diff options
Diffstat (limited to 'drivers/net/ethernet/intel')
40 files changed, 2467 insertions, 910 deletions
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 184f11242f56..44b3937f7e81 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -1710,9 +1710,9 @@ static void e100_adjust_adaptive_ifs(struct nic *nic, int speed, int duplex) } } -static void e100_watchdog(unsigned long data) +static void e100_watchdog(struct timer_list *t) { - struct nic *nic = (struct nic *)data; + struct nic *nic = from_timer(nic, t, watchdog); struct ethtool_cmd cmd = { .cmd = ETHTOOL_GSET }; u32 speed; @@ -2920,7 +2920,7 @@ static int e100_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_master(pdev); - setup_timer(&nic->watchdog, e100_watchdog, (unsigned long)nic); + timer_setup(&nic->watchdog, e100_watchdog, 0); INIT_WORK(&nic->tx_timeout_task, e100_tx_timeout_task); diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h index 0641c0098738..afb7ebe20b24 100644 --- a/drivers/net/ethernet/intel/e1000e/defines.h +++ b/drivers/net/ethernet/intel/e1000e/defines.h @@ -398,6 +398,7 @@ #define E1000_ICR_LSC 0x00000004 /* Link Status Change */ #define E1000_ICR_RXSEQ 0x00000008 /* Rx sequence error */ #define E1000_ICR_RXDMT0 0x00000010 /* Rx desc min. threshold (0) */ +#define E1000_ICR_RXO 0x00000040 /* Receiver Overrun */ #define E1000_ICR_RXT0 0x00000080 /* Rx timer intr (ring 0) */ #define E1000_ICR_ECCER 0x00400000 /* Uncorrectable ECC Error */ /* If this bit asserted, the driver should claim the interrupt */ diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index 98e68888abb1..2311b31bdcac 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -94,10 +94,6 @@ struct e1000_info; */ #define E1000_CHECK_RESET_COUNT 25 -#define DEFAULT_RDTR 0 -#define DEFAULT_RADV 8 -#define BURST_RDTR 0x20 -#define BURST_RADV 0x20 #define PCICFG_DESC_RING_STATUS 0xe4 #define FLUSH_DESC_REQUIRED 0x100 diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c index b322011ec282..f457c5703d0c 100644 --- a/drivers/net/ethernet/intel/e1000e/mac.c +++ b/drivers/net/ethernet/intel/e1000e/mac.c @@ -410,6 +410,9 @@ void e1000e_clear_hw_cntrs_base(struct e1000_hw *hw) * Checks to see of the link status of the hardware has changed. If a * change in link status has been detected, then we read the PHY registers * to get the current speed/duplex if link exists. + * + * Returns a negative error code (-E1000_ERR_*) or 0 (link down) or 1 (link + * up). **/ s32 e1000e_check_for_copper_link(struct e1000_hw *hw) { @@ -423,7 +426,7 @@ s32 e1000e_check_for_copper_link(struct e1000_hw *hw) * Change or Rx Sequence Error interrupt. */ if (!mac->get_link_status) - return 0; + return 1; /* First we want to see if the MII Status Register reports * link. If so, then we want to get the current speed/duplex @@ -461,10 +464,12 @@ s32 e1000e_check_for_copper_link(struct e1000_hw *hw) * different link partner. */ ret_val = e1000e_config_fc_after_link_up(hw); - if (ret_val) + if (ret_val) { e_dbg("Error configuring flow control\n"); + return ret_val; + } - return ret_val; + return 1; } /** diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 8436c5f2c3e8..f2f49239b015 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -1071,7 +1071,8 @@ next_desc: } static void e1000_put_txbuf(struct e1000_ring *tx_ring, - struct e1000_buffer *buffer_info) + struct e1000_buffer *buffer_info, + bool drop) { struct e1000_adapter *adapter = tx_ring->adapter; @@ -1085,7 +1086,10 @@ static void e1000_put_txbuf(struct e1000_ring *tx_ring, buffer_info->dma = 0; } if (buffer_info->skb) { - dev_kfree_skb_any(buffer_info->skb); + if (drop) + dev_kfree_skb_any(buffer_info->skb); + else + dev_consume_skb_any(buffer_info->skb); buffer_info->skb = NULL; } buffer_info->time_stamp = 0; @@ -1199,7 +1203,7 @@ static void e1000e_tx_hwtstamp_work(struct work_struct *work) wmb(); /* force write prior to skb_tstamp_tx */ skb_tstamp_tx(skb, &shhwtstamps); - dev_kfree_skb_any(skb); + dev_consume_skb_any(skb); } else if (time_after(jiffies, adapter->tx_hwtstamp_start + adapter->tx_timeout_factor * HZ)) { dev_kfree_skb_any(adapter->tx_hwtstamp_skb); @@ -1254,7 +1258,7 @@ static bool e1000_clean_tx_irq(struct e1000_ring *tx_ring) } } - e1000_put_txbuf(tx_ring, buffer_info); + e1000_put_txbuf(tx_ring, buffer_info, false); tx_desc->upper.data = 0; i++; @@ -1910,14 +1914,30 @@ static irqreturn_t e1000_msix_other(int __always_unused irq, void *data) struct net_device *netdev = data; struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; + u32 icr; + bool enable = true; + + icr = er32(ICR); + if (icr & E1000_ICR_RXO) { + ew32(ICR, E1000_ICR_RXO); + enable = false; + /* napi poll will re-enable Other, make sure it runs */ + if (napi_schedule_prep(&adapter->napi)) { + adapter->total_rx_bytes = 0; + adapter->total_rx_packets = 0; + __napi_schedule(&adapter->napi); + } + } + if (icr & E1000_ICR_LSC) { + ew32(ICR, E1000_ICR_LSC); + hw->mac.get_link_status = true; + /* guard against interrupt when we're going down */ + if (!test_bit(__E1000_DOWN, &adapter->state)) + mod_timer(&adapter->watchdog_timer, jiffies + 1); + } - hw->mac.get_link_status = true; - - /* guard against interrupt when we're going down */ - if (!test_bit(__E1000_DOWN, &adapter->state)) { - mod_timer(&adapter->watchdog_timer, jiffies + 1); + if (enable && !test_bit(__E1000_DOWN, &adapter->state)) ew32(IMS, E1000_IMS_OTHER); - } return IRQ_HANDLED; } @@ -2421,7 +2441,7 @@ static void e1000_clean_tx_ring(struct e1000_ring *tx_ring) for (i = 0; i < tx_ring->count; i++) { buffer_info = &tx_ring->buffer_info[i]; - e1000_put_txbuf(tx_ring, buffer_info); + e1000_put_txbuf(tx_ring, buffer_info, false); } netdev_reset_queue(adapter->netdev); @@ -2687,7 +2707,8 @@ static int e1000e_poll(struct napi_struct *napi, int weight) napi_complete_done(napi, work_done); if (!test_bit(__E1000_DOWN, &adapter->state)) { if (adapter->msix_entries) - ew32(IMS, adapter->rx_ring->ims_val); + ew32(IMS, adapter->rx_ring->ims_val | + E1000_IMS_OTHER); else e1000_irq_enable(adapter); } @@ -3004,8 +3025,8 @@ static void e1000_configure_tx(struct e1000_adapter *adapter) hw->mac.ops.config_collision_dist(hw); - /* SPT and CNP Si errata workaround to avoid data corruption */ - if (hw->mac.type >= e1000_pch_spt) { + /* SPT and KBL Si errata workaround to avoid data corruption */ + if (hw->mac.type == e1000_pch_spt) { u32 reg_val; reg_val = er32(IOSFPC); @@ -3013,7 +3034,9 @@ static void e1000_configure_tx(struct e1000_adapter *adapter) ew32(IOSFPC, reg_val); reg_val = er32(TARC(0)); - reg_val |= E1000_TARC0_CB_MULTIQ_3_REQ; + /* SPT and KBL Si errata workaround to avoid Tx hang */ + reg_val &= ~BIT(28); + reg_val |= BIT(29); ew32(TARC(0), reg_val); } } @@ -3223,14 +3246,6 @@ static void e1000_configure_rx(struct e1000_adapter *adapter) */ ew32(RXDCTL(0), E1000_RXDCTL_DMA_BURST_ENABLE); ew32(RXDCTL(1), E1000_RXDCTL_DMA_BURST_ENABLE); - - /* override the delay timers for enabling bursting, only if - * the value was not set by the user via module options - */ - if (adapter->rx_int_delay == DEFAULT_RDTR) - adapter->rx_int_delay = BURST_RDTR; - if (adapter->rx_abs_int_delay == DEFAULT_RADV) - adapter->rx_abs_int_delay = BURST_RADV; } /* set the Receive Delay Timer Register */ @@ -4204,7 +4219,7 @@ static void e1000e_trigger_lsc(struct e1000_adapter *adapter) struct e1000_hw *hw = &adapter->hw; if (adapter->msix_entries) - ew32(ICS, E1000_ICS_OTHER); + ew32(ICS, E1000_ICS_LSC | E1000_ICS_OTHER); else ew32(ICS, E1000_ICS_LSC); } @@ -4808,9 +4823,9 @@ static void e1000e_update_phy_task(struct work_struct *work) * Need to wait a few seconds after link up to get diagnostic information from * the phy **/ -static void e1000_update_phy_info(unsigned long data) +static void e1000_update_phy_info(struct timer_list *t) { - struct e1000_adapter *adapter = (struct e1000_adapter *)data; + struct e1000_adapter *adapter = from_timer(adapter, t, phy_info_timer); if (test_bit(__E1000_DOWN, &adapter->state)) return; @@ -5074,14 +5089,14 @@ static bool e1000e_has_link(struct e1000_adapter *adapter) /* get_link_status is set on LSC (link status) interrupt or * Rx sequence error interrupt. get_link_status will stay - * false until the check_for_link establishes link + * true until the check_for_link establishes link * for copper adapters ONLY */ switch (hw->phy.media_type) { case e1000_media_type_copper: if (hw->mac.get_link_status) { ret_val = hw->mac.ops.check_for_link(hw); - link_active = !hw->mac.get_link_status; + link_active = ret_val > 0; } else { link_active = true; } @@ -5092,14 +5107,14 @@ static bool e1000e_has_link(struct e1000_adapter *adapter) break; case e1000_media_type_internal_serdes: ret_val = hw->mac.ops.check_for_link(hw); - link_active = adapter->hw.mac.serdes_has_link; + link_active = hw->mac.serdes_has_link; break; default: case e1000_media_type_unknown: break; } - if ((ret_val == E1000_ERR_PHY) && (hw->phy.type == e1000_phy_igp_3) && + if ((ret_val == -E1000_ERR_PHY) && (hw->phy.type == e1000_phy_igp_3) && (er32(CTRL) & E1000_PHY_CTRL_GBE_DISABLE)) { /* See e1000_kmrn_lock_loss_workaround_ich8lan() */ e_info("Gigabit has been disabled, downgrading speed\n"); @@ -5144,9 +5159,9 @@ static void e1000e_check_82574_phy_workaround(struct e1000_adapter *adapter) * e1000_watchdog - Timer Call-back * @data: pointer to adapter cast into an unsigned long **/ -static void e1000_watchdog(unsigned long data) +static void e1000_watchdog(struct timer_list *t) { - struct e1000_adapter *adapter = (struct e1000_adapter *)data; + struct e1000_adapter *adapter = from_timer(adapter, t, watchdog_timer); /* Do the rest outside of interrupt context */ schedule_work(&adapter->watchdog_task); @@ -5614,7 +5629,7 @@ dma_error: i += tx_ring->count; i--; buffer_info = &tx_ring->buffer_info[i]; - e1000_put_txbuf(tx_ring, buffer_info); + e1000_put_txbuf(tx_ring, buffer_info, true); } return 0; @@ -7252,10 +7267,8 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_eeprom; } - setup_timer(&adapter->watchdog_timer, e1000_watchdog, - (unsigned long)adapter); - setup_timer(&adapter->phy_info_timer, e1000_update_phy_info, - (unsigned long)adapter); + timer_setup(&adapter->watchdog_timer, e1000_watchdog, 0); + timer_setup(&adapter->phy_info_timer, e1000_update_phy_info, 0); INIT_WORK(&adapter->reset_task, e1000_reset_task); INIT_WORK(&adapter->watchdog_task, e1000_watchdog_task); @@ -7408,7 +7421,7 @@ static void e1000_remove(struct pci_dev *pdev) if (adapter->flags & FLAG_HAS_HW_TIMESTAMP) { cancel_work_sync(&adapter->tx_hwtstamp_work); if (adapter->tx_hwtstamp_skb) { - dev_kfree_skb_any(adapter->tx_hwtstamp_skb); + dev_consume_skb_any(adapter->tx_hwtstamp_skb); adapter->tx_hwtstamp_skb = NULL; } } diff --git a/drivers/net/ethernet/intel/e1000e/param.c b/drivers/net/ethernet/intel/e1000e/param.c index 6d8c39abee16..47da51864543 100644 --- a/drivers/net/ethernet/intel/e1000e/param.c +++ b/drivers/net/ethernet/intel/e1000e/param.c @@ -73,17 +73,25 @@ E1000_PARAM(TxAbsIntDelay, "Transmit Absolute Interrupt Delay"); /* Receive Interrupt Delay in units of 1.024 microseconds * hardware will likely hang if you set this to anything but zero. * + * Burst variant is used as default if device has FLAG2_DMA_BURST. + * * Valid Range: 0-65535 */ E1000_PARAM(RxIntDelay, "Receive Interrupt Delay"); +#define DEFAULT_RDTR 0 +#define BURST_RDTR 0x20 #define MAX_RXDELAY 0xFFFF #define MIN_RXDELAY 0 /* Receive Absolute Interrupt Delay in units of 1.024 microseconds * + * Burst variant is used as default if device has FLAG2_DMA_BURST. + * * Valid Range: 0-65535 */ E1000_PARAM(RxAbsIntDelay, "Receive Absolute Interrupt Delay"); +#define DEFAULT_RADV 8 +#define BURST_RADV 0x20 #define MAX_RXABSDELAY 0xFFFF #define MIN_RXABSDELAY 0 @@ -297,6 +305,9 @@ void e1000e_check_options(struct e1000_adapter *adapter) .max = MAX_RXDELAY } } }; + if (adapter->flags2 & FLAG2_DMA_BURST) + opt.def = BURST_RDTR; + if (num_RxIntDelay > bd) { adapter->rx_int_delay = RxIntDelay[bd]; e1000_validate_option(&adapter->rx_int_delay, &opt, @@ -307,7 +318,7 @@ void e1000e_check_options(struct e1000_adapter *adapter) } /* Receive Absolute Interrupt Delay */ { - static const struct e1000_option opt = { + static struct e1000_option opt = { .type = range_option, .name = "Receive Absolute Interrupt Delay", .err = "using default of " @@ -317,6 +328,9 @@ void e1000e_check_options(struct e1000_adapter *adapter) .max = MAX_RXABSDELAY } } }; + if (adapter->flags2 & FLAG2_DMA_BURST) + opt.def = BURST_RADV; + if (num_RxAbsIntDelay > bd) { adapter->rx_abs_int_delay = RxAbsIntDelay[bd]; e1000_validate_option(&adapter->rx_abs_int_delay, &opt, diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c index d78d47b41a71..86ff0969efb6 100644 --- a/drivers/net/ethernet/intel/e1000e/phy.c +++ b/drivers/net/ethernet/intel/e1000e/phy.c @@ -1744,6 +1744,7 @@ s32 e1000e_phy_has_link_generic(struct e1000_hw *hw, u32 iterations, s32 ret_val = 0; u16 i, phy_status; + *success = false; for (i = 0; i < iterations; i++) { /* Some PHYs require the MII_BMSR register to be read * twice due to the link bit being sticky. No harm doing @@ -1763,16 +1764,16 @@ s32 e1000e_phy_has_link_generic(struct e1000_hw *hw, u32 iterations, ret_val = e1e_rphy(hw, MII_BMSR, &phy_status); if (ret_val) break; - if (phy_status & BMSR_LSTATUS) + if (phy_status & BMSR_LSTATUS) { + *success = true; break; + } if (usec_interval >= 1000) msleep(usec_interval / 1000); else udelay(usec_interval); } - *success = (i < iterations); - return ret_val; } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 1e9ae3197b17..7f605221a686 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -213,9 +213,10 @@ static void fm10k_start_service_event(struct fm10k_intfc *interface) * fm10k_service_timer - Timer Call-back * @data: pointer to interface cast into an unsigned long **/ -static void fm10k_service_timer(unsigned long data) +static void fm10k_service_timer(struct timer_list *t) { - struct fm10k_intfc *interface = (struct fm10k_intfc *)data; + struct fm10k_intfc *interface = from_timer(interface, t, + service_timer); /* Reset the timer */ mod_timer(&interface->service_timer, (HZ * 2) + jiffies); @@ -2315,8 +2316,7 @@ static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Initialize service timer and service task late in order to avoid * cleanup issues. */ - setup_timer(&interface->service_timer, &fm10k_service_timer, - (unsigned long)interface); + timer_setup(&interface->service_timer, fm10k_service_timer, 0); INIT_WORK(&interface->service_task, fm10k_service_task); /* Setup the MAC/VLAN queue */ diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 439c63cb2a0c..eb017763646d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -54,6 +54,7 @@ #include <linux/clocksource.h> #include <linux/net_tstamp.h> #include <linux/ptp_clock_kernel.h> +#include <net/pkt_cls.h> #include "i40e_type.h" #include "i40e_prototype.h" #include "i40e_client.h" @@ -87,6 +88,7 @@ #define I40E_AQ_LEN 256 #define I40E_AQ_WORK_LIMIT 66 /* max number of VFs + a little */ #define I40E_MAX_USER_PRIORITY 8 +#define I40E_MAX_QUEUES_PER_CH 64 #define I40E_DEFAULT_TRAFFIC_CLASS BIT(0) #define I40E_DEFAULT_MSG_ENABLE 4 #define I40E_QUEUE_WAIT_RETRY_LIMIT 10 @@ -126,6 +128,11 @@ /* default to trying for four seconds */ #define I40E_TRY_LINK_TIMEOUT (4 * HZ) +/* BW rate limiting */ +#define I40E_BW_CREDIT_DIVISOR 50 /* 50Mbps per BW credit */ +#define I40E_BW_MBPS_DIVISOR 125000 /* rate / (1000000 / 8) Mbps */ +#define I40E_MAX_BW_INACTIVE_ACCUM 4 /* accumulate 4 credits max */ + /* driver state flags */ enum i40e_state_t { __I40E_TESTING, @@ -157,6 +164,8 @@ enum i40e_state_t { __I40E_STATE_SIZE__, }; +#define I40E_PF_RESET_FLAG BIT_ULL(__I40E_PF_RESET_REQUESTED) + /* VSI state flags */ enum i40e_vsi_state_t { __I40E_VSI_DOWN, @@ -338,6 +347,25 @@ struct i40e_flex_pit { u8 pit_index; }; +struct i40e_channel { + struct list_head list; + bool initialized; + u8 type; + u16 vsi_number; /* Assigned VSI number from AQ 'Add VSI' response */ + u16 stat_counter_idx; + u16 base_queue; + u16 num_queue_pairs; /* Requested by user */ + u16 seid; + + u8 enabled_tc; + struct i40e_aqc_vsi_properties_data info; + + u64 max_tx_rate; + + /* track this channel belongs to which VSI */ + struct i40e_vsi *parent_vsi; +}; + /* struct that defines the Ethernet device */ struct i40e_pf { struct pci_dev *pdev; @@ -350,7 +378,7 @@ struct i40e_pf { u16 num_vmdq_vsis; /* num vmdq vsis this PF has set up */ u16 num_vmdq_qps; /* num queue pairs per vmdq pool */ u16 num_vmdq_msix; /* num queue vectors per vmdq pool */ - u16 num_req_vfs; /* num VFs requested for this VF */ + u16 num_req_vfs; /* num VFs requested for this PF */ u16 num_vf_qps; /* num queue pairs per VF */ u16 num_lan_qps; /* num lan queues this PF has set up */ u16 num_lan_msix; /* num queue vectors for the base PF vsi */ @@ -403,55 +431,58 @@ struct i40e_pf { struct timer_list service_timer; struct work_struct service_task; - u64 hw_features; -#define I40E_HW_RSS_AQ_CAPABLE BIT_ULL(0) -#define I40E_HW_128_QP_RSS_CAPABLE BIT_ULL(1) -#define I40E_HW_ATR_EVICT_CAPABLE BIT_ULL(2) -#define I40E_HW_WB_ON_ITR_CAPABLE BIT_ULL(3) -#define I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE BIT_ULL(4) -#define I40E_HW_NO_PCI_LINK_CHECK BIT_ULL(5) -#define I40E_HW_100M_SGMII_CAPABLE BIT_ULL(6) -#define I40E_HW_NO_DCB_SUPPORT BIT_ULL(7) -#define I40E_HW_USE_SET_LLDP_MIB BIT_ULL(8) -#define I40E_HW_GENEVE_OFFLOAD_CAPABLE BIT_ULL(9) -#define I40E_HW_PTP_L4_CAPABLE BIT_ULL(10) -#define I40E_HW_WOL_MC_MAGIC_PKT_WAKE BIT_ULL(11) -#define I40E_HW_MPLS_HDR_OFFLOAD_CAPABLE BIT_ULL(12) -#define I40E_HW_HAVE_CRT_RETIMER BIT_ULL(13) -#define I40E_HW_OUTER_UDP_CSUM_CAPABLE BIT_ULL(14) -#define I40E_HW_PHY_CONTROLS_LEDS BIT_ULL(15) -#define I40E_HW_STOP_FW_LLDP BIT_ULL(16) -#define I40E_HW_PORT_ID_VALID BIT_ULL(17) -#define I40E_HW_RESTART_AUTONEG BIT_ULL(18) - - u64 flags; -#define I40E_FLAG_RX_CSUM_ENABLED BIT_ULL(1) -#define I40E_FLAG_MSI_ENABLED BIT_ULL(2) -#define I40E_FLAG_MSIX_ENABLED BIT_ULL(3) -#define I40E_FLAG_HW_ATR_EVICT_ENABLED BIT_ULL(4) -#define I40E_FLAG_RSS_ENABLED BIT_ULL(6) -#define I40E_FLAG_VMDQ_ENABLED BIT_ULL(7) -#define I40E_FLAG_IWARP_ENABLED BIT_ULL(10) -#define I40E_FLAG_FILTER_SYNC BIT_ULL(15) -#define I40E_FLAG_SERVICE_CLIENT_REQUESTED BIT_ULL(16) -#define I40E_FLAG_SRIOV_ENABLED BIT_ULL(19) -#define I40E_FLAG_DCB_ENABLED BIT_ULL(20) -#define I40E_FLAG_FD_SB_ENABLED BIT_ULL(21) -#define I40E_FLAG_FD_ATR_ENABLED BIT_ULL(22) -#define I40E_FLAG_FD_SB_AUTO_DISABLED BIT_ULL(23) -#define I40E_FLAG_FD_ATR_AUTO_DISABLED BIT_ULL(24) -#define I40E_FLAG_PTP BIT_ULL(25) -#define I40E_FLAG_MFP_ENABLED BIT_ULL(26) -#define I40E_FLAG_UDP_FILTER_SYNC BIT_ULL(27) -#define I40E_FLAG_DCB_CAPABLE BIT_ULL(29) -#define I40E_FLAG_VEB_STATS_ENABLED BIT_ULL(37) -#define I40E_FLAG_LINK_POLLING_ENABLED BIT_ULL(39) -#define I40E_FLAG_VEB_MODE_ENABLED BIT_ULL(40) -#define I40E_FLAG_TRUE_PROMISC_SUPPORT BIT_ULL(51) -#define I40E_FLAG_CLIENT_RESET BIT_ULL(54) -#define I40E_FLAG_TEMP_LINK_POLLING BIT_ULL(55) -#define I40E_FLAG_CLIENT_L2_CHANGE BIT_ULL(56) -#define I40E_FLAG_LEGACY_RX BIT_ULL(58) + u32 hw_features; +#define I40E_HW_RSS_AQ_CAPABLE BIT(0) +#define I40E_HW_128_QP_RSS_CAPABLE BIT(1) +#define I40E_HW_ATR_EVICT_CAPABLE BIT(2) +#define I40E_HW_WB_ON_ITR_CAPABLE BIT(3) +#define I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE BIT(4) +#define I40E_HW_NO_PCI_LINK_CHECK BIT(5) +#define I40E_HW_100M_SGMII_CAPABLE BIT(6) +#define I40E_HW_NO_DCB_SUPPORT BIT(7) +#define I40E_HW_USE_SET_LLDP_MIB BIT(8) +#define I40E_HW_GENEVE_OFFLOAD_CAPABLE BIT(9) +#define I40E_HW_PTP_L4_CAPABLE BIT(10) +#define I40E_HW_WOL_MC_MAGIC_PKT_WAKE BIT(11) +#define I40E_HW_MPLS_HDR_OFFLOAD_CAPABLE BIT(12) +#define I40E_HW_HAVE_CRT_RETIMER BIT(13) +#define I40E_HW_OUTER_UDP_CSUM_CAPABLE BIT(14) +#define I40E_HW_PHY_CONTROLS_LEDS BIT(15) +#define I40E_HW_STOP_FW_LLDP BIT(16) +#define I40E_HW_PORT_ID_VALID BIT(17) +#define I40E_HW_RESTART_AUTONEG BIT(18) + + u32 flags; +#define I40E_FLAG_RX_CSUM_ENABLED BIT(0) +#define I40E_FLAG_MSI_ENABLED BIT(1) +#define I40E_FLAG_MSIX_ENABLED BIT(2) +#define I40E_FLAG_RSS_ENABLED BIT(3) +#define I40E_FLAG_VMDQ_ENABLED BIT(4) +#define I40E_FLAG_FILTER_SYNC BIT(5) +#define I40E_FLAG_SRIOV_ENABLED BIT(6) +#define I40E_FLAG_DCB_CAPABLE BIT(7) +#define I40E_FLAG_DCB_ENABLED BIT(8) +#define I40E_FLAG_FD_SB_ENABLED BIT(9) +#define I40E_FLAG_FD_ATR_ENABLED BIT(10) +#define I40E_FLAG_FD_SB_AUTO_DISABLED BIT(11) +#define I40E_FLAG_FD_ATR_AUTO_DISABLED BIT(12) +#define I40E_FLAG_MFP_ENABLED BIT(13) +#define I40E_FLAG_UDP_FILTER_SYNC BIT(14) +#define I40E_FLAG_HW_ATR_EVICT_ENABLED BIT(15) +#define I40E_FLAG_VEB_MODE_ENABLED BIT(16) +#define I40E_FLAG_VEB_STATS_ENABLED BIT(17) +#define I40E_FLAG_LINK_POLLING_ENABLED BIT(18) +#define I40E_FLAG_TRUE_PROMISC_SUPPORT BIT(19) +#define I40E_FLAG_TEMP_LINK_POLLING BIT(20) +#define I40E_FLAG_LEGACY_RX BIT(21) +#define I40E_FLAG_PTP BIT(22) +#define I40E_FLAG_IWARP_ENABLED BIT(23) +#define I40E_FLAG_SERVICE_CLIENT_REQUESTED BIT(24) +#define I40E_FLAG_CLIENT_L2_CHANGE BIT(25) +#define I40E_FLAG_CLIENT_RESET BIT(26) +#define I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED BIT(27) +#define I40E_FLAG_SOURCE_PRUNING_DISABLED BIT(28) +#define I40E_FLAG_TC_MQPRIO BIT(29) struct i40e_client_instance *cinst; bool stat_offsets_loaded; @@ -532,6 +563,8 @@ struct i40e_pf { u32 ioremap_len; u32 fd_inv; u16 phy_led_val; + + u16 override_q_count; }; /** @@ -675,6 +708,7 @@ struct i40e_vsi { enum i40e_vsi_type type; /* VSI type, e.g., LAN, FCoE, etc */ s16 vf_id; /* Virtual function ID for SRIOV VSIs */ + struct tc_mqprio_qopt_offload mqprio_qopt; /* queue parameters */ struct i40e_tc_configuration tc_config; struct i40e_aqc_vsi_properties_data info; @@ -696,6 +730,16 @@ struct i40e_vsi { bool current_isup; /* Sync 'link up' logging */ enum i40e_aq_link_speed current_speed; /* Sync link speed logging */ + /* channel specific fields */ + u16 cnt_q_avail; /* num of queues available for channel usage */ + u16 orig_rss_size; + u16 current_rss_size; + bool reconfig_rss; + + u16 next_base_queue; /* next queue to be used for channel setup */ + + struct list_head ch_list; + void *priv; /* client driver data reference. */ /* VSI specific handlers */ @@ -947,9 +991,6 @@ static inline void i40e_irq_dynamic_enable(struct i40e_vsi *vsi, int vector) struct i40e_hw *hw = &pf->hw; u32 val; - /* definitely clear the PBA here, as this function is meant to - * clean out all previous interrupts AND enable the interrupt - */ val = I40E_PFINT_DYN_CTLN_INTENA_MASK | I40E_PFINT_DYN_CTLN_CLEARPBA_MASK | (I40E_ITR_NONE << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT); @@ -958,7 +999,7 @@ static inline void i40e_irq_dynamic_enable(struct i40e_vsi *vsi, int vector) } void i40e_irq_dynamic_disable_icr0(struct i40e_pf *pf); -void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf, bool clearpba); +void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf); int i40e_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd); int i40e_open(struct net_device *netdev); int i40e_close(struct net_device *netdev); @@ -1003,4 +1044,7 @@ static inline bool i40e_enabled_xdp_vsi(struct i40e_vsi *vsi) { return !!vsi->xdp_prog; } + +int i40e_create_queue_channel(struct i40e_vsi *vsi, struct i40e_channel *ch); +int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate); #endif /* _I40E_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 4c85ea9cd89a..6a5db1b33fa2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -1771,9 +1771,12 @@ enum i40e_aq_phy_type { I40E_PHY_TYPE_25GBASE_CR = 0x20, I40E_PHY_TYPE_25GBASE_SR = 0x21, I40E_PHY_TYPE_25GBASE_LR = 0x22, + I40E_PHY_TYPE_25GBASE_AOC = 0x23, + I40E_PHY_TYPE_25GBASE_ACC = 0x24, + I40E_PHY_TYPE_MAX, + I40E_PHY_TYPE_NOT_SUPPORTED_HIGH_TEMP = 0xFD, I40E_PHY_TYPE_EMPTY = 0xFE, I40E_PHY_TYPE_DEFAULT = 0xFF, - I40E_PHY_TYPE_MAX }; #define I40E_LINK_SPEED_100MB_SHIFT 0x1 @@ -1830,6 +1833,8 @@ struct i40e_aq_get_phy_abilities_resp { #define I40E_AQ_PHY_TYPE_EXT_25G_CR 0X02 #define I40E_AQ_PHY_TYPE_EXT_25G_SR 0x04 #define I40E_AQ_PHY_TYPE_EXT_25G_LR 0x08 +#define I40E_AQ_PHY_TYPE_EXT_25G_AOC 0x10 +#define I40E_AQ_PHY_TYPE_EXT_25G_ACC 0x20 u8 fec_cfg_curr_mod_ext_info; #define I40E_AQ_ENABLE_FEC_KR 0x01 #define I40E_AQ_ENABLE_FEC_RS 0x02 diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 60542beda7ad..8d0ee006606b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1180,6 +1180,8 @@ static enum i40e_media_type i40e_get_media_type(struct i40e_hw *hw) case I40E_PHY_TYPE_40GBASE_AOC: case I40E_PHY_TYPE_10GBASE_AOC: case I40E_PHY_TYPE_25GBASE_CR: + case I40E_PHY_TYPE_25GBASE_AOC: + case I40E_PHY_TYPE_25GBASE_ACC: media = I40E_MEDIA_TYPE_DA; break; case I40E_PHY_TYPE_1000BASE_KX: @@ -1567,36 +1569,57 @@ i40e_status i40e_aq_get_phy_capabilities(struct i40e_hw *hw, struct i40e_aq_desc desc; i40e_status status; u16 abilities_size = sizeof(struct i40e_aq_get_phy_abilities_resp); + u16 max_delay = I40E_MAX_PHY_TIMEOUT, total_delay = 0; if (!abilities) return I40E_ERR_PARAM; - i40e_fill_default_direct_cmd_desc(&desc, - i40e_aqc_opc_get_phy_abilities); + do { + i40e_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_get_phy_abilities); - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); - if (abilities_size > I40E_AQ_LARGE_BUF) - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); + if (abilities_size > I40E_AQ_LARGE_BUF) + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); - if (qualified_modules) - desc.params.external.param0 |= + if (qualified_modules) + desc.params.external.param0 |= cpu_to_le32(I40E_AQ_PHY_REPORT_QUALIFIED_MODULES); - if (report_init) - desc.params.external.param0 |= + if (report_init) + desc.params.external.param0 |= cpu_to_le32(I40E_AQ_PHY_REPORT_INITIAL_VALUES); - status = i40e_asq_send_command(hw, &desc, abilities, abilities_size, - cmd_details); + status = i40e_asq_send_command(hw, &desc, abilities, + abilities_size, cmd_details); - if (hw->aq.asq_last_status == I40E_AQ_RC_EIO) - status = I40E_ERR_UNKNOWN_PHY; + if (status) + break; + + if (hw->aq.asq_last_status == I40E_AQ_RC_EIO) { + status = I40E_ERR_UNKNOWN_PHY; + break; + } else if (hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN) { + usleep_range(1000, 2000); + total_delay++; + status = I40E_ERR_TIMEOUT; + } + } while ((hw->aq.asq_last_status != I40E_AQ_RC_OK) && + (total_delay < max_delay)); + + if (status) + return status; if (report_init) { if (hw->mac.type == I40E_MAC_XL710 && hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR && - hw->aq.api_min_ver >= I40E_MINOR_VER_GET_LINK_INFO_XL710) + hw->aq.api_min_ver >= I40E_MINOR_VER_GET_LINK_INFO_XL710) { status = i40e_aq_get_link_info(hw, true, NULL, NULL); + } else { + hw->phy.phy_types = le32_to_cpu(abilities->phy_type); + hw->phy.phy_types |= + ((u64)abilities->phy_type_ext << 32); + } } return status; diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 8f326f87a815..2b8bbc84e34f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -278,8 +278,8 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) rx_ring->netdev, rx_ring->rx_bi); dev_info(&pf->pdev->dev, - " rx_rings[%i]: state = %li, queue_index = %d, reg_idx = %d\n", - i, rx_ring->state, + " rx_rings[%i]: state = %lu, queue_index = %d, reg_idx = %d\n", + i, *rx_ring->state, rx_ring->queue_index, rx_ring->reg_idx); dev_info(&pf->pdev->dev, @@ -334,8 +334,8 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) tx_ring->netdev, tx_ring->tx_bi); dev_info(&pf->pdev->dev, - " tx_rings[%i]: state = %li, queue_index = %d, reg_idx = %d\n", - i, tx_ring->state, + " tx_rings[%i]: state = %lu, queue_index = %d, reg_idx = %d\n", + i, *tx_ring->state, tx_ring->queue_index, tx_ring->reg_idx); dev_info(&pf->pdev->dev, @@ -798,8 +798,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp, */ if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) { pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; - i40e_do_reset_safe(pf, - BIT_ULL(__I40E_PF_RESET_REQUESTED)); + i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG); } vsi = i40e_vsi_setup(pf, I40E_VSI_VMDQ2, vsi_seid, 0); diff --git a/drivers/net/ethernet/intel/i40e/i40e_diag.c b/drivers/net/ethernet/intel/i40e/i40e_diag.c index f141e78d409e..76ed56641864 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_diag.c +++ b/drivers/net/ethernet/intel/i40e/i40e_diag.c @@ -36,7 +36,9 @@ static i40e_status i40e_diag_reg_pattern_test(struct i40e_hw *hw, u32 reg, u32 mask) { - const u32 patterns[] = {0x5A5A5A5A, 0xA5A5A5A5, 0x00000000, 0xFFFFFFFF}; + static const u32 patterns[] = { + 0x5A5A5A5A, 0xA5A5A5A5, 0x00000000, 0xFFFFFFFF + }; u32 pat, val, orig_val; int i; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 1136d02e2e95..9eb618799a30 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -227,6 +227,8 @@ static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = { I40E_PRIV_FLAG("veb-stats", I40E_FLAG_VEB_STATS_ENABLED, 0), I40E_PRIV_FLAG("hw-atr-eviction", I40E_FLAG_HW_ATR_EVICT_ENABLED, 0), I40E_PRIV_FLAG("legacy-rx", I40E_FLAG_LEGACY_RX, 0), + I40E_PRIV_FLAG("disable-source-pruning", + I40E_FLAG_SOURCE_PRUNING_DISABLED, 0), }; #define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gstrings_priv_flags) @@ -251,428 +253,557 @@ static void i40e_partition_setting_complaint(struct i40e_pf *pf) /** * i40e_phy_type_to_ethtool - convert the phy_types to ethtool link modes - * @phy_types: PHY types to convert - * @supported: pointer to the ethtool supported variable to fill in - * @advertising: pointer to the ethtool advertising variable to fill in + * @pf: PF struct with phy_types + * @ks: ethtool link ksettings struct to fill out * **/ -static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported, - u32 *advertising) +static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, + struct ethtool_link_ksettings *ks) { struct i40e_link_status *hw_link_info = &pf->hw.phy.link_info; u64 phy_types = pf->hw.phy.phy_types; - *supported = 0x0; - *advertising = 0x0; + ethtool_link_ksettings_zero_link_mode(ks, supported); + ethtool_link_ksettings_zero_link_mode(ks, advertising); if (phy_types & I40E_CAP_PHY_TYPE_SGMII) { - *supported |= SUPPORTED_Autoneg | - SUPPORTED_1000baseT_Full; - *advertising |= ADVERTISED_Autoneg; + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseT_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) - *advertising |= ADVERTISED_1000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseT_Full); if (pf->hw_features & I40E_HW_100M_SGMII_CAPABLE) { - *supported |= SUPPORTED_100baseT_Full; - *advertising |= ADVERTISED_100baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, + 100baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 100baseT_Full); } } if (phy_types & I40E_CAP_PHY_TYPE_XAUI || phy_types & I40E_CAP_PHY_TYPE_XFI || phy_types & I40E_CAP_PHY_TYPE_SFI || phy_types & I40E_CAP_PHY_TYPE_10GBASE_SFPP_CU || - phy_types & I40E_CAP_PHY_TYPE_10GBASE_AOC) - *supported |= SUPPORTED_10000baseT_Full; - if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1_CU || - phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1 || - phy_types & I40E_CAP_PHY_TYPE_10GBASE_T || - phy_types & I40E_CAP_PHY_TYPE_10GBASE_SR || - phy_types & I40E_CAP_PHY_TYPE_10GBASE_LR) { - *supported |= SUPPORTED_Autoneg | - SUPPORTED_10000baseT_Full; - *advertising |= ADVERTISED_Autoneg; + phy_types & I40E_CAP_PHY_TYPE_10GBASE_AOC) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseT_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) - *advertising |= ADVERTISED_10000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseT_Full); + } + if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_T) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseT_Full); + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseT_Full); } if (phy_types & I40E_CAP_PHY_TYPE_XLAUI || phy_types & I40E_CAP_PHY_TYPE_XLPPI || phy_types & I40E_CAP_PHY_TYPE_40GBASE_AOC) - *supported |= SUPPORTED_40000baseCR4_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseCR4_Full); if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_CR4_CU || phy_types & I40E_CAP_PHY_TYPE_40GBASE_CR4) { - *supported |= SUPPORTED_Autoneg | - SUPPORTED_40000baseCR4_Full; - *advertising |= ADVERTISED_Autoneg; + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseCR4_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_40GB) - *advertising |= ADVERTISED_40000baseCR4_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseCR4_Full); } if (phy_types & I40E_CAP_PHY_TYPE_100BASE_TX) { - *supported |= SUPPORTED_Autoneg | - SUPPORTED_100baseT_Full; - *advertising |= ADVERTISED_Autoneg; + ethtool_link_ksettings_add_link_mode(ks, supported, + 100baseT_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB) - *advertising |= ADVERTISED_100baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 100baseT_Full); } - if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_T || - phy_types & I40E_CAP_PHY_TYPE_1000BASE_SX || - phy_types & I40E_CAP_PHY_TYPE_1000BASE_LX || - phy_types & I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL) { - *supported |= SUPPORTED_Autoneg | - SUPPORTED_1000baseT_Full; - *advertising |= ADVERTISED_Autoneg; + if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_T) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseT_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) - *advertising |= ADVERTISED_1000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseT_Full); } if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_SR4) - *supported |= SUPPORTED_40000baseSR4_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseSR4_Full); if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_LR4) - *supported |= SUPPORTED_40000baseLR4_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseLR4_Full); if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_KR4) { - *supported |= SUPPORTED_40000baseKR4_Full | - SUPPORTED_Autoneg; - *advertising |= ADVERTISED_40000baseKR4_Full | - ADVERTISED_Autoneg; + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseLR4_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseLR4_Full); } if (phy_types & I40E_CAP_PHY_TYPE_20GBASE_KR2) { - *supported |= SUPPORTED_20000baseKR2_Full | - SUPPORTED_Autoneg; - *advertising |= ADVERTISED_Autoneg; + ethtool_link_ksettings_add_link_mode(ks, supported, + 20000baseKR2_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_20GB) - *advertising |= ADVERTISED_20000baseKR2_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 20000baseKR2_Full); } - if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KR) { - if (!(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) - *supported |= SUPPORTED_10000baseKR_Full | - SUPPORTED_Autoneg; - *advertising |= ADVERTISED_Autoneg; + if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KX4) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseKX4_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) - if (!(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) - *advertising |= ADVERTISED_10000baseKR_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseKX4_Full); } - if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KX4) { - *supported |= SUPPORTED_10000baseKX4_Full | - SUPPORTED_Autoneg; - *advertising |= ADVERTISED_Autoneg; + if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KR && + !(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseKR_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) - *advertising |= ADVERTISED_10000baseKX4_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseKR_Full); } - if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_KX) { - if (!(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) - *supported |= SUPPORTED_1000baseKX_Full | - SUPPORTED_Autoneg; - *advertising |= ADVERTISED_Autoneg; + if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_KX && + !(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseKX_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) - if (!(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) - *advertising |= ADVERTISED_1000baseKX_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseKX_Full); } - if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_KR || - phy_types & I40E_CAP_PHY_TYPE_25GBASE_CR || - phy_types & I40E_CAP_PHY_TYPE_25GBASE_SR || + /* need to add 25G PHY types */ + if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_KR) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseKR_Full); + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_25GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseKR_Full); + } + if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_CR) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseCR_Full); + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_25GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseCR_Full); + } + if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_SR || phy_types & I40E_CAP_PHY_TYPE_25GBASE_LR) { - *supported |= SUPPORTED_Autoneg; - *advertising |= ADVERTISED_Autoneg; + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseSR_Full); + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_25GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseSR_Full); + } + if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_AOC || + phy_types & I40E_CAP_PHY_TYPE_25GBASE_ACC) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseCR_Full); + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_25GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseCR_Full); + } + /* need to add new 10G PHY types */ + if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1 || + phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1_CU) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseCR_Full); + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseCR_Full); + } + if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_SR) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseSR_Full); + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseSR_Full); + } + if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_LR) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseLR_Full); + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseLR_Full); + } + if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_SX || + phy_types & I40E_CAP_PHY_TYPE_1000BASE_LX || + phy_types & I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseX_Full); + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseX_Full); + } + /* Autoneg PHY types */ + if (phy_types & I40E_CAP_PHY_TYPE_SGMII || + phy_types & I40E_CAP_PHY_TYPE_40GBASE_KR4 || + phy_types & I40E_CAP_PHY_TYPE_40GBASE_CR4_CU || + phy_types & I40E_CAP_PHY_TYPE_40GBASE_CR4 || + phy_types & I40E_CAP_PHY_TYPE_25GBASE_SR || + phy_types & I40E_CAP_PHY_TYPE_25GBASE_LR || + phy_types & I40E_CAP_PHY_TYPE_25GBASE_KR || + phy_types & I40E_CAP_PHY_TYPE_25GBASE_CR || + phy_types & I40E_CAP_PHY_TYPE_20GBASE_KR2 || + phy_types & I40E_CAP_PHY_TYPE_10GBASE_T || + phy_types & I40E_CAP_PHY_TYPE_10GBASE_SR || + phy_types & I40E_CAP_PHY_TYPE_10GBASE_LR || + phy_types & I40E_CAP_PHY_TYPE_10GBASE_KX4 || + phy_types & I40E_CAP_PHY_TYPE_10GBASE_KR || + phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1_CU || + phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1 || + phy_types & I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL || + phy_types & I40E_CAP_PHY_TYPE_1000BASE_T || + phy_types & I40E_CAP_PHY_TYPE_1000BASE_SX || + phy_types & I40E_CAP_PHY_TYPE_1000BASE_LX || + phy_types & I40E_CAP_PHY_TYPE_1000BASE_KX || + phy_types & I40E_CAP_PHY_TYPE_100BASE_TX) { + ethtool_link_ksettings_add_link_mode(ks, supported, + Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + Autoneg); } } /** * i40e_get_settings_link_up - Get the Link settings for when link is up * @hw: hw structure - * @ecmd: ethtool command to fill in + * @ks: ethtool ksettings to fill in * @netdev: network interface device structure - * + * @pf: pointer to physical function struct **/ static void i40e_get_settings_link_up(struct i40e_hw *hw, - struct ethtool_link_ksettings *cmd, + struct ethtool_link_ksettings *ks, struct net_device *netdev, struct i40e_pf *pf) { struct i40e_link_status *hw_link_info = &hw->phy.link_info; + struct ethtool_link_ksettings cap_ksettings; u32 link_speed = hw_link_info->link_speed; - u32 e_advertising = 0x0; - u32 e_supported = 0x0; - u32 supported, advertising; - - ethtool_convert_link_mode_to_legacy_u32(&supported, - cmd->link_modes.supported); - ethtool_convert_link_mode_to_legacy_u32(&advertising, - cmd->link_modes.advertising); /* Initialize supported and advertised settings based on phy settings */ switch (hw_link_info->phy_type) { case I40E_PHY_TYPE_40GBASE_CR4: case I40E_PHY_TYPE_40GBASE_CR4_CU: - supported = SUPPORTED_Autoneg | - SUPPORTED_40000baseCR4_Full; - advertising = ADVERTISED_Autoneg | - ADVERTISED_40000baseCR4_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseCR4_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseCR4_Full); break; case I40E_PHY_TYPE_XLAUI: case I40E_PHY_TYPE_XLPPI: case I40E_PHY_TYPE_40GBASE_AOC: - supported = SUPPORTED_40000baseCR4_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseCR4_Full); break; case I40E_PHY_TYPE_40GBASE_SR4: - supported = SUPPORTED_40000baseSR4_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseSR4_Full); break; case I40E_PHY_TYPE_40GBASE_LR4: - supported = SUPPORTED_40000baseLR4_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseLR4_Full); break; + case I40E_PHY_TYPE_25GBASE_SR: + case I40E_PHY_TYPE_25GBASE_LR: case I40E_PHY_TYPE_10GBASE_SR: case I40E_PHY_TYPE_10GBASE_LR: case I40E_PHY_TYPE_1000BASE_SX: case I40E_PHY_TYPE_1000BASE_LX: - supported = SUPPORTED_10000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseSR_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseSR_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseSR_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseSR_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseLR_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseLR_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseX_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseX_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseT_Full); if (hw_link_info->module_type[2] & I40E_MODULE_TYPE_1000BASE_SX || hw_link_info->module_type[2] & I40E_MODULE_TYPE_1000BASE_LX) { - supported |= SUPPORTED_1000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseT_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) - advertising |= ADVERTISED_1000baseT_Full; + ethtool_link_ksettings_add_link_mode( + ks, advertising, 1000baseT_Full); } if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) - advertising |= ADVERTISED_10000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseT_Full); break; case I40E_PHY_TYPE_10GBASE_T: case I40E_PHY_TYPE_1000BASE_T: case I40E_PHY_TYPE_100BASE_TX: - supported = SUPPORTED_Autoneg | - SUPPORTED_10000baseT_Full | - SUPPORTED_1000baseT_Full | - SUPPORTED_100baseT_Full; - advertising = ADVERTISED_Autoneg; + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 100baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) - advertising |= ADVERTISED_10000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseT_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) - advertising |= ADVERTISED_1000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseT_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB) - advertising |= ADVERTISED_100baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 100baseT_Full); break; case I40E_PHY_TYPE_1000BASE_T_OPTICAL: - supported = SUPPORTED_Autoneg | - SUPPORTED_1000baseT_Full; - advertising = ADVERTISED_Autoneg | - ADVERTISED_1000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseT_Full); break; case I40E_PHY_TYPE_10GBASE_CR1_CU: case I40E_PHY_TYPE_10GBASE_CR1: - supported = SUPPORTED_Autoneg | - SUPPORTED_10000baseT_Full; - advertising = ADVERTISED_Autoneg | - ADVERTISED_10000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseT_Full); break; case I40E_PHY_TYPE_XAUI: case I40E_PHY_TYPE_XFI: case I40E_PHY_TYPE_SFI: case I40E_PHY_TYPE_10GBASE_SFPP_CU: case I40E_PHY_TYPE_10GBASE_AOC: - supported = SUPPORTED_10000baseT_Full; - advertising = SUPPORTED_10000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseT_Full); + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseT_Full); break; case I40E_PHY_TYPE_SGMII: - supported = SUPPORTED_Autoneg | - SUPPORTED_1000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseT_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) - advertising |= ADVERTISED_1000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseT_Full); if (pf->hw_features & I40E_HW_100M_SGMII_CAPABLE) { - supported |= SUPPORTED_100baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, + 100baseT_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB) - advertising |= ADVERTISED_100baseT_Full; + ethtool_link_ksettings_add_link_mode( + ks, advertising, 100baseT_Full); } break; case I40E_PHY_TYPE_40GBASE_KR4: + case I40E_PHY_TYPE_25GBASE_KR: case I40E_PHY_TYPE_20GBASE_KR2: case I40E_PHY_TYPE_10GBASE_KR: case I40E_PHY_TYPE_10GBASE_KX4: case I40E_PHY_TYPE_1000BASE_KX: - supported |= SUPPORTED_40000baseKR4_Full | - SUPPORTED_20000baseKR2_Full | - SUPPORTED_10000baseKR_Full | - SUPPORTED_10000baseKX4_Full | - SUPPORTED_1000baseKX_Full | - SUPPORTED_Autoneg; - advertising |= ADVERTISED_40000baseKR4_Full | - ADVERTISED_20000baseKR2_Full | - ADVERTISED_10000baseKR_Full | - ADVERTISED_10000baseKX4_Full | - ADVERTISED_1000baseKX_Full | - ADVERTISED_Autoneg; + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseKR4_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseKR_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 20000baseKR2_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseKR_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseKX4_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseKX_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseKR4_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseKR_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 20000baseKR2_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseKR_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseKX4_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseKX_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); break; - case I40E_PHY_TYPE_25GBASE_KR: case I40E_PHY_TYPE_25GBASE_CR: - case I40E_PHY_TYPE_25GBASE_SR: - case I40E_PHY_TYPE_25GBASE_LR: - supported = SUPPORTED_Autoneg; - advertising = ADVERTISED_Autoneg; - /* TODO: add speeds when ethtool is ready to support*/ + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseCR_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseCR_Full); + break; + case I40E_PHY_TYPE_25GBASE_AOC: + case I40E_PHY_TYPE_25GBASE_ACC: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseCR_Full); + + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseCR_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseCR_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseCR_Full); break; default: /* if we got here and link is up something bad is afoot */ - netdev_info(netdev, "WARNING: Link is up but PHY type 0x%x is not recognized.\n", + netdev_info(netdev, + "WARNING: Link is up but PHY type 0x%x is not recognized.\n", hw_link_info->phy_type); } /* Now that we've worked out everything that could be supported by the - * current PHY type, get what is supported by the NVM and them to - * get what is truly supported + * current PHY type, get what is supported by the NVM and intersect + * them to get what is truly supported */ - i40e_phy_type_to_ethtool(pf, &e_supported, - &e_advertising); - - supported = supported & e_supported; - advertising = advertising & e_advertising; + memset(&cap_ksettings, 0, sizeof(struct ethtool_link_ksettings)); + i40e_phy_type_to_ethtool(pf, &cap_ksettings); + ethtool_intersect_link_masks(ks, &cap_ksettings); /* Set speed and duplex */ switch (link_speed) { case I40E_LINK_SPEED_40GB: - cmd->base.speed = SPEED_40000; + ks->base.speed = SPEED_40000; break; case I40E_LINK_SPEED_25GB: -#ifdef SPEED_25000 - cmd->base.speed = SPEED_25000; -#else - netdev_info(netdev, - "Speed is 25G, display not supported by this version of ethtool.\n"); -#endif + ks->base.speed = SPEED_25000; break; case I40E_LINK_SPEED_20GB: - cmd->base.speed = SPEED_20000; + ks->base.speed = SPEED_20000; break; case I40E_LINK_SPEED_10GB: - cmd->base.speed = SPEED_10000; + ks->base.speed = SPEED_10000; break; case I40E_LINK_SPEED_1GB: - cmd->base.speed = SPEED_1000; + ks->base.speed = SPEED_1000; break; case I40E_LINK_SPEED_100MB: - cmd->base.speed = SPEED_100; + ks->base.speed = SPEED_100; break; default: break; } - cmd->base.duplex = DUPLEX_FULL; - - ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, - supported); - ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, - advertising); + ks->base.duplex = DUPLEX_FULL; } /** * i40e_get_settings_link_down - Get the Link settings for when link is down * @hw: hw structure - * @ecmd: ethtool command to fill in + * @ks: ethtool ksettings to fill in + * @pf: pointer to physical function struct * * Reports link settings that can be determined when link is down **/ static void i40e_get_settings_link_down(struct i40e_hw *hw, - struct ethtool_link_ksettings *cmd, + struct ethtool_link_ksettings *ks, struct i40e_pf *pf) { - u32 supported, advertising; - /* link is down and the driver needs to fall back on * supported phy types to figure out what info to display */ - i40e_phy_type_to_ethtool(pf, &supported, &advertising); - - ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, - supported); - ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, - advertising); + i40e_phy_type_to_ethtool(pf, ks); /* With no link speed and duplex are unknown */ - cmd->base.speed = SPEED_UNKNOWN; - cmd->base.duplex = DUPLEX_UNKNOWN; + ks->base.speed = SPEED_UNKNOWN; + ks->base.duplex = DUPLEX_UNKNOWN; } /** - * i40e_get_settings - Get Link Speed and Duplex settings + * i40e_get_link_ksettings - Get Link Speed and Duplex settings * @netdev: network interface device structure - * @ecmd: ethtool command + * @ks: ethtool ksettings * * Reports speed/duplex settings based on media_type **/ static int i40e_get_link_ksettings(struct net_device *netdev, - struct ethtool_link_ksettings *cmd) + struct ethtool_link_ksettings *ks) { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_pf *pf = np->vsi->back; struct i40e_hw *hw = &pf->hw; struct i40e_link_status *hw_link_info = &hw->phy.link_info; bool link_up = hw_link_info->link_info & I40E_AQ_LINK_UP; - u32 advertising; + + ethtool_link_ksettings_zero_link_mode(ks, supported); + ethtool_link_ksettings_zero_link_mode(ks, advertising); if (link_up) - i40e_get_settings_link_up(hw, cmd, netdev, pf); + i40e_get_settings_link_up(hw, ks, netdev, pf); else - i40e_get_settings_link_down(hw, cmd, pf); + i40e_get_settings_link_down(hw, ks, pf); /* Now set the settings that don't rely on link being up/down */ /* Set autoneg settings */ - cmd->base.autoneg = ((hw_link_info->an_info & I40E_AQ_AN_COMPLETED) ? - AUTONEG_ENABLE : AUTONEG_DISABLE); + ks->base.autoneg = ((hw_link_info->an_info & I40E_AQ_AN_COMPLETED) ? + AUTONEG_ENABLE : AUTONEG_DISABLE); + /* Set media type settings */ switch (hw->phy.media_type) { case I40E_MEDIA_TYPE_BACKPLANE: - ethtool_link_ksettings_add_link_mode(cmd, supported, - Autoneg); - ethtool_link_ksettings_add_link_mode(cmd, supported, - Backplane); - ethtool_link_ksettings_add_link_mode(cmd, advertising, - Autoneg); - ethtool_link_ksettings_add_link_mode(cmd, advertising, + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, Backplane); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, Backplane); - cmd->base.port = PORT_NONE; + ks->base.port = PORT_NONE; break; case I40E_MEDIA_TYPE_BASET: - ethtool_link_ksettings_add_link_mode(cmd, supported, TP); - ethtool_link_ksettings_add_link_mode(cmd, advertising, TP); - cmd->base.port = PORT_TP; + ethtool_link_ksettings_add_link_mode(ks, supported, TP); + ethtool_link_ksettings_add_link_mode(ks, advertising, TP); + ks->base.port = PORT_TP; break; case I40E_MEDIA_TYPE_DA: case I40E_MEDIA_TYPE_CX4: - ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE); - ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE); - cmd->base.port = PORT_DA; + ethtool_link_ksettings_add_link_mode(ks, supported, FIBRE); + ethtool_link_ksettings_add_link_mode(ks, advertising, FIBRE); + ks->base.port = PORT_DA; break; case I40E_MEDIA_TYPE_FIBER: - ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE); - cmd->base.port = PORT_FIBRE; + ethtool_link_ksettings_add_link_mode(ks, supported, FIBRE); + ks->base.port = PORT_FIBRE; break; case I40E_MEDIA_TYPE_UNKNOWN: default: - cmd->base.port = PORT_OTHER; + ks->base.port = PORT_OTHER; break; } /* Set flow control settings */ - ethtool_link_ksettings_add_link_mode(cmd, supported, Pause); + ethtool_link_ksettings_add_link_mode(ks, supported, Pause); switch (hw->fc.requested_mode) { case I40E_FC_FULL: - ethtool_link_ksettings_add_link_mode(cmd, advertising, - Pause); + ethtool_link_ksettings_add_link_mode(ks, advertising, Pause); break; case I40E_FC_TX_PAUSE: - ethtool_link_ksettings_add_link_mode(cmd, advertising, + ethtool_link_ksettings_add_link_mode(ks, advertising, Asym_Pause); break; case I40E_FC_RX_PAUSE: - ethtool_link_ksettings_add_link_mode(cmd, advertising, - Pause); - ethtool_link_ksettings_add_link_mode(cmd, advertising, + ethtool_link_ksettings_add_link_mode(ks, advertising, Pause); + ethtool_link_ksettings_add_link_mode(ks, advertising, Asym_Pause); break; default: - ethtool_convert_link_mode_to_legacy_u32( - &advertising, cmd->link_modes.advertising); - - advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause); - - ethtool_convert_legacy_u32_to_link_mode( - cmd->link_modes.advertising, advertising); + ethtool_link_ksettings_del_link_mode(ks, advertising, Pause); + ethtool_link_ksettings_del_link_mode(ks, advertising, + Asym_Pause); break; } @@ -680,30 +811,28 @@ static int i40e_get_link_ksettings(struct net_device *netdev, } /** - * i40e_set_settings - Set Speed and Duplex + * i40e_set_link_ksettings - Set Speed and Duplex * @netdev: network interface device structure - * @ecmd: ethtool command + * @ks: ethtool ksettings * * Set speed/duplex per media_types advertised/forced **/ static int i40e_set_link_ksettings(struct net_device *netdev, - const struct ethtool_link_ksettings *cmd) + const struct ethtool_link_ksettings *ks) { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_aq_get_phy_abilities_resp abilities; + struct ethtool_link_ksettings safe_ks; + struct ethtool_link_ksettings copy_ks; struct i40e_aq_set_phy_config config; struct i40e_pf *pf = np->vsi->back; struct i40e_vsi *vsi = np->vsi; struct i40e_hw *hw = &pf->hw; - struct ethtool_link_ksettings safe_cmd; - struct ethtool_link_ksettings copy_cmd; + bool autoneg_changed = false; i40e_status status = 0; - bool change = false; int timeout = 50; int err = 0; - u32 autoneg; - u32 advertise; - u32 tmp; + u8 autoneg; /* Changing port settings is not supported if this isn't the * port's controlling PF @@ -712,17 +841,14 @@ static int i40e_set_link_ksettings(struct net_device *netdev, i40e_partition_setting_complaint(pf); return -EOPNOTSUPP; } - if (vsi != pf->vsi[pf->lan_vsi]) return -EOPNOTSUPP; - if (hw->phy.media_type != I40E_MEDIA_TYPE_BASET && hw->phy.media_type != I40E_MEDIA_TYPE_FIBER && hw->phy.media_type != I40E_MEDIA_TYPE_BACKPLANE && hw->phy.media_type != I40E_MEDIA_TYPE_DA && hw->phy.link_info.link_info & I40E_AQ_LINK_UP) return -EOPNOTSUPP; - if (hw->device_id == I40E_DEV_ID_KX_B || hw->device_id == I40E_DEV_ID_KX_C || hw->device_id == I40E_DEV_ID_20G_KR2 || @@ -731,31 +857,37 @@ static int i40e_set_link_ksettings(struct net_device *netdev, return -EOPNOTSUPP; } - /* copy the cmd to copy_cmd to avoid modifying the origin */ - memcpy(©_cmd, cmd, sizeof(struct ethtool_link_ksettings)); + /* copy the ksettings to copy_ks to avoid modifying the origin */ + memcpy(©_ks, ks, sizeof(struct ethtool_link_ksettings)); - /* get our own copy of the bits to check against */ - memset(&safe_cmd, 0, sizeof(struct ethtool_link_ksettings)); - i40e_get_link_ksettings(netdev, &safe_cmd); + /* save autoneg out of ksettings */ + autoneg = copy_ks.base.autoneg; - /* save autoneg and speed out of cmd */ - autoneg = cmd->base.autoneg; - ethtool_convert_link_mode_to_legacy_u32(&advertise, - cmd->link_modes.advertising); + memset(&safe_ks, 0, sizeof(safe_ks)); + /* Get link modes supported by hardware and check against modes + * requested by the user. Return an error if unsupported mode was set. + */ + i40e_phy_type_to_ethtool(pf, &safe_ks); + if (!bitmap_subset(copy_ks.link_modes.advertising, + safe_ks.link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NBITS)) + return -EINVAL; - /* set autoneg and speed back to what they currently are */ - copy_cmd.base.autoneg = safe_cmd.base.autoneg; - ethtool_convert_link_mode_to_legacy_u32( - &tmp, safe_cmd.link_modes.advertising); - ethtool_convert_legacy_u32_to_link_mode( - copy_cmd.link_modes.advertising, tmp); + /* get our own copy of the bits to check against */ + memset(&safe_ks, 0, sizeof(struct ethtool_link_ksettings)); + safe_ks.base.cmd = copy_ks.base.cmd; + safe_ks.base.link_mode_masks_nwords = + copy_ks.base.link_mode_masks_nwords; + i40e_get_link_ksettings(netdev, &safe_ks); - copy_cmd.base.cmd = safe_cmd.base.cmd; + /* set autoneg back to what it currently is */ + copy_ks.base.autoneg = safe_ks.base.autoneg; - /* If copy_cmd and safe_cmd are not the same now, then they are - * trying to set something that we do not support + /* If copy_ks.base and safe_ks.base are not the same now, then they are + * trying to set something that we do not support. */ - if (memcmp(©_cmd, &safe_cmd, sizeof(struct ethtool_link_ksettings))) + if (memcmp(©_ks.base, &safe_ks.base, + sizeof(struct ethtool_link_settings))) return -EOPNOTSUPP; while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state)) { @@ -784,8 +916,9 @@ static int i40e_set_link_ksettings(struct net_device *netdev, /* If autoneg was not already enabled */ if (!(hw->phy.link_info.an_info & I40E_AQ_AN_COMPLETED)) { /* If autoneg is not supported, return error */ - if (!ethtool_link_ksettings_test_link_mode( - &safe_cmd, supported, Autoneg)) { + if (!ethtool_link_ksettings_test_link_mode(&safe_ks, + supported, + Autoneg)) { netdev_info(netdev, "Autoneg not supported on this phy\n"); err = -EINVAL; goto done; @@ -793,7 +926,7 @@ static int i40e_set_link_ksettings(struct net_device *netdev, /* Autoneg is allowed to change */ config.abilities = abilities.abilities | I40E_AQ_PHY_ENABLE_AN; - change = true; + autoneg_changed = true; } } else { /* If autoneg is currently enabled */ @@ -801,8 +934,9 @@ static int i40e_set_link_ksettings(struct net_device *netdev, /* If autoneg is supported 10GBASE_T is the only PHY * that can disable it, so otherwise return error */ - if (ethtool_link_ksettings_test_link_mode( - &safe_cmd, supported, Autoneg) && + if (ethtool_link_ksettings_test_link_mode(&safe_ks, + supported, + Autoneg) && hw->phy.link_info.phy_type != I40E_PHY_TYPE_10GBASE_T) { netdev_info(netdev, "Autoneg cannot be disabled on this phy\n"); @@ -812,32 +946,49 @@ static int i40e_set_link_ksettings(struct net_device *netdev, /* Autoneg is allowed to change */ config.abilities = abilities.abilities & ~I40E_AQ_PHY_ENABLE_AN; - change = true; + autoneg_changed = true; } } - ethtool_convert_link_mode_to_legacy_u32(&tmp, - safe_cmd.link_modes.supported); - if (advertise & ~tmp) { - err = -EINVAL; - goto done; - } - - if (advertise & ADVERTISED_100baseT_Full) + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 100baseT_Full)) config.link_speed |= I40E_LINK_SPEED_100MB; - if (advertise & ADVERTISED_1000baseT_Full || - advertise & ADVERTISED_1000baseKX_Full) + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 1000baseT_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 1000baseX_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 1000baseKX_Full)) config.link_speed |= I40E_LINK_SPEED_1GB; - if (advertise & ADVERTISED_10000baseT_Full || - advertise & ADVERTISED_10000baseKX4_Full || - advertise & ADVERTISED_10000baseKR_Full) + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseT_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseKX4_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseKR_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseCR_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseSR_Full)) config.link_speed |= I40E_LINK_SPEED_10GB; - if (advertise & ADVERTISED_20000baseKR2_Full) + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 20000baseKR2_Full)) config.link_speed |= I40E_LINK_SPEED_20GB; - if (advertise & ADVERTISED_40000baseKR4_Full || - advertise & ADVERTISED_40000baseCR4_Full || - advertise & ADVERTISED_40000baseSR4_Full || - advertise & ADVERTISED_40000baseLR4_Full) + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 25000baseCR_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 25000baseKR_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 25000baseSR_Full)) + config.link_speed |= I40E_LINK_SPEED_25GB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 40000baseKR4_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 40000baseCR4_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 40000baseSR4_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 40000baseLR4_Full)) config.link_speed |= I40E_LINK_SPEED_40GB; /* If speed didn't get set, set it to what it currently is. @@ -846,8 +997,7 @@ static int i40e_set_link_ksettings(struct net_device *netdev, */ if (!config.link_speed) config.link_speed = abilities.link_speed; - - if (change || (abilities.link_speed != config.link_speed)) { + if (autoneg_changed || abilities.link_speed != config.link_speed) { /* copy over the rest of the abilities */ config.phy_type = abilities.phy_type; config.phy_type_ext = abilities.phy_type_ext; @@ -874,7 +1024,8 @@ static int i40e_set_link_ksettings(struct net_device *netdev, /* make the aq call */ status = i40e_aq_set_phy_config(hw, &config, NULL); if (status) { - netdev_info(netdev, "Set phy config failed, err %s aq_err %s\n", + netdev_info(netdev, + "Set phy config failed, err %s aq_err %s\n", i40e_stat_str(hw, status), i40e_aq_str(hw, hw->aq.asq_last_status)); err = -EAGAIN; @@ -883,7 +1034,8 @@ static int i40e_set_link_ksettings(struct net_device *netdev, status = i40e_update_link_info(hw); if (status) - netdev_dbg(netdev, "Updating link info failed with err %s aq_err %s\n", + netdev_dbg(netdev, + "Updating link info failed with err %s aq_err %s\n", i40e_stat_str(hw, status), i40e_aq_str(hw, hw->aq.asq_last_status)); @@ -2008,7 +2160,9 @@ static int i40e_set_phys_id(struct net_device *netdev, if (!(pf->hw_features & I40E_HW_PHY_CONTROLS_LEDS)) { pf->led_status = i40e_led_get(hw); } else { - i40e_aq_set_phy_debug(hw, I40E_PHY_DEBUG_ALL, NULL); + if (!(hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE)) + i40e_aq_set_phy_debug(hw, I40E_PHY_DEBUG_ALL, + NULL); ret = i40e_led_get_phy(hw, &temp_status, &pf->phy_led_val); pf->led_status = temp_status; @@ -2033,7 +2187,8 @@ static int i40e_set_phys_id(struct net_device *netdev, ret = i40e_led_set_phy(hw, false, pf->led_status, (pf->phy_led_val | I40E_PHY_LED_MODE_ORIG)); - i40e_aq_set_phy_debug(hw, 0, NULL); + if (!(hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE)) + i40e_aq_set_phy_debug(hw, 0, NULL); } break; default: @@ -2071,14 +2226,13 @@ static int __i40e_get_coalesce(struct net_device *netdev, ec->tx_max_coalesced_frames_irq = vsi->work_limit; ec->rx_max_coalesced_frames_irq = vsi->work_limit; - /* rx and tx usecs has per queue value. If user doesn't specify the queue, - * return queue 0's value to represent. + /* rx and tx usecs has per queue value. If user doesn't specify the + * queue, return queue 0's value to represent. */ - if (queue < 0) { + if (queue < 0) queue = 0; - } else if (queue >= vsi->num_queue_pairs) { + else if (queue >= vsi->num_queue_pairs) return -EINVAL; - } rx_ring = vsi->rx_rings[queue]; tx_ring = vsi->tx_rings[queue]; @@ -2092,7 +2246,6 @@ static int __i40e_get_coalesce(struct net_device *netdev, ec->rx_coalesce_usecs = rx_ring->rx_itr_setting & ~I40E_ITR_DYNAMIC; ec->tx_coalesce_usecs = tx_ring->tx_itr_setting & ~I40E_ITR_DYNAMIC; - /* we use the _usecs_high to store/set the interrupt rate limit * that the hardware supports, that almost but not quite * fits the original intent of the ethtool variable, @@ -2142,7 +2295,6 @@ static int i40e_get_per_queue_coalesce(struct net_device *netdev, u32 queue, * * Change the ITR settings for a specific queue. **/ - static void i40e_set_itr_per_queue(struct i40e_vsi *vsi, struct ethtool_coalesce *ec, int queue) @@ -2264,8 +2416,8 @@ static int __i40e_set_coalesce(struct net_device *netdev, vsi->int_rate_limit); } - /* rx and tx usecs has per queue value. If user doesn't specify the queue, - * apply to all queues. + /* rx and tx usecs has per queue value. If user doesn't specify the + * queue, apply to all queues. */ if (queue < 0) { for (i = 0; i < vsi->num_queue_pairs; i++) @@ -2647,7 +2799,7 @@ static int i40e_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, switch (cmd->cmd) { case ETHTOOL_GRXRINGS: - cmd->data = vsi->num_queue_pairs; + cmd->data = vsi->rss_size; ret = 0; break; case ETHTOOL_GRXFH: @@ -3892,6 +4044,12 @@ static int i40e_set_channels(struct net_device *dev, if (vsi->type != I40E_VSI_MAIN) return -EINVAL; + /* We do not support setting channels via ethtool when TCs are + * configured through mqprio + */ + if (pf->flags & I40E_FLAG_TC_MQPRIO) + return -EINVAL; + /* verify they are not requesting separate vectors */ if (!count || ch->rx_count || ch->tx_count) return -EINVAL; @@ -3959,6 +4117,16 @@ static u32 i40e_get_rxfh_indir_size(struct net_device *netdev) return I40E_HLUT_ARRAY_SIZE; } +/** + * i40e_get_rxfh - get the rx flow hash indirection table + * @netdev: network interface device structure + * @indir: indirection table + * @key: hash key + * @hfunc: hash function + * + * Reads the indirection table directly from the hardware. Returns 0 on + * success. + **/ static int i40e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc) { @@ -4090,7 +4258,7 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) struct i40e_netdev_priv *np = netdev_priv(dev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; - u64 orig_flags, new_flags, changed_flags; + u32 orig_flags, new_flags, changed_flags; u32 i, j; orig_flags = READ_ONCE(pf->flags); @@ -4142,12 +4310,12 @@ flags_complete: return -EOPNOTSUPP; /* Compare and exchange the new flags into place. If we failed, that - * is if cmpxchg64 returns anything but the old value, this means that + * is if cmpxchg returns anything but the old value, this means that * something else has modified the flags variable since we copied it * originally. We'll just punt with an error and log something in the * message buffer. */ - if (cmpxchg64(&pf->flags, orig_flags, new_flags) != orig_flags) { + if (cmpxchg(&pf->flags, orig_flags, new_flags) != orig_flags) { dev_warn(&pf->pdev->dev, "Unable to update pf->flags as it was modified by another thread...\n"); return -EAGAIN; @@ -4189,8 +4357,9 @@ flags_complete: /* Issue reset to cause things to take effect, as additional bits * are added we will need to create a mask of bits requiring reset */ - if ((changed_flags & I40E_FLAG_VEB_STATS_ENABLED) || - ((changed_flags & I40E_FLAG_LEGACY_RX) && netif_running(dev))) + if (changed_flags & (I40E_FLAG_VEB_STATS_ENABLED | + I40E_FLAG_LEGACY_RX | + I40E_FLAG_SOURCE_PRUNING_DISABLED)) i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED), true); return 0; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 3f9e89b054ec..54ff34faca37 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1589,6 +1589,170 @@ static int i40e_set_mac(struct net_device *netdev, void *p) } /** + * i40e_config_rss_aq - Prepare for RSS using AQ commands + * @vsi: vsi structure + * @seed: RSS hash seed + **/ +static int i40e_config_rss_aq(struct i40e_vsi *vsi, const u8 *seed, + u8 *lut, u16 lut_size) +{ + struct i40e_pf *pf = vsi->back; + struct i40e_hw *hw = &pf->hw; + int ret = 0; + + if (seed) { + struct i40e_aqc_get_set_rss_key_data *seed_dw = + (struct i40e_aqc_get_set_rss_key_data *)seed; + ret = i40e_aq_set_rss_key(hw, vsi->id, seed_dw); + if (ret) { + dev_info(&pf->pdev->dev, + "Cannot set RSS key, err %s aq_err %s\n", + i40e_stat_str(hw, ret), + i40e_aq_str(hw, hw->aq.asq_last_status)); + return ret; + } + } + if (lut) { + bool pf_lut = vsi->type == I40E_VSI_MAIN ? true : false; + + ret = i40e_aq_set_rss_lut(hw, vsi->id, pf_lut, lut, lut_size); + if (ret) { + dev_info(&pf->pdev->dev, + "Cannot set RSS lut, err %s aq_err %s\n", + i40e_stat_str(hw, ret), + i40e_aq_str(hw, hw->aq.asq_last_status)); + return ret; + } + } + return ret; +} + +/** + * i40e_vsi_config_rss - Prepare for VSI(VMDq) RSS if used + * @vsi: VSI structure + **/ +static int i40e_vsi_config_rss(struct i40e_vsi *vsi) +{ + struct i40e_pf *pf = vsi->back; + u8 seed[I40E_HKEY_ARRAY_SIZE]; + u8 *lut; + int ret; + + if (!(pf->hw_features & I40E_HW_RSS_AQ_CAPABLE)) + return 0; + if (!vsi->rss_size) + vsi->rss_size = min_t(int, pf->alloc_rss_size, + vsi->num_queue_pairs); + if (!vsi->rss_size) + return -EINVAL; + lut = kzalloc(vsi->rss_table_size, GFP_KERNEL); + if (!lut) + return -ENOMEM; + + /* Use the user configured hash keys and lookup table if there is one, + * otherwise use default + */ + if (vsi->rss_lut_user) + memcpy(lut, vsi->rss_lut_user, vsi->rss_table_size); + else + i40e_fill_rss_lut(pf, lut, vsi->rss_table_size, vsi->rss_size); + if (vsi->rss_hkey_user) + memcpy(seed, vsi->rss_hkey_user, I40E_HKEY_ARRAY_SIZE); + else + netdev_rss_key_fill((void *)seed, I40E_HKEY_ARRAY_SIZE); + ret = i40e_config_rss_aq(vsi, seed, lut, vsi->rss_table_size); + kfree(lut); + return ret; +} + +/** + * i40e_vsi_setup_queue_map_mqprio - Prepares mqprio based tc_config + * @vsi: the VSI being configured, + * @ctxt: VSI context structure + * @enabled_tc: number of traffic classes to enable + * + * Prepares VSI tc_config to have queue configurations based on MQPRIO options. + **/ +static int i40e_vsi_setup_queue_map_mqprio(struct i40e_vsi *vsi, + struct i40e_vsi_context *ctxt, + u8 enabled_tc) +{ + u16 qcount = 0, max_qcount, qmap, sections = 0; + int i, override_q, pow, num_qps, ret; + u8 netdev_tc = 0, offset = 0; + + if (vsi->type != I40E_VSI_MAIN) + return -EINVAL; + sections = I40E_AQ_VSI_PROP_QUEUE_MAP_VALID; + sections |= I40E_AQ_VSI_PROP_SCHED_VALID; + vsi->tc_config.numtc = vsi->mqprio_qopt.qopt.num_tc; + vsi->tc_config.enabled_tc = enabled_tc ? enabled_tc : 1; + num_qps = vsi->mqprio_qopt.qopt.count[0]; + + /* find the next higher power-of-2 of num queue pairs */ + pow = ilog2(num_qps); + if (!is_power_of_2(num_qps)) + pow++; + qmap = (offset << I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT) | + (pow << I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT); + + /* Setup queue offset/count for all TCs for given VSI */ + max_qcount = vsi->mqprio_qopt.qopt.count[0]; + for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { + /* See if the given TC is enabled for the given VSI */ + if (vsi->tc_config.enabled_tc & BIT(i)) { + offset = vsi->mqprio_qopt.qopt.offset[i]; + qcount = vsi->mqprio_qopt.qopt.count[i]; + if (qcount > max_qcount) + max_qcount = qcount; + vsi->tc_config.tc_info[i].qoffset = offset; + vsi->tc_config.tc_info[i].qcount = qcount; + vsi->tc_config.tc_info[i].netdev_tc = netdev_tc++; + } else { + /* TC is not enabled so set the offset to + * default queue and allocate one queue + * for the given TC. + */ + vsi->tc_config.tc_info[i].qoffset = 0; + vsi->tc_config.tc_info[i].qcount = 1; + vsi->tc_config.tc_info[i].netdev_tc = 0; + } + } + + /* Set actual Tx/Rx queue pairs */ + vsi->num_queue_pairs = offset + qcount; + + /* Setup queue TC[0].qmap for given VSI context */ + ctxt->info.tc_mapping[0] = cpu_to_le16(qmap); + ctxt->info.mapping_flags |= cpu_to_le16(I40E_AQ_VSI_QUE_MAP_CONTIG); + ctxt->info.queue_mapping[0] = cpu_to_le16(vsi->base_queue); + ctxt->info.valid_sections |= cpu_to_le16(sections); + + /* Reconfigure RSS for main VSI with max queue count */ + vsi->rss_size = max_qcount; + ret = i40e_vsi_config_rss(vsi); + if (ret) { + dev_info(&vsi->back->pdev->dev, + "Failed to reconfig rss for num_queues (%u)\n", + max_qcount); + return ret; + } + vsi->reconfig_rss = true; + dev_dbg(&vsi->back->pdev->dev, + "Reconfigured rss with num_queues (%u)\n", max_qcount); + + /* Find queue count available for channel VSIs and starting offset + * for channel VSIs + */ + override_q = vsi->mqprio_qopt.qopt.count[0]; + if (override_q && override_q < vsi->num_queue_pairs) { + vsi->cnt_q_avail = vsi->num_queue_pairs - override_q; + vsi->next_base_queue = override_q; + } + return 0; +} + +/** * i40e_vsi_setup_queue_map - Setup a VSI queue map based on enabled_tc * @vsi: the VSI being setup * @ctxt: VSI context structure @@ -1626,7 +1790,7 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, numtc = 1; } } else { - /* At least TC0 is enabled in case of non-DCB case */ + /* At least TC0 is enabled in non-DCB, non-MQPRIO case */ numtc = 1; } @@ -1776,11 +1940,6 @@ static void i40e_set_rx_mode(struct net_device *netdev) vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; vsi->back->flags |= I40E_FLAG_FILTER_SYNC; } - - /* schedule our worker thread which will take care of - * applying the new filter changes - */ - i40e_service_event_schedule(vsi->back); } /** @@ -2884,22 +3043,18 @@ static void i40e_vsi_free_rx_resources(struct i40e_vsi *vsi) **/ static void i40e_config_xps_tx_ring(struct i40e_ring *ring) { - struct i40e_vsi *vsi = ring->vsi; + int cpu; - if (!ring->q_vector || !ring->netdev) + if (!ring->q_vector || !ring->netdev || ring->ch) return; - if ((vsi->tc_config.numtc <= 1) && - !test_and_set_bit(__I40E_TX_XPS_INIT_DONE, &ring->state)) { - netif_set_xps_queue(ring->netdev, - get_cpu_mask(ring->q_vector->v_idx), - ring->queue_index); - } + /* We only initialize XPS once, so as not to overwrite user settings */ + if (test_and_set_bit(__I40E_TX_XPS_INIT_DONE, ring->state)) + return; - /* schedule our worker thread which will take care of - * applying the new filter changes - */ - i40e_service_event_schedule(vsi->back); + cpu = cpumask_local_spread(ring->q_vector->v_idx, -1); + netif_set_xps_queue(ring->netdev, get_cpu_mask(cpu), + ring->queue_index); } /** @@ -2953,7 +3108,14 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring) * initialization. This has to be done regardless of * DCB as by default everything is mapped to TC0. */ - tx_ctx.rdylist = le16_to_cpu(vsi->info.qs_handle[ring->dcb_tc]); + + if (ring->ch) + tx_ctx.rdylist = + le16_to_cpu(ring->ch->info.qs_handle[ring->dcb_tc]); + + else + tx_ctx.rdylist = le16_to_cpu(vsi->info.qs_handle[ring->dcb_tc]); + tx_ctx.rdylist_act = 0; /* clear the context in the HMC */ @@ -2975,12 +3137,23 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring) } /* Now associate this queue with this PCI function */ - if (vsi->type == I40E_VSI_VMDQ2) { - qtx_ctl = I40E_QTX_CTL_VM_QUEUE; - qtx_ctl |= ((vsi->id) << I40E_QTX_CTL_VFVM_INDX_SHIFT) & - I40E_QTX_CTL_VFVM_INDX_MASK; + if (ring->ch) { + if (ring->ch->type == I40E_VSI_VMDQ2) + qtx_ctl = I40E_QTX_CTL_VM_QUEUE; + else + return -EINVAL; + + qtx_ctl |= (ring->ch->vsi_number << + I40E_QTX_CTL_VFVM_INDX_SHIFT) & + I40E_QTX_CTL_VFVM_INDX_MASK; } else { - qtx_ctl = I40E_QTX_CTL_PF_QUEUE; + if (vsi->type == I40E_VSI_VMDQ2) { + qtx_ctl = I40E_QTX_CTL_VM_QUEUE; + qtx_ctl |= ((vsi->id) << I40E_QTX_CTL_VFVM_INDX_SHIFT) & + I40E_QTX_CTL_VFVM_INDX_MASK; + } else { + qtx_ctl = I40E_QTX_CTL_PF_QUEUE; + } } qtx_ctl |= ((hw->pf_id << I40E_QTX_CTL_PF_INDX_SHIFT) & @@ -3009,7 +3182,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) struct i40e_hmc_obj_rxq rx_ctx; i40e_status err = 0; - ring->state = 0; + bitmap_zero(ring->state, __I40E_RING_STATE_NBITS); /* clear the context structure first */ memset(&rx_ctx, 0, sizeof(rx_ctx)); @@ -3034,7 +3207,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) if (hw->revision_id == 0) rx_ctx.lrxqthresh = 0; else - rx_ctx.lrxqthresh = 2; + rx_ctx.lrxqthresh = 1; rx_ctx.crcstrip = 1; rx_ctx.l2tsel = 1; /* this controls whether VLAN is stripped from inner headers */ @@ -3149,6 +3322,7 @@ static void i40e_vsi_config_dcb_rings(struct i40e_vsi *vsi) rx_ring->dcb_tc = 0; tx_ring->dcb_tc = 0; } + return; } for (n = 0; n < I40E_MAX_TRAFFIC_CLASS; n++) { @@ -3407,15 +3581,14 @@ void i40e_irq_dynamic_disable_icr0(struct i40e_pf *pf) /** * i40e_irq_dynamic_enable_icr0 - Enable default interrupt generation for icr0 * @pf: board private structure - * @clearpba: true when all pending interrupt events should be cleared **/ -void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf, bool clearpba) +void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf) { struct i40e_hw *hw = &pf->hw; u32 val; val = I40E_PFINT_DYN_CTL0_INTENA_MASK | - (clearpba ? I40E_PFINT_DYN_CTL0_CLEARPBA_MASK : 0) | + I40E_PFINT_DYN_CTL0_CLEARPBA_MASK | (I40E_ITR_NONE << I40E_PFINT_DYN_CTL0_ITR_INDX_SHIFT); wr32(hw, I40E_PFINT_DYN_CTL0, val); @@ -3482,6 +3655,7 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename) int tx_int_idx = 0; int vector, err; int irq_num; + int cpu; for (vector = 0; vector < q_vectors; vector++) { struct i40e_q_vector *q_vector = vsi->q_vectors[vector]; @@ -3517,10 +3691,14 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename) q_vector->affinity_notify.notify = i40e_irq_affinity_notify; q_vector->affinity_notify.release = i40e_irq_affinity_release; irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify); - /* get_cpu_mask returns a static constant mask with - * a permanent lifetime so it's ok to use here. + /* Spread affinity hints out across online CPUs. + * + * get_cpu_mask returns a static constant mask with + * a permanent lifetime so it's ok to pass to + * irq_set_affinity_hint without making a copy. */ - irq_set_affinity_hint(irq_num, get_cpu_mask(q_vector->v_idx)); + cpu = cpumask_local_spread(q_vector->v_idx, -1); + irq_set_affinity_hint(irq_num, get_cpu_mask(cpu)); } vsi->irqs_ready = true; @@ -3596,7 +3774,7 @@ static int i40e_vsi_enable_irq(struct i40e_vsi *vsi) for (i = 0; i < vsi->num_q_vectors; i++) i40e_irq_dynamic_enable(vsi, i); } else { - i40e_irq_dynamic_enable_icr0(pf, true); + i40e_irq_dynamic_enable_icr0(pf); } i40e_flush(&pf->hw); @@ -3745,7 +3923,7 @@ enable_intr: wr32(hw, I40E_PFINT_ICR0_ENA, ena_mask); if (!test_bit(__I40E_DOWN, pf->state)) { i40e_service_event_schedule(pf); - i40e_irq_dynamic_enable_icr0(pf, false); + i40e_irq_dynamic_enable_icr0(pf); } return ret; @@ -4861,6 +5039,24 @@ static u8 i40e_dcb_get_enabled_tc(struct i40e_dcbx_config *dcbcfg) } /** + * i40e_mqprio_get_enabled_tc - Get enabled traffic classes + * @pf: PF being queried + * + * Query the current MQPRIO configuration and return the number of + * traffic classes enabled. + **/ +static u8 i40e_mqprio_get_enabled_tc(struct i40e_pf *pf) +{ + struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; + u8 num_tc = vsi->mqprio_qopt.qopt.num_tc; + u8 enabled_tc = 1, i; + + for (i = 1; i < num_tc; i++) + enabled_tc |= BIT(i); + return enabled_tc; +} + +/** * i40e_pf_get_num_tc - Get enabled traffic classes for PF * @pf: PF being queried * @@ -4873,7 +5069,10 @@ static u8 i40e_pf_get_num_tc(struct i40e_pf *pf) u8 num_tc = 0; struct i40e_dcbx_config *dcbcfg = &hw->local_dcbx_config; - /* If DCB is not enabled then always in single TC */ + if (pf->flags & I40E_FLAG_TC_MQPRIO) + return pf->vsi[pf->lan_vsi]->mqprio_qopt.qopt.num_tc; + + /* If neither MQPRIO nor DCB is enabled, then always use single TC */ if (!(pf->flags & I40E_FLAG_DCB_ENABLED)) return 1; @@ -4902,7 +5101,12 @@ static u8 i40e_pf_get_num_tc(struct i40e_pf *pf) **/ static u8 i40e_pf_get_tc_map(struct i40e_pf *pf) { - /* If DCB is not enabled for this PF then just return default TC */ + if (pf->flags & I40E_FLAG_TC_MQPRIO) + return i40e_mqprio_get_enabled_tc(pf); + + /* If neither MQPRIO nor DCB is enabled for this PF then just return + * default TC + */ if (!(pf->flags & I40E_FLAG_DCB_ENABLED)) return I40E_DEFAULT_TRAFFIC_CLASS; @@ -4992,6 +5196,16 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc, i40e_status ret; int i; + if (vsi->back->flags & I40E_FLAG_TC_MQPRIO) + return 0; + if (!vsi->mqprio_qopt.qopt.hw) { + ret = i40e_set_bw_limit(vsi, vsi->seid, 0); + if (ret) + dev_info(&vsi->back->pdev->dev, + "Failed to reset tx rate for vsi->seid %u\n", + vsi->seid); + return ret; + } bw_data.tc_valid_bits = enabled_tc; for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) bw_data.tc_bw_credits[i] = bw_share[i]; @@ -5054,6 +5268,9 @@ static void i40e_vsi_config_netdev_tc(struct i40e_vsi *vsi, u8 enabled_tc) vsi->tc_config.tc_info[i].qoffset); } + if (pf->flags & I40E_FLAG_TC_MQPRIO) + return; + /* Assign UP2TC map for the VSI */ for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) { /* Get the actual TC# for the UP */ @@ -5104,7 +5321,8 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc) int i; /* Check if enabled_tc is same as existing or new TCs */ - if (vsi->tc_config.enabled_tc == enabled_tc) + if (vsi->tc_config.enabled_tc == enabled_tc && + vsi->mqprio_qopt.mode != TC_MQPRIO_MODE_CHANNEL) return ret; /* Enable ETS TCs with equal BW Share for now across all VSIs */ @@ -5127,15 +5345,37 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc) ctxt.vf_num = 0; ctxt.uplink_seid = vsi->uplink_seid; ctxt.info = vsi->info; - i40e_vsi_setup_queue_map(vsi, &ctxt, enabled_tc, false); + if (vsi->back->flags & I40E_FLAG_TC_MQPRIO) { + ret = i40e_vsi_setup_queue_map_mqprio(vsi, &ctxt, enabled_tc); + if (ret) + goto out; + } else { + i40e_vsi_setup_queue_map(vsi, &ctxt, enabled_tc, false); + } + /* On destroying the qdisc, reset vsi->rss_size, as number of enabled + * queues changed. + */ + if (!vsi->mqprio_qopt.qopt.hw && vsi->reconfig_rss) { + vsi->rss_size = min_t(int, vsi->back->alloc_rss_size, + vsi->num_queue_pairs); + ret = i40e_vsi_config_rss(vsi); + if (ret) { + dev_info(&vsi->back->pdev->dev, + "Failed to reconfig rss for num_queues\n"); + return ret; + } + vsi->reconfig_rss = false; + } if (vsi->back->flags & I40E_FLAG_IWARP_ENABLED) { ctxt.info.valid_sections |= cpu_to_le16(I40E_AQ_VSI_PROP_QUEUE_OPT_VALID); ctxt.info.queueing_opt_flags |= I40E_AQ_VSI_QUE_OPT_TCP_ENA; } - /* Update the VSI after updating the VSI queue-mapping information */ + /* Update the VSI after updating the VSI queue-mapping + * information + */ ret = i40e_aq_update_vsi_params(&vsi->back->hw, &ctxt, NULL); if (ret) { dev_info(&vsi->back->pdev->dev, @@ -5167,6 +5407,739 @@ out: } /** + * i40e_get_link_speed - Returns link speed for the interface + * @vsi: VSI to be configured + * + **/ +int i40e_get_link_speed(struct i40e_vsi *vsi) +{ + struct i40e_pf *pf = vsi->back; + + switch (pf->hw.phy.link_info.link_speed) { + case I40E_LINK_SPEED_40GB: + return 40000; + case I40E_LINK_SPEED_25GB: + return 25000; + case I40E_LINK_SPEED_20GB: + return 20000; + case I40E_LINK_SPEED_10GB: + return 10000; + case I40E_LINK_SPEED_1GB: + return 1000; + default: + return -EINVAL; + } +} + +/** + * i40e_set_bw_limit - setup BW limit for Tx traffic based on max_tx_rate + * @vsi: VSI to be configured + * @seid: seid of the channel/VSI + * @max_tx_rate: max TX rate to be configured as BW limit + * + * Helper function to set BW limit for a given VSI + **/ +int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate) +{ + struct i40e_pf *pf = vsi->back; + u64 credits = 0; + int speed = 0; + int ret = 0; + + speed = i40e_get_link_speed(vsi); + if (max_tx_rate > speed) { + dev_err(&pf->pdev->dev, + "Invalid max tx rate %llu specified for VSI seid %d.", + max_tx_rate, seid); + return -EINVAL; + } + if (max_tx_rate && max_tx_rate < 50) { + dev_warn(&pf->pdev->dev, + "Setting max tx rate to minimum usable value of 50Mbps.\n"); + max_tx_rate = 50; + } + + /* Tx rate credits are in values of 50Mbps, 0 is disabled */ + credits = max_tx_rate; + do_div(credits, I40E_BW_CREDIT_DIVISOR); + ret = i40e_aq_config_vsi_bw_limit(&pf->hw, seid, credits, + I40E_MAX_BW_INACTIVE_ACCUM, NULL); + if (ret) + dev_err(&pf->pdev->dev, + "Failed set tx rate (%llu Mbps) for vsi->seid %u, err %s aq_err %s\n", + max_tx_rate, seid, i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + return ret; +} + +/** + * i40e_remove_queue_channels - Remove queue channels for the TCs + * @vsi: VSI to be configured + * + * Remove queue channels for the TCs + **/ +static void i40e_remove_queue_channels(struct i40e_vsi *vsi) +{ + struct i40e_channel *ch, *ch_tmp; + int ret, i; + + /* Reset rss size that was stored when reconfiguring rss for + * channel VSIs with non-power-of-2 queue count. + */ + vsi->current_rss_size = 0; + + /* perform cleanup for channels if they exist */ + if (list_empty(&vsi->ch_list)) + return; + + list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) { + struct i40e_vsi *p_vsi; + + list_del(&ch->list); + p_vsi = ch->parent_vsi; + if (!p_vsi || !ch->initialized) { + kfree(ch); + continue; + } + /* Reset queue contexts */ + for (i = 0; i < ch->num_queue_pairs; i++) { + struct i40e_ring *tx_ring, *rx_ring; + u16 pf_q; + + pf_q = ch->base_queue + i; + tx_ring = vsi->tx_rings[pf_q]; + tx_ring->ch = NULL; + + rx_ring = vsi->rx_rings[pf_q]; + rx_ring->ch = NULL; + } + + /* Reset BW configured for this VSI via mqprio */ + ret = i40e_set_bw_limit(vsi, ch->seid, 0); + if (ret) + dev_info(&vsi->back->pdev->dev, + "Failed to reset tx rate for ch->seid %u\n", + ch->seid); + + /* delete VSI from FW */ + ret = i40e_aq_delete_element(&vsi->back->hw, ch->seid, + NULL); + if (ret) + dev_err(&vsi->back->pdev->dev, + "unable to remove channel (%d) for parent VSI(%d)\n", + ch->seid, p_vsi->seid); + kfree(ch); + } + INIT_LIST_HEAD(&vsi->ch_list); +} + +/** + * i40e_is_any_channel - channel exist or not + * @vsi: ptr to VSI to which channels are associated with + * + * Returns true or false if channel(s) exist for associated VSI or not + **/ +static bool i40e_is_any_channel(struct i40e_vsi *vsi) +{ + struct i40e_channel *ch, *ch_tmp; + + list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) { + if (ch->initialized) + return true; + } + + return false; +} + +/** + * i40e_get_max_queues_for_channel + * @vsi: ptr to VSI to which channels are associated with + * + * Helper function which returns max value among the queue counts set on the + * channels/TCs created. + **/ +static int i40e_get_max_queues_for_channel(struct i40e_vsi *vsi) +{ + struct i40e_channel *ch, *ch_tmp; + int max = 0; + + list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) { + if (!ch->initialized) + continue; + if (ch->num_queue_pairs > max) + max = ch->num_queue_pairs; + } + + return max; +} + +/** + * i40e_validate_num_queues - validate num_queues w.r.t channel + * @pf: ptr to PF device + * @num_queues: number of queues + * @vsi: the parent VSI + * @reconfig_rss: indicates should the RSS be reconfigured or not + * + * This function validates number of queues in the context of new channel + * which is being established and determines if RSS should be reconfigured + * or not for parent VSI. + **/ +static int i40e_validate_num_queues(struct i40e_pf *pf, int num_queues, + struct i40e_vsi *vsi, bool *reconfig_rss) +{ + int max_ch_queues; + + if (!reconfig_rss) + return -EINVAL; + + *reconfig_rss = false; + + if (num_queues > I40E_MAX_QUEUES_PER_CH) { + dev_err(&pf->pdev->dev, + "Failed to create VMDq VSI. User requested num_queues (%d) > I40E_MAX_QUEUES_PER_VSI (%u)\n", + num_queues, I40E_MAX_QUEUES_PER_CH); + return -EINVAL; + } + + if (vsi->current_rss_size) { + if (num_queues > vsi->current_rss_size) { + dev_dbg(&pf->pdev->dev, + "Error: num_queues (%d) > vsi's current_size(%d)\n", + num_queues, vsi->current_rss_size); + return -EINVAL; + } else if ((num_queues < vsi->current_rss_size) && + (!is_power_of_2(num_queues))) { + dev_dbg(&pf->pdev->dev, + "Error: num_queues (%d) < vsi's current_size(%d), but not power of 2\n", + num_queues, vsi->current_rss_size); + return -EINVAL; + } + } + + if (!is_power_of_2(num_queues)) { + /* Find the max num_queues configured for channel if channel + * exist. + * if channel exist, then enforce 'num_queues' to be more than + * max ever queues configured for channel. + */ + max_ch_queues = i40e_get_max_queues_for_channel(vsi); + if (num_queues < max_ch_queues) { + dev_dbg(&pf->pdev->dev, + "Error: num_queues (%d) < max queues configured for channel(%d)\n", + num_queues, max_ch_queues); + return -EINVAL; + } + *reconfig_rss = true; + } + + return 0; +} + +/** + * i40e_vsi_reconfig_rss - reconfig RSS based on specified rss_size + * @vsi: the VSI being setup + * @rss_size: size of RSS, accordingly LUT gets reprogrammed + * + * This function reconfigures RSS by reprogramming LUTs using 'rss_size' + **/ +static int i40e_vsi_reconfig_rss(struct i40e_vsi *vsi, u16 rss_size) +{ + struct i40e_pf *pf = vsi->back; + u8 seed[I40E_HKEY_ARRAY_SIZE]; + struct i40e_hw *hw = &pf->hw; + int local_rss_size; + u8 *lut; + int ret; + + if (!vsi->rss_size) + return -EINVAL; + + if (rss_size > vsi->rss_size) + return -EINVAL; + + local_rss_size = min_t(int, vsi->rss_size, rss_size); + lut = kzalloc(vsi->rss_table_size, GFP_KERNEL); + if (!lut) + return -ENOMEM; + + /* Ignoring user configured lut if there is one */ + i40e_fill_rss_lut(pf, lut, vsi->rss_table_size, local_rss_size); + + /* Use user configured hash key if there is one, otherwise + * use default. + */ + if (vsi->rss_hkey_user) + memcpy(seed, vsi->rss_hkey_user, I40E_HKEY_ARRAY_SIZE); + else + netdev_rss_key_fill((void *)seed, I40E_HKEY_ARRAY_SIZE); + + ret = i40e_config_rss(vsi, seed, lut, vsi->rss_table_size); + if (ret) { + dev_info(&pf->pdev->dev, + "Cannot set RSS lut, err %s aq_err %s\n", + i40e_stat_str(hw, ret), + i40e_aq_str(hw, hw->aq.asq_last_status)); + kfree(lut); + return ret; + } + kfree(lut); + + /* Do the update w.r.t. storing rss_size */ + if (!vsi->orig_rss_size) + vsi->orig_rss_size = vsi->rss_size; + vsi->current_rss_size = local_rss_size; + + return ret; +} + +/** + * i40e_channel_setup_queue_map - Setup a channel queue map + * @pf: ptr to PF device + * @vsi: the VSI being setup + * @ctxt: VSI context structure + * @ch: ptr to channel structure + * + * Setup queue map for a specific channel + **/ +static void i40e_channel_setup_queue_map(struct i40e_pf *pf, + struct i40e_vsi_context *ctxt, + struct i40e_channel *ch) +{ + u16 qcount, qmap, sections = 0; + u8 offset = 0; + int pow; + + sections = I40E_AQ_VSI_PROP_QUEUE_MAP_VALID; + sections |= I40E_AQ_VSI_PROP_SCHED_VALID; + + qcount = min_t(int, ch->num_queue_pairs, pf->num_lan_msix); + ch->num_queue_pairs = qcount; + + /* find the next higher power-of-2 of num queue pairs */ + pow = ilog2(qcount); + if (!is_power_of_2(qcount)) + pow++; + + qmap = (offset << I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT) | + (pow << I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT); + + /* Setup queue TC[0].qmap for given VSI context */ + ctxt->info.tc_mapping[0] = cpu_to_le16(qmap); + + ctxt->info.up_enable_bits = 0x1; /* TC0 enabled */ + ctxt->info.mapping_flags |= cpu_to_le16(I40E_AQ_VSI_QUE_MAP_CONTIG); + ctxt->info.queue_mapping[0] = cpu_to_le16(ch->base_queue); + ctxt->info.valid_sections |= cpu_to_le16(sections); +} + +/** + * i40e_add_channel - add a channel by adding VSI + * @pf: ptr to PF device + * @uplink_seid: underlying HW switching element (VEB) ID + * @ch: ptr to channel structure + * + * Add a channel (VSI) using add_vsi and queue_map + **/ +static int i40e_add_channel(struct i40e_pf *pf, u16 uplink_seid, + struct i40e_channel *ch) +{ + struct i40e_hw *hw = &pf->hw; + struct i40e_vsi_context ctxt; + u8 enabled_tc = 0x1; /* TC0 enabled */ + int ret; + + if (ch->type != I40E_VSI_VMDQ2) { + dev_info(&pf->pdev->dev, + "add new vsi failed, ch->type %d\n", ch->type); + return -EINVAL; + } + + memset(&ctxt, 0, sizeof(ctxt)); + ctxt.pf_num = hw->pf_id; + ctxt.vf_num = 0; + ctxt.uplink_seid = uplink_seid; + ctxt.connection_type = I40E_AQ_VSI_CONN_TYPE_NORMAL; + if (ch->type == I40E_VSI_VMDQ2) + ctxt.flags = I40E_AQ_VSI_TYPE_VMDQ2; + + if (pf->flags & I40E_FLAG_VEB_MODE_ENABLED) { + ctxt.info.valid_sections |= + cpu_to_le16(I40E_AQ_VSI_PROP_SWITCH_VALID); + ctxt.info.switch_id = + cpu_to_le16(I40E_AQ_VSI_SW_ID_FLAG_ALLOW_LB); + } + + /* Set queue map for a given VSI context */ + i40e_channel_setup_queue_map(pf, &ctxt, ch); + + /* Now time to create VSI */ + ret = i40e_aq_add_vsi(hw, &ctxt, NULL); + if (ret) { + dev_info(&pf->pdev->dev, + "add new vsi failed, err %s aq_err %s\n", + i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, + pf->hw.aq.asq_last_status)); + return -ENOENT; + } + + /* Success, update channel */ + ch->enabled_tc = enabled_tc; + ch->seid = ctxt.seid; + ch->vsi_number = ctxt.vsi_number; + ch->stat_counter_idx = cpu_to_le16(ctxt.info.stat_counter_idx); + + /* copy just the sections touched not the entire info + * since not all sections are valid as returned by + * update vsi params + */ + ch->info.mapping_flags = ctxt.info.mapping_flags; + memcpy(&ch->info.queue_mapping, + &ctxt.info.queue_mapping, sizeof(ctxt.info.queue_mapping)); + memcpy(&ch->info.tc_mapping, ctxt.info.tc_mapping, + sizeof(ctxt.info.tc_mapping)); + + return 0; +} + +static int i40e_channel_config_bw(struct i40e_vsi *vsi, struct i40e_channel *ch, + u8 *bw_share) +{ + struct i40e_aqc_configure_vsi_tc_bw_data bw_data; + i40e_status ret; + int i; + + bw_data.tc_valid_bits = ch->enabled_tc; + for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) + bw_data.tc_bw_credits[i] = bw_share[i]; + + ret = i40e_aq_config_vsi_tc_bw(&vsi->back->hw, ch->seid, + &bw_data, NULL); + if (ret) { + dev_info(&vsi->back->pdev->dev, + "Config VSI BW allocation per TC failed, aq_err: %d for new_vsi->seid %u\n", + vsi->back->hw.aq.asq_last_status, ch->seid); + return -EINVAL; + } + + for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) + ch->info.qs_handle[i] = bw_data.qs_handles[i]; + + return 0; +} + +/** + * i40e_channel_config_tx_ring - config TX ring associated with new channel + * @pf: ptr to PF device + * @vsi: the VSI being setup + * @ch: ptr to channel structure + * + * Configure TX rings associated with channel (VSI) since queues are being + * from parent VSI. + **/ +static int i40e_channel_config_tx_ring(struct i40e_pf *pf, + struct i40e_vsi *vsi, + struct i40e_channel *ch) +{ + i40e_status ret; + int i; + u8 bw_share[I40E_MAX_TRAFFIC_CLASS] = {0}; + + /* Enable ETS TCs with equal BW Share for now across all VSIs */ + for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { + if (ch->enabled_tc & BIT(i)) + bw_share[i] = 1; + } + + /* configure BW for new VSI */ + ret = i40e_channel_config_bw(vsi, ch, bw_share); + if (ret) { + dev_info(&vsi->back->pdev->dev, + "Failed configuring TC map %d for channel (seid %u)\n", + ch->enabled_tc, ch->seid); + return ret; + } + + for (i = 0; i < ch->num_queue_pairs; i++) { + struct i40e_ring *tx_ring, *rx_ring; + u16 pf_q; + + pf_q = ch->base_queue + i; + + /* Get to TX ring ptr of main VSI, for re-setup TX queue + * context + */ + tx_ring = vsi->tx_rings[pf_q]; + tx_ring->ch = ch; + + /* Get the RX ring ptr */ + rx_ring = vsi->rx_rings[pf_q]; + rx_ring->ch = ch; + } + + return 0; +} + +/** + * i40e_setup_hw_channel - setup new channel + * @pf: ptr to PF device + * @vsi: the VSI being setup + * @ch: ptr to channel structure + * @uplink_seid: underlying HW switching element (VEB) ID + * @type: type of channel to be created (VMDq2/VF) + * + * Setup new channel (VSI) based on specified type (VMDq2/VF) + * and configures TX rings accordingly + **/ +static inline int i40e_setup_hw_channel(struct i40e_pf *pf, + struct i40e_vsi *vsi, + struct i40e_channel *ch, + u16 uplink_seid, u8 type) +{ + int ret; + + ch->initialized = false; + ch->base_queue = vsi->next_base_queue; + ch->type = type; + + /* Proceed with creation of channel (VMDq2) VSI */ + ret = i40e_add_channel(pf, uplink_seid, ch); + if (ret) { + dev_info(&pf->pdev->dev, + "failed to add_channel using uplink_seid %u\n", + uplink_seid); + return ret; + } + + /* Mark the successful creation of channel */ + ch->initialized = true; + + /* Reconfigure TX queues using QTX_CTL register */ + ret = i40e_channel_config_tx_ring(pf, vsi, ch); + if (ret) { + dev_info(&pf->pdev->dev, + "failed to configure TX rings for channel %u\n", + ch->seid); + return ret; + } + + /* update 'next_base_queue' */ + vsi->next_base_queue = vsi->next_base_queue + ch->num_queue_pairs; + dev_dbg(&pf->pdev->dev, + "Added channel: vsi_seid %u, vsi_number %u, stat_counter_idx %u, num_queue_pairs %u, pf->next_base_queue %d\n", + ch->seid, ch->vsi_number, ch->stat_counter_idx, + ch->num_queue_pairs, + vsi->next_base_queue); + return ret; +} + +/** + * i40e_setup_channel - setup new channel using uplink element + * @pf: ptr to PF device + * @type: type of channel to be created (VMDq2/VF) + * @uplink_seid: underlying HW switching element (VEB) ID + * @ch: ptr to channel structure + * + * Setup new channel (VSI) based on specified type (VMDq2/VF) + * and uplink switching element (uplink_seid) + **/ +static bool i40e_setup_channel(struct i40e_pf *pf, struct i40e_vsi *vsi, + struct i40e_channel *ch) +{ + u8 vsi_type; + u16 seid; + int ret; + + if (vsi->type == I40E_VSI_MAIN) { + vsi_type = I40E_VSI_VMDQ2; + } else { + dev_err(&pf->pdev->dev, "unsupported parent vsi type(%d)\n", + vsi->type); + return false; + } + + /* underlying switching element */ + seid = pf->vsi[pf->lan_vsi]->uplink_seid; + + /* create channel (VSI), configure TX rings */ + ret = i40e_setup_hw_channel(pf, vsi, ch, seid, vsi_type); + if (ret) { + dev_err(&pf->pdev->dev, "failed to setup hw_channel\n"); + return false; + } + + return ch->initialized ? true : false; +} + +/** + * i40e_create_queue_channel - function to create channel + * @vsi: VSI to be configured + * @ch: ptr to channel (it contains channel specific params) + * + * This function creates channel (VSI) using num_queues specified by user, + * reconfigs RSS if needed. + **/ +int i40e_create_queue_channel(struct i40e_vsi *vsi, + struct i40e_channel *ch) +{ + struct i40e_pf *pf = vsi->back; + bool reconfig_rss; + int err; + + if (!ch) + return -EINVAL; + + if (!ch->num_queue_pairs) { + dev_err(&pf->pdev->dev, "Invalid num_queues requested: %d\n", + ch->num_queue_pairs); + return -EINVAL; + } + + /* validate user requested num_queues for channel */ + err = i40e_validate_num_queues(pf, ch->num_queue_pairs, vsi, + &reconfig_rss); + if (err) { + dev_info(&pf->pdev->dev, "Failed to validate num_queues (%d)\n", + ch->num_queue_pairs); + return -EINVAL; + } + + /* By default we are in VEPA mode, if this is the first VF/VMDq + * VSI to be added switch to VEB mode. + */ + if ((!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) || + (!i40e_is_any_channel(vsi))) { + if (!is_power_of_2(vsi->tc_config.tc_info[0].qcount)) { + dev_dbg(&pf->pdev->dev, + "Failed to create channel. Override queues (%u) not power of 2\n", + vsi->tc_config.tc_info[0].qcount); + return -EINVAL; + } + + if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) { + pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; + + if (vsi->type == I40E_VSI_MAIN) { + if (pf->flags & I40E_FLAG_TC_MQPRIO) + i40e_do_reset(pf, I40E_PF_RESET_FLAG, + true); + else + i40e_do_reset_safe(pf, + I40E_PF_RESET_FLAG); + } + } + /* now onwards for main VSI, number of queues will be value + * of TC0's queue count + */ + } + + /* By this time, vsi->cnt_q_avail shall be set to non-zero and + * it should be more than num_queues + */ + if (!vsi->cnt_q_avail || vsi->cnt_q_avail < ch->num_queue_pairs) { + dev_dbg(&pf->pdev->dev, + "Error: cnt_q_avail (%u) less than num_queues %d\n", + vsi->cnt_q_avail, ch->num_queue_pairs); + return -EINVAL; + } + + /* reconfig_rss only if vsi type is MAIN_VSI */ + if (reconfig_rss && (vsi->type == I40E_VSI_MAIN)) { + err = i40e_vsi_reconfig_rss(vsi, ch->num_queue_pairs); + if (err) { + dev_info(&pf->pdev->dev, + "Error: unable to reconfig rss for num_queues (%u)\n", + ch->num_queue_pairs); + return -EINVAL; + } + } + + if (!i40e_setup_channel(pf, vsi, ch)) { + dev_info(&pf->pdev->dev, "Failed to setup channel\n"); + return -EINVAL; + } + + dev_info(&pf->pdev->dev, + "Setup channel (id:%u) utilizing num_queues %d\n", + ch->seid, ch->num_queue_pairs); + + /* configure VSI for BW limit */ + if (ch->max_tx_rate) { + u64 credits = ch->max_tx_rate; + + if (i40e_set_bw_limit(vsi, ch->seid, ch->max_tx_rate)) + return -EINVAL; + + do_div(credits, I40E_BW_CREDIT_DIVISOR); + dev_dbg(&pf->pdev->dev, + "Set tx rate of %llu Mbps (count of 50Mbps %llu) for vsi->seid %u\n", + ch->max_tx_rate, + credits, + ch->seid); + } + + /* in case of VF, this will be main SRIOV VSI */ + ch->parent_vsi = vsi; + + /* and update main_vsi's count for queue_available to use */ + vsi->cnt_q_avail -= ch->num_queue_pairs; + + return 0; +} + +/** + * i40e_configure_queue_channels - Add queue channel for the given TCs + * @vsi: VSI to be configured + * + * Configures queue channel mapping to the given TCs + **/ +static int i40e_configure_queue_channels(struct i40e_vsi *vsi) +{ + struct i40e_channel *ch; + u64 max_rate = 0; + int ret = 0, i; + + /* Create app vsi with the TCs. Main VSI with TC0 is already set up */ + for (i = 1; i < I40E_MAX_TRAFFIC_CLASS; i++) { + if (vsi->tc_config.enabled_tc & BIT(i)) { + ch = kzalloc(sizeof(*ch), GFP_KERNEL); + if (!ch) { + ret = -ENOMEM; + goto err_free; + } + + INIT_LIST_HEAD(&ch->list); + ch->num_queue_pairs = + vsi->tc_config.tc_info[i].qcount; + ch->base_queue = + vsi->tc_config.tc_info[i].qoffset; + + /* Bandwidth limit through tc interface is in bytes/s, + * change to Mbit/s + */ + max_rate = vsi->mqprio_qopt.max_rate[i]; + do_div(max_rate, I40E_BW_MBPS_DIVISOR); + ch->max_tx_rate = max_rate; + + list_add_tail(&ch->list, &vsi->ch_list); + + ret = i40e_create_queue_channel(vsi, ch); + if (ret) { + dev_err(&vsi->back->pdev->dev, + "Failed creating queue channel with TC%d: queues %d\n", + i, ch->num_queue_pairs); + goto err_free; + } + } + } + return ret; + +err_free: + i40e_remove_queue_channels(vsi); + return ret; +} + +/** * i40e_veb_config_tc - Configure TCs for given VEB * @veb: given VEB * @enabled_tc: TC bitmap @@ -5567,74 +6540,221 @@ void i40e_down(struct i40e_vsi *vsi) } /** + * i40e_validate_mqprio_qopt- validate queue mapping info + * @vsi: the VSI being configured + * @mqprio_qopt: queue parametrs + **/ +static int i40e_validate_mqprio_qopt(struct i40e_vsi *vsi, + struct tc_mqprio_qopt_offload *mqprio_qopt) +{ + u64 sum_max_rate = 0; + u64 max_rate = 0; + int i; + + if (mqprio_qopt->qopt.offset[0] != 0 || + mqprio_qopt->qopt.num_tc < 1 || + mqprio_qopt->qopt.num_tc > I40E_MAX_TRAFFIC_CLASS) + return -EINVAL; + for (i = 0; ; i++) { + if (!mqprio_qopt->qopt.count[i]) + return -EINVAL; + if (mqprio_qopt->min_rate[i]) { + dev_err(&vsi->back->pdev->dev, + "Invalid min tx rate (greater than 0) specified\n"); + return -EINVAL; + } + max_rate = mqprio_qopt->max_rate[i]; + do_div(max_rate, I40E_BW_MBPS_DIVISOR); + sum_max_rate += max_rate; + + if (i >= mqprio_qopt->qopt.num_tc - 1) + break; + if (mqprio_qopt->qopt.offset[i + 1] != + (mqprio_qopt->qopt.offset[i] + mqprio_qopt->qopt.count[i])) + return -EINVAL; + } + if (vsi->num_queue_pairs < + (mqprio_qopt->qopt.offset[i] + mqprio_qopt->qopt.count[i])) { + return -EINVAL; + } + if (sum_max_rate > i40e_get_link_speed(vsi)) { + dev_err(&vsi->back->pdev->dev, + "Invalid max tx rate specified\n"); + return -EINVAL; + } + return 0; +} + +/** + * i40e_vsi_set_default_tc_config - set default values for tc configuration + * @vsi: the VSI being configured + **/ +static void i40e_vsi_set_default_tc_config(struct i40e_vsi *vsi) +{ + u16 qcount; + int i; + + /* Only TC0 is enabled */ + vsi->tc_config.numtc = 1; + vsi->tc_config.enabled_tc = 1; + qcount = min_t(int, vsi->alloc_queue_pairs, + i40e_pf_get_max_q_per_tc(vsi->back)); + for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { + /* For the TC that is not enabled set the offset to to default + * queue and allocate one queue for the given TC. + */ + vsi->tc_config.tc_info[i].qoffset = 0; + if (i == 0) + vsi->tc_config.tc_info[i].qcount = qcount; + else + vsi->tc_config.tc_info[i].qcount = 1; + vsi->tc_config.tc_info[i].netdev_tc = 0; + } +} + +/** * i40e_setup_tc - configure multiple traffic classes * @netdev: net device to configure - * @tc: number of traffic classes to enable + * @type_data: tc offload data **/ -static int i40e_setup_tc(struct net_device *netdev, u8 tc) +static int i40e_setup_tc(struct net_device *netdev, void *type_data) { + struct tc_mqprio_qopt_offload *mqprio_qopt = type_data; struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; - u8 enabled_tc = 0; + u8 enabled_tc = 0, num_tc, hw; + bool need_reset = false; int ret = -EINVAL; + u16 mode; int i; - /* Check if DCB enabled to continue */ - if (!(pf->flags & I40E_FLAG_DCB_ENABLED)) { - netdev_info(netdev, "DCB is not enabled for adapter\n"); - goto exit; + num_tc = mqprio_qopt->qopt.num_tc; + hw = mqprio_qopt->qopt.hw; + mode = mqprio_qopt->mode; + if (!hw) { + pf->flags &= ~I40E_FLAG_TC_MQPRIO; + memcpy(&vsi->mqprio_qopt, mqprio_qopt, sizeof(*mqprio_qopt)); + goto config_tc; } /* Check if MFP enabled */ if (pf->flags & I40E_FLAG_MFP_ENABLED) { - netdev_info(netdev, "Configuring TC not supported in MFP mode\n"); - goto exit; + netdev_info(netdev, + "Configuring TC not supported in MFP mode\n"); + return ret; } + switch (mode) { + case TC_MQPRIO_MODE_DCB: + pf->flags &= ~I40E_FLAG_TC_MQPRIO; - /* Check whether tc count is within enabled limit */ - if (tc > i40e_pf_get_num_tc(pf)) { - netdev_info(netdev, "TC count greater than enabled on link for adapter\n"); - goto exit; + /* Check if DCB enabled to continue */ + if (!(pf->flags & I40E_FLAG_DCB_ENABLED)) { + netdev_info(netdev, + "DCB is not enabled for adapter\n"); + return ret; + } + + /* Check whether tc count is within enabled limit */ + if (num_tc > i40e_pf_get_num_tc(pf)) { + netdev_info(netdev, + "TC count greater than enabled on link for adapter\n"); + return ret; + } + break; + case TC_MQPRIO_MODE_CHANNEL: + if (pf->flags & I40E_FLAG_DCB_ENABLED) { + netdev_info(netdev, + "Full offload of TC Mqprio options is not supported when DCB is enabled\n"); + return ret; + } + if (!(pf->flags & I40E_FLAG_MSIX_ENABLED)) + return ret; + ret = i40e_validate_mqprio_qopt(vsi, mqprio_qopt); + if (ret) + return ret; + memcpy(&vsi->mqprio_qopt, mqprio_qopt, + sizeof(*mqprio_qopt)); + pf->flags |= I40E_FLAG_TC_MQPRIO; + pf->flags &= ~I40E_FLAG_DCB_ENABLED; + break; + default: + return -EINVAL; } +config_tc: /* Generate TC map for number of tc requested */ - for (i = 0; i < tc; i++) + for (i = 0; i < num_tc; i++) enabled_tc |= BIT(i); /* Requesting same TC configuration as already enabled */ - if (enabled_tc == vsi->tc_config.enabled_tc) + if (enabled_tc == vsi->tc_config.enabled_tc && + mode != TC_MQPRIO_MODE_CHANNEL) return 0; /* Quiesce VSI queues */ i40e_quiesce_vsi(vsi); + if (!hw && !(pf->flags & I40E_FLAG_TC_MQPRIO)) + i40e_remove_queue_channels(vsi); + /* Configure VSI for enabled TCs */ ret = i40e_vsi_config_tc(vsi, enabled_tc); if (ret) { netdev_info(netdev, "Failed configuring TC for VSI seid=%d\n", vsi->seid); + need_reset = true; goto exit; } - /* Unquiesce VSI */ - i40e_unquiesce_vsi(vsi); + if (pf->flags & I40E_FLAG_TC_MQPRIO) { + if (vsi->mqprio_qopt.max_rate[0]) { + u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0]; + + do_div(max_tx_rate, I40E_BW_MBPS_DIVISOR); + ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate); + if (!ret) { + u64 credits = max_tx_rate; + + do_div(credits, I40E_BW_CREDIT_DIVISOR); + dev_dbg(&vsi->back->pdev->dev, + "Set tx rate of %llu Mbps (count of 50Mbps %llu) for vsi->seid %u\n", + max_tx_rate, + credits, + vsi->seid); + } else { + need_reset = true; + goto exit; + } + } + ret = i40e_configure_queue_channels(vsi); + if (ret) { + netdev_info(netdev, + "Failed configuring queue channels\n"); + need_reset = true; + goto exit; + } + } exit: + /* Reset the configuration data to defaults, only TC0 is enabled */ + if (need_reset) { + i40e_vsi_set_default_tc_config(vsi); + need_reset = false; + } + + /* Unquiesce VSI */ + i40e_unquiesce_vsi(vsi); return ret; } static int __i40e_setup_tc(struct net_device *netdev, enum tc_setup_type type, void *type_data) { - struct tc_mqprio_qopt *mqprio = type_data; - if (type != TC_SETUP_MQPRIO) return -EOPNOTSUPP; - mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; - - return i40e_setup_tc(netdev, mqprio->num_tc); + return i40e_setup_tc(netdev, type_data); } /** @@ -5752,7 +6872,7 @@ err_setup_rx: err_setup_tx: i40e_vsi_free_tx_resources(vsi); if (vsi == pf->vsi[pf->lan_vsi]) - i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED), true); + i40e_do_reset(pf, I40E_PF_RESET_FLAG, true); return err; } @@ -5880,7 +7000,7 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired) wr32(&pf->hw, I40E_GLGEN_RTRIG, val); i40e_flush(&pf->hw); - } else if (reset_flags & BIT_ULL(__I40E_PF_RESET_REQUESTED)) { + } else if (reset_flags & I40E_PF_RESET_FLAG) { /* Request a PF Reset * @@ -6231,6 +7351,7 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf) hlist_del(&filter->fdir_node); kfree(filter); pf->fdir_pf_active_filters--; + pf->fd_inv = 0; } } } @@ -6557,12 +7678,26 @@ static void i40e_handle_link_event(struct i40e_pf *pf, */ i40e_link_event(pf); - /* check for unqualified module, if link is down */ - if ((status->link_info & I40E_AQ_MEDIA_AVAILABLE) && - (!(status->an_info & I40E_AQ_QUALIFIED_MODULE)) && - (!(status->link_info & I40E_AQ_LINK_UP))) + /* Check if module meets thermal requirements */ + if (status->phy_type == I40E_PHY_TYPE_NOT_SUPPORTED_HIGH_TEMP) { dev_err(&pf->pdev->dev, - "The driver failed to link because an unqualified module was detected.\n"); + "Rx/Tx is disabled on this device because the module does not meet thermal requirements.\n"); + dev_err(&pf->pdev->dev, + "Refer to the Intel(R) Ethernet Adapters and Devices User Guide for a list of supported modules.\n"); + } else { + /* check for unqualified module, if link is down, suppress + * the message if link was forced to be down. + */ + if ((status->link_info & I40E_AQ_MEDIA_AVAILABLE) && + (!(status->an_info & I40E_AQ_QUALIFIED_MODULE)) && + (!(status->link_info & I40E_AQ_LINK_UP)) && + (!(pf->flags & I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED))) { + dev_err(&pf->pdev->dev, + "Rx/Tx is disabled on this device because an unsupported SFP module type was detected.\n"); + dev_err(&pf->pdev->dev, + "Refer to the Intel(R) Ethernet Adapters and Devices User Guide for a list of supported modules.\n"); + } + } } /** @@ -7021,6 +8156,49 @@ static void i40e_fdir_teardown(struct i40e_pf *pf) } /** + * i40e_rebuild_channels - Rebuilds channel VSIs if they existed before reset + * @vsi: PF main vsi + * + * Rebuilds channel VSIs if they existed before reset + **/ +static int i40e_rebuild_channels(struct i40e_vsi *vsi) +{ + struct i40e_channel *ch, *ch_tmp; + i40e_status ret; + + if (list_empty(&vsi->ch_list)) + return 0; + + list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) { + if (!ch->initialized) + break; + /* Proceed with creation of channel (VMDq2) VSI */ + ret = i40e_add_channel(vsi->back, vsi->uplink_seid, ch); + if (ret) { + dev_info(&vsi->back->pdev->dev, + "failed to rebuild channels using uplink_seid %u\n", + vsi->uplink_seid); + return ret; + } + if (ch->max_tx_rate) { + u64 credits = ch->max_tx_rate; + + if (i40e_set_bw_limit(vsi, ch->seid, + ch->max_tx_rate)) + return -EINVAL; + + do_div(credits, I40E_BW_CREDIT_DIVISOR); + dev_dbg(&vsi->back->pdev->dev, + "Set tx rate of %llu Mbps (count of 50Mbps %llu) for vsi->seid %u\n", + ch->max_tx_rate, + credits, + ch->seid); + } + } + return 0; +} + +/** * i40e_prep_for_reset - prep for the core to reset * @pf: board private structure * @lock_acquired: indicates whether or not the lock has been acquired @@ -7156,6 +8334,7 @@ static int i40e_reset(struct i40e_pf *pf) **/ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) { + struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; struct i40e_hw *hw = &pf->hw; u8 set_fc_aq_fail = 0; i40e_status ret; @@ -7238,7 +8417,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) * If there were VEBs but the reconstitution failed, we'll try * try to recover minimal use by getting the basic PF VSI working. */ - if (pf->vsi[pf->lan_vsi]->uplink_seid != pf->mac_seid) { + if (vsi->uplink_seid != pf->mac_seid) { dev_dbg(&pf->pdev->dev, "attempting to rebuild switch\n"); /* find the one VEB connected to the MAC, and find orphans */ for (v = 0; v < I40E_MAX_VEB; v++) { @@ -7262,8 +8441,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) dev_info(&pf->pdev->dev, "rebuild of switch failed: %d, will try to set up simple PF connection\n", ret); - pf->vsi[pf->lan_vsi]->uplink_seid - = pf->mac_seid; + vsi->uplink_seid = pf->mac_seid; break; } else if (pf->veb[v]->uplink_seid == 0) { dev_info(&pf->pdev->dev, @@ -7274,10 +8452,10 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) } } - if (pf->vsi[pf->lan_vsi]->uplink_seid == pf->mac_seid) { + if (vsi->uplink_seid == pf->mac_seid) { dev_dbg(&pf->pdev->dev, "attempting to rebuild PF VSI\n"); /* no VEB, so rebuild only the Main VSI */ - ret = i40e_add_vsi(pf->vsi[pf->lan_vsi]); + ret = i40e_add_vsi(vsi); if (ret) { dev_info(&pf->pdev->dev, "rebuild of Main VSI failed: %d\n", ret); @@ -7285,6 +8463,31 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) } } + if (vsi->mqprio_qopt.max_rate[0]) { + u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0]; + u64 credits = 0; + + do_div(max_tx_rate, I40E_BW_MBPS_DIVISOR); + ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate); + if (ret) + goto end_unlock; + + credits = max_tx_rate; + do_div(credits, I40E_BW_CREDIT_DIVISOR); + dev_dbg(&vsi->back->pdev->dev, + "Set tx rate of %llu Mbps (count of 50Mbps %llu) for vsi->seid %u\n", + max_tx_rate, + credits, + vsi->seid); + } + + /* PF Main VSI is rebuild by now, go ahead and rebuild channel VSIs + * for this main VSI if they exist + */ + ret = i40e_rebuild_channels(vsi); + if (ret) + goto end_unlock; + /* Reconfigure hardware for allowing smaller MSS in the case * of TSO, so that we avoid the MDD being fired and causing * a reset in the case of small MSS+TSO. @@ -7619,9 +8822,9 @@ static void i40e_service_task(struct work_struct *work) * i40e_service_timer - timer callback * @data: pointer to PF struct **/ -static void i40e_service_timer(unsigned long data) +static void i40e_service_timer(struct timer_list *t) { - struct i40e_pf *pf = (struct i40e_pf *)data; + struct i40e_pf *pf = from_timer(pf, t, service_timer); mod_timer(&pf->service_timer, round_jiffies(jiffies + pf->service_timer_period)); @@ -7678,7 +8881,7 @@ static int i40e_set_num_rings_in_vsi(struct i40e_vsi *vsi) /** * i40e_vsi_alloc_arrays - Allocate queue and vector pointer arrays for the vsi - * @type: VSI pointer + * @vsi: VSI pointer * @alloc_qvectors: a bool to specify if q_vectors need to be allocated. * * On error: returns error code (negative) @@ -8439,51 +9642,12 @@ static int i40e_setup_misc_vector(struct i40e_pf *pf) i40e_flush(hw); - i40e_irq_dynamic_enable_icr0(pf, true); + i40e_irq_dynamic_enable_icr0(pf); return err; } /** - * i40e_config_rss_aq - Prepare for RSS using AQ commands - * @vsi: vsi structure - * @seed: RSS hash seed - **/ -static int i40e_config_rss_aq(struct i40e_vsi *vsi, const u8 *seed, - u8 *lut, u16 lut_size) -{ - struct i40e_pf *pf = vsi->back; - struct i40e_hw *hw = &pf->hw; - int ret = 0; - - if (seed) { - struct i40e_aqc_get_set_rss_key_data *seed_dw = - (struct i40e_aqc_get_set_rss_key_data *)seed; - ret = i40e_aq_set_rss_key(hw, vsi->id, seed_dw); - if (ret) { - dev_info(&pf->pdev->dev, - "Cannot set RSS key, err %s aq_err %s\n", - i40e_stat_str(hw, ret), - i40e_aq_str(hw, hw->aq.asq_last_status)); - return ret; - } - } - if (lut) { - bool pf_lut = vsi->type == I40E_VSI_MAIN ? true : false; - - ret = i40e_aq_set_rss_lut(hw, vsi->id, pf_lut, lut, lut_size); - if (ret) { - dev_info(&pf->pdev->dev, - "Cannot set RSS lut, err %s aq_err %s\n", - i40e_stat_str(hw, ret), - i40e_aq_str(hw, hw->aq.asq_last_status)); - return ret; - } - } - return ret; -} - -/** * i40e_get_rss_aq - Get RSS keys and lut by using AQ commands * @vsi: Pointer to vsi structure * @seed: Buffter to store the hash keys @@ -8530,46 +9694,6 @@ static int i40e_get_rss_aq(struct i40e_vsi *vsi, const u8 *seed, } /** - * i40e_vsi_config_rss - Prepare for VSI(VMDq) RSS if used - * @vsi: VSI structure - **/ -static int i40e_vsi_config_rss(struct i40e_vsi *vsi) -{ - u8 seed[I40E_HKEY_ARRAY_SIZE]; - struct i40e_pf *pf = vsi->back; - u8 *lut; - int ret; - - if (!(pf->hw_features & I40E_HW_RSS_AQ_CAPABLE)) - return 0; - - if (!vsi->rss_size) - vsi->rss_size = min_t(int, pf->alloc_rss_size, - vsi->num_queue_pairs); - if (!vsi->rss_size) - return -EINVAL; - - lut = kzalloc(vsi->rss_table_size, GFP_KERNEL); - if (!lut) - return -ENOMEM; - /* Use the user configured hash keys and lookup table if there is one, - * otherwise use default - */ - if (vsi->rss_lut_user) - memcpy(lut, vsi->rss_lut_user, vsi->rss_table_size); - else - i40e_fill_rss_lut(pf, lut, vsi->rss_table_size, vsi->rss_size); - if (vsi->rss_hkey_user) - memcpy(seed, vsi->rss_hkey_user, I40E_HKEY_ARRAY_SIZE); - else - netdev_rss_key_fill((void *)seed, I40E_HKEY_ARRAY_SIZE); - ret = i40e_config_rss_aq(vsi, seed, lut, vsi->rss_table_size); - kfree(lut); - - return ret; -} - -/** * i40e_config_rss_reg - Configure RSS keys and lut by writing registers * @vsi: Pointer to vsi structure * @seed: RSS hash seed @@ -8967,8 +10091,8 @@ static int i40e_sw_init(struct i40e_pf *pf) I40E_FLAG_MSIX_ENABLED; /* Set default ITR */ - pf->rx_itr_default = I40E_ITR_DYNAMIC | I40E_ITR_RX_DEF; - pf->tx_itr_default = I40E_ITR_DYNAMIC | I40E_ITR_TX_DEF; + pf->rx_itr_default = I40E_ITR_RX_DEF; + pf->tx_itr_default = I40E_ITR_TX_DEF; /* Depending on PF configurations, it is possible that the RSS * maximum might end up larger than the available queues @@ -9068,6 +10192,11 @@ static int i40e_sw_init(struct i40e_pf *pf) (pf->hw.aq.fw_maj_ver >= 5))) pf->hw_features |= I40E_HW_USE_SET_LLDP_MIB; + /* Enable PTP L4 if FW > v6.0 */ + if (pf->hw.mac.type == I40E_MAC_XL710 && + pf->hw.aq.fw_maj_ver >= 6) + pf->hw_features |= I40E_HW_PTP_L4_CAPABLE; + if (pf->hw.func_caps.vmdq) { pf->num_vmdq_vsis = I40E_DEFAULT_NUM_VMDQ_VSI; pf->flags |= I40E_FLAG_VMDQ_ENABLED; @@ -9208,7 +10337,7 @@ static int i40e_set_features(struct net_device *netdev, need_reset = i40e_set_ntuple(pf, features); if (need_reset) - i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED), true); + i40e_do_reset(pf, I40E_PF_RESET_FLAG, true); return 0; } @@ -9460,8 +10589,7 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev, pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; else pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED; - i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED), - true); + i40e_do_reset(pf, I40E_PF_RESET_FLAG, true); break; } } @@ -9903,6 +11031,31 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) enabled_tc = i40e_pf_get_tc_map(pf); + /* Source pruning is enabled by default, so the flag is + * negative logic - if it's set, we need to fiddle with + * the VSI to disable source pruning. + */ + if (pf->flags & I40E_FLAG_SOURCE_PRUNING_DISABLED) { + memset(&ctxt, 0, sizeof(ctxt)); + ctxt.seid = pf->main_vsi_seid; + ctxt.pf_num = pf->hw.pf_id; + ctxt.vf_num = 0; + ctxt.info.valid_sections |= + cpu_to_le16(I40E_AQ_VSI_PROP_SWITCH_VALID); + ctxt.info.switch_id = + cpu_to_le16(I40E_AQ_VSI_SW_ID_FLAG_LOCAL_LB); + ret = i40e_aq_update_vsi_params(hw, &ctxt, NULL); + if (ret) { + dev_info(&pf->pdev->dev, + "update vsi failed, err %s aq_err %s\n", + i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, + pf->hw.aq.asq_last_status)); + ret = -ENOENT; + goto err; + } + } + /* MFP mode setup queue map and update VSI */ if ((pf->flags & I40E_FLAG_MFP_ENABLED) && !(pf->hw.func_caps.iscsi)) { /* NIC type PF */ @@ -11517,7 +12670,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) #endif /* CONFIG_I40E_DCB */ /* set up periodic task facility */ - setup_timer(&pf->service_timer, i40e_service_timer, (unsigned long)pf); + timer_setup(&pf->service_timer, i40e_service_timer, 0); pf->service_timer_period = HZ; INIT_WORK(&pf->service_task, i40e_service_task); @@ -11569,6 +12722,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_info(&pdev->dev, "setup_pf_switch failed: %d\n", err); goto err_vsis; } + INIT_LIST_HEAD(&pf->vsi[pf->lan_vsi]->ch_list); /* Make sure flow control is set according to current settings */ err = i40e_set_fc(hw, &set_fc_aq_fail, true); @@ -11840,7 +12994,7 @@ static void i40e_remove(struct pci_dev *pdev) /* no more scheduling of any task */ set_bit(__I40E_SUSPENDED, pf->state); set_bit(__I40E_DOWN, pf->state); - if (pf->service_timer.data) + if (pf->service_timer.function) del_timer_sync(&pf->service_timer); if (pf->service_task.func) cancel_work_sync(&pf->service_task); @@ -12000,6 +13154,28 @@ static pci_ers_result_t i40e_pci_error_slot_reset(struct pci_dev *pdev) } /** + * i40e_pci_error_reset_prepare - prepare device driver for pci reset + * @pdev: PCI device information struct + */ +static void i40e_pci_error_reset_prepare(struct pci_dev *pdev) +{ + struct i40e_pf *pf = pci_get_drvdata(pdev); + + i40e_prep_for_reset(pf, false); +} + +/** + * i40e_pci_error_reset_done - pci reset done, device driver reset can begin + * @pdev: PCI device information struct + */ +static void i40e_pci_error_reset_done(struct pci_dev *pdev) +{ + struct i40e_pf *pf = pci_get_drvdata(pdev); + + i40e_reset_and_rebuild(pf, false, false); +} + +/** * i40e_pci_error_resume - restart operations after PCI error recovery * @pdev: PCI device information struct * @@ -12189,6 +13365,8 @@ static int i40e_resume(struct device *dev) static const struct pci_error_handlers i40e_err_handler = { .error_detected = i40e_pci_error_detected, .slot_reset = i40e_pci_error_slot_reset, + .reset_prepare = i40e_pci_error_reset_prepare, + .reset_done = i40e_pci_error_reset_done, .resume = i40e_pci_error_resume, }; diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c index 57505b1df98d..151d9cfb6ea4 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c +++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c @@ -311,13 +311,10 @@ static i40e_status i40e_read_nvm_word_aq(struct i40e_hw *hw, u16 offset, static i40e_status __i40e_read_nvm_word(struct i40e_hw *hw, u16 offset, u16 *data) { - i40e_status ret_code = 0; - if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) - ret_code = i40e_read_nvm_word_aq(hw, offset, data); - else - ret_code = i40e_read_nvm_word_srctl(hw, offset, data); - return ret_code; + return i40e_read_nvm_word_aq(hw, offset, data); + + return i40e_read_nvm_word_srctl(hw, offset, data); } /** @@ -331,7 +328,7 @@ static i40e_status __i40e_read_nvm_word(struct i40e_hw *hw, i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset, u16 *data) { - i40e_status ret_code = 0; + i40e_status ret_code; ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); if (ret_code) @@ -446,13 +443,10 @@ static i40e_status __i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset, u16 *words, u16 *data) { - i40e_status ret_code = 0; - if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) - ret_code = i40e_read_nvm_buffer_aq(hw, offset, words, data); - else - ret_code = i40e_read_nvm_buffer_srctl(hw, offset, words, data); - return ret_code; + return i40e_read_nvm_buffer_aq(hw, offset, words, data); + + return i40e_read_nvm_buffer_srctl(hw, offset, words, data); } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h index 86ca27f72f02..c234758dad15 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_register.h +++ b/drivers/net/ethernet/intel/i40e/i40e_register.h @@ -2794,7 +2794,7 @@ #define I40E_GLV_RUPP_MAX_INDEX 383 #define I40E_GLV_RUPP_RUPP_SHIFT 0 #define I40E_GLV_RUPP_RUPP_MASK I40E_MASK(0xFFFFFFFF, I40E_GLV_RUPP_RUPP_SHIFT) -#define I40E_GLV_TEPC(_VSI) (0x00344000 + ((_VSI) * 4)) /* _i=0...383 */ /* Reset: CORER */ +#define I40E_GLV_TEPC(_i) (0x00344000 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */ #define I40E_GLV_TEPC_MAX_INDEX 383 #define I40E_GLV_TEPC_TEPC_SHIFT 0 #define I40E_GLV_TEPC_TEPC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLV_TEPC_TEPC_SHIFT) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index d9fdf69bbc6e..a23306f04e00 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1372,6 +1372,15 @@ bool i40e_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) union i40e_rx_desc *rx_desc; struct i40e_rx_buffer *bi; + /* Hardware only fetches new descriptors in cache lines of 8, + * essentially ignoring the lower 3 bits of the tail register. We want + * to ensure our tail writes are aligned to avoid unnecessary work. We + * can't simply round down the cleaned count, since we might fail to + * allocate some buffers. What we really want is to ensure that + * next_to_used + cleaned_count produces an aligned value. + */ + cleaned_count -= (ntu + cleaned_count) & 0x7; + /* do nothing if no valid netdev defined */ if (!rx_ring->netdev || !cleaned_count) return false; @@ -2202,9 +2211,7 @@ static u32 i40e_buildreg_itr(const int type, const u16 itr) u32 val; val = I40E_PFINT_DYN_CTLN_INTENA_MASK | - /* Don't clear PBA because that can cause lost interrupts that - * came in while we were cleaning/polling - */ + I40E_PFINT_DYN_CTLN_CLEARPBA_MASK | (type << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) | (itr << I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT); @@ -2241,7 +2248,7 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, /* If we don't have MSIX, then we only need to re-enable icr0 */ if (!(vsi->back->flags & I40E_FLAG_MSIX_ENABLED)) { - i40e_irq_dynamic_enable_icr0(vsi->back, false); + i40e_irq_dynamic_enable_icr0(vsi->back); return; } @@ -3167,38 +3174,12 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, /* write last descriptor with EOP bit */ td_cmd |= I40E_TX_DESC_CMD_EOP; - /* We can OR these values together as they both are checked against - * 4 below and at this point desc_count will be used as a boolean value - * after this if/else block. + /* We OR these values together to check both against 4 (WB_STRIDE) + * below. This is safe since we don't re-use desc_count afterwards. */ desc_count |= ++tx_ring->packet_stride; - /* Algorithm to optimize tail and RS bit setting: - * if queue is stopped - * mark RS bit - * reset packet counter - * else if xmit_more is supported and is true - * advance packet counter to 4 - * reset desc_count to 0 - * - * if desc_count >= 4 - * mark RS bit - * reset packet counter - * if desc_count > 0 - * update tail - * - * Note: If there are less than 4 descriptors - * pending and interrupts were disabled the service task will - * trigger a force WB. - */ - if (netif_xmit_stopped(txring_txq(tx_ring))) { - goto do_rs; - } else if (skb->xmit_more) { - /* set stride to arm on next packet and reset desc_count */ - tx_ring->packet_stride = WB_STRIDE; - desc_count = 0; - } else if (desc_count >= WB_STRIDE) { -do_rs: + if (desc_count >= WB_STRIDE) { /* write last descriptor with RS bit set */ td_cmd |= I40E_TX_DESC_CMD_RS; tx_ring->packet_stride = 0; @@ -3219,7 +3200,7 @@ do_rs: first->next_to_watch = tx_desc; /* notify HW of packet */ - if (desc_count) { + if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { writel(i, tx_ring->tail); /* we need this if more than one processor can write to our tail diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 2f848bc5e391..fbae1182e2ea 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -38,8 +38,10 @@ #define I40E_ITR_8K 0x003E #define I40E_ITR_4K 0x007A #define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ -#define I40E_ITR_RX_DEF I40E_ITR_20K -#define I40E_ITR_TX_DEF I40E_ITR_20K +#define I40E_ITR_RX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ + I40E_ITR_DYNAMIC) +#define I40E_ITR_TX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ + I40E_ITR_DYNAMIC) #define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ #define I40E_MIN_INT_RATE 250 /* ~= 1000000 / (I40E_MAX_ITR * 2) */ #define I40E_MAX_INT_RATE 500000 /* == 1000000 / (I40E_MIN_ITR * 2) */ @@ -206,7 +208,7 @@ static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc, } /* How many Rx Buffers do we bundle into one write to the hardware ? */ -#define I40E_RX_BUFFER_WRITE 16 /* Must be power of 2 */ +#define I40E_RX_BUFFER_WRITE 32 /* Must be power of 2 */ #define I40E_RX_INCREMENT(r, i) \ do { \ (i)++; \ @@ -342,6 +344,7 @@ struct i40e_rx_queue_stats { enum i40e_ring_state_t { __I40E_TX_FDIR_INIT_DONE, __I40E_TX_XPS_INIT_DONE, + __I40E_RING_STATE_NBITS /* must be last */ }; /* some useful defines for virtchannel interface, which @@ -366,7 +369,7 @@ struct i40e_ring { struct i40e_tx_buffer *tx_bi; struct i40e_rx_buffer *rx_bi; }; - unsigned long state; + DECLARE_BITMAP(state, __I40E_RING_STATE_NBITS); u16 queue_index; /* Queue number of ring */ u8 dcb_tc; /* Traffic class of ring */ u8 __iomem *tail; @@ -423,6 +426,8 @@ struct i40e_ring { * i40e_clean_rx_ring_irq() is called * for this ring. */ + + struct i40e_channel *ch; } ____cacheline_internodealigned_in_smp; static inline bool ring_uses_build_skb(struct i40e_ring *ring) diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index 4b32b1d38a66..17a99b53acd9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -46,6 +46,9 @@ /* Max default timeout in ms, */ #define I40E_MAX_NVM_TIMEOUT 18000 +/* Max timeout in ms for the phy to respond */ +#define I40E_MAX_PHY_TIMEOUT 500 + /* Switch from ms to the 1usec global time (this is the GTIME resolution) */ #define I40E_MS_TO_GTIME(time) ((time) * 1000) @@ -268,6 +271,10 @@ struct i40e_phy_info { I40E_PHY_TYPE_OFFSET) #define I40E_CAP_PHY_TYPE_25GBASE_LR BIT_ULL(I40E_PHY_TYPE_25GBASE_LR + \ I40E_PHY_TYPE_OFFSET) +#define I40E_CAP_PHY_TYPE_25GBASE_AOC BIT_ULL(I40E_PHY_TYPE_25GBASE_AOC + \ + I40E_PHY_TYPE_OFFSET) +#define I40E_CAP_PHY_TYPE_25GBASE_ACC BIT_ULL(I40E_PHY_TYPE_25GBASE_ACC + \ + I40E_PHY_TYPE_OFFSET) #define I40E_HW_CAP_MAX_GPIO 30 /* Capabilities of a PF or a VF or the whole device */ struct i40e_hw_capabilities { diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 04568137e029..f8a794b72462 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -273,7 +273,7 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id, struct i40e_hw *hw = &pf->hw; u16 vsi_queue_id, pf_queue_id; enum i40e_queue_type qtype; - u16 next_q, vector_id; + u16 next_q, vector_id, size; u32 reg, reg_idx; u16 itr_idx = 0; @@ -303,9 +303,11 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id, vsi_queue_id + 1)); } - next_q = find_first_bit(&linklistmap, - (I40E_MAX_VSI_QP * - I40E_VIRTCHNL_SUPPORTED_QTYPES)); + size = I40E_MAX_VSI_QP * I40E_VIRTCHNL_SUPPORTED_QTYPES; + next_q = find_first_bit(&linklistmap, size); + if (unlikely(next_q == size)) + goto irq_list_done; + vsi_queue_id = next_q / I40E_VIRTCHNL_SUPPORTED_QTYPES; qtype = next_q % I40E_VIRTCHNL_SUPPORTED_QTYPES; pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, vsi_queue_id); @@ -313,7 +315,7 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id, wr32(hw, reg_idx, reg); - while (next_q < (I40E_MAX_VSI_QP * I40E_VIRTCHNL_SUPPORTED_QTYPES)) { + while (next_q < size) { switch (qtype) { case I40E_QUEUE_TYPE_RX: reg_idx = I40E_QINT_RQCTL(pf_queue_id); @@ -327,12 +329,8 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id, break; } - next_q = find_next_bit(&linklistmap, - (I40E_MAX_VSI_QP * - I40E_VIRTCHNL_SUPPORTED_QTYPES), - next_q + 1); - if (next_q < - (I40E_MAX_VSI_QP * I40E_VIRTCHNL_SUPPORTED_QTYPES)) { + next_q = find_next_bit(&linklistmap, size, next_q + 1); + if (next_q < size) { vsi_queue_id = next_q / I40E_VIRTCHNL_SUPPORTED_QTYPES; qtype = next_q % I40E_VIRTCHNL_SUPPORTED_QTYPES; pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, @@ -639,7 +637,7 @@ static int i40e_config_vsi_rx_queue(struct i40e_vf *vf, u16 vsi_id, rx_ctx.dsize = 1; /* default values */ - rx_ctx.lrxqthresh = 2; + rx_ctx.lrxqthresh = 1; rx_ctx.crcstrip = 1; rx_ctx.prefena = 1; rx_ctx.l2tsel = 1; @@ -1358,7 +1356,7 @@ err_alloc: i40e_free_vfs(pf); err_iov: /* Re-enable interrupt 0. */ - i40e_irq_dynamic_enable_icr0(pf, false); + i40e_irq_dynamic_enable_icr0(pf); return ret; } @@ -1427,8 +1425,7 @@ int i40e_pci_sriov_configure(struct pci_dev *pdev, int num_vfs) if (num_vfs) { if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) { pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; - i40e_do_reset_safe(pf, - BIT_ULL(__I40E_PF_RESET_REQUESTED)); + i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG); } return i40e_pci_sriov_enable(pdev, num_vfs); } @@ -1436,7 +1433,7 @@ int i40e_pci_sriov_configure(struct pci_dev *pdev, int num_vfs) if (!pci_vfs_assigned(pf->pdev)) { i40e_free_vfs(pf); pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED; - i40e_do_reset_safe(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED)); + i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG); } else { dev_warn(&pdev->dev, "Unable to free VFs because some are assigned to VMs.\n"); return -EINVAL; @@ -2048,8 +2045,9 @@ error_param: * @msglen: msg length * * VFs get a default number of queues but can use this message to request a - * different number. Will respond with either the number requested or the - * maximum we can support. + * different number. If the request is successful, PF will reset the VF and + * return 0. If unsuccessful, PF will send message informing VF of number of + * available queues and return result of sending VF a message. **/ static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg, int msglen) { @@ -2080,7 +2078,11 @@ static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg, int msglen) pf->queues_left); vfres->num_queue_pairs = pf->queues_left + cur_pairs; } else { + /* successful request */ vf->num_req_queues = req_pairs; + i40e_vc_notify_vf_reset(vf); + i40e_reset_vf(vf, false); + return 0; } return i40e_vc_send_msg_to_vf(vf, VIRTCHNL_OP_REQUEST_QUEUES, 0, @@ -2883,6 +2885,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) struct i40e_mac_filter *f; struct i40e_vf *vf; int ret = 0; + struct hlist_node *h; int bkt; /* validate the request */ @@ -2921,7 +2924,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) /* Delete all the filters for this VSI - we're going to kill it * anyway. */ - hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) __i40e_del_filter(vsi, f); spin_unlock_bh(&vsi->mac_filter_hash_lock); @@ -3119,8 +3122,6 @@ error_pvid: return ret; } -#define I40E_BW_CREDIT_DIVISOR 50 /* 50Mbps per BW credit */ -#define I40E_MAX_BW_INACTIVE_ACCUM 4 /* device can accumulate 4 credits max */ /** * i40e_ndo_set_vf_bw * @netdev: network interface device structure @@ -3136,7 +3137,6 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, struct i40e_pf *pf = np->vsi->back; struct i40e_vsi *vsi; struct i40e_vf *vf; - int speed = 0; int ret = 0; /* validate the request */ @@ -3161,48 +3161,10 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, goto error; } - switch (pf->hw.phy.link_info.link_speed) { - case I40E_LINK_SPEED_40GB: - speed = 40000; - break; - case I40E_LINK_SPEED_25GB: - speed = 25000; - break; - case I40E_LINK_SPEED_20GB: - speed = 20000; - break; - case I40E_LINK_SPEED_10GB: - speed = 10000; - break; - case I40E_LINK_SPEED_1GB: - speed = 1000; - break; - default: - break; - } - - if (max_tx_rate > speed) { - dev_err(&pf->pdev->dev, "Invalid max tx rate %d specified for VF %d.\n", - max_tx_rate, vf->vf_id); - ret = -EINVAL; + ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate); + if (ret) goto error; - } - - if ((max_tx_rate < 50) && (max_tx_rate > 0)) { - dev_warn(&pf->pdev->dev, "Setting max Tx rate to minimum usable value of 50Mbps.\n"); - max_tx_rate = 50; - } - /* Tx rate credits are in values of 50Mbps, 0 is disabled*/ - ret = i40e_aq_config_vsi_bw_limit(&pf->hw, vsi->seid, - max_tx_rate / I40E_BW_CREDIT_DIVISOR, - I40E_MAX_BW_INACTIVE_ACCUM, NULL); - if (ret) { - dev_err(&pf->pdev->dev, "Unable to set max tx rate, error code %d.\n", - ret); - ret = -EIO; - goto error; - } vf->tx_rate = max_tx_rate; error: return ret; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h index ed5602f4bbcd..463e331a70a9 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h @@ -1767,9 +1767,12 @@ enum i40e_aq_phy_type { I40E_PHY_TYPE_25GBASE_CR = 0x20, I40E_PHY_TYPE_25GBASE_SR = 0x21, I40E_PHY_TYPE_25GBASE_LR = 0x22, + I40E_PHY_TYPE_25GBASE_AOC = 0x23, + I40E_PHY_TYPE_25GBASE_ACC = 0x24, + I40E_PHY_TYPE_MAX, + I40E_PHY_TYPE_NOT_SUPPORTED_HIGH_TEMP = 0xFD, I40E_PHY_TYPE_EMPTY = 0xFE, I40E_PHY_TYPE_DEFAULT = 0xFF, - I40E_PHY_TYPE_MAX }; #define I40E_LINK_SPEED_100MB_SHIFT 0x1 @@ -1826,6 +1829,8 @@ struct i40e_aq_get_phy_abilities_resp { #define I40E_AQ_PHY_TYPE_EXT_25G_CR 0X02 #define I40E_AQ_PHY_TYPE_EXT_25G_SR 0x04 #define I40E_AQ_PHY_TYPE_EXT_25G_LR 0x08 +#define I40E_AQ_PHY_TYPE_EXT_25G_AOC 0x10 +#define I40E_AQ_PHY_TYPE_EXT_25G_ACC 0x20 u8 fec_cfg_curr_mod_ext_info; #define I40E_AQ_ENABLE_FEC_KR 0x01 #define I40E_AQ_ENABLE_FEC_RS 0x02 diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 37e1de886d48..6806ada11490 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -711,6 +711,15 @@ bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) union i40e_rx_desc *rx_desc; struct i40e_rx_buffer *bi; + /* Hardware only fetches new descriptors in cache lines of 8, + * essentially ignoring the lower 3 bits of the tail register. We want + * to ensure our tail writes are aligned to avoid unnecessary work. We + * can't simply round down the cleaned count, since we might fail to + * allocate some buffers. What we really want is to ensure that + * next_to_used + cleaned_count produces an aligned value. + */ + cleaned_count -= (ntu + cleaned_count) & 0x7; + /* do nothing if no valid netdev defined */ if (!rx_ring->netdev || !cleaned_count) return false; @@ -1409,9 +1418,7 @@ static u32 i40e_buildreg_itr(const int type, const u16 itr) u32 val; val = I40E_VFINT_DYN_CTLN1_INTENA_MASK | - /* Don't clear PBA because that can cause lost interrupts that - * came in while we were cleaning/polling - */ + I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK | (type << I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) | (itr << I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT); diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index 0d9f98bc07bd..8d26c85d12e1 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -38,8 +38,10 @@ #define I40E_ITR_8K 0x003E #define I40E_ITR_4K 0x007A #define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ -#define I40E_ITR_RX_DEF I40E_ITR_20K -#define I40E_ITR_TX_DEF I40E_ITR_20K +#define I40E_ITR_RX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ + I40E_ITR_DYNAMIC) +#define I40E_ITR_TX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ + I40E_ITR_DYNAMIC) #define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ #define I40E_MIN_INT_RATE 250 /* ~= 1000000 / (I40E_MAX_ITR * 2) */ #define I40E_MAX_INT_RATE 500000 /* == 1000000 / (I40E_MIN_ITR * 2) */ @@ -189,7 +191,7 @@ static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc, } /* How many Rx Buffers do we bundle into one write to the hardware ? */ -#define I40E_RX_BUFFER_WRITE 16 /* Must be power of 2 */ +#define I40E_RX_BUFFER_WRITE 32 /* Must be power of 2 */ #define I40E_RX_INCREMENT(r, i) \ do { \ (i)++; \ @@ -325,6 +327,7 @@ struct i40e_rx_queue_stats { enum i40e_ring_state_t { __I40E_TX_FDIR_INIT_DONE, __I40E_TX_XPS_INIT_DONE, + __I40E_RING_STATE_NBITS /* must be last */ }; /* some useful defines for virtchannel interface, which @@ -348,7 +351,7 @@ struct i40e_ring { struct i40e_tx_buffer *tx_bi; struct i40e_rx_buffer *rx_bi; }; - unsigned long state; + DECLARE_BITMAP(state, __I40E_RING_STATE_NBITS); u16 queue_index; /* Queue number of ring */ u8 dcb_tc; /* Traffic class of ring */ u8 __iomem *tail; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h index 9364b67fff9c..213b773dfad6 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_type.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h @@ -46,6 +46,9 @@ /* Max default timeout in ms, */ #define I40E_MAX_NVM_TIMEOUT 18000 +/* Max timeout in ms for the phy to respond */ +#define I40E_MAX_PHY_TIMEOUT 500 + /* Switch from ms to the 1usec global time (this is the GTIME resolution) */ #define I40E_MS_TO_GTIME(time) ((time) * 1000) diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h index 5982362c5643..de0af521d602 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ b/drivers/net/ethernet/intel/i40evf/i40evf.h @@ -222,22 +222,22 @@ struct i40evf_adapter { u32 flags; #define I40EVF_FLAG_RX_CSUM_ENABLED BIT(0) -#define I40EVF_FLAG_IMIR_ENABLED BIT(5) -#define I40EVF_FLAG_MQ_CAPABLE BIT(6) -#define I40EVF_FLAG_PF_COMMS_FAILED BIT(8) -#define I40EVF_FLAG_RESET_PENDING BIT(9) -#define I40EVF_FLAG_RESET_NEEDED BIT(10) -#define I40EVF_FLAG_WB_ON_ITR_CAPABLE BIT(11) -#define I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE BIT(12) -#define I40EVF_FLAG_ADDR_SET_BY_PF BIT(13) -#define I40EVF_FLAG_SERVICE_CLIENT_REQUESTED BIT(14) -#define I40EVF_FLAG_CLIENT_NEEDS_OPEN BIT(15) -#define I40EVF_FLAG_CLIENT_NEEDS_CLOSE BIT(16) -#define I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS BIT(17) -#define I40EVF_FLAG_PROMISC_ON BIT(18) -#define I40EVF_FLAG_ALLMULTI_ON BIT(19) -#define I40EVF_FLAG_LEGACY_RX BIT(20) -#define I40EVF_FLAG_REINIT_ITR_NEEDED BIT(21) +#define I40EVF_FLAG_IMIR_ENABLED BIT(1) +#define I40EVF_FLAG_MQ_CAPABLE BIT(2) +#define I40EVF_FLAG_PF_COMMS_FAILED BIT(3) +#define I40EVF_FLAG_RESET_PENDING BIT(4) +#define I40EVF_FLAG_RESET_NEEDED BIT(5) +#define I40EVF_FLAG_WB_ON_ITR_CAPABLE BIT(6) +#define I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE BIT(7) +#define I40EVF_FLAG_ADDR_SET_BY_PF BIT(8) +#define I40EVF_FLAG_SERVICE_CLIENT_REQUESTED BIT(9) +#define I40EVF_FLAG_CLIENT_NEEDS_OPEN BIT(10) +#define I40EVF_FLAG_CLIENT_NEEDS_CLOSE BIT(11) +#define I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS BIT(12) +#define I40EVF_FLAG_PROMISC_ON BIT(13) +#define I40EVF_FLAG_ALLMULTI_ON BIT(14) +#define I40EVF_FLAG_LEGACY_RX BIT(15) +#define I40EVF_FLAG_REINIT_ITR_NEEDED BIT(16) /* duplicates for common code */ #define I40E_FLAG_DCB_ENABLED 0 #define I40E_FLAG_RX_CSUM_ENABLED I40EVF_FLAG_RX_CSUM_ENABLED diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index f2f1e754c2ce..ca2ebdbd24d7 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -515,6 +515,7 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename) unsigned int vector, q_vectors; unsigned int rx_int_idx = 0, tx_int_idx = 0; int irq_num, err; + int cpu; i40evf_irq_disable(adapter); /* Decrement for Other and TCP Timer vectors */ @@ -553,10 +554,12 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename) q_vector->affinity_notify.release = i40evf_irq_affinity_release; irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify); - /* get_cpu_mask returns a static constant mask with - * a permanent lifetime so it's ok to use here. + /* Spread the IRQ affinity hints across online CPUs. Note that + * get_cpu_mask returns a mask with a permanent lifetime so + * it's safe to use as a hint for irq_set_affinity_hint. */ - irq_set_affinity_hint(irq_num, get_cpu_mask(q_vector->v_idx)); + cpu = cpumask_local_spread(q_vector->v_idx, -1); + irq_set_affinity_hint(irq_num, get_cpu_mask(cpu)); } return 0; @@ -877,6 +880,8 @@ i40evf_mac_filter *i40evf_add_filter(struct i40evf_adapter *adapter, list_add_tail(&f->list, &adapter->mac_filter_list); f->add = true; adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER; + } else { + f->remove = false; } clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); @@ -1218,7 +1223,7 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) tx_ring->netdev = adapter->netdev; tx_ring->dev = &adapter->pdev->dev; tx_ring->count = adapter->tx_desc_count; - tx_ring->tx_itr_setting = (I40E_ITR_DYNAMIC | I40E_ITR_TX_DEF); + tx_ring->tx_itr_setting = I40E_ITR_TX_DEF; if (adapter->flags & I40EVF_FLAG_WB_ON_ITR_CAPABLE) tx_ring->flags |= I40E_TXR_FLAGS_WB_ON_ITR; @@ -1227,7 +1232,7 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) rx_ring->netdev = adapter->netdev; rx_ring->dev = &adapter->pdev->dev; rx_ring->count = adapter->rx_desc_count; - rx_ring->rx_itr_setting = (I40E_ITR_DYNAMIC | I40E_ITR_RX_DEF); + rx_ring->rx_itr_setting = I40E_ITR_RX_DEF; } adapter->num_active_queues = num_active_queues; @@ -1589,9 +1594,10 @@ err: * i40evf_watchdog_timer - Periodic call-back timer * @data: pointer to adapter disguised as unsigned long **/ -static void i40evf_watchdog_timer(unsigned long data) +static void i40evf_watchdog_timer(struct timer_list *t) { - struct i40evf_adapter *adapter = (struct i40evf_adapter *)data; + struct i40evf_adapter *adapter = from_timer(adapter, t, + watchdog_timer); schedule_work(&adapter->watchdog_task); /* timer will be rescheduled in watchdog task */ @@ -2420,10 +2426,6 @@ out_err: return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } -#define I40EVF_VLAN_FEATURES (NETIF_F_HW_VLAN_CTAG_TX |\ - NETIF_F_HW_VLAN_CTAG_RX |\ - NETIF_F_HW_VLAN_CTAG_FILTER) - /** * i40evf_fix_features - fix up the netdev feature bits * @netdev: our net device @@ -2436,9 +2438,11 @@ static netdev_features_t i40evf_fix_features(struct net_device *netdev, { struct i40evf_adapter *adapter = netdev_priv(netdev); - features &= ~I40EVF_VLAN_FEATURES; - if (adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN) - features |= I40EVF_VLAN_FEATURES; + if (!(adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)) + features &= ~(NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_FILTER); + return features; } @@ -2569,9 +2573,17 @@ int i40evf_process_config(struct i40evf_adapter *adapter) */ hw_features = hw_enc_features; + /* Enable VLAN features if supported */ + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN) + hw_features |= (NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX); + netdev->hw_features |= hw_features; - netdev->features |= hw_features | I40EVF_VLAN_FEATURES; + netdev->features |= hw_features; + + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN) + netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; adapter->vsi.id = adapter->vsi_res->vsi_id; @@ -2737,8 +2749,7 @@ static void i40evf_init_task(struct work_struct *work) ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); } - setup_timer(&adapter->watchdog_timer, &i40evf_watchdog_timer, - (unsigned long)adapter); + timer_setup(&adapter->watchdog_timer, i40evf_watchdog_timer, 0); mod_timer(&adapter->watchdog_timer, jiffies + 1); adapter->tx_desc_count = I40EVF_DEFAULT_TXD; diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c index 2bb81c39d85f..46c8b8a3907c 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c @@ -407,6 +407,7 @@ int i40evf_request_queues(struct i40evf_adapter *adapter, int num) vfres.num_queue_pairs = num; adapter->current_op = VIRTCHNL_OP_REQUEST_QUEUES; + adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED; return i40evf_send_pf_msg(adapter, VIRTCHNL_OP_REQUEST_QUEUES, (u8 *)&vfres, sizeof(vfres)); } @@ -1098,15 +1099,13 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, case VIRTCHNL_OP_REQUEST_QUEUES: { struct virtchnl_vf_res_request *vfres = (struct virtchnl_vf_res_request *)msg; - if (vfres->num_queue_pairs == adapter->num_req_queues) { - adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED; - i40evf_schedule_reset(adapter); - } else { + if (vfres->num_queue_pairs != adapter->num_req_queues) { dev_info(&adapter->pdev->dev, "Requested %d queues, PF can support %d\n", adapter->num_req_queues, vfres->num_queue_pairs); adapter->num_req_queues = 0; + adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; } } break; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index fd4a46b03cc8..58d01a211367 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -133,8 +133,8 @@ static void igb_clean_all_rx_rings(struct igb_adapter *); static void igb_clean_tx_ring(struct igb_ring *); static void igb_clean_rx_ring(struct igb_ring *); static void igb_set_rx_mode(struct net_device *); -static void igb_update_phy_info(unsigned long); -static void igb_watchdog(unsigned long); +static void igb_update_phy_info(struct timer_list *); +static void igb_watchdog(struct timer_list *); static void igb_watchdog_task(struct work_struct *); static netdev_tx_t igb_xmit_frame(struct sk_buff *skb, struct net_device *); static void igb_get_stats64(struct net_device *dev, @@ -2538,10 +2538,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) wr32(E1000_TXPBS, I210_TXPBSIZE_DEFAULT); } - setup_timer(&adapter->watchdog_timer, igb_watchdog, - (unsigned long) adapter); - setup_timer(&adapter->phy_info_timer, igb_update_phy_info, - (unsigned long) adapter); + timer_setup(&adapter->watchdog_timer, igb_watchdog, 0); + timer_setup(&adapter->phy_info_timer, igb_update_phy_info, 0); INIT_WORK(&adapter->reset_task, igb_reset_task); INIT_WORK(&adapter->watchdog_task, igb_watchdog_task); @@ -3162,6 +3160,8 @@ static int igb_sw_init(struct igb_adapter *adapter) /* Setup and initialize a copy of the hw vlan table array */ adapter->shadow_vfta = kcalloc(E1000_VLAN_FILTER_TBL_SIZE, sizeof(u32), GFP_ATOMIC); + if (!adapter->shadow_vfta) + return -ENOMEM; /* This call may decrease the number of queues */ if (igb_init_interrupt_scheme(adapter, true)) { @@ -4423,9 +4423,9 @@ static void igb_spoof_check(struct igb_adapter *adapter) /* Need to wait a few seconds after link up to get diagnostic information from * the phy */ -static void igb_update_phy_info(unsigned long data) +static void igb_update_phy_info(struct timer_list *t) { - struct igb_adapter *adapter = (struct igb_adapter *) data; + struct igb_adapter *adapter = from_timer(adapter, t, phy_info_timer); igb_get_phy_info(&adapter->hw); } @@ -4512,9 +4512,9 @@ static void igb_check_lvmmc(struct igb_adapter *adapter) * igb_watchdog - Timer Call-back * @data: pointer to adapter cast into an unsigned long **/ -static void igb_watchdog(unsigned long data) +static void igb_watchdog(struct timer_list *t) { - struct igb_adapter *adapter = (struct igb_adapter *)data; + struct igb_adapter *adapter = from_timer(adapter, t, watchdog_timer); /* Do the rest outside of interrupt context */ schedule_work(&adapter->watchdog_task); } diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 1ed556911b14..713e8df23744 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -1915,9 +1915,9 @@ static bool igbvf_has_link(struct igbvf_adapter *adapter) * igbvf_watchdog - Timer Call-back * @data: pointer to adapter cast into an unsigned long **/ -static void igbvf_watchdog(unsigned long data) +static void igbvf_watchdog(struct timer_list *t) { - struct igbvf_adapter *adapter = (struct igbvf_adapter *)data; + struct igbvf_adapter *adapter = from_timer(adapter, t, watchdog_timer); /* Do the rest outside of interrupt context */ schedule_work(&adapter->watchdog_task); @@ -2878,8 +2878,7 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->addr_len); } - setup_timer(&adapter->watchdog_timer, &igbvf_watchdog, - (unsigned long)adapter); + timer_setup(&adapter->watchdog_timer, igbvf_watchdog, 0); INIT_WORK(&adapter->reset_task, igbvf_reset_task); INIT_WORK(&adapter->watchdog_task, igbvf_watchdog_task); diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index 1e6ec2277d54..2353c383f0a7 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -83,7 +83,7 @@ static void ixgb_setup_rctl(struct ixgb_adapter *adapter); static void ixgb_clean_tx_ring(struct ixgb_adapter *adapter); static void ixgb_clean_rx_ring(struct ixgb_adapter *adapter); static void ixgb_set_multi(struct net_device *netdev); -static void ixgb_watchdog(unsigned long data); +static void ixgb_watchdog(struct timer_list *t); static netdev_tx_t ixgb_xmit_frame(struct sk_buff *skb, struct net_device *netdev); static int ixgb_change_mtu(struct net_device *netdev, int new_mtu); @@ -508,8 +508,7 @@ ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) adapter->part_num = ixgb_get_ee_pba_number(&adapter->hw); - setup_timer(&adapter->watchdog_timer, ixgb_watchdog, - (unsigned long)adapter); + timer_setup(&adapter->watchdog_timer, ixgb_watchdog, 0); INIT_WORK(&adapter->tx_timeout_task, ixgb_tx_timeout_task); @@ -1151,9 +1150,9 @@ alloc_failed: **/ static void -ixgb_watchdog(unsigned long data) +ixgb_watchdog(struct timer_list *t) { - struct ixgb_adapter *adapter = (struct ixgb_adapter *)data; + struct ixgb_adapter *adapter = from_timer(adapter, t, watchdog_timer); struct net_device *netdev = adapter->netdev; struct ixgb_desc_ring *txdr = &adapter->tx_ring; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index dd5578756ae0..468c3555a629 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -275,6 +275,7 @@ struct ixgbe_rx_queue_stats { u64 rsc_count; u64 rsc_flush; u64 non_eop_descs; + u64 alloc_rx_page; u64 alloc_rx_page_failed; u64 alloc_rx_buff_failed; u64 csum_err; @@ -434,8 +435,15 @@ static inline unsigned int ixgbe_rx_pg_order(struct ixgbe_ring *ring) } #define ixgbe_rx_pg_size(_ring) (PAGE_SIZE << ixgbe_rx_pg_order(_ring)) +#define IXGBE_ITR_ADAPTIVE_MIN_INC 2 +#define IXGBE_ITR_ADAPTIVE_MIN_USECS 10 +#define IXGBE_ITR_ADAPTIVE_MAX_USECS 126 +#define IXGBE_ITR_ADAPTIVE_LATENCY 0x80 +#define IXGBE_ITR_ADAPTIVE_BULK 0x00 + struct ixgbe_ring_container { struct ixgbe_ring *ring; /* pointer to linked list of rings */ + unsigned long next_update; /* jiffies value of last update */ unsigned int total_bytes; /* total bytes processed this int */ unsigned int total_packets; /* total packets processed this int */ u16 work_limit; /* total work allowed per interrupt */ @@ -655,6 +663,7 @@ struct ixgbe_adapter { u64 rsc_total_count; u64 rsc_total_flush; u64 non_eop_descs; + u32 alloc_rx_page; u32 alloc_rx_page_failed; u32 alloc_rx_buff_failed; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c index 523f9d05a810..8a32eb7d47b9 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c @@ -175,31 +175,9 @@ static s32 ixgbe_init_phy_ops_82598(struct ixgbe_hw *hw) **/ static s32 ixgbe_start_hw_82598(struct ixgbe_hw *hw) { -#ifndef CONFIG_SPARC - u32 regval; - u32 i; -#endif s32 ret_val; ret_val = ixgbe_start_hw_generic(hw); - -#ifndef CONFIG_SPARC - /* Disable relaxed ordering */ - for (i = 0; ((i < hw->mac.max_tx_queues) && - (i < IXGBE_DCA_MAX_QUEUES_82598)); i++) { - regval = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL(i)); - regval &= ~IXGBE_DCA_TXCTRL_DESC_WRO_EN; - IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL(i), regval); - } - - for (i = 0; ((i < hw->mac.max_rx_queues) && - (i < IXGBE_DCA_MAX_QUEUES_82598)); i++) { - regval = IXGBE_READ_REG(hw, IXGBE_DCA_RXCTRL(i)); - regval &= ~(IXGBE_DCA_RXCTRL_DATA_WRO_EN | - IXGBE_DCA_RXCTRL_HEAD_WRO_EN); - IXGBE_WRITE_REG(hw, IXGBE_DCA_RXCTRL(i), regval); - } -#endif if (ret_val) return ret_val; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 2c19070d2a0b..9bef255f6a18 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -366,25 +366,6 @@ s32 ixgbe_start_hw_gen2(struct ixgbe_hw *hw) } IXGBE_WRITE_FLUSH(hw); -#ifndef CONFIG_ARCH_WANT_RELAX_ORDER - /* Disable relaxed ordering */ - for (i = 0; i < hw->mac.max_tx_queues; i++) { - u32 regval; - - regval = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL_82599(i)); - regval &= ~IXGBE_DCA_TXCTRL_DESC_WRO_EN; - IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL_82599(i), regval); - } - - for (i = 0; i < hw->mac.max_rx_queues; i++) { - u32 regval; - - regval = IXGBE_READ_REG(hw, IXGBE_DCA_RXCTRL(i)); - regval &= ~(IXGBE_DCA_RXCTRL_DATA_WRO_EN | - IXGBE_DCA_RXCTRL_HEAD_WRO_EN); - IXGBE_WRITE_REG(hw, IXGBE_DCA_RXCTRL(i), regval); - } -#endif return 0; } @@ -3800,10 +3781,10 @@ s32 ixgbe_set_fw_drv_ver_generic(struct ixgbe_hw *hw, u8 maj, u8 min, fw_cmd.ver_build = build; fw_cmd.ver_sub = sub; fw_cmd.hdr.checksum = 0; - fw_cmd.hdr.checksum = ixgbe_calculate_checksum((u8 *)&fw_cmd, - (FW_CEM_HDR_LEN + fw_cmd.hdr.buf_len)); fw_cmd.pad = 0; fw_cmd.pad2 = 0; + fw_cmd.hdr.checksum = ixgbe_calculate_checksum((u8 *)&fw_cmd, + (FW_CEM_HDR_LEN + fw_cmd.hdr.buf_len)); for (i = 0; i <= FW_CEM_MAX_RETRIES; i++) { ret_val = ixgbe_host_interface_command(hw, &fw_cmd, @@ -4100,8 +4081,8 @@ bool ixgbe_mng_present(struct ixgbe_hw *hw) return false; fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw)); - fwsm &= IXGBE_FWSM_MODE_MASK; - return fwsm == IXGBE_FWSM_FW_MODE_PT; + + return !!(fwsm & IXGBE_FWSM_FW_MODE_PT); } /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 72c565712a5f..0aad1c2a3667 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -104,6 +104,7 @@ static const struct ixgbe_stats ixgbe_gstrings_stats[] = { {"tx_flow_control_xoff", IXGBE_STAT(stats.lxofftxc)}, {"rx_flow_control_xoff", IXGBE_STAT(stats.lxoffrxc)}, {"rx_csum_offload_errors", IXGBE_STAT(hw_csum_rx_error)}, + {"alloc_rx_page", IXGBE_STAT(alloc_rx_page)}, {"alloc_rx_page_failed", IXGBE_STAT(alloc_rx_page_failed)}, {"alloc_rx_buff_failed", IXGBE_STAT(alloc_rx_buff_failed)}, {"rx_no_dma_resources", IXGBE_STAT(hw_rx_no_dma_resources)}, @@ -1048,7 +1049,7 @@ static int ixgbe_set_ringparam(struct net_device *netdev, { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_ring *temp_ring; - int i, err = 0; + int i, j, err = 0; u32 new_rx_count, new_tx_count; if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) @@ -1085,8 +1086,8 @@ static int ixgbe_set_ringparam(struct net_device *netdev, } /* allocate temporary buffer to store rings in */ - i = max_t(int, adapter->num_tx_queues, adapter->num_rx_queues); - i = max_t(int, i, adapter->num_xdp_queues); + i = max_t(int, adapter->num_tx_queues + adapter->num_xdp_queues, + adapter->num_rx_queues); temp_ring = vmalloc(i * sizeof(struct ixgbe_ring)); if (!temp_ring) { @@ -1118,8 +1119,8 @@ static int ixgbe_set_ringparam(struct net_device *netdev, } } - for (i = 0; i < adapter->num_xdp_queues; i++) { - memcpy(&temp_ring[i], adapter->xdp_ring[i], + for (j = 0; j < adapter->num_xdp_queues; j++, i++) { + memcpy(&temp_ring[i], adapter->xdp_ring[j], sizeof(struct ixgbe_ring)); temp_ring[i].count = new_tx_count; @@ -1139,10 +1140,10 @@ static int ixgbe_set_ringparam(struct net_device *netdev, memcpy(adapter->tx_ring[i], &temp_ring[i], sizeof(struct ixgbe_ring)); } - for (i = 0; i < adapter->num_xdp_queues; i++) { - ixgbe_free_tx_resources(adapter->xdp_ring[i]); + for (j = 0; j < adapter->num_xdp_queues; j++, i++) { + ixgbe_free_tx_resources(adapter->xdp_ring[j]); - memcpy(adapter->xdp_ring[i], &temp_ring[i], + memcpy(adapter->xdp_ring[j], &temp_ring[i], sizeof(struct ixgbe_ring)); } @@ -1916,8 +1917,6 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring, unsigned int size) { union ixgbe_adv_rx_desc *rx_desc; - struct ixgbe_rx_buffer *rx_buffer; - struct ixgbe_tx_buffer *tx_buffer; u16 rx_ntc, tx_ntc, count = 0; /* initialize next to clean and descriptor values */ @@ -1925,7 +1924,38 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring, tx_ntc = tx_ring->next_to_clean; rx_desc = IXGBE_RX_DESC(rx_ring, rx_ntc); + while (tx_ntc != tx_ring->next_to_use) { + union ixgbe_adv_tx_desc *tx_desc; + struct ixgbe_tx_buffer *tx_buffer; + + tx_desc = IXGBE_TX_DESC(tx_ring, tx_ntc); + + /* if DD is not set transmit has not completed */ + if (!(tx_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD))) + return count; + + /* unmap buffer on Tx side */ + tx_buffer = &tx_ring->tx_buffer_info[tx_ntc]; + + /* Free all the Tx ring sk_buffs */ + dev_kfree_skb_any(tx_buffer->skb); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + + /* increment Tx next to clean counter */ + tx_ntc++; + if (tx_ntc == tx_ring->count) + tx_ntc = 0; + } + while (rx_desc->wb.upper.length) { + struct ixgbe_rx_buffer *rx_buffer; + /* check Rx buffer */ rx_buffer = &rx_ring->rx_buffer_info[rx_ntc]; @@ -1938,6 +1968,8 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring, /* verify contents of skb */ if (ixgbe_check_lbtest_frame(rx_buffer, size)) count++; + else + break; /* sync Rx buffer for device write */ dma_sync_single_for_device(rx_ring->dev, @@ -1945,26 +1977,10 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring, ixgbe_rx_bufsz(rx_ring), DMA_FROM_DEVICE); - /* unmap buffer on Tx side */ - tx_buffer = &tx_ring->tx_buffer_info[tx_ntc]; - - /* Free all the Tx ring sk_buffs */ - dev_kfree_skb_any(tx_buffer->skb); - - /* unmap skb header data */ - dma_unmap_single(tx_ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); - dma_unmap_len_set(tx_buffer, len, 0); - - /* increment Rx/Tx next to clean counters */ + /* increment Rx next to clean counter */ rx_ntc++; if (rx_ntc == rx_ring->count) rx_ntc = 0; - tx_ntc++; - if (tx_ntc == tx_ring->count) - tx_ntc = 0; /* fetch next descriptor */ rx_desc = IXGBE_RX_DESC(rx_ring, rx_ntc); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index f1bfae0c41d0..8e2a957aca18 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -806,6 +806,7 @@ static void ixgbe_add_ring(struct ixgbe_ring *ring, ring->next = head->ring; head->ring = ring; head->count++; + head->next_update = jiffies + 1; } /** @@ -879,8 +880,11 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, /* initialize work limits */ q_vector->tx.work_limit = adapter->tx_work_limit; - /* initialize pointer to rings */ - ring = q_vector->ring; + /* Initialize setting for adaptive ITR */ + q_vector->tx.itr = IXGBE_ITR_ADAPTIVE_MAX_USECS | + IXGBE_ITR_ADAPTIVE_LATENCY; + q_vector->rx.itr = IXGBE_ITR_ADAPTIVE_MAX_USECS | + IXGBE_ITR_ADAPTIVE_LATENCY; /* intialize ITR */ if (txr_count && !rxr_count) { @@ -897,6 +901,9 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, q_vector->itr = adapter->rx_itr_setting; } + /* initialize pointer to rings */ + ring = q_vector->ring; + while (txr_count) { /* assign generic ring traits */ ring->dev = &adapter->pdev->dev; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 3942c6208745..3e83edd10e23 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1620,6 +1620,7 @@ static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring, bi->page = page; bi->page_offset = ixgbe_rx_offset(rx_ring); bi->pagecnt_bias = 1; + rx_ring->rx_stats.alloc_rx_page++; return true; } @@ -2539,50 +2540,174 @@ enum latency_range { static void ixgbe_update_itr(struct ixgbe_q_vector *q_vector, struct ixgbe_ring_container *ring_container) { - int bytes = ring_container->total_bytes; - int packets = ring_container->total_packets; - u32 timepassed_us; - u64 bytes_perint; - u8 itr_setting = ring_container->itr; + unsigned int itr = IXGBE_ITR_ADAPTIVE_MIN_USECS | + IXGBE_ITR_ADAPTIVE_LATENCY; + unsigned int avg_wire_size, packets, bytes; + unsigned long next_update = jiffies; - if (packets == 0) + /* If we don't have any rings just leave ourselves set for maximum + * possible latency so we take ourselves out of the equation. + */ + if (!ring_container->ring) return; - /* simple throttlerate management - * 0-10MB/s lowest (100000 ints/s) - * 10-20MB/s low (20000 ints/s) - * 20-1249MB/s bulk (12000 ints/s) + /* If we didn't update within up to 1 - 2 jiffies we can assume + * that either packets are coming in so slow there hasn't been + * any work, or that there is so much work that NAPI is dealing + * with interrupt moderation and we don't need to do anything. */ - /* what was last interrupt timeslice? */ - timepassed_us = q_vector->itr >> 2; - if (timepassed_us == 0) - return; + if (time_after(next_update, ring_container->next_update)) + goto clear_counts; - bytes_perint = bytes / timepassed_us; /* bytes/usec */ + packets = ring_container->total_packets; - switch (itr_setting) { - case lowest_latency: - if (bytes_perint > 10) - itr_setting = low_latency; - break; - case low_latency: - if (bytes_perint > 20) - itr_setting = bulk_latency; - else if (bytes_perint <= 10) - itr_setting = lowest_latency; + /* We have no packets to actually measure against. This means + * either one of the other queues on this vector is active or + * we are a Tx queue doing TSO with too high of an interrupt rate. + * + * When this occurs just tick up our delay by the minimum value + * and hope that this extra delay will prevent us from being called + * without any work on our queue. + */ + if (!packets) { + itr = (q_vector->itr >> 2) + IXGBE_ITR_ADAPTIVE_MIN_INC; + if (itr > IXGBE_ITR_ADAPTIVE_MAX_USECS) + itr = IXGBE_ITR_ADAPTIVE_MAX_USECS; + itr += ring_container->itr & IXGBE_ITR_ADAPTIVE_LATENCY; + goto clear_counts; + } + + bytes = ring_container->total_bytes; + + /* If packets are less than 4 or bytes are less than 9000 assume + * insufficient data to use bulk rate limiting approach. We are + * likely latency driven. + */ + if (packets < 4 && bytes < 9000) { + itr = IXGBE_ITR_ADAPTIVE_LATENCY; + goto adjust_by_size; + } + + /* Between 4 and 48 we can assume that our current interrupt delay + * is only slightly too low. As such we should increase it by a small + * fixed amount. + */ + if (packets < 48) { + itr = (q_vector->itr >> 2) + IXGBE_ITR_ADAPTIVE_MIN_INC; + if (itr > IXGBE_ITR_ADAPTIVE_MAX_USECS) + itr = IXGBE_ITR_ADAPTIVE_MAX_USECS; + goto clear_counts; + } + + /* Between 48 and 96 is our "goldilocks" zone where we are working + * out "just right". Just report that our current ITR is good for us. + */ + if (packets < 96) { + itr = q_vector->itr >> 2; + goto clear_counts; + } + + /* If packet count is 96 or greater we are likely looking at a slight + * overrun of the delay we want. Try halving our delay to see if that + * will cut the number of packets in half per interrupt. + */ + if (packets < 256) { + itr = q_vector->itr >> 3; + if (itr < IXGBE_ITR_ADAPTIVE_MIN_USECS) + itr = IXGBE_ITR_ADAPTIVE_MIN_USECS; + goto clear_counts; + } + + /* The paths below assume we are dealing with a bulk ITR since number + * of packets is 256 or greater. We are just going to have to compute + * a value and try to bring the count under control, though for smaller + * packet sizes there isn't much we can do as NAPI polling will likely + * be kicking in sooner rather than later. + */ + itr = IXGBE_ITR_ADAPTIVE_BULK; + +adjust_by_size: + /* If packet counts are 256 or greater we can assume we have a gross + * overestimation of what the rate should be. Instead of trying to fine + * tune it just use the formula below to try and dial in an exact value + * give the current packet size of the frame. + */ + avg_wire_size = bytes / packets; + + /* The following is a crude approximation of: + * wmem_default / (size + overhead) = desired_pkts_per_int + * rate / bits_per_byte / (size + ethernet overhead) = pkt_rate + * (desired_pkt_rate / pkt_rate) * usecs_per_sec = ITR value + * + * Assuming wmem_default is 212992 and overhead is 640 bytes per + * packet, (256 skb, 64 headroom, 320 shared info), we can reduce the + * formula down to + * + * (170 * (size + 24)) / (size + 640) = ITR + * + * We first do some math on the packet size and then finally bitshift + * by 8 after rounding up. We also have to account for PCIe link speed + * difference as ITR scales based on this. + */ + if (avg_wire_size <= 60) { + /* Start at 50k ints/sec */ + avg_wire_size = 5120; + } else if (avg_wire_size <= 316) { + /* 50K ints/sec to 16K ints/sec */ + avg_wire_size *= 40; + avg_wire_size += 2720; + } else if (avg_wire_size <= 1084) { + /* 16K ints/sec to 9.2K ints/sec */ + avg_wire_size *= 15; + avg_wire_size += 11452; + } else if (avg_wire_size <= 1980) { + /* 9.2K ints/sec to 8K ints/sec */ + avg_wire_size *= 5; + avg_wire_size += 22420; + } else { + /* plateau at a limit of 8K ints/sec */ + avg_wire_size = 32256; + } + + /* If we are in low latency mode half our delay which doubles the rate + * to somewhere between 100K to 16K ints/sec + */ + if (itr & IXGBE_ITR_ADAPTIVE_LATENCY) + avg_wire_size >>= 1; + + /* Resultant value is 256 times larger than it needs to be. This + * gives us room to adjust the value as needed to either increase + * or decrease the value based on link speeds of 10G, 2.5G, 1G, etc. + * + * Use addition as we have already recorded the new latency flag + * for the ITR value. + */ + switch (q_vector->adapter->link_speed) { + case IXGBE_LINK_SPEED_10GB_FULL: + case IXGBE_LINK_SPEED_100_FULL: + default: + itr += DIV_ROUND_UP(avg_wire_size, + IXGBE_ITR_ADAPTIVE_MIN_INC * 256) * + IXGBE_ITR_ADAPTIVE_MIN_INC; break; - case bulk_latency: - if (bytes_perint <= 20) - itr_setting = low_latency; + case IXGBE_LINK_SPEED_2_5GB_FULL: + case IXGBE_LINK_SPEED_1GB_FULL: + case IXGBE_LINK_SPEED_10_FULL: + itr += DIV_ROUND_UP(avg_wire_size, + IXGBE_ITR_ADAPTIVE_MIN_INC * 64) * + IXGBE_ITR_ADAPTIVE_MIN_INC; break; } - /* clear work counters since we have the values we need */ +clear_counts: + /* write back value */ + ring_container->itr = itr; + + /* next update should occur within next jiffy */ + ring_container->next_update = next_update + 1; + ring_container->total_bytes = 0; ring_container->total_packets = 0; - - /* write updated itr to ring container */ - ring_container->itr = itr_setting; } /** @@ -2624,34 +2749,19 @@ void ixgbe_write_eitr(struct ixgbe_q_vector *q_vector) static void ixgbe_set_itr(struct ixgbe_q_vector *q_vector) { - u32 new_itr = q_vector->itr; - u8 current_itr; + u32 new_itr; ixgbe_update_itr(q_vector, &q_vector->tx); ixgbe_update_itr(q_vector, &q_vector->rx); - current_itr = max(q_vector->rx.itr, q_vector->tx.itr); + /* use the smallest value of new ITR delay calculations */ + new_itr = min(q_vector->rx.itr, q_vector->tx.itr); - switch (current_itr) { - /* counts and packets in update_itr are dependent on these numbers */ - case lowest_latency: - new_itr = IXGBE_100K_ITR; - break; - case low_latency: - new_itr = IXGBE_20K_ITR; - break; - case bulk_latency: - new_itr = IXGBE_12K_ITR; - break; - default: - break; - } + /* Clear latency flag if set, shift into correct position */ + new_itr &= ~IXGBE_ITR_ADAPTIVE_LATENCY; + new_itr <<= 2; if (new_itr != q_vector->itr) { - /* do an exponential smoothing */ - new_itr = (10 * new_itr * q_vector->itr) / - ((9 * new_itr) + q_vector->itr); - /* save the algorithm value here */ q_vector->itr = new_itr; @@ -4904,7 +5014,7 @@ static void ixgbe_clear_udp_tunnel_port(struct ixgbe_adapter *adapter, u32 mask) IXGBE_FLAG_GENEVE_OFFLOAD_CAPABLE))) return; - vxlanctrl = IXGBE_READ_REG(hw, IXGBE_VXLANCTRL) && ~mask; + vxlanctrl = IXGBE_READ_REG(hw, IXGBE_VXLANCTRL) & ~mask; IXGBE_WRITE_REG(hw, IXGBE_VXLANCTRL, vxlanctrl); if (mask & IXGBE_VXLANCTRL_VXLAN_UDPPORT_MASK) @@ -6794,6 +6904,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) u32 i, missed_rx = 0, mpc, bprc, lxon, lxoff, xon_off_tot; u64 non_eop_descs = 0, restart_queue = 0, tx_busy = 0; u64 alloc_rx_page_failed = 0, alloc_rx_buff_failed = 0; + u64 alloc_rx_page = 0; u64 bytes = 0, packets = 0, hw_csum_rx_error = 0; if (test_bit(__IXGBE_DOWN, &adapter->state) || @@ -6814,6 +6925,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) for (i = 0; i < adapter->num_rx_queues; i++) { struct ixgbe_ring *rx_ring = adapter->rx_ring[i]; non_eop_descs += rx_ring->rx_stats.non_eop_descs; + alloc_rx_page += rx_ring->rx_stats.alloc_rx_page; alloc_rx_page_failed += rx_ring->rx_stats.alloc_rx_page_failed; alloc_rx_buff_failed += rx_ring->rx_stats.alloc_rx_buff_failed; hw_csum_rx_error += rx_ring->rx_stats.csum_err; @@ -6821,6 +6933,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) packets += rx_ring->stats.packets; } adapter->non_eop_descs = non_eop_descs; + adapter->alloc_rx_page = alloc_rx_page; adapter->alloc_rx_page_failed = alloc_rx_page_failed; adapter->alloc_rx_buff_failed = alloc_rx_buff_failed; adapter->hw_csum_rx_error = hw_csum_rx_error; @@ -7577,9 +7690,9 @@ static void ixgbe_sfp_link_config_subtask(struct ixgbe_adapter *adapter) * ixgbe_service_timer - Timer Call-back * @data: pointer to adapter cast into an unsigned long **/ -static void ixgbe_service_timer(unsigned long data) +static void ixgbe_service_timer(struct timer_list *t) { - struct ixgbe_adapter *adapter = (struct ixgbe_adapter *)data; + struct ixgbe_adapter *adapter = from_timer(adapter, t, service_timer); unsigned long next_event_offset; /* poll faster when waiting for link */ @@ -8552,6 +8665,10 @@ static int ixgbe_ioctl(struct net_device *netdev, struct ifreq *req, int cmd) return ixgbe_ptp_set_ts_config(adapter, req); case SIOCGHWTSTAMP: return ixgbe_ptp_get_ts_config(adapter, req); + case SIOCGMIIPHY: + if (!adapter->hw.phy.ops.read_reg) + return -EOPNOTSUPP; + /* fall through */ default: return mdio_mii_ioctl(&adapter->hw.phy.mdio, if_mii(req), cmd); } @@ -9758,6 +9875,17 @@ static void ixgbe_fwd_del(struct net_device *pdev, void *priv) limit = find_last_bit(&adapter->fwd_bitmask, 32); adapter->ring_feature[RING_F_VMDQ].limit = limit + 1; ixgbe_fwd_ring_down(fwd_adapter->netdev, fwd_adapter); + + /* go back to full RSS if we're done with our VMQs */ + if (adapter->ring_feature[RING_F_VMDQ].limit == 1) { + int rss = min_t(int, ixgbe_max_rss_indices(adapter), + num_online_cpus()); + + adapter->flags &= ~IXGBE_FLAG_VMDQ_ENABLED; + adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED; + adapter->ring_feature[RING_F_RSS].limit = rss; + } + ixgbe_setup_tc(pdev, netdev_get_num_tc(pdev)); netdev_dbg(pdev, "pool %i:%i queues %i:%i VSI bitmask %lx\n", fwd_adapter->pool, adapter->num_rx_pools, @@ -10380,8 +10508,7 @@ skip_sriov: ether_addr_copy(hw->mac.addr, hw->mac.perm_addr); ixgbe_mac_set_default_filter(adapter); - setup_timer(&adapter->service_timer, &ixgbe_service_timer, - (unsigned long) adapter); + timer_setup(&adapter->service_timer, ixgbe_service_timer, 0); if (ixgbe_removed(hw->hw_addr)) { err = -EIO; @@ -10737,6 +10864,9 @@ skip_bad_vf_detection: if (!test_bit(__IXGBE_SERVICE_INITED, &adapter->state)) return PCI_ERS_RESULT_DISCONNECT; + if (!netif_device_present(netdev)) + return PCI_ERS_RESULT_DISCONNECT; + rtnl_lock(); netif_device_detach(netdev); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c index 6ea0d6a5fb90..b8c5fd2a2115 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c @@ -619,12 +619,6 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask) usleep_range(5000, 10000); } - /* Failed to get SW only semaphore */ - if (swmask == IXGBE_GSSR_SW_MNG_SM) { - hw_dbg(hw, "Failed to get SW only semaphore\n"); - return IXGBE_ERR_SWFW_SYNC; - } - /* If the resource is not released by the FW/HW the SW can assume that * the FW/HW malfunctions. In that case the SW should set the SW bit(s) * of the requested resource(s) while ignoring the corresponding FW/HW @@ -647,7 +641,8 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask) */ if (swfw_sync & swmask) { u32 rmask = IXGBE_GSSR_EEP_SM | IXGBE_GSSR_PHY0_SM | - IXGBE_GSSR_PHY1_SM | IXGBE_GSSR_MAC_CSR_SM; + IXGBE_GSSR_PHY1_SM | IXGBE_GSSR_MAC_CSR_SM | + IXGBE_GSSR_SW_MNG_SM; if (swi2c_mask) rmask |= IXGBE_GSSR_I2C_MASK; @@ -763,6 +758,8 @@ static void ixgbe_release_swfw_sync_semaphore(struct ixgbe_hw *hw) **/ void ixgbe_init_swfw_sync_X540(struct ixgbe_hw *hw) { + u32 rmask; + /* First try to grab the semaphore but we don't need to bother * looking to see whether we got the lock or not since we do * the same thing regardless of whether we got the lock or not. @@ -771,6 +768,14 @@ void ixgbe_init_swfw_sync_X540(struct ixgbe_hw *hw) */ ixgbe_get_swfw_sync_semaphore(hw); ixgbe_release_swfw_sync_semaphore(hw); + + /* Acquire and release all software resources. */ + rmask = IXGBE_GSSR_EEP_SM | IXGBE_GSSR_PHY0_SM | + IXGBE_GSSR_PHY1_SM | IXGBE_GSSR_MAC_CSR_SM | + IXGBE_GSSR_SW_MNG_SM | IXGBE_GSSR_I2C_MASK; + + ixgbe_acquire_swfw_sync_X540(hw, rmask); + ixgbe_release_swfw_sync_X540(hw, rmask); } /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 19fbb2f28ea4..cb7da5f9c4da 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -900,6 +900,8 @@ static s32 ixgbe_read_ee_hostif_buffer_X550(struct ixgbe_hw *hw, /* convert offset from words to bytes */ buffer.address = cpu_to_be32((offset + current_word) * 2); buffer.length = cpu_to_be16(words_to_read * 2); + buffer.pad2 = 0; + buffer.pad3 = 0; status = ixgbe_hic_unlocked(hw, (u32 *)&buffer, sizeof(buffer), IXGBE_HI_COMMAND_TIMEOUT); @@ -3192,6 +3194,9 @@ static s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw) /* Identify the PHY or SFP module */ ret_val = phy->ops.identify(hw); + if (ret_val == IXGBE_ERR_SFP_NOT_SUPPORTED || + ret_val == IXGBE_ERR_PHY_ADDR_INVALID) + return ret_val; /* Setup function pointers based on detected hardware */ ixgbe_init_mac_link_ops_X550em(hw); @@ -3394,9 +3399,10 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw) ixgbe_clear_tx_pending(hw); /* PHY ops must be identified and initialized prior to reset */ - - /* Identify PHY and related function pointers */ status = hw->phy.ops.init(hw); + if (status == IXGBE_ERR_SFP_NOT_SUPPORTED || + status == IXGBE_ERR_PHY_ADDR_INVALID) + return status; /* start the external PHY */ if (hw->phy.type == ixgbe_phy_x550em_ext_t) { @@ -3884,7 +3890,7 @@ static const struct ixgbe_mac_operations mac_ops_X550EM_x_fw = { .write_iosf_sb_reg = ixgbe_write_iosf_sb_reg_x550, }; -static struct ixgbe_mac_operations mac_ops_x550em_a = { +static const struct ixgbe_mac_operations mac_ops_x550em_a = { X550_COMMON_MAC .led_on = ixgbe_led_on_t_x550em, .led_off = ixgbe_led_off_t_x550em, @@ -3905,7 +3911,7 @@ static struct ixgbe_mac_operations mac_ops_x550em_a = { .write_iosf_sb_reg = ixgbe_write_iosf_sb_reg_x550a, }; -static struct ixgbe_mac_operations mac_ops_x550em_a_fw = { +static const struct ixgbe_mac_operations mac_ops_x550em_a_fw = { X550_COMMON_MAC .led_on = ixgbe_led_on_generic, .led_off = ixgbe_led_off_generic, diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 032f8ac06357..12d3601b1d57 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -2747,9 +2747,10 @@ void ixgbevf_update_stats(struct ixgbevf_adapter *adapter) * ixgbevf_service_timer - Timer Call-back * @data: pointer to adapter cast into an unsigned long **/ -static void ixgbevf_service_timer(unsigned long data) +static void ixgbevf_service_timer(struct timer_list *t) { - struct ixgbevf_adapter *adapter = (struct ixgbevf_adapter *)data; + struct ixgbevf_adapter *adapter = from_timer(adapter, t, + service_timer); /* Reset the timer */ mod_timer(&adapter->service_timer, (HZ * 2) + jiffies); @@ -4120,8 +4121,7 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_sw_init; } - setup_timer(&adapter->service_timer, &ixgbevf_service_timer, - (unsigned long)adapter); + timer_setup(&adapter->service_timer, ixgbevf_service_timer, 0); INIT_WORK(&adapter->service_task, ixgbevf_service_task); set_bit(__IXGBEVF_SERVICE_INITED, &adapter->state); |