TOPO_FLAGS_SRC_RAM BIT(1) +#define ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW BIT(4) +#define ICE_AQC_TX_TOPO_FLAGS_ISSUED BIT(5) + + u8 get_flags; +#define ICE_AQC_TX_TOPO_GET_RAM 2 + + __le16 reserved1; + __le32 reserved2; + __le32 addr_high; + __le32 addr_low; +}; + /* Update TSE (indirect 0x0403) * Get TSE (indirect 0x0404) * Add TSE (indirect 0x0401) @@ -1440,6 +1477,71 @@ struct ice_aqc_get_sensor_reading_resp { } data; }; +/* DNL call command (indirect 0x0682) + * Struct is used for both command and response + */ +struct ice_aqc_dnl_call_command { + u8 ctx; /* Used in command, reserved in response */ + u8 reserved; + __le16 activity_id; +#define ICE_AQC_ACT_ID_DNL 0x1129 + __le32 reserved1; + __le32 addr_high; + __le32 addr_low; +}; + +struct ice_aqc_dnl_equa_param { + __le16 data_in; +#define ICE_AQC_RX_EQU_SHIFT 8 +#define ICE_AQC_RX_EQU_PRE2 (0x10 << ICE_AQC_RX_EQU_SHIFT) +#define ICE_AQC_RX_EQU_PRE1 (0x11 << ICE_AQC_RX_EQU_SHIFT) +#define ICE_AQC_RX_EQU_POST1 (0x12 << ICE_AQC_RX_EQU_SHIFT) +#define ICE_AQC_RX_EQU_BFLF (0x13 << ICE_AQC_RX_EQU_SHIFT) +#define ICE_AQC_RX_EQU_BFHF (0x14 << ICE_AQC_RX_EQU_SHIFT) +#define ICE_AQC_RX_EQU_CTLE_GAINHF (0x20 << ICE_AQC_RX_EQU_SHIFT) +#define ICE_AQC_RX_EQU_CTLE_GAINLF (0x21 << ICE_AQC_RX_EQU_SHIFT) +#define ICE_AQC_RX_EQU_CTLE_GAINDC (0x22 << ICE_AQC_RX_EQU_SHIFT) +#define ICE_AQC_RX_EQU_CTLE_BW (0x23 << ICE_AQC_RX_EQU_SHIFT) +#define ICE_AQC_RX_EQU_DFE_GAIN (0x30 << ICE_AQC_RX_EQU_SHIFT) +#define ICE_AQC_RX_EQU_DFE_GAIN2 (0x31 << ICE_AQC_RX_EQU_SHIFT) +#define ICE_AQC_RX_EQU_DFE_2 (0x32 << ICE_AQC_RX_EQU_SHIFT) +#define ICE_AQC_RX_EQU_DFE_3 (0x33 << ICE_AQC_RX_EQU_SHIFT) +#define ICE_AQC_RX_EQU_DFE_4 (0x34 << ICE_AQC_RX_EQU_SHIFT) +#define ICE_AQC_RX_EQU_DFE_5 (0x35 << ICE_AQC_RX_EQU_SHIFT) +#define ICE_AQC_RX_EQU_DFE_6 (0x36 << ICE_AQC_RX_EQU_SHIFT) +#define ICE_AQC_RX_EQU_DFE_7 (0x37 << ICE_AQC_RX_EQU_SHIFT) +#define ICE_AQC_RX_EQU_DFE_8 (0x38 << ICE_AQC_RX_EQU_SHIFT) +#define ICE_AQC_RX_EQU_DFE_9 (0x39 << ICE_AQC_RX_EQU_SHIFT) +#define ICE_AQC_RX_EQU_DFE_10 (0x3A << ICE_AQC_RX_EQU_SHIFT) +#define ICE_AQC_RX_EQU_DFE_11 (0x3B << ICE_AQC_RX_EQU_SHIFT) +#define ICE_AQC_RX_EQU_DFE_12 (0x3C << ICE_AQC_RX_EQU_SHIFT) +#define ICE_AQC_TX_EQU_PRE1 0x0 +#define ICE_AQC_TX_EQU_PRE3 0x3 +#define ICE_AQC_TX_EQU_ATTEN 0x4 +#define ICE_AQC_TX_EQU_POST1 0x8 +#define ICE_AQC_TX_EQU_PRE2 0xC + __le16 op_code_serdes_sel; +#define ICE_AQC_OP_CODE_SHIFT 4 +#define ICE_AQC_OP_CODE_RX_EQU (0x9 << ICE_AQC_OP_CODE_SHIFT) +#define ICE_AQC_OP_CODE_TX_EQU (0x10 << ICE_AQC_OP_CODE_SHIFT) + __le32 reserved[3]; +}; + +struct ice_aqc_dnl_equa_respon { + /* Equalization value can be negative */ + int val; + __le32 reserved[3]; +}; + +/* DNL call command/response buffer (indirect 0x0682) */ +struct ice_aqc_dnl_call { + union { + struct ice_aqc_dnl_equa_param txrx_equa_reqs; + __le32 stores[4]; + struct ice_aqc_dnl_equa_respon txrx_equa_resp; + } sto; +}; + struct ice_aqc_link_topo_params { u8 lport_num; u8 lport_num_valid; @@ -1569,6 +1671,7 @@ struct ice_aqc_get_port_options_elem { #define ICE_AQC_PORT_OPT_MAX_LANE_25G 5 #define ICE_AQC_PORT_OPT_MAX_LANE_50G 6 #define ICE_AQC_PORT_OPT_MAX_LANE_100G 7 +#define ICE_AQC_PORT_OPT_MAX_LANE_200G 8 u8 global_scid[2]; u8 phy_scid[2]; @@ -1663,6 +1766,24 @@ struct ice_aqc_nvm { }; #define ICE_AQC_NVM_START_POINT 0 +#define ICE_AQC_NVM_SECTOR_UNIT 4096 +#define ICE_AQC_NVM_SDP_AC_PTR_OFFSET 0xD8 +#define ICE_AQC_NVM_SDP_AC_PTR_M GENMASK(14, 0) +#define ICE_AQC_NVM_SDP_AC_PTR_INVAL 0x7FFF +#define ICE_AQC_NVM_SDP_AC_PTR_TYPE_M BIT(15) +#define ICE_AQC_NVM_SDP_AC_SDP_NUM_M GENMASK(2, 0) +#define ICE_AQC_NVM_SDP_AC_DIR_M BIT(3) +#define ICE_AQC_NVM_SDP_AC_PIN_M GENMASK(15, 6) +#define ICE_AQC_NVM_SDP_AC_MAX_SIZE 7 + +#define ICE_AQC_NVM_TX_TOPO_MOD_ID 0x14B + +struct ice_aqc_nvm_tx_topo_user_sel { + __le16 length; + u8 data; +#define ICE_AQC_NVM_TX_TOPO_USER_SEL BIT(4) + u8 reserved; +}; /* NVM Checksum Command (direct, 0x0706) */ struct ice_aqc_nvm_checksum { @@ -1693,6 +1814,7 @@ struct ice_aqc_nvm_pass_comp_tbl { #define ICE_AQ_NVM_PASS_COMP_CAN_BE_UPDATED 0x0 #define ICE_AQ_NVM_PASS_COMP_CAN_MAY_BE_UPDATEABLE 0x1 #define ICE_AQ_NVM_PASS_COMP_CAN_NOT_BE_UPDATED 0x2 +#define ICE_AQ_NVM_PASS_COMP_PARTIAL_CHECK 0x3 u8 component_response_code; /* Response only */ #define ICE_AQ_NVM_PASS_COMP_CAN_BE_UPDATED_CODE 0x0 #define ICE_AQ_NVM_PASS_COMP_STAMP_IDENTICAL_CODE 0x1 @@ -1970,10 +2092,10 @@ struct ice_aqc_add_txqs_perq { __le16 txq_id; u8 rsvd[2]; __le32 q_teid; - u8 txq_ctx[22]; + ice_txq_ctx_buf_t txq_ctx; u8 rsvd2[2]; struct ice_aqc_txsched_elem info; -}; +} __packed; /* The format of the command buffer for Add Tx LAN Queues (0x0C30) * is an array of the following structs. Please note that the length of @@ -2150,6 +2272,8 @@ struct ice_aqc_get_pkg_info_resp { struct ice_aqc_get_pkg_info pkg_info[]; }; +#define ICE_AQC_GET_CGU_MAX_PHASE_ADJ GENMASK(30, 0) + /* Get CGU abilities command response data structure (indirect 0x0C61) */ struct ice_aqc_get_cgu_abilities { u8 num_inputs; @@ -2394,6 +2518,87 @@ enum ice_aqc_fw_logging_mod { ICE_AQC_FW_LOG_ID_MAX, }; +enum ice_aqc_health_status_mask { + ICE_AQC_HEALTH_STATUS_SET_PF_SPECIFIC_MASK = BIT(0), + ICE_AQC_HEALTH_STATUS_SET_ALL_PF_MASK = BIT(1), + ICE_AQC_HEALTH_STATUS_SET_GLOBAL_MASK = BIT(2), +}; + +/* Set Health Status (direct 0xFF20) */ +struct ice_aqc_set_health_status_cfg { + u8 event_source; + u8 reserved[15]; +}; + +enum ice_aqc_health_status { + ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_STRICT = 0x101, + ICE_AQC_HEALTH_STATUS_ERR_MOD_TYPE = 0x102, + ICE_AQC_HEALTH_STATUS_ERR_MOD_QUAL = 0x103, + ICE_AQC_HEALTH_STATUS_ERR_MOD_COMM = 0x104, + ICE_AQC_HEALTH_STATUS_ERR_MOD_CONFLICT = 0x105, + ICE_AQC_HEALTH_STATUS_ERR_MOD_NOT_PRESENT = 0x106, + ICE_AQC_HEALTH_STATUS_INFO_MOD_UNDERUTILIZED = 0x107, + ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_LENIENT = 0x108, + ICE_AQC_HEALTH_STATUS_ERR_MOD_DIAGNOSTIC_FEATURE = 0x109, + ICE_AQC_HEALTH_STATUS_ERR_INVALID_LINK_CFG = 0x10B, + ICE_AQC_HEALTH_STATUS_ERR_PORT_ACCESS = 0x10C, + ICE_AQC_HEALTH_STATUS_ERR_PORT_UNREACHABLE = 0x10D, + ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_MOD_LIMITED = 0x10F, + ICE_AQC_HEALTH_STATUS_ERR_PARALLEL_FAULT = 0x110, + ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_PHY_LIMITED = 0x111, + ICE_AQC_HEALTH_STATUS_ERR_NETLIST_TOPO = 0x112, + ICE_AQC_HEALTH_STATUS_ERR_NETLIST = 0x113, + ICE_AQC_HEALTH_STATUS_ERR_TOPO_CONFLICT = 0x114, + ICE_AQC_HEALTH_STATUS_ERR_LINK_HW_ACCESS = 0x115, + ICE_AQC_HEALTH_STATUS_ERR_LINK_RUNTIME = 0x116, + ICE_AQC_HEALTH_STATUS_ERR_DNL_INIT = 0x117, + ICE_AQC_HEALTH_STATUS_ERR_PHY_NVM_PROG = 0x120, + ICE_AQC_HEALTH_STATUS_ERR_PHY_FW_LOAD = 0x121, + ICE_AQC_HEALTH_STATUS_INFO_RECOVERY = 0x500, + ICE_AQC_HEALTH_STATUS_ERR_FLASH_ACCESS = 0x501, + ICE_AQC_HEALTH_STATUS_ERR_NVM_AUTH = 0x502, + ICE_AQC_HEALTH_STATUS_ERR_OROM_AUTH = 0x503, + ICE_AQC_HEALTH_STATUS_ERR_DDP_AUTH = 0x504, + ICE_AQC_HEALTH_STATUS_ERR_NVM_COMPAT = 0x505, + ICE_AQC_HEALTH_STATUS_ERR_OROM_COMPAT = 0x506, + ICE_AQC_HEALTH_STATUS_ERR_NVM_SEC_VIOLATION = 0x507, + ICE_AQC_HEALTH_STATUS_ERR_OROM_SEC_VIOLATION = 0x508, + ICE_AQC_HEALTH_STATUS_ERR_DCB_MIB = 0x509, + ICE_AQC_HEALTH_STATUS_ERR_MNG_TIMEOUT = 0x50A, + ICE_AQC_HEALTH_STATUS_ERR_BMC_RESET = 0x50B, + ICE_AQC_HEALTH_STATUS_ERR_LAST_MNG_FAIL = 0x50C, + ICE_AQC_HEALTH_STATUS_ERR_RESOURCE_ALLOC_FAIL = 0x50D, + ICE_AQC_HEALTH_STATUS_ERR_FW_LOOP = 0x1000, + ICE_AQC_HEALTH_STATUS_ERR_FW_PFR_FAIL = 0x1001, + ICE_AQC_HEALTH_STATUS_ERR_LAST_FAIL_AQ = 0x1002, +}; + +/* Get Health Status (indirect 0xFF22) */ +struct ice_aqc_get_health_status { + __le16 health_status_count; + u8 reserved[6]; + __le32 addr_high; + __le32 addr_low; +}; + +enum ice_aqc_health_status_scope { + ICE_AQC_HEALTH_STATUS_PF = 0x1, + ICE_AQC_HEALTH_STATUS_PORT = 0x2, + ICE_AQC_HEALTH_STATUS_GLOBAL = 0x3, +}; + +#define ICE_AQC_HEALTH_STATUS_UNDEFINED_DATA 0xDEADBEEF + +/* Get Health Status event buffer entry (0xFF22), + * repeated per reported health status. + */ +struct ice_aqc_health_status_elem { + __le16 health_status_code; + __le16 event_source; + __le32 internal_data1; + __le32 internal_data2; +}; + /* Set FW Logging configuration (indirect 0xFF30) * Register for FW Logging (indirect 0xFF31) * Query FW Logging (indirect 0xFF32) @@ -2534,20 +2739,28 @@ struct ice_aq_desc { struct ice_aqc_get_link_status get_link_status; struct ice_aqc_event_lan_overflow lan_overflow; struct ice_aqc_get_link_topo get_link_topo; + struct ice_aqc_set_health_status_cfg set_health_status_cfg; + struct ice_aqc_get_health_status get_health_status; + struct ice_aqc_dnl_call_command dnl_call; struct ice_aqc_i2c read_write_i2c; struct ice_aqc_read_i2c_resp read_i2c_resp; + struct ice_aqc_get_set_tx_topo get_set_tx_topo; } params; }; /* FW defined boundary for a large buffer, 4k >= Large buffer > 512 bytes */ #define ICE_AQ_LG_BUF 512 +#define ICE_AQ_FLAG_DD_S 0 +#define ICE_AQ_FLAG_CMP_S 1 #define ICE_AQ_FLAG_ERR_S 2 #define ICE_AQ_FLAG_LB_S 9 #define ICE_AQ_FLAG_RD_S 10 #define ICE_AQ_FLAG_BUF_S 12 #define ICE_AQ_FLAG_SI_S 13 +#define ICE_AQ_FLAG_DD BIT(ICE_AQ_FLAG_DD_S) /* 0x1 */ +#define ICE_AQ_FLAG_CMP BIT(ICE_AQ_FLAG_CMP_S) /* 0x2 */ #define ICE_AQ_FLAG_ERR BIT(ICE_AQ_FLAG_ERR_S) /* 0x4 */ #define ICE_AQ_FLAG_LB BIT(ICE_AQ_FLAG_LB_S) /* 0x200 */ #define ICE_AQ_FLAG_RD BIT(ICE_AQ_FLAG_RD_S) /* 0x400 */ @@ -2642,6 +2855,10 @@ enum ice_adminq_opc { ice_aqc_opc_query_sched_res = 0x0412, ice_aqc_opc_remove_rl_profiles = 0x0415, + /* tx topology commands */ + ice_aqc_opc_set_tx_topo = 0x0417, + ice_aqc_opc_get_tx_topo = 0x0418, + /* PHY commands */ ice_aqc_opc_get_phy_caps = 0x0600, ice_aqc_opc_set_phy_cfg = 0x0601, @@ -2653,6 +2870,7 @@ enum ice_adminq_opc { ice_aqc_opc_set_phy_rec_clk_out = 0x0630, ice_aqc_opc_get_phy_rec_clk_out = 0x0631, ice_aqc_opc_get_sensor_reading = 0x0632, + ice_aqc_opc_dnl_call = 0x0682, ice_aqc_opc_get_link_topo = 0x06E0, ice_aqc_opc_read_i2c = 0x06E2, ice_aqc_opc_write_i2c = 0x06E3, @@ -2725,6 +2943,10 @@ enum ice_adminq_opc { /* Standalone Commands/Events */ ice_aqc_opc_event_lan_overflow = 0x1001, + /* System Diagnostic commands */ + ice_aqc_opc_set_health_status_cfg = 0xFF20, + ice_aqc_opc_get_health_status = 0xFF22, + /* FW Logging Commands */ ice_aqc_opc_fw_logs_config = 0xFF30, ice_aqc_opc_fw_logs_register = 0xFF31, diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c index 7cee365cc7d1..2bc5c7f59844 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.c +++ b/drivers/net/ethernet/intel/ice/ice_arfs.c @@ -511,7 +511,7 @@ void ice_init_arfs(struct ice_vsi *vsi) struct hlist_head *arfs_fltr_list; unsigned int i; - if (!vsi || vsi->type != ICE_VSI_PF) + if (!vsi || vsi->type != ICE_VSI_PF || ice_is_arfs_active(vsi)) return; arfs_fltr_list = kcalloc(ICE_MAX_ARFS_LIST, sizeof(*arfs_fltr_list), @@ -571,25 +571,6 @@ void ice_clear_arfs(struct ice_vsi *vsi) } /** - * ice_free_cpu_rx_rmap - free setup CPU reverse map - * @vsi: the VSI to be forwarded to - */ -void ice_free_cpu_rx_rmap(struct ice_vsi *vsi) -{ - struct net_device *netdev; - - if (!vsi || vsi->type != ICE_VSI_PF) - return; - - netdev = vsi->netdev; - if (!netdev || !netdev->rx_cpu_rmap) - return; - - free_irq_cpu_rmap(netdev->rx_cpu_rmap); - netdev->rx_cpu_rmap = NULL; -} - -/** * ice_set_cpu_rx_rmap - setup CPU reverse map for each queue * @vsi: the VSI to be forwarded to */ @@ -597,7 +578,6 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi) { struct net_device *netdev; struct ice_pf *pf; - int i; if (!vsi || vsi->type != ICE_VSI_PF) return 0; @@ -610,18 +590,7 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi) netdev_dbg(netdev, "Setup CPU RMAP: vsi type 0x%x, ifname %s, q_vectors %d\n", vsi->type, netdev->name, vsi->num_q_vectors); - netdev->rx_cpu_rmap = alloc_irq_cpu_rmap(vsi->num_q_vectors); - if (unlikely(!netdev->rx_cpu_rmap)) - return -EINVAL; - - ice_for_each_q_vector(vsi, i) - if (irq_cpu_rmap_add(netdev->rx_cpu_rmap, - vsi->q_vectors[i]->irq.virq)) { - ice_free_cpu_rx_rmap(vsi); - return -EINVAL; - } - - return 0; + return netif_enable_cpu_rmap(netdev, vsi->num_q_vectors); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.h b/drivers/net/ethernet/intel/ice/ice_arfs.h index 9669ad9bf7b5..9706293128c3 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.h +++ b/drivers/net/ethernet/intel/ice/ice_arfs.h @@ -45,7 +45,6 @@ int ice_rx_flow_steer(struct net_device *netdev, const struct sk_buff *skb, u16 rxq_idx, u32 flow_id); void ice_clear_arfs(struct ice_vsi *vsi); -void ice_free_cpu_rx_rmap(struct ice_vsi *vsi); void ice_init_arfs(struct ice_vsi *vsi); void ice_sync_arfs_fltrs(struct ice_pf *pf); int ice_set_cpu_rx_rmap(struct ice_vsi *vsi); @@ -56,7 +55,6 @@ ice_is_arfs_using_perfect_flow(struct ice_hw *hw, enum ice_fltr_ptype flow_type); #else static inline void ice_clear_arfs(struct ice_vsi *vsi) { } -static inline void ice_free_cpu_rx_rmap(struct ice_vsi *vsi) { } static inline void ice_init_arfs(struct ice_vsi *vsi) { } static inline void ice_sync_arfs_fltrs(struct ice_pf *pf) { } static inline void ice_remove_arfs(struct ice_pf *pf) { } diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index a545a7917e4f..6db4ad8fc70b 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -121,7 +121,7 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, u16 v_idx) q_vector->irq.index = -ENOENT; if (vsi->type == ICE_VSI_VF) { - q_vector->reg_idx = ice_calc_vf_reg_idx(vsi->vf, q_vector); + ice_calc_vf_reg_idx(vsi->vf, q_vector); goto out; } else if (vsi->type == ICE_VSI_CTRL && vsi->vf) { struct ice_vsi *ctrl_vsi = ice_get_vf_ctrl_vsi(pf, vsi); @@ -145,17 +145,15 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, u16 v_idx) skip_alloc: q_vector->reg_idx = q_vector->irq.index; - - /* only set affinity_mask if the CPU is online */ - if (cpu_online(v_idx)) - cpumask_set_cpu(v_idx, &q_vector->affinity_mask); + q_vector->vf_reg_idx = q_vector->irq.index; /* This will not be called in the driver load path because the netdev * will not be created yet. All other cases with register the NAPI * handler here (i.e. resume, reset/rebuild, etc.) */ if (vsi->netdev) - netif_napi_add(vsi->netdev, &q_vector->napi, ice_napi_poll); + netif_napi_add_config(vsi->netdev, &q_vector->napi, + ice_napi_poll, v_idx); out: /* tie q_vector and VSI together */ @@ -189,16 +187,11 @@ static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx) } q_vector = vsi->q_vectors[v_idx]; - ice_for_each_tx_ring(tx_ring, q_vector->tx) { - ice_queue_set_napi(vsi, tx_ring->q_index, NETDEV_QUEUE_TYPE_TX, - NULL); + ice_for_each_tx_ring(tx_ring, vsi->q_vectors[v_idx]->tx) tx_ring->q_vector = NULL; - } - ice_for_each_rx_ring(rx_ring, q_vector->rx) { - ice_queue_set_napi(vsi, rx_ring->q_index, NETDEV_QUEUE_TYPE_RX, - NULL); + + ice_for_each_rx_ring(rx_ring, vsi->q_vectors[v_idx]->rx) rx_ring->q_vector = NULL; - } /* only VSI with an associated netdev is set up with NAPI */ if (vsi->netdev) @@ -264,30 +257,6 @@ static u16 ice_calc_txq_handle(struct ice_vsi *vsi, struct ice_tx_ring *ring, u8 } /** - * ice_eswitch_calc_txq_handle - * @ring: pointer to ring which unique index is needed - * - * To correctly work with many netdevs ring->q_index of Tx rings on switchdev - * VSI can repeat. Hardware ring setup requires unique q_index. Calculate it - * here by finding index in vsi->tx_rings of this ring. - * - * Return ICE_INVAL_Q_INDEX when index wasn't found. Should never happen, - * because VSI is get from ring->vsi, so it has to be present in this VSI. - */ -static u16 ice_eswitch_calc_txq_handle(struct ice_tx_ring *ring) -{ - const struct ice_vsi *vsi = ring->vsi; - int i; - - ice_for_each_txq(vsi, i) { - if (vsi->tx_rings[i] == ring) - return i; - } - - return ICE_INVAL_Q_INDEX; -} - -/** * ice_cfg_xps_tx_ring - Configure XPS for a Tx ring * @ring: The Tx ring to configure * @@ -303,7 +272,8 @@ static void ice_cfg_xps_tx_ring(struct ice_tx_ring *ring) if (test_and_set_bit(ICE_TX_XPS_INIT_DONE, ring->xps_state)) return; - netif_set_xps_queue(ring->netdev, &ring->q_vector->affinity_mask, + netif_set_xps_queue(ring->netdev, + &ring->q_vector->napi.config->affinity_mask, ring->q_index); } @@ -353,7 +323,7 @@ ice_setup_tx_ctx(struct ice_tx_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf tlan_ctx->vmvf_num = hw->func_caps.vf_base_id + vsi->vf->vf_id; tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_VF; break; - case ICE_VSI_SWITCHDEV_CTRL: + case ICE_VSI_SF: tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_VMQ; break; default: @@ -375,6 +345,8 @@ ice_setup_tx_ctx(struct ice_tx_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf break; } + tlan_ctx->quanta_prof_idx = ring->quanta_prof_id; + tlan_ctx->tso_ena = ICE_TX_LEGACY; tlan_ctx->tso_qnum = pf_q; @@ -473,12 +445,23 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) /* 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, + rlan_ctx.rxmax = min_t(u32, ring->max_frame, ICE_MAX_CHAINED_RX_BUFS * ring->rx_buf_len); /* Rx queue threshold in units of 64 */ rlan_ctx.lrxqthresh = 1; + /* Enable descriptor prefetch */ + rlan_ctx.prefena = 1; + + /* PF acts as uplink for switchdev; set flex descriptor with src_vsi + * metadata and flags to allow redirecting to PR netdev + */ + if (ice_is_eswitch_mode_switchdev(vsi->back)) { + ring->flags |= ICE_RX_FLAGS_MULTIDEV; + rxdid = ICE_RXDID_FLEX_NIC_2; + } + /* Enable Flexible Descriptors in the queue context which * allows this driver to select a specific receive descriptor format * increasing context priority to pick up profile ID; default is 0x01; @@ -487,9 +470,6 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) */ if (vsi->type != ICE_VSI_VF) ice_write_qrxflxp_cntxt(hw, pf_q, rxdid, 0x3, true); - else - ice_write_qrxflxp_cntxt(hw, pf_q, ICE_RXDID_LEGACY_1, 0x3, - false); /* Absolute queue number out of 2K needs to be passed */ err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q); @@ -531,6 +511,25 @@ static void ice_xsk_pool_fill_cb(struct ice_rx_ring *ring) } /** + * ice_get_frame_sz - calculate xdp_buff::frame_sz + * @rx_ring: the ring being configured + * + * Return frame size based on underlying PAGE_SIZE + */ +static unsigned int ice_get_frame_sz(struct ice_rx_ring *rx_ring) +{ + unsigned int frame_sz; + +#if (PAGE_SIZE >= 8192) + frame_sz = rx_ring->rx_buf_len; +#else + frame_sz = ice_rx_pg_size(rx_ring) / 2; +#endif + + return frame_sz; +} + +/** * ice_vsi_cfg_rxq - Configure an Rx queue * @ring: the ring being configured * @@ -542,9 +541,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) u32 num_bufs = ICE_RX_DESC_UNUSED(ring); int err; - ring->rx_buf_len = ring->vsi->rx_buf_len; - - if (ring->vsi->type == ICE_VSI_PF) { + if (ring->vsi->type == ICE_VSI_PF || ring->vsi->type == ICE_VSI_SF) { if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) { err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, ring->q_index, @@ -554,7 +551,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) return err; } - ring->xsk_pool = ice_xsk_pool(ring); + ice_rx_xsk_pool(ring); if (ring->xsk_pool) { xdp_rxq_info_unreg(&ring->xdp_rxq); @@ -594,7 +591,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) } } - xdp_init_buff(&ring->xdp, ice_rx_pg_size(ring) / 2, &ring->xdp_rxq); + xdp_init_buff(&ring->xdp, ice_get_frame_sz(ring), &ring->xdp_rxq); ring->xdp.data = NULL; ring->xdp_ext.pkt_ctx = &ring->pkt_ctx; err = ice_setup_rx_ctx(ring); @@ -615,7 +612,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) return 0; } - ok = ice_alloc_rx_bufs_zc(ring, num_bufs); + ok = ice_alloc_rx_bufs_zc(ring, ring->xsk_pool, num_bufs); if (!ok) { u16 pf_q = ring->vsi->rxq_map[ring->q_index]; @@ -642,21 +639,25 @@ int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx) /** * ice_vsi_cfg_frame_size - setup max frame size and Rx buffer length * @vsi: VSI + * @ring: Rx ring to configure + * + * Determine the maximum frame size and Rx buffer length to use for a PF VSI. + * Set these in the associated Rx ring structure. */ -static void ice_vsi_cfg_frame_size(struct ice_vsi *vsi) +static void ice_vsi_cfg_frame_size(struct ice_vsi *vsi, struct ice_rx_ring *ring) { 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; + ring->max_frame = ICE_MAX_FRAME_LEGACY_RX; + ring->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; + ring->max_frame = ICE_RXBUF_1536 - NET_IP_ALIGN; + ring->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; + ring->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX; + ring->rx_buf_len = ICE_RXBUF_3072; } } @@ -671,15 +672,15 @@ int ice_vsi_cfg_rxqs(struct ice_vsi *vsi) { u16 i; - if (vsi->type == ICE_VSI_VF) - goto setup_rings; - - ice_vsi_cfg_frame_size(vsi); -setup_rings: /* set up individual rings */ ice_for_each_rxq(vsi, i) { - int err = ice_vsi_cfg_rxq(vsi->rx_rings[i]); + struct ice_rx_ring *ring = vsi->rx_rings[i]; + int err; + + if (vsi->type != ICE_VSI_VF) + ice_vsi_cfg_frame_size(vsi, ring); + err = ice_vsi_cfg_rxq(ring); if (err) return err; } @@ -794,13 +795,11 @@ int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi) return 0; err_out: - while (v_idx--) - ice_free_q_vector(vsi, v_idx); - dev_err(dev, "Failed to allocate %d q_vector for VSI %d, ret=%d\n", - vsi->num_q_vectors, vsi->vsi_num, err); - vsi->num_q_vectors = 0; - return err; + dev_info(dev, "Failed to allocate %d q_vectors for VSI %d, new value %d", + vsi->num_q_vectors, vsi->vsi_num, v_idx); + vsi->num_q_vectors = v_idx; + return v_idx ? 0 : err; } /** @@ -860,6 +859,9 @@ void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi) } rx_rings_rem -= rx_rings_per_v; } + + if (ice_is_xdp_ena_vsi(vsi)) + ice_map_xdp_rings(vsi); } /** @@ -903,8 +905,7 @@ ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_tx_ring *ring, ice_setup_tx_ctx(ring, &tlan_ctx, pf_q); /* copy context contents into the qg_buf */ qg_buf->txqs[0].txq_id = cpu_to_le16(pf_q); - ice_set_ctx(hw, (u8 *)&tlan_ctx, qg_buf->txqs[0].txq_ctx, - ice_tlan_ctx_info); + ice_pack_txq_ctx(&tlan_ctx, &qg_buf->txqs[0].txq_ctx); /* init queue specific tail reg. It is referred as * transmit comm scheduler queue doorbell. @@ -919,14 +920,7 @@ ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_tx_ring *ring, /* Add unique software queue handle of the Tx queue per * TC into the VSI Tx ring */ - if (vsi->type == ICE_VSI_SWITCHDEV_CTRL) { - ring->q_handle = ice_eswitch_calc_txq_handle(ring); - - if (ring->q_handle == ICE_INVAL_Q_INDEX) - return -ENODEV; - } else { - ring->q_handle = ice_calc_txq_handle(vsi, ring, tc); - } + ring->q_handle = ice_calc_txq_handle(vsi, ring, tc); if (ch) status = ice_ena_vsi_txq(vsi->port_info, ch->ch_vsi->idx, 0, diff --git a/drivers/net/ethernet/intel/ice/ice_cgu_regs.h b/drivers/net/ethernet/intel/ice/ice_cgu_regs.h index 57abd52386d0..10d9d74f3545 100644 --- a/drivers/net/ethernet/intel/ice/ice_cgu_regs.h +++ b/drivers/net/ethernet/intel/ice/ice_cgu_regs.h @@ -23,7 +23,18 @@ union nac_cgu_dword9 { u32 clk_synce0_amp : 2; u32 one_pps_out_amp : 2; u32 misc24 : 12; - } field; + }; + u32 val; +}; + +#define NAC_CGU_DWORD16_E825C 0x40 +union nac_cgu_dword16_e825c { + struct { + u32 synce_remndr : 6; + u32 synce_phlmt_en : 1; + u32 misc13 : 17; + u32 tspll_ck_refclkfreq : 8; + }; u32 val; }; @@ -39,7 +50,7 @@ union nac_cgu_dword19 { u32 japll_ndivratio : 4; u32 japll_iref_ndivratio : 3; u32 misc27 : 1; - } field; + }; u32 val; }; @@ -63,7 +74,23 @@ union nac_cgu_dword22 { u32 fdpllclk_sel_div2 : 1; u32 time1588clk_sel_div2 : 1; u32 misc3 : 1; - } field; + }; + u32 val; +}; + +#define NAC_CGU_DWORD23_E825C 0x5C +union nac_cgu_dword23_e825c { + struct { + u32 cgupll_fbdiv_intgr : 10; + u32 ux56pll_fbdiv_intgr : 10; + u32 misc20 : 4; + u32 ts_pll_enable : 1; + u32 time_sync_tspll_align_sel : 1; + u32 ext_synce_sel : 1; + u32 ref1588_ck_div : 4; + u32 time_ref_sel : 1; + + }; u32 val; }; @@ -77,7 +104,7 @@ union nac_cgu_dword24 { u32 ext_synce_sel : 1; u32 ref1588_ck_div : 4; u32 time_ref_sel : 1; - } field; + }; u32 val; }; @@ -92,7 +119,7 @@ union tspll_cntr_bist_settings { u32 i_plllock_cnt_6_0 : 7; u32 i_plllock_cnt_10_7 : 4; u32 reserved200 : 4; - } field; + }; u32 val; }; @@ -109,7 +136,45 @@ union tspll_ro_bwm_lf { u32 afcdone_cri : 1; u32 feedfwrdgain_cal_cri_7_0 : 8; u32 m2fbdivmod_cri_7_0 : 8; - } field; + }; + u32 val; +}; + +#define TSPLL_RO_LOCK_E825C 0x3f0 +union tspll_ro_lock_e825c { + struct { + u32 bw_freqov_high_cri_7_0 : 8; + u32 bw_freqov_high_cri_9_8 : 2; + u32 reserved455 : 1; + u32 plllock_gain_tran_cri : 1; + u32 plllock_true_lock_cri : 1; + u32 pllunlock_flag_cri : 1; + u32 afcerr_cri : 1; + u32 afcdone_cri : 1; + u32 feedfwrdgain_cal_cri_7_0 : 8; + u32 reserved462 : 8; + }; + u32 val; +}; + +#define TSPLL_BW_TDC_E825C 0x31c +union tspll_bw_tdc_e825c { + struct { + u32 i_tdc_offset_lock_1_0 : 2; + u32 i_bbthresh1_2_0 : 3; + u32 i_bbthresh2_2_0 : 3; + u32 i_tdcsel_1_0 : 2; + u32 i_tdcovccorr_en_h : 1; + u32 i_divretimeren : 1; + u32 i_bw_ampmeas_window : 1; + u32 i_bw_lowerbound_2_0 : 3; + u32 i_bw_upperbound_2_0 : 3; + u32 i_bw_mode_1_0 : 2; + u32 i_ft_mode_sel_2_0 : 3; + u32 i_bwphase_4_0 : 5; + u32 i_plllock_sel_1_0 : 2; + u32 i_afc_divratio : 1; + }; u32 val; }; diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index d9f6cc71d900..4fedf0181c4e 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -6,6 +6,7 @@ #include "ice_adminq_cmd.h" #include "ice_flow.h" #include "ice_ptp_hw.h" +#include <linux/packing.h> #define ICE_PF_RESET_WAIT_COUNT 300 #define ICE_MAX_NETLIST_SIZE 10 @@ -160,10 +161,16 @@ static int ice_set_mac_type(struct ice_hw *hw) case ICE_DEV_ID_E825C_SGMII: hw->mac_type = ICE_MAC_GENERIC_3K_E825; 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: + case ICE_DEV_ID_E830CC_BACKPLANE: + case ICE_DEV_ID_E830CC_QSFP56: + case ICE_DEV_ID_E830CC_SFP: + case ICE_DEV_ID_E830CC_SFP_DD: + case ICE_DEV_ID_E830C_BACKPLANE: + case ICE_DEV_ID_E830_XXV_BACKPLANE: + case ICE_DEV_ID_E830C_QSFP: + case ICE_DEV_ID_E830_XXV_QSFP: + case ICE_DEV_ID_E830C_SFP: + case ICE_DEV_ID_E830_XXV_SFP: hw->mac_type = ICE_MAC_E830; break; default: @@ -179,7 +186,7 @@ static int ice_set_mac_type(struct ice_hw *hw) * ice_is_generic_mac - check if device's mac_type is generic * @hw: pointer to the hardware structure * - * Return: true if mac_type is generic (with SBQ support), false if not + * Return: true if mac_type is ICE_MAC_GENERIC*, false otherwise. */ bool ice_is_generic_mac(struct ice_hw *hw) { @@ -188,93 +195,39 @@ bool ice_is_generic_mac(struct ice_hw *hw) } /** - * ice_is_e810 - * @hw: pointer to the hardware structure - * - * returns true if the device is E810 based, false if not. - */ -bool ice_is_e810(struct ice_hw *hw) -{ - return hw->mac_type == ICE_MAC_E810; -} - -/** - * ice_is_e810t - * @hw: pointer to the hardware structure + * ice_is_pf_c827 - check if pf contains c827 phy + * @hw: pointer to the hw struct * - * returns true if the device is E810T based, false if not. + * Return: true if the device has c827 phy. */ -bool ice_is_e810t(struct ice_hw *hw) +static bool ice_is_pf_c827(struct ice_hw *hw) { - switch (hw->device_id) { - case ICE_DEV_ID_E810C_SFP: - switch (hw->subsystem_device_id) { - case ICE_SUBDEV_ID_E810T: - case ICE_SUBDEV_ID_E810T2: - case ICE_SUBDEV_ID_E810T3: - case ICE_SUBDEV_ID_E810T4: - case ICE_SUBDEV_ID_E810T6: - case ICE_SUBDEV_ID_E810T7: - return true; - } - break; - case ICE_DEV_ID_E810C_QSFP: - switch (hw->subsystem_device_id) { - case ICE_SUBDEV_ID_E810T2: - case ICE_SUBDEV_ID_E810T3: - case ICE_SUBDEV_ID_E810T5: - return true; - } - break; - default: - break; - } + struct ice_aqc_get_link_topo cmd = {}; + u8 node_part_number; + u16 node_handle; + int status; - return false; -} + if (hw->mac_type != ICE_MAC_E810) + return false; -/** - * ice_is_e823 - * @hw: pointer to the hardware structure - * - * returns true if the device is E823-L or E823-C based, false if not. - */ -bool ice_is_e823(struct ice_hw *hw) -{ - switch (hw->device_id) { - case ICE_DEV_ID_E823L_BACKPLANE: - case ICE_DEV_ID_E823L_SFP: - case ICE_DEV_ID_E823L_10G_BASE_T: - case ICE_DEV_ID_E823L_1GBE: - case ICE_DEV_ID_E823L_QSFP: - case ICE_DEV_ID_E823C_BACKPLANE: - case ICE_DEV_ID_E823C_QSFP: - case ICE_DEV_ID_E823C_SFP: - case ICE_DEV_ID_E823C_10G_BASE_T: - case ICE_DEV_ID_E823C_SGMII: + if (hw->device_id != ICE_DEV_ID_E810C_QSFP) return true; - default: + + 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; - } -} -/** - * ice_is_e825c - Check if a device is E825C family device - * @hw: pointer to the hardware structure - * - * Return: true if the device is E825-C based, false if not. - */ -bool ice_is_e825c(struct ice_hw *hw) -{ - switch (hw->device_id) { - case ICE_DEV_ID_E825C_BACKPLANE: - case ICE_DEV_ID_E825C_QSFP: - case ICE_DEV_ID_E825C_SFP: - case ICE_DEV_ID_E825C_SGMII: + if (node_handle == E810C_QSFP_C827_0_HANDLE || node_handle == E810C_QSFP_C827_1_HANDLE) return true; - default: - return false; - } + + return false; } /** @@ -512,7 +465,8 @@ ice_aq_get_netlist_node(struct ice_hw *hw, struct ice_aqc_get_link_topo *cmd, /** * ice_find_netlist_node * @hw: pointer to the hw struct - * @node_type_ctx: type of netlist node to look for + * @node_type: type of netlist node to look for + * @ctx: context of the search * @node_part_number: node part number to look for * @node_handle: output parameter if node found - optional * @@ -522,10 +476,12 @@ ice_aq_get_netlist_node(struct ice_hw *hw, struct ice_aqc_get_link_topo *cmd, * 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. + * Return: + * * 0 if the node is found, + * * -ENOENT if no handle was found, + * * negative error code on failure to access the AQ. */ -static int ice_find_netlist_node(struct ice_hw *hw, u8 node_type_ctx, +static int ice_find_netlist_node(struct ice_hw *hw, u8 node_type, u8 ctx, u8 node_part_number, u16 *node_handle) { u8 idx; @@ -536,8 +492,8 @@ static int ice_find_netlist_node(struct ice_hw *hw, u8 node_type_ctx, int status; cmd.addr.topo_params.node_type_ctx = - FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M, - node_type_ctx); + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M, node_type) | + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, ctx); cmd.addr.topo_params.index = idx; status = ice_aq_get_netlist_node(hw, &cmd, @@ -904,6 +860,9 @@ static int ice_init_fltr_mgmt_struct(struct ice_hw *hw) INIT_LIST_HEAD(&sw->vsi_list_map_head); sw->prof_res_bm_init = 0; + /* Initialize recipe count with default recipes read from NVM */ + sw->recp_cnt = ICE_SW_LKUP_LAST; + status = ice_init_def_sw_recp(hw); if (status) { devm_kfree(ice_hw_to_dev(hw), hw->switch_info); @@ -931,14 +890,7 @@ static void ice_cleanup_fltr_mgmt_struct(struct ice_hw *hw) } recps = sw->recp_list; for (i = 0; i < ICE_MAX_NUM_RECIPES; i++) { - struct ice_recp_grp_entry *rg_entry, *tmprg_entry; - recps[i].root_rid = i; - list_for_each_entry_safe(rg_entry, tmprg_entry, - &recps[i].rg_list, l_entry) { - list_del(&rg_entry->l_entry); - devm_kfree(ice_hw_to_dev(hw), rg_entry); - } if (recps[i].adv_rule) { struct ice_adv_fltr_mgmt_list_entry *tmp_entry; @@ -963,7 +915,6 @@ static void ice_cleanup_fltr_mgmt_struct(struct ice_hw *hw) devm_kfree(ice_hw_to_dev(hw), lst_itr); } } - devm_kfree(ice_hw_to_dev(hw), recps[i].root_buf); } ice_rm_all_sw_replay_rule_info(hw); devm_kfree(ice_hw_to_dev(hw), sw->recp_list); @@ -997,6 +948,33 @@ static void ice_get_itr_intrl_gran(struct ice_hw *hw) } /** + * ice_wait_for_fw - wait for full FW readiness + * @hw: pointer to the hardware structure + * @timeout: milliseconds that can elapse before timing out + * + * Return: 0 on success, -ETIMEDOUT on timeout. + */ +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; +} + +/** * ice_init_hw - main hardware initialization routine * @hw: pointer to the hardware structure */ @@ -1056,6 +1034,7 @@ int ice_init_hw(struct ice_hw *hw) goto err_unroll_cqinit; } + hw->port_info->local_fwd_mode = ICE_LOCAL_FWD_MODE_ENABLED; /* set the back pointer to HW */ hw->port_info->hw = hw; @@ -1142,8 +1121,23 @@ int ice_init_hw(struct ice_hw *hw) if (status) goto err_unroll_fltr_mgmt_struct; mutex_init(&hw->tnl_lock); - return 0; + ice_init_chk_recipe_reuse_support(hw); + + /* 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)) { + status = ice_wait_for_fw(hw, 30000); + if (status) { + dev_err(ice_hw_to_dev(hw), "ice_wait_for_fw timed out"); + goto err_unroll_fltr_mgmt_struct; + } + } + + hw->lane_num = ice_get_phy_lane_number(hw); + return 0; err_unroll_fltr_mgmt_struct: ice_cleanup_fltr_mgmt_struct(hw); err_unroll_sched: @@ -1329,39 +1323,31 @@ int ice_reset(struct ice_hw *hw, enum ice_reset_req req) } /** - * ice_copy_rxq_ctx_to_hw + * ice_copy_rxq_ctx_to_hw - Copy packed Rx queue context to HW registers * @hw: pointer to the hardware structure - * @ice_rxq_ctx: pointer to the rxq context + * @rxq_ctx: pointer to the packed Rx queue context * @rxq_index: the index of the Rx queue - * - * Copies rxq context from dense structure to HW register space */ -static int -ice_copy_rxq_ctx_to_hw(struct ice_hw *hw, u8 *ice_rxq_ctx, u32 rxq_index) +static void ice_copy_rxq_ctx_to_hw(struct ice_hw *hw, + const ice_rxq_ctx_buf_t *rxq_ctx, + u32 rxq_index) { - u8 i; - - if (!ice_rxq_ctx) - return -EINVAL; - - if (rxq_index > QRX_CTRL_MAX_INDEX) - return -EINVAL; - /* Copy each dword separately to HW */ - for (i = 0; i < ICE_RXQ_CTX_SIZE_DWORDS; i++) { - wr32(hw, QRX_CONTEXT(i, rxq_index), - *((u32 *)(ice_rxq_ctx + (i * sizeof(u32))))); + for (int i = 0; i < ICE_RXQ_CTX_SIZE_DWORDS; i++) { + u32 ctx = ((const u32 *)rxq_ctx)[i]; - ice_debug(hw, ICE_DBG_QCTX, "qrxdata[%d]: %08X\n", i, - *((u32 *)(ice_rxq_ctx + (i * sizeof(u32))))); - } + wr32(hw, QRX_CONTEXT(i, rxq_index), ctx); - return 0; + ice_debug(hw, ICE_DBG_QCTX, "qrxdata[%d]: %08X\n", i, ctx); + } } +#define ICE_CTX_STORE(struct_name, struct_field, width, lsb) \ + PACKED_FIELD((lsb) + (width) - 1, (lsb), struct struct_name, struct_field) + /* LAN Rx Queue Context */ -static const struct ice_ctx_ele ice_rlan_ctx_info[] = { - /* Field Width LSB */ +static const struct packed_field_u8 ice_rlan_ctx_fields[] = { + /* Field Width LSB */ ICE_CTX_STORE(ice_rlan_ctx, head, 13, 0), ICE_CTX_STORE(ice_rlan_ctx, cpuid, 8, 13), ICE_CTX_STORE(ice_rlan_ctx, base, 57, 32), @@ -1382,35 +1368,50 @@ static const struct ice_ctx_ele ice_rlan_ctx_info[] = { ICE_CTX_STORE(ice_rlan_ctx, tphhead_ena, 1, 196), ICE_CTX_STORE(ice_rlan_ctx, lrxqthresh, 3, 198), ICE_CTX_STORE(ice_rlan_ctx, prefena, 1, 201), - { 0 } }; /** - * ice_write_rxq_ctx + * ice_pack_rxq_ctx - Pack Rx queue context into a HW buffer + * @ctx: the Rx queue context to pack + * @buf: the HW buffer to pack into + * + * Pack the Rx queue context from the CPU-friendly unpacked buffer into its + * bit-packed HW layout. + */ +static void ice_pack_rxq_ctx(const struct ice_rlan_ctx *ctx, + ice_rxq_ctx_buf_t *buf) +{ + pack_fields(buf, sizeof(*buf), ctx, ice_rlan_ctx_fields, + QUIRK_LITTLE_ENDIAN | QUIRK_LSW32_IS_FIRST); +} + +/** + * ice_write_rxq_ctx - Write Rx Queue context to hardware * @hw: pointer to the hardware structure - * @rlan_ctx: pointer to the rxq context + * @rlan_ctx: pointer to the unpacked Rx queue context * @rxq_index: the index of the Rx queue * - * Converts rxq context from sparse to dense structure and then writes - * it to HW register space and enables the hardware to prefetch descriptors - * instead of only fetching them on demand + * Pack the sparse Rx Queue context into dense hardware format and write it + * into the HW register space. + * + * Return: 0 on success, or -EINVAL if the Rx queue index is invalid. */ int ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx, u32 rxq_index) { - u8 ctx_buf[ICE_RXQ_CTX_SZ] = { 0 }; + ice_rxq_ctx_buf_t buf = {}; - if (!rlan_ctx) + if (rxq_index > QRX_CTRL_MAX_INDEX) return -EINVAL; - rlan_ctx->prefena = 1; + ice_pack_rxq_ctx(rlan_ctx, &buf); + ice_copy_rxq_ctx_to_hw(hw, &buf, rxq_index); - ice_set_ctx(hw, (u8 *)rlan_ctx, ctx_buf, ice_rlan_ctx_info); - return ice_copy_rxq_ctx_to_hw(hw, ctx_buf, rxq_index); + return 0; } /* LAN Tx Queue Context */ -const struct ice_ctx_ele ice_tlan_ctx_info[] = { +static const struct packed_field_u8 ice_tlan_ctx_fields[] = { /* Field Width LSB */ ICE_CTX_STORE(ice_tlan_ctx, base, 57, 0), ICE_CTX_STORE(ice_tlan_ctx, port_num, 3, 57), @@ -1439,10 +1440,22 @@ const struct ice_ctx_ele ice_tlan_ctx_info[] = { ICE_CTX_STORE(ice_tlan_ctx, drop_ena, 1, 165), ICE_CTX_STORE(ice_tlan_ctx, cache_prof_idx, 2, 166), ICE_CTX_STORE(ice_tlan_ctx, pkt_shaper_prof_idx, 3, 168), - ICE_CTX_STORE(ice_tlan_ctx, int_q_state, 122, 171), - { 0 } }; +/** + * ice_pack_txq_ctx - Pack Tx queue context into a HW buffer + * @ctx: the Tx queue context to pack + * @buf: the HW buffer to pack into + * + * Pack the Tx queue context from the CPU-friendly unpacked buffer into its + * bit-packed HW layout. + */ +void ice_pack_txq_ctx(const struct ice_tlan_ctx *ctx, ice_txq_ctx_buf_t *buf) +{ + pack_fields(buf, sizeof(*buf), ctx, ice_tlan_ctx_fields, + QUIRK_LITTLE_ENDIAN | QUIRK_LSW32_IS_FIRST); +} + /* Sideband Queue command wrappers */ /** @@ -1465,8 +1478,9 @@ ice_sbq_send_cmd(struct ice_hw *hw, struct ice_sbq_cmd_desc *desc, * ice_sbq_rw_reg - Fill Sideband Queue command * @hw: pointer to the HW struct * @in: message info to be filled in descriptor + * @flags: control queue descriptor flags */ -int ice_sbq_rw_reg(struct ice_hw *hw, struct ice_sbq_msg_input *in) +int ice_sbq_rw_reg(struct ice_hw *hw, struct ice_sbq_msg_input *in, u16 flags) { struct ice_sbq_cmd_desc desc = {0}; struct ice_sbq_msg_req msg = {0}; @@ -1490,7 +1504,7 @@ int ice_sbq_rw_reg(struct ice_hw *hw, struct ice_sbq_msg_input *in) */ msg_len -= sizeof(msg.data); - desc.flags = cpu_to_le16(ICE_AQ_FLAG_RD); + desc.flags = cpu_to_le16(flags); desc.opcode = cpu_to_le16(ice_sbq_opc_neigh_dev_req); desc.param0.cmd_len = cpu_to_le16(msg_len); status = ice_sbq_send_cmd(hw, &desc, &msg, msg_len, NULL); @@ -1615,6 +1629,8 @@ ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf, case ice_aqc_opc_set_port_params: case ice_aqc_opc_get_vlan_mode_parameters: case ice_aqc_opc_set_vlan_mode_parameters: + case ice_aqc_opc_set_tx_topo: + case ice_aqc_opc_get_tx_topo: case ice_aqc_opc_add_recipe: case ice_aqc_opc_recipe_to_profile: case ice_aqc_opc_get_recipe: @@ -2143,7 +2159,8 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps, caps->nvm_unified_update); break; case ICE_AQC_CAPS_RDMA: - caps->rdma = (number == 1); + if (IS_ENABLED(CONFIG_INFINIBAND_IRDMA)) + caps->rdma = (number == 1); ice_debug(hw, ICE_DBG_INIT, "%s: rdma = %d\n", prefix, caps->rdma); break; case ICE_AQC_CAPS_MAX_MTU: @@ -2171,6 +2188,9 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps, ice_debug(hw, ICE_DBG_INIT, "%s: sriov_lag = %u\n", prefix, caps->sriov_lag); break; + case ICE_AQC_CAPS_TX_SCHED_TOPO_COMP_MODE: + caps->tx_sched_topo_comp_mode_en = (number == 1); + break; default: /* Not one of the recognized common capabilities */ found = false; @@ -2277,8 +2297,13 @@ ice_parse_1588_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p, info->tmr_index_owned = ((number & ICE_TS_TMR_IDX_OWND_M) != 0); info->tmr_index_assoc = ((number & ICE_TS_TMR_IDX_ASSOC_M) != 0); - info->clk_freq = FIELD_GET(ICE_TS_CLK_FREQ_M, number); - info->clk_src = ((number & ICE_TS_CLK_SRC_M) != 0); + if (hw->mac_type != ICE_MAC_GENERIC_3K_E825) { + info->clk_freq = FIELD_GET(ICE_TS_CLK_FREQ_M, number); + info->clk_src = ((number & ICE_TS_CLK_SRC_M) != 0); + } else { + info->clk_freq = ICE_TIME_REF_FREQ_156_250; + info->clk_src = ICE_CLK_SRC_TCXO; + } if (info->clk_freq < NUM_ICE_TIME_REF_FREQ) { info->time_ref = (enum ice_time_ref_freq)info->clk_freq; @@ -2398,6 +2423,25 @@ ice_parse_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p, } /** + * ice_func_id_to_logical_id - map from function id to logical pf id + * @active_function_bitmap: active function bitmap + * @pf_id: function number of device + * + * Return: logical PF ID. + */ +static int ice_func_id_to_logical_id(u32 active_function_bitmap, u8 pf_id) +{ + u8 logical_id = 0; + u8 i; + + for (i = 0; i < pf_id; i++) + if (active_function_bitmap & BIT(i)) + logical_id++; + + return logical_id; +} + +/** * ice_parse_valid_functions_cap - Parse ICE_AQC_CAPS_VALID_FUNCTIONS caps * @hw: pointer to the HW struct * @dev_p: pointer to device capabilities structure @@ -2414,6 +2458,8 @@ ice_parse_valid_functions_cap(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, dev_p->num_funcs = hweight32(number); ice_debug(hw, ICE_DBG_INIT, "dev caps: num_funcs = %d\n", dev_p->num_funcs); + + hw->logical_pf_id = ice_func_id_to_logical_id(number, hw->pf_id); } /** @@ -2484,6 +2530,7 @@ ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, info->ts_ll_read = ((number & ICE_TS_LL_TX_TS_READ_M) != 0); info->ts_ll_int_read = ((number & ICE_TS_LL_TX_TS_INT_READ_M) != 0); + info->ll_phy_tmr_update = ((number & ICE_TS_LL_PHY_TMR_UPDATE_M) != 0); info->ena_ports = logical_id; info->tmr_own_map = phys_id; @@ -2506,6 +2553,8 @@ ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, info->ts_ll_read); ice_debug(hw, ICE_DBG_INIT, "dev caps: ts_ll_int_read = %u\n", info->ts_ll_int_read); + ice_debug(hw, ICE_DBG_INIT, "dev caps: ll_phy_tmr_update = %u\n", + info->ll_phy_tmr_update); ice_debug(hw, ICE_DBG_INIT, "dev caps: ieee_1588 ena_ports = %u\n", info->ena_ports); ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr_own_map = %u\n", @@ -2552,6 +2601,34 @@ ice_parse_sensor_reading_cap(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, } /** + * ice_parse_nac_topo_dev_caps - Parse ICE_AQC_CAPS_NAC_TOPOLOGY cap + * @hw: pointer to the HW struct + * @dev_p: pointer to device capabilities structure + * @cap: capability element to parse + * + * Parse ICE_AQC_CAPS_NAC_TOPOLOGY for device capabilities. + */ +static void ice_parse_nac_topo_dev_caps(struct ice_hw *hw, + struct ice_hw_dev_caps *dev_p, + struct ice_aqc_list_caps_elem *cap) +{ + dev_p->nac_topo.mode = le32_to_cpu(cap->number); + dev_p->nac_topo.id = le32_to_cpu(cap->phys_id) & ICE_NAC_TOPO_ID_M; + + dev_info(ice_hw_to_dev(hw), + "PF is configured in %s mode with IP instance ID %d\n", + (dev_p->nac_topo.mode & ICE_NAC_TOPO_PRIMARY_M) ? + "primary" : "secondary", dev_p->nac_topo.id); + + ice_debug(hw, ICE_DBG_INIT, "dev caps: nac topology is_primary = %d\n", + !!(dev_p->nac_topo.mode & ICE_NAC_TOPO_PRIMARY_M)); + ice_debug(hw, ICE_DBG_INIT, "dev caps: nac topology is_dual = %d\n", + !!(dev_p->nac_topo.mode & ICE_NAC_TOPO_DUAL_M)); + ice_debug(hw, ICE_DBG_INIT, "dev caps: nac topology id = %d\n", + dev_p->nac_topo.id); +} + +/** * ice_parse_dev_caps - Parse device capabilities * @hw: pointer to the HW struct * @dev_p: pointer to device capabilities structure @@ -2602,6 +2679,9 @@ ice_parse_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, case ICE_AQC_CAPS_SENSOR_READING: ice_parse_sensor_reading_cap(hw, dev_p, &cap_resp[i]); break; + case ICE_AQC_CAPS_NAC_TOPOLOGY: + ice_parse_nac_topo_dev_caps(hw, dev_p, &cap_resp[i]); + break; default: /* Don't list common capabilities as unknown */ if (!found) @@ -2615,40 +2695,6 @@ 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 * @@ -2656,9 +2702,11 @@ bool ice_is_pf_c827(struct ice_hw *hw) */ 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, + if (ice_find_netlist_node(hw, ICE_AQC_LINK_TOPO_NODE_TYPE_PHY, + ICE_AQC_LINK_TOPO_NODE_CTX_PORT, ICE_AQC_GET_LINK_TOPO_NODE_NR_C827, NULL) && - ice_find_netlist_node(hw, ICE_AQC_LINK_TOPO_NODE_TYPE_CLK_CTRL, + ice_find_netlist_node(hw, ICE_AQC_LINK_TOPO_NODE_TYPE_PHY, + ICE_AQC_LINK_TOPO_NODE_CTX_PORT, ICE_AQC_GET_LINK_TOPO_NODE_NR_E822_PHY, NULL)) return false; @@ -2674,6 +2722,7 @@ bool ice_is_phy_rclk_in_netlist(struct ice_hw *hw) 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_LINK_TOPO_NODE_CTX_GLOBAL, ICE_AQC_GET_LINK_TOPO_NODE_NR_GEN_CLK_MUX, NULL)) return false; @@ -2694,12 +2743,14 @@ bool ice_is_clock_mux_in_netlist(struct ice_hw *hw) 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_LINK_TOPO_NODE_CTX_GLOBAL, 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_LINK_TOPO_NODE_CTX_GLOBAL, ICE_AQC_GET_LINK_TOPO_NODE_NR_SI5383_5384, NULL)) { hw->cgu_part_number = ICE_AQC_GET_LINK_TOPO_NODE_NR_SI5383_5384; @@ -2718,6 +2769,7 @@ bool ice_is_cgu_in_netlist(struct ice_hw *hw) 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_LINK_TOPO_NODE_CTX_GLOBAL, ICE_AQC_GET_LINK_TOPO_NODE_NR_GEN_GPS, NULL)) return false; @@ -2997,6 +3049,9 @@ ice_aq_set_port_params(struct ice_port_info *pi, bool double_vlan, cmd_flags |= ICE_AQC_SET_P_PARAMS_DOUBLE_VLAN_ENA; cmd->cmd_flags = cpu_to_le16(cmd_flags); + cmd->local_fwd_mode = pi->local_fwd_mode | + ICE_AQC_SET_P_PARAMS_LOCAL_FWD_MODE_VALID; + return ice_aq_send_cmd(hw, &desc, NULL, 0, cd); } @@ -3030,11 +3085,13 @@ bool ice_is_100m_speed_supported(struct ice_hw *hw) * Note: In the structure of [phy_type_low, phy_type_high], there should * be one bit set, as this function will convert one PHY type to its * speed. - * If no bit gets set, ICE_AQ_LINK_SPEED_UNKNOWN will be returned - * If more than one bit gets set, ICE_AQ_LINK_SPEED_UNKNOWN will be returned + * + * Return: + * * PHY speed for recognized PHY type + * * If no bit gets set, ICE_AQ_LINK_SPEED_UNKNOWN will be returned + * * If more than one bit gets set, ICE_AQ_LINK_SPEED_UNKNOWN will be returned */ -static u16 -ice_get_link_speed_based_on_phy_type(u64 phy_type_low, u64 phy_type_high) +u16 ice_get_link_speed_based_on_phy_type(u64 phy_type_low, u64 phy_type_high) { u16 speed_phy_type_high = ICE_AQ_LINK_SPEED_UNKNOWN; u16 speed_phy_type_low = ICE_AQ_LINK_SPEED_UNKNOWN; @@ -3135,6 +3192,16 @@ ice_get_link_speed_based_on_phy_type(u64 phy_type_low, u64 phy_type_high) case ICE_PHY_TYPE_HIGH_100G_AUI2: speed_phy_type_high = ICE_AQ_LINK_SPEED_100GB; break; + case ICE_PHY_TYPE_HIGH_200G_CR4_PAM4: + case ICE_PHY_TYPE_HIGH_200G_SR4: + case ICE_PHY_TYPE_HIGH_200G_FR4: + case ICE_PHY_TYPE_HIGH_200G_LR4: + case ICE_PHY_TYPE_HIGH_200G_DR4: + case ICE_PHY_TYPE_HIGH_200G_KR4_PAM4: + case ICE_PHY_TYPE_HIGH_200G_AUI4_AOC_ACC: + case ICE_PHY_TYPE_HIGH_200G_AUI4: + speed_phy_type_high = ICE_AQ_LINK_SPEED_200GB; + break; default: speed_phy_type_high = ICE_AQ_LINK_SPEED_UNKNOWN; break; @@ -3286,6 +3353,100 @@ int ice_update_link_info(struct ice_port_info *pi) } /** + * ice_aq_get_phy_equalization - function to read serdes equaliser + * value from firmware using admin queue command. + * @hw: pointer to the HW struct + * @data_in: represents the serdes equalization parameter requested + * @op_code: represents the serdes number and flag to represent tx or rx + * @serdes_num: represents the serdes number + * @output: pointer to the caller-supplied buffer to return serdes equaliser + * + * Return: non-zero status on error and 0 on success. + */ +int ice_aq_get_phy_equalization(struct ice_hw *hw, u16 data_in, u16 op_code, + u8 serdes_num, int *output) +{ + struct ice_aqc_dnl_call_command *cmd; + struct ice_aqc_dnl_call buf = {}; + struct ice_aq_desc desc; + int err; + + buf.sto.txrx_equa_reqs.data_in = cpu_to_le16(data_in); + buf.sto.txrx_equa_reqs.op_code_serdes_sel = + cpu_to_le16(op_code | (serdes_num & 0xF)); + cmd = &desc.params.dnl_call; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_dnl_call); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_BUF | + ICE_AQ_FLAG_RD | + ICE_AQ_FLAG_SI); + desc.datalen = cpu_to_le16(sizeof(struct ice_aqc_dnl_call)); + cmd->activity_id = cpu_to_le16(ICE_AQC_ACT_ID_DNL); + + err = ice_aq_send_cmd(hw, &desc, &buf, sizeof(struct ice_aqc_dnl_call), + NULL); + *output = err ? 0 : buf.sto.txrx_equa_resp.val; + + return err; +} + +#define FEC_REG_PORT(port) { \ + FEC_CORR_LOW_REG_PORT##port, \ + FEC_CORR_HIGH_REG_PORT##port, \ + FEC_UNCORR_LOW_REG_PORT##port, \ + FEC_UNCORR_HIGH_REG_PORT##port, \ +} + +static const u32 fec_reg[][ICE_FEC_MAX] = { + FEC_REG_PORT(0), + FEC_REG_PORT(1), + FEC_REG_PORT(2), + FEC_REG_PORT(3) +}; + +/** + * ice_aq_get_fec_stats - reads fec stats from phy + * @hw: pointer to the HW struct + * @pcs_quad: represents pcsquad of user input serdes + * @pcs_port: represents the pcs port number part of above pcs quad + * @fec_type: represents FEC stats type + * @output: pointer to the caller-supplied buffer to return requested fec stats + * + * Return: non-zero status on error and 0 on success. + */ +int ice_aq_get_fec_stats(struct ice_hw *hw, u16 pcs_quad, u16 pcs_port, + enum ice_fec_stats_types fec_type, u32 *output) +{ + u16 flag = (ICE_AQ_FLAG_RD | ICE_AQ_FLAG_BUF | ICE_AQ_FLAG_SI); + struct ice_sbq_msg_input msg = {}; + u32 receiver_id, reg_offset; + int err; + + if (pcs_port > 3) + return -EINVAL; + + reg_offset = fec_reg[pcs_port][fec_type]; + + if (pcs_quad == 0) + receiver_id = FEC_RECEIVER_ID_PCS0; + else if (pcs_quad == 1) + receiver_id = FEC_RECEIVER_ID_PCS1; + else + return -EINVAL; + + msg.msg_addr_low = lower_16_bits(reg_offset); + msg.msg_addr_high = receiver_id; + msg.opcode = ice_sbq_msg_rd; + msg.dest_dev = ice_sbq_dev_phy_0; + + err = ice_sbq_rw_reg(hw, &msg, flag); + if (err) + return err; + + *output = msg.data; + return 0; +} + +/** * ice_cache_phy_user_req * @pi: port information structure * @cache_data: PHY logging data @@ -3887,6 +4048,59 @@ ice_aq_set_port_option(struct ice_hw *hw, u8 lport, u8 lport_valid, } /** + * ice_get_phy_lane_number - Get PHY lane number for current adapter + * @hw: pointer to the hw struct + * + * Return: PHY lane number on success, negative error code otherwise. + */ +int ice_get_phy_lane_number(struct ice_hw *hw) +{ + struct ice_aqc_get_port_options_elem *options; + unsigned int lport = 0; + unsigned int lane; + int err; + + options = kcalloc(ICE_AQC_PORT_OPT_MAX, sizeof(*options), GFP_KERNEL); + if (!options) + return -ENOMEM; + + for (lane = 0; lane < ICE_MAX_PORT_PER_PCI_DEV; lane++) { + u8 options_count = ICE_AQC_PORT_OPT_MAX; + u8 speed, active_idx, pending_idx; + bool active_valid, pending_valid; + + err = ice_aq_get_port_options(hw, options, &options_count, lane, + true, &active_idx, &active_valid, + &pending_idx, &pending_valid); + if (err) + goto err; + + if (!active_valid) + continue; + + speed = options[active_idx].max_lane_speed; + /* If we don't get speed for this lane, it's unoccupied */ + if (speed > ICE_AQC_PORT_OPT_MAX_LANE_200G) + continue; + + if (hw->pf_id == lport) { + if (hw->mac_type == ICE_MAC_GENERIC_3K_E825 && + ice_is_dual(hw) && !ice_is_primary(hw)) + lane += ICE_PORTS_PER_QUAD; + kfree(options); + return lane; + } + lport++; + } + + /* PHY lane not found */ + err = -ENXIO; +err: + kfree(options); + return err; +} + +/** * ice_aq_sff_eeprom * @hw: pointer to the HW struct * @lport: bits [7:0] = logical port, bit [8] = logical port valid @@ -4349,205 +4563,6 @@ ice_aq_add_rdma_qsets(struct ice_hw *hw, u8 num_qset_grps, /* End of FW Admin Queue command wrappers */ /** - * ice_pack_ctx_byte - write a byte to a packed context structure - * @src_ctx: unpacked source context structure - * @dest_ctx: packed destination context data - * @ce_info: context element description - */ -static void ice_pack_ctx_byte(u8 *src_ctx, u8 *dest_ctx, - const struct ice_ctx_ele *ce_info) -{ - u8 src_byte, dest_byte, mask; - u8 *from, *dest; - u16 shift_width; - - /* copy from the next struct field */ - from = src_ctx + ce_info->offset; - - /* prepare the bits and mask */ - shift_width = ce_info->lsb % 8; - mask = GENMASK(ce_info->width - 1 + shift_width, shift_width); - - src_byte = *from; - src_byte <<= shift_width; - src_byte &= mask; - - /* get the current bits from the target bit string */ - dest = dest_ctx + (ce_info->lsb / 8); - - memcpy(&dest_byte, dest, sizeof(dest_byte)); - - dest_byte &= ~mask; /* get the bits not changing */ - dest_byte |= src_byte; /* add in the new bits */ - - /* put it all back */ - memcpy(dest, &dest_byte, sizeof(dest_byte)); -} - -/** - * ice_pack_ctx_word - write a word to a packed context structure - * @src_ctx: unpacked source context structure - * @dest_ctx: packed destination context data - * @ce_info: context element description - */ -static void ice_pack_ctx_word(u8 *src_ctx, u8 *dest_ctx, - const struct ice_ctx_ele *ce_info) -{ - u16 src_word, mask; - __le16 dest_word; - u8 *from, *dest; - u16 shift_width; - - /* copy from the next struct field */ - from = src_ctx + ce_info->offset; - - /* prepare the bits and mask */ - shift_width = ce_info->lsb % 8; - mask = GENMASK(ce_info->width - 1 + shift_width, shift_width); - - /* don't swizzle the bits until after the mask because the mask bits - * will be in a different bit position on big endian machines - */ - src_word = *(u16 *)from; - src_word <<= shift_width; - src_word &= mask; - - /* get the current bits from the target bit string */ - dest = dest_ctx + (ce_info->lsb / 8); - - memcpy(&dest_word, dest, sizeof(dest_word)); - - dest_word &= ~(cpu_to_le16(mask)); /* get the bits not changing */ - dest_word |= cpu_to_le16(src_word); /* add in the new bits */ - - /* put it all back */ - memcpy(dest, &dest_word, sizeof(dest_word)); -} - -/** - * ice_pack_ctx_dword - write a dword to a packed context structure - * @src_ctx: unpacked source context structure - * @dest_ctx: packed destination context data - * @ce_info: context element description - */ -static void ice_pack_ctx_dword(u8 *src_ctx, u8 *dest_ctx, - const struct ice_ctx_ele *ce_info) -{ - u32 src_dword, mask; - __le32 dest_dword; - u8 *from, *dest; - u16 shift_width; - - /* copy from the next struct field */ - from = src_ctx + ce_info->offset; - - /* prepare the bits and mask */ - shift_width = ce_info->lsb % 8; - mask = GENMASK(ce_info->width - 1 + shift_width, shift_width); - - /* don't swizzle the bits until after the mask because the mask bits - * will be in a different bit position on big endian machines - */ - src_dword = *(u32 *)from; - src_dword <<= shift_width; - src_dword &= mask; - - /* get the current bits from the target bit string */ - dest = dest_ctx + (ce_info->lsb / 8); - - memcpy(&dest_dword, dest, sizeof(dest_dword)); - - dest_dword &= ~(cpu_to_le32(mask)); /* get the bits not changing */ - dest_dword |= cpu_to_le32(src_dword); /* add in the new bits */ - - /* put it all back */ - memcpy(dest, &dest_dword, sizeof(dest_dword)); -} - -/** - * ice_pack_ctx_qword - write a qword to a packed context structure - * @src_ctx: unpacked source context structure - * @dest_ctx: packed destination context data - * @ce_info: context element description - */ -static void ice_pack_ctx_qword(u8 *src_ctx, u8 *dest_ctx, - const struct ice_ctx_ele *ce_info) -{ - u64 src_qword, mask; - __le64 dest_qword; - u8 *from, *dest; - u16 shift_width; - - /* copy from the next struct field */ - from = src_ctx + ce_info->offset; - - /* prepare the bits and mask */ - shift_width = ce_info->lsb % 8; - mask = GENMASK_ULL(ce_info->width - 1 + shift_width, shift_width); - - /* don't swizzle the bits until after the mask because the mask bits - * will be in a different bit position on big endian machines - */ - src_qword = *(u64 *)from; - src_qword <<= shift_width; - src_qword &= mask; - - /* get the current bits from the target bit string */ - dest = dest_ctx + (ce_info->lsb / 8); - - memcpy(&dest_qword, dest, sizeof(dest_qword)); - - dest_qword &= ~(cpu_to_le64(mask)); /* get the bits not changing */ - dest_qword |= cpu_to_le64(src_qword); /* add in the new bits */ - - /* put it all back */ - memcpy(dest, &dest_qword, sizeof(dest_qword)); -} - -/** - * ice_set_ctx - set context bits in packed structure - * @hw: pointer to the hardware structure - * @src_ctx: pointer to a generic non-packed context structure - * @dest_ctx: pointer to memory for the packed structure - * @ce_info: List of Rx context elements - */ -int ice_set_ctx(struct ice_hw *hw, u8 *src_ctx, u8 *dest_ctx, - const struct ice_ctx_ele *ce_info) -{ - int f; - - for (f = 0; ce_info[f].width; f++) { - /* We have to deal with each element of the FW response - * using the correct size so that we are correct regardless - * of the endianness of the machine. - */ - if (ce_info[f].width > (ce_info[f].size_of * BITS_PER_BYTE)) { - ice_debug(hw, ICE_DBG_QCTX, "Field %d width of %d bits larger than size of %d byte(s) ... skipping write\n", - f, ce_info[f].width, ce_info[f].size_of); - continue; - } - switch (ce_info[f].size_of) { - case sizeof(u8): - ice_pack_ctx_byte(src_ctx, dest_ctx, &ce_info[f]); - break; - case sizeof(u16): - ice_pack_ctx_word(src_ctx, dest_ctx, &ce_info[f]); - break; - case sizeof(u32): - ice_pack_ctx_dword(src_ctx, dest_ctx, &ce_info[f]); - break; - case sizeof(u64): - ice_pack_ctx_qword(src_ctx, dest_ctx, &ce_info[f]); - break; - default: - return -EINVAL; - } - } - - return 0; -} - -/** * ice_get_lan_q_ctx - get the LAN queue context for the given VSI and TC * @hw: pointer to the HW struct * @vsi_handle: software VSI handle @@ -5641,6 +5656,96 @@ ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, } /** + * ice_get_pca9575_handle - find and return the PCA9575 controller + * @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. + * + * Return: 0 on success, -ENXIO when there's no PCA9575 present. + */ +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 err; + u8 idx; + + /* If handle was read previously return cached value */ + if (hw->io_expander_handle) { + *pca9575_handle = hw->io_expander_handle; + return 0; + } + +#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 -ENXIO; + + /* If handle was not detected read it from the netlist */ + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo); + cmd = &desc.params.get_link_topo; + cmd->addr.topo_params.node_type_ctx = + ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL; + cmd->addr.topo_params.index = idx; + + err = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (err) + return -ENXIO; + + /* 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 -ENXIO; + + /* 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_pca9575_reg - read the register from the PCA9575 controller + * @hw: pointer to the hw struct + * @offset: GPIO controller register offset + * @data: pointer to data to be read from the GPIO controller + * + * Return: 0 on success, negative error code otherwise. + */ +int ice_read_pca9575_reg(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); +} + +/** * ice_aq_set_gpio * @hw: pointer to the hw struct * @gpio_ctrl_handle: GPIO controller node handle @@ -5823,6 +5928,44 @@ bool ice_is_phy_caps_an_enabled(struct ice_aqc_get_phy_caps_data *caps) } /** + * ice_is_fw_health_report_supported - checks if firmware supports health events + * @hw: pointer to the hardware structure + * + * Return: true if firmware supports health status reports, + * false otherwise + */ +bool ice_is_fw_health_report_supported(struct ice_hw *hw) +{ + return ice_is_fw_api_min_ver(hw, ICE_FW_API_HEALTH_REPORT_MAJ, + ICE_FW_API_HEALTH_REPORT_MIN, + ICE_FW_API_HEALTH_REPORT_PATCH); +} + +/** + * ice_aq_set_health_status_cfg - Configure FW health events + * @hw: pointer to the HW struct + * @event_source: type of diagnostic events to enable + * + * Configure the health status event types that the firmware will send to this + * PF. The supported event types are: PF-specific, all PFs, and global. + * + * Return: 0 on success, negative error code otherwise. + */ +int ice_aq_set_health_status_cfg(struct ice_hw *hw, u8 event_source) +{ + struct ice_aqc_set_health_status_cfg *cmd; + struct ice_aq_desc desc; + + cmd = &desc.params.set_health_status_cfg; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_health_status_cfg); + + cmd->event_source = event_source; + + return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); +} + +/** * ice_aq_set_lldp_mib - Set the LLDP MIB * @hw: pointer to the HW struct * @mib_type: Local, Remote or both Local and Remote MIBs @@ -5872,15 +6015,21 @@ bool ice_fw_supports_lldp_fltr_ctrl(struct ice_hw *hw) /** * ice_lldp_fltr_add_remove - add or remove a LLDP Rx switch filter * @hw: pointer to HW struct - * @vsi_num: absolute HW index for VSI + * @vsi: VSI to add the filter to * @add: boolean for if adding or removing a filter + * + * Return: 0 on success, -EOPNOTSUPP if the operation cannot be performed + * with this HW or VSI, otherwise an error corresponding to + * the AQ transaction result. */ -int -ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add) +int ice_lldp_fltr_add_remove(struct ice_hw *hw, struct ice_vsi *vsi, bool add) { struct ice_aqc_lldp_filter_ctrl *cmd; struct ice_aq_desc desc; + if (vsi->type != ICE_VSI_PF || !ice_fw_supports_lldp_fltr_ctrl(hw)) + return -EOPNOTSUPP; + cmd = &desc.params.lldp_filter_ctrl; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_filter_ctrl); @@ -5890,7 +6039,7 @@ ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add) else cmd->cmd_flags = ICE_AQC_LLDP_FILTER_ACTION_DELETE; - cmd->vsi_num = cpu_to_le16(vsi_num); + cmd->vsi_num = cpu_to_le16(vsi->vsi_num); return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); } diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index ffb22c7ce28b..64c530b39191 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -10,6 +10,7 @@ #include "ice_type.h" #include "ice_nvm.h" #include "ice_flex_pipe.h" +#include "ice_parser.h" #include <linux/avf/virtchnl.h> #include "ice_switch.h" #include "ice_fdir.h" @@ -17,13 +18,34 @@ #define ICE_SQ_SEND_DELAY_TIME_MS 10 #define ICE_SQ_SEND_MAX_EXECUTE 3 +#define FEC_REG_SHIFT 2 +#define FEC_RECV_ID_SHIFT 4 +#define FEC_CORR_LOW_REG_PORT0 (0x02 << FEC_REG_SHIFT) +#define FEC_CORR_HIGH_REG_PORT0 (0x03 << FEC_REG_SHIFT) +#define FEC_UNCORR_LOW_REG_PORT0 (0x04 << FEC_REG_SHIFT) +#define FEC_UNCORR_HIGH_REG_PORT0 (0x05 << FEC_REG_SHIFT) +#define FEC_CORR_LOW_REG_PORT1 (0x42 << FEC_REG_SHIFT) +#define FEC_CORR_HIGH_REG_PORT1 (0x43 << FEC_REG_SHIFT) +#define FEC_UNCORR_LOW_REG_PORT1 (0x44 << FEC_REG_SHIFT) +#define FEC_UNCORR_HIGH_REG_PORT1 (0x45 << FEC_REG_SHIFT) +#define FEC_CORR_LOW_REG_PORT2 (0x4A << FEC_REG_SHIFT) +#define FEC_CORR_HIGH_REG_PORT2 (0x4B << FEC_REG_SHIFT) +#define FEC_UNCORR_LOW_REG_PORT2 (0x4C << FEC_REG_SHIFT) +#define FEC_UNCORR_HIGH_REG_PORT2 (0x4D << FEC_REG_SHIFT) +#define FEC_CORR_LOW_REG_PORT3 (0x52 << FEC_REG_SHIFT) +#define FEC_CORR_HIGH_REG_PORT3 (0x53 << FEC_REG_SHIFT) +#define FEC_UNCORR_LOW_REG_PORT3 (0x54 << FEC_REG_SHIFT) +#define FEC_UNCORR_HIGH_REG_PORT3 (0x55 << FEC_REG_SHIFT) +#define FEC_RECEIVER_ID_PCS0 (0x33 << FEC_RECV_ID_SHIFT) +#define FEC_RECEIVER_ID_PCS1 (0x34 << FEC_RECV_ID_SHIFT) + int ice_init_hw(struct ice_hw *hw); void ice_deinit_hw(struct ice_hw *hw); int ice_check_reset(struct ice_hw *hw); int ice_reset(struct ice_hw *hw, enum ice_reset_req req); int ice_create_all_ctrlq(struct ice_hw *hw); int ice_init_all_ctrlq(struct ice_hw *hw); -void ice_shutdown_all_ctrlq(struct ice_hw *hw); +void ice_shutdown_all_ctrlq(struct ice_hw *hw, bool unloading); void ice_destroy_all_ctrlq(struct ice_hw *hw); int ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq, @@ -70,9 +92,8 @@ ice_aq_set_rss_key(struct ice_hw *hw, u16 vsi_handle, bool ice_check_sq_alive(struct ice_hw *hw, struct ice_ctl_q_info *cq); int ice_aq_q_shutdown(struct ice_hw *hw, bool unloading); void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode); -extern const struct ice_ctx_ele ice_tlan_ctx_info[]; -int ice_set_ctx(struct ice_hw *hw, u8 *src_ctx, u8 *dest_ctx, - const struct ice_ctx_ele *ce_info); + +void ice_pack_txq_ctx(const struct ice_tlan_ctx *ctx, ice_txq_ctx_buf_t *buf); extern struct mutex ice_global_cfg_lock_sw; @@ -91,7 +112,6 @@ 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); @@ -111,7 +131,6 @@ int ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags, struct ice_sq_cd *cd); bool ice_is_generic_mac(struct ice_hw *hw); -bool ice_is_e810(struct ice_hw *hw); int ice_clear_pf_cfg(struct ice_hw *hw); int ice_aq_set_phy_cfg(struct ice_hw *hw, struct ice_port_info *pi, @@ -121,6 +140,13 @@ int ice_get_link_default_override(struct ice_link_default_override_tlv *ldo, struct ice_port_info *pi); bool ice_is_phy_caps_an_enabled(struct ice_aqc_get_phy_caps_data *caps); +bool ice_is_fw_health_report_supported(struct ice_hw *hw); +int ice_aq_set_health_status_cfg(struct ice_hw *hw, u8 event_source); +int ice_aq_get_phy_equalization(struct ice_hw *hw, u16 data_in, u16 op_code, + u8 serdes_num, int *output); +int +ice_aq_get_fec_stats(struct ice_hw *hw, u16 pcs_quad, u16 pcs_port, + enum ice_fec_stats_types fec_type, u32 *output); enum ice_fc_mode ice_caps_to_fc_mode(u8 caps); enum ice_fec_mode ice_caps_to_fec_mode(u8 caps, u8 fec_options); @@ -166,6 +192,7 @@ ice_aq_get_port_options(struct ice_hw *hw, int ice_aq_set_port_option(struct ice_hw *hw, u8 lport, u8 lport_valid, u8 new_option); +int ice_get_phy_lane_number(struct ice_hw *hw); int ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr, u16 mem_addr, u8 page, u8 set_page, u8 *data, u8 length, @@ -201,7 +228,7 @@ int ice_replay_vsi(struct ice_hw *hw, u16 vsi_handle); void ice_replay_post(struct ice_hw *hw); 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_sbq_rw_reg(struct ice_hw *hw, struct ice_sbq_msg_input *in, u16 flag); int ice_aq_get_cgu_abilities(struct ice_hw *hw, struct ice_aqc_get_cgu_abilities *abilities); @@ -248,9 +275,6 @@ ice_stat_update40(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, void ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat); -bool ice_is_e810t(struct ice_hw *hw); -bool ice_is_e823(struct ice_hw *hw); -bool ice_is_e825c(struct ice_hw *hw); int ice_sched_query_elem(struct ice_hw *hw, u32 node_teid, struct ice_aqc_txsched_elem_data *buf); @@ -261,12 +285,12 @@ int ice_aq_get_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx, bool *value, struct ice_sq_cd *cd); bool ice_is_100m_speed_supported(struct ice_hw *hw); +u16 ice_get_link_speed_based_on_phy_type(u64 phy_type_low, u64 phy_type_high); int ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size, struct ice_sq_cd *cd); bool ice_fw_supports_lldp_fltr_ctrl(struct ice_hw *hw); -int -ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add); +int ice_lldp_fltr_add_remove(struct ice_hw *hw, struct ice_vsi *vsi, bool add); int ice_lldp_execute_pending_mib(struct ice_hw *hw); int ice_aq_read_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, @@ -276,5 +300,7 @@ int ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, u16 bus_addr, __le16 addr, u8 params, const u8 *data, struct ice_sq_cd *cd); +int ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle); +int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data); bool ice_fw_supports_report_dflt_cfg(struct ice_hw *hw); #endif /* _ICE_COMMON_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c index ffe660f34992..e3959ad442a2 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.c +++ b/drivers/net/ethernet/intel/ice/ice_controlq.c @@ -99,17 +99,6 @@ ice_alloc_ctrlq_sq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq) return -ENOMEM; cq->sq.desc_buf.size = size; - cq->sq.cmd_buf = devm_kcalloc(ice_hw_to_dev(hw), cq->num_sq_entries, - sizeof(struct ice_sq_cd), GFP_KERNEL); - if (!cq->sq.cmd_buf) { - dmam_free_coherent(ice_hw_to_dev(hw), cq->sq.desc_buf.size, - cq->sq.desc_buf.va, cq->sq.desc_buf.pa); - cq->sq.desc_buf.va = NULL; - cq->sq.desc_buf.pa = 0; - cq->sq.desc_buf.size = 0; - return -ENOMEM; - } - return 0; } @@ -188,7 +177,7 @@ ice_alloc_rq_bufs(struct ice_hw *hw, struct ice_ctl_q_info *cq) if (cq->rq_buf_size > ICE_AQ_LG_BUF) desc->flags |= cpu_to_le16(ICE_AQ_FLAG_LB); desc->opcode = 0; - /* This is in accordance with Admin queue design, there is no + /* This is in accordance with control queue design, there is no * register for buffer size configuration */ desc->datalen = cpu_to_le16(bi->size); @@ -338,8 +327,6 @@ do { \ (qi)->ring.r.ring##_bi[i].size = 0;\ } \ } \ - /* free the buffer info list */ \ - devm_kfree(ice_hw_to_dev(hw), (qi)->ring.cmd_buf); \ /* free DMA head */ \ devm_kfree(ice_hw_to_dev(hw), (qi)->ring.dma_head); \ } while (0) @@ -405,11 +392,11 @@ init_ctrlq_exit: } /** - * ice_init_rq - initialize ARQ + * ice_init_rq - initialize receive side of a control queue * @hw: pointer to the hardware structure * @cq: pointer to the specific Control queue * - * The main initialization routine for the Admin Receive (Event) Queue. + * The main initialization routine for Receive side of a control queue. * Prior to calling this function, the driver *MUST* set the following fields * in the cq->structure: * - cq->num_rq_entries @@ -465,7 +452,7 @@ init_ctrlq_exit: } /** - * ice_shutdown_sq - shutdown the Control ATQ + * ice_shutdown_sq - shutdown the transmit side of a control queue * @hw: pointer to the hardware structure * @cq: pointer to the specific Control queue * @@ -482,7 +469,7 @@ static int ice_shutdown_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq) goto shutdown_sq_out; } - /* Stop firmware AdminQ processing */ + /* Stop processing of the control queue */ wr32(hw, cq->sq.head, 0); wr32(hw, cq->sq.tail, 0); wr32(hw, cq->sq.len, 0); @@ -501,7 +488,7 @@ shutdown_sq_out: } /** - * ice_aq_ver_check - Check the reported AQ API version. + * ice_aq_ver_check - Check the reported AQ API version * @hw: pointer to the hardware structure * * Checks if the driver should load on a given AQ API version. @@ -510,22 +497,31 @@ shutdown_sq_out: */ static bool ice_aq_ver_check(struct ice_hw *hw) { - if (hw->api_maj_ver > EXP_FW_API_VER_MAJOR) { + u8 exp_fw_api_ver_major = EXP_FW_API_VER_MAJOR_BY_MAC(hw); + u8 exp_fw_api_ver_minor = EXP_FW_API_VER_MINOR_BY_MAC(hw); + + if (hw->api_maj_ver > exp_fw_api_ver_major) { /* Major API version is newer than expected, don't load */ dev_warn(ice_hw_to_dev(hw), "The driver for the device stopped because the NVM image is newer than expected. You must install the most recent version of the network driver.\n"); return false; - } else if (hw->api_maj_ver == EXP_FW_API_VER_MAJOR) { - if (hw->api_min_ver > (EXP_FW_API_VER_MINOR + 2)) + } else if (hw->api_maj_ver == exp_fw_api_ver_major) { + if (hw->api_min_ver > (exp_fw_api_ver_minor + 2)) dev_info(ice_hw_to_dev(hw), - "The driver for the device detected a newer version of the NVM image than expected. Please install the most recent version of the network driver.\n"); - else if ((hw->api_min_ver + 2) < EXP_FW_API_VER_MINOR) + "The driver for the device detected a newer version (%u.%u) of the NVM image than expected (%u.%u). Please install the most recent version of the network driver.\n", + hw->api_maj_ver, hw->api_min_ver, + exp_fw_api_ver_major, exp_fw_api_ver_minor); + else if ((hw->api_min_ver + 2) < exp_fw_api_ver_minor) dev_info(ice_hw_to_dev(hw), - "The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n"); + "The driver for the device detected an older version (%u.%u) of the NVM image than expected (%u.%u). Please update the NVM image.\n", + hw->api_maj_ver, hw->api_min_ver, + exp_fw_api_ver_major, exp_fw_api_ver_minor); } else { /* Major API version is older than expected, log a warning */ dev_info(ice_hw_to_dev(hw), - "The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n"); + "The driver for the device detected an older version (%u.%u) of the NVM image than expected (%u.%u). Please update the NVM image.\n", + hw->api_maj_ver, hw->api_min_ver, + exp_fw_api_ver_major, exp_fw_api_ver_minor); } return true; } @@ -684,10 +680,12 @@ struct ice_ctl_q_info *ice_get_sbq(struct ice_hw *hw) * ice_shutdown_ctrlq - shutdown routine for any control queue * @hw: pointer to the hardware structure * @q_type: specific Control queue type + * @unloading: is the driver unloading itself * * NOTE: this function does not destroy the control queue locks. */ -static void ice_shutdown_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) +static void ice_shutdown_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type, + bool unloading) { struct ice_ctl_q_info *cq; @@ -695,7 +693,7 @@ static void ice_shutdown_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) case ICE_CTL_Q_ADMIN: cq = &hw->adminq; if (ice_check_sq_alive(hw, cq)) - ice_aq_q_shutdown(hw, true); + ice_aq_q_shutdown(hw, unloading); break; case ICE_CTL_Q_SB: cq = &hw->sbq; @@ -714,20 +712,21 @@ static void ice_shutdown_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) /** * ice_shutdown_all_ctrlq - shutdown routine for all control queues * @hw: pointer to the hardware structure + * @unloading: is the driver unloading itself * * NOTE: this function does not destroy the control queue locks. The driver * may call this at runtime to shutdown and later restart control queues, such * as in response to a reset event. */ -void ice_shutdown_all_ctrlq(struct ice_hw *hw) +void ice_shutdown_all_ctrlq(struct ice_hw *hw, bool unloading) { /* Shutdown FW admin queue */ - ice_shutdown_ctrlq(hw, ICE_CTL_Q_ADMIN); + ice_shutdown_ctrlq(hw, ICE_CTL_Q_ADMIN, unloading); /* Shutdown PHY Sideband */ if (ice_is_sbq_supported(hw)) - ice_shutdown_ctrlq(hw, ICE_CTL_Q_SB); + ice_shutdown_ctrlq(hw, ICE_CTL_Q_SB, unloading); /* Shutdown PF-VF Mailbox */ - ice_shutdown_ctrlq(hw, ICE_CTL_Q_MAILBOX); + ice_shutdown_ctrlq(hw, ICE_CTL_Q_MAILBOX, unloading); } /** @@ -759,7 +758,7 @@ int ice_init_all_ctrlq(struct ice_hw *hw) break; ice_debug(hw, ICE_DBG_AQ_MSG, "Retry Admin Queue init due to FW critical error\n"); - ice_shutdown_ctrlq(hw, ICE_CTL_Q_ADMIN); + ice_shutdown_ctrlq(hw, ICE_CTL_Q_ADMIN, true); msleep(ICE_CTL_Q_ADMIN_INIT_MSEC); } while (retry++ < ICE_CTL_Q_ADMIN_INIT_TIMEOUT); @@ -840,7 +839,7 @@ static void ice_destroy_ctrlq_locks(struct ice_ctl_q_info *cq) void ice_destroy_all_ctrlq(struct ice_hw *hw) { /* shut down all the control queues first */ - ice_shutdown_all_ctrlq(hw); + ice_shutdown_all_ctrlq(hw, true); ice_destroy_ctrlq_locks(&hw->adminq); if (ice_is_sbq_supported(hw)) @@ -849,7 +848,7 @@ void ice_destroy_all_ctrlq(struct ice_hw *hw) } /** - * ice_clean_sq - cleans Admin send queue (ATQ) + * ice_clean_sq - cleans send side of a control queue * @hw: pointer to the hardware structure * @cq: pointer to the specific Control queue * @@ -859,21 +858,17 @@ static u16 ice_clean_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq) { struct ice_ctl_q_ring *sq = &cq->sq; u16 ntc = sq->next_to_clean; - struct ice_sq_cd *details; struct ice_aq_desc *desc; desc = ICE_CTL_Q_DESC(*sq, ntc); - details = ICE_CTL_Q_DETAILS(*sq, ntc); while (rd32(hw, cq->sq.head) != ntc) { ice_debug(hw, ICE_DBG_AQ_MSG, "ntc %d head %d.\n", ntc, rd32(hw, cq->sq.head)); memset(desc, 0, sizeof(*desc)); - memset(details, 0, sizeof(*details)); ntc++; if (ntc == sq->count) ntc = 0; desc = ICE_CTL_Q_DESC(*sq, ntc); - details = ICE_CTL_Q_DETAILS(*sq, ntc); } sq->next_to_clean = ntc; @@ -882,18 +877,43 @@ static u16 ice_clean_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq) } /** + * ice_ctl_q_str - Convert control queue type to string + * @qtype: the control queue type + * + * Return: A string name for the given control queue type. + */ +static const char *ice_ctl_q_str(enum ice_ctl_q qtype) +{ + switch (qtype) { + case ICE_CTL_Q_UNKNOWN: + return "Unknown CQ"; + case ICE_CTL_Q_ADMIN: + return "AQ"; + case ICE_CTL_Q_MAILBOX: + return "MBXQ"; + case ICE_CTL_Q_SB: + return "SBQ"; + default: + return "Unrecognized CQ"; + } +} + +/** * ice_debug_cq * @hw: pointer to the hardware structure + * @cq: pointer to the specific Control queue * @desc: pointer to control queue descriptor * @buf: pointer to command buffer * @buf_len: max length of buf + * @response: true if this is the writeback response * * Dumps debug log about control command with descriptor contents. */ -static void ice_debug_cq(struct ice_hw *hw, void *desc, void *buf, u16 buf_len) +static void ice_debug_cq(struct ice_hw *hw, struct ice_ctl_q_info *cq, + void *desc, void *buf, u16 buf_len, bool response) { struct ice_aq_desc *cq_desc = desc; - u16 len; + u16 datalen, flags; if (!IS_ENABLED(CONFIG_DYNAMIC_DEBUG) && !((ICE_DBG_AQ_DESC | ICE_DBG_AQ_DESC_BUF) & hw->debug_mask)) @@ -902,48 +922,63 @@ static void ice_debug_cq(struct ice_hw *hw, void *desc, void *buf, u16 buf_len) if (!desc) return; - len = le16_to_cpu(cq_desc->datalen); + datalen = le16_to_cpu(cq_desc->datalen); + flags = le16_to_cpu(cq_desc->flags); - ice_debug(hw, ICE_DBG_AQ_DESC, "CQ CMD: opcode 0x%04X, flags 0x%04X, datalen 0x%04X, retval 0x%04X\n", - le16_to_cpu(cq_desc->opcode), - le16_to_cpu(cq_desc->flags), - le16_to_cpu(cq_desc->datalen), le16_to_cpu(cq_desc->retval)); - ice_debug(hw, ICE_DBG_AQ_DESC, "\tcookie (h,l) 0x%08X 0x%08X\n", + ice_debug(hw, ICE_DBG_AQ_DESC, "%s %s: opcode 0x%04X, flags 0x%04X, datalen 0x%04X, retval 0x%04X\n\tcookie (h,l) 0x%08X 0x%08X\n\tparam (0,1) 0x%08X 0x%08X\n\taddr (h,l) 0x%08X 0x%08X\n", + ice_ctl_q_str(cq->qtype), response ? "Response" : "Command", + le16_to_cpu(cq_desc->opcode), flags, datalen, + le16_to_cpu(cq_desc->retval), le32_to_cpu(cq_desc->cookie_high), - le32_to_cpu(cq_desc->cookie_low)); - ice_debug(hw, ICE_DBG_AQ_DESC, "\tparam (0,1) 0x%08X 0x%08X\n", + le32_to_cpu(cq_desc->cookie_low), le32_to_cpu(cq_desc->params.generic.param0), - le32_to_cpu(cq_desc->params.generic.param1)); - ice_debug(hw, ICE_DBG_AQ_DESC, "\taddr (h,l) 0x%08X 0x%08X\n", + le32_to_cpu(cq_desc->params.generic.param1), le32_to_cpu(cq_desc->params.generic.addr_high), le32_to_cpu(cq_desc->params.generic.addr_low)); - if (buf && cq_desc->datalen != 0) { - ice_debug(hw, ICE_DBG_AQ_DESC_BUF, "Buffer:\n"); - if (buf_len < len) - len = buf_len; - - ice_debug_array(hw, ICE_DBG_AQ_DESC_BUF, 16, 1, buf, len); + /* Dump buffer iff 1) one exists and 2) is either a response indicated + * by the DD and/or CMP flag set or a command with the RD flag set. + */ + if (buf && cq_desc->datalen && + (flags & (ICE_AQ_FLAG_DD | ICE_AQ_FLAG_CMP | ICE_AQ_FLAG_RD))) { + char prefix[] = KBUILD_MODNAME " 0x12341234 0x12341234 "; + + sprintf(prefix, KBUILD_MODNAME " 0x%08X 0x%08X ", + le32_to_cpu(cq_desc->params.generic.addr_high), + le32_to_cpu(cq_desc->params.generic.addr_low)); + ice_debug_array_w_prefix(hw, ICE_DBG_AQ_DESC_BUF, prefix, + buf, + min_t(u16, buf_len, datalen)); } } /** - * ice_sq_done - check if FW has processed the Admin Send Queue (ATQ) + * ice_sq_done - poll until the last send on a control queue has completed * @hw: pointer to the HW struct * @cq: pointer to the specific Control queue * - * Returns true if the firmware has processed all descriptors on the - * admin send queue. Returns false if there are still requests pending. + * Use read_poll_timeout to poll the control queue head, checking until it + * matches next_to_use. According to the control queue designers, this has + * better timing reliability than the DD bit. + * + * Return: true if all the descriptors on the send side of a control queue + * are finished processing, false otherwise. */ static bool ice_sq_done(struct ice_hw *hw, struct ice_ctl_q_info *cq) { - /* AQ designers suggest use of head for better - * timing reliability than DD bit + u32 head; + + /* Wait a short time before the initial check, to allow hardware time + * for completion. */ - return rd32(hw, cq->sq.head) == cq->sq.next_to_use; + udelay(5); + + return !rd32_poll_timeout(hw, cq->sq.head, + head, head == cq->sq.next_to_use, + 20, ICE_CTL_Q_SQ_CMD_TIMEOUT); } /** - * ice_sq_send_cmd - send command to Control Queue (ATQ) + * ice_sq_send_cmd - send command to a control queue * @hw: pointer to the HW struct * @cq: pointer to the specific Control queue * @desc: prefilled descriptor describing the command @@ -951,8 +986,9 @@ static bool ice_sq_done(struct ice_hw *hw, struct ice_ctl_q_info *cq) * @buf_size: size of buffer for indirect commands (or 0 for direct commands) * @cd: pointer to command details structure * - * This is the main send command routine for the ATQ. It runs the queue, - * cleans the queue, etc. + * Main command for the transmit side of a control queue. It puts the command + * on the queue, bumps the tail, waits for processing of the command, captures + * command status and results, etc. */ int ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, @@ -962,8 +998,6 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, struct ice_dma_mem *dma_buf = NULL; struct ice_aq_desc *desc_on_ring; bool cmd_completed = false; - struct ice_sq_cd *details; - unsigned long timeout; int status = 0; u16 retval = 0; u32 val = 0; @@ -1007,12 +1041,6 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, goto sq_send_command_error; } - details = ICE_CTL_Q_DETAILS(cq->sq, cq->sq.next_to_use); - if (cd) - *details = *cd; - else - memset(details, 0, sizeof(*details)); - /* Call clean and check queue available function to reclaim the * descriptors that were processed by FW/MBX; the function returns the * number of desc available. The clean function called here could be @@ -1049,7 +1077,7 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, /* Debug desc and buffer */ ice_debug(hw, ICE_DBG_AQ_DESC, "ATQ: Control Send queue desc and buffer:\n"); - ice_debug_cq(hw, (void *)desc_on_ring, buf, buf_size); + ice_debug_cq(hw, cq, (void *)desc_on_ring, buf, buf_size, false); (cq->sq.next_to_use)++; if (cq->sq.next_to_use == cq->sq.count) @@ -1057,20 +1085,9 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, wr32(hw, cq->sq.tail, cq->sq.next_to_use); ice_flush(hw); - /* Wait a short time before initial ice_sq_done() check, to allow - * hardware time for completion. + /* Wait for the command to complete. If it finishes within the + * timeout, copy the descriptor back to temp. */ - udelay(5); - - timeout = jiffies + ICE_CTL_Q_SQ_CMD_TIMEOUT; - do { - if (ice_sq_done(hw, cq)) - break; - - usleep_range(100, 150); - } while (time_before(jiffies, timeout)); - - /* if ready, copy the desc back to temp */ if (ice_sq_done(hw, cq)) { memcpy(desc, desc_on_ring, sizeof(*desc)); if (buf) { @@ -1102,12 +1119,11 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, ice_debug(hw, ICE_DBG_AQ_MSG, "ATQ: desc and buffer writeback:\n"); - ice_debug_cq(hw, (void *)desc, buf, buf_size); + ice_debug_cq(hw, cq, (void *)desc, buf, buf_size, true); /* save writeback AQ if requested */ - if (details->wb_desc) - memcpy(details->wb_desc, desc_on_ring, - sizeof(*details->wb_desc)); + if (cd && cd->wb_desc) + memcpy(cd->wb_desc, desc_on_ring, sizeof(*cd->wb_desc)); /* update the error if time out occurred */ if (!cmd_completed) { @@ -1148,9 +1164,9 @@ void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode) * @e: event info from the receive descriptor, includes any buffers * @pending: number of events that could be left to process * - * This function cleans one Admin Receive Queue element and returns - * the contents through e. It can also return how many events are - * left to process through 'pending'. + * Clean one element from the receive side of a control queue. On return 'e' + * contains contents of the message, and 'pending' contains the number of + * events left to process. */ int ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq, @@ -1206,7 +1222,7 @@ ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq, ice_debug(hw, ICE_DBG_AQ_DESC, "ARQ: desc and buffer:\n"); - ice_debug_cq(hw, (void *)desc, e->msg_buf, cq->rq_buf_size); + ice_debug_cq(hw, cq, (void *)desc, e->msg_buf, cq->rq_buf_size, true); /* Restore the original datalen and buffer address in the desc, * FW updates datalen to indicate the event message size diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.h b/drivers/net/ethernet/intel/ice/ice_controlq.h index 8f2fd1613a95..ca97b7365a1b 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.h +++ b/drivers/net/ethernet/intel/ice/ice_controlq.h @@ -21,9 +21,18 @@ /* Defines that help manage the driver vs FW API checks. * Take a look at ice_aq_ver_check in ice_controlq.c for actual usage. */ -#define EXP_FW_API_VER_BRANCH 0x00 -#define EXP_FW_API_VER_MAJOR 0x01 -#define EXP_FW_API_VER_MINOR 0x05 +#define EXP_FW_API_VER_MAJOR_E810 0x01 +#define EXP_FW_API_VER_MINOR_E810 0x05 + +#define EXP_FW_API_VER_MAJOR_E830 0x01 +#define EXP_FW_API_VER_MINOR_E830 0x07 + +#define EXP_FW_API_VER_MAJOR_BY_MAC(hw) ((hw)->mac_type == ICE_MAC_E830 ? \ + EXP_FW_API_VER_MAJOR_E830 : \ + EXP_FW_API_VER_MAJOR_E810) +#define EXP_FW_API_VER_MINOR_BY_MAC(hw) ((hw)->mac_type == ICE_MAC_E830 ? \ + EXP_FW_API_VER_MINOR_E830 : \ + EXP_FW_API_VER_MINOR_E810) /* Different control queue types: These are mainly for SW consumption. */ enum ice_ctl_q { @@ -34,14 +43,13 @@ enum ice_ctl_q { }; /* Control Queue timeout settings - max delay 1s */ -#define ICE_CTL_Q_SQ_CMD_TIMEOUT HZ /* Wait max 1s */ +#define ICE_CTL_Q_SQ_CMD_TIMEOUT USEC_PER_SEC #define ICE_CTL_Q_ADMIN_INIT_TIMEOUT 10 /* Count 10 times */ #define ICE_CTL_Q_ADMIN_INIT_MSEC 100 /* Check every 100msec */ struct ice_ctl_q_ring { void *dma_head; /* Virtual address to DMA head */ struct ice_dma_mem desc_buf; /* descriptor ring memory */ - void *cmd_buf; /* command buffer memory */ union { struct ice_dma_mem *sq_bi; @@ -71,8 +79,6 @@ struct ice_sq_cd { struct ice_aq_desc *wb_desc; }; -#define ICE_CTL_Q_DETAILS(R, i) (&(((struct ice_sq_cd *)((R).cmd_buf))[i])) - /* rq event information */ struct ice_rq_event_info { struct ice_aq_desc desc; diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c index 74418c445cc4..64737fc62306 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb.c @@ -1288,7 +1288,7 @@ ice_add_dscp_up_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg) tlv->ouisubtype = htonl(ouisubtype); /* bytes 0 - 63 - IPv4 DSCP2UP LUT */ - for (i = 0; i < ICE_DSCP_NUM_VAL; i++) { + for (i = 0; i < DSCP_MAX; i++) { /* IPv4 mapping */ buf[i] = dcbcfg->dscp_map[i]; /* IPv6 mapping */ diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index 6e20ee610022..533eb8930aa8 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -3,7 +3,7 @@ #include "ice_dcb_lib.h" #include "ice_dcb_nl.h" -#include "ice_devlink.h" +#include "devlink/devlink.h" /** * ice_dcb_get_ena_tc - return bitmap of enabled TCs @@ -187,6 +187,7 @@ void ice_vsi_set_dcb_tc_cfg(struct ice_vsi *vsi) vsi->tc_cfg.numtc = ice_dcb_get_num_tc(cfg); break; case ICE_VSI_CHNL: + case ICE_VSI_SF: vsi->tc_cfg.ena_tc = BIT(ice_get_first_droptc(vsi)); vsi->tc_cfg.numtc = 1; break; @@ -291,7 +292,6 @@ static void ice_dcb_ena_dis_vsi(struct ice_pf *pf, bool ena, bool locked) switch (vsi->type) { case ICE_VSI_CHNL: - case ICE_VSI_SWITCHDEV_CTRL: case ICE_VSI_PF: if (ena) ice_ena_vsi(vsi, locked); @@ -352,8 +352,8 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked) struct ice_aqc_port_ets_elem buf = { 0 }; struct ice_dcbx_cfg *old_cfg, *curr_cfg; struct device *dev = ice_pf_to_dev(pf); + struct iidc_rdma_event *event; int ret = ICE_DCB_NO_HW_CHG; - struct iidc_event *event; struct ice_vsi *pf_vsi; curr_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; @@ -405,7 +405,7 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked) goto free_cfg; } - set_bit(IIDC_EVENT_BEFORE_TC_CHANGE, event->type); + set_bit(IIDC_RDMA_EVENT_BEFORE_TC_CHANGE, event->type); ice_send_event_to_aux(pf, event); kfree(event); @@ -740,7 +740,9 @@ static int ice_dcb_noncontig_cfg(struct ice_pf *pf) void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked) { struct ice_dcbx_cfg *dcbcfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; - struct iidc_event *event; + struct iidc_rdma_priv_dev_info *privd; + struct iidc_rdma_core_dev_info *cdev; + struct iidc_rdma_event *event; u8 tc_map = 0; int v, ret; @@ -776,21 +778,24 @@ void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked) /* no need to proceed with remaining cfg if it is CHNL * or switchdev VSI */ - if (vsi->type == ICE_VSI_CHNL || - vsi->type == ICE_VSI_SWITCHDEV_CTRL) + if (vsi->type == ICE_VSI_CHNL) continue; ice_vsi_map_rings_to_vectors(vsi); if (vsi->type == ICE_VSI_PF) ice_dcbnl_set_all(vsi); } - if (!locked) { + + cdev = pf->cdev_info; + if (cdev && !locked) { + privd = cdev->iidc_priv; + ice_setup_dcb_qos_info(pf, &privd->qos_info); /* Notify the AUX drivers that TC change is finished */ event = kzalloc(sizeof(*event), GFP_KERNEL); if (!event) return; - set_bit(IIDC_EVENT_AFTER_TC_CHANGE, event->type); + set_bit(IIDC_RDMA_EVENT_AFTER_TC_CHANGE, event->type); ice_send_event_to_aux(pf, event); kfree(event); } @@ -847,7 +852,7 @@ int ice_init_pf_dcb(struct ice_pf *pf, bool locked) goto dcb_init_err; } - ice_cfg_sw_lldp(pf_vsi, false, true); + ice_cfg_sw_rx_lldp(pf, true); pf->dcbx_cap = ice_dcb_get_mode(port_info, true); return 0; @@ -946,6 +951,37 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring, } /** + * ice_setup_dcb_qos_info - Setup DCB QoS information + * @pf: ptr to ice_pf + * @qos_info: QoS param instance + */ +void ice_setup_dcb_qos_info(struct ice_pf *pf, struct iidc_rdma_qos_params *qos_info) +{ + struct ice_dcbx_cfg *dcbx_cfg; + unsigned int i; + u32 up2tc; + + if (!pf || !qos_info) + return; + + dcbx_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; + up2tc = rd32(&pf->hw, PRTDCB_TUP2TC); + + qos_info->num_tc = ice_dcb_get_num_tc(dcbx_cfg); + + for (i = 0; i < IIDC_MAX_USER_PRIORITY; i++) + qos_info->up2tc[i] = (up2tc >> (i * 3)) & 0x7; + + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) + qos_info->tc_info[i].rel_bw = dcbx_cfg->etscfg.tcbwtable[i]; + + qos_info->pfc_mode = dcbx_cfg->pfc_mode; + if (qos_info->pfc_mode == IIDC_DSCP_PFC_MODE) + for (i = 0; i < DSCP_MAX; i++) + qos_info->dscp_map[i] = dcbx_cfg->dscp_map[i]; +} + +/** * ice_dcb_is_mib_change_pending - Check if MIB change is pending * @state: MIB change state */ diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h index 800879a88c5e..da9ba814b4e8 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h @@ -31,6 +31,9 @@ void ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first); void +ice_setup_dcb_qos_info(struct ice_pf *pf, + struct iidc_rdma_qos_params *qos_info); +void ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, struct ice_rq_event_info *event); /** @@ -134,5 +137,11 @@ static inline void ice_update_dcb_stats(struct ice_pf *pf) { } static inline void ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, struct ice_rq_event_info *event) { } static inline void ice_set_cgd_num(struct ice_tlan_ctx *tlan_ctx, u8 dcb_tc) { } +static inline void +ice_setup_dcb_qos_info(struct ice_pf *pf, struct iidc_rdma_qos_params *qos_info) +{ + qos_info->num_tc = 1; + qos_info->tc_info[0].rel_bw = 100; +} #endif /* CONFIG_DCB */ #endif /* _ICE_DCB_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c index 6d50b90a7359..a10c1c8d8697 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c @@ -754,7 +754,7 @@ static int ice_dcbnl_setapp(struct net_device *netdev, struct dcb_app *app) if (!ice_is_feature_supported(pf, ICE_F_DSCP)) return -EOPNOTSUPP; - if (app->protocol >= ICE_DSCP_NUM_VAL) { + if (app->protocol >= DSCP_MAX) { netdev_err(netdev, "DSCP value 0x%04X out of range\n", app->protocol); return -EINVAL; @@ -931,7 +931,7 @@ static int ice_dcbnl_delapp(struct net_device *netdev, struct dcb_app *app) /* if the last DSCP mapping just got deleted, need to switch * to L2 VLAN QoS mode */ - if (bitmap_empty(new_cfg->dscp_mapped, ICE_DSCP_NUM_VAL) && + if (bitmap_empty(new_cfg->dscp_mapped, DSCP_MAX) && new_cfg->pfc_mode == ICE_QOS_MODE_DSCP) { ret = ice_aq_set_pfc_mode(&pf->hw, ICE_AQC_PFC_VLAN_BASED_PFC, diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c index fc91c4d41186..59323c019544 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.c +++ b/drivers/net/ethernet/intel/ice/ice_ddp.c @@ -4,6 +4,7 @@ #include "ice_common.h" #include "ice.h" #include "ice_ddp.h" +#include "ice_sched.h" /* For supporting double VLAN mode, it is necessary to enable or disable certain * boost tcam entries. The metadata labels names that match the following @@ -30,7 +31,7 @@ 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. */ -static enum ice_ddp_state ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len) +static enum ice_ddp_state ice_verify_pkg(const struct ice_pkg_hdr *pkg, u32 len) { u32 seg_count; u32 i; @@ -56,13 +57,13 @@ static enum ice_ddp_state ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len) /* all segments must fit within length */ for (i = 0; i < seg_count; i++) { u32 off = le32_to_cpu(pkg->seg_offset[i]); - struct ice_generic_seg_hdr *seg; + const struct ice_generic_seg_hdr *seg; /* segment header must fit */ if (len < off + sizeof(*seg)) return ICE_DDP_PKG_INVALID_FILE; - seg = (struct ice_generic_seg_hdr *)((u8 *)pkg + off); + seg = (void *)pkg + off; /* segment body must fit */ if (len < off + le32_to_cpu(seg->seg_size)) @@ -118,13 +119,13 @@ static enum ice_ddp_state ice_chk_pkg_version(struct ice_pkg_ver *pkg_ver) * * This helper function validates a buffer's header. */ -static struct ice_buf_hdr *ice_pkg_val_buf(struct ice_buf *buf) +static const struct ice_buf_hdr *ice_pkg_val_buf(const struct ice_buf *buf) { - struct ice_buf_hdr *hdr; + const struct ice_buf_hdr *hdr; u16 section_count; u16 data_end; - hdr = (struct ice_buf_hdr *)buf->buf; + hdr = (const struct ice_buf_hdr *)buf->buf; /* verify data */ section_count = le16_to_cpu(hdr->section_count); if (section_count < ICE_MIN_S_COUNT || section_count > ICE_MAX_S_COUNT) @@ -164,8 +165,8 @@ static struct ice_buf_table *ice_find_buf_table(struct ice_seg *ice_seg) * unexpected value has been detected (for example an invalid section count or * an invalid buffer end value). */ -static struct ice_buf_hdr *ice_pkg_enum_buf(struct ice_seg *ice_seg, - struct ice_pkg_enum *state) +static const struct ice_buf_hdr *ice_pkg_enum_buf(struct ice_seg *ice_seg, + struct ice_pkg_enum *state) { if (ice_seg) { state->buf_table = ice_find_buf_table(ice_seg); @@ -288,11 +289,11 @@ void *ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state, * indicates a base offset of 10, and the index for the entry is 2, then * section handler function should set the offset to 10 + 2 = 12. */ -static void *ice_pkg_enum_entry(struct ice_seg *ice_seg, - struct ice_pkg_enum *state, u32 sect_type, - u32 *offset, - void *(*handler)(u32 sect_type, void *section, - u32 index, u32 *offset)) +void *ice_pkg_enum_entry(struct ice_seg *ice_seg, + struct ice_pkg_enum *state, u32 sect_type, + u32 *offset, + void *(*handler)(u32 sect_type, void *section, + u32 index, u32 *offset)) { void *entry; @@ -721,6 +722,12 @@ static bool ice_is_gtp_c_profile(u16 prof_idx) } } +static bool ice_is_pfcp_profile(u16 prof_idx) +{ + return prof_idx >= ICE_PROFID_IPV4_PFCP_NODE && + prof_idx <= ICE_PROFID_IPV6_PFCP_SESSION; +} + /** * ice_get_sw_prof_type - determine switch profile type * @hw: pointer to the HW structure @@ -738,6 +745,9 @@ static enum ice_prof_type ice_get_sw_prof_type(struct ice_hw *hw, if (ice_is_gtp_u_profile(prof_idx)) return ICE_PROF_TUN_GTPU; + if (ice_is_pfcp_profile(prof_idx)) + return ICE_PROF_TUN_PFCP; + for (i = 0; i < hw->blk[ICE_BLK_SW].es.fvw; i++) { /* UDP tunnel will have UDP_OF protocol ID and VNI offset */ if (fv->ew[i].prot_id == (u8)ICE_PROT_UDP_OF && @@ -1201,6 +1211,131 @@ ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, } /** + * ice_is_buffer_metadata - determine if package buffer is a metadata buffer + * @buf: pointer to buffer header + * Return: whether given @buf is a metadata one. + */ +static bool ice_is_buffer_metadata(struct ice_buf_hdr *buf) +{ + return le32_to_cpu(buf->section_entry[0].type) & ICE_METADATA_BUF; +} + +/** + * struct ice_ddp_send_ctx - sending context of current DDP segment + * @hw: pointer to the hardware struct + * + * Keeps current sending state (header, error) for the purpose of proper "last" + * bit setting in ice_aq_download_pkg(). Use via calls to ice_ddp_send_hunk(). + */ +struct ice_ddp_send_ctx { + struct ice_hw *hw; +/* private: only for ice_ddp_send_hunk() */ + struct ice_buf_hdr *hdr; + int err; +}; + +static void ice_ddp_send_ctx_set_err(struct ice_ddp_send_ctx *ctx, int err) +{ + ctx->err = err; +} + +/** + * ice_ddp_send_hunk - send one hunk of data to FW + * @ctx: current segment sending context + * @hunk: next hunk to send, size is always ICE_PKG_BUF_SIZE + * + * Send the next hunk of data to FW, retrying if needed. + * + * Notice: must be called once more with a NULL @hunk to finish up; such call + * will set up the "last" bit of an AQ request. After such call @ctx.hdr is + * cleared, @hw is still valid. + * + * Return: %ICE_DDP_PKG_SUCCESS if there were no problems; a sticky @err + * otherwise. + */ +static enum ice_ddp_state ice_ddp_send_hunk(struct ice_ddp_send_ctx *ctx, + struct ice_buf_hdr *hunk) +{ + struct ice_buf_hdr *prev_hunk = ctx->hdr; + struct ice_hw *hw = ctx->hw; + bool prev_was_last = !hunk; + enum ice_aq_err aq_err; + u32 offset, info; + int attempt, err; + + if (ctx->err) + return ctx->err; + + ctx->hdr = hunk; + if (!prev_hunk) + return ICE_DDP_PKG_SUCCESS; /* no problem so far */ + + for (attempt = 0; attempt < 5; attempt++) { + if (attempt) + msleep(20); + + err = ice_aq_download_pkg(hw, prev_hunk, ICE_PKG_BUF_SIZE, + prev_was_last, &offset, &info, NULL); + + aq_err = hw->adminq.sq_last_status; + if (aq_err != ICE_AQ_RC_ENOSEC && aq_err != ICE_AQ_RC_EBADSIG) + break; + } + + if (err) { + ice_debug(hw, ICE_DBG_PKG, "Pkg download failed: err %d off %d inf %d\n", + err, offset, info); + ctx->err = ice_map_aq_err_to_ddp_state(aq_err); + } else if (attempt) { + dev_dbg(ice_hw_to_dev(hw), + "ice_aq_download_pkg number of retries: %d\n", attempt); + } + + return ctx->err; +} + +/** + * ice_dwnld_cfg_bufs_no_lock + * @ctx: context of the current buffers section to send + * @bufs: pointer to an array of buffers + * @start: buffer index of first buffer to download + * @count: the number of buffers to download + * + * 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_no_lock(struct ice_ddp_send_ctx *ctx, struct ice_buf *bufs, + u32 start, u32 count) +{ + struct ice_buf_hdr *bh; + enum ice_ddp_state err; + + if (!bufs || !count) { + ice_ddp_send_ctx_set_err(ctx, ICE_DDP_PKG_ERR); + return ICE_DDP_PKG_ERR; + } + + bufs += start; + + for (int i = 0; i < count; i++, bufs++) { + bh = (struct ice_buf_hdr *)bufs; + /* Metadata buffers should not be sent to FW, + * their presence means "we are done here". + */ + if (ice_is_buffer_metadata(bh)) + break; + + err = ice_ddp_send_hunk(ctx, bh); + if (err) + return err; + } + + return 0; +} + +/** * ice_get_pkg_seg_by_idx * @pkg_hdr: pointer to the package header to be searched * @idx: index of segment @@ -1260,117 +1395,20 @@ ice_is_signing_seg_type_at_idx(struct ice_pkg_hdr *pkg_hdr, u32 idx, } /** - * 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 - * @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 - * - * 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_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; - - if (!bufs || !count) - return ICE_DDP_PKG_ERR; - - /* 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 + start); - if (le32_to_cpu(bh->section_entry[0].type) & ICE_METADATA_BUF) - return ICE_DDP_PKG_SUCCESS; - - for (i = 0; i < count; i++) { - bool last = false; - int status; - - bh = (struct ice_buf_hdr *)(bufs + start + 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", - status, offset, info); - err = hw->adminq.sq_last_status; - state = ice_map_aq_err_to_ddp_state(err); - break; - } - - if (last) - break; - } - - return state; -} - -/** * ice_download_pkg_sig_seg - download a signature segment - * @hw: pointer to the hardware structure + * @ctx: context of the current buffers section to send * @seg: pointer to signature segment */ static enum ice_ddp_state -ice_download_pkg_sig_seg(struct ice_hw *hw, struct ice_sign_seg *seg) +ice_download_pkg_sig_seg(struct ice_ddp_send_ctx *ctx, 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); + return ice_dwnld_cfg_bufs_no_lock(ctx, seg->buf_tbl.buf_array, 0, + le32_to_cpu(seg->buf_tbl.buf_count)); } /** * ice_download_pkg_config_seg - download a config segment - * @hw: pointer to the hardware structure + * @ctx: context of the current buffers section to send * @pkg_hdr: pointer to package header * @idx: segment index * @start: starting buffer @@ -1379,8 +1417,9 @@ ice_download_pkg_sig_seg(struct ice_hw *hw, struct ice_sign_seg *seg) * 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) +ice_download_pkg_config_seg(struct ice_ddp_send_ctx *ctx, + struct ice_pkg_hdr *pkg_hdr, u32 idx, u32 start, + u32 count) { struct ice_buf_table *bufs; struct ice_seg *seg; @@ -1396,46 +1435,56 @@ ice_download_pkg_config_seg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr, 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); + return ice_dwnld_cfg_bufs_no_lock(ctx, bufs->buf_array, start, count); +} + +static bool ice_is_last_sign_seg(u32 flags) +{ + return !(flags & ICE_SIGN_SEG_FLAGS_VALID) || /* behavior prior to valid */ + (flags & ICE_SIGN_SEG_FLAGS_LAST); } /** * ice_dwnld_sign_and_cfg_segs - download a signing segment and config segment - * @hw: pointer to the hardware structure + * @ctx: context of the current buffers section to send * @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) +ice_dwnld_sign_and_cfg_segs(struct ice_ddp_send_ctx *ctx, + struct ice_pkg_hdr *pkg_hdr, u32 idx) { + u32 conf_idx, start, count, flags; 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; + ice_ddp_send_ctx_set_err(ctx, state); + return state; } - 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(ctx, seg); + if (state || !count) + return state; - state = ice_download_pkg_sig_seg(hw, seg); - if (state) - goto exit; + conf_idx = le32_to_cpu(seg->signed_seg_idx); + start = le32_to_cpu(seg->signed_buf_start); - state = ice_download_pkg_config_seg(hw, pkg_hdr, conf_idx, start, + state = ice_download_pkg_config_seg(ctx, pkg_hdr, conf_idx, start, count); -exit: + /* finish up by sending last hunk with "last" flag set if requested by + * DDP content + */ + flags = le32_to_cpu(seg->flags); + if (ice_is_last_sign_seg(flags)) + state = ice_ddp_send_hunk(ctx, NULL); + return state; } @@ -1490,6 +1539,7 @@ 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; + struct ice_ddp_send_ctx ctx = { .hw = hw }; int status; u32 i; @@ -1510,7 +1560,7 @@ ice_download_pkg_with_sig_seg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr) hw->pkg_sign_type)) continue; - state = ice_dwnld_sign_and_cfg_segs(hw, pkg_hdr, i); + state = ice_dwnld_sign_and_cfg_segs(&ctx, pkg_hdr, i); if (state) break; } @@ -1535,6 +1585,7 @@ ice_download_pkg_with_sig_seg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr) static enum ice_ddp_state ice_dwnld_cfg_bufs(struct ice_hw *hw, struct ice_buf *bufs, u32 count) { + struct ice_ddp_send_ctx ctx = { .hw = hw }; enum ice_ddp_state state; struct ice_buf_hdr *bh; int status; @@ -1547,7 +1598,7 @@ ice_dwnld_cfg_bufs(struct ice_hw *hw, struct ice_buf *bufs, u32 count) * considered a success. */ bh = (struct ice_buf_hdr *)bufs; - if (le32_to_cpu(bh->section_entry[0].type) & ICE_METADATA_BUF) + if (ice_is_buffer_metadata(bh)) return ICE_DDP_PKG_SUCCESS; status = ice_acquire_global_cfg_lock(hw, ICE_RES_WRITE); @@ -1557,7 +1608,9 @@ ice_dwnld_cfg_bufs(struct ice_hw *hw, struct ice_buf *bufs, u32 count) 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); + ice_dwnld_cfg_bufs_no_lock(&ctx, bufs, 0, count); + /* finish up by sending last hunk with "last" flag set */ + state = ice_ddp_send_hunk(&ctx, NULL); if (!state) state = ice_post_dwnld_pkg_actions(hw); @@ -1771,9 +1824,9 @@ 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. */ -static struct ice_generic_seg_hdr * +static const struct ice_generic_seg_hdr * ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type, - struct ice_pkg_hdr *pkg_hdr) + const struct ice_pkg_hdr *pkg_hdr) { u32 i; @@ -1784,11 +1837,9 @@ ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type, /* Search all package segments for the requested segment type */ for (i = 0; i < le32_to_cpu(pkg_hdr->seg_count); i++) { - struct ice_generic_seg_hdr *seg; + const struct ice_generic_seg_hdr *seg; - seg = (struct ice_generic_seg_hdr - *)((u8 *)pkg_hdr + - le32_to_cpu(pkg_hdr->seg_offset[i])); + seg = (void *)pkg_hdr + le32_to_cpu(pkg_hdr->seg_offset[i]); if (le32_to_cpu(seg->seg_type) == seg_type) return seg; @@ -2263,3 +2314,211 @@ enum ice_ddp_state ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf, return state; } + +/** + * ice_get_set_tx_topo - get or set Tx topology + * @hw: pointer to the HW struct + * @buf: pointer to Tx topology buffer + * @buf_size: buffer size + * @cd: pointer to command details structure or NULL + * @flags: pointer to descriptor flags + * @set: 0-get, 1-set topology + * + * The function will get or set Tx topology + * + * Return: zero when set was successful, negative values otherwise. + */ +static int +ice_get_set_tx_topo(struct ice_hw *hw, u8 *buf, u16 buf_size, + struct ice_sq_cd *cd, u8 *flags, bool set) +{ + struct ice_aqc_get_set_tx_topo *cmd; + struct ice_aq_desc desc; + int status; + + cmd = &desc.params.get_set_tx_topo; + if (set) { + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_tx_topo); + cmd->set_flags = ICE_AQC_TX_TOPO_FLAGS_ISSUED; + /* requested to update a new topology, not a default topology */ + if (buf) + cmd->set_flags |= ICE_AQC_TX_TOPO_FLAGS_SRC_RAM | + ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW; + + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + } else { + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_tx_topo); + cmd->get_flags = ICE_AQC_TX_TOPO_GET_RAM; + + if (hw->mac_type == ICE_MAC_E810 || + hw->mac_type == ICE_MAC_GENERIC) + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + } + + status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd); + if (status) + return status; + /* read the return flag values (first byte) for get operation */ + if (!set && flags) + *flags = desc.params.get_set_tx_topo.set_flags; + + return 0; +} + +/** + * ice_cfg_tx_topo - Initialize new Tx topology if available + * @hw: pointer to the HW struct + * @buf: pointer to Tx topology buffer + * @len: buffer size + * + * The function will apply the new Tx topology from the package buffer + * if available. + * + * Return: zero when update was successful, negative values otherwise. + */ +int ice_cfg_tx_topo(struct ice_hw *hw, const void *buf, u32 len) +{ + u8 *new_topo = NULL, *topo __free(kfree) = NULL; + const struct ice_run_time_cfg_seg *seg; + const struct ice_buf_hdr *section; + const struct ice_pkg_hdr *pkg_hdr; + enum ice_ddp_state state; + u16 offset, size = 0; + u32 reg = 0; + int status; + u8 flags; + + if (!buf || !len) + return -EINVAL; + + /* Does FW support new Tx topology mode ? */ + if (!hw->func_caps.common_cap.tx_sched_topo_comp_mode_en) { + ice_debug(hw, ICE_DBG_INIT, "FW doesn't support compatibility mode\n"); + return -EOPNOTSUPP; + } + + topo = kzalloc(ICE_AQ_MAX_BUF_LEN, GFP_KERNEL); + if (!topo) + return -ENOMEM; + + /* Get the current Tx topology flags */ + status = ice_get_set_tx_topo(hw, topo, ICE_AQ_MAX_BUF_LEN, NULL, &flags, + false); + + if (status) { + ice_debug(hw, ICE_DBG_INIT, "Get current topology is failed\n"); + return status; + } + + /* Is default topology already applied ? */ + if (!(flags & ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW) && + hw->num_tx_sched_layers == ICE_SCHED_9_LAYERS) { + ice_debug(hw, ICE_DBG_INIT, "Default topology already applied\n"); + return -EEXIST; + } + + /* Is new topology already applied ? */ + if ((flags & ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW) && + hw->num_tx_sched_layers == ICE_SCHED_5_LAYERS) { + ice_debug(hw, ICE_DBG_INIT, "New topology already applied\n"); + return -EEXIST; + } + + /* Setting topology already issued? */ + if (flags & ICE_AQC_TX_TOPO_FLAGS_ISSUED) { + ice_debug(hw, ICE_DBG_INIT, "Update Tx topology was done by another PF\n"); + /* Add a small delay before exiting */ + msleep(2000); + return -EEXIST; + } + + /* Change the topology from new to default (5 to 9) */ + if (!(flags & ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW) && + hw->num_tx_sched_layers == ICE_SCHED_5_LAYERS) { + ice_debug(hw, ICE_DBG_INIT, "Change topology from 5 to 9 layers\n"); + goto update_topo; + } + + pkg_hdr = (const struct ice_pkg_hdr *)buf; + state = ice_verify_pkg(pkg_hdr, len); + if (state) { + ice_debug(hw, ICE_DBG_INIT, "Failed to verify pkg (err: %d)\n", + state); + return -EIO; + } + + /* Find runtime configuration segment */ + seg = (const struct ice_run_time_cfg_seg *) + ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE_RUN_TIME_CFG, pkg_hdr); + if (!seg) { + ice_debug(hw, ICE_DBG_INIT, "5 layer topology segment is missing\n"); + return -EIO; + } + + if (le32_to_cpu(seg->buf_table.buf_count) < ICE_MIN_S_COUNT) { + ice_debug(hw, ICE_DBG_INIT, "5 layer topology segment count(%d) is wrong\n", + seg->buf_table.buf_count); + return -EIO; + } + + section = ice_pkg_val_buf(seg->buf_table.buf_array); + if (!section || le32_to_cpu(section->section_entry[0].type) != + ICE_SID_TX_5_LAYER_TOPO) { + ice_debug(hw, ICE_DBG_INIT, "5 layer topology section type is wrong\n"); + return -EIO; + } + + size = le16_to_cpu(section->section_entry[0].size); + offset = le16_to_cpu(section->section_entry[0].offset); + if (size < ICE_MIN_S_SZ || size > ICE_MAX_S_SZ) { + ice_debug(hw, ICE_DBG_INIT, "5 layer topology section size is wrong\n"); + return -EIO; + } + + /* Make sure the section fits in the buffer */ + if (offset + size > ICE_PKG_BUF_SIZE) { + ice_debug(hw, ICE_DBG_INIT, "5 layer topology buffer > 4K\n"); + return -EIO; + } + + /* Get the new topology buffer, reuse current topo copy mem */ + static_assert(ICE_PKG_BUF_SIZE == ICE_AQ_MAX_BUF_LEN); + new_topo = topo; + memcpy(new_topo, (u8 *)section + offset, size); + +update_topo: + /* Acquire global lock to make sure that set topology issued + * by one PF. + */ + status = ice_acquire_res(hw, ICE_GLOBAL_CFG_LOCK_RES_ID, ICE_RES_WRITE, + ICE_GLOBAL_CFG_LOCK_TIMEOUT); + if (status) { + ice_debug(hw, ICE_DBG_INIT, "Failed to acquire global lock\n"); + return status; + } + + /* Check if reset was triggered already. */ + reg = rd32(hw, GLGEN_RSTAT); + if (reg & GLGEN_RSTAT_DEVSTATE_M) { + /* Reset is in progress, re-init the HW again */ + ice_debug(hw, ICE_DBG_INIT, "Reset is in progress. Layer topology might be applied already\n"); + ice_check_reset(hw); + return 0; + } + + /* Set new topology */ + status = ice_get_set_tx_topo(hw, new_topo, size, NULL, NULL, true); + if (status) { + ice_debug(hw, ICE_DBG_INIT, "Failed setting Tx topology\n"); + return status; + } + + /* New topology is updated, delay 1 second before issuing the CORER */ + msleep(1000); + ice_reset(hw, ICE_RESET_CORER); + /* CORER will clear the global lock, so no explicit call + * required for release. + */ + + return 0; +} diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.h b/drivers/net/ethernet/intel/ice/ice_ddp.h index ff66c2ffb1a2..8a2d57fc5dae 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.h +++ b/drivers/net/ethernet/intel/ice/ice_ddp.h @@ -181,7 +181,10 @@ struct ice_sign_seg { __le32 signed_seg_idx; __le32 signed_buf_start; __le32 signed_buf_count; -#define ICE_SIGN_SEG_RESERVED_COUNT 44 +#define ICE_SIGN_SEG_FLAGS_VALID 0x80000000 +#define ICE_SIGN_SEG_FLAGS_LAST 0x00000001 + __le32 flags; +#define ICE_SIGN_SEG_RESERVED_COUNT 40 u8 reserved[ICE_SIGN_SEG_RESERVED_COUNT]; struct ice_buf_table buf_tbl; }; @@ -261,10 +264,17 @@ struct ice_meta_sect { #define ICE_SID_CDID_KEY_BUILDER_RSS 47 #define ICE_SID_CDID_REDIR_RSS 48 +#define ICE_SID_RXPARSER_CAM 50 +#define ICE_SID_RXPARSER_NOMATCH_CAM 51 +#define ICE_SID_RXPARSER_IMEM 52 #define ICE_SID_RXPARSER_MARKER_PTYPE 55 #define ICE_SID_RXPARSER_BOOST_TCAM 56 +#define ICE_SID_RXPARSER_PROTO_GRP 57 #define ICE_SID_RXPARSER_METADATA_INIT 58 #define ICE_SID_TXPARSER_BOOST_TCAM 66 +#define ICE_SID_RXPARSER_MARKER_GRP 72 +#define ICE_SID_RXPARSER_PG_SPILL 76 +#define ICE_SID_RXPARSER_NOMATCH_SPILL 78 #define ICE_SID_XLT0_PE 80 #define ICE_SID_XLT_KEY_BUILDER_PE 81 @@ -276,6 +286,7 @@ struct ice_meta_sect { #define ICE_SID_CDID_KEY_BUILDER_PE 87 #define ICE_SID_CDID_REDIR_PE 88 +#define ICE_SID_RXPARSER_FLAG_REDIR 97 /* Label Metadata section IDs */ #define ICE_SID_LBL_FIRST 0x80000010 #define ICE_SID_LBL_RXPARSER_TMEM 0x80000018 @@ -430,7 +441,7 @@ struct ice_pkg_enum { u32 buf_idx; u32 type; - struct ice_buf_hdr *buf; + const struct ice_buf_hdr *buf; u32 sect_idx; void *sect; u32 sect_type; @@ -451,7 +462,14 @@ int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count); int ice_pkg_buf_reserve_section(struct ice_buf_build *bld, u16 count); u16 ice_pkg_buf_get_active_sections(struct ice_buf_build *bld); +void * +ice_pkg_enum_entry(struct ice_seg *ice_seg, struct ice_pkg_enum *state, + u32 sect_type, u32 *offset, + void *(*handler)(u32 sect_type, void *section, + u32 index, u32 *offset)); void *ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state, u32 sect_type); +int ice_cfg_tx_topo(struct ice_hw *hw, const void *buf, u32 len); + #endif diff --git a/drivers/net/ethernet/intel/ice/ice_devids.h b/drivers/net/ethernet/intel/ice/ice_devids.h index 9dfae9bce758..34fd604132f5 100644 --- a/drivers/net/ethernet/intel/ice/ice_devids.h +++ b/drivers/net/ethernet/intel/ice/ice_devids.h @@ -16,14 +16,26 @@ #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-CC for backplane */ +#define ICE_DEV_ID_E830CC_BACKPLANE 0x12D1 +/* Intel(R) Ethernet Controller E830-CC for QSFP */ +#define ICE_DEV_ID_E830CC_QSFP56 0x12D2 +/* Intel(R) Ethernet Controller E830-CC for SFP */ +#define ICE_DEV_ID_E830CC_SFP 0x12D3 +/* Intel(R) Ethernet Controller E830-CC for SFP-DD */ +#define ICE_DEV_ID_E830CC_SFP_DD 0x12D4 /* Intel(R) Ethernet Controller E830-C for backplane */ -#define ICE_DEV_ID_E830_BACKPLANE 0x12D1 +#define ICE_DEV_ID_E830C_BACKPLANE 0x12D5 /* Intel(R) Ethernet Controller E830-C for QSFP */ -#define ICE_DEV_ID_E830_QSFP56 0x12D2 +#define ICE_DEV_ID_E830C_QSFP 0x12D8 /* 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 +#define ICE_DEV_ID_E830C_SFP 0x12DA +/* Intel(R) Ethernet Controller E830-XXV for backplane */ +#define ICE_DEV_ID_E830_XXV_BACKPLANE 0x12DC +/* Intel(R) Ethernet Controller E830-XXV for QSFP */ +#define ICE_DEV_ID_E830_XXV_QSFP 0x12DD +/* Intel(R) Ethernet Controller E830-XXV for SFP */ +#define ICE_DEV_ID_E830_XXV_SFP 0x12DE /* 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 index e92be6f130a3..bce3ad6ca2a6 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -9,6 +9,8 @@ #define ICE_CGU_STATE_ACQ_ERR_THRESHOLD 50 #define ICE_DPLL_PIN_IDX_INVALID 0xff #define ICE_DPLL_RCLK_NUM_PER_PF 1 +#define ICE_DPLL_PIN_ESYNC_PULSE_HIGH_PERCENT 25 +#define ICE_DPLL_PIN_GEN_RCLK_FREQ 1953125 /** * enum ice_dpll_pin_type - enumerate ice pin types: @@ -30,6 +32,10 @@ static const char * const pin_type_name[] = { [ICE_DPLL_PIN_TYPE_RCLK_INPUT] = "rclk-input", }; +static const struct dpll_pin_frequency ice_esync_range[] = { + DPLL_PIN_FREQUENCY_RANGE(0, DPLL_PIN_FREQUENCY_1_HZ), +}; + /** * ice_dpll_is_reset - check if reset is in progress * @pf: private board structure @@ -89,7 +95,7 @@ ice_dpll_pin_freq_set(struct ice_pf *pf, struct ice_dpll_pin *pin, } if (ret) { NL_SET_ERR_MSG_FMT(extack, - "err:%d %s failed to set pin freq:%u on pin:%u\n", + "err:%d %s failed to set pin freq:%u on pin:%u", ret, ice_aq_str(pf->hw.adminq.sq_last_status), freq, pin->idx); @@ -316,7 +322,7 @@ ice_dpll_pin_enable(struct ice_hw *hw, struct ice_dpll_pin *pin, } if (ret) NL_SET_ERR_MSG_FMT(extack, - "err:%d %s failed to enable %s pin:%u\n", + "err:%d %s failed to enable %s pin:%u", ret, ice_aq_str(hw->adminq.sq_last_status), pin_type_name[pin_type], pin->idx); @@ -361,7 +367,7 @@ ice_dpll_pin_disable(struct ice_hw *hw, struct ice_dpll_pin *pin, } if (ret) NL_SET_ERR_MSG_FMT(extack, - "err:%d %s failed to disable %s pin:%u\n", + "err:%d %s failed to disable %s pin:%u", ret, ice_aq_str(hw->adminq.sq_last_status), pin_type_name[pin_type], pin->idx); @@ -394,8 +400,8 @@ ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin, 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], + ret = ice_aq_get_input_pin_cfg(&pf->hw, pin->idx, &pin->status, + NULL, NULL, &pin->flags[0], &pin->freq, &pin->phase_adjust); if (ret) goto err; @@ -430,7 +436,7 @@ ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin, goto err; parent &= ICE_AQC_GET_CGU_OUT_CFG_DPLL_SRC_SEL; - if (ICE_AQC_SET_CGU_OUT_CFG_OUT_EN & pin->flags[0]) { + if (ICE_AQC_GET_CGU_OUT_CFG_OUT_EN & pin->flags[0]) { pin->state[pf->dplls.eec.dpll_idx] = parent == pf->dplls.eec.dpll_idx ? DPLL_PIN_STATE_CONNECTED : @@ -473,7 +479,7 @@ ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin, err: if (extack) NL_SET_ERR_MSG_FMT(extack, - "err:%d %s failed to update %s pin:%u\n", + "err:%d %s failed to update %s pin:%u", ret, ice_aq_str(pf->hw.adminq.sq_last_status), pin_type_name[pin_type], pin->idx); @@ -512,7 +518,7 @@ ice_dpll_hw_input_prio_set(struct ice_pf *pf, struct ice_dpll *dpll, (u8)prio); if (ret) NL_SET_ERR_MSG_FMT(extack, - "err:%d %s failed to set pin prio:%u on pin:%u\n", + "err:%d %s failed to set pin prio:%u on pin:%u", ret, ice_aq_str(pf->hw.adminq.sq_last_status), prio, pin->idx); @@ -651,6 +657,8 @@ ice_dpll_output_state_set(const struct dpll_pin *pin, void *pin_priv, struct ice_dpll_pin *p = pin_priv; struct ice_dpll *d = dpll_priv; + if (state == DPLL_PIN_STATE_SELECTABLE) + return -EINVAL; if (!enable && p->state[d->dpll_idx] == DPLL_PIN_STATE_DISCONNECTED) return 0; @@ -996,7 +1004,7 @@ ice_dpll_pin_phase_adjust_set(const struct dpll_pin *pin, void *pin_priv, 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", + "err:%d %s failed to set pin phase_adjust:%d for pin:%u on dpll:%u", ret, ice_aq_str(pf->hw.adminq.sq_last_status), phase_adjust, p->idx, d->dpll_idx); @@ -1099,6 +1107,214 @@ ice_dpll_phase_offset_get(const struct dpll_pin *pin, void *pin_priv, } /** + * ice_dpll_output_esync_set - callback for setting embedded sync + * @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 + * @freq: requested embedded sync frequency + * @extack: error reporting + * + * Dpll subsystem callback. Handler for setting embedded sync frequency value + * on output pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_output_esync_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u64 freq, struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + u8 flags = 0; + int ret; + + if (ice_dpll_is_reset(pf, extack)) + return -EBUSY; + mutex_lock(&pf->dplls.lock); + if (p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_OUT_EN) + flags = ICE_AQC_SET_CGU_OUT_CFG_OUT_EN; + if (freq == DPLL_PIN_FREQUENCY_1_HZ) { + if (p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_EN) { + ret = 0; + } else { + flags |= ICE_AQC_SET_CGU_OUT_CFG_ESYNC_EN; + ret = ice_aq_set_output_pin_cfg(&pf->hw, p->idx, flags, + 0, 0, 0); + } + } else { + if (!(p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_EN)) { + ret = 0; + } else { + flags &= ~ICE_AQC_SET_CGU_OUT_CFG_ESYNC_EN; + ret = ice_aq_set_output_pin_cfg(&pf->hw, p->idx, flags, + 0, 0, 0); + } + } + mutex_unlock(&pf->dplls.lock); + + return ret; +} + +/** + * ice_dpll_output_esync_get - callback for getting embedded sync config + * @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 + * @esync: on success holds embedded sync pin properties + * @extack: error reporting + * + * Dpll subsystem callback. Handler for getting embedded sync frequency value + * and capabilities on output pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_output_esync_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + struct dpll_pin_esync *esync, + struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + + if (ice_dpll_is_reset(pf, extack)) + return -EBUSY; + mutex_lock(&pf->dplls.lock); + if (!(p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_ABILITY) || + p->freq != DPLL_PIN_FREQUENCY_10_MHZ) { + mutex_unlock(&pf->dplls.lock); + return -EOPNOTSUPP; + } + esync->range = ice_esync_range; + esync->range_num = ARRAY_SIZE(ice_esync_range); + if (p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_EN) { + esync->freq = DPLL_PIN_FREQUENCY_1_HZ; + esync->pulse = ICE_DPLL_PIN_ESYNC_PULSE_HIGH_PERCENT; + } else { + esync->freq = 0; + esync->pulse = 0; + } + mutex_unlock(&pf->dplls.lock); + + return 0; +} + +/** + * ice_dpll_input_esync_set - callback for setting embedded sync + * @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 + * @freq: requested embedded sync frequency + * @extack: error reporting + * + * Dpll subsystem callback. Handler for setting embedded sync frequency value + * on input pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_input_esync_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u64 freq, struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + u8 flags_en = 0; + int ret; + + if (ice_dpll_is_reset(pf, extack)) + return -EBUSY; + mutex_lock(&pf->dplls.lock); + if (p->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_INPUT_EN) + flags_en = ICE_AQC_SET_CGU_IN_CFG_FLG2_INPUT_EN; + if (freq == DPLL_PIN_FREQUENCY_1_HZ) { + if (p->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_ESYNC_EN) { + ret = 0; + } else { + flags_en |= ICE_AQC_SET_CGU_IN_CFG_FLG2_ESYNC_EN; + ret = ice_aq_set_input_pin_cfg(&pf->hw, p->idx, 0, + flags_en, 0, 0); + } + } else { + if (!(p->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_ESYNC_EN)) { + ret = 0; + } else { + flags_en &= ~ICE_AQC_SET_CGU_IN_CFG_FLG2_ESYNC_EN; + ret = ice_aq_set_input_pin_cfg(&pf->hw, p->idx, 0, + flags_en, 0, 0); + } + } + mutex_unlock(&pf->dplls.lock); + + return ret; +} + +/** + * ice_dpll_input_esync_get - callback for getting embedded sync config + * @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 + * @esync: on success holds embedded sync pin properties + * @extack: error reporting + * + * Dpll subsystem callback. Handler for getting embedded sync frequency value + * and capabilities on input pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_input_esync_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + struct dpll_pin_esync *esync, + struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + + if (ice_dpll_is_reset(pf, extack)) + return -EBUSY; + mutex_lock(&pf->dplls.lock); + if (!(p->status & ICE_AQC_GET_CGU_IN_CFG_STATUS_ESYNC_CAP) || + p->freq != DPLL_PIN_FREQUENCY_10_MHZ) { + mutex_unlock(&pf->dplls.lock); + return -EOPNOTSUPP; + } + esync->range = ice_esync_range; + esync->range_num = ARRAY_SIZE(ice_esync_range); + if (p->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_ESYNC_EN) { + esync->freq = DPLL_PIN_FREQUENCY_1_HZ; + esync->pulse = ICE_DPLL_PIN_ESYNC_PULSE_HIGH_PERCENT; + } else { + esync->freq = 0; + esync->pulse = 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 @@ -1146,7 +1362,7 @@ ice_dpll_rclk_state_on_pin_set(const struct dpll_pin *pin, void *pin_priv, &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", + "err:%d %s failed to set pin state:%u for pin:%u on parent:%u", ret, ice_aq_str(pf->hw.adminq.sq_last_status), state, p->idx, parent->idx); @@ -1222,6 +1438,8 @@ static const struct dpll_pin_ops ice_dpll_input_ops = { .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, + .esync_set = ice_dpll_input_esync_set, + .esync_get = ice_dpll_input_esync_get, }; static const struct dpll_pin_ops ice_dpll_output_ops = { @@ -1232,6 +1450,8 @@ static const struct dpll_pin_ops ice_dpll_output_ops = { .direction_get = ice_dpll_output_direction, .phase_adjust_get = ice_dpll_pin_phase_adjust_get, .phase_adjust_set = ice_dpll_output_phase_adjust_set, + .esync_set = ice_dpll_output_esync_set, + .esync_get = ice_dpll_output_esync_get, }; static const struct dpll_device_ops ice_dpll_ops = { @@ -1626,6 +1846,8 @@ ice_dpll_init_rclk_pins(struct ice_pf *pf, struct ice_dpll_pin *pin, struct dpll_pin *parent; int ret, i; + if (WARN_ON((!vsi || !vsi->netdev))) + return -EINVAL; ret = ice_dpll_get_pins(pf, pin, start_idx, ICE_DPLL_RCLK_NUM_PER_PF, pf->dplls.clock_id); if (ret) @@ -1641,8 +1863,6 @@ ice_dpll_init_rclk_pins(struct ice_pf *pf, struct ice_dpll_pin *pin, if (ret) goto unregister_pins; } - if (WARN_ON((!vsi || !vsi->netdev))) - return -EINVAL; dpll_netdev_pin_set(vsi->netdev, pf->dplls.rclk.pin); return 0; @@ -1833,7 +2053,7 @@ static int ice_dpll_init_worker(struct ice_pf *pf) struct kthread_worker *kworker; kthread_init_delayed_work(&d->work, ice_dpll_periodic_work); - kworker = kthread_create_worker(0, "ice-dplls-%s", + kworker = kthread_run_worker(0, "ice-dplls-%s", dev_name(ice_pf_to_dev(pf))); if (IS_ERR(kworker)) return PTR_ERR(kworker); @@ -1845,6 +2065,85 @@ static int ice_dpll_init_worker(struct ice_pf *pf) } /** + * ice_dpll_phase_range_set - initialize phase adjust range helper + * @range: pointer to phase adjust range struct to be initialized + * @phase_adj: a value to be used as min(-)/max(+) boundary + */ +static void ice_dpll_phase_range_set(struct dpll_pin_phase_adjust_range *range, + u32 phase_adj) +{ + range->min = -phase_adj; + range->max = phase_adj; +} + +/** + * ice_dpll_init_info_pins_generic - initializes generic pins info + * @pf: board private structure + * @input: if input pins initialized + * + * Init information for generic pins, cache them in PF's pins structures. + * + * Return: + * * 0 - success + * * negative - init failure reason + */ +static int ice_dpll_init_info_pins_generic(struct ice_pf *pf, bool input) +{ + struct ice_dpll *de = &pf->dplls.eec, *dp = &pf->dplls.pps; + static const char labels[][sizeof("99")] = { + "0", "1", "2", "3", "4", "5", "6", "7", "8", + "9", "10", "11", "12", "13", "14", "15" }; + u32 cap = DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE; + enum ice_dpll_pin_type pin_type; + int i, pin_num, ret = -EINVAL; + struct ice_dpll_pin *pins; + u32 phase_adj_max; + + if (input) { + pin_num = pf->dplls.num_inputs; + pins = pf->dplls.inputs; + phase_adj_max = pf->dplls.input_phase_adj_max; + pin_type = ICE_DPLL_PIN_TYPE_INPUT; + cap |= DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE; + } else { + pin_num = pf->dplls.num_outputs; + pins = pf->dplls.outputs; + phase_adj_max = pf->dplls.output_phase_adj_max; + pin_type = ICE_DPLL_PIN_TYPE_OUTPUT; + } + if (pin_num > ARRAY_SIZE(labels)) + return ret; + + for (i = 0; i < pin_num; i++) { + pins[i].idx = i; + pins[i].prop.board_label = labels[i]; + ice_dpll_phase_range_set(&pins[i].prop.phase_range, + phase_adj_max); + pins[i].prop.capabilities = cap; + pins[i].pf = pf; + ret = ice_dpll_pin_state_update(pf, &pins[i], pin_type, NULL); + if (ret) + break; + if (input && pins[i].freq == ICE_DPLL_PIN_GEN_RCLK_FREQ) + pins[i].prop.type = DPLL_PIN_TYPE_MUX; + else + pins[i].prop.type = DPLL_PIN_TYPE_EXT; + if (!input) + continue; + ret = ice_aq_get_cgu_ref_prio(&pf->hw, de->dpll_idx, i, + &de->input_prio[i]); + if (ret) + break; + ret = ice_aq_get_cgu_ref_prio(&pf->hw, dp->dpll_idx, i, + &dp->input_prio[i]); + if (ret) + break; + } + + return ret; +} + +/** * ice_dpll_init_info_direct_pins - initializes direct pins info * @pf: board private structure * @pin_type: type of pins being initialized @@ -1865,6 +2164,7 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf, struct ice_hw *hw = &pf->hw; struct ice_dpll_pin *pins; unsigned long caps; + u32 phase_adj_max; u8 freq_supp_num; bool input; @@ -1872,16 +2172,20 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf, case ICE_DPLL_PIN_TYPE_INPUT: pins = pf->dplls.inputs; num_pins = pf->dplls.num_inputs; + phase_adj_max = pf->dplls.input_phase_adj_max; input = true; break; case ICE_DPLL_PIN_TYPE_OUTPUT: pins = pf->dplls.outputs; num_pins = pf->dplls.num_outputs; + phase_adj_max = pf->dplls.output_phase_adj_max; input = false; break; default: return -EINVAL; } + if (num_pins != ice_cgu_get_num_pins(hw, input)) + return ice_dpll_init_info_pins_generic(pf, input); for (i = 0; i < num_pins; i++) { caps = 0; @@ -1899,19 +2203,13 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf, 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; } + ice_dpll_phase_range_set(&pins[i].prop.phase_range, + phase_adj_max); pins[i].prop.capabilities = caps; ret = ice_dpll_pin_state_update(pf, &pins[i], pin_type, NULL); if (ret) @@ -2019,8 +2317,10 @@ static int ice_dpll_init_info(struct ice_pf *pf, bool cgu) 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); + d->input_phase_adj_max = le32_to_cpu(abilities.max_in_phase_adj) & + ICE_AQC_GET_CGU_MAX_PHASE_ADJ; + d->output_phase_adj_max = le32_to_cpu(abilities.max_out_phase_adj) & + ICE_AQC_GET_CGU_MAX_PHASE_ADJ; alloc_size = sizeof(*d->inputs) * d->num_inputs; d->inputs = kzalloc(alloc_size, GFP_KERNEL); diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.h b/drivers/net/ethernet/intel/ice/ice_dpll.h index 93172e93995b..c320f1bf7d6d 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.h +++ b/drivers/net/ethernet/intel/ice/ice_dpll.h @@ -31,6 +31,7 @@ struct ice_dpll_pin { struct dpll_pin_properties prop; u32 freq; s32 phase_adjust; + u8 status; }; /** ice_dpll - store info required for DPLL control diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index 9069725c71b4..6aae03771746 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -7,89 +7,10 @@ #include "ice_eswitch_br.h" #include "ice_fltr.h" #include "ice_repr.h" -#include "ice_devlink.h" +#include "devlink/devlink.h" #include "ice_tc_lib.h" /** - * ice_eswitch_del_sp_rules - delete adv rules added on PRs - * @pf: pointer to the PF struct - * - * Delete all advanced rules that were used to forward packets with the - * device's VSI index to the corresponding eswitch ctrl VSI queue. - */ -static void ice_eswitch_del_sp_rules(struct ice_pf *pf) -{ - struct ice_repr *repr; - unsigned long id; - - xa_for_each(&pf->eswitch.reprs, id, repr) { - if (repr->sp_rule.rid) - ice_rem_adv_rule_by_id(&pf->hw, &repr->sp_rule); - } -} - -/** - * ice_eswitch_add_sp_rule - add adv rule with device's VSI index - * @pf: pointer to PF struct - * @repr: pointer to the repr struct - * - * This function adds advanced rule that forwards packets with - * device's VSI index to the corresponding eswitch ctrl VSI queue. - */ -static int ice_eswitch_add_sp_rule(struct ice_pf *pf, struct ice_repr *repr) -{ - struct ice_vsi *ctrl_vsi = pf->eswitch.control_vsi; - struct ice_adv_rule_info rule_info = { 0 }; - struct ice_adv_lkup_elem *list; - struct ice_hw *hw = &pf->hw; - const u16 lkups_cnt = 1; - int err; - - list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC); - if (!list) - return -ENOMEM; - - ice_rule_add_src_vsi_metadata(list); - - rule_info.sw_act.flag = ICE_FLTR_TX; - rule_info.sw_act.vsi_handle = ctrl_vsi->idx; - rule_info.sw_act.fltr_act = ICE_FWD_TO_Q; - rule_info.sw_act.fwd_id.q_id = hw->func_caps.common_cap.rxq_first_id + - ctrl_vsi->rxq_map[repr->q_id]; - rule_info.flags_info.act |= ICE_SINGLE_ACT_LB_ENABLE; - rule_info.flags_info.act_valid = true; - rule_info.tun_type = ICE_SW_TUN_AND_NON_TUN; - rule_info.src_vsi = repr->src_vsi->idx; - - err = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, - &repr->sp_rule); - if (err) - dev_err(ice_pf_to_dev(pf), "Unable to add slow-path rule for eswitch for PR %d", - repr->id); - - kfree(list); - return err; -} - -static int -ice_eswitch_add_sp_rules(struct ice_pf *pf) -{ - struct ice_repr *repr; - unsigned long id; - int err; - - xa_for_each(&pf->eswitch.reprs, id, repr) { - err = ice_eswitch_add_sp_rule(pf, repr); - if (err) { - ice_eswitch_del_sp_rules(pf); - return err; - } - } - - return 0; -} - -/** * ice_eswitch_setup_env - configure eswitch HW filters * @pf: pointer to PF struct * @@ -99,12 +20,16 @@ ice_eswitch_add_sp_rules(struct ice_pf *pf) static int ice_eswitch_setup_env(struct ice_pf *pf) { struct ice_vsi *uplink_vsi = pf->eswitch.uplink_vsi; - struct ice_vsi *ctrl_vsi = pf->eswitch.control_vsi; struct net_device *netdev = uplink_vsi->netdev; + bool if_running = netif_running(netdev); struct ice_vsi_vlan_ops *vlan_ops; - bool rule_added = false; + + if (if_running && !test_and_set_bit(ICE_VSI_DOWN, uplink_vsi->state)) + if (ice_down(uplink_vsi)) + return -ENODEV; ice_remove_vsi_fltr(&pf->hw, uplink_vsi->idx); + ice_vsi_cfg_sw_lldp(uplink_vsi, true, false); netif_addr_lock_bh(netdev); __dev_uc_unsync(netdev, NULL); @@ -112,98 +37,47 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) netif_addr_unlock_bh(netdev); if (ice_vsi_add_vlan_zero(uplink_vsi)) + goto err_vlan_zero; + + if (ice_set_dflt_vsi(uplink_vsi)) goto err_def_rx; - if (!ice_is_dflt_vsi_in_use(uplink_vsi->port_info)) { - if (ice_set_dflt_vsi(uplink_vsi)) - goto err_def_rx; - rule_added = true; - } + if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true, + ICE_FLTR_TX)) + goto err_def_tx; 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; + goto err_vlan_filtering; if (ice_vsi_update_local_lb(uplink_vsi, true)) goto err_override_local_lb; + if (if_running && ice_up(uplink_vsi)) + goto err_up; + return 0; +err_up: + ice_vsi_update_local_lb(uplink_vsi, false); 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_vlan_filtering: + ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false, + ICE_FLTR_TX); +err_def_tx: + ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false, + ICE_FLTR_RX); err_def_rx: + ice_vsi_del_vlan_zero(uplink_vsi); +err_vlan_zero: ice_fltr_add_mac_and_broadcast(uplink_vsi, uplink_vsi->port_info->mac.perm_addr, ICE_FWD_TO_VSI); - return -ENODEV; -} - -/** - * ice_eswitch_remap_rings_to_vectors - reconfigure rings of eswitch ctrl VSI - * @eswitch: pointer to eswitch struct - * - * In eswitch number of allocated Tx/Rx rings is equal. - * - * This function fills q_vectors structures associated with representor and - * move each ring pairs to port representor netdevs. Each port representor - * will have dedicated 1 Tx/Rx ring pair, so number of rings pair is equal to - * number of VFs. - */ -static void ice_eswitch_remap_rings_to_vectors(struct ice_eswitch *eswitch) -{ - struct ice_vsi *vsi = eswitch->control_vsi; - unsigned long repr_id = 0; - int q_id; - - ice_for_each_txq(vsi, q_id) { - struct ice_q_vector *q_vector; - struct ice_tx_ring *tx_ring; - struct ice_rx_ring *rx_ring; - struct ice_repr *repr; - - repr = xa_find(&eswitch->reprs, &repr_id, U32_MAX, - XA_PRESENT); - if (!repr) - break; - - repr_id += 1; - repr->q_id = q_id; - q_vector = repr->q_vector; - tx_ring = vsi->tx_rings[q_id]; - rx_ring = vsi->rx_rings[q_id]; - - q_vector->vsi = vsi; - q_vector->reg_idx = vsi->q_vectors[0]->reg_idx; - - q_vector->num_ring_tx = 1; - q_vector->tx.tx_ring = tx_ring; - tx_ring->q_vector = q_vector; - tx_ring->next = NULL; - tx_ring->netdev = repr->netdev; - /* In switchdev mode, from OS stack perspective, there is only - * one queue for given netdev, so it needs to be indexed as 0. - */ - tx_ring->q_index = 0; + if (if_running) + ice_up(uplink_vsi); - q_vector->num_ring_rx = 1; - q_vector->rx.rx_ring = rx_ring; - rx_ring->q_vector = q_vector; - rx_ring->next = NULL; - rx_ring->netdev = repr->netdev; - } + return -ENODEV; } /** @@ -225,8 +99,6 @@ ice_eswitch_release_repr(struct ice_pf *pf, struct ice_repr *repr) repr->dst = NULL; ice_fltr_add_mac_and_broadcast(vsi, repr->parent_mac, ICE_FWD_TO_VSI); - - netif_napi_del(&repr->q_vector->napi); } /** @@ -236,43 +108,64 @@ ice_eswitch_release_repr(struct ice_pf *pf, struct ice_repr *repr) */ static int ice_eswitch_setup_repr(struct ice_pf *pf, struct ice_repr *repr) { - struct ice_vsi *ctrl_vsi = pf->eswitch.control_vsi; + struct ice_vsi *uplink_vsi = pf->eswitch.uplink_vsi; struct ice_vsi *vsi = repr->src_vsi; struct metadata_dst *dst; - ice_remove_vsi_fltr(&pf->hw, vsi->idx); repr->dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX, GFP_KERNEL); if (!repr->dst) - goto err_add_mac_fltr; + return -ENOMEM; - if (ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof)) - goto err_dst_free; + netif_keep_dst(uplink_vsi->netdev); - if (ice_vsi_add_vlan_zero(vsi)) - goto err_update_security; + dst = repr->dst; + dst->u.port_info.port_id = vsi->vsi_num; + dst->u.port_info.lower_dev = uplink_vsi->netdev; + + return 0; +} - netif_napi_add(repr->netdev, &repr->q_vector->napi, - ice_napi_poll); +/** + * ice_eswitch_cfg_vsi - configure VSI to work in slow-path + * @vsi: VSI structure of representee + * @mac: representee MAC + * + * Return: 0 on success, non-zero on error. + */ +int ice_eswitch_cfg_vsi(struct ice_vsi *vsi, const u8 *mac) +{ + int err; - netif_keep_dst(repr->netdev); + ice_remove_vsi_fltr(&vsi->back->hw, vsi->idx); - dst = repr->dst; - dst->u.port_info.port_id = vsi->vsi_num; - dst->u.port_info.lower_dev = repr->netdev; - ice_repr_set_traffic_vsi(repr, ctrl_vsi); + err = ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof); + if (err) + goto err_update_security; + + err = ice_vsi_add_vlan_zero(vsi); + if (err) + goto err_vlan_zero; return 0; -err_update_security: +err_vlan_zero: ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof); -err_dst_free: - metadata_dst_free(repr->dst); - repr->dst = NULL; -err_add_mac_fltr: - ice_fltr_add_mac_and_broadcast(vsi, repr->parent_mac, ICE_FWD_TO_VSI); +err_update_security: + ice_fltr_add_mac_and_broadcast(vsi, mac, ICE_FWD_TO_VSI); - return -ENODEV; + return err; +} + +/** + * ice_eswitch_decfg_vsi - unroll changes done to VSI for switchdev + * @vsi: VSI structure of representee + * @mac: representee MAC + */ +void ice_eswitch_decfg_vsi(struct ice_vsi *vsi, const u8 *mac) +{ + ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof); + ice_fltr_add_mac_and_broadcast(vsi, mac, ICE_FWD_TO_VSI); } /** @@ -280,16 +173,16 @@ err_add_mac_fltr: * @repr_id: representor ID * @vsi: VSI for which port representor is configured */ -void ice_eswitch_update_repr(unsigned long repr_id, struct ice_vsi *vsi) +void ice_eswitch_update_repr(unsigned long *repr_id, struct ice_vsi *vsi) { struct ice_pf *pf = vsi->back; struct ice_repr *repr; - int ret; + int err; if (!ice_is_switchdev_running(pf)) return; - repr = xa_load(&pf->eswitch.reprs, repr_id); + repr = xa_load(&pf->eswitch.reprs, *repr_id); if (!repr) return; @@ -299,12 +192,19 @@ void ice_eswitch_update_repr(unsigned long repr_id, struct ice_vsi *vsi) 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, repr->parent_mac, - ICE_FWD_TO_VSI); + err = ice_eswitch_cfg_vsi(vsi, repr->parent_mac); + if (err) dev_err(ice_pf_to_dev(pf), "Failed to update VSI of port representor %d", repr->id); + + /* The VSI number is different, reload the PR with new id */ + if (repr->id != vsi->vsi_num) { + xa_erase(&pf->eswitch.reprs, repr->id); + repr->id = vsi->vsi_num; + if (xa_insert(&pf->eswitch.reprs, repr->id, repr, GFP_KERNEL)) + dev_err(ice_pf_to_dev(pf), "Failed to reload port representor %d", + repr->id); + *repr_id = repr->id; } } @@ -318,27 +218,19 @@ void ice_eswitch_update_repr(unsigned long repr_id, struct ice_vsi *vsi) netdev_tx_t ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev) { - struct ice_netdev_priv *np; - struct ice_repr *repr; - struct ice_vsi *vsi; - - 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; + struct ice_repr *repr = ice_netdev_to_repr(netdev); + unsigned int len = skb->len; + int ret; - repr = ice_netdev_to_repr(netdev); skb_dst_drop(skb); dst_hold((struct dst_entry *)repr->dst); skb_dst_set(skb, (struct dst_entry *)repr->dst); - skb->queue_mapping = repr->q_id; + skb->dev = repr->dst->u.port_info.lower_dev; + + ret = dev_queue_xmit(skb); + ice_repr_inc_tx_stats(repr, len, ret); - return ice_start_xmit(skb, netdev); + return ret; } /** @@ -354,6 +246,10 @@ ice_eswitch_set_target_vsi(struct sk_buff *skb, u64 cd_cmd, dst_vsi; if (!dst) { + struct ethhdr *eth = (struct ethhdr *)skb_mac_header(skb); + + if (unlikely(eth->h_proto == htons(ETH_P_LLDP))) + return; cd_cmd = ICE_TX_CTX_DESC_SWTCH_UPLINK << ICE_TXD_CTX_QW1_CMD_S; off->cd_qw1 |= (cd_cmd | ICE_TX_DESC_DTYPE_CTX); } else { @@ -374,62 +270,20 @@ ice_eswitch_set_target_vsi(struct sk_buff *skb, static void ice_eswitch_release_env(struct ice_pf *pf) { struct ice_vsi *uplink_vsi = pf->eswitch.uplink_vsi; - struct ice_vsi *ctrl_vsi = pf->eswitch.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_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false, + ICE_FLTR_TX); + ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false, + ICE_FLTR_RX); ice_fltr_add_mac_and_broadcast(uplink_vsi, uplink_vsi->port_info->mac.perm_addr, ICE_FWD_TO_VSI); -} - -/** - * ice_eswitch_vsi_setup - configure eswitch control VSI - * @pf: pointer to PF structure - * @pi: pointer to port_info structure - */ -static struct ice_vsi * -ice_eswitch_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) -{ - struct ice_vsi_cfg_params params = {}; - - params.type = ICE_VSI_SWITCHDEV_CTRL; - params.pi = pi; - params.flags = ICE_VSI_FLAG_INIT; - - return ice_vsi_setup(pf, ¶ms); -} - -/** - * ice_eswitch_napi_enable - enable NAPI for all port representors - * @reprs: xarray of reprs - */ -static void ice_eswitch_napi_enable(struct xarray *reprs) -{ - struct ice_repr *repr; - unsigned long id; - - xa_for_each(reprs, id, repr) - napi_enable(&repr->q_vector->napi); -} - -/** - * ice_eswitch_napi_disable - disable NAPI for all port representors - * @reprs: xarray of reprs - */ -static void ice_eswitch_napi_disable(struct xarray *reprs) -{ - struct ice_repr *repr; - unsigned long id; - - xa_for_each(reprs, id, repr) - napi_disable(&repr->q_vector->napi); + ice_vsi_cfg_sw_lldp(uplink_vsi, true, true); } /** @@ -438,7 +292,7 @@ static void ice_eswitch_napi_disable(struct xarray *reprs) */ static int ice_eswitch_enable_switchdev(struct ice_pf *pf) { - struct ice_vsi *ctrl_vsi, *uplink_vsi; + struct ice_vsi *uplink_vsi; uplink_vsi = ice_get_main_vsi(pf); if (!uplink_vsi) @@ -450,17 +304,10 @@ static int ice_eswitch_enable_switchdev(struct ice_pf *pf) return -EINVAL; } - pf->eswitch.control_vsi = ice_eswitch_vsi_setup(pf, pf->hw.port_info); - if (!pf->eswitch.control_vsi) - return -ENODEV; - - ctrl_vsi = pf->eswitch.control_vsi; - /* cp VSI is createad with 1 queue as default */ - pf->eswitch.qs.value = 1; pf->eswitch.uplink_vsi = uplink_vsi; if (ice_eswitch_setup_env(pf)) - goto err_vsi; + return -ENODEV; if (ice_eswitch_br_offloads_init(pf)) goto err_br_offloads; @@ -471,8 +318,6 @@ static int ice_eswitch_enable_switchdev(struct ice_pf *pf) err_br_offloads: ice_eswitch_release_env(pf); -err_vsi: - ice_vsi_release(ctrl_vsi); return -ENODEV; } @@ -482,14 +327,10 @@ err_vsi: */ static void ice_eswitch_disable_switchdev(struct ice_pf *pf) { - struct ice_vsi *ctrl_vsi = pf->eswitch.control_vsi; - ice_eswitch_br_offloads_deinit(pf); ice_eswitch_release_env(pf); - ice_vsi_release(ctrl_vsi); pf->eswitch.is_running = false; - pf->eswitch.qs.is_reaching = false; } /** @@ -530,7 +371,7 @@ ice_eswitch_mode_set(struct devlink *devlink, u16 mode, dev_info(ice_pf_to_dev(pf), "PF %d changed eswitch mode to switchdev", pf->hw.pf_id); - xa_init_flags(&pf->eswitch.reprs, XA_FLAGS_ALLOC); + xa_init(&pf->eswitch.reprs); NL_SET_ERR_MSG_MOD(extack, "Changed eswitch mode to switchdev"); break; } @@ -602,56 +443,17 @@ void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf) static void ice_eswitch_stop_reprs(struct ice_pf *pf) { - ice_eswitch_del_sp_rules(pf); ice_eswitch_stop_all_tx_queues(pf); - ice_eswitch_napi_disable(&pf->eswitch.reprs); } static void ice_eswitch_start_reprs(struct ice_pf *pf) { - ice_eswitch_napi_enable(&pf->eswitch.reprs); ice_eswitch_start_all_tx_queues(pf); - ice_eswitch_add_sp_rules(pf); -} - -static void -ice_eswitch_cp_change_queues(struct ice_eswitch *eswitch, int change) -{ - struct ice_vsi *cp = eswitch->control_vsi; - int queues = 0; - - if (eswitch->qs.is_reaching) { - if (eswitch->qs.to_reach >= eswitch->qs.value + change) { - queues = eswitch->qs.to_reach; - eswitch->qs.is_reaching = false; - } else { - queues = 0; - } - } else if ((change > 0 && cp->alloc_txq <= eswitch->qs.value) || - change < 0) { - queues = cp->alloc_txq + change; - } - - if (queues) { - cp->req_txq = queues; - cp->req_rxq = queues; - ice_vsi_close(cp); - ice_vsi_rebuild(cp, ICE_VSI_FLAG_NO_INIT); - ice_vsi_open(cp); - } else if (!change) { - /* change == 0 means that VSI wasn't open, open it here */ - ice_vsi_open(cp); - } - - eswitch->qs.value += change; - ice_eswitch_remap_rings_to_vectors(eswitch); } -int -ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf) +static int +ice_eswitch_attach(struct ice_pf *pf, struct ice_repr *repr, unsigned long *id) { - struct ice_repr *repr; - int change = 1; int err; if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_LEGACY) @@ -661,31 +463,24 @@ ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf) err = ice_eswitch_enable_switchdev(pf); if (err) return err; - /* Control plane VSI is created with 1 queue as default */ - pf->eswitch.qs.to_reach -= 1; - change = 0; } ice_eswitch_stop_reprs(pf); - repr = ice_repr_add_vf(vf); - if (IS_ERR(repr)) { - err = PTR_ERR(repr); + err = repr->ops.add(repr); + if (err) goto err_create_repr; - } err = ice_eswitch_setup_repr(pf, repr); if (err) goto err_setup_repr; - err = xa_alloc(&pf->eswitch.reprs, &repr->id, repr, - XA_LIMIT(1, INT_MAX), GFP_KERNEL); + err = xa_insert(&pf->eswitch.reprs, repr->id, repr, GFP_KERNEL); if (err) goto err_xa_alloc; - vf->repr_id = repr->id; + *id = repr->id; - ice_eswitch_cp_change_queues(&pf->eswitch, change); ice_eswitch_start_reprs(pf); return 0; @@ -693,7 +488,7 @@ ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf) err_xa_alloc: ice_eswitch_release_repr(pf, repr); err_setup_repr: - ice_repr_rem_vf(repr); + repr->ops.rem(repr); err_create_repr: if (xa_empty(&pf->eswitch.reprs)) ice_eswitch_disable_switchdev(pf); @@ -702,73 +497,135 @@ err_create_repr: return err; } -void ice_eswitch_detach(struct ice_pf *pf, struct ice_vf *vf) +/** + * ice_eswitch_attach_vf - attach VF to a eswitch + * @pf: pointer to PF structure + * @vf: pointer to VF structure to be attached + * + * During attaching port representor for VF is created. + * + * Return: zero on success or an error code on failure. + */ +int ice_eswitch_attach_vf(struct ice_pf *pf, struct ice_vf *vf) { - struct ice_repr *repr = xa_load(&pf->eswitch.reprs, vf->repr_id); + struct ice_repr *repr = ice_repr_create_vf(vf); struct devlink *devlink = priv_to_devlink(pf); + int err; - if (!repr) - return; + if (IS_ERR(repr)) + return PTR_ERR(repr); + + devl_lock(devlink); + err = ice_eswitch_attach(pf, repr, &vf->repr_id); + if (err) + ice_repr_destroy(repr); + devl_unlock(devlink); + + return err; +} +/** + * ice_eswitch_attach_sf - attach SF to a eswitch + * @pf: pointer to PF structure + * @sf: pointer to SF structure to be attached + * + * During attaching port representor for SF is created. + * + * Return: zero on success or an error code on failure. + */ +int ice_eswitch_attach_sf(struct ice_pf *pf, struct ice_dynamic_port *sf) +{ + struct ice_repr *repr = ice_repr_create_sf(sf); + int err; + + if (IS_ERR(repr)) + return PTR_ERR(repr); + + err = ice_eswitch_attach(pf, repr, &sf->repr_id); + if (err) + ice_repr_destroy(repr); + + return err; +} + +static void ice_eswitch_detach(struct ice_pf *pf, struct ice_repr *repr) +{ ice_eswitch_stop_reprs(pf); + repr->ops.rem(repr); + xa_erase(&pf->eswitch.reprs, repr->id); if (xa_empty(&pf->eswitch.reprs)) ice_eswitch_disable_switchdev(pf); - else - ice_eswitch_cp_change_queues(&pf->eswitch, -1); ice_eswitch_release_repr(pf, repr); - ice_repr_rem_vf(repr); + ice_repr_destroy(repr); if (xa_empty(&pf->eswitch.reprs)) { + struct devlink *devlink = priv_to_devlink(pf); + /* since all port representors are destroyed, there is * no point in keeping the nodes */ ice_devlink_rate_clear_tx_topology(ice_get_main_vsi(pf)); - devl_lock(devlink); devl_rate_nodes_destroy(devlink); - devl_unlock(devlink); } else { ice_eswitch_start_reprs(pf); } } /** - * ice_eswitch_rebuild - rebuild eswitch + * ice_eswitch_detach_vf - detach VF from a eswitch * @pf: pointer to PF structure + * @vf: pointer to VF structure to be detached */ -int ice_eswitch_rebuild(struct ice_pf *pf) +void ice_eswitch_detach_vf(struct ice_pf *pf, struct ice_vf *vf) { - struct ice_repr *repr; - unsigned long id; - int err; + struct ice_repr *repr = xa_load(&pf->eswitch.reprs, vf->repr_id); + struct devlink *devlink = priv_to_devlink(pf); - if (!ice_is_switchdev_running(pf)) - return 0; + if (!repr) + return; - err = ice_vsi_rebuild(pf->eswitch.control_vsi, ICE_VSI_FLAG_INIT); - if (err) - return err; + devl_lock(devlink); + ice_eswitch_detach(pf, repr); + devl_unlock(devlink); +} - xa_for_each(&pf->eswitch.reprs, id, repr) - ice_eswitch_detach(pf, repr->vf); +/** + * ice_eswitch_detach_sf - detach SF from a eswitch + * @pf: pointer to PF structure + * @sf: pointer to SF structure to be detached + */ +void ice_eswitch_detach_sf(struct ice_pf *pf, struct ice_dynamic_port *sf) +{ + struct ice_repr *repr = xa_load(&pf->eswitch.reprs, sf->repr_id); - return 0; + if (!repr) + return; + + ice_eswitch_detach(pf, repr); } /** - * ice_eswitch_reserve_cp_queues - reserve control plane VSI queues - * @pf: pointer to PF structure - * @change: how many more (or less) queues is needed + * ice_eswitch_get_target - get netdev based on src_vsi from descriptor + * @rx_ring: ring used to receive the packet + * @rx_desc: descriptor used to get src_vsi value * - * Remember to call ice_eswitch_attach/detach() the "change" times. + * Get src_vsi value from descriptor and load correct representor. If it isn't + * found return rx_ring->netdev. */ -void ice_eswitch_reserve_cp_queues(struct ice_pf *pf, int change) +struct net_device *ice_eswitch_get_target(struct ice_rx_ring *rx_ring, + union ice_32b_rx_flex_desc *rx_desc) { - if (pf->eswitch.qs.value + change < 0) - return; + struct ice_eswitch *eswitch = &rx_ring->vsi->back->eswitch; + struct ice_32b_rx_flex_desc_nic_2 *desc; + struct ice_repr *repr; + + desc = (struct ice_32b_rx_flex_desc_nic_2 *)rx_desc; + repr = xa_load(&eswitch->reprs, le16_to_cpu(desc->src_vsi)); + if (!repr) + return rx_ring->netdev; - pf->eswitch.qs.to_reach = pf->eswitch.qs.value + change; - pf->eswitch.qs.is_reaching = true; + return repr->netdev; } diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.h b/drivers/net/ethernet/intel/ice/ice_eswitch.h index 1a288a03a79a..5c7dcf21b222 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.h +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.h @@ -5,12 +5,13 @@ #define _ICE_ESWITCH_H_ #include <net/devlink.h> +#include "devlink/port.h" #ifdef CONFIG_ICE_SWITCHDEV -void ice_eswitch_detach(struct ice_pf *pf, struct ice_vf *vf); -int -ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf); -int ice_eswitch_rebuild(struct ice_pf *pf); +void ice_eswitch_detach_vf(struct ice_pf *pf, struct ice_vf *vf); +void ice_eswitch_detach_sf(struct ice_pf *pf, struct ice_dynamic_port *sf); +int ice_eswitch_attach_vf(struct ice_pf *pf, struct ice_vf *vf); +int ice_eswitch_attach_sf(struct ice_pf *pf, struct ice_dynamic_port *sf); int ice_eswitch_mode_get(struct devlink *devlink, u16 *mode); int @@ -18,7 +19,7 @@ ice_eswitch_mode_set(struct devlink *devlink, u16 mode, struct netlink_ext_ack *extack); bool ice_is_eswitch_mode_switchdev(struct ice_pf *pf); -void ice_eswitch_update_repr(unsigned long repr_id, struct ice_vsi *vsi); +void ice_eswitch_update_repr(unsigned long *repr_id, struct ice_vsi *vsi); void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf); @@ -26,12 +27,26 @@ void ice_eswitch_set_target_vsi(struct sk_buff *skb, struct ice_tx_offload_params *off); netdev_tx_t ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev); -void ice_eswitch_reserve_cp_queues(struct ice_pf *pf, int change); +struct net_device *ice_eswitch_get_target(struct ice_rx_ring *rx_ring, + union ice_32b_rx_flex_desc *rx_desc); + +int ice_eswitch_cfg_vsi(struct ice_vsi *vsi, const u8 *mac); +void ice_eswitch_decfg_vsi(struct ice_vsi *vsi, const u8 *mac); #else /* CONFIG_ICE_SWITCHDEV */ -static inline void ice_eswitch_detach(struct ice_pf *pf, struct ice_vf *vf) { } +static inline void +ice_eswitch_detach_vf(struct ice_pf *pf, struct ice_vf *vf) { } + +static inline void +ice_eswitch_detach_sf(struct ice_pf *pf, struct ice_dynamic_port *sf) { } static inline int -ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf) +ice_eswitch_attach_vf(struct ice_pf *pf, struct ice_vf *vf) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_eswitch_attach_sf(struct ice_pf *pf, struct ice_dynamic_port *sf) { return -EOPNOTSUPP; } @@ -43,17 +58,7 @@ ice_eswitch_set_target_vsi(struct sk_buff *skb, struct ice_tx_offload_params *off) { } static inline void -ice_eswitch_update_repr(unsigned long repr_id, struct ice_vsi *vsi) { } - -static inline int ice_eswitch_configure(struct ice_pf *pf) -{ - return 0; -} - -static inline int ice_eswitch_rebuild(struct ice_pf *pf) -{ - return -EOPNOTSUPP; -} +ice_eswitch_update_repr(unsigned long *repr_id, struct ice_vsi *vsi) { } static inline int ice_eswitch_mode_get(struct devlink *devlink, u16 *mode) { @@ -78,7 +83,18 @@ ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev) return NETDEV_TX_BUSY; } -static inline void -ice_eswitch_reserve_cp_queues(struct ice_pf *pf, int change) { } +static inline struct net_device * +ice_eswitch_get_target(struct ice_rx_ring *rx_ring, + union ice_32b_rx_flex_desc *rx_desc) +{ + return rx_ring->netdev; +} + +static inline int ice_eswitch_cfg_vsi(struct ice_vsi *vsi, const u8 *mac) +{ + return -EOPNOTSUPP; +} + +static inline void ice_eswitch_decfg_vsi(struct ice_vsi *vsi, const u8 *mac) { } #endif /* CONFIG_ICE_SWITCHDEV */ #endif /* _ICE_ESWITCH_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c index ac5beecd028b..cccb7ddf61c9 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c @@ -582,10 +582,13 @@ ice_eswitch_br_switchdev_event(struct notifier_block *nb, return NOTIFY_DONE; } -static void ice_eswitch_br_fdb_flush(struct ice_esw_br *bridge) +void ice_eswitch_br_fdb_flush(struct ice_esw_br *bridge) { struct ice_esw_br_fdb_entry *entry, *tmp; + if (!bridge) + return; + list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) ice_eswitch_br_fdb_entry_notify_and_cleanup(bridge, entry); } @@ -896,7 +899,8 @@ ice_eswitch_br_port_deinit(struct ice_esw_br *bridge, if (br_port->type == ICE_ESWITCH_BR_UPLINK_PORT && vsi->back) { vsi->back->br_port = NULL; } else { - struct ice_repr *repr = ice_repr_get_by_vsi(vsi); + struct ice_repr *repr = + ice_repr_get(vsi->back, br_port->repr_id); if (repr) repr->br_port = NULL; @@ -937,6 +941,7 @@ ice_eswitch_br_vf_repr_port_init(struct ice_esw_br *bridge, br_port->vsi = repr->src_vsi; br_port->vsi_idx = br_port->vsi->idx; br_port->type = ICE_ESWITCH_BR_VF_REPR_PORT; + br_port->repr_id = repr->id; repr->br_port = br_port; err = xa_insert(&bridge->ports, br_port->vsi_idx, br_port, GFP_KERNEL); diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.h b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h index 85a8fadb2928..66a2c804338f 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch_br.h +++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h @@ -46,6 +46,7 @@ struct ice_esw_br_port { enum ice_esw_br_port_type type; u16 vsi_idx; u16 pvid; + u32 repr_id; struct xarray vlans; }; @@ -116,5 +117,6 @@ void ice_eswitch_br_offloads_deinit(struct ice_pf *pf); int ice_eswitch_br_offloads_init(struct ice_pf *pf); +void ice_eswitch_br_fdb_flush(struct ice_esw_br *bridge); #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 78b833b3e1d7..bbf9e6fd315b 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -463,7 +463,331 @@ ice_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) static int ice_get_regs_len(struct net_device __always_unused *netdev) { - return sizeof(ice_regs_dump_list); + return (sizeof(ice_regs_dump_list) + + sizeof(struct ice_regdump_to_ethtool)); +} + +/** + * ice_ethtool_get_maxspeed - Get the max speed for given lport + * @hw: pointer to the HW struct + * @lport: logical port for which max speed is requested + * @max_speed: return max speed for input lport + * + * Return: 0 on success, negative on failure. + */ +static int ice_ethtool_get_maxspeed(struct ice_hw *hw, u8 lport, u8 *max_speed) +{ + struct ice_aqc_get_port_options_elem options[ICE_AQC_PORT_OPT_MAX] = {}; + bool active_valid = false, pending_valid = true; + u8 option_count = ICE_AQC_PORT_OPT_MAX; + u8 active_idx = 0, pending_idx = 0; + int status; + + status = ice_aq_get_port_options(hw, options, &option_count, lport, + true, &active_idx, &active_valid, + &pending_idx, &pending_valid); + if (status) + return -EIO; + if (!active_valid) + return -EINVAL; + + *max_speed = options[active_idx].max_lane_speed & ICE_AQC_PORT_OPT_MAX_LANE_M; + return 0; +} + +/** + * ice_is_serdes_muxed - returns whether serdes is muxed in hardware + * @hw: pointer to the HW struct + * + * Return: true when serdes is muxed, false when serdes is not muxed. + */ +static bool ice_is_serdes_muxed(struct ice_hw *hw) +{ + u32 reg_value = rd32(hw, GLGEN_SWITCH_MODE_CONFIG); + + return FIELD_GET(GLGEN_SWITCH_MODE_CONFIG_25X4_QUAD_M, reg_value); +} + +static int ice_map_port_topology_for_sfp(struct ice_port_topology *port_topology, + u8 lport, bool is_muxed) +{ + switch (lport) { + case 0: + port_topology->pcs_quad_select = 0; + port_topology->pcs_port = 0; + port_topology->primary_serdes_lane = 0; + break; + case 1: + port_topology->pcs_quad_select = 1; + port_topology->pcs_port = 0; + if (is_muxed) + port_topology->primary_serdes_lane = 2; + else + port_topology->primary_serdes_lane = 4; + break; + case 2: + port_topology->pcs_quad_select = 0; + port_topology->pcs_port = 1; + port_topology->primary_serdes_lane = 1; + break; + case 3: + port_topology->pcs_quad_select = 1; + port_topology->pcs_port = 1; + if (is_muxed) + port_topology->primary_serdes_lane = 3; + else + port_topology->primary_serdes_lane = 5; + break; + case 4: + port_topology->pcs_quad_select = 0; + port_topology->pcs_port = 2; + port_topology->primary_serdes_lane = 2; + break; + case 5: + port_topology->pcs_quad_select = 1; + port_topology->pcs_port = 2; + port_topology->primary_serdes_lane = 6; + break; + case 6: + port_topology->pcs_quad_select = 0; + port_topology->pcs_port = 3; + port_topology->primary_serdes_lane = 3; + break; + case 7: + port_topology->pcs_quad_select = 1; + port_topology->pcs_port = 3; + port_topology->primary_serdes_lane = 7; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int ice_map_port_topology_for_qsfp(struct ice_port_topology *port_topology, + u8 lport, bool is_muxed) +{ + switch (lport) { + case 0: + port_topology->pcs_quad_select = 0; + port_topology->pcs_port = 0; + port_topology->primary_serdes_lane = 0; + break; + case 1: + port_topology->pcs_quad_select = 1; + port_topology->pcs_port = 0; + if (is_muxed) + port_topology->primary_serdes_lane = 2; + else + port_topology->primary_serdes_lane = 4; + break; + case 2: + port_topology->pcs_quad_select = 0; + port_topology->pcs_port = 1; + port_topology->primary_serdes_lane = 1; + break; + case 3: + port_topology->pcs_quad_select = 1; + port_topology->pcs_port = 1; + if (is_muxed) + port_topology->primary_serdes_lane = 3; + else + port_topology->primary_serdes_lane = 5; + break; + case 4: + port_topology->pcs_quad_select = 0; + port_topology->pcs_port = 2; + port_topology->primary_serdes_lane = 2; + break; + case 5: + port_topology->pcs_quad_select = 1; + port_topology->pcs_port = 2; + port_topology->primary_serdes_lane = 6; + break; + case 6: + port_topology->pcs_quad_select = 0; + port_topology->pcs_port = 3; + port_topology->primary_serdes_lane = 3; + break; + case 7: + port_topology->pcs_quad_select = 1; + port_topology->pcs_port = 3; + port_topology->primary_serdes_lane = 7; + break; + default: + return -EINVAL; + } + + return 0; +} + +/** + * ice_get_port_topology - returns physical topology like pcsquad, pcsport, + * serdes number + * @hw: pointer to the HW struct + * @lport: logical port for which physical info requested + * @port_topology: buffer to hold port topology + * + * Return: 0 on success, negative on failure. + */ +static int ice_get_port_topology(struct ice_hw *hw, u8 lport, + struct ice_port_topology *port_topology) +{ + struct ice_aqc_get_link_topo cmd = {}; + u16 node_handle = 0; + u8 cage_type = 0; + bool is_muxed; + int err; + u8 ctx; + + ctx = ICE_AQC_LINK_TOPO_NODE_TYPE_CAGE << 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; + + err = ice_aq_get_netlist_node(hw, &cmd, &cage_type, &node_handle); + if (err) + return -EINVAL; + + is_muxed = ice_is_serdes_muxed(hw); + + if (cage_type == 0x11 || /* SFP+ */ + cage_type == 0x12) { /* SFP28 */ + port_topology->serdes_lane_count = 1; + err = ice_map_port_topology_for_sfp(port_topology, lport, is_muxed); + if (err) + return err; + } else if (cage_type == 0x13 || /* QSFP */ + cage_type == 0x14) { /* QSFP28 */ + u8 max_speed = 0; + + err = ice_ethtool_get_maxspeed(hw, lport, &max_speed); + if (err) + return err; + + if (max_speed == ICE_AQC_PORT_OPT_MAX_LANE_100G) + port_topology->serdes_lane_count = 4; + else if (max_speed == ICE_AQC_PORT_OPT_MAX_LANE_50G) + port_topology->serdes_lane_count = 2; + else + port_topology->serdes_lane_count = 1; + + err = ice_map_port_topology_for_qsfp(port_topology, lport, is_muxed); + if (err) + return err; + } else { + return -EINVAL; + } + + return 0; +} + +/** + * ice_get_tx_rx_equa - read serdes tx rx equaliser param + * @hw: pointer to the HW struct + * @serdes_num: represents the serdes number + * @ptr: structure to read all serdes parameter for given serdes + * + * Return: all serdes equalization parameter supported per serdes number + */ +static int ice_get_tx_rx_equa(struct ice_hw *hw, u8 serdes_num, + struct ice_serdes_equalization_to_ethtool *ptr) +{ + static const int tx = ICE_AQC_OP_CODE_TX_EQU; + static const int rx = ICE_AQC_OP_CODE_RX_EQU; + struct { + int data_in; + int opcode; + int *out; + } aq_params[] = { + { ICE_AQC_TX_EQU_PRE1, tx, &ptr->tx_equ_pre1 }, + { ICE_AQC_TX_EQU_PRE3, tx, &ptr->tx_equ_pre3 }, + { ICE_AQC_TX_EQU_ATTEN, tx, &ptr->tx_equ_atten }, + { ICE_AQC_TX_EQU_POST1, tx, &ptr->tx_equ_post1 }, + { ICE_AQC_TX_EQU_PRE2, tx, &ptr->tx_equ_pre2 }, + { ICE_AQC_RX_EQU_PRE2, rx, &ptr->rx_equ_pre2 }, + { ICE_AQC_RX_EQU_PRE1, rx, &ptr->rx_equ_pre1 }, + { ICE_AQC_RX_EQU_POST1, rx, &ptr->rx_equ_post1 }, + { ICE_AQC_RX_EQU_BFLF, rx, &ptr->rx_equ_bflf }, + { ICE_AQC_RX_EQU_BFHF, rx, &ptr->rx_equ_bfhf }, + { ICE_AQC_RX_EQU_CTLE_GAINHF, rx, &ptr->rx_equ_ctle_gainhf }, + { ICE_AQC_RX_EQU_CTLE_GAINLF, rx, &ptr->rx_equ_ctle_gainlf }, + { ICE_AQC_RX_EQU_CTLE_GAINDC, rx, &ptr->rx_equ_ctle_gaindc }, + { ICE_AQC_RX_EQU_CTLE_BW, rx, &ptr->rx_equ_ctle_bw }, + { ICE_AQC_RX_EQU_DFE_GAIN, rx, &ptr->rx_equ_dfe_gain }, + { ICE_AQC_RX_EQU_DFE_GAIN2, rx, &ptr->rx_equ_dfe_gain_2 }, + { ICE_AQC_RX_EQU_DFE_2, rx, &ptr->rx_equ_dfe_2 }, + { ICE_AQC_RX_EQU_DFE_3, rx, &ptr->rx_equ_dfe_3 }, + { ICE_AQC_RX_EQU_DFE_4, rx, &ptr->rx_equ_dfe_4 }, + { ICE_AQC_RX_EQU_DFE_5, rx, &ptr->rx_equ_dfe_5 }, + { ICE_AQC_RX_EQU_DFE_6, rx, &ptr->rx_equ_dfe_6 }, + { ICE_AQC_RX_EQU_DFE_7, rx, &ptr->rx_equ_dfe_7 }, + { ICE_AQC_RX_EQU_DFE_8, rx, &ptr->rx_equ_dfe_8 }, + { ICE_AQC_RX_EQU_DFE_9, rx, &ptr->rx_equ_dfe_9 }, + { ICE_AQC_RX_EQU_DFE_10, rx, &ptr->rx_equ_dfe_10 }, + { ICE_AQC_RX_EQU_DFE_11, rx, &ptr->rx_equ_dfe_11 }, + { ICE_AQC_RX_EQU_DFE_12, rx, &ptr->rx_equ_dfe_12 }, + }; + int err; + + for (int i = 0; i < ARRAY_SIZE(aq_params); i++) { + err = ice_aq_get_phy_equalization(hw, aq_params[i].data_in, + aq_params[i].opcode, + serdes_num, aq_params[i].out); + if (err) + break; + } + + return err; +} + +/** + * ice_get_extended_regs - returns FEC correctable, uncorrectable stats per + * pcsquad, pcsport + * @netdev: pointer to net device structure + * @p: output buffer to fill requested register dump + * + * Return: 0 on success, negative on failure. + */ +static int ice_get_extended_regs(struct net_device *netdev, void *p) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_regdump_to_ethtool *ice_prv_regs_buf; + struct ice_port_topology port_topology = {}; + struct ice_port_info *pi; + struct ice_pf *pf; + struct ice_hw *hw; + unsigned int i; + int err; + + pf = np->vsi->back; + hw = &pf->hw; + pi = np->vsi->port_info; + + /* Serdes parameters are not supported if not the PF VSI */ + if (np->vsi->type != ICE_VSI_PF || !pi) + return -EINVAL; + + err = ice_get_port_topology(hw, pi->lport, &port_topology); + if (err) + return -EINVAL; + if (port_topology.serdes_lane_count > 4) + return -EINVAL; + + ice_prv_regs_buf = p; + + /* Get serdes equalization parameter for available serdes */ + for (i = 0; i < port_topology.serdes_lane_count; i++) { + u8 serdes_num = 0; + + serdes_num = port_topology.primary_serdes_lane + i; + err = ice_get_tx_rx_equa(hw, serdes_num, + &ice_prv_regs_buf->equalization[i]); + if (err) + return -EINVAL; + } + + return 0; } static void @@ -475,10 +799,12 @@ ice_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p) u32 *regs_buf = (u32 *)p; unsigned int i; - regs->version = 1; + regs->version = 2; for (i = 0; i < ARRAY_SIZE(ice_regs_dump_list); ++i) regs_buf[i] = rd32(hw, ice_regs_dump_list[i]); + + ice_get_extended_regs(netdev, (void *)®s_buf[i]); } static u32 ice_get_msglevel(struct net_device *netdev) @@ -1492,7 +1818,7 @@ static int ice_set_priv_flags(struct net_device *netdev, u32 flags) /* Remove rule to direct LLDP packets to default VSI. * The FW LLDP engine will now be consuming them. */ - ice_cfg_sw_lldp(vsi, false, false); + ice_cfg_sw_rx_lldp(vsi->back, false); /* AQ command to start FW LLDP agent will return an * error if the agent is already started @@ -3434,7 +3760,7 @@ ice_set_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh, } static int -ice_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) +ice_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info) { struct ice_pf *pf = ice_netdev_to_pf(dev); @@ -3443,8 +3769,6 @@ ice_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) return ethtool_op_get_ts_info(dev, info); info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | - SOF_TIMESTAMPING_RX_SOFTWARE | - SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_TX_HARDWARE | SOF_TIMESTAMPING_RX_HARDWARE | SOF_TIMESTAMPING_RAW_HARDWARE; @@ -3464,8 +3788,7 @@ ice_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) */ static int ice_get_max_txq(struct ice_pf *pf) { - return min3(pf->num_lan_msix, (u16)num_online_cpus(), - (u16)pf->hw.func_caps.common_cap.num_txq); + return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_txq); } /** @@ -3474,8 +3797,7 @@ static int ice_get_max_txq(struct ice_pf *pf) */ static int ice_get_max_rxq(struct ice_pf *pf) { - return min3(pf->num_lan_msix, (u16)num_online_cpus(), - (u16)pf->hw.func_caps.common_cap.num_rxq); + return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_rxq); } /** @@ -3493,8 +3815,7 @@ static u32 ice_get_combined_cnt(struct ice_vsi *vsi) ice_for_each_q_vector(vsi, q_idx) { struct ice_q_vector *q_vector = vsi->q_vectors[q_idx]; - if (q_vector->rx.rx_ring && q_vector->tx.tx_ring) - combined++; + combined += min(q_vector->num_ring_tx, q_vector->num_ring_rx); } return combined; @@ -3593,7 +3914,6 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch) struct ice_pf *pf = vsi->back; int new_rx = 0, new_tx = 0; bool locked = false; - u32 curr_combined; int ret = 0; /* do not support changing channels in Safe Mode */ @@ -3615,22 +3935,8 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch) return -EOPNOTSUPP; } - curr_combined = ice_get_combined_cnt(vsi); - - /* 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->rx_count == vsi->num_rxq - curr_combined) - ch->rx_count = 0; - if (ch->tx_count == vsi->num_txq - curr_combined) - ch->tx_count = 0; - if (ch->combined_count == curr_combined) - ch->combined_count = 0; - - if (!(ch->combined_count || (ch->rx_count && ch->tx_count))) { - netdev_err(dev, "Please specify at least 1 Rx and 1 Tx channel\n"); + if (ch->rx_count && ch->tx_count) { + netdev_err(dev, "Dedicated RX or TX channels cannot be used simultaneously\n"); return -EINVAL; } @@ -3658,11 +3964,11 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch) return -EINVAL; } - if (pf->adev) { + if (pf->cdev_info && pf->cdev_info->adev) { mutex_lock(&pf->adev_mutex); - device_lock(&pf->adev->dev); + device_lock(&pf->cdev_info->adev->dev); locked = true; - if (pf->adev->dev.driver) { + if (pf->cdev_info->adev->dev.driver) { netdev_err(dev, "Cannot change channels when RDMA is active\n"); ret = -EBUSY; goto adev_unlock; @@ -3681,7 +3987,7 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch) adev_unlock: if (locked) { - device_unlock(&pf->adev->dev); + device_unlock(&pf->cdev_info->adev->dev); mutex_unlock(&pf->adev_mutex); } return ret; @@ -4080,7 +4386,7 @@ ice_repr_get_drvinfo(struct net_device *netdev, { struct ice_repr *repr = ice_netdev_to_repr(netdev); - if (ice_check_vf_ready_for_cfg(repr->vf)) + if (repr->ops.ready(repr)) return; __ice_get_drvinfo(netdev, drvinfo, repr->src_vsi); @@ -4092,8 +4398,7 @@ ice_repr_get_strings(struct net_device *netdev, u32 stringset, u8 *data) struct ice_repr *repr = ice_netdev_to_repr(netdev); /* for port representors only ETH_SS_STATS is supported */ - if (ice_check_vf_ready_for_cfg(repr->vf) || - stringset != ETH_SS_STATS) + if (repr->ops.ready(repr) || stringset != ETH_SS_STATS) return; __ice_get_strings(netdev, stringset, data, repr->src_vsi); @@ -4106,7 +4411,7 @@ ice_repr_get_ethtool_stats(struct net_device *netdev, { struct ice_repr *repr = ice_netdev_to_repr(netdev); - if (ice_check_vf_ready_for_cfg(repr->vf)) + if (repr->ops.ready(repr)) return; __ice_get_ethtool_stats(netdev, stats, data, repr->src_vsi); @@ -4297,14 +4602,179 @@ ice_get_module_eeprom(struct net_device *netdev, return 0; } +/** + * ice_get_port_fec_stats - returns FEC correctable, uncorrectable stats per + * pcsquad, pcsport + * @hw: pointer to the HW struct + * @pcs_quad: pcsquad for input port + * @pcs_port: pcsport for input port + * @fec_stats: buffer to hold FEC statistics for given port + * + * Return: 0 on success, negative on failure. + */ +static int ice_get_port_fec_stats(struct ice_hw *hw, u16 pcs_quad, u16 pcs_port, + struct ethtool_fec_stats *fec_stats) +{ + u32 fec_uncorr_low_val = 0, fec_uncorr_high_val = 0; + u32 fec_corr_low_val = 0, fec_corr_high_val = 0; + int err; + + if (pcs_quad > 1 || pcs_port > 3) + return -EINVAL; + + err = ice_aq_get_fec_stats(hw, pcs_quad, pcs_port, ICE_FEC_CORR_LOW, + &fec_corr_low_val); + if (err) + return err; + + err = ice_aq_get_fec_stats(hw, pcs_quad, pcs_port, ICE_FEC_CORR_HIGH, + &fec_corr_high_val); + if (err) + return err; + + err = ice_aq_get_fec_stats(hw, pcs_quad, pcs_port, + ICE_FEC_UNCORR_LOW, + &fec_uncorr_low_val); + if (err) + return err; + + err = ice_aq_get_fec_stats(hw, pcs_quad, pcs_port, + ICE_FEC_UNCORR_HIGH, + &fec_uncorr_high_val); + if (err) + return err; + + fec_stats->corrected_blocks.total = (fec_corr_high_val << 16) + + fec_corr_low_val; + fec_stats->uncorrectable_blocks.total = (fec_uncorr_high_val << 16) + + fec_uncorr_low_val; + return 0; +} + +/** + * ice_get_fec_stats - returns FEC correctable, uncorrectable stats per netdev + * @netdev: network interface device structure + * @fec_stats: buffer to hold FEC statistics for given port + * + */ +static void ice_get_fec_stats(struct net_device *netdev, + struct ethtool_fec_stats *fec_stats) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_port_topology port_topology; + struct ice_port_info *pi; + struct ice_pf *pf; + struct ice_hw *hw; + int err; + + pf = np->vsi->back; + hw = &pf->hw; + pi = np->vsi->port_info; + + /* Serdes parameters are not supported if not the PF VSI */ + if (np->vsi->type != ICE_VSI_PF || !pi) + return; + + err = ice_get_port_topology(hw, pi->lport, &port_topology); + if (err) { + netdev_info(netdev, "Extended register dump failed Lport %d\n", + pi->lport); + return; + } + + /* Get FEC correctable, uncorrectable counter */ + err = ice_get_port_fec_stats(hw, port_topology.pcs_quad_select, + port_topology.pcs_port, fec_stats); + if (err) + netdev_info(netdev, "FEC stats get failed Lport %d Err %d\n", + pi->lport, err); +} + +#define ICE_ETHTOOL_PFR (ETH_RESET_IRQ | ETH_RESET_DMA | \ + ETH_RESET_FILTER | ETH_RESET_OFFLOAD) + +#define ICE_ETHTOOL_CORER ((ICE_ETHTOOL_PFR | ETH_RESET_RAM) << \ + ETH_RESET_SHARED_SHIFT) + +#define ICE_ETHTOOL_GLOBR (ICE_ETHTOOL_CORER | \ + (ETH_RESET_MAC << ETH_RESET_SHARED_SHIFT) | \ + (ETH_RESET_PHY << ETH_RESET_SHARED_SHIFT)) + +#define ICE_ETHTOOL_VFR ICE_ETHTOOL_PFR + +/** + * ice_ethtool_reset - triggers a given type of reset + * @dev: network interface device structure + * @flags: set of reset flags + * + * Return: 0 on success, -EOPNOTSUPP when using unsupported set of flags. + */ +static int ice_ethtool_reset(struct net_device *dev, u32 *flags) +{ + struct ice_netdev_priv *np = netdev_priv(dev); + struct ice_pf *pf = np->vsi->back; + enum ice_reset_req reset; + + switch (*flags) { + case ICE_ETHTOOL_CORER: + reset = ICE_RESET_CORER; + break; + case ICE_ETHTOOL_GLOBR: + reset = ICE_RESET_GLOBR; + break; + case ICE_ETHTOOL_PFR: + reset = ICE_RESET_PFR; + break; + default: + netdev_info(dev, "Unsupported set of ethtool flags"); + return -EOPNOTSUPP; + } + + ice_schedule_reset(pf, reset); + + *flags = 0; + + return 0; +} + +/** + * ice_repr_ethtool_reset - triggers a VF reset + * @dev: network interface device structure + * @flags: set of reset flags + * + * Return: 0 on success, + * -EOPNOTSUPP when using unsupported set of flags + * -EBUSY when VF is not ready for reset. + */ +static int ice_repr_ethtool_reset(struct net_device *dev, u32 *flags) +{ + struct ice_repr *repr = ice_netdev_to_repr(dev); + struct ice_vf *vf; + + if (repr->type != ICE_REPR_TYPE_VF || + *flags != ICE_ETHTOOL_VFR) + return -EOPNOTSUPP; + + vf = repr->vf; + + if (ice_check_vf_ready_for_cfg(vf)) + return -EBUSY; + + *flags = 0; + + return ice_reset_vf(vf, ICE_VF_RESET_VFLR | ICE_VF_RESET_LOCK); +} + static const struct ethtool_ops ice_ethtool_ops = { .cap_rss_ctx_supported = true, .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_USE_ADAPTIVE | ETHTOOL_COALESCE_RX_USECS_HIGH, - .cap_rss_sym_xor_supported = true, + .supported_input_xfrm = RXH_XFRM_SYM_XOR, + .rxfh_per_ctx_key = true, .get_link_ksettings = ice_get_link_ksettings, .set_link_ksettings = ice_set_link_ksettings, + .get_fec_stats = ice_get_fec_stats, .get_drvinfo = ice_get_drvinfo, .get_regs_len = ice_get_regs_len, .get_regs = ice_get_regs, @@ -4331,6 +4801,7 @@ static const struct ethtool_ops ice_ethtool_ops = { .nway_reset = ice_nway_reset, .get_pauseparam = ice_get_pauseparam, .set_pauseparam = ice_set_pauseparam, + .reset = ice_ethtool_reset, .get_rxfh_key_size = ice_get_rxfh_key_size, .get_rxfh_indir_size = ice_get_rxfh_indir_size, .get_rxfh = ice_get_rxfh, @@ -4383,6 +4854,7 @@ static const struct ethtool_ops ice_ethtool_repr_ops = { .get_strings = ice_repr_get_strings, .get_ethtool_stats = ice_repr_get_ethtool_stats, .get_sset_count = ice_repr_get_sset_count, + .reset = ice_repr_ethtool_reset, }; /** diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.h b/drivers/net/ethernet/intel/ice/ice_ethtool.h index b88e3da06f13..23b2cfbc9684 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.h +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.h @@ -9,6 +9,51 @@ struct ice_phy_type_to_ethtool { u8 link_mode; }; +struct ice_serdes_equalization_to_ethtool { + int rx_equ_pre2; + int rx_equ_pre1; + int rx_equ_post1; + int rx_equ_bflf; + int rx_equ_bfhf; + int rx_equ_ctle_gainhf; + int rx_equ_ctle_gainlf; + int rx_equ_ctle_gaindc; + int rx_equ_ctle_bw; + int rx_equ_dfe_gain; + int rx_equ_dfe_gain_2; + int rx_equ_dfe_2; + int rx_equ_dfe_3; + int rx_equ_dfe_4; + int rx_equ_dfe_5; + int rx_equ_dfe_6; + int rx_equ_dfe_7; + int rx_equ_dfe_8; + int rx_equ_dfe_9; + int rx_equ_dfe_10; + int rx_equ_dfe_11; + int rx_equ_dfe_12; + int tx_equ_pre1; + int tx_equ_pre3; + int tx_equ_atten; + int tx_equ_post1; + int tx_equ_pre2; +}; + +struct ice_regdump_to_ethtool { + /* A multilane port can have max 4 serdes */ + struct ice_serdes_equalization_to_ethtool equalization[4]; +}; + +/* Port topology from lport i.e. + * serdes mapping, pcsquad, macport, cage etc... + */ +struct ice_port_topology { + u16 pcs_port; + u16 primary_serdes_lane; + u16 serdes_lane_count; + u16 pcs_quad_select; +}; + /* Macro to make PHY type to Ethtool link mode table entry. * The index is the PHY type. */ diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c index 9a1a04f5f146..aceec184e89b 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c @@ -41,6 +41,8 @@ static struct in6_addr zero_ipv6_addr_mask = { static int ice_fltr_to_ethtool_flow(enum ice_fltr_ptype flow) { switch (flow) { + case ICE_FLTR_PTYPE_NONF_ETH: + return ETHER_FLOW; case ICE_FLTR_PTYPE_NONF_IPV4_TCP: return TCP_V4_FLOW; case ICE_FLTR_PTYPE_NONF_IPV4_UDP: @@ -72,6 +74,8 @@ static int ice_fltr_to_ethtool_flow(enum ice_fltr_ptype flow) static enum ice_fltr_ptype ice_ethtool_flow_to_fltr(int eth) { switch (eth) { + case ETHER_FLOW: + return ICE_FLTR_PTYPE_NONF_ETH; case TCP_V4_FLOW: return ICE_FLTR_PTYPE_NONF_IPV4_TCP; case UDP_V4_FLOW: @@ -137,6 +141,10 @@ int ice_get_ethtool_fdir_entry(struct ice_hw *hw, struct ethtool_rxnfc *cmd) memset(&fsp->m_ext, 0, sizeof(fsp->m_ext)); switch (fsp->flow_type) { + case ETHER_FLOW: + fsp->h_u.ether_spec = rule->eth; + fsp->m_u.ether_spec = rule->eth_mask; + break; case IPV4_USER_FLOW: fsp->h_u.usr_ip4_spec.ip_ver = ETH_RX_NFC_IP4; fsp->h_u.usr_ip4_spec.proto = 0; @@ -526,7 +534,7 @@ ice_parse_rx_flow_user_data(struct ethtool_rx_flow_spec *fsp, * * Returns the number of available flow director filters to this VSI */ -static int ice_fdir_num_avail_fltr(struct ice_hw *hw, struct ice_vsi *vsi) +int ice_fdir_num_avail_fltr(struct ice_hw *hw, struct ice_vsi *vsi) { u16 vsi_num = ice_get_hw_vsi_num(hw, vsi->idx); u16 num_guar; @@ -1194,6 +1202,122 @@ ice_set_fdir_ip6_usr_seg(struct ice_flow_seg_info *seg, } /** + * ice_fdir_vlan_valid - validate VLAN data for Flow Director rule + * @dev: network interface device structure + * @fsp: pointer to ethtool Rx flow specification + * + * Return: true if vlan data is valid, false otherwise + */ +static bool ice_fdir_vlan_valid(struct device *dev, + struct ethtool_rx_flow_spec *fsp) +{ + if (fsp->m_ext.vlan_etype && !eth_type_vlan(fsp->h_ext.vlan_etype)) + return false; + + if (fsp->m_ext.vlan_tci && ntohs(fsp->h_ext.vlan_tci) >= VLAN_N_VID) + return false; + + /* proto and vlan must have vlan-etype defined */ + if (fsp->m_u.ether_spec.h_proto && fsp->m_ext.vlan_tci && + !fsp->m_ext.vlan_etype) { + dev_warn(dev, "Filter with proto and vlan require also vlan-etype"); + return false; + } + + return true; +} + +/** + * ice_set_ether_flow_seg - set address and protocol segments for ether flow + * @dev: network interface device structure + * @seg: flow segment for programming + * @eth_spec: mask data from ethtool + * + * Return: 0 on success and errno in case of error. + */ +static int ice_set_ether_flow_seg(struct device *dev, + struct ice_flow_seg_info *seg, + struct ethhdr *eth_spec) +{ + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_ETH); + + /* empty rules are not valid */ + if (is_zero_ether_addr(eth_spec->h_source) && + is_zero_ether_addr(eth_spec->h_dest) && + !eth_spec->h_proto) + return -EINVAL; + + /* Ethertype */ + if (eth_spec->h_proto == htons(0xFFFF)) { + ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_ETH_TYPE, + ICE_FLOW_FLD_OFF_INVAL, + ICE_FLOW_FLD_OFF_INVAL, + ICE_FLOW_FLD_OFF_INVAL, false); + } else if (eth_spec->h_proto) { + dev_warn(dev, "Only 0x0000 or 0xffff proto mask is allowed for flow-type ether"); + return -EOPNOTSUPP; + } + + /* Source MAC address */ + if (is_broadcast_ether_addr(eth_spec->h_source)) + ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_ETH_SA, + ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL, + ICE_FLOW_FLD_OFF_INVAL, false); + else if (!is_zero_ether_addr(eth_spec->h_source)) + goto err_mask; + + /* Destination MAC address */ + if (is_broadcast_ether_addr(eth_spec->h_dest)) + ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_ETH_DA, + ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL, + ICE_FLOW_FLD_OFF_INVAL, false); + else if (!is_zero_ether_addr(eth_spec->h_dest)) + goto err_mask; + + return 0; + +err_mask: + dev_warn(dev, "Only 00:00:00:00:00:00 or ff:ff:ff:ff:ff:ff MAC address mask is allowed for flow-type ether"); + return -EOPNOTSUPP; +} + +/** + * ice_set_fdir_vlan_seg - set vlan segments for ether flow + * @seg: flow segment for programming + * @ext_masks: masks for additional RX flow fields + * + * Return: 0 on success and errno in case of error. + */ +static int +ice_set_fdir_vlan_seg(struct ice_flow_seg_info *seg, + struct ethtool_flow_ext *ext_masks) +{ + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_VLAN); + + if (ext_masks->vlan_etype) { + if (ext_masks->vlan_etype != htons(0xFFFF)) + return -EOPNOTSUPP; + + ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_S_VLAN, + ICE_FLOW_FLD_OFF_INVAL, + ICE_FLOW_FLD_OFF_INVAL, + ICE_FLOW_FLD_OFF_INVAL, false); + } + + if (ext_masks->vlan_tci) { + if (ext_masks->vlan_tci != htons(0xFFFF)) + return -EOPNOTSUPP; + + ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_C_VLAN, + ICE_FLOW_FLD_OFF_INVAL, + ICE_FLOW_FLD_OFF_INVAL, + ICE_FLOW_FLD_OFF_INVAL, false); + } + + return 0; +} + +/** * ice_cfg_fdir_xtrct_seq - Configure extraction sequence for the given filter * @pf: PF structure * @fsp: pointer to ethtool Rx flow specification @@ -1209,7 +1333,7 @@ ice_cfg_fdir_xtrct_seq(struct ice_pf *pf, struct ethtool_rx_flow_spec *fsp, struct device *dev = ice_pf_to_dev(pf); enum ice_fltr_ptype fltr_idx; struct ice_hw *hw = &pf->hw; - bool perfect_filter; + bool perfect_filter = false; int ret; seg = devm_kzalloc(dev, sizeof(*seg), GFP_KERNEL); @@ -1262,6 +1386,16 @@ ice_cfg_fdir_xtrct_seq(struct ice_pf *pf, struct ethtool_rx_flow_spec *fsp, ret = ice_set_fdir_ip6_usr_seg(seg, &fsp->m_u.usr_ip6_spec, &perfect_filter); break; + case ETHER_FLOW: + ret = ice_set_ether_flow_seg(dev, seg, &fsp->m_u.ether_spec); + if (!ret && (fsp->m_ext.vlan_etype || fsp->m_ext.vlan_tci)) { + if (!ice_fdir_vlan_valid(dev, fsp)) { + ret = -EINVAL; + break; + } + ret = ice_set_fdir_vlan_seg(seg, &fsp->m_ext); + } + break; default: ret = -EINVAL; } @@ -1471,22 +1605,19 @@ void ice_fdir_replay_fltrs(struct ice_pf *pf) */ int ice_fdir_create_dflt_rules(struct ice_pf *pf) { + static const enum ice_fltr_ptype dflt_rules[] = { + ICE_FLTR_PTYPE_NONF_IPV4_TCP, ICE_FLTR_PTYPE_NONF_IPV4_UDP, + ICE_FLTR_PTYPE_NONF_IPV6_TCP, ICE_FLTR_PTYPE_NONF_IPV6_UDP, + }; int err; /* Create perfect TCP and UDP rules in hardware. */ - err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV4_TCP); - if (err) - return err; + for (int i = 0; i < ARRAY_SIZE(dflt_rules); i++) { + err = ice_create_init_fdir_rule(pf, dflt_rules[i]); - err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV4_UDP); - if (err) - return err; - - err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV6_TCP); - if (err) - return err; - - err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV6_UDP); + if (err) + break; + } return err; } @@ -1696,11 +1827,12 @@ static int ice_set_fdir_input_set(struct ice_vsi *vsi, struct ethtool_rx_flow_spec *fsp, struct ice_fdir_fltr *input) { - u16 dest_vsi, q_index = 0; + s16 q_index = ICE_FDIR_NO_QUEUE_IDX; u16 orig_q_index = 0; struct ice_pf *pf; struct ice_hw *hw; int flow_type; + u16 dest_vsi; u8 dest_ctl; if (!vsi || !fsp || !input) @@ -1823,6 +1955,10 @@ ice_set_fdir_input_set(struct ice_vsi *vsi, struct ethtool_rx_flow_spec *fsp, input->mask.v6.tc = fsp->m_u.usr_ip6_spec.tclass; input->mask.v6.proto = fsp->m_u.usr_ip6_spec.l4_proto; break; + case ETHER_FLOW: + input->eth = fsp->h_u.ether_spec; + input->eth_mask = fsp->m_u.ether_spec; + break; default: /* not doing un-parsed flow types */ return -EINVAL; diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.c b/drivers/net/ethernet/intel/ice/ice_fdir.c index 5840c3e04a5b..26b357c0ae15 100644 --- a/drivers/net/ethernet/intel/ice/ice_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_fdir.c @@ -4,6 +4,8 @@ #include "ice_common.h" /* These are training packet headers used to program flow director filters. */ +static const u8 ice_fdir_eth_pkt[22]; + static const u8 ice_fdir_tcpv4_pkt[] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00, @@ -417,6 +419,11 @@ static const u8 ice_fdir_ip6_tun_pkt[] = { /* Flow Director no-op training packet table */ static const struct ice_fdir_base_pkt ice_fdir_pkt[] = { { + ICE_FLTR_PTYPE_NONF_ETH, + sizeof(ice_fdir_eth_pkt), ice_fdir_eth_pkt, + sizeof(ice_fdir_eth_pkt), ice_fdir_eth_pkt, + }, + { ICE_FLTR_PTYPE_NONF_IPV4_TCP, sizeof(ice_fdir_tcpv4_pkt), ice_fdir_tcpv4_pkt, sizeof(ice_fdir_tcp4_tun_pkt), ice_fdir_tcp4_tun_pkt, @@ -914,6 +921,21 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input, * perspective. The input from user is from Rx filter perspective. */ switch (flow) { + case ICE_FLTR_PTYPE_NONF_ETH: + ice_pkt_insert_mac_addr(loc, input->eth.h_dest); + ice_pkt_insert_mac_addr(loc + ETH_ALEN, input->eth.h_source); + if (input->ext_data.vlan_tag || input->ext_data.vlan_type) { + ice_pkt_insert_u16(loc, ICE_ETH_TYPE_F_OFFSET, + input->ext_data.vlan_type); + ice_pkt_insert_u16(loc, ICE_ETH_VLAN_TCI_OFFSET, + input->ext_data.vlan_tag); + ice_pkt_insert_u16(loc, ICE_ETH_TYPE_VLAN_OFFSET, + input->eth.h_proto); + } else { + ice_pkt_insert_u16(loc, ICE_ETH_TYPE_F_OFFSET, + input->eth.h_proto); + } + break; case ICE_FLTR_PTYPE_NONF_IPV4_TCP: ice_pkt_insert_u32(loc, ICE_IPV4_DST_ADDR_OFFSET, input->ip.v4.src_ip); @@ -1189,52 +1211,58 @@ static int ice_cmp_ipv6_addr(__be32 *a, __be32 *b) * ice_fdir_comp_rules - compare 2 filters * @a: a Flow Director filter data structure * @b: a Flow Director filter data structure - * @v6: bool true if v6 filter * * Returns true if the filters match */ static bool -ice_fdir_comp_rules(struct ice_fdir_fltr *a, struct ice_fdir_fltr *b, bool v6) +ice_fdir_comp_rules(struct ice_fdir_fltr *a, struct ice_fdir_fltr *b) { enum ice_fltr_ptype flow_type = a->flow_type; /* The calling function already checks that the two filters have the * same flow_type. */ - if (!v6) { - if (flow_type == ICE_FLTR_PTYPE_NONF_IPV4_TCP || - flow_type == ICE_FLTR_PTYPE_NONF_IPV4_UDP || - flow_type == ICE_FLTR_PTYPE_NONF_IPV4_SCTP) { - if (a->ip.v4.dst_ip == b->ip.v4.dst_ip && - a->ip.v4.src_ip == b->ip.v4.src_ip && - a->ip.v4.dst_port == b->ip.v4.dst_port && - a->ip.v4.src_port == b->ip.v4.src_port) - return true; - } else if (flow_type == ICE_FLTR_PTYPE_NONF_IPV4_OTHER) { - if (a->ip.v4.dst_ip == b->ip.v4.dst_ip && - a->ip.v4.src_ip == b->ip.v4.src_ip && - a->ip.v4.l4_header == b->ip.v4.l4_header && - a->ip.v4.proto == b->ip.v4.proto && - a->ip.v4.ip_ver == b->ip.v4.ip_ver && - a->ip.v4.tos == b->ip.v4.tos) - return true; - } - } else { - if (flow_type == ICE_FLTR_PTYPE_NONF_IPV6_UDP || - flow_type == ICE_FLTR_PTYPE_NONF_IPV6_TCP || - flow_type == ICE_FLTR_PTYPE_NONF_IPV6_SCTP) { - if (a->ip.v6.dst_port == b->ip.v6.dst_port && - a->ip.v6.src_port == b->ip.v6.src_port && - !ice_cmp_ipv6_addr(a->ip.v6.dst_ip, - b->ip.v6.dst_ip) && - !ice_cmp_ipv6_addr(a->ip.v6.src_ip, - b->ip.v6.src_ip)) - return true; - } else if (flow_type == ICE_FLTR_PTYPE_NONF_IPV6_OTHER) { - if (a->ip.v6.dst_port == b->ip.v6.dst_port && - a->ip.v6.src_port == b->ip.v6.src_port) - return true; - } + switch (flow_type) { + case ICE_FLTR_PTYPE_NONF_ETH: + if (!memcmp(&a->eth, &b->eth, sizeof(a->eth))) + return true; + break; + case ICE_FLTR_PTYPE_NONF_IPV4_TCP: + case ICE_FLTR_PTYPE_NONF_IPV4_UDP: + case ICE_FLTR_PTYPE_NONF_IPV4_SCTP: + if (a->ip.v4.dst_ip == b->ip.v4.dst_ip && + a->ip.v4.src_ip == b->ip.v4.src_ip && + a->ip.v4.dst_port == b->ip.v4.dst_port && + a->ip.v4.src_port == b->ip.v4.src_port) + return true; + break; + case ICE_FLTR_PTYPE_NONF_IPV4_OTHER: + if (a->ip.v4.dst_ip == b->ip.v4.dst_ip && + a->ip.v4.src_ip == b->ip.v4.src_ip && + a->ip.v4.l4_header == b->ip.v4.l4_header && + a->ip.v4.proto == b->ip.v4.proto && + a->ip.v4.ip_ver == b->ip.v4.ip_ver && + a->ip.v4.tos == b->ip.v4.tos) + return true; + break; + case ICE_FLTR_PTYPE_NONF_IPV6_UDP: + case ICE_FLTR_PTYPE_NONF_IPV6_TCP: + case ICE_FLTR_PTYPE_NONF_IPV6_SCTP: + if (a->ip.v6.dst_port == b->ip.v6.dst_port && + a->ip.v6.src_port == b->ip.v6.src_port && + !ice_cmp_ipv6_addr(a->ip.v6.dst_ip, + b->ip.v6.dst_ip) && + !ice_cmp_ipv6_addr(a->ip.v6.src_ip, + b->ip.v6.src_ip)) + return true; + break; + case ICE_FLTR_PTYPE_NONF_IPV6_OTHER: + if (a->ip.v6.dst_port == b->ip.v6.dst_port && + a->ip.v6.src_port == b->ip.v6.src_port) + return true; + break; + default: + break; } return false; @@ -1253,19 +1281,10 @@ bool ice_fdir_is_dup_fltr(struct ice_hw *hw, struct ice_fdir_fltr *input) bool ret = false; list_for_each_entry(rule, &hw->fdir_list_head, fltr_node) { - enum ice_fltr_ptype flow_type; - if (rule->flow_type != input->flow_type) continue; - flow_type = input->flow_type; - if (flow_type == ICE_FLTR_PTYPE_NONF_IPV4_TCP || - flow_type == ICE_FLTR_PTYPE_NONF_IPV4_UDP || - flow_type == ICE_FLTR_PTYPE_NONF_IPV4_SCTP || - flow_type == ICE_FLTR_PTYPE_NONF_IPV4_OTHER) - ret = ice_fdir_comp_rules(rule, input, false); - else - ret = ice_fdir_comp_rules(rule, input, true); + ret = ice_fdir_comp_rules(rule, input); if (ret) { if (rule->fltr_id == input->fltr_id && rule->q_index != input->q_index) diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.h b/drivers/net/ethernet/intel/ice/ice_fdir.h index 1b9b84490689..820023c0271f 100644 --- a/drivers/net/ethernet/intel/ice/ice_fdir.h +++ b/drivers/net/ethernet/intel/ice/ice_fdir.h @@ -8,6 +8,9 @@ #define ICE_FDIR_MAX_RAW_PKT_SIZE (512 + ICE_FDIR_TUN_PKT_OFF) /* macros for offsets into packets for flow director programming */ +#define ICE_ETH_TYPE_F_OFFSET 12 +#define ICE_ETH_VLAN_TCI_OFFSET 14 +#define ICE_ETH_TYPE_VLAN_OFFSET 16 #define ICE_IPV4_SRC_ADDR_OFFSET 26 #define ICE_IPV4_DST_ADDR_OFFSET 30 #define ICE_IPV4_TCP_SRC_PORT_OFFSET 34 @@ -50,6 +53,8 @@ */ #define ICE_FDIR_IPV4_PKT_FLAG_MF 0x20 +#define ICE_FDIR_NO_QUEUE_IDX -1 + enum ice_fltr_prgm_desc_dest { ICE_FLTR_PRGM_DESC_DEST_DROP_PKT, ICE_FLTR_PRGM_DESC_DEST_DIRECT_PKT_QINDEX, @@ -159,6 +164,8 @@ struct ice_fdir_fltr { struct list_head fltr_node; enum ice_fltr_ptype flow_type; + struct ethhdr eth, eth_mask; + union { struct ice_fdir_v4 v4; struct ice_fdir_v6 v6; @@ -181,7 +188,7 @@ struct ice_fdir_fltr { u16 flex_fltr; /* filter control */ - u16 q_index; + s16 q_index; u16 orig_q_index; u16 dest_vsi; u8 dest_ctl; @@ -202,6 +209,8 @@ struct ice_fdir_base_pkt { const u8 *tun_pkt; }; +struct ice_vsi; + int ice_alloc_fd_res_cntr(struct ice_hw *hw, u16 *cntr_id); int ice_free_fd_res_cntr(struct ice_hw *hw, u16 cntr_id); int ice_alloc_fd_guar_item(struct ice_hw *hw, u16 *cntr_id, u16 num_fltr); @@ -213,6 +222,7 @@ int ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input, u8 *pkt, bool frag, bool tun); int ice_get_fdir_cnt_all(struct ice_hw *hw); +int ice_fdir_num_avail_fltr(struct ice_hw *hw, struct ice_vsi *vsi); bool ice_fdir_is_dup_fltr(struct ice_hw *hw, struct ice_fdir_fltr *input); bool ice_fdir_has_frag(enum ice_fltr_ptype flow); struct ice_fdir_fltr * diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c index 20d5db88c99f..ed95072ca6e3 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c @@ -2981,6 +2981,50 @@ ice_add_prof_attrib(struct ice_prof_map *prof, u8 ptg, u16 ptype, } /** + * ice_disable_fd_swap - set register appropriately to disable FD SWAP + * @hw: pointer to the HW struct + * @prof_id: profile ID + */ +static void +ice_disable_fd_swap(struct ice_hw *hw, u8 prof_id) +{ + u16 swap_val, fvw_num; + unsigned int i; + + swap_val = ICE_SWAP_VALID; + fvw_num = hw->blk[ICE_BLK_FD].es.fvw / ICE_FDIR_REG_SET_SIZE; + + /* Since the SWAP Flag in the Programming Desc doesn't work, + * here add method to disable the SWAP Option via setting + * certain SWAP and INSET register sets. + */ + for (i = 0; i < fvw_num ; i++) { + u32 raw_swap, raw_in; + unsigned int j; + + raw_swap = 0; + raw_in = 0; + + for (j = 0; j < ICE_FDIR_REG_SET_SIZE; j++) { + raw_swap |= (swap_val++) << (j * BITS_PER_BYTE); + raw_in |= ICE_INSET_DFLT << (j * BITS_PER_BYTE); + } + + /* write the FDIR swap register set */ + wr32(hw, GLQF_FDSWAP(prof_id, i), raw_swap); + + ice_debug(hw, ICE_DBG_INIT, "swap wr(%d, %d): 0x%x = 0x%08x\n", + prof_id, i, GLQF_FDSWAP(prof_id, i), raw_swap); + + /* write the FDIR inset register set */ + wr32(hw, GLQF_FDINSET(prof_id, i), raw_in); + + ice_debug(hw, ICE_DBG_INIT, "inset wr(%d, %d): 0x%x = 0x%08x\n", + prof_id, i, GLQF_FDINSET(prof_id, i), raw_in); + } +} + +/* * ice_add_prof - add profile * @hw: pointer to the HW struct * @blk: hardware block @@ -2991,6 +3035,7 @@ ice_add_prof_attrib(struct ice_prof_map *prof, u8 ptg, u16 ptype, * @es: extraction sequence (length of array is determined by the block) * @masks: mask for extraction sequence * @symm: symmetric setting for RSS profiles + * @fd_swap: enable/disable FDIR paired src/dst fields swap option * * This function registers a profile, which matches a set of PTYPES with a * particular extraction sequence. While the hardware profile is allocated @@ -3000,7 +3045,7 @@ ice_add_prof_attrib(struct ice_prof_map *prof, u8 ptg, u16 ptype, int ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], const struct ice_ptype_attributes *attr, u16 attr_cnt, - struct ice_fv_word *es, u16 *masks, bool symm) + struct ice_fv_word *es, u16 *masks, bool symm, bool fd_swap) { u32 bytes = DIV_ROUND_UP(ICE_FLOW_PTYPE_MAX, BITS_PER_BYTE); DECLARE_BITMAP(ptgs_used, ICE_XLT1_CNT); @@ -3020,7 +3065,7 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], status = ice_alloc_prof_id(hw, blk, &prof_id); if (status) goto err_ice_add_prof; - if (blk == ICE_BLK_FD) { + if (blk == ICE_BLK_FD && fd_swap) { /* For Flow Director block, the extraction sequence may * need to be altered in the case where there are paired * fields that have no match. This is necessary because @@ -3031,6 +3076,8 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], status = ice_update_fd_swap(hw, prof_id, es); if (status) goto err_ice_add_prof; + } else if (blk == ICE_BLK_FD) { + ice_disable_fd_swap(hw, prof_id); } status = ice_update_prof_masking(hw, blk, prof_id, masks); if (status) @@ -4099,6 +4146,54 @@ err_ice_add_prof_id_flow: } /** + * ice_flow_assoc_fdir_prof - add an FDIR profile for main/ctrl VSI + * @hw: pointer to the HW struct + * @blk: HW block + * @dest_vsi: dest VSI + * @fdir_vsi: fdir programming VSI + * @hdl: profile handle + * + * Update the hardware tables to enable the FDIR profile indicated by @hdl for + * the VSI specified by @dest_vsi. On success, the flow will be enabled. + * + * Return: 0 on success or negative errno on failure. + */ +int +ice_flow_assoc_fdir_prof(struct ice_hw *hw, enum ice_block blk, + u16 dest_vsi, u16 fdir_vsi, u64 hdl) +{ + u16 vsi_num; + int status; + + if (blk != ICE_BLK_FD) + return -EINVAL; + + vsi_num = ice_get_hw_vsi_num(hw, dest_vsi); + status = ice_add_prof_id_flow(hw, blk, vsi_num, hdl); + if (status) { + ice_debug(hw, ICE_DBG_FLOW, "Adding HW profile failed for main VSI flow entry: %d\n", + status); + return status; + } + + vsi_num = ice_get_hw_vsi_num(hw, fdir_vsi); + status = ice_add_prof_id_flow(hw, blk, vsi_num, hdl); + if (status) { + ice_debug(hw, ICE_DBG_FLOW, "Adding HW profile failed for ctrl VSI flow entry: %d\n", + status); + goto err; + } + + return 0; + +err: + vsi_num = ice_get_hw_vsi_num(hw, dest_vsi); + ice_rem_prof_id_flow(hw, blk, vsi_num, hdl); + + return status; +} + +/** * ice_rem_prof_from_list - remove a profile from list * @hw: pointer to the HW struct * @lst: list to remove the profile from diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h index b39d7cdc381f..28b0897adf32 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h @@ -6,6 +6,8 @@ #include "ice_type.h" +#define ICE_FDIR_REG_SET_SIZE 4 + int ice_acquire_change_lock(struct ice_hw *hw, enum ice_aq_res_access_type access); void ice_release_change_lock(struct ice_hw *hw); @@ -21,9 +23,6 @@ int ice_get_sw_fv_list(struct ice_hw *hw, struct ice_prot_lkup_ext *lkups, unsigned long *bm, struct list_head *fv_list); int -ice_pkg_buf_unreserve_section(struct ice_buf_build *bld, u16 count); -u16 ice_pkg_buf_get_free_space(struct ice_buf_build *bld); -int ice_aq_upload_section(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, u16 buf_size, struct ice_sq_cd *cd); bool @@ -42,13 +41,16 @@ bool ice_hw_ptype_ena(struct ice_hw *hw, u16 ptype); int ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], const struct ice_ptype_attributes *attr, u16 attr_cnt, - struct ice_fv_word *es, u16 *masks, bool symm); + struct ice_fv_word *es, u16 *masks, bool symm, bool fd_swap); struct ice_prof_map * ice_search_prof_id(struct ice_hw *hw, enum ice_block blk, u64 id); int ice_add_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl); int ice_rem_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl); +int +ice_flow_assoc_fdir_prof(struct ice_hw *hw, enum ice_block blk, + u16 dest_vsi, u16 fdir_vsi, u64 hdl); enum ice_ddp_state ice_init_pkg(struct ice_hw *hw, u8 *buff, u32 len); enum ice_ddp_state ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf, u32 len); diff --git a/drivers/net/ethernet/intel/ice/ice_flex_type.h b/drivers/net/ethernet/intel/ice/ice_flex_type.h index d427a79d001a..817beca591e0 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_type.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_type.h @@ -93,6 +93,7 @@ enum ice_tunnel_type { TNL_GRETAP, TNL_GTPC, TNL_GTPU, + TNL_PFCP, __TNL_TYPE_CNT, TNL_LAST = 0xFF, TNL_ALL = 0xFF, @@ -358,7 +359,8 @@ enum ice_prof_type { ICE_PROF_TUN_GRE = 0x4, ICE_PROF_TUN_GTPU = 0x8, ICE_PROF_TUN_GTPC = 0x10, - ICE_PROF_TUN_ALL = 0x1E, + ICE_PROF_TUN_PFCP = 0x20, + ICE_PROF_TUN_ALL = 0x3E, ICE_PROF_ALL = 0xFF, }; diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c index fc2b58f56279..d97b751052f2 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.c +++ b/drivers/net/ethernet/intel/ice/ice_flow.c @@ -409,6 +409,29 @@ static const u32 ice_ptypes_gtpc_tid[] = { }; /* Packet types for GTPU */ +static const struct ice_ptype_attributes ice_attr_gtpu_session[] = { + { ICE_MAC_IPV4_GTPU_IPV4_FRAG, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV4_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV4_UDP_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV4_TCP, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV4_ICMP, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV4_FRAG, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV4_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV4_UDP_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV4_TCP, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV4_ICMP, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV6_FRAG, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV6_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV6_UDP_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV6_TCP, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV6_ICMPV6, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV6_FRAG, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV6_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV6_UDP_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV6_TCP, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV6_ICMPV6, ICE_PTYPE_ATTR_GTP_SESSION }, +}; + static const struct ice_ptype_attributes ice_attr_gtpu_eh[] = { { ICE_MAC_IPV4_GTPU_IPV4_FRAG, ICE_PTYPE_ATTR_GTP_PDU_EH }, { ICE_MAC_IPV4_GTPU_IPV4_PAY, ICE_PTYPE_ATTR_GTP_PDU_EH }, @@ -1400,7 +1423,7 @@ ice_flow_add_prof_sync(struct ice_hw *hw, enum ice_block blk, /* Add a HW profile for this flow profile */ status = ice_add_prof(hw, blk, prof_id, (u8 *)params->ptypes, params->attr, params->attr_cnt, params->es, - params->mask, symm); + params->mask, symm, true); if (status) { ice_debug(hw, ICE_DBG_FLOW, "Error adding a HW flow profile\n"); goto out; @@ -1523,6 +1546,90 @@ ice_flow_disassoc_prof(struct ice_hw *hw, enum ice_block blk, return status; } +#define FLAG_GTP_EH_PDU_LINK BIT_ULL(13) +#define FLAG_GTP_EH_PDU BIT_ULL(14) + +#define HI_BYTE_IN_WORD GENMASK(15, 8) +#define LO_BYTE_IN_WORD GENMASK(7, 0) + +#define FLAG_GTPU_MSK \ + (FLAG_GTP_EH_PDU | FLAG_GTP_EH_PDU_LINK) +#define FLAG_GTPU_UP \ + (FLAG_GTP_EH_PDU | FLAG_GTP_EH_PDU_LINK) +#define FLAG_GTPU_DW FLAG_GTP_EH_PDU + +/** + * ice_flow_set_parser_prof - Set flow profile based on the parsed profile info + * @hw: pointer to the HW struct + * @dest_vsi: dest VSI + * @fdir_vsi: fdir programming VSI + * @prof: stores parsed profile info from raw flow + * @blk: classification blk + * + * Return: 0 on success or negative errno on failure. + */ +int +ice_flow_set_parser_prof(struct ice_hw *hw, u16 dest_vsi, u16 fdir_vsi, + struct ice_parser_profile *prof, enum ice_block blk) +{ + u64 id = find_first_bit(prof->ptypes, ICE_FLOW_PTYPE_MAX); + struct ice_flow_prof_params *params __free(kfree); + u8 fv_words = hw->blk[blk].es.fvw; + int status; + int i, idx; + + params = kzalloc(sizeof(*params), GFP_KERNEL); + if (!params) + return -ENOMEM; + + for (i = 0; i < ICE_MAX_FV_WORDS; i++) { + params->es[i].prot_id = ICE_PROT_INVALID; + params->es[i].off = ICE_FV_OFFSET_INVAL; + } + + for (i = 0; i < prof->fv_num; i++) { + if (hw->blk[blk].es.reverse) + idx = fv_words - i - 1; + else + idx = i; + params->es[idx].prot_id = prof->fv[i].proto_id; + params->es[idx].off = prof->fv[i].offset; + params->mask[idx] = (((prof->fv[i].msk) << BITS_PER_BYTE) & + HI_BYTE_IN_WORD) | + (((prof->fv[i].msk) >> BITS_PER_BYTE) & + LO_BYTE_IN_WORD); + } + + switch (prof->flags) { + case FLAG_GTPU_DW: + params->attr = ice_attr_gtpu_down; + params->attr_cnt = ARRAY_SIZE(ice_attr_gtpu_down); + break; + case FLAG_GTPU_UP: + params->attr = ice_attr_gtpu_up; + params->attr_cnt = ARRAY_SIZE(ice_attr_gtpu_up); + break; + default: + if (prof->flags_msk & FLAG_GTPU_MSK) { + params->attr = ice_attr_gtpu_session; + params->attr_cnt = ARRAY_SIZE(ice_attr_gtpu_session); + } + break; + } + + status = ice_add_prof(hw, blk, id, (u8 *)prof->ptypes, + params->attr, params->attr_cnt, + params->es, params->mask, false, false); + if (status) + return status; + + status = ice_flow_assoc_fdir_prof(hw, blk, dest_vsi, fdir_vsi, id); + if (status) + ice_rem_prof(hw, blk, id); + + return status; +} + /** * ice_flow_add_prof - Add a flow profile for packet segments and matched fields * @hw: pointer to the HW struct diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h index 2fd2e0cb483d..6cb7bb879c98 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.h +++ b/drivers/net/ethernet/intel/ice/ice_flow.h @@ -5,6 +5,7 @@ #define _ICE_FLOW_H_ #include "ice_flex_type.h" +#include "ice_parser.h" #define ICE_FLOW_ENTRY_HANDLE_INVAL 0 #define ICE_FLOW_FLD_OFF_INVAL 0xffff @@ -326,6 +327,7 @@ enum ice_rss_cfg_hdr_type { ICE_RSS_ANY_HEADERS }; +struct ice_vsi; struct ice_rss_hash_cfg { u32 addl_hdrs; /* protocol header fields */ u64 hash_flds; /* hash bit field (ICE_FLOW_HASH_*) to configure */ @@ -445,6 +447,9 @@ ice_flow_add_prof(struct ice_hw *hw, enum ice_block blk, enum ice_flow_dir dir, bool symm, struct ice_flow_prof **prof); int ice_flow_rem_prof(struct ice_hw *hw, enum ice_block blk, u64 prof_id); int +ice_flow_set_parser_prof(struct ice_hw *hw, u16 dest_vsi, u16 fdir_vsi, + struct ice_parser_profile *prof, enum ice_block blk); +int ice_flow_add_entry(struct ice_hw *hw, enum ice_block blk, u64 prof_id, u64 entry_id, u16 vsi, enum ice_flow_priority prio, void *data, u64 *entry_h); diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c index 319a2d6fe26c..70c201f569ce 100644 --- a/drivers/net/ethernet/intel/ice/ice_fw_update.c +++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c @@ -1,11 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) 2018-2019, Intel Corporation. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/uuid.h> #include <linux/crc32.h> #include <linux/pldmfw.h> #include "ice.h" +#include "ice_lib.h" #include "ice_fw_update.h" struct ice_fwu_priv { @@ -125,6 +126,10 @@ ice_check_component_response(struct ice_pf *pf, u16 id, u8 response, u8 code, case ICE_AQ_NVM_PASS_COMP_CAN_NOT_BE_UPDATED: dev_info(dev, "firmware has rejected updating %s\n", component); break; + case ICE_AQ_NVM_PASS_COMP_PARTIAL_CHECK: + if (ice_is_recovery_mode(&pf->hw)) + return 0; + break; } switch (code) { @@ -286,10 +291,9 @@ ice_send_component_table(struct pldmfw *context, struct pldmfw_component *compon * * Returns: zero on success, or a negative error code on failure. */ -static int -ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, - u16 block_size, u8 *block, bool last_cmd, - u8 *reset_level, struct netlink_ext_ack *extack) +int ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, + u16 block_size, u8 *block, bool last_cmd, + u8 *reset_level, struct netlink_ext_ack *extack) { u16 completion_module, completion_retval; struct device *dev = ice_pf_to_dev(pf); @@ -1005,13 +1009,20 @@ int ice_devlink_flash_update(struct devlink *devlink, return -EOPNOTSUPP; } - if (!hw->dev_caps.common_cap.nvm_unified_update) { + if (!hw->dev_caps.common_cap.nvm_unified_update && !ice_is_recovery_mode(hw)) { NL_SET_ERR_MSG_MOD(extack, "Current firmware does not support unified update"); return -EOPNOTSUPP; } memset(&priv, 0, sizeof(priv)); + if (params->component && strcmp(params->component, "fw.mgmt") == 0) { + priv.context.mode = PLDMFW_UPDATE_MODE_SINGLE_COMPONENT; + priv.context.component_identifier = NVM_COMP_ID_NVM; + } else if (params->component) { + return -EOPNOTSUPP; + } + /* the E822 device needs a slightly different ops */ if (hw->mac_type == ICE_MAC_GENERIC) priv.context.ops = &ice_fwu_ops_e822; diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.h b/drivers/net/ethernet/intel/ice/ice_fw_update.h index 750574885716..04b200462757 100644 --- a/drivers/net/ethernet/intel/ice/ice_fw_update.h +++ b/drivers/net/ethernet/intel/ice/ice_fw_update.h @@ -9,5 +9,8 @@ int ice_devlink_flash_update(struct devlink *devlink, struct netlink_ext_ack *extack); int ice_get_pending_updates(struct ice_pf *pf, u8 *pending, struct netlink_ext_ack *extack); +int ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, + u16 block_size, u8 *block, bool last_cmd, + u8 *reset_level, struct netlink_ext_ack *extack); #endif diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c index c8ea1af51ad3..6b26290452d4 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.c +++ b/drivers/net/ethernet/intel/ice/ice_gnss.c @@ -182,7 +182,7 @@ static struct gnss_serial *ice_gnss_struct_init(struct ice_pf *pf) pf->gnss_serial = gnss; kthread_init_delayed_work(&gnss->read_work, ice_gnss_read); - kworker = kthread_create_worker(0, "ice-gnss-%s", dev_name(dev)); + kworker = kthread_run_worker(0, "ice-gnss-%s", dev_name(dev)); if (IS_ERR(kworker)) { kfree(gnss); return NULL; @@ -381,32 +381,23 @@ void ice_gnss_exit(struct ice_pf *pf) } /** - * ice_gnss_is_gps_present - Check if GPS HW is present + * ice_gnss_is_module_present - Check if GNSS HW is present * @hw: pointer to HW struct + * + * Return: true when GNSS is present, false otherwise. */ -bool ice_gnss_is_gps_present(struct ice_hw *hw) +bool ice_gnss_is_module_present(struct ice_hw *hw) { - if (!hw->func_caps.ts_func_info.src_tmr_owned) - return false; + int err; + u8 data; - if (!ice_is_gps_in_netlist(hw)) + if (!hw->func_caps.ts_func_info.src_tmr_owned || + !ice_is_gps_in_netlist(hw)) return false; -#if IS_ENABLED(CONFIG_PTP_1588_CLOCK) - if (ice_is_e810t(hw)) { - int err; - u8 data; - - err = ice_read_pca9575_reg_e810t(hw, ICE_PCA9575_P0_IN, &data); - if (err || !!(data & ICE_E810T_P0_GNSS_PRSNT_N)) - return false; - } else { - return false; - } -#else - if (!ice_is_e810t(hw)) + err = ice_read_pca9575_reg(hw, ICE_PCA9575_P0_IN, &data); + if (err || !!(data & ICE_P0_GNSS_PRSNT_N)) return false; -#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ return true; } diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.h b/drivers/net/ethernet/intel/ice/ice_gnss.h index 75e567ad7059..15daf603ed7b 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.h +++ b/drivers/net/ethernet/intel/ice/ice_gnss.h @@ -37,11 +37,11 @@ struct gnss_serial { #if IS_ENABLED(CONFIG_GNSS) void ice_gnss_init(struct ice_pf *pf); void ice_gnss_exit(struct ice_pf *pf); -bool ice_gnss_is_gps_present(struct ice_hw *hw); +bool ice_gnss_is_module_present(struct ice_hw *hw); #else static inline void ice_gnss_init(struct ice_pf *pf) { } static inline void ice_gnss_exit(struct ice_pf *pf) { } -static inline bool ice_gnss_is_gps_present(struct ice_hw *hw) +static inline bool ice_gnss_is_module_present(struct ice_hw *hw) { return false; } diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index cfac1d432c15..aa4bfbcf85d2 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -6,6 +6,14 @@ #ifndef _ICE_HW_AUTOGEN_H_ #define _ICE_HW_AUTOGEN_H_ +#define GLCOMM_QUANTA_PROF(_i) (0x002D2D68 + ((_i) * 4)) +#define GLCOMM_QUANTA_PROF_MAX_INDEX 15 +#define GLCOMM_QUANTA_PROF_QUANTA_SIZE_S 0 +#define GLCOMM_QUANTA_PROF_QUANTA_SIZE_M ICE_M(0x3FFF, 0) +#define GLCOMM_QUANTA_PROF_MAX_CMD_S 16 +#define GLCOMM_QUANTA_PROF_MAX_CMD_M ICE_M(0xFF, 16) +#define GLCOMM_QUANTA_PROF_MAX_DESC_S 24 +#define GLCOMM_QUANTA_PROF_MAX_DESC_M ICE_M(0x3F, 24) #define QTX_COMM_DBELL(_DBQM) (0x002C0000 + ((_DBQM) * 4)) #define QTX_COMM_HEAD(_DBQM) (0x000E0000 + ((_DBQM) * 4)) #define QTX_COMM_HEAD_HEAD_S 0 @@ -157,6 +165,8 @@ #define GLGEN_RTRIG_CORER_M BIT(0) #define GLGEN_RTRIG_GLOBR_M BIT(1) #define GLGEN_STAT 0x000B612C +#define GLGEN_SWITCH_MODE_CONFIG 0x000B81E0 +#define GLGEN_SWITCH_MODE_CONFIG_25X4_QUAD_M BIT(2) #define GLGEN_VFLRSTAT(_i) (0x00093A04 + ((_i) * 4)) #define PFGEN_CTRL 0x00091000 #define PFGEN_CTRL_PFSWR_M BIT(0) @@ -177,6 +187,8 @@ #define GLINT_CTL_ITR_GRAN_50_M ICE_M(0xF, 24) #define GLINT_CTL_ITR_GRAN_25_S 28 #define GLINT_CTL_ITR_GRAN_25_M ICE_M(0xF, 28) +#define GLGEN_MAC_LINK_TOPO 0x000B81DC +#define GLGEN_MAC_LINK_TOPO_LINK_TOPO_M GENMASK(1, 0) #define GLINT_DYN_CTL(_INT) (0x00160000 + ((_INT) * 4)) #define GLINT_DYN_CTL_INTENA_M BIT(0) #define GLINT_DYN_CTL_CLEARPBA_M BIT(1) @@ -529,11 +541,26 @@ #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_TS_TX_MEM_VALID_H 0x001E2020 +#define E830_PRTMAC_TS_TX_MEM_VALID_L 0x001E2000 #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 E830_PRTTSYN_TXTIME_H(_i) (0x001E5800 + ((_i) * 32)) +#define E830_PRTTSYN_TXTIME_L(_i) (0x001E5000 + ((_i) * 32)) +#define E830_GLPTM_ART_CTL 0x00088B50 +#define E830_GLPTM_ART_CTL_ACTIVE_M BIT(0) +#define E830_GLPTM_ART_TIME_H 0x00088B54 +#define E830_GLPTM_ART_TIME_L 0x00088B58 +#define E830_GLTSYN_PTMTIME_H(_i) (0x00088B48 + ((_i) * 4)) +#define E830_GLTSYN_PTMTIME_L(_i) (0x00088B40 + ((_i) * 4)) +#define E830_PFPTM_SEM 0x00088B00 +#define E830_PFPTM_SEM_BUSY_M BIT(0) #define VFINT_DYN_CTLN(_i) (0x00003800 + ((_i) * 4)) #define VFINT_DYN_CTLN_CLEARPBA_M BIT(1) +#define E830_MBX_PF_IN_FLIGHT_VF_MSGS_THRESH 0x00234000 +#define E830_MBX_VF_DEC_TRIG(_VF) (0x00233800 + (_VF) * 4) +#define E830_MBX_VF_IN_FLIGHT_MSGS_AT_PF_CNT(_VF) (0x00233000 + (_VF) * 4) #endif /* _ICE_HW_AUTOGEN_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_hwmon.c b/drivers/net/ethernet/intel/ice/ice_hwmon.c index e4c2c1bff6c0..b7aa6812510a 100644 --- a/drivers/net/ethernet/intel/ice/ice_hwmon.c +++ b/drivers/net/ethernet/intel/ice/ice_hwmon.c @@ -96,7 +96,7 @@ static bool ice_is_internal_reading_supported(struct ice_pf *pf) unsigned long sensors = pf->hw.dev_caps.supported_sensors; - return _test_bit(ICE_SENSOR_SUPPORT_E810_INT_TEMP_BIT, &sensors); + return test_bit(ICE_SENSOR_SUPPORT_E810_INT_TEMP_BIT, &sensors); }; void ice_hwmon_init(struct ice_pf *pf) diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c index 145b27f2a4ce..6ab53e430f91 100644 --- a/drivers/net/ethernet/intel/ice/ice_idc.c +++ b/drivers/net/ethernet/intel/ice/ice_idc.c @@ -9,22 +9,25 @@ static DEFINE_XARRAY_ALLOC1(ice_aux_id); /** - * ice_get_auxiliary_drv - retrieve iidc_auxiliary_drv struct - * @pf: pointer to PF struct + * ice_get_auxiliary_drv - retrieve iidc_rdma_core_auxiliary_drv struct + * @cdev: pointer to iidc_rdma_core_dev_info struct * * This function has to be called with a device_lock on the - * pf->adev.dev to avoid race conditions. + * cdev->adev.dev to avoid race conditions. + * + * Return: pointer to the matched auxiliary driver struct */ -static struct iidc_auxiliary_drv *ice_get_auxiliary_drv(struct ice_pf *pf) +static struct iidc_rdma_core_auxiliary_drv * +ice_get_auxiliary_drv(struct iidc_rdma_core_dev_info *cdev) { struct auxiliary_device *adev; - adev = pf->adev; + adev = cdev->adev; if (!adev || !adev->dev.driver) return NULL; - return container_of(adev->dev.driver, struct iidc_auxiliary_drv, - adrv.driver); + return container_of(adev->dev.driver, + struct iidc_rdma_core_auxiliary_drv, adrv.driver); } /** @@ -32,44 +35,54 @@ static struct iidc_auxiliary_drv *ice_get_auxiliary_drv(struct ice_pf *pf) * @pf: pointer to PF struct * @event: event struct */ -void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_event *event) +void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_rdma_event *event) { - struct iidc_auxiliary_drv *iadrv; + struct iidc_rdma_core_auxiliary_drv *iadrv; + struct iidc_rdma_core_dev_info *cdev; if (WARN_ON_ONCE(!in_task())) return; + cdev = pf->cdev_info; + if (!cdev) + return; + mutex_lock(&pf->adev_mutex); - if (!pf->adev) + if (!cdev->adev) goto finish; - device_lock(&pf->adev->dev); - iadrv = ice_get_auxiliary_drv(pf); + device_lock(&cdev->adev->dev); + iadrv = ice_get_auxiliary_drv(cdev); if (iadrv && iadrv->event_handler) - iadrv->event_handler(pf, event); - device_unlock(&pf->adev->dev); + iadrv->event_handler(cdev, event); + device_unlock(&cdev->adev->dev); finish: mutex_unlock(&pf->adev_mutex); } /** * ice_add_rdma_qset - Add Leaf Node for RDMA Qset - * @pf: PF struct + * @cdev: pointer to iidc_rdma_core_dev_info struct * @qset: Resource to be allocated + * + * Return: Zero on success or error code encountered */ -int ice_add_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset) +int ice_add_rdma_qset(struct iidc_rdma_core_dev_info *cdev, + struct iidc_rdma_qset_params *qset) { u16 max_rdmaqs[ICE_MAX_TRAFFIC_CLASS]; struct ice_vsi *vsi; struct device *dev; + struct ice_pf *pf; u32 qset_teid; u16 qs_handle; int status; int i; - if (WARN_ON(!pf || !qset)) + if (WARN_ON(!cdev || !qset)) return -EINVAL; + pf = pci_get_drvdata(cdev->pdev); dev = ice_pf_to_dev(pf); if (!ice_is_rdma_ena(pf)) @@ -100,7 +113,6 @@ int ice_add_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset) dev_err(dev, "Failed VSI RDMA Qset enable\n"); return status; } - vsi->qset_handle[qset->tc] = qset->qs_handle; qset->teid = qset_teid; return 0; @@ -109,18 +121,23 @@ EXPORT_SYMBOL_GPL(ice_add_rdma_qset); /** * ice_del_rdma_qset - Delete leaf node for RDMA Qset - * @pf: PF struct + * @cdev: pointer to iidc_rdma_core_dev_info struct * @qset: Resource to be freed + * + * Return: Zero on success, error code on failure */ -int ice_del_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset) +int ice_del_rdma_qset(struct iidc_rdma_core_dev_info *cdev, + struct iidc_rdma_qset_params *qset) { struct ice_vsi *vsi; + struct ice_pf *pf; u32 teid; u16 q_id; - if (WARN_ON(!pf || !qset)) + if (WARN_ON(!cdev || !qset)) return -EINVAL; + pf = pci_get_drvdata(cdev->pdev); vsi = ice_find_vsi(pf, qset->vport_id); if (!vsi) { dev_err(ice_pf_to_dev(pf), "RDMA Invalid VSI\n"); @@ -130,36 +147,36 @@ int ice_del_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset) q_id = qset->qs_handle; teid = qset->teid; - vsi->qset_handle[qset->tc] = 0; - return ice_dis_vsi_rdma_qset(vsi->port_info, 1, &teid, &q_id); } EXPORT_SYMBOL_GPL(ice_del_rdma_qset); /** * ice_rdma_request_reset - accept request from RDMA to perform a reset - * @pf: struct for PF + * @cdev: pointer to iidc_rdma_core_dev_info struct * @reset_type: type of reset + * + * Return: Zero on success, error code on failure */ -int ice_rdma_request_reset(struct ice_pf *pf, enum iidc_reset_type reset_type) +int ice_rdma_request_reset(struct iidc_rdma_core_dev_info *cdev, + enum iidc_rdma_reset_type reset_type) { enum ice_reset_req reset; + struct ice_pf *pf; - if (WARN_ON(!pf)) + if (WARN_ON(!cdev)) return -EINVAL; + pf = pci_get_drvdata(cdev->pdev); + switch (reset_type) { - case IIDC_PFR: + case IIDC_FUNC_RESET: reset = ICE_RESET_PFR; break; - case IIDC_CORER: + case IIDC_DEV_RESET: reset = ICE_RESET_CORER; break; - case IIDC_GLOBR: - reset = ICE_RESET_GLOBR; - break; default: - dev_err(ice_pf_to_dev(pf), "incorrect reset request\n"); return -EINVAL; } @@ -169,18 +186,23 @@ EXPORT_SYMBOL_GPL(ice_rdma_request_reset); /** * ice_rdma_update_vsi_filter - update main VSI filters for RDMA - * @pf: pointer to struct for PF + * @cdev: pointer to iidc_rdma_core_dev_info struct * @vsi_id: VSI HW idx to update filter on * @enable: bool whether to enable or disable filters + * + * Return: Zero on success, error code on failure */ -int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable) +int ice_rdma_update_vsi_filter(struct iidc_rdma_core_dev_info *cdev, + u16 vsi_id, bool enable) { struct ice_vsi *vsi; + struct ice_pf *pf; int status; - if (WARN_ON(!pf)) + if (WARN_ON(!cdev)) return -EINVAL; + pf = pci_get_drvdata(cdev->pdev); vsi = ice_find_vsi(pf, vsi_id); if (!vsi) return -EINVAL; @@ -201,88 +223,54 @@ int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable) EXPORT_SYMBOL_GPL(ice_rdma_update_vsi_filter); /** - * ice_get_qos_params - parse QoS params for RDMA consumption - * @pf: pointer to PF struct - * @qos: set of QoS values - */ -void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos) -{ - struct ice_dcbx_cfg *dcbx_cfg; - unsigned int i; - u32 up2tc; - - dcbx_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; - up2tc = rd32(&pf->hw, PRTDCB_TUP2TC); - - qos->num_tc = ice_dcb_get_num_tc(dcbx_cfg); - for (i = 0; i < IIDC_MAX_USER_PRIORITY; i++) - qos->up2tc[i] = (up2tc >> (i * 3)) & 0x7; - - for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) - qos->tc_info[i].rel_bw = dcbx_cfg->etscfg.tcbwtable[i]; - - qos->pfc_mode = dcbx_cfg->pfc_mode; - if (qos->pfc_mode == IIDC_DSCP_PFC_MODE) - for (i = 0; i < IIDC_MAX_DSCP_MAPPING; i++) - qos->dscp_map[i] = dcbx_cfg->dscp_map[i]; -} -EXPORT_SYMBOL_GPL(ice_get_qos_params); - -/** - * ice_alloc_rdma_qvectors - Allocate vector resources for RDMA driver - * @pf: board private structure to initialize + * ice_alloc_rdma_qvector - alloc vector resources reserved for RDMA driver + * @cdev: pointer to iidc_rdma_core_dev_info struct + * @entry: MSI-X entry to be removed + * + * Return: Zero on success, error code on failure */ -static int ice_alloc_rdma_qvectors(struct ice_pf *pf) +int ice_alloc_rdma_qvector(struct iidc_rdma_core_dev_info *cdev, + struct msix_entry *entry) { - if (ice_is_rdma_ena(pf)) { - int i; - - pf->msix_entries = kcalloc(pf->num_rdma_msix, - sizeof(*pf->msix_entries), - GFP_KERNEL); - if (!pf->msix_entries) - return -ENOMEM; + struct msi_map map; + struct ice_pf *pf; - /* RDMA is the only user of pf->msix_entries array */ - pf->rdma_base_vector = 0; + if (WARN_ON(!cdev)) + return -EINVAL; - for (i = 0; i < pf->num_rdma_msix; i++) { - struct msix_entry *entry = &pf->msix_entries[i]; - struct msi_map map; + pf = pci_get_drvdata(cdev->pdev); + map = ice_alloc_irq(pf, true); + if (map.index < 0) + return -ENOMEM; - map = ice_alloc_irq(pf, false); - if (map.index < 0) - break; + entry->entry = map.index; + entry->vector = map.virq; - entry->entry = map.index; - entry->vector = map.virq; - } - } return 0; } +EXPORT_SYMBOL_GPL(ice_alloc_rdma_qvector); /** * ice_free_rdma_qvector - free vector resources reserved for RDMA driver - * @pf: board private structure to initialize + * @cdev: pointer to iidc_rdma_core_dev_info struct + * @entry: MSI-X entry to be removed */ -static void ice_free_rdma_qvector(struct ice_pf *pf) +void ice_free_rdma_qvector(struct iidc_rdma_core_dev_info *cdev, + struct msix_entry *entry) { - int i; + struct msi_map map; + struct ice_pf *pf; - if (!pf->msix_entries) + if (WARN_ON(!cdev || !entry)) return; - for (i = 0; i < pf->num_rdma_msix; i++) { - struct msi_map map; - - map.index = pf->msix_entries[i].entry; - map.virq = pf->msix_entries[i].vector; - ice_free_irq(pf, map); - } + pf = pci_get_drvdata(cdev->pdev); - kfree(pf->msix_entries); - pf->msix_entries = NULL; + map.index = entry->entry; + map.virq = entry->vector; + ice_free_irq(pf, map); } +EXPORT_SYMBOL_GPL(ice_free_rdma_qvector); /** * ice_adev_release - function to be mapped to AUX dev's release op @@ -290,19 +278,23 @@ static void ice_free_rdma_qvector(struct ice_pf *pf) */ static void ice_adev_release(struct device *dev) { - struct iidc_auxiliary_dev *iadev; + struct iidc_rdma_core_auxiliary_dev *iadev; - iadev = container_of(dev, struct iidc_auxiliary_dev, adev.dev); + iadev = container_of(dev, struct iidc_rdma_core_auxiliary_dev, + adev.dev); kfree(iadev); } /** * ice_plug_aux_dev - allocate and register AUX device * @pf: pointer to pf struct + * + * Return: Zero on success, error code on failure */ int ice_plug_aux_dev(struct ice_pf *pf) { - struct iidc_auxiliary_dev *iadev; + struct iidc_rdma_core_auxiliary_dev *iadev; + struct iidc_rdma_core_dev_info *cdev; struct auxiliary_device *adev; int ret; @@ -312,17 +304,22 @@ int ice_plug_aux_dev(struct ice_pf *pf) if (!ice_is_rdma_ena(pf)) return 0; + cdev = pf->cdev_info; + if (!cdev) + return -ENODEV; + iadev = kzalloc(sizeof(*iadev), GFP_KERNEL); if (!iadev) return -ENOMEM; adev = &iadev->adev; - iadev->pf = pf; + iadev->cdev_info = cdev; adev->id = pf->aux_idx; adev->dev.release = ice_adev_release; adev->dev.parent = &pf->pdev->dev; - adev->name = pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2 ? "roce" : "iwarp"; + adev->name = cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_ROCEV2 ? + "roce" : "iwarp"; ret = auxiliary_device_init(adev); if (ret) { @@ -337,7 +334,7 @@ int ice_plug_aux_dev(struct ice_pf *pf) } mutex_lock(&pf->adev_mutex); - pf->adev = adev; + cdev->adev = adev; mutex_unlock(&pf->adev_mutex); return 0; @@ -351,8 +348,8 @@ void ice_unplug_aux_dev(struct ice_pf *pf) struct auxiliary_device *adev; mutex_lock(&pf->adev_mutex); - adev = pf->adev; - pf->adev = NULL; + adev = pf->cdev_info->adev; + pf->cdev_info->adev = NULL; mutex_unlock(&pf->adev_mutex); if (adev) { @@ -367,7 +364,9 @@ void ice_unplug_aux_dev(struct ice_pf *pf) */ int ice_init_rdma(struct ice_pf *pf) { + struct iidc_rdma_priv_dev_info *privd; struct device *dev = &pf->pdev->dev; + struct iidc_rdma_core_dev_info *cdev; int ret; if (!ice_is_rdma_ena(pf)) { @@ -375,30 +374,50 @@ int ice_init_rdma(struct ice_pf *pf) return 0; } + cdev = kzalloc(sizeof(*cdev), GFP_KERNEL); + if (!cdev) + return -ENOMEM; + + pf->cdev_info = cdev; + + privd = kzalloc(sizeof(*privd), GFP_KERNEL); + if (!privd) { + ret = -ENOMEM; + goto err_privd_alloc; + } + + privd->pf_id = pf->hw.pf_id; ret = xa_alloc(&ice_aux_id, &pf->aux_idx, NULL, XA_LIMIT(1, INT_MAX), GFP_KERNEL); if (ret) { dev_err(dev, "Failed to allocate device ID for AUX driver\n"); - return -ENOMEM; + ret = -ENOMEM; + goto err_alloc_xa; } - /* Reserve vector resources */ - ret = ice_alloc_rdma_qvectors(pf); - if (ret < 0) { - dev_err(dev, "failed to reserve vectors for RDMA\n"); - goto err_reserve_rdma_qvector; - } - pf->rdma_mode |= IIDC_RDMA_PROTOCOL_ROCEV2; + cdev->iidc_priv = privd; + privd->netdev = pf->vsi[0]->netdev; + + privd->hw_addr = (u8 __iomem *)pf->hw.hw_addr; + cdev->pdev = pf->pdev; + privd->vport_id = pf->vsi[0]->vsi_num; + + pf->cdev_info->rdma_protocol |= IIDC_RDMA_PROTOCOL_ROCEV2; + ice_setup_dcb_qos_info(pf, &privd->qos_info); ret = ice_plug_aux_dev(pf); if (ret) goto err_plug_aux_dev; return 0; err_plug_aux_dev: - ice_free_rdma_qvector(pf); -err_reserve_rdma_qvector: - pf->adev = NULL; + pf->cdev_info->adev = NULL; xa_erase(&ice_aux_id, pf->aux_idx); +err_alloc_xa: + kfree(privd); +err_privd_alloc: + kfree(cdev); + pf->cdev_info = NULL; + return ret; } @@ -412,6 +431,8 @@ void ice_deinit_rdma(struct ice_pf *pf) return; ice_unplug_aux_dev(pf); - ice_free_rdma_qvector(pf); xa_erase(&ice_aux_id, pf->aux_idx); + kfree(pf->cdev_info->iidc_priv); + kfree(pf->cdev_info); + pf->cdev_info = NULL; } diff --git a/drivers/net/ethernet/intel/ice/ice_idc_int.h b/drivers/net/ethernet/intel/ice/ice_idc_int.h index 4b0c86757df9..17dbfcfb6a2a 100644 --- a/drivers/net/ethernet/intel/ice/ice_idc_int.h +++ b/drivers/net/ethernet/intel/ice/ice_idc_int.h @@ -4,10 +4,11 @@ #ifndef _ICE_IDC_INT_H_ #define _ICE_IDC_INT_H_ -#include <linux/net/intel/iidc.h> +#include <linux/net/intel/iidc_rdma.h> +#include <linux/net/intel/iidc_rdma_ice.h> struct ice_pf; -void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_event *event); +void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_rdma_event *event); #endif /* !_ICE_IDC_INT_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_irq.c b/drivers/net/ethernet/intel/ice/ice_irq.c index ad82ff7d1995..30801fd375f0 100644 --- a/drivers/net/ethernet/intel/ice/ice_irq.c +++ b/drivers/net/ethernet/intel/ice/ice_irq.c @@ -20,6 +20,19 @@ ice_init_irq_tracker(struct ice_pf *pf, unsigned int max_vectors, xa_init_flags(&pf->irq_tracker.entries, XA_FLAGS_ALLOC); } +static int +ice_init_virt_irq_tracker(struct ice_pf *pf, u32 base, u32 num_entries) +{ + pf->virt_irq_tracker.bm = bitmap_zalloc(num_entries, GFP_KERNEL); + if (!pf->virt_irq_tracker.bm) + return -ENOMEM; + + pf->virt_irq_tracker.num_entries = num_entries; + pf->virt_irq_tracker.base = base; + + return 0; +} + /** * ice_deinit_irq_tracker - free xarray tracker * @pf: board private structure @@ -29,6 +42,11 @@ static void ice_deinit_irq_tracker(struct ice_pf *pf) xa_destroy(&pf->irq_tracker.entries); } +static void ice_deinit_virt_irq_tracker(struct ice_pf *pf) +{ + bitmap_free(pf->virt_irq_tracker.bm); +} + /** * ice_free_irq_res - free a block of resources * @pf: board private structure @@ -45,7 +63,7 @@ static void ice_free_irq_res(struct ice_pf *pf, u16 index) /** * ice_get_irq_res - get an interrupt resource * @pf: board private structure - * @dyn_only: force entry to be dynamically allocated + * @dyn_allowed: allow entry to be dynamically allocated * * Allocate new irq entry in the free slot of the tracker. Since xarray * is used, always allocate new entry at the lowest possible index. Set @@ -53,11 +71,12 @@ static void ice_free_irq_res(struct ice_pf *pf, u16 index) * * Returns allocated irq entry or NULL on failure. */ -static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only) +static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, + bool dyn_allowed) { - struct xa_limit limit = { .max = pf->irq_tracker.num_entries, + struct xa_limit limit = { .max = pf->irq_tracker.num_entries - 1, .min = 0 }; - unsigned int num_static = pf->irq_tracker.num_static; + unsigned int num_static = pf->irq_tracker.num_static - 1; struct ice_irq_entry *entry; unsigned int index; int ret; @@ -66,9 +85,9 @@ static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only) if (!entry) return NULL; - /* skip preallocated entries if the caller says so */ - if (dyn_only) - limit.min = num_static; + /* only already allocated if the caller says so */ + if (!dyn_allowed) + limit.max = num_static; ret = xa_alloc(&pf->irq_tracker.entries, &index, entry, limit, GFP_KERNEL); @@ -78,161 +97,18 @@ static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only) entry = NULL; } else { entry->index = index; - entry->dynamic = index >= num_static; + entry->dynamic = index > num_static; } return entry; } -/** - * ice_reduce_msix_usage - Reduce usage of MSI-X vectors - * @pf: board private structure - * @v_remain: number of remaining MSI-X vectors to be distributed - * - * Reduce the usage of MSI-X vectors when entire request cannot be fulfilled. - * pf->num_lan_msix and pf->num_rdma_msix values are set based on number of - * remaining vectors. - */ -static void ice_reduce_msix_usage(struct ice_pf *pf, int v_remain) -{ - int v_rdma; - - if (!ice_is_rdma_ena(pf)) { - pf->num_lan_msix = v_remain; - return; - } - - /* RDMA needs at least 1 interrupt in addition to AEQ MSIX */ - v_rdma = ICE_RDMA_NUM_AEQ_MSIX + 1; - - if (v_remain < ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_RDMA_MSIX) { - dev_warn(ice_pf_to_dev(pf), "Not enough MSI-X vectors to support RDMA.\n"); - clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); - - pf->num_rdma_msix = 0; - pf->num_lan_msix = ICE_MIN_LAN_TXRX_MSIX; - } else if ((v_remain < ICE_MIN_LAN_TXRX_MSIX + v_rdma) || - (v_remain - v_rdma < v_rdma)) { - /* Support minimum RDMA and give remaining vectors to LAN MSIX - */ - pf->num_rdma_msix = ICE_MIN_RDMA_MSIX; - pf->num_lan_msix = v_remain - ICE_MIN_RDMA_MSIX; - } else { - /* Split remaining MSIX with RDMA after accounting for AEQ MSIX - */ - pf->num_rdma_msix = (v_remain - ICE_RDMA_NUM_AEQ_MSIX) / 2 + - ICE_RDMA_NUM_AEQ_MSIX; - pf->num_lan_msix = v_remain - pf->num_rdma_msix; - } -} - -/** - * ice_ena_msix_range - Request a range of MSIX vectors from the OS - * @pf: board private structure - * - * Compute the number of MSIX vectors wanted and request from the OS. Adjust - * device usage if there are not enough vectors. Return the number of vectors - * reserved or negative on failure. - */ -static int ice_ena_msix_range(struct ice_pf *pf) +#define ICE_RDMA_AEQ_MSIX 1 +static int ice_get_default_msix_amount(struct ice_pf *pf) { - int num_cpus, hw_num_msix, v_other, v_wanted, v_actual; - struct device *dev = ice_pf_to_dev(pf); - int err; - - hw_num_msix = pf->hw.func_caps.common_cap.num_msix_vectors; - num_cpus = num_online_cpus(); - - /* LAN miscellaneous handler */ - v_other = ICE_MIN_LAN_OICR_MSIX; - - /* Flow Director */ - if (test_bit(ICE_FLAG_FD_ENA, pf->flags)) - v_other += ICE_FDIR_MSIX; - - /* switchdev */ - v_other += ICE_ESWITCH_MSIX; - - v_wanted = v_other; - - /* LAN traffic */ - pf->num_lan_msix = num_cpus; - v_wanted += pf->num_lan_msix; - - /* RDMA auxiliary driver */ - if (ice_is_rdma_ena(pf)) { - pf->num_rdma_msix = num_cpus + ICE_RDMA_NUM_AEQ_MSIX; - v_wanted += pf->num_rdma_msix; - } - - if (v_wanted > hw_num_msix) { - int v_remain; - - dev_warn(dev, "not enough device MSI-X vectors. wanted = %d, available = %d\n", - v_wanted, hw_num_msix); - - if (hw_num_msix < ICE_MIN_MSIX) { - err = -ERANGE; - goto exit_err; - } - - v_remain = hw_num_msix - v_other; - if (v_remain < ICE_MIN_LAN_TXRX_MSIX) { - v_other = ICE_MIN_MSIX - ICE_MIN_LAN_TXRX_MSIX; - v_remain = ICE_MIN_LAN_TXRX_MSIX; - } - - ice_reduce_msix_usage(pf, v_remain); - v_wanted = pf->num_lan_msix + pf->num_rdma_msix + v_other; - - dev_notice(dev, "Reducing request to %d MSI-X vectors for LAN traffic.\n", - pf->num_lan_msix); - if (ice_is_rdma_ena(pf)) - dev_notice(dev, "Reducing request to %d MSI-X vectors for RDMA.\n", - pf->num_rdma_msix); - } - - /* actually reserve the vectors */ - v_actual = pci_alloc_irq_vectors(pf->pdev, ICE_MIN_MSIX, v_wanted, - PCI_IRQ_MSIX); - if (v_actual < 0) { - dev_err(dev, "unable to reserve MSI-X vectors\n"); - err = v_actual; - goto exit_err; - } - - if (v_actual < v_wanted) { - dev_warn(dev, "not enough OS MSI-X vectors. requested = %d, obtained = %d\n", - v_wanted, v_actual); - - if (v_actual < ICE_MIN_MSIX) { - /* error if we can't get minimum vectors */ - pci_free_irq_vectors(pf->pdev); - err = -ERANGE; - goto exit_err; - } else { - int v_remain = v_actual - v_other; - - if (v_remain < ICE_MIN_LAN_TXRX_MSIX) - v_remain = ICE_MIN_LAN_TXRX_MSIX; - - ice_reduce_msix_usage(pf, v_remain); - - dev_notice(dev, "Enabled %d MSI-X vectors for LAN traffic.\n", - pf->num_lan_msix); - - if (ice_is_rdma_ena(pf)) - dev_notice(dev, "Enabled %d MSI-X vectors for RDMA.\n", - pf->num_rdma_msix); - } - } - - return v_actual; - -exit_err: - pf->num_rdma_msix = 0; - pf->num_lan_msix = 0; - return err; + return ICE_MIN_LAN_OICR_MSIX + num_online_cpus() + + (test_bit(ICE_FLAG_FD_ENA, pf->flags) ? ICE_FDIR_MSIX : 0) + + (ice_is_rdma_ena(pf) ? num_online_cpus() + ICE_RDMA_AEQ_MSIX : 0); } /** @@ -243,6 +119,7 @@ void ice_clear_interrupt_scheme(struct ice_pf *pf) { pci_free_irq_vectors(pf->pdev); ice_deinit_irq_tracker(pf); + ice_deinit_virt_irq_tracker(pf); } /** @@ -252,27 +129,38 @@ void ice_clear_interrupt_scheme(struct ice_pf *pf) int ice_init_interrupt_scheme(struct ice_pf *pf) { int total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors; - int vectors, max_vectors; + int vectors; - vectors = ice_ena_msix_range(pf); + /* load default PF MSI-X range */ + if (!pf->msix.min) + pf->msix.min = ICE_MIN_MSIX; - if (vectors < 0) - return -ENOMEM; + if (!pf->msix.max) + pf->msix.max = min(total_vectors, + ice_get_default_msix_amount(pf)); + + pf->msix.total = total_vectors; + pf->msix.rest = total_vectors - pf->msix.max; if (pci_msix_can_alloc_dyn(pf->pdev)) - max_vectors = total_vectors; + vectors = pf->msix.min; else - max_vectors = vectors; + vectors = pf->msix.max; + + vectors = pci_alloc_irq_vectors(pf->pdev, pf->msix.min, vectors, + PCI_IRQ_MSIX); + if (vectors < 0) + return vectors; - ice_init_irq_tracker(pf, max_vectors, vectors); + ice_init_irq_tracker(pf, pf->msix.max, vectors); - return 0; + return ice_init_virt_irq_tracker(pf, pf->msix.max, pf->msix.rest); } /** * ice_alloc_irq - Allocate new interrupt vector * @pf: board private structure - * @dyn_only: force dynamic allocation of the interrupt + * @dyn_allowed: allow dynamic allocation of the interrupt * * Allocate new interrupt vector for a given owner id. * return struct msi_map with interrupt details and track @@ -285,27 +173,22 @@ int ice_init_interrupt_scheme(struct ice_pf *pf) * interrupt will be allocated with pci_msix_alloc_irq_at. * * Some callers may only support dynamically allocated interrupts. - * This is indicated with dyn_only flag. + * This is indicated with dyn_allowed flag. * * On failure, return map with negative .index. The caller * is expected to check returned map index. * */ -struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_only) +struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_allowed) { - int sriov_base_vector = pf->sriov_base_vector; struct msi_map map = { .index = -ENOENT }; struct device *dev = ice_pf_to_dev(pf); struct ice_irq_entry *entry; - entry = ice_get_irq_res(pf, dyn_only); + entry = ice_get_irq_res(pf, dyn_allowed); if (!entry) return map; - /* fail if we're about to violate SRIOV vectors space */ - if (sriov_base_vector && entry->index >= sriov_base_vector) - goto exit_free_res; - if (pci_msix_can_alloc_dyn(pf->pdev) && entry->dynamic) { map = pci_msix_alloc_irq_at(pf->pdev, entry->index, NULL); if (map.index < 0) @@ -353,26 +236,40 @@ void ice_free_irq(struct ice_pf *pf, struct msi_map map) } /** - * ice_get_max_used_msix_vector - Get the max used interrupt vector - * @pf: board private structure + * ice_virt_get_irqs - get irqs for SR-IOV usacase + * @pf: pointer to PF structure + * @needed: number of irqs to get * - * Return index of maximum used interrupt vectors with respect to the - * beginning of the MSIX table. Take into account that some interrupts - * may have been dynamically allocated after MSIX was initially enabled. + * 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 */ -int ice_get_max_used_msix_vector(struct ice_pf *pf) +int ice_virt_get_irqs(struct ice_pf *pf, u32 needed) { - unsigned long start, index, max_idx; - void *entry; + int res = bitmap_find_next_zero_area(pf->virt_irq_tracker.bm, + pf->virt_irq_tracker.num_entries, + 0, needed, 0); - /* Treat all preallocated interrupts as used */ - start = pf->irq_tracker.num_static; - max_idx = start - 1; + if (res >= pf->virt_irq_tracker.num_entries) + return -ENOENT; - xa_for_each_start(&pf->irq_tracker.entries, index, entry, start) { - if (index > max_idx) - max_idx = index; - } + bitmap_set(pf->virt_irq_tracker.bm, res, needed); + + /* conversion from number in bitmap to global irq index */ + return res + pf->virt_irq_tracker.base; +} - return max_idx; +/** + * ice_virt_free_irqs - free irqs used by the VF + * @pf: pointer to PF structure + * @index: first index to be free + * @irqs: number of irqs to free + */ +void ice_virt_free_irqs(struct ice_pf *pf, u32 index, u32 irqs) +{ + bitmap_clear(pf->virt_irq_tracker.bm, index - pf->virt_irq_tracker.base, + irqs); } diff --git a/drivers/net/ethernet/intel/ice/ice_irq.h b/drivers/net/ethernet/intel/ice/ice_irq.h index f35efc08575e..b2f9dbafd57e 100644 --- a/drivers/net/ethernet/intel/ice/ice_irq.h +++ b/drivers/net/ethernet/intel/ice/ice_irq.h @@ -15,11 +15,22 @@ struct ice_irq_tracker { u16 num_static; /* preallocated entries */ }; +struct ice_virt_irq_tracker { + unsigned long *bm; /* bitmap to track irq usage */ + u32 num_entries; + /* First MSIX vector used by SR-IOV VFs. Calculated by subtracting the + * number of MSIX vectors needed for all SR-IOV VFs from the number of + * MSIX vectors allowed on this PF. + */ + u32 base; +}; + int ice_init_interrupt_scheme(struct ice_pf *pf); void ice_clear_interrupt_scheme(struct ice_pf *pf); struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_only); void ice_free_irq(struct ice_pf *pf, struct msi_map map); -int ice_get_max_used_msix_vector(struct ice_pf *pf); +int ice_virt_get_irqs(struct ice_pf *pf, u32 needed); +void ice_virt_free_irqs(struct ice_pf *pf, u32 index, u32 irqs); #endif diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index f0e76f0a6d60..2410aee59fb2 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -202,11 +202,12 @@ static struct ice_lag *ice_lag_find_primary(struct ice_lag *lag) * @act: rule action * @recipe_id: recipe id for the new rule * @rule_idx: pointer to rule index + * @direction: ICE_FLTR_RX or ICE_FLTR_TX * @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) + u8 direction, bool add) { struct ice_sw_rule_lkup_rx_tx *s_rule; u16 s_rule_sz, vsi_num; @@ -231,9 +232,16 @@ ice_lag_cfg_fltr(struct ice_lag *lag, u32 act, u16 recipe_id, u16 *rule_idx, act |= FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M, vsi_num); - 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); + if (direction == ICE_FLTR_RX) { + s_rule->hdr.type = + cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX); + s_rule->src = cpu_to_le16(hw->port_info->lport); + } else { + s_rule->hdr.type = + cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_TX); + s_rule->src = cpu_to_le16(vsi_num); + } 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; @@ -266,9 +274,27 @@ 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; + int err; + + err = ice_lag_cfg_fltr(lag, act, lag->pf_recipe, &lag->pf_rx_rule_id, + ICE_FLTR_RX, add); + if (err) + goto err_rx; - return ice_lag_cfg_fltr(lag, act, lag->pf_recipe, - &lag->pf_rule_id, add); + act = ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_VALID_BIT | + ICE_SINGLE_ACT_LB_ENABLE; + err = ice_lag_cfg_fltr(lag, act, lag->pf_recipe, &lag->pf_tx_rule_id, + ICE_FLTR_TX, add); + if (err) + goto err_tx; + + return 0; + +err_tx: + ice_lag_cfg_fltr(lag, act, lag->pf_recipe, &lag->pf_rx_rule_id, + ICE_FLTR_RX, !add); +err_rx: + return err; } /** @@ -284,7 +310,7 @@ ice_lag_cfg_drop_fltr(struct ice_lag *lag, bool add) ICE_SINGLE_ACT_DROP; return ice_lag_cfg_fltr(lag, act, lag->lport_recipe, - &lag->lport_rule_idx, add); + &lag->lport_rule_idx, ICE_FLTR_RX, add); } /** @@ -310,7 +336,7 @@ ice_lag_cfg_pf_fltrs(struct ice_lag *lag, void *ptr) 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 (bonding_info->slave.state && lag->pf_rx_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)) @@ -319,7 +345,7 @@ ice_lag_cfg_pf_fltrs(struct ice_lag *lag, void *ptr) } /* interface becoming active - add new default VSI rule */ - if (!bonding_info->slave.state && !lag->pf_rule_id) { + if (!bonding_info->slave.state && !lag->pf_rx_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)) @@ -714,8 +740,7 @@ static void ice_lag_move_vf_nodes(struct ice_lag *lag, u8 oldport, u8 newport) 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)) + if (pf->vsi[i] && pf->vsi[i]->type == ICE_VSI_VF) ice_lag_move_single_vf_nodes(lag, oldport, newport, i); } @@ -953,8 +978,7 @@ ice_lag_reclaim_vf_nodes(struct ice_lag *lag, struct ice_hw *src_hw) 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)) + if (pf->vsi[i] && pf->vsi[i]->type == ICE_VSI_VF) ice_for_each_traffic_class(tc) ice_lag_reclaim_vf_tc(lag, src_hw, i, tc); } @@ -977,6 +1001,28 @@ static void ice_lag_link(struct ice_lag *lag) } /** + * ice_lag_config_eswitch - configure eswitch to work with LAG + * @lag: lag info struct + * @netdev: active network interface device struct + * + * Updates all port representors in eswitch to use @netdev for Tx. + * + * Configures the netdev to keep dst metadata (also used in representor Tx). + * This is required for an uplink without switchdev mode configured. + */ +static void ice_lag_config_eswitch(struct ice_lag *lag, + struct net_device *netdev) +{ + struct ice_repr *repr; + unsigned long id; + + xa_for_each(&lag->pf->eswitch.reprs, id, repr) + repr->dst->u.port_info.lower_dev = netdev; + + netif_keep_dst(netdev); +} + +/** * ice_lag_unlink - handle unlink event * @lag: LAG info struct */ @@ -997,6 +1043,9 @@ static void ice_lag_unlink(struct ice_lag *lag) ice_lag_move_vf_nodes(lag, act_port, pri_port); lag->primary = false; lag->active_port = ICE_LAG_INVALID_PORT; + + /* Config primary's eswitch back to normal operation. */ + ice_lag_config_eswitch(lag, lag->netdev); } else { struct ice_lag *primary_lag; @@ -1272,12 +1321,18 @@ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr) */ if (!primary_lag) { lag->primary = true; + if (!ice_is_switchdev_running(lag->pf)) + return; + /* Configure primary's SWID to be shared */ ice_lag_primary_swid(lag, true); primary_lag = lag; } else { u16 swid; + if (!ice_is_switchdev_running(primary_lag->pf)) + return; + 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); @@ -1395,6 +1450,7 @@ static void ice_lag_monitor_active(struct ice_lag *lag, void *ptr) ice_lag_move_vf_nodes(lag, prim_port, event_port); lag->active_port = event_port; + ice_lag_config_eswitch(lag, event_netdev); return; } @@ -1404,6 +1460,7 @@ static void ice_lag_monitor_active(struct ice_lag *lag, void *ptr) /* new active port */ ice_lag_move_vf_nodes(lag, lag->active_port, event_port); lag->active_port = event_port; + ice_lag_config_eswitch(lag, event_netdev); } else { /* port not set as currently active (e.g. new active port * has already claimed the nodes and filters @@ -1976,8 +2033,7 @@ ice_lag_move_vf_nodes_sync(struct ice_lag *lag, struct ice_hw *dest_hw) 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)) + if (pf->vsi[i] && pf->vsi[i]->type == ICE_VSI_VF) ice_for_each_traffic_class(tc) ice_lag_move_vf_nodes_tc_sync(lag, dest_hw, i, tc); @@ -2149,7 +2205,7 @@ void ice_lag_rebuild(struct ice_pf *pf) ice_lag_cfg_cp_fltr(lag, true); - if (lag->pf_rule_id) + if (lag->pf_rx_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"); diff --git a/drivers/net/ethernet/intel/ice/ice_lag.h b/drivers/net/ethernet/intel/ice/ice_lag.h index 183b38792ef2..bab2c83142a1 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.h +++ b/drivers/net/ethernet/intel/ice/ice_lag.h @@ -43,7 +43,8 @@ struct ice_lag { u8 primary:1; /* this is primary */ u16 pf_recipe; u16 lport_recipe; - u16 pf_rule_id; + u16 pf_rx_rule_id; + u16 pf_tx_rule_id; u16 cp_rule_idx; u16 lport_rule_idx; u8 role; diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h index d384ddfcb83e..77ba26538b07 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -160,64 +160,6 @@ struct ice_fltr_desc { (0x1ULL << ICE_FXD_FLTR_WB_QW1_FAIL_PROF_S) #define ICE_FXD_FLTR_WB_QW1_FAIL_PROF_YES 0x1ULL -struct ice_rx_ptype_decoded { - 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 ice_rx_ptype_outer_ip { - ICE_RX_PTYPE_OUTER_L2 = 0, - ICE_RX_PTYPE_OUTER_IP = 1, -}; - -enum ice_rx_ptype_outer_ip_ver { - ICE_RX_PTYPE_OUTER_NONE = 0, - ICE_RX_PTYPE_OUTER_IPV4 = 1, - ICE_RX_PTYPE_OUTER_IPV6 = 2, -}; - -enum ice_rx_ptype_outer_fragmented { - ICE_RX_PTYPE_NOT_FRAG = 0, - ICE_RX_PTYPE_FRAG = 1, -}; - -enum ice_rx_ptype_tunnel_type { - ICE_RX_PTYPE_TUNNEL_NONE = 0, - ICE_RX_PTYPE_TUNNEL_IP_IP = 1, - ICE_RX_PTYPE_TUNNEL_IP_GRENAT = 2, - ICE_RX_PTYPE_TUNNEL_IP_GRENAT_MAC = 3, - ICE_RX_PTYPE_TUNNEL_IP_GRENAT_MAC_VLAN = 4, -}; - -enum ice_rx_ptype_tunnel_end_prot { - ICE_RX_PTYPE_TUNNEL_END_NONE = 0, - ICE_RX_PTYPE_TUNNEL_END_IPV4 = 1, - ICE_RX_PTYPE_TUNNEL_END_IPV6 = 2, -}; - -enum ice_rx_ptype_inner_prot { - ICE_RX_PTYPE_INNER_PROT_NONE = 0, - ICE_RX_PTYPE_INNER_PROT_UDP = 1, - ICE_RX_PTYPE_INNER_PROT_TCP = 2, - ICE_RX_PTYPE_INNER_PROT_SCTP = 3, - ICE_RX_PTYPE_INNER_PROT_ICMP = 4, - ICE_RX_PTYPE_INNER_PROT_TIMESYNC = 5, -}; - -enum ice_rx_ptype_payload_layer { - ICE_RX_PTYPE_PAYLOAD_LAYER_NONE = 0, - ICE_RX_PTYPE_PAYLOAD_LAYER_PAY2 = 1, - ICE_RX_PTYPE_PAYLOAD_LAYER_PAY3 = 2, - ICE_RX_PTYPE_PAYLOAD_LAYER_PAY4 = 3, -}; - /* Rx Flex Descriptor * This descriptor is used instead of the legacy version descriptor when * ice_rlan_ctx.adv_desc is set @@ -287,7 +229,7 @@ struct ice_32b_rx_flex_desc_nic { __le16 status_error1; u8 flexi_flags2; u8 ts_low; - __le16 l2tag2_1st; + __le16 raw_csum; __le16 l2tag2_2nd; /* Qword 3 */ @@ -429,29 +371,21 @@ enum ice_rx_flex_desc_status_error_1_bits { ICE_RX_FLEX_DESC_STATUS1_LAST /* this entry must be last!!! */ }; -#define ICE_RXQ_CTX_SIZE_DWORDS 8 -#define ICE_RXQ_CTX_SZ (ICE_RXQ_CTX_SIZE_DWORDS * sizeof(u32)) #define ICE_TX_CMPLTNQ_CTX_SIZE_DWORDS 22 #define ICE_TX_DRBELL_Q_CTX_SIZE_DWORDS 5 #define GLTCLAN_CQ_CNTX(i, CQ) (GLTCLAN_CQ_CNTX0(CQ) + ((i) * 0x0800)) -/* RLAN Rx queue context data - * - * The sizes of the variables may be larger than needed due to crossing byte - * boundaries. If we do not have the width of the variable set to the correct - * size then we could end up shifting bits off the top of the variable when the - * variable is at the top of a byte and crosses over into the next byte. - */ +/* RLAN Rx queue context data */ struct ice_rlan_ctx { u16 head; - u16 cpuid; /* bigger than needed, see above for reason */ + u8 cpuid; #define ICE_RLAN_BASE_S 7 u64 base; u16 qlen; #define ICE_RLAN_CTX_DBUF_S 7 - u16 dbuf; /* bigger than needed, see above for reason */ + u8 dbuf; #define ICE_RLAN_CTX_HBUF_S 6 - u16 hbuf; /* bigger than needed, see above for reason */ + u8 hbuf; u8 dtype; u8 dsize; u8 crcstrip; @@ -459,29 +393,15 @@ struct ice_rlan_ctx { u8 hsplit_0; u8 hsplit_1; u8 showiv; - u32 rxmax; /* bigger than needed, see above for reason */ + u16 rxmax; u8 tphrdesc_ena; u8 tphwdesc_ena; u8 tphdata_ena; u8 tphhead_ena; - u16 lrxqthresh; /* bigger than needed, see above for reason */ + u8 lrxqthresh; u8 prefena; /* NOTE: normally must be set to 1 at init */ }; -struct ice_ctx_ele { - u16 offset; - u16 size_of; - u16 width; - u16 lsb; -}; - -#define ICE_CTX_STORE(_struct, _ele, _width, _lsb) { \ - .offset = offsetof(struct _struct, _ele), \ - .size_of = sizeof_field(struct _struct, _ele), \ - .width = _width, \ - .lsb = _lsb, \ -} - /* for hsplit_0 field of Rx RLAN context */ enum ice_rlan_ctx_rx_hsplit_0 { ICE_RLAN_RX_HSPLIT_0_NO_SPLIT = 0, @@ -558,10 +478,15 @@ enum ice_tx_desc_len_fields { struct ice_tx_ctx_desc { __le32 tunneling_params; __le16 l2tag2; - __le16 rsvd; + __le16 gcs; __le64 qw1; }; +#define ICE_TX_GCS_DESC_START_M GENMASK(7, 0) +#define ICE_TX_GCS_DESC_OFFSET_M GENMASK(11, 8) +#define ICE_TX_GCS_DESC_TYPE_M GENMASK(14, 12) +#define ICE_TX_GCS_DESC_CSUM_PSH 1 + #define ICE_TXD_CTX_QW1_CMD_S 4 #define ICE_TXD_CTX_QW1_CMD_M (0x7FUL << ICE_TXD_CTX_QW1_CMD_S) @@ -609,18 +534,12 @@ enum ice_tx_ctx_desc_eipt_offload { #define ICE_LAN_TXQ_MAX_QGRPS 127 #define ICE_LAN_TXQ_MAX_QDIS 1023 -/* Tx queue context data - * - * The sizes of the variables may be larger than needed due to crossing byte - * boundaries. If we do not have the width of the variable set to the correct - * size then we could end up shifting bits off the top of the variable when the - * variable is at the top of a byte and crosses over into the next byte. - */ +/* Tx queue context data */ struct ice_tlan_ctx { #define ICE_TLAN_CTX_BASE_S 7 u64 base; /* base is defined in 128-byte units */ u8 port_num; - u16 cgd_num; /* bigger than needed, see above for reason */ + u8 cgd_num; u8 pf_num; u16 vmvf_num; u8 vmvf_type; @@ -631,7 +550,7 @@ struct ice_tlan_ctx { u8 tsyn_ena; u8 internal_usage_flag; u8 alt_vlan; - u16 cpuid; /* bigger than needed, see above for reason */ + u8 cpuid; u8 wb_mode; u8 tphrd_desc; u8 tphrd; @@ -640,7 +559,7 @@ struct ice_tlan_ctx { u16 qnum_in_func; u8 itr_notification_mode; u8 adjust_prof_id; - u32 qlen; /* bigger than needed, see above for reason */ + u16 qlen; u8 quanta_prof_idx; u8 tso_ena; u16 tso_qnum; @@ -648,269 +567,6 @@ struct ice_tlan_ctx { u8 drop_ena; u8 cache_prof_idx; u8 pkt_shaper_prof_idx; - u8 int_q_state; /* width not needed - internal - DO NOT WRITE!!! */ }; -/* The ice_ptype_lkup table is used to convert from the 10-bit ptype in the - * hardware to a bit-field that can be used by SW to more easily determine the - * packet type. - * - * Macros are used to shorten the table lines and make this table human - * readable. - * - * We store the PTYPE in the top byte of the bit field - this is just so that - * we can check that the table doesn't have a row missing, as the index into - * the table should be the PTYPE. - * - * Typical work flow: - * - * IF NOT ice_ptype_lkup[ptype].known - * THEN - * Packet is unknown - * ELSE IF ice_ptype_lkup[ptype].outer_ip == ICE_RX_PTYPE_OUTER_IP - * Use the rest of the fields to look at the tunnels, inner protocols, etc - * ELSE - * Use the enum ice_rx_l2_ptype to decode the packet type - * ENDIF - */ -#define ICE_PTYPES \ - /* L2 Packet types */ \ - ICE_PTT_UNUSED_ENTRY(0), \ - ICE_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), \ - ICE_PTT_UNUSED_ENTRY(2), \ - ICE_PTT_UNUSED_ENTRY(3), \ - ICE_PTT_UNUSED_ENTRY(4), \ - ICE_PTT_UNUSED_ENTRY(5), \ - ICE_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), \ - ICE_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), \ - ICE_PTT_UNUSED_ENTRY(8), \ - ICE_PTT_UNUSED_ENTRY(9), \ - ICE_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), \ - ICE_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), \ - ICE_PTT_UNUSED_ENTRY(12), \ - ICE_PTT_UNUSED_ENTRY(13), \ - ICE_PTT_UNUSED_ENTRY(14), \ - ICE_PTT_UNUSED_ENTRY(15), \ - ICE_PTT_UNUSED_ENTRY(16), \ - ICE_PTT_UNUSED_ENTRY(17), \ - ICE_PTT_UNUSED_ENTRY(18), \ - ICE_PTT_UNUSED_ENTRY(19), \ - ICE_PTT_UNUSED_ENTRY(20), \ - ICE_PTT_UNUSED_ENTRY(21), \ - \ - /* Non Tunneled IPv4 */ \ - ICE_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3), \ - ICE_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3), \ - ICE_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP, PAY4), \ - ICE_PTT_UNUSED_ENTRY(25), \ - ICE_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP, PAY4), \ - ICE_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4), \ - ICE_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4), \ - \ - /* IPv4 --> IPv4 */ \ - ICE_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3), \ - ICE_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3), \ - ICE_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP, PAY4), \ - ICE_PTT_UNUSED_ENTRY(32), \ - ICE_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP, PAY4), \ - ICE_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), \ - ICE_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), \ - \ - /* IPv4 --> IPv6 */ \ - ICE_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3), \ - ICE_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3), \ - ICE_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP, PAY4), \ - ICE_PTT_UNUSED_ENTRY(39), \ - ICE_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP, PAY4), \ - ICE_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), \ - ICE_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), \ - \ - /* IPv4 --> GRE/NAT */ \ - ICE_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), \ - \ - /* IPv4 --> GRE/NAT --> IPv4 */ \ - ICE_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), \ - ICE_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), \ - ICE_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), \ - ICE_PTT_UNUSED_ENTRY(47), \ - ICE_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), \ - ICE_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), \ - ICE_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), \ - \ - /* IPv4 --> GRE/NAT --> IPv6 */ \ - ICE_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), \ - ICE_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), \ - ICE_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), \ - ICE_PTT_UNUSED_ENTRY(54), \ - ICE_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), \ - ICE_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), \ - ICE_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), \ - \ - /* IPv4 --> GRE/NAT --> MAC */ \ - ICE_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), \ - \ - /* IPv4 --> GRE/NAT --> MAC --> IPv4 */ \ - ICE_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), \ - ICE_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), \ - ICE_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), \ - ICE_PTT_UNUSED_ENTRY(62), \ - ICE_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), \ - ICE_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), \ - ICE_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), \ - \ - /* IPv4 --> GRE/NAT -> MAC --> IPv6 */ \ - ICE_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), \ - ICE_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), \ - ICE_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), \ - ICE_PTT_UNUSED_ENTRY(69), \ - ICE_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), \ - ICE_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), \ - ICE_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), \ - \ - /* IPv4 --> GRE/NAT --> MAC/VLAN */ \ - ICE_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), \ - \ - /* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */ \ - ICE_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), \ - ICE_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), \ - ICE_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), \ - ICE_PTT_UNUSED_ENTRY(77), \ - ICE_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), \ - ICE_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), \ - ICE_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), \ - \ - /* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */ \ - ICE_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), \ - ICE_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), \ - ICE_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), \ - ICE_PTT_UNUSED_ENTRY(84), \ - ICE_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), \ - ICE_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), \ - ICE_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), \ - \ - /* Non Tunneled IPv6 */ \ - ICE_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3), \ - ICE_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3), \ - ICE_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY4), \ - ICE_PTT_UNUSED_ENTRY(91), \ - ICE_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP, PAY4), \ - ICE_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4), \ - ICE_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4), \ - \ - /* IPv6 --> IPv4 */ \ - ICE_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3), \ - ICE_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3), \ - ICE_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP, PAY4), \ - ICE_PTT_UNUSED_ENTRY(98), \ - ICE_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP, PAY4), \ - ICE_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), \ - ICE_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), \ - \ - /* IPv6 --> IPv6 */ \ - ICE_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3), \ - ICE_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3), \ - ICE_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP, PAY4), \ - ICE_PTT_UNUSED_ENTRY(105), \ - ICE_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP, PAY4), \ - ICE_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), \ - ICE_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), \ - \ - /* IPv6 --> GRE/NAT */ \ - ICE_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), \ - \ - /* IPv6 --> GRE/NAT -> IPv4 */ \ - ICE_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), \ - ICE_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), \ - ICE_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), \ - ICE_PTT_UNUSED_ENTRY(113), \ - ICE_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), \ - ICE_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), \ - ICE_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), \ - \ - /* IPv6 --> GRE/NAT -> IPv6 */ \ - ICE_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), \ - ICE_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), \ - ICE_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), \ - ICE_PTT_UNUSED_ENTRY(120), \ - ICE_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), \ - ICE_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), \ - ICE_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), \ - \ - /* IPv6 --> GRE/NAT -> MAC */ \ - ICE_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), \ - \ - /* IPv6 --> GRE/NAT -> MAC -> IPv4 */ \ - ICE_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), \ - ICE_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), \ - ICE_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), \ - ICE_PTT_UNUSED_ENTRY(128), \ - ICE_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), \ - ICE_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), \ - ICE_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), \ - \ - /* IPv6 --> GRE/NAT -> MAC -> IPv6 */ \ - ICE_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), \ - ICE_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), \ - ICE_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), \ - ICE_PTT_UNUSED_ENTRY(135), \ - ICE_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), \ - ICE_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), \ - ICE_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), \ - \ - /* IPv6 --> GRE/NAT -> MAC/VLAN */ \ - ICE_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), \ - \ - /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */ \ - ICE_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), \ - ICE_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), \ - ICE_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), \ - ICE_PTT_UNUSED_ENTRY(143), \ - ICE_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), \ - ICE_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), \ - ICE_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), \ - \ - /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */ \ - ICE_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), \ - ICE_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), \ - ICE_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), \ - ICE_PTT_UNUSED_ENTRY(150), \ - ICE_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), \ - ICE_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), \ - ICE_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), - -#define ICE_NUM_DEFINED_PTYPES 154 - -/* macro to make the table lines short, use explicit indexing with [PTYPE] */ -#define ICE_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\ - [PTYPE] = { \ - 1, \ - ICE_RX_PTYPE_OUTER_##OUTER_IP, \ - ICE_RX_PTYPE_OUTER_##OUTER_IP_VER, \ - ICE_RX_PTYPE_##OUTER_FRAG, \ - ICE_RX_PTYPE_TUNNEL_##T, \ - ICE_RX_PTYPE_TUNNEL_END_##TE, \ - ICE_RX_PTYPE_##TEF, \ - ICE_RX_PTYPE_INNER_PROT_##I, \ - ICE_RX_PTYPE_PAYLOAD_LAYER_##PL } - -#define ICE_PTT_UNUSED_ENTRY(PTYPE) [PTYPE] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 } - -/* shorter macros makes the table fit but are terse */ -#define ICE_RX_PTYPE_NOF ICE_RX_PTYPE_NOT_FRAG -#define ICE_RX_PTYPE_FRG ICE_RX_PTYPE_FRAG - -/* Lookup table mapping in the 10-bit HW PTYPE to the bit field for decoding */ -static const struct ice_rx_ptype_decoded ice_ptype_lkup[BIT(10)] = { - ICE_PTYPES - - /* unused entries */ - [ICE_NUM_DEFINED_PTYPES ... 1023] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 } -}; - -static inline struct ice_rx_ptype_decoded ice_decode_rx_desc_ptype(u16 ptype) -{ - return ice_ptype_lkup[ptype]; -} - - #endif /* _ICE_LAN_TX_RX_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 558422120312..03bb16191237 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -7,7 +7,7 @@ #include "ice_lib.h" #include "ice_fltr.h" #include "ice_dcb_lib.h" -#include "ice_devlink.h" +#include "ice_type.h" #include "ice_vsi_vlan_ops.h" /** @@ -21,14 +21,14 @@ const char *ice_vsi_type_str(enum ice_vsi_type vsi_type) return "ICE_VSI_PF"; case ICE_VSI_VF: return "ICE_VSI_VF"; + case ICE_VSI_SF: + return "ICE_VSI_SF"; case ICE_VSI_CTRL: return "ICE_VSI_CTRL"; case ICE_VSI_CHNL: return "ICE_VSI_CHNL"; case ICE_VSI_LB: return "ICE_VSI_LB"; - case ICE_VSI_SWITCHDEV_CTRL: - return "ICE_VSI_SWITCHDEV_CTRL"; default: return "unknown"; } @@ -117,14 +117,8 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi) if (!vsi->q_vectors) goto err_vectors; - vsi->af_xdp_zc_qps = bitmap_zalloc(max_t(int, vsi->alloc_txq, vsi->alloc_rxq), GFP_KERNEL); - if (!vsi->af_xdp_zc_qps) - goto err_zc_qps; - return 0; -err_zc_qps: - devm_kfree(dev, vsi->q_vectors); err_vectors: devm_kfree(dev, vsi->rxq_map); err_rxq_map: @@ -144,7 +138,7 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi) { switch (vsi->type) { case ICE_VSI_PF: - case ICE_VSI_SWITCHDEV_CTRL: + case ICE_VSI_SF: case ICE_VSI_CTRL: case ICE_VSI_LB: /* a user could change the values of num_[tr]x_desc using @@ -163,6 +157,16 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi) } } +static u16 ice_get_rxq_count(struct ice_pf *pf) +{ + return min(ice_get_avail_rxq_count(pf), num_online_cpus()); +} + +static u16 ice_get_txq_count(struct ice_pf *pf) +{ + return min(ice_get_avail_txq_count(pf), num_online_cpus()); +} + /** * ice_vsi_set_num_qs - Set number of queues, descriptors and vectors for a VSI * @vsi: the VSI being configured @@ -184,9 +188,7 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi) vsi->alloc_txq = vsi->req_txq; vsi->num_txq = vsi->req_txq; } else { - vsi->alloc_txq = min3(pf->num_lan_msix, - ice_get_avail_txq_count(pf), - (u16)num_online_cpus()); + vsi->alloc_txq = ice_get_txq_count(pf); } pf->num_lan_tx = vsi->alloc_txq; @@ -199,32 +201,19 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi) vsi->alloc_rxq = vsi->req_rxq; vsi->num_rxq = vsi->req_rxq; } else { - vsi->alloc_rxq = min3(pf->num_lan_msix, - ice_get_avail_rxq_count(pf), - (u16)num_online_cpus()); + vsi->alloc_rxq = ice_get_rxq_count(pf); } } pf->num_lan_rx = vsi->alloc_rxq; - vsi->num_q_vectors = min_t(int, pf->num_lan_msix, - max_t(int, vsi->alloc_rxq, - vsi->alloc_txq)); + vsi->num_q_vectors = max(vsi->alloc_rxq, vsi->alloc_txq); break; - case ICE_VSI_SWITCHDEV_CTRL: - /* The number of queues for ctrl VSI is equal to number of PRs - * Each ring is associated to the corresponding VF_PR netdev. - * Tx and Rx rings are always equal - */ - if (vsi->req_txq && vsi->req_rxq) { - vsi->alloc_txq = vsi->req_txq; - vsi->alloc_rxq = vsi->req_rxq; - } else { - vsi->alloc_txq = 1; - vsi->alloc_rxq = 1; - } - + case ICE_VSI_SF: + vsi->alloc_txq = 1; + vsi->alloc_rxq = 1; vsi->num_q_vectors = 1; + vsi->irq_dyn_alloc = true; break; case ICE_VSI_VF: if (vf->num_req_qs) @@ -328,8 +317,6 @@ static void ice_vsi_free_arrays(struct ice_vsi *vsi) dev = ice_pf_to_dev(pf); - bitmap_free(vsi->af_xdp_zc_qps); - vsi->af_xdp_zc_qps = NULL; /* free the ring and vector containers */ devm_kfree(dev, vsi->q_vectors); vsi->q_vectors = NULL; @@ -450,7 +437,7 @@ err_out: * This deallocates the VSI's queue resources, removes it from the PF's * VSI array if necessary, and deallocates the VSI */ -static void ice_vsi_free(struct ice_vsi *vsi) +void ice_vsi_free(struct ice_vsi *vsi) { struct ice_pf *pf = NULL; struct device *dev; @@ -474,6 +461,7 @@ static void ice_vsi_free(struct ice_vsi *vsi) ice_vsi_free_stats(vsi); ice_vsi_free_arrays(vsi); + mutex_destroy(&vsi->xdp_state_lock); mutex_unlock(&pf->sw_mutex); devm_kfree(dev, vsi); } @@ -522,22 +510,6 @@ static irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data) return IRQ_HANDLED; } -static irqreturn_t ice_eswitch_msix_clean_rings(int __always_unused irq, void *data) -{ - struct ice_q_vector *q_vector = (struct ice_q_vector *)data; - struct ice_pf *pf = q_vector->vsi->back; - struct ice_repr *repr; - unsigned long id; - - if (!q_vector->tx.tx_ring && !q_vector->rx.rx_ring) - return IRQ_HANDLED; - - xa_for_each(&pf->eswitch.reprs, id, repr) - napi_schedule(&repr->q_vector->napi); - - return IRQ_HANDLED; -} - /** * ice_vsi_alloc_stat_arrays - Allocate statistics arrays * @vsi: VSI pointer @@ -599,12 +571,11 @@ ice_vsi_alloc_def(struct ice_vsi *vsi, struct ice_channel *ch) return -ENOMEM; } + vsi->irq_dyn_alloc = pci_msix_can_alloc_dyn(vsi->back->pdev); + switch (vsi->type) { - case ICE_VSI_SWITCHDEV_CTRL: - /* Setup eswitch MSIX irq handler for VSI */ - vsi->irq_handler = ice_eswitch_msix_clean_rings; - break; case ICE_VSI_PF: + case ICE_VSI_SF: /* Setup default MSIX irq handler for VSI */ vsi->irq_handler = ice_msix_clean_rings; break; @@ -641,7 +612,7 @@ ice_vsi_alloc_def(struct ice_vsi *vsi, struct ice_channel *ch) * * returns a pointer to a VSI on success, NULL on failure. */ -static struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf) +struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf) { struct device *dev = ice_pf_to_dev(pf); struct ice_vsi *vsi = NULL; @@ -673,6 +644,8 @@ static struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf) pf->next_vsi = ice_get_free_slot(pf->vsi, pf->num_alloc_vsi, pf->next_vsi); + mutex_init(&vsi->xdp_state_lock); + unlock_pf: mutex_unlock(&pf->sw_mutex); return vsi; @@ -860,7 +833,13 @@ bool ice_is_safe_mode(struct ice_pf *pf) */ bool ice_is_rdma_ena(struct ice_pf *pf) { - return test_bit(ICE_FLAG_RDMA_ENA, pf->flags); + union devlink_param_value value; + int err; + + err = devl_param_driverinit_value_get(priv_to_devlink(pf), + DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA, + &value); + return err ? test_bit(ICE_FLAG_RDMA_ENA, pf->flags) : value.vbool; } /** @@ -933,7 +912,7 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi) max_rss_size); vsi->rss_lut_type = ICE_LUT_PF; break; - case ICE_VSI_SWITCHDEV_CTRL: + case ICE_VSI_SF: 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; @@ -1185,6 +1164,7 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_PF; break; case ICE_VSI_VF: + case ICE_VSI_SF: /* VF VSI will gets a small RSS table which is a VSI LUT type */ lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI; break; @@ -1205,12 +1185,11 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) static void ice_chnl_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) { - struct ice_pf *pf = vsi->back; u16 qcount, qmap; u8 offset = 0; int pow; - qcount = min_t(int, vsi->num_rxq, pf->num_lan_msix); + qcount = vsi->num_rxq; pow = order_base_2(qcount); qmap = FIELD_PREP(ICE_AQ_VSI_TC_Q_OFFSET_M, offset); @@ -1263,7 +1242,7 @@ static int ice_vsi_init(struct ice_vsi *vsi, u32 vsi_flags) case ICE_VSI_PF: ctxt->flags = ICE_AQ_VSI_TYPE_PF; break; - case ICE_VSI_SWITCHDEV_CTRL: + case ICE_VSI_SF: case ICE_VSI_CHNL: ctxt->flags = ICE_AQ_VSI_TYPE_VMDQ2; break; @@ -1452,6 +1431,10 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) ring->dev = dev; ring->count = vsi->num_rx_desc; ring->cached_phctime = pf->ptp.cached_phc_time; + + if (ice_is_feature_supported(pf, ICE_F_GCS)) + ring->flags |= ICE_RX_FLAGS_RING_GCS; + WRITE_ONCE(vsi->rx_rings[i], ring); } @@ -1732,6 +1715,12 @@ bool ice_pf_state_is_nominal(struct ice_pf *pf) return true; } +#define ICE_FW_MODE_REC_M BIT(1) +bool ice_is_recovery_mode(struct ice_hw *hw) +{ + return rd32(hw, GL_MNG_FWSM) & ICE_FW_MODE_REC_M; +} + /** * ice_update_eth_stats - Update VSI-specific ethernet statistics counters * @vsi: the VSI to be updated @@ -1790,9 +1779,8 @@ void ice_update_eth_stats(struct ice_vsi *vsi) * @prio: priority for the RXDID for this queue * @ena_ts: true to enable timestamp and false to disable timestamp */ -void -ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio, - bool ena_ts) +void ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio, + bool ena_ts) { int regval = rd32(hw, QRXFLXP_CNTXT(pf_q)); @@ -2077,12 +2065,15 @@ static void ice_vsi_set_tc_cfg(struct ice_vsi *vsi) } /** - * ice_cfg_sw_lldp - Config switch rules for LLDP packet handling + * ice_vsi_cfg_sw_lldp - Config switch rules for LLDP packet handling * @vsi: the VSI being configured * @tx: bool to determine Tx or Rx rule * @create: bool to determine create or remove Rule + * + * Adding an ethtype Tx rule to the uplink VSI results in it being applied + * to the whole port, so LLDP transmission for VFs will be blocked too. */ -void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create) +void ice_vsi_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create) { int (*eth_fltr)(struct ice_vsi *v, u16 type, u16 flag, enum ice_sw_fwd_act_type act); @@ -2097,19 +2088,59 @@ void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create) status = eth_fltr(vsi, ETH_P_LLDP, ICE_FLTR_TX, ICE_DROP_PACKET); } else { - if (ice_fw_supports_lldp_fltr_ctrl(&pf->hw)) { - status = ice_lldp_fltr_add_remove(&pf->hw, vsi->vsi_num, - create); - } else { + if (!test_bit(ICE_FLAG_LLDP_AQ_FLTR, pf->flags)) { status = eth_fltr(vsi, ETH_P_LLDP, ICE_FLTR_RX, ICE_FWD_TO_VSI); + if (!status || !create) + goto report; + + dev_info(dev, + "Failed to add generic LLDP Rx filter on VSI %i error: %d, falling back to specialized AQ control\n", + vsi->vsi_num, status); } + + status = ice_lldp_fltr_add_remove(&pf->hw, vsi, create); + if (!status) + set_bit(ICE_FLAG_LLDP_AQ_FLTR, pf->flags); + } +report: if (status) - dev_dbg(dev, "Fail %s %s LLDP rule on VSI %i error: %d\n", - create ? "adding" : "removing", tx ? "TX" : "RX", - vsi->vsi_num, status); + dev_warn(dev, "Failed to %s %s LLDP rule on VSI %i error: %d\n", + create ? "add" : "remove", tx ? "Tx" : "Rx", + vsi->vsi_num, status); +} + +/** + * ice_cfg_sw_rx_lldp - Enable/disable software handling of LLDP + * @pf: the PF being configured + * @enable: enable or disable + * + * Configure switch rules to enable/disable LLDP handling by software + * across PF. + */ +void ice_cfg_sw_rx_lldp(struct ice_pf *pf, bool enable) +{ + struct ice_vsi *vsi; + struct ice_vf *vf; + unsigned int bkt; + + vsi = ice_get_main_vsi(pf); + ice_vsi_cfg_sw_lldp(vsi, false, enable); + + if (!test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) + return; + + ice_for_each_vf(pf, bkt, vf) { + vsi = ice_get_vf_vsi(vf); + + if (WARN_ON(!vsi)) + continue; + + if (ice_vf_is_lldp_ena(vf)) + ice_vsi_cfg_sw_lldp(vsi, false, enable); + } } /** @@ -2145,7 +2176,7 @@ static void ice_set_agg_vsi(struct ice_vsi *vsi) case ICE_VSI_CHNL: case ICE_VSI_LB: case ICE_VSI_PF: - case ICE_VSI_SWITCHDEV_CTRL: + case ICE_VSI_SF: max_agg_nodes = ICE_MAX_PF_AGG_NODES; agg_node_id_start = ICE_PF_AGG_NODE_ID_START; agg_node_iter = &pf->pf_agg_node[0]; @@ -2273,10 +2304,8 @@ static int ice_vsi_cfg_tc_lan(struct ice_pf *pf, struct ice_vsi *vsi) /** * ice_vsi_cfg_def - configure default VSI based on the type * @vsi: pointer to VSI - * @params: the parameters to configure this VSI with */ -static int -ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) +static int ice_vsi_cfg_def(struct ice_vsi *vsi) { struct device *dev = ice_pf_to_dev(vsi->back); struct ice_pf *pf = vsi->back; @@ -2284,7 +2313,7 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) vsi->vsw = pf->first_sw; - ret = ice_vsi_alloc_def(vsi, params->ch); + ret = ice_vsi_alloc_def(vsi, vsi->ch); if (ret) return ret; @@ -2309,7 +2338,7 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) ice_vsi_set_tc_cfg(vsi); /* create the VSI */ - ret = ice_vsi_init(vsi, params->flags); + ret = ice_vsi_init(vsi, vsi->flags); if (ret) goto unroll_get_qs; @@ -2317,7 +2346,7 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) switch (vsi->type) { case ICE_VSI_CTRL: - case ICE_VSI_SWITCHDEV_CTRL: + case ICE_VSI_SF: case ICE_VSI_PF: ret = ice_vsi_alloc_q_vectors(vsi); if (ret) @@ -2331,22 +2360,20 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) if (ret) goto unroll_vector_base; - ice_vsi_map_rings_to_vectors(vsi); - - /* Associate q_vector rings to napi */ - ice_vsi_set_napi_queues(vsi); - - vsi->stat_offsets_loaded = false; - if (ice_is_xdp_ena_vsi(vsi)) { ret = ice_vsi_determine_xdp_res(vsi); if (ret) goto unroll_vector_base; - ret = ice_prepare_xdp_rings(vsi, vsi->xdp_prog); + ret = ice_prepare_xdp_rings(vsi, vsi->xdp_prog, + ICE_XDP_CFG_PART); if (ret) goto unroll_vector_base; } + ice_vsi_map_rings_to_vectors(vsi); + + vsi->stat_offsets_loaded = false; + /* ICE_VSI_CTRL does not need RSS so skip RSS processing */ if (vsi->type != ICE_VSI_CTRL) /* Do not exit if configuring RSS had an issue, at @@ -2430,23 +2457,16 @@ unroll_vsi_alloc: /** * ice_vsi_cfg - configure a previously allocated VSI * @vsi: pointer to VSI - * @params: parameters used to configure this VSI */ -int ice_vsi_cfg(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) +int ice_vsi_cfg(struct ice_vsi *vsi) { struct ice_pf *pf = vsi->back; int ret; - if (WARN_ON(params->type == ICE_VSI_VF && !params->vf)) + if (WARN_ON(vsi->type == ICE_VSI_VF && !vsi->vf)) return -EINVAL; - vsi->type = params->type; - vsi->port_info = params->pi; - - /* For VSIs which don't have a connected VF, this will be NULL */ - vsi->vf = params->vf; - - ret = ice_vsi_cfg_def(vsi, params); + ret = ice_vsi_cfg_def(vsi); if (ret) return ret; @@ -2476,24 +2496,17 @@ void ice_vsi_decfg(struct ice_vsi *vsi) struct ice_pf *pf = vsi->back; int err; - /* The Rx rule will only exist to remove if the LLDP FW - * engine is currently stopped - */ - if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF && - !test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags)) - ice_cfg_sw_lldp(vsi, false, false); - ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx); if (err) dev_err(ice_pf_to_dev(pf), "Failed to remove RDMA scheduler config for VSI %u, err %d\n", vsi->vsi_num, err); - if (ice_is_xdp_ena_vsi(vsi)) + if (vsi->xdp_rings) /* return value check can be skipped here, it always returns * 0 if reset is in progress */ - ice_destroy_xdp_rings(vsi); + ice_destroy_xdp_rings(vsi, ICE_XDP_CFG_PART); ice_vsi_clear_rings(vsi); ice_vsi_free_q_vectors(vsi); @@ -2532,7 +2545,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params) * a port_info structure for it. */ if (WARN_ON(!(params->flags & ICE_VSI_FLAG_INIT)) || - WARN_ON(!params->pi)) + WARN_ON(!params->port_info)) return NULL; vsi = ice_vsi_alloc(pf); @@ -2541,7 +2554,8 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params) return NULL; } - ret = ice_vsi_cfg(vsi, params); + vsi->params = *params; + ret = ice_vsi_cfg(vsi); if (ret) goto err_vsi_cfg; @@ -2557,7 +2571,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params) if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF) { ice_fltr_add_eth(vsi, ETH_P_PAUSE, ICE_FLTR_TX, ICE_DROP_PACKET); - ice_cfg_sw_lldp(vsi, true, true); + ice_vsi_cfg_sw_lldp(vsi, true, true); } if (!vsi->agg_node) @@ -2590,7 +2604,7 @@ static void ice_vsi_release_msix(struct ice_vsi *vsi) for (q = 0; q < q_vector->num_ring_tx; q++) { ice_write_itr(&q_vector->tx, 0); wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), 0); - if (ice_is_xdp_ena_vsi(vsi)) { + if (vsi->xdp_rings) { u32 xdp_txq = txq + vsi->num_xdp_txq; wr32(hw, QINT_TQCTL(vsi->txq_map[xdp_txq]), 0); @@ -2625,7 +2639,6 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) return; vsi->irqs_ready = false; - ice_free_cpu_rx_rmap(vsi); ice_for_each_q_vector(vsi, i) { int irq_num; @@ -2638,12 +2651,6 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) vsi->q_vectors[i]->num_ring_rx)) continue; - /* clear the affinity notifier in the IRQ descriptor */ - if (!IS_ENABLED(CONFIG_RFS_ACCEL)) - irq_set_affinity_notifier(irq_num, NULL); - - /* clear the affinity_mask in the IRQ descriptor */ - irq_set_affinity_hint(irq_num, NULL); synchronize_irq(irq_num); devm_free_irq(ice_pf_to_dev(pf), irq_num, vsi->q_vectors[i]); } @@ -2690,6 +2697,7 @@ void ice_vsi_close(struct ice_vsi *vsi) if (!test_and_set_bit(ICE_VSI_DOWN, vsi->state)) ice_down(vsi); + ice_vsi_clear_napi_queues(vsi); ice_vsi_free_irq(vsi); ice_vsi_free_tx_rings(vsi); ice_vsi_free_rx_rings(vsi); @@ -2709,7 +2717,8 @@ int ice_ena_vsi(struct ice_vsi *vsi, bool locked) clear_bit(ICE_VSI_NEEDS_RESTART, vsi->state); - if (vsi->netdev && vsi->type == ICE_VSI_PF) { + if (vsi->netdev && (vsi->type == ICE_VSI_PF || + vsi->type == ICE_VSI_SF)) { if (netif_running(vsi->netdev)) { if (!locked) rtnl_lock(); @@ -2733,144 +2742,108 @@ int ice_ena_vsi(struct ice_vsi *vsi, bool locked) */ void ice_dis_vsi(struct ice_vsi *vsi, bool locked) { - if (test_bit(ICE_VSI_DOWN, vsi->state)) - return; + bool already_down = test_bit(ICE_VSI_DOWN, vsi->state); set_bit(ICE_VSI_NEEDS_RESTART, vsi->state); - if (vsi->type == ICE_VSI_PF && vsi->netdev) { + if (vsi->netdev && (vsi->type == ICE_VSI_PF || + vsi->type == ICE_VSI_SF)) { if (netif_running(vsi->netdev)) { if (!locked) rtnl_lock(); - - ice_vsi_close(vsi); + already_down = test_bit(ICE_VSI_DOWN, vsi->state); + if (!already_down) + ice_vsi_close(vsi); if (!locked) rtnl_unlock(); - } else { + } else if (!already_down) { ice_vsi_close(vsi); } - } else if (vsi->type == ICE_VSI_CTRL || - vsi->type == ICE_VSI_SWITCHDEV_CTRL) { + } else if (vsi->type == ICE_VSI_CTRL && !already_down) { ice_vsi_close(vsi); } } /** - * __ice_queue_set_napi - Set the napi instance for the queue - * @dev: device to which NAPI and queue belong - * @queue_index: Index of queue - * @type: queue type as RX or TX - * @napi: NAPI context - * @locked: is the rtnl_lock already held - * - * Set the napi instance for the queue. Caller indicates the lock status. - */ -static void -__ice_queue_set_napi(struct net_device *dev, unsigned int queue_index, - enum netdev_queue_type type, struct napi_struct *napi, - bool locked) -{ - if (!locked) - rtnl_lock(); - netif_queue_set_napi(dev, queue_index, type, napi); - if (!locked) - rtnl_unlock(); -} - -/** - * ice_queue_set_napi - Set the napi instance for the queue - * @vsi: VSI being configured - * @queue_index: Index of queue - * @type: queue type as RX or TX - * @napi: NAPI context + * ice_vsi_set_napi_queues - associate netdev queues with napi + * @vsi: VSI pointer * - * Set the napi instance for the queue. The rtnl lock state is derived from the - * execution path. + * Associate queue[s] with napi for all vectors. + * The caller must hold rtnl_lock. */ -void -ice_queue_set_napi(struct ice_vsi *vsi, unsigned int queue_index, - enum netdev_queue_type type, struct napi_struct *napi) +void ice_vsi_set_napi_queues(struct ice_vsi *vsi) { - struct ice_pf *pf = vsi->back; + struct net_device *netdev = vsi->netdev; + int q_idx, v_idx; - if (!vsi->netdev) + if (!netdev) return; - if (current_work() == &pf->serv_task || - test_bit(ICE_PREPARED_FOR_RESET, pf->state) || - test_bit(ICE_DOWN, pf->state) || - test_bit(ICE_SUSPENDED, pf->state)) - __ice_queue_set_napi(vsi->netdev, queue_index, type, napi, - false); - else - __ice_queue_set_napi(vsi->netdev, queue_index, type, napi, - true); + ice_for_each_rxq(vsi, q_idx) + netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX, + &vsi->rx_rings[q_idx]->q_vector->napi); + + ice_for_each_txq(vsi, q_idx) + netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX, + &vsi->tx_rings[q_idx]->q_vector->napi); + /* Also set the interrupt number for the NAPI */ + ice_for_each_q_vector(vsi, v_idx) { + struct ice_q_vector *q_vector = vsi->q_vectors[v_idx]; + + netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq); + } } /** - * __ice_q_vector_set_napi_queues - Map queue[s] associated with the napi - * @q_vector: q_vector pointer - * @locked: is the rtnl_lock already held + * ice_vsi_clear_napi_queues - dissociate netdev queues from napi + * @vsi: VSI pointer * - * Associate the q_vector napi with all the queue[s] on the vector. - * Caller indicates the lock status. + * Clear the association between all VSI queues queue[s] and napi. + * The caller must hold rtnl_lock. */ -void __ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked) +void ice_vsi_clear_napi_queues(struct ice_vsi *vsi) { - struct ice_rx_ring *rx_ring; - struct ice_tx_ring *tx_ring; + struct net_device *netdev = vsi->netdev; + int q_idx, v_idx; - ice_for_each_rx_ring(rx_ring, q_vector->rx) - __ice_queue_set_napi(q_vector->vsi->netdev, rx_ring->q_index, - NETDEV_QUEUE_TYPE_RX, &q_vector->napi, - locked); + if (!netdev) + return; - ice_for_each_tx_ring(tx_ring, q_vector->tx) - __ice_queue_set_napi(q_vector->vsi->netdev, tx_ring->q_index, - NETDEV_QUEUE_TYPE_TX, &q_vector->napi, - locked); - /* Also set the interrupt number for the NAPI */ - netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq); -} + /* Clear the NAPI's interrupt number */ + ice_for_each_q_vector(vsi, v_idx) { + struct ice_q_vector *q_vector = vsi->q_vectors[v_idx]; -/** - * ice_q_vector_set_napi_queues - Map queue[s] associated with the napi - * @q_vector: q_vector pointer - * - * Associate the q_vector napi with all the queue[s] on the vector - */ -void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector) -{ - struct ice_rx_ring *rx_ring; - struct ice_tx_ring *tx_ring; + netif_napi_set_irq(&q_vector->napi, -1); + } - ice_for_each_rx_ring(rx_ring, q_vector->rx) - ice_queue_set_napi(q_vector->vsi, rx_ring->q_index, - NETDEV_QUEUE_TYPE_RX, &q_vector->napi); + ice_for_each_txq(vsi, q_idx) + netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX, NULL); - ice_for_each_tx_ring(tx_ring, q_vector->tx) - ice_queue_set_napi(q_vector->vsi, tx_ring->q_index, - NETDEV_QUEUE_TYPE_TX, &q_vector->napi); - /* Also set the interrupt number for the NAPI */ - netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq); + ice_for_each_rxq(vsi, q_idx) + netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX, NULL); } /** - * ice_vsi_set_napi_queues - * @vsi: VSI pointer + * ice_napi_add - register NAPI handler for the VSI + * @vsi: VSI for which NAPI handler is to be registered * - * Associate queue[s] with napi for all vectors + * This function is only called in the driver's load path. Registering the NAPI + * handler is done in ice_vsi_alloc_q_vector() for all other cases (i.e. resume, + * reset/rebuild, etc.) */ -void ice_vsi_set_napi_queues(struct ice_vsi *vsi) +void ice_napi_add(struct ice_vsi *vsi) { - int i; + int v_idx; if (!vsi->netdev) return; - ice_for_each_q_vector(vsi, i) - ice_q_vector_set_napi_queues(vsi->q_vectors[i]); + ice_for_each_q_vector(vsi, v_idx) + netif_napi_add_config(vsi->netdev, + &vsi->q_vectors[v_idx]->napi, + ice_napi_poll, + v_idx); } /** @@ -2891,6 +2864,16 @@ int ice_vsi_release(struct ice_vsi *vsi) ice_rss_clean(vsi); ice_vsi_close(vsi); + + /* The Rx rule will only exist to remove if the LLDP FW + * engine is currently stopped + */ + if (!ice_is_safe_mode(pf) && + !test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags) && + (vsi->type == ICE_VSI_PF || (vsi->type == ICE_VSI_VF && + ice_vf_is_lldp_ena(vsi->vf)))) + ice_vsi_cfg_sw_lldp(vsi, false, false); + ice_vsi_decfg(vsi); /* retain SW VSI data structure since it is needed to unregister and @@ -3089,7 +3072,6 @@ ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi) */ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags) { - struct ice_vsi_cfg_params params = {}; struct ice_coalesce_stored *coalesce; int prev_num_q_vectors; struct ice_pf *pf; @@ -3098,26 +3080,28 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags) if (!vsi) return -EINVAL; - params = ice_vsi_to_params(vsi); - params.flags = vsi_flags; - + vsi->flags = vsi_flags; pf = vsi->back; if (WARN_ON(vsi->type == ICE_VSI_VF && !vsi->vf)) return -EINVAL; + mutex_lock(&vsi->xdp_state_lock); + ret = ice_vsi_realloc_stat_arrays(vsi); if (ret) - goto err_vsi_cfg; + goto unlock; ice_vsi_decfg(vsi); - ret = ice_vsi_cfg_def(vsi, ¶ms); + ret = ice_vsi_cfg_def(vsi); if (ret) - goto err_vsi_cfg; + goto unlock; coalesce = kcalloc(vsi->num_q_vectors, sizeof(struct ice_coalesce_stored), GFP_KERNEL); - if (!coalesce) - return -ENOMEM; + if (!coalesce) { + ret = -ENOMEM; + goto decfg; + } prev_num_q_vectors = ice_vsi_rebuild_get_coalesce(vsi, coalesce); @@ -3125,22 +3109,23 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags) if (ret) { if (vsi_flags & ICE_VSI_FLAG_INIT) { ret = -EIO; - goto err_vsi_cfg_tc_lan; + goto free_coalesce; } - kfree(coalesce); - return ice_schedule_reset(pf, ICE_RESET_PFR); + ret = ice_schedule_reset(pf, ICE_RESET_PFR); + goto free_coalesce; } ice_vsi_rebuild_set_coalesce(vsi, coalesce, prev_num_q_vectors); - kfree(coalesce); - - return 0; + clear_bit(ICE_VSI_REBUILD_PENDING, vsi->state); -err_vsi_cfg_tc_lan: - ice_vsi_decfg(vsi); +free_coalesce: kfree(coalesce); -err_vsi_cfg: +decfg: + if (ret) + ice_vsi_decfg(vsi); +unlock: + mutex_unlock(&vsi->xdp_state_lock); return ret; } @@ -3956,12 +3941,17 @@ void ice_init_feature_support(struct ice_pf *pf) 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)) + if (ice_gnss_is_module_present(&pf->hw)) ice_set_feature_support(pf, ICE_F_GNSS); break; default: break; } + + if (pf->hw.mac_type == ICE_MAC_E830) { + ice_set_feature_support(pf, ICE_F_MBX_LIMIT); + ice_set_feature_support(pf, ICE_F_GCS); + } } /** @@ -4008,24 +3998,6 @@ void ice_vsi_ctx_clear_antispoof(struct ice_vsi_ctx *ctx) } /** - * ice_vsi_ctx_set_allow_override - allow destination override on VSI - * @ctx: pointer to VSI ctx structure - */ -void ice_vsi_ctx_set_allow_override(struct ice_vsi_ctx *ctx) -{ - ctx->info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD; -} - -/** - * ice_vsi_ctx_clear_allow_override - turn off destination override on VSI - * @ctx: pointer to VSI ctx structure - */ -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 diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index 9cd23afe5f15..654516c5fc3e 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -11,43 +11,6 @@ #define ICE_VSI_FLAG_INIT BIT(0) #define ICE_VSI_FLAG_NO_INIT 0 -/** - * struct ice_vsi_cfg_params - VSI configuration parameters - * @pi: pointer to the port_info instance for the VSI - * @ch: pointer to the channel structure for the VSI, may be NULL - * @vf: pointer to the VF associated with this VSI, may be NULL - * @type: the type of VSI to configure - * @flags: VSI flags used for rebuild and configuration - * - * Parameter structure used when configuring a new VSI. - */ -struct ice_vsi_cfg_params { - struct ice_port_info *pi; - struct ice_channel *ch; - struct ice_vf *vf; - enum ice_vsi_type type; - u32 flags; -}; - -/** - * ice_vsi_to_params - Get parameters for an existing VSI - * @vsi: the VSI to get parameters for - * - * Fill a parameter structure for reconfiguring a VSI with its current - * parameters, such as during a rebuild operation. - */ -static inline struct ice_vsi_cfg_params ice_vsi_to_params(struct ice_vsi *vsi) -{ - struct ice_vsi_cfg_params params = {}; - - params.pi = vsi->port_info; - params.ch = vsi->ch; - params.vf = vsi->vf; - params.type = vsi->type; - - return params; -} - const char *ice_vsi_type_str(enum ice_vsi_type vsi_type); bool ice_pf_state_is_nominal(struct ice_pf *pf); @@ -66,7 +29,8 @@ ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi); -void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create); +void ice_vsi_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create); +void ice_cfg_sw_rx_lldp(struct ice_pf *pf, bool enable); int ice_set_link(struct ice_vsi *vsi, bool ena); @@ -81,15 +45,10 @@ 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_queue_set_napi(struct ice_vsi *vsi, unsigned int queue_index, - enum netdev_queue_type type, struct napi_struct *napi); - -void __ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked); - -void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector); - void ice_vsi_set_napi_queues(struct ice_vsi *vsi); +void ice_napi_add(struct ice_vsi *vsi); + +void ice_vsi_clear_napi_queues(struct ice_vsi *vsi); int ice_vsi_release(struct ice_vsi *vsi); @@ -101,7 +60,9 @@ void ice_vsi_decfg(struct ice_vsi *vsi); void ice_dis_vsi(struct ice_vsi *vsi, bool locked); int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags); -int ice_vsi_cfg(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params); +int ice_vsi_cfg(struct ice_vsi *vsi); +struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf); +void ice_vsi_free(struct ice_vsi *vsi); bool ice_is_reset_in_progress(unsigned long *state); int ice_wait_for_reset(struct ice_pf *pf, unsigned long timeout); @@ -128,10 +89,9 @@ 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); -int ice_vsi_cfg_mac_fltr(struct ice_vsi *vsi, const u8 *macaddr, bool set); - bool ice_is_safe_mode(struct ice_pf *pf); bool ice_is_rdma_ena(struct ice_pf *pf); +bool ice_is_recovery_mode(struct ice_hw *hw); bool ice_is_dflt_vsi_in_use(struct ice_port_info *pi); bool ice_is_vsi_dflt_vsi(struct ice_vsi *vsi); int ice_set_dflt_vsi(struct ice_vsi *vsi); @@ -146,10 +106,6 @@ ice_vsi_update_security(struct ice_vsi *vsi, void (*fill)(struct ice_vsi_ctx *)) void ice_vsi_ctx_set_antispoof(struct ice_vsi_ctx *ctx); 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); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 33a164fa325a..20d3baf955e3 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -13,7 +13,9 @@ #include "ice_fltr.h" #include "ice_dcb_lib.h" #include "ice_dcb_nl.h" -#include "ice_devlink.h" +#include "devlink/devlink.h" +#include "devlink/port.h" +#include "ice_sf_eth.h" #include "ice_hwmon.h" /* Including ice_trace.h with CREATE_TRACE_POINTS defined will generate the * ice tracepoint functions. This must be done exactly once across the @@ -34,8 +36,8 @@ static const char ice_copyright[] = "Copyright (c) 2018, Intel Corporation."; #define ICE_DDP_PKG_PATH "intel/ice/ddp/" #define ICE_DDP_PKG_FILE ICE_DDP_PKG_PATH "ice.pkg" -MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION(DRV_SUMMARY); +MODULE_IMPORT_NS("LIBIE"); MODULE_LICENSE("GPL v2"); MODULE_FIRMWARE(ICE_DDP_PKG_FILE); @@ -85,7 +87,8 @@ ice_indr_setup_tc_cb(struct net_device *netdev, struct Qdisc *sch, bool netif_is_ice(const struct net_device *dev) { - return dev && (dev->netdev_ops == &ice_netdev_ops); + return dev && (dev->netdev_ops == &ice_netdev_ops || + dev->netdev_ops == &ice_netdev_safe_mode_ops); } /** @@ -519,25 +522,6 @@ static void ice_pf_dis_all_vsi(struct ice_pf *pf, bool locked) } /** - * ice_clear_sw_switch_recipes - clear switch recipes - * @pf: board private structure - * - * Mark switch recipes as not created in sw structures. There are cases where - * rules (especially advanced rules) need to be restored, either re-read from - * hardware or added again. For example after the reset. 'recp_created' flag - * prevents from doing that and need to be cleared upfront. - */ -static void ice_clear_sw_switch_recipes(struct ice_pf *pf) -{ - struct ice_sw_recipe *recp; - u8 i; - - recp = pf->hw.switch_info->recp_list; - for (i = 0; i < ICE_MAX_NUM_RECIPES; i++) - recp[i].recp_created = false; -} - -/** * ice_prepare_for_reset - prep for reset * @pf: board private structure * @reset_type: reset type requested @@ -558,6 +542,8 @@ ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type) if (test_bit(ICE_PREPARED_FOR_RESET, pf->state)) return; + synchronize_irq(pf->oicr_irq.virq); + ice_unplug_aux_dev(pf); /* Notify VFs of impending reset */ @@ -571,8 +557,9 @@ ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type) mutex_unlock(&pf->vfs.table_lock); if (ice_is_eswitch_mode_switchdev(pf)) { - if (reset_type != ICE_RESET_PFR) - ice_clear_sw_switch_recipes(pf); + rtnl_lock(); + ice_eswitch_br_fdb_flush(pf->eswitch.br_offloads->bridge); + rtnl_unlock(); } /* release ADQ specific HW and SW resources */ @@ -605,11 +592,15 @@ ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type) memset(&vsi->mqprio_qopt, 0, sizeof(vsi->mqprio_qopt)); } } + + if (vsi->netdev) + netif_device_detach(vsi->netdev); skip: /* clear SW filtering DB */ ice_clear_hw_tbls(hw); /* disable the VSIs and their queues that are not already DOWN */ + set_bit(ICE_VSI_REBUILD_PENDING, ice_get_main_vsi(pf)->state); ice_pf_dis_all_vsi(pf, false); if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) @@ -621,7 +612,7 @@ skip: if (hw->port_info) ice_sched_clear_port(hw->port_info); - ice_shutdown_all_ctrlq(hw); + ice_shutdown_all_ctrlq(hw, false); set_bit(ICE_PREPARED_FOR_RESET, pf->state); } @@ -803,6 +794,9 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup) } switch (vsi->port_info->phy.link_info.link_speed) { + case ICE_AQ_LINK_SPEED_200GB: + speed = "200 G"; + break; case ICE_AQ_LINK_SPEED_100GB: speed = "100 G"; break; @@ -1150,7 +1144,7 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up, if (link_up == old_link && link_speed == old_link_speed) return 0; - ice_ptp_link_change(pf, pf->hw.pf_id, link_up); + ice_ptp_link_change(pf, link_up); if (ice_is_dcb_active(pf)) { if (test_bit(ICE_FLAG_DCB_ENA, pf->flags)) @@ -1552,12 +1546,20 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) ice_vf_lan_overflow_event(pf, &event); break; case ice_mbx_opc_send_msg_to_pf: - data.num_msg_proc = i; - data.num_pending_arq = pending; - data.max_num_msgs_mbx = hw->mailboxq.num_rq_entries; - data.async_watermark_val = ICE_MBX_OVERFLOW_WATERMARK; + if (ice_is_feature_supported(pf, ICE_F_MBX_LIMIT)) { + ice_vc_process_vf_msg(pf, &event, NULL); + ice_mbx_vf_dec_trig_e830(hw, &event); + } else { + u16 val = hw->mailboxq.num_rq_entries; + + data.max_num_msgs_mbx = val; + val = ICE_MBX_OVERFLOW_WATERMARK; + data.async_watermark_val = val; + data.num_msg_proc = i; + data.num_pending_arq = pending; - ice_vc_process_vf_msg(pf, &event, &data); + ice_vc_process_vf_msg(pf, &event, &data); + } break; case ice_aqc_opc_fw_logs_event: ice_get_fwlog_data(pf, &event); @@ -1565,6 +1567,9 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) case ice_aqc_opc_lldp_set_mib_change: ice_dcb_process_lldp_set_mib_change(pf, &event); break; + case ice_aqc_opc_get_health_status: + ice_process_health_status_event(pf, &event); + break; default: dev_dbg(dev, "%s Receive Queue unknown event 0x%04x ignored\n", qtype, opcode); @@ -1712,7 +1717,7 @@ static int ice_service_task_stop(struct ice_pf *pf) ret = test_and_set_bit(ICE_SERVICE_DIS, pf->state); if (pf->serv_tmr.function) - del_timer_sync(&pf->serv_tmr); + timer_delete_sync(&pf->serv_tmr); if (pf->serv_task.func) cancel_work_sync(&pf->serv_task); @@ -1745,6 +1750,39 @@ static void ice_service_timer(struct timer_list *t) } /** + * ice_mdd_maybe_reset_vf - reset VF after MDD event + * @pf: pointer to the PF structure + * @vf: pointer to the VF structure + * @reset_vf_tx: whether Tx MDD has occurred + * @reset_vf_rx: whether Rx MDD has occurred + * + * Since the queue can get stuck on VF MDD events, the PF can be configured to + * automatically reset the VF by enabling the private ethtool flag + * mdd-auto-reset-vf. + */ +static void ice_mdd_maybe_reset_vf(struct ice_pf *pf, struct ice_vf *vf, + bool reset_vf_tx, bool reset_vf_rx) +{ + struct device *dev = ice_pf_to_dev(pf); + + if (!test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags)) + return; + + /* VF MDD event counters will be cleared by reset, so print the event + * prior to reset. + */ + if (reset_vf_tx) + ice_print_vf_tx_mdd_event(vf); + + if (reset_vf_rx) + ice_print_vf_rx_mdd_event(vf); + + dev_info(dev, "PF-to-VF reset on PF %d VF %d due to MDD event\n", + pf->hw.pf_id, vf->vf_id); + ice_reset_vf(vf, ICE_VF_RESET_NOTIFY | ICE_VF_RESET_LOCK); +} + +/** * ice_handle_mdd_event - handle malicious driver detect event * @pf: pointer to the PF structure * @@ -1781,6 +1819,8 @@ 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); + ice_report_mdd_event(pf, ICE_MDD_SRC_TX_PQM, pf_num, vf_num, + event, queue); wr32(hw, GL_MDET_TX_PQM, 0xffffffff); } @@ -1794,6 +1834,8 @@ 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); + ice_report_mdd_event(pf, ICE_MDD_SRC_TX_TCLAN, pf_num, vf_num, + event, queue); wr32(hw, GL_MDET_TX_TCLAN_BY_MAC(hw), U32_MAX); } @@ -1807,6 +1849,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf) if (netif_msg_rx_err(pf)) dev_info(dev, "Malicious Driver Detection event %d on RX queue %d PF# %d VF# %d\n", event, queue, pf_num, vf_num); + ice_report_mdd_event(pf, ICE_MDD_SRC_RX, pf_num, vf_num, event, + queue); wr32(hw, GL_MDET_RX, 0xffffffff); } @@ -1837,6 +1881,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf) */ mutex_lock(&pf->vfs.table_lock); ice_for_each_vf(pf, bkt, vf) { + bool reset_vf_tx = false, reset_vf_rx = false; + reg = rd32(hw, VP_MDET_TX_PQM(vf->vf_id)); if (reg & VP_MDET_TX_PQM_VALID_M) { wr32(hw, VP_MDET_TX_PQM(vf->vf_id), 0xFFFF); @@ -1845,6 +1891,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf) if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event TX_PQM detected on VF %d\n", vf->vf_id); + + reset_vf_tx = true; } reg = rd32(hw, VP_MDET_TX_TCLAN(vf->vf_id)); @@ -1855,6 +1903,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf) if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event TX_TCLAN detected on VF %d\n", vf->vf_id); + + reset_vf_tx = true; } reg = rd32(hw, VP_MDET_TX_TDPU(vf->vf_id)); @@ -1865,6 +1915,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf) if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event TX_TDPU detected on VF %d\n", vf->vf_id); + + reset_vf_tx = true; } reg = rd32(hw, VP_MDET_RX(vf->vf_id)); @@ -1876,18 +1928,12 @@ static void ice_handle_mdd_event(struct ice_pf *pf) dev_info(dev, "Malicious Driver Detection event RX detected on VF %d\n", vf->vf_id); - /* Since the queue is disabled on VF Rx MDD events, the - * PF can be configured to reset the VF through ethtool - * private flag mdd-auto-reset-vf. - */ - if (test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags)) { - /* VF MDD event counters will be cleared by - * reset, so print the event prior to reset. - */ - ice_print_vf_rx_mdd_event(vf); - ice_reset_vf(vf, ICE_VF_RESET_LOCK); - } + reset_vf_rx = true; } + + if (reset_vf_tx || reset_vf_rx) + ice_mdd_maybe_reset_vf(pf, vf, reset_vf_tx, + reset_vf_rx); } mutex_unlock(&pf->vfs.table_lock); @@ -2318,6 +2364,18 @@ static void ice_check_media_subtask(struct ice_pf *pf) } } +static void ice_service_task_recovery_mode(struct work_struct *work) +{ + struct ice_pf *pf = container_of(work, struct ice_pf, serv_task); + + set_bit(ICE_ADMINQ_EVENT_PENDING, pf->state); + ice_clean_adminq_subtask(pf); + + ice_service_task_complete(pf); + + mod_timer(&pf->serv_tmr, jiffies + msecs_to_jiffies(100)); +} + /** * ice_service_task - manage and run subtasks * @work: pointer to work_struct contained by the PF struct @@ -2327,9 +2385,11 @@ static void ice_service_task(struct work_struct *work) struct ice_pf *pf = container_of(work, struct ice_pf, serv_task); unsigned long start_time = jiffies; - /* subtasks */ + if (pf->health_reporters.tx_hang_buf.tx_ring) { + ice_report_tx_hang(pf); + pf->health_reporters.tx_hang_buf.tx_ring = NULL; + } - /* process reset requests first */ ice_reset_subtask(pf); /* bail if a reset/recovery cycle is pending or rebuild failed */ @@ -2341,11 +2401,11 @@ static void ice_service_task(struct work_struct *work) } if (test_and_clear_bit(ICE_AUX_ERR_PENDING, pf->state)) { - struct iidc_event *event; + struct iidc_rdma_event *event; event = kzalloc(sizeof(*event), GFP_KERNEL); if (event) { - set_bit(IIDC_EVENT_CRIT_ERR, event->type); + set_bit(IIDC_RDMA_EVENT_CRIT_ERR, event->type); /* report the entire OICR value to AUX driver */ swap(event->reg, pf->oicr_err_reg); ice_send_event_to_aux(pf, event); @@ -2364,11 +2424,11 @@ static void ice_service_task(struct work_struct *work) ice_plug_aux_dev(pf); if (test_and_clear_bit(ICE_FLAG_MTU_CHANGED, pf->flags)) { - struct iidc_event *event; + struct iidc_rdma_event *event; event = kzalloc(sizeof(*event), GFP_KERNEL); if (event) { - set_bit(IIDC_EVENT_AFTER_MTU_CHANGE, event->type); + set_bit(IIDC_RDMA_EVENT_AFTER_MTU_CHANGE, event->type); ice_send_event_to_aux(pf, event); kfree(event); } @@ -2468,34 +2528,6 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset) } /** - * ice_irq_affinity_notify - Callback for affinity changes - * @notify: context as to what irq was changed - * @mask: the new affinity mask - * - * This is a callback function used by the irq_set_affinity_notifier function - * so that we may register to receive changes to the irq affinity masks. - */ -static void -ice_irq_affinity_notify(struct irq_affinity_notify *notify, - const cpumask_t *mask) -{ - struct ice_q_vector *q_vector = - container_of(notify, struct ice_q_vector, affinity_notify); - - cpumask_copy(&q_vector->affinity_mask, mask); -} - -/** - * ice_irq_affinity_release - Callback for affinity notifier release - * @ref: internal core kernel usage - * - * This is a callback function used by the irq_set_affinity_notifier function - * to inform the current notification subscriber that they will no longer - * receive notifications. - */ -static void ice_irq_affinity_release(struct kref __always_unused *ref) {} - -/** * ice_vsi_ena_irq - Enable IRQ for the given VSI * @vsi: the VSI being configured */ @@ -2558,19 +2590,6 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) err); goto free_q_irqs; } - - /* register for affinity change notifications */ - if (!IS_ENABLED(CONFIG_RFS_ACCEL)) { - struct irq_affinity_notify *affinity_notify; - - affinity_notify = &q_vector->affinity_notify; - affinity_notify->notify = ice_irq_affinity_notify; - affinity_notify->release = ice_irq_affinity_release; - irq_set_affinity_notifier(irq_num, affinity_notify); - } - - /* assign the mask for this irq */ - irq_set_affinity_hint(irq_num, &q_vector->affinity_mask); } err = ice_set_cpu_rx_rmap(vsi); @@ -2586,9 +2605,6 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) free_q_irqs: while (vector--) { irq_num = vsi->q_vectors[vector]->irq.virq; - if (!IS_ENABLED(CONFIG_RFS_ACCEL)) - irq_set_affinity_notifier(irq_num, NULL); - irq_set_affinity_hint(irq_num, NULL); devm_free_irq(dev, irq_num, &vsi->q_vectors[vector]); } return err; @@ -2670,17 +2686,72 @@ static void ice_vsi_assign_bpf_prog(struct ice_vsi *vsi, struct bpf_prog *prog) bpf_prog_put(old_prog); } +static struct ice_tx_ring *ice_xdp_ring_from_qid(struct ice_vsi *vsi, int qid) +{ + struct ice_q_vector *q_vector; + struct ice_tx_ring *ring; + + if (static_key_enabled(&ice_xdp_locking_key)) + return vsi->xdp_rings[qid % vsi->num_xdp_txq]; + + q_vector = vsi->rx_rings[qid]->q_vector; + ice_for_each_tx_ring(ring, q_vector->tx) + if (ice_ring_is_xdp(ring)) + return ring; + + return NULL; +} + +/** + * ice_map_xdp_rings - Map XDP rings to interrupt vectors + * @vsi: the VSI with XDP rings being configured + * + * Map XDP rings to interrupt vectors and perform the configuration steps + * dependent on the mapping. + */ +void ice_map_xdp_rings(struct ice_vsi *vsi) +{ + int xdp_rings_rem = vsi->num_xdp_txq; + int v_idx, q_idx; + + /* follow the logic from ice_vsi_map_rings_to_vectors */ + ice_for_each_q_vector(vsi, v_idx) { + struct ice_q_vector *q_vector = vsi->q_vectors[v_idx]; + int xdp_rings_per_v, q_id, q_base; + + xdp_rings_per_v = DIV_ROUND_UP(xdp_rings_rem, + vsi->num_q_vectors - v_idx); + q_base = vsi->num_xdp_txq - xdp_rings_rem; + + for (q_id = q_base; q_id < (q_base + xdp_rings_per_v); q_id++) { + struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_id]; + + xdp_ring->q_vector = q_vector; + xdp_ring->next = q_vector->tx.tx_ring; + q_vector->tx.tx_ring = xdp_ring; + } + xdp_rings_rem -= xdp_rings_per_v; + } + + ice_for_each_rxq(vsi, q_idx) { + vsi->rx_rings[q_idx]->xdp_ring = ice_xdp_ring_from_qid(vsi, + q_idx); + ice_tx_xsk_pool(vsi, q_idx); + } +} + /** * ice_prepare_xdp_rings - Allocate, configure and setup Tx rings for XDP * @vsi: VSI to bring up Tx rings used by XDP * @prog: bpf program that will be assigned to VSI + * @cfg_type: create from scratch or restore the existing configuration * * Return 0 on success and negative value on error */ -int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) +int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog, + enum ice_xdp_cfg cfg_type) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; - int xdp_rings_rem = vsi->num_xdp_txq; struct ice_pf *pf = vsi->back; struct ice_qs_cfg xdp_qs_cfg = { .qs_mutex = &pf->avail_q_mutex, @@ -2693,8 +2764,7 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) .mapping_mode = ICE_VSI_MAP_CONTIG }; struct device *dev; - int i, v_idx; - int status; + int status, i; dev = ice_pf_to_dev(pf); vsi->xdp_rings = devm_kcalloc(dev, vsi->num_xdp_txq, @@ -2713,49 +2783,15 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) if (ice_xdp_alloc_setup_rings(vsi)) goto clear_xdp_rings; - /* follow the logic from ice_vsi_map_rings_to_vectors */ - ice_for_each_q_vector(vsi, v_idx) { - struct ice_q_vector *q_vector = vsi->q_vectors[v_idx]; - int xdp_rings_per_v, q_id, q_base; - - xdp_rings_per_v = DIV_ROUND_UP(xdp_rings_rem, - vsi->num_q_vectors - v_idx); - q_base = vsi->num_xdp_txq - xdp_rings_rem; - - for (q_id = q_base; q_id < (q_base + xdp_rings_per_v); q_id++) { - struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_id]; - - xdp_ring->q_vector = q_vector; - xdp_ring->next = q_vector->tx.tx_ring; - q_vector->tx.tx_ring = xdp_ring; - } - xdp_rings_rem -= xdp_rings_per_v; - } - - ice_for_each_rxq(vsi, i) { - if (static_key_enabled(&ice_xdp_locking_key)) { - vsi->rx_rings[i]->xdp_ring = vsi->xdp_rings[i % vsi->num_xdp_txq]; - } else { - struct ice_q_vector *q_vector = vsi->rx_rings[i]->q_vector; - struct ice_tx_ring *ring; - - ice_for_each_tx_ring(ring, q_vector->tx) { - if (ice_ring_is_xdp(ring)) { - vsi->rx_rings[i]->xdp_ring = ring; - break; - } - } - } - ice_tx_xsk_pool(vsi, i); - } - /* omit the scheduler update if in reset path; XDP queues will be * taken into account at the end of ice_vsi_rebuild, where * ice_cfg_vsi_lan is being called */ - if (ice_is_reset_in_progress(pf->state)) + if (cfg_type == ICE_XDP_CFG_PART) return 0; + ice_map_xdp_rings(vsi); + /* tell the Tx scheduler that right now we have * additional queues */ @@ -2805,22 +2841,21 @@ err_map_xdp: /** * ice_destroy_xdp_rings - undo the configuration made by ice_prepare_xdp_rings * @vsi: VSI to remove XDP rings + * @cfg_type: disable XDP permanently or allow it to be restored later * * Detach XDP rings from irq vectors, clean up the PF bitmap and free * resources */ -int ice_destroy_xdp_rings(struct ice_vsi *vsi) +int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; struct ice_pf *pf = vsi->back; int i, v_idx; /* q_vectors are freed in reset path so there's no point in detaching - * rings; in case of rebuild being triggered not from reset bits - * in pf->state won't be set, so additionally check first q_vector - * against NULL + * rings */ - if (ice_is_reset_in_progress(pf->state) || !vsi->q_vectors[0]) + if (cfg_type == ICE_XDP_CFG_PART) goto free_qmap; ice_for_each_q_vector(vsi, v_idx) { @@ -2861,7 +2896,7 @@ free_qmap: if (static_key_enabled(&ice_xdp_locking_key)) static_branch_dec(&ice_xdp_locking_key); - if (ice_is_reset_in_progress(pf->state) || !vsi->q_vectors[0]) + if (cfg_type == ICE_XDP_CFG_PART) return 0; ice_vsi_assign_bpf_prog(vsi, NULL); @@ -2890,7 +2925,7 @@ static void ice_vsi_rx_napi_schedule(struct ice_vsi *vsi) ice_for_each_rxq(vsi, i) { struct ice_rx_ring *rx_ring = vsi->rx_rings[i]; - if (rx_ring->xsk_pool) + if (READ_ONCE(rx_ring->xsk_pool)) napi_schedule(&rx_ring->q_vector->napi); } } @@ -2910,6 +2945,9 @@ int ice_vsi_determine_xdp_res(struct ice_vsi *vsi) if (avail < cpus / 2) return -ENOMEM; + if (vsi->type == ICE_VSI_SF) + avail = vsi->alloc_txq; + vsi->num_xdp_txq = min_t(u16, avail, cpus); if (vsi->num_xdp_txq < cpus) @@ -2941,8 +2979,8 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, struct netlink_ext_ack *extack) { unsigned int frame_size = vsi->netdev->mtu + ICE_ETH_PKT_HDR_PAD; - bool if_running = netif_running(vsi->netdev); int ret = 0, xdp_ring_err = 0; + bool if_running; if (prog && !prog->aux->xdp_has_frags) { if (frame_size > ice_max_xdp_frame_size(vsi)) { @@ -2953,13 +2991,17 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, } /* hot swap progs and avoid toggling link */ - if (ice_is_xdp_ena_vsi(vsi) == !!prog) { + if (ice_is_xdp_ena_vsi(vsi) == !!prog || + test_bit(ICE_VSI_REBUILD_PENDING, vsi->state)) { ice_vsi_assign_bpf_prog(vsi, prog); return 0; } + if_running = netif_running(vsi->netdev) && + !test_and_set_bit(ICE_VSI_DOWN, vsi->state); + /* need to stop netdev while setting up the program for Rx rings */ - if (if_running && !test_and_set_bit(ICE_VSI_DOWN, vsi->state)) { + if (if_running) { ret = ice_down(vsi); if (ret) { NL_SET_ERR_MSG_MOD(extack, "Preparing device for XDP attach failed"); @@ -2972,7 +3014,8 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, if (xdp_ring_err) { NL_SET_ERR_MSG_MOD(extack, "Not enough Tx resources for XDP"); } else { - xdp_ring_err = ice_prepare_xdp_rings(vsi, prog); + xdp_ring_err = ice_prepare_xdp_rings(vsi, prog, + ICE_XDP_CFG_FULL); if (xdp_ring_err) NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed"); } @@ -2983,7 +3026,7 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Rx resources failed"); } else if (ice_is_xdp_ena_vsi(vsi) && !prog) { xdp_features_clear_redirect_target(vsi->netdev); - xdp_ring_err = ice_destroy_xdp_rings(vsi); + xdp_ring_err = ice_destroy_xdp_rings(vsi, ICE_XDP_CFG_FULL); if (xdp_ring_err) NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed"); /* reallocate Rx queues that were used for zero-copy */ @@ -3020,25 +3063,32 @@ static int ice_xdp_safe_mode(struct net_device __always_unused *dev, * @dev: netdevice * @xdp: XDP command */ -static int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp) +int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp) { struct ice_netdev_priv *np = netdev_priv(dev); struct ice_vsi *vsi = np->vsi; + int ret; - if (vsi->type != ICE_VSI_PF) { - NL_SET_ERR_MSG_MOD(xdp->extack, "XDP can be loaded only on PF VSI"); + if (vsi->type != ICE_VSI_PF && vsi->type != ICE_VSI_SF) { + NL_SET_ERR_MSG_MOD(xdp->extack, "XDP can be loaded only on PF or SF VSI"); return -EINVAL; } + mutex_lock(&vsi->xdp_state_lock); + switch (xdp->command) { case XDP_SETUP_PROG: - return ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack); + ret = ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack); + break; case XDP_SETUP_XSK_POOL: - return ice_xsk_pool_setup(vsi, xdp->xsk.pool, - xdp->xsk.queue_id); + ret = ice_xsk_pool_setup(vsi, xdp->xsk.pool, xdp->xsk.queue_id); + break; default: - return -EINVAL; + ret = -EINVAL; } + + mutex_unlock(&vsi->xdp_state_lock); + return ret; } /** @@ -3210,22 +3260,8 @@ 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 (ice_pf_state_is_nominal(pf) && - pf->hw.dev_caps.ts_dev_info.ts_ll_int_read) { - struct ice_ptp_tx *tx = &pf->ptp.port.tx; - unsigned long flags; - u8 idx; - - spin_lock_irqsave(&tx->lock, flags); - idx = find_next_bit_wrap(tx->in_use, tx->len, - tx->last_ll_ts_idx_read + 1); - if (idx != tx->len) - ice_ptp_req_tx_single_tstamp(tx, idx); - spin_unlock_irqrestore(&tx->lock, flags); - } else if (ice_ptp_pf_handles_tx_interrupt(pf)) { - set_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread); - ret = IRQ_WAKE_THREAD; - } + + ret = ice_ptp_ts_irq(pf); } if (oicr & PFINT_OICR_TSYN_EVNT_M) { @@ -3480,28 +3516,6 @@ skip_req_irq: } /** - * ice_napi_add - register NAPI handler for the VSI - * @vsi: VSI for which NAPI handler is to be registered - * - * This function is only called in the driver's load path. Registering the NAPI - * handler is done in ice_vsi_alloc_q_vector() for all other cases (i.e. resume, - * reset/rebuild, etc.) - */ -static void ice_napi_add(struct ice_vsi *vsi) -{ - int v_idx; - - if (!vsi->netdev) - return; - - ice_for_each_q_vector(vsi, v_idx) { - netif_napi_add(vsi->netdev, &vsi->q_vectors[v_idx]->napi, - ice_napi_poll); - __ice_q_vector_set_napi_queues(vsi->q_vectors[v_idx], false); - } -} - -/** * ice_set_ops - set netdev and ethtools ops for the given netdev * @vsi: the VSI associated with the new netdev */ @@ -3534,7 +3548,7 @@ static void ice_set_ops(struct ice_vsi *vsi) * ice_set_netdev_features - set features for the given netdev * @netdev: netdev instance */ -static void ice_set_netdev_features(struct net_device *netdev) +void ice_set_netdev_features(struct net_device *netdev) { struct ice_pf *pf = ice_netdev_to_pf(netdev); bool is_dvm_ena = ice_is_dvm_ena(&pf->hw); @@ -3617,6 +3631,15 @@ static void ice_set_netdev_features(struct net_device *netdev) */ netdev->hw_features |= NETIF_F_RXFCS; + /* Allow core to manage IRQs affinity */ + netif_set_affinity_auto(netdev); + + /* Mutual exclusivity for TSO and GCS is enforced by the set features + * ndo callback. + */ + if (ice_is_feature_supported(pf, ICE_F_GCS)) + netdev->hw_features |= NETIF_F_HW_CSUM; + netif_set_tso_max_size(netdev, ICE_MAX_TSO_SIZE); } @@ -3648,7 +3671,7 @@ ice_pf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) struct ice_vsi_cfg_params params = {}; params.type = ICE_VSI_PF; - params.pi = pi; + params.port_info = pi; params.flags = ICE_VSI_FLAG_INIT; return ice_vsi_setup(pf, ¶ms); @@ -3661,7 +3684,7 @@ ice_chnl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, struct ice_vsi_cfg_params params = {}; params.type = ICE_VSI_CHNL; - params.pi = pi; + params.port_info = pi; params.ch = ch; params.flags = ICE_VSI_FLAG_INIT; @@ -3682,7 +3705,7 @@ ice_ctrl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) struct ice_vsi_cfg_params params = {}; params.type = ICE_VSI_CTRL; - params.pi = pi; + params.port_info = pi; params.flags = ICE_VSI_FLAG_INIT; return ice_vsi_setup(pf, ¶ms); @@ -3702,7 +3725,7 @@ ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) struct ice_vsi_cfg_params params = {}; params.type = ICE_VSI_LB; - params.pi = pi; + params.port_info = pi; params.flags = ICE_VSI_FLAG_INIT; return ice_vsi_setup(pf, ¶ms); @@ -3716,8 +3739,7 @@ ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) * * net_device_ops implementation for adding VLAN IDs */ -static int -ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) +int ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi_vlan_ops *vlan_ops; @@ -3779,8 +3801,7 @@ finish: * * net_device_ops implementation for removing VLAN IDs */ -static int -ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) +int ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi_vlan_ops *vlan_ops; @@ -3949,6 +3970,9 @@ static void ice_deinit_pf(struct ice_pf *pf) if (pf->ptp.clock) ptp_clock_unregister(pf->ptp.clock); + + xa_destroy(&pf->dyn_ports); + xa_destroy(&pf->sf_nums); } /** @@ -3993,8 +4017,7 @@ 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 && - !(pf->hw.mac_type == ICE_MAC_E830)) + if (func_caps->common_cap.ieee_1588) set_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags); pf->max_pf_txqs = func_caps->common_cap.num_txq; @@ -4040,7 +4063,14 @@ static int ice_init_pf(struct ice_pf *pf) mutex_init(&pf->vfs.table_lock); hash_init(pf->vfs.table); - ice_mbx_init_snapshot(&pf->hw); + if (ice_is_feature_supported(pf, ICE_F_MBX_LIMIT)) + wr32(&pf->hw, E830_MBX_PF_IN_FLIGHT_VF_MSGS_THRESH, + ICE_MBX_OVERFLOW_WATERMARK); + else + ice_mbx_init_snapshot(&pf->hw); + + xa_init(&pf->dyn_ports); + xa_init(&pf->sf_nums); return 0; } @@ -4079,7 +4109,7 @@ bool ice_is_wol_supported(struct ice_hw *hw) int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked) { struct ice_pf *pf = vsi->back; - int err = 0, timeout = 50; + int i, err = 0, timeout = 50; if (!new_rx && !new_tx) return -EINVAL; @@ -4098,15 +4128,32 @@ int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked) /* set for the next time the netdev is started */ if (!netif_running(vsi->netdev)) { - ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT); + err = ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT); + if (err) + goto rebuild_err; dev_dbg(ice_pf_to_dev(pf), "Link is down, queue count change happens when link is brought up\n"); goto done; } ice_vsi_close(vsi); - ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT); + err = ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT); + if (err) + goto rebuild_err; + + ice_for_each_traffic_class(i) { + if (vsi->tc_cfg.ena_tc & BIT(i)) + netdev_set_tc_queue(vsi->netdev, + vsi->tc_cfg.tc_info[i].netdev_tc, + vsi->tc_cfg.tc_info[i].qcount_tx, + vsi->tc_cfg.tc_info[i].qoffset); + } ice_pf_dcb_recfg(pf, locked); ice_vsi_open(vsi); + goto done; + +rebuild_err: + dev_err(ice_pf_to_dev(pf), "Error during VSI rebuild: %d. Unload and reload the driver.\n", + err); done: clear_bit(ICE_CFG_BUSY, pf->state); return err; @@ -4417,11 +4464,13 @@ static char *ice_get_opt_fw_name(struct ice_pf *pf) /** * ice_request_fw - Device initialization routine * @pf: pointer to the PF instance + * @firmware: double pointer to firmware struct + * + * Return: zero when successful, negative values otherwise. */ -static void ice_request_fw(struct ice_pf *pf) +static int ice_request_fw(struct ice_pf *pf, const struct firmware **firmware) { char *opt_fw_filename = ice_get_opt_fw_name(pf); - const struct firmware *firmware = NULL; struct device *dev = ice_pf_to_dev(pf); int err = 0; @@ -4430,29 +4479,120 @@ static void ice_request_fw(struct ice_pf *pf) * and warning messages for other errors. */ if (opt_fw_filename) { - err = firmware_request_nowarn(&firmware, opt_fw_filename, dev); - if (err) { - kfree(opt_fw_filename); - goto dflt_pkg_load; - } - - /* request for firmware was successful. Download to device */ - ice_load_pkg(firmware, pf); + err = firmware_request_nowarn(firmware, opt_fw_filename, dev); kfree(opt_fw_filename); - release_firmware(firmware); - return; + if (!err) + return err; } + err = request_firmware(firmware, ICE_DDP_PKG_FILE, dev); + if (err) + dev_err(dev, "The DDP package file was not found or could not be read. Entering Safe Mode\n"); -dflt_pkg_load: - err = request_firmware(&firmware, ICE_DDP_PKG_FILE, dev); + return err; +} + +/** + * ice_init_tx_topology - performs Tx topology initialization + * @hw: pointer to the hardware structure + * @firmware: pointer to firmware structure + * + * Return: zero when init was successful, negative values otherwise. + */ +static int +ice_init_tx_topology(struct ice_hw *hw, const struct firmware *firmware) +{ + u8 num_tx_sched_layers = hw->num_tx_sched_layers; + struct ice_pf *pf = hw->back; + struct device *dev; + int err; + + dev = ice_pf_to_dev(pf); + err = ice_cfg_tx_topo(hw, firmware->data, firmware->size); + if (!err) { + if (hw->num_tx_sched_layers > num_tx_sched_layers) + dev_info(dev, "Tx scheduling layers switching feature disabled\n"); + else + dev_info(dev, "Tx scheduling layers switching feature enabled\n"); + /* if there was a change in topology ice_cfg_tx_topo triggered + * a CORER and we need to re-init hw + */ + ice_deinit_hw(hw); + err = ice_init_hw(hw); + + return err; + } else if (err == -EIO) { + dev_info(dev, "DDP package does not support Tx scheduling layers switching feature - please update to the latest DDP package and try again\n"); + } + + return 0; +} + +/** + * ice_init_supported_rxdids - Initialize supported Rx descriptor IDs + * @hw: pointer to the hardware structure + * @pf: pointer to pf structure + * + * The pf->supported_rxdids bitmap is used to indicate to VFs which descriptor + * formats the PF hardware supports. The exact list of supported RXDIDs + * depends on the loaded DDP package. The IDs can be determined by reading the + * GLFLXP_RXDID_FLAGS register after the DDP package is loaded. + * + * Note that the legacy 32-byte RXDID 0 is always supported but is not listed + * in the DDP package. The 16-byte legacy descriptor is never supported by + * VFs. + */ +static void ice_init_supported_rxdids(struct ice_hw *hw, struct ice_pf *pf) +{ + pf->supported_rxdids = BIT(ICE_RXDID_LEGACY_1); + + for (int i = ICE_RXDID_FLEX_NIC; i < ICE_FLEX_DESC_RXDID_MAX_NUM; i++) { + u32 regval; + + regval = rd32(hw, GLFLXP_RXDID_FLAGS(i, 0)); + if ((regval >> GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S) + & GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M) + pf->supported_rxdids |= BIT(i); + } +} + +/** + * ice_init_ddp_config - DDP related configuration + * @hw: pointer to the hardware structure + * @pf: pointer to pf structure + * + * This function loads DDP file from the disk, then initializes Tx + * topology. At the end DDP package is loaded on the card. + * + * Return: zero when init was successful, negative values otherwise. + */ +static int ice_init_ddp_config(struct ice_hw *hw, struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + const struct firmware *firmware = NULL; + int err; + + err = ice_request_fw(pf, &firmware); if (err) { - dev_err(dev, "The DDP package file was not found or could not be read. Entering Safe Mode\n"); - return; + dev_err(dev, "Fail during requesting FW: %d\n", err); + return err; + } + + err = ice_init_tx_topology(hw, firmware); + if (err) { + dev_err(dev, "Fail during initialization of Tx topology: %d\n", + err); + release_firmware(firmware); + return err; } - /* request for firmware was successful. Download to device */ + /* Download firmware to device */ ice_load_pkg(firmware, pf); release_firmware(firmware); + + /* Initialize the supported Rx descriptor IDs after loading DDP */ + ice_init_supported_rxdids(hw, pf); + + return 0; } /** @@ -4574,64 +4714,21 @@ static void ice_decfg_netdev(struct ice_vsi *vsi) vsi->netdev = NULL; } -/** - * 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; -} - int ice_init_dev(struct ice_pf *pf) { struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; int err; - err = ice_init_hw(hw); - if (err) { - dev_err(dev, "ice_init_hw failed: %d\n", err); - 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); + err = ice_init_ddp_config(hw, pf); - /* if ice_request_fw fails, ICE_FLAG_ADV_FEATURES bit won't be + /* if ice_init_ddp_config fails, ICE_FLAG_ADV_FEATURES bit won't be * set in pf->state, which will cause ice_is_safe_mode to return * true */ - if (ice_is_safe_mode(pf)) { + if (err || ice_is_safe_mode(pf)) { /* we already got function/device capabilities but these don't * reflect what the driver needs to do in safe mode. Instead of * adding conditional logic everywhere to ignore these @@ -4643,7 +4740,7 @@ int ice_init_dev(struct ice_pf *pf) err = ice_init_pf(pf); if (err) { dev_err(dev, "ice_init_pf failed: %d\n", err); - goto err_init_pf; + return err; } pf->hw.udp_tunnel_nic.set_port = ice_udp_tunnel_set_port; @@ -4667,7 +4764,7 @@ int ice_init_dev(struct ice_pf *pf) if (err) { dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err); err = -EIO; - goto err_init_interrupt_scheme; + goto unroll_pf_init; } /* In case of MSIX we are going to setup the misc vector right here @@ -4678,17 +4775,15 @@ int ice_init_dev(struct ice_pf *pf) err = ice_req_irq_msix_misc(pf); if (err) { dev_err(dev, "setup of misc vector failed: %d\n", err); - goto err_req_irq_msix_misc; + goto unroll_irq_scheme_init; } return 0; -err_req_irq_msix_misc: +unroll_irq_scheme_init: ice_clear_interrupt_scheme(pf); -err_init_interrupt_scheme: +unroll_pf_init: ice_deinit_pf(pf); -err_init_pf: - ice_deinit_hw(hw); return err; } @@ -4921,12 +5016,14 @@ static int ice_init_devlink(struct ice_pf *pf) ice_devlink_init_regions(pf); ice_devlink_register(pf); + ice_health_init(pf); return 0; } static void ice_deinit_devlink(struct ice_pf *pf) { + ice_health_deinit(pf); ice_devlink_unregister(pf); ice_devlink_destroy_regions(pf); ice_devlink_unregister_params(pf); @@ -4940,6 +5037,12 @@ static int ice_init(struct ice_pf *pf) if (err) return err; + if (pf->hw.mac_type == ICE_MAC_E830) { + err = pci_enable_ptm(pf->pdev, NULL); + if (err) + dev_dbg(ice_pf_to_dev(pf), "PCIe PTM not supported by PCIe bus/controller\n"); + } + err = ice_alloc_vsis(pf); if (err) goto err_alloc_vsis; @@ -5039,11 +5142,12 @@ int ice_load(struct ice_pf *pf) ice_napi_add(vsi); + ice_init_features(pf); + err = ice_init_rdma(pf); if (err) goto err_init_rdma; - ice_init_features(pf); ice_service_task_restart(pf); clear_bit(ICE_DOWN, pf->state); @@ -5051,6 +5155,7 @@ int ice_load(struct ice_pf *pf) return 0; err_init_rdma: + ice_deinit_features(pf); ice_tc_indir_block_unregister(vsi); err_tc_indir_block_register: ice_unregister_netdev(vsi); @@ -5074,14 +5179,44 @@ void ice_unload(struct ice_pf *pf) devl_assert_locked(priv_to_devlink(pf)); - ice_deinit_features(pf); ice_deinit_rdma(pf); + ice_deinit_features(pf); ice_tc_indir_block_unregister(vsi); ice_unregister_netdev(vsi); ice_devlink_destroy_pf_port(pf); ice_decfg_netdev(vsi); } +static int ice_probe_recovery_mode(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + int err; + + dev_err(dev, "Firmware recovery mode detected. Limiting functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode\n"); + + INIT_HLIST_HEAD(&pf->aq_wait_list); + spin_lock_init(&pf->aq_wait_lock); + init_waitqueue_head(&pf->aq_wait_queue); + + timer_setup(&pf->serv_tmr, ice_service_timer, 0); + pf->serv_tmr_period = HZ; + INIT_WORK(&pf->serv_task, ice_service_task_recovery_mode); + clear_bit(ICE_SERVICE_SCHED, pf->state); + err = ice_create_all_ctrlq(&pf->hw); + if (err) + return err; + + scoped_guard(devl, priv_to_devlink(pf)) { + err = ice_init_devlink(pf); + if (err) + return err; + } + + ice_service_task_restart(pf); + + return 0; +} + /** * ice_probe - Device initialization routine * @pdev: PCI device information struct @@ -5093,6 +5228,7 @@ static int ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) { struct device *dev = &pdev->dev; + struct ice_adapter *adapter; struct ice_pf *pf; struct ice_hw *hw; int err; @@ -5144,7 +5280,6 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) } pci_set_master(pdev); - pf->pdev = pdev; pci_set_drvdata(pdev, pf); set_bit(ICE_DOWN, pf->state); @@ -5173,30 +5308,47 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) hw->debug_mask = debug; #endif + if (ice_is_recovery_mode(hw)) + return ice_probe_recovery_mode(pf); + + err = ice_init_hw(hw); + if (err) { + dev_err(dev, "ice_init_hw failed: %d\n", err); + return err; + } + + adapter = ice_adapter_get(pdev); + if (IS_ERR(adapter)) { + err = PTR_ERR(adapter); + goto unroll_hw_init; + } + pf->adapter = adapter; + err = ice_init(pf); if (err) - goto err_init; + goto unroll_adapter; devl_lock(priv_to_devlink(pf)); err = ice_load(pf); - devl_unlock(priv_to_devlink(pf)); if (err) - goto err_load; + goto unroll_init; err = ice_init_devlink(pf); if (err) - goto err_init_devlink; + goto unroll_load; + devl_unlock(priv_to_devlink(pf)); return 0; -err_init_devlink: - devl_lock(priv_to_devlink(pf)); +unroll_load: ice_unload(pf); +unroll_init: devl_unlock(priv_to_devlink(pf)); -err_load: ice_deinit(pf); -err_init: - pci_disable_device(pdev); +unroll_adapter: + ice_adapter_put(pdev); +unroll_hw_init: + ice_deinit_hw(hw); return err; } @@ -5276,6 +5428,14 @@ static void ice_remove(struct pci_dev *pdev) msleep(100); } + if (ice_is_recovery_mode(&pf->hw)) { + ice_service_task_stop(pf); + scoped_guard(devl, priv_to_devlink(pf)) { + ice_deinit_devlink(pf); + } + return; + } + if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) { set_bit(ICE_VF_RESETS_DISABLED, pf->state); ice_free_vfs(pf); @@ -5290,9 +5450,10 @@ static void ice_remove(struct pci_dev *pdev) if (!ice_is_safe_mode(pf)) ice_remove_arfs(pf); + devl_lock(priv_to_devlink(pf)); + ice_dealloc_all_dynamic_ports(pf); ice_deinit_devlink(pf); - devl_lock(priv_to_devlink(pf)); ice_unload(pf); devl_unlock(priv_to_devlink(pf)); @@ -5302,7 +5463,7 @@ static void ice_remove(struct pci_dev *pdev) ice_setup_mc_magic_wake(pf); ice_set_wake(pf); - pci_disable_device(pdev); + ice_adapter_put(pdev); } /** @@ -5321,7 +5482,6 @@ static void ice_shutdown(struct pci_dev *pdev) } } -#ifdef CONFIG_PM /** * ice_prepare_for_shutdown - prep for PCI shutdown * @pf: board private structure @@ -5346,7 +5506,7 @@ static void ice_prepare_for_shutdown(struct ice_pf *pf) if (pf->vsi[v]) pf->vsi[v]->vsi_num = 0; - ice_shutdown_all_ctrlq(hw); + ice_shutdown_all_ctrlq(hw, true); } /** @@ -5383,7 +5543,9 @@ static int ice_reinit_interrupt_scheme(struct ice_pf *pf) if (ret) goto err_reinit; ice_vsi_map_rings_to_vectors(pf->vsi[v]); + rtnl_lock(); ice_vsi_set_napi_queues(pf->vsi[v]); + rtnl_unlock(); } ret = ice_req_irq_msix_misc(pf); @@ -5397,8 +5559,12 @@ static int ice_reinit_interrupt_scheme(struct ice_pf *pf) err_reinit: while (v--) - if (pf->vsi[v]) + if (pf->vsi[v]) { + rtnl_lock(); + ice_vsi_clear_napi_queues(pf->vsi[v]); + rtnl_unlock(); ice_vsi_free_q_vectors(pf->vsi[v]); + } return ret; } @@ -5410,7 +5576,7 @@ err_reinit: * Power Management callback to quiesce the device and prepare * for D3 transition. */ -static int __maybe_unused ice_suspend(struct device *dev) +static int ice_suspend(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct ice_pf *pf; @@ -5431,7 +5597,7 @@ static int __maybe_unused ice_suspend(struct device *dev) */ disabled = ice_service_task_stop(pf); - ice_unplug_aux_dev(pf); + ice_deinit_rdma(pf); /* Already suspended?, then there is nothing to do */ if (test_and_set_bit(ICE_SUSPENDED, pf->state)) { @@ -5463,6 +5629,9 @@ static int __maybe_unused ice_suspend(struct device *dev) ice_for_each_vsi(pf, v) { if (!pf->vsi[v]) continue; + rtnl_lock(); + ice_vsi_clear_napi_queues(pf->vsi[v]); + rtnl_unlock(); ice_vsi_free_q_vectors(pf->vsi[v]); } ice_clear_interrupt_scheme(pf); @@ -5477,7 +5646,7 @@ static int __maybe_unused ice_suspend(struct device *dev) * ice_resume - PM callback for waking up from D3 * @dev: generic device information structure */ -static int __maybe_unused ice_resume(struct device *dev) +static int ice_resume(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); enum ice_reset_req reset_type; @@ -5511,6 +5680,11 @@ static int __maybe_unused ice_resume(struct device *dev) if (ret) dev_err(dev, "Cannot restore interrupt scheme: %d\n", ret); + ret = ice_init_rdma(pf); + if (ret) + dev_err(dev, "Reinitialize RDMA during resume failed: %d\n", + ret); + clear_bit(ICE_DOWN, pf->state); /* Now perform PF reset and rebuild */ reset_type = ICE_RESET_PFR; @@ -5528,7 +5702,6 @@ static int __maybe_unused ice_resume(struct device *dev) return 0; } -#endif /* CONFIG_PM */ /** * ice_pci_err_detected - warning that PCI error has been detected @@ -5693,16 +5866,22 @@ static const struct pci_device_id ice_pci_tbl[] = { { PCI_VDEVICE(INTEL, ICE_DEV_ID_E825C_QSFP), }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_E825C_SFP), }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_E825C_SGMII), }, - { 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) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830CC_BACKPLANE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830CC_QSFP56) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830CC_SFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830CC_SFP_DD) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830C_BACKPLANE), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_XXV_BACKPLANE), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830C_QSFP), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_XXV_QSFP), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830C_SFP), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_XXV_SFP), }, /* required last entry */ {} }; MODULE_DEVICE_TABLE(pci, ice_pci_tbl); -static __maybe_unused SIMPLE_DEV_PM_OPS(ice_pm_ops, ice_suspend, ice_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(ice_pm_ops, ice_suspend, ice_resume); static const struct pci_error_handlers ice_pci_err_handler = { .error_detected = ice_pci_err_detected, @@ -5717,9 +5896,7 @@ static struct pci_driver ice_driver = { .id_table = ice_pci_tbl, .probe = ice_probe, .remove = ice_remove, -#ifdef CONFIG_PM - .driver.pm = &ice_pm_ops, -#endif /* CONFIG_PM */ + .driver.pm = pm_sleep_ptr(&ice_pm_ops), .shutdown = ice_shutdown, .sriov_configure = ice_sriov_configure, .sriov_get_vf_total_msix = ice_sriov_get_vf_total_msix, @@ -5742,7 +5919,7 @@ static int __init ice_module_init(void) ice_adv_lnk_speed_maps_init(); - ice_wq = alloc_workqueue("%s", 0, 0, KBUILD_MODNAME); + ice_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, KBUILD_MODNAME); if (!ice_wq) { pr_err("Failed to create workqueue\n"); return status; @@ -5762,8 +5939,16 @@ static int __init ice_module_init(void) goto err_dest_lag_wq; } + status = ice_sf_driver_register(); + if (status) { + pr_err("Failed to register SF driver, err %d\n", status); + goto err_sf_driver; + } + return 0; +err_sf_driver: + pci_unregister_driver(&ice_driver); err_dest_lag_wq: destroy_workqueue(ice_lag_wq); ice_debugfs_exit(); @@ -5781,6 +5966,7 @@ module_init(ice_module_init); */ static void __exit ice_module_exit(void) { + ice_sf_driver_unregister(); pci_unregister_driver(&ice_driver); ice_debugfs_exit(); destroy_workqueue(ice_wq); @@ -5958,12 +6144,14 @@ ice_set_tx_maxrate(struct net_device *netdev, int queue_index, u32 maxrate) * @addr: the MAC address entry being added * @vid: VLAN ID * @flags: instructions from stack about fdb operation + * @notified: whether notification was emitted * @extack: netlink extended ack */ static int ice_fdb_add(struct ndmsg *ndm, struct nlattr __always_unused *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, - u16 flags, struct netlink_ext_ack __always_unused *extack) + u16 flags, bool *notified, + struct netlink_ext_ack __always_unused *extack) { int err; @@ -5997,12 +6185,14 @@ ice_fdb_add(struct ndmsg *ndm, struct nlattr __always_unused *tb[], * @dev: the net device pointer * @addr: the MAC address entry being added * @vid: VLAN ID + * @notified: whether notification was emitted * @extack: netlink extended ack */ static int ice_fdb_del(struct ndmsg *ndm, __always_unused struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, - __always_unused u16 vid, struct netlink_ext_ack *extack) + __always_unused u16 vid, bool *notified, + struct netlink_ext_ack *extack) { int err; @@ -6206,10 +6396,12 @@ ice_set_vlan_filtering_features(struct ice_vsi *vsi, netdev_features_t features) int err = 0; /* support Single VLAN Mode (SVM) and Double VLAN Mode (DVM) by checking - * if either bit is set + * if either bit is set. In switchdev mode Rx filtering should never be + * enabled. */ - if (features & - (NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER)) + if ((features & + (NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER)) && + !ice_is_eswitch_mode_switchdev(vsi->back)) err = vlan_ops->ena_rx_filtering(vsi); else err = vlan_ops->dis_rx_filtering(vsi); @@ -6357,13 +6549,24 @@ ice_set_features(struct net_device *netdev, netdev_features_t features) if (changed & NETIF_F_HW_TC) { bool ena = !!(features & NETIF_F_HW_TC); - ena ? set_bit(ICE_FLAG_CLS_FLOWER, pf->flags) : - clear_bit(ICE_FLAG_CLS_FLOWER, pf->flags); + assign_bit(ICE_FLAG_CLS_FLOWER, pf->flags, ena); } if (changed & NETIF_F_LOOPBACK) ret = ice_set_loopback(vsi, !!(features & NETIF_F_LOOPBACK)); + /* Due to E830 hardware limitations, TSO (NETIF_F_ALL_TSO) with GCS + * (NETIF_F_HW_CSUM) is not supported. + */ + if (ice_is_feature_supported(pf, ICE_F_GCS) && + ((features & NETIF_F_HW_CSUM) && (features & NETIF_F_ALL_TSO))) { + if (netdev->features & NETIF_F_HW_CSUM) + dev_err(ice_pf_to_dev(pf), "To enable TSO, you must first disable HW checksum.\n"); + else + dev_err(ice_pf_to_dev(pf), "To enable HW checksum, you must first disable TSO.\n"); + return -EIO; + } + return ret; } @@ -6582,11 +6785,12 @@ static int ice_up_complete(struct ice_vsi *vsi) if (vsi->port_info && (vsi->port_info->phy.link_info.link_info & ICE_AQ_LINK_UP) && - vsi->netdev && vsi->type == ICE_VSI_PF) { + ((vsi->netdev && (vsi->type == ICE_VSI_PF || + vsi->type == ICE_VSI_SF)))) { ice_print_link_msg(vsi, true); netif_tx_start_all_queues(vsi->netdev); netif_carrier_on(vsi->netdev); - ice_ptp_link_change(pf, pf->hw.pf_id, true); + ice_ptp_link_change(pf, true); } /* Perform an initial read of the statistics registers now to @@ -6940,7 +7144,6 @@ void ice_update_pf_stats(struct ice_pf *pf) * @netdev: network interface device structure * @stats: main device statistics structure */ -static void ice_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) { struct ice_netdev_priv *np = netdev_priv(netdev); @@ -7055,13 +7258,11 @@ int ice_down(struct ice_vsi *vsi) WARN_ON(!test_bit(ICE_VSI_DOWN, vsi->state)); - if (vsi->netdev && vsi->type == ICE_VSI_PF) { + if (vsi->netdev) { vlan_err = ice_vsi_del_vlan_zero(vsi); - ice_ptp_link_change(vsi->back, vsi->back->hw.pf_id, false); + ice_ptp_link_change(vsi->back, false); netif_carrier_off(vsi->netdev); netif_tx_disable(vsi->netdev); - } else if (vsi->type == ICE_VSI_SWITCHDEV_CTRL) { - ice_eswitch_stop_all_tx_queues(vsi->back); } ice_vsi_dis_irq(vsi); @@ -7070,7 +7271,7 @@ int ice_down(struct ice_vsi *vsi) if (tx_err) netdev_err(vsi->netdev, "Failed stop Tx rings, VSI %d error %d\n", vsi->vsi_num, tx_err); - if (!tx_err && ice_is_xdp_ena_vsi(vsi)) { + if (!tx_err && vsi->xdp_rings) { tx_err = ice_vsi_stop_xdp_tx_rings(vsi); if (tx_err) netdev_err(vsi->netdev, "Failed stop XDP rings, VSI %d error %d\n", @@ -7087,7 +7288,7 @@ int ice_down(struct ice_vsi *vsi) ice_for_each_txq(vsi, i) ice_clean_tx_ring(vsi->tx_rings[i]); - if (ice_is_xdp_ena_vsi(vsi)) + if (vsi->xdp_rings) ice_for_each_xdp_txq(vsi, i) ice_clean_tx_ring(vsi->xdp_rings[i]); @@ -7283,7 +7484,7 @@ int ice_vsi_open(struct ice_vsi *vsi) ice_vsi_cfg_netdev_tc(vsi, vsi->tc_cfg.ena_tc); - if (vsi->type == ICE_VSI_PF) { + if (vsi->type == ICE_VSI_PF || vsi->type == ICE_VSI_SF) { /* Notify the stack of the actual queue counts. */ err = netif_set_real_num_tx_queues(vsi->netdev, vsi->num_txq); if (err) @@ -7292,6 +7493,8 @@ int ice_vsi_open(struct ice_vsi *vsi) err = netif_set_real_num_rx_queues(vsi->netdev, vsi->num_rxq); if (err) goto err_set_qs; + + ice_vsi_set_napi_queues(vsi); } err = ice_up_complete(vsi); @@ -7429,6 +7632,7 @@ static void ice_update_pf_netdev_link(struct ice_pf *pf) */ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) { + struct ice_vsi *vsi = ice_get_main_vsi(pf); struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; bool dvm; @@ -7544,12 +7748,6 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) goto err_vsi_rebuild; } - err = ice_eswitch_rebuild(pf); - if (err) { - dev_err(dev, "Switchdev rebuild failed: %d\n", err); - goto err_vsi_rebuild; - } - if (reset_type == ICE_RESET_PFR) { err = ice_rebuild_channels(pf); if (err) { @@ -7577,6 +7775,9 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) ice_rebuild_arfs(pf); } + if (vsi && vsi->netdev) + netif_device_attach(vsi->netdev); + ice_update_pf_netdev_link(pf); /* tell the firmware we are up */ @@ -7592,6 +7793,8 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) /* if we get here, reset flow is successful */ clear_bit(ICE_RESET_FAILED, pf->state); + ice_health_clear(pf); + ice_plug_aux_dev(pf); if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) ice_lag_rebuild(pf); @@ -7604,7 +7807,7 @@ err_vsi_rebuild: err_sched_init_port: ice_sched_cleanup_all(hw); err_init_ctrlq: - ice_shutdown_all_ctrlq(hw); + ice_shutdown_all_ctrlq(hw, false); set_bit(ICE_RESET_FAILED, pf->state); clear_recovery: /* set this bit in PF state to control service task scheduling */ @@ -7619,7 +7822,7 @@ clear_recovery: * * Returns 0 on success, negative on failure */ -static int ice_change_mtu(struct net_device *netdev, int new_mtu) +int ice_change_mtu(struct net_device *netdev, int new_mtu) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; @@ -7666,7 +7869,7 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) return -EBUSY; } - netdev->mtu = (unsigned int)new_mtu; + WRITE_ONCE(netdev->mtu, (unsigned int)new_mtu); err = ice_down_up(vsi); if (err) return err; @@ -7999,12 +8202,9 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, if (!br_spec) return -EINVAL; - nla_for_each_nested(attr, br_spec, rem) { - __u16 mode; + nla_for_each_nested_type(attr, IFLA_BRIDGE_MODE, br_spec, rem) { + __u16 mode = nla_get_u16(attr); - if (nla_type(attr) != IFLA_BRIDGE_MODE) - continue; - mode = nla_get_u16(attr); if (mode != BRIDGE_MODE_VEPA && mode != BRIDGE_MODE_VEB) return -EINVAL; /* Continue if bridge mode is not being flipped */ @@ -8046,7 +8246,7 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, * @netdev: network interface device structure * @txqueue: Tx queue */ -static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) +void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_tx_ring *tx_ring = NULL; @@ -8085,16 +8285,18 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) if (tx_ring) { struct ice_hw *hw = &pf->hw; - u32 head, val = 0; + u32 head, intr = 0; head = FIELD_GET(QTX_COMM_HEAD_HEAD_M, rd32(hw, QTX_COMM_HEAD(vsi->txq_map[txqueue]))); /* Read interrupt register */ - val = rd32(hw, GLINT_DYN_CTL(tx_ring->q_vector->reg_idx)); + intr = rd32(hw, GLINT_DYN_CTL(tx_ring->q_vector->reg_idx)); netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %u, NTC: 0x%x, HW_HEAD: 0x%x, NTU: 0x%x, INT: 0x%x\n", vsi->vsi_num, txqueue, tx_ring->next_to_clean, - head, tx_ring->next_to_use, val); + head, tx_ring->next_to_use, intr); + + ice_prep_tx_hang_report(pf, tx_ring, vsi->vsi_num, head, intr); } pf->tx_timeout_last_recovery = jiffies; @@ -8128,11 +8330,16 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) * @np: net device to configure * @filter_dev: device on which filter is added * @cls_flower: offload data + * @ingress: if the rule is added to an ingress block + * + * Return: 0 if the flower was successfully added or deleted, + * negative error code otherwise. */ static int ice_setup_tc_cls_flower(struct ice_netdev_priv *np, struct net_device *filter_dev, - struct flow_cls_offload *cls_flower) + struct flow_cls_offload *cls_flower, + bool ingress) { struct ice_vsi *vsi = np->vsi; @@ -8141,7 +8348,7 @@ ice_setup_tc_cls_flower(struct ice_netdev_priv *np, switch (cls_flower->command) { case FLOW_CLS_REPLACE: - return ice_add_cls_flower(filter_dev, vsi, cls_flower); + return ice_add_cls_flower(filter_dev, vsi, cls_flower, ingress); case FLOW_CLS_DESTROY: return ice_del_cls_flower(vsi, cls_flower); default: @@ -8150,20 +8357,46 @@ ice_setup_tc_cls_flower(struct ice_netdev_priv *np, } /** - * ice_setup_tc_block_cb - callback handler registered for TC block + * ice_setup_tc_block_cb_ingress - callback handler for ingress TC block * @type: TC SETUP type * @type_data: TC flower offload data that contains user input * @cb_priv: netdev private data + * + * Return: 0 if the setup was successful, negative error code otherwise. */ static int -ice_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv) +ice_setup_tc_block_cb_ingress(enum tc_setup_type type, void *type_data, + void *cb_priv) { struct ice_netdev_priv *np = cb_priv; switch (type) { case TC_SETUP_CLSFLOWER: return ice_setup_tc_cls_flower(np, np->vsi->netdev, - type_data); + type_data, true); + default: + return -EOPNOTSUPP; + } +} + +/** + * ice_setup_tc_block_cb_egress - callback handler for egress TC block + * @type: TC SETUP type + * @type_data: TC flower offload data that contains user input + * @cb_priv: netdev private data + * + * Return: 0 if the setup was successful, negative error code otherwise. + */ +static int +ice_setup_tc_block_cb_egress(enum tc_setup_type type, void *type_data, + void *cb_priv) +{ + struct ice_netdev_priv *np = cb_priv; + + switch (type) { + case TC_SETUP_CLSFLOWER: + return ice_setup_tc_cls_flower(np, np->vsi->netdev, + type_data, false); default: return -EOPNOTSUPP; } @@ -9108,27 +9341,45 @@ ice_setup_tc(struct net_device *netdev, enum tc_setup_type type, void *type_data) { struct ice_netdev_priv *np = netdev_priv(netdev); + enum flow_block_binder_type binder_type; + struct iidc_rdma_core_dev_info *cdev; struct ice_pf *pf = np->vsi->back; + flow_setup_cb_t *flower_handler; bool locked = false; int err; switch (type) { case TC_SETUP_BLOCK: + binder_type = + ((struct flow_block_offload *)type_data)->binder_type; + + switch (binder_type) { + case FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS: + flower_handler = ice_setup_tc_block_cb_ingress; + break; + case FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS: + flower_handler = ice_setup_tc_block_cb_egress; + break; + default: + return -EOPNOTSUPP; + } + return flow_block_cb_setup_simple(type_data, &ice_block_cb_list, - ice_setup_tc_block_cb, - np, np, true); + flower_handler, + np, np, false); case TC_SETUP_QDISC_MQPRIO: if (ice_is_eswitch_mode_switchdev(pf)) { netdev_err(netdev, "TC MQPRIO offload not supported, switchdev is enabled\n"); return -EOPNOTSUPP; } - if (pf->adev) { + cdev = pf->cdev_info; + if (cdev && cdev->adev) { mutex_lock(&pf->adev_mutex); - device_lock(&pf->adev->dev); + device_lock(&cdev->adev->dev); locked = true; - if (pf->adev->dev.driver) { + if (cdev->adev->dev.driver) { netdev_err(netdev, "Cannot change qdisc when RDMA is active\n"); err = -EBUSY; goto adev_unlock; @@ -9142,7 +9393,7 @@ ice_setup_tc(struct net_device *netdev, enum tc_setup_type type, adev_unlock: if (locked) { - device_unlock(&pf->adev->dev); + device_unlock(&cdev->adev->dev); mutex_unlock(&pf->adev_mutex); } return err; @@ -9178,7 +9429,7 @@ ice_indr_setup_block_cb(enum tc_setup_type type, void *type_data, case TC_SETUP_CLSFLOWER: return ice_setup_tc_cls_flower(np, priv->netdev, (struct flow_cls_offload *) - type_data); + type_data, false); default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c index d4e05d2cb30c..59e8879ac059 100644 --- a/drivers/net/ethernet/intel/ice/ice_nvm.c +++ b/drivers/net/ethernet/intel/ice/ice_nvm.c @@ -18,10 +18,9 @@ * * Read the NVM using the admin queue commands (0x0701) */ -static int -ice_aq_read_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset, u16 length, - void *data, bool last_command, bool read_shadow_ram, - struct ice_sq_cd *cd) +int ice_aq_read_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset, + u16 length, void *data, bool last_command, + bool read_shadow_ram, struct ice_sq_cd *cd) { struct ice_aq_desc desc; struct ice_aqc_nvm *cmd; @@ -375,11 +374,25 @@ ice_read_nvm_module(struct ice_hw *hw, enum ice_bank_select bank, u32 offset, u1 * * Read the specified word from the copy of the Shadow RAM found in the * specified NVM module. + * + * Note that the Shadow RAM copy is always located after the CSS header, and + * is aligned to 64-byte (32-word) offsets. */ static int ice_read_nvm_sr_copy(struct ice_hw *hw, enum ice_bank_select bank, u32 offset, u16 *data) { - return ice_read_nvm_module(hw, bank, ICE_NVM_SR_COPY_WORD_OFFSET + offset, data); + u32 sr_copy; + + switch (bank) { + case ICE_ACTIVE_FLASH_BANK: + sr_copy = roundup(hw->flash.banks.active_css_hdr_len, 32); + break; + case ICE_INACTIVE_FLASH_BANK: + sr_copy = roundup(hw->flash.banks.inactive_css_hdr_len, 32); + break; + } + + return ice_read_nvm_module(hw, bank, sr_copy + offset, data); } /** @@ -441,8 +454,7 @@ int ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len, u16 module_type) { - u16 pfa_len, pfa_ptr; - u16 next_tlv; + u16 pfa_len, pfa_ptr, next_tlv, max_tlv; int status; status = ice_read_sr_word(hw, ICE_SR_PFA_PTR, &pfa_ptr); @@ -455,11 +467,23 @@ ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len, ice_debug(hw, ICE_DBG_INIT, "Failed to read PFA length.\n"); return status; } + + /* The Preserved Fields Area contains a sequence of Type-Length-Value + * structures which define its contents. The PFA length includes all + * of the TLVs, plus the initial length word itself, *and* one final + * word at the end after all of the TLVs. + */ + if (check_add_overflow(pfa_ptr, pfa_len - 1, &max_tlv)) { + dev_warn(ice_hw_to_dev(hw), "PFA starts at offset %u. PFA length of %u caused 16-bit arithmetic overflow.\n", + pfa_ptr, pfa_len); + return -EINVAL; + } + /* Starting with first TLV after PFA length, iterate through the list * of TLVs to find the requested one. */ next_tlv = pfa_ptr + 1; - while (next_tlv < pfa_ptr + pfa_len) { + while (next_tlv < max_tlv) { u16 tlv_sub_module_type; u16 tlv_len; @@ -483,10 +507,13 @@ ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len, } return -EINVAL; } - /* Check next TLV, i.e. current TLV pointer + length + 2 words - * (for current TLV's type and length) - */ - next_tlv = next_tlv + tlv_len + 2; + + if (check_add_overflow(next_tlv, 2, &next_tlv) || + check_add_overflow(next_tlv, tlv_len, &next_tlv)) { + dev_warn(ice_hw_to_dev(hw), "TLV of type %u and length 0x%04x caused 16-bit arithmetic overflow. The PFA starts at 0x%04x and has length of 0x%04x\n", + tlv_sub_module_type, tlv_len, pfa_ptr, pfa_len); + return -EINVAL; + } } /* Module does not exist */ return -ENOENT; @@ -1011,6 +1038,72 @@ static int ice_determine_active_flash_banks(struct ice_hw *hw) } /** + * ice_get_nvm_css_hdr_len - Read the CSS header length from the NVM CSS header + * @hw: pointer to the HW struct + * @bank: whether to read from the active or inactive flash bank + * @hdr_len: storage for header length in words + * + * Read the CSS header length from the NVM CSS header and add the Authentication + * header size, and then convert to words. + * + * Return: zero on success, or a negative error code on failure. + */ +static int +ice_get_nvm_css_hdr_len(struct ice_hw *hw, enum ice_bank_select bank, + u32 *hdr_len) +{ + u16 hdr_len_l, hdr_len_h; + u32 hdr_len_dword; + int status; + + status = ice_read_nvm_module(hw, bank, ICE_NVM_CSS_HDR_LEN_L, + &hdr_len_l); + if (status) + return status; + + status = ice_read_nvm_module(hw, bank, ICE_NVM_CSS_HDR_LEN_H, + &hdr_len_h); + if (status) + return status; + + /* CSS header length is in DWORD, so convert to words and add + * authentication header size + */ + hdr_len_dword = hdr_len_h << 16 | hdr_len_l; + *hdr_len = (hdr_len_dword * 2) + ICE_NVM_AUTH_HEADER_LEN; + + return 0; +} + +/** + * ice_determine_css_hdr_len - Discover CSS header length for the device + * @hw: pointer to the HW struct + * + * Determine the size of the CSS header at the start of the NVM module. This + * is useful for locating the Shadow RAM copy in the NVM, as the Shadow RAM is + * always located just after the CSS header. + * + * Return: zero on success, or a negative error code on failure. + */ +static int ice_determine_css_hdr_len(struct ice_hw *hw) +{ + struct ice_bank_info *banks = &hw->flash.banks; + int status; + + status = ice_get_nvm_css_hdr_len(hw, ICE_ACTIVE_FLASH_BANK, + &banks->active_css_hdr_len); + if (status) + return status; + + status = ice_get_nvm_css_hdr_len(hw, ICE_INACTIVE_FLASH_BANK, + &banks->inactive_css_hdr_len); + if (status) + return status; + + return 0; +} + +/** * ice_init_nvm - initializes NVM setting * @hw: pointer to the HW struct * @@ -1056,6 +1149,12 @@ int ice_init_nvm(struct ice_hw *hw) return status; } + status = ice_determine_css_hdr_len(hw); + if (status) { + ice_debug(hw, ICE_DBG_NVM, "Failed to determine Shadow RAM copy offsets.\n"); + return status; + } + status = ice_get_nvm_ver_info(hw, ICE_ACTIVE_FLASH_BANK, &flash->nvm); if (status) { ice_debug(hw, ICE_DBG_INIT, "Failed to read NVM info.\n"); diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.h b/drivers/net/ethernet/intel/ice/ice_nvm.h index 774c2317967d..63cdc6bdac58 100644 --- a/drivers/net/ethernet/intel/ice/ice_nvm.h +++ b/drivers/net/ethernet/intel/ice/ice_nvm.h @@ -14,6 +14,9 @@ struct ice_orom_civd_info { int ice_acquire_nvm(struct ice_hw *hw, enum ice_aq_res_access_type access); void ice_release_nvm(struct ice_hw *hw); +int ice_aq_read_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset, + u16 length, void *data, bool last_command, + bool read_shadow_ram, struct ice_sq_cd *cd); int ice_read_flat_nvm(struct ice_hw *hw, u32 offset, u32 *length, u8 *data, bool read_shadow_ram); diff --git a/drivers/net/ethernet/intel/ice/ice_osdep.h b/drivers/net/ethernet/intel/ice/ice_osdep.h index a2562f04267f..b9f383494b3f 100644 --- a/drivers/net/ethernet/intel/ice/ice_osdep.h +++ b/drivers/net/ethernet/intel/ice/ice_osdep.h @@ -12,6 +12,7 @@ #include <linux/ethtool.h> #include <linux/etherdevice.h> #include <linux/if_ether.h> +#include <linux/iopoll.h> #include <linux/pci_ids.h> #ifndef CONFIG_64BIT #include <linux/io-64-nonatomic-lo-hi.h> @@ -23,6 +24,9 @@ #define wr64(a, reg, value) writeq((value), ((a)->hw_addr + (reg))) #define rd64(a, reg) readq((a)->hw_addr + (reg)) +#define rd32_poll_timeout(a, addr, val, cond, delay_us, timeout_us) \ + read_poll_timeout(rd32, val, cond, delay_us, timeout_us, false, a, addr) + #define ice_flush(a) rd32((a), GLGEN_STAT) #define ICE_M(m, s) ((m ## U) << (s)) @@ -39,11 +43,10 @@ struct device *ice_hw_to_dev(struct ice_hw *hw); #define ice_debug(hw, type, fmt, args...) \ dev_dbg(ice_hw_to_dev(hw), fmt, ##args) -#define ice_debug_array(hw, type, rowsize, groupsize, buf, len) \ - print_hex_dump_debug(KBUILD_MODNAME " ", \ - DUMP_PREFIX_OFFSET, rowsize, \ - groupsize, buf, len, false) -#else +#define _ice_debug_array(hw, type, prefix, rowsize, groupsize, buf, len) \ + print_hex_dump_debug(prefix, DUMP_PREFIX_OFFSET, \ + rowsize, groupsize, buf, len, false) +#else /* CONFIG_DYNAMIC_DEBUG */ #define ice_debug(hw, type, fmt, args...) \ do { \ if ((type) & (hw)->debug_mask) \ @@ -51,16 +54,15 @@ do { \ } while (0) #ifdef DEBUG -#define ice_debug_array(hw, type, rowsize, groupsize, buf, len) \ +#define _ice_debug_array(hw, type, prefix, rowsize, groupsize, buf, len) \ do { \ if ((type) & (hw)->debug_mask) \ - print_hex_dump_debug(KBUILD_MODNAME, \ - DUMP_PREFIX_OFFSET, \ + print_hex_dump_debug(prefix, DUMP_PREFIX_OFFSET,\ rowsize, groupsize, buf, \ len, false); \ } while (0) -#else -#define ice_debug_array(hw, type, rowsize, groupsize, buf, len) \ +#else /* DEBUG */ +#define _ice_debug_array(hw, type, prefix, rowsize, groupsize, buf, len) \ do { \ struct ice_hw *hw_l = hw; \ if ((type) & (hw_l)->debug_mask) { \ @@ -78,4 +80,10 @@ do { \ #endif /* DEBUG */ #endif /* CONFIG_DYNAMIC_DEBUG */ +#define ice_debug_array(hw, type, rowsize, groupsize, buf, len) \ + _ice_debug_array(hw, type, KBUILD_MODNAME, rowsize, groupsize, buf, len) + +#define ice_debug_array_w_prefix(hw, type, prefix, buf, len) \ + _ice_debug_array(hw, type, prefix, 16, 1, buf, len) + #endif /* _ICE_OSDEP_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_parser.c b/drivers/net/ethernet/intel/ice/ice_parser.c new file mode 100644 index 000000000000..664beb64f557 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_parser.c @@ -0,0 +1,2430 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2024 Intel Corporation */ + +#include "ice_common.h" + +struct ice_pkg_sect_hdr { + __le16 count; + __le16 offset; +}; + +/** + * ice_parser_sect_item_get - parse an item from a section + * @sect_type: section type + * @section: section object + * @index: index of the item to get + * @offset: dummy as prototype of ice_pkg_enum_entry's last parameter + * + * Return: a pointer to the item or NULL. + */ +static void *ice_parser_sect_item_get(u32 sect_type, void *section, + u32 index, u32 __maybe_unused *offset) +{ + size_t data_off = ICE_SEC_DATA_OFFSET; + struct ice_pkg_sect_hdr *hdr; + size_t size; + + if (!section) + return NULL; + + switch (sect_type) { + case ICE_SID_RXPARSER_IMEM: + size = ICE_SID_RXPARSER_IMEM_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_METADATA_INIT: + size = ICE_SID_RXPARSER_METADATA_INIT_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_CAM: + size = ICE_SID_RXPARSER_CAM_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_PG_SPILL: + size = ICE_SID_RXPARSER_PG_SPILL_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_NOMATCH_CAM: + size = ICE_SID_RXPARSER_NOMATCH_CAM_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_NOMATCH_SPILL: + size = ICE_SID_RXPARSER_NOMATCH_SPILL_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_BOOST_TCAM: + size = ICE_SID_RXPARSER_BOOST_TCAM_ENTRY_SIZE; + break; + case ICE_SID_LBL_RXPARSER_TMEM: + data_off = ICE_SEC_LBL_DATA_OFFSET; + size = ICE_SID_LBL_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_MARKER_PTYPE: + size = ICE_SID_RXPARSER_MARKER_TYPE_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_MARKER_GRP: + size = ICE_SID_RXPARSER_MARKER_GRP_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_PROTO_GRP: + size = ICE_SID_RXPARSER_PROTO_GRP_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_FLAG_REDIR: + size = ICE_SID_RXPARSER_FLAG_REDIR_ENTRY_SIZE; + break; + default: + return NULL; + } + + hdr = section; + if (index >= le16_to_cpu(hdr->count)) + return NULL; + + return section + data_off + index * size; +} + +/** + * ice_parser_create_table - create an item table from a section + * @hw: pointer to the hardware structure + * @sect_type: section type + * @item_size: item size in bytes + * @length: number of items in the table to create + * @parse_item: the function to parse the item + * @no_offset: ignore header offset, calculate index from 0 + * + * Return: a pointer to the allocated table or ERR_PTR. + */ +static void * +ice_parser_create_table(struct ice_hw *hw, u32 sect_type, + u32 item_size, u32 length, + void (*parse_item)(struct ice_hw *hw, u16 idx, + void *item, void *data, + int size), bool no_offset) +{ + struct ice_pkg_enum state = {}; + struct ice_seg *seg = hw->seg; + void *table, *data, *item; + u16 idx = 0; + + if (!seg) + return ERR_PTR(-EINVAL); + + table = kzalloc(item_size * length, GFP_KERNEL); + if (!table) + return ERR_PTR(-ENOMEM); + + do { + data = ice_pkg_enum_entry(seg, &state, sect_type, NULL, + ice_parser_sect_item_get); + seg = NULL; + if (data) { + struct ice_pkg_sect_hdr *hdr = state.sect; + + if (!no_offset) + idx = le16_to_cpu(hdr->offset) + + state.entry_idx; + + item = (void *)((uintptr_t)table + idx * item_size); + parse_item(hw, idx, item, data, item_size); + + if (no_offset) + idx++; + } + } while (data); + + return table; +} + +/*** ICE_SID_RXPARSER_IMEM section ***/ +static void ice_imem_bst_bm_dump(struct ice_hw *hw, struct ice_bst_main *bm) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "boost main:\n"); + dev_info(dev, "\talu0 = %d\n", bm->alu0); + dev_info(dev, "\talu1 = %d\n", bm->alu1); + dev_info(dev, "\talu2 = %d\n", bm->alu2); + dev_info(dev, "\tpg = %d\n", bm->pg); +} + +static void ice_imem_bst_kb_dump(struct ice_hw *hw, + struct ice_bst_keybuilder *kb) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "boost key builder:\n"); + dev_info(dev, "\tpriority = %d\n", kb->prio); + dev_info(dev, "\ttsr_ctrl = %d\n", kb->tsr_ctrl); +} + +static void ice_imem_np_kb_dump(struct ice_hw *hw, + struct ice_np_keybuilder *kb) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "next proto key builder:\n"); + dev_info(dev, "\topc = %d\n", kb->opc); + dev_info(dev, "\tstart_or_reg0 = %d\n", kb->start_reg0); + dev_info(dev, "\tlen_or_reg1 = %d\n", kb->len_reg1); +} + +static void ice_imem_pg_kb_dump(struct ice_hw *hw, + struct ice_pg_keybuilder *kb) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "parse graph key builder:\n"); + dev_info(dev, "\tflag0_ena = %d\n", kb->flag0_ena); + dev_info(dev, "\tflag1_ena = %d\n", kb->flag1_ena); + dev_info(dev, "\tflag2_ena = %d\n", kb->flag2_ena); + dev_info(dev, "\tflag3_ena = %d\n", kb->flag3_ena); + dev_info(dev, "\tflag0_idx = %d\n", kb->flag0_idx); + dev_info(dev, "\tflag1_idx = %d\n", kb->flag1_idx); + dev_info(dev, "\tflag2_idx = %d\n", kb->flag2_idx); + dev_info(dev, "\tflag3_idx = %d\n", kb->flag3_idx); + dev_info(dev, "\talu_reg_idx = %d\n", kb->alu_reg_idx); +} + +static void ice_imem_alu_dump(struct ice_hw *hw, + struct ice_alu *alu, int index) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "alu%d:\n", index); + dev_info(dev, "\topc = %d\n", alu->opc); + dev_info(dev, "\tsrc_start = %d\n", alu->src_start); + dev_info(dev, "\tsrc_len = %d\n", alu->src_len); + dev_info(dev, "\tshift_xlate_sel = %d\n", alu->shift_xlate_sel); + dev_info(dev, "\tshift_xlate_key = %d\n", alu->shift_xlate_key); + dev_info(dev, "\tsrc_reg_id = %d\n", alu->src_reg_id); + dev_info(dev, "\tdst_reg_id = %d\n", alu->dst_reg_id); + dev_info(dev, "\tinc0 = %d\n", alu->inc0); + dev_info(dev, "\tinc1 = %d\n", alu->inc1); + dev_info(dev, "\tproto_offset_opc = %d\n", alu->proto_offset_opc); + dev_info(dev, "\tproto_offset = %d\n", alu->proto_offset); + dev_info(dev, "\tbranch_addr = %d\n", alu->branch_addr); + dev_info(dev, "\timm = %d\n", alu->imm); + dev_info(dev, "\tdst_start = %d\n", alu->dst_start); + dev_info(dev, "\tdst_len = %d\n", alu->dst_len); + dev_info(dev, "\tflags_extr_imm = %d\n", alu->flags_extr_imm); + dev_info(dev, "\tflags_start_imm= %d\n", alu->flags_start_imm); +} + +/** + * ice_imem_dump - dump an imem item info + * @hw: pointer to the hardware structure + * @item: imem item to dump + */ +static void ice_imem_dump(struct ice_hw *hw, struct ice_imem_item *item) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "index = %d\n", item->idx); + ice_imem_bst_bm_dump(hw, &item->b_m); + ice_imem_bst_kb_dump(hw, &item->b_kb); + dev_info(dev, "pg priority = %d\n", item->pg_prio); + ice_imem_np_kb_dump(hw, &item->np_kb); + ice_imem_pg_kb_dump(hw, &item->pg_kb); + ice_imem_alu_dump(hw, &item->alu0, 0); + ice_imem_alu_dump(hw, &item->alu1, 1); + ice_imem_alu_dump(hw, &item->alu2, 2); +} + +#define ICE_IM_BM_ALU0 BIT(0) +#define ICE_IM_BM_ALU1 BIT(1) +#define ICE_IM_BM_ALU2 BIT(2) +#define ICE_IM_BM_PG BIT(3) + +/** + * ice_imem_bm_init - parse 4 bits of Boost Main + * @bm: pointer to the Boost Main structure + * @data: Boost Main data to be parsed + */ +static void ice_imem_bm_init(struct ice_bst_main *bm, u8 data) +{ + bm->alu0 = FIELD_GET(ICE_IM_BM_ALU0, data); + bm->alu1 = FIELD_GET(ICE_IM_BM_ALU1, data); + bm->alu2 = FIELD_GET(ICE_IM_BM_ALU2, data); + bm->pg = FIELD_GET(ICE_IM_BM_PG, data); +} + +#define ICE_IM_BKB_PRIO GENMASK(7, 0) +#define ICE_IM_BKB_TSR_CTRL BIT(8) + +/** + * ice_imem_bkb_init - parse 10 bits of Boost Main Build + * @bkb: pointer to the Boost Main Build structure + * @data: Boost Main Build data to be parsed + */ +static void ice_imem_bkb_init(struct ice_bst_keybuilder *bkb, u16 data) +{ + bkb->prio = FIELD_GET(ICE_IM_BKB_PRIO, data); + bkb->tsr_ctrl = FIELD_GET(ICE_IM_BKB_TSR_CTRL, data); +} + +#define ICE_IM_NPKB_OPC GENMASK(1, 0) +#define ICE_IM_NPKB_S_R0 GENMASK(9, 2) +#define ICE_IM_NPKB_L_R1 GENMASK(17, 10) + +/** + * ice_imem_npkb_init - parse 18 bits of Next Protocol Key Build + * @kb: pointer to the Next Protocol Key Build structure + * @data: Next Protocol Key Build data to be parsed + */ +static void ice_imem_npkb_init(struct ice_np_keybuilder *kb, u32 data) +{ + kb->opc = FIELD_GET(ICE_IM_NPKB_OPC, data); + kb->start_reg0 = FIELD_GET(ICE_IM_NPKB_S_R0, data); + kb->len_reg1 = FIELD_GET(ICE_IM_NPKB_L_R1, data); +} + +#define ICE_IM_PGKB_F0_ENA BIT_ULL(0) +#define ICE_IM_PGKB_F0_IDX GENMASK_ULL(6, 1) +#define ICE_IM_PGKB_F1_ENA BIT_ULL(7) +#define ICE_IM_PGKB_F1_IDX GENMASK_ULL(13, 8) +#define ICE_IM_PGKB_F2_ENA BIT_ULL(14) +#define ICE_IM_PGKB_F2_IDX GENMASK_ULL(20, 15) +#define ICE_IM_PGKB_F3_ENA BIT_ULL(21) +#define ICE_IM_PGKB_F3_IDX GENMASK_ULL(27, 22) +#define ICE_IM_PGKB_AR_IDX GENMASK_ULL(34, 28) + +/** + * ice_imem_pgkb_init - parse 35 bits of Parse Graph Key Build + * @kb: pointer to the Parse Graph Key Build structure + * @data: Parse Graph Key Build data to be parsed + */ +static void ice_imem_pgkb_init(struct ice_pg_keybuilder *kb, u64 data) +{ + kb->flag0_ena = FIELD_GET(ICE_IM_PGKB_F0_ENA, data); + kb->flag0_idx = FIELD_GET(ICE_IM_PGKB_F0_IDX, data); + kb->flag1_ena = FIELD_GET(ICE_IM_PGKB_F1_ENA, data); + kb->flag1_idx = FIELD_GET(ICE_IM_PGKB_F1_IDX, data); + kb->flag2_ena = FIELD_GET(ICE_IM_PGKB_F2_ENA, data); + kb->flag2_idx = FIELD_GET(ICE_IM_PGKB_F2_IDX, data); + kb->flag3_ena = FIELD_GET(ICE_IM_PGKB_F3_ENA, data); + kb->flag3_idx = FIELD_GET(ICE_IM_PGKB_F3_IDX, data); + kb->alu_reg_idx = FIELD_GET(ICE_IM_PGKB_AR_IDX, data); +} + +#define ICE_IM_ALU_OPC GENMASK_ULL(5, 0) +#define ICE_IM_ALU_SS GENMASK_ULL(13, 6) +#define ICE_IM_ALU_SL GENMASK_ULL(18, 14) +#define ICE_IM_ALU_SXS BIT_ULL(19) +#define ICE_IM_ALU_SXK GENMASK_ULL(23, 20) +#define ICE_IM_ALU_SRID GENMASK_ULL(30, 24) +#define ICE_IM_ALU_DRID GENMASK_ULL(37, 31) +#define ICE_IM_ALU_INC0 BIT_ULL(38) +#define ICE_IM_ALU_INC1 BIT_ULL(39) +#define ICE_IM_ALU_POO GENMASK_ULL(41, 40) +#define ICE_IM_ALU_PO GENMASK_ULL(49, 42) +#define ICE_IM_ALU_BA_S 50 /* offset for the 2nd 64-bits field */ +#define ICE_IM_ALU_BA GENMASK_ULL(57 - ICE_IM_ALU_BA_S, \ + 50 - ICE_IM_ALU_BA_S) +#define ICE_IM_ALU_IMM GENMASK_ULL(73 - ICE_IM_ALU_BA_S, \ + 58 - ICE_IM_ALU_BA_S) +#define ICE_IM_ALU_DFE BIT_ULL(74 - ICE_IM_ALU_BA_S) +#define ICE_IM_ALU_DS GENMASK_ULL(80 - ICE_IM_ALU_BA_S, \ + 75 - ICE_IM_ALU_BA_S) +#define ICE_IM_ALU_DL GENMASK_ULL(86 - ICE_IM_ALU_BA_S, \ + 81 - ICE_IM_ALU_BA_S) +#define ICE_IM_ALU_FEI BIT_ULL(87 - ICE_IM_ALU_BA_S) +#define ICE_IM_ALU_FSI GENMASK_ULL(95 - ICE_IM_ALU_BA_S, \ + 88 - ICE_IM_ALU_BA_S) + +/** + * ice_imem_alu_init - parse 96 bits of ALU entry + * @alu: pointer to the ALU entry structure + * @data: ALU entry data to be parsed + * @off: offset of the ALU entry data + */ +static void ice_imem_alu_init(struct ice_alu *alu, u8 *data, u8 off) +{ + u64 d64; + u8 idd; + + d64 = *((u64 *)data) >> off; + + alu->opc = FIELD_GET(ICE_IM_ALU_OPC, d64); + alu->src_start = FIELD_GET(ICE_IM_ALU_SS, d64); + alu->src_len = FIELD_GET(ICE_IM_ALU_SL, d64); + alu->shift_xlate_sel = FIELD_GET(ICE_IM_ALU_SXS, d64); + alu->shift_xlate_key = FIELD_GET(ICE_IM_ALU_SXK, d64); + alu->src_reg_id = FIELD_GET(ICE_IM_ALU_SRID, d64); + alu->dst_reg_id = FIELD_GET(ICE_IM_ALU_DRID, d64); + alu->inc0 = FIELD_GET(ICE_IM_ALU_INC0, d64); + alu->inc1 = FIELD_GET(ICE_IM_ALU_INC1, d64); + alu->proto_offset_opc = FIELD_GET(ICE_IM_ALU_POO, d64); + alu->proto_offset = FIELD_GET(ICE_IM_ALU_PO, d64); + + idd = (ICE_IM_ALU_BA_S + off) / BITS_PER_BYTE; + off = (ICE_IM_ALU_BA_S + off) % BITS_PER_BYTE; + d64 = *((u64 *)(&data[idd])) >> off; + + alu->branch_addr = FIELD_GET(ICE_IM_ALU_BA, d64); + alu->imm = FIELD_GET(ICE_IM_ALU_IMM, d64); + alu->dedicate_flags_ena = FIELD_GET(ICE_IM_ALU_DFE, d64); + alu->dst_start = FIELD_GET(ICE_IM_ALU_DS, d64); + alu->dst_len = FIELD_GET(ICE_IM_ALU_DL, d64); + alu->flags_extr_imm = FIELD_GET(ICE_IM_ALU_FEI, d64); + alu->flags_start_imm = FIELD_GET(ICE_IM_ALU_FSI, d64); +} + +#define ICE_IMEM_BM_S 0 +#define ICE_IMEM_BKB_S 4 +#define ICE_IMEM_BKB_IDD (ICE_IMEM_BKB_S / BITS_PER_BYTE) +#define ICE_IMEM_BKB_OFF (ICE_IMEM_BKB_S % BITS_PER_BYTE) +#define ICE_IMEM_PGP GENMASK(15, 14) +#define ICE_IMEM_NPKB_S 16 +#define ICE_IMEM_NPKB_IDD (ICE_IMEM_NPKB_S / BITS_PER_BYTE) +#define ICE_IMEM_NPKB_OFF (ICE_IMEM_NPKB_S % BITS_PER_BYTE) +#define ICE_IMEM_PGKB_S 34 +#define ICE_IMEM_PGKB_IDD (ICE_IMEM_PGKB_S / BITS_PER_BYTE) +#define ICE_IMEM_PGKB_OFF (ICE_IMEM_PGKB_S % BITS_PER_BYTE) +#define ICE_IMEM_ALU0_S 69 +#define ICE_IMEM_ALU0_IDD (ICE_IMEM_ALU0_S / BITS_PER_BYTE) +#define ICE_IMEM_ALU0_OFF (ICE_IMEM_ALU0_S % BITS_PER_BYTE) +#define ICE_IMEM_ALU1_S 165 +#define ICE_IMEM_ALU1_IDD (ICE_IMEM_ALU1_S / BITS_PER_BYTE) +#define ICE_IMEM_ALU1_OFF (ICE_IMEM_ALU1_S % BITS_PER_BYTE) +#define ICE_IMEM_ALU2_S 357 +#define ICE_IMEM_ALU2_IDD (ICE_IMEM_ALU2_S / BITS_PER_BYTE) +#define ICE_IMEM_ALU2_OFF (ICE_IMEM_ALU2_S % BITS_PER_BYTE) + +/** + * ice_imem_parse_item - parse 384 bits of IMEM entry + * @hw: pointer to the hardware structure + * @idx: index of IMEM entry + * @item: item of IMEM entry + * @data: IMEM entry data to be parsed + * @size: size of IMEM entry + */ +static void ice_imem_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_imem_item *ii = item; + u8 *buf = data; + + ii->idx = idx; + + ice_imem_bm_init(&ii->b_m, *(u8 *)buf); + ice_imem_bkb_init(&ii->b_kb, + *((u16 *)(&buf[ICE_IMEM_BKB_IDD])) >> + ICE_IMEM_BKB_OFF); + + ii->pg_prio = FIELD_GET(ICE_IMEM_PGP, *(u16 *)buf); + + ice_imem_npkb_init(&ii->np_kb, + *((u32 *)(&buf[ICE_IMEM_NPKB_IDD])) >> + ICE_IMEM_NPKB_OFF); + ice_imem_pgkb_init(&ii->pg_kb, + *((u64 *)(&buf[ICE_IMEM_PGKB_IDD])) >> + ICE_IMEM_PGKB_OFF); + + ice_imem_alu_init(&ii->alu0, + &buf[ICE_IMEM_ALU0_IDD], + ICE_IMEM_ALU0_OFF); + ice_imem_alu_init(&ii->alu1, + &buf[ICE_IMEM_ALU1_IDD], + ICE_IMEM_ALU1_OFF); + ice_imem_alu_init(&ii->alu2, + &buf[ICE_IMEM_ALU2_IDD], + ICE_IMEM_ALU2_OFF); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_imem_dump(hw, ii); +} + +/** + * ice_imem_table_get - create an imem table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated IMEM table. + */ +static struct ice_imem_item *ice_imem_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_IMEM, + sizeof(struct ice_imem_item), + ICE_IMEM_TABLE_SIZE, + ice_imem_parse_item, false); +} + +/*** ICE_SID_RXPARSER_METADATA_INIT section ***/ +/** + * ice_metainit_dump - dump an metainit item info + * @hw: pointer to the hardware structure + * @item: metainit item to dump + */ +static void ice_metainit_dump(struct ice_hw *hw, struct ice_metainit_item *item) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "index = %d\n", item->idx); + + dev_info(dev, "tsr = %d\n", item->tsr); + dev_info(dev, "ho = %d\n", item->ho); + dev_info(dev, "pc = %d\n", item->pc); + dev_info(dev, "pg_rn = %d\n", item->pg_rn); + dev_info(dev, "cd = %d\n", item->cd); + + dev_info(dev, "gpr_a_ctrl = %d\n", item->gpr_a_ctrl); + dev_info(dev, "gpr_a_data_mdid = %d\n", item->gpr_a_data_mdid); + dev_info(dev, "gpr_a_data_start = %d\n", item->gpr_a_data_start); + dev_info(dev, "gpr_a_data_len = %d\n", item->gpr_a_data_len); + dev_info(dev, "gpr_a_id = %d\n", item->gpr_a_id); + + dev_info(dev, "gpr_b_ctrl = %d\n", item->gpr_b_ctrl); + dev_info(dev, "gpr_b_data_mdid = %d\n", item->gpr_b_data_mdid); + dev_info(dev, "gpr_b_data_start = %d\n", item->gpr_b_data_start); + dev_info(dev, "gpr_b_data_len = %d\n", item->gpr_b_data_len); + dev_info(dev, "gpr_b_id = %d\n", item->gpr_b_id); + + dev_info(dev, "gpr_c_ctrl = %d\n", item->gpr_c_ctrl); + dev_info(dev, "gpr_c_data_mdid = %d\n", item->gpr_c_data_mdid); + dev_info(dev, "gpr_c_data_start = %d\n", item->gpr_c_data_start); + dev_info(dev, "gpr_c_data_len = %d\n", item->gpr_c_data_len); + dev_info(dev, "gpr_c_id = %d\n", item->gpr_c_id); + + dev_info(dev, "gpr_d_ctrl = %d\n", item->gpr_d_ctrl); + dev_info(dev, "gpr_d_data_mdid = %d\n", item->gpr_d_data_mdid); + dev_info(dev, "gpr_d_data_start = %d\n", item->gpr_d_data_start); + dev_info(dev, "gpr_d_data_len = %d\n", item->gpr_d_data_len); + dev_info(dev, "gpr_d_id = %d\n", item->gpr_d_id); + + dev_info(dev, "flags = 0x%llx\n", (unsigned long long)(item->flags)); +} + +#define ICE_MI_TSR GENMASK_ULL(7, 0) +#define ICE_MI_HO GENMASK_ULL(16, 8) +#define ICE_MI_PC GENMASK_ULL(24, 17) +#define ICE_MI_PGRN GENMASK_ULL(35, 25) +#define ICE_MI_CD GENMASK_ULL(38, 36) +#define ICE_MI_GAC BIT_ULL(39) +#define ICE_MI_GADM GENMASK_ULL(44, 40) +#define ICE_MI_GADS GENMASK_ULL(48, 45) +#define ICE_MI_GADL GENMASK_ULL(53, 49) +#define ICE_MI_GAI GENMASK_ULL(59, 56) +#define ICE_MI_GBC BIT_ULL(60) +#define ICE_MI_GBDM_S 61 /* offset for the 2nd 64-bits field */ +#define ICE_MI_GBDM_IDD (ICE_MI_GBDM_S / BITS_PER_BYTE) +#define ICE_MI_GBDM_OFF (ICE_MI_GBDM_S % BITS_PER_BYTE) + +#define ICE_MI_GBDM_GENMASK_ULL(high, low) \ + GENMASK_ULL((high) - ICE_MI_GBDM_S, (low) - ICE_MI_GBDM_S) +#define ICE_MI_GBDM ICE_MI_GBDM_GENMASK_ULL(65, 61) +#define ICE_MI_GBDS ICE_MI_GBDM_GENMASK_ULL(69, 66) +#define ICE_MI_GBDL ICE_MI_GBDM_GENMASK_ULL(74, 70) +#define ICE_MI_GBI ICE_MI_GBDM_GENMASK_ULL(80, 77) +#define ICE_MI_GCC BIT_ULL(81 - ICE_MI_GBDM_S) +#define ICE_MI_GCDM ICE_MI_GBDM_GENMASK_ULL(86, 82) +#define ICE_MI_GCDS ICE_MI_GBDM_GENMASK_ULL(90, 87) +#define ICE_MI_GCDL ICE_MI_GBDM_GENMASK_ULL(95, 91) +#define ICE_MI_GCI ICE_MI_GBDM_GENMASK_ULL(101, 98) +#define ICE_MI_GDC BIT_ULL(102 - ICE_MI_GBDM_S) +#define ICE_MI_GDDM ICE_MI_GBDM_GENMASK_ULL(107, 103) +#define ICE_MI_GDDS ICE_MI_GBDM_GENMASK_ULL(111, 108) +#define ICE_MI_GDDL ICE_MI_GBDM_GENMASK_ULL(116, 112) +#define ICE_MI_GDI ICE_MI_GBDM_GENMASK_ULL(122, 119) +#define ICE_MI_FLAG_S 123 /* offset for the 3rd 64-bits field */ +#define ICE_MI_FLAG_IDD (ICE_MI_FLAG_S / BITS_PER_BYTE) +#define ICE_MI_FLAG_OFF (ICE_MI_FLAG_S % BITS_PER_BYTE) +#define ICE_MI_FLAG GENMASK_ULL(186 - ICE_MI_FLAG_S, \ + 123 - ICE_MI_FLAG_S) + +/** + * ice_metainit_parse_item - parse 192 bits of Metadata Init entry + * @hw: pointer to the hardware structure + * @idx: index of Metadata Init entry + * @item: item of Metadata Init entry + * @data: Metadata Init entry data to be parsed + * @size: size of Metadata Init entry + */ +static void ice_metainit_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_metainit_item *mi = item; + u8 *buf = data; + u64 d64; + + mi->idx = idx; + + d64 = *(u64 *)buf; + + mi->tsr = FIELD_GET(ICE_MI_TSR, d64); + mi->ho = FIELD_GET(ICE_MI_HO, d64); + mi->pc = FIELD_GET(ICE_MI_PC, d64); + mi->pg_rn = FIELD_GET(ICE_MI_PGRN, d64); + mi->cd = FIELD_GET(ICE_MI_CD, d64); + + mi->gpr_a_ctrl = FIELD_GET(ICE_MI_GAC, d64); + mi->gpr_a_data_mdid = FIELD_GET(ICE_MI_GADM, d64); + mi->gpr_a_data_start = FIELD_GET(ICE_MI_GADS, d64); + mi->gpr_a_data_len = FIELD_GET(ICE_MI_GADL, d64); + mi->gpr_a_id = FIELD_GET(ICE_MI_GAI, d64); + + mi->gpr_b_ctrl = FIELD_GET(ICE_MI_GBC, d64); + + d64 = *((u64 *)&buf[ICE_MI_GBDM_IDD]) >> ICE_MI_GBDM_OFF; + + mi->gpr_b_data_mdid = FIELD_GET(ICE_MI_GBDM, d64); + mi->gpr_b_data_start = FIELD_GET(ICE_MI_GBDS, d64); + mi->gpr_b_data_len = FIELD_GET(ICE_MI_GBDL, d64); + mi->gpr_b_id = FIELD_GET(ICE_MI_GBI, d64); + + mi->gpr_c_ctrl = FIELD_GET(ICE_MI_GCC, d64); + mi->gpr_c_data_mdid = FIELD_GET(ICE_MI_GCDM, d64); + mi->gpr_c_data_start = FIELD_GET(ICE_MI_GCDS, d64); + mi->gpr_c_data_len = FIELD_GET(ICE_MI_GCDL, d64); + mi->gpr_c_id = FIELD_GET(ICE_MI_GCI, d64); + + mi->gpr_d_ctrl = FIELD_GET(ICE_MI_GDC, d64); + mi->gpr_d_data_mdid = FIELD_GET(ICE_MI_GDDM, d64); + mi->gpr_d_data_start = FIELD_GET(ICE_MI_GDDS, d64); + mi->gpr_d_data_len = FIELD_GET(ICE_MI_GDDL, d64); + mi->gpr_d_id = FIELD_GET(ICE_MI_GDI, d64); + + d64 = *((u64 *)&buf[ICE_MI_FLAG_IDD]) >> ICE_MI_FLAG_OFF; + + mi->flags = FIELD_GET(ICE_MI_FLAG, d64); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_metainit_dump(hw, mi); +} + +/** + * ice_metainit_table_get - create a metainit table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Metadata initialization table. + */ +static struct ice_metainit_item *ice_metainit_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_METADATA_INIT, + sizeof(struct ice_metainit_item), + ICE_METAINIT_TABLE_SIZE, + ice_metainit_parse_item, false); +} + +/** + * ice_bst_tcam_search - find a TCAM item with specific type + * @tcam_table: the TCAM table + * @lbl_table: the lbl table to search + * @type: the type we need to match against + * @start: start searching from this index + * + * Return: a pointer to the matching BOOST TCAM item or NULL. + */ +struct ice_bst_tcam_item * +ice_bst_tcam_search(struct ice_bst_tcam_item *tcam_table, + struct ice_lbl_item *lbl_table, + enum ice_lbl_type type, u16 *start) +{ + u16 i = *start; + + for (; i < ICE_BST_TCAM_TABLE_SIZE; i++) { + if (lbl_table[i].type == type) { + *start = i; + return &tcam_table[lbl_table[i].idx]; + } + } + + return NULL; +} + +/*** ICE_SID_RXPARSER_CAM, ICE_SID_RXPARSER_PG_SPILL, + * ICE_SID_RXPARSER_NOMATCH_CAM and ICE_SID_RXPARSER_NOMATCH_CAM + * sections ***/ +static void ice_pg_cam_key_dump(struct ice_hw *hw, struct ice_pg_cam_key *key) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "key:\n"); + dev_info(dev, "\tvalid = %d\n", key->valid); + dev_info(dev, "\tnode_id = %d\n", key->node_id); + dev_info(dev, "\tflag0 = %d\n", key->flag0); + dev_info(dev, "\tflag1 = %d\n", key->flag1); + dev_info(dev, "\tflag2 = %d\n", key->flag2); + dev_info(dev, "\tflag3 = %d\n", key->flag3); + dev_info(dev, "\tboost_idx = %d\n", key->boost_idx); + dev_info(dev, "\talu_reg = 0x%04x\n", key->alu_reg); + dev_info(dev, "\tnext_proto = 0x%08x\n", key->next_proto); +} + +static void ice_pg_nm_cam_key_dump(struct ice_hw *hw, + struct ice_pg_nm_cam_key *key) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "key:\n"); + dev_info(dev, "\tvalid = %d\n", key->valid); + dev_info(dev, "\tnode_id = %d\n", key->node_id); + dev_info(dev, "\tflag0 = %d\n", key->flag0); + dev_info(dev, "\tflag1 = %d\n", key->flag1); + dev_info(dev, "\tflag2 = %d\n", key->flag2); + dev_info(dev, "\tflag3 = %d\n", key->flag3); + dev_info(dev, "\tboost_idx = %d\n", key->boost_idx); + dev_info(dev, "\talu_reg = 0x%04x\n", key->alu_reg); +} + +static void ice_pg_cam_action_dump(struct ice_hw *hw, + struct ice_pg_cam_action *action) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "action:\n"); + dev_info(dev, "\tnext_node = %d\n", action->next_node); + dev_info(dev, "\tnext_pc = %d\n", action->next_pc); + dev_info(dev, "\tis_pg = %d\n", action->is_pg); + dev_info(dev, "\tproto_id = %d\n", action->proto_id); + dev_info(dev, "\tis_mg = %d\n", action->is_mg); + dev_info(dev, "\tmarker_id = %d\n", action->marker_id); + dev_info(dev, "\tis_last_round = %d\n", action->is_last_round); + dev_info(dev, "\tho_polarity = %d\n", action->ho_polarity); + dev_info(dev, "\tho_inc = %d\n", action->ho_inc); +} + +/** + * ice_pg_cam_dump - dump an parse graph cam info + * @hw: pointer to the hardware structure + * @item: parse graph cam to dump + */ +static void ice_pg_cam_dump(struct ice_hw *hw, struct ice_pg_cam_item *item) +{ + dev_info(ice_hw_to_dev(hw), "index = %d\n", item->idx); + ice_pg_cam_key_dump(hw, &item->key); + ice_pg_cam_action_dump(hw, &item->action); +} + +/** + * ice_pg_nm_cam_dump - dump an parse graph no match cam info + * @hw: pointer to the hardware structure + * @item: parse graph no match cam to dump + */ +static void ice_pg_nm_cam_dump(struct ice_hw *hw, + struct ice_pg_nm_cam_item *item) +{ + dev_info(ice_hw_to_dev(hw), "index = %d\n", item->idx); + ice_pg_nm_cam_key_dump(hw, &item->key); + ice_pg_cam_action_dump(hw, &item->action); +} + +#define ICE_PGCA_NN GENMASK_ULL(10, 0) +#define ICE_PGCA_NPC GENMASK_ULL(18, 11) +#define ICE_PGCA_IPG BIT_ULL(19) +#define ICE_PGCA_PID GENMASK_ULL(30, 23) +#define ICE_PGCA_IMG BIT_ULL(31) +#define ICE_PGCA_MID GENMASK_ULL(39, 32) +#define ICE_PGCA_ILR BIT_ULL(40) +#define ICE_PGCA_HOP BIT_ULL(41) +#define ICE_PGCA_HOI GENMASK_ULL(50, 42) + +/** + * ice_pg_cam_action_init - parse 55 bits of Parse Graph CAM Action + * @action: pointer to the Parse Graph CAM Action structure + * @data: Parse Graph CAM Action data to be parsed + */ +static void ice_pg_cam_action_init(struct ice_pg_cam_action *action, u64 data) +{ + action->next_node = FIELD_GET(ICE_PGCA_NN, data); + action->next_pc = FIELD_GET(ICE_PGCA_NPC, data); + action->is_pg = FIELD_GET(ICE_PGCA_IPG, data); + action->proto_id = FIELD_GET(ICE_PGCA_PID, data); + action->is_mg = FIELD_GET(ICE_PGCA_IMG, data); + action->marker_id = FIELD_GET(ICE_PGCA_MID, data); + action->is_last_round = FIELD_GET(ICE_PGCA_ILR, data); + action->ho_polarity = FIELD_GET(ICE_PGCA_HOP, data); + action->ho_inc = FIELD_GET(ICE_PGCA_HOI, data); +} + +#define ICE_PGNCK_VLD BIT_ULL(0) +#define ICE_PGNCK_NID GENMASK_ULL(11, 1) +#define ICE_PGNCK_F0 BIT_ULL(12) +#define ICE_PGNCK_F1 BIT_ULL(13) +#define ICE_PGNCK_F2 BIT_ULL(14) +#define ICE_PGNCK_F3 BIT_ULL(15) +#define ICE_PGNCK_BH BIT_ULL(16) +#define ICE_PGNCK_BI GENMASK_ULL(24, 17) +#define ICE_PGNCK_AR GENMASK_ULL(40, 25) + +/** + * ice_pg_nm_cam_key_init - parse 41 bits of Parse Graph NoMatch CAM Key + * @key: pointer to the Parse Graph NoMatch CAM Key structure + * @data: Parse Graph NoMatch CAM Key data to be parsed + */ +static void ice_pg_nm_cam_key_init(struct ice_pg_nm_cam_key *key, u64 data) +{ + key->valid = FIELD_GET(ICE_PGNCK_VLD, data); + key->node_id = FIELD_GET(ICE_PGNCK_NID, data); + key->flag0 = FIELD_GET(ICE_PGNCK_F0, data); + key->flag1 = FIELD_GET(ICE_PGNCK_F1, data); + key->flag2 = FIELD_GET(ICE_PGNCK_F2, data); + key->flag3 = FIELD_GET(ICE_PGNCK_F3, data); + + if (FIELD_GET(ICE_PGNCK_BH, data)) + key->boost_idx = FIELD_GET(ICE_PGNCK_BI, data); + else + key->boost_idx = 0; + + key->alu_reg = FIELD_GET(ICE_PGNCK_AR, data); +} + +#define ICE_PGCK_VLD BIT_ULL(0) +#define ICE_PGCK_NID GENMASK_ULL(11, 1) +#define ICE_PGCK_F0 BIT_ULL(12) +#define ICE_PGCK_F1 BIT_ULL(13) +#define ICE_PGCK_F2 BIT_ULL(14) +#define ICE_PGCK_F3 BIT_ULL(15) +#define ICE_PGCK_BH BIT_ULL(16) +#define ICE_PGCK_BI GENMASK_ULL(24, 17) +#define ICE_PGCK_AR GENMASK_ULL(40, 25) +#define ICE_PGCK_NPK_S 41 /* offset for the 2nd 64-bits field */ +#define ICE_PGCK_NPK_IDD (ICE_PGCK_NPK_S / BITS_PER_BYTE) +#define ICE_PGCK_NPK_OFF (ICE_PGCK_NPK_S % BITS_PER_BYTE) +#define ICE_PGCK_NPK GENMASK_ULL(72 - ICE_PGCK_NPK_S, \ + 41 - ICE_PGCK_NPK_S) + +/** + * ice_pg_cam_key_init - parse 73 bits of Parse Graph CAM Key + * @key: pointer to the Parse Graph CAM Key structure + * @data: Parse Graph CAM Key data to be parsed + */ +static void ice_pg_cam_key_init(struct ice_pg_cam_key *key, u8 *data) +{ + u64 d64 = *(u64 *)data; + + key->valid = FIELD_GET(ICE_PGCK_VLD, d64); + key->node_id = FIELD_GET(ICE_PGCK_NID, d64); + key->flag0 = FIELD_GET(ICE_PGCK_F0, d64); + key->flag1 = FIELD_GET(ICE_PGCK_F1, d64); + key->flag2 = FIELD_GET(ICE_PGCK_F2, d64); + key->flag3 = FIELD_GET(ICE_PGCK_F3, d64); + + if (FIELD_GET(ICE_PGCK_BH, d64)) + key->boost_idx = FIELD_GET(ICE_PGCK_BI, d64); + else + key->boost_idx = 0; + + key->alu_reg = FIELD_GET(ICE_PGCK_AR, d64); + + d64 = *((u64 *)&data[ICE_PGCK_NPK_IDD]) >> ICE_PGCK_NPK_OFF; + + key->next_proto = FIELD_GET(ICE_PGCK_NPK, d64); +} + +#define ICE_PG_CAM_ACT_S 73 +#define ICE_PG_CAM_ACT_IDD (ICE_PG_CAM_ACT_S / BITS_PER_BYTE) +#define ICE_PG_CAM_ACT_OFF (ICE_PG_CAM_ACT_S % BITS_PER_BYTE) + +/** + * ice_pg_cam_parse_item - parse 128 bits of Parse Graph CAM Entry + * @hw: pointer to the hardware structure + * @idx: index of Parse Graph CAM Entry + * @item: item of Parse Graph CAM Entry + * @data: Parse Graph CAM Entry data to be parsed + * @size: size of Parse Graph CAM Entry + */ +static void ice_pg_cam_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_pg_cam_item *ci = item; + u8 *buf = data; + u64 d64; + + ci->idx = idx; + + ice_pg_cam_key_init(&ci->key, buf); + + d64 = *((u64 *)&buf[ICE_PG_CAM_ACT_IDD]) >> ICE_PG_CAM_ACT_OFF; + ice_pg_cam_action_init(&ci->action, d64); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_pg_cam_dump(hw, ci); +} + +#define ICE_PG_SP_CAM_KEY_S 56 +#define ICE_PG_SP_CAM_KEY_IDD (ICE_PG_SP_CAM_KEY_S / BITS_PER_BYTE) + +/** + * ice_pg_sp_cam_parse_item - parse 136 bits of Parse Graph Spill CAM Entry + * @hw: pointer to the hardware structure + * @idx: index of Parse Graph Spill CAM Entry + * @item: item of Parse Graph Spill CAM Entry + * @data: Parse Graph Spill CAM Entry data to be parsed + * @size: size of Parse Graph Spill CAM Entry + */ +static void ice_pg_sp_cam_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_pg_cam_item *ci = item; + u8 *buf = data; + u64 d64; + + ci->idx = idx; + + d64 = *(u64 *)buf; + ice_pg_cam_action_init(&ci->action, d64); + + ice_pg_cam_key_init(&ci->key, &buf[ICE_PG_SP_CAM_KEY_IDD]); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_pg_cam_dump(hw, ci); +} + +#define ICE_PG_NM_CAM_ACT_S 41 +#define ICE_PG_NM_CAM_ACT_IDD (ICE_PG_NM_CAM_ACT_S / BITS_PER_BYTE) +#define ICE_PG_NM_CAM_ACT_OFF (ICE_PG_NM_CAM_ACT_S % BITS_PER_BYTE) + +/** + * ice_pg_nm_cam_parse_item - parse 96 bits of Parse Graph NoMatch CAM Entry + * @hw: pointer to the hardware structure + * @idx: index of Parse Graph NoMatch CAM Entry + * @item: item of Parse Graph NoMatch CAM Entry + * @data: Parse Graph NoMatch CAM Entry data to be parsed + * @size: size of Parse Graph NoMatch CAM Entry + */ +static void ice_pg_nm_cam_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_pg_nm_cam_item *ci = item; + u8 *buf = data; + u64 d64; + + ci->idx = idx; + + d64 = *(u64 *)buf; + ice_pg_nm_cam_key_init(&ci->key, d64); + + d64 = *((u64 *)&buf[ICE_PG_NM_CAM_ACT_IDD]) >> ICE_PG_NM_CAM_ACT_OFF; + ice_pg_cam_action_init(&ci->action, d64); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_pg_nm_cam_dump(hw, ci); +} + +#define ICE_PG_NM_SP_CAM_ACT_S 56 +#define ICE_PG_NM_SP_CAM_ACT_IDD (ICE_PG_NM_SP_CAM_ACT_S / BITS_PER_BYTE) +#define ICE_PG_NM_SP_CAM_ACT_OFF (ICE_PG_NM_SP_CAM_ACT_S % BITS_PER_BYTE) + +/** + * ice_pg_nm_sp_cam_parse_item - parse 104 bits of Parse Graph NoMatch Spill + * CAM Entry + * @hw: pointer to the hardware structure + * @idx: index of Parse Graph NoMatch Spill CAM Entry + * @item: item of Parse Graph NoMatch Spill CAM Entry + * @data: Parse Graph NoMatch Spill CAM Entry data to be parsed + * @size: size of Parse Graph NoMatch Spill CAM Entry + */ +static void ice_pg_nm_sp_cam_parse_item(struct ice_hw *hw, u16 idx, + void *item, void *data, + int __maybe_unused size) +{ + struct ice_pg_nm_cam_item *ci = item; + u8 *buf = data; + u64 d64; + + ci->idx = idx; + + d64 = *(u64 *)buf; + ice_pg_cam_action_init(&ci->action, d64); + + d64 = *((u64 *)&buf[ICE_PG_NM_SP_CAM_ACT_IDD]) >> + ICE_PG_NM_SP_CAM_ACT_OFF; + ice_pg_nm_cam_key_init(&ci->key, d64); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_pg_nm_cam_dump(hw, ci); +} + +/** + * ice_pg_cam_table_get - create a parse graph cam table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Parse Graph CAM table. + */ +static struct ice_pg_cam_item *ice_pg_cam_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_CAM, + sizeof(struct ice_pg_cam_item), + ICE_PG_CAM_TABLE_SIZE, + ice_pg_cam_parse_item, false); +} + +/** + * ice_pg_sp_cam_table_get - create a parse graph spill cam table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Parse Graph Spill CAM table. + */ +static struct ice_pg_cam_item *ice_pg_sp_cam_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_PG_SPILL, + sizeof(struct ice_pg_cam_item), + ICE_PG_SP_CAM_TABLE_SIZE, + ice_pg_sp_cam_parse_item, false); +} + +/** + * ice_pg_nm_cam_table_get - create a parse graph no match cam table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Parse Graph No Match CAM table. + */ +static struct ice_pg_nm_cam_item *ice_pg_nm_cam_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_NOMATCH_CAM, + sizeof(struct ice_pg_nm_cam_item), + ICE_PG_NM_CAM_TABLE_SIZE, + ice_pg_nm_cam_parse_item, false); +} + +/** + * ice_pg_nm_sp_cam_table_get - create a parse graph no match spill cam table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Parse Graph No Match Spill CAM table. + */ +static struct ice_pg_nm_cam_item *ice_pg_nm_sp_cam_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_NOMATCH_SPILL, + sizeof(struct ice_pg_nm_cam_item), + ICE_PG_NM_SP_CAM_TABLE_SIZE, + ice_pg_nm_sp_cam_parse_item, false); +} + +static bool __ice_pg_cam_match(struct ice_pg_cam_item *item, + struct ice_pg_cam_key *key) +{ + return (item->key.valid && + !memcmp(&item->key.val, &key->val, sizeof(key->val))); +} + +static bool __ice_pg_nm_cam_match(struct ice_pg_nm_cam_item *item, + struct ice_pg_cam_key *key) +{ + return (item->key.valid && + !memcmp(&item->key.val, &key->val, sizeof(item->key.val))); +} + +/** + * ice_pg_cam_match - search parse graph cam table by key + * @table: parse graph cam table to search + * @size: cam table size + * @key: search key + * + * Return: a pointer to the matching PG CAM item or NULL. + */ +struct ice_pg_cam_item *ice_pg_cam_match(struct ice_pg_cam_item *table, + int size, struct ice_pg_cam_key *key) +{ + int i; + + for (i = 0; i < size; i++) { + struct ice_pg_cam_item *item = &table[i]; + + if (__ice_pg_cam_match(item, key)) + return item; + } + + return NULL; +} + +/** + * ice_pg_nm_cam_match - search parse graph no match cam table by key + * @table: parse graph no match cam table to search + * @size: cam table size + * @key: search key + * + * Return: a pointer to the matching PG No Match CAM item or NULL. + */ +struct ice_pg_nm_cam_item * +ice_pg_nm_cam_match(struct ice_pg_nm_cam_item *table, int size, + struct ice_pg_cam_key *key) +{ + int i; + + for (i = 0; i < size; i++) { + struct ice_pg_nm_cam_item *item = &table[i]; + + if (__ice_pg_nm_cam_match(item, key)) + return item; + } + + return NULL; +} + +/*** Ternary match ***/ +/* Perform a ternary match on a 1-byte pattern (@pat) given @key and @key_inv + * Rules (per bit): + * Key == 0 and Key_inv == 0 : Never match (Don't care) + * Key == 0 and Key_inv == 1 : Match on bit == 1 + * Key == 1 and Key_inv == 0 : Match on bit == 0 + * Key == 1 and Key_inv == 1 : Always match (Don't care) + * + * Return: true if all bits match, false otherwise. + */ +static bool ice_ternary_match_byte(u8 key, u8 key_inv, u8 pat) +{ + u8 bit_key, bit_key_inv, bit_pat; + int i; + + for (i = 0; i < BITS_PER_BYTE; i++) { + bit_key = key & BIT(i); + bit_key_inv = key_inv & BIT(i); + bit_pat = pat & BIT(i); + + if (bit_key != 0 && bit_key_inv != 0) + continue; + + if ((bit_key == 0 && bit_key_inv == 0) || bit_key == bit_pat) + return false; + } + + return true; +} + +static bool ice_ternary_match(const u8 *key, const u8 *key_inv, + const u8 *pat, int len) +{ + int i; + + for (i = 0; i < len; i++) + if (!ice_ternary_match_byte(key[i], key_inv[i], pat[i])) + return false; + + return true; +} + +/*** ICE_SID_RXPARSER_BOOST_TCAM and ICE_SID_LBL_RXPARSER_TMEM sections ***/ +static void ice_bst_np_kb_dump(struct ice_hw *hw, struct ice_np_keybuilder *kb) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "next proto key builder:\n"); + dev_info(dev, "\topc = %d\n", kb->opc); + dev_info(dev, "\tstart_reg0 = %d\n", kb->start_reg0); + dev_info(dev, "\tlen_reg1 = %d\n", kb->len_reg1); +} + +static void ice_bst_pg_kb_dump(struct ice_hw *hw, struct ice_pg_keybuilder *kb) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "parse graph key builder:\n"); + dev_info(dev, "\tflag0_ena = %d\n", kb->flag0_ena); + dev_info(dev, "\tflag1_ena = %d\n", kb->flag1_ena); + dev_info(dev, "\tflag2_ena = %d\n", kb->flag2_ena); + dev_info(dev, "\tflag3_ena = %d\n", kb->flag3_ena); + dev_info(dev, "\tflag0_idx = %d\n", kb->flag0_idx); + dev_info(dev, "\tflag1_idx = %d\n", kb->flag1_idx); + dev_info(dev, "\tflag2_idx = %d\n", kb->flag2_idx); + dev_info(dev, "\tflag3_idx = %d\n", kb->flag3_idx); + dev_info(dev, "\talu_reg_idx = %d\n", kb->alu_reg_idx); +} + +static void ice_bst_alu_dump(struct ice_hw *hw, struct ice_alu *alu, int idx) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "alu%d:\n", idx); + dev_info(dev, "\topc = %d\n", alu->opc); + dev_info(dev, "\tsrc_start = %d\n", alu->src_start); + dev_info(dev, "\tsrc_len = %d\n", alu->src_len); + dev_info(dev, "\tshift_xlate_sel = %d\n", alu->shift_xlate_sel); + dev_info(dev, "\tshift_xlate_key = %d\n", alu->shift_xlate_key); + dev_info(dev, "\tsrc_reg_id = %d\n", alu->src_reg_id); + dev_info(dev, "\tdst_reg_id = %d\n", alu->dst_reg_id); + dev_info(dev, "\tinc0 = %d\n", alu->inc0); + dev_info(dev, "\tinc1 = %d\n", alu->inc1); + dev_info(dev, "\tproto_offset_opc = %d\n", alu->proto_offset_opc); + dev_info(dev, "\tproto_offset = %d\n", alu->proto_offset); + dev_info(dev, "\tbranch_addr = %d\n", alu->branch_addr); + dev_info(dev, "\timm = %d\n", alu->imm); + dev_info(dev, "\tdst_start = %d\n", alu->dst_start); + dev_info(dev, "\tdst_len = %d\n", alu->dst_len); + dev_info(dev, "\tflags_extr_imm = %d\n", alu->flags_extr_imm); + dev_info(dev, "\tflags_start_imm= %d\n", alu->flags_start_imm); +} + +/** + * ice_bst_tcam_dump - dump a boost tcam info + * @hw: pointer to the hardware structure + * @item: boost tcam to dump + */ +static void ice_bst_tcam_dump(struct ice_hw *hw, struct ice_bst_tcam_item *item) +{ + struct device *dev = ice_hw_to_dev(hw); + int i; + + dev_info(dev, "addr = %d\n", item->addr); + + dev_info(dev, "key : "); + for (i = 0; i < ICE_BST_TCAM_KEY_SIZE; i++) + dev_info(dev, "%02x ", item->key[i]); + + dev_info(dev, "\n"); + + dev_info(dev, "key_inv: "); + for (i = 0; i < ICE_BST_TCAM_KEY_SIZE; i++) + dev_info(dev, "%02x ", item->key_inv[i]); + + dev_info(dev, "\n"); + + dev_info(dev, "hit_idx_grp = %d\n", item->hit_idx_grp); + dev_info(dev, "pg_prio = %d\n", item->pg_prio); + + ice_bst_np_kb_dump(hw, &item->np_kb); + ice_bst_pg_kb_dump(hw, &item->pg_kb); + + ice_bst_alu_dump(hw, &item->alu0, ICE_ALU0_IDX); + ice_bst_alu_dump(hw, &item->alu1, ICE_ALU1_IDX); + ice_bst_alu_dump(hw, &item->alu2, ICE_ALU2_IDX); +} + +static void ice_lbl_dump(struct ice_hw *hw, struct ice_lbl_item *item) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "index = %u\n", item->idx); + dev_info(dev, "type = %u\n", item->type); + dev_info(dev, "label = %s\n", item->label); +} + +#define ICE_BST_ALU_OPC GENMASK_ULL(5, 0) +#define ICE_BST_ALU_SS GENMASK_ULL(13, 6) +#define ICE_BST_ALU_SL GENMASK_ULL(18, 14) +#define ICE_BST_ALU_SXS BIT_ULL(19) +#define ICE_BST_ALU_SXK GENMASK_ULL(23, 20) +#define ICE_BST_ALU_SRID GENMASK_ULL(30, 24) +#define ICE_BST_ALU_DRID GENMASK_ULL(37, 31) +#define ICE_BST_ALU_INC0 BIT_ULL(38) +#define ICE_BST_ALU_INC1 BIT_ULL(39) +#define ICE_BST_ALU_POO GENMASK_ULL(41, 40) +#define ICE_BST_ALU_PO GENMASK_ULL(49, 42) +#define ICE_BST_ALU_BA_S 50 /* offset for the 2nd 64-bits field */ +#define ICE_BST_ALU_BA GENMASK_ULL(57 - ICE_BST_ALU_BA_S, \ + 50 - ICE_BST_ALU_BA_S) +#define ICE_BST_ALU_IMM GENMASK_ULL(73 - ICE_BST_ALU_BA_S, \ + 58 - ICE_BST_ALU_BA_S) +#define ICE_BST_ALU_DFE BIT_ULL(74 - ICE_BST_ALU_BA_S) +#define ICE_BST_ALU_DS GENMASK_ULL(80 - ICE_BST_ALU_BA_S, \ + 75 - ICE_BST_ALU_BA_S) +#define ICE_BST_ALU_DL GENMASK_ULL(86 - ICE_BST_ALU_BA_S, \ + 81 - ICE_BST_ALU_BA_S) +#define ICE_BST_ALU_FEI BIT_ULL(87 - ICE_BST_ALU_BA_S) +#define ICE_BST_ALU_FSI GENMASK_ULL(95 - ICE_BST_ALU_BA_S, \ + 88 - ICE_BST_ALU_BA_S) + +/** + * ice_bst_alu_init - parse 96 bits of ALU entry + * @alu: pointer to the ALU entry structure + * @data: ALU entry data to be parsed + * @off: offset of the ALU entry data + */ +static void ice_bst_alu_init(struct ice_alu *alu, u8 *data, u8 off) +{ + u64 d64; + u8 idd; + + d64 = *((u64 *)data) >> off; + + alu->opc = FIELD_GET(ICE_BST_ALU_OPC, d64); + alu->src_start = FIELD_GET(ICE_BST_ALU_SS, d64); + alu->src_len = FIELD_GET(ICE_BST_ALU_SL, d64); + alu->shift_xlate_sel = FIELD_GET(ICE_BST_ALU_SXS, d64); + alu->shift_xlate_key = FIELD_GET(ICE_BST_ALU_SXK, d64); + alu->src_reg_id = FIELD_GET(ICE_BST_ALU_SRID, d64); + alu->dst_reg_id = FIELD_GET(ICE_BST_ALU_DRID, d64); + alu->inc0 = FIELD_GET(ICE_BST_ALU_INC0, d64); + alu->inc1 = FIELD_GET(ICE_BST_ALU_INC1, d64); + alu->proto_offset_opc = FIELD_GET(ICE_BST_ALU_POO, d64); + alu->proto_offset = FIELD_GET(ICE_BST_ALU_PO, d64); + + idd = (ICE_BST_ALU_BA_S + off) / BITS_PER_BYTE; + off = (ICE_BST_ALU_BA_S + off) % BITS_PER_BYTE; + d64 = *((u64 *)(&data[idd])) >> off; + + alu->branch_addr = FIELD_GET(ICE_BST_ALU_BA, d64); + alu->imm = FIELD_GET(ICE_BST_ALU_IMM, d64); + alu->dedicate_flags_ena = FIELD_GET(ICE_BST_ALU_DFE, d64); + alu->dst_start = FIELD_GET(ICE_BST_ALU_DS, d64); + alu->dst_len = FIELD_GET(ICE_BST_ALU_DL, d64); + alu->flags_extr_imm = FIELD_GET(ICE_BST_ALU_FEI, d64); + alu->flags_start_imm = FIELD_GET(ICE_BST_ALU_FSI, d64); +} + +#define ICE_BST_PGKB_F0_ENA BIT_ULL(0) +#define ICE_BST_PGKB_F0_IDX GENMASK_ULL(6, 1) +#define ICE_BST_PGKB_F1_ENA BIT_ULL(7) +#define ICE_BST_PGKB_F1_IDX GENMASK_ULL(13, 8) +#define ICE_BST_PGKB_F2_ENA BIT_ULL(14) +#define ICE_BST_PGKB_F2_IDX GENMASK_ULL(20, 15) +#define ICE_BST_PGKB_F3_ENA BIT_ULL(21) +#define ICE_BST_PGKB_F3_IDX GENMASK_ULL(27, 22) +#define ICE_BST_PGKB_AR_IDX GENMASK_ULL(34, 28) + +/** + * ice_bst_pgkb_init - parse 35 bits of Parse Graph Key Build + * @kb: pointer to the Parse Graph Key Build structure + * @data: Parse Graph Key Build data to be parsed + */ +static void ice_bst_pgkb_init(struct ice_pg_keybuilder *kb, u64 data) +{ + kb->flag0_ena = FIELD_GET(ICE_BST_PGKB_F0_ENA, data); + kb->flag0_idx = FIELD_GET(ICE_BST_PGKB_F0_IDX, data); + kb->flag1_ena = FIELD_GET(ICE_BST_PGKB_F1_ENA, data); + kb->flag1_idx = FIELD_GET(ICE_BST_PGKB_F1_IDX, data); + kb->flag2_ena = FIELD_GET(ICE_BST_PGKB_F2_ENA, data); + kb->flag2_idx = FIELD_GET(ICE_BST_PGKB_F2_IDX, data); + kb->flag3_ena = FIELD_GET(ICE_BST_PGKB_F3_ENA, data); + kb->flag3_idx = FIELD_GET(ICE_BST_PGKB_F3_IDX, data); + kb->alu_reg_idx = FIELD_GET(ICE_BST_PGKB_AR_IDX, data); +} + +#define ICE_BST_NPKB_OPC GENMASK(1, 0) +#define ICE_BST_NPKB_S_R0 GENMASK(9, 2) +#define ICE_BST_NPKB_L_R1 GENMASK(17, 10) + +/** + * ice_bst_npkb_init - parse 18 bits of Next Protocol Key Build + * @kb: pointer to the Next Protocol Key Build structure + * @data: Next Protocol Key Build data to be parsed + */ +static void ice_bst_npkb_init(struct ice_np_keybuilder *kb, u32 data) +{ + kb->opc = FIELD_GET(ICE_BST_NPKB_OPC, data); + kb->start_reg0 = FIELD_GET(ICE_BST_NPKB_S_R0, data); + kb->len_reg1 = FIELD_GET(ICE_BST_NPKB_L_R1, data); +} + +#define ICE_BT_KEY_S 32 +#define ICE_BT_KEY_IDD (ICE_BT_KEY_S / BITS_PER_BYTE) +#define ICE_BT_KIV_S 192 +#define ICE_BT_KIV_IDD (ICE_BT_KIV_S / BITS_PER_BYTE) +#define ICE_BT_HIG_S 352 +#define ICE_BT_HIG_IDD (ICE_BT_HIG_S / BITS_PER_BYTE) +#define ICE_BT_PGP_S 360 +#define ICE_BT_PGP_IDD (ICE_BT_PGP_S / BITS_PER_BYTE) +#define ICE_BT_PGP_M GENMASK(361 - ICE_BT_PGP_S, 360 - ICE_BT_PGP_S) +#define ICE_BT_NPKB_S 362 +#define ICE_BT_NPKB_IDD (ICE_BT_NPKB_S / BITS_PER_BYTE) +#define ICE_BT_NPKB_OFF (ICE_BT_NPKB_S % BITS_PER_BYTE) +#define ICE_BT_PGKB_S 380 +#define ICE_BT_PGKB_IDD (ICE_BT_PGKB_S / BITS_PER_BYTE) +#define ICE_BT_PGKB_OFF (ICE_BT_PGKB_S % BITS_PER_BYTE) +#define ICE_BT_ALU0_S 415 +#define ICE_BT_ALU0_IDD (ICE_BT_ALU0_S / BITS_PER_BYTE) +#define ICE_BT_ALU0_OFF (ICE_BT_ALU0_S % BITS_PER_BYTE) +#define ICE_BT_ALU1_S 511 +#define ICE_BT_ALU1_IDD (ICE_BT_ALU1_S / BITS_PER_BYTE) +#define ICE_BT_ALU1_OFF (ICE_BT_ALU1_S % BITS_PER_BYTE) +#define ICE_BT_ALU2_S 607 +#define ICE_BT_ALU2_IDD (ICE_BT_ALU2_S / BITS_PER_BYTE) +#define ICE_BT_ALU2_OFF (ICE_BT_ALU2_S % BITS_PER_BYTE) + +/** + * ice_bst_parse_item - parse 704 bits of Boost TCAM entry + * @hw: pointer to the hardware structure + * @idx: index of Boost TCAM entry + * @item: item of Boost TCAM entry + * @data: Boost TCAM entry data to be parsed + * @size: size of Boost TCAM entry + */ +static void ice_bst_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_bst_tcam_item *ti = item; + u8 *buf = (u8 *)data; + int i; + + ti->addr = *(u16 *)buf; + + for (i = 0; i < ICE_BST_TCAM_KEY_SIZE; i++) { + ti->key[i] = buf[ICE_BT_KEY_IDD + i]; + ti->key_inv[i] = buf[ICE_BT_KIV_IDD + i]; + } + ti->hit_idx_grp = buf[ICE_BT_HIG_IDD]; + ti->pg_prio = buf[ICE_BT_PGP_IDD] & ICE_BT_PGP_M; + + ice_bst_npkb_init(&ti->np_kb, + *((u32 *)(&buf[ICE_BT_NPKB_IDD])) >> + ICE_BT_NPKB_OFF); + ice_bst_pgkb_init(&ti->pg_kb, + *((u64 *)(&buf[ICE_BT_PGKB_IDD])) >> + ICE_BT_PGKB_OFF); + + ice_bst_alu_init(&ti->alu0, &buf[ICE_BT_ALU0_IDD], ICE_BT_ALU0_OFF); + ice_bst_alu_init(&ti->alu1, &buf[ICE_BT_ALU1_IDD], ICE_BT_ALU1_OFF); + ice_bst_alu_init(&ti->alu2, &buf[ICE_BT_ALU2_IDD], ICE_BT_ALU2_OFF); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_bst_tcam_dump(hw, ti); +} + +/** + * ice_bst_tcam_table_get - create a boost tcam table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Boost TCAM table. + */ +static struct ice_bst_tcam_item *ice_bst_tcam_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_BOOST_TCAM, + sizeof(struct ice_bst_tcam_item), + ICE_BST_TCAM_TABLE_SIZE, + ice_bst_parse_item, true); +} + +static void ice_parse_lbl_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_lbl_item *lbl_item = item; + struct ice_lbl_item *lbl_data = data; + + lbl_item->idx = lbl_data->idx; + memcpy(lbl_item->label, lbl_data->label, sizeof(lbl_item->label)); + + if (strstarts(lbl_item->label, ICE_LBL_BST_DVM)) + lbl_item->type = ICE_LBL_BST_TYPE_DVM; + else if (strstarts(lbl_item->label, ICE_LBL_BST_SVM)) + lbl_item->type = ICE_LBL_BST_TYPE_SVM; + else if (strstarts(lbl_item->label, ICE_LBL_TNL_VXLAN)) + lbl_item->type = ICE_LBL_BST_TYPE_VXLAN; + else if (strstarts(lbl_item->label, ICE_LBL_TNL_GENEVE)) + lbl_item->type = ICE_LBL_BST_TYPE_GENEVE; + else if (strstarts(lbl_item->label, ICE_LBL_TNL_UDP_ECPRI)) + lbl_item->type = ICE_LBL_BST_TYPE_UDP_ECPRI; + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_lbl_dump(hw, lbl_item); +} + +/** + * ice_bst_lbl_table_get - create a boost label table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Boost label table. + */ +static struct ice_lbl_item *ice_bst_lbl_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_LBL_RXPARSER_TMEM, + sizeof(struct ice_lbl_item), + ICE_BST_TCAM_TABLE_SIZE, + ice_parse_lbl_item, true); +} + +/** + * ice_bst_tcam_match - match a pattern on the boost tcam table + * @tcam_table: boost tcam table to search + * @pat: pattern to match + * + * Return: a pointer to the matching Boost TCAM item or NULL. + */ +struct ice_bst_tcam_item * +ice_bst_tcam_match(struct ice_bst_tcam_item *tcam_table, u8 *pat) +{ + int i; + + for (i = 0; i < ICE_BST_TCAM_TABLE_SIZE; i++) { + struct ice_bst_tcam_item *item = &tcam_table[i]; + + if (item->hit_idx_grp == 0) + continue; + if (ice_ternary_match(item->key, item->key_inv, pat, + ICE_BST_TCAM_KEY_SIZE)) + return item; + } + + return NULL; +} + +/*** ICE_SID_RXPARSER_MARKER_PTYPE section ***/ +/** + * ice_ptype_mk_tcam_dump - dump an ptype marker tcam info + * @hw: pointer to the hardware structure + * @item: ptype marker tcam to dump + */ +static void ice_ptype_mk_tcam_dump(struct ice_hw *hw, + struct ice_ptype_mk_tcam_item *item) +{ + struct device *dev = ice_hw_to_dev(hw); + int i; + + dev_info(dev, "address = %d\n", item->address); + dev_info(dev, "ptype = %d\n", item->ptype); + + dev_info(dev, "key :"); + for (i = 0; i < ICE_PTYPE_MK_TCAM_KEY_SIZE; i++) + dev_info(dev, "%02x ", item->key[i]); + + dev_info(dev, "\n"); + + dev_info(dev, "key_inv:"); + for (i = 0; i < ICE_PTYPE_MK_TCAM_KEY_SIZE; i++) + dev_info(dev, "%02x ", item->key_inv[i]); + + dev_info(dev, "\n"); +} + +static void ice_parse_ptype_mk_tcam_item(struct ice_hw *hw, u16 idx, + void *item, void *data, int size) +{ + memcpy(item, data, size); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_ptype_mk_tcam_dump(hw, + (struct ice_ptype_mk_tcam_item *)item); +} + +/** + * ice_ptype_mk_tcam_table_get - create a ptype marker tcam table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Marker PType TCAM table. + */ +static +struct ice_ptype_mk_tcam_item *ice_ptype_mk_tcam_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_MARKER_PTYPE, + sizeof(struct ice_ptype_mk_tcam_item), + ICE_PTYPE_MK_TCAM_TABLE_SIZE, + ice_parse_ptype_mk_tcam_item, true); +} + +/** + * ice_ptype_mk_tcam_match - match a pattern on a ptype marker tcam table + * @table: ptype marker tcam table to search + * @pat: pattern to match + * @len: length of the pattern + * + * Return: a pointer to the matching Marker PType item or NULL. + */ +struct ice_ptype_mk_tcam_item * +ice_ptype_mk_tcam_match(struct ice_ptype_mk_tcam_item *table, + u8 *pat, int len) +{ + int i; + + for (i = 0; i < ICE_PTYPE_MK_TCAM_TABLE_SIZE; i++) { + struct ice_ptype_mk_tcam_item *item = &table[i]; + + if (ice_ternary_match(item->key, item->key_inv, pat, len)) + return item; + } + + return NULL; +} + +/*** ICE_SID_RXPARSER_MARKER_GRP section ***/ +/** + * ice_mk_grp_dump - dump an marker group item info + * @hw: pointer to the hardware structure + * @item: marker group item to dump + */ +static void ice_mk_grp_dump(struct ice_hw *hw, struct ice_mk_grp_item *item) +{ + struct device *dev = ice_hw_to_dev(hw); + int i; + + dev_info(dev, "index = %d\n", item->idx); + + dev_info(dev, "markers: "); + for (i = 0; i < ICE_MK_COUNT_PER_GRP; i++) + dev_info(dev, "%d ", item->markers[i]); + + dev_info(dev, "\n"); +} + +static void ice_mk_grp_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_mk_grp_item *grp = item; + u8 *buf = data; + int i; + + grp->idx = idx; + + for (i = 0; i < ICE_MK_COUNT_PER_GRP; i++) + grp->markers[i] = buf[i]; + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_mk_grp_dump(hw, grp); +} + +/** + * ice_mk_grp_table_get - create a marker group table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Marker Group ID table. + */ +static struct ice_mk_grp_item *ice_mk_grp_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_MARKER_GRP, + sizeof(struct ice_mk_grp_item), + ICE_MK_GRP_TABLE_SIZE, + ice_mk_grp_parse_item, false); +} + +/*** ICE_SID_RXPARSER_PROTO_GRP section ***/ +static void ice_proto_off_dump(struct ice_hw *hw, + struct ice_proto_off *po, int idx) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "proto %d\n", idx); + dev_info(dev, "\tpolarity = %d\n", po->polarity); + dev_info(dev, "\tproto_id = %d\n", po->proto_id); + dev_info(dev, "\toffset = %d\n", po->offset); +} + +/** + * ice_proto_grp_dump - dump a proto group item info + * @hw: pointer to the hardware structure + * @item: proto group item to dump + */ +static void ice_proto_grp_dump(struct ice_hw *hw, + struct ice_proto_grp_item *item) +{ + int i; + + dev_info(ice_hw_to_dev(hw), "index = %d\n", item->idx); + + for (i = 0; i < ICE_PROTO_COUNT_PER_GRP; i++) + ice_proto_off_dump(hw, &item->po[i], i); +} + +#define ICE_PO_POL BIT(0) +#define ICE_PO_PID GENMASK(8, 1) +#define ICE_PO_OFF GENMASK(21, 12) + +/** + * ice_proto_off_parse - parse 22 bits of Protocol entry + * @po: pointer to the Protocol entry structure + * @data: Protocol entry data to be parsed + */ +static void ice_proto_off_parse(struct ice_proto_off *po, u32 data) +{ + po->polarity = FIELD_GET(ICE_PO_POL, data); + po->proto_id = FIELD_GET(ICE_PO_PID, data); + po->offset = FIELD_GET(ICE_PO_OFF, data); +} + +/** + * ice_proto_grp_parse_item - parse 192 bits of Protocol Group Table entry + * @hw: pointer to the hardware structure + * @idx: index of Protocol Group Table entry + * @item: item of Protocol Group Table entry + * @data: Protocol Group Table entry data to be parsed + * @size: size of Protocol Group Table entry + */ +static void ice_proto_grp_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_proto_grp_item *grp = item; + u8 *buf = (u8 *)data; + u8 idd, off; + u32 d32; + int i; + + grp->idx = idx; + + for (i = 0; i < ICE_PROTO_COUNT_PER_GRP; i++) { + idd = (ICE_PROTO_GRP_ITEM_SIZE * i) / BITS_PER_BYTE; + off = (ICE_PROTO_GRP_ITEM_SIZE * i) % BITS_PER_BYTE; + d32 = *((u32 *)&buf[idd]) >> off; + ice_proto_off_parse(&grp->po[i], d32); + } + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_proto_grp_dump(hw, grp); +} + +/** + * ice_proto_grp_table_get - create a proto group table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Protocol Group table. + */ +static struct ice_proto_grp_item *ice_proto_grp_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_PROTO_GRP, + sizeof(struct ice_proto_grp_item), + ICE_PROTO_GRP_TABLE_SIZE, + ice_proto_grp_parse_item, false); +} + +/*** ICE_SID_RXPARSER_FLAG_REDIR section ***/ +/** + * ice_flg_rd_dump - dump a flag redirect item info + * @hw: pointer to the hardware structure + * @item: flag redirect item to dump + */ +static void ice_flg_rd_dump(struct ice_hw *hw, struct ice_flg_rd_item *item) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "index = %d\n", item->idx); + dev_info(dev, "expose = %d\n", item->expose); + dev_info(dev, "intr_flg_id = %d\n", item->intr_flg_id); +} + +#define ICE_FRT_EXPO BIT(0) +#define ICE_FRT_IFID GENMASK(6, 1) + +/** + * ice_flg_rd_parse_item - parse 8 bits of Flag Redirect Table entry + * @hw: pointer to the hardware structure + * @idx: index of Flag Redirect Table entry + * @item: item of Flag Redirect Table entry + * @data: Flag Redirect Table entry data to be parsed + * @size: size of Flag Redirect Table entry + */ +static void ice_flg_rd_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_flg_rd_item *rdi = item; + u8 d8 = *(u8 *)data; + + rdi->idx = idx; + rdi->expose = FIELD_GET(ICE_FRT_EXPO, d8); + rdi->intr_flg_id = FIELD_GET(ICE_FRT_IFID, d8); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_flg_rd_dump(hw, rdi); +} + +/** + * ice_flg_rd_table_get - create a flag redirect table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Flags Redirection table. + */ +static struct ice_flg_rd_item *ice_flg_rd_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_FLAG_REDIR, + sizeof(struct ice_flg_rd_item), + ICE_FLG_RD_TABLE_SIZE, + ice_flg_rd_parse_item, false); +} + +/** + * ice_flg_redirect - redirect a parser flag to packet flag + * @table: flag redirect table + * @psr_flg: parser flag to redirect + * + * Return: flag or 0 if @psr_flag = 0. + */ +u64 ice_flg_redirect(struct ice_flg_rd_item *table, u64 psr_flg) +{ + u64 flg = 0; + int i; + + for (i = 0; i < ICE_FLG_RDT_SIZE; i++) { + struct ice_flg_rd_item *item = &table[i]; + + if (!item->expose) + continue; + + if (psr_flg & BIT(item->intr_flg_id)) + flg |= BIT(i); + } + + return flg; +} + +/*** ICE_SID_XLT_KEY_BUILDER_SW, ICE_SID_XLT_KEY_BUILDER_ACL, + * ICE_SID_XLT_KEY_BUILDER_FD and ICE_SID_XLT_KEY_BUILDER_RSS + * sections ***/ +static void ice_xlt_kb_entry_dump(struct ice_hw *hw, + struct ice_xlt_kb_entry *entry, int idx) +{ + struct device *dev = ice_hw_to_dev(hw); + int i; + + dev_info(dev, "key builder entry %d\n", idx); + dev_info(dev, "\txlt1_ad_sel = %d\n", entry->xlt1_ad_sel); + dev_info(dev, "\txlt2_ad_sel = %d\n", entry->xlt2_ad_sel); + + for (i = 0; i < ICE_XLT_KB_FLAG0_14_CNT; i++) + dev_info(dev, "\tflg%d_sel = %d\n", i, entry->flg0_14_sel[i]); + + dev_info(dev, "\txlt1_md_sel = %d\n", entry->xlt1_md_sel); + dev_info(dev, "\txlt2_md_sel = %d\n", entry->xlt2_md_sel); +} + +/** + * ice_xlt_kb_dump - dump a xlt key build info + * @hw: pointer to the hardware structure + * @kb: key build to dump + */ +static void ice_xlt_kb_dump(struct ice_hw *hw, struct ice_xlt_kb *kb) +{ + struct device *dev = ice_hw_to_dev(hw); + int i; + + dev_info(dev, "xlt1_pm = %d\n", kb->xlt1_pm); + dev_info(dev, "xlt2_pm = %d\n", kb->xlt2_pm); + dev_info(dev, "prof_id_pm = %d\n", kb->prof_id_pm); + dev_info(dev, "flag15 lo = 0x%08x\n", (u32)kb->flag15); + dev_info(dev, "flag15 hi = 0x%08x\n", + (u32)(kb->flag15 >> (sizeof(u32) * BITS_PER_BYTE))); + + for (i = 0; i < ICE_XLT_KB_TBL_CNT; i++) + ice_xlt_kb_entry_dump(hw, &kb->entries[i], i); +} + +#define ICE_XLT_KB_X1AS_S 32 /* offset for the 1st 64-bits field */ +#define ICE_XLT_KB_X1AS_IDD (ICE_XLT_KB_X1AS_S / BITS_PER_BYTE) +#define ICE_XLT_KB_X1AS_OFF (ICE_XLT_KB_X1AS_S % BITS_PER_BYTE) +#define ICE_XLT_KB_X1AS GENMASK_ULL(34 - ICE_XLT_KB_X1AS_S, \ + 32 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_X2AS GENMASK_ULL(37 - ICE_XLT_KB_X1AS_S, \ + 35 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_FL00 GENMASK_ULL(46 - ICE_XLT_KB_X1AS_S, \ + 38 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_FL01 GENMASK_ULL(55 - ICE_XLT_KB_X1AS_S, \ + 47 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_FL02 GENMASK_ULL(64 - ICE_XLT_KB_X1AS_S, \ + 56 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_FL03 GENMASK_ULL(73 - ICE_XLT_KB_X1AS_S, \ + 65 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_FL04 GENMASK_ULL(82 - ICE_XLT_KB_X1AS_S, \ + 74 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_FL05 GENMASK_ULL(91 - ICE_XLT_KB_X1AS_S, \ + 83 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_FL06_S 92 /* offset for the 2nd 64-bits field */ +#define ICE_XLT_KB_FL06_IDD (ICE_XLT_KB_FL06_S / BITS_PER_BYTE) +#define ICE_XLT_KB_FL06_OFF (ICE_XLT_KB_FL06_S % BITS_PER_BYTE) +#define ICE_XLT_KB_FL06 GENMASK_ULL(100 - ICE_XLT_KB_FL06_S, \ + 92 - ICE_XLT_KB_FL06_S) +#define ICE_XLT_KB_FL07 GENMASK_ULL(109 - ICE_XLT_KB_FL06_S, \ + 101 - ICE_XLT_KB_FL06_S) +#define ICE_XLT_KB_FL08 GENMASK_ULL(118 - ICE_XLT_KB_FL06_S, \ + 110 - ICE_XLT_KB_FL06_S) +#define ICE_XLT_KB_FL09 GENMASK_ULL(127 - ICE_XLT_KB_FL06_S, \ + 119 - ICE_XLT_KB_FL06_S) +#define ICE_XLT_KB_FL10 GENMASK_ULL(136 - ICE_XLT_KB_FL06_S, \ + 128 - ICE_XLT_KB_FL06_S) +#define ICE_XLT_KB_FL11 GENMASK_ULL(145 - ICE_XLT_KB_FL06_S, \ + 137 - ICE_XLT_KB_FL06_S) +#define ICE_XLT_KB_FL12_S 146 /* offset for the 3rd 64-bits field */ +#define ICE_XLT_KB_FL12_IDD (ICE_XLT_KB_FL12_S / BITS_PER_BYTE) +#define ICE_XLT_KB_FL12_OFF (ICE_XLT_KB_FL12_S % BITS_PER_BYTE) +#define ICE_XLT_KB_FL12 GENMASK_ULL(154 - ICE_XLT_KB_FL12_S, \ + 146 - ICE_XLT_KB_FL12_S) +#define ICE_XLT_KB_FL13 GENMASK_ULL(163 - ICE_XLT_KB_FL12_S, \ + 155 - ICE_XLT_KB_FL12_S) +#define ICE_XLT_KB_FL14 GENMASK_ULL(181 - ICE_XLT_KB_FL12_S, \ + 164 - ICE_XLT_KB_FL12_S) +#define ICE_XLT_KB_X1MS GENMASK_ULL(186 - ICE_XLT_KB_FL12_S, \ + 182 - ICE_XLT_KB_FL12_S) +#define ICE_XLT_KB_X2MS GENMASK_ULL(191 - ICE_XLT_KB_FL12_S, \ + 187 - ICE_XLT_KB_FL12_S) + +/** + * ice_kb_entry_init - parse 192 bits of XLT Key Builder entry + * @entry: pointer to the XLT Key Builder entry structure + * @data: XLT Key Builder entry data to be parsed + */ +static void ice_kb_entry_init(struct ice_xlt_kb_entry *entry, u8 *data) +{ + u8 i = 0; + u64 d64; + + d64 = *((u64 *)&data[ICE_XLT_KB_X1AS_IDD]) >> ICE_XLT_KB_X1AS_OFF; + + entry->xlt1_ad_sel = FIELD_GET(ICE_XLT_KB_X1AS, d64); + entry->xlt2_ad_sel = FIELD_GET(ICE_XLT_KB_X2AS, d64); + + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL00, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL01, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL02, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL03, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL04, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL05, d64); + + d64 = *((u64 *)&data[ICE_XLT_KB_FL06_IDD]) >> ICE_XLT_KB_FL06_OFF; + + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL06, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL07, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL08, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL09, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL10, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL11, d64); + + d64 = *((u64 *)&data[ICE_XLT_KB_FL12_IDD]) >> ICE_XLT_KB_FL12_OFF; + + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL12, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL13, d64); + entry->flg0_14_sel[i] = FIELD_GET(ICE_XLT_KB_FL14, d64); + + entry->xlt1_md_sel = FIELD_GET(ICE_XLT_KB_X1MS, d64); + entry->xlt2_md_sel = FIELD_GET(ICE_XLT_KB_X2MS, d64); +} + +#define ICE_XLT_KB_X1PM_OFF 0 +#define ICE_XLT_KB_X2PM_OFF 1 +#define ICE_XLT_KB_PIPM_OFF 2 +#define ICE_XLT_KB_FL15_OFF 4 +#define ICE_XLT_KB_TBL_OFF 12 + +/** + * ice_parse_kb_data - parse 204 bits of XLT Key Build Table + * @hw: pointer to the hardware structure + * @kb: pointer to the XLT Key Build Table structure + * @data: XLT Key Build Table data to be parsed + */ +static void ice_parse_kb_data(struct ice_hw *hw, struct ice_xlt_kb *kb, + void *data) +{ + u8 *buf = data; + int i; + + kb->xlt1_pm = buf[ICE_XLT_KB_X1PM_OFF]; + kb->xlt2_pm = buf[ICE_XLT_KB_X2PM_OFF]; + kb->prof_id_pm = buf[ICE_XLT_KB_PIPM_OFF]; + + kb->flag15 = *(u64 *)&buf[ICE_XLT_KB_FL15_OFF]; + for (i = 0; i < ICE_XLT_KB_TBL_CNT; i++) + ice_kb_entry_init(&kb->entries[i], + &buf[ICE_XLT_KB_TBL_OFF + + i * ICE_XLT_KB_TBL_ENTRY_SIZE]); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_xlt_kb_dump(hw, kb); +} + +static struct ice_xlt_kb *ice_xlt_kb_get(struct ice_hw *hw, u32 sect_type) +{ + struct ice_pkg_enum state = {}; + struct ice_seg *seg = hw->seg; + struct ice_xlt_kb *kb; + void *data; + + if (!seg) + return ERR_PTR(-EINVAL); + + kb = kzalloc(sizeof(*kb), GFP_KERNEL); + if (!kb) + return ERR_PTR(-ENOMEM); + + data = ice_pkg_enum_section(seg, &state, sect_type); + if (!data) { + ice_debug(hw, ICE_DBG_PARSER, "failed to find section type %d.\n", + sect_type); + kfree(kb); + return ERR_PTR(-EINVAL); + } + + ice_parse_kb_data(hw, kb, data); + + return kb; +} + +/** + * ice_xlt_kb_get_sw - create switch xlt key build + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Key Builder table for Switch. + */ +static struct ice_xlt_kb *ice_xlt_kb_get_sw(struct ice_hw *hw) +{ + return ice_xlt_kb_get(hw, ICE_SID_XLT_KEY_BUILDER_SW); +} + +/** + * ice_xlt_kb_get_acl - create acl xlt key build + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Key Builder table for ACL. + */ +static struct ice_xlt_kb *ice_xlt_kb_get_acl(struct ice_hw *hw) +{ + return ice_xlt_kb_get(hw, ICE_SID_XLT_KEY_BUILDER_ACL); +} + +/** + * ice_xlt_kb_get_fd - create fdir xlt key build + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Key Builder table for Flow Director. + */ +static struct ice_xlt_kb *ice_xlt_kb_get_fd(struct ice_hw *hw) +{ + return ice_xlt_kb_get(hw, ICE_SID_XLT_KEY_BUILDER_FD); +} + +/** + * ice_xlt_kb_get_rss - create rss xlt key build + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Key Builder table for RSS. + */ +static struct ice_xlt_kb *ice_xlt_kb_get_rss(struct ice_hw *hw) +{ + return ice_xlt_kb_get(hw, ICE_SID_XLT_KEY_BUILDER_RSS); +} + +#define ICE_XLT_KB_MASK GENMASK_ULL(5, 0) + +/** + * ice_xlt_kb_flag_get - aggregate 64 bits packet flag into 16 bits xlt flag + * @kb: xlt key build + * @pkt_flag: 64 bits packet flag + * + * Return: XLT flag or 0 if @pkt_flag = 0. + */ +u16 ice_xlt_kb_flag_get(struct ice_xlt_kb *kb, u64 pkt_flag) +{ + struct ice_xlt_kb_entry *entry = &kb->entries[0]; + u16 flag = 0; + int i; + + /* check flag 15 */ + if (kb->flag15 & pkt_flag) + flag = BIT(ICE_XLT_KB_FLAG0_14_CNT); + + /* check flag 0 - 14 */ + for (i = 0; i < ICE_XLT_KB_FLAG0_14_CNT; i++) { + /* only check first entry */ + u16 idx = entry->flg0_14_sel[i] & ICE_XLT_KB_MASK; + + if (pkt_flag & BIT(idx)) + flag |= (u16)BIT(i); + } + + return flag; +} + +/*** Parser API ***/ +/** + * ice_parser_create - create a parser instance + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated parser instance or ERR_PTR + * in case of error. + */ +struct ice_parser *ice_parser_create(struct ice_hw *hw) +{ + struct ice_parser *p; + void *err; + + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return ERR_PTR(-ENOMEM); + + p->hw = hw; + p->rt.psr = p; + + p->imem_table = ice_imem_table_get(hw); + if (IS_ERR(p->imem_table)) { + err = p->imem_table; + goto err; + } + + p->mi_table = ice_metainit_table_get(hw); + if (IS_ERR(p->mi_table)) { + err = p->mi_table; + goto err; + } + + p->pg_cam_table = ice_pg_cam_table_get(hw); + if (IS_ERR(p->pg_cam_table)) { + err = p->pg_cam_table; + goto err; + } + + p->pg_sp_cam_table = ice_pg_sp_cam_table_get(hw); + if (IS_ERR(p->pg_sp_cam_table)) { + err = p->pg_sp_cam_table; + goto err; + } + + p->pg_nm_cam_table = ice_pg_nm_cam_table_get(hw); + if (IS_ERR(p->pg_nm_cam_table)) { + err = p->pg_nm_cam_table; + goto err; + } + + p->pg_nm_sp_cam_table = ice_pg_nm_sp_cam_table_get(hw); + if (IS_ERR(p->pg_nm_sp_cam_table)) { + err = p->pg_nm_sp_cam_table; + goto err; + } + + p->bst_tcam_table = ice_bst_tcam_table_get(hw); + if (IS_ERR(p->bst_tcam_table)) { + err = p->bst_tcam_table; + goto err; + } + + p->bst_lbl_table = ice_bst_lbl_table_get(hw); + if (IS_ERR(p->bst_lbl_table)) { + err = p->bst_lbl_table; + goto err; + } + + p->ptype_mk_tcam_table = ice_ptype_mk_tcam_table_get(hw); + if (IS_ERR(p->ptype_mk_tcam_table)) { + err = p->ptype_mk_tcam_table; + goto err; + } + + p->mk_grp_table = ice_mk_grp_table_get(hw); + if (IS_ERR(p->mk_grp_table)) { + err = p->mk_grp_table; + goto err; + } + + p->proto_grp_table = ice_proto_grp_table_get(hw); + if (IS_ERR(p->proto_grp_table)) { + err = p->proto_grp_table; + goto err; + } + + p->flg_rd_table = ice_flg_rd_table_get(hw); + if (IS_ERR(p->flg_rd_table)) { + err = p->flg_rd_table; + goto err; + } + + p->xlt_kb_sw = ice_xlt_kb_get_sw(hw); + if (IS_ERR(p->xlt_kb_sw)) { + err = p->xlt_kb_sw; + goto err; + } + + p->xlt_kb_acl = ice_xlt_kb_get_acl(hw); + if (IS_ERR(p->xlt_kb_acl)) { + err = p->xlt_kb_acl; + goto err; + } + + p->xlt_kb_fd = ice_xlt_kb_get_fd(hw); + if (IS_ERR(p->xlt_kb_fd)) { + err = p->xlt_kb_fd; + goto err; + } + + p->xlt_kb_rss = ice_xlt_kb_get_rss(hw); + if (IS_ERR(p->xlt_kb_rss)) { + err = p->xlt_kb_rss; + goto err; + } + + return p; +err: + ice_parser_destroy(p); + return err; +} + +/** + * ice_parser_destroy - destroy a parser instance + * @psr: pointer to a parser instance + */ +void ice_parser_destroy(struct ice_parser *psr) +{ + kfree(psr->imem_table); + kfree(psr->mi_table); + kfree(psr->pg_cam_table); + kfree(psr->pg_sp_cam_table); + kfree(psr->pg_nm_cam_table); + kfree(psr->pg_nm_sp_cam_table); + kfree(psr->bst_tcam_table); + kfree(psr->bst_lbl_table); + kfree(psr->ptype_mk_tcam_table); + kfree(psr->mk_grp_table); + kfree(psr->proto_grp_table); + kfree(psr->flg_rd_table); + kfree(psr->xlt_kb_sw); + kfree(psr->xlt_kb_acl); + kfree(psr->xlt_kb_fd); + kfree(psr->xlt_kb_rss); + + kfree(psr); +} + +/** + * ice_parser_run - parse on a packet in binary and return the result + * @psr: pointer to a parser instance + * @pkt_buf: packet data + * @pkt_len: packet length + * @rslt: input/output parameter to save parser result. + * + * Return: 0 on success or errno. + */ +int ice_parser_run(struct ice_parser *psr, const u8 *pkt_buf, + int pkt_len, struct ice_parser_result *rslt) +{ + ice_parser_rt_reset(&psr->rt); + ice_parser_rt_pktbuf_set(&psr->rt, pkt_buf, pkt_len); + + return ice_parser_rt_execute(&psr->rt, rslt); +} + +/** + * ice_parser_result_dump - dump a parser result info + * @hw: pointer to the hardware structure + * @rslt: parser result info to dump + */ +void ice_parser_result_dump(struct ice_hw *hw, struct ice_parser_result *rslt) +{ + struct device *dev = ice_hw_to_dev(hw); + int i; + + dev_info(dev, "ptype = %d\n", rslt->ptype); + for (i = 0; i < rslt->po_num; i++) + dev_info(dev, "proto = %d, offset = %d\n", + rslt->po[i].proto_id, rslt->po[i].offset); + + dev_info(dev, "flags_psr = 0x%016llx\n", rslt->flags_psr); + dev_info(dev, "flags_pkt = 0x%016llx\n", rslt->flags_pkt); + dev_info(dev, "flags_sw = 0x%04x\n", rslt->flags_sw); + dev_info(dev, "flags_fd = 0x%04x\n", rslt->flags_fd); + dev_info(dev, "flags_rss = 0x%04x\n", rslt->flags_rss); +} + +#define ICE_BT_VLD_KEY 0xFF +#define ICE_BT_INV_KEY 0xFE + +static void ice_bst_dvm_set(struct ice_parser *psr, enum ice_lbl_type type, + bool on) +{ + u16 i = 0; + + while (true) { + struct ice_bst_tcam_item *item; + u8 key; + + item = ice_bst_tcam_search(psr->bst_tcam_table, + psr->bst_lbl_table, + type, &i); + if (!item) + break; + + key = on ? ICE_BT_VLD_KEY : ICE_BT_INV_KEY; + item->key[ICE_BT_VM_OFF] = key; + item->key_inv[ICE_BT_VM_OFF] = key; + i++; + } +} + +/** + * ice_parser_dvm_set - configure double vlan mode for parser + * @psr: pointer to a parser instance + * @on: true to turn on; false to turn off + */ +void ice_parser_dvm_set(struct ice_parser *psr, bool on) +{ + ice_bst_dvm_set(psr, ICE_LBL_BST_TYPE_DVM, on); + ice_bst_dvm_set(psr, ICE_LBL_BST_TYPE_SVM, !on); +} + +static int ice_tunnel_port_set(struct ice_parser *psr, enum ice_lbl_type type, + u16 udp_port, bool on) +{ + u8 *buf = (u8 *)&udp_port; + u16 i = 0; + + while (true) { + struct ice_bst_tcam_item *item; + + item = ice_bst_tcam_search(psr->bst_tcam_table, + psr->bst_lbl_table, + type, &i); + if (!item) + break; + + /* found empty slot to add */ + if (on && item->key[ICE_BT_TUN_PORT_OFF_H] == ICE_BT_INV_KEY && + item->key_inv[ICE_BT_TUN_PORT_OFF_H] == ICE_BT_INV_KEY) { + item->key_inv[ICE_BT_TUN_PORT_OFF_L] = + buf[ICE_UDP_PORT_OFF_L]; + item->key_inv[ICE_BT_TUN_PORT_OFF_H] = + buf[ICE_UDP_PORT_OFF_H]; + + item->key[ICE_BT_TUN_PORT_OFF_L] = + ICE_BT_VLD_KEY - buf[ICE_UDP_PORT_OFF_L]; + item->key[ICE_BT_TUN_PORT_OFF_H] = + ICE_BT_VLD_KEY - buf[ICE_UDP_PORT_OFF_H]; + + return 0; + /* found a matched slot to delete */ + } else if (!on && + (item->key_inv[ICE_BT_TUN_PORT_OFF_L] == + buf[ICE_UDP_PORT_OFF_L] || + item->key_inv[ICE_BT_TUN_PORT_OFF_H] == + buf[ICE_UDP_PORT_OFF_H])) { + item->key_inv[ICE_BT_TUN_PORT_OFF_L] = ICE_BT_VLD_KEY; + item->key_inv[ICE_BT_TUN_PORT_OFF_H] = ICE_BT_INV_KEY; + + item->key[ICE_BT_TUN_PORT_OFF_L] = ICE_BT_VLD_KEY; + item->key[ICE_BT_TUN_PORT_OFF_H] = ICE_BT_INV_KEY; + + return 0; + } + i++; + } + + return -EINVAL; +} + +/** + * ice_parser_vxlan_tunnel_set - configure vxlan tunnel for parser + * @psr: pointer to a parser instance + * @udp_port: vxlan tunnel port in UDP header + * @on: true to turn on; false to turn off + * + * Return: 0 on success or errno on failure. + */ +int ice_parser_vxlan_tunnel_set(struct ice_parser *psr, + u16 udp_port, bool on) +{ + return ice_tunnel_port_set(psr, ICE_LBL_BST_TYPE_VXLAN, udp_port, on); +} + +/** + * ice_parser_geneve_tunnel_set - configure geneve tunnel for parser + * @psr: pointer to a parser instance + * @udp_port: geneve tunnel port in UDP header + * @on: true to turn on; false to turn off + * + * Return: 0 on success or errno on failure. + */ +int ice_parser_geneve_tunnel_set(struct ice_parser *psr, + u16 udp_port, bool on) +{ + return ice_tunnel_port_set(psr, ICE_LBL_BST_TYPE_GENEVE, udp_port, on); +} + +/** + * ice_parser_ecpri_tunnel_set - configure ecpri tunnel for parser + * @psr: pointer to a parser instance + * @udp_port: ecpri tunnel port in UDP header + * @on: true to turn on; false to turn off + * + * Return: 0 on success or errno on failure. + */ +int ice_parser_ecpri_tunnel_set(struct ice_parser *psr, + u16 udp_port, bool on) +{ + return ice_tunnel_port_set(psr, ICE_LBL_BST_TYPE_UDP_ECPRI, + udp_port, on); +} + +/** + * ice_nearest_proto_id - find nearest protocol ID + * @rslt: pointer to a parser result instance + * @offset: a min value for the protocol offset + * @proto_id: the protocol ID (output) + * @proto_off: the protocol offset (output) + * + * From the protocols in @rslt, find the nearest protocol that has offset + * larger than @offset. + * + * Return: if true, the protocol's ID and offset + */ +static bool ice_nearest_proto_id(struct ice_parser_result *rslt, u16 offset, + u8 *proto_id, u16 *proto_off) +{ + u16 dist = U16_MAX; + u8 proto = 0; + int i; + + for (i = 0; i < rslt->po_num; i++) { + if (offset < rslt->po[i].offset) + continue; + if (offset - rslt->po[i].offset < dist) { + proto = rslt->po[i].proto_id; + dist = offset - rslt->po[i].offset; + } + } + + if (dist % 2) + return false; + + *proto_id = proto; + *proto_off = dist; + + return true; +} + +/* default flag mask to cover GTP_EH_PDU, GTP_EH_PDU_LINK and TUN2 + * In future, the flag masks should learn from DDP + */ +#define ICE_KEYBUILD_FLAG_MASK_DEFAULT_SW 0x4002 +#define ICE_KEYBUILD_FLAG_MASK_DEFAULT_ACL 0x0000 +#define ICE_KEYBUILD_FLAG_MASK_DEFAULT_FD 0x6080 +#define ICE_KEYBUILD_FLAG_MASK_DEFAULT_RSS 0x6010 + +/** + * ice_parser_profile_init - initialize a FXP profile based on parser result + * @rslt: a instance of a parser result + * @pkt_buf: packet data buffer + * @msk_buf: packet mask buffer + * @buf_len: packet length + * @blk: FXP pipeline stage + * @prof: input/output parameter to save the profile + * + * Return: 0 on success or errno on failure. + */ +int ice_parser_profile_init(struct ice_parser_result *rslt, + const u8 *pkt_buf, const u8 *msk_buf, + int buf_len, enum ice_block blk, + struct ice_parser_profile *prof) +{ + u8 proto_id = U8_MAX; + u16 proto_off = 0; + u16 off; + + memset(prof, 0, sizeof(*prof)); + set_bit(rslt->ptype, prof->ptypes); + if (blk == ICE_BLK_SW) { + prof->flags = rslt->flags_sw; + prof->flags_msk = ICE_KEYBUILD_FLAG_MASK_DEFAULT_SW; + } else if (blk == ICE_BLK_ACL) { + prof->flags = rslt->flags_acl; + prof->flags_msk = ICE_KEYBUILD_FLAG_MASK_DEFAULT_ACL; + } else if (blk == ICE_BLK_FD) { + prof->flags = rslt->flags_fd; + prof->flags_msk = ICE_KEYBUILD_FLAG_MASK_DEFAULT_FD; + } else if (blk == ICE_BLK_RSS) { + prof->flags = rslt->flags_rss; + prof->flags_msk = ICE_KEYBUILD_FLAG_MASK_DEFAULT_RSS; + } else { + return -EINVAL; + } + + for (off = 0; off < buf_len - 1; off++) { + if (msk_buf[off] == 0 && msk_buf[off + 1] == 0) + continue; + if (!ice_nearest_proto_id(rslt, off, &proto_id, &proto_off)) + continue; + if (prof->fv_num >= ICE_PARSER_FV_MAX) + return -EINVAL; + + prof->fv[prof->fv_num].proto_id = proto_id; + prof->fv[prof->fv_num].offset = proto_off; + prof->fv[prof->fv_num].spec = *(const u16 *)&pkt_buf[off]; + prof->fv[prof->fv_num].msk = *(const u16 *)&msk_buf[off]; + prof->fv_num++; + } + + return 0; +} + +/** + * ice_parser_profile_dump - dump an FXP profile info + * @hw: pointer to the hardware structure + * @prof: profile info to dump + */ +void ice_parser_profile_dump(struct ice_hw *hw, + struct ice_parser_profile *prof) +{ + struct device *dev = ice_hw_to_dev(hw); + u16 i; + + dev_info(dev, "ptypes:\n"); + for (i = 0; i < ICE_FLOW_PTYPE_MAX; i++) + if (test_bit(i, prof->ptypes)) + dev_info(dev, "\t%u\n", i); + + for (i = 0; i < prof->fv_num; i++) + dev_info(dev, "proto = %u, offset = %2u, spec = 0x%04x, mask = 0x%04x\n", + prof->fv[i].proto_id, prof->fv[i].offset, + prof->fv[i].spec, prof->fv[i].msk); + + dev_info(dev, "flags = 0x%04x\n", prof->flags); + dev_info(dev, "flags_msk = 0x%04x\n", prof->flags_msk); +} diff --git a/drivers/net/ethernet/intel/ice/ice_parser.h b/drivers/net/ethernet/intel/ice/ice_parser.h new file mode 100644 index 000000000000..4f56d53d56b9 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_parser.h @@ -0,0 +1,538 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2024 Intel Corporation */ + +#ifndef _ICE_PARSER_H_ +#define _ICE_PARSER_H_ + +#define ICE_SEC_DATA_OFFSET 4 +#define ICE_SID_RXPARSER_IMEM_ENTRY_SIZE 48 +#define ICE_SID_RXPARSER_METADATA_INIT_ENTRY_SIZE 24 +#define ICE_SID_RXPARSER_CAM_ENTRY_SIZE 16 +#define ICE_SID_RXPARSER_PG_SPILL_ENTRY_SIZE 17 +#define ICE_SID_RXPARSER_NOMATCH_CAM_ENTRY_SIZE 12 +#define ICE_SID_RXPARSER_NOMATCH_SPILL_ENTRY_SIZE 13 +#define ICE_SID_RXPARSER_BOOST_TCAM_ENTRY_SIZE 88 +#define ICE_SID_RXPARSER_MARKER_TYPE_ENTRY_SIZE 24 +#define ICE_SID_RXPARSER_MARKER_GRP_ENTRY_SIZE 8 +#define ICE_SID_RXPARSER_PROTO_GRP_ENTRY_SIZE 24 +#define ICE_SID_RXPARSER_FLAG_REDIR_ENTRY_SIZE 1 + +#define ICE_SEC_LBL_DATA_OFFSET 2 +#define ICE_SID_LBL_ENTRY_SIZE 66 + +/*** ICE_SID_RXPARSER_IMEM section ***/ +#define ICE_IMEM_TABLE_SIZE 192 + +/* TCAM boost Master; if bit is set, and TCAM hit, TCAM output overrides iMEM + * output. + */ +struct ice_bst_main { + bool alu0; + bool alu1; + bool alu2; + bool pg; +}; + +struct ice_bst_keybuilder { + u8 prio; /* 0-3: PG precedence within ALUs (3 highest) */ + bool tsr_ctrl; /* TCAM Search Register control */ +}; + +/* Next protocol Key builder */ +struct ice_np_keybuilder { + u8 opc; + u8 start_reg0; + u8 len_reg1; +}; + +enum ice_np_keybuilder_opcode { + ICE_NPKB_OPC_EXTRACT = 0, + ICE_NPKB_OPC_BUILD = 1, + ICE_NPKB_OPC_BYPASS = 2, +}; + +/* Parse Graph Key builder */ +struct ice_pg_keybuilder { + bool flag0_ena; + bool flag1_ena; + bool flag2_ena; + bool flag3_ena; + u8 flag0_idx; + u8 flag1_idx; + u8 flag2_idx; + u8 flag3_idx; + u8 alu_reg_idx; +}; + +enum ice_alu_idx { + ICE_ALU0_IDX = 0, + ICE_ALU1_IDX = 1, + ICE_ALU2_IDX = 2, +}; + +enum ice_alu_opcode { + ICE_ALU_PARK = 0, + ICE_ALU_MOV_ADD = 1, + ICE_ALU_ADD = 2, + ICE_ALU_MOV_AND = 4, + ICE_ALU_AND = 5, + ICE_ALU_AND_IMM = 6, + ICE_ALU_MOV_OR = 7, + ICE_ALU_OR = 8, + ICE_ALU_MOV_XOR = 9, + ICE_ALU_XOR = 10, + ICE_ALU_NOP = 11, + ICE_ALU_BR = 12, + ICE_ALU_BREQ = 13, + ICE_ALU_BRNEQ = 14, + ICE_ALU_BRGT = 15, + ICE_ALU_BRLT = 16, + ICE_ALU_BRGEQ = 17, + ICE_ALU_BRLEG = 18, + ICE_ALU_SETEQ = 19, + ICE_ALU_ANDEQ = 20, + ICE_ALU_OREQ = 21, + ICE_ALU_SETNEQ = 22, + ICE_ALU_ANDNEQ = 23, + ICE_ALU_ORNEQ = 24, + ICE_ALU_SETGT = 25, + ICE_ALU_ANDGT = 26, + ICE_ALU_ORGT = 27, + ICE_ALU_SETLT = 28, + ICE_ALU_ANDLT = 29, + ICE_ALU_ORLT = 30, + ICE_ALU_MOV_SUB = 31, + ICE_ALU_SUB = 32, + ICE_ALU_INVALID = 64, +}; + +enum ice_proto_off_opcode { + ICE_PO_OFF_REMAIN = 0, + ICE_PO_OFF_HDR_ADD = 1, + ICE_PO_OFF_HDR_SUB = 2, +}; + +struct ice_alu { + enum ice_alu_opcode opc; + u8 src_start; + u8 src_len; + bool shift_xlate_sel; + u8 shift_xlate_key; + u8 src_reg_id; + u8 dst_reg_id; + bool inc0; + bool inc1; + u8 proto_offset_opc; + u8 proto_offset; + u8 branch_addr; + u16 imm; + bool dedicate_flags_ena; + u8 dst_start; + u8 dst_len; + bool flags_extr_imm; + u8 flags_start_imm; +}; + +/* Parser program code (iMEM) */ +struct ice_imem_item { + u16 idx; + struct ice_bst_main b_m; + struct ice_bst_keybuilder b_kb; + u8 pg_prio; + struct ice_np_keybuilder np_kb; + struct ice_pg_keybuilder pg_kb; + struct ice_alu alu0; + struct ice_alu alu1; + struct ice_alu alu2; +}; + +/*** ICE_SID_RXPARSER_METADATA_INIT section ***/ +#define ICE_METAINIT_TABLE_SIZE 16 + +/* Metadata Initialization item */ +struct ice_metainit_item { + u16 idx; + + u8 tsr; /* TCAM Search key Register */ + u16 ho; /* Header Offset register */ + u16 pc; /* Program Counter register */ + u16 pg_rn; /* Parse Graph Root Node */ + u8 cd; /* Control Domain ID */ + + /* General Purpose Registers */ + bool gpr_a_ctrl; + u8 gpr_a_data_mdid; + u8 gpr_a_data_start; + u8 gpr_a_data_len; + u8 gpr_a_id; + + bool gpr_b_ctrl; + u8 gpr_b_data_mdid; + u8 gpr_b_data_start; + u8 gpr_b_data_len; + u8 gpr_b_id; + + bool gpr_c_ctrl; + u8 gpr_c_data_mdid; + u8 gpr_c_data_start; + u8 gpr_c_data_len; + u8 gpr_c_id; + + bool gpr_d_ctrl; + u8 gpr_d_data_mdid; + u8 gpr_d_data_start; + u8 gpr_d_data_len; + u8 gpr_d_id; + + u64 flags; /* Initial value for all flags */ +}; + +/*** ICE_SID_RXPARSER_CAM, ICE_SID_RXPARSER_PG_SPILL, + * ICE_SID_RXPARSER_NOMATCH_CAM and ICE_SID_RXPARSER_NOMATCH_CAM + * sections ***/ +#define ICE_PG_CAM_TABLE_SIZE 2048 +#define ICE_PG_SP_CAM_TABLE_SIZE 128 +#define ICE_PG_NM_CAM_TABLE_SIZE 1024 +#define ICE_PG_NM_SP_CAM_TABLE_SIZE 64 + +struct ice_pg_cam_key { + bool valid; + struct_group_attr(val, __packed, + u16 node_id; /* Node ID of protocol in parse graph */ + bool flag0; + bool flag1; + bool flag2; + bool flag3; + u8 boost_idx; /* Boost TCAM match index */ + u16 alu_reg; + u32 next_proto; /* next Protocol value (must be last) */ + ); +}; + +struct ice_pg_nm_cam_key { + bool valid; + struct_group_attr(val, __packed, + u16 node_id; + bool flag0; + bool flag1; + bool flag2; + bool flag3; + u8 boost_idx; + u16 alu_reg; + ); +}; + +struct ice_pg_cam_action { + u16 next_node; /* Parser Node ID for the next round */ + u8 next_pc; /* next Program Counter */ + bool is_pg; /* is protocol group */ + u8 proto_id; /* protocol ID or proto group ID */ + bool is_mg; /* is marker group */ + u8 marker_id; /* marker ID or marker group ID */ + bool is_last_round; + bool ho_polarity; /* header offset polarity */ + u16 ho_inc; +}; + +/* Parse Graph item */ +struct ice_pg_cam_item { + u16 idx; + struct ice_pg_cam_key key; + struct ice_pg_cam_action action; +}; + +/* Parse Graph No Match item */ +struct ice_pg_nm_cam_item { + u16 idx; + struct ice_pg_nm_cam_key key; + struct ice_pg_cam_action action; +}; + +struct ice_pg_cam_item *ice_pg_cam_match(struct ice_pg_cam_item *table, + int size, struct ice_pg_cam_key *key); +struct ice_pg_nm_cam_item * +ice_pg_nm_cam_match(struct ice_pg_nm_cam_item *table, int size, + struct ice_pg_cam_key *key); + +/*** ICE_SID_RXPARSER_BOOST_TCAM and ICE_SID_LBL_RXPARSER_TMEM sections ***/ +#define ICE_BST_TCAM_TABLE_SIZE 256 +#define ICE_BST_TCAM_KEY_SIZE 20 + +/* Boost TCAM item */ +struct ice_bst_tcam_item { + u16 addr; + u8 key[ICE_BST_TCAM_KEY_SIZE]; + u8 key_inv[ICE_BST_TCAM_KEY_SIZE]; + u8 hit_idx_grp; + u8 pg_prio; + struct ice_np_keybuilder np_kb; + struct ice_pg_keybuilder pg_kb; + struct ice_alu alu0; + struct ice_alu alu1; + struct ice_alu alu2; +}; + +#define ICE_LBL_LEN 64 +#define ICE_LBL_BST_DVM "BOOST_MAC_VLAN_DVM" +#define ICE_LBL_BST_SVM "BOOST_MAC_VLAN_SVM" +#define ICE_LBL_TNL_VXLAN "TNL_VXLAN" +#define ICE_LBL_TNL_GENEVE "TNL_GENEVE" +#define ICE_LBL_TNL_UDP_ECPRI "TNL_UDP_ECPRI" + +enum ice_lbl_type { + ICE_LBL_BST_TYPE_UNKNOWN, + ICE_LBL_BST_TYPE_DVM, + ICE_LBL_BST_TYPE_SVM, + ICE_LBL_BST_TYPE_VXLAN, + ICE_LBL_BST_TYPE_GENEVE, + ICE_LBL_BST_TYPE_UDP_ECPRI, +}; + +struct ice_lbl_item { + u16 idx; + char label[ICE_LBL_LEN]; + + /* must be at the end, not part of the DDP section */ + enum ice_lbl_type type; +}; + +struct ice_bst_tcam_item * +ice_bst_tcam_match(struct ice_bst_tcam_item *tcam_table, u8 *pat); +struct ice_bst_tcam_item * +ice_bst_tcam_search(struct ice_bst_tcam_item *tcam_table, + struct ice_lbl_item *lbl_table, + enum ice_lbl_type type, u16 *start); + +/*** ICE_SID_RXPARSER_MARKER_PTYPE section ***/ +#define ICE_PTYPE_MK_TCAM_TABLE_SIZE 1024 +#define ICE_PTYPE_MK_TCAM_KEY_SIZE 10 + +struct ice_ptype_mk_tcam_item { + u16 address; + u16 ptype; + u8 key[ICE_PTYPE_MK_TCAM_KEY_SIZE]; + u8 key_inv[ICE_PTYPE_MK_TCAM_KEY_SIZE]; +} __packed; + +struct ice_ptype_mk_tcam_item * +ice_ptype_mk_tcam_match(struct ice_ptype_mk_tcam_item *table, + u8 *pat, int len); +/*** ICE_SID_RXPARSER_MARKER_GRP section ***/ +#define ICE_MK_GRP_TABLE_SIZE 128 +#define ICE_MK_COUNT_PER_GRP 8 + +/* Marker Group item */ +struct ice_mk_grp_item { + int idx; + u8 markers[ICE_MK_COUNT_PER_GRP]; +}; + +/*** ICE_SID_RXPARSER_PROTO_GRP section ***/ +#define ICE_PROTO_COUNT_PER_GRP 8 +#define ICE_PROTO_GRP_TABLE_SIZE 192 +#define ICE_PROTO_GRP_ITEM_SIZE 22 +struct ice_proto_off { + bool polarity; /* true: positive, false: negative */ + u8 proto_id; + u16 offset; /* 10 bit protocol offset */ +}; + +/* Protocol Group item */ +struct ice_proto_grp_item { + u16 idx; + struct ice_proto_off po[ICE_PROTO_COUNT_PER_GRP]; +}; + +/*** ICE_SID_RXPARSER_FLAG_REDIR section ***/ +#define ICE_FLG_RD_TABLE_SIZE 64 +#define ICE_FLG_RDT_SIZE 64 + +/* Flags Redirection item */ +struct ice_flg_rd_item { + u16 idx; + bool expose; + u8 intr_flg_id; /* Internal Flag ID */ +}; + +u64 ice_flg_redirect(struct ice_flg_rd_item *table, u64 psr_flg); + +/*** ICE_SID_XLT_KEY_BUILDER_SW, ICE_SID_XLT_KEY_BUILDER_ACL, + * ICE_SID_XLT_KEY_BUILDER_FD and ICE_SID_XLT_KEY_BUILDER_RSS + * sections ***/ +#define ICE_XLT_KB_FLAG0_14_CNT 15 +#define ICE_XLT_KB_TBL_CNT 8 +#define ICE_XLT_KB_TBL_ENTRY_SIZE 24 + +struct ice_xlt_kb_entry { + u8 xlt1_ad_sel; + u8 xlt2_ad_sel; + u16 flg0_14_sel[ICE_XLT_KB_FLAG0_14_CNT]; + u8 xlt1_md_sel; + u8 xlt2_md_sel; +}; + +/* XLT Key Builder */ +struct ice_xlt_kb { + u8 xlt1_pm; /* XLT1 Partition Mode */ + u8 xlt2_pm; /* XLT2 Partition Mode */ + u8 prof_id_pm; /* Profile ID Partition Mode */ + u64 flag15; + + struct ice_xlt_kb_entry entries[ICE_XLT_KB_TBL_CNT]; +}; + +u16 ice_xlt_kb_flag_get(struct ice_xlt_kb *kb, u64 pkt_flag); + +/*** Parser API ***/ +#define ICE_GPR_HV_IDX 64 +#define ICE_GPR_HV_SIZE 32 +#define ICE_GPR_ERR_IDX 84 +#define ICE_GPR_FLG_IDX 104 +#define ICE_GPR_FLG_SIZE 16 + +#define ICE_GPR_TSR_IDX 108 /* TSR: TCAM Search Register */ +#define ICE_GPR_NN_IDX 109 /* NN: Next Parsing Cycle Node ID */ +#define ICE_GPR_HO_IDX 110 /* HO: Next Parsing Cycle hdr Offset */ +#define ICE_GPR_NP_IDX 111 /* NP: Next Parsing Cycle */ + +#define ICE_PARSER_MAX_PKT_LEN 504 +#define ICE_PARSER_PKT_REV 32 +#define ICE_PARSER_GPR_NUM 128 +#define ICE_PARSER_FLG_NUM 64 +#define ICE_PARSER_ERR_NUM 16 +#define ICE_MARKER_ID_SIZE 9 +#define ICE_MARKER_MAX_SIZE \ + (ICE_MARKER_ID_SIZE * BITS_PER_BYTE - 1) +#define ICE_MARKER_ID_NUM 8 +#define ICE_PO_PAIR_SIZE 256 + +struct ice_gpr_pu { + /* array of flags to indicate if GRP needs to be updated */ + bool gpr_val_upd[ICE_PARSER_GPR_NUM]; + u16 gpr_val[ICE_PARSER_GPR_NUM]; + u64 flg_msk; + u64 flg_val; + u16 err_msk; + u16 err_val; +}; + +enum ice_pg_prio { + ICE_PG_P0 = 0, + ICE_PG_P1 = 1, + ICE_PG_P2 = 2, + ICE_PG_P3 = 3, +}; + +struct ice_parser_rt { + struct ice_parser *psr; + u16 gpr[ICE_PARSER_GPR_NUM]; + u8 pkt_buf[ICE_PARSER_MAX_PKT_LEN + ICE_PARSER_PKT_REV]; + u16 pkt_len; + u16 po; + u8 bst_key[ICE_BST_TCAM_KEY_SIZE]; + struct ice_pg_cam_key pg_key; + u8 pg_prio; + struct ice_alu *alu0; + struct ice_alu *alu1; + struct ice_alu *alu2; + struct ice_pg_cam_action *action; + struct ice_gpr_pu pu; + u8 markers[ICE_MARKER_ID_SIZE]; + bool protocols[ICE_PO_PAIR_SIZE]; + u16 offsets[ICE_PO_PAIR_SIZE]; +}; + +struct ice_parser_proto_off { + u8 proto_id; /* hardware protocol ID */ + u16 offset; /* offset from the start of the protocol header */ +}; + +#define ICE_PARSER_PROTO_OFF_PAIR_SIZE 16 +#define ICE_PARSER_FLAG_PSR_SIZE 8 +#define ICE_PARSER_FV_SIZE 48 +#define ICE_PARSER_FV_MAX 24 +#define ICE_BT_TUN_PORT_OFF_H 16 +#define ICE_BT_TUN_PORT_OFF_L 15 +#define ICE_BT_VM_OFF 0 +#define ICE_UDP_PORT_OFF_H 1 +#define ICE_UDP_PORT_OFF_L 0 + +struct ice_parser_result { + u16 ptype; /* 16 bits hardware PTYPE */ + /* array of protocol and header offset pairs */ + struct ice_parser_proto_off po[ICE_PARSER_PROTO_OFF_PAIR_SIZE]; + int po_num; /* # of protocol-offset pairs must <= 16 */ + u64 flags_psr; /* parser flags */ + u64 flags_pkt; /* packet flags */ + u16 flags_sw; /* key builder flags for SW */ + u16 flags_acl; /* key builder flags for ACL */ + u16 flags_fd; /* key builder flags for FD */ + u16 flags_rss; /* key builder flags for RSS */ +}; + +void ice_parser_rt_reset(struct ice_parser_rt *rt); +void ice_parser_rt_pktbuf_set(struct ice_parser_rt *rt, const u8 *pkt_buf, + int pkt_len); +int ice_parser_rt_execute(struct ice_parser_rt *rt, + struct ice_parser_result *rslt); + +struct ice_parser { + struct ice_hw *hw; /* pointer to the hardware structure */ + + struct ice_imem_item *imem_table; + struct ice_metainit_item *mi_table; + + struct ice_pg_cam_item *pg_cam_table; + struct ice_pg_cam_item *pg_sp_cam_table; + struct ice_pg_nm_cam_item *pg_nm_cam_table; + struct ice_pg_nm_cam_item *pg_nm_sp_cam_table; + + struct ice_bst_tcam_item *bst_tcam_table; + struct ice_lbl_item *bst_lbl_table; + struct ice_ptype_mk_tcam_item *ptype_mk_tcam_table; + struct ice_mk_grp_item *mk_grp_table; + struct ice_proto_grp_item *proto_grp_table; + struct ice_flg_rd_item *flg_rd_table; + + struct ice_xlt_kb *xlt_kb_sw; + struct ice_xlt_kb *xlt_kb_acl; + struct ice_xlt_kb *xlt_kb_fd; + struct ice_xlt_kb *xlt_kb_rss; + + struct ice_parser_rt rt; +}; + +struct ice_parser *ice_parser_create(struct ice_hw *hw); +void ice_parser_destroy(struct ice_parser *psr); +void ice_parser_dvm_set(struct ice_parser *psr, bool on); +int ice_parser_vxlan_tunnel_set(struct ice_parser *psr, u16 udp_port, bool on); +int ice_parser_geneve_tunnel_set(struct ice_parser *psr, u16 udp_port, bool on); +int ice_parser_ecpri_tunnel_set(struct ice_parser *psr, u16 udp_port, bool on); +int ice_parser_run(struct ice_parser *psr, const u8 *pkt_buf, + int pkt_len, struct ice_parser_result *rslt); +void ice_parser_result_dump(struct ice_hw *hw, struct ice_parser_result *rslt); + +struct ice_parser_fv { + u8 proto_id; /* hardware protocol ID */ + u16 offset; /* offset from the start of the protocol header */ + u16 spec; /* pattern to match */ + u16 msk; /* pattern mask */ +}; + +struct ice_parser_profile { + /* array of field vectors */ + struct ice_parser_fv fv[ICE_PARSER_FV_SIZE]; + int fv_num; /* # of field vectors must <= 48 */ + u16 flags; /* key builder flags */ + u16 flags_msk; /* key builder flag mask */ + + DECLARE_BITMAP(ptypes, ICE_FLOW_PTYPE_MAX); /* PTYPE bitmap */ +}; + +int ice_parser_profile_init(struct ice_parser_result *rslt, + const u8 *pkt_buf, const u8 *msk_buf, + int buf_len, enum ice_block blk, + struct ice_parser_profile *prof); +void ice_parser_profile_dump(struct ice_hw *hw, + struct ice_parser_profile *prof); +#endif /* _ICE_PARSER_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_parser_rt.c b/drivers/net/ethernet/intel/ice/ice_parser_rt.c new file mode 100644 index 000000000000..3995d662e050 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_parser_rt.c @@ -0,0 +1,859 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2024 Intel Corporation */ + +#include "ice_common.h" + +static void ice_rt_tsr_set(struct ice_parser_rt *rt, u16 tsr) +{ + rt->gpr[ICE_GPR_TSR_IDX] = tsr; +} + +static void ice_rt_ho_set(struct ice_parser_rt *rt, u16 ho) +{ + rt->gpr[ICE_GPR_HO_IDX] = ho; + memcpy(&rt->gpr[ICE_GPR_HV_IDX], &rt->pkt_buf[ho], ICE_GPR_HV_SIZE); +} + +static void ice_rt_np_set(struct ice_parser_rt *rt, u16 pc) +{ + rt->gpr[ICE_GPR_NP_IDX] = pc; +} + +static void ice_rt_nn_set(struct ice_parser_rt *rt, u16 node) +{ + rt->gpr[ICE_GPR_NN_IDX] = node; +} + +static void +ice_rt_flag_set(struct ice_parser_rt *rt, unsigned int idx, bool set) +{ + struct ice_hw *hw = rt->psr->hw; + unsigned int word, id; + + word = idx / ICE_GPR_FLG_SIZE; + id = idx % ICE_GPR_FLG_SIZE; + + if (set) { + rt->gpr[ICE_GPR_FLG_IDX + word] |= (u16)BIT(id); + ice_debug(hw, ICE_DBG_PARSER, "Set parser flag %u\n", idx); + } else { + rt->gpr[ICE_GPR_FLG_IDX + word] &= ~(u16)BIT(id); + ice_debug(hw, ICE_DBG_PARSER, "Clear parser flag %u\n", idx); + } +} + +static void ice_rt_gpr_set(struct ice_parser_rt *rt, int idx, u16 val) +{ + struct ice_hw *hw = rt->psr->hw; + + if (idx == ICE_GPR_HO_IDX) + ice_rt_ho_set(rt, val); + else + rt->gpr[idx] = val; + + ice_debug(hw, ICE_DBG_PARSER, "Set GPR %d value %d\n", idx, val); +} + +static void ice_rt_err_set(struct ice_parser_rt *rt, unsigned int idx, bool set) +{ + struct ice_hw *hw = rt->psr->hw; + + if (set) { + rt->gpr[ICE_GPR_ERR_IDX] |= (u16)BIT(idx); + ice_debug(hw, ICE_DBG_PARSER, "Set parser error %u\n", idx); + } else { + rt->gpr[ICE_GPR_ERR_IDX] &= ~(u16)BIT(idx); + ice_debug(hw, ICE_DBG_PARSER, "Reset parser error %u\n", idx); + } +} + +/** + * ice_parser_rt_reset - reset the parser runtime + * @rt: pointer to the parser runtime + */ +void ice_parser_rt_reset(struct ice_parser_rt *rt) +{ + struct ice_parser *psr = rt->psr; + struct ice_metainit_item *mi; + unsigned int i; + + mi = &psr->mi_table[0]; + + memset(rt, 0, sizeof(*rt)); + rt->psr = psr; + + ice_rt_tsr_set(rt, mi->tsr); + ice_rt_ho_set(rt, mi->ho); + ice_rt_np_set(rt, mi->pc); + ice_rt_nn_set(rt, mi->pg_rn); + + for (i = 0; i < ICE_PARSER_FLG_NUM; i++) { + if (mi->flags & BIT(i)) + ice_rt_flag_set(rt, i, true); + } +} + +/** + * ice_parser_rt_pktbuf_set - set a packet into parser runtime + * @rt: pointer to the parser runtime + * @pkt_buf: buffer with packet data + * @pkt_len: packet buffer length + */ +void ice_parser_rt_pktbuf_set(struct ice_parser_rt *rt, const u8 *pkt_buf, + int pkt_len) +{ + int len = min(ICE_PARSER_MAX_PKT_LEN, pkt_len); + u16 ho = rt->gpr[ICE_GPR_HO_IDX]; + + memcpy(rt->pkt_buf, pkt_buf, len); + rt->pkt_len = pkt_len; + + memcpy(&rt->gpr[ICE_GPR_HV_IDX], &rt->pkt_buf[ho], ICE_GPR_HV_SIZE); +} + +static void ice_bst_key_init(struct ice_parser_rt *rt, + struct ice_imem_item *imem) +{ + u8 tsr = (u8)rt->gpr[ICE_GPR_TSR_IDX]; + u16 ho = rt->gpr[ICE_GPR_HO_IDX]; + u8 *key = rt->bst_key; + int idd, i; + + idd = ICE_BST_TCAM_KEY_SIZE - 1; + if (imem->b_kb.tsr_ctrl) + key[idd] = tsr; + else + key[idd] = imem->b_kb.prio; + + idd = ICE_BST_TCAM_KEY_SIZE - 2; + for (i = idd; i >= 0; i--) { + int j; + + j = ho + idd - i; + if (j < ICE_PARSER_MAX_PKT_LEN) + key[i] = rt->pkt_buf[j]; + else + key[i] = 0; + } + + ice_debug_array_w_prefix(rt->psr->hw, ICE_DBG_PARSER, + KBUILD_MODNAME ": Generated Boost TCAM Key", + key, ICE_BST_TCAM_KEY_SIZE); +} + +static u16 ice_bit_rev_u16(u16 v, int len) +{ + return bitrev16(v) >> (BITS_PER_TYPE(v) - len); +} + +static u32 ice_bit_rev_u32(u32 v, int len) +{ + return bitrev32(v) >> (BITS_PER_TYPE(v) - len); +} + +static u32 ice_hv_bit_sel(struct ice_parser_rt *rt, int start, int len) +{ + int offset; + u32 buf[2]; + u64 val; + + offset = ICE_GPR_HV_IDX + (start / BITS_PER_TYPE(u16)); + + memcpy(buf, &rt->gpr[offset], sizeof(buf)); + + buf[0] = bitrev8x4(buf[0]); + buf[1] = bitrev8x4(buf[1]); + + val = *(u64 *)buf; + val >>= start % BITS_PER_TYPE(u16); + + return ice_bit_rev_u32(val, len); +} + +static u32 ice_pk_build(struct ice_parser_rt *rt, + struct ice_np_keybuilder *kb) +{ + if (kb->opc == ICE_NPKB_OPC_EXTRACT) + return ice_hv_bit_sel(rt, kb->start_reg0, kb->len_reg1); + else if (kb->opc == ICE_NPKB_OPC_BUILD) + return rt->gpr[kb->start_reg0] | + ((u32)rt->gpr[kb->len_reg1] << BITS_PER_TYPE(u16)); + else if (kb->opc == ICE_NPKB_OPC_BYPASS) + return 0; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Unsupported OP Code %u\n", + kb->opc); + return U32_MAX; +} + +static bool ice_flag_get(struct ice_parser_rt *rt, unsigned int index) +{ + int word = index / ICE_GPR_FLG_SIZE; + int id = index % ICE_GPR_FLG_SIZE; + + return !!(rt->gpr[ICE_GPR_FLG_IDX + word] & (u16)BIT(id)); +} + +static int ice_imem_pgk_init(struct ice_parser_rt *rt, + struct ice_imem_item *imem) +{ + memset(&rt->pg_key, 0, sizeof(rt->pg_key)); + rt->pg_key.next_proto = ice_pk_build(rt, &imem->np_kb); + if (rt->pg_key.next_proto == U32_MAX) + return -EINVAL; + + if (imem->pg_kb.flag0_ena) + rt->pg_key.flag0 = ice_flag_get(rt, imem->pg_kb.flag0_idx); + if (imem->pg_kb.flag1_ena) + rt->pg_key.flag1 = ice_flag_get(rt, imem->pg_kb.flag1_idx); + if (imem->pg_kb.flag2_ena) + rt->pg_key.flag2 = ice_flag_get(rt, imem->pg_kb.flag2_idx); + if (imem->pg_kb.flag3_ena) + rt->pg_key.flag3 = ice_flag_get(rt, imem->pg_kb.flag3_idx); + + rt->pg_key.alu_reg = rt->gpr[imem->pg_kb.alu_reg_idx]; + rt->pg_key.node_id = rt->gpr[ICE_GPR_NN_IDX]; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Generate Parse Graph Key: node_id(%d), flag0-3(%d,%d,%d,%d), boost_idx(%d), alu_reg(0x%04x), next_proto(0x%08x)\n", + rt->pg_key.node_id, + rt->pg_key.flag0, + rt->pg_key.flag1, + rt->pg_key.flag2, + rt->pg_key.flag3, + rt->pg_key.boost_idx, + rt->pg_key.alu_reg, + rt->pg_key.next_proto); + + return 0; +} + +static void ice_imem_alu0_set(struct ice_parser_rt *rt, + struct ice_imem_item *imem) +{ + rt->alu0 = &imem->alu0; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU0 from imem pc %d\n", + imem->idx); +} + +static void ice_imem_alu1_set(struct ice_parser_rt *rt, + struct ice_imem_item *imem) +{ + rt->alu1 = &imem->alu1; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU1 from imem pc %d\n", + imem->idx); +} + +static void ice_imem_alu2_set(struct ice_parser_rt *rt, + struct ice_imem_item *imem) +{ + rt->alu2 = &imem->alu2; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU2 from imem pc %d\n", + imem->idx); +} + +static void ice_imem_pgp_set(struct ice_parser_rt *rt, + struct ice_imem_item *imem) +{ + rt->pg_prio = imem->pg_prio; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load PG priority %d from imem pc %d\n", + rt->pg_prio, imem->idx); +} + +static int ice_bst_pgk_init(struct ice_parser_rt *rt, + struct ice_bst_tcam_item *bst) +{ + memset(&rt->pg_key, 0, sizeof(rt->pg_key)); + rt->pg_key.boost_idx = bst->hit_idx_grp; + rt->pg_key.next_proto = ice_pk_build(rt, &bst->np_kb); + if (rt->pg_key.next_proto == U32_MAX) + return -EINVAL; + + if (bst->pg_kb.flag0_ena) + rt->pg_key.flag0 = ice_flag_get(rt, bst->pg_kb.flag0_idx); + if (bst->pg_kb.flag1_ena) + rt->pg_key.flag1 = ice_flag_get(rt, bst->pg_kb.flag1_idx); + if (bst->pg_kb.flag2_ena) + rt->pg_key.flag2 = ice_flag_get(rt, bst->pg_kb.flag2_idx); + if (bst->pg_kb.flag3_ena) + rt->pg_key.flag3 = ice_flag_get(rt, bst->pg_kb.flag3_idx); + + rt->pg_key.alu_reg = rt->gpr[bst->pg_kb.alu_reg_idx]; + rt->pg_key.node_id = rt->gpr[ICE_GPR_NN_IDX]; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Generate Parse Graph Key: node_id(%d), flag0-3(%d,%d,%d,%d), boost_idx(%d), alu_reg(0x%04x), next_proto(0x%08x)\n", + rt->pg_key.node_id, + rt->pg_key.flag0, + rt->pg_key.flag1, + rt->pg_key.flag2, + rt->pg_key.flag3, + rt->pg_key.boost_idx, + rt->pg_key.alu_reg, + rt->pg_key.next_proto); + + return 0; +} + +static void ice_bst_alu0_set(struct ice_parser_rt *rt, + struct ice_bst_tcam_item *bst) +{ + rt->alu0 = &bst->alu0; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU0 from boost address %d\n", + bst->addr); +} + +static void ice_bst_alu1_set(struct ice_parser_rt *rt, + struct ice_bst_tcam_item *bst) +{ + rt->alu1 = &bst->alu1; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU1 from boost address %d\n", + bst->addr); +} + +static void ice_bst_alu2_set(struct ice_parser_rt *rt, + struct ice_bst_tcam_item *bst) +{ + rt->alu2 = &bst->alu2; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU2 from boost address %d\n", + bst->addr); +} + +static void ice_bst_pgp_set(struct ice_parser_rt *rt, + struct ice_bst_tcam_item *bst) +{ + rt->pg_prio = bst->pg_prio; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load PG priority %d from boost address %d\n", + rt->pg_prio, bst->addr); +} + +static struct ice_pg_cam_item *ice_rt_pg_cam_match(struct ice_parser_rt *rt) +{ + struct ice_parser *psr = rt->psr; + struct ice_pg_cam_item *item; + + item = ice_pg_cam_match(psr->pg_cam_table, ICE_PG_CAM_TABLE_SIZE, + &rt->pg_key); + if (!item) + item = ice_pg_cam_match(psr->pg_sp_cam_table, + ICE_PG_SP_CAM_TABLE_SIZE, &rt->pg_key); + return item; +} + +static +struct ice_pg_nm_cam_item *ice_rt_pg_nm_cam_match(struct ice_parser_rt *rt) +{ + struct ice_parser *psr = rt->psr; + struct ice_pg_nm_cam_item *item; + + item = ice_pg_nm_cam_match(psr->pg_nm_cam_table, + ICE_PG_NM_CAM_TABLE_SIZE, &rt->pg_key); + + if (!item) + item = ice_pg_nm_cam_match(psr->pg_nm_sp_cam_table, + ICE_PG_NM_SP_CAM_TABLE_SIZE, + &rt->pg_key); + return item; +} + +static void ice_gpr_add(struct ice_parser_rt *rt, int idx, u16 val) +{ + rt->pu.gpr_val_upd[idx] = true; + rt->pu.gpr_val[idx] = val; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Pending update for register %d value %d\n", + idx, val); +} + +static void ice_pg_exe(struct ice_parser_rt *rt) +{ + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ParseGraph action ...\n"); + + ice_gpr_add(rt, ICE_GPR_NP_IDX, rt->action->next_pc); + ice_gpr_add(rt, ICE_GPR_NN_IDX, rt->action->next_node); + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ParseGraph action done.\n"); +} + +static void ice_flg_add(struct ice_parser_rt *rt, int idx, bool val) +{ + rt->pu.flg_msk |= BIT_ULL(idx); + if (val) + rt->pu.flg_val |= BIT_ULL(idx); + else + rt->pu.flg_val &= ~BIT_ULL(idx); + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Pending update for flag %d value %d\n", + idx, val); +} + +static void ice_flg_update(struct ice_parser_rt *rt, struct ice_alu *alu) +{ + u32 hv_bit_sel; + int i; + + if (!alu->dedicate_flags_ena) + return; + + if (alu->flags_extr_imm) { + for (i = 0; i < alu->dst_len; i++) + ice_flg_add(rt, alu->dst_start + i, + !!(alu->flags_start_imm & BIT(i))); + } else { + for (i = 0; i < alu->dst_len; i++) { + hv_bit_sel = ice_hv_bit_sel(rt, + alu->flags_start_imm + i, + 1); + ice_flg_add(rt, alu->dst_start + i, !!hv_bit_sel); + } + } +} + +static void ice_po_update(struct ice_parser_rt *rt, struct ice_alu *alu) +{ + if (alu->proto_offset_opc == ICE_PO_OFF_HDR_ADD) + rt->po = (u16)(rt->gpr[ICE_GPR_HO_IDX] + alu->proto_offset); + else if (alu->proto_offset_opc == ICE_PO_OFF_HDR_SUB) + rt->po = (u16)(rt->gpr[ICE_GPR_HO_IDX] - alu->proto_offset); + else if (alu->proto_offset_opc == ICE_PO_OFF_REMAIN) + rt->po = rt->gpr[ICE_GPR_HO_IDX]; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Update Protocol Offset = %d\n", + rt->po); +} + +static u16 ice_reg_bit_sel(struct ice_parser_rt *rt, int reg_idx, + int start, int len) +{ + int offset; + u32 val; + + offset = ICE_GPR_HV_IDX + (start / BITS_PER_TYPE(u16)); + + memcpy(&val, &rt->gpr[offset], sizeof(val)); + + val = bitrev8x4(val); + val >>= start % BITS_PER_TYPE(u16); + + return ice_bit_rev_u16(val, len); +} + +static void ice_err_add(struct ice_parser_rt *rt, int idx, bool val) +{ + rt->pu.err_msk |= (u16)BIT(idx); + if (val) + rt->pu.flg_val |= (u64)BIT_ULL(idx); + else + rt->pu.flg_val &= ~(u64)BIT_ULL(idx); + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Pending update for error %d value %d\n", + idx, val); +} + +static void ice_dst_reg_bit_set(struct ice_parser_rt *rt, struct ice_alu *alu, + bool val) +{ + u16 flg_idx; + + if (alu->dedicate_flags_ena) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "DedicatedFlagsEnable should not be enabled in opcode %d\n", + alu->opc); + return; + } + + if (alu->dst_reg_id == ICE_GPR_ERR_IDX) { + if (alu->dst_start >= ICE_PARSER_ERR_NUM) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Invalid error %d\n", + alu->dst_start); + return; + } + ice_err_add(rt, alu->dst_start, val); + } else if (alu->dst_reg_id >= ICE_GPR_FLG_IDX) { + flg_idx = (u16)(((alu->dst_reg_id - ICE_GPR_FLG_IDX) << 4) + + alu->dst_start); + + if (flg_idx >= ICE_PARSER_FLG_NUM) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Invalid flag %d\n", + flg_idx); + return; + } + ice_flg_add(rt, flg_idx, val); + } else { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Unexpected Dest Register Bit set, RegisterID %d Start %d\n", + alu->dst_reg_id, alu->dst_start); + } +} + +static void ice_alu_exe(struct ice_parser_rt *rt, struct ice_alu *alu) +{ + u16 dst, src, shift, imm; + + if (alu->shift_xlate_sel) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "shift_xlate_sel != 0 is not expected\n"); + return; + } + + ice_po_update(rt, alu); + ice_flg_update(rt, alu); + + dst = rt->gpr[alu->dst_reg_id]; + src = ice_reg_bit_sel(rt, alu->src_reg_id, + alu->src_start, alu->src_len); + shift = alu->shift_xlate_key; + imm = alu->imm; + + switch (alu->opc) { + case ICE_ALU_PARK: + break; + case ICE_ALU_MOV_ADD: + dst = (src << shift) + imm; + ice_gpr_add(rt, alu->dst_reg_id, dst); + break; + case ICE_ALU_ADD: + dst += (src << shift) + imm; + ice_gpr_add(rt, alu->dst_reg_id, dst); + break; + case ICE_ALU_ORLT: + if (src < imm) + ice_dst_reg_bit_set(rt, alu, true); + ice_gpr_add(rt, ICE_GPR_NP_IDX, alu->branch_addr); + break; + case ICE_ALU_OREQ: + if (src == imm) + ice_dst_reg_bit_set(rt, alu, true); + ice_gpr_add(rt, ICE_GPR_NP_IDX, alu->branch_addr); + break; + case ICE_ALU_SETEQ: + ice_dst_reg_bit_set(rt, alu, src == imm); + ice_gpr_add(rt, ICE_GPR_NP_IDX, alu->branch_addr); + break; + case ICE_ALU_MOV_XOR: + dst = (src << shift) ^ imm; + ice_gpr_add(rt, alu->dst_reg_id, dst); + break; + default: + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Unsupported ALU instruction %d\n", + alu->opc); + break; + } +} + +static void ice_alu0_exe(struct ice_parser_rt *rt) +{ + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU0 ...\n"); + ice_alu_exe(rt, rt->alu0); + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU0 done.\n"); +} + +static void ice_alu1_exe(struct ice_parser_rt *rt) +{ + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU1 ...\n"); + ice_alu_exe(rt, rt->alu1); + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU1 done.\n"); +} + +static void ice_alu2_exe(struct ice_parser_rt *rt) +{ + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU2 ...\n"); + ice_alu_exe(rt, rt->alu2); + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU2 done.\n"); +} + +static void ice_pu_exe(struct ice_parser_rt *rt) +{ + struct ice_gpr_pu *pu = &rt->pu; + unsigned int i; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Updating Registers ...\n"); + + for (i = 0; i < ICE_PARSER_GPR_NUM; i++) { + if (pu->gpr_val_upd[i]) + ice_rt_gpr_set(rt, i, pu->gpr_val[i]); + } + + for (i = 0; i < ICE_PARSER_FLG_NUM; i++) { + if (pu->flg_msk & BIT(i)) + ice_rt_flag_set(rt, i, pu->flg_val & BIT(i)); + } + + for (i = 0; i < ICE_PARSER_ERR_NUM; i++) { + if (pu->err_msk & BIT(i)) + ice_rt_err_set(rt, i, pu->err_val & BIT(i)); + } + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Updating Registers done.\n"); +} + +static void ice_alu_pg_exe(struct ice_parser_rt *rt) +{ + memset(&rt->pu, 0, sizeof(rt->pu)); + + switch (rt->pg_prio) { + case (ICE_PG_P0): + ice_pg_exe(rt); + ice_alu0_exe(rt); + ice_alu1_exe(rt); + ice_alu2_exe(rt); + break; + case (ICE_PG_P1): + ice_alu0_exe(rt); + ice_pg_exe(rt); + ice_alu1_exe(rt); + ice_alu2_exe(rt); + break; + case (ICE_PG_P2): + ice_alu0_exe(rt); + ice_alu1_exe(rt); + ice_pg_exe(rt); + ice_alu2_exe(rt); + break; + case (ICE_PG_P3): + ice_alu0_exe(rt); + ice_alu1_exe(rt); + ice_alu2_exe(rt); + ice_pg_exe(rt); + break; + } + + ice_pu_exe(rt); + + if (rt->action->ho_inc == 0) + return; + + if (rt->action->ho_polarity) + ice_rt_ho_set(rt, rt->gpr[ICE_GPR_HO_IDX] + rt->action->ho_inc); + else + ice_rt_ho_set(rt, rt->gpr[ICE_GPR_HO_IDX] - rt->action->ho_inc); +} + +static void ice_proto_off_update(struct ice_parser_rt *rt) +{ + struct ice_parser *psr = rt->psr; + + if (rt->action->is_pg) { + struct ice_proto_grp_item *proto_grp = + &psr->proto_grp_table[rt->action->proto_id]; + u16 po; + int i; + + for (i = 0; i < ICE_PROTO_COUNT_PER_GRP; i++) { + struct ice_proto_off *entry = &proto_grp->po[i]; + + if (entry->proto_id == U8_MAX) + break; + + if (!entry->polarity) + po = rt->po + entry->offset; + else + po = rt->po - entry->offset; + + rt->protocols[entry->proto_id] = true; + rt->offsets[entry->proto_id] = po; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Set Protocol %d at offset %d\n", + entry->proto_id, po); + } + } else { + rt->protocols[rt->action->proto_id] = true; + rt->offsets[rt->action->proto_id] = rt->po; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Set Protocol %d at offset %d\n", + rt->action->proto_id, rt->po); + } +} + +static void ice_marker_set(struct ice_parser_rt *rt, int idx) +{ + unsigned int byte = idx / BITS_PER_BYTE; + unsigned int bit = idx % BITS_PER_BYTE; + + rt->markers[byte] |= (u8)BIT(bit); +} + +static void ice_marker_update(struct ice_parser_rt *rt) +{ + struct ice_parser *psr = rt->psr; + + if (rt->action->is_mg) { + struct ice_mk_grp_item *mk_grp = + &psr->mk_grp_table[rt->action->marker_id]; + int i; + + for (i = 0; i < ICE_MARKER_ID_NUM; i++) { + u8 marker = mk_grp->markers[i]; + + if (marker == ICE_MARKER_MAX_SIZE) + break; + + ice_marker_set(rt, marker); + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Set Marker %d\n", + marker); + } + } else { + if (rt->action->marker_id != ICE_MARKER_MAX_SIZE) + ice_marker_set(rt, rt->action->marker_id); + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Set Marker %d\n", + rt->action->marker_id); + } +} + +static u16 ice_ptype_resolve(struct ice_parser_rt *rt) +{ + struct ice_ptype_mk_tcam_item *item; + struct ice_parser *psr = rt->psr; + + item = ice_ptype_mk_tcam_match(psr->ptype_mk_tcam_table, + rt->markers, ICE_MARKER_ID_SIZE); + if (item) + return item->ptype; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Could not resolve PTYPE\n"); + return U16_MAX; +} + +static void ice_proto_off_resolve(struct ice_parser_rt *rt, + struct ice_parser_result *rslt) +{ + int i; + + for (i = 0; i < ICE_PO_PAIR_SIZE - 1; i++) { + if (rt->protocols[i]) { + rslt->po[rslt->po_num].proto_id = (u8)i; + rslt->po[rslt->po_num].offset = rt->offsets[i]; + rslt->po_num++; + } + } +} + +static void ice_result_resolve(struct ice_parser_rt *rt, + struct ice_parser_result *rslt) +{ + struct ice_parser *psr = rt->psr; + + memset(rslt, 0, sizeof(*rslt)); + + memcpy(&rslt->flags_psr, &rt->gpr[ICE_GPR_FLG_IDX], + ICE_PARSER_FLAG_PSR_SIZE); + rslt->flags_pkt = ice_flg_redirect(psr->flg_rd_table, rslt->flags_psr); + rslt->flags_sw = ice_xlt_kb_flag_get(psr->xlt_kb_sw, rslt->flags_pkt); + rslt->flags_fd = ice_xlt_kb_flag_get(psr->xlt_kb_fd, rslt->flags_pkt); + rslt->flags_rss = ice_xlt_kb_flag_get(psr->xlt_kb_rss, rslt->flags_pkt); + + ice_proto_off_resolve(rt, rslt); + rslt->ptype = ice_ptype_resolve(rt); +} + +/** + * ice_parser_rt_execute - parser execution routine + * @rt: pointer to the parser runtime + * @rslt: input/output parameter to save parser result + * + * Return: 0 on success or errno. + */ +int ice_parser_rt_execute(struct ice_parser_rt *rt, + struct ice_parser_result *rslt) +{ + struct ice_pg_nm_cam_item *pg_nm_cam; + struct ice_parser *psr = rt->psr; + struct ice_pg_cam_item *pg_cam; + int status = 0; + u16 node; + u16 pc; + + node = rt->gpr[ICE_GPR_NN_IDX]; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Start with Node: %u\n", node); + + while (true) { + struct ice_bst_tcam_item *bst; + struct ice_imem_item *imem; + + pc = rt->gpr[ICE_GPR_NP_IDX]; + imem = &psr->imem_table[pc]; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load imem at pc: %u\n", + pc); + + ice_bst_key_init(rt, imem); + bst = ice_bst_tcam_match(psr->bst_tcam_table, rt->bst_key); + if (!bst) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "No Boost TCAM Match\n"); + status = ice_imem_pgk_init(rt, imem); + if (status) + break; + ice_imem_alu0_set(rt, imem); + ice_imem_alu1_set(rt, imem); + ice_imem_alu2_set(rt, imem); + ice_imem_pgp_set(rt, imem); + } else { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Boost TCAM Match address: %u\n", + bst->addr); + if (imem->b_m.pg) { + status = ice_bst_pgk_init(rt, bst); + if (status) + break; + ice_bst_pgp_set(rt, bst); + } else { + status = ice_imem_pgk_init(rt, imem); + if (status) + break; + ice_imem_pgp_set(rt, imem); + } + + if (imem->b_m.alu0) + ice_bst_alu0_set(rt, bst); + else + ice_imem_alu0_set(rt, imem); + + if (imem->b_m.alu1) + ice_bst_alu1_set(rt, bst); + else + ice_imem_alu1_set(rt, imem); + + if (imem->b_m.alu2) + ice_bst_alu2_set(rt, bst); + else + ice_imem_alu2_set(rt, imem); + } + + rt->action = NULL; + pg_cam = ice_rt_pg_cam_match(rt); + if (!pg_cam) { + pg_nm_cam = ice_rt_pg_nm_cam_match(rt); + if (pg_nm_cam) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Match ParseGraph Nomatch CAM Address %u\n", + pg_nm_cam->idx); + rt->action = &pg_nm_cam->action; + } + } else { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Match ParseGraph CAM Address %u\n", + pg_cam->idx); + rt->action = &pg_cam->action; + } + + if (!rt->action) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Failed to match ParseGraph CAM, stop parsing.\n"); + status = -EINVAL; + break; + } + + ice_alu_pg_exe(rt); + ice_marker_update(rt); + ice_proto_off_update(rt); + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Go to node %u\n", + rt->action->next_node); + + if (rt->action->is_last_round) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Last Round in ParseGraph Action, stop parsing.\n"); + break; + } + + if (rt->gpr[ICE_GPR_HO_IDX] >= rt->pkt_len) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Header Offset (%u) is larger than packet len (%u), stop parsing\n", + rt->gpr[ICE_GPR_HO_IDX], rt->pkt_len); + break; + } + } + + ice_result_resolve(rt, rslt); + + return status; +} diff --git a/drivers/net/ethernet/intel/ice/ice_protocol_type.h b/drivers/net/ethernet/intel/ice/ice_protocol_type.h index f6f27361c3cf..7c09ea0f03ba 100644 --- a/drivers/net/ethernet/intel/ice/ice_protocol_type.h +++ b/drivers/net/ethernet/intel/ice/ice_protocol_type.h @@ -7,18 +7,24 @@ /* Each recipe can match up to 5 different fields. Fields to match can be meta- * data, values extracted from packet headers, or results from other recipes. - * One of the 5 fields is reserved for matching the switch ID. So, up to 4 - * recipes can provide intermediate results to another one through chaining, - * e.g. recipes 0, 1, 2, and 3 can provide intermediate results to recipe 4. + * Therefore, up to 5 recipes can provide intermediate results to another one + * through chaining, e.g. recipes 0, 1, 2, 3 and 4 can provide intermediate + * results to recipe 5. Note that one of the fields in one of the recipes must + * always be reserved for matching the switch ID. */ -#define ICE_NUM_WORDS_RECIPE 4 +#define ICE_NUM_WORDS_RECIPE 5 -/* Max recipes that can be chained */ +/* Max recipes that can be chained, not including the last one, which combines + * intermediate results. + */ #define ICE_MAX_CHAIN_RECIPE 5 -/* 1 word reserved for switch ID from allowed 5 words. - * So a recipe can have max 4 words. And you can chain 5 such recipes - * together. So maximum words that can be programmed for look up is 5 * 4. +/* Total max recipes in chain recipe (including intermediate results) */ +#define ICE_MAX_CHAIN_RECIPE_RES (ICE_MAX_CHAIN_RECIPE + 1) + +/* A recipe can have max 5 words, and 5 recipes can be chained together (using + * the 6th one, which would contain only result indexes). So maximum words that + * can be programmed for lookup is 5 * 5 (not including intermediate results). */ #define ICE_MAX_CHAIN_WORDS (ICE_NUM_WORDS_RECIPE * ICE_MAX_CHAIN_RECIPE) @@ -43,6 +49,7 @@ enum ice_protocol_type { ICE_NVGRE, ICE_GTP, ICE_GTP_NO_PAY, + ICE_PFCP, ICE_PPPOE, ICE_L2TPV3, ICE_VLAN_EX, @@ -61,6 +68,7 @@ enum ice_sw_tunnel_type { ICE_SW_TUN_NVGRE, ICE_SW_TUN_GTPU, ICE_SW_TUN_GTPC, + ICE_SW_TUN_PFCP, ICE_ALL_TUNNELS /* All tunnel types including NVGRE */ }; @@ -202,6 +210,15 @@ struct ice_udp_gtp_hdr { u8 rsvrd; }; +struct ice_pfcp_hdr { + u8 flags; + u8 msg_type; + __be16 length; + __be64 seid; + __be32 seq; + u8 spare; +} __packed __aligned(__alignof__(u16)); + struct ice_pppoe_hdr { u8 rsrvd_ver_type; u8 rsrvd_code; @@ -418,6 +435,7 @@ union ice_prot_hdr { struct ice_udp_tnl_hdr tnl_hdr; struct ice_nvgre_hdr nvgre_hdr; struct ice_udp_gtp_hdr gtp_hdr; + struct ice_pfcp_hdr pfcp_hdr; struct ice_pppoe_hdr pppoe_hdr; struct ice_l2tpv3_sess_hdr l2tpv3_sess_hdr; struct ice_hw_metadata metadata; @@ -437,32 +455,11 @@ struct ice_prot_ext_tbl_entry { /* Extractions to be looked up for a given recipe */ struct ice_prot_lkup_ext { - u16 prot_type; u8 n_val_words; /* create a buffer to hold max words per recipe */ - u16 field_off[ICE_MAX_CHAIN_WORDS]; u16 field_mask[ICE_MAX_CHAIN_WORDS]; struct ice_fv_word fv_words[ICE_MAX_CHAIN_WORDS]; - - /* Indicate field offsets that have field vector indices assigned */ - DECLARE_BITMAP(done, ICE_MAX_CHAIN_WORDS); -}; - -struct ice_pref_recipe_group { - u8 n_val_pairs; /* Number of valid pairs */ - struct ice_fv_word pairs[ICE_NUM_WORDS_RECIPE]; - u16 mask[ICE_NUM_WORDS_RECIPE]; }; -struct ice_recp_grp_entry { - struct list_head l_entry; - -#define ICE_INVAL_CHAIN_IND 0xFF - u16 rid; - u8 chain_idx; - u16 fv_idx[ICE_NUM_WORDS_RECIPE]; - u16 fv_mask[ICE_NUM_WORDS_RECIPE]; - struct ice_pref_recipe_group r_group; -}; #endif /* _ICE_PROTOCOL_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index c11eba07283c..b79a148ed0f2 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -4,255 +4,187 @@ #include "ice.h" #include "ice_lib.h" #include "ice_trace.h" +#include "ice_cgu_regs.h" + +static const char ice_pin_names[][64] = { + "SDP0", + "SDP1", + "SDP2", + "SDP3", + "TIME_SYNC", + "1PPS" +}; -#define E810_OUT_PROP_DELAY_NS 1 - -#define UNKNOWN_INCVAL_E82X 0x100000000ULL +static const struct ice_ptp_pin_desc ice_pin_desc_e82x[] = { + /* name, gpio, delay */ + { TIME_SYNC, { 4, -1 }, { 0, 0 }}, + { ONE_PPS, { -1, 5 }, { 0, 11 }}, +}; -static const struct ptp_pin_desc ice_pin_desc_e810t[] = { - /* name idx func chan */ - { "GNSS", GNSS, PTP_PF_EXTTS, 0, { 0, } }, - { "SMA1", SMA1, PTP_PF_NONE, 1, { 0, } }, - { "U.FL1", UFL1, PTP_PF_NONE, 1, { 0, } }, - { "SMA2", SMA2, PTP_PF_NONE, 2, { 0, } }, - { "U.FL2", UFL2, PTP_PF_NONE, 2, { 0, } }, +static const struct ice_ptp_pin_desc ice_pin_desc_e825c[] = { + /* name, gpio, delay */ + { SDP0, { 0, 0 }, { 15, 14 }}, + { SDP1, { 1, 1 }, { 15, 14 }}, + { SDP2, { 2, 2 }, { 15, 14 }}, + { SDP3, { 3, 3 }, { 15, 14 }}, + { TIME_SYNC, { 4, -1 }, { 11, 0 }}, + { ONE_PPS, { -1, 5 }, { 0, 9 }}, }; -/** - * ice_get_sma_config_e810t - * @hw: pointer to the hw struct - * @ptp_pins: pointer to the ptp_pin_desc struture - * - * Read the configuration of the SMA control logic and put it into the - * ptp_pin_desc structure - */ -static int -ice_get_sma_config_e810t(struct ice_hw *hw, struct ptp_pin_desc *ptp_pins) -{ - u8 data, i; - int status; +static const struct ice_ptp_pin_desc ice_pin_desc_e810[] = { + /* name, gpio, delay */ + { SDP0, { 0, 0 }, { 0, 1 }}, + { SDP1, { 1, 1 }, { 0, 1 }}, + { SDP2, { 2, 2 }, { 0, 1 }}, + { SDP3, { 3, 3 }, { 0, 1 }}, + { ONE_PPS, { -1, 5 }, { 0, 1 }}, +}; - /* Read initial pin state */ - status = ice_read_sma_ctrl_e810t(hw, &data); - if (status) - return status; +static const char ice_pin_names_nvm[][64] = { + "GNSS", + "SMA1", + "U.FL1", + "SMA2", + "U.FL2", +}; - /* initialize with defaults */ - for (i = 0; i < NUM_PTP_PINS_E810T; i++) { - 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; - } +static const struct ice_ptp_pin_desc ice_pin_desc_e810_sma[] = { + /* name, gpio, delay */ + { GNSS, { 1, -1 }, { 0, 0 }}, + { SMA1, { 1, 0 }, { 0, 1 }}, + { UFL1, { -1, 0 }, { 0, 1 }}, + { SMA2, { 3, 2 }, { 0, 1 }}, + { UFL2, { 3, -1 }, { 0, 0 }}, +}; - /* Parse SMA1/UFL1 */ - switch (data & ICE_SMA1_MASK_E810T) { - case ICE_SMA1_MASK_E810T: - default: - ptp_pins[SMA1].func = PTP_PF_NONE; - ptp_pins[UFL1].func = PTP_PF_NONE; - break; - case ICE_SMA1_DIR_EN_E810T: - ptp_pins[SMA1].func = PTP_PF_PEROUT; - ptp_pins[UFL1].func = PTP_PF_NONE; - break; - case ICE_SMA1_TX_EN_E810T: - ptp_pins[SMA1].func = PTP_PF_EXTTS; - ptp_pins[UFL1].func = PTP_PF_NONE; - break; - case 0: - ptp_pins[SMA1].func = PTP_PF_EXTTS; - ptp_pins[UFL1].func = PTP_PF_PEROUT; - break; - } +static struct ice_pf *ice_get_ctrl_pf(struct ice_pf *pf) +{ + return !pf->adapter ? NULL : pf->adapter->ctrl_pf; +} - /* Parse SMA2/UFL2 */ - switch (data & ICE_SMA2_MASK_E810T) { - case ICE_SMA2_MASK_E810T: - default: - ptp_pins[SMA2].func = PTP_PF_NONE; - ptp_pins[UFL2].func = PTP_PF_NONE; - break; - case (ICE_SMA2_TX_EN_E810T | ICE_SMA2_UFL2_RX_DIS_E810T): - ptp_pins[SMA2].func = PTP_PF_EXTTS; - ptp_pins[UFL2].func = PTP_PF_NONE; - break; - case (ICE_SMA2_DIR_EN_E810T | ICE_SMA2_UFL2_RX_DIS_E810T): - ptp_pins[SMA2].func = PTP_PF_PEROUT; - ptp_pins[UFL2].func = PTP_PF_NONE; - break; - case (ICE_SMA2_DIR_EN_E810T | ICE_SMA2_TX_EN_E810T): - ptp_pins[SMA2].func = PTP_PF_NONE; - ptp_pins[UFL2].func = PTP_PF_EXTTS; - break; - case ICE_SMA2_DIR_EN_E810T: - ptp_pins[SMA2].func = PTP_PF_PEROUT; - ptp_pins[UFL2].func = PTP_PF_EXTTS; - break; - } +static struct ice_ptp *ice_get_ctrl_ptp(struct ice_pf *pf) +{ + struct ice_pf *ctrl_pf = ice_get_ctrl_pf(pf); - return 0; + return !ctrl_pf ? NULL : &ctrl_pf->ptp; } /** - * ice_ptp_set_sma_config_e810t - * @hw: pointer to the hw struct - * @ptp_pins: pointer to the ptp_pin_desc struture + * ice_ptp_find_pin_idx - Find pin index in ptp_pin_desc + * @pf: Board private structure + * @func: Pin function + * @chan: GPIO channel * - * Set the configuration of the SMA control logic based on the configuration in - * num_pins parameter + * Return: positive pin number when pin is present, -1 otherwise */ -static int -ice_ptp_set_sma_config_e810t(struct ice_hw *hw, - const struct ptp_pin_desc *ptp_pins) +static int ice_ptp_find_pin_idx(struct ice_pf *pf, enum ptp_pin_function func, + unsigned int chan) { - int status; - u8 data; + const struct ptp_clock_info *info = &pf->ptp.info; + int i; - /* SMA1 and UFL1 cannot be set to TX at the same time */ - if (ptp_pins[SMA1].func == PTP_PF_PEROUT && - ptp_pins[UFL1].func == PTP_PF_PEROUT) - return -EINVAL; + for (i = 0; i < info->n_pins; i++) { + if (info->pin_config[i].func == func && + info->pin_config[i].chan == chan) + return i; + } - /* SMA2 and UFL2 cannot be set to RX at the same time */ - if (ptp_pins[SMA2].func == PTP_PF_EXTTS && - ptp_pins[UFL2].func == PTP_PF_EXTTS) - return -EINVAL; + return -1; +} - /* Read initial pin state value */ - status = ice_read_sma_ctrl_e810t(hw, &data); - if (status) - return status; - - /* Set the right sate based on the desired configuration */ - data &= ~ICE_SMA1_MASK_E810T; - if (ptp_pins[SMA1].func == PTP_PF_NONE && - ptp_pins[UFL1].func == PTP_PF_NONE) { - dev_info(ice_hw_to_dev(hw), "SMA1 + U.FL1 disabled"); - data |= ICE_SMA1_MASK_E810T; - } else if (ptp_pins[SMA1].func == PTP_PF_EXTTS && - ptp_pins[UFL1].func == PTP_PF_NONE) { - dev_info(ice_hw_to_dev(hw), "SMA1 RX"); - data |= ICE_SMA1_TX_EN_E810T; - } else if (ptp_pins[SMA1].func == PTP_PF_NONE && - ptp_pins[UFL1].func == PTP_PF_PEROUT) { - /* U.FL 1 TX will always enable SMA 1 RX */ - dev_info(ice_hw_to_dev(hw), "SMA1 RX + U.FL1 TX"); - } else if (ptp_pins[SMA1].func == PTP_PF_EXTTS && - ptp_pins[UFL1].func == PTP_PF_PEROUT) { - dev_info(ice_hw_to_dev(hw), "SMA1 RX + U.FL1 TX"); - } else if (ptp_pins[SMA1].func == PTP_PF_PEROUT && - ptp_pins[UFL1].func == PTP_PF_NONE) { - dev_info(ice_hw_to_dev(hw), "SMA1 TX"); - data |= ICE_SMA1_DIR_EN_E810T; - } - - data &= ~ICE_SMA2_MASK_E810T; - if (ptp_pins[SMA2].func == PTP_PF_NONE && - ptp_pins[UFL2].func == PTP_PF_NONE) { - dev_info(ice_hw_to_dev(hw), "SMA2 + U.FL2 disabled"); - data |= ICE_SMA2_MASK_E810T; - } else if (ptp_pins[SMA2].func == PTP_PF_EXTTS && - ptp_pins[UFL2].func == PTP_PF_NONE) { - dev_info(ice_hw_to_dev(hw), "SMA2 RX"); - data |= (ICE_SMA2_TX_EN_E810T | - ICE_SMA2_UFL2_RX_DIS_E810T); - } else if (ptp_pins[SMA2].func == PTP_PF_NONE && - ptp_pins[UFL2].func == PTP_PF_EXTTS) { - dev_info(ice_hw_to_dev(hw), "UFL2 RX"); - data |= (ICE_SMA2_DIR_EN_E810T | ICE_SMA2_TX_EN_E810T); - } else if (ptp_pins[SMA2].func == PTP_PF_PEROUT && - ptp_pins[UFL2].func == PTP_PF_NONE) { - dev_info(ice_hw_to_dev(hw), "SMA2 TX"); - data |= (ICE_SMA2_DIR_EN_E810T | - ICE_SMA2_UFL2_RX_DIS_E810T); - } else if (ptp_pins[SMA2].func == PTP_PF_PEROUT && - ptp_pins[UFL2].func == PTP_PF_EXTTS) { - dev_info(ice_hw_to_dev(hw), "SMA2 TX + U.FL2 RX"); - data |= ICE_SMA2_DIR_EN_E810T; - } - - return ice_write_sma_ctrl_e810t(hw, data); -} - -/** - * ice_ptp_set_sma_e810t - * @info: the driver's PTP info structure - * @pin: pin index in kernel structure - * @func: Pin function to be set (PTP_PF_NONE, PTP_PF_EXTTS or PTP_PF_PEROUT) - * - * Set the configuration of a single SMA pin +/** + * ice_ptp_update_sma_data - update SMA pins data according to pins setup + * @pf: Board private structure + * @sma_pins: parsed SMA pins status + * @data: SMA data to update */ -static int -ice_ptp_set_sma_e810t(struct ptp_clock_info *info, unsigned int pin, - enum ptp_pin_function func) +static void ice_ptp_update_sma_data(struct ice_pf *pf, unsigned int sma_pins[], + u8 *data) { - struct ptp_pin_desc ptp_pins[NUM_PTP_PINS_E810T]; - struct ice_pf *pf = ptp_info_to_pf(info); - struct ice_hw *hw = &pf->hw; - int err; - - if (pin < SMA1 || func > PTP_PF_PEROUT) - return -EOPNOTSUPP; + const char *state1, *state2; - err = ice_get_sma_config_e810t(hw, ptp_pins); - if (err) - return err; - - /* Disable the same function on the other pin sharing the channel */ - if (pin == SMA1 && ptp_pins[UFL1].func == func) - ptp_pins[UFL1].func = PTP_PF_NONE; - if (pin == UFL1 && ptp_pins[SMA1].func == func) - ptp_pins[SMA1].func = PTP_PF_NONE; - - if (pin == SMA2 && ptp_pins[UFL2].func == func) - ptp_pins[UFL2].func = PTP_PF_NONE; - if (pin == UFL2 && ptp_pins[SMA2].func == func) - ptp_pins[SMA2].func = PTP_PF_NONE; + /* Set the right state based on the desired configuration. + * When bit is set, functionality is disabled. + */ + *data &= ~ICE_ALL_SMA_MASK; + if (!sma_pins[UFL1 - 1]) { + if (sma_pins[SMA1 - 1] == PTP_PF_EXTTS) { + state1 = "SMA1 Rx, U.FL1 disabled"; + *data |= ICE_SMA1_TX_EN; + } else if (sma_pins[SMA1 - 1] == PTP_PF_PEROUT) { + state1 = "SMA1 Tx U.FL1 disabled"; + *data |= ICE_SMA1_DIR_EN; + } else { + state1 = "SMA1 disabled, U.FL1 disabled"; + *data |= ICE_SMA1_MASK; + } + } else { + /* U.FL1 Tx will always enable SMA1 Rx */ + state1 = "SMA1 Rx, U.FL1 Tx"; + } - /* Set up new pin function in the temp table */ - ptp_pins[pin].func = func; + if (!sma_pins[UFL2 - 1]) { + if (sma_pins[SMA2 - 1] == PTP_PF_EXTTS) { + state2 = "SMA2 Rx, U.FL2 disabled"; + *data |= ICE_SMA2_TX_EN | ICE_SMA2_UFL2_RX_DIS; + } else if (sma_pins[SMA2 - 1] == PTP_PF_PEROUT) { + state2 = "SMA2 Tx, U.FL2 disabled"; + *data |= ICE_SMA2_DIR_EN | ICE_SMA2_UFL2_RX_DIS; + } else { + state2 = "SMA2 disabled, U.FL2 disabled"; + *data |= ICE_SMA2_MASK; + } + } else { + if (!sma_pins[SMA2 - 1]) { + state2 = "SMA2 disabled, U.FL2 Rx"; + *data |= ICE_SMA2_DIR_EN | ICE_SMA2_TX_EN; + } else { + state2 = "SMA2 Tx, U.FL2 Rx"; + *data |= ICE_SMA2_DIR_EN; + } + } - return ice_ptp_set_sma_config_e810t(hw, ptp_pins); + dev_dbg(ice_pf_to_dev(pf), "%s, %s\n", state1, state2); } /** - * ice_verify_pin_e810t - * @info: the driver's PTP info structure - * @pin: Pin index - * @func: Assigned function - * @chan: Assigned channel + * ice_ptp_set_sma_cfg - set the configuration of the SMA control logic + * @pf: Board private structure * - * Verify if pin supports requested pin function. If the Check pins consistency. - * Reconfigure the SMA logic attached to the given pin to enable its - * desired functionality + * Return: 0 on success, negative error code otherwise */ -static int -ice_verify_pin_e810t(struct ptp_clock_info *info, unsigned int pin, - enum ptp_pin_function func, unsigned int chan) +static int ice_ptp_set_sma_cfg(struct ice_pf *pf) { - /* Don't allow channel reassignment */ - if (chan != ice_pin_desc_e810t[pin].chan) - return -EOPNOTSUPP; + const struct ice_ptp_pin_desc *ice_pins = pf->ptp.ice_pin_desc; + struct ptp_pin_desc *pins = pf->ptp.pin_desc; + unsigned int sma_pins[ICE_SMA_PINS_NUM] = {}; + int err; + u8 data; - /* Check if functions are properly assigned */ - switch (func) { - case PTP_PF_NONE: - break; - case PTP_PF_EXTTS: - if (pin == UFL1) - return -EOPNOTSUPP; - break; - case PTP_PF_PEROUT: - if (pin == UFL2 || pin == GNSS) - return -EOPNOTSUPP; - break; - case PTP_PF_PHYSYNC: - return -EOPNOTSUPP; - } + /* Read initial pin state value */ + err = ice_read_sma_ctrl(&pf->hw, &data); + if (err) + return err; - return ice_ptp_set_sma_e810t(info, pin, func); + /* Get SMA/U.FL pins states */ + for (int i = 0; i < pf->ptp.info.n_pins; i++) + if (pins[i].func) { + int name_idx = ice_pins[i].name_idx; + + switch (name_idx) { + case SMA1: + case UFL1: + case SMA2: + case UFL2: + sma_pins[name_idx - 1] = pins[i].func; + break; + default: + continue; + } + } + + ice_ptp_update_sma_data(pf, sma_pins, &data); + return ice_write_sma_ctrl(&pf->hw, data); } /** @@ -366,17 +298,30 @@ void ice_ptp_restore_timestamp_mode(struct ice_pf *pf) * @sts: Optional parameter for holding a pair of system timestamps from * the system clock. Will be ignored if NULL is given. */ -static u64 -ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts) +u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf, + struct ptp_system_timestamp *sts) { struct ice_hw *hw = &pf->hw; u32 hi, lo, lo2; u8 tmr_idx; + if (!ice_is_primary(hw)) + hw = ice_get_primary_hw(pf); + tmr_idx = ice_get_ptp_src_clock_index(hw); + guard(spinlock)(&pf->adapter->ptp_gltsyn_time_lock); /* Read the system timestamp pre PHC read */ ptp_read_system_prets(sts); + if (hw->mac_type == ICE_MAC_E830) { + u64 clk_time = rd64(hw, E830_GLTSYN_TIME_L(tmr_idx)); + + /* Read the system timestamp post PHC read */ + ptp_read_system_postts(sts); + + return clk_time; + } + lo = rd32(hw, GLTSYN_TIME_L(tmr_idx)); /* Read the system timestamp post PHC read */ @@ -531,7 +476,9 @@ ice_ptp_is_tx_tracker_up(struct ice_ptp_tx *tx) */ void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx) { + struct ice_e810_params *params; struct ice_ptp_port *ptp_port; + unsigned long flags; struct sk_buff *skb; struct ice_pf *pf; @@ -540,6 +487,7 @@ void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx) ptp_port = container_of(tx, struct ice_ptp_port, tx); pf = ptp_port_to_pf(ptp_port); + params = &pf->hw.ptp.phy.e810; /* Drop packets which have waited for more than 2 seconds */ if (time_is_before_jiffies(tx->tstamps[idx].start + 2 * HZ)) { @@ -556,11 +504,17 @@ void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx) ice_trace(tx_tstamp_fw_req, tx->tstamps[idx].skb, idx); + spin_lock_irqsave(¶ms->atqbal_wq.lock, flags); + + params->atqbal_flags |= ATQBAL_FLAGS_INTR_IN_PROGRESS; + /* Write TS index to read to the PF register so the FW can read it */ - wr32(&pf->hw, PF_SB_ATQBAL, - TS_LL_READ_TS_INTR | FIELD_PREP(TS_LL_READ_TS_IDX, idx) | - TS_LL_READ_TS); + wr32(&pf->hw, REG_LL_PROXY_H, + REG_LL_PROXY_H_TS_INTR_ENA | FIELD_PREP(REG_LL_PROXY_H_TS_IDX, idx) | + REG_LL_PROXY_H_EXEC); tx->last_ll_ts_idx_read = idx; + + spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); } /** @@ -571,35 +525,52 @@ void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx) { struct skb_shared_hwtstamps shhwtstamps = {}; u8 idx = tx->last_ll_ts_idx_read; + struct ice_e810_params *params; struct ice_ptp_port *ptp_port; u64 raw_tstamp, tstamp; bool drop_ts = false; struct sk_buff *skb; + unsigned long flags; + struct device *dev; struct ice_pf *pf; - u32 val; + u32 reg_ll_high; if (!tx->init || tx->last_ll_ts_idx_read < 0) return; ptp_port = container_of(tx, struct ice_ptp_port, tx); pf = ptp_port_to_pf(ptp_port); + dev = ice_pf_to_dev(pf); + params = &pf->hw.ptp.phy.e810; ice_trace(tx_tstamp_fw_done, tx->tstamps[idx].skb, idx); - val = rd32(&pf->hw, PF_SB_ATQBAL); + spin_lock_irqsave(¶ms->atqbal_wq.lock, flags); + + if (!(params->atqbal_flags & ATQBAL_FLAGS_INTR_IN_PROGRESS)) + dev_dbg(dev, "%s: low latency interrupt request not in progress?\n", + __func__); + + /* Read the low 32 bit value */ + raw_tstamp = rd32(&pf->hw, REG_LL_PROXY_L); + /* Read the status together with high TS part */ + reg_ll_high = rd32(&pf->hw, REG_LL_PROXY_H); + + /* Wake up threads waiting on low latency interface */ + params->atqbal_flags &= ~ATQBAL_FLAGS_INTR_IN_PROGRESS; + + wake_up_locked(¶ms->atqbal_wq); + + spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); /* When the bit is cleared, the TS is ready in the register */ - if (val & TS_LL_READ_TS) { + if (reg_ll_high & REG_LL_PROXY_H_EXEC) { dev_err(ice_pf_to_dev(pf), "Failed to get the Tx tstamp - FW not ready"); return; } /* High 8 bit value of the TS is on the bits 16:23 */ - raw_tstamp = FIELD_GET(TS_LL_READ_TS_HIGH, val); - raw_tstamp <<= 32; - - /* Read the low 32 bit value */ - raw_tstamp |= (u64)rd32(&pf->hw, PF_SB_ATQBAH); + raw_tstamp |= ((u64)FIELD_GET(REG_LL_PROXY_H_TS_HIGH, reg_ll_high)) << 32; /* Devices using this interface always verify the timestamp differs * relative to the last cached timestamp value. @@ -801,8 +772,8 @@ 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) { + mutex_lock(&pf->adapter->ports.lock); + list_for_each_entry(port, &pf->adapter->ports.ports, list_node) { struct ice_ptp_tx *tx = &port->tx; if (!tx || !tx->init) @@ -810,9 +781,9 @@ static enum ice_tx_tstamp_work ice_ptp_tx_tstamp_owner(struct ice_pf *pf) ice_ptp_process_tx_tstamp(tx); } - mutex_unlock(&pf->ptp.ports_owner.lock); + mutex_unlock(&pf->adapter->ports.lock); - for (i = 0; i < ICE_MAX_QUAD; i++) { + for (i = 0; i < ICE_GET_QUAD_NUM(pf->hw.ptp.num_lports); i++) { u64 tstamp_ready; int err; @@ -975,7 +946,7 @@ ice_ptp_flush_all_tx_tracker(struct ice_pf *pf) { struct ice_ptp_port *port; - list_for_each_entry(port, &pf->ptp.ports_owner.ports, list_member) + list_for_each_entry(port, &pf->adapter->ports.ports, list_node) ice_ptp_flush_tx_tracker(ptp_port_to_pf(port), &port->tx); } @@ -1022,11 +993,13 @@ ice_ptp_release_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx) * the timestamp block is shared for all ports in the same quad. To avoid * ports using the same timestamp index, logically break the block of * registers into chunks based on the port number. + * + * Return: 0 on success, -ENOMEM when out of memory */ -static int -ice_ptp_init_tx_e82x(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port) +static int ice_ptp_init_tx_e82x(struct ice_pf *pf, struct ice_ptp_tx *tx, + u8 port) { - tx->block = port / ICE_PORTS_PER_QUAD; + tx->block = ICE_GET_QUAD_NUM(port); tx->offset = (port % ICE_PORTS_PER_QUAD) * INDEX_PER_PORT_E82X; tx->len = INDEX_PER_PORT_E82X; tx->has_ready_bitmap = 1; @@ -1035,24 +1008,27 @@ ice_ptp_init_tx_e82x(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port) } /** - * ice_ptp_init_tx_e810 - Initialize tracking for Tx timestamps + * ice_ptp_init_tx - Initialize tracking for Tx timestamps * @pf: Board private structure * @tx: the Tx tracking structure to initialize + * @port: the port this structure tracks * - * Initialize the Tx timestamp tracker for this PF. For E810 devices, each - * port has its own block of timestamps, independent of the other ports. + * Initialize the Tx timestamp tracker for this PF. For all PHYs except E82X, + * each port has its own block of timestamps, independent of the other ports. + * + * Return: 0 on success, -ENOMEM when out of memory */ -static int -ice_ptp_init_tx_e810(struct ice_pf *pf, struct ice_ptp_tx *tx) +static int ice_ptp_init_tx(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port) { - tx->block = pf->hw.port_info->lport; + tx->block = port; tx->offset = 0; - tx->len = INDEX_PER_PORT_E810; + tx->len = INDEX_PER_PORT; + /* The E810 PHY does not provide a timestamp ready bitmap. Instead, * verify new timestamps against cached copy of the last read * timestamp. */ - tx->has_ready_bitmap = 0; + tx->has_ready_bitmap = pf->hw.mac_type != ICE_MAC_E810; return ice_ptp_alloc_tx_tracker(tx); } @@ -1166,26 +1142,6 @@ static void ice_ptp_reset_cached_phctime(struct ice_pf *pf) } /** - * ice_ptp_read_time - Read the time from the device - * @pf: Board private structure - * @ts: timespec structure to hold the current time value - * @sts: Optional parameter for holding a pair of system timestamps from - * the system clock. Will be ignored if NULL is given. - * - * This function reads the source clock registers and stores them in a timespec. - * However, since the registers are 64 bits of nanoseconds, we must convert the - * result to a timespec before we can return. - */ -static void -ice_ptp_read_time(struct ice_pf *pf, struct timespec64 *ts, - struct ptp_system_timestamp *sts) -{ - u64 time_ns = ice_ptp_read_src_clk_reg(pf, sts); - - *ts = ns_to_timespec64(time_ns); -} - -/** * ice_ptp_write_init - Set PHC time to provided value * @pf: Board private structure * @ts: timespec structure that holds the new time value @@ -1229,12 +1185,7 @@ static u64 ice_base_incval(struct ice_pf *pf) struct ice_hw *hw = &pf->hw; u64 incval; - if (ice_is_e810(hw)) - incval = ICE_PTP_NOMINAL_INCVAL_E810; - else if (ice_e82x_time_ref(hw) < NUM_ICE_TIME_REF_FREQ) - incval = ice_e82x_nominal_incval(ice_e82x_time_ref(hw)); - else - incval = UNKNOWN_INCVAL_E82X; + incval = ice_get_base_incval(hw); dev_dbg(ice_pf_to_dev(pf), "PTP: using base increment value of 0x%016llx\n", incval); @@ -1248,8 +1199,8 @@ static u64 ice_base_incval(struct ice_pf *pf) */ static int ice_ptp_check_tx_fifo(struct ice_ptp_port *port) { - int quad = port->port_num / ICE_PORTS_PER_QUAD; int offs = port->port_num % ICE_PORTS_PER_QUAD; + int quad = ICE_GET_QUAD_NUM(port->port_num); struct ice_pf *pf; struct ice_hw *hw; u32 val, phy_sts; @@ -1362,15 +1313,25 @@ ice_ptp_port_phy_stop(struct ice_ptp_port *ptp_port) struct ice_hw *hw = &pf->hw; int err; - if (ice_is_e810(hw)) - return 0; - mutex_lock(&ptp_port->ps_lock); - kthread_cancel_delayed_work_sync(&ptp_port->ov_work); + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: + err = 0; + break; + case ICE_MAC_GENERIC: + kthread_cancel_delayed_work_sync(&ptp_port->ov_work); - err = ice_stop_phy_timer_e82x(hw, port, true); - if (err) + err = ice_stop_phy_timer_e82x(hw, port, true); + break; + case ICE_MAC_GENERIC_3K_E825: + err = ice_stop_phy_timer_eth56g(hw, port, true); + break; + default: + err = -ENODEV; + } + if (err && err != -EBUSY) dev_err(ice_pf_to_dev(pf), "PTP failed to set PHY port %d down, err %d\n", port, err); @@ -1396,35 +1357,48 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port) unsigned long flags; int err; - if (ice_is_e810(hw)) - return 0; - if (!ptp_port->link_up) return ice_ptp_port_phy_stop(ptp_port); mutex_lock(&ptp_port->ps_lock); - kthread_cancel_delayed_work_sync(&ptp_port->ov_work); + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: + err = 0; + break; + case ICE_MAC_GENERIC: + /* Start the PHY timer in Vernier mode */ + kthread_cancel_delayed_work_sync(&ptp_port->ov_work); - /* temporarily disable Tx timestamps while calibrating PHY offset */ - spin_lock_irqsave(&ptp_port->tx.lock, flags); - ptp_port->tx.calibrating = true; - spin_unlock_irqrestore(&ptp_port->tx.lock, flags); - ptp_port->tx_fifo_busy_cnt = 0; + /* temporarily disable Tx timestamps while calibrating + * PHY offset + */ + spin_lock_irqsave(&ptp_port->tx.lock, flags); + ptp_port->tx.calibrating = true; + spin_unlock_irqrestore(&ptp_port->tx.lock, flags); + ptp_port->tx_fifo_busy_cnt = 0; - /* Start the PHY timer in Vernier mode */ - err = ice_start_phy_timer_e82x(hw, port); - if (err) - goto out_unlock; + /* Start the PHY timer in Vernier mode */ + err = ice_start_phy_timer_e82x(hw, port); + if (err) + break; - /* Enable Tx timestamps right away */ - spin_lock_irqsave(&ptp_port->tx.lock, flags); - ptp_port->tx.calibrating = false; - spin_unlock_irqrestore(&ptp_port->tx.lock, flags); + /* Enable Tx timestamps right away */ + spin_lock_irqsave(&ptp_port->tx.lock, flags); + ptp_port->tx.calibrating = false; + spin_unlock_irqrestore(&ptp_port->tx.lock, flags); - kthread_queue_delayed_work(pf->ptp.kworker, &ptp_port->ov_work, 0); + kthread_queue_delayed_work(pf->ptp.kworker, &ptp_port->ov_work, + 0); + break; + case ICE_MAC_GENERIC_3K_E825: + err = ice_start_phy_timer_eth56g(hw, port); + break; + default: + err = -ENODEV; + } -out_unlock: if (err) dev_err(ice_pf_to_dev(pf), "PTP failed to set PHY port %d up, err %d\n", port, err); @@ -1437,10 +1411,9 @@ out_unlock: /** * ice_ptp_link_change - Reconfigure PTP after link status change * @pf: Board private structure - * @port: Port for which the PHY start is set * @linkup: Link is up or down */ -void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) +void ice_ptp_link_change(struct ice_pf *pf, bool linkup) { struct ice_ptp_port *ptp_port; struct ice_hw *hw = &pf->hw; @@ -1448,21 +1421,22 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) if (pf->ptp.state != ICE_PTP_READY) return; - if (WARN_ON_ONCE(port >= ICE_NUM_EXTERNAL_PORTS)) - return; - ptp_port = &pf->ptp.port; - if (WARN_ON_ONCE(ptp_port->port_num != port)) - return; /* Update cached link status for this port immediately */ ptp_port->link_up = linkup; - switch (hw->phy_model) { - case ICE_PHY_E810: - /* Do not reconfigure E810 PHY */ + /* Skip HW writes if reset is in progress */ + if (pf->hw.reset_ongoing) + return; + + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: + /* Do not reconfigure E810 or E830 PHY */ return; - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: + case ICE_MAC_GENERIC_3K_E825: ice_ptp_port_phy_restart(ptp_port); return; default: @@ -1476,42 +1450,61 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) * @ena: bool value to enable or disable interrupt * @threshold: Minimum number of packets at which intr is triggered * - * Utility function to enable or disable Tx timestamp interrupt and threshold + * Utility function to configure all the PHY interrupt settings, including + * whether the PHY interrupt is enabled, and what threshold to use. Also + * configures The E82X timestamp owner to react to interrupts from all PHYs. + * + * Return: 0 on success, -EOPNOTSUPP when PHY model incorrect, other error codes + * when failed to configure PHY interrupt for E82X */ static int ice_ptp_cfg_phy_interrupt(struct ice_pf *pf, bool ena, u32 threshold) { + struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; - int err = 0; - int quad; - u32 val; ice_ptp_reset_ts_memory(hw); - for (quad = 0; quad < ICE_MAX_QUAD; quad++) { - err = ice_read_quad_reg_e82x(hw, quad, Q_REG_TX_MEM_GBL_CFG, - &val); - if (err) - break; - - if (ena) { - val |= Q_REG_TX_MEM_GBL_CFG_INTR_ENA_M; - val &= ~Q_REG_TX_MEM_GBL_CFG_INTR_THR_M; - val |= FIELD_PREP(Q_REG_TX_MEM_GBL_CFG_INTR_THR_M, - threshold); - } else { - val &= ~Q_REG_TX_MEM_GBL_CFG_INTR_ENA_M; + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: + return 0; + case ICE_MAC_GENERIC: { + int quad; + + for (quad = 0; quad < ICE_GET_QUAD_NUM(hw->ptp.num_lports); + quad++) { + int err; + + err = ice_phy_cfg_intr_e82x(hw, quad, ena, threshold); + if (err) { + dev_err(dev, "Failed to configure PHY interrupt for quad %d, err %d\n", + quad, err); + return err; + } } - err = ice_write_quad_reg_e82x(hw, quad, Q_REG_TX_MEM_GBL_CFG, - val); - if (err) - break; + return 0; } + case ICE_MAC_GENERIC_3K_E825: { + int port; - if (err) - dev_err(ice_pf_to_dev(pf), "PTP failed in intr ena, err %d\n", - err); - return err; + for (port = 0; port < hw->ptp.num_lports; port++) { + int err; + + err = ice_phy_cfg_intr_eth56g(hw, port, ena, threshold); + if (err) { + dev_err(dev, "Failed to configure PHY interrupt for port %d, err %d\n", + port, err); + return err; + } + } + + return 0; + } + case ICE_MAC_UNKNOWN: + default: + return -EOPNOTSUPP; + } } /** @@ -1531,10 +1524,10 @@ static void ice_ptp_restart_all_phy(struct ice_pf *pf) { struct list_head *entry; - list_for_each(entry, &pf->ptp.ports_owner.ports) { + list_for_each(entry, &pf->adapter->ports.ports) { struct ice_ptp_port *port = list_entry(entry, struct ice_ptp_port, - list_member); + list_node); if (port->link_up) ice_ptp_port_phy_restart(port); @@ -1578,6 +1571,10 @@ void ice_ptp_extts_event(struct ice_pf *pf) u8 chan, tmr_idx; u32 hi, lo; + /* Don't process timestamp events if PTP is not ready */ + if (pf->ptp.state != ICE_PTP_READY) + return; + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; /* Event time is captured by one of the two matched registers * GLTSYN_EVNT_L: 32 LSB of sampled time event @@ -1585,45 +1582,62 @@ void ice_ptp_extts_event(struct ice_pf *pf) * Event is defined in GLTSYN_EVNT_0 register */ for (chan = 0; chan < GLTSYN_EVNT_H_IDX_MAX; chan++) { + int pin_desc_idx; + /* Check if channel is enabled */ - if (pf->ptp.ext_ts_irq & (1 << chan)) { - lo = rd32(hw, GLTSYN_EVNT_L(chan, tmr_idx)); - hi = rd32(hw, GLTSYN_EVNT_H(chan, tmr_idx)); - event.timestamp = (((u64)hi) << 32) | lo; - event.type = PTP_CLOCK_EXTTS; - event.index = chan; - - /* Fire event */ - ptp_clock_event(pf->ptp.clock, &event); - pf->ptp.ext_ts_irq &= ~(1 << chan); + if (!(pf->ptp.ext_ts_irq & (1 << chan))) + continue; + + lo = rd32(hw, GLTSYN_EVNT_L(chan, tmr_idx)); + hi = rd32(hw, GLTSYN_EVNT_H(chan, tmr_idx)); + event.timestamp = (u64)hi << 32 | lo; + + /* Add delay compensation */ + pin_desc_idx = ice_ptp_find_pin_idx(pf, PTP_PF_EXTTS, chan); + if (pin_desc_idx >= 0) { + const struct ice_ptp_pin_desc *desc; + + desc = &pf->ptp.ice_pin_desc[pin_desc_idx]; + event.timestamp -= desc->delay[0]; } + + event.type = PTP_CLOCK_EXTTS; + event.index = chan; + pf->ptp.ext_ts_irq &= ~(1 << chan); + ptp_clock_event(pf->ptp.clock, &event); } } /** * ice_ptp_cfg_extts - Configure EXTTS pin and channel * @pf: Board private structure - * @ena: true to enable; false to disable - * @chan: GPIO channel (0-3) - * @gpio_pin: GPIO pin - * @extts_flags: request flags from the ptp_extts_request.flags + * @rq: External timestamp request + * @on: Enable/disable flag + * + * Configure an external timestamp event on the requested channel. + * + * Return: 0 on success, negative error code otherwise */ -static int -ice_ptp_cfg_extts(struct ice_pf *pf, bool ena, unsigned int chan, u32 gpio_pin, - unsigned int extts_flags) +static int ice_ptp_cfg_extts(struct ice_pf *pf, struct ptp_extts_request *rq, + int on) { - u32 func, aux_reg, gpio_reg, irq_reg; + u32 aux_reg, gpio_reg, irq_reg; struct ice_hw *hw = &pf->hw; + unsigned int chan, gpio_pin; + int pin_desc_idx; u8 tmr_idx; - if (chan > (unsigned int)pf->ptp.info.n_ext_ts) - return -EINVAL; - tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + chan = rq->index; + + pin_desc_idx = ice_ptp_find_pin_idx(pf, PTP_PF_EXTTS, chan); + if (pin_desc_idx < 0) + return -EIO; + gpio_pin = pf->ptp.ice_pin_desc[pin_desc_idx].gpio[0]; irq_reg = rd32(hw, PFINT_OICR_ENA); - if (ena) { + if (on) { /* Enable the interrupt */ irq_reg |= PFINT_OICR_TSYN_EVNT_M; aux_reg = GLTSYN_AUX_IN_0_INT_ENA_M; @@ -1632,24 +1646,32 @@ ice_ptp_cfg_extts(struct ice_pf *pf, bool ena, unsigned int chan, u32 gpio_pin, #define GLTSYN_AUX_IN_0_EVNTLVL_FALLING_EDGE BIT(1) /* set event level to requested edge */ - if (extts_flags & PTP_FALLING_EDGE) + if (rq->flags & PTP_FALLING_EDGE) aux_reg |= GLTSYN_AUX_IN_0_EVNTLVL_FALLING_EDGE; - if (extts_flags & PTP_RISING_EDGE) + if (rq->flags & PTP_RISING_EDGE) aux_reg |= GLTSYN_AUX_IN_0_EVNTLVL_RISING_EDGE; /* Write GPIO CTL reg. * 0x1 is input sampled by EVENT register(channel) * + num_in_channels * tmr_idx */ - func = 1 + chan + (tmr_idx * 3); - gpio_reg = FIELD_PREP(GLGEN_GPIO_CTL_PIN_FUNC_M, func); - pf->ptp.ext_ts_chan |= (1 << chan); + gpio_reg = FIELD_PREP(GLGEN_GPIO_CTL_PIN_FUNC_M, + 1 + chan + (tmr_idx * 3)); } else { + bool last_enabled = true; + /* clear the values we set to reset defaults */ aux_reg = 0; gpio_reg = 0; - pf->ptp.ext_ts_chan &= ~(1 << chan); - if (!pf->ptp.ext_ts_chan) + + for (unsigned int i = 0; i < pf->ptp.info.n_ext_ts; i++) + if ((pf->ptp.extts_rqs[i].flags & + PTP_ENABLE_FEATURE) && + i != chan) { + last_enabled = false; + } + + if (last_enabled) irq_reg &= ~PFINT_OICR_TSYN_EVNT_M; } @@ -1661,253 +1683,347 @@ ice_ptp_cfg_extts(struct ice_pf *pf, bool ena, unsigned int chan, u32 gpio_pin, } /** - * ice_ptp_cfg_clkout - Configure clock to generate periodic wave + * ice_ptp_disable_all_extts - Disable all EXTTS channels * @pf: Board private structure - * @chan: GPIO channel (0-3) - * @config: desired periodic clk configuration. NULL will disable channel - * @store: If set to true the values will be stored - * - * Configure the internal clock generator modules to generate the clock wave of - * specified period. */ -static int ice_ptp_cfg_clkout(struct ice_pf *pf, unsigned int chan, - struct ice_perout_channel *config, bool store) +static void ice_ptp_disable_all_extts(struct ice_pf *pf) { - u64 current_time, period, start_time, phase; - struct ice_hw *hw = &pf->hw; - u32 func, val, gpio_pin; - u8 tmr_idx; + for (unsigned int i = 0; i < pf->ptp.info.n_ext_ts ; i++) + if (pf->ptp.extts_rqs[i].flags & PTP_ENABLE_FEATURE) + ice_ptp_cfg_extts(pf, &pf->ptp.extts_rqs[i], + false); - tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + synchronize_irq(pf->oicr_irq.virq); +} - /* 0. Reset mode & out_en in AUX_OUT */ - wr32(hw, GLTSYN_AUX_OUT(chan, tmr_idx), 0); +/** + * ice_ptp_enable_all_extts - Enable all EXTTS channels + * @pf: Board private structure + * + * Called during reset to restore user configuration. + */ +static void ice_ptp_enable_all_extts(struct ice_pf *pf) +{ + for (unsigned int i = 0; i < pf->ptp.info.n_ext_ts ; i++) + if (pf->ptp.extts_rqs[i].flags & PTP_ENABLE_FEATURE) + ice_ptp_cfg_extts(pf, &pf->ptp.extts_rqs[i], + true); +} - /* If we're disabling the output, clear out CLKO and TGT and keep - * output level low - */ - if (!config || !config->ena) { - wr32(hw, GLTSYN_CLKO(chan, tmr_idx), 0); - wr32(hw, GLTSYN_TGT_L(chan, tmr_idx), 0); - wr32(hw, GLTSYN_TGT_H(chan, tmr_idx), 0); +/** + * ice_ptp_write_perout - Write periodic wave parameters to HW + * @hw: pointer to the HW struct + * @chan: target channel + * @gpio_pin: target GPIO pin + * @start: target time to start periodic output + * @period: target period + * + * Return: 0 on success, negative error code otherwise + */ +static int ice_ptp_write_perout(struct ice_hw *hw, unsigned int chan, + unsigned int gpio_pin, u64 start, u64 period) +{ - val = GLGEN_GPIO_CTL_PIN_DIR_M; - gpio_pin = pf->ptp.perout_channels[chan].gpio_pin; - wr32(hw, GLGEN_GPIO_CTL(gpio_pin), val); + u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + u32 val = 0; - /* Store the value if requested */ - if (store) - memset(&pf->ptp.perout_channels[chan], 0, - sizeof(struct ice_perout_channel)); + /* 0. Reset mode & out_en in AUX_OUT */ + wr32(hw, GLTSYN_AUX_OUT(chan, tmr_idx), 0); - return 0; - } - period = config->period; - start_time = config->start_time; - div64_u64_rem(start_time, period, &phase); - gpio_pin = config->gpio_pin; + if (hw->mac_type == ICE_MAC_GENERIC_3K_E825) { + int err; - /* 1. Write clkout with half of required period value */ - if (period & 0x1) { - dev_err(ice_pf_to_dev(pf), "CLK Period must be an even value\n"); - goto err; + /* Enable/disable CGU 1PPS output for E825C */ + err = ice_cgu_cfg_pps_out(hw, !!period); + if (err) + return err; } + /* 1. Write perout with half of required period value. + * HW toggles output when source clock hits the TGT and then adds + * GLTSYN_CLKO value to the target, so it ends up with 50% duty cycle. + */ period >>= 1; - /* For proper operation, the GLTSYN_CLKO must be larger than clock tick + /* For proper operation, GLTSYN_CLKO must be larger than clock tick and + * period has to fit in 32 bit register. */ #define MIN_PULSE 3 - if (period <= MIN_PULSE || period > U32_MAX) { - dev_err(ice_pf_to_dev(pf), "CLK Period must be > %d && < 2^33", - MIN_PULSE * 2); - goto err; + if (!!period && (period <= MIN_PULSE || period > U32_MAX)) { + dev_err(ice_hw_to_dev(hw), "CLK period ticks must be >= %d && <= 2^32", + MIN_PULSE); + return -EIO; } wr32(hw, GLTSYN_CLKO(chan, tmr_idx), lower_32_bits(period)); - /* Allow time for programming before start_time is hit */ - current_time = ice_ptp_read_src_clk_reg(pf, NULL); - - /* if start time is in the past start the timer at the nearest second - * maintaining phase - */ - if (start_time < current_time) - start_time = div64_u64(current_time + NSEC_PER_SEC - 1, - NSEC_PER_SEC) * NSEC_PER_SEC + phase; - - if (ice_is_e810(hw)) - start_time -= E810_OUT_PROP_DELAY_NS; - else - start_time -= ice_e82x_pps_delay(ice_e82x_time_ref(hw)); - /* 2. Write TARGET time */ - wr32(hw, GLTSYN_TGT_L(chan, tmr_idx), lower_32_bits(start_time)); - wr32(hw, GLTSYN_TGT_H(chan, tmr_idx), upper_32_bits(start_time)); + wr32(hw, GLTSYN_TGT_L(chan, tmr_idx), lower_32_bits(start)); + wr32(hw, GLTSYN_TGT_H(chan, tmr_idx), upper_32_bits(start)); /* 3. Write AUX_OUT register */ - val = GLTSYN_AUX_OUT_0_OUT_ENA_M | GLTSYN_AUX_OUT_0_OUTMOD_M; + if (!!period) + val = GLTSYN_AUX_OUT_0_OUT_ENA_M | GLTSYN_AUX_OUT_0_OUTMOD_M; wr32(hw, GLTSYN_AUX_OUT(chan, tmr_idx), val); /* 4. write GPIO CTL reg */ - func = 8 + chan + (tmr_idx * 4); - val = GLGEN_GPIO_CTL_PIN_DIR_M | - FIELD_PREP(GLGEN_GPIO_CTL_PIN_FUNC_M, func); + val = GLGEN_GPIO_CTL_PIN_DIR_M; + if (!!period) + val |= FIELD_PREP(GLGEN_GPIO_CTL_PIN_FUNC_M, + 8 + chan + (tmr_idx * 4)); + wr32(hw, GLGEN_GPIO_CTL(gpio_pin), val); + ice_flush(hw); + + return 0; +} + +/** + * ice_ptp_cfg_perout - Configure clock to generate periodic wave + * @pf: Board private structure + * @rq: Periodic output request + * @on: Enable/disable flag + * + * Configure the internal clock generator modules to generate the clock wave of + * specified period. + * + * Return: 0 on success, negative error code otherwise + */ +static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq, + int on) +{ + unsigned int gpio_pin, prop_delay_ns; + u64 clk, period, start, phase; + struct ice_hw *hw = &pf->hw; + int pin_desc_idx; + + pin_desc_idx = ice_ptp_find_pin_idx(pf, PTP_PF_PEROUT, rq->index); + if (pin_desc_idx < 0) + return -EIO; + + gpio_pin = pf->ptp.ice_pin_desc[pin_desc_idx].gpio[1]; + prop_delay_ns = pf->ptp.ice_pin_desc[pin_desc_idx].delay[1]; + period = rq->period.sec * NSEC_PER_SEC + rq->period.nsec; + + /* If we're disabling the output or period is 0, clear out CLKO and TGT + * and keep output level low. + */ + if (!on || !period) + return ice_ptp_write_perout(hw, rq->index, gpio_pin, 0, 0); + + if (strncmp(pf->ptp.pin_desc[pin_desc_idx].name, "1PPS", 64) == 0 && + period != NSEC_PER_SEC && hw->mac_type == ICE_MAC_GENERIC) { + dev_err(ice_pf_to_dev(pf), "1PPS pin supports only 1 s period\n"); + return -EOPNOTSUPP; + } - /* Store the value if requested */ - if (store) { - memcpy(&pf->ptp.perout_channels[chan], config, - sizeof(struct ice_perout_channel)); - pf->ptp.perout_channels[chan].start_time = phase; + if (period & 0x1) { + dev_err(ice_pf_to_dev(pf), "CLK Period must be an even value\n"); + return -EIO; } - return 0; -err: - dev_err(ice_pf_to_dev(pf), "PTP failed to cfg per_clk\n"); - return -EFAULT; + start = rq->start.sec * NSEC_PER_SEC + rq->start.nsec; + + /* If PTP_PEROUT_PHASE is set, rq has phase instead of start time */ + if (rq->flags & PTP_PEROUT_PHASE) + phase = start; + else + div64_u64_rem(start, period, &phase); + + /* If we have only phase or start time is in the past, start the timer + * at the next multiple of period, maintaining phase at least 0.5 second + * from now, so we have time to write it to HW. + */ + clk = ice_ptp_read_src_clk_reg(pf, NULL) + NSEC_PER_MSEC * 500; + if (rq->flags & PTP_PEROUT_PHASE || start <= clk - prop_delay_ns) + start = div64_u64(clk + period - 1, period) * period + phase; + + /* Compensate for propagation delay from the generator to the pin. */ + start -= prop_delay_ns; + + return ice_ptp_write_perout(hw, rq->index, gpio_pin, start, period); } /** - * ice_ptp_disable_all_clkout - Disable all currently configured outputs - * @pf: pointer to the PF structure + * ice_ptp_disable_all_perout - Disable all currently configured outputs + * @pf: Board private structure * * Disable all currently configured clock outputs. This is necessary before - * certain changes to the PTP hardware clock. Use ice_ptp_enable_all_clkout to + * certain changes to the PTP hardware clock. Use ice_ptp_enable_all_perout to * re-enable the clocks again. */ -static void ice_ptp_disable_all_clkout(struct ice_pf *pf) +static void ice_ptp_disable_all_perout(struct ice_pf *pf) { - uint i; - - for (i = 0; i < pf->ptp.info.n_per_out; i++) - if (pf->ptp.perout_channels[i].ena) - ice_ptp_cfg_clkout(pf, i, NULL, false); + for (unsigned int i = 0; i < pf->ptp.info.n_per_out; i++) + if (pf->ptp.perout_rqs[i].period.sec || + pf->ptp.perout_rqs[i].period.nsec) + ice_ptp_cfg_perout(pf, &pf->ptp.perout_rqs[i], + false); } /** - * ice_ptp_enable_all_clkout - Enable all configured periodic clock outputs - * @pf: pointer to the PF structure + * ice_ptp_enable_all_perout - Enable all configured periodic clock outputs + * @pf: Board private structure * * Enable all currently configured clock outputs. Use this after - * ice_ptp_disable_all_clkout to reconfigure the output signals according to + * ice_ptp_disable_all_perout to reconfigure the output signals according to * their configuration. */ -static void ice_ptp_enable_all_clkout(struct ice_pf *pf) +static void ice_ptp_enable_all_perout(struct ice_pf *pf) { - uint i; - - for (i = 0; i < pf->ptp.info.n_per_out; i++) - if (pf->ptp.perout_channels[i].ena) - ice_ptp_cfg_clkout(pf, i, &pf->ptp.perout_channels[i], - false); + for (unsigned int i = 0; i < pf->ptp.info.n_per_out; i++) + if (pf->ptp.perout_rqs[i].period.sec || + pf->ptp.perout_rqs[i].period.nsec) + ice_ptp_cfg_perout(pf, &pf->ptp.perout_rqs[i], + true); } /** - * ice_ptp_gpio_enable_e810 - Enable/disable ancillary features of PHC - * @info: the driver's PTP info structure - * @rq: The requested feature to change - * @on: Enable/disable flag + * ice_ptp_disable_shared_pin - Disable enabled pin that shares GPIO + * @pf: Board private structure + * @pin: Pin index + * @func: Assigned function + * + * Return: 0 on success, negative error code otherwise */ -static int -ice_ptp_gpio_enable_e810(struct ptp_clock_info *info, - struct ptp_clock_request *rq, int on) +static int ice_ptp_disable_shared_pin(struct ice_pf *pf, unsigned int pin, + enum ptp_pin_function func) { - struct ice_pf *pf = ptp_info_to_pf(info); - struct ice_perout_channel clk_cfg = {0}; - bool sma_pres = false; - unsigned int chan; - u32 gpio_pin; - int err; + unsigned int gpio_pin; - if (ice_is_feature_supported(pf, ICE_F_SMA_CTRL)) - sma_pres = true; + switch (func) { + case PTP_PF_PEROUT: + gpio_pin = pf->ptp.ice_pin_desc[pin].gpio[1]; + break; + case PTP_PF_EXTTS: + gpio_pin = pf->ptp.ice_pin_desc[pin].gpio[0]; + break; + default: + return -EOPNOTSUPP; + } - switch (rq->type) { - case PTP_CLK_REQ_PEROUT: - chan = rq->perout.index; - if (sma_pres) { - if (chan == ice_pin_desc_e810t[SMA1].chan) - clk_cfg.gpio_pin = GPIO_20; - else if (chan == ice_pin_desc_e810t[SMA2].chan) - clk_cfg.gpio_pin = GPIO_22; - else - return -1; - } else if (ice_is_e810t(&pf->hw)) { - if (chan == 0) - clk_cfg.gpio_pin = GPIO_20; - else - clk_cfg.gpio_pin = GPIO_22; - } else if (chan == PPS_CLK_GEN_CHAN) { - clk_cfg.gpio_pin = PPS_PIN_INDEX; - } else { - clk_cfg.gpio_pin = chan; - } + for (unsigned int i = 0; i < pf->ptp.info.n_pins; i++) { + struct ptp_pin_desc *pin_desc = &pf->ptp.pin_desc[i]; + unsigned int chan = pin_desc->chan; - clk_cfg.period = ((rq->perout.period.sec * NSEC_PER_SEC) + - rq->perout.period.nsec); - clk_cfg.start_time = ((rq->perout.start.sec * NSEC_PER_SEC) + - rq->perout.start.nsec); - clk_cfg.ena = !!on; + /* Skip pin idx from the request */ + if (i == pin) + continue; - err = ice_ptp_cfg_clkout(pf, chan, &clk_cfg, true); - break; - case PTP_CLK_REQ_EXTTS: - chan = rq->extts.index; - if (sma_pres) { - if (chan < ice_pin_desc_e810t[SMA2].chan) - gpio_pin = GPIO_21; - else - gpio_pin = GPIO_23; - } else if (ice_is_e810t(&pf->hw)) { - if (chan == 0) - gpio_pin = GPIO_21; - else - gpio_pin = GPIO_23; - } else { - gpio_pin = chan; + if (pin_desc->func == PTP_PF_PEROUT && + pf->ptp.ice_pin_desc[i].gpio[1] == gpio_pin) { + pf->ptp.perout_rqs[chan].period.sec = 0; + pf->ptp.perout_rqs[chan].period.nsec = 0; + pin_desc->func = PTP_PF_NONE; + pin_desc->chan = 0; + dev_dbg(ice_pf_to_dev(pf), "Disabling pin %u with shared output GPIO pin %u\n", + i, gpio_pin); + return ice_ptp_cfg_perout(pf, &pf->ptp.perout_rqs[chan], + false); + } else if (pf->ptp.pin_desc->func == PTP_PF_EXTTS && + pf->ptp.ice_pin_desc[i].gpio[0] == gpio_pin) { + pf->ptp.extts_rqs[chan].flags &= ~PTP_ENABLE_FEATURE; + pin_desc->func = PTP_PF_NONE; + pin_desc->chan = 0; + dev_dbg(ice_pf_to_dev(pf), "Disabling pin %u with shared input GPIO pin %u\n", + i, gpio_pin); + return ice_ptp_cfg_extts(pf, &pf->ptp.extts_rqs[chan], + false); } + } + + return 0; +} - err = ice_ptp_cfg_extts(pf, !!on, chan, gpio_pin, - rq->extts.flags); +/** + * ice_verify_pin - verify if pin supports requested pin function + * @info: the driver's PTP info structure + * @pin: Pin index + * @func: Assigned function + * @chan: Assigned channel + * + * Return: 0 on success, -EOPNOTSUPP when function is not supported. + */ +static int ice_verify_pin(struct ptp_clock_info *info, unsigned int pin, + enum ptp_pin_function func, unsigned int chan) +{ + struct ice_pf *pf = ptp_info_to_pf(info); + const struct ice_ptp_pin_desc *pin_desc; + + pin_desc = &pf->ptp.ice_pin_desc[pin]; + + /* Is assigned function allowed? */ + switch (func) { + case PTP_PF_EXTTS: + if (pin_desc->gpio[0] < 0) + return -EOPNOTSUPP; break; + case PTP_PF_PEROUT: + if (pin_desc->gpio[1] < 0) + return -EOPNOTSUPP; + break; + case PTP_PF_NONE: + break; + case PTP_PF_PHYSYNC: default: return -EOPNOTSUPP; } - return err; + /* On adapters with SMA_CTRL disable other pins that share same GPIO */ + if (ice_is_feature_supported(pf, ICE_F_SMA_CTRL)) { + ice_ptp_disable_shared_pin(pf, pin, func); + pf->ptp.pin_desc[pin].func = func; + pf->ptp.pin_desc[pin].chan = chan; + return ice_ptp_set_sma_cfg(pf); + } + + return 0; } /** - * ice_ptp_gpio_enable_e823 - Enable/disable ancillary features of PHC - * @info: the driver's PTP info structure + * ice_ptp_gpio_enable - Enable/disable ancillary features of PHC + * @info: The driver's PTP info structure * @rq: The requested feature to change * @on: Enable/disable flag + * + * Return: 0 on success, negative error code otherwise */ -static int ice_ptp_gpio_enable_e823(struct ptp_clock_info *info, - struct ptp_clock_request *rq, int on) +static int ice_ptp_gpio_enable(struct ptp_clock_info *info, + struct ptp_clock_request *rq, int on) { struct ice_pf *pf = ptp_info_to_pf(info); - struct ice_perout_channel clk_cfg = {0}; int err; switch (rq->type) { - case PTP_CLK_REQ_PPS: - clk_cfg.gpio_pin = PPS_PIN_INDEX; - clk_cfg.period = NSEC_PER_SEC; - clk_cfg.ena = !!on; + case PTP_CLK_REQ_PEROUT: + { + struct ptp_perout_request *cached = + &pf->ptp.perout_rqs[rq->perout.index]; - err = ice_ptp_cfg_clkout(pf, PPS_CLK_GEN_CHAN, &clk_cfg, true); - break; + err = ice_ptp_cfg_perout(pf, &rq->perout, on); + if (!err) { + *cached = rq->perout; + } else { + cached->period.sec = 0; + cached->period.nsec = 0; + } + return err; + } case PTP_CLK_REQ_EXTTS: - err = ice_ptp_cfg_extts(pf, !!on, rq->extts.index, - TIME_SYNC_PIN_INDEX, rq->extts.flags); - break; + { + struct ptp_extts_request *cached = + &pf->ptp.extts_rqs[rq->extts.index]; + + err = ice_ptp_cfg_extts(pf, &rq->extts, on); + if (!err) + *cached = rq->extts; + else + cached->flags &= ~PTP_ENABLE_FEATURE; + return err; + } default: return -EOPNOTSUPP; } - - return err; } /** @@ -1925,16 +2041,10 @@ ice_ptp_gettimex64(struct ptp_clock_info *info, struct timespec64 *ts, struct ptp_system_timestamp *sts) { struct ice_pf *pf = ptp_info_to_pf(info); - struct ice_hw *hw = &pf->hw; - - if (!ice_ptp_lock(hw)) { - dev_err(ice_pf_to_dev(pf), "PTP failed to get time\n"); - return -EBUSY; - } - - ice_ptp_read_time(pf, ts, sts); - ice_ptp_unlock(hw); + u64 time_ns; + time_ns = ice_ptp_read_src_clk_reg(pf, sts); + *ts = ns_to_timespec64(time_ns); return 0; } @@ -1954,11 +2064,14 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts) struct ice_hw *hw = &pf->hw; int err; - /* For Vernier mode, we need to recalibrate after new settime - * Start with disabling timestamp block + /* For Vernier mode on E82X, we need to recalibrate after new settime. + * Start with marking timestamps as invalid. */ - if (pf->ptp.port.link_up) - ice_ptp_port_phy_stop(&pf->ptp.port); + if (hw->mac_type == ICE_MAC_GENERIC) { + err = ice_ptp_clear_phy_offset_ready_e82x(hw); + if (err) + dev_warn(ice_pf_to_dev(pf), "Failed to mark timestamps as invalid before settime\n"); + } if (!ice_ptp_lock(hw)) { err = -EBUSY; @@ -1966,7 +2079,7 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts) } /* Disable periodic outputs */ - ice_ptp_disable_all_clkout(pf); + ice_ptp_disable_all_perout(pf); err = ice_ptp_write_init(pf, &ts64); ice_ptp_unlock(hw); @@ -1975,10 +2088,10 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts) ice_ptp_reset_cached_phctime(pf); /* Reenable periodic outputs */ - ice_ptp_enable_all_clkout(pf); + ice_ptp_enable_all_perout(pf); /* Recalibrate and re-enable timestamp blocks for E822/E823 */ - if (hw->phy_model == ICE_PHY_E82X) + if (hw->mac_type == ICE_MAC_GENERIC) ice_ptp_restart_all_phy(pf); exit: if (err) { @@ -2037,12 +2150,12 @@ static int ice_ptp_adjtime(struct ptp_clock_info *info, s64 delta) } /* Disable periodic outputs */ - ice_ptp_disable_all_clkout(pf); + ice_ptp_disable_all_perout(pf); err = ice_ptp_write_adj(pf, delta); /* Reenable periodic outputs */ - ice_ptp_enable_all_clkout(pf); + ice_ptp_enable_all_perout(pf); ice_ptp_unlock(hw); @@ -2056,92 +2169,157 @@ static int ice_ptp_adjtime(struct ptp_clock_info *info, s64 delta) return 0; } +/** + * struct ice_crosststamp_cfg - Device cross timestamp configuration + * @lock_reg: The hardware semaphore lock to use + * @lock_busy: Bit in the semaphore lock indicating the lock is busy + * @ctl_reg: The hardware register to request cross timestamp + * @ctl_active: Bit in the control register to request cross timestamp + * @art_time_l: Lower 32-bits of ART system time + * @art_time_h: Upper 32-bits of ART system time + * @dev_time_l: Lower 32-bits of device time (per timer index) + * @dev_time_h: Upper 32-bits of device time (per timer index) + */ +struct ice_crosststamp_cfg { + /* HW semaphore lock register */ + u32 lock_reg; + u32 lock_busy; + + /* Capture control register */ + u32 ctl_reg; + u32 ctl_active; + + /* Time storage */ + u32 art_time_l; + u32 art_time_h; + u32 dev_time_l[2]; + u32 dev_time_h[2]; +}; + +static const struct ice_crosststamp_cfg ice_crosststamp_cfg_e82x = { + .lock_reg = PFHH_SEM, + .lock_busy = PFHH_SEM_BUSY_M, + .ctl_reg = GLHH_ART_CTL, + .ctl_active = GLHH_ART_CTL_ACTIVE_M, + .art_time_l = GLHH_ART_TIME_L, + .art_time_h = GLHH_ART_TIME_H, + .dev_time_l[0] = GLTSYN_HHTIME_L(0), + .dev_time_h[0] = GLTSYN_HHTIME_H(0), + .dev_time_l[1] = GLTSYN_HHTIME_L(1), + .dev_time_h[1] = GLTSYN_HHTIME_H(1), +}; + #ifdef CONFIG_ICE_HWTS +static const struct ice_crosststamp_cfg ice_crosststamp_cfg_e830 = { + .lock_reg = E830_PFPTM_SEM, + .lock_busy = E830_PFPTM_SEM_BUSY_M, + .ctl_reg = E830_GLPTM_ART_CTL, + .ctl_active = E830_GLPTM_ART_CTL_ACTIVE_M, + .art_time_l = E830_GLPTM_ART_TIME_L, + .art_time_h = E830_GLPTM_ART_TIME_H, + .dev_time_l[0] = E830_GLTSYN_PTMTIME_L(0), + .dev_time_h[0] = E830_GLTSYN_PTMTIME_H(0), + .dev_time_l[1] = E830_GLTSYN_PTMTIME_L(1), + .dev_time_h[1] = E830_GLTSYN_PTMTIME_H(1), +}; + +#endif /* CONFIG_ICE_HWTS */ +/** + * struct ice_crosststamp_ctx - Device cross timestamp context + * @snapshot: snapshot of system clocks for historic interpolation + * @pf: pointer to the PF private structure + * @cfg: pointer to hardware configuration for cross timestamp + */ +struct ice_crosststamp_ctx { + struct system_time_snapshot snapshot; + struct ice_pf *pf; + const struct ice_crosststamp_cfg *cfg; +}; + /** - * ice_ptp_get_syncdevicetime - Get the cross time stamp info + * ice_capture_crosststamp - Capture a device/system cross timestamp * @device: Current device time * @system: System counter value read synchronously with device time - * @ctx: Context provided by timekeeping code + * @__ctx: Context passed from ice_ptp_getcrosststamp * * Read device and system (ART) clock simultaneously and return the corrected * clock values in ns. + * + * Return: zero on success, or a negative error code on failure. */ -static int -ice_ptp_get_syncdevicetime(ktime_t *device, - struct system_counterval_t *system, - void *ctx) +static int ice_capture_crosststamp(ktime_t *device, + struct system_counterval_t *system, + void *__ctx) { - struct ice_pf *pf = (struct ice_pf *)ctx; - struct ice_hw *hw = &pf->hw; - u32 hh_lock, hh_art_ctl; - int i; + struct ice_crosststamp_ctx *ctx = __ctx; + const struct ice_crosststamp_cfg *cfg; + u32 lock, ctl, ts_lo, ts_hi, tmr_idx; + struct ice_pf *pf; + struct ice_hw *hw; + int err; + u64 ts; -#define MAX_HH_HW_LOCK_TRIES 5 -#define MAX_HH_CTL_LOCK_TRIES 100 + cfg = ctx->cfg; + pf = ctx->pf; + hw = &pf->hw; - 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"); + tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc; + if (tmr_idx > 1) + return -EINVAL; + + /* Poll until we obtain the cross-timestamp hardware semaphore */ + err = rd32_poll_timeout(hw, cfg->lock_reg, lock, + !(lock & cfg->lock_busy), + 10 * USEC_PER_MSEC, 50 * USEC_PER_MSEC); + if (err) { + dev_err(ice_pf_to_dev(pf), "PTP failed to get cross timestamp lock\n"); return -EBUSY; } + /* Snapshot system time for historic interpolation */ + ktime_get_snapshot(&ctx->snapshot); + /* 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); - - 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) { - udelay(1); - continue; - } else { - u32 hh_ts_lo, hh_ts_hi, tmr_idx; - u64 hh_ts; - - tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc; - /* Read ART time */ - hh_ts_lo = rd32(hw, GLHH_ART_TIME_L); - hh_ts_hi = rd32(hw, GLHH_ART_TIME_H); - hh_ts = ((u64)hh_ts_hi << 32) | hh_ts_lo; - *system = convert_art_ns_to_tsc(hh_ts); - /* Read Device source clock time */ - hh_ts_lo = rd32(hw, GLTSYN_HHTIME_L(tmr_idx)); - hh_ts_hi = rd32(hw, GLTSYN_HHTIME_H(tmr_idx)); - hh_ts = ((u64)hh_ts_hi << 32) | hh_ts_lo; - *device = ns_to_ktime(hh_ts); - break; - } - } + ctl = rd32(hw, cfg->ctl_reg); + ctl |= cfg->ctl_active; + wr32(hw, cfg->ctl_reg, ctl); + /* Poll until hardware completes the capture */ + err = rd32_poll_timeout(hw, cfg->ctl_reg, ctl, !(ctl & cfg->ctl_active), + 5, 20 * USEC_PER_MSEC); + if (err) + goto err_timeout; + + /* Read ART system time */ + ts_lo = rd32(hw, cfg->art_time_l); + ts_hi = rd32(hw, cfg->art_time_h); + ts = ((u64)ts_hi << 32) | ts_lo; + system->cycles = ts; + system->cs_id = CSID_X86_ART; + + /* Read Device source clock time */ + ts_lo = rd32(hw, cfg->dev_time_l[tmr_idx]); + ts_hi = rd32(hw, cfg->dev_time_h[tmr_idx]); + ts = ((u64)ts_hi << 32) | ts_lo; + *device = ns_to_ktime(ts); + +err_timeout: /* 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); + lock = rd32(hw, cfg->lock_reg); + lock &= ~cfg->lock_busy; + wr32(hw, cfg->lock_reg, lock); - if (i == MAX_HH_CTL_LOCK_TRIES) - return -ETIMEDOUT; - - return 0; + return err; } /** - * ice_ptp_getcrosststamp_e82x - Capture a device cross timestamp + * ice_ptp_getcrosststamp - Capture a device cross timestamp * @info: the driver's PTP info structure * @cts: The memory to fill the cross timestamp info * @@ -2149,22 +2327,36 @@ 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 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. + * + * Return: zero on success, or a negative error code on failure. */ -static int -ice_ptp_getcrosststamp_e82x(struct ptp_clock_info *info, - struct system_device_crosststamp *cts) +static int ice_ptp_getcrosststamp(struct ptp_clock_info *info, + struct system_device_crosststamp *cts) { struct ice_pf *pf = ptp_info_to_pf(info); + struct ice_crosststamp_ctx ctx = { + .pf = pf, + }; + + switch (pf->hw.mac_type) { + case ICE_MAC_GENERIC: + case ICE_MAC_GENERIC_3K_E825: + ctx.cfg = &ice_crosststamp_cfg_e82x; + break; +#ifdef CONFIG_ICE_HWTS + case ICE_MAC_E830: + ctx.cfg = &ice_crosststamp_cfg_e830; + break; +#endif /* CONFIG_ICE_HWTS */ + default: + return -EOPNOTSUPP; + } - return get_device_system_crosststamp(ice_ptp_get_syncdevicetime, - pf, NULL, cts); + return get_device_system_crosststamp(ice_capture_crosststamp, &ctx, + &ctx.snapshot, cts); } -#endif /* CONFIG_ICE_HWTS */ /** * ice_ptp_get_ts_config - ioctl interface to read the timestamping config @@ -2299,20 +2491,41 @@ u64 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc, } /** - * ice_ptp_disable_sma_pins_e810t - Disable E810-T SMA pins + * ice_ptp_setup_pin_cfg - setup PTP pin_config structure + * @pf: Board private structure + */ +static void ice_ptp_setup_pin_cfg(struct ice_pf *pf) +{ + for (unsigned int i = 0; i < pf->ptp.info.n_pins; i++) { + const struct ice_ptp_pin_desc *desc = &pf->ptp.ice_pin_desc[i]; + struct ptp_pin_desc *pin = &pf->ptp.pin_desc[i]; + const char *name = NULL; + + if (!ice_is_feature_supported(pf, ICE_F_SMA_CTRL)) + name = ice_pin_names[desc->name_idx]; + else if (desc->name_idx != GPIO_NA) + name = ice_pin_names_nvm[desc->name_idx]; + if (name) + strscpy(pin->name, name, sizeof(pin->name)); + + pin->index = i; + } + + pf->ptp.info.pin_config = pf->ptp.pin_desc; +} + +/** + * ice_ptp_disable_pins - Disable PTP pins * @pf: pointer to the PF structure - * @info: PTP clock info structure * * Disable the OS access to the SMA pins. Called to clear out the OS - * indications of pin support when we fail to setup the E810-T SMA control - * register. + * indications of pin support when we fail to setup the SMA control register. */ -static void -ice_ptp_disable_sma_pins_e810t(struct ice_pf *pf, struct ptp_clock_info *info) +static void ice_ptp_disable_pins(struct ice_pf *pf) { - struct device *dev = ice_pf_to_dev(pf); + struct ptp_clock_info *info = &pf->ptp.info; - dev_warn(dev, "Failed to configure E810-T SMA pin control\n"); + dev_warn(ice_pf_to_dev(pf), "Failed to configure PTP pin control\n"); info->enable = NULL; info->verify = NULL; @@ -2322,126 +2535,176 @@ ice_ptp_disable_sma_pins_e810t(struct ice_pf *pf, struct ptp_clock_info *info) } /** - * ice_ptp_setup_sma_pins_e810t - Setup the SMA pins + * ice_ptp_parse_sdp_entries - update ice_ptp_pin_desc structure from NVM * @pf: pointer to the PF structure - * @info: PTP clock info structure + * @entries: SDP connection section from NVM + * @num_entries: number of valid entries in sdp_entries + * @pins: PTP pins array to update * - * Finish setting up the SMA pins by allocating pin_config, and setting it up - * according to the current status of the SMA. On failure, disable all of the - * extended SMA pin support. + * Return: 0 on success, negative error code otherwise. */ -static void -ice_ptp_setup_sma_pins_e810t(struct ice_pf *pf, struct ptp_clock_info *info) +static int ice_ptp_parse_sdp_entries(struct ice_pf *pf, __le16 *entries, + unsigned int num_entries, + struct ice_ptp_pin_desc *pins) { - struct device *dev = ice_pf_to_dev(pf); - int err; + unsigned int n_pins = 0; + unsigned int i; - /* Allocate memory for kernel pins interface */ - info->pin_config = devm_kcalloc(dev, info->n_pins, - sizeof(*info->pin_config), GFP_KERNEL); - if (!info->pin_config) { - ice_ptp_disable_sma_pins_e810t(pf, info); - return; - } + /* Setup ice_pin_desc array */ + for (i = 0; i < ICE_N_PINS_MAX; i++) { + pins[i].name_idx = -1; + pins[i].gpio[0] = -1; + pins[i].gpio[1] = -1; + } + + for (i = 0; i < num_entries; i++) { + u16 entry = le16_to_cpu(entries[i]); + DECLARE_BITMAP(bitmap, GPIO_NA); + unsigned int bitmap_idx; + bool dir; + u16 gpio; + + *bitmap = FIELD_GET(ICE_AQC_NVM_SDP_AC_PIN_M, entry); + dir = !!FIELD_GET(ICE_AQC_NVM_SDP_AC_DIR_M, entry); + gpio = FIELD_GET(ICE_AQC_NVM_SDP_AC_SDP_NUM_M, entry); + for_each_set_bit(bitmap_idx, bitmap, GPIO_NA + 1) { + unsigned int idx; + + /* Check if entry's pin bit is valid */ + if (bitmap_idx >= NUM_PTP_PINS_NVM && + bitmap_idx != GPIO_NA) + continue; - /* Read current SMA status */ - err = ice_get_sma_config_e810t(&pf->hw, info->pin_config); - if (err) - ice_ptp_disable_sma_pins_e810t(pf, info); -} + /* Check if pin already exists */ + for (idx = 0; idx < ICE_N_PINS_MAX; idx++) + if (pins[idx].name_idx == bitmap_idx) + break; + + if (idx == ICE_N_PINS_MAX) { + /* Pin not found, setup its entry and name */ + idx = n_pins++; + pins[idx].name_idx = bitmap_idx; + if (bitmap_idx == GPIO_NA) + strscpy(pf->ptp.pin_desc[idx].name, + ice_pin_names[gpio], + sizeof(pf->ptp.pin_desc[idx] + .name)); + } + + /* Setup in/out GPIO number */ + pins[idx].gpio[dir] = gpio; + } + } -/** - * ice_ptp_setup_pins_e810 - Setup PTP pins in sysfs - * @pf: pointer to the PF instance - * @info: PTP clock capabilities - */ -static void -ice_ptp_setup_pins_e810(struct ice_pf *pf, struct ptp_clock_info *info) -{ - 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; + for (i = 0; i < n_pins; i++) { + dev_dbg(ice_pf_to_dev(pf), + "NVM pin entry[%d] : name_idx %d gpio_out %d gpio_in %d\n", + i, pins[i].name_idx, pins[i].gpio[1], pins[i].gpio[0]); } -} -/** - * ice_ptp_setup_pins_e823 - Setup PTP pins in sysfs - * @pf: pointer to the PF instance - * @info: PTP clock capabilities - */ -static void -ice_ptp_setup_pins_e823(struct ice_pf *pf, struct ptp_clock_info *info) -{ - info->pps = 1; - info->n_per_out = 0; - info->n_ext_ts = 1; + pf->ptp.info.n_pins = n_pins; + return 0; } /** - * ice_ptp_set_funcs_e82x - Set specialized functions for E82x 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 E82x devices. + * Assign functions to the PTP capabilities 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 E82x + * in ice_ptp_set_caps. Only add functions here which are distinct for E82X * devices. */ -static void -ice_ptp_set_funcs_e82x(struct ice_pf *pf, struct ptp_clock_info *info) +static void ice_ptp_set_funcs_e82x(struct ice_pf *pf) { -#ifdef CONFIG_ICE_HWTS - if (boot_cpu_has(X86_FEATURE_ART) && - boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) - info->getcrosststamp = ice_ptp_getcrosststamp_e82x; -#endif /* CONFIG_ICE_HWTS */ + pf->ptp.info.getcrosststamp = ice_ptp_getcrosststamp; + + if (pf->hw.mac_type == ICE_MAC_GENERIC_3K_E825) { + pf->ptp.ice_pin_desc = ice_pin_desc_e825c; + pf->ptp.info.n_pins = ICE_PIN_DESC_ARR_LEN(ice_pin_desc_e825c); + } else { + pf->ptp.ice_pin_desc = ice_pin_desc_e82x; + pf->ptp.info.n_pins = ICE_PIN_DESC_ARR_LEN(ice_pin_desc_e82x); + } + ice_ptp_setup_pin_cfg(pf); } /** * ice_ptp_set_funcs_e810 - Set specialized functions for E810 support * @pf: Board private structure - * @info: PTP info to fill * * Assign functions to the PTP capabiltiies structure for E810 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 e810 + * in ice_ptp_set_caps. Only add functions here which are distinct for E810 * devices. */ -static void -ice_ptp_set_funcs_e810(struct ice_pf *pf, struct ptp_clock_info *info) +static void ice_ptp_set_funcs_e810(struct ice_pf *pf) { - info->enable = ice_ptp_gpio_enable_e810; - ice_ptp_setup_pins_e810(pf, info); + __le16 entries[ICE_AQC_NVM_SDP_AC_MAX_SIZE]; + struct ice_ptp_pin_desc *desc = NULL; + struct ice_ptp *ptp = &pf->ptp; + unsigned int num_entries; + int err; + + err = ice_ptp_read_sdp_ac(&pf->hw, entries, &num_entries); + if (err) { + /* SDP section does not exist in NVM or is corrupted */ + if (ice_is_feature_supported(pf, ICE_F_SMA_CTRL)) { + ptp->ice_pin_desc = ice_pin_desc_e810_sma; + ptp->info.n_pins = + ICE_PIN_DESC_ARR_LEN(ice_pin_desc_e810_sma); + } else { + pf->ptp.ice_pin_desc = ice_pin_desc_e810; + pf->ptp.info.n_pins = + ICE_PIN_DESC_ARR_LEN(ice_pin_desc_e810); + err = 0; + } + } else { + desc = devm_kcalloc(ice_pf_to_dev(pf), ICE_N_PINS_MAX, + sizeof(struct ice_ptp_pin_desc), + GFP_KERNEL); + if (!desc) + goto err; + + err = ice_ptp_parse_sdp_entries(pf, entries, num_entries, desc); + if (err) + goto err; + + ptp->ice_pin_desc = (const struct ice_ptp_pin_desc *)desc; + } + + ptp->info.pin_config = ptp->pin_desc; + ice_ptp_setup_pin_cfg(pf); + + if (ice_is_feature_supported(pf, ICE_F_SMA_CTRL)) + err = ice_ptp_set_sma_cfg(pf); +err: + if (err) { + devm_kfree(ice_pf_to_dev(pf), desc); + ice_ptp_disable_pins(pf); + } } /** - * ice_ptp_set_funcs_e823 - Set specialized functions for E823 support + * ice_ptp_set_funcs_e830 - Set specialized functions for E830 support * @pf: Board private structure - * @info: PTP info to fill * - * Assign functions to the PTP capabiltiies structure for E823 devices. + * Assign functions to the PTP capabiltiies structure for E830 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 e823 + * in ice_ptp_set_caps. Only add functions here which are distinct for E830 * devices. */ -static void -ice_ptp_set_funcs_e823(struct ice_pf *pf, struct ptp_clock_info *info) +static void ice_ptp_set_funcs_e830(struct ice_pf *pf) { - ice_ptp_set_funcs_e82x(pf, info); +#ifdef CONFIG_ICE_HWTS + if (pcie_ptm_enabled(pf->pdev) && boot_cpu_has(X86_FEATURE_ART)) + pf->ptp.info.getcrosststamp = ice_ptp_getcrosststamp; - info->enable = ice_ptp_gpio_enable_e823; - ice_ptp_setup_pins_e823(pf, info); +#endif /* CONFIG_ICE_HWTS */ + /* Rest of the config is the same as base E810 */ + pf->ptp.ice_pin_desc = ice_pin_desc_e810; + pf->ptp.info.n_pins = ICE_PIN_DESC_ARR_LEN(ice_pin_desc_e810); + ice_ptp_setup_pin_cfg(pf); } /** @@ -2461,13 +2724,30 @@ static void ice_ptp_set_caps(struct ice_pf *pf) info->adjfine = ice_ptp_adjfine; info->gettimex64 = ice_ptp_gettimex64; info->settime64 = ice_ptp_settime64; - - if (ice_is_e810(&pf->hw)) - ice_ptp_set_funcs_e810(pf, info); - else if (ice_is_e823(&pf->hw)) - ice_ptp_set_funcs_e823(pf, info); - else - ice_ptp_set_funcs_e82x(pf, info); + info->n_per_out = GLTSYN_TGT_H_IDX_MAX; + info->n_ext_ts = GLTSYN_EVNT_H_IDX_MAX; + info->enable = ice_ptp_gpio_enable; + info->verify = ice_verify_pin; + + info->supported_extts_flags = PTP_RISING_EDGE | + PTP_FALLING_EDGE | + PTP_STRICT_FLAGS; + info->supported_perout_flags = PTP_PEROUT_PHASE; + + switch (pf->hw.mac_type) { + case ICE_MAC_E810: + ice_ptp_set_funcs_e810(pf); + return; + case ICE_MAC_E830: + ice_ptp_set_funcs_e830(pf); + return; + case ICE_MAC_GENERIC: + case ICE_MAC_GENERIC_3K_E825: + ice_ptp_set_funcs_e82x(pf); + return; + default: + return; + } } /** @@ -2578,6 +2858,65 @@ enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf) } /** + * ice_ptp_ts_irq - Process the PTP Tx timestamps in IRQ context + * @pf: Board private structure + * + * Return: IRQ_WAKE_THREAD if Tx timestamp read has to be handled in the bottom + * half of the interrupt and IRQ_HANDLED otherwise. + */ +irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + + switch (hw->mac_type) { + case ICE_MAC_E810: + /* E810 capable of low latency timestamping with interrupt can + * request a single timestamp in the top half and wait for + * a second LL TS interrupt from the FW when it's ready. + */ + if (hw->dev_caps.ts_dev_info.ts_ll_int_read) { + struct ice_ptp_tx *tx = &pf->ptp.port.tx; + u8 idx; + + if (!ice_pf_state_is_nominal(pf)) + return IRQ_HANDLED; + + spin_lock(&tx->lock); + idx = find_next_bit_wrap(tx->in_use, tx->len, + tx->last_ll_ts_idx_read + 1); + if (idx != tx->len) + ice_ptp_req_tx_single_tstamp(tx, idx); + spin_unlock(&tx->lock); + + return IRQ_HANDLED; + } + fallthrough; /* non-LL_TS E810 */ + case ICE_MAC_GENERIC: + case ICE_MAC_GENERIC_3K_E825: + /* All other devices process timestamps in the bottom half due + * to sleeping or polling. + */ + if (!ice_ptp_pf_handles_tx_interrupt(pf)) + return IRQ_HANDLED; + + set_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread); + return IRQ_WAKE_THREAD; + case ICE_MAC_E830: + /* E830 can read timestamps in the top half using rd32() */ + if (ice_ptp_process_ts(pf) == ICE_TX_TSTAMP_WORK_PENDING) { + /* Process outstanding Tx timestamps. If there + * is more work, re-arm the interrupt to trigger again. + */ + wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M); + ice_flush(hw); + } + return IRQ_HANDLED; + default: + return IRQ_HANDLED; + } +} + +/** * ice_ptp_maybe_trigger_tx_interrupt - Trigger Tx timstamp interrupt * @pf: Board private structure * @@ -2597,13 +2936,13 @@ static void ice_ptp_maybe_trigger_tx_interrupt(struct ice_pf *pf) bool trigger_oicr = false; unsigned int i; - if (ice_is_e810(hw)) + if (!pf->ptp.port.tx.has_ready_bitmap) return; if (!ice_pf_src_tmr_owned(pf)) return; - for (i = 0; i < ICE_MAX_QUAD; i++) { + for (i = 0; i < ICE_GET_QUAD_NUM(hw->ptp.num_lports); i++) { u64 tstamp_ready; int err; @@ -2644,6 +2983,32 @@ static void ice_ptp_periodic_work(struct kthread_work *work) } /** + * ice_ptp_prepare_rebuild_sec - Prepare second NAC for PTP reset or rebuild + * @pf: Board private structure + * @rebuild: rebuild if true, prepare if false + * @reset_type: the reset type being performed + */ +static void ice_ptp_prepare_rebuild_sec(struct ice_pf *pf, bool rebuild, + enum ice_reset_req reset_type) +{ + struct list_head *entry; + + list_for_each(entry, &pf->adapter->ports.ports) { + struct ice_ptp_port *port = list_entry(entry, + struct ice_ptp_port, + list_node); + struct ice_pf *peer_pf = ptp_port_to_pf(port); + + if (!ice_is_primary(&peer_pf->hw)) { + if (rebuild) + ice_ptp_rebuild(peer_pf, reset_type); + else + ice_ptp_prepare_for_reset(peer_pf, reset_type); + } + } +} + +/** * ice_ptp_prepare_for_reset - Prepare PTP for reset * @pf: Board private structure * @reset_type: the reset type being performed @@ -2651,6 +3016,7 @@ static void ice_ptp_periodic_work(struct kthread_work *work) void ice_ptp_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type) { struct ice_ptp *ptp = &pf->ptp; + struct ice_hw *hw = &pf->hw; u8 src_tmr; if (ptp->state != ICE_PTP_READY) @@ -2666,10 +3032,13 @@ void ice_ptp_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type) if (reset_type == ICE_RESET_PFR) return; + if (ice_pf_src_tmr_owned(pf) && hw->mac_type == ICE_MAC_GENERIC_3K_E825) + ice_ptp_prepare_rebuild_sec(pf, false, reset_type); + ice_ptp_release_tx_tracker(pf, &pf->ptp.port.tx); /* Disable periodic outputs */ - ice_ptp_disable_all_clkout(pf); + ice_ptp_disable_all_perout(pf); src_tmr = ice_get_ptp_src_clock_index(&pf->hw); @@ -2707,10 +3076,8 @@ static int ice_ptp_rebuild_owner(struct ice_pf *pf) /* Write the increment time value to PHY and LAN */ err = ice_ptp_write_incval(hw, ice_base_incval(pf)); - if (err) { - ice_ptp_unlock(hw); - return err; - } + if (err) + goto err_unlock; /* Write the initial Time value to PHY and LAN using the cached PHC * time before the reset and time difference between stopping and @@ -2723,10 +3090,8 @@ static int ice_ptp_rebuild_owner(struct ice_pf *pf) ts = ktime_to_timespec64(ktime_get_real()); } err = ice_ptp_write_init(pf, &ts); - if (err) { - ice_ptp_unlock(hw); - return err; - } + if (err) + goto err_unlock; /* Release the global hardware lock */ ice_ptp_unlock(hw); @@ -2736,16 +3101,22 @@ static int ice_ptp_rebuild_owner(struct ice_pf *pf) */ ice_ptp_flush_all_tx_tracker(pf); - if (!ice_is_e810(hw)) { - /* Enable quad interrupts */ - err = ice_ptp_cfg_phy_interrupt(pf, true, 1); - if (err) - return err; + /* Enable quad interrupts */ + err = ice_ptp_cfg_phy_interrupt(pf, true, 1); + if (err) + return err; - ice_ptp_restart_all_phy(pf); - } + ice_ptp_restart_all_phy(pf); + + /* Re-enable all periodic outputs and external timestamp events */ + ice_ptp_enable_all_perout(pf); + ice_ptp_enable_all_extts(pf); return 0; + +err_unlock: + ice_ptp_unlock(hw); + return err; } /** @@ -2785,187 +3156,43 @@ err: dev_err(ice_pf_to_dev(pf), "PTP reset failed %d\n", 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) +static int ice_ptp_setup_adapter(struct ice_pf *pf) { - 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 (!ice_pf_src_tmr_owned(pf) || !ice_is_primary(&pf->hw)) + return -EPERM; - 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); + pf->adapter->ctrl_pf = pf; 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) +static int ice_ptp_setup_pf(struct ice_pf *pf) { - 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); + struct ice_ptp *ctrl_ptp = ice_get_ctrl_ptp(pf); + struct ice_ptp *ptp = &pf->ptp; - mutex_lock(&owner_pf->ptp.ports_owner.lock); - list_del(&aux_pf->ptp.port.list_member); - mutex_unlock(&owner_pf->ptp.ports_owner.lock); -} + if (WARN_ON(!ctrl_ptp) || pf->hw.mac_type == ICE_MAC_UNKNOWN) + return -ENODEV; -/** - * 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 */ -} + INIT_LIST_HEAD(&ptp->port.list_node); + mutex_lock(&pf->adapter->ports.lock); -/** - * 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; -} + list_add(&ptp->port.list_node, + &pf->adapter->ports.ports); + mutex_unlock(&pf->adapter->ports.lock); -/** - * 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) +static void ice_ptp_cleanup_pf(struct ice_pf *pf) { - 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)); - if (!name) - return -ENOMEM; - - 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; + struct ice_ptp *ptp = &pf->ptp; - 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); + if (pf->hw.mac_type != ICE_MAC_UNKNOWN) { + mutex_lock(&pf->adapter->ports.lock); + list_del(&ptp->port.list_node); + mutex_unlock(&pf->adapter->ports.lock); } - - 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); } /** @@ -2977,15 +3204,12 @@ static void ice_ptp_unregister_auxbus_driver(struct ice_pf *pf) */ int ice_ptp_clock_index(struct ice_pf *pf) { - struct auxiliary_device *aux_dev; - struct ice_pf *owner_pf; + struct ice_ptp *ctrl_ptp = ice_get_ctrl_ptp(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) + if (!ctrl_ptp) return -1; - clock = owner_pf->ptp.clock; + clock = ctrl_ptp->clock; return clock ? ptp_clock_index(clock) : -1; } @@ -3019,47 +3243,37 @@ static int ice_ptp_init_owner(struct ice_pf *pf) /* Write the increment time value to PHY and LAN */ err = ice_ptp_write_incval(hw, ice_base_incval(pf)); - if (err) { - ice_ptp_unlock(hw); - goto err_exit; - } + if (err) + goto err_unlock; ts = ktime_to_timespec64(ktime_get_real()); /* Write the initial Time value to PHY and LAN */ err = ice_ptp_write_init(pf, &ts); - if (err) { - ice_ptp_unlock(hw); - goto err_exit; - } + if (err) + goto err_unlock; /* Release the global hardware lock */ ice_ptp_unlock(hw); - if (!ice_is_e810(hw)) { - /* Enable quad interrupts */ - err = ice_ptp_cfg_phy_interrupt(pf, true, 1); - if (err) - goto err_exit; - } + /* Configure PHY interrupt settings */ + err = ice_ptp_cfg_phy_interrupt(pf, true, 1); + if (err) + goto err_exit; /* Ensure we have a clock device */ err = ice_ptp_create_clock(pf); if (err) goto err_clk; - 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: return err; + +err_unlock: + ice_ptp_unlock(hw); + return err; } /** @@ -3077,7 +3291,7 @@ static int ice_ptp_init_work(struct ice_pf *pf, struct ice_ptp *ptp) /* Allocate a kworker for handling work required for the ports * connected to the PTP hardware clock. */ - kworker = kthread_create_worker(0, "ice-ptp-%s", + kworker = kthread_run_worker(0, "ice-ptp-%s", dev_name(ice_pf_to_dev(pf))); if (IS_ERR(kworker)) return PTR_ERR(kworker); @@ -3094,6 +3308,8 @@ static int ice_ptp_init_work(struct ice_pf *pf, struct ice_ptp *ptp) * ice_ptp_init_port - Initialize PTP port structure * @pf: Board private structure * @ptp_port: PTP port structure + * + * Return: 0 on success, -ENODEV on invalid MAC type, -ENOMEM on failed alloc. */ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port) { @@ -3101,13 +3317,14 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port) mutex_init(&ptp_port->ps_lock); - switch (hw->phy_model) { - case ICE_PHY_E810: - return ice_ptp_init_tx_e810(pf, &ptp_port->tx); - case ICE_PHY_E82X: + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: + case ICE_MAC_GENERIC_3K_E825: + return ice_ptp_init_tx(pf, &ptp_port->tx, ptp_port->port_num); + case ICE_MAC_GENERIC: kthread_init_delayed_work(&ptp_port->ov_work, ice_ptp_wait_for_offsets); - return ice_ptp_init_tx_e82x(pf, &ptp_port->tx, ptp_port->port_num); default: @@ -3116,76 +3333,6 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port) } /** - * 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)); - if (!name) - return -ENOMEM; - - 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 * @@ -3196,8 +3343,8 @@ static void ice_ptp_remove_auxbus_device(struct ice_pf *pf) */ static void ice_ptp_init_tx_interrupt_mode(struct ice_pf *pf) { - switch (pf->hw.phy_model) { - case ICE_PHY_E82X: + switch (pf->hw.mac_type) { + case ICE_MAC_GENERIC: /* E822 based PHY has the clock owner process the interrupt * for all ports. */ @@ -3232,23 +3379,35 @@ void ice_ptp_init(struct ice_pf *pf) ptp->state = ICE_PTP_INITIALIZING; - ice_ptp_init_phy_model(hw); + if (hw->lane_num < 0) { + err = hw->lane_num; + goto err_exit; + } + ptp->port.port_num = hw->lane_num; + + ice_ptp_init_hw(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 (ice_pf_src_tmr_owned(pf)) { + if (ice_pf_src_tmr_owned(pf) && ice_is_primary(hw)) { + err = ice_ptp_setup_adapter(pf); + if (err) + goto err_exit; err = ice_ptp_init_owner(pf); if (err) - goto err; + goto err_exit; } - ptp->port.port_num = hw->pf_id; + err = ice_ptp_setup_pf(pf); + if (err) + goto err_exit; + err = ice_ptp_init_port(pf, &ptp->port); if (err) - goto err; + goto err_exit; /* Start the PHY timestamping block */ ice_ptp_reset_phy_timestamping(pf); @@ -3256,20 +3415,16 @@ void ice_ptp_init(struct ice_pf *pf) /* Configure initial Tx interrupt settings */ ice_ptp_cfg_tx_interrupt(pf); - err = ice_ptp_create_auxbus_device(pf); - if (err) - goto err; - ptp->state = ICE_PTP_READY; err = ice_ptp_init_work(pf, ptp); if (err) - goto err; + goto err_exit; dev_info(ice_pf_to_dev(pf), "PTP init successful\n"); return; -err: +err_exit: /* If we registered a PTP clock, release it */ if (pf->ptp.clock) { ptp_clock_unregister(ptp->clock); @@ -3296,10 +3451,12 @@ void ice_ptp_release(struct ice_pf *pf) /* Disable timestamping for both Tx and Rx */ ice_ptp_disable_timestamp_mode(pf); - ice_ptp_remove_auxbus_device(pf); + ice_ptp_cleanup_pf(pf); ice_ptp_release_tx_tracker(pf, &pf->ptp.port.tx); + ice_ptp_disable_all_extts(pf); + kthread_cancel_delayed_work_sync(&pf->ptp.work); ice_ptp_port_phy_stop(&pf->ptp.port); @@ -3309,14 +3466,11 @@ void ice_ptp_release(struct ice_pf *pf) pf->ptp.kworker = NULL; } - if (ice_pf_src_tmr_owned(pf)) - ice_ptp_unregister_auxbus_driver(pf); - if (!pf->ptp.clock) return; /* Disable periodic outputs */ - ice_ptp_disable_all_clkout(pf); + ice_ptp_disable_all_perout(pf); ptp_clock_unregister(pf->ptp.clock); pf->ptp.clock = NULL; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index 3af20025043a..3b769a0cad00 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -9,30 +9,6 @@ #include "ice_ptp_hw.h" -enum ice_ptp_pin_e810 { - GPIO_20 = 0, - GPIO_21, - GPIO_22, - GPIO_23, - NUM_PTP_PIN_E810 -}; - -enum ice_ptp_pin_e810t { - GNSS = 0, - SMA1, - UFL1, - SMA2, - UFL2, - NUM_PTP_PINS_E810T -}; - -struct ice_perout_channel { - bool ena; - u32 gpio_pin; - u64 period; - u64 start_time; -}; - /* The ice hardware captures Tx hardware timestamps in the PHY. The timestamp * is stored in a buffer of registers. Depending on the specific hardware, * this buffer might be shared across multiple PHY ports. @@ -152,7 +128,7 @@ struct ice_ptp_tx { /* Quad and port information for initializing timestamp blocks */ #define INDEX_PER_QUAD 64 #define INDEX_PER_PORT_E82X 16 -#define INDEX_PER_PORT_E810 64 +#define INDEX_PER_PORT 64 /** * struct ice_ptp_port - data used to initialize an external port for PTP @@ -161,9 +137,8 @@ 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 + * @list_node: list member structure * @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 @@ -171,9 +146,8 @@ struct ice_ptp_tx { * @port_num: the port number this structure represents */ struct ice_ptp_port { - struct list_head list_member; + struct list_head list_node; 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; @@ -187,22 +161,6 @@ enum ice_ptp_tx_interrupt { 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 enum ice_ptp_state { @@ -213,19 +171,71 @@ enum ice_ptp_state { ICE_PTP_ERROR, }; +enum ice_ptp_pin { + SDP0 = 0, + SDP1, + SDP2, + SDP3, + TIME_SYNC, + ONE_PPS +}; + +enum ice_ptp_pin_nvm { + GNSS = 0, + SMA1, + UFL1, + SMA2, + UFL2, + NUM_PTP_PINS_NVM, + GPIO_NA = 9 +}; + +/* Per-channel register definitions */ +#define GLTSYN_AUX_OUT(_chan, _idx) (GLTSYN_AUX_OUT_0(_idx) + ((_chan) * 8)) +#define GLTSYN_AUX_IN(_chan, _idx) (GLTSYN_AUX_IN_0(_idx) + ((_chan) * 8)) +#define GLTSYN_CLKO(_chan, _idx) (GLTSYN_CLKO_0(_idx) + ((_chan) * 8)) +#define GLTSYN_TGT_L(_chan, _idx) (GLTSYN_TGT_L_0(_idx) + ((_chan) * 16)) +#define GLTSYN_TGT_H(_chan, _idx) (GLTSYN_TGT_H_0(_idx) + ((_chan) * 16)) +#define GLTSYN_EVNT_L(_chan, _idx) (GLTSYN_EVNT_L_0(_idx) + ((_chan) * 16)) +#define GLTSYN_EVNT_H(_chan, _idx) (GLTSYN_EVNT_H_0(_idx) + ((_chan) * 16)) +#define GLTSYN_EVNT_H_IDX_MAX 3 + +/* Pin definitions for PTP */ +#define ICE_N_PINS_MAX 6 +#define ICE_SMA_PINS_NUM 4 +#define ICE_PIN_DESC_ARR_LEN(_arr) (sizeof(_arr) / \ + sizeof(struct ice_ptp_pin_desc)) + +/** + * struct ice_ptp_pin_desc - hardware pin description data + * @name_idx: index of the name of pin in ice_pin_names + * @gpio: the associated GPIO input and output pins + * @delay: input and output signal delays in nanoseconds + * + * Structure describing a PTP-capable GPIO pin that extends ptp_pin_desc array + * for the device. Device families have separate sets of available pins with + * varying restrictions. + */ +struct ice_ptp_pin_desc { + int name_idx; + int gpio[2]; + unsigned int delay[2]; +}; + /** * struct ice_ptp - data used for integrating with CONFIG_PTP_1588_CLOCK * @state: current state of PTP state machine * @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 - * @ext_ts_chan: the external timestamp channel in use - * @ext_ts_irq: the external timestamp IRQ in use * @kworker: kwork thread for handling periodic work - * @perout_channels: periodic output data + * @ext_ts_irq: the external timestamp IRQ in use + * @pin_desc: structure defining pins + * @ice_pin_desc: internal structure describing pin relations + * @perout_rqs: cached periodic output requests + * @extts_rqs: cached external timestamp requests * @info: structure defining PTP hardware capabilities * @clock: pointer to registered PTP clock device * @tstamp_config: hardware timestamping configuration @@ -241,14 +251,15 @@ struct ice_ptp { enum ice_ptp_state state; 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; - u8 ext_ts_chan; - u8 ext_ts_irq; struct kthread_worker *kworker; - struct ice_perout_channel perout_channels[GLTSYN_TGT_H_IDX_MAX]; + u8 ext_ts_irq; + struct ptp_pin_desc pin_desc[ICE_N_PINS_MAX]; + const struct ice_ptp_pin_desc *ice_pin_desc; + struct ptp_perout_request perout_rqs[GLTSYN_TGT_H_IDX_MAX]; + struct ptp_extts_request extts_rqs[GLTSYN_EVNT_H_IDX_MAX]; struct ptp_clock_info info; struct ptp_clock *clock; struct hwtstamp_config tstamp_config; @@ -279,27 +290,6 @@ struct ice_ptp { #define FIFO_EMPTY BIT(2) #define FIFO_OK 0xFF #define ICE_PTP_FIFO_NUM_CHECKS 5 -/* Per-channel register definitions */ -#define GLTSYN_AUX_OUT(_chan, _idx) (GLTSYN_AUX_OUT_0(_idx) + ((_chan) * 8)) -#define GLTSYN_AUX_IN(_chan, _idx) (GLTSYN_AUX_IN_0(_idx) + ((_chan) * 8)) -#define GLTSYN_CLKO(_chan, _idx) (GLTSYN_CLKO_0(_idx) + ((_chan) * 8)) -#define GLTSYN_TGT_L(_chan, _idx) (GLTSYN_TGT_L_0(_idx) + ((_chan) * 16)) -#define GLTSYN_TGT_H(_chan, _idx) (GLTSYN_TGT_H_0(_idx) + ((_chan) * 16)) -#define GLTSYN_EVNT_L(_chan, _idx) (GLTSYN_EVNT_L_0(_idx) + ((_chan) * 16)) -#define GLTSYN_EVNT_H(_chan, _idx) (GLTSYN_EVNT_H_0(_idx) + ((_chan) * 16)) -#define GLTSYN_EVNT_H_IDX_MAX 3 - -/* Pin definitions for PTP PPS out */ -#define PPS_CLK_GEN_CHAN 3 -#define PPS_CLK_SRC_CHAN 2 -#define PPS_PIN_INDEX 5 -#define TIME_SYNC_PIN_INDEX 4 -#define N_EXT_TS_E810 3 -#define N_PER_OUT_E810 4 -#define N_PER_OUT_E810T 3 -#define N_PER_OUT_NO_SMA_E810T 2 -#define N_EXT_TS_NO_SMA_E810T 2 -#define ETH_GLTSYN_ENA(_i) (0x03000348 + ((_i) * 4)) #if IS_ENABLED(CONFIG_PTP_1588_CLOCK) int ice_ptp_clock_index(struct ice_pf *pf); @@ -313,6 +303,9 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb); void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx); void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx); enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf); +irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf); +u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf, + struct ptp_system_timestamp *sts); u64 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc, const struct ice_pkt_ctx *pkt_ctx); @@ -321,7 +314,7 @@ void ice_ptp_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type); void ice_ptp_init(struct ice_pf *pf); void ice_ptp_release(struct ice_pf *pf); -void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup); +void ice_ptp_link_change(struct ice_pf *pf, bool linkup); #else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ static inline int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr) { @@ -351,6 +344,17 @@ static inline bool ice_ptp_process_ts(struct ice_pf *pf) return true; } +static inline irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf) +{ + return IRQ_HANDLED; +} + +static inline u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf, + struct ptp_system_timestamp *sts) +{ + return 0; +} + static inline u64 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc, const struct ice_pkt_ctx *pkt_ctx) @@ -369,7 +373,7 @@ static inline void ice_ptp_prepare_for_reset(struct ice_pf *pf, } static inline void ice_ptp_init(struct ice_pf *pf) { } 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 void ice_ptp_link_change(struct ice_pf *pf, bool linkup) { } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h index 2c4dab0c48ab..003cdfada3ca 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h @@ -9,6 +9,276 @@ */ /* Constants defined for the PTP 1588 clock hardware. */ +const struct ice_phy_reg_info_eth56g eth56g_phy_res[NUM_ETH56G_PHY_RES] = { + [ETH56G_PHY_REG_PTP] = { + .base_addr = 0x092000, + .step = 0x98, + }, + [ETH56G_PHY_MEM_PTP] = { + .base_addr = 0x093000, + .step = 0x200, + }, + [ETH56G_PHY_REG_XPCS] = { + .base_addr = 0x000000, + .step = 0x21000, + }, + [ETH56G_PHY_REG_MAC] = { + .base_addr = 0x085000, + .step = 0x1000, + }, + [ETH56G_PHY_REG_GPCS] = { + .base_addr = 0x084000, + .step = 0x400, + }, +}; + +const +struct ice_eth56g_mac_reg_cfg eth56g_mac_cfg[NUM_ICE_ETH56G_LNK_SPD] = { + [ICE_ETH56G_LNK_SPD_1G] = { + .tx_mode = { .def = 6, }, + .rx_mode = { .def = 6, }, + .blks_per_clk = 1, + .blktime = 0x4000, /* 32 */ + .tx_offset = { + .serdes = 0x6666, /* 51.2 */ + .no_fec = 0xd066, /* 104.2 */ + .sfd = 0x3000, /* 24 */ + .onestep = 0x30000 /* 384 */ + }, + .rx_offset = { + .serdes = 0xffffc59a, /* -29.2 */ + .no_fec = 0xffff0a80, /* -122.75 */ + .sfd = 0x2c00, /* 22 */ + .bs_ds = 0x19a /* 0.8 */ + /* Dynamic bitslip 0 equals to 10 */ + } + }, + [ICE_ETH56G_LNK_SPD_2_5G] = { + .tx_mode = { .def = 6, }, + .rx_mode = { .def = 6, }, + .blks_per_clk = 1, + .blktime = 0x199a, /* 12.8 */ + .tx_offset = { + .serdes = 0x28f6, /* 20.48 */ + .no_fec = 0x53b8, /* 41.86 */ + .sfd = 0x1333, /* 9.6 */ + .onestep = 0x13333 /* 153.6 */ + }, + .rx_offset = { + .serdes = 0xffffe8a4, /* -11.68 */ + .no_fec = 0xffff9a76, /* -50.77 */ + .sfd = 0xf33, /* 7.6 */ + .bs_ds = 0xa4 /* 0.32 */ + } + }, + [ICE_ETH56G_LNK_SPD_10G] = { + .tx_mode = { .def = 1, }, + .rx_mode = { .def = 1, }, + .blks_per_clk = 1, + .blktime = 0x666, /* 3.2 */ + .tx_offset = { + .serdes = 0x234c, /* 17.6484848 */ + .no_fec = 0x8e80, /* 71.25 */ + .fc = 0xb4a4, /* 90.32 */ + .sfd = 0x4a4, /* 2.32 */ + .onestep = 0x4ccd /* 38.4 */ + }, + .rx_offset = { + .serdes = 0xffffeb27, /* -10.42424 */ + .no_fec = 0xffffcccd, /* -25.6 */ + .fc = 0xfffc557b, /* -469.26 */ + .sfd = 0x4a4, /* 2.32 */ + .bs_ds = 0x32 /* 0.0969697 */ + } + }, + [ICE_ETH56G_LNK_SPD_25G] = { + .tx_mode = { + .def = 1, + .rs = 4 + }, + .tx_mk_dly = 4, + .tx_cw_dly = { + .def = 1, + .onestep = 6 + }, + .rx_mode = { + .def = 1, + .rs = 4 + }, + .rx_mk_dly = { + .def = 1, + .rs = 1 + }, + .rx_cw_dly = { + .def = 1, + .rs = 1 + }, + .blks_per_clk = 1, + .blktime = 0x28f, /* 1.28 */ + .mktime = 0x147b, /* 10.24, only if RS-FEC enabled */ + .tx_offset = { + .serdes = 0xe1e, /* 7.0593939 */ + .no_fec = 0x3857, /* 28.17 */ + .fc = 0x48c3, /* 36.38 */ + .rs = 0x8100, /* 64.5 */ + .sfd = 0x1dc, /* 0.93 */ + .onestep = 0x1eb8 /* 15.36 */ + }, + .rx_offset = { + .serdes = 0xfffff7a9, /* -4.1697 */ + .no_fec = 0xffffe71a, /* -12.45 */ + .fc = 0xfffe894d, /* -187.35 */ + .rs = 0xfffff8cd, /* -3.6 */ + .sfd = 0x1dc, /* 0.93 */ + .bs_ds = 0x14 /* 0.0387879, RS-FEC 0 */ + } + }, + [ICE_ETH56G_LNK_SPD_40G] = { + .tx_mode = { .def = 3 }, + .tx_mk_dly = 4, + .tx_cw_dly = { + .def = 1, + .onestep = 6 + }, + .rx_mode = { .def = 4 }, + .rx_mk_dly = { .def = 1 }, + .rx_cw_dly = { .def = 1 }, + .blktime = 0x333, /* 1.6 */ + .mktime = 0xccd, /* 6.4 */ + .tx_offset = { + .serdes = 0x234c, /* 17.6484848 */ + .no_fec = 0x5a8a, /* 45.27 */ + .fc = 0x81b8, /* 64.86 */ + .sfd = 0x4a4, /* 2.32 */ + .onestep = 0x1333 /* 9.6 */ + }, + .rx_offset = { + .serdes = 0xffffeb27, /* -10.42424 */ + .no_fec = 0xfffff594, /* -5.21 */ + .fc = 0xfffe3080, /* -231.75 */ + .sfd = 0x4a4, /* 2.32 */ + .bs_ds = 0xccd /* 6.4 */ + } + }, + [ICE_ETH56G_LNK_SPD_50G] = { + .tx_mode = { .def = 5 }, + .tx_mk_dly = 4, + .tx_cw_dly = { + .def = 1, + .onestep = 6 + }, + .rx_mode = { .def = 5 }, + .rx_mk_dly = { .def = 1 }, + .rx_cw_dly = { .def = 1 }, + .blktime = 0x28f, /* 1.28 */ + .mktime = 0xa3d, /* 5.12 */ + .tx_offset = { + .serdes = 0x13ba, /* 9.86353 */ + .rs = 0x5400, /* 42 */ + .sfd = 0xe6, /* 0.45 */ + .onestep = 0xf5c /* 7.68 */ + }, + .rx_offset = { + .serdes = 0xfffff7e8, /* -4.04706 */ + .rs = 0xfffff994, /* -3.21 */ + .sfd = 0xe6 /* 0.45 */ + } + }, + [ICE_ETH56G_LNK_SPD_50G2] = { + .tx_mode = { + .def = 3, + .rs = 2 + }, + .tx_mk_dly = 4, + .tx_cw_dly = { + .def = 1, + .onestep = 6 + }, + .rx_mode = { + .def = 4, + .rs = 1 + }, + .rx_mk_dly = { .def = 1 }, + .rx_cw_dly = { .def = 1 }, + .blktime = 0x28f, /* 1.28 */ + .mktime = 0xa3d, /* 5.12 */ + .tx_offset = { + .serdes = 0xe1e, /* 7.0593939 */ + .no_fec = 0x3d33, /* 30.6 */ + .rs = 0x5057, /* 40.17 */ + .sfd = 0x1dc, /* 0.93 */ + .onestep = 0xf5c /* 7.68 */ + }, + .rx_offset = { + .serdes = 0xfffff7a9, /* -4.1697 */ + .no_fec = 0xfffff8cd, /* -3.6 */ + .rs = 0xfffff21a, /* -6.95 */ + .sfd = 0x1dc, /* 0.93 */ + .bs_ds = 0xa3d /* 5.12, RS-FEC 0x633 (3.1) */ + } + }, + [ICE_ETH56G_LNK_SPD_100G] = { + .tx_mode = { + .def = 3, + .rs = 2 + }, + .tx_mk_dly = 10, + .tx_cw_dly = { + .def = 3, + .onestep = 6 + }, + .rx_mode = { + .def = 4, + .rs = 1 + }, + .rx_mk_dly = { .def = 5 }, + .rx_cw_dly = { .def = 5 }, + .blks_per_clk = 1, + .blktime = 0x148, /* 0.64 */ + .mktime = 0x199a, /* 12.8 */ + .tx_offset = { + .serdes = 0xe1e, /* 7.0593939 */ + .no_fec = 0x67ec, /* 51.96 */ + .rs = 0x44fb, /* 34.49 */ + .sfd = 0x1dc, /* 0.93 */ + .onestep = 0xf5c /* 7.68 */ + }, + .rx_offset = { + .serdes = 0xfffff7a9, /* -4.1697 */ + .no_fec = 0xfffff5a9, /* -5.17 */ + .rs = 0xfffff6e6, /* -4.55 */ + .sfd = 0x1dc, /* 0.93 */ + .bs_ds = 0x199a /* 12.8, RS-FEC 0x31b (1.552) */ + } + }, + [ICE_ETH56G_LNK_SPD_100G2] = { + .tx_mode = { .def = 5 }, + .tx_mk_dly = 10, + .tx_cw_dly = { + .def = 3, + .onestep = 6 + }, + .rx_mode = { .def = 5 }, + .rx_mk_dly = { .def = 5 }, + .rx_cw_dly = { .def = 5 }, + .blks_per_clk = 1, + .blktime = 0x148, /* 0.64 */ + .mktime = 0x199a, /* 12.8 */ + .tx_offset = { + .serdes = 0x13ba, /* 9.86353 */ + .rs = 0x460a, /* 35.02 */ + .sfd = 0xe6, /* 0.45 */ + .onestep = 0xf5c /* 7.68 */ + }, + .rx_offset = { + .serdes = 0xfffff7e8, /* -4.04706 */ + .rs = 0xfffff548, /* -5.36 */ + .sfd = 0xe6, /* 0.45 */ + .bs_ds = 0x303 /* 1.506 */ + } + } +}; + /* struct ice_time_ref_info_e82x * * E822 hardware can use different sources as the reference for the PTP @@ -19,15 +289,13 @@ * reference. See the struct ice_time_ref_info_e82x for information about the * meaning of each constant. */ -const struct ice_time_ref_info_e82x e822_time_ref[NUM_ICE_TIME_REF_FREQ] = { +const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = { /* ICE_TIME_REF_FREQ_25_000 -> 25 MHz */ { /* pll_freq */ 823437500, /* 823.4375 MHz PLL */ /* nominal_incval */ 0x136e44fabULL, - /* pps_delay */ - 11, }, /* ICE_TIME_REF_FREQ_122_880 -> 122.88 MHz */ @@ -36,8 +304,6 @@ const struct ice_time_ref_info_e82x e822_time_ref[NUM_ICE_TIME_REF_FREQ] = { 783360000, /* 783.36 MHz */ /* nominal_incval */ 0x146cc2177ULL, - /* pps_delay */ - 12, }, /* ICE_TIME_REF_FREQ_125_000 -> 125 MHz */ @@ -46,8 +312,6 @@ const struct ice_time_ref_info_e82x e822_time_ref[NUM_ICE_TIME_REF_FREQ] = { 796875000, /* 796.875 MHz */ /* nominal_incval */ 0x141414141ULL, - /* pps_delay */ - 12, }, /* ICE_TIME_REF_FREQ_153_600 -> 153.6 MHz */ @@ -56,8 +320,6 @@ const struct ice_time_ref_info_e82x e822_time_ref[NUM_ICE_TIME_REF_FREQ] = { 816000000, /* 816 MHz */ /* nominal_incval */ 0x139b9b9baULL, - /* pps_delay */ - 12, }, /* ICE_TIME_REF_FREQ_156_250 -> 156.25 MHz */ @@ -66,8 +328,6 @@ const struct ice_time_ref_info_e82x e822_time_ref[NUM_ICE_TIME_REF_FREQ] = { 830078125, /* 830.78125 MHz */ /* nominal_incval */ 0x134679aceULL, - /* pps_delay */ - 11, }, /* ICE_TIME_REF_FREQ_245_760 -> 245.76 MHz */ @@ -76,8 +336,6 @@ const struct ice_time_ref_info_e82x e822_time_ref[NUM_ICE_TIME_REF_FREQ] = { 783360000, /* 783.36 MHz */ /* nominal_incval */ 0x146cc2177ULL, - /* pps_delay */ - 12, }, }; @@ -155,6 +413,93 @@ const struct ice_cgu_pll_params_e82x e822_cgu_params[NUM_ICE_TIME_REF_FREQ] = { }, }; +const +struct ice_cgu_pll_params_e825c e825c_cgu_params[NUM_ICE_TIME_REF_FREQ] = { + /* ICE_TIME_REF_FREQ_25_000 -> 25 MHz */ + { + /* tspll_ck_refclkfreq */ + 0x19, + /* tspll_ndivratio */ + 1, + /* tspll_fbdiv_intgr */ + 320, + /* tspll_fbdiv_frac */ + 0, + /* ref1588_ck_div */ + 0, + }, + + /* ICE_TIME_REF_FREQ_122_880 -> 122.88 MHz */ + { + /* tspll_ck_refclkfreq */ + 0x29, + /* tspll_ndivratio */ + 3, + /* tspll_fbdiv_intgr */ + 195, + /* tspll_fbdiv_frac */ + 1342177280UL, + /* ref1588_ck_div */ + 0, + }, + + /* ICE_TIME_REF_FREQ_125_000 -> 125 MHz */ + { + /* tspll_ck_refclkfreq */ + 0x3E, + /* tspll_ndivratio */ + 2, + /* tspll_fbdiv_intgr */ + 128, + /* tspll_fbdiv_frac */ + 0, + /* ref1588_ck_div */ + 0, + }, + + /* ICE_TIME_REF_FREQ_153_600 -> 153.6 MHz */ + { + /* tspll_ck_refclkfreq */ + 0x33, + /* tspll_ndivratio */ + 3, + /* tspll_fbdiv_intgr */ + 156, + /* tspll_fbdiv_frac */ + 1073741824UL, + /* ref1588_ck_div */ + 0, + }, + + /* ICE_TIME_REF_FREQ_156_250 -> 156.25 MHz */ + { + /* tspll_ck_refclkfreq */ + 0x1F, + /* tspll_ndivratio */ + 5, + /* tspll_fbdiv_intgr */ + 256, + /* tspll_fbdiv_frac */ + 0, + /* ref1588_ck_div */ + 0, + }, + + /* ICE_TIME_REF_FREQ_245_760 -> 245.76 MHz */ + { + /* tspll_ck_refclkfreq */ + 0x52, + /* tspll_ndivratio */ + 3, + /* tspll_fbdiv_intgr */ + 97, + /* tspll_fbdiv_frac */ + 2818572288UL, + /* ref1588_ck_div */ + 0, + }, +}; + /* struct ice_vernier_info_e82x * * E822 hardware calibrates the delay of the timestamp indication from the @@ -359,9 +704,9 @@ const struct ice_vernier_info_e82x e822_vernier[NUM_ICE_PTP_LNK_SPD] = { /* rx_desk_rsgb_par */ 644531250, /* 644.53125 MHz Reed Solomon gearbox */ /* tx_desk_rsgb_pcs */ - 644531250, /* 644.53125 MHz Reed Solomon gearbox */ + 390625000, /* 390.625 MHz Reed Solomon gearbox */ /* rx_desk_rsgb_pcs */ - 644531250, /* 644.53125 MHz Reed Solomon gearbox */ + 390625000, /* 390.625 MHz Reed Solomon gearbox */ /* tx_fixed_delay */ 1620, /* pmd_adj_divisor */ diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index 187ce9b54e1a..ccac84eb34c9 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -2,6 +2,7 @@ /* Copyright (C) 2021, Intel Corporation. */ #include <linux/delay.h> +#include <linux/iopoll.h> #include "ice_common.h" #include "ice_ptp_hw.h" #include "ice_ptp_consts.h" @@ -33,7 +34,6 @@ static const struct ice_cgu_pin_desc ice_e810t_sfp_cgu_inputs[] = { 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[] = { @@ -51,7 +51,6 @@ static const struct ice_cgu_pin_desc ice_e810t_qsfp_cgu_inputs[] = { 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[] = { @@ -227,40 +226,660 @@ static u64 ice_ptp_read_src_incval(struct ice_hw *hw) } /** - * ice_ptp_src_cmd - Prepare source timer for a timer command - * @hw: pointer to HW structure + * ice_read_cgu_reg_e82x - Read a CGU register + * @hw: pointer to the HW struct + * @addr: Register address to read + * @val: storage for register value read + * + * Read the contents of a register of the Clock Generation Unit. Only + * applicable to E822 devices. + * + * Return: 0 on success, other error codes when failed to read from CGU + */ +static int ice_read_cgu_reg_e82x(struct ice_hw *hw, u32 addr, u32 *val) +{ + struct ice_sbq_msg_input cgu_msg = { + .opcode = ice_sbq_msg_rd, + .dest_dev = ice_sbq_dev_cgu, + .msg_addr_low = addr + }; + int err; + + err = ice_sbq_rw_reg(hw, &cgu_msg, ICE_AQ_FLAG_RD); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read CGU register 0x%04x, err %d\n", + addr, err); + return err; + } + + *val = cgu_msg.data; + + return 0; +} + +/** + * ice_write_cgu_reg_e82x - Write a CGU register + * @hw: pointer to the HW struct + * @addr: Register address to write + * @val: value to write into the register + * + * Write the specified value to a register of the Clock Generation Unit. Only + * applicable to E822 devices. + * + * Return: 0 on success, other error codes when failed to write to CGU + */ +static int ice_write_cgu_reg_e82x(struct ice_hw *hw, u32 addr, u32 val) +{ + struct ice_sbq_msg_input cgu_msg = { + .opcode = ice_sbq_msg_wr, + .dest_dev = ice_sbq_dev_cgu, + .msg_addr_low = addr, + .data = val + }; + int err; + + err = ice_sbq_rw_reg(hw, &cgu_msg, ICE_AQ_FLAG_RD); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write CGU register 0x%04x, err %d\n", + addr, err); + return err; + } + + return err; +} + +/** + * ice_clk_freq_str - Convert time_ref_freq to string + * @clk_freq: Clock frequency + * + * Return: specified TIME_REF clock frequency converted to a string + */ +static const char *ice_clk_freq_str(enum ice_time_ref_freq clk_freq) +{ + switch (clk_freq) { + case ICE_TIME_REF_FREQ_25_000: + return "25 MHz"; + case ICE_TIME_REF_FREQ_122_880: + return "122.88 MHz"; + case ICE_TIME_REF_FREQ_125_000: + return "125 MHz"; + case ICE_TIME_REF_FREQ_153_600: + return "153.6 MHz"; + case ICE_TIME_REF_FREQ_156_250: + return "156.25 MHz"; + case ICE_TIME_REF_FREQ_245_760: + return "245.76 MHz"; + default: + return "Unknown"; + } +} + +/** + * ice_clk_src_str - Convert time_ref_src to string + * @clk_src: Clock source + * + * Return: specified clock source converted to its string name + */ +static const char *ice_clk_src_str(enum ice_clk_src clk_src) +{ + switch (clk_src) { + case ICE_CLK_SRC_TCXO: + return "TCXO"; + case ICE_CLK_SRC_TIME_REF: + return "TIME_REF"; + default: + return "Unknown"; + } +} + +/** + * ice_cfg_cgu_pll_e82x - Configure the Clock Generation Unit + * @hw: pointer to the HW struct + * @clk_freq: Clock frequency to program + * @clk_src: Clock source to select (TIME_REF, or TCXO) + * + * Configure the Clock Generation Unit with the desired clock frequency and + * time reference, enabling the PLL which drives the PTP hardware clock. + * + * Return: + * * %0 - success + * * %-EINVAL - input parameters are incorrect + * * %-EBUSY - failed to lock TS PLL + * * %other - CGU read/write failure + */ +static int ice_cfg_cgu_pll_e82x(struct ice_hw *hw, + enum ice_time_ref_freq clk_freq, + enum ice_clk_src clk_src) +{ + union tspll_ro_bwm_lf bwm_lf; + union nac_cgu_dword19 dw19; + union nac_cgu_dword22 dw22; + union nac_cgu_dword24 dw24; + union nac_cgu_dword9 dw9; + int err; + + if (clk_freq >= NUM_ICE_TIME_REF_FREQ) { + dev_warn(ice_hw_to_dev(hw), "Invalid TIME_REF frequency %u\n", + clk_freq); + return -EINVAL; + } + + if (clk_src >= NUM_ICE_CLK_SRC) { + dev_warn(ice_hw_to_dev(hw), "Invalid clock source %u\n", + clk_src); + return -EINVAL; + } + + if (clk_src == ICE_CLK_SRC_TCXO && + clk_freq != ICE_TIME_REF_FREQ_25_000) { + dev_warn(ice_hw_to_dev(hw), + "TCXO only supports 25 MHz frequency\n"); + return -EINVAL; + } + + err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD9, &dw9.val); + if (err) + return err; + + err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD24, &dw24.val); + if (err) + return err; + + err = ice_read_cgu_reg_e82x(hw, TSPLL_RO_BWM_LF, &bwm_lf.val); + if (err) + return err; + + /* Log the current clock configuration */ + ice_debug(hw, ICE_DBG_PTP, "Current CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n", + str_enabled_disabled(dw24.ts_pll_enable), + ice_clk_src_str(dw24.time_ref_sel), + ice_clk_freq_str(dw9.time_ref_freq_sel), + bwm_lf.plllock_true_lock_cri ? "locked" : "unlocked"); + + /* Disable the PLL before changing the clock source or frequency */ + if (dw24.ts_pll_enable) { + dw24.ts_pll_enable = 0; + + err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val); + if (err) + return err; + } + + /* Set the frequency */ + dw9.time_ref_freq_sel = clk_freq; + err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD9, dw9.val); + if (err) + return err; + + /* Configure the TS PLL feedback divisor */ + err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD19, &dw19.val); + if (err) + return err; + + dw19.tspll_fbdiv_intgr = e822_cgu_params[clk_freq].feedback_div; + dw19.tspll_ndivratio = 1; + + err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD19, dw19.val); + if (err) + return err; + + /* Configure the TS PLL post divisor */ + err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD22, &dw22.val); + if (err) + return err; + + dw22.time1588clk_div = e822_cgu_params[clk_freq].post_pll_div; + dw22.time1588clk_sel_div2 = 0; + + err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD22, dw22.val); + if (err) + return err; + + /* Configure the TS PLL pre divisor and clock source */ + err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD24, &dw24.val); + if (err) + return err; + + dw24.ref1588_ck_div = e822_cgu_params[clk_freq].refclk_pre_div; + dw24.tspll_fbdiv_frac = e822_cgu_params[clk_freq].frac_n_div; + dw24.time_ref_sel = clk_src; + + err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val); + if (err) + return err; + + /* Finally, enable the PLL */ + dw24.ts_pll_enable = 1; + + err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val); + if (err) + return err; + + /* Wait to verify if the PLL locks */ + usleep_range(1000, 5000); + + err = ice_read_cgu_reg_e82x(hw, TSPLL_RO_BWM_LF, &bwm_lf.val); + if (err) + return err; + + if (!bwm_lf.plllock_true_lock_cri) { + dev_warn(ice_hw_to_dev(hw), "CGU PLL failed to lock\n"); + return -EBUSY; + } + + /* Log the current clock configuration */ + ice_debug(hw, ICE_DBG_PTP, "New CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n", + str_enabled_disabled(dw24.ts_pll_enable), + ice_clk_src_str(dw24.time_ref_sel), + ice_clk_freq_str(dw9.time_ref_freq_sel), + bwm_lf.plllock_true_lock_cri ? "locked" : "unlocked"); + + return 0; +} + +/** + * ice_cfg_cgu_pll_e825c - Configure the Clock Generation Unit for E825-C + * @hw: pointer to the HW struct + * @clk_freq: Clock frequency to program + * @clk_src: Clock source to select (TIME_REF, or TCXO) + * + * Configure the Clock Generation Unit with the desired clock frequency and + * time reference, enabling the PLL which drives the PTP hardware clock. + * + * Return: + * * %0 - success + * * %-EINVAL - input parameters are incorrect + * * %-EBUSY - failed to lock TS PLL + * * %other - CGU read/write failure + */ +static int ice_cfg_cgu_pll_e825c(struct ice_hw *hw, + enum ice_time_ref_freq clk_freq, + enum ice_clk_src clk_src) +{ + union tspll_ro_lock_e825c ro_lock; + union nac_cgu_dword16_e825c dw16; + union nac_cgu_dword23_e825c dw23; + union nac_cgu_dword19 dw19; + union nac_cgu_dword22 dw22; + union nac_cgu_dword24 dw24; + union nac_cgu_dword9 dw9; + int err; + + if (clk_freq >= NUM_ICE_TIME_REF_FREQ) { + dev_warn(ice_hw_to_dev(hw), "Invalid TIME_REF frequency %u\n", + clk_freq); + return -EINVAL; + } + + if (clk_src >= NUM_ICE_CLK_SRC) { + dev_warn(ice_hw_to_dev(hw), "Invalid clock source %u\n", + clk_src); + return -EINVAL; + } + + if (clk_src == ICE_CLK_SRC_TCXO && + clk_freq != ICE_TIME_REF_FREQ_156_250) { + dev_warn(ice_hw_to_dev(hw), + "TCXO only supports 156.25 MHz frequency\n"); + return -EINVAL; + } + + err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD9, &dw9.val); + if (err) + return err; + + err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD24, &dw24.val); + if (err) + return err; + + err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD16_E825C, &dw16.val); + if (err) + return err; + + err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD23_E825C, &dw23.val); + if (err) + return err; + + err = ice_read_cgu_reg_e82x(hw, TSPLL_RO_LOCK_E825C, &ro_lock.val); + if (err) + return err; + + /* Log the current clock configuration */ + ice_debug(hw, ICE_DBG_PTP, "Current CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n", + str_enabled_disabled(dw24.ts_pll_enable), + ice_clk_src_str(dw23.time_ref_sel), + ice_clk_freq_str(dw9.time_ref_freq_sel), + ro_lock.plllock_true_lock_cri ? "locked" : "unlocked"); + + /* Disable the PLL before changing the clock source or frequency */ + if (dw23.ts_pll_enable) { + dw23.ts_pll_enable = 0; + + err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD23_E825C, + dw23.val); + if (err) + return err; + } + + /* Set the frequency */ + dw9.time_ref_freq_sel = clk_freq; + + /* Enable the correct receiver */ + if (clk_src == ICE_CLK_SRC_TCXO) { + dw9.time_ref_en = 0; + dw9.clk_eref0_en = 1; + } else { + dw9.time_ref_en = 1; + dw9.clk_eref0_en = 0; + } + err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD9, dw9.val); + if (err) + return err; + + /* Choose the referenced frequency */ + dw16.tspll_ck_refclkfreq = + e825c_cgu_params[clk_freq].tspll_ck_refclkfreq; + err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD16_E825C, dw16.val); + if (err) + return err; + + /* Configure the TS PLL feedback divisor */ + err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD19, &dw19.val); + if (err) + return err; + + dw19.tspll_fbdiv_intgr = + e825c_cgu_params[clk_freq].tspll_fbdiv_intgr; + dw19.tspll_ndivratio = + e825c_cgu_params[clk_freq].tspll_ndivratio; + + err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD19, dw19.val); + if (err) + return err; + + /* Configure the TS PLL post divisor */ + err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD22, &dw22.val); + if (err) + return err; + + /* These two are constant for E825C */ + dw22.time1588clk_div = 5; + dw22.time1588clk_sel_div2 = 0; + + err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD22, dw22.val); + if (err) + return err; + + /* Configure the TS PLL pre divisor and clock source */ + err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD23_E825C, &dw23.val); + if (err) + return err; + + dw23.ref1588_ck_div = + e825c_cgu_params[clk_freq].ref1588_ck_div; + dw23.time_ref_sel = clk_src; + + err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD23_E825C, dw23.val); + if (err) + return err; + + dw24.tspll_fbdiv_frac = + e825c_cgu_params[clk_freq].tspll_fbdiv_frac; + + err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val); + if (err) + return err; + + /* Finally, enable the PLL */ + dw23.ts_pll_enable = 1; + + err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD23_E825C, dw23.val); + if (err) + return err; + + /* Wait to verify if the PLL locks */ + usleep_range(1000, 5000); + + err = ice_read_cgu_reg_e82x(hw, TSPLL_RO_LOCK_E825C, &ro_lock.val); + if (err) + return err; + + if (!ro_lock.plllock_true_lock_cri) { + dev_warn(ice_hw_to_dev(hw), "CGU PLL failed to lock\n"); + return -EBUSY; + } + + /* Log the current clock configuration */ + ice_debug(hw, ICE_DBG_PTP, "New CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n", + str_enabled_disabled(dw24.ts_pll_enable), + ice_clk_src_str(dw23.time_ref_sel), + ice_clk_freq_str(dw9.time_ref_freq_sel), + ro_lock.plllock_true_lock_cri ? "locked" : "unlocked"); + + return 0; +} + +#define ICE_ONE_PPS_OUT_AMP_MAX 3 + +/** + * ice_cgu_cfg_pps_out - Configure 1PPS output from CGU + * @hw: pointer to the HW struct + * @enable: true to enable 1PPS output, false to disable it + * + * Return: 0 on success, other negative error code when CGU read/write failed + */ +int ice_cgu_cfg_pps_out(struct ice_hw *hw, bool enable) +{ + union nac_cgu_dword9 dw9; + int err; + + err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD9, &dw9.val); + if (err) + return err; + + dw9.one_pps_out_en = enable; + dw9.one_pps_out_amp = enable * ICE_ONE_PPS_OUT_AMP_MAX; + return ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD9, dw9.val); +} + +/** + * ice_cfg_cgu_pll_dis_sticky_bits_e82x - disable TS PLL sticky bits + * @hw: pointer to the HW struct + * + * Configure the Clock Generation Unit TS PLL sticky bits so they don't latch on + * losing TS PLL lock, but always show current state. + * + * Return: 0 on success, other error codes when failed to read/write CGU + */ +static int ice_cfg_cgu_pll_dis_sticky_bits_e82x(struct ice_hw *hw) +{ + union tspll_cntr_bist_settings cntr_bist; + int err; + + err = ice_read_cgu_reg_e82x(hw, TSPLL_CNTR_BIST_SETTINGS, + &cntr_bist.val); + if (err) + return err; + + /* Disable sticky lock detection so lock err reported is accurate */ + cntr_bist.i_plllock_sel_0 = 0; + cntr_bist.i_plllock_sel_1 = 0; + + return ice_write_cgu_reg_e82x(hw, TSPLL_CNTR_BIST_SETTINGS, + cntr_bist.val); +} + +/** + * ice_cfg_cgu_pll_dis_sticky_bits_e825c - disable TS PLL sticky bits for E825-C + * @hw: pointer to the HW struct + * + * Configure the Clock Generation Unit TS PLL sticky bits so they don't latch on + * losing TS PLL lock, but always show current state. + * + * Return: 0 on success, other error codes when failed to read/write CGU + */ +static int ice_cfg_cgu_pll_dis_sticky_bits_e825c(struct ice_hw *hw) +{ + union tspll_bw_tdc_e825c bw_tdc; + int err; + + err = ice_read_cgu_reg_e82x(hw, TSPLL_BW_TDC_E825C, &bw_tdc.val); + if (err) + return err; + + bw_tdc.i_plllock_sel_1_0 = 0; + + return ice_write_cgu_reg_e82x(hw, TSPLL_BW_TDC_E825C, bw_tdc.val); +} + +/** + * ice_init_cgu_e82x - Initialize CGU with settings from firmware + * @hw: pointer to the HW structure + * + * Initialize the Clock Generation Unit of the E822 device. + * + * Return: 0 on success, other error codes when failed to read/write/cfg CGU + */ +static int ice_init_cgu_e82x(struct ice_hw *hw) +{ + struct ice_ts_func_info *ts_info = &hw->func_caps.ts_func_info; + int err; + + /* Disable sticky lock detection so lock err reported is accurate */ + if (hw->mac_type == ICE_MAC_GENERIC_3K_E825) + err = ice_cfg_cgu_pll_dis_sticky_bits_e825c(hw); + else + err = ice_cfg_cgu_pll_dis_sticky_bits_e82x(hw); + if (err) + return err; + + /* Configure the CGU PLL using the parameters from the function + * capabilities. + */ + if (hw->mac_type == ICE_MAC_GENERIC_3K_E825) + err = ice_cfg_cgu_pll_e825c(hw, ts_info->time_ref, + (enum ice_clk_src)ts_info->clk_src); + else + err = ice_cfg_cgu_pll_e82x(hw, ts_info->time_ref, + (enum ice_clk_src)ts_info->clk_src); + + return err; +} + +/** + * ice_ptp_tmr_cmd_to_src_reg - Convert to source timer command value + * @hw: pointer to HW struct * @cmd: Timer command * - * Prepare the source timer for an upcoming timer sync command. + * Return: the source timer command register value for the given PTP timer + * command. */ -void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) +static u32 ice_ptp_tmr_cmd_to_src_reg(struct ice_hw *hw, + enum ice_ptp_tmr_cmd cmd) { - u32 cmd_val; - u8 tmr_idx; + u32 cmd_val, tmr_idx; + + switch (cmd) { + case ICE_PTP_INIT_TIME: + cmd_val = GLTSYN_CMD_INIT_TIME; + break; + case ICE_PTP_INIT_INCVAL: + cmd_val = GLTSYN_CMD_INIT_INCVAL; + break; + case ICE_PTP_ADJ_TIME: + cmd_val = GLTSYN_CMD_ADJ_TIME; + break; + case ICE_PTP_ADJ_TIME_AT_TIME: + cmd_val = GLTSYN_CMD_ADJ_INIT_TIME; + break; + case ICE_PTP_NOP: + case ICE_PTP_READ_TIME: + cmd_val = GLTSYN_CMD_READ_TIME; + break; + default: + dev_warn(ice_hw_to_dev(hw), + "Ignoring unrecognized timer command %u\n", cmd); + cmd_val = 0; + } tmr_idx = ice_get_ptp_src_clock_index(hw); - cmd_val = tmr_idx << SEL_CPK_SRC; + + return tmr_idx << SEL_CPK_SRC | cmd_val; +} + +/** + * ice_ptp_tmr_cmd_to_port_reg- Convert to port timer command value + * @hw: pointer to HW struct + * @cmd: Timer command + * + * Note that some hardware families use a different command register value for + * the PHY ports, while other hardware families use the same register values + * as the source timer. + * + * Return: the PHY port timer command register value for the given PTP timer + * command. + */ +static u32 ice_ptp_tmr_cmd_to_port_reg(struct ice_hw *hw, + enum ice_ptp_tmr_cmd cmd) +{ + u32 cmd_val, tmr_idx; + + /* Certain hardware families share the same register values for the + * port register and source timer register. + */ + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: + return ice_ptp_tmr_cmd_to_src_reg(hw, cmd) & TS_CMD_MASK_E810; + default: + break; + } switch (cmd) { case ICE_PTP_INIT_TIME: - cmd_val |= GLTSYN_CMD_INIT_TIME; + cmd_val = PHY_CMD_INIT_TIME; break; case ICE_PTP_INIT_INCVAL: - cmd_val |= GLTSYN_CMD_INIT_INCVAL; + cmd_val = PHY_CMD_INIT_INCVAL; break; case ICE_PTP_ADJ_TIME: - cmd_val |= GLTSYN_CMD_ADJ_TIME; + cmd_val = PHY_CMD_ADJ_TIME; break; case ICE_PTP_ADJ_TIME_AT_TIME: - cmd_val |= GLTSYN_CMD_ADJ_INIT_TIME; + cmd_val = PHY_CMD_ADJ_TIME_AT_TIME; break; case ICE_PTP_READ_TIME: - cmd_val |= GLTSYN_CMD_READ_TIME; + cmd_val = PHY_CMD_READ_TIME; break; case ICE_PTP_NOP: + cmd_val = 0; break; + default: + dev_warn(ice_hw_to_dev(hw), + "Ignoring unrecognized timer command %u\n", cmd); + cmd_val = 0; } + tmr_idx = ice_get_ptp_src_clock_index(hw); + + return tmr_idx << SEL_PHY_SRC | cmd_val; +} + +/** + * ice_ptp_src_cmd - Prepare source timer for a timer command + * @hw: pointer to HW structure + * @cmd: Timer command + * + * Prepare the source timer for an upcoming timer sync command. + */ +void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) +{ + struct ice_pf *pf = container_of(hw, struct ice_pf, hw); + u32 cmd_val = ice_ptp_tmr_cmd_to_src_reg(hw, cmd); + + if (!ice_is_primary(hw)) + hw = ice_get_primary_hw(pf); + wr32(hw, GLTSYN_CMD, cmd_val); } @@ -274,10 +893,1868 @@ void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) */ static void ice_ptp_exec_tmr_cmd(struct ice_hw *hw) { + struct ice_pf *pf = container_of(hw, struct ice_pf, hw); + + if (!ice_is_primary(hw)) + hw = ice_get_primary_hw(pf); + + guard(spinlock)(&pf->adapter->ptp_gltsyn_time_lock); wr32(hw, GLTSYN_CMD_SYNC, SYNC_EXEC_CMD); ice_flush(hw); } +/** + * ice_ptp_cfg_sync_delay - Configure PHC to PHY synchronization delay + * @hw: pointer to HW struct + * @delay: delay between PHC and PHY SYNC command execution in nanoseconds + */ +static void ice_ptp_cfg_sync_delay(const struct ice_hw *hw, u32 delay) +{ + wr32(hw, GLTSYN_SYNC_DLAY, delay); + ice_flush(hw); +} + +/* 56G PHY device functions + * + * The following functions operate on devices with the ETH 56G PHY. + */ + +/** + * ice_ptp_get_dest_dev_e825 - get destination PHY for given port number + * @hw: pointer to the HW struct + * @port: destination port + * + * Return: destination sideband queue PHY device. + */ +static enum ice_sbq_dev_id ice_ptp_get_dest_dev_e825(struct ice_hw *hw, + u8 port) +{ + u8 curr_phy, tgt_phy; + + tgt_phy = port >= hw->ptp.ports_per_phy; + curr_phy = hw->lane_num >= hw->ptp.ports_per_phy; + /* In the driver, lanes 4..7 are in fact 0..3 on a second PHY. + * On a single complex E825C, PHY 0 is always destination device phy_0 + * and PHY 1 is phy_0_peer. + * On dual complex E825C, device phy_0 points to PHY on a current + * complex and phy_0_peer to PHY on a different complex. + */ + if ((!ice_is_dual(hw) && tgt_phy == 1) || + (ice_is_dual(hw) && tgt_phy != curr_phy)) + return ice_sbq_dev_phy_0_peer; + else + return ice_sbq_dev_phy_0; +} + +/** + * ice_write_phy_eth56g - Write a PHY port register + * @hw: pointer to the HW struct + * @port: destination port + * @addr: PHY register address + * @val: Value to write + * + * Return: 0 on success, other error codes when failed to write to PHY + */ +static int ice_write_phy_eth56g(struct ice_hw *hw, u8 port, u32 addr, u32 val) +{ + struct ice_sbq_msg_input msg = { + .dest_dev = ice_ptp_get_dest_dev_e825(hw, port), + .opcode = ice_sbq_msg_wr, + .msg_addr_low = lower_16_bits(addr), + .msg_addr_high = upper_16_bits(addr), + .data = val + }; + int err; + + err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD); + if (err) + ice_debug(hw, ICE_DBG_PTP, "PTP failed to send msg to phy %d\n", + err); + + return err; +} + +/** + * ice_read_phy_eth56g - Read a PHY port register + * @hw: pointer to the HW struct + * @port: destination port + * @addr: PHY register address + * @val: Value to write + * + * Return: 0 on success, other error codes when failed to read from PHY + */ +static int ice_read_phy_eth56g(struct ice_hw *hw, u8 port, u32 addr, u32 *val) +{ + struct ice_sbq_msg_input msg = { + .dest_dev = ice_ptp_get_dest_dev_e825(hw, port), + .opcode = ice_sbq_msg_rd, + .msg_addr_low = lower_16_bits(addr), + .msg_addr_high = upper_16_bits(addr) + }; + int err; + + err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD); + if (err) + ice_debug(hw, ICE_DBG_PTP, "PTP failed to send msg to phy %d\n", + err); + else + *val = msg.data; + + return err; +} + +/** + * ice_phy_res_address_eth56g - Calculate a PHY port register address + * @hw: pointer to the HW struct + * @lane: Lane number to be written + * @res_type: resource type (register/memory) + * @offset: Offset from PHY port register base + * @addr: The result address + * + * Return: + * * %0 - success + * * %EINVAL - invalid port number or resource type + */ +static int ice_phy_res_address_eth56g(struct ice_hw *hw, u8 lane, + enum eth56g_res_type res_type, + u32 offset, + u32 *addr) +{ + if (res_type >= NUM_ETH56G_PHY_RES) + return -EINVAL; + + /* Lanes 4..7 are in fact 0..3 on a second PHY */ + lane %= hw->ptp.ports_per_phy; + *addr = eth56g_phy_res[res_type].base_addr + + lane * eth56g_phy_res[res_type].step + offset; + + return 0; +} + +/** + * ice_write_port_eth56g - Write a PHY port register + * @hw: pointer to the HW struct + * @offset: PHY register offset + * @port: Port number + * @val: Value to write + * @res_type: resource type (register/memory) + * + * Return: + * * %0 - success + * * %EINVAL - invalid port number or resource type + * * %other - failed to write to PHY + */ +static int ice_write_port_eth56g(struct ice_hw *hw, u8 port, u32 offset, + u32 val, enum eth56g_res_type res_type) +{ + u32 addr; + int err; + + if (port >= hw->ptp.num_lports) + return -EINVAL; + + err = ice_phy_res_address_eth56g(hw, port, res_type, offset, &addr); + if (err) + return err; + + return ice_write_phy_eth56g(hw, port, addr, val); +} + +/** + * ice_read_port_eth56g - Read a PHY port register + * @hw: pointer to the HW struct + * @offset: PHY register offset + * @port: Port number + * @val: Value to write + * @res_type: resource type (register/memory) + * + * Return: + * * %0 - success + * * %EINVAL - invalid port number or resource type + * * %other - failed to read from PHY + */ +static int ice_read_port_eth56g(struct ice_hw *hw, u8 port, u32 offset, + u32 *val, enum eth56g_res_type res_type) +{ + u32 addr; + int err; + + if (port >= hw->ptp.num_lports) + return -EINVAL; + + err = ice_phy_res_address_eth56g(hw, port, res_type, offset, &addr); + if (err) + return err; + + return ice_read_phy_eth56g(hw, port, addr, val); +} + +/** + * ice_write_ptp_reg_eth56g - Write a PHY port register + * @hw: pointer to the HW struct + * @port: Port number to be written + * @offset: Offset from PHY port register base + * @val: Value to write + * + * Return: + * * %0 - success + * * %EINVAL - invalid port number or resource type + * * %other - failed to write to PHY + */ +static int ice_write_ptp_reg_eth56g(struct ice_hw *hw, u8 port, u16 offset, + u32 val) +{ + return ice_write_port_eth56g(hw, port, offset, val, ETH56G_PHY_REG_PTP); +} + +/** + * ice_write_mac_reg_eth56g - Write a MAC PHY port register + * parameter + * @hw: pointer to the HW struct + * @port: Port number to be written + * @offset: Offset from PHY port register base + * @val: Value to write + * + * Return: + * * %0 - success + * * %EINVAL - invalid port number or resource type + * * %other - failed to write to PHY + */ +static int ice_write_mac_reg_eth56g(struct ice_hw *hw, u8 port, u32 offset, + u32 val) +{ + return ice_write_port_eth56g(hw, port, offset, val, ETH56G_PHY_REG_MAC); +} + +/** + * ice_write_xpcs_reg_eth56g - Write a PHY port register + * @hw: pointer to the HW struct + * @port: Port number to be written + * @offset: Offset from PHY port register base + * @val: Value to write + * + * Return: + * * %0 - success + * * %EINVAL - invalid port number or resource type + * * %other - failed to write to PHY + */ +static int ice_write_xpcs_reg_eth56g(struct ice_hw *hw, u8 port, u32 offset, + u32 val) +{ + return ice_write_port_eth56g(hw, port, offset, val, + ETH56G_PHY_REG_XPCS); +} + +/** + * ice_read_ptp_reg_eth56g - Read a PHY port register + * @hw: pointer to the HW struct + * @port: Port number to be read + * @offset: Offset from PHY port register base + * @val: Pointer to the value to read (out param) + * + * Return: + * * %0 - success + * * %EINVAL - invalid port number or resource type + * * %other - failed to read from PHY + */ +static int ice_read_ptp_reg_eth56g(struct ice_hw *hw, u8 port, u16 offset, + u32 *val) +{ + return ice_read_port_eth56g(hw, port, offset, val, ETH56G_PHY_REG_PTP); +} + +/** + * ice_read_mac_reg_eth56g - Read a PHY port register + * @hw: pointer to the HW struct + * @port: Port number to be read + * @offset: Offset from PHY port register base + * @val: Pointer to the value to read (out param) + * + * Return: + * * %0 - success + * * %EINVAL - invalid port number or resource type + * * %other - failed to read from PHY + */ +static int ice_read_mac_reg_eth56g(struct ice_hw *hw, u8 port, u16 offset, + u32 *val) +{ + return ice_read_port_eth56g(hw, port, offset, val, ETH56G_PHY_REG_MAC); +} + +/** + * ice_read_gpcs_reg_eth56g - Read a PHY port register + * @hw: pointer to the HW struct + * @port: Port number to be read + * @offset: Offset from PHY port register base + * @val: Pointer to the value to read (out param) + * + * Return: + * * %0 - success + * * %EINVAL - invalid port number or resource type + * * %other - failed to read from PHY + */ +static int ice_read_gpcs_reg_eth56g(struct ice_hw *hw, u8 port, u16 offset, + u32 *val) +{ + return ice_read_port_eth56g(hw, port, offset, val, ETH56G_PHY_REG_GPCS); +} + +/** + * ice_read_port_mem_eth56g - Read a PHY port memory location + * @hw: pointer to the HW struct + * @port: Port number to be read + * @offset: Offset from PHY port register base + * @val: Pointer to the value to read (out param) + * + * Return: + * * %0 - success + * * %EINVAL - invalid port number or resource type + * * %other - failed to read from PHY + */ +static int ice_read_port_mem_eth56g(struct ice_hw *hw, u8 port, u16 offset, + u32 *val) +{ + return ice_read_port_eth56g(hw, port, offset, val, ETH56G_PHY_MEM_PTP); +} + +/** + * ice_write_port_mem_eth56g - Write a PHY port memory location + * @hw: pointer to the HW struct + * @port: Port number to be read + * @offset: Offset from PHY port register base + * @val: Pointer to the value to read (out param) + * + * Return: + * * %0 - success + * * %EINVAL - invalid port number or resource type + * * %other - failed to write to PHY + */ +static int ice_write_port_mem_eth56g(struct ice_hw *hw, u8 port, u16 offset, + u32 val) +{ + return ice_write_port_eth56g(hw, port, offset, val, ETH56G_PHY_MEM_PTP); +} + +/** + * ice_write_quad_ptp_reg_eth56g - Write a PHY quad register + * @hw: pointer to the HW struct + * @offset: PHY register offset + * @port: Port number + * @val: Value to write + * + * Return: + * * %0 - success + * * %EIO - invalid port number or resource type + * * %other - failed to write to PHY + */ +static int ice_write_quad_ptp_reg_eth56g(struct ice_hw *hw, u8 port, + u32 offset, u32 val) +{ + u32 addr; + + if (port >= hw->ptp.num_lports) + return -EIO; + + addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base_addr + offset; + + return ice_write_phy_eth56g(hw, port, addr, val); +} + +/** + * ice_read_quad_ptp_reg_eth56g - Read a PHY quad register + * @hw: pointer to the HW struct + * @offset: PHY register offset + * @port: Port number + * @val: Value to read + * + * Return: + * * %0 - success + * * %EIO - invalid port number or resource type + * * %other - failed to read from PHY + */ +static int ice_read_quad_ptp_reg_eth56g(struct ice_hw *hw, u8 port, + u32 offset, u32 *val) +{ + u32 addr; + + if (port >= hw->ptp.num_lports) + return -EIO; + + addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base_addr + offset; + + return ice_read_phy_eth56g(hw, port, addr, val); +} + +/** + * ice_is_64b_phy_reg_eth56g - Check if this is a 64bit PHY register + * @low_addr: the low address to check + * @high_addr: on return, contains the high address of the 64bit register + * + * Write the appropriate high register offset to use. + * + * Return: true if the provided low address is one of the known 64bit PHY values + * represented as two 32bit registers, false otherwise. + */ +static bool ice_is_64b_phy_reg_eth56g(u16 low_addr, u16 *high_addr) +{ + switch (low_addr) { + case PHY_REG_TX_TIMER_INC_PRE_L: + *high_addr = PHY_REG_TX_TIMER_INC_PRE_U; + return true; + case PHY_REG_RX_TIMER_INC_PRE_L: + *high_addr = PHY_REG_RX_TIMER_INC_PRE_U; + return true; + case PHY_REG_TX_CAPTURE_L: + *high_addr = PHY_REG_TX_CAPTURE_U; + return true; + case PHY_REG_RX_CAPTURE_L: + *high_addr = PHY_REG_RX_CAPTURE_U; + return true; + case PHY_REG_TOTAL_TX_OFFSET_L: + *high_addr = PHY_REG_TOTAL_TX_OFFSET_U; + return true; + case PHY_REG_TOTAL_RX_OFFSET_L: + *high_addr = PHY_REG_TOTAL_RX_OFFSET_U; + return true; + case PHY_REG_TX_MEMORY_STATUS_L: + *high_addr = PHY_REG_TX_MEMORY_STATUS_U; + return true; + default: + return false; + } +} + +/** + * ice_is_40b_phy_reg_eth56g - Check if this is a 40bit PHY register + * @low_addr: the low address to check + * @high_addr: on return, contains the high address of the 40bit value + * + * Write the appropriate high register offset to use. + * + * Return: true if the provided low address is one of the known 40bit PHY + * values split into two registers with the lower 8 bits in the low register and + * the upper 32 bits in the high register, false otherwise. + */ +static bool ice_is_40b_phy_reg_eth56g(u16 low_addr, u16 *high_addr) +{ + switch (low_addr) { + case PHY_REG_TIMETUS_L: + *high_addr = PHY_REG_TIMETUS_U; + return true; + case PHY_PCS_REF_TUS_L: + *high_addr = PHY_PCS_REF_TUS_U; + return true; + case PHY_PCS_REF_INC_L: + *high_addr = PHY_PCS_REF_INC_U; + return true; + default: + return false; + } +} + +/** + * ice_read_64b_phy_reg_eth56g - Read a 64bit value from PHY registers + * @hw: pointer to the HW struct + * @port: PHY port to read from + * @low_addr: offset of the lower register to read from + * @val: on return, the contents of the 64bit value from the PHY registers + * @res_type: resource type + * + * Check if the caller has specified a known 40 bit register offset and read + * the two registers associated with a 40bit value and return it in the val + * pointer. + * + * Return: + * * %0 - success + * * %EINVAL - not a 64 bit register + * * %other - failed to read from PHY + */ +static int ice_read_64b_phy_reg_eth56g(struct ice_hw *hw, u8 port, u16 low_addr, + u64 *val, enum eth56g_res_type res_type) +{ + u16 high_addr; + u32 lo, hi; + int err; + + if (!ice_is_64b_phy_reg_eth56g(low_addr, &high_addr)) + return -EINVAL; + + err = ice_read_port_eth56g(hw, port, low_addr, &lo, res_type); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read from low register %#08x\n, err %d", + low_addr, err); + return err; + } + + err = ice_read_port_eth56g(hw, port, high_addr, &hi, res_type); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read from high register %#08x\n, err %d", + high_addr, err); + return err; + } + + *val = ((u64)hi << 32) | lo; + + return 0; +} + +/** + * ice_read_64b_ptp_reg_eth56g - Read a 64bit value from PHY registers + * @hw: pointer to the HW struct + * @port: PHY port to read from + * @low_addr: offset of the lower register to read from + * @val: on return, the contents of the 64bit value from the PHY registers + * + * Check if the caller has specified a known 40 bit register offset and read + * the two registers associated with a 40bit value and return it in the val + * pointer. + * + * Return: + * * %0 - success + * * %EINVAL - not a 64 bit register + * * %other - failed to read from PHY + */ +static int ice_read_64b_ptp_reg_eth56g(struct ice_hw *hw, u8 port, u16 low_addr, + u64 *val) +{ + return ice_read_64b_phy_reg_eth56g(hw, port, low_addr, val, + ETH56G_PHY_REG_PTP); +} + +/** + * ice_write_40b_phy_reg_eth56g - Write a 40b value to the PHY + * @hw: pointer to the HW struct + * @port: port to write to + * @low_addr: offset of the low register + * @val: 40b value to write + * @res_type: resource type + * + * Check if the caller has specified a known 40 bit register offset and write + * provided 40b value to the two associated registers by splitting it up into + * two chunks, the lower 8 bits and the upper 32 bits. + * + * Return: + * * %0 - success + * * %EINVAL - not a 40 bit register + * * %other - failed to write to PHY + */ +static int ice_write_40b_phy_reg_eth56g(struct ice_hw *hw, u8 port, + u16 low_addr, u64 val, + enum eth56g_res_type res_type) +{ + u16 high_addr; + u32 lo, hi; + int err; + + if (!ice_is_40b_phy_reg_eth56g(low_addr, &high_addr)) + return -EINVAL; + + lo = FIELD_GET(P_REG_40B_LOW_M, val); + hi = (u32)(val >> P_REG_40B_HIGH_S); + + err = ice_write_port_eth56g(hw, port, low_addr, lo, res_type); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write to low register 0x%08x\n, err %d", + low_addr, err); + return err; + } + + err = ice_write_port_eth56g(hw, port, high_addr, hi, res_type); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write to high register 0x%08x\n, err %d", + high_addr, err); + return err; + } + + return 0; +} + +/** + * ice_write_40b_ptp_reg_eth56g - Write a 40b value to the PHY + * @hw: pointer to the HW struct + * @port: port to write to + * @low_addr: offset of the low register + * @val: 40b value to write + * + * Check if the caller has specified a known 40 bit register offset and write + * provided 40b value to the two associated registers by splitting it up into + * two chunks, the lower 8 bits and the upper 32 bits. + * + * Return: + * * %0 - success + * * %EINVAL - not a 40 bit register + * * %other - failed to write to PHY + */ +static int ice_write_40b_ptp_reg_eth56g(struct ice_hw *hw, u8 port, + u16 low_addr, u64 val) +{ + return ice_write_40b_phy_reg_eth56g(hw, port, low_addr, val, + ETH56G_PHY_REG_PTP); +} + +/** + * ice_write_64b_phy_reg_eth56g - Write a 64bit value to PHY registers + * @hw: pointer to the HW struct + * @port: PHY port to read from + * @low_addr: offset of the lower register to read from + * @val: the contents of the 64bit value to write to PHY + * @res_type: resource type + * + * Check if the caller has specified a known 64 bit register offset and write + * the 64bit value to the two associated 32bit PHY registers. + * + * Return: + * * %0 - success + * * %EINVAL - not a 64 bit register + * * %other - failed to write to PHY + */ +static int ice_write_64b_phy_reg_eth56g(struct ice_hw *hw, u8 port, + u16 low_addr, u64 val, + enum eth56g_res_type res_type) +{ + u16 high_addr; + u32 lo, hi; + int err; + + if (!ice_is_64b_phy_reg_eth56g(low_addr, &high_addr)) + return -EINVAL; + + lo = lower_32_bits(val); + hi = upper_32_bits(val); + + err = ice_write_port_eth56g(hw, port, low_addr, lo, res_type); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write to low register 0x%08x\n, err %d", + low_addr, err); + return err; + } + + err = ice_write_port_eth56g(hw, port, high_addr, hi, res_type); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write to high register 0x%08x\n, err %d", + high_addr, err); + return err; + } + + return 0; +} + +/** + * ice_write_64b_ptp_reg_eth56g - Write a 64bit value to PHY registers + * @hw: pointer to the HW struct + * @port: PHY port to read from + * @low_addr: offset of the lower register to read from + * @val: the contents of the 64bit value to write to PHY + * + * Check if the caller has specified a known 64 bit register offset and write + * the 64bit value to the two associated 32bit PHY registers. + * + * Return: + * * %0 - success + * * %EINVAL - not a 64 bit register + * * %other - failed to write to PHY + */ +static int ice_write_64b_ptp_reg_eth56g(struct ice_hw *hw, u8 port, + u16 low_addr, u64 val) +{ + return ice_write_64b_phy_reg_eth56g(hw, port, low_addr, val, + ETH56G_PHY_REG_PTP); +} + +/** + * ice_read_ptp_tstamp_eth56g - Read a PHY timestamp out of the port memory + * @hw: pointer to the HW struct + * @port: the port to read from + * @idx: the timestamp index to read + * @tstamp: on return, the 40bit timestamp value + * + * Read a 40bit timestamp value out of the two associated entries in the + * port memory block of the internal PHYs of the 56G devices. + * + * Return: + * * %0 - success + * * %other - failed to read from PHY + */ +static int ice_read_ptp_tstamp_eth56g(struct ice_hw *hw, u8 port, u8 idx, + u64 *tstamp) +{ + u16 lo_addr, hi_addr; + u32 lo, hi; + int err; + + lo_addr = (u16)PHY_TSTAMP_L(idx); + hi_addr = (u16)PHY_TSTAMP_U(idx); + + err = ice_read_port_mem_eth56g(hw, port, lo_addr, &lo); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read low PTP timestamp register, err %d\n", + err); + return err; + } + + err = ice_read_port_mem_eth56g(hw, port, hi_addr, &hi); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read high PTP timestamp register, err %d\n", + err); + return err; + } + + /* For 56G based internal PHYs, the timestamp is reported with the + * lower 8 bits in the low register, and the upper 32 bits in the high + * register. + */ + *tstamp = FIELD_PREP(PHY_40B_HIGH_M, hi) | + FIELD_PREP(PHY_40B_LOW_M, lo); + return 0; +} + +/** + * ice_clear_ptp_tstamp_eth56g - Clear a timestamp from the quad block + * @hw: pointer to the HW struct + * @port: the quad to read from + * @idx: the timestamp index to reset + * + * Read and then forcibly clear the timestamp index to ensure the valid bit is + * cleared and the timestamp status bit is reset in the PHY port memory of + * internal PHYs of the 56G devices. + * + * 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_eth56g(). + * + * This function should only be called on an idx whose bit is set according to + * ice_get_phy_tx_tstamp_ready(). + * + * Return: + * * %0 - success + * * %other - failed to write to PHY + */ +static int ice_clear_ptp_tstamp_eth56g(struct ice_hw *hw, u8 port, u8 idx) +{ + u64 unused_tstamp; + u16 lo_addr; + int err; + + /* Read the timestamp register to ensure the timestamp status bit is + * cleared. + */ + err = ice_read_ptp_tstamp_eth56g(hw, port, idx, &unused_tstamp); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read the PHY timestamp register for port %u, idx %u, err %d\n", + port, idx, err); + } + + lo_addr = (u16)PHY_TSTAMP_L(idx); + + err = ice_write_port_mem_eth56g(hw, port, lo_addr, 0); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to clear low PTP timestamp register for port %u, idx %u, err %d\n", + port, idx, err); + return err; + } + + return 0; +} + +/** + * ice_ptp_reset_ts_memory_eth56g - Clear all timestamps from the port block + * @hw: pointer to the HW struct + */ +static void ice_ptp_reset_ts_memory_eth56g(struct ice_hw *hw) +{ + unsigned int port; + + for (port = 0; port < hw->ptp.num_lports; port++) { + ice_write_ptp_reg_eth56g(hw, port, PHY_REG_TX_MEMORY_STATUS_L, + 0); + ice_write_ptp_reg_eth56g(hw, port, PHY_REG_TX_MEMORY_STATUS_U, + 0); + } +} + +/** + * ice_ptp_prep_port_time_eth56g - Prepare one PHY port with initial time + * @hw: pointer to the HW struct + * @port: port number + * @time: time to initialize the PHY port clocks to + * + * Write a new initial time value into registers of a specific PHY port. + * + * Return: + * * %0 - success + * * %other - failed to write to PHY + */ +static int ice_ptp_prep_port_time_eth56g(struct ice_hw *hw, u8 port, + u64 time) +{ + int err; + + /* Tx case */ + err = ice_write_64b_ptp_reg_eth56g(hw, port, PHY_REG_TX_TIMER_INC_PRE_L, + time); + if (err) + return err; + + /* Rx case */ + return ice_write_64b_ptp_reg_eth56g(hw, port, + PHY_REG_RX_TIMER_INC_PRE_L, time); +} + +/** + * ice_ptp_prep_phy_time_eth56g - Prepare PHY port with initial time + * @hw: pointer to the HW struct + * @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 ICE_PTP_INIT_TIME sync + * command. The time value is the upper 32 bits of the PHY timer, usually in + * units of nominal nanoseconds. + * + * Return: + * * %0 - success + * * %other - failed to write to PHY + */ +static int ice_ptp_prep_phy_time_eth56g(struct ice_hw *hw, u32 time) +{ + u64 phy_time; + u8 port; + + /* The time represents the upper 32 bits of the PHY timer, so we need + * to shift to account for this when programming. + */ + phy_time = (u64)time << 32; + + for (port = 0; port < hw->ptp.num_lports; port++) { + int err; + + err = ice_ptp_prep_port_time_eth56g(hw, port, phy_time); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write init time for port %u, err %d\n", + port, err); + return err; + } + } + + return 0; +} + +/** + * ice_ptp_prep_port_adj_eth56g - Prepare a single port for time adjust + * @hw: pointer to HW struct + * @port: Port number to be programmed + * @time: time in cycles to adjust the port clocks + * + * 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 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. + * + * Return: + * * %0 - success + * * %other - failed to write to PHY + */ +static int ice_ptp_prep_port_adj_eth56g(struct ice_hw *hw, u8 port, s64 time) +{ + u32 l_time, u_time; + int err; + + l_time = lower_32_bits(time); + u_time = upper_32_bits(time); + + /* Tx case */ + err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_TX_TIMER_INC_PRE_L, + l_time); + if (err) + goto exit_err; + + err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_TX_TIMER_INC_PRE_U, + u_time); + if (err) + goto exit_err; + + /* Rx case */ + err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_RX_TIMER_INC_PRE_L, + l_time); + if (err) + goto exit_err; + + err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_RX_TIMER_INC_PRE_U, + u_time); + if (err) + goto exit_err; + + return 0; + +exit_err: + ice_debug(hw, ICE_DBG_PTP, "Failed to write time adjust for port %u, err %d\n", + port, err); + return err; +} + +/** + * ice_ptp_prep_phy_adj_eth56g - Prep PHY ports for a time adjustment + * @hw: pointer to HW struct + * @adj: adjustment in nanoseconds + * + * 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 + * ICE_PTP_ADJ_TIME or ICE_PTP_ADJ_TIME_AT_TIME sync command. + * + * Return: + * * %0 - success + * * %other - failed to write to PHY + */ +static int ice_ptp_prep_phy_adj_eth56g(struct ice_hw *hw, s32 adj) +{ + s64 cycles; + u8 port; + + /* The port clock supports adjustment of the sub-nanosecond portion of + * the clock (lowest 32 bits). We shift the provided adjustment in + * nanoseconds by 32 to calculate the appropriate adjustment to program + * into the PHY ports. + */ + cycles = (s64)adj << 32; + + for (port = 0; port < hw->ptp.num_lports; port++) { + int err; + + err = ice_ptp_prep_port_adj_eth56g(hw, port, cycles); + if (err) + return err; + } + + return 0; +} + +/** + * ice_ptp_prep_phy_incval_eth56g - Prepare PHY ports for time adjustment + * @hw: pointer to HW struct + * @incval: new increment value to prepare + * + * 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 ICE_PTP_INIT_INCVAL command. + * + * Return: + * * %0 - success + * * %other - failed to write to PHY + */ +static int ice_ptp_prep_phy_incval_eth56g(struct ice_hw *hw, u64 incval) +{ + u8 port; + + for (port = 0; port < hw->ptp.num_lports; port++) { + int err; + + err = ice_write_40b_ptp_reg_eth56g(hw, port, PHY_REG_TIMETUS_L, + incval); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write incval for port %u, err %d\n", + port, err); + return err; + } + } + + return 0; +} + +/** + * ice_ptp_read_port_capture_eth56g - Read a port's local time capture + * @hw: pointer to HW struct + * @port: Port number to read + * @tx_ts: on return, the Tx port time capture + * @rx_ts: on return, the Rx port time capture + * + * Read the port's Tx and Rx local time capture values. + * + * Return: + * * %0 - success + * * %other - failed to read from PHY + */ +static int ice_ptp_read_port_capture_eth56g(struct ice_hw *hw, u8 port, + u64 *tx_ts, u64 *rx_ts) +{ + int err; + + /* Tx case */ + err = ice_read_64b_ptp_reg_eth56g(hw, port, PHY_REG_TX_CAPTURE_L, + tx_ts); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read REG_TX_CAPTURE, err %d\n", + err); + return err; + } + + ice_debug(hw, ICE_DBG_PTP, "tx_init = %#016llx\n", *tx_ts); + + /* Rx case */ + err = ice_read_64b_ptp_reg_eth56g(hw, port, PHY_REG_RX_CAPTURE_L, + rx_ts); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read RX_CAPTURE, err %d\n", + err); + return err; + } + + ice_debug(hw, ICE_DBG_PTP, "rx_init = %#016llx\n", *rx_ts); + + return 0; +} + +/** + * ice_ptp_write_port_cmd_eth56g - 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. + * + * Return: + * * %0 - success + * * %other - failed to write to PHY + */ +static int ice_ptp_write_port_cmd_eth56g(struct ice_hw *hw, u8 port, + enum ice_ptp_tmr_cmd cmd) +{ + u32 val = ice_ptp_tmr_cmd_to_port_reg(hw, cmd); + int err; + + /* Tx case */ + err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_TX_TMR_CMD, val); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write back TX_TMR_CMD, err %d\n", + err); + return err; + } + + /* Rx case */ + err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_RX_TMR_CMD, val); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write back RX_TMR_CMD, err %d\n", + err); + return err; + } + + return 0; +} + +/** + * ice_phy_get_speed_eth56g - Get link speed based on PHY link type + * @li: pointer to link information struct + * + * Return: simplified ETH56G PHY speed + */ +static enum ice_eth56g_link_spd +ice_phy_get_speed_eth56g(struct ice_link_status *li) +{ + u16 speed = ice_get_link_speed_based_on_phy_type(li->phy_type_low, + li->phy_type_high); + + switch (speed) { + case ICE_AQ_LINK_SPEED_1000MB: + return ICE_ETH56G_LNK_SPD_1G; + case ICE_AQ_LINK_SPEED_2500MB: + return ICE_ETH56G_LNK_SPD_2_5G; + case ICE_AQ_LINK_SPEED_10GB: + return ICE_ETH56G_LNK_SPD_10G; + case ICE_AQ_LINK_SPEED_25GB: + return ICE_ETH56G_LNK_SPD_25G; + case ICE_AQ_LINK_SPEED_40GB: + return ICE_ETH56G_LNK_SPD_40G; + case ICE_AQ_LINK_SPEED_50GB: + switch (li->phy_type_low) { + case ICE_PHY_TYPE_LOW_50GBASE_SR: + case ICE_PHY_TYPE_LOW_50GBASE_FR: + case ICE_PHY_TYPE_LOW_50GBASE_LR: + case ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4: + case ICE_PHY_TYPE_LOW_50G_AUI1_AOC_ACC: + case ICE_PHY_TYPE_LOW_50G_AUI1: + return ICE_ETH56G_LNK_SPD_50G; + default: + return ICE_ETH56G_LNK_SPD_50G2; + } + case ICE_AQ_LINK_SPEED_100GB: + if (li->phy_type_high || + li->phy_type_low == ICE_PHY_TYPE_LOW_100GBASE_SR2) + return ICE_ETH56G_LNK_SPD_100G2; + else + return ICE_ETH56G_LNK_SPD_100G; + default: + return ICE_ETH56G_LNK_SPD_1G; + } +} + +/** + * ice_phy_cfg_parpcs_eth56g - Configure TUs per PAR/PCS clock cycle + * @hw: pointer to the HW struct + * @port: port to configure + * + * Configure the number of TUs for the PAR and PCS clocks used as part of the + * timestamp calibration process. + * + * Return: + * * %0 - success + * * %other - PHY read/write failed + */ +static int ice_phy_cfg_parpcs_eth56g(struct ice_hw *hw, u8 port) +{ + u32 val; + int err; + + err = ice_write_xpcs_reg_eth56g(hw, port, PHY_VENDOR_TXLANE_THRESH, + ICE_ETH56G_NOMINAL_THRESH4); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read VENDOR_TXLANE_THRESH, status: %d", + err); + return err; + } + + switch (ice_phy_get_speed_eth56g(&hw->port_info->phy.link_info)) { + case ICE_ETH56G_LNK_SPD_1G: + case ICE_ETH56G_LNK_SPD_2_5G: + err = ice_read_quad_ptp_reg_eth56g(hw, port, + PHY_GPCS_CONFIG_REG0, &val); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read PHY_GPCS_CONFIG_REG0, status: %d", + err); + return err; + } + + val &= ~PHY_GPCS_CONFIG_REG0_TX_THR_M; + val |= FIELD_PREP(PHY_GPCS_CONFIG_REG0_TX_THR_M, + ICE_ETH56G_NOMINAL_TX_THRESH); + + err = ice_write_quad_ptp_reg_eth56g(hw, port, + PHY_GPCS_CONFIG_REG0, val); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write PHY_GPCS_CONFIG_REG0, status: %d", + err); + return err; + } + break; + default: + break; + } + + err = ice_write_40b_ptp_reg_eth56g(hw, port, PHY_PCS_REF_TUS_L, + ICE_ETH56G_NOMINAL_PCS_REF_TUS); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write PHY_PCS_REF_TUS, status: %d", + err); + return err; + } + + err = ice_write_40b_ptp_reg_eth56g(hw, port, PHY_PCS_REF_INC_L, + ICE_ETH56G_NOMINAL_PCS_REF_INC); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write PHY_PCS_REF_INC, status: %d", + err); + return err; + } + + return 0; +} + +/** + * ice_phy_cfg_ptp_1step_eth56g - Configure 1-step PTP settings + * @hw: Pointer to the HW struct + * @port: Port to configure + * + * Return: + * * %0 - success + * * %other - PHY read/write failed + */ +int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port) +{ + u8 quad_lane = port % ICE_PORTS_PER_QUAD; + u32 addr, val, peer_delay; + bool enable, sfd_ena; + int err; + + enable = hw->ptp.phy.eth56g.onestep_ena; + peer_delay = hw->ptp.phy.eth56g.peer_delay; + sfd_ena = hw->ptp.phy.eth56g.sfd_ena; + + addr = PHY_PTP_1STEP_CONFIG; + err = ice_read_quad_ptp_reg_eth56g(hw, port, addr, &val); + if (err) + return err; + + if (enable) + val |= BIT(quad_lane); + else + val &= ~BIT(quad_lane); + + val &= ~(PHY_PTP_1STEP_T1S_UP64_M | PHY_PTP_1STEP_T1S_DELTA_M); + + err = ice_write_quad_ptp_reg_eth56g(hw, port, addr, val); + if (err) + return err; + + addr = PHY_PTP_1STEP_PEER_DELAY(quad_lane); + val = FIELD_PREP(PHY_PTP_1STEP_PD_DELAY_M, peer_delay); + if (peer_delay) + val |= PHY_PTP_1STEP_PD_ADD_PD_M; + val |= PHY_PTP_1STEP_PD_DLY_V_M; + err = ice_write_quad_ptp_reg_eth56g(hw, port, addr, val); + if (err) + return err; + + val &= ~PHY_PTP_1STEP_PD_DLY_V_M; + err = ice_write_quad_ptp_reg_eth56g(hw, port, addr, val); + if (err) + return err; + + addr = PHY_MAC_XIF_MODE; + err = ice_read_mac_reg_eth56g(hw, port, addr, &val); + if (err) + return err; + + val &= ~(PHY_MAC_XIF_1STEP_ENA_M | PHY_MAC_XIF_TS_BIN_MODE_M | + PHY_MAC_XIF_TS_SFD_ENA_M | PHY_MAC_XIF_GMII_TS_SEL_M); + + switch (ice_phy_get_speed_eth56g(&hw->port_info->phy.link_info)) { + case ICE_ETH56G_LNK_SPD_1G: + case ICE_ETH56G_LNK_SPD_2_5G: + val |= PHY_MAC_XIF_GMII_TS_SEL_M; + break; + default: + break; + } + + val |= FIELD_PREP(PHY_MAC_XIF_1STEP_ENA_M, enable) | + FIELD_PREP(PHY_MAC_XIF_TS_BIN_MODE_M, enable) | + FIELD_PREP(PHY_MAC_XIF_TS_SFD_ENA_M, sfd_ena); + + return ice_write_mac_reg_eth56g(hw, port, addr, val); +} + +/** + * mul_u32_u32_fx_q9 - Multiply two u32 fixed point Q9 values + * @a: multiplier value + * @b: multiplicand value + * + * Return: result of multiplication + */ +static u32 mul_u32_u32_fx_q9(u32 a, u32 b) +{ + return (u32)(((u64)a * b) >> ICE_ETH56G_MAC_CFG_FRAC_W); +} + +/** + * add_u32_u32_fx - Add two u32 fixed point values and discard overflow + * @a: first value + * @b: second value + * + * Return: result of addition + */ +static u32 add_u32_u32_fx(u32 a, u32 b) +{ + return lower_32_bits(((u64)a + b)); +} + +/** + * ice_ptp_calc_bitslip_eth56g - Calculate bitslip value + * @hw: pointer to the HW struct + * @port: port to configure + * @bs: bitslip multiplier + * @fc: FC-FEC enabled + * @rs: RS-FEC enabled + * @spd: link speed + * + * Return: calculated bitslip value + */ +static u32 ice_ptp_calc_bitslip_eth56g(struct ice_hw *hw, u8 port, u32 bs, + bool fc, bool rs, + enum ice_eth56g_link_spd spd) +{ + u32 bitslip; + int err; + + if (!bs || rs) + return 0; + + if (spd == ICE_ETH56G_LNK_SPD_1G || spd == ICE_ETH56G_LNK_SPD_2_5G) { + err = ice_read_gpcs_reg_eth56g(hw, port, PHY_GPCS_BITSLIP, + &bitslip); + } else { + u8 quad_lane = port % ICE_PORTS_PER_QUAD; + u32 addr; + + addr = PHY_REG_SD_BIT_SLIP(quad_lane); + err = ice_read_quad_ptp_reg_eth56g(hw, port, addr, &bitslip); + } + if (err) + return 0; + + if (spd == ICE_ETH56G_LNK_SPD_1G && !bitslip) { + /* Bitslip register value of 0 corresponds to 10 so substitute + * it for calculations + */ + bitslip = 10; + } else if (spd == ICE_ETH56G_LNK_SPD_10G || + spd == ICE_ETH56G_LNK_SPD_25G) { + if (fc) + bitslip = bitslip * 2 + 32; + else + bitslip = (u32)((s32)bitslip * -1 + 20); + } + + bitslip <<= ICE_ETH56G_MAC_CFG_FRAC_W; + return mul_u32_u32_fx_q9(bitslip, bs); +} + +/** + * ice_ptp_calc_deskew_eth56g - Calculate deskew value + * @hw: pointer to the HW struct + * @port: port to configure + * @ds: deskew multiplier + * @rs: RS-FEC enabled + * @spd: link speed + * + * Return: calculated deskew value + */ +static u32 ice_ptp_calc_deskew_eth56g(struct ice_hw *hw, u8 port, u32 ds, + bool rs, enum ice_eth56g_link_spd spd) +{ + u32 deskew_i, deskew_f; + int err; + + if (!ds) + return 0; + + read_poll_timeout(ice_read_ptp_reg_eth56g, err, + FIELD_GET(PHY_REG_DESKEW_0_VALID, deskew_i), 500, + 50 * USEC_PER_MSEC, false, hw, port, PHY_REG_DESKEW_0, + &deskew_i); + if (err) + return err; + + deskew_f = FIELD_GET(PHY_REG_DESKEW_0_RLEVEL_FRAC, deskew_i); + deskew_i = FIELD_GET(PHY_REG_DESKEW_0_RLEVEL, deskew_i); + + if (rs && spd == ICE_ETH56G_LNK_SPD_50G2) + ds = 0x633; /* 3.1 */ + else if (rs && spd == ICE_ETH56G_LNK_SPD_100G) + ds = 0x31b; /* 1.552 */ + + deskew_i = FIELD_PREP(ICE_ETH56G_MAC_CFG_RX_OFFSET_INT, deskew_i); + /* Shift 3 fractional bits to the end of the integer part */ + deskew_f <<= ICE_ETH56G_MAC_CFG_FRAC_W - PHY_REG_DESKEW_0_RLEVEL_FRAC_W; + return mul_u32_u32_fx_q9(deskew_i | deskew_f, ds); +} + +/** + * ice_phy_set_offsets_eth56g - Set Tx/Rx offset values + * @hw: pointer to the HW struct + * @port: port to configure + * @spd: link speed + * @cfg: structure to store output values + * @fc: FC-FEC enabled + * @rs: RS-FEC enabled + * + * Return: + * * %0 - success + * * %other - failed to write to PHY + */ +static int ice_phy_set_offsets_eth56g(struct ice_hw *hw, u8 port, + enum ice_eth56g_link_spd spd, + const struct ice_eth56g_mac_reg_cfg *cfg, + bool fc, bool rs) +{ + u32 rx_offset, tx_offset, bs_ds; + bool onestep, sfd; + + onestep = hw->ptp.phy.eth56g.onestep_ena; + sfd = hw->ptp.phy.eth56g.sfd_ena; + bs_ds = cfg->rx_offset.bs_ds; + + if (fc) + rx_offset = cfg->rx_offset.fc; + else if (rs) + rx_offset = cfg->rx_offset.rs; + else + rx_offset = cfg->rx_offset.no_fec; + + rx_offset = add_u32_u32_fx(rx_offset, cfg->rx_offset.serdes); + if (sfd) + rx_offset = add_u32_u32_fx(rx_offset, cfg->rx_offset.sfd); + + if (spd < ICE_ETH56G_LNK_SPD_40G) + bs_ds = ice_ptp_calc_bitslip_eth56g(hw, port, bs_ds, fc, rs, + spd); + else + bs_ds = ice_ptp_calc_deskew_eth56g(hw, port, bs_ds, rs, spd); + rx_offset = add_u32_u32_fx(rx_offset, bs_ds); + rx_offset &= ICE_ETH56G_MAC_CFG_RX_OFFSET_INT | + ICE_ETH56G_MAC_CFG_RX_OFFSET_FRAC; + + if (fc) + tx_offset = cfg->tx_offset.fc; + else if (rs) + tx_offset = cfg->tx_offset.rs; + else + tx_offset = cfg->tx_offset.no_fec; + tx_offset += cfg->tx_offset.serdes + cfg->tx_offset.sfd * sfd + + cfg->tx_offset.onestep * onestep; + + ice_write_mac_reg_eth56g(hw, port, PHY_MAC_RX_OFFSET, rx_offset); + return ice_write_mac_reg_eth56g(hw, port, PHY_MAC_TX_OFFSET, tx_offset); +} + +/** + * ice_phy_cfg_mac_eth56g - Configure MAC for PTP + * @hw: Pointer to the HW struct + * @port: Port to configure + * + * Return: + * * %0 - success + * * %other - failed to write to PHY + */ +static int ice_phy_cfg_mac_eth56g(struct ice_hw *hw, u8 port) +{ + const struct ice_eth56g_mac_reg_cfg *cfg; + enum ice_eth56g_link_spd spd; + struct ice_link_status *li; + bool fc = false; + bool rs = false; + bool onestep; + u32 val; + int err; + + onestep = hw->ptp.phy.eth56g.onestep_ena; + li = &hw->port_info->phy.link_info; + spd = ice_phy_get_speed_eth56g(li); + if (!!(li->an_info & ICE_AQ_FEC_EN)) { + if (spd == ICE_ETH56G_LNK_SPD_10G) { + fc = true; + } else { + fc = !!(li->fec_info & ICE_AQ_LINK_25G_KR_FEC_EN); + rs = !!(li->fec_info & ~ICE_AQ_LINK_25G_KR_FEC_EN); + } + } + cfg = ð56g_mac_cfg[spd]; + + err = ice_write_mac_reg_eth56g(hw, port, PHY_MAC_RX_MODULO, 0); + if (err) + return err; + + err = ice_write_mac_reg_eth56g(hw, port, PHY_MAC_TX_MODULO, 0); + if (err) + return err; + + val = FIELD_PREP(PHY_MAC_TSU_CFG_TX_MODE_M, + cfg->tx_mode.def + rs * cfg->tx_mode.rs) | + FIELD_PREP(PHY_MAC_TSU_CFG_TX_MII_MK_DLY_M, cfg->tx_mk_dly) | + FIELD_PREP(PHY_MAC_TSU_CFG_TX_MII_CW_DLY_M, + cfg->tx_cw_dly.def + + onestep * cfg->tx_cw_dly.onestep) | + FIELD_PREP(PHY_MAC_TSU_CFG_RX_MODE_M, + cfg->rx_mode.def + rs * cfg->rx_mode.rs) | + FIELD_PREP(PHY_MAC_TSU_CFG_RX_MII_MK_DLY_M, + cfg->rx_mk_dly.def + rs * cfg->rx_mk_dly.rs) | + FIELD_PREP(PHY_MAC_TSU_CFG_RX_MII_CW_DLY_M, + cfg->rx_cw_dly.def + rs * cfg->rx_cw_dly.rs) | + FIELD_PREP(PHY_MAC_TSU_CFG_BLKS_PER_CLK_M, cfg->blks_per_clk); + err = ice_write_mac_reg_eth56g(hw, port, PHY_MAC_TSU_CONFIG, val); + if (err) + return err; + + err = ice_write_mac_reg_eth56g(hw, port, PHY_MAC_BLOCKTIME, + cfg->blktime); + if (err) + return err; + + err = ice_phy_set_offsets_eth56g(hw, port, spd, cfg, fc, rs); + if (err) + return err; + + if (spd == ICE_ETH56G_LNK_SPD_25G && !rs) + val = 0; + else + val = cfg->mktime; + + return ice_write_mac_reg_eth56g(hw, port, PHY_MAC_MARKERTIME, val); +} + +/** + * ice_phy_cfg_intr_eth56g - Configure TX timestamp interrupt + * @hw: pointer to the HW struct + * @port: the timestamp port + * @ena: enable or disable interrupt + * @threshold: interrupt threshold + * + * Configure TX timestamp interrupt for the specified port + * + * Return: + * * %0 - success + * * %other - PHY read/write failed + */ +int ice_phy_cfg_intr_eth56g(struct ice_hw *hw, u8 port, bool ena, u8 threshold) +{ + int err; + u32 val; + + err = ice_read_ptp_reg_eth56g(hw, port, PHY_REG_TS_INT_CONFIG, &val); + if (err) + return err; + + if (ena) { + val |= PHY_TS_INT_CONFIG_ENA_M; + val &= ~PHY_TS_INT_CONFIG_THRESHOLD_M; + val |= FIELD_PREP(PHY_TS_INT_CONFIG_THRESHOLD_M, threshold); + } else { + val &= ~PHY_TS_INT_CONFIG_ENA_M; + } + + return ice_write_ptp_reg_eth56g(hw, port, PHY_REG_TS_INT_CONFIG, val); +} + +/** + * ice_read_phy_and_phc_time_eth56g - Simultaneously capture PHC and PHY time + * @hw: pointer to the HW struct + * @port: the PHY port to read + * @phy_time: on return, the 64bit PHY timer value + * @phc_time: on return, the lower 64bits of PHC time + * + * Issue a ICE_PTP_READ_TIME timer command to simultaneously capture the PHY + * and PHC timer values. + * + * Return: + * * %0 - success + * * %other - PHY read/write failed + */ +static int ice_read_phy_and_phc_time_eth56g(struct ice_hw *hw, u8 port, + u64 *phy_time, u64 *phc_time) +{ + struct ice_pf *pf = container_of(hw, struct ice_pf, hw); + u64 tx_time, rx_time; + u32 zo, lo; + u8 tmr_idx; + int err; + + tmr_idx = ice_get_ptp_src_clock_index(hw); + + /* 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 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 ICE_PTP_READ_TIME capture */ + ice_ptp_exec_tmr_cmd(hw); + + /* Read the captured PHC time from the shadow time registers */ + if (ice_is_primary(hw)) { + zo = rd32(hw, GLTSYN_SHTIME_0(tmr_idx)); + lo = rd32(hw, GLTSYN_SHTIME_L(tmr_idx)); + } else { + zo = rd32(ice_get_primary_hw(pf), GLTSYN_SHTIME_0(tmr_idx)); + lo = rd32(ice_get_primary_hw(pf), GLTSYN_SHTIME_L(tmr_idx)); + } + *phc_time = (u64)lo << 32 | zo; + + /* Read the captured PHY time from the PHY shadow registers */ + err = ice_ptp_read_port_capture_eth56g(hw, port, &tx_time, &rx_time); + if (err) + return err; + + /* If the PHY Tx and Rx timers don't match, log a warning message. + * Note that this should not happen in normal circumstances since the + * driver always programs them together. + */ + if (tx_time != rx_time) + dev_warn(ice_hw_to_dev(hw), "PHY port %u Tx and Rx timers do not match, tx_time 0x%016llX, rx_time 0x%016llX\n", + port, tx_time, rx_time); + + *phy_time = tx_time; + + return 0; +} + +/** + * ice_sync_phy_timer_eth56g - Synchronize the PHY timer with PHC timer + * @hw: pointer to the HW struct + * @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 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. + * + * Return: + * * %0 - success + * * %-EBUSY- failed to acquire PTP semaphore + * * %other - PHY read/write failed + */ +static int ice_sync_phy_timer_eth56g(struct ice_hw *hw, u8 port) +{ + u64 phc_time, phy_time, difference; + int err; + + if (!ice_ptp_lock(hw)) { + ice_debug(hw, ICE_DBG_PTP, "Failed to acquire PTP semaphore\n"); + return -EBUSY; + } + + err = ice_read_phy_and_phc_time_eth56g(hw, port, &phy_time, &phc_time); + if (err) + goto err_unlock; + + /* Calculate the amount required to add to the port time in order for + * it to match the PHC time. + * + * Note that the port adjustment is done using 2s complement + * arithmetic. This is convenient since it means that we can simply + * calculate the difference between the PHC time and the port time, + * and it will be interpreted correctly. + */ + + ice_ptp_src_cmd(hw, ICE_PTP_NOP); + difference = phc_time - phy_time; + + err = ice_ptp_prep_port_adj_eth56g(hw, port, (s64)difference); + if (err) + goto err_unlock; + + err = ice_ptp_one_port_cmd(hw, port, ICE_PTP_ADJ_TIME); + if (err) + goto err_unlock; + + /* Issue the sync to activate the time adjustment */ + ice_ptp_exec_tmr_cmd(hw); + + /* Re-capture the timer values to flush the command registers and + * verify that the time was properly adjusted. + */ + err = ice_read_phy_and_phc_time_eth56g(hw, port, &phy_time, &phc_time); + if (err) + goto err_unlock; + + dev_info(ice_hw_to_dev(hw), + "Port %u PHY time synced to PHC: 0x%016llX, 0x%016llX\n", + port, phy_time, phc_time); + +err_unlock: + ice_ptp_unlock(hw); + return err; +} + +/** + * ice_stop_phy_timer_eth56g - Stop the PHY clock timer + * @hw: pointer to the HW struct + * @port: the PHY port to stop + * @soft_reset: if true, hold the SOFT_RESET bit of PHY_REG_PS + * + * Stop the clock of a PHY port. This must be done as part of the flow to + * re-calibrate Tx and Rx timestamping offsets whenever the clock time is + * initialized or when link speed changes. + * + * Return: + * * %0 - success + * * %other - failed to write to PHY + */ +int ice_stop_phy_timer_eth56g(struct ice_hw *hw, u8 port, bool soft_reset) +{ + int err; + + err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_TX_OFFSET_READY, 0); + if (err) + return err; + + err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_RX_OFFSET_READY, 0); + if (err) + return err; + + ice_debug(hw, ICE_DBG_PTP, "Disabled clock on PHY port %u\n", port); + + return 0; +} + +/** + * ice_start_phy_timer_eth56g - Start the PHY clock timer + * @hw: pointer to the HW struct + * @port: the PHY port to start + * + * Start the clock of a PHY port. This must be done as part of the flow to + * re-calibrate Tx and Rx timestamping offsets whenever the clock time is + * initialized or when link speed changes. + * + * Return: + * * %0 - success + * * %other - PHY read/write failed + */ +int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port) +{ + struct ice_pf *pf = container_of(hw, struct ice_pf, hw); + u32 lo, hi; + u64 incval; + u8 tmr_idx; + int err; + + tmr_idx = ice_get_ptp_src_clock_index(hw); + + err = ice_stop_phy_timer_eth56g(hw, port, false); + if (err) + return err; + + ice_ptp_src_cmd(hw, ICE_PTP_NOP); + + err = ice_phy_cfg_parpcs_eth56g(hw, port); + if (err) + return err; + + err = ice_phy_cfg_ptp_1step_eth56g(hw, port); + if (err) + return err; + + err = ice_phy_cfg_mac_eth56g(hw, port); + if (err) + return err; + + if (ice_is_primary(hw)) { + lo = rd32(hw, GLTSYN_INCVAL_L(tmr_idx)); + hi = rd32(hw, GLTSYN_INCVAL_H(tmr_idx)); + } else { + lo = rd32(ice_get_primary_hw(pf), GLTSYN_INCVAL_L(tmr_idx)); + hi = rd32(ice_get_primary_hw(pf), GLTSYN_INCVAL_H(tmr_idx)); + } + incval = (u64)hi << 32 | lo; + + err = ice_write_40b_ptp_reg_eth56g(hw, port, PHY_REG_TIMETUS_L, incval); + if (err) + return err; + + err = ice_ptp_one_port_cmd(hw, port, ICE_PTP_INIT_INCVAL); + if (err) + return err; + + ice_ptp_exec_tmr_cmd(hw); + + err = ice_sync_phy_timer_eth56g(hw, port); + if (err) + return err; + + err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_TX_OFFSET_READY, 1); + if (err) + return err; + + err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_RX_OFFSET_READY, 1); + if (err) + return err; + + ice_debug(hw, ICE_DBG_PTP, "Enabled clock on PHY port %u\n", port); + + return 0; +} + +/** + * ice_ptp_init_phc_e825 - Perform E825 specific PHC initialization + * @hw: pointer to HW struct + * + * Perform E825-specific PTP hardware clock initialization steps. + * + * Return: 0 on success, negative error code otherwise. + */ +static int ice_ptp_init_phc_e825(struct ice_hw *hw) +{ + /* Initialize the Clock Generation Unit */ + return ice_init_cgu_e82x(hw); +} + +/** + * ice_ptp_read_tx_hwtstamp_status_eth56g - Get TX timestamp status + * @hw: pointer to the HW struct + * @ts_status: the timestamp mask pointer + * + * Read the PHY Tx timestamp status mask indicating which ports have Tx + * timestamps available. + * + * Return: + * * %0 - success + * * %other - failed to read from PHY + */ +int ice_ptp_read_tx_hwtstamp_status_eth56g(struct ice_hw *hw, u32 *ts_status) +{ + const struct ice_eth56g_params *params = &hw->ptp.phy.eth56g; + u8 phy, mask; + u32 status; + + mask = (1 << hw->ptp.ports_per_phy) - 1; + *ts_status = 0; + + for (phy = 0; phy < params->num_phys; phy++) { + int err; + + err = ice_read_phy_eth56g(hw, phy, PHY_PTP_INT_STATUS, &status); + if (err) + return err; + + *ts_status |= (status & mask) << (phy * hw->ptp.ports_per_phy); + } + + ice_debug(hw, ICE_DBG_PTP, "PHY interrupt err: %x\n", *ts_status); + + return 0; +} + +/** + * ice_get_phy_tx_tstamp_ready_eth56g - Read the Tx memory status register + * @hw: pointer to the HW struct + * @port: the PHY port to read from + * @tstamp_ready: contents of the Tx memory status register + * + * Read the PHY_REG_TX_MEMORY_STATUS register indicating which timestamps in + * the PHY are ready. A set bit means the corresponding timestamp is valid and + * ready to be captured from the PHY timestamp block. + * + * Return: + * * %0 - success + * * %other - failed to read from PHY + */ +static int ice_get_phy_tx_tstamp_ready_eth56g(struct ice_hw *hw, u8 port, + u64 *tstamp_ready) +{ + int err; + + err = ice_read_64b_ptp_reg_eth56g(hw, port, PHY_REG_TX_MEMORY_STATUS_L, + tstamp_ready); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read TX_MEMORY_STATUS for port %u, err %d\n", + port, err); + return err; + } + + return 0; +} + +/** + * ice_ptp_init_phy_e825 - initialize PHY parameters + * @hw: pointer to the HW struct + */ +static void ice_ptp_init_phy_e825(struct ice_hw *hw) +{ + struct ice_ptp_hw *ptp = &hw->ptp; + struct ice_eth56g_params *params; + + params = &ptp->phy.eth56g; + params->onestep_ena = false; + params->peer_delay = 0; + params->sfd_ena = false; + params->num_phys = 2; + ptp->ports_per_phy = 4; + ptp->num_lports = params->num_phys * ptp->ports_per_phy; +} + /* E822 family functions * * The following functions operate on the E822 family of devices. @@ -285,18 +2762,20 @@ static void ice_ptp_exec_tmr_cmd(struct ice_hw *hw) /** * ice_fill_phy_msg_e82x - Fill message data for a PHY register access + * @hw: pointer to the HW struct * @msg: the PHY message buffer to fill in * @port: the port to access * @offset: the register offset */ -static void -ice_fill_phy_msg_e82x(struct ice_sbq_msg_input *msg, u8 port, u16 offset) +static void ice_fill_phy_msg_e82x(struct ice_hw *hw, + struct ice_sbq_msg_input *msg, u8 port, + u16 offset) { - int phy_port, phy, quadtype; + int phy_port, quadtype; - phy_port = port % ICE_PORTS_PER_PHY_E82X; - phy = port / ICE_PORTS_PER_PHY_E82X; - quadtype = (port / ICE_PORTS_PER_QUAD) % ICE_QUADS_PER_PHY_E82X; + phy_port = port % hw->ptp.ports_per_phy; + quadtype = ICE_GET_QUAD_NUM(port) % + ICE_GET_QUAD_NUM(hw->ptp.ports_per_phy); if (quadtype == 0) { msg->msg_addr_low = P_Q0_L(P_0_BASE + offset, phy_port); @@ -306,12 +2785,7 @@ ice_fill_phy_msg_e82x(struct ice_sbq_msg_input *msg, u8 port, u16 offset) msg->msg_addr_high = P_Q1_H(P_4_BASE + offset, phy_port); } - if (phy == 0) - msg->dest_dev = rmn_0; - else if (phy == 1) - msg->dest_dev = rmn_1; - else - msg->dest_dev = rmn_2; + msg->dest_dev = ice_sbq_dev_phy_0; } /** @@ -427,10 +2901,10 @@ ice_read_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 offset, u32 *val) struct ice_sbq_msg_input msg = {0}; int err; - ice_fill_phy_msg_e82x(&msg, port, offset); + ice_fill_phy_msg_e82x(hw, &msg, port, offset); msg.opcode = ice_sbq_msg_rd; - err = ice_sbq_rw_reg(hw, &msg); + err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n", err); @@ -504,11 +2978,11 @@ ice_write_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 offset, u32 val) struct ice_sbq_msg_input msg = {0}; int err; - ice_fill_phy_msg_e82x(&msg, port, offset); + ice_fill_phy_msg_e82x(hw, &msg, port, offset); msg.opcode = ice_sbq_msg_wr; msg.data = val; - err = ice_sbq_rw_reg(hw, &msg); + err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n", err); @@ -543,8 +3017,7 @@ ice_write_40b_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 low_addr, u64 val) low_addr); return -EINVAL; } - - low = (u32)(val & P_REG_40B_LOW_M); + low = FIELD_GET(P_REG_40B_LOW_M, val); high = (u32)(val >> P_REG_40B_HIGH_S); err = ice_write_phy_reg_e82x(hw, port, low_addr, low); @@ -614,24 +3087,30 @@ ice_write_64b_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 low_addr, u64 val) /** * ice_fill_quad_msg_e82x - Fill message data for quad register access + * @hw: pointer to the HW struct * @msg: the PHY message buffer to fill in * @quad: the quad to access * @offset: the register offset * * Fill a message buffer for accessing a register in a quad shared between * multiple PHYs. + * + * Return: + * * %0 - OK + * * %-EINVAL - invalid quad number */ -static int -ice_fill_quad_msg_e82x(struct ice_sbq_msg_input *msg, u8 quad, u16 offset) +static int ice_fill_quad_msg_e82x(struct ice_hw *hw, + struct ice_sbq_msg_input *msg, u8 quad, + u16 offset) { u32 addr; - if (quad >= ICE_MAX_QUAD) + if (quad >= ICE_GET_QUAD_NUM(hw->ptp.num_lports)) return -EINVAL; - msg->dest_dev = rmn_0; + msg->dest_dev = ice_sbq_dev_phy_0; - if ((quad % ICE_QUADS_PER_PHY_E82X) == 0) + if (!(quad % ICE_GET_QUAD_NUM(hw->ptp.ports_per_phy))) addr = Q_0_BASE + offset; else addr = Q_1_BASE + offset; @@ -658,13 +3137,13 @@ ice_read_quad_reg_e82x(struct ice_hw *hw, u8 quad, u16 offset, u32 *val) struct ice_sbq_msg_input msg = {0}; int err; - err = ice_fill_quad_msg_e82x(&msg, quad, offset); + err = ice_fill_quad_msg_e82x(hw, &msg, quad, offset); if (err) return err; msg.opcode = ice_sbq_msg_rd; - err = ice_sbq_rw_reg(hw, &msg); + err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n", err); @@ -692,14 +3171,14 @@ ice_write_quad_reg_e82x(struct ice_hw *hw, u8 quad, u16 offset, u32 val) struct ice_sbq_msg_input msg = {0}; int err; - err = ice_fill_quad_msg_e82x(&msg, quad, offset); + err = ice_fill_quad_msg_e82x(hw, &msg, quad, offset); if (err) return err; msg.opcode = ice_sbq_msg_wr; msg.data = val; - err = ice_sbq_rw_reg(hw, &msg); + err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n", err); @@ -748,7 +3227,8 @@ ice_read_phy_tstamp_e82x(struct ice_hw *hw, u8 quad, u8 idx, u64 *tstamp) * lower 8 bits in the low register, and the upper 32 bits in the high * register. */ - *tstamp = ((u64)hi) << TS_PHY_HIGH_S | ((u64)lo & TS_PHY_LOW_M); + *tstamp = FIELD_PREP(PHY_40B_HIGH_M, hi) | + FIELD_PREP(PHY_40B_LOW_M, lo); return 0; } @@ -813,294 +3293,11 @@ static void ice_ptp_reset_ts_memory_e82x(struct ice_hw *hw) { unsigned int quad; - for (quad = 0; quad < ICE_MAX_QUAD; quad++) + for (quad = 0; quad < ICE_GET_QUAD_NUM(hw->ptp.num_lports); quad++) ice_ptp_reset_ts_memory_quad_e82x(hw, quad); } /** - * ice_read_cgu_reg_e82x - Read a CGU register - * @hw: pointer to the HW struct - * @addr: Register address to read - * @val: storage for register value read - * - * Read the contents of a register of the Clock Generation Unit. Only - * applicable to E822 devices. - */ -static int -ice_read_cgu_reg_e82x(struct ice_hw *hw, u32 addr, u32 *val) -{ - struct ice_sbq_msg_input cgu_msg; - int err; - - cgu_msg.opcode = ice_sbq_msg_rd; - cgu_msg.dest_dev = cgu; - cgu_msg.msg_addr_low = addr; - cgu_msg.msg_addr_high = 0x0; - - err = ice_sbq_rw_reg(hw, &cgu_msg); - if (err) { - ice_debug(hw, ICE_DBG_PTP, "Failed to read CGU register 0x%04x, err %d\n", - addr, err); - return err; - } - - *val = cgu_msg.data; - - return err; -} - -/** - * ice_write_cgu_reg_e82x - Write a CGU register - * @hw: pointer to the HW struct - * @addr: Register address to write - * @val: value to write into the register - * - * Write the specified value to a register of the Clock Generation Unit. Only - * applicable to E822 devices. - */ -static int -ice_write_cgu_reg_e82x(struct ice_hw *hw, u32 addr, u32 val) -{ - struct ice_sbq_msg_input cgu_msg; - int err; - - cgu_msg.opcode = ice_sbq_msg_wr; - cgu_msg.dest_dev = cgu; - cgu_msg.msg_addr_low = addr; - cgu_msg.msg_addr_high = 0x0; - cgu_msg.data = val; - - err = ice_sbq_rw_reg(hw, &cgu_msg); - if (err) { - ice_debug(hw, ICE_DBG_PTP, "Failed to write CGU register 0x%04x, err %d\n", - addr, err); - return err; - } - - return err; -} - -/** - * ice_clk_freq_str - Convert time_ref_freq to string - * @clk_freq: Clock frequency - * - * Convert the specified TIME_REF clock frequency to a string. - */ -static const char *ice_clk_freq_str(u8 clk_freq) -{ - switch ((enum ice_time_ref_freq)clk_freq) { - case ICE_TIME_REF_FREQ_25_000: - return "25 MHz"; - case ICE_TIME_REF_FREQ_122_880: - return "122.88 MHz"; - case ICE_TIME_REF_FREQ_125_000: - return "125 MHz"; - case ICE_TIME_REF_FREQ_153_600: - return "153.6 MHz"; - case ICE_TIME_REF_FREQ_156_250: - return "156.25 MHz"; - case ICE_TIME_REF_FREQ_245_760: - return "245.76 MHz"; - default: - return "Unknown"; - } -} - -/** - * ice_clk_src_str - Convert time_ref_src to string - * @clk_src: Clock source - * - * Convert the specified clock source to its string name. - */ -static const char *ice_clk_src_str(u8 clk_src) -{ - switch ((enum ice_clk_src)clk_src) { - case ICE_CLK_SRC_TCX0: - return "TCX0"; - case ICE_CLK_SRC_TIME_REF: - return "TIME_REF"; - default: - return "Unknown"; - } -} - -/** - * ice_cfg_cgu_pll_e82x - Configure the Clock Generation Unit - * @hw: pointer to the HW struct - * @clk_freq: Clock frequency to program - * @clk_src: Clock source to select (TIME_REF, or TCX0) - * - * Configure the Clock Generation Unit with the desired clock frequency and - * time reference, enabling the PLL which drives the PTP hardware clock. - */ -static int -ice_cfg_cgu_pll_e82x(struct ice_hw *hw, enum ice_time_ref_freq clk_freq, - enum ice_clk_src clk_src) -{ - union tspll_ro_bwm_lf bwm_lf; - union nac_cgu_dword19 dw19; - union nac_cgu_dword22 dw22; - union nac_cgu_dword24 dw24; - union nac_cgu_dword9 dw9; - int err; - - if (clk_freq >= NUM_ICE_TIME_REF_FREQ) { - dev_warn(ice_hw_to_dev(hw), "Invalid TIME_REF frequency %u\n", - clk_freq); - return -EINVAL; - } - - if (clk_src >= NUM_ICE_CLK_SRC) { - dev_warn(ice_hw_to_dev(hw), "Invalid clock source %u\n", - clk_src); - return -EINVAL; - } - - if (clk_src == ICE_CLK_SRC_TCX0 && - clk_freq != ICE_TIME_REF_FREQ_25_000) { - dev_warn(ice_hw_to_dev(hw), - "TCX0 only supports 25 MHz frequency\n"); - return -EINVAL; - } - - err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD9, &dw9.val); - if (err) - return err; - - err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD24, &dw24.val); - if (err) - return err; - - err = ice_read_cgu_reg_e82x(hw, TSPLL_RO_BWM_LF, &bwm_lf.val); - if (err) - return err; - - /* Log the current clock configuration */ - ice_debug(hw, ICE_DBG_PTP, "Current CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n", - dw24.field.ts_pll_enable ? "enabled" : "disabled", - ice_clk_src_str(dw24.field.time_ref_sel), - ice_clk_freq_str(dw9.field.time_ref_freq_sel), - bwm_lf.field.plllock_true_lock_cri ? "locked" : "unlocked"); - - /* Disable the PLL before changing the clock source or frequency */ - if (dw24.field.ts_pll_enable) { - dw24.field.ts_pll_enable = 0; - - err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val); - if (err) - return err; - } - - /* Set the frequency */ - dw9.field.time_ref_freq_sel = clk_freq; - err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD9, dw9.val); - if (err) - return err; - - /* Configure the TS PLL feedback divisor */ - err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD19, &dw19.val); - if (err) - return err; - - dw19.field.tspll_fbdiv_intgr = e822_cgu_params[clk_freq].feedback_div; - dw19.field.tspll_ndivratio = 1; - - err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD19, dw19.val); - if (err) - return err; - - /* Configure the TS PLL post divisor */ - err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD22, &dw22.val); - if (err) - return err; - - dw22.field.time1588clk_div = e822_cgu_params[clk_freq].post_pll_div; - dw22.field.time1588clk_sel_div2 = 0; - - err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD22, dw22.val); - if (err) - return err; - - /* Configure the TS PLL pre divisor and clock source */ - err = ice_read_cgu_reg_e82x(hw, NAC_CGU_DWORD24, &dw24.val); - if (err) - return err; - - dw24.field.ref1588_ck_div = e822_cgu_params[clk_freq].refclk_pre_div; - dw24.field.tspll_fbdiv_frac = e822_cgu_params[clk_freq].frac_n_div; - dw24.field.time_ref_sel = clk_src; - - err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val); - if (err) - return err; - - /* Finally, enable the PLL */ - dw24.field.ts_pll_enable = 1; - - err = ice_write_cgu_reg_e82x(hw, NAC_CGU_DWORD24, dw24.val); - if (err) - return err; - - /* Wait to verify if the PLL locks */ - usleep_range(1000, 5000); - - err = ice_read_cgu_reg_e82x(hw, TSPLL_RO_BWM_LF, &bwm_lf.val); - if (err) - return err; - - if (!bwm_lf.field.plllock_true_lock_cri) { - dev_warn(ice_hw_to_dev(hw), "CGU PLL failed to lock\n"); - return -EBUSY; - } - - /* Log the current clock configuration */ - ice_debug(hw, ICE_DBG_PTP, "New CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n", - dw24.field.ts_pll_enable ? "enabled" : "disabled", - ice_clk_src_str(dw24.field.time_ref_sel), - ice_clk_freq_str(dw9.field.time_ref_freq_sel), - bwm_lf.field.plllock_true_lock_cri ? "locked" : "unlocked"); - - return 0; -} - -/** - * ice_init_cgu_e82x - Initialize CGU with settings from firmware - * @hw: pointer to the HW structure - * - * Initialize the Clock Generation Unit of the E822 device. - */ -static int ice_init_cgu_e82x(struct ice_hw *hw) -{ - struct ice_ts_func_info *ts_info = &hw->func_caps.ts_func_info; - union tspll_cntr_bist_settings cntr_bist; - int err; - - err = ice_read_cgu_reg_e82x(hw, TSPLL_CNTR_BIST_SETTINGS, - &cntr_bist.val); - if (err) - return err; - - /* Disable sticky lock detection so lock err reported is accurate */ - cntr_bist.field.i_plllock_sel_0 = 0; - cntr_bist.field.i_plllock_sel_1 = 0; - - err = ice_write_cgu_reg_e82x(hw, TSPLL_CNTR_BIST_SETTINGS, - cntr_bist.val); - if (err) - return err; - - /* Configure the CGU PLL using the parameters from the function - * capabilities. - */ - err = ice_cfg_cgu_pll_e82x(hw, ts_info->time_ref, - (enum ice_clk_src)ts_info->clk_src); - if (err) - return err; - - return 0; -} - -/** * ice_ptp_set_vernier_wl - Set the window length for vernier calibration * @hw: pointer to the HW struct * @@ -1110,7 +3307,7 @@ static int ice_ptp_set_vernier_wl(struct ice_hw *hw) { u8 port; - for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) { + for (port = 0; port < hw->ptp.num_lports; port++) { int err; err = ice_write_phy_reg_e82x(hw, port, P_REG_WL, @@ -1134,15 +3331,14 @@ static int ice_ptp_set_vernier_wl(struct ice_hw *hw) static int ice_ptp_init_phc_e82x(struct ice_hw *hw) { int err; - u32 regval; + u32 val; /* Enable reading switch and PHY registers over the sideband queue */ #define PF_SB_REM_DEV_CTL_SWITCH_READ BIT(1) #define PF_SB_REM_DEV_CTL_PHY0 BIT(2) - regval = rd32(hw, PF_SB_REM_DEV_CTL); - regval |= (PF_SB_REM_DEV_CTL_SWITCH_READ | - PF_SB_REM_DEV_CTL_PHY0); - wr32(hw, PF_SB_REM_DEV_CTL, regval); + val = rd32(hw, PF_SB_REM_DEV_CTL); + val |= (PF_SB_REM_DEV_CTL_SWITCH_READ | PF_SB_REM_DEV_CTL_PHY0); + wr32(hw, PF_SB_REM_DEV_CTL, val); /* Initialize the Clock Generation Unit */ err = ice_init_cgu_e82x(hw); @@ -1175,7 +3371,7 @@ ice_ptp_prep_phy_time_e82x(struct ice_hw *hw, u32 time) */ phy_time = (u64)time << 32; - for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) { + for (port = 0; port < hw->ptp.num_lports; port++) { /* Tx case */ err = ice_write_64b_phy_reg_e82x(hw, port, P_REG_TX_TIMER_INC_PRE_L, @@ -1278,7 +3474,7 @@ ice_ptp_prep_phy_adj_e82x(struct ice_hw *hw, s32 adj) else cycles = -(((s64)-adj) << 32); - for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) { + for (port = 0; port < hw->ptp.num_lports; port++) { int err; err = ice_ptp_prep_port_adj_e82x(hw, port, cycles); @@ -1304,7 +3500,7 @@ ice_ptp_prep_phy_incval_e82x(struct ice_hw *hw, u64 incval) int err; u8 port; - for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) { + for (port = 0; port < hw->ptp.num_lports; port++) { err = ice_write_40b_phy_reg_e82x(hw, port, P_REG_TIMETUS_L, incval); if (err) @@ -1369,51 +3565,20 @@ ice_ptp_read_port_capture(struct ice_hw *hw, u8 port, u64 *tx_ts, u64 *rx_ts) * * Prepare the requested port for an upcoming timer sync command. * - * Do not use this function directly. If you want to configure exactly one - * port, use ice_ptp_one_port_cmd() instead. + * Note there is no equivalent of this operation on E810, as that device + * always handles all external PHYs internally. + * + * Return: + * * %0 - success + * * %other - failed to write to PHY */ static int ice_ptp_write_port_cmd_e82x(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd) { - u32 cmd_val, val; - u8 tmr_idx; + u32 val = ice_ptp_tmr_cmd_to_port_reg(hw, cmd); int err; - tmr_idx = ice_get_ptp_src_clock_index(hw); - cmd_val = tmr_idx << SEL_PHY_SRC; - switch (cmd) { - case ICE_PTP_INIT_TIME: - cmd_val |= PHY_CMD_INIT_TIME; - break; - case ICE_PTP_INIT_INCVAL: - cmd_val |= PHY_CMD_INIT_INCVAL; - break; - case ICE_PTP_ADJ_TIME: - cmd_val |= PHY_CMD_ADJ_TIME; - break; - case ICE_PTP_READ_TIME: - cmd_val |= PHY_CMD_READ_TIME; - break; - case ICE_PTP_ADJ_TIME_AT_TIME: - cmd_val |= PHY_CMD_ADJ_TIME_AT_TIME; - break; - case ICE_PTP_NOP: - break; - } - /* Tx case */ - /* Read, modify, write */ - err = ice_read_phy_reg_e82x(hw, port, P_REG_TX_TMR_CMD, &val); - if (err) { - ice_debug(hw, ICE_DBG_PTP, "Failed to read TX_TMR_CMD, err %d\n", - err); - return err; - } - - /* Modify necessary bits only and perform write */ - val &= ~TS_CMD_MASK; - val |= cmd_val; - err = ice_write_phy_reg_e82x(hw, port, P_REG_TX_TMR_CMD, val); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to write back TX_TMR_CMD, err %d\n", @@ -1422,19 +3587,8 @@ static int ice_ptp_write_port_cmd_e82x(struct ice_hw *hw, u8 port, } /* Rx case */ - /* Read, modify, write */ - err = ice_read_phy_reg_e82x(hw, port, P_REG_RX_TMR_CMD, &val); - if (err) { - ice_debug(hw, ICE_DBG_PTP, "Failed to read RX_TMR_CMD, err %d\n", - err); - return err; - } - - /* Modify necessary bits only and perform write */ - val &= ~TS_CMD_MASK; - val |= cmd_val; - - err = ice_write_phy_reg_e82x(hw, port, P_REG_RX_TMR_CMD, val); + err = ice_write_phy_reg_e82x(hw, port, P_REG_RX_TMR_CMD, + val | TS_CMD_RX_TYPE); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to write back RX_TMR_CMD, err %d\n", err); @@ -1444,63 +3598,6 @@ static int ice_ptp_write_port_cmd_e82x(struct ice_hw *hw, u8 port, return 0; } -/** - * 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_e82x(hw, port, cmd); - if (err) - return err; - } - - return 0; -} - -/** - * ice_ptp_port_cmd_e82x - Prepare all ports for a timer command - * @hw: pointer to the HW struct - * @cmd: timer command to prepare - * - * Prepare all ports connected to this device for an upcoming timer sync - * command. - */ -static int -ice_ptp_port_cmd_e82x(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) -{ - u8 port; - - for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) { - int err; - - err = ice_ptp_write_port_cmd_e82x(hw, port, cmd); - if (err) - return err; - } - - return 0; -} - /* E822 Vernier calibration functions * * The following functions are used as part of the vernier calibration of @@ -1603,7 +3700,7 @@ static void ice_phy_cfg_lane_e82x(struct ice_hw *hw, u8 port) return; } - quad = port / ICE_PORTS_PER_QUAD; + quad = ICE_GET_QUAD_NUM(port); err = ice_read_quad_reg_e82x(hw, quad, Q_REG_TX_MEM_GBL_CFG, &val); if (err) { @@ -2324,6 +4421,40 @@ int ice_phy_cfg_rx_offset_e82x(struct ice_hw *hw, u8 port) } /** + * ice_ptp_clear_phy_offset_ready_e82x - Clear PHY TX_/RX_OFFSET_READY registers + * @hw: pointer to the HW struct + * + * Clear PHY TX_/RX_OFFSET_READY registers, effectively marking all transmitted + * and received timestamps as invalid. + * + * Return: 0 on success, other error codes when failed to write to PHY + */ +int ice_ptp_clear_phy_offset_ready_e82x(struct ice_hw *hw) +{ + u8 port; + + for (port = 0; port < hw->ptp.num_lports; port++) { + int err; + + err = ice_write_phy_reg_e82x(hw, port, P_REG_TX_OR, 0); + if (err) { + dev_warn(ice_hw_to_dev(hw), + "Failed to clear PHY TX_OFFSET_READY register\n"); + return err; + } + + err = ice_write_phy_reg_e82x(hw, port, P_REG_RX_OR, 0); + if (err) { + dev_warn(ice_hw_to_dev(hw), + "Failed to clear PHY RX_OFFSET_READY register\n"); + return err; + } + } + + return 0; +} + +/** * ice_read_phy_and_phc_time_e82x - Simultaneously capture PHC and PHY time * @hw: pointer to the HW struct * @port: the PHY port to read @@ -2633,6 +4764,47 @@ ice_get_phy_tx_tstamp_ready_e82x(struct ice_hw *hw, u8 quad, u64 *tstamp_ready) return 0; } +/** + * ice_phy_cfg_intr_e82x - Configure TX timestamp interrupt + * @hw: pointer to the HW struct + * @quad: the timestamp quad + * @ena: enable or disable interrupt + * @threshold: interrupt threshold + * + * Configure TX timestamp interrupt for the specified quad + * + * Return: 0 on success, other error codes when failed to read/write quad + */ + +int ice_phy_cfg_intr_e82x(struct ice_hw *hw, u8 quad, bool ena, u8 threshold) +{ + int err; + u32 val; + + err = ice_read_quad_reg_e82x(hw, quad, Q_REG_TX_MEM_GBL_CFG, &val); + if (err) + return err; + + val &= ~Q_REG_TX_MEM_GBL_CFG_INTR_ENA_M; + if (ena) { + val |= Q_REG_TX_MEM_GBL_CFG_INTR_ENA_M; + val &= ~Q_REG_TX_MEM_GBL_CFG_INTR_THR_M; + val |= FIELD_PREP(Q_REG_TX_MEM_GBL_CFG_INTR_THR_M, threshold); + } + + return ice_write_quad_reg_e82x(hw, quad, Q_REG_TX_MEM_GBL_CFG, val); +} + +/** + * ice_ptp_init_phy_e82x - initialize PHY parameters + * @ptp: pointer to the PTP HW struct + */ +static void ice_ptp_init_phy_e82x(struct ice_ptp_hw *ptp) +{ + ptp->num_lports = 8; + ptp->ports_per_phy = 8; +} + /* E810 functions * * The following functions operate on the E810 series devices which use @@ -2655,9 +4827,9 @@ static int ice_read_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 *val) msg.msg_addr_low = lower_16_bits(addr); msg.msg_addr_high = upper_16_bits(addr); msg.opcode = ice_sbq_msg_rd; - msg.dest_dev = rmn_0; + msg.dest_dev = ice_sbq_dev_phy_0; - err = ice_sbq_rw_reg(hw, &msg); + err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n", err); @@ -2685,10 +4857,10 @@ static int ice_write_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 val) msg.msg_addr_low = lower_16_bits(addr); msg.msg_addr_high = upper_16_bits(addr); msg.opcode = ice_sbq_msg_wr; - msg.dest_dev = rmn_0; + msg.dest_dev = ice_sbq_dev_phy_0; msg.data = val; - err = ice_sbq_rw_reg(hw, &msg); + err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n", err); @@ -2712,33 +4884,46 @@ static int ice_write_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 val) static int ice_read_phy_tstamp_ll_e810(struct ice_hw *hw, u8 idx, u8 *hi, u32 *lo) { + struct ice_e810_params *params = &hw->ptp.phy.e810; + unsigned long flags; u32 val; - u8 i; + int err; + + spin_lock_irqsave(¶ms->atqbal_wq.lock, flags); + + /* Wait for any pending in-progress low latency interrupt */ + err = wait_event_interruptible_locked_irq(params->atqbal_wq, + !(params->atqbal_flags & + ATQBAL_FLAGS_INTR_IN_PROGRESS)); + if (err) { + spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); + return err; + } /* Write TS index to read to the PF register so the FW can read it */ - val = FIELD_PREP(TS_LL_READ_TS_IDX, idx) | TS_LL_READ_TS; - wr32(hw, PF_SB_ATQBAL, val); + val = FIELD_PREP(REG_LL_PROXY_H_TS_IDX, idx) | REG_LL_PROXY_H_EXEC; + wr32(hw, REG_LL_PROXY_H, val); /* Read the register repeatedly until the FW provides us the TS */ - for (i = TS_LL_READ_RETRIES; i > 0; i--) { - val = rd32(hw, PF_SB_ATQBAL); + err = read_poll_timeout_atomic(rd32, val, + !FIELD_GET(REG_LL_PROXY_H_EXEC, val), 10, + REG_LL_PROXY_H_TIMEOUT_US, false, hw, + REG_LL_PROXY_H); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read PTP timestamp using low latency read\n"); + spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); + return err; + } - /* When the bit is cleared, the TS is ready in the register */ - if (!(FIELD_GET(TS_LL_READ_TS, val))) { - /* High 8 bit value of the TS is on the bits 16:23 */ - *hi = FIELD_GET(TS_LL_READ_TS_HIGH, val); + /* High 8 bit value of the TS is on the bits 16:23 */ + *hi = FIELD_GET(REG_LL_PROXY_H_TS_HIGH, val); - /* Read the low 32 bit value and set the TS valid bit */ - *lo = rd32(hw, PF_SB_ATQBAH) | TS_VALID; - return 0; - } + /* Read the low 32 bit value and set the TS valid bit */ + *lo = rd32(hw, REG_LL_PROXY_L) | TS_VALID; - udelay(10); - } + spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); - /* FW failed to provide the TS in time */ - ice_debug(hw, ICE_DBG_PTP, "Failed to read PTP timestamp using low latency read\n"); - return -EINVAL; + return 0; } /** @@ -2809,7 +4994,8 @@ ice_read_phy_tstamp_e810(struct ice_hw *hw, u8 lport, u8 idx, u64 *tstamp) /* For E810 devices, the timestamp is reported with the lower 32 bits * in the low register, and the upper 8 bits in the high register. */ - *tstamp = ((u64)hi) << TS_HIGH_S | ((u64)lo & TS_LOW_M); + *tstamp = FIELD_PREP(PHY_EXT_40B_HIGH_M, hi) | + FIELD_PREP(PHY_EXT_40B_LOW_M, lo); return 0; } @@ -2860,17 +5046,20 @@ static int ice_clear_phy_tstamp_e810(struct ice_hw *hw, u8 lport, u8 idx) } /** - * ice_ptp_init_phy_e810 - Enable PTP function on the external PHY + * ice_ptp_init_phc_e810 - Perform E810 specific PHC initialization * @hw: pointer to HW struct * - * Enable the timesync PTP functionality for the external PHY connected to - * this function. + * Perform E810-specific PTP hardware clock initialization steps. + * + * Return: 0 on success, other error codes when failed to initialize TimeSync */ -int ice_ptp_init_phy_e810(struct ice_hw *hw) +static int ice_ptp_init_phc_e810(struct ice_hw *hw) { u8 tmr_idx; int err; + ice_ptp_cfg_sync_delay(hw, ICE_E810_E830_SYNC_DELAY); + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; err = ice_write_phy_reg_e810(hw, ETH_GLTSYN_ENA(tmr_idx), GLTSYN_ENA_TSYN_ENA_M); @@ -2882,21 +5071,6 @@ int ice_ptp_init_phy_e810(struct ice_hw *hw) } /** - * ice_ptp_init_phc_e810 - Perform E810 specific PHC initialization - * @hw: pointer to HW struct - * - * Perform E810-specific PTP hardware clock initialization steps. - */ -static int ice_ptp_init_phc_e810(struct ice_hw *hw) -{ - /* Ensure synchronization delay is zero */ - wr32(hw, GLTSYN_SYNC_DLAY, 0); - - /* Initialize the PHY */ - return ice_ptp_init_phy_e810(hw); -} - -/** * ice_ptp_prep_phy_time_e810 - Prepare PHY port with initial time * @hw: Board private structure * @time: Time to initialize the PHY port clock to @@ -2932,6 +5106,55 @@ static int ice_ptp_prep_phy_time_e810(struct ice_hw *hw, u32 time) } /** + * ice_ptp_prep_phy_adj_ll_e810 - Prep PHY ports for a time adjustment + * @hw: pointer to HW struct + * @adj: adjustment value to program + * + * Use the low latency firmware interface to program PHY time adjustment to + * all PHY ports. + * + * Return: 0 on success, -EBUSY on timeout + */ +static int ice_ptp_prep_phy_adj_ll_e810(struct ice_hw *hw, s32 adj) +{ + const u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + struct ice_e810_params *params = &hw->ptp.phy.e810; + u32 val; + int err; + + spin_lock_irq(¶ms->atqbal_wq.lock); + + /* Wait for any pending in-progress low latency interrupt */ + err = wait_event_interruptible_locked_irq(params->atqbal_wq, + !(params->atqbal_flags & + ATQBAL_FLAGS_INTR_IN_PROGRESS)); + if (err) { + spin_unlock_irq(¶ms->atqbal_wq.lock); + return err; + } + + wr32(hw, REG_LL_PROXY_L, adj); + val = FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_CMD_M, REG_LL_PROXY_H_PHY_TMR_CMD_ADJ) | + FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_IDX_M, tmr_idx) | REG_LL_PROXY_H_EXEC; + wr32(hw, REG_LL_PROXY_H, val); + + /* Read the register repeatedly until the FW indicates completion */ + err = read_poll_timeout_atomic(rd32, val, + !FIELD_GET(REG_LL_PROXY_H_EXEC, val), + 10, REG_LL_PROXY_H_TIMEOUT_US, false, hw, + REG_LL_PROXY_H); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to prepare PHY timer adjustment using low latency interface\n"); + spin_unlock_irq(¶ms->atqbal_wq.lock); + return err; + } + + spin_unlock_irq(¶ms->atqbal_wq.lock); + + return 0; +} + +/** * ice_ptp_prep_phy_adj_e810 - Prep PHY port for a time adjustment * @hw: pointer to HW struct * @adj: adjustment value to program @@ -2949,6 +5172,9 @@ static int ice_ptp_prep_phy_adj_e810(struct ice_hw *hw, s32 adj) u8 tmr_idx; int err; + if (hw->dev_caps.ts_dev_info.ll_phy_tmr_update) + return ice_ptp_prep_phy_adj_ll_e810(hw, adj); + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; /* Adjustments are represented as signed 2's complement values in @@ -2972,6 +5198,56 @@ static int ice_ptp_prep_phy_adj_e810(struct ice_hw *hw, s32 adj) } /** + * ice_ptp_prep_phy_incval_ll_e810 - Prep PHY ports increment value change + * @hw: pointer to HW struct + * @incval: The new 40bit increment value to prepare + * + * Use the low latency firmware interface to program PHY time increment value + * for all PHY ports. + * + * Return: 0 on success, -EBUSY on timeout + */ +static int ice_ptp_prep_phy_incval_ll_e810(struct ice_hw *hw, u64 incval) +{ + const u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + struct ice_e810_params *params = &hw->ptp.phy.e810; + u32 val; + int err; + + spin_lock_irq(¶ms->atqbal_wq.lock); + + /* Wait for any pending in-progress low latency interrupt */ + err = wait_event_interruptible_locked_irq(params->atqbal_wq, + !(params->atqbal_flags & + ATQBAL_FLAGS_INTR_IN_PROGRESS)); + if (err) { + spin_unlock_irq(¶ms->atqbal_wq.lock); + return err; + } + + wr32(hw, REG_LL_PROXY_L, lower_32_bits(incval)); + val = FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_CMD_M, REG_LL_PROXY_H_PHY_TMR_CMD_FREQ) | + FIELD_PREP(REG_LL_PROXY_H_TS_HIGH, (u8)upper_32_bits(incval)) | + FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_IDX_M, tmr_idx) | REG_LL_PROXY_H_EXEC; + wr32(hw, REG_LL_PROXY_H, val); + + /* Read the register repeatedly until the FW indicates completion */ + err = read_poll_timeout_atomic(rd32, val, + !FIELD_GET(REG_LL_PROXY_H_EXEC, val), + 10, REG_LL_PROXY_H_TIMEOUT_US, false, hw, + REG_LL_PROXY_H); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to prepare PHY timer increment using low latency interface\n"); + spin_unlock_irq(¶ms->atqbal_wq.lock); + return err; + } + + spin_unlock_irq(¶ms->atqbal_wq.lock); + + return 0; +} + +/** * ice_ptp_prep_phy_incval_e810 - Prep PHY port increment value change * @hw: pointer to HW struct * @incval: The new 40bit increment value to prepare @@ -2986,6 +5262,9 @@ static int ice_ptp_prep_phy_incval_e810(struct ice_hw *hw, u64 incval) u8 tmr_idx; int err; + if (hw->dev_caps.ts_dev_info.ll_phy_tmr_update) + return ice_ptp_prep_phy_incval_ll_e810(hw, incval); + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; low = lower_32_bits(incval); high = upper_32_bits(incval); @@ -3017,47 +5296,9 @@ static int ice_ptp_prep_phy_incval_e810(struct ice_hw *hw, u64 incval) */ static int ice_ptp_port_cmd_e810(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) { - u32 cmd_val, val; - int err; + u32 val = ice_ptp_tmr_cmd_to_port_reg(hw, cmd); - switch (cmd) { - case ICE_PTP_INIT_TIME: - cmd_val = GLTSYN_CMD_INIT_TIME; - break; - case ICE_PTP_INIT_INCVAL: - cmd_val = GLTSYN_CMD_INIT_INCVAL; - break; - case ICE_PTP_ADJ_TIME: - cmd_val = GLTSYN_CMD_ADJ_TIME; - break; - case ICE_PTP_READ_TIME: - cmd_val = GLTSYN_CMD_READ_TIME; - break; - case ICE_PTP_ADJ_TIME_AT_TIME: - cmd_val = GLTSYN_CMD_ADJ_INIT_TIME; - break; - case ICE_PTP_NOP: - return 0; - } - - /* Read, modify, write */ - err = ice_read_phy_reg_e810(hw, ETH_GLTSYN_CMD, &val); - if (err) { - ice_debug(hw, ICE_DBG_PTP, "Failed to read GLTSYN_CMD, err %d\n", err); - return err; - } - - /* Modify necessary bits only and perform write */ - val &= ~TS_CMD_MASK_E810; - val |= cmd_val; - - err = ice_write_phy_reg_e810(hw, ETH_GLTSYN_CMD, val); - if (err) { - ice_debug(hw, ICE_DBG_PTP, "Failed to write back GLTSYN_CMD, err %d\n", err); - return err; - } - - return 0; + return ice_write_phy_reg_e810(hw, E810_ETH_GLTSYN_CMD, val); } /** @@ -3076,83 +5317,21 @@ ice_get_phy_tx_tstamp_ready_e810(struct ice_hw *hw, u8 port, u64 *tstamp_ready) return 0; } -/* E810T SMA functions +/* E810 SMA functions * - * The following functions operate specifically on E810T hardware and are used + * The following functions operate specifically on E810 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 + * ice_read_sma_ctrl * @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 ice_read_sma_ctrl(struct ice_hw *hw, u8 *data) { int status; u16 handle; @@ -3164,7 +5343,7 @@ int ice_read_sma_ctrl_e810t(struct ice_hw *hw, u8 *data) *data = 0; - for (i = ICE_SMA_MIN_BIT_E810T; i <= ICE_SMA_MAX_BIT_E810T; i++) { + for (i = ICE_SMA_MIN_BIT; i <= ICE_SMA_MAX_BIT; i++) { bool pin; status = ice_aq_get_gpio(hw, handle, i + ICE_PCA9575_P1_OFFSET, @@ -3178,14 +5357,14 @@ int ice_read_sma_ctrl_e810t(struct ice_hw *hw, u8 *data) } /** - * ice_write_sma_ctrl_e810t + * ice_write_sma_ctrl * @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 ice_write_sma_ctrl(struct ice_hw *hw, u8 data) { int status; u16 handle; @@ -3195,7 +5374,7 @@ int ice_write_sma_ctrl_e810t(struct ice_hw *hw, u8 data) if (status) return status; - for (i = ICE_SMA_MIN_BIT_E810T; i <= ICE_SMA_MAX_BIT_E810T; i++) { + for (i = ICE_SMA_MIN_BIT; i <= ICE_SMA_MAX_BIT; i++) { bool pin; pin = !(data & (1 << i)); @@ -3209,41 +5388,203 @@ int ice_write_sma_ctrl_e810t(struct ice_hw *hw, u8 data) } /** - * 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 + * ice_ptp_read_sdp_ac - read SDP available connections section from NVM + * @hw: pointer to the HW struct + * @entries: returns the SDP available connections section from NVM + * @num_entries: returns the number of valid entries * - * Read the register from the GPIO controller + * Return: 0 on success, negative error code if NVM read failed or section does + * not exist or is corrupted */ -int ice_read_pca9575_reg_e810t(struct ice_hw *hw, u8 offset, u8 *data) +int ice_ptp_read_sdp_ac(struct ice_hw *hw, __le16 *entries, uint *num_entries) { - struct ice_aqc_link_topo_addr link_topo; - __le16 addr; - u16 handle; + __le16 data; + u32 offset; int err; - memset(&link_topo, 0, sizeof(link_topo)); + err = ice_acquire_nvm(hw, ICE_RES_READ); + if (err) + goto exit; - err = ice_get_pca9575_handle(hw, &handle); + /* Read the offset of SDP_AC */ + offset = ICE_AQC_NVM_SDP_AC_PTR_OFFSET; + err = ice_aq_read_nvm(hw, 0, offset, sizeof(data), &data, false, true, + NULL); if (err) - return err; + goto exit; + + /* Check if section exist */ + offset = FIELD_GET(ICE_AQC_NVM_SDP_AC_PTR_M, le16_to_cpu(data)); + if (offset == ICE_AQC_NVM_SDP_AC_PTR_INVAL) { + err = -EINVAL; + goto exit; + } + + if (offset & ICE_AQC_NVM_SDP_AC_PTR_TYPE_M) { + offset &= ICE_AQC_NVM_SDP_AC_PTR_M; + offset *= ICE_AQC_NVM_SECTOR_UNIT; + } else { + offset *= sizeof(data); + } + + /* Skip reading section length and read the number of valid entries */ + offset += sizeof(data); + err = ice_aq_read_nvm(hw, 0, offset, sizeof(data), &data, false, true, + NULL); + if (err) + goto exit; + *num_entries = le16_to_cpu(data); + + /* Read SDP configuration section */ + offset += sizeof(data); + err = ice_aq_read_nvm(hw, 0, offset, *num_entries * sizeof(data), + entries, false, true, NULL); + +exit: + if (err) + dev_dbg(ice_hw_to_dev(hw), "Failed to configure SDP connection section\n"); + ice_release_nvm(hw); + return err; +} + +/** + * ice_ptp_init_phy_e810 - initialize PHY parameters + * @ptp: pointer to the PTP HW struct + */ +static void ice_ptp_init_phy_e810(struct ice_ptp_hw *ptp) +{ + ptp->num_lports = 8; + ptp->ports_per_phy = 4; + + init_waitqueue_head(&ptp->phy.e810.atqbal_wq); +} + +/* E830 functions + * + * The following functions operate on the E830 series devices. + * + */ + +/** + * ice_ptp_init_phc_e830 - Perform E830 specific PHC initialization + * @hw: pointer to HW struct + * + * Perform E830-specific PTP hardware clock initialization steps. + */ +static void ice_ptp_init_phc_e830(const struct ice_hw *hw) +{ + ice_ptp_cfg_sync_delay(hw, ICE_E810_E830_SYNC_DELAY); +} + +/** + * ice_ptp_write_direct_incval_e830 - Prep PHY port increment value change + * @hw: pointer to HW struct + * @incval: The new 40bit increment value to prepare + * + * Prepare the PHY port for a new increment value by programming the PHC + * GLTSYN_INCVAL_L and GLTSYN_INCVAL_H registers. The actual change is + * completed by FW automatically. + */ +static void ice_ptp_write_direct_incval_e830(const struct ice_hw *hw, + u64 incval) +{ + u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + + wr32(hw, GLTSYN_INCVAL_L(tmr_idx), lower_32_bits(incval)); + wr32(hw, GLTSYN_INCVAL_H(tmr_idx), upper_32_bits(incval)); +} + +/** + * ice_ptp_write_direct_phc_time_e830 - Prepare PHY port with initial time + * @hw: Board private structure + * @time: Time to initialize the PHY port clock to + * + * 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 ICE_PTP_INIT_TIME command. + * + * The time value is the upper 32 bits of the PHY timer, usually in units of + * nominal nanoseconds. + */ +static void ice_ptp_write_direct_phc_time_e830(const struct ice_hw *hw, + u64 time) +{ + u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; - 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); + wr32(hw, GLTSYN_TIME_0(tmr_idx), 0); + wr32(hw, GLTSYN_TIME_L(tmr_idx), lower_32_bits(time)); + wr32(hw, GLTSYN_TIME_H(tmr_idx), upper_32_bits(time)); +} - addr = cpu_to_le16((u16)offset); +/** + * ice_ptp_port_cmd_e830 - Prepare all external PHYs for a timer command + * @hw: pointer to HW struct + * @cmd: Command to be sent to the port + * + * Prepare the external PHYs connected to this device for a timer sync + * command. + * + * Return: 0 on success, negative error code when PHY write failed + */ +static int ice_ptp_port_cmd_e830(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) +{ + u32 val = ice_ptp_tmr_cmd_to_port_reg(hw, cmd); - return ice_aq_read_i2c(hw, link_topo, 0, addr, 1, data, NULL); + return ice_write_phy_reg_e810(hw, E830_ETH_GLTSYN_CMD, val); +} + +/** + * ice_read_phy_tstamp_e830 - Read a PHY timestamp out of the external PHY + * @hw: pointer to the HW struct + * @idx: the timestamp index to read + * @tstamp: on return, the 40bit timestamp value + * + * Read a 40bit timestamp value out of the timestamp block of the external PHY + * on the E830 device. + */ +static void ice_read_phy_tstamp_e830(const struct ice_hw *hw, u8 idx, + u64 *tstamp) +{ + u32 hi, lo; + + hi = rd32(hw, E830_PRTTSYN_TXTIME_H(idx)); + lo = rd32(hw, E830_PRTTSYN_TXTIME_L(idx)); + + /* For E830 devices, the timestamp is reported with the lower 32 bits + * in the low register, and the upper 8 bits in the high register. + */ + *tstamp = FIELD_PREP(PHY_EXT_40B_HIGH_M, hi) | + FIELD_PREP(PHY_EXT_40B_LOW_M, lo); +} + +/** + * ice_get_phy_tx_tstamp_ready_e830 - 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 + */ +static void ice_get_phy_tx_tstamp_ready_e830(const struct ice_hw *hw, u8 port, + u64 *tstamp_ready) +{ + *tstamp_ready = rd32(hw, E830_PRTMAC_TS_TX_MEM_VALID_H); + *tstamp_ready <<= 32; + *tstamp_ready |= rd32(hw, E830_PRTMAC_TS_TX_MEM_VALID_L); +} + +/** + * ice_ptp_init_phy_e830 - initialize PHY parameters + * @ptp: pointer to the PTP HW struct + */ +static void ice_ptp_init_phy_e830(struct ice_ptp_hw *ptp) +{ + ptp->num_lports = 8; + ptp->ports_per_phy = 4; } /* Device agnostic functions * - * The following functions implement shared behavior common to both E822 and - * E810 devices, possibly calling a device specific implementation where - * necessary. + * The following functions implement shared behavior common to all devices, + * possibly calling a device specific implementation where necessary. */ /** @@ -3296,18 +5637,136 @@ void ice_ptp_unlock(struct ice_hw *hw) } /** - * ice_ptp_init_phy_model - Initialize hw->phy_model based on device type + * ice_ptp_init_hw - Initialize hw based on device type * @hw: pointer to the HW structure * - * Determine the PHY model for the device, and initialize hw->phy_model + * Determine the PHY model for the device, and initialize hw * for use by other functions. */ -void ice_ptp_init_phy_model(struct ice_hw *hw) +void ice_ptp_init_hw(struct ice_hw *hw) { - if (ice_is_e810(hw)) - hw->phy_model = ICE_PHY_E810; - else - hw->phy_model = ICE_PHY_E82X; + struct ice_ptp_hw *ptp = &hw->ptp; + + switch (hw->mac_type) { + case ICE_MAC_E810: + ice_ptp_init_phy_e810(ptp); + break; + case ICE_MAC_E830: + ice_ptp_init_phy_e830(ptp); + break; + case ICE_MAC_GENERIC: + ice_ptp_init_phy_e82x(ptp); + break; + case ICE_MAC_GENERIC_3K_E825: + ice_ptp_init_phy_e825(hw); + break; + default: + return; + } +} + +/** + * ice_ptp_write_port_cmd - 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 one port for the upcoming timer sync command. Do not use this for + * programming only a single port, instead use ice_ptp_one_port_cmd() to + * ensure non-modified ports get properly initialized to ICE_PTP_NOP. + * + * Return: + * * %0 - success + * %-EBUSY - PHY type not supported + * * %other - failed to write port command + */ +static int ice_ptp_write_port_cmd(struct ice_hw *hw, u8 port, + enum ice_ptp_tmr_cmd cmd) +{ + switch (hw->mac_type) { + case ICE_MAC_GENERIC: + return ice_ptp_write_port_cmd_e82x(hw, port, cmd); + case ICE_MAC_GENERIC_3K_E825: + return ice_ptp_write_port_cmd_eth56g(hw, port, cmd); + default: + return -EOPNOTSUPP; + } +} + +/** + * ice_ptp_one_port_cmd - Program one PHY port for a timer command + * @hw: pointer to HW struct + * @configured_port: the port that should execute the command + * @configured_cmd: the command to be executed on the configured port + * + * Prepare one port for executing a timer command, while preparing all other + * ports to ICE_PTP_NOP. This allows executing a command on a single port + * while ensuring all other ports do not execute stale commands. + * + * Return: + * * %0 - success + * * %other - failed to write port command + */ +int ice_ptp_one_port_cmd(struct ice_hw *hw, u8 configured_port, + enum ice_ptp_tmr_cmd configured_cmd) +{ + u32 port; + + for (port = 0; port < hw->ptp.num_lports; port++) { + int err; + + /* Program the configured port with the configured command, + * program all other ports with ICE_PTP_NOP. + */ + if (port == configured_port) + err = ice_ptp_write_port_cmd(hw, port, configured_cmd); + else + err = ice_ptp_write_port_cmd(hw, port, ICE_PTP_NOP); + + if (err) + return err; + } + + return 0; +} + +/** + * ice_ptp_port_cmd - Prepare PHY ports for a timer sync command + * @hw: pointer to HW struct + * @cmd: the timer command to setup + * + * Prepare all PHY ports on this device for the requested timer command. For + * some families this can be done in one shot, but for other families each + * port must be configured individually. + * + * Return: + * * %0 - success + * * %other - failed to write port command + */ +static int ice_ptp_port_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) +{ + u32 port; + + /* PHY models which can program all ports simultaneously */ + switch (hw->mac_type) { + case ICE_MAC_E810: + return ice_ptp_port_cmd_e810(hw, cmd); + case ICE_MAC_E830: + return ice_ptp_port_cmd_e830(hw, cmd); + default: + break; + } + + /* PHY models which require programming each port separately */ + for (port = 0; port < hw->ptp.num_lports; port++) { + int err; + + err = ice_ptp_write_port_cmd(hw, port, cmd); + if (err) + return err; + } + + return 0; } /** @@ -3328,17 +5787,7 @@ 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 */ - switch (hw->phy_model) { - case ICE_PHY_E810: - err = ice_ptp_port_cmd_e810(hw, cmd); - break; - case ICE_PHY_E82X: - err = ice_ptp_port_cmd_e82x(hw, cmd); - break; - default: - err = -EOPNOTSUPP; - } - + err = ice_ptp_port_cmd(hw, cmd); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to prepare PHY ports for timer command %u, err %d\n", cmd, err); @@ -3374,19 +5823,29 @@ int ice_ptp_init_time(struct ice_hw *hw, u64 time) tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; /* Source timers */ + /* For E830 we don't need to use shadow registers, its automatic */ + if (hw->mac_type == ICE_MAC_E830) { + ice_ptp_write_direct_phc_time_e830(hw, time); + return 0; + } + wr32(hw, GLTSYN_SHTIME_L(tmr_idx), lower_32_bits(time)); wr32(hw, GLTSYN_SHTIME_H(tmr_idx), upper_32_bits(time)); wr32(hw, GLTSYN_SHTIME_0(tmr_idx), 0); /* PHY timers */ /* Fill Rx and Tx ports and send msg to PHY */ - switch (hw->phy_model) { - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: err = ice_ptp_prep_phy_time_e810(hw, time & 0xFFFFFFFF); break; - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: err = ice_ptp_prep_phy_time_e82x(hw, time & 0xFFFFFFFF); break; + case ICE_MAC_GENERIC_3K_E825: + err = ice_ptp_prep_phy_time_eth56g(hw, + (u32)(time & 0xFFFFFFFF)); + break; default: err = -EOPNOTSUPP; } @@ -3418,17 +5877,26 @@ int ice_ptp_write_incval(struct ice_hw *hw, u64 incval) tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + /* For E830 we don't need to use shadow registers, its automatic */ + if (hw->mac_type == ICE_MAC_E830) { + ice_ptp_write_direct_incval_e830(hw, incval); + return 0; + } + /* Shadow Adjust */ wr32(hw, GLTSYN_SHADJ_L(tmr_idx), lower_32_bits(incval)); wr32(hw, GLTSYN_SHADJ_H(tmr_idx), upper_32_bits(incval)); - switch (hw->phy_model) { - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: err = ice_ptp_prep_phy_incval_e810(hw, incval); break; - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: err = ice_ptp_prep_phy_incval_e82x(hw, incval); break; + case ICE_MAC_GENERIC_3K_E825: + err = ice_ptp_prep_phy_incval_eth56g(hw, incval); + break; default: err = -EOPNOTSUPP; } @@ -3488,13 +5956,19 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj) wr32(hw, GLTSYN_SHADJ_L(tmr_idx), 0); wr32(hw, GLTSYN_SHADJ_H(tmr_idx), adj); - switch (hw->phy_model) { - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: err = ice_ptp_prep_phy_adj_e810(hw, adj); break; - case ICE_PHY_E82X: + case ICE_MAC_E830: + /* E830 sync PHYs automatically after setting GLTSYN_SHADJ */ + return 0; + case ICE_MAC_GENERIC: err = ice_ptp_prep_phy_adj_e82x(hw, adj); break; + case ICE_MAC_GENERIC_3K_E825: + err = ice_ptp_prep_phy_adj_eth56g(hw, adj); + break; default: err = -EOPNOTSUPP; } @@ -3518,11 +5992,16 @@ 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) { - switch (hw->phy_model) { - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: return ice_read_phy_tstamp_e810(hw, block, idx, tstamp); - case ICE_PHY_E82X: + case ICE_MAC_E830: + ice_read_phy_tstamp_e830(hw, idx, tstamp); + return 0; + case ICE_MAC_GENERIC: return ice_read_phy_tstamp_e82x(hw, block, idx, tstamp); + case ICE_MAC_GENERIC_3K_E825: + return ice_read_ptp_tstamp_eth56g(hw, block, idx, tstamp); default: return -EOPNOTSUPP; } @@ -3546,11 +6025,13 @@ int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp) */ int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx) { - switch (hw->phy_model) { - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: return ice_clear_phy_tstamp_e810(hw, block, idx); - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: return ice_clear_phy_tstamp_e82x(hw, block, idx); + case ICE_MAC_GENERIC_3K_E825: + return ice_clear_ptp_tstamp_eth56g(hw, block, idx); default: return -EOPNOTSUPP; } @@ -3607,11 +6088,14 @@ static int ice_get_pf_c827_idx(struct ice_hw *hw, u8 *idx) */ void ice_ptp_reset_ts_memory(struct ice_hw *hw) { - switch (hw->phy_model) { - case ICE_PHY_E82X: + switch (hw->mac_type) { + case ICE_MAC_GENERIC: ice_ptp_reset_ts_memory_e82x(hw); break; - case ICE_PHY_E810: + case ICE_MAC_GENERIC_3K_E825: + ice_ptp_reset_ts_memory_eth56g(hw); + break; + case ICE_MAC_E810: default: return; } @@ -3633,11 +6117,16 @@ int ice_ptp_init_phc(struct ice_hw *hw) /* Clear event err indications for auxiliary pins */ (void)rd32(hw, GLTSYN_STAT(src_idx)); - switch (hw->phy_model) { - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: return ice_ptp_init_phc_e810(hw); - case ICE_PHY_E82X: + case ICE_MAC_E830: + ice_ptp_init_phc_e830(hw); + return 0; + case ICE_MAC_GENERIC: return ice_ptp_init_phc_e82x(hw); + case ICE_MAC_GENERIC_3K_E825: + return ice_ptp_init_phc_e825(hw); default: return -EOPNOTSUPP; } @@ -3656,14 +6145,19 @@ 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) { - switch (hw->phy_model) { - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: return ice_get_phy_tx_tstamp_ready_e810(hw, block, tstamp_ready); - case ICE_PHY_E82X: + case ICE_MAC_E830: + ice_get_phy_tx_tstamp_ready_e830(hw, block, tstamp_ready); + return 0; + case ICE_MAC_GENERIC: return ice_get_phy_tx_tstamp_ready_e82x(hw, block, tstamp_ready); - break; + case ICE_MAC_GENERIC_3K_E825: + return ice_get_phy_tx_tstamp_ready_eth56g(hw, block, + tstamp_ready); default: return -EOPNOTSUPP; } @@ -3760,6 +6254,25 @@ ice_cgu_get_pin_desc(struct ice_hw *hw, bool input, int *size) } /** + * ice_cgu_get_num_pins - get pin description array size + * @hw: pointer to the hw struct + * @input: if request is done against input or output pins + * + * Return: size of pin description array for given hw. + */ +int ice_cgu_get_num_pins(struct ice_hw *hw, bool input) +{ + const struct ice_cgu_pin_desc *t; + int size; + + t = ice_cgu_get_pin_desc(hw, input, &size); + if (t) + return size; + + return 0; +} + +/** * ice_cgu_get_pin_type - get pin's type * @hw: pointer to the hw struct * @pin: pin index diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h index 1f3e03124430..83f20fa7ace7 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -41,11 +41,45 @@ enum ice_ptp_fec_mode { ICE_PTP_FEC_MODE_RS_FEC }; +enum eth56g_res_type { + ETH56G_PHY_REG_PTP, + ETH56G_PHY_MEM_PTP, + ETH56G_PHY_REG_XPCS, + ETH56G_PHY_REG_MAC, + ETH56G_PHY_REG_GPCS, + NUM_ETH56G_PHY_RES +}; + +enum ice_eth56g_link_spd { + ICE_ETH56G_LNK_SPD_1G, + ICE_ETH56G_LNK_SPD_2_5G, + ICE_ETH56G_LNK_SPD_10G, + ICE_ETH56G_LNK_SPD_25G, + ICE_ETH56G_LNK_SPD_40G, + ICE_ETH56G_LNK_SPD_50G, + ICE_ETH56G_LNK_SPD_50G2, + ICE_ETH56G_LNK_SPD_100G, + ICE_ETH56G_LNK_SPD_100G2, + NUM_ICE_ETH56G_LNK_SPD /* Must be last */ +}; + +/** + * struct ice_phy_reg_info_eth56g - ETH56G PHY register parameters + * @base_addr: base address for each PHY block + * @step: step between PHY lanes + * + * Characteristic information for the various PHY register parameters in the + * ETH56G devices + */ +struct ice_phy_reg_info_eth56g { + u32 base_addr; + u32 step; +}; + /** * struct ice_time_ref_info_e82x * @pll_freq: Frequency of PLL that drives timer ticks in Hz * @nominal_incval: increment to generate nanoseconds in GLTSYN_TIME_L - * @pps_delay: propagation delay of the PPS output signal * * Characteristic information for the various TIME_REF sources possible in the * E822 devices @@ -53,7 +87,6 @@ enum ice_ptp_fec_mode { struct ice_time_ref_info_e82x { u64 pll_freq; u64 nominal_incval; - u8 pps_delay; }; /** @@ -94,8 +127,75 @@ struct ice_vernier_info_e82x { u32 rx_fixed_delay; }; +#define ICE_ETH56G_MAC_CFG_RX_OFFSET_INT GENMASK(19, 9) +#define ICE_ETH56G_MAC_CFG_RX_OFFSET_FRAC GENMASK(8, 0) +#define ICE_ETH56G_MAC_CFG_FRAC_W 9 +/** + * struct ice_eth56g_mac_reg_cfg - MAC config values for specific PTP registers + * @tx_mode: Tx timestamp compensation mode + * @tx_mk_dly: Tx timestamp marker start strobe delay + * @tx_cw_dly: Tx timestamp codeword start strobe delay + * @rx_mode: Rx timestamp compensation mode + * @rx_mk_dly: Rx timestamp marker start strobe delay + * @rx_cw_dly: Rx timestamp codeword start strobe delay + * @blks_per_clk: number of blocks transferred per clock cycle + * @blktime: block time, fixed point + * @mktime: marker time, fixed point + * @tx_offset: total Tx offset, fixed point + * @rx_offset: total Rx offset, contains value for bitslip/deskew, fixed point + * + * All fixed point registers except Rx offset are 23 bit unsigned ints with + * a 9 bit fractional. + * Rx offset is 11 bit unsigned int with a 9 bit fractional. + */ +struct ice_eth56g_mac_reg_cfg { + struct { + u8 def; + u8 rs; + } tx_mode; + u8 tx_mk_dly; + struct { + u8 def; + u8 onestep; + } tx_cw_dly; + struct { + u8 def; + u8 rs; + } rx_mode; + struct { + u8 def; + u8 rs; + } rx_mk_dly; + struct { + u8 def; + u8 rs; + } rx_cw_dly; + u8 blks_per_clk; + u16 blktime; + u16 mktime; + struct { + u32 serdes; + u32 no_fec; + u32 fc; + u32 rs; + u32 sfd; + u32 onestep; + } tx_offset; + struct { + u32 serdes; + u32 no_fec; + u32 fc; + u32 rs; + u32 sfd; + u32 bs_ds; + } rx_offset; +}; + +extern +const struct ice_eth56g_mac_reg_cfg eth56g_mac_cfg[NUM_ICE_ETH56G_LNK_SPD]; + /** - * struct ice_cgu_pll_params_e82x + * struct ice_cgu_pll_params_e82x - E82X CGU parameters * @refclk_pre_div: Reference clock pre-divisor * @feedback_div: Feedback divisor * @frac_n_div: Fractional divisor @@ -185,11 +285,36 @@ struct ice_cgu_pin_desc { extern const struct ice_cgu_pll_params_e82x e822_cgu_params[NUM_ICE_TIME_REF_FREQ]; +/** + * struct ice_cgu_pll_params_e825c - E825C CGU parameters + * @tspll_ck_refclkfreq: tspll_ck_refclkfreq selection + * @tspll_ndivratio: ndiv ratio that goes directly to the pll + * @tspll_fbdiv_intgr: TS PLL integer feedback divide + * @tspll_fbdiv_frac: TS PLL fractional feedback divide + * @ref1588_ck_div: clock divider for tspll ref + * + * Clock Generation Unit parameters used to program the PLL based on the + * selected TIME_REF/TCXO frequency. + */ +struct ice_cgu_pll_params_e825c { + u32 tspll_ck_refclkfreq; + u32 tspll_ndivratio; + u32 tspll_fbdiv_intgr; + u32 tspll_fbdiv_frac; + u32 ref1588_ck_div; +}; + +extern const struct +ice_cgu_pll_params_e825c e825c_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 ETH56G PHY resources */ +extern const struct ice_phy_reg_info_eth56g eth56g_phy_res[NUM_ETH56G_PHY_RES]; + /* Table of constants related to possible TIME_REF sources */ -extern const struct ice_time_ref_info_e82x e822_time_ref[NUM_ICE_TIME_REF_FREQ]; +extern const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ]; /* Table of constants for Vernier calibration on E822 */ extern const struct ice_vernier_info_e82x e822_vernier[NUM_ICE_PTP_LNK_SPD]; @@ -197,10 +322,13 @@ extern const struct ice_vernier_info_e82x e822_vernier[NUM_ICE_PTP_LNK_SPD]; /* Increment value to generate nanoseconds in the GLTSYN_TIME_L register for * the E810 devices. Based off of a PLL with an 812.5 MHz frequency. */ -#define ICE_PTP_NOMINAL_INCVAL_E810 0x13b13b13bULL +#define ICE_E810_PLL_FREQ 812500000 +#define ICE_PTP_NOMINAL_INCVAL_E810 0x13b13b13bULL +#define ICE_E810_E830_SYNC_DELAY 0 /* Device agnostic functions */ u8 ice_get_ptp_src_clock_index(struct ice_hw *hw); +int ice_cgu_cfg_pps_out(struct ice_hw *hw, bool enable); 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); @@ -208,11 +336,15 @@ 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); int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj); +int ice_ptp_clear_phy_offset_ready_e82x(struct ice_hw *hw); int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp); int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx); void ice_ptp_reset_ts_memory(struct ice_hw *hw); int ice_ptp_init_phc(struct ice_hw *hw); +void ice_ptp_init_hw(struct ice_hw *hw); int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready); +int ice_ptp_one_port_cmd(struct ice_hw *hw, u8 configured_port, + enum ice_ptp_tmr_cmd configured_cmd); /* E822 family functions */ int ice_read_quad_reg_e82x(struct ice_hw *hw, u8 quad, u16 offset, u32 *val); @@ -225,7 +357,7 @@ void ice_ptp_reset_ts_memory_quad_e82x(struct ice_hw *hw, u8 quad); * * Returns the current TIME_REF from the capabilities structure. */ -static inline enum ice_time_ref_freq ice_e82x_time_ref(struct ice_hw *hw) +static inline enum ice_time_ref_freq ice_e82x_time_ref(const struct ice_hw *hw) { return hw->func_caps.ts_func_info.time_ref; } @@ -246,17 +378,12 @@ ice_set_e82x_time_ref(struct ice_hw *hw, enum ice_time_ref_freq time_ref) static inline u64 ice_e82x_pll_freq(enum ice_time_ref_freq time_ref) { - return e822_time_ref[time_ref].pll_freq; + return e82x_time_ref[time_ref].pll_freq; } static inline u64 ice_e82x_nominal_incval(enum ice_time_ref_freq time_ref) { - return e822_time_ref[time_ref].nominal_incval; -} - -static inline u64 ice_e82x_pps_delay(enum ice_time_ref_freq time_ref) -{ - return e822_time_ref[time_ref].pps_delay; + return e82x_time_ref[time_ref].nominal_incval; } /* E822 Vernier calibration functions */ @@ -264,13 +391,13 @@ int ice_stop_phy_timer_e82x(struct ice_hw *hw, u8 port, bool soft_reset); int ice_start_phy_timer_e82x(struct ice_hw *hw, u8 port); int ice_phy_cfg_tx_offset_e82x(struct ice_hw *hw, u8 port); int ice_phy_cfg_rx_offset_e82x(struct ice_hw *hw, u8 port); +int ice_phy_cfg_intr_e82x(struct ice_hw *hw, u8 quad, bool ena, u8 threshold); /* E810 family functions */ -int ice_ptp_init_phy_e810(struct ice_hw *hw); -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); +int ice_read_sma_ctrl(struct ice_hw *hw, u8 *data); +int ice_write_sma_ctrl(struct ice_hw *hw, u8 data); +int ice_ptp_read_sdp_ac(struct ice_hw *hw, __le16 *entries, uint *num_entries); +int ice_cgu_get_num_pins(struct ice_hw *hw, bool input); 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); @@ -280,11 +407,43 @@ int ice_get_cgu_state(struct ice_hw *hw, u8 dpll_idx, 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); +/* ETH56G family functions */ +int ice_ptp_read_tx_hwtstamp_status_eth56g(struct ice_hw *hw, u32 *ts_status); +int ice_stop_phy_timer_eth56g(struct ice_hw *hw, u8 port, bool soft_reset); +int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port); +int ice_phy_cfg_intr_eth56g(struct ice_hw *hw, u8 port, bool ena, u8 threshold); +int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port); + +#define ICE_ETH56G_NOMINAL_INCVAL 0x140000000ULL +#define ICE_ETH56G_NOMINAL_PCS_REF_TUS 0x100000000ULL +#define ICE_ETH56G_NOMINAL_PCS_REF_INC 0x300000000ULL +#define ICE_ETH56G_NOMINAL_THRESH4 0x7777 +#define ICE_ETH56G_NOMINAL_TX_THRESH 0x6 + +/** + * ice_get_base_incval - Get base clock increment value + * @hw: pointer to the HW struct + * + * Return: base clock increment value for supported PHYs, 0 otherwise + */ +static inline u64 ice_get_base_incval(struct ice_hw *hw) +{ + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: + return ICE_PTP_NOMINAL_INCVAL_E810; + case ICE_MAC_GENERIC: + return ice_e82x_nominal_incval(ice_e82x_time_ref(hw)); + case ICE_MAC_GENERIC_3K_E825: + return ICE_ETH56G_NOMINAL_INCVAL; + default: + return 0; + } +} + #define PFTSYN_SEM_BYTES 4 #define ICE_PTP_CLOCK_INDEX_0 0x00 @@ -312,6 +471,7 @@ int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id, #define TS_CMD_MASK_E810 0xFF #define TS_CMD_MASK 0xF #define SYNC_EXEC_CMD 0x3 +#define TS_CMD_RX_TYPE ICE_M(0x18, 0x4) /* Macros to derive port low and high addresses on both quads */ #define P_Q0_L(a, p) ((((a) + (0x2000 * (p)))) & 0xFFFF) @@ -344,11 +504,8 @@ int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id, #define Q_REG_TX_MEM_GBL_CFG 0xC08 #define Q_REG_TX_MEM_GBL_CFG_LANE_TYPE_S 0 #define Q_REG_TX_MEM_GBL_CFG_LANE_TYPE_M BIT(0) -#define Q_REG_TX_MEM_GBL_CFG_TX_TYPE_S 1 #define Q_REG_TX_MEM_GBL_CFG_TX_TYPE_M ICE_M(0xFF, 1) -#define Q_REG_TX_MEM_GBL_CFG_INTR_THR_S 9 #define Q_REG_TX_MEM_GBL_CFG_INTR_THR_M ICE_M(0x3F, 9) -#define Q_REG_TX_MEM_GBL_CFG_INTR_ENA_S 15 #define Q_REG_TX_MEM_GBL_CFG_INTR_ENA_M BIT(15) /* Tx Timestamp data registers */ @@ -380,7 +537,7 @@ int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id, #define P_REG_TIMETUS_L 0x410 #define P_REG_TIMETUS_U 0x414 -#define P_REG_40B_LOW_M 0xFF +#define P_REG_40B_LOW_M GENMASK(7, 0) #define P_REG_40B_HIGH_S 8 /* PHY window length registers */ @@ -487,30 +644,43 @@ int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id, #define ETH_GLTSYN_SHADJ_H(_i) (0x0300037C + ((_i) * 32)) /* E810 timer command register */ -#define ETH_GLTSYN_CMD 0x03000344 +#define E810_ETH_GLTSYN_CMD 0x03000344 + +/* E830 timer command register */ +#define E830_ETH_GLTSYN_CMD 0x00088814 + +/* E810 PHC time register */ +#define E830_GLTSYN_TIME_L(_tmr_idx) (0x0008A000 + 0x1000 * (_tmr_idx)) /* Source timer incval macros */ #define INCVAL_HIGH_M 0xFF -/* Timestamp block macros */ +/* PHY 40b registers macros */ +#define PHY_EXT_40B_LOW_M GENMASK(31, 0) +#define PHY_EXT_40B_HIGH_M GENMASK_ULL(39, 32) +#define PHY_40B_LOW_M GENMASK(7, 0) +#define PHY_40B_HIGH_M GENMASK_ULL(39, 8) #define TS_VALID BIT(0) #define TS_LOW_M 0xFFFFFFFF #define TS_HIGH_M 0xFF #define TS_HIGH_S 32 -#define TS_PHY_LOW_M 0xFF -#define TS_PHY_HIGH_M 0xFFFFFFFF -#define TS_PHY_HIGH_S 8 - #define BYTES_PER_IDX_ADDR_L_U 8 #define BYTES_PER_IDX_ADDR_L 4 /* Tx timestamp low latency read definitions */ -#define TS_LL_READ_RETRIES 200 -#define TS_LL_READ_TS_HIGH GENMASK(23, 16) -#define TS_LL_READ_TS_IDX GENMASK(29, 24) -#define TS_LL_READ_TS_INTR BIT(30) -#define TS_LL_READ_TS BIT(31) +#define REG_LL_PROXY_H_TIMEOUT_US 2000 +#define REG_LL_PROXY_H_PHY_TMR_CMD_M GENMASK(7, 6) +#define REG_LL_PROXY_H_PHY_TMR_CMD_ADJ 0x1 +#define REG_LL_PROXY_H_PHY_TMR_CMD_FREQ 0x2 +#define REG_LL_PROXY_H_TS_HIGH GENMASK(23, 16) +#define REG_LL_PROXY_H_PHY_TMR_IDX_M BIT(24) +#define REG_LL_PROXY_H_TS_IDX GENMASK(29, 24) +#define REG_LL_PROXY_H_TS_INTR_ENA BIT(30) +#define REG_LL_PROXY_H_EXEC BIT(31) + +#define REG_LL_PROXY_L PF_SB_ATQBAH +#define REG_LL_PROXY_H PF_SB_ATQBAL /* Internal PHY timestamp address */ #define TS_L(a, idx) ((a) + ((idx) * BYTES_PER_IDX_ADDR_L_U)) @@ -524,29 +694,134 @@ int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id, #define LOW_TX_MEMORY_BANK_START 0x03090000 #define HIGH_TX_MEMORY_BANK_START 0x03090004 -/* E810T SMA controller pin control */ -#define ICE_SMA1_DIR_EN_E810T BIT(4) -#define ICE_SMA1_TX_EN_E810T BIT(5) -#define ICE_SMA2_UFL2_RX_DIS_E810T BIT(3) -#define ICE_SMA2_DIR_EN_E810T BIT(6) -#define ICE_SMA2_TX_EN_E810T BIT(7) - -#define ICE_SMA1_MASK_E810T (ICE_SMA1_DIR_EN_E810T | \ - ICE_SMA1_TX_EN_E810T) -#define ICE_SMA2_MASK_E810T (ICE_SMA2_UFL2_RX_DIS_E810T | \ - ICE_SMA2_DIR_EN_E810T | \ - ICE_SMA2_TX_EN_E810T) -#define ICE_ALL_SMA_MASK_E810T (ICE_SMA1_MASK_E810T | \ - ICE_SMA2_MASK_E810T) - -#define ICE_SMA_MIN_BIT_E810T 3 -#define ICE_SMA_MAX_BIT_E810T 7 +/* SMA controller pin control */ +#define ICE_SMA1_DIR_EN BIT(4) +#define ICE_SMA1_TX_EN BIT(5) +#define ICE_SMA2_UFL2_RX_DIS BIT(3) +#define ICE_SMA2_DIR_EN BIT(6) +#define ICE_SMA2_TX_EN BIT(7) + +#define ICE_SMA1_MASK (ICE_SMA1_DIR_EN | ICE_SMA1_TX_EN) +#define ICE_SMA2_MASK (ICE_SMA2_UFL2_RX_DIS | ICE_SMA2_DIR_EN | \ + ICE_SMA2_TX_EN) +#define ICE_ALL_SMA_MASK (ICE_SMA1_MASK | ICE_SMA2_MASK) + +#define ICE_SMA_MIN_BIT 3 +#define ICE_SMA_MAX_BIT 7 #define ICE_PCA9575_P1_OFFSET 8 -/* E810T PCA9575 IO controller registers */ +/* PCA9575 IO controller registers */ #define ICE_PCA9575_P0_IN 0x0 -/* E810T PCA9575 IO controller pin control */ -#define ICE_E810T_P0_GNSS_PRSNT_N BIT(4) +/* PCA9575 IO controller pin control */ +#define ICE_P0_GNSS_PRSNT_N BIT(4) + +/* ETH56G PHY register addresses */ +/* Timestamp PHY incval registers */ +#define PHY_REG_TIMETUS_L 0x8 +#define PHY_REG_TIMETUS_U 0xC + +/* Timestamp PCS registers */ +#define PHY_PCS_REF_TUS_L 0x18 +#define PHY_PCS_REF_TUS_U 0x1C + +/* Timestamp PCS ref incval registers */ +#define PHY_PCS_REF_INC_L 0x20 +#define PHY_PCS_REF_INC_U 0x24 + +/* Timestamp init registers */ +#define PHY_REG_RX_TIMER_INC_PRE_L 0x64 +#define PHY_REG_RX_TIMER_INC_PRE_U 0x68 +#define PHY_REG_TX_TIMER_INC_PRE_L 0x44 +#define PHY_REG_TX_TIMER_INC_PRE_U 0x48 + +/* Timestamp match and adjust target registers */ +#define PHY_REG_RX_TIMER_CNT_ADJ_L 0x6C +#define PHY_REG_RX_TIMER_CNT_ADJ_U 0x70 +#define PHY_REG_TX_TIMER_CNT_ADJ_L 0x4C +#define PHY_REG_TX_TIMER_CNT_ADJ_U 0x50 + +/* Timestamp command registers */ +#define PHY_REG_TX_TMR_CMD 0x40 +#define PHY_REG_RX_TMR_CMD 0x60 + +/* Phy offset ready registers */ +#define PHY_REG_TX_OFFSET_READY 0x54 +#define PHY_REG_RX_OFFSET_READY 0x74 + +/* Phy total offset registers */ +#define PHY_REG_TOTAL_TX_OFFSET_L 0x38 +#define PHY_REG_TOTAL_TX_OFFSET_U 0x3C +#define PHY_REG_TOTAL_RX_OFFSET_L 0x58 +#define PHY_REG_TOTAL_RX_OFFSET_U 0x5C + +/* Timestamp capture registers */ +#define PHY_REG_TX_CAPTURE_L 0x78 +#define PHY_REG_TX_CAPTURE_U 0x7C +#define PHY_REG_RX_CAPTURE_L 0x8C +#define PHY_REG_RX_CAPTURE_U 0x90 + +/* Memory status registers */ +#define PHY_REG_TX_MEMORY_STATUS_L 0x80 +#define PHY_REG_TX_MEMORY_STATUS_U 0x84 + +/* Interrupt config register */ +#define PHY_REG_TS_INT_CONFIG 0x88 + +/* XIF mode config register */ +#define PHY_MAC_XIF_MODE 0x24 +#define PHY_MAC_XIF_1STEP_ENA_M ICE_M(0x1, 5) +#define PHY_MAC_XIF_TS_BIN_MODE_M ICE_M(0x1, 11) +#define PHY_MAC_XIF_TS_SFD_ENA_M ICE_M(0x1, 20) +#define PHY_MAC_XIF_GMII_TS_SEL_M ICE_M(0x1, 21) + +#define PHY_TS_INT_CONFIG_THRESHOLD_M ICE_M(0x3F, 0) +#define PHY_TS_INT_CONFIG_ENA_M BIT(6) + +/* Macros to derive offsets for TimeStampLow and TimeStampHigh */ +#define PHY_TSTAMP_L(x) (((x) * 8) + 0) +#define PHY_TSTAMP_U(x) (((x) * 8) + 4) + +#define PHY_REG_DESKEW_0 0x94 +#define PHY_REG_DESKEW_0_RLEVEL GENMASK(6, 0) +#define PHY_REG_DESKEW_0_RLEVEL_FRAC GENMASK(9, 7) +#define PHY_REG_DESKEW_0_RLEVEL_FRAC_W 3 +#define PHY_REG_DESKEW_0_VALID GENMASK(10, 10) + +#define PHY_REG_SD_BIT_SLIP(_port_offset) (0x29C + 4 * (_port_offset)) +#define PHY_REVISION_ETH56G 0x10200 +#define PHY_VENDOR_TXLANE_THRESH 0x2000C + +#define PHY_MAC_TSU_CONFIG 0x40 +#define PHY_MAC_TSU_CFG_RX_MODE_M ICE_M(0x7, 0) +#define PHY_MAC_TSU_CFG_RX_MII_CW_DLY_M ICE_M(0x7, 4) +#define PHY_MAC_TSU_CFG_RX_MII_MK_DLY_M ICE_M(0x7, 8) +#define PHY_MAC_TSU_CFG_TX_MODE_M ICE_M(0x7, 12) +#define PHY_MAC_TSU_CFG_TX_MII_CW_DLY_M ICE_M(0x1F, 16) +#define PHY_MAC_TSU_CFG_TX_MII_MK_DLY_M ICE_M(0x1F, 21) +#define PHY_MAC_TSU_CFG_BLKS_PER_CLK_M ICE_M(0x1, 28) +#define PHY_MAC_RX_MODULO 0x44 +#define PHY_MAC_RX_OFFSET 0x48 +#define PHY_MAC_RX_OFFSET_M ICE_M(0xFFFFFF, 0) +#define PHY_MAC_TX_MODULO 0x4C +#define PHY_MAC_BLOCKTIME 0x50 +#define PHY_MAC_MARKERTIME 0x54 +#define PHY_MAC_TX_OFFSET 0x58 +#define PHY_GPCS_BITSLIP 0x5C + +#define PHY_PTP_INT_STATUS 0x7FD140 + +/* ETH56G registers shared per quad */ +/* GPCS config register */ +#define PHY_GPCS_CONFIG_REG0 0x268 +#define PHY_GPCS_CONFIG_REG0_TX_THR_M GENMASK(27, 24) +/* 1-step PTP config */ +#define PHY_PTP_1STEP_CONFIG 0x270 +#define PHY_PTP_1STEP_T1S_UP64_M GENMASK(7, 4) +#define PHY_PTP_1STEP_T1S_DELTA_M GENMASK(11, 8) +#define PHY_PTP_1STEP_PEER_DELAY(_quad_lane) (0x274 + 4 * (_quad_lane)) +#define PHY_PTP_1STEP_PD_ADD_PD_M BIT(0) +#define PHY_PTP_1STEP_PD_DELAY_M GENMASK(30, 1) +#define PHY_PTP_1STEP_PD_DLY_V_M BIT(31) #endif /* _ICE_PTP_HW_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c index 5f30fb131f74..cb08746556a6 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.c +++ b/drivers/net/ethernet/intel/ice/ice_repr.c @@ -3,42 +3,51 @@ #include "ice.h" #include "ice_eswitch.h" -#include "ice_devlink.h" +#include "devlink/devlink.h" +#include "devlink/port.h" #include "ice_sriov.h" #include "ice_tc_lib.h" #include "ice_dcb_lib.h" /** - * ice_repr_get_sw_port_id - get port ID associated with representor - * @repr: pointer to port representor + * ice_repr_inc_tx_stats - increment Tx statistic by one packet + * @repr: repr to increment stats on + * @len: length of the packet + * @xmit_status: value returned by xmit function */ -static int ice_repr_get_sw_port_id(struct ice_repr *repr) +void ice_repr_inc_tx_stats(struct ice_repr *repr, unsigned int len, + int xmit_status) { - return repr->src_vsi->back->hw.port_info->lport; + struct ice_repr_pcpu_stats *stats; + + if (unlikely(xmit_status != NET_XMIT_SUCCESS && + xmit_status != NET_XMIT_CN)) { + this_cpu_inc(repr->stats->tx_drops); + return; + } + + stats = this_cpu_ptr(repr->stats); + u64_stats_update_begin(&stats->syncp); + stats->tx_packets++; + stats->tx_bytes += len; + u64_stats_update_end(&stats->syncp); } /** - * ice_repr_get_phys_port_name - get phys port name - * @netdev: pointer to port representor netdev - * @buf: write here port name - * @len: max length of buf + * ice_repr_inc_rx_stats - increment Rx statistic by one packet + * @netdev: repr netdev to increment stats on + * @len: length of the packet */ -static int -ice_repr_get_phys_port_name(struct net_device *netdev, char *buf, size_t len) +void ice_repr_inc_rx_stats(struct net_device *netdev, unsigned int len) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_repr *repr = np->repr; - int res; - - /* Devlink port is registered and devlink core is taking care of name formatting. */ - if (repr->vf->devlink_port.devlink) - return -EOPNOTSUPP; + struct ice_repr *repr = ice_netdev_to_repr(netdev); + struct ice_repr_pcpu_stats *stats; - res = snprintf(buf, len, "pf%dvfr%d", ice_repr_get_sw_port_id(repr), - repr->id); - if (res <= 0) - return -EOPNOTSUPP; - return 0; + stats = this_cpu_ptr(repr->stats); + u64_stats_update_begin(&stats->syncp); + stats->rx_packets++; + stats->rx_bytes += len; + u64_stats_update_end(&stats->syncp); } /** @@ -50,12 +59,13 @@ static void ice_repr_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) { struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_repr *repr = np->repr; struct ice_eth_stats *eth_stats; struct ice_vsi *vsi; - if (ice_is_vf_disabled(np->repr->vf)) + if (repr->ops.ready(repr)) return; - vsi = np->repr->src_vsi; + vsi = repr->src_vsi; ice_update_vsi_stats(vsi); eth_stats = &vsi->eth_stats; @@ -76,7 +86,7 @@ ice_repr_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) * ice_netdev_to_repr - Get port representor for given netdevice * @netdev: pointer to port representor netdev */ -struct ice_repr *ice_netdev_to_repr(struct net_device *netdev) +struct ice_repr *ice_netdev_to_repr(const struct net_device *netdev) { struct ice_netdev_priv *np = netdev_priv(netdev); @@ -84,7 +94,7 @@ struct ice_repr *ice_netdev_to_repr(struct net_device *netdev) } /** - * ice_repr_open - Enable port representor's network interface + * ice_repr_vf_open - Enable port representor's network interface * @netdev: network interface device structure * * The open entry point is called when a port representor's network @@ -93,7 +103,7 @@ struct ice_repr *ice_netdev_to_repr(struct net_device *netdev) * * Returns 0 on success */ -static int ice_repr_open(struct net_device *netdev) +static int ice_repr_vf_open(struct net_device *netdev) { struct ice_repr *repr = ice_netdev_to_repr(netdev); struct ice_vf *vf; @@ -109,8 +119,16 @@ static int ice_repr_open(struct net_device *netdev) return 0; } +static int ice_repr_sf_open(struct net_device *netdev) +{ + netif_carrier_on(netdev); + netif_tx_start_all_queues(netdev); + + return 0; +} + /** - * ice_repr_stop - Disable port representor's network interface + * ice_repr_vf_stop - Disable port representor's network interface * @netdev: network interface device structure * * The stop entry point is called when a port representor's network @@ -119,7 +137,7 @@ static int ice_repr_open(struct net_device *netdev) * * Returns 0 on success */ -static int ice_repr_stop(struct net_device *netdev) +static int ice_repr_vf_stop(struct net_device *netdev) { struct ice_repr *repr = ice_netdev_to_repr(netdev); struct ice_vf *vf; @@ -135,42 +153,47 @@ static int ice_repr_stop(struct net_device *netdev) return 0; } +static int ice_repr_sf_stop(struct net_device *netdev) +{ + netif_carrier_off(netdev); + netif_tx_stop_all_queues(netdev); + + return 0; +} + /** * ice_repr_sp_stats64 - get slow path stats for port representor * @dev: network interface device structure * @stats: netlink stats structure - * - * RX/TX stats are being swapped here to be consistent with VF stats. In slow - * path, port representor receives data when the corresponding VF is sending it - * (and vice versa), TX and RX bytes/packets are effectively swapped on port - * representor. */ static int ice_repr_sp_stats64(const struct net_device *dev, struct rtnl_link_stats64 *stats) { - struct ice_netdev_priv *np = netdev_priv(dev); - int vf_id = np->repr->vf->vf_id; - struct ice_tx_ring *tx_ring; - struct ice_rx_ring *rx_ring; - u64 pkts, bytes; - - tx_ring = np->vsi->tx_rings[vf_id]; - ice_fetch_u64_stats_per_ring(&tx_ring->ring_stats->syncp, - tx_ring->ring_stats->stats, - &pkts, &bytes); - stats->rx_packets = pkts; - stats->rx_bytes = bytes; - - rx_ring = np->vsi->rx_rings[vf_id]; - ice_fetch_u64_stats_per_ring(&rx_ring->ring_stats->syncp, - rx_ring->ring_stats->stats, - &pkts, &bytes); - stats->tx_packets = pkts; - stats->tx_bytes = bytes; - stats->tx_dropped = rx_ring->ring_stats->rx_stats.alloc_page_failed + - rx_ring->ring_stats->rx_stats.alloc_buf_failed; - + struct ice_repr *repr = ice_netdev_to_repr(dev); + int i; + + for_each_possible_cpu(i) { + u64 tbytes, tpkts, tdrops, rbytes, rpkts; + struct ice_repr_pcpu_stats *repr_stats; + unsigned int start; + + repr_stats = per_cpu_ptr(repr->stats, i); + do { + start = u64_stats_fetch_begin(&repr_stats->syncp); + tbytes = repr_stats->tx_bytes; + tpkts = repr_stats->tx_packets; + tdrops = repr_stats->tx_drops; + rbytes = repr_stats->rx_bytes; + rpkts = repr_stats->rx_packets; + } while (u64_stats_fetch_retry(&repr_stats->syncp, start)); + + stats->tx_bytes += tbytes; + stats->tx_packets += tpkts; + stats->tx_dropped += tdrops; + stats->rx_bytes += rbytes; + stats->rx_packets += rpkts; + } return 0; } @@ -196,7 +219,8 @@ ice_repr_setup_tc_cls_flower(struct ice_repr *repr, { switch (flower->command) { case FLOW_CLS_REPLACE: - return ice_add_cls_flower(repr->netdev, repr->src_vsi, flower); + return ice_add_cls_flower(repr->netdev, repr->src_vsi, flower, + true); case FLOW_CLS_DESTROY: return ice_del_cls_flower(repr->src_vsi, flower); default: @@ -239,11 +263,20 @@ ice_repr_setup_tc(struct net_device *netdev, enum tc_setup_type type, } } -static const struct net_device_ops ice_repr_netdev_ops = { - .ndo_get_phys_port_name = ice_repr_get_phys_port_name, +static const struct net_device_ops ice_repr_vf_netdev_ops = { .ndo_get_stats64 = ice_repr_get_stats64, - .ndo_open = ice_repr_open, - .ndo_stop = ice_repr_stop, + .ndo_open = ice_repr_vf_open, + .ndo_stop = ice_repr_vf_stop, + .ndo_start_xmit = ice_eswitch_port_start_xmit, + .ndo_setup_tc = ice_repr_setup_tc, + .ndo_has_offload_stats = ice_repr_ndo_has_offload_stats, + .ndo_get_offload_stats = ice_repr_ndo_get_offload_stats, +}; + +static const struct net_device_ops ice_repr_sf_netdev_ops = { + .ndo_get_stats64 = ice_repr_get_stats64, + .ndo_open = ice_repr_sf_open, + .ndo_stop = ice_repr_sf_stop, .ndo_start_xmit = ice_eswitch_port_start_xmit, .ndo_setup_tc = ice_repr_setup_tc, .ndo_has_offload_stats = ice_repr_ndo_has_offload_stats, @@ -256,18 +289,20 @@ static const struct net_device_ops ice_repr_netdev_ops = { */ bool ice_is_port_repr_netdev(const struct net_device *netdev) { - return netdev && (netdev->netdev_ops == &ice_repr_netdev_ops); + return netdev && (netdev->netdev_ops == &ice_repr_vf_netdev_ops || + netdev->netdev_ops == &ice_repr_sf_netdev_ops); } /** * ice_repr_reg_netdev - register port representor netdev * @netdev: pointer to port representor netdev + * @ops: new ops for netdev */ static int -ice_repr_reg_netdev(struct net_device *netdev) +ice_repr_reg_netdev(struct net_device *netdev, const struct net_device_ops *ops) { eth_hw_addr_random(netdev); - netdev->netdev_ops = &ice_repr_netdev_ops; + netdev->netdev_ops = ops; ice_set_ethtool_repr_ops(netdev); netdev->hw_features |= NETIF_F_HW_TC; @@ -278,60 +313,58 @@ ice_repr_reg_netdev(struct net_device *netdev) return register_netdev(netdev); } -static void ice_repr_remove_node(struct devlink_port *devlink_port) +static int ice_repr_ready_vf(struct ice_repr *repr) { - devl_lock(devlink_port->devlink); - devl_rate_leaf_destroy(devlink_port); - devl_unlock(devlink_port->devlink); + return !ice_check_vf_ready_for_cfg(repr->vf); +} + +static int ice_repr_ready_sf(struct ice_repr *repr) +{ + return !repr->sf->active; } /** - * ice_repr_rem - remove representor from VF + * ice_repr_destroy - remove representor from VF * @repr: pointer to representor structure */ -static void ice_repr_rem(struct ice_repr *repr) +void ice_repr_destroy(struct ice_repr *repr) { - kfree(repr->q_vector); + free_percpu(repr->stats); free_netdev(repr->netdev); kfree(repr); } -/** - * ice_repr_rem_vf - remove representor from VF - * @repr: pointer to representor structure - */ -void ice_repr_rem_vf(struct ice_repr *repr) +static void ice_repr_rem_vf(struct ice_repr *repr) { - ice_repr_remove_node(&repr->vf->devlink_port); + ice_eswitch_decfg_vsi(repr->src_vsi, repr->parent_mac); + ice_pass_vf_tx_lldp(repr->src_vsi, true); unregister_netdev(repr->netdev); ice_devlink_destroy_vf_port(repr->vf); ice_virtchnl_set_dflt_ops(repr->vf); - ice_repr_rem(repr); } -static void ice_repr_set_tx_topology(struct ice_pf *pf) +static void ice_repr_rem_sf(struct ice_repr *repr) { - struct devlink *devlink; + unregister_netdev(repr->netdev); + ice_devlink_destroy_sf_port(repr->sf); +} +static void ice_repr_set_tx_topology(struct ice_pf *pf, struct devlink *devlink) +{ /* only export if ADQ and DCB disabled and eswitch enabled*/ if (ice_is_adq_active(pf) || ice_is_dcb_active(pf) || !ice_is_switchdev_running(pf)) return; - devlink = priv_to_devlink(pf); ice_devlink_rate_init_tx_topology(devlink, ice_get_main_vsi(pf)); } /** - * ice_repr_add - add representor for generic VSI - * @pf: pointer to PF structure + * ice_repr_create - add representor for generic VSI * @src_vsi: pointer to VSI structure of device to represent - * @parent_mac: device MAC address */ -static struct ice_repr * -ice_repr_add(struct ice_pf *pf, struct ice_vsi *src_vsi, const u8 *parent_mac) +static struct ice_repr *ice_repr_create(struct ice_vsi *src_vsi) { - struct ice_q_vector *q_vector; struct ice_netdev_priv *np; struct ice_repr *repr; int err; @@ -346,78 +379,153 @@ ice_repr_add(struct ice_pf *pf, struct ice_vsi *src_vsi, const u8 *parent_mac) goto err_alloc; } + repr->stats = netdev_alloc_pcpu_stats(struct ice_repr_pcpu_stats); + if (!repr->stats) { + err = -ENOMEM; + goto err_stats; + } + repr->src_vsi = src_vsi; + repr->id = src_vsi->vsi_num; np = netdev_priv(repr->netdev); np->repr = repr; - q_vector = kzalloc(sizeof(*q_vector), GFP_KERNEL); - if (!q_vector) { - err = -ENOMEM; - goto err_alloc_q_vector; - } - repr->q_vector = q_vector; - repr->q_id = repr->id; + repr->netdev->min_mtu = ETH_MIN_MTU; + repr->netdev->max_mtu = ICE_MAX_MTU; - ether_addr_copy(repr->parent_mac, parent_mac); + SET_NETDEV_DEV(repr->netdev, ice_pf_to_dev(src_vsi->back)); return repr; -err_alloc_q_vector: +err_stats: free_netdev(repr->netdev); err_alloc: kfree(repr); return ERR_PTR(err); } -struct ice_repr *ice_repr_add_vf(struct ice_vf *vf) +static int ice_repr_add_vf(struct ice_repr *repr) { - struct ice_repr *repr; - struct ice_vsi *vsi; + struct ice_vf *vf = repr->vf; + struct devlink *devlink; int err; - vsi = ice_get_vf_vsi(vf); - if (!vsi) - return ERR_PTR(-ENOENT); - err = ice_devlink_create_vf_port(vf); if (err) - return ERR_PTR(err); + return err; - repr = ice_repr_add(vf->pf, vsi, vf->hw_lan_addr); - if (IS_ERR(repr)) { - err = PTR_ERR(repr); - goto err_repr_add; - } + SET_NETDEV_DEVLINK_PORT(repr->netdev, &vf->devlink_port); + err = ice_repr_reg_netdev(repr->netdev, &ice_repr_vf_netdev_ops); + if (err) + goto err_netdev; + + err = ice_drop_vf_tx_lldp(repr->src_vsi, true); + if (err) + goto err_drop_lldp; + + err = ice_eswitch_cfg_vsi(repr->src_vsi, repr->parent_mac); + if (err) + goto err_cfg_vsi; + + ice_virtchnl_set_repr_ops(vf); + + devlink = priv_to_devlink(vf->pf); + ice_repr_set_tx_topology(vf->pf, devlink); + + return 0; + +err_cfg_vsi: + ice_pass_vf_tx_lldp(repr->src_vsi, true); +err_drop_lldp: + unregister_netdev(repr->netdev); +err_netdev: + ice_devlink_destroy_vf_port(vf); + return err; +} +/** + * ice_repr_create_vf - add representor for VF VSI + * @vf: VF to create port representor on + * + * Set correct representor type for VF and functions pointer. + * + * Return: created port representor on success, error otherwise + */ +struct ice_repr *ice_repr_create_vf(struct ice_vf *vf) +{ + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + struct ice_repr *repr; + + if (!vsi) + return ERR_PTR(-EINVAL); + + repr = ice_repr_create(vsi); + if (IS_ERR(repr)) + return repr; + + repr->type = ICE_REPR_TYPE_VF; repr->vf = vf; + repr->ops.add = ice_repr_add_vf; + repr->ops.rem = ice_repr_rem_vf; + repr->ops.ready = ice_repr_ready_vf; - repr->netdev->min_mtu = ETH_MIN_MTU; - repr->netdev->max_mtu = ICE_MAX_MTU; + ether_addr_copy(repr->parent_mac, vf->hw_lan_addr); - SET_NETDEV_DEV(repr->netdev, ice_pf_to_dev(vf->pf)); - SET_NETDEV_DEVLINK_PORT(repr->netdev, &vf->devlink_port); - err = ice_repr_reg_netdev(repr->netdev); + return repr; +} + +static int ice_repr_add_sf(struct ice_repr *repr) +{ + struct ice_dynamic_port *sf = repr->sf; + int err; + + err = ice_devlink_create_sf_port(sf); + if (err) + return err; + + SET_NETDEV_DEVLINK_PORT(repr->netdev, &sf->devlink_port); + err = ice_repr_reg_netdev(repr->netdev, &ice_repr_sf_netdev_ops); if (err) goto err_netdev; - ice_virtchnl_set_repr_ops(vf); - ice_repr_set_tx_topology(vf->pf); + ice_repr_set_tx_topology(sf->vsi->back, priv_to_devlink(sf->vsi->back)); - return repr; + return 0; err_netdev: - ice_repr_rem(repr); -err_repr_add: - ice_devlink_destroy_vf_port(vf); - return ERR_PTR(err); + ice_devlink_destroy_sf_port(sf); + return err; } -struct ice_repr *ice_repr_get_by_vsi(struct ice_vsi *vsi) +/** + * ice_repr_create_sf - add representor for SF VSI + * @sf: SF to create port representor on + * + * Set correct representor type for SF and functions pointer. + * + * Return: created port representor on success, error otherwise + */ +struct ice_repr *ice_repr_create_sf(struct ice_dynamic_port *sf) { - if (!vsi->vf) - return NULL; + struct ice_repr *repr = ice_repr_create(sf->vsi); + + if (IS_ERR(repr)) + return repr; + + repr->type = ICE_REPR_TYPE_SF; + repr->sf = sf; + repr->ops.add = ice_repr_add_sf; + repr->ops.rem = ice_repr_rem_sf; + repr->ops.ready = ice_repr_ready_sf; - return xa_load(&vsi->back->eswitch.reprs, vsi->vf->repr_id); + ether_addr_copy(repr->parent_mac, sf->hw_addr); + + return repr; +} + +struct ice_repr *ice_repr_get(struct ice_pf *pf, u32 id) +{ + return xa_load(&pf->eswitch.reprs, id); } /** @@ -439,15 +547,3 @@ void ice_repr_stop_tx_queues(struct ice_repr *repr) netif_carrier_off(repr->netdev); netif_tx_stop_all_queues(repr->netdev); } - -/** - * ice_repr_set_traffic_vsi - set traffic VSI for port representor - * @repr: repr on with VSI will be set - * @vsi: pointer to VSI that will be used by port representor to pass traffic - */ -void ice_repr_set_traffic_vsi(struct ice_repr *repr, struct ice_vsi *vsi) -{ - struct ice_netdev_priv *np = netdev_priv(repr->netdev); - - np->vsi = vsi; -} diff --git a/drivers/net/ethernet/intel/ice/ice_repr.h b/drivers/net/ethernet/intel/ice/ice_repr.h index f9aede315716..35bd93165e1e 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.h +++ b/drivers/net/ethernet/intel/ice/ice_repr.h @@ -6,32 +6,53 @@ #include <net/dst_metadata.h> +struct ice_repr_pcpu_stats { + struct u64_stats_sync syncp; + u64 rx_packets; + u64 rx_bytes; + u64 tx_packets; + u64 tx_bytes; + u64 tx_drops; +}; + +enum ice_repr_type { + ICE_REPR_TYPE_VF, + ICE_REPR_TYPE_SF, +}; + struct ice_repr { struct ice_vsi *src_vsi; - struct ice_vf *vf; - struct ice_q_vector *q_vector; struct net_device *netdev; struct metadata_dst *dst; struct ice_esw_br_port *br_port; - int q_id; + struct ice_repr_pcpu_stats __percpu *stats; u32 id; u8 parent_mac[ETH_ALEN]; -#ifdef CONFIG_ICE_SWITCHDEV - /* info about slow path rule */ - struct ice_rule_query_data sp_rule; -#endif + enum ice_repr_type type; + union { + struct ice_vf *vf; + struct ice_dynamic_port *sf; + }; + struct { + int (*add)(struct ice_repr *repr); + void (*rem)(struct ice_repr *repr); + int (*ready)(struct ice_repr *repr); + } ops; }; -struct ice_repr *ice_repr_add_vf(struct ice_vf *vf); -void ice_repr_rem_vf(struct ice_repr *repr); +struct ice_repr *ice_repr_create_vf(struct ice_vf *vf); +struct ice_repr *ice_repr_create_sf(struct ice_dynamic_port *sf); + +void ice_repr_destroy(struct ice_repr *repr); void ice_repr_start_tx_queues(struct ice_repr *repr); 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); +struct ice_repr *ice_netdev_to_repr(const struct net_device *netdev); bool ice_is_port_repr_netdev(const struct net_device *netdev); -struct ice_repr *ice_repr_get_by_vsi(struct ice_vsi *vsi); +void ice_repr_inc_tx_stats(struct ice_repr *repr, unsigned int len, + int xmit_status); +void ice_repr_inc_rx_stats(struct net_device *netdev, unsigned int len); +struct ice_repr *ice_repr_get(struct ice_pf *pf, u32 id); #endif diff --git a/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h b/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h index ead75fe2bcda..183dd5457d6a 100644 --- a/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h @@ -46,11 +46,10 @@ struct ice_sbq_evt_desc { u8 data[24]; }; -enum ice_sbq_msg_dev { - rmn_0 = 0x02, - rmn_1 = 0x03, - rmn_2 = 0x04, - cgu = 0x06 +enum ice_sbq_dev_id { + ice_sbq_dev_phy_0 = 0x02, + ice_sbq_dev_cgu = 0x06, + ice_sbq_dev_phy_0_peer = 0x0D, }; enum ice_sbq_msg_opcode { diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index a1525992d14b..6ca13c5dcb14 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -28,9 +28,8 @@ ice_sched_add_root_node(struct ice_port_info *pi, if (!root) return -ENOMEM; - /* coverity[suspicious_sizeof] */ root->children = devm_kcalloc(ice_hw_to_dev(hw), hw->max_children[0], - sizeof(*root), GFP_KERNEL); + sizeof(*root->children), GFP_KERNEL); if (!root->children) { devm_kfree(ice_hw_to_dev(hw), root); return -ENOMEM; @@ -186,10 +185,9 @@ ice_sched_add_node(struct ice_port_info *pi, u8 layer, if (!node) return -ENOMEM; if (hw->max_children[layer]) { - /* coverity[suspicious_sizeof] */ node->children = devm_kcalloc(ice_hw_to_dev(hw), hw->max_children[layer], - sizeof(*node), GFP_KERNEL); + sizeof(*node->children), GFP_KERNEL); if (!node->children) { devm_kfree(ice_hw_to_dev(hw), node); return -ENOMEM; @@ -1128,12 +1126,11 @@ u8 ice_sched_get_vsi_layer(struct ice_hw *hw) * 5 or less sw_entry_point_layer */ /* calculate the VSI layer based on number of layers. */ - if (hw->num_tx_sched_layers > ICE_VSI_LAYER_OFFSET + 1) { - u8 layer = hw->num_tx_sched_layers - ICE_VSI_LAYER_OFFSET; - - if (layer > hw->sw_entry_point_layer) - return layer; - } + if (hw->num_tx_sched_layers == ICE_SCHED_9_LAYERS) + return hw->num_tx_sched_layers - ICE_VSI_LAYER_OFFSET; + else if (hw->num_tx_sched_layers == ICE_SCHED_5_LAYERS) + /* qgroup and VSI layers are same */ + return hw->num_tx_sched_layers - ICE_QGRP_LAYER_OFFSET; return hw->sw_entry_point_layer; } @@ -1150,13 +1147,10 @@ u8 ice_sched_get_agg_layer(struct ice_hw *hw) * 7 or less sw_entry_point_layer */ /* calculate the aggregator layer based on number of layers. */ - if (hw->num_tx_sched_layers > ICE_AGG_LAYER_OFFSET + 1) { - u8 layer = hw->num_tx_sched_layers - ICE_AGG_LAYER_OFFSET; - - if (layer > hw->sw_entry_point_layer) - return layer; - } - return hw->sw_entry_point_layer; + if (hw->num_tx_sched_layers == ICE_SCHED_9_LAYERS) + return hw->num_tx_sched_layers - ICE_AGG_LAYER_OFFSET; + else + return hw->sw_entry_point_layer; } /** @@ -1510,10 +1504,11 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc, { struct ice_sched_node *vsi_node, *qgrp_node; struct ice_vsi_ctx *vsi_ctx; + u8 qgrp_layer, vsi_layer; u16 max_children; - u8 qgrp_layer; qgrp_layer = ice_sched_get_qgrp_layer(pi->hw); + vsi_layer = ice_sched_get_vsi_layer(pi->hw); max_children = pi->hw->max_children[qgrp_layer]; vsi_ctx = ice_get_vsi_ctx(pi->hw, vsi_handle); @@ -1524,6 +1519,12 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc, if (!vsi_node) return NULL; + /* If the queue group and VSI layer are same then queues + * are all attached directly to VSI + */ + if (qgrp_layer == vsi_layer) + return vsi_node; + /* get the first queue group node from VSI sub-tree */ qgrp_node = ice_sched_get_first_node(pi, vsi_node, qgrp_layer); while (qgrp_node) { @@ -3199,7 +3200,7 @@ ice_sched_add_rl_profile(struct ice_port_info *pi, u8 profile_type; int status; - if (layer_num >= ICE_AQC_TOPO_MAX_LEVEL_NUM) + if (!pi || layer_num >= pi->hw->num_tx_sched_layers) return NULL; switch (rl_type) { case ICE_MIN_BW: @@ -3215,8 +3216,6 @@ ice_sched_add_rl_profile(struct ice_port_info *pi, return NULL; } - if (!pi) - return NULL; hw = pi->hw; list_for_each_entry(rl_prof_elem, &pi->rl_prof_list[layer_num], list_entry) @@ -3446,7 +3445,7 @@ ice_sched_rm_rl_profile(struct ice_port_info *pi, u8 layer_num, u8 profile_type, struct ice_aqc_rl_profile_info *rl_prof_elem; int status = 0; - if (layer_num >= ICE_AQC_TOPO_MAX_LEVEL_NUM) + if (layer_num >= pi->hw->num_tx_sched_layers) return -EINVAL; /* Check the existing list for RL profile */ list_for_each_entry(rl_prof_elem, &pi->rl_prof_list[layer_num], diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h index 1aef05ea5a57..7b668083be07 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.h +++ b/drivers/net/ethernet/intel/ice/ice_sched.h @@ -6,6 +6,17 @@ #include "ice_common.h" +/** + * DOC: ice_sched.h + * + * This header file stores everything that is needed for broadly understood + * scheduler. It consists of defines related to layers, structures related to + * aggregator, functions declarations and others. + */ + +#define ICE_SCHED_5_LAYERS 5 +#define ICE_SCHED_9_LAYERS 9 + #define SCHED_NODE_NAME_MAX_LEN 32 #define ICE_QGRP_LAYER_OFFSET 2 diff --git a/drivers/net/ethernet/intel/ice/ice_sf_eth.c b/drivers/net/ethernet/intel/ice/ice_sf_eth.c new file mode 100644 index 000000000000..1a2c94375ca7 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_sf_eth.c @@ -0,0 +1,329 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024, Intel Corporation. */ +#include "ice.h" +#include "ice_lib.h" +#include "ice_txrx.h" +#include "ice_fltr.h" +#include "ice_sf_eth.h" +#include "devlink/devlink.h" +#include "devlink/port.h" + +static const struct net_device_ops ice_sf_netdev_ops = { + .ndo_open = ice_open, + .ndo_stop = ice_stop, + .ndo_start_xmit = ice_start_xmit, + .ndo_vlan_rx_add_vid = ice_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = ice_vlan_rx_kill_vid, + .ndo_change_mtu = ice_change_mtu, + .ndo_get_stats64 = ice_get_stats64, + .ndo_tx_timeout = ice_tx_timeout, + .ndo_bpf = ice_xdp, + .ndo_xdp_xmit = ice_xdp_xmit, + .ndo_xsk_wakeup = ice_xsk_wakeup, +}; + +/** + * ice_sf_cfg_netdev - Allocate, configure and register a netdev + * @dyn_port: subfunction associated with configured netdev + * @devlink_port: subfunction devlink port to be linked with netdev + * + * Return: 0 on success, negative value on failure + */ +static int ice_sf_cfg_netdev(struct ice_dynamic_port *dyn_port, + struct devlink_port *devlink_port) +{ + struct ice_vsi *vsi = dyn_port->vsi; + struct ice_netdev_priv *np; + struct net_device *netdev; + int err; + + netdev = alloc_etherdev_mqs(sizeof(*np), vsi->alloc_txq, + vsi->alloc_rxq); + if (!netdev) + return -ENOMEM; + + SET_NETDEV_DEV(netdev, &vsi->back->pdev->dev); + set_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); + vsi->netdev = netdev; + np = netdev_priv(netdev); + np->vsi = vsi; + + ice_set_netdev_features(netdev); + + 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; + + eth_hw_addr_set(netdev, dyn_port->hw_addr); + ether_addr_copy(netdev->perm_addr, dyn_port->hw_addr); + netdev->netdev_ops = &ice_sf_netdev_ops; + SET_NETDEV_DEVLINK_PORT(netdev, devlink_port); + + err = register_netdev(netdev); + if (err) { + free_netdev(netdev); + vsi->netdev = NULL; + return -ENOMEM; + } + set_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); + netif_carrier_off(netdev); + netif_tx_stop_all_queues(netdev); + + return 0; +} + +static void ice_sf_decfg_netdev(struct ice_vsi *vsi) +{ + unregister_netdev(vsi->netdev); + clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); + free_netdev(vsi->netdev); + vsi->netdev = NULL; + clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); +} + +/** + * ice_sf_dev_probe - subfunction driver probe function + * @adev: pointer to the auxiliary device + * @id: pointer to the auxiliary_device id + * + * Configure VSI and netdev resources for the subfunction device. + * + * Return: zero on success or an error code on failure. + */ +static int ice_sf_dev_probe(struct auxiliary_device *adev, + const struct auxiliary_device_id *id) +{ + struct ice_sf_dev *sf_dev = ice_adev_to_sf_dev(adev); + struct ice_dynamic_port *dyn_port = sf_dev->dyn_port; + struct ice_vsi *vsi = dyn_port->vsi; + struct ice_pf *pf = dyn_port->pf; + struct device *dev = &adev->dev; + struct ice_sf_priv *priv; + struct devlink *devlink; + int err; + + vsi->type = ICE_VSI_SF; + vsi->port_info = pf->hw.port_info; + vsi->flags = ICE_VSI_FLAG_INIT; + + priv = ice_allocate_sf(&adev->dev, pf); + if (IS_ERR(priv)) { + dev_err(dev, "Subfunction devlink alloc failed"); + return PTR_ERR(priv); + } + + priv->dev = sf_dev; + sf_dev->priv = priv; + devlink = priv_to_devlink(priv); + + devl_lock(devlink); + + err = ice_vsi_cfg(vsi); + if (err) { + dev_err(dev, "Subfunction vsi config failed"); + goto err_free_devlink; + } + vsi->sf = dyn_port; + + ice_eswitch_update_repr(&dyn_port->repr_id, vsi); + + err = ice_devlink_create_sf_dev_port(sf_dev); + if (err) { + dev_err(dev, "Cannot add ice virtual devlink port for subfunction"); + goto err_vsi_decfg; + } + + err = ice_sf_cfg_netdev(dyn_port, &sf_dev->priv->devlink_port); + if (err) { + dev_err(dev, "Subfunction netdev config failed"); + goto err_devlink_destroy; + } + + err = devl_port_fn_devlink_set(&dyn_port->devlink_port, devlink); + if (err) { + dev_err(dev, "Can't link devlink instance to SF devlink port"); + goto err_netdev_decfg; + } + + ice_napi_add(vsi); + + devl_register(devlink); + devl_unlock(devlink); + + dyn_port->attached = true; + + return 0; + +err_netdev_decfg: + ice_sf_decfg_netdev(vsi); +err_devlink_destroy: + ice_devlink_destroy_sf_dev_port(sf_dev); +err_vsi_decfg: + ice_vsi_decfg(vsi); +err_free_devlink: + devl_unlock(devlink); + devlink_free(devlink); + return err; +} + +/** + * ice_sf_dev_remove - subfunction driver remove function + * @adev: pointer to the auxiliary device + * + * Deinitalize VSI and netdev resources for the subfunction device. + */ +static void ice_sf_dev_remove(struct auxiliary_device *adev) +{ + struct ice_sf_dev *sf_dev = ice_adev_to_sf_dev(adev); + struct ice_dynamic_port *dyn_port = sf_dev->dyn_port; + struct ice_vsi *vsi = dyn_port->vsi; + struct devlink *devlink; + + devlink = priv_to_devlink(sf_dev->priv); + devl_lock(devlink); + + ice_vsi_close(vsi); + + ice_sf_decfg_netdev(vsi); + ice_devlink_destroy_sf_dev_port(sf_dev); + devl_unregister(devlink); + devl_unlock(devlink); + devlink_free(devlink); + ice_vsi_decfg(vsi); + + dyn_port->attached = false; +} + +static const struct auxiliary_device_id ice_sf_dev_id_table[] = { + { .name = "ice.sf", }, + { }, +}; + +MODULE_DEVICE_TABLE(auxiliary, ice_sf_dev_id_table); + +static struct auxiliary_driver ice_sf_driver = { + .name = "sf", + .probe = ice_sf_dev_probe, + .remove = ice_sf_dev_remove, + .id_table = ice_sf_dev_id_table +}; + +static DEFINE_XARRAY_ALLOC1(ice_sf_aux_id); + +/** + * ice_sf_driver_register - Register new auxiliary subfunction driver + * + * Return: zero on success or an error code on failure. + */ +int ice_sf_driver_register(void) +{ + return auxiliary_driver_register(&ice_sf_driver); +} + +/** + * ice_sf_driver_unregister - Unregister new auxiliary subfunction driver + * + */ +void ice_sf_driver_unregister(void) +{ + auxiliary_driver_unregister(&ice_sf_driver); +} + +/** + * ice_sf_dev_release - Release device associated with auxiliary device + * @device: pointer to the device + * + * Since most of the code for subfunction deactivation is handled in + * the remove handler, here just free tracking resources. + */ +static void ice_sf_dev_release(struct device *device) +{ + struct auxiliary_device *adev = to_auxiliary_dev(device); + struct ice_sf_dev *sf_dev = ice_adev_to_sf_dev(adev); + + xa_erase(&ice_sf_aux_id, adev->id); + kfree(sf_dev); +} + +/** + * ice_sf_eth_activate - Activate Ethernet subfunction port + * @dyn_port: the dynamic port instance for this subfunction + * @extack: extack for reporting error messages + * + * Activate the dynamic port as an Ethernet subfunction. Setup the netdev + * resources associated and initialize the auxiliary device. + * + * Return: zero on success or an error code on failure. + */ +int +ice_sf_eth_activate(struct ice_dynamic_port *dyn_port, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = dyn_port->pf; + struct ice_sf_dev *sf_dev; + struct pci_dev *pdev; + int err; + u32 id; + + err = xa_alloc(&ice_sf_aux_id, &id, NULL, xa_limit_32b, + GFP_KERNEL); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Could not allocate SF ID"); + return err; + } + + sf_dev = kzalloc(sizeof(*sf_dev), GFP_KERNEL); + if (!sf_dev) { + err = -ENOMEM; + NL_SET_ERR_MSG_MOD(extack, "Could not allocate SF memory"); + goto xa_erase; + } + pdev = pf->pdev; + + sf_dev->dyn_port = dyn_port; + sf_dev->adev.id = id; + sf_dev->adev.name = "sf"; + sf_dev->adev.dev.release = ice_sf_dev_release; + sf_dev->adev.dev.parent = &pdev->dev; + + err = auxiliary_device_init(&sf_dev->adev); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to initialize SF device"); + goto sf_dev_free; + } + + err = auxiliary_device_add(&sf_dev->adev); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to add SF device"); + goto aux_dev_uninit; + } + + dyn_port->sf_dev = sf_dev; + + return 0; + +aux_dev_uninit: + auxiliary_device_uninit(&sf_dev->adev); +sf_dev_free: + kfree(sf_dev); +xa_erase: + xa_erase(&ice_sf_aux_id, id); + + return err; +} + +/** + * ice_sf_eth_deactivate - Deactivate Ethernet subfunction port + * @dyn_port: the dynamic port instance for this subfunction + * + * Deactivate the Ethernet subfunction, removing its auxiliary device and the + * associated resources. + */ +void ice_sf_eth_deactivate(struct ice_dynamic_port *dyn_port) +{ + struct ice_sf_dev *sf_dev = dyn_port->sf_dev; + + auxiliary_device_delete(&sf_dev->adev); + auxiliary_device_uninit(&sf_dev->adev); +} diff --git a/drivers/net/ethernet/intel/ice/ice_sf_eth.h b/drivers/net/ethernet/intel/ice/ice_sf_eth.h new file mode 100644 index 000000000000..c558cad0a183 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_sf_eth.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024, Intel Corporation. */ + +#ifndef _ICE_SF_ETH_H_ +#define _ICE_SF_ETH_H_ + +#include <linux/auxiliary_bus.h> +#include "ice.h" + +struct ice_sf_dev { + struct auxiliary_device adev; + struct ice_dynamic_port *dyn_port; + struct ice_sf_priv *priv; +}; + +struct ice_sf_priv { + struct ice_sf_dev *dev; + struct devlink_port devlink_port; +}; + +static inline struct +ice_sf_dev *ice_adev_to_sf_dev(struct auxiliary_device *adev) +{ + return container_of(adev, struct ice_sf_dev, adev); +} + +int ice_sf_driver_register(void); +void ice_sf_driver_unregister(void); + +int ice_sf_eth_activate(struct ice_dynamic_port *dyn_port, + struct netlink_ext_ack *extack); +void ice_sf_eth_deactivate(struct ice_dynamic_port *dyn_port); +#endif /* _ICE_SF_ETH_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_sf_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_sf_vsi_vlan_ops.c new file mode 100644 index 000000000000..3d7e96721cf9 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_sf_vsi_vlan_ops.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023, Intel Corporation. */ + +#include "ice_vsi_vlan_ops.h" +#include "ice_vsi_vlan_lib.h" +#include "ice_vlan_mode.h" +#include "ice.h" +#include "ice_sf_vsi_vlan_ops.h" + +void ice_sf_vsi_init_vlan_ops(struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops; + + if (ice_is_dvm_ena(&vsi->back->hw)) + vlan_ops = &vsi->outer_vlan_ops; + else + vlan_ops = &vsi->inner_vlan_ops; + + vlan_ops->add_vlan = ice_vsi_add_vlan; + vlan_ops->del_vlan = ice_vsi_del_vlan; +} diff --git a/drivers/net/ethernet/intel/ice/ice_sf_vsi_vlan_ops.h b/drivers/net/ethernet/intel/ice/ice_sf_vsi_vlan_ops.h new file mode 100644 index 000000000000..8c44eafceea0 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_sf_vsi_vlan_ops.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2023, Intel Corporation. */ + +#ifndef _ICE_SF_VSI_VLAN_OPS_H_ +#define _ICE_SF_VSI_VLAN_OPS_H_ + +#include "ice_vsi_vlan_ops.h" + +struct ice_vsi; + +void ice_sf_vsi_init_vlan_ops(struct ice_vsi *vsi); + +#endif /* _ICE_SF_VSI_VLAN_OPS_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index a958fcf3e6be..0e4dc1a5cff0 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -36,6 +36,7 @@ static void ice_free_vf_entries(struct ice_pf *pf) hash_for_each_safe(vfs->table, bkt, tmp, vf, entry) { hash_del_rcu(&vf->entry); + ice_deinitialize_vf_entry(vf); ice_put_vf(vf); } } @@ -62,6 +63,7 @@ static void ice_free_vf_res(struct ice_vf *vf) if (vf->lan_vsi_idx != ICE_NO_VSI) { ice_vf_vsi_release(vf); vf->num_mac = 0; + vf->num_mac_lldp = 0; } last_vector_idx = vf->first_vector_idx + vf->num_msix - 1; @@ -123,27 +125,6 @@ static void ice_dis_vf_mappings(struct ice_vf *vf) } /** - * ice_sriov_free_msix_res - Reset/free any used MSIX resources - * @pf: pointer to the PF structure - * - * Since no MSIX entries are taken from the pf->irq_tracker then just clear - * the pf->sriov_base_vector. - * - * Returns 0 on success, and -EINVAL on error. - */ -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; -} - -/** * ice_free_vfs - Free all VFs * @pf: pointer to the PF structure */ @@ -170,15 +151,14 @@ void ice_free_vfs(struct ice_pf *pf) else dev_warn(dev, "VFs are assigned - not disabling SR-IOV\n"); - ice_eswitch_reserve_cp_queues(pf, -ice_get_num_vfs(pf)); - mutex_lock(&vfs->table_lock); ice_for_each_vf(pf, bkt, vf) { mutex_lock(&vf->cfg_lock); - ice_eswitch_detach(pf, vf); + ice_eswitch_detach_vf(pf, vf); ice_dis_vf_qs(vf); + ice_virt_free_irqs(pf, vf->first_vector_idx, vf->num_msix); if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { /* disable VF qp mappings and set VF disable state */ @@ -195,15 +175,9 @@ void ice_free_vfs(struct ice_pf *pf) wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx)); } - /* clear malicious info since the VF is getting released */ - list_del(&vf->mbx_info.list_entry); - mutex_unlock(&vf->cfg_lock); } - if (ice_sriov_free_msix_res(pf)) - dev_err(dev, "Failed to free MSIX resources used by SR-IOV\n"); - vfs->num_qps_per = 0; ice_free_vf_entries(pf); @@ -227,7 +201,7 @@ static struct ice_vsi *ice_vf_vsi_setup(struct ice_vf *vf) struct ice_vsi *vsi; params.type = ICE_VSI_VF; - params.pi = ice_vf_get_port_info(vf); + params.port_info = ice_vf_get_port_info(vf); params.vf = vf; params.flags = ICE_VSI_FLAG_INIT; @@ -362,47 +336,14 @@ static void ice_ena_vf_mappings(struct ice_vf *vf) * @vf: VF to calculate the register index for * @q_vector: a q_vector associated to the VF */ -int ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector) +void ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector) { if (!vf || !q_vector) - return -EINVAL; + return; /* always add one to account for the OICR being the first MSIX */ - return vf->first_vector_idx + q_vector->v_idx + 1; -} - -/** - * ice_sriov_set_msix_res - Set any used MSIX resources - * @pf: pointer to PF structure - * @num_msix_needed: number of MSIX vectors needed for all SR-IOV VFs - * - * This function allows SR-IOV resources to be taken from the end of the PF's - * allowed HW MSIX vectors so that the irq_tracker will not be affected. We - * just set the pf->sriov_base_vector and return success. - * - * If there are not enough resources available, return an error. This should - * always be caught by ice_set_per_vf_res(). - * - * Return 0 on success, and -EINVAL when there are not enough MSIX vectors - * in the PF's space available for SR-IOV. - */ -static int ice_sriov_set_msix_res(struct ice_pf *pf, u16 num_msix_needed) -{ - u16 total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors; - int vectors_used = ice_get_max_used_msix_vector(pf); - int sriov_base_vector; - - sriov_base_vector = total_vectors - num_msix_needed; - - /* make sure we only grab irq_tracker entries from the list end and - * that we have enough available MSIX vectors - */ - if (sriov_base_vector < vectors_used) - return -EINVAL; - - pf->sriov_base_vector = sriov_base_vector; - - return 0; + q_vector->vf_reg_idx = q_vector->v_idx + ICE_NONQ_VECS_VF; + q_vector->reg_idx = vf->first_vector_idx + q_vector->vf_reg_idx; } /** @@ -429,11 +370,9 @@ static int ice_sriov_set_msix_res(struct ice_pf *pf, u16 num_msix_needed) */ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs) { - int vectors_used = ice_get_max_used_msix_vector(pf); u16 num_msix_per_vf, num_txq, num_rxq, avail_qs; int msix_avail_per_vf, msix_avail_for_sriov; struct device *dev = ice_pf_to_dev(pf); - int err; lockdep_assert_held(&pf->vfs.table_lock); @@ -441,8 +380,7 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs) return -EINVAL; /* determine MSI-X resources per VF */ - msix_avail_for_sriov = pf->hw.func_caps.common_cap.num_msix_vectors - - vectors_used; + msix_avail_for_sriov = pf->virt_irq_tracker.num_entries; msix_avail_per_vf = msix_avail_for_sriov / num_vfs; if (msix_avail_per_vf >= ICE_NUM_VF_MSIX_MED) { num_msix_per_vf = ICE_NUM_VF_MSIX_MED; @@ -481,13 +419,6 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs) return -ENOSPC; } - err = ice_sriov_set_msix_res(pf, num_msix_per_vf * num_vfs); - if (err) { - dev_err(dev, "Unable to set MSI-X resources for %d VFs, err %d\n", - num_vfs, err); - return err; - } - /* only allow equal Tx/Rx queue count (i.e. queue pairs) */ pf->vfs.num_qps_per = min_t(int, num_txq, num_rxq); pf->vfs.num_msix_per = num_msix_per_vf; @@ -498,52 +429,6 @@ 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 * @@ -556,7 +441,7 @@ static int ice_init_vf_vsi_res(struct ice_vf *vf) struct ice_vsi *vsi; int err; - vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix); + vf->first_vector_idx = ice_virt_get_irqs(pf, vf->num_msix); if (vf->first_vector_idx < 0) return -ENOMEM; @@ -599,7 +484,7 @@ static int ice_start_vfs(struct ice_pf *pf) goto teardown; } - retval = ice_eswitch_attach(pf, vf); + retval = ice_eswitch_attach_vf(pf, vf); if (retval) { dev_err(ice_pf_to_dev(pf), "Failed to attach VF %d to eswitch, error %d", vf->vf_id, retval); @@ -833,11 +718,6 @@ static int ice_create_vf_entries(struct ice_pf *pf, u16 num_vfs) 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); } @@ -861,16 +741,10 @@ 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); @@ -897,7 +771,6 @@ static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs) goto err_unroll_sriov; } - ice_eswitch_reserve_cp_queues(pf, num_vfs); ret = ice_start_vfs(pf); if (ret) { dev_err(dev, "Failed to start %d VFs, err %d\n", num_vfs, ret); @@ -924,7 +797,6 @@ 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; } @@ -998,16 +870,7 @@ 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; + return pf->virt_irq_tracker.num_entries; } static void ice_sriov_remap_vectors(struct ice_pf *pf, u16 restricted_id) @@ -1026,7 +889,8 @@ static void ice_sriov_remap_vectors(struct ice_pf *pf, u16 restricted_id) continue; ice_dis_vf_mappings(tmp_vf); - ice_sriov_free_irqs(pf, tmp_vf); + ice_virt_free_irqs(pf, tmp_vf->first_vector_idx, + tmp_vf->num_msix); vf_ids[to_remap] = tmp_vf->vf_id; to_remap += 1; @@ -1038,7 +902,7 @@ static void ice_sriov_remap_vectors(struct ice_pf *pf, u16 restricted_id) continue; tmp_vf->first_vector_idx = - ice_sriov_get_irqs(pf, tmp_vf->num_msix); + ice_virt_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 */ @@ -1103,30 +967,30 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count) return -ENOENT; vsi = ice_get_vf_vsi(vf); - if (!vsi) + if (!vsi) { + ice_put_vf(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); + ice_virt_free_irqs(pf, vf->first_vector_idx, vf->num_msix); /* 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); + vf->first_vector_idx = ice_virt_get_irqs(pf, vf->num_msix); if (vf->first_vector_idx < 0) goto unroll; - if (ice_vf_reconfig_vsi(vf) || ice_vf_init_host_cfg(vf, vsi)) { + vsi->req_txq = queues; + vsi->req_rxq = queues; + + if (ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT)) { /* Try to rebuild with previous values */ needs_rebuild = true; goto unroll; @@ -1148,13 +1012,18 @@ unroll: 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) + + vf->first_vector_idx = ice_virt_get_irqs(pf, vf->num_msix); + if (vf->first_vector_idx < 0) { + ice_put_vf(vf); return -EINVAL; + } if (needs_rebuild) { - ice_vf_reconfig_vsi(vf); - ice_vf_init_host_cfg(vf, vsi); + vsi->req_txq = prev_queues; + vsi->req_rxq = prev_queues; + + ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT); } ice_ena_vf_mappings(vf); @@ -1423,21 +1292,23 @@ out_put_vf: } /** - * ice_set_vf_mac - * @netdev: network interface device structure + * __ice_set_vf_mac - program VF MAC address + * @pf: PF to be configure * @vf_id: VF identifier * @mac: MAC address * * program VF MAC address + * Return: zero on success or an error code on failure */ -int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) +int __ice_set_vf_mac(struct ice_pf *pf, u16 vf_id, const u8 *mac) { - struct ice_pf *pf = ice_netdev_to_pf(netdev); + struct device *dev; struct ice_vf *vf; int ret; + dev = ice_pf_to_dev(pf); if (is_multicast_ether_addr(mac)) { - netdev_err(netdev, "%pM not a valid unicast address\n", mac); + dev_err(dev, "%pM not a valid unicast address\n", mac); return -EINVAL; } @@ -1466,13 +1337,13 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) if (is_zero_ether_addr(mac)) { /* VF will send VIRTCHNL_OP_ADD_ETH_ADDR message with its MAC */ vf->pf_set_mac = false; - netdev_info(netdev, "Removing MAC on VF %d. VF driver will be reinitialized\n", - vf->vf_id); + dev_info(dev, "Removing MAC on VF %d. VF driver will be reinitialized\n", + vf->vf_id); } else { /* PF will add MAC rule for the VF */ vf->pf_set_mac = true; - netdev_info(netdev, "Setting MAC %pM on VF %d. VF driver will be reinitialized\n", - mac, vf_id); + dev_info(dev, "Setting MAC %pM on VF %d. VF driver will be reinitialized\n", + mac, vf_id); } ice_reset_vf(vf, ICE_VF_RESET_NOTIFY); @@ -1484,6 +1355,20 @@ out_put_vf: } /** + * ice_set_vf_mac - .ndo_set_vf_mac handler + * @netdev: network interface device structure + * @vf_id: VF identifier + * @mac: MAC address + * + * program VF MAC address + * Return: zero on success or an error code on failure + */ +int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) +{ + return __ice_set_vf_mac(ice_netdev_to_pf(netdev), vf_id, mac); +} + +/** * ice_set_vf_trust * @netdev: network interface device structure * @vf_id: VF identifier @@ -1518,6 +1403,9 @@ int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted) mutex_lock(&vf->cfg_lock); + while (!trusted && vf->num_mac_lldp) + ice_vf_update_mac_lldp_num(vf, ice_get_vf_vsi(vf), false); + vf->trusted = trusted; ice_reset_vf(vf, ICE_VF_RESET_NOTIFY); dev_info(ice_pf_to_dev(pf), "VF %u is now %strusted\n", @@ -1869,6 +1757,24 @@ void ice_print_vf_rx_mdd_event(struct ice_vf *vf) } /** + * ice_print_vf_tx_mdd_event - print VF Tx malicious driver detect event + * @vf: pointer to the VF structure + */ +void ice_print_vf_tx_mdd_event(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + struct device *dev; + + dev = ice_pf_to_dev(pf); + + dev_info(dev, "%d Tx Malicious Driver Detection events detected on PF %d VF %d MAC %pM. mdd-auto-reset-vfs=%s\n", + vf->mdd_tx_events.count, pf->hw.pf_id, vf->vf_id, + vf->dev_lan_addr, + test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags) + ? "on" : "off"); +} + +/** * ice_print_vfs_mdd_events - print VFs malicious driver detect event * @pf: pointer to the PF structure * @@ -1876,8 +1782,6 @@ void ice_print_vf_rx_mdd_event(struct ice_vf *vf) */ void ice_print_vfs_mdd_events(struct ice_pf *pf) { - struct device *dev = ice_pf_to_dev(pf); - struct ice_hw *hw = &pf->hw; struct ice_vf *vf; unsigned int bkt; @@ -1904,10 +1808,7 @@ void ice_print_vfs_mdd_events(struct ice_pf *pf) if (vf->mdd_tx_events.count != vf->mdd_tx_events.last_printed) { vf->mdd_tx_events.last_printed = vf->mdd_tx_events.count; - - dev_info(dev, "%d Tx Malicious Driver Detection events detected on PF %d VF %d MAC %pM.\n", - vf->mdd_tx_events.count, hw->pf_id, vf->vf_id, - vf->dev_lan_addr); + ice_print_vf_tx_mdd_event(vf); } } mutex_unlock(&pf->vfs.table_lock); diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.h b/drivers/net/ethernet/intel/ice/ice_sriov.h index 8488df38b586..96549ca5c52c 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.h +++ b/drivers/net/ethernet/intel/ice/ice_sriov.h @@ -28,6 +28,7 @@ #ifdef CONFIG_PCI_IOV void ice_process_vflr_event(struct ice_pf *pf); int ice_sriov_configure(struct pci_dev *pdev, int num_vfs); +int __ice_set_vf_mac(struct ice_pf *pf, u16 vf_id, const u8 *mac); int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac); int ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi); @@ -49,7 +50,7 @@ int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state); int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena); -int ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector); +void ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector); int ice_get_vf_stats(struct net_device *netdev, int vf_id, @@ -58,6 +59,7 @@ void ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event); void ice_print_vfs_mdd_events(struct ice_pf *pf); void ice_print_vf_rx_mdd_event(struct ice_vf *vf); +void ice_print_vf_tx_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); @@ -69,6 +71,7 @@ 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_print_vf_tx_mdd_event(struct ice_vf *vf) { } static inline void ice_restore_all_vfs_msi_state(struct ice_pf *pf) { } static inline int @@ -79,6 +82,13 @@ ice_sriov_configure(struct pci_dev __always_unused *pdev, } static inline int +__ice_set_vf_mac(struct ice_pf __always_unused *pf, + u16 __always_unused vf_id, const u8 __always_unused *mac) +{ + return -EOPNOTSUPP; +} + +static inline int ice_set_vf_mac(struct net_device __always_unused *netdev, int __always_unused vf_id, u8 __always_unused *mac) { @@ -130,11 +140,10 @@ ice_set_vf_bw(struct net_device __always_unused *netdev, return -EOPNOTSUPP; } -static inline int +static inline void ice_calc_vf_reg_idx(struct ice_vf __always_unused *vf, struct ice_q_vector __always_unused *q_vector) { - return 0; } static inline int diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index b4ea935e8300..9d9a7edd3618 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -3,6 +3,7 @@ #include "ice_lib.h" #include "ice_switch.h" +#include "ice_trace.h" #define ICE_ETH_DA_OFFSET 0 #define ICE_ETH_ETHTYPE_OFFSET 12 @@ -42,6 +43,7 @@ enum { ICE_PKT_KMALLOC = BIT(9), ICE_PKT_PPPOE = BIT(10), ICE_PKT_L2TPV3 = BIT(11), + ICE_PKT_PFCP = BIT(12), }; struct ice_dummy_pkt_offsets { @@ -1110,6 +1112,77 @@ ICE_DECLARE_PKT_TEMPLATE(ipv6_gtp) = { 0x00, 0x00, }; +ICE_DECLARE_PKT_OFFSETS(pfcp_session_ipv4) = { + { ICE_MAC_OFOS, 0 }, + { ICE_ETYPE_OL, 12 }, + { ICE_IPV4_OFOS, 14 }, + { ICE_UDP_ILOS, 34 }, + { ICE_PFCP, 42 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(pfcp_session_ipv4) = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x08, 0x00, /* ICE_ETYPE_OL 12 */ + + 0x45, 0x00, 0x00, 0x2c, /* ICE_IPV4_OFOS 14 */ + 0x00, 0x01, 0x00, 0x00, + 0x00, 0x11, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x22, 0x65, /* ICE_UDP_ILOS 34 */ + 0x00, 0x18, 0x00, 0x00, + + 0x21, 0x01, 0x00, 0x0c, /* ICE_PFCP 42 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + +ICE_DECLARE_PKT_OFFSETS(pfcp_session_ipv6) = { + { ICE_MAC_OFOS, 0 }, + { ICE_ETYPE_OL, 12 }, + { ICE_IPV6_OFOS, 14 }, + { ICE_UDP_ILOS, 54 }, + { ICE_PFCP, 62 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(pfcp_session_ipv6) = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x86, 0xdd, /* ICE_ETYPE_OL 12 */ + + 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_OFOS 14 */ + 0x00, 0x10, 0x11, 0x00, /* Next header UDP */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x22, 0x65, /* ICE_UDP_ILOS 54 */ + 0x00, 0x18, 0x00, 0x00, + + 0x21, 0x01, 0x00, 0x0c, /* ICE_PFCP 62 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + ICE_DECLARE_PKT_OFFSETS(pppoe_ipv4_tcp) = { { ICE_MAC_OFOS, 0 }, { ICE_ETYPE_OL, 12 }, @@ -1343,6 +1416,8 @@ static const struct ice_dummy_pkt_profile ice_dummy_pkt_profiles[] = { ICE_PKT_PROFILE(ipv4_gtpu_ipv4_tcp, ICE_PKT_TUN_GTPU), ICE_PKT_PROFILE(ipv6_gtp, ICE_PKT_TUN_GTPC | ICE_PKT_OUTER_IPV6), ICE_PKT_PROFILE(ipv4_gtpu_ipv4, ICE_PKT_TUN_GTPC), + ICE_PKT_PROFILE(pfcp_session_ipv6, ICE_PKT_PFCP | ICE_PKT_OUTER_IPV6), + ICE_PKT_PROFILE(pfcp_session_ipv4, ICE_PKT_PFCP), ICE_PKT_PROFILE(pppoe_ipv6_udp, ICE_PKT_PPPOE | ICE_PKT_OUTER_IPV6 | ICE_PKT_INNER_UDP), ICE_PKT_PROFILE(pppoe_ipv6_tcp, ICE_PKT_PPPOE | ICE_PKT_OUTER_IPV6), @@ -1397,7 +1472,6 @@ int ice_init_def_sw_recp(struct ice_hw *hw) recps[i].root_rid = i; INIT_LIST_HEAD(&recps[i].filt_rules); INIT_LIST_HEAD(&recps[i].filt_replay_rules); - INIT_LIST_HEAD(&recps[i].rg_list); mutex_init(&recps[i].filt_rule_lock); } @@ -1825,7 +1899,8 @@ ice_aq_alloc_free_vsi_list(struct ice_hw *hw, u16 *vsi_list_id, lkup_type == ICE_SW_LKUP_ETHERTYPE_MAC || lkup_type == ICE_SW_LKUP_PROMISC || lkup_type == ICE_SW_LKUP_PROMISC_VLAN || - lkup_type == ICE_SW_LKUP_DFLT) { + lkup_type == ICE_SW_LKUP_DFLT || + lkup_type == ICE_SW_LKUP_LAST) { sw_buf->res_type = cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_REP); } else if (lkup_type == ICE_SW_LKUP_VLAN) { if (opc == ice_aqc_opc_alloc_res) @@ -1887,6 +1962,15 @@ ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz, hw->adminq.sq_last_status == ICE_AQ_RC_ENOENT) status = -ENOENT; + if (!status) { + if (opc == ice_aqc_opc_add_sw_rules) + hw->switch_info->rule_cnt += num_rules; + else if (opc == ice_aqc_opc_remove_sw_rules) + hw->switch_info->rule_cnt -= num_rules; + } + + trace_ice_aq_sw_rules(hw->switch_info); + return status; } @@ -2075,6 +2159,18 @@ ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 *r_assoc, } /** + * ice_init_chk_recipe_reuse_support - check if recipe reuse is supported + * @hw: pointer to the hardware structure + */ +void ice_init_chk_recipe_reuse_support(struct ice_hw *hw) +{ + struct ice_nvm_info *nvm = &hw->flash.nvm; + + hw->recp_reuse = (nvm->major == 0x4 && nvm->minor >= 0x30) || + nvm->major > 0x4; +} + +/** * ice_alloc_recipe - add recipe resource * @hw: pointer to the hardware structure * @rid: recipe ID returned as response to AQ call @@ -2083,21 +2179,97 @@ int ice_alloc_recipe(struct ice_hw *hw, u16 *rid) { DEFINE_RAW_FLEX(struct ice_aqc_alloc_free_res_elem, sw_buf, elem, 1); u16 buf_len = __struct_size(sw_buf); + u16 res_type; int status; 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); + res_type = FIELD_PREP(ICE_AQC_RES_TYPE_M, ICE_AQC_RES_TYPE_RECIPE); + if (hw->recp_reuse) + res_type |= ICE_AQC_RES_TYPE_FLAG_SUBSCRIBE_SHARED; + else + res_type |= ICE_AQC_RES_TYPE_FLAG_SHARED; + sw_buf->res_type = cpu_to_le16(res_type); status = ice_aq_alloc_free_res(hw, sw_buf, buf_len, ice_aqc_opc_alloc_res); - if (!status) + if (!status) { *rid = le16_to_cpu(sw_buf->elem[0].e.sw_resp); + hw->switch_info->recp_cnt++; + } + + return status; +} + +/** + * ice_free_recipe_res - free recipe resource + * @hw: pointer to the hardware structure + * @rid: recipe ID to free + * + * Return: 0 on success, and others on error + */ +static int ice_free_recipe_res(struct ice_hw *hw, u16 rid) +{ + int status; + + status = ice_free_hw_res(hw, ICE_AQC_RES_TYPE_RECIPE, 1, &rid); + if (!status) + hw->switch_info->recp_cnt--; return status; } /** + * ice_release_recipe_res - disassociate and free recipe resource + * @hw: pointer to the hardware structure + * @recp: the recipe struct resource to unassociate and free + * + * Return: 0 on success, and others on error + */ +static int ice_release_recipe_res(struct ice_hw *hw, + struct ice_sw_recipe *recp) +{ + DECLARE_BITMAP(r_bitmap, ICE_MAX_NUM_RECIPES); + struct ice_switch_info *sw = hw->switch_info; + u64 recp_assoc; + u32 rid, prof; + int status; + + for_each_set_bit(rid, recp->r_bitmap, ICE_MAX_NUM_RECIPES) { + for_each_set_bit(prof, recipe_to_profile[rid], + ICE_MAX_NUM_PROFILES) { + status = ice_aq_get_recipe_to_profile(hw, prof, + &recp_assoc, + NULL); + if (status) + return status; + + bitmap_from_arr64(r_bitmap, &recp_assoc, + ICE_MAX_NUM_RECIPES); + bitmap_andnot(r_bitmap, r_bitmap, recp->r_bitmap, + ICE_MAX_NUM_RECIPES); + bitmap_to_arr64(&recp_assoc, r_bitmap, + ICE_MAX_NUM_RECIPES); + ice_aq_map_recipe_to_profile(hw, prof, + recp_assoc, NULL); + + clear_bit(rid, profile_to_recipe[prof]); + clear_bit(prof, recipe_to_profile[rid]); + } + + status = ice_free_recipe_res(hw, rid); + if (status) + return status; + + sw->recp_list[rid].recp_created = false; + sw->recp_list[rid].adv_rule = false; + memset(&sw->recp_list[rid].lkup_exts, 0, + sizeof(sw->recp_list[rid].lkup_exts)); + clear_bit(rid, recp->r_bitmap); + } + + return 0; +} + +/** * ice_get_recp_to_prof_map - updates recipe to profile mapping * @hw: pointer to hardware structure * @@ -2127,25 +2299,12 @@ static void ice_get_recp_to_prof_map(struct ice_hw *hw) } /** - * ice_collect_result_idx - copy result index values - * @buf: buffer that contains the result index - * @recp: the recipe struct to copy data into - */ -static void -ice_collect_result_idx(struct ice_aqc_recipe_data_elem *buf, - struct ice_sw_recipe *recp) -{ - if (buf->content.result_indx & ICE_AQ_RECIPE_RESULT_EN) - set_bit(buf->content.result_indx & ~ICE_AQ_RECIPE_RESULT_EN, - recp->res_idxs); -} - -/** * ice_get_recp_frm_fw - update SW bookkeeping from FW recipe entries * @hw: pointer to hardware structure * @recps: struct that we need to populate * @rid: recipe ID that we are populating * @refresh_required: true if we should get recipe to profile mapping from FW + * @is_add: flag of adding recipe * * This function is used to populate all the necessary entries into our * bookkeeping so that we have a current list of all the recipes that are @@ -2153,7 +2312,7 @@ ice_collect_result_idx(struct ice_aqc_recipe_data_elem *buf, */ static int ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid, - bool *refresh_required) + bool *refresh_required, bool is_add) { DECLARE_BITMAP(result_bm, ICE_MAX_FV_WORDS); struct ice_aqc_recipe_data_elem *tmp; @@ -2197,18 +2356,10 @@ ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid, for (sub_recps = 0; sub_recps < num_recps; sub_recps++) { struct ice_aqc_recipe_data_elem root_bufs = tmp[sub_recps]; - struct ice_recp_grp_entry *rg_entry; u8 i, prof, idx, prot = 0; bool is_root; u16 off = 0; - rg_entry = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*rg_entry), - GFP_KERNEL); - if (!rg_entry) { - status = -ENOMEM; - goto err_unroll; - } - idx = root_bufs.recipe_indx; is_root = root_bufs.content.rid & ICE_AQ_RECIPE_ID_IS_ROOT; @@ -2221,11 +2372,8 @@ ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid, prof = find_first_bit(recipe_to_profile[idx], ICE_MAX_NUM_PROFILES); for (i = 0; i < ICE_NUM_WORDS_RECIPE; i++) { - u8 lkup_indx = root_bufs.content.lkup_indx[i + 1]; - - rg_entry->fv_idx[i] = lkup_indx; - rg_entry->fv_mask[i] = - le16_to_cpu(root_bufs.content.mask[i + 1]); + u8 lkup_indx = root_bufs.content.lkup_indx[i]; + u16 lkup_mask = le16_to_cpu(root_bufs.content.mask[i]); /* If the recipe is a chained recipe then all its * child recipe's result will have a result index. @@ -2236,42 +2384,38 @@ ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid, * has ICE_AQ_RECIPE_LKUP_IGNORE or 0 since it isn't a * valid offset value. */ - if (test_bit(rg_entry->fv_idx[i], hw->switch_info->prof_res_bm[prof]) || - rg_entry->fv_idx[i] & ICE_AQ_RECIPE_LKUP_IGNORE || - rg_entry->fv_idx[i] == 0) + if (!lkup_indx || + (lkup_indx & ICE_AQ_RECIPE_LKUP_IGNORE) || + test_bit(lkup_indx, + hw->switch_info->prof_res_bm[prof])) continue; - ice_find_prot_off(hw, ICE_BLK_SW, prof, - rg_entry->fv_idx[i], &prot, &off); + ice_find_prot_off(hw, ICE_BLK_SW, prof, lkup_indx, + &prot, &off); lkup_exts->fv_words[fv_word_idx].prot_id = prot; lkup_exts->fv_words[fv_word_idx].off = off; - lkup_exts->field_mask[fv_word_idx] = - rg_entry->fv_mask[i]; + lkup_exts->field_mask[fv_word_idx] = lkup_mask; fv_word_idx++; } - /* populate rg_list with the data from the child entry of this - * recipe - */ - list_add(&rg_entry->l_entry, &recps[rid].rg_list); /* 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; + 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 & - ~ICE_AQ_RECIPE_RESULT_EN; - set_bit(recps[idx].chain_idx, recps[idx].res_idxs); - } else { - recps[idx].chain_idx = ICE_INVAL_CHAIN_IND; + set_bit(root_bufs.content.result_indx & + ~ICE_AQ_RECIPE_RESULT_EN, recps[idx].res_idxs); } - if (!is_root) + if (!is_root) { + if (hw->recp_reuse && is_add) + recps[idx].recp_created = true; + continue; + } /* Only do the following for root recipes entries */ memcpy(recps[idx].r_bitmap, root_bufs.recipe_bitmap, @@ -2283,19 +2427,11 @@ ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid, /* Complete initialization of the root recipe entry */ lkup_exts->n_val_words = fv_word_idx; - recps[rid].big_recp = (num_recps > 1); - recps[rid].n_grp_count = (u8)num_recps; - recps[rid].root_buf = devm_kmemdup(ice_hw_to_dev(hw), tmp, - recps[rid].n_grp_count * sizeof(*recps[rid].root_buf), - GFP_KERNEL); - if (!recps[rid].root_buf) { - status = -ENOMEM; - goto err_unroll; - } /* Copy result indexes */ bitmap_copy(recps[rid].res_idxs, result_bm, ICE_MAX_FV_WORDS); - recps[rid].recp_created = true; + if (is_add) + recps[rid].recp_created = true; err_unroll: kfree(tmp); @@ -2446,6 +2582,9 @@ static void ice_fill_sw_info(struct ice_hw *hw, struct ice_fltr_info *fi) fi->lan_en = true; } } + + if (fi->flag & ICE_FLTR_TX_ONLY) + fi->lan_en = false; } /** @@ -2759,7 +2898,8 @@ ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi, lkup_type == ICE_SW_LKUP_ETHERTYPE_MAC || lkup_type == ICE_SW_LKUP_PROMISC || lkup_type == ICE_SW_LKUP_PROMISC_VLAN || - lkup_type == ICE_SW_LKUP_DFLT) + lkup_type == ICE_SW_LKUP_DFLT || + lkup_type == ICE_SW_LKUP_LAST) rule_type = remove ? ICE_AQC_SW_RULES_T_VSI_LIST_CLEAR : ICE_AQC_SW_RULES_T_VSI_LIST_SET; else if (lkup_type == ICE_SW_LKUP_VLAN) @@ -3006,7 +3146,7 @@ ice_add_update_vsi_list(struct ice_hw *hw, u16 vsi_handle_arr[2]; /* A rule already exists with the new VSI being added */ - if (cur_fltr->fwd_id.hw_vsi_id == new_fltr->fwd_id.hw_vsi_id) + if (cur_fltr->vsi_handle == new_fltr->vsi_handle) return -EEXIST; vsi_handle_arr[0] = cur_fltr->vsi_handle; @@ -3054,7 +3194,7 @@ ice_add_update_vsi_list(struct ice_hw *hw, /* A rule already exists with the new VSI being added */ if (test_bit(vsi_handle, m_entry->vsi_list_info->vsi_map)) - return 0; + return -EEXIST; /* Update the previously created VSI list set with * the new VSI ID passed in @@ -3124,7 +3264,7 @@ 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_list_info) { + if (list_itr->vsi_count == 1 && 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; @@ -3821,6 +3961,7 @@ ice_cfg_dflt_vsi(struct ice_port_info *pi, u16 vsi_handle, bool set, } else if (f_info.flag & ICE_FLTR_TX) { f_info.src_id = ICE_SRC_ID_VSI; f_info.src = hw_vsi_id; + f_info.flag |= ICE_FLTR_TX_ONLY; } f_list_entry.fltr_info = f_info; @@ -4528,6 +4669,7 @@ static const struct ice_prot_ext_tbl_entry ice_prot_ext[ICE_PROTOCOL_LAST] = { ICE_PROTOCOL_ENTRY(ICE_NVGRE, 0, 2, 4, 6), ICE_PROTOCOL_ENTRY(ICE_GTP, 8, 10, 12, 14, 16, 18, 20, 22), ICE_PROTOCOL_ENTRY(ICE_GTP_NO_PAY, 8, 10, 12, 14), + ICE_PROTOCOL_ENTRY(ICE_PFCP, 8, 10, 12, 14, 16, 18, 20, 22), ICE_PROTOCOL_ENTRY(ICE_PPPOE, 0, 2, 4, 6), ICE_PROTOCOL_ENTRY(ICE_L2TPV3, 0, 2, 4, 6, 8, 10), ICE_PROTOCOL_ENTRY(ICE_VLAN_EX, 2, 0), @@ -4561,6 +4703,7 @@ static struct ice_protocol_entry ice_prot_id_tbl[ICE_PROTOCOL_LAST] = { { ICE_NVGRE, ICE_GRE_OF_HW }, { ICE_GTP, ICE_UDP_OF_HW }, { ICE_GTP_NO_PAY, ICE_UDP_ILOS_HW }, + { ICE_PFCP, ICE_UDP_ILOS_HW }, { ICE_PPPOE, ICE_PPPOE_HW }, { ICE_L2TPV3, ICE_L2TPV3_HW }, { ICE_VLAN_EX, ICE_VLAN_OF_HW }, @@ -4573,12 +4716,13 @@ static struct ice_protocol_entry ice_prot_id_tbl[ICE_PROTOCOL_LAST] = { * @hw: pointer to the hardware structure * @lkup_exts: extension sequence to match * @rinfo: information regarding the rule e.g. priority and action info + * @is_add: flag of adding recipe * * 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, - const struct ice_adv_rule_info *rinfo) + const struct ice_adv_rule_info *rinfo, bool is_add) { bool refresh_required = true; struct ice_sw_recipe *recp; @@ -4592,16 +4736,12 @@ ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts, * entry update it in our SW bookkeeping and continue with the * matching. */ - if (!recp[i].recp_created) + if (hw->recp_reuse) { if (ice_get_recp_frm_fw(hw, hw->switch_info->recp_list, i, - &refresh_required)) + &refresh_required, is_add)) continue; - - /* Skip inverse action recipes */ - if (recp[i].root_buf && recp[i].root_buf->content.act_ctrl & - ICE_AQ_RECIPE_ACT_INV_ACT) - continue; + } /* if number of words we are looking for match */ if (lkup_exts->n_val_words == recp[i].lkup_exts.n_val_words) { @@ -4644,7 +4784,8 @@ ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts, */ 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) + recp[i].allow_pass_l2 == rinfo->allow_pass_l2 && + recp[i].priority == rinfo->priority) return i; /* Return the recipe ID */ } } @@ -4727,110 +4868,55 @@ ice_fill_valid_words(struct ice_adv_lkup_elem *rule, } /** - * ice_create_first_fit_recp_def - Create a recipe grouping - * @hw: pointer to the hardware structure - * @lkup_exts: an array of protocol header extractions - * @rg_list: pointer to a list that stores new recipe groups - * @recp_cnt: pointer to a variable that stores returned number of recipe groups - * - * Using first fit algorithm, take all the words that are still not done - * and start grouping them in 4-word groups. Each group makes up one - * recipe. - */ -static int -ice_create_first_fit_recp_def(struct ice_hw *hw, - struct ice_prot_lkup_ext *lkup_exts, - struct list_head *rg_list, - u8 *recp_cnt) -{ - struct ice_pref_recipe_group *grp = NULL; - u8 j; - - *recp_cnt = 0; - - /* Walk through every word in the rule to check if it is not done. If so - * then this word needs to be part of a new recipe. - */ - for (j = 0; j < lkup_exts->n_val_words; j++) - if (!test_bit(j, lkup_exts->done)) { - if (!grp || - grp->n_val_pairs == ICE_NUM_WORDS_RECIPE) { - struct ice_recp_grp_entry *entry; - - entry = devm_kzalloc(ice_hw_to_dev(hw), - sizeof(*entry), - GFP_KERNEL); - if (!entry) - return -ENOMEM; - list_add(&entry->l_entry, rg_list); - grp = &entry->r_group; - (*recp_cnt)++; - } - - grp->pairs[grp->n_val_pairs].prot_id = - lkup_exts->fv_words[j].prot_id; - grp->pairs[grp->n_val_pairs].off = - lkup_exts->fv_words[j].off; - grp->mask[grp->n_val_pairs] = lkup_exts->field_mask[j]; - grp->n_val_pairs++; - } - - return 0; -} - -/** * ice_fill_fv_word_index - fill in the field vector indices for a recipe group * @hw: pointer to the hardware structure - * @fv_list: field vector with the extraction sequence information - * @rg_list: recipe groupings with protocol-offset pairs + * @rm: recipe management list entry * * Helper function to fill in the field vector indices for protocol-offset * pairs. These indexes are then ultimately programmed into a recipe. */ static int -ice_fill_fv_word_index(struct ice_hw *hw, struct list_head *fv_list, - struct list_head *rg_list) +ice_fill_fv_word_index(struct ice_hw *hw, struct ice_sw_recipe *rm) { struct ice_sw_fv_list_entry *fv; - struct ice_recp_grp_entry *rg; struct ice_fv_word *fv_ext; + u8 i; - if (list_empty(fv_list)) - return 0; + if (list_empty(&rm->fv_list)) + return -EINVAL; - fv = list_first_entry(fv_list, struct ice_sw_fv_list_entry, + fv = list_first_entry(&rm->fv_list, struct ice_sw_fv_list_entry, list_entry); fv_ext = fv->fv_ptr->ew; - list_for_each_entry(rg, rg_list, l_entry) { - u8 i; - - for (i = 0; i < rg->r_group.n_val_pairs; i++) { - struct ice_fv_word *pr; - bool found = false; - u16 mask; - u8 j; - - pr = &rg->r_group.pairs[i]; - mask = rg->r_group.mask[i]; + /* Add switch id as the first word. */ + rm->fv_idx[0] = ICE_AQ_SW_ID_LKUP_IDX; + rm->fv_mask[0] = ICE_AQ_SW_ID_LKUP_MASK; + rm->n_ext_words++; - for (j = 0; j < hw->blk[ICE_BLK_SW].es.fvw; j++) - if (fv_ext[j].prot_id == pr->prot_id && - fv_ext[j].off == pr->off) { - found = true; + for (i = 1; i < rm->n_ext_words; i++) { + struct ice_fv_word *fv_word = &rm->ext_words[i - 1]; + u16 fv_mask = rm->word_masks[i - 1]; + bool found = false; + u8 j; - /* Store index of field vector */ - rg->fv_idx[i] = j; - rg->fv_mask[i] = mask; - break; - } + for (j = 0; j < hw->blk[ICE_BLK_SW].es.fvw; j++) { + if (fv_ext[j].prot_id == fv_word->prot_id && + fv_ext[j].off == fv_word->off) { + found = true; - /* Protocol/offset could not be found, caller gave an - * invalid pair - */ - if (!found) - return -EINVAL; + /* Store index of field vector */ + rm->fv_idx[i] = j; + rm->fv_mask[i] = fv_mask; + break; + } } + + /* Protocol/offset could not be found, caller gave an invalid + * pair. + */ + if (!found) + return -EINVAL; } return 0; @@ -4904,335 +4990,223 @@ ice_find_free_recp_res_idx(struct ice_hw *hw, const unsigned long *profiles, } /** - * ice_add_sw_recipe - function to call AQ calls to create switch recipe - * @hw: pointer to hardware structure - * @rm: recipe management list entry - * @profiles: bitmap of profiles that will be associated. + * ice_calc_recp_cnt - calculate number of recipes based on word count + * @word_cnt: number of lookup words + * + * Word count should include switch ID word and regular lookup words. + * Returns: number of recipes required to fit @word_cnt, including extra recipes + * needed for recipe chaining (if needed). */ -static int -ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, - unsigned long *profiles) +static int ice_calc_recp_cnt(u8 word_cnt) { - 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; - u16 free_res_idx; - u16 recipe_count; - u8 chain_idx; - u8 recps = 0; - int status; + /* All words fit in a single recipe, no need for chaining. */ + if (word_cnt <= ICE_NUM_WORDS_RECIPE) + return 1; - /* When more than one recipe are required, another recipe is needed to - * chain them together. Matching a tunnel metadata ID takes up one of - * the match fields in the chaining recipe reducing the number of - * chained recipes by one. + /* Recipe chaining required. Result indexes are fitted right after + * regular lookup words. In some cases a new recipe must be added in + * order to fit result indexes. + * + * While the word count increases, every 5 words an extra recipe needs + * to be added. However, by adding a recipe, one word for its result + * index must also be added, therefore every 4 words recipe count + * increases by 1. This calculation does not apply to word count == 1, + * which is handled above. */ - /* check number of free result indices */ - bitmap_zero(result_idx_bm, ICE_MAX_FV_WORDS); - free_res_idx = ice_find_free_recp_res_idx(hw, profiles, result_idx_bm); + return (word_cnt + 2) / (ICE_NUM_WORDS_RECIPE - 1); +} - ice_debug(hw, ICE_DBG_SW, "Result idx slots: %d, need %d\n", - free_res_idx, rm->n_grp_count); +static void fill_recipe_template(struct ice_aqc_recipe_data_elem *recp, u16 rid, + const struct ice_sw_recipe *rm) +{ + int i; - if (rm->n_grp_count > 1) { - if (rm->n_grp_count > free_res_idx) - return -ENOSPC; + recp->recipe_indx = rid; + recp->content.act_ctrl |= ICE_AQ_RECIPE_ACT_PRUNE_INDX_M; - rm->n_grp_count++; + for (i = 0; i < ICE_NUM_WORDS_RECIPE; i++) { + recp->content.lkup_indx[i] = ICE_AQ_RECIPE_LKUP_IGNORE; + recp->content.mask[i] = cpu_to_le16(0); } - if (rm->n_grp_count > ICE_MAX_CHAIN_RECIPE) - return -ENOSPC; + set_bit(rid, (unsigned long *)recp->recipe_bitmap); + recp->content.act_ctrl_fwd_priority = rm->priority; - tmp = kcalloc(ICE_MAX_NUM_RECIPES, sizeof(*tmp), GFP_KERNEL); - if (!tmp) - return -ENOMEM; + if (rm->need_pass_l2) + recp->content.act_ctrl |= ICE_AQ_RECIPE_ACT_NEED_PASS_L2; - buf = devm_kcalloc(ice_hw_to_dev(hw), rm->n_grp_count, sizeof(*buf), - GFP_KERNEL); - if (!buf) { - status = -ENOMEM; - goto err_mem; - } - - bitmap_zero(rm->r_bitmap, ICE_MAX_NUM_RECIPES); - recipe_count = ICE_MAX_NUM_RECIPES; - status = ice_aq_get_recipe(hw, tmp, &recipe_count, ICE_SW_LKUP_MAC, - NULL); - if (status || recipe_count == 0) - goto err_unroll; + if (rm->allow_pass_l2) + recp->content.act_ctrl |= ICE_AQ_RECIPE_ACT_ALLOW_PASS_L2; +} - /* Allocate the recipe resources, and configure them according to the - * match fields from protocol headers and extracted field vectors. - */ - chain_idx = find_first_bit(result_idx_bm, ICE_MAX_FV_WORDS); - list_for_each_entry(entry, &rm->rg_list, l_entry) { - u8 i; +static void bookkeep_recipe(struct ice_sw_recipe *recipe, + struct ice_aqc_recipe_data_elem *r, + const struct ice_sw_recipe *rm) +{ + memcpy(recipe->r_bitmap, r->recipe_bitmap, sizeof(recipe->r_bitmap)); - status = ice_alloc_recipe(hw, &entry->rid); - if (status) - goto err_unroll; + recipe->priority = r->content.act_ctrl_fwd_priority; + recipe->tun_type = rm->tun_type; + recipe->need_pass_l2 = rm->need_pass_l2; + recipe->allow_pass_l2 = rm->allow_pass_l2; + recipe->recp_created = true; +} - content = &buf[recps].content; +/* For memcpy in ice_add_sw_recipe. */ +static_assert(sizeof_field(struct ice_aqc_recipe_data_elem, recipe_bitmap) == + sizeof_field(struct ice_sw_recipe, r_bitmap)); - /* Clear the result index of the located recipe, as this will be - * updated, if needed, later in the recipe creation process. - */ - tmp[0].content.result_indx = 0; +/** + * ice_add_sw_recipe - function to call AQ calls to create switch recipe + * @hw: pointer to hardware structure + * @rm: recipe management list entry + * @profiles: bitmap of profiles that will be associated. + */ +static int +ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, + unsigned long *profiles) +{ + struct ice_aqc_recipe_data_elem *buf __free(kfree) = NULL; + DECLARE_BITMAP(result_idx_bm, ICE_MAX_FV_WORDS); + struct ice_aqc_recipe_data_elem *root; + struct ice_sw_recipe *recipe; + u16 free_res_idx, rid; + int lookup = 0; + int recp_cnt; + int status; + int word; + int i; - buf[recps] = tmp[0]; - buf[recps].recipe_indx = (u8)entry->rid; - /* if the recipe is a non-root recipe RID should be programmed - * as 0 for the rules to be applied correctly. - */ - content->rid = 0; - memset(&content->lkup_indx, 0, - sizeof(content->lkup_indx)); - - /* All recipes use look-up index 0 to match switch ID. */ - 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++) { - content->lkup_indx[i] = 0x80; - content->mask[i] = 0; - } + recp_cnt = ice_calc_recp_cnt(rm->n_ext_words); - for (i = 0; i < entry->r_group.n_val_pairs; i++) { - content->lkup_indx[i + 1] = entry->fv_idx[i]; - content->mask[i + 1] = cpu_to_le16(entry->fv_mask[i]); - } + bitmap_zero(result_idx_bm, ICE_MAX_FV_WORDS); + bitmap_zero(rm->r_bitmap, ICE_MAX_NUM_RECIPES); - if (rm->n_grp_count > 1) { - /* Checks to see if there really is a valid result index - * that can be used. - */ - if (chain_idx >= ICE_MAX_FV_WORDS) { - ice_debug(hw, ICE_DBG_SW, "No chain index available\n"); - status = -ENOSPC; - goto err_unroll; - } + /* Check number of free result indices */ + free_res_idx = ice_find_free_recp_res_idx(hw, profiles, result_idx_bm); - entry->chain_idx = chain_idx; - content->result_indx = - ICE_AQ_RECIPE_RESULT_EN | - FIELD_PREP(ICE_AQ_RECIPE_RESULT_DATA_M, - chain_idx); - clear_bit(chain_idx, result_idx_bm); - chain_idx = find_first_bit(result_idx_bm, - ICE_MAX_FV_WORDS); - } + ice_debug(hw, ICE_DBG_SW, "Result idx slots: %d, need %d\n", + free_res_idx, recp_cnt); - /* fill recipe dependencies */ - bitmap_zero((unsigned long *)buf[recps].recipe_bitmap, - ICE_MAX_NUM_RECIPES); - set_bit(buf[recps].recipe_indx, - (unsigned long *)buf[recps].recipe_bitmap); - content->act_ctrl_fwd_priority = rm->priority; + /* Last recipe doesn't need result index */ + if (recp_cnt - 1 > free_res_idx) + return -ENOSPC; - if (rm->need_pass_l2) - content->act_ctrl |= ICE_AQ_RECIPE_ACT_NEED_PASS_L2; + if (recp_cnt > ICE_MAX_CHAIN_RECIPE_RES) + return -E2BIG; - if (rm->allow_pass_l2) - content->act_ctrl |= ICE_AQ_RECIPE_ACT_ALLOW_PASS_L2; - recps++; - } + buf = kcalloc(recp_cnt, sizeof(*buf), GFP_KERNEL); + if (!buf) + return -ENOMEM; - if (rm->n_grp_count == 1) { - rm->root_rid = buf[0].recipe_indx; - set_bit(buf[0].recipe_indx, rm->r_bitmap); - buf[0].content.rid = rm->root_rid | ICE_AQ_RECIPE_ID_IS_ROOT; - if (sizeof(buf[0].recipe_bitmap) >= sizeof(rm->r_bitmap)) { - memcpy(buf[0].recipe_bitmap, rm->r_bitmap, - sizeof(buf[0].recipe_bitmap)); - } else { - status = -EINVAL; - goto err_unroll; - } - /* Applicable only for ROOT_RECIPE, set the fwd_priority for - * the recipe which is getting created if specified - * by user. Usually any advanced switch filter, which results - * into new extraction sequence, ended up creating a new recipe - * of type ROOT and usually recipes are associated with profiles - * Switch rule referreing newly created recipe, needs to have - * either/or 'fwd' or 'join' priority, otherwise switch rule - * evaluation will not happen correctly. In other words, if - * switch rule to be evaluated on priority basis, then recipe - * needs to have priority, otherwise it will be evaluated last. - */ - buf[0].content.act_ctrl_fwd_priority = rm->priority; - } else { - struct ice_recp_grp_entry *last_chain_entry; - u16 rid, i; + /* Setup the non-root subrecipes. These do not contain lookups for other + * subrecipes results. Set associated recipe only to own recipe index. + * Each non-root subrecipe needs a free result index from FV. + * + * Note: only done if there is more than one recipe. + */ + for (i = 0; i < recp_cnt - 1; i++) { + struct ice_aqc_recipe_content *content; + u8 result_idx; - /* Allocate the last recipe that will chain the outcomes of the - * other recipes together - */ status = ice_alloc_recipe(hw, &rid); if (status) - goto err_unroll; + return status; - content = &buf[recps].content; + fill_recipe_template(&buf[i], rid, rm); - buf[recps].recipe_indx = (u8)rid; - 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 + result_idx = find_first_bit(result_idx_bm, ICE_MAX_FV_WORDS); + /* Check if there really is a valid result index that can be + * used. */ - last_chain_entry = devm_kzalloc(ice_hw_to_dev(hw), - sizeof(*last_chain_entry), - GFP_KERNEL); - if (!last_chain_entry) { - status = -ENOMEM; - goto err_unroll; - } - last_chain_entry->rid = rid; - memset(&content->lkup_indx, 0, sizeof(content->lkup_indx)); - /* All recipes use look-up index 0 to match switch ID. */ - 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++) { - content->lkup_indx[i] = ICE_AQ_RECIPE_LKUP_IGNORE; - content->mask[i] = 0; + if (result_idx >= ICE_MAX_FV_WORDS) { + ice_debug(hw, ICE_DBG_SW, "No chain index available\n"); + return -ENOSPC; } + clear_bit(result_idx, result_idx_bm); + + content = &buf[i].content; + content->result_indx = ICE_AQ_RECIPE_RESULT_EN | + FIELD_PREP(ICE_AQ_RECIPE_RESULT_DATA_M, + result_idx); - i = 1; - /* update r_bitmap with the recp that is used for chaining */ + /* Set recipe association to be used for root recipe */ set_bit(rid, rm->r_bitmap); - /* this is the recipe that chains all the other recipes so it - * should not have a chaining ID to indicate the same - */ - 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; - 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); - if (sizeof(buf[recps].recipe_bitmap) >= - sizeof(rm->r_bitmap)) { - memcpy(buf[recps].recipe_bitmap, rm->r_bitmap, - sizeof(buf[recps].recipe_bitmap)); - } else { - status = -EINVAL; - goto err_unroll; + + word = 0; + while (lookup < rm->n_ext_words && + word < ICE_NUM_WORDS_RECIPE) { + content->lkup_indx[word] = rm->fv_idx[lookup]; + content->mask[word] = cpu_to_le16(rm->fv_mask[lookup]); + + lookup++; + word++; } - content->act_ctrl_fwd_priority = rm->priority; - recps++; - rm->root_rid = (u8)rid; + recipe = &hw->switch_info->recp_list[rid]; + set_bit(result_idx, recipe->res_idxs); + bookkeep_recipe(recipe, &buf[i], rm); } - status = ice_acquire_change_lock(hw, ICE_RES_WRITE); - if (status) - goto err_unroll; - status = ice_aq_add_recipe(hw, buf, rm->n_grp_count, NULL); - ice_release_change_lock(hw); + /* Setup the root recipe */ + status = ice_alloc_recipe(hw, &rid); if (status) - goto err_unroll; - - /* Every recipe that just got created add it to the recipe - * book keeping list - */ - list_for_each_entry(entry, &rm->rg_list, l_entry) { - struct ice_switch_info *sw = hw->switch_info; - bool is_root, idx_found = false; - struct ice_sw_recipe *recp; - u16 idx, buf_idx = 0; - - /* find buffer index for copying some data */ - for (idx = 0; idx < rm->n_grp_count; idx++) - if (buf[idx].recipe_indx == entry->rid) { - buf_idx = idx; - idx_found = true; - } + return status; - if (!idx_found) { - status = -EIO; - goto err_unroll; - } + recipe = &hw->switch_info->recp_list[rid]; + root = &buf[recp_cnt - 1]; + fill_recipe_template(root, rid, rm); - recp = &sw->recp_list[entry->rid]; - is_root = (rm->root_rid == entry->rid); - recp->is_root = is_root; + /* Set recipe association, use previously set bitmap and own rid */ + set_bit(rid, rm->r_bitmap); + memcpy(root->recipe_bitmap, rm->r_bitmap, sizeof(root->recipe_bitmap)); - recp->root_rid = entry->rid; - recp->big_recp = (is_root && rm->n_grp_count > 1); + /* For non-root recipes rid should be 0, for root it should be correct + * rid value ored with 0x80 (is root bit). + */ + root->content.rid = rid | ICE_AQ_RECIPE_ID_IS_ROOT; - memcpy(&recp->ext_words, entry->r_group.pairs, - entry->r_group.n_val_pairs * sizeof(struct ice_fv_word)); + /* Fill remaining lookups in root recipe */ + word = 0; + while (lookup < rm->n_ext_words && + word < ICE_NUM_WORDS_RECIPE /* should always be true */) { + root->content.lkup_indx[word] = rm->fv_idx[lookup]; + root->content.mask[word] = cpu_to_le16(rm->fv_mask[lookup]); - memcpy(recp->r_bitmap, buf[buf_idx].recipe_bitmap, - sizeof(recp->r_bitmap)); + lookup++; + word++; + } - /* Copy non-result fv index values and masks to recipe. This - * call will also update the result recipe bitmask. + /* Fill result indexes as lookups */ + i = 0; + while (i < recp_cnt - 1 && + word < ICE_NUM_WORDS_RECIPE /* should always be true */) { + root->content.lkup_indx[word] = buf[i].content.result_indx & + ~ICE_AQ_RECIPE_RESULT_EN; + root->content.mask[word] = cpu_to_le16(0xffff); + /* For bookkeeping, it is needed to mark FV index as used for + * intermediate result. */ - ice_collect_result_idx(&buf[buf_idx], recp); + set_bit(root->content.lkup_indx[word], recipe->res_idxs); - /* for non-root recipes, also copy to the root, this allows - * easier matching of a complete chained recipe - */ - if (!is_root) - ice_collect_result_idx(&buf[buf_idx], - &sw->recp_list[rm->root_rid]); - - recp->n_ext_words = entry->r_group.n_val_pairs; - recp->chain_idx = entry->chain_idx; - 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; + i++; + word++; } - rm->root_buf = buf; - kfree(tmp); - return status; -err_unroll: -err_mem: - kfree(tmp); - devm_kfree(ice_hw_to_dev(hw), buf); - return status; -} + rm->root_rid = rid; + bookkeep_recipe(&hw->switch_info->recp_list[rid], root, rm); -/** - * ice_create_recipe_group - creates recipe group - * @hw: pointer to hardware structure - * @rm: recipe management list entry - * @lkup_exts: lookup elements - */ -static int -ice_create_recipe_group(struct ice_hw *hw, struct ice_sw_recipe *rm, - struct ice_prot_lkup_ext *lkup_exts) -{ - u8 recp_count = 0; - int status; - - rm->n_grp_count = 0; + /* Program the recipe */ + status = ice_acquire_change_lock(hw, ICE_RES_WRITE); + if (status) + return status; - /* Create recipes for words that are marked not done by packing them - * as best fit. - */ - status = ice_create_first_fit_recp_def(hw, lkup_exts, - &rm->rg_list, &recp_count); - if (!status) { - rm->n_grp_count += recp_count; - rm->n_ext_words = lkup_exts->n_val_words; - memcpy(&rm->ext_words, lkup_exts->fv_words, - sizeof(rm->ext_words)); - memcpy(rm->word_masks, lkup_exts->field_mask, - sizeof(rm->word_masks)); - } + status = ice_aq_add_recipe(hw, buf, recp_cnt, NULL); + ice_release_change_lock(hw); + if (status) + return status; - return status; + return 0; } /* ice_get_compat_fv_bitmap - Get compatible field vector bitmap for rule @@ -5268,6 +5242,9 @@ ice_get_compat_fv_bitmap(struct ice_hw *hw, struct ice_adv_rule_info *rinfo, case ICE_SW_TUN_GTPC: prof_type = ICE_PROF_TUN_GTPC; break; + case ICE_SW_TUN_PFCP: + prof_type = ICE_PROF_TUN_PFCP; + break; case ICE_SW_TUN_AND_NON_TUN: default: prof_type = ICE_PROF_ALL; @@ -5278,6 +5255,49 @@ ice_get_compat_fv_bitmap(struct ice_hw *hw, struct ice_adv_rule_info *rinfo, } /** + * ice_subscribe_recipe - subscribe to an existing recipe + * @hw: pointer to the hardware structure + * @rid: recipe ID to subscribe to + * + * Return: 0 on success, and others on error + */ +static int ice_subscribe_recipe(struct ice_hw *hw, u16 rid) +{ + DEFINE_RAW_FLEX(struct ice_aqc_alloc_free_res_elem, sw_buf, elem, 1); + u16 buf_len = __struct_size(sw_buf); + u16 res_type; + int status; + + /* Prepare buffer to allocate resource */ + sw_buf->num_elems = cpu_to_le16(1); + res_type = FIELD_PREP(ICE_AQC_RES_TYPE_M, ICE_AQC_RES_TYPE_RECIPE) | + ICE_AQC_RES_TYPE_FLAG_SUBSCRIBE_SHARED | + ICE_AQC_RES_TYPE_FLAG_SUBSCRIBE_CTL; + sw_buf->res_type = cpu_to_le16(res_type); + + sw_buf->elem[0].e.sw_resp = cpu_to_le16(rid); + + status = ice_aq_alloc_free_res(hw, sw_buf, buf_len, + ice_aqc_opc_alloc_res); + + return status; +} + +/** + * ice_subscribable_recp_shared - share an existing subscribable recipe + * @hw: pointer to the hardware structure + * @rid: recipe ID to subscribe to + */ +static void ice_subscribable_recp_shared(struct ice_hw *hw, u16 rid) +{ + struct ice_sw_recipe *recps = hw->switch_info->recp_list; + u16 sub_rid; + + for_each_set_bit(sub_rid, recps[rid].r_bitmap, ICE_MAX_NUM_RECIPES) + ice_subscribe_recipe(hw, sub_rid); +} + +/** * ice_add_adv_recipe - Add an advanced recipe that is not part of the default * @hw: pointer to hardware structure * @lkups: lookup elements or match criteria for the advanced recipe, one @@ -5293,12 +5313,11 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, DECLARE_BITMAP(fv_bitmap, ICE_MAX_NUM_PROFILES); DECLARE_BITMAP(profiles, ICE_MAX_NUM_PROFILES); struct ice_prot_lkup_ext *lkup_exts; - struct ice_recp_grp_entry *r_entry; struct ice_sw_fv_list_entry *fvit; - struct ice_recp_grp_entry *r_tmp; struct ice_sw_fv_list_entry *tmp; struct ice_sw_recipe *rm; int status = 0; + u16 rid_tmp; u8 i; if (!lkups_cnt) @@ -5336,7 +5355,6 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, * headers being programmed. */ INIT_LIST_HEAD(&rm->fv_list); - INIT_LIST_HEAD(&rm->rg_list); /* Get bitmap of field vectors (profiles) that are compatible with the * rule request; only these will be searched in the subsequent call to @@ -5348,12 +5366,10 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, if (status) goto err_unroll; - /* Group match words into recipes using preferred recipe grouping - * criteria. - */ - status = ice_create_recipe_group(hw, rm, lkup_exts); - if (status) - goto err_unroll; + /* Copy FV words and masks from lkup_exts to recipe struct. */ + rm->n_ext_words = lkup_exts->n_val_words; + memcpy(rm->ext_words, lkup_exts->fv_words, sizeof(rm->ext_words)); + memcpy(rm->word_masks, lkup_exts->field_mask, sizeof(rm->word_masks)); /* set the recipe priority if specified */ rm->priority = (u8)rinfo->priority; @@ -5364,7 +5380,7 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, /* Find offsets from the field vector. Pick the first one for all the * recipes. */ - status = ice_fill_fv_word_index(hw, &rm->fv_list, &rm->rg_list); + status = ice_fill_fv_word_index(hw, rm); if (status) goto err_unroll; @@ -5376,10 +5392,14 @@ 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); - if (*rid < ICE_MAX_NUM_RECIPES) + *rid = ice_find_recp(hw, lkup_exts, rinfo, true); + if (*rid < ICE_MAX_NUM_RECIPES) { /* Success if found a recipe that match the existing criteria */ + if (hw->recp_reuse) + ice_subscribable_recp_shared(hw, *rid); + goto err_unroll; + } rm->tun_type = rinfo->tun_type; /* Recipe we need does not exist, add a recipe */ @@ -5398,14 +5418,14 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, status = ice_aq_get_recipe_to_profile(hw, fvit->profile_id, &recp_assoc, NULL); if (status) - goto err_unroll; + goto err_free_recipe; bitmap_from_arr64(r_bitmap, &recp_assoc, ICE_MAX_NUM_RECIPES); bitmap_or(r_bitmap, r_bitmap, rm->r_bitmap, ICE_MAX_NUM_RECIPES); status = ice_acquire_change_lock(hw, ICE_RES_WRITE); if (status) - goto err_unroll; + goto err_free_recipe; bitmap_to_arr64(&recp_assoc, r_bitmap, ICE_MAX_NUM_RECIPES); status = ice_aq_map_recipe_to_profile(hw, fvit->profile_id, @@ -5413,7 +5433,7 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, ice_release_change_lock(hw); if (status) - goto err_unroll; + goto err_free_recipe; /* Update profile to recipe bitmap array */ bitmap_copy(profile_to_recipe[fvit->profile_id], r_bitmap, @@ -5427,18 +5447,22 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, *rid = rm->root_rid; memcpy(&hw->switch_info->recp_list[*rid].lkup_exts, lkup_exts, sizeof(*lkup_exts)); -err_unroll: - list_for_each_entry_safe(r_entry, r_tmp, &rm->rg_list, l_entry) { - list_del(&r_entry->l_entry); - devm_kfree(ice_hw_to_dev(hw), r_entry); + goto err_unroll; + +err_free_recipe: + if (hw->recp_reuse) { + for_each_set_bit(rid_tmp, rm->r_bitmap, ICE_MAX_NUM_RECIPES) { + if (!ice_free_recipe_res(hw, rid_tmp)) + clear_bit(rid_tmp, rm->r_bitmap); + } } +err_unroll: list_for_each_entry_safe(fvit, tmp, &rm->fv_list, list_entry) { list_del(&fvit->list_entry); devm_kfree(ice_hw_to_dev(hw), fvit); } - devm_kfree(ice_hw_to_dev(hw), rm->root_buf); kfree(rm); err_free_lkup_exts: @@ -5552,6 +5576,9 @@ ice_find_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, case ICE_SW_TUN_VXLAN: match |= ICE_PKT_TUN_UDP; break; + case ICE_SW_TUN_PFCP: + match |= ICE_PKT_PFCP; + break; default: break; } @@ -5692,6 +5719,9 @@ ice_fill_adv_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, case ICE_GTP: len = sizeof(struct ice_udp_gtp_hdr); break; + case ICE_PFCP: + len = sizeof(struct ice_pfcp_hdr); + break; case ICE_PPPOE: len = sizeof(struct ice_pppoe_hdr); break; @@ -5948,7 +5978,7 @@ ice_adv_add_update_vsi_list(struct ice_hw *hw, /* A rule already exists with the new VSI being added */ if (test_bit(vsi_handle, m_entry->vsi_list_info->vsi_map)) - return 0; + return -EEXIST; /* Update the previously created VSI list set with * the new VSI ID passed in @@ -6293,8 +6323,6 @@ ice_replay_vsi_fltr(struct ice_hw *hw, u16 vsi_handle, u8 recp_id, if (!itr->vsi_list_info || !test_bit(vsi_handle, itr->vsi_list_info->vsi_map)) continue; - /* Clearing it so that the logic can add it back */ - clear_bit(vsi_handle, itr->vsi_list_info->vsi_map); f_entry.fltr_info.vsi_handle = vsi_handle; f_entry.fltr_info.fltr_act = ICE_FWD_TO_VSI; /* update the src in case it is VSI num */ @@ -6440,7 +6468,7 @@ ice_rem_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, return -EIO; } - rid = ice_find_recp(hw, &lkup_exts, rinfo); + rid = ice_find_recp(hw, &lkup_exts, rinfo, false); /* If did not find a recipe that match the existing criteria */ if (rid == ICE_MAX_NUM_RECIPES) return -EINVAL; @@ -6484,14 +6512,21 @@ ice_rem_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, ice_aqc_opc_remove_sw_rules, NULL); if (!status || status == -ENOENT) { struct ice_switch_info *sw = hw->switch_info; + struct ice_sw_recipe *r_list = sw->recp_list; mutex_lock(rule_lock); list_del(&list_elem->list_entry); devm_kfree(ice_hw_to_dev(hw), list_elem->lkups); devm_kfree(ice_hw_to_dev(hw), list_elem); mutex_unlock(rule_lock); - if (list_empty(&sw->recp_list[rid].filt_rules)) - sw->recp_list[rid].adv_rule = false; + if (list_empty(&r_list[rid].filt_rules)) { + r_list[rid].adv_rule = false; + + /* All rules for this recipe are now removed */ + if (hw->recp_reuse) + ice_release_recipe_res(hw, + &r_list[rid]); + } } kfree(s_rule); } diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index 89ffa1b51b5a..671d7a5f359f 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -8,8 +8,9 @@ #define ICE_SW_CFG_MAX_BUF_LEN 2048 #define ICE_DFLT_VSI_INVAL 0xff -#define ICE_FLTR_RX BIT(0) -#define ICE_FLTR_TX BIT(1) +#define ICE_FLTR_RX BIT(0) +#define ICE_FLTR_TX BIT(1) +#define ICE_FLTR_TX_ONLY BIT(2) #define ICE_VSI_INVAL_ID 0xffff #define ICE_INVAL_Q_HANDLE 0xFFFF @@ -21,6 +22,8 @@ #define ICE_PROFID_IPV6_GTPC_NO_TEID 45 #define ICE_PROFID_IPV6_GTPU_TEID 46 #define ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER 70 +#define ICE_PROFID_IPV4_PFCP_NODE 79 +#define ICE_PROFID_IPV6_PFCP_SESSION 82 #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)) @@ -213,7 +216,6 @@ struct ice_sw_recipe { /* For a chained recipe the root recipe is what should be used for * programming rules */ - u8 is_root; u8 root_rid; u8 recp_created; @@ -224,19 +226,8 @@ struct ice_sw_recipe { */ struct ice_fv_word ext_words[ICE_MAX_CHAIN_WORDS]; u16 word_masks[ICE_MAX_CHAIN_WORDS]; - - /* if this recipe is a collection of other recipe */ - u8 big_recp; - - /* if this recipe is part of another bigger recipe then chain index - * corresponding to this recipe - */ - u8 chain_idx; - - /* if this recipe is a collection of other recipe then count of other - * recipes and recipe IDs of those recipes - */ - u8 n_grp_count; + u8 fv_idx[ICE_MAX_CHAIN_WORDS]; + u16 fv_mask[ICE_MAX_CHAIN_WORDS]; /* Bit map specifying the IDs associated with this group of recipe */ DECLARE_BITMAP(r_bitmap, ICE_MAX_NUM_RECIPES); @@ -269,10 +260,6 @@ struct ice_sw_recipe { u8 need_pass_l2:1; u8 allow_pass_l2:1; - struct list_head rg_list; - - /* AQ buffer associated with this recipe */ - struct ice_aqc_recipe_data_elem *root_buf; /* This struct saves the fv_words for a given lookup */ struct ice_prot_lkup_ext lkup_exts; }; @@ -429,5 +416,6 @@ ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 *r_assoc, int ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 r_assoc, struct ice_sq_cd *cd); +void ice_init_chk_recipe_reuse_support(struct ice_hw *hw); #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 688ccb0615ab..fb9ea7f8ef44 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -12,14 +12,11 @@ /** * ice_tc_count_lkups - determine lookup count for switch filter * @flags: TC-flower flags - * @headers: Pointer to TC flower filter header structure * @fltr: Pointer to outer TC filter structure * - * Determine lookup count based on TC flower input for switch filter. + * Return: lookup count based on TC flower input for a switch filter. */ -static int -ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, - struct ice_tc_flower_fltr *fltr) +static int ice_tc_count_lkups(u32 flags, struct ice_tc_flower_fltr *fltr) { int lkups_cnt = 1; /* 0th lookup is metadata */ @@ -37,7 +34,10 @@ ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, if (flags & ICE_TC_FLWR_FIELD_ENC_DST_MAC) lkups_cnt++; - if (flags & ICE_TC_FLWR_FIELD_ENC_OPTS) + if (flags & ICE_TC_FLWR_FIELD_GTP_OPTS) + lkups_cnt++; + + if (flags & ICE_TC_FLWR_FIELD_PFCP_OPTS) lkups_cnt++; if (flags & (ICE_TC_FLWR_FIELD_ENC_SRC_IPV4 | @@ -140,6 +140,8 @@ ice_proto_type_from_tunnel(enum ice_tunnel_type type) return ICE_GTP; case TNL_GTPC: return ICE_GTP_NO_PAY; + case TNL_PFCP: + return ICE_PFCP; default: return 0; } @@ -159,6 +161,8 @@ ice_sw_type_from_tunnel(enum ice_tunnel_type type) return ICE_SW_TUN_GTPU; case TNL_GTPC: return ICE_SW_TUN_GTPC; + case TNL_PFCP: + return ICE_SW_TUN_PFCP; default: return ICE_NON_TUN; } @@ -221,8 +225,7 @@ ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr, i++; } - if (flags & ICE_TC_FLWR_FIELD_ENC_OPTS && - (fltr->tunnel_type == TNL_GTPU || fltr->tunnel_type == TNL_GTPC)) { + if (flags & ICE_TC_FLWR_FIELD_GTP_OPTS) { list[i].type = ice_proto_type_from_tunnel(fltr->tunnel_type); if (fltr->gtp_pdu_info_masks.pdu_type) { @@ -239,6 +242,22 @@ ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr, i++; } + if (flags & ICE_TC_FLWR_FIELD_PFCP_OPTS) { + struct ice_pfcp_hdr *hdr_h, *hdr_m; + + hdr_h = &list[i].h_u.pfcp_hdr; + hdr_m = &list[i].m_u.pfcp_hdr; + list[i].type = ICE_PFCP; + + hdr_h->flags = fltr->pfcp_meta_keys.type; + hdr_m->flags = fltr->pfcp_meta_masks.type & 0x01; + + hdr_h->seid = fltr->pfcp_meta_keys.seid; + hdr_m->seid = fltr->pfcp_meta_masks.seid; + + i++; + } + if (flags & (ICE_TC_FLWR_FIELD_ENC_SRC_IPV4 | ICE_TC_FLWR_FIELD_ENC_DEST_IPV4)) { list[i].type = ice_proto_type_from_ipv4(false); @@ -374,8 +393,11 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags, if (tc_fltr->tunnel_type != TNL_LAST) { i = ice_tc_fill_tunnel_outer(flags, tc_fltr, list, i); - headers = &tc_fltr->inner_headers; - inner = true; + /* PFCP is considered non-tunneled - don't swap headers. */ + if (tc_fltr->tunnel_type != TNL_PFCP) { + headers = &tc_fltr->inner_headers; + inner = true; + } } if (flags & ICE_TC_FLWR_FIELD_ETH_TYPE_ID) { @@ -629,6 +651,8 @@ static int ice_tc_tun_get_type(struct net_device *tunnel_dev) */ if (netif_is_gtp(tunnel_dev)) return TNL_GTPU; + if (netif_is_pfcp(tunnel_dev)) + return TNL_PFCP; return TNL_LAST; } @@ -642,35 +666,41 @@ 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) +static int ice_tc_setup_action(struct net_device *filter_dev, + struct ice_tc_flower_fltr *fltr, + struct net_device *target_dev, + enum ice_sw_fwd_act_type action) { struct ice_repr *repr; - fltr->action.fltr_act = ICE_FWD_TO_VSI; + if (action != ICE_FWD_TO_VSI && action != ICE_MIRROR_PACKET) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported action to setup provided"); + return -EINVAL; + } + + fltr->action.fltr_act = action; if (ice_is_port_repr_netdev(filter_dev) && - ice_is_port_repr_netdev(target_dev)) { + ice_is_port_repr_netdev(target_dev) && + fltr->direction == ICE_ESWITCH_FLTR_EGRESS) { 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)) { + ice_tc_is_dev_uplink(target_dev) && + fltr->direction == ICE_ESWITCH_FLTR_EGRESS) { repr = ice_netdev_to_repr(filter_dev); fltr->dest_vsi = repr->src_vsi->back->eswitch.uplink_vsi; - fltr->direction = ICE_ESWITCH_FLTR_EGRESS; } else if (ice_tc_is_dev_uplink(filter_dev) && - ice_is_port_repr_netdev(target_dev)) { + ice_is_port_repr_netdev(target_dev) && + fltr->direction == ICE_ESWITCH_FLTR_INGRESS) { 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"); + "The action is not supported for this netdevice"); return -EINVAL; } @@ -683,48 +713,11 @@ ice_tc_setup_drop_action(struct net_device *filter_dev, { 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 { + if (!ice_tc_is_dev_uplink(filter_dev) && + !(ice_is_port_repr_netdev(filter_dev) && + fltr->direction == ICE_ESWITCH_FLTR_INGRESS)) { NL_SET_ERR_MSG_MOD(fltr->extack, - "Unsupported netdevice in switchdev mode"); - return -EINVAL; - } - - return 0; -} - -static int ice_tc_setup_mirror_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_MIRROR_PACKET; - - 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->eswitch.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"); + "The action is not supported for this netdevice"); return -EINVAL; } @@ -746,16 +739,19 @@ static int ice_eswitch_tc_parse_action(struct net_device *filter_dev, break; case FLOW_ACTION_REDIRECT: - err = ice_tc_setup_redirect_action(filter_dev, fltr, act->dev); + err = ice_tc_setup_action(filter_dev, fltr, + act->dev, ICE_FWD_TO_VSI); if (err) return err; break; case FLOW_ACTION_MIRRED: - err = ice_tc_setup_mirror_action(filter_dev, fltr, act->dev); + err = ice_tc_setup_action(filter_dev, fltr, + act->dev, ICE_MIRROR_PACKET); if (err) return err; + break; default: @@ -766,10 +762,157 @@ static int ice_eswitch_tc_parse_action(struct net_device *filter_dev, return 0; } +static bool ice_is_fltr_lldp(struct ice_tc_flower_fltr *fltr) +{ + return fltr->outer_headers.l2_key.n_proto == htons(ETH_P_LLDP); +} + +static bool ice_is_fltr_pf_tx_lldp(struct ice_tc_flower_fltr *fltr) +{ + struct ice_vsi *vsi = fltr->src_vsi, *uplink; + + if (!ice_is_switchdev_running(vsi->back)) + return false; + + uplink = vsi->back->eswitch.uplink_vsi; + return vsi == uplink && fltr->action.fltr_act == ICE_DROP_PACKET && + ice_is_fltr_lldp(fltr) && + fltr->direction == ICE_ESWITCH_FLTR_EGRESS && + fltr->flags == ICE_TC_FLWR_FIELD_ETH_TYPE_ID; +} + +static bool ice_is_fltr_vf_tx_lldp(struct ice_tc_flower_fltr *fltr) +{ + struct ice_vsi *vsi = fltr->src_vsi, *uplink; + + uplink = vsi->back->eswitch.uplink_vsi; + return fltr->src_vsi->type == ICE_VSI_VF && ice_is_fltr_lldp(fltr) && + fltr->direction == ICE_ESWITCH_FLTR_EGRESS && + fltr->dest_vsi == uplink; +} + +static struct ice_tc_flower_fltr * +ice_find_pf_tx_lldp_fltr(struct ice_pf *pf) +{ + struct ice_tc_flower_fltr *fltr; + + hlist_for_each_entry(fltr, &pf->tc_flower_fltr_list, tc_flower_node) + if (ice_is_fltr_pf_tx_lldp(fltr)) + return fltr; + + return NULL; +} + +static bool ice_any_vf_lldp_tx_ena(struct ice_pf *pf) +{ + struct ice_vf *vf; + unsigned int bkt; + + ice_for_each_vf(pf, bkt, vf) + if (vf->lldp_tx_ena) + return true; + + return false; +} + +int ice_pass_vf_tx_lldp(struct ice_vsi *vsi, bool deinit) +{ + struct ice_rule_query_data remove_entry = { + .rid = vsi->vf->lldp_recipe_id, + .rule_id = vsi->vf->lldp_rule_id, + .vsi_handle = vsi->idx, + }; + struct ice_pf *pf = vsi->back; + int err; + + if (vsi->vf->lldp_tx_ena) + return 0; + + if (!deinit && !ice_find_pf_tx_lldp_fltr(vsi->back)) + return -EINVAL; + + if (!deinit && ice_any_vf_lldp_tx_ena(pf)) + return -EINVAL; + + err = ice_rem_adv_rule_by_id(&pf->hw, &remove_entry); + if (!err) + vsi->vf->lldp_tx_ena = true; + + return err; +} + +int ice_drop_vf_tx_lldp(struct ice_vsi *vsi, bool init) +{ + struct ice_rule_query_data rule_added; + struct ice_adv_rule_info rinfo = { + .priority = 7, + .src_vsi = vsi->idx, + .sw_act = { + .src = vsi->idx, + .flag = ICE_FLTR_TX, + .fltr_act = ICE_DROP_PACKET, + .vsi_handle = vsi->idx, + }, + .flags_info.act_valid = true, + }; + struct ice_adv_lkup_elem list[3]; + struct ice_pf *pf = vsi->back; + int err; + + if (!init && !vsi->vf->lldp_tx_ena) + return 0; + + memset(list, 0, sizeof(list)); + ice_rule_add_direction_metadata(&list[0]); + ice_rule_add_src_vsi_metadata(&list[1]); + list[2].type = ICE_ETYPE_OL; + list[2].h_u.ethertype.ethtype_id = htons(ETH_P_LLDP); + list[2].m_u.ethertype.ethtype_id = htons(0xFFFF); + + err = ice_add_adv_rule(&pf->hw, list, ARRAY_SIZE(list), &rinfo, + &rule_added); + if (err) { + dev_err(&pf->pdev->dev, + "Failed to add an LLDP rule to VSI 0x%X: %d\n", + vsi->idx, err); + } else { + vsi->vf->lldp_recipe_id = rule_added.rid; + vsi->vf->lldp_rule_id = rule_added.rule_id; + vsi->vf->lldp_tx_ena = false; + } + + return err; +} + +static void ice_handle_add_pf_lldp_drop_rule(struct ice_vsi *vsi) +{ + struct ice_tc_flower_fltr *fltr; + struct ice_pf *pf = vsi->back; + + hlist_for_each_entry(fltr, &pf->tc_flower_fltr_list, tc_flower_node) { + if (!ice_is_fltr_vf_tx_lldp(fltr)) + continue; + ice_pass_vf_tx_lldp(fltr->src_vsi, true); + break; + } +} + +static void ice_handle_del_pf_lldp_drop_rule(struct ice_pf *pf) +{ + int i; + + /* Make the VF LLDP fwd to uplink rule dormant */ + ice_for_each_vsi(pf, i) { + struct ice_vsi *vf_vsi = pf->vsi[i]; + + if (vf_vsi && vf_vsi->type == ICE_VSI_VF) + ice_drop_vf_tx_lldp(vf_vsi, false); + } +} + static int ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) { - struct ice_tc_flower_lyr_2_4_hdrs *headers = &fltr->outer_headers; struct ice_adv_rule_info rule_info = { 0 }; struct ice_rule_query_data rule_added; struct ice_hw *hw = &vsi->back->hw; @@ -784,7 +927,10 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) return -EOPNOTSUPP; } - lkups_cnt = ice_tc_count_lkups(flags, headers, fltr); + if (ice_is_fltr_vf_tx_lldp(fltr)) + return ice_pass_vf_tx_lldp(vsi, false); + + lkups_cnt = ice_tc_count_lkups(flags, fltr); list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC); if (!list) return -ENOMEM; @@ -813,11 +959,27 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) rule_info.sw_act.src = hw->pf_id; rule_info.flags_info.act = ICE_SINGLE_ACT_LB_ENABLE; } else if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS && + !fltr->dest_vsi && vsi == vsi->back->eswitch.uplink_vsi) { + /* PF to Uplink */ + rule_info.sw_act.flag |= ICE_FLTR_TX; + rule_info.sw_act.src = vsi->idx; + } else if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS && fltr->dest_vsi == vsi->back->eswitch.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; + /* This is a specific case. The destination VSI index is + * overwritten by the source VSI index. This type of filter + * should allow the packet to go to the LAN, not to the + * VSI passed here. It should set LAN_EN bit only. However, + * the VSI must be a valid one. Setting source VSI index + * here is safe. Even if the result from switch is set LAN_EN + * and LB_EN (which normally will pass the packet to this VSI) + * packet won't be seen on the VSI, because local loopback is + * turned off. + */ + rule_info.sw_act.vsi_handle = vsi->idx; } else { /* VF to VF */ rule_info.sw_act.flag |= ICE_FLTR_TX; @@ -834,11 +996,17 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter because it already exist"); ret = -EINVAL; goto exit; + } else if (ret == -ENOSPC) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter: insufficient space available."); + goto exit; } else if (ret) { NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter due to error"); goto exit; } + if (ice_is_fltr_pf_tx_lldp(fltr)) + ice_handle_add_pf_lldp_drop_rule(vsi); + /* store the output params, which are needed later for removing * advanced switch filter */ @@ -973,7 +1141,6 @@ static int ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *tc_fltr) { - struct ice_tc_flower_lyr_2_4_hdrs *headers = &tc_fltr->outer_headers; struct ice_adv_rule_info rule_info = {0}; struct ice_rule_query_data rule_added; struct ice_adv_lkup_elem *list; @@ -1009,7 +1176,7 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, return PTR_ERR(dest_vsi); } - lkups_cnt = ice_tc_count_lkups(flags, headers, tc_fltr); + lkups_cnt = ice_tc_count_lkups(flags, tc_fltr); list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC); if (!list) return -ENOMEM; @@ -1044,8 +1211,13 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, tc_fltr->action.fwd.q.hw_queue, lkups_cnt); break; case ICE_DROP_PACKET: - rule_info.sw_act.flag |= ICE_FLTR_RX; - rule_info.sw_act.src = hw->pf_id; + if (tc_fltr->direction == ICE_ESWITCH_FLTR_EGRESS) { + rule_info.sw_act.flag |= ICE_FLTR_TX; + rule_info.sw_act.src = vsi->idx; + } else { + rule_info.sw_act.flag |= ICE_FLTR_RX; + rule_info.sw_act.src = hw->pf_id; + } rule_info.priority = ICE_SWITCH_FLTR_PRIO_VSI; break; default: @@ -1059,6 +1231,10 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, "Unable to add filter because it already exist"); ret = -EINVAL; goto exit; + } else if (ret == -ENOSPC) { + NL_SET_ERR_MSG_MOD(tc_fltr->extack, + "Unable to add filter: insufficient space available."); + goto exit; } else if (ret) { NL_SET_ERR_MSG_MOD(tc_fltr->extack, "Unable to add filter due to error"); @@ -1352,6 +1528,7 @@ ice_parse_tunnel_attr(struct net_device *dev, struct flow_rule *rule, struct ice_tc_flower_fltr *fltr) { struct ice_tc_flower_lyr_2_4_hdrs *headers = &fltr->outer_headers; + struct netlink_ext_ack *extack = fltr->extack; struct flow_match_control enc_control; fltr->tunnel_type = ice_tc_tun_get_type(dev); @@ -1372,6 +1549,9 @@ ice_parse_tunnel_attr(struct net_device *dev, struct flow_rule *rule, flow_rule_match_enc_control(rule, &enc_control); + if (flow_rule_has_enc_control_flags(enc_control.mask->flags, extack)) + return -EOPNOTSUPP; + if (enc_control.key->addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { struct flow_match_ipv4_addrs match; @@ -1409,7 +1589,8 @@ ice_parse_tunnel_attr(struct net_device *dev, struct flow_rule *rule, } } - if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_OPTS)) { + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_OPTS) && + (fltr->tunnel_type == TNL_GTPU || fltr->tunnel_type == TNL_GTPC)) { struct flow_match_enc_opts match; flow_rule_match_enc_opts(rule, &match); @@ -1420,7 +1601,21 @@ ice_parse_tunnel_attr(struct net_device *dev, struct flow_rule *rule, memcpy(&fltr->gtp_pdu_info_masks, &match.mask->data[0], sizeof(struct gtp_pdu_session_info)); - fltr->flags |= ICE_TC_FLWR_FIELD_ENC_OPTS; + fltr->flags |= ICE_TC_FLWR_FIELD_GTP_OPTS; + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_OPTS) && + fltr->tunnel_type == TNL_PFCP) { + struct flow_match_enc_opts match; + + flow_rule_match_enc_opts(rule, &match); + + memcpy(&fltr->pfcp_meta_keys, match.key->data, + sizeof(struct pfcp_metadata)); + memcpy(&fltr->pfcp_meta_masks, match.mask->data, + sizeof(struct pfcp_metadata)); + + fltr->flags |= ICE_TC_FLWR_FIELD_PFCP_OPTS; } return 0; @@ -1432,11 +1627,16 @@ ice_parse_tunnel_attr(struct net_device *dev, struct flow_rule *rule, * @filter_dev: Pointer to device on which filter is being added * @f: Pointer to struct flow_cls_offload * @fltr: Pointer to filter structure + * @ingress: if the rule is added to an ingress block + * + * Return: 0 if the flower was parsed successfully, -EINVAL if the flower + * cannot be parsed, -EOPNOTSUPP if such filter cannot be configured + * for the given VSI. */ static int ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, struct flow_cls_offload *f, - struct ice_tc_flower_fltr *fltr) + struct ice_tc_flower_fltr *fltr, bool ingress) { struct ice_tc_flower_lyr_2_4_hdrs *headers = &fltr->outer_headers; struct flow_rule *rule = flow_cls_offload_flow_rule(f); @@ -1481,10 +1681,14 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, return err; } - /* header pointers should point to the inner headers, outer - * header were already set by ice_parse_tunnel_attr - */ - headers = &fltr->inner_headers; + /* PFCP is considered non-tunneled - don't swap headers. */ + if (fltr->tunnel_type != TNL_PFCP) { + /* Header pointers should point to the inner headers, + * outer header were already set by + * ice_parse_tunnel_attr(). + */ + headers = &fltr->inner_headers; + } } else if (dissector->used_keys & (BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | @@ -1516,6 +1720,20 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, fltr->flags |= ICE_TC_FLWR_FIELD_ETH_TYPE_ID; } + if (!ingress) { + bool switchdev = + ice_is_eswitch_mode_switchdev(vsi->back); + + if (switchdev != (n_proto_key == ETH_P_LLDP)) { + NL_SET_ERR_MSG_FMT_MOD(fltr->extack, + "%sLLDP filtering is not supported on egress in %s mode", + switchdev ? "Non-" : "", + switchdev ? "switchdev" : + "legacy"); + return -EOPNOTSUPP; + } + } + headers->l2_key.n_proto = cpu_to_be16(n_proto_key); headers->l2_mask.n_proto = cpu_to_be16(n_proto_mask); headers->l3_key.ip_proto = match.key->ip_proto; @@ -1638,6 +1856,10 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, flow_rule_match_control(rule, &match); addr_type = match.key->addr_type; + + if (flow_rule_has_control_flags(match.mask->flags, + fltr->extack)) + return -EOPNOTSUPP; } if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { @@ -1687,6 +1909,14 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, return -EINVAL; } } + + /* Ingress filter on representor results in an egress filter in HW + * and vice versa + */ + ingress = ice_is_port_repr_netdev(filter_dev) ? !ingress : ingress; + fltr->direction = ingress ? ICE_ESWITCH_FLTR_INGRESS : + ICE_ESWITCH_FLTR_EGRESS; + return 0; } @@ -1900,6 +2130,12 @@ static int ice_del_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) struct ice_pf *pf = vsi->back; int err; + if (ice_is_fltr_pf_tx_lldp(fltr)) + ice_handle_del_pf_lldp_drop_rule(pf); + + if (ice_is_fltr_vf_tx_lldp(fltr)) + return ice_drop_vf_tx_lldp(vsi, false); + rule_rem.rid = fltr->rid; rule_rem.rule_id = fltr->rule_id; rule_rem.vsi_handle = fltr->dest_vsi_handle; @@ -1936,14 +2172,18 @@ static int ice_del_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) * @vsi: Pointer to VSI * @f: Pointer to flower offload structure * @__fltr: Pointer to struct ice_tc_flower_fltr + * @ingress: if the rule is added to an ingress block * * This function parses TC-flower input fields, parses action, * and adds a filter. + * + * Return: 0 if the filter was successfully added, + * negative error code otherwise. */ static int ice_add_tc_fltr(struct net_device *netdev, struct ice_vsi *vsi, struct flow_cls_offload *f, - struct ice_tc_flower_fltr **__fltr) + struct ice_tc_flower_fltr **__fltr, bool ingress) { struct ice_tc_flower_fltr *fltr; int err; @@ -1960,7 +2200,7 @@ ice_add_tc_fltr(struct net_device *netdev, struct ice_vsi *vsi, fltr->src_vsi = vsi; INIT_HLIST_NODE(&fltr->tc_flower_node); - err = ice_parse_cls_flower(netdev, vsi, f, fltr); + err = ice_parse_cls_flower(netdev, vsi, f, fltr, ingress); if (err < 0) goto err; @@ -2003,10 +2243,13 @@ ice_find_tc_flower_fltr(struct ice_pf *pf, unsigned long cookie) * @netdev: Pointer to filter device * @vsi: Pointer to VSI * @cls_flower: Pointer to flower offload structure + * @ingress: if the rule is added to an ingress block + * + * Return: 0 if the flower was successfully added, + * negative error code otherwise. */ -int -ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi, - struct flow_cls_offload *cls_flower) +int ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi, + struct flow_cls_offload *cls_flower, bool ingress) { struct netlink_ext_ack *extack = cls_flower->common.extack; struct net_device *vsi_netdev = vsi->netdev; @@ -2041,7 +2284,7 @@ ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi, } /* prep and add TC-flower filter in HW */ - err = ice_add_tc_fltr(netdev, vsi, cls_flower, &fltr); + err = ice_add_tc_fltr(netdev, vsi, cls_flower, &fltr, ingress); if (err) return err; diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.h b/drivers/net/ethernet/intel/ice/ice_tc_lib.h index 65d387163a46..8a3ab2f22af9 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.h @@ -4,6 +4,9 @@ #ifndef _ICE_TC_LIB_H_ #define _ICE_TC_LIB_H_ +#include <linux/bits.h> +#include <net/pfcp.h> + #define ICE_TC_FLWR_FIELD_DST_MAC BIT(0) #define ICE_TC_FLWR_FIELD_SRC_MAC BIT(1) #define ICE_TC_FLWR_FIELD_VLAN BIT(2) @@ -22,7 +25,7 @@ #define ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT BIT(15) #define ICE_TC_FLWR_FIELD_ENC_DST_MAC BIT(16) #define ICE_TC_FLWR_FIELD_ETH_TYPE_ID BIT(17) -#define ICE_TC_FLWR_FIELD_ENC_OPTS BIT(18) +#define ICE_TC_FLWR_FIELD_GTP_OPTS BIT(18) #define ICE_TC_FLWR_FIELD_CVLAN BIT(19) #define ICE_TC_FLWR_FIELD_PPPOE_SESSID BIT(20) #define ICE_TC_FLWR_FIELD_PPP_PROTO BIT(21) @@ -34,6 +37,7 @@ #define ICE_TC_FLWR_FIELD_VLAN_PRIO BIT(27) #define ICE_TC_FLWR_FIELD_CVLAN_PRIO BIT(28) #define ICE_TC_FLWR_FIELD_VLAN_TPID BIT(29) +#define ICE_TC_FLWR_FIELD_PFCP_OPTS BIT(30) #define ICE_TC_FLOWER_MASK_32 0xFFFFFFFF @@ -161,6 +165,8 @@ struct ice_tc_flower_fltr { __be32 tenant_id; struct gtp_pdu_session_info gtp_pdu_info_keys; struct gtp_pdu_session_info gtp_pdu_info_masks; + struct pfcp_metadata pfcp_meta_keys; + struct pfcp_metadata pfcp_meta_masks; u32 flags; u8 tunnel_type; struct ice_tc_flower_action action; @@ -205,13 +211,14 @@ static inline int ice_chnl_dmac_fltr_cnt(struct ice_pf *pf) } struct ice_vsi *ice_locate_vsi_using_queue(struct ice_vsi *vsi, int queue); -int -ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi, - struct flow_cls_offload *cls_flower); -int -ice_del_cls_flower(struct ice_vsi *vsi, struct flow_cls_offload *cls_flower); +int ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi, + struct flow_cls_offload *cls_flower, bool ingress); +int ice_del_cls_flower(struct ice_vsi *vsi, + struct flow_cls_offload *cls_flower); void ice_replay_tc_fltrs(struct ice_pf *pf); bool ice_is_tunnel_supported(struct net_device *dev); +int ice_drop_vf_tx_lldp(struct ice_vsi *vsi, bool init); +int ice_pass_vf_tx_lldp(struct ice_vsi *vsi, bool deinit); static inline bool ice_is_forward_action(enum ice_sw_fwd_act_type fltr_act) { diff --git a/drivers/net/ethernet/intel/ice/ice_trace.h b/drivers/net/ethernet/intel/ice/ice_trace.h index b2f5c9fe0149..07aab6e130cd 100644 --- a/drivers/net/ethernet/intel/ice/ice_trace.h +++ b/drivers/net/ethernet/intel/ice/ice_trace.h @@ -69,7 +69,7 @@ DECLARE_EVENT_CLASS(ice_rx_dim_template, TP_fast_assign(__entry->q_vector = q_vector; __entry->dim = dim; - __assign_str(devname, q_vector->rx.rx_ring->netdev->name);), + __assign_str(devname);), TP_printk("netdev: %s Rx-Q: %d dim-state: %d dim-profile: %d dim-tune: %d dim-st-right: %d dim-st-left: %d dim-tired: %d", __get_str(devname), @@ -96,7 +96,7 @@ DECLARE_EVENT_CLASS(ice_tx_dim_template, TP_fast_assign(__entry->q_vector = q_vector; __entry->dim = dim; - __assign_str(devname, q_vector->tx.tx_ring->netdev->name);), + __assign_str(devname);), TP_printk("netdev: %s Tx-Q: %d dim-state: %d dim-profile: %d dim-tune: %d dim-st-right: %d dim-st-left: %d dim-tired: %d", __get_str(devname), @@ -128,7 +128,7 @@ DECLARE_EVENT_CLASS(ice_tx_template, TP_fast_assign(__entry->ring = ring; __entry->desc = desc; __entry->buf = buf; - __assign_str(devname, ring->netdev->name);), + __assign_str(devname);), TP_printk("netdev: %s ring: %pK desc: %pK buf %pK", __get_str(devname), __entry->ring, __entry->desc, __entry->buf) @@ -156,7 +156,7 @@ DECLARE_EVENT_CLASS(ice_rx_template, TP_fast_assign(__entry->ring = ring; __entry->desc = desc; - __assign_str(devname, ring->netdev->name);), + __assign_str(devname);), TP_printk("netdev: %s ring: %pK desc: %pK", __get_str(devname), __entry->ring, __entry->desc) @@ -180,7 +180,7 @@ DECLARE_EVENT_CLASS(ice_rx_indicate_template, TP_fast_assign(__entry->ring = ring; __entry->desc = desc; __entry->skb = skb; - __assign_str(devname, ring->netdev->name);), + __assign_str(devname);), TP_printk("netdev: %s ring: %pK desc: %pK skb %pK", __get_str(devname), __entry->ring, __entry->desc, __entry->skb) @@ -203,7 +203,7 @@ DECLARE_EVENT_CLASS(ice_xmit_template, TP_fast_assign(__entry->ring = ring; __entry->skb = skb; - __assign_str(devname, ring->netdev->name);), + __assign_str(devname);), TP_printk("netdev: %s skb: %pK ring: %pK", __get_str(devname), __entry->skb, __entry->ring) @@ -330,6 +330,24 @@ DEFINE_EVENT(ice_esw_br_port_template, TP_ARGS(port) ); +DECLARE_EVENT_CLASS(ice_switch_stats_template, + TP_PROTO(struct ice_switch_info *sw_info), + TP_ARGS(sw_info), + TP_STRUCT__entry(__field(u16, rule_cnt) + __field(u8, recp_cnt)), + TP_fast_assign(__entry->rule_cnt = sw_info->rule_cnt; + __entry->recp_cnt = sw_info->recp_cnt;), + TP_printk("rules=%u recipes=%u", + __entry->rule_cnt, + __entry->recp_cnt) +); + +DEFINE_EVENT(ice_switch_stats_template, + ice_aq_sw_rules, + TP_PROTO(struct ice_switch_info *sw_info), + TP_ARGS(sw_info) +); + /* 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 97d41d6ebf1f..0e5107fe62ad 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -456,7 +456,7 @@ void ice_free_rx_ring(struct ice_rx_ring *rx_ring) if (rx_ring->vsi->type == ICE_VSI_PF) if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) xdp_rxq_info_unreg(&rx_ring->xdp_rxq); - rx_ring->xdp_prog = NULL; + WRITE_ONCE(rx_ring->xdp_prog, NULL); if (rx_ring->xsk_pool) { kfree(rx_ring->xdp_buf); rx_ring->xdp_buf = NULL; @@ -522,44 +522,19 @@ err: } /** - * ice_rx_frame_truesize - * @rx_ring: ptr to Rx ring - * @size: size - * - * calculate the truesize with taking into the account PAGE_SIZE of - * underlying arch - */ -static unsigned int -ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, const unsigned int size) -{ - unsigned int truesize; - -#if (PAGE_SIZE < 8192) - truesize = ice_rx_pg_size(rx_ring) / 2; /* Must be power-of-2 */ -#else - truesize = rx_ring->rx_offset ? - SKB_DATA_ALIGN(rx_ring->rx_offset + size) + - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) : - SKB_DATA_ALIGN(size); -#endif - return truesize; -} - -/** * ice_run_xdp - Executes an XDP program on initialized xdp_buff * @rx_ring: Rx ring * @xdp: xdp_buff used as input to the XDP program * @xdp_prog: XDP program to run * @xdp_ring: ring to be used for XDP_TX action - * @rx_buf: Rx buffer to store the XDP action * @eop_desc: Last descriptor in packet to read metadata from * * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR} */ -static void +static u32 ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring, - struct ice_rx_buf *rx_buf, union ice_32b_rx_flex_desc *eop_desc) + union ice_32b_rx_flex_desc *eop_desc) { unsigned int ret = ICE_XDP_PASS; u32 act; @@ -598,7 +573,7 @@ out_failure: ret = ICE_XDP_CONSUMED; } exit: - ice_set_rx_bufs_act(xdp, rx_ring, ret); + return ret; } /** @@ -837,16 +812,15 @@ ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf) if (!dev_page_is_reusable(page)) return false; -#if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ if (unlikely(rx_buf->pgcnt - pagecnt_bias > 1)) return false; -#else +#if (PAGE_SIZE >= 8192) #define ICE_LAST_OFFSET \ - (SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_2048) + (SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_3072) if (rx_buf->page_offset > ICE_LAST_OFFSET) return false; -#endif /* PAGE_SIZE < 8192) */ +#endif /* PAGE_SIZE >= 8192) */ /* If we have drained the page fragment pool we need to update * the pagecnt_bias and page count so that we fully restock the @@ -885,10 +859,8 @@ ice_add_xdp_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, xdp_buff_set_frags_flag(xdp); } - if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) { - ice_set_rx_bufs_act(xdp, rx_ring, ICE_XDP_CONSUMED); + if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) return -ENOMEM; - } __skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buf->page, rx_buf->page_offset, size); @@ -949,12 +921,6 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size, struct ice_rx_buf *rx_buf; rx_buf = &rx_ring->rx_buf[ntc]; - rx_buf->pgcnt = -#if (PAGE_SIZE < 8192) - page_count(rx_buf->page); -#else - 0; -#endif prefetchw(rx_buf->page); if (!size) @@ -971,6 +937,31 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size, } /** + * ice_get_pgcnts - grab page_count() for gathered fragments + * @rx_ring: Rx descriptor ring to store the page counts on + * + * This function is intended to be called right before running XDP + * program so that the page recycling mechanism will be able to take + * a correct decision regarding underlying pages; this is done in such + * way as XDP program can change the refcount of page + */ +static void ice_get_pgcnts(struct ice_rx_ring *rx_ring) +{ + u32 nr_frags = rx_ring->nr_frags + 1; + u32 idx = rx_ring->first_desc; + struct ice_rx_buf *rx_buf; + u32 cnt = rx_ring->count; + + for (int i = 0; i < nr_frags; i++) { + rx_buf = &rx_ring->rx_buf[idx]; + rx_buf->pgcnt = page_count(rx_buf->page); + + if (++idx == cnt) + idx = 0; + } +} + +/** * ice_build_skb - Build skb around an existing buffer * @rx_ring: Rx descriptor ring to transact packets on * @xdp: xdp_buff pointing to the data @@ -1051,8 +1042,7 @@ ice_construct_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) } /* allocate a skb to store the frags */ - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, ICE_RX_HDR_SIZE, - GFP_ATOMIC | __GFP_NOWARN); + skb = napi_alloc_skb(&rx_ring->q_vector->napi, ICE_RX_HDR_SIZE); if (unlikely(!skb)) return NULL; @@ -1082,12 +1072,12 @@ ice_construct_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) rx_buf->page_offset + headlen, size, xdp->frame_sz); } else { - /* buffer is unused, change the act that should be taken later - * on; data was copied onto skb's linear part so there's no + /* buffer is unused, restore biased page count in Rx buffer; + * data was copied onto skb's linear part so there's no * need for adjusting page offset and we can reuse this buffer * as-is */ - rx_buf->act = ICE_SKB_CONSUMED; + rx_buf->pagecnt_bias++; } if (unlikely(xdp_buff_has_frags(xdp))) { @@ -1135,6 +1125,65 @@ ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf) } /** + * ice_put_rx_mbuf - ice_put_rx_buf() caller, for all frame frags + * @rx_ring: Rx ring with all the auxiliary data + * @xdp: XDP buffer carrying linear + frags part + * @xdp_xmit: XDP_TX/XDP_REDIRECT verdict storage + * @ntc: a current next_to_clean value to be stored at rx_ring + * @verdict: return code from XDP program execution + * + * Walk through gathered fragments and satisfy internal page + * recycle mechanism; we take here an action related to verdict + * returned by XDP program; + */ +static void ice_put_rx_mbuf(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, + u32 *xdp_xmit, u32 ntc, u32 verdict) +{ + u32 nr_frags = rx_ring->nr_frags + 1; + u32 idx = rx_ring->first_desc; + u32 cnt = rx_ring->count; + u32 post_xdp_frags = 1; + struct ice_rx_buf *buf; + int i; + + if (unlikely(xdp_buff_has_frags(xdp))) + post_xdp_frags += xdp_get_shared_info_from_buff(xdp)->nr_frags; + + for (i = 0; i < post_xdp_frags; i++) { + buf = &rx_ring->rx_buf[idx]; + + if (verdict & (ICE_XDP_TX | ICE_XDP_REDIR)) { + ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); + *xdp_xmit |= verdict; + } else if (verdict & ICE_XDP_CONSUMED) { + buf->pagecnt_bias++; + } else if (verdict == ICE_XDP_PASS) { + ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); + } + + ice_put_rx_buf(rx_ring, buf); + + if (++idx == cnt) + idx = 0; + } + /* handle buffers that represented frags released by XDP prog; + * for these we keep pagecnt_bias as-is; refcount from struct page + * has been decremented within XDP prog and we do not have to increase + * the biased refcnt + */ + for (; i < nr_frags; i++) { + buf = &rx_ring->rx_buf[idx]; + ice_put_rx_buf(rx_ring, buf); + if (++idx == cnt) + idx = 0; + } + + xdp->data = NULL; + rx_ring->first_desc = ntc; + rx_ring->nr_frags = 0; +} + +/** * ice_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf * @rx_ring: Rx descriptor ring to transact packets on * @budget: Total limit on number of packets to process @@ -1151,20 +1200,13 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) unsigned int total_rx_bytes = 0, total_rx_pkts = 0; unsigned int offset = rx_ring->rx_offset; struct xdp_buff *xdp = &rx_ring->xdp; - u32 cached_ntc = rx_ring->first_desc; struct ice_tx_ring *xdp_ring = NULL; struct bpf_prog *xdp_prog = NULL; u32 ntc = rx_ring->next_to_clean; + u32 cached_ntu, xdp_verdict; u32 cnt = rx_ring->count; u32 xdp_xmit = 0; - u32 cached_ntu; bool failure; - u32 first; - - /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ -#if (PAGE_SIZE < 8192) - xdp->frame_sz = ice_rx_frame_truesize(rx_ring, 0); -#endif xdp_prog = READ_ONCE(rx_ring->xdp_prog); if (xdp_prog) { @@ -1224,12 +1266,9 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) hard_start = page_address(rx_buf->page) + rx_buf->page_offset - offset; xdp_prepare_buff(xdp, hard_start, offset, size, !!offset); -#if (PAGE_SIZE > 4096) - /* At larger PAGE_SIZE, frame_sz depend on len size */ - xdp->frame_sz = ice_rx_frame_truesize(rx_ring, size); -#endif xdp_buff_clear_frags_flag(xdp); } else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) { + ice_put_rx_mbuf(rx_ring, xdp, NULL, ntc, ICE_XDP_CONSUMED); break; } if (++ntc == cnt) @@ -1239,15 +1278,15 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) if (ice_is_non_eop(rx_ring, rx_desc)) continue; - ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf, rx_desc); - if (rx_buf->act == ICE_XDP_PASS) + ice_get_pgcnts(rx_ring); + xdp_verdict = ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_desc); + if (xdp_verdict == ICE_XDP_PASS) goto construct_skb; total_rx_bytes += xdp_get_buff_len(xdp); total_rx_pkts++; - xdp->data = NULL; - rx_ring->first_desc = ntc; - rx_ring->nr_frags = 0; + ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict); + continue; construct_skb: if (likely(ice_ring_uses_build_skb(rx_ring))) @@ -1257,18 +1296,12 @@ construct_skb: /* exit if we failed to retrieve a buffer */ if (!skb) { rx_ring->ring_stats->rx_stats.alloc_page_failed++; - rx_buf->act = ICE_XDP_CONSUMED; - if (unlikely(xdp_buff_has_frags(xdp))) - ice_set_rx_bufs_act(xdp, rx_ring, - ICE_XDP_CONSUMED); - xdp->data = NULL; - rx_ring->first_desc = ntc; - rx_ring->nr_frags = 0; - break; + xdp_verdict = ICE_XDP_CONSUMED; } - xdp->data = NULL; - rx_ring->first_desc = ntc; - rx_ring->nr_frags = 0; + ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict); + + if (!skb) + break; stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S); if (unlikely(ice_test_staterr(rx_desc->wb.status_error0, @@ -1297,23 +1330,6 @@ construct_skb: total_rx_pkts++; } - first = rx_ring->first_desc; - while (cached_ntc != first) { - struct ice_rx_buf *buf = &rx_ring->rx_buf[cached_ntc]; - - if (buf->act & (ICE_XDP_TX | ICE_XDP_REDIR)) { - ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); - xdp_xmit |= buf->act; - } else if (buf->act & ICE_XDP_CONSUMED) { - buf->pagecnt_bias++; - } else if (buf->act == ICE_XDP_PASS) { - ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); - } - - ice_put_rx_buf(rx_ring, buf); - if (++cached_ntc >= cnt) - cached_ntc = 0; - } rx_ring->next_to_clean = ntc; /* return up to cleaned_count buffers to hardware */ failure = ice_alloc_rx_bufs(rx_ring, ICE_RX_DESC_UNUSED(rx_ring)); @@ -1392,14 +1408,14 @@ static void ice_net_dim(struct ice_q_vector *q_vector) struct dim_sample dim_sample; __ice_update_sample(q_vector, tx, &dim_sample, true); - net_dim(&tx->dim, dim_sample); + net_dim(&tx->dim, &dim_sample); } if (ITR_IS_DYNAMIC(rx)) { struct dim_sample dim_sample; __ice_update_sample(q_vector, rx, &dim_sample, false); - net_dim(&rx->dim, dim_sample); + net_dim(&rx->dim, &dim_sample); } } @@ -1522,10 +1538,11 @@ int ice_napi_poll(struct napi_struct *napi, int budget) * budget and be more aggressive about cleaning up the Tx descriptors. */ ice_for_each_tx_ring(tx_ring, q_vector->tx) { + struct xsk_buff_pool *xsk_pool = READ_ONCE(tx_ring->xsk_pool); bool wd; - if (tx_ring->xsk_pool) - wd = ice_xmit_zc(tx_ring); + if (xsk_pool) + wd = ice_xmit_zc(tx_ring, xsk_pool); else if (ice_ring_is_xdp(tx_ring)) wd = true; else @@ -1551,6 +1568,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget) budget_per_ring = budget; ice_for_each_rx_ring(rx_ring, q_vector->rx) { + struct xsk_buff_pool *xsk_pool = READ_ONCE(rx_ring->xsk_pool); int cleaned; /* A dedicated path for zero-copy allows making a single @@ -1558,7 +1576,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget) * ice_clean_rx_irq function and makes the codebase cleaner. */ cleaned = rx_ring->xsk_pool ? - ice_clean_rx_irq_zc(rx_ring, budget_per_ring) : + ice_clean_rx_irq_zc(rx_ring, xsk_pool, budget_per_ring) : ice_clean_rx_irq(rx_ring, budget_per_ring); work_done += cleaned; /* if we clean as many as budgeted, we must not be done */ @@ -1791,6 +1809,7 @@ dma_error: static int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off) { + const struct ice_tx_ring *tx_ring = off->tx_ring; u32 l4_len = 0, l3_len = 0, l2_len = 0; struct sk_buff *skb = first->skb; union { @@ -1940,6 +1959,30 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off) l3_len = l4.hdr - ip.hdr; offset |= (l3_len / 4) << ICE_TX_DESC_LEN_IPLEN_S; + if ((tx_ring->netdev->features & NETIF_F_HW_CSUM) && + !(first->tx_flags & ICE_TX_FLAGS_TSO) && + !skb_csum_is_sctp(skb)) { + /* Set GCS */ + u16 csum_start = (skb->csum_start - skb->mac_header) / 2; + u16 csum_offset = skb->csum_offset / 2; + u16 gcs_params; + + gcs_params = FIELD_PREP(ICE_TX_GCS_DESC_START_M, csum_start) | + FIELD_PREP(ICE_TX_GCS_DESC_OFFSET_M, csum_offset) | + FIELD_PREP(ICE_TX_GCS_DESC_TYPE_M, + ICE_TX_GCS_DESC_CSUM_PSH); + + /* Unlike legacy HW checksums, GCS requires a context + * descriptor. + */ + off->cd_qw1 |= ICE_TX_DESC_DTYPE_CTX; + off->cd_gcs_params = gcs_params; + /* Fill out CSO info in data descriptors */ + off->td_offset |= offset; + off->td_cmd |= cmd; + return 1; + } + /* Enable L4 checksum offloads */ switch (l4_proto) { case IPPROTO_TCP: @@ -2397,17 +2440,20 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) /* allow CONTROL frames egress from main VSI if FW LLDP disabled */ eth = (struct ethhdr *)skb_mac_header(skb); - if (unlikely((skb->priority == TC_PRIO_CONTROL || - eth->h_proto == htons(ETH_P_LLDP)) && - vsi->type == ICE_VSI_PF && - vsi->port_info->qos_cfg.is_sw_lldp)) + + if ((ice_is_switchdev_running(vsi->back) || + ice_lag_is_switchdev_running(vsi->back)) && + vsi->type != ICE_VSI_SF) + ice_eswitch_set_target_vsi(skb, &offload); + else if (unlikely((skb->priority == TC_PRIO_CONTROL || + eth->h_proto == htons(ETH_P_LLDP)) && + vsi->type == ICE_VSI_PF && + vsi->port_info->qos_cfg.is_sw_lldp)) offload.cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX | ICE_TX_CTX_DESC_SWTCH_UPLINK << ICE_TXD_CTX_QW1_CMD_S); ice_tstamp(tx_ring, skb, first, &offload); - if (ice_is_switchdev_running(vsi->back)) - ice_eswitch_set_target_vsi(skb, &offload); if (offload.cd_qw1 & ICE_TX_DESC_DTYPE_CTX) { struct ice_tx_ctx_desc *cdesc; @@ -2421,7 +2467,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) /* setup context descriptor */ cdesc->tunneling_params = cpu_to_le32(offload.cd_tunnel_params); cdesc->l2tag2 = cpu_to_le16(offload.cd_l2tag2); - cdesc->rsvd = cpu_to_le16(0); + cdesc->gcs = cpu_to_le16(offload.cd_gcs_params); cdesc->qw1 = cpu_to_le64(offload.cd_qw1); } diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index af955b0e5dc5..a4b1e9514632 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -193,6 +193,7 @@ struct ice_tx_offload_params { u32 td_l2tag1; u32 cd_tunnel_params; u16 cd_l2tag2; + u16 cd_gcs_params; u8 header_len; }; @@ -201,7 +202,6 @@ struct ice_rx_buf { struct page *page; unsigned int page_offset; unsigned int pgcnt; - unsigned int act; unsigned int pagecnt_bias; }; @@ -359,12 +359,15 @@ struct ice_rx_ring { struct ice_rx_ring *next; /* pointer to next ring in q_vector */ struct xsk_buff_pool *xsk_pool; u32 nr_frags; - dma_addr_t dma; /* physical address of ring */ + u16 max_frame; u16 rx_buf_len; + dma_addr_t dma; /* physical address of ring */ u8 dcb_tc; /* Traffic class of ring */ u8 ptp_rx; #define ICE_RX_FLAGS_RING_BUILD_SKB BIT(1) #define ICE_RX_FLAGS_CRC_STRIP_DIS BIT(2) +#define ICE_RX_FLAGS_MULTIDEV BIT(3) +#define ICE_RX_FLAGS_RING_GCS BIT(4) u8 flags; /* CL5 - 5th cacheline starts here */ struct xdp_rxq_info xdp_rxq; @@ -405,6 +408,7 @@ struct ice_tx_ring { #define ICE_TX_FLAGS_RING_VLAN_L2TAG2 BIT(2) u8 flags; u8 dcb_tc; /* Traffic class of ring */ + u16 quanta_prof_id; } ____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 f8f1d2bdc1be..45cfaabc41cb 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -2,6 +2,7 @@ /* Copyright (c) 2019, Intel Corporation. */ #include <linux/filter.h> +#include <linux/net/intel/libie/rx.h> #include "ice_txrx_lib.h" #include "ice_eswitch.h" @@ -39,30 +40,6 @@ void ice_release_rx_desc(struct ice_rx_ring *rx_ring, u16 val) } /** - * ice_ptype_to_htype - get a hash type - * @ptype: the ptype value from the descriptor - * - * 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. - */ -static enum pkt_hash_types ice_ptype_to_htype(u16 ptype) -{ - struct ice_rx_ptype_decoded decoded = ice_decode_rx_desc_ptype(ptype); - - if (!decoded.known) - return PKT_HASH_TYPE_NONE; - if (decoded.payload_layer == ICE_RX_PTYPE_PAYLOAD_LAYER_PAY4) - return PKT_HASH_TYPE_L4; - if (decoded.payload_layer == ICE_RX_PTYPE_PAYLOAD_LAYER_PAY3) - return PKT_HASH_TYPE_L3; - if (decoded.outer_ip == ICE_RX_PTYPE_OUTER_L2) - return PKT_HASH_TYPE_L2; - - return PKT_HASH_TYPE_NONE; -} - -/** * ice_get_rx_hash - get RX hash value from descriptor * @rx_desc: specific descriptor * @@ -91,14 +68,33 @@ ice_rx_hash_to_skb(const struct ice_rx_ring *rx_ring, const union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb, u16 rx_ptype) { + struct libeth_rx_pt decoded; u32 hash; - if (!(rx_ring->netdev->features & NETIF_F_RXHASH)) + decoded = libie_rx_pt_parse(rx_ptype); + if (!libeth_rx_pt_has_hash(rx_ring->netdev, decoded)) return; hash = ice_get_rx_hash(rx_desc); if (likely(hash)) - skb_set_hash(skb, hash, ice_ptype_to_htype(rx_ptype)); + libeth_rx_pt_set_hash(skb, hash, decoded); +} + +/** + * ice_rx_gcs - Set generic checksum in skb + * @skb: skb currently being received and modified + * @rx_desc: receive descriptor + */ +static void ice_rx_gcs(struct sk_buff *skb, + const union ice_32b_rx_flex_desc *rx_desc) +{ + const struct ice_32b_rx_flex_desc_nic *desc; + u16 csum; + + desc = (struct ice_32b_rx_flex_desc_nic *)rx_desc; + skb->ip_summed = CHECKSUM_COMPLETE; + csum = (__force u16)desc->raw_csum; + skb->csum = csum_unfold((__force __sum16)swab16(csum)); } /** @@ -114,34 +110,35 @@ static void ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb, union ice_32b_rx_flex_desc *rx_desc, u16 ptype) { - struct ice_rx_ptype_decoded decoded; + struct libeth_rx_pt decoded; u16 rx_status0, rx_status1; bool ipv4, ipv6; - rx_status0 = le16_to_cpu(rx_desc->wb.status_error0); - rx_status1 = le16_to_cpu(rx_desc->wb.status_error1); - - decoded = ice_decode_rx_desc_ptype(ptype); - /* Start with CHECKSUM_NONE and by default csum_level = 0 */ skb->ip_summed = CHECKSUM_NONE; - skb_checksum_none_assert(skb); - /* check if Rx checksum is enabled */ - if (!(ring->netdev->features & NETIF_F_RXCSUM)) + decoded = libie_rx_pt_parse(ptype); + if (!libeth_rx_pt_has_checksum(ring->netdev, decoded)) return; - /* check if HW has decoded the packet and checksum */ - if (!(rx_status0 & BIT(ICE_RX_FLEX_DESC_STATUS0_L3L4P_S))) + rx_status0 = le16_to_cpu(rx_desc->wb.status_error0); + rx_status1 = le16_to_cpu(rx_desc->wb.status_error1); + + if ((ring->flags & ICE_RX_FLAGS_RING_GCS) && + rx_desc->wb.rxdid == ICE_RXDID_FLEX_NIC && + (decoded.inner_prot == LIBETH_RX_PT_INNER_TCP || + decoded.inner_prot == LIBETH_RX_PT_INNER_UDP || + decoded.inner_prot == LIBETH_RX_PT_INNER_ICMP)) { + ice_rx_gcs(skb, rx_desc); return; + } - if (!(decoded.known && decoded.outer_ip)) + /* check if HW has decoded the packet and checksum */ + if (!(rx_status0 & BIT(ICE_RX_FLEX_DESC_STATUS0_L3L4P_S))) return; - ipv4 = (decoded.outer_ip == ICE_RX_PTYPE_OUTER_IP) && - (decoded.outer_ip_ver == ICE_RX_PTYPE_OUTER_IPV4); - ipv6 = (decoded.outer_ip == ICE_RX_PTYPE_OUTER_IP) && - (decoded.outer_ip_ver == ICE_RX_PTYPE_OUTER_IPV6); + ipv4 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV4; + ipv6 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV6; if (ipv4 && (rx_status0 & (BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_EIPE_S)))) { ring->vsi->back->hw_rx_eipe_error++; @@ -169,19 +166,10 @@ ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb, * 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 >= ICE_RX_PTYPE_TUNNEL_IP_GRENAT) + if (decoded.tunnel_type >= LIBETH_RX_PT_TUNNEL_IP_GRENAT) skb->csum_level = 1; - /* Only report checksum unnecessary for TCP, UDP, or SCTP */ - switch (decoded.inner_prot) { - case ICE_RX_PTYPE_INNER_PROT_TCP: - case ICE_RX_PTYPE_INNER_PROT_UDP: - case ICE_RX_PTYPE_INNER_PROT_SCTP: - skb->ip_summed = CHECKSUM_UNNECESSARY; - break; - default: - break; - } + skb->ip_summed = CHECKSUM_UNNECESSARY; return; checksum_fail: @@ -236,7 +224,16 @@ ice_process_skb_fields(struct ice_rx_ring *rx_ring, ice_rx_hash_to_skb(rx_ring, rx_desc, skb, ptype); /* modifies the skb - consumes the enet header */ - skb->protocol = eth_type_trans(skb, rx_ring->netdev); + if (unlikely(rx_ring->flags & ICE_RX_FLAGS_MULTIDEV)) { + struct net_device *netdev = ice_eswitch_get_target(rx_ring, + rx_desc); + + if (ice_is_port_repr_netdev(netdev)) + ice_repr_inc_rx_stats(netdev, skb->len); + skb->protocol = eth_type_trans(skb, netdev); + } else { + skb->protocol = eth_type_trans(skb, rx_ring->netdev); + } ice_rx_csum(rx_ring, skb, rx_desc, ptype); @@ -527,42 +524,6 @@ static int ice_xdp_rx_hw_ts(const struct xdp_md *ctx, u64 *ts_ns) return 0; } -/* Define a ptype index -> XDP hash type lookup table. - * It uses the same ptype definitions as ice_decode_rx_desc_ptype[], - * avoiding possible copy-paste errors. - */ -#undef ICE_PTT -#undef ICE_PTT_UNUSED_ENTRY - -#define ICE_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\ - [PTYPE] = XDP_RSS_L3_##OUTER_IP_VER | XDP_RSS_L4_##I | XDP_RSS_TYPE_##PL - -#define ICE_PTT_UNUSED_ENTRY(PTYPE) [PTYPE] = 0 - -/* A few supplementary definitions for when XDP hash types do not coincide - * with what can be generated from ptype definitions - * by means of preprocessor concatenation. - */ -#define XDP_RSS_L3_NONE XDP_RSS_TYPE_NONE -#define XDP_RSS_L4_NONE XDP_RSS_TYPE_NONE -#define XDP_RSS_TYPE_PAY2 XDP_RSS_TYPE_L2 -#define XDP_RSS_TYPE_PAY3 XDP_RSS_TYPE_NONE -#define XDP_RSS_TYPE_PAY4 XDP_RSS_L4 - -static const enum xdp_rss_hash_type -ice_ptype_to_xdp_hash[ICE_NUM_DEFINED_PTYPES] = { - ICE_PTYPES -}; - -#undef XDP_RSS_L3_NONE -#undef XDP_RSS_L4_NONE -#undef XDP_RSS_TYPE_PAY2 -#undef XDP_RSS_TYPE_PAY3 -#undef XDP_RSS_TYPE_PAY4 - -#undef ICE_PTT -#undef ICE_PTT_UNUSED_ENTRY - /** * ice_xdp_rx_hash_type - Get XDP-specific hash type from the RX descriptor * @eop_desc: End of Packet descriptor @@ -570,12 +531,7 @@ ice_ptype_to_xdp_hash[ICE_NUM_DEFINED_PTYPES] = { static enum xdp_rss_hash_type ice_xdp_rx_hash_type(const union ice_32b_rx_flex_desc *eop_desc) { - u16 ptype = ice_get_ptype(eop_desc); - - if (unlikely(ptype >= ICE_NUM_DEFINED_PTYPES)) - return 0; - - return ice_ptype_to_xdp_hash[ptype]; + return libie_rx_pt_parse(ice_get_ptype(eop_desc)).hash_type; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h index afcead4baef4..6cf32b404127 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h @@ -6,49 +6,6 @@ #include "ice.h" /** - * ice_set_rx_bufs_act - propagate Rx buffer action to frags - * @xdp: XDP buffer representing frame (linear and frags part) - * @rx_ring: Rx ring struct - * act: action to store onto Rx buffers related to XDP buffer parts - * - * Set action that should be taken before putting Rx buffer from first frag - * to the last. - */ -static inline void -ice_set_rx_bufs_act(struct xdp_buff *xdp, const struct ice_rx_ring *rx_ring, - const unsigned int act) -{ - u32 sinfo_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags; - u32 nr_frags = rx_ring->nr_frags + 1; - u32 idx = rx_ring->first_desc; - u32 cnt = rx_ring->count; - struct ice_rx_buf *buf; - - for (int i = 0; i < nr_frags; i++) { - buf = &rx_ring->rx_buf[idx]; - buf->act = act; - - if (++idx == cnt) - idx = 0; - } - - /* adjust pagecnt_bias on frags freed by XDP prog */ - if (sinfo_frags < rx_ring->nr_frags && act == ICE_XDP_CONSUMED) { - u32 delta = rx_ring->nr_frags - sinfo_frags; - - while (delta) { - if (idx == 0) - idx = cnt - 1; - else - idx--; - buf = &rx_ring->rx_buf[idx]; - buf->pagecnt_bias--; - delta--; - } - } -} - -/** * ice_test_staterr - tests bits in Rx descriptor status and error fields * @status_err_n: Rx descriptor status_error0 or status_error1 bits * @stat_err_bits: value to mask @@ -154,7 +111,6 @@ static inline u32 ice_set_rs_bit(const struct ice_tx_ring *xdp_ring) } void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res, u32 first_idx); -int ice_xmit_xdp_buff(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring); int __ice_xmit_xdp_ring(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring, bool frame); void ice_release_rx_desc(struct ice_rx_ring *rx_ring, u16 val); diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 9ff92dba5823..3d68f465952d 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -18,6 +18,8 @@ #include "ice_sbq_cmd.h" #include "ice_vlan_mode.h" #include "ice_fwlog.h" +#include <linux/wait.h> +#include <net/dscp.h> static inline bool ice_is_tc_ena(unsigned long bitmap, u8 tc) { @@ -61,6 +63,7 @@ static inline u32 ice_round_to_num(u32 N, u32 R) ICE_DBG_AQ_DESC | \ ICE_DBG_AQ_DESC_BUF | \ ICE_DBG_AQ_CMD) +#define ICE_DBG_PARSER BIT_ULL(28) #define ICE_DBG_USER BIT_ULL(31) @@ -71,6 +74,14 @@ enum ice_aq_res_ids { ICE_GLOBAL_CFG_LOCK_RES_ID }; +enum ice_fec_stats_types { + ICE_FEC_CORR_LOW, + ICE_FEC_CORR_HIGH, + ICE_FEC_UNCORR_LOW, + ICE_FEC_UNCORR_HIGH, + ICE_FEC_MAX +}; + /* FW update timeout definitions are in milliseconds */ #define ICE_NVM_TIMEOUT 180000 #define ICE_CHANGE_LOCK_TIMEOUT 1000 @@ -150,7 +161,7 @@ enum ice_vsi_type { ICE_VSI_CTRL = 3, /* equates to ICE_VSI_PF with 1 queue pair */ ICE_VSI_CHNL = 4, ICE_VSI_LB = 6, - ICE_VSI_SWITCHDEV_CTRL = 7, + ICE_VSI_SF = 9, }; struct ice_link_status { @@ -204,6 +215,7 @@ struct ice_phy_info { enum ice_fltr_ptype { /* NONE - used for undef/error */ ICE_FLTR_PTYPE_NONF_NONE = 0, + ICE_FLTR_PTYPE_NONF_ETH, ICE_FLTR_PTYPE_NONF_IPV4_UDP, ICE_FLTR_PTYPE_NONF_IPV4_TCP, ICE_FLTR_PTYPE_NONF_IPV4_SCTP, @@ -296,6 +308,7 @@ struct ice_hw_common_caps { bool pcie_reset_avoidance; /* Post update reset restriction */ bool reset_restrict_support; + bool tx_sched_topo_comp_mode_en; }; /* IEEE 1588 TIME_SYNC specific info */ @@ -321,12 +334,14 @@ enum ice_time_ref_freq { ICE_TIME_REF_FREQ_156_250 = 4, ICE_TIME_REF_FREQ_245_760 = 5, - NUM_ICE_TIME_REF_FREQ + NUM_ICE_TIME_REF_FREQ, + + ICE_TIME_REF_FREQ_INVALID = -1, }; /* Clock source specification */ enum ice_clk_src { - ICE_CLK_SRC_TCX0 = 0, /* Temperature compensated oscillator */ + ICE_CLK_SRC_TCXO = 0, /* Temperature compensated oscillator */ ICE_CLK_SRC_TIME_REF = 1, /* Use TIME_REF reference clock */ NUM_ICE_CLK_SRC @@ -355,6 +370,7 @@ struct ice_ts_func_info { #define ICE_TS_TMR1_ENA_M BIT(26) #define ICE_TS_LL_TX_TS_READ_M BIT(28) #define ICE_TS_LL_TX_TS_INT_READ_M BIT(29) +#define ICE_TS_LL_PHY_TMR_UPDATE_M BIT(30) struct ice_ts_dev_info { /* Device specific info */ @@ -369,6 +385,16 @@ struct ice_ts_dev_info { u8 tmr1_ena; u8 ts_ll_read; u8 ts_ll_int_read; + u8 ll_phy_tmr_update; +}; + +#define ICE_NAC_TOPO_PRIMARY_M BIT(0) +#define ICE_NAC_TOPO_DUAL_M BIT(1) +#define ICE_NAC_TOPO_ID_M GENMASK(0xF, 0) + +struct ice_nac_topology { + u32 mode; + u8 id; }; /* Function specific capabilities */ @@ -392,6 +418,7 @@ struct ice_hw_dev_caps { u32 num_flow_director_fltr; /* Number of FD filters available */ struct ice_ts_dev_info ts_dev_info; u32 num_funcs; + struct ice_nac_topology nac_topo; /* bitmap of supported sensors * bit 0 - internal temperature sensor * bit 31:1 - Reserved @@ -481,6 +508,8 @@ struct ice_bank_info { u32 orom_size; /* Size of OROM bank */ u32 netlist_ptr; /* Pointer to 1st Netlist bank */ u32 netlist_size; /* Size of Netlist bank */ + u32 active_css_hdr_len; /* Active CSS header length */ + u32 inactive_css_hdr_len; /* Inactive CSS header length */ enum ice_flash_bank nvm_bank; /* Active NVM bank */ enum ice_flash_bank orom_bank; /* Active OROM bank */ enum ice_flash_bank netlist_bank; /* Active Netlist bank */ @@ -667,7 +696,6 @@ struct ice_dcb_app_priority_table { #define ICE_MAX_USER_PRIORITY 8 #define ICE_DCBX_MAX_APPS 64 -#define ICE_DSCP_NUM_VAL 64 #define ICE_LLDPDU_SIZE 1500 #define ICE_TLV_STATUS_OPER 0x1 #define ICE_TLV_STATUS_SYNC 0x2 @@ -690,9 +718,9 @@ struct ice_dcbx_cfg { u8 pfc_mode; struct ice_dcb_app_priority_table app[ICE_DCBX_MAX_APPS]; /* when DSCP mapping defined by user set its bit to 1 */ - DECLARE_BITMAP(dscp_mapped, ICE_DSCP_NUM_VAL); + DECLARE_BITMAP(dscp_mapped, DSCP_MAX); /* array holding DSCP -> UP/TC values for DSCP L3 QoS mode */ - u8 dscp_map[ICE_DSCP_NUM_VAL]; + u8 dscp_map[DSCP_MAX]; u8 dcbx_mode; #define ICE_DCBX_MODE_CEE 0x1 #define ICE_DCBX_MODE_IEEE 0x2 @@ -715,6 +743,7 @@ struct ice_port_info { u16 sw_id; /* Initial switch ID belongs to port */ u16 pf_vf_num; u8 port_state; + u8 local_fwd_mode; #define ICE_SCHED_PORT_STATE_INIT 0x0 #define ICE_SCHED_PORT_STATE_READY 0x1 u8 lport; @@ -738,6 +767,8 @@ struct ice_switch_info { struct ice_sw_recipe *recp_list; u16 prof_res_bm_init; u16 max_used_prof_index; + u16 rule_cnt; + u8 recp_cnt; DECLARE_BITMAP(prof_res_bm[ICE_MAX_NUM_PROFILES], ICE_MAX_FV_WORDS); }; @@ -817,11 +848,41 @@ struct ice_mbx_data { u16 async_watermark_val; }; -/* PHY model */ -enum ice_phy_model { - ICE_PHY_UNSUP = -1, - ICE_PHY_E810 = 1, - ICE_PHY_E82X, +#define ICE_PORTS_PER_QUAD 4 +#define ICE_GET_QUAD_NUM(port) ((port) / ICE_PORTS_PER_QUAD) + +#define ATQBAL_FLAGS_INTR_IN_PROGRESS BIT(0) + +struct ice_e810_params { + /* The wait queue lock also protects the low latency interface */ + wait_queue_head_t atqbal_wq; + unsigned int atqbal_flags; +}; + +struct ice_eth56g_params { + u8 num_phys; + bool onestep_ena; + bool sfd_ena; + u32 peer_delay; +}; + +union ice_phy_params { + struct ice_e810_params e810; + struct ice_eth56g_params eth56g; +}; + +/* Global Link Topology */ +enum ice_global_link_topo { + ICE_LINK_TOPO_UP_TO_2_LINKS, + ICE_LINK_TOPO_UP_TO_4_LINKS, + ICE_LINK_TOPO_UP_TO_8_LINKS, + ICE_LINK_TOPO_RESERVED, +}; + +struct ice_ptp_hw { + union ice_phy_params phy; + u8 num_lports; + u8 ports_per_phy; }; /* Port hardware description */ @@ -845,10 +906,12 @@ struct ice_hw { u8 revision_id; u8 pf_id; /* device profile info */ - enum ice_phy_model phy_model; + u8 logical_pf_id; u16 max_burst_size; /* driver sets this value */ + u8 recp_reuse:1; /* indicates whether FW supports recipe reuse */ + /* Tx Scheduler values */ u8 num_tx_sched_layers; u8 num_tx_sched_phys_layers; @@ -906,12 +969,8 @@ struct ice_hw { /* INTRL granularity in 1 us */ u8 intrl_gran; -#define ICE_MAX_QUAD 2 -#define ICE_QUADS_PER_PHY_E82X 2 -#define ICE_PORTS_PER_PHY_E82X 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) + struct ice_ptp_hw ptp; + s8 lane_num; /* Active package version (currently active) */ struct ice_pkg_ver active_pkg_ver; @@ -1084,17 +1143,13 @@ struct ice_aq_get_set_rss_lut_params { #define ICE_SR_SECTOR_SIZE_IN_WORDS 0x800 /* CSS Header words */ +#define ICE_NVM_CSS_HDR_LEN_L 0x02 +#define ICE_NVM_CSS_HDR_LEN_H 0x03 #define ICE_NVM_CSS_SREV_L 0x14 #define ICE_NVM_CSS_SREV_H 0x15 -/* Length of CSS header section in words */ -#define ICE_CSS_HEADER_LENGTH 330 - -/* Offset of Shadow RAM copy in the NVM bank area. */ -#define ICE_NVM_SR_COPY_WORD_OFFSET roundup(ICE_CSS_HEADER_LENGTH, 32) - -/* Size in bytes of Option ROM trailer */ -#define ICE_NVM_OROM_TRAILER_LENGTH (2 * ICE_CSS_HEADER_LENGTH) +/* Length of Authentication header section in words */ +#define ICE_NVM_AUTH_HEADER_LEN 0x08 /* The Link Topology Netlist section is stored as a series of words. It is * stored in the NVM as a TLV, with the first two words containing the type @@ -1163,4 +1218,9 @@ struct ice_aq_get_set_rss_lut_params { #define ICE_FW_API_REPORT_DFLT_CFG_MIN 7 #define ICE_FW_API_REPORT_DFLT_CFG_PATCH 3 +/* AQ API version for Health Status support */ +#define ICE_FW_API_HEALTH_REPORT_MAJ 1 +#define ICE_FW_API_HEALTH_REPORT_MIN 7 +#define ICE_FW_API_HEALTH_REPORT_PATCH 6 + #endif /* _ICE_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index d10a4be965b5..48cd533e93b7 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -226,6 +226,7 @@ static void ice_vf_clear_counters(struct ice_vf *vf) vsi->num_vlan = 0; vf->num_mac = 0; + vf->num_mac_lldp = 0; memset(&vf->mdd_tx_events, 0, sizeof(vf->mdd_tx_events)); memset(&vf->mdd_rx_events, 0, sizeof(vf->mdd_rx_events)); } @@ -256,23 +257,21 @@ static void ice_vf_pre_vsi_rebuild(struct ice_vf *vf) * * It brings the VSI down and then reconfigures it with the hardware. */ -int ice_vf_reconfig_vsi(struct ice_vf *vf) +static int ice_vf_reconfig_vsi(struct ice_vf *vf) { struct ice_vsi *vsi = ice_get_vf_vsi(vf); - struct ice_vsi_cfg_params params = {}; struct ice_pf *pf = vf->pf; int err; if (WARN_ON(!vsi)) return -EINVAL; - params = ice_vsi_to_params(vsi); - params.flags = ICE_VSI_FLAG_NO_INIT; + vsi->flags = ICE_VSI_FLAG_NO_INIT; ice_vsi_decfg(vsi); ice_fltr_remove_all(vsi); - err = ice_vsi_cfg(vsi, ¶ms); + err = ice_vsi_cfg(vsi); if (err) { dev_err(ice_pf_to_dev(pf), "Failed to reconfigure the VF%u's VSI, error %d\n", @@ -337,6 +336,13 @@ static int ice_vf_rebuild_host_vlan_cfg(struct ice_vf *vf, struct ice_vsi *vsi) err = vlan_ops->add_vlan(vsi, &vf->port_vlan_info); } else { + /* clear possible previous port vlan config */ + err = ice_vsi_clear_port_vlan(vsi); + if (err) { + dev_err(dev, "failed to clear port VLAN via VSI parameters for VF %u, error %d\n", + vf->vf_id, err); + return err; + } err = ice_vsi_add_vlan_zero(vsi); } @@ -712,6 +718,23 @@ ice_vf_clear_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m) } /** + * ice_reset_vf_mbx_cnt - reset VF mailbox message count + * @vf: pointer to the VF structure + * + * This function clears the VF mailbox message count, and should be called on + * VF reset. + */ +static void ice_reset_vf_mbx_cnt(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + + if (ice_is_feature_supported(pf, ICE_F_MBX_LIMIT)) + ice_mbx_vf_clear_cnt_e830(&pf->hw, vf->vf_id); + else + ice_mbx_clear_malvf(&vf->mbx_info); +} + +/** * ice_reset_all_vfs - reset all allocated VFs in one go * @pf: pointer to the PF structure * @@ -737,7 +760,7 @@ void ice_reset_all_vfs(struct ice_pf *pf) /* clear all malicious info if the VFs are getting reset */ ice_for_each_vf(pf, bkt, vf) - ice_mbx_clear_malvf(&vf->mbx_info); + ice_reset_vf_mbx_cnt(vf); /* If VFs have been disabled, there is no need to reset */ if (test_and_set_bit(ICE_VF_DIS, pf->state)) { @@ -768,7 +791,7 @@ void ice_reset_all_vfs(struct ice_pf *pf) ice_for_each_vf(pf, bkt, vf) { mutex_lock(&vf->cfg_lock); - ice_eswitch_detach(pf, vf); + ice_eswitch_detach_vf(pf, vf); vf->driver_caps = 0; ice_vc_set_default_allowlist(vf); @@ -784,7 +807,7 @@ void ice_reset_all_vfs(struct ice_pf *pf) ice_vf_rebuild_vsi(vf); ice_vf_post_vsi_rebuild(vf); - ice_eswitch_attach(pf, vf); + ice_eswitch_attach_vf(pf, vf); mutex_unlock(&vf->cfg_lock); } @@ -950,10 +973,10 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) goto out_unlock; } - ice_eswitch_update_repr(vf->repr_id, vsi); + ice_eswitch_update_repr(&vf->repr_id, vsi); /* if the VF has been reset allow it to come up again */ - ice_mbx_clear_malvf(&vf->mbx_info); + ice_reset_vf_mbx_cnt(vf); out_unlock: if (lag && lag->bonded && lag->primary && @@ -992,10 +1015,13 @@ void ice_initialize_vf_entry(struct ice_vf *vf) /* assign default capabilities */ vf->spoofchk = true; - vf->num_vf_qs = vfs->num_qps_per; ice_vc_set_default_allowlist(vf); ice_virtchnl_set_dflt_ops(vf); + /* set default number of MSI-X */ + vf->num_msix = vfs->num_msix_per; + vf->num_vf_qs = vfs->num_qps_per; + /* ctrl_vsi_idx will be set to a valid value only when iAVF * creates its first fdir rule. */ @@ -1003,11 +1029,22 @@ void ice_initialize_vf_entry(struct ice_vf *vf) ice_vf_fdir_init(vf); /* Initialize mailbox info for this VF */ - ice_mbx_init_vf_info(&pf->hw, &vf->mbx_info); + if (ice_is_feature_supported(pf, ICE_F_MBX_LIMIT)) + ice_mbx_vf_clear_cnt_e830(&pf->hw, vf->vf_id); + else + ice_mbx_init_vf_info(&pf->hw, &vf->mbx_info); mutex_init(&vf->cfg_lock); } +void ice_deinitialize_vf_entry(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + + if (!ice_is_feature_supported(pf, ICE_F_MBX_LIMIT)) + list_del(&vf->mbx_info.list_entry); +} + /** * ice_dis_vf_qs - Disable the VF queues * @vf: pointer to the VF structure @@ -1240,7 +1277,7 @@ struct ice_vsi *ice_vf_ctrl_vsi_setup(struct ice_vf *vf) struct ice_vsi *vsi; params.type = ICE_VSI_CTRL; - params.pi = ice_vf_get_port_info(vf); + params.port_info = ice_vf_get_port_info(vf); params.vf = vf; params.flags = ICE_VSI_FLAG_INIT; @@ -1365,3 +1402,28 @@ struct ice_vsi *ice_get_vf_ctrl_vsi(struct ice_pf *pf, struct ice_vsi *vsi) rcu_read_unlock(); return ctrl_vsi; } + +/** + * ice_vf_update_mac_lldp_num - update the VF's number of LLDP addresses + * @vf: a VF to add the address to + * @vsi: the corresponding VSI + * @incr: is the rule added or removed + */ +void ice_vf_update_mac_lldp_num(struct ice_vf *vf, struct ice_vsi *vsi, + bool incr) +{ + bool lldp_by_fw = test_bit(ICE_FLAG_FW_LLDP_AGENT, vsi->back->flags); + bool was_ena = ice_vf_is_lldp_ena(vf) && !lldp_by_fw; + bool is_ena; + + if (WARN_ON(!vsi)) { + vf->num_mac_lldp = 0; + return; + } + + vf->num_mac_lldp += incr ? 1 : -1; + is_ena = ice_vf_is_lldp_ena(vf) && !lldp_by_fw; + + if (was_ena != is_ena) + ice_vsi_cfg_sw_lldp(vsi, false, is_ena); +} diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h index fec16919ec19..482f4285fd35 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -12,6 +12,7 @@ #include <net/devlink.h> #include <linux/avf/virtchnl.h> #include "ice_type.h" +#include "ice_flow.h" #include "ice_virtchnl_fdir.h" #include "ice_vsi_vlan_ops.h" @@ -52,6 +53,19 @@ struct ice_mdd_vf_events { u16 last_printed; }; +/* Structure to store fdir fv entry */ +struct ice_fdir_prof_info { + struct ice_parser_profile prof; + u64 fdir_active_cnt; +}; + +struct ice_vf_qs_bw { + u32 committed; + u32 peak; + u16 queue_id; + u8 tc; +}; + /* VF operations */ struct ice_vf_ops { enum ice_disq_rst_src reset_type; @@ -91,6 +105,7 @@ struct ice_vf { u16 lan_vsi_idx; /* index into PF struct */ u16 ctrl_vsi_idx; struct ice_vf_fdir fdir; + struct ice_fdir_prof_info fdir_prof_info[ICE_MAX_PTGS]; /* first vector index of this VF in the PF space */ int first_vector_idx; struct ice_sw *vf_sw_id; /* switch ID the VF VSIs connect to */ @@ -109,6 +124,10 @@ struct ice_vf { u8 spoofchk:1; u8 link_forced:1; u8 link_up:1; /* only valid if VF link is forced */ + u8 lldp_tx_ena:1; + + u32 ptp_caps; + unsigned int min_tx_rate; /* Minimum Tx bandwidth limit in Mbps */ unsigned int max_tx_rate; /* Maximum Tx bandwidth limit in Mbps */ DECLARE_BITMAP(vf_states, ICE_VF_STATES_NBITS); /* VF runtime states */ @@ -116,6 +135,7 @@ struct ice_vf { unsigned long vf_caps; /* VF's adv. capabilities */ u8 num_req_qs; /* num of queue pairs requested by VF */ u16 num_mac; + u16 num_mac_lldp; 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) @@ -131,7 +151,11 @@ struct ice_vf { /* devlink port data */ struct devlink_port devlink_port; + u16 lldp_recipe_id; + u16 lldp_rule_id; + u16 num_msix; /* num of MSI-X configured on this VF */ + struct ice_vf_qs_bw qs_bw[ICE_MAX_RSS_QS_PER_VF]; }; /* Flags for controlling behavior of ice_reset_vf */ @@ -161,6 +185,11 @@ static inline u16 ice_vf_get_port_vlan_tpid(struct ice_vf *vf) return vf->port_vlan_info.tpid; } +static inline bool ice_vf_is_lldp_ena(struct ice_vf *vf) +{ + return vf->num_mac_lldp && vf->trusted; +} + /* VF Hash Table access functions * * These functions provide abstraction for interacting with the VF hash table. @@ -226,6 +255,8 @@ ice_vf_clear_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m); int ice_reset_vf(struct ice_vf *vf, u32 flags); void ice_reset_all_vfs(struct ice_pf *pf); struct ice_vsi *ice_get_vf_ctrl_vsi(struct ice_pf *pf, struct ice_vsi *vsi); +void ice_vf_update_mac_lldp_num(struct ice_vf *vf, struct ice_vsi *vsi, + bool incr); #else /* CONFIG_PCI_IOV */ static inline struct ice_vf *ice_get_vf_by_id(struct ice_pf *pf, u16 vf_id) { 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 91ba7fe0eaee..5392b0404986 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h @@ -23,8 +23,8 @@ #warning "Only include ice_vf_lib_private.h in CONFIG_PCI_IOV virtualization files" #endif -int ice_vf_reconfig_vsi(struct ice_vf *vf); void ice_initialize_vf_entry(struct ice_vf *vf); +void ice_deinitialize_vf_entry(struct ice_vf *vf); void ice_dis_vf_qs(struct ice_vf *vf); int ice_check_vf_init(struct ice_vf *vf); enum virtchnl_status_code ice_err_to_virt_err(int err); diff --git a/drivers/net/ethernet/intel/ice/ice_vf_mbx.c b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c index 40cb4ba0789c..75c8113e58ee 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_mbx.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c @@ -211,6 +211,38 @@ ice_mbx_detect_malvf(struct ice_hw *hw, struct ice_mbx_vf_info *vf_info, } /** + * ice_mbx_vf_dec_trig_e830 - Decrements the VF mailbox queue counter + * @hw: pointer to the HW struct + * @event: pointer to the control queue receive event + * + * This function triggers to decrement the counter + * MBX_VF_IN_FLIGHT_MSGS_AT_PF_CNT when the driver replenishes + * the buffers at the PF mailbox queue. + */ +void ice_mbx_vf_dec_trig_e830(const struct ice_hw *hw, + const struct ice_rq_event_info *event) +{ + u16 vfid = le16_to_cpu(event->desc.retval); + + wr32(hw, E830_MBX_VF_DEC_TRIG(vfid), 1); +} + +/** + * ice_mbx_vf_clear_cnt_e830 - Clear the VF mailbox queue count + * @hw: pointer to the HW struct + * @vf_id: VF ID in the PF space + * + * This function clears the counter MBX_VF_IN_FLIGHT_MSGS_AT_PF_CNT, and should + * be called when a VF is created and on VF reset. + */ +void ice_mbx_vf_clear_cnt_e830(const struct ice_hw *hw, u16 vf_id) +{ + u32 reg = rd32(hw, E830_MBX_VF_IN_FLIGHT_MSGS_AT_PF_CNT(vf_id)); + + wr32(hw, E830_MBX_VF_DEC_TRIG(vf_id), reg); +} + +/** * ice_mbx_vf_state_handler - Handle states of the overflow algorithm * @hw: pointer to the HW struct * @mbx_data: pointer to structure containing mailbox data diff --git a/drivers/net/ethernet/intel/ice/ice_vf_mbx.h b/drivers/net/ethernet/intel/ice/ice_vf_mbx.h index 44bc030d17e0..684de89e5c5e 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_mbx.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_mbx.h @@ -19,6 +19,9 @@ ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen, struct ice_sq_cd *cd); u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed); +void ice_mbx_vf_dec_trig_e830(const struct ice_hw *hw, + const struct ice_rq_event_info *event); +void ice_mbx_vf_clear_cnt_e830(const struct ice_hw *hw, u16 vf_id); int ice_mbx_vf_state_handler(struct ice_hw *hw, struct ice_mbx_data *mbx_data, struct ice_mbx_vf_info *vf_info, bool *report_malvf); @@ -47,5 +50,11 @@ static inline void ice_mbx_init_snapshot(struct ice_hw *hw) { } +static inline void +ice_mbx_vf_dec_trig_e830(const struct ice_hw *hw, + const struct ice_rq_event_info *event) +{ +} + #endif /* CONFIG_PCI_IOV */ #endif /* _ICE_VF_MBX_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 1ff9818b4c84..eeeb9968e477 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -461,6 +461,10 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_FDIR_PF) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_FDIR_PF; + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_TC_U32 && + vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_FDIR_PF) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_TC_U32; + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2; @@ -491,6 +495,12 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_USO) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_USO; + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_QOS) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_QOS; + + if (vf->driver_caps & VIRTCHNL_VF_CAP_PTP) + vfres->vf_cap_flags |= VIRTCHNL_VF_CAP_PTP; + vfres->num_vsis = 1; /* Tx and Rx queue are equal for VF */ vfres->num_queue_pairs = vsi->num_txq; @@ -555,7 +565,7 @@ bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id) * * check for the valid queue ID */ -static bool ice_vc_isvalid_q_id(struct ice_vsi *vsi, u8 qid) +static bool ice_vc_isvalid_q_id(struct ice_vsi *vsi, u16 qid) { /* allocated Tx and Rx queues should be always equal for VF VSI */ return qid < vsi->alloc_txq; @@ -1031,6 +1041,191 @@ error_param: } /** + * ice_vc_get_qos_caps - Get current QoS caps from PF + * @vf: pointer to the VF info + * + * Get VF's QoS capabilities, such as TC number, arbiter and + * bandwidth from PF. + * + * Return: 0 on success or negative error value. + */ +static int ice_vc_get_qos_caps(struct ice_vf *vf) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_qos_cap_list *cap_list = NULL; + u8 tc_prio[ICE_MAX_TRAFFIC_CLASS] = { 0 }; + struct virtchnl_qos_cap_elem *cfg = NULL; + struct ice_vsi_ctx *vsi_ctx; + struct ice_pf *pf = vf->pf; + struct ice_port_info *pi; + struct ice_vsi *vsi; + u8 numtc, tc; + u16 len = 0; + int ret, i; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + + pi = pf->hw.port_info; + numtc = vsi->tc_cfg.numtc; + + vsi_ctx = ice_get_vsi_ctx(pi->hw, vf->lan_vsi_idx); + if (!vsi_ctx) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + + len = struct_size(cap_list, cap, numtc); + cap_list = kzalloc(len, GFP_KERNEL); + if (!cap_list) { + v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + len = 0; + goto err; + } + + cap_list->vsi_id = vsi->vsi_num; + cap_list->num_elem = numtc; + + /* Store the UP2TC configuration from DCB to a user priority bitmap + * of each TC. Each element of prio_of_tc represents one TC. Each + * bitmap indicates the user priorities belong to this TC. + */ + for (i = 0; i < ICE_MAX_USER_PRIORITY; i++) { + tc = pi->qos_cfg.local_dcbx_cfg.etscfg.prio_table[i]; + tc_prio[tc] |= BIT(i); + } + + for (i = 0; i < numtc; i++) { + cfg = &cap_list->cap[i]; + cfg->tc_num = i; + cfg->tc_prio = tc_prio[i]; + cfg->arbiter = pi->qos_cfg.local_dcbx_cfg.etscfg.tsatable[i]; + cfg->weight = VIRTCHNL_STRICT_WEIGHT; + cfg->type = VIRTCHNL_BW_SHAPER; + cfg->shaper.committed = vsi_ctx->sched.bw_t_info[i].cir_bw.bw; + cfg->shaper.peak = vsi_ctx->sched.bw_t_info[i].eir_bw.bw; + } + +err: + ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_QOS_CAPS, v_ret, + (u8 *)cap_list, len); + kfree(cap_list); + return ret; +} + +/** + * ice_vf_cfg_qs_bw - Configure per queue bandwidth + * @vf: pointer to the VF info + * @num_queues: number of queues to be configured + * + * Configure per queue bandwidth. + * + * Return: 0 on success or negative error value. + */ +static int ice_vf_cfg_qs_bw(struct ice_vf *vf, u16 num_queues) +{ + struct ice_hw *hw = &vf->pf->hw; + struct ice_vsi *vsi; + int ret; + u16 i; + + vsi = ice_get_vf_vsi(vf); + if (!vsi) + return -EINVAL; + + for (i = 0; i < num_queues; i++) { + u32 p_rate, min_rate; + u8 tc; + + p_rate = vf->qs_bw[i].peak; + min_rate = vf->qs_bw[i].committed; + tc = vf->qs_bw[i].tc; + if (p_rate) + ret = ice_cfg_q_bw_lmt(hw->port_info, vsi->idx, tc, + vf->qs_bw[i].queue_id, + ICE_MAX_BW, p_rate); + else + ret = ice_cfg_q_bw_dflt_lmt(hw->port_info, vsi->idx, tc, + vf->qs_bw[i].queue_id, + ICE_MAX_BW); + if (ret) + return ret; + + if (min_rate) + ret = ice_cfg_q_bw_lmt(hw->port_info, vsi->idx, tc, + vf->qs_bw[i].queue_id, + ICE_MIN_BW, min_rate); + else + ret = ice_cfg_q_bw_dflt_lmt(hw->port_info, vsi->idx, tc, + vf->qs_bw[i].queue_id, + ICE_MIN_BW); + + if (ret) + return ret; + } + + return 0; +} + +/** + * ice_vf_cfg_q_quanta_profile - Configure quanta profile + * @vf: pointer to the VF info + * @quanta_prof_idx: pointer to the quanta profile index + * @quanta_size: quanta size to be set + * + * This function chooses available quanta profile and configures the register. + * The quanta profile is evenly divided by the number of device ports, and then + * available to the specific PF and VFs. The first profile for each PF is a + * reserved default profile. Only quanta size of the rest unused profile can be + * modified. + * + * Return: 0 on success or negative error value. + */ +static int ice_vf_cfg_q_quanta_profile(struct ice_vf *vf, u16 quanta_size, + u16 *quanta_prof_idx) +{ + const u16 n_desc = calc_quanta_desc(quanta_size); + struct ice_hw *hw = &vf->pf->hw; + const u16 n_cmd = 2 * n_desc; + struct ice_pf *pf = vf->pf; + u16 per_pf, begin_id; + u8 n_used; + u32 reg; + + begin_id = (GLCOMM_QUANTA_PROF_MAX_INDEX + 1) / hw->dev_caps.num_funcs * + hw->logical_pf_id; + + if (quanta_size == ICE_DFLT_QUANTA) { + *quanta_prof_idx = begin_id; + } else { + per_pf = (GLCOMM_QUANTA_PROF_MAX_INDEX + 1) / + hw->dev_caps.num_funcs; + n_used = pf->num_quanta_prof_used; + if (n_used < per_pf) { + *quanta_prof_idx = begin_id + 1 + n_used; + pf->num_quanta_prof_used++; + } else { + return -EINVAL; + } + } + + reg = FIELD_PREP(GLCOMM_QUANTA_PROF_QUANTA_SIZE_M, quanta_size) | + FIELD_PREP(GLCOMM_QUANTA_PROF_MAX_CMD_M, n_cmd) | + FIELD_PREP(GLCOMM_QUANTA_PROF_MAX_DESC_M, n_desc); + wr32(hw, GLCOMM_QUANTA_PROF(*quanta_prof_idx), reg); + + return 0; +} + +/** * ice_vc_cfg_promiscuous_mode_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -1505,13 +1700,12 @@ error_param: * ice_cfg_interrupt * @vf: pointer to the VF info * @vsi: the VSI being configured - * @vector_id: vector ID * @map: vector map for mapping vectors to queues * @q_vector: structure for interrupt vector * configure the IRQ to queue map */ -static int -ice_cfg_interrupt(struct ice_vf *vf, struct ice_vsi *vsi, u16 vector_id, +static enum virtchnl_status_code +ice_cfg_interrupt(struct ice_vf *vf, struct ice_vsi *vsi, struct virtchnl_vector_map *map, struct ice_q_vector *q_vector) { @@ -1531,7 +1725,8 @@ ice_cfg_interrupt(struct ice_vf *vf, struct ice_vsi *vsi, u16 vector_id, q_vector->num_ring_rx++; q_vector->rx.itr_idx = map->rxitr_idx; vsi->rx_rings[vsi_q_id]->q_vector = q_vector; - ice_cfg_rxq_interrupt(vsi, vsi_q_id, vector_id, + ice_cfg_rxq_interrupt(vsi, vsi_q_id, + q_vector->vf_reg_idx, q_vector->rx.itr_idx); } @@ -1545,7 +1740,8 @@ ice_cfg_interrupt(struct ice_vf *vf, struct ice_vsi *vsi, u16 vector_id, q_vector->num_ring_tx++; q_vector->tx.itr_idx = map->txitr_idx; vsi->tx_rings[vsi_q_id]->q_vector = q_vector; - ice_cfg_txq_interrupt(vsi, vsi_q_id, vector_id, + ice_cfg_txq_interrupt(vsi, vsi_q_id, + q_vector->vf_reg_idx, q_vector->tx.itr_idx); } @@ -1619,8 +1815,7 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg) } /* lookout for the invalid queue index */ - v_ret = (enum virtchnl_status_code) - ice_cfg_interrupt(vf, vsi, vector_id, map, q_vector); + v_ret = ice_cfg_interrupt(vf, vsi, map, q_vector); if (v_ret) goto error_param; } @@ -1632,6 +1827,164 @@ error_param: } /** + * ice_vc_cfg_q_bw - Configure per queue bandwidth + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer which holds the command descriptor + * + * Configure VF queues bandwidth. + * + * Return: 0 on success or negative error value. + */ +static int ice_vc_cfg_q_bw(struct ice_vf *vf, u8 *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_queues_bw_cfg *qbw = + (struct virtchnl_queues_bw_cfg *)msg; + struct ice_vsi *vsi; + u16 i; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) || + !ice_vc_isvalid_vsi_id(vf, qbw->vsi_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + + if (qbw->num_queues > ICE_MAX_RSS_QS_PER_VF || + qbw->num_queues > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) { + dev_err(ice_pf_to_dev(vf->pf), "VF-%d trying to configure more than allocated number of queues: %d\n", + vf->vf_id, min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + + for (i = 0; i < qbw->num_queues; i++) { + if (qbw->cfg[i].shaper.peak != 0 && vf->max_tx_rate != 0 && + qbw->cfg[i].shaper.peak > vf->max_tx_rate) { + dev_warn(ice_pf_to_dev(vf->pf), "The maximum queue %d rate limit configuration may not take effect because the maximum TX rate for VF-%d is %d\n", + qbw->cfg[i].queue_id, vf->vf_id, + vf->max_tx_rate); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + if (qbw->cfg[i].shaper.committed != 0 && vf->min_tx_rate != 0 && + qbw->cfg[i].shaper.committed < vf->min_tx_rate) { + dev_warn(ice_pf_to_dev(vf->pf), "The minimum queue %d rate limit configuration may not take effect because the minimum TX rate for VF-%d is %d\n", + qbw->cfg[i].queue_id, vf->vf_id, + vf->min_tx_rate); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + if (qbw->cfg[i].queue_id > vf->num_vf_qs) { + dev_warn(ice_pf_to_dev(vf->pf), "VF-%d trying to configure invalid queue_id\n", + vf->vf_id); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + if (qbw->cfg[i].tc >= ICE_MAX_TRAFFIC_CLASS) { + dev_warn(ice_pf_to_dev(vf->pf), "VF-%d trying to configure a traffic class higher than allowed\n", + vf->vf_id); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + } + + for (i = 0; i < qbw->num_queues; i++) { + vf->qs_bw[i].queue_id = qbw->cfg[i].queue_id; + vf->qs_bw[i].peak = qbw->cfg[i].shaper.peak; + vf->qs_bw[i].committed = qbw->cfg[i].shaper.committed; + vf->qs_bw[i].tc = qbw->cfg[i].tc; + } + + if (ice_vf_cfg_qs_bw(vf, qbw->num_queues)) + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + +err: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_QUEUE_BW, + v_ret, NULL, 0); +} + +/** + * ice_vc_cfg_q_quanta - Configure per queue quanta + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer which holds the command descriptor + * + * Configure VF queues quanta. + * + * Return: 0 on success or negative error value. + */ +static int ice_vc_cfg_q_quanta(struct ice_vf *vf, u8 *msg) +{ + u16 quanta_prof_id, quanta_size, start_qid, num_queues, end_qid, i; + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_quanta_cfg *qquanta = + (struct virtchnl_quanta_cfg *)msg; + struct ice_vsi *vsi; + int ret; + + start_qid = qquanta->queue_select.start_queue_id; + num_queues = qquanta->queue_select.num_queues; + + if (check_add_overflow(start_qid, num_queues, &end_qid)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + + if (end_qid > ICE_MAX_RSS_QS_PER_VF || + end_qid > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) { + dev_err(ice_pf_to_dev(vf->pf), "VF-%d trying to configure more than allocated number of queues: %d\n", + vf->vf_id, min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + + quanta_size = qquanta->quanta_size; + if (quanta_size > ICE_MAX_QUANTA_SIZE || + quanta_size < ICE_MIN_QUANTA_SIZE) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + + if (quanta_size % 64) { + dev_err(ice_pf_to_dev(vf->pf), "quanta size should be the product of 64\n"); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + + ret = ice_vf_cfg_q_quanta_profile(vf, quanta_size, + &quanta_prof_id); + if (ret) { + v_ret = VIRTCHNL_STATUS_ERR_NOT_SUPPORTED; + goto err; + } + + for (i = start_qid; i < end_qid; i++) + vsi->tx_rings[i]->quanta_prof_id = quanta_prof_id; + +err: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_QUANTA, + v_ret, NULL, 0); +} + +/** * ice_vc_cfg_qs_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -1648,6 +2001,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) struct ice_vsi *vsi; u8 act_prt, pri_prt; int i = -1, q_idx; + bool ena_ts; lag = pf->lag; mutex_lock(&pf->lag_mutex); @@ -1711,8 +2065,8 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) /* copy Tx queue info from VF into VSI */ if (qpi->txq.ring_len > 0) { - vsi->tx_rings[i]->dma = qpi->txq.dma_ring_addr; - vsi->tx_rings[i]->count = qpi->txq.ring_len; + vsi->tx_rings[q_idx]->dma = qpi->txq.dma_ring_addr; + vsi->tx_rings[q_idx]->count = qpi->txq.ring_len; /* Disable any existing queue first */ if (ice_vf_vsi_dis_single_txq(vf, vsi, q_idx)) @@ -1721,7 +2075,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) /* Configure a queue with the requested settings */ if (ice_vsi_cfg_single_txq(vsi, vsi->tx_rings, q_idx)) { dev_warn(ice_pf_to_dev(pf), "VF-%d failed to configure TX queue %d\n", - vf->vf_id, i); + vf->vf_id, q_idx); goto error_param; } } @@ -1729,39 +2083,37 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) /* copy Rx queue info from VF into VSI */ if (qpi->rxq.ring_len > 0) { u16 max_frame_size = ice_vc_get_max_frame_size(vf); + struct ice_rx_ring *ring = vsi->rx_rings[q_idx]; u32 rxdid; - vsi->rx_rings[i]->dma = qpi->rxq.dma_ring_addr; - vsi->rx_rings[i]->count = qpi->rxq.ring_len; + ring->dma = qpi->rxq.dma_ring_addr; + ring->count = qpi->rxq.ring_len; if (qpi->rxq.crc_disable) - vsi->rx_rings[q_idx]->flags |= - ICE_RX_FLAGS_CRC_STRIP_DIS; + ring->flags |= ICE_RX_FLAGS_CRC_STRIP_DIS; else - vsi->rx_rings[q_idx]->flags &= - ~ICE_RX_FLAGS_CRC_STRIP_DIS; + ring->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)) goto error_param; - vsi->rx_buf_len = qpi->rxq.databuffer_size; - vsi->rx_rings[i]->rx_buf_len = vsi->rx_buf_len; + ring->rx_buf_len = qpi->rxq.databuffer_size; if (qpi->rxq.max_pkt_size > max_frame_size || qpi->rxq.max_pkt_size < 64) goto error_param; - vsi->max_frame = qpi->rxq.max_pkt_size; + ring->max_frame = qpi->rxq.max_pkt_size; /* add space for the port VLAN since the VF driver is * not expected to account for it in the MTU * calculation */ if (ice_vf_is_port_vlan_ena(vf)) - vsi->max_frame += VLAN_HLEN; + ring->max_frame += VLAN_HLEN; if (ice_vsi_cfg_single_rxq(vsi, q_idx)) { dev_warn(ice_pf_to_dev(pf), "VF-%d failed to configure RX queue %d\n", - vf->vf_id, i); + vf->vf_id, q_idx); goto error_param; } @@ -1779,9 +2131,14 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) rxdid = ICE_RXDID_LEGACY_1; } + ena_ts = ((vf->driver_caps & + VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) && + (vf->driver_caps & VIRTCHNL_VF_CAP_PTP) && + (qpi->rxq.flags & VIRTCHNL_PTP_RX_TSTAMP)); + ice_write_qrxflxp_cntxt(&vsi->back->hw, - vsi->rxq_map[q_idx], - rxdid, 0x03, false); + vsi->rxq_map[q_idx], rxdid, + ICE_RXDID_PRIO, ena_ts); } } @@ -1909,6 +2266,51 @@ ice_vfhw_mac_add(struct ice_vf *vf, struct virtchnl_ether_addr *vc_ether_addr) } /** + * ice_is_mc_lldp_eth_addr - check if the given MAC is a multicast LLDP address + * @mac: address to check + * + * Return: true if the address is one of the three possible LLDP multicast + * addresses, false otherwise. + */ +static bool ice_is_mc_lldp_eth_addr(const u8 *mac) +{ + const u8 lldp_mac_base[] = {0x01, 0x80, 0xc2, 0x00, 0x00}; + + if (memcmp(mac, lldp_mac_base, sizeof(lldp_mac_base))) + return false; + + return (mac[5] == 0x0e || mac[5] == 0x03 || mac[5] == 0x00); +} + +/** + * ice_vc_can_add_mac - check if the VF is allowed to add a given MAC + * @vf: a VF to add the address to + * @mac: address to check + * + * Return: true if the VF is allowed to add such MAC address, false otherwise. + */ +static bool ice_vc_can_add_mac(const struct ice_vf *vf, const u8 *mac) +{ + struct device *dev = ice_pf_to_dev(vf->pf); + + if (is_unicast_ether_addr(mac) && + !ice_can_vf_change_mac((struct ice_vf *)vf)) { + dev_err(dev, + "VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n"); + return false; + } + + if (!vf->trusted && ice_is_mc_lldp_eth_addr(mac)) { + dev_warn(dev, + "An untrusted VF %u is attempting to configure an LLDP multicast address\n", + vf->vf_id); + return false; + } + + return true; +} + +/** * ice_vc_add_mac_addr - attempt to add the MAC address passed in * @vf: pointer to the VF info * @vsi: pointer to the VF's VSI @@ -1926,10 +2328,8 @@ ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, if (ether_addr_equal(mac_addr, vf->dev_lan_addr)) return 0; - if (is_unicast_ether_addr(mac_addr) && !ice_can_vf_change_mac(vf)) { - dev_err(dev, "VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n"); + if (!ice_vc_can_add_mac(vf, mac_addr)) return -EPERM; - } ret = ice_fltr_add_mac(vsi, mac_addr, ICE_FWD_TO_VSI); if (ret == -EEXIST) { @@ -1944,6 +2344,8 @@ ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, return ret; } else { vf->num_mac++; + if (ice_is_mc_lldp_eth_addr(mac_addr)) + ice_vf_update_mac_lldp_num(vf, vsi, true); } ice_vfhw_mac_add(vf, vc_ether_addr); @@ -2038,6 +2440,8 @@ ice_vc_del_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, ice_vfhw_mac_del(vf, vc_ether_addr); vf->num_mac--; + if (ice_is_mc_lldp_eth_addr(mac_addr)) + ice_vf_update_mac_lldp_num(vf, vsi, false); return 0; } @@ -2229,17 +2633,27 @@ static bool ice_is_vlan_promisc_allowed(struct ice_vf *vf) /** * ice_vf_ena_vlan_promisc - Enable Tx/Rx VLAN promiscuous for the VLAN + * @vf: VF to enable VLAN promisc on * @vsi: VF's VSI used to enable VLAN promiscuous mode * @vlan: VLAN used to enable VLAN promiscuous * * This function should only be called if VLAN promiscuous mode is allowed, * which can be determined via ice_is_vlan_promisc_allowed(). */ -static int ice_vf_ena_vlan_promisc(struct ice_vsi *vsi, struct ice_vlan *vlan) +static int ice_vf_ena_vlan_promisc(struct ice_vf *vf, struct ice_vsi *vsi, + struct ice_vlan *vlan) { - u8 promisc_m = ICE_PROMISC_VLAN_TX | ICE_PROMISC_VLAN_RX; + u8 promisc_m = 0; int status; + if (test_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states)) + promisc_m |= ICE_UCAST_VLAN_PROMISC_BITS; + if (test_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states)) + promisc_m |= ICE_MCAST_VLAN_PROMISC_BITS; + + if (!promisc_m) + return 0; + status = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, vlan->vid); if (status && status != -EEXIST) @@ -2258,7 +2672,7 @@ static int ice_vf_ena_vlan_promisc(struct ice_vsi *vsi, struct ice_vlan *vlan) */ static int ice_vf_dis_vlan_promisc(struct ice_vsi *vsi, struct ice_vlan *vlan) { - u8 promisc_m = ICE_PROMISC_VLAN_TX | ICE_PROMISC_VLAN_RX; + u8 promisc_m = ICE_UCAST_VLAN_PROMISC_BITS | ICE_MCAST_VLAN_PROMISC_BITS; int status; status = ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, @@ -2413,7 +2827,7 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) goto error_param; } } else if (vlan_promisc) { - status = ice_vf_ena_vlan_promisc(vsi, &vlan); + status = ice_vf_ena_vlan_promisc(vf, vsi, &vlan); if (status) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; dev_err(dev, "Enable Unicast/multicast promiscuous mode on VLAN ID:%d failed error-%d\n", @@ -2696,12 +3110,8 @@ err: static int ice_vc_query_rxdid(struct ice_vf *vf) { enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - struct virtchnl_supported_rxdids *rxdid = NULL; - struct ice_hw *hw = &vf->pf->hw; struct ice_pf *pf = vf->pf; - int len = 0; - int ret, i; - u32 regval; + u64 rxdid; if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; @@ -2713,35 +3123,11 @@ static int ice_vc_query_rxdid(struct ice_vf *vf) goto err; } - len = sizeof(struct virtchnl_supported_rxdids); - rxdid = kzalloc(len, GFP_KERNEL); - if (!rxdid) { - v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; - len = 0; - goto err; - } - - /* 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. - */ - 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) - rxdid->supported_rxdids |= BIT(i); - } - - pf->supported_rxdids = rxdid->supported_rxdids; + rxdid = pf->supported_rxdids; err: - ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_SUPPORTED_RXDIDS, - v_ret, (u8 *)rxdid, len); - kfree(rxdid); - return ret; + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_SUPPORTED_RXDIDS, + v_ret, (u8 *)&rxdid, sizeof(rxdid)); } /** @@ -3250,7 +3636,7 @@ ice_vc_add_vlans(struct ice_vf *vf, struct ice_vsi *vsi, return err; if (vlan_promisc) { - err = ice_vf_ena_vlan_promisc(vsi, &vlan); + err = ice_vf_ena_vlan_promisc(vf, vsi, &vlan); if (err) return err; } @@ -3278,7 +3664,8 @@ ice_vc_add_vlans(struct ice_vf *vf, struct ice_vsi *vsi, */ if (!ice_is_dvm_ena(&vsi->back->hw)) { if (vlan_promisc) { - err = ice_vf_ena_vlan_promisc(vsi, &vlan); + err = ice_vf_ena_vlan_promisc(vf, vsi, + &vlan); if (err) return err; } @@ -3784,6 +4171,59 @@ out: v_ret, NULL, 0); } +static int ice_vc_get_ptp_cap(struct ice_vf *vf, + const struct virtchnl_ptp_caps *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_ERR_PARAM; + u32 caps = VIRTCHNL_1588_PTP_CAP_RX_TSTAMP | + VIRTCHNL_1588_PTP_CAP_READ_PHC; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + goto err; + + v_ret = VIRTCHNL_STATUS_SUCCESS; + + if (msg->caps & caps) + vf->ptp_caps = caps; + +err: + /* send the response back to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_1588_PTP_GET_CAPS, v_ret, + (u8 *)&vf->ptp_caps, + sizeof(struct virtchnl_ptp_caps)); +} + +static int ice_vc_get_phc_time(struct ice_vf *vf) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_ERR_PARAM; + struct virtchnl_phc_time *phc_time = NULL; + struct ice_pf *pf = vf->pf; + u32 len = 0; + int ret; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + goto err; + + v_ret = VIRTCHNL_STATUS_SUCCESS; + + phc_time = kzalloc(sizeof(*phc_time), GFP_KERNEL); + if (!phc_time) { + v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + goto err; + } + + len = sizeof(*phc_time); + + phc_time->time = ice_ptp_read_src_clk_reg(pf, NULL); + +err: + /* send the response back to the VF */ + ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_1588_PTP_GET_TIME, v_ret, + (u8 *)phc_time, len); + kfree(phc_time); + return ret; +} + static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = { .get_ver_msg = ice_vc_get_ver_msg, .get_vf_res_msg = ice_vc_get_vf_res_msg, @@ -3817,6 +4257,14 @@ static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = { .dis_vlan_stripping_v2_msg = ice_vc_dis_vlan_stripping_v2_msg, .ena_vlan_insertion_v2_msg = ice_vc_ena_vlan_insertion_v2_msg, .dis_vlan_insertion_v2_msg = ice_vc_dis_vlan_insertion_v2_msg, + .get_qos_caps = ice_vc_get_qos_caps, + .cfg_q_bw = ice_vc_cfg_q_bw, + .cfg_q_quanta = ice_vc_cfg_q_quanta, + .get_ptp_cap = ice_vc_get_ptp_cap, + .get_phc_time = ice_vc_get_phc_time, + /* If you add a new op here please make sure to add it to + * ice_virtchnl_repr_ops as well. + */ }; /** @@ -3874,7 +4322,6 @@ static int ice_vc_repr_add_mac(struct ice_vf *vf, u8 *msg) } ice_vfhw_mac_add(vf, &al->list[i]); - vf->num_mac++; break; } @@ -3947,6 +4394,11 @@ static const struct ice_virtchnl_ops ice_virtchnl_repr_ops = { .dis_vlan_stripping_v2_msg = ice_vc_dis_vlan_stripping_v2_msg, .ena_vlan_insertion_v2_msg = ice_vc_ena_vlan_insertion_v2_msg, .dis_vlan_insertion_v2_msg = ice_vc_dis_vlan_insertion_v2_msg, + .get_qos_caps = ice_vc_get_qos_caps, + .cfg_q_bw = ice_vc_cfg_q_bw, + .cfg_q_quanta = ice_vc_cfg_q_quanta, + .get_ptp_cap = ice_vc_get_ptp_cap, + .get_phc_time = ice_vc_get_phc_time, }; /** @@ -4005,8 +4457,10 @@ ice_is_malicious_vf(struct ice_vf *vf, struct ice_mbx_data *mbxdata) * @event: pointer to the AQ event * @mbxdata: information used to detect VF attempting mailbox overflow * - * called from the common asq/arq handler to - * process request from VF + * Called from the common asq/arq handler to process request from VF. When this + * flow is used for devices with hardware VF to PF message queue overflow + * support (ICE_F_MBX_LIMIT) mbxdata is set to NULL and ice_is_malicious_vf + * check is skipped. */ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event, struct ice_mbx_data *mbxdata) @@ -4032,7 +4486,7 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event, mutex_lock(&vf->cfg_lock); /* Check if the VF is trying to overflow the mailbox */ - if (ice_is_malicious_vf(vf, mbxdata)) + if (mbxdata && ice_is_malicious_vf(vf, mbxdata)) goto finish; /* Check if VF is disabled. */ @@ -4173,6 +4627,21 @@ error_handler: case VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2: err = ops->dis_vlan_insertion_v2_msg(vf, msg); break; + case VIRTCHNL_OP_GET_QOS_CAPS: + err = ops->get_qos_caps(vf); + break; + case VIRTCHNL_OP_CONFIG_QUEUE_BW: + err = ops->cfg_q_bw(vf, msg); + break; + case VIRTCHNL_OP_CONFIG_QUANTA: + err = ops->cfg_q_quanta(vf, msg); + break; + case VIRTCHNL_OP_1588_PTP_GET_CAPS: + err = ops->get_ptp_cap(vf, (const void *)msg); + break; + case VIRTCHNL_OP_1588_PTP_GET_TIME: + err = ops->get_phc_time(vf); + break; case VIRTCHNL_OP_UNKNOWN: default: dev_err(dev, "Unsupported opcode %d from VF %d\n", v_opcode, diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.h b/drivers/net/ethernet/intel/ice/ice_virtchnl.h index 3a4115869153..222990f229d5 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.h @@ -13,12 +13,22 @@ /* Restrict number of MAC Addr and VLAN that non-trusted VF can programmed */ #define ICE_MAX_VLAN_PER_VF 8 +#define ICE_DFLT_QUANTA 1024 +#define ICE_MAX_QUANTA_SIZE 4096 +#define ICE_MIN_QUANTA_SIZE 256 + +#define calc_quanta_desc(x) \ + max_t(u16, 12, min_t(u16, 63, (((x) + 66) / 132) * 2 + 4)) + /* MAC filters: 1 is reserved for the VF's default/perm_addr/LAA MAC, 1 for * broadcast, and 16 for additional unicast/multicast filters */ #define ICE_MAX_MACADDR_PER_VF 18 #define ICE_FLEX_DESC_RXDID_MAX_NUM 64 +/* Priority to be compared against previous priority from the pipe */ +#define ICE_RXDID_PRIO 0x03 + /* VFs only get a single VSI. For ice hardware, the VF does not need to know * its VSI index. However, the virtchnl interface requires a VSI number, * mainly due to legacy hardware. @@ -61,6 +71,13 @@ struct ice_virtchnl_ops { int (*dis_vlan_stripping_v2_msg)(struct ice_vf *vf, u8 *msg); int (*ena_vlan_insertion_v2_msg)(struct ice_vf *vf, u8 *msg); int (*dis_vlan_insertion_v2_msg)(struct ice_vf *vf, u8 *msg); + int (*get_qos_caps)(struct ice_vf *vf); + int (*cfg_q_tc_map)(struct ice_vf *vf, u8 *msg); + int (*cfg_q_bw)(struct ice_vf *vf, u8 *msg); + int (*cfg_q_quanta)(struct ice_vf *vf, u8 *msg); + int (*get_ptp_cap)(struct ice_vf *vf, + const struct virtchnl_ptp_caps *msg); + int (*get_phc_time)(struct ice_vf *vf); }; #ifdef CONFIG_PCI_IOV diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c index d796dbd2a440..a3d1579a619a 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c @@ -84,6 +84,17 @@ static const u32 fdir_pf_allowlist_opcodes[] = { VIRTCHNL_OP_ADD_FDIR_FILTER, VIRTCHNL_OP_DEL_FDIR_FILTER, }; +/* VIRTCHNL_VF_CAP_PTP */ +static const u32 ptp_allowlist_opcodes[] = { + VIRTCHNL_OP_1588_PTP_GET_CAPS, + VIRTCHNL_OP_1588_PTP_GET_TIME, +}; + +static const u32 tc_allowlist_opcodes[] = { + VIRTCHNL_OP_GET_QOS_CAPS, VIRTCHNL_OP_CONFIG_QUEUE_BW, + VIRTCHNL_OP_CONFIG_QUANTA, +}; + struct allowlist_opcode_info { const u32 *opcodes; size_t size; @@ -104,6 +115,8 @@ static const struct allowlist_opcode_info allowlist_opcodes[] = { ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF, adv_rss_pf_allowlist_opcodes), ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_FDIR_PF, fdir_pf_allowlist_opcodes), ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_VLAN_V2, vlan_v2_allowlist_opcodes), + ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_QOS, tc_allowlist_opcodes), + ALLOW_ITEM(VIRTCHNL_VF_CAP_PTP, ptp_allowlist_opcodes), }; /** diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c index 8e4ff3af86c6..1cca9b2262e8 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c @@ -26,6 +26,15 @@ enum ice_fdir_tunnel_type { ICE_FDIR_TUNNEL_TYPE_NONE = 0, ICE_FDIR_TUNNEL_TYPE_GTPU, ICE_FDIR_TUNNEL_TYPE_GTPU_EH, + ICE_FDIR_TUNNEL_TYPE_ECPRI, + ICE_FDIR_TUNNEL_TYPE_GTPU_INNER, + ICE_FDIR_TUNNEL_TYPE_GTPU_EH_INNER, + ICE_FDIR_TUNNEL_TYPE_GRE, + ICE_FDIR_TUNNEL_TYPE_GTPOGRE, + ICE_FDIR_TUNNEL_TYPE_GTPOGRE_INNER, + ICE_FDIR_TUNNEL_TYPE_GRE_INNER, + ICE_FDIR_TUNNEL_TYPE_L2TPV2, + ICE_FDIR_TUNNEL_TYPE_L2TPV2_INNER, }; struct virtchnl_fdir_fltr_conf { @@ -33,6 +42,11 @@ struct virtchnl_fdir_fltr_conf { enum ice_fdir_tunnel_type ttype; u64 inset_flag; u32 flow_id; + + struct ice_parser_profile *prof; + bool parser_ena; + u8 *pkt_buf; + u8 pkt_len; }; struct virtchnl_fdir_inset_map { @@ -536,6 +550,8 @@ static void ice_vc_fdir_reset_cnt_all(struct ice_vf_fdir *fdir) fdir->fdir_fltr_cnt[flow][0] = 0; fdir->fdir_fltr_cnt[flow][1] = 0; } + + fdir->fdir_fltr_cnt_total = 0; } /** @@ -785,6 +801,113 @@ err_exit: } /** + * ice_vc_fdir_is_raw_flow - check if FDIR flow is raw (binary) + * @proto: virtchnl protocol headers + * + * Check if the FDIR rule is raw flow (protocol agnostic flow) or not. Note + * that common FDIR rule must have non-zero proto->count. Thus, we choose the + * tunnel_level and count of proto as the indicators. If both tunnel_level and + * count of proto are zero, this FDIR rule will be regarded as raw flow. + * + * Returns: true if headers describe raw flow, false otherwise. + */ +static bool +ice_vc_fdir_is_raw_flow(struct virtchnl_proto_hdrs *proto) +{ + return (proto->tunnel_level == 0 && proto->count == 0); +} + +/** + * ice_vc_fdir_parse_raw - parse a virtchnl raw FDIR rule + * @vf: pointer to the VF info + * @proto: virtchnl protocol headers + * @conf: FDIR configuration for each filter + * + * Parse the virtual channel filter's raw flow and store it in @conf + * + * Return: 0 on success or negative errno on failure. + */ +static int +ice_vc_fdir_parse_raw(struct ice_vf *vf, + struct virtchnl_proto_hdrs *proto, + struct virtchnl_fdir_fltr_conf *conf) +{ + u8 *pkt_buf, *msk_buf __free(kfree) = NULL; + struct ice_parser_result rslt; + struct ice_pf *pf = vf->pf; + u16 pkt_len, udp_port = 0; + struct ice_parser *psr; + int status = -ENOMEM; + struct ice_hw *hw; + + pkt_len = proto->raw.pkt_len; + + if (!pkt_len || pkt_len > VIRTCHNL_MAX_SIZE_RAW_PACKET) + return -EINVAL; + + pkt_buf = kzalloc(pkt_len, GFP_KERNEL); + msk_buf = kzalloc(pkt_len, GFP_KERNEL); + + if (!pkt_buf || !msk_buf) + goto err_mem_alloc; + + memcpy(pkt_buf, proto->raw.spec, pkt_len); + memcpy(msk_buf, proto->raw.mask, pkt_len); + + hw = &pf->hw; + + /* Get raw profile info via Parser Lib */ + psr = ice_parser_create(hw); + if (IS_ERR(psr)) { + status = PTR_ERR(psr); + goto err_mem_alloc; + } + + ice_parser_dvm_set(psr, ice_is_dvm_ena(hw)); + + if (ice_get_open_tunnel_port(hw, &udp_port, TNL_VXLAN)) + ice_parser_vxlan_tunnel_set(psr, udp_port, true); + + status = ice_parser_run(psr, pkt_buf, pkt_len, &rslt); + if (status) + goto err_parser_destroy; + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_parser_result_dump(hw, &rslt); + + conf->prof = kzalloc(sizeof(*conf->prof), GFP_KERNEL); + if (!conf->prof) { + status = -ENOMEM; + goto err_parser_destroy; + } + + status = ice_parser_profile_init(&rslt, pkt_buf, msk_buf, + pkt_len, ICE_BLK_FD, + conf->prof); + if (status) + goto err_parser_profile_init; + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_parser_profile_dump(hw, conf->prof); + + /* Store raw flow info into @conf */ + conf->pkt_len = pkt_len; + conf->pkt_buf = pkt_buf; + conf->parser_ena = true; + + ice_parser_destroy(psr); + return 0; + +err_parser_profile_init: + kfree(conf->prof); +err_parser_destroy: + ice_parser_destroy(psr); +err_mem_alloc: + kfree(pkt_buf); + return status; +} + +/** * ice_vc_fdir_parse_pattern * @vf: pointer to the VF info * @fltr: virtual channel add cmd buffer @@ -811,6 +934,10 @@ ice_vc_fdir_parse_pattern(struct ice_vf *vf, struct virtchnl_fdir_add *fltr, return -EINVAL; } + /* For raw FDIR filters created by the parser */ + if (ice_vc_fdir_is_raw_flow(proto)) + return ice_vc_fdir_parse_raw(vf, proto, conf); + for (i = 0; i < proto->count; i++) { struct virtchnl_proto_hdr *hdr = &proto->proto_hdr[i]; struct ip_esp_hdr *esph; @@ -1099,8 +1226,10 @@ ice_vc_validate_fdir_fltr(struct ice_vf *vf, struct virtchnl_fdir_add *fltr, struct virtchnl_proto_hdrs *proto = &fltr->rule_cfg.proto_hdrs; int ret; - if (!ice_vc_validate_pattern(vf, proto)) - return -EINVAL; + /* For raw FDIR filters created by the parser */ + if (!ice_vc_fdir_is_raw_flow(proto)) + if (!ice_vc_validate_pattern(vf, proto)) + return -EINVAL; ret = ice_vc_fdir_parse_pattern(vf, fltr, conf); if (ret) @@ -1293,11 +1422,15 @@ static int ice_vc_fdir_write_fltr(struct ice_vf *vf, return -ENOMEM; ice_fdir_get_prgm_desc(hw, input, &desc, add); - ret = ice_fdir_get_gen_prgm_pkt(hw, input, pkt, false, is_tun); - if (ret) { - dev_dbg(dev, "Gen training pkt for VF %d ptype %d failed\n", - vf->vf_id, input->flow_type); - goto err_free_pkt; + if (conf->parser_ena) { + memcpy(pkt, conf->pkt_buf, conf->pkt_len); + } else { + ret = ice_fdir_get_gen_prgm_pkt(hw, input, pkt, false, is_tun); + if (ret) { + dev_dbg(dev, "Gen training pkt for VF %d ptype %d failed\n", + vf->vf_id, input->flow_type); + goto err_free_pkt; + } } ret = ice_prgm_fdir_fltr(ctrl_vsi, &desc, pkt); @@ -1388,7 +1521,7 @@ ice_vc_fdir_irq_handler(struct ice_vsi *ctrl_vsi, memcpy(&ctx_done->rx_desc, rx_desc, sizeof(*rx_desc)); spin_unlock_irqrestore(&fdir->ctx_lock, flags); - ret = del_timer(&ctx_irq->rx_tmr); + ret = timer_delete(&ctx_irq->rx_tmr); if (!ret) dev_err(dev, "VF %d: Unexpected inactive timer!\n", vf->vf_id); @@ -1519,6 +1652,16 @@ err_exit: return ret; } +static int ice_fdir_is_tunnel(enum ice_fdir_tunnel_type ttype) +{ + return (ttype == ICE_FDIR_TUNNEL_TYPE_GRE_INNER || + ttype == ICE_FDIR_TUNNEL_TYPE_GTPU_INNER || + ttype == ICE_FDIR_TUNNEL_TYPE_GTPU_EH_INNER || + ttype == ICE_FDIR_TUNNEL_TYPE_GTPOGRE_INNER || + ttype == ICE_FDIR_TUNNEL_TYPE_ECPRI || + ttype == ICE_FDIR_TUNNEL_TYPE_L2TPV2_INNER); +} + /** * ice_vc_add_fdir_fltr_post * @vf: pointer to the VF structure @@ -1560,6 +1703,7 @@ ice_vc_add_fdir_fltr_post(struct ice_vf *vf, struct ice_vf_fdir_ctx *ctx, resp->status = status; resp->flow_id = conf->flow_id; vf->fdir.fdir_fltr_cnt[conf->input.flow_type][is_tun]++; + vf->fdir.fdir_fltr_cnt_total++; ret = ice_vc_send_msg_to_vf(vf, ctx->v_opcode, v_ret, (u8 *)resp, len); @@ -1624,6 +1768,7 @@ ice_vc_del_fdir_fltr_post(struct ice_vf *vf, struct ice_vf_fdir_ctx *ctx, resp->status = status; ice_vc_fdir_remove_entry(vf, conf, conf->flow_id); vf->fdir.fdir_fltr_cnt[conf->input.flow_type][is_tun]--; + vf->fdir.fdir_fltr_cnt_total--; ret = ice_vc_send_msg_to_vf(vf, ctx->v_opcode, v_ret, (u8 *)resp, len); @@ -1771,13 +1916,165 @@ static void ice_vc_fdir_clear_irq_ctx(struct ice_vf *vf) struct ice_vf_fdir_ctx *ctx = &vf->fdir.ctx_irq; unsigned long flags; - del_timer(&ctx->rx_tmr); + timer_delete(&ctx->rx_tmr); spin_lock_irqsave(&vf->fdir.ctx_lock, flags); ctx->flags &= ~ICE_VF_FDIR_CTX_VALID; spin_unlock_irqrestore(&vf->fdir.ctx_lock, flags); } /** + * ice_vc_parser_fv_check_diff - check two parsed FDIR profile fv context + * @fv_a: struct of parsed FDIR profile field vector + * @fv_b: struct of parsed FDIR profile field vector + * + * Check if the two parsed FDIR profile field vector context are different, + * including proto_id, offset and mask. + * + * Return: true on different, false on otherwise. + */ +static bool ice_vc_parser_fv_check_diff(struct ice_parser_fv *fv_a, + struct ice_parser_fv *fv_b) +{ + return (fv_a->proto_id != fv_b->proto_id || + fv_a->offset != fv_b->offset || + fv_a->msk != fv_b->msk); +} + +/** + * ice_vc_parser_fv_save - save parsed FDIR profile fv context + * @fv: struct of parsed FDIR profile field vector + * @fv_src: parsed FDIR profile field vector context to save + * + * Save the parsed FDIR profile field vector context, including proto_id, + * offset and mask. + * + * Return: Void. + */ +static void ice_vc_parser_fv_save(struct ice_parser_fv *fv, + struct ice_parser_fv *fv_src) +{ + fv->proto_id = fv_src->proto_id; + fv->offset = fv_src->offset; + fv->msk = fv_src->msk; + fv->spec = 0; +} + +/** + * ice_vc_add_fdir_raw - add a raw FDIR filter for VF + * @vf: pointer to the VF info + * @conf: FDIR configuration for each filter + * @v_ret: the final VIRTCHNL code + * @stat: pointer to the VIRTCHNL_OP_ADD_FDIR_FILTER + * @len: length of the stat + * + * Return: 0 on success or negative errno on failure. + */ +static int +ice_vc_add_fdir_raw(struct ice_vf *vf, + struct virtchnl_fdir_fltr_conf *conf, + enum virtchnl_status_code *v_ret, + struct virtchnl_fdir_add *stat, int len) +{ + struct ice_vsi *vf_vsi, *ctrl_vsi; + struct ice_fdir_prof_info *pi; + struct ice_pf *pf = vf->pf; + int ret, ptg, id, i; + struct device *dev; + struct ice_hw *hw; + bool fv_found; + + dev = ice_pf_to_dev(pf); + hw = &pf->hw; + *v_ret = VIRTCHNL_STATUS_ERR_PARAM; + stat->status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE; + + id = find_first_bit(conf->prof->ptypes, ICE_FLOW_PTYPE_MAX); + ptg = hw->blk[ICE_BLK_FD].xlt1.t[id]; + + vf_vsi = ice_get_vf_vsi(vf); + if (!vf_vsi) { + dev_err(dev, "Can not get FDIR vf_vsi for VF %d\n", vf->vf_id); + return -ENODEV; + } + + ctrl_vsi = pf->vsi[vf->ctrl_vsi_idx]; + if (!ctrl_vsi) { + dev_err(dev, "Can not get FDIR ctrl_vsi for VF %d\n", + vf->vf_id); + return -ENODEV; + } + + fv_found = false; + + /* Check if profile info already exists, then update the counter */ + pi = &vf->fdir_prof_info[ptg]; + if (pi->fdir_active_cnt != 0) { + for (i = 0; i < ICE_MAX_FV_WORDS; i++) + if (ice_vc_parser_fv_check_diff(&pi->prof.fv[i], + &conf->prof->fv[i])) + break; + if (i == ICE_MAX_FV_WORDS) { + fv_found = true; + pi->fdir_active_cnt++; + } + } + + /* HW profile setting is only required for the first time */ + if (!fv_found) { + ret = ice_flow_set_parser_prof(hw, vf_vsi->idx, + ctrl_vsi->idx, conf->prof, + ICE_BLK_FD); + + if (ret) { + *v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + dev_dbg(dev, "VF %d: insert hw prof failed\n", + vf->vf_id); + return ret; + } + } + + ret = ice_vc_fdir_insert_entry(vf, conf, &conf->flow_id); + if (ret) { + *v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + dev_dbg(dev, "VF %d: insert FDIR list failed\n", + vf->vf_id); + return ret; + } + + ret = ice_vc_fdir_set_irq_ctx(vf, conf, + VIRTCHNL_OP_ADD_FDIR_FILTER); + if (ret) { + dev_dbg(dev, "VF %d: set FDIR context failed\n", + vf->vf_id); + goto err_rem_entry; + } + + ret = ice_vc_fdir_write_fltr(vf, conf, true, false); + if (ret) { + dev_err(dev, "VF %d: adding FDIR raw flow rule failed, ret:%d\n", + vf->vf_id, ret); + goto err_clr_irq; + } + + /* Save parsed profile fv info of the FDIR rule for the first time */ + if (!fv_found) { + for (i = 0; i < conf->prof->fv_num; i++) + ice_vc_parser_fv_save(&pi->prof.fv[i], + &conf->prof->fv[i]); + pi->prof.fv_num = conf->prof->fv_num; + pi->fdir_active_cnt = 1; + } + + return 0; + +err_clr_irq: + ice_vc_fdir_clear_irq_ctx(vf); +err_rem_entry: + ice_vc_fdir_remove_entry(vf, conf, conf->flow_id); + return ret; +} + +/** * ice_vc_add_fdir_fltr - add a FDIR filter for VF by the msg buffer * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -1790,6 +2087,7 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg) struct virtchnl_fdir_add *stat = NULL; struct virtchnl_fdir_fltr_conf *conf; enum virtchnl_status_code v_ret; + struct ice_vsi *vf_vsi; struct device *dev; struct ice_pf *pf; int is_tun = 0; @@ -1798,6 +2096,22 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg) pf = vf->pf; dev = ice_pf_to_dev(pf); + vf_vsi = ice_get_vf_vsi(vf); + if (!vf_vsi) { + dev_err(dev, "Can not get FDIR vf_vsi for VF %u\n", vf->vf_id); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err_exit; + } + +#define ICE_VF_MAX_FDIR_FILTERS 128 + if (!ice_fdir_num_avail_fltr(&pf->hw, vf_vsi) || + vf->fdir.fdir_fltr_cnt_total >= ICE_VF_MAX_FDIR_FILTERS) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + dev_err(dev, "Max number of FDIR filters for VF %d is reached\n", + vf->vf_id); + goto err_exit; + } + ret = ice_vc_fdir_param_check(vf, fltr->vsi_id); if (ret) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; @@ -1830,7 +2144,7 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg) len = sizeof(*stat); ret = ice_vc_validate_fdir_fltr(vf, fltr, conf); if (ret) { - v_ret = VIRTCHNL_STATUS_SUCCESS; + v_ret = VIRTCHNL_STATUS_ERR_PARAM; stat->status = VIRTCHNL_FDIR_FAILURE_RULE_INVALID; dev_dbg(dev, "Invalid FDIR filter from VF %d\n", vf->vf_id); goto err_free_conf; @@ -1845,6 +2159,15 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg) goto exit; } + /* For raw FDIR filters created by the parser */ + if (conf->parser_ena) { + ret = ice_vc_add_fdir_raw(vf, conf, &v_ret, stat, len); + if (ret) + goto err_free_conf; + goto exit; + } + + is_tun = ice_fdir_is_tunnel(conf->ttype); ret = ice_vc_fdir_config_input_set(vf, fltr, conf, is_tun); if (ret) { v_ret = VIRTCHNL_STATUS_SUCCESS; @@ -1906,6 +2229,78 @@ err_exit: } /** + * ice_vc_del_fdir_raw - delete a raw FDIR filter for VF + * @vf: pointer to the VF info + * @conf: FDIR configuration for each filter + * @v_ret: the final VIRTCHNL code + * @stat: pointer to the VIRTCHNL_OP_DEL_FDIR_FILTER + * @len: length of the stat + * + * Return: 0 on success or negative errno on failure. + */ +static int +ice_vc_del_fdir_raw(struct ice_vf *vf, + struct virtchnl_fdir_fltr_conf *conf, + enum virtchnl_status_code *v_ret, + struct virtchnl_fdir_del *stat, int len) +{ + struct ice_vsi *vf_vsi, *ctrl_vsi; + enum ice_block blk = ICE_BLK_FD; + struct ice_fdir_prof_info *pi; + struct ice_pf *pf = vf->pf; + struct device *dev; + struct ice_hw *hw; + unsigned long id; + u16 vsi_num; + int ptg; + int ret; + + dev = ice_pf_to_dev(pf); + hw = &pf->hw; + *v_ret = VIRTCHNL_STATUS_ERR_PARAM; + stat->status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE; + + id = find_first_bit(conf->prof->ptypes, ICE_FLOW_PTYPE_MAX); + ptg = hw->blk[ICE_BLK_FD].xlt1.t[id]; + + ret = ice_vc_fdir_write_fltr(vf, conf, false, false); + if (ret) { + dev_err(dev, "VF %u: deleting FDIR raw flow rule failed: %d\n", + vf->vf_id, ret); + return ret; + } + + vf_vsi = ice_get_vf_vsi(vf); + if (!vf_vsi) { + dev_err(dev, "Can not get FDIR vf_vsi for VF %u\n", vf->vf_id); + return -ENODEV; + } + + ctrl_vsi = pf->vsi[vf->ctrl_vsi_idx]; + if (!ctrl_vsi) { + dev_err(dev, "Can not get FDIR ctrl_vsi for VF %u\n", + vf->vf_id); + return -ENODEV; + } + + pi = &vf->fdir_prof_info[ptg]; + if (pi->fdir_active_cnt != 0) { + pi->fdir_active_cnt--; + /* Remove the profile id flow if no active FDIR rule left */ + if (!pi->fdir_active_cnt) { + vsi_num = ice_get_hw_vsi_num(hw, ctrl_vsi->idx); + ice_rem_prof_id_flow(hw, blk, vsi_num, id); + + vsi_num = ice_get_hw_vsi_num(hw, vf_vsi->idx); + ice_rem_prof_id_flow(hw, blk, vsi_num, id); + } + } + + conf->parser_ena = false; + return 0; +} + +/** * ice_vc_del_fdir_fltr - delete a FDIR filter for VF by the msg buffer * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -1917,7 +2312,10 @@ int ice_vc_del_fdir_fltr(struct ice_vf *vf, u8 *msg) struct virtchnl_fdir_del *fltr = (struct virtchnl_fdir_del *)msg; struct virtchnl_fdir_del *stat = NULL; struct virtchnl_fdir_fltr_conf *conf; + struct ice_vf_fdir *fdir = &vf->fdir; enum virtchnl_status_code v_ret; + struct ice_fdir_fltr *input; + enum ice_fltr_ptype flow; struct device *dev; struct ice_pf *pf; int is_tun = 0; @@ -1967,6 +2365,15 @@ int ice_vc_del_fdir_fltr(struct ice_vf *vf, u8 *msg) goto err_exit; } + /* For raw FDIR filters created by the parser */ + if (conf->parser_ena) { + ret = ice_vc_del_fdir_raw(vf, conf, &v_ret, stat, len); + if (ret) + goto err_del_tmr; + goto exit; + } + + is_tun = ice_fdir_is_tunnel(conf->ttype); ret = ice_vc_fdir_write_fltr(vf, conf, false, is_tun); if (ret) { v_ret = VIRTCHNL_STATUS_SUCCESS; @@ -1976,6 +2383,13 @@ int ice_vc_del_fdir_fltr(struct ice_vf *vf, u8 *msg) goto err_del_tmr; } + /* Remove unused profiles to avoid unexpected behaviors */ + input = &conf->input; + flow = input->flow_type; + if (fdir->fdir_fltr_cnt[flow][is_tun] == 1) + ice_vc_fdir_rem_prof(vf, flow, is_tun); + +exit: kfree(stat); return ret; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h index c5bcc8d7481c..ac6dcab454b4 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h @@ -29,6 +29,7 @@ struct ice_vf_fdir_ctx { struct ice_vf_fdir { u16 fdir_fltr_cnt[ICE_FLTR_PTYPE_MAX][ICE_FD_HW_SEG_MAX]; int prof_entry_cnt[ICE_FLTR_PTYPE_MAX][ICE_FD_HW_SEG_MAX]; + u16 fdir_fltr_cnt_total; struct ice_fd_hw_prof **fdir_prof; struct idr fdir_rule_idr; 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 2e9ad27cb9d1..5291f2888ef8 100644 --- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c @@ -45,14 +45,15 @@ int ice_vsi_add_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) return -EINVAL; err = ice_fltr_add_vlan(vsi, vlan); - if (err && err != -EEXIST) { + if (!err) + vsi->num_vlan++; + else if (err == -EEXIST) + err = 0; + else dev_err(ice_pf_to_dev(vsi->back), "Failure Adding VLAN %d on VSI %i, status %d\n", vlan->vid, vsi->vsi_num, err); - return err; - } - vsi->num_vlan++; - return 0; + return err; } /** @@ -786,3 +787,60 @@ int ice_vsi_clear_outer_port_vlan(struct ice_vsi *vsi) kfree(ctxt); return err; } + +int ice_vsi_clear_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; + + ctxt->info = vsi->info; + + ctxt->info.port_based_outer_vlan = 0; + ctxt->info.port_based_inner_vlan = 0; + + ctxt->info.inner_vlan_flags = + FIELD_PREP(ICE_AQ_VSI_INNER_VLAN_TX_MODE_M, + ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL); + if (ice_is_dvm_ena(hw)) { + ctxt->info.inner_vlan_flags |= + FIELD_PREP(ICE_AQ_VSI_INNER_VLAN_EMODE_M, + ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING); + ctxt->info.outer_vlan_flags = + FIELD_PREP(ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M, + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL); + ctxt->info.outer_vlan_flags |= + FIELD_PREP(ICE_AQ_VSI_OUTER_TAG_TYPE_M, + ICE_AQ_VSI_OUTER_TAG_VLAN_8100); + ctxt->info.outer_vlan_flags |= + ICE_AQ_VSI_OUTER_VLAN_EMODE_NOTHING << + ICE_AQ_VSI_OUTER_VLAN_EMODE_S; + } + + ctxt->info.sw_flags2 &= ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; + ctxt->info.valid_sections = + cpu_to_le16(ICE_AQ_VSI_PROP_OUTER_TAG_VALID | + ICE_AQ_VSI_PROP_VLAN_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 port based VLAN failed, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); + } else { + vsi->info.port_based_outer_vlan = + ctxt->info.port_based_outer_vlan; + vsi->info.port_based_inner_vlan = + ctxt->info.port_based_inner_vlan; + vsi->info.outer_vlan_flags = ctxt->info.outer_vlan_flags; + vsi->info.inner_vlan_flags = ctxt->info.inner_vlan_flags; + vsi->info.sw_flags2 = ctxt->info.sw_flags2; + } + + 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 f0d84d11bd5b..12b227621a7d 100644 --- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h @@ -36,5 +36,6 @@ 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); +int ice_vsi_clear_port_vlan(struct ice_vsi *vsi); #endif /* _ICE_VSI_VLAN_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.c index 4a6c850d83ac..8c7a9b41fb63 100644 --- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.c +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.c @@ -3,6 +3,7 @@ #include "ice_pf_vsi_vlan_ops.h" #include "ice_vf_vsi_vlan_ops.h" +#include "ice_sf_vsi_vlan_ops.h" #include "ice_lib.h" #include "ice.h" @@ -72,12 +73,14 @@ void ice_vsi_init_vlan_ops(struct ice_vsi *vsi) switch (vsi->type) { case ICE_VSI_PF: - case ICE_VSI_SWITCHDEV_CTRL: ice_pf_vsi_init_vlan_ops(vsi); break; case ICE_VSI_VF: ice_vf_vsi_init_vlan_ops(vsi); break; + case ICE_VSI_SF: + ice_sf_vsi_init_vlan_ops(vsi); + break; default: dev_dbg(ice_pf_to_dev(vsi->back), "%s does not support VLAN operations\n", ice_vsi_type_str(vsi->type)); diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 1857220d27fe..a3a4eaa17739 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -2,6 +2,7 @@ /* Copyright (c) 2019, Intel Corporation. */ #include <linux/bpf_trace.h> +#include <linux/unroll.h> #include <net/xdp_sock_drv.h> #include <net/xdp.h> #include "ice.h" @@ -39,7 +40,7 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx) sizeof(vsi_stat->rx_ring_stats[q_idx]->rx_stats)); memset(&vsi_stat->tx_ring_stats[q_idx]->stats, 0, sizeof(vsi_stat->tx_ring_stats[q_idx]->stats)); - if (ice_is_xdp_ena_vsi(vsi)) + if (vsi->xdp_rings) memset(&vsi->xdp_rings[q_idx]->ring_stats->stats, 0, sizeof(vsi->xdp_rings[q_idx]->ring_stats->stats)); } @@ -52,10 +53,8 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx) static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx) { ice_clean_tx_ring(vsi->tx_rings[q_idx]); - if (ice_is_xdp_ena_vsi(vsi)) { - synchronize_rcu(); + if (vsi->xdp_rings) ice_clean_tx_ring(vsi->xdp_rings[q_idx]); - } ice_clean_rx_ring(vsi->rx_rings[q_idx]); } @@ -112,25 +111,29 @@ ice_qvec_dis_irq(struct ice_vsi *vsi, struct ice_rx_ring *rx_ring, * ice_qvec_cfg_msix - Enable IRQ for given queue vector * @vsi: the VSI that contains queue vector * @q_vector: queue vector + * @qid: queue index */ static void -ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector) +ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector, u16 qid) { u16 reg_idx = q_vector->reg_idx; struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; - struct ice_tx_ring *tx_ring; - struct ice_rx_ring *rx_ring; + int q, _qid = qid; ice_cfg_itr(hw, q_vector); - ice_for_each_tx_ring(tx_ring, q_vector->tx) - ice_cfg_txq_interrupt(vsi, tx_ring->reg_idx, reg_idx, - q_vector->tx.itr_idx); + for (q = 0; q < q_vector->num_ring_tx; q++) { + ice_cfg_txq_interrupt(vsi, _qid, reg_idx, q_vector->tx.itr_idx); + _qid++; + } + + _qid = qid; - ice_for_each_rx_ring(rx_ring, q_vector->rx) - ice_cfg_rxq_interrupt(vsi, rx_ring->reg_idx, reg_idx, - q_vector->rx.itr_idx); + for (q = 0; q < q_vector->num_ring_rx; q++) { + ice_cfg_rxq_interrupt(vsi, _qid, reg_idx, q_vector->rx.itr_idx); + _qid++; + } ice_flush(hw); } @@ -163,7 +166,7 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) struct ice_q_vector *q_vector; struct ice_tx_ring *tx_ring; struct ice_rx_ring *rx_ring; - int timeout = 50; + int fail = 0; int err; if (q_idx >= vsi->num_rxq || q_idx >= vsi->num_txq) @@ -173,40 +176,33 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) rx_ring = vsi->rx_rings[q_idx]; q_vector = rx_ring->q_vector; - while (test_and_set_bit(ICE_CFG_BUSY, vsi->state)) { - timeout--; - if (!timeout) - return -EBUSY; - usleep_range(1000, 2000); - } + synchronize_net(); + netif_carrier_off(vsi->netdev); + netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); ice_qvec_dis_irq(vsi, rx_ring, q_vector); ice_qvec_toggle_napi(vsi, q_vector, false); - netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); - ice_fill_txq_meta(vsi, tx_ring, &txq_meta); err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, tx_ring, &txq_meta); - if (err) - return err; - if (ice_is_xdp_ena_vsi(vsi)) { + if (!fail) + fail = err; + if (vsi->xdp_rings) { struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx]; memset(&txq_meta, 0, sizeof(txq_meta)); ice_fill_txq_meta(vsi, xdp_ring, &txq_meta); err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, xdp_ring, &txq_meta); - if (err) - return err; + if (!fail) + fail = err; } - err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true); - if (err) - return err; + ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, false); ice_qp_clean_rings(vsi, q_idx); ice_qp_reset_stats(vsi, q_idx); - return 0; + return fail; } /** @@ -219,40 +215,47 @@ 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_q_vector *q_vector; + int fail = 0; + bool link_up; int err; err = ice_vsi_cfg_single_txq(vsi, vsi->tx_rings, q_idx); - if (err) - return err; + if (!fail) + fail = err; if (ice_is_xdp_ena_vsi(vsi)) { struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx]; err = ice_vsi_cfg_single_txq(vsi, vsi->xdp_rings, q_idx); - if (err) - return err; + if (!fail) + fail = err; ice_set_ring_xdp(xdp_ring); ice_tx_xsk_pool(vsi, q_idx); } err = ice_vsi_cfg_single_rxq(vsi, q_idx); - if (err) - return err; + if (!fail) + fail = err; q_vector = vsi->rx_rings[q_idx]->q_vector; - ice_qvec_cfg_msix(vsi, q_vector); + ice_qvec_cfg_msix(vsi, q_vector, q_idx); err = ice_vsi_ctrl_one_rx_ring(vsi, true, q_idx, true); - if (err) - return err; + if (!fail) + fail = err; 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)); - clear_bit(ICE_CFG_BUSY, vsi->state); + /* make sure NAPI sees updated ice_{t,x}_ring::xsk_pool */ + synchronize_net(); + ice_get_link_status(vsi->port_info, &link_up); + if (link_up) { + netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); + netif_carrier_on(vsi->netdev); + } - return 0; + return fail; } /** @@ -269,7 +272,6 @@ static int ice_xsk_pool_disable(struct ice_vsi *vsi, u16 qid) if (!pool) return -EINVAL; - clear_bit(qid, vsi->af_xdp_zc_qps); xsk_pool_dma_unmap(pool, ICE_RX_DMA_ATTR); return 0; @@ -288,7 +290,7 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) { int err; - if (vsi->type != ICE_VSI_PF) + if (vsi->type != ICE_VSI_PF && vsi->type != ICE_VSI_SF) return -EINVAL; if (qid >= vsi->netdev->real_num_rx_queues || @@ -300,8 +302,6 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) if (err) return err; - set_bit(qid, vsi->af_xdp_zc_qps); - return 0; } @@ -349,11 +349,13 @@ ice_realloc_rx_xdp_bufs(struct ice_rx_ring *rx_ring, bool pool_present) int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc) { struct ice_rx_ring *rx_ring; - unsigned long q; + uint i; + + ice_for_each_rxq(vsi, i) { + rx_ring = vsi->rx_rings[i]; + if (!rx_ring->xsk_pool) + continue; - for_each_set_bit(q, vsi->af_xdp_zc_qps, - max_t(int, vsi->alloc_txq, vsi->alloc_rxq)) { - rx_ring = vsi->rx_rings[q]; if (ice_realloc_rx_xdp_bufs(rx_ring, zc)) return -ENOMEM; } @@ -380,7 +382,8 @@ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) goto failure; } - if_running = netif_running(vsi->netdev) && ice_is_xdp_ena_vsi(vsi); + if_running = !test_bit(ICE_VSI_DOWN, vsi->state) && + ice_is_xdp_ena_vsi(vsi); if (if_running) { struct ice_rx_ring *rx_ring = vsi->rx_rings[qid]; @@ -460,6 +463,7 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp, /** * __ice_alloc_rx_bufs_zc - allocate a number of Rx buffers * @rx_ring: Rx ring + * @xsk_pool: XSK buffer pool to pick buffers to be filled by HW * @count: The number of buffers to allocate * * Place the @count of descriptors onto Rx ring. Handle the ring wrap @@ -468,7 +472,8 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp, * * Returns true if all allocations were successful, false if any fail. */ -static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) +static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, + struct xsk_buff_pool *xsk_pool, u16 count) { u32 nb_buffs_extra = 0, nb_buffs = 0; union ice_32b_rx_flex_desc *rx_desc; @@ -480,8 +485,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) xdp = ice_xdp_buf(rx_ring, ntu); if (ntu + count >= rx_ring->count) { - nb_buffs_extra = ice_fill_rx_descs(rx_ring->xsk_pool, xdp, - rx_desc, + nb_buffs_extra = ice_fill_rx_descs(xsk_pool, xdp, rx_desc, rx_ring->count - ntu); if (nb_buffs_extra != rx_ring->count - ntu) { ntu += nb_buffs_extra; @@ -494,7 +498,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) ice_release_rx_desc(rx_ring, 0); } - nb_buffs = ice_fill_rx_descs(rx_ring->xsk_pool, xdp, rx_desc, count); + nb_buffs = ice_fill_rx_descs(xsk_pool, xdp, rx_desc, count); ntu += nb_buffs; if (ntu == rx_ring->count) @@ -510,6 +514,7 @@ exit: /** * ice_alloc_rx_bufs_zc - allocate a number of Rx buffers * @rx_ring: Rx ring + * @xsk_pool: XSK buffer pool to pick buffers to be filled by HW * @count: The number of buffers to allocate * * Wrapper for internal allocation routine; figure out how many tail @@ -517,7 +522,8 @@ exit: * * Returns true if all calls to internal alloc routine succeeded */ -bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) +bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, + struct xsk_buff_pool *xsk_pool, u16 count) { u16 rx_thresh = ICE_RING_QUARTER(rx_ring); u16 leftover, i, tail_bumps; @@ -526,9 +532,9 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) leftover = count - (tail_bumps * rx_thresh); for (i = 0; i < tail_bumps; i++) - if (!__ice_alloc_rx_bufs_zc(rx_ring, rx_thresh)) + if (!__ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, rx_thresh)) return false; - return __ice_alloc_rx_bufs_zc(rx_ring, leftover); + return __ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, leftover); } /** @@ -555,8 +561,7 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) } net_prefetch(xdp->data_meta); - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize, - GFP_ATOMIC | __GFP_NOWARN); + skb = napi_alloc_skb(&rx_ring->q_vector->napi, totalsize); if (unlikely(!skb)) return NULL; @@ -598,8 +603,10 @@ out: /** * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ * @xdp_ring: XDP Tx ring + * @xsk_pool: AF_XDP buffer pool pointer */ -static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring) +static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring, + struct xsk_buff_pool *xsk_pool) { u16 ntc = xdp_ring->next_to_clean; struct ice_tx_desc *tx_desc; @@ -650,7 +657,7 @@ skip: if (xdp_ring->next_to_clean >= cnt) xdp_ring->next_to_clean -= cnt; if (xsk_frames) - xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames); + xsk_tx_completed(xsk_pool, xsk_frames); return completed_frames; } @@ -659,6 +666,7 @@ skip: * ice_xmit_xdp_tx_zc - AF_XDP ZC handler for XDP_TX * @xdp: XDP buffer to xmit * @xdp_ring: XDP ring to produce descriptor onto + * @xsk_pool: AF_XDP buffer pool pointer * * note that this function works directly on xdp_buff, no need to convert * it to xdp_frame. xdp_buff pointer is stored to ice_tx_buf so that cleaning @@ -668,7 +676,8 @@ skip: * was not enough space on XDP ring */ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp, - struct ice_tx_ring *xdp_ring) + struct ice_tx_ring *xdp_ring, + struct xsk_buff_pool *xsk_pool) { struct skb_shared_info *sinfo = NULL; u32 size = xdp->data_end - xdp->data; @@ -682,7 +691,7 @@ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp, free_space = ICE_DESC_UNUSED(xdp_ring); if (free_space < ICE_RING_QUARTER(xdp_ring)) - free_space += ice_clean_xdp_irq_zc(xdp_ring); + free_space += ice_clean_xdp_irq_zc(xdp_ring, xsk_pool); if (unlikely(!free_space)) goto busy; @@ -702,7 +711,7 @@ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp, dma_addr_t dma; dma = xsk_buff_xdp_get_dma(xdp); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size); + xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, size); tx_buf->xdp = xdp; tx_buf->type = ICE_TX_BUF_XSK_TX; @@ -744,12 +753,14 @@ busy: * @xdp: xdp_buff used as input to the XDP program * @xdp_prog: XDP program to run * @xdp_ring: ring to be used for XDP_TX action + * @xsk_pool: AF_XDP buffer pool pointer * * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR} */ static int ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring) + struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring, + struct xsk_buff_pool *xsk_pool) { int err, result = ICE_XDP_PASS; u32 act; @@ -760,7 +771,7 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); if (!err) return ICE_XDP_REDIR; - if (xsk_uses_need_wakeup(rx_ring->xsk_pool) && err == -ENOBUFS) + if (xsk_uses_need_wakeup(xsk_pool) && err == -ENOBUFS) result = ICE_XDP_EXIT; else result = ICE_XDP_CONSUMED; @@ -771,7 +782,7 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, case XDP_PASS: break; case XDP_TX: - result = ice_xmit_xdp_tx_zc(xdp, xdp_ring); + result = ice_xmit_xdp_tx_zc(xdp, xdp_ring, xsk_pool); if (result == ICE_XDP_CONSUMED) goto out_failure; break; @@ -791,46 +802,19 @@ 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), - XDP_PACKET_HEADROOM, 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 + * @xsk_pool: AF_XDP buffer pool pointer * @budget: NAPI budget * * Returns number of processed packets on success, remaining budget on failure. */ -int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) +int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, + struct xsk_buff_pool *xsk_pool, + 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; @@ -879,11 +863,12 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) ICE_RX_FLX_DESC_PKT_LEN_M; xsk_buff_set_size(xdp, size); - xsk_buff_dma_sync_for_cpu(xdp, xsk_pool); + xsk_buff_dma_sync_for_cpu(xdp); if (!first) { first = xdp; - } else if (ice_add_xsk_frag(rx_ring, first, xdp, size)) { + } else if (likely(size) && !xsk_buff_add_frag(first, xdp)) { + xsk_buff_free(first); break; } @@ -893,7 +878,8 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) if (ice_is_non_eop(rx_ring, rx_desc)) continue; - xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring); + xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring, + xsk_pool); if (likely(xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))) { xdp_xmit |= xdp_res; } else if (xdp_res == ICE_XDP_EXIT) { @@ -942,7 +928,8 @@ construct_skb: 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); + failure |= !ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, + 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); @@ -965,17 +952,19 @@ construct_skb: /** * ice_xmit_pkt - produce a single HW Tx descriptor out of AF_XDP descriptor * @xdp_ring: XDP ring to produce the HW Tx descriptor on + * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW * @desc: AF_XDP descriptor to pull the DMA address and length from * @total_bytes: bytes accumulator that will be used for stats update */ -static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc, +static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, + struct xsk_buff_pool *xsk_pool, struct xdp_desc *desc, unsigned int *total_bytes) { struct ice_tx_desc *tx_desc; dma_addr_t dma; - dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc->addr); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc->len); + dma = xsk_buff_raw_get_dma(xsk_pool, desc->addr); + xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, desc->len); tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_to_use++); tx_desc->buf_addr = cpu_to_le64(dma); @@ -988,21 +977,25 @@ static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc, /** * ice_xmit_pkt_batch - produce a batch of HW Tx descriptors out of AF_XDP descriptors * @xdp_ring: XDP ring to produce the HW Tx descriptors on + * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW * @descs: AF_XDP descriptors to pull the DMA addresses and lengths from * @total_bytes: bytes accumulator that will be used for stats update */ -static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs, +static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, + struct xsk_buff_pool *xsk_pool, + struct xdp_desc *descs, unsigned int *total_bytes) { u16 ntu = xdp_ring->next_to_use; struct ice_tx_desc *tx_desc; u32 i; - loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) { + unrolled_count(PKTS_PER_BATCH) + for (i = 0; i < PKTS_PER_BATCH; i++) { dma_addr_t dma; - dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, descs[i].addr); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, descs[i].len); + dma = xsk_buff_raw_get_dma(xsk_pool, descs[i].addr); + xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, descs[i].len); tx_desc = ICE_TX_DESC(xdp_ring, ntu++); tx_desc->buf_addr = cpu_to_le64(dma); @@ -1018,60 +1011,69 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de /** * ice_fill_tx_hw_ring - produce the number of Tx descriptors onto ring * @xdp_ring: XDP ring to produce the HW Tx descriptors on + * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW * @descs: AF_XDP descriptors to pull the DMA addresses and lengths from * @nb_pkts: count of packets to be send * @total_bytes: bytes accumulator that will be used for stats update */ -static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs, - u32 nb_pkts, unsigned int *total_bytes) +static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring, + struct xsk_buff_pool *xsk_pool, + struct xdp_desc *descs, u32 nb_pkts, + unsigned int *total_bytes) { u32 batched, leftover, i; batched = ALIGN_DOWN(nb_pkts, PKTS_PER_BATCH); leftover = nb_pkts & (PKTS_PER_BATCH - 1); for (i = 0; i < batched; i += PKTS_PER_BATCH) - ice_xmit_pkt_batch(xdp_ring, &descs[i], total_bytes); + ice_xmit_pkt_batch(xdp_ring, xsk_pool, &descs[i], total_bytes); for (; i < batched + leftover; i++) - ice_xmit_pkt(xdp_ring, &descs[i], total_bytes); + ice_xmit_pkt(xdp_ring, xsk_pool, &descs[i], total_bytes); } /** * ice_xmit_zc - take entries from XSK Tx ring and place them onto HW Tx ring * @xdp_ring: XDP ring to produce the HW Tx descriptors on + * @xsk_pool: AF_XDP buffer pool pointer * * Returns true if there is no more work that needs to be done, false otherwise */ -bool ice_xmit_zc(struct ice_tx_ring *xdp_ring) +bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, struct xsk_buff_pool *xsk_pool) { - struct xdp_desc *descs = xdp_ring->xsk_pool->tx_descs; + struct xdp_desc *descs = xsk_pool->tx_descs; u32 nb_pkts, nb_processed = 0; unsigned int total_bytes = 0; int budget; - ice_clean_xdp_irq_zc(xdp_ring); + ice_clean_xdp_irq_zc(xdp_ring, xsk_pool); + + if (!netif_carrier_ok(xdp_ring->vsi->netdev) || + !netif_running(xdp_ring->vsi->netdev)) + return true; budget = ICE_DESC_UNUSED(xdp_ring); budget = min_t(u16, budget, ICE_RING_QUARTER(xdp_ring)); - nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, budget); + nb_pkts = xsk_tx_peek_release_desc_batch(xsk_pool, budget); if (!nb_pkts) return true; if (xdp_ring->next_to_use + nb_pkts >= xdp_ring->count) { nb_processed = xdp_ring->count - xdp_ring->next_to_use; - ice_fill_tx_hw_ring(xdp_ring, descs, nb_processed, &total_bytes); + ice_fill_tx_hw_ring(xdp_ring, xsk_pool, descs, nb_processed, + &total_bytes); xdp_ring->next_to_use = 0; } - ice_fill_tx_hw_ring(xdp_ring, &descs[nb_processed], nb_pkts - nb_processed, - &total_bytes); + ice_fill_tx_hw_ring(xdp_ring, xsk_pool, &descs[nb_processed], + nb_pkts - nb_processed, &total_bytes); ice_set_rs_bit(xdp_ring); ice_xdp_ring_update_tail(xdp_ring); ice_update_tx_ring_stats(xdp_ring, nb_pkts, total_bytes); - if (xsk_uses_need_wakeup(xdp_ring->xsk_pool)) - xsk_set_tx_need_wakeup(xdp_ring->xsk_pool); + if (xsk_uses_need_wakeup(xsk_pool)) + xsk_set_tx_need_wakeup(xsk_pool); return nb_pkts < budget; } @@ -1093,7 +1095,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, struct ice_vsi *vsi = np->vsi; struct ice_tx_ring *ring; - if (test_bit(ICE_VSI_DOWN, vsi->state)) + if (test_bit(ICE_VSI_DOWN, vsi->state) || !netif_carrier_ok(netdev)) return -ENETDOWN; if (!ice_is_xdp_ena_vsi(vsi)) @@ -1104,7 +1106,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, ring = vsi->rx_rings[queue_id]->xdp_ring; - if (!ring->xsk_pool) + if (!READ_ONCE(ring->xsk_pool)) return -EINVAL; /* The idea here is that if NAPI is running, mark a miss, so diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h index 6fa181f080ef..8dc5d55e26c5 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.h +++ b/drivers/net/ethernet/intel/ice/ice_xsk.h @@ -7,29 +7,25 @@ #define PKTS_PER_BATCH 8 -#ifdef __clang__ -#define loop_unrolled_for _Pragma("clang loop unroll_count(8)") for -#elif __GNUC__ >= 8 -#define loop_unrolled_for _Pragma("GCC unroll 8") for -#else -#define loop_unrolled_for for -#endif - struct ice_vsi; #ifdef CONFIG_XDP_SOCKETS int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid); -int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget); +int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, + struct xsk_buff_pool *xsk_pool, + int budget); int ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, u32 flags); -bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count); +bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, + struct xsk_buff_pool *xsk_pool, u16 count); bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi); void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring); void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring); -bool ice_xmit_zc(struct ice_tx_ring *xdp_ring); +bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, struct xsk_buff_pool *xsk_pool); int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc); #else -static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring) +static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring, + struct xsk_buff_pool __always_unused *xsk_pool) { return false; } @@ -44,6 +40,7 @@ ice_xsk_pool_setup(struct ice_vsi __always_unused *vsi, static inline int ice_clean_rx_irq_zc(struct ice_rx_ring __always_unused *rx_ring, + struct xsk_buff_pool __always_unused *xsk_pool, int __always_unused budget) { return 0; @@ -51,6 +48,7 @@ ice_clean_rx_irq_zc(struct ice_rx_ring __always_unused *rx_ring, static inline bool ice_alloc_rx_bufs_zc(struct ice_rx_ring __always_unused *rx_ring, + struct xsk_buff_pool __always_unused *xsk_pool, u16 __always_unused count) { return false; diff --git a/drivers/net/ethernet/intel/idpf/Kconfig b/drivers/net/ethernet/intel/idpf/Kconfig new file mode 100644 index 000000000000..2c359a8551c7 --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/Kconfig @@ -0,0 +1,27 @@ +# SPDX-License-Identifier: GPL-2.0-only +# Copyright (C) 2024 Intel Corporation + +config IDPF + tristate "Intel(R) Infrastructure Data Path Function Support" + depends on PCI_MSI + depends on PTP_1588_CLOCK_OPTIONAL + select DIMLIB + select LIBETH + 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. + +if IDPF + +config IDPF_SINGLEQ + bool "idpf singleq support" + help + This option enables support for legacy single Rx/Tx queues w/no + completion and fill queues. Only enable if you have hardware which + wants to work in this mode as it increases the driver size and adds + runtme checks on hotpath. + +endif # IDPF diff --git a/drivers/net/ethernet/intel/idpf/Makefile b/drivers/net/ethernet/intel/idpf/Makefile index 6844ead2f3ac..83ac5e296382 100644 --- a/drivers/net/ethernet/intel/idpf/Makefile +++ b/drivers/net/ethernet/intel/idpf/Makefile @@ -12,7 +12,11 @@ idpf-y := \ idpf_ethtool.o \ idpf_lib.o \ idpf_main.o \ - idpf_singleq_txrx.o \ idpf_txrx.o \ idpf_virtchnl.o \ idpf_vf_dev.o + +idpf-$(CONFIG_IDPF_SINGLEQ) += idpf_singleq_txrx.o + +idpf-$(CONFIG_PTP_1588_CLOCK) += idpf_ptp.o +idpf-$(CONFIG_PTP_1588_CLOCK) += idpf_virtchnl_ptp.o diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h index e7a036538246..1e812c3f62f9 100644 --- a/drivers/net/ethernet/intel/idpf/idpf.h +++ b/drivers/net/ethernet/intel/idpf/idpf.h @@ -17,10 +17,8 @@ struct idpf_vport_max_q; #include <linux/sctp.h> #include <linux/ethtool_netlink.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" @@ -143,7 +141,9 @@ enum idpf_vport_state { * @adapter: Adapter back pointer * @vport: Vport back pointer * @vport_id: Vport identifier + * @link_speed_mbps: Link speed in mbps * @vport_idx: Relative vport index + * @max_tx_hdr_size: Max header length hardware can support * @state: See enum idpf_vport_state * @netstats: Packet and byte stats * @stats_lock: Lock to protect stats update @@ -152,7 +152,9 @@ struct idpf_netdev_priv { struct idpf_adapter *adapter; struct idpf_vport *vport; u32 vport_id; + u32 link_speed_mbps; u16 vport_idx; + u16 max_tx_hdr_size; enum idpf_vport_state state; struct rtnl_link_stats64 netstats; spinlock_t stats_lock; @@ -189,6 +191,7 @@ struct idpf_vport_max_q { * @mb_intr_reg_init: Mailbox interrupt register initialization * @reset_reg_init: Reset register initialization * @trigger_reset: Trigger a reset to occur + * @ptp_reg_init: PTP register initialization */ struct idpf_reg_ops { void (*ctlq_reg_init)(struct idpf_ctlq_create_info *cq); @@ -197,6 +200,7 @@ struct idpf_reg_ops { void (*reset_reg_init)(struct idpf_adapter *adapter); void (*trigger_reset)(struct idpf_adapter *adapter, enum idpf_flags trig_cause); + void (*ptp_reg_init)(const struct idpf_adapter *adapter); }; /** @@ -266,7 +270,6 @@ struct idpf_port_stats { * 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. @@ -290,8 +293,10 @@ struct idpf_port_stats { * @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 * @sw_marker_wq: workqueue for marker packets + * @tx_tstamp_caps: Capabilities negotiated for Tx timestamping + * @tstamp_config: The Tx tstamp config + * @tstamp_task: Tx timestamping task */ struct idpf_vport { u16 num_txq; @@ -302,7 +307,7 @@ struct idpf_vport { u16 num_txq_grp; struct idpf_txq_group *txq_grps; u32 txq_model; - struct idpf_queue **txqs; + struct idpf_tx_queue **txqs; bool crc_enable; u16 num_rxq; @@ -310,11 +315,10 @@ struct idpf_vport { 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 libeth_rx_pt *rx_ptype_lkup; struct idpf_adapter *adapter; struct net_device *netdev; @@ -335,9 +339,12 @@ struct idpf_vport { struct idpf_port_stats port_stats; bool link_up; - u32 link_speed_mbps; wait_queue_head_t sw_marker_wq; + + struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps; + struct kernel_hwtstamp_config tstamp_config; + struct work_struct tstamp_task; }; /** @@ -482,6 +489,13 @@ struct idpf_vport_config { struct idpf_vc_xn_manager; +#define idpf_for_each_vport(adapter, iter) \ + for (struct idpf_vport **__##iter = &(adapter)->vports[0], \ + *iter = (adapter)->max_vports ? *__##iter : NULL; \ + iter; \ + iter = (++__##iter) < &(adapter)->vports[(adapter)->max_vports] ? \ + *__##iter : NULL) + /** * struct idpf_adapter - Device data struct generated on probe * @pdev: PCI device struct given on probe @@ -534,6 +548,7 @@ struct idpf_vc_xn_manager; * @vector_lock: Lock to protect vector distribution * @queue_lock: Lock to protect queue distribution * @vc_buf_lock: Lock to protect virtchnl buffer + * @ptp: Storage for PTP-related data */ struct idpf_adapter { struct pci_dev *pdev; @@ -591,6 +606,8 @@ struct idpf_adapter { struct mutex vector_lock; struct mutex queue_lock; struct mutex vc_buf_lock; + + struct idpf_ptp *ptp; }; /** @@ -601,7 +618,8 @@ struct idpf_adapter { */ static inline int idpf_is_queue_model_split(u16 q_model) { - return q_model == VIRTCHNL2_QUEUE_MODEL_SPLIT; + return !IS_ENABLED(CONFIG_IDPF_SINGLEQ) || + q_model == VIRTCHNL2_QUEUE_MODEL_SPLIT; } #define idpf_is_cap_ena(adapter, field, flag) \ @@ -632,13 +650,13 @@ bool idpf_is_capability_ena(struct idpf_adapter *adapter, bool all, 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_TX_CSUM_L4V4 (\ + VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_TCP |\ + VIRTCHNL2_CAP_TX_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_TX_CSUM_L4V6 (\ + VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_TCP |\ + VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_UDP) #define IDPF_CAP_RX_CSUM (\ VIRTCHNL2_CAP_RX_CSUM_L3_IPV4 |\ @@ -647,11 +665,9 @@ bool idpf_is_capability_ena(struct idpf_adapter *adapter, bool all, VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_TCP |\ VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_UDP) -#define IDPF_CAP_SCTP_CSUM (\ +#define IDPF_CAP_TX_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) + VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_SCTP) #define IDPF_CAP_TUNNEL_TX_CSUM (\ VIRTCHNL2_CAP_TX_CSUM_L3_SINGLE_TUNNEL |\ diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq.c b/drivers/net/ethernet/intel/idpf/idpf_controlq.c index 4849590a5591..b28991dd1870 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_controlq.c +++ b/drivers/net/ethernet/intel/idpf/idpf_controlq.c @@ -376,6 +376,9 @@ int idpf_ctlq_clean_sq(struct idpf_ctlq_info *cq, u16 *clean_count, if (!(le16_to_cpu(desc->flags) & IDPF_CTLQ_FLAG_DD)) break; + /* Ensure no other fields are read until DD flag is checked */ + dma_rmb(); + /* strip off FW internal code */ desc_err = le16_to_cpu(desc->ret_val) & 0xff; @@ -563,6 +566,9 @@ int idpf_ctlq_recv(struct idpf_ctlq_info *cq, u16 *num_q_msg, if (!(flags & IDPF_CTLQ_FLAG_DD)) break; + /* Ensure no other fields are read until DD flag is checked */ + dma_rmb(); + q_msg[i].vmvf_type = (flags & (IDPF_CTLQ_FLAG_FTYPE_VM | IDPF_CTLQ_FLAG_FTYPE_PF)) >> diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h b/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h index e8e046ef2f0d..9642494a67d8 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h +++ b/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h @@ -123,9 +123,12 @@ struct idpf_ctlq_info { /** * 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 + * @idpf_mbq_opc_send_msg_to_peer_drv: used by PF or VF to send a message to + * any peer driver */ enum idpf_mbx_opc { idpf_mbq_opc_send_msg_to_cp = 0x0801, + idpf_mbq_opc_send_msg_to_peer_drv = 0x0804, }; /* API supported for control queue management */ diff --git a/drivers/net/ethernet/intel/idpf/idpf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_dev.c index 3df9935685e9..3fae81f1f988 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_dev.c +++ b/drivers/net/ethernet/intel/idpf/idpf_dev.c @@ -4,6 +4,7 @@ #include "idpf.h" #include "idpf_lan_pf_regs.h" #include "idpf_virtchnl.h" +#include "idpf_ptp.h" #define IDPF_PF_ITR_IDX_SPACING 0x4 @@ -97,8 +98,13 @@ static int idpf_intr_reg_init(struct idpf_vport *vport) 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_intena_msk_m = PF_GLINT_DYN_CTL_INTENA_MSK_M; intr->dyn_ctl_itridx_s = PF_GLINT_DYN_CTL_ITR_INDX_S; intr->dyn_ctl_intrvl_s = PF_GLINT_DYN_CTL_INTERVAL_S; + intr->dyn_ctl_wb_on_itr_m = PF_GLINT_DYN_CTL_WB_ON_ITR_M; + intr->dyn_ctl_swint_trig_m = PF_GLINT_DYN_CTL_SWINT_TRIG_M; + intr->dyn_ctl_sw_itridx_ena_m = + PF_GLINT_DYN_CTL_SW_ITR_INDX_ENA_M; spacing = IDPF_ITR_IDX_SPACING(reg_vals[vec_id].itrn_index_spacing, IDPF_PF_ITR_IDX_SPACING); @@ -144,6 +150,18 @@ static void idpf_trigger_reset(struct idpf_adapter *adapter, } /** + * idpf_ptp_reg_init - Initialize required registers + * @adapter: Driver specific private structure + * + * Set the bits required for enabling shtime and cmd execution + */ +static void idpf_ptp_reg_init(const struct idpf_adapter *adapter) +{ + adapter->ptp->cmd.shtime_enable_mask = PF_GLTSYN_CMD_SYNC_SHTIME_EN_M; + adapter->ptp->cmd.exec_cmd_mask = PF_GLTSYN_CMD_SYNC_EXEC_CMD_M; +} + +/** * idpf_reg_ops_init - Initialize register API function pointers * @adapter: Driver specific private structure */ @@ -154,6 +172,7 @@ static void idpf_reg_ops_init(struct idpf_adapter *adapter) 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; + adapter->dev_ops.reg_ops.ptp_reg_init = idpf_ptp_reg_init; } /** diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c index 986d429d1175..9bdb309b668e 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c +++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c @@ -2,6 +2,7 @@ /* Copyright (C) 2023 Intel Corporation */ #include "idpf.h" +#include "idpf_ptp.h" /** * idpf_get_rxnfc - command to get RX flow classification rules @@ -222,14 +223,19 @@ 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; + u16 num_txq, num_rxq; struct device *dev; int err = 0; u16 idx; + if (ch->rx_count && ch->tx_count) { + netdev_err(netdev, "Dedicated RX or TX channels cannot be used simultaneously\n"); + return -EINVAL; + } + idpf_vport_ctrl_lock(netdev); vport = idpf_netdev_to_vport(netdev); @@ -239,20 +245,6 @@ static int idpf_set_channels(struct net_device *netdev, 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; @@ -376,7 +368,8 @@ static int idpf_set_ringparam(struct net_device *netdev, new_tx_count); if (new_tx_count == vport->txq_desc_count && - new_rx_count == vport->rxq_desc_count) + new_rx_count == vport->rxq_desc_count && + kring->tcp_data_split == idpf_vport_get_hsplit(vport)) goto unlock_mutex; if (!idpf_vport_set_hsplit(vport, kring->tcp_data_split)) { @@ -445,22 +438,24 @@ struct idpf_stats { .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) +/* Helper macros for defining some statistics related to queues */ +#define IDPF_RX_QUEUE_STAT(_name, _stat) \ + IDPF_STAT(struct idpf_rx_queue, _name, _stat) +#define IDPF_TX_QUEUE_STAT(_name, _stat) \ + IDPF_STAT(struct idpf_tx_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), + IDPF_TX_QUEUE_STAT("pkts", q_stats.packets), + IDPF_TX_QUEUE_STAT("bytes", q_stats.bytes), + IDPF_TX_QUEUE_STAT("lso_pkts", q_stats.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), + IDPF_RX_QUEUE_STAT("pkts", q_stats.packets), + IDPF_RX_QUEUE_STAT("bytes", q_stats.bytes), + IDPF_RX_QUEUE_STAT("rx_gro_hw_pkts", q_stats.rsc_pkts), }; #define IDPF_TX_QUEUE_STATS_LEN ARRAY_SIZE(idpf_gstrings_tx_queue_stats) @@ -571,8 +566,6 @@ static void idpf_get_stat_strings(struct net_device *netdev, u8 *data) 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); } /** @@ -606,7 +599,6 @@ 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; @@ -625,11 +617,8 @@ static int idpf_get_sset_count(struct net_device *netdev, int sset) 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) + + return 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; } /** @@ -641,7 +630,7 @@ static int idpf_get_sset_count(struct net_device *netdev, int sset) * 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, +static void idpf_add_one_ethtool_stat(u64 *data, const void *pstat, const struct idpf_stats *stat) { char *p; @@ -679,6 +668,7 @@ static void idpf_add_one_ethtool_stat(u64 *data, void *pstat, * idpf_add_queue_stats - copy queue statistics into supplied buffer * @data: ethtool stats buffer * @q: the queue to copy + * @type: type of the queue * * 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 @@ -689,19 +679,23 @@ static void idpf_add_one_ethtool_stat(u64 *data, void *pstat, * * This function expects to be called while under rcu_read_lock(). */ -static void idpf_add_queue_stats(u64 **data, struct idpf_queue *q) +static void idpf_add_queue_stats(u64 **data, const void *q, + enum virtchnl2_queue_type type) { + const struct u64_stats_sync *stats_sync; const struct idpf_stats *stats; unsigned int start; unsigned int size; unsigned int i; - if (q->q_type == VIRTCHNL2_QUEUE_TYPE_RX) { + if (type == VIRTCHNL2_QUEUE_TYPE_RX) { size = IDPF_RX_QUEUE_STATS_LEN; stats = idpf_gstrings_rx_queue_stats; + stats_sync = &((const struct idpf_rx_queue *)q)->stats_sync; } else { size = IDPF_TX_QUEUE_STATS_LEN; stats = idpf_gstrings_tx_queue_stats; + stats_sync = &((const struct idpf_tx_queue *)q)->stats_sync; } /* To avoid invalid statistics values, ensure that we keep retrying @@ -709,10 +703,10 @@ static void idpf_add_queue_stats(u64 **data, struct idpf_queue *q) * u64_stats_fetch_retry. */ do { - start = u64_stats_fetch_begin(&q->stats_sync); + start = u64_stats_fetch_begin(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)); + } while (u64_stats_fetch_retry(stats_sync, start)); /* Once we successfully copy the stats in, update the data pointer */ *data += size; @@ -801,7 +795,7 @@ static void idpf_collect_queue_stats(struct idpf_vport *vport) 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; + struct idpf_rx_queue *rxq; unsigned int start; if (idpf_is_queue_model_split(vport->rxq_model)) @@ -815,7 +809,7 @@ static void idpf_collect_queue_stats(struct idpf_vport *vport) do { start = u64_stats_fetch_begin(&rxq->stats_sync); - stats = &rxq->q_stats.rx; + stats = &rxq->q_stats; 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); @@ -836,7 +830,7 @@ static void idpf_collect_queue_stats(struct idpf_vport *vport) 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 *txq = txq_grp->txqs[j]; struct idpf_tx_queue_stats *stats; unsigned int start; @@ -846,7 +840,7 @@ static void idpf_collect_queue_stats(struct idpf_vport *vport) do { start = u64_stats_fetch_begin(&txq->stats_sync); - stats = &txq->q_stats.tx; + stats = &txq->q_stats; linearize = u64_stats_read(&stats->linearize); qbusy = u64_stats_read(&stats->q_busy); skb_drops = u64_stats_read(&stats->skb_drops); @@ -877,7 +871,6 @@ static void idpf_get_ethtool_stats(struct net_device *netdev, { 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; @@ -904,12 +897,12 @@ static void idpf_get_ethtool_stats(struct net_device *netdev, qtype = VIRTCHNL2_QUEUE_TYPE_TX; for (j = 0; j < txq_grp->num_txq; j++, total++) { - struct idpf_queue *txq = txq_grp->txqs[j]; + struct idpf_tx_queue *txq = txq_grp->txqs[j]; if (!txq) idpf_add_empty_queue_stats(&data, qtype); else - idpf_add_queue_stats(&data, txq); + idpf_add_queue_stats(&data, txq, qtype); } } @@ -937,7 +930,7 @@ static void idpf_get_ethtool_stats(struct net_device *netdev, num_rxq = rxq_grp->singleq.num_rxq; for (j = 0; j < num_rxq; j++, total++) { - struct idpf_queue *rxq; + struct idpf_rx_queue *rxq; if (is_splitq) rxq = &rxq_grp->splitq.rxq_sets[j]->rxq; @@ -946,93 +939,77 @@ static void idpf_get_ethtool_stats(struct net_device *netdev, 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); + idpf_add_queue_stats(&data, rxq, qtype); } } 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 + * idpf_find_rxq_vec - find rxq vector from q index * @vport: virtual port associated to queue * @q_num: q index used to find queue * - * returns pointer to rx queue + * returns pointer to rx vector */ -static struct idpf_queue *idpf_find_rxq(struct idpf_vport *vport, int q_num) +static struct idpf_q_vector *idpf_find_rxq_vec(const 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]; + return vport->rxq_grps->singleq.rxqs[q_num]->q_vector; 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; + return vport->rxq_grps[q_grp].splitq.rxq_sets[q_idx]->rxq.q_vector; } /** - * idpf_find_txq - find txq from q index + * idpf_find_txq_vec - find txq vector from q index * @vport: virtual port associated to queue * @q_num: q index used to find queue * - * returns pointer to tx queue + * returns pointer to tx vector */ -static struct idpf_queue *idpf_find_txq(struct idpf_vport *vport, int q_num) +static struct idpf_q_vector *idpf_find_txq_vec(const struct idpf_vport *vport, + int q_num) { int q_grp; if (!idpf_is_queue_model_split(vport->txq_model)) - return vport->txqs[q_num]; + return vport->txqs[q_num]->q_vector; q_grp = q_num / IDPF_DFLT_SPLITQ_TXQ_PER_GROUP; - return vport->txq_grps[q_grp].complq; + return vport->txq_grps[q_grp].complq->q_vector; } /** * __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 + * @q_vector: queue vector corresponding to this queue + * @type: queue type */ static void __idpf_get_q_coalesce(struct ethtool_coalesce *ec, - struct idpf_queue *q) + const struct idpf_q_vector *q_vector, + enum virtchnl2_queue_type type) { - if (q->q_type == VIRTCHNL2_QUEUE_TYPE_RX) { + if (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; + IDPF_ITR_IS_DYNAMIC(q_vector->rx_intr_mode); + ec->rx_coalesce_usecs = 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_ITR_IS_DYNAMIC(q_vector->tx_intr_mode); + ec->tx_coalesce_usecs = q_vector->tx_itr_value; } } @@ -1048,8 +1025,8 @@ 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; + const struct idpf_netdev_priv *np = netdev_priv(netdev); + const struct idpf_vport *vport; int err = 0; idpf_vport_ctrl_lock(netdev); @@ -1064,10 +1041,12 @@ static int idpf_get_q_coalesce(struct net_device *netdev, } if (q_num < vport->num_rxq) - __idpf_get_q_coalesce(ec, idpf_find_rxq(vport, q_num)); + __idpf_get_q_coalesce(ec, idpf_find_rxq_vec(vport, q_num), + VIRTCHNL2_QUEUE_TYPE_RX); if (q_num < vport->num_txq) - __idpf_get_q_coalesce(ec, idpf_find_txq(vport, q_num)); + __idpf_get_q_coalesce(ec, idpf_find_txq_vec(vport, q_num), + VIRTCHNL2_QUEUE_TYPE_TX); unlock_mutex: idpf_vport_ctrl_unlock(netdev); @@ -1111,16 +1090,15 @@ static int idpf_get_per_q_coalesce(struct net_device *netdev, u32 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 + * @qv: queue vector 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) +static int __idpf_set_q_coalesce(const struct ethtool_coalesce *ec, + struct idpf_q_vector *qv, 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; @@ -1136,7 +1114,7 @@ static int __idpf_set_q_coalesce(struct ethtool_coalesce *ec, 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"); + netdev_err(qv->vport->netdev, "Cannot set coalesce usecs if adaptive enabled\n"); return -EINVAL; } @@ -1145,7 +1123,7 @@ static int __idpf_set_q_coalesce(struct ethtool_coalesce *ec, return 0; if (coalesce_usecs > IDPF_ITR_MAX) { - netdev_err(q->vport->netdev, + netdev_err(qv->vport->netdev, "Invalid value, %d-usecs range is 0-%d\n", coalesce_usecs, IDPF_ITR_MAX); @@ -1154,7 +1132,7 @@ static int __idpf_set_q_coalesce(struct ethtool_coalesce *ec, if (coalesce_usecs % 2) { coalesce_usecs--; - netdev_info(q->vport->netdev, + netdev_info(qv->vport->netdev, "HW only supports even ITR values, ITR rounded to %d\n", coalesce_usecs); } @@ -1193,15 +1171,16 @@ static int __idpf_set_q_coalesce(struct ethtool_coalesce *ec, * * Return 0 on success, and negative on failure */ -static int idpf_set_q_coalesce(struct idpf_vport *vport, - struct ethtool_coalesce *ec, +static int idpf_set_q_coalesce(const struct idpf_vport *vport, + const struct ethtool_coalesce *ec, int q_num, bool is_rxq) { - struct idpf_queue *q; + struct idpf_q_vector *qv; - q = is_rxq ? idpf_find_rxq(vport, q_num) : idpf_find_txq(vport, q_num); + qv = is_rxq ? idpf_find_rxq_vec(vport, q_num) : + idpf_find_txq_vec(vport, q_num); - if (q && __idpf_set_q_coalesce(ec, q, is_rxq)) + if (qv && __idpf_set_q_coalesce(ec, qv, is_rxq)) return -EINVAL; return 0; @@ -1318,27 +1297,87 @@ static void idpf_set_msglevel(struct net_device *netdev, u32 data) 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); + struct idpf_netdev_priv *np = netdev_priv(netdev); ethtool_link_ksettings_zero_link_mode(cmd, supported); cmd->base.autoneg = AUTONEG_DISABLE; cmd->base.port = PORT_NONE; - if (vport->link_up) { + if (netif_carrier_ok(netdev)) { cmd->base.duplex = DUPLEX_FULL; - cmd->base.speed = vport->link_speed_mbps; + cmd->base.speed = np->link_speed_mbps; } else { cmd->base.duplex = DUPLEX_UNKNOWN; cmd->base.speed = SPEED_UNKNOWN; } - idpf_vport_ctrl_unlock(netdev); - return 0; } +/** + * idpf_get_timestamp_filters - Get the supported timestamping mode + * @vport: Virtual port structure + * @info: ethtool timestamping info structure + * + * Get the Tx/Rx timestamp filters. + */ +static void idpf_get_timestamp_filters(const struct idpf_vport *vport, + struct kernel_ethtool_ts_info *info) +{ + info->so_timestamping = SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + + info->tx_types = BIT(HWTSTAMP_TX_OFF); + info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | BIT(HWTSTAMP_FILTER_ALL); + + if (!vport->tx_tstamp_caps || + vport->adapter->ptp->tx_tstamp_access == IDPF_PTP_NONE) + return; + + info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_TX_HARDWARE; + + info->tx_types |= BIT(HWTSTAMP_TX_ON); +} + +/** + * idpf_get_ts_info - Get device PHC association + * @netdev: network interface device structure + * @info: ethtool timestamping info structure + * + * Return: 0 on success, -errno otherwise. + */ +static int idpf_get_ts_info(struct net_device *netdev, + struct kernel_ethtool_ts_info *info) +{ + struct idpf_netdev_priv *np = netdev_priv(netdev); + struct idpf_vport *vport; + int err = 0; + + if (!mutex_trylock(&np->adapter->vport_ctrl_lock)) + return -EBUSY; + + vport = idpf_netdev_to_vport(netdev); + + if (!vport->adapter->ptp) { + err = -EOPNOTSUPP; + goto unlock; + } + + if (idpf_is_cap_ena(vport->adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_PTP) && + vport->adapter->ptp->clock) { + info->phc_index = ptp_clock_index(vport->adapter->ptp->clock); + idpf_get_timestamp_filters(vport, info); + } else { + pci_dbg(vport->adapter->pdev, "PTP clock not detected\n"); + err = ethtool_op_get_ts_info(netdev, info); + } + +unlock: + mutex_unlock(&np->adapter->vport_ctrl_lock); + + return err; +} + static const struct ethtool_ops idpf_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_USE_ADAPTIVE, @@ -1363,6 +1402,7 @@ static const struct ethtool_ops idpf_ethtool_ops = { .get_ringparam = idpf_get_ringparam, .set_ringparam = idpf_set_ringparam, .get_link_ksettings = idpf_get_link_ksettings, + .get_ts_info = idpf_get_ts_info, }; /** diff --git a/drivers/net/ethernet/intel/idpf/idpf_lan_pf_regs.h b/drivers/net/ethernet/intel/idpf/idpf_lan_pf_regs.h index 24edb8a6ec2e..cc9aa2b6a14a 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lan_pf_regs.h +++ b/drivers/net/ethernet/intel/idpf/idpf_lan_pf_regs.h @@ -53,6 +53,10 @@ #define PF_FW_ATQH_ATQH_M GENMASK(9, 0) #define PF_FW_ATQT (PF_FW_BASE + 0x24) +/* Timesync registers */ +#define PF_GLTSYN_CMD_SYNC_EXEC_CMD_M GENMASK(1, 0) +#define PF_GLTSYN_CMD_SYNC_SHTIME_EN_M BIT(2) + /* Interrupts */ #define PF_GLINT_BASE 0x08900000 #define PF_GLINT_DYN_CTL(_INT) (PF_GLINT_BASE + ((_INT) * 0x1000)) diff --git a/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h index a5752dcab888..7492d1713243 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h +++ b/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h @@ -4,6 +4,8 @@ #ifndef _IDPF_LAN_TXRX_H_ #define _IDPF_LAN_TXRX_H_ +#include <linux/bits.h> + enum idpf_rss_hash { IDPF_HASH_INVALID = 0, /* Values 1 - 28 are reserved for future use */ @@ -280,7 +282,18 @@ struct idpf_flex_tx_tso_ctx_qw { u8 flex; }; -struct idpf_flex_tx_ctx_desc { +union idpf_flex_tx_ctx_desc { + /* DTYPE = IDPF_TX_DESC_DTYPE_CTX (0x01) */ + struct { + __le64 qw0; +#define IDPF_TX_CTX_L2TAG2_M GENMASK_ULL(47, 32) + __le64 qw1; +#define IDPF_TX_CTX_DTYPE_M GENMASK_ULL(3, 0) +#define IDPF_TX_CTX_CMD_M GENMASK_ULL(15, 4) +#define IDPF_TX_CTX_TSYN_REG_M GENMASK_ULL(47, 30) +#define IDPF_TX_CTX_MSS_M GENMASK_ULL(50, 63) + } tsyn; + /* DTYPE = IDPF_TX_DESC_DTYPE_FLEX_TSO_CTX (0x05) */ struct { struct idpf_flex_tx_tso_ctx_qw qw0; diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index 5d3532c27d57..bab12ecb2df5 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -3,9 +3,9 @@ #include "idpf.h" #include "idpf_virtchnl.h" +#include "idpf_ptp.h" -static const struct net_device_ops idpf_netdev_ops_splitq; -static const struct net_device_ops idpf_netdev_ops_singleq; +static const struct net_device_ops idpf_netdev_ops; /** * idpf_init_vector_stack - Fill the MSIX vector stack with vector index @@ -69,7 +69,7 @@ static void idpf_deinit_vector_stack(struct idpf_adapter *adapter) 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); + kfree(free_irq(adapter->msix_entries[0].vector, adapter)); queue_delayed_work(adapter->mbx_wq, &adapter->mbx_task, 0); } @@ -124,15 +124,14 @@ static void idpf_mb_irq_enable(struct idpf_adapter *adapter) */ 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; + char *name; 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); + 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, name, adapter); if (err) { dev_err(&adapter->pdev->dev, "IRQ request for mailbox failed, error: %d\n", err); @@ -146,22 +145,6 @@ static int idpf_mb_intr_req_irq(struct idpf_adapter *adapter) } /** - * 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 */ @@ -351,7 +334,7 @@ int idpf_intr_req(struct idpf_adapter *adapter) goto free_irq; } - idpf_set_mb_vec_id(adapter); + adapter->mb_vector.v_idx = le16_to_cpu(adapter->caps.mailbox_vector_id); vecids = kcalloc(total_vecs, sizeof(u16), GFP_KERNEL); if (!vecids) { @@ -359,24 +342,11 @@ int idpf_intr_req(struct idpf_adapter *adapter) 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; + num_vec_ids = idpf_get_vec_ids(adapter, vecids, total_vecs, + &adapter->req_vec_chunks->vchunks); + if (num_vec_ids < v_actual) { + err = -EINVAL; + goto free_vecids; } for (vector = 0; vector < v_actual; vector++) { @@ -718,8 +688,10 @@ static int idpf_cfg_netdev(struct idpf_vport *vport) { struct idpf_adapter *adapter = vport->adapter; struct idpf_vport_config *vport_config; + netdev_features_t other_offloads = 0; + netdev_features_t csum_offloads = 0; + netdev_features_t tso_offloads = 0; netdev_features_t dflt_features; - netdev_features_t offloads = 0; struct idpf_netdev_priv *np; struct net_device *netdev; u16 idx = vport->idx; @@ -736,6 +708,7 @@ static int idpf_cfg_netdev(struct idpf_vport *vport) np->vport = vport; np->vport_idx = vport->idx; np->vport_id = vport->vport_id; + np->max_tx_hdr_size = idpf_get_max_tx_hdr_size(adapter); vport->netdev = netdev; return idpf_init_mac_addr(vport, netdev); @@ -753,6 +726,7 @@ static int idpf_cfg_netdev(struct idpf_vport *vport) np->adapter = adapter; np->vport_idx = vport->idx; np->vport_id = vport->vport_id; + np->max_tx_hdr_size = idpf_get_max_tx_hdr_size(adapter); spin_lock_init(&np->stats_lock); @@ -765,10 +739,7 @@ static int idpf_cfg_netdev(struct idpf_vport *vport) } /* 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; + netdev->netdev_ops = &idpf_netdev_ops; /* setup watchdog timeout value to be 5 second */ netdev->watchdog_timeo = 5 * HZ; @@ -784,54 +755,34 @@ static int idpf_cfg_netdev(struct idpf_vport *vport) 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_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_TX_CSUM_L4V4)) + csum_offloads |= NETIF_F_IP_CSUM; + if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_TX_CSUM_L4V6)) + csum_offloads |= 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; + csum_offloads |= NETIF_F_RXCSUM; + if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_TX_SCTP_CSUM)) + csum_offloads |= NETIF_F_SCTP_CRC; if (idpf_is_cap_ena(adapter, IDPF_SEG_CAPS, VIRTCHNL2_CAP_SEG_IPV4_TCP)) - dflt_features |= NETIF_F_TSO; + tso_offloads |= NETIF_F_TSO; if (idpf_is_cap_ena(adapter, IDPF_SEG_CAPS, VIRTCHNL2_CAP_SEG_IPV6_TCP)) - dflt_features |= NETIF_F_TSO6; + tso_offloads |= 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; + tso_offloads |= 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; - } + other_offloads |= NETIF_F_GRO_HW; if (idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_LOOPBACK)) - offloads |= NETIF_F_LOOPBACK; + other_offloads |= NETIF_F_LOOPBACK; - netdev->features |= dflt_features; - netdev->hw_features |= dflt_features | offloads; - netdev->hw_enc_features |= dflt_features | offloads; + netdev->features |= dflt_features | csum_offloads | tso_offloads; + netdev->hw_features |= netdev->features | other_offloads; + netdev->vlan_features |= netdev->features | other_offloads; + netdev->hw_enc_features |= dflt_features | other_offloads; idpf_set_ethtool_ops(netdev); + netif_set_affinity_auto(netdev); SET_NETDEV_DEV(netdev, &adapter->pdev->dev); /* carrier off on init to avoid Tx hangs */ @@ -905,8 +856,8 @@ static void idpf_vport_stop(struct idpf_vport *vport) vport->link_up = false; idpf_vport_intr_deinit(vport); - idpf_vport_intr_rel(vport); idpf_vport_queues_rel(vport); + idpf_vport_intr_rel(vport); np->state = __IDPF_VPORT_DOWN; } @@ -945,12 +896,19 @@ static int idpf_stop(struct net_device *netdev) static void idpf_decfg_netdev(struct idpf_vport *vport) { struct idpf_adapter *adapter = vport->adapter; + u16 idx = vport->idx; - unregister_netdev(vport->netdev); - free_netdev(vport->netdev); + kfree(vport->rx_ptype_lkup); + vport->rx_ptype_lkup = NULL; + + if (test_and_clear_bit(IDPF_VPORT_REG_NETDEV, + adapter->vport_config[idx]->flags)) { + unregister_netdev(vport->netdev); + free_netdev(vport->netdev); + } vport->netdev = NULL; - adapter->netdevs[vport->idx] = NULL; + adapter->netdevs[idx] = NULL; } /** @@ -1142,11 +1100,9 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *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); + if (!vport->q_vector_idxs) + goto free_vport; - return NULL; - } idpf_vport_init(vport, max_q); /* This alloc is done separate from the LUT because it's not strictly @@ -1156,11 +1112,9 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter, */ 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); + if (!rss_data->rss_key) + goto free_vector_idxs; - return NULL; - } /* Initialize default rss key */ netdev_rss_key_fill((void *)rss_data->rss_key, rss_data->rss_key_size); @@ -1173,6 +1127,13 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter, adapter->next_vport = idpf_get_free_slot(adapter); return vport; + +free_vector_idxs: + kfree(vport->q_vector_idxs); +free_vport: + kfree(vport); + + return NULL; } /** @@ -1318,14 +1279,14 @@ static void idpf_rx_init_buf_tail(struct idpf_vport *vport) if (idpf_is_queue_model_split(vport->rxq_model)) { for (j = 0; j < vport->num_bufqs_per_qgrp; j++) { - struct idpf_queue *q = + const struct idpf_buf_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 = + const struct idpf_rx_queue *q = grp->singleq.rxqs[j]; writel(q->next_to_alloc, q->tail); @@ -1337,9 +1298,8 @@ static void idpf_rx_init_buf_tail(struct idpf_vport *vport) /** * 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) +static int idpf_vport_open(struct idpf_vport *vport) { struct idpf_netdev_priv *np = netdev_priv(vport->netdev); struct idpf_adapter *adapter = vport->adapter; @@ -1352,48 +1312,47 @@ static int idpf_vport_open(struct idpf_vport *vport, bool alloc_res) /* 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; + return err; } + err = idpf_vport_queues_alloc(vport); + if (err) + goto intr_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; + goto queues_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; + goto queues_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; + goto queues_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; + goto queues_rel; } idpf_rx_init_buf_tail(vport); + idpf_vport_intr_ena(vport); err = idpf_send_config_queues_msg(vport); if (err) { @@ -1456,10 +1415,10 @@ 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); +intr_rel: + idpf_vport_intr_rel(vport); return err; } @@ -1540,7 +1499,7 @@ void idpf_init_task(struct work_struct *work) 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); + idpf_vport_open(vport); /* Spawn and return 'idpf_init_task' work queue until all the * default vports are created @@ -1553,13 +1512,22 @@ void idpf_init_task(struct work_struct *work) } 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); + struct net_device *netdev = adapter->netdevs[index]; + struct idpf_vport_config *vport_config; + + vport_config = adapter->vport_config[index]; + + if (!netdev || + test_bit(IDPF_VPORT_REG_NETDEV, vport_config->flags)) + continue; + + err = register_netdev(netdev); + if (err) { + dev_err(&pdev->dev, "failed to register netdev for vport %d: %pe\n", + index, ERR_PTR(err)); + continue; } + set_bit(IDPF_VPORT_REG_NETDEV, vport_config->flags); } /* As all the required vports are created, clear the reset flag @@ -1803,6 +1771,7 @@ static int idpf_init_hard_reset(struct idpf_adapter *adapter) */ err = idpf_vc_core_init(adapter); if (err) { + cancel_delayed_work_sync(&adapter->mbx_task); idpf_deinit_dflt_mbx(adapter); goto unlock_mutex; } @@ -1854,7 +1823,7 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport, enum idpf_vport_state current_state = np->state; struct idpf_adapter *adapter = vport->adapter; struct idpf_vport *new_vport; - int err, i; + int err; /* 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 @@ -1877,7 +1846,7 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport, * 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, link_speed_mbps)); + memcpy(new_vport, vport, offsetof(struct idpf_vport, link_up)); /* Adjust resource parameters prior to reallocating resources */ switch (reset_cause) { @@ -1899,9 +1868,6 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport, 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 { @@ -1926,64 +1892,30 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport, /* 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, link_speed_mbps)); - - /* 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; - } - } + memcpy(vport, new_vport, offsetof(struct idpf_vport, link_up)); 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; + goto err_open; if (current_state == __IDPF_VPORT_UP) - err = idpf_vport_open(vport, false); + err = idpf_vport_open(vport); kfree(new_vport); return err; err_reset: - idpf_vport_queues_rel(new_vport); + idpf_send_add_queues_msg(vport, vport->num_txq, vport->num_complq, + vport->num_rxq, vport->num_bufq); + +err_open: + if (current_state == __IDPF_VPORT_UP) + idpf_vport_open(vport); + free_vport: kfree(new_vport); @@ -2212,8 +2144,13 @@ static int idpf_open(struct net_device *netdev) idpf_vport_ctrl_lock(netdev); vport = idpf_netdev_to_vport(netdev); - err = idpf_vport_open(vport, true); + err = idpf_set_real_num_queues(vport); + if (err) + goto unlock; + + err = idpf_vport_open(vport); +unlock: idpf_vport_ctrl_unlock(netdev); return err; @@ -2234,7 +2171,7 @@ static int idpf_change_mtu(struct net_device *netdev, int new_mtu) idpf_vport_ctrl_lock(netdev); vport = idpf_netdev_to_vport(netdev); - netdev->mtu = new_mtu; + WRITE_ONCE(netdev->mtu, new_mtu); err = idpf_initiate_soft_reset(vport, IDPF_SR_MTU_CHANGE); @@ -2253,8 +2190,8 @@ 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; + struct idpf_netdev_priv *np = netdev_priv(netdev); + u16 max_tx_hdr_size = np->max_tx_hdr_size; size_t len; /* No point in doing any of this if neither checksum nor GSO are @@ -2277,7 +2214,7 @@ static netdev_features_t idpf_features_check(struct sk_buff *skb, goto unsupported; len = skb_network_header_len(skb); - if (unlikely(len > idpf_get_max_tx_hdr_size(adapter))) + if (unlikely(len > max_tx_hdr_size)) goto unsupported; if (!skb->encapsulation) @@ -2290,7 +2227,7 @@ static netdev_features_t idpf_features_check(struct sk_buff *skb, /* IPLEN can support at most 127 dwords */ len = skb_inner_network_header_len(skb); - if (unlikely(len > idpf_get_max_tx_hdr_size(adapter))) + if (unlikely(len > max_tx_hdr_size)) goto unsupported; /* No need to validate L4LEN as TCP is the only protocol with a @@ -2392,24 +2329,64 @@ void idpf_free_dma_mem(struct idpf_hw *hw, struct idpf_dma_mem *mem) 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 int idpf_hwtstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + struct idpf_vport *vport; + int err; + + idpf_vport_ctrl_lock(netdev); + vport = idpf_netdev_to_vport(netdev); + + if (!vport->link_up) { + idpf_vport_ctrl_unlock(netdev); + return -EPERM; + } + + if (!idpf_ptp_is_vport_tx_tstamp_ena(vport) && + !idpf_ptp_is_vport_rx_tstamp_ena(vport)) { + idpf_vport_ctrl_unlock(netdev); + return -EOPNOTSUPP; + } + + err = idpf_ptp_set_timestamp_mode(vport, config); + + idpf_vport_ctrl_unlock(netdev); + + return err; +} + +static int idpf_hwtstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *config) +{ + struct idpf_vport *vport; + + idpf_vport_ctrl_lock(netdev); + vport = idpf_netdev_to_vport(netdev); + + if (!vport->link_up) { + idpf_vport_ctrl_unlock(netdev); + return -EPERM; + } + + if (!idpf_ptp_is_vport_tx_tstamp_ena(vport) && + !idpf_ptp_is_vport_rx_tstamp_ena(vport)) { + idpf_vport_ctrl_unlock(netdev); + return 0; + } + + *config = vport->tstamp_config; + + idpf_vport_ctrl_unlock(netdev); + + return 0; +} -static const struct net_device_ops idpf_netdev_ops_singleq = { +static const struct net_device_ops idpf_netdev_ops = { .ndo_open = idpf_open, .ndo_stop = idpf_stop, - .ndo_start_xmit = idpf_tx_singleq_start, + .ndo_start_xmit = idpf_tx_start, .ndo_features_check = idpf_features_check, .ndo_set_rx_mode = idpf_set_rx_mode, .ndo_validate_addr = eth_validate_addr, @@ -2418,4 +2395,6 @@ static const struct net_device_ops idpf_netdev_ops_singleq = { .ndo_get_stats64 = idpf_get_stats64, .ndo_set_features = idpf_set_features, .ndo_tx_timeout = idpf_tx_timeout, + .ndo_hwtstamp_get = idpf_hwtstamp_get, + .ndo_hwtstamp_set = idpf_hwtstamp_set, }; diff --git a/drivers/net/ethernet/intel/idpf/idpf_main.c b/drivers/net/ethernet/intel/idpf/idpf_main.c index f784eea044bd..0efd9c0c7a90 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_main.c +++ b/drivers/net/ethernet/intel/idpf/idpf_main.c @@ -8,6 +8,7 @@ #define DRV_SUMMARY "Intel(R) Infrastructure Data Path Function Linux Driver" MODULE_DESCRIPTION(DRV_SUMMARY); +MODULE_IMPORT_NS("LIBETH"); MODULE_LICENSE("GPL"); /** @@ -86,7 +87,12 @@ destroy_wqs: */ static void idpf_shutdown(struct pci_dev *pdev) { - idpf_remove(pdev); + struct idpf_adapter *adapter = pci_get_drvdata(pdev); + + cancel_delayed_work_sync(&adapter->serv_task); + cancel_delayed_work_sync(&adapter->vc_event_task); + idpf_vc_core_deinit(adapter); + idpf_deinit_dflt_mbx(adapter); if (system_state == SYSTEM_POWER_OFF) pci_set_power_state(pdev, PCI_D3hot); @@ -162,6 +168,10 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_free; } + err = pci_enable_ptm(pdev, NULL); + if (err) + pci_dbg(pdev, "PCIe PTM is not supported by PCIe bus/controller\n"); + /* set up for high or low dma */ err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); if (err) { @@ -173,7 +183,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_master(pdev); pci_set_drvdata(pdev, adapter); - adapter->init_wq = alloc_workqueue("%s-%s-init", 0, 0, + adapter->init_wq = alloc_workqueue("%s-%s-init", + WQ_UNBOUND | WQ_MEM_RECLAIM, 0, dev_driver_string(dev), dev_name(dev)); if (!adapter->init_wq) { @@ -182,7 +193,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_free; } - adapter->serv_wq = alloc_workqueue("%s-%s-service", 0, 0, + adapter->serv_wq = alloc_workqueue("%s-%s-service", + WQ_UNBOUND | WQ_MEM_RECLAIM, 0, dev_driver_string(dev), dev_name(dev)); if (!adapter->serv_wq) { @@ -191,8 +203,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_serv_wq_alloc; } - adapter->mbx_wq = alloc_workqueue("%s-%s-mbx", 0, 0, - dev_driver_string(dev), + adapter->mbx_wq = alloc_workqueue("%s-%s-mbx", WQ_UNBOUND | WQ_HIGHPRI, + 0, dev_driver_string(dev), dev_name(dev)); if (!adapter->mbx_wq) { dev_err(dev, "Failed to allocate mailbox workqueue\n"); @@ -200,7 +212,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_mbx_wq_alloc; } - adapter->stats_wq = alloc_workqueue("%s-%s-stats", 0, 0, + adapter->stats_wq = alloc_workqueue("%s-%s-stats", + WQ_UNBOUND | WQ_MEM_RECLAIM, 0, dev_driver_string(dev), dev_name(dev)); if (!adapter->stats_wq) { @@ -209,7 +222,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_stats_wq_alloc; } - adapter->vc_event_wq = alloc_workqueue("%s-%s-vc_event", 0, 0, + adapter->vc_event_wq = alloc_workqueue("%s-%s-vc_event", + WQ_UNBOUND | WQ_MEM_RECLAIM, 0, dev_driver_string(dev), dev_name(dev)); if (!adapter->vc_event_wq) { diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_ptp.c new file mode 100644 index 000000000000..4f8725c85332 --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.c @@ -0,0 +1,873 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2024 Intel Corporation */ + +#include "idpf.h" +#include "idpf_ptp.h" + +/** + * idpf_ptp_get_access - Determine the access type of the PTP features + * @adapter: Driver specific private structure + * @direct: Capability that indicates the direct access + * @mailbox: Capability that indicates the mailbox access + * + * Return: the type of supported access for the PTP feature. + */ +static enum idpf_ptp_access +idpf_ptp_get_access(const struct idpf_adapter *adapter, u32 direct, u32 mailbox) +{ + if (adapter->ptp->caps & direct) + return IDPF_PTP_DIRECT; + else if (adapter->ptp->caps & mailbox) + return IDPF_PTP_MAILBOX; + else + return IDPF_PTP_NONE; +} + +/** + * idpf_ptp_get_features_access - Determine the access type of PTP features + * @adapter: Driver specific private structure + * + * Fulfill the adapter structure with type of the supported PTP features + * access. + */ +void idpf_ptp_get_features_access(const struct idpf_adapter *adapter) +{ + struct idpf_ptp *ptp = adapter->ptp; + u32 direct, mailbox; + + /* Get the device clock time */ + direct = VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME; + mailbox = VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME_MB; + ptp->get_dev_clk_time_access = idpf_ptp_get_access(adapter, + direct, + mailbox); + + /* Set the device clock time */ + direct = VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME; + mailbox = VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME; + ptp->set_dev_clk_time_access = idpf_ptp_get_access(adapter, + direct, + mailbox); + + /* Adjust the device clock time */ + direct = VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK; + mailbox = VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK_MB; + ptp->adj_dev_clk_time_access = idpf_ptp_get_access(adapter, + direct, + mailbox); + + /* Tx timestamping */ + direct = VIRTCHNL2_CAP_PTP_TX_TSTAMPS; + mailbox = VIRTCHNL2_CAP_PTP_TX_TSTAMPS_MB; + ptp->tx_tstamp_access = idpf_ptp_get_access(adapter, + direct, + mailbox); +} + +/** + * idpf_ptp_enable_shtime - Enable shadow time and execute a command + * @adapter: Driver specific private structure + */ +static void idpf_ptp_enable_shtime(struct idpf_adapter *adapter) +{ + u32 shtime_enable, exec_cmd; + + /* Get offsets */ + shtime_enable = adapter->ptp->cmd.shtime_enable_mask; + exec_cmd = adapter->ptp->cmd.exec_cmd_mask; + + /* Set the shtime en and the sync field */ + writel(shtime_enable, adapter->ptp->dev_clk_regs.cmd_sync); + writel(exec_cmd | shtime_enable, adapter->ptp->dev_clk_regs.cmd_sync); +} + +/** + * idpf_ptp_read_src_clk_reg_direct - Read directly the main timer value + * @adapter: Driver specific private structure + * @sts: Optional parameter for holding a pair of system timestamps from + * the system clock. Will be ignored when NULL is given. + * + * Return: the device clock time. + */ +static u64 idpf_ptp_read_src_clk_reg_direct(struct idpf_adapter *adapter, + struct ptp_system_timestamp *sts) +{ + struct idpf_ptp *ptp = adapter->ptp; + u32 hi, lo; + + spin_lock(&ptp->read_dev_clk_lock); + + /* Read the system timestamp pre PHC read */ + ptp_read_system_prets(sts); + + idpf_ptp_enable_shtime(adapter); + + /* Read the system timestamp post PHC read */ + ptp_read_system_postts(sts); + + lo = readl(ptp->dev_clk_regs.dev_clk_ns_l); + hi = readl(ptp->dev_clk_regs.dev_clk_ns_h); + + spin_unlock(&ptp->read_dev_clk_lock); + + return ((u64)hi << 32) | lo; +} + +/** + * idpf_ptp_read_src_clk_reg_mailbox - Read the main timer value through mailbox + * @adapter: Driver specific private structure + * @sts: Optional parameter for holding a pair of system timestamps from + * the system clock. Will be ignored when NULL is given. + * @src_clk: Returned main timer value in nanoseconds unit + * + * Return: 0 on success, -errno otherwise. + */ +static int idpf_ptp_read_src_clk_reg_mailbox(struct idpf_adapter *adapter, + struct ptp_system_timestamp *sts, + u64 *src_clk) +{ + struct idpf_ptp_dev_timers clk_time; + int err; + + /* Read the system timestamp pre PHC read */ + ptp_read_system_prets(sts); + + err = idpf_ptp_get_dev_clk_time(adapter, &clk_time); + if (err) + return err; + + /* Read the system timestamp post PHC read */ + ptp_read_system_postts(sts); + + *src_clk = clk_time.dev_clk_time_ns; + + return 0; +} + +/** + * idpf_ptp_read_src_clk_reg - Read the main timer value + * @adapter: Driver specific private structure + * @src_clk: Returned main timer value in nanoseconds unit + * @sts: Optional parameter for holding a pair of system timestamps from + * the system clock. Will be ignored if NULL is given. + * + * Return: the device clock time on success, -errno otherwise. + */ +static int idpf_ptp_read_src_clk_reg(struct idpf_adapter *adapter, u64 *src_clk, + struct ptp_system_timestamp *sts) +{ + switch (adapter->ptp->get_dev_clk_time_access) { + case IDPF_PTP_NONE: + return -EOPNOTSUPP; + case IDPF_PTP_MAILBOX: + return idpf_ptp_read_src_clk_reg_mailbox(adapter, sts, src_clk); + case IDPF_PTP_DIRECT: + *src_clk = idpf_ptp_read_src_clk_reg_direct(adapter, sts); + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +/** + * idpf_ptp_gettimex64 - Get the time of the clock + * @info: the driver's PTP info structure + * @ts: timespec64 structure to hold the current time value + * @sts: Optional parameter for holding a pair of system timestamps from + * the system clock. Will be ignored if NULL is given. + * + * Return: the device clock value in ns, after converting it into a timespec + * struct on success, -errno otherwise. + */ +static int idpf_ptp_gettimex64(struct ptp_clock_info *info, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info); + u64 time_ns; + int err; + + err = idpf_ptp_read_src_clk_reg(adapter, &time_ns, sts); + if (err) + return -EACCES; + + *ts = ns_to_timespec64(time_ns); + + return 0; +} + +/** + * idpf_ptp_update_phctime_rxq_grp - Update the cached PHC time for a given Rx + * queue group. + * @grp: receive queue group in which Rx timestamp is enabled + * @split: Indicates whether the queue model is split or single queue + * @systime: Cached system time + */ +static void +idpf_ptp_update_phctime_rxq_grp(const struct idpf_rxq_group *grp, bool split, + u64 systime) +{ + struct idpf_rx_queue *rxq; + u16 i; + + if (!split) { + for (i = 0; i < grp->singleq.num_rxq; i++) { + rxq = grp->singleq.rxqs[i]; + if (rxq) + WRITE_ONCE(rxq->cached_phc_time, systime); + } + } else { + for (i = 0; i < grp->splitq.num_rxq_sets; i++) { + rxq = &grp->splitq.rxq_sets[i]->rxq; + if (rxq) + WRITE_ONCE(rxq->cached_phc_time, systime); + } + } +} + +/** + * idpf_ptp_update_cached_phctime - Update the cached PHC time values + * @adapter: Driver specific private structure + * + * This function updates the system time values which are cached in the adapter + * structure and the Rx queues. + * + * This function must be called periodically to ensure that the cached value + * is never more than 2 seconds old. + * + * Return: 0 on success, -errno otherwise. + */ +static int idpf_ptp_update_cached_phctime(struct idpf_adapter *adapter) +{ + u64 systime; + int err; + + err = idpf_ptp_read_src_clk_reg(adapter, &systime, NULL); + if (err) + return -EACCES; + + /* Update the cached PHC time stored in the adapter structure. + * These values are used to extend Tx timestamp values to 64 bit + * expected by the stack. + */ + WRITE_ONCE(adapter->ptp->cached_phc_time, systime); + WRITE_ONCE(adapter->ptp->cached_phc_jiffies, jiffies); + + idpf_for_each_vport(adapter, vport) { + bool split; + + if (!vport || !vport->rxq_grps) + continue; + + split = idpf_is_queue_model_split(vport->rxq_model); + + for (u16 i = 0; i < vport->num_rxq_grp; i++) { + struct idpf_rxq_group *grp = &vport->rxq_grps[i]; + + idpf_ptp_update_phctime_rxq_grp(grp, split, systime); + } + } + + return 0; +} + +/** + * idpf_ptp_settime64 - Set the time of the clock + * @info: the driver's PTP info structure + * @ts: timespec64 structure that holds the new time value + * + * Set the device clock to the user input value. The conversion from timespec + * to ns happens in the write function. + * + * Return: 0 on success, -errno otherwise. + */ +static int idpf_ptp_settime64(struct ptp_clock_info *info, + const struct timespec64 *ts) +{ + struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info); + enum idpf_ptp_access access; + int err; + u64 ns; + + access = adapter->ptp->set_dev_clk_time_access; + if (access != IDPF_PTP_MAILBOX) + return -EOPNOTSUPP; + + ns = timespec64_to_ns(ts); + + err = idpf_ptp_set_dev_clk_time(adapter, ns); + if (err) { + pci_err(adapter->pdev, "Failed to set the time, err: %pe\n", + ERR_PTR(err)); + return err; + } + + err = idpf_ptp_update_cached_phctime(adapter); + if (err) + pci_warn(adapter->pdev, + "Unable to immediately update cached PHC time\n"); + + return 0; +} + +/** + * idpf_ptp_adjtime_nonatomic - Do a non-atomic clock adjustment + * @info: the driver's PTP info structure + * @delta: Offset in nanoseconds to adjust the time by + * + * Return: 0 on success, -errno otherwise. + */ +static int idpf_ptp_adjtime_nonatomic(struct ptp_clock_info *info, s64 delta) +{ + struct timespec64 now, then; + int err; + + err = idpf_ptp_gettimex64(info, &now, NULL); + if (err) + return err; + + then = ns_to_timespec64(delta); + now = timespec64_add(now, then); + + return idpf_ptp_settime64(info, &now); +} + +/** + * idpf_ptp_adjtime - Adjust the time of the clock by the indicated delta + * @info: the driver's PTP info structure + * @delta: Offset in nanoseconds to adjust the time by + * + * Return: 0 on success, -errno otherwise. + */ +static int idpf_ptp_adjtime(struct ptp_clock_info *info, s64 delta) +{ + struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info); + enum idpf_ptp_access access; + int err; + + access = adapter->ptp->adj_dev_clk_time_access; + if (access != IDPF_PTP_MAILBOX) + return -EOPNOTSUPP; + + /* Hardware only supports atomic adjustments using signed 32-bit + * integers. For any adjustment outside this range, perform + * a non-atomic get->adjust->set flow. + */ + if (delta > S32_MAX || delta < S32_MIN) + return idpf_ptp_adjtime_nonatomic(info, delta); + + err = idpf_ptp_adj_dev_clk_time(adapter, delta); + if (err) { + pci_err(adapter->pdev, "Failed to adjust the clock with delta %lld err: %pe\n", + delta, ERR_PTR(err)); + return err; + } + + err = idpf_ptp_update_cached_phctime(adapter); + if (err) + pci_warn(adapter->pdev, + "Unable to immediately update cached PHC time\n"); + + return 0; +} + +/** + * idpf_ptp_adjfine - Adjust clock increment rate + * @info: the driver's PTP info structure + * @scaled_ppm: Parts per million with 16-bit fractional field + * + * Adjust the frequency of the clock by the indicated scaled ppm from the + * base frequency. + * + * Return: 0 on success, -errno otherwise. + */ +static int idpf_ptp_adjfine(struct ptp_clock_info *info, long scaled_ppm) +{ + struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info); + enum idpf_ptp_access access; + u64 incval, diff; + int err; + + access = adapter->ptp->adj_dev_clk_time_access; + if (access != IDPF_PTP_MAILBOX) + return -EOPNOTSUPP; + + incval = adapter->ptp->base_incval; + + diff = adjust_by_scaled_ppm(incval, scaled_ppm); + err = idpf_ptp_adj_dev_clk_fine(adapter, diff); + if (err) + pci_err(adapter->pdev, "Failed to adjust clock increment rate for scaled ppm %ld %pe\n", + scaled_ppm, ERR_PTR(err)); + + return 0; +} + +/** + * idpf_ptp_verify_pin - Verify if pin supports requested pin function + * @info: the driver's PTP info structure + * @pin: Pin index + * @func: Assigned function + * @chan: Assigned channel + * + * Return: EOPNOTSUPP as not supported yet. + */ +static int idpf_ptp_verify_pin(struct ptp_clock_info *info, unsigned int pin, + enum ptp_pin_function func, unsigned int chan) +{ + return -EOPNOTSUPP; +} + +/** + * idpf_ptp_gpio_enable - Enable/disable ancillary features of PHC + * @info: the driver's PTP info structure + * @rq: The requested feature to change + * @on: Enable/disable flag + * + * Return: EOPNOTSUPP as not supported yet. + */ +static int idpf_ptp_gpio_enable(struct ptp_clock_info *info, + struct ptp_clock_request *rq, int on) +{ + return -EOPNOTSUPP; +} + +/** + * idpf_ptp_tstamp_extend_32b_to_64b - Convert a 32b nanoseconds Tx or Rx + * timestamp value to 64b. + * @cached_phc_time: recently cached copy of PHC time + * @in_timestamp: Ingress/egress 32b nanoseconds timestamp value + * + * Hardware captures timestamps which contain only 32 bits of nominal + * nanoseconds, as opposed to the 64bit timestamps that the stack expects. + * + * Return: Tx timestamp value extended to 64 bits based on cached PHC time. + */ +u64 idpf_ptp_tstamp_extend_32b_to_64b(u64 cached_phc_time, u32 in_timestamp) +{ + u32 delta, phc_time_lo; + u64 ns; + + /* Extract the lower 32 bits of the PHC time */ + phc_time_lo = (u32)cached_phc_time; + + /* Calculate the delta between the lower 32bits of the cached PHC + * time and the in_timestamp value. + */ + delta = in_timestamp - phc_time_lo; + + if (delta > U32_MAX / 2) { + /* Reverse the delta calculation here */ + delta = phc_time_lo - in_timestamp; + ns = cached_phc_time - delta; + } else { + ns = cached_phc_time + delta; + } + + return ns; +} + +/** + * idpf_ptp_extend_ts - Convert a 40b timestamp to 64b nanoseconds + * @vport: Virtual port structure + * @in_tstamp: Ingress/egress timestamp value + * + * It is assumed that the caller verifies the timestamp is valid prior to + * calling this function. + * + * Extract the 32bit nominal nanoseconds and extend them. Use the cached PHC + * time stored in the device private PTP structure as the basis for timestamp + * extension. + * + * Return: Tx timestamp value extended to 64 bits. + */ +u64 idpf_ptp_extend_ts(struct idpf_vport *vport, u64 in_tstamp) +{ + struct idpf_ptp *ptp = vport->adapter->ptp; + unsigned long discard_time; + + discard_time = ptp->cached_phc_jiffies + 2 * HZ; + + if (time_is_before_jiffies(discard_time)) + return 0; + + return idpf_ptp_tstamp_extend_32b_to_64b(ptp->cached_phc_time, + lower_32_bits(in_tstamp)); +} + +/** + * idpf_ptp_request_ts - Request an available Tx timestamp index + * @tx_q: Transmit queue on which the Tx timestamp is requested + * @skb: The SKB to associate with this timestamp request + * @idx: Index of the Tx timestamp latch + * + * Request tx timestamp index negotiated during PTP init that will be set into + * Tx descriptor. + * + * Return: 0 and the index that can be provided to Tx descriptor on success, + * -errno otherwise. + */ +int idpf_ptp_request_ts(struct idpf_tx_queue *tx_q, struct sk_buff *skb, + u32 *idx) +{ + struct idpf_ptp_tx_tstamp *ptp_tx_tstamp; + struct list_head *head; + + /* Get the index from the free latches list */ + spin_lock(&tx_q->cached_tstamp_caps->latches_lock); + + head = &tx_q->cached_tstamp_caps->latches_free; + if (list_empty(head)) { + spin_unlock(&tx_q->cached_tstamp_caps->latches_lock); + return -ENOBUFS; + } + + ptp_tx_tstamp = list_first_entry(head, struct idpf_ptp_tx_tstamp, + list_member); + list_del(&ptp_tx_tstamp->list_member); + + ptp_tx_tstamp->skb = skb_get(skb); + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + + /* Move the element to the used latches list */ + list_add(&ptp_tx_tstamp->list_member, + &tx_q->cached_tstamp_caps->latches_in_use); + spin_unlock(&tx_q->cached_tstamp_caps->latches_lock); + + *idx = ptp_tx_tstamp->idx; + + return 0; +} + +/** + * idpf_ptp_set_rx_tstamp - Enable or disable Rx timestamping + * @vport: Virtual port structure + * @rx_filter: Receive timestamp filter + */ +static void idpf_ptp_set_rx_tstamp(struct idpf_vport *vport, int rx_filter) +{ + bool enable = true, splitq; + + splitq = idpf_is_queue_model_split(vport->rxq_model); + + if (rx_filter == HWTSTAMP_FILTER_NONE) { + enable = false; + vport->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; + } else { + vport->tstamp_config.rx_filter = HWTSTAMP_FILTER_ALL; + } + + for (u16 i = 0; i < vport->num_rxq_grp; i++) { + struct idpf_rxq_group *grp = &vport->rxq_grps[i]; + struct idpf_rx_queue *rx_queue; + u16 j, num_rxq; + + if (splitq) + num_rxq = grp->splitq.num_rxq_sets; + else + num_rxq = grp->singleq.num_rxq; + + for (j = 0; j < num_rxq; j++) { + if (splitq) + rx_queue = &grp->splitq.rxq_sets[j]->rxq; + else + rx_queue = grp->singleq.rxqs[j]; + + if (enable) + idpf_queue_set(PTP, rx_queue); + else + idpf_queue_clear(PTP, rx_queue); + } + } +} + +/** + * idpf_ptp_set_timestamp_mode - Setup driver for requested timestamp mode + * @vport: Virtual port structure + * @config: Hwtstamp settings requested or saved + * + * Return: 0 on success, -errno otherwise. + */ +int idpf_ptp_set_timestamp_mode(struct idpf_vport *vport, + struct kernel_hwtstamp_config *config) +{ + switch (config->tx_type) { + case HWTSTAMP_TX_OFF: + break; + case HWTSTAMP_TX_ON: + if (!idpf_ptp_is_vport_tx_tstamp_ena(vport)) + return -EINVAL; + break; + default: + return -EINVAL; + } + + vport->tstamp_config.tx_type = config->tx_type; + idpf_ptp_set_rx_tstamp(vport, config->rx_filter); + *config = vport->tstamp_config; + + return 0; +} + +/** + * idpf_tstamp_task - Delayed task to handle Tx tstamps + * @work: work_struct handle + */ +void idpf_tstamp_task(struct work_struct *work) +{ + struct idpf_vport *vport; + + vport = container_of(work, struct idpf_vport, tstamp_task); + + idpf_ptp_get_tx_tstamp(vport); +} + +/** + * idpf_ptp_do_aux_work - Do PTP periodic work + * @info: Driver's PTP info structure + * + * Return: Number of jiffies to periodic work. + */ +static long idpf_ptp_do_aux_work(struct ptp_clock_info *info) +{ + struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info); + + idpf_ptp_update_cached_phctime(adapter); + + return msecs_to_jiffies(500); +} + +/** + * idpf_ptp_set_caps - Set PTP capabilities + * @adapter: Driver specific private structure + * + * This function sets the PTP functions. + */ +static void idpf_ptp_set_caps(const struct idpf_adapter *adapter) +{ + struct ptp_clock_info *info = &adapter->ptp->info; + + snprintf(info->name, sizeof(info->name), "%s-%s-clk", + KBUILD_MODNAME, pci_name(adapter->pdev)); + + info->owner = THIS_MODULE; + info->max_adj = adapter->ptp->max_adj; + info->gettimex64 = idpf_ptp_gettimex64; + info->settime64 = idpf_ptp_settime64; + info->adjfine = idpf_ptp_adjfine; + info->adjtime = idpf_ptp_adjtime; + info->verify = idpf_ptp_verify_pin; + info->enable = idpf_ptp_gpio_enable; + info->do_aux_work = idpf_ptp_do_aux_work; +} + +/** + * idpf_ptp_create_clock - Create PTP clock device for userspace + * @adapter: Driver specific private structure + * + * This function creates a new PTP clock device. + * + * Return: 0 on success, -errno otherwise. + */ +static int idpf_ptp_create_clock(const struct idpf_adapter *adapter) +{ + struct ptp_clock *clock; + + idpf_ptp_set_caps(adapter); + + /* Attempt to register the clock before enabling the hardware. */ + clock = ptp_clock_register(&adapter->ptp->info, + &adapter->pdev->dev); + if (IS_ERR(clock)) { + pci_err(adapter->pdev, "PTP clock creation failed: %pe\n", + clock); + return PTR_ERR(clock); + } + + adapter->ptp->clock = clock; + + return 0; +} + +/** + * idpf_ptp_release_vport_tstamp - Release the Tx timestamps trakcers for a + * given vport. + * @vport: Virtual port structure + * + * Remove the queues and delete lists that tracks Tx timestamp entries for a + * given vport. + */ +static void idpf_ptp_release_vport_tstamp(struct idpf_vport *vport) +{ + struct idpf_ptp_tx_tstamp *ptp_tx_tstamp, *tmp; + struct list_head *head; + + cancel_work_sync(&vport->tstamp_task); + + /* Remove list with free latches */ + spin_lock_bh(&vport->tx_tstamp_caps->latches_lock); + + head = &vport->tx_tstamp_caps->latches_free; + list_for_each_entry_safe(ptp_tx_tstamp, tmp, head, list_member) { + list_del(&ptp_tx_tstamp->list_member); + kfree(ptp_tx_tstamp); + } + + /* Remove list with latches in use */ + head = &vport->tx_tstamp_caps->latches_in_use; + list_for_each_entry_safe(ptp_tx_tstamp, tmp, head, list_member) { + list_del(&ptp_tx_tstamp->list_member); + kfree(ptp_tx_tstamp); + } + + spin_unlock_bh(&vport->tx_tstamp_caps->latches_lock); + + kfree(vport->tx_tstamp_caps); + vport->tx_tstamp_caps = NULL; +} + +/** + * idpf_ptp_release_tstamp - Release the Tx timestamps trackers + * @adapter: Driver specific private structure + * + * Remove the queues and delete lists that tracks Tx timestamp entries. + */ +static void idpf_ptp_release_tstamp(struct idpf_adapter *adapter) +{ + idpf_for_each_vport(adapter, vport) { + if (!idpf_ptp_is_vport_tx_tstamp_ena(vport)) + continue; + + idpf_ptp_release_vport_tstamp(vport); + } +} + +/** + * idpf_ptp_get_txq_tstamp_capability - Verify the timestamping capability + * for a given tx queue. + * @txq: Transmit queue + * + * Since performing timestamp flows requires reading the device clock value and + * the support in the Control Plane, the function checks both factors and + * summarizes the support for the timestamping. + * + * Return: true if the timestamping is supported, false otherwise. + */ +bool idpf_ptp_get_txq_tstamp_capability(struct idpf_tx_queue *txq) +{ + if (!txq || !txq->cached_tstamp_caps) + return false; + else if (txq->cached_tstamp_caps->access) + return true; + else + return false; +} + +/** + * idpf_ptp_init - Initialize PTP hardware clock support + * @adapter: Driver specific private structure + * + * Set up the device for interacting with the PTP hardware clock for all + * functions. Function will allocate and register a ptp_clock with the + * PTP_1588_CLOCK infrastructure. + * + * Return: 0 on success, -errno otherwise. + */ +int idpf_ptp_init(struct idpf_adapter *adapter) +{ + struct timespec64 ts; + int err; + + if (!idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_PTP)) { + pci_dbg(adapter->pdev, "PTP capability is not detected\n"); + return -EOPNOTSUPP; + } + + adapter->ptp = kzalloc(sizeof(*adapter->ptp), GFP_KERNEL); + if (!adapter->ptp) + return -ENOMEM; + + /* add a back pointer to adapter */ + adapter->ptp->adapter = adapter; + + if (adapter->dev_ops.reg_ops.ptp_reg_init) + adapter->dev_ops.reg_ops.ptp_reg_init(adapter); + + err = idpf_ptp_get_caps(adapter); + if (err) { + pci_err(adapter->pdev, "Failed to get PTP caps err %d\n", err); + goto free_ptp; + } + + err = idpf_ptp_create_clock(adapter); + if (err) + goto free_ptp; + + if (adapter->ptp->get_dev_clk_time_access != IDPF_PTP_NONE) + ptp_schedule_worker(adapter->ptp->clock, 0); + + /* Write the default increment time value if the clock adjustments + * are enabled. + */ + if (adapter->ptp->adj_dev_clk_time_access != IDPF_PTP_NONE) { + err = idpf_ptp_adj_dev_clk_fine(adapter, + adapter->ptp->base_incval); + if (err) + goto remove_clock; + } + + /* Write the initial time value if the set time operation is enabled */ + if (adapter->ptp->set_dev_clk_time_access != IDPF_PTP_NONE) { + ts = ktime_to_timespec64(ktime_get_real()); + err = idpf_ptp_settime64(&adapter->ptp->info, &ts); + if (err) + goto remove_clock; + } + + spin_lock_init(&adapter->ptp->read_dev_clk_lock); + + pci_dbg(adapter->pdev, "PTP init successful\n"); + + return 0; + +remove_clock: + if (adapter->ptp->get_dev_clk_time_access != IDPF_PTP_NONE) + ptp_cancel_worker_sync(adapter->ptp->clock); + + ptp_clock_unregister(adapter->ptp->clock); + adapter->ptp->clock = NULL; + +free_ptp: + kfree(adapter->ptp); + adapter->ptp = NULL; + + return err; +} + +/** + * idpf_ptp_release - Clear PTP hardware clock support + * @adapter: Driver specific private structure + */ +void idpf_ptp_release(struct idpf_adapter *adapter) +{ + struct idpf_ptp *ptp = adapter->ptp; + + if (!ptp) + return; + + if (ptp->tx_tstamp_access != IDPF_PTP_NONE && + ptp->get_dev_clk_time_access != IDPF_PTP_NONE) + idpf_ptp_release_tstamp(adapter); + + if (ptp->clock) { + if (adapter->ptp->get_dev_clk_time_access != IDPF_PTP_NONE) + ptp_cancel_worker_sync(adapter->ptp->clock); + + ptp_clock_unregister(ptp->clock); + } + + kfree(ptp); + adapter->ptp = NULL; +} diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.h b/drivers/net/ethernet/intel/idpf/idpf_ptp.h new file mode 100644 index 000000000000..a876749d6116 --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.h @@ -0,0 +1,362 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2024 Intel Corporation */ + +#ifndef _IDPF_PTP_H +#define _IDPF_PTP_H + +#include <linux/ptp_clock_kernel.h> + +/** + * struct idpf_ptp_cmd - PTP command masks + * @exec_cmd_mask: mask to trigger command execution + * @shtime_enable_mask: mask to enable shadow time + */ +struct idpf_ptp_cmd { + u32 exec_cmd_mask; + u32 shtime_enable_mask; +}; + +/* struct idpf_ptp_dev_clk_regs - PTP device registers + * @dev_clk_ns_l: low part of the device clock register + * @dev_clk_ns_h: high part of the device clock register + * @phy_clk_ns_l: low part of the PHY clock register + * @phy_clk_ns_h: high part of the PHY clock register + * @incval_l: low part of the increment value register + * @incval_h: high part of the increment value register + * @shadj_l: low part of the shadow adjust register + * @shadj_h: high part of the shadow adjust register + * @phy_incval_l: low part of the PHY increment value register + * @phy_incval_h: high part of the PHY increment value register + * @phy_shadj_l: low part of the PHY shadow adjust register + * @phy_shadj_h: high part of the PHY shadow adjust register + * @cmd: PTP command register + * @phy_cmd: PHY command register + * @cmd_sync: PTP command synchronization register + */ +struct idpf_ptp_dev_clk_regs { + /* Main clock */ + void __iomem *dev_clk_ns_l; + void __iomem *dev_clk_ns_h; + + /* PHY timer */ + void __iomem *phy_clk_ns_l; + void __iomem *phy_clk_ns_h; + + /* Main timer adjustments */ + void __iomem *incval_l; + void __iomem *incval_h; + void __iomem *shadj_l; + void __iomem *shadj_h; + + /* PHY timer adjustments */ + void __iomem *phy_incval_l; + void __iomem *phy_incval_h; + void __iomem *phy_shadj_l; + void __iomem *phy_shadj_h; + + /* Command */ + void __iomem *cmd; + void __iomem *phy_cmd; + void __iomem *cmd_sync; +}; + +/** + * enum idpf_ptp_access - the type of access to PTP operations + * @IDPF_PTP_NONE: no access + * @IDPF_PTP_DIRECT: direct access through BAR registers + * @IDPF_PTP_MAILBOX: access through mailbox messages + */ +enum idpf_ptp_access { + IDPF_PTP_NONE = 0, + IDPF_PTP_DIRECT, + IDPF_PTP_MAILBOX, +}; + +/** + * struct idpf_ptp_secondary_mbx - PTP secondary mailbox + * @peer_mbx_q_id: PTP mailbox queue ID + * @peer_id: Peer ID for PTP Device Control daemon + * @valid: indicates whether secondary mailblox is supported by the Control + * Plane + */ +struct idpf_ptp_secondary_mbx { + u16 peer_mbx_q_id; + u16 peer_id; + bool valid:1; +}; + +/** + * enum idpf_ptp_tx_tstamp_state - Tx timestamp states + * @IDPF_PTP_FREE: Tx timestamp index free to use + * @IDPF_PTP_REQUEST: Tx timestamp index set to the Tx descriptor + * @IDPF_PTP_READ_VALUE: Tx timestamp value ready to be read + */ +enum idpf_ptp_tx_tstamp_state { + IDPF_PTP_FREE, + IDPF_PTP_REQUEST, + IDPF_PTP_READ_VALUE, +}; + +/** + * struct idpf_ptp_tx_tstamp_status - Parameters to track Tx timestamp + * @skb: the pointer to the SKB that received the completion tag + * @state: the state of the Tx timestamp + */ +struct idpf_ptp_tx_tstamp_status { + struct sk_buff *skb; + enum idpf_ptp_tx_tstamp_state state; +}; + +/** + * struct idpf_ptp_tx_tstamp - Parameters for Tx timestamping + * @list_member: the list member structure + * @tx_latch_reg_offset_l: Tx tstamp latch low register offset + * @tx_latch_reg_offset_h: Tx tstamp latch high register offset + * @skb: the pointer to the SKB for this timestamp request + * @tstamp: the Tx tstamp value + * @idx: the index of the Tx tstamp + */ +struct idpf_ptp_tx_tstamp { + struct list_head list_member; + u32 tx_latch_reg_offset_l; + u32 tx_latch_reg_offset_h; + struct sk_buff *skb; + u64 tstamp; + u32 idx; +}; + +/** + * struct idpf_ptp_vport_tx_tstamp_caps - Tx timestamp capabilities + * @vport_id: the vport id + * @num_entries: the number of negotiated Tx timestamp entries + * @tstamp_ns_lo_bit: first bit for nanosecond part of the timestamp + * @latches_lock: the lock to the lists of free/used timestamp indexes + * @status_lock: the lock to the status tracker + * @access: indicates an access to Tx timestamp + * @latches_free: the list of the free Tx timestamps latches + * @latches_in_use: the list of the used Tx timestamps latches + * @tx_tstamp_status: Tx tstamp status tracker + */ +struct idpf_ptp_vport_tx_tstamp_caps { + u32 vport_id; + u16 num_entries; + u16 tstamp_ns_lo_bit; + spinlock_t latches_lock; + spinlock_t status_lock; + bool access:1; + struct list_head latches_free; + struct list_head latches_in_use; + struct idpf_ptp_tx_tstamp_status tx_tstamp_status[]; +}; + +/** + * struct idpf_ptp - PTP parameters + * @info: structure defining PTP hardware capabilities + * @clock: pointer to registered PTP clock device + * @adapter: back pointer to the adapter + * @base_incval: base increment value of the PTP clock + * @max_adj: maximum adjustment of the PTP clock + * @cmd: HW specific command masks + * @cached_phc_time: a cached copy of the PHC time for timestamp extension + * @cached_phc_jiffies: jiffies when cached_phc_time was last updated + * @dev_clk_regs: the set of registers to access the device clock + * @caps: PTP capabilities negotiated with the Control Plane + * @get_dev_clk_time_access: access type for getting the device clock time + * @set_dev_clk_time_access: access type for setting the device clock time + * @adj_dev_clk_time_access: access type for the adjusting the device clock + * @tx_tstamp_access: access type for the Tx timestamp value read + * @rsv: reserved bits + * @secondary_mbx: parameters for using dedicated PTP mailbox + * @read_dev_clk_lock: spinlock protecting access to the device clock read + * operation executed by the HW latch + */ +struct idpf_ptp { + struct ptp_clock_info info; + struct ptp_clock *clock; + struct idpf_adapter *adapter; + u64 base_incval; + u64 max_adj; + struct idpf_ptp_cmd cmd; + u64 cached_phc_time; + unsigned long cached_phc_jiffies; + struct idpf_ptp_dev_clk_regs dev_clk_regs; + u32 caps; + enum idpf_ptp_access get_dev_clk_time_access:2; + enum idpf_ptp_access set_dev_clk_time_access:2; + enum idpf_ptp_access adj_dev_clk_time_access:2; + enum idpf_ptp_access tx_tstamp_access:2; + u8 rsv; + struct idpf_ptp_secondary_mbx secondary_mbx; + spinlock_t read_dev_clk_lock; +}; + +/** + * idpf_ptp_info_to_adapter - get driver adapter struct from ptp_clock_info + * @info: pointer to ptp_clock_info struct + * + * Return: pointer to the corresponding adapter struct + */ +static inline struct idpf_adapter * +idpf_ptp_info_to_adapter(const struct ptp_clock_info *info) +{ + const struct idpf_ptp *ptp = container_of_const(info, struct idpf_ptp, + info); + return ptp->adapter; +} + +/** + * struct idpf_ptp_dev_timers - System time and device time values + * @sys_time_ns: system time value expressed in nanoseconds + * @dev_clk_time_ns: device clock time value expressed in nanoseconds + */ +struct idpf_ptp_dev_timers { + u64 sys_time_ns; + u64 dev_clk_time_ns; +}; + +/** + * idpf_ptp_is_vport_tx_tstamp_ena - Verify the Tx timestamping enablement for + * a given vport. + * @vport: Virtual port structure + * + * Tx timestamp capabilities are negotiated with the Control Plane only if the + * device clock value can be read, Tx timestamp access type is different than + * NONE, and the PTP clock for the adapter is created. When all those conditions + * are satisfied, Tx timestamp feature is enabled and tx_tstamp_caps is + * allocated and fulfilled. + * + * Return: true if the Tx timestamping is enabled, false otherwise. + */ +static inline bool idpf_ptp_is_vport_tx_tstamp_ena(struct idpf_vport *vport) +{ + if (!vport->tx_tstamp_caps) + return false; + else + return true; +} + +/** + * idpf_ptp_is_vport_rx_tstamp_ena - Verify the Rx timestamping enablement for + * a given vport. + * @vport: Virtual port structure + * + * Rx timestamp feature is enabled if the PTP clock for the adapter is created + * and it is possible to read the value of the device clock. The second + * assumption comes from the need to extend the Rx timestamp value to 64 bit + * based on the current device clock time. + * + * Return: true if the Rx timestamping is enabled, false otherwise. + */ +static inline bool idpf_ptp_is_vport_rx_tstamp_ena(struct idpf_vport *vport) +{ + if (!vport->adapter->ptp || + vport->adapter->ptp->get_dev_clk_time_access == IDPF_PTP_NONE) + return false; + else + return true; +} + +#if IS_ENABLED(CONFIG_PTP_1588_CLOCK) +int idpf_ptp_init(struct idpf_adapter *adapter); +void idpf_ptp_release(struct idpf_adapter *adapter); +int idpf_ptp_get_caps(struct idpf_adapter *adapter); +void idpf_ptp_get_features_access(const struct idpf_adapter *adapter); +bool idpf_ptp_get_txq_tstamp_capability(struct idpf_tx_queue *txq); +int idpf_ptp_get_dev_clk_time(struct idpf_adapter *adapter, + struct idpf_ptp_dev_timers *dev_clk_time); +int idpf_ptp_set_dev_clk_time(struct idpf_adapter *adapter, u64 time); +int idpf_ptp_adj_dev_clk_fine(struct idpf_adapter *adapter, u64 incval); +int idpf_ptp_adj_dev_clk_time(struct idpf_adapter *adapter, s64 delta); +int idpf_ptp_get_vport_tstamps_caps(struct idpf_vport *vport); +int idpf_ptp_get_tx_tstamp(struct idpf_vport *vport); +int idpf_ptp_set_timestamp_mode(struct idpf_vport *vport, + struct kernel_hwtstamp_config *config); +u64 idpf_ptp_extend_ts(struct idpf_vport *vport, u64 in_tstamp); +u64 idpf_ptp_tstamp_extend_32b_to_64b(u64 cached_phc_time, u32 in_timestamp); +int idpf_ptp_request_ts(struct idpf_tx_queue *tx_q, struct sk_buff *skb, + u32 *idx); +void idpf_tstamp_task(struct work_struct *work); +#else /* CONFIG_PTP_1588_CLOCK */ +static inline int idpf_ptp_init(struct idpf_adapter *adapter) +{ + return 0; +} + +static inline void idpf_ptp_release(struct idpf_adapter *adapter) { } + +static inline int idpf_ptp_get_caps(struct idpf_adapter *adapter) +{ + return -EOPNOTSUPP; +} + +static inline void +idpf_ptp_get_features_access(const struct idpf_adapter *adapter) { } + +static inline bool +idpf_ptp_get_txq_tstamp_capability(struct idpf_tx_queue *txq) +{ + return false; +} + +static inline int +idpf_ptp_get_dev_clk_time(struct idpf_adapter *adapter, + struct idpf_ptp_dev_timers *dev_clk_time) +{ + return -EOPNOTSUPP; +} + +static inline int idpf_ptp_set_dev_clk_time(struct idpf_adapter *adapter, + u64 time) +{ + return -EOPNOTSUPP; +} + +static inline int idpf_ptp_adj_dev_clk_fine(struct idpf_adapter *adapter, + u64 incval) +{ + return -EOPNOTSUPP; +} + +static inline int idpf_ptp_adj_dev_clk_time(struct idpf_adapter *adapter, + s64 delta) +{ + return -EOPNOTSUPP; +} + +static inline int idpf_ptp_get_vport_tstamps_caps(struct idpf_vport *vport) +{ + return -EOPNOTSUPP; +} + +static inline int idpf_ptp_get_tx_tstamp(struct idpf_vport *vport) +{ + return -EOPNOTSUPP; +} + +static inline int +idpf_ptp_set_timestamp_mode(struct idpf_vport *vport, + struct kernel_hwtstamp_config *config) +{ + return -EOPNOTSUPP; +} + +static inline u64 idpf_ptp_extend_ts(struct idpf_vport *vport, u32 in_tstamp) +{ + return 0; +} + +static inline u64 idpf_ptp_tstamp_extend_32b_to_64b(u64 cached_phc_time, + u32 in_timestamp) +{ + return 0; +} + +static inline int idpf_ptp_request_ts(struct idpf_tx_queue *tx_q, + struct sk_buff *skb, u32 *idx) +{ + return -EOPNOTSUPP; +} + +static inline void idpf_tstamp_task(struct work_struct *work) { } +#endif /* CONFIG_PTP_1588_CLOCK */ +#endif /* _IDPF_PTP_H */ diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c index 27b93592c4ba..2e356dd10812 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c @@ -1,6 +1,9 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2023 Intel Corporation */ +#include <net/libeth/rx.h> +#include <net/libeth/tx.h> + #include "idpf.h" /** @@ -186,7 +189,7 @@ static int idpf_tx_singleq_csum(struct sk_buff *skb, * 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, +static void idpf_tx_singleq_map(struct idpf_tx_queue *tx_q, struct idpf_tx_buf *first, struct idpf_tx_offload_params *offloads) { @@ -205,12 +208,12 @@ static void idpf_tx_singleq_map(struct idpf_queue *tx_q, data_len = skb->data_len; size = skb_headlen(skb); - tx_desc = IDPF_BASE_TX_DESC(tx_q, i); + tx_desc = &tx_q->base_tx[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) + if (idpf_queue_has(CRC_EN, tx_q)) td_cmd |= IDPF_TX_DESC_CMD_ICRC; for (frag = &skb_shinfo(skb)->frags[0];; frag++) { @@ -222,6 +225,7 @@ static void idpf_tx_singleq_map(struct idpf_queue *tx_q, /* record length, and DMA address */ dma_unmap_len_set(tx_buf, len, size); dma_unmap_addr_set(tx_buf, dma, dma); + tx_buf->type = LIBETH_SQE_FRAG; /* align size to end of page */ max_data += -dma & (IDPF_TX_MAX_READ_REQ_SIZE - 1); @@ -235,14 +239,17 @@ static void idpf_tx_singleq_map(struct idpf_queue *tx_q, offsets, max_data, td_tag); - tx_desc++; - i++; - - if (i == tx_q->desc_count) { - tx_desc = IDPF_BASE_TX_DESC(tx_q, 0); + if (unlikely(++i == tx_q->desc_count)) { + tx_buf = &tx_q->tx_buf[0]; + tx_desc = &tx_q->base_tx[0]; i = 0; + } else { + tx_buf++; + tx_desc++; } + tx_buf->type = LIBETH_SQE_EMPTY; + dma += max_data; size -= max_data; @@ -255,12 +262,14 @@ static void idpf_tx_singleq_map(struct idpf_queue *tx_q, 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); + if (unlikely(++i == tx_q->desc_count)) { + tx_buf = &tx_q->tx_buf[0]; + tx_desc = &tx_q->base_tx[0]; i = 0; + } else { + tx_buf++; + tx_desc++; } size = skb_frag_size(frag); @@ -268,8 +277,6 @@ static void idpf_tx_singleq_map(struct idpf_queue *tx_q, 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); @@ -280,13 +287,13 @@ static void idpf_tx_singleq_map(struct idpf_queue *tx_q, tx_desc->qw1 = idpf_tx_singleq_build_ctob(td_cmd, offsets, size, td_tag); - IDPF_SINGLEQ_BUMP_RING_IDX(tx_q, i); + first->type = LIBETH_SQE_SKB; + first->rs_idx = i; - /* set next_to_watch value indicating a packet is present */ - first->next_to_watch = tx_desc; + IDPF_SINGLEQ_BUMP_RING_IDX(tx_q, i); - nq = netdev_get_tx_queue(tx_q->vport->netdev, tx_q->idx); - netdev_tx_sent_queue(nq, first->bytecount); + nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx); + netdev_tx_sent_queue(nq, first->bytes); idpf_tx_buf_hw_update(tx_q, i, netdev_xmit_more()); } @@ -299,15 +306,14 @@ static void idpf_tx_singleq_map(struct idpf_queue *tx_q, * 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) +idpf_tx_singleq_get_ctx_desc(struct idpf_tx_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; + txq->tx_buf[ntu].type = LIBETH_SQE_CTX; - ctx_desc = IDPF_BASE_TX_CTX_DESC(txq, ntu); + ctx_desc = &txq->base_ctx[ntu]; IDPF_SINGLEQ_BUMP_RING_IDX(txq, ntu); txq->next_to_use = ntu; @@ -320,7 +326,7 @@ idpf_tx_singleq_get_ctx_desc(struct idpf_queue *txq) * @txq: queue to send buffer on * @offload: offload parameter structure **/ -static void idpf_tx_singleq_build_ctx_desc(struct idpf_queue *txq, +static void idpf_tx_singleq_build_ctx_desc(struct idpf_tx_queue *txq, struct idpf_tx_offload_params *offload) { struct idpf_base_tx_ctx_desc *desc = idpf_tx_singleq_get_ctx_desc(txq); @@ -333,7 +339,7 @@ static void idpf_tx_singleq_build_ctx_desc(struct idpf_queue *txq, qw1 |= FIELD_PREP(IDPF_TXD_CTX_QW1_MSS_M, offload->mss); u64_stats_update_begin(&txq->stats_sync); - u64_stats_inc(&txq->q_stats.tx.lso_pkts); + u64_stats_inc(&txq->q_stats.lso_pkts); u64_stats_update_end(&txq->stats_sync); } @@ -351,8 +357,8 @@ static void idpf_tx_singleq_build_ctx_desc(struct idpf_queue *txq, * * 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) +netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb, + struct idpf_tx_queue *tx_q) { struct idpf_tx_offload_params offload = { }; struct idpf_tx_buf *first; @@ -369,6 +375,10 @@ static netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb, IDPF_TX_DESCS_FOR_CTX)) { idpf_tx_buf_hw_update(tx_q, tx_q->next_to_use, false); + u64_stats_update_begin(&tx_q->stats_sync); + u64_stats_inc(&tx_q->q_stats.q_busy); + u64_stats_update_end(&tx_q->stats_sync); + return NETDEV_TX_BUSY; } @@ -394,11 +404,11 @@ static netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb, first->skb = skb; if (tso) { - first->gso_segs = offload.tso_segs; - first->bytecount = skb->len + ((first->gso_segs - 1) * offload.tso_hdr_len); + first->packets = offload.tso_segs; + first->bytes = skb->len + ((first->packets - 1) * offload.tso_hdr_len); } else { - first->bytecount = max_t(unsigned int, skb->len, ETH_ZLEN); - first->gso_segs = 1; + first->bytes = max_t(unsigned int, skb->len, ETH_ZLEN); + first->packets = 1; } idpf_tx_singleq_map(tx_q, first, &offload); @@ -409,53 +419,30 @@ out_drop: } /** - * 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, +static bool idpf_tx_singleq_clean(struct idpf_tx_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 libeth_sq_napi_stats ss = { }; struct idpf_base_tx_desc *tx_desc; + u32 budget = tx_q->clean_budget; s16 ntc = tx_q->next_to_clean; + struct libeth_cq_pp cp = { + .dev = tx_q->dev, + .ss = &ss, + .napi = napi_budget, + }; 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_desc = &tx_q->base_tx[ntc]; tx_buf = &tx_q->tx_buf[ntc]; ntc -= tx_q->desc_count; @@ -467,47 +454,26 @@ static bool idpf_tx_singleq_clean(struct idpf_queue *tx_q, int napi_budget, * 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; + if (unlikely(tx_buf->type <= LIBETH_SQE_CTX)) { + tx_buf->type = LIBETH_SQE_EMPTY; 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) + if (unlikely(tx_buf->type != LIBETH_SQE_SKB)) break; - /* prevent any other reads prior to eop_desc */ + /* prevent any other reads prior to type */ smp_rmb(); + eop_desc = &tx_q->base_tx[tx_buf->rs_idx]; + /* 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); + libeth_tx_complete(tx_buf, &cp); /* unmap remaining buffers */ while (tx_desc != eop_desc) { @@ -517,17 +483,11 @@ static bool idpf_tx_singleq_clean(struct idpf_queue *tx_q, int napi_budget, if (unlikely(!ntc)) { ntc -= tx_q->desc_count; tx_buf = tx_q->tx_buf; - tx_desc = IDPF_BASE_TX_DESC(tx_q, 0); + tx_desc = &tx_q->base_tx[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); - } + libeth_tx_complete(tx_buf, &cp); } /* update budget only if we did something */ @@ -540,27 +500,26 @@ fetch_next_txq_desc: if (unlikely(!ntc)) { ntc -= tx_q->desc_count; tx_buf = tx_q->tx_buf; - tx_desc = IDPF_BASE_TX_DESC(tx_q, 0); + tx_desc = &tx_q->base_tx[0]; } } while (likely(budget)); ntc += tx_q->desc_count; tx_q->next_to_clean = ntc; - *cleaned += total_pkts; + *cleaned += ss.packets; 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_add(&tx_q->q_stats.packets, ss.packets); + u64_stats_add(&tx_q->q_stats.bytes, ss.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); + np = netdev_priv(tx_q->netdev); + nq = netdev_get_tx_queue(tx_q->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, + !netif_carrier_ok(tx_q->netdev); + __netif_txq_completed_wake(nq, ss.packets, ss.bytes, IDPF_DESC_UNUSED(tx_q), IDPF_TX_WAKE_THRESH, dont_wake); @@ -584,7 +543,7 @@ static bool idpf_tx_singleq_clean_all(struct idpf_q_vector *q_vec, int budget, budget_per_q = num_txq ? max(budget / num_txq, 1) : 0; for (i = 0; i < num_txq; i++) { - struct idpf_queue *q; + struct idpf_tx_queue *q; q = q_vec->tx[i]; clean_complete &= idpf_tx_singleq_clean(q, budget_per_q, @@ -614,14 +573,9 @@ static bool idpf_rx_singleq_test_staterr(const union virtchnl2_rx_desc *rx_desc, /** * 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) +static bool idpf_rx_singleq_is_non_eop(const union virtchnl2_rx_desc *rx_desc) { /* 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))) @@ -635,98 +589,82 @@ static bool idpf_rx_singleq_is_non_eop(struct idpf_queue *rxq, * @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 + * @decoded: 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) +static void idpf_rx_singleq_csum(struct idpf_rx_queue *rxq, + struct sk_buff *skb, + struct libeth_rx_csum csum_bits, + struct libeth_rx_pt decoded) { - struct idpf_rx_ptype_decoded decoded; bool ipv4, ipv6; /* check if Rx checksum is enabled */ - if (unlikely(!(rxq->vport->netdev->features & NETIF_F_RXCSUM))) + if (!libeth_rx_pt_has_checksum(rxq->netdev, decoded)) 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))) + if (unlikely(!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); + ipv4 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV4; + ipv6 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV6; /* Check if there were any checksum errors */ - if (unlikely(ipv4 && (csum_bits->ipe || csum_bits->eipe))) + 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)) + 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)) + if (unlikely(csum_bits.l4e)) goto checksum_fail; - if (unlikely(csum_bits->nat && csum_bits->eudpe)) + 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)) + 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) + if (decoded.tunnel_type >= LIBETH_RX_PT_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; - } + skb->ip_summed = CHECKSUM_UNNECESSARY; + return; checksum_fail: u64_stats_update_begin(&rxq->stats_sync); - u64_stats_inc(&rxq->q_stats.rx.hw_csum_err); + u64_stats_inc(&rxq->q_stats.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. + * + * Return: parsed checksum status. **/ -static void idpf_rx_singleq_base_csum(struct idpf_queue *rx_q, - struct sk_buff *skb, - union virtchnl2_rx_desc *rx_desc, - u16 ptype) +static struct libeth_rx_csum +idpf_rx_singleq_base_csum(const union virtchnl2_rx_desc *rx_desc) { - struct idpf_rx_csum_decoded csum_bits; + struct libeth_rx_csum csum_bits = { }; u32 rx_error, rx_status; u64 qword; @@ -745,28 +683,23 @@ static void idpf_rx_singleq_base_csum(struct idpf_queue *rx_q, 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); + return csum_bits; } /** * 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. + * + * Return: parsed checksum status. **/ -static void idpf_rx_singleq_flex_csum(struct idpf_queue *rx_q, - struct sk_buff *skb, - union virtchnl2_rx_desc *rx_desc, - u16 ptype) +static struct libeth_rx_csum +idpf_rx_singleq_flex_csum(const union virtchnl2_rx_desc *rx_desc) { - struct idpf_rx_csum_decoded csum_bits; + struct libeth_rx_csum csum_bits = { }; u16 rx_status0, rx_status1; rx_status0 = le16_to_cpu(rx_desc->flex_nic_wb.status_error0); @@ -786,9 +719,8 @@ static void idpf_rx_singleq_flex_csum(struct idpf_queue *rx_q, 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); + return csum_bits; } /** @@ -801,14 +733,14 @@ static void idpf_rx_singleq_flex_csum(struct idpf_queue *rx_q, * 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, +static void idpf_rx_singleq_base_hash(struct idpf_rx_queue *rx_q, struct sk_buff *skb, - union virtchnl2_rx_desc *rx_desc, - struct idpf_rx_ptype_decoded *decoded) + const union virtchnl2_rx_desc *rx_desc, + struct libeth_rx_pt decoded) { u64 mask, qw1; - if (unlikely(!(rx_q->vport->netdev->features & NETIF_F_RXHASH))) + if (!libeth_rx_pt_has_hash(rx_q->netdev, decoded)) return; mask = VIRTCHNL2_RX_BASE_DESC_FLTSTAT_RSS_HASH_M; @@ -817,7 +749,7 @@ static void idpf_rx_singleq_base_hash(struct idpf_queue *rx_q, 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)); + libeth_rx_pt_set_hash(skb, hash, decoded); } } @@ -831,18 +763,20 @@ static void idpf_rx_singleq_base_hash(struct idpf_queue *rx_q, * 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, +static void idpf_rx_singleq_flex_hash(struct idpf_rx_queue *rx_q, struct sk_buff *skb, - union virtchnl2_rx_desc *rx_desc, - struct idpf_rx_ptype_decoded *decoded) + const union virtchnl2_rx_desc *rx_desc, + struct libeth_rx_pt decoded) { - if (unlikely(!(rx_q->vport->netdev->features & NETIF_F_RXHASH))) + if (!libeth_rx_pt_has_hash(rx_q->netdev, decoded)) 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)); + le16_to_cpu(rx_desc->flex_nic_wb.status_error0))) { + u32 hash = le32_to_cpu(rx_desc->flex_nic_wb.rss_hash); + + libeth_rx_pt_set_hash(skb, hash, decoded); + } } /** @@ -857,25 +791,45 @@ static void idpf_rx_singleq_flex_hash(struct idpf_queue *rx_q, * 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) +static void +idpf_rx_singleq_process_skb_fields(struct idpf_rx_queue *rx_q, + struct sk_buff *skb, + const union virtchnl2_rx_desc *rx_desc, + u16 ptype) { - struct idpf_rx_ptype_decoded decoded = - rx_q->vport->rx_ptype_lkup[ptype]; + struct libeth_rx_pt decoded = rx_q->rx_ptype_lkup[ptype]; + struct libeth_rx_csum csum_bits; /* modifies the skb - consumes the enet header */ - skb->protocol = eth_type_trans(skb, rx_q->vport->netdev); + skb->protocol = eth_type_trans(skb, rx_q->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); + idpf_rx_singleq_base_hash(rx_q, skb, rx_desc, decoded); + csum_bits = idpf_rx_singleq_base_csum(rx_desc); } 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_flex_hash(rx_q, skb, rx_desc, decoded); + csum_bits = idpf_rx_singleq_flex_csum(rx_desc); } + + idpf_rx_singleq_csum(rx_q, skb, csum_bits, decoded); + skb_record_rx_queue(skb, rx_q->idx); +} + +/** + * idpf_rx_buf_hw_update - Store the new tail and head values + * @rxq: queue to bump + * @val: new head index + */ +static void idpf_rx_buf_hw_update(struct idpf_rx_queue *rxq, u32 val) +{ + rxq->next_to_use = val; + + if (unlikely(!rxq->tail)) + return; + + /* writel has an implicit memory barrier */ + writel(val, rxq->tail); } /** @@ -885,24 +839,28 @@ static void idpf_rx_singleq_process_skb_fields(struct idpf_queue *rx_q, * * Returns false if all allocations were successful, true if any fail */ -bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_queue *rx_q, +bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_rx_queue *rx_q, u16 cleaned_count) { struct virtchnl2_singleq_rx_buf_desc *desc; + const struct libeth_fq_fp fq = { + .pp = rx_q->pp, + .fqes = rx_q->rx_buf, + .truesize = rx_q->truesize, + .count = rx_q->desc_count, + }; 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]; + desc = &rx_q->single_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)) + addr = libeth_rx_alloc(&fq, nta); + if (addr == DMA_MAPPING_ERROR) break; /* Refresh the desc even if buffer_addrs didn't change @@ -912,11 +870,9 @@ bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_queue *rx_q, 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; + desc = &rx_q->single_buf[0]; nta = 0; } @@ -933,7 +889,6 @@ bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_queue *rx_q, /** * 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 * @@ -943,21 +898,20 @@ bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_queue *rx_q, * 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) +static void +idpf_rx_singleq_extract_base_fields(const union virtchnl2_rx_desc *rx_desc, + struct libeth_rqe_info *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); + fields->len = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_LEN_PBUF_M, qword); + fields->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 * @@ -967,14 +921,14 @@ static void idpf_rx_singleq_extract_base_fields(struct idpf_queue *rx_q, * 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) +static void +idpf_rx_singleq_extract_flex_fields(const union virtchnl2_rx_desc *rx_desc, + struct libeth_rqe_info *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)); + fields->len = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PKT_LEN_M, + le16_to_cpu(rx_desc->flex_nic_wb.pkt_len)); + fields->ptype = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PTYPE_M, + le16_to_cpu(rx_desc->flex_nic_wb.ptype_flex_flags0)); } /** @@ -984,14 +938,15 @@ static void idpf_rx_singleq_extract_flex_fields(struct idpf_queue *rx_q, * @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) +static void +idpf_rx_singleq_extract_fields(const struct idpf_rx_queue *rx_q, + const union virtchnl2_rx_desc *rx_desc, + struct libeth_rqe_info *fields) { if (rx_q->rxdids == VIRTCHNL2_RXDID_1_32B_BASE_M) - idpf_rx_singleq_extract_base_fields(rx_q, rx_desc, fields); + idpf_rx_singleq_extract_base_fields(rx_desc, fields); else - idpf_rx_singleq_extract_flex_fields(rx_q, rx_desc, fields); + idpf_rx_singleq_extract_flex_fields(rx_desc, fields); } /** @@ -1001,7 +956,7 @@ static void idpf_rx_singleq_extract_fields(struct idpf_queue *rx_q, * * 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) +static int idpf_rx_singleq_clean(struct idpf_rx_queue *rx_q, int budget) { unsigned int total_rx_bytes = 0, total_rx_pkts = 0; struct sk_buff *skb = rx_q->skb; @@ -1011,12 +966,12 @@ static int idpf_rx_singleq_clean(struct idpf_queue *rx_q, int budget) /* Process Rx packets bounded by budget */ while (likely(total_rx_pkts < (unsigned int)budget)) { - struct idpf_rx_extracted fields = { }; + struct libeth_rqe_info 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); + rx_desc = &rx_q->rx[ntc]; /* status_error_ptype_len will always be zero for unused * descriptors because it's cleared in cleanup, and overlaps @@ -1036,29 +991,27 @@ static int idpf_rx_singleq_clean(struct idpf_queue *rx_q, int budget) 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); + rx_buf = &rx_q->rx_buf[ntc]; + if (!libeth_rx_sync_for_cpu(rx_buf, fields.len)) goto skip_data; - } - idpf_rx_sync_for_cpu(rx_buf, fields.size); if (skb) - idpf_rx_add_frag(rx_buf, skb, fields.size); + idpf_rx_add_frag(rx_buf, skb, fields.len); else - skb = idpf_rx_construct_skb(rx_q, rx_buf, fields.size); + skb = idpf_rx_build_skb(rx_buf, fields.len); /* exit if we failed to retrieve a buffer */ if (!skb) break; skip_data: - IDPF_SINGLEQ_BUMP_RING_IDX(rx_q, ntc); + rx_buf->page = NULL; + 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)) + if (idpf_rx_singleq_is_non_eop(rx_desc) || unlikely(!skb)) continue; #define IDPF_RXD_ERR_S FIELD_PREP(VIRTCHNL2_RX_BASE_DESC_QW1_ERROR_M, \ @@ -1080,11 +1033,11 @@ skip_data: total_rx_bytes += skb->len; /* protocol */ - idpf_rx_singleq_process_skb_fields(rx_q, skb, - rx_desc, fields.rx_ptype); + idpf_rx_singleq_process_skb_fields(rx_q, skb, rx_desc, + fields.ptype); /* send completed skb up the stack */ - napi_gro_receive(&rx_q->q_vector->napi, skb); + napi_gro_receive(rx_q->pp->p.napi, skb); skb = NULL; /* update budget accounting */ @@ -1095,12 +1048,13 @@ skip_data: rx_q->next_to_clean = ntc; + page_pool_nid_changed(rx_q->pp, numa_mem_id()); 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_add(&rx_q->q_stats.packets, total_rx_pkts); + u64_stats_add(&rx_q->q_stats.bytes, total_rx_bytes); u64_stats_update_end(&rx_q->stats_sync); /* guarantee a trip back through this routine if there was a failure */ @@ -1127,7 +1081,7 @@ static bool idpf_rx_singleq_clean_all(struct idpf_q_vector *q_vec, int budget, */ 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]; + struct idpf_rx_queue *rxq = q_vec->rx[i]; int pkts_cleaned_per_q; pkts_cleaned_per_q = idpf_rx_singleq_clean(rxq, budget_per_q); @@ -1166,8 +1120,10 @@ int idpf_vport_singleq_napi_poll(struct napi_struct *napi, int budget) &work_done); /* If work not completed, return budget and polling will return */ - if (!clean_complete) + if (!clean_complete) { + idpf_vport_intr_set_wb_on_itr(q_vector); return budget; + } work_done = min_t(int, work_done, budget - 1); @@ -1176,6 +1132,8 @@ int idpf_vport_singleq_napi_poll(struct napi_struct *napi, int budget) */ if (likely(napi_complete_done(napi, work_done))) idpf_vport_intr_update_itr_ena_irq(q_vector); + else + idpf_vport_intr_set_wb_on_itr(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 index f5bc4a278074..631679cdaa6f 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -1,9 +1,24 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2023 Intel Corporation */ +#include <net/libeth/rx.h> +#include <net/libeth/tx.h> + #include "idpf.h" +#include "idpf_ptp.h" #include "idpf_virtchnl.h" +struct idpf_tx_stash { + struct hlist_node hlist; + struct libeth_sqe buf; +}; + +#define idpf_tx_buf_compl_tag(buf) (*(u32 *)&(buf)->priv) +LIBETH_SQE_CHECK_PRIV(u32); + +static bool idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs, + unsigned int count); + /** * idpf_buf_lifo_push - push a buffer pointer onto stack * @stack: pointer to stack struct @@ -56,39 +71,20 @@ void idpf_tx_timeout(struct net_device *netdev, unsigned int txqueue) } /** - * 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) +static void idpf_tx_buf_rel_all(struct idpf_tx_queue *txq) { - u16 i; + struct libeth_sq_napi_stats ss = { }; + struct idpf_buf_lifo *buf_stack; + struct idpf_tx_stash *stash; + struct libeth_cq_pp cp = { + .dev = txq->dev, + .ss = &ss, + }; + struct hlist_node *tmp; + u32 i, tag; /* Buffers already cleared, nothing to do */ if (!txq->tx_buf) @@ -96,44 +92,78 @@ static void idpf_tx_buf_rel_all(struct idpf_queue *txq) /* Free all the Tx buffer sk_buffs */ for (i = 0; i < txq->desc_count; i++) - idpf_tx_buf_rel(txq, &txq->tx_buf[i]); + libeth_tx_complete(&txq->tx_buf[i], &cp); kfree(txq->tx_buf); txq->tx_buf = NULL; - if (!txq->buf_stack.bufs) + if (!idpf_queue_has(FLOW_SCH_EN, txq)) return; - for (i = 0; i < txq->buf_stack.size; i++) - kfree(txq->buf_stack.bufs[i]); + buf_stack = &txq->stash->buf_stack; + if (!buf_stack->bufs) + return; - kfree(txq->buf_stack.bufs); - txq->buf_stack.bufs = NULL; + /* + * If a Tx timeout occurred, there are potentially still bufs in the + * hash table, free them here. + */ + hash_for_each_safe(txq->stash->sched_buf_hash, tag, tmp, stash, + hlist) { + if (!stash) + continue; + + libeth_tx_complete(&stash->buf, &cp); + hash_del(&stash->hlist); + idpf_buf_lifo_push(buf_stack, stash); + } + + for (i = 0; i < buf_stack->size; i++) + kfree(buf_stack->bufs[i]); + + kfree(buf_stack->bufs); + 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) +static void idpf_tx_desc_rel(struct idpf_tx_queue *txq) { - if (bufq) - idpf_tx_buf_rel_all(txq); + idpf_tx_buf_rel_all(txq); + netdev_tx_reset_subqueue(txq->netdev, txq->idx); 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_compl_desc_rel - Free completion resources per queue + * @complq: completion queue + * + * Free all completion software resources. + */ +static void idpf_compl_desc_rel(struct idpf_compl_queue *complq) +{ + if (!complq->comp) + return; + + dma_free_coherent(complq->netdev->dev.parent, complq->size, + complq->comp, complq->dma); + complq->comp = NULL; + complq->next_to_use = 0; + complq->next_to_clean = 0; +} + +/** * idpf_tx_desc_rel_all - Free Tx Resources for All Queues * @vport: virtual port structure * @@ -150,10 +180,10 @@ static void idpf_tx_desc_rel_all(struct idpf_vport *vport) 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); + idpf_tx_desc_rel(txq_grp->txqs[j]); if (idpf_is_queue_model_split(vport->txq_model)) - idpf_tx_desc_rel(txq_grp->complq, false); + idpf_compl_desc_rel(txq_grp->complq); } } @@ -163,8 +193,9 @@ static void idpf_tx_desc_rel_all(struct idpf_vport *vport) * * Returns 0 on success, negative on failure */ -static int idpf_tx_buf_alloc_all(struct idpf_queue *tx_q) +static int idpf_tx_buf_alloc_all(struct idpf_tx_queue *tx_q) { + struct idpf_buf_lifo *buf_stack; int buf_size; int i; @@ -176,26 +207,26 @@ static int idpf_tx_buf_alloc_all(struct idpf_queue *tx_q) 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; + if (!idpf_queue_has(FLOW_SCH_EN, tx_q)) + return 0; + + buf_stack = &tx_q->stash->buf_stack; /* 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) + buf_stack->bufs = kcalloc(tx_q->desc_count, sizeof(*buf_stack->bufs), + GFP_KERNEL); + if (!buf_stack->bufs) return -ENOMEM; - tx_q->buf_stack.size = tx_q->desc_count; - tx_q->buf_stack.top = tx_q->desc_count; + buf_stack->size = tx_q->desc_count; + 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]) + buf_stack->bufs[i] = kzalloc(sizeof(*buf_stack->bufs[i]), + GFP_KERNEL); + if (!buf_stack->bufs[i]) return -ENOMEM; } @@ -204,28 +235,22 @@ static int idpf_tx_buf_alloc_all(struct idpf_queue *tx_q) /** * idpf_tx_desc_alloc - Allocate the Tx descriptors + * @vport: vport to allocate resources for * @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) +static int idpf_tx_desc_alloc(const struct idpf_vport *vport, + struct idpf_tx_queue *tx_q) { 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); - } + err = idpf_tx_buf_alloc_all(tx_q); + if (err) + goto err_alloc; - tx_q->size = tx_q->desc_count * desc_sz; + tx_q->size = tx_q->desc_count * sizeof(*tx_q->base_tx); /* Allocate descriptors also round up to nearest 4K */ tx_q->size = ALIGN(tx_q->size, 4096); @@ -238,20 +263,44 @@ static int idpf_tx_desc_alloc(struct idpf_queue *tx_q, bool bufq) 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); + idpf_queue_set(GEN_CHK, tx_q); return 0; err_alloc: - idpf_tx_desc_rel(tx_q, bufq); + idpf_tx_desc_rel(tx_q); return err; } /** + * idpf_compl_desc_alloc - allocate completion descriptors + * @vport: vport to allocate resources for + * @complq: completion queue to set up + * + * Return: 0 on success, -errno on failure. + */ +static int idpf_compl_desc_alloc(const struct idpf_vport *vport, + struct idpf_compl_queue *complq) +{ + complq->size = array_size(complq->desc_count, sizeof(*complq->comp)); + + complq->comp = dma_alloc_coherent(complq->netdev->dev.parent, + complq->size, &complq->dma, + GFP_KERNEL); + if (!complq->comp) + return -ENOMEM; + + complq->next_to_use = 0; + complq->next_to_clean = 0; + idpf_queue_set(GEN_CHK, complq); + + return 0; +} + +/** * idpf_tx_desc_alloc_all - allocate all queues Tx resources * @vport: virtual port private structure * @@ -259,7 +308,6 @@ err_alloc: */ static int idpf_tx_desc_alloc_all(struct idpf_vport *vport) { - struct device *dev = &vport->adapter->pdev->dev; int err = 0; int i, j; @@ -268,13 +316,14 @@ static int idpf_tx_desc_alloc_all(struct idpf_vport *vport) */ 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]; + struct idpf_tx_queue *txq = vport->txq_grps[i].txqs[j]; u8 gen_bits = 0; u16 bufidx_mask; - err = idpf_tx_desc_alloc(txq, true); + err = idpf_tx_desc_alloc(vport, txq); if (err) { - dev_err(dev, "Allocation for Tx Queue %u failed\n", + pci_err(vport->adapter->pdev, + "Allocation for Tx Queue %u failed\n", i); goto err_out; } @@ -312,9 +361,10 @@ static int idpf_tx_desc_alloc_all(struct idpf_vport *vport) continue; /* Setup completion queues */ - err = idpf_tx_desc_alloc(vport->txq_grps[i].complq, false); + err = idpf_compl_desc_alloc(vport, vport->txq_grps[i].complq); if (err) { - dev_err(dev, "Allocation for Tx Completion Queue %u failed\n", + pci_err(vport->adapter->pdev, + "Allocation for Tx Completion Queue %u failed\n", i); goto err_out; } @@ -329,70 +379,97 @@ err_out: /** * 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) +static void idpf_rx_page_rel(struct libeth_fqe *rx_buf) { if (unlikely(!rx_buf->page)) return; - page_pool_put_full_page(rxq->pp, rx_buf->page, false); + page_pool_put_full_page(rx_buf->page->pp, rx_buf->page, false); rx_buf->page = NULL; - rx_buf->page_offset = 0; + rx_buf->offset = 0; } /** * idpf_rx_hdr_buf_rel_all - Release header buffer memory - * @rxq: queue to use + * @bufq: queue to use */ -static void idpf_rx_hdr_buf_rel_all(struct idpf_queue *rxq) +static void idpf_rx_hdr_buf_rel_all(struct idpf_buf_queue *bufq) { - struct idpf_adapter *adapter = rxq->vport->adapter; + struct libeth_fq fq = { + .fqes = bufq->hdr_buf, + .pp = bufq->hdr_pp, + }; - 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; + for (u32 i = 0; i < bufq->desc_count; i++) + idpf_rx_page_rel(&bufq->hdr_buf[i]); + + libeth_rx_fq_destroy(&fq); + bufq->hdr_buf = NULL; + bufq->hdr_pp = NULL; } /** - * idpf_rx_buf_rel_all - Free all Rx buffer resources for a queue - * @rxq: queue to be cleaned + * idpf_rx_buf_rel_bufq - Free all Rx buffer resources for a buffer queue + * @bufq: queue to be cleaned */ -static void idpf_rx_buf_rel_all(struct idpf_queue *rxq) +static void idpf_rx_buf_rel_bufq(struct idpf_buf_queue *bufq) { - u16 i; + struct libeth_fq fq = { + .fqes = bufq->buf, + .pp = bufq->pp, + }; /* queue already cleared, nothing to do */ - if (!rxq->rx_buf.buf) + if (!bufq->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]); + for (u32 i = 0; i < bufq->desc_count; i++) + idpf_rx_page_rel(&bufq->buf[i]); - if (rxq->rx_hsplit_en) - idpf_rx_hdr_buf_rel_all(rxq); + if (idpf_queue_has(HSPLIT_EN, bufq)) + idpf_rx_hdr_buf_rel_all(bufq); - page_pool_destroy(rxq->pp); - rxq->pp = NULL; + libeth_rx_fq_destroy(&fq); + bufq->buf = NULL; + bufq->pp = NULL; +} - kfree(rxq->rx_buf.buf); - rxq->rx_buf.buf = NULL; +/** + * idpf_rx_buf_rel_all - Free all Rx buffer resources for a receive queue + * @rxq: queue to be cleaned + */ +static void idpf_rx_buf_rel_all(struct idpf_rx_queue *rxq) +{ + struct libeth_fq fq = { + .fqes = rxq->rx_buf, + .pp = rxq->pp, + }; + + if (!rxq->rx_buf) + return; + + for (u32 i = 0; i < rxq->desc_count; i++) + idpf_rx_page_rel(&rxq->rx_buf[i]); + + libeth_rx_fq_destroy(&fq); + rxq->rx_buf = NULL; + rxq->pp = 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 + * @dev: device to free DMA memory + * @model: single or split queue model * * Free a specific rx queue resources */ -static void idpf_rx_desc_rel(struct idpf_queue *rxq, bool bufq, s32 q_model) +static void idpf_rx_desc_rel(struct idpf_rx_queue *rxq, struct device *dev, + u32 model) { if (!rxq) return; @@ -402,7 +479,7 @@ static void idpf_rx_desc_rel(struct idpf_queue *rxq, bool bufq, s32 q_model) rxq->skb = NULL; } - if (bufq || !idpf_is_queue_model_split(q_model)) + if (!idpf_is_queue_model_split(model)) idpf_rx_buf_rel_all(rxq); rxq->next_to_alloc = 0; @@ -411,11 +488,35 @@ static void idpf_rx_desc_rel(struct idpf_queue *rxq, bool bufq, s32 q_model) if (!rxq->desc_ring) return; - dmam_free_coherent(rxq->dev, rxq->size, rxq->desc_ring, rxq->dma); + dmam_free_coherent(dev, rxq->size, rxq->desc_ring, rxq->dma); rxq->desc_ring = NULL; } /** + * idpf_rx_desc_rel_bufq - free buffer queue resources + * @bufq: buffer queue to clean the resources from + * @dev: device to free DMA memory + */ +static void idpf_rx_desc_rel_bufq(struct idpf_buf_queue *bufq, + struct device *dev) +{ + if (!bufq) + return; + + idpf_rx_buf_rel_bufq(bufq); + + bufq->next_to_alloc = 0; + bufq->next_to_clean = 0; + bufq->next_to_use = 0; + + if (!bufq->split_buf) + return; + + dma_free_coherent(dev, bufq->size, bufq->split_buf, bufq->dma); + bufq->split_buf = NULL; +} + +/** * idpf_rx_desc_rel_all - Free Rx Resources for All Queues * @vport: virtual port structure * @@ -423,6 +524,7 @@ static void idpf_rx_desc_rel(struct idpf_queue *rxq, bool bufq, s32 q_model) */ static void idpf_rx_desc_rel_all(struct idpf_vport *vport) { + struct device *dev = &vport->adapter->pdev->dev; struct idpf_rxq_group *rx_qgrp; u16 num_rxq; int i, j; @@ -435,15 +537,15 @@ static void idpf_rx_desc_rel_all(struct idpf_vport *vport) 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); + idpf_rx_desc_rel(rx_qgrp->singleq.rxqs[j], dev, + VIRTCHNL2_QUEUE_MODEL_SINGLE); 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); + dev, VIRTCHNL2_QUEUE_MODEL_SPLIT); if (!rx_qgrp->splitq.bufq_sets) continue; @@ -452,45 +554,50 @@ static void idpf_rx_desc_rel_all(struct idpf_vport *vport) 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_desc_rel_bufq(&bufq_set->bufq, dev); } } } /** * idpf_rx_buf_hw_update - Store the new tail and head values - * @rxq: queue to bump + * @bufq: queue to bump * @val: new head index */ -void idpf_rx_buf_hw_update(struct idpf_queue *rxq, u32 val) +static void idpf_rx_buf_hw_update(struct idpf_buf_queue *bufq, u32 val) { - rxq->next_to_use = val; + bufq->next_to_use = val; - if (unlikely(!rxq->tail)) + if (unlikely(!bufq->tail)) return; /* writel has an implicit memory barrier */ - writel(val, rxq->tail); + writel(val, bufq->tail); } /** * idpf_rx_hdr_buf_alloc_all - Allocate memory for header buffers - * @rxq: ring to use + * @bufq: ring to use * * Returns 0 on success, negative on failure. */ -static int idpf_rx_hdr_buf_alloc_all(struct idpf_queue *rxq) +static int idpf_rx_hdr_buf_alloc_all(struct idpf_buf_queue *bufq) { - 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; + struct libeth_fq fq = { + .count = bufq->desc_count, + .type = LIBETH_FQE_HDR, + .nid = idpf_q_vector_to_mem(bufq->q_vector), + }; + int ret; + + ret = libeth_rx_fq_create(&fq, &bufq->q_vector->napi); + if (ret) + return ret; + + bufq->hdr_pp = fq.pp; + bufq->hdr_buf = fq.fqes; + bufq->hdr_truesize = fq.truesize; + bufq->rx_hbuf_size = fq.buf_len; return 0; } @@ -502,19 +609,20 @@ static int idpf_rx_hdr_buf_alloc_all(struct idpf_queue *rxq) */ static void idpf_rx_post_buf_refill(struct idpf_sw_queue *refillq, u16 buf_id) { - u16 nta = refillq->next_to_alloc; + u32 nta = refillq->next_to_use; /* store the buffer ID and the SW maintained GEN bit to the refillq */ refillq->ring[nta] = FIELD_PREP(IDPF_RX_BI_BUFID_M, buf_id) | FIELD_PREP(IDPF_RX_BI_GEN_M, - test_bit(__IDPF_Q_GEN_CHK, refillq->flags)); + idpf_queue_has(GEN_CHK, refillq)); if (unlikely(++nta == refillq->desc_count)) { nta = 0; - change_bit(__IDPF_Q_GEN_CHK, refillq->flags); + idpf_queue_change(GEN_CHK, refillq); } - refillq->next_to_alloc = nta; + + refillq->next_to_use = nta; } /** @@ -524,24 +632,35 @@ static void idpf_rx_post_buf_refill(struct idpf_sw_queue *refillq, u16 buf_id) * * Returns false if buffer could not be allocated, true otherwise. */ -static bool idpf_rx_post_buf_desc(struct idpf_queue *bufq, u16 buf_id) +static bool idpf_rx_post_buf_desc(struct idpf_buf_queue *bufq, u16 buf_id) { struct virtchnl2_splitq_rx_buf_desc *splitq_rx_desc = NULL; + struct libeth_fq_fp fq = { + .count = bufq->desc_count, + }; 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]; + splitq_rx_desc = &bufq->split_buf[nta]; + + if (idpf_queue_has(HSPLIT_EN, bufq)) { + fq.pp = bufq->hdr_pp; + fq.fqes = bufq->hdr_buf; + fq.truesize = bufq->hdr_truesize; - 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 = libeth_rx_alloc(&fq, buf_id); + if (addr == DMA_MAPPING_ERROR) + return false; + + splitq_rx_desc->hdr_addr = cpu_to_le64(addr); } - addr = idpf_alloc_page(bufq->pp, buf, bufq->rx_buf_size); - if (unlikely(addr == DMA_MAPPING_ERROR)) + fq.pp = bufq->pp; + fq.fqes = bufq->buf; + fq.truesize = bufq->truesize; + + addr = libeth_rx_alloc(&fq, buf_id); + if (addr == DMA_MAPPING_ERROR) return false; splitq_rx_desc->pkt_addr = cpu_to_le64(addr); @@ -562,7 +681,8 @@ static bool idpf_rx_post_buf_desc(struct idpf_queue *bufq, u16 buf_id) * * 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) +static bool idpf_rx_post_init_bufs(struct idpf_buf_queue *bufq, + u16 working_set) { int i; @@ -571,95 +691,114 @@ static bool idpf_rx_post_init_bufs(struct idpf_queue *bufq, u16 working_set) return false; } - idpf_rx_buf_hw_update(bufq, - bufq->next_to_alloc & ~(bufq->rx_buf_stride - 1)); + idpf_rx_buf_hw_update(bufq, ALIGN_DOWN(bufq->next_to_alloc, + IDPF_RX_BUF_STRIDE)); return true; } /** - * idpf_rx_create_page_pool - Create a page pool - * @rxbufq: RX queue to create page pool for + * idpf_rx_buf_alloc_singleq - Allocate memory for all buffer resources + * @rxq: queue for which the buffers are allocated + * + * Return: 0 on success, -ENOMEM on failure. + */ +static int idpf_rx_buf_alloc_singleq(struct idpf_rx_queue *rxq) +{ + if (idpf_rx_singleq_buf_hw_alloc_all(rxq, rxq->desc_count - 1)) + goto err; + + return 0; + +err: + idpf_rx_buf_rel_all(rxq); + + return -ENOMEM; +} + +/** + * idpf_rx_bufs_init_singleq - Initialize page pool and allocate Rx bufs + * @rxq: buffer queue to create page pool for * - * Returns &page_pool on success, casted -errno on failure + * Return: 0 on success, -errno on failure. */ -static struct page_pool *idpf_rx_create_page_pool(struct idpf_queue *rxbufq) +static int idpf_rx_bufs_init_singleq(struct idpf_rx_queue *rxq) { - 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, + struct libeth_fq fq = { + .count = rxq->desc_count, + .type = LIBETH_FQE_MTU, + .nid = idpf_q_vector_to_mem(rxq->q_vector), }; + int ret; + + ret = libeth_rx_fq_create(&fq, &rxq->q_vector->napi); + if (ret) + return ret; - return page_pool_create(&pp); + rxq->pp = fq.pp; + rxq->rx_buf = fq.fqes; + rxq->truesize = fq.truesize; + rxq->rx_buf_size = fq.buf_len; + + return idpf_rx_buf_alloc_singleq(rxq); } /** * 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 + * @rxbufq: queue for which the buffers are allocated * * Returns 0 on success, negative on failure */ -static int idpf_rx_buf_alloc_all(struct idpf_queue *rxbufq) +static int idpf_rx_buf_alloc_all(struct idpf_buf_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) { + if (idpf_queue_has(HSPLIT_EN, rxbufq)) { 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; - } + if (!idpf_rx_post_init_bufs(rxbufq, IDPF_RX_BUFQ_WORKING_SET(rxbufq))) + err = -ENOMEM; rx_buf_alloc_all_out: if (err) - idpf_rx_buf_rel_all(rxbufq); + idpf_rx_buf_rel_bufq(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 + * @bufq: buffer queue to create page pool for + * @type: type of Rx buffers to allocate * * Returns 0 on success, negative on failure */ -static int idpf_rx_bufs_init(struct idpf_queue *rxbufq) +static int idpf_rx_bufs_init(struct idpf_buf_queue *bufq, + enum libeth_fqe_type type) { - struct page_pool *pool; + struct libeth_fq fq = { + .truesize = bufq->truesize, + .count = bufq->desc_count, + .type = type, + .hsplit = idpf_queue_has(HSPLIT_EN, bufq), + .nid = idpf_q_vector_to_mem(bufq->q_vector), + }; + int ret; - pool = idpf_rx_create_page_pool(rxbufq); - if (IS_ERR(pool)) - return PTR_ERR(pool); + ret = libeth_rx_fq_create(&fq, &bufq->q_vector->napi); + if (ret) + return ret; - rxbufq->pp = pool; + bufq->pp = fq.pp; + bufq->buf = fq.fqes; + bufq->truesize = fq.truesize; + bufq->rx_buf_size = fq.buf_len; - return idpf_rx_buf_alloc_all(rxbufq); + return idpf_rx_buf_alloc_all(bufq); } /** @@ -670,20 +809,22 @@ static int idpf_rx_bufs_init(struct idpf_queue *rxbufq) */ int idpf_rx_bufs_init_all(struct idpf_vport *vport) { - struct idpf_rxq_group *rx_qgrp; - struct idpf_queue *q; + bool split = idpf_is_queue_model_split(vport->rxq_model); int i, j, err; for (i = 0; i < vport->num_rxq_grp; i++) { - rx_qgrp = &vport->rxq_grps[i]; + struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i]; + u32 truesize = 0; /* Allocate bufs for the rxq itself in singleq */ - if (!idpf_is_queue_model_split(vport->rxq_model)) { + if (!split) { int num_rxq = rx_qgrp->singleq.num_rxq; for (j = 0; j < num_rxq; j++) { + struct idpf_rx_queue *q; + q = rx_qgrp->singleq.rxqs[j]; - err = idpf_rx_bufs_init(q); + err = idpf_rx_bufs_init_singleq(q); if (err) return err; } @@ -693,10 +834,19 @@ int idpf_rx_bufs_init_all(struct idpf_vport *vport) /* Otherwise, allocate bufs for the buffer queues */ for (j = 0; j < vport->num_bufqs_per_qgrp; j++) { + enum libeth_fqe_type type; + struct idpf_buf_queue *q; + q = &rx_qgrp->splitq.bufq_sets[j].bufq; - err = idpf_rx_bufs_init(q); + q->truesize = truesize; + + type = truesize ? LIBETH_FQE_SHORT : LIBETH_FQE_MTU; + + err = idpf_rx_bufs_init(q, type); if (err) return err; + + truesize = q->truesize >> 1; } } @@ -705,22 +855,17 @@ int idpf_rx_bufs_init_all(struct idpf_vport *vport) /** * idpf_rx_desc_alloc - Allocate queue Rx resources + * @vport: vport to allocate resources for * @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) +static int idpf_rx_desc_alloc(const struct idpf_vport *vport, + struct idpf_rx_queue *rxq) { - struct device *dev = rxq->dev; + struct device *dev = &vport->adapter->pdev->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); + 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); @@ -735,7 +880,35 @@ static int idpf_rx_desc_alloc(struct idpf_queue *rxq, bool bufq, s32 q_model) rxq->next_to_alloc = 0; rxq->next_to_clean = 0; rxq->next_to_use = 0; - set_bit(__IDPF_Q_GEN_CHK, rxq->flags); + idpf_queue_set(GEN_CHK, rxq); + + return 0; +} + +/** + * idpf_bufq_desc_alloc - Allocate buffer queue descriptor ring + * @vport: vport to allocate resources for + * @bufq: buffer queue for which the resources are set up + * + * Return: 0 on success, -ENOMEM on failure. + */ +static int idpf_bufq_desc_alloc(const struct idpf_vport *vport, + struct idpf_buf_queue *bufq) +{ + struct device *dev = &vport->adapter->pdev->dev; + + bufq->size = array_size(bufq->desc_count, sizeof(*bufq->split_buf)); + + bufq->split_buf = dma_alloc_coherent(dev, bufq->size, &bufq->dma, + GFP_KERNEL); + if (!bufq->split_buf) + return -ENOMEM; + + bufq->next_to_alloc = 0; + bufq->next_to_clean = 0; + bufq->next_to_use = 0; + + idpf_queue_set(GEN_CHK, bufq); return 0; } @@ -748,9 +921,7 @@ static int idpf_rx_desc_alloc(struct idpf_queue *rxq, bool bufq, s32 q_model) */ 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; @@ -762,13 +933,17 @@ static int idpf_rx_desc_alloc_all(struct idpf_vport *vport) num_rxq = rx_qgrp->singleq.num_rxq; for (j = 0; j < num_rxq; j++) { + struct idpf_rx_queue *q; + 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); + + err = idpf_rx_desc_alloc(vport, q); if (err) { - dev_err(dev, "Memory allocation for Rx Queue %u failed\n", + pci_err(vport->adapter->pdev, + "Memory allocation for Rx Queue %u failed\n", i); goto err_out; } @@ -778,10 +953,14 @@ static int idpf_rx_desc_alloc_all(struct idpf_vport *vport) continue; for (j = 0; j < vport->num_bufqs_per_qgrp; j++) { + struct idpf_buf_queue *q; + q = &rx_qgrp->splitq.bufq_sets[j].bufq; - err = idpf_rx_desc_alloc(q, true, vport->rxq_model); + + err = idpf_bufq_desc_alloc(vport, q); if (err) { - dev_err(dev, "Memory allocation for Rx Buffer Queue %u failed\n", + pci_err(vport->adapter->pdev, + "Memory allocation for Rx Buffer Queue %u failed\n", i); goto err_out; } @@ -802,11 +981,16 @@ err_out: */ static void idpf_txq_group_rel(struct idpf_vport *vport) { + bool split, flow_sch_en; int i, j; if (!vport->txq_grps) return; + split = idpf_is_queue_model_split(vport->txq_model); + 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 *txq_grp = &vport->txq_grps[i]; @@ -814,8 +998,15 @@ static void idpf_txq_group_rel(struct idpf_vport *vport) kfree(txq_grp->txqs[j]); txq_grp->txqs[j] = NULL; } + + if (!split) + continue; + kfree(txq_grp->complq); txq_grp->complq = NULL; + + if (flow_sch_en) + kfree(txq_grp->stashes); } kfree(vport->txq_grps); vport->txq_grps = NULL; @@ -917,9 +1108,11 @@ void idpf_vport_queues_rel(struct idpf_vport *vport) */ static int idpf_vport_init_fast_path_txqs(struct idpf_vport *vport) { + struct idpf_ptp_vport_tx_tstamp_caps *caps = vport->tx_tstamp_caps; + struct work_struct *tstamp_task = &vport->tstamp_task; int i, j, k = 0; - vport->txqs = kcalloc(vport->num_txq, sizeof(struct idpf_queue *), + vport->txqs = kcalloc(vport->num_txq, sizeof(*vport->txqs), GFP_KERNEL); if (!vport->txqs) @@ -931,6 +1124,12 @@ static int idpf_vport_init_fast_path_txqs(struct idpf_vport *vport) for (j = 0; j < tx_grp->num_txq; j++, k++) { vport->txqs[k] = tx_grp->txqs[j]; vport->txqs[k]->idx = k; + + if (!caps) + continue; + + vport->txqs[k]->cached_tstamp_caps = caps; + vport->txqs[k]->tstamp_task = tstamp_task; } } @@ -967,17 +1166,11 @@ void idpf_vport_init_num_qs(struct idpf_vport *vport, /* 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; } /** @@ -1137,9 +1330,10 @@ static void idpf_vport_calc_numq_per_grp(struct idpf_vport *vport, * @q: rx queue for which descids are set * */ -static void idpf_rxq_set_descids(struct idpf_vport *vport, struct idpf_queue *q) +static void idpf_rxq_set_descids(const struct idpf_vport *vport, + struct idpf_rx_queue *q) { - if (vport->rxq_model == VIRTCHNL2_QUEUE_MODEL_SPLIT) { + if (idpf_is_queue_model_split(vport->rxq_model)) { q->rxdids = VIRTCHNL2_RXDID_2_FLEX_SPLITQ_M; } else { if (vport->base_rxd) @@ -1158,20 +1352,22 @@ static void idpf_rxq_set_descids(struct idpf_vport *vport, struct idpf_queue *q) */ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq) { - bool flow_sch_en; - int err, i; + bool split, flow_sch_en; + int i; vport->txq_grps = kcalloc(vport->num_txq_grp, sizeof(*vport->txq_grps), GFP_KERNEL); if (!vport->txq_grps) return -ENOMEM; + split = idpf_is_queue_model_split(vport->txq_model); 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; + struct idpf_txq_stash *stashes; int j; tx_qgrp->vport = vport; @@ -1180,45 +1376,62 @@ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 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; + if (!tx_qgrp->txqs[j]) goto err_alloc; - } + } + + if (split && flow_sch_en) { + stashes = kcalloc(num_txq, sizeof(*stashes), + GFP_KERNEL); + if (!stashes) + goto err_alloc; + + tx_qgrp->stashes = stashes; } for (j = 0; j < tx_qgrp->num_txq; j++) { - struct idpf_queue *q = tx_qgrp->txqs[j]; + struct idpf_tx_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->netdev = vport->netdev; 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 (!split) { + q->clean_budget = vport->compln_clean_budget; + idpf_queue_assign(CRC_EN, q, + vport->crc_enable); + } + + if (!flow_sch_en) + continue; + + if (split) { + q->stash = &stashes[j]; + hash_init(q->stash->sched_buf_hash); + } + + idpf_queue_set(FLOW_SCH_EN, q); } - if (!idpf_is_queue_model_split(vport->txq_model)) + if (!split) continue; tx_qgrp->complq = kcalloc(IDPF_COMPLQ_PER_GROUP, sizeof(*tx_qgrp->complq), GFP_KERNEL); - if (!tx_qgrp->complq) { - err = -ENOMEM; + if (!tx_qgrp->complq) 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; + tx_qgrp->complq->netdev = vport->netdev; + tx_qgrp->complq->clean_budget = vport->compln_clean_budget; if (flow_sch_en) - __set_bit(__IDPF_Q_FLOW_SCH_EN, tx_qgrp->complq->flags); + idpf_queue_set(FLOW_SCH_EN, tx_qgrp->complq); } return 0; @@ -1226,7 +1439,7 @@ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq) err_alloc: idpf_txq_group_rel(vport); - return err; + return -ENOMEM; } /** @@ -1238,8 +1451,6 @@ err_alloc: */ 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; bool hs; @@ -1292,21 +1503,13 @@ static int idpf_rxq_group_alloc(struct idpf_vport *vport, u16 num_rxq) struct idpf_bufq_set *bufq_set = &rx_qgrp->splitq.bufq_sets[j]; int swq_size = sizeof(struct idpf_sw_queue); + struct idpf_buf_queue *q; 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 (hs) { - q->rx_hsplit_en = true; - q->rx_hbuf_size = IDPF_HDR_BUF_SIZE; - } + idpf_queue_assign(HSPLIT_EN, q, hs); bufq_set->num_refillqs = num_rxq; bufq_set->refillqs = kcalloc(num_rxq, swq_size, @@ -1319,13 +1522,12 @@ static int idpf_rxq_group_alloc(struct idpf_vport *vport, u16 num_rxq) 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); + idpf_queue_set(GEN_CHK, refillq); + idpf_queue_set(RFL_GEN_CHK, refillq); refillq->ring = kcalloc(refillq->desc_count, - sizeof(u16), + sizeof(*refillq->ring), GFP_KERNEL); if (!refillq->ring) { err = -ENOMEM; @@ -1336,36 +1538,30 @@ static int idpf_rxq_group_alloc(struct idpf_vport *vport, u16 num_rxq) skip_splitq_rx_init: for (j = 0; j < num_rxq; j++) { + struct idpf_rx_queue *q; + 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.rxq_sets[j]->refillq[0] = &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.rxq_sets[j]->refillq[1] = &rx_qgrp->splitq.bufq_sets[1].refillqs[j]; - if (hs) { - q->rx_hsplit_en = true; - q->rx_hbuf_size = IDPF_HDR_BUF_SIZE; - } + idpf_queue_assign(HSPLIT_EN, q, hs); setup_rxq: - q->dev = &adapter->pdev->dev; q->desc_count = vport->rxq_desc_count; - q->vport = vport; - q->rxq_grp = rx_qgrp; + q->rx_ptype_lkup = vport->rx_ptype_lkup; + q->netdev = vport->netdev; + q->bufq_sets = rx_qgrp->splitq.bufq_sets; 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; + LIBETH_RX_LL_LEN; idpf_rxq_set_descids(vport, q); } } @@ -1445,12 +1641,13 @@ err_out: * 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) +static void idpf_tx_handle_sw_marker(struct idpf_tx_queue *tx_q) { - struct idpf_vport *vport = tx_q->vport; + struct idpf_netdev_priv *priv = netdev_priv(tx_q->netdev); + struct idpf_vport *vport = priv->vport; int i; - clear_bit(__IDPF_Q_SW_MARKER, tx_q->flags); + idpf_queue_clear(SW_MARKER, tx_q); /* Hardware must write marker packets to all queues associated with * completion queues. So check if all queues received marker packets */ @@ -1458,7 +1655,7 @@ static void idpf_tx_handle_sw_marker(struct idpf_queue *tx_q) /* 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)) + if (idpf_queue_has(SW_MARKER, vport->txqs[i])) return; /* Drain complete */ @@ -1467,34 +1664,37 @@ static void idpf_tx_handle_sw_marker(struct idpf_queue *tx_q) } /** - * 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 + * idpf_tx_read_tstamp - schedule a work to read Tx timestamp value + * @txq: queue to read the timestamp from + * @skb: socket buffer to provide Tx timestamp value + * + * Schedule a work to read Tx timestamp value generated once the packet is + * transmitted. */ -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) +static void idpf_tx_read_tstamp(struct idpf_tx_queue *txq, struct sk_buff *skb) { - napi_consume_skb(tx_buf->skb, napi_budget); + struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps; + struct idpf_ptp_tx_tstamp_status *tx_tstamp_status; - 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); + tx_tstamp_caps = txq->cached_tstamp_caps; + spin_lock_bh(&tx_tstamp_caps->status_lock); - dma_unmap_len_set(tx_buf, len, 0); - } + for (u32 i = 0; i < tx_tstamp_caps->num_entries; i++) { + tx_tstamp_status = &tx_tstamp_caps->tx_tstamp_status[i]; + if (tx_tstamp_status->state != IDPF_PTP_FREE) + continue; - /* clear tx_buf data */ - tx_buf->skb = NULL; + tx_tstamp_status->skb = skb; + tx_tstamp_status->state = IDPF_PTP_REQUEST; - cleaned->bytes += tx_buf->bytecount; - cleaned->packets += tx_buf->gso_segs; + /* Fetch timestamp from completion descriptor through + * virtchnl msg to report to stack. + */ + queue_work(system_unbound_wq, txq->tstamp_task); + break; + } + + spin_unlock_bh(&tx_tstamp_caps->status_lock); } /** @@ -1505,34 +1705,35 @@ static void idpf_tx_splitq_clean_hdr(struct idpf_queue *tx_q, * @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, +static void idpf_tx_clean_stashed_bufs(struct idpf_tx_queue *txq, + u16 compl_tag, + struct libeth_sq_napi_stats *cleaned, int budget) { struct idpf_tx_stash *stash; struct hlist_node *tmp_buf; + struct libeth_cq_pp cp = { + .dev = txq->dev, + .ss = cleaned, + .napi = budget, + }; /* Buffer completion */ - hash_for_each_possible_safe(txq->sched_buf_hash, stash, tmp_buf, + hash_for_each_possible_safe(txq->stash->sched_buf_hash, stash, tmp_buf, hlist, compl_tag) { - if (unlikely(stash->buf.compl_tag != (int)compl_tag)) + if (unlikely(idpf_tx_buf_compl_tag(&stash->buf) != 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); - } + hash_del(&stash->hlist); - /* Push shadow buf back onto stack */ - idpf_buf_lifo_push(&txq->buf_stack, stash); + if (stash->buf.type == LIBETH_SQE_SKB && + (skb_shinfo(stash->buf.skb)->tx_flags & SKBTX_IN_PROGRESS)) + idpf_tx_read_tstamp(txq, stash->buf.skb); - hash_del(&stash->hlist); + libeth_tx_complete(&stash->buf, &cp); + + /* Push shadow buf back onto stack */ + idpf_buf_lifo_push(&txq->stash->buf_stack, stash); } } @@ -1542,49 +1743,47 @@ static void idpf_tx_clean_stashed_bufs(struct idpf_queue *txq, u16 compl_tag, * @txq: Tx queue to clean * @tx_buf: buffer to store */ -static int idpf_stash_flow_sch_buffers(struct idpf_queue *txq, +static int idpf_stash_flow_sch_buffers(struct idpf_tx_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))) + if (unlikely(tx_buf->type <= LIBETH_SQE_CTX)) return 0; - stash = idpf_buf_lifo_pop(&txq->buf_stack); + stash = idpf_buf_lifo_pop(&txq->stash->buf_stack); if (unlikely(!stash)) { net_err_ratelimited("%s: No out-of-order TX buffers left!\n", - txq->vport->netdev->name); + netdev_name(txq->netdev)); 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; + stash->buf.bytes = tx_buf->bytes; + stash->buf.packets = tx_buf->packets; + stash->buf.type = tx_buf->type; + stash->buf.nr_frags = tx_buf->nr_frags; 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; + idpf_tx_buf_compl_tag(&stash->buf) = idpf_tx_buf_compl_tag(tx_buf); /* Add buffer to buf_hash table to be freed later */ - hash_add(txq->sched_buf_hash, &stash->hlist, stash->buf.compl_tag); + hash_add(txq->stash->sched_buf_hash, &stash->hlist, + idpf_tx_buf_compl_tag(&stash->buf)); - 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; + tx_buf->type = LIBETH_SQE_EMPTY; return 0; } #define idpf_tx_splitq_clean_bump_ntc(txq, ntc, desc, buf) \ do { \ - (ntc)++; \ - if (unlikely(!(ntc))) { \ - ntc -= (txq)->desc_count; \ + if (unlikely(++(ntc) == (txq)->desc_count)) { \ + ntc = 0; \ buf = (txq)->tx_buf; \ - desc = IDPF_FLEX_TX_DESC(txq, 0); \ + desc = &(txq)->flex_tx[0]; \ } else { \ (buf)++; \ (desc)++; \ @@ -1606,69 +1805,71 @@ do { \ * 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. + * + * Furthermore, in flow scheduling mode, check to make sure there are enough + * reserve buffers to stash the packet. If there are not, return early, which + * will leave next_to_clean pointing to the packet that failed to be stashed. + * + * Return: false in the scenario above, true otherwise. */ -static void idpf_tx_splitq_clean(struct idpf_queue *tx_q, u16 end, +static bool idpf_tx_splitq_clean(struct idpf_tx_queue *tx_q, u16 end, int napi_budget, - struct idpf_cleaned_stats *cleaned, + struct libeth_sq_napi_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; + u32 ntc = tx_q->next_to_clean; + struct libeth_cq_pp cp = { + .dev = tx_q->dev, + .ss = cleaned, + .napi = napi_budget, + }; struct idpf_tx_buf *tx_buf; + bool clean_complete = true; - tx_desc = IDPF_FLEX_TX_DESC(tx_q, ntc); - next_pending_desc = IDPF_FLEX_TX_DESC(tx_q, end); + tx_desc = &tx_q->flex_tx[ntc]; + next_pending_desc = &tx_q->flex_tx[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; + u32 eop_idx; /* 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. + * it's corresponding entry in the buffer ring is reserved. We + * can skip this descriptor since there is no buffer to clean. */ - if (unlikely(tx_buf->compl_tag == IDPF_SPLITQ_TX_INVAL_COMPL_TAG)) + if (tx_buf->type <= LIBETH_SQE_CTX) goto fetch_next_txq_desc; - eop_desc = (union idpf_tx_flex_desc *)tx_buf->next_to_watch; + if (unlikely(tx_buf->type != LIBETH_SQE_SKB)) + break; - /* clear next_to_watch to prevent false hangs */ - tx_buf->next_to_watch = NULL; + eop_idx = tx_buf->rs_idx; if (descs_only) { - if (idpf_stash_flow_sch_buffers(tx_q, tx_buf)) + if (IDPF_TX_BUF_RSV_UNUSED(tx_q) < tx_buf->nr_frags) { + clean_complete = false; goto tx_splitq_clean_out; + } - while (tx_desc != eop_desc) { + idpf_stash_flow_sch_buffers(tx_q, tx_buf); + + while (ntc != eop_idx) { 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; - } + idpf_stash_flow_sch_buffers(tx_q, tx_buf); } } else { - idpf_tx_splitq_clean_hdr(tx_q, tx_buf, cleaned, - napi_budget); + libeth_tx_complete(tx_buf, &cp); /* unmap remaining buffers */ - while (tx_desc != eop_desc) { + while (ntc != eop_idx) { 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); - } + libeth_tx_complete(tx_buf, &cp); } } @@ -1677,8 +1878,9 @@ fetch_next_txq_desc: } tx_splitq_clean_out: - ntc += tx_q->desc_count; tx_q->next_to_clean = ntc; + + return clean_complete; } #define idpf_tx_clean_buf_ring_bump_ntc(txq, ntc, buf) \ @@ -1703,58 +1905,73 @@ do { \ * 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, +static bool idpf_tx_clean_buf_ring(struct idpf_tx_queue *txq, u16 compl_tag, + struct libeth_sq_napi_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; + struct libeth_cq_pp cp = { + .dev = txq->dev, + .ss = cleaned, + .napi = budget, + }; + u16 ntc, 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); - } + if (unlikely(tx_buf->type <= LIBETH_SQE_CTX || + idpf_tx_buf_compl_tag(tx_buf) != compl_tag)) + return false; - memset(tx_buf, 0, sizeof(struct idpf_tx_buf)); - tx_buf->compl_tag = IDPF_SPLITQ_TX_INVAL_COMPL_TAG; + if (tx_buf->type == LIBETH_SQE_SKB) { + if (skb_shinfo(tx_buf->skb)->tx_flags & SKBTX_IN_PROGRESS) + idpf_tx_read_tstamp(txq, tx_buf->skb); - num_descs_cleaned++; - idpf_tx_clean_buf_ring_bump_ntc(txq, idx, tx_buf); + libeth_tx_complete(tx_buf, &cp); } - /* 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; + idpf_tx_clean_buf_ring_bump_ntc(txq, idx, tx_buf); + + while (idpf_tx_buf_compl_tag(tx_buf) == compl_tag) { + libeth_tx_complete(tx_buf, &cp); + idpf_tx_clean_buf_ring_bump_ntc(txq, idx, tx_buf); + } - /* 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. + /* + * It's possible the packet we just cleaned was an out of order + * completion, which means we can stash the buffers starting from + * the original next_to_clean and reuse the descriptors. We need + * to compare the descriptor ring next_to_clean packet's "first" buffer + * to the "first" buffer of the packet we just cleaned to determine if + * this is the case. Howevever, next_to_clean can point to either a + * reserved buffer that corresponds to a context descriptor used for the + * next_to_clean packet (TSO packet) or the "first" buffer (single + * packet). The orig_idx from the packet we just cleaned will always + * point to the "first" buffer. If next_to_clean points to a reserved + * buffer, let's bump ntc once and start the comparison from there. */ + ntc = txq->next_to_clean; tx_buf = &txq->tx_buf[ntc]; - while (tx_buf != &txq->tx_buf[orig_idx]) { - idpf_stash_flow_sch_buffers(txq, tx_buf); + + if (tx_buf->type == LIBETH_SQE_CTX) 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 + /* + * If ntc still points to a different "first" buffer, clean the + * descriptor ring and stash all of the buffers for later cleaning. If + * we cannot stash all of the buffers, next_to_clean will point to the + * "first" buffer of the packet that could not be stashed and cleaning + * will start there next time. + */ + if (unlikely(tx_buf != &txq->tx_buf[orig_idx] && + !idpf_tx_splitq_clean(txq, orig_idx, budget, cleaned, + true))) + return true; + + /* + * Otherwise, update next_to_clean to reflect the cleaning that was + * done above. */ txq->next_to_clean = idx; @@ -1772,17 +1989,18 @@ static bool idpf_tx_clean_buf_ring(struct idpf_queue *txq, u16 compl_tag, * * Returns bytes/packets cleaned */ -static void idpf_tx_handle_rs_completion(struct idpf_queue *txq, +static void idpf_tx_handle_rs_completion(struct idpf_tx_queue *txq, struct idpf_splitq_tx_compl_desc *desc, - struct idpf_cleaned_stats *cleaned, + struct libeth_sq_napi_stats *cleaned, int budget) { u16 compl_tag; - if (!test_bit(__IDPF_Q_FLOW_SCH_EN, txq->flags)) { + if (!idpf_queue_has(FLOW_SCH_EN, txq)) { u16 head = le16_to_cpu(desc->q_head_compl_tag.q_head); - return idpf_tx_splitq_clean(txq, head, budget, cleaned, false); + idpf_tx_splitq_clean(txq, head, budget, cleaned, false); + return; } compl_tag = le16_to_cpu(desc->q_head_compl_tag.compl_tag); @@ -1802,24 +2020,23 @@ static void idpf_tx_handle_rs_completion(struct idpf_queue *txq, * * 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, +static bool idpf_tx_clean_complq(struct idpf_compl_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); + complq_budget = complq->clean_budget; + tx_desc = &complq->comp[ntc]; ntc -= complq->desc_count; do { - struct idpf_cleaned_stats cleaned_stats = { }; - struct idpf_queue *tx_q; + struct libeth_sq_napi_stats cleaned_stats = { }; + struct idpf_tx_queue *tx_q; int rel_tx_qid; u16 hw_head; u8 ctype; /* completion type */ @@ -1828,7 +2045,7 @@ static bool idpf_tx_clean_complq(struct idpf_queue *complq, int budget, /* if the descriptor isn't done, no work yet to do */ gen = le16_get_bits(tx_desc->qid_comptype_gen, IDPF_TXD_COMPLQ_GEN_M); - if (test_bit(__IDPF_Q_GEN_CHK, complq->flags) != gen) + if (idpf_queue_has(GEN_CHK, complq) != gen) break; /* Find necessary info of TX queue to clean buffers */ @@ -1836,8 +2053,7 @@ static bool idpf_tx_clean_complq(struct idpf_queue *complq, int budget, IDPF_TXD_COMPLQ_QID_M); 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"); + netdev_err(complq->netdev, "TxQ not found\n"); goto fetch_next_desc; } tx_q = complq->txq_grp->txqs[rel_tx_qid]; @@ -1860,15 +2076,14 @@ static bool idpf_tx_clean_complq(struct idpf_queue *complq, int budget, idpf_tx_handle_sw_marker(tx_q); break; default: - dev_err(&tx_q->vport->adapter->pdev->dev, - "Unknown TX completion type: %d\n", - ctype); + netdev_err(tx_q->netdev, + "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); + u64_stats_add(&tx_q->q_stats.packets, cleaned_stats.packets); + u64_stats_add(&tx_q->q_stats.bytes, cleaned_stats.bytes); tx_q->cleaned_pkts += cleaned_stats.packets; tx_q->cleaned_bytes += cleaned_stats.bytes; complq->num_completions++; @@ -1879,8 +2094,8 @@ fetch_next_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); + tx_desc = &complq->comp[0]; + idpf_queue_change(GEN_CHK, complq); } prefetch(tx_desc); @@ -1896,9 +2111,9 @@ fetch_next_desc: IDPF_TX_COMPLQ_OVERFLOW_THRESH(complq))) complq_ok = false; - np = netdev_priv(complq->vport->netdev); + np = netdev_priv(complq->netdev); for (i = 0; i < complq->txq_grp->num_txq; ++i) { - struct idpf_queue *tx_q = complq->txq_grp->txqs[i]; + struct idpf_tx_queue *tx_q = complq->txq_grp->txqs[i]; struct netdev_queue *nq; bool dont_wake; @@ -1909,11 +2124,11 @@ fetch_next_desc: *cleaned += tx_q->cleaned_pkts; /* Update BQL */ - nq = netdev_get_tx_queue(tx_q->vport->netdev, tx_q->idx); + nq = netdev_get_tx_queue(tx_q->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); + !netif_carrier_ok(tx_q->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, @@ -1964,46 +2179,23 @@ 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; + *(u32 *)&desc->flow.qw1.cmd_dtype = (u8)(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, +static int idpf_tx_maybe_stop_splitq(struct idpf_tx_queue *tx_q, unsigned int descs_needed) { if (idpf_tx_maybe_stop_common(tx_q, descs_needed)) - goto splitq_stop; + goto out; /* If there are too many outstanding completions expected on the * completion queue, stop the TX queue to give the device some time to @@ -2022,10 +2214,12 @@ static int idpf_tx_maybe_stop_splitq(struct idpf_queue *tx_q, return 0; splitq_stop: + netif_stop_subqueue(tx_q->netdev, tx_q->idx); + +out: u64_stats_update_begin(&tx_q->stats_sync); - u64_stats_inc(&tx_q->q_stats.tx.q_busy); + u64_stats_inc(&tx_q->q_stats.q_busy); u64_stats_update_end(&tx_q->stats_sync); - netif_stop_subqueue(tx_q->vport->netdev, tx_q->idx); return -EBUSY; } @@ -2040,15 +2234,19 @@ splitq_stop: * 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, +void idpf_tx_buf_hw_update(struct idpf_tx_queue *tx_q, u32 val, bool xmit_more) { struct netdev_queue *nq; - nq = netdev_get_tx_queue(tx_q->vport->netdev, tx_q->idx); + nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx); tx_q->next_to_use = val; - idpf_tx_maybe_stop_common(tx_q, IDPF_TX_DESC_NEEDED); + if (idpf_tx_maybe_stop_common(tx_q, IDPF_TX_DESC_NEEDED)) { + u64_stats_update_begin(&tx_q->stats_sync); + u64_stats_inc(&tx_q->q_stats.q_busy); + u64_stats_update_end(&tx_q->stats_sync); + } /* Force memory writes to complete before letting h/w * know there are new descriptors to fetch. (Only @@ -2069,7 +2267,7 @@ void idpf_tx_buf_hw_update(struct idpf_queue *tx_q, u32 val, * * Returns number of data descriptors needed for this skb. */ -unsigned int idpf_tx_desc_count_required(struct idpf_queue *txq, +unsigned int idpf_tx_desc_count_required(struct idpf_tx_queue *txq, struct sk_buff *skb) { const struct skb_shared_info *shinfo; @@ -2102,7 +2300,7 @@ unsigned int idpf_tx_desc_count_required(struct idpf_queue *txq, 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_inc(&txq->q_stats.linearize); u64_stats_update_end(&txq->stats_sync); } @@ -2116,11 +2314,17 @@ unsigned int idpf_tx_desc_count_required(struct idpf_queue *txq, * @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, +void idpf_tx_dma_map_error(struct idpf_tx_queue *txq, struct sk_buff *skb, struct idpf_tx_buf *first, u16 idx) { + struct libeth_sq_napi_stats ss = { }; + struct libeth_cq_pp cp = { + .dev = txq->dev, + .ss = &ss, + }; + u64_stats_update_begin(&txq->stats_sync); - u64_stats_inc(&txq->q_stats.tx.dma_map_errs); + u64_stats_inc(&txq->q_stats.dma_map_errs); u64_stats_update_end(&txq->stats_sync); /* clear dma mappings for failed tx_buf map */ @@ -2128,7 +2332,7 @@ void idpf_tx_dma_map_error(struct idpf_queue *txq, struct sk_buff *skb, struct idpf_tx_buf *tx_buf; tx_buf = &txq->tx_buf[idx]; - idpf_tx_buf_rel(txq, tx_buf); + libeth_tx_complete(tx_buf, &cp); if (tx_buf == first) break; if (idx == 0) @@ -2143,8 +2347,8 @@ void idpf_tx_dma_map_error(struct idpf_queue *txq, struct sk_buff *skb, * 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)); + tx_desc = &txq->flex_tx[idx]; + memset(tx_desc, 0, sizeof(*tx_desc)); if (idx == 0) idx = txq->desc_count; idx--; @@ -2159,7 +2363,7 @@ void idpf_tx_dma_map_error(struct idpf_queue *txq, struct sk_buff *skb, * @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) +static unsigned int idpf_tx_splitq_bump_ntu(struct idpf_tx_queue *txq, u16 ntu) { ntu++; @@ -2181,7 +2385,7 @@ static unsigned int idpf_tx_splitq_bump_ntu(struct idpf_queue *txq, u16 ntu) * 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, +static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q, struct idpf_tx_splitq_params *params, struct idpf_tx_buf *first) { @@ -2202,11 +2406,12 @@ static void idpf_tx_splitq_map(struct idpf_queue *tx_q, data_len = skb->data_len; size = skb_headlen(skb); - tx_desc = IDPF_FLEX_TX_DESC(tx_q, i); + tx_desc = &tx_q->flex_tx[i]; dma = dma_map_single(tx_q->dev, skb->data, size, DMA_TO_DEVICE); tx_buf = first; + first->nr_frags = 0; params->compl_tag = (tx_q->compl_tag_cur_gen << tx_q->compl_tag_gen_s) | i; @@ -2217,7 +2422,9 @@ static void idpf_tx_splitq_map(struct idpf_queue *tx_q, 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; + first->nr_frags++; + idpf_tx_buf_compl_tag(tx_buf) = params->compl_tag; + tx_buf->type = LIBETH_SQE_FRAG; /* record length, and DMA address */ dma_unmap_len_set(tx_buf, len, size); @@ -2271,14 +2478,15 @@ static void idpf_tx_splitq_map(struct idpf_queue *tx_q, 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); + if (unlikely(++i == tx_q->desc_count)) { + tx_buf = tx_q->tx_buf; + tx_desc = &tx_q->flex_tx[0]; i = 0; tx_q->compl_tag_cur_gen = IDPF_TX_ADJ_COMPL_TAG_GEN(tx_q); + } else { + tx_buf++; + tx_desc++; } /* Since this packet has a buffer that is going to span @@ -2291,8 +2499,8 @@ static void idpf_tx_splitq_map(struct idpf_queue *tx_q, * 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; + tx_buf->type = LIBETH_SQE_EMPTY; + idpf_tx_buf_compl_tag(tx_buf) = params->compl_tag; /* Adjust the DMA offset and the remaining size of the * fragment. On the first iteration of this loop, @@ -2316,13 +2524,15 @@ static void idpf_tx_splitq_map(struct idpf_queue *tx_q, 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); + if (unlikely(++i == tx_q->desc_count)) { + tx_buf = tx_q->tx_buf; + tx_desc = &tx_q->flex_tx[0]; i = 0; tx_q->compl_tag_cur_gen = IDPF_TX_ADJ_COMPL_TAG_GEN(tx_q); + } else { + tx_buf++; + tx_desc++; } size = skb_frag_size(frag); @@ -2330,26 +2540,24 @@ static void idpf_tx_splitq_map(struct idpf_queue *tx_q, 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); + first->type = LIBETH_SQE_SKB; + /* write last descriptor with RS and EOP bits */ + first->rs_idx = i; 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); + nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx); + netdev_tx_sent_queue(nq, first->bytes); idpf_tx_buf_hw_update(tx_q, i, netdev_xmit_more()); } @@ -2525,8 +2733,8 @@ static bool __idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs) * 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) +static bool idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs, + unsigned int count) { if (likely(count < max_bufs)) return false; @@ -2543,17 +2751,16 @@ bool idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs, * 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) +static union idpf_flex_tx_ctx_desc * +idpf_tx_splitq_get_ctx_desc(struct idpf_tx_queue *txq) { - struct idpf_flex_tx_ctx_desc *desc; + union 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; + txq->tx_buf[i].type = LIBETH_SQE_CTX; /* grab the next descriptor */ - desc = IDPF_FLEX_TX_CTX_DESC(txq, i); + desc = &txq->flex_ctx[i]; txq->next_to_use = idpf_tx_splitq_bump_ntu(txq, i); return desc; @@ -2564,10 +2771,10 @@ idpf_tx_splitq_get_ctx_desc(struct idpf_queue *txq) * @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) +netdev_tx_t idpf_tx_drop_skb(struct idpf_tx_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_inc(&tx_q->q_stats.skb_drops); u64_stats_update_end(&tx_q->stats_sync); idpf_tx_buf_hw_update(tx_q, tx_q->next_to_use, false); @@ -2577,6 +2784,73 @@ netdev_tx_t idpf_tx_drop_skb(struct idpf_queue *tx_q, struct sk_buff *skb) return NETDEV_TX_OK; } +#if (IS_ENABLED(CONFIG_PTP_1588_CLOCK)) +/** + * idpf_tx_tstamp - set up context descriptor for hardware timestamp + * @tx_q: queue to send buffer on + * @skb: pointer to the SKB we're sending + * @off: pointer to the offload struct + * + * Return: Positive index number on success, negative otherwise. + */ +static int idpf_tx_tstamp(struct idpf_tx_queue *tx_q, struct sk_buff *skb, + struct idpf_tx_offload_params *off) +{ + int err, idx; + + /* only timestamp the outbound packet if the user has requested it */ + if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))) + return -1; + + if (!idpf_ptp_get_txq_tstamp_capability(tx_q)) + return -1; + + /* Tx timestamps cannot be sampled when doing TSO */ + if (off->tx_flags & IDPF_TX_FLAGS_TSO) + return -1; + + /* Grab an open timestamp slot */ + err = idpf_ptp_request_ts(tx_q, skb, &idx); + if (err) { + u64_stats_update_begin(&tx_q->stats_sync); + u64_stats_inc(&tx_q->q_stats.tstamp_skipped); + u64_stats_update_end(&tx_q->stats_sync); + + return -1; + } + + off->tx_flags |= IDPF_TX_FLAGS_TSYN; + + return idx; +} + +/** + * idpf_tx_set_tstamp_desc - Set the Tx descriptor fields needed to generate + * PHY Tx timestamp + * @ctx_desc: Context descriptor + * @idx: Index of the Tx timestamp latch + */ +static void idpf_tx_set_tstamp_desc(union idpf_flex_tx_ctx_desc *ctx_desc, + u32 idx) +{ + ctx_desc->tsyn.qw1 = le64_encode_bits(IDPF_TX_DESC_DTYPE_CTX, + IDPF_TX_CTX_DTYPE_M) | + le64_encode_bits(IDPF_TX_CTX_DESC_TSYN, + IDPF_TX_CTX_CMD_M) | + le64_encode_bits(idx, IDPF_TX_CTX_TSYN_REG_M); +} +#else /* CONFIG_PTP_1588_CLOCK */ +static int idpf_tx_tstamp(struct idpf_tx_queue *tx_q, struct sk_buff *skb, + struct idpf_tx_offload_params *off) +{ + return -1; +} + +static void idpf_tx_set_tstamp_desc(union idpf_flex_tx_ctx_desc *ctx_desc, + u32 idx) +{ } +#endif /* CONFIG_PTP_1588_CLOCK */ + /** * idpf_tx_splitq_frame - Sends buffer on Tx ring using flex descriptors * @skb: send buffer @@ -2585,12 +2859,13 @@ netdev_tx_t idpf_tx_drop_skb(struct idpf_queue *tx_q, struct sk_buff *skb) * 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_queue *tx_q) { struct idpf_tx_splitq_params tx_params = { }; + union idpf_flex_tx_ctx_desc *ctx_desc; struct idpf_tx_buf *first; unsigned int count; - int tso; + int tso, idx; count = idpf_tx_desc_count_required(tx_q, skb); if (unlikely(!count)) @@ -2610,8 +2885,7 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb, 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 = idpf_tx_splitq_get_ctx_desc(tx_q); ctx_desc->tso.qw1.cmd_dtype = cpu_to_le16(IDPF_TX_DESC_DTYPE_FLEX_TSO_CTX | @@ -2625,24 +2899,30 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb, 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_inc(&tx_q->q_stats.lso_pkts); u64_stats_update_end(&tx_q->stats_sync); } + idx = idpf_tx_tstamp(tx_q, skb, &tx_params.offload); + if (idx != -1) { + ctx_desc = idpf_tx_splitq_get_ctx_desc(tx_q); + idpf_tx_set_tstamp_desc(ctx_desc, idx); + } + /* 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); + first->packets = tx_params.offload.tso_segs; + first->bytes = skb->len + + ((first->packets - 1) * tx_params.offload.tso_hdr_len); } else { - first->gso_segs = 1; - first->bytecount = max_t(unsigned int, skb->len, ETH_ZLEN); + first->packets = 1; + first->bytes = max_t(unsigned int, skb->len, ETH_ZLEN); } - if (test_bit(__IDPF_Q_FLOW_SCH_EN, tx_q->flags)) { + if (idpf_queue_has(FLOW_SCH_EN, tx_q)) { 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 @@ -2672,17 +2952,16 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb, } /** - * idpf_tx_splitq_start - Selects the right Tx queue to send buffer + * idpf_tx_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) +netdev_tx_t idpf_tx_start(struct sk_buff *skb, struct net_device *netdev) { struct idpf_vport *vport = idpf_netdev_to_vport(netdev); - struct idpf_queue *tx_q; + struct idpf_tx_queue *tx_q; if (unlikely(skb_get_queue_mapping(skb) >= vport->num_txq)) { dev_kfree_skb_any(skb); @@ -2701,31 +2980,10 @@ netdev_tx_t idpf_tx_splitq_start(struct sk_buff *skb, 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; + if (idpf_is_queue_model_split(vport->txq_model)) + return idpf_tx_splitq_frame(skb, tx_q); + else + return idpf_tx_singleq_frame(skb, tx_q); } /** @@ -2735,20 +2993,21 @@ enum pkt_hash_types idpf_ptype_to_htype(const struct idpf_rx_ptype_decoded *deco * @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) +static void +idpf_rx_hash(const struct idpf_rx_queue *rxq, struct sk_buff *skb, + const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc, + struct libeth_rx_pt decoded) { u32 hash; - if (unlikely(!idpf_is_feature_ena(rxq->vport, NETIF_F_RXHASH))) + if (!libeth_rx_pt_has_hash(rxq->netdev, decoded)) 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)); + libeth_rx_pt_set_hash(skb, hash, decoded); } /** @@ -2760,92 +3019,83 @@ static void idpf_rx_hash(struct idpf_queue *rxq, struct sk_buff *skb, * * 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) +static void idpf_rx_csum(struct idpf_rx_queue *rxq, struct sk_buff *skb, + struct libeth_rx_csum csum_bits, + struct libeth_rx_pt decoded) { bool ipv4, ipv6; /* check if Rx checksum is enabled */ - if (unlikely(!idpf_is_feature_ena(rxq->vport, NETIF_F_RXCSUM))) + if (!libeth_rx_pt_has_checksum(rxq->netdev, decoded)) return; /* check if HW has decoded the packet and checksum */ - if (!(csum_bits->l3l4p)) + if (unlikely(!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); + ipv4 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV4; + ipv6 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV6; - if (ipv4 && (csum_bits->ipe || csum_bits->eipe)) + if (unlikely(ipv4 && (csum_bits.ipe || csum_bits.eipe))) goto checksum_fail; - if (ipv6 && csum_bits->ipv6exadd) + if (unlikely(ipv6 && csum_bits.ipv6exadd)) return; /* check for L4 errors and handle packets that were not able to be * checksummed */ - if (csum_bits->l4e) + if (unlikely(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: + if (!csum_bits.raw_csum_valid || + decoded.inner_prot == LIBETH_RX_PT_INNER_SCTP) { skb->ip_summed = CHECKSUM_UNNECESSARY; - break; - default: - break; + return; } + skb->csum = csum_unfold((__force __sum16)~swab16(csum_bits.raw_csum)); + skb->ip_summed = CHECKSUM_COMPLETE; + return; checksum_fail: u64_stats_update_begin(&rxq->stats_sync); - u64_stats_inc(&rxq->q_stats.rx.hw_csum_err); + u64_stats_inc(&rxq->q_stats.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 * + * Return: parsed checksum status. **/ -static void idpf_rx_splitq_extract_csum_bits(struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc, - struct idpf_rx_csum_decoded *csum) +static struct libeth_rx_csum +idpf_rx_splitq_extract_csum_bits(const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc) { + struct libeth_rx_csum 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, + 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->eipe = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_XSUM_EIPE_M, + 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->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 = - le16_get_bits(rx_desc->ptype_err_fflags0, - VIRTCHNL2_RX_FLEX_DESC_ADV_RAW_CSUM_INV_M); - csum->raw_csum = le16_to_cpu(rx_desc->misc.raw_cs); + csum.ipv6exadd = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_IPV6EXADD_M, + qword0); + csum.raw_csum_valid = + !le16_get_bits(rx_desc->ptype_err_fflags0, + VIRTCHNL2_RX_FLEX_DESC_ADV_RAW_CSUM_INV_M); + csum.raw_csum = le16_to_cpu(rx_desc->misc.raw_cs); + + return csum; } /** @@ -2860,36 +3110,34 @@ static void idpf_rx_splitq_extract_csum_bits(struct virtchnl2_rx_flex_desc_adv_n * 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) +static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb, + const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc, + struct libeth_rx_pt decoded) { u16 rsc_segments, rsc_seg_len; bool ipv4, ipv6; int len; - if (unlikely(!decoded->outer_ip)) + if (unlikely(libeth_rx_pt_get_ip_ver(decoded) == + LIBETH_RX_PT_OUTER_L2)) 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); + ipv4 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV4; + ipv6 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_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); @@ -2898,6 +3146,7 @@ static int idpf_rx_rsc(struct idpf_queue *rxq, struct sk_buff *skb, /* Reset and set transport header offset in skb */ skb_set_transport_header(skb, sizeof(struct iphdr)); + len = skb->len - skb_transport_offset(skb); /* Compute the TCP pseudo header checksum*/ tcp_hdr(skb)->check = @@ -2907,6 +3156,7 @@ static int idpf_rx_rsc(struct idpf_queue *rxq, struct sk_buff *skb, skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; skb_set_transport_header(skb, sizeof(struct ipv6hdr)); + len = skb->len - skb_transport_offset(skb); tcp_hdr(skb)->check = ~tcp_v6_check(len, &ipv6h->saddr, &ipv6h->daddr, 0); } @@ -2914,13 +3164,40 @@ static int idpf_rx_rsc(struct idpf_queue *rxq, struct sk_buff *skb, tcp_gro_complete(skb); u64_stats_update_begin(&rxq->stats_sync); - u64_stats_inc(&rxq->q_stats.rx.rsc_pkts); + u64_stats_inc(&rxq->q_stats.rsc_pkts); u64_stats_update_end(&rxq->stats_sync); return 0; } /** + * idpf_rx_hwtstamp - check for an RX timestamp and pass up the stack + * @rxq: pointer to the rx queue that receives the timestamp + * @rx_desc: pointer to rx descriptor containing timestamp + * @skb: skb to put timestamp in + */ +static void +idpf_rx_hwtstamp(const struct idpf_rx_queue *rxq, + const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc, + struct sk_buff *skb) +{ + u64 cached_time, ts_ns; + u32 ts_high; + + if (!(rx_desc->ts_low & VIRTCHNL2_RX_FLEX_TSTAMP_VALID)) + return; + + cached_time = READ_ONCE(rxq->cached_phc_time); + + ts_high = le32_to_cpu(rx_desc->ts_high); + ts_ns = idpf_ptp_tstamp_extend_32b_to_64b(cached_time, ts_high); + + *skb_hwtstamps(skb) = (struct skb_shared_hwtstamps) { + .hwtstamp = ns_to_ktime(ts_ns), + }; +} + +/** * 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 @@ -2930,35 +3207,33 @@ static int idpf_rx_rsc(struct idpf_queue *rxq, struct sk_buff *skb, * 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) +static int +idpf_rx_process_skb_fields(struct idpf_rx_queue *rxq, struct sk_buff *skb, + const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc) { - struct idpf_rx_csum_decoded csum_bits = { }; - struct idpf_rx_ptype_decoded decoded; + struct libeth_rx_csum csum_bits; + struct libeth_rx_pt decoded; u16 rx_ptype; rx_ptype = le16_get_bits(rx_desc->ptype_err_fflags0, VIRTCHNL2_RX_FLEX_DESC_ADV_PTYPE_M); + decoded = rxq->rx_ptype_lkup[rx_ptype]; - skb->protocol = eth_type_trans(skb, rxq->vport->netdev); + /* process RSS/hash */ + idpf_rx_hash(rxq, skb, rx_desc, decoded); - 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; + if (idpf_queue_has(PTP, rxq)) + idpf_rx_hwtstamp(rxq, rx_desc, skb); - /* process RSS/hash */ - idpf_rx_hash(rxq, skb, rx_desc, &decoded); + skb->protocol = eth_type_trans(skb, rxq->netdev); + skb_record_rx_queue(skb, rxq->idx); if (le16_get_bits(rx_desc->hdrlen_flags, VIRTCHNL2_RX_FLEX_DESC_ADV_RSC_M)) - return idpf_rx_rsc(rxq, skb, rx_desc, &decoded); + 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); + csum_bits = idpf_rx_splitq_extract_csum_bits(rx_desc); + idpf_rx_csum(rxq, skb, csum_bits, decoded); return 0; } @@ -2976,104 +3251,73 @@ static int idpf_rx_process_skb_fields(struct idpf_queue *rxq, 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); + u32 hr = rx_buf->page->pp->p.offset; - rx_buf->page = NULL; + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buf->page, + rx_buf->offset + hr, size, rx_buf->truesize); } /** - * 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 + * idpf_rx_hsplit_wa - handle header buffer overflows and split errors + * @hdr: Rx buffer for the headers + * @buf: Rx buffer for the payload + * @data_len: number of bytes received to the payload buffer + * + * When a header buffer overflow occurs or the HW was unable do parse the + * packet type to perform header split, the whole frame gets placed to the + * payload buffer. We can't build a valid skb around a payload buffer when + * the header split is active since it doesn't reserve any head- or tailroom. + * In that case, copy either the whole frame when it's short or just the + * Ethernet header to the header buffer to be able to build an skb and adjust + * the data offset in the payload buffer, IOW emulate the header split. * - * 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. + * Return: number of bytes copied to the header buffer. */ -struct sk_buff *idpf_rx_construct_skb(struct idpf_queue *rxq, - struct idpf_rx_buf *rx_buf, - unsigned int size) +static u32 idpf_rx_hsplit_wa(const struct libeth_fqe *hdr, + struct libeth_fqe *buf, u32 data_len) { - 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))); + u32 copy = data_len <= L1_CACHE_BYTES ? data_len : ETH_HLEN; + const void *src; + void *dst; - /* if we exhaust the linear part then add what is left as a frag */ - size -= headlen; - if (!size) { - idpf_rx_put_page(rx_buf); + if (!libeth_rx_sync_for_cpu(buf, copy)) + return 0; - return skb; - } + dst = page_address(hdr->page) + hdr->offset + hdr->page->pp->p.offset; + src = page_address(buf->page) + buf->offset + buf->page->pp->p.offset; + memcpy(dst, src, LARGEST_ALIGN(copy)); - skb_add_rx_frag(skb, 0, rx_buf->page, rx_buf->page_offset + headlen, - size, rx_buf->truesize); + buf->offset += copy; - /* 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; + return copy; } /** - * idpf_rx_hdr_construct_skb - Allocate skb and populate it from header buffer - * @rxq: Rx descriptor queue - * @va: Rx buffer to pull data from + * idpf_rx_build_skb - Allocate skb and populate it from header buffer + * @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. - * 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 *idpf_rx_build_skb(const struct libeth_fqe *buf, u32 size) { + u32 hr = buf->page->pp->p.offset; struct sk_buff *skb; + void *va; - /* allocate a skb to store the frags */ - skb = __napi_alloc_skb(&rxq->q_vector->napi, size, GFP_ATOMIC); + va = page_address(buf->page) + buf->offset; + prefetch(va + hr); + + skb = napi_build_skb(va, buf->truesize); 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); + skb_reserve(skb, hr); + __skb_put(skb, size); + return skb; } @@ -3116,31 +3360,27 @@ static bool idpf_rx_splitq_is_eop(struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_de * * Returns amount of work completed */ -static int idpf_rx_splitq_clean(struct idpf_queue *rxq, int budget) +static int idpf_rx_splitq_clean(struct idpf_rx_queue *rxq, int budget) { int total_rx_bytes = 0, total_rx_pkts = 0; - struct idpf_queue *rx_bufq = NULL; + struct idpf_buf_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 libeth_fqe *hdr, *rx_buf = NULL; 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; + rx_desc = &rxq->rx[ntc].flex_adv_nic_3_wb; /* This memory barrier is needed to keep us from reading * any other fields out of the rx_desc @@ -3151,7 +3391,7 @@ static int idpf_rx_splitq_clean(struct idpf_queue *rxq, int budget) gen_id = le16_get_bits(rx_desc->pktlen_gen_bufq_id, VIRTCHNL2_RX_FLEX_DESC_ADV_GEN_M); - if (test_bit(__IDPF_Q_GEN_CHK, rxq->flags) != gen_id) + if (idpf_queue_has(GEN_CHK, rxq) != gen_id) break; rxdid = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_RXDID_M, @@ -3159,7 +3399,7 @@ static int idpf_rx_splitq_clean(struct idpf_queue *rxq, int budget) 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_inc(&rxq->q_stats.bad_descs); u64_stats_update_end(&rxq->stats_sync); continue; } @@ -3167,71 +3407,79 @@ static int idpf_rx_splitq_clean(struct idpf_queue *rxq, int budget) pkt_len = le16_get_bits(rx_desc->pktlen_gen_bufq_id, VIRTCHNL2_RX_FLEX_DESC_ADV_LEN_PBUF_M); - 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_get_bits(rx_desc->hdrlen_flags, - VIRTCHNL2_RX_FLEX_DESC_ADV_LEN_HDR_M); - -bypass_hsplit: bufq_id = le16_get_bits(rx_desc->pktlen_gen_bufq_id, VIRTCHNL2_RX_FLEX_DESC_ADV_BUFQ_ID_M); rxq_set = container_of(rxq, struct idpf_rxq_set, rxq); - if (!bufq_id) - refillq = rxq_set->refillq0; - else - refillq = rxq_set->refillq1; + refillq = rxq_set->refillq[bufq_id]; /* retrieve buffer from the rxq */ - rx_bufq = &rxq->rxq_grp->splitq.bufq_sets[bufq_id].bufq; + rx_bufq = &rxq->bufq_sets[bufq_id].bufq; buf_id = le16_to_cpu(rx_desc->buf_id); - rx_buf = &rx_bufq->rx_buf.buf[buf_id]; + rx_buf = &rx_bufq->buf[buf_id]; + + if (!rx_bufq->hdr_pp) + goto payload; + +#define __HBO_BIT VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_HBO_M +#define __HDR_LEN_MASK VIRTCHNL2_RX_FLEX_DESC_ADV_LEN_HDR_M + if (likely(!(rx_desc->status_err0_qw1 & __HBO_BIT))) + /* 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. + */ + hdr_len = le16_get_bits(rx_desc->hdrlen_flags, + __HDR_LEN_MASK); +#undef __HDR_LEN_MASK +#undef __HBO_BIT + + hdr = &rx_bufq->hdr_buf[buf_id]; - if (hdr_len) { - const void *va = (u8 *)rx_bufq->rx_buf.hdr_buf_va + - (u32)buf_id * IDPF_HDR_BUF_SIZE; + if (unlikely(!hdr_len && !skb)) { + hdr_len = idpf_rx_hsplit_wa(hdr, rx_buf, pkt_len); + pkt_len -= hdr_len; - 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_inc(&rxq->q_stats.hsplit_buf_ovf); 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); + if (libeth_rx_sync_for_cpu(hdr, hdr_len)) { + skb = idpf_rx_build_skb(hdr, hdr_len); + if (!skb) + break; + + u64_stats_update_begin(&rxq->stats_sync); + u64_stats_inc(&rxq->q_stats.hsplit_pkts); + u64_stats_update_end(&rxq->stats_sync); } + hdr->page = NULL; + +payload: + if (!libeth_rx_sync_for_cpu(rx_buf, pkt_len)) + goto skip_data; + + if (skb) + idpf_rx_add_frag(rx_buf, skb, pkt_len); + else + skb = idpf_rx_build_skb(rx_buf, pkt_len); + /* exit if we failed to retrieve a buffer */ if (!skb) break; - idpf_rx_post_buf_refill(refillq, buf_id); +skip_data: + rx_buf->page = NULL; + 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)) + if (!idpf_rx_splitq_is_eop(rx_desc) || unlikely(!skb)) continue; /* pad skb if needed (to make valid ethernet frame) */ @@ -3251,7 +3499,7 @@ bypass_hsplit: } /* send completed skb up the stack */ - napi_gro_receive(&rxq->q_vector->napi, skb); + napi_gro_receive(rxq->napi, skb); skb = NULL; /* update budget accounting */ @@ -3262,8 +3510,8 @@ bypass_hsplit: 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_add(&rxq->q_stats.packets, total_rx_pkts); + u64_stats_add(&rxq->q_stats.bytes, total_rx_bytes); u64_stats_update_end(&rxq->stats_sync); /* guarantee a trip back through this routine if there was a failure */ @@ -3273,34 +3521,41 @@ bypass_hsplit: /** * 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_id: 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, +static int idpf_rx_update_bufq_desc(struct idpf_buf_queue *bufq, u32 buf_id, struct virtchnl2_splitq_rx_buf_desc *buf_desc) { - struct idpf_rx_buf *buf; + struct libeth_fq_fp fq = { + .pp = bufq->pp, + .fqes = bufq->buf, + .truesize = bufq->truesize, + .count = bufq->desc_count, + }; 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)) + addr = libeth_rx_alloc(&fq, buf_id); + if (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) + if (!idpf_queue_has(HSPLIT_EN, bufq)) return 0; - buf_desc->hdr_addr = cpu_to_le64(bufq->rx_buf.hdr_buf_pa + - (u32)buf_id * IDPF_HDR_BUF_SIZE); + fq.pp = bufq->hdr_pp; + fq.fqes = bufq->hdr_buf; + fq.truesize = bufq->hdr_truesize; + + addr = libeth_rx_alloc(&fq, buf_id); + if (addr == DMA_MAPPING_ERROR) + return -ENOMEM; + + buf_desc->hdr_addr = cpu_to_le64(addr); return 0; } @@ -3312,38 +3567,37 @@ static int idpf_rx_update_bufq_desc(struct idpf_queue *bufq, u16 refill_desc, * * This function takes care of the buffer refill management */ -static void idpf_rx_clean_refillq(struct idpf_queue *bufq, +static void idpf_rx_clean_refillq(struct idpf_buf_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); + buf_desc = &bufq->split_buf[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); + u32 buf_id, refill_desc = refillq->ring[ntc]; bool failure; - gen = FIELD_GET(IDPF_RX_BI_GEN_M, refill_desc); - if (test_bit(__IDPF_RFLQ_GEN_CHK, refillq->flags) != gen) + if (idpf_queue_has(RFL_GEN_CHK, refillq) != + !!(refill_desc & IDPF_RX_BI_GEN_M)) break; - failure = idpf_rx_update_bufq_desc(bufq, refill_desc, - buf_desc); + buf_id = FIELD_GET(IDPF_RX_BI_BUFID_M, refill_desc); + failure = idpf_rx_update_bufq_desc(bufq, buf_id, buf_desc); if (failure) break; if (unlikely(++ntc == refillq->desc_count)) { - change_bit(__IDPF_RFLQ_GEN_CHK, refillq->flags); + idpf_queue_change(RFL_GEN_CHK, refillq); ntc = 0; } if (unlikely(++bufq_nta == bufq->desc_count)) { - buf_desc = IDPF_SPLITQ_RX_BUF_DESC(bufq, 0); + buf_desc = &bufq->split_buf[0]; bufq_nta = 0; } else { buf_desc++; @@ -3372,16 +3626,21 @@ static void idpf_rx_clean_refillq(struct idpf_queue *bufq, /** * idpf_rx_clean_refillq_all - Clean all refill queues * @bufq: buffer queue with refill queues + * @nid: ID of the closest NUMA node with memory * * 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) +static void idpf_rx_clean_refillq_all(struct idpf_buf_queue *bufq, int nid) { struct idpf_bufq_set *bufq_set; int i; + page_pool_nid_changed(bufq->pp, nid); + if (bufq->hdr_pp) + page_pool_nid_changed(bufq->hdr_pp, nid); + 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]); @@ -3437,11 +3696,11 @@ static void idpf_vport_intr_napi_dis_all(struct idpf_vport *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++) { + for (u32 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->complq); + q_vector->complq = NULL; kfree(q_vector->bufq); q_vector->bufq = NULL; kfree(q_vector->tx); @@ -3450,26 +3709,6 @@ void idpf_vport_intr_rel(struct idpf_vport *vport) 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; } @@ -3494,9 +3733,7 @@ static void idpf_vport_intr_rel_irq(struct idpf_vport *vport) 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); + kfree(free_irq(irq_num, q_vector)); } } @@ -3516,21 +3753,31 @@ static void idpf_vport_intr_dis_irq_all(struct idpf_vport *vport) /** * 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) +static u32 idpf_vport_intr_buildreg_itr(struct idpf_q_vector *q_vector) { - u32 itr_val; + u32 itr_val = q_vector->intr_reg.dyn_ctl_intena_m; + int type = IDPF_NO_ITR_UPDATE_IDX; + u16 itr = 0; + + if (q_vector->wb_on_itr) { + /* + * Trigger a software interrupt when exiting wb_on_itr, to make + * sure we catch any pending write backs that might have been + * missed due to interrupt state transition. + */ + itr_val |= q_vector->intr_reg.dyn_ctl_swint_trig_m | + q_vector->intr_reg.dyn_ctl_sw_itridx_ena_m; + type = IDPF_SW_ITR_UPDATE_IDX; + itr = IDPF_ITR_20K; + } 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)); + itr_val |= (type << q_vector->intr_reg.dyn_ctl_itridx_s) | + (itr << (q_vector->intr_reg.dyn_ctl_intrvl_s - 1)); return itr_val; } @@ -3580,38 +3827,38 @@ static void idpf_net_dim(struct idpf_q_vector *q_vector) 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]; + struct idpf_tx_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); + packets += u64_stats_read(&txq->q_stats.packets); + bytes += u64_stats_read(&txq->q_stats.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); + 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]; + struct idpf_rx_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); + packets += u64_stats_read(&rxq->q_stats.packets); + bytes += u64_stats_read(&rxq->q_stats.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); + net_dim(&q_vector->rx_dim, &dim_sample); } /** @@ -3628,8 +3875,8 @@ void idpf_vport_intr_update_itr_ena_irq(struct idpf_q_vector *q_vector) /* 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); + intval = idpf_vport_intr_buildreg_itr(q_vector); + q_vector->wb_on_itr = false; writel(intval, q_vector->intr_reg.dyn_ctl); } @@ -3637,16 +3884,19 @@ void idpf_vport_intr_update_itr_ena_irq(struct idpf_q_vector *q_vector) /** * 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) +static int idpf_vport_intr_req_irq(struct idpf_vport *vport) { struct idpf_adapter *adapter = vport->adapter; + const char *drv_name, *if_name, *vec_name; int vector, err, irq_num, vidx; - const char *vec_name; + + drv_name = dev_driver_string(&adapter->pdev->dev); + if_name = netdev_name(vport->netdev); for (vector = 0; vector < vport->num_q_vectors; vector++) { struct idpf_q_vector *q_vector = &vport->q_vectors[vector]; + char *name; vidx = vport->q_vector_idxs[vector]; irq_num = adapter->msix_entries[vidx].vector; @@ -3660,18 +3910,16 @@ static int idpf_vport_intr_req_irq(struct idpf_vport *vport, char *basename) else continue; - q_vector->name = kasprintf(GFP_KERNEL, "%s-%s-%d", - basename, vec_name, vidx); + name = kasprintf(GFP_KERNEL, "%s-%s-%s-%d", drv_name, if_name, + vec_name, vidx); err = request_irq(irq_num, idpf_vport_intr_clean_queues, 0, - q_vector->name, 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; @@ -3680,7 +3928,7 @@ 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]); + kfree(free_irq(irq_num, &vport->q_vectors[vector])); } return err; @@ -3747,9 +3995,9 @@ static void idpf_vport_intr_ena_irq_all(struct idpf_vport *vport) */ void idpf_vport_intr_deinit(struct idpf_vport *vport) { + idpf_vport_intr_dis_irq_all(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); } @@ -3847,16 +4095,17 @@ static void idpf_vport_intr_napi_ena_all(struct idpf_vport *vport) static bool idpf_tx_splitq_clean_all(struct idpf_q_vector *q_vec, int budget, int *cleaned) { - u16 num_txq = q_vec->num_txq; + u16 num_complq = q_vec->num_complq; bool clean_complete = true; int i, budget_per_q; - if (unlikely(!num_txq)) + if (unlikely(!num_complq)) 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 = DIV_ROUND_UP(budget, num_complq); + + for (i = 0; i < num_complq; i++) + clean_complete &= idpf_tx_clean_complq(q_vec->complq[i], budget_per_q, cleaned); return clean_complete; @@ -3877,13 +4126,14 @@ static bool idpf_rx_splitq_clean_all(struct idpf_q_vector *q_vec, int budget, bool clean_complete = true; int pkts_cleaned = 0; int i, budget_per_q; + int nid; /* 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]; + struct idpf_rx_queue *rxq = q_vec->rx[i]; int pkts_cleaned_per_q; pkts_cleaned_per_q = idpf_rx_splitq_clean(rxq, budget_per_q); @@ -3894,8 +4144,10 @@ static bool idpf_rx_splitq_clean_all(struct idpf_q_vector *q_vec, int budget, } *cleaned = pkts_cleaned; + nid = numa_mem_id(); + for (i = 0; i < q_vec->num_bufq; i++) - idpf_rx_clean_refillq_all(q_vec->bufq[i]); + idpf_rx_clean_refillq_all(q_vec->bufq[i], nid); return clean_complete; } @@ -3923,7 +4175,17 @@ static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget) 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) + if (!clean_complete) { + idpf_vport_intr_set_wb_on_itr(q_vector); + return budget; + } + + /* 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 && idpf_queue_has(POLL_MODE, + q_vector->tx[0]))) return budget; work_done = min_t(int, work_done, budget - 1); @@ -3933,16 +4195,10 @@ static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget) */ 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_set_wb_on_itr(q_vector); + + return work_done; } /** @@ -3953,27 +4209,28 @@ static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget) */ static void idpf_vport_intr_map_vector_to_qs(struct idpf_vport *vport) { + bool split = idpf_is_queue_model_split(vport->rxq_model); 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; + u32 i, qv_idx, q_index; for (i = 0, qv_idx = 0; i < vport->num_rxq_grp; i++) { u16 num_rxq; + if (qv_idx >= vport->num_q_vectors) + qv_idx = 0; + rx_qgrp = &vport->rxq_grps[i]; - if (idpf_is_queue_model_split(vport->rxq_model)) + if (split) 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; + for (u32 j = 0; j < num_rxq; j++) { + struct idpf_rx_queue *q; - if (idpf_is_queue_model_split(vport->rxq_model)) + if (split) q = &rx_qgrp->splitq.rxq_sets[j]->rxq; else q = rx_qgrp->singleq.rxqs[j]; @@ -3981,52 +4238,53 @@ static void idpf_vport_intr_map_vector_to_qs(struct idpf_vport *vport) q_index = q->q_vector->num_rxq; q->q_vector->rx[q_index] = q; q->q_vector->num_rxq++; - qv_idx++; + + if (split) + q->napi = &q->q_vector->napi; } - if (idpf_is_queue_model_split(vport->rxq_model)) { - for (j = 0; j < vport->num_bufqs_per_qgrp; j++) { + if (split) { + for (u32 j = 0; j < vport->num_bufqs_per_qgrp; j++) { + struct idpf_buf_queue *bufq; + bufq = &rx_qgrp->splitq.bufq_sets[j].bufq; - bufq->q_vector = &vport->q_vectors[bufq_vidx]; + bufq->q_vector = &vport->q_vectors[qv_idx]; 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; } + + qv_idx++; } + split = idpf_is_queue_model_split(vport->txq_model); + for (i = 0, qv_idx = 0; i < num_txq_grp; i++) { u16 num_txq; + if (qv_idx >= vport->num_q_vectors) + qv_idx = 0; + 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; + for (u32 j = 0; j < num_txq; j++) { + struct idpf_tx_queue *q; - q = tx_qgrp->complq; + 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++; - } else { - for (j = 0; j < num_txq; j++) { - if (qv_idx >= vport->num_q_vectors) - qv_idx = 0; + q->q_vector->tx[q->q_vector->num_txq++] = q; + } - 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++; + if (split) { + struct idpf_compl_queue *q = tx_qgrp->complq; - qv_idx++; - } + q->q_vector = &vport->q_vectors[qv_idx]; + q->q_vector->complq[q->q_vector->num_complq++] = q; } + + qv_idx++; } } @@ -4073,7 +4331,8 @@ static int idpf_vport_intr_init_vec_idx(struct idpf_vport *vport) static void idpf_vport_intr_napi_add_all(struct idpf_vport *vport) { int (*napi_poll)(struct napi_struct *napi, int budget); - u16 v_idx; + u16 v_idx, qv_idx; + int irq_num; if (idpf_is_queue_model_split(vport->txq_model)) napi_poll = idpf_vport_splitq_napi_poll; @@ -4082,12 +4341,12 @@ static void idpf_vport_intr_napi_add_all(struct idpf_vport *vport) for (v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) { struct idpf_q_vector *q_vector = &vport->q_vectors[v_idx]; + qv_idx = vport->q_vector_idxs[v_idx]; + irq_num = vport->adapter->msix_entries[qv_idx].vector; - 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); + netif_napi_add_config(vport->netdev, &q_vector->napi, + napi_poll, v_idx); + netif_napi_set_irq(&q_vector->napi, irq_num); } } @@ -4102,18 +4361,22 @@ 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; + u32 complqs_per_vector, v_idx; 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); + txqs_per_vector = DIV_ROUND_UP(vport->num_txq_grp, + vport->num_q_vectors); + rxqs_per_vector = DIV_ROUND_UP(vport->num_rxq_grp, + vport->num_q_vectors); bufqs_per_vector = vport->num_bufqs_per_qgrp * DIV_ROUND_UP(vport->num_rxq_grp, vport->num_q_vectors); + complqs_per_vector = DIV_ROUND_UP(vport->num_txq_grp, + vport->num_q_vectors); for (v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) { q_vector = &vport->q_vectors[v_idx]; @@ -4127,32 +4390,30 @@ int idpf_vport_intr_alloc(struct idpf_vport *vport) 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 *), + q_vector->tx = kcalloc(txqs_per_vector, sizeof(*q_vector->tx), GFP_KERNEL); - if (!q_vector->tx) { - err = -ENOMEM; + if (!q_vector->tx) goto error; - } - q_vector->rx = kcalloc(rxqs_per_vector, - sizeof(struct idpf_queue *), + q_vector->rx = kcalloc(rxqs_per_vector, sizeof(*q_vector->rx), GFP_KERNEL); - if (!q_vector->rx) { - err = -ENOMEM; + if (!q_vector->rx) goto error; - } if (!idpf_is_queue_model_split(vport->rxq_model)) continue; q_vector->bufq = kcalloc(bufqs_per_vector, - sizeof(struct idpf_queue *), + sizeof(*q_vector->bufq), GFP_KERNEL); - if (!q_vector->bufq) { - err = -ENOMEM; + if (!q_vector->bufq) + goto error; + + q_vector->complq = kcalloc(complqs_per_vector, + sizeof(*q_vector->complq), + GFP_KERNEL); + if (!q_vector->complq) goto error; - } } return 0; @@ -4160,7 +4421,7 @@ int idpf_vport_intr_alloc(struct idpf_vport *vport) error: idpf_vport_intr_rel(vport); - return err; + return -ENOMEM; } /** @@ -4171,7 +4432,6 @@ error: */ int idpf_vport_intr_init(struct idpf_vport *vport) { - char *int_name; int err; err = idpf_vport_intr_init_vec_idx(vport); @@ -4180,31 +4440,29 @@ int idpf_vport_intr_init(struct idpf_vport *vport) 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); + err = idpf_vport_intr_req_irq(vport); 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; } +void idpf_vport_intr_ena(struct idpf_vport *vport) +{ + idpf_vport_intr_napi_ena_all(vport); + idpf_vport_intr_ena_irq_all(vport); +} + /** * idpf_config_rss - Send virtchnl messages to configure RSS * @vport: virtual port diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h index df76493faa75..c779fe71df99 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h @@ -4,10 +4,15 @@ #ifndef _IDPF_TXRX_H_ #define _IDPF_TXRX_H_ -#include <net/page_pool/helpers.h> +#include <linux/dim.h> + +#include <net/libeth/cache.h> #include <net/tcp.h> #include <net/netdev_queues.h> +#include "idpf_lan_txrx.h" +#include "virtchnl2_lan_desc.h" + #define IDPF_LARGE_MAX_Q 256 #define IDPF_MAX_Q 16 #define IDPF_MIN_Q 2 @@ -81,7 +86,7 @@ do { \ if (unlikely(++(ntc) == (rxq)->desc_count)) { \ ntc = 0; \ - change_bit(__IDPF_Q_GEN_CHK, (rxq)->flags); \ + idpf_queue_change(GEN_CHK, rxq); \ } \ } while (0) @@ -91,16 +96,10 @@ do { \ 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; @@ -108,36 +107,17 @@ do { \ */ #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_RX_BI_GEN_M BIT(16) +#define IDPF_RX_BI_BUFID_M GENMASK(15, 0) + #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_UNUSED(txq) ((txq)->stash->buf_stack.top) #define IDPF_TX_BUF_RSV_LOW(txq) (IDPF_TX_BUF_RSV_UNUSED(txq) < \ (txq)->desc_count >> 2) @@ -147,11 +127,10 @@ do { \ */ #define IDPF_TX_COMPLQ_PENDING(txq) \ (((txq)->num_completions_pending >= (txq)->complq->num_completions ? \ - 0 : U64_MAX) + \ + 0 : U32_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 ? \ @@ -163,53 +142,14 @@ do { \ #define IDPF_TX_FLAGS_IPV4 BIT(1) #define IDPF_TX_FLAGS_IPV6 BIT(2) #define IDPF_TX_FLAGS_TUNNEL BIT(3) +#define IDPF_TX_FLAGS_TSYN BIT(4) 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; -}; +#define idpf_tx_buf libeth_sqe /** * struct idpf_buf_lifo - LIFO for managing OOO completions @@ -274,25 +214,6 @@ enum idpf_tx_ctx_desc_eipt_offload { 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 @@ -313,16 +234,7 @@ struct idpf_rx_extracted { #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_buf libeth_fqe #define IDPF_RX_MAX_PTYPE_PROTO_IDS 32 #define IDPF_RX_MAX_PTYPE_SZ (sizeof(struct virtchnl2_ptype) + \ @@ -346,72 +258,6 @@ struct idpf_rx_buf { #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), @@ -419,22 +265,9 @@ enum idpf_tunnel_state { }; 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; + bool outer_ip:1; + bool outer_frag:1; + u8 tunnel_state:6; }; /** @@ -450,23 +283,40 @@ struct idpf_rx_ptype_decoded { * 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_RFL_GEN_CHK: Refill queues are SW only, so Q_GEN acts as the HW + * bit and Q_RFL_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_CRC_EN: enable CRC offload in singleq mode + * @__IDPF_Q_HSPLIT_EN: enable header split on Rx (splitq) + * @__IDPF_Q_PTP: indicates whether the Rx timestamping is enabled for the + * queue * @__IDPF_Q_FLAGS_NBITS: Must be last */ enum idpf_queue_flags_t { __IDPF_Q_GEN_CHK, - __IDPF_RFLQ_GEN_CHK, + __IDPF_Q_RFL_GEN_CHK, __IDPF_Q_FLOW_SCH_EN, __IDPF_Q_SW_MARKER, __IDPF_Q_POLL_MODE, + __IDPF_Q_CRC_EN, + __IDPF_Q_HSPLIT_EN, + __IDPF_Q_PTP, __IDPF_Q_FLAGS_NBITS, }; +#define idpf_queue_set(f, q) __set_bit(__IDPF_Q_##f, (q)->flags) +#define idpf_queue_clear(f, q) __clear_bit(__IDPF_Q_##f, (q)->flags) +#define idpf_queue_change(f, q) __change_bit(__IDPF_Q_##f, (q)->flags) +#define idpf_queue_has(f, q) test_bit(__IDPF_Q_##f, (q)->flags) + +#define idpf_queue_has_clear(f, q) \ + __test_and_clear_bit(__IDPF_Q_##f, (q)->flags) +#define idpf_queue_assign(f, q, v) \ + __assign_bit(__IDPF_Q_##f, (q)->flags, v) + /** * struct idpf_vec_regs * @dyn_ctl_reg: Dynamic control interrupt register offset @@ -484,9 +334,13 @@ struct idpf_vec_regs { * struct idpf_intr_reg * @dyn_ctl: Dynamic control interrupt register * @dyn_ctl_intena_m: Mask for dyn_ctl interrupt enable + * @dyn_ctl_intena_msk_m: Mask for dyn_ctl interrupt enable mask * @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 + * @dyn_ctl_wb_on_itr_m: Mask for WB on ITR feature + * @dyn_ctl_sw_itridx_ena_m: Mask for SW ITR index + * @dyn_ctl_swint_trig_m: Mask for dyn_ctl SW triggered interrupt enable * @rx_itr: RX ITR register * @tx_itr: TX ITR register * @icr_ena: Interrupt cause register offset @@ -495,9 +349,13 @@ struct idpf_vec_regs { struct idpf_intr_reg { void __iomem *dyn_ctl; u32 dyn_ctl_intena_m; + u32 dyn_ctl_intena_msk_m; u32 dyn_ctl_itridx_s; u32 dyn_ctl_itridx_m; u32 dyn_ctl_intrvl_s; + u32 dyn_ctl_wb_on_itr_m; + u32 dyn_ctl_sw_itridx_ena_m; + u32 dyn_ctl_swint_trig_m; void __iomem *rx_itr; void __iomem *tx_itr; void __iomem *icr_ena; @@ -507,54 +365,69 @@ struct idpf_intr_reg { /** * 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_rxq: Number of RX queues * @num_txq: Number of TX queues + * @num_bufq: Number of buffer queues + * @num_complq: number of completion queues + * @rx: Array of RX queues to service * @tx: Array of TX queues to service + * @bufq: Array of buffer queues to service + * @complq: array of completion queues + * @intr_reg: See struct idpf_intr_reg + * @napi: napi handler + * @total_events: Number of interrupts processed + * @wb_on_itr: whether WB on ITR is enabled * @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 + * @v_idx: Vector index */ struct idpf_q_vector { + __cacheline_group_begin_aligned(read_mostly); struct idpf_vport *vport; - cpumask_t affinity_mask; - struct napi_struct napi; - u16 v_idx; - struct idpf_intr_reg intr_reg; + u16 num_rxq; u16 num_txq; - struct idpf_queue **tx; + u16 num_bufq; + u16 num_complq; + struct idpf_rx_queue **rx; + struct idpf_tx_queue **tx; + struct idpf_buf_queue **bufq; + struct idpf_compl_queue **complq; + + struct idpf_intr_reg intr_reg; + __cacheline_group_end_aligned(read_mostly); + + __cacheline_group_begin_aligned(read_write); + struct napi_struct napi; + u16 total_events; + bool wb_on_itr; + 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; + __cacheline_group_end_aligned(read_write); - u16 num_bufq; - struct idpf_queue **bufq; + __cacheline_group_begin_aligned(cold); + u16 v_idx; - u16 total_events; - char *name; + __cacheline_group_end_aligned(cold); }; +libeth_cacheline_set_assert(struct idpf_q_vector, 120, + 24 + sizeof(struct napi_struct) + + 2 * sizeof(struct dim), + 8); struct idpf_rx_queue_stats { u64_stats_t packets; @@ -574,16 +447,7 @@ struct idpf_tx_queue_stats { 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; + u64_stats_t tstamp_skipped; }; #define IDPF_ITR_DYNAMIC 1 @@ -595,74 +459,133 @@ union idpf_queue_stats { #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 'SW ITR' update in DYN_CTL register */ +#define IDPF_SW_ITR_UPDATE_IDX 2 /* 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 + * struct idpf_txq_stash - Tx buffer stash for Flow-based scheduling mode + * @buf_stack: Stack of empty buffers to store buffer info for out of order + * buffer completions. See struct idpf_buf_lifo + * @sched_buf_hash: Hash table to store buffers + */ +struct idpf_txq_stash { + struct idpf_buf_lifo buf_stack; + DECLARE_HASHTABLE(sched_buf_hash, 12); +} ____cacheline_aligned; + +/** + * struct idpf_rx_queue - software structure representing a receive queue + * @rx: universal receive descriptor array + * @single_buf: buffer descriptor array in singleq + * @desc_ring: virtual descriptor ring address + * @bufq_sets: Pointer to the array of buffer queues in splitq mode + * @napi: NAPI instance corresponding to this queue (splitq) + * @rx_buf: See struct &libeth_fqe + * @pp: Page pool pointer in singleq mode + * @netdev: &net_device corresponding to this queue + * @tail: Tail offset. Used for both queue models single and split. + * @flags: See enum idpf_queue_flags_t + * @idx: 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 + * @rxdids: Supported RX descriptor ids + * @rx_ptype_lkup: LUT of Rx ptypes + * @next_to_use: Next descriptor to use + * @next_to_clean: Next descriptor to clean + * @next_to_alloc: RX buffer to allocate at + * @skb: Pointer to the skb + * @truesize: data buffer truesize in singleq + * @cached_phc_time: Cached PHC time for the Rx queue * @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 + * @q_stats: See union idpf_rx_queue_stats + * @q_id: Queue id + * @size: Length of descriptor ring in bytes + * @dma: Physical address of ring + * @q_vector: Backreference to associated vector + * @rx_buffer_low_watermark: RX buffer low watermark * @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 + */ +struct idpf_rx_queue { + __cacheline_group_begin_aligned(read_mostly); + union { + union virtchnl2_rx_desc *rx; + struct virtchnl2_singleq_rx_buf_desc *single_buf; + + void *desc_ring; + }; + union { + struct { + struct idpf_bufq_set *bufq_sets; + struct napi_struct *napi; + }; + struct { + struct libeth_fqe *rx_buf; + struct page_pool *pp; + }; + }; + struct net_device *netdev; + void __iomem *tail; + + DECLARE_BITMAP(flags, __IDPF_Q_FLAGS_NBITS); + u16 idx; + u16 desc_count; + + u32 rxdids; + const struct libeth_rx_pt *rx_ptype_lkup; + __cacheline_group_end_aligned(read_mostly); + + __cacheline_group_begin_aligned(read_write); + u16 next_to_use; + u16 next_to_clean; + u16 next_to_alloc; + + struct sk_buff *skb; + u32 truesize; + u64 cached_phc_time; + + struct u64_stats_sync stats_sync; + struct idpf_rx_queue_stats q_stats; + __cacheline_group_end_aligned(read_write); + + __cacheline_group_begin_aligned(cold); + u32 q_id; + u32 size; + dma_addr_t dma; + + struct idpf_q_vector *q_vector; + + u16 rx_buffer_low_watermark; + u16 rx_hbuf_size; + u16 rx_buf_size; + u16 rx_max_pkt_size; + __cacheline_group_end_aligned(cold); +}; +libeth_cacheline_set_assert(struct idpf_rx_queue, 64, + 88 + sizeof(struct u64_stats_sync), + 32); + +/** + * struct idpf_tx_queue - software structure representing a transmit queue + * @base_tx: base Tx descriptor array + * @base_ctx: base Tx context descriptor array + * @flex_tx: flex Tx descriptor array + * @flex_ctx: flex Tx context descriptor array + * @desc_ring: virtual descriptor ring address + * @tx_buf: See struct idpf_tx_buf + * @txq_grp: See struct idpf_txq_group + * @dev: Device back pointer for DMA mapping + * @tail: Tail offset. Used for both queue models single and split + * @flags: See enum idpf_queue_flags_t + * @idx: 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. + * @desc_count: Number of descriptors * @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 @@ -683,108 +606,243 @@ union idpf_queue_stats { * -------------------------------- * * This gives us 8*8160 = 65280 possible unique values. + * @netdev: &net_device corresponding to this queue + * @next_to_use: Next descriptor to use + * @next_to_clean: Next descriptor to clean + * @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. + * @clean_budget: singleq only, queue cleaning budget + * @cleaned_pkts: Number of packets cleaned for the above said case + * @tx_max_bufs: Max buffers that can be transmitted with scatter-gather + * @stash: Tx buffer stash for Flow-based scheduling mode + * @compl_tag_bufid_m: Completion tag buffer id mask * @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 + * @cached_tstamp_caps: Tx timestamp capabilities negotiated with the CP + * @tstamp_task: Work that handles Tx timestamp read + * @stats_sync: See struct u64_stats_sync + * @q_stats: See union idpf_tx_queue_stats + * @q_id: Queue id + * @size: Length of descriptor ring in bytes + * @dma: Physical address of ring + * @q_vector: Backreference to associated vector */ -struct idpf_queue { - struct device *dev; - struct idpf_vport *vport; +struct idpf_tx_queue { + __cacheline_group_begin_aligned(read_mostly); union { - struct idpf_txq_group *txq_grp; - struct idpf_rxq_group *rxq_grp; + struct idpf_base_tx_desc *base_tx; + struct idpf_base_tx_ctx_desc *base_ctx; + union idpf_tx_flex_desc *flex_tx; + union idpf_flex_tx_ctx_desc *flex_ctx; + + void *desc_ring; }; - u16 idx; + struct libeth_sqe *tx_buf; + struct idpf_txq_group *txq_grp; + struct device *dev; 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; + + DECLARE_BITMAP(flags, __IDPF_Q_FLAGS_NBITS); + u16 idx; u16 desc_count; + u16 tx_min_pkt_len; + u16 compl_tag_gen_s; + + struct net_device *netdev; + __cacheline_group_end_aligned(read_mostly); + + __cacheline_group_begin_aligned(read_write); 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; + union { + u32 cleaned_bytes; + u32 clean_budget; + }; + u16 cleaned_pkts; + + u16 tx_max_bufs; + struct idpf_txq_stash *stash; + + u16 compl_tag_bufid_m; + u16 compl_tag_cur_gen; + u16 compl_tag_gen_max; + + struct idpf_ptp_vport_tx_tstamp_caps *cached_tstamp_caps; + struct work_struct *tstamp_task; + struct u64_stats_sync stats_sync; + struct idpf_tx_queue_stats q_stats; + __cacheline_group_end_aligned(read_write); - u32 cleaned_bytes; - u16 cleaned_pkts; + __cacheline_group_begin_aligned(cold); + u32 q_id; + u32 size; + dma_addr_t dma; - 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; + __cacheline_group_end_aligned(cold); +}; +libeth_cacheline_set_assert(struct idpf_tx_queue, 64, + 112 + sizeof(struct u64_stats_sync), + 24); + +/** + * struct idpf_buf_queue - software structure representing a buffer queue + * @split_buf: buffer descriptor array + * @hdr_buf: &libeth_fqe for header buffers + * @hdr_pp: &page_pool for header buffers + * @buf: &libeth_fqe for data buffers + * @pp: &page_pool for data buffers + * @tail: Tail offset + * @flags: See enum idpf_queue_flags_t + * @desc_count: Number of descriptors + * @next_to_use: Next descriptor to use + * @next_to_clean: Next descriptor to clean + * @next_to_alloc: RX buffer to allocate at + * @hdr_truesize: truesize for buffer headers + * @truesize: truesize for data buffers + * @q_id: Queue id + * @size: Length of descriptor ring in bytes + * @dma: Physical address of ring + * @q_vector: Backreference to associated vector + * @rx_buffer_low_watermark: RX buffer low watermark + * @rx_hbuf_size: Header buffer size + * @rx_buf_size: Buffer size + */ +struct idpf_buf_queue { + __cacheline_group_begin_aligned(read_mostly); + struct virtchnl2_splitq_rx_buf_desc *split_buf; + struct libeth_fqe *hdr_buf; + struct page_pool *hdr_pp; + struct libeth_fqe *buf; + struct page_pool *pp; + void __iomem *tail; + + DECLARE_BITMAP(flags, __IDPF_Q_FLAGS_NBITS); + u32 desc_count; + __cacheline_group_end_aligned(read_mostly); + + __cacheline_group_begin_aligned(read_write); + u32 next_to_use; + u32 next_to_clean; + u32 next_to_alloc; + + u32 hdr_truesize; + u32 truesize; + __cacheline_group_end_aligned(read_write); + + __cacheline_group_begin_aligned(cold); + u32 q_id; + u32 size; dma_addr_t dma; - void *desc_ring; - u16 tx_max_bufs; - u8 tx_min_pkt_len; + struct idpf_q_vector *q_vector; - u32 num_completions; + u16 rx_buffer_low_watermark; + u16 rx_hbuf_size; + u16 rx_buf_size; + __cacheline_group_end_aligned(cold); +}; +libeth_cacheline_set_assert(struct idpf_buf_queue, 64, 24, 32); - struct idpf_buf_lifo buf_stack; +/** + * struct idpf_compl_queue - software structure representing a completion queue + * @comp: completion descriptor array + * @txq_grp: See struct idpf_txq_group + * @flags: See enum idpf_queue_flags_t + * @desc_count: Number of descriptors + * @clean_budget: queue cleaning budget + * @netdev: &net_device corresponding to this queue + * @next_to_use: Next descriptor to use. Relevant in both split & single txq + * and bufq. + * @next_to_clean: Next descriptor to clean + * @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. + * @q_id: Queue id + * @size: Length of descriptor ring in bytes + * @dma: Physical address of ring + * @q_vector: Backreference to associated vector + */ +struct idpf_compl_queue { + __cacheline_group_begin_aligned(read_mostly); + struct idpf_splitq_tx_compl_desc *comp; + struct idpf_txq_group *txq_grp; - u16 compl_tag_bufid_m; - u16 compl_tag_gen_s; + DECLARE_BITMAP(flags, __IDPF_Q_FLAGS_NBITS); + u32 desc_count; - u16 compl_tag_cur_gen; - u16 compl_tag_gen_max; + u32 clean_budget; + struct net_device *netdev; + __cacheline_group_end_aligned(read_mostly); - DECLARE_HASHTABLE(sched_buf_hash, 12); -} ____cacheline_internodealigned_in_smp; + __cacheline_group_begin_aligned(read_write); + u32 next_to_use; + u32 next_to_clean; + + aligned_u64 num_completions; + __cacheline_group_end_aligned(read_write); + + __cacheline_group_begin_aligned(cold); + u32 q_id; + u32 size; + dma_addr_t dma; + + struct idpf_q_vector *q_vector; + __cacheline_group_end_aligned(cold); +}; +libeth_cacheline_set_assert(struct idpf_compl_queue, 40, 16, 24); /** * 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 + * @flags: See enum idpf_queue_flags_t * @desc_count: Descriptor count - * @dev: Device back pointer for DMA mapping + * @next_to_use: Buffer to allocate at + * @next_to_clean: Next descriptor to clean * * 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; + __cacheline_group_begin_aligned(read_mostly); + u32 *ring; + DECLARE_BITMAP(flags, __IDPF_Q_FLAGS_NBITS); - u16 *ring; - u16 desc_count; - struct device *dev; -} ____cacheline_internodealigned_in_smp; + u32 desc_count; + __cacheline_group_end_aligned(read_mostly); + + __cacheline_group_begin_aligned(read_write); + u32 next_to_use; + u32 next_to_clean; + __cacheline_group_end_aligned(read_write); +}; +libeth_cacheline_group_assert(struct idpf_sw_queue, read_mostly, 24); +libeth_cacheline_group_assert(struct idpf_sw_queue, read_write, 8); +libeth_cacheline_struct_assert(struct idpf_sw_queue, 24, 8); /** * struct idpf_rxq_set * @rxq: RX queue - * @refillq0: Pointer to refill queue 0 - * @refillq1: Pointer to refill queue 1 + * @refillq: pointers to refill queues * * 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_rx_queue rxq; + struct idpf_sw_queue *refillq[IDPF_MAX_BUFQS_PER_RXQ_GRP]; }; /** @@ -803,7 +861,7 @@ struct idpf_rxq_set { * managed by at most two bufqs (depending on performance configuration). */ struct idpf_bufq_set { - struct idpf_queue bufq; + struct idpf_buf_queue bufq; int num_refillqs; struct idpf_sw_queue *refillqs; }; @@ -829,7 +887,7 @@ struct idpf_rxq_group { union { struct { u16 num_rxq; - struct idpf_queue *rxqs[IDPF_LARGE_MAX_Q]; + struct idpf_rx_queue *rxqs[IDPF_LARGE_MAX_Q]; } singleq; struct { u16 num_rxq_sets; @@ -844,6 +902,7 @@ struct idpf_rxq_group { * @vport: Vport back pointer * @num_txq: Number of TX queues associated * @txqs: Array of TX queue pointers + * @stashes: array of OOO stashes for the queues * @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 @@ -857,13 +916,26 @@ struct idpf_txq_group { struct idpf_vport *vport; u16 num_txq; - struct idpf_queue *txqs[IDPF_LARGE_MAX_Q]; + struct idpf_tx_queue *txqs[IDPF_LARGE_MAX_Q]; + struct idpf_txq_stash *stashes; - struct idpf_queue *complq; + struct idpf_compl_queue *complq; - u32 num_completions_pending; + aligned_u64 num_completions_pending; }; +static inline int idpf_q_vector_to_mem(const struct idpf_q_vector *q_vector) +{ + u32 cpu; + + if (!q_vector) + return NUMA_NO_NODE; + + cpu = cpumask_first(&q_vector->napi.config->affinity_mask); + + return cpu < nr_cpu_ids ? cpu_to_mem(cpu) : NUMA_NO_NODE; +} + /** * idpf_size_to_txd_count - Get number of descriptors needed for large Tx frag * @size: transmit request size in bytes @@ -920,57 +992,22 @@ static inline void idpf_tx_splitq_build_desc(union idpf_tx_flex_desc *desc, } /** - * 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. + * idpf_vport_intr_set_wb_on_itr - enable descriptor writeback on disabled interrupts + * @q_vector: pointer to queue vector struct */ -static inline dma_addr_t idpf_alloc_page(struct page_pool *pool, - struct idpf_rx_buf *buf, - unsigned int buf_size) +static inline void idpf_vport_intr_set_wb_on_itr(struct idpf_q_vector *q_vector) { - 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); + struct idpf_intr_reg *reg; - if (!buf->page) - return DMA_MAPPING_ERROR; + if (q_vector->wb_on_itr) + return; - buf->truesize = buf_size; + q_vector->wb_on_itr = true; + reg = &q_vector->intr_reg; - 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)); + writel(reg->dyn_ctl_wb_on_itr_m | reg->dyn_ctl_intena_msk_m | + (IDPF_NO_ITR_UPDATE_IDX << reg->dyn_ctl_itridx_s), + reg->dyn_ctl); } int idpf_vport_singleq_napi_poll(struct napi_struct *napi, int budget); @@ -988,36 +1025,36 @@ 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); +void idpf_vport_intr_ena(struct idpf_vport *vport); 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, +struct sk_buff *idpf_rx_build_skb(const struct libeth_fqe *buf, u32 size); +void idpf_tx_buf_hw_update(struct idpf_tx_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, +netdev_tx_t idpf_tx_drop_skb(struct idpf_tx_queue *tx_q, struct sk_buff *skb); +void idpf_tx_dma_map_error(struct idpf_tx_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, +unsigned int idpf_tx_desc_count_required(struct idpf_tx_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, +netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb, + struct idpf_tx_queue *tx_q); +netdev_tx_t idpf_tx_start(struct sk_buff *skb, struct net_device *netdev); +bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_rx_queue *rxq, u16 cleaned_count); int idpf_tso(struct sk_buff *skb, struct idpf_tx_offload_params *off); +static inline bool idpf_tx_maybe_stop_common(struct idpf_tx_queue *tx_q, + u32 needed) +{ + return !netif_subqueue_maybe_stop(tx_q->netdev, tx_q->idx, + IDPF_DESC_UNUSED(tx_q), + needed, needed); +} + #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 index 629cb5cb7c9f..aba828abcb17 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c +++ b/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c @@ -97,7 +97,13 @@ static int idpf_vf_intr_reg_init(struct idpf_vport *vport) 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_intena_msk_m = VF_INT_DYN_CTLN_INTENA_MSK_M; intr->dyn_ctl_itridx_s = VF_INT_DYN_CTLN_ITR_INDX_S; + intr->dyn_ctl_intrvl_s = VF_INT_DYN_CTLN_INTERVAL_S; + intr->dyn_ctl_wb_on_itr_m = VF_INT_DYN_CTLN_WB_ON_ITR_M; + intr->dyn_ctl_swint_trig_m = VF_INT_DYN_CTLN_SWINT_TRIG_M; + intr->dyn_ctl_sw_itridx_ena_m = + VF_INT_DYN_CTLN_SW_ITR_INDX_ENA_M; spacing = IDPF_ITR_IDX_SPACING(reg_vals[vec_id].itrn_index_spacing, IDPF_VF_ITR_IDX_SPACING); diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c index a5f9b7a5effe..07a9f5ae34fd 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c @@ -1,90 +1,11 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2023 Intel Corporation */ +#include <net/libeth/rx.h> + #include "idpf.h" #include "idpf_virtchnl.h" - -#define IDPF_VC_XN_MIN_TIMEOUT_MSEC 2000 -#define IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC (60 * 1000) -#define IDPF_VC_XN_IDX_M GENMASK(7, 0) -#define IDPF_VC_XN_SALT_M GENMASK(15, 8) -#define IDPF_VC_XN_RING_LEN U8_MAX - -/** - * enum idpf_vc_xn_state - Virtchnl transaction status - * @IDPF_VC_XN_IDLE: not expecting a reply, ready to be used - * @IDPF_VC_XN_WAITING: expecting a reply, not yet received - * @IDPF_VC_XN_COMPLETED_SUCCESS: a reply was expected and received, - * buffer updated - * @IDPF_VC_XN_COMPLETED_FAILED: a reply was expected and received, but there - * was an error, buffer not updated - * @IDPF_VC_XN_SHUTDOWN: transaction object cannot be used, VC torn down - * @IDPF_VC_XN_ASYNC: transaction sent asynchronously and doesn't have the - * return context; a callback may be provided to handle - * return - */ -enum idpf_vc_xn_state { - IDPF_VC_XN_IDLE = 1, - IDPF_VC_XN_WAITING, - IDPF_VC_XN_COMPLETED_SUCCESS, - IDPF_VC_XN_COMPLETED_FAILED, - IDPF_VC_XN_SHUTDOWN, - IDPF_VC_XN_ASYNC, -}; - -struct idpf_vc_xn; -/* Callback for asynchronous messages */ -typedef int (*async_vc_cb) (struct idpf_adapter *, struct idpf_vc_xn *, - const struct idpf_ctlq_msg *); - -/** - * struct idpf_vc_xn - Data structure representing virtchnl transactions - * @completed: virtchnl event loop uses that to signal when a reply is - * available, uses kernel completion API - * @state: virtchnl event loop stores the data below, protected by the - * completion's lock. - * @reply_sz: Original size of reply, may be > reply_buf.iov_len; it will be - * truncated on its way to the receiver thread according to - * reply_buf.iov_len. - * @reply: Reference to the buffer(s) where the reply data should be written - * to. May be 0-length (then NULL address permitted) if the reply data - * should be ignored. - * @async_handler: if sent asynchronously, a callback can be provided to handle - * the reply when it's received - * @vc_op: corresponding opcode sent with this transaction - * @idx: index used as retrieval on reply receive, used for cookie - * @salt: changed every message to make unique, used for cookie - */ -struct idpf_vc_xn { - struct completion completed; - enum idpf_vc_xn_state state; - size_t reply_sz; - struct kvec reply; - async_vc_cb async_handler; - u32 vc_op; - u8 idx; - u8 salt; -}; - -/** - * struct idpf_vc_xn_params - Parameters for executing transaction - * @send_buf: kvec for send buffer - * @recv_buf: kvec for recv buffer, may be NULL, must then have zero length - * @timeout_ms: timeout to wait for reply - * @async: send message asynchronously, will not wait on completion - * @async_handler: If sent asynchronously, optional callback handler. The user - * must be careful when using async handlers as the memory for - * the recv_buf _cannot_ be on stack if this is async. - * @vc_op: virtchnl op to send - */ -struct idpf_vc_xn_params { - struct kvec send_buf; - struct kvec recv_buf; - int timeout_ms; - bool async; - async_vc_cb async_handler; - u32 vc_op; -}; +#include "idpf_ptp.h" /** * struct idpf_vc_xn_manager - Manager for tracking transactions @@ -139,7 +60,7 @@ static void idpf_handle_event_link(struct idpf_adapter *adapter, } np = netdev_priv(vport->netdev); - vport->link_speed_mbps = le32_to_cpu(v2e->link_speed); + np->link_speed_mbps = le32_to_cpu(v2e->link_speed); if (vport->link_up == v2e->link_status) return; @@ -233,6 +154,55 @@ err_kfree: return err; } +#if IS_ENABLED(CONFIG_PTP_1588_CLOCK) +/** + * idpf_ptp_is_mb_msg - Check if the message is PTP-related + * @op: virtchnl opcode + * + * Return: true if msg is PTP-related, false otherwise. + */ +static bool idpf_ptp_is_mb_msg(u32 op) +{ + switch (op) { + case VIRTCHNL2_OP_PTP_GET_DEV_CLK_TIME: + case VIRTCHNL2_OP_PTP_GET_CROSS_TIME: + case VIRTCHNL2_OP_PTP_SET_DEV_CLK_TIME: + case VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_FINE: + case VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_TIME: + case VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP_CAPS: + case VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP: + return true; + default: + return false; + } +} + +/** + * idpf_prepare_ptp_mb_msg - Prepare PTP related message + * + * @adapter: Driver specific private structure + * @op: virtchnl opcode + * @ctlq_msg: Corresponding control queue message + */ +static void idpf_prepare_ptp_mb_msg(struct idpf_adapter *adapter, u32 op, + struct idpf_ctlq_msg *ctlq_msg) +{ + /* If the message is PTP-related and the secondary mailbox is available, + * send the message through the secondary mailbox. + */ + if (!idpf_ptp_is_mb_msg(op) || !adapter->ptp->secondary_mbx.valid) + return; + + ctlq_msg->opcode = idpf_mbq_opc_send_msg_to_peer_drv; + ctlq_msg->func_id = adapter->ptp->secondary_mbx.peer_mbx_q_id; + ctlq_msg->host_id = adapter->ptp->secondary_mbx.peer_id; +} +#else /* !CONFIG_PTP_1588_CLOCK */ +static void idpf_prepare_ptp_mb_msg(struct idpf_adapter *adapter, u32 op, + struct idpf_ctlq_msg *ctlq_msg) +{ } +#endif /* CONFIG_PTP_1588_CLOCK */ + /** * idpf_send_mb_msg - Send message over mailbox * @adapter: Driver specific private structure @@ -276,6 +246,9 @@ int idpf_send_mb_msg(struct idpf_adapter *adapter, u32 op, ctlq_msg->opcode = idpf_mbq_opc_send_msg_to_cp; ctlq_msg->func_id = 0; + + idpf_prepare_ptp_mb_msg(adapter, op, ctlq_msg); + ctlq_msg->data_len = msg_size; ctlq_msg->cookie.mbx.chnl_opcode = op; ctlq_msg->cookie.mbx.chnl_retval = 0; @@ -447,8 +420,8 @@ static void idpf_vc_xn_push_free(struct idpf_vc_xn_manager *vcxn_mngr, * >= @recv_buf.iov_len, but we never overflow @@recv_buf_iov_base). < 0 for * error. */ -static ssize_t idpf_vc_xn_exec(struct idpf_adapter *adapter, - const struct idpf_vc_xn_params *params) +ssize_t idpf_vc_xn_exec(struct idpf_adapter *adapter, + const struct idpf_vc_xn_params *params) { const struct kvec *send_buf = ¶ms->send_buf; struct idpf_vc_xn *xn; @@ -515,8 +488,10 @@ static ssize_t idpf_vc_xn_exec(struct idpf_adapter *adapter, retval = -ENXIO; goto only_unlock; case IDPF_VC_XN_WAITING: - dev_notice_ratelimited(&adapter->pdev->dev, "Transaction timed-out (op %d, %dms)\n", - params->vc_op, params->timeout_ms); + dev_notice_ratelimited(&adapter->pdev->dev, + "Transaction timed-out (op:%d cookie:%04x vc_op:%d salt:%02x timeout:%dms)\n", + params->vc_op, cookie, xn->vc_op, + xn->salt, params->timeout_ms); retval = -ETIME; break; case IDPF_VC_XN_COMPLETED_SUCCESS: @@ -610,14 +585,16 @@ idpf_vc_xn_forward_reply(struct idpf_adapter *adapter, return -EINVAL; } xn = &adapter->vcxn_mngr->ring[xn_idx]; + idpf_vc_xn_lock(xn); salt = FIELD_GET(IDPF_VC_XN_SALT_M, msg_info); if (xn->salt != salt) { - dev_err_ratelimited(&adapter->pdev->dev, "Transaction salt does not match (%02x != %02x)\n", - xn->salt, salt); + dev_err_ratelimited(&adapter->pdev->dev, "Transaction salt does not match (exp:%d@%02x(%d) != got:%d@%02x)\n", + xn->vc_op, xn->salt, xn->state, + ctlq_msg->cookie.mbx.chnl_opcode, salt); + idpf_vc_xn_unlock(xn); return -EINVAL; } - idpf_vc_xn_lock(xn); switch (xn->state) { case IDPF_VC_XN_WAITING: /* success */ @@ -664,7 +641,7 @@ idpf_vc_xn_forward_reply(struct idpf_adapter *adapter, if (ctlq_msg->data_len) { payload = ctlq_msg->ctx.indirect.payload->va; - payload_size = ctlq_msg->ctx.indirect.payload->size; + payload_size = ctlq_msg->data_len; } xn->reply_sz = payload_size; @@ -750,7 +727,7 @@ static int idpf_wait_for_marker_event(struct idpf_vport *vport) int i; for (i = 0; i < vport->num_txq; i++) - set_bit(__IDPF_Q_SW_MARKER, vport->txqs[i]->flags); + idpf_queue_set(SW_MARKER, vport->txqs[i]); event = wait_event_timeout(vport->sw_marker_wq, test_and_clear_bit(IDPF_VPORT_SW_MARKER, @@ -758,7 +735,7 @@ static int idpf_wait_for_marker_event(struct idpf_vport *vport) msecs_to_jiffies(500)); for (i = 0; i < vport->num_txq; i++) - clear_bit(__IDPF_Q_POLL_MODE, vport->txqs[i]->flags); + idpf_queue_clear(POLL_MODE, vport->txqs[i]); if (event) return 0; @@ -894,7 +871,8 @@ static int idpf_send_get_caps_msg(struct idpf_adapter *adapter) VIRTCHNL2_CAP_MACFILTER | VIRTCHNL2_CAP_SPLITQ_QSCHED | VIRTCHNL2_CAP_PROMISC | - VIRTCHNL2_CAP_LOOPBACK); + VIRTCHNL2_CAP_LOOPBACK | + VIRTCHNL2_CAP_PTP); xn_params.vc_op = VIRTCHNL2_OP_GET_CAPS; xn_params.send_buf.iov_base = ∩︀ @@ -1092,7 +1070,6 @@ 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) { @@ -1111,6 +1088,8 @@ static int __idpf_queue_reg_init(struct idpf_vport *vport, u32 *reg_vals, u16 num_rxq = rx_qgrp->singleq.num_rxq; for (j = 0; j < num_rxq && k < num_regs; j++, k++) { + struct idpf_rx_queue *q; + q = rx_qgrp->singleq.rxqs[j]; q->tail = idpf_get_reg_addr(adapter, reg_vals[k]); @@ -1123,6 +1102,8 @@ static int __idpf_queue_reg_init(struct idpf_vport *vport, u32 *reg_vals, u8 num_bufqs = vport->num_bufqs_per_qgrp; for (j = 0; j < num_bufqs && k < num_regs; j++, k++) { + struct idpf_buf_queue *q; + q = &rx_qgrp->splitq.bufq_sets[j].bufq; q->tail = idpf_get_reg_addr(adapter, reg_vals[k]); @@ -1253,12 +1234,12 @@ int idpf_send_create_vport_msg(struct idpf_adapter *adapter, vport_msg->vport_type = cpu_to_le16(VIRTCHNL2_VPORT_TYPE_DEFAULT); vport_msg->vport_index = cpu_to_le16(idx); - if (adapter->req_tx_splitq) + if (adapter->req_tx_splitq || !IS_ENABLED(CONFIG_IDPF_SINGLEQ)) 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) + if (adapter->req_rx_splitq || !IS_ENABLED(CONFIG_IDPF_SINGLEQ)) vport_msg->rxq_model = cpu_to_le16(VIRTCHNL2_QUEUE_MODEL_SPLIT); else vport_msg->rxq_model = cpu_to_le16(VIRTCHNL2_QUEUE_MODEL_SINGLE); @@ -1290,10 +1271,6 @@ int idpf_send_create_vport_msg(struct idpf_adapter *adapter, err = reply_sz; goto free_vport_params; } - if (reply_sz < IDPF_CTLQ_MAX_BUF_LEN) { - err = -EIO; - goto free_vport_params; - } return 0; @@ -1320,10 +1297,17 @@ int idpf_check_supported_desc_ids(struct idpf_vport *vport) vport_msg = adapter->vport_params_recvd[vport->idx]; + if (!IS_ENABLED(CONFIG_IDPF_SINGLEQ) && + (vport_msg->rxq_model == VIRTCHNL2_QUEUE_MODEL_SINGLE || + vport_msg->txq_model == VIRTCHNL2_QUEUE_MODEL_SINGLE)) { + pci_err(adapter->pdev, "singleq mode requested, but not compiled-in\n"); + return -EOPNOTSUPP; + } + 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 (idpf_is_queue_model_split(vport->rxq_model)) { 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); @@ -1333,7 +1317,7 @@ int idpf_check_supported_desc_ids(struct idpf_vport *vport) vport->base_rxd = true; } - if (vport->txq_model != VIRTCHNL2_QUEUE_MODEL_SPLIT) + if (!idpf_is_queue_model_split(vport->txq_model)) return 0; if ((tx_desc_ids & MIN_SUPPORT_TXDID) != MIN_SUPPORT_TXDID) { @@ -1449,19 +1433,19 @@ static int idpf_send_config_tx_queues_msg(struct idpf_vport *vport) qi[k].model = cpu_to_le16(vport->txq_model); qi[k].type = - cpu_to_le32(tx_qgrp->txqs[j]->q_type); + cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_TX); 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]; + struct idpf_tx_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)) + if (idpf_queue_has(FLOW_SCH_EN, q)) qi[k].sched_mode = cpu_to_le16(VIRTCHNL2_TXQ_SCHED_MODE_FLOW); else @@ -1478,11 +1462,11 @@ static int idpf_send_config_tx_queues_msg(struct idpf_vport *vport) 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].type = cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION); 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)) + if (idpf_queue_has(FLOW_SCH_EN, tx_qgrp->complq)) sched_mode = VIRTCHNL2_TXQ_SCHED_MODE_FLOW; else sched_mode = VIRTCHNL2_TXQ_SCHED_MODE_QUEUE; @@ -1567,17 +1551,18 @@ static int idpf_send_config_rx_queues_msg(struct idpf_vport *vport) goto setup_rxqs; for (j = 0; j < vport->num_bufqs_per_qgrp; j++, k++) { - struct idpf_queue *bufq = + struct idpf_buf_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].type = + cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_RX_BUFFER); 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].buffer_notif_stride = IDPF_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)) @@ -1591,35 +1576,47 @@ setup_rxqs: num_rxq = rx_qgrp->singleq.num_rxq; for (j = 0; j < num_rxq; j++, k++) { - struct idpf_queue *rxq; + const struct idpf_bufq_set *sets; + struct idpf_rx_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); + sets = rxq->bufq_sets; + + /* In splitq mode, RXQ buffer size should be + * set to that of the first buffer queue + * associated with this RXQ. + */ + rxq->rx_buf_size = sets[0].bufq.rx_buf_size; + + qi[k].rx_bufq1_id = cpu_to_le16(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); + cpu_to_le16(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) { + rxq->rx_hbuf_size = sets[0].bufq.rx_hbuf_size; + + if (idpf_queue_has(HSPLIT_EN, rxq)) { qi[k].qflags |= cpu_to_le16(VIRTCHNL2_RXQ_HDR_SPLIT); qi[k].hdr_buffer_size = cpu_to_le16(rxq->rx_hbuf_size); } + +common_qi_fields: 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].type = cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_RX); 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); @@ -1706,7 +1703,7 @@ static int idpf_send_ena_dis_queues_msg(struct idpf_vport *vport, bool ena) 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].type = cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_TX); 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); } @@ -1720,7 +1717,7 @@ static int idpf_send_ena_dis_queues_msg(struct idpf_vport *vport, bool ena) 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].type = cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION); qc[k].start_queue_id = cpu_to_le32(tx_qgrp->complq->q_id); qc[k].num_queues = cpu_to_le32(IDPF_NUMQ_PER_CHUNK); } @@ -1741,12 +1738,12 @@ setup_rx: 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); + cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_RX); } 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); + cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_RX); } qc[k].num_queues = cpu_to_le32(IDPF_NUMQ_PER_CHUNK); } @@ -1761,10 +1758,11 @@ setup_rx: 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; + const struct idpf_buf_queue *q; q = &rx_qgrp->splitq.bufq_sets[j].bufq; - qc[k].type = cpu_to_le32(q->q_type); + qc[k].type = + cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_RX_BUFFER); qc[k].start_queue_id = cpu_to_le32(q->q_id); qc[k].num_queues = cpu_to_le32(IDPF_NUMQ_PER_CHUNK); } @@ -1849,7 +1847,8 @@ int idpf_send_map_unmap_queue_vector_msg(struct idpf_vport *vport, bool map) 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_type = + cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_TX); vqv[k].queue_id = cpu_to_le32(tx_qgrp->txqs[j]->q_id); if (idpf_is_queue_model_split(vport->txq_model)) { @@ -1879,14 +1878,15 @@ int idpf_send_map_unmap_queue_vector_msg(struct idpf_vport *vport, bool map) num_rxq = rx_qgrp->singleq.num_rxq; for (j = 0; j < num_rxq; j++, k++) { - struct idpf_queue *rxq; + struct idpf_rx_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_type = + cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_RX); 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); @@ -1975,7 +1975,7 @@ int idpf_send_disable_queues_msg(struct idpf_vport *vport) * queues virtchnl message is sent */ for (i = 0; i < vport->num_txq; i++) - set_bit(__IDPF_Q_POLL_MODE, vport->txqs[i]->flags); + idpf_queue_set(POLL_MODE, vport->txqs[i]); /* schedule the napi to receive all the marker packets */ local_bh_disable(); @@ -2469,39 +2469,52 @@ do_memcpy: * @frag: fragmentation allowed * */ -static void idpf_fill_ptype_lookup(struct idpf_rx_ptype_decoded *ptype, +static void idpf_fill_ptype_lookup(struct libeth_rx_pt *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; + ptype->outer_ip = LIBETH_RX_PT_OUTER_IPV4; else - ptype->outer_ip_ver = IDPF_RX_PTYPE_OUTER_IPV6; + ptype->outer_ip = LIBETH_RX_PT_OUTER_IPV6; if (frag) { - ptype->outer_frag = IDPF_RX_PTYPE_FRAG; + ptype->outer_frag = LIBETH_RX_PT_FRAG; pstate->outer_frag = true; } } else { - ptype->tunnel_type = IDPF_RX_PTYPE_TUNNEL_IP_IP; + ptype->tunnel_type = LIBETH_RX_PT_TUNNEL_IP_IP; pstate->tunnel_state = IDPF_PTYPE_TUNNEL_IP; if (ipv4) - ptype->tunnel_end_prot = - IDPF_RX_PTYPE_TUNNEL_END_IPV4; + ptype->tunnel_end_prot = LIBETH_RX_PT_TUNNEL_END_IPV4; else - ptype->tunnel_end_prot = - IDPF_RX_PTYPE_TUNNEL_END_IPV6; + ptype->tunnel_end_prot = LIBETH_RX_PT_TUNNEL_END_IPV6; if (frag) - ptype->tunnel_end_frag = IDPF_RX_PTYPE_FRAG; + ptype->tunnel_end_frag = LIBETH_RX_PT_FRAG; } } +static void idpf_finalize_ptype_lookup(struct libeth_rx_pt *ptype) +{ + if (ptype->payload_layer == LIBETH_RX_PT_PAYLOAD_L2 && + ptype->inner_prot) + ptype->payload_layer = LIBETH_RX_PT_PAYLOAD_L4; + else if (ptype->payload_layer == LIBETH_RX_PT_PAYLOAD_L2 && + ptype->outer_ip) + ptype->payload_layer = LIBETH_RX_PT_PAYLOAD_L3; + else if (ptype->outer_ip == LIBETH_RX_PT_OUTER_L2) + ptype->payload_layer = LIBETH_RX_PT_PAYLOAD_L2; + else + ptype->payload_layer = LIBETH_RX_PT_PAYLOAD_NONE; + + libeth_rx_pt_gen_hash_type(ptype); +} + /** * idpf_send_get_rx_ptype_msg - Send virtchnl for ptype info * @vport: virtual port data structure @@ -2512,7 +2525,7 @@ int idpf_send_get_rx_ptype_msg(struct idpf_vport *vport) { struct virtchnl2_get_ptype_info *get_ptype_info __free(kfree) = NULL; struct virtchnl2_get_ptype_info *ptype_info __free(kfree) = NULL; - struct idpf_rx_ptype_decoded *ptype_lkup = vport->rx_ptype_lkup; + struct libeth_rx_pt *ptype_lkup __free(kfree) = NULL; int max_ptype, ptypes_recvd = 0, ptype_offset; struct idpf_adapter *adapter = vport->adapter; struct idpf_vc_xn_params xn_params = {}; @@ -2520,12 +2533,17 @@ int idpf_send_get_rx_ptype_msg(struct idpf_vport *vport) ssize_t reply_sz; int i, j, k; + if (vport->rx_ptype_lkup) + return 0; + 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_lkup = kcalloc(max_ptype, sizeof(*ptype_lkup), GFP_KERNEL); + if (!ptype_lkup) + return -ENOMEM; get_ptype_info = kzalloc(sizeof(*get_ptype_info), GFP_KERNEL); if (!get_ptype_info) @@ -2556,9 +2574,6 @@ int idpf_send_get_rx_ptype_msg(struct idpf_vport *vport) if (reply_sz < 0) return reply_sz; - if (reply_sz < IDPF_CTLQ_MAX_BUF_LEN) - return -EIO; - ptypes_recvd += le16_to_cpu(ptype_info->num_ptypes); if (ptypes_recvd > max_ptype) return -EINVAL; @@ -2583,16 +2598,13 @@ int idpf_send_get_rx_ptype_msg(struct idpf_vport *vport) /* 0xFFFF indicates end of ptypes */ if (le16_to_cpu(ptype->ptype_id_10) == IDPF_INVALID_PTYPE_ID) - return 0; + goto out; 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) { @@ -2600,18 +2612,18 @@ int idpf_send_get_rx_ptype_msg(struct idpf_vport *vport) if (pstate.tunnel_state == IDPF_PTYPE_TUNNEL_IP) { ptype_lkup[k].tunnel_type = - IDPF_RX_PTYPE_TUNNEL_IP_GRENAT; + LIBETH_RX_PT_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; + LIBETH_RX_PT_OUTER_L2; if (pstate.tunnel_state == IDPF_TUN_IP_GRE) { ptype_lkup[k].tunnel_type = - IDPF_RX_PTYPE_TUNNEL_IP_GRENAT_MAC; + LIBETH_RX_PT_TUNNEL_IP_GRENAT_MAC; pstate.tunnel_state |= IDPF_PTYPE_TUNNEL_IP_GRENAT_MAC; } @@ -2638,23 +2650,23 @@ int idpf_send_get_rx_ptype_msg(struct idpf_vport *vport) break; case VIRTCHNL2_PROTO_HDR_UDP: ptype_lkup[k].inner_prot = - IDPF_RX_PTYPE_INNER_PROT_UDP; + LIBETH_RX_PT_INNER_UDP; break; case VIRTCHNL2_PROTO_HDR_TCP: ptype_lkup[k].inner_prot = - IDPF_RX_PTYPE_INNER_PROT_TCP; + LIBETH_RX_PT_INNER_TCP; break; case VIRTCHNL2_PROTO_HDR_SCTP: ptype_lkup[k].inner_prot = - IDPF_RX_PTYPE_INNER_PROT_SCTP; + LIBETH_RX_PT_INNER_SCTP; break; case VIRTCHNL2_PROTO_HDR_ICMP: ptype_lkup[k].inner_prot = - IDPF_RX_PTYPE_INNER_PROT_ICMP; + LIBETH_RX_PT_INNER_ICMP; break; case VIRTCHNL2_PROTO_HDR_PAY: ptype_lkup[k].payload_layer = - IDPF_RX_PTYPE_PAYLOAD_LAYER_PAY2; + LIBETH_RX_PT_PAYLOAD_L2; break; case VIRTCHNL2_PROTO_HDR_ICMPV6: case VIRTCHNL2_PROTO_HDR_IPV6_EH: @@ -2708,9 +2720,14 @@ int idpf_send_get_rx_ptype_msg(struct idpf_vport *vport) break; } } + + idpf_finalize_ptype_lookup(&ptype_lkup[k]); } } +out: + vport->rx_ptype_lkup = no_free_ptr(ptype_lkup); + return 0; } @@ -2984,6 +3001,11 @@ restart: goto err_intr_req; } + err = idpf_ptp_init(adapter); + if (err) + pci_err(adapter->pdev, "PTP init failed, err=%pe\n", + ERR_PTR(err)); + idpf_init_avail_queues(adapter); /* Skew the delay for init tasks for each function based on fn number @@ -3022,7 +3044,6 @@ init_failed: adapter->state = __IDPF_VER_CHECK; if (adapter->vcxn_mngr) idpf_vc_xn_shutdown(adapter->vcxn_mngr); - 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)); @@ -3037,13 +3058,23 @@ init_failed: */ void idpf_vc_core_deinit(struct idpf_adapter *adapter) { + bool remove_in_prog; + if (!test_bit(IDPF_VC_CORE_INIT, adapter->flags)) return; - idpf_vc_xn_shutdown(adapter->vcxn_mngr); + /* Avoid transaction timeouts when called during reset */ + remove_in_prog = test_bit(IDPF_REMOVE_IN_PROG, adapter->flags); + if (!remove_in_prog) + idpf_vc_xn_shutdown(adapter->vcxn_mngr); + + idpf_ptp_release(adapter); idpf_deinit_task(adapter); idpf_intr_rel(adapter); + if (remove_in_prog) + idpf_vc_xn_shutdown(adapter->vcxn_mngr); + cancel_delayed_work_sync(&adapter->serv_task); cancel_delayed_work_sync(&adapter->mbx_task); @@ -3105,6 +3136,7 @@ void idpf_vport_init(struct idpf_vport *vport, struct idpf_vport_max_q *max_q) u16 rx_itr[] = {2, 8, 32, 96, 128}; struct idpf_rss_data *rss_data; u16 idx = vport->idx; + int err; vport_config = adapter->vport_config[idx]; rss_data = &vport_config->user_config.rss_data; @@ -3125,7 +3157,7 @@ void idpf_vport_init(struct idpf_vport *vport, struct idpf_vport_max_q *max_q) 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; + vport->max_mtu = le16_to_cpu(vport_msg->max_mtu) - LIBETH_RX_LL_LEN; /* Initialize Tx and Rx profiles for Dynamic Interrupt Moderation */ memcpy(vport->rx_itr_profile, rx_itr, IDPF_DIM_PROFILE_SLOTS); @@ -3139,6 +3171,18 @@ void idpf_vport_init(struct idpf_vport *vport, struct idpf_vport_max_q *max_q) idpf_vport_alloc_vec_indexes(vport); vport->crc_enable = adapter->crc_enable; + + if (!(vport_msg->vport_flags & + cpu_to_le16(VIRTCHNL2_VPORT_UPLINK_PORT))) + return; + + err = idpf_ptp_get_vport_tstamps_caps(vport); + if (err) { + pci_dbg(vport->adapter->pdev, "Tx timestamping not supported\n"); + return; + } + + INIT_WORK(&vport->tstamp_task, idpf_tstamp_task); } /** @@ -3242,7 +3286,6 @@ static int __idpf_vport_queue_ids_init(struct idpf_vport *vport, int num_qids, u32 q_type) { - struct idpf_queue *q; int i, j, k = 0; switch (q_type) { @@ -3250,11 +3293,8 @@ static int __idpf_vport_queue_ids_init(struct idpf_vport *vport, 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++) { + 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: @@ -3268,12 +3308,13 @@ static int __idpf_vport_queue_ids_init(struct idpf_vport *vport, num_rxq = rx_qgrp->singleq.num_rxq; for (j = 0; j < num_rxq && k < num_qids; j++, k++) { + struct idpf_rx_queue *q; + 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; @@ -3282,8 +3323,6 @@ static int __idpf_vport_queue_ids_init(struct idpf_vport *vport, 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: @@ -3292,9 +3331,10 @@ static int __idpf_vport_queue_ids_init(struct idpf_vport *vport, u8 num_bufqs = vport->num_bufqs_per_qgrp; for (j = 0; j < num_bufqs && k < num_qids; j++, k++) { + struct idpf_buf_queue *q; + q = &rx_qgrp->splitq.bufq_sets[j].bufq; q->q_id = qids[k]; - q->q_type = VIRTCHNL2_QUEUE_TYPE_RX_BUFFER; } } break; diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h index 83da5d8da56b..3522c1238ea2 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h @@ -4,6 +4,88 @@ #ifndef _IDPF_VIRTCHNL_H_ #define _IDPF_VIRTCHNL_H_ +#define IDPF_VC_XN_MIN_TIMEOUT_MSEC 2000 +#define IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC (60 * 1000) +#define IDPF_VC_XN_IDX_M GENMASK(7, 0) +#define IDPF_VC_XN_SALT_M GENMASK(15, 8) +#define IDPF_VC_XN_RING_LEN U8_MAX + +/** + * enum idpf_vc_xn_state - Virtchnl transaction status + * @IDPF_VC_XN_IDLE: not expecting a reply, ready to be used + * @IDPF_VC_XN_WAITING: expecting a reply, not yet received + * @IDPF_VC_XN_COMPLETED_SUCCESS: a reply was expected and received, buffer + * updated + * @IDPF_VC_XN_COMPLETED_FAILED: a reply was expected and received, but there + * was an error, buffer not updated + * @IDPF_VC_XN_SHUTDOWN: transaction object cannot be used, VC torn down + * @IDPF_VC_XN_ASYNC: transaction sent asynchronously and doesn't have the + * return context; a callback may be provided to handle + * return + */ +enum idpf_vc_xn_state { + IDPF_VC_XN_IDLE = 1, + IDPF_VC_XN_WAITING, + IDPF_VC_XN_COMPLETED_SUCCESS, + IDPF_VC_XN_COMPLETED_FAILED, + IDPF_VC_XN_SHUTDOWN, + IDPF_VC_XN_ASYNC, +}; + +struct idpf_vc_xn; +/* Callback for asynchronous messages */ +typedef int (*async_vc_cb) (struct idpf_adapter *, struct idpf_vc_xn *, + const struct idpf_ctlq_msg *); + +/** + * struct idpf_vc_xn - Data structure representing virtchnl transactions + * @completed: virtchnl event loop uses that to signal when a reply is + * available, uses kernel completion API + * @state: virtchnl event loop stores the data below, protected by the + * completion's lock. + * @reply_sz: Original size of reply, may be > reply_buf.iov_len; it will be + * truncated on its way to the receiver thread according to + * reply_buf.iov_len. + * @reply: Reference to the buffer(s) where the reply data should be written + * to. May be 0-length (then NULL address permitted) if the reply data + * should be ignored. + * @async_handler: if sent asynchronously, a callback can be provided to handle + * the reply when it's received + * @vc_op: corresponding opcode sent with this transaction + * @idx: index used as retrieval on reply receive, used for cookie + * @salt: changed every message to make unique, used for cookie + */ +struct idpf_vc_xn { + struct completion completed; + enum idpf_vc_xn_state state; + size_t reply_sz; + struct kvec reply; + async_vc_cb async_handler; + u32 vc_op; + u8 idx; + u8 salt; +}; + +/** + * struct idpf_vc_xn_params - Parameters for executing transaction + * @send_buf: kvec for send buffer + * @recv_buf: kvec for recv buffer, may be NULL, must then have zero length + * @timeout_ms: timeout to wait for reply + * @async: send message asynchronously, will not wait on completion + * @async_handler: If sent asynchronously, optional callback handler. The user + * must be careful when using async handlers as the memory for + * the recv_buf _cannot_ be on stack if this is async. + * @vc_op: virtchnl op to send + */ +struct idpf_vc_xn_params { + struct kvec send_buf; + struct kvec recv_buf; + int timeout_ms; + bool async; + async_vc_cb async_handler; + u32 vc_op; +}; + struct idpf_adapter; struct idpf_netdev_priv; struct idpf_vec_regs; @@ -11,6 +93,8 @@ struct idpf_vport; struct idpf_vport_max_q; struct idpf_vport_user_config_data; +ssize_t idpf_vc_xn_exec(struct idpf_adapter *adapter, + const struct idpf_vc_xn_params *params); 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); diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c new file mode 100644 index 000000000000..bdcc54a5fb56 --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c @@ -0,0 +1,615 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2024 Intel Corporation */ + +#include "idpf.h" +#include "idpf_ptp.h" +#include "idpf_virtchnl.h" + +/** + * idpf_ptp_get_caps - Send virtchnl get ptp capabilities message + * @adapter: Driver specific private structure + * + * Send virtchnl get PTP capabilities message. + * + * Return: 0 on success, -errno on failure. + */ +int idpf_ptp_get_caps(struct idpf_adapter *adapter) +{ + struct virtchnl2_ptp_get_caps *recv_ptp_caps_msg __free(kfree) = NULL; + struct virtchnl2_ptp_get_caps send_ptp_caps_msg = { + .caps = cpu_to_le32(VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME | + VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME_MB | + VIRTCHNL2_CAP_PTP_GET_CROSS_TIME | + VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME_MB | + VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK_MB | + VIRTCHNL2_CAP_PTP_TX_TSTAMPS_MB) + }; + struct idpf_vc_xn_params xn_params = { + .vc_op = VIRTCHNL2_OP_PTP_GET_CAPS, + .send_buf.iov_base = &send_ptp_caps_msg, + .send_buf.iov_len = sizeof(send_ptp_caps_msg), + .timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC, + }; + struct virtchnl2_ptp_clk_adj_reg_offsets clk_adj_offsets; + struct virtchnl2_ptp_clk_reg_offsets clock_offsets; + struct idpf_ptp_secondary_mbx *scnd_mbx; + struct idpf_ptp *ptp = adapter->ptp; + enum idpf_ptp_access access_type; + u32 temp_offset; + int reply_sz; + + recv_ptp_caps_msg = kzalloc(sizeof(struct virtchnl2_ptp_get_caps), + GFP_KERNEL); + if (!recv_ptp_caps_msg) + return -ENOMEM; + + xn_params.recv_buf.iov_base = recv_ptp_caps_msg; + xn_params.recv_buf.iov_len = sizeof(*recv_ptp_caps_msg); + + reply_sz = idpf_vc_xn_exec(adapter, &xn_params); + if (reply_sz < 0) + return reply_sz; + else if (reply_sz != sizeof(*recv_ptp_caps_msg)) + return -EIO; + + ptp->caps = le32_to_cpu(recv_ptp_caps_msg->caps); + ptp->base_incval = le64_to_cpu(recv_ptp_caps_msg->base_incval); + ptp->max_adj = le32_to_cpu(recv_ptp_caps_msg->max_adj); + + scnd_mbx = &ptp->secondary_mbx; + scnd_mbx->peer_mbx_q_id = le16_to_cpu(recv_ptp_caps_msg->peer_mbx_q_id); + + /* if the ptp_mb_q_id holds invalid value (0xffff), the secondary + * mailbox is not supported. + */ + scnd_mbx->valid = scnd_mbx->peer_mbx_q_id != 0xffff; + if (scnd_mbx->valid) + scnd_mbx->peer_id = recv_ptp_caps_msg->peer_id; + + /* Determine the access type for the PTP features */ + idpf_ptp_get_features_access(adapter); + + access_type = ptp->get_dev_clk_time_access; + if (access_type != IDPF_PTP_DIRECT) + goto discipline_clock; + + clock_offsets = recv_ptp_caps_msg->clk_offsets; + + temp_offset = le32_to_cpu(clock_offsets.dev_clk_ns_l); + ptp->dev_clk_regs.dev_clk_ns_l = idpf_get_reg_addr(adapter, + temp_offset); + temp_offset = le32_to_cpu(clock_offsets.dev_clk_ns_h); + ptp->dev_clk_regs.dev_clk_ns_h = idpf_get_reg_addr(adapter, + temp_offset); + temp_offset = le32_to_cpu(clock_offsets.phy_clk_ns_l); + ptp->dev_clk_regs.phy_clk_ns_l = idpf_get_reg_addr(adapter, + temp_offset); + temp_offset = le32_to_cpu(clock_offsets.phy_clk_ns_h); + ptp->dev_clk_regs.phy_clk_ns_h = idpf_get_reg_addr(adapter, + temp_offset); + temp_offset = le32_to_cpu(clock_offsets.cmd_sync_trigger); + ptp->dev_clk_regs.cmd_sync = idpf_get_reg_addr(adapter, temp_offset); + +discipline_clock: + access_type = ptp->adj_dev_clk_time_access; + if (access_type != IDPF_PTP_DIRECT) + return 0; + + clk_adj_offsets = recv_ptp_caps_msg->clk_adj_offsets; + + /* Device clock offsets */ + temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_cmd_type); + ptp->dev_clk_regs.cmd = idpf_get_reg_addr(adapter, temp_offset); + temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_incval_l); + ptp->dev_clk_regs.incval_l = idpf_get_reg_addr(adapter, temp_offset); + temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_incval_h); + ptp->dev_clk_regs.incval_h = idpf_get_reg_addr(adapter, temp_offset); + temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_shadj_l); + ptp->dev_clk_regs.shadj_l = idpf_get_reg_addr(adapter, temp_offset); + temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_shadj_h); + ptp->dev_clk_regs.shadj_h = idpf_get_reg_addr(adapter, temp_offset); + + /* PHY clock offsets */ + temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_cmd_type); + ptp->dev_clk_regs.phy_cmd = idpf_get_reg_addr(adapter, temp_offset); + temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_incval_l); + ptp->dev_clk_regs.phy_incval_l = idpf_get_reg_addr(adapter, + temp_offset); + temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_incval_h); + ptp->dev_clk_regs.phy_incval_h = idpf_get_reg_addr(adapter, + temp_offset); + temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_shadj_l); + ptp->dev_clk_regs.phy_shadj_l = idpf_get_reg_addr(adapter, temp_offset); + temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_shadj_h); + ptp->dev_clk_regs.phy_shadj_h = idpf_get_reg_addr(adapter, temp_offset); + + return 0; +} + +/** + * idpf_ptp_get_dev_clk_time - Send virtchnl get device clk time message + * @adapter: Driver specific private structure + * @dev_clk_time: Pointer to the device clock structure where the value is set + * + * Send virtchnl get time message to get the time of the clock. + * + * Return: 0 on success, -errno otherwise. + */ +int idpf_ptp_get_dev_clk_time(struct idpf_adapter *adapter, + struct idpf_ptp_dev_timers *dev_clk_time) +{ + struct virtchnl2_ptp_get_dev_clk_time get_dev_clk_time_msg; + struct idpf_vc_xn_params xn_params = { + .vc_op = VIRTCHNL2_OP_PTP_GET_DEV_CLK_TIME, + .send_buf.iov_base = &get_dev_clk_time_msg, + .send_buf.iov_len = sizeof(get_dev_clk_time_msg), + .recv_buf.iov_base = &get_dev_clk_time_msg, + .recv_buf.iov_len = sizeof(get_dev_clk_time_msg), + .timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC, + }; + int reply_sz; + u64 dev_time; + + reply_sz = idpf_vc_xn_exec(adapter, &xn_params); + if (reply_sz < 0) + return reply_sz; + if (reply_sz != sizeof(get_dev_clk_time_msg)) + return -EIO; + + dev_time = le64_to_cpu(get_dev_clk_time_msg.dev_time_ns); + dev_clk_time->dev_clk_time_ns = dev_time; + + return 0; +} + +/** + * idpf_ptp_set_dev_clk_time - Send virtchnl set device time message + * @adapter: Driver specific private structure + * @time: New time value + * + * Send virtchnl set time message to set the time of the clock. + * + * Return: 0 on success, -errno otherwise. + */ +int idpf_ptp_set_dev_clk_time(struct idpf_adapter *adapter, u64 time) +{ + struct virtchnl2_ptp_set_dev_clk_time set_dev_clk_time_msg = { + .dev_time_ns = cpu_to_le64(time), + }; + struct idpf_vc_xn_params xn_params = { + .vc_op = VIRTCHNL2_OP_PTP_SET_DEV_CLK_TIME, + .send_buf.iov_base = &set_dev_clk_time_msg, + .send_buf.iov_len = sizeof(set_dev_clk_time_msg), + .recv_buf.iov_base = &set_dev_clk_time_msg, + .recv_buf.iov_len = sizeof(set_dev_clk_time_msg), + .timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC, + }; + int reply_sz; + + reply_sz = idpf_vc_xn_exec(adapter, &xn_params); + if (reply_sz < 0) + return reply_sz; + if (reply_sz != sizeof(set_dev_clk_time_msg)) + return -EIO; + + return 0; +} + +/** + * idpf_ptp_adj_dev_clk_time - Send virtchnl adj device clock time message + * @adapter: Driver specific private structure + * @delta: Offset in nanoseconds to adjust the time by + * + * Send virtchnl adj time message to adjust the clock by the indicated delta. + * + * Return: 0 on success, -errno otherwise. + */ +int idpf_ptp_adj_dev_clk_time(struct idpf_adapter *adapter, s64 delta) +{ + struct virtchnl2_ptp_adj_dev_clk_time adj_dev_clk_time_msg = { + .delta = cpu_to_le64(delta), + }; + struct idpf_vc_xn_params xn_params = { + .vc_op = VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_TIME, + .send_buf.iov_base = &adj_dev_clk_time_msg, + .send_buf.iov_len = sizeof(adj_dev_clk_time_msg), + .recv_buf.iov_base = &adj_dev_clk_time_msg, + .recv_buf.iov_len = sizeof(adj_dev_clk_time_msg), + .timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC, + }; + int reply_sz; + + reply_sz = idpf_vc_xn_exec(adapter, &xn_params); + if (reply_sz < 0) + return reply_sz; + if (reply_sz != sizeof(adj_dev_clk_time_msg)) + return -EIO; + + return 0; +} + +/** + * idpf_ptp_adj_dev_clk_fine - Send virtchnl adj time message + * @adapter: Driver specific private structure + * @incval: Source timer increment value per clock cycle + * + * Send virtchnl adj fine message to adjust the frequency of the clock by + * incval. + * + * Return: 0 on success, -errno otherwise. + */ +int idpf_ptp_adj_dev_clk_fine(struct idpf_adapter *adapter, u64 incval) +{ + struct virtchnl2_ptp_adj_dev_clk_fine adj_dev_clk_fine_msg = { + .incval = cpu_to_le64(incval), + }; + struct idpf_vc_xn_params xn_params = { + .vc_op = VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_FINE, + .send_buf.iov_base = &adj_dev_clk_fine_msg, + .send_buf.iov_len = sizeof(adj_dev_clk_fine_msg), + .recv_buf.iov_base = &adj_dev_clk_fine_msg, + .recv_buf.iov_len = sizeof(adj_dev_clk_fine_msg), + .timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC, + }; + int reply_sz; + + reply_sz = idpf_vc_xn_exec(adapter, &xn_params); + if (reply_sz < 0) + return reply_sz; + if (reply_sz != sizeof(adj_dev_clk_fine_msg)) + return -EIO; + + return 0; +} + +/** + * idpf_ptp_get_vport_tstamps_caps - Send virtchnl to get tstamps caps for vport + * @vport: Virtual port structure + * + * Send virtchnl get vport tstamps caps message to receive the set of tstamp + * capabilities per vport. + * + * Return: 0 on success, -errno otherwise. + */ +int idpf_ptp_get_vport_tstamps_caps(struct idpf_vport *vport) +{ + struct virtchnl2_ptp_get_vport_tx_tstamp_caps send_tx_tstamp_caps; + struct virtchnl2_ptp_get_vport_tx_tstamp_caps *rcv_tx_tstamp_caps; + struct virtchnl2_ptp_tx_tstamp_latch_caps tx_tstamp_latch_caps; + struct idpf_ptp_vport_tx_tstamp_caps *tstamp_caps; + struct idpf_ptp_tx_tstamp *ptp_tx_tstamp, *tmp; + struct idpf_vc_xn_params xn_params = { + .vc_op = VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP_CAPS, + .send_buf.iov_base = &send_tx_tstamp_caps, + .send_buf.iov_len = sizeof(send_tx_tstamp_caps), + .recv_buf.iov_len = IDPF_CTLQ_MAX_BUF_LEN, + .timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC, + }; + enum idpf_ptp_access tstamp_access, get_dev_clk_access; + struct idpf_ptp *ptp = vport->adapter->ptp; + struct list_head *head; + int err = 0, reply_sz; + u16 num_latches; + u32 size; + + if (!ptp) + return -EOPNOTSUPP; + + tstamp_access = ptp->tx_tstamp_access; + get_dev_clk_access = ptp->get_dev_clk_time_access; + if (tstamp_access == IDPF_PTP_NONE || + get_dev_clk_access == IDPF_PTP_NONE) + return -EOPNOTSUPP; + + rcv_tx_tstamp_caps = kzalloc(IDPF_CTLQ_MAX_BUF_LEN, GFP_KERNEL); + if (!rcv_tx_tstamp_caps) + return -ENOMEM; + + send_tx_tstamp_caps.vport_id = cpu_to_le32(vport->vport_id); + xn_params.recv_buf.iov_base = rcv_tx_tstamp_caps; + + reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params); + if (reply_sz < 0) { + err = reply_sz; + goto get_tstamp_caps_out; + } + + num_latches = le16_to_cpu(rcv_tx_tstamp_caps->num_latches); + size = struct_size(rcv_tx_tstamp_caps, tstamp_latches, num_latches); + if (reply_sz != size) { + err = -EIO; + goto get_tstamp_caps_out; + } + + size = struct_size(tstamp_caps, tx_tstamp_status, num_latches); + tstamp_caps = kzalloc(size, GFP_KERNEL); + if (!tstamp_caps) { + err = -ENOMEM; + goto get_tstamp_caps_out; + } + + tstamp_caps->access = true; + tstamp_caps->num_entries = num_latches; + + INIT_LIST_HEAD(&tstamp_caps->latches_in_use); + INIT_LIST_HEAD(&tstamp_caps->latches_free); + + spin_lock_init(&tstamp_caps->latches_lock); + spin_lock_init(&tstamp_caps->status_lock); + + tstamp_caps->tstamp_ns_lo_bit = rcv_tx_tstamp_caps->tstamp_ns_lo_bit; + + for (u16 i = 0; i < tstamp_caps->num_entries; i++) { + __le32 offset_l, offset_h; + + ptp_tx_tstamp = kzalloc(sizeof(*ptp_tx_tstamp), GFP_KERNEL); + if (!ptp_tx_tstamp) { + err = -ENOMEM; + goto err_free_ptp_tx_stamp_list; + } + + tx_tstamp_latch_caps = rcv_tx_tstamp_caps->tstamp_latches[i]; + + if (tstamp_access != IDPF_PTP_DIRECT) + goto skip_offsets; + + offset_l = tx_tstamp_latch_caps.tx_latch_reg_offset_l; + offset_h = tx_tstamp_latch_caps.tx_latch_reg_offset_h; + ptp_tx_tstamp->tx_latch_reg_offset_l = le32_to_cpu(offset_l); + ptp_tx_tstamp->tx_latch_reg_offset_h = le32_to_cpu(offset_h); + +skip_offsets: + ptp_tx_tstamp->idx = tx_tstamp_latch_caps.index; + + list_add(&ptp_tx_tstamp->list_member, + &tstamp_caps->latches_free); + + tstamp_caps->tx_tstamp_status[i].state = IDPF_PTP_FREE; + } + + vport->tx_tstamp_caps = tstamp_caps; + kfree(rcv_tx_tstamp_caps); + + return 0; + +err_free_ptp_tx_stamp_list: + head = &tstamp_caps->latches_free; + list_for_each_entry_safe(ptp_tx_tstamp, tmp, head, list_member) { + list_del(&ptp_tx_tstamp->list_member); + kfree(ptp_tx_tstamp); + } + + kfree(tstamp_caps); +get_tstamp_caps_out: + kfree(rcv_tx_tstamp_caps); + + return err; +} + +/** + * idpf_ptp_update_tstamp_tracker - Update the Tx timestamp tracker based on + * the skb compatibility. + * @caps: Tx timestamp capabilities that monitor the latch status + * @skb: skb for which the tstamp value is returned through virtchnl message + * @current_state: Current state of the Tx timestamp latch + * @expected_state: Expected state of the Tx timestamp latch + * + * Find a proper skb tracker for which the Tx timestamp is received and change + * the state to expected value. + * + * Return: true if the tracker has been found and updated, false otherwise. + */ +static bool +idpf_ptp_update_tstamp_tracker(struct idpf_ptp_vport_tx_tstamp_caps *caps, + struct sk_buff *skb, + enum idpf_ptp_tx_tstamp_state current_state, + enum idpf_ptp_tx_tstamp_state expected_state) +{ + bool updated = false; + + spin_lock(&caps->status_lock); + for (u16 i = 0; i < caps->num_entries; i++) { + struct idpf_ptp_tx_tstamp_status *status; + + status = &caps->tx_tstamp_status[i]; + + if (skb == status->skb && status->state == current_state) { + status->state = expected_state; + updated = true; + break; + } + } + spin_unlock(&caps->status_lock); + + return updated; +} + +/** + * idpf_ptp_get_tstamp_value - Get the Tx timestamp value and provide it + * back to the skb. + * @vport: Virtual port structure + * @tstamp_latch: Tx timestamp latch structure fulfilled by the Control Plane + * @ptp_tx_tstamp: Tx timestamp latch to add to the free list + * + * Read the value of the Tx timestamp for a given latch received from the + * Control Plane, extend it to 64 bit and provide back to the skb. + * + * Return: 0 on success, -errno otherwise. + */ +static int +idpf_ptp_get_tstamp_value(struct idpf_vport *vport, + struct virtchnl2_ptp_tx_tstamp_latch *tstamp_latch, + struct idpf_ptp_tx_tstamp *ptp_tx_tstamp) +{ + struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps; + struct skb_shared_hwtstamps shhwtstamps; + bool state_upd = false; + u8 tstamp_ns_lo_bit; + u64 tstamp; + + tx_tstamp_caps = vport->tx_tstamp_caps; + tstamp_ns_lo_bit = tx_tstamp_caps->tstamp_ns_lo_bit; + + ptp_tx_tstamp->tstamp = le64_to_cpu(tstamp_latch->tstamp); + ptp_tx_tstamp->tstamp >>= tstamp_ns_lo_bit; + + state_upd = idpf_ptp_update_tstamp_tracker(tx_tstamp_caps, + ptp_tx_tstamp->skb, + IDPF_PTP_READ_VALUE, + IDPF_PTP_FREE); + if (!state_upd) + return -EINVAL; + + tstamp = idpf_ptp_extend_ts(vport, ptp_tx_tstamp->tstamp); + shhwtstamps.hwtstamp = ns_to_ktime(tstamp); + skb_tstamp_tx(ptp_tx_tstamp->skb, &shhwtstamps); + consume_skb(ptp_tx_tstamp->skb); + + list_add(&ptp_tx_tstamp->list_member, + &tx_tstamp_caps->latches_free); + + return 0; +} + +/** + * idpf_ptp_get_tx_tstamp_async_handler - Async callback for getting Tx tstamps + * @adapter: Driver specific private structure + * @xn: transaction for message + * @ctlq_msg: received message + * + * Read the tstamps Tx tstamp values from a received message and put them + * directly to the skb. The number of timestamps to read is specified by + * the virtchnl message. + * + * Return: 0 on success, -errno otherwise. + */ +static int +idpf_ptp_get_tx_tstamp_async_handler(struct idpf_adapter *adapter, + struct idpf_vc_xn *xn, + const struct idpf_ctlq_msg *ctlq_msg) +{ + struct virtchnl2_ptp_get_vport_tx_tstamp_latches *recv_tx_tstamp_msg; + struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps; + struct virtchnl2_ptp_tx_tstamp_latch tstamp_latch; + struct idpf_ptp_tx_tstamp *tx_tstamp, *tmp; + struct idpf_vport *tstamp_vport = NULL; + struct list_head *head; + u16 num_latches; + u32 vport_id; + int err = 0; + + recv_tx_tstamp_msg = ctlq_msg->ctx.indirect.payload->va; + vport_id = le32_to_cpu(recv_tx_tstamp_msg->vport_id); + + idpf_for_each_vport(adapter, vport) { + if (!vport) + continue; + + if (vport->vport_id == vport_id) { + tstamp_vport = vport; + break; + } + } + + if (!tstamp_vport || !tstamp_vport->tx_tstamp_caps) + return -EINVAL; + + tx_tstamp_caps = tstamp_vport->tx_tstamp_caps; + num_latches = le16_to_cpu(recv_tx_tstamp_msg->num_latches); + + spin_lock_bh(&tx_tstamp_caps->latches_lock); + head = &tx_tstamp_caps->latches_in_use; + + for (u16 i = 0; i < num_latches; i++) { + tstamp_latch = recv_tx_tstamp_msg->tstamp_latches[i]; + + if (!tstamp_latch.valid) + continue; + + if (list_empty(head)) { + err = -ENOBUFS; + goto unlock; + } + + list_for_each_entry_safe(tx_tstamp, tmp, head, list_member) { + if (tstamp_latch.index == tx_tstamp->idx) { + list_del(&tx_tstamp->list_member); + err = idpf_ptp_get_tstamp_value(tstamp_vport, + &tstamp_latch, + tx_tstamp); + if (err) + goto unlock; + + break; + } + } + } + +unlock: + spin_unlock_bh(&tx_tstamp_caps->latches_lock); + + return err; +} + +/** + * idpf_ptp_get_tx_tstamp - Send virtchnl get Tx timestamp latches message + * @vport: Virtual port structure + * + * Send virtchnl get Tx tstamp message to read the value of the HW timestamp. + * The message contains a list of indexes set in the Tx descriptors. + * + * Return: 0 on success, -errno otherwise. + */ +int idpf_ptp_get_tx_tstamp(struct idpf_vport *vport) +{ + struct virtchnl2_ptp_get_vport_tx_tstamp_latches *send_tx_tstamp_msg; + struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps; + struct idpf_vc_xn_params xn_params = { + .vc_op = VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP, + .timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC, + .async = true, + .async_handler = idpf_ptp_get_tx_tstamp_async_handler, + }; + struct idpf_ptp_tx_tstamp *ptp_tx_tstamp; + int reply_sz, size, msg_size; + struct list_head *head; + bool state_upd; + u16 id = 0; + + tx_tstamp_caps = vport->tx_tstamp_caps; + head = &tx_tstamp_caps->latches_in_use; + + size = struct_size(send_tx_tstamp_msg, tstamp_latches, + tx_tstamp_caps->num_entries); + send_tx_tstamp_msg = kzalloc(size, GFP_KERNEL); + if (!send_tx_tstamp_msg) + return -ENOMEM; + + spin_lock_bh(&tx_tstamp_caps->latches_lock); + list_for_each_entry(ptp_tx_tstamp, head, list_member) { + u8 idx; + + state_upd = idpf_ptp_update_tstamp_tracker(tx_tstamp_caps, + ptp_tx_tstamp->skb, + IDPF_PTP_REQUEST, + IDPF_PTP_READ_VALUE); + if (!state_upd) + continue; + + idx = ptp_tx_tstamp->idx; + send_tx_tstamp_msg->tstamp_latches[id].index = idx; + id++; + } + spin_unlock_bh(&tx_tstamp_caps->latches_lock); + + msg_size = struct_size(send_tx_tstamp_msg, tstamp_latches, id); + send_tx_tstamp_msg->vport_id = cpu_to_le32(vport->vport_id); + send_tx_tstamp_msg->num_latches = cpu_to_le16(id); + xn_params.send_buf.iov_base = send_tx_tstamp_msg; + xn_params.send_buf.iov_len = msg_size; + + reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params); + kfree(send_tx_tstamp_msg); + + return min(reply_sz, 0); +} diff --git a/drivers/net/ethernet/intel/idpf/virtchnl2.h b/drivers/net/ethernet/intel/idpf/virtchnl2.h index 4a3c4454d25a..11b8f6f05799 100644 --- a/drivers/net/ethernet/intel/idpf/virtchnl2.h +++ b/drivers/net/ethernet/intel/idpf/virtchnl2.h @@ -4,6 +4,8 @@ #ifndef _VIRTCHNL2_H_ #define _VIRTCHNL2_H_ +#include <linux/if_ether.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. @@ -17,8 +19,6 @@ * 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. */ @@ -68,6 +68,16 @@ enum virtchnl2_op { VIRTCHNL2_OP_ADD_MAC_ADDR = 535, VIRTCHNL2_OP_DEL_MAC_ADDR = 536, VIRTCHNL2_OP_CONFIG_PROMISCUOUS_MODE = 537, + + /* TimeSync opcodes */ + VIRTCHNL2_OP_PTP_GET_CAPS = 541, + VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP = 542, + VIRTCHNL2_OP_PTP_GET_DEV_CLK_TIME = 543, + VIRTCHNL2_OP_PTP_GET_CROSS_TIME = 544, + VIRTCHNL2_OP_PTP_SET_DEV_CLK_TIME = 545, + VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_FINE = 546, + VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_TIME = 547, + VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP_CAPS = 548, }; /** @@ -555,11 +565,19 @@ VIRTCHNL2_CHECK_STRUCT_LEN(32, virtchnl2_queue_reg_chunk); struct virtchnl2_queue_reg_chunks { __le16 num_chunks; u8 pad[6]; - struct virtchnl2_queue_reg_chunk chunks[]; + struct virtchnl2_queue_reg_chunk chunks[] __counted_by_le(num_chunks); }; VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_queue_reg_chunks); /** + * enum virtchnl2_vport_flags - Vport flags that indicate vport capabilities. + * @VIRTCHNL2_VPORT_UPLINK_PORT: Representatives of underlying physical ports + */ +enum virtchnl2_vport_flags { + VIRTCHNL2_VPORT_UPLINK_PORT = BIT(0), +}; + +/** * struct virtchnl2_create_vport - Create vport config info. * @vport_type: See enum virtchnl2_vport_type. * @txq_model: See virtchnl2_queue_model. @@ -577,7 +595,7 @@ VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_queue_reg_chunks); * @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. + * @vport_flags: See enum virtchnl2_vport_flags. * @rx_desc_ids: See VIRTCHNL2_RX_DESC_IDS definitions. * @tx_desc_ids: See VIRTCHNL2_TX_DESC_IDS definitions. * @pad1: Padding. @@ -610,7 +628,7 @@ struct virtchnl2_create_vport { __le16 max_mtu; __le32 vport_id; u8 default_mac_addr[ETH_ALEN]; - __le16 pad; + __le16 vport_flags; __le64 rx_desc_ids; __le64 tx_desc_ids; u8 pad1[72]; @@ -703,7 +721,7 @@ struct virtchnl2_config_tx_queues { __le32 vport_id; __le16 num_qinfo; u8 pad[10]; - struct virtchnl2_txq_info qinfo[]; + struct virtchnl2_txq_info qinfo[] __counted_by_le(num_qinfo); }; VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_config_tx_queues); @@ -782,7 +800,7 @@ struct virtchnl2_config_rx_queues { __le32 vport_id; __le16 num_qinfo; u8 pad[18]; - struct virtchnl2_rxq_info qinfo[]; + struct virtchnl2_rxq_info qinfo[] __counted_by_le(num_qinfo); }; VIRTCHNL2_CHECK_STRUCT_LEN(24, virtchnl2_config_rx_queues); @@ -868,7 +886,7 @@ VIRTCHNL2_CHECK_STRUCT_LEN(32, virtchnl2_vector_chunk); struct virtchnl2_vector_chunks { __le16 num_vchunks; u8 pad[14]; - struct virtchnl2_vector_chunk vchunks[]; + struct virtchnl2_vector_chunk vchunks[] __counted_by_le(num_vchunks); }; VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_vector_chunks); @@ -912,7 +930,7 @@ struct virtchnl2_rss_lut { __le16 lut_entries_start; __le16 lut_entries; u8 pad[4]; - __le32 lut[]; + __le32 lut[] __counted_by_le(lut_entries); }; VIRTCHNL2_CHECK_STRUCT_LEN(12, virtchnl2_rss_lut); @@ -977,7 +995,7 @@ struct virtchnl2_ptype { u8 ptype_id_8; u8 proto_id_count; __le16 pad; - __le16 proto_id[]; + __le16 proto_id[] __counted_by(proto_id_count); } __packed __aligned(2); VIRTCHNL2_CHECK_STRUCT_LEN(6, virtchnl2_ptype); @@ -1104,7 +1122,7 @@ struct virtchnl2_rss_key { __le32 vport_id; __le16 key_len; u8 pad; - u8 key_flex[]; + u8 key_flex[] __counted_by_le(key_len); } __packed; VIRTCHNL2_CHECK_STRUCT_LEN(7, virtchnl2_rss_key); @@ -1131,7 +1149,7 @@ VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_queue_chunk); struct virtchnl2_queue_chunks { __le16 num_chunks; u8 pad[6]; - struct virtchnl2_queue_chunk chunks[]; + struct virtchnl2_queue_chunk chunks[] __counted_by_le(num_chunks); }; VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_queue_chunks); @@ -1195,7 +1213,7 @@ struct virtchnl2_queue_vector_maps { __le32 vport_id; __le16 num_qv_maps; u8 pad[10]; - struct virtchnl2_queue_vector qv_maps[]; + struct virtchnl2_queue_vector qv_maps[] __counted_by_le(num_qv_maps); }; VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_queue_vector_maps); @@ -1247,7 +1265,7 @@ struct virtchnl2_mac_addr_list { __le32 vport_id; __le16 num_mac_addr; u8 pad[2]; - struct virtchnl2_mac_addr mac_addr_list[]; + struct virtchnl2_mac_addr mac_addr_list[] __counted_by_le(num_mac_addr); }; VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_mac_addr_list); @@ -1270,4 +1288,296 @@ struct virtchnl2_promisc_info { }; VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_promisc_info); +/** + * enum virtchnl2_ptp_caps - PTP capabilities + * @VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME: direct access to get the time of + * device clock + * @VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME_MB: mailbox access to get the time of + * device clock + * @VIRTCHNL2_CAP_PTP_GET_CROSS_TIME: direct access to cross timestamp + * @VIRTCHNL2_CAP_PTP_GET_CROSS_TIME_MB: mailbox access to cross timestamp + * @VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME: direct access to set the time of + * device clock + * @VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME_MB: mailbox access to set the time of + * device clock + * @VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK: direct access to adjust the time of device + * clock + * @VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK_MB: mailbox access to adjust the time of + * device clock + * @VIRTCHNL2_CAP_PTP_TX_TSTAMPS: direct access to the Tx timestamping + * @VIRTCHNL2_CAP_PTP_TX_TSTAMPS_MB: mailbox access to the Tx timestamping + * + * PF/VF negotiates a set of supported PTP capabilities with the Control Plane. + * There are two access methods - mailbox (_MB) and direct. + * PTP capabilities enables Main Timer operations: get/set/adjust Main Timer, + * cross timestamping and the Tx timestamping. + */ +enum virtchnl2_ptp_caps { + VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME = BIT(0), + VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME_MB = BIT(1), + VIRTCHNL2_CAP_PTP_GET_CROSS_TIME = BIT(2), + VIRTCHNL2_CAP_PTP_GET_CROSS_TIME_MB = BIT(3), + VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME = BIT(4), + VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME_MB = BIT(5), + VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK = BIT(6), + VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK_MB = BIT(7), + VIRTCHNL2_CAP_PTP_TX_TSTAMPS = BIT(8), + VIRTCHNL2_CAP_PTP_TX_TSTAMPS_MB = BIT(9), +}; + +/** + * struct virtchnl2_ptp_clk_reg_offsets - Offsets of device and PHY clocks + * registers. + * @dev_clk_ns_l: Device clock low register offset + * @dev_clk_ns_h: Device clock high register offset + * @phy_clk_ns_l: PHY clock low register offset + * @phy_clk_ns_h: PHY clock high register offset + * @cmd_sync_trigger: The command sync trigger register offset + * @pad: Padding for future extensions + */ +struct virtchnl2_ptp_clk_reg_offsets { + __le32 dev_clk_ns_l; + __le32 dev_clk_ns_h; + __le32 phy_clk_ns_l; + __le32 phy_clk_ns_h; + __le32 cmd_sync_trigger; + u8 pad[4]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(24, virtchnl2_ptp_clk_reg_offsets); + +/** + * struct virtchnl2_ptp_cross_time_reg_offsets - Offsets of the device cross + * time registers. + * @sys_time_ns_l: System time low register offset + * @sys_time_ns_h: System time high register offset + * @cmd_sync_trigger: The command sync trigger register offset + * @pad: Padding for future extensions + */ +struct virtchnl2_ptp_cross_time_reg_offsets { + __le32 sys_time_ns_l; + __le32 sys_time_ns_h; + __le32 cmd_sync_trigger; + u8 pad[4]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_cross_time_reg_offsets); + +/** + * struct virtchnl2_ptp_clk_adj_reg_offsets - Offsets of device and PHY clocks + * adjustments registers. + * @dev_clk_cmd_type: Device clock command type register offset + * @dev_clk_incval_l: Device clock increment value low register offset + * @dev_clk_incval_h: Device clock increment value high registers offset + * @dev_clk_shadj_l: Device clock shadow adjust low register offset + * @dev_clk_shadj_h: Device clock shadow adjust high register offset + * @phy_clk_cmd_type: PHY timer command type register offset + * @phy_clk_incval_l: PHY timer increment value low register offset + * @phy_clk_incval_h: PHY timer increment value high register offset + * @phy_clk_shadj_l: PHY timer shadow adjust low register offset + * @phy_clk_shadj_h: PHY timer shadow adjust high register offset + */ +struct virtchnl2_ptp_clk_adj_reg_offsets { + __le32 dev_clk_cmd_type; + __le32 dev_clk_incval_l; + __le32 dev_clk_incval_h; + __le32 dev_clk_shadj_l; + __le32 dev_clk_shadj_h; + __le32 phy_clk_cmd_type; + __le32 phy_clk_incval_l; + __le32 phy_clk_incval_h; + __le32 phy_clk_shadj_l; + __le32 phy_clk_shadj_h; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(40, virtchnl2_ptp_clk_adj_reg_offsets); + +/** + * struct virtchnl2_ptp_tx_tstamp_latch_caps - PTP Tx timestamp latch + * capabilities. + * @tx_latch_reg_offset_l: Tx timestamp latch low register offset + * @tx_latch_reg_offset_h: Tx timestamp latch high register offset + * @index: Latch index provided to the Tx descriptor + * @pad: Padding for future extensions + */ +struct virtchnl2_ptp_tx_tstamp_latch_caps { + __le32 tx_latch_reg_offset_l; + __le32 tx_latch_reg_offset_h; + u8 index; + u8 pad[7]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_tx_tstamp_latch_caps); + +/** + * struct virtchnl2_ptp_get_vport_tx_tstamp_caps - Structure that defines Tx + * tstamp entries. + * @vport_id: Vport number + * @num_latches: Total number of latches + * @tstamp_ns_lo_bit: First bit for nanosecond part of the timestamp + * @tstamp_ns_hi_bit: Last bit for nanosecond part of the timestamp + * @pad: Padding for future tstamp granularity extensions + * @tstamp_latches: Capabilities of Tx timestamp entries + * + * PF/VF sends this message to negotiate the Tx timestamp latches for each + * Vport. + * + * Associated with VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP_CAPS. + */ +struct virtchnl2_ptp_get_vport_tx_tstamp_caps { + __le32 vport_id; + __le16 num_latches; + u8 tstamp_ns_lo_bit; + u8 tstamp_ns_hi_bit; + u8 pad[8]; + + struct virtchnl2_ptp_tx_tstamp_latch_caps tstamp_latches[] + __counted_by_le(num_latches); +}; +VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_get_vport_tx_tstamp_caps); + +/** + * struct virtchnl2_ptp_get_caps - Get PTP capabilities + * @caps: PTP capability bitmap. See enum virtchnl2_ptp_caps + * @max_adj: The maximum possible frequency adjustment + * @base_incval: The default timer increment value + * @peer_mbx_q_id: ID of the PTP Device Control daemon queue + * @peer_id: Peer ID for PTP Device Control daemon + * @secondary_mbx: Indicates to the driver that it should create a secondary + * mailbox to inetract with control plane for PTP + * @pad: Padding for future extensions + * @clk_offsets: Main timer and PHY registers offsets + * @cross_time_offsets: Cross time registers offsets + * @clk_adj_offsets: Offsets needed to adjust the PHY and the main timer + * + * PF/VF sends this message to negotiate PTP capabilities. CP updates bitmap + * with supported features and fulfills appropriate structures. + * If HW uses primary MBX for PTP: secondary_mbx is set to false. + * If HW uses secondary MBX for PTP: secondary_mbx is set to true. + * Control plane has 2 MBX and the driver has 1 MBX, send to peer + * driver may be used to send a message using valid ptp_peer_mb_q_id and + * ptp_peer_id. + * If HW does not use send to peer driver: secondary_mbx is no care field and + * peer_mbx_q_id holds invalid value (0xFFFF). + * + * Associated with VIRTCHNL2_OP_PTP_GET_CAPS. + */ +struct virtchnl2_ptp_get_caps { + __le32 caps; + __le32 max_adj; + __le64 base_incval; + __le16 peer_mbx_q_id; + u8 peer_id; + u8 secondary_mbx; + u8 pad[4]; + + struct virtchnl2_ptp_clk_reg_offsets clk_offsets; + struct virtchnl2_ptp_cross_time_reg_offsets cross_time_offsets; + struct virtchnl2_ptp_clk_adj_reg_offsets clk_adj_offsets; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(104, virtchnl2_ptp_get_caps); + +/** + * struct virtchnl2_ptp_tx_tstamp_latch - Structure that describes tx tstamp + * values, index and validity. + * @tstamp: Timestamp value + * @index: Timestamp index from which the value is read + * @valid: Timestamp validity + * @pad: Padding for future extensions + */ +struct virtchnl2_ptp_tx_tstamp_latch { + __le64 tstamp; + u8 index; + u8 valid; + u8 pad[6]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_tx_tstamp_latch); + +/** + * struct virtchnl2_ptp_get_vport_tx_tstamp_latches - Tx timestamp latches + * associated with the vport. + * @vport_id: Number of vport that requests the timestamp + * @num_latches: Number of latches + * @get_devtime_with_txtstmp: Flag to request device time along with Tx timestamp + * @pad: Padding for future extensions + * @device_time: device time if get_devtime_with_txtstmp was set in request + * @tstamp_latches: PTP TX timestamp latch + * + * PF/VF sends this message to receive a specified number of timestamps + * entries. + * + * Associated with VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP. + */ +struct virtchnl2_ptp_get_vport_tx_tstamp_latches { + __le32 vport_id; + __le16 num_latches; + u8 get_devtime_with_txtstmp; + u8 pad[1]; + __le64 device_time; + + struct virtchnl2_ptp_tx_tstamp_latch tstamp_latches[] + __counted_by_le(num_latches); +}; +VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_get_vport_tx_tstamp_latches); + +/** + * struct virtchnl2_ptp_get_dev_clk_time - Associated with message + * VIRTCHNL2_OP_PTP_GET_DEV_CLK_TIME. + * @dev_time_ns: Device clock time value in nanoseconds + * + * PF/VF sends this message to receive the time from the main timer. + */ +struct virtchnl2_ptp_get_dev_clk_time { + __le64 dev_time_ns; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_ptp_get_dev_clk_time); + +/** + * struct virtchnl2_ptp_get_cross_time: Associated with message + * VIRTCHNL2_OP_PTP_GET_CROSS_TIME. + * @sys_time_ns: System counter value expressed in nanoseconds, read + * synchronously with device time + * @dev_time_ns: Device clock time value expressed in nanoseconds + * + * PF/VF sends this message to receive the cross time. + */ +struct virtchnl2_ptp_get_cross_time { + __le64 sys_time_ns; + __le64 dev_time_ns; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_get_cross_time); + +/** + * struct virtchnl2_ptp_set_dev_clk_time: Associated with message + * VIRTCHNL2_OP_PTP_SET_DEV_CLK_TIME. + * @dev_time_ns: Device time value expressed in nanoseconds to set + * + * PF/VF sends this message to set the time of the main timer. + */ +struct virtchnl2_ptp_set_dev_clk_time { + __le64 dev_time_ns; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_ptp_set_dev_clk_time); + +/** + * struct virtchnl2_ptp_adj_dev_clk_fine: Associated with message + * VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_FINE. + * @incval: Source timer increment value per clock cycle + * + * PF/VF sends this message to adjust the frequency of the main timer by the + * indicated increment value. + */ +struct virtchnl2_ptp_adj_dev_clk_fine { + __le64 incval; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_ptp_adj_dev_clk_fine); + +/** + * struct virtchnl2_ptp_adj_dev_clk_time: Associated with message + * VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_TIME. + * @delta: Offset in nanoseconds to adjust the time by + * + * PF/VF sends this message to adjust the time of the main timer by the delta. + */ +struct virtchnl2_ptp_adj_dev_clk_time { + __le64 delta; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_ptp_adj_dev_clk_time); + #endif /* _VIRTCHNL_2_H_ */ diff --git a/drivers/net/ethernet/intel/igb/Makefile b/drivers/net/ethernet/intel/igb/Makefile index 394c1e0656b9..6c1b702fd992 100644 --- a/drivers/net/ethernet/intel/igb/Makefile +++ b/drivers/net/ethernet/intel/igb/Makefile @@ -6,6 +6,6 @@ obj-$(CONFIG_IGB) += igb.o -igb-objs := igb_main.o igb_ethtool.o e1000_82575.o \ - e1000_mac.o e1000_nvm.o e1000_phy.o e1000_mbx.o \ - e1000_i210.o igb_ptp.o igb_hwmon.o +igb-y := igb_main.o igb_ethtool.o e1000_82575.o \ + e1000_mac.o e1000_nvm.o e1000_phy.o e1000_mbx.o \ + e1000_i210.o igb_ptp.o igb_hwmon.o igb_xsk.o diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.h b/drivers/net/ethernet/intel/igb/e1000_mac.h index 6e110f28f922..529b7d18b662 100644 --- a/drivers/net/ethernet/intel/igb/e1000_mac.h +++ b/drivers/net/ethernet/intel/igb/e1000_mac.h @@ -63,6 +63,5 @@ enum e1000_mng_mode { #define E1000_MNG_DHCP_COOKIE_STATUS_VLAN 0x2 -void e1000_init_function_pointers_82575(struct e1000_hw *hw); #endif diff --git a/drivers/net/ethernet/intel/igb/e1000_nvm.h b/drivers/net/ethernet/intel/igb/e1000_nvm.h index 091cddf4ada8..4f652ab713b3 100644 --- a/drivers/net/ethernet/intel/igb/e1000_nvm.h +++ b/drivers/net/ethernet/intel/igb/e1000_nvm.h @@ -7,7 +7,6 @@ s32 igb_acquire_nvm(struct e1000_hw *hw); void igb_release_nvm(struct e1000_hw *hw); s32 igb_read_mac_addr(struct e1000_hw *hw); -s32 igb_read_part_num(struct e1000_hw *hw, u32 *part_num); s32 igb_read_part_string(struct e1000_hw *hw, u8 *part_num, u32 part_num_size); s32 igb_read_nvm_eerd(struct e1000_hw *hw, u16 offset, u16 words, u16 *data); diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 3c2dc7bdebb5..f34ead8243e9 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -18,8 +18,10 @@ #include <linux/i2c-algo-bit.h> #include <linux/pci.h> #include <linux/mdio.h> +#include <linux/lockdep.h> #include <net/xdp.h> +#include <net/xdp_sock_drv.h> struct igb_adapter; @@ -86,6 +88,7 @@ struct igb_adapter; #define IGB_XDP_CONSUMED BIT(0) #define IGB_XDP_TX BIT(1) #define IGB_XDP_REDIR BIT(2) +#define IGB_XDP_EXIT BIT(3) struct vf_data_storage { unsigned char vf_mac_addresses[ETH_ALEN]; @@ -255,6 +258,7 @@ enum igb_tx_flags { enum igb_tx_buf_type { IGB_TYPE_SKB = 0, IGB_TYPE_XDP, + IGB_TYPE_XSK }; /* wrapper around a pointer to a socket buffer, @@ -320,6 +324,7 @@ struct igb_ring { union { /* array of buffer info structs */ struct igb_tx_buffer *tx_buffer_info; struct igb_rx_buffer *rx_buffer_info; + struct xdp_buff **rx_buffer_info_zc; }; void *desc; /* descriptor ring memory */ unsigned long flags; /* ring specific flags */ @@ -357,6 +362,7 @@ struct igb_ring { }; }; struct xdp_rxq_info xdp_rxq; + struct xsk_buff_pool *xsk_pool; } ____cacheline_internodealigned_in_smp; struct igb_q_vector { @@ -384,7 +390,9 @@ enum e1000_ring_flags_t { IGB_RING_FLAG_RX_SCTP_CSUM, IGB_RING_FLAG_RX_LB_VLAN_BSWAP, IGB_RING_FLAG_TX_CTX_IDX, - IGB_RING_FLAG_TX_DETECT_HANG + IGB_RING_FLAG_TX_DETECT_HANG, + IGB_RING_FLAG_TX_DISABLED, + IGB_RING_FLAG_RX_ALLOC_FAILED, }; #define ring_uses_large_buffer(ring) \ @@ -715,6 +723,8 @@ enum igb_boards { extern char igb_driver_name[]; +void igb_set_queue_napi(struct igb_adapter *adapter, int q_idx, + struct napi_struct *napi); int igb_xmit_xdp_ring(struct igb_adapter *adapter, struct igb_ring *ring, struct xdp_frame *xdpf); @@ -731,12 +741,21 @@ int igb_setup_tx_resources(struct igb_ring *); int igb_setup_rx_resources(struct igb_ring *); void igb_free_tx_resources(struct igb_ring *); void igb_free_rx_resources(struct igb_ring *); +void igb_clean_tx_ring(struct igb_ring *tx_ring); +void igb_clean_rx_ring(struct igb_ring *rx_ring); void igb_configure_tx_ring(struct igb_adapter *, struct igb_ring *); void igb_configure_rx_ring(struct igb_adapter *, struct igb_ring *); +void igb_finalize_xdp(struct igb_adapter *adapter, unsigned int status); +void igb_update_rx_stats(struct igb_q_vector *q_vector, unsigned int packets, + unsigned int bytes); void igb_setup_tctl(struct igb_adapter *); void igb_setup_rctl(struct igb_adapter *); void igb_setup_srrctl(struct igb_adapter *, struct igb_ring *); netdev_tx_t igb_xmit_frame_ring(struct sk_buff *, struct igb_ring *); +int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp); +void igb_process_skb_fields(struct igb_ring *rx_ring, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb); void igb_alloc_rx_buffers(struct igb_ring *, u16); void igb_update_stats(struct igb_adapter *); bool igb_has_link(struct igb_adapter *adapter); @@ -797,6 +816,33 @@ static inline struct netdev_queue *txring_txq(const struct igb_ring *tx_ring) return netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index); } +/* This function assumes __netif_tx_lock is held by the caller. */ +static inline void igb_xdp_ring_update_tail(struct igb_ring *ring) +{ + lockdep_assert_held(&txring_txq(ring)->_xmit_lock); + + /* Force memory writes to complete before letting h/w know there + * are new descriptors to fetch. + */ + wmb(); + writel(ring->next_to_use, ring->tail); +} + +static inline struct igb_ring *igb_xdp_tx_queue_mapping(struct igb_adapter *adapter) +{ + unsigned int r_idx = smp_processor_id(); + + if (r_idx >= adapter->num_tx_queues) + r_idx = r_idx % adapter->num_tx_queues; + + return adapter->tx_ring[r_idx]; +} + +static inline bool igb_xdp_is_enabled(struct igb_adapter *adapter) +{ + return !!READ_ONCE(adapter->xdp_prog); +} + int igb_add_filter(struct igb_adapter *adapter, struct igb_nfc_filter *input); int igb_erase_filter(struct igb_adapter *adapter, @@ -807,4 +853,17 @@ int igb_add_mac_steering_filter(struct igb_adapter *adapter, int igb_del_mac_steering_filter(struct igb_adapter *adapter, const u8 *addr, u8 queue, u8 flags); +struct xsk_buff_pool *igb_xsk_pool(struct igb_adapter *adapter, + struct igb_ring *ring); +int igb_xsk_pool_setup(struct igb_adapter *adapter, + struct xsk_buff_pool *pool, + u16 qid); +bool igb_alloc_rx_buffers_zc(struct igb_ring *rx_ring, + struct xsk_buff_pool *xsk_pool, u16 count); +void igb_clean_rx_ring_zc(struct igb_ring *rx_ring); +int igb_clean_rx_irq_zc(struct igb_q_vector *q_vector, + struct xsk_buff_pool *xsk_pool, const int budget); +bool igb_xmit_zc(struct igb_ring *tx_ring, struct xsk_buff_pool *xsk_pool); +int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags); + #endif /* _IGB_H_ */ diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 99977a22b843..ca6ccbc13954 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -2381,21 +2381,17 @@ static void igb_get_strings(struct net_device *netdev, u32 stringset, u8 *data) } static int igb_get_ts_info(struct net_device *dev, - struct ethtool_ts_info *info) + struct kernel_ethtool_ts_info *info) { struct igb_adapter *adapter = netdev_priv(dev); if (adapter->ptp_clock) info->phc_index = ptp_clock_index(adapter->ptp_clock); - else - info->phc_index = -1; switch (adapter->hw.mac.type) { case e1000_82575: info->so_timestamping = - SOF_TIMESTAMPING_TX_SOFTWARE | - SOF_TIMESTAMPING_RX_SOFTWARE | - SOF_TIMESTAMPING_SOFTWARE; + SOF_TIMESTAMPING_TX_SOFTWARE; return 0; case e1000_82576: case e1000_82580: @@ -2405,8 +2401,6 @@ static int igb_get_ts_info(struct net_device *dev, case e1000_i211: info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | - SOF_TIMESTAMPING_RX_SOFTWARE | - SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_TX_HARDWARE | SOF_TIMESTAMPING_RX_HARDWARE | SOF_TIMESTAMPING_RAW_HARDWARE; @@ -3272,19 +3266,6 @@ static int igb_get_module_eeprom(struct net_device *netdev, return 0; } -static int igb_ethtool_begin(struct net_device *netdev) -{ - struct igb_adapter *adapter = netdev_priv(netdev); - pm_runtime_get_sync(&adapter->pdev->dev); - return 0; -} - -static void igb_ethtool_complete(struct net_device *netdev) -{ - struct igb_adapter *adapter = netdev_priv(netdev); - pm_runtime_put(&adapter->pdev->dev); -} - static u32 igb_get_rxfh_indir_size(struct net_device *netdev) { return IGB_RETA_SIZE; @@ -3508,8 +3489,6 @@ static const struct ethtool_ops igb_ethtool_ops = { .set_channels = igb_set_channels, .get_priv_flags = igb_get_priv_flags, .set_priv_flags = igb_set_priv_flags, - .begin = igb_ethtool_begin, - .complete = igb_ethtool_complete, .get_link_ksettings = igb_get_link_ksettings, .set_link_ksettings = igb_set_link_ksettings, }; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index a3f100769e39..9e9a5900e6e5 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -106,8 +106,6 @@ static int igb_setup_all_rx_resources(struct igb_adapter *); static void igb_free_all_tx_resources(struct igb_adapter *); static void igb_free_all_rx_resources(struct igb_adapter *); static void igb_setup_mrqc(struct igb_adapter *); -static int igb_probe(struct pci_dev *, const struct pci_device_id *); -static void igb_remove(struct pci_dev *pdev); static void igb_init_queue_configuration(struct igb_adapter *adapter); static int igb_sw_init(struct igb_adapter *); int igb_open(struct net_device *); @@ -117,8 +115,6 @@ static void igb_configure_tx(struct igb_adapter *); static void igb_configure_rx(struct igb_adapter *); static void igb_clean_all_tx_rings(struct igb_adapter *); static void igb_clean_all_rx_rings(struct igb_adapter *); -static void igb_clean_tx_ring(struct igb_ring *); -static void igb_clean_rx_ring(struct igb_ring *); static void igb_set_rx_mode(struct net_device *); static void igb_update_phy_info(struct timer_list *); static void igb_watchdog(struct timer_list *); @@ -178,20 +174,6 @@ static int igb_vf_configure(struct igb_adapter *adapter, int vf); static int igb_disable_sriov(struct pci_dev *dev, bool reinit); #endif -static int igb_suspend(struct device *); -static int igb_resume(struct device *); -static int igb_runtime_suspend(struct device *dev); -static int igb_runtime_resume(struct device *dev); -static int igb_runtime_idle(struct device *dev); -#ifdef CONFIG_PM -static const struct dev_pm_ops igb_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(igb_suspend, igb_resume) - SET_RUNTIME_PM_OPS(igb_runtime_suspend, igb_runtime_resume, - igb_runtime_idle) -}; -#endif -static void igb_shutdown(struct pci_dev *); -static int igb_pci_sriov_configure(struct pci_dev *dev, int num_vfs); #ifdef CONFIG_IGB_DCA static int igb_notify_dca(struct notifier_block *, unsigned long, void *); static struct notifier_block dca_notifier = { @@ -219,20 +201,6 @@ static const struct pci_error_handlers igb_err_handler = { static void igb_init_dmac(struct igb_adapter *adapter, u32 pba); -static struct pci_driver igb_driver = { - .name = igb_driver_name, - .id_table = igb_pci_tbl, - .probe = igb_probe, - .remove = igb_remove, -#ifdef CONFIG_PM - .driver.pm = &igb_pm_ops, -#endif - .shutdown = igb_shutdown, - .sriov_configure = igb_pci_sriov_configure, - .err_handler = &igb_err_handler -}; - -MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>"); MODULE_DESCRIPTION("Intel(R) Gigabit Ethernet Network Driver"); MODULE_LICENSE("GPL v2"); @@ -504,12 +472,17 @@ rx_ring_summary: for (i = 0; i < rx_ring->count; i++) { const char *next_desc; - struct igb_rx_buffer *buffer_info; - buffer_info = &rx_ring->rx_buffer_info[i]; + dma_addr_t dma = (dma_addr_t)0; + struct igb_rx_buffer *buffer_info = NULL; rx_desc = IGB_RX_DESC(rx_ring, i); u0 = (struct my_u0 *)rx_desc; staterr = le32_to_cpu(rx_desc->wb.upper.status_error); + if (!rx_ring->xsk_pool) { + buffer_info = &rx_ring->rx_buffer_info[i]; + dma = buffer_info->dma; + } + if (i == rx_ring->next_to_use) next_desc = " NTU"; else if (i == rx_ring->next_to_clean) @@ -529,11 +502,11 @@ rx_ring_summary: "R ", i, le64_to_cpu(u0->a), le64_to_cpu(u0->b), - (u64)buffer_info->dma, + (u64)dma, next_desc); if (netif_msg_pktdata(adapter) && - buffer_info->dma && buffer_info->page) { + buffer_info && dma && buffer_info->page) { print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 1, @@ -647,6 +620,8 @@ struct net_device *igb_get_hw_dev(struct e1000_hw *hw) return adapter->netdev; } +static struct pci_driver igb_driver; + /** * igb_init_module - Driver Registration Routine * @@ -664,6 +639,10 @@ static int __init igb_init_module(void) dca_register_notify(&dca_notifier); #endif ret = pci_register_driver(&igb_driver); +#ifdef CONFIG_IGB_DCA + if (ret) + dca_unregister_notify(&dca_notifier); +#endif return ret; } @@ -968,6 +947,9 @@ static int igb_request_msix(struct igb_adapter *adapter) q_vector); if (err) goto err_free; + + netif_napi_set_irq(&q_vector->napi, + adapter->msix_entries[vector].vector); } igb_configure_msix(adapter); @@ -1215,7 +1197,8 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter, return -ENOMEM; /* initialize NAPI */ - netif_napi_add(adapter->netdev, &q_vector->napi, igb_poll); + netif_napi_add_config(adapter->netdev, &q_vector->napi, igb_poll, + v_idx); /* tie q_vector and adapter together */ adapter->q_vector[v_idx] = q_vector; @@ -1231,7 +1214,7 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter, /* initialize pointer to rings */ ring = q_vector->ring; - /* intialize ITR */ + /* initialize ITR */ if (rxr_count) { /* rx or rx/tx vector */ if (!adapter->rx_itr_setting || adapter->rx_itr_setting > 3) @@ -2013,7 +1996,11 @@ static void igb_configure(struct igb_adapter *adapter) */ for (i = 0; i < adapter->num_rx_queues; i++) { struct igb_ring *ring = adapter->rx_ring[i]; - igb_alloc_rx_buffers(ring, igb_desc_unused(ring)); + if (ring->xsk_pool) + igb_alloc_rx_buffers_zc(ring, ring->xsk_pool, + igb_desc_unused(ring)); + else + igb_alloc_rx_buffers(ring, igb_desc_unused(ring)); } } @@ -2113,6 +2100,22 @@ static void igb_check_swap_media(struct igb_adapter *adapter) wr32(E1000_CTRL_EXT, ctrl_ext); } +void igb_set_queue_napi(struct igb_adapter *adapter, int vector, + struct napi_struct *napi) +{ + struct igb_q_vector *q_vector = adapter->q_vector[vector]; + + if (q_vector->rx.ring) + netif_queue_set_napi(adapter->netdev, + q_vector->rx.ring->queue_index, + NETDEV_QUEUE_TYPE_RX, napi); + + if (q_vector->tx.ring) + netif_queue_set_napi(adapter->netdev, + q_vector->tx.ring->queue_index, + NETDEV_QUEUE_TYPE_TX, napi); +} + /** * igb_up - Open the interface and prepare it to handle traffic * @adapter: board private structure @@ -2120,6 +2123,7 @@ static void igb_check_swap_media(struct igb_adapter *adapter) int igb_up(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; + struct napi_struct *napi; int i; /* hardware has been reset, we need to reload some things */ @@ -2127,8 +2131,11 @@ int igb_up(struct igb_adapter *adapter) clear_bit(__IGB_DOWN, &adapter->state); - for (i = 0; i < adapter->num_q_vectors; i++) - napi_enable(&(adapter->q_vector[i]->napi)); + for (i = 0; i < adapter->num_q_vectors; i++) { + napi = &adapter->q_vector[i]->napi; + napi_enable(napi); + igb_set_queue_napi(adapter, i, napi); + } if (adapter->flags & IGB_FLAG_HAS_MSIX) igb_configure_msix(adapter); @@ -2198,12 +2205,13 @@ void igb_down(struct igb_adapter *adapter) for (i = 0; i < adapter->num_q_vectors; i++) { if (adapter->q_vector[i]) { napi_synchronize(&adapter->q_vector[i]->napi); + igb_set_queue_napi(adapter, i, NULL); napi_disable(&adapter->q_vector[i]->napi); } } - del_timer_sync(&adapter->watchdog_timer); - del_timer_sync(&adapter->phy_info_timer); + timer_delete_sync(&adapter->watchdog_timer); + timer_delete_sync(&adapter->phy_info_timer); /* record the stats before reset*/ spin_lock(&adapter->stats64_lock); @@ -2513,7 +2521,7 @@ static int igb_set_features(struct net_device *netdev, static int igb_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, - u16 flags, + u16 flags, bool *notified, struct netlink_ext_ack *extack) { /* guarantee we can provide a unique filter for the unicast address */ @@ -2624,6 +2632,9 @@ static int igb_parse_cls_flower(struct igb_adapter *adapter, return -EOPNOTSUPP; } + if (flow_rule_match_has_control_flags(rule, extack)) + return -EOPNOTSUPP; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { struct flow_match_eth_addrs match; @@ -2931,34 +2942,20 @@ static int igb_xdp_setup(struct net_device *dev, struct netdev_bpf *bpf) static int igb_xdp(struct net_device *dev, struct netdev_bpf *xdp) { + struct igb_adapter *adapter = netdev_priv(dev); + switch (xdp->command) { case XDP_SETUP_PROG: return igb_xdp_setup(dev, xdp); + case XDP_SETUP_XSK_POOL: + return igb_xsk_pool_setup(adapter, xdp->xsk.pool, + xdp->xsk.queue_id); default: return -EINVAL; } } -static void igb_xdp_ring_update_tail(struct igb_ring *ring) -{ - /* Force memory writes to complete before letting h/w know there - * are new descriptors to fetch. - */ - wmb(); - writel(ring->next_to_use, ring->tail); -} - -static struct igb_ring *igb_xdp_tx_queue_mapping(struct igb_adapter *adapter) -{ - unsigned int r_idx = smp_processor_id(); - - if (r_idx >= adapter->num_tx_queues) - r_idx = r_idx % adapter->num_tx_queues; - - return adapter->tx_ring[r_idx]; -} - -static int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp) +int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp) { struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp); int cpu = smp_processor_id(); @@ -2972,7 +2969,8 @@ static int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp) /* During program transitions its possible adapter->xdp_prog is assigned * but ring has not been configured yet. In this case simply abort xmit. */ - tx_ring = adapter->xdp_prog ? igb_xdp_tx_queue_mapping(adapter) : NULL; + tx_ring = igb_xdp_is_enabled(adapter) ? + igb_xdp_tx_queue_mapping(adapter) : NULL; if (unlikely(!tx_ring)) return IGB_XDP_CONSUMED; @@ -3005,10 +3003,14 @@ static int igb_xdp_xmit(struct net_device *dev, int n, /* During program transitions its possible adapter->xdp_prog is assigned * but ring has not been configured yet. In this case simply abort xmit. */ - tx_ring = adapter->xdp_prog ? igb_xdp_tx_queue_mapping(adapter) : NULL; + tx_ring = igb_xdp_is_enabled(adapter) ? + igb_xdp_tx_queue_mapping(adapter) : NULL; if (unlikely(!tx_ring)) return -ENXIO; + if (unlikely(test_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags))) + return -ENXIO; + nq = txring_txq(tx_ring); __netif_tx_lock(nq, cpu); @@ -3025,11 +3027,11 @@ static int igb_xdp_xmit(struct net_device *dev, int n, nxmit++; } - __netif_tx_unlock(nq); - if (unlikely(flags & XDP_XMIT_FLUSH)) igb_xdp_ring_update_tail(tx_ring); + __netif_tx_unlock(nq); + return nxmit; } @@ -3059,6 +3061,7 @@ static const struct net_device_ops igb_netdev_ops = { .ndo_setup_tc = igb_setup_tc, .ndo_bpf = igb_xdp, .ndo_xdp_xmit = igb_xdp_xmit, + .ndo_xsk_wakeup = igb_xsk_wakeup, }; /** @@ -3355,7 +3358,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->priv_flags |= IFF_SUPP_NOFCS; netdev->priv_flags |= IFF_UNICAST_FLT; - netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT; + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_XSK_ZEROCOPY; /* MTU range: 68 - 9216 */ netdev->min_mtu = ETH_MIN_MTU; @@ -3881,8 +3885,8 @@ static void igb_remove(struct pci_dev *pdev) * disable watchdog from being rescheduled. */ set_bit(__IGB_DOWN, &adapter->state); - del_timer_sync(&adapter->watchdog_timer); - del_timer_sync(&adapter->phy_info_timer); + timer_delete_sync(&adapter->watchdog_timer); + timer_delete_sync(&adapter->phy_info_timer); cancel_work_sync(&adapter->reset_task); cancel_work_sync(&adapter->watchdog_task); @@ -3927,7 +3931,7 @@ static void igb_remove(struct pci_dev *pdev) * * This function initializes the vf specific data storage and then attempts to * allocate the VFs. The reason for ordering it this way is because it is much - * mor expensive time wise to disable SR-IOV than it is to allocate and free + * more expensive time wise to disable SR-IOV than it is to allocate and free * the memory for the VFs. **/ static void igb_probe_vfs(struct igb_adapter *adapter) @@ -4134,8 +4138,9 @@ static int igb_sw_init(struct igb_adapter *adapter) static int __igb_open(struct net_device *netdev, bool resuming) { struct igb_adapter *adapter = netdev_priv(netdev); - struct e1000_hw *hw = &adapter->hw; struct pci_dev *pdev = adapter->pdev; + struct e1000_hw *hw = &adapter->hw; + struct napi_struct *napi; int err; int i; @@ -4187,8 +4192,11 @@ static int __igb_open(struct net_device *netdev, bool resuming) /* From here on the code is the same as igb_up() */ clear_bit(__IGB_DOWN, &adapter->state); - for (i = 0; i < adapter->num_q_vectors; i++) - napi_enable(&(adapter->q_vector[i]->napi)); + for (i = 0; i < adapter->num_q_vectors; i++) { + napi = &adapter->q_vector[i]->napi; + napi_enable(napi); + igb_set_queue_napi(adapter, i, napi); + } /* Clear any pending interrupts. */ rd32(E1000_TSICR); @@ -4381,6 +4389,8 @@ void igb_configure_tx_ring(struct igb_adapter *adapter, u64 tdba = ring->dma; int reg_idx = ring->reg_idx; + WRITE_ONCE(ring->xsk_pool, igb_xsk_pool(adapter, ring)); + wr32(E1000_TDLEN(reg_idx), ring->count * sizeof(union e1000_adv_tx_desc)); wr32(E1000_TDBAL(reg_idx), @@ -4441,7 +4451,8 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring) if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) xdp_rxq_info_unreg(&rx_ring->xdp_rxq); res = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, - rx_ring->queue_index, 0); + rx_ring->queue_index, + rx_ring->q_vector->napi.napi_id); if (res < 0) { dev_err(dev, "Failed to register xdp_rxq index %u\n", rx_ring->queue_index); @@ -4737,12 +4748,17 @@ void igb_setup_srrctl(struct igb_adapter *adapter, struct igb_ring *ring) struct e1000_hw *hw = &adapter->hw; int reg_idx = ring->reg_idx; u32 srrctl = 0; + u32 buf_size; - srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT; - if (ring_uses_large_buffer(ring)) - srrctl |= IGB_RXBUFFER_3072 >> E1000_SRRCTL_BSIZEPKT_SHIFT; + if (ring->xsk_pool) + buf_size = xsk_pool_get_rx_frame_size(ring->xsk_pool); + else if (ring_uses_large_buffer(ring)) + buf_size = IGB_RXBUFFER_3072; else - srrctl |= IGB_RXBUFFER_2048 >> E1000_SRRCTL_BSIZEPKT_SHIFT; + buf_size = IGB_RXBUFFER_2048; + + srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT; + srrctl |= buf_size >> E1000_SRRCTL_BSIZEPKT_SHIFT; srrctl |= E1000_SRRCTL_DESCTYPE_ADV_ONEBUF; if (hw->mac.type >= e1000_82580) srrctl |= E1000_SRRCTL_TIMESTAMP; @@ -4774,8 +4790,17 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, u32 rxdctl = 0; xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); - WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, - MEM_TYPE_PAGE_SHARED, NULL)); + WRITE_ONCE(ring->xsk_pool, igb_xsk_pool(adapter, ring)); + if (ring->xsk_pool) { + WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_XSK_BUFF_POOL, + NULL)); + xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq); + } else { + WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_PAGE_SHARED, + NULL)); + } /* disable the queue */ wr32(E1000_RXDCTL(reg_idx), 0); @@ -4802,9 +4827,12 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, rxdctl |= IGB_RX_HTHRESH << 8; rxdctl |= IGB_RX_WTHRESH << 16; - /* initialize rx_buffer_info */ - memset(ring->rx_buffer_info, 0, - sizeof(struct igb_rx_buffer) * ring->count); + if (ring->xsk_pool) + memset(ring->rx_buffer_info_zc, 0, + sizeof(*ring->rx_buffer_info_zc) * ring->count); + else + memset(ring->rx_buffer_info, 0, + sizeof(*ring->rx_buffer_info) * ring->count); /* initialize Rx descriptor 0 */ rx_desc = IGB_RX_DESC(ring, 0); @@ -4833,6 +4861,7 @@ static void igb_set_rx_buffer_len(struct igb_adapter *adapter, #if (PAGE_SIZE < 8192) if (adapter->max_frame_size > IGB_MAX_FRAME_BUILD_SKB || + IGB_2K_TOO_SMALL_WITH_PADDING || rd32(E1000_RCTL) & E1000_RCTL_SBP) set_ring_uses_large_buffer(rx_ring); #endif @@ -4904,19 +4933,24 @@ static void igb_free_all_tx_resources(struct igb_adapter *adapter) * igb_clean_tx_ring - Free Tx Buffers * @tx_ring: ring to be cleaned **/ -static void igb_clean_tx_ring(struct igb_ring *tx_ring) +void igb_clean_tx_ring(struct igb_ring *tx_ring) { u16 i = tx_ring->next_to_clean; struct igb_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i]; + u32 xsk_frames = 0; while (i != tx_ring->next_to_use) { union e1000_adv_tx_desc *eop_desc, *tx_desc; /* Free all the Tx ring sk_buffs or xdp frames */ - if (tx_buffer->type == IGB_TYPE_SKB) + if (tx_buffer->type == IGB_TYPE_SKB) { dev_kfree_skb_any(tx_buffer->skb); - else + } else if (tx_buffer->type == IGB_TYPE_XDP) { xdp_return_frame(tx_buffer->xdpf); + } else if (tx_buffer->type == IGB_TYPE_XSK) { + xsk_frames++; + goto skip_for_xsk; + } /* unmap skb header data */ dma_unmap_single(tx_ring->dev, @@ -4947,6 +4981,7 @@ static void igb_clean_tx_ring(struct igb_ring *tx_ring) DMA_TO_DEVICE); } +skip_for_xsk: tx_buffer->next_to_watch = NULL; /* move us one more past the eop_desc for start of next pkt */ @@ -4961,6 +4996,9 @@ static void igb_clean_tx_ring(struct igb_ring *tx_ring) /* reset BQL for queue */ netdev_tx_reset_queue(txring_txq(tx_ring)); + if (tx_ring->xsk_pool && xsk_frames) + xsk_tx_completed(tx_ring->xsk_pool, xsk_frames); + /* reset next_to_use and next_to_clean */ tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; @@ -4991,8 +5029,13 @@ void igb_free_rx_resources(struct igb_ring *rx_ring) rx_ring->xdp_prog = NULL; xdp_rxq_info_unreg(&rx_ring->xdp_rxq); - vfree(rx_ring->rx_buffer_info); - rx_ring->rx_buffer_info = NULL; + if (rx_ring->xsk_pool) { + vfree(rx_ring->rx_buffer_info_zc); + rx_ring->rx_buffer_info_zc = NULL; + } else { + vfree(rx_ring->rx_buffer_info); + rx_ring->rx_buffer_info = NULL; + } /* if not set, then don't free */ if (!rx_ring->desc) @@ -5023,13 +5066,18 @@ static void igb_free_all_rx_resources(struct igb_adapter *adapter) * igb_clean_rx_ring - Free Rx Buffers per Queue * @rx_ring: ring to free buffers from **/ -static void igb_clean_rx_ring(struct igb_ring *rx_ring) +void igb_clean_rx_ring(struct igb_ring *rx_ring) { u16 i = rx_ring->next_to_clean; dev_kfree_skb(rx_ring->skb); rx_ring->skb = NULL; + if (rx_ring->xsk_pool) { + igb_clean_rx_ring_zc(rx_ring); + goto skip_for_xsk; + } + /* Free all the Rx ring sk_buffs */ while (i != rx_ring->next_to_alloc) { struct igb_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i]; @@ -5057,6 +5105,7 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring) i = 0; } +skip_for_xsk: rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; @@ -5706,11 +5755,29 @@ no_wait: if (adapter->flags & IGB_FLAG_HAS_MSIX) { u32 eics = 0; - for (i = 0; i < adapter->num_q_vectors; i++) - eics |= adapter->q_vector[i]->eims_value; - wr32(E1000_EICS, eics); + for (i = 0; i < adapter->num_q_vectors; i++) { + struct igb_q_vector *q_vector = adapter->q_vector[i]; + struct igb_ring *rx_ring; + + if (!q_vector->rx.ring) + continue; + + rx_ring = adapter->rx_ring[q_vector->rx.ring->queue_index]; + + if (test_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags)) { + eics |= q_vector->eims_value; + clear_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); + } + } + if (eics) + wr32(E1000_EICS, eics); } else { - wr32(E1000_ICS, E1000_ICS_RXDMT0); + struct igb_ring *rx_ring = adapter->rx_ring[0]; + + if (test_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags)) { + clear_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); + wr32(E1000_ICS, E1000_ICS_RXDMT0); + } } igb_spoof_check(adapter); @@ -6483,6 +6550,9 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, return NETDEV_TX_BUSY; } + if (unlikely(test_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags))) + return NETDEV_TX_BUSY; + /* record the location of the first descriptor for this packet */ first = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; first->type = IGB_TYPE_SKB; @@ -6638,7 +6708,7 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu) struct igb_adapter *adapter = netdev_priv(netdev); int max_frame = new_mtu + IGB_ETH_PKT_HDR_PAD; - if (adapter->xdp_prog) { + if (igb_xdp_is_enabled(adapter)) { int i; for (i = 0; i < adapter->num_rx_queues; i++) { @@ -6668,7 +6738,7 @@ static int igb_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; + WRITE_ONCE(netdev->mtu, new_mtu); if (netif_running(netdev)) igb_up(adapter); @@ -6984,10 +7054,20 @@ static void igb_extts(struct igb_adapter *adapter, int tsintr_tt) static void igb_tsync_interrupt(struct igb_adapter *adapter) { + const u32 mask = (TSINTR_SYS_WRAP | E1000_TSICR_TXTS | + TSINTR_TT0 | TSINTR_TT1 | + TSINTR_AUTT0 | TSINTR_AUTT1); struct e1000_hw *hw = &adapter->hw; u32 tsicr = rd32(E1000_TSICR); struct ptp_clock_event event; + if (hw->mac.type == e1000_82580) { + /* 82580 has a hardware bug that requires an explicit + * write to clear the TimeSync interrupt cause. + */ + wr32(E1000_TSICR, tsicr & mask); + } + if (tsicr & TSINTR_SYS_WRAP) { event.type = PTP_CLOCK_PPS; if (adapter->ptp_caps.pps) @@ -8201,6 +8281,7 @@ static int igb_poll(struct napi_struct *napi, int budget) struct igb_q_vector *q_vector = container_of(napi, struct igb_q_vector, napi); + struct xsk_buff_pool *xsk_pool; bool clean_complete = true; int work_done = 0; @@ -8212,7 +8293,12 @@ static int igb_poll(struct napi_struct *napi, int budget) clean_complete = igb_clean_tx_irq(q_vector, budget); if (q_vector->rx.ring) { - int cleaned = igb_clean_rx_irq(q_vector, budget); + int cleaned; + + xsk_pool = READ_ONCE(q_vector->rx.ring->xsk_pool); + cleaned = xsk_pool ? + igb_clean_rx_irq_zc(q_vector, xsk_pool, budget) : + igb_clean_rx_irq(q_vector, budget); work_done += cleaned; if (cleaned >= budget) @@ -8241,13 +8327,18 @@ static int igb_poll(struct napi_struct *napi, int budget) **/ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) { - struct igb_adapter *adapter = q_vector->adapter; - struct igb_ring *tx_ring = q_vector->tx.ring; - struct igb_tx_buffer *tx_buffer; - union e1000_adv_tx_desc *tx_desc; unsigned int total_bytes = 0, total_packets = 0; + struct igb_adapter *adapter = q_vector->adapter; unsigned int budget = q_vector->tx.work_limit; + struct igb_ring *tx_ring = q_vector->tx.ring; unsigned int i = tx_ring->next_to_clean; + union e1000_adv_tx_desc *tx_desc; + struct igb_tx_buffer *tx_buffer; + struct xsk_buff_pool *xsk_pool; + int cpu = smp_processor_id(); + bool xsk_xmit_done = true; + struct netdev_queue *nq; + u32 xsk_frames = 0; if (test_bit(__IGB_DOWN, &adapter->state)) return true; @@ -8278,10 +8369,14 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) total_packets += tx_buffer->gso_segs; /* free the skb */ - if (tx_buffer->type == IGB_TYPE_SKB) + if (tx_buffer->type == IGB_TYPE_SKB) { napi_consume_skb(tx_buffer->skb, napi_budget); - else + } else if (tx_buffer->type == IGB_TYPE_XDP) { xdp_return_frame(tx_buffer->xdpf); + } else if (tx_buffer->type == IGB_TYPE_XSK) { + xsk_frames++; + goto skip_for_xsk; + } /* unmap skb header data */ dma_unmap_single(tx_ring->dev, @@ -8313,6 +8408,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) } } +skip_for_xsk: /* move us one more past the eop_desc for start of next pkt */ tx_buffer++; tx_desc++; @@ -8341,6 +8437,21 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) q_vector->tx.total_bytes += total_bytes; q_vector->tx.total_packets += total_packets; + xsk_pool = READ_ONCE(tx_ring->xsk_pool); + if (xsk_pool) { + if (xsk_frames) + xsk_tx_completed(xsk_pool, xsk_frames); + if (xsk_uses_need_wakeup(xsk_pool)) + xsk_set_tx_need_wakeup(xsk_pool); + + nq = txring_txq(tx_ring); + __netif_tx_lock(nq, cpu); + /* Avoid transmit queue timeout since we share it with the slow path */ + txq_trans_cond_update(nq); + xsk_xmit_done = igb_xmit_zc(tx_ring, xsk_pool); + __netif_tx_unlock(nq); + } + if (test_bit(IGB_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags)) { struct e1000_hw *hw = &adapter->hw; @@ -8403,7 +8514,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) } } - return !!budget; + return !!budget && xsk_xmit_done; } /** @@ -8594,9 +8705,8 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, return skb; } -static struct sk_buff *igb_run_xdp(struct igb_adapter *adapter, - struct igb_ring *rx_ring, - struct xdp_buff *xdp) +static int igb_run_xdp(struct igb_adapter *adapter, struct igb_ring *rx_ring, + struct xdp_buff *xdp) { int err, result = IGB_XDP_PASS; struct bpf_prog *xdp_prog; @@ -8636,7 +8746,7 @@ out_failure: break; } xdp_out: - return ERR_PTR(-result); + return result; } static unsigned int igb_rx_frame_truesize(struct igb_ring *rx_ring, @@ -8762,10 +8872,6 @@ static bool igb_cleanup_headers(struct igb_ring *rx_ring, union e1000_adv_rx_desc *rx_desc, struct sk_buff *skb) { - /* XDP packets use error pointer so abort at this point */ - if (IS_ERR(skb)) - return true; - if (unlikely((igb_test_staterr(rx_desc, E1000_RXDEXT_ERR_FRAME_ERR_MASK)))) { struct net_device *netdev = rx_ring->netdev; @@ -8792,9 +8898,9 @@ static bool igb_cleanup_headers(struct igb_ring *rx_ring, * order to populate the hash, checksum, VLAN, timestamp, protocol, and * other fields within the skb. **/ -static void igb_process_skb_fields(struct igb_ring *rx_ring, - union e1000_adv_rx_desc *rx_desc, - struct sk_buff *skb) +void igb_process_skb_fields(struct igb_ring *rx_ring, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb) { struct net_device *dev = rx_ring->netdev; @@ -8876,17 +8982,50 @@ static void igb_put_rx_buffer(struct igb_ring *rx_ring, rx_buffer->page = NULL; } +void igb_finalize_xdp(struct igb_adapter *adapter, unsigned int status) +{ + int cpu = smp_processor_id(); + struct netdev_queue *nq; + + if (status & IGB_XDP_REDIR) + xdp_do_flush(); + + if (status & IGB_XDP_TX) { + struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter); + + nq = txring_txq(tx_ring); + __netif_tx_lock(nq, cpu); + igb_xdp_ring_update_tail(tx_ring); + __netif_tx_unlock(nq); + } +} + +void igb_update_rx_stats(struct igb_q_vector *q_vector, unsigned int packets, + unsigned int bytes) +{ + struct igb_ring *ring = q_vector->rx.ring; + + u64_stats_update_begin(&ring->rx_syncp); + ring->rx_stats.packets += packets; + ring->rx_stats.bytes += bytes; + u64_stats_update_end(&ring->rx_syncp); + + q_vector->rx.total_packets += packets; + q_vector->rx.total_bytes += bytes; +} + static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) { + unsigned int total_bytes = 0, total_packets = 0; struct igb_adapter *adapter = q_vector->adapter; struct igb_ring *rx_ring = q_vector->rx.ring; - struct sk_buff *skb = rx_ring->skb; - unsigned int total_bytes = 0, total_packets = 0; u16 cleaned_count = igb_desc_unused(rx_ring); + struct sk_buff *skb = rx_ring->skb; unsigned int xdp_xmit = 0; struct xdp_buff xdp; u32 frame_sz = 0; int rx_buf_pgcnt; + int xdp_res = 0; /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ #if (PAGE_SIZE < 8192) @@ -8944,12 +9083,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) /* At larger PAGE_SIZE, frame_sz depend on len size */ xdp.frame_sz = igb_rx_frame_truesize(rx_ring, size); #endif - skb = igb_run_xdp(adapter, rx_ring, &xdp); + xdp_res = igb_run_xdp(adapter, rx_ring, &xdp); } - if (IS_ERR(skb)) { - unsigned int xdp_res = -PTR_ERR(skb); - + if (xdp_res) { if (xdp_res & (IGB_XDP_TX | IGB_XDP_REDIR)) { xdp_xmit |= xdp_res; igb_rx_buffer_flip(rx_ring, rx_buffer, size); @@ -8968,9 +9105,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) &xdp, timestamp); /* exit if we failed to retrieve a buffer */ - if (!skb) { + if (!xdp_res && !skb) { rx_ring->rx_stats.alloc_failed++; rx_buffer->pagecnt_bias++; + set_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); break; } @@ -8982,7 +9120,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) continue; /* verify the packet layout is correct */ - if (igb_cleanup_headers(rx_ring, rx_desc, skb)) { + if (xdp_res || igb_cleanup_headers(rx_ring, rx_desc, skb)) { skb = NULL; continue; } @@ -9005,21 +9143,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) /* place incomplete frames back on ring for completion */ rx_ring->skb = skb; - if (xdp_xmit & IGB_XDP_REDIR) - xdp_do_flush(); - - if (xdp_xmit & IGB_XDP_TX) { - struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter); - - igb_xdp_ring_update_tail(tx_ring); - } + if (xdp_xmit) + igb_finalize_xdp(adapter, xdp_xmit); - u64_stats_update_begin(&rx_ring->rx_syncp); - rx_ring->rx_stats.packets += total_packets; - rx_ring->rx_stats.bytes += total_bytes; - u64_stats_update_end(&rx_ring->rx_syncp); - q_vector->rx.total_packets += total_packets; - q_vector->rx.total_bytes += total_bytes; + igb_update_rx_stats(q_vector, total_packets, total_bytes); if (cleaned_count) igb_alloc_rx_buffers(rx_ring, cleaned_count); @@ -9041,6 +9168,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, page = dev_alloc_pages(igb_rx_pg_order(rx_ring)); if (unlikely(!page)) { rx_ring->rx_stats.alloc_failed++; + set_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); return false; } @@ -9057,6 +9185,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, __free_pages(page, igb_rx_pg_order(rx_ring)); rx_ring->rx_stats.alloc_failed++; + set_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); return false; } @@ -9163,6 +9292,10 @@ static int igb_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) return -EIO; break; case SIOCSMIIREG: + if (igb_write_phy_reg(&adapter->hw, data->reg_num & 0x1F, + data->val_in)) + return -EIO; + break; default: return -EOPNOTSUPP; } @@ -9453,12 +9586,12 @@ static void igb_deliver_wake_packet(struct net_device *netdev) netif_rx(skb); } -static int __maybe_unused igb_suspend(struct device *dev) +static int igb_suspend(struct device *dev) { return __igb_shutdown(to_pci_dev(dev), NULL, 0); } -static int __maybe_unused __igb_resume(struct device *dev, bool rpm) +static int __igb_resume(struct device *dev, bool rpm) { struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); @@ -9514,12 +9647,12 @@ static int __maybe_unused __igb_resume(struct device *dev, bool rpm) return err; } -static int __maybe_unused igb_resume(struct device *dev) +static int igb_resume(struct device *dev) { return __igb_resume(dev, false); } -static int __maybe_unused igb_runtime_idle(struct device *dev) +static int igb_runtime_idle(struct device *dev) { struct net_device *netdev = dev_get_drvdata(dev); struct igb_adapter *adapter = netdev_priv(netdev); @@ -9530,12 +9663,12 @@ static int __maybe_unused igb_runtime_idle(struct device *dev) return -EBUSY; } -static int __maybe_unused igb_runtime_suspend(struct device *dev) +static int igb_runtime_suspend(struct device *dev) { return __igb_shutdown(to_pci_dev(dev), NULL, 1); } -static int __maybe_unused igb_runtime_resume(struct device *dev) +static int igb_runtime_resume(struct device *dev) { return __igb_resume(dev, true); } @@ -9591,8 +9724,11 @@ static pci_ers_result_t igb_io_error_detected(struct pci_dev *pdev, if (state == pci_channel_io_perm_failure) return PCI_ERS_RESULT_DISCONNECT; + rtnl_lock(); if (netif_running(netdev)) igb_down(adapter); + rtnl_unlock(); + pci_disable_device(pdev); /* Request a slot reset. */ @@ -9651,12 +9787,21 @@ static void igb_io_resume(struct pci_dev *pdev) struct net_device *netdev = pci_get_drvdata(pdev); struct igb_adapter *adapter = netdev_priv(netdev); + rtnl_lock(); if (netif_running(netdev)) { + if (!test_bit(__IGB_DOWN, &adapter->state)) { + dev_dbg(&pdev->dev, "Resuming from non-fatal error, do nothing.\n"); + rtnl_unlock(); + return; + } + if (igb_up(adapter)) { dev_err(&pdev->dev, "igb_up failed after reset\n"); + rtnl_unlock(); return; } } + rtnl_unlock(); netif_device_attach(netdev); @@ -10157,4 +10302,20 @@ static void igb_nfc_filter_restore(struct igb_adapter *adapter) spin_unlock(&adapter->nfc_lock); } + +static _DEFINE_DEV_PM_OPS(igb_pm_ops, igb_suspend, igb_resume, + igb_runtime_suspend, igb_runtime_resume, + igb_runtime_idle); + +static struct pci_driver igb_driver = { + .name = igb_driver_name, + .id_table = igb_pci_tbl, + .probe = igb_probe, + .remove = igb_remove, + .driver.pm = pm_ptr(&igb_pm_ops), + .shutdown = igb_shutdown, + .sriov_configure = igb_pci_sriov_configure, + .err_handler = &igb_err_handler +}; + /* igb_main.c */ diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index f94570556120..793c96016288 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -502,11 +502,10 @@ static int igb_ptp_feature_enable_82580(struct ptp_clock_info *ptp, switch (rq->type) { case PTP_CLK_REQ_EXTTS: - /* Reject requests with unsupported flags */ - if (rq->extts.flags & ~(PTP_ENABLE_FEATURE | - PTP_RISING_EDGE | - PTP_FALLING_EDGE | - PTP_STRICT_FLAGS)) + /* Both the rising and falling edge are timestamped */ + if (rq->extts.flags & PTP_STRICT_FLAGS && + (rq->extts.flags & PTP_ENABLE_FEATURE) && + (rq->extts.flags & PTP_EXTTS_EDGES) != PTP_EXTTS_EDGES) return -EOPNOTSUPP; if (on) { @@ -652,13 +651,6 @@ static int igb_ptp_feature_enable_i210(struct ptp_clock_info *ptp, switch (rq->type) { case PTP_CLK_REQ_EXTTS: - /* Reject requests with unsupported flags */ - if (rq->extts.flags & ~(PTP_ENABLE_FEATURE | - PTP_RISING_EDGE | - PTP_FALLING_EDGE | - PTP_STRICT_FLAGS)) - return -EOPNOTSUPP; - /* Reject requests failing to enable both edges. */ if ((rq->extts.flags & PTP_STRICT_FLAGS) && (rq->extts.flags & PTP_ENABLE_FEATURE) && @@ -1350,6 +1342,9 @@ void igb_ptp_init(struct igb_adapter *adapter) adapter->ptp_caps.n_per_out = IGB_N_PEROUT; adapter->ptp_caps.n_pins = IGB_N_SDP; adapter->ptp_caps.pps = 0; + adapter->ptp_caps.supported_extts_flags = PTP_RISING_EDGE | + PTP_FALLING_EDGE | + PTP_STRICT_FLAGS; adapter->ptp_caps.pin_config = adapter->sdp_config; adapter->ptp_caps.adjfine = igb_ptp_adjfine_82580; adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576; @@ -1372,6 +1367,9 @@ void igb_ptp_init(struct igb_adapter *adapter) adapter->ptp_caps.n_ext_ts = IGB_N_EXTTS; adapter->ptp_caps.n_per_out = IGB_N_PEROUT; adapter->ptp_caps.n_pins = IGB_N_SDP; + adapter->ptp_caps.supported_extts_flags = PTP_RISING_EDGE | + PTP_FALLING_EDGE | + PTP_STRICT_FLAGS; adapter->ptp_caps.pps = 1; adapter->ptp_caps.pin_config = adapter->sdp_config; adapter->ptp_caps.adjfine = igb_ptp_adjfine_82580; diff --git a/drivers/net/ethernet/intel/igb/igb_xsk.c b/drivers/net/ethernet/intel/igb/igb_xsk.c new file mode 100644 index 000000000000..5cf67ba29269 --- /dev/null +++ b/drivers/net/ethernet/intel/igb/igb_xsk.c @@ -0,0 +1,563 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2018 Intel Corporation. */ + +#include <linux/bpf_trace.h> +#include <net/xdp_sock_drv.h> +#include <net/xdp.h> + +#include "e1000_hw.h" +#include "igb.h" + +static int igb_realloc_rx_buffer_info(struct igb_ring *ring, bool pool_present) +{ + int size = pool_present ? + sizeof(*ring->rx_buffer_info_zc) * ring->count : + sizeof(*ring->rx_buffer_info) * ring->count; + void *buff_info = vmalloc(size); + + if (!buff_info) + return -ENOMEM; + + if (pool_present) { + vfree(ring->rx_buffer_info); + ring->rx_buffer_info = NULL; + ring->rx_buffer_info_zc = buff_info; + } else { + vfree(ring->rx_buffer_info_zc); + ring->rx_buffer_info_zc = NULL; + ring->rx_buffer_info = buff_info; + } + + return 0; +} + +static void igb_txrx_ring_disable(struct igb_adapter *adapter, u16 qid) +{ + struct igb_ring *tx_ring = adapter->tx_ring[qid]; + struct igb_ring *rx_ring = adapter->rx_ring[qid]; + struct e1000_hw *hw = &adapter->hw; + + set_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags); + + wr32(E1000_TXDCTL(tx_ring->reg_idx), 0); + wr32(E1000_RXDCTL(rx_ring->reg_idx), 0); + + synchronize_net(); + + /* Rx/Tx share the same napi context. */ + napi_disable(&rx_ring->q_vector->napi); + + igb_clean_tx_ring(tx_ring); + igb_clean_rx_ring(rx_ring); + + memset(&rx_ring->rx_stats, 0, sizeof(rx_ring->rx_stats)); + memset(&tx_ring->tx_stats, 0, sizeof(tx_ring->tx_stats)); +} + +static void igb_txrx_ring_enable(struct igb_adapter *adapter, u16 qid) +{ + struct igb_ring *tx_ring = adapter->tx_ring[qid]; + struct igb_ring *rx_ring = adapter->rx_ring[qid]; + + igb_configure_tx_ring(adapter, tx_ring); + igb_configure_rx_ring(adapter, rx_ring); + + synchronize_net(); + + clear_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags); + + /* call igb_desc_unused which always leaves + * at least 1 descriptor unused to make sure + * next_to_use != next_to_clean + */ + if (rx_ring->xsk_pool) + igb_alloc_rx_buffers_zc(rx_ring, rx_ring->xsk_pool, + igb_desc_unused(rx_ring)); + else + igb_alloc_rx_buffers(rx_ring, igb_desc_unused(rx_ring)); + + /* Rx/Tx share the same napi context. */ + napi_enable(&rx_ring->q_vector->napi); +} + +struct xsk_buff_pool *igb_xsk_pool(struct igb_adapter *adapter, + struct igb_ring *ring) +{ + int qid = ring->queue_index; + struct xsk_buff_pool *pool; + + pool = xsk_get_pool_from_qid(adapter->netdev, qid); + + if (!igb_xdp_is_enabled(adapter)) + return NULL; + + return (pool && pool->dev) ? pool : NULL; +} + +static int igb_xsk_pool_enable(struct igb_adapter *adapter, + struct xsk_buff_pool *pool, + u16 qid) +{ + struct net_device *netdev = adapter->netdev; + struct igb_ring *rx_ring; + bool if_running; + int err; + + if (qid >= adapter->num_rx_queues) + return -EINVAL; + + if (qid >= netdev->real_num_rx_queues || + qid >= netdev->real_num_tx_queues) + return -EINVAL; + + err = xsk_pool_dma_map(pool, &adapter->pdev->dev, IGB_RX_DMA_ATTR); + if (err) + return err; + + rx_ring = adapter->rx_ring[qid]; + if_running = netif_running(adapter->netdev) && igb_xdp_is_enabled(adapter); + if (if_running) + igb_txrx_ring_disable(adapter, qid); + + if (if_running) { + err = igb_realloc_rx_buffer_info(rx_ring, true); + if (!err) { + igb_txrx_ring_enable(adapter, qid); + /* Kick start the NAPI context so that receiving will start */ + err = igb_xsk_wakeup(adapter->netdev, qid, XDP_WAKEUP_RX); + } + + if (err) { + xsk_pool_dma_unmap(pool, IGB_RX_DMA_ATTR); + return err; + } + } + + return 0; +} + +static int igb_xsk_pool_disable(struct igb_adapter *adapter, u16 qid) +{ + struct xsk_buff_pool *pool; + struct igb_ring *rx_ring; + bool if_running; + int err; + + pool = xsk_get_pool_from_qid(adapter->netdev, qid); + if (!pool) + return -EINVAL; + + rx_ring = adapter->rx_ring[qid]; + if_running = netif_running(adapter->netdev) && igb_xdp_is_enabled(adapter); + if (if_running) + igb_txrx_ring_disable(adapter, qid); + + xsk_pool_dma_unmap(pool, IGB_RX_DMA_ATTR); + + if (if_running) { + err = igb_realloc_rx_buffer_info(rx_ring, false); + if (err) + return err; + + igb_txrx_ring_enable(adapter, qid); + } + + return 0; +} + +int igb_xsk_pool_setup(struct igb_adapter *adapter, + struct xsk_buff_pool *pool, + u16 qid) +{ + return pool ? igb_xsk_pool_enable(adapter, pool, qid) : + igb_xsk_pool_disable(adapter, qid); +} + +static u16 igb_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp, + union e1000_adv_rx_desc *rx_desc, u16 count) +{ + dma_addr_t dma; + u16 buffs; + int i; + + /* nothing to do */ + if (!count) + return 0; + + buffs = xsk_buff_alloc_batch(pool, xdp, count); + for (i = 0; i < buffs; i++) { + dma = xsk_buff_xdp_get_dma(*xdp); + rx_desc->read.pkt_addr = cpu_to_le64(dma); + rx_desc->wb.upper.length = 0; + + rx_desc++; + xdp++; + } + + return buffs; +} + +bool igb_alloc_rx_buffers_zc(struct igb_ring *rx_ring, + struct xsk_buff_pool *xsk_pool, u16 count) +{ + u32 nb_buffs_extra = 0, nb_buffs = 0; + union e1000_adv_rx_desc *rx_desc; + u16 ntu = rx_ring->next_to_use; + u16 total_count = count; + struct xdp_buff **xdp; + + rx_desc = IGB_RX_DESC(rx_ring, ntu); + xdp = &rx_ring->rx_buffer_info_zc[ntu]; + + if (ntu + count >= rx_ring->count) { + nb_buffs_extra = igb_fill_rx_descs(xsk_pool, xdp, rx_desc, + rx_ring->count - ntu); + if (nb_buffs_extra != rx_ring->count - ntu) { + ntu += nb_buffs_extra; + goto exit; + } + rx_desc = IGB_RX_DESC(rx_ring, 0); + xdp = rx_ring->rx_buffer_info_zc; + ntu = 0; + count -= nb_buffs_extra; + } + + nb_buffs = igb_fill_rx_descs(xsk_pool, xdp, rx_desc, count); + ntu += nb_buffs; + if (ntu == rx_ring->count) + ntu = 0; + + /* clear the length for the next_to_use descriptor */ + rx_desc = IGB_RX_DESC(rx_ring, ntu); + rx_desc->wb.upper.length = 0; + +exit: + if (rx_ring->next_to_use != ntu) { + rx_ring->next_to_use = ntu; + + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. (Only + * applicable for weak-ordered memory model archs, + * such as IA-64). + */ + wmb(); + writel(ntu, rx_ring->tail); + } + + return total_count == (nb_buffs + nb_buffs_extra); +} + +void igb_clean_rx_ring_zc(struct igb_ring *rx_ring) +{ + u16 ntc = rx_ring->next_to_clean; + u16 ntu = rx_ring->next_to_use; + + while (ntc != ntu) { + struct xdp_buff *xdp = rx_ring->rx_buffer_info_zc[ntc]; + + xsk_buff_free(xdp); + ntc++; + if (ntc >= rx_ring->count) + ntc = 0; + } +} + +static struct sk_buff *igb_construct_skb_zc(struct igb_ring *rx_ring, + struct xdp_buff *xdp, + ktime_t timestamp) +{ + unsigned int totalsize = xdp->data_end - xdp->data_meta; + unsigned int metasize = xdp->data - xdp->data_meta; + struct sk_buff *skb; + + net_prefetch(xdp->data_meta); + + /* allocate a skb to store the frags */ + skb = napi_alloc_skb(&rx_ring->q_vector->napi, totalsize); + if (unlikely(!skb)) + return NULL; + + if (timestamp) + skb_hwtstamps(skb)->hwtstamp = timestamp; + + memcpy(__skb_put(skb, totalsize), xdp->data_meta, + ALIGN(totalsize, sizeof(long))); + + if (metasize) { + skb_metadata_set(skb, metasize); + __skb_pull(skb, metasize); + } + + return skb; +} + +static int igb_run_xdp_zc(struct igb_adapter *adapter, struct igb_ring *rx_ring, + struct xdp_buff *xdp, struct xsk_buff_pool *xsk_pool, + struct bpf_prog *xdp_prog) +{ + int err, result = IGB_XDP_PASS; + u32 act; + + prefetchw(xdp->data_hard_start); /* xdp_frame write */ + + act = bpf_prog_run_xdp(xdp_prog, xdp); + + if (likely(act == XDP_REDIRECT)) { + err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog); + if (!err) + return IGB_XDP_REDIR; + + if (xsk_uses_need_wakeup(xsk_pool) && + err == -ENOBUFS) + result = IGB_XDP_EXIT; + else + result = IGB_XDP_CONSUMED; + goto out_failure; + } + + switch (act) { + case XDP_PASS: + break; + case XDP_TX: + result = igb_xdp_xmit_back(adapter, xdp); + if (result == IGB_XDP_CONSUMED) + goto out_failure; + break; + default: + bpf_warn_invalid_xdp_action(adapter->netdev, xdp_prog, act); + fallthrough; + case XDP_ABORTED: +out_failure: + trace_xdp_exception(rx_ring->netdev, xdp_prog, act); + fallthrough; + case XDP_DROP: + result = IGB_XDP_CONSUMED; + break; + } + + return result; +} + +int igb_clean_rx_irq_zc(struct igb_q_vector *q_vector, + struct xsk_buff_pool *xsk_pool, const int budget) +{ + struct igb_adapter *adapter = q_vector->adapter; + unsigned int total_bytes = 0, total_packets = 0; + struct igb_ring *rx_ring = q_vector->rx.ring; + u32 ntc = rx_ring->next_to_clean; + struct bpf_prog *xdp_prog; + unsigned int xdp_xmit = 0; + bool failure = false; + u16 entries_to_alloc; + struct sk_buff *skb; + + /* xdp_prog cannot be NULL in the ZC path */ + xdp_prog = READ_ONCE(rx_ring->xdp_prog); + + while (likely(total_packets < budget)) { + union e1000_adv_rx_desc *rx_desc; + ktime_t timestamp = 0; + struct xdp_buff *xdp; + unsigned int size; + int xdp_res = 0; + + rx_desc = IGB_RX_DESC(rx_ring, ntc); + size = le16_to_cpu(rx_desc->wb.upper.length); + if (!size) + break; + + /* This memory barrier is needed to keep us from reading + * any other fields out of the rx_desc until we know the + * descriptor has been written back + */ + dma_rmb(); + + xdp = rx_ring->rx_buffer_info_zc[ntc]; + xsk_buff_set_size(xdp, size); + xsk_buff_dma_sync_for_cpu(xdp); + + /* pull rx packet timestamp if available and valid */ + if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { + int ts_hdr_len; + + ts_hdr_len = igb_ptp_rx_pktstamp(rx_ring->q_vector, + xdp->data, + ×tamp); + + xdp->data += ts_hdr_len; + xdp->data_meta += ts_hdr_len; + size -= ts_hdr_len; + } + + xdp_res = igb_run_xdp_zc(adapter, rx_ring, xdp, xsk_pool, + xdp_prog); + + if (xdp_res) { + if (likely(xdp_res & (IGB_XDP_TX | IGB_XDP_REDIR))) { + xdp_xmit |= xdp_res; + } else if (xdp_res == IGB_XDP_EXIT) { + failure = true; + break; + } else if (xdp_res == IGB_XDP_CONSUMED) { + xsk_buff_free(xdp); + } + + total_packets++; + total_bytes += size; + ntc++; + if (ntc == rx_ring->count) + ntc = 0; + continue; + } + + skb = igb_construct_skb_zc(rx_ring, xdp, timestamp); + + /* exit if we failed to retrieve a buffer */ + if (!skb) { + rx_ring->rx_stats.alloc_failed++; + set_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); + break; + } + + xsk_buff_free(xdp); + ntc++; + if (ntc == rx_ring->count) + ntc = 0; + + if (eth_skb_pad(skb)) + continue; + + /* probably a little skewed due to removing CRC */ + total_bytes += skb->len; + + /* populate checksum, timestamp, VLAN, and protocol */ + igb_process_skb_fields(rx_ring, rx_desc, skb); + + napi_gro_receive(&q_vector->napi, skb); + + /* update budget accounting */ + total_packets++; + } + + rx_ring->next_to_clean = ntc; + + if (xdp_xmit) + igb_finalize_xdp(adapter, xdp_xmit); + + igb_update_rx_stats(q_vector, total_packets, total_bytes); + + entries_to_alloc = igb_desc_unused(rx_ring); + if (entries_to_alloc >= IGB_RX_BUFFER_WRITE) + failure |= !igb_alloc_rx_buffers_zc(rx_ring, xsk_pool, + entries_to_alloc); + + if (xsk_uses_need_wakeup(xsk_pool)) { + if (failure || rx_ring->next_to_clean == rx_ring->next_to_use) + xsk_set_rx_need_wakeup(xsk_pool); + else + xsk_clear_rx_need_wakeup(xsk_pool); + + return (int)total_packets; + } + return failure ? budget : (int)total_packets; +} + +bool igb_xmit_zc(struct igb_ring *tx_ring, struct xsk_buff_pool *xsk_pool) +{ + unsigned int budget = igb_desc_unused(tx_ring); + u32 cmd_type, olinfo_status, nb_pkts, i = 0; + struct xdp_desc *descs = xsk_pool->tx_descs; + union e1000_adv_tx_desc *tx_desc = NULL; + struct igb_tx_buffer *tx_buffer_info; + unsigned int total_bytes = 0; + dma_addr_t dma; + + if (!netif_carrier_ok(tx_ring->netdev)) + return true; + + if (test_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags)) + return true; + + nb_pkts = xsk_tx_peek_release_desc_batch(xsk_pool, budget); + if (!nb_pkts) + return true; + + while (nb_pkts-- > 0) { + dma = xsk_buff_raw_get_dma(xsk_pool, descs[i].addr); + xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, descs[i].len); + + tx_buffer_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + tx_buffer_info->bytecount = descs[i].len; + tx_buffer_info->type = IGB_TYPE_XSK; + tx_buffer_info->xdpf = NULL; + tx_buffer_info->gso_segs = 1; + tx_buffer_info->time_stamp = jiffies; + + tx_desc = IGB_TX_DESC(tx_ring, tx_ring->next_to_use); + tx_desc->read.buffer_addr = cpu_to_le64(dma); + + /* put descriptor type bits */ + cmd_type = E1000_ADVTXD_DTYP_DATA | E1000_ADVTXD_DCMD_DEXT | + E1000_ADVTXD_DCMD_IFCS; + olinfo_status = descs[i].len << E1000_ADVTXD_PAYLEN_SHIFT; + + /* FIXME: This sets the Report Status (RS) bit for every + * descriptor. One nice to have optimization would be to set it + * only for the last descriptor in the whole batch. See Intel + * ice driver for an example on how to do it. + */ + cmd_type |= descs[i].len | IGB_TXD_DCMD; + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); + tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); + + total_bytes += descs[i].len; + + i++; + tx_ring->next_to_use++; + tx_buffer_info->next_to_watch = tx_desc; + if (tx_ring->next_to_use == tx_ring->count) + tx_ring->next_to_use = 0; + } + + netdev_tx_sent_queue(txring_txq(tx_ring), total_bytes); + igb_xdp_ring_update_tail(tx_ring); + + return nb_pkts < budget; +} + +int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) +{ + struct igb_adapter *adapter = netdev_priv(dev); + struct e1000_hw *hw = &adapter->hw; + struct igb_ring *ring; + u32 eics = 0; + + if (test_bit(__IGB_DOWN, &adapter->state)) + return -ENETDOWN; + + if (!igb_xdp_is_enabled(adapter)) + return -EINVAL; + + if (qid >= adapter->num_tx_queues) + return -EINVAL; + + ring = adapter->tx_ring[qid]; + + if (test_bit(IGB_RING_FLAG_TX_DISABLED, &ring->flags)) + return -ENETDOWN; + + if (!READ_ONCE(ring->xsk_pool)) + return -EINVAL; + + if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) { + /* Cause software interrupt */ + if (adapter->flags & IGB_FLAG_HAS_MSIX) { + eics |= ring->q_vector->eims_value; + wr32(E1000_EICS, eics); + } else { + wr32(E1000_ICS, E1000_ICS_RXDMT0); + } + } + + return 0; +} diff --git a/drivers/net/ethernet/intel/igbvf/Makefile b/drivers/net/ethernet/intel/igbvf/Makefile index afd3e36eae75..902711d5e691 100644 --- a/drivers/net/ethernet/intel/igbvf/Makefile +++ b/drivers/net/ethernet/intel/igbvf/Makefile @@ -6,8 +6,4 @@ obj-$(CONFIG_IGBVF) += igbvf.o -igbvf-objs := vf.o \ - mbx.o \ - ethtool.o \ - netdev.o - +igbvf-y := vf.o mbx.o ethtool.o netdev.o diff --git a/drivers/net/ethernet/intel/igbvf/igbvf.h b/drivers/net/ethernet/intel/igbvf/igbvf.h index 7b83678ba83a..ca6e44245a7b 100644 --- a/drivers/net/ethernet/intel/igbvf/igbvf.h +++ b/drivers/net/ethernet/intel/igbvf/igbvf.h @@ -169,8 +169,6 @@ struct igbvf_adapter { u16 link_speed; u16 link_duplex; - spinlock_t tx_queue_lock; /* prevent concurrent tail updates */ - /* track device up/down/testing state */ unsigned long state; @@ -220,7 +218,6 @@ struct igbvf_adapter { /* OS defined structs */ struct net_device *netdev; struct pci_dev *pdev; - spinlock_t stats_lock; /* prevent concurrent stats updates */ /* structs defined in e1000_hw.h */ struct e1000_hw hw; @@ -282,7 +279,6 @@ enum igbvf_state_t { extern char igbvf_driver_name[]; -void igbvf_check_options(struct igbvf_adapter *); void igbvf_set_ethtool_ops(struct net_device *); int igbvf_up(struct igbvf_adapter *); diff --git a/drivers/net/ethernet/intel/igbvf/mbx.h b/drivers/net/ethernet/intel/igbvf/mbx.h index e5b31818d565..7637d21445bf 100644 --- a/drivers/net/ethernet/intel/igbvf/mbx.h +++ b/drivers/net/ethernet/intel/igbvf/mbx.h @@ -49,7 +49,6 @@ #define E1000_PF_CONTROL_MSG 0x0100 /* PF control message */ -void e1000_init_mbx_ops_generic(struct e1000_hw *hw); s32 e1000_init_mbx_params_vf(struct e1000_hw *); #endif /* _E1000_MBX_H_ */ diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index b0cf310e6f7b..beb01248600f 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -1592,7 +1592,7 @@ void igbvf_down(struct igbvf_adapter *adapter) igbvf_irq_disable(adapter); - del_timer_sync(&adapter->watchdog_timer); + timer_delete_sync(&adapter->watchdog_timer); /* record the stats before reset*/ igbvf_update_stats(adapter); @@ -1656,12 +1656,9 @@ static int igbvf_sw_init(struct igbvf_adapter *adapter) if (igbvf_alloc_queues(adapter)) return -ENOMEM; - spin_lock_init(&adapter->tx_queue_lock); - /* Explicitly disable IRQ since the NIC can be in any state. */ igbvf_irq_disable(adapter); - spin_lock_init(&adapter->stats_lock); spin_lock_init(&adapter->hw.mbx_lock); set_bit(__IGBVF_DOWN, &adapter->state); @@ -2434,7 +2431,7 @@ static int igbvf_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; + WRITE_ONCE(netdev->mtu, new_mtu); if (netif_running(netdev)) igbvf_up(adapter); @@ -2470,7 +2467,7 @@ static int igbvf_suspend(struct device *dev_d) return 0; } -static int __maybe_unused igbvf_resume(struct device *dev_d) +static int igbvf_resume(struct device *dev_d) { struct pci_dev *pdev = to_pci_dev(dev_d); struct net_device *netdev = pci_get_drvdata(pdev); @@ -2915,7 +2912,7 @@ static void igbvf_remove(struct pci_dev *pdev) * disable it from being rescheduled. */ set_bit(__IGBVF_DOWN, &adapter->state); - del_timer_sync(&adapter->watchdog_timer); + timer_delete_sync(&adapter->watchdog_timer); cancel_work_sync(&adapter->reset_task); cancel_work_sync(&adapter->watchdog_task); @@ -2957,7 +2954,7 @@ static const struct pci_device_id igbvf_pci_tbl[] = { }; MODULE_DEVICE_TABLE(pci, igbvf_pci_tbl); -static SIMPLE_DEV_PM_OPS(igbvf_pm_ops, igbvf_suspend, igbvf_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(igbvf_pm_ops, igbvf_suspend, igbvf_resume); /* PCI Device API Driver */ static struct pci_driver igbvf_driver = { @@ -2965,7 +2962,7 @@ static struct pci_driver igbvf_driver = { .id_table = igbvf_pci_tbl, .probe = igbvf_probe, .remove = igbvf_remove, - .driver.pm = &igbvf_pm_ops, + .driver.pm = pm_sleep_ptr(&igbvf_pm_ops), .shutdown = igbvf_shutdown, .err_handler = &igbvf_err_handler }; @@ -3001,7 +2998,6 @@ static void __exit igbvf_exit_module(void) } module_exit(igbvf_exit_module); -MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>"); MODULE_DESCRIPTION("Intel(R) Gigabit Virtual Function Network Driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/ethernet/intel/igc/Makefile b/drivers/net/ethernet/intel/igc/Makefile index ebffd3054285..efc5e7983dad 100644 --- a/drivers/net/ethernet/intel/igc/Makefile +++ b/drivers/net/ethernet/intel/igc/Makefile @@ -6,7 +6,7 @@ # obj-$(CONFIG_IGC) += igc.o -igc-$(CONFIG_IGC_LEDS) += igc_leds.o -igc-objs := igc_main.o igc_mac.o igc_i225.o igc_base.o igc_nvm.o igc_phy.o \ -igc_diag.o igc_ethtool.o igc_ptp.o igc_dump.o igc_tsn.o igc_xdp.o +igc-y := igc_main.o igc_mac.o igc_i225.o igc_base.o igc_nvm.o igc_phy.o \ + igc_diag.o igc_ethtool.o igc_ptp.o igc_dump.o igc_tsn.o igc_xdp.o +igc-$(CONFIG_IGC_LEDS) += igc_leds.o diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 6bc56c7c181e..859a15e4ccba 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -40,6 +40,11 @@ void igc_ethtool_set_ops(struct net_device *); #define IGC_MAX_TX_TSTAMP_REGS 4 +struct igc_fpe_t { + struct ethtool_mmsv mmsv; + u32 tx_min_frag_size; +}; + enum igc_mac_filter_type { IGC_MAC_FILTER_TYPE_DST = 0, IGC_MAC_FILTER_TYPE_SRC @@ -72,13 +77,46 @@ struct igc_rx_packet_stats { u64 other_packets; }; +enum igc_tx_buffer_type { + IGC_TX_BUFFER_TYPE_SKB, + IGC_TX_BUFFER_TYPE_XDP, + IGC_TX_BUFFER_TYPE_XSK, +}; + +/* wrapper around a pointer to a socket buffer, + * so a DMA handle can be stored along with the buffer + */ +struct igc_tx_buffer { + union igc_adv_tx_desc *next_to_watch; + unsigned long time_stamp; + enum igc_tx_buffer_type type; + union { + struct sk_buff *skb; + struct xdp_frame *xdpf; + }; + unsigned int bytecount; + u16 gso_segs; + __be16 protocol; + + DEFINE_DMA_UNMAP_ADDR(dma); + DEFINE_DMA_UNMAP_LEN(len); + u32 tx_flags; + bool xsk_pending_ts; +}; + struct igc_tx_timestamp_request { - struct sk_buff *skb; /* reference to the packet being timestamped */ + union { /* reference to the packet being timestamped */ + struct sk_buff *skb; + struct igc_tx_buffer *xsk_tx_buffer; + }; + enum igc_tx_buffer_type buffer_type; 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 */ + u8 xsk_queue_index; /* Tx queue which requesting timestamp */ + struct xsk_tx_metadata_compl xsk_meta; /* ref to xsk Tx metadata */ }; struct igc_inline_rx_tstamps { @@ -169,7 +207,6 @@ struct igc_adapter { struct net_device *netdev; struct ethtool_keee eee; - u16 eee_advert; unsigned long state; unsigned int flags; @@ -227,6 +264,10 @@ struct igc_adapter { */ spinlock_t qbv_tx_lock; + bool strict_priority_enable; + u8 num_tc; + u16 queue_per_tc[IGC_MAX_TX_QUEUES]; + /* OS defined structs */ struct pci_dev *pdev; /* lock for statistics */ @@ -283,6 +324,7 @@ struct igc_adapter { struct timespec64 prev_ptp_time; /* Pre-reset PTP clock */ ktime_t ptp_reset_start; /* Reset time in clock mono */ struct system_time_snapshot snapshot; + struct mutex ptm_lock; /* Only allow one PTM transaction at a time */ char fw_version[32]; @@ -296,6 +338,8 @@ struct igc_adapter { struct timespec64 period; } perout[IGC_N_PEROUT]; + struct igc_fpe_t fpe; + /* LEDs */ struct mutex led_mutex; struct igc_led_classdev *leds; @@ -323,6 +367,9 @@ void igc_disable_tx_ring(struct igc_ring *ring); void igc_enable_tx_ring(struct igc_ring *ring); int igc_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags); +/* AF_XDP TX metadata operations */ +extern const struct xsk_tx_metadata_ops igc_xsk_tx_metadata_ops; + /* igc_dump declarations */ void igc_rings_dump(struct igc_adapter *adapter); void igc_regs_dump(struct igc_adapter *adapter); @@ -347,9 +394,11 @@ extern char igc_driver_name[]; #define IGC_FLAG_RX_LEGACY BIT(16) #define IGC_FLAG_TSN_QBV_ENABLED BIT(17) #define IGC_FLAG_TSN_QAV_ENABLED BIT(18) +#define IGC_FLAG_TSN_PREEMPT_ENABLED BIT(19) -#define IGC_FLAG_TSN_ANY_ENABLED \ - (IGC_FLAG_TSN_QBV_ENABLED | IGC_FLAG_TSN_QAV_ENABLED) +#define IGC_FLAG_TSN_ANY_ENABLED \ + (IGC_FLAG_TSN_QBV_ENABLED | IGC_FLAG_TSN_QAV_ENABLED | \ + IGC_FLAG_TSN_PREEMPT_ENABLED) #define IGC_FLAG_RSS_FIELD_IPV4_UDP BIT(6) #define IGC_FLAG_RSS_FIELD_IPV6_UDP BIT(7) @@ -508,32 +557,6 @@ enum igc_boards { #define TXD_USE_COUNT(S) DIV_ROUND_UP((S), IGC_MAX_DATA_PER_TXD) #define DESC_NEEDED (MAX_SKB_FRAGS + 4) -enum igc_tx_buffer_type { - IGC_TX_BUFFER_TYPE_SKB, - IGC_TX_BUFFER_TYPE_XDP, - IGC_TX_BUFFER_TYPE_XSK, -}; - -/* wrapper around a pointer to a socket buffer, - * so a DMA handle can be stored along with the buffer - */ -struct igc_tx_buffer { - union igc_adv_tx_desc *next_to_watch; - unsigned long time_stamp; - enum igc_tx_buffer_type type; - union { - struct sk_buff *skb; - struct xdp_frame *xdpf; - }; - unsigned int bytecount; - u16 gso_segs; - __be16 protocol; - - DEFINE_DMA_UNMAP_ADDR(dma); - DEFINE_DMA_UNMAP_LEN(len); - u32 tx_flags; -}; - struct igc_rx_buffer { union { struct { @@ -557,6 +580,14 @@ struct igc_xdp_buff { struct igc_inline_rx_tstamps *rx_ts; /* data indication bit IGC_RXDADV_STAT_TSIP */ }; +struct igc_metadata_request { + struct igc_tx_buffer *tx_buffer; + struct xsk_tx_metadata *meta; + struct igc_ring *tx_ring; + u32 cmd_type; + u16 used_desc; +}; + struct igc_q_vector { struct igc_adapter *adapter; /* backlink */ void __iomem *itr_register; @@ -665,6 +696,7 @@ enum igc_ring_flags_t { IGC_RING_FLAG_TX_DETECT_HANG, IGC_RING_FLAG_AF_XDP_ZC, IGC_RING_FLAG_TX_HWTSTAMP, + IGC_RING_FLAG_RX_ALLOC_FAILED, }; #define ring_uses_large_buffer(ring) \ @@ -711,7 +743,10 @@ struct igc_nfc_rule *igc_get_nfc_rule(struct igc_adapter *adapter, u32 location); int igc_add_nfc_rule(struct igc_adapter *adapter, struct igc_nfc_rule *rule); void igc_del_nfc_rule(struct igc_adapter *adapter, struct igc_nfc_rule *rule); - +void igc_disable_empty_addr_recv(struct igc_adapter *adapter); +int igc_enable_empty_addr_recv(struct igc_adapter *adapter); +struct igc_ring *igc_get_tx_ring(struct igc_adapter *adapter, int cpu); +void igc_flush_tx_descriptors(struct igc_ring *ring); void igc_ptp_init(struct igc_adapter *adapter); void igc_ptp_reset(struct igc_adapter *adapter); void igc_ptp_suspend(struct igc_adapter *adapter); diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c index 9fae8bdec2a7..1613b562d17c 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.c +++ b/drivers/net/ethernet/intel/igc/igc_base.c @@ -68,6 +68,10 @@ static s32 igc_init_nvm_params_base(struct igc_hw *hw) u32 eecd = rd32(IGC_EECD); u16 size; + /* failed to read reg and got all F's */ + if (!(~eecd)) + return -ENXIO; + size = FIELD_GET(IGC_EECD_SIZE_EX_MASK, eecd); /* Added to a constant, "size" becomes the left-shift value @@ -221,6 +225,8 @@ static s32 igc_get_invariants_base(struct igc_hw *hw) /* NVM initialization */ ret_val = igc_init_nvm_params_base(hw); + if (ret_val) + goto out; switch (hw->mac.type) { case igc_i225: ret_val = igc_init_nvm_params_i225(hw); diff --git a/drivers/net/ethernet/intel/igc/igc_base.h b/drivers/net/ethernet/intel/igc/igc_base.h index bf8cdfbba9ff..6320eabb72fe 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.h +++ b/drivers/net/ethernet/intel/igc/igc_base.h @@ -49,6 +49,7 @@ struct igc_adv_tx_context_desc { #define IGC_ADVTXD_DCMD_DEXT 0x20000000 /* Descriptor extension (1=Adv) */ #define IGC_ADVTXD_DCMD_VLE 0x40000000 /* VLAN pkt enable */ #define IGC_ADVTXD_DCMD_TSE 0x80000000 /* TCP Seg enable */ +#define IGC_ADVTXD_PAYLEN_MASK 0XFFFFC000 /* Adv desc PAYLEN mask */ #define IGC_ADVTXD_PAYLEN_SHIFT 14 /* Adv desc PAYLEN shift */ #define IGC_RAR_ENTRIES 16 diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index 5f92b3c7c3d4..7189dfc389ad 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -4,6 +4,8 @@ #ifndef _IGC_DEFINES_H_ #define _IGC_DEFINES_H_ +#include <linux/bitfield.h> + /* Number of Transmit and Receive Descriptors must be a multiple of 8 */ #define REQ_TX_DESCRIPTOR_MULTIPLE 8 #define REQ_RX_DESCRIPTOR_MULTIPLE 8 @@ -176,7 +178,6 @@ /* PHY GPY 211 registers */ #define STANDARD_AN_REG_MASK 0x0007 /* MMD */ -#define ANEG_MULTIGBT_AN_CTRL 0x0020 /* MULTI GBT AN Control Register */ #define MMD_DEVADDR_SHIFT 16 /* Shift MMD to higher bits */ #define CR_2500T_FD_CAPS 0x0080 /* Advertise 2500T FD capability */ @@ -307,6 +308,8 @@ #define IGC_TXD_DTYP_C 0x00000000 /* Context Descriptor */ #define IGC_TXD_POPTS_IXSM 0x01 /* Insert IP checksum */ #define IGC_TXD_POPTS_TXSM 0x02 /* Insert TCP/UDP checksum */ +#define IGC_TXD_POPTS_SMD_MASK 0x3000 /* Indicates whether it's SMD-V or SMD-R */ + #define IGC_TXD_CMD_EOP 0x01000000 /* End of Packet */ #define IGC_TXD_CMD_IC 0x04000000 /* Insert Checksum */ #define IGC_TXD_CMD_DEXT 0x20000000 /* Desc extension (0 = legacy) */ @@ -362,6 +365,8 @@ #define IGC_SRRCTL_TIMER0SEL(timer) (((timer) & 0x3) << 17) /* Receive Descriptor bit definitions */ +#define IGC_RXD_STAT_SMD_TYPE_V 0x01 /* SMD-V Packet */ +#define IGC_RXD_STAT_SMD_TYPE_R 0x02 /* SMD-R Packet */ #define IGC_RXD_STAT_EOP 0x02 /* End of Packet */ #define IGC_RXD_STAT_IXSM 0x04 /* Ignore checksum */ #define IGC_RXD_STAT_UDPCS 0x10 /* UDP xsum calculated */ @@ -371,7 +376,8 @@ #define IGC_RXDEXT_STATERR_LB 0x00040000 /* Advanced Receive Descriptor bit definitions */ -#define IGC_RXDADV_STAT_TSIP 0x08000 /* timestamp in packet */ +#define IGC_RXDADV_STAT_SMD_TYPE_MASK 0x06000 +#define IGC_RXDADV_STAT_TSIP 0x08000 /* timestamp in packet */ #define IGC_RXDEXT_STATERR_L4E 0x20000000 #define IGC_RXDEXT_STATERR_IPE 0x40000000 @@ -395,15 +401,57 @@ #define IGC_RCTL_PMCF 0x00800000 /* pass MAC control frames */ #define IGC_RCTL_SECRC 0x04000000 /* Strip Ethernet CRC */ -#define I225_RXPBSIZE_DEFAULT 0x000000A2 /* RXPBSIZE default */ -#define I225_TXPBSIZE_DEFAULT 0x04000014 /* TXPBSIZE default */ -#define IGC_RXPBS_CFG_TS_EN 0x80000000 /* Timestamp in Rx buffer */ - -#define IGC_TXPBSIZE_TSN 0x04145145 /* 5k bytes buffer for each queue */ +/* Mask for RX packet buffer size */ +#define IGC_RXPBSIZE_EXP_MASK GENMASK(5, 0) +#define IGC_BMC2OSPBSIZE_MASK GENMASK(11, 6) +#define IGC_RXPBSIZE_BE_MASK GENMASK(17, 12) +/* Mask for timestamp in RX buffer */ +#define IGC_RXPBS_CFG_TS_EN_MASK GENMASK(31, 31) +/* High-priority RX packet buffer size (KB). Used for Express traffic when preemption is enabled */ +#define IGC_RXPBSIZE_EXP(x) FIELD_PREP(IGC_RXPBSIZE_EXP_MASK, (x)) +/* BMC to OS packet buffer size in KB */ +#define IGC_BMC2OSPBSIZE(x) FIELD_PREP(IGC_BMC2OSPBSIZE_MASK, (x)) +/* Low-priority RX packet buffer size (KB). Used for BE traffic when preemption is enabled */ +#define IGC_RXPBSIZE_BE(x) FIELD_PREP(IGC_RXPBSIZE_BE_MASK, (x)) +/* Enable RX packet buffer for timestamp descriptor, saving 16 bytes per packet if set */ +#define IGC_RXPBS_CFG_TS_EN FIELD_PREP(IGC_RXPBS_CFG_TS_EN_MASK, 1) +/* Default value following I225/I226 SW User Manual Section 8.3.1 */ +#define IGC_RXPBSIZE_EXP_BMC_DEFAULT ( \ + IGC_RXPBSIZE_EXP(34) | IGC_BMC2OSPBSIZE(2)) +#define IGC_RXPBSIZE_EXP_BMC_BE_TSN ( \ + IGC_RXPBSIZE_EXP(15) | IGC_BMC2OSPBSIZE(2) | IGC_RXPBSIZE_BE(15)) + +/* Mask for TX packet buffer size */ +#define IGC_TXPB0SIZE_MASK GENMASK(5, 0) +#define IGC_TXPB1SIZE_MASK GENMASK(11, 6) +#define IGC_TXPB2SIZE_MASK GENMASK(17, 12) +#define IGC_TXPB3SIZE_MASK GENMASK(23, 18) +/* Mask for OS to BMC packet buffer size */ +#define IGC_OS2BMCPBSIZE_MASK GENMASK(29, 24) +/* TX Packet buffer size in KB */ +#define IGC_TXPB0SIZE(x) FIELD_PREP(IGC_TXPB0SIZE_MASK, (x)) +#define IGC_TXPB1SIZE(x) FIELD_PREP(IGC_TXPB1SIZE_MASK, (x)) +#define IGC_TXPB2SIZE(x) FIELD_PREP(IGC_TXPB2SIZE_MASK, (x)) +#define IGC_TXPB3SIZE(x) FIELD_PREP(IGC_TXPB3SIZE_MASK, (x)) +/* OS to BMC packet buffer size in KB */ +#define IGC_OS2BMCPBSIZE(x) FIELD_PREP(IGC_OS2BMCPBSIZE_MASK, (x)) +/* Default value following I225/I226 SW User Manual Section 8.3.2 */ +#define IGC_TXPBSIZE_DEFAULT ( \ + IGC_TXPB0SIZE(20) | IGC_TXPB1SIZE(0) | IGC_TXPB2SIZE(0) | \ + IGC_TXPB3SIZE(0) | IGC_OS2BMCPBSIZE(4)) +#define IGC_TXPBSIZE_TSN ( \ + IGC_TXPB0SIZE(7) | IGC_TXPB1SIZE(7) | IGC_TXPB2SIZE(7) | \ + IGC_TXPB3SIZE(7) | IGC_OS2BMCPBSIZE(4)) #define IGC_DTXMXPKTSZ_TSN 0x19 /* 1600 bytes of max TX DMA packet size */ #define IGC_DTXMXPKTSZ_DEFAULT 0x98 /* 9728-byte Jumbo frames */ +/* Retry Buffer Control */ +#define IGC_RETX_CTL 0x041C +#define IGC_RETX_CTL_WATERMARK_MASK 0xF +#define IGC_RETX_CTL_QBVFULLTH_SHIFT 8 /* QBV Retry Buffer Full Threshold */ +#define IGC_RETX_CTL_QBVFULLEN 0x1000 /* Enable QBV Retry Buffer Full Threshold */ + /* Transmit Scheduling Latency */ /* Latency between transmission scheduling (LaunchTime) and the time * the packet is transmitted to the network in nanosecond. @@ -532,8 +580,10 @@ /* Transmit Scheduling */ #define IGC_TQAVCTRL_TRANSMIT_MODE_TSN 0x00000001 +#define IGC_TQAVCTRL_PREEMPT_ENA 0x00000002 #define IGC_TQAVCTRL_ENHANCED_QAV 0x00000008 #define IGC_TQAVCTRL_FUTSCDDIS 0x00000080 +#define IGC_TQAVCTRL_MIN_FRAG_MASK 0x0000C000 #define IGC_TXQCTL_QUEUE_MODE_LAUNCHT 0x00000001 #define IGC_TXQCTL_STRICT_CYCLE 0x00000002 @@ -547,6 +597,15 @@ #define IGC_MAX_SR_QUEUES 2 +#define IGC_TXARB_TXQ_PRIO_0_MASK GENMASK(1, 0) +#define IGC_TXARB_TXQ_PRIO_1_MASK GENMASK(3, 2) +#define IGC_TXARB_TXQ_PRIO_2_MASK GENMASK(5, 4) +#define IGC_TXARB_TXQ_PRIO_3_MASK GENMASK(7, 6) +#define IGC_TXARB_TXQ_PRIO_0(x) FIELD_PREP(IGC_TXARB_TXQ_PRIO_0_MASK, (x)) +#define IGC_TXARB_TXQ_PRIO_1(x) FIELD_PREP(IGC_TXARB_TXQ_PRIO_1_MASK, (x)) +#define IGC_TXARB_TXQ_PRIO_2(x) FIELD_PREP(IGC_TXARB_TXQ_PRIO_2_MASK, (x)) +#define IGC_TXARB_TXQ_PRIO_3(x) FIELD_PREP(IGC_TXARB_TXQ_PRIO_3_MASK, (x)) + /* Receive Checksum Control */ #define IGC_RXCSUM_CRCOFL 0x00000800 /* CRC32 offload enable */ #define IGC_RXCSUM_PCSD 0x00002000 /* packet checksum disabled */ @@ -558,7 +617,10 @@ #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 1 /* Default short cycle interval */ +/* A short cycle time of 1us theoretically should work, but appears to be too + * short in practice. + */ +#define IGC_PTM_SHORT_CYC_DEFAULT 4 /* 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 */ @@ -577,6 +639,7 @@ #define IGC_PTM_STAT_T4M1_OVFL BIT(3) /* T4 minus T1 overflow */ #define IGC_PTM_STAT_ADJUST_1ST BIT(4) /* 1588 timer adjusted during 1st PTM cycle */ #define IGC_PTM_STAT_ADJUST_CYC BIT(5) /* 1588 timer adjusted during non-1st PTM cycle */ +#define IGC_PTM_STAT_ALL GENMASK(5, 0) /* Used to clear all status */ /* PCIe PTM Cycle Control */ #define IGC_PTM_CYCLE_CTRL_CYC_TIME(msec) ((msec) & 0x3ff) /* PTM Cycle Time (msec) */ @@ -635,6 +698,16 @@ #define IGC_MDIC_READY 0x10000000 #define IGC_MDIC_ERROR 0x40000000 +/* EEE Link Ability */ +#define IGC_EEE_2500BT_MASK BIT(0) +#define IGC_EEE_1000BT_MASK BIT(2) +#define IGC_EEE_100BT_MASK BIT(1) + +/* EEE Link-Partner Ability */ +#define IGC_LP_EEE_2500BT_MASK BIT(0) +#define IGC_LP_EEE_1000BT_MASK BIT(2) +#define IGC_LP_EEE_100BT_MASK BIT(1) + #define IGC_N0_QUEUE -1 #define IGC_MAX_MAC_HDR_LEN 127 diff --git a/drivers/net/ethernet/intel/igc/igc_diag.c b/drivers/net/ethernet/intel/igc/igc_diag.c index cc621970c0cd..a43d7244ee70 100644 --- a/drivers/net/ethernet/intel/igc/igc_diag.c +++ b/drivers/net/ethernet/intel/igc/igc_diag.c @@ -173,8 +173,7 @@ bool igc_link_test(struct igc_adapter *adapter, u64 *data) *data = 0; /* add delay to give enough time for autonegotioation to finish */ - if (adapter->hw.mac.autoneg) - ssleep(5); + ssleep(5); link_up = igc_has_link(adapter); if (!link_up) { diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index 1a64f1ca6ca8..3fc1eded9605 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -8,6 +8,7 @@ #include "igc.h" #include "igc_diag.h" +#include "igc_tsn.h" /* forward declaration */ struct igc_stats { @@ -1540,6 +1541,10 @@ static int igc_ethtool_set_channels(struct net_device *netdev, if (ch->other_count != NON_Q_VECTORS) return -EINVAL; + /* Do not allow channel reconfiguration when mqprio is enabled */ + if (adapter->strict_priority_enable) + return -EINVAL; + /* Verify the number of channels doesn't exceed hw limits */ max_combined = igc_get_max_rss_queues(adapter); if (count > max_combined) @@ -1559,21 +1564,17 @@ static int igc_ethtool_set_channels(struct net_device *netdev, } static int igc_ethtool_get_ts_info(struct net_device *dev, - struct ethtool_ts_info *info) + struct kernel_ethtool_ts_info *info) { struct igc_adapter *adapter = netdev_priv(dev); if (adapter->ptp_clock) info->phc_index = ptp_clock_index(adapter->ptp_clock); - else - info->phc_index = -1; switch (adapter->hw.mac.type) { case igc_i225: info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | - SOF_TIMESTAMPING_RX_SOFTWARE | - SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_TX_HARDWARE | SOF_TIMESTAMPING_RX_HARDWARE | SOF_TIMESTAMPING_RAW_HARDWARE; @@ -1627,13 +1628,85 @@ static int igc_ethtool_get_eee(struct net_device *netdev, { struct igc_adapter *adapter = netdev_priv(netdev); struct igc_hw *hw = &adapter->hw; - u32 eeer; + struct igc_phy_info *phy = &hw->phy; + u16 eee_advert, eee_lp_advert; + u32 eeer, ret_val; + + /* EEE supported */ + linkmode_set_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + edata->supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + edata->supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, + edata->supported); + + /* EEE Advertisement 1 - reg 7.60 */ + ret_val = phy->ops.read_reg(hw, (STANDARD_AN_REG_MASK << + MMD_DEVADDR_SHIFT) | + IGC_ANEG_EEE_AB1, + &eee_advert); + if (ret_val) { + netdev_err(adapter->netdev, + "Failed to read IEEE 7.60 register\n"); + return -EINVAL; + } - if (hw->dev_spec._base.eee_enable) - mii_eee_cap1_mod_linkmode_t(edata->advertised, - adapter->eee_advert); + if (eee_advert & IGC_EEE_1000BT_MASK) + linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + edata->advertised); - *edata = adapter->eee; + if (eee_advert & IGC_EEE_100BT_MASK) + linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, + edata->advertised); + + /* EEE Advertisement 2 - reg 7.62 */ + ret_val = phy->ops.read_reg(hw, (STANDARD_AN_REG_MASK << + MMD_DEVADDR_SHIFT) | + IGC_ANEG_EEE_AB2, + &eee_advert); + if (ret_val) { + netdev_err(adapter->netdev, + "Failed to read IEEE 7.62 register\n"); + return -EINVAL; + } + + if (eee_advert & IGC_EEE_2500BT_MASK) + linkmode_set_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + edata->advertised); + + /* EEE Link-Partner Ability 1 - reg 7.61 */ + ret_val = phy->ops.read_reg(hw, (STANDARD_AN_REG_MASK << + MMD_DEVADDR_SHIFT) | + IGC_ANEG_EEE_LP_AB1, + &eee_lp_advert); + if (ret_val) { + netdev_err(adapter->netdev, + "Failed to read IEEE 7.61 register\n"); + return -EINVAL; + } + + if (eee_lp_advert & IGC_LP_EEE_1000BT_MASK) + linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + edata->lp_advertised); + + if (eee_lp_advert & IGC_LP_EEE_100BT_MASK) + linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, + edata->lp_advertised); + + /* EEE Link-Partner Ability 2 - reg 7.63 */ + ret_val = phy->ops.read_reg(hw, (STANDARD_AN_REG_MASK << + MMD_DEVADDR_SHIFT) | + IGC_ANEG_EEE_LP_AB2, + &eee_lp_advert); + if (ret_val) { + netdev_err(adapter->netdev, + "Failed to read IEEE 7.63 register\n"); + return -EINVAL; + } + + if (eee_lp_advert & IGC_LP_EEE_2500BT_MASK) + linkmode_set_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + edata->lp_advertised); eeer = rd32(IGC_EEER); @@ -1695,8 +1768,6 @@ static int igc_ethtool_set_eee(struct net_device *netdev, return -EINVAL; } - adapter->eee_advert = linkmode_to_mii_eee_cap1_t(edata->advertised); - if (hw->dev_spec._base.eee_enable != edata->eee_enabled) { hw->dev_spec._base.eee_enable = edata->eee_enabled; adapter->flags |= IGC_FLAG_EEE; @@ -1711,19 +1782,81 @@ static int igc_ethtool_set_eee(struct net_device *netdev, return 0; } -static int igc_ethtool_begin(struct net_device *netdev) +static int igc_ethtool_get_mm(struct net_device *netdev, + struct ethtool_mm_state *cmd) { struct igc_adapter *adapter = netdev_priv(netdev); + struct igc_fpe_t *fpe = &adapter->fpe; + + ethtool_mmsv_get_mm(&fpe->mmsv, cmd); + cmd->tx_min_frag_size = fpe->tx_min_frag_size; + cmd->rx_min_frag_size = IGC_RX_MIN_FRAG_SIZE; - pm_runtime_get_sync(&adapter->pdev->dev); return 0; } -static void igc_ethtool_complete(struct net_device *netdev) +static int igc_ethtool_set_mm(struct net_device *netdev, + struct ethtool_mm_cfg *cmd, + struct netlink_ext_ack *extack) { struct igc_adapter *adapter = netdev_priv(netdev); + struct igc_fpe_t *fpe = &adapter->fpe; + + fpe->tx_min_frag_size = igc_fpe_get_supported_frag_size(cmd->tx_min_frag_size); + if (fpe->tx_min_frag_size != cmd->tx_min_frag_size) + NL_SET_ERR_MSG_MOD(extack, + "tx-min-frag-size value set is unsupported. Rounded up to supported value (64, 128, 192, 256)"); + + if (fpe->mmsv.pmac_enabled != cmd->pmac_enabled) { + if (cmd->pmac_enabled) + static_branch_inc(&igc_fpe_enabled); + else + static_branch_dec(&igc_fpe_enabled); + } - pm_runtime_put(&adapter->pdev->dev); + ethtool_mmsv_set_mm(&fpe->mmsv, cmd); + + return igc_tsn_offload_apply(adapter); +} + +/** + * igc_ethtool_get_frame_ass_error - Get the frame assembly error count. + * @reg_value: Register value for IGC_PRMEXCPRCNT + * Return: The count of frame assembly errors. + */ +static u64 igc_ethtool_get_frame_ass_error(u32 reg_value) +{ + /* Out of order statistics */ + u32 ooo_frame_cnt, ooo_frag_cnt; + u32 miss_frame_frag_cnt; + + ooo_frame_cnt = FIELD_GET(IGC_PRMEXCPRCNT_OOO_FRAME_CNT, reg_value); + ooo_frag_cnt = FIELD_GET(IGC_PRMEXCPRCNT_OOO_FRAG_CNT, reg_value); + miss_frame_frag_cnt = FIELD_GET(IGC_PRMEXCPRCNT_MISS_FRAME_FRAG_CNT, + reg_value); + + return ooo_frame_cnt + ooo_frag_cnt + miss_frame_frag_cnt; +} + +static u64 igc_ethtool_get_frame_smd_error(u32 reg_value) +{ + return FIELD_GET(IGC_PRMEXCPRCNT_OOO_SMDC, reg_value); +} + +static void igc_ethtool_get_mm_stats(struct net_device *dev, + struct ethtool_mm_stats *stats) +{ + struct igc_adapter *adapter = netdev_priv(dev); + struct igc_hw *hw = &adapter->hw; + u32 reg_value; + + reg_value = rd32(IGC_PRMEXCPRCNT); + + stats->MACMergeFrameAssErrorCount = igc_ethtool_get_frame_ass_error(reg_value); + stats->MACMergeFrameSmdErrorCount = igc_ethtool_get_frame_smd_error(reg_value); + stats->MACMergeFrameAssOkCount = rd32(IGC_PRMPTDRCNT); + stats->MACMergeFragCountRx = rd32(IGC_PRMEVNTRCNT); + stats->MACMergeFragCountTx = rd32(IGC_PRMEVNTTCNT); } static int igc_ethtool_get_link_ksettings(struct net_device *netdev, @@ -1766,11 +1899,8 @@ static int igc_ethtool_get_link_ksettings(struct net_device *netdev, ethtool_link_ksettings_add_link_mode(cmd, advertising, 2500baseT_Full); /* set autoneg settings */ - if (hw->mac.autoneg == 1) { - ethtool_link_ksettings_add_link_mode(cmd, supported, Autoneg); - ethtool_link_ksettings_add_link_mode(cmd, advertising, - Autoneg); - } + ethtool_link_ksettings_add_link_mode(cmd, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(cmd, advertising, Autoneg); /* Set pause flow control settings */ ethtool_link_ksettings_add_link_mode(cmd, supported, Pause); @@ -1823,10 +1953,7 @@ static int igc_ethtool_get_link_ksettings(struct net_device *netdev, cmd->base.duplex = DUPLEX_UNKNOWN; } cmd->base.speed = speed; - if (hw->mac.autoneg) - cmd->base.autoneg = AUTONEG_ENABLE; - else - cmd->base.autoneg = AUTONEG_DISABLE; + cmd->base.autoneg = AUTONEG_ENABLE; /* MDI-X => 2; MDI =>1; Invalid =>0 */ if (hw->phy.media_type == igc_media_type_copper) @@ -1900,7 +2027,6 @@ igc_ethtool_set_link_ksettings(struct net_device *netdev, advertised |= ADVERTISE_10_HALF; if (cmd->base.autoneg == AUTONEG_ENABLE) { - hw->mac.autoneg = 1; hw->phy.autoneg_advertised = advertised; if (adapter->fc_autoneg) hw->fc.requested_mode = igc_fc_default; @@ -2025,11 +2151,12 @@ static const struct ethtool_ops igc_ethtool_ops = { .set_priv_flags = igc_ethtool_set_priv_flags, .get_eee = igc_ethtool_get_eee, .set_eee = igc_ethtool_set_eee, - .begin = igc_ethtool_begin, - .complete = igc_ethtool_complete, .get_link_ksettings = igc_ethtool_get_link_ksettings, .set_link_ksettings = igc_ethtool_set_link_ksettings, .self_test = igc_ethtool_diag_test, + .get_mm = igc_ethtool_get_mm, + .get_mm_stats = igc_ethtool_get_mm_stats, + .set_mm = igc_ethtool_set_mm, }; void igc_ethtool_set_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/intel/igc/igc_hw.h b/drivers/net/ethernet/intel/igc/igc_hw.h index e1c572e0d4ef..be8a49a86d09 100644 --- a/drivers/net/ethernet/intel/igc/igc_hw.h +++ b/drivers/net/ethernet/intel/igc/igc_hw.h @@ -92,7 +92,6 @@ struct igc_mac_info { bool asf_firmware_present; bool arc_subsystem_valid; - bool autoneg; bool autoneg_failed; bool get_link_status; }; @@ -280,9 +279,4 @@ struct net_device *igc_get_hw_dev(struct igc_hw *hw); #define hw_dbg(format, arg...) \ netdev_dbg(igc_get_hw_dev(hw), format, ##arg) -s32 igc_read_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value); -s32 igc_write_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value); -void igc_read_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value); -void igc_write_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value); - #endif /* _IGC_HW_H_ */ diff --git a/drivers/net/ethernet/intel/igc/igc_mac.c b/drivers/net/ethernet/intel/igc/igc_mac.c index a5c4b19d71a2..d344e0a1cd5e 100644 --- a/drivers/net/ethernet/intel/igc/igc_mac.c +++ b/drivers/net/ethernet/intel/igc/igc_mac.c @@ -386,14 +386,6 @@ s32 igc_check_for_copper_link(struct igc_hw *hw) */ igc_check_downshift(hw); - /* If we are forcing speed/duplex, then we simply return since - * we have already determined whether we have link or not. - */ - if (!mac->autoneg) { - ret_val = -IGC_ERR_CONFIG; - goto out; - } - /* Auto-Neg is enabled. Auto Speed Detection takes care * of MAC speed/duplex configuration. So we only need to * configure Collision Distance in the MAC. @@ -468,173 +460,171 @@ s32 igc_config_fc_after_link_up(struct igc_hw *hw) goto out; } - /* Check for the case where we have copper media and auto-neg is - * enabled. In this case, we need to check and see if Auto-Neg - * has completed, and if so, how the PHY and link partner has - * flow control configured. + /* In auto-neg, we need to check and see if Auto-Neg has completed, + * and if so, how the PHY and link partner has flow control + * configured. */ - if (mac->autoneg) { - /* Read the MII Status Register and check to see if AutoNeg - * has completed. We read this twice because this reg has - * some "sticky" (latched) bits. - */ - ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, - &mii_status_reg); - if (ret_val) - goto out; - ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, - &mii_status_reg); - if (ret_val) - goto out; - if (!(mii_status_reg & MII_SR_AUTONEG_COMPLETE)) { - hw_dbg("Copper PHY and Auto Neg has not completed.\n"); - goto out; - } + /* Read the MII Status Register and check to see if AutoNeg + * has completed. We read this twice because this reg has + * some "sticky" (latched) bits. + */ + ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, + &mii_status_reg); + if (ret_val) + goto out; + ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, + &mii_status_reg); + if (ret_val) + goto out; - /* The AutoNeg process has completed, so we now need to - * read both the Auto Negotiation Advertisement - * Register (Address 4) and the Auto_Negotiation Base - * Page Ability Register (Address 5) to determine how - * flow control was negotiated. - */ - ret_val = hw->phy.ops.read_reg(hw, PHY_AUTONEG_ADV, - &mii_nway_adv_reg); - if (ret_val) - goto out; - ret_val = hw->phy.ops.read_reg(hw, PHY_LP_ABILITY, - &mii_nway_lp_ability_reg); - if (ret_val) - goto out; - /* Two bits in the Auto Negotiation Advertisement Register - * (Address 4) and two bits in the Auto Negotiation Base - * Page Ability Register (Address 5) determine flow control - * for both the PHY and the link partner. The following - * table, taken out of the IEEE 802.3ab/D6.0 dated March 25, - * 1999, describes these PAUSE resolution bits and how flow - * control is determined based upon these settings. - * NOTE: DC = Don't Care - * - * LOCAL DEVICE | LINK PARTNER - * PAUSE | ASM_DIR | PAUSE | ASM_DIR | NIC Resolution - *-------|---------|-------|---------|-------------------- - * 0 | 0 | DC | DC | igc_fc_none - * 0 | 1 | 0 | DC | igc_fc_none - * 0 | 1 | 1 | 0 | igc_fc_none - * 0 | 1 | 1 | 1 | igc_fc_tx_pause - * 1 | 0 | 0 | DC | igc_fc_none - * 1 | DC | 1 | DC | igc_fc_full - * 1 | 1 | 0 | 0 | igc_fc_none - * 1 | 1 | 0 | 1 | igc_fc_rx_pause - * - * Are both PAUSE bits set to 1? If so, this implies - * Symmetric Flow Control is enabled at both ends. The - * ASM_DIR bits are irrelevant per the spec. - * - * For Symmetric Flow Control: - * - * LOCAL DEVICE | LINK PARTNER - * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result - *-------|---------|-------|---------|-------------------- - * 1 | DC | 1 | DC | IGC_fc_full - * - */ - if ((mii_nway_adv_reg & NWAY_AR_PAUSE) && - (mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE)) { - /* Now we need to check if the user selected RX ONLY - * of pause frames. In this case, we had to advertise - * FULL flow control because we could not advertise RX - * ONLY. Hence, we must now check to see if we need to - * turn OFF the TRANSMISSION of PAUSE frames. - */ - if (hw->fc.requested_mode == igc_fc_full) { - hw->fc.current_mode = igc_fc_full; - hw_dbg("Flow Control = FULL.\n"); - } else { - hw->fc.current_mode = igc_fc_rx_pause; - hw_dbg("Flow Control = RX PAUSE frames only.\n"); - } - } + if (!(mii_status_reg & MII_SR_AUTONEG_COMPLETE)) { + hw_dbg("Copper PHY and Auto Neg has not completed.\n"); + goto out; + } - /* For receiving PAUSE frames ONLY. - * - * LOCAL DEVICE | LINK PARTNER - * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result - *-------|---------|-------|---------|-------------------- - * 0 | 1 | 1 | 1 | igc_fc_tx_pause - */ - else if (!(mii_nway_adv_reg & NWAY_AR_PAUSE) && - (mii_nway_adv_reg & NWAY_AR_ASM_DIR) && - (mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE) && - (mii_nway_lp_ability_reg & NWAY_LPAR_ASM_DIR)) { - hw->fc.current_mode = igc_fc_tx_pause; - hw_dbg("Flow Control = TX PAUSE frames only.\n"); - } - /* For transmitting PAUSE frames ONLY. - * - * LOCAL DEVICE | LINK PARTNER - * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result - *-------|---------|-------|---------|-------------------- - * 1 | 1 | 0 | 1 | igc_fc_rx_pause - */ - else if ((mii_nway_adv_reg & NWAY_AR_PAUSE) && - (mii_nway_adv_reg & NWAY_AR_ASM_DIR) && - !(mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE) && - (mii_nway_lp_ability_reg & NWAY_LPAR_ASM_DIR)) { - hw->fc.current_mode = igc_fc_rx_pause; - hw_dbg("Flow Control = RX PAUSE frames only.\n"); - } - /* Per the IEEE spec, at this point flow control should be - * disabled. However, we want to consider that we could - * be connected to a legacy switch that doesn't advertise - * desired flow control, but can be forced on the link - * partner. So if we advertised no flow control, that is - * what we will resolve to. If we advertised some kind of - * receive capability (Rx Pause Only or Full Flow Control) - * and the link partner advertised none, we will configure - * ourselves to enable Rx Flow Control only. We can do - * this safely for two reasons: If the link partner really - * didn't want flow control enabled, and we enable Rx, no - * harm done since we won't be receiving any PAUSE frames - * anyway. If the intent on the link partner was to have - * flow control enabled, then by us enabling RX only, we - * can at least receive pause frames and process them. - * This is a good idea because in most cases, since we are - * predominantly a server NIC, more times than not we will - * be asked to delay transmission of packets than asking - * our link partner to pause transmission of frames. + /* The AutoNeg process has completed, so we now need to + * read both the Auto Negotiation Advertisement + * Register (Address 4) and the Auto_Negotiation Base + * Page Ability Register (Address 5) to determine how + * flow control was negotiated. + */ + ret_val = hw->phy.ops.read_reg(hw, PHY_AUTONEG_ADV, + &mii_nway_adv_reg); + if (ret_val) + goto out; + ret_val = hw->phy.ops.read_reg(hw, PHY_LP_ABILITY, + &mii_nway_lp_ability_reg); + if (ret_val) + goto out; + /* Two bits in the Auto Negotiation Advertisement Register + * (Address 4) and two bits in the Auto Negotiation Base + * Page Ability Register (Address 5) determine flow control + * for both the PHY and the link partner. The following + * table, taken out of the IEEE 802.3ab/D6.0 dated March 25, + * 1999, describes these PAUSE resolution bits and how flow + * control is determined based upon these settings. + * NOTE: DC = Don't Care + * + * LOCAL DEVICE | LINK PARTNER + * PAUSE | ASM_DIR | PAUSE | ASM_DIR | NIC Resolution + *-------|---------|-------|---------|-------------------- + * 0 | 0 | DC | DC | igc_fc_none + * 0 | 1 | 0 | DC | igc_fc_none + * 0 | 1 | 1 | 0 | igc_fc_none + * 0 | 1 | 1 | 1 | igc_fc_tx_pause + * 1 | 0 | 0 | DC | igc_fc_none + * 1 | DC | 1 | DC | igc_fc_full + * 1 | 1 | 0 | 0 | igc_fc_none + * 1 | 1 | 0 | 1 | igc_fc_rx_pause + * + * Are both PAUSE bits set to 1? If so, this implies + * Symmetric Flow Control is enabled at both ends. The + * ASM_DIR bits are irrelevant per the spec. + * + * For Symmetric Flow Control: + * + * LOCAL DEVICE | LINK PARTNER + * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result + *-------|---------|-------|---------|-------------------- + * 1 | DC | 1 | DC | IGC_fc_full + * + */ + if ((mii_nway_adv_reg & NWAY_AR_PAUSE) && + (mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE)) { + /* Now we need to check if the user selected RX ONLY + * of pause frames. In this case, we had to advertise + * FULL flow control because we could not advertise RX + * ONLY. Hence, we must now check to see if we need to + * turn OFF the TRANSMISSION of PAUSE frames. */ - else if ((hw->fc.requested_mode == igc_fc_none) || - (hw->fc.requested_mode == igc_fc_tx_pause) || - (hw->fc.strict_ieee)) { - hw->fc.current_mode = igc_fc_none; - hw_dbg("Flow Control = NONE.\n"); + if (hw->fc.requested_mode == igc_fc_full) { + hw->fc.current_mode = igc_fc_full; + hw_dbg("Flow Control = FULL.\n"); } else { hw->fc.current_mode = igc_fc_rx_pause; hw_dbg("Flow Control = RX PAUSE frames only.\n"); } + } - /* Now we need to do one last check... If we auto- - * negotiated to HALF DUPLEX, flow control should not be - * enabled per IEEE 802.3 spec. - */ - ret_val = hw->mac.ops.get_speed_and_duplex(hw, &speed, &duplex); - if (ret_val) { - hw_dbg("Error getting link speed and duplex\n"); - goto out; - } + /* For receiving PAUSE frames ONLY. + * + * LOCAL DEVICE | LINK PARTNER + * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result + *-------|---------|-------|---------|-------------------- + * 0 | 1 | 1 | 1 | igc_fc_tx_pause + */ + else if (!(mii_nway_adv_reg & NWAY_AR_PAUSE) && + (mii_nway_adv_reg & NWAY_AR_ASM_DIR) && + (mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE) && + (mii_nway_lp_ability_reg & NWAY_LPAR_ASM_DIR)) { + hw->fc.current_mode = igc_fc_tx_pause; + hw_dbg("Flow Control = TX PAUSE frames only.\n"); + } + /* For transmitting PAUSE frames ONLY. + * + * LOCAL DEVICE | LINK PARTNER + * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result + *-------|---------|-------|---------|-------------------- + * 1 | 1 | 0 | 1 | igc_fc_rx_pause + */ + else if ((mii_nway_adv_reg & NWAY_AR_PAUSE) && + (mii_nway_adv_reg & NWAY_AR_ASM_DIR) && + !(mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE) && + (mii_nway_lp_ability_reg & NWAY_LPAR_ASM_DIR)) { + hw->fc.current_mode = igc_fc_rx_pause; + hw_dbg("Flow Control = RX PAUSE frames only.\n"); + } + /* Per the IEEE spec, at this point flow control should be + * disabled. However, we want to consider that we could + * be connected to a legacy switch that doesn't advertise + * desired flow control, but can be forced on the link + * partner. So if we advertised no flow control, that is + * what we will resolve to. If we advertised some kind of + * receive capability (Rx Pause Only or Full Flow Control) + * and the link partner advertised none, we will configure + * ourselves to enable Rx Flow Control only. We can do + * this safely for two reasons: If the link partner really + * didn't want flow control enabled, and we enable Rx, no + * harm done since we won't be receiving any PAUSE frames + * anyway. If the intent on the link partner was to have + * flow control enabled, then by us enabling RX only, we + * can at least receive pause frames and process them. + * This is a good idea because in most cases, since we are + * predominantly a server NIC, more times than not we will + * be asked to delay transmission of packets than asking + * our link partner to pause transmission of frames. + */ + else if ((hw->fc.requested_mode == igc_fc_none) || + (hw->fc.requested_mode == igc_fc_tx_pause) || + (hw->fc.strict_ieee)) { + hw->fc.current_mode = igc_fc_none; + hw_dbg("Flow Control = NONE.\n"); + } else { + hw->fc.current_mode = igc_fc_rx_pause; + hw_dbg("Flow Control = RX PAUSE frames only.\n"); + } - if (duplex == HALF_DUPLEX) - hw->fc.current_mode = igc_fc_none; + /* Now we need to do one last check... If we auto- + * negotiated to HALF DUPLEX, flow control should not be + * enabled per IEEE 802.3 spec. + */ + ret_val = hw->mac.ops.get_speed_and_duplex(hw, &speed, &duplex); + if (ret_val) { + hw_dbg("Error getting link speed and duplex\n"); + goto out; + } - /* Now we call a subroutine to actually force the MAC - * controller to use the correct flow control settings. - */ - ret_val = igc_force_mac_fc(hw); - if (ret_val) { - hw_dbg("Error forcing flow control settings\n"); - goto out; - } + if (duplex == HALF_DUPLEX) + hw->fc.current_mode = igc_fc_none; + + /* Now we call a subroutine to actually force the MAC + * controller to use the correct flow control settings. + */ + ret_val = igc_force_mac_fc(hw); + if (ret_val) { + hw_dbg("Error forcing flow control settings\n"); + goto out; } out: diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 4d975d620a8e..27575a1e1777 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -12,6 +12,7 @@ #include <linux/bpf_trace.h> #include <net/xdp_sock_drv.h> #include <linux/pci.h> +#include <linux/mdio.h> #include <net/ipv6.h> @@ -31,7 +32,6 @@ static int debug = -1; -MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION(DRV_SUMMARY); MODULE_LICENSE("GPL v2"); module_param(debug, int, 0); @@ -1092,10 +1092,12 @@ static int igc_init_empty_frame(struct igc_ring *ring, dma = dma_map_single(ring->dev, skb->data, size, DMA_TO_DEVICE); if (dma_mapping_error(ring->dev, dma)) { - netdev_err_once(ring->netdev, "Failed to map DMA for TX\n"); + net_err_ratelimited("%s: DMA mapping error for empty frame\n", + netdev_name(ring->netdev)); return -ENOMEM; } + buffer->type = IGC_TX_BUFFER_TYPE_SKB; buffer->skb = skb; buffer->protocol = 0; buffer->bytecount = skb->len; @@ -1107,20 +1109,12 @@ static int igc_init_empty_frame(struct igc_ring *ring, return 0; } -static int igc_init_tx_empty_descriptor(struct igc_ring *ring, - struct sk_buff *skb, - struct igc_tx_buffer *first) +static void igc_init_tx_empty_descriptor(struct igc_ring *ring, + struct sk_buff *skb, + struct igc_tx_buffer *first) { union igc_adv_tx_desc *desc; u32 cmd_type, olinfo_status; - int err; - - if (!igc_desc_unused(ring)) - return -EBUSY; - - err = igc_init_empty_frame(ring, first, skb); - if (err) - return err; cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT | IGC_ADVTXD_DCMD_IFCS | IGC_TXD_DCMD | @@ -1139,8 +1133,6 @@ static int igc_init_tx_empty_descriptor(struct igc_ring *ring, ring->next_to_use++; if (ring->next_to_use == ring->count) ring->next_to_use = 0; - - return 0; } #define IGC_EMPTY_FRAME_SIZE 60 @@ -1566,6 +1558,40 @@ static bool igc_request_tx_tstamp(struct igc_adapter *adapter, struct sk_buff *s return false; } +static int igc_insert_empty_frame(struct igc_ring *tx_ring) +{ + struct igc_tx_buffer *empty_info; + struct sk_buff *empty_skb; + void *data; + int ret; + + empty_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + empty_skb = alloc_skb(IGC_EMPTY_FRAME_SIZE, GFP_ATOMIC); + if (unlikely(!empty_skb)) { + net_err_ratelimited("%s: skb alloc error for empty frame\n", + netdev_name(tx_ring->netdev)); + return -ENOMEM; + } + + data = skb_put(empty_skb, IGC_EMPTY_FRAME_SIZE); + memset(data, 0, IGC_EMPTY_FRAME_SIZE); + + /* Prepare DMA mapping and Tx buffer information */ + ret = igc_init_empty_frame(tx_ring, empty_info, empty_skb); + if (unlikely(ret)) { + dev_kfree_skb_any(empty_skb); + return ret; + } + + /* Prepare advanced context descriptor for empty packet */ + igc_tx_ctxtdesc(tx_ring, 0, false, 0, 0, 0); + + /* Prepare advanced data descriptor for empty packet */ + igc_init_tx_empty_descriptor(tx_ring, empty_skb, empty_info); + + return 0; +} + static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, struct igc_ring *tx_ring) { @@ -1585,6 +1611,7 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, * + 1 desc for skb_headlen/IGC_MAX_DATA_PER_TXD, * + 2 desc gap to keep tail from touching head, * + 1 desc for context descriptor, + * + 2 desc for inserting an empty packet for launch time, * otherwise try next time */ for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) @@ -1604,24 +1631,16 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, launch_time = igc_tx_launchtime(tx_ring, txtime, &first_flag, &insert_empty); if (insert_empty) { - struct igc_tx_buffer *empty_info; - struct sk_buff *empty; - void *data; - - empty_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; - empty = alloc_skb(IGC_EMPTY_FRAME_SIZE, GFP_ATOMIC); - if (!empty) - goto done; - - data = skb_put(empty, IGC_EMPTY_FRAME_SIZE); - memset(data, 0, IGC_EMPTY_FRAME_SIZE); - - igc_tx_ctxtdesc(tx_ring, 0, false, 0, 0, 0); - - if (igc_init_tx_empty_descriptor(tx_ring, - empty, - empty_info) < 0) - dev_kfree_skb_any(empty); + /* Reset the launch time if the required empty frame fails to + * be inserted. However, this packet is not dropped, so it + * "dirties" the current Qbv cycle. This ensures that the + * upcoming packet, which is scheduled in the next Qbv cycle, + * does not require an empty frame. This way, the launch time + * continues to function correctly despite the current failure + * to insert the empty frame. + */ + if (igc_insert_empty_frame(tx_ring)) + launch_time = 0; } done: @@ -1649,7 +1668,8 @@ done: if (igc_request_tx_tstamp(adapter, skb, &tstamp_flags)) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; tx_flags |= IGC_TX_FLAGS_TSTAMP | tstamp_flags; - if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_USE_CYCLES) + if (skb->sk && + READ_ONCE(skb->sk->sk_tsflags) & SOF_TIMESTAMPING_BIND_PHC) tx_flags |= IGC_TX_FLAGS_TSTAMP_TIMER_1; } else { adapter->tx_hwtstamp_skipped++; @@ -2123,10 +2143,6 @@ static bool igc_cleanup_headers(struct igc_ring *rx_ring, union igc_adv_rx_desc *rx_desc, struct sk_buff *skb) { - /* XDP packets use error pointer so abort at this point */ - if (IS_ERR(skb)) - return true; - if (unlikely(igc_test_staterr(rx_desc, IGC_RXDEXT_STATERR_RXE))) { struct net_device *netdev = rx_ring->netdev; @@ -2191,6 +2207,7 @@ static bool igc_alloc_mapped_page(struct igc_ring *rx_ring, page = dev_alloc_pages(igc_rx_pg_order(rx_ring)); if (unlikely(!page)) { rx_ring->rx_stats.alloc_failed++; + set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); return false; } @@ -2207,6 +2224,7 @@ static bool igc_alloc_mapped_page(struct igc_ring *rx_ring, __free_page(page); rx_ring->rx_stats.alloc_failed++; + set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); return false; } @@ -2446,8 +2464,7 @@ unmap: return -ENOMEM; } -static struct igc_ring *igc_xdp_get_tx_ring(struct igc_adapter *adapter, - int cpu) +struct igc_ring *igc_get_tx_ring(struct igc_adapter *adapter, int cpu) { int index = cpu; @@ -2471,7 +2488,7 @@ static int igc_xdp_xmit_back(struct igc_adapter *adapter, struct xdp_buff *xdp) if (unlikely(!xdpf)) return -EFAULT; - ring = igc_xdp_get_tx_ring(adapter, cpu); + ring = igc_get_tx_ring(adapter, cpu); nq = txring_txq(ring); __netif_tx_lock(nq, cpu); @@ -2513,8 +2530,7 @@ out_failure: } } -static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter, - struct xdp_buff *xdp) +static int igc_xdp_run_prog(struct igc_adapter *adapter, struct xdp_buff *xdp) { struct bpf_prog *prog; int res; @@ -2528,11 +2544,11 @@ static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter, res = __igc_xdp_run_prog(adapter, prog, xdp); out: - return ERR_PTR(-res); + return res; } /* This function assumes __netif_tx_lock is held by the caller. */ -static void igc_flush_tx_descriptors(struct igc_ring *ring) +void igc_flush_tx_descriptors(struct igc_ring *ring) { /* Once tail pointer is updated, hardware can fetch the descriptors * any time so we issue a write membar here to ensure all memory @@ -2549,7 +2565,7 @@ static void igc_finalize_xdp(struct igc_adapter *adapter, int status) struct igc_ring *ring; if (status & IGC_XDP_TX) { - ring = igc_xdp_get_tx_ring(adapter, cpu); + ring = igc_get_tx_ring(adapter, cpu); nq = txring_txq(ring); __netif_tx_lock(nq, cpu); @@ -2583,6 +2599,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) struct sk_buff *skb = rx_ring->skb; u16 cleaned_count = igc_desc_unused(rx_ring); int xdp_status = 0, rx_buffer_pgcnt; + int xdp_res = 0; while (likely(total_packets < budget)) { struct igc_xdp_buff ctx = { .rx_ts = NULL }; @@ -2620,6 +2637,14 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) size -= IGC_TS_HDR_LEN; } + if (igc_fpe_is_pmac_enabled(adapter) && + igc_fpe_handle_mpacket(adapter, rx_desc, size, pktbuf)) { + /* Advance the ring next-to-clean */ + igc_is_non_eop(rx_ring, rx_desc); + cleaned_count++; + continue; + } + if (!skb) { xdp_init_buff(&ctx.xdp, truesize, &rx_ring->xdp_rxq); xdp_prepare_buff(&ctx.xdp, pktbuf - igc_rx_offset(rx_ring), @@ -2628,12 +2653,10 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) xdp_buff_clear_frags_flag(&ctx.xdp); ctx.rx_desc = rx_desc; - skb = igc_xdp_run_prog(adapter, &ctx.xdp); + xdp_res = igc_xdp_run_prog(adapter, &ctx.xdp); } - if (IS_ERR(skb)) { - unsigned int xdp_res = -PTR_ERR(skb); - + if (xdp_res) { switch (xdp_res) { case IGC_XDP_CONSUMED: rx_buffer->pagecnt_bias++; @@ -2655,9 +2678,10 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) skb = igc_construct_skb(rx_ring, rx_buffer, &ctx); /* exit if we failed to retrieve a buffer */ - if (!skb) { + if (!xdp_res && !skb) { rx_ring->rx_stats.alloc_failed++; rx_buffer->pagecnt_bias++; + set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); break; } @@ -2669,7 +2693,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) continue; /* verify the packet layout is correct */ - if (igc_cleanup_headers(rx_ring, rx_desc, skb)) { + if (xdp_res || igc_cleanup_headers(rx_ring, rx_desc, skb)) { skb = NULL; continue; } @@ -2704,16 +2728,16 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) } static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring, - struct xdp_buff *xdp) + struct igc_xdp_buff *ctx) { + struct xdp_buff *xdp = &ctx->xdp; unsigned int totalsize = xdp->data_end - xdp->data_meta; unsigned int metasize = xdp->data - xdp->data_meta; struct sk_buff *skb; net_prefetch(xdp->data_meta); - skb = __napi_alloc_skb(&ring->q_vector->napi, totalsize, - GFP_ATOMIC | __GFP_NOWARN); + skb = napi_alloc_skb(&ring->q_vector->napi, totalsize); if (unlikely(!skb)) return NULL; @@ -2725,26 +2749,28 @@ static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring, __skb_pull(skb, metasize); } + if (ctx->rx_ts) { + skb_shinfo(skb)->tx_flags |= SKBTX_HW_TSTAMP_NETDEV; + skb_hwtstamps(skb)->netdev_data = ctx->rx_ts; + } + return skb; } static void igc_dispatch_skb_zc(struct igc_q_vector *q_vector, union igc_adv_rx_desc *desc, - struct xdp_buff *xdp, - ktime_t timestamp) + struct igc_xdp_buff *ctx) { struct igc_ring *ring = q_vector->rx.ring; struct sk_buff *skb; - skb = igc_construct_skb_zc(ring, xdp); + skb = igc_construct_skb_zc(ring, ctx); if (!skb) { ring->rx_stats.alloc_failed++; + set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &ring->flags); return; } - if (timestamp) - skb_hwtstamps(skb)->hwtstamp = timestamp; - if (igc_cleanup_headers(ring, desc, skb)) return; @@ -2780,7 +2806,6 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget) union igc_adv_rx_desc *desc; struct igc_rx_buffer *bi; struct igc_xdp_buff *ctx; - ktime_t timestamp = 0; unsigned int size; int res; @@ -2810,15 +2835,17 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget) */ bi->xdp->data_meta += IGC_TS_HDR_LEN; size -= IGC_TS_HDR_LEN; + } else { + ctx->rx_ts = NULL; } bi->xdp->data_end = bi->xdp->data + size; - xsk_buff_dma_sync_for_cpu(bi->xdp, ring->xsk_pool); + xsk_buff_dma_sync_for_cpu(bi->xdp); res = __igc_xdp_run_prog(adapter, prog, bi->xdp); switch (res) { case IGC_XDP_PASS: - igc_dispatch_skb_zc(q_vector, desc, bi->xdp, timestamp); + igc_dispatch_skb_zc(q_vector, desc, ctx); fallthrough; case IGC_XDP_CONSUMED: xsk_buff_free(bi->xdp); @@ -2874,6 +2901,128 @@ static void igc_update_tx_stats(struct igc_q_vector *q_vector, q_vector->tx.total_packets += packets; } +static void igc_xsk_request_timestamp(void *_priv) +{ + struct igc_metadata_request *meta_req = _priv; + struct igc_ring *tx_ring = meta_req->tx_ring; + struct igc_tx_timestamp_request *tstamp; + u32 tx_flags = IGC_TX_FLAGS_TSTAMP; + struct igc_adapter *adapter; + unsigned long lock_flags; + bool found = false; + int i; + + if (test_bit(IGC_RING_FLAG_TX_HWTSTAMP, &tx_ring->flags)) { + adapter = netdev_priv(tx_ring->netdev); + + spin_lock_irqsave(&adapter->ptp_tx_lock, lock_flags); + + /* Search for available tstamp regs */ + for (i = 0; i < IGC_MAX_TX_TSTAMP_REGS; i++) { + tstamp = &adapter->tx_tstamp[i]; + + /* tstamp->skb and tstamp->xsk_tx_buffer are in union. + * When tstamp->skb is equal to NULL, + * tstamp->xsk_tx_buffer is equal to NULL as well. + * This condition means that the particular tstamp reg + * is not occupied by other packet. + */ + if (!tstamp->skb) { + found = true; + break; + } + } + + /* Return if no available tstamp regs */ + if (!found) { + adapter->tx_hwtstamp_skipped++; + spin_unlock_irqrestore(&adapter->ptp_tx_lock, + lock_flags); + return; + } + + tstamp->start = jiffies; + tstamp->xsk_queue_index = tx_ring->queue_index; + tstamp->xsk_tx_buffer = meta_req->tx_buffer; + tstamp->buffer_type = IGC_TX_BUFFER_TYPE_XSK; + + /* Hold the transmit completion until timestamp is ready */ + meta_req->tx_buffer->xsk_pending_ts = true; + + /* Keep the pointer to tx_timestamp, which is located in XDP + * metadata area. It is the location to store the value of + * tx hardware timestamp. + */ + xsk_tx_metadata_to_compl(meta_req->meta, &tstamp->xsk_meta); + + /* Set timestamp bit based on the _TSTAMP(_X) bit. */ + tx_flags |= tstamp->flags; + meta_req->cmd_type |= IGC_SET_FLAG(tx_flags, + IGC_TX_FLAGS_TSTAMP, + (IGC_ADVTXD_MAC_TSTAMP)); + meta_req->cmd_type |= IGC_SET_FLAG(tx_flags, + IGC_TX_FLAGS_TSTAMP_1, + (IGC_ADVTXD_TSTAMP_REG_1)); + meta_req->cmd_type |= IGC_SET_FLAG(tx_flags, + IGC_TX_FLAGS_TSTAMP_2, + (IGC_ADVTXD_TSTAMP_REG_2)); + meta_req->cmd_type |= IGC_SET_FLAG(tx_flags, + IGC_TX_FLAGS_TSTAMP_3, + (IGC_ADVTXD_TSTAMP_REG_3)); + + spin_unlock_irqrestore(&adapter->ptp_tx_lock, lock_flags); + } +} + +static u64 igc_xsk_fill_timestamp(void *_priv) +{ + return *(u64 *)_priv; +} + +static void igc_xsk_request_launch_time(u64 launch_time, void *_priv) +{ + struct igc_metadata_request *meta_req = _priv; + struct igc_ring *tx_ring = meta_req->tx_ring; + __le32 launch_time_offset; + bool insert_empty = false; + bool first_flag = false; + u16 used_desc = 0; + + if (!tx_ring->launchtime_enable) + return; + + launch_time_offset = igc_tx_launchtime(tx_ring, + ns_to_ktime(launch_time), + &first_flag, &insert_empty); + if (insert_empty) { + /* Disregard the launch time request if the required empty frame + * fails to be inserted. + */ + if (igc_insert_empty_frame(tx_ring)) + return; + + meta_req->tx_buffer = + &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + /* Inserting an empty packet requires two descriptors: + * one data descriptor and one context descriptor. + */ + used_desc += 2; + } + + /* Use one context descriptor to specify launch time and first flag. */ + igc_tx_ctxtdesc(tx_ring, launch_time_offset, first_flag, 0, 0, 0); + used_desc += 1; + + /* Update the number of used descriptors in this request */ + meta_req->used_desc += used_desc; +} + +const struct xsk_tx_metadata_ops igc_xsk_tx_metadata_ops = { + .tmo_request_timestamp = igc_xsk_request_timestamp, + .tmo_fill_timestamp = igc_xsk_fill_timestamp, + .tmo_request_launch_time = igc_xsk_request_launch_time, +}; + static void igc_xdp_xmit_zc(struct igc_ring *ring) { struct xsk_buff_pool *pool = ring->xsk_pool; @@ -2894,25 +3043,51 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) ntu = ring->next_to_use; budget = igc_desc_unused(ring); - while (xsk_tx_peek_desc(pool, &xdp_desc) && budget--) { - u32 cmd_type, olinfo_status; + /* Packets with launch time require one data descriptor and one context + * descriptor. When the launch time falls into the next Qbv cycle, we + * may need to insert an empty packet, which requires two more + * descriptors. Therefore, to be safe, we always ensure we have at least + * 4 descriptors available. + */ + while (budget >= 4 && xsk_tx_peek_desc(pool, &xdp_desc)) { + struct igc_metadata_request meta_req; + struct xsk_tx_metadata *meta = NULL; struct igc_tx_buffer *bi; + u32 olinfo_status; dma_addr_t dma; - cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT | - IGC_ADVTXD_DCMD_IFCS | IGC_TXD_DCMD | - xdp_desc.len; + meta_req.cmd_type = IGC_ADVTXD_DTYP_DATA | + IGC_ADVTXD_DCMD_DEXT | + IGC_ADVTXD_DCMD_IFCS | + IGC_TXD_DCMD | xdp_desc.len; olinfo_status = xdp_desc.len << IGC_ADVTXD_PAYLEN_SHIFT; dma = xsk_buff_raw_get_dma(pool, xdp_desc.addr); + meta = xsk_buff_get_metadata(pool, xdp_desc.addr); xsk_buff_raw_dma_sync_for_device(pool, dma, xdp_desc.len); + bi = &ring->tx_buffer_info[ntu]; + + meta_req.tx_ring = ring; + meta_req.tx_buffer = bi; + meta_req.meta = meta; + meta_req.used_desc = 0; + xsk_tx_metadata_request(meta, &igc_xsk_tx_metadata_ops, + &meta_req); + + /* xsk_tx_metadata_request() may have updated next_to_use */ + ntu = ring->next_to_use; + + /* xsk_tx_metadata_request() may have updated Tx buffer info */ + bi = meta_req.tx_buffer; + + /* xsk_tx_metadata_request() may use a few descriptors */ + budget -= meta_req.used_desc; tx_desc = IGC_TX_DESC(ring, ntu); - tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); + tx_desc->read.cmd_type_len = cpu_to_le32(meta_req.cmd_type); tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); tx_desc->read.buffer_addr = cpu_to_le64(dma); - bi = &ring->tx_buffer_info[ntu]; bi->type = IGC_TX_BUFFER_TYPE_XSK; bi->protocol = 0; bi->bytecount = xdp_desc.len; @@ -2925,9 +3100,11 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) ntu++; if (ntu == ring->count) ntu = 0; + + ring->next_to_use = ntu; + budget--; } - ring->next_to_use = ntu; if (tx_desc) { igc_flush_tx_descriptors(ring); xsk_tx_release(pool); @@ -2975,6 +3152,18 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget) if (!(eop_desc->wb.status & cpu_to_le32(IGC_TXD_STAT_DD))) break; + if (igc_fpe_is_pmac_enabled(adapter) && + igc_fpe_transmitted_smd_v(tx_desc)) + ethtool_mmsv_event_handle(&adapter->fpe.mmsv, + ETHTOOL_MMSV_LD_SENT_VERIFY_MPACKET); + + /* Hold the completions while there's a pending tx hardware + * timestamp request from XDP Tx metadata. + */ + if (tx_buffer->type == IGC_TX_BUFFER_TYPE_XSK && + tx_buffer->xsk_pending_ts) + break; + /* clear next_to_watch to prevent false hangs */ tx_buffer->next_to_watch = NULL; @@ -3860,6 +4049,30 @@ static int igc_uc_unsync(struct net_device *netdev, const unsigned char *addr) } /** + * igc_enable_empty_addr_recv - Enable Rx of packets with all-zeroes MAC address + * @adapter: Pointer to the igc_adapter structure. + * + * Frame preemption verification requires that packets with the all-zeroes + * MAC address are allowed to be received by the driver. This function adds the + * all-zeroes destination address to the list of acceptable addresses. + * + * Return: 0 on success, negative value otherwise. + */ +int igc_enable_empty_addr_recv(struct igc_adapter *adapter) +{ + u8 empty[ETH_ALEN] = {}; + + return igc_add_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST, empty, -1); +} + +void igc_disable_empty_addr_recv(struct igc_adapter *adapter) +{ + u8 empty[ETH_ALEN] = {}; + + igc_del_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST, empty); +} + +/** * igc_set_rx_mode - Secondary Unicast, Multicast and Promiscuous mode set * @netdev: network interface device structure * @@ -4845,6 +5058,22 @@ static int igc_sw_init(struct igc_adapter *adapter) return 0; } +static void igc_set_queue_napi(struct igc_adapter *adapter, int vector, + struct napi_struct *napi) +{ + struct igc_q_vector *q_vector = adapter->q_vector[vector]; + + if (q_vector->rx.ring) + netif_queue_set_napi(adapter->netdev, + q_vector->rx.ring->queue_index, + NETDEV_QUEUE_TYPE_RX, napi); + + if (q_vector->tx.ring) + netif_queue_set_napi(adapter->netdev, + q_vector->tx.ring->queue_index, + NETDEV_QUEUE_TYPE_TX, napi); +} + /** * igc_up - Open the interface and prepare it to handle traffic * @adapter: board private structure @@ -4852,6 +5081,7 @@ static int igc_sw_init(struct igc_adapter *adapter) void igc_up(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; + struct napi_struct *napi; int i = 0; /* hardware has been reset, we need to reload some things */ @@ -4859,8 +5089,11 @@ void igc_up(struct igc_adapter *adapter) clear_bit(__IGC_DOWN, &adapter->state); - for (i = 0; i < adapter->num_q_vectors; i++) - napi_enable(&adapter->q_vector[i]->napi); + for (i = 0; i < adapter->num_q_vectors; i++) { + napi = &adapter->q_vector[i]->napi; + napi_enable(napi); + igc_set_queue_napi(adapter, i, napi); + } if (adapter->msix_entries) igc_configure_msix(adapter); @@ -5089,12 +5322,13 @@ void igc_down(struct igc_adapter *adapter) for (i = 0; i < adapter->num_q_vectors; i++) { if (adapter->q_vector[i]) { napi_synchronize(&adapter->q_vector[i]->napi); + igc_set_queue_napi(adapter, i, NULL); napi_disable(&adapter->q_vector[i]->napi); } } - del_timer_sync(&adapter->watchdog_timer); - del_timer_sync(&adapter->phy_info_timer); + timer_delete_sync(&adapter->watchdog_timer); + timer_delete_sync(&adapter->phy_info_timer); /* record the stats before reset*/ spin_lock(&adapter->stats64_lock); @@ -5113,6 +5347,9 @@ void igc_down(struct igc_adapter *adapter) igc_disable_all_tx_rings_hw(adapter); igc_clean_all_tx_rings(adapter); igc_clean_all_rx_rings(adapter); + + if (adapter->fpe.mmsv.pmac_enabled) + ethtool_mmsv_stop(&adapter->fpe.mmsv); } void igc_reinit_locked(struct igc_adapter *adapter) @@ -5176,7 +5413,7 @@ static int igc_change_mtu(struct net_device *netdev, int new_mtu) igc_down(adapter); netdev_dbg(netdev, "changing MTU from %d to %d\n", netdev->mtu, new_mtu); - netdev->mtu = new_mtu; + WRITE_ONCE(netdev->mtu, new_mtu); if (netif_running(netdev)) igc_up(adapter); @@ -5473,6 +5710,9 @@ static int igc_request_msix(struct igc_adapter *adapter) q_vector); if (err) goto err_free; + + netif_napi_set_irq(&q_vector->napi, + adapter->msix_entries[vector].vector); } igc_configure_msix(adapter); @@ -5634,6 +5874,10 @@ static void igc_watchdog_task(struct work_struct *work) */ igc_tsn_adjust_txtime_offset(adapter); + if (adapter->fpe.mmsv.pmac_enabled) + ethtool_mmsv_link_state_handle(&adapter->fpe.mmsv, + true); + if (adapter->link_speed != SPEED_1000) goto no_wait; @@ -5669,6 +5913,10 @@ no_wait: netdev_info(netdev, "NIC Link is Down\n"); netif_carrier_off(netdev); + if (adapter->fpe.mmsv.pmac_enabled) + ethtool_mmsv_link_state_handle(&adapter->fpe.mmsv, + false); + /* link state has changed, schedule phy info update */ if (!test_bit(__IGC_DOWN, &adapter->state)) mod_timer(&adapter->phy_info_timer, @@ -5708,11 +5956,29 @@ no_wait: if (adapter->flags & IGC_FLAG_HAS_MSIX) { u32 eics = 0; - for (i = 0; i < adapter->num_q_vectors; i++) - eics |= adapter->q_vector[i]->eims_value; - wr32(IGC_EICS, eics); + for (i = 0; i < adapter->num_q_vectors; i++) { + struct igc_q_vector *q_vector = adapter->q_vector[i]; + struct igc_ring *rx_ring; + + if (!q_vector->rx.ring) + continue; + + rx_ring = adapter->rx_ring[q_vector->rx.ring->queue_index]; + + if (test_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags)) { + eics |= q_vector->eims_value; + clear_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); + } + } + if (eics) + wr32(IGC_EICS, eics); } else { - wr32(IGC_ICS, IGC_ICS_RXDMT0); + struct igc_ring *rx_ring = adapter->rx_ring[0]; + + if (test_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags)) { + clear_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); + wr32(IGC_ICS, IGC_ICS_RXDMT0); + } } igc_ptp_tx_hang(adapter); @@ -5897,6 +6163,7 @@ static int __igc_open(struct net_device *netdev, bool resuming) struct igc_adapter *adapter = netdev_priv(netdev); struct pci_dev *pdev = adapter->pdev; struct igc_hw *hw = &adapter->hw; + struct napi_struct *napi; int err = 0; int i = 0; @@ -5930,19 +6197,13 @@ static int __igc_open(struct net_device *netdev, bool resuming) if (err) goto err_req_irq; - /* Notify the stack of the actual queue counts. */ - err = netif_set_real_num_tx_queues(netdev, adapter->num_tx_queues); - if (err) - goto err_set_queues; - - err = netif_set_real_num_rx_queues(netdev, adapter->num_rx_queues); - if (err) - goto err_set_queues; - clear_bit(__IGC_DOWN, &adapter->state); - for (i = 0; i < adapter->num_q_vectors; i++) - napi_enable(&adapter->q_vector[i]->napi); + for (i = 0; i < adapter->num_q_vectors; i++) { + napi = &adapter->q_vector[i]->napi; + napi_enable(napi); + igc_set_queue_napi(adapter, i, napi); + } /* Clear any pending interrupts. */ rd32(IGC_ICR); @@ -5959,8 +6220,6 @@ static int __igc_open(struct net_device *netdev, bool resuming) return IGC_SUCCESS; -err_set_queues: - igc_free_irq(adapter); err_req_irq: igc_release_hw_control(adapter); igc_power_down_phy_copper_base(&adapter->hw); @@ -5977,6 +6236,17 @@ err_setup_tx: int igc_open(struct net_device *netdev) { + struct igc_adapter *adapter = netdev_priv(netdev); + int err; + + /* Notify the stack of the actual queue counts. */ + err = netif_set_real_num_queues(netdev, adapter->num_tx_queues, + adapter->num_rx_queues); + if (err) { + netdev_err(netdev, "error setting real queue count\n"); + return err; + } + return __igc_open(netdev, false); } @@ -6207,21 +6477,6 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, size_t n; int i; - switch (qopt->cmd) { - case TAPRIO_CMD_REPLACE: - break; - case TAPRIO_CMD_DESTROY: - return igc_tsn_clear_schedule(adapter); - 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; @@ -6231,12 +6486,20 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, if (!validate_schedule(adapter, qopt)) return -EINVAL; + /* preemptible isn't supported yet */ + if (qopt->mqprio.preemptible_tcs) + return -EOPNOTSUPP; + + igc_ptp_read(adapter, &now); + + if (igc_tsn_is_taprio_activated_by_user(adapter) && + is_base_time_past(qopt->base_time, &now)) + adapter->qbv_config_change_errors++; + adapter->cycle_time = qopt->cycle_time; adapter->base_time = qopt->base_time; adapter->taprio_offload_enable = true; - igc_ptp_read(adapter, &now); - for (n = 0; n < qopt->num_entries; n++) { struct tc_taprio_sched_entry *e = &qopt->entries[n]; @@ -6330,7 +6593,23 @@ static int igc_tsn_enable_qbv_scheduling(struct igc_adapter *adapter, if (hw->mac.type != igc_i225) return -EOPNOTSUPP; - err = igc_save_qbv_schedule(adapter, qopt); + switch (qopt->cmd) { + case TAPRIO_CMD_REPLACE: + err = igc_save_qbv_schedule(adapter, qopt); + break; + case TAPRIO_CMD_DESTROY: + err = igc_tsn_clear_schedule(adapter); + break; + 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 (err) return err; @@ -6411,6 +6690,13 @@ static int igc_tc_query_caps(struct igc_adapter *adapter, struct igc_hw *hw = &adapter->hw; switch (base->type) { + case TC_SETUP_QDISC_MQPRIO: { + struct tc_mqprio_caps *caps = base->caps; + + caps->validate_queue_counts = true; + + return 0; + } case TC_SETUP_QDISC_TAPRIO: { struct tc_taprio_caps *caps = base->caps; @@ -6428,6 +6714,81 @@ static int igc_tc_query_caps(struct igc_adapter *adapter, } } +static void igc_save_mqprio_params(struct igc_adapter *adapter, u8 num_tc, + u16 *offset) +{ + int i; + + adapter->strict_priority_enable = true; + adapter->num_tc = num_tc; + + for (i = 0; i < num_tc; i++) + adapter->queue_per_tc[i] = offset[i]; +} + +static int igc_tsn_enable_mqprio(struct igc_adapter *adapter, + struct tc_mqprio_qopt_offload *mqprio) +{ + struct igc_hw *hw = &adapter->hw; + int err, i; + + if (hw->mac.type != igc_i225) + return -EOPNOTSUPP; + + if (!mqprio->qopt.num_tc) { + adapter->strict_priority_enable = false; + netdev_reset_tc(adapter->netdev); + goto apply; + } + + /* There are as many TCs as Tx queues. */ + if (mqprio->qopt.num_tc != adapter->num_tx_queues) { + NL_SET_ERR_MSG_FMT_MOD(mqprio->extack, + "Only %d traffic classes supported", + adapter->num_tx_queues); + return -EOPNOTSUPP; + } + + /* Only one queue per TC is supported. */ + for (i = 0; i < mqprio->qopt.num_tc; i++) { + if (mqprio->qopt.count[i] != 1) { + NL_SET_ERR_MSG_MOD(mqprio->extack, + "Only one queue per TC supported"); + return -EOPNOTSUPP; + } + } + + /* Preemption is not supported yet. */ + if (mqprio->preemptible_tcs) { + NL_SET_ERR_MSG_MOD(mqprio->extack, + "Preemption is not supported yet"); + return -EOPNOTSUPP; + } + + igc_save_mqprio_params(adapter, mqprio->qopt.num_tc, + mqprio->qopt.offset); + + err = netdev_set_num_tc(adapter->netdev, adapter->num_tc); + if (err) + return err; + + for (i = 0; i < adapter->num_tc; i++) { + err = netdev_set_tc_queue(adapter->netdev, i, 1, + adapter->queue_per_tc[i]); + if (err) + return err; + } + + /* In case the card is configured with less than four queues. */ + for (; i < IGC_MAX_TX_QUEUES; i++) + adapter->queue_per_tc[i] = i; + + mqprio->qopt.hw = TC_MQPRIO_HW_OFFLOAD_TCS; + +apply: + return igc_tsn_offload_apply(adapter); +} + static int igc_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { @@ -6447,6 +6808,9 @@ static int igc_setup_tc(struct net_device *dev, enum tc_setup_type type, case TC_SETUP_QDISC_CBS: return igc_tsn_enable_cbs(adapter, type_data); + case TC_SETUP_QDISC_MQPRIO: + return igc_tsn_enable_mqprio(adapter, type_data); + default: return -EOPNOTSUPP; } @@ -6482,7 +6846,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) return -EINVAL; - ring = igc_xdp_get_tx_ring(adapter, cpu); + ring = igc_get_tx_ring(adapter, cpu); nq = txring_txq(ring); __netif_tx_lock(nq, cpu); @@ -6584,45 +6948,6 @@ static const struct net_device_ops igc_netdev_ops = { .ndo_get_tstamp = igc_get_tstamp, }; -/* PCIe configuration access */ -void igc_read_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value) -{ - struct igc_adapter *adapter = hw->back; - - pci_read_config_word(adapter->pdev, reg, value); -} - -void igc_write_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value) -{ - struct igc_adapter *adapter = hw->back; - - pci_write_config_word(adapter->pdev, reg, *value); -} - -s32 igc_read_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value) -{ - struct igc_adapter *adapter = hw->back; - - if (!pci_is_pcie(adapter->pdev)) - return -IGC_ERR_CONFIG; - - pcie_capability_read_word(adapter->pdev, reg, value); - - return IGC_SUCCESS; -} - -s32 igc_write_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value) -{ - struct igc_adapter *adapter = hw->back; - - if (!pci_is_pcie(adapter->pdev)) - return -IGC_ERR_CONFIG; - - pcie_capability_write_word(adapter->pdev, reg, *value); - - return IGC_SUCCESS; -} - u32 igc_rd32(struct igc_hw *hw, u32 reg) { struct igc_adapter *igc = container_of(hw, struct igc_adapter, hw); @@ -6803,6 +7128,7 @@ static int igc_probe(struct pci_dev *pdev, netdev->netdev_ops = &igc_netdev_ops; netdev->xdp_metadata_ops = &igc_xdp_metadata_ops; + netdev->xsk_tx_metadata_ops = &igc_xsk_tx_metadata_ops; igc_ethtool_set_ops(netdev); netdev->watchdog_timeo = 5 * HZ; @@ -6866,6 +7192,9 @@ static int igc_probe(struct pci_dev *pdev, netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_XSK_ZEROCOPY; + /* enable HW vlan tag insertion/stripping by default */ + netdev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; + /* MTU range: 68 - 9216 */ netdev->min_mtu = ETH_MIN_MTU; netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE; @@ -6898,8 +7227,8 @@ static int igc_probe(struct pci_dev *pdev, } /* configure RXPBSIZE and TXPBSIZE */ - wr32(IGC_RXPBS, I225_RXPBSIZE_DEFAULT); - wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT); + wr32(IGC_RXPBS, IGC_RXPBSIZE_EXP_BMC_DEFAULT); + wr32(IGC_TXPBS, IGC_TXPBSIZE_DEFAULT); timer_setup(&adapter->watchdog_timer, igc_watchdog, 0); timer_setup(&adapter->phy_info_timer, igc_update_phy_info, 0); @@ -6907,12 +7236,11 @@ static int igc_probe(struct pci_dev *pdev, INIT_WORK(&adapter->reset_task, igc_reset_task); INIT_WORK(&adapter->watchdog_task, igc_watchdog_task); - hrtimer_init(&adapter->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - adapter->hrtimer.function = &igc_qbv_scheduling_timer; + hrtimer_setup(&adapter->hrtimer, &igc_qbv_scheduling_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL); /* Initialize link properties that are user-changeable */ adapter->fc_autoneg = true; - hw->mac.autoneg = true; hw->phy.autoneg_advertised = 0xaf; hw->fc.requested_mode = igc_fc_default; @@ -6932,6 +7260,8 @@ static int igc_probe(struct pci_dev *pdev, igc_tsn_clear_schedule(adapter); + igc_fpe_init(adapter); + /* reset the hardware with the new settings */ igc_reset(adapter); @@ -6973,6 +7303,7 @@ static int igc_probe(struct pci_dev *pdev, err_register: igc_release_hw_control(adapter); + igc_ptp_stop(adapter); err_eeprom: if (!igc_check_reset_block(hw)) igc_reset_phy(hw); @@ -7014,8 +7345,8 @@ static void igc_remove(struct pci_dev *pdev) set_bit(__IGC_DOWN, &adapter->state); - del_timer_sync(&adapter->watchdog_timer); - del_timer_sync(&adapter->phy_info_timer); + timer_delete_sync(&adapter->watchdog_timer); + timer_delete_sync(&adapter->phy_info_timer); cancel_work_sync(&adapter->reset_task); cancel_work_sync(&adapter->watchdog_task); @@ -7108,8 +7439,7 @@ static int __igc_shutdown(struct pci_dev *pdev, bool *enable_wake, return 0; } -#ifdef CONFIG_PM -static int __maybe_unused igc_runtime_suspend(struct device *dev) +static int igc_runtime_suspend(struct device *dev) { return __igc_shutdown(to_pci_dev(dev), NULL, 1); } @@ -7144,7 +7474,7 @@ static void igc_deliver_wake_packet(struct net_device *netdev) netif_rx(skb); } -static int __maybe_unused igc_resume(struct device *dev) +static int __igc_resume(struct device *dev, bool rpm) { struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); @@ -7186,23 +7516,30 @@ static int __maybe_unused igc_resume(struct device *dev) wr32(IGC_WUS, ~0); - rtnl_lock(); - if (!err && netif_running(netdev)) + if (netif_running(netdev)) { + if (!rpm) + rtnl_lock(); err = __igc_open(netdev, true); - - if (!err) - netif_device_attach(netdev); - rtnl_unlock(); + if (!rpm) + rtnl_unlock(); + if (!err) + netif_device_attach(netdev); + } return err; } -static int __maybe_unused igc_runtime_resume(struct device *dev) +static int igc_resume(struct device *dev) { - return igc_resume(dev); + return __igc_resume(dev, false); } -static int __maybe_unused igc_suspend(struct device *dev) +static int igc_runtime_resume(struct device *dev) +{ + return __igc_resume(dev, true); +} + +static int igc_suspend(struct device *dev) { return __igc_shutdown(to_pci_dev(dev), NULL, 0); } @@ -7217,7 +7554,6 @@ static int __maybe_unused igc_runtime_idle(struct device *dev) return -EBUSY; } -#endif /* CONFIG_PM */ static void igc_shutdown(struct pci_dev *pdev) { @@ -7245,14 +7581,18 @@ static pci_ers_result_t igc_io_error_detected(struct pci_dev *pdev, struct net_device *netdev = pci_get_drvdata(pdev); struct igc_adapter *adapter = netdev_priv(netdev); + rtnl_lock(); netif_device_detach(netdev); - if (state == pci_channel_io_perm_failure) + if (state == pci_channel_io_perm_failure) { + rtnl_unlock(); return PCI_ERS_RESULT_DISCONNECT; + } if (netif_running(netdev)) igc_down(adapter); pci_disable_device(pdev); + rtnl_unlock(); /* Request a slot reset. */ return PCI_ERS_RESULT_NEED_RESET; @@ -7263,7 +7603,7 @@ static pci_ers_result_t igc_io_error_detected(struct pci_dev *pdev, * @pdev: Pointer to PCI device * * Restart the card from scratch, as if from a cold-boot. Implementation - * resembles the first-half of the igc_resume routine. + * resembles the first-half of the __igc_resume routine. **/ static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev) { @@ -7302,7 +7642,7 @@ static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev) * * This callback is called when the error recovery driver tells us that * its OK to resume normal operation. Implementation resembles the - * second-half of the igc_resume routine. + * second-half of the __igc_resume routine. */ static void igc_io_resume(struct pci_dev *pdev) { @@ -7312,6 +7652,7 @@ static void igc_io_resume(struct pci_dev *pdev) rtnl_lock(); if (netif_running(netdev)) { if (igc_open(netdev)) { + rtnl_unlock(); netdev_err(netdev, "igc_open failed after reset\n"); return; } @@ -7332,22 +7673,16 @@ static const struct pci_error_handlers igc_err_handler = { .resume = igc_io_resume, }; -#ifdef CONFIG_PM -static const struct dev_pm_ops igc_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(igc_suspend, igc_resume) - SET_RUNTIME_PM_OPS(igc_runtime_suspend, igc_runtime_resume, - igc_runtime_idle) -}; -#endif +static _DEFINE_DEV_PM_OPS(igc_pm_ops, igc_suspend, igc_resume, + igc_runtime_suspend, igc_runtime_resume, + igc_runtime_idle); static struct pci_driver igc_driver = { .name = igc_driver_name, .id_table = igc_pci_tbl, .probe = igc_probe, .remove = igc_remove, -#ifdef CONFIG_PM - .driver.pm = &igc_pm_ops, -#endif + .driver.pm = pm_ptr(&igc_pm_ops), .shutdown = igc_shutdown, .err_handler = &igc_err_handler, }; diff --git a/drivers/net/ethernet/intel/igc/igc_nvm.c b/drivers/net/ethernet/intel/igc/igc_nvm.c index 58f81aba0144..efd121c03967 100644 --- a/drivers/net/ethernet/intel/igc/igc_nvm.c +++ b/drivers/net/ethernet/intel/igc/igc_nvm.c @@ -36,56 +36,6 @@ static s32 igc_poll_eerd_eewr_done(struct igc_hw *hw, int ee_reg) } /** - * igc_acquire_nvm - Generic request for access to EEPROM - * @hw: pointer to the HW structure - * - * Set the EEPROM access request bit and wait for EEPROM access grant bit. - * Return successful if access grant bit set, else clear the request for - * EEPROM access and return -IGC_ERR_NVM (-1). - */ -s32 igc_acquire_nvm(struct igc_hw *hw) -{ - s32 timeout = IGC_NVM_GRANT_ATTEMPTS; - u32 eecd = rd32(IGC_EECD); - s32 ret_val = 0; - - wr32(IGC_EECD, eecd | IGC_EECD_REQ); - eecd = rd32(IGC_EECD); - - while (timeout) { - if (eecd & IGC_EECD_GNT) - break; - udelay(5); - eecd = rd32(IGC_EECD); - timeout--; - } - - if (!timeout) { - eecd &= ~IGC_EECD_REQ; - wr32(IGC_EECD, eecd); - hw_dbg("Could not acquire NVM grant\n"); - ret_val = -IGC_ERR_NVM; - } - - return ret_val; -} - -/** - * igc_release_nvm - Release exclusive access to EEPROM - * @hw: pointer to the HW structure - * - * Stop any current commands to the EEPROM and clear the EEPROM request bit. - */ -void igc_release_nvm(struct igc_hw *hw) -{ - u32 eecd; - - eecd = rd32(IGC_EECD); - eecd &= ~IGC_EECD_REQ; - wr32(IGC_EECD, eecd); -} - -/** * igc_read_nvm_eerd - Reads EEPROM using EERD register * @hw: pointer to the HW structure * @offset: offset of word in the EEPROM to read diff --git a/drivers/net/ethernet/intel/igc/igc_nvm.h b/drivers/net/ethernet/intel/igc/igc_nvm.h index f9fc2e9cfb03..ab78d0c64547 100644 --- a/drivers/net/ethernet/intel/igc/igc_nvm.h +++ b/drivers/net/ethernet/intel/igc/igc_nvm.h @@ -4,8 +4,6 @@ #ifndef _IGC_NVM_H_ #define _IGC_NVM_H_ -s32 igc_acquire_nvm(struct igc_hw *hw); -void igc_release_nvm(struct igc_hw *hw); s32 igc_read_mac_addr(struct igc_hw *hw); s32 igc_read_nvm_eerd(struct igc_hw *hw, u16 offset, u16 words, u16 *data); s32 igc_validate_nvm_checksum(struct igc_hw *hw); diff --git a/drivers/net/ethernet/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c index 861f37076861..6c4d204aecfa 100644 --- a/drivers/net/ethernet/intel/igc/igc_phy.c +++ b/drivers/net/ethernet/intel/igc/igc_phy.c @@ -240,7 +240,7 @@ static s32 igc_phy_setup_autoneg(struct igc_hw *hw) /* Read the MULTI GBT AN Control Register - reg 7.32 */ ret_val = phy->ops.read_reg(hw, (STANDARD_AN_REG_MASK << MMD_DEVADDR_SHIFT) | - ANEG_MULTIGBT_AN_CTRL, + IGC_ANEG_MULTIGBT_AN_CTRL, &aneg_multigbt_an_ctrl); if (ret_val) @@ -380,7 +380,7 @@ static s32 igc_phy_setup_autoneg(struct igc_hw *hw) ret_val = phy->ops.write_reg(hw, (STANDARD_AN_REG_MASK << MMD_DEVADDR_SHIFT) | - ANEG_MULTIGBT_AN_CTRL, + IGC_ANEG_MULTIGBT_AN_CTRL, aneg_multigbt_an_ctrl); return ret_val; @@ -494,24 +494,12 @@ s32 igc_setup_copper_link(struct igc_hw *hw) s32 ret_val = 0; bool link; - if (hw->mac.autoneg) { - /* Setup autoneg and flow control advertisement and perform - * autonegotiation. - */ - ret_val = igc_copper_link_autoneg(hw); - if (ret_val) - goto out; - } else { - /* PHY will be set to 10H, 10F, 100H or 100F - * depending on user settings. - */ - hw_dbg("Forcing Speed and Duplex\n"); - ret_val = hw->phy.ops.force_speed_duplex(hw); - if (ret_val) { - hw_dbg("Error Forcing Speed and Duplex\n"); - goto out; - } - } + /* Setup autoneg and flow control advertisement and perform + * autonegotiation. + */ + ret_val = igc_copper_link_autoneg(hw); + if (ret_val) + goto out; /* Check link status. Wait up to 100 microseconds for link to become * valid. diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 885faaa7b9de..f4f5c28615d3 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -11,6 +11,7 @@ #include <linux/ktime.h> #include <linux/delay.h> #include <linux/iopoll.h> +#include <net/xdp_sock_drv.h> #define INCVALUE_MASK 0x7fffffff #define ISGN 0x80000000 @@ -256,13 +257,6 @@ static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp, switch (rq->type) { case PTP_CLK_REQ_EXTTS: - /* Reject requests with unsupported flags */ - if (rq->extts.flags & ~(PTP_ENABLE_FEATURE | - PTP_RISING_EDGE | - PTP_FALLING_EDGE | - PTP_STRICT_FLAGS)) - return -EOPNOTSUPP; - /* Reject requests failing to enable both edges. */ if ((rq->extts.flags & PTP_STRICT_FLAGS) && (rq->extts.flags & PTP_ENABLE_FEATURE) && @@ -299,10 +293,6 @@ static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp, return 0; case PTP_CLK_REQ_PEROUT: - /* Reject requests with unsupported flags */ - if (rq->perout.flags) - return -EOPNOTSUPP; - if (on) { pin = ptp_find_pin(igc->ptp_clock, PTP_PF_PEROUT, rq->perout.index); @@ -545,6 +535,30 @@ static void igc_ptp_enable_rx_timestamp(struct igc_adapter *adapter) wr32(IGC_TSYNCRXCTL, val); } +static void igc_ptp_free_tx_buffer(struct igc_adapter *adapter, + struct igc_tx_timestamp_request *tstamp) +{ + if (tstamp->buffer_type == IGC_TX_BUFFER_TYPE_XSK) { + /* Release the transmit completion */ + tstamp->xsk_tx_buffer->xsk_pending_ts = false; + + /* Note: tstamp->skb and tstamp->xsk_tx_buffer are in union. + * By setting tstamp->xsk_tx_buffer to NULL, tstamp->skb will + * become NULL as well. + */ + tstamp->xsk_tx_buffer = NULL; + tstamp->buffer_type = 0; + + /* Trigger txrx interrupt for transmit completion */ + igc_xsk_wakeup(adapter->netdev, tstamp->xsk_queue_index, 0); + + return; + } + + dev_kfree_skb_any(tstamp->skb); + tstamp->skb = NULL; +} + static void igc_ptp_clear_tx_tstamp(struct igc_adapter *adapter) { unsigned long flags; @@ -555,8 +569,8 @@ static void igc_ptp_clear_tx_tstamp(struct igc_adapter *adapter) 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; + if (tstamp->skb) + igc_ptp_free_tx_buffer(adapter, tstamp); } spin_unlock_irqrestore(&adapter->ptp_tx_lock, flags); @@ -657,8 +671,9 @@ static int igc_ptp_set_timestamp_mode(struct igc_adapter *adapter, static void igc_ptp_tx_timeout(struct igc_adapter *adapter, struct igc_tx_timestamp_request *tstamp) { - dev_kfree_skb_any(tstamp->skb); - tstamp->skb = NULL; + if (tstamp->skb) + igc_ptp_free_tx_buffer(adapter, tstamp); + adapter->tx_hwtstamp_timeouts++; netdev_warn(adapter->netdev, "Tx timestamp timeout\n"); @@ -729,10 +744,21 @@ static void igc_ptp_tx_reg_to_stamp(struct igc_adapter *adapter, shhwtstamps.hwtstamp = ktime_add_ns(shhwtstamps.hwtstamp, adjust); - tstamp->skb = NULL; + /* Copy the tx hardware timestamp into xdp metadata or skb */ + if (tstamp->buffer_type == IGC_TX_BUFFER_TYPE_XSK) { + struct xsk_buff_pool *xsk_pool; + + xsk_pool = adapter->tx_ring[tstamp->xsk_queue_index]->xsk_pool; + if (xsk_pool && xp_tx_metadata_enabled(xsk_pool)) { + xsk_tx_metadata_complete(&tstamp->xsk_meta, + &igc_xsk_tx_metadata_ops, + &shhwtstamps.hwtstamp); + } + } else { + skb_tstamp_tx(skb, &shhwtstamps); + } - skb_tstamp_tx(skb, &shhwtstamps); - dev_kfree_skb_any(skb); + igc_ptp_free_tx_buffer(adapter, tstamp); } /** @@ -901,7 +927,11 @@ static bool igc_is_crosststamp_supported(struct igc_adapter *adapter) static struct system_counterval_t igc_device_tstamp_to_system(u64 tstamp) { #if IS_ENABLED(CONFIG_X86_TSC) && !defined(CONFIG_UML) - return convert_art_ns_to_tsc(tstamp); + return (struct system_counterval_t) { + .cs_id = CSID_X86_ART, + .cycles = tstamp, + .use_nsecs = true, + }; #else return (struct system_counterval_t) { }; #endif @@ -933,45 +963,62 @@ static void igc_ptm_log_error(struct igc_adapter *adapter, u32 ptm_stat) } } +/* The PTM lock: adapter->ptm_lock must be held when calling igc_ptm_trigger() */ +static void igc_ptm_trigger(struct igc_hw *hw) +{ + u32 ctrl; + + /* To "manually" start the PTM cycle we need to set the + * trigger (TRIG) bit + */ + ctrl = rd32(IGC_PTM_CTRL); + ctrl |= IGC_PTM_CTRL_TRIG; + wr32(IGC_PTM_CTRL, ctrl); + /* Perform flush after write to CTRL register otherwise + * transaction may not start + */ + wrfl(); +} + +/* The PTM lock: adapter->ptm_lock must be held when calling igc_ptm_reset() */ +static void igc_ptm_reset(struct igc_hw *hw) +{ + u32 ctrl; + + ctrl = rd32(IGC_PTM_CTRL); + ctrl &= ~IGC_PTM_CTRL_TRIG; + wr32(IGC_PTM_CTRL, ctrl); + /* Write to clear all status */ + wr32(IGC_PTM_STAT, IGC_PTM_STAT_ALL); +} + static int igc_phc_get_syncdevicetime(ktime_t *device, struct system_counterval_t *system, void *ctx) { - u32 stat, t2_curr_h, t2_curr_l, ctrl; struct igc_adapter *adapter = ctx; struct igc_hw *hw = &adapter->hw; + u32 stat, t2_curr_h, t2_curr_l; int err, count = 100; ktime_t t1, t2_curr; - /* Get a snapshot of system clocks to use as historic value. */ - ktime_get_snapshot(&adapter->snapshot); - + /* Doing this in a loop because in the event of a + * badly timed (ha!) system clock adjustment, we may + * get PTM errors from the PCI root, but these errors + * are transitory. Repeating the process returns valid + * data eventually. + */ do { - /* Doing this in a loop because in the event of a - * badly timed (ha!) system clock adjustment, we may - * get PTM errors from the PCI root, but these errors - * are transitory. Repeating the process returns valid - * data eventually. - */ - - /* To "manually" start the PTM cycle we need to clear and - * then set again the TRIG bit. - */ - ctrl = rd32(IGC_PTM_CTRL); - ctrl &= ~IGC_PTM_CTRL_TRIG; - wr32(IGC_PTM_CTRL, ctrl); - ctrl |= IGC_PTM_CTRL_TRIG; - wr32(IGC_PTM_CTRL, ctrl); + /* Get a snapshot of system clocks to use as historic value. */ + ktime_get_snapshot(&adapter->snapshot); - /* The cycle only starts "for real" when software notifies - * that it has read the registers, this is done by setting - * VALID bit. - */ - wr32(IGC_PTM_STAT, IGC_PTM_STAT_VALID); + igc_ptm_trigger(hw); err = readx_poll_timeout(rd32, IGC_PTM_STAT, stat, stat, IGC_PTM_STAT_SLEEP, IGC_PTM_STAT_TIMEOUT); + igc_ptm_reset(hw); + if (err < 0) { netdev_err(adapter->netdev, "Timeout reading IGC_PTM_STAT register\n"); return err; @@ -980,15 +1027,7 @@ static int igc_phc_get_syncdevicetime(ktime_t *device, if ((stat & IGC_PTM_STAT_VALID) == IGC_PTM_STAT_VALID) break; - if (stat & ~IGC_PTM_STAT_VALID) { - /* An error occurred, log it. */ - igc_ptm_log_error(adapter, stat); - /* The STAT register is write-1-to-clear (W1C), - * so write the previous error status to clear it. - */ - wr32(IGC_PTM_STAT, stat); - continue; - } + igc_ptm_log_error(adapter, stat); } while (--count); if (!count) { @@ -1020,9 +1059,16 @@ static int igc_ptp_getcrosststamp(struct ptp_clock_info *ptp, { struct igc_adapter *adapter = container_of(ptp, struct igc_adapter, ptp_caps); + int ret; - return get_device_system_crosststamp(igc_phc_get_syncdevicetime, - adapter, &adapter->snapshot, cts); + /* This blocks until any in progress PTM transactions complete */ + mutex_lock(&adapter->ptm_lock); + + ret = get_device_system_crosststamp(igc_phc_get_syncdevicetime, + adapter, &adapter->snapshot, cts); + mutex_unlock(&adapter->ptm_lock); + + return ret; } static int igc_ptp_getcyclesx64(struct ptp_clock_info *ptp, @@ -1105,6 +1151,9 @@ void igc_ptp_init(struct igc_adapter *adapter) adapter->ptp_caps.pin_config = adapter->sdp_config; adapter->ptp_caps.n_ext_ts = IGC_N_EXTTS; adapter->ptp_caps.n_per_out = IGC_N_PEROUT; + adapter->ptp_caps.supported_extts_flags = PTP_RISING_EDGE | + PTP_FALLING_EDGE | + PTP_STRICT_FLAGS; adapter->ptp_caps.n_pins = IGC_N_SDP; adapter->ptp_caps.verify = igc_ptp_verify_pin; @@ -1121,6 +1170,7 @@ void igc_ptp_init(struct igc_adapter *adapter) spin_lock_init(&adapter->ptp_tx_lock); spin_lock_init(&adapter->free_timer_lock); spin_lock_init(&adapter->tmreg_lock); + mutex_init(&adapter->ptm_lock); adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF; @@ -1133,6 +1183,7 @@ void igc_ptp_init(struct igc_adapter *adapter) if (IS_ERR(adapter->ptp_clock)) { adapter->ptp_clock = NULL; netdev_err(netdev, "ptp_clock_register failed\n"); + mutex_destroy(&adapter->ptm_lock); } else if (adapter->ptp_clock) { netdev_info(netdev, "PHC added\n"); adapter->ptp_flags |= IGC_PTP_ENABLED; @@ -1162,10 +1213,12 @@ static void igc_ptm_stop(struct igc_adapter *adapter) struct igc_hw *hw = &adapter->hw; u32 ctrl; + mutex_lock(&adapter->ptm_lock); ctrl = rd32(IGC_PTM_CTRL); ctrl &= ~IGC_PTM_CTRL_EN; wr32(IGC_PTM_CTRL, ctrl); + mutex_unlock(&adapter->ptm_lock); } /** @@ -1196,13 +1249,18 @@ void igc_ptp_suspend(struct igc_adapter *adapter) **/ void igc_ptp_stop(struct igc_adapter *adapter) { + if (!(adapter->ptp_flags & IGC_PTP_ENABLED)) + return; + igc_ptp_suspend(adapter); + adapter->ptp_flags &= ~IGC_PTP_ENABLED; if (adapter->ptp_clock) { ptp_clock_unregister(adapter->ptp_clock); netdev_info(adapter->netdev, "PHC removed\n"); adapter->ptp_flags &= ~IGC_PTP_ENABLED; } + mutex_destroy(&adapter->ptm_lock); } /** @@ -1214,13 +1272,18 @@ void igc_ptp_stop(struct igc_adapter *adapter) void igc_ptp_reset(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; - u32 cycle_ctrl, ctrl; + u32 cycle_ctrl, ctrl, stat; unsigned long flags; u32 timadj; + if (!(adapter->ptp_flags & IGC_PTP_ENABLED)) + return; + /* reset the tstamp_config */ igc_ptp_set_timestamp_mode(adapter, &adapter->tstamp_config); + mutex_lock(&adapter->ptm_lock); + spin_lock_irqsave(&adapter->tmreg_lock, flags); switch (adapter->hw.mac.type) { @@ -1249,14 +1312,19 @@ void igc_ptp_reset(struct igc_adapter *adapter) ctrl = IGC_PTM_CTRL_EN | IGC_PTM_CTRL_START_NOW | IGC_PTM_CTRL_SHRT_CYC(IGC_PTM_SHORT_CYC_DEFAULT) | - IGC_PTM_CTRL_PTM_TO(IGC_PTM_TIMEOUT_DEFAULT) | - IGC_PTM_CTRL_TRIG; + IGC_PTM_CTRL_PTM_TO(IGC_PTM_TIMEOUT_DEFAULT); wr32(IGC_PTM_CTRL, ctrl); /* Force the first cycle to run. */ - wr32(IGC_PTM_STAT, IGC_PTM_STAT_VALID); + igc_ptm_trigger(hw); + + if (readx_poll_timeout_atomic(rd32, IGC_PTM_STAT, stat, + stat, IGC_PTM_STAT_SLEEP, + IGC_PTM_STAT_TIMEOUT)) + netdev_err(adapter->netdev, "Timeout reading IGC_PTM_STAT register\n"); + igc_ptm_reset(hw); break; default: /* No work to do. */ @@ -1273,5 +1341,7 @@ void igc_ptp_reset(struct igc_adapter *adapter) out: spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + mutex_unlock(&adapter->ptm_lock); + wrfl(); } diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h index e5b893fc5b66..f343c6bfc6be 100644 --- a/drivers/net/ethernet/intel/igc/igc_regs.h +++ b/drivers/net/ethernet/intel/igc/igc_regs.h @@ -222,6 +222,22 @@ #define IGC_FTQF(_n) (0x059E0 + (4 * (_n))) /* 5-tuple Queue Fltr */ +/* Time sync registers - preemption statistics */ +#define IGC_PRMPTDRCNT 0x04284 /* Good RX Preempted Packets */ +#define IGC_PRMEVNTTCNT 0x04298 /* TX Preemption event counter */ +#define IGC_PRMEVNTRCNT 0x0429C /* RX Preemption event counter */ + + /* Preemption Exception Counter */ + #define IGC_PRMEXCPRCNT 0x42A0 +/* Received out of order packets with SMD-C */ +#define IGC_PRMEXCPRCNT_OOO_SMDC 0x000000FF +/* Received out of order packets with SMD-C and wrong Frame CNT */ +#define IGC_PRMEXCPRCNT_OOO_FRAME_CNT 0x0000FF00 +/* Received out of order packets with SMD-C and wrong Frag CNT */ +#define IGC_PRMEXCPRCNT_OOO_FRAG_CNT 0x00FF0000 +/* Received packets with SMD-S and wrong Frag CNT and Frame CNT */ +#define IGC_PRMEXCPRCNT_MISS_FRAME_FRAG_CNT 0xFF000000 + /* Transmit Scheduling Registers */ #define IGC_TQAVCTRL 0x3570 #define IGC_TXQCTL(_n) (0x3344 + 0x4 * (_n)) @@ -238,6 +254,8 @@ #define IGC_TQAVCC(_n) (0x3004 + ((_n) * 0x40)) #define IGC_TQAVHC(_n) (0x300C + ((_n) * 0x40)) +#define IGC_TXARB 0x3354 /* Tx Arbitration Control TxARB - RW */ + /* System Time Registers */ #define IGC_SYSTIML 0x0B600 /* System time register Low - RO */ #define IGC_SYSTIMH 0x0B604 /* System time register High - RO */ @@ -308,6 +326,16 @@ #define IGC_IPCNFG 0x0E38 /* Internal PHY Configuration */ #define IGC_EEE_SU 0x0E34 /* EEE Setup */ +/* MULTI GBT AN Control Register - reg. 7.32 */ +#define IGC_ANEG_MULTIGBT_AN_CTRL 0x0020 + +/* EEE ANeg Advertisement Register - reg 7.60 and reg 7.62 */ +#define IGC_ANEG_EEE_AB1 0x003c +#define IGC_ANEG_EEE_AB2 0x003e +/* EEE ANeg Link-Partner Advertisement Register - reg 7.61 and reg 7.63 */ +#define IGC_ANEG_EEE_LP_AB1 0x003d +#define IGC_ANEG_EEE_LP_AB2 0x003f + /* LTR registers */ #define IGC_LTRC 0x01A0 /* Latency Tolerance Reporting Control */ #define IGC_LTRMINV 0x5BB0 /* LTR Minimum Value */ diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index 22cefb1eeedf..f22cc4d4f459 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -2,9 +2,143 @@ /* Copyright (c) 2019 Intel Corporation */ #include "igc.h" +#include "igc_base.h" #include "igc_hw.h" #include "igc_tsn.h" +#define MIN_MULTPLIER_TX_MIN_FRAG 0 +#define MAX_MULTPLIER_TX_MIN_FRAG 3 +/* Frag size is based on the Section 8.12.2 of the SW User Manual */ +#define TX_MIN_FRAG_SIZE 64 +#define TX_MAX_FRAG_SIZE (TX_MIN_FRAG_SIZE * \ + (MAX_MULTPLIER_TX_MIN_FRAG + 1)) + +DEFINE_STATIC_KEY_FALSE(igc_fpe_enabled); + +static int igc_fpe_init_smd_frame(struct igc_ring *ring, + struct igc_tx_buffer *buffer, + struct sk_buff *skb) +{ + dma_addr_t dma = dma_map_single(ring->dev, skb->data, skb->len, + DMA_TO_DEVICE); + + if (dma_mapping_error(ring->dev, dma)) { + netdev_err_once(ring->netdev, "Failed to map DMA for TX\n"); + return -ENOMEM; + } + + buffer->skb = skb; + buffer->protocol = 0; + buffer->bytecount = skb->len; + buffer->gso_segs = 1; + buffer->time_stamp = jiffies; + dma_unmap_len_set(buffer, len, skb->len); + dma_unmap_addr_set(buffer, dma, dma); + + return 0; +} + +static int igc_fpe_init_tx_descriptor(struct igc_ring *ring, + struct sk_buff *skb, + enum igc_txd_popts_type type) +{ + u32 cmd_type, olinfo_status = 0; + struct igc_tx_buffer *buffer; + union igc_adv_tx_desc *desc; + int err; + + if (!igc_desc_unused(ring)) + return -EBUSY; + + buffer = &ring->tx_buffer_info[ring->next_to_use]; + err = igc_fpe_init_smd_frame(ring, buffer, skb); + if (err) + return err; + + cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT | + IGC_ADVTXD_DCMD_IFCS | IGC_TXD_DCMD | + buffer->bytecount; + + olinfo_status |= FIELD_PREP(IGC_ADVTXD_PAYLEN_MASK, buffer->bytecount); + + switch (type) { + case SMD_V: + case SMD_R: + olinfo_status |= FIELD_PREP(IGC_TXD_POPTS_SMD_MASK, type); + break; + } + + desc = IGC_TX_DESC(ring, ring->next_to_use); + desc->read.cmd_type_len = cpu_to_le32(cmd_type); + desc->read.olinfo_status = cpu_to_le32(olinfo_status); + desc->read.buffer_addr = cpu_to_le64(dma_unmap_addr(buffer, dma)); + + netdev_tx_sent_queue(txring_txq(ring), skb->len); + + buffer->next_to_watch = desc; + ring->next_to_use = (ring->next_to_use + 1) % ring->count; + + return 0; +} + +static int igc_fpe_xmit_smd_frame(struct igc_adapter *adapter, + enum igc_txd_popts_type type) +{ + int cpu = smp_processor_id(); + struct netdev_queue *nq; + struct igc_ring *ring; + struct sk_buff *skb; + int err; + + ring = igc_get_tx_ring(adapter, cpu); + nq = txring_txq(ring); + + skb = alloc_skb(SMD_FRAME_SIZE, GFP_ATOMIC); + if (!skb) + return -ENOMEM; + + skb_put_zero(skb, SMD_FRAME_SIZE); + + __netif_tx_lock(nq, cpu); + + err = igc_fpe_init_tx_descriptor(ring, skb, type); + igc_flush_tx_descriptors(ring); + + __netif_tx_unlock(nq); + + return err; +} + +static void igc_fpe_send_mpacket(struct ethtool_mmsv *mmsv, + enum ethtool_mpacket type) +{ + struct igc_fpe_t *fpe = container_of(mmsv, struct igc_fpe_t, mmsv); + struct igc_adapter *adapter; + int err; + + adapter = container_of(fpe, struct igc_adapter, fpe); + + if (type == ETHTOOL_MPACKET_VERIFY) { + err = igc_fpe_xmit_smd_frame(adapter, SMD_V); + if (err && net_ratelimit()) + netdev_err(adapter->netdev, "Error sending SMD-V\n"); + } else if (type == ETHTOOL_MPACKET_RESPONSE) { + err = igc_fpe_xmit_smd_frame(adapter, SMD_R); + if (err && net_ratelimit()) + netdev_err(adapter->netdev, "Error sending SMD-R frame\n"); + } +} + +static const struct ethtool_mmsv_ops igc_mmsv_ops = { + .send_mpacket = igc_fpe_send_mpacket, +}; + +void igc_fpe_init(struct igc_adapter *adapter) +{ + adapter->fpe.tx_min_frag_size = TX_MIN_FRAG_SIZE; + ethtool_mmsv_init(&adapter->fpe.mmsv, adapter->netdev, &igc_mmsv_ops); +} + static bool is_any_launchtime(struct igc_adapter *adapter) { int i; @@ -37,24 +171,33 @@ static unsigned int igc_tsn_new_flags(struct igc_adapter *adapter) { unsigned int new_flags = adapter->flags & ~IGC_FLAG_TSN_ANY_ENABLED; - if (adapter->taprio_offload_enable) - new_flags |= IGC_FLAG_TSN_QBV_ENABLED; - if (is_any_launchtime(adapter)) + if (adapter->taprio_offload_enable || is_any_launchtime(adapter) || + adapter->strict_priority_enable) new_flags |= IGC_FLAG_TSN_QBV_ENABLED; if (is_cbs_enabled(adapter)) new_flags |= IGC_FLAG_TSN_QAV_ENABLED; + if (adapter->fpe.mmsv.pmac_enabled) + new_flags |= IGC_FLAG_TSN_PREEMPT_ENABLED; + return new_flags; } +static bool igc_tsn_is_tx_mode_in_tsn(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + + return !!(rd32(IGC_TQAVCTRL) & IGC_TQAVCTRL_TRANSMIT_MODE_TSN); +} + void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; u16 txoffset; - if (!is_any_launchtime(adapter)) + if (!igc_tsn_is_tx_mode_in_tsn(adapter)) return; switch (adapter->link_speed) { @@ -78,22 +221,89 @@ void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter) wr32(IGC_GTXOFFSET, txoffset); } +static void igc_tsn_restore_retx_default(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 retxctl; + + retxctl = rd32(IGC_RETX_CTL) & IGC_RETX_CTL_WATERMARK_MASK; + wr32(IGC_RETX_CTL, retxctl); +} + +bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + + return (rd32(IGC_BASET_H) || rd32(IGC_BASET_L)) && + adapter->taprio_offload_enable; +} + +static void igc_tsn_tx_arb(struct igc_adapter *adapter, u16 *queue_per_tc) +{ + struct igc_hw *hw = &adapter->hw; + u32 txarb; + + txarb = rd32(IGC_TXARB); + + txarb &= ~(IGC_TXARB_TXQ_PRIO_0_MASK | + IGC_TXARB_TXQ_PRIO_1_MASK | + IGC_TXARB_TXQ_PRIO_2_MASK | + IGC_TXARB_TXQ_PRIO_3_MASK); + + txarb |= IGC_TXARB_TXQ_PRIO_0(queue_per_tc[3]); + txarb |= IGC_TXARB_TXQ_PRIO_1(queue_per_tc[2]); + txarb |= IGC_TXARB_TXQ_PRIO_2(queue_per_tc[1]); + txarb |= IGC_TXARB_TXQ_PRIO_3(queue_per_tc[0]); + + wr32(IGC_TXARB, txarb); +} + +/** + * igc_tsn_set_rxpbsize - Set the receive packet buffer size + * @adapter: Pointer to the igc_adapter structure + * @rxpbs_exp_bmc_be: Value to set the receive packet buffer size, including + * express buffer, BMC buffer, and Best Effort buffer + * + * The IGC_RXPBS register value may include allocations for the Express buffer, + * BMC buffer, Best Effort buffer, and the timestamp descriptor buffer + * (IGC_RXPBS_CFG_TS_EN). + */ +static void igc_tsn_set_rxpbsize(struct igc_adapter *adapter, + u32 rxpbs_exp_bmc_be) +{ + struct igc_hw *hw = &adapter->hw; + u32 rxpbs = rd32(IGC_RXPBS); + + rxpbs &= ~(IGC_RXPBSIZE_EXP_MASK | IGC_BMC2OSPBSIZE_MASK | + IGC_RXPBSIZE_BE_MASK); + rxpbs |= rxpbs_exp_bmc_be; + + wr32(IGC_RXPBS, rxpbs); +} + /* Returns the TSN specific registers to their default values after * the adapter is reset. */ static int igc_tsn_disable_offload(struct igc_adapter *adapter) { + u16 queue_per_tc[4] = { 3, 2, 1, 0 }; struct igc_hw *hw = &adapter->hw; u32 tqavctrl; int i; wr32(IGC_GTXOFFSET, 0); - wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT); + wr32(IGC_TXPBS, IGC_TXPBSIZE_DEFAULT); wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_DEFAULT); + igc_tsn_set_rxpbsize(adapter, IGC_RXPBSIZE_EXP_BMC_DEFAULT); + + if (igc_is_device_id_i226(hw)) + igc_tsn_restore_retx_default(adapter); + tqavctrl = rd32(IGC_TQAVCTRL); tqavctrl &= ~(IGC_TQAVCTRL_TRANSMIT_MODE_TSN | - IGC_TQAVCTRL_ENHANCED_QAV | IGC_TQAVCTRL_FUTSCDDIS); + IGC_TQAVCTRL_ENHANCED_QAV | IGC_TQAVCTRL_FUTSCDDIS | + IGC_TQAVCTRL_PREEMPT_ENA | IGC_TQAVCTRL_MIN_FRAG_MASK); wr32(IGC_TQAVCTRL, tqavctrl); @@ -106,23 +316,82 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) wr32(IGC_QBVCYCLET_S, 0); wr32(IGC_QBVCYCLET, NSEC_PER_SEC); + /* Restore the default Tx arbitration: Priority 0 has the highest + * priority and is assigned to queue 0 and so on and so forth. + */ + igc_tsn_tx_arb(adapter, queue_per_tc); + adapter->flags &= ~IGC_FLAG_TSN_QBV_ENABLED; return 0; } +/* To partially fix i226 HW errata, reduce MAC internal buffering from 192 Bytes + * to 88 Bytes by setting RETX_CTL register using the recommendation from: + * a) Ethernet Controller I225/I226 Specification Update Rev 2.1 + * Item 9: TSN: Packet Transmission Might Cross the Qbv Window + * b) I225/6 SW User Manual Rev 1.2.4: Section 8.11.5 Retry Buffer Control + */ +static void igc_tsn_set_retx_qbvfullthreshold(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 retxctl, watermark; + + retxctl = rd32(IGC_RETX_CTL); + watermark = retxctl & IGC_RETX_CTL_WATERMARK_MASK; + /* Set QBVFULLTH value using watermark and set QBVFULLEN */ + retxctl |= (watermark << IGC_RETX_CTL_QBVFULLTH_SHIFT) | + IGC_RETX_CTL_QBVFULLEN; + wr32(IGC_RETX_CTL, retxctl); +} + +static u8 igc_fpe_get_frag_size_mult(const struct igc_fpe_t *fpe) +{ + u8 mult = (fpe->tx_min_frag_size / TX_MIN_FRAG_SIZE) - 1; + + return clamp_t(u8, mult, MIN_MULTPLIER_TX_MIN_FRAG, + MAX_MULTPLIER_TX_MIN_FRAG); +} + +u32 igc_fpe_get_supported_frag_size(u32 frag_size) +{ + const u32 supported_sizes[] = {64, 128, 192, 256}; + + /* Find the smallest supported size that is >= frag_size */ + for (int i = 0; i < ARRAY_SIZE(supported_sizes); i++) { + if (frag_size <= supported_sizes[i]) + return supported_sizes[i]; + } + + /* Should not happen */ + return TX_MAX_FRAG_SIZE; +} + static int igc_tsn_enable_offload(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; u32 tqavctrl, baset_l, baset_h; u32 sec, nsec, cycle; ktime_t base_time, systim; + u32 frag_size_mult; int i; wr32(IGC_TSAUXC, 0); wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_TSN); wr32(IGC_TXPBS, IGC_TXPBSIZE_TSN); + igc_tsn_set_rxpbsize(adapter, IGC_RXPBSIZE_EXP_BMC_BE_TSN); + + if (igc_is_device_id_i226(hw)) + igc_tsn_set_retx_qbvfullthreshold(adapter); + + if (adapter->strict_priority_enable) { + /* Configure queue priorities according to the user provided + * mapping. + */ + igc_tsn_tx_arb(adapter, adapter->queue_per_tc); + } + for (i = 0; i < adapter->num_tx_queues; i++) { struct igc_ring *ring = adapter->tx_ring[i]; u32 txqctl = 0; @@ -245,10 +514,16 @@ skip_cbs: wr32(IGC_TXQCTL(i), txqctl); } - tqavctrl = rd32(IGC_TQAVCTRL) & ~IGC_TQAVCTRL_FUTSCDDIS; - + tqavctrl = rd32(IGC_TQAVCTRL) & ~(IGC_TQAVCTRL_FUTSCDDIS | + IGC_TQAVCTRL_PREEMPT_ENA | IGC_TQAVCTRL_MIN_FRAG_MASK); tqavctrl |= IGC_TQAVCTRL_TRANSMIT_MODE_TSN | IGC_TQAVCTRL_ENHANCED_QAV; + if (adapter->fpe.mmsv.pmac_enabled) + tqavctrl |= IGC_TQAVCTRL_PREEMPT_ENA; + + frag_size_mult = igc_fpe_get_frag_size_mult(&adapter->fpe); + tqavctrl |= FIELD_PREP(IGC_TQAVCTRL_MIN_FRAG_MASK, frag_size_mult); + adapter->qbv_count++; cycle = adapter->cycle_time; @@ -262,14 +537,6 @@ skip_cbs: s64 n = div64_s64(ktime_sub_ns(systim, base_time), cycle); base_time = ktime_add_ns(base_time, (n + 1) * cycle); - - /* Increase the counter if scheduling into the past while - * Gate Control List (GCL) is running. - */ - if ((rd32(IGC_BASET_H) || rd32(IGC_BASET_L)) && - (adapter->tc_setup_type == TC_SETUP_QDISC_TAPRIO) && - (adapter->qbv_count > 1)) - adapter->qbv_config_change_errors++; } else { if (igc_is_device_id_i226(hw)) { ktime_t adjust_time, expires_time; @@ -317,6 +584,14 @@ int igc_tsn_reset(struct igc_adapter *adapter) unsigned int new_flags; int err = 0; + if (adapter->fpe.mmsv.pmac_enabled) { + err = igc_enable_empty_addr_recv(adapter); + if (err && net_ratelimit()) + netdev_err(adapter->netdev, "Error adding empty address to MAC filter\n"); + } else { + igc_disable_empty_addr_recv(adapter); + } + new_flags = igc_tsn_new_flags(adapter); if (!(new_flags & IGC_FLAG_TSN_ANY_ENABLED)) @@ -331,15 +606,22 @@ int igc_tsn_reset(struct igc_adapter *adapter) return err; } -int igc_tsn_offload_apply(struct igc_adapter *adapter) +static bool igc_tsn_will_tx_mode_change(struct igc_adapter *adapter) { - struct igc_hw *hw = &adapter->hw; + bool any_tsn_enabled = !!(igc_tsn_new_flags(adapter) & + IGC_FLAG_TSN_ANY_ENABLED); - /* Per I225/6 HW Design Section 7.5.2.1, transmit mode - * cannot be changed dynamically. Require reset the adapter. + return (any_tsn_enabled && !igc_tsn_is_tx_mode_in_tsn(adapter)) || + (!any_tsn_enabled && igc_tsn_is_tx_mode_in_tsn(adapter)); +} + +int igc_tsn_offload_apply(struct igc_adapter *adapter) +{ + /* Per I225/6 HW Design Section 7.5.2.1 guideline, if tx mode change + * from legacy->tsn or tsn->legacy, then reset adapter is needed. */ if (netif_running(adapter->netdev) && - (igc_is_device_id_i225(hw) || !adapter->qbv_count)) { + igc_tsn_will_tx_mode_change(adapter)) { schedule_work(&adapter->reset_task); return 0; } diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.h b/drivers/net/ethernet/intel/igc/igc_tsn.h index b53e6af560b7..c2a77229207b 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.h +++ b/drivers/net/ethernet/intel/igc/igc_tsn.h @@ -4,8 +4,61 @@ #ifndef _IGC_TSN_H_ #define _IGC_TSN_H_ +#define IGC_RX_MIN_FRAG_SIZE 60 +#define SMD_FRAME_SIZE 60 + +enum igc_txd_popts_type { + SMD_V = 0x01, + SMD_R = 0x02, +}; + +DECLARE_STATIC_KEY_FALSE(igc_fpe_enabled); + +void igc_fpe_init(struct igc_adapter *adapter); +u32 igc_fpe_get_supported_frag_size(u32 frag_size); int igc_tsn_offload_apply(struct igc_adapter *adapter); int igc_tsn_reset(struct igc_adapter *adapter); void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter); +bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter); + +static inline bool igc_fpe_is_pmac_enabled(struct igc_adapter *adapter) +{ + return static_branch_unlikely(&igc_fpe_enabled) && + adapter->fpe.mmsv.pmac_enabled; +} + +static inline bool igc_fpe_handle_mpacket(struct igc_adapter *adapter, + union igc_adv_rx_desc *rx_desc, + unsigned int size, void *pktbuf) +{ + u32 status_error = le32_to_cpu(rx_desc->wb.upper.status_error); + int smd; + + smd = FIELD_GET(IGC_RXDADV_STAT_SMD_TYPE_MASK, status_error); + if (smd != IGC_RXD_STAT_SMD_TYPE_V && smd != IGC_RXD_STAT_SMD_TYPE_R) + return false; + + if (size == SMD_FRAME_SIZE && mem_is_zero(pktbuf, SMD_FRAME_SIZE)) { + struct ethtool_mmsv *mmsv = &adapter->fpe.mmsv; + enum ethtool_mmsv_event event; + + if (smd == IGC_RXD_STAT_SMD_TYPE_V) + event = ETHTOOL_MMSV_LP_SENT_VERIFY_MPACKET; + else + event = ETHTOOL_MMSV_LP_SENT_RESPONSE_MPACKET; + + ethtool_mmsv_event_handle(mmsv, event); + } + + return true; +} + +static inline bool igc_fpe_transmitted_smd_v(union igc_adv_tx_desc *tx_desc) +{ + u32 olinfo_status = le32_to_cpu(tx_desc->read.olinfo_status); + u8 smd = FIELD_GET(IGC_TXD_POPTS_SMD_MASK, olinfo_status); + + return smd == SMD_V; +} #endif /* _IGC_BASE_H */ diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.c b/drivers/net/ethernet/intel/igc/igc_xdp.c index e27af72aada8..9eb47b4beb06 100644 --- a/drivers/net/ethernet/intel/igc/igc_xdp.c +++ b/drivers/net/ethernet/intel/igc/igc_xdp.c @@ -13,6 +13,8 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, struct net_device *dev = adapter->netdev; bool if_running = netif_running(dev); struct bpf_prog *old_prog; + bool need_update; + unsigned int i; if (dev->mtu > ETH_DATA_LEN) { /* For now, the driver doesn't support XDP functionality with @@ -22,8 +24,14 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, return -EOPNOTSUPP; } - if (if_running) - igc_close(dev); + need_update = !!adapter->xdp_prog != !!prog; + if (if_running && need_update) { + for (i = 0; i < adapter->num_rx_queues; i++) { + igc_disable_rx_ring(adapter->rx_ring[i]); + igc_disable_tx_ring(adapter->tx_ring[i]); + napi_disable(&adapter->rx_ring[i]->q_vector->napi); + } + } old_prog = xchg(&adapter->xdp_prog, prog); if (old_prog) @@ -34,8 +42,13 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, else xdp_features_clear_redirect_target(dev); - if (if_running) - igc_open(dev); + if (if_running && need_update) { + for (i = 0; i < adapter->num_rx_queues; i++) { + napi_enable(&adapter->rx_ring[i]->q_vector->napi); + igc_enable_tx_ring(adapter->tx_ring[i]); + igc_enable_rx_ring(adapter->rx_ring[i]); + } + } return 0; } diff --git a/drivers/net/ethernet/intel/ixgbe/Makefile b/drivers/net/ethernet/intel/ixgbe/Makefile index 4fb0d9e3f2da..2e7738f41c58 100644 --- a/drivers/net/ethernet/intel/ixgbe/Makefile +++ b/drivers/net/ethernet/intel/ixgbe/Makefile @@ -1,15 +1,17 @@ # SPDX-License-Identifier: GPL-2.0 -# Copyright(c) 1999 - 2018 Intel Corporation. +# Copyright(c) 1999 - 2024 Intel Corporation. # # Makefile for the Intel(R) 10GbE PCI Express ethernet driver # +subdir-ccflags-y += -I$(src) obj-$(CONFIG_IXGBE) += ixgbe.o -ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \ - ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \ - ixgbe_mbx.o ixgbe_x540.o ixgbe_x550.o ixgbe_lib.o ixgbe_ptp.o \ - ixgbe_xsk.o +ixgbe-y := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \ + ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \ + ixgbe_mbx.o ixgbe_x540.o ixgbe_x550.o ixgbe_lib.o ixgbe_ptp.o \ + ixgbe_xsk.o ixgbe_e610.o devlink/devlink.o ixgbe_fw_update.o \ + devlink/region.o ixgbe-$(CONFIG_IXGBE_DCB) += ixgbe_dcb.o ixgbe_dcb_82598.o \ ixgbe_dcb_82599.o ixgbe_dcb_nl.o diff --git a/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c new file mode 100644 index 000000000000..54f1b83dfe42 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c @@ -0,0 +1,557 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025, Intel Corporation. */ + +#include "ixgbe.h" +#include "devlink.h" +#include "ixgbe_fw_update.h" + +struct ixgbe_info_ctx { + char buf[128]; + struct ixgbe_orom_info pending_orom; + struct ixgbe_nvm_info pending_nvm; + struct ixgbe_netlist_info pending_netlist; + struct ixgbe_hw_dev_caps dev_caps; +}; + +enum ixgbe_devlink_version_type { + IXGBE_DL_VERSION_RUNNING, + IXGBE_DL_VERSION_STORED +}; + +static void ixgbe_info_get_dsn(struct ixgbe_adapter *adapter, + struct ixgbe_info_ctx *ctx) +{ + u8 dsn[8]; + + /* Copy the DSN into an array in Big Endian format */ + put_unaligned_be64(pci_get_dsn(adapter->pdev), dsn); + + snprintf(ctx->buf, sizeof(ctx->buf), "%8phD", dsn); +} + +static void ixgbe_info_orom_ver(struct ixgbe_adapter *adapter, + struct ixgbe_info_ctx *ctx, + enum ixgbe_devlink_version_type type) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_nvm_version nvm_ver; + + ctx->buf[0] = '\0'; + + if (hw->mac.type == ixgbe_mac_e610) { + struct ixgbe_orom_info *orom = &adapter->hw.flash.orom; + + if (type == IXGBE_DL_VERSION_STORED && + ctx->dev_caps.common_cap.nvm_update_pending_orom) + orom = &ctx->pending_orom; + + snprintf(ctx->buf, sizeof(ctx->buf), "%u.%u.%u", + orom->major, orom->build, orom->patch); + return; + } + + ixgbe_get_oem_prod_version(hw, &nvm_ver); + if (nvm_ver.oem_valid) { + snprintf(ctx->buf, sizeof(ctx->buf), "%x.%x.%x", + nvm_ver.oem_major, nvm_ver.oem_minor, + nvm_ver.oem_release); + + return; + } + + ixgbe_get_orom_version(hw, &nvm_ver); + if (nvm_ver.or_valid) + snprintf(ctx->buf, sizeof(ctx->buf), "%d.%d.%d", + nvm_ver.or_major, nvm_ver.or_build, nvm_ver.or_patch); +} + +static void ixgbe_info_eetrack(struct ixgbe_adapter *adapter, + struct ixgbe_info_ctx *ctx, + enum ixgbe_devlink_version_type type) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_nvm_version nvm_ver; + + if (hw->mac.type == ixgbe_mac_e610) { + u32 eetrack = hw->flash.nvm.eetrack; + + if (type == IXGBE_DL_VERSION_STORED && + ctx->dev_caps.common_cap.nvm_update_pending_nvm) + eetrack = ctx->pending_nvm.eetrack; + + snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", eetrack); + return; + } + + ixgbe_get_oem_prod_version(hw, &nvm_ver); + + /* No ETRACK version for OEM */ + if (nvm_ver.oem_valid) { + ctx->buf[0] = '\0'; + return; + } + + ixgbe_get_etk_id(hw, &nvm_ver); + snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", nvm_ver.etk_id); +} + +static void ixgbe_info_fw_api(struct ixgbe_adapter *adapter, + struct ixgbe_info_ctx *ctx) +{ + struct ixgbe_hw *hw = &adapter->hw; + + snprintf(ctx->buf, sizeof(ctx->buf), "%u.%u.%u", + hw->api_maj_ver, hw->api_min_ver, hw->api_patch); +} + +static void ixgbe_info_fw_build(struct ixgbe_adapter *adapter, + struct ixgbe_info_ctx *ctx) +{ + struct ixgbe_hw *hw = &adapter->hw; + + snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", hw->fw_build); +} + +static void ixgbe_info_fw_srev(struct ixgbe_adapter *adapter, + struct ixgbe_info_ctx *ctx, + enum ixgbe_devlink_version_type type) +{ + struct ixgbe_nvm_info *nvm = &adapter->hw.flash.nvm; + + if (type == IXGBE_DL_VERSION_STORED && + ctx->dev_caps.common_cap.nvm_update_pending_nvm) + nvm = &ctx->pending_nvm; + + snprintf(ctx->buf, sizeof(ctx->buf), "%u", nvm->srev); +} + +static void ixgbe_info_orom_srev(struct ixgbe_adapter *adapter, + struct ixgbe_info_ctx *ctx, + enum ixgbe_devlink_version_type type) +{ + struct ixgbe_orom_info *orom = &adapter->hw.flash.orom; + + if (type == IXGBE_DL_VERSION_STORED && + ctx->dev_caps.common_cap.nvm_update_pending_orom) + orom = &ctx->pending_orom; + + snprintf(ctx->buf, sizeof(ctx->buf), "%u", orom->srev); +} + +static void ixgbe_info_nvm_ver(struct ixgbe_adapter *adapter, + struct ixgbe_info_ctx *ctx, + enum ixgbe_devlink_version_type type) +{ + struct ixgbe_nvm_info *nvm = &adapter->hw.flash.nvm; + + if (type == IXGBE_DL_VERSION_STORED && + ctx->dev_caps.common_cap.nvm_update_pending_nvm) + nvm = &ctx->pending_nvm; + + snprintf(ctx->buf, sizeof(ctx->buf), "%x.%02x", nvm->major, nvm->minor); +} + +static void ixgbe_info_netlist_ver(struct ixgbe_adapter *adapter, + struct ixgbe_info_ctx *ctx, + enum ixgbe_devlink_version_type type) +{ + struct ixgbe_netlist_info *netlist = &adapter->hw.flash.netlist; + + if (type == IXGBE_DL_VERSION_STORED && + ctx->dev_caps.common_cap.nvm_update_pending_netlist) + netlist = &ctx->pending_netlist; + + /* The netlist version fields are BCD formatted */ + snprintf(ctx->buf, sizeof(ctx->buf), "%x.%x.%x-%x.%x.%x", + netlist->major, netlist->minor, + netlist->type >> 16, netlist->type & 0xFFFF, + netlist->rev, netlist->cust_ver); +} + +static void ixgbe_info_netlist_build(struct ixgbe_adapter *adapter, + struct ixgbe_info_ctx *ctx, + enum ixgbe_devlink_version_type type) +{ + struct ixgbe_netlist_info *netlist = &adapter->hw.flash.netlist; + + if (type == IXGBE_DL_VERSION_STORED && + ctx->dev_caps.common_cap.nvm_update_pending_netlist) + netlist = &ctx->pending_netlist; + + snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", netlist->hash); +} + +static int ixgbe_set_ctx_dev_caps(struct ixgbe_hw *hw, + struct ixgbe_info_ctx *ctx, + struct netlink_ext_ack *extack) +{ + bool *pending_orom, *pending_nvm, *pending_netlist; + int err; + + err = ixgbe_discover_dev_caps(hw, &ctx->dev_caps); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Unable to discover device capabilities"); + return err; + } + + pending_orom = &ctx->dev_caps.common_cap.nvm_update_pending_orom; + pending_nvm = &ctx->dev_caps.common_cap.nvm_update_pending_nvm; + pending_netlist = &ctx->dev_caps.common_cap.nvm_update_pending_netlist; + + if (*pending_orom) { + err = ixgbe_get_inactive_orom_ver(hw, &ctx->pending_orom); + if (err) + *pending_orom = false; + } + + if (*pending_nvm) { + err = ixgbe_get_inactive_nvm_ver(hw, &ctx->pending_nvm); + if (err) + *pending_nvm = false; + } + + if (*pending_netlist) { + err = ixgbe_get_inactive_netlist_ver(hw, &ctx->pending_netlist); + if (err) + *pending_netlist = false; + } + + return 0; +} + +static int ixgbe_devlink_info_get_e610(struct ixgbe_adapter *adapter, + struct devlink_info_req *req, + struct ixgbe_info_ctx *ctx) +{ + int err; + + ixgbe_info_fw_api(adapter, ctx); + err = devlink_info_version_running_put(req, + DEVLINK_INFO_VERSION_GENERIC_FW_MGMT_API, + ctx->buf); + if (err) + return err; + + ixgbe_info_fw_build(adapter, ctx); + err = devlink_info_version_running_put(req, "fw.mgmt.build", ctx->buf); + if (err) + return err; + + ixgbe_info_fw_srev(adapter, ctx, IXGBE_DL_VERSION_RUNNING); + err = devlink_info_version_running_put(req, "fw.mgmt.srev", ctx->buf); + if (err) + return err; + + ixgbe_info_orom_srev(adapter, ctx, IXGBE_DL_VERSION_RUNNING); + err = devlink_info_version_running_put(req, "fw.undi.srev", ctx->buf); + if (err) + return err; + + ixgbe_info_nvm_ver(adapter, ctx, IXGBE_DL_VERSION_RUNNING); + err = devlink_info_version_running_put(req, "fw.psid.api", ctx->buf); + if (err) + return err; + + ixgbe_info_netlist_ver(adapter, ctx, IXGBE_DL_VERSION_RUNNING); + err = devlink_info_version_running_put(req, "fw.netlist", ctx->buf); + if (err) + return err; + + ixgbe_info_netlist_build(adapter, ctx, IXGBE_DL_VERSION_RUNNING); + return devlink_info_version_running_put(req, "fw.netlist.build", + ctx->buf); +} + +static int +ixgbe_devlink_pending_info_get_e610(struct ixgbe_adapter *adapter, + struct devlink_info_req *req, + struct ixgbe_info_ctx *ctx) +{ + int err; + + ixgbe_info_orom_ver(adapter, ctx, IXGBE_DL_VERSION_STORED); + err = devlink_info_version_stored_put(req, + DEVLINK_INFO_VERSION_GENERIC_FW_UNDI, + ctx->buf); + if (err) + return err; + + ixgbe_info_eetrack(adapter, ctx, IXGBE_DL_VERSION_STORED); + err = devlink_info_version_stored_put(req, + DEVLINK_INFO_VERSION_GENERIC_FW_BUNDLE_ID, + ctx->buf); + if (err) + return err; + + ixgbe_info_fw_srev(adapter, ctx, IXGBE_DL_VERSION_STORED); + err = devlink_info_version_stored_put(req, "fw.mgmt.srev", ctx->buf); + if (err) + return err; + + ixgbe_info_orom_srev(adapter, ctx, IXGBE_DL_VERSION_STORED); + err = devlink_info_version_stored_put(req, "fw.undi.srev", ctx->buf); + if (err) + return err; + + ixgbe_info_nvm_ver(adapter, ctx, IXGBE_DL_VERSION_STORED); + err = devlink_info_version_stored_put(req, "fw.psid.api", ctx->buf); + if (err) + return err; + + ixgbe_info_netlist_ver(adapter, ctx, IXGBE_DL_VERSION_STORED); + err = devlink_info_version_stored_put(req, "fw.netlist", ctx->buf); + if (err) + return err; + + ixgbe_info_netlist_build(adapter, ctx, IXGBE_DL_VERSION_STORED); + return devlink_info_version_stored_put(req, "fw.netlist.build", + ctx->buf); +} + +static int ixgbe_devlink_info_get(struct devlink *devlink, + struct devlink_info_req *req, + struct netlink_ext_ack *extack) +{ + struct ixgbe_adapter *adapter = devlink_priv(devlink); + struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_info_ctx *ctx; + int err; + + ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + if (hw->mac.type == ixgbe_mac_e610) + ixgbe_refresh_fw_version(adapter); + + ixgbe_info_get_dsn(adapter, ctx); + err = devlink_info_serial_number_put(req, ctx->buf); + if (err) + goto free_ctx; + + err = hw->eeprom.ops.read_pba_string(hw, ctx->buf, sizeof(ctx->buf)); + if (err) + goto free_ctx; + + err = devlink_info_version_fixed_put(req, + DEVLINK_INFO_VERSION_GENERIC_BOARD_ID, + ctx->buf); + if (err) + goto free_ctx; + + ixgbe_info_orom_ver(adapter, ctx, IXGBE_DL_VERSION_RUNNING); + err = devlink_info_version_running_put(req, + DEVLINK_INFO_VERSION_GENERIC_FW_UNDI, + ctx->buf); + if (err) + goto free_ctx; + + ixgbe_info_eetrack(adapter, ctx, IXGBE_DL_VERSION_RUNNING); + err = devlink_info_version_running_put(req, + DEVLINK_INFO_VERSION_GENERIC_FW_BUNDLE_ID, + ctx->buf); + if (err || hw->mac.type != ixgbe_mac_e610) + goto free_ctx; + + err = ixgbe_set_ctx_dev_caps(hw, ctx, extack); + if (err) + goto free_ctx; + + err = ixgbe_devlink_info_get_e610(adapter, req, ctx); + if (err) + goto free_ctx; + + err = ixgbe_devlink_pending_info_get_e610(adapter, req, ctx); +free_ctx: + kfree(ctx); + return err; +} + +/** + * ixgbe_devlink_reload_empr_start - Start EMP reset to activate new firmware + * @devlink: pointer to the devlink instance to reload + * @netns_change: if true, the network namespace is changing + * @action: the action to perform. Must be DEVLINK_RELOAD_ACTION_FW_ACTIVATE + * @limit: limits on what reload should do, such as not resetting + * @extack: netlink extended ACK structure + * + * Allow user to activate new Embedded Management Processor firmware by + * issuing device specific EMP reset. Called in response to + * a DEVLINK_CMD_RELOAD with the DEVLINK_RELOAD_ACTION_FW_ACTIVATE. + * + * Note that teardown and rebuild of the driver state happens automatically as + * part of an interrupt and watchdog task. This is because all physical + * functions on the device must be able to reset when an EMP reset occurs from + * any source. + * + * Return: the exit code of the operation. + */ +static int ixgbe_devlink_reload_empr_start(struct devlink *devlink, + bool netns_change, + enum devlink_reload_action action, + enum devlink_reload_limit limit, + struct netlink_ext_ack *extack) +{ + struct ixgbe_adapter *adapter = devlink_priv(devlink); + struct ixgbe_hw *hw = &adapter->hw; + u8 pending; + int err; + + if (hw->mac.type != ixgbe_mac_e610) + return -EOPNOTSUPP; + + err = ixgbe_get_pending_updates(adapter, &pending, extack); + if (err) + return err; + + /* Pending is a bitmask of which flash banks have a pending update, + * including the main NVM bank, the Option ROM bank, and the netlist + * bank. If any of these bits are set, then there is a pending update + * waiting to be activated. + */ + if (!pending) { + NL_SET_ERR_MSG_MOD(extack, "No pending firmware update"); + return -ECANCELED; + } + + if (adapter->fw_emp_reset_disabled) { + NL_SET_ERR_MSG_MOD(extack, + "EMP reset is not available. To activate firmware, a reboot or power cycle is needed"); + return -ECANCELED; + } + + err = ixgbe_aci_nvm_update_empr(hw); + if (err) + NL_SET_ERR_MSG_MOD(extack, + "Failed to trigger EMP device reset to reload firmware"); + + return err; +} + +/*Wait for 10 sec with 0.5 sec tic. EMPR takes no less than half of a sec */ +#define IXGBE_DEVLINK_RELOAD_TIMEOUT_SEC 20 + +/** + * ixgbe_devlink_reload_empr_finish - finishes EMP reset + * @devlink: pointer to the devlink instance + * @action: the action to perform. + * @limit: limits on what reload should do + * @actions_performed: actions performed + * @extack: netlink extended ACK structure + * + * Wait for new NVM to be loaded during EMP reset. + * + * Return: -ETIME when timer is exceeded, 0 on success. + */ +static int ixgbe_devlink_reload_empr_finish(struct devlink *devlink, + enum devlink_reload_action action, + enum devlink_reload_limit limit, + u32 *actions_performed, + struct netlink_ext_ack *extack) +{ + struct ixgbe_adapter *adapter = devlink_priv(devlink); + struct ixgbe_hw *hw = &adapter->hw; + int i = 0; + u32 fwsm; + + do { + /* Just right away after triggering EMP reset the FWSM register + * may be not cleared yet, so begin the loop with the delay + * in order to not check the not updated register. + */ + mdelay(500); + + fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw)); + + if (i++ >= IXGBE_DEVLINK_RELOAD_TIMEOUT_SEC) + return -ETIME; + + } while (!(fwsm & IXGBE_FWSM_FW_VAL_BIT)); + + *actions_performed = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE); + + adapter->flags2 &= ~(IXGBE_FLAG2_API_MISMATCH | + IXGBE_FLAG2_FW_ROLLBACK); + + return 0; +} + +static const struct devlink_ops ixgbe_devlink_ops = { + .info_get = ixgbe_devlink_info_get, + .supported_flash_update_params = + DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK, + .flash_update = ixgbe_flash_pldm_image, + .reload_actions = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE), + .reload_down = ixgbe_devlink_reload_empr_start, + .reload_up = ixgbe_devlink_reload_empr_finish, +}; + +/** + * ixgbe_allocate_devlink - Allocate devlink instance + * @dev: device to allocate devlink for + * + * Allocate a devlink instance for this physical function. + * + * Return: pointer to the device adapter structure on success, + * ERR_PTR(-ENOMEM) when allocation failed. + */ +struct ixgbe_adapter *ixgbe_allocate_devlink(struct device *dev) +{ + struct ixgbe_adapter *adapter; + struct devlink *devlink; + + devlink = devlink_alloc(&ixgbe_devlink_ops, sizeof(*adapter), dev); + if (!devlink) + return ERR_PTR(-ENOMEM); + + adapter = devlink_priv(devlink); + adapter->devlink = devlink; + + return adapter; +} + +/** + * ixgbe_devlink_set_switch_id - Set unique switch ID based on PCI DSN + * @adapter: pointer to the device adapter structure + * @ppid: struct with switch id information + */ +static void ixgbe_devlink_set_switch_id(struct ixgbe_adapter *adapter, + struct netdev_phys_item_id *ppid) +{ + u64 id = pci_get_dsn(adapter->pdev); + + ppid->id_len = sizeof(id); + put_unaligned_be64(id, &ppid->id); +} + +/** + * ixgbe_devlink_register_port - Register devlink port + * @adapter: pointer to the device adapter structure + * + * Create and register a devlink_port for this physical function. + * + * Return: 0 on success, error code on failure. + */ +int ixgbe_devlink_register_port(struct ixgbe_adapter *adapter) +{ + struct devlink_port *devlink_port = &adapter->devlink_port; + struct devlink *devlink = adapter->devlink; + struct device *dev = &adapter->pdev->dev; + struct devlink_port_attrs attrs = {}; + int err; + + attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; + attrs.phys.port_number = adapter->hw.bus.func; + ixgbe_devlink_set_switch_id(adapter, &attrs.switch_id); + + devlink_port_attrs_set(devlink_port, &attrs); + + err = devl_port_register(devlink, devlink_port, 0); + if (err) { + dev_err(dev, + "devlink port registration failed, err %d\n", err); + } + + return err; +} diff --git a/drivers/net/ethernet/intel/ixgbe/devlink/devlink.h b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.h new file mode 100644 index 000000000000..381558058048 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2025, Intel Corporation. */ + +#ifndef _IXGBE_DEVLINK_H_ +#define _IXGBE_DEVLINK_H_ + +struct ixgbe_adapter *ixgbe_allocate_devlink(struct device *dev); +int ixgbe_devlink_register_port(struct ixgbe_adapter *adapter); +void ixgbe_devlink_init_regions(struct ixgbe_adapter *adapter); +void ixgbe_devlink_destroy_regions(struct ixgbe_adapter *adapter); + +#endif /* _IXGBE_DEVLINK_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/devlink/region.c b/drivers/net/ethernet/intel/ixgbe/devlink/region.c new file mode 100644 index 000000000000..76f6571c3c34 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/devlink/region.c @@ -0,0 +1,290 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025, Intel Corporation. */ + +#include "ixgbe.h" +#include "devlink.h" + +#define IXGBE_DEVLINK_READ_BLK_SIZE (1024 * 1024) + +static const struct devlink_region_ops ixgbe_nvm_region_ops; +static const struct devlink_region_ops ixgbe_sram_region_ops; + +static int ixgbe_devlink_parse_region(struct ixgbe_hw *hw, + const struct devlink_region_ops *ops, + bool *read_shadow_ram, u32 *nvm_size) +{ + if (ops == &ixgbe_nvm_region_ops) { + *read_shadow_ram = false; + *nvm_size = hw->flash.flash_size; + } else if (ops == &ixgbe_sram_region_ops) { + *read_shadow_ram = true; + *nvm_size = hw->flash.sr_words * 2u; + } else { + return -EOPNOTSUPP; + } + + return 0; +} + +/** + * ixgbe_devlink_nvm_snapshot - Capture a snapshot of the NVM content + * @devlink: the devlink instance + * @ops: the devlink region being snapshotted + * @extack: extended ACK response structure + * @data: on exit points to snapshot data buffer + * + * This function is called in response to the DEVLINK_CMD_REGION_NEW cmd. + * + * Capture a snapshot of the whole requested NVM region. + * + * No need to worry with freeing @data, devlink core takes care if it. + * + * Return: 0 on success, -EOPNOTSUPP for unsupported regions, -EBUSY when + * cannot lock NVM, -ENOMEM when cannot alloc mem and -EIO when error + * occurs during reading. + */ +static int ixgbe_devlink_nvm_snapshot(struct devlink *devlink, + const struct devlink_region_ops *ops, + struct netlink_ext_ack *extack, u8 **data) +{ + struct ixgbe_adapter *adapter = devlink_priv(devlink); + struct ixgbe_hw *hw = &adapter->hw; + bool read_shadow_ram; + u8 *nvm_data, *buf; + u32 nvm_size, left; + u8 num_blks; + int err; + + err = ixgbe_devlink_parse_region(hw, ops, &read_shadow_ram, &nvm_size); + if (err) + return err; + + nvm_data = kvzalloc(nvm_size, GFP_KERNEL); + if (!nvm_data) + return -ENOMEM; + + num_blks = DIV_ROUND_UP(nvm_size, IXGBE_DEVLINK_READ_BLK_SIZE); + buf = nvm_data; + left = nvm_size; + + for (int i = 0; i < num_blks; i++) { + u32 read_sz = min_t(u32, IXGBE_DEVLINK_READ_BLK_SIZE, left); + + /* Need to acquire NVM lock during each loop run because the + * total period of reading whole NVM is longer than the maximum + * period the lock can be taken defined by the IXGBE_NVM_TIMEOUT. + */ + err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Failed to acquire NVM semaphore"); + kvfree(nvm_data); + return -EBUSY; + } + + err = ixgbe_read_flat_nvm(hw, i * IXGBE_DEVLINK_READ_BLK_SIZE, + &read_sz, buf, read_shadow_ram); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Failed to read RAM content"); + ixgbe_release_nvm(hw); + kvfree(nvm_data); + return -EIO; + } + + ixgbe_release_nvm(hw); + + buf += read_sz; + left -= read_sz; + } + + *data = nvm_data; + return 0; +} + +/** + * ixgbe_devlink_devcaps_snapshot - Capture a snapshot of device capabilities + * @devlink: the devlink instance + * @ops: the devlink region being snapshotted + * @extack: extended ACK response structure + * @data: on exit points to snapshot data buffer + * + * This function is called in response to the DEVLINK_CMD_REGION_NEW for + * the device-caps devlink region. + * + * Capture a snapshot of the device capabilities reported by firmware. + * + * No need to worry with freeing @data, devlink core takes care if it. + * + * Return: 0 on success, -ENOMEM when cannot alloc mem, or return code of + * the reading operation. + */ +static int ixgbe_devlink_devcaps_snapshot(struct devlink *devlink, + const struct devlink_region_ops *ops, + struct netlink_ext_ack *extack, + u8 **data) +{ + struct ixgbe_adapter *adapter = devlink_priv(devlink); + struct ixgbe_aci_cmd_list_caps_elem *caps; + struct ixgbe_hw *hw = &adapter->hw; + int err; + + caps = kvzalloc(IXGBE_ACI_MAX_BUFFER_SIZE, GFP_KERNEL); + if (!caps) + return -ENOMEM; + + err = ixgbe_aci_list_caps(hw, caps, IXGBE_ACI_MAX_BUFFER_SIZE, NULL, + ixgbe_aci_opc_list_dev_caps); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Failed to read device capabilities"); + kvfree(caps); + return err; + } + + *data = (u8 *)caps; + return 0; +} + +/** + * ixgbe_devlink_nvm_read - Read a portion of NVM flash content + * @devlink: the devlink instance + * @ops: the devlink region to snapshot + * @extack: extended ACK response structure + * @offset: the offset to start at + * @size: the amount to read + * @data: the data buffer to read into + * + * This function is called in response to DEVLINK_CMD_REGION_READ to directly + * read a section of the NVM contents. + * + * Read from either the nvm-flash region either shadow-ram region. + * + * Return: 0 on success, -EOPNOTSUPP for unsupported regions, -EBUSY when + * cannot lock NVM, -ERANGE when buffer limit exceeded and -EIO when error + * occurs during reading. + */ +static int ixgbe_devlink_nvm_read(struct devlink *devlink, + const struct devlink_region_ops *ops, + struct netlink_ext_ack *extack, + u64 offset, u32 size, u8 *data) +{ + struct ixgbe_adapter *adapter = devlink_priv(devlink); + struct ixgbe_hw *hw = &adapter->hw; + bool read_shadow_ram; + u32 nvm_size; + int err; + + err = ixgbe_devlink_parse_region(hw, ops, &read_shadow_ram, &nvm_size); + if (err) + return err; + + if (offset + size > nvm_size) { + NL_SET_ERR_MSG_MOD(extack, "Cannot read beyond the region size"); + return -ERANGE; + } + + err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore"); + return -EBUSY; + } + + err = ixgbe_read_flat_nvm(hw, (u32)offset, &size, data, read_shadow_ram); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to read NVM contents"); + ixgbe_release_nvm(hw); + return -EIO; + } + + ixgbe_release_nvm(hw); + return 0; +} + +static const struct devlink_region_ops ixgbe_nvm_region_ops = { + .name = "nvm-flash", + .destructor = kvfree, + .snapshot = ixgbe_devlink_nvm_snapshot, + .read = ixgbe_devlink_nvm_read, +}; + +static const struct devlink_region_ops ixgbe_sram_region_ops = { + .name = "shadow-ram", + .destructor = kvfree, + .snapshot = ixgbe_devlink_nvm_snapshot, + .read = ixgbe_devlink_nvm_read, +}; + +static const struct devlink_region_ops ixgbe_devcaps_region_ops = { + .name = "device-caps", + .destructor = kvfree, + .snapshot = ixgbe_devlink_devcaps_snapshot, +}; + +/** + * ixgbe_devlink_init_regions - Initialize devlink regions + * @adapter: adapter instance + * + * Create devlink regions used to enable access to dump the contents of the + * flash memory of the device. + */ +void ixgbe_devlink_init_regions(struct ixgbe_adapter *adapter) +{ + struct devlink *devlink = adapter->devlink; + struct device *dev = &adapter->pdev->dev; + u64 nvm_size, sram_size; + + if (adapter->hw.mac.type != ixgbe_mac_e610) + return; + + nvm_size = adapter->hw.flash.flash_size; + adapter->nvm_region = devl_region_create(devlink, &ixgbe_nvm_region_ops, + 1, nvm_size); + if (IS_ERR(adapter->nvm_region)) { + dev_err(dev, + "Failed to create NVM devlink region, err %ld\n", + PTR_ERR(adapter->nvm_region)); + adapter->nvm_region = NULL; + } + + sram_size = adapter->hw.flash.sr_words * 2u; + adapter->sram_region = devl_region_create(devlink, &ixgbe_sram_region_ops, + 1, sram_size); + if (IS_ERR(adapter->sram_region)) { + dev_err(dev, + "Failed to create shadow-ram devlink region, err %ld\n", + PTR_ERR(adapter->sram_region)); + adapter->sram_region = NULL; + } + + adapter->devcaps_region = devl_region_create(devlink, + &ixgbe_devcaps_region_ops, + 10, IXGBE_ACI_MAX_BUFFER_SIZE); + if (IS_ERR(adapter->devcaps_region)) { + dev_err(dev, + "Failed to create device-caps devlink region, err %ld\n", + PTR_ERR(adapter->devcaps_region)); + adapter->devcaps_region = NULL; + } +} + +/** + * ixgbe_devlink_destroy_regions - Destroy devlink regions + * @adapter: adapter instance + * + * Remove previously created regions for this adapter instance. + */ +void ixgbe_devlink_destroy_regions(struct ixgbe_adapter *adapter) +{ + if (adapter->hw.mac.type != ixgbe_mac_e610) + return; + + if (adapter->nvm_region) + devl_region_destroy(adapter->nvm_region); + + if (adapter->sram_region) + devl_region_destroy(adapter->sram_region); + + if (adapter->devcaps_region) + devl_region_destroy(adapter->devcaps_region); +} diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 559b443c409f..47311b134a7a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #ifndef _IXGBE_H_ #define _IXGBE_H_ @@ -17,9 +17,12 @@ #include <linux/net_tstamp.h> #include <linux/ptp_clock_kernel.h> +#include <net/devlink.h> + #include "ixgbe_type.h" #include "ixgbe_common.h" #include "ixgbe_dcb.h" +#include "ixgbe_e610.h" #if IS_ENABLED(CONFIG_FCOE) #define IXGBE_FCOE #include "ixgbe_fcoe.h" @@ -173,6 +176,7 @@ enum ixgbe_tx_flags { #define VMDQ_P(p) ((p) + adapter->ring_feature[RING_F_VMDQ].offset) #define IXGBE_82599_VF_DEVICE_ID 0x10ED #define IXGBE_X540_VF_DEVICE_ID 0x1515 +#define IXGBE_E610_VF_DEVICE_ID 0x57AD #define UPDATE_VF_COUNTER_32bit(reg, last_counter, counter) \ { \ @@ -610,6 +614,11 @@ struct ixgbe_adapter { struct bpf_prog *xdp_prog; struct pci_dev *pdev; struct mii_bus *mii_bus; + struct devlink *devlink; + struct devlink_port devlink_port; + struct devlink_region *nvm_region; + struct devlink_region *sram_region; + struct devlink_region *devcaps_region; unsigned long state; @@ -654,6 +663,7 @@ struct ixgbe_adapter { #define IXGBE_FLAG2_RSS_FIELD_IPV6_UDP BIT(9) #define IXGBE_FLAG2_PTP_PPS_ENABLED BIT(10) #define IXGBE_FLAG2_PHY_INTERRUPT BIT(11) +#define IXGBE_FLAG2_FW_ASYNC_EVENT BIT(12) #define IXGBE_FLAG2_VLAN_PROMISC BIT(13) #define IXGBE_FLAG2_EEE_CAPABLE BIT(14) #define IXGBE_FLAG2_EEE_ENABLED BIT(15) @@ -661,6 +671,11 @@ struct ixgbe_adapter { #define IXGBE_FLAG2_IPSEC_ENABLED BIT(17) #define IXGBE_FLAG2_VF_IPSEC_ENABLED BIT(18) #define IXGBE_FLAG2_AUTO_DISABLE_VF BIT(19) +#define IXGBE_FLAG2_PHY_FW_LOAD_FAILED BIT(20) +#define IXGBE_FLAG2_NO_MEDIA BIT(21) +#define IXGBE_FLAG2_MOD_POWER_UNSUPPORTED BIT(22) +#define IXGBE_FLAG2_API_MISMATCH BIT(23) +#define IXGBE_FLAG2_FW_ROLLBACK BIT(24) /* Tx fast path data */ int num_tx_queues; @@ -749,6 +764,8 @@ struct ixgbe_adapter { u32 atr_sample_rate; spinlock_t fdir_perfect_lock; + bool fw_emp_reset_disabled; + #ifdef IXGBE_FCOE struct ixgbe_fcoe fcoe; #endif /* IXGBE_FCOE */ @@ -793,6 +810,7 @@ struct ixgbe_adapter { u32 vferr_refcount; struct ixgbe_mac_addr *mac_table; struct kobject *info_kobj; + u16 lse_mask; #ifdef CONFIG_IXGBE_HWMON struct hwmon_buff *ixgbe_hwmon_buff; #endif /* CONFIG_IXGBE_HWMON */ @@ -823,6 +841,17 @@ struct ixgbe_adapter { spinlock_t vfs_lock; }; +struct ixgbe_netdevice_priv { + struct ixgbe_adapter *adapter; +}; + +static inline struct ixgbe_adapter *ixgbe_from_netdev(struct net_device *netdev) +{ + struct ixgbe_netdevice_priv *priv = netdev_priv(netdev); + + return priv->adapter; +} + static inline int ixgbe_determine_xdp_q_idx(int cpu) { if (static_key_enabled(&ixgbe_xdp_locking_key)) @@ -849,6 +878,7 @@ static inline u8 ixgbe_max_rss_indices(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: return IXGBE_MAX_RSS_INDICES_X550; default: return 0; @@ -874,6 +904,7 @@ enum ixgbe_state_t { __IXGBE_PTP_RUNNING, __IXGBE_PTP_TX_IN_PROGRESS, __IXGBE_RESET_REQUESTED, + __IXGBE_PHY_INIT_COMPLETE, }; struct ixgbe_cb { @@ -896,6 +927,7 @@ enum ixgbe_boards { board_x550em_x_fw, board_x550em_a, board_x550em_a_fw, + board_e610, }; extern const struct ixgbe_info ixgbe_82598_info; @@ -906,6 +938,7 @@ extern const struct ixgbe_info ixgbe_X550EM_x_info; extern const struct ixgbe_info ixgbe_x550em_x_fw_info; extern const struct ixgbe_info ixgbe_x550em_a_info; extern const struct ixgbe_info ixgbe_x550em_a_fw_info; +extern const struct ixgbe_info ixgbe_e610_info; #ifdef CONFIG_IXGBE_DCB extern const struct dcbnl_rtnl_ops ixgbe_dcbnl_ops; #endif @@ -934,6 +967,8 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter); int ixgbe_init_interrupt_scheme(struct ixgbe_adapter *adapter); bool ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id, u16 subdevice_id); +void ixgbe_set_fw_version_e610(struct ixgbe_adapter *adapter); +void ixgbe_refresh_fw_version(struct ixgbe_adapter *adapter); #ifdef CONFIG_PCI_IOV void ixgbe_full_sync_mac_table(struct ixgbe_adapter *adapter); #endif diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c index 283a23150a4d..444da982593f 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c @@ -6,6 +6,7 @@ #include <linux/sched.h> #include "ixgbe.h" +#include "ixgbe_mbx.h" #include "ixgbe_phy.h" #define IXGBE_82598_MAX_TX_QUEUES 32 @@ -1168,6 +1169,7 @@ static const struct ixgbe_eeprom_operations eeprom_ops_82598 = { .calc_checksum = &ixgbe_calc_eeprom_checksum_generic, .validate_checksum = &ixgbe_validate_eeprom_checksum_generic, .update_checksum = &ixgbe_update_eeprom_checksum_generic, + .read_pba_string = &ixgbe_read_pba_string_generic, }; static const struct ixgbe_phy_operations phy_ops_82598 = { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c index cdaf087b4e85..d5b1b974b4a3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #include <linux/pci.h> #include <linux/delay.h> @@ -1615,6 +1615,7 @@ int ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: IXGBE_WRITE_REG(hw, IXGBE_FDIRSCTPM, ~fdirtcpm); break; default: @@ -2229,6 +2230,7 @@ static const struct ixgbe_eeprom_operations eeprom_ops_82599 = { .calc_checksum = &ixgbe_calc_eeprom_checksum_generic, .validate_checksum = &ixgbe_validate_eeprom_checksum_generic, .update_checksum = &ixgbe_update_eeprom_checksum_generic, + .read_pba_string = &ixgbe_read_pba_string_generic, }; static const struct ixgbe_phy_operations phy_ops_82599 = { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 3be1bfb16498..5784d5d1896e 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #include <linux/pci.h> #include <linux/delay.h> @@ -58,6 +58,7 @@ bool ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw) switch (hw->device_id) { case IXGBE_DEV_ID_X550EM_A_SFP: case IXGBE_DEV_ID_X550EM_A_SFP_N: + case IXGBE_DEV_ID_E610_SFP: supported = false; break; default: @@ -88,6 +89,8 @@ bool ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw) case IXGBE_DEV_ID_X550EM_A_10G_T: case IXGBE_DEV_ID_X550EM_A_1G_T: case IXGBE_DEV_ID_X550EM_A_1G_T_L: + case IXGBE_DEV_ID_E610_10G_T: + case IXGBE_DEV_ID_E610_2_5G_T: supported = true; break; default: @@ -329,6 +332,7 @@ int ixgbe_start_hw_generic(struct ixgbe_hw *hw) * Devices in the second generation: * 82599 * X540 + * E610 **/ int ixgbe_start_hw_gen2(struct ixgbe_hw *hw) { @@ -469,9 +473,14 @@ int ixgbe_clear_hw_cntrs_generic(struct ixgbe_hw *hw) } } - if (hw->mac.type == ixgbe_mac_X550 || hw->mac.type == ixgbe_mac_X540) { + if (hw->mac.type == ixgbe_mac_X550 || + hw->mac.type == ixgbe_mac_X540 || + hw->mac.type == ixgbe_mac_e610) { if (hw->phy.id == 0) hw->phy.ops.identify(hw); + } + + if (hw->mac.type == ixgbe_mac_X550 || hw->mac.type == ixgbe_mac_X540) { hw->phy.ops.read_reg(hw, IXGBE_PCRC8ECL, MDIO_MMD_PCS, &i); hw->phy.ops.read_reg(hw, IXGBE_PCRC8ECH, MDIO_MMD_PCS, &i); hw->phy.ops.read_reg(hw, IXGBE_LDPCECL, MDIO_MMD_PCS, &i); @@ -660,7 +669,11 @@ int ixgbe_get_bus_info_generic(struct ixgbe_hw *hw) hw->bus.type = ixgbe_bus_type_pci_express; /* Get the negotiated link width and speed from PCI config space */ - link_status = ixgbe_read_pci_cfg_word(hw, IXGBE_PCI_LINK_STATUS); + if (hw->mac.type == ixgbe_mac_e610) + link_status = ixgbe_read_pci_cfg_word(hw, IXGBE_PCI_LINK_STATUS_E610); + else + link_status = ixgbe_read_pci_cfg_word(hw, + IXGBE_PCI_LINK_STATUS); hw->bus.width = ixgbe_convert_bus_width(link_status); hw->bus.speed = ixgbe_convert_bus_speed(link_status); @@ -2918,6 +2931,10 @@ u16 ixgbe_get_pcie_msix_count_generic(struct ixgbe_hw *hw) pcie_offset = IXGBE_PCIE_MSIX_82599_CAPS; max_msix_count = IXGBE_MAX_MSIX_VECTORS_82599; break; + case ixgbe_mac_e610: + pcie_offset = IXGBE_PCIE_MSIX_E610_CAPS; + max_msix_count = IXGBE_MAX_MSIX_VECTORS_82599; + break; default: return 1; } @@ -3366,7 +3383,8 @@ int ixgbe_check_mac_link_generic(struct ixgbe_hw *hw, ixgbe_link_speed *speed, *speed = IXGBE_LINK_SPEED_1GB_FULL; break; case IXGBE_LINKS_SPEED_100_82599: - if ((hw->mac.type >= ixgbe_mac_X550) && + if ((hw->mac.type >= ixgbe_mac_X550 || + hw->mac.type == ixgbe_mac_e610) && (links_reg & IXGBE_LINKS_SPEED_NON_STD)) *speed = IXGBE_LINK_SPEED_5GB_FULL; else diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h index 6493abf189de..6639069ad528 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h @@ -194,6 +194,8 @@ u32 ixgbe_read_reg(struct ixgbe_hw *hw, u32 reg); dev_err(&adapter->pdev->dev, format, ## arg) #define e_dev_notice(format, arg...) \ dev_notice(&adapter->pdev->dev, format, ## arg) +#define e_dbg(msglvl, format, arg...) \ + netif_dbg(adapter, msglvl, adapter->netdev, format, ## arg) #define e_info(msglvl, format, arg...) \ netif_info(adapter, msglvl, adapter->netdev, format, ## arg) #define e_err(msglvl, format, arg...) \ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c index e85f7d2e8810..3dd5a16a14df 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #include "ixgbe.h" #include <linux/dcbnl.h> @@ -118,14 +118,14 @@ static int ixgbe_copy_dcb_cfg(struct ixgbe_adapter *adapter, int tc_max) static u8 ixgbe_dcbnl_get_state(struct net_device *netdev) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); return !!(adapter->flags & IXGBE_FLAG_DCB_ENABLED); } static u8 ixgbe_dcbnl_set_state(struct net_device *netdev, u8 state) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); /* Fail command if not in CEE mode */ if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_CEE)) @@ -142,7 +142,7 @@ static u8 ixgbe_dcbnl_set_state(struct net_device *netdev, u8 state) static void ixgbe_dcbnl_get_perm_hw_addr(struct net_device *netdev, u8 *perm_addr) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); int i, j; memset(perm_addr, 0xff, MAX_ADDR_LEN); @@ -154,6 +154,7 @@ static void ixgbe_dcbnl_get_perm_hw_addr(struct net_device *netdev, case ixgbe_mac_82599EB: case ixgbe_mac_X540: case ixgbe_mac_X550: + case ixgbe_mac_e610: for (j = 0; j < netdev->addr_len; j++, i++) perm_addr[i] = adapter->hw.mac.san_addr[j]; break; @@ -166,7 +167,7 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_tx(struct net_device *netdev, int tc, u8 prio, u8 bwg_id, u8 bw_pct, u8 up_map) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); if (prio != DCB_ATTR_VALUE_UNDEFINED) adapter->temp_dcb_cfg.tc_config[tc].path[0].prio_type = prio; @@ -183,7 +184,7 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_tx(struct net_device *netdev, int tc, static void ixgbe_dcbnl_set_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id, u8 bw_pct) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); adapter->temp_dcb_cfg.bw_percentage[0][bwg_id] = bw_pct; } @@ -192,7 +193,7 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_rx(struct net_device *netdev, int tc, u8 prio, u8 bwg_id, u8 bw_pct, u8 up_map) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); if (prio != DCB_ATTR_VALUE_UNDEFINED) adapter->temp_dcb_cfg.tc_config[tc].path[1].prio_type = prio; @@ -209,7 +210,7 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_rx(struct net_device *netdev, int tc, static void ixgbe_dcbnl_set_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id, u8 bw_pct) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); adapter->temp_dcb_cfg.bw_percentage[1][bwg_id] = bw_pct; } @@ -218,7 +219,7 @@ static void ixgbe_dcbnl_get_pg_tc_cfg_tx(struct net_device *netdev, int tc, u8 *prio, u8 *bwg_id, u8 *bw_pct, u8 *up_map) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); *prio = adapter->dcb_cfg.tc_config[tc].path[0].prio_type; *bwg_id = adapter->dcb_cfg.tc_config[tc].path[0].bwg_id; @@ -229,7 +230,7 @@ static void ixgbe_dcbnl_get_pg_tc_cfg_tx(struct net_device *netdev, int tc, static void ixgbe_dcbnl_get_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id, u8 *bw_pct) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); *bw_pct = adapter->dcb_cfg.bw_percentage[0][bwg_id]; } @@ -238,7 +239,7 @@ static void ixgbe_dcbnl_get_pg_tc_cfg_rx(struct net_device *netdev, int tc, u8 *prio, u8 *bwg_id, u8 *bw_pct, u8 *up_map) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); *prio = adapter->dcb_cfg.tc_config[tc].path[1].prio_type; *bwg_id = adapter->dcb_cfg.tc_config[tc].path[1].bwg_id; @@ -249,7 +250,7 @@ static void ixgbe_dcbnl_get_pg_tc_cfg_rx(struct net_device *netdev, int tc, static void ixgbe_dcbnl_get_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id, u8 *bw_pct) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); *bw_pct = adapter->dcb_cfg.bw_percentage[1][bwg_id]; } @@ -257,7 +258,7 @@ static void ixgbe_dcbnl_get_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id, static void ixgbe_dcbnl_set_pfc_cfg(struct net_device *netdev, int priority, u8 setting) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); adapter->temp_dcb_cfg.tc_config[priority].dcb_pfc = setting; if (adapter->temp_dcb_cfg.tc_config[priority].dcb_pfc != @@ -268,14 +269,14 @@ static void ixgbe_dcbnl_set_pfc_cfg(struct net_device *netdev, int priority, static void ixgbe_dcbnl_get_pfc_cfg(struct net_device *netdev, int priority, u8 *setting) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); *setting = adapter->dcb_cfg.tc_config[priority].dcb_pfc; } static void ixgbe_dcbnl_devreset(struct net_device *dev) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); while (test_and_set_bit(__IXGBE_RESETTING, &adapter->state)) usleep_range(1000, 2000); @@ -294,7 +295,7 @@ static void ixgbe_dcbnl_devreset(struct net_device *dev) static u8 ixgbe_dcbnl_set_all(struct net_device *netdev) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_dcb_config *dcb_cfg = &adapter->dcb_cfg; struct ixgbe_hw *hw = &adapter->hw; int ret = DCB_NO_HW_CHG; @@ -317,7 +318,7 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev) int max_frame = adapter->netdev->mtu + ETH_HLEN + ETH_FCS_LEN; #ifdef IXGBE_FCOE - if (adapter->netdev->features & NETIF_F_FCOE_MTU) + if (adapter->netdev->fcoe_mtu) max_frame = max(max_frame, IXGBE_FCOE_JUMBO_FRAME_SIZE); #endif @@ -382,7 +383,7 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev) static u8 ixgbe_dcbnl_getcap(struct net_device *netdev, int capid, u8 *cap) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); switch (capid) { case DCB_CAP_ATTR_PG: @@ -419,7 +420,7 @@ static u8 ixgbe_dcbnl_getcap(struct net_device *netdev, int capid, u8 *cap) static int ixgbe_dcbnl_getnumtcs(struct net_device *netdev, int tcid, u8 *num) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) { switch (tcid) { @@ -446,14 +447,14 @@ static int ixgbe_dcbnl_setnumtcs(struct net_device *netdev, int tcid, u8 num) static u8 ixgbe_dcbnl_getpfcstate(struct net_device *netdev) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); return adapter->dcb_cfg.pfc_mode_enable; } static void ixgbe_dcbnl_setpfcstate(struct net_device *netdev, u8 state) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); adapter->temp_dcb_cfg.pfc_mode_enable = state; } @@ -470,7 +471,7 @@ static void ixgbe_dcbnl_setpfcstate(struct net_device *netdev, u8 state) */ static int ixgbe_dcbnl_getapp(struct net_device *netdev, u8 idtype, u16 id) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct dcb_app app = { .selector = idtype, .protocol = id, @@ -485,7 +486,7 @@ static int ixgbe_dcbnl_getapp(struct net_device *netdev, u8 idtype, u16 id) static int ixgbe_dcbnl_ieee_getets(struct net_device *dev, struct ieee_ets *ets) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct ieee_ets *my_ets = adapter->ixgbe_ieee_ets; ets->ets_cap = adapter->dcb_cfg.num_tcs.pg_tcs; @@ -505,7 +506,7 @@ static int ixgbe_dcbnl_ieee_getets(struct net_device *dev, static int ixgbe_dcbnl_ieee_setets(struct net_device *dev, struct ieee_ets *ets) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); int max_frame = dev->mtu + ETH_HLEN + ETH_FCS_LEN; int i, err; __u8 max_tc = 0; @@ -558,7 +559,7 @@ static int ixgbe_dcbnl_ieee_setets(struct net_device *dev, static int ixgbe_dcbnl_ieee_getpfc(struct net_device *dev, struct ieee_pfc *pfc) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct ieee_pfc *my_pfc = adapter->ixgbe_ieee_pfc; int i; @@ -583,7 +584,7 @@ static int ixgbe_dcbnl_ieee_getpfc(struct net_device *dev, static int ixgbe_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct ixgbe_hw *hw = &adapter->hw; u8 *prio_tc; int err; @@ -615,7 +616,7 @@ static int ixgbe_dcbnl_ieee_setpfc(struct net_device *dev, static int ixgbe_dcbnl_ieee_setapp(struct net_device *dev, struct dcb_app *app) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); int err; if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) @@ -660,7 +661,7 @@ static int ixgbe_dcbnl_ieee_setapp(struct net_device *dev, static int ixgbe_dcbnl_ieee_delapp(struct net_device *dev, struct dcb_app *app) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); int err; if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) @@ -704,13 +705,13 @@ static int ixgbe_dcbnl_ieee_delapp(struct net_device *dev, static u8 ixgbe_dcbnl_getdcbx(struct net_device *dev) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); return adapter->dcbx_cap; } static u8 ixgbe_dcbnl_setdcbx(struct net_device *dev, u8 mode) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct ieee_ets ets = {0}; struct ieee_pfc pfc = {0}; int err = 0; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c new file mode 100644 index 000000000000..71ea25de1bac --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c @@ -0,0 +1,3995 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2024 Intel Corporation. */ + +#include "ixgbe_common.h" +#include "ixgbe_e610.h" +#include "ixgbe_x550.h" +#include "ixgbe_type.h" +#include "ixgbe_x540.h" +#include "ixgbe_mbx.h" +#include "ixgbe_phy.h" + +/** + * ixgbe_should_retry_aci_send_cmd_execute - decide if ACI command should + * be resent + * @opcode: ACI opcode + * + * Check if ACI command should be sent again depending on the provided opcode. + * It may happen when CSR is busy during link state changes. + * + * Return: true if the sending command routine should be repeated, + * otherwise false. + */ +static bool ixgbe_should_retry_aci_send_cmd_execute(u16 opcode) +{ + switch (opcode) { + case ixgbe_aci_opc_disable_rxen: + case ixgbe_aci_opc_get_phy_caps: + case ixgbe_aci_opc_get_link_status: + case ixgbe_aci_opc_get_link_topo: + return true; + } + + return false; +} + +/** + * ixgbe_aci_send_cmd_execute - execute sending FW Admin Command to FW Admin + * Command Interface + * @hw: pointer to the HW struct + * @desc: descriptor describing the command + * @buf: buffer to use for indirect commands (NULL for direct commands) + * @buf_size: size of buffer for indirect commands (0 for direct commands) + * + * Admin Command is sent using CSR by setting descriptor and buffer in specific + * registers. + * + * Return: the exit code of the operation. + * * - 0 - success. + * * - -EIO - CSR mechanism is not enabled. + * * - -EBUSY - CSR mechanism is busy. + * * - -EINVAL - buf_size is too big or + * invalid argument buf or buf_size. + * * - -ETIME - Admin Command X command timeout. + * * - -EIO - Admin Command X invalid state of HICR register or + * Admin Command failed because of bad opcode was returned or + * Admin Command failed with error Y. + */ +static int ixgbe_aci_send_cmd_execute(struct ixgbe_hw *hw, + struct ixgbe_aci_desc *desc, + void *buf, u16 buf_size) +{ + u16 opcode, buf_tail_size = buf_size % 4; + u32 *raw_desc = (u32 *)desc; + u32 hicr, i, buf_tail = 0; + bool valid_buf = false; + + hw->aci.last_status = IXGBE_ACI_RC_OK; + + /* It's necessary to check if mechanism is enabled */ + hicr = IXGBE_READ_REG(hw, IXGBE_PF_HICR); + + if (!(hicr & IXGBE_PF_HICR_EN)) + return -EIO; + + if (hicr & IXGBE_PF_HICR_C) { + hw->aci.last_status = IXGBE_ACI_RC_EBUSY; + return -EBUSY; + } + + opcode = le16_to_cpu(desc->opcode); + + if (buf_size > IXGBE_ACI_MAX_BUFFER_SIZE) + return -EINVAL; + + if (buf) + desc->flags |= cpu_to_le16(IXGBE_ACI_FLAG_BUF); + + if (desc->flags & cpu_to_le16(IXGBE_ACI_FLAG_BUF)) { + if ((buf && !buf_size) || + (!buf && buf_size)) + return -EINVAL; + if (buf && buf_size) + valid_buf = true; + } + + if (valid_buf) { + if (buf_tail_size) + memcpy(&buf_tail, buf + buf_size - buf_tail_size, + buf_tail_size); + + if (((buf_size + 3) & ~0x3) > IXGBE_ACI_LG_BUF) + desc->flags |= cpu_to_le16(IXGBE_ACI_FLAG_LB); + + desc->datalen = cpu_to_le16(buf_size); + + if (desc->flags & cpu_to_le16(IXGBE_ACI_FLAG_RD)) { + for (i = 0; i < buf_size / 4; i++) + IXGBE_WRITE_REG(hw, IXGBE_PF_HIBA(i), ((u32 *)buf)[i]); + if (buf_tail_size) + IXGBE_WRITE_REG(hw, IXGBE_PF_HIBA(i), buf_tail); + } + } + + /* Descriptor is written to specific registers */ + for (i = 0; i < IXGBE_ACI_DESC_SIZE_IN_DWORDS; i++) + IXGBE_WRITE_REG(hw, IXGBE_PF_HIDA(i), raw_desc[i]); + + /* SW has to set PF_HICR.C bit and clear PF_HICR.SV and + * PF_HICR_EV + */ + hicr = (IXGBE_READ_REG(hw, IXGBE_PF_HICR) | IXGBE_PF_HICR_C) & + ~(IXGBE_PF_HICR_SV | IXGBE_PF_HICR_EV); + IXGBE_WRITE_REG(hw, IXGBE_PF_HICR, hicr); + +#define MAX_SLEEP_RESP_US 1000 +#define MAX_TMOUT_RESP_SYNC_US 100000000 + + /* Wait for sync Admin Command response */ + read_poll_timeout(IXGBE_READ_REG, hicr, + (hicr & IXGBE_PF_HICR_SV) || + !(hicr & IXGBE_PF_HICR_C), + MAX_SLEEP_RESP_US, MAX_TMOUT_RESP_SYNC_US, true, hw, + IXGBE_PF_HICR); + +#define MAX_TMOUT_RESP_ASYNC_US 150000000 + + /* Wait for async Admin Command response */ + read_poll_timeout(IXGBE_READ_REG, hicr, + (hicr & IXGBE_PF_HICR_EV) || + !(hicr & IXGBE_PF_HICR_C), + MAX_SLEEP_RESP_US, MAX_TMOUT_RESP_ASYNC_US, true, hw, + IXGBE_PF_HICR); + + /* Read sync Admin Command response */ + if ((hicr & IXGBE_PF_HICR_SV)) { + for (i = 0; i < IXGBE_ACI_DESC_SIZE_IN_DWORDS; i++) { + raw_desc[i] = IXGBE_READ_REG(hw, IXGBE_PF_HIDA(i)); + raw_desc[i] = raw_desc[i]; + } + } + + /* Read async Admin Command response */ + if ((hicr & IXGBE_PF_HICR_EV) && !(hicr & IXGBE_PF_HICR_C)) { + for (i = 0; i < IXGBE_ACI_DESC_SIZE_IN_DWORDS; i++) { + raw_desc[i] = IXGBE_READ_REG(hw, IXGBE_PF_HIDA_2(i)); + raw_desc[i] = raw_desc[i]; + } + } + + /* Handle timeout and invalid state of HICR register */ + if (hicr & IXGBE_PF_HICR_C) + return -ETIME; + + if (!(hicr & IXGBE_PF_HICR_SV) && !(hicr & IXGBE_PF_HICR_EV)) + return -EIO; + + /* For every command other than 0x0014 treat opcode mismatch + * as an error. Response to 0x0014 command read from HIDA_2 + * is a descriptor of an event which is expected to contain + * different opcode than the command. + */ + if (desc->opcode != cpu_to_le16(opcode) && + opcode != ixgbe_aci_opc_get_fw_event) + return -EIO; + + if (desc->retval) { + hw->aci.last_status = (enum ixgbe_aci_err) + le16_to_cpu(desc->retval); + return -EIO; + } + + /* Write a response values to a buf */ + if (valid_buf) { + for (i = 0; i < buf_size / 4; i++) + ((u32 *)buf)[i] = IXGBE_READ_REG(hw, IXGBE_PF_HIBA(i)); + if (buf_tail_size) { + buf_tail = IXGBE_READ_REG(hw, IXGBE_PF_HIBA(i)); + memcpy(buf + buf_size - buf_tail_size, &buf_tail, + buf_tail_size); + } + } + + return 0; +} + +/** + * ixgbe_aci_send_cmd - send FW Admin Command to FW Admin Command Interface + * @hw: pointer to the HW struct + * @desc: descriptor describing the command + * @buf: buffer to use for indirect commands (NULL for direct commands) + * @buf_size: size of buffer for indirect commands (0 for direct commands) + * + * Helper function to send FW Admin Commands to the FW Admin Command Interface. + * + * Retry sending the FW Admin Command multiple times to the FW ACI + * if the EBUSY Admin Command error is returned. + * + * Return: the exit code of the operation. + */ +int ixgbe_aci_send_cmd(struct ixgbe_hw *hw, struct ixgbe_aci_desc *desc, + void *buf, u16 buf_size) +{ + u16 opcode = le16_to_cpu(desc->opcode); + struct ixgbe_aci_desc desc_cpy; + enum ixgbe_aci_err last_status; + u8 idx = 0, *buf_cpy = NULL; + bool is_cmd_for_retry; + unsigned long timeout; + int err; + + is_cmd_for_retry = ixgbe_should_retry_aci_send_cmd_execute(opcode); + if (is_cmd_for_retry) { + if (buf) { + buf_cpy = kmalloc(buf_size, GFP_KERNEL); + if (!buf_cpy) + return -ENOMEM; + *buf_cpy = *(u8 *)buf; + } + desc_cpy = *desc; + } + + timeout = jiffies + msecs_to_jiffies(IXGBE_ACI_SEND_TIMEOUT_MS); + do { + mutex_lock(&hw->aci.lock); + err = ixgbe_aci_send_cmd_execute(hw, desc, buf, buf_size); + last_status = hw->aci.last_status; + mutex_unlock(&hw->aci.lock); + + if (!is_cmd_for_retry || !err || + last_status != IXGBE_ACI_RC_EBUSY) + break; + + if (buf) + memcpy(buf, buf_cpy, buf_size); + *desc = desc_cpy; + + msleep(IXGBE_ACI_SEND_DELAY_TIME_MS); + } while (++idx < IXGBE_ACI_SEND_MAX_EXECUTE && + time_before(jiffies, timeout)); + + kfree(buf_cpy); + + return err; +} + +/** + * ixgbe_aci_check_event_pending - check if there are any pending events + * @hw: pointer to the HW struct + * + * Determine if there are any pending events. + * + * Return: true if there are any currently pending events + * otherwise false. + */ +bool ixgbe_aci_check_event_pending(struct ixgbe_hw *hw) +{ + u32 ep_bit_mask = hw->bus.func ? GL_FWSTS_EP_PF1 : GL_FWSTS_EP_PF0; + u32 fwsts = IXGBE_READ_REG(hw, GL_FWSTS); + + return (fwsts & ep_bit_mask) ? true : false; +} + +/** + * ixgbe_aci_get_event - get an event from ACI + * @hw: pointer to the HW struct + * @e: event information structure + * @pending: optional flag signaling that there are more pending events + * + * Obtain an event from ACI and return its content + * through 'e' using ACI command (0x0014). + * Provide information if there are more events + * to retrieve through 'pending'. + * + * Return: the exit code of the operation. + */ +int ixgbe_aci_get_event(struct ixgbe_hw *hw, struct ixgbe_aci_event *e, + bool *pending) +{ + struct ixgbe_aci_desc desc; + int err; + + if (!e || (!e->msg_buf && e->buf_len)) + return -EINVAL; + + mutex_lock(&hw->aci.lock); + + /* Check if there are any events pending */ + if (!ixgbe_aci_check_event_pending(hw)) { + err = -ENOENT; + goto aci_get_event_exit; + } + + /* Obtain pending event */ + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_fw_event); + err = ixgbe_aci_send_cmd_execute(hw, &desc, e->msg_buf, e->buf_len); + if (err) + goto aci_get_event_exit; + + /* Returned 0x0014 opcode indicates that no event was obtained */ + if (desc.opcode == cpu_to_le16(ixgbe_aci_opc_get_fw_event)) { + err = -ENOENT; + goto aci_get_event_exit; + } + + /* Determine size of event data */ + e->msg_len = min_t(u16, le16_to_cpu(desc.datalen), e->buf_len); + /* Write event descriptor to event info structure */ + memcpy(&e->desc, &desc, sizeof(e->desc)); + + /* Check if there are any further events pending */ + if (pending) + *pending = ixgbe_aci_check_event_pending(hw); + +aci_get_event_exit: + mutex_unlock(&hw->aci.lock); + + return err; +} + +/** + * ixgbe_fill_dflt_direct_cmd_desc - fill ACI descriptor with default values. + * @desc: pointer to the temp descriptor (non DMA mem) + * @opcode: the opcode can be used to decide which flags to turn off or on + * + * Helper function to fill the descriptor desc with default values + * and the provided opcode. + */ +void ixgbe_fill_dflt_direct_cmd_desc(struct ixgbe_aci_desc *desc, u16 opcode) +{ + /* Zero out the desc. */ + memset(desc, 0, sizeof(*desc)); + desc->opcode = cpu_to_le16(opcode); + desc->flags = cpu_to_le16(IXGBE_ACI_FLAG_SI); +} + +/** + * ixgbe_aci_get_fw_ver - Get the firmware version + * @hw: pointer to the HW struct + * + * Get the firmware version using ACI command (0x0001). + * + * Return: the exit code of the operation. + */ +static int ixgbe_aci_get_fw_ver(struct ixgbe_hw *hw) +{ + struct ixgbe_aci_cmd_get_ver *resp; + struct ixgbe_aci_desc desc; + int err; + + resp = &desc.params.get_ver; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_ver); + + err = ixgbe_aci_send_cmd(hw, &desc, NULL, 0); + if (!err) { + hw->fw_branch = resp->fw_branch; + hw->fw_maj_ver = resp->fw_major; + hw->fw_min_ver = resp->fw_minor; + hw->fw_patch = resp->fw_patch; + hw->fw_build = le32_to_cpu(resp->fw_build); + hw->api_branch = resp->api_branch; + hw->api_maj_ver = resp->api_major; + hw->api_min_ver = resp->api_minor; + hw->api_patch = resp->api_patch; + } + + return err; +} + +/** + * ixgbe_aci_req_res - request a common resource + * @hw: pointer to the HW struct + * @res: resource ID + * @access: access type + * @sdp_number: resource number + * @timeout: the maximum time in ms that the driver may hold the resource + * + * Requests a common resource using the ACI command (0x0008). + * Specifies the maximum time the driver may hold the resource. + * If the requested resource is currently occupied by some other driver, + * a busy return value is returned and the timeout field value indicates the + * maximum time the current owner has to free it. + * + * Return: the exit code of the operation. + */ +static int ixgbe_aci_req_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res, + enum ixgbe_aci_res_access_type access, + u8 sdp_number, u32 *timeout) +{ + struct ixgbe_aci_cmd_req_res *cmd_resp; + struct ixgbe_aci_desc desc; + int err; + + cmd_resp = &desc.params.res_owner; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_req_res); + + cmd_resp->res_id = cpu_to_le16(res); + cmd_resp->access_type = cpu_to_le16(access); + cmd_resp->res_number = cpu_to_le32(sdp_number); + cmd_resp->timeout = cpu_to_le32(*timeout); + *timeout = 0; + + err = ixgbe_aci_send_cmd(hw, &desc, NULL, 0); + + /* If the resource is held by some other driver, the command completes + * with a busy return value and the timeout field indicates the maximum + * time the current owner of the resource has to free it. + */ + if (!err || hw->aci.last_status == IXGBE_ACI_RC_EBUSY) + *timeout = le32_to_cpu(cmd_resp->timeout); + + return err; +} + +/** + * ixgbe_aci_release_res - release a common resource using ACI + * @hw: pointer to the HW struct + * @res: resource ID + * @sdp_number: resource number + * + * Release a common resource using ACI command (0x0009). + * + * Return: the exit code of the operation. + */ +static int ixgbe_aci_release_res(struct ixgbe_hw *hw, + enum ixgbe_aci_res_ids res, u8 sdp_number) +{ + struct ixgbe_aci_cmd_req_res *cmd; + struct ixgbe_aci_desc desc; + + cmd = &desc.params.res_owner; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_release_res); + + cmd->res_id = cpu_to_le16(res); + cmd->res_number = cpu_to_le32(sdp_number); + + return ixgbe_aci_send_cmd(hw, &desc, NULL, 0); +} + +/** + * ixgbe_acquire_res - acquire the ownership of a resource + * @hw: pointer to the HW structure + * @res: resource ID + * @access: access type (read or write) + * @timeout: timeout in milliseconds + * + * Make an attempt to acquire the ownership of a resource using + * the ixgbe_aci_req_res to utilize ACI. + * In case if some other driver has previously acquired the resource and + * performed any necessary updates, the -EALREADY is returned, + * and the caller does not obtain the resource and has no further work to do. + * If needed, the function will poll until the current lock owner timeouts. + * + * Return: the exit code of the operation. + */ +int ixgbe_acquire_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res, + enum ixgbe_aci_res_access_type access, u32 timeout) +{ +#define IXGBE_RES_POLLING_DELAY_MS 10 + u32 delay = IXGBE_RES_POLLING_DELAY_MS; + u32 res_timeout = timeout; + u32 retry_timeout; + int err; + + err = ixgbe_aci_req_res(hw, res, access, 0, &res_timeout); + + /* A return code of -EALREADY means that another driver has + * previously acquired the resource and performed any necessary updates; + * in this case the caller does not obtain the resource and has no + * further work to do. + */ + if (err == -EALREADY) + return err; + + /* If necessary, poll until the current lock owner timeouts. + * Set retry_timeout to the timeout value reported by the FW in the + * response to the "Request Resource Ownership" (0x0008) Admin Command + * as it indicates the maximum time the current owner of the resource + * is allowed to hold it. + */ + retry_timeout = res_timeout; + while (err && retry_timeout && res_timeout) { + msleep(delay); + retry_timeout = (retry_timeout > delay) ? + retry_timeout - delay : 0; + err = ixgbe_aci_req_res(hw, res, access, 0, &res_timeout); + + /* Success - lock acquired. + * -EALREADY - lock free, no work to do. + */ + if (!err || err == -EALREADY) + break; + } + + return err; +} + +/** + * ixgbe_release_res - release a common resource + * @hw: pointer to the HW structure + * @res: resource ID + * + * Release a common resource using ixgbe_aci_release_res. + */ +void ixgbe_release_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res) +{ + u32 total_delay = 0; + int err; + + err = ixgbe_aci_release_res(hw, res, 0); + + /* There are some rare cases when trying to release the resource + * results in an admin command timeout, so handle them correctly. + */ + while (err == -ETIME && + total_delay < IXGBE_ACI_RELEASE_RES_TIMEOUT) { + usleep_range(1000, 1500); + err = ixgbe_aci_release_res(hw, res, 0); + total_delay++; + } +} + +/** + * ixgbe_parse_e610_caps - Parse common device/function capabilities + * @hw: pointer to the HW struct + * @caps: pointer to common capabilities structure + * @elem: the capability element to parse + * @prefix: message prefix for tracing capabilities + * + * Given a capability element, extract relevant details into the common + * capability structure. + * + * Return: true if the capability matches one of the common capability ids, + * false otherwise. + */ +static bool ixgbe_parse_e610_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_caps *caps, + struct ixgbe_aci_cmd_list_caps_elem *elem, + const char *prefix) +{ + u32 logical_id = le32_to_cpu(elem->logical_id); + u32 phys_id = le32_to_cpu(elem->phys_id); + u32 number = le32_to_cpu(elem->number); + u16 cap = le16_to_cpu(elem->cap); + + switch (cap) { + case IXGBE_ACI_CAPS_VALID_FUNCTIONS: + caps->valid_functions = number; + break; + case IXGBE_ACI_CAPS_SRIOV: + caps->sr_iov_1_1 = (number == 1); + break; + case IXGBE_ACI_CAPS_VMDQ: + caps->vmdq = (number == 1); + break; + case IXGBE_ACI_CAPS_DCB: + caps->dcb = (number == 1); + caps->active_tc_bitmap = logical_id; + caps->maxtc = phys_id; + break; + case IXGBE_ACI_CAPS_RSS: + caps->rss_table_size = number; + caps->rss_table_entry_width = logical_id; + break; + case IXGBE_ACI_CAPS_RXQS: + caps->num_rxq = number; + caps->rxq_first_id = phys_id; + break; + case IXGBE_ACI_CAPS_TXQS: + caps->num_txq = number; + caps->txq_first_id = phys_id; + break; + case IXGBE_ACI_CAPS_MSIX: + caps->num_msix_vectors = number; + caps->msix_vector_first_id = phys_id; + break; + case IXGBE_ACI_CAPS_NVM_VER: + break; + case IXGBE_ACI_CAPS_PENDING_NVM_VER: + caps->nvm_update_pending_nvm = true; + break; + case IXGBE_ACI_CAPS_PENDING_OROM_VER: + caps->nvm_update_pending_orom = true; + break; + case IXGBE_ACI_CAPS_PENDING_NET_VER: + caps->nvm_update_pending_netlist = true; + break; + case IXGBE_ACI_CAPS_NVM_MGMT: + caps->nvm_unified_update = + (number & IXGBE_NVM_MGMT_UNIFIED_UPD_SUPPORT) ? + true : false; + break; + case IXGBE_ACI_CAPS_MAX_MTU: + caps->max_mtu = number; + break; + case IXGBE_ACI_CAPS_PCIE_RESET_AVOIDANCE: + caps->pcie_reset_avoidance = (number > 0); + break; + case IXGBE_ACI_CAPS_POST_UPDATE_RESET_RESTRICT: + caps->reset_restrict_support = (number == 1); + break; + case IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG0: + case IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG1: + case IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG2: + case IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG3: + { + u8 index = cap - IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG0; + + caps->ext_topo_dev_img_ver_high[index] = number; + caps->ext_topo_dev_img_ver_low[index] = logical_id; + caps->ext_topo_dev_img_part_num[index] = + FIELD_GET(IXGBE_EXT_TOPO_DEV_IMG_PART_NUM_M, phys_id); + caps->ext_topo_dev_img_load_en[index] = + (phys_id & IXGBE_EXT_TOPO_DEV_IMG_LOAD_EN) != 0; + caps->ext_topo_dev_img_prog_en[index] = + (phys_id & IXGBE_EXT_TOPO_DEV_IMG_PROG_EN) != 0; + break; + } + default: + /* Not one of the recognized common capabilities */ + return false; + } + + return true; +} + +/** + * ixgbe_parse_valid_functions_cap - Parse IXGBE_ACI_CAPS_VALID_FUNCTIONS caps + * @hw: pointer to the HW struct + * @dev_p: pointer to device capabilities structure + * @cap: capability element to parse + * + * Parse IXGBE_ACI_CAPS_VALID_FUNCTIONS for device capabilities. + */ +static void +ixgbe_parse_valid_functions_cap(struct ixgbe_hw *hw, + struct ixgbe_hw_dev_caps *dev_p, + struct ixgbe_aci_cmd_list_caps_elem *cap) +{ + dev_p->num_funcs = hweight32(le32_to_cpu(cap->number)); +} + +/** + * ixgbe_parse_vf_dev_caps - Parse IXGBE_ACI_CAPS_VF device caps + * @hw: pointer to the HW struct + * @dev_p: pointer to device capabilities structure + * @cap: capability element to parse + * + * Parse IXGBE_ACI_CAPS_VF for device capabilities. + */ +static void ixgbe_parse_vf_dev_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_dev_caps *dev_p, + struct ixgbe_aci_cmd_list_caps_elem *cap) +{ + dev_p->num_vfs_exposed = le32_to_cpu(cap->number); +} + +/** + * ixgbe_parse_vsi_dev_caps - Parse IXGBE_ACI_CAPS_VSI device caps + * @hw: pointer to the HW struct + * @dev_p: pointer to device capabilities structure + * @cap: capability element to parse + * + * Parse IXGBE_ACI_CAPS_VSI for device capabilities. + */ +static void ixgbe_parse_vsi_dev_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_dev_caps *dev_p, + struct ixgbe_aci_cmd_list_caps_elem *cap) +{ + dev_p->num_vsi_allocd_to_host = le32_to_cpu(cap->number); +} + +/** + * ixgbe_parse_fdir_dev_caps - Parse IXGBE_ACI_CAPS_FD device caps + * @hw: pointer to the HW struct + * @dev_p: pointer to device capabilities structure + * @cap: capability element to parse + * + * Parse IXGBE_ACI_CAPS_FD for device capabilities. + */ +static void ixgbe_parse_fdir_dev_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_dev_caps *dev_p, + struct ixgbe_aci_cmd_list_caps_elem *cap) +{ + dev_p->num_flow_director_fltr = le32_to_cpu(cap->number); +} + +/** + * ixgbe_parse_dev_caps - Parse device capabilities + * @hw: pointer to the HW struct + * @dev_p: pointer to device capabilities structure + * @buf: buffer containing the device capability records + * @cap_count: the number of capabilities + * + * Helper device to parse device (0x000B) capabilities list. For + * capabilities shared between device and function, this relies on + * ixgbe_parse_e610_caps. + * + * Loop through the list of provided capabilities and extract the relevant + * data into the device capabilities structured. + */ +static void ixgbe_parse_dev_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_dev_caps *dev_p, + void *buf, u32 cap_count) +{ + struct ixgbe_aci_cmd_list_caps_elem *cap_resp; + u32 i; + + cap_resp = (struct ixgbe_aci_cmd_list_caps_elem *)buf; + + memset(dev_p, 0, sizeof(*dev_p)); + + for (i = 0; i < cap_count; i++) { + u16 cap = le16_to_cpu(cap_resp[i].cap); + + ixgbe_parse_e610_caps(hw, &dev_p->common_cap, &cap_resp[i], + "dev caps"); + + switch (cap) { + case IXGBE_ACI_CAPS_VALID_FUNCTIONS: + ixgbe_parse_valid_functions_cap(hw, dev_p, + &cap_resp[i]); + break; + case IXGBE_ACI_CAPS_VF: + ixgbe_parse_vf_dev_caps(hw, dev_p, &cap_resp[i]); + break; + case IXGBE_ACI_CAPS_VSI: + ixgbe_parse_vsi_dev_caps(hw, dev_p, &cap_resp[i]); + break; + case IXGBE_ACI_CAPS_FD: + ixgbe_parse_fdir_dev_caps(hw, dev_p, &cap_resp[i]); + break; + default: + /* Don't list common capabilities as unknown */ + break; + } + } +} + +/** + * ixgbe_parse_vf_func_caps - Parse IXGBE_ACI_CAPS_VF function caps + * @hw: pointer to the HW struct + * @func_p: pointer to function capabilities structure + * @cap: pointer to the capability element to parse + * + * Extract function capabilities for IXGBE_ACI_CAPS_VF. + */ +static void ixgbe_parse_vf_func_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_func_caps *func_p, + struct ixgbe_aci_cmd_list_caps_elem *cap) +{ + func_p->num_allocd_vfs = le32_to_cpu(cap->number); + func_p->vf_base_id = le32_to_cpu(cap->logical_id); +} + +/** + * ixgbe_get_num_per_func - determine number of resources per PF + * @hw: pointer to the HW structure + * @max: value to be evenly split between each PF + * + * Determine the number of valid functions by going through the bitmap returned + * from parsing capabilities and use this to calculate the number of resources + * per PF based on the max value passed in. + * + * Return: the number of resources per PF or 0, if no PH are available. + */ +static u32 ixgbe_get_num_per_func(struct ixgbe_hw *hw, u32 max) +{ +#define IXGBE_CAPS_VALID_FUNCS_M GENMASK(7, 0) + u8 funcs = hweight8(hw->dev_caps.common_cap.valid_functions & + IXGBE_CAPS_VALID_FUNCS_M); + + return funcs ? (max / funcs) : 0; +} + +/** + * ixgbe_parse_vsi_func_caps - Parse IXGBE_ACI_CAPS_VSI function caps + * @hw: pointer to the HW struct + * @func_p: pointer to function capabilities structure + * @cap: pointer to the capability element to parse + * + * Extract function capabilities for IXGBE_ACI_CAPS_VSI. + */ +static void ixgbe_parse_vsi_func_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_func_caps *func_p, + struct ixgbe_aci_cmd_list_caps_elem *cap) +{ + func_p->guar_num_vsi = ixgbe_get_num_per_func(hw, IXGBE_MAX_VSI); +} + +/** + * ixgbe_parse_func_caps - Parse function capabilities + * @hw: pointer to the HW struct + * @func_p: pointer to function capabilities structure + * @buf: buffer containing the function capability records + * @cap_count: the number of capabilities + * + * Helper function to parse function (0x000A) capabilities list. For + * capabilities shared between device and function, this relies on + * ixgbe_parse_e610_caps. + * + * Loop through the list of provided capabilities and extract the relevant + * data into the function capabilities structured. + */ +static void ixgbe_parse_func_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_func_caps *func_p, + void *buf, u32 cap_count) +{ + struct ixgbe_aci_cmd_list_caps_elem *cap_resp; + u32 i; + + cap_resp = (struct ixgbe_aci_cmd_list_caps_elem *)buf; + + memset(func_p, 0, sizeof(*func_p)); + + for (i = 0; i < cap_count; i++) { + u16 cap = le16_to_cpu(cap_resp[i].cap); + + ixgbe_parse_e610_caps(hw, &func_p->common_cap, + &cap_resp[i], "func caps"); + + switch (cap) { + case IXGBE_ACI_CAPS_VF: + ixgbe_parse_vf_func_caps(hw, func_p, &cap_resp[i]); + break; + case IXGBE_ACI_CAPS_VSI: + ixgbe_parse_vsi_func_caps(hw, func_p, &cap_resp[i]); + break; + default: + /* Don't list common capabilities as unknown */ + break; + } + } +} + +/** + * ixgbe_aci_list_caps - query function/device capabilities + * @hw: pointer to the HW struct + * @buf: a buffer to hold the capabilities + * @buf_size: size of the buffer + * @cap_count: if not NULL, set to the number of capabilities reported + * @opc: capabilities type to discover, device or function + * + * Get the function (0x000A) or device (0x000B) capabilities description from + * firmware and store it in the buffer. + * + * If the cap_count pointer is not NULL, then it is set to the number of + * capabilities firmware will report. Note that if the buffer size is too + * small, it is possible the command will return -ENOMEM. The + * cap_count will still be updated in this case. It is recommended that the + * buffer size be set to IXGBE_ACI_MAX_BUFFER_SIZE (the largest possible + * buffer that firmware could return) to avoid this. + * + * Return: the exit code of the operation. + * Exit code of -ENOMEM means the buffer size is too small. + */ +int ixgbe_aci_list_caps(struct ixgbe_hw *hw, void *buf, u16 buf_size, + u32 *cap_count, enum ixgbe_aci_opc opc) +{ + struct ixgbe_aci_cmd_list_caps *cmd; + struct ixgbe_aci_desc desc; + int err; + + cmd = &desc.params.get_cap; + + if (opc != ixgbe_aci_opc_list_func_caps && + opc != ixgbe_aci_opc_list_dev_caps) + return -EINVAL; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, opc); + err = ixgbe_aci_send_cmd(hw, &desc, buf, buf_size); + + if (cap_count) + *cap_count = le32_to_cpu(cmd->count); + + return err; +} + +/** + * ixgbe_discover_dev_caps - Read and extract device capabilities + * @hw: pointer to the hardware structure + * @dev_caps: pointer to device capabilities structure + * + * Read the device capabilities and extract them into the dev_caps structure + * for later use. + * + * Return: the exit code of the operation. + */ +int ixgbe_discover_dev_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_dev_caps *dev_caps) +{ + u32 cap_count; + u8 *cbuf; + int err; + + cbuf = kzalloc(IXGBE_ACI_MAX_BUFFER_SIZE, GFP_KERNEL); + if (!cbuf) + return -ENOMEM; + + /* Although the driver doesn't know the number of capabilities the + * device will return, we can simply send a 4KB buffer, the maximum + * possible size that firmware can return. + */ + cap_count = IXGBE_ACI_MAX_BUFFER_SIZE / + sizeof(struct ixgbe_aci_cmd_list_caps_elem); + + err = ixgbe_aci_list_caps(hw, cbuf, IXGBE_ACI_MAX_BUFFER_SIZE, + &cap_count, + ixgbe_aci_opc_list_dev_caps); + if (!err) + ixgbe_parse_dev_caps(hw, dev_caps, cbuf, cap_count); + + kfree(cbuf); + + return 0; +} + +/** + * ixgbe_discover_func_caps - Read and extract function capabilities + * @hw: pointer to the hardware structure + * @func_caps: pointer to function capabilities structure + * + * Read the function capabilities and extract them into the func_caps structure + * for later use. + * + * Return: the exit code of the operation. + */ +int ixgbe_discover_func_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_func_caps *func_caps) +{ + u32 cap_count; + u8 *cbuf; + int err; + + cbuf = kzalloc(IXGBE_ACI_MAX_BUFFER_SIZE, GFP_KERNEL); + if (!cbuf) + return -ENOMEM; + + /* Although the driver doesn't know the number of capabilities the + * device will return, we can simply send a 4KB buffer, the maximum + * possible size that firmware can return. + */ + cap_count = IXGBE_ACI_MAX_BUFFER_SIZE / + sizeof(struct ixgbe_aci_cmd_list_caps_elem); + + err = ixgbe_aci_list_caps(hw, cbuf, IXGBE_ACI_MAX_BUFFER_SIZE, + &cap_count, + ixgbe_aci_opc_list_func_caps); + if (!err) + ixgbe_parse_func_caps(hw, func_caps, cbuf, cap_count); + + kfree(cbuf); + + return 0; +} + +/** + * ixgbe_get_caps - get info about the HW + * @hw: pointer to the hardware structure + * + * Retrieve both device and function capabilities. + * + * Return: the exit code of the operation. + */ +int ixgbe_get_caps(struct ixgbe_hw *hw) +{ + int err; + + err = ixgbe_discover_dev_caps(hw, &hw->dev_caps); + if (err) + return err; + + return ixgbe_discover_func_caps(hw, &hw->func_caps); +} + +/** + * ixgbe_aci_disable_rxen - disable RX + * @hw: pointer to the HW struct + * + * Request a safe disable of Receive Enable using ACI command (0x000C). + * + * Return: the exit code of the operation. + */ +int ixgbe_aci_disable_rxen(struct ixgbe_hw *hw) +{ + struct ixgbe_aci_cmd_disable_rxen *cmd; + struct ixgbe_aci_desc desc; + + cmd = &desc.params.disable_rxen; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_disable_rxen); + + cmd->lport_num = hw->bus.func; + + return ixgbe_aci_send_cmd(hw, &desc, NULL, 0); +} + +/** + * ixgbe_aci_get_phy_caps - returns PHY capabilities + * @hw: pointer to the HW struct + * @qual_mods: report qualified modules + * @report_mode: report mode capabilities + * @pcaps: structure for PHY capabilities to be filled + * + * Returns the various PHY capabilities supported on the Port + * using ACI command (0x0600). + * + * Return: the exit code of the operation. + */ +int ixgbe_aci_get_phy_caps(struct ixgbe_hw *hw, bool qual_mods, u8 report_mode, + struct ixgbe_aci_cmd_get_phy_caps_data *pcaps) +{ + struct ixgbe_aci_cmd_get_phy_caps *cmd; + u16 pcaps_size = sizeof(*pcaps); + struct ixgbe_aci_desc desc; + int err; + + cmd = &desc.params.get_phy; + + if (!pcaps || (report_mode & ~IXGBE_ACI_REPORT_MODE_M)) + return -EINVAL; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_phy_caps); + + if (qual_mods) + cmd->param0 |= cpu_to_le16(IXGBE_ACI_GET_PHY_RQM); + + cmd->param0 |= cpu_to_le16(report_mode); + err = ixgbe_aci_send_cmd(hw, &desc, pcaps, pcaps_size); + if (!err && report_mode == IXGBE_ACI_REPORT_TOPO_CAP_MEDIA) { + hw->phy.phy_type_low = le64_to_cpu(pcaps->phy_type_low); + hw->phy.phy_type_high = le64_to_cpu(pcaps->phy_type_high); + memcpy(hw->link.link_info.module_type, &pcaps->module_type, + sizeof(hw->link.link_info.module_type)); + } + + return err; +} + +/** + * ixgbe_copy_phy_caps_to_cfg - Copy PHY ability data to configuration data + * @caps: PHY ability structure to copy data from + * @cfg: PHY configuration structure to copy data to + * + * Helper function to copy data from PHY capabilities data structure + * to PHY configuration data structure + */ +void ixgbe_copy_phy_caps_to_cfg(struct ixgbe_aci_cmd_get_phy_caps_data *caps, + struct ixgbe_aci_cmd_set_phy_cfg_data *cfg) +{ + if (!caps || !cfg) + return; + + memset(cfg, 0, sizeof(*cfg)); + cfg->phy_type_low = caps->phy_type_low; + cfg->phy_type_high = caps->phy_type_high; + cfg->caps = caps->caps; + cfg->low_power_ctrl_an = caps->low_power_ctrl_an; + cfg->eee_cap = caps->eee_cap; + cfg->eeer_value = caps->eeer_value; + cfg->link_fec_opt = caps->link_fec_options; + cfg->module_compliance_enforcement = + caps->module_compliance_enforcement; +} + +/** + * ixgbe_aci_set_phy_cfg - set PHY configuration + * @hw: pointer to the HW struct + * @cfg: structure with PHY configuration data to be set + * + * Set the various PHY configuration parameters supported on the Port + * using ACI command (0x0601). + * One or more of the Set PHY config parameters may be ignored in an MFP + * mode as the PF may not have the privilege to set some of the PHY Config + * parameters. + * + * Return: the exit code of the operation. + */ +int ixgbe_aci_set_phy_cfg(struct ixgbe_hw *hw, + struct ixgbe_aci_cmd_set_phy_cfg_data *cfg) +{ + struct ixgbe_aci_desc desc; + int err; + + if (!cfg) + return -EINVAL; + + /* Ensure that only valid bits of cfg->caps can be turned on. */ + cfg->caps &= IXGBE_ACI_PHY_ENA_VALID_MASK; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_set_phy_cfg); + desc.params.set_phy.lport_num = hw->bus.func; + desc.flags |= cpu_to_le16(IXGBE_ACI_FLAG_RD); + + err = ixgbe_aci_send_cmd(hw, &desc, cfg, sizeof(*cfg)); + if (!err) + hw->phy.curr_user_phy_cfg = *cfg; + + return err; +} + +/** + * ixgbe_aci_set_link_restart_an - set up link and restart AN + * @hw: pointer to the HW struct + * @ena_link: if true: enable link, if false: disable link + * + * Function sets up the link and restarts the Auto-Negotiation over the link. + * + * Return: the exit code of the operation. + */ +int ixgbe_aci_set_link_restart_an(struct ixgbe_hw *hw, bool ena_link) +{ + struct ixgbe_aci_cmd_restart_an *cmd; + struct ixgbe_aci_desc desc; + + cmd = &desc.params.restart_an; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_restart_an); + + cmd->cmd_flags = IXGBE_ACI_RESTART_AN_LINK_RESTART; + cmd->lport_num = hw->bus.func; + if (ena_link) + cmd->cmd_flags |= IXGBE_ACI_RESTART_AN_LINK_ENABLE; + else + cmd->cmd_flags &= ~IXGBE_ACI_RESTART_AN_LINK_ENABLE; + + return ixgbe_aci_send_cmd(hw, &desc, NULL, 0); +} + +/** + * ixgbe_is_media_cage_present - check if media cage is present + * @hw: pointer to the HW struct + * + * Identify presence of media cage using the ACI command (0x06E0). + * + * Return: true if media cage is present, else false. If no cage, then + * media type is backplane or BASE-T. + */ +static bool ixgbe_is_media_cage_present(struct ixgbe_hw *hw) +{ + struct ixgbe_aci_cmd_get_link_topo *cmd; + struct ixgbe_aci_desc desc; + + cmd = &desc.params.get_link_topo; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_link_topo); + + cmd->addr.topo_params.node_type_ctx = + FIELD_PREP(IXGBE_ACI_LINK_TOPO_NODE_CTX_M, + IXGBE_ACI_LINK_TOPO_NODE_CTX_PORT); + + /* Set node type. */ + cmd->addr.topo_params.node_type_ctx |= + FIELD_PREP(IXGBE_ACI_LINK_TOPO_NODE_TYPE_M, + IXGBE_ACI_LINK_TOPO_NODE_TYPE_CAGE); + + /* Node type cage can be used to determine if cage is present. If AQC + * returns error (ENOENT), then no cage present. If no cage present then + * connection type is backplane or BASE-T. + */ + return !ixgbe_aci_get_netlist_node(hw, cmd, NULL, NULL); +} + +/** + * ixgbe_get_media_type_from_phy_type - Gets media type based on phy type + * @hw: pointer to the HW struct + * + * Try to identify the media type based on the phy type. + * If more than one media type, the ixgbe_media_type_unknown is returned. + * First, phy_type_low is checked, then phy_type_high. + * If none are identified, the ixgbe_media_type_unknown is returned + * + * Return: type of a media based on phy type in form of enum. + */ +static enum ixgbe_media_type +ixgbe_get_media_type_from_phy_type(struct ixgbe_hw *hw) +{ + struct ixgbe_link_status *hw_link_info; + + if (!hw) + return ixgbe_media_type_unknown; + + hw_link_info = &hw->link.link_info; + if (hw_link_info->phy_type_low && hw_link_info->phy_type_high) + /* If more than one media type is selected, report unknown */ + return ixgbe_media_type_unknown; + + if (hw_link_info->phy_type_low) { + /* 1G SGMII is a special case where some DA cable PHYs + * may show this as an option when it really shouldn't + * be since SGMII is meant to be between a MAC and a PHY + * in a backplane. Try to detect this case and handle it + */ + if (hw_link_info->phy_type_low == IXGBE_PHY_TYPE_LOW_1G_SGMII && + (hw_link_info->module_type[IXGBE_ACI_MOD_TYPE_IDENT] == + IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_ACTIVE || + hw_link_info->module_type[IXGBE_ACI_MOD_TYPE_IDENT] == + IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_PASSIVE)) + return ixgbe_media_type_da; + + switch (hw_link_info->phy_type_low) { + case IXGBE_PHY_TYPE_LOW_1000BASE_SX: + case IXGBE_PHY_TYPE_LOW_1000BASE_LX: + case IXGBE_PHY_TYPE_LOW_10GBASE_SR: + case IXGBE_PHY_TYPE_LOW_10GBASE_LR: + case IXGBE_PHY_TYPE_LOW_25GBASE_SR: + case IXGBE_PHY_TYPE_LOW_25GBASE_LR: + return ixgbe_media_type_fiber; + case IXGBE_PHY_TYPE_LOW_10G_SFI_AOC_ACC: + case IXGBE_PHY_TYPE_LOW_25G_AUI_AOC_ACC: + return ixgbe_media_type_fiber; + case IXGBE_PHY_TYPE_LOW_100BASE_TX: + case IXGBE_PHY_TYPE_LOW_1000BASE_T: + case IXGBE_PHY_TYPE_LOW_2500BASE_T: + case IXGBE_PHY_TYPE_LOW_5GBASE_T: + case IXGBE_PHY_TYPE_LOW_10GBASE_T: + case IXGBE_PHY_TYPE_LOW_25GBASE_T: + return ixgbe_media_type_copper; + case IXGBE_PHY_TYPE_LOW_10G_SFI_DA: + case IXGBE_PHY_TYPE_LOW_25GBASE_CR: + case IXGBE_PHY_TYPE_LOW_25GBASE_CR_S: + case IXGBE_PHY_TYPE_LOW_25GBASE_CR1: + return ixgbe_media_type_da; + case IXGBE_PHY_TYPE_LOW_25G_AUI_C2C: + if (ixgbe_is_media_cage_present(hw)) + return ixgbe_media_type_aui; + fallthrough; + case IXGBE_PHY_TYPE_LOW_1000BASE_KX: + case IXGBE_PHY_TYPE_LOW_2500BASE_KX: + case IXGBE_PHY_TYPE_LOW_2500BASE_X: + case IXGBE_PHY_TYPE_LOW_5GBASE_KR: + case IXGBE_PHY_TYPE_LOW_10GBASE_KR_CR1: + case IXGBE_PHY_TYPE_LOW_10G_SFI_C2C: + case IXGBE_PHY_TYPE_LOW_25GBASE_KR: + case IXGBE_PHY_TYPE_LOW_25GBASE_KR1: + case IXGBE_PHY_TYPE_LOW_25GBASE_KR_S: + return ixgbe_media_type_backplane; + } + } else { + switch (hw_link_info->phy_type_high) { + case IXGBE_PHY_TYPE_HIGH_10BASE_T: + return ixgbe_media_type_copper; + } + } + return ixgbe_media_type_unknown; +} + +/** + * ixgbe_update_link_info - update status of the HW network link + * @hw: pointer to the HW struct + * + * Update the status of the HW network link. + * + * Return: the exit code of the operation. + */ +int ixgbe_update_link_info(struct ixgbe_hw *hw) +{ + struct ixgbe_aci_cmd_get_phy_caps_data *pcaps; + struct ixgbe_link_status *li; + int err; + + if (!hw) + return -EINVAL; + + li = &hw->link.link_info; + + err = ixgbe_aci_get_link_info(hw, true, NULL); + if (err) + return err; + + if (!(li->link_info & IXGBE_ACI_MEDIA_AVAILABLE)) + return 0; + + pcaps = kzalloc(sizeof(*pcaps), GFP_KERNEL); + if (!pcaps) + return -ENOMEM; + + err = ixgbe_aci_get_phy_caps(hw, false, IXGBE_ACI_REPORT_TOPO_CAP_MEDIA, + pcaps); + + if (!err) + memcpy(li->module_type, &pcaps->module_type, + sizeof(li->module_type)); + + kfree(pcaps); + + return err; +} + +/** + * ixgbe_get_link_status - get status of the HW network link + * @hw: pointer to the HW struct + * @link_up: pointer to bool (true/false = linkup/linkdown) + * + * Variable link_up is true if link is up, false if link is down. + * The variable link_up is invalid if status is non zero. As a + * result of this call, link status reporting becomes enabled + * + * Return: the exit code of the operation. + */ +int ixgbe_get_link_status(struct ixgbe_hw *hw, bool *link_up) +{ + if (!hw || !link_up) + return -EINVAL; + + if (hw->link.get_link_info) { + int err = ixgbe_update_link_info(hw); + + if (err) + return err; + } + + *link_up = hw->link.link_info.link_info & IXGBE_ACI_LINK_UP; + + return 0; +} + +/** + * ixgbe_aci_get_link_info - get the link status + * @hw: pointer to the HW struct + * @ena_lse: enable/disable LinkStatusEvent reporting + * @link: pointer to link status structure - optional + * + * Get the current Link Status using ACI command (0x607). + * The current link can be optionally provided to update + * the status. + * + * Return: the link status of the adapter. + */ +int ixgbe_aci_get_link_info(struct ixgbe_hw *hw, bool ena_lse, + struct ixgbe_link_status *link) +{ + struct ixgbe_aci_cmd_get_link_status_data link_data = {}; + struct ixgbe_aci_cmd_get_link_status *resp; + struct ixgbe_link_status *li_old, *li; + struct ixgbe_fc_info *hw_fc_info; + struct ixgbe_aci_desc desc; + bool tx_pause, rx_pause; + u8 cmd_flags; + int err; + + if (!hw) + return -EINVAL; + + li_old = &hw->link.link_info_old; + li = &hw->link.link_info; + hw_fc_info = &hw->fc; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_link_status); + cmd_flags = (ena_lse) ? IXGBE_ACI_LSE_ENA : IXGBE_ACI_LSE_DIS; + resp = &desc.params.get_link_status; + resp->cmd_flags = cpu_to_le16(cmd_flags); + resp->lport_num = hw->bus.func; + + err = ixgbe_aci_send_cmd(hw, &desc, &link_data, sizeof(link_data)); + if (err) + return err; + + /* Save off old link status information. */ + *li_old = *li; + + /* Update current link status information. */ + li->link_speed = le16_to_cpu(link_data.link_speed); + li->phy_type_low = le64_to_cpu(link_data.phy_type_low); + li->phy_type_high = le64_to_cpu(link_data.phy_type_high); + li->link_info = link_data.link_info; + li->link_cfg_err = link_data.link_cfg_err; + li->an_info = link_data.an_info; + li->ext_info = link_data.ext_info; + li->max_frame_size = le16_to_cpu(link_data.max_frame_size); + li->fec_info = link_data.cfg & IXGBE_ACI_FEC_MASK; + li->topo_media_conflict = link_data.topo_media_conflict; + li->pacing = link_data.cfg & (IXGBE_ACI_CFG_PACING_M | + IXGBE_ACI_CFG_PACING_TYPE_M); + + /* Update fc info. */ + tx_pause = !!(link_data.an_info & IXGBE_ACI_LINK_PAUSE_TX); + rx_pause = !!(link_data.an_info & IXGBE_ACI_LINK_PAUSE_RX); + if (tx_pause && rx_pause) + hw_fc_info->current_mode = ixgbe_fc_full; + else if (tx_pause) + hw_fc_info->current_mode = ixgbe_fc_tx_pause; + else if (rx_pause) + hw_fc_info->current_mode = ixgbe_fc_rx_pause; + else + hw_fc_info->current_mode = ixgbe_fc_none; + + li->lse_ena = !!(le16_to_cpu(resp->cmd_flags) & + IXGBE_ACI_LSE_IS_ENABLED); + + /* Save link status information. */ + if (link) + *link = *li; + + /* Flag cleared so calling functions don't call AQ again. */ + hw->link.get_link_info = false; + + return 0; +} + +/** + * ixgbe_aci_set_event_mask - set event mask + * @hw: pointer to the HW struct + * @port_num: port number of the physical function + * @mask: event mask to be set + * + * Set the event mask using ACI command (0x0613). + * + * Return: the exit code of the operation. + */ +int ixgbe_aci_set_event_mask(struct ixgbe_hw *hw, u8 port_num, u16 mask) +{ + struct ixgbe_aci_cmd_set_event_mask *cmd; + struct ixgbe_aci_desc desc; + + cmd = &desc.params.set_event_mask; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_set_event_mask); + + cmd->lport_num = port_num; + + cmd->event_mask = cpu_to_le16(mask); + return ixgbe_aci_send_cmd(hw, &desc, NULL, 0); +} + +/** + * ixgbe_configure_lse - enable/disable link status events + * @hw: pointer to the HW struct + * @activate: true for enable lse, false otherwise + * @mask: event mask to be set; a set bit means deactivation of the + * corresponding event + * + * Set the event mask and then enable or disable link status events + * + * Return: the exit code of the operation. + */ +int ixgbe_configure_lse(struct ixgbe_hw *hw, bool activate, u16 mask) +{ + int err; + + err = ixgbe_aci_set_event_mask(hw, (u8)hw->bus.func, mask); + if (err) + return err; + + /* Enabling link status events generation by fw. */ + return ixgbe_aci_get_link_info(hw, activate, NULL); +} + +/** + * ixgbe_start_hw_e610 - Prepare hardware for Tx/Rx + * @hw: pointer to hardware structure + * + * Get firmware version and start the hardware using the generic + * start_hw() and ixgbe_start_hw_gen2() functions. + * + * Return: the exit code of the operation. + */ +static int ixgbe_start_hw_e610(struct ixgbe_hw *hw) +{ + int err; + + err = ixgbe_aci_get_fw_ver(hw); + if (err) + return err; + + err = ixgbe_start_hw_generic(hw); + if (err) + return err; + + ixgbe_start_hw_gen2(hw); + + return 0; +} + +/** + * ixgbe_aci_set_port_id_led - set LED value for the given port + * @hw: pointer to the HW struct + * @orig_mode: set LED original mode + * + * Set LED value for the given port (0x06E9) + * + * Return: the exit code of the operation. + */ +int ixgbe_aci_set_port_id_led(struct ixgbe_hw *hw, bool orig_mode) +{ + struct ixgbe_aci_cmd_set_port_id_led *cmd; + struct ixgbe_aci_desc desc; + + cmd = &desc.params.set_port_id_led; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_set_port_id_led); + + cmd->lport_num = (u8)hw->bus.func; + cmd->lport_num_valid = IXGBE_ACI_PORT_ID_PORT_NUM_VALID; + + if (orig_mode) + cmd->ident_mode = IXGBE_ACI_PORT_IDENT_LED_ORIG; + else + cmd->ident_mode = IXGBE_ACI_PORT_IDENT_LED_BLINK; + + return ixgbe_aci_send_cmd(hw, &desc, NULL, 0); +} + +/** + * ixgbe_get_media_type_e610 - Gets media type + * @hw: pointer to the HW struct + * + * In order to get the media type, the function gets PHY + * capabilities and later on use them to identify the PHY type + * checking phy_type_high and phy_type_low. + * + * Return: the type of media in form of ixgbe_media_type enum + * or ixgbe_media_type_unknown in case of an error. + */ +enum ixgbe_media_type ixgbe_get_media_type_e610(struct ixgbe_hw *hw) +{ + struct ixgbe_aci_cmd_get_phy_caps_data pcaps; + int rc; + + rc = ixgbe_update_link_info(hw); + if (rc) + return ixgbe_media_type_unknown; + + /* If there is no link but PHY (dongle) is available SW should use + * Get PHY Caps admin command instead of Get Link Status, find most + * significant bit that is set in PHY types reported by the command + * and use it to discover media type. + */ + if (!(hw->link.link_info.link_info & IXGBE_ACI_LINK_UP) && + (hw->link.link_info.link_info & IXGBE_ACI_MEDIA_AVAILABLE)) { + int highest_bit; + + /* Get PHY Capabilities */ + rc = ixgbe_aci_get_phy_caps(hw, false, + IXGBE_ACI_REPORT_TOPO_CAP_MEDIA, + &pcaps); + if (rc) + return ixgbe_media_type_unknown; + + highest_bit = fls64(le64_to_cpu(pcaps.phy_type_high)); + if (highest_bit) { + hw->link.link_info.phy_type_high = + BIT_ULL(highest_bit - 1); + hw->link.link_info.phy_type_low = 0; + } else { + highest_bit = fls64(le64_to_cpu(pcaps.phy_type_low)); + if (highest_bit) { + hw->link.link_info.phy_type_low = + BIT_ULL(highest_bit - 1); + hw->link.link_info.phy_type_high = 0; + } + } + } + + /* Based on link status or search above try to discover media type. */ + hw->phy.media_type = ixgbe_get_media_type_from_phy_type(hw); + + return hw->phy.media_type; +} + +/** + * ixgbe_setup_link_e610 - Set up link + * @hw: pointer to hardware structure + * @speed: new link speed + * @autoneg_wait: true when waiting for completion is needed + * + * Set up the link with the specified speed. + * + * Return: the exit code of the operation. + */ +int ixgbe_setup_link_e610(struct ixgbe_hw *hw, ixgbe_link_speed speed, + bool autoneg_wait) +{ + /* Simply request FW to perform proper PHY setup */ + return hw->phy.ops.setup_link_speed(hw, speed, autoneg_wait); +} + +/** + * ixgbe_check_link_e610 - Determine link and speed status + * @hw: pointer to hardware structure + * @speed: pointer to link speed + * @link_up: true when link is up + * @link_up_wait_to_complete: bool used to wait for link up or not + * + * Determine if the link is up and the current link speed + * using ACI command (0x0607). + * + * Return: the exit code of the operation. + */ +int ixgbe_check_link_e610(struct ixgbe_hw *hw, ixgbe_link_speed *speed, + bool *link_up, bool link_up_wait_to_complete) +{ + int err; + u32 i; + + if (!speed || !link_up) + return -EINVAL; + + /* Set get_link_info flag to ensure that fresh + * link information will be obtained from FW + * by sending Get Link Status admin command. + */ + hw->link.get_link_info = true; + + /* Update link information in adapter context. */ + err = ixgbe_get_link_status(hw, link_up); + if (err) + return err; + + /* Wait for link up if it was requested. */ + if (link_up_wait_to_complete && !(*link_up)) { + for (i = 0; i < hw->mac.max_link_up_time; i++) { + msleep(100); + hw->link.get_link_info = true; + err = ixgbe_get_link_status(hw, link_up); + if (err) + return err; + if (*link_up) + break; + } + } + + /* Use link information in adapter context updated by the call + * to ixgbe_get_link_status() to determine current link speed. + * Link speed information is valid only when link up was + * reported by FW. + */ + if (*link_up) { + switch (hw->link.link_info.link_speed) { + case IXGBE_ACI_LINK_SPEED_10MB: + *speed = IXGBE_LINK_SPEED_10_FULL; + break; + case IXGBE_ACI_LINK_SPEED_100MB: + *speed = IXGBE_LINK_SPEED_100_FULL; + break; + case IXGBE_ACI_LINK_SPEED_1000MB: + *speed = IXGBE_LINK_SPEED_1GB_FULL; + break; + case IXGBE_ACI_LINK_SPEED_2500MB: + *speed = IXGBE_LINK_SPEED_2_5GB_FULL; + break; + case IXGBE_ACI_LINK_SPEED_5GB: + *speed = IXGBE_LINK_SPEED_5GB_FULL; + break; + case IXGBE_ACI_LINK_SPEED_10GB: + *speed = IXGBE_LINK_SPEED_10GB_FULL; + break; + default: + *speed = IXGBE_LINK_SPEED_UNKNOWN; + break; + } + } else { + *speed = IXGBE_LINK_SPEED_UNKNOWN; + } + + return 0; +} + +/** + * ixgbe_get_link_capabilities_e610 - Determine link capabilities + * @hw: pointer to hardware structure + * @speed: pointer to link speed + * @autoneg: true when autoneg or autotry is enabled + * + * Determine speed and AN parameters of a link. + * + * Return: the exit code of the operation. + */ +int ixgbe_get_link_capabilities_e610(struct ixgbe_hw *hw, + ixgbe_link_speed *speed, + bool *autoneg) +{ + if (!speed || !autoneg) + return -EINVAL; + + *autoneg = true; + *speed = hw->phy.speeds_supported; + + return 0; +} + +/** + * ixgbe_cfg_phy_fc - Configure PHY Flow Control (FC) data based on FC mode + * @hw: pointer to hardware structure + * @cfg: PHY configuration data to set FC mode + * @req_mode: FC mode to configure + * + * Configures PHY Flow Control according to the provided configuration. + * + * Return: the exit code of the operation. + */ +int ixgbe_cfg_phy_fc(struct ixgbe_hw *hw, + struct ixgbe_aci_cmd_set_phy_cfg_data *cfg, + enum ixgbe_fc_mode req_mode) +{ + u8 pause_mask = 0x0; + + if (!cfg) + return -EINVAL; + + switch (req_mode) { + case ixgbe_fc_full: + pause_mask |= IXGBE_ACI_PHY_EN_TX_LINK_PAUSE; + pause_mask |= IXGBE_ACI_PHY_EN_RX_LINK_PAUSE; + break; + case ixgbe_fc_rx_pause: + pause_mask |= IXGBE_ACI_PHY_EN_RX_LINK_PAUSE; + break; + case ixgbe_fc_tx_pause: + pause_mask |= IXGBE_ACI_PHY_EN_TX_LINK_PAUSE; + break; + default: + break; + } + + /* Clear the old pause settings. */ + cfg->caps &= ~(IXGBE_ACI_PHY_EN_TX_LINK_PAUSE | + IXGBE_ACI_PHY_EN_RX_LINK_PAUSE); + + /* Set the new capabilities. */ + cfg->caps |= pause_mask; + + return 0; +} + +/** + * ixgbe_setup_fc_e610 - Set up flow control + * @hw: pointer to hardware structure + * + * Set up flow control. This has to be done during init time. + * + * Return: the exit code of the operation. + */ +int ixgbe_setup_fc_e610(struct ixgbe_hw *hw) +{ + struct ixgbe_aci_cmd_get_phy_caps_data pcaps = {}; + struct ixgbe_aci_cmd_set_phy_cfg_data cfg = {}; + int err; + + /* Get the current PHY config */ + err = ixgbe_aci_get_phy_caps(hw, false, + IXGBE_ACI_REPORT_ACTIVE_CFG, &pcaps); + if (err) + return err; + + ixgbe_copy_phy_caps_to_cfg(&pcaps, &cfg); + + /* Configure the set PHY data */ + err = ixgbe_cfg_phy_fc(hw, &cfg, hw->fc.requested_mode); + if (err) + return err; + + /* If the capabilities have changed, then set the new config */ + if (cfg.caps != pcaps.caps) { + cfg.caps |= IXGBE_ACI_PHY_ENA_AUTO_LINK_UPDT; + + err = ixgbe_aci_set_phy_cfg(hw, &cfg); + if (err) + return err; + } + + return err; +} + +/** + * ixgbe_fc_autoneg_e610 - Configure flow control + * @hw: pointer to hardware structure + * + * Configure Flow Control. + */ +void ixgbe_fc_autoneg_e610(struct ixgbe_hw *hw) +{ + int err; + + /* Get current link err. + * Current FC mode will be stored in the hw context. + */ + err = ixgbe_aci_get_link_info(hw, false, NULL); + if (err) + goto no_autoneg; + + /* Check if the link is up */ + if (!(hw->link.link_info.link_info & IXGBE_ACI_LINK_UP)) + goto no_autoneg; + + /* Check if auto-negotiation has completed */ + if (!(hw->link.link_info.an_info & IXGBE_ACI_AN_COMPLETED)) + goto no_autoneg; + + hw->fc.fc_was_autonegged = true; + return; + +no_autoneg: + hw->fc.fc_was_autonegged = false; + hw->fc.current_mode = hw->fc.requested_mode; +} + +/** + * ixgbe_disable_rx_e610 - Disable RX unit + * @hw: pointer to hardware structure + * + * Disable RX DMA unit on E610 with use of ACI command (0x000C). + * + * Return: the exit code of the operation. + */ +void ixgbe_disable_rx_e610(struct ixgbe_hw *hw) +{ + u32 rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL); + u32 pfdtxgswc; + int err; + + if (!(rxctrl & IXGBE_RXCTRL_RXEN)) + return; + + pfdtxgswc = IXGBE_READ_REG(hw, IXGBE_PFDTXGSWC); + if (pfdtxgswc & IXGBE_PFDTXGSWC_VT_LBEN) { + pfdtxgswc &= ~IXGBE_PFDTXGSWC_VT_LBEN; + IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, pfdtxgswc); + hw->mac.set_lben = true; + } else { + hw->mac.set_lben = false; + } + + err = ixgbe_aci_disable_rxen(hw); + + /* If we fail - disable RX using register write */ + if (err) { + rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL); + if (rxctrl & IXGBE_RXCTRL_RXEN) { + rxctrl &= ~IXGBE_RXCTRL_RXEN; + IXGBE_WRITE_REG(hw, IXGBE_RXCTRL, rxctrl); + } + } +} + +/** + * ixgbe_fw_recovery_mode_e610 - Check FW NVM recovery mode + * @hw: pointer to hardware structure + * + * Check FW NVM recovery mode by reading the value of + * the dedicated register. + * + * Return: true if FW is in recovery mode, otherwise false. + */ +static bool ixgbe_fw_recovery_mode_e610(struct ixgbe_hw *hw) +{ + u32 fwsm = IXGBE_READ_REG(hw, IXGBE_GL_MNG_FWSM); + + return !!(fwsm & IXGBE_GL_MNG_FWSM_RECOVERY_M); +} + +/** + * ixgbe_fw_rollback_mode_e610 - Check FW NVM rollback mode + * @hw: pointer to hardware structure + * + * Check FW NVM rollback mode by reading the value of + * the dedicated register. + * + * Return: true if FW is in rollback mode, otherwise false. + */ +static bool ixgbe_fw_rollback_mode_e610(struct ixgbe_hw *hw) +{ + u32 fwsm = IXGBE_READ_REG(hw, IXGBE_GL_MNG_FWSM); + + return !!(fwsm & IXGBE_GL_MNG_FWSM_ROLLBACK_M); +} + +/** + * ixgbe_init_phy_ops_e610 - PHY specific init + * @hw: pointer to hardware structure + * + * Initialize any function pointers that were not able to be + * set during init_shared_code because the PHY type was not known. + * + * Return: the exit code of the operation. + */ +int ixgbe_init_phy_ops_e610(struct ixgbe_hw *hw) +{ + struct ixgbe_mac_info *mac = &hw->mac; + struct ixgbe_phy_info *phy = &hw->phy; + + if (mac->ops.get_media_type(hw) == ixgbe_media_type_copper) + phy->ops.set_phy_power = ixgbe_set_phy_power_e610; + else + phy->ops.set_phy_power = NULL; + + /* Identify the PHY */ + return phy->ops.identify(hw); +} + +/** + * ixgbe_identify_phy_e610 - Identify PHY + * @hw: pointer to hardware structure + * + * Determine PHY type, supported speeds and PHY ID. + * + * Return: the exit code of the operation. + */ +int ixgbe_identify_phy_e610(struct ixgbe_hw *hw) +{ + struct ixgbe_aci_cmd_get_phy_caps_data pcaps; + u64 phy_type_low, phy_type_high; + int err; + + /* Set PHY type */ + hw->phy.type = ixgbe_phy_fw; + + err = ixgbe_aci_get_phy_caps(hw, false, + IXGBE_ACI_REPORT_TOPO_CAP_MEDIA, &pcaps); + if (err) + return err; + + if (!(pcaps.module_compliance_enforcement & + IXGBE_ACI_MOD_ENFORCE_STRICT_MODE)) { + /* Handle lenient mode */ + err = ixgbe_aci_get_phy_caps(hw, false, + IXGBE_ACI_REPORT_TOPO_CAP_NO_MEDIA, + &pcaps); + if (err) + return err; + } + + /* Determine supported speeds */ + hw->phy.speeds_supported = IXGBE_LINK_SPEED_UNKNOWN; + phy_type_high = le64_to_cpu(pcaps.phy_type_high); + phy_type_low = le64_to_cpu(pcaps.phy_type_low); + + if (phy_type_high & IXGBE_PHY_TYPE_HIGH_10BASE_T || + phy_type_high & IXGBE_PHY_TYPE_HIGH_10M_SGMII) + hw->phy.speeds_supported |= IXGBE_LINK_SPEED_10_FULL; + if (phy_type_low & IXGBE_PHY_TYPE_LOW_100BASE_TX || + phy_type_low & IXGBE_PHY_TYPE_LOW_100M_SGMII || + phy_type_high & IXGBE_PHY_TYPE_HIGH_100M_USXGMII) + hw->phy.speeds_supported |= IXGBE_LINK_SPEED_100_FULL; + if (phy_type_low & IXGBE_PHY_TYPE_LOW_1000BASE_T || + phy_type_low & IXGBE_PHY_TYPE_LOW_1000BASE_SX || + phy_type_low & IXGBE_PHY_TYPE_LOW_1000BASE_LX || + phy_type_low & IXGBE_PHY_TYPE_LOW_1000BASE_KX || + phy_type_low & IXGBE_PHY_TYPE_LOW_1G_SGMII || + phy_type_high & IXGBE_PHY_TYPE_HIGH_1G_USXGMII) + hw->phy.speeds_supported |= IXGBE_LINK_SPEED_1GB_FULL; + if (phy_type_low & IXGBE_PHY_TYPE_LOW_10GBASE_T || + phy_type_low & IXGBE_PHY_TYPE_LOW_10G_SFI_DA || + phy_type_low & IXGBE_PHY_TYPE_LOW_10GBASE_SR || + phy_type_low & IXGBE_PHY_TYPE_LOW_10GBASE_LR || + phy_type_low & IXGBE_PHY_TYPE_LOW_10GBASE_KR_CR1 || + phy_type_low & IXGBE_PHY_TYPE_LOW_10G_SFI_AOC_ACC || + phy_type_low & IXGBE_PHY_TYPE_LOW_10G_SFI_C2C || + phy_type_high & IXGBE_PHY_TYPE_HIGH_10G_USXGMII) + hw->phy.speeds_supported |= IXGBE_LINK_SPEED_10GB_FULL; + + /* 2.5 and 5 Gbps link speeds must be excluded from the + * auto-negotiation set used during driver initialization due to + * compatibility issues with certain switches. Those issues do not + * exist in case of E610 2.5G SKU device (0x57b1). + */ + if (!hw->phy.autoneg_advertised && + hw->device_id != IXGBE_DEV_ID_E610_2_5G_T) + hw->phy.autoneg_advertised = hw->phy.speeds_supported; + + if (phy_type_low & IXGBE_PHY_TYPE_LOW_2500BASE_T || + phy_type_low & IXGBE_PHY_TYPE_LOW_2500BASE_X || + phy_type_low & IXGBE_PHY_TYPE_LOW_2500BASE_KX || + phy_type_high & IXGBE_PHY_TYPE_HIGH_2500M_SGMII || + phy_type_high & IXGBE_PHY_TYPE_HIGH_2500M_USXGMII) + hw->phy.speeds_supported |= IXGBE_LINK_SPEED_2_5GB_FULL; + + if (!hw->phy.autoneg_advertised && + hw->device_id == IXGBE_DEV_ID_E610_2_5G_T) + hw->phy.autoneg_advertised = hw->phy.speeds_supported; + + if (phy_type_low & IXGBE_PHY_TYPE_LOW_5GBASE_T || + phy_type_low & IXGBE_PHY_TYPE_LOW_5GBASE_KR || + phy_type_high & IXGBE_PHY_TYPE_HIGH_5G_USXGMII) + hw->phy.speeds_supported |= IXGBE_LINK_SPEED_5GB_FULL; + + /* Set PHY ID */ + memcpy(&hw->phy.id, pcaps.phy_id_oui, sizeof(u32)); + + hw->phy.eee_speeds_supported = IXGBE_LINK_SPEED_10_FULL | + IXGBE_LINK_SPEED_100_FULL | + IXGBE_LINK_SPEED_1GB_FULL; + hw->phy.eee_speeds_advertised = hw->phy.eee_speeds_supported; + + return 0; +} + +/** + * ixgbe_identify_module_e610 - Identify SFP module type + * @hw: pointer to hardware structure + * + * Identify the SFP module type. + * + * Return: the exit code of the operation. + */ +int ixgbe_identify_module_e610(struct ixgbe_hw *hw) +{ + bool media_available; + u8 module_type; + int err; + + err = ixgbe_update_link_info(hw); + if (err) + return err; + + media_available = + (hw->link.link_info.link_info & IXGBE_ACI_MEDIA_AVAILABLE); + + if (media_available) { + hw->phy.sfp_type = ixgbe_sfp_type_unknown; + + /* Get module type from hw context updated by + * ixgbe_update_link_info() + */ + module_type = hw->link.link_info.module_type[IXGBE_ACI_MOD_TYPE_IDENT]; + + if ((module_type & IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_PASSIVE) || + (module_type & IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_ACTIVE)) { + hw->phy.sfp_type = ixgbe_sfp_type_da_cu; + } else if (module_type & IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_SR) { + hw->phy.sfp_type = ixgbe_sfp_type_sr; + } else if ((module_type & IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_LR) || + (module_type & IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_LRM)) { + hw->phy.sfp_type = ixgbe_sfp_type_lr; + } + } else { + hw->phy.sfp_type = ixgbe_sfp_type_not_present; + return -ENOENT; + } + + return 0; +} + +/** + * ixgbe_setup_phy_link_e610 - Sets up firmware-controlled PHYs + * @hw: pointer to hardware structure + * + * Set the parameters for the firmware-controlled PHYs. + * + * Return: the exit code of the operation. + */ +int ixgbe_setup_phy_link_e610(struct ixgbe_hw *hw) +{ + struct ixgbe_aci_cmd_get_phy_caps_data pcaps; + struct ixgbe_aci_cmd_set_phy_cfg_data pcfg; + u8 rmode = IXGBE_ACI_REPORT_TOPO_CAP_MEDIA; + u64 sup_phy_type_low, sup_phy_type_high; + u64 phy_type_low = 0, phy_type_high = 0; + int err; + + err = ixgbe_aci_get_link_info(hw, false, NULL); + if (err) + return err; + + /* If media is not available get default config. */ + if (!(hw->link.link_info.link_info & IXGBE_ACI_MEDIA_AVAILABLE)) + rmode = IXGBE_ACI_REPORT_DFLT_CFG; + + err = ixgbe_aci_get_phy_caps(hw, false, rmode, &pcaps); + if (err) + return err; + + sup_phy_type_low = le64_to_cpu(pcaps.phy_type_low); + sup_phy_type_high = le64_to_cpu(pcaps.phy_type_high); + + /* Get Active configuration to avoid unintended changes. */ + err = ixgbe_aci_get_phy_caps(hw, false, IXGBE_ACI_REPORT_ACTIVE_CFG, + &pcaps); + if (err) + return err; + + ixgbe_copy_phy_caps_to_cfg(&pcaps, &pcfg); + + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10_FULL) { + phy_type_high |= IXGBE_PHY_TYPE_HIGH_10BASE_T; + phy_type_high |= IXGBE_PHY_TYPE_HIGH_10M_SGMII; + } + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_100_FULL) { + phy_type_low |= IXGBE_PHY_TYPE_LOW_100BASE_TX; + phy_type_low |= IXGBE_PHY_TYPE_LOW_100M_SGMII; + phy_type_high |= IXGBE_PHY_TYPE_HIGH_100M_USXGMII; + } + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL) { + phy_type_low |= IXGBE_PHY_TYPE_LOW_1000BASE_T; + phy_type_low |= IXGBE_PHY_TYPE_LOW_1000BASE_SX; + phy_type_low |= IXGBE_PHY_TYPE_LOW_1000BASE_LX; + phy_type_low |= IXGBE_PHY_TYPE_LOW_1000BASE_KX; + phy_type_low |= IXGBE_PHY_TYPE_LOW_1G_SGMII; + phy_type_high |= IXGBE_PHY_TYPE_HIGH_1G_USXGMII; + } + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_2_5GB_FULL) { + phy_type_low |= IXGBE_PHY_TYPE_LOW_2500BASE_T; + phy_type_low |= IXGBE_PHY_TYPE_LOW_2500BASE_X; + phy_type_low |= IXGBE_PHY_TYPE_LOW_2500BASE_KX; + phy_type_high |= IXGBE_PHY_TYPE_HIGH_2500M_SGMII; + phy_type_high |= IXGBE_PHY_TYPE_HIGH_2500M_USXGMII; + } + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_5GB_FULL) { + phy_type_low |= IXGBE_PHY_TYPE_LOW_5GBASE_T; + phy_type_low |= IXGBE_PHY_TYPE_LOW_5GBASE_KR; + phy_type_high |= IXGBE_PHY_TYPE_HIGH_5G_USXGMII; + } + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL) { + phy_type_low |= IXGBE_PHY_TYPE_LOW_10GBASE_T; + phy_type_low |= IXGBE_PHY_TYPE_LOW_10G_SFI_DA; + phy_type_low |= IXGBE_PHY_TYPE_LOW_10GBASE_SR; + phy_type_low |= IXGBE_PHY_TYPE_LOW_10GBASE_LR; + phy_type_low |= IXGBE_PHY_TYPE_LOW_10GBASE_KR_CR1; + phy_type_low |= IXGBE_PHY_TYPE_LOW_10G_SFI_AOC_ACC; + phy_type_low |= IXGBE_PHY_TYPE_LOW_10G_SFI_C2C; + phy_type_high |= IXGBE_PHY_TYPE_HIGH_10G_USXGMII; + } + + /* Mask the set values to avoid requesting unsupported link types. */ + phy_type_low &= sup_phy_type_low; + pcfg.phy_type_low = cpu_to_le64(phy_type_low); + phy_type_high &= sup_phy_type_high; + pcfg.phy_type_high = cpu_to_le64(phy_type_high); + + if (pcfg.phy_type_high != pcaps.phy_type_high || + pcfg.phy_type_low != pcaps.phy_type_low || + pcfg.caps != pcaps.caps) { + pcfg.caps |= IXGBE_ACI_PHY_ENA_LINK; + pcfg.caps |= IXGBE_ACI_PHY_ENA_AUTO_LINK_UPDT; + + err = ixgbe_aci_set_phy_cfg(hw, &pcfg); + if (err) + return err; + } + + return 0; +} + +/** + * ixgbe_set_phy_power_e610 - Control power for copper PHY + * @hw: pointer to hardware structure + * @on: true for on, false for off + * + * Set the power on/off of the PHY + * by getting its capabilities and setting the appropriate + * configuration parameters. + * + * Return: the exit code of the operation. + */ +int ixgbe_set_phy_power_e610(struct ixgbe_hw *hw, bool on) +{ + struct ixgbe_aci_cmd_get_phy_caps_data phy_caps = {}; + struct ixgbe_aci_cmd_set_phy_cfg_data phy_cfg = {}; + int err; + + err = ixgbe_aci_get_phy_caps(hw, false, + IXGBE_ACI_REPORT_ACTIVE_CFG, + &phy_caps); + if (err) + return err; + + ixgbe_copy_phy_caps_to_cfg(&phy_caps, &phy_cfg); + + if (on) + phy_cfg.caps &= ~IXGBE_ACI_PHY_ENA_LOW_POWER; + else + phy_cfg.caps |= IXGBE_ACI_PHY_ENA_LOW_POWER; + + /* PHY is already in requested power mode. */ + if (phy_caps.caps == phy_cfg.caps) + return 0; + + phy_cfg.caps |= IXGBE_ACI_PHY_ENA_LINK; + phy_cfg.caps |= IXGBE_ACI_PHY_ENA_AUTO_LINK_UPDT; + + return ixgbe_aci_set_phy_cfg(hw, &phy_cfg); +} + +/** + * ixgbe_enter_lplu_e610 - Transition to low power states + * @hw: pointer to hardware structure + * + * Configures Low Power Link Up on transition to low power states + * (from D0 to non-D0). Link is required to enter LPLU so avoid resetting the + * X557 PHY immediately prior to entering LPLU. + * + * Return: the exit code of the operation. + */ +int ixgbe_enter_lplu_e610(struct ixgbe_hw *hw) +{ + struct ixgbe_aci_cmd_get_phy_caps_data phy_caps = {}; + struct ixgbe_aci_cmd_set_phy_cfg_data phy_cfg = {}; + int err; + + err = ixgbe_aci_get_phy_caps(hw, false, + IXGBE_ACI_REPORT_ACTIVE_CFG, + &phy_caps); + if (err) + return err; + + ixgbe_copy_phy_caps_to_cfg(&phy_caps, &phy_cfg); + + phy_cfg.low_power_ctrl_an |= IXGBE_ACI_PHY_EN_D3COLD_LOW_POWER_AUTONEG; + + return ixgbe_aci_set_phy_cfg(hw, &phy_cfg); +} + +/** + * ixgbe_init_eeprom_params_e610 - Initialize EEPROM params + * @hw: pointer to hardware structure + * + * Initialize the EEPROM parameters ixgbe_eeprom_info within the ixgbe_hw + * struct in order to set up EEPROM access. + * + * Return: the operation exit code. + */ +int ixgbe_init_eeprom_params_e610(struct ixgbe_hw *hw) +{ + struct ixgbe_eeprom_info *eeprom = &hw->eeprom; + u32 gens_stat; + u8 sr_size; + + if (eeprom->type != ixgbe_eeprom_uninitialized) + return 0; + + eeprom->type = ixgbe_flash; + + gens_stat = IXGBE_READ_REG(hw, GLNVM_GENS); + sr_size = FIELD_GET(GLNVM_GENS_SR_SIZE_M, gens_stat); + + /* Switching to words (sr_size contains power of 2). */ + eeprom->word_size = BIT(sr_size) * IXGBE_SR_WORDS_IN_1KB; + + hw_dbg(hw, "Eeprom params: type = %d, size = %d\n", eeprom->type, + eeprom->word_size); + + return 0; +} + +/** + * ixgbe_aci_get_netlist_node - get a node handle + * @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 the netlist node and assigns it to + * the provided handle using ACI command (0x06E0). + * + * Return: the exit code of the operation. + */ +int ixgbe_aci_get_netlist_node(struct ixgbe_hw *hw, + struct ixgbe_aci_cmd_get_link_topo *cmd, + u8 *node_part_number, u16 *node_handle) +{ + struct ixgbe_aci_desc desc; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_link_topo); + desc.params.get_link_topo = *cmd; + + if (ixgbe_aci_send_cmd(hw, &desc, NULL, 0)) + return -EOPNOTSUPP; + + 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; +} + +/** + * ixgbe_acquire_nvm - Generic request for acquiring the NVM ownership + * @hw: pointer to the HW structure + * @access: NVM access type (read or write) + * + * Request NVM ownership. + * + * Return: the exit code of the operation. + */ +int ixgbe_acquire_nvm(struct ixgbe_hw *hw, + enum ixgbe_aci_res_access_type access) +{ + u32 fla; + + /* Skip if we are in blank NVM programming mode */ + fla = IXGBE_READ_REG(hw, IXGBE_GLNVM_FLA); + if ((fla & IXGBE_GLNVM_FLA_LOCKED_M) == 0) + return 0; + + return ixgbe_acquire_res(hw, IXGBE_NVM_RES_ID, access, + IXGBE_NVM_TIMEOUT); +} + +/** + * ixgbe_release_nvm - Generic request for releasing the NVM ownership + * @hw: pointer to the HW structure + * + * Release NVM ownership. + */ +void ixgbe_release_nvm(struct ixgbe_hw *hw) +{ + u32 fla; + + /* Skip if we are in blank NVM programming mode */ + fla = IXGBE_READ_REG(hw, IXGBE_GLNVM_FLA); + if ((fla & IXGBE_GLNVM_FLA_LOCKED_M) == 0) + return; + + ixgbe_release_res(hw, IXGBE_NVM_RES_ID); +} + +/** + * ixgbe_aci_read_nvm - read NVM + * @hw: pointer to the HW struct + * @module_typeid: module pointer location in words from the NVM beginning + * @offset: byte offset from the module beginning + * @length: length of the section to be read (in bytes from the offset) + * @data: command buffer (size [bytes] = length) + * @last_command: tells if this is the last command in a series + * @read_shadow_ram: tell if this is a shadow RAM read + * + * Read the NVM using ACI command (0x0701). + * + * Return: the exit code of the operation. + */ +int ixgbe_aci_read_nvm(struct ixgbe_hw *hw, u16 module_typeid, u32 offset, + u16 length, void *data, bool last_command, + bool read_shadow_ram) +{ + struct ixgbe_aci_cmd_nvm *cmd; + struct ixgbe_aci_desc desc; + + if (offset > IXGBE_ACI_NVM_MAX_OFFSET) + return -EINVAL; + + cmd = &desc.params.nvm; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_read); + + if (!read_shadow_ram && module_typeid == IXGBE_ACI_NVM_START_POINT) + cmd->cmd_flags |= IXGBE_ACI_NVM_FLASH_ONLY; + + /* If this is the last command in a series, set the proper flag. */ + if (last_command) + cmd->cmd_flags |= IXGBE_ACI_NVM_LAST_CMD; + cmd->module_typeid = cpu_to_le16(module_typeid); + cmd->offset_low = cpu_to_le16(offset & 0xFFFF); + cmd->offset_high = (offset >> 16) & 0xFF; + cmd->length = cpu_to_le16(length); + + return ixgbe_aci_send_cmd(hw, &desc, data, length); +} + +/** + * ixgbe_aci_erase_nvm - erase NVM sector + * @hw: pointer to the HW struct + * @module_typeid: module pointer location in words from the NVM beginning + * + * Erase the NVM sector using the ACI command (0x0702). + * + * Return: the exit code of the operation. + */ +int ixgbe_aci_erase_nvm(struct ixgbe_hw *hw, u16 module_typeid) +{ + struct ixgbe_aci_cmd_nvm *cmd; + struct ixgbe_aci_desc desc; + __le16 len; + int err; + + /* Read a length value from SR, so module_typeid is equal to 0, + * calculate offset where module size is placed from bytes to words + * set last command and read from SR values to true. + */ + err = ixgbe_aci_read_nvm(hw, 0, 2 * module_typeid + 2, 2, &len, true, + true); + if (err) + return err; + + cmd = &desc.params.nvm; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_erase); + + cmd->module_typeid = cpu_to_le16(module_typeid); + cmd->length = len; + cmd->offset_low = 0; + cmd->offset_high = 0; + + return ixgbe_aci_send_cmd(hw, &desc, NULL, 0); +} + +/** + * ixgbe_aci_update_nvm - update NVM + * @hw: pointer to the HW struct + * @module_typeid: module pointer location in words from the NVM beginning + * @offset: byte offset from the module beginning + * @length: length of the section to be written (in bytes from the offset) + * @data: command buffer (size [bytes] = length) + * @last_command: tells if this is the last command in a series + * @command_flags: command parameters + * + * Update the NVM using the ACI command (0x0703). + * + * Return: the exit code of the operation. + */ +int ixgbe_aci_update_nvm(struct ixgbe_hw *hw, u16 module_typeid, + u32 offset, u16 length, void *data, + bool last_command, u8 command_flags) +{ + struct ixgbe_aci_cmd_nvm *cmd; + struct ixgbe_aci_desc desc; + + cmd = &desc.params.nvm; + + /* In offset the highest byte must be zeroed. */ + if (offset & 0xFF000000) + return -EINVAL; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_write); + + cmd->cmd_flags |= command_flags; + + /* If this is the last command in a series, set the proper flag. */ + if (last_command) + cmd->cmd_flags |= IXGBE_ACI_NVM_LAST_CMD; + cmd->module_typeid = cpu_to_le16(module_typeid); + cmd->offset_low = cpu_to_le16(offset & 0xFFFF); + cmd->offset_high = FIELD_GET(IXGBE_ACI_NVM_OFFSET_HI_U_MASK, offset); + cmd->length = cpu_to_le16(length); + + desc.flags |= cpu_to_le16(IXGBE_ACI_FLAG_RD); + + return ixgbe_aci_send_cmd(hw, &desc, data, length); +} + +/** + * ixgbe_nvm_write_activate - NVM activate write + * @hw: pointer to the HW struct + * @cmd_flags: flags for write activate command + * @response_flags: response indicators from firmware + * + * Update the control word with the required banks' validity bits + * and dumps the Shadow RAM to flash using ACI command (0x0707). + * + * cmd_flags controls which banks to activate, the preservation level to use + * when activating the NVM bank, and whether an EMP reset is required for + * activation. + * + * Note that the 16bit cmd_flags value is split between two separate 1 byte + * flag values in the descriptor. + * + * On successful return of the firmware command, the response_flags variable + * is updated with the flags reported by firmware indicating certain status, + * such as whether EMP reset is enabled. + * + * Return: the exit code of the operation. + */ +int ixgbe_nvm_write_activate(struct ixgbe_hw *hw, u16 cmd_flags, + u8 *response_flags) +{ + struct ixgbe_aci_cmd_nvm *cmd; + struct ixgbe_aci_desc desc; + s32 err; + + cmd = &desc.params.nvm; + ixgbe_fill_dflt_direct_cmd_desc(&desc, + ixgbe_aci_opc_nvm_write_activate); + + cmd->cmd_flags = (u8)(cmd_flags & 0xFF); + cmd->offset_high = (u8)FIELD_GET(IXGBE_ACI_NVM_OFFSET_HI_A_MASK, + cmd_flags); + + err = ixgbe_aci_send_cmd(hw, &desc, NULL, 0); + if (!err && response_flags) + *response_flags = cmd->cmd_flags; + + return err; +} + +/** + * ixgbe_nvm_validate_checksum - validate checksum + * @hw: pointer to the HW struct + * + * Verify NVM PFA checksum validity using ACI command (0x0706). + * If the checksum verification failed, IXGBE_ERR_NVM_CHECKSUM is returned. + * The function acquires and then releases the NVM ownership. + * + * Return: the exit code of the operation. + */ +int ixgbe_nvm_validate_checksum(struct ixgbe_hw *hw) +{ + struct ixgbe_aci_cmd_nvm_checksum *cmd; + struct ixgbe_aci_desc desc; + int err; + + err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ); + if (err) + return err; + + cmd = &desc.params.nvm_checksum; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_checksum); + cmd->flags = IXGBE_ACI_NVM_CHECKSUM_VERIFY; + + err = ixgbe_aci_send_cmd(hw, &desc, NULL, 0); + + ixgbe_release_nvm(hw); + + if (!err && cmd->checksum != + cpu_to_le16(IXGBE_ACI_NVM_CHECKSUM_CORRECT)) { + struct ixgbe_adapter *adapter = container_of(hw, struct ixgbe_adapter, + hw); + + err = -EIO; + netdev_err(adapter->netdev, "Invalid Shadow Ram checksum"); + } + + return err; +} + +/** + * ixgbe_discover_flash_size - Discover the available flash size + * @hw: pointer to the HW struct + * + * The device flash could be up to 16MB in size. However, it is possible that + * the actual size is smaller. Use bisection to determine the accessible size + * of flash memory. + * + * Return: the exit code of the operation. + */ +static int ixgbe_discover_flash_size(struct ixgbe_hw *hw) +{ + u32 min_size = 0, max_size = IXGBE_ACI_NVM_MAX_OFFSET + 1; + int err; + + err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ); + if (err) + return err; + + while ((max_size - min_size) > 1) { + u32 offset = (max_size + min_size) / 2; + u32 len = 1; + u8 data; + + err = ixgbe_read_flat_nvm(hw, offset, &len, &data, false); + if (err == -EIO && + hw->aci.last_status == IXGBE_ACI_RC_EINVAL) { + err = 0; + max_size = offset; + } else if (!err) { + min_size = offset; + } else { + /* an unexpected error occurred */ + goto err_read_flat_nvm; + } + } + + hw->flash.flash_size = max_size; + +err_read_flat_nvm: + ixgbe_release_nvm(hw); + + return err; +} + +/** + * ixgbe_read_sr_base_address - Read the value of a Shadow RAM pointer word + * @hw: pointer to the HW structure + * @offset: the word offset of the Shadow RAM word to read + * @pointer: pointer value read from Shadow RAM + * + * Read the given Shadow RAM word, and convert it to a pointer value specified + * in bytes. This function assumes the specified offset is a valid pointer + * word. + * + * Each pointer word specifies whether it is stored in word size or 4KB + * sector size by using the highest bit. The reported pointer value will be in + * bytes, intended for flat NVM reads. + * + * Return: the exit code of the operation. + */ +static int ixgbe_read_sr_base_address(struct ixgbe_hw *hw, u16 offset, + u32 *pointer) +{ + u16 value; + int err; + + err = ixgbe_read_ee_aci_e610(hw, offset, &value); + if (err) + return err; + + /* Determine if the pointer is in 4KB or word units */ + if (value & IXGBE_SR_NVM_PTR_4KB_UNITS) + *pointer = (value & ~IXGBE_SR_NVM_PTR_4KB_UNITS) * SZ_4K; + else + *pointer = value * sizeof(u16); + + return 0; +} + +/** + * ixgbe_read_sr_area_size - Read an area size from a Shadow RAM word + * @hw: pointer to the HW structure + * @offset: the word offset of the Shadow RAM to read + * @size: size value read from the Shadow RAM + * + * Read the given Shadow RAM word, and convert it to an area size value + * specified in bytes. This function assumes the specified offset is a valid + * area size word. + * + * Each area size word is specified in 4KB sector units. This function reports + * the size in bytes, intended for flat NVM reads. + * + * Return: the exit code of the operation. + */ +static int ixgbe_read_sr_area_size(struct ixgbe_hw *hw, u16 offset, u32 *size) +{ + u16 value; + int err; + + err = ixgbe_read_ee_aci_e610(hw, offset, &value); + if (err) + return err; + + /* Area sizes are always specified in 4KB units */ + *size = value * SZ_4K; + + return 0; +} + +/** + * ixgbe_determine_active_flash_banks - Discover active bank for each module + * @hw: pointer to the HW struct + * + * Read the Shadow RAM control word and determine which banks are active for + * the NVM, OROM, and Netlist modules. Also read and calculate the associated + * pointer and size. These values are then cached into the ixgbe_flash_info + * structure for later use in order to calculate the correct offset to read + * from the active module. + * + * Return: the exit code of the operation. + */ +static int ixgbe_determine_active_flash_banks(struct ixgbe_hw *hw) +{ + struct ixgbe_bank_info *banks = &hw->flash.banks; + u16 ctrl_word; + int err; + + err = ixgbe_read_ee_aci_e610(hw, IXGBE_E610_SR_NVM_CTRL_WORD, + &ctrl_word); + if (err) + return err; + + if (FIELD_GET(IXGBE_SR_CTRL_WORD_1_M, ctrl_word) != + IXGBE_SR_CTRL_WORD_VALID) + return -ENODATA; + + if (!(ctrl_word & IXGBE_SR_CTRL_WORD_NVM_BANK)) + banks->nvm_bank = IXGBE_1ST_FLASH_BANK; + else + banks->nvm_bank = IXGBE_2ND_FLASH_BANK; + + if (!(ctrl_word & IXGBE_SR_CTRL_WORD_OROM_BANK)) + banks->orom_bank = IXGBE_1ST_FLASH_BANK; + else + banks->orom_bank = IXGBE_2ND_FLASH_BANK; + + if (!(ctrl_word & IXGBE_SR_CTRL_WORD_NETLIST_BANK)) + banks->netlist_bank = IXGBE_1ST_FLASH_BANK; + else + banks->netlist_bank = IXGBE_2ND_FLASH_BANK; + + err = ixgbe_read_sr_base_address(hw, IXGBE_E610_SR_1ST_NVM_BANK_PTR, + &banks->nvm_ptr); + if (err) + return err; + + err = ixgbe_read_sr_area_size(hw, IXGBE_E610_SR_NVM_BANK_SIZE, + &banks->nvm_size); + if (err) + return err; + + err = ixgbe_read_sr_base_address(hw, IXGBE_E610_SR_1ST_OROM_BANK_PTR, + &banks->orom_ptr); + if (err) + return err; + + err = ixgbe_read_sr_area_size(hw, IXGBE_E610_SR_OROM_BANK_SIZE, + &banks->orom_size); + if (err) + return err; + + err = ixgbe_read_sr_base_address(hw, IXGBE_E610_SR_NETLIST_BANK_PTR, + &banks->netlist_ptr); + if (err) + return err; + + err = ixgbe_read_sr_area_size(hw, IXGBE_E610_SR_NETLIST_BANK_SIZE, + &banks->netlist_size); + + return err; +} + +/** + * ixgbe_get_flash_bank_offset - Get offset into requested flash bank + * @hw: pointer to the HW structure + * @bank: whether to read from the active or inactive flash bank + * @module: the module to read from + * + * Based on the module, lookup the module offset from the beginning of the + * flash. + * + * Return: the flash offset. Note that a value of zero is invalid and must be + * treated as an error. + */ +static int ixgbe_get_flash_bank_offset(struct ixgbe_hw *hw, + enum ixgbe_bank_select bank, + u16 module) +{ + struct ixgbe_bank_info *banks = &hw->flash.banks; + enum ixgbe_flash_bank active_bank; + bool second_bank_active; + u32 offset, size; + + switch (module) { + case IXGBE_E610_SR_1ST_NVM_BANK_PTR: + offset = banks->nvm_ptr; + size = banks->nvm_size; + active_bank = banks->nvm_bank; + break; + case IXGBE_E610_SR_1ST_OROM_BANK_PTR: + offset = banks->orom_ptr; + size = banks->orom_size; + active_bank = banks->orom_bank; + break; + case IXGBE_E610_SR_NETLIST_BANK_PTR: + offset = banks->netlist_ptr; + size = banks->netlist_size; + active_bank = banks->netlist_bank; + break; + default: + return 0; + } + + switch (active_bank) { + case IXGBE_1ST_FLASH_BANK: + second_bank_active = false; + break; + case IXGBE_2ND_FLASH_BANK: + second_bank_active = true; + break; + default: + return 0; + } + + /* The second flash bank is stored immediately following the first + * bank. Based on whether the 1st or 2nd bank is active, and whether + * we want the active or inactive bank, calculate the desired offset. + */ + switch (bank) { + case IXGBE_ACTIVE_FLASH_BANK: + return offset + (second_bank_active ? size : 0); + case IXGBE_INACTIVE_FLASH_BANK: + return offset + (second_bank_active ? 0 : size); + } + + return 0; +} + +/** + * ixgbe_read_flash_module - Read a word from one of the main NVM modules + * @hw: pointer to the HW structure + * @bank: which bank of the module to read + * @module: the module to read + * @offset: the offset into the module in bytes + * @data: storage for the word read from the flash + * @length: bytes of data to read + * + * Read data from the specified flash module. The bank parameter indicates + * whether or not to read from the active bank or the inactive bank of that + * module. + * + * The word will be read using flat NVM access, and relies on the + * hw->flash.banks data being setup by ixgbe_determine_active_flash_banks() + * during initialization. + * + * Return: the exit code of the operation. + */ +static int ixgbe_read_flash_module(struct ixgbe_hw *hw, + enum ixgbe_bank_select bank, + u16 module, u32 offset, u8 *data, u32 length) +{ + u32 start; + int err; + + start = ixgbe_get_flash_bank_offset(hw, bank, module); + if (!start) + return -EINVAL; + + err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ); + if (err) + return err; + + err = ixgbe_read_flat_nvm(hw, start + offset, &length, data, false); + + ixgbe_release_nvm(hw); + + return err; +} + +/** + * ixgbe_read_nvm_module - Read from the active main NVM module + * @hw: pointer to the HW structure + * @bank: whether to read from active or inactive NVM module + * @offset: offset into the NVM module to read, in words + * @data: storage for returned word value + * + * Read the specified word from the active NVM module. This includes the CSS + * header at the start of the NVM module. + * + * Return: the exit code of the operation. + */ +static int ixgbe_read_nvm_module(struct ixgbe_hw *hw, + enum ixgbe_bank_select bank, + u32 offset, u16 *data) +{ + __le16 data_local; + int err; + + err = ixgbe_read_flash_module(hw, bank, IXGBE_E610_SR_1ST_NVM_BANK_PTR, + offset * sizeof(data_local), + (u8 *)&data_local, + sizeof(data_local)); + if (!err) + *data = le16_to_cpu(data_local); + + return err; +} + +/** + * ixgbe_read_netlist_module - Read data from the netlist module area + * @hw: pointer to the HW structure + * @bank: whether to read from the active or inactive module + * @offset: offset into the netlist to read from + * @data: storage for returned word value + * + * Read a word from the specified netlist bank. + * + * Return: the exit code of the operation. + */ +static int ixgbe_read_netlist_module(struct ixgbe_hw *hw, + enum ixgbe_bank_select bank, + u32 offset, u16 *data) +{ + __le16 data_local; + int err; + + err = ixgbe_read_flash_module(hw, bank, IXGBE_E610_SR_NETLIST_BANK_PTR, + offset * sizeof(data_local), + (u8 *)&data_local, sizeof(data_local)); + if (!err) + *data = le16_to_cpu(data_local); + + return err; +} + +/** + * ixgbe_read_orom_module - Read from the active Option ROM module + * @hw: pointer to the HW structure + * @bank: whether to read from active or inactive OROM module + * @offset: offset into the OROM module to read, in words + * @data: storage for returned word value + * + * Read the specified word from the active Option ROM module of the flash. + * Note that unlike the NVM module, the CSS data is stored at the end of the + * module instead of at the beginning. + * + * Return: the exit code of the operation. + */ +static int ixgbe_read_orom_module(struct ixgbe_hw *hw, + enum ixgbe_bank_select bank, + u32 offset, u16 *data) +{ + __le16 data_local; + int err; + + err = ixgbe_read_flash_module(hw, bank, IXGBE_E610_SR_1ST_OROM_BANK_PTR, + offset * sizeof(data_local), + (u8 *)&data_local, sizeof(data_local)); + if (!err) + *data = le16_to_cpu(data_local); + + return err; +} + +/** + * ixgbe_get_nvm_css_hdr_len - Read the CSS header length + * @hw: pointer to the HW struct + * @bank: whether to read from the active or inactive flash bank + * @hdr_len: storage for header length in words + * + * Read the CSS header length from the NVM CSS header and add the + * Authentication header size, and then convert to words. + * + * Return: the exit code of the operation. + */ +static int ixgbe_get_nvm_css_hdr_len(struct ixgbe_hw *hw, + enum ixgbe_bank_select bank, + u32 *hdr_len) +{ + u16 hdr_len_l, hdr_len_h; + u32 hdr_len_dword; + int err; + + err = ixgbe_read_nvm_module(hw, bank, IXGBE_NVM_CSS_HDR_LEN_L, + &hdr_len_l); + if (err) + return err; + + err = ixgbe_read_nvm_module(hw, bank, IXGBE_NVM_CSS_HDR_LEN_H, + &hdr_len_h); + if (err) + return err; + + /* CSS header length is in DWORD, so convert to words and add + * authentication header size. + */ + hdr_len_dword = (hdr_len_h << 16) | hdr_len_l; + *hdr_len = hdr_len_dword * 2 + IXGBE_NVM_AUTH_HEADER_LEN; + + return 0; +} + +/** + * ixgbe_read_nvm_sr_copy - Read a word from the Shadow RAM copy + * @hw: pointer to the HW structure + * @bank: whether to read from the active or inactive NVM module + * @offset: offset into the Shadow RAM copy to read, in words + * @data: storage for returned word value + * + * Read the specified word from the copy of the Shadow RAM found in the + * specified NVM module. + * + * Return: the exit code of the operation. + */ +static int ixgbe_read_nvm_sr_copy(struct ixgbe_hw *hw, + enum ixgbe_bank_select bank, + u32 offset, u16 *data) +{ + u32 hdr_len; + int err; + + err = ixgbe_get_nvm_css_hdr_len(hw, bank, &hdr_len); + if (err) + return err; + + hdr_len = round_up(hdr_len, IXGBE_HDR_LEN_ROUNDUP); + + return ixgbe_read_nvm_module(hw, bank, hdr_len + offset, data); +} + +/** + * ixgbe_get_nvm_srev - Read the security revision from the NVM CSS header + * @hw: pointer to the HW struct + * @bank: whether to read from the active or inactive flash bank + * @srev: storage for security revision + * + * Read the security revision out of the CSS header of the active NVM module + * bank. + * + * Return: the exit code of the operation. + */ +static int ixgbe_get_nvm_srev(struct ixgbe_hw *hw, + enum ixgbe_bank_select bank, u32 *srev) +{ + u16 srev_l, srev_h; + int err; + + err = ixgbe_read_nvm_module(hw, bank, IXGBE_NVM_CSS_SREV_L, &srev_l); + if (err) + return err; + + err = ixgbe_read_nvm_module(hw, bank, IXGBE_NVM_CSS_SREV_H, &srev_h); + if (err) + return err; + + *srev = (srev_h << 16) | srev_l; + + return 0; +} + +/** + * ixgbe_get_orom_civd_data - Get the combo version information from Option ROM + * @hw: pointer to the HW struct + * @bank: whether to read from the active or inactive flash module + * @civd: storage for the Option ROM CIVD data. + * + * Searches through the Option ROM flash contents to locate the CIVD data for + * the image. + * + * Return: the exit code of the operation. + */ +static int +ixgbe_get_orom_civd_data(struct ixgbe_hw *hw, enum ixgbe_bank_select bank, + struct ixgbe_orom_civd_info *civd) +{ + struct ixgbe_orom_civd_info tmp; + u32 offset; + int err; + + /* The CIVD section is located in the Option ROM aligned to 512 bytes. + * The first 4 bytes must contain the ASCII characters "$CIV". + * A simple modulo 256 sum of all of the bytes of the structure must + * equal 0. + */ + for (offset = 0; (offset + SZ_512) <= hw->flash.banks.orom_size; + offset += SZ_512) { + u8 sum = 0; + u32 i; + + err = ixgbe_read_flash_module(hw, bank, + IXGBE_E610_SR_1ST_OROM_BANK_PTR, + offset, + (u8 *)&tmp, sizeof(tmp)); + if (err) + return err; + + /* Skip forward until we find a matching signature */ + if (memcmp(IXGBE_OROM_CIV_SIGNATURE, tmp.signature, + sizeof(tmp.signature))) + continue; + + /* Verify that the simple checksum is zero */ + for (i = 0; i < sizeof(tmp); i++) + sum += ((u8 *)&tmp)[i]; + + if (sum) + return -EDOM; + + *civd = tmp; + return 0; + } + + return -ENODATA; +} + +/** + * ixgbe_get_orom_srev - Read the security revision from the OROM CSS header + * @hw: pointer to the HW struct + * @bank: whether to read from active or inactive flash module + * @srev: storage for security revision + * + * Read the security revision out of the CSS header of the active OROM module + * bank. + * + * Return: the exit code of the operation. + */ +static int ixgbe_get_orom_srev(struct ixgbe_hw *hw, + enum ixgbe_bank_select bank, + u32 *srev) +{ + u32 orom_size_word = hw->flash.banks.orom_size / 2; + u32 css_start, hdr_len; + u16 srev_l, srev_h; + int err; + + err = ixgbe_get_nvm_css_hdr_len(hw, bank, &hdr_len); + if (err) + return err; + + if (orom_size_word < hdr_len) + return -EINVAL; + + /* Calculate how far into the Option ROM the CSS header starts. Note + * that ixgbe_read_orom_module takes a word offset. + */ + css_start = orom_size_word - hdr_len; + err = ixgbe_read_orom_module(hw, bank, + css_start + IXGBE_NVM_CSS_SREV_L, + &srev_l); + if (err) + return err; + + err = ixgbe_read_orom_module(hw, bank, + css_start + IXGBE_NVM_CSS_SREV_H, + &srev_h); + if (err) + return err; + + *srev = srev_h << 16 | srev_l; + + return 0; +} + +/** + * ixgbe_get_orom_ver_info - Read Option ROM version information + * @hw: pointer to the HW struct + * @bank: whether to read from the active or inactive flash module + * @orom: pointer to Option ROM info structure + * + * Read Option ROM version and security revision from the Option ROM flash + * section. + * + * Return: the exit code of the operation. + */ +static int ixgbe_get_orom_ver_info(struct ixgbe_hw *hw, + enum ixgbe_bank_select bank, + struct ixgbe_orom_info *orom) +{ + struct ixgbe_orom_civd_info civd; + u32 combo_ver; + int err; + + err = ixgbe_get_orom_civd_data(hw, bank, &civd); + if (err) + return err; + + combo_ver = le32_to_cpu(civd.combo_ver); + + orom->major = (u8)FIELD_GET(IXGBE_OROM_VER_MASK, combo_ver); + orom->patch = (u8)FIELD_GET(IXGBE_OROM_VER_PATCH_MASK, combo_ver); + orom->build = (u16)FIELD_GET(IXGBE_OROM_VER_BUILD_MASK, combo_ver); + + return ixgbe_get_orom_srev(hw, bank, &orom->srev); +} + +/** + * ixgbe_get_inactive_orom_ver - Read Option ROM version from the inactive bank + * @hw: pointer to the HW structure + * @orom: storage for Option ROM version information + * + * Read the Option ROM version and security revision data for the inactive + * section of flash. Used to access version data for a pending update that has + * not yet been activated. + * + * Return: the exit code of the operation. + */ +int ixgbe_get_inactive_orom_ver(struct ixgbe_hw *hw, + struct ixgbe_orom_info *orom) +{ + return ixgbe_get_orom_ver_info(hw, IXGBE_INACTIVE_FLASH_BANK, orom); +} + +/** + * ixgbe_get_nvm_ver_info - Read NVM version information + * @hw: pointer to the HW struct + * @bank: whether to read from the active or inactive flash bank + * @nvm: pointer to NVM info structure + * + * Read the NVM EETRACK ID and map version of the main NVM image bank, filling + * in the nvm info structure. + * + * Return: the exit code of the operation. + */ +static int ixgbe_get_nvm_ver_info(struct ixgbe_hw *hw, + enum ixgbe_bank_select bank, + struct ixgbe_nvm_info *nvm) +{ + u16 eetrack_lo, eetrack_hi, ver; + int err; + + err = ixgbe_read_nvm_sr_copy(hw, bank, + IXGBE_E610_SR_NVM_DEV_STARTER_VER, &ver); + if (err) + return err; + + nvm->major = FIELD_GET(IXGBE_E610_NVM_VER_HI_MASK, ver); + nvm->minor = FIELD_GET(IXGBE_E610_NVM_VER_LO_MASK, ver); + + err = ixgbe_read_nvm_sr_copy(hw, bank, IXGBE_E610_SR_NVM_EETRACK_LO, + &eetrack_lo); + if (err) + return err; + + err = ixgbe_read_nvm_sr_copy(hw, bank, IXGBE_E610_SR_NVM_EETRACK_HI, + &eetrack_hi); + if (err) + return err; + + nvm->eetrack = (eetrack_hi << 16) | eetrack_lo; + + ixgbe_get_nvm_srev(hw, bank, &nvm->srev); + + return 0; +} + +/** + * ixgbe_get_inactive_nvm_ver - Read Option ROM version from the inactive bank + * @hw: pointer to the HW structure + * @nvm: storage for Option ROM version information + * + * Read the NVM EETRACK ID, Map version, and security revision of the + * inactive NVM bank. Used to access version data for a pending update that + * has not yet been activated. + * + * Return: the exit code of the operation. + */ +int ixgbe_get_inactive_nvm_ver(struct ixgbe_hw *hw, struct ixgbe_nvm_info *nvm) +{ + return ixgbe_get_nvm_ver_info(hw, IXGBE_INACTIVE_FLASH_BANK, nvm); +} + +/** + * ixgbe_get_active_nvm_ver - Read Option ROM version from the active bank + * @hw: pointer to the HW structure + * @nvm: storage for Option ROM version information + * + * Reads the NVM EETRACK ID, Map version, and security revision of the + * active NVM bank. + * + * Return: the exit code of the operation. + */ +static int ixgbe_get_active_nvm_ver(struct ixgbe_hw *hw, + struct ixgbe_nvm_info *nvm) +{ + return ixgbe_get_nvm_ver_info(hw, IXGBE_ACTIVE_FLASH_BANK, nvm); +} + +/** + * ixgbe_get_netlist_info - Read the netlist version information + * @hw: pointer to the HW struct + * @bank: whether to read from the active or inactive flash bank + * @netlist: pointer to netlist version info structure + * + * Get the netlist version information from the requested bank. Reads the Link + * Topology section to find the Netlist ID block and extract the relevant + * information into the netlist version structure. + * + * Return: the exit code of the operation. + */ +static int ixgbe_get_netlist_info(struct ixgbe_hw *hw, + enum ixgbe_bank_select bank, + struct ixgbe_netlist_info *netlist) +{ + u16 module_id, length, node_count, i; + u16 *id_blk; + int err; + + err = ixgbe_read_netlist_module(hw, bank, IXGBE_NETLIST_TYPE_OFFSET, + &module_id); + if (err) + return err; + + if (module_id != IXGBE_NETLIST_LINK_TOPO_MOD_ID) + return -EIO; + + err = ixgbe_read_netlist_module(hw, bank, IXGBE_LINK_TOPO_MODULE_LEN, + &length); + if (err) + return err; + + /* Sanity check that we have at least enough words to store the + * netlist ID block. + */ + if (length < IXGBE_NETLIST_ID_BLK_SIZE) + return -EIO; + + err = ixgbe_read_netlist_module(hw, bank, IXGBE_LINK_TOPO_NODE_COUNT, + &node_count); + if (err) + return err; + + node_count &= IXGBE_LINK_TOPO_NODE_COUNT_M; + + id_blk = kcalloc(IXGBE_NETLIST_ID_BLK_SIZE, sizeof(*id_blk), GFP_KERNEL); + if (!id_blk) + return -ENOMEM; + + /* Read out the entire Netlist ID Block at once. */ + err = ixgbe_read_flash_module(hw, bank, IXGBE_E610_SR_NETLIST_BANK_PTR, + IXGBE_NETLIST_ID_BLK_OFFSET(node_count) * + sizeof(*id_blk), (u8 *)id_blk, + IXGBE_NETLIST_ID_BLK_SIZE * + sizeof(*id_blk)); + if (err) + goto free_id_blk; + + for (i = 0; i < IXGBE_NETLIST_ID_BLK_SIZE; i++) + id_blk[i] = le16_to_cpu(((__le16 *)id_blk)[i]); + + netlist->major = id_blk[IXGBE_NETLIST_ID_BLK_MAJOR_VER_HIGH] << 16 | + id_blk[IXGBE_NETLIST_ID_BLK_MAJOR_VER_LOW]; + netlist->minor = id_blk[IXGBE_NETLIST_ID_BLK_MINOR_VER_HIGH] << 16 | + id_blk[IXGBE_NETLIST_ID_BLK_MINOR_VER_LOW]; + netlist->type = id_blk[IXGBE_NETLIST_ID_BLK_TYPE_HIGH] << 16 | + id_blk[IXGBE_NETLIST_ID_BLK_TYPE_LOW]; + netlist->rev = id_blk[IXGBE_NETLIST_ID_BLK_REV_HIGH] << 16 | + id_blk[IXGBE_NETLIST_ID_BLK_REV_LOW]; + netlist->cust_ver = id_blk[IXGBE_NETLIST_ID_BLK_CUST_VER]; + /* Read the left most 4 bytes of SHA */ + netlist->hash = id_blk[IXGBE_NETLIST_ID_BLK_SHA_HASH_WORD(15)] << 16 | + id_blk[IXGBE_NETLIST_ID_BLK_SHA_HASH_WORD(14)]; + +free_id_blk: + kfree(id_blk); + return err; +} + +/** + * ixgbe_get_inactive_netlist_ver - Read netlist version from the inactive bank + * @hw: pointer to the HW struct + * @netlist: pointer to netlist version info structure + * + * Read the netlist version data from the inactive netlist bank. Used to + * extract version data of a pending flash update in order to display the + * version data. + * + * Return: the exit code of the operation. + */ +int ixgbe_get_inactive_netlist_ver(struct ixgbe_hw *hw, + struct ixgbe_netlist_info *netlist) +{ + return ixgbe_get_netlist_info(hw, IXGBE_INACTIVE_FLASH_BANK, netlist); +} + +/** + * ixgbe_get_flash_data - get flash data + * @hw: pointer to the HW struct + * + * Read and populate flash data such as Shadow RAM size, + * max_timeout and blank_nvm_mode + * + * Return: the exit code of the operation. + */ +int ixgbe_get_flash_data(struct ixgbe_hw *hw) +{ + struct ixgbe_flash_info *flash = &hw->flash; + u32 fla, gens_stat; + u8 sr_size; + int err; + + /* The SR size is stored regardless of the NVM programming mode + * as the blank mode may be used in the factory line. + */ + gens_stat = IXGBE_READ_REG(hw, GLNVM_GENS); + sr_size = FIELD_GET(GLNVM_GENS_SR_SIZE_M, gens_stat); + + /* Switching to words (sr_size contains power of 2) */ + flash->sr_words = BIT(sr_size) * (SZ_1K / sizeof(u16)); + + /* Check if we are in the normal or blank NVM programming mode */ + fla = IXGBE_READ_REG(hw, IXGBE_GLNVM_FLA); + if (fla & IXGBE_GLNVM_FLA_LOCKED_M) { + flash->blank_nvm_mode = false; + } else { + flash->blank_nvm_mode = true; + return -EIO; + } + + err = ixgbe_discover_flash_size(hw); + if (err) + return err; + + err = ixgbe_determine_active_flash_banks(hw); + if (err) + return err; + + err = ixgbe_get_nvm_ver_info(hw, IXGBE_ACTIVE_FLASH_BANK, + &flash->nvm); + if (err) + return err; + + err = ixgbe_get_orom_ver_info(hw, IXGBE_ACTIVE_FLASH_BANK, + &flash->orom); + if (err) + return err; + + err = ixgbe_get_netlist_info(hw, IXGBE_ACTIVE_FLASH_BANK, + &flash->netlist); + return err; +} + +/** + * ixgbe_aci_nvm_update_empr - update NVM using EMPR + * @hw: pointer to the HW struct + * + * Force EMP reset using ACI command (0x0709). This command allows SW to + * request an EMPR to activate new FW. + * + * Return: the exit code of the operation. + */ +int ixgbe_aci_nvm_update_empr(struct ixgbe_hw *hw) +{ + struct ixgbe_aci_desc desc; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_update_empr); + + return ixgbe_aci_send_cmd(hw, &desc, NULL, 0); +} + +/* ixgbe_nvm_set_pkg_data - NVM set package data + * @hw: pointer to the HW struct + * @del_pkg_data_flag: If is set then the current pkg_data store by FW + * is deleted. + * If bit is set to 1, then buffer should be size 0. + * @data: pointer to buffer + * @length: length of the buffer + * + * Set package data using ACI command (0x070A). + * This command is equivalent to the reception of + * a PLDM FW Update GetPackageData cmd. This command should be sent + * as part of the NVM update as the first cmd in the flow. + * + * Return: the exit code of the operation. + */ +int ixgbe_nvm_set_pkg_data(struct ixgbe_hw *hw, bool del_pkg_data_flag, + u8 *data, u16 length) +{ + struct ixgbe_aci_cmd_nvm_pkg_data *cmd; + struct ixgbe_aci_desc desc; + + if (length != 0 && !data) + return -EINVAL; + + cmd = &desc.params.pkg_data; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_pkg_data); + desc.flags |= cpu_to_le16(IXGBE_ACI_FLAG_RD); + + if (del_pkg_data_flag) + cmd->cmd_flags |= IXGBE_ACI_NVM_PKG_DELETE; + + return ixgbe_aci_send_cmd(hw, &desc, data, length); +} + +/* ixgbe_nvm_pass_component_tbl - NVM pass component table + * @hw: pointer to the HW struct + * @data: pointer to buffer + * @length: length of the buffer + * @transfer_flag: parameter for determining stage of the update + * @comp_response: a pointer to the response from the 0x070B ACI. + * @comp_response_code: a pointer to the response code from the 0x070B ACI. + * + * Pass component table using ACI command (0x070B). This command is equivalent + * to the reception of a PLDM FW Update PassComponentTable cmd. + * This command should be sent once per component. It can be only sent after + * Set Package Data cmd and before actual update. FW will assume these + * commands are going to be sent until the TransferFlag is set to End or + * StartAndEnd. + * + * Return: the exit code of the operation. + */ +int ixgbe_nvm_pass_component_tbl(struct ixgbe_hw *hw, u8 *data, u16 length, + u8 transfer_flag, u8 *comp_response, + u8 *comp_response_code) +{ + struct ixgbe_aci_cmd_nvm_pass_comp_tbl *cmd; + struct ixgbe_aci_desc desc; + int err; + + if (!data || !comp_response || !comp_response_code) + return -EINVAL; + + cmd = &desc.params.pass_comp_tbl; + + ixgbe_fill_dflt_direct_cmd_desc(&desc, + ixgbe_aci_opc_nvm_pass_component_tbl); + desc.flags |= cpu_to_le16(IXGBE_ACI_FLAG_RD); + + cmd->transfer_flag = transfer_flag; + err = ixgbe_aci_send_cmd(hw, &desc, data, length); + if (!err) { + *comp_response = cmd->component_response; + *comp_response_code = cmd->component_response_code; + } + + return err; +} + +/** + * ixgbe_read_sr_word_aci - Reads Shadow RAM via ACI + * @hw: pointer to the HW structure + * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF) + * @data: word read from the Shadow RAM + * + * Reads one 16 bit word from the Shadow RAM using ixgbe_read_flat_nvm. + * + * Return: the exit code of the operation. + */ +int ixgbe_read_sr_word_aci(struct ixgbe_hw *hw, u16 offset, u16 *data) +{ + u32 bytes = sizeof(u16); + u16 data_local; + int err; + + err = ixgbe_read_flat_nvm(hw, offset * sizeof(u16), &bytes, + (u8 *)&data_local, true); + if (err) + return err; + + *data = data_local; + return 0; +} + +/** + * ixgbe_read_flat_nvm - Read portion of NVM by flat offset + * @hw: pointer to the HW struct + * @offset: offset from beginning of NVM + * @length: (in) number of bytes to read; (out) number of bytes actually read + * @data: buffer to return data in (sized to fit the specified length) + * @read_shadow_ram: if true, read from shadow RAM instead of NVM + * + * Reads a portion of the NVM, as a flat memory space. This function correctly + * breaks read requests across Shadow RAM sectors, prevents Shadow RAM size + * from being exceeded in case of Shadow RAM read requests and ensures that no + * single read request exceeds the maximum 4KB read for a single admin command. + * + * Returns an error code on failure. Note that the data pointer may be + * partially updated if some reads succeed before a failure. + * + * Return: the exit code of the operation. + */ +int ixgbe_read_flat_nvm(struct ixgbe_hw *hw, u32 offset, u32 *length, + u8 *data, bool read_shadow_ram) +{ + u32 inlen = *length; + u32 bytes_read = 0; + bool last_cmd; + int err; + + /* Verify the length of the read if this is for the Shadow RAM */ + if (read_shadow_ram && ((offset + inlen) > + (hw->eeprom.word_size * 2u))) + return -EINVAL; + + do { + u32 read_size, sector_offset; + + /* ixgbe_aci_read_nvm cannot read more than 4KB at a time. + * Additionally, a read from the Shadow RAM may not cross over + * a sector boundary. Conveniently, the sector size is also 4KB. + */ + sector_offset = offset % IXGBE_ACI_MAX_BUFFER_SIZE; + read_size = min_t(u32, + IXGBE_ACI_MAX_BUFFER_SIZE - sector_offset, + inlen - bytes_read); + + last_cmd = !(bytes_read + read_size < inlen); + + /* ixgbe_aci_read_nvm takes the length as a u16. Our read_size + * is calculated using a u32, but the IXGBE_ACI_MAX_BUFFER_SIZE + * maximum size guarantees that it will fit within the 2 bytes. + */ + err = ixgbe_aci_read_nvm(hw, IXGBE_ACI_NVM_START_POINT, + offset, (u16)read_size, + data + bytes_read, last_cmd, + read_shadow_ram); + if (err) + break; + + bytes_read += read_size; + offset += read_size; + } while (!last_cmd); + + *length = bytes_read; + return err; +} + +/** + * ixgbe_read_sr_buf_aci - Read Shadow RAM buffer via ACI + * @hw: pointer to the HW structure + * @offset: offset of the Shadow RAM words to read (0x000000 - 0x001FFF) + * @words: (in) number of words to read; (out) number of words actually read + * @data: words read from the Shadow RAM + * + * Read 16 bit words (data buf) from the Shadow RAM. Acquire/release the NVM + * ownership. + * + * Return: the operation exit code. + */ +int ixgbe_read_sr_buf_aci(struct ixgbe_hw *hw, u16 offset, u16 *words, + u16 *data) +{ + u32 bytes = *words * 2; + int err; + + err = ixgbe_read_flat_nvm(hw, offset * 2, &bytes, (u8 *)data, true); + if (err) + return err; + + *words = bytes / 2; + + for (int i = 0; i < *words; i++) + data[i] = le16_to_cpu(((__le16 *)data)[i]); + + return 0; +} + +/** + * ixgbe_read_ee_aci_e610 - Read EEPROM word using the admin command. + * @hw: pointer to hardware structure + * @offset: offset of word in the EEPROM to read + * @data: word read from the EEPROM + * + * Reads a 16 bit word from the EEPROM using the ACI. + * If the EEPROM params are not initialized, the function + * initialize them before proceeding with reading. + * The function acquires and then releases the NVM ownership. + * + * Return: the exit code of the operation. + */ +int ixgbe_read_ee_aci_e610(struct ixgbe_hw *hw, u16 offset, u16 *data) +{ + int err; + + if (hw->eeprom.type == ixgbe_eeprom_uninitialized) { + err = hw->eeprom.ops.init_params(hw); + if (err) + return err; + } + + err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ); + if (err) + return err; + + err = ixgbe_read_sr_word_aci(hw, offset, data); + ixgbe_release_nvm(hw); + + return err; +} + +/** + * ixgbe_read_ee_aci_buffer_e610 - Read EEPROM words via ACI + * @hw: pointer to hardware structure + * @offset: offset of words in the EEPROM to read + * @words: number of words to read + * @data: words to read from the EEPROM + * + * Read 16 bit words from the EEPROM via the ACI. Initialize the EEPROM params + * prior to the read. Acquire/release the NVM ownership. + * + * Return: the operation exit code. + */ +int ixgbe_read_ee_aci_buffer_e610(struct ixgbe_hw *hw, u16 offset, + u16 words, u16 *data) +{ + int err; + + if (hw->eeprom.type == ixgbe_eeprom_uninitialized) { + err = hw->eeprom.ops.init_params(hw); + if (err) + return err; + } + + err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ); + if (err) + return err; + + err = ixgbe_read_sr_buf_aci(hw, offset, &words, data); + ixgbe_release_nvm(hw); + + return err; +} + +/** + * ixgbe_validate_eeprom_checksum_e610 - Validate EEPROM checksum + * @hw: pointer to hardware structure + * @checksum_val: calculated checksum + * + * Performs checksum calculation and validates the EEPROM checksum. If the + * caller does not need checksum_val, the value can be NULL. + * If the EEPROM params are not initialized, the function + * initialize them before proceeding. + * The function acquires and then releases the NVM ownership. + * + * Return: the exit code of the operation. + */ +int ixgbe_validate_eeprom_checksum_e610(struct ixgbe_hw *hw, u16 *checksum_val) +{ + int err; + + if (hw->eeprom.type == ixgbe_eeprom_uninitialized) { + err = hw->eeprom.ops.init_params(hw); + if (err) + return err; + } + + err = ixgbe_nvm_validate_checksum(hw); + if (err) + return err; + + if (checksum_val) { + u16 tmp_checksum; + + err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ); + if (err) + return err; + + err = ixgbe_read_sr_word_aci(hw, IXGBE_E610_SR_SW_CHECKSUM_WORD, + &tmp_checksum); + ixgbe_release_nvm(hw); + + if (!err) + *checksum_val = tmp_checksum; + } + + return err; +} + +/** + * ixgbe_reset_hw_e610 - Perform hardware reset + * @hw: pointer to hardware structure + * + * Resets the hardware by resetting the transmit and receive units, masks + * and clears all interrupts, and performs a reset. + * + * Return: the exit code of the operation. + */ +int ixgbe_reset_hw_e610(struct ixgbe_hw *hw) +{ + u32 swfw_mask = hw->phy.phy_semaphore_mask; + u32 ctrl, i; + int err; + + /* Call adapter stop to disable tx/rx and clear interrupts */ + err = hw->mac.ops.stop_adapter(hw); + if (err) + goto reset_hw_out; + + /* Flush pending Tx transactions. */ + ixgbe_clear_tx_pending(hw); + + hw->phy.ops.init(hw); +mac_reset_top: + err = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask); + if (err) + return -EBUSY; + ctrl = IXGBE_CTRL_RST; + ctrl |= IXGBE_READ_REG(hw, IXGBE_CTRL); + IXGBE_WRITE_REG(hw, IXGBE_CTRL, ctrl); + IXGBE_WRITE_FLUSH(hw); + hw->mac.ops.release_swfw_sync(hw, swfw_mask); + + /* Poll for reset bit to self-clear indicating reset is complete */ + for (i = 0; i < 10; i++) { + udelay(1); + ctrl = IXGBE_READ_REG(hw, IXGBE_CTRL); + if (!(ctrl & IXGBE_CTRL_RST_MASK)) + break; + } + + if (ctrl & IXGBE_CTRL_RST_MASK) { + struct ixgbe_adapter *adapter = container_of(hw, struct ixgbe_adapter, + hw); + + err = -EIO; + netdev_err(adapter->netdev, "Reset polling failed to complete."); + } + + /* Double resets are required for recovery from certain error + * conditions. Between resets, it is necessary to stall to allow time + * for any pending HW events to complete. + */ + msleep(100); + if (hw->mac.flags & IXGBE_FLAGS_DOUBLE_RESET_REQUIRED) { + hw->mac.flags &= ~IXGBE_FLAGS_DOUBLE_RESET_REQUIRED; + goto mac_reset_top; + } + + /* Set the Rx packet buffer size. */ + IXGBE_WRITE_REG(hw, IXGBE_RXPBSIZE(0), GENMASK(18, 17)); + + /* Store the permanent mac address */ + hw->mac.ops.get_mac_addr(hw, hw->mac.perm_addr); + + /* Maximum number of Receive Address Registers. */ +#define IXGBE_MAX_NUM_RAR 128 + + /* Store MAC address from RAR0, clear receive address registers, and + * clear the multicast table. Also reset num_rar_entries to the + * maximum number of Receive Address Registers, since we modify this + * value when programming the SAN MAC address. + */ + hw->mac.num_rar_entries = IXGBE_MAX_NUM_RAR; + hw->mac.ops.init_rx_addrs(hw); + + /* Initialize bus function number */ + hw->mac.ops.set_lan_id(hw); + +reset_hw_out: + return err; +} + +/** + * ixgbe_get_pfa_module_tlv - Read sub module TLV from NVM PFA + * @hw: pointer to hardware structure + * @module_tlv: pointer to module TLV to return + * @module_tlv_len: pointer to module TLV length to return + * @module_type: module type requested + * + * Find the requested sub module TLV type from the Preserved Field + * Area (PFA) and returns the TLV pointer and length. The caller can + * use these to read the variable length TLV value. + * + * Return: the exit code of the operation. + */ +static int ixgbe_get_pfa_module_tlv(struct ixgbe_hw *hw, u16 *module_tlv, + u16 *module_tlv_len, u16 module_type) +{ + u16 pfa_len, pfa_ptr, pfa_end_ptr; + u16 next_tlv; + int err; + + err = ixgbe_read_ee_aci_e610(hw, IXGBE_E610_SR_PFA_PTR, &pfa_ptr); + if (err) + return err; + + err = ixgbe_read_ee_aci_e610(hw, pfa_ptr, &pfa_len); + if (err) + return err; + + /* Starting with first TLV after PFA length, iterate through the list + * of TLVs to find the requested one. + */ + next_tlv = pfa_ptr + 1; + pfa_end_ptr = pfa_ptr + pfa_len; + while (next_tlv < pfa_end_ptr) { + u16 tlv_sub_module_type, tlv_len; + + /* Read TLV type */ + err = ixgbe_read_ee_aci_e610(hw, next_tlv, + &tlv_sub_module_type); + if (err) + break; + + /* Read TLV length */ + err = ixgbe_read_ee_aci_e610(hw, next_tlv + 1, &tlv_len); + if (err) + break; + + if (tlv_sub_module_type == module_type) { + if (tlv_len) { + *module_tlv = next_tlv; + *module_tlv_len = tlv_len; + return 0; + } + return -EIO; + } + /* Check next TLV, i.e. current TLV pointer + length + 2 words + * (for current TLV's type and length). + */ + next_tlv = next_tlv + tlv_len + 2; + } + /* Module does not exist */ + return -ENODATA; +} + +/** + * ixgbe_read_pba_string_e610 - Read PBA string from NVM + * @hw: pointer to hardware structure + * @pba_num: stores the part number string from the NVM + * @pba_num_size: part number string buffer length + * + * Read the part number string from the NVM. + * + * Return: the exit code of the operation. + */ +static int ixgbe_read_pba_string_e610(struct ixgbe_hw *hw, u8 *pba_num, + u32 pba_num_size) +{ + u16 pba_tlv, pba_tlv_len; + u16 pba_word, pba_size; + int err; + + *pba_num = '\0'; + + err = ixgbe_get_pfa_module_tlv(hw, &pba_tlv, &pba_tlv_len, + IXGBE_E610_SR_PBA_BLOCK_PTR); + if (err) + return err; + + /* pba_size is the next word */ + err = ixgbe_read_ee_aci_e610(hw, (pba_tlv + 2), &pba_size); + if (err) + return err; + + if (pba_tlv_len < pba_size) + return -EINVAL; + + /* Subtract one to get PBA word count (PBA Size word is included in + * total size). + */ + pba_size--; + + if (pba_num_size < (((u32)pba_size * 2) + 1)) + return -EINVAL; + + for (u16 i = 0; i < pba_size; i++) { + err = ixgbe_read_ee_aci_e610(hw, (pba_tlv + 2 + 1) + i, + &pba_word); + if (err) + return err; + + pba_num[(i * 2)] = FIELD_GET(IXGBE_E610_SR_PBA_BLOCK_MASK, + pba_word); + pba_num[(i * 2) + 1] = pba_word & 0xFF; + } + + pba_num[(pba_size * 2)] = '\0'; + + return err; +} + +static const struct ixgbe_mac_operations mac_ops_e610 = { + .init_hw = ixgbe_init_hw_generic, + .start_hw = ixgbe_start_hw_e610, + .clear_hw_cntrs = ixgbe_clear_hw_cntrs_generic, + .enable_rx_dma = ixgbe_enable_rx_dma_generic, + .get_mac_addr = ixgbe_get_mac_addr_generic, + .get_device_caps = ixgbe_get_device_caps_generic, + .stop_adapter = ixgbe_stop_adapter_generic, + .set_lan_id = ixgbe_set_lan_id_multi_port_pcie, + .set_rxpba = ixgbe_set_rxpba_generic, + .check_link = ixgbe_check_link_e610, + .blink_led_start = ixgbe_blink_led_start_X540, + .blink_led_stop = ixgbe_blink_led_stop_X540, + .set_rar = ixgbe_set_rar_generic, + .clear_rar = ixgbe_clear_rar_generic, + .set_vmdq = ixgbe_set_vmdq_generic, + .set_vmdq_san_mac = ixgbe_set_vmdq_san_mac_generic, + .clear_vmdq = ixgbe_clear_vmdq_generic, + .init_rx_addrs = ixgbe_init_rx_addrs_generic, + .update_mc_addr_list = ixgbe_update_mc_addr_list_generic, + .enable_mc = ixgbe_enable_mc_generic, + .disable_mc = ixgbe_disable_mc_generic, + .clear_vfta = ixgbe_clear_vfta_generic, + .set_vfta = ixgbe_set_vfta_generic, + .fc_enable = ixgbe_fc_enable_generic, + .set_fw_drv_ver = ixgbe_set_fw_drv_ver_x550, + .init_uta_tables = ixgbe_init_uta_tables_generic, + .set_mac_anti_spoofing = ixgbe_set_mac_anti_spoofing, + .set_vlan_anti_spoofing = ixgbe_set_vlan_anti_spoofing, + .set_source_address_pruning = + ixgbe_set_source_address_pruning_x550, + .set_ethertype_anti_spoofing = + ixgbe_set_ethertype_anti_spoofing_x550, + .disable_rx_buff = ixgbe_disable_rx_buff_generic, + .enable_rx_buff = ixgbe_enable_rx_buff_generic, + .enable_rx = ixgbe_enable_rx_generic, + .disable_rx = ixgbe_disable_rx_e610, + .led_on = ixgbe_led_on_generic, + .led_off = ixgbe_led_off_generic, + .init_led_link_act = ixgbe_init_led_link_act_generic, + .reset_hw = ixgbe_reset_hw_e610, + .get_fw_ver = ixgbe_aci_get_fw_ver, + .get_media_type = ixgbe_get_media_type_e610, + .setup_link = ixgbe_setup_link_e610, + .fw_recovery_mode = ixgbe_fw_recovery_mode_e610, + .fw_rollback_mode = ixgbe_fw_rollback_mode_e610, + .get_nvm_ver = ixgbe_get_active_nvm_ver, + .get_link_capabilities = ixgbe_get_link_capabilities_e610, + .get_bus_info = ixgbe_get_bus_info_generic, + .acquire_swfw_sync = ixgbe_acquire_swfw_sync_X540, + .release_swfw_sync = ixgbe_release_swfw_sync_X540, + .init_swfw_sync = ixgbe_init_swfw_sync_X540, + .prot_autoc_read = prot_autoc_read_generic, + .prot_autoc_write = prot_autoc_write_generic, + .setup_fc = ixgbe_setup_fc_e610, + .fc_autoneg = ixgbe_fc_autoneg_e610, +}; + +static const struct ixgbe_phy_operations phy_ops_e610 = { + .init = ixgbe_init_phy_ops_e610, + .identify = ixgbe_identify_phy_e610, + .identify_sfp = ixgbe_identify_module_e610, + .setup_link_speed = ixgbe_setup_phy_link_speed_generic, + .setup_link = ixgbe_setup_phy_link_e610, + .enter_lplu = ixgbe_enter_lplu_e610, +}; + +static const struct ixgbe_eeprom_operations eeprom_ops_e610 = { + .read = ixgbe_read_ee_aci_e610, + .read_buffer = ixgbe_read_ee_aci_buffer_e610, + .validate_checksum = ixgbe_validate_eeprom_checksum_e610, + .read_pba_string = ixgbe_read_pba_string_e610, + .init_params = ixgbe_init_eeprom_params_e610, +}; + +const struct ixgbe_info ixgbe_e610_info = { + .mac = ixgbe_mac_e610, + .get_invariants = ixgbe_get_invariants_X540, + .mac_ops = &mac_ops_e610, + .eeprom_ops = &eeprom_ops_e610, + .phy_ops = &phy_ops_e610, + .mbx_ops = &mbx_ops_generic, + .mvals = ixgbe_mvals_x550em_a, +}; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h new file mode 100644 index 000000000000..bb31d65bd1c8 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2024 Intel Corporation. */ + +#ifndef _IXGBE_E610_H_ +#define _IXGBE_E610_H_ + +#include "ixgbe_type.h" + +int ixgbe_aci_send_cmd(struct ixgbe_hw *hw, struct ixgbe_aci_desc *desc, + void *buf, u16 buf_size); +bool ixgbe_aci_check_event_pending(struct ixgbe_hw *hw); +int ixgbe_aci_get_event(struct ixgbe_hw *hw, struct ixgbe_aci_event *e, + bool *pending); +void ixgbe_fill_dflt_direct_cmd_desc(struct ixgbe_aci_desc *desc, u16 opcode); +int ixgbe_acquire_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res, + enum ixgbe_aci_res_access_type access, u32 timeout); +void ixgbe_release_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res); +int ixgbe_aci_list_caps(struct ixgbe_hw *hw, void *buf, u16 buf_size, + u32 *cap_count, enum ixgbe_aci_opc opc); +int ixgbe_discover_dev_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_dev_caps *dev_caps); +int ixgbe_discover_func_caps(struct ixgbe_hw *hw, + struct ixgbe_hw_func_caps *func_caps); +int ixgbe_get_caps(struct ixgbe_hw *hw); +int ixgbe_aci_disable_rxen(struct ixgbe_hw *hw); +int ixgbe_aci_get_phy_caps(struct ixgbe_hw *hw, bool qual_mods, u8 report_mode, + struct ixgbe_aci_cmd_get_phy_caps_data *pcaps); +void ixgbe_copy_phy_caps_to_cfg(struct ixgbe_aci_cmd_get_phy_caps_data *caps, + struct ixgbe_aci_cmd_set_phy_cfg_data *cfg); +int ixgbe_aci_set_phy_cfg(struct ixgbe_hw *hw, + struct ixgbe_aci_cmd_set_phy_cfg_data *cfg); +int ixgbe_aci_set_link_restart_an(struct ixgbe_hw *hw, bool ena_link); +int ixgbe_update_link_info(struct ixgbe_hw *hw); +int ixgbe_get_link_status(struct ixgbe_hw *hw, bool *link_up); +int ixgbe_aci_get_link_info(struct ixgbe_hw *hw, bool ena_lse, + struct ixgbe_link_status *link); +int ixgbe_aci_set_event_mask(struct ixgbe_hw *hw, u8 port_num, u16 mask); +int ixgbe_configure_lse(struct ixgbe_hw *hw, bool activate, u16 mask); +int ixgbe_aci_set_port_id_led(struct ixgbe_hw *hw, bool orig_mode); +enum ixgbe_media_type ixgbe_get_media_type_e610(struct ixgbe_hw *hw); +int ixgbe_setup_link_e610(struct ixgbe_hw *hw, ixgbe_link_speed speed, + bool autoneg_wait); +int ixgbe_check_link_e610(struct ixgbe_hw *hw, ixgbe_link_speed *speed, + bool *link_up, bool link_up_wait_to_complete); +int ixgbe_get_link_capabilities_e610(struct ixgbe_hw *hw, + ixgbe_link_speed *speed, + bool *autoneg); +int ixgbe_cfg_phy_fc(struct ixgbe_hw *hw, + struct ixgbe_aci_cmd_set_phy_cfg_data *cfg, + enum ixgbe_fc_mode req_mode); +int ixgbe_setup_fc_e610(struct ixgbe_hw *hw); +void ixgbe_fc_autoneg_e610(struct ixgbe_hw *hw); +void ixgbe_disable_rx_e610(struct ixgbe_hw *hw); +int ixgbe_init_phy_ops_e610(struct ixgbe_hw *hw); +int ixgbe_identify_phy_e610(struct ixgbe_hw *hw); +int ixgbe_identify_module_e610(struct ixgbe_hw *hw); +int ixgbe_setup_phy_link_e610(struct ixgbe_hw *hw); +int ixgbe_set_phy_power_e610(struct ixgbe_hw *hw, bool on); +int ixgbe_enter_lplu_e610(struct ixgbe_hw *hw); +int ixgbe_init_eeprom_params_e610(struct ixgbe_hw *hw); +int ixgbe_aci_get_netlist_node(struct ixgbe_hw *hw, + struct ixgbe_aci_cmd_get_link_topo *cmd, + u8 *node_part_number, u16 *node_handle); +int ixgbe_acquire_nvm(struct ixgbe_hw *hw, + enum ixgbe_aci_res_access_type access); +void ixgbe_release_nvm(struct ixgbe_hw *hw); +int ixgbe_aci_read_nvm(struct ixgbe_hw *hw, u16 module_typeid, u32 offset, + u16 length, void *data, bool last_command, + bool read_shadow_ram); +int ixgbe_nvm_validate_checksum(struct ixgbe_hw *hw); +int ixgbe_get_inactive_orom_ver(struct ixgbe_hw *hw, + struct ixgbe_orom_info *orom); +int ixgbe_get_inactive_nvm_ver(struct ixgbe_hw *hw, struct ixgbe_nvm_info *nvm); +int ixgbe_get_inactive_netlist_ver(struct ixgbe_hw *hw, + struct ixgbe_netlist_info *netlist); +int ixgbe_read_sr_word_aci(struct ixgbe_hw *hw, u16 offset, u16 *data); +int ixgbe_read_flat_nvm(struct ixgbe_hw *hw, u32 offset, u32 *length, + u8 *data, bool read_shadow_ram); +int ixgbe_read_sr_buf_aci(struct ixgbe_hw *hw, u16 offset, u16 *words, + u16 *data); +int ixgbe_read_ee_aci_e610(struct ixgbe_hw *hw, u16 offset, u16 *data); +int ixgbe_read_ee_aci_buffer_e610(struct ixgbe_hw *hw, u16 offset, + u16 words, u16 *data); +int ixgbe_validate_eeprom_checksum_e610(struct ixgbe_hw *hw, u16 *checksum_val); +int ixgbe_reset_hw_e610(struct ixgbe_hw *hw); +int ixgbe_get_flash_data(struct ixgbe_hw *hw); +int ixgbe_aci_nvm_update_empr(struct ixgbe_hw *hw); +int ixgbe_nvm_set_pkg_data(struct ixgbe_hw *hw, bool del_pkg_data_flag, + u8 *data, u16 length); +int ixgbe_nvm_pass_component_tbl(struct ixgbe_hw *hw, u8 *data, u16 length, + u8 transfer_flag, u8 *comp_response, + u8 *comp_response_code); +int ixgbe_aci_erase_nvm(struct ixgbe_hw *hw, u16 module_typeid); +int ixgbe_aci_update_nvm(struct ixgbe_hw *hw, u16 module_typeid, + u32 offset, u16 length, void *data, + bool last_command, u8 command_flags); +int ixgbe_nvm_write_activate(struct ixgbe_hw *hw, u16 cmd_flags, + u8 *response_flags); + +#endif /* _IXGBE_E610_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 6e6e6f1847b6..d8a919ab7027 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ /* ethtool support for ixgbe */ @@ -213,7 +213,7 @@ static void ixgbe_set_advertising_10gtypes(struct ixgbe_hw *hw, static int ixgbe_get_link_ksettings(struct net_device *netdev, struct ethtool_link_ksettings *cmd) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; ixgbe_link_speed supported_link; bool autoneg = false; @@ -458,7 +458,7 @@ static int ixgbe_get_link_ksettings(struct net_device *netdev, static int ixgbe_set_link_ksettings(struct net_device *netdev, const struct ethtool_link_ksettings *cmd) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; u32 advertised, old; int err = 0; @@ -535,7 +535,7 @@ static int ixgbe_set_link_ksettings(struct net_device *netdev, static void ixgbe_get_pause_stats(struct net_device *netdev, struct ethtool_pause_stats *stats) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw_stats *hwstats = &adapter->stats; stats->tx_pause_frames = hwstats->lxontxc + hwstats->lxofftxc; @@ -545,7 +545,7 @@ static void ixgbe_get_pause_stats(struct net_device *netdev, static void ixgbe_get_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; if (ixgbe_device_supports_autoneg_fc(hw) && @@ -564,10 +564,26 @@ static void ixgbe_get_pauseparam(struct net_device *netdev, } } +static void ixgbe_set_pauseparam_finalize(struct net_device *netdev, + struct ixgbe_fc_info *fc) +{ + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); + struct ixgbe_hw *hw = &adapter->hw; + + /* If the thing changed then we'll update and use new autoneg. */ + if (memcmp(fc, &hw->fc, sizeof(*fc))) { + hw->fc = *fc; + if (netif_running(netdev)) + ixgbe_reinit_locked(adapter); + else + ixgbe_reset(adapter); + } +} + static int ixgbe_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; struct ixgbe_fc_info fc = hw->fc; @@ -592,27 +608,52 @@ static int ixgbe_set_pauseparam(struct net_device *netdev, else fc.requested_mode = ixgbe_fc_none; - /* if the thing changed then we'll update and use new autoneg */ - if (memcmp(&fc, &hw->fc, sizeof(struct ixgbe_fc_info))) { - hw->fc = fc; - if (netif_running(netdev)) - ixgbe_reinit_locked(adapter); - else - ixgbe_reset(adapter); + ixgbe_set_pauseparam_finalize(netdev, &fc); + + return 0; +} + +static int ixgbe_set_pauseparam_e610(struct net_device *netdev, + struct ethtool_pauseparam *pause) +{ + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); + struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_fc_info fc = hw->fc; + + if (!ixgbe_device_supports_autoneg_fc(hw)) + return -EOPNOTSUPP; + + if (pause->autoneg == AUTONEG_DISABLE) { + netdev_info(netdev, + "Cannot disable autonegotiation on this device.\n"); + return -EOPNOTSUPP; } + fc.disable_fc_autoneg = false; + + if (pause->rx_pause && pause->tx_pause) + fc.requested_mode = ixgbe_fc_full; + else if (pause->rx_pause) + fc.requested_mode = ixgbe_fc_rx_pause; + else if (pause->tx_pause) + fc.requested_mode = ixgbe_fc_tx_pause; + else + fc.requested_mode = ixgbe_fc_none; + + ixgbe_set_pauseparam_finalize(netdev, &fc); + return 0; } static u32 ixgbe_get_msglevel(struct net_device *netdev) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); return adapter->msg_enable; } static void ixgbe_set_msglevel(struct net_device *netdev, u32 data) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); adapter->msg_enable = data; } @@ -627,7 +668,7 @@ static int ixgbe_get_regs_len(struct net_device *netdev) static void ixgbe_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; u32 *regs_buff = p; u8 i; @@ -690,6 +731,7 @@ static void ixgbe_get_regs(struct net_device *netdev, case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: regs_buff[35 + i] = IXGBE_READ_REG(hw, IXGBE_FCRTL_82599(i)); regs_buff[43 + i] = IXGBE_READ_REG(hw, IXGBE_FCRTH_82599(i)); break; @@ -993,14 +1035,14 @@ static void ixgbe_get_regs(struct net_device *netdev, static int ixgbe_get_eeprom_len(struct net_device *netdev) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); return adapter->hw.eeprom.word_size * 2; } static int ixgbe_get_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom, u8 *bytes) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; u16 *eeprom_buff; int first_word, last_word, eeprom_len; @@ -1036,7 +1078,7 @@ static int ixgbe_get_eeprom(struct net_device *netdev, static int ixgbe_set_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom, u8 *bytes) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; u16 *eeprom_buff; void *ptr; @@ -1103,10 +1145,22 @@ err: return ret_val; } +void ixgbe_refresh_fw_version(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + + ixgbe_get_flash_data(hw); + ixgbe_set_fw_version_e610(adapter); +} + static void ixgbe_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); + + /* need to refresh info for e610 in case fw reloads in runtime */ + if (adapter->hw.mac.type == ixgbe_mac_e610) + ixgbe_refresh_fw_version(adapter); strscpy(drvinfo->driver, ixgbe_driver_name, sizeof(drvinfo->driver)); @@ -1160,7 +1214,7 @@ static void ixgbe_get_ringparam(struct net_device *netdev, struct kernel_ethtool_ringparam *kernel_ring, struct netlink_ext_ack *extack) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_ring *tx_ring = adapter->tx_ring[0]; struct ixgbe_ring *rx_ring = adapter->rx_ring[0]; @@ -1175,7 +1229,7 @@ static int ixgbe_set_ringparam(struct net_device *netdev, struct kernel_ethtool_ringparam *kernel_ring, struct netlink_ext_ack *extack) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_ring *temp_ring; int i, j, err = 0; u32 new_rx_count, new_tx_count; @@ -1335,7 +1389,7 @@ static int ixgbe_get_sset_count(struct net_device *netdev, int sset) static void ixgbe_get_ethtool_stats(struct net_device *netdev, struct ethtool_stats *stats, u64 *data) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct rtnl_link_stats64 temp; const struct rtnl_link_stats64 *net_stats; unsigned int start; @@ -1613,6 +1667,7 @@ static int ixgbe_reg_test(struct ixgbe_adapter *adapter, u64 *data) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: toggle = 0x7FFFF30F; test = reg_test_82599; break; @@ -1708,7 +1763,7 @@ static int ixgbe_eeprom_test(struct ixgbe_adapter *adapter, u64 *data) static irqreturn_t ixgbe_test_intr(int irq, void *data) { struct net_device *netdev = (struct net_device *) data; - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); adapter->test_icr |= IXGBE_READ_REG(&adapter->hw, IXGBE_EICR); @@ -1874,6 +1929,7 @@ static int ixgbe_setup_desc_rings(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: reg_data = IXGBE_READ_REG(&adapter->hw, IXGBE_DMATXCTL); reg_data |= IXGBE_DMATXCTL_TE; IXGBE_WRITE_REG(&adapter->hw, IXGBE_DMATXCTL, reg_data); @@ -1935,6 +1991,7 @@ static int ixgbe_setup_loopback_test(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: reg_data = IXGBE_READ_REG(hw, IXGBE_MACC); reg_data |= IXGBE_MACC_FLU; IXGBE_WRITE_REG(hw, IXGBE_MACC, reg_data); @@ -2179,7 +2236,7 @@ out: static void ixgbe_diag_test(struct net_device *netdev, struct ethtool_test *eth_test, u64 *data) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); bool if_running = netif_running(netdev); if (ixgbe_removed(adapter->hw.hw_addr)) { @@ -2302,7 +2359,7 @@ static int ixgbe_wol_exclusion(struct ixgbe_adapter *adapter, static void ixgbe_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); wol->supported = WAKE_UCAST | WAKE_MCAST | WAKE_BCAST | WAKE_MAGIC; @@ -2324,7 +2381,7 @@ static void ixgbe_get_wol(struct net_device *netdev, static int ixgbe_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); if (wol->wolopts & (WAKE_PHY | WAKE_ARP | WAKE_MAGICSECURE | WAKE_FILTER)) @@ -2349,9 +2406,53 @@ static int ixgbe_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) return 0; } +static int ixgbe_set_wol_acpi(struct net_device *netdev, + struct ethtool_wolinfo *wol) +{ + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); + struct ixgbe_hw *hw = &adapter->hw; + u32 grc; + + if (ixgbe_wol_exclusion(adapter, wol)) + return wol->wolopts ? -EOPNOTSUPP : 0; + + /* disable APM wakeup */ + grc = IXGBE_READ_REG(hw, IXGBE_GRC_X550EM_a); + grc &= ~IXGBE_GRC_APME; + IXGBE_WRITE_REG(hw, IXGBE_GRC_X550EM_a, grc); + + /* erase existing filters */ + IXGBE_WRITE_REG(hw, IXGBE_WUFC, 0); + adapter->wol = 0; + + if (wol->wolopts & WAKE_UCAST) + adapter->wol |= IXGBE_WUFC_EX; + if (wol->wolopts & WAKE_MCAST) + adapter->wol |= IXGBE_WUFC_MC; + if (wol->wolopts & WAKE_BCAST) + adapter->wol |= IXGBE_WUFC_BC; + + IXGBE_WRITE_REG(hw, IXGBE_WUC, IXGBE_WUC_PME_EN); + IXGBE_WRITE_REG(hw, IXGBE_WUFC, adapter->wol); + + hw->wol_enabled = adapter->wol; + device_set_wakeup_enable(&adapter->pdev->dev, adapter->wol); + + return 0; +} + +static int ixgbe_set_wol_e610(struct net_device *netdev, + struct ethtool_wolinfo *wol) +{ + if (wol->wolopts & (WAKE_UCAST | WAKE_MCAST | WAKE_BCAST)) + return ixgbe_set_wol_acpi(netdev, wol); + else + return ixgbe_set_wol(netdev, wol); +} + static int ixgbe_nway_reset(struct net_device *netdev) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); if (netif_running(netdev)) ixgbe_reinit_locked(adapter); @@ -2362,7 +2463,7 @@ static int ixgbe_nway_reset(struct net_device *netdev) static int ixgbe_set_phys_id(struct net_device *netdev, enum ethtool_phys_id_state state) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; if (!hw->mac.ops.led_on || !hw->mac.ops.led_off) @@ -2390,12 +2491,32 @@ static int ixgbe_set_phys_id(struct net_device *netdev, return 0; } +static int ixgbe_set_phys_id_e610(struct net_device *netdev, + enum ethtool_phys_id_state state) +{ + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); + bool led_active; + + switch (state) { + case ETHTOOL_ID_ACTIVE: + led_active = true; + break; + case ETHTOOL_ID_INACTIVE: + led_active = false; + break; + default: + return -EOPNOTSUPP; + } + + return ixgbe_aci_set_port_id_led(&adapter->hw, !led_active); +} + static int ixgbe_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec, struct kernel_ethtool_coalesce *kernel_coal, struct netlink_ext_ack *extack) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); /* only valid if in constant ITR mode */ if (adapter->rx_itr_setting <= 1) @@ -2451,7 +2572,7 @@ static int ixgbe_set_coalesce(struct net_device *netdev, struct kernel_ethtool_coalesce *kernel_coal, struct netlink_ext_ack *extack) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_q_vector *q_vector; int i; u16 tx_itr_param, rx_itr_param, tx_itr_prev; @@ -2677,7 +2798,7 @@ static int ixgbe_rss_indir_tbl_max(struct ixgbe_adapter *adapter) static int ixgbe_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, u32 *rule_locs) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); int ret = -EOPNOTSUPP; switch (cmd->cmd) { @@ -3065,7 +3186,7 @@ static int ixgbe_set_rss_hash_opt(struct ixgbe_adapter *adapter, static int ixgbe_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); int ret = -EOPNOTSUPP; switch (cmd->cmd) { @@ -3092,7 +3213,7 @@ static u32 ixgbe_get_rxfh_key_size(struct net_device *netdev) static u32 ixgbe_rss_indir_size(struct net_device *netdev) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); return ixgbe_rss_indir_tbl_entries(adapter); } @@ -3112,7 +3233,7 @@ static void ixgbe_get_reta(struct ixgbe_adapter *adapter, u32 *indir) static int ixgbe_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); rxfh->hfunc = ETH_RSS_HASH_TOP; @@ -3130,7 +3251,7 @@ static int ixgbe_set_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh, struct netlink_ext_ack *extack) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); int i; u32 reta_entries = ixgbe_rss_indir_tbl_entries(adapter); @@ -3170,9 +3291,9 @@ static int ixgbe_set_rxfh(struct net_device *netdev, } static int ixgbe_get_ts_info(struct net_device *dev, - struct ethtool_ts_info *info) + struct kernel_ethtool_ts_info *info) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); /* we always support timestamping disabled */ info->rx_filters = BIT(HWTSTAMP_FILTER_NONE); @@ -3181,6 +3302,7 @@ static int ixgbe_get_ts_info(struct net_device *dev, case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: info->rx_filters |= BIT(HWTSTAMP_FILTER_ALL); break; case ixgbe_mac_X540: @@ -3196,16 +3318,12 @@ static int ixgbe_get_ts_info(struct net_device *dev, info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | - SOF_TIMESTAMPING_RX_SOFTWARE | - SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_TX_HARDWARE | SOF_TIMESTAMPING_RX_HARDWARE | SOF_TIMESTAMPING_RAW_HARDWARE; if (adapter->ptp_clock) info->phc_index = ptp_clock_index(adapter->ptp_clock); - else - info->phc_index = -1; info->tx_types = BIT(HWTSTAMP_TX_OFF) | @@ -3251,7 +3369,7 @@ static unsigned int ixgbe_max_channels(struct ixgbe_adapter *adapter) static void ixgbe_get_channels(struct net_device *dev, struct ethtool_channels *ch) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); /* report maximum channels */ ch->max_combined = ixgbe_max_channels(adapter); @@ -3288,7 +3406,7 @@ static void ixgbe_get_channels(struct net_device *dev, static int ixgbe_set_channels(struct net_device *dev, struct ethtool_channels *ch) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); unsigned int count = ch->combined_count; u8 max_rss_indices = ixgbe_max_rss_indices(adapter); @@ -3326,7 +3444,7 @@ static int ixgbe_set_channels(struct net_device *dev, static int ixgbe_get_module_info(struct net_device *dev, struct ethtool_modinfo *modinfo) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct ixgbe_hw *hw = &adapter->hw; u8 sff8472_rev, addr_mode; bool page_swap = false; @@ -3372,7 +3490,7 @@ static int ixgbe_get_module_eeprom(struct net_device *dev, struct ethtool_eeprom *ee, u8 *data) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct ixgbe_hw *hw = &adapter->hw; int status = -EFAULT; u8 databyte = 0xFF; @@ -3468,7 +3586,7 @@ ixgbe_get_eee_fw(struct ixgbe_adapter *adapter, struct ethtool_keee *edata) static int ixgbe_get_eee(struct net_device *netdev, struct ethtool_keee *edata) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; if (!(adapter->flags2 & IXGBE_FLAG2_EEE_CAPABLE)) @@ -3482,7 +3600,7 @@ static int ixgbe_get_eee(struct net_device *netdev, struct ethtool_keee *edata) static int ixgbe_set_eee(struct net_device *netdev, struct ethtool_keee *edata) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; struct ethtool_keee eee_data; int ret_val; @@ -3537,7 +3655,7 @@ static int ixgbe_set_eee(struct net_device *netdev, struct ethtool_keee *edata) static u32 ixgbe_get_priv_flags(struct net_device *netdev) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); u32 priv_flags = 0; if (adapter->flags2 & IXGBE_FLAG2_RX_LEGACY) @@ -3554,7 +3672,7 @@ static u32 ixgbe_get_priv_flags(struct net_device *netdev) static int ixgbe_set_priv_flags(struct net_device *netdev, u32 priv_flags) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); unsigned int flags2 = adapter->flags2; unsigned int i; @@ -3637,7 +3755,57 @@ static const struct ethtool_ops ixgbe_ethtool_ops = { .set_link_ksettings = ixgbe_set_link_ksettings, }; +static const struct ethtool_ops ixgbe_ethtool_ops_e610 = { + .supported_coalesce_params = ETHTOOL_COALESCE_USECS, + .get_drvinfo = ixgbe_get_drvinfo, + .get_regs_len = ixgbe_get_regs_len, + .get_regs = ixgbe_get_regs, + .get_wol = ixgbe_get_wol, + .set_wol = ixgbe_set_wol_e610, + .nway_reset = ixgbe_nway_reset, + .get_link = ethtool_op_get_link, + .get_eeprom_len = ixgbe_get_eeprom_len, + .get_eeprom = ixgbe_get_eeprom, + .set_eeprom = ixgbe_set_eeprom, + .get_ringparam = ixgbe_get_ringparam, + .set_ringparam = ixgbe_set_ringparam, + .get_pause_stats = ixgbe_get_pause_stats, + .get_pauseparam = ixgbe_get_pauseparam, + .set_pauseparam = ixgbe_set_pauseparam_e610, + .get_msglevel = ixgbe_get_msglevel, + .set_msglevel = ixgbe_set_msglevel, + .self_test = ixgbe_diag_test, + .get_strings = ixgbe_get_strings, + .set_phys_id = ixgbe_set_phys_id_e610, + .get_sset_count = ixgbe_get_sset_count, + .get_ethtool_stats = ixgbe_get_ethtool_stats, + .get_coalesce = ixgbe_get_coalesce, + .set_coalesce = ixgbe_set_coalesce, + .get_rxnfc = ixgbe_get_rxnfc, + .set_rxnfc = ixgbe_set_rxnfc, + .get_rxfh_indir_size = ixgbe_rss_indir_size, + .get_rxfh_key_size = ixgbe_get_rxfh_key_size, + .get_rxfh = ixgbe_get_rxfh, + .set_rxfh = ixgbe_set_rxfh, + .get_eee = ixgbe_get_eee, + .set_eee = ixgbe_set_eee, + .get_channels = ixgbe_get_channels, + .set_channels = ixgbe_set_channels, + .get_priv_flags = ixgbe_get_priv_flags, + .set_priv_flags = ixgbe_set_priv_flags, + .get_ts_info = ixgbe_get_ts_info, + .get_module_info = ixgbe_get_module_info, + .get_module_eeprom = ixgbe_get_module_eeprom, + .get_link_ksettings = ixgbe_get_link_ksettings, + .set_link_ksettings = ixgbe_set_link_ksettings, +}; + void ixgbe_set_ethtool_ops(struct net_device *netdev) { - netdev->ethtool_ops = &ixgbe_ethtool_ops; + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); + + if (adapter->hw.mac.type == ixgbe_mac_e610) + netdev->ethtool_ops = &ixgbe_ethtool_ops_e610; + else + netdev->ethtool_ops = &ixgbe_ethtool_ops; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c index 18d63c8c2ff4..7dcf6ecd157b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c @@ -56,7 +56,7 @@ int ixgbe_fcoe_ddp_put(struct net_device *netdev, u16 xid) if (xid >= netdev->fcoe_ddp_xid) return 0; - adapter = netdev_priv(netdev); + adapter = ixgbe_from_netdev(netdev); fcoe = &adapter->fcoe; ddp = &fcoe->ddp[xid]; if (!ddp->udl) @@ -153,7 +153,7 @@ static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid, if (!netdev || !sgl) return 0; - adapter = netdev_priv(netdev); + adapter = ixgbe_from_netdev(netdev); if (xid >= netdev->fcoe_ddp_xid) { e_warn(drv, "xid=0x%x out-of-range\n", xid); return 0; @@ -834,7 +834,7 @@ static void ixgbe_fcoe_ddp_disable(struct ixgbe_adapter *adapter) */ int ixgbe_fcoe_enable(struct net_device *netdev) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_fcoe *fcoe = &adapter->fcoe; atomic_inc(&fcoe->refcnt); @@ -858,7 +858,7 @@ int ixgbe_fcoe_enable(struct net_device *netdev) /* enable FCoE and notify stack */ adapter->flags |= IXGBE_FLAG_FCOE_ENABLED; - netdev->features |= NETIF_F_FCOE_MTU; + netdev->fcoe_mtu = true; netdev_features_change(netdev); /* release existing queues and reallocate them */ @@ -881,7 +881,7 @@ int ixgbe_fcoe_enable(struct net_device *netdev) */ int ixgbe_fcoe_disable(struct net_device *netdev) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); if (!atomic_dec_and_test(&adapter->fcoe.refcnt)) return -EINVAL; @@ -898,7 +898,7 @@ int ixgbe_fcoe_disable(struct net_device *netdev) /* disable FCoE and notify stack */ adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED; - netdev->features &= ~NETIF_F_FCOE_MTU; + netdev->fcoe_mtu = false; netdev_features_change(netdev); @@ -927,7 +927,7 @@ int ixgbe_fcoe_disable(struct net_device *netdev) int ixgbe_fcoe_get_wwn(struct net_device *netdev, u64 *wwn, int type) { u16 prefix = 0xffff; - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_mac_info *mac = &adapter->hw.mac; switch (type) { @@ -967,7 +967,7 @@ 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) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; u64 dsn; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.c new file mode 100644 index 000000000000..49d3b66add7e --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.c @@ -0,0 +1,707 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2025 Intel Corporation. */ + +#include <linux/crc32.h> +#include <linux/pldmfw.h> +#include <linux/uuid.h> + +#include "ixgbe.h" +#include "ixgbe_fw_update.h" + +struct ixgbe_fwu_priv { + struct pldmfw context; + + struct ixgbe_adapter *adapter; + struct netlink_ext_ack *extack; + + /* Track which NVM banks to activate at the end of the update */ + u8 activate_flags; + bool emp_reset_available; +}; + +/** + * ixgbe_send_package_data - Send record package data to firmware + * @context: PLDM fw update structure + * @data: pointer to the package data + * @length: length of the package data + * + * Send a copy of the package data associated with the PLDM record matching + * this device to the firmware. + * + * Note that this function sends an AdminQ command that will fail unless the + * NVM resource has been acquired. + * + * Return: zero on success, or a negative error code on failure. + */ +static int ixgbe_send_package_data(struct pldmfw *context, + const u8 *data, u16 length) +{ + struct ixgbe_fwu_priv *priv = container_of(context, + struct ixgbe_fwu_priv, + context); + struct ixgbe_adapter *adapter = priv->adapter; + struct ixgbe_hw *hw = &adapter->hw; + u8 *package_data; + int err; + + package_data = kmemdup(data, length, GFP_KERNEL); + if (!package_data) + return -ENOMEM; + + err = ixgbe_nvm_set_pkg_data(hw, false, package_data, length); + + kfree(package_data); + + return err; +} + +/** + * ixgbe_check_component_response - Report firmware response to a component + * @adapter: device private data structure + * @response: indicates whether this component can be updated + * @code: code indicating reason for response + * @extack: netlink extended ACK structure + * + * Check whether firmware indicates if this component can be updated. Report + * a suitable error message over the netlink extended ACK if the component + * cannot be updated. + * + * Return: 0 if the component can be updated, or -ECANCELED if the + * firmware indicates the component cannot be updated. + */ +static int ixgbe_check_component_response(struct ixgbe_adapter *adapter, + u8 response, u8 code, + struct netlink_ext_ack *extack) +{ + struct ixgbe_hw *hw = &adapter->hw; + + switch (response) { + case IXGBE_ACI_NVM_PASS_COMP_CAN_BE_UPDATED: + /* Firmware indicated this update is good to proceed. */ + return 0; + case IXGBE_ACI_NVM_PASS_COMP_CAN_MAY_BE_UPDATEABLE: + NL_SET_ERR_MSG_MOD(extack, + "Firmware recommends not updating, as it may result in a downgrade. Continuing anyways"); + return 0; + case IXGBE_ACI_NVM_PASS_COMP_CAN_NOT_BE_UPDATED: + NL_SET_ERR_MSG_MOD(extack, "Firmware has rejected updating."); + break; + case IXGBE_ACI_NVM_PASS_COMP_PARTIAL_CHECK: + if (hw->mac.ops.fw_recovery_mode && + hw->mac.ops.fw_recovery_mode(hw)) + return 0; + break; + } + + switch (code) { + case IXGBE_ACI_NVM_PASS_COMP_STAMP_IDENTICAL_CODE: + NL_SET_ERR_MSG_MOD(extack, + "Component comparison stamp is identical to running image"); + break; + case IXGBE_ACI_NVM_PASS_COMP_STAMP_LOWER: + NL_SET_ERR_MSG_MOD(extack, + "Component comparison stamp is lower than running image"); + break; + case IXGBE_ACI_NVM_PASS_COMP_INVALID_STAMP_CODE: + NL_SET_ERR_MSG_MOD(extack, + "Component comparison stamp is invalid"); + break; + case IXGBE_ACI_NVM_PASS_COMP_CONFLICT_CODE: + NL_SET_ERR_MSG_MOD(extack, + "Component table conflict occurred"); + break; + case IXGBE_ACI_NVM_PASS_COMP_PRE_REQ_NOT_MET_CODE: + NL_SET_ERR_MSG_MOD(extack, "Component pre-requisites not met"); + break; + case IXGBE_ACI_NVM_PASS_COMP_NOT_SUPPORTED_CODE: + NL_SET_ERR_MSG_MOD(extack, "Component not supported"); + break; + case IXGBE_ACI_NVM_PASS_COMP_CANNOT_DOWNGRADE_CODE: + NL_SET_ERR_MSG_MOD(extack, "Component cannot be downgraded"); + break; + case IXGBE_ACI_NVM_PASS_COMP_INCOMPLETE_IMAGE_CODE: + NL_SET_ERR_MSG_MOD(extack, "Incomplete component image"); + break; + case IXGBE_ACI_NVM_PASS_COMP_VER_STR_IDENTICAL_CODE: + NL_SET_ERR_MSG_MOD(extack, + "Component version is identical to running image"); + break; + case IXGBE_ACI_NVM_PASS_COMP_VER_STR_LOWER_CODE: + NL_SET_ERR_MSG_MOD(extack, + "Component version is lower than the running image"); + break; + default: + NL_SET_ERR_MSG_MOD(extack, + "Received unexpected response code from firmware"); + break; + } + + return -ECANCELED; +} + +/** + * ixgbe_send_component_table - Send PLDM component table to firmware + * @context: PLDM fw update structure + * @component: the component to process + * @transfer_flag: relative transfer order of this component + * + * Read relevant data from the component and forward it to the device + * firmware. Check the response to determine if the firmware indicates that + * the update can proceed. + * + * This function sends ACI commands related to the NVM, and assumes that + * the NVM resource has been acquired. + * + * Return: 0 on success, or a negative error code on failure. + */ +static int ixgbe_send_component_table(struct pldmfw *context, + struct pldmfw_component *component, + u8 transfer_flag) +{ + struct ixgbe_fwu_priv *priv = container_of(context, + struct ixgbe_fwu_priv, + context); + struct ixgbe_adapter *adapter = priv->adapter; + struct netlink_ext_ack *extack = priv->extack; + struct ixgbe_aci_cmd_nvm_comp_tbl *comp_tbl; + u8 comp_response, comp_response_code; + struct ixgbe_hw *hw = &adapter->hw; + size_t length; + int err; + + switch (component->identifier) { + case NVM_COMP_ID_OROM: + case NVM_COMP_ID_NVM: + case NVM_COMP_ID_NETLIST: + break; + default: + NL_SET_ERR_MSG_MOD(extack, + "Unable to update due to unknown firmware component"); + return -EOPNOTSUPP; + } + + length = struct_size(comp_tbl, cvs, component->version_len); + comp_tbl = kzalloc(length, GFP_KERNEL); + if (!comp_tbl) + return -ENOMEM; + + comp_tbl->comp_class = cpu_to_le16(component->classification); + comp_tbl->comp_id = cpu_to_le16(component->identifier); + comp_tbl->comp_class_idx = FWU_COMP_CLASS_IDX_NOT_USE; + comp_tbl->comp_cmp_stamp = cpu_to_le32(component->comparison_stamp); + comp_tbl->cvs_type = component->version_type; + comp_tbl->cvs_len = component->version_len; + + memcpy(comp_tbl->cvs, component->version_string, + component->version_len); + + err = ixgbe_nvm_pass_component_tbl(hw, (u8 *)comp_tbl, length, + transfer_flag, &comp_response, + &comp_response_code); + + kfree(comp_tbl); + + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Failed to transfer component table to firmware"); + return -EIO; + } + + return ixgbe_check_component_response(adapter, + comp_response, + comp_response_code, extack); +} + +/** + * ixgbe_write_one_nvm_block - Write an NVM block and await completion response + * @adapter: the PF data structure + * @module: the module to write to + * @offset: offset in bytes + * @block_size: size of the block to write, up to 4k + * @block: pointer to block of data to write + * @last_cmd: whether this is the last command + * @extack: netlink extended ACK structure + * + * Write a block of data to a flash module, and await for the completion + * response message from firmware. + * + * Note this function assumes the caller has acquired the NVM resource. + * + * On successful return, reset level indicates the device reset required to + * complete the update. + * + * 0 - IXGBE_ACI_NVM_POR_FLAG - A full power on is required + * 1 - IXGBE_ACI_NVM_PERST_FLAG - A cold PCIe reset is required + * 2 - IXGBE_ACI_NVM_EMPR_FLAG - An EMP reset is required + * + * Return: 0 on success, or a negative error code on failure. + */ +static int ixgbe_write_one_nvm_block(struct ixgbe_adapter *adapter, + u16 module, u32 offset, + u16 block_size, u8 *block, bool last_cmd, + struct netlink_ext_ack *extack) +{ + struct ixgbe_hw *hw = &adapter->hw; + + return ixgbe_aci_update_nvm(hw, module, offset, block_size, block, + last_cmd, 0); +} + +/** + * ixgbe_write_nvm_module - Write data to an NVM module + * @adapter: the PF driver structure + * @module: the module id to program + * @component: the name of the component being updated + * @image: buffer of image data to write to the NVM + * @length: length of the buffer + * @extack: netlink extended ACK structure + * + * Loop over the data for a given NVM module and program it in 4 Kb + * blocks. Notify devlink core of progress after each block is programmed. + * Loops over a block of data and programs the NVM in 4k block chunks. + * + * Note this function assumes the caller has acquired the NVM resource. + * + * Return: 0 on success, or a negative error code on failure. + */ +static int ixgbe_write_nvm_module(struct ixgbe_adapter *adapter, u16 module, + const char *component, const u8 *image, + u32 length, + struct netlink_ext_ack *extack) +{ + struct devlink *devlink = adapter->devlink; + u32 offset = 0; + bool last_cmd; + u8 *block; + int err; + + devlink_flash_update_status_notify(devlink, "Flashing", + component, 0, length); + + block = kzalloc(IXGBE_ACI_MAX_BUFFER_SIZE, GFP_KERNEL); + if (!block) + return -ENOMEM; + + do { + u32 block_size; + + block_size = min_t(u32, IXGBE_ACI_MAX_BUFFER_SIZE, + length - offset); + last_cmd = !(offset + block_size < length); + + memcpy(block, image + offset, block_size); + + err = ixgbe_write_one_nvm_block(adapter, module, offset, + block_size, block, last_cmd, + extack); + if (err) + break; + + offset += block_size; + + devlink_flash_update_status_notify(devlink, "Flashing", + component, offset, length); + } while (!last_cmd); + + if (err) + devlink_flash_update_status_notify(devlink, "Flashing failed", + component, length, length); + else + devlink_flash_update_status_notify(devlink, "Flashing done", + component, length, length); + + kfree(block); + + return err; +} + +/* Length in seconds to wait before timing out when erasing a flash module. + * Yes, erasing really can take minutes to complete. + */ +#define IXGBE_FW_ERASE_TIMEOUT 300 + +/** + * ixgbe_erase_nvm_module - Erase an NVM module and await firmware completion + * @adapter: the PF data structure + * @module: the module to erase + * @component: name of the component being updated + * @extack: netlink extended ACK structure + * + * Erase the inactive NVM bank associated with this module, and await for + * a completion response message from firmware. + * + * Note this function assumes the caller has acquired the NVM resource. + * + * Return: 0 on success, or a negative error code on failure. + */ +static int ixgbe_erase_nvm_module(struct ixgbe_adapter *adapter, u16 module, + const char *component, + struct netlink_ext_ack *extack) +{ + struct devlink *devlink = adapter->devlink; + struct ixgbe_hw *hw = &adapter->hw; + int err; + + devlink_flash_update_timeout_notify(devlink, "Erasing", component, + IXGBE_FW_ERASE_TIMEOUT); + + err = ixgbe_aci_erase_nvm(hw, module); + if (err) + devlink_flash_update_status_notify(devlink, "Erasing failed", + component, 0, 0); + else + devlink_flash_update_status_notify(devlink, "Erasing done", + component, 0, 0); + + return err; +} + +/** + * ixgbe_switch_flash_banks - Tell firmware to switch NVM banks + * @adapter: Pointer to the PF data structure + * @activate_flags: flags used for the activation command + * @emp_reset_available: on return, indicates if EMP reset is available + * @extack: netlink extended ACK structure + * + * Notify firmware to activate the newly written flash banks, and wait for the + * firmware response. + * + * Return: 0 on success or an error code on failure. + */ +static int ixgbe_switch_flash_banks(struct ixgbe_adapter *adapter, + u8 activate_flags, + bool *emp_reset_available, + struct netlink_ext_ack *extack) +{ + struct ixgbe_hw *hw = &adapter->hw; + u8 response_flags; + int err; + + err = ixgbe_nvm_write_activate(hw, activate_flags, &response_flags); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Failed to switch active flash banks"); + return err; + } + + if (emp_reset_available) { + if (hw->dev_caps.common_cap.reset_restrict_support) + *emp_reset_available = + response_flags & IXGBE_ACI_NVM_EMPR_ENA; + else + *emp_reset_available = true; + } + + return 0; +} + +/** + * ixgbe_flash_component - Flash a component of the NVM + * @context: PLDM fw update structure + * @component: the component table to program + * + * Program the flash contents for a given component. First, determine the + * module id. Then, erase the secondary bank for this module. Finally, write + * the contents of the component to the NVM. + * + * Note this function assumes the caller has acquired the NVM resource. + * + * Return: 0 on success, or a negative error code on failure. + */ +static int ixgbe_flash_component(struct pldmfw *context, + struct pldmfw_component *component) +{ + struct ixgbe_fwu_priv *priv = container_of(context, + struct ixgbe_fwu_priv, + context); + struct netlink_ext_ack *extack = priv->extack; + struct ixgbe_adapter *adapter = priv->adapter; + const char *name; + u16 module; + int err; + u8 flag; + + switch (component->identifier) { + case NVM_COMP_ID_OROM: + module = IXGBE_E610_SR_1ST_OROM_BANK_PTR; + flag = IXGBE_ACI_NVM_ACTIV_SEL_OROM; + name = "fw.undi"; + break; + case NVM_COMP_ID_NVM: + module = IXGBE_E610_SR_1ST_NVM_BANK_PTR; + flag = IXGBE_ACI_NVM_ACTIV_SEL_NVM; + name = "fw.mgmt"; + break; + case NVM_COMP_ID_NETLIST: + module = IXGBE_E610_SR_NETLIST_BANK_PTR; + flag = IXGBE_ACI_NVM_ACTIV_SEL_NETLIST; + name = "fw.netlist"; + break; + + default: + return -EOPNOTSUPP; + } + + /* Mark this component for activating at the end. */ + priv->activate_flags |= flag; + + err = ixgbe_erase_nvm_module(adapter, module, name, extack); + if (err) + return err; + + return ixgbe_write_nvm_module(adapter, module, name, + component->component_data, + component->component_size, extack); +} + +/** + * ixgbe_finalize_update - Perform last steps to complete device update + * @context: PLDM fw update structure + * + * Called as the last step of the update process. Complete the update by + * telling the firmware to switch active banks, and perform a reset of + * configured. + * + * Return: 0 on success, or an error code on failure. + */ +static int ixgbe_finalize_update(struct pldmfw *context) +{ + struct ixgbe_fwu_priv *priv = container_of(context, + struct ixgbe_fwu_priv, + context); + struct ixgbe_adapter *adapter = priv->adapter; + struct netlink_ext_ack *extack = priv->extack; + struct devlink *devlink = adapter->devlink; + int err; + + /* Finally, notify firmware to activate the written NVM banks */ + err = ixgbe_switch_flash_banks(adapter, priv->activate_flags, + &priv->emp_reset_available, extack); + if (err) + return err; + + adapter->fw_emp_reset_disabled = !priv->emp_reset_available; + + if (!adapter->fw_emp_reset_disabled) + devlink_flash_update_status_notify(devlink, + "Suggested is to activate new firmware by devlink reload, if it doesn't work then a power cycle is required", + NULL, 0, 0); + + return 0; +} + +static const struct pldmfw_ops ixgbe_fwu_ops_e610 = { + .match_record = &pldmfw_op_pci_match_record, + .send_package_data = &ixgbe_send_package_data, + .send_component_table = &ixgbe_send_component_table, + .flash_component = &ixgbe_flash_component, + .finalize_update = &ixgbe_finalize_update, +}; + +/** + * ixgbe_get_pending_updates - Check if the component has a pending update + * @adapter: the PF driver structure + * @pending: on return, bitmap of updates pending + * @extack: Netlink extended ACK + * + * Check if the device has any pending updates on any flash components. + * + * Return: 0 on success, or a negative error code on failure. Update + * pending with the bitmap of pending updates. + */ +int ixgbe_get_pending_updates(struct ixgbe_adapter *adapter, u8 *pending, + struct netlink_ext_ack *extack) +{ + struct ixgbe_hw_dev_caps *dev_caps; + struct ixgbe_hw *hw = &adapter->hw; + int err; + + dev_caps = kzalloc(sizeof(*dev_caps), GFP_KERNEL); + if (!dev_caps) + return -ENOMEM; + + err = ixgbe_discover_dev_caps(hw, dev_caps); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Unable to read device capabilities"); + kfree(dev_caps); + return -EIO; + } + + *pending = 0; + + if (dev_caps->common_cap.nvm_update_pending_nvm) + *pending |= IXGBE_ACI_NVM_ACTIV_SEL_NVM; + + if (dev_caps->common_cap.nvm_update_pending_orom) + *pending |= IXGBE_ACI_NVM_ACTIV_SEL_OROM; + + if (dev_caps->common_cap.nvm_update_pending_netlist) + *pending |= IXGBE_ACI_NVM_ACTIV_SEL_NETLIST; + + kfree(dev_caps); + + return 0; +} + +/** + * ixgbe_cancel_pending_update - Cancel any pending update for a component + * @adapter: the PF driver structure + * @component: if not NULL, the name of the component being updated + * @extack: Netlink extended ACK structure + * + * Cancel any pending update for the specified component. If component is + * NULL, all device updates will be canceled. + * + * Return: 0 on success, or a negative error code on failure. + */ +static int ixgbe_cancel_pending_update(struct ixgbe_adapter *adapter, + const char *component, + struct netlink_ext_ack *extack) +{ + struct devlink *devlink = adapter->devlink; + struct ixgbe_hw *hw = &adapter->hw; + u8 pending; + int err; + + err = ixgbe_get_pending_updates(adapter, &pending, extack); + if (err) + return err; + + /* If the flash_update request is for a specific component, ignore all + * of the other components. + */ + if (component) { + if (strcmp(component, "fw.mgmt") == 0) + pending &= IXGBE_ACI_NVM_ACTIV_SEL_NVM; + else if (strcmp(component, "fw.undi") == 0) + pending &= IXGBE_ACI_NVM_ACTIV_SEL_OROM; + else if (strcmp(component, "fw.netlist") == 0) + pending &= IXGBE_ACI_NVM_ACTIV_SEL_NETLIST; + else + return -EINVAL; + } + + /* There is no previous pending update, so this request may continue */ + if (!pending) + return 0; + + /* In order to allow overwriting a previous pending update, notify + * firmware to cancel that update by issuing the appropriate command. + */ + devlink_flash_update_status_notify(devlink, + "Canceling previous pending update", + component, 0, 0); + + err = ixgbe_acquire_nvm(hw, IXGBE_RES_WRITE); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Failed to acquire device flash lock"); + return -EIO; + } + + pending |= IXGBE_ACI_NVM_REVERT_LAST_ACTIV; + err = ixgbe_switch_flash_banks(adapter, pending, NULL, extack); + + ixgbe_release_nvm(hw); + + return err; +} + +/** + * ixgbe_flash_pldm_image - Write a PLDM-formatted firmware image to the device + * @devlink: pointer to devlink associated with the device to update + * @params: devlink flash update parameters + * @extack: netlink extended ACK structure + * + * Parse the data for a given firmware file, verifying that it is a valid PLDM + * formatted image that matches this device. + * + * Extract the device record Package Data and Component Tables and send them + * to the firmware. Extract and write the flash data for each of the three + * main flash components, "fw.mgmt", "fw.undi", and "fw.netlist". Notify + * firmware once the data is written to the inactive banks. + * + * Return: 0 on success or a negative error code on failure. + */ +int ixgbe_flash_pldm_image(struct devlink *devlink, + struct devlink_flash_update_params *params, + struct netlink_ext_ack *extack) +{ + struct ixgbe_adapter *adapter = devlink_priv(devlink); + struct device *dev = &adapter->pdev->dev; + struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_fwu_priv priv; + u8 preservation; + int err; + + if (hw->mac.type != ixgbe_mac_e610) + return -EOPNOTSUPP; + + switch (params->overwrite_mask) { + case 0: + /* preserve all settings and identifiers */ + preservation = IXGBE_ACI_NVM_PRESERVE_ALL; + break; + case DEVLINK_FLASH_OVERWRITE_SETTINGS: + /* Overwrite settings, but preserve vital information such as + * device identifiers. + */ + preservation = IXGBE_ACI_NVM_PRESERVE_SELECTED; + break; + case (DEVLINK_FLASH_OVERWRITE_SETTINGS | + DEVLINK_FLASH_OVERWRITE_IDENTIFIERS): + /* overwrite both settings and identifiers, preserve nothing */ + preservation = IXGBE_ACI_NVM_NO_PRESERVATION; + break; + default: + NL_SET_ERR_MSG_MOD(extack, + "Requested overwrite mask is not supported"); + return -EOPNOTSUPP; + } + + /* Cannot get caps in recovery mode, so lack of nvm_unified_update bit + * cannot lead to error + */ + if (!hw->dev_caps.common_cap.nvm_unified_update && + (hw->mac.ops.fw_recovery_mode && + !hw->mac.ops.fw_recovery_mode(hw))) { + NL_SET_ERR_MSG_MOD(extack, + "Current firmware does not support unified update"); + return -EOPNOTSUPP; + } + + memset(&priv, 0, sizeof(priv)); + + priv.context.ops = &ixgbe_fwu_ops_e610; + priv.context.dev = dev; + priv.extack = extack; + priv.adapter = adapter; + priv.activate_flags = preservation; + + devlink_flash_update_status_notify(devlink, + "Preparing to flash", NULL, 0, 0); + + err = ixgbe_cancel_pending_update(adapter, NULL, extack); + if (err) + return err; + + err = ixgbe_acquire_nvm(hw, IXGBE_RES_WRITE); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Failed to acquire device flash lock"); + return -EIO; + } + + err = pldmfw_flash_image(&priv.context, params->fw); + if (err == -ENOENT) { + NL_SET_ERR_MSG_MOD(extack, + "Firmware image has no record matching this device"); + } else if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to flash PLDM image"); + } + + ixgbe_release_nvm(hw); + + return err; +} diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.h new file mode 100644 index 000000000000..abdd708c93df --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2025 Intel Corporation. */ + +#ifndef _IXGBE_FW_UPDATE_H_ +#define _IXGBE_FW_UPDATE_H_ + +int ixgbe_flash_pldm_image(struct devlink *devlink, + struct devlink_flash_update_params *params, + struct netlink_ext_ack *extack); +int ixgbe_get_pending_updates(struct ixgbe_adapter *adapter, u8 *pending, + struct netlink_ext_ack *extack); +#endif diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c index 866024f2b9ee..d1f4073b36f9 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c @@ -9,7 +9,7 @@ #define IXGBE_IPSEC_KEY_BITS 160 static const char aes_gcm_name[] = "rfc4106(gcm(aes))"; -static void ixgbe_ipsec_del_sa(struct xfrm_state *xs); +static void ixgbe_ipsec_del_sa(struct net_device *dev, struct xfrm_state *xs); /** * ixgbe_ipsec_set_tx_sa - set the Tx SA registers @@ -321,7 +321,7 @@ void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter) if (r->used) { if (r->mode & IXGBE_RXTXMOD_VF) - ixgbe_ipsec_del_sa(r->xs); + ixgbe_ipsec_del_sa(adapter->netdev, r->xs); else ixgbe_ipsec_set_rx_sa(hw, i, r->xs->id.spi, r->key, r->salt, @@ -330,7 +330,7 @@ void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter) if (t->used) { if (t->mode & IXGBE_RXTXMOD_VF) - ixgbe_ipsec_del_sa(t->xs); + ixgbe_ipsec_del_sa(adapter->netdev, t->xs); else ixgbe_ipsec_set_tx_sa(hw, i, t->key, t->salt); } @@ -417,6 +417,7 @@ static struct xfrm_state *ixgbe_ipsec_find_rx_state(struct ixgbe_ipsec *ipsec, /** * ixgbe_ipsec_parse_proto_keys - find the key and salt based on the protocol + * @dev: pointer to net device * @xs: pointer to xfrm_state struct * @mykey: pointer to key array to populate * @mysalt: pointer to salt value to populate @@ -424,10 +425,10 @@ static struct xfrm_state *ixgbe_ipsec_find_rx_state(struct ixgbe_ipsec *ipsec, * This copies the protocol keys and salt to our own data tables. The * 82599 family only supports the one algorithm. **/ -static int ixgbe_ipsec_parse_proto_keys(struct xfrm_state *xs, +static int ixgbe_ipsec_parse_proto_keys(struct net_device *dev, + struct xfrm_state *xs, u32 *mykey, u32 *mysalt) { - struct net_device *dev = xs->xso.real_dev; unsigned char *key_data; char *alg_name = NULL; int key_len; @@ -473,12 +474,13 @@ static int ixgbe_ipsec_parse_proto_keys(struct xfrm_state *xs, /** * ixgbe_ipsec_check_mgmt_ip - make sure there is no clash with mgmt IP filters + * @dev: pointer to net device * @xs: pointer to transformer state struct **/ -static int ixgbe_ipsec_check_mgmt_ip(struct xfrm_state *xs) +static int ixgbe_ipsec_check_mgmt_ip(struct net_device *dev, + struct xfrm_state *xs) { - struct net_device *dev = xs->xso.real_dev; - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct ixgbe_hw *hw = &adapter->hw; u32 mfval, manc, reg; int num_filters = 4; @@ -556,14 +558,15 @@ static int ixgbe_ipsec_check_mgmt_ip(struct xfrm_state *xs) /** * ixgbe_ipsec_add_sa - program device with a security association + * @dev: pointer to device to program * @xs: pointer to transformer state struct * @extack: extack point to fill failure reason **/ -static int ixgbe_ipsec_add_sa(struct xfrm_state *xs, +static int ixgbe_ipsec_add_sa(struct net_device *dev, + struct xfrm_state *xs, struct netlink_ext_ack *extack) { - struct net_device *dev = xs->xso.real_dev; - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct ixgbe_ipsec *ipsec = adapter->ipsec; struct ixgbe_hw *hw = &adapter->hw; int checked, match, first; @@ -581,7 +584,7 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs, return -EINVAL; } - if (ixgbe_ipsec_check_mgmt_ip(xs)) { + if (ixgbe_ipsec_check_mgmt_ip(dev, xs)) { NL_SET_ERR_MSG_MOD(extack, "IPsec IP addr clash with mgmt filters"); return -EINVAL; } @@ -615,7 +618,7 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs, rsa.decrypt = xs->ealg || xs->aead; /* get the key and salt */ - ret = ixgbe_ipsec_parse_proto_keys(xs, rsa.key, &rsa.salt); + ret = ixgbe_ipsec_parse_proto_keys(dev, xs, rsa.key, &rsa.salt); if (ret) { NL_SET_ERR_MSG_MOD(extack, "Failed to get key data for Rx SA table"); return ret; @@ -724,7 +727,7 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs, if (xs->id.proto & IPPROTO_ESP) tsa.encrypt = xs->ealg || xs->aead; - ret = ixgbe_ipsec_parse_proto_keys(xs, tsa.key, &tsa.salt); + ret = ixgbe_ipsec_parse_proto_keys(dev, xs, tsa.key, &tsa.salt); if (ret) { NL_SET_ERR_MSG_MOD(extack, "Failed to get key data for Tx SA table"); memset(&tsa, 0, sizeof(tsa)); @@ -752,12 +755,12 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs, /** * ixgbe_ipsec_del_sa - clear out this specific SA + * @dev: pointer to device to program * @xs: pointer to transformer state struct **/ -static void ixgbe_ipsec_del_sa(struct xfrm_state *xs) +static void ixgbe_ipsec_del_sa(struct net_device *dev, struct xfrm_state *xs) { - struct net_device *dev = xs->xso.real_dev; - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct ixgbe_ipsec *ipsec = adapter->ipsec; struct ixgbe_hw *hw = &adapter->hw; u32 zerobuf[4] = {0, 0, 0, 0}; @@ -817,30 +820,9 @@ static void ixgbe_ipsec_del_sa(struct xfrm_state *xs) } } -/** - * ixgbe_ipsec_offload_ok - can this packet use the xfrm hw offload - * @skb: current data packet - * @xs: pointer to transformer state struct - **/ -static bool ixgbe_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) -{ - if (xs->props.family == AF_INET) { - /* Offload with IPv4 options is not supported yet */ - if (ip_hdr(skb)->ihl != 5) - return false; - } else { - /* Offload with IPv6 extension headers is not support yet */ - if (ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr)) - return false; - } - - return true; -} - static const struct xfrmdev_ops ixgbe_xfrmdev_ops = { .xdo_dev_state_add = ixgbe_ipsec_add_sa, .xdo_dev_state_delete = ixgbe_ipsec_del_sa, - .xdo_dev_offload_ok = ixgbe_ipsec_offload_ok, }; /** @@ -862,7 +844,8 @@ void ixgbe_ipsec_vf_clear(struct ixgbe_adapter *adapter, u32 vf) continue; if (ipsec->rx_tbl[i].mode & IXGBE_RXTXMOD_VF && ipsec->rx_tbl[i].vf == vf) - ixgbe_ipsec_del_sa(ipsec->rx_tbl[i].xs); + ixgbe_ipsec_del_sa(adapter->netdev, + ipsec->rx_tbl[i].xs); } /* search tx sa table */ @@ -871,7 +854,8 @@ void ixgbe_ipsec_vf_clear(struct ixgbe_adapter *adapter, u32 vf) continue; if (ipsec->tx_tbl[i].mode & IXGBE_RXTXMOD_VF && ipsec->tx_tbl[i].vf == vf) - ixgbe_ipsec_del_sa(ipsec->tx_tbl[i].xs); + ixgbe_ipsec_del_sa(adapter->netdev, + ipsec->tx_tbl[i].xs); } } @@ -951,7 +935,7 @@ int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) memcpy(xs->aead->alg_name, aes_gcm_name, sizeof(aes_gcm_name)); /* set up the HW offload */ - err = ixgbe_ipsec_add_sa(xs, NULL); + err = ixgbe_ipsec_add_sa(adapter->netdev, xs, NULL); if (err) goto err_aead; @@ -1055,7 +1039,7 @@ int ixgbe_ipsec_vf_del_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) xs = ipsec->tx_tbl[sa_idx].xs; } - ixgbe_ipsec_del_sa(xs); + ixgbe_ipsec_del_sa(adapter->netdev, xs); /* remove the xs that was made-up in the add request */ kfree_sensitive(xs); @@ -1073,7 +1057,7 @@ int ixgbe_ipsec_tx(struct ixgbe_ring *tx_ring, struct ixgbe_tx_buffer *first, struct ixgbe_ipsec_tx_data *itd) { - struct ixgbe_adapter *adapter = netdev_priv(tx_ring->netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(tx_ring->netdev); struct ixgbe_ipsec *ipsec = adapter->ipsec; struct xfrm_state *xs; struct sec_path *sp; @@ -1163,7 +1147,7 @@ void ixgbe_ipsec_rx(struct ixgbe_ring *rx_ring, union ixgbe_adv_rx_desc *rx_desc, struct sk_buff *skb) { - struct ixgbe_adapter *adapter = netdev_priv(rx_ring->netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(rx_ring->netdev); __le16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info; __le16 ipsec_pkt_types = cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPSEC_AH | IXGBE_RXDADV_PKTTYPE_IPSEC_ESP); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index 0ee943db3dc9..336d47ffb95a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #include "ixgbe.h" #include "ixgbe_sriov.h" @@ -107,6 +107,7 @@ static void ixgbe_get_first_reg_idx(struct ixgbe_adapter *adapter, u8 tc, case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: if (num_tcs > 4) { /* * TCs : TC0/1 TC2/3 TC4-7 @@ -981,7 +982,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, set_bit(__IXGBE_RX_CSUM_UDP_ZERO_ERR, &ring->state); #ifdef IXGBE_FCOE - if (adapter->netdev->features & NETIF_F_FCOE_MTU) { + if (adapter->netdev->fcoe_mtu) { struct ixgbe_ring_feature *f; f = &adapter->ring_feature[RING_F_FCOE]; if ((rxr_idx >= f->offset) && diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index f985252c8c8d..03d31e5b131d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #include <linux/types.h> #include <linux/module.h> @@ -42,11 +42,14 @@ #include "ixgbe.h" #include "ixgbe_common.h" +#include "ixgbe_e610.h" #include "ixgbe_dcb_82599.h" +#include "ixgbe_mbx.h" #include "ixgbe_phy.h" #include "ixgbe_sriov.h" #include "ixgbe_model.h" #include "ixgbe_txrx_common.h" +#include "devlink/devlink.h" char ixgbe_driver_name[] = "ixgbe"; static const char ixgbe_driver_string[] = @@ -72,6 +75,7 @@ static const struct ixgbe_info *ixgbe_info_tbl[] = { [board_x550em_x_fw] = &ixgbe_x550em_x_fw_info, [board_x550em_a] = &ixgbe_x550em_a_info, [board_x550em_a_fw] = &ixgbe_x550em_a_fw_info, + [board_e610] = &ixgbe_e610_info, }; /* ixgbe_pci_tbl - PCI Device ID Table @@ -130,6 +134,11 @@ static const struct pci_device_id ixgbe_pci_tbl[] = { {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_SFP), board_x550em_a }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_1G_T), board_x550em_a_fw }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_1G_T_L), board_x550em_a_fw }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_BACKPLANE), board_e610}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_SFP), board_e610}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_10G_T), board_e610}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_2_5G_T), board_e610}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_SGMII), board_e610}, /* required last entry */ {0, } }; @@ -162,7 +171,6 @@ static int debug = -1; module_param(debug, int, 0); MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); -MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION("Intel(R) 10 Gigabit PCI Express Network Driver"); MODULE_LICENSE("GPL v2"); @@ -173,6 +181,8 @@ static struct workqueue_struct *ixgbe_wq; static bool ixgbe_check_cfg_remove(struct ixgbe_hw *hw, struct pci_dev *pdev); static void ixgbe_watchdog_link_is_down(struct ixgbe_adapter *); +static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *); +static void ixgbe_watchdog_update_link(struct ixgbe_adapter *); static const struct net_device_ops ixgbe_netdev_ops; @@ -236,8 +246,11 @@ static int ixgbe_get_parent_bus_info(struct ixgbe_adapter *adapter) * bandwidth details should be gathered from the parent bus instead of from the * device. Used to ensure that various locations all have the correct device ID * checks. + * + * Return: true if information should be collected from the parent bus, false + * otherwise */ -static inline bool ixgbe_pcie_from_parent(struct ixgbe_hw *hw) +static bool ixgbe_pcie_from_parent(struct ixgbe_hw *hw) { switch (hw->device_id) { case IXGBE_DEV_ID_82599_SFP_SF_QP: @@ -876,6 +889,7 @@ static void ixgbe_set_ivar(struct ixgbe_adapter *adapter, s8 direction, case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: if (direction == -1) { /* other causes */ msix_vector |= IXGBE_IVAR_ALLOC_VAL; @@ -915,6 +929,7 @@ void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter, case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: mask = (qmask & 0xFFFFFFFF); IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS_EX(0), mask); mask = (qmask >> 32); @@ -1025,7 +1040,7 @@ static u64 ixgbe_get_tx_pending(struct ixgbe_ring *ring) return ((head <= tail) ? tail : tail + ring->count) - head; } -static inline bool ixgbe_check_tx_hang(struct ixgbe_ring *tx_ring) +static bool ixgbe_check_tx_hang(struct ixgbe_ring *tx_ring) { u32 tx_done = ixgbe_get_tx_completed(tx_ring); u32 tx_done_old = tx_ring->tx_stats.tx_done_old; @@ -1081,7 +1096,7 @@ static void ixgbe_tx_timeout_reset(struct ixgbe_adapter *adapter) static int ixgbe_tx_maxrate(struct net_device *netdev, int queue_index, u32 maxrate) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; u32 bcnrc_val = ixgbe_link_mbps(adapter); @@ -1909,10 +1924,6 @@ bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, { struct net_device *netdev = rx_ring->netdev; - /* XDP packets use error pointer so abort at this point */ - if (IS_ERR(skb)) - return true; - /* Verify netdev is present, and that packet does not have any * errors that would be unacceptable to the netdev. */ @@ -2095,7 +2106,7 @@ static void ixgbe_put_rx_buffer(struct ixgbe_ring *rx_ring, /* hand second half of page back to the ring */ ixgbe_reuse_rx_page(rx_ring, rx_buffer); } else { - if (!IS_ERR(skb) && IXGBE_CB(skb)->dma == rx_buffer->dma) { + if (skb && IXGBE_CB(skb)->dma == rx_buffer->dma) { /* the page has been released from the ring */ IXGBE_CB(skb)->page_released = true; } else { @@ -2220,9 +2231,9 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, return skb; } -static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, - struct ixgbe_ring *rx_ring, - struct xdp_buff *xdp) +static int ixgbe_run_xdp(struct ixgbe_adapter *adapter, + struct ixgbe_ring *rx_ring, + struct xdp_buff *xdp) { int err, result = IXGBE_XDP_PASS; struct bpf_prog *xdp_prog; @@ -2272,7 +2283,7 @@ out_failure: break; } xdp_out: - return ERR_PTR(-result); + return result; } static unsigned int ixgbe_rx_frame_truesize(struct ixgbe_ring *rx_ring, @@ -2330,6 +2341,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, unsigned int offset = rx_ring->rx_offset; unsigned int xdp_xmit = 0; struct xdp_buff xdp; + int xdp_res = 0; /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ #if (PAGE_SIZE < 8192) @@ -2375,12 +2387,10 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, /* At larger PAGE_SIZE, frame_sz depend on len size */ xdp.frame_sz = ixgbe_rx_frame_truesize(rx_ring, size); #endif - skb = ixgbe_run_xdp(adapter, rx_ring, &xdp); + xdp_res = ixgbe_run_xdp(adapter, rx_ring, &xdp); } - if (IS_ERR(skb)) { - unsigned int xdp_res = -PTR_ERR(skb); - + if (xdp_res) { if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) { xdp_xmit |= xdp_res; ixgbe_rx_buffer_flip(rx_ring, rx_buffer, size); @@ -2400,7 +2410,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, } /* exit if we failed to retrieve a buffer */ - if (!skb) { + if (!xdp_res && !skb) { rx_ring->rx_stats.alloc_rx_buff_failed++; rx_buffer->pagecnt_bias++; break; @@ -2414,7 +2424,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, continue; /* verify the packet layout is correct */ - if (ixgbe_cleanup_headers(rx_ring, rx_desc, skb)) + if (xdp_res || ixgbe_cleanup_headers(rx_ring, rx_desc, skb)) continue; /* probably a little skewed due to removing CRC */ @@ -2515,6 +2525,7 @@ static void ixgbe_configure_msix(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: ixgbe_set_ivar(adapter, -1, 1, v_idx); break; default: @@ -2528,6 +2539,9 @@ static void ixgbe_configure_msix(struct ixgbe_adapter *adapter) IXGBE_EIMS_MAILBOX | IXGBE_EIMS_LSC); + if (adapter->hw.mac.type == ixgbe_mac_e610) + mask &= ~IXGBE_EIMS_FW_EVENT; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIAC, mask); } @@ -2744,6 +2758,7 @@ void ixgbe_write_eitr(struct ixgbe_q_vector *q_vector) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: /* * set the WDIS bit to not clear the timer bits and cause an * immediate assertion of the interrupt @@ -2966,6 +2981,222 @@ static void ixgbe_check_lsc(struct ixgbe_adapter *adapter) } } +/** + * ixgbe_check_phy_fw_load - check if PHY FW load failed + * @adapter: pointer to adapter structure + * @link_cfg_err: bitmap from the link info structure + * + * Check if external PHY FW load failed and print an error message if it did. + */ +static void ixgbe_check_phy_fw_load(struct ixgbe_adapter *adapter, + u8 link_cfg_err) +{ + if (!(link_cfg_err & IXGBE_ACI_LINK_EXTERNAL_PHY_LOAD_FAILURE)) { + adapter->flags2 &= ~IXGBE_FLAG2_PHY_FW_LOAD_FAILED; + return; + } + + if (adapter->flags2 & IXGBE_FLAG2_PHY_FW_LOAD_FAILED) + return; + + if (link_cfg_err & IXGBE_ACI_LINK_EXTERNAL_PHY_LOAD_FAILURE) { + netdev_err(adapter->netdev, "Device failed to load the FW for the external PHY. Please download and install the latest NVM for your device and try again\n"); + adapter->flags2 |= IXGBE_FLAG2_PHY_FW_LOAD_FAILED; + } +} + +/** + * ixgbe_check_module_power - check module power level + * @adapter: pointer to adapter structure + * @link_cfg_err: bitmap from the link info structure + * + * Check module power level returned by a previous call to aci_get_link_info + * and print error messages if module power level is not supported. + */ +static void ixgbe_check_module_power(struct ixgbe_adapter *adapter, + u8 link_cfg_err) +{ + /* If module power level is supported, clear the flag. */ + if (!(link_cfg_err & (IXGBE_ACI_LINK_INVAL_MAX_POWER_LIMIT | + IXGBE_ACI_LINK_MODULE_POWER_UNSUPPORTED))) { + adapter->flags2 &= ~IXGBE_FLAG2_MOD_POWER_UNSUPPORTED; + return; + } + + /* If IXGBE_FLAG2_MOD_POWER_UNSUPPORTED was previously set and the + * above block didn't clear this bit, there's nothing to do. + */ + if (adapter->flags2 & IXGBE_FLAG2_MOD_POWER_UNSUPPORTED) + return; + + if (link_cfg_err & IXGBE_ACI_LINK_INVAL_MAX_POWER_LIMIT) { + netdev_err(adapter->netdev, "The installed module is incompatible with the device's NVM image. Cannot start link.\n"); + adapter->flags2 |= IXGBE_FLAG2_MOD_POWER_UNSUPPORTED; + } else if (link_cfg_err & IXGBE_ACI_LINK_MODULE_POWER_UNSUPPORTED) { + netdev_err(adapter->netdev, "The module's power requirements exceed the device's power supply. Cannot start link.\n"); + adapter->flags2 |= IXGBE_FLAG2_MOD_POWER_UNSUPPORTED; + } +} + +/** + * ixgbe_check_link_cfg_err - check if link configuration failed + * @adapter: pointer to adapter structure + * @link_cfg_err: bitmap from the link info structure + * + * Print if any link configuration failure happens due to the value in the + * link_cfg_err parameter in the link info structure. + */ +static void ixgbe_check_link_cfg_err(struct ixgbe_adapter *adapter, + u8 link_cfg_err) +{ + ixgbe_check_module_power(adapter, link_cfg_err); + ixgbe_check_phy_fw_load(adapter, link_cfg_err); +} + +/** + * ixgbe_process_link_status_event - process the link event + * @adapter: pointer to adapter structure + * @link_up: true if the physical link is up and false if it is down + * @link_speed: current link speed received from the link event + * + * Return: 0 on success or negative value on failure. + */ +static int +ixgbe_process_link_status_event(struct ixgbe_adapter *adapter, bool link_up, + u16 link_speed) +{ + struct ixgbe_hw *hw = &adapter->hw; + int status; + + /* Update the link info structures and re-enable link events, + * don't bail on failure due to other book keeping needed. + */ + status = ixgbe_update_link_info(hw); + if (status) + e_dev_err("Failed to update link status, err %d aq_err %d\n", + status, hw->aci.last_status); + + ixgbe_check_link_cfg_err(adapter, hw->link.link_info.link_cfg_err); + + /* Check if the link state is up after updating link info, and treat + * this event as an UP event since the link is actually UP now. + */ + if (hw->link.link_info.link_info & IXGBE_ACI_LINK_UP) + link_up = true; + + /* Turn off PHY if media was removed. */ + if (!(adapter->flags2 & IXGBE_FLAG2_NO_MEDIA) && + !(hw->link.link_info.link_info & IXGBE_ACI_MEDIA_AVAILABLE)) + adapter->flags2 |= IXGBE_FLAG2_NO_MEDIA; + + if (link_up == adapter->link_up && + link_up == netif_carrier_ok(adapter->netdev) && + link_speed == adapter->link_speed) + return 0; + + adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE; + adapter->link_check_timeout = jiffies; + ixgbe_watchdog_update_link(adapter); + + if (link_up) + ixgbe_watchdog_link_is_up(adapter); + else + ixgbe_watchdog_link_is_down(adapter); + + return 0; +} + +/** + * ixgbe_handle_link_status_event - handle link status event via ACI + * @adapter: pointer to adapter structure + * @e: event structure containing link status info + */ +static void +ixgbe_handle_link_status_event(struct ixgbe_adapter *adapter, + struct ixgbe_aci_event *e) +{ + struct ixgbe_aci_cmd_get_link_status_data *link_data; + u16 link_speed; + bool link_up; + + link_data = (struct ixgbe_aci_cmd_get_link_status_data *)e->msg_buf; + + link_up = !!(link_data->link_info & IXGBE_ACI_LINK_UP); + link_speed = le16_to_cpu(link_data->link_speed); + + if (ixgbe_process_link_status_event(adapter, link_up, link_speed)) + e_dev_warn("Could not process link status event"); +} + +/** + * ixgbe_schedule_fw_event - schedule Firmware event + * @adapter: pointer to the adapter structure + * + * If the adapter is not in down, removing or resetting state, + * an event is scheduled. + */ +static void ixgbe_schedule_fw_event(struct ixgbe_adapter *adapter) +{ + if (!test_bit(__IXGBE_DOWN, &adapter->state) && + !test_bit(__IXGBE_REMOVING, &adapter->state) && + !test_bit(__IXGBE_RESETTING, &adapter->state)) { + adapter->flags2 |= IXGBE_FLAG2_FW_ASYNC_EVENT; + ixgbe_service_event_schedule(adapter); + } +} + +/** + * ixgbe_aci_event_cleanup - release msg_buf memory + * @event: pointer to the event holding msg_buf to be released + * + * Clean memory allocated for event's msg_buf. Implements auto memory cleanup. + */ +static void ixgbe_aci_event_cleanup(struct ixgbe_aci_event *event) +{ + kfree(event->msg_buf); +} + +/** + * ixgbe_handle_fw_event - handle Firmware event + * @adapter: pointer to the adapter structure + * + * Obtain an event from the ACI and then and then process it according to the + * type of the event and the opcode. + */ +static void ixgbe_handle_fw_event(struct ixgbe_adapter *adapter) +{ + struct ixgbe_aci_event event __cleanup(ixgbe_aci_event_cleanup); + struct ixgbe_hw *hw = &adapter->hw; + bool pending = false; + int err; + + if (adapter->flags2 & IXGBE_FLAG2_FW_ASYNC_EVENT) + adapter->flags2 &= ~IXGBE_FLAG2_FW_ASYNC_EVENT; + event.buf_len = IXGBE_ACI_MAX_BUFFER_SIZE; + event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL); + if (!event.msg_buf) + return; + + do { + err = ixgbe_aci_get_event(hw, &event, &pending); + if (err) + break; + + switch (le16_to_cpu(event.desc.opcode)) { + case ixgbe_aci_opc_get_link_status: + ixgbe_handle_link_status_event(adapter, &event); + break; + case ixgbe_aci_opc_temp_tca_event: + e_crit(drv, "%s\n", ixgbe_overheat_msg); + ixgbe_down(adapter); + break; + default: + e_warn(hw, "unknown FW async event captured\n"); + break; + } + } while (pending); +} + static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter, u64 qmask) { @@ -2982,6 +3213,7 @@ static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter, case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: mask = (qmask & 0xFFFFFFFF); if (mask) IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(0), mask); @@ -3035,6 +3267,9 @@ static inline void ixgbe_irq_enable(struct ixgbe_adapter *adapter, bool queues, case ixgbe_mac_X540: case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: + case ixgbe_mac_e610: + mask |= IXGBE_EIMS_FW_EVENT; + fallthrough; case ixgbe_mac_x550em_a: if (adapter->hw.device_id == IXGBE_DEV_ID_X550EM_X_SFP || adapter->hw.device_id == IXGBE_DEV_ID_X550EM_A_SFP || @@ -3091,12 +3326,16 @@ static irqreturn_t ixgbe_msix_other(int irq, void *data) if (eicr & IXGBE_EICR_MAILBOX) ixgbe_msg_task(adapter); + if (eicr & IXGBE_EICR_FW_EVENT) + ixgbe_schedule_fw_event(adapter); + switch (hw->mac.type) { case ixgbe_mac_82599EB: case ixgbe_mac_X540: case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: if (hw->phy.type == ixgbe_phy_x550em_ext_t && (eicr & IXGBE_EICR_GPI_SDP0_X540)) { adapter->flags2 |= IXGBE_FLAG2_PHY_INTERRUPT; @@ -3334,6 +3573,9 @@ static irqreturn_t ixgbe_intr(int irq, void *data) if (eicr & IXGBE_EICR_LSC) ixgbe_check_lsc(adapter); + if (eicr & IXGBE_EICR_FW_EVENT) + ixgbe_schedule_fw_event(adapter); + switch (hw->mac.type) { case ixgbe_mac_82599EB: ixgbe_check_sfp_event(adapter, eicr); @@ -3342,6 +3584,7 @@ static irqreturn_t ixgbe_intr(int irq, void *data) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: if (eicr & IXGBE_EICR_ECC) { e_info(link, "Received ECC Err, initiating reset\n"); set_bit(__IXGBE_RESET_REQUESTED, &adapter->state); @@ -3442,6 +3685,7 @@ static inline void ixgbe_irq_disable(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, 0xFFFF0000); IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(0), ~0); IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(1), ~0); @@ -4359,6 +4603,7 @@ static void ixgbe_setup_rdrxctl(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: if (adapter->num_vfs) rdrxctl |= IXGBE_RDRXCTL_PSP; fallthrough; @@ -4434,7 +4679,7 @@ static void ixgbe_configure_rx(struct ixgbe_adapter *adapter) static int ixgbe_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; /* add VID to filter table */ @@ -4493,7 +4738,7 @@ void ixgbe_update_pf_promisc_vlvf(struct ixgbe_adapter *adapter, u32 vid) static int ixgbe_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; /* remove VID from filter table */ @@ -4526,6 +4771,7 @@ static void ixgbe_vlan_strip_disable(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: for (i = 0; i < adapter->num_rx_queues; i++) { struct ixgbe_ring *ring = adapter->rx_ring[i]; @@ -4564,6 +4810,7 @@ static void ixgbe_vlan_strip_enable(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: for (i = 0; i < adapter->num_rx_queues; i++) { struct ixgbe_ring *ring = adapter->rx_ring[i]; @@ -4716,7 +4963,7 @@ static void ixgbe_restore_vlan(struct ixgbe_adapter *adapter) **/ static int ixgbe_write_mc_addr_list(struct net_device *netdev) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; if (!netif_running(netdev)) @@ -4892,7 +5139,7 @@ int ixgbe_del_mac_filter(struct ixgbe_adapter *adapter, static int ixgbe_uc_sync(struct net_device *netdev, const unsigned char *addr) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); int ret; ret = ixgbe_add_mac_filter(adapter, addr, VMDQ_P(0)); @@ -4902,7 +5149,7 @@ static int ixgbe_uc_sync(struct net_device *netdev, const unsigned char *addr) static int ixgbe_uc_unsync(struct net_device *netdev, const unsigned char *addr) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); ixgbe_del_mac_filter(adapter, addr, VMDQ_P(0)); @@ -4920,7 +5167,7 @@ static int ixgbe_uc_unsync(struct net_device *netdev, const unsigned char *addr) **/ void ixgbe_set_rx_mode(struct net_device *netdev) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; u32 fctrl, vmolr = IXGBE_VMOLR_BAM | IXGBE_VMOLR_AUPE; netdev_features_t features = netdev->features; @@ -5022,7 +5269,7 @@ static void ixgbe_napi_disable_all(struct ixgbe_adapter *adapter) static int ixgbe_udp_tunnel_sync(struct net_device *dev, unsigned int table) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct ixgbe_hw *hw = &adapter->hw; struct udp_tunnel_info ti; @@ -5080,7 +5327,7 @@ static void ixgbe_configure_dcb(struct ixgbe_adapter *adapter) netif_set_tso_max_size(adapter->netdev, 32768); #ifdef IXGBE_FCOE - if (adapter->netdev->features & NETIF_F_FCOE_MTU) + if (adapter->netdev->fcoe_mtu) max_frame = max(max_frame, IXGBE_FCOE_JUMBO_FRAME_SIZE); #endif @@ -5137,8 +5384,7 @@ static int ixgbe_hpbthresh(struct ixgbe_adapter *adapter, int pb) #ifdef IXGBE_FCOE /* FCoE traffic class uses FCOE jumbo frames */ - if ((dev->features & NETIF_F_FCOE_MTU) && - (tc < IXGBE_FCOE_JUMBO_FRAME_SIZE) && + if (dev->fcoe_mtu && tc < IXGBE_FCOE_JUMBO_FRAME_SIZE && (pb == ixgbe_fcoe_get_tc(adapter))) tc = IXGBE_FCOE_JUMBO_FRAME_SIZE; #endif @@ -5149,6 +5395,7 @@ static int ixgbe_hpbthresh(struct ixgbe_adapter *adapter, int pb) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: dv_id = IXGBE_DV_X540(link, tc); break; default: @@ -5198,8 +5445,7 @@ static int ixgbe_lpbthresh(struct ixgbe_adapter *adapter, int pb) #ifdef IXGBE_FCOE /* FCoE traffic class uses FCOE jumbo frames */ - if ((dev->features & NETIF_F_FCOE_MTU) && - (tc < IXGBE_FCOE_JUMBO_FRAME_SIZE) && + if (dev->fcoe_mtu && tc < IXGBE_FCOE_JUMBO_FRAME_SIZE && (pb == netdev_get_prio_tc_map(dev, adapter->fcoe.up))) tc = IXGBE_FCOE_JUMBO_FRAME_SIZE; #endif @@ -5210,6 +5456,7 @@ static int ixgbe_lpbthresh(struct ixgbe_adapter *adapter, int pb) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: dv_id = IXGBE_LOW_DV_X540(tc); break; default: @@ -5512,6 +5759,48 @@ static void ixgbe_configure(struct ixgbe_adapter *adapter) } /** + * ixgbe_enable_link_status_events - enable link status events + * @adapter: pointer to the adapter structure + * @mask: event mask to be set + * + * Enables link status events by invoking ixgbe_configure_lse() + * + * Return: the exit code of the operation. + */ +static int ixgbe_enable_link_status_events(struct ixgbe_adapter *adapter, + u16 mask) +{ + int err; + + err = ixgbe_configure_lse(&adapter->hw, true, mask); + if (err) + return err; + + adapter->lse_mask = mask; + return 0; +} + +/** + * ixgbe_disable_link_status_events - disable link status events + * @adapter: pointer to the adapter structure + * + * Disables link status events by invoking ixgbe_configure_lse() + * + * Return: the exit code of the operation. + */ +static int ixgbe_disable_link_status_events(struct ixgbe_adapter *adapter) +{ + int err; + + err = ixgbe_configure_lse(&adapter->hw, false, adapter->lse_mask); + if (err) + return err; + + adapter->lse_mask = 0; + return 0; +} + +/** * ixgbe_sfp_link_config - set up SFP+ link * @adapter: pointer to private adapter struct **/ @@ -5534,13 +5823,21 @@ static void ixgbe_sfp_link_config(struct ixgbe_adapter *adapter) * ixgbe_non_sfp_link_config - set up non-SFP+ link * @hw: pointer to private hardware struct * - * Returns 0 on success, negative on failure + * Configure non-SFP link. + * + * Return: 0 on success, negative on failure **/ static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw) { - u32 speed; + struct ixgbe_adapter *adapter = container_of(hw, struct ixgbe_adapter, + hw); + u16 mask = ~((u16)(IXGBE_ACI_LINK_EVENT_UPDOWN | + IXGBE_ACI_LINK_EVENT_MEDIA_NA | + IXGBE_ACI_LINK_EVENT_MODULE_QUAL_FAIL | + IXGBE_ACI_LINK_EVENT_PHY_FW_LOAD_FAIL)); bool autoneg, link_up = false; int ret = -EIO; + u32 speed; if (hw->mac.ops.check_link) ret = hw->mac.ops.check_link(hw, &speed, &link_up, false); @@ -5563,13 +5860,53 @@ static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw) if (ret) return ret; - if (hw->mac.ops.setup_link) + if (hw->mac.ops.setup_link) { + if (adapter->hw.mac.type == ixgbe_mac_e610) { + ret = ixgbe_enable_link_status_events(adapter, mask); + if (ret) + return ret; + } ret = hw->mac.ops.setup_link(hw, speed, link_up); + } return ret; } /** + * ixgbe_check_media_subtask - check for media + * @adapter: pointer to adapter structure + * + * If media is available then initialize PHY user configuration. Configure the + * PHY if the interface is up. + */ +static void ixgbe_check_media_subtask(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + + /* No need to check for media if it's already present */ + if (!(adapter->flags2 & IXGBE_FLAG2_NO_MEDIA)) + return; + + /* Refresh link info and check if media is present */ + if (ixgbe_update_link_info(hw)) + return; + + ixgbe_check_link_cfg_err(adapter, hw->link.link_info.link_cfg_err); + + if (hw->link.link_info.link_info & IXGBE_ACI_MEDIA_AVAILABLE) { + /* PHY settings are reset on media insertion, reconfigure + * PHY to preserve settings. + */ + if (!(ixgbe_non_sfp_link_config(&adapter->hw))) + adapter->flags2 &= ~IXGBE_FLAG2_NO_MEDIA; + + /* A Link Status Event will be generated; the event handler + * will complete bringing the interface up + */ + } +} + +/** * ixgbe_clear_vf_stats_counters - Clear out VF stats after reset * @adapter: board private structure * @@ -5632,6 +5969,7 @@ static void ixgbe_setup_gpie(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: default: IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(0), 0xFFFFFFFF); IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(1), 0xFFFFFFFF); @@ -5982,6 +6320,7 @@ dma_engine_disable: case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL, (IXGBE_READ_REG(hw, IXGBE_DMATXCTL) & ~IXGBE_DMATXCTL_TE)); @@ -6200,7 +6539,7 @@ void ixgbe_down(struct ixgbe_adapter *adapter) adapter->flags2 &= ~IXGBE_FLAG2_FDIR_REQUIRES_REINIT; adapter->flags &= ~IXGBE_FLAG_NEED_LINK_UPDATE; - del_timer_sync(&adapter->service_timer); + timer_delete_sync(&adapter->service_timer); if (adapter->num_vfs) { /* Clear EITR Select mapping */ @@ -6226,6 +6565,8 @@ void ixgbe_down(struct ixgbe_adapter *adapter) ixgbe_clean_all_tx_rings(adapter); ixgbe_clean_all_rx_rings(adapter); + if (adapter->hw.mac.type == ixgbe_mac_e610) + ixgbe_disable_link_status_events(adapter); } /** @@ -6260,7 +6601,7 @@ static void ixgbe_set_eee_capable(struct ixgbe_adapter *adapter) **/ static void ixgbe_tx_timeout(struct net_device *netdev, unsigned int __always_unused txqueue) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); /* Do the reset outside of interrupt context */ ixgbe_tx_timeout_reset(adapter); @@ -6281,6 +6622,7 @@ static void ixgbe_init_dcb(struct ixgbe_adapter *adapter) break; case ixgbe_mac_X540: case ixgbe_mac_X550: + case ixgbe_mac_e610: adapter->dcb_cfg.num_tcs.pg_tcs = X540_TRAFFIC_CLASS; adapter->dcb_cfg.num_tcs.pfc_tcs = X540_TRAFFIC_CLASS; break; @@ -6344,6 +6686,8 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, hw->subsystem_vendor_id = pdev->subsystem_vendor; hw->subsystem_device_id = pdev->subsystem_device; + hw->mac.max_link_up_time = IXGBE_LINK_UP_TIME; + /* get_invariants needs the device IDs */ ii->get_invariants(hw); @@ -6506,7 +6850,7 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, adapter->tx_work_limit = IXGBE_DEFAULT_TX_WORK; /* initialize eeprom parameters */ - if (ixgbe_init_eeprom_params_generic(hw)) { + if (hw->eeprom.ops.init_params(hw)) { e_dev_err("EEPROM initialization failed\n"); return -EIO; } @@ -6822,7 +7166,7 @@ static int ixgbe_max_xdp_frame_size(struct ixgbe_adapter *adapter) **/ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); if (ixgbe_enabled_xdp_adapter(adapter)) { int new_frame_size = new_mtu + IXGBE_PKT_HDR_PAD; @@ -6847,7 +7191,7 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu) netdev->mtu, new_mtu); /* must set new MTU before calling down or up */ - netdev->mtu = new_mtu; + WRITE_ONCE(netdev->mtu, new_mtu); if (netif_running(netdev)) ixgbe_reinit_locked(adapter); @@ -6869,7 +7213,7 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu) **/ int ixgbe_open(struct net_device *netdev) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; int err, queues; @@ -6911,6 +7255,19 @@ int ixgbe_open(struct net_device *netdev) ixgbe_up_complete(adapter); udp_tunnel_nic_reset_ntf(netdev); + if (adapter->hw.mac.type == ixgbe_mac_e610) { + int err = ixgbe_update_link_info(&adapter->hw); + + if (err) + e_dev_err("Failed to update link info, err %d.\n", err); + + ixgbe_check_link_cfg_err(adapter, + adapter->hw.link.link_info.link_cfg_err); + + err = ixgbe_non_sfp_link_config(&adapter->hw); + if (ixgbe_non_sfp_link_config(&adapter->hw)) + e_dev_err("Link setup failed, err %d.\n", err); + } return 0; @@ -6960,7 +7317,7 @@ static void ixgbe_close_suspend(struct ixgbe_adapter *adapter) **/ int ixgbe_close(struct net_device *netdev) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); ixgbe_ptp_stop(adapter); @@ -6974,7 +7331,7 @@ int ixgbe_close(struct net_device *netdev) return 0; } -static int __maybe_unused ixgbe_resume(struct device *dev_d) +static int ixgbe_resume(struct device *dev_d) { struct pci_dev *pdev = to_pci_dev(dev_d); struct ixgbe_adapter *adapter = pci_get_drvdata(pdev); @@ -7064,6 +7421,7 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: pci_wake_from_d3(pdev, !!wufc); break; default: @@ -7082,7 +7440,7 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake) return 0; } -static int __maybe_unused ixgbe_suspend(struct device *dev_d) +static int ixgbe_suspend(struct device *dev_d) { struct pci_dev *pdev = to_pci_dev(dev_d); int retval; @@ -7211,6 +7569,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: hwstats->pxonrxc[i] += IXGBE_READ_REG(hw, IXGBE_PXONRXCNT(i)); break; @@ -7223,11 +7582,12 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) for (i = 0; i < 16; i++) { hwstats->qptc[i] += IXGBE_READ_REG(hw, IXGBE_QPTC(i)); hwstats->qprc[i] += IXGBE_READ_REG(hw, IXGBE_QPRC(i)); - if ((hw->mac.type == ixgbe_mac_82599EB) || - (hw->mac.type == ixgbe_mac_X540) || - (hw->mac.type == ixgbe_mac_X550) || - (hw->mac.type == ixgbe_mac_X550EM_x) || - (hw->mac.type == ixgbe_mac_x550em_a)) { + if (hw->mac.type == ixgbe_mac_82599EB || + hw->mac.type == ixgbe_mac_X540 || + hw->mac.type == ixgbe_mac_X550 || + hw->mac.type == ixgbe_mac_X550EM_x || + hw->mac.type == ixgbe_mac_x550em_a || + hw->mac.type == ixgbe_mac_e610) { hwstats->qbtc[i] += IXGBE_READ_REG(hw, IXGBE_QBTC_L(i)); IXGBE_READ_REG(hw, IXGBE_QBTC_H(i)); /* to clear */ hwstats->qbrc[i] += IXGBE_READ_REG(hw, IXGBE_QBRC_L(i)); @@ -7253,6 +7613,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: /* OS2BMC stats are X540 and later */ hwstats->o2bgptc += IXGBE_READ_REG(hw, IXGBE_O2BGPTC); hwstats->o2bspc += IXGBE_READ_REG(hw, IXGBE_O2BSPC); @@ -7553,6 +7914,7 @@ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: case ixgbe_mac_82599EB: { u32 mflcn = IXGBE_READ_REG(hw, IXGBE_MFLCN); u32 fccfg = IXGBE_READ_REG(hw, IXGBE_FCCFG); @@ -8003,6 +8365,34 @@ static void ixgbe_reset_subtask(struct ixgbe_adapter *adapter) rtnl_unlock(); } +static int ixgbe_check_fw_api_mismatch(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + + if (hw->mac.type != ixgbe_mac_e610) + return 0; + + if (hw->mac.ops.get_fw_ver && hw->mac.ops.get_fw_ver(hw)) + return 0; + + if (hw->api_maj_ver > IXGBE_FW_API_VER_MAJOR) { + e_dev_err("The driver for the device stopped because the NVM image is newer than expected. You must install the most recent version of the network driver.\n"); + + adapter->flags2 |= IXGBE_FLAG2_API_MISMATCH; + return -EOPNOTSUPP; + } else if (hw->api_maj_ver == IXGBE_FW_API_VER_MAJOR && + hw->api_min_ver > IXGBE_FW_API_VER_MINOR + IXGBE_FW_API_VER_DIFF_ALLOWED) { + e_dev_info("The driver for the device detected a newer version of the NVM image than expected. Please install the most recent version of the network driver.\n"); + adapter->flags2 |= IXGBE_FLAG2_API_MISMATCH; + } else if (hw->api_maj_ver < IXGBE_FW_API_VER_MAJOR || + hw->api_min_ver < IXGBE_FW_API_VER_MINOR - IXGBE_FW_API_VER_DIFF_ALLOWED) { + e_dev_info("The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n"); + adapter->flags2 |= IXGBE_FLAG2_API_MISMATCH; + } + + return 0; +} + /** * ixgbe_check_fw_error - Check firmware for errors * @adapter: the adapter private structure @@ -8013,12 +8403,14 @@ static bool ixgbe_check_fw_error(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; u32 fwsm; + int err; /* read fwsm.ext_err_ind register and log errors */ fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw)); + /* skip if E610's FW is reloading, warning in that case may be misleading */ if (fwsm & IXGBE_FWSM_EXT_ERR_IND_MASK || - !(fwsm & IXGBE_FWSM_FW_VAL_BIT)) + (!(fwsm & IXGBE_FWSM_FW_VAL_BIT) && !(hw->mac.type == ixgbe_mac_e610))) e_dev_warn("Warning firmware error detected FWSM: 0x%08X\n", fwsm); @@ -8026,10 +8418,53 @@ static bool ixgbe_check_fw_error(struct ixgbe_adapter *adapter) e_dev_err("Firmware recovery mode detected. Limiting functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode.\n"); return true; } + if (!(adapter->flags2 & IXGBE_FLAG2_API_MISMATCH)) { + err = ixgbe_check_fw_api_mismatch(adapter); + if (err) + return true; + } + + /* return here if FW rollback mode has been already detected */ + if (adapter->flags2 & IXGBE_FLAG2_FW_ROLLBACK) + return false; + + if (hw->mac.ops.fw_rollback_mode && hw->mac.ops.fw_rollback_mode(hw)) { + struct ixgbe_nvm_info *nvm_info = &adapter->hw.flash.nvm; + char ver_buff[64] = ""; + + if (hw->mac.ops.get_fw_ver && hw->mac.ops.get_fw_ver(hw)) + goto no_version; + + if (hw->mac.ops.get_nvm_ver && + hw->mac.ops.get_nvm_ver(hw, nvm_info)) + goto no_version; + + snprintf(ver_buff, sizeof(ver_buff), + "Current version is NVM:%x.%x.%x, FW:%d.%d. ", + nvm_info->major, nvm_info->minor, nvm_info->eetrack, + hw->fw_maj_ver, hw->fw_maj_ver); +no_version: + e_dev_warn("Firmware rollback mode detected. %sDevice may exhibit limited functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware rollback mode.", + ver_buff); + + adapter->flags2 |= IXGBE_FLAG2_FW_ROLLBACK; + } return false; } +static void ixgbe_recovery_service_task(struct work_struct *work) +{ + struct ixgbe_adapter *adapter = container_of(work, + struct ixgbe_adapter, + service_task); + + ixgbe_handle_fw_event(adapter); + ixgbe_service_event_complete(adapter); + + mod_timer(&adapter->service_timer, jiffies + msecs_to_jiffies(100)); +} + /** * ixgbe_service_task - manages and runs subtasks * @work: pointer to work_struct containing our data @@ -8049,11 +8484,21 @@ static void ixgbe_service_task(struct work_struct *work) return; } if (ixgbe_check_fw_error(adapter)) { - if (!test_bit(__IXGBE_DOWN, &adapter->state)) + if (!test_bit(__IXGBE_DOWN, &adapter->state)) { + if (adapter->mii_bus) { + mdiobus_unregister(adapter->mii_bus); + adapter->mii_bus = NULL; + } unregister_netdev(adapter->netdev); + } ixgbe_service_event_complete(adapter); return; } + if (adapter->hw.mac.type == ixgbe_mac_e610) { + if (adapter->flags2 & IXGBE_FLAG2_FW_ASYNC_EVENT) + ixgbe_handle_fw_event(adapter); + ixgbe_check_media_subtask(adapter); + } ixgbe_reset_subtask(adapter); ixgbe_phy_interrupt_subtask(adapter); ixgbe_sfp_detection_subtask(adapter); @@ -8635,7 +9080,7 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, switch (vlan_get_protocol(skb)) { case htons(ETH_P_FCOE): case htons(ETH_P_FIP): - adapter = netdev_priv(dev); + adapter = ixgbe_from_netdev(dev); if (!sb_dev && (adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) break; @@ -8894,7 +9339,7 @@ static netdev_tx_t __ixgbe_xmit_frame(struct sk_buff *skb, struct net_device *netdev, struct ixgbe_ring *ring) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_ring *tx_ring; /* @@ -8926,7 +9371,7 @@ static netdev_tx_t ixgbe_xmit_frame(struct sk_buff *skb, **/ static int ixgbe_set_mac(struct net_device *netdev, void *p) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; struct sockaddr *addr = p; @@ -8944,7 +9389,7 @@ static int ixgbe_set_mac(struct net_device *netdev, void *p) static int ixgbe_mdio_read(struct net_device *netdev, int prtad, int devad, u16 addr) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; u16 value; int rc; @@ -8970,7 +9415,7 @@ ixgbe_mdio_read(struct net_device *netdev, int prtad, int devad, u16 addr) static int ixgbe_mdio_write(struct net_device *netdev, int prtad, int devad, u16 addr, u16 value) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; if (adapter->mii_bus) { @@ -8990,7 +9435,7 @@ static int ixgbe_mdio_write(struct net_device *netdev, int prtad, int devad, static int ixgbe_ioctl(struct net_device *netdev, struct ifreq *req, int cmd) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); switch (cmd) { case SIOCSHWTSTAMP: @@ -9016,7 +9461,7 @@ static int ixgbe_ioctl(struct net_device *netdev, struct ifreq *req, int cmd) static int ixgbe_add_sanmac_netdev(struct net_device *dev) { int err = 0; - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct ixgbe_hw *hw = &adapter->hw; if (is_valid_ether_addr(hw->mac.san_addr)) { @@ -9040,7 +9485,7 @@ static int ixgbe_add_sanmac_netdev(struct net_device *dev) static int ixgbe_del_sanmac_netdev(struct net_device *dev) { int err = 0; - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct ixgbe_mac_info *mac = &adapter->hw.mac; if (is_valid_ether_addr(mac->san_addr)) { @@ -9071,7 +9516,7 @@ static void ixgbe_get_ring_stats64(struct rtnl_link_stats64 *stats, static void ixgbe_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); int i; rcu_read_lock(); @@ -9114,7 +9559,7 @@ static void ixgbe_get_stats64(struct net_device *netdev, static int ixgbe_ndo_get_vf_stats(struct net_device *netdev, int vf, struct ifla_vf_stats *vf_stats) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); if (vf < 0 || vf >= adapter->num_vfs) return -EINVAL; @@ -9231,7 +9676,7 @@ static int ixgbe_reassign_macvlan_pool(struct net_device *vdev, static void ixgbe_defrag_macvlan_pools(struct net_device *dev) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct netdev_nested_priv priv = { .data = (void *)adapter, }; @@ -9252,7 +9697,7 @@ static void ixgbe_defrag_macvlan_pools(struct net_device *dev) */ int ixgbe_setup_tc(struct net_device *dev, u8 tc) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct ixgbe_hw *hw = &adapter->hw; /* Hardware supports up to 8 traffic classes */ @@ -9810,7 +10255,7 @@ static LIST_HEAD(ixgbe_block_cb_list); static int __ixgbe_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); switch (type) { case TC_SETUP_BLOCK: @@ -9838,7 +10283,7 @@ void ixgbe_sriov_reinit(struct ixgbe_adapter *adapter) #endif void ixgbe_do_reset(struct net_device *netdev) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); if (netif_running(netdev)) ixgbe_reinit_locked(adapter); @@ -9849,7 +10294,7 @@ void ixgbe_do_reset(struct net_device *netdev) static netdev_features_t ixgbe_fix_features(struct net_device *netdev, netdev_features_t features) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); /* If Rx checksum is disabled, then RSC/LRO should also be disabled */ if (!(features & NETIF_F_RXCSUM)) @@ -9886,7 +10331,7 @@ static void ixgbe_reset_l2fw_offload(struct ixgbe_adapter *adapter) static int ixgbe_set_features(struct net_device *netdev, netdev_features_t features) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); netdev_features_t changed = netdev->features ^ features; bool need_reset = false; @@ -9957,12 +10402,12 @@ static int ixgbe_set_features(struct net_device *netdev, static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, - u16 flags, + u16 flags, bool *notified, struct netlink_ext_ack *extack) { /* guarantee we can provide a unique filter for the unicast address */ if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); u16 pool = VMDQ_P(0); if (netdev_uc_count(dev) >= ixgbe_available_rars(adapter, pool)) @@ -10050,7 +10495,7 @@ static int ixgbe_ndo_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags, struct netlink_ext_ack *extack) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct nlattr *attr, *br_spec; int rem; @@ -10061,15 +10506,10 @@ static int ixgbe_ndo_bridge_setlink(struct net_device *dev, if (!br_spec) return -EINVAL; - nla_for_each_nested(attr, br_spec, rem) { - int status; - __u16 mode; - - if (nla_type(attr) != IFLA_BRIDGE_MODE) - continue; + nla_for_each_nested_type(attr, IFLA_BRIDGE_MODE, br_spec, rem) { + __u16 mode = nla_get_u16(attr); + int status = ixgbe_configure_bridge_mode(adapter, mode); - mode = nla_get_u16(attr); - status = ixgbe_configure_bridge_mode(adapter, mode); if (status) return status; @@ -10083,7 +10523,7 @@ static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask, int nlflags) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) return 0; @@ -10095,7 +10535,7 @@ static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev) { - struct ixgbe_adapter *adapter = netdev_priv(pdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(pdev); struct ixgbe_fwd_adapter *accel; int tcs = adapter->hw_tcs ? : 1; int pool, err; @@ -10192,7 +10632,7 @@ static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev) static void ixgbe_fwd_del(struct net_device *pdev, void *priv) { struct ixgbe_fwd_adapter *accel = priv; - struct ixgbe_adapter *adapter = netdev_priv(pdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(pdev); unsigned int rxbase = accel->rx_base_queue; unsigned int i; @@ -10270,7 +10710,7 @@ ixgbe_features_check(struct sk_buff *skb, struct net_device *dev, static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) { int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct bpf_prog *old_prog; bool need_reset; int num_queues; @@ -10342,7 +10782,7 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); switch (xdp->command) { case XDP_SETUP_PROG: @@ -10377,7 +10817,7 @@ void ixgbe_xdp_ring_update_tail_locked(struct ixgbe_ring *ring) static int ixgbe_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct ixgbe_ring *ring; int nxmit = 0; int i; @@ -10778,6 +11218,24 @@ bool ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id, } /** + * ixgbe_set_fw_version_e610 - Set FW version specifically on E610 adapters + * @adapter: the adapter private structure + * + * This function is used by probe and ethtool to determine the FW version to + * format to display. The FW version is taken from the EEPROM/NVM. + * + */ +void ixgbe_set_fw_version_e610(struct ixgbe_adapter *adapter) +{ + struct ixgbe_orom_info *orom = &adapter->hw.flash.orom; + struct ixgbe_nvm_info *nvm = &adapter->hw.flash.nvm; + + snprintf(adapter->eeprom_id, sizeof(adapter->eeprom_id), + "%x.%02x 0x%x %d.%d.%d", nvm->major, nvm->minor, + nvm->eetrack, orom->major, orom->build, orom->patch); +} + +/** * ixgbe_set_fw_version - Set FW version * @adapter: the adapter private structure * @@ -10789,6 +11247,11 @@ static void ixgbe_set_fw_version(struct ixgbe_adapter *adapter) struct ixgbe_hw *hw = &adapter->hw; struct ixgbe_nvm_version nvm_ver; + if (adapter->hw.mac.type == ixgbe_mac_e610) { + ixgbe_set_fw_version_e610(adapter); + return; + } + ixgbe_get_oem_prod_version(hw, &nvm_ver); if (nvm_ver.oem_valid) { snprintf(adapter->eeprom_id, sizeof(adapter->eeprom_id), @@ -10813,6 +11276,66 @@ static void ixgbe_set_fw_version(struct ixgbe_adapter *adapter) } /** + * ixgbe_recovery_probe - Handle FW recovery mode during probe + * @adapter: the adapter private structure + * + * Perform limited driver initialization when FW error is detected. + * + * Return: 0 on successful probe for E610, -EIO if recovery mode is detected + * for non-E610 adapter, error status code on any other case. + */ +static int ixgbe_recovery_probe(struct ixgbe_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct pci_dev *pdev = adapter->pdev; + struct ixgbe_hw *hw = &adapter->hw; + bool disable_dev; + int err = -EIO; + + if (hw->mac.type != ixgbe_mac_e610) + goto clean_up_probe; + + ixgbe_get_hw_control(adapter); + mutex_init(&hw->aci.lock); + err = ixgbe_get_flash_data(&adapter->hw); + if (err) + goto shutdown_aci; + + timer_setup(&adapter->service_timer, ixgbe_service_timer, 0); + INIT_WORK(&adapter->service_task, ixgbe_recovery_service_task); + set_bit(__IXGBE_SERVICE_INITED, &adapter->state); + clear_bit(__IXGBE_SERVICE_SCHED, &adapter->state); + + if (hw->mac.ops.get_bus_info) + hw->mac.ops.get_bus_info(hw); + + pci_set_drvdata(pdev, adapter); + /* We are creating devlink interface so NIC can be managed, + * e.g. new NVM image loaded + */ + devl_lock(adapter->devlink); + ixgbe_devlink_register_port(adapter); + SET_NETDEV_DEVLINK_PORT(adapter->netdev, + &adapter->devlink_port); + ixgbe_devlink_init_regions(adapter); + devl_register(adapter->devlink); + devl_unlock(adapter->devlink); + + return 0; +shutdown_aci: + mutex_destroy(&adapter->hw.aci.lock); + ixgbe_release_hw_control(adapter); + devlink_free(adapter->devlink); +clean_up_probe: + disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state); + free_netdev(netdev); + pci_release_mem_regions(pdev); + if (disable_dev) + pci_disable_device(pdev); + return err; +} + +/** * ixgbe_probe - Device Initialization Routine * @pdev: PCI device information struct * @ent: entry in ixgbe_pci_tbl @@ -10826,6 +11349,7 @@ static void ixgbe_set_fw_version(struct ixgbe_adapter *adapter) static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct net_device *netdev; + struct ixgbe_netdevice_priv *netdev_priv_wrapper; struct ixgbe_adapter *adapter = NULL; struct ixgbe_hw *hw; const struct ixgbe_info *ii = ixgbe_info_tbl[ent->driver_data]; @@ -10875,9 +11399,17 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) #else indices = IXGBE_MAX_RSS_INDICES; #endif + } else if (ii->mac == ixgbe_mac_e610) { + indices = IXGBE_MAX_RSS_INDICES_X550; } - netdev = alloc_etherdev_mq(sizeof(struct ixgbe_adapter), indices); + adapter = ixgbe_allocate_devlink(&pdev->dev); + if (IS_ERR(adapter)) { + err = PTR_ERR(adapter); + goto err_devlink; + } + + netdev = alloc_etherdev_mq(sizeof(*netdev_priv_wrapper), indices); if (!netdev) { err = -ENOMEM; goto err_alloc_etherdev; @@ -10885,7 +11417,8 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) SET_NETDEV_DEV(netdev, &pdev->dev); - adapter = netdev_priv(netdev); + netdev_priv_wrapper = netdev_priv(netdev); + netdev_priv_wrapper->adapter = adapter; adapter->netdev = netdev; adapter->pdev = pdev; @@ -10901,11 +11434,6 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_ioremap; } - netdev->netdev_ops = &ixgbe_netdev_ops; - ixgbe_set_ethtool_ops(netdev); - netdev->watchdog_timeo = 5 * HZ; - strscpy(netdev->name, pci_name(pdev), sizeof(netdev->name)); - /* Setup hw api */ hw->mac.ops = *ii->mac_ops; hw->mac.type = ii->mac; @@ -10935,17 +11463,40 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->phy.mdio.mdio_read = ixgbe_mdio_read; hw->phy.mdio.mdio_write = ixgbe_mdio_write; + netdev->netdev_ops = &ixgbe_netdev_ops; + ixgbe_set_ethtool_ops(netdev); + netdev->watchdog_timeo = 5 * HZ; + strscpy(netdev->name, pci_name(pdev), sizeof(netdev->name)); + /* setup the private structure */ err = ixgbe_sw_init(adapter, ii); if (err) goto err_sw_init; + /* Make sure the SWFW semaphore is in a valid state */ + if (hw->mac.ops.init_swfw_sync) + hw->mac.ops.init_swfw_sync(hw); + + if (ixgbe_check_fw_error(adapter)) + return ixgbe_recovery_probe(adapter); + + if (adapter->hw.mac.type == ixgbe_mac_e610) { + err = ixgbe_get_caps(&adapter->hw); + if (err) + dev_err(&pdev->dev, "ixgbe_get_caps failed %d\n", err); + + err = ixgbe_get_flash_data(&adapter->hw); + if (err) + goto err_sw_init; + } + if (adapter->hw.mac.type == ixgbe_mac_82599EB) adapter->flags2 |= IXGBE_FLAG2_AUTO_DISABLE_VF; switch (adapter->hw.mac.type) { case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: + case ixgbe_mac_e610: netdev->udp_tunnel_nic_info = &ixgbe_udp_tunnels_x550; break; case ixgbe_mac_x550em_a: @@ -10955,10 +11506,6 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) break; } - /* Make sure the SWFW semaphore is in a valid state */ - if (hw->mac.ops.init_swfw_sync) - hw->mac.ops.init_swfw_sync(hw); - /* Make it possible the adapter to be woken up via WOL */ switch (adapter->hw.mac.type) { case ixgbe_mac_82599EB: @@ -10966,6 +11513,7 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: IXGBE_WRITE_REG(&adapter->hw, IXGBE_WUS, ~0); break; default: @@ -11102,8 +11650,7 @@ skip_sriov: NETIF_F_FCOE_CRC; netdev->vlan_features |= NETIF_F_FSO | - NETIF_F_FCOE_CRC | - NETIF_F_FCOE_MTU; + NETIF_F_FCOE_CRC; } #endif /* IXGBE_FCOE */ if (adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE) @@ -11111,11 +11658,6 @@ skip_sriov: if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) netdev->features |= NETIF_F_LRO; - if (ixgbe_check_fw_error(adapter)) { - err = -EIO; - goto err_sw_init; - } - /* make sure the EEPROM is good */ if (hw->eeprom.ops.validate_checksum(hw, NULL) < 0) { e_dev_err("The EEPROM Checksum Is Not Valid\n"); @@ -11138,6 +11680,8 @@ skip_sriov: ether_addr_copy(hw->mac.addr, hw->mac.perm_addr); ixgbe_mac_set_default_filter(adapter); + if (hw->mac.type == ixgbe_mac_e610) + mutex_init(&hw->aci.lock); timer_setup(&adapter->service_timer, ixgbe_service_timer, 0); if (ixgbe_removed(hw->hw_addr)) { @@ -11196,7 +11740,7 @@ skip_sriov: if (expected_gts > 0) ixgbe_check_minimum_link(adapter, expected_gts); - err = ixgbe_read_pba_string_generic(hw, part_str, sizeof(part_str)); + err = hw->eeprom.ops.read_pba_string(hw, part_str, sizeof(part_str)); if (err) strscpy(part_str, "Unknown", sizeof(part_str)); if (ixgbe_is_sfp(hw) && hw->phy.sfp_type != ixgbe_sfp_type_not_present) @@ -11222,6 +11766,11 @@ skip_sriov: } strcpy(netdev->name, "eth%d"); pci_set_drvdata(pdev, adapter); + + devl_lock(adapter->devlink); + ixgbe_devlink_register_port(adapter); + SET_NETDEV_DEVLINK_PORT(adapter->netdev, &adapter->devlink_port); + err = register_netdev(netdev); if (err) goto err_register; @@ -11276,13 +11825,20 @@ skip_sriov: if (err) goto err_netdev; + ixgbe_devlink_init_regions(adapter); + devl_register(adapter->devlink); + devl_unlock(adapter->devlink); return 0; err_netdev: unregister_netdev(netdev); err_register: + devl_port_unregister(&adapter->devlink_port); + devl_unlock(adapter->devlink); ixgbe_release_hw_control(adapter); ixgbe_clear_interrupt_scheme(adapter); + if (hw->mac.type == ixgbe_mac_e610) + mutex_destroy(&adapter->hw.aci.lock); err_sw_init: ixgbe_disable_sriov(adapter); adapter->flags2 &= ~IXGBE_FLAG2_SEARCH_FOR_SFP; @@ -11295,7 +11851,9 @@ err_ioremap: disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state); free_netdev(netdev); err_alloc_etherdev: + devlink_free(adapter->devlink); pci_release_mem_regions(pdev); +err_devlink: err_pci_reg: err_dma: if (!adapter || disable_dev) @@ -11324,11 +11882,19 @@ static void ixgbe_remove(struct pci_dev *pdev) return; netdev = adapter->netdev; + devl_lock(adapter->devlink); + devl_unregister(adapter->devlink); + ixgbe_devlink_destroy_regions(adapter); ixgbe_dbg_adapter_exit(adapter); set_bit(__IXGBE_REMOVING, &adapter->state); cancel_work_sync(&adapter->service_task); + if (adapter->hw.mac.type == ixgbe_mac_e610) { + ixgbe_disable_link_status_events(adapter); + mutex_destroy(&adapter->hw.aci.lock); + } + if (adapter->mii_bus) mdiobus_unregister(adapter->mii_bus); @@ -11354,6 +11920,10 @@ static void ixgbe_remove(struct pci_dev *pdev) if (netdev->reg_state == NETREG_REGISTERED) unregister_netdev(netdev); + devl_port_unregister(&adapter->devlink_port); + devl_unlock(adapter->devlink); + devlink_free(adapter->devlink); + ixgbe_stop_ipsec_offload(adapter); ixgbe_clear_interrupt_scheme(adapter); @@ -11460,6 +12030,9 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev, case ixgbe_mac_x550em_a: device_id = IXGBE_DEV_ID_X550EM_A_VF; break; + case ixgbe_mac_e610: + device_id = IXGBE_DEV_ID_E610_VF; + break; default: device_id = 0; break; @@ -11588,14 +12161,14 @@ static const struct pci_error_handlers ixgbe_err_handler = { .resume = ixgbe_io_resume, }; -static SIMPLE_DEV_PM_OPS(ixgbe_pm_ops, ixgbe_suspend, ixgbe_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(ixgbe_pm_ops, ixgbe_suspend, ixgbe_resume); static struct pci_driver ixgbe_driver = { .name = ixgbe_driver_name, .id_table = ixgbe_pci_tbl, .probe = ixgbe_probe, .remove = ixgbe_remove, - .driver.pm = &ixgbe_pm_ops, + .driver.pm = pm_sleep_ptr(&ixgbe_pm_ops), .shutdown = ixgbe_shutdown, .sriov_configure = ixgbe_pci_sriov_configure, .err_handler = &ixgbe_err_handler diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c index d67d77e5dacc..788b5af07c70 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #include <linux/pci.h> #include <linux/delay.h> @@ -283,6 +283,7 @@ static int ixgbe_check_for_rst_pf(struct ixgbe_hw *hw, u16 vf_number) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: vflre = IXGBE_READ_REG(hw, IXGBE_VFLREC(reg_offset)); break; default: @@ -407,6 +408,7 @@ void ixgbe_init_mbx_params_pf(struct ixgbe_hw *hw) hw->mac.type != ixgbe_mac_X550 && hw->mac.type != ixgbe_mac_X550EM_x && hw->mac.type != ixgbe_mac_x550em_a && + hw->mac.type != ixgbe_mac_e610 && hw->mac.type != ixgbe_mac_X540) return; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h index bd205306934b..bf65e82b4c61 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h @@ -4,7 +4,7 @@ #ifndef _IXGBE_MBX_H_ #define _IXGBE_MBX_H_ -#include "ixgbe_type.h" +#include <linux/types.h> #define IXGBE_VFMAILBOX_SIZE 16 /* 16 32 bit words - 64 bytes */ @@ -96,6 +96,8 @@ enum ixgbe_pfvf_api_rev { #define IXGBE_VF_MBX_INIT_TIMEOUT 2000 /* number of retries on mailbox */ #define IXGBE_VF_MBX_INIT_DELAY 500 /* microseconds between retries */ +struct ixgbe_hw; + int ixgbe_read_mbx(struct ixgbe_hw *, u32 *, u16, u16); int ixgbe_write_mbx(struct ixgbe_hw *, u32 *, u16, u16); int ixgbe_check_for_msg(struct ixgbe_hw *, u16); @@ -105,6 +107,18 @@ int ixgbe_check_for_rst(struct ixgbe_hw *, u16); void ixgbe_init_mbx_params_pf(struct ixgbe_hw *); #endif /* CONFIG_PCI_IOV */ +struct ixgbe_mbx_operations { + int (*init_params)(struct ixgbe_hw *hw); + int (*read)(struct ixgbe_hw *hw, u32 *msg, u16 size, u16 vf_number); + int (*write)(struct ixgbe_hw *hw, u32 *msg, u16 size, u16 vf_number); + int (*read_posted)(struct ixgbe_hw *hw, u32 *msg, u16 size, u16 mbx_id); + int (*write_posted)(struct ixgbe_hw *hw, u32 *msg, u16 size, + u16 mbx_id); + int (*check_for_msg)(struct ixgbe_hw *hw, u16 vf_number); + int (*check_for_ack)(struct ixgbe_hw *hw, u16 vf_number); + int (*check_for_rst)(struct ixgbe_hw *hw, u16 vf_number); +}; + extern const struct ixgbe_mbx_operations mbx_ops_generic; #endif /* _IXGBE_MBX_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index 07eaa3c3f4d3..2d54828bdfbb 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #include <linux/pci.h> #include <linux/delay.h> @@ -167,7 +167,7 @@ int ixgbe_write_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr, u16 reg, u16 val, bool lock) { u32 swfw_mask = hw->phy.phy_semaphore_mask; - int max_retry = 1; + int max_retry = 3; int retry = 0; u8 reg_high; u8 csum; @@ -1117,7 +1117,7 @@ int ixgbe_setup_phy_link_generic(struct ixgbe_hw *hw) hw->phy.ops.read_reg(hw, IXGBE_MII_AUTONEG_VENDOR_PROVISION_1_REG, MDIO_MMD_AN, &autoneg_reg); - if (hw->mac.type == ixgbe_mac_X550) { + if (hw->mac.type == ixgbe_mac_X550 || hw->mac.type == ixgbe_mac_e610) { /* Set or unset auto-negotiation 5G advertisement */ autoneg_reg &= ~IXGBE_MII_5GBASE_T_ADVERTISE; if ((hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_5GB_FULL) && @@ -1233,6 +1233,7 @@ static int ixgbe_get_copper_speeds_supported(struct ixgbe_hw *hw) switch (hw->mac.type) { case ixgbe_mac_X550: + case ixgbe_mac_e610: hw->phy.speeds_supported |= IXGBE_LINK_SPEED_2_5GB_FULL; hw->phy.speeds_supported |= IXGBE_LINK_SPEED_5GB_FULL; break; @@ -2284,7 +2285,7 @@ static int ixgbe_write_i2c_byte_generic_int(struct ixgbe_hw *hw, u8 byte_offset, u8 dev_addr, u8 data, bool lock) { u32 swfw_mask = hw->phy.phy_semaphore_mask; - u32 max_retry = 1; + u32 max_retry = 3; u32 retry = 0; int status; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h index 14aa2ca51f70..81179c60af4e 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h @@ -40,7 +40,7 @@ #define IXGBE_SFF_1GBASESX_CAPABLE 0x1 #define IXGBE_SFF_1GBASELX_CAPABLE 0x2 #define IXGBE_SFF_1GBASET_CAPABLE 0x8 -#define IXGBE_SFF_BASEBX10_CAPABLE 0x64 +#define IXGBE_SFF_BASEBX10_CAPABLE 0x40 #define IXGBE_SFF_10GBASESR_CAPABLE 0x10 #define IXGBE_SFF_10GBASELR_CAPABLE 0x20 #define IXGBE_SFF_SOFT_RS_SELECT_MASK 0x8 diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index 9339edbd9082..eef25e11d938 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -140,6 +140,7 @@ * proper mult and shift to convert the cycles into nanoseconds of time. */ #define IXGBE_X550_BASE_PERIOD 0xC80000000ULL +#define IXGBE_E610_BASE_PERIOD 0x333333333ULL #define INCVALUE_MASK 0x7FFFFFFF #define ISGN 0x80000000 @@ -415,6 +416,7 @@ static void ixgbe_ptp_convert_to_hwtstamp(struct ixgbe_adapter *adapter, case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: /* Upper 32 bits represent billions of cycles, lower 32 bits * represent cycles. However, we use timespec64_to_ns for the * correct math even though the units haven't been corrected @@ -492,11 +494,13 @@ static int ixgbe_ptp_adjfine_X550(struct ptp_clock_info *ptp, long scaled_ppm) struct ixgbe_adapter *adapter = container_of(ptp, struct ixgbe_adapter, ptp_caps); struct ixgbe_hw *hw = &adapter->hw; + u64 rate, base; bool neg_adj; - u64 rate; u32 inca; - neg_adj = diff_by_scaled_ppm(IXGBE_X550_BASE_PERIOD, scaled_ppm, &rate); + base = hw->mac.type == ixgbe_mac_e610 ? IXGBE_E610_BASE_PERIOD : + IXGBE_X550_BASE_PERIOD; + neg_adj = diff_by_scaled_ppm(base, scaled_ppm, &rate); /* warn if rate is too large */ if (rate >= INCVALUE_MASK) @@ -559,6 +563,7 @@ static int ixgbe_ptp_gettimex(struct ptp_clock_info *ptp, case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: /* Upper 32 bits represent billions of cycles, lower 32 bits * represent cycles. However, we use timespec64_to_ns for the * correct math even though the units haven't been corrected @@ -1067,6 +1072,7 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter, case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: /* enable timestamping all packets only if at least some * packets were requested. Otherwise, play nice and disable * timestamping @@ -1233,6 +1239,7 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter) fallthrough; case ixgbe_mac_x550em_a: case ixgbe_mac_X550: + case ixgbe_mac_e610: cc.read = ixgbe_ptp_read_X550; break; case ixgbe_mac_X540: @@ -1280,6 +1287,7 @@ static void ixgbe_ptp_init_systime(struct ixgbe_adapter *adapter) case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: case ixgbe_mac_X550: + case ixgbe_mac_e610: tsauxc = IXGBE_READ_REG(hw, IXGBE_TSAUXC); /* Reset SYSTIME registers to 0 */ @@ -1407,6 +1415,7 @@ static long ixgbe_ptp_create_clock(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: snprintf(adapter->ptp_caps.name, 16, "%s", netdev->name); adapter->ptp_caps.owner = THIS_MODULE; adapter->ptp_caps.max_adj = 30000000; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index fcfd0a075eee..0dbbd2befd4d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -18,6 +18,7 @@ #include "ixgbe.h" #include "ixgbe_type.h" +#include "ixgbe_mbx.h" #include "ixgbe_sriov.h" #ifdef CONFIG_PCI_IOV @@ -495,7 +496,7 @@ static int ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 max_frame, u32 vf int err = 0; #ifdef CONFIG_FCOE - if (dev->features & NETIF_F_FCOE_MTU) + if (dev->fcoe_mtu) pf_max_frame = max_t(int, pf_max_frame, IXGBE_FCOE_JUMBO_FRAME_SIZE); @@ -857,7 +858,7 @@ static void ixgbe_set_vf_rx_tx(struct ixgbe_adapter *adapter, int vf) int pf_max_frame = dev->mtu + ETH_HLEN; #if IS_ENABLED(CONFIG_FCOE) - if (dev->features & NETIF_F_FCOE_MTU) + if (dev->fcoe_mtu) pf_max_frame = max_t(int, pf_max_frame, IXGBE_FCOE_JUMBO_FRAME_SIZE); #endif /* CONFIG_FCOE */ @@ -1047,7 +1048,7 @@ static int ixgbe_negotiate_vf_api(struct ixgbe_adapter *adapter, break; } - e_info(drv, "VF %d requested invalid api version %u\n", vf, api); + e_dbg(drv, "VF %d requested unsupported api version %u\n", vf, api); return -1; } @@ -1417,7 +1418,7 @@ void ixgbe_set_all_vfs(struct ixgbe_adapter *adapter) int ixgbe_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); int retval; if (vf >= adapter->num_vfs) @@ -1525,7 +1526,7 @@ int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos, __be16 vlan_proto) { int err = 0; - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); if ((vf >= adapter->num_vfs) || (vlan > 4095) || (qos > 7)) return -EINVAL; @@ -1643,7 +1644,7 @@ void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter) int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int min_tx_rate, int max_tx_rate) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); int link_speed; /* verify VF is active */ @@ -1678,7 +1679,7 @@ int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int min_tx_rate, int ixgbe_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; if (vf >= adapter->num_vfs) @@ -1756,7 +1757,7 @@ void ixgbe_set_vf_link_state(struct ixgbe_adapter *adapter, int vf, int state) **/ int ixgbe_ndo_set_vf_link_state(struct net_device *netdev, int vf, int state) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); int ret = 0; if (vf < 0 || vf >= adapter->num_vfs) { @@ -1793,7 +1794,7 @@ int ixgbe_ndo_set_vf_link_state(struct net_device *netdev, int vf, int state) int ixgbe_ndo_set_vf_rss_query_en(struct net_device *netdev, int vf, bool setting) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); /* This operation is currently supported only for 82599 and x540 * devices. @@ -1812,7 +1813,7 @@ int ixgbe_ndo_set_vf_rss_query_en(struct net_device *netdev, int vf, int ixgbe_ndo_set_vf_trust(struct net_device *netdev, int vf, bool setting) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); if (vf >= adapter->num_vfs) return -EINVAL; @@ -1835,7 +1836,7 @@ int ixgbe_ndo_set_vf_trust(struct net_device *netdev, int vf, bool setting) int ixgbe_ndo_get_vf_config(struct net_device *netdev, int vf, struct ifla_vf_info *ivi) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); if (vf >= adapter->num_vfs) return -EINVAL; ivi->vf = vf; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h index ed440dd0c4f9..892fa6c1f879 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #ifndef _IXGBE_TYPE_H_ #define _IXGBE_TYPE_H_ @@ -7,6 +7,7 @@ #include <linux/types.h> #include <linux/mdio.h> #include <linux/netdevice.h> +#include "ixgbe_type_e610.h" /* Device IDs */ #define IXGBE_DEV_ID_82598 0x10B6 @@ -71,12 +72,19 @@ #define IXGBE_DEV_ID_X550EM_A_1G_T 0x15E4 #define IXGBE_DEV_ID_X550EM_A_1G_T_L 0x15E5 +#define IXGBE_DEV_ID_E610_BACKPLANE 0x57AE +#define IXGBE_DEV_ID_E610_SFP 0x57AF +#define IXGBE_DEV_ID_E610_10G_T 0x57B0 +#define IXGBE_DEV_ID_E610_2_5G_T 0x57B1 +#define IXGBE_DEV_ID_E610_SGMII 0x57B2 + /* VF Device IDs */ #define IXGBE_DEV_ID_82599_VF 0x10ED #define IXGBE_DEV_ID_X540_VF 0x1515 #define IXGBE_DEV_ID_X550_VF 0x1565 #define IXGBE_DEV_ID_X550EM_X_VF 0x15A8 #define IXGBE_DEV_ID_X550EM_A_VF 0x15C5 +#define IXGBE_DEV_ID_E610_VF 0x57AD #define IXGBE_CAT(r, m) IXGBE_##r##_##m @@ -1600,7 +1608,7 @@ enum { #define IXGBE_EICR_PCI 0x00040000 /* PCI Exception */ #define IXGBE_EICR_MAILBOX 0x00080000 /* VF to PF Mailbox Interrupt */ #define IXGBE_EICR_LSC 0x00100000 /* Link Status Change */ -#define IXGBE_EICR_LINKSEC 0x00200000 /* PN Threshold */ +#define IXGBE_EICR_FW_EVENT 0x00200000 /* Async FW event */ #define IXGBE_EICR_MNG 0x00400000 /* Manageability Event Interrupt */ #define IXGBE_EICR_TS 0x00800000 /* Thermal Sensor Event */ #define IXGBE_EICR_TIMESYNC 0x01000000 /* Timesync Event */ @@ -1636,6 +1644,7 @@ enum { #define IXGBE_EICS_PCI IXGBE_EICR_PCI /* PCI Exception */ #define IXGBE_EICS_MAILBOX IXGBE_EICR_MAILBOX /* VF to PF Mailbox Int */ #define IXGBE_EICS_LSC IXGBE_EICR_LSC /* Link Status Change */ +#define IXGBE_EICS_FW_EVENT IXGBE_EICR_FW_EVENT /* Async FW event */ #define IXGBE_EICS_MNG IXGBE_EICR_MNG /* MNG Event Interrupt */ #define IXGBE_EICS_TIMESYNC IXGBE_EICR_TIMESYNC /* Timesync Event */ #define IXGBE_EICS_GPI_SDP0(_hw) IXGBE_EICR_GPI_SDP0(_hw) @@ -1654,6 +1663,7 @@ enum { #define IXGBE_EIMS_PCI IXGBE_EICR_PCI /* PCI Exception */ #define IXGBE_EIMS_MAILBOX IXGBE_EICR_MAILBOX /* VF to PF Mailbox Int */ #define IXGBE_EIMS_LSC IXGBE_EICR_LSC /* Link Status Change */ +#define IXGBE_EIMS_FW_EVENT IXGBE_EICR_FW_EVENT /* Async FW event */ #define IXGBE_EIMS_MNG IXGBE_EICR_MNG /* MNG Event Interrupt */ #define IXGBE_EIMS_TS IXGBE_EICR_TS /* Thermel Sensor Event */ #define IXGBE_EIMS_TIMESYNC IXGBE_EICR_TIMESYNC /* Timesync Event */ @@ -1673,6 +1683,7 @@ enum { #define IXGBE_EIMC_PCI IXGBE_EICR_PCI /* PCI Exception */ #define IXGBE_EIMC_MAILBOX IXGBE_EICR_MAILBOX /* VF to PF Mailbox Int */ #define IXGBE_EIMC_LSC IXGBE_EICR_LSC /* Link Status Change */ +#define IXGBE_EIMC_FW_EVENT IXGBE_EICR_FW_EVENT /* Async FW event */ #define IXGBE_EIMC_MNG IXGBE_EICR_MNG /* MNG Event Interrupt */ #define IXGBE_EIMC_TIMESYNC IXGBE_EICR_TIMESYNC /* Timesync Event */ #define IXGBE_EIMC_GPI_SDP0(_hw) IXGBE_EICR_GPI_SDP0(_hw) @@ -2068,6 +2079,7 @@ enum { #define IXGBE_SAN_MAC_ADDR_PTR 0x28 #define IXGBE_DEVICE_CAPS 0x2C #define IXGBE_SERIAL_NUMBER_MAC_ADDR 0x11 +#define IXGBE_PCIE_MSIX_E610_CAPS 0xB2 #define IXGBE_PCIE_MSIX_82599_CAPS 0x72 #define IXGBE_MAX_MSIX_VECTORS_82599 0x40 #define IXGBE_PCIE_MSIX_82598_CAPS 0x62 @@ -2168,6 +2180,7 @@ enum { #define IXGBE_PCI_DEVICE_STATUS 0xAA #define IXGBE_PCI_DEVICE_STATUS_TRANSACTION_PENDING 0x0020 #define IXGBE_PCI_LINK_STATUS 0xB2 +#define IXGBE_PCI_LINK_STATUS_E610 0x82 #define IXGBE_PCI_DEVICE_CONTROL2 0xC8 #define IXGBE_PCI_LINK_WIDTH 0x3F0 #define IXGBE_PCI_LINK_WIDTH_1 0x10 @@ -2179,7 +2192,6 @@ enum { #define IXGBE_PCI_LINK_SPEED_5000 0x2 #define IXGBE_PCI_LINK_SPEED_8000 0x3 #define IXGBE_PCI_HEADER_TYPE_REGISTER 0x0E -#define IXGBE_PCI_HEADER_TYPE_MULTIFUNC 0x80 #define IXGBE_PCI_DEVICE_CONTROL2_16ms 0x0005 #define IXGBE_PCIDEVCTRL2_TIMEO_MASK 0xf @@ -2289,6 +2301,7 @@ enum { #define IXGBE_RXMTRL_V2_MGMT_MSG 0x0D00 #define IXGBE_FCTRL_SBP 0x00000002 /* Store Bad Packet */ +#define IXGBE_FCTRL_TPE 0x00000080 /* Tag Promiscuous Ena*/ #define IXGBE_FCTRL_MPE 0x00000100 /* Multicast Promiscuous Ena*/ #define IXGBE_FCTRL_UPE 0x00000200 /* Unicast Promiscuous Ena */ #define IXGBE_FCTRL_BAM 0x00000400 /* Broadcast Accept Mode */ @@ -2352,6 +2365,7 @@ enum { /* Multiple Transmit Queue Command Register */ #define IXGBE_MTQC_RT_ENA 0x1 /* DCB Enable */ #define IXGBE_MTQC_VT_ENA 0x2 /* VMDQ2 Enable */ +#define IXGBE_MTQC_NUM_TC_OR_Q 0xC /* Number of TCs or TxQs per pool */ #define IXGBE_MTQC_64Q_1PB 0x0 /* 64 queues 1 pack buffer */ #define IXGBE_MTQC_32VF 0x8 /* 4 TX Queues per pool w/32VF's */ #define IXGBE_MTQC_64VF 0x4 /* 2 TX Queues per pool w/64VF's */ @@ -2971,6 +2985,29 @@ typedef u32 ixgbe_link_speed; IXGBE_LINK_SPEED_1GB_FULL | \ IXGBE_LINK_SPEED_10GB_FULL) +/* Physical layer type */ +typedef u64 ixgbe_physical_layer; +#define IXGBE_PHYSICAL_LAYER_UNKNOWN 0 +#define IXGBE_PHYSICAL_LAYER_10GBASE_T 0x00001 +#define IXGBE_PHYSICAL_LAYER_1000BASE_T 0x00002 +#define IXGBE_PHYSICAL_LAYER_100BASE_TX 0x00004 +#define IXGBE_PHYSICAL_LAYER_SFP_PLUS_CU 0x00008 +#define IXGBE_PHYSICAL_LAYER_10GBASE_LR 0x00010 +#define IXGBE_PHYSICAL_LAYER_10GBASE_LRM 0x00020 +#define IXGBE_PHYSICAL_LAYER_10GBASE_SR 0x00040 +#define IXGBE_PHYSICAL_LAYER_10GBASE_KX4 0x00080 +#define IXGBE_PHYSICAL_LAYER_10GBASE_CX4 0x00100 +#define IXGBE_PHYSICAL_LAYER_1000BASE_KX 0x00200 +#define IXGBE_PHYSICAL_LAYER_1000BASE_BX 0x00400 +#define IXGBE_PHYSICAL_LAYER_10GBASE_KR 0x00800 +#define IXGBE_PHYSICAL_LAYER_10GBASE_XAUI 0x01000 +#define IXGBE_PHYSICAL_LAYER_SFP_ACTIVE_DA 0x02000 +#define IXGBE_PHYSICAL_LAYER_1000BASE_SX 0x04000 +#define IXGBE_PHYSICAL_LAYER_10BASE_T 0x08000 +#define IXGBE_PHYSICAL_LAYER_2500BASE_KX 0x10000 +#define IXGBE_PHYSICAL_LAYER_2500BASE_T 0x20000 +#define IXGBE_PHYSICAL_LAYER_5000BASE_T 0x40000 + /* Flow Control Data Sheet defined values * Calculation and defines taken from 802.1bb Annex O */ @@ -3146,6 +3183,8 @@ enum ixgbe_mac_type { ixgbe_mac_X550, ixgbe_mac_X550EM_x, ixgbe_mac_x550em_a, + ixgbe_mac_e610, + ixgbe_mac_e610_vf, ixgbe_num_macs }; @@ -3225,7 +3264,9 @@ enum ixgbe_media_type { ixgbe_media_type_copper, ixgbe_media_type_backplane, ixgbe_media_type_cx4, - ixgbe_media_type_virtual + ixgbe_media_type_virtual, + ixgbe_media_type_da, + ixgbe_media_type_aui, }; /* Flow Control Settings */ @@ -3234,7 +3275,8 @@ enum ixgbe_fc_mode { ixgbe_fc_rx_pause, ixgbe_fc_tx_pause, ixgbe_fc_full, - ixgbe_fc_default + ixgbe_fc_default, + ixgbe_fc_pfc, }; /* Smart Speed Settings */ @@ -3404,6 +3446,8 @@ struct ixgbe_eeprom_operations { int (*validate_checksum)(struct ixgbe_hw *, u16 *); int (*update_checksum)(struct ixgbe_hw *); int (*calc_checksum)(struct ixgbe_hw *); + int (*read_pba_string)(struct ixgbe_hw *hw, u8 *pba_num, + u32 pba_num_size); }; struct ixgbe_mac_operations { @@ -3412,6 +3456,7 @@ struct ixgbe_mac_operations { int (*start_hw)(struct ixgbe_hw *); int (*clear_hw_cntrs)(struct ixgbe_hw *); enum ixgbe_media_type (*get_media_type)(struct ixgbe_hw *); + int (*get_fw_ver)(struct ixgbe_hw *hw); int (*get_mac_addr)(struct ixgbe_hw *, u8 *); int (*get_san_mac_addr)(struct ixgbe_hw *, u8 *); int (*get_device_caps)(struct ixgbe_hw *, u16 *); @@ -3480,6 +3525,8 @@ struct ixgbe_mac_operations { int (*get_thermal_sensor_data)(struct ixgbe_hw *); int (*init_thermal_sensor_thresh)(struct ixgbe_hw *hw); bool (*fw_recovery_mode)(struct ixgbe_hw *hw); + bool (*fw_rollback_mode)(struct ixgbe_hw *hw); + int (*get_nvm_ver)(struct ixgbe_hw *hw, struct ixgbe_nvm_info *nvm); void (*disable_rx)(struct ixgbe_hw *hw); void (*enable_rx)(struct ixgbe_hw *hw); void (*set_source_address_pruning)(struct ixgbe_hw *, bool, @@ -3534,6 +3581,9 @@ struct ixgbe_link_operations { struct ixgbe_link_info { struct ixgbe_link_operations ops; u8 addr; + struct ixgbe_link_status link_info; + struct ixgbe_link_status link_info_old; + u8 get_link_info; }; struct ixgbe_eeprom_info { @@ -3576,6 +3626,7 @@ struct ixgbe_mac_info { u8 san_mac_rar_index; struct ixgbe_thermal_sensor_data thermal_sensor_data; bool set_lben; + u32 max_link_up_time; u8 led_link_act; }; @@ -3600,19 +3651,10 @@ struct ixgbe_phy_info { bool reset_if_overtemp; bool qsfp_shared_i2c_bus; u32 nw_mng_if_sel; -}; - -#include "ixgbe_mbx.h" - -struct ixgbe_mbx_operations { - int (*init_params)(struct ixgbe_hw *hw); - int (*read)(struct ixgbe_hw *, u32 *, u16, u16); - int (*write)(struct ixgbe_hw *, u32 *, u16, u16); - int (*read_posted)(struct ixgbe_hw *, u32 *, u16, u16); - int (*write_posted)(struct ixgbe_hw *, u32 *, u16, u16); - int (*check_for_msg)(struct ixgbe_hw *, u16); - int (*check_for_ack)(struct ixgbe_hw *, u16); - int (*check_for_rst)(struct ixgbe_hw *, u16); + u64 phy_type_low; + u64 phy_type_high; + u16 curr_user_speed_req; + struct ixgbe_aci_cmd_set_phy_cfg_data curr_user_phy_cfg; }; struct ixgbe_mbx_stats { @@ -3624,6 +3666,8 @@ struct ixgbe_mbx_stats { u32 rsts; }; +struct ixgbe_mbx_operations; + struct ixgbe_mbx_info { const struct ixgbe_mbx_operations *ops; struct ixgbe_mbx_stats stats; @@ -3655,6 +3699,19 @@ struct ixgbe_hw { bool allow_unsupported_sfp; bool wol_enabled; bool need_crosstalk_fix; + u8 api_branch; + u8 api_maj_ver; + u8 api_min_ver; + u8 api_patch; + u8 fw_branch; + u8 fw_maj_ver; + u8 fw_min_ver; + u8 fw_patch; + u32 fw_build; + struct ixgbe_aci_info aci; + struct ixgbe_flash_info flash; + struct ixgbe_hw_dev_caps dev_caps; + struct ixgbe_hw_func_caps func_caps; }; struct ixgbe_info { @@ -3676,9 +3733,7 @@ struct ixgbe_info { #define IXGBE_KRM_LINK_S1(P) ((P) ? 0x8200 : 0x4200) #define IXGBE_KRM_LINK_CTRL_1(P) ((P) ? 0x820C : 0x420C) #define IXGBE_KRM_AN_CNTL_1(P) ((P) ? 0x822C : 0x422C) -#define IXGBE_KRM_AN_CNTL_4(P) ((P) ? 0x8238 : 0x4238) #define IXGBE_KRM_AN_CNTL_8(P) ((P) ? 0x8248 : 0x4248) -#define IXGBE_KRM_PCS_KX_AN(P) ((P) ? 0x9918 : 0x5918) #define IXGBE_KRM_SGMII_CTRL(P) ((P) ? 0x82A0 : 0x42A0) #define IXGBE_KRM_LP_BASE_PAGE_HIGH(P) ((P) ? 0x836C : 0x436C) #define IXGBE_KRM_DSP_TXFFE_STATE_4(P) ((P) ? 0x8634 : 0x4634) @@ -3688,7 +3743,6 @@ struct ixgbe_info { #define IXGBE_KRM_PMD_FLX_MASK_ST20(P) ((P) ? 0x9054 : 0x5054) #define IXGBE_KRM_TX_COEFF_CTRL_1(P) ((P) ? 0x9520 : 0x5520) #define IXGBE_KRM_RX_ANA_CTL(P) ((P) ? 0x9A00 : 0x5A00) -#define IXGBE_KRM_FLX_TMRS_CTRL_ST31(P) ((P) ? 0x9180 : 0x5180) #define IXGBE_KRM_PMD_FLX_MASK_ST20_SFI_10G_DA ~(0x3 << 20) #define IXGBE_KRM_PMD_FLX_MASK_ST20_SFI_10G_SR BIT(20) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h new file mode 100644 index 000000000000..09df67f03cf4 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h @@ -0,0 +1,1250 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2024 Intel Corporation. */ + +#ifndef _IXGBE_TYPE_E610_H_ +#define _IXGBE_TYPE_E610_H_ + +#define BYTES_PER_DWORD 4 + +/* General E610 defines */ +#define IXGBE_MAX_VSI 768 + +/* Checksum and Shadow RAM pointers */ +#define IXGBE_E610_SR_NVM_CTRL_WORD 0x00 +#define IXGBE_E610_SR_PBA_BLOCK_PTR 0x16 +#define IXGBE_E610_SR_PBA_BLOCK_MASK GENMASK(15, 8) +#define IXGBE_E610_SR_NVM_DEV_STARTER_VER 0x18 +#define IXGBE_E610_SR_NVM_EETRACK_LO 0x2D +#define IXGBE_E610_SR_NVM_EETRACK_HI 0x2E +#define IXGBE_E610_NVM_VER_LO_MASK GENMASK(7, 0) +#define IXGBE_E610_NVM_VER_HI_MASK GENMASK(15, 12) +#define IXGBE_E610_SR_SW_CHECKSUM_WORD 0x3F +#define IXGBE_E610_SR_PFA_PTR 0x40 +#define IXGBE_E610_SR_1ST_NVM_BANK_PTR 0x42 +#define IXGBE_E610_SR_NVM_BANK_SIZE 0x43 +#define IXGBE_E610_SR_1ST_OROM_BANK_PTR 0x44 +#define IXGBE_E610_SR_OROM_BANK_SIZE 0x45 +#define IXGBE_E610_SR_NETLIST_BANK_PTR 0x46 +#define IXGBE_E610_SR_NETLIST_BANK_SIZE 0x47 + +/* The OROM version topology */ +#define IXGBE_OROM_VER_PATCH_MASK GENMASK_ULL(7, 0) +#define IXGBE_OROM_VER_BUILD_MASK GENMASK_ULL(23, 8) +#define IXGBE_OROM_VER_MASK GENMASK_ULL(31, 24) + +/* CSS Header words */ +#define IXGBE_NVM_CSS_HDR_LEN_L 0x02 +#define IXGBE_NVM_CSS_HDR_LEN_H 0x03 +#define IXGBE_NVM_CSS_SREV_L 0x14 +#define IXGBE_NVM_CSS_SREV_H 0x15 + +#define IXGBE_HDR_LEN_ROUNDUP 32 + +/* Length of Authentication header section in words */ +#define IXGBE_NVM_AUTH_HEADER_LEN 0x08 + +/* Shadow RAM related */ +#define IXGBE_SR_WORDS_IN_1KB 512 + +/* The Netlist ID Block is located after all of the Link Topology nodes. */ +#define IXGBE_NETLIST_ID_BLK_SIZE 0x30 +#define IXGBE_NETLIST_ID_BLK_OFFSET(n) IXGBE_NETLIST_LINK_TOPO_OFFSET(0x0004 + 2 * (n)) + +/* netlist ID block field offsets (word offsets) */ +#define IXGBE_NETLIST_ID_BLK_MAJOR_VER_LOW 0x02 +#define IXGBE_NETLIST_ID_BLK_MAJOR_VER_HIGH 0x03 +#define IXGBE_NETLIST_ID_BLK_MINOR_VER_LOW 0x04 +#define IXGBE_NETLIST_ID_BLK_MINOR_VER_HIGH 0x05 +#define IXGBE_NETLIST_ID_BLK_TYPE_LOW 0x06 +#define IXGBE_NETLIST_ID_BLK_TYPE_HIGH 0x07 +#define IXGBE_NETLIST_ID_BLK_REV_LOW 0x08 +#define IXGBE_NETLIST_ID_BLK_REV_HIGH 0x09 +#define IXGBE_NETLIST_ID_BLK_SHA_HASH_WORD(n) (0x0A + (n)) +#define IXGBE_NETLIST_ID_BLK_CUST_VER 0x2F + +/* The Link Topology Netlist section is stored as a series of words. It is + * stored in the NVM as a TLV, with the first two words containing the type + * and length. + */ +#define IXGBE_NETLIST_LINK_TOPO_MOD_ID 0x011B +#define IXGBE_NETLIST_TYPE_OFFSET 0x0000 +#define IXGBE_NETLIST_LEN_OFFSET 0x0001 + +/* The Link Topology section follows the TLV header. When reading the netlist + * using ixgbe_read_netlist_module, we need to account for the 2-word TLV + * header. + */ +#define IXGBE_NETLIST_LINK_TOPO_OFFSET(n) ((n) + 2) +#define IXGBE_LINK_TOPO_MODULE_LEN IXGBE_NETLIST_LINK_TOPO_OFFSET(0x0000) +#define IXGBE_LINK_TOPO_NODE_COUNT IXGBE_NETLIST_LINK_TOPO_OFFSET(0x0001) +#define IXGBE_LINK_TOPO_NODE_COUNT_M GENMASK_ULL(9, 0) + +/* Firmware Status Register (GL_FWSTS) */ +#define GL_FWSTS 0x00083048 /* Reset Source: POR */ +#define GL_FWSTS_EP_PF0 BIT(24) +#define GL_FWSTS_EP_PF1 BIT(25) + +/* Global NVM General Status Register */ +#define GLNVM_GENS 0x000B6100 /* Reset Source: POR */ +#define GLNVM_GENS_SR_SIZE_M GENMASK(7, 5) + +#define IXGBE_GL_MNG_FWSM 0x000B6134 /* Reset Source: POR */ +#define IXGBE_GL_MNG_FWSM_RECOVERY_M BIT(1) +#define IXGBE_GL_MNG_FWSM_ROLLBACK_M BIT(2) + +/* Flash Access Register */ +#define IXGBE_GLNVM_FLA 0x000B6108 /* Reset Source: POR */ +#define IXGBE_GLNVM_FLA_LOCKED_S 6 +#define IXGBE_GLNVM_FLA_LOCKED_M BIT(6) + +/* Auxiliary field, mask and shift definition for Shadow RAM and NVM Flash */ +#define IXGBE_SR_CTRL_WORD_1_M GENMASK(7, 6) +#define IXGBE_SR_CTRL_WORD_VALID BIT(0) +#define IXGBE_SR_CTRL_WORD_OROM_BANK BIT(3) +#define IXGBE_SR_CTRL_WORD_NETLIST_BANK BIT(4) +#define IXGBE_SR_CTRL_WORD_NVM_BANK BIT(5) +#define IXGBE_SR_NVM_PTR_4KB_UNITS BIT(15) + +/* Admin Command Interface (ACI) registers */ +#define IXGBE_PF_HIDA(_i) (0x00085000 + ((_i) * 4)) +#define IXGBE_PF_HIDA_2(_i) (0x00085020 + ((_i) * 4)) +#define IXGBE_PF_HIBA(_i) (0x00084000 + ((_i) * 4)) +#define IXGBE_PF_HICR 0x00082048 + +#define IXGBE_PF_HICR_EN BIT(0) +#define IXGBE_PF_HICR_C BIT(1) +#define IXGBE_PF_HICR_SV BIT(2) +#define IXGBE_PF_HICR_EV BIT(3) + +#define IXGBE_FW_API_VER_MAJOR 0x01 +#define IXGBE_FW_API_VER_MINOR 0x07 +#define IXGBE_FW_API_VER_DIFF_ALLOWED 0x02 + +#define IXGBE_ACI_DESC_SIZE 32 +#define IXGBE_ACI_DESC_SIZE_IN_DWORDS (IXGBE_ACI_DESC_SIZE / BYTES_PER_DWORD) + +#define IXGBE_ACI_MAX_BUFFER_SIZE 4096 /* Size in bytes */ +#define IXGBE_ACI_SEND_DELAY_TIME_MS 10 +#define IXGBE_ACI_SEND_MAX_EXECUTE 3 +#define IXGBE_ACI_SEND_TIMEOUT_MS \ + (IXGBE_ACI_SEND_MAX_EXECUTE * IXGBE_ACI_SEND_DELAY_TIME_MS) +/* [ms] timeout of waiting for sync response */ +#define IXGBE_ACI_SYNC_RESPONSE_TIMEOUT 100000 +/* [ms] timeout of waiting for async response */ +#define IXGBE_ACI_ASYNC_RESPONSE_TIMEOUT 150000 +/* [ms] timeout of waiting for resource release */ +#define IXGBE_ACI_RELEASE_RES_TIMEOUT 10000 + +/* FW defined boundary for a large buffer, 4k >= Large buffer > 512 bytes */ +#define IXGBE_ACI_LG_BUF 512 + +/* Flags sub-structure + * |0 |1 |2 |3 |4 |5 |6 |7 |8 |9 |10 |11 |12 |13 |14 |15 | + * |DD |CMP|ERR|VFE| * * RESERVED * * |LB |RD |VFC|BUF|SI |EI |FE | + */ + +#define IXGBE_ACI_FLAG_DD BIT(0) /* 0x1 */ +#define IXGBE_ACI_FLAG_CMP BIT(1) /* 0x2 */ +#define IXGBE_ACI_FLAG_ERR BIT(2) /* 0x4 */ +#define IXGBE_ACI_FLAG_VFE BIT(3) /* 0x8 */ +#define IXGBE_ACI_FLAG_LB BIT(9) /* 0x200 */ +#define IXGBE_ACI_FLAG_RD BIT(10) /* 0x400 */ +#define IXGBE_ACI_FLAG_VFC BIT(11) /* 0x800 */ +#define IXGBE_ACI_FLAG_BUF BIT(12) /* 0x1000 */ +#define IXGBE_ACI_FLAG_SI BIT(13) /* 0x2000 */ +#define IXGBE_ACI_FLAG_EI BIT(14) /* 0x4000 */ +#define IXGBE_ACI_FLAG_FE BIT(15) /* 0x8000 */ + +/* Admin Command Interface (ACI) error codes */ +enum ixgbe_aci_err { + IXGBE_ACI_RC_OK = 0, /* Success */ + IXGBE_ACI_RC_EPERM = 1, /* Operation not permitted */ + IXGBE_ACI_RC_ENOENT = 2, /* No such element */ + IXGBE_ACI_RC_ESRCH = 3, /* Bad opcode */ + IXGBE_ACI_RC_EINTR = 4, /* Operation interrupted */ + IXGBE_ACI_RC_EIO = 5, /* I/O error */ + IXGBE_ACI_RC_ENXIO = 6, /* No such resource */ + IXGBE_ACI_RC_E2BIG = 7, /* Arg too long */ + IXGBE_ACI_RC_EAGAIN = 8, /* Try again */ + IXGBE_ACI_RC_ENOMEM = 9, /* Out of memory */ + IXGBE_ACI_RC_EACCES = 10, /* Permission denied */ + IXGBE_ACI_RC_EFAULT = 11, /* Bad address */ + IXGBE_ACI_RC_EBUSY = 12, /* Device or resource busy */ + IXGBE_ACI_RC_EEXIST = 13, /* Object already exists */ + IXGBE_ACI_RC_EINVAL = 14, /* Invalid argument */ + IXGBE_ACI_RC_ENOTTY = 15, /* Not a typewriter */ + IXGBE_ACI_RC_ENOSPC = 16, /* No space left or alloc failure */ + IXGBE_ACI_RC_ENOSYS = 17, /* Function not implemented */ + IXGBE_ACI_RC_ERANGE = 18, /* Parameter out of range */ + IXGBE_ACI_RC_EFLUSHED = 19, /* Cmd flushed due to prev cmd error */ + IXGBE_ACI_RC_BAD_ADDR = 20, /* Descriptor contains a bad pointer */ + IXGBE_ACI_RC_EMODE = 21, /* Op not allowed in current dev mode */ + IXGBE_ACI_RC_EFBIG = 22, /* File too big */ + IXGBE_ACI_RC_ESBCOMP = 23, /* SB-IOSF completion unsuccessful */ + IXGBE_ACI_RC_ENOSEC = 24, /* Missing security manifest */ + IXGBE_ACI_RC_EBADSIG = 25, /* Bad RSA signature */ + IXGBE_ACI_RC_ESVN = 26, /* SVN number prohibits this package */ + IXGBE_ACI_RC_EBADMAN = 27, /* Manifest hash mismatch */ + IXGBE_ACI_RC_EBADBUF = 28, /* Buffer hash mismatches manifest */ + IXGBE_ACI_RC_EACCES_BMCU = 29, /* BMC Update in progress */ +}; + +/* Admin Command Interface (ACI) opcodes */ +enum ixgbe_aci_opc { + ixgbe_aci_opc_get_ver = 0x0001, + ixgbe_aci_opc_driver_ver = 0x0002, + ixgbe_aci_opc_get_exp_err = 0x0005, + + /* resource ownership */ + ixgbe_aci_opc_req_res = 0x0008, + ixgbe_aci_opc_release_res = 0x0009, + + /* device/function capabilities */ + ixgbe_aci_opc_list_func_caps = 0x000A, + ixgbe_aci_opc_list_dev_caps = 0x000B, + + /* safe disable of RXEN */ + ixgbe_aci_opc_disable_rxen = 0x000C, + + /* FW events */ + ixgbe_aci_opc_get_fw_event = 0x0014, + + /* PHY commands */ + ixgbe_aci_opc_get_phy_caps = 0x0600, + ixgbe_aci_opc_set_phy_cfg = 0x0601, + ixgbe_aci_opc_restart_an = 0x0605, + ixgbe_aci_opc_get_link_status = 0x0607, + ixgbe_aci_opc_set_event_mask = 0x0613, + ixgbe_aci_opc_get_link_topo = 0x06E0, + ixgbe_aci_opc_get_link_topo_pin = 0x06E1, + ixgbe_aci_opc_read_i2c = 0x06E2, + ixgbe_aci_opc_write_i2c = 0x06E3, + ixgbe_aci_opc_read_mdio = 0x06E4, + ixgbe_aci_opc_write_mdio = 0x06E5, + ixgbe_aci_opc_set_gpio_by_func = 0x06E6, + ixgbe_aci_opc_get_gpio_by_func = 0x06E7, + ixgbe_aci_opc_set_port_id_led = 0x06E9, + ixgbe_aci_opc_set_gpio = 0x06EC, + ixgbe_aci_opc_get_gpio = 0x06ED, + ixgbe_aci_opc_sff_eeprom = 0x06EE, + ixgbe_aci_opc_prog_topo_dev_nvm = 0x06F2, + ixgbe_aci_opc_read_topo_dev_nvm = 0x06F3, + + /* NVM commands */ + ixgbe_aci_opc_nvm_read = 0x0701, + ixgbe_aci_opc_nvm_erase = 0x0702, + ixgbe_aci_opc_nvm_write = 0x0703, + ixgbe_aci_opc_nvm_cfg_read = 0x0704, + ixgbe_aci_opc_nvm_cfg_write = 0x0705, + ixgbe_aci_opc_nvm_checksum = 0x0706, + ixgbe_aci_opc_nvm_write_activate = 0x0707, + ixgbe_aci_opc_nvm_sr_dump = 0x0707, + ixgbe_aci_opc_nvm_save_factory_settings = 0x0708, + ixgbe_aci_opc_nvm_update_empr = 0x0709, + ixgbe_aci_opc_nvm_pkg_data = 0x070A, + ixgbe_aci_opc_nvm_pass_component_tbl = 0x070B, + + /* Alternate Structure Commands */ + ixgbe_aci_opc_write_alt_direct = 0x0900, + ixgbe_aci_opc_write_alt_indirect = 0x0901, + ixgbe_aci_opc_read_alt_direct = 0x0902, + ixgbe_aci_opc_read_alt_indirect = 0x0903, + ixgbe_aci_opc_done_alt_write = 0x0904, + ixgbe_aci_opc_clear_port_alt_write = 0x0906, + + /* TCA Events */ + ixgbe_aci_opc_temp_tca_event = 0x0C94, + + /* debug commands */ + ixgbe_aci_opc_debug_dump_internals = 0xFF08, + + /* SystemDiagnostic commands */ + ixgbe_aci_opc_set_health_status_config = 0xFF20, + ixgbe_aci_opc_get_supported_health_status_codes = 0xFF21, + ixgbe_aci_opc_get_health_status = 0xFF22, + ixgbe_aci_opc_clear_health_status = 0xFF23, +}; + +/* Get version (direct 0x0001) */ +struct ixgbe_aci_cmd_get_ver { + __le32 rom_ver; + __le32 fw_build; + u8 fw_branch; + u8 fw_major; + u8 fw_minor; + u8 fw_patch; + u8 api_branch; + u8 api_major; + u8 api_minor; + u8 api_patch; +}; + +#define IXGBE_DRV_VER_STR_LEN_E610 32 + +/* Send driver version (indirect 0x0002) */ +struct ixgbe_aci_cmd_driver_ver { + u8 major_ver; + u8 minor_ver; + u8 build_ver; + u8 subbuild_ver; + u8 reserved[4]; + __le32 addr_high; + __le32 addr_low; +}; + +/* Get Expanded Error Code (0x0005, direct) */ +struct ixgbe_aci_cmd_get_exp_err { + __le32 reason; +#define IXGBE_ACI_EXPANDED_ERROR_NOT_PROVIDED 0xFFFFFFFF + __le32 identifier; + u8 rsvd[8]; +}; + +/* FW update timeout definitions are in milliseconds */ +#define IXGBE_NVM_TIMEOUT 180000 + +enum ixgbe_aci_res_access_type { + IXGBE_RES_READ = 1, + IXGBE_RES_WRITE +}; + +enum ixgbe_aci_res_ids { + IXGBE_NVM_RES_ID = 1, + IXGBE_SPD_RES_ID, + IXGBE_CHANGE_LOCK_RES_ID, + IXGBE_GLOBAL_CFG_LOCK_RES_ID +}; + +/* Request resource ownership (direct 0x0008) + * Release resource ownership (direct 0x0009) + */ +struct ixgbe_aci_cmd_req_res { + __le16 res_id; + __le16 access_type; + + /* Upon successful completion, FW writes this value and driver is + * expected to release resource before timeout. This value is provided + * in milliseconds. + */ + __le32 timeout; +#define IXGBE_ACI_RES_NVM_READ_DFLT_TIMEOUT_MS 3000 +#define IXGBE_ACI_RES_NVM_WRITE_DFLT_TIMEOUT_MS 180000 +#define IXGBE_ACI_RES_CHNG_LOCK_DFLT_TIMEOUT_MS 1000 +#define IXGBE_ACI_RES_GLBL_LOCK_DFLT_TIMEOUT_MS 3000 + /* For SDP: pin ID of the SDP */ + __le32 res_number; + __le16 status; +#define IXGBE_ACI_RES_GLBL_SUCCESS 0 +#define IXGBE_ACI_RES_GLBL_IN_PROG 1 +#define IXGBE_ACI_RES_GLBL_DONE 2 + u8 reserved[2]; +}; + +/* Get function capabilities (indirect 0x000A) + * Get device capabilities (indirect 0x000B) + */ +struct ixgbe_aci_cmd_list_caps { + u8 cmd_flags; + u8 pf_index; + u8 reserved[2]; + __le32 count; + __le32 addr_high; + __le32 addr_low; +}; + +/* Device/Function buffer entry, repeated per reported capability */ +struct ixgbe_aci_cmd_list_caps_elem { + __le16 cap; +#define IXGBE_ACI_CAPS_VALID_FUNCTIONS 0x0005 +#define IXGBE_ACI_MAX_VALID_FUNCTIONS 0x8 +#define IXGBE_ACI_CAPS_SRIOV 0x0012 +#define IXGBE_ACI_CAPS_VF 0x0013 +#define IXGBE_ACI_CAPS_VMDQ 0x0014 +#define IXGBE_ACI_CAPS_VSI 0x0017 +#define IXGBE_ACI_CAPS_DCB 0x0018 +#define IXGBE_ACI_CAPS_RSS 0x0040 +#define IXGBE_ACI_CAPS_RXQS 0x0041 +#define IXGBE_ACI_CAPS_TXQS 0x0042 +#define IXGBE_ACI_CAPS_MSIX 0x0043 +#define IXGBE_ACI_CAPS_FD 0x0045 +#define IXGBE_ACI_CAPS_1588 0x0046 +#define IXGBE_ACI_CAPS_MAX_MTU 0x0047 +#define IXGBE_ACI_CAPS_NVM_VER 0x0048 +#define IXGBE_ACI_CAPS_PENDING_NVM_VER 0x0049 +#define IXGBE_ACI_CAPS_OROM_VER 0x004A +#define IXGBE_ACI_CAPS_PENDING_OROM_VER 0x004B +#define IXGBE_ACI_CAPS_PENDING_NET_VER 0x004D +#define IXGBE_ACI_CAPS_INLINE_IPSEC 0x0070 +#define IXGBE_ACI_CAPS_NUM_ENABLED_PORTS 0x0072 +#define IXGBE_ACI_CAPS_PCIE_RESET_AVOIDANCE 0x0076 +#define IXGBE_ACI_CAPS_POST_UPDATE_RESET_RESTRICT 0x0077 +#define IXGBE_ACI_CAPS_NVM_MGMT 0x0080 +#define IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG0 0x0081 +#define IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG1 0x0082 +#define IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG2 0x0083 +#define IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG3 0x0084 + u8 major_ver; + u8 minor_ver; + /* Number of resources described by this capability */ + __le32 number; + /* Only meaningful for some types of resources */ + __le32 logical_id; + /* Only meaningful for some types of resources */ + __le32 phys_id; + __le64 rsvd1; + __le64 rsvd2; +}; + +/* Disable RXEN (direct 0x000C) */ +struct ixgbe_aci_cmd_disable_rxen { + u8 lport_num; + u8 reserved[15]; +}; + +/* Get PHY capabilities (indirect 0x0600) */ +struct ixgbe_aci_cmd_get_phy_caps { + u8 lport_num; + u8 reserved; + __le16 param0; + /* 18.0 - Report qualified modules */ +#define IXGBE_ACI_GET_PHY_RQM BIT(0) + /* 18.1 - 18.3 : Report mode + * 000b - Report topology capabilities, without media + * 001b - Report topology capabilities, with media + * 010b - Report Active configuration + * 011b - Report PHY Type and FEC mode capabilities + * 100b - Report Default capabilities + */ +#define IXGBE_ACI_REPORT_MODE_M GENMASK(3, 1) +#define IXGBE_ACI_REPORT_TOPO_CAP_NO_MEDIA 0 +#define IXGBE_ACI_REPORT_TOPO_CAP_MEDIA BIT(1) +#define IXGBE_ACI_REPORT_ACTIVE_CFG BIT(2) +#define IXGBE_ACI_REPORT_DFLT_CFG BIT(3) + __le32 reserved1; + __le32 addr_high; + __le32 addr_low; +}; + +/* This is #define of PHY type (Extended): + * The first set of defines is for phy_type_low. + */ +#define IXGBE_PHY_TYPE_LOW_100BASE_TX BIT_ULL(0) +#define IXGBE_PHY_TYPE_LOW_100M_SGMII BIT_ULL(1) +#define IXGBE_PHY_TYPE_LOW_1000BASE_T BIT_ULL(2) +#define IXGBE_PHY_TYPE_LOW_1000BASE_SX BIT_ULL(3) +#define IXGBE_PHY_TYPE_LOW_1000BASE_LX BIT_ULL(4) +#define IXGBE_PHY_TYPE_LOW_1000BASE_KX BIT_ULL(5) +#define IXGBE_PHY_TYPE_LOW_1G_SGMII BIT_ULL(6) +#define IXGBE_PHY_TYPE_LOW_2500BASE_T BIT_ULL(7) +#define IXGBE_PHY_TYPE_LOW_2500BASE_X BIT_ULL(8) +#define IXGBE_PHY_TYPE_LOW_2500BASE_KX BIT_ULL(9) +#define IXGBE_PHY_TYPE_LOW_5GBASE_T BIT_ULL(10) +#define IXGBE_PHY_TYPE_LOW_5GBASE_KR BIT_ULL(11) +#define IXGBE_PHY_TYPE_LOW_10GBASE_T BIT_ULL(12) +#define IXGBE_PHY_TYPE_LOW_10G_SFI_DA BIT_ULL(13) +#define IXGBE_PHY_TYPE_LOW_10GBASE_SR BIT_ULL(14) +#define IXGBE_PHY_TYPE_LOW_10GBASE_LR BIT_ULL(15) +#define IXGBE_PHY_TYPE_LOW_10GBASE_KR_CR1 BIT_ULL(16) +#define IXGBE_PHY_TYPE_LOW_10G_SFI_AOC_ACC BIT_ULL(17) +#define IXGBE_PHY_TYPE_LOW_10G_SFI_C2C BIT_ULL(18) +#define IXGBE_PHY_TYPE_LOW_25GBASE_T BIT_ULL(19) +#define IXGBE_PHY_TYPE_LOW_25GBASE_CR BIT_ULL(20) +#define IXGBE_PHY_TYPE_LOW_25GBASE_CR_S BIT_ULL(21) +#define IXGBE_PHY_TYPE_LOW_25GBASE_CR1 BIT_ULL(22) +#define IXGBE_PHY_TYPE_LOW_25GBASE_SR BIT_ULL(23) +#define IXGBE_PHY_TYPE_LOW_25GBASE_LR BIT_ULL(24) +#define IXGBE_PHY_TYPE_LOW_25GBASE_KR BIT_ULL(25) +#define IXGBE_PHY_TYPE_LOW_25GBASE_KR_S BIT_ULL(26) +#define IXGBE_PHY_TYPE_LOW_25GBASE_KR1 BIT_ULL(27) +#define IXGBE_PHY_TYPE_LOW_25G_AUI_AOC_ACC BIT_ULL(28) +#define IXGBE_PHY_TYPE_LOW_25G_AUI_C2C BIT_ULL(29) +#define IXGBE_PHY_TYPE_LOW_MAX_INDEX 29 +/* The second set of defines is for phy_type_high. */ +#define IXGBE_PHY_TYPE_HIGH_10BASE_T BIT_ULL(1) +#define IXGBE_PHY_TYPE_HIGH_10M_SGMII BIT_ULL(2) +#define IXGBE_PHY_TYPE_HIGH_2500M_SGMII BIT_ULL(56) +#define IXGBE_PHY_TYPE_HIGH_100M_USXGMII BIT_ULL(57) +#define IXGBE_PHY_TYPE_HIGH_1G_USXGMII BIT_ULL(58) +#define IXGBE_PHY_TYPE_HIGH_2500M_USXGMII BIT_ULL(59) +#define IXGBE_PHY_TYPE_HIGH_5G_USXGMII BIT_ULL(60) +#define IXGBE_PHY_TYPE_HIGH_10G_USXGMII BIT_ULL(61) +#define IXGBE_PHY_TYPE_HIGH_MAX_INDEX 61 + +struct ixgbe_aci_cmd_get_phy_caps_data { + __le64 phy_type_low; /* Use values from IXGBE_PHY_TYPE_LOW_* */ + __le64 phy_type_high; /* Use values from IXGBE_PHY_TYPE_HIGH_* */ + u8 caps; +#define IXGBE_ACI_PHY_EN_TX_LINK_PAUSE BIT(0) +#define IXGBE_ACI_PHY_EN_RX_LINK_PAUSE BIT(1) +#define IXGBE_ACI_PHY_LOW_POWER_MODE BIT(2) +#define IXGBE_ACI_PHY_EN_LINK BIT(3) +#define IXGBE_ACI_PHY_AN_MODE BIT(4) +#define IXGBE_ACI_PHY_EN_MOD_QUAL BIT(5) +#define IXGBE_ACI_PHY_EN_LESM BIT(6) +#define IXGBE_ACI_PHY_EN_AUTO_FEC BIT(7) +#define IXGBE_ACI_PHY_CAPS_MASK GENMASK(7, 0) + u8 low_power_ctrl_an; +#define IXGBE_ACI_PHY_EN_D3COLD_LOW_POWER_AUTONEG BIT(0) +#define IXGBE_ACI_PHY_AN_EN_CLAUSE28 BIT(1) +#define IXGBE_ACI_PHY_AN_EN_CLAUSE73 BIT(2) +#define IXGBE_ACI_PHY_AN_EN_CLAUSE37 BIT(3) + __le16 eee_cap; +#define IXGBE_ACI_PHY_EEE_EN_100BASE_TX BIT(0) +#define IXGBE_ACI_PHY_EEE_EN_1000BASE_T BIT(1) +#define IXGBE_ACI_PHY_EEE_EN_10GBASE_T BIT(2) +#define IXGBE_ACI_PHY_EEE_EN_1000BASE_KX BIT(3) +#define IXGBE_ACI_PHY_EEE_EN_10GBASE_KR BIT(4) +#define IXGBE_ACI_PHY_EEE_EN_25GBASE_KR BIT(5) +#define IXGBE_ACI_PHY_EEE_EN_10BASE_T BIT(11) + __le16 eeer_value; + u8 phy_id_oui[4]; /* PHY/Module ID connected on the port */ + u8 phy_fw_ver[8]; + u8 link_fec_options; +#define IXGBE_ACI_PHY_FEC_10G_KR_40G_KR4_EN BIT(0) +#define IXGBE_ACI_PHY_FEC_10G_KR_40G_KR4_REQ BIT(1) +#define IXGBE_ACI_PHY_FEC_25G_RS_528_REQ BIT(2) +#define IXGBE_ACI_PHY_FEC_25G_KR_REQ BIT(3) +#define IXGBE_ACI_PHY_FEC_25G_RS_544_REQ BIT(4) +#define IXGBE_ACI_PHY_FEC_25G_RS_CLAUSE91_EN BIT(6) +#define IXGBE_ACI_PHY_FEC_25G_KR_CLAUSE74_EN BIT(7) +#define IXGBE_ACI_PHY_FEC_MASK 0xdf + u8 module_compliance_enforcement; +#define IXGBE_ACI_MOD_ENFORCE_STRICT_MODE BIT(0) + u8 extended_compliance_code; +#define IXGBE_ACI_MODULE_TYPE_TOTAL_BYTE 3 + u8 module_type[IXGBE_ACI_MODULE_TYPE_TOTAL_BYTE]; +#define IXGBE_ACI_MOD_TYPE_BYTE0_SFP_PLUS 0xA0 +#define IXGBE_ACI_MOD_TYPE_BYTE0_QSFP_PLUS 0x80 +#define IXGBE_ACI_MOD_TYPE_IDENT 1 +#define IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_PASSIVE BIT(0) +#define IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_ACTIVE BIT(1) +#define IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_SR BIT(4) +#define IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_LR BIT(5) +#define IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_LRM BIT(6) +#define IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_ER BIT(7) +#define IXGBE_ACI_MOD_TYPE_BYTE2_SFP_PLUS 0xA0 +#define IXGBE_ACI_MOD_TYPE_BYTE2_QSFP_PLUS 0x86 + u8 qualified_module_count; + u8 rsvd2[7]; /* Bytes 47:41 reserved */ +#define IXGBE_ACI_QUAL_MOD_COUNT_MAX 16 + struct { + u8 v_oui[3]; + u8 rsvd3; + u8 v_part[16]; + __le32 v_rev; + __le64 rsvd4; + } qual_modules[IXGBE_ACI_QUAL_MOD_COUNT_MAX]; +}; + +/* Set PHY capabilities (direct 0x0601) + * NOTE: This command must be followed by setup link and restart auto-neg + */ +struct ixgbe_aci_cmd_set_phy_cfg { + u8 lport_num; + u8 reserved[7]; + __le32 addr_high; + __le32 addr_low; +}; + +/* Set PHY config command data structure */ +struct ixgbe_aci_cmd_set_phy_cfg_data { + __le64 phy_type_low; /* Use values from IXGBE_PHY_TYPE_LOW_* */ + __le64 phy_type_high; /* Use values from IXGBE_PHY_TYPE_HIGH_* */ + u8 caps; +#define IXGBE_ACI_PHY_ENA_VALID_MASK 0xef +#define IXGBE_ACI_PHY_ENA_TX_PAUSE_ABILITY BIT(0) +#define IXGBE_ACI_PHY_ENA_RX_PAUSE_ABILITY BIT(1) +#define IXGBE_ACI_PHY_ENA_LOW_POWER BIT(2) +#define IXGBE_ACI_PHY_ENA_LINK BIT(3) +#define IXGBE_ACI_PHY_ENA_AUTO_LINK_UPDT BIT(5) +#define IXGBE_ACI_PHY_ENA_LESM BIT(6) +#define IXGBE_ACI_PHY_ENA_AUTO_FEC BIT(7) + u8 low_power_ctrl_an; + __le16 eee_cap; /* Value from ixgbe_aci_get_phy_caps */ + __le16 eeer_value; /* Use defines from ixgbe_aci_get_phy_caps */ + u8 link_fec_opt; /* Use defines from ixgbe_aci_get_phy_caps */ + u8 module_compliance_enforcement; +}; + +/* Restart AN command data structure (direct 0x0605) + * Also used for response, with only the lport_num field present. + */ +struct ixgbe_aci_cmd_restart_an { + u8 lport_num; + u8 reserved; + u8 cmd_flags; +#define IXGBE_ACI_RESTART_AN_LINK_RESTART BIT(1) +#define IXGBE_ACI_RESTART_AN_LINK_ENABLE BIT(2) + u8 reserved2[13]; +}; + +/* Get link status (indirect 0x0607), also used for Link Status Event */ +struct ixgbe_aci_cmd_get_link_status { + u8 lport_num; + u8 reserved; + __le16 cmd_flags; +#define IXGBE_ACI_LSE_M GENMASK(1, 0) +#define IXGBE_ACI_LSE_NOP 0x0 +#define IXGBE_ACI_LSE_DIS 0x2 +#define IXGBE_ACI_LSE_ENA 0x3 + /* only response uses this flag */ +#define IXGBE_ACI_LSE_IS_ENABLED 0x1 + __le32 reserved2; + __le32 addr_high; + __le32 addr_low; +}; + +/* Get link status response data structure, also used for Link Status Event */ +struct ixgbe_aci_cmd_get_link_status_data { + u8 topo_media_conflict; +#define IXGBE_ACI_LINK_TOPO_CONFLICT BIT(0) +#define IXGBE_ACI_LINK_MEDIA_CONFLICT BIT(1) +#define IXGBE_ACI_LINK_TOPO_CORRUPT BIT(2) +#define IXGBE_ACI_LINK_TOPO_UNREACH_PRT BIT(4) +#define IXGBE_ACI_LINK_TOPO_UNDRUTIL_PRT BIT(5) +#define IXGBE_ACI_LINK_TOPO_UNDRUTIL_MEDIA BIT(6) +#define IXGBE_ACI_LINK_TOPO_UNSUPP_MEDIA BIT(7) + u8 link_cfg_err; +#define IXGBE_ACI_LINK_CFG_ERR BIT(0) +#define IXGBE_ACI_LINK_CFG_COMPLETED BIT(1) +#define IXGBE_ACI_LINK_ACT_PORT_OPT_INVAL BIT(2) +#define IXGBE_ACI_LINK_FEAT_ID_OR_CONFIG_ID_INVAL BIT(3) +#define IXGBE_ACI_LINK_TOPO_CRITICAL_SDP_ERR BIT(4) +#define IXGBE_ACI_LINK_MODULE_POWER_UNSUPPORTED BIT(5) +#define IXGBE_ACI_LINK_EXTERNAL_PHY_LOAD_FAILURE BIT(6) +#define IXGBE_ACI_LINK_INVAL_MAX_POWER_LIMIT BIT(7) + u8 link_info; +#define IXGBE_ACI_LINK_UP BIT(0) /* Link Status */ +#define IXGBE_ACI_LINK_FAULT BIT(1) +#define IXGBE_ACI_LINK_FAULT_TX BIT(2) +#define IXGBE_ACI_LINK_FAULT_RX BIT(3) +#define IXGBE_ACI_LINK_FAULT_REMOTE BIT(4) +#define IXGBE_ACI_LINK_UP_PORT BIT(5) /* External Port Link Status */ +#define IXGBE_ACI_MEDIA_AVAILABLE BIT(6) +#define IXGBE_ACI_SIGNAL_DETECT BIT(7) + u8 an_info; +#define IXGBE_ACI_AN_COMPLETED BIT(0) +#define IXGBE_ACI_LP_AN_ABILITY BIT(1) +#define IXGBE_ACI_PD_FAULT BIT(2) /* Parallel Detection Fault */ +#define IXGBE_ACI_FEC_EN BIT(3) +#define IXGBE_ACI_PHY_LOW_POWER BIT(4) /* Low Power State */ +#define IXGBE_ACI_LINK_PAUSE_TX BIT(5) +#define IXGBE_ACI_LINK_PAUSE_RX BIT(6) +#define IXGBE_ACI_QUALIFIED_MODULE BIT(7) + u8 ext_info; +#define IXGBE_ACI_LINK_PHY_TEMP_ALARM BIT(0) +#define IXGBE_ACI_LINK_EXCESSIVE_ERRORS BIT(1) /* Excessive Link Errors */ + /* Port Tx Suspended */ +#define IXGBE_ACI_LINK_TX_ACTIVE 0 +#define IXGBE_ACI_LINK_TX_DRAINED 1 +#define IXGBE_ACI_LINK_TX_FLUSHED 3 + u8 lb_status; +#define IXGBE_ACI_LINK_LB_PHY_LCL BIT(0) +#define IXGBE_ACI_LINK_LB_PHY_RMT BIT(1) +#define IXGBE_ACI_LINK_LB_MAC_LCL BIT(2) + __le16 max_frame_size; + u8 cfg; +#define IXGBE_ACI_LINK_25G_KR_FEC_EN BIT(0) +#define IXGBE_ACI_LINK_25G_RS_528_FEC_EN BIT(1) +#define IXGBE_ACI_LINK_25G_RS_544_FEC_EN BIT(2) +#define IXGBE_ACI_FEC_MASK GENMASK(2, 0) + /* Pacing Config */ +#define IXGBE_ACI_CFG_PACING_M GENMASK(6, 3) +#define IXGBE_ACI_CFG_PACING_TYPE_M BIT(7) +#define IXGBE_ACI_CFG_PACING_TYPE_AVG 0 +#define IXGBE_ACI_CFG_PACING_TYPE_FIXED IXGBE_ACI_CFG_PACING_TYPE_M + /* External Device Power Ability */ + u8 power_desc; +#define IXGBE_ACI_PWR_CLASS_M GENMASK(5, 0) +#define IXGBE_ACI_LINK_PWR_BASET_LOW_HIGH 0 +#define IXGBE_ACI_LINK_PWR_BASET_HIGH 1 +#define IXGBE_ACI_LINK_PWR_QSFP_CLASS_1 0 +#define IXGBE_ACI_LINK_PWR_QSFP_CLASS_2 1 +#define IXGBE_ACI_LINK_PWR_QSFP_CLASS_3 2 +#define IXGBE_ACI_LINK_PWR_QSFP_CLASS_4 3 + __le16 link_speed; +#define IXGBE_ACI_LINK_SPEED_M GENMASK(10, 0) +#define IXGBE_ACI_LINK_SPEED_10MB BIT(0) +#define IXGBE_ACI_LINK_SPEED_100MB BIT(1) +#define IXGBE_ACI_LINK_SPEED_1000MB BIT(2) +#define IXGBE_ACI_LINK_SPEED_2500MB BIT(3) +#define IXGBE_ACI_LINK_SPEED_5GB BIT(4) +#define IXGBE_ACI_LINK_SPEED_10GB BIT(5) +#define IXGBE_ACI_LINK_SPEED_20GB BIT(6) +#define IXGBE_ACI_LINK_SPEED_25GB BIT(7) +#define IXGBE_ACI_LINK_SPEED_40GB BIT(8) +#define IXGBE_ACI_LINK_SPEED_50GB BIT(9) +#define IXGBE_ACI_LINK_SPEED_100GB BIT(10) +#define IXGBE_ACI_LINK_SPEED_200GB BIT(11) +#define IXGBE_ACI_LINK_SPEED_UNKNOWN BIT(15) + __le16 reserved3; + u8 ext_fec_status; +#define IXGBE_ACI_LINK_RS_272_FEC_EN BIT(0) /* RS 272 FEC enabled */ + u8 reserved4; + __le64 phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */ + __le64 phy_type_high; /* Use values from ICE_PHY_TYPE_HIGH_* */ + /* Get link status version 2 link partner data */ + __le64 lp_phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */ + __le64 lp_phy_type_high; /* Use values from ICE_PHY_TYPE_HIGH_* */ + u8 lp_fec_adv; +#define IXGBE_ACI_LINK_LP_10G_KR_FEC_CAP BIT(0) +#define IXGBE_ACI_LINK_LP_25G_KR_FEC_CAP BIT(1) +#define IXGBE_ACI_LINK_LP_RS_528_FEC_CAP BIT(2) +#define IXGBE_ACI_LINK_LP_50G_KR_272_FEC_CAP BIT(3) +#define IXGBE_ACI_LINK_LP_100G_KR_272_FEC_CAP BIT(4) +#define IXGBE_ACI_LINK_LP_200G_KR_272_FEC_CAP BIT(5) + u8 lp_fec_req; +#define IXGBE_ACI_LINK_LP_10G_KR_FEC_REQ BIT(0) +#define IXGBE_ACI_LINK_LP_25G_KR_FEC_REQ BIT(1) +#define IXGBE_ACI_LINK_LP_RS_528_FEC_REQ BIT(2) +#define IXGBE_ACI_LINK_LP_KR_272_FEC_REQ BIT(3) + u8 lp_flowcontrol; +#define IXGBE_ACI_LINK_LP_PAUSE_ADV BIT(0) +#define IXGBE_ACI_LINK_LP_ASM_DIR_ADV BIT(1) + u8 reserved5[5]; +} __packed; + +/* Set event mask command (direct 0x0613) */ +struct ixgbe_aci_cmd_set_event_mask { + u8 lport_num; + u8 reserved[7]; + __le16 event_mask; +#define IXGBE_ACI_LINK_EVENT_UPDOWN BIT(1) +#define IXGBE_ACI_LINK_EVENT_MEDIA_NA BIT(2) +#define IXGBE_ACI_LINK_EVENT_LINK_FAULT BIT(3) +#define IXGBE_ACI_LINK_EVENT_PHY_TEMP_ALARM BIT(4) +#define IXGBE_ACI_LINK_EVENT_EXCESSIVE_ERRORS BIT(5) +#define IXGBE_ACI_LINK_EVENT_SIGNAL_DETECT BIT(6) +#define IXGBE_ACI_LINK_EVENT_AN_COMPLETED BIT(7) +#define IXGBE_ACI_LINK_EVENT_MODULE_QUAL_FAIL BIT(8) +#define IXGBE_ACI_LINK_EVENT_PORT_TX_SUSPENDED BIT(9) +#define IXGBE_ACI_LINK_EVENT_TOPO_CONFLICT BIT(10) +#define IXGBE_ACI_LINK_EVENT_MEDIA_CONFLICT BIT(11) +#define IXGBE_ACI_LINK_EVENT_PHY_FW_LOAD_FAIL BIT(12) + u8 reserved1[6]; +}; + +struct ixgbe_aci_cmd_link_topo_params { + u8 lport_num; + u8 lport_num_valid; +#define IXGBE_ACI_LINK_TOPO_PORT_NUM_VALID BIT(0) + u8 node_type_ctx; +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_M GENMASK(3, 0) +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_PHY 0 +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_GPIO_CTRL 1 +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_MUX_CTRL 2 +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_LED_CTRL 3 +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_LED 4 +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_THERMAL 5 +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_CAGE 6 +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_MEZZ 7 +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_ID_EEPROM 8 +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_CLK_CTRL 9 +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_CLK_MUX 10 +#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_GPS 11 +#define IXGBE_ACI_LINK_TOPO_NODE_CTX_S 4 +#define IXGBE_ACI_LINK_TOPO_NODE_CTX_M GENMASK(7, 4) +#define IXGBE_ACI_LINK_TOPO_NODE_CTX_GLOBAL 0 +#define IXGBE_ACI_LINK_TOPO_NODE_CTX_BOARD 1 +#define IXGBE_ACI_LINK_TOPO_NODE_CTX_PORT 2 +#define IXGBE_ACI_LINK_TOPO_NODE_CTX_NODE 3 +#define IXGBE_ACI_LINK_TOPO_NODE_CTX_NODE_HANDLE 4 +#define IXGBE_ACI_LINK_TOPO_NODE_CTX_DIRECT_BUS_ACCESS 5 +#define IXGBE_ACI_LINK_TOPO_NODE_CTX_NODE_HANDLE_BUS_ADDRESS 6 + u8 index; +}; + +struct ixgbe_aci_cmd_link_topo_addr { + struct ixgbe_aci_cmd_link_topo_params topo_params; + __le16 handle; +/* Used to decode the handle field */ +#define IXGBE_ACI_LINK_TOPO_HANDLE_BRD_TYPE_M BIT(9) +#define IXGBE_ACI_LINK_TOPO_HANDLE_BRD_TYPE_LOM BIT(9) +#define IXGBE_ACI_LINK_TOPO_HANDLE_BRD_TYPE_MEZZ 0 +}; + +/* Get Link Topology Handle (direct, 0x06E0) */ +struct ixgbe_aci_cmd_get_link_topo { + struct ixgbe_aci_cmd_link_topo_addr addr; + u8 node_part_num; +#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_PCA9575 0x21 +#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_ZL30632_80032 0x24 +#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_SI5384 0x25 +#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_C827 0x31 +#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_GEN_CLK_MUX 0x47 +#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_GEN_GPS 0x48 +#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_E610_PTC 0x49 + u8 rsvd[9]; +}; + +/* Get Link Topology Pin (direct, 0x06E1) */ +struct ixgbe_aci_cmd_get_link_topo_pin { + struct ixgbe_aci_cmd_link_topo_addr addr; + u8 input_io_params; +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_GPIO 0 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_RESET_N 1 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_INT_N 2 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_PRESENT_N 3 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_TX_DIS 4 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_MODSEL_N 5 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_LPMODE 6 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_TX_FAULT 7 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_RX_LOSS 8 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_RS0 9 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_RS1 10 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_EEPROM_WP 11 +/* 12 repeats intentionally due to two different uses depending on context */ +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_LED 12 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_RED_LED 12 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_GREEN_LED 13 +#define IXGBE_ACI_LINK_TOPO_IO_FUNC_BLUE_LED 14 +#define IXGBE_ACI_LINK_TOPO_INPUT_IO_TYPE_GPIO 3 +/* Use IXGBE_ACI_LINK_TOPO_NODE_TYPE_* for the type values */ + u8 output_io_params; +/* Use IXGBE_ACI_LINK_TOPO_NODE_TYPE_* for the type values */ + u8 output_io_flags; +#define IXGBE_ACI_LINK_TOPO_OUTPUT_POLARITY BIT(5) +#define IXGBE_ACI_LINK_TOPO_OUTPUT_VALUE BIT(6) +#define IXGBE_ACI_LINK_TOPO_OUTPUT_DRIVEN BIT(7) + u8 rsvd[7]; +}; + +/* Set Port Identification LED (direct, 0x06E9) */ +struct ixgbe_aci_cmd_set_port_id_led { + u8 lport_num; + u8 lport_num_valid; + u8 ident_mode; + u8 rsvd[13]; +}; + +#define IXGBE_ACI_PORT_ID_PORT_NUM_VALID BIT(0) +#define IXGBE_ACI_PORT_IDENT_LED_ORIG 0 +#define IXGBE_ACI_PORT_IDENT_LED_BLINK BIT(0) + +/* Read/Write SFF EEPROM command (indirect 0x06EE) */ +struct ixgbe_aci_cmd_sff_eeprom { + u8 lport_num; + u8 lport_num_valid; +#define IXGBE_ACI_SFF_PORT_NUM_VALID BIT(0) + __le16 i2c_bus_addr; +#define IXGBE_ACI_SFF_I2CBUS_7BIT_M GENMASK(6, 0) +#define IXGBE_ACI_SFF_I2CBUS_10BIT_M GENMASK(9, 0) +#define IXGBE_ACI_SFF_I2CBUS_TYPE_M BIT(10) +#define IXGBE_ACI_SFF_I2CBUS_TYPE_7BIT 0 +#define IXGBE_ACI_SFF_I2CBUS_TYPE_10BIT IXGBE_ACI_SFF_I2CBUS_TYPE_M +#define IXGBE_ACI_SFF_NO_PAGE_BANK_UPDATE 0 +#define IXGBE_ACI_SFF_UPDATE_PAGE 1 +#define IXGBE_ACI_SFF_UPDATE_BANK 2 +#define IXGBE_ACI_SFF_UPDATE_PAGE_BANK 3 +#define IXGBE_ACI_SFF_IS_WRITE BIT(15) + __le16 i2c_offset; + u8 module_bank; + u8 module_page; + __le32 addr_high; + __le32 addr_low; +}; + +/* NVM Read command (indirect 0x0701) + * NVM Erase commands (direct 0x0702) + * NVM Write commands (indirect 0x0703) + * NVM Write Activate commands (direct 0x0707) + * NVM Shadow RAM Dump commands (direct 0x0707) + */ +struct ixgbe_aci_cmd_nvm { +#define IXGBE_ACI_NVM_MAX_OFFSET 0xFFFFFF + __le16 offset_low; + u8 offset_high; /* For Write Activate offset_high is used as flags2 */ +#define IXGBE_ACI_NVM_OFFSET_HI_A_MASK GENMASK(15, 8) +#define IXGBE_ACI_NVM_OFFSET_HI_U_MASK GENMASK(23, 16) + u8 cmd_flags; +#define IXGBE_ACI_NVM_LAST_CMD BIT(0) +#define IXGBE_ACI_NVM_PCIR_REQ BIT(0) /* Used by NVM Write reply */ +#define IXGBE_ACI_NVM_PRESERVE_ALL BIT(1) +#define IXGBE_ACI_NVM_ACTIV_SEL_NVM BIT(3) /* Write Activate/SR Dump only */ +#define IXGBE_ACI_NVM_ACTIV_SEL_OROM BIT(4) +#define IXGBE_ACI_NVM_ACTIV_SEL_NETLIST BIT(5) +#define IXGBE_ACI_NVM_SPECIAL_UPDATE BIT(6) +#define IXGBE_ACI_NVM_REVERT_LAST_ACTIV BIT(6) /* Write Activate only */ +#define IXGBE_ACI_NVM_FLASH_ONLY BIT(7) +#define IXGBE_ACI_NVM_RESET_LVL_M GENMASK(1, 0) /* Write reply only */ +#define IXGBE_ACI_NVM_POR_FLAG 0 +#define IXGBE_ACI_NVM_PERST_FLAG 1 +#define IXGBE_ACI_NVM_EMPR_FLAG 2 +#define IXGBE_ACI_NVM_EMPR_ENA BIT(0) /* Write Activate reply only */ +#define IXGBE_ACI_NVM_NO_PRESERVATION 0x0 +#define IXGBE_ACI_NVM_PRESERVE_SELECTED 0x6 + + /* For Write Activate, several flags are sent as part of a separate + * flags2 field using a separate byte. For simplicity of the software + * interface, we pass the flags as a 16 bit value so these flags are + * all offset by 8 bits + */ +#define IXGBE_ACI_NVM_ACTIV_REQ_EMPR BIT(8) /* NVM Write Activate only */ + __le16 module_typeid; + __le16 length; +#define IXGBE_ACI_NVM_ERASE_LEN 0xFFFF + __le32 addr_high; + __le32 addr_low; +}; + +/* NVM Module_Type ID, needed offset and read_len for + * struct ixgbe_aci_cmd_nvm. + */ +#define IXGBE_ACI_NVM_START_POINT 0 + +/* NVM Checksum Command (direct, 0x0706) */ +struct ixgbe_aci_cmd_nvm_checksum { + u8 flags; +#define IXGBE_ACI_NVM_CHECKSUM_VERIFY BIT(0) +#define IXGBE_ACI_NVM_CHECKSUM_RECALC BIT(1) + u8 rsvd; + __le16 checksum; /* Used only by response */ +#define IXGBE_ACI_NVM_CHECKSUM_CORRECT 0xBABA + u8 rsvd2[12]; +}; + +/* Used for NVM Set Package Data command - 0x070A */ +struct ixgbe_aci_cmd_nvm_pkg_data { + u8 reserved[3]; + u8 cmd_flags; +#define IXGBE_ACI_NVM_PKG_DELETE BIT(0) /* used for command call */ + + u32 reserved1; + __le32 addr_high; + __le32 addr_low; +}; + +/* Used for Pass Component Table command - 0x070B */ +struct ixgbe_aci_cmd_nvm_pass_comp_tbl { + u8 component_response; /* Response only */ +#define IXGBE_ACI_NVM_PASS_COMP_CAN_BE_UPDATED 0x0 +#define IXGBE_ACI_NVM_PASS_COMP_CAN_MAY_BE_UPDATEABLE 0x1 +#define IXGBE_ACI_NVM_PASS_COMP_CAN_NOT_BE_UPDATED 0x2 +#define IXGBE_ACI_NVM_PASS_COMP_PARTIAL_CHECK 0x3 + u8 component_response_code; /* Response only */ +#define IXGBE_ACI_NVM_PASS_COMP_CAN_BE_UPDATED_CODE 0x0 +#define IXGBE_ACI_NVM_PASS_COMP_STAMP_IDENTICAL_CODE 0x1 +#define IXGBE_ACI_NVM_PASS_COMP_STAMP_LOWER 0x2 +#define IXGBE_ACI_NVM_PASS_COMP_INVALID_STAMP_CODE 0x3 +#define IXGBE_ACI_NVM_PASS_COMP_CONFLICT_CODE 0x4 +#define IXGBE_ACI_NVM_PASS_COMP_PRE_REQ_NOT_MET_CODE 0x5 +#define IXGBE_ACI_NVM_PASS_COMP_NOT_SUPPORTED_CODE 0x6 +#define IXGBE_ACI_NVM_PASS_COMP_CANNOT_DOWNGRADE_CODE 0x7 +#define IXGBE_ACI_NVM_PASS_COMP_INCOMPLETE_IMAGE_CODE 0x8 +#define IXGBE_ACI_NVM_PASS_COMP_VER_STR_IDENTICAL_CODE 0xA +#define IXGBE_ACI_NVM_PASS_COMP_VER_STR_LOWER_CODE 0xB + u8 reserved; + u8 transfer_flag; + __le32 reserved1; + __le32 addr_high; + __le32 addr_low; +}; + +struct ixgbe_aci_cmd_nvm_comp_tbl { + __le16 comp_class; +#define NVM_COMP_CLASS_ALL_FW 0x000A + + __le16 comp_id; +#define NVM_COMP_ID_OROM 0x5 +#define NVM_COMP_ID_NVM 0x6 +#define NVM_COMP_ID_NETLIST 0x8 + + u8 comp_class_idx; +#define FWU_COMP_CLASS_IDX_NOT_USE 0x0 + + __le32 comp_cmp_stamp; + u8 cvs_type; +#define NVM_CVS_TYPE_ASCII 0x1 + + u8 cvs_len; + u8 cvs[]; /* Component Version String */ +} __packed; + +/** + * struct ixgbe_aci_desc - Admin Command (AC) descriptor + * @flags: IXGBE_ACI_FLAG_* flags + * @opcode: Admin command opcode + * @datalen: length in bytes of indirect/external data buffer + * @retval: return value from firmware + * @cookie_high: opaque data high-half + * @cookie_low: opaque data low-half + * @params: command-specific parameters + * + * Descriptor format for commands the driver posts via the + * Admin Command Interface (ACI). + * The firmware writes back onto the command descriptor and returns + * the result of the command. Asynchronous events that are not an immediate + * result of the command are written to the Admin Command Interface (ACI) using + * the same descriptor format. Descriptors are in little-endian notation with + * 32-bit words. + */ +struct ixgbe_aci_desc { + __le16 flags; + __le16 opcode; + __le16 datalen; + __le16 retval; + __le32 cookie_high; + __le32 cookie_low; + union { + u8 raw[16]; + struct ixgbe_aci_cmd_get_ver get_ver; + struct ixgbe_aci_cmd_driver_ver driver_ver; + struct ixgbe_aci_cmd_get_exp_err exp_err; + struct ixgbe_aci_cmd_req_res res_owner; + struct ixgbe_aci_cmd_list_caps get_cap; + struct ixgbe_aci_cmd_disable_rxen disable_rxen; + struct ixgbe_aci_cmd_get_phy_caps get_phy; + struct ixgbe_aci_cmd_set_phy_cfg set_phy; + struct ixgbe_aci_cmd_restart_an restart_an; + struct ixgbe_aci_cmd_get_link_status get_link_status; + struct ixgbe_aci_cmd_set_event_mask set_event_mask; + struct ixgbe_aci_cmd_set_port_id_led set_port_id_led; + struct ixgbe_aci_cmd_get_link_topo get_link_topo; + struct ixgbe_aci_cmd_get_link_topo_pin get_link_topo_pin; + struct ixgbe_aci_cmd_sff_eeprom read_write_sff_param; + struct ixgbe_aci_cmd_nvm nvm; + struct ixgbe_aci_cmd_nvm_checksum nvm_checksum; + struct ixgbe_aci_cmd_nvm_pkg_data pkg_data; + struct ixgbe_aci_cmd_nvm_pass_comp_tbl pass_comp_tbl; + } params; +}; + +/* E610-specific adapter context structures */ + +struct ixgbe_link_status { + /* Refer to ixgbe_aci_phy_type for bits definition */ + u64 phy_type_low; + u64 phy_type_high; + u16 max_frame_size; + u16 link_speed; + u16 req_speeds; + u8 topo_media_conflict; + u8 link_cfg_err; + u8 lse_ena; /* Link Status Event notification */ + u8 link_info; + u8 an_info; + u8 ext_info; + u8 fec_info; + u8 pacing; + /* Refer to #define from module_type[IXGBE_ACI_MODULE_TYPE_TOTAL_BYTE] + * of ixgbe_aci_get_phy_caps structure + */ + u8 module_type[IXGBE_ACI_MODULE_TYPE_TOTAL_BYTE]; +}; + +/* Common HW capabilities for SW use */ +struct ixgbe_hw_caps { + /* Write CSR protection */ + u64 wr_csr_prot; + u32 switching_mode; + /* switching mode supported - EVB switching (including cloud) */ +#define IXGBE_NVM_IMAGE_TYPE_EVB 0x0 + + /* Manageability mode & supported protocols over MCTP */ + u32 mgmt_mode; +#define IXGBE_MGMT_MODE_PASS_THRU_MODE_M GENMASK(3, 0) +#define IXGBE_MGMT_MODE_CTL_INTERFACE_M GENMASK(7, 4) +#define IXGBE_MGMT_MODE_REDIR_SB_INTERFACE_M GENMASK(11, 8) + + u32 mgmt_protocols_mctp; +#define IXGBE_MGMT_MODE_PROTO_RSVD BIT(0) +#define IXGBE_MGMT_MODE_PROTO_PLDM BIT(1) +#define IXGBE_MGMT_MODE_PROTO_OEM BIT(2) +#define IXGBE_MGMT_MODE_PROTO_NC_SI BIT(3) + + u32 os2bmc; + u32 valid_functions; + /* DCB capabilities */ + u32 active_tc_bitmap; + u32 maxtc; + + /* RSS related capabilities */ + u32 rss_table_size; /* 512 for PFs and 64 for VFs */ + u32 rss_table_entry_width; /* RSS Entry width in bits */ + + /* Tx/Rx queues */ + u32 num_rxq; /* Number/Total Rx queues */ + u32 rxq_first_id; /* First queue ID for Rx queues */ + u32 num_txq; /* Number/Total Tx queues */ + u32 txq_first_id; /* First queue ID for Tx queues */ + + /* MSI-X vectors */ + u32 num_msix_vectors; + u32 msix_vector_first_id; + + /* Max MTU for function or device */ + u32 max_mtu; + + /* WOL related */ + u32 num_wol_proxy_fltr; + u32 wol_proxy_vsi_seid; + + /* LED/SDP pin count */ + u32 led_pin_num; + u32 sdp_pin_num; + + /* LED/SDP - Supports up to 12 LED pins and 8 SDP signals */ +#define IXGBE_MAX_SUPPORTED_GPIO_LED 12 +#define IXGBE_MAX_SUPPORTED_GPIO_SDP 8 + u8 led[IXGBE_MAX_SUPPORTED_GPIO_LED]; + u8 sdp[IXGBE_MAX_SUPPORTED_GPIO_SDP]; + /* SR-IOV virtualization */ + u8 sr_iov_1_1; /* SR-IOV enabled */ + /* VMDQ */ + u8 vmdq; /* VMDQ supported */ + + /* EVB capabilities */ + u8 evb_802_1_qbg; /* Edge Virtual Bridging */ + u8 evb_802_1_qbh; /* Bridge Port Extension */ + + u8 dcb; + u8 iscsi; + u8 ieee_1588; + u8 mgmt_cem; + + /* WoL and APM support */ +#define IXGBE_WOL_SUPPORT_M BIT(0) +#define IXGBE_ACPI_PROG_MTHD_M BIT(1) +#define IXGBE_PROXY_SUPPORT_M BIT(2) + u8 apm_wol_support; + u8 acpi_prog_mthd; + u8 proxy_support; + bool nvm_update_pending_nvm; + bool nvm_update_pending_orom; + bool nvm_update_pending_netlist; +#define IXGBE_NVM_PENDING_NVM_IMAGE BIT(0) +#define IXGBE_NVM_PENDING_OROM BIT(1) +#define IXGBE_NVM_PENDING_NETLIST BIT(2) + bool sec_rev_disabled; + bool update_disabled; + bool nvm_unified_update; + bool netlist_auth; +#define IXGBE_NVM_MGMT_SEC_REV_DISABLED BIT(0) +#define IXGBE_NVM_MGMT_UPDATE_DISABLED BIT(1) +#define IXGBE_NVM_MGMT_UNIFIED_UPD_SUPPORT BIT(3) +#define IXGBE_NVM_MGMT_NETLIST_AUTH_SUPPORT BIT(5) + bool no_drop_policy_support; + /* PCIe reset avoidance */ + bool pcie_reset_avoidance; /* false: not supported, true: supported */ + /* Post update reset restriction */ + bool reset_restrict_support; /* false: not supported, true: supported */ + + /* External topology device images within the NVM */ +#define IXGBE_EXT_TOPO_DEV_IMG_COUNT 4 + u32 ext_topo_dev_img_ver_high[IXGBE_EXT_TOPO_DEV_IMG_COUNT]; + u32 ext_topo_dev_img_ver_low[IXGBE_EXT_TOPO_DEV_IMG_COUNT]; + u8 ext_topo_dev_img_part_num[IXGBE_EXT_TOPO_DEV_IMG_COUNT]; +#define IXGBE_EXT_TOPO_DEV_IMG_PART_NUM_S 8 +#define IXGBE_EXT_TOPO_DEV_IMG_PART_NUM_M GENMASK(15, 8) + bool ext_topo_dev_img_load_en[IXGBE_EXT_TOPO_DEV_IMG_COUNT]; +#define IXGBE_EXT_TOPO_DEV_IMG_LOAD_EN BIT(0) + bool ext_topo_dev_img_prog_en[IXGBE_EXT_TOPO_DEV_IMG_COUNT]; +#define IXGBE_EXT_TOPO_DEV_IMG_PROG_EN BIT(1) +} __packed; + +#define IXGBE_OROM_CIV_SIGNATURE "$CIV" + +struct ixgbe_orom_civd_info { + u8 signature[4]; /* Must match ASCII '$CIV' characters */ + u8 checksum; /* Simple modulo 256 sum of all structure bytes must equal 0 */ + __le32 combo_ver; /* Combo Image Version number */ + u8 combo_name_len; /* Length of the unicode combo image version string, max of 32 */ + __le16 combo_name[32]; /* Unicode string representing the Combo Image version */ +}; + +/* Function specific capabilities */ +struct ixgbe_hw_func_caps { + u32 num_allocd_vfs; /* Number of allocated VFs */ + u32 vf_base_id; /* Logical ID of the first VF */ + u32 guar_num_vsi; + struct ixgbe_hw_caps common_cap; + bool no_drop_policy_ena; +}; + +/* Device wide capabilities */ +struct ixgbe_hw_dev_caps { + struct ixgbe_hw_caps common_cap; + u32 num_vfs_exposed; /* Total number of VFs exposed */ + u32 num_vsi_allocd_to_host; /* Excluding EMP VSI */ + u32 num_flow_director_fltr; /* Number of FD filters available */ + u32 num_funcs; +}; + +/* ACI event information */ +struct ixgbe_aci_event { + struct ixgbe_aci_desc desc; + u8 *msg_buf; + u16 msg_len; + u16 buf_len; +}; + +struct ixgbe_aci_info { + struct mutex lock; /* admin command interface lock */ + enum ixgbe_aci_err last_status; /* last status of sent admin command */ +}; + +enum ixgbe_bank_select { + IXGBE_ACTIVE_FLASH_BANK, + IXGBE_INACTIVE_FLASH_BANK, +}; + +/* Option ROM version information */ +struct ixgbe_orom_info { + u8 major; /* Major version of OROM */ + u8 patch; /* Patch version of OROM */ + u16 build; /* Build version of OROM */ + u32 srev; /* Security revision */ +}; + +/* NVM version information */ +struct ixgbe_nvm_info { + u32 eetrack; + u32 srev; + u8 major; + u8 minor; +} __packed; + +/* netlist version information */ +struct ixgbe_netlist_info { + u32 major; /* major high/low */ + u32 minor; /* minor high/low */ + u32 type; /* type high/low */ + u32 rev; /* revision high/low */ + u32 hash; /* SHA-1 hash word */ + u16 cust_ver; /* customer version */ +} __packed; + +/* Enumeration of possible flash banks for the NVM, OROM, and Netlist modules + * of the flash image. + */ +enum ixgbe_flash_bank { + IXGBE_INVALID_FLASH_BANK, + IXGBE_1ST_FLASH_BANK, + IXGBE_2ND_FLASH_BANK, +}; + +/* information for accessing NVM, OROM, and Netlist flash banks */ +struct ixgbe_bank_info { + u32 nvm_ptr; /* Pointer to 1st NVM bank */ + u32 nvm_size; /* Size of NVM bank */ + u32 orom_ptr; /* Pointer to 1st OROM bank */ + u32 orom_size; /* Size of OROM bank */ + u32 netlist_ptr; /* Ptr to 1st Netlist bank */ + u32 netlist_size; /* Size of Netlist bank */ + enum ixgbe_flash_bank nvm_bank; /* Active NVM bank */ + enum ixgbe_flash_bank orom_bank; /* Active OROM bank */ + enum ixgbe_flash_bank netlist_bank; /* Active Netlist bank */ +}; + +/* Flash Chip Information */ +struct ixgbe_flash_info { + struct ixgbe_orom_info orom; /* Option ROM version info */ + u32 flash_size; /* Available flash size in bytes */ + struct ixgbe_nvm_info nvm; /* NVM version information */ + struct ixgbe_netlist_info netlist; /* Netlist version info */ + struct ixgbe_bank_info banks; /* Flash Bank information */ + u16 sr_words; /* Shadow RAM size in words */ + u8 blank_nvm_mode; /* is NVM empty (no FW present) */ +}; + +#endif /* _IXGBE_TYPE_E610_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c index f1ffa398f6df..f1ab95aa8c83 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c @@ -1,11 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #include <linux/pci.h> #include <linux/delay.h> #include <linux/sched.h> #include "ixgbe.h" +#include "ixgbe_mbx.h" #include "ixgbe_phy.h" #include "ixgbe_x540.h" @@ -65,7 +66,9 @@ int ixgbe_setup_mac_link_X540(struct ixgbe_hw *hw, ixgbe_link_speed speed, * Resets the hardware by resetting the transmit and receive units, masks * and clears all interrupts, perform a PHY reset, and perform a link (MAC) * reset. - **/ + * + * Return: 0 on success or negative value on failure + */ int ixgbe_reset_hw_X540(struct ixgbe_hw *hw) { u32 swfw_mask = hw->phy.phy_semaphore_mask; @@ -132,10 +135,14 @@ mac_reset_top: hw->mac.num_rar_entries = IXGBE_X540_MAX_TX_QUEUES; hw->mac.ops.init_rx_addrs(hw); + /* The following is not supported by E610. */ + if (hw->mac.type == ixgbe_mac_e610) + return status; + /* Store the permanent SAN mac address */ hw->mac.ops.get_san_mac_addr(hw, hw->mac.san_addr); - /* Add the SAN MAC address to the RAR only if it's a valid address */ + /* Add the SAN MAC address to RAR if it's a valid address */ if (is_valid_ether_addr(hw->mac.san_addr)) { /* Save the SAN MAC RAR index */ hw->mac.san_mac_rar_index = hw->mac.num_rar_entries - 1; @@ -887,6 +894,7 @@ static const struct ixgbe_eeprom_operations eeprom_ops_X540 = { .calc_checksum = &ixgbe_calc_eeprom_checksum_X540, .validate_checksum = &ixgbe_validate_eeprom_checksum_X540, .update_checksum = &ixgbe_update_eeprom_checksum_X540, + .read_pba_string = &ixgbe_read_pba_string_generic, }; static const struct ixgbe_phy_operations phy_ops_X540 = { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.h index b69a680d3ab5..6ed360c5b605 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.h @@ -1,5 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ + +#ifndef _IXGBE_X540_H_ +#define _IXGBE_X540_H_ #include "ixgbe_type.h" @@ -17,3 +20,5 @@ int ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask); void ixgbe_release_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask); void ixgbe_init_swfw_sync_X540(struct ixgbe_hw *hw); int ixgbe_init_eeprom_params_X540(struct ixgbe_hw *hw); + +#endif /* _IXGBE_X540_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 2decb0710b6e..1d2acdb64f45 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -1,9 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #include "ixgbe_x540.h" +#include "ixgbe_x550.h" #include "ixgbe_type.h" #include "ixgbe_common.h" +#include "ixgbe_mbx.h" #include "ixgbe_phy.h" static int ixgbe_setup_kr_speed_x550em(struct ixgbe_hw *, ixgbe_link_speed); @@ -1722,59 +1724,9 @@ static int ixgbe_setup_sfi_x550a(struct ixgbe_hw *hw, ixgbe_link_speed *speed) return -EINVAL; } - (void)mac->ops.write_iosf_sb_reg(hw, - IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); - - /* change mode enforcement rules to hybrid */ - (void)mac->ops.read_iosf_sb_reg(hw, - IXGBE_KRM_FLX_TMRS_CTRL_ST31(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val); - reg_val |= 0x0400; - - (void)mac->ops.write_iosf_sb_reg(hw, - IXGBE_KRM_FLX_TMRS_CTRL_ST31(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); - - /* manually control the config */ - (void)mac->ops.read_iosf_sb_reg(hw, - IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val); - reg_val |= 0x20002240; - - (void)mac->ops.write_iosf_sb_reg(hw, - IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); - - /* move the AN base page values */ - (void)mac->ops.read_iosf_sb_reg(hw, - IXGBE_KRM_PCS_KX_AN(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val); - reg_val |= 0x1; - - (void)mac->ops.write_iosf_sb_reg(hw, - IXGBE_KRM_PCS_KX_AN(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); - - /* set the AN37 over CB mode */ - (void)mac->ops.read_iosf_sb_reg(hw, - IXGBE_KRM_AN_CNTL_4(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val); - reg_val |= 0x20000000; - - (void)mac->ops.write_iosf_sb_reg(hw, - IXGBE_KRM_AN_CNTL_4(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); - - /* restart AN manually */ - (void)mac->ops.read_iosf_sb_reg(hw, - IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val); - reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_RESTART; - - (void)mac->ops.write_iosf_sb_reg(hw, - IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); + status = mac->ops.write_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); /* Toggle port SW reset by AN reset. */ status = ixgbe_restart_an_internal_phy_x550em(hw); @@ -2819,9 +2771,9 @@ static int ixgbe_led_off_t_x550em(struct ixgbe_hw *hw, u32 led_idx) * semaphore, -EIO when command fails or -ENIVAL when incorrect * params passed. **/ -static int ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min, - u8 build, u8 sub, u16 len, - const char *driver_ver) +int ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min, + u8 build, u8 sub, u16 len, + const char *driver_ver) { struct ixgbe_hic_drv_info2 fw_cmd; int ret_val; @@ -3554,14 +3506,14 @@ mac_reset_top: return status; } -/** ixgbe_set_ethertype_anti_spoofing_X550 - Enable/Disable Ethertype +/** ixgbe_set_ethertype_anti_spoofing_x550 - Enable/Disable Ethertype * anti-spoofing * @hw: pointer to hardware structure * @enable: enable or disable switch for Ethertype anti-spoofing * @vf: Virtual Function pool - VF Pool to set for Ethertype anti-spoofing **/ -static void ixgbe_set_ethertype_anti_spoofing_X550(struct ixgbe_hw *hw, - bool enable, int vf) +void ixgbe_set_ethertype_anti_spoofing_x550(struct ixgbe_hw *hw, + bool enable, int vf) { int vf_target_reg = vf >> 3; int vf_target_shift = vf % 8 + IXGBE_SPOOF_ETHERTYPEAS_SHIFT; @@ -3576,14 +3528,14 @@ static void ixgbe_set_ethertype_anti_spoofing_X550(struct ixgbe_hw *hw, IXGBE_WRITE_REG(hw, IXGBE_PFVFSPOOF(vf_target_reg), pfvfspoof); } -/** ixgbe_set_source_address_pruning_X550 - Enable/Disbale src address pruning +/** ixgbe_set_source_address_pruning_x550 - Enable/Disable src address pruning * @hw: pointer to hardware structure * @enable: enable or disable source address pruning * @pool: Rx pool to set source address pruning for **/ -static void ixgbe_set_source_address_pruning_X550(struct ixgbe_hw *hw, - bool enable, - unsigned int pool) +void ixgbe_set_source_address_pruning_x550(struct ixgbe_hw *hw, + bool enable, + unsigned int pool) { u64 pfflp; @@ -3880,9 +3832,9 @@ static int ixgbe_write_phy_reg_x550a(struct ixgbe_hw *hw, u32 reg_addr, .set_mac_anti_spoofing = &ixgbe_set_mac_anti_spoofing, \ .set_vlan_anti_spoofing = &ixgbe_set_vlan_anti_spoofing, \ .set_source_address_pruning = \ - &ixgbe_set_source_address_pruning_X550, \ + &ixgbe_set_source_address_pruning_x550, \ .set_ethertype_anti_spoofing = \ - &ixgbe_set_ethertype_anti_spoofing_X550, \ + &ixgbe_set_ethertype_anti_spoofing_x550, \ .disable_rx_buff = &ixgbe_disable_rx_buff_generic, \ .enable_rx_buff = &ixgbe_enable_rx_buff_generic, \ .get_thermal_sensor_data = NULL, \ @@ -4007,6 +3959,7 @@ static const struct ixgbe_mac_operations mac_ops_x550em_a_fw = { .validate_checksum = &ixgbe_validate_eeprom_checksum_X550, \ .update_checksum = &ixgbe_update_eeprom_checksum_X550, \ .calc_checksum = &ixgbe_calc_eeprom_checksum_X550, \ + .read_pba_string = &ixgbe_read_pba_string_generic, \ static const struct ixgbe_eeprom_operations eeprom_ops_X550 = { X550_COMMON_EEP @@ -4096,7 +4049,7 @@ static const u32 ixgbe_mvals_X550EM_x[IXGBE_MVALS_IDX_LIMIT] = { IXGBE_MVALS_INIT(X550EM_x) }; -static const u32 ixgbe_mvals_x550em_a[IXGBE_MVALS_IDX_LIMIT] = { +const u32 ixgbe_mvals_x550em_a[IXGBE_MVALS_IDX_LIMIT] = { IXGBE_MVALS_INIT(X550EM_a) }; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.h new file mode 100644 index 000000000000..3e4092f8da3e --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2024 Intel Corporation. */ + +#ifndef _IXGBE_X550_H_ +#define _IXGBE_X550_H_ + +#include "ixgbe_type.h" + +extern const u32 ixgbe_mvals_x550em_a[IXGBE_MVALS_IDX_LIMIT]; + +int ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min, + u8 build, u8 sub, u16 len, + const char *driver_ver); +void ixgbe_set_source_address_pruning_x550(struct ixgbe_hw *hw, + bool enable, + unsigned int pool); +void ixgbe_set_ethertype_anti_spoofing_x550(struct ixgbe_hw *hw, + bool enable, int vf); + +#endif /* _IXGBE_X550_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index d34d715c59eb..ac58964b2f08 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -220,8 +220,7 @@ static struct sk_buff *ixgbe_construct_skb_zc(struct ixgbe_ring *rx_ring, net_prefetch(xdp->data_meta); /* allocate a skb to store the frags */ - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize, - GFP_ATOMIC | __GFP_NOWARN); + skb = napi_alloc_skb(&rx_ring->q_vector->napi, totalsize); if (unlikely(!skb)) return NULL; @@ -304,7 +303,7 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, } bi->xdp->data_end = bi->xdp->data + size; - xsk_buff_dma_sync_for_cpu(bi->xdp, rx_ring->xsk_pool); + xsk_buff_dma_sync_for_cpu(bi->xdp); xdp_res = ixgbe_run_xdp_zc(adapter, rx_ring, bi->xdp); if (likely(xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR))) { @@ -509,7 +508,7 @@ bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector, int ixgbe_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct ixgbe_ring *ring; if (test_bit(__IXGBE_DOWN, &adapter->state)) diff --git a/drivers/net/ethernet/intel/ixgbevf/Makefile b/drivers/net/ethernet/intel/ixgbevf/Makefile index 186a4bb24fde..01d3e892f3fa 100644 --- a/drivers/net/ethernet/intel/ixgbevf/Makefile +++ b/drivers/net/ethernet/intel/ixgbevf/Makefile @@ -6,9 +6,5 @@ obj-$(CONFIG_IXGBEVF) += ixgbevf.o -ixgbevf-objs := vf.o \ - mbx.o \ - ethtool.o \ - ixgbevf_main.o +ixgbevf-y := vf.o mbx.o ethtool.o ixgbevf_main.o ixgbevf-$(CONFIG_IXGBEVF_IPSEC) += ipsec.o - diff --git a/drivers/net/ethernet/intel/ixgbevf/defines.h b/drivers/net/ethernet/intel/ixgbevf/defines.h index 5f08779c0e4e..a9bc96f6399d 100644 --- a/drivers/net/ethernet/intel/ixgbevf/defines.h +++ b/drivers/net/ethernet/intel/ixgbevf/defines.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #ifndef _IXGBEVF_DEFINES_H_ #define _IXGBEVF_DEFINES_H_ @@ -16,6 +16,9 @@ #define IXGBE_DEV_ID_X550_VF_HV 0x1564 #define IXGBE_DEV_ID_X550EM_X_VF_HV 0x15A9 +#define IXGBE_DEV_ID_E610_VF 0x57AD +#define IXGBE_SUBDEV_ID_E610_VF_HV 0x00FF + #define IXGBE_VF_IRQ_CLEAR_MASK 7 #define IXGBE_VF_MAX_TX_QUEUES 8 #define IXGBE_VF_MAX_RX_QUEUES 8 diff --git a/drivers/net/ethernet/intel/ixgbevf/ipsec.c b/drivers/net/ethernet/intel/ixgbevf/ipsec.c index 66cf17f19408..65580b9cb06f 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ipsec.c +++ b/drivers/net/ethernet/intel/ixgbevf/ipsec.c @@ -201,6 +201,7 @@ struct xfrm_state *ixgbevf_ipsec_find_rx_state(struct ixgbevf_ipsec *ipsec, /** * ixgbevf_ipsec_parse_proto_keys - find the key and salt based on the protocol + * @dev: pointer to net device to program * @xs: pointer to xfrm_state struct * @mykey: pointer to key array to populate * @mysalt: pointer to salt value to populate @@ -208,10 +209,10 @@ struct xfrm_state *ixgbevf_ipsec_find_rx_state(struct ixgbevf_ipsec *ipsec, * This copies the protocol keys and salt to our own data tables. The * 82599 family only supports the one algorithm. **/ -static int ixgbevf_ipsec_parse_proto_keys(struct xfrm_state *xs, +static int ixgbevf_ipsec_parse_proto_keys(struct net_device *dev, + struct xfrm_state *xs, u32 *mykey, u32 *mysalt) { - struct net_device *dev = xs->xso.real_dev; unsigned char *key_data; char *alg_name = NULL; int key_len; @@ -256,13 +257,14 @@ static int ixgbevf_ipsec_parse_proto_keys(struct xfrm_state *xs, /** * ixgbevf_ipsec_add_sa - program device with a security association + * @dev: pointer to net device to program * @xs: pointer to transformer state struct * @extack: extack point to fill failure reason **/ -static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs, +static int ixgbevf_ipsec_add_sa(struct net_device *dev, + struct xfrm_state *xs, struct netlink_ext_ack *extack) { - struct net_device *dev = xs->xso.real_dev; struct ixgbevf_adapter *adapter; struct ixgbevf_ipsec *ipsec; u16 sa_idx; @@ -310,7 +312,8 @@ static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs, rsa.decrypt = xs->ealg || xs->aead; /* get the key and salt */ - ret = ixgbevf_ipsec_parse_proto_keys(xs, rsa.key, &rsa.salt); + ret = ixgbevf_ipsec_parse_proto_keys(dev, xs, rsa.key, + &rsa.salt); if (ret) { NL_SET_ERR_MSG_MOD(extack, "Failed to get key data for Rx SA table"); return ret; @@ -363,7 +366,8 @@ static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs, if (xs->id.proto & IPPROTO_ESP) tsa.encrypt = xs->ealg || xs->aead; - ret = ixgbevf_ipsec_parse_proto_keys(xs, tsa.key, &tsa.salt); + ret = ixgbevf_ipsec_parse_proto_keys(dev, xs, tsa.key, + &tsa.salt); if (ret) { NL_SET_ERR_MSG_MOD(extack, "Failed to get key data for Tx SA table"); memset(&tsa, 0, sizeof(tsa)); @@ -388,11 +392,12 @@ static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs, /** * ixgbevf_ipsec_del_sa - clear out this specific SA + * @dev: pointer to net device to program * @xs: pointer to transformer state struct **/ -static void ixgbevf_ipsec_del_sa(struct xfrm_state *xs) +static void ixgbevf_ipsec_del_sa(struct net_device *dev, + struct xfrm_state *xs) { - struct net_device *dev = xs->xso.real_dev; struct ixgbevf_adapter *adapter; struct ixgbevf_ipsec *ipsec; u16 sa_idx; @@ -428,30 +433,9 @@ static void ixgbevf_ipsec_del_sa(struct xfrm_state *xs) } } -/** - * ixgbevf_ipsec_offload_ok - can this packet use the xfrm hw offload - * @skb: current data packet - * @xs: pointer to transformer state struct - **/ -static bool ixgbevf_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) -{ - if (xs->props.family == AF_INET) { - /* Offload with IPv4 options is not supported yet */ - if (ip_hdr(skb)->ihl != 5) - return false; - } else { - /* Offload with IPv6 extension headers is not support yet */ - if (ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr)) - return false; - } - - return true; -} - static const struct xfrmdev_ops ixgbevf_xfrmdev_ops = { .xdo_dev_state_add = ixgbevf_ipsec_add_sa, .xdo_dev_state_delete = ixgbevf_ipsec_del_sa, - .xdo_dev_offload_ok = ixgbevf_ipsec_offload_ok, }; /** @@ -629,7 +613,6 @@ void ixgbevf_init_ipsec_offload(struct ixgbevf_adapter *adapter) switch (adapter->hw.api_version) { case ixgbe_mbox_api_14: - case ixgbe_mbox_api_15: break; default: return; diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h index 130cb868774c..4384e892f967 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #ifndef _IXGBEVF_H_ #define _IXGBEVF_H_ @@ -418,6 +418,8 @@ enum ixgbevf_boards { board_X550EM_x_vf, board_X550EM_x_vf_hv, board_x550em_a_vf, + board_e610_vf, + board_e610_vf_hv, }; enum ixgbevf_xcast_modes { @@ -434,12 +436,13 @@ extern const struct ixgbevf_info ixgbevf_X550EM_x_vf_info; extern const struct ixgbe_mbx_operations ixgbevf_mbx_ops; extern const struct ixgbe_mbx_operations ixgbevf_mbx_ops_legacy; extern const struct ixgbevf_info ixgbevf_x550em_a_vf_info; +extern const struct ixgbevf_info ixgbevf_e610_vf_info; extern const struct ixgbevf_info ixgbevf_82599_vf_hv_info; extern const struct ixgbevf_info ixgbevf_X540_vf_hv_info; extern const struct ixgbevf_info ixgbevf_X550_vf_hv_info; extern const struct ixgbevf_info ixgbevf_X550EM_x_vf_hv_info; -extern const struct ixgbe_mbx_operations ixgbevf_hv_mbx_ops; +extern const struct ixgbevf_info ixgbevf_e610_vf_hv_info; /* needed by ethtool.c */ extern const char ixgbevf_driver_name[]; diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 9c960017a6de..a217c5c04804 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ /****************************************************************************** Copyright (c)2006 - 2007 Myricom, Inc. for some LRO specific code @@ -39,7 +39,7 @@ static const char ixgbevf_driver_string[] = "Intel(R) 10 Gigabit PCI Express Virtual Function Network Driver"; static char ixgbevf_copyright[] = - "Copyright (c) 2009 - 2018 Intel Corporation."; + "Copyright (c) 2009 - 2024 Intel Corporation."; static const struct ixgbevf_info *ixgbevf_info_tbl[] = { [board_82599_vf] = &ixgbevf_82599_vf_info, @@ -51,6 +51,8 @@ static const struct ixgbevf_info *ixgbevf_info_tbl[] = { [board_X550EM_x_vf] = &ixgbevf_X550EM_x_vf_info, [board_X550EM_x_vf_hv] = &ixgbevf_X550EM_x_vf_hv_info, [board_x550em_a_vf] = &ixgbevf_x550em_a_vf_info, + [board_e610_vf] = &ixgbevf_e610_vf_info, + [board_e610_vf_hv] = &ixgbevf_e610_vf_hv_info, }; /* ixgbevf_pci_tbl - PCI Device ID Table @@ -71,12 +73,14 @@ static const struct pci_device_id ixgbevf_pci_tbl[] = { {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_VF), board_X550EM_x_vf }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_VF_HV), board_X550EM_x_vf_hv}, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_VF), board_x550em_a_vf }, + {PCI_VDEVICE_SUB(INTEL, IXGBE_DEV_ID_E610_VF, PCI_ANY_ID, + IXGBE_SUBDEV_ID_E610_VF_HV), board_e610_vf_hv}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_VF), board_e610_vf}, /* required last entry */ {0, } }; MODULE_DEVICE_TABLE(pci, ixgbevf_pci_tbl); -MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION("Intel(R) 10 Gigabit Virtual Function Network Driver"); MODULE_LICENSE("GPL v2"); @@ -733,10 +737,6 @@ static bool ixgbevf_cleanup_headers(struct ixgbevf_ring *rx_ring, union ixgbe_adv_rx_desc *rx_desc, struct sk_buff *skb) { - /* XDP packets use error pointer so abort at this point */ - if (IS_ERR(skb)) - return true; - /* verify that the packet does not have any known errors */ if (unlikely(ixgbevf_test_staterr(rx_desc, IXGBE_RXDADV_ERR_FRAME_ERR_MASK))) { @@ -1045,9 +1045,9 @@ static int ixgbevf_xmit_xdp_ring(struct ixgbevf_ring *ring, return IXGBEVF_XDP_TX; } -static struct sk_buff *ixgbevf_run_xdp(struct ixgbevf_adapter *adapter, - struct ixgbevf_ring *rx_ring, - struct xdp_buff *xdp) +static int ixgbevf_run_xdp(struct ixgbevf_adapter *adapter, + struct ixgbevf_ring *rx_ring, + struct xdp_buff *xdp) { int result = IXGBEVF_XDP_PASS; struct ixgbevf_ring *xdp_ring; @@ -1081,7 +1081,7 @@ out_failure: break; } xdp_out: - return ERR_PTR(-result); + return result; } static unsigned int ixgbevf_rx_frame_truesize(struct ixgbevf_ring *rx_ring, @@ -1123,6 +1123,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, struct sk_buff *skb = rx_ring->skb; bool xdp_xmit = false; struct xdp_buff xdp; + int xdp_res = 0; /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ #if (PAGE_SIZE < 8192) @@ -1166,11 +1167,11 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, /* At larger PAGE_SIZE, frame_sz depend on len size */ xdp.frame_sz = ixgbevf_rx_frame_truesize(rx_ring, size); #endif - skb = ixgbevf_run_xdp(adapter, rx_ring, &xdp); + xdp_res = ixgbevf_run_xdp(adapter, rx_ring, &xdp); } - if (IS_ERR(skb)) { - if (PTR_ERR(skb) == -IXGBEVF_XDP_TX) { + if (xdp_res) { + if (xdp_res == IXGBEVF_XDP_TX) { xdp_xmit = true; ixgbevf_rx_buffer_flip(rx_ring, rx_buffer, size); @@ -1190,7 +1191,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, } /* exit if we failed to retrieve a buffer */ - if (!skb) { + if (!xdp_res && !skb) { rx_ring->rx_stats.alloc_rx_buff_failed++; rx_buffer->pagecnt_bias++; break; @@ -1204,7 +1205,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, continue; /* verify the packet layout is correct */ - if (ixgbevf_cleanup_headers(rx_ring, rx_desc, skb)) { + if (xdp_res || ixgbevf_cleanup_headers(rx_ring, rx_desc, skb)) { skb = NULL; continue; } @@ -2513,7 +2514,7 @@ void ixgbevf_down(struct ixgbevf_adapter *adapter) ixgbevf_napi_disable_all(adapter); - del_timer_sync(&adapter->service_timer); + timer_delete_sync(&adapter->service_timer); /* disable transmits in the hardware now that interrupts are off */ for (i = 0; i < adapter->num_tx_queues; i++) { @@ -4292,7 +4293,7 @@ static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu) netdev->mtu, new_mtu); /* must set new MTU before calling down or up */ - netdev->mtu = new_mtu; + WRITE_ONCE(netdev->mtu, new_mtu); if (netif_running(netdev)) ixgbevf_reinit_locked(adapter); @@ -4300,7 +4301,7 @@ static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu) return 0; } -static int __maybe_unused ixgbevf_suspend(struct device *dev_d) +static int ixgbevf_suspend(struct device *dev_d) { struct net_device *netdev = dev_get_drvdata(dev_d); struct ixgbevf_adapter *adapter = netdev_priv(netdev); @@ -4317,7 +4318,7 @@ static int __maybe_unused ixgbevf_suspend(struct device *dev_d) return 0; } -static int __maybe_unused ixgbevf_resume(struct device *dev_d) +static int ixgbevf_resume(struct device *dev_d) { struct pci_dev *pdev = to_pci_dev(dev_d); struct net_device *netdev = pci_get_drvdata(pdev); @@ -4694,6 +4695,9 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) case ixgbe_mac_X540_vf: dev_info(&pdev->dev, "Intel(R) X540 Virtual Function\n"); break; + case ixgbe_mac_e610_vf: + dev_info(&pdev->dev, "Intel(R) E610 Virtual Function\n"); + break; case ixgbe_mac_82599_vf: default: dev_info(&pdev->dev, "Intel(R) 82599 Virtual Function\n"); @@ -4854,7 +4858,7 @@ static const struct pci_error_handlers ixgbevf_err_handler = { .resume = ixgbevf_io_resume, }; -static SIMPLE_DEV_PM_OPS(ixgbevf_pm_ops, ixgbevf_suspend, ixgbevf_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(ixgbevf_pm_ops, ixgbevf_suspend, ixgbevf_resume); static struct pci_driver ixgbevf_driver = { .name = ixgbevf_driver_name, @@ -4863,7 +4867,7 @@ static struct pci_driver ixgbevf_driver = { .remove = ixgbevf_remove, /* Power Management Hooks */ - .driver.pm = &ixgbevf_pm_ops, + .driver.pm = pm_sleep_ptr(&ixgbevf_pm_ops), .shutdown = ixgbevf_shutdown, .err_handler = &ixgbevf_err_handler diff --git a/drivers/net/ethernet/intel/ixgbevf/mbx.c b/drivers/net/ethernet/intel/ixgbevf/mbx.c index a55dd978f7ca..24d0237e7a99 100644 --- a/drivers/net/ethernet/intel/ixgbevf/mbx.c +++ b/drivers/net/ethernet/intel/ixgbevf/mbx.c @@ -505,15 +505,3 @@ const struct ixgbe_mbx_operations ixgbevf_mbx_ops_legacy = { .check_for_ack = ixgbevf_check_for_ack_vf, .check_for_rst = ixgbevf_check_for_rst_vf, }; - -/* Mailbox operations when running on Hyper-V. - * On Hyper-V, PF/VF communication is not through the - * hardware mailbox; this communication is through - * a software mediated path. - * Most mail box operations are noop while running on - * Hyper-V. - */ -const struct ixgbe_mbx_operations ixgbevf_hv_mbx_ops = { - .init_params = ixgbevf_init_mbx_params_vf, - .check_for_rst = ixgbevf_check_for_rst_vf, -}; diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c index 1641d00d8ed3..da7a72ecce7a 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.c +++ b/drivers/net/ethernet/intel/ixgbevf/vf.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #include "vf.h" #include "ixgbevf.h" @@ -1076,3 +1076,13 @@ const struct ixgbevf_info ixgbevf_x550em_a_vf_info = { .mac = ixgbe_mac_x550em_a_vf, .mac_ops = &ixgbevf_mac_ops, }; + +const struct ixgbevf_info ixgbevf_e610_vf_info = { + .mac = ixgbe_mac_e610_vf, + .mac_ops = &ixgbevf_mac_ops, +}; + +const struct ixgbevf_info ixgbevf_e610_vf_hv_info = { + .mac = ixgbe_mac_e610_vf, + .mac_ops = &ixgbevf_hv_mac_ops, +}; diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.h b/drivers/net/ethernet/intel/ixgbevf/vf.h index b4eef5b6c172..2d791bc26ae4 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.h +++ b/drivers/net/ethernet/intel/ixgbevf/vf.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #ifndef __IXGBE_VF_H__ #define __IXGBE_VF_H__ @@ -54,6 +54,8 @@ enum ixgbe_mac_type { ixgbe_mac_X550_vf, ixgbe_mac_X550EM_x_vf, ixgbe_mac_x550em_a_vf, + ixgbe_mac_e610, + ixgbe_mac_e610_vf, ixgbe_num_macs }; diff --git a/drivers/net/ethernet/intel/libeth/Kconfig b/drivers/net/ethernet/intel/libeth/Kconfig new file mode 100644 index 000000000000..480293b71dbc --- /dev/null +++ b/drivers/net/ethernet/intel/libeth/Kconfig @@ -0,0 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0-only +# Copyright (C) 2024 Intel Corporation + +config LIBETH + tristate + select PAGE_POOL + help + libeth is a common library containing routines shared between several + drivers, but not yet promoted to the generic kernel API. diff --git a/drivers/net/ethernet/intel/libeth/Makefile b/drivers/net/ethernet/intel/libeth/Makefile new file mode 100644 index 000000000000..52492b081132 --- /dev/null +++ b/drivers/net/ethernet/intel/libeth/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0-only +# Copyright (C) 2024 Intel Corporation + +obj-$(CONFIG_LIBETH) += libeth.o + +libeth-y := rx.o diff --git a/drivers/net/ethernet/intel/libeth/rx.c b/drivers/net/ethernet/intel/libeth/rx.c new file mode 100644 index 000000000000..66d1d23b8ad2 --- /dev/null +++ b/drivers/net/ethernet/intel/libeth/rx.c @@ -0,0 +1,259 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2024 Intel Corporation */ + +#include <net/libeth/rx.h> + +/* Rx buffer management */ + +/** + * libeth_rx_hw_len_mtu - get the actual buffer size to be passed to HW + * @pp: &page_pool_params of the netdev to calculate the size for + * @max_len: maximum buffer size for a single descriptor + * + * Return: HW-writeable length per one buffer to pass it to the HW accounting: + * MTU the @dev has, HW required alignment, minimum and maximum allowed values, + * and system's page size. + */ +static u32 libeth_rx_hw_len_mtu(const struct page_pool_params *pp, u32 max_len) +{ + u32 len; + + len = READ_ONCE(pp->netdev->mtu) + LIBETH_RX_LL_LEN; + len = ALIGN(len, LIBETH_RX_BUF_STRIDE); + len = min3(len, ALIGN_DOWN(max_len ? : U32_MAX, LIBETH_RX_BUF_STRIDE), + pp->max_len); + + return len; +} + +/** + * libeth_rx_hw_len_truesize - get the short buffer size to be passed to HW + * @pp: &page_pool_params of the netdev to calculate the size for + * @max_len: maximum buffer size for a single descriptor + * @truesize: desired truesize for the buffers + * + * Return: HW-writeable length per one buffer to pass it to the HW ignoring the + * MTU and closest to the passed truesize. Can be used for "short" buffer + * queues to fragment pages more efficiently. + */ +static u32 libeth_rx_hw_len_truesize(const struct page_pool_params *pp, + u32 max_len, u32 truesize) +{ + u32 min, len; + + min = SKB_HEAD_ALIGN(pp->offset + LIBETH_RX_BUF_STRIDE); + truesize = clamp(roundup_pow_of_two(truesize), roundup_pow_of_two(min), + PAGE_SIZE << LIBETH_RX_PAGE_ORDER); + + len = SKB_WITH_OVERHEAD(truesize - pp->offset); + len = ALIGN_DOWN(len, LIBETH_RX_BUF_STRIDE) ? : LIBETH_RX_BUF_STRIDE; + len = min3(len, ALIGN_DOWN(max_len ? : U32_MAX, LIBETH_RX_BUF_STRIDE), + pp->max_len); + + return len; +} + +/** + * libeth_rx_page_pool_params - calculate params with the stack overhead + * @fq: buffer queue to calculate the size for + * @pp: &page_pool_params of the netdev + * + * Set the PP params to will all needed stack overhead (headroom, tailroom) and + * both the HW buffer length and the truesize for all types of buffers. For + * "short" buffers, truesize never exceeds the "wanted" one; for the rest, + * it can be up to the page size. + * + * Return: true on success, false on invalid input params. + */ +static bool libeth_rx_page_pool_params(struct libeth_fq *fq, + struct page_pool_params *pp) +{ + pp->offset = LIBETH_SKB_HEADROOM; + /* HW-writeable / syncable length per one page */ + pp->max_len = LIBETH_RX_PAGE_LEN(pp->offset); + + /* HW-writeable length per buffer */ + switch (fq->type) { + case LIBETH_FQE_MTU: + fq->buf_len = libeth_rx_hw_len_mtu(pp, fq->buf_len); + break; + case LIBETH_FQE_SHORT: + fq->buf_len = libeth_rx_hw_len_truesize(pp, fq->buf_len, + fq->truesize); + break; + case LIBETH_FQE_HDR: + fq->buf_len = ALIGN(LIBETH_MAX_HEAD, LIBETH_RX_BUF_STRIDE); + break; + default: + return false; + } + + /* Buffer size to allocate */ + fq->truesize = roundup_pow_of_two(SKB_HEAD_ALIGN(pp->offset + + fq->buf_len)); + + return true; +} + +/** + * libeth_rx_page_pool_params_zc - calculate params without the stack overhead + * @fq: buffer queue to calculate the size for + * @pp: &page_pool_params of the netdev + * + * Set the PP params to exclude the stack overhead and both the buffer length + * and the truesize, which are equal for the data buffers. Note that this + * requires separate header buffers to be always active and account the + * overhead. + * With the MTU == ``PAGE_SIZE``, this allows the kernel to enable the zerocopy + * mode. + * + * Return: true on success, false on invalid input params. + */ +static bool libeth_rx_page_pool_params_zc(struct libeth_fq *fq, + struct page_pool_params *pp) +{ + u32 mtu, max; + + pp->offset = 0; + pp->max_len = PAGE_SIZE << LIBETH_RX_PAGE_ORDER; + + switch (fq->type) { + case LIBETH_FQE_MTU: + mtu = READ_ONCE(pp->netdev->mtu); + break; + case LIBETH_FQE_SHORT: + mtu = fq->truesize; + break; + default: + return false; + } + + mtu = roundup_pow_of_two(mtu); + max = min(rounddown_pow_of_two(fq->buf_len ? : U32_MAX), + pp->max_len); + + fq->buf_len = clamp(mtu, LIBETH_RX_BUF_STRIDE, max); + fq->truesize = fq->buf_len; + + return true; +} + +/** + * libeth_rx_fq_create - create a PP with the default libeth settings + * @fq: buffer queue struct to fill + * @napi: &napi_struct covering this PP (no usage outside its poll loops) + * + * Return: %0 on success, -%errno on failure. + */ +int libeth_rx_fq_create(struct libeth_fq *fq, struct napi_struct *napi) +{ + struct page_pool_params pp = { + .flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV, + .order = LIBETH_RX_PAGE_ORDER, + .pool_size = fq->count, + .nid = fq->nid, + .dev = napi->dev->dev.parent, + .netdev = napi->dev, + .napi = napi, + .dma_dir = DMA_FROM_DEVICE, + }; + struct libeth_fqe *fqes; + struct page_pool *pool; + bool ret; + + if (!fq->hsplit) + ret = libeth_rx_page_pool_params(fq, &pp); + else + ret = libeth_rx_page_pool_params_zc(fq, &pp); + if (!ret) + return -EINVAL; + + pool = page_pool_create(&pp); + if (IS_ERR(pool)) + return PTR_ERR(pool); + + fqes = kvcalloc_node(fq->count, sizeof(*fqes), GFP_KERNEL, fq->nid); + if (!fqes) + goto err_buf; + + fq->fqes = fqes; + fq->pp = pool; + + return 0; + +err_buf: + page_pool_destroy(pool); + + return -ENOMEM; +} +EXPORT_SYMBOL_NS_GPL(libeth_rx_fq_create, "LIBETH"); + +/** + * libeth_rx_fq_destroy - destroy a &page_pool created by libeth + * @fq: buffer queue to process + */ +void libeth_rx_fq_destroy(struct libeth_fq *fq) +{ + kvfree(fq->fqes); + page_pool_destroy(fq->pp); +} +EXPORT_SYMBOL_NS_GPL(libeth_rx_fq_destroy, "LIBETH"); + +/** + * libeth_rx_recycle_slow - recycle a libeth page from the NAPI context + * @page: page to recycle + * + * To be used on exceptions or rare cases not requiring fast inline recycling. + */ +void libeth_rx_recycle_slow(struct page *page) +{ + page_pool_recycle_direct(page->pp, page); +} +EXPORT_SYMBOL_NS_GPL(libeth_rx_recycle_slow, "LIBETH"); + +/* Converting abstract packet type numbers into a software structure with + * the packet parameters to do O(1) lookup on Rx. + */ + +static const u16 libeth_rx_pt_xdp_oip[] = { + [LIBETH_RX_PT_OUTER_L2] = XDP_RSS_TYPE_NONE, + [LIBETH_RX_PT_OUTER_IPV4] = XDP_RSS_L3_IPV4, + [LIBETH_RX_PT_OUTER_IPV6] = XDP_RSS_L3_IPV6, +}; + +static const u16 libeth_rx_pt_xdp_iprot[] = { + [LIBETH_RX_PT_INNER_NONE] = XDP_RSS_TYPE_NONE, + [LIBETH_RX_PT_INNER_UDP] = XDP_RSS_L4_UDP, + [LIBETH_RX_PT_INNER_TCP] = XDP_RSS_L4_TCP, + [LIBETH_RX_PT_INNER_SCTP] = XDP_RSS_L4_SCTP, + [LIBETH_RX_PT_INNER_ICMP] = XDP_RSS_L4_ICMP, + [LIBETH_RX_PT_INNER_TIMESYNC] = XDP_RSS_TYPE_NONE, +}; + +static const u16 libeth_rx_pt_xdp_pl[] = { + [LIBETH_RX_PT_PAYLOAD_NONE] = XDP_RSS_TYPE_NONE, + [LIBETH_RX_PT_PAYLOAD_L2] = XDP_RSS_TYPE_NONE, + [LIBETH_RX_PT_PAYLOAD_L3] = XDP_RSS_TYPE_NONE, + [LIBETH_RX_PT_PAYLOAD_L4] = XDP_RSS_L4, +}; + +/** + * libeth_rx_pt_gen_hash_type - generate an XDP RSS hash type for a PT + * @pt: PT structure to evaluate + * + * Generates ```hash_type``` field with XDP RSS type values from the parsed + * packet parameters if they're obtained dynamically at runtime. + */ +void libeth_rx_pt_gen_hash_type(struct libeth_rx_pt *pt) +{ + pt->hash_type = 0; + pt->hash_type |= libeth_rx_pt_xdp_oip[pt->outer_ip]; + pt->hash_type |= libeth_rx_pt_xdp_iprot[pt->inner_prot]; + pt->hash_type |= libeth_rx_pt_xdp_pl[pt->payload_layer]; +} +EXPORT_SYMBOL_NS_GPL(libeth_rx_pt_gen_hash_type, "LIBETH"); + +/* Module */ + +MODULE_DESCRIPTION("Common Ethernet library"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/intel/libie/Kconfig b/drivers/net/ethernet/intel/libie/Kconfig new file mode 100644 index 000000000000..33aff6bc8f81 --- /dev/null +++ b/drivers/net/ethernet/intel/libie/Kconfig @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0-only +# Copyright (C) 2024 Intel Corporation + +config LIBIE + tristate + select LIBETH + help + libie (Intel Ethernet library) is a common library built on top of + libeth and containing vendor-specific routines shared between several + Intel Ethernet drivers. diff --git a/drivers/net/ethernet/intel/libie/Makefile b/drivers/net/ethernet/intel/libie/Makefile new file mode 100644 index 000000000000..ffd27fab916a --- /dev/null +++ b/drivers/net/ethernet/intel/libie/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0-only +# Copyright (C) 2024 Intel Corporation + +obj-$(CONFIG_LIBIE) += libie.o + +libie-y := rx.o diff --git a/drivers/net/ethernet/intel/libie/rx.c b/drivers/net/ethernet/intel/libie/rx.c new file mode 100644 index 000000000000..66a9825fe11f --- /dev/null +++ b/drivers/net/ethernet/intel/libie/rx.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2024 Intel Corporation */ + +#include <linux/net/intel/libie/rx.h> + +/* O(1) converting i40e/ice/iavf's 8/10-bit hardware packet type to a parsed + * bitfield struct. + */ + +/* A few supplementary definitions for when XDP hash types do not coincide + * with what can be generated from ptype definitions by means of preprocessor + * concatenation. + */ +#define XDP_RSS_L3_L2 XDP_RSS_TYPE_NONE +#define XDP_RSS_L4_NONE XDP_RSS_TYPE_NONE +#define XDP_RSS_L4_TIMESYNC XDP_RSS_TYPE_NONE +#define XDP_RSS_TYPE_L3 XDP_RSS_TYPE_NONE +#define XDP_RSS_TYPE_L4 XDP_RSS_L4 + +#define LIBIE_RX_PT(oip, ofrag, tun, tp, tefr, iprot, pl) { \ + .outer_ip = LIBETH_RX_PT_OUTER_##oip, \ + .outer_frag = LIBETH_RX_PT_##ofrag, \ + .tunnel_type = LIBETH_RX_PT_TUNNEL_IP_##tun, \ + .tunnel_end_prot = LIBETH_RX_PT_TUNNEL_END_##tp, \ + .tunnel_end_frag = LIBETH_RX_PT_##tefr, \ + .inner_prot = LIBETH_RX_PT_INNER_##iprot, \ + .payload_layer = LIBETH_RX_PT_PAYLOAD_##pl, \ + .hash_type = XDP_RSS_L3_##oip | \ + XDP_RSS_L4_##iprot | \ + XDP_RSS_TYPE_##pl, \ + } + +#define LIBIE_RX_PT_UNUSED { } + +#define __LIBIE_RX_PT_L2(iprot, pl) \ + LIBIE_RX_PT(L2, NOT_FRAG, NONE, NONE, NOT_FRAG, iprot, pl) +#define LIBIE_RX_PT_L2 __LIBIE_RX_PT_L2(NONE, L2) +#define LIBIE_RX_PT_TS __LIBIE_RX_PT_L2(TIMESYNC, L2) +#define LIBIE_RX_PT_L3 __LIBIE_RX_PT_L2(NONE, L3) + +#define LIBIE_RX_PT_IP_FRAG(oip) \ + LIBIE_RX_PT(IPV##oip, FRAG, NONE, NONE, NOT_FRAG, NONE, L3) +#define LIBIE_RX_PT_IP_L3(oip, tun, teprot, tefr) \ + LIBIE_RX_PT(IPV##oip, NOT_FRAG, tun, teprot, tefr, NONE, L3) +#define LIBIE_RX_PT_IP_L4(oip, tun, teprot, iprot) \ + LIBIE_RX_PT(IPV##oip, NOT_FRAG, tun, teprot, NOT_FRAG, iprot, L4) + +#define LIBIE_RX_PT_IP_NOF(oip, tun, ver) \ + LIBIE_RX_PT_IP_L3(oip, tun, ver, NOT_FRAG), \ + LIBIE_RX_PT_IP_L4(oip, tun, ver, UDP), \ + LIBIE_RX_PT_UNUSED, \ + LIBIE_RX_PT_IP_L4(oip, tun, ver, TCP), \ + LIBIE_RX_PT_IP_L4(oip, tun, ver, SCTP), \ + LIBIE_RX_PT_IP_L4(oip, tun, ver, ICMP) + +/* IPv oip --> tun --> IPv ver */ +#define LIBIE_RX_PT_IP_TUN_VER(oip, tun, ver) \ + LIBIE_RX_PT_IP_L3(oip, tun, ver, FRAG), \ + LIBIE_RX_PT_IP_NOF(oip, tun, ver) + +/* Non Tunneled IPv oip */ +#define LIBIE_RX_PT_IP_RAW(oip) \ + LIBIE_RX_PT_IP_FRAG(oip), \ + LIBIE_RX_PT_IP_NOF(oip, NONE, NONE) + +/* IPv oip --> tun --> { IPv4, IPv6 } */ +#define LIBIE_RX_PT_IP_TUN(oip, tun) \ + LIBIE_RX_PT_IP_TUN_VER(oip, tun, IPV4), \ + LIBIE_RX_PT_IP_TUN_VER(oip, tun, IPV6) + +/* IPv oip --> GRE/NAT tun --> { x, IPv4, IPv6 } */ +#define LIBIE_RX_PT_IP_GRE(oip, tun) \ + LIBIE_RX_PT_IP_L3(oip, tun, NONE, NOT_FRAG), \ + LIBIE_RX_PT_IP_TUN(oip, tun) + +/* Non Tunneled IPv oip + * IPv oip --> { IPv4, IPv6 } + * IPv oip --> GRE/NAT --> { x, IPv4, IPv6 } + * IPv oip --> GRE/NAT --> MAC --> { x, IPv4, IPv6 } + * IPv oip --> GRE/NAT --> MAC/VLAN --> { x, IPv4, IPv6 } + */ +#define LIBIE_RX_PT_IP(oip) \ + LIBIE_RX_PT_IP_RAW(oip), \ + LIBIE_RX_PT_IP_TUN(oip, IP), \ + LIBIE_RX_PT_IP_GRE(oip, GRENAT), \ + LIBIE_RX_PT_IP_GRE(oip, GRENAT_MAC), \ + LIBIE_RX_PT_IP_GRE(oip, GRENAT_MAC_VLAN) + +/* Lookup table mapping for O(1) parsing */ +const struct libeth_rx_pt libie_rx_pt_lut[LIBIE_RX_PT_NUM] = { + /* L2 packet types */ + LIBIE_RX_PT_UNUSED, + LIBIE_RX_PT_L2, + LIBIE_RX_PT_TS, + LIBIE_RX_PT_L2, + LIBIE_RX_PT_UNUSED, + LIBIE_RX_PT_UNUSED, + LIBIE_RX_PT_L2, + LIBIE_RX_PT_L2, + LIBIE_RX_PT_UNUSED, + LIBIE_RX_PT_UNUSED, + LIBIE_RX_PT_L2, + LIBIE_RX_PT_UNUSED, + + LIBIE_RX_PT_L3, + LIBIE_RX_PT_L3, + LIBIE_RX_PT_L3, + LIBIE_RX_PT_L3, + LIBIE_RX_PT_L3, + LIBIE_RX_PT_L3, + LIBIE_RX_PT_L3, + LIBIE_RX_PT_L3, + LIBIE_RX_PT_L3, + LIBIE_RX_PT_L3, + + LIBIE_RX_PT_IP(4), + LIBIE_RX_PT_IP(6), +}; +EXPORT_SYMBOL_NS_GPL(libie_rx_pt_lut, "LIBIE"); + +MODULE_DESCRIPTION("Intel(R) Ethernet common library"); +MODULE_IMPORT_NS("LIBETH"); +MODULE_LICENSE("GPL"); |