diff options
Diffstat (limited to 'drivers/net/ethernet/intel')
141 files changed, 11227 insertions, 2569 deletions
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index 24ec9a4f1ffa..5a331c1c76cb 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -147,6 +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 @@ -264,6 +266,7 @@ 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 @@ -336,7 +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 @@ -366,6 +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. diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 3a5bbda235cb..c0ead54ea186 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -2293,7 +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: @@ -2308,7 +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); diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h index 5e2cfa73f889..8294a7c4f122 100644 --- a/drivers/net/ethernet/intel/e1000e/defines.h +++ b/drivers/net/ethernet/intel/e1000e/defines.h @@ -803,4 +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/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 2f9655cf5dd9..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: @@ -4888,6 +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 286155efcedf..e0f492a6723f 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -3574,6 +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 @@ -3587,7 +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; @@ -3598,8 +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: @@ -3608,6 +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; } @@ -3681,6 +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; } @@ -3693,7 +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; } @@ -3706,7 +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; } @@ -3901,6 +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; @@ -3932,7 +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); + } } /** @@ -4287,8 +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); @@ -6079,8 +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); @@ -6140,7 +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 @@ -6153,20 +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: @@ -6178,38 +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) @@ -7346,9 +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, }; /** @@ -7741,8 +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); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 92de609b7218..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); diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 370b4bddee44..b11c35e307ca 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -817,10 +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; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 65a702668e21..120d68654e3f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -16382,7 +16382,7 @@ static int i40e_io_suspend(struct i40e_pf *pf) set_bit(__I40E_DOWN, pf->state); /* Ensure service task will not be running */ - del_timer_sync(&pf->service_timer); + timer_delete_sync(&pf->service_timer); cancel_work_sync(&pf->service_task); /* Client close must be called explicitly here because the timer @@ -16581,7 +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); diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index e28f1905a4a0..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" @@ -529,7 +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 356ac9faa5bf..e13720a728ff 100644 --- a/drivers/net/ethernet/intel/iavf/Makefile +++ b/drivers/net/ethernet/intel/iavf/Makefile @@ -13,3 +13,5 @@ obj-$(CONFIG_IAVF) += iavf.o iavf-y := iavf_main.o iavf_ethtool.o iavf_virtchnl.o iavf_fdir.o \ iavf_adv_rss.o iavf_txrx.o iavf_common.o iavf_adminq.o + +iavf-$(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 532a0a595fe8..9de3e0ba3731 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -41,6 +41,7 @@ #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 @@ -82,7 +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])) @@ -271,6 +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; @@ -343,6 +345,17 @@ struct iavf_adapter { #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 @@ -354,10 +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 @@ -417,12 +438,18 @@ struct iavf_adapter { 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; @@ -555,6 +582,10 @@ 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); diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 74a1e9fe1821..288bb5b2e72e 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -1808,7 +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, diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 852e5b62f0a5..6d7ba4d67a19 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -2,8 +2,10 @@ /* 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 @@ -710,6 +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 * @@ -719,8 +762,12 @@ static void iavf_configure_rx(struct iavf_adapter *adapter) { struct iavf_hw *hw = &adapter->hw; - for (u32 i = 0; i < adapter->num_active_queues; i++) + adapter->rxdid = iavf_select_rx_desc_format(adapter); + + 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].rxdid = adapter->rxdid; + } } /** @@ -1983,7 +2030,7 @@ err: static void iavf_finish_config(struct work_struct *work) { struct iavf_adapter *adapter; - bool netdev_released = false; + bool locks_released = false; int pairs, err; adapter = container_of(work, struct iavf_adapter, finish_config); @@ -2012,19 +2059,22 @@ static void iavf_finish_config(struct work_struct *work) 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); - netdev_released = true; + 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; } } @@ -2040,9 +2090,10 @@ static void iavf_finish_config(struct work_struct *work) } out: - mutex_unlock(&adapter->crit_lock); - if (!netdev_released) + if (!locks_released) { + mutex_unlock(&adapter->crit_lock); netdev_unlock(adapter->netdev); + } rtnl_unlock(); } @@ -2071,6 +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; @@ -2235,7 +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; @@ -2600,6 +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 * @@ -2623,6 +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 */ @@ -2714,6 +2896,9 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) 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; @@ -3139,15 +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 @@ -3707,10 +3895,8 @@ exit: if (test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) return 0; - netdev_lock(netdev); netif_set_real_num_rx_queues(netdev, total_qps); netif_set_real_num_tx_queues(netdev, total_qps); - netdev_unlock(netdev); return ret; } @@ -4375,22 +4561,21 @@ 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; } - netdev_lock(netdev); while (!mutex_trylock(&adapter->crit_lock)) { /* If we are in __IAVF_INIT_CONFIG_ADAPTER state the crit_lock * is already taken and iavf_open is called from an upper * device's notifier reacting on NETDEV_REGISTER event. * We have to leave here to avoid dead lock. */ - if (adapter->state == __IAVF_INIT_CONFIG_ADAPTER) { - netdev_unlock(netdev); + if (adapter->state == __IAVF_INIT_CONFIG_ADAPTER) return -EBUSY; - } usleep_range(500, 1000); } @@ -4439,7 +4624,6 @@ static int iavf_open(struct net_device *netdev) iavf_irq_enable(adapter, true); mutex_unlock(&adapter->crit_lock); - netdev_unlock(netdev); return 0; @@ -4452,7 +4636,6 @@ err_setup_tx: iavf_free_all_tx_resources(adapter); err_unlock: mutex_unlock(&adapter->crit_lock); - netdev_unlock(netdev); return err; } @@ -4474,12 +4657,12 @@ static int iavf_close(struct net_device *netdev) u64 aq_to_restore; int status; - netdev_lock(netdev); + netdev_assert_locked(netdev); + mutex_lock(&adapter->crit_lock); if (adapter->state <= __IAVF_DOWN_PENDING) { mutex_unlock(&adapter->crit_lock); - netdev_unlock(netdev); return 0; } @@ -4532,6 +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); @@ -4996,6 +5180,25 @@ 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, @@ -5104,6 +5307,8 @@ static const struct net_device_ops iavf_netdev_ops = { .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, }; /** @@ -5358,6 +5563,10 @@ 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. */ @@ -5514,6 +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); 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 62212011c807..c5e4d1823886 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_trace.h +++ b/drivers/net/ethernet/intel/iavf/iavf_trace.h @@ -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), @@ -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)); diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index 26b424fd6718..422312b8b54a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -8,6 +8,26 @@ #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) @@ -766,7 +786,7 @@ int iavf_setup_rx_descriptors(struct iavf_ring *rx_ring) 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(fq.pp->p.dev, rx_ring->size, &rx_ring->dma, GFP_KERNEL); @@ -845,7 +865,7 @@ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count) .count = rx_ring->count, }; u16 ntu = rx_ring->next_to_use; - union iavf_rx_desc *rx_desc; + struct iavf_rx_desc *rx_desc; /* do nothing if no valid netdev defined */ if (!rx_ring->netdev || !cleaned_count) @@ -863,7 +883,7 @@ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count) /* 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(addr); + rx_desc->qw0 = cpu_to_le64(addr); rx_desc++; ntu++; @@ -873,7 +893,7 @@ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count) } /* 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); @@ -896,60 +916,43 @@ 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 libeth_rx_pt decoded; - u32 rx_error, rx_status; bool ipv4, ipv6; - u8 ptype; - u64 qword; skb->ip_summed = CHECKSUM_NONE; - qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword); - - decoded = libie_rx_pt_parse(ptype); - if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded)) - return; - - rx_error = FIELD_GET(IAVF_RXD_QW1_ERROR_MASK, qword); - rx_status = FIELD_GET(IAVF_RXD_QW1_STATUS_MASK, qword); - /* did the hardware decode the packet and checksum? */ - if (!(rx_status & BIT(IAVF_RX_DESC_STATUS_L3L4P_SHIFT))) + if (unlikely(!csum_bits.l3l4p)) return; - 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; + 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; skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -960,52 +963,196 @@ checksum_fail: } /** - * iavf_rx_hash - set the hash value in the skb + * 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 + * + * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte + * descriptor writeback format. + * + * Return: decoded checksum bits. + **/ +static struct libeth_rx_csum +iavf_legacy_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_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_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 + * @qw0: quad word 0 + * @qw1: quad word 1 + * @skb: skb currently being received and modified + * @decoded_pt: decoded packet type + * + * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte + * descriptor writeback format. + **/ +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; + + if (!libeth_rx_pt_has_hash(ring->netdev, decoded_pt)) + return; + + 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 - * @rx_desc: specific descriptor + * @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_2_FLEX_SQ_NIC flexible + * 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_flex_rx_hash(const struct iavf_ring *ring, __le64 qw1, + struct sk_buff *skb, + const struct libeth_rx_pt decoded_pt) { - struct libeth_rx_pt decoded; + bool rss_valid; u32 hash; - const __le64 rss_mask = - cpu_to_le64((u64)IAVF_RX_DESC_FLTSTAT_RSS_HASH << - IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT); - decoded = libie_rx_pt_parse(rx_ptype); - if (!libeth_rx_pt_has_hash(ring->netdev, decoded)) + 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); - libeth_rx_pt_set_hash(skb, hash, decoded); + 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); @@ -1092,8 +1239,7 @@ static struct sk_buff *iavf_build_skb(const struct libeth_fqe *rx_buffer, /** * 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 @@ -1101,8 +1247,7 @@ static struct sk_buff *iavf_build_skb(const struct libeth_fqe *rx_buffer, * 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; @@ -1113,8 +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++; @@ -1123,6 +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 @@ -1136,18 +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 libeth_rqe_info fields; struct libeth_fqe *rx_buffer; - union iavf_rx_desc *rx_desc; - unsigned int size; - u16 vlan_tag = 0; - u8 rx_ptype; - u64 qword; + 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) { @@ -1158,35 +1404,32 @@ 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 = &rx_ring->rx_fqes[rx_ring->next_to_clean]; - if (!libeth_rx_sync_for_cpu(rx_buffer, size)) + 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(skb, rx_buffer, size); + iavf_add_rx_frag(skb, rx_buffer, fields.len); else - skb = iavf_build_skb(rx_buffer, size); + skb = iavf_build_skb(rx_buffer, fields.len); /* exit if we failed to retrieve a buffer */ if (!skb) { @@ -1197,15 +1440,14 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget) skip_data: cleaned_count++; - if (iavf_is_non_eop(rx_ring, rx_desc, skb) || unlikely(!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; @@ -1219,22 +1461,11 @@ skip_data: /* 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 */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h index f97c702c0802..79ad554f2d53 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h @@ -80,25 +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)) -#define iavf_rx_desc iavf_32byte_rx_desc - -/** - * 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 { \ @@ -262,6 +243,8 @@ struct iavf_ring { u16 next_to_use; u16 next_to_clean; + u16 rxdid; /* Rx descriptor format */ + u16 flags; #define IAVF_TXR_FLAGS_WB_ON_ITR BIT(0) #define IAVF_TXR_FLAGS_ARM_WB BIT(1) @@ -269,6 +252,7 @@ struct iavf_ring { #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; @@ -295,6 +279,8 @@ struct iavf_ring { * for this ring. */ + struct iavf_ptp *ptp; + u32 rx_buf_len; struct net_shaper q_shaper; bool q_shaper_update; diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h index f6b09e57abce..f9e1319620f4 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_type.h +++ b/drivers/net/ethernet/intel/iavf/iavf_type.h @@ -178,110 +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 << \ @@ -298,22 +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, @@ -322,13 +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) - -#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) @@ -347,6 +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 15d388b431c5..a6f0e5990be2 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -4,6 +4,7 @@ #include <linux/net/intel/libie/rx.h> #include "iavf.h" +#include "iavf_ptp.h" #include "iavf_prototype.h" /** @@ -144,9 +145,11 @@ int iavf_send_vf_config_msg(struct iavf_adapter *adapter) 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 | @@ -177,6 +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 @@ -263,6 +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 @@ -275,6 +360,7 @@ void iavf_configure_queues(struct iavf_adapter *adapter) int pairs = adapter->num_active_queues; struct virtchnl_queue_pair_info *vqpi; u32 i, max_frame; + u8 rx_flags = 0; size_t len; max_frame = LIBIE_MAX_RX_FRM_LEN(adapter->rx_rings->pp->p.offset); @@ -292,6 +378,9 @@ void iavf_configure_queues(struct iavf_adapter *adapter) if (!vqci) return; + 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; vqpi = vqci->qpair; @@ -309,9 +398,12 @@ void iavf_configure_queues(struct iavf_adapter *adapter) vqpi->rxq.dma_ring_addr = adapter->rx_rings[i].dma; vqpi->rxq.max_pkt_size = max_frame; 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++; } @@ -1402,6 +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 @@ -2098,6 +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 @@ -2509,6 +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); diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c index dbdb83567364..4af60e2f37df 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c @@ -1205,6 +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 @@ -1220,6 +1239,9 @@ static int ice_devlink_reinit_up(struct ice_pf *pf) return err; } + /* load MSI-X values */ + ice_set_min_max_msix(pf); + err = ice_init_dev(pf); if (err) goto unroll_hw_init; @@ -1317,8 +1339,13 @@ 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; } @@ -1328,19 +1355,24 @@ static int ice_devlink_enable_roce_set(struct devlink *devlink, u32 id, 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; } @@ -1351,11 +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; } @@ -1368,8 +1405,13 @@ 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; } @@ -1379,19 +1421,24 @@ static int ice_devlink_enable_iw_set(struct devlink *devlink, u32 id, 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; } @@ -1406,7 +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; } @@ -1533,6 +1580,43 @@ static int ice_devlink_local_fwd_validate(struct devlink *devlink, u32 id, 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 ice_pf *pf = devlink_priv(devlink); + + if (val.vu32 > pf->hw.func_caps.common_cap.num_msix_vectors) + return -EINVAL; + + return 0; +} + +static int +ice_devlink_msix_min_pf_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + if (val.vu32 < ICE_MIN_MSIX) + return -EINVAL; + + return 0; +} + +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, @@ -1548,6 +1632,17 @@ static const struct devlink_param ice_dvl_rdma_params[] = { 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[] = { @@ -1651,6 +1746,7 @@ void ice_devlink_unregister(struct ice_pf *pf) 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; @@ -1659,10 +1755,39 @@ int ice_devlink_register_params(struct ice_pf *pf) if (status) return status; + status = devl_params_register(devlink, ice_dvl_msix_params, + ARRAY_SIZE(ice_dvl_msix_params)); + if (status) + goto unregister_rdma_params; + 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; } @@ -1673,6 +1798,8 @@ void ice_devlink_unregister_params(struct ice_pf *pf) 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, diff --git a/drivers/net/ethernet/intel/ice/devlink/health.c b/drivers/net/ethernet/intel/ice/devlink/health.c index ea40f7941259..19c3d37aa768 100644 --- a/drivers/net/ethernet/intel/ice/devlink/health.c +++ b/drivers/net/ethernet/intel/ice/devlink/health.c @@ -25,10 +25,10 @@ struct ice_health_status { * The below lookup requires to be sorted by code. */ -static const char *const ice_common_port_solutions = +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 *const ice_port_number_label = "Port Number"; -static const char *const ice_update_nvm_solution = "Update to the latest NVM image."; +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.", diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 71e05d30f0fd..ddd0ad68185b 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -97,9 +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 @@ -196,14 +193,13 @@ #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, @@ -403,7 +399,6 @@ 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 */ @@ -478,9 +473,6 @@ 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]; @@ -520,6 +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 */ }; @@ -542,6 +535,14 @@ 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; @@ -554,15 +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 */ @@ -595,7 +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; @@ -612,7 +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! */ @@ -628,14 +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 @@ -667,6 +658,7 @@ struct ice_pf { 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; }; @@ -1047,10 +1039,63 @@ static inline void ice_clear_rdma_cap(struct ice_pf *pf) clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); } -static inline enum ice_phy_model ice_get_phy_model(const struct ice_hw *hw) +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->ptp.phy_model; + return hw->mac_type == ICE_MAC_GENERIC_3K_E825 && + (hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_DUAL_M); } -extern const struct xdp_metadata_ops ice_xdp_md_ops; +/** + * 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 index 01a08cfd0090..66e070095d1b 100644 --- a/drivers/net/ethernet/intel/ice/ice_adapter.c +++ b/drivers/net/ethernet/intel/ice/ice_adapter.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only // SPDX-FileCopyrightText: Copyright Red Hat -#include <linux/bitfield.h> #include <linux/cleanup.h> #include <linux/mutex.h> #include <linux/pci.h> @@ -14,32 +13,16 @@ static DEFINE_XARRAY(ice_adapters); static DEFINE_MUTEX(ice_adapters_mutex); -/* PCI bus number is 8 bits. Slot is 5 bits. Domain can have the rest. */ -#define INDEX_FIELD_DOMAIN GENMASK(BITS_PER_LONG - 1, 13) -#define INDEX_FIELD_DEV GENMASK(31, 16) -#define INDEX_FIELD_BUS GENMASK(12, 5) -#define INDEX_FIELD_SLOT GENMASK(4, 0) - -static unsigned long ice_adapter_index(const struct pci_dev *pdev) +static unsigned long ice_adapter_index(u64 dsn) { - unsigned int domain = pci_domain_nr(pdev->bus); - - WARN_ON(domain > FIELD_MAX(INDEX_FIELD_DOMAIN)); - - switch (pdev->device) { - case ICE_DEV_ID_E825C_BACKPLANE: - case ICE_DEV_ID_E825C_QSFP: - case ICE_DEV_ID_E825C_SFP: - case ICE_DEV_ID_E825C_SGMII: - return FIELD_PREP(INDEX_FIELD_DEV, pdev->device); - default: - return FIELD_PREP(INDEX_FIELD_DOMAIN, domain) | - FIELD_PREP(INDEX_FIELD_BUS, pdev->bus->number) | - FIELD_PREP(INDEX_FIELD_SLOT, PCI_SLOT(pdev->devfn)); - } +#if BITS_PER_LONG == 64 + return dsn; +#else + return (u32)dsn ^ (u32)(dsn >> 32); +#endif } -static struct ice_adapter *ice_adapter_new(void) +static struct ice_adapter *ice_adapter_new(u64 dsn) { struct ice_adapter *adapter; @@ -47,6 +30,7 @@ static struct ice_adapter *ice_adapter_new(void) if (!adapter) return NULL; + adapter->device_serial_number = dsn; spin_lock_init(&adapter->ptp_gltsyn_time_lock); refcount_set(&adapter->refcount, 1); @@ -77,23 +61,26 @@ static void ice_adapter_free(struct ice_adapter *adapter) * Return: Pointer to ice_adapter on success. * ERR_PTR() on error. -ENOMEM is the only possible error. */ -struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev) +struct ice_adapter *ice_adapter_get(struct pci_dev *pdev) { - unsigned long index = ice_adapter_index(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(); + adapter = ice_adapter_new(dsn); if (!adapter) return ERR_PTR(-ENOMEM); xa_store(&ice_adapters, index, adapter, GFP_KERNEL); @@ -110,11 +97,13 @@ struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev) * * Context: Process, may sleep. */ -void ice_adapter_put(const struct pci_dev *pdev) +void ice_adapter_put(struct pci_dev *pdev) { - unsigned long index = ice_adapter_index(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)) diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.h b/drivers/net/ethernet/intel/ice/ice_adapter.h index e233225848b3..ac15c0d2bc1a 100644 --- a/drivers/net/ethernet/intel/ice/ice_adapter.h +++ b/drivers/net/ethernet/intel/ice/ice_adapter.h @@ -32,6 +32,7 @@ struct ice_port_list { * @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; @@ -40,9 +41,10 @@ struct ice_adapter { struct ice_pf *ctrl_pf; struct ice_port_list ports; + u64 device_serial_number; }; -struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev); -void ice_adapter_put(const struct pci_dev *pdev); +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_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 b2af8e3586f7..6db4ad8fc70b 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -147,10 +147,6 @@ skip_alloc: q_vector->reg_idx = q_vector->irq.index; q_vector->vf_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); - /* 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.) @@ -276,7 +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); } @@ -473,9 +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); @@ -801,13 +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; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 7a2a2e8da8fa..4fedf0181c4e 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -186,7 +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) { @@ -195,120 +195,6 @@ 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 - * - * returns true if the device is E810T based, false if not. - */ -bool ice_is_e810t(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; - } - - return false; -} - -/** - * ice_is_e822 - Check if a device is E822 family device - * @hw: pointer to the hardware structure - * - * Return: true if the device is E822 based, false if not. - */ -bool ice_is_e822(struct ice_hw *hw) -{ - switch (hw->device_id) { - case ICE_DEV_ID_E822C_BACKPLANE: - case ICE_DEV_ID_E822C_QSFP: - case ICE_DEV_ID_E822C_SFP: - case ICE_DEV_ID_E822C_10G_BASE_T: - case ICE_DEV_ID_E822C_SGMII: - case ICE_DEV_ID_E822L_BACKPLANE: - case ICE_DEV_ID_E822L_SFP: - case ICE_DEV_ID_E822L_10G_BASE_T: - case ICE_DEV_ID_E822L_SGMII: - return true; - default: - 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: - return true; - default: - 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: - return true; - default: - return false; - } -} - -/** * ice_is_pf_c827 - check if pf contains c827 phy * @hw: pointer to the hw struct * @@ -1249,6 +1135,8 @@ int ice_init_hw(struct ice_hw *hw) } } + hw->lane_num = ice_get_phy_lane_number(hw); + return 0; err_unroll_fltr_mgmt_struct: ice_cleanup_fltr_mgmt_struct(hw); @@ -2271,7 +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: @@ -2408,7 +2297,7 @@ 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); - if (!ice_is_e825c(hw)) { + 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 { @@ -3547,7 +3436,7 @@ int ice_aq_get_fec_stats(struct ice_hw *hw, u16 pcs_quad, u16 pcs_port, msg.msg_addr_low = lower_16_bits(reg_offset); msg.msg_addr_high = receiver_id; 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, flag); if (err) @@ -4195,10 +4084,12 @@ int ice_get_phy_lane_number(struct ice_hw *hw) 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++; } @@ -5765,6 +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 @@ -6034,15 +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); @@ -6052,7 +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 15ba38543738..64c530b39191 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -131,7 +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, @@ -276,10 +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_e822(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); @@ -295,8 +290,7 @@ 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, @@ -306,5 +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_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 a7c510832824..533eb8930aa8 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -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; @@ -783,13 +785,17 @@ void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked) 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); } @@ -846,7 +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; @@ -945,6 +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 03988be03729..59323c019544 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.c +++ b/drivers/net/ethernet/intel/ice/ice_ddp.c @@ -2345,15 +2345,15 @@ ice_get_set_tx_topo(struct ice_hw *hw, u8 *buf, u16 buf_size, cmd->set_flags |= ICE_AQC_TX_TOPO_FLAGS_SRC_RAM | ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW; - if (ice_is_e825c(hw)) - desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + 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 (!ice_is_e825c(hw)) - desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + 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) diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index 8d806d8ad761..bce3ad6ca2a6 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -95,7 +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); @@ -322,7 +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); @@ -367,7 +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); @@ -479,7 +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); @@ -518,7 +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); @@ -1004,7 +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); @@ -1362,7 +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); diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index fb527434b58b..6aae03771746 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -29,6 +29,7 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) 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); @@ -38,8 +39,7 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) if (ice_vsi_add_vlan_zero(uplink_vsi)) goto err_vlan_zero; - if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true, - ICE_FLTR_RX)) + if (ice_set_dflt_vsi(uplink_vsi)) goto err_def_rx; if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true, @@ -50,9 +50,6 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) if (vlan_ops->dis_rx_filtering(uplink_vsi)) goto err_vlan_filtering; - if (ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_set_allow_override)) - goto err_override_uplink; - if (ice_vsi_update_local_lb(uplink_vsi, true)) goto err_override_local_lb; @@ -64,8 +61,6 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) err_up: ice_vsi_update_local_lb(uplink_vsi, false); err_override_local_lb: - ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override); -err_override_uplink: vlan_ops->ena_rx_filtering(uplink_vsi); err_vlan_filtering: ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false, @@ -251,6 +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 { @@ -276,7 +275,6 @@ static void ice_eswitch_release_env(struct ice_pf *pf) vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi); ice_vsi_update_local_lb(uplink_vsi, false); - ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override); vlan_ops->ena_rx_filtering(uplink_vsi); ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false, ICE_FLTR_TX); @@ -285,6 +283,7 @@ static void ice_eswitch_release_env(struct ice_pf *pf) ice_fltr_add_mac_and_broadcast(uplink_vsi, uplink_vsi->port_info->mac.perm_addr, ICE_FWD_TO_VSI); + ice_vsi_cfg_sw_lldp(uplink_vsi, true, true); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index f241493a6ac8..bbf9e6fd315b 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -1818,7 +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 @@ -3788,8 +3788,7 @@ ice_get_ts_info(struct net_device *dev, struct kernel_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); } /** @@ -3798,8 +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); } /** @@ -3817,8 +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; @@ -3967,11 +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; @@ -3990,7 +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; @@ -4773,7 +4770,7 @@ static const struct ethtool_ops ice_ethtool_ops = { .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, diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c index ee9862ddfe15..aceec184e89b 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c @@ -1605,22 +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; - - err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV4_UDP); - 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_IPV6_TCP); - if (err) - return err; - - err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV6_UDP); + if (err) + break; + } return err; } diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c index b2148dbe49b2..6b26290452d4 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.c +++ b/drivers/net/ethernet/intel/ice/ice_gnss.c @@ -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(hw, ICE_PCA9575_P0_IN, &data); - if (err || !!(data & ICE_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 dc88aea9f473..aa4bfbcf85d2 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -541,10 +541,22 @@ #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 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 1ccb572ce285..2410aee59fb2 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -1001,6 +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 */ @@ -1021,6 +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; @@ -1296,12 +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); @@ -1419,6 +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; } @@ -1428,6 +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 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 1479b45738af..77ba26538b07 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -229,7 +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 */ @@ -478,10 +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) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 38a1c8372180..03bb16191237 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -157,6 +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 @@ -178,9 +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; @@ -193,17 +201,13 @@ 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_SF: vsi->alloc_txq = 1; @@ -567,6 +571,8 @@ 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_PF: case ICE_VSI_SF: @@ -827,7 +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; } /** @@ -1173,12 +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); @@ -1420,6 +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); } @@ -1764,9 +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)); @@ -2051,12 +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); @@ -2071,19 +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); + } } /** @@ -2514,7 +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) @@ -2582,7 +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; @@ -2595,12 +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_hint in the IRQ descriptor */ - irq_update_affinity_hint(irq_num, NULL); synchronize_irq(irq_num); devm_free_irq(ice_pf_to_dev(pf), irq_num, vsi->q_vectors[i]); } @@ -2755,11 +2805,18 @@ void ice_vsi_set_napi_queues(struct ice_vsi *vsi) void ice_vsi_clear_napi_queues(struct ice_vsi *vsi) { struct net_device *netdev = vsi->netdev; - int q_idx; + int q_idx, v_idx; if (!netdev) return; + /* 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]; + + netif_napi_set_irq(&q_vector->napi, -1); + } + ice_for_each_txq(vsi, q_idx) netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX, NULL); @@ -2811,9 +2868,11 @@ int ice_vsi_release(struct ice_vsi *vsi) /* 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); + 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); @@ -3882,15 +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) + 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); + } } /** @@ -3937,24 +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 eabb35834a24..654516c5fc3e 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -29,7 +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); @@ -105,10 +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 c3a0fb97c5ee..20d3baf955e3 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -1717,7 +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); @@ -2401,11 +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); @@ -2424,11 +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); } @@ -2528,34 +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 */ @@ -2618,19 +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_update_affinity_hint(irq_num, &q_vector->affinity_mask); } err = ice_set_cpu_rx_rmap(vsi); @@ -2646,9 +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_update_affinity_hint(irq_num, NULL); devm_free_irq(dev, irq_num, &vsi->q_vectors[vector]); } return err; @@ -3304,22 +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) { @@ -3689,6 +3631,15 @@ 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); } @@ -4066,8 +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; @@ -5065,16 +5015,16 @@ static int ice_init_devlink(struct ice_pf *pf) return err; ice_devlink_init_regions(pf); - ice_health_init(pf); ice_devlink_register(pf); + ice_health_init(pf); return 0; } static void ice_deinit_devlink(struct ice_pf *pf) { - ice_devlink_unregister(pf); ice_health_deinit(pf); + ice_devlink_unregister(pf); ice_devlink_destroy_regions(pf); ice_devlink_unregister_params(pf); } @@ -5087,6 +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; @@ -5186,11 +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); @@ -5198,6 +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); @@ -5221,8 +5179,8 @@ 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); @@ -6597,6 +6555,18 @@ ice_set_features(struct net_device *netdev, netdev_features_t features) 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; } @@ -8360,11 +8330,16 @@ 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; @@ -8373,7 +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: @@ -8382,20 +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; } @@ -9340,27 +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; @@ -9374,7 +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; @@ -9410,7 +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_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index e26320ce52ca..b79a148ed0f2 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -298,18 +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 */ @@ -972,28 +984,6 @@ ice_ptp_release_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx) } /** - * ice_ptp_init_tx_eth56g - 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 port. ETH56G PHYs - * have independent memory blocks for all ports. - * - * Return: 0 for success, -ENOMEM when failed to allocate Tx tracker - */ -static int ice_ptp_init_tx_eth56g(struct ice_pf *pf, struct ice_ptp_tx *tx, - u8 port) -{ - tx->block = port; - tx->offset = 0; - tx->len = INDEX_PER_PORT_ETH56G; - tx->has_ready_bitmap = 1; - - return ice_ptp_alloc_tx_tracker(tx); -} - -/** * ice_ptp_init_tx_e82x - Initialize tracking for Tx timestamps * @pf: Board private structure * @tx: the Tx tracking structure to initialize @@ -1003,9 +993,11 @@ static int ice_ptp_init_tx_eth56g(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 = ICE_GET_QUAD_NUM(port); tx->offset = (port % ICE_PORTS_PER_QUAD) * INDEX_PER_PORT_E82X; @@ -1016,24 +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); } @@ -1318,20 +1313,21 @@ 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); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - err = ice_stop_phy_timer_eth56g(hw, port, true); + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: + err = 0; break; - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: kthread_cancel_delayed_work_sync(&ptp_port->ov_work); 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; } @@ -1361,19 +1357,17 @@ 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); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - err = ice_start_phy_timer_eth56g(hw, port); + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: + err = 0; break; - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: /* Start the PHY timer in Vernier mode */ kthread_cancel_delayed_work_sync(&ptp_port->ov_work); @@ -1398,6 +1392,9 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port) 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; } @@ -1432,12 +1429,14 @@ void ice_ptp_link_change(struct ice_pf *pf, bool linkup) /* Skip HW writes if reset is in progress */ if (pf->hw.reset_ongoing) return; - switch (ice_get_phy_model(hw)) { - case ICE_PHY_E810: - /* Do not reconfigure E810 PHY */ + + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: + /* Do not reconfigure E810 or E830 PHY */ return; - case ICE_PHY_ETH56G: - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: + case ICE_MAC_GENERIC_3K_E825: ice_ptp_port_phy_restart(ptp_port); return; default: @@ -1465,46 +1464,45 @@ static int ice_ptp_cfg_phy_interrupt(struct ice_pf *pf, bool ena, u32 threshold) ice_ptp_reset_ts_memory(hw); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: { - int port; + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: + return 0; + case ICE_MAC_GENERIC: { + int quad; - for (port = 0; port < hw->ptp.num_lports; port++) { + for (quad = 0; quad < ICE_GET_QUAD_NUM(hw->ptp.num_lports); + quad++) { int err; - err = ice_phy_cfg_intr_eth56g(hw, port, ena, threshold); + err = ice_phy_cfg_intr_e82x(hw, quad, ena, threshold); if (err) { - dev_err(dev, "Failed to configure PHY interrupt for port %d, err %d\n", - port, err); + dev_err(dev, "Failed to configure PHY interrupt for quad %d, err %d\n", + quad, err); return err; } } return 0; } - case ICE_PHY_E82X: { - int quad; + case ICE_MAC_GENERIC_3K_E825: { + int port; - for (quad = 0; quad < ICE_GET_QUAD_NUM(hw->ptp.num_lports); - quad++) { + for (port = 0; port < hw->ptp.num_lports; port++) { int err; - err = ice_phy_cfg_intr_e82x(hw, quad, ena, threshold); + err = ice_phy_cfg_intr_eth56g(hw, port, ena, threshold); if (err) { - dev_err(dev, "Failed to configure PHY interrupt for quad %d, err %d\n", - quad, err); + dev_err(dev, "Failed to configure PHY interrupt for port %d, err %d\n", + port, err); return err; } } return 0; } - case ICE_PHY_E810: - return 0; - case ICE_PHY_UNSUP: + case ICE_MAC_UNKNOWN: default: - dev_warn(dev, "%s: Unexpected PHY model %d\n", __func__, - ice_get_phy_model(hw)); return -EOPNOTSUPP; } } @@ -1629,14 +1627,6 @@ static int ice_ptp_cfg_extts(struct ice_pf *pf, struct ptp_extts_request *rq, int pin_desc_idx; u8 tmr_idx; - /* Reject requests with unsupported flags */ - - if (rq->flags & ~(PTP_ENABLE_FEATURE | - PTP_RISING_EDGE | - PTP_FALLING_EDGE | - PTP_STRICT_FLAGS)) - return -EOPNOTSUPP; - tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; chan = rq->index; @@ -1740,7 +1730,7 @@ static int ice_ptp_write_perout(struct ice_hw *hw, unsigned int chan, /* 0. Reset mode & out_en in AUX_OUT */ wr32(hw, GLTSYN_AUX_OUT(chan, tmr_idx), 0); - if (ice_is_e825c(hw)) { + if (hw->mac_type == ICE_MAC_GENERIC_3K_E825) { int err; /* Enable/disable CGU 1PPS output for E825C */ @@ -1783,6 +1773,7 @@ static int ice_ptp_write_perout(struct ice_hw *hw, unsigned int chan, 8 + chan + (tmr_idx * 4)); wr32(hw, GLGEN_GPIO_CTL(gpio_pin), val); + ice_flush(hw); return 0; } @@ -1806,9 +1797,6 @@ static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq, struct ice_hw *hw = &pf->hw; int pin_desc_idx; - if (rq->flags & ~PTP_PEROUT_PHASE) - return -EOPNOTSUPP; - pin_desc_idx = ice_ptp_find_pin_idx(pf, PTP_PF_PEROUT, rq->index); if (pin_desc_idx < 0) return -EIO; @@ -1824,7 +1812,7 @@ static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq, 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->ptp.phy_model == ICE_PHY_E82X) { + 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; } @@ -1843,9 +1831,10 @@ static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq, 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 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); + 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; @@ -2078,7 +2067,7 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts) /* For Vernier mode on E82X, we need to recalibrate after new settime. * Start with marking timestamps as invalid. */ - if (ice_get_phy_model(hw) == ICE_PHY_E82X) { + 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"); @@ -2102,7 +2091,7 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts) ice_ptp_enable_all_perout(pf); /* Recalibrate and re-enable timestamp blocks for E822/E823 */ - if (ice_get_phy_model(hw) == ICE_PHY_E82X) + if (hw->mac_type == ICE_MAC_GENERIC) ice_ptp_restart_all_phy(pf); exit: if (err) { @@ -2180,93 +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->cycles = hh_ts; - system->cs_id = CSID_X86_ART; - /* 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); - - if (i == MAX_HH_CTL_LOCK_TRIES) - return -ETIMEDOUT; + lock = rd32(hw, cfg->lock_reg); + lock &= ~cfg->lock_busy; + wr32(hw, cfg->lock_reg, lock); - 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 * @@ -2274,22 +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 @@ -2550,13 +2617,9 @@ static int ice_ptp_parse_sdp_entries(struct ice_pf *pf, __le16 *entries, */ 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)) - pf->ptp.info.getcrosststamp = ice_ptp_getcrosststamp_e82x; + pf->ptp.info.getcrosststamp = ice_ptp_getcrosststamp; -#endif /* CONFIG_ICE_HWTS */ - if (ice_is_e825c(&pf->hw)) { + 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 { @@ -2623,6 +2686,28 @@ err: } /** + * ice_ptp_set_funcs_e830 - Set specialized functions for E830 support + * @pf: Board private structure + * + * 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 E830 + * devices. + */ +static void ice_ptp_set_funcs_e830(struct ice_pf *pf) +{ +#ifdef CONFIG_ICE_HWTS + if (pcie_ptm_enabled(pf->pdev) && boot_cpu_has(X86_FEATURE_ART)) + pf->ptp.info.getcrosststamp = ice_ptp_getcrosststamp; + +#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); +} + +/** * ice_ptp_set_caps - Set PTP capabilities * @pf: Board private structure */ @@ -2644,10 +2729,25 @@ static void ice_ptp_set_caps(struct ice_pf *pf) info->enable = ice_ptp_gpio_enable; info->verify = ice_verify_pin; - if (ice_is_e810(&pf->hw)) + 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); - else + 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; + } } /** @@ -2758,6 +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 * @@ -2777,7 +2936,7 @@ 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)) @@ -2824,6 +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 @@ -2831,6 +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) @@ -2846,6 +3032,9 @@ 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 */ @@ -2912,14 +3101,12 @@ 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); @@ -2969,12 +3156,6 @@ err: dev_err(ice_pf_to_dev(pf), "PTP reset failed %d\n", err); } -static bool ice_is_primary(struct ice_hw *hw) -{ - return ice_is_e825c(hw) && ice_is_dual(hw) ? - !!(hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_PRIMARY_M) : true; -} - static int ice_ptp_setup_adapter(struct ice_pf *pf) { if (!ice_pf_src_tmr_owned(pf) || !ice_is_primary(&pf->hw)) @@ -2990,7 +3171,7 @@ static int ice_ptp_setup_pf(struct ice_pf *pf) struct ice_ptp *ctrl_ptp = ice_get_ctrl_ptp(pf); struct ice_ptp *ptp = &pf->ptp; - if (WARN_ON(!ctrl_ptp) || ice_get_phy_model(&pf->hw) == ICE_PHY_UNSUP) + if (WARN_ON(!ctrl_ptp) || pf->hw.mac_type == ICE_MAC_UNKNOWN) return -ENODEV; INIT_LIST_HEAD(&ptp->port.list_node); @@ -3007,7 +3188,7 @@ static void ice_ptp_cleanup_pf(struct ice_pf *pf) { struct ice_ptp *ptp = &pf->ptp; - if (ice_get_phy_model(&pf->hw) != ICE_PHY_UNSUP) { + 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); @@ -3127,6 +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) { @@ -3134,16 +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 (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_ptp_init_tx_eth56g(pf, &ptp_port->tx, - ptp_port->port_num); - 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: @@ -3162,8 +3343,8 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port) */ static void ice_ptp_init_tx_interrupt_mode(struct ice_pf *pf) { - switch (ice_get_phy_model(&pf->hw)) { - 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. */ @@ -3194,17 +3375,16 @@ void ice_ptp_init(struct ice_pf *pf) { struct ice_ptp *ptp = &pf->ptp; struct ice_hw *hw = &pf->hw; - int lane_num, err; + int err; ptp->state = ICE_PTP_INITIALIZING; - lane_num = ice_get_phy_lane_number(hw); - if (lane_num < 0) { - err = lane_num; + if (hw->lane_num < 0) { + err = hw->lane_num; goto err_exit; } + ptp->port.port_num = hw->lane_num; - ptp->port.port_num = (u8)lane_num; ice_ptp_init_hw(hw); ice_ptp_init_tx_interrupt_mode(pf); diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index a1d0e988c084..3b769a0cad00 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -128,8 +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_ETH56G 64 +#define INDEX_PER_PORT 64 /** * struct ice_ptp_port - data used to initialize an external port for PTP @@ -304,6 +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); @@ -342,6 +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) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h index ac46d1183300..003cdfada3ca 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h @@ -10,70 +10,25 @@ /* 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, - 0x126000, - 0x1BA000, - 0x24E000, - 0x2E2000, - }, - /* step */ - 0x98, + [ETH56G_PHY_REG_PTP] = { + .base_addr = 0x092000, + .step = 0x98, }, - /* ETH56G_PHY_MEM_PTP */ - { - /* base_addr */ - { - 0x093000, - 0x127000, - 0x1BB000, - 0x24F000, - 0x2E3000, - }, - /* step */ - 0x200, + [ETH56G_PHY_MEM_PTP] = { + .base_addr = 0x093000, + .step = 0x200, }, - /* ETH56G_PHY_REG_XPCS */ - { - /* base_addr */ - { - 0x000000, - 0x009400, - 0x128000, - 0x1BC000, - 0x250000, - }, - /* step */ - 0x21000, + [ETH56G_PHY_REG_XPCS] = { + .base_addr = 0x000000, + .step = 0x21000, }, - /* ETH56G_PHY_REG_MAC */ - { - /* base_addr */ - { - 0x085000, - 0x119000, - 0x1AD000, - 0x241000, - 0x2D5000, - }, - /* step */ - 0x1000, + [ETH56G_PHY_REG_MAC] = { + .base_addr = 0x085000, + .step = 0x1000, }, - /* ETH56G_PHY_REG_GPCS */ - { - /* base_addr */ - { - 0x084000, - 0x118000, - 0x1AC000, - 0x240000, - 0x2D4000, - }, - /* step */ - 0x400, + [ETH56G_PHY_REG_GPCS] = { + .base_addr = 0x084000, + .step = 0x400, }, }; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index ec91822e9280..ccac84eb34c9 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -240,7 +240,7 @@ 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 = cgu, + .dest_dev = ice_sbq_dev_cgu, .msg_addr_low = addr }; int err; @@ -272,7 +272,7 @@ 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 = cgu, + .dest_dev = ice_sbq_dev_cgu, .msg_addr_low = addr, .data = val }; @@ -746,7 +746,7 @@ static int ice_init_cgu_e82x(struct ice_hw *hw) int err; /* Disable sticky lock detection so lock err reported is accurate */ - if (ice_is_e825c(hw)) + 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); @@ -756,7 +756,7 @@ static int ice_init_cgu_e82x(struct ice_hw *hw) /* Configure the CGU PLL using the parameters from the function * capabilities. */ - if (ice_is_e825c(hw)) + 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 @@ -827,8 +827,9 @@ static u32 ice_ptp_tmr_cmd_to_port_reg(struct ice_hw *hw, /* Certain hardware families share the same register values for the * port register and source timer register. */ - switch (ice_get_phy_model(hw)) { - case ICE_PHY_E810: + 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; @@ -873,8 +874,12 @@ static u32 ice_ptp_tmr_cmd_to_port_reg(struct ice_hw *hw, */ 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); } @@ -890,11 +895,25 @@ 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. @@ -907,16 +926,24 @@ static void ice_ptp_exec_tmr_cmd(struct ice_hw *hw) * * Return: destination sideband queue PHY device. */ -static enum ice_sbq_msg_dev ice_ptp_get_dest_dev_e825(struct ice_hw *hw, - u8 port) +static enum ice_sbq_dev_id ice_ptp_get_dest_dev_e825(struct ice_hw *hw, + u8 port) { - /* On a single complex E825, PHY 0 is always destination device phy_0 + 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 (port >= hw->ptp.ports_per_phy) - return eth56g_phy_1; + 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 eth56g_phy_0; + return ice_sbq_dev_phy_0; } /** @@ -998,7 +1025,7 @@ static int ice_phy_res_address_eth56g(struct ice_hw *hw, u8 lane, /* 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[0] + + *addr = eth56g_phy_res[res_type].base_addr + lane * eth56g_phy_res[res_type].step + offset; return 0; @@ -1228,7 +1255,7 @@ static int ice_write_quad_ptp_reg_eth56g(struct ice_hw *hw, u8 port, if (port >= hw->ptp.num_lports) return -EIO; - addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base[0] + offset; + addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base_addr + offset; return ice_write_phy_eth56g(hw, port, addr, val); } @@ -1253,7 +1280,7 @@ static int ice_read_quad_ptp_reg_eth56g(struct ice_hw *hw, u8 port, if (port >= hw->ptp.num_lports) return -EIO; - addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base[0] + offset; + addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base_addr + offset; return ice_read_phy_eth56g(hw, port, addr, val); } @@ -1576,9 +1603,8 @@ static int ice_read_ptp_tstamp_eth56g(struct ice_hw *hw, u8 port, u8 idx, * lower 8 bits in the low register, and the upper 32 bits in the high * register. */ - *tstamp = FIELD_PREP(TS_PHY_HIGH_M, hi) | - FIELD_PREP(TS_PHY_LOW_M, lo); - + *tstamp = FIELD_PREP(PHY_40B_HIGH_M, hi) | + FIELD_PREP(PHY_40B_LOW_M, lo); return 0; } @@ -2406,6 +2432,7 @@ int ice_phy_cfg_intr_eth56g(struct ice_hw *hw, u8 port, bool ena, u8 threshold) 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; @@ -2425,8 +2452,13 @@ static int ice_read_phy_and_phc_time_eth56g(struct ice_hw *hw, u8 port, ice_ptp_exec_tmr_cmd(hw); /* Read the captured PHC time from the shadow time registers */ - zo = rd32(hw, GLTSYN_SHTIME_0(tmr_idx)); - lo = rd32(hw, GLTSYN_SHTIME_L(tmr_idx)); + 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 */ @@ -2563,6 +2595,7 @@ 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) { + struct ice_pf *pf = container_of(hw, struct ice_pf, hw); u32 lo, hi; u64 incval; u8 tmr_idx; @@ -2588,8 +2621,13 @@ int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port) if (err) return err; - lo = rd32(hw, GLTSYN_INCVAL_L(tmr_idx)); - hi = rd32(hw, GLTSYN_INCVAL_H(tmr_idx)); + 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); @@ -2620,37 +2658,15 @@ int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port) } /** - * ice_sb_access_ena_eth56g - Enable SB devices (PHY and others) access + * ice_ptp_init_phc_e825 - Perform E825 specific PHC initialization * @hw: pointer to HW struct - * @enable: Enable or disable access * - * Enable sideband devices (PHY and others) access. - */ -static void ice_sb_access_ena_eth56g(struct ice_hw *hw, bool enable) -{ - u32 val = rd32(hw, PF_SB_REM_DEV_CTL); - - if (enable) - val |= BIT(eth56g_phy_0) | BIT(cgu) | BIT(eth56g_phy_1); - else - val &= ~(BIT(eth56g_phy_0) | BIT(cgu) | BIT(eth56g_phy_1)); - - wr32(hw, PF_SB_REM_DEV_CTL, val); -} - -/** - * ice_ptp_init_phc_eth56g - Perform E82X specific PHC initialization - * @hw: pointer to HW struct - * - * Perform PHC initialization steps specific to E82X devices. + * Perform E825-specific PTP hardware clock initialization steps. * - * Return: - * * %0 - success - * * %other - failed to initialize CGU + * Return: 0 on success, negative error code otherwise. */ -static int ice_ptp_init_phc_eth56g(struct ice_hw *hw) +static int ice_ptp_init_phc_e825(struct ice_hw *hw) { - ice_sb_access_ena_eth56g(hw, true); /* Initialize the Clock Generation Unit */ return ice_init_cgu_e82x(hw); } @@ -2729,10 +2745,7 @@ static void ice_ptp_init_phy_e825(struct ice_hw *hw) { struct ice_ptp_hw *ptp = &hw->ptp; struct ice_eth56g_params *params; - u32 phy_rev; - int err; - ptp->phy_model = ICE_PHY_ETH56G; params = &ptp->phy.eth56g; params->onestep_ena = false; params->peer_delay = 0; @@ -2740,11 +2753,6 @@ static void ice_ptp_init_phy_e825(struct ice_hw *hw) params->num_phys = 2; ptp->ports_per_phy = 4; ptp->num_lports = params->num_phys * ptp->ports_per_phy; - - ice_sb_access_ena_eth56g(hw, true); - err = ice_read_phy_eth56g(hw, hw->pf_id, PHY_REG_REVISION, &phy_rev); - if (err || phy_rev != PHY_REVISION_ETH56G) - ptp->phy_model = ICE_PHY_UNSUP; } /* E822 family functions @@ -2777,7 +2785,7 @@ static void ice_fill_phy_msg_e82x(struct ice_hw *hw, msg->msg_addr_high = P_Q1_H(P_4_BASE + offset, phy_port); } - msg->dest_dev = rmn_0; + msg->dest_dev = ice_sbq_dev_phy_0; } /** @@ -3100,7 +3108,7 @@ static int ice_fill_quad_msg_e82x(struct ice_hw *hw, 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_GET_QUAD_NUM(hw->ptp.ports_per_phy))) addr = Q_0_BASE + offset; @@ -3219,7 +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 = FIELD_PREP(TS_PHY_HIGH_M, hi) | FIELD_PREP(TS_PHY_LOW_M, lo); + *tstamp = FIELD_PREP(PHY_40B_HIGH_M, hi) | + FIELD_PREP(PHY_40B_LOW_M, lo); return 0; } @@ -4792,7 +4801,6 @@ int ice_phy_cfg_intr_e82x(struct ice_hw *hw, u8 quad, bool ena, u8 threshold) */ static void ice_ptp_init_phy_e82x(struct ice_ptp_hw *ptp) { - ptp->phy_model = ICE_PHY_E82X; ptp->num_lports = 8; ptp->ports_per_phy = 8; } @@ -4819,7 +4827,7 @@ 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, ICE_AQ_FLAG_RD); if (err) { @@ -4849,7 +4857,7 @@ 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, ICE_AQ_FLAG_RD); @@ -4986,7 +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; } @@ -5049,8 +5058,7 @@ static int ice_ptp_init_phc_e810(struct ice_hw *hw) u8 tmr_idx; int err; - /* Ensure synchronization delay is zero */ - wr32(hw, GLTSYN_SYNC_DLAY, 0); + 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), @@ -5316,68 +5324,6 @@ ice_get_phy_tx_tstamp_ready_e810(struct ice_hw *hw, u8 port, u64 *tstamp_ready) */ /** - * 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 * @hw: pointer to the hw struct * @data: pointer to data to be read from the GPIO controller @@ -5442,37 +5388,6 @@ int ice_write_sma_ctrl(struct ice_hw *hw, u8 data) } /** - * ice_read_pca9575_reg - * @hw: pointer to the hw struct - * @offset: GPIO controller register offset - * @data: pointer to data to be read from the GPIO controller - * - * Read the register from the GPIO controller - */ -int ice_read_pca9575_reg(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_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 @@ -5538,18 +5453,138 @@ exit: */ static void ice_ptp_init_phy_e810(struct ice_ptp_hw *ptp) { - ptp->phy_model = ICE_PHY_E810; 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; + + 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)); +} + +/** + * 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_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. */ /** @@ -5612,14 +5647,22 @@ void ice_ptp_init_hw(struct ice_hw *hw) { struct ice_ptp_hw *ptp = &hw->ptp; - if (ice_is_e822(hw) || ice_is_e823(hw)) - ice_ptp_init_phy_e82x(ptp); - else if (ice_is_e810(hw)) + switch (hw->mac_type) { + case ICE_MAC_E810: ice_ptp_init_phy_e810(ptp); - else if (ice_is_e825c(hw)) + 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); - else - ptp->phy_model = ICE_PHY_UNSUP; + break; + default: + return; + } } /** @@ -5640,11 +5683,11 @@ void ice_ptp_init_hw(struct ice_hw *hw) static int ice_ptp_write_port_cmd(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd) { - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_ptp_write_port_cmd_eth56g(hw, port, cmd); - case ICE_PHY_E82X: + 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; } @@ -5705,9 +5748,11 @@ 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 (ice_get_phy_model(hw)) { - case ICE_PHY_E810: + 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; } @@ -5778,23 +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 (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - err = ice_ptp_prep_phy_time_eth56g(hw, - (u32)(time & 0xFFFFFFFF)); - break; - 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; } @@ -5826,20 +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 (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - err = ice_ptp_prep_phy_incval_eth56g(hw, incval); - break; - 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; } @@ -5899,16 +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 (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - err = ice_ptp_prep_phy_adj_eth56g(hw, adj); - break; - 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; } @@ -5932,13 +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 (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_read_ptp_tstamp_eth56g(hw, block, idx, tstamp); - 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; } @@ -5962,13 +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 (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_clear_ptp_tstamp_eth56g(hw, block, idx); - 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; } @@ -6025,14 +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 (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - ice_ptp_reset_ts_memory_eth56g(hw); - break; - 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; } @@ -6054,13 +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 (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_ptp_init_phc_eth56g(hw); - 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; } @@ -6079,17 +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 (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_get_phy_tx_tstamp_ready_eth56g(hw, block, - tstamp_ready); - 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; } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h index 6779ce120515..83f20fa7ace7 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -65,14 +65,14 @@ enum ice_eth56g_link_spd { /** * struct ice_phy_reg_info_eth56g - ETH56G PHY register parameters - * @base: base address for each PHY block + * @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[NUM_ETH56G_PHY_RES]; + u32 base_addr; u32 step; }; @@ -324,6 +324,7 @@ extern const struct ice_vernier_info_e82x e822_vernier[NUM_ICE_PTP_LNK_SPD]; */ #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); @@ -395,7 +396,6 @@ int ice_phy_cfg_intr_e82x(struct ice_hw *hw, u8 quad, bool ena, u8 threshold); /* E810 family functions */ int ice_read_sma_ctrl(struct ice_hw *hw, u8 *data); int ice_write_sma_ctrl(struct ice_hw *hw, u8 data); -int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, 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); @@ -431,23 +431,19 @@ int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port); */ static inline u64 ice_get_base_incval(struct ice_hw *hw) { - switch (hw->ptp.phy_model) { - case ICE_PHY_ETH56G: - return ICE_ETH56G_NOMINAL_INCVAL; - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: return ICE_PTP_NOMINAL_INCVAL_E810; - case ICE_PHY_E82X: + 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; } } -static inline bool ice_is_dual(struct ice_hw *hw) -{ - return !!(hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_DUAL_M); -} - #define PFTSYN_SEM_BYTES 4 #define ICE_PTP_CLOCK_INDEX_0 0x00 @@ -650,18 +646,25 @@ static inline bool ice_is_dual(struct ice_hw *hw) /* E810 timer command register */ #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 GENMASK(7, 0) -#define TS_PHY_HIGH_M GENMASK_ULL(39, 8) - #define BYTES_PER_IDX_ADDR_L_U 8 #define BYTES_PER_IDX_ADDR_L 4 @@ -772,36 +775,19 @@ static inline bool ice_is_dual(struct ice_hw *hw) #define PHY_MAC_XIF_TS_SFD_ENA_M ICE_M(0x1, 20) #define PHY_MAC_XIF_GMII_TS_SEL_M ICE_M(0x1, 21) -/* GPCS config register */ -#define PHY_GPCS_CONFIG_REG0 0x268 -#define PHY_GPCS_CONFIG_REG0_TX_THR_M ICE_M(0xF, 24) -#define PHY_GPCS_BITSLIP 0x5C - #define PHY_TS_INT_CONFIG_THRESHOLD_M ICE_M(0x3F, 0) #define PHY_TS_INT_CONFIG_ENA_M BIT(6) -/* 1-step PTP config */ -#define PHY_PTP_1STEP_CONFIG 0x270 -#define PHY_PTP_1STEP_T1S_UP64_M ICE_M(0xF, 4) -#define PHY_PTP_1STEP_T1S_DELTA_M ICE_M(0xF, 8) -#define PHY_PTP_1STEP_PEER_DELAY(_port) (0x274 + 4 * (_port)) -#define PHY_PTP_1STEP_PD_ADD_PD_M ICE_M(0x1, 0) -#define PHY_PTP_1STEP_PD_DELAY_M ICE_M(0x3fffffff, 1) -#define PHY_PTP_1STEP_PD_DLY_V_M ICE_M(0x1, 31) - /* 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_REVISION 0x85000 - #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_GPCS_BITSLIP 0x5C #define PHY_REG_SD_BIT_SLIP(_port_offset) (0x29C + 4 * (_port_offset)) #define PHY_REVISION_ETH56G 0x10200 #define PHY_VENDOR_TXLANE_THRESH 0x2000C @@ -821,7 +807,21 @@ static inline bool ice_is_dual(struct ice_hw *hw) #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 fb7a1b9a4313..cb08746556a6 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.c +++ b/drivers/net/ethernet/intel/ice/ice_repr.c @@ -219,7 +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: @@ -336,6 +337,7 @@ void ice_repr_destroy(struct ice_repr *repr) static void ice_repr_rem_vf(struct ice_repr *repr) { 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); @@ -417,6 +419,10 @@ static int ice_repr_add_vf(struct ice_repr *repr) 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; @@ -429,6 +435,8 @@ static int ice_repr_add_vf(struct ice_repr *repr) 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); diff --git a/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h b/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h index 3b0054faf70c..183dd5457d6a 100644 --- a/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h @@ -46,13 +46,10 @@ struct ice_sbq_evt_desc { u8 data[24]; }; -enum ice_sbq_msg_dev { - eth56g_phy_0 = 0x02, - rmn_0 = 0x02, - rmn_1 = 0x03, - rmn_2 = 0x04, - cgu = 0x06, - eth56g_phy_1 = 0x0D, +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_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index b83f99c01d91..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 */ @@ -177,6 +158,7 @@ void ice_free_vfs(struct ice_pf *pf) 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 */ @@ -193,16 +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 */ - if (!ice_is_feature_supported(pf, ICE_F_MBX_LIMIT)) - 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); @@ -372,40 +347,6 @@ void ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector) } /** - * 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; -} - -/** * ice_set_per_vf_res - check if vectors and queues are available * @pf: pointer to the PF structure * @num_vfs: the number of SR-IOV VFs being configured @@ -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; @@ -856,16 +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); @@ -918,7 +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; } @@ -992,16 +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) @@ -1020,7 +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; @@ -1032,7 +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 */ @@ -1105,20 +975,15 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count) 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; @@ -1147,7 +1012,8 @@ unroll: vf->num_msix = prev_msix; vf->num_vf_qs = prev_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) { ice_put_vf(vf); return -EINVAL; @@ -1537,6 +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", diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 4a91e0aaf0a5..9d9a7edd3618 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -3146,7 +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; @@ -5978,7 +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 diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index ea39b999a0d0..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 */ @@ -684,26 +681,26 @@ static int ice_tc_setup_action(struct net_device *filter_dev, 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; } @@ -716,13 +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"); + "The action is not supported for this netdevice"); return -EINVAL; } @@ -767,10 +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; @@ -785,7 +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; @@ -814,6 +959,11 @@ 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; @@ -846,11 +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 */ @@ -985,7 +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; @@ -1021,7 +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; @@ -1056,8 +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: @@ -1071,6 +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"); @@ -1463,11 +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); @@ -1551,6 +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; @@ -1726,6 +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; } @@ -1939,6 +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; @@ -1975,14 +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; @@ -1999,7 +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; @@ -2042,10 +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; @@ -2080,7 +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 d84f153517ec..8a3ab2f22af9 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.h @@ -211,13 +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_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 9c9ea4c1b93b..0e5107fe62ad 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -1809,6 +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 { @@ -1958,6 +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: @@ -2415,17 +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) && vsi->type != ICE_VSI_SF) - ice_eswitch_set_target_vsi(skb, &offload); if (offload.cd_qw1 & ICE_TX_DESC_DTYPE_CTX) { struct ice_tx_ctx_desc *cdesc; @@ -2439,7 +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 806bce701df3..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; }; @@ -366,6 +367,7 @@ struct ice_rx_ring { #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; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index 2719f0e20933..45cfaabc41cb 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -81,6 +81,23 @@ ice_rx_hash_to_skb(const struct ice_rx_ring *rx_ring, } /** + * 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)); +} + +/** * ice_rx_csum - Indicate in skb if checksum is good * @ring: the ring we care about * @skb: skb currently being received and modified @@ -107,6 +124,15 @@ ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb, 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; + } + /* check if HW has decoded the packet and checksum */ if (!(rx_status0 & BIT(ICE_RX_FLEX_DESC_STATUS0_L3L4P_S))) return; diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 33a1a5934c0d..3d68f465952d 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -19,6 +19,7 @@ #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) { @@ -695,7 +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 @@ -718,9 +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 @@ -871,14 +871,6 @@ union ice_phy_params { struct ice_eth56g_params eth56g; }; -/* PHY model */ -enum ice_phy_model { - ICE_PHY_UNSUP = -1, - ICE_PHY_E810 = 1, - ICE_PHY_E82X, - ICE_PHY_ETH56G, -}; - /* Global Link Topology */ enum ice_global_link_topo { ICE_LINK_TOPO_UP_TO_2_LINKS, @@ -888,7 +880,6 @@ enum ice_global_link_topo { }; struct ice_ptp_hw { - enum ice_phy_model phy_model; union ice_phy_params phy; u8 num_lports; u8 ports_per_phy; @@ -979,6 +970,7 @@ struct ice_hw { u8 intrl_gran; struct ice_ptp_hw ptp; + s8 lane_num; /* Active package version (currently active) */ struct ice_pkg_ver active_pkg_ver; diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index c7c0c2f50c26..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)); } @@ -1036,6 +1037,14 @@ void ice_initialize_vf_entry(struct ice_vf *vf) 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 @@ -1393,3 +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 4261fe1c2bcd..482f4285fd35 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -124,6 +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 */ @@ -131,6 +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) @@ -146,6 +151,9 @@ 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]; }; @@ -177,6 +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. @@ -242,6 +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 0c7e77c0a09f..5392b0404986 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h @@ -24,6 +24,7 @@ #endif 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_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index ff4ad788d96a..eeeb9968e477 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -498,6 +498,9 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) 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; @@ -562,7 +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; @@ -1862,15 +1865,33 @@ static int ice_vc_cfg_q_bw(struct ice_vf *vf, u8 *msg) 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) + 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) + 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->max_tx_rate); + 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++) { @@ -1900,13 +1921,21 @@ err: */ 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; - u16 quanta_prof_id, quanta_size, start_qid, end_qid, i; 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; @@ -1918,8 +1947,6 @@ static int ice_vc_cfg_q_quanta(struct ice_vf *vf, u8 *msg) goto err; } - end_qid = qquanta->queue_select.start_queue_id + - qquanta->queue_select.num_queues; 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", @@ -1948,7 +1975,6 @@ static int ice_vc_cfg_q_quanta(struct ice_vf *vf, u8 *msg) goto err; } - start_qid = qquanta->queue_select.start_queue_id; for (i = start_qid; i < end_qid; i++) vsi->tx_rings[i]->quanta_prof_id = quanta_prof_id; @@ -1975,6 +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); @@ -2104,9 +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); } } @@ -2234,6 +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 @@ -2251,10 +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) { @@ -2269,6 +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); @@ -2363,6 +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; } @@ -3031,8 +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 = {}; struct ice_pf *pf = vf->pf; + u64 rxdid; if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; @@ -3044,7 +3123,7 @@ static int ice_vc_query_rxdid(struct ice_vf *vf) goto err; } - rxdid.supported_rxdids = pf->supported_rxdids; + rxdid = pf->supported_rxdids; err: return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_SUPPORTED_RXDIDS, @@ -4092,6 +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, @@ -4128,6 +4260,8 @@ static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = { .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. */ @@ -4188,7 +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; } @@ -4264,6 +4397,8 @@ static const struct ice_virtchnl_ops ice_virtchnl_repr_ops = { .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, }; /** @@ -4501,6 +4636,12 @@ error_handler: 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 0c629aef9baf..222990f229d5 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.h @@ -26,6 +26,9 @@ #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. @@ -72,6 +75,9 @@ struct ice_virtchnl_ops { 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 c105a82ee136..a3d1579a619a 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c @@ -84,6 +84,12 @@ 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, @@ -110,6 +116,7 @@ static const struct allowlist_opcode_info 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 14e3f0f89c78..1cca9b2262e8 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c @@ -832,21 +832,27 @@ 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); + 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; - u16 udp_port = 0; - pkt_buf = kzalloc(proto->raw.pkt_len, GFP_KERNEL); - msk_buf = kzalloc(proto->raw.pkt_len, GFP_KERNEL); + 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, proto->raw.pkt_len); - memcpy(msk_buf, proto->raw.mask, proto->raw.pkt_len); + memcpy(pkt_buf, proto->raw.spec, pkt_len); + memcpy(msk_buf, proto->raw.mask, pkt_len); hw = &pf->hw; @@ -862,7 +868,7 @@ ice_vc_fdir_parse_raw(struct ice_vf *vf, 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, proto->raw.pkt_len, &rslt); + status = ice_parser_run(psr, pkt_buf, pkt_len, &rslt); if (status) goto err_parser_destroy; @@ -876,7 +882,7 @@ ice_vc_fdir_parse_raw(struct ice_vf *vf, } status = ice_parser_profile_init(&rslt, pkt_buf, msk_buf, - proto->raw.pkt_len, ICE_BLK_FD, + pkt_len, ICE_BLK_FD, conf->prof); if (status) goto err_parser_profile_init; @@ -885,7 +891,7 @@ ice_vc_fdir_parse_raw(struct ice_vf *vf, ice_parser_profile_dump(hw, conf->prof); /* Store raw flow info into @conf */ - conf->pkt_len = proto->raw.pkt_len; + conf->pkt_len = pkt_len; conf->pkt_buf = pkt_buf; conf->parser_ena = true; @@ -1515,7 +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); @@ -1910,7 +1916,7 @@ 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); @@ -2091,6 +2097,11 @@ 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) || diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 8975d2971bc3..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" @@ -989,7 +990,8 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, 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(xsk_pool, descs[i].addr); diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h index 45adeb513253..8dc5d55e26c5 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.h +++ b/drivers/net/ethernet/intel/ice/ice_xsk.h @@ -7,14 +7,6 @@ #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 diff --git a/drivers/net/ethernet/intel/idpf/Kconfig b/drivers/net/ethernet/intel/idpf/Kconfig index 1addd663acad..2c359a8551c7 100644 --- a/drivers/net/ethernet/intel/idpf/Kconfig +++ b/drivers/net/ethernet/intel/idpf/Kconfig @@ -4,6 +4,7 @@ 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 diff --git a/drivers/net/ethernet/intel/idpf/Makefile b/drivers/net/ethernet/intel/idpf/Makefile index 2ce01a0b5898..83ac5e296382 100644 --- a/drivers/net/ethernet/intel/idpf/Makefile +++ b/drivers/net/ethernet/intel/idpf/Makefile @@ -17,3 +17,6 @@ idpf-y := \ 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 66544faab710..1e812c3f62f9 100644 --- a/drivers/net/ethernet/intel/idpf/idpf.h +++ b/drivers/net/ethernet/intel/idpf/idpf.h @@ -143,6 +143,7 @@ enum idpf_vport_state { * @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 @@ -153,6 +154,7 @@ struct idpf_netdev_priv { 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); }; /** @@ -290,6 +294,9 @@ struct idpf_port_stats { * @port_stats: per port csum, header split, and other offload stats * @link_up: True if link is up * @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; @@ -334,6 +341,10 @@ struct idpf_vport { bool link_up; 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; }; /** @@ -478,6 +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 @@ -530,6 +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; @@ -587,6 +606,8 @@ struct idpf_adapter { struct mutex vector_lock; struct mutex queue_lock; struct mutex vc_buf_lock; + + struct idpf_ptp *ptp; }; /** @@ -629,13 +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 |\ @@ -644,11 +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_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 41e4bd49402a..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 @@ -149,6 +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 */ @@ -159,6 +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 59b1a1a09996..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 @@ -1312,6 +1313,71 @@ static int idpf_get_link_ksettings(struct net_device *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, @@ -1336,6 +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 8c7f8ef8f1a1..7492d1713243 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h +++ b/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h @@ -282,7 +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 a3d6b8f198a8..bab12ecb2df5 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -3,6 +3,7 @@ #include "idpf.h" #include "idpf_virtchnl.h" +#include "idpf_ptp.h" static const struct net_device_ops idpf_netdev_ops; @@ -144,22 +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 */ @@ -349,7 +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) { @@ -703,8 +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; @@ -721,6 +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); @@ -738,6 +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); @@ -766,54 +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 */ @@ -927,15 +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; kfree(vport->rx_ptype_lkup); vport->rx_ptype_lkup = NULL; - unregister_netdev(vport->netdev); - free_netdev(vport->netdev); + 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; } /** @@ -1127,11 +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 @@ -1141,11 +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); @@ -1158,6 +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; } /** @@ -1536,13 +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 @@ -2205,8 +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 @@ -2229,7 +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) @@ -2242,7 +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 @@ -2344,6 +2329,60 @@ void idpf_free_dma_mem(struct idpf_hw *hw, struct idpf_dma_mem *mem) mem->pa = 0; } +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 = { .ndo_open = idpf_open, .ndo_stop = idpf_stop, @@ -2356,4 +2395,6 @@ static const struct net_device_ops idpf_netdev_ops = { .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 b6c515d14cbf..0efd9c0c7a90 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_main.c +++ b/drivers/net/ethernet/intel/idpf/idpf_main.c @@ -87,7 +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); @@ -163,6 +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) { @@ -194,9 +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", - WQ_UNBOUND | WQ_MEM_RECLAIM, 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"); 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 dfd7cf1d9aa0..2e356dd10812 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c @@ -595,7 +595,7 @@ static bool idpf_rx_singleq_is_non_eop(const union virtchnl2_rx_desc *rx_desc) */ static void idpf_rx_singleq_csum(struct idpf_rx_queue *rxq, struct sk_buff *skb, - struct idpf_rx_csum_decoded csum_bits, + struct libeth_rx_csum csum_bits, struct libeth_rx_pt decoded) { bool ipv4, ipv6; @@ -661,10 +661,10 @@ checksum_fail: * * Return: parsed checksum status. **/ -static struct idpf_rx_csum_decoded +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; @@ -696,10 +696,10 @@ idpf_rx_singleq_base_csum(const union virtchnl2_rx_desc *rx_desc) * * Return: parsed checksum status. **/ -static struct idpf_rx_csum_decoded +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); @@ -798,7 +798,7 @@ idpf_rx_singleq_process_skb_fields(struct idpf_rx_queue *rx_q, u16 ptype) { struct libeth_rx_pt decoded = rx_q->rx_ptype_lkup[ptype]; - struct idpf_rx_csum_decoded csum_bits; + struct libeth_rx_csum csum_bits; /* modifies the skb - consumes the enet header */ skb->protocol = eth_type_trans(skb, rx_q->netdev); @@ -900,14 +900,14 @@ bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_rx_queue *rx_q, */ static void idpf_rx_singleq_extract_base_fields(const union virtchnl2_rx_desc *rx_desc, - struct idpf_rx_extracted *fields) + 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); } /** @@ -923,12 +923,12 @@ idpf_rx_singleq_extract_base_fields(const union virtchnl2_rx_desc *rx_desc, */ static void idpf_rx_singleq_extract_flex_fields(const union virtchnl2_rx_desc *rx_desc, - struct idpf_rx_extracted *fields) + 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)); } /** @@ -941,7 +941,7 @@ idpf_rx_singleq_extract_flex_fields(const union virtchnl2_rx_desc *rx_desc, static void idpf_rx_singleq_extract_fields(const struct idpf_rx_queue *rx_q, const union virtchnl2_rx_desc *rx_desc, - struct idpf_rx_extracted *fields) + struct libeth_rqe_info *fields) { if (rx_q->rxdids == VIRTCHNL2_RXDID_1_32B_BASE_M) idpf_rx_singleq_extract_base_fields(rx_desc, fields); @@ -966,7 +966,7 @@ static int idpf_rx_singleq_clean(struct idpf_rx_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; @@ -992,13 +992,13 @@ static int idpf_rx_singleq_clean(struct idpf_rx_queue *rx_q, int budget) idpf_rx_singleq_extract_fields(rx_q, rx_desc, &fields); rx_buf = &rx_q->rx_buf[ntc]; - if (!libeth_rx_sync_for_cpu(rx_buf, fields.size)) + if (!libeth_rx_sync_for_cpu(rx_buf, fields.len)) goto skip_data; if (skb) - idpf_rx_add_frag(rx_buf, skb, fields.size); + idpf_rx_add_frag(rx_buf, skb, fields.len); else - skb = idpf_rx_build_skb(rx_buf, fields.size); + skb = idpf_rx_build_skb(rx_buf, fields.len); /* exit if we failed to retrieve a buffer */ if (!skb) @@ -1033,8 +1033,8 @@ 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->pp->p.napi, skb); diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 9be6a6b59c4e..631679cdaa6f 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -5,6 +5,7 @@ #include <net/libeth/tx.h> #include "idpf.h" +#include "idpf_ptp.h" #include "idpf_virtchnl.h" struct idpf_tx_stash { @@ -1107,6 +1108,8 @@ 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(*vport->txqs), @@ -1121,6 +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; } } @@ -1655,6 +1664,40 @@ static void idpf_tx_handle_sw_marker(struct idpf_tx_queue *tx_q) } /** + * 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_read_tstamp(struct idpf_tx_queue *txq, struct sk_buff *skb) +{ + struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps; + struct idpf_ptp_tx_tstamp_status *tx_tstamp_status; + + tx_tstamp_caps = txq->cached_tstamp_caps; + spin_lock_bh(&tx_tstamp_caps->status_lock); + + 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; + + tx_tstamp_status->skb = skb; + tx_tstamp_status->state = IDPF_PTP_REQUEST; + + /* 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); +} + +/** * idpf_tx_clean_stashed_bufs - clean bufs that were stored for * out of order completions * @txq: queue to clean @@ -1682,6 +1725,11 @@ static void idpf_tx_clean_stashed_bufs(struct idpf_tx_queue *txq, continue; hash_del(&stash->hlist); + + 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); + libeth_tx_complete(&stash->buf, &cp); /* Push shadow buf back onto stack */ @@ -1876,8 +1924,12 @@ static bool idpf_tx_clean_buf_ring(struct idpf_tx_queue *txq, u16 compl_tag, idpf_tx_buf_compl_tag(tx_buf) != compl_tag)) return false; - if (tx_buf->type == LIBETH_SQE_SKB) + 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); + libeth_tx_complete(tx_buf, &cp); + } idpf_tx_clean_buf_ring_bump_ntc(txq, idx, tx_buf); @@ -2127,7 +2179,7 @@ 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); } @@ -2296,7 +2348,7 @@ void idpf_tx_dma_map_error(struct idpf_tx_queue *txq, struct sk_buff *skb, * descriptor. Reset that here. */ tx_desc = &txq->flex_tx[idx]; - memset(tx_desc, 0, sizeof(struct idpf_flex_tx_ctx_desc)); + memset(tx_desc, 0, sizeof(*tx_desc)); if (idx == 0) idx = txq->desc_count; idx--; @@ -2699,10 +2751,10 @@ static 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 * +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; txq->tx_buf[i].type = LIBETH_SQE_CTX; @@ -2732,6 +2784,73 @@ netdev_tx_t idpf_tx_drop_skb(struct idpf_tx_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 @@ -2743,9 +2862,10 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb, 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)) @@ -2765,8 +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 | @@ -2784,6 +2903,12 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb, 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; @@ -2895,7 +3020,7 @@ idpf_rx_hash(const struct idpf_rx_queue *rxq, struct sk_buff *skb, * skb->protocol must be set before this function is called */ static void idpf_rx_csum(struct idpf_rx_queue *rxq, struct sk_buff *skb, - struct idpf_rx_csum_decoded csum_bits, + struct libeth_rx_csum csum_bits, struct libeth_rx_pt decoded) { bool ipv4, ipv6; @@ -2923,7 +3048,7 @@ static void idpf_rx_csum(struct idpf_rx_queue *rxq, struct sk_buff *skb, if (unlikely(csum_bits.l4e)) goto checksum_fail; - if (csum_bits.raw_csum_inv || + if (!csum_bits.raw_csum_valid || decoded.inner_prot == LIBETH_RX_PT_INNER_SCTP) { skb->ip_summed = CHECKSUM_UNNECESSARY; return; @@ -2946,10 +3071,10 @@ checksum_fail: * * Return: parsed checksum status. **/ -static struct idpf_rx_csum_decoded +static struct libeth_rx_csum idpf_rx_splitq_extract_csum_bits(const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc) { - struct idpf_rx_csum_decoded csum = { }; + struct libeth_rx_csum csum = { }; u8 qword0, qword1; qword0 = rx_desc->status_err0_qw0; @@ -2965,9 +3090,9 @@ idpf_rx_splitq_extract_csum_bits(const struct virtchnl2_rx_flex_desc_adv_nic_3 * 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_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; @@ -3013,7 +3138,6 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb, 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); @@ -3022,6 +3146,7 @@ static int idpf_rx_rsc(struct idpf_rx_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 = @@ -3031,6 +3156,7 @@ static int idpf_rx_rsc(struct idpf_rx_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); } @@ -3045,6 +3171,33 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb, } /** + * 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 @@ -3058,7 +3211,7 @@ 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 libeth_rx_csum csum_bits; struct libeth_rx_pt decoded; u16 rx_ptype; @@ -3069,6 +3222,9 @@ idpf_rx_process_skb_fields(struct idpf_rx_queue *rxq, struct sk_buff *skb, /* process RSS/hash */ idpf_rx_hash(rxq, skb, rx_desc, decoded); + if (idpf_queue_has(PTP, rxq)) + idpf_rx_hwtstamp(rxq, rx_desc, skb); + skb->protocol = eth_type_trans(skb, rxq->netdev); skb_record_rx_queue(skb, rxq->idx); @@ -3551,8 +3707,6 @@ void idpf_vport_intr_rel(struct idpf_vport *vport) q_vector->tx = NULL; kfree(q_vector->rx); q_vector->rx = NULL; - - free_cpumask_var(q_vector->affinity_mask); } kfree(vport->q_vectors); @@ -3579,8 +3733,6 @@ 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); kfree(free_irq(irq_num, q_vector)); } } @@ -3768,8 +3920,6 @@ static int idpf_vport_intr_req_irq(struct idpf_vport *vport) "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; @@ -4030,6 +4180,14 @@ static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget) 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); /* Exit the polling mode, but don't re-enable interrupts if stack might @@ -4040,15 +4198,7 @@ static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget) else idpf_vport_intr_set_wb_on_itr(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 && idpf_queue_has(POLL_MODE, - q_vector->tx[0]))) - return budget; - else - return work_done; + return work_done; } /** @@ -4181,7 +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; @@ -4190,12 +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); } } @@ -4239,9 +4390,6 @@ 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; - if (!zalloc_cpumask_var(&q_vector->affinity_mask, GFP_KERNEL)) - goto error; - q_vector->tx = kcalloc(txqs_per_vector, sizeof(*q_vector->tx), GFP_KERNEL); if (!q_vector->tx) diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h index 0f71a6f5557b..c779fe71df99 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h @@ -142,6 +142,7 @@ 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 */ @@ -213,25 +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 @@ -308,6 +290,8 @@ struct idpf_ptype_state { * @__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 { @@ -318,6 +302,7 @@ enum idpf_queue_flags_t { __IDPF_Q_POLL_MODE, __IDPF_Q_CRC_EN, __IDPF_Q_HSPLIT_EN, + __IDPF_Q_PTP, __IDPF_Q_FLAGS_NBITS, }; @@ -401,7 +386,6 @@ struct idpf_intr_reg { * @rx_intr_mode: Dynamic ITR or not * @rx_itr_idx: RX ITR index * @v_idx: Vector index - * @affinity_mask: CPU affinity mask */ struct idpf_q_vector { __cacheline_group_begin_aligned(read_mostly); @@ -438,13 +422,12 @@ struct idpf_q_vector { __cacheline_group_begin_aligned(cold); u16 v_idx; - cpumask_var_t affinity_mask; __cacheline_group_end_aligned(cold); }; libeth_cacheline_set_assert(struct idpf_q_vector, 120, 24 + sizeof(struct napi_struct) + 2 * sizeof(struct dim), - 8 + sizeof(cpumask_var_t)); + 8); struct idpf_rx_queue_stats { u64_stats_t packets; @@ -464,6 +447,7 @@ struct idpf_tx_queue_stats { u64_stats_t q_busy; u64_stats_t skb_drops; u64_stats_t dma_map_errs; + u64_stats_t tstamp_skipped; }; #define IDPF_ITR_DYNAMIC 1 @@ -515,6 +499,7 @@ struct idpf_txq_stash { * @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 * @q_stats: See union idpf_rx_queue_stats * @q_id: Queue id @@ -562,6 +547,7 @@ struct idpf_rx_queue { struct sk_buff *skb; u32 truesize; + u64 cached_phc_time; struct u64_stats_sync stats_sync; struct idpf_rx_queue_stats q_stats; @@ -581,7 +567,7 @@ struct idpf_rx_queue { __cacheline_group_end_aligned(cold); }; libeth_cacheline_set_assert(struct idpf_rx_queue, 64, - 80 + sizeof(struct u64_stats_sync), + 88 + sizeof(struct u64_stats_sync), 32); /** @@ -638,6 +624,8 @@ libeth_cacheline_set_assert(struct idpf_rx_queue, 64, * @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 + * @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 @@ -651,7 +639,7 @@ struct idpf_tx_queue { struct idpf_base_tx_desc *base_tx; struct idpf_base_tx_ctx_desc *base_ctx; union idpf_tx_flex_desc *flex_tx; - struct idpf_flex_tx_ctx_desc *flex_ctx; + union idpf_flex_tx_ctx_desc *flex_ctx; void *desc_ring; }; @@ -687,6 +675,9 @@ struct idpf_tx_queue { 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); @@ -700,7 +691,7 @@ struct idpf_tx_queue { __cacheline_group_end_aligned(cold); }; libeth_cacheline_set_assert(struct idpf_tx_queue, 64, - 88 + sizeof(struct u64_stats_sync), + 112 + sizeof(struct u64_stats_sync), 24); /** @@ -940,7 +931,7 @@ static inline int idpf_q_vector_to_mem(const struct idpf_q_vector *q_vector) if (!q_vector) return NUMA_NO_NODE; - cpu = cpumask_first(q_vector->affinity_mask); + cpu = cpumask_first(&q_vector->napi.config->affinity_mask); return cpu < nr_cpu_ids ? cpu_to_mem(cpu) : NUMA_NO_NODE; } diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c index 3d2413b8684f..07a9f5ae34fd 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c @@ -5,88 +5,7 @@ #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 @@ -235,6 +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 @@ -278,6 +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; @@ -449,8 +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; @@ -900,7 +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 = ∩︀ @@ -3029,6 +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 @@ -3091,6 +3068,7 @@ void idpf_vc_core_deinit(struct idpf_adapter *adapter) if (!remove_in_prog) idpf_vc_xn_shutdown(adapter->vcxn_mngr); + idpf_ptp_release(adapter); idpf_deinit_task(adapter); idpf_intr_rel(adapter); @@ -3158,6 +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; @@ -3192,6 +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); } /** 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 63deb120359c..11b8f6f05799 100644 --- a/drivers/net/ethernet/intel/idpf/virtchnl2.h +++ b/drivers/net/ethernet/intel/idpf/virtchnl2.h @@ -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, }; /** @@ -560,6 +570,14 @@ struct virtchnl2_queue_reg_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]; @@ -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/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 02f340280d20..f34ead8243e9 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -391,7 +391,8 @@ enum e1000_ring_flags_t { IGB_RING_FLAG_RX_LB_VLAN_BSWAP, IGB_RING_FLAG_TX_CTX_IDX, IGB_RING_FLAG_TX_DETECT_HANG, - IGB_RING_FLAG_TX_DISABLED + IGB_RING_FLAG_TX_DISABLED, + IGB_RING_FLAG_RX_ALLOC_FAILED, }; #define ring_uses_large_buffer(ring) \ @@ -722,6 +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); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index d368b753a467..9e9a5900e6e5 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -947,6 +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); @@ -1194,7 +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; @@ -2096,6 +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 @@ -2103,6 +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 */ @@ -2110,8 +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); @@ -2181,12 +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); @@ -3860,8 +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); @@ -4113,8 +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; @@ -4166,8 +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); @@ -5726,11 +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); @@ -9061,6 +9108,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) 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; } @@ -9120,6 +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; } @@ -9136,6 +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; } @@ -9674,8 +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. */ @@ -9734,16 +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); 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 index 157d43787fa0..5cf67ba29269 100644 --- a/drivers/net/ethernet/intel/igb/igb_xsk.c +++ b/drivers/net/ethernet/intel/igb/igb_xsk.c @@ -415,6 +415,7 @@ int igb_clean_rx_irq_zc(struct igb_q_vector *q_vector, /* 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; } diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 02044aa2181b..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); @@ -2912,7 +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); diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index b8111ad9a9a8..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 @@ -319,6 +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]; @@ -332,13 +338,13 @@ 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; }; -void igc_set_queue_napi(struct igc_adapter *adapter, int q_idx, - struct napi_struct *napi); void igc_up(struct igc_adapter *adapter); void igc_down(struct igc_adapter *adapter); int igc_open(struct net_device *netdev); @@ -388,11 +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_LEGACY_ENABLED BIT(19) +#define IGC_FLAG_TSN_PREEMPT_ENABLED BIT(19) #define IGC_FLAG_TSN_ANY_ENABLED \ (IGC_FLAG_TSN_QBV_ENABLED | IGC_FLAG_TSN_QAV_ENABLED | \ - IGC_FLAG_TSN_LEGACY_ENABLED) + IGC_FLAG_TSN_PREEMPT_ENABLED) #define IGC_FLAG_RSS_FIELD_IPV4_UDP BIT(6) #define IGC_FLAG_RSS_FIELD_IPV6_UDP BIT(7) @@ -579,6 +585,7 @@ struct igc_metadata_request { struct xsk_tx_metadata *meta; struct igc_ring *tx_ring; u32 cmd_type; + u16 used_desc; }; struct igc_q_vector { @@ -736,7 +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.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 8e449904aa7d..7189dfc389ad 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -308,6 +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) */ @@ -363,6 +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 */ @@ -372,7 +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 @@ -396,11 +401,47 @@ #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 */ @@ -539,8 +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 @@ -574,7 +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 */ @@ -593,6 +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) */ diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index 817838677817..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 { @@ -1781,6 +1782,83 @@ static int igc_ethtool_set_eee(struct net_device *netdev, return 0; } +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; + + return 0; +} + +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); + } + + 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, struct ethtool_link_ksettings *cmd) { @@ -2076,6 +2154,9 @@ static const struct ethtool_ops igc_ethtool_ops = { .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_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 84307bb7313e..27575a1e1777 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -1092,7 +1092,8 @@ 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; } @@ -1108,20 +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 | @@ -1140,8 +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 @@ -1567,6 +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) { @@ -1586,6 +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++) @@ -1605,24 +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: @@ -1650,7 +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++; @@ -2445,8 +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; @@ -2470,7 +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); @@ -2530,7 +2548,7 @@ out: } /* 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 @@ -2547,7 +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); @@ -2619,6 +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), @@ -2953,9 +2979,48 @@ 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) @@ -2978,7 +3043,13 @@ 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--) { + /* 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; @@ -2999,9 +3070,19 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) 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(meta_req.cmd_type); tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); @@ -3019,9 +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); @@ -3069,6 +3152,11 @@ 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. */ @@ -3961,6 +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 * @@ -4946,8 +5058,8 @@ static int igc_sw_init(struct igc_adapter *adapter) return 0; } -void igc_set_queue_napi(struct igc_adapter *adapter, int vector, - struct napi_struct *napi) +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]; @@ -5215,8 +5327,8 @@ void igc_down(struct igc_adapter *adapter) } } - 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); @@ -5235,6 +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) @@ -5759,6 +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; @@ -5794,6 +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, @@ -6363,6 +6486,10 @@ 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) && @@ -6603,13 +6730,14 @@ static int igc_tsn_enable_mqprio(struct igc_adapter *adapter, struct tc_mqprio_qopt_offload *mqprio) { struct igc_hw *hw = &adapter->hw; - int i; + 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; } @@ -6640,6 +6768,21 @@ static int igc_tsn_enable_mqprio(struct igc_adapter *adapter, 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: @@ -6703,7 +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); @@ -7049,6 +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; @@ -7081,8 +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); @@ -7090,8 +7236,8 @@ 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; @@ -7114,6 +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); @@ -7155,6 +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); @@ -7196,8 +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); diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 946edbad4302..f4f5c28615d3 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -257,13 +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) && @@ -300,10 +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); @@ -974,45 +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; @@ -1021,15 +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) { @@ -1061,9 +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; + + /* This blocks until any in progress PTM transactions complete */ + mutex_lock(&adapter->ptm_lock); - return get_device_system_crosststamp(igc_phc_get_syncdevicetime, - adapter, &adapter->snapshot, cts); + 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, @@ -1146,6 +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; @@ -1162,6 +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; @@ -1174,6 +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; @@ -1203,10 +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); } /** @@ -1237,13 +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); } /** @@ -1255,13 +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) { @@ -1290,14 +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. */ @@ -1314,5 +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 12ddc5793651..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)) diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index 1e44374ca1ff..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; @@ -37,17 +171,16 @@ 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->strict_priority_enable) - new_flags |= IGC_FLAG_TSN_LEGACY_ENABLED; + if (adapter->fpe.mmsv.pmac_enabled) + new_flags |= IGC_FLAG_TSN_PREEMPT_ENABLED; return new_flags; } @@ -125,6 +258,29 @@ static void igc_tsn_tx_arb(struct igc_adapter *adapter, u16 *queue_per_tc) 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. */ @@ -136,15 +292,18 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) 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); @@ -157,16 +316,12 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) wr32(IGC_QBVCYCLET_S, 0); wr32(IGC_QBVCYCLET, NSEC_PER_SEC); - /* Reset mqprio TC configuration. */ - netdev_reset_tc(adapter->netdev); - /* 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; - adapter->flags &= ~IGC_FLAG_TSN_LEGACY_ENABLED; return 0; } @@ -190,53 +345,51 @@ static void igc_tsn_set_retx_qbvfullthreshold(struct igc_adapter *adapter) 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) { - int err; - - 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; - /* Configure queue priorities according to the user provided * mapping. */ igc_tsn_tx_arb(adapter, adapter->queue_per_tc); - - /* Enable legacy TSN mode which will do strict priority without - * any other TSN features. - */ - tqavctrl = rd32(IGC_TQAVCTRL); - tqavctrl |= IGC_TQAVCTRL_TRANSMIT_MODE_TSN; - tqavctrl &= ~IGC_TQAVCTRL_ENHANCED_QAV; - wr32(IGC_TQAVCTRL, tqavctrl); - - return 0; } for (i = 0; i < adapter->num_tx_queues; i++) { @@ -361,10 +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; @@ -425,6 +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)) diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.h b/drivers/net/ethernet/intel/igc/igc_tsn.h index 98ec845a86bf..c2a77229207b 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.h +++ b/drivers/net/ethernet/intel/igc/igc_tsn.h @@ -4,9 +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 13bbd3346e01..9eb47b4beb06 100644 --- a/drivers/net/ethernet/intel/igc/igc_xdp.c +++ b/drivers/net/ethernet/intel/igc/igc_xdp.c @@ -14,6 +14,7 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, 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 @@ -24,8 +25,13 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, } need_update = !!adapter->xdp_prog != !!prog; - if (if_running && need_update) - igc_close(dev); + 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) @@ -36,8 +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 && need_update) - 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; } @@ -86,7 +97,6 @@ static int igc_xdp_enable_pool(struct igc_adapter *adapter, napi_disable(napi); } - igc_set_queue_napi(adapter, queue_id, NULL); set_bit(IGC_RING_FLAG_AF_XDP_ZC, &rx_ring->flags); set_bit(IGC_RING_FLAG_AF_XDP_ZC, &tx_ring->flags); @@ -136,7 +146,6 @@ static int igc_xdp_disable_pool(struct igc_adapter *adapter, u16 queue_id) xsk_pool_dma_unmap(pool, IGC_RX_DMA_ATTR); clear_bit(IGC_RING_FLAG_AF_XDP_ZC, &rx_ring->flags); clear_bit(IGC_RING_FLAG_AF_XDP_ZC, &tx_ring->flags); - igc_set_queue_napi(adapter, queue_id, napi); if (needs_reset) { napi_enable(napi); diff --git a/drivers/net/ethernet/intel/ixgbe/Makefile b/drivers/net/ethernet/intel/ixgbe/Makefile index b456d102655a..2e7738f41c58 100644 --- a/drivers/net/ethernet/intel/ixgbe/Makefile +++ b/drivers/net/ethernet/intel/ixgbe/Makefile @@ -4,12 +4,14 @@ # Makefile for the Intel(R) 10GbE PCI Express ethernet driver # +subdir-ccflags-y += -I$(src) obj-$(CONFIG_IXGBE) += ixgbe.o ixgbe-y := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \ ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \ ixgbe_mbx.o ixgbe_x540.o ixgbe_x550.o ixgbe_lib.o ixgbe_ptp.o \ - ixgbe_xsk.o ixgbe_e610.o + ixgbe_xsk.o ixgbe_e610.o devlink/devlink.o ixgbe_fw_update.o \ + devlink/region.o ixgbe-$(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 e6a380d4929b..47311b134a7a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -17,6 +17,8 @@ #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" @@ -612,6 +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; @@ -667,6 +674,8 @@ struct ixgbe_adapter { #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; @@ -755,6 +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 */ @@ -830,6 +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)) @@ -945,6 +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 4aaaea3b5f8f..444da982593f 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c @@ -1169,6 +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 964988b4d58b..d5b1b974b4a3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c @@ -2230,6 +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 7beaf6ea57f9..5784d5d1896e 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -332,6 +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) { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c index 19d6b6fa8fb3..3dd5a16a14df 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c @@ -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); @@ -167,7 +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; @@ -184,7 +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; } @@ -193,7 +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; @@ -210,7 +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; } @@ -219,7 +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; @@ -230,7 +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]; } @@ -239,7 +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; @@ -250,7 +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]; } @@ -258,7 +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 != @@ -269,14 +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); @@ -295,7 +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; @@ -383,7 +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: @@ -420,7 +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) { @@ -447,14 +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; } @@ -471,7 +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, @@ -486,7 +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; @@ -506,7 +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; @@ -559,7 +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; @@ -584,7 +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; @@ -616,7 +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)) @@ -661,7 +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)) @@ -705,13 +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 index 683c668672d6..71ea25de1bac 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c @@ -344,6 +344,40 @@ void ixgbe_fill_dflt_direct_cmd_desc(struct ixgbe_aci_desc *desc, u16 opcode) } /** + * 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 @@ -554,6 +588,20 @@ static bool ixgbe_parse_e610_caps(struct ixgbe_hw *hw, 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; @@ -1122,7 +1170,7 @@ static bool ixgbe_is_media_cage_present(struct ixgbe_hw *hw) * 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); + return !ixgbe_aci_get_netlist_node(hw, cmd, NULL, NULL); } /** @@ -1411,6 +1459,61 @@ int ixgbe_configure_lse(struct ixgbe_hw *hw, bool activate, u16 mask) } /** + * 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 * @@ -1453,9 +1556,11 @@ enum ixgbe_media_type ixgbe_get_media_type_e610(struct ixgbe_hw *hw) hw->link.link_info.phy_type_low = 0; } else { highest_bit = fls64(le64_to_cpu(pcaps.phy_type_low)); - if (highest_bit) + if (highest_bit) { hw->link.link_info.phy_type_low = BIT_ULL(highest_bit - 1); + hw->link.link_info.phy_type_high = 0; + } } } @@ -1741,6 +1846,38 @@ void ixgbe_disable_rx_e610(struct ixgbe_hw *hw) } /** + * 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 * @@ -2224,6 +2361,131 @@ int ixgbe_aci_read_nvm(struct ixgbe_hw *hw, u16 module_typeid, u32 offset, } /** + * 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 * @@ -2265,6 +2527,955 @@ int ixgbe_nvm_validate_checksum(struct ixgbe_hw *hw) } /** + * 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) @@ -2483,7 +3694,7 @@ int ixgbe_validate_eeprom_checksum_e610(struct ixgbe_hw *hw, u16 *checksum_val) if (err) return err; - err = ixgbe_read_sr_word_aci(hw, E610_SR_SW_CHECKSUM_WORD, + err = ixgbe_read_sr_word_aci(hw, IXGBE_E610_SR_SW_CHECKSUM_WORD, &tmp_checksum); ixgbe_release_nvm(hw); @@ -2578,9 +3789,129 @@ 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_X540, + .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, @@ -2619,8 +3950,12 @@ static const struct ixgbe_mac_operations mac_ops_e610 = { .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, @@ -2645,6 +3980,8 @@ 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 = { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h index ba8c06b73810..bb31d65bd1c8 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h @@ -36,6 +36,7 @@ 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); @@ -67,6 +68,11 @@ 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); @@ -77,5 +83,18 @@ 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 da91c582d439..d8a919ab7027 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -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; @@ -994,14 +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; @@ -1037,7 +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; @@ -1104,10 +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)); @@ -1161,7 +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]; @@ -1176,7 +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; @@ -1336,7 +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; @@ -1710,7 +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); @@ -2183,7 +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)) { @@ -2306,7 +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; @@ -2328,7 +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)) @@ -2353,9 +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); @@ -2366,7 +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) @@ -2394,12 +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) @@ -2455,7 +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; @@ -2681,7 +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) { @@ -3069,7 +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) { @@ -3096,7 +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); } @@ -3116,7 +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; @@ -3134,7 +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); @@ -3176,7 +3293,7 @@ static int ixgbe_set_rxfh(struct net_device *netdev, static int ixgbe_get_ts_info(struct net_device *dev, 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); @@ -3185,6 +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: @@ -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 955dced844a9..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); @@ -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; @@ -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_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 467f81239e12..03d31e5b131d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -49,6 +49,7 @@ #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[] = @@ -1095,7 +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); @@ -3185,6 +3186,10 @@ static void ixgbe_handle_fw_event(struct ixgbe_adapter *adapter) 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; @@ -4674,7 +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 */ @@ -4733,7 +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 */ @@ -4958,7 +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)) @@ -5134,7 +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)); @@ -5144,7 +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)); @@ -5162,7 +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; @@ -5264,7 +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; @@ -6534,7 +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 */ @@ -6596,7 +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); @@ -6845,7 +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; } @@ -7161,7 +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; @@ -7208,7 +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; @@ -7312,7 +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); @@ -8360,6 +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 @@ -8370,12 +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); @@ -8383,10 +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 @@ -8406,8 +8484,13 @@ 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; } @@ -8997,7 +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; @@ -9256,7 +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; /* @@ -9288,7 +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; @@ -9306,7 +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; @@ -9332,7 +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) { @@ -9352,7 +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: @@ -9378,7 +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)) { @@ -9402,7 +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)) { @@ -9433,7 +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(); @@ -9476,7 +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; @@ -9593,7 +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, }; @@ -9614,7 +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 */ @@ -10172,7 +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: @@ -10200,7 +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); @@ -10211,7 +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)) @@ -10248,7 +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; @@ -10324,7 +10407,7 @@ static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], { /* 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)) @@ -10412,7 +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; @@ -10440,7 +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; @@ -10452,7 +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; @@ -10549,7 +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; @@ -10627,7 +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; @@ -10699,7 +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: @@ -10734,7 +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; @@ -11142,7 +11225,7 @@ bool ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id, * format to display. The FW version is taken from the EEPROM/NVM. * */ -static void ixgbe_set_fw_version_e610(struct ixgbe_adapter *adapter) +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; @@ -11193,6 +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 @@ -11206,6 +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]; @@ -11259,7 +11403,13 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) 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; @@ -11267,7 +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; @@ -11283,11 +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; @@ -11317,15 +11463,31 @@ 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) @@ -11344,10 +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: @@ -11500,11 +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"); @@ -11587,7 +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) @@ -11613,6 +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; @@ -11667,11 +11825,16 @@ 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) @@ -11688,7 +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) @@ -11717,6 +11882,9 @@ 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); @@ -11752,6 +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); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index 0a03a8bb5f88..2d54828bdfbb 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -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; @@ -2285,7 +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_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 ccdce80edd14..0dbbd2befd4d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -1418,7 +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) @@ -1526,7 +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; @@ -1644,7 +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 */ @@ -1679,7 +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) @@ -1757,7 +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) { @@ -1794,7 +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. @@ -1813,7 +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; @@ -1836,7 +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 5fdf32d79d82..892fa6c1f879 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -3446,6 +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 { @@ -3454,6 +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 *); @@ -3522,6 +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, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h index 8d06ade3c7cd..09df67f03cf4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h @@ -10,11 +10,75 @@ #define IXGBE_MAX_VSI 768 /* Checksum and Shadow RAM pointers */ -#define E610_SR_SW_CHECKSUM_WORD 0x3F +#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) @@ -24,11 +88,23 @@ #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)) @@ -40,6 +116,10 @@ #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) @@ -143,6 +223,7 @@ enum ixgbe_aci_opc { 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, @@ -171,6 +252,9 @@ enum ixgbe_aci_opc { 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, @@ -725,6 +809,18 @@ struct ixgbe_aci_cmd_get_link_topo_pin { 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; @@ -758,6 +854,8 @@ 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 */ @@ -773,6 +871,9 @@ struct ixgbe_aci_cmd_nvm { #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 @@ -802,6 +903,63 @@ struct ixgbe_aci_cmd_nvm_checksum { 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 @@ -840,11 +998,14 @@ struct ixgbe_aci_desc { 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; }; @@ -981,6 +1142,16 @@ struct ixgbe_hw_caps { #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 */ @@ -1012,6 +1183,11 @@ struct ixgbe_aci_info { 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 */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c index 1fc821fb351a..f1ab95aa8c83 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c @@ -894,6 +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_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 277ceaf8a793..1d2acdb64f45 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -3959,6 +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 diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index 3e3b471e53f0..ac58964b2f08 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -508,7 +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/ipsec.c b/drivers/net/ethernet/intel/ixgbevf/ipsec.c index f804b35d79c7..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, }; /** diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 6442f115a262..a217c5c04804 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -2514,7 +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++) { |