diff options
Diffstat (limited to 'drivers/net/ethernet/intel')
57 files changed, 6227 insertions, 1345 deletions
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 4d10270ddf8f..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; @@ -1910,11 +1910,10 @@ static int e100_alloc_cbs(struct nic *nic) nic->cb_to_use = nic->cb_to_send = nic->cb_to_clean = NULL; nic->cbs_avail = 0; - nic->cbs = pci_pool_alloc(nic->cbs_pool, GFP_KERNEL, - &nic->cbs_dma_addr); + nic->cbs = pci_pool_zalloc(nic->cbs_pool, GFP_KERNEL, + &nic->cbs_dma_addr); if (!nic->cbs) return -ENOMEM; - memset(nic->cbs, 0, count * sizeof(struct cb)); for (cb = nic->cbs, i = 0; i < count; cb++, i++) { cb->next = (i + 1 < count) ? cb + 1 : nic->cbs; @@ -2921,7 +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 327dfe5bedc0..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; @@ -7252,13 +7267,8 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_eeprom; } - init_timer(&adapter->watchdog_timer); - adapter->watchdog_timer.function = e1000_watchdog; - adapter->watchdog_timer.data = (unsigned long)adapter; - - init_timer(&adapter->phy_info_timer); - adapter->phy_info_timer.function = e1000_update_phy_info; - adapter->phy_info_timer.data = (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); @@ -7411,7 +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.h b/drivers/net/ethernet/intel/fm10k/fm10k.h index 689c413b7782..46973fb234c5 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k.h @@ -248,6 +248,29 @@ struct fm10k_udp_port { __be16 port; }; +enum fm10k_macvlan_request_type { + FM10K_UC_MAC_REQUEST, + FM10K_MC_MAC_REQUEST, + FM10K_VLAN_REQUEST +}; + +struct fm10k_macvlan_request { + enum fm10k_macvlan_request_type type; + struct list_head list; + union { + struct fm10k_mac_request { + u8 addr[ETH_ALEN]; + u16 glort; + u16 vid; + } mac; + struct fm10k_vlan_request { + u32 vid; + u8 vsi; + } vlan; + }; + bool set; +}; + /* one work queue for entire driver */ extern struct workqueue_struct *fm10k_workqueue; @@ -270,11 +293,15 @@ enum fm10k_flags_t { enum fm10k_state_t { __FM10K_RESETTING, + __FM10K_RESET_DETACHED, + __FM10K_RESET_SUSPENDED, __FM10K_DOWN, __FM10K_SERVICE_SCHED, __FM10K_SERVICE_REQUEST, __FM10K_SERVICE_DISABLE, - __FM10K_MBX_LOCK, + __FM10K_MACVLAN_SCHED, + __FM10K_MACVLAN_REQUEST, + __FM10K_MACVLAN_DISABLE, __FM10K_LINK_DOWN, __FM10K_UPDATING_STATS, /* This value must be last and determines the BITMAP size */ @@ -344,6 +371,8 @@ struct fm10k_intfc { struct fm10k_hw_stats stats; struct fm10k_hw hw; + /* Mailbox lock */ + spinlock_t mbx_lock; u32 __iomem *uc_addr; u32 __iomem *sw_addr; u16 msg_enable; @@ -365,6 +394,12 @@ struct fm10k_intfc { struct list_head vxlan_port; struct list_head geneve_port; + /* MAC/VLAN update queue */ + struct list_head macvlan_requests; + struct delayed_work macvlan_task; + /* MAC/VLAN update queue lock */ + spinlock_t macvlan_lock; + #ifdef CONFIG_DEBUG_FS struct dentry *dbg_intfc; #endif /* CONFIG_DEBUG_FS */ @@ -384,23 +419,17 @@ struct fm10k_intfc { static inline void fm10k_mbx_lock(struct fm10k_intfc *interface) { - /* busy loop if we cannot obtain the lock as some calls - * such as ndo_set_rx_mode may be made in atomic context - */ - while (test_and_set_bit(__FM10K_MBX_LOCK, interface->state)) - udelay(20); + spin_lock(&interface->mbx_lock); } static inline void fm10k_mbx_unlock(struct fm10k_intfc *interface) { - /* flush memory to make sure state is correct */ - smp_mb__before_atomic(); - clear_bit(__FM10K_MBX_LOCK, interface->state); + spin_unlock(&interface->mbx_lock); } static inline int fm10k_mbx_trylock(struct fm10k_intfc *interface) { - return !test_and_set_bit(__FM10K_MBX_LOCK, interface->state); + return spin_trylock(&interface->mbx_lock); } /* fm10k_test_staterr - test bits in Rx descriptor status and error fields */ @@ -490,6 +519,7 @@ void fm10k_up(struct fm10k_intfc *interface); void fm10k_down(struct fm10k_intfc *interface); void fm10k_update_stats(struct fm10k_intfc *interface); void fm10k_service_event_schedule(struct fm10k_intfc *interface); +void fm10k_macvlan_schedule(struct fm10k_intfc *interface); void fm10k_update_rx_drop_en(struct fm10k_intfc *interface); #ifdef CONFIG_NET_POLL_CONTROLLER void fm10k_netpoll(struct net_device *netdev); @@ -510,6 +540,12 @@ void fm10k_reset_rx_state(struct fm10k_intfc *); int fm10k_setup_tc(struct net_device *dev, u8 tc); int fm10k_open(struct net_device *netdev); int fm10k_close(struct net_device *netdev); +int fm10k_queue_vlan_request(struct fm10k_intfc *interface, u32 vid, + u8 vsi, bool set); +int fm10k_queue_mac_request(struct fm10k_intfc *interface, u16 glort, + const unsigned char *addr, u16 vid, bool set); +void fm10k_clear_macvlan_queue(struct fm10k_intfc *interface, + u16 glort, bool vlans); /* Ethtool */ void fm10k_set_ethtool_ops(struct net_device *dev); @@ -526,8 +562,8 @@ s32 fm10k_iov_update_pvid(struct fm10k_intfc *interface, u16 glort, u16 pvid); int fm10k_ndo_set_vf_mac(struct net_device *netdev, int vf_idx, u8 *mac); int fm10k_ndo_set_vf_vlan(struct net_device *netdev, int vf_idx, u16 vid, u8 qos, __be16 vlan_proto); -int fm10k_ndo_set_vf_bw(struct net_device *netdev, int vf_idx, int rate, - int unused); +int fm10k_ndo_set_vf_bw(struct net_device *netdev, int vf_idx, + int __always_unused min_rate, int max_rate); int fm10k_ndo_get_vf_config(struct net_device *netdev, int vf_idx, struct ifla_vf_info *ivi); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_common.c b/drivers/net/ethernet/intel/fm10k/fm10k_common.c index 62a6ad9b3eed..736a9f087bc9 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_common.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_common.c @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. + * Copyright(c) 2013 - 2017 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -517,8 +517,8 @@ s32 fm10k_get_host_state_generic(struct fm10k_hw *hw, bool *host_ready) goto out; } - /* verify Mailbox is still valid */ - if (!mbx->ops.tx_ready(mbx, FM10K_VFMBX_MSG_MTU)) + /* verify Mailbox is still open */ + if (mbx->state != FM10K_STATE_OPEN) goto out; /* interface cannot receive traffic without logical ports */ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c index 5116fd043630..14df09e2d964 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c @@ -52,9 +52,9 @@ static void fm10k_dbg_desc_seq_stop(struct seq_file __always_unused *s, static void fm10k_dbg_desc_break(struct seq_file *s, int i) { while (i--) - seq_puts(s, "-"); + seq_putc(s, '-'); - seq_puts(s, "\n"); + seq_putc(s, '\n'); } static int fm10k_dbg_tx_desc_seq_show(struct seq_file *s, void *v) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c index 5f4dac0d36ef..ea3ab24265ee 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. + * Copyright(c) 2013 - 2017 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -35,10 +35,133 @@ static s32 fm10k_iov_msg_error(struct fm10k_hw *hw, u32 **results, return fm10k_tlv_msg_error(hw, results, mbx); } +/** + * fm10k_iov_msg_queue_mac_vlan - Message handler for MAC/VLAN request from VF + * @hw: Pointer to hardware structure + * @results: Pointer array to message, results[0] is pointer to message + * @mbx: Pointer to mailbox information structure + * + * This function is a custom handler for MAC/VLAN requests from the VF. The + * assumption is that it is acceptable to directly hand off the message from + * the VF to the PF's switch manager. However, we use a MAC/VLAN message + * queue to avoid overloading the mailbox when a large number of requests + * come in. + **/ +static s32 fm10k_iov_msg_queue_mac_vlan(struct fm10k_hw *hw, u32 **results, + struct fm10k_mbx_info *mbx) +{ + struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx; + struct fm10k_intfc *interface = hw->back; + u8 mac[ETH_ALEN]; + u32 *result; + int err = 0; + bool set; + u16 vlan; + u32 vid; + + /* we shouldn't be updating rules on a disabled interface */ + if (!FM10K_VF_FLAG_ENABLED(vf_info)) + err = FM10K_ERR_PARAM; + + if (!err && !!results[FM10K_MAC_VLAN_MSG_VLAN]) { + result = results[FM10K_MAC_VLAN_MSG_VLAN]; + + /* record VLAN id requested */ + err = fm10k_tlv_attr_get_u32(result, &vid); + if (err) + return err; + + set = !(vid & FM10K_VLAN_CLEAR); + vid &= ~FM10K_VLAN_CLEAR; + + /* if the length field has been set, this is a multi-bit + * update request. For multi-bit requests, simply disallow + * them when the pf_vid has been set. In this case, the PF + * should have already cleared the VLAN_TABLE, and if we + * allowed them, it could allow a rogue VF to receive traffic + * on a VLAN it was not assigned. In the single-bit case, we + * need to modify requests for VLAN 0 to use the default PF or + * SW vid when assigned. + */ + + if (vid >> 16) { + /* prevent multi-bit requests when PF has + * administratively set the VLAN for this VF + */ + if (vf_info->pf_vid) + return FM10K_ERR_PARAM; + } else { + err = fm10k_iov_select_vid(vf_info, (u16)vid); + if (err < 0) + return err; + + vid = err; + } + + /* update VSI info for VF in regards to VLAN table */ + err = hw->mac.ops.update_vlan(hw, vid, vf_info->vsi, set); + } + + if (!err && !!results[FM10K_MAC_VLAN_MSG_MAC]) { + result = results[FM10K_MAC_VLAN_MSG_MAC]; + + /* record unicast MAC address requested */ + err = fm10k_tlv_attr_get_mac_vlan(result, mac, &vlan); + if (err) + return err; + + /* block attempts to set MAC for a locked device */ + if (is_valid_ether_addr(vf_info->mac) && + !ether_addr_equal(mac, vf_info->mac)) + return FM10K_ERR_PARAM; + + set = !(vlan & FM10K_VLAN_CLEAR); + vlan &= ~FM10K_VLAN_CLEAR; + + err = fm10k_iov_select_vid(vf_info, vlan); + if (err < 0) + return err; + + vlan = (u16)err; + + /* Add this request to the MAC/VLAN queue */ + err = fm10k_queue_mac_request(interface, vf_info->glort, + mac, vlan, set); + } + + if (!err && !!results[FM10K_MAC_VLAN_MSG_MULTICAST]) { + result = results[FM10K_MAC_VLAN_MSG_MULTICAST]; + + /* record multicast MAC address requested */ + err = fm10k_tlv_attr_get_mac_vlan(result, mac, &vlan); + if (err) + return err; + + /* verify that the VF is allowed to request multicast */ + if (!(vf_info->vf_flags & FM10K_VF_FLAG_MULTI_ENABLED)) + return FM10K_ERR_PARAM; + + set = !(vlan & FM10K_VLAN_CLEAR); + vlan &= ~FM10K_VLAN_CLEAR; + + err = fm10k_iov_select_vid(vf_info, vlan); + if (err < 0) + return err; + + vlan = (u16)err; + + /* Add this request to the MAC/VLAN queue */ + err = fm10k_queue_mac_request(interface, vf_info->glort, + mac, vlan, set); + } + + return err; +} + static const struct fm10k_msg_data iov_mbx_data[] = { FM10K_TLV_MSG_TEST_HANDLER(fm10k_tlv_msg_test), FM10K_VF_MSG_MSIX_HANDLER(fm10k_iov_msg_msix_pf), - FM10K_VF_MSG_MAC_VLAN_HANDLER(fm10k_iov_msg_mac_vlan_pf), + FM10K_VF_MSG_MAC_VLAN_HANDLER(fm10k_iov_msg_queue_mac_vlan), FM10K_VF_MSG_LPORT_STATE_HANDLER(fm10k_iov_msg_lport_state_pf), FM10K_TLV_MSG_ERROR_HANDLER(fm10k_iov_msg_error), }; @@ -66,25 +189,21 @@ s32 fm10k_iov_event(struct fm10k_intfc *interface) goto read_unlock; /* read VFLRE to determine if any VFs have been reset */ - do { - vflre = fm10k_read_reg(hw, FM10K_PFVFLRE(0)); - vflre <<= 32; - vflre |= fm10k_read_reg(hw, FM10K_PFVFLRE(1)); - vflre = (vflre << 32) | (vflre >> 32); - vflre |= fm10k_read_reg(hw, FM10K_PFVFLRE(0)); + vflre = fm10k_read_reg(hw, FM10K_PFVFLRE(1)); + vflre <<= 32; + vflre |= fm10k_read_reg(hw, FM10K_PFVFLRE(0)); - i = iov_data->num_vfs; + i = iov_data->num_vfs; - for (vflre <<= 64 - i; vflre && i--; vflre += vflre) { - struct fm10k_vf_info *vf_info = &iov_data->vf_info[i]; + for (vflre <<= 64 - i; vflre && i--; vflre += vflre) { + struct fm10k_vf_info *vf_info = &iov_data->vf_info[i]; - if (vflre >= 0) - continue; + if (vflre >= 0) + continue; - hw->iov.ops.reset_resources(hw, vf_info); - vf_info->mbx.ops.connect(hw, &vf_info->mbx); - } - } while (i != iov_data->num_vfs); + hw->iov.ops.reset_resources(hw, vf_info); + vf_info->mbx.ops.connect(hw, &vf_info->mbx); + } read_unlock: rcu_read_unlock(); @@ -126,9 +245,14 @@ process_mbx: struct fm10k_mbx_info *mbx = &vf_info->mbx; u16 glort = vf_info->glort; + /* process the SM mailbox first to drain outgoing messages */ + hw->mbx.ops.process(hw, &hw->mbx); + /* verify port mapping is valid, if not reset port */ - if (vf_info->vf_flags && !fm10k_glort_valid_pf(hw, glort)) + if (vf_info->vf_flags && !fm10k_glort_valid_pf(hw, glort)) { hw->iov.ops.reset_lport(hw, vf_info); + fm10k_clear_macvlan_queue(interface, glort, false); + } /* reset VFs that have mailbox timed out */ if (!mbx->timeout) { @@ -140,6 +264,10 @@ process_mbx: if (!hw->mbx.ops.tx_ready(&hw->mbx, FM10K_VFMBX_MSG_MTU)) { /* keep track of how many times this occurs */ interface->hw_sm_mbx_full++; + + /* make sure we try again momentarily */ + fm10k_service_event_schedule(interface); + break; } @@ -187,6 +315,7 @@ void fm10k_iov_suspend(struct pci_dev *pdev) hw->iov.ops.reset_resources(hw, vf_info); hw->iov.ops.reset_lport(hw, vf_info); + fm10k_clear_macvlan_queue(interface, vf_info->glort, false); } } @@ -411,6 +540,8 @@ static inline void fm10k_reset_vf_info(struct fm10k_intfc *interface, /* disable LPORT for this VF which clears switch rules */ hw->iov.ops.reset_lport(hw, vf_info); + fm10k_clear_macvlan_queue(interface, vf_info->glort, false); + /* assign new MAC+VLAN for this VF */ hw->iov.ops.assign_default_mac_vlan(hw, vf_info); @@ -482,7 +613,7 @@ int fm10k_ndo_set_vf_vlan(struct net_device *netdev, int vf_idx, u16 vid, } int fm10k_ndo_set_vf_bw(struct net_device *netdev, int vf_idx, - int __always_unused unused, int rate) + int __always_unused min_rate, int max_rate) { struct fm10k_intfc *interface = netdev_priv(netdev); struct fm10k_iov_data *iov_data = interface->iov_data; @@ -493,14 +624,15 @@ int fm10k_ndo_set_vf_bw(struct net_device *netdev, int vf_idx, return -EINVAL; /* rate limit cannot be less than 10Mbs or greater than link speed */ - if (rate && ((rate < FM10K_VF_TC_MIN) || rate > FM10K_VF_TC_MAX)) + if (max_rate && + (max_rate < FM10K_VF_TC_MIN || max_rate > FM10K_VF_TC_MAX)) return -EINVAL; /* store values */ - iov_data->vf_info[vf_idx].rate = rate; + iov_data->vf_info[vf_idx].rate = max_rate; /* update hardware configuration */ - hw->iov.ops.configure_tc(hw, vf_idx, rate); + hw->iov.ops.configure_tc(hw, vf_idx, max_rate); return 0; } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 9dffaba85ae6..dbd69310f263 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -28,7 +28,7 @@ #include "fm10k.h" -#define DRV_VERSION "0.21.7-k" +#define DRV_VERSION "0.22.1-k" #define DRV_SUMMARY "Intel(R) Ethernet Switch Host Interface Driver" const char fm10k_driver_version[] = DRV_VERSION; char fm10k_driver_name[] = "fm10k"; @@ -806,9 +806,10 @@ static int fm10k_tso(struct fm10k_ring *tx_ring, tx_desc->mss = cpu_to_le16(skb_shinfo(skb)->gso_size); return 1; + err_vxlan: tx_ring->netdev->features &= ~NETIF_F_GSO_UDP_TUNNEL; - if (!net_ratelimit()) + if (net_ratelimit()) netdev_err(tx_ring->netdev, "TSO requested for unsupported tunnel, disabling offload\n"); return -1; @@ -876,6 +877,7 @@ static void fm10k_tx_csum(struct fm10k_ring *tx_ring, case IPPROTO_GRE: if (skb->encapsulation) break; + /* fall through */ default: if (unlikely(net_ratelimit())) { dev_warn(tx_ring->dev, diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c index 334088a101c3..244d3ad58ca7 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. + * Copyright(c) 2013 - 2017 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -1586,7 +1586,7 @@ s32 fm10k_pfvf_mbx_init(struct fm10k_hw *hw, struct fm10k_mbx_info *mbx, mbx->mbmem_reg = FM10K_MBMEM_VF(id, 0); break; } - /* fallthough */ + /* fall through */ default: return FM10K_MBX_ERR_NO_MBX; } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index e69d49d91d67..adc62fb38c49 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -643,9 +643,13 @@ int fm10k_close(struct net_device *netdev) static netdev_tx_t fm10k_xmit_frame(struct sk_buff *skb, struct net_device *dev) { struct fm10k_intfc *interface = netdev_priv(dev); + int num_tx_queues = READ_ONCE(interface->num_tx_queues); unsigned int r_idx = skb->queue_mapping; int err; + if (!num_tx_queues) + return NETDEV_TX_BUSY; + if ((skb->protocol == htons(ETH_P_8021Q)) && !skb_vlan_tag_present(skb)) { /* FM10K only supports hardware tagging, any tags in frame @@ -698,8 +702,8 @@ static netdev_tx_t fm10k_xmit_frame(struct sk_buff *skb, struct net_device *dev) __skb_put(skb, pad_len); } - if (r_idx >= interface->num_tx_queues) - r_idx %= interface->num_tx_queues; + if (r_idx >= num_tx_queues) + r_idx %= num_tx_queues; err = fm10k_xmit_frame_ring(skb, interface->tx_ring[r_idx]); @@ -754,11 +758,132 @@ static bool fm10k_host_mbx_ready(struct fm10k_intfc *interface) return (hw->mac.type == fm10k_mac_vf || interface->host_ready); } +/** + * fm10k_queue_vlan_request - Queue a VLAN update request + * @interface: the fm10k interface structure + * @vid: the VLAN vid + * @vsi: VSI index number + * @set: whether to set or clear + * + * This function queues up a VLAN update. For VFs, this must be sent to the + * managing PF over the mailbox. For PFs, we'll use the same handling so that + * it's similar to the VF. This avoids storming the PF<->VF mailbox with too + * many VLAN updates during reset. + */ +int fm10k_queue_vlan_request(struct fm10k_intfc *interface, + u32 vid, u8 vsi, bool set) +{ + struct fm10k_macvlan_request *request; + unsigned long flags; + + /* This must be atomic since we may be called while the netdev + * addr_list_lock is held + */ + request = kzalloc(sizeof(*request), GFP_ATOMIC); + if (!request) + return -ENOMEM; + + request->type = FM10K_VLAN_REQUEST; + request->vlan.vid = vid; + request->vlan.vsi = vsi; + request->set = set; + + spin_lock_irqsave(&interface->macvlan_lock, flags); + list_add_tail(&request->list, &interface->macvlan_requests); + spin_unlock_irqrestore(&interface->macvlan_lock, flags); + + fm10k_macvlan_schedule(interface); + + return 0; +} + +/** + * fm10k_queue_mac_request - Queue a MAC update request + * @interface: the fm10k interface structure + * @glort: the target glort for this update + * @addr: the address to update + * @vid: the vid to update + * @sync: whether to add or remove + * + * This function queues up a MAC request for sending to the switch manager. + * A separate thread monitors the queue and sends updates to the switch + * manager. Return 0 on success, and negative error code on failure. + **/ +int fm10k_queue_mac_request(struct fm10k_intfc *interface, u16 glort, + const unsigned char *addr, u16 vid, bool set) +{ + struct fm10k_macvlan_request *request; + unsigned long flags; + + /* This must be atomic since we may be called while the netdev + * addr_list_lock is held + */ + request = kzalloc(sizeof(*request), GFP_ATOMIC); + if (!request) + return -ENOMEM; + + if (is_multicast_ether_addr(addr)) + request->type = FM10K_MC_MAC_REQUEST; + else + request->type = FM10K_UC_MAC_REQUEST; + + ether_addr_copy(request->mac.addr, addr); + request->mac.glort = glort; + request->mac.vid = vid; + request->set = set; + + spin_lock_irqsave(&interface->macvlan_lock, flags); + list_add_tail(&request->list, &interface->macvlan_requests); + spin_unlock_irqrestore(&interface->macvlan_lock, flags); + + fm10k_macvlan_schedule(interface); + + return 0; +} + +/** + * fm10k_clear_macvlan_queue - Cancel pending updates for a given glort + * @interface: the fm10k interface structure + * @glort: the target glort to clear + * @vlans: true to clear VLAN messages, false to ignore them + * + * Cancel any outstanding MAC/VLAN requests for a given glort. This is + * expected to be called when a logical port goes down. + **/ +void fm10k_clear_macvlan_queue(struct fm10k_intfc *interface, + u16 glort, bool vlans) + +{ + struct fm10k_macvlan_request *r, *tmp; + unsigned long flags; + + spin_lock_irqsave(&interface->macvlan_lock, flags); + + /* Free any outstanding MAC/VLAN requests for this interface */ + list_for_each_entry_safe(r, tmp, &interface->macvlan_requests, list) { + switch (r->type) { + case FM10K_MC_MAC_REQUEST: + case FM10K_UC_MAC_REQUEST: + /* Don't free requests for other interfaces */ + if (r->mac.glort != glort) + break; + /* fall through */ + case FM10K_VLAN_REQUEST: + if (vlans) { + list_del(&r->list); + kfree(r); + } + break; + } + } + + spin_unlock_irqrestore(&interface->macvlan_lock, flags); +} + static int fm10k_uc_vlan_unsync(struct net_device *netdev, const unsigned char *uc_addr) { struct fm10k_intfc *interface = netdev_priv(netdev); - struct fm10k_hw *hw = &interface->hw; u16 glort = interface->glort; u16 vid = interface->vid; bool set = !!(vid / VLAN_N_VID); @@ -767,10 +892,7 @@ static int fm10k_uc_vlan_unsync(struct net_device *netdev, /* drop any leading bits on the VLAN ID */ vid &= VLAN_N_VID - 1; - if (fm10k_host_mbx_ready(interface)) - err = hw->mac.ops.update_uc_addr(hw, glort, uc_addr, - vid, set, 0); - + err = fm10k_queue_mac_request(interface, glort, uc_addr, vid, set); if (err) return err; @@ -782,7 +904,6 @@ static int fm10k_mc_vlan_unsync(struct net_device *netdev, const unsigned char *mc_addr) { struct fm10k_intfc *interface = netdev_priv(netdev); - struct fm10k_hw *hw = &interface->hw; u16 glort = interface->glort; u16 vid = interface->vid; bool set = !!(vid / VLAN_N_VID); @@ -791,9 +912,7 @@ static int fm10k_mc_vlan_unsync(struct net_device *netdev, /* drop any leading bits on the VLAN ID */ vid &= VLAN_N_VID - 1; - if (fm10k_host_mbx_ready(interface)) - err = hw->mac.ops.update_mc_addr(hw, glort, mc_addr, vid, set); - + err = fm10k_queue_mac_request(interface, glort, mc_addr, vid, set); if (err) return err; @@ -851,18 +970,14 @@ static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set) /* only need to update the VLAN if not in promiscuous mode */ if (!(netdev->flags & IFF_PROMISC)) { - err = hw->mac.ops.update_vlan(hw, vid, 0, set); + err = fm10k_queue_vlan_request(interface, vid, 0, set); if (err) goto err_out; } - /* update our base MAC address if host's mailbox is ready */ - if (fm10k_host_mbx_ready(interface)) - err = hw->mac.ops.update_uc_addr(hw, interface->glort, - hw->mac.addr, vid, set, 0); - else - err = -EHOSTDOWN; - + /* Update our base MAC address */ + err = fm10k_queue_mac_request(interface, interface->glort, + hw->mac.addr, vid, set); if (err) goto err_out; @@ -906,7 +1021,6 @@ static u16 fm10k_find_next_vlan(struct fm10k_intfc *interface, u16 vid) static void fm10k_clear_unused_vlans(struct fm10k_intfc *interface) { - struct fm10k_hw *hw = &interface->hw; u32 vid, prev_vid; /* loop through and find any gaps in the table */ @@ -918,7 +1032,7 @@ static void fm10k_clear_unused_vlans(struct fm10k_intfc *interface) /* send request to clear multiple bits at a time */ prev_vid += (vid - prev_vid - 1) << FM10K_VLAN_LENGTH_SHIFT; - hw->mac.ops.update_vlan(hw, prev_vid, 0, false); + fm10k_queue_vlan_request(interface, prev_vid, 0, false); } } @@ -933,15 +1047,11 @@ static int __fm10k_uc_sync(struct net_device *dev, if (!is_valid_ether_addr(addr)) return -EADDRNOTAVAIL; - /* update table with current entries if host's mailbox is ready */ - if (!fm10k_host_mbx_ready(interface)) - return -EHOSTDOWN; - for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 1; vid < VLAN_N_VID; vid = fm10k_find_next_vlan(interface, vid)) { - err = hw->mac.ops.update_uc_addr(hw, glort, addr, - vid, sync, 0); + err = fm10k_queue_mac_request(interface, glort, + addr, vid, sync); if (err) return err; } @@ -998,15 +1108,18 @@ static int __fm10k_mc_sync(struct net_device *dev, struct fm10k_intfc *interface = netdev_priv(dev); struct fm10k_hw *hw = &interface->hw; u16 vid, glort = interface->glort; + s32 err; - /* update table with current entries if host's mailbox is ready */ - if (!fm10k_host_mbx_ready(interface)) - return 0; + if (!is_multicast_ether_addr(addr)) + return -EADDRNOTAVAIL; for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 1; vid < VLAN_N_VID; vid = fm10k_find_next_vlan(interface, vid)) { - hw->mac.ops.update_mc_addr(hw, glort, addr, vid, sync); + err = fm10k_queue_mac_request(interface, glort, + addr, vid, sync); + if (err) + return err; } return 0; @@ -1046,7 +1159,8 @@ static void fm10k_set_rx_mode(struct net_device *dev) if (interface->xcast_mode != xcast_mode) { /* update VLAN table */ if (xcast_mode == FM10K_XCAST_MODE_PROMISC) - hw->mac.ops.update_vlan(hw, FM10K_VLAN_ALL, 0, true); + fm10k_queue_vlan_request(interface, FM10K_VLAN_ALL, + 0, true); if (interface->xcast_mode == FM10K_XCAST_MODE_PROMISC) fm10k_clear_unused_vlans(interface); @@ -1094,22 +1208,20 @@ void fm10k_restore_rx_state(struct fm10k_intfc *interface) interface->glort_count, true); /* update VLAN table */ - hw->mac.ops.update_vlan(hw, FM10K_VLAN_ALL, 0, - xcast_mode == FM10K_XCAST_MODE_PROMISC); + fm10k_queue_vlan_request(interface, FM10K_VLAN_ALL, 0, + xcast_mode == FM10K_XCAST_MODE_PROMISC); /* Add filter for VLAN 0 */ - hw->mac.ops.update_vlan(hw, 0, 0, true); + fm10k_queue_vlan_request(interface, 0, 0, true); /* update table with current entries */ for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 1; vid < VLAN_N_VID; vid = fm10k_find_next_vlan(interface, vid)) { - hw->mac.ops.update_vlan(hw, vid, 0, true); + fm10k_queue_vlan_request(interface, vid, 0, true); - /* Update unicast entries if host's mailbox is ready */ - if (fm10k_host_mbx_ready(interface)) - hw->mac.ops.update_uc_addr(hw, glort, hw->mac.addr, - vid, true, 0); + fm10k_queue_mac_request(interface, glort, + hw->mac.addr, vid, true); } /* update xcast mode before synchronizing addresses if host's mailbox @@ -1136,6 +1248,13 @@ void fm10k_reset_rx_state(struct fm10k_intfc *interface) struct net_device *netdev = interface->netdev; struct fm10k_hw *hw = &interface->hw; + /* Wait for MAC/VLAN work to finish */ + while (test_bit(__FM10K_MACVLAN_SCHED, interface->state)) + usleep_range(1000, 2000); + + /* Cancel pending MAC/VLAN requests */ + fm10k_clear_macvlan_queue(interface, interface->glort, true); + fm10k_mbx_lock(interface); /* clear the logical port state on lower device if host's mailbox is @@ -1270,7 +1389,7 @@ static int __fm10k_setup_tc(struct net_device *dev, enum tc_setup_type type, { struct tc_mqprio_qopt *mqprio = type_data; - if (type != TC_SETUP_MQPRIO) + if (type != TC_SETUP_QDISC_MQPRIO) return -EOPNOTSUPP; mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; @@ -1370,8 +1489,8 @@ static void *fm10k_dfwd_add_station(struct net_device *dev, if (fm10k_host_mbx_ready(interface)) { hw->mac.ops.update_xcast_mode(hw, glort, FM10K_XCAST_MODE_MULTI); - hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr, - 0, true, 0); + fm10k_queue_mac_request(interface, glort, sdev->dev_addr, + 0, true); } fm10k_mbx_unlock(interface); @@ -1410,8 +1529,8 @@ static void fm10k_dfwd_del_station(struct net_device *dev, void *priv) if (fm10k_host_mbx_ready(interface)) { hw->mac.ops.update_xcast_mode(hw, glort, FM10K_XCAST_MODE_NONE); - hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr, - 0, false, 0); + fm10k_queue_mac_request(interface, glort, sdev->dev_addr, + 0, false); } fm10k_mbx_unlock(interface); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 63784576ae8b..7f605221a686 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -91,6 +91,76 @@ static int fm10k_hw_ready(struct fm10k_intfc *interface) return FM10K_REMOVED(hw->hw_addr) ? -ENODEV : 0; } +/** + * fm10k_macvlan_schedule - Schedule MAC/VLAN queue task + * @interface: fm10k private interface structure + * + * Schedule the MAC/VLAN queue monitor task. If the MAC/VLAN task cannot be + * started immediately, request that it be restarted when possible. + */ +void fm10k_macvlan_schedule(struct fm10k_intfc *interface) +{ + /* Avoid processing the MAC/VLAN queue when the service task is + * disabled, or when we're resetting the device. + */ + if (!test_bit(__FM10K_MACVLAN_DISABLE, interface->state) && + !test_and_set_bit(__FM10K_MACVLAN_SCHED, interface->state)) { + clear_bit(__FM10K_MACVLAN_REQUEST, interface->state); + /* We delay the actual start of execution in order to allow + * multiple MAC/VLAN updates to accumulate before handling + * them, and to allow some time to let the mailbox drain + * between runs. + */ + queue_delayed_work(fm10k_workqueue, + &interface->macvlan_task, 10); + } else { + set_bit(__FM10K_MACVLAN_REQUEST, interface->state); + } +} + +/** + * fm10k_stop_macvlan_task - Stop the MAC/VLAN queue monitor + * @interface: fm10k private interface structure + * + * Wait until the MAC/VLAN queue task has stopped, and cancel any future + * requests. + */ +static void fm10k_stop_macvlan_task(struct fm10k_intfc *interface) +{ + /* Disable the MAC/VLAN work item */ + set_bit(__FM10K_MACVLAN_DISABLE, interface->state); + + /* Make sure we waited until any current invocations have stopped */ + cancel_delayed_work_sync(&interface->macvlan_task); + + /* We set the __FM10K_MACVLAN_SCHED bit when we schedule the task. + * However, it may not be unset of the MAC/VLAN task never actually + * got a chance to run. Since we've canceled the task here, and it + * cannot be rescheuled right now, we need to ensure the scheduled bit + * gets unset. + */ + clear_bit(__FM10K_MACVLAN_SCHED, interface->state); +} + +/** + * fm10k_resume_macvlan_task - Restart the MAC/VLAN queue monitor + * @interface: fm10k private interface structure + * + * Clear the __FM10K_MACVLAN_DISABLE bit and, if a request occurred, schedule + * the MAC/VLAN work monitor. + */ +static void fm10k_resume_macvlan_task(struct fm10k_intfc *interface) +{ + /* Re-enable the MAC/VLAN work item */ + clear_bit(__FM10K_MACVLAN_DISABLE, interface->state); + + /* We might have received a MAC/VLAN request while disabled. If so, + * kick off the queue now. + */ + if (test_bit(__FM10K_MACVLAN_REQUEST, interface->state)) + fm10k_macvlan_schedule(interface); +} + void fm10k_service_event_schedule(struct fm10k_intfc *interface) { if (!test_bit(__FM10K_SERVICE_DISABLE, interface->state) && @@ -118,13 +188,35 @@ static void fm10k_service_event_complete(struct fm10k_intfc *interface) fm10k_service_event_schedule(interface); } +static void fm10k_stop_service_event(struct fm10k_intfc *interface) +{ + set_bit(__FM10K_SERVICE_DISABLE, interface->state); + cancel_work_sync(&interface->service_task); + + /* It's possible that cancel_work_sync stopped the service task from + * running before it could actually start. In this case the + * __FM10K_SERVICE_SCHED bit will never be cleared. Since we know that + * the service task cannot be running at this point, we need to clear + * the scheduled bit, as otherwise the service task may never be + * restarted. + */ + clear_bit(__FM10K_SERVICE_SCHED, interface->state); +} + +static void fm10k_start_service_event(struct fm10k_intfc *interface) +{ + clear_bit(__FM10K_SERVICE_DISABLE, interface->state); + fm10k_service_event_schedule(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); @@ -132,36 +224,15 @@ static void fm10k_service_timer(unsigned long data) fm10k_service_event_schedule(interface); } -static void fm10k_detach_subtask(struct fm10k_intfc *interface) -{ - struct net_device *netdev = interface->netdev; - u32 __iomem *hw_addr; - u32 value; - - /* do nothing if device is still present or hw_addr is set */ - if (netif_device_present(netdev) || interface->hw.hw_addr) - return; - - /* check the real address space to see if we've recovered */ - hw_addr = READ_ONCE(interface->uc_addr); - value = readl(hw_addr); - if (~value) { - interface->hw.hw_addr = interface->uc_addr; - netif_device_attach(netdev); - set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); - netdev_warn(netdev, "PCIe link restored, device now attached\n"); - return; - } - - rtnl_lock(); - - if (netif_running(netdev)) - dev_close(netdev); - - rtnl_unlock(); -} - -static void fm10k_prepare_for_reset(struct fm10k_intfc *interface) +/** + * fm10k_prepare_for_reset - Prepare the driver and device for a pending reset + * @interface: fm10k private data structure + * + * This function prepares for a device reset by shutting as much down as we + * can. It does nothing and returns false if __FM10K_RESETTING was already set + * prior to calling this function. It returns true if it actually did work. + */ +static bool fm10k_prepare_for_reset(struct fm10k_intfc *interface) { struct net_device *netdev = interface->netdev; @@ -170,8 +241,15 @@ static void fm10k_prepare_for_reset(struct fm10k_intfc *interface) /* put off any impending NetWatchDogTimeout */ netif_trans_update(netdev); - while (test_and_set_bit(__FM10K_RESETTING, interface->state)) - usleep_range(1000, 2000); + /* Nothing to do if a reset is already in progress */ + if (test_and_set_bit(__FM10K_RESETTING, interface->state)) + return false; + + /* As the MAC/VLAN task will be accessing registers it must not be + * running while we reset. Although the task will not be scheduled + * once we start resetting it may already be running + */ + fm10k_stop_macvlan_task(interface); rtnl_lock(); @@ -189,6 +267,8 @@ static void fm10k_prepare_for_reset(struct fm10k_intfc *interface) interface->last_reset = jiffies + (10 * HZ); rtnl_unlock(); + + return true; } static int fm10k_handle_reset(struct fm10k_intfc *interface) @@ -197,6 +277,8 @@ static int fm10k_handle_reset(struct fm10k_intfc *interface) struct fm10k_hw *hw = &interface->hw; int err; + WARN_ON(!test_bit(__FM10K_RESETTING, interface->state)); + rtnl_lock(); pci_set_master(interface->pdev); @@ -253,6 +335,8 @@ static int fm10k_handle_reset(struct fm10k_intfc *interface) rtnl_unlock(); + fm10k_resume_macvlan_task(interface); + clear_bit(__FM10K_RESETTING, interface->state); return err; @@ -270,27 +354,80 @@ reinit_err: return err; } -static void fm10k_reinit(struct fm10k_intfc *interface) +static void fm10k_detach_subtask(struct fm10k_intfc *interface) { + struct net_device *netdev = interface->netdev; + u32 __iomem *hw_addr; + u32 value; int err; - fm10k_prepare_for_reset(interface); + /* do nothing if netdev is still present or hw_addr is set */ + if (netif_device_present(netdev) || interface->hw.hw_addr) + return; - err = fm10k_handle_reset(interface); - if (err) - dev_err(&interface->pdev->dev, - "fm10k_handle_reset failed: %d\n", err); + /* We've lost the PCIe register space, and can no longer access the + * device. Shut everything except the detach subtask down and prepare + * to reset the device in case we recover. If we actually prepare for + * reset, indicate that we're detached. + */ + if (fm10k_prepare_for_reset(interface)) + set_bit(__FM10K_RESET_DETACHED, interface->state); + + /* check the real address space to see if we've recovered */ + hw_addr = READ_ONCE(interface->uc_addr); + value = readl(hw_addr); + if (~value) { + /* Make sure the reset was initiated because we detached, + * otherwise we might race with a different reset flow. + */ + if (!test_and_clear_bit(__FM10K_RESET_DETACHED, + interface->state)) + return; + + /* Restore the hardware address */ + interface->hw.hw_addr = interface->uc_addr; + + /* PCIe link has been restored, and the device is active + * again. Restore everything and reset the device. + */ + err = fm10k_handle_reset(interface); + if (err) { + netdev_err(netdev, "Unable to reset device: %d\n", err); + interface->hw.hw_addr = NULL; + return; + } + + /* Re-attach the netdev */ + netif_device_attach(netdev); + netdev_warn(netdev, "PCIe link restored, device now attached\n"); + return; + } } static void fm10k_reset_subtask(struct fm10k_intfc *interface) { + int err; + if (!test_and_clear_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags)) return; + /* If another thread has already prepared to reset the device, we + * should not attempt to handle a reset here, since we'd race with + * that thread. This may happen if we suspend the device or if the + * PCIe link is lost. In this case, we'll just ignore the RESET + * request, as it will (eventually) be taken care of when the thread + * which actually started the reset is finished. + */ + if (!fm10k_prepare_for_reset(interface)) + return; + netdev_err(interface->netdev, "Reset interface\n"); - fm10k_reinit(interface); + err = fm10k_handle_reset(interface); + if (err) + dev_err(&interface->pdev->dev, + "fm10k_handle_reset failed: %d\n", err); } /** @@ -360,6 +497,10 @@ static void fm10k_watchdog_update_host_state(struct fm10k_intfc *interface) **/ static void fm10k_mbx_subtask(struct fm10k_intfc *interface) { + /* If we're resetting, bail out */ + if (test_bit(__FM10K_RESETTING, interface->state)) + return; + /* process upstream mailbox and update device state */ fm10k_watchdog_update_host_state(interface); @@ -609,9 +750,11 @@ static void fm10k_service_task(struct work_struct *work) interface = container_of(work, struct fm10k_intfc, service_task); + /* Check whether we're detached first */ + fm10k_detach_subtask(interface); + /* tasks run even when interface is down */ fm10k_mbx_subtask(interface); - fm10k_detach_subtask(interface); fm10k_reset_subtask(interface); /* tasks only run when interface is up */ @@ -623,6 +766,112 @@ static void fm10k_service_task(struct work_struct *work) } /** + * fm10k_macvlan_task - send queued MAC/VLAN requests to switch manager + * @work: pointer to work_struct containing our data + * + * This work item handles sending MAC/VLAN updates to the switch manager. When + * the interface is up, it will attempt to queue mailbox messages to the + * switch manager requesting updates for MAC/VLAN pairs. If the Tx fifo of the + * mailbox is full, it will reschedule itself to try again in a short while. + * This ensures that the driver does not overload the switch mailbox with too + * many simultaneous requests, causing an unnecessary reset. + **/ +static void fm10k_macvlan_task(struct work_struct *work) +{ + struct fm10k_macvlan_request *item; + struct fm10k_intfc *interface; + struct delayed_work *dwork; + struct list_head *requests; + struct fm10k_hw *hw; + unsigned long flags; + + dwork = to_delayed_work(work); + interface = container_of(dwork, struct fm10k_intfc, macvlan_task); + hw = &interface->hw; + requests = &interface->macvlan_requests; + + do { + /* Pop the first item off the list */ + spin_lock_irqsave(&interface->macvlan_lock, flags); + item = list_first_entry_or_null(requests, + struct fm10k_macvlan_request, + list); + if (item) + list_del_init(&item->list); + + spin_unlock_irqrestore(&interface->macvlan_lock, flags); + + /* We have no more items to process */ + if (!item) + goto done; + + fm10k_mbx_lock(interface); + + /* Check that we have plenty of space to send the message. We + * want to ensure that the mailbox stays low enough to avoid a + * change in the host state, otherwise we may see spurious + * link up / link down notifications. + */ + if (!hw->mbx.ops.tx_ready(&hw->mbx, FM10K_VFMBX_MSG_MTU + 5)) { + hw->mbx.ops.process(hw, &hw->mbx); + set_bit(__FM10K_MACVLAN_REQUEST, interface->state); + fm10k_mbx_unlock(interface); + + /* Put the request back on the list */ + spin_lock_irqsave(&interface->macvlan_lock, flags); + list_add(&item->list, requests); + spin_unlock_irqrestore(&interface->macvlan_lock, flags); + break; + } + + switch (item->type) { + case FM10K_MC_MAC_REQUEST: + hw->mac.ops.update_mc_addr(hw, + item->mac.glort, + item->mac.addr, + item->mac.vid, + item->set); + break; + case FM10K_UC_MAC_REQUEST: + hw->mac.ops.update_uc_addr(hw, + item->mac.glort, + item->mac.addr, + item->mac.vid, + item->set, + 0); + break; + case FM10K_VLAN_REQUEST: + hw->mac.ops.update_vlan(hw, + item->vlan.vid, + item->vlan.vsi, + item->set); + break; + default: + break; + } + + fm10k_mbx_unlock(interface); + + /* Free the item now that we've sent the update */ + kfree(item); + } while (true); + +done: + WARN_ON(!test_bit(__FM10K_MACVLAN_SCHED, interface->state)); + + /* flush memory to make sure state is correct */ + smp_mb__before_atomic(); + clear_bit(__FM10K_MACVLAN_SCHED, interface->state); + + /* If a MAC/VLAN request was scheduled since we started, we should + * re-schedule. However, there is no reason to re-schedule if there is + * no work to do. + */ + if (test_bit(__FM10K_MACVLAN_REQUEST, interface->state)) + fm10k_macvlan_schedule(interface); +} + +/** * fm10k_configure_tx_ring - Configure Tx ring after Reset * @interface: board private structure * @ring: structure containing ring specific data @@ -1544,7 +1793,7 @@ int fm10k_qv_request_irq(struct fm10k_intfc *interface) struct net_device *dev = interface->netdev; struct fm10k_hw *hw = &interface->hw; struct msix_entry *entry; - int ri = 0, ti = 0; + unsigned int ri = 0, ti = 0; int vector, err; entry = &interface->msix_entries[NON_Q_VECTORS(hw)]; @@ -1554,15 +1803,15 @@ int fm10k_qv_request_irq(struct fm10k_intfc *interface) /* name the vector */ if (q_vector->tx.count && q_vector->rx.count) { - snprintf(q_vector->name, sizeof(q_vector->name) - 1, - "%s-TxRx-%d", dev->name, ri++); + snprintf(q_vector->name, sizeof(q_vector->name), + "%s-TxRx-%u", dev->name, ri++); ti++; } else if (q_vector->rx.count) { - snprintf(q_vector->name, sizeof(q_vector->name) - 1, - "%s-rx-%d", dev->name, ri++); + snprintf(q_vector->name, sizeof(q_vector->name), + "%s-rx-%u", dev->name, ri++); } else if (q_vector->tx.count) { - snprintf(q_vector->name, sizeof(q_vector->name) - 1, - "%s-tx-%d", dev->name, ti++); + snprintf(q_vector->name, sizeof(q_vector->name), + "%s-tx-%u", dev->name, ti++); } else { /* skip this unused q_vector */ continue; @@ -1800,9 +2049,6 @@ static int fm10k_sw_init(struct fm10k_intfc *interface, netdev->vlan_features |= NETIF_F_HIGHDMA; } - /* delay any future reset requests */ - interface->last_reset = jiffies + (10 * HZ); - /* reset and initialize the hardware so it is in a known state */ err = hw->mac.ops.reset_hw(hw); if (err) { @@ -1857,9 +2103,16 @@ static int fm10k_sw_init(struct fm10k_intfc *interface, INIT_LIST_HEAD(&interface->vxlan_port); INIT_LIST_HEAD(&interface->geneve_port); + /* Initialize the MAC/VLAN queue */ + INIT_LIST_HEAD(&interface->macvlan_requests); + netdev_rss_key_fill(rss_key, sizeof(rss_key)); memcpy(interface->rssrk, rss_key, sizeof(rss_key)); + /* Initialize the mailbox lock */ + spin_lock_init(&interface->mbx_lock); + spin_lock_init(&interface->macvlan_lock); + /* Start off interface as being down */ set_bit(__FM10K_DOWN, interface->state); set_bit(__FM10K_UPDATING_STATS, interface->state); @@ -2063,10 +2316,12 @@ 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 */ + INIT_DELAYED_WORK(&interface->macvlan_task, fm10k_macvlan_task); + /* kick off service timer now, even when interface is down */ mod_timer(&interface->service_timer, (HZ * 2) + jiffies); @@ -2079,8 +2334,9 @@ static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* enable SR-IOV after registering netdev to enforce PF/VF ordering */ fm10k_iov_configure(pdev, 0); - /* clear the service task disable bit to allow service task to start */ + /* clear the service task disable bit and kick off service task */ clear_bit(__FM10K_SERVICE_DISABLE, interface->state); + fm10k_service_event_schedule(interface); return 0; @@ -2118,8 +2374,11 @@ static void fm10k_remove(struct pci_dev *pdev) del_timer_sync(&interface->service_timer); - set_bit(__FM10K_SERVICE_DISABLE, interface->state); - cancel_work_sync(&interface->service_task); + fm10k_stop_service_event(interface); + fm10k_stop_macvlan_task(interface); + + /* Remove all pending MAC/VLAN requests */ + fm10k_clear_macvlan_queue(interface, interface->glort, true); /* free netdev, this may bounce the interrupts due to setup_tc */ if (netdev->reg_state == NETREG_REGISTERED) @@ -2156,11 +2415,14 @@ static void fm10k_prepare_suspend(struct fm10k_intfc *interface) * a surprise remove if the PCIe device is disabled while we're * stopped. We stop the watchdog task until after we resume software * activity. + * + * Note that the MAC/VLAN task will be stopped as part of preparing + * for reset so we don't need to handle it here. */ - set_bit(__FM10K_SERVICE_DISABLE, interface->state); - cancel_work_sync(&interface->service_task); + fm10k_stop_service_event(interface); - fm10k_prepare_for_reset(interface); + if (fm10k_prepare_for_reset(interface)) + set_bit(__FM10K_RESET_SUSPENDED, interface->state); } static int fm10k_handle_resume(struct fm10k_intfc *interface) @@ -2168,6 +2430,13 @@ static int fm10k_handle_resume(struct fm10k_intfc *interface) struct fm10k_hw *hw = &interface->hw; int err; + /* Even if we didn't properly prepare for reset in + * fm10k_prepare_suspend, we'll attempt to resume anyways. + */ + if (!test_and_clear_bit(__FM10K_RESET_SUSPENDED, interface->state)) + dev_warn(&interface->pdev->dev, + "Device was shut down as part of suspend... Attempting to recover\n"); + /* reset statistics starting values */ hw->mac.ops.rebind_hw_stats(hw, &interface->stats); @@ -2185,45 +2454,30 @@ static int fm10k_handle_resume(struct fm10k_intfc *interface) interface->link_down_event = jiffies + (HZ); set_bit(__FM10K_LINK_DOWN, interface->state); - /* clear the service task disable bit to allow service task to start */ - clear_bit(__FM10K_SERVICE_DISABLE, interface->state); - fm10k_service_event_schedule(interface); + /* restart the service task */ + fm10k_start_service_event(interface); + + /* Restart the MAC/VLAN request queue in-case of outstanding events */ + fm10k_macvlan_schedule(interface); return err; } #ifdef CONFIG_PM /** - * fm10k_resume - Restore device to pre-sleep state - * @pdev: PCI device information struct + * fm10k_resume - Generic PM resume hook + * @dev: generic device structure * - * fm10k_resume is called after the system has powered back up from a sleep - * state and is ready to resume operation. This function is meant to restore - * the device back to its pre-sleep state. + * Generic PM hook used when waking the device from a low power state after + * suspend or hibernation. This function does not need to handle lower PCIe + * device state as the stack takes care of that for us. **/ -static int fm10k_resume(struct pci_dev *pdev) +static int fm10k_resume(struct device *dev) { - struct fm10k_intfc *interface = pci_get_drvdata(pdev); + struct fm10k_intfc *interface = pci_get_drvdata(to_pci_dev(dev)); struct net_device *netdev = interface->netdev; struct fm10k_hw *hw = &interface->hw; - u32 err; - - pci_set_power_state(pdev, PCI_D0); - pci_restore_state(pdev); - - /* pci_restore_state clears dev->state_saved so call - * pci_save_state to restore it. - */ - pci_save_state(pdev); - - err = pci_enable_device_mem(pdev); - if (err) { - dev_err(&pdev->dev, "Cannot enable PCI device from suspend\n"); - return err; - } - pci_set_master(pdev); - - pci_wake_from_d3(pdev, false); + int err; /* refresh hw_addr in case it was dropped */ hw->hw_addr = interface->uc_addr; @@ -2238,36 +2492,27 @@ static int fm10k_resume(struct pci_dev *pdev) } /** - * fm10k_suspend - Prepare the device for a system sleep state - * @pdev: PCI device information struct + * fm10k_suspend - Generic PM suspend hook + * @dev: generic device structure * - * fm10k_suspend is meant to shutdown the device prior to the system entering - * a sleep state. The fm10k hardware does not support wake on lan so the - * driver simply needs to shut down the device so it is in a low power state. + * Generic PM hook used when setting the device into a low power state for + * system suspend or hibernation. This function does not need to handle lower + * PCIe device state as the stack takes care of that for us. **/ -static int fm10k_suspend(struct pci_dev *pdev, - pm_message_t __always_unused state) +static int fm10k_suspend(struct device *dev) { - struct fm10k_intfc *interface = pci_get_drvdata(pdev); + struct fm10k_intfc *interface = pci_get_drvdata(to_pci_dev(dev)); struct net_device *netdev = interface->netdev; - int err = 0; netif_device_detach(netdev); fm10k_prepare_suspend(interface); - err = pci_save_state(pdev); - if (err) - return err; - - pci_disable_device(pdev); - pci_wake_from_d3(pdev, false); - pci_set_power_state(pdev, PCI_D3hot); - return 0; } #endif /* CONFIG_PM */ + /** * fm10k_io_error_detected - called when PCI error is detected * @pdev: Pointer to PCI device @@ -2343,11 +2588,18 @@ static void fm10k_io_resume(struct pci_dev *pdev) if (err) dev_warn(&pdev->dev, - "fm10k_io_resume failed: %d\n", err); + "%s failed: %d\n", __func__, err); else netif_device_attach(netdev); } +/** + * fm10k_io_reset_prepare - called when PCI function is about to be reset + * @pdev: Pointer to PCI device + * + * This callback is called when the PCI function is about to be reset, + * allowing the device driver to prepare for it. + */ static void fm10k_io_reset_prepare(struct pci_dev *pdev) { /* warn incase we have any active VF devices */ @@ -2357,6 +2609,13 @@ static void fm10k_io_reset_prepare(struct pci_dev *pdev) fm10k_prepare_suspend(pci_get_drvdata(pdev)); } +/** + * fm10k_io_reset_done - called when PCI function has finished resetting + * @pdev: Pointer to PCI device + * + * This callback is called just after the PCI function is reset, such as via + * /sys/class/net/<enpX>/device/reset or similar. + */ static void fm10k_io_reset_done(struct pci_dev *pdev) { struct fm10k_intfc *interface = pci_get_drvdata(pdev); @@ -2364,7 +2623,7 @@ static void fm10k_io_reset_done(struct pci_dev *pdev) if (err) { dev_warn(&pdev->dev, - "fm10k_io_reset_notify failed: %d\n", err); + "%s failed: %d\n", __func__, err); netif_device_detach(interface->netdev); } } @@ -2377,15 +2636,18 @@ static const struct pci_error_handlers fm10k_err_handler = { .reset_done = fm10k_io_reset_done, }; +static SIMPLE_DEV_PM_OPS(fm10k_pm_ops, fm10k_suspend, fm10k_resume); + static struct pci_driver fm10k_driver = { .name = fm10k_driver_name, .id_table = fm10k_pci_tbl, .probe = fm10k_probe, .remove = fm10k_remove, #ifdef CONFIG_PM - .suspend = fm10k_suspend, - .resume = fm10k_resume, -#endif + .driver = { + .pm = &fm10k_pm_ops, + }, +#endif /* CONFIG_PM */ .sriov_configure = fm10k_iov_configure, .err_handler = &fm10k_err_handler }; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c index 40ee0242a80a..425d814aed4d 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. + * Copyright(c) 2013 - 2017 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -1186,7 +1186,7 @@ s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *hw, u32 **results, * Will report an error if the VLAN ID is out of range. For VID = 0, it will * return either the pf_vid or sw_vid depending on which one is set. */ -static s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid) +s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid) { if (!vid) return vf_info->pf_vid ? vf_info->pf_vid : vf_info->sw_vid; @@ -1334,19 +1334,19 @@ static u8 fm10k_iov_supported_xcast_mode_pf(struct fm10k_vf_info *vf_info, case FM10K_XCAST_MODE_PROMISC: if (vf_flags & FM10K_VF_FLAG_PROMISC_CAPABLE) return FM10K_XCAST_MODE_PROMISC; - /* fallthough */ + /* fall through */ case FM10K_XCAST_MODE_ALLMULTI: if (vf_flags & FM10K_VF_FLAG_ALLMULTI_CAPABLE) return FM10K_XCAST_MODE_ALLMULTI; - /* fallthough */ + /* fall through */ case FM10K_XCAST_MODE_MULTI: if (vf_flags & FM10K_VF_FLAG_MULTI_CAPABLE) return FM10K_XCAST_MODE_MULTI; - /* fallthough */ + /* fall through */ case FM10K_XCAST_MODE_NONE: if (vf_flags & FM10K_VF_FLAG_NONE_CAPABLE) return FM10K_XCAST_MODE_NONE; - /* fallthough */ + /* fall through */ default: break; } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.h b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h index 3336d3c10760..e04d41f1a532 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. + * Copyright(c) 2013 - 2017 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -114,6 +114,7 @@ extern const struct fm10k_tlv_attr fm10k_err_msg_attr[]; #define FM10K_PF_MSG_ERR_HANDLER(msg, func) \ FM10K_MSG_HANDLER(FM10K_PF_MSG_ID_##msg, fm10k_err_msg_attr, func) +s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid); s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *, u32 **, struct fm10k_mbx_info *); s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *, u32 **, struct fm10k_mbx_info *); diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index d0c1bf5441d8..5829715fa342 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -54,6 +54,9 @@ #include <linux/clocksource.h> #include <linux/net_tstamp.h> #include <linux/ptp_clock_kernel.h> +#include <net/pkt_cls.h> +#include <net/tc_act/tc_gact.h> +#include <net/tc_act/tc_mirred.h> #include "i40e_type.h" #include "i40e_prototype.h" #include "i40e_client.h" @@ -77,6 +80,7 @@ #define i40e_default_queues_per_vmdq(pf) \ (((pf)->hw_features & I40E_HW_RSS_AQ_CAPABLE) ? 4 : 1) #define I40E_DEFAULT_QUEUES_PER_VF 4 +#define I40E_MAX_VF_QUEUES 16 #define I40E_DEFAULT_QUEUES_PER_TC 1 /* should be a power of 2 */ #define i40e_pf_get_max_q_per_tc(pf) \ (((pf)->hw_features & I40E_HW_128_QP_RSS_CAPABLE) ? 128 : 64) @@ -86,6 +90,7 @@ #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 @@ -125,6 +130,11 @@ /* 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, @@ -136,6 +146,7 @@ enum i40e_state_t { __I40E_MDD_EVENT_PENDING, __I40E_VFLR_EVENT_PENDING, __I40E_RESET_RECOVERY_PENDING, + __I40E_MISC_IRQ_REQUESTED, __I40E_RESET_INTR_RECEIVED, __I40E_REINIT_REQUESTED, __I40E_PF_RESET_REQUESTED, @@ -155,6 +166,8 @@ 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, @@ -242,6 +255,58 @@ struct i40e_fdir_filter { u32 fd_id; }; +#define I40E_CLOUD_FIELD_OMAC 0x01 +#define I40E_CLOUD_FIELD_IMAC 0x02 +#define I40E_CLOUD_FIELD_IVLAN 0x04 +#define I40E_CLOUD_FIELD_TEN_ID 0x08 +#define I40E_CLOUD_FIELD_IIP 0x10 + +#define I40E_CLOUD_FILTER_FLAGS_OMAC I40E_CLOUD_FIELD_OMAC +#define I40E_CLOUD_FILTER_FLAGS_IMAC I40E_CLOUD_FIELD_IMAC +#define I40E_CLOUD_FILTER_FLAGS_IMAC_IVLAN (I40E_CLOUD_FIELD_IMAC | \ + I40E_CLOUD_FIELD_IVLAN) +#define I40E_CLOUD_FILTER_FLAGS_IMAC_TEN_ID (I40E_CLOUD_FIELD_IMAC | \ + I40E_CLOUD_FIELD_TEN_ID) +#define I40E_CLOUD_FILTER_FLAGS_OMAC_TEN_ID_IMAC (I40E_CLOUD_FIELD_OMAC | \ + I40E_CLOUD_FIELD_IMAC | \ + I40E_CLOUD_FIELD_TEN_ID) +#define I40E_CLOUD_FILTER_FLAGS_IMAC_IVLAN_TEN_ID (I40E_CLOUD_FIELD_IMAC | \ + I40E_CLOUD_FIELD_IVLAN | \ + I40E_CLOUD_FIELD_TEN_ID) +#define I40E_CLOUD_FILTER_FLAGS_IIP I40E_CLOUD_FIELD_IIP + +struct i40e_cloud_filter { + struct hlist_node cloud_node; + unsigned long cookie; + /* cloud filter input set follows */ + u8 dst_mac[ETH_ALEN]; + u8 src_mac[ETH_ALEN]; + __be16 vlan_id; + u16 seid; /* filter control */ + __be16 dst_port; + __be16 src_port; + u32 tenant_id; + union { + struct { + struct in_addr dst_ip; + struct in_addr src_ip; + } v4; + struct { + struct in6_addr dst_ip6; + struct in6_addr src_ip6; + } v6; + } ip; +#define dst_ipv6 ip.v6.dst_ip6.s6_addr32 +#define src_ipv6 ip.v6.src_ip6.s6_addr32 +#define dst_ipv4 ip.v4.dst_ip.s_addr +#define src_ipv4 ip.v4.src_ip.s_addr + u16 n_proto; /* Ethernet Protocol */ + u8 ip_proto; /* IPPROTO value */ + u8 flags; +#define I40E_CLOUD_TNL_TYPE_NONE 0xff + u8 tunnel_type; +}; + #define I40E_ETH_P_LLDP 0x88cc #define I40E_DCB_PRIO_TYPE_STRICT 0 @@ -336,6 +401,25 @@ 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; @@ -348,7 +432,7 @@ 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 */ @@ -390,6 +474,9 @@ struct i40e_pf { struct i40e_udp_port_config udp_ports[I40E_MAX_PF_UDP_OFFLOAD_PORTS]; u16 pending_udp_bitmap; + struct hlist_head cloud_filter_list; + u16 num_cloud_filters; + enum i40e_interrupt_policy int_policy; u16 rx_itr_default; u16 tx_itr_default; @@ -401,55 +488,60 @@ 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) +#define I40E_FLAG_FD_SB_INACTIVE BIT(30) +#define I40E_FLAG_FD_SB_TO_CLOUD_FILTER BIT(31) struct i40e_client_instance *cinst; bool stat_offsets_loaded; @@ -530,6 +622,10 @@ struct i40e_pf { u32 ioremap_len; u32 fd_inv; u16 phy_led_val; + + u16 override_q_count; + u16 last_sw_conf_flags; + u16 last_sw_conf_valid_flags; }; /** @@ -673,6 +769,7 @@ 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; @@ -694,6 +791,17 @@ 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; + u16 tc_seid_map[I40E_MAX_TRAFFIC_CLASS]; + void *priv; /* client driver data reference. */ /* VSI specific handlers */ @@ -945,9 +1053,6 @@ 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); @@ -956,7 +1061,7 @@ 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); @@ -1001,4 +1106,7 @@ 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.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index ba04988e0598..9dcb2a961197 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -607,6 +607,18 @@ i40e_status i40e_init_adminq(struct i40e_hw *hw) &oem_lo); hw->nvm.oem_ver = ((u32)oem_hi << 16) | oem_lo; + 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->flags |= I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE; + } + + /* The ability to RX (not drop) 802.1ad frames was added in API 1.7 */ + if (hw->aq.api_maj_ver > 1 || + (hw->aq.api_maj_ver == 1 && + hw->aq.api_min_ver >= 7)) + hw->flags |= I40E_HW_FLAG_802_1AD_CAPABLE; + if (hw->aq.api_maj_ver > I40E_FW_API_VERSION_MAJOR) { ret_code = I40E_ERR_FIRMWARE_API_VERSION; goto init_adminq_free_arq; diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 5d5f422cbae5..b0188b8f91ba 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -34,7 +34,15 @@ */ #define I40E_FW_API_VERSION_MAJOR 0x0001 -#define I40E_FW_API_VERSION_MINOR 0x0005 +#define I40E_FW_API_VERSION_MINOR_X722 0x0005 +#define I40E_FW_API_VERSION_MINOR_X710 0x0007 + +#define I40E_FW_MINOR_VERSION(_h) ((_h)->mac.type == I40E_MAC_XL710 ? \ + I40E_FW_API_VERSION_MINOR_X710 : \ + I40E_FW_API_VERSION_MINOR_X722) + +/* API version 1.7 implements additional link and PHY-specific APIs */ +#define I40E_MINOR_VER_GET_LINK_INFO_XL710 0x0007 struct i40e_aq_desc { __le16 flags; @@ -236,6 +244,8 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_set_phy_debug = 0x0622, i40e_aqc_opc_upload_ext_phy_fm = 0x0625, i40e_aqc_opc_run_phy_activity = 0x0626, + i40e_aqc_opc_set_phy_register = 0x0628, + i40e_aqc_opc_get_phy_register = 0x0629, /* NVM commands */ i40e_aqc_opc_nvm_read = 0x0701, @@ -765,7 +775,50 @@ struct i40e_aqc_set_switch_config { #define I40E_AQ_SET_SWITCH_CFG_PROMISC 0x0001 #define I40E_AQ_SET_SWITCH_CFG_L2_FILTER 0x0002 __le16 valid_flags; - u8 reserved[12]; + /* The ethertype in switch_tag is dropped on ingress and used + * internally by the switch. Set this to zero for the default + * of 0x88a8 (802.1ad). Should be zero for firmware API + * versions lower than 1.7. + */ + __le16 switch_tag; + /* The ethertypes in first_tag and second_tag are used to + * match the outer and inner VLAN tags (respectively) when HW + * double VLAN tagging is enabled via the set port parameters + * AQ command. Otherwise these are both ignored. Set them to + * zero for their defaults of 0x8100 (802.1Q). Should be zero + * for firmware API versions lower than 1.7. + */ + __le16 first_tag; + __le16 second_tag; + /* Next byte is split into following: + * Bit 7 : 0 : No action, 1: Switch to mode defined by bits 6:0 + * Bit 6 : 0 : Destination Port, 1: source port + * Bit 5..4 : L4 type + * 0: rsvd + * 1: TCP + * 2: UDP + * 3: Both TCP and UDP + * Bits 3:0 Mode + * 0: default mode + * 1: L4 port only mode + * 2: non-tunneled mode + * 3: tunneled mode + */ +#define I40E_AQ_SET_SWITCH_BIT7_VALID 0x80 + +#define I40E_AQ_SET_SWITCH_L4_SRC_PORT 0x40 + +#define I40E_AQ_SET_SWITCH_L4_TYPE_RSVD 0x00 +#define I40E_AQ_SET_SWITCH_L4_TYPE_TCP 0x10 +#define I40E_AQ_SET_SWITCH_L4_TYPE_UDP 0x20 +#define I40E_AQ_SET_SWITCH_L4_TYPE_BOTH 0x30 + +#define I40E_AQ_SET_SWITCH_MODE_DEFAULT 0x00 +#define I40E_AQ_SET_SWITCH_MODE_L4_PORT 0x01 +#define I40E_AQ_SET_SWITCH_MODE_NON_TUNNEL 0x02 +#define I40E_AQ_SET_SWITCH_MODE_TUNNEL 0x03 + u8 mode; + u8 rsvd5[5]; }; I40E_CHECK_CMD_LENGTH(i40e_aqc_set_switch_config); @@ -1318,14 +1371,16 @@ struct i40e_aqc_add_remove_cloud_filters { #define I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_SHIFT 0 #define I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_MASK (0x3FF << \ I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_SHIFT) - u8 reserved2[4]; + u8 big_buffer_flag; +#define I40E_AQC_ADD_CLOUD_CMD_BB 1 + u8 reserved2[3]; __le32 addr_high; __le32 addr_low; }; I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_cloud_filters); -struct i40e_aqc_add_remove_cloud_filters_element_data { +struct i40e_aqc_cloud_filters_element_data { u8 outer_mac[6]; u8 inner_mac[6]; __le16 inner_vlan; @@ -1337,6 +1392,9 @@ struct i40e_aqc_add_remove_cloud_filters_element_data { struct { u8 data[16]; } v6; + struct { + __le16 data[8]; + } raw_v6; } ipaddr; __le16 flags; #define I40E_AQC_ADD_CLOUD_FILTER_SHIFT 0 @@ -1355,6 +1413,10 @@ struct i40e_aqc_add_remove_cloud_filters_element_data { #define I40E_AQC_ADD_CLOUD_FILTER_IMAC 0x000A #define I40E_AQC_ADD_CLOUD_FILTER_OMAC_TEN_ID_IMAC 0x000B #define I40E_AQC_ADD_CLOUD_FILTER_IIP 0x000C +/* 0x0010 to 0x0017 is for custom filters */ +#define I40E_AQC_ADD_CLOUD_FILTER_IP_PORT 0x0010 /* Dest IP + L4 Port */ +#define I40E_AQC_ADD_CLOUD_FILTER_MAC_PORT 0x0011 /* Dest MAC + L4 Port */ +#define I40E_AQC_ADD_CLOUD_FILTER_MAC_VLAN_PORT 0x0012 /* Dest MAC + VLAN + L4 Port */ #define I40E_AQC_ADD_CLOUD_FLAGS_TO_QUEUE 0x0080 #define I40E_AQC_ADD_CLOUD_VNK_SHIFT 6 @@ -1389,6 +1451,49 @@ struct i40e_aqc_add_remove_cloud_filters_element_data { u8 response_reserved[7]; }; +I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_cloud_filters_element_data); + +/* i40e_aqc_cloud_filters_element_bb is used when + * I40E_AQC_CLOUD_CMD_BB flag is set. + */ +struct i40e_aqc_cloud_filters_element_bb { + struct i40e_aqc_cloud_filters_element_data element; + u16 general_fields[32]; +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD0 0 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD1 1 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD2 2 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD0 3 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD1 4 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD2 5 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD0 6 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD1 7 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD2 8 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD0 9 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD1 10 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD2 11 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD0 12 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD1 13 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD2 14 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD0 15 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD1 16 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD2 17 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD3 18 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD4 19 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD5 20 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD6 21 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD7 22 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD0 23 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD1 24 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD2 25 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD3 26 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD4 27 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD5 28 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD6 29 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD7 30 +}; + +I40E_CHECK_STRUCT_LEN(0x80, i40e_aqc_cloud_filters_element_bb); + struct i40e_aqc_remove_cloud_filters_completion { __le16 perfect_ovlan_used; __le16 perfect_ovlan_free; @@ -1400,6 +1505,60 @@ struct i40e_aqc_remove_cloud_filters_completion { I40E_CHECK_CMD_LENGTH(i40e_aqc_remove_cloud_filters_completion); +/* Replace filter Command 0x025F + * uses the i40e_aqc_replace_cloud_filters, + * and the generic indirect completion structure + */ +struct i40e_filter_data { + u8 filter_type; + u8 input[3]; +}; + +I40E_CHECK_STRUCT_LEN(4, i40e_filter_data); + +struct i40e_aqc_replace_cloud_filters_cmd { + u8 valid_flags; +#define I40E_AQC_REPLACE_L1_FILTER 0x0 +#define I40E_AQC_REPLACE_CLOUD_FILTER 0x1 +#define I40E_AQC_GET_CLOUD_FILTERS 0x2 +#define I40E_AQC_MIRROR_CLOUD_FILTER 0x4 +#define I40E_AQC_HIGH_PRIORITY_CLOUD_FILTER 0x8 + u8 old_filter_type; + u8 new_filter_type; + u8 tr_bit; + u8 reserved[4]; + __le32 addr_high; + __le32 addr_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_replace_cloud_filters_cmd); + +struct i40e_aqc_replace_cloud_filters_cmd_buf { + u8 data[32]; +/* Filter type INPUT codes*/ +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_ENTRIES_MAX 3 +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_VALIDATED BIT(7) + +/* Field Vector offsets */ +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_MAC_DA 0 +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_ETH 6 +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG 7 +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_VLAN 8 +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_OVLAN 9 +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_IVLAN 10 +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_TUNNLE_KEY 11 +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_IMAC 12 +/* big FLU */ +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_IP_DA 14 +/* big FLU */ +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_OIP_DA 15 + +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_INNER_VLAN 37 + struct i40e_filter_data filters[8]; +}; + +I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_replace_cloud_filters_cmd_buf); + /* Add Mirror Rule (indirect or direct 0x0260) * Delete Mirror Rule (indirect or direct 0x0261) * note: some rule types (4,5) do not use an external buffer. @@ -1726,6 +1885,8 @@ enum i40e_aq_phy_type { I40E_PHY_TYPE_10GBASE_CR1_CU = 0xB, I40E_PHY_TYPE_10GBASE_AOC = 0xC, I40E_PHY_TYPE_40GBASE_AOC = 0xD, + I40E_PHY_TYPE_UNRECOGNIZED = 0xE, + I40E_PHY_TYPE_UNSUPPORTED = 0xF, I40E_PHY_TYPE_100BASE_TX = 0x11, I40E_PHY_TYPE_1000BASE_T = 0x12, I40E_PHY_TYPE_10GBASE_T = 0x13, @@ -1744,7 +1905,12 @@ 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_MAX + 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, }; #define I40E_LINK_SPEED_100MB_SHIFT 0x1 @@ -1801,6 +1967,8 @@ 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 @@ -1934,19 +2102,31 @@ struct i40e_aqc_get_link_status { #define I40E_AQ_25G_SERDES_UCODE_ERR 0X04 #define I40E_AQ_25G_NIMB_UCODE_ERR 0X05 u8 loopback; /* use defines from i40e_aqc_set_lb_mode */ +/* Since firmware API 1.7 loopback field keeps power class info as well */ +#define I40E_AQ_LOOPBACK_MASK 0x07 +#define I40E_AQ_PWR_CLASS_SHIFT_LB 6 +#define I40E_AQ_PWR_CLASS_MASK_LB (0x03 << I40E_AQ_PWR_CLASS_SHIFT_LB) __le16 max_frame_size; u8 config; #define I40E_AQ_CONFIG_FEC_KR_ENA 0x01 #define I40E_AQ_CONFIG_FEC_RS_ENA 0x02 #define I40E_AQ_CONFIG_CRC_ENA 0x04 #define I40E_AQ_CONFIG_PACING_MASK 0x78 - u8 power_desc; + union { + struct { + u8 power_desc; #define I40E_AQ_LINK_POWER_CLASS_1 0x00 #define I40E_AQ_LINK_POWER_CLASS_2 0x01 #define I40E_AQ_LINK_POWER_CLASS_3 0x02 #define I40E_AQ_LINK_POWER_CLASS_4 0x03 #define I40E_AQ_PWR_CLASS_MASK 0x03 - u8 reserved[4]; + u8 reserved[4]; + }; + struct { + u8 link_type[4]; + u8 link_type_ext; + }; + }; }; I40E_CHECK_CMD_LENGTH(i40e_aqc_get_link_status); @@ -2029,6 +2209,22 @@ struct i40e_aqc_run_phy_activity { I40E_CHECK_CMD_LENGTH(i40e_aqc_run_phy_activity); +/* Set PHY Register command (0x0628) */ +/* Get PHY Register command (0x0629) */ +struct i40e_aqc_phy_register_access { + u8 phy_interface; +#define I40E_AQ_PHY_REG_ACCESS_INTERNAL 0 +#define I40E_AQ_PHY_REG_ACCESS_EXTERNAL 1 +#define I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE 2 + u8 dev_address; + u8 reserved1[2]; + __le32 reg_address; + __le32 reg_value; + u8 reserved2[4]; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_phy_register_access); + /* NVM Read command (indirect 0x0701) * NVM Erase commands (direct 0x0702) * NVM Update commands (indirect 0x0703) diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 111426ba5fbc..0203665cb53c 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: @@ -1567,34 +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) { - hw->phy.phy_types = le32_to_cpu(abilities->phy_type); - hw->phy.phy_types |= ((u64)abilities->phy_type_ext << 32); + 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) { + 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; @@ -1819,7 +1844,7 @@ i40e_status i40e_aq_get_link_info(struct i40e_hw *hw, hw_link_info->fec_info = resp->config & (I40E_AQ_CONFIG_FEC_KR_ENA | I40E_AQ_CONFIG_FEC_RS_ENA); hw_link_info->ext_info = resp->ext_info; - hw_link_info->loopback = resp->loopback; + hw_link_info->loopback = resp->loopback & I40E_AQ_LOOPBACK_MASK; hw_link_info->max_frame_size = le16_to_cpu(resp->max_frame_size); hw_link_info->pacing = resp->config & I40E_AQ_CONFIG_PACING_MASK; @@ -1850,6 +1875,15 @@ i40e_status i40e_aq_get_link_info(struct i40e_hw *hw, hw->aq.fw_min_ver < 40)) && hw_link_info->phy_type == 0xE) hw_link_info->phy_type = I40E_PHY_TYPE_10GBASE_SFPP_CU; + if (hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR && + hw->aq.api_min_ver >= 7) { + __le32 tmp; + + memcpy(&tmp, resp->link_type, sizeof(tmp)); + hw->phy.phy_types = le32_to_cpu(tmp); + hw->phy.phy_types |= ((u64)resp->link_type_ext << 32); + } + /* save link status information */ if (link) *link = *hw_link_info; @@ -2373,13 +2407,14 @@ i40e_status i40e_aq_get_switch_config(struct i40e_hw *hw, * @hw: pointer to the hardware structure * @flags: bit flag values to set * @valid_flags: which bit flags to set + * @mode: cloud filter mode * @cmd_details: pointer to command details structure or NULL * * Set switch configuration bits **/ enum i40e_status_code i40e_aq_set_switch_config(struct i40e_hw *hw, u16 flags, - u16 valid_flags, + u16 valid_flags, u8 mode, struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; @@ -2391,7 +2426,12 @@ enum i40e_status_code i40e_aq_set_switch_config(struct i40e_hw *hw, i40e_aqc_opc_set_switch_config); scfg->flags = cpu_to_le16(flags); scfg->valid_flags = cpu_to_le16(valid_flags); - + scfg->mode = mode; + if (hw->flags & I40E_HW_FLAG_802_1AD_CAPABLE) { + scfg->switch_tag = cpu_to_le16(hw->switch_tag); + scfg->first_tag = cpu_to_le16(hw->first_tag); + scfg->second_tag = cpu_to_le16(hw->second_tag); + } status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); return status; @@ -4826,6 +4866,74 @@ phy_blinking_end: } /** + * i40e_led_get_reg - read LED register + * @hw: pointer to the HW structure + * @led_addr: LED register address + * @reg_val: read register value + **/ +static enum i40e_status_code i40e_led_get_reg(struct i40e_hw *hw, u16 led_addr, + u32 *reg_val) +{ + enum i40e_status_code status; + u8 phy_addr = 0; + u8 port_num; + u32 i; + + *reg_val = 0; + if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE) { + status = + i40e_aq_get_phy_register(hw, + I40E_AQ_PHY_REG_ACCESS_EXTERNAL, + I40E_PHY_COM_REG_PAGE, + I40E_PHY_LED_PROV_REG_1, + reg_val, NULL); + } else { + i = rd32(hw, I40E_PFGEN_PORTNUM); + port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK); + phy_addr = i40e_get_phy_address(hw, port_num); + status = i40e_read_phy_register_clause45(hw, + I40E_PHY_COM_REG_PAGE, + led_addr, phy_addr, + (u16 *)reg_val); + } + return status; +} + +/** + * i40e_led_set_reg - write LED register + * @hw: pointer to the HW structure + * @led_addr: LED register address + * @reg_val: register value to write + **/ +static enum i40e_status_code i40e_led_set_reg(struct i40e_hw *hw, u16 led_addr, + u32 reg_val) +{ + enum i40e_status_code status; + u8 phy_addr = 0; + u8 port_num; + u32 i; + + if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE) { + status = + i40e_aq_set_phy_register(hw, + I40E_AQ_PHY_REG_ACCESS_EXTERNAL, + I40E_PHY_COM_REG_PAGE, + I40E_PHY_LED_PROV_REG_1, + reg_val, NULL); + } else { + i = rd32(hw, I40E_PFGEN_PORTNUM); + port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK); + phy_addr = i40e_get_phy_address(hw, port_num); + status = i40e_write_phy_register_clause45(hw, + I40E_PHY_COM_REG_PAGE, + led_addr, phy_addr, + (u16)reg_val); + } + + return status; +} + +/** * i40e_led_get_phy - return current on/off mode * @hw: pointer to the hw struct * @led_addr: address of led register to use @@ -4842,7 +4950,19 @@ i40e_status i40e_led_get_phy(struct i40e_hw *hw, u16 *led_addr, u16 temp_addr; u8 port_num; u32 i; - + u32 reg_val_aq; + + if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE) { + status = + i40e_aq_get_phy_register(hw, + I40E_AQ_PHY_REG_ACCESS_EXTERNAL, + I40E_PHY_COM_REG_PAGE, + I40E_PHY_LED_PROV_REG_1, + ®_val_aq, NULL); + if (status == I40E_SUCCESS) + *val = (u16)reg_val_aq; + return status; + } temp_addr = I40E_PHY_LED_PROV_REG_1; i = rd32(hw, I40E_PFGEN_PORTNUM); port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK); @@ -4877,51 +4997,38 @@ i40e_status i40e_led_set_phy(struct i40e_hw *hw, bool on, u16 led_addr, u32 mode) { i40e_status status = 0; - u16 led_ctl = 0; - u16 led_reg = 0; - u8 phy_addr = 0; - u8 port_num; - u32 i; + u32 led_ctl = 0; + u32 led_reg = 0; - i = rd32(hw, I40E_PFGEN_PORTNUM); - port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK); - phy_addr = i40e_get_phy_address(hw, port_num); - status = i40e_read_phy_register_clause45(hw, I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, &led_reg); + status = i40e_led_get_reg(hw, led_addr, &led_reg); if (status) return status; led_ctl = led_reg; if (led_reg & I40E_PHY_LED_LINK_MODE_MASK) { led_reg = 0; - status = i40e_write_phy_register_clause45(hw, - I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, - led_reg); + status = i40e_led_set_reg(hw, led_addr, led_reg); if (status) return status; } - status = i40e_read_phy_register_clause45(hw, I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, &led_reg); + status = i40e_led_get_reg(hw, led_addr, &led_reg); if (status) goto restore_config; if (on) led_reg = I40E_PHY_LED_MANUAL_ON; else led_reg = 0; - status = i40e_write_phy_register_clause45(hw, I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, led_reg); + + status = i40e_led_set_reg(hw, led_addr, led_reg); if (status) goto restore_config; if (mode & I40E_PHY_LED_MODE_ORIG) { led_ctl = (mode & I40E_PHY_LED_MODE_MASK); - status = i40e_write_phy_register_clause45(hw, - I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, led_ctl); + status = i40e_led_set_reg(hw, led_addr, led_ctl); } return status; + restore_config: - status = i40e_write_phy_register_clause45(hw, I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, led_ctl); + status = i40e_led_set_reg(hw, led_addr, led_ctl); return status; } @@ -5052,6 +5159,75 @@ do_retry: } /** + * i40e_aq_set_phy_register + * @hw: pointer to the hw struct + * @phy_select: select which phy should be accessed + * @dev_addr: PHY device address + * @reg_addr: PHY register address + * @reg_val: new register value + * @cmd_details: pointer to command details structure or NULL + * + * Write the external PHY register. + **/ +i40e_status i40e_aq_set_phy_register(struct i40e_hw *hw, + u8 phy_select, u8 dev_addr, + u32 reg_addr, u32 reg_val, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_phy_register_access *cmd = + (struct i40e_aqc_phy_register_access *)&desc.params.raw; + i40e_status status; + + i40e_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_set_phy_register); + + cmd->phy_interface = phy_select; + cmd->dev_address = dev_addr; + cmd->reg_address = cpu_to_le32(reg_addr); + cmd->reg_value = cpu_to_le32(reg_val); + + status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); + + return status; +} + +/** + * i40e_aq_get_phy_register + * @hw: pointer to the hw struct + * @phy_select: select which phy should be accessed + * @dev_addr: PHY device address + * @reg_addr: PHY register address + * @reg_val: read register value + * @cmd_details: pointer to command details structure or NULL + * + * Read the external PHY register. + **/ +i40e_status i40e_aq_get_phy_register(struct i40e_hw *hw, + u8 phy_select, u8 dev_addr, + u32 reg_addr, u32 *reg_val, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_phy_register_access *cmd = + (struct i40e_aqc_phy_register_access *)&desc.params.raw; + i40e_status status; + + i40e_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_get_phy_register); + + cmd->phy_interface = phy_select; + cmd->dev_address = dev_addr; + cmd->reg_address = cpu_to_le32(reg_addr); + + status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); + if (!status) + *reg_val = le32_to_cpu(cmd->reg_value); + + return status; +} + +/** * i40e_aq_write_ppp - Write pipeline personalization profile (ppp) * @hw: pointer to the hw struct * @buff: command buffer (size in bytes = buff_size) @@ -5260,5 +5436,194 @@ i40e_add_pinfo_to_list(struct i40e_hw *hw, status = i40e_aq_write_ppp(hw, (void *)sec, sec->data_end, track_id, &offset, &info, NULL); + + return status; +} + +/** + * i40e_aq_add_cloud_filters + * @hw: pointer to the hardware structure + * @seid: VSI seid to add cloud filters from + * @filters: Buffer which contains the filters to be added + * @filter_count: number of filters contained in the buffer + * + * Set the cloud filters for a given VSI. The contents of the + * i40e_aqc_cloud_filters_element_data are filled in by the caller + * of the function. + * + **/ +enum i40e_status_code +i40e_aq_add_cloud_filters(struct i40e_hw *hw, u16 seid, + struct i40e_aqc_cloud_filters_element_data *filters, + u8 filter_count) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_add_remove_cloud_filters *cmd = + (struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw; + enum i40e_status_code status; + u16 buff_len; + + i40e_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_add_cloud_filters); + + buff_len = filter_count * sizeof(*filters); + desc.datalen = cpu_to_le16(buff_len); + desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD)); + cmd->num_filters = filter_count; + cmd->seid = cpu_to_le16(seid); + + status = i40e_asq_send_command(hw, &desc, filters, buff_len, NULL); + + return status; +} + +/** + * i40e_aq_add_cloud_filters_bb + * @hw: pointer to the hardware structure + * @seid: VSI seid to add cloud filters from + * @filters: Buffer which contains the filters in big buffer to be added + * @filter_count: number of filters contained in the buffer + * + * Set the big buffer cloud filters for a given VSI. The contents of the + * i40e_aqc_cloud_filters_element_bb are filled in by the caller of the + * function. + * + **/ +i40e_status +i40e_aq_add_cloud_filters_bb(struct i40e_hw *hw, u16 seid, + struct i40e_aqc_cloud_filters_element_bb *filters, + u8 filter_count) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_add_remove_cloud_filters *cmd = + (struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw; + i40e_status status; + u16 buff_len; + int i; + + i40e_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_add_cloud_filters); + + buff_len = filter_count * sizeof(*filters); + desc.datalen = cpu_to_le16(buff_len); + desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD)); + cmd->num_filters = filter_count; + cmd->seid = cpu_to_le16(seid); + cmd->big_buffer_flag = I40E_AQC_ADD_CLOUD_CMD_BB; + + for (i = 0; i < filter_count; i++) { + u16 tnl_type; + u32 ti; + + tnl_type = (le16_to_cpu(filters[i].element.flags) & + I40E_AQC_ADD_CLOUD_TNL_TYPE_MASK) >> + I40E_AQC_ADD_CLOUD_TNL_TYPE_SHIFT; + + /* Due to hardware eccentricities, the VNI for Geneve is shifted + * one more byte further than normally used for Tenant ID in + * other tunnel types. + */ + if (tnl_type == I40E_AQC_ADD_CLOUD_TNL_TYPE_GENEVE) { + ti = le32_to_cpu(filters[i].element.tenant_id); + filters[i].element.tenant_id = cpu_to_le32(ti << 8); + } + } + + status = i40e_asq_send_command(hw, &desc, filters, buff_len, NULL); + + return status; +} + +/** + * i40e_aq_rem_cloud_filters + * @hw: pointer to the hardware structure + * @seid: VSI seid to remove cloud filters from + * @filters: Buffer which contains the filters to be removed + * @filter_count: number of filters contained in the buffer + * + * Remove the cloud filters for a given VSI. The contents of the + * i40e_aqc_cloud_filters_element_data are filled in by the caller + * of the function. + * + **/ +enum i40e_status_code +i40e_aq_rem_cloud_filters(struct i40e_hw *hw, u16 seid, + struct i40e_aqc_cloud_filters_element_data *filters, + u8 filter_count) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_add_remove_cloud_filters *cmd = + (struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw; + enum i40e_status_code status; + u16 buff_len; + + i40e_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_remove_cloud_filters); + + buff_len = filter_count * sizeof(*filters); + desc.datalen = cpu_to_le16(buff_len); + desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD)); + cmd->num_filters = filter_count; + cmd->seid = cpu_to_le16(seid); + + status = i40e_asq_send_command(hw, &desc, filters, buff_len, NULL); + + return status; +} + +/** + * i40e_aq_rem_cloud_filters_bb + * @hw: pointer to the hardware structure + * @seid: VSI seid to remove cloud filters from + * @filters: Buffer which contains the filters in big buffer to be removed + * @filter_count: number of filters contained in the buffer + * + * Remove the big buffer cloud filters for a given VSI. The contents of the + * i40e_aqc_cloud_filters_element_bb are filled in by the caller of the + * function. + * + **/ +i40e_status +i40e_aq_rem_cloud_filters_bb(struct i40e_hw *hw, u16 seid, + struct i40e_aqc_cloud_filters_element_bb *filters, + u8 filter_count) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_add_remove_cloud_filters *cmd = + (struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw; + i40e_status status; + u16 buff_len; + int i; + + i40e_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_remove_cloud_filters); + + buff_len = filter_count * sizeof(*filters); + desc.datalen = cpu_to_le16(buff_len); + desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD)); + cmd->num_filters = filter_count; + cmd->seid = cpu_to_le16(seid); + cmd->big_buffer_flag = I40E_AQC_ADD_CLOUD_CMD_BB; + + for (i = 0; i < filter_count; i++) { + u16 tnl_type; + u32 ti; + + tnl_type = (le16_to_cpu(filters[i].element.flags) & + I40E_AQC_ADD_CLOUD_TNL_TYPE_MASK) >> + I40E_AQC_ADD_CLOUD_TNL_TYPE_SHIFT; + + /* Due to hardware eccentricities, the VNI for Geneve is shifted + * one more byte further than normally used for Tenant ID in + * other tunnel types. + */ + if (tnl_type == I40E_AQC_ADD_CLOUD_TNL_TYPE_GENEVE) { + ti = le32_to_cpu(filters[i].element.tenant_id); + filters[i].element.tenant_id = cpu_to_le32(ti << 8); + } + } + + status = i40e_asq_send_command(hw, &desc, filters, buff_len, NULL); + return status; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 2cb9539c931e..4c3b4243cf65 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 e9e04a485e0a..5f6cf7212d4f 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) + 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) - *advertising |= ADVERTISED_10000baseT_Full; + 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; @@ -4175,7 +4343,7 @@ flags_complete: sw_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC; valid_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC; ret = i40e_aq_set_switch_config(&pf->hw, sw_flags, valid_flags, - NULL); + 0, NULL); if (ret && pf->hw.aq.asq_last_status != I40E_AQ_RC_ESRCH) { dev_info(&pf->pdev->dev, "couldn't set switch config bits, err %s aq_err %s\n", @@ -4189,13 +4357,166 @@ 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; } +/** + * i40e_get_module_info - get (Q)SFP+ module type info + * @netdev: network interface device structure + * @modinfo: module EEPROM size and layout information structure + **/ +static int i40e_get_module_info(struct net_device *netdev, + struct ethtool_modinfo *modinfo) +{ + struct i40e_netdev_priv *np = netdev_priv(netdev); + struct i40e_vsi *vsi = np->vsi; + struct i40e_pf *pf = vsi->back; + struct i40e_hw *hw = &pf->hw; + u32 sff8472_comp = 0; + u32 sff8472_swap = 0; + u32 sff8636_rev = 0; + i40e_status status; + u32 type = 0; + + /* Check if firmware supports reading module EEPROM. */ + if (!(hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE)) { + netdev_err(vsi->netdev, "Module EEPROM memory read not supported. Please update the NVM image.\n"); + return -EINVAL; + } + + status = i40e_update_link_info(hw); + if (status) + return -EIO; + + if (hw->phy.link_info.phy_type == I40E_PHY_TYPE_EMPTY) { + netdev_err(vsi->netdev, "Cannot read module EEPROM memory. No module connected.\n"); + return -EINVAL; + } + + type = hw->phy.link_info.module_type[0]; + + switch (type) { + case I40E_MODULE_TYPE_SFP: + status = i40e_aq_get_phy_register(hw, + I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE, + I40E_I2C_EEPROM_DEV_ADDR, + I40E_MODULE_SFF_8472_COMP, + &sff8472_comp, NULL); + if (status) + return -EIO; + + status = i40e_aq_get_phy_register(hw, + I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE, + I40E_I2C_EEPROM_DEV_ADDR, + I40E_MODULE_SFF_8472_SWAP, + &sff8472_swap, NULL); + if (status) + return -EIO; + + /* Check if the module requires address swap to access + * the other EEPROM memory page. + */ + if (sff8472_swap & I40E_MODULE_SFF_ADDR_MODE) { + netdev_warn(vsi->netdev, "Module address swap to access page 0xA2 is not supported.\n"); + modinfo->type = ETH_MODULE_SFF_8079; + modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN; + } else if (sff8472_comp == 0x00) { + /* Module is not SFF-8472 compliant */ + modinfo->type = ETH_MODULE_SFF_8079; + modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN; + } else { + modinfo->type = ETH_MODULE_SFF_8472; + modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; + } + break; + case I40E_MODULE_TYPE_QSFP_PLUS: + /* Read from memory page 0. */ + status = i40e_aq_get_phy_register(hw, + I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE, + 0, + I40E_MODULE_REVISION_ADDR, + &sff8636_rev, NULL); + if (status) + return -EIO; + /* Determine revision compliance byte */ + if (sff8636_rev > 0x02) { + /* Module is SFF-8636 compliant */ + modinfo->type = ETH_MODULE_SFF_8636; + modinfo->eeprom_len = I40E_MODULE_QSFP_MAX_LEN; + } else { + modinfo->type = ETH_MODULE_SFF_8436; + modinfo->eeprom_len = I40E_MODULE_QSFP_MAX_LEN; + } + break; + case I40E_MODULE_TYPE_QSFP28: + modinfo->type = ETH_MODULE_SFF_8636; + modinfo->eeprom_len = I40E_MODULE_QSFP_MAX_LEN; + break; + default: + netdev_err(vsi->netdev, "Module type unrecognized\n"); + return -EINVAL; + } + return 0; +} + +/** + * i40e_get_module_eeprom - fills buffer with (Q)SFP+ module memory contents + * @netdev: network interface device structure + * @ee: EEPROM dump request structure + * @data: buffer to be filled with EEPROM contents + **/ +static int i40e_get_module_eeprom(struct net_device *netdev, + struct ethtool_eeprom *ee, + u8 *data) +{ + struct i40e_netdev_priv *np = netdev_priv(netdev); + struct i40e_vsi *vsi = np->vsi; + struct i40e_pf *pf = vsi->back; + struct i40e_hw *hw = &pf->hw; + bool is_sfp = false; + i40e_status status; + u32 value = 0; + int i; + + if (!ee || !ee->len || !data) + return -EINVAL; + + if (hw->phy.link_info.module_type[0] == I40E_MODULE_TYPE_SFP) + is_sfp = true; + + for (i = 0; i < ee->len; i++) { + u32 offset = i + ee->offset; + u32 addr = is_sfp ? I40E_I2C_EEPROM_DEV_ADDR : 0; + + /* Check if we need to access the other memory page */ + if (is_sfp) { + if (offset >= ETH_MODULE_SFF_8079_LEN) { + offset -= ETH_MODULE_SFF_8079_LEN; + addr = I40E_I2C_EEPROM_DEV_ADDR2; + } + } else { + while (offset >= ETH_MODULE_SFF_8436_LEN) { + /* Compute memory page number and offset. */ + offset -= ETH_MODULE_SFF_8436_LEN / 2; + addr++; + } + } + + status = i40e_aq_get_phy_register(hw, + I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE, + addr, offset, &value, NULL); + if (status) + return -EIO; + data[i] = value; + } + return 0; +} + static const struct ethtool_ops i40e_ethtool_ops = { .get_drvinfo = i40e_get_drvinfo, .get_regs_len = i40e_get_regs_len, @@ -4228,6 +4549,8 @@ static const struct ethtool_ops i40e_ethtool_ops = { .set_rxfh = i40e_set_rxfh, .get_channels = i40e_get_channels, .set_channels = i40e_set_channels, + .get_module_info = i40e_get_module_info, + .get_module_eeprom = i40e_get_module_eeprom, .get_ts_info = i40e_get_ts_info, .get_priv_flags = i40e_get_priv_flags, .set_priv_flags = i40e_set_priv_flags, diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index de1fcac7834d..4a964d6e4a9e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -69,6 +69,15 @@ static int i40e_reset(struct i40e_pf *pf); static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired); static void i40e_fdir_sb_setup(struct i40e_pf *pf); static int i40e_veb_get_bw_info(struct i40e_veb *veb); +static int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, + struct i40e_cloud_filter *filter, + bool add); +static int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi, + struct i40e_cloud_filter *filter, + bool add); +static int i40e_get_capabilities(struct i40e_pf *pf, + enum i40e_admin_queue_opc list_type); + /* i40e_pci_tbl - PCI Device ID Table * @@ -600,6 +609,20 @@ static void i40e_stat_update32(struct i40e_hw *hw, u32 reg, } /** + * i40e_stat_update_and_clear32 - read and clear hw reg, update a 32 bit stat + * @hw: ptr to the hardware info + * @reg: the hw reg to read and clear + * @stat: ptr to the stat + **/ +static void i40e_stat_update_and_clear32(struct i40e_hw *hw, u32 reg, u64 *stat) +{ + u32 new_data = rd32(hw, reg); + + wr32(hw, reg, 1); /* must write a nonzero value to clear register */ + *stat += new_data; +} + +/** * i40e_update_eth_stats - Update VSI-specific ethernet statistics counters. * @vsi: the VSI to be updated **/ @@ -1040,18 +1063,15 @@ static void i40e_update_pf_stats(struct i40e_pf *pf) &osd->rx_jabber, &nsd->rx_jabber); /* FDIR stats */ - i40e_stat_update32(hw, - I40E_GLQF_PCNT(I40E_FD_ATR_STAT_IDX(pf->hw.pf_id)), - pf->stat_offsets_loaded, - &osd->fd_atr_match, &nsd->fd_atr_match); - i40e_stat_update32(hw, - I40E_GLQF_PCNT(I40E_FD_SB_STAT_IDX(pf->hw.pf_id)), - pf->stat_offsets_loaded, - &osd->fd_sb_match, &nsd->fd_sb_match); - i40e_stat_update32(hw, - I40E_GLQF_PCNT(I40E_FD_ATR_TUNNEL_STAT_IDX(pf->hw.pf_id)), - pf->stat_offsets_loaded, - &osd->fd_atr_tunnel_match, &nsd->fd_atr_tunnel_match); + i40e_stat_update_and_clear32(hw, + I40E_GLQF_PCNT(I40E_FD_ATR_STAT_IDX(hw->pf_id)), + &nsd->fd_atr_match); + i40e_stat_update_and_clear32(hw, + I40E_GLQF_PCNT(I40E_FD_SB_STAT_IDX(hw->pf_id)), + &nsd->fd_sb_match); + i40e_stat_update_and_clear32(hw, + I40E_GLQF_PCNT(I40E_FD_ATR_TUNNEL_STAT_IDX(hw->pf_id)), + &nsd->fd_atr_tunnel_match); val = rd32(hw, I40E_PRTPM_EEE_STAT); nsd->tx_lpi_status = @@ -1578,6 +1598,170 @@ 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 @@ -1615,7 +1799,7 @@ 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; } @@ -1765,11 +1949,6 @@ 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); } /** @@ -2873,22 +3052,18 @@ 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); } /** @@ -2942,7 +3117,14 @@ 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 */ @@ -2964,12 +3146,23 @@ 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) & @@ -2998,7 +3191,7 @@ 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)); @@ -3023,7 +3216,7 @@ 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 */ @@ -3138,6 +3331,7 @@ 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++) { @@ -3396,15 +3590,14 @@ 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); @@ -3471,6 +3664,7 @@ 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]; @@ -3506,10 +3700,14 @@ 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; @@ -3585,7 +3783,7 @@ 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); @@ -3593,14 +3791,20 @@ static int i40e_vsi_enable_irq(struct i40e_vsi *vsi) } /** - * i40e_stop_misc_vector - Stop the vector that handles non-queue events + * i40e_free_misc_vector - Free the vector that handles non-queue events * @pf: board private structure **/ -static void i40e_stop_misc_vector(struct i40e_pf *pf) +static void i40e_free_misc_vector(struct i40e_pf *pf) { /* Disable ICR 0 */ wr32(&pf->hw, I40E_PFINT_ICR0_ENA, 0); i40e_flush(&pf->hw); + + if (pf->flags & I40E_FLAG_MSIX_ENABLED && pf->msix_entries) { + synchronize_irq(pf->msix_entries[0].vector); + free_irq(pf->msix_entries[0].vector, pf); + clear_bit(__I40E_MISC_IRQ_REQUESTED, pf->state); + } } /** @@ -3728,7 +3932,7 @@ 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; @@ -4455,11 +4659,7 @@ static void i40e_clear_interrupt_scheme(struct i40e_pf *pf) { int i; - i40e_stop_misc_vector(pf); - if (pf->flags & I40E_FLAG_MSIX_ENABLED && pf->msix_entries) { - synchronize_irq(pf->msix_entries[0].vector); - free_irq(pf->msix_entries[0].vector, pf); - } + i40e_free_misc_vector(pf); i40e_put_lump(pf->irq_pile, pf->iwarp_base_vector, I40E_IWARP_IRQ_PILE_ID); @@ -4848,6 +5048,24 @@ 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 * @@ -4860,7 +5078,10 @@ 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; @@ -4889,7 +5110,12 @@ 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; @@ -4979,6 +5205,16 @@ 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]; @@ -5041,6 +5277,9 @@ 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 */ @@ -5091,7 +5330,8 @@ 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 */ @@ -5114,15 +5354,37 @@ 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, @@ -5154,6 +5416,825 @@ 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) +{ + enum i40e_admin_queue_err last_aq_status; + struct i40e_cloud_filter *cfilter; + struct i40e_channel *ch, *ch_tmp; + struct i40e_pf *pf = vsi->back; + struct hlist_node *node; + 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 cloud filters associated with this channel */ + hlist_for_each_entry_safe(cfilter, node, + &pf->cloud_filter_list, cloud_node) { + if (cfilter->seid != ch->seid) + continue; + + hash_del(&cfilter->cloud_node); + if (cfilter->dst_port) + ret = i40e_add_del_cloud_filter_big_buf(vsi, + cfilter, + false); + else + ret = i40e_add_del_cloud_filter(vsi, cfilter, + false); + last_aq_status = pf->hw.aq.asq_last_status; + if (ret) + dev_info(&pf->pdev->dev, + "Failed to delete cloud filter, err %s aq_err %s\n", + i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, last_aq_status)); + kfree(cfilter); + } + + /* 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_validate_and_set_switch_mode - sets up switch mode correctly + * @vsi: ptr to VSI which has PF backing + * + * Sets up switch mode correctly if it needs to be changed and perform + * what are allowed modes. + **/ +static int i40e_validate_and_set_switch_mode(struct i40e_vsi *vsi) +{ + u8 mode; + struct i40e_pf *pf = vsi->back; + struct i40e_hw *hw = &pf->hw; + int ret; + + ret = i40e_get_capabilities(pf, i40e_aqc_opc_list_dev_capabilities); + if (ret) + return -EINVAL; + + if (hw->dev_caps.switch_mode) { + /* if switch mode is set, support mode2 (non-tunneled for + * cloud filter) for now + */ + u32 switch_mode = hw->dev_caps.switch_mode & + I40E_SWITCH_MODE_MASK; + if (switch_mode >= I40E_CLOUD_FILTER_MODE1) { + if (switch_mode == I40E_CLOUD_FILTER_MODE2) + return 0; + dev_err(&pf->pdev->dev, + "Invalid switch_mode (%d), only non-tunneled mode for cloud filter is supported\n", + hw->dev_caps.switch_mode); + return -EINVAL; + } + } + + /* Set Bit 7 to be valid */ + mode = I40E_AQ_SET_SWITCH_BIT7_VALID; + + /* Set L4type to both TCP and UDP support */ + mode |= I40E_AQ_SET_SWITCH_L4_TYPE_BOTH; + + /* Set cloud filter mode */ + mode |= I40E_AQ_SET_SWITCH_MODE_NON_TUNNEL; + + /* Prep mode field for set_switch_config */ + ret = i40e_aq_set_switch_config(hw, pf->last_sw_conf_flags, + pf->last_sw_conf_valid_flags, + mode, NULL); + if (ret && hw->aq.asq_last_status != I40E_AQ_RC_ESRCH) + dev_err(&pf->pdev->dev, + "couldn't set switch config bits, err %s aq_err %s\n", + i40e_stat_str(hw, ret), + i40e_aq_str(hw, + hw->aq.asq_last_status)); + + return ret; +} + +/** + * 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 */ + vsi->tc_seid_map[0] = vsi->seid; + 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; + } + vsi->tc_seid_map[i] = ch->seid; + } + } + 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 @@ -5346,13 +6427,14 @@ out: void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) { enum i40e_aq_link_speed new_speed; + struct i40e_pf *pf = vsi->back; char *speed = "Unknown"; char *fc = "Unknown"; char *fec = ""; char *req_fec = ""; char *an = ""; - new_speed = vsi->back->hw.phy.link_info.link_speed; + new_speed = pf->hw.phy.link_info.link_speed; if ((vsi->current_isup == isup) && (vsi->current_speed == new_speed)) return; @@ -5366,13 +6448,13 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) /* Warn user if link speed on NPAR enabled partition is not at * least 10GB */ - if (vsi->back->hw.func_caps.npar_enable && - (vsi->back->hw.phy.link_info.link_speed == I40E_LINK_SPEED_1GB || - vsi->back->hw.phy.link_info.link_speed == I40E_LINK_SPEED_100MB)) + if (pf->hw.func_caps.npar_enable && + (pf->hw.phy.link_info.link_speed == I40E_LINK_SPEED_1GB || + pf->hw.phy.link_info.link_speed == I40E_LINK_SPEED_100MB)) netdev_warn(vsi->netdev, "The partition detected link speed that is less than 10Gbps\n"); - switch (vsi->back->hw.phy.link_info.link_speed) { + switch (pf->hw.phy.link_info.link_speed) { case I40E_LINK_SPEED_40GB: speed = "40 G"; break; @@ -5395,7 +6477,7 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) break; } - switch (vsi->back->hw.fc.current_mode) { + switch (pf->hw.fc.current_mode) { case I40E_FC_FULL: fc = "RX/TX"; break; @@ -5410,18 +6492,18 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) break; } - if (vsi->back->hw.phy.link_info.link_speed == I40E_LINK_SPEED_25GB) { + if (pf->hw.phy.link_info.link_speed == I40E_LINK_SPEED_25GB) { req_fec = ", Requested FEC: None"; fec = ", FEC: None"; an = ", Autoneg: False"; - if (vsi->back->hw.phy.link_info.an_info & I40E_AQ_AN_COMPLETED) + if (pf->hw.phy.link_info.an_info & I40E_AQ_AN_COMPLETED) an = ", Autoneg: True"; - if (vsi->back->hw.phy.link_info.fec_info & + if (pf->hw.phy.link_info.fec_info & I40E_AQ_CONFIG_FEC_KR_ENA) fec = ", FEC: CL74 FC-FEC/BASE-R"; - else if (vsi->back->hw.phy.link_info.fec_info & + else if (pf->hw.phy.link_info.fec_info & I40E_AQ_CONFIG_FEC_RS_ENA) fec = ", FEC: CL108 RS-FEC"; @@ -5470,15 +6552,6 @@ static int i40e_up_complete(struct i40e_vsi *vsi) i40e_print_link_message(vsi, true); netif_tx_start_all_queues(vsi->netdev); netif_carrier_on(vsi->netdev); - } else if (vsi->netdev) { - i40e_print_link_message(vsi, false); - /* need to check for qualified module here*/ - if ((pf->hw.phy.link_info.link_info & - I40E_AQ_MEDIA_AVAILABLE) && - (!(pf->hw.phy.link_info.an_info & - I40E_AQ_QUALIFIED_MODULE))) - netdev_err(vsi->netdev, - "the driver failed to link because an unqualified module was detected."); } /* replay FDIR SB filters */ @@ -5562,74 +6635,928 @@ 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; } + 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; +} -exit: +/** + * i40e_set_cld_element - sets cloud filter element data + * @filter: cloud filter rule + * @cld: ptr to cloud filter element data + * + * This is helper function to copy data into cloud filter element + **/ +static inline void +i40e_set_cld_element(struct i40e_cloud_filter *filter, + struct i40e_aqc_cloud_filters_element_data *cld) +{ + int i, j; + u32 ipa; + + memset(cld, 0, sizeof(*cld)); + ether_addr_copy(cld->outer_mac, filter->dst_mac); + ether_addr_copy(cld->inner_mac, filter->src_mac); + + if (filter->n_proto != ETH_P_IP && filter->n_proto != ETH_P_IPV6) + return; + + if (filter->n_proto == ETH_P_IPV6) { +#define IPV6_MAX_INDEX (ARRAY_SIZE(filter->dst_ipv6) - 1) + for (i = 0, j = 0; i < ARRAY_SIZE(filter->dst_ipv6); + i++, j += 2) { + ipa = be32_to_cpu(filter->dst_ipv6[IPV6_MAX_INDEX - i]); + ipa = cpu_to_le32(ipa); + memcpy(&cld->ipaddr.raw_v6.data[j], &ipa, sizeof(ipa)); + } + } else { + ipa = be32_to_cpu(filter->dst_ipv4); + memcpy(&cld->ipaddr.v4.data, &ipa, sizeof(ipa)); + } + + cld->inner_vlan = cpu_to_le16(ntohs(filter->vlan_id)); + + /* tenant_id is not supported by FW now, once the support is enabled + * fill the cld->tenant_id with cpu_to_le32(filter->tenant_id) + */ + if (filter->tenant_id) + return; +} + +/** + * i40e_add_del_cloud_filter - Add/del cloud filter + * @vsi: pointer to VSI + * @filter: cloud filter rule + * @add: if true, add, if false, delete + * + * Add or delete a cloud filter for a specific flow spec. + * Returns 0 if the filter were successfully added. + **/ +static int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, + struct i40e_cloud_filter *filter, bool add) +{ + struct i40e_aqc_cloud_filters_element_data cld_filter; + struct i40e_pf *pf = vsi->back; + int ret; + static const u16 flag_table[128] = { + [I40E_CLOUD_FILTER_FLAGS_OMAC] = + I40E_AQC_ADD_CLOUD_FILTER_OMAC, + [I40E_CLOUD_FILTER_FLAGS_IMAC] = + I40E_AQC_ADD_CLOUD_FILTER_IMAC, + [I40E_CLOUD_FILTER_FLAGS_IMAC_IVLAN] = + I40E_AQC_ADD_CLOUD_FILTER_IMAC_IVLAN, + [I40E_CLOUD_FILTER_FLAGS_IMAC_TEN_ID] = + I40E_AQC_ADD_CLOUD_FILTER_IMAC_TEN_ID, + [I40E_CLOUD_FILTER_FLAGS_OMAC_TEN_ID_IMAC] = + I40E_AQC_ADD_CLOUD_FILTER_OMAC_TEN_ID_IMAC, + [I40E_CLOUD_FILTER_FLAGS_IMAC_IVLAN_TEN_ID] = + I40E_AQC_ADD_CLOUD_FILTER_IMAC_IVLAN_TEN_ID, + [I40E_CLOUD_FILTER_FLAGS_IIP] = + I40E_AQC_ADD_CLOUD_FILTER_IIP, + }; + + if (filter->flags >= ARRAY_SIZE(flag_table)) + return I40E_ERR_CONFIG; + + /* copy element needed to add cloud filter from filter */ + i40e_set_cld_element(filter, &cld_filter); + + if (filter->tunnel_type != I40E_CLOUD_TNL_TYPE_NONE) + cld_filter.flags = cpu_to_le16(filter->tunnel_type << + I40E_AQC_ADD_CLOUD_TNL_TYPE_SHIFT); + + if (filter->n_proto == ETH_P_IPV6) + cld_filter.flags |= cpu_to_le16(flag_table[filter->flags] | + I40E_AQC_ADD_CLOUD_FLAGS_IPV6); + else + cld_filter.flags |= cpu_to_le16(flag_table[filter->flags] | + I40E_AQC_ADD_CLOUD_FLAGS_IPV4); + + if (add) + ret = i40e_aq_add_cloud_filters(&pf->hw, filter->seid, + &cld_filter, 1); + else + ret = i40e_aq_rem_cloud_filters(&pf->hw, filter->seid, + &cld_filter, 1); + if (ret) + dev_dbg(&pf->pdev->dev, + "Failed to %s cloud filter using l4 port %u, err %d aq_err %d\n", + add ? "add" : "delete", filter->dst_port, ret, + pf->hw.aq.asq_last_status); + else + dev_info(&pf->pdev->dev, + "%s cloud filter for VSI: %d\n", + add ? "Added" : "Deleted", filter->seid); return ret; } -static int __i40e_setup_tc(struct net_device *netdev, enum tc_setup_type type, - void *type_data) +/** + * i40e_add_del_cloud_filter_big_buf - Add/del cloud filter using big_buf + * @vsi: pointer to VSI + * @filter: cloud filter rule + * @add: if true, add, if false, delete + * + * Add or delete a cloud filter for a specific flow spec using big buffer. + * Returns 0 if the filter were successfully added. + **/ +static int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi, + struct i40e_cloud_filter *filter, + bool add) { - struct tc_mqprio_qopt *mqprio = type_data; + struct i40e_aqc_cloud_filters_element_bb cld_filter; + struct i40e_pf *pf = vsi->back; + int ret; + + /* Both (src/dst) valid mac_addr are not supported */ + if ((is_valid_ether_addr(filter->dst_mac) && + is_valid_ether_addr(filter->src_mac)) || + (is_multicast_ether_addr(filter->dst_mac) && + is_multicast_ether_addr(filter->src_mac))) + return -EINVAL; + + /* Make sure port is specified, otherwise bail out, for channel + * specific cloud filter needs 'L4 port' to be non-zero + */ + if (!filter->dst_port) + return -EINVAL; + + /* adding filter using src_port/src_ip is not supported at this stage */ + if (filter->src_port || filter->src_ipv4 || + !ipv6_addr_any(&filter->ip.v6.src_ip6)) + return -EINVAL; + + /* copy element needed to add cloud filter from filter */ + i40e_set_cld_element(filter, &cld_filter.element); + + if (is_valid_ether_addr(filter->dst_mac) || + is_valid_ether_addr(filter->src_mac) || + is_multicast_ether_addr(filter->dst_mac) || + is_multicast_ether_addr(filter->src_mac)) { + /* MAC + IP : unsupported mode */ + if (filter->dst_ipv4) + return -EINVAL; + + /* since we validated that L4 port must be valid before + * we get here, start with respective "flags" value + * and update if vlan is present or not + */ + cld_filter.element.flags = + cpu_to_le16(I40E_AQC_ADD_CLOUD_FILTER_MAC_PORT); + + if (filter->vlan_id) { + cld_filter.element.flags = + cpu_to_le16(I40E_AQC_ADD_CLOUD_FILTER_MAC_VLAN_PORT); + } + + } else if (filter->dst_ipv4 || + !ipv6_addr_any(&filter->ip.v6.dst_ip6)) { + cld_filter.element.flags = + cpu_to_le16(I40E_AQC_ADD_CLOUD_FILTER_IP_PORT); + if (filter->n_proto == ETH_P_IPV6) + cld_filter.element.flags |= + cpu_to_le16(I40E_AQC_ADD_CLOUD_FLAGS_IPV6); + else + cld_filter.element.flags |= + cpu_to_le16(I40E_AQC_ADD_CLOUD_FLAGS_IPV4); + } else { + dev_err(&pf->pdev->dev, + "either mac or ip has to be valid for cloud filter\n"); + return -EINVAL; + } + + /* Now copy L4 port in Byte 6..7 in general fields */ + cld_filter.general_fields[I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD0] = + be16_to_cpu(filter->dst_port); + + if (add) { + /* Validate current device switch mode, change if necessary */ + ret = i40e_validate_and_set_switch_mode(vsi); + if (ret) { + dev_err(&pf->pdev->dev, + "failed to set switch mode, ret %d\n", + ret); + return ret; + } - if (type != TC_SETUP_MQPRIO) + ret = i40e_aq_add_cloud_filters_bb(&pf->hw, filter->seid, + &cld_filter, 1); + } else { + ret = i40e_aq_rem_cloud_filters_bb(&pf->hw, filter->seid, + &cld_filter, 1); + } + + if (ret) + dev_dbg(&pf->pdev->dev, + "Failed to %s cloud filter(big buffer) err %d aq_err %d\n", + add ? "add" : "delete", ret, pf->hw.aq.asq_last_status); + else + dev_info(&pf->pdev->dev, + "%s cloud filter for VSI: %d, L4 port: %d\n", + add ? "add" : "delete", filter->seid, + ntohs(filter->dst_port)); + return ret; +} + +/** + * i40e_parse_cls_flower - Parse tc flower filters provided by kernel + * @vsi: Pointer to VSI + * @cls_flower: Pointer to struct tc_cls_flower_offload + * @filter: Pointer to cloud filter structure + * + **/ +static int i40e_parse_cls_flower(struct i40e_vsi *vsi, + struct tc_cls_flower_offload *f, + struct i40e_cloud_filter *filter) +{ + u16 n_proto_mask = 0, n_proto_key = 0, addr_type = 0; + struct i40e_pf *pf = vsi->back; + u8 field_flags = 0; + + if (f->dissector->used_keys & + ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | + BIT(FLOW_DISSECTOR_KEY_BASIC) | + BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_VLAN) | + BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_PORTS) | + BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) { + dev_err(&pf->pdev->dev, "Unsupported key used: 0x%x\n", + f->dissector->used_keys); return -EOPNOTSUPP; + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_dissector_key_keyid *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ENC_KEYID, + f->key); + + struct flow_dissector_key_keyid *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ENC_KEYID, + f->mask); + + if (mask->keyid != 0) + field_flags |= I40E_CLOUD_FIELD_TEN_ID; + + filter->tenant_id = be32_to_cpu(key->keyid); + } - mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_dissector_key_basic *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_BASIC, + f->key); - return i40e_setup_tc(netdev, mqprio->num_tc); + struct flow_dissector_key_basic *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_BASIC, + f->mask); + + n_proto_key = ntohs(key->n_proto); + n_proto_mask = ntohs(mask->n_proto); + + if (n_proto_key == ETH_P_ALL) { + n_proto_key = 0; + n_proto_mask = 0; + } + filter->n_proto = n_proto_key & n_proto_mask; + filter->ip_proto = key->ip_proto; + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_dissector_key_eth_addrs *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ETH_ADDRS, + f->key); + + struct flow_dissector_key_eth_addrs *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ETH_ADDRS, + f->mask); + + /* use is_broadcast and is_zero to check for all 0xf or 0 */ + if (!is_zero_ether_addr(mask->dst)) { + if (is_broadcast_ether_addr(mask->dst)) { + field_flags |= I40E_CLOUD_FIELD_OMAC; + } else { + dev_err(&pf->pdev->dev, "Bad ether dest mask %pM\n", + mask->dst); + return I40E_ERR_CONFIG; + } + } + + if (!is_zero_ether_addr(mask->src)) { + if (is_broadcast_ether_addr(mask->src)) { + field_flags |= I40E_CLOUD_FIELD_IMAC; + } else { + dev_err(&pf->pdev->dev, "Bad ether src mask %pM\n", + mask->src); + return I40E_ERR_CONFIG; + } + } + ether_addr_copy(filter->dst_mac, key->dst); + ether_addr_copy(filter->src_mac, key->src); + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_dissector_key_vlan *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_VLAN, + f->key); + struct flow_dissector_key_vlan *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_VLAN, + f->mask); + + if (mask->vlan_id) { + if (mask->vlan_id == VLAN_VID_MASK) { + field_flags |= I40E_CLOUD_FIELD_IVLAN; + + } else { + dev_err(&pf->pdev->dev, "Bad vlan mask 0x%04x\n", + mask->vlan_id); + return I40E_ERR_CONFIG; + } + } + + filter->vlan_id = cpu_to_be16(key->vlan_id); + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_dissector_key_control *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_CONTROL, + f->key); + + addr_type = key->addr_type; + } + + if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + struct flow_dissector_key_ipv4_addrs *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS, + f->key); + struct flow_dissector_key_ipv4_addrs *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS, + f->mask); + + if (mask->dst) { + if (mask->dst == cpu_to_be32(0xffffffff)) { + field_flags |= I40E_CLOUD_FIELD_IIP; + } else { + mask->dst = be32_to_cpu(mask->dst); + dev_err(&pf->pdev->dev, "Bad ip dst mask %pI4\n", + &mask->dst); + return I40E_ERR_CONFIG; + } + } + + if (mask->src) { + if (mask->src == cpu_to_be32(0xffffffff)) { + field_flags |= I40E_CLOUD_FIELD_IIP; + } else { + mask->src = be32_to_cpu(mask->src); + dev_err(&pf->pdev->dev, "Bad ip src mask %pI4\n", + &mask->src); + return I40E_ERR_CONFIG; + } + } + + if (field_flags & I40E_CLOUD_FIELD_TEN_ID) { + dev_err(&pf->pdev->dev, "Tenant id not allowed for ip filter\n"); + return I40E_ERR_CONFIG; + } + filter->dst_ipv4 = key->dst; + filter->src_ipv4 = key->src; + } + + if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + struct flow_dissector_key_ipv6_addrs *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS, + f->key); + struct flow_dissector_key_ipv6_addrs *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS, + f->mask); + + /* src and dest IPV6 address should not be LOOPBACK + * (0:0:0:0:0:0:0:1), which can be represented as ::1 + */ + if (ipv6_addr_loopback(&key->dst) || + ipv6_addr_loopback(&key->src)) { + dev_err(&pf->pdev->dev, + "Bad ipv6, addr is LOOPBACK\n"); + return I40E_ERR_CONFIG; + } + if (!ipv6_addr_any(&mask->dst) || !ipv6_addr_any(&mask->src)) + field_flags |= I40E_CLOUD_FIELD_IIP; + + memcpy(&filter->src_ipv6, &key->src.s6_addr32, + sizeof(filter->src_ipv6)); + memcpy(&filter->dst_ipv6, &key->dst.s6_addr32, + sizeof(filter->dst_ipv6)); + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_dissector_key_ports *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_PORTS, + f->key); + struct flow_dissector_key_ports *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_PORTS, + f->mask); + + if (mask->src) { + if (mask->src == cpu_to_be16(0xffff)) { + field_flags |= I40E_CLOUD_FIELD_IIP; + } else { + dev_err(&pf->pdev->dev, "Bad src port mask 0x%04x\n", + be16_to_cpu(mask->src)); + return I40E_ERR_CONFIG; + } + } + + if (mask->dst) { + if (mask->dst == cpu_to_be16(0xffff)) { + field_flags |= I40E_CLOUD_FIELD_IIP; + } else { + dev_err(&pf->pdev->dev, "Bad dst port mask 0x%04x\n", + be16_to_cpu(mask->dst)); + return I40E_ERR_CONFIG; + } + } + + filter->dst_port = key->dst; + filter->src_port = key->src; + + switch (filter->ip_proto) { + case IPPROTO_TCP: + case IPPROTO_UDP: + break; + default: + dev_err(&pf->pdev->dev, + "Only UDP and TCP transport are supported\n"); + return -EINVAL; + } + } + filter->flags = field_flags; + return 0; +} + +/** + * i40e_handle_tclass: Forward to a traffic class on the device + * @vsi: Pointer to VSI + * @tc: traffic class index on the device + * @filter: Pointer to cloud filter structure + * + **/ +static int i40e_handle_tclass(struct i40e_vsi *vsi, u32 tc, + struct i40e_cloud_filter *filter) +{ + struct i40e_channel *ch, *ch_tmp; + + /* direct to a traffic class on the same device */ + if (tc == 0) { + filter->seid = vsi->seid; + return 0; + } else if (vsi->tc_config.enabled_tc & BIT(tc)) { + if (!filter->dst_port) { + dev_err(&vsi->back->pdev->dev, + "Specify destination port to direct to traffic class that is not default\n"); + return -EINVAL; + } + if (list_empty(&vsi->ch_list)) + return -EINVAL; + list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, + list) { + if (ch->seid == vsi->tc_seid_map[tc]) + filter->seid = ch->seid; + } + return 0; + } + dev_err(&vsi->back->pdev->dev, "TC is not enabled\n"); + return -EINVAL; +} + +/** + * i40e_configure_clsflower - Configure tc flower filters + * @vsi: Pointer to VSI + * @cls_flower: Pointer to struct tc_cls_flower_offload + * + **/ +static int i40e_configure_clsflower(struct i40e_vsi *vsi, + struct tc_cls_flower_offload *cls_flower) +{ + int tc = tc_classid_to_hwtc(vsi->netdev, cls_flower->classid); + struct i40e_cloud_filter *filter = NULL; + struct i40e_pf *pf = vsi->back; + int err = 0; + + if (tc < 0) { + dev_err(&vsi->back->pdev->dev, "Invalid traffic class\n"); + return -EINVAL; + } + + if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state) || + test_bit(__I40E_RESET_INTR_RECEIVED, pf->state)) + return -EBUSY; + + if (pf->fdir_pf_active_filters || + (!hlist_empty(&pf->fdir_filter_list))) { + dev_err(&vsi->back->pdev->dev, + "Flow Director Sideband filters exists, turn ntuple off to configure cloud filters\n"); + return -EINVAL; + } + + if (vsi->back->flags & I40E_FLAG_FD_SB_ENABLED) { + dev_err(&vsi->back->pdev->dev, + "Disable Flow Director Sideband, configuring Cloud filters via tc-flower\n"); + vsi->back->flags &= ~I40E_FLAG_FD_SB_ENABLED; + vsi->back->flags |= I40E_FLAG_FD_SB_TO_CLOUD_FILTER; + } + + filter = kzalloc(sizeof(*filter), GFP_KERNEL); + if (!filter) + return -ENOMEM; + + filter->cookie = cls_flower->cookie; + + err = i40e_parse_cls_flower(vsi, cls_flower, filter); + if (err < 0) + goto err; + + err = i40e_handle_tclass(vsi, tc, filter); + if (err < 0) + goto err; + + /* Add cloud filter */ + if (filter->dst_port) + err = i40e_add_del_cloud_filter_big_buf(vsi, filter, true); + else + err = i40e_add_del_cloud_filter(vsi, filter, true); + + if (err) { + dev_err(&pf->pdev->dev, + "Failed to add cloud filter, err %s\n", + i40e_stat_str(&pf->hw, err)); + err = i40e_aq_rc_to_posix(err, pf->hw.aq.asq_last_status); + goto err; + } + + /* add filter to the ordered list */ + INIT_HLIST_NODE(&filter->cloud_node); + + hlist_add_head(&filter->cloud_node, &pf->cloud_filter_list); + + pf->num_cloud_filters++; + + return err; +err: + kfree(filter); + return err; +} + +/** + * i40e_find_cloud_filter - Find the could filter in the list + * @vsi: Pointer to VSI + * @cookie: filter specific cookie + * + **/ +static struct i40e_cloud_filter *i40e_find_cloud_filter(struct i40e_vsi *vsi, + unsigned long *cookie) +{ + struct i40e_cloud_filter *filter = NULL; + struct hlist_node *node2; + + hlist_for_each_entry_safe(filter, node2, + &vsi->back->cloud_filter_list, cloud_node) + if (!memcmp(cookie, &filter->cookie, sizeof(filter->cookie))) + return filter; + return NULL; +} + +/** + * i40e_delete_clsflower - Remove tc flower filters + * @vsi: Pointer to VSI + * @cls_flower: Pointer to struct tc_cls_flower_offload + * + **/ +static int i40e_delete_clsflower(struct i40e_vsi *vsi, + struct tc_cls_flower_offload *cls_flower) +{ + struct i40e_cloud_filter *filter = NULL; + struct i40e_pf *pf = vsi->back; + int err = 0; + + filter = i40e_find_cloud_filter(vsi, &cls_flower->cookie); + + if (!filter) + return -EINVAL; + + hash_del(&filter->cloud_node); + + if (filter->dst_port) + err = i40e_add_del_cloud_filter_big_buf(vsi, filter, false); + else + err = i40e_add_del_cloud_filter(vsi, filter, false); + + kfree(filter); + if (err) { + dev_err(&pf->pdev->dev, + "Failed to delete cloud filter, err %s\n", + i40e_stat_str(&pf->hw, err)); + return i40e_aq_rc_to_posix(err, pf->hw.aq.asq_last_status); + } + + pf->num_cloud_filters--; + if (!pf->num_cloud_filters) + if ((pf->flags & I40E_FLAG_FD_SB_TO_CLOUD_FILTER) && + !(pf->flags & I40E_FLAG_FD_SB_INACTIVE)) { + pf->flags |= I40E_FLAG_FD_SB_ENABLED; + pf->flags &= ~I40E_FLAG_FD_SB_TO_CLOUD_FILTER; + pf->flags &= ~I40E_FLAG_FD_SB_INACTIVE; + } + return 0; +} + +/** + * i40e_setup_tc_cls_flower - flower classifier offloads + * @netdev: net device to configure + * @type_data: offload data + **/ +static int i40e_setup_tc_cls_flower(struct i40e_netdev_priv *np, + struct tc_cls_flower_offload *cls_flower) +{ + struct i40e_vsi *vsi = np->vsi; + + if (cls_flower->common.chain_index) + return -EOPNOTSUPP; + + switch (cls_flower->command) { + case TC_CLSFLOWER_REPLACE: + return i40e_configure_clsflower(vsi, cls_flower); + case TC_CLSFLOWER_DESTROY: + return i40e_delete_clsflower(vsi, cls_flower); + case TC_CLSFLOWER_STATS: + return -EOPNOTSUPP; + default: + return -EINVAL; + } +} + +static int i40e_setup_tc_block_cb(enum tc_setup_type type, void *type_data, + void *cb_priv) +{ + struct i40e_netdev_priv *np = cb_priv; + + switch (type) { + case TC_SETUP_CLSFLOWER: + return i40e_setup_tc_cls_flower(np, type_data); + + default: + return -EOPNOTSUPP; + } +} + +static int i40e_setup_tc_block(struct net_device *dev, + struct tc_block_offload *f) +{ + struct i40e_netdev_priv *np = netdev_priv(dev); + + if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) + return -EOPNOTSUPP; + + switch (f->command) { + case TC_BLOCK_BIND: + return tcf_block_cb_register(f->block, i40e_setup_tc_block_cb, + np, np); + case TC_BLOCK_UNBIND: + tcf_block_cb_unregister(f->block, i40e_setup_tc_block_cb, np); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int __i40e_setup_tc(struct net_device *netdev, enum tc_setup_type type, + void *type_data) +{ + switch (type) { + case TC_SETUP_QDISC_MQPRIO: + return i40e_setup_tc(netdev, type_data); + case TC_SETUP_BLOCK: + return i40e_setup_tc_block(netdev, type_data); + default: + return -EOPNOTSUPP; + } } /** @@ -5747,7 +7674,7 @@ 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; } @@ -5810,6 +7737,33 @@ static void i40e_fdir_filter_exit(struct i40e_pf *pf) } /** + * i40e_cloud_filter_exit - Cleans up the cloud filters + * @pf: Pointer to PF + * + * This function destroys the hlist where all the cloud filters + * were saved. + **/ +static void i40e_cloud_filter_exit(struct i40e_pf *pf) +{ + struct i40e_cloud_filter *cfilter; + struct hlist_node *node; + + hlist_for_each_entry_safe(cfilter, node, + &pf->cloud_filter_list, cloud_node) { + hlist_del(&cfilter->cloud_node); + kfree(cfilter); + } + pf->num_cloud_filters = 0; + + if ((pf->flags & I40E_FLAG_FD_SB_TO_CLOUD_FILTER) && + !(pf->flags & I40E_FLAG_FD_SB_INACTIVE)) { + pf->flags |= I40E_FLAG_FD_SB_ENABLED; + pf->flags &= ~I40E_FLAG_FD_SB_TO_CLOUD_FILTER; + pf->flags &= ~I40E_FLAG_FD_SB_INACTIVE; + } +} + +/** * i40e_close - Disables a network interface * @netdev: network interface device structure * @@ -5875,7 +7829,7 @@ 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 * @@ -6226,6 +8180,7 @@ 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; } } } @@ -6429,8 +8384,7 @@ static void i40e_link_event(struct i40e_pf *pf) new_link == netif_carrier_ok(vsi->netdev))) return; - if (!test_bit(__I40E_VSI_DOWN, vsi->state)) - i40e_print_link_message(vsi, new_link); + i40e_print_link_message(vsi, new_link); /* Notify the base of the switch tree connected to * the link. Floating VEBs are not notified. @@ -6553,12 +8507,26 @@ 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, + "Rx/Tx is disabled on this device because the module does not meet thermal requirements.\n"); dev_err(&pf->pdev->dev, - "The driver failed to link because an unqualified module was detected.\n"); + "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"); + } + } } /** @@ -6900,7 +8868,8 @@ end_reconstitute: * i40e_get_capabilities - get info about the HW * @pf: the PF struct **/ -static int i40e_get_capabilities(struct i40e_pf *pf) +static int i40e_get_capabilities(struct i40e_pf *pf, + enum i40e_admin_queue_opc list_type) { struct i40e_aqc_list_capabilities_element_resp *cap_buf; u16 data_size; @@ -6915,9 +8884,8 @@ static int i40e_get_capabilities(struct i40e_pf *pf) /* this loads the data into the hw struct for us */ err = i40e_aq_discover_capabilities(&pf->hw, cap_buf, buf_len, - &data_size, - i40e_aqc_opc_list_func_capabilities, - NULL); + &data_size, list_type, + NULL); /* data loaded, buffer no longer needed */ kfree(cap_buf); @@ -6934,26 +8902,44 @@ static int i40e_get_capabilities(struct i40e_pf *pf) } } while (err); - if (pf->hw.debug_mask & I40E_DEBUG_USER) - dev_info(&pf->pdev->dev, - "pf=%d, num_vfs=%d, msix_pf=%d, msix_vf=%d, fd_g=%d, fd_b=%d, pf_max_q=%d num_vsi=%d\n", - pf->hw.pf_id, pf->hw.func_caps.num_vfs, - pf->hw.func_caps.num_msix_vectors, - pf->hw.func_caps.num_msix_vectors_vf, - pf->hw.func_caps.fd_filters_guaranteed, - pf->hw.func_caps.fd_filters_best_effort, - pf->hw.func_caps.num_tx_qp, - pf->hw.func_caps.num_vsis); - + if (pf->hw.debug_mask & I40E_DEBUG_USER) { + if (list_type == i40e_aqc_opc_list_func_capabilities) { + dev_info(&pf->pdev->dev, + "pf=%d, num_vfs=%d, msix_pf=%d, msix_vf=%d, fd_g=%d, fd_b=%d, pf_max_q=%d num_vsi=%d\n", + pf->hw.pf_id, pf->hw.func_caps.num_vfs, + pf->hw.func_caps.num_msix_vectors, + pf->hw.func_caps.num_msix_vectors_vf, + pf->hw.func_caps.fd_filters_guaranteed, + pf->hw.func_caps.fd_filters_best_effort, + pf->hw.func_caps.num_tx_qp, + pf->hw.func_caps.num_vsis); + } else if (list_type == i40e_aqc_opc_list_dev_capabilities) { + dev_info(&pf->pdev->dev, + "switch_mode=0x%04x, function_valid=0x%08x\n", + pf->hw.dev_caps.switch_mode, + pf->hw.dev_caps.valid_functions); + dev_info(&pf->pdev->dev, + "SR-IOV=%d, num_vfs for all function=%u\n", + pf->hw.dev_caps.sr_iov_1_1, + pf->hw.dev_caps.num_vfs); + dev_info(&pf->pdev->dev, + "num_vsis=%u, num_rx:%u, num_tx=%u\n", + pf->hw.dev_caps.num_vsis, + pf->hw.dev_caps.num_rx_qp, + pf->hw.dev_caps.num_tx_qp); + } + } + if (list_type == i40e_aqc_opc_list_func_capabilities) { #define DEF_NUM_VSI (1 + (pf->hw.func_caps.fcoe ? 1 : 0) \ + pf->hw.func_caps.num_vfs) - if (pf->hw.revision_id == 0 && (DEF_NUM_VSI > pf->hw.func_caps.num_vsis)) { - dev_info(&pf->pdev->dev, - "got num_vsis %d, setting num_vsis to %d\n", - pf->hw.func_caps.num_vsis, DEF_NUM_VSI); - pf->hw.func_caps.num_vsis = DEF_NUM_VSI; + if (pf->hw.revision_id == 0 && + pf->hw.func_caps.num_vsis < DEF_NUM_VSI) { + dev_info(&pf->pdev->dev, + "got num_vsis %d, setting num_vsis to %d\n", + pf->hw.func_caps.num_vsis, DEF_NUM_VSI); + pf->hw.func_caps.num_vsis = DEF_NUM_VSI; + } } - return 0; } @@ -6995,6 +8981,7 @@ static void i40e_fdir_sb_setup(struct i40e_pf *pf) if (!vsi) { dev_info(&pf->pdev->dev, "Couldn't create FDir VSI\n"); pf->flags &= ~I40E_FLAG_FD_SB_ENABLED; + pf->flags |= I40E_FLAG_FD_SB_INACTIVE; return; } } @@ -7017,6 +9004,95 @@ static void i40e_fdir_teardown(struct i40e_pf *pf) } /** + * i40e_rebuild_cloud_filters - Rebuilds cloud filters for VSIs + * @vsi: PF main vsi + * @seid: seid of main or channel VSIs + * + * Rebuilds cloud filters associated with main VSI and channel VSIs if they + * existed before reset + **/ +static int i40e_rebuild_cloud_filters(struct i40e_vsi *vsi, u16 seid) +{ + struct i40e_cloud_filter *cfilter; + struct i40e_pf *pf = vsi->back; + struct hlist_node *node; + i40e_status ret; + + /* Add cloud filters back if they exist */ + hlist_for_each_entry_safe(cfilter, node, &pf->cloud_filter_list, + cloud_node) { + if (cfilter->seid != seid) + continue; + + if (cfilter->dst_port) + ret = i40e_add_del_cloud_filter_big_buf(vsi, cfilter, + true); + else + ret = i40e_add_del_cloud_filter(vsi, cfilter, true); + + if (ret) { + dev_dbg(&pf->pdev->dev, + "Failed to rebuild cloud filter, err %s aq_err %s\n", + i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, + pf->hw.aq.asq_last_status)); + return ret; + } + } + return 0; +} + +/** + * 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); + } + ret = i40e_rebuild_cloud_filters(vsi, ch->seid); + if (ret) { + dev_dbg(&vsi->back->pdev->dev, + "Failed to rebuild cloud filters for channel VSI %u\n", + ch->seid); + return ret; + } + } + 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 @@ -7152,6 +9228,7 @@ 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; @@ -7177,7 +9254,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) i40e_verify_eeprom(pf); i40e_clear_pxe_mode(hw); - ret = i40e_get_capabilities(pf); + ret = i40e_get_capabilities(pf, i40e_aqc_opc_list_func_capabilities); if (ret) goto end_core_reset; @@ -7234,7 +9311,7 @@ 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++) { @@ -7258,8 +9335,7 @@ 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, @@ -7270,10 +9346,10 @@ 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); @@ -7281,6 +9357,35 @@ 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); + } + + ret = i40e_rebuild_cloud_filters(vsi, vsi->seid); + if (ret) + goto end_unlock; + + /* 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. @@ -7615,9 +9720,9 @@ 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)); @@ -7674,7 +9779,7 @@ 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) @@ -8139,7 +10244,7 @@ static int i40e_init_msix(struct i40e_pf *pf) pf->num_lan_qps = 1; pf->num_lan_msix = 1; - } else if (!vectors_left) { + } else if (v_actual != v_budget) { /* If we have limited resources, we will start with no vectors * for the special features and then allocate vectors to some * of these features based on the policy and at the end disable @@ -8148,7 +10253,8 @@ static int i40e_init_msix(struct i40e_pf *pf) int vec; dev_info(&pf->pdev->dev, - "MSI-X vector limit reached, attempting to redistribute vectors\n"); + "MSI-X vector limit reached with %d, wanted %d, attempting to redistribute vectors\n", + v_actual, v_budget); /* reserve the misc vector */ vec = v_actual - 1; @@ -8196,6 +10302,7 @@ static int i40e_init_msix(struct i40e_pf *pf) (pf->num_fdsb_msix == 0)) { dev_info(&pf->pdev->dev, "Sideband Flowdir disabled, not enough MSI-X vectors\n"); pf->flags &= ~I40E_FLAG_FD_SB_ENABLED; + pf->flags |= I40E_FLAG_FD_SB_INACTIVE; } if ((pf->flags & I40E_FLAG_VMDQ_ENABLED) && (pf->num_vmdq_msix == 0)) { @@ -8313,6 +10420,7 @@ static int i40e_init_interrupt_scheme(struct i40e_pf *pf) I40E_FLAG_FD_SB_ENABLED | I40E_FLAG_FD_ATR_ENABLED | I40E_FLAG_VMDQ_ENABLED); + pf->flags |= I40E_FLAG_FD_SB_INACTIVE; /* rework the queue expectations without MSIX */ i40e_determine_queue_usage(pf); @@ -8351,6 +10459,55 @@ static int i40e_init_interrupt_scheme(struct i40e_pf *pf) } /** + * i40e_restore_interrupt_scheme - Restore the interrupt scheme + * @pf: private board data structure + * + * Restore the interrupt scheme that was cleared when we suspended the + * device. This should be called during resume to re-allocate the q_vectors + * and reacquire IRQs. + */ +static int i40e_restore_interrupt_scheme(struct i40e_pf *pf) +{ + int err, i; + + /* We cleared the MSI and MSI-X flags when disabling the old interrupt + * scheme. We need to re-enabled them here in order to attempt to + * re-acquire the MSI or MSI-X vectors + */ + pf->flags |= (I40E_FLAG_MSIX_ENABLED | I40E_FLAG_MSI_ENABLED); + + err = i40e_init_interrupt_scheme(pf); + if (err) + return err; + + /* Now that we've re-acquired IRQs, we need to remap the vectors and + * rings together again. + */ + for (i = 0; i < pf->num_alloc_vsi; i++) { + if (pf->vsi[i]) { + err = i40e_vsi_alloc_q_vectors(pf->vsi[i]); + if (err) + goto err_unwind; + i40e_vsi_map_rings_to_vectors(pf->vsi[i]); + } + } + + err = i40e_setup_misc_vector(pf); + if (err) + goto err_unwind; + + return 0; + +err_unwind: + while (i--) { + if (pf->vsi[i]) + i40e_vsi_free_q_vectors(pf->vsi[i]); + } + + return err; +} + +/** * i40e_setup_misc_vector - Setup the misc vector to handle non queue events * @pf: board private structure * @@ -8363,13 +10520,12 @@ static int i40e_setup_misc_vector(struct i40e_pf *pf) struct i40e_hw *hw = &pf->hw; int err = 0; - /* Only request the irq if this is the first time through, and - * not when we're rebuilding after a Reset - */ - if (!test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) { + /* Only request the IRQ once, the first time through. */ + if (!test_and_set_bit(__I40E_MISC_IRQ_REQUESTED, pf->state)) { err = request_irq(pf->msix_entries[0].vector, i40e_intr, 0, pf->int_name, pf); if (err) { + clear_bit(__I40E_MISC_IRQ_REQUESTED, pf->state); dev_info(&pf->pdev->dev, "request_irq for %s failed: %d\n", pf->int_name, err); @@ -8385,51 +10541,12 @@ 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 @@ -8476,46 +10593,6 @@ 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 @@ -8913,8 +10990,8 @@ 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 @@ -9014,6 +11091,11 @@ 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; @@ -9079,9 +11161,13 @@ bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features) /* Enable filters and mark for reset */ if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED)) need_reset = true; - /* enable FD_SB only if there is MSI-X vector */ - if (pf->num_fdsb_msix > 0) + /* enable FD_SB only if there is MSI-X vector and no cloud + * filters exist + */ + if (pf->num_fdsb_msix > 0 && !pf->num_cloud_filters) { pf->flags |= I40E_FLAG_FD_SB_ENABLED; + pf->flags &= ~I40E_FLAG_FD_SB_INACTIVE; + } } else { /* turn off filters, mark for reset and clear SW filter list */ if (pf->flags & I40E_FLAG_FD_SB_ENABLED) { @@ -9090,6 +11176,8 @@ bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features) } pf->flags &= ~(I40E_FLAG_FD_SB_ENABLED | I40E_FLAG_FD_SB_AUTO_DISABLED); + pf->flags |= I40E_FLAG_FD_SB_INACTIVE; + /* reset fd counters */ pf->fd_add_err = 0; pf->fd_atr_cnt = 0; @@ -9151,10 +11239,16 @@ static int i40e_set_features(struct net_device *netdev, else i40e_vlan_stripping_disable(vsi); + if (!(features & NETIF_F_HW_TC) && pf->num_cloud_filters) { + dev_err(&pf->pdev->dev, + "Offloaded tc filters active, can't turn hw_tc_offload off"); + return -EINVAL; + } + 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; } @@ -9406,8 +11500,7 @@ 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; } } @@ -9555,12 +11648,12 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, } /** - * i40e_xdp - implements ndo_xdp for i40e + * i40e_xdp - implements ndo_bpf for i40e * @dev: netdevice * @xdp: XDP command **/ static int i40e_xdp(struct net_device *dev, - struct netdev_xdp *xdp) + struct netdev_bpf *xdp) { struct i40e_netdev_priv *np = netdev_priv(dev); struct i40e_vsi *vsi = np->vsi; @@ -9612,7 +11705,7 @@ static const struct net_device_ops i40e_netdev_ops = { .ndo_features_check = i40e_features_check, .ndo_bridge_getlink = i40e_ndo_bridge_getlink, .ndo_bridge_setlink = i40e_ndo_bridge_setlink, - .ndo_xdp = i40e_xdp, + .ndo_bpf = i40e_xdp, }; /** @@ -9671,7 +11764,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) netdev->vlan_features |= hw_enc_features | NETIF_F_TSO_MANGLEID; if (!(pf->flags & I40E_FLAG_MFP_ENABLED)) - netdev->hw_features |= NETIF_F_NTUPLE; + netdev->hw_features |= NETIF_F_NTUPLE | NETIF_F_HW_TC; + hw_features = hw_enc_features | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; @@ -9849,6 +11943,31 @@ 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 */ @@ -10951,14 +13070,16 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit) */ if ((pf->hw.pf_id == 0) && - !(pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT)) + !(pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT)) { flags = I40E_AQ_SET_SWITCH_CFG_PROMISC; + pf->last_sw_conf_flags = flags; + } if (pf->hw.pf_id == 0) { u16 valid_flags; valid_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC; - ret = i40e_aq_set_switch_config(&pf->hw, flags, valid_flags, + ret = i40e_aq_set_switch_config(&pf->hw, flags, valid_flags, 0, NULL); if (ret && pf->hw.aq.asq_last_status != I40E_AQ_RC_ESRCH) { dev_info(&pf->pdev->dev, @@ -10968,6 +13089,7 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit) pf->hw.aq.asq_last_status)); /* not a fatal problem, just keep going */ } + pf->last_sw_conf_valid_flags = valid_flags; } /* first time setup */ @@ -10988,6 +13110,7 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit) vsi = i40e_vsi_reinit_setup(pf->vsi[pf->lan_vsi]); if (!vsi) { dev_info(&pf->pdev->dev, "setup of MAIN VSI failed\n"); + i40e_cloud_filter_exit(pf); i40e_fdir_teardown(pf); return -EAGAIN; } @@ -11039,6 +13162,7 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit) static void i40e_determine_queue_usage(struct i40e_pf *pf) { int queues_left; + int q_max; pf->num_lan_qps = 0; @@ -11063,6 +13187,7 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf) I40E_FLAG_DCB_ENABLED | I40E_FLAG_SRIOV_ENABLED | I40E_FLAG_VMDQ_ENABLED); + pf->flags |= I40E_FLAG_FD_SB_INACTIVE; } else if (!(pf->flags & (I40E_FLAG_RSS_ENABLED | I40E_FLAG_FD_SB_ENABLED | I40E_FLAG_FD_ATR_ENABLED | @@ -11077,6 +13202,7 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf) I40E_FLAG_FD_ATR_ENABLED | I40E_FLAG_DCB_ENABLED | I40E_FLAG_VMDQ_ENABLED); + pf->flags |= I40E_FLAG_FD_SB_INACTIVE; } else { /* Not enough queues for all TCs */ if ((pf->flags & I40E_FLAG_DCB_CAPABLE) && @@ -11085,10 +13211,12 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf) I40E_FLAG_DCB_ENABLED); dev_info(&pf->pdev->dev, "not enough queues for DCB. DCB is disabled.\n"); } - pf->num_lan_qps = max_t(int, pf->rss_size_max, - num_online_cpus()); - pf->num_lan_qps = min_t(int, pf->num_lan_qps, - pf->hw.func_caps.num_tx_qp); + + /* limit lan qps to the smaller of qps, cpus or msix */ + q_max = max_t(int, pf->rss_size_max, num_online_cpus()); + q_max = min_t(int, q_max, pf->hw.func_caps.num_tx_qp); + q_max = min_t(int, q_max, pf->hw.func_caps.num_msix_vectors); + pf->num_lan_qps = q_max; queues_left -= pf->num_lan_qps; } @@ -11098,6 +13226,7 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf) queues_left -= 1; /* save 1 queue for FD */ } else { pf->flags &= ~I40E_FLAG_FD_SB_ENABLED; + pf->flags |= I40E_FLAG_FD_SB_INACTIVE; dev_info(&pf->pdev->dev, "not enough queues for Flow Director. Flow Director feature is disabled\n"); } } @@ -11304,6 +13433,13 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->bus.bus_id = pdev->bus->number; pf->instance = pfs_found; + /* Select something other than the 802.1ad ethertype for the + * switch to use internally and drop on ingress. + */ + hw->switch_tag = 0xffff; + hw->first_tag = ETH_P_8021AD; + hw->second_tag = ETH_P_8021Q; + INIT_LIST_HEAD(&pf->l3_flex_pit_list); INIT_LIST_HEAD(&pf->l4_flex_pit_list); @@ -11380,11 +13516,10 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) i40e_nvm_version_str(hw)); if (hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR && - hw->aq.api_min_ver > I40E_FW_API_VERSION_MINOR) + hw->aq.api_min_ver > I40E_FW_MINOR_VERSION(hw)) dev_info(&pdev->dev, "The driver for the device detected a newer version of the NVM image than expected. Please install the most recent version of the network driver.\n"); - else if (hw->aq.api_maj_ver < I40E_FW_API_VERSION_MAJOR || - hw->aq.api_min_ver < (I40E_FW_API_VERSION_MINOR - 1)) + else if (hw->aq.api_maj_ver == 1 && hw->aq.api_min_ver < 4) dev_info(&pdev->dev, "The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n"); @@ -11395,7 +13530,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_warn(&pdev->dev, "This device is a pre-production adapter/LOM. Please be aware there may be issues with your hardware. If you are experiencing problems please contact your Intel or hardware representative who provided you with this hardware.\n"); i40e_clear_pxe_mode(hw); - err = i40e_get_capabilities(pf); + err = i40e_get_capabilities(pf, i40e_aqc_opc_list_func_capabilities); if (err) goto err_adminq_setup; @@ -11454,7 +13589,7 @@ 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); @@ -11506,6 +13641,7 @@ 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); @@ -11777,7 +13913,7 @@ 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); @@ -11812,6 +13948,8 @@ static void i40e_remove(struct pci_dev *pdev) if (pf->vsi[pf->lan_vsi]) i40e_vsi_release(pf->vsi[pf->lan_vsi]); + i40e_cloud_filter_exit(pf); + /* remove attached clients */ if (pf->flags & I40E_FLAG_IWARP_ENABLED) { ret_code = i40e_lan_del_device(pf); @@ -11937,6 +14075,28 @@ 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 * @@ -12021,6 +14181,7 @@ static void i40e_shutdown(struct pci_dev *pdev) del_timer_sync(&pf->service_timer); cancel_work_sync(&pf->service_task); + i40e_cloud_filter_exit(pf); i40e_fdir_teardown(pf); /* Client close must be called explicitly here because the timer @@ -12046,20 +14207,26 @@ static void i40e_shutdown(struct pci_dev *pdev) } } -#ifdef CONFIG_PM /** - * i40e_suspend - PCI callback for moving to D3 - * @pdev: PCI device information struct + * i40e_suspend - PM callback for moving to D3 + * @dev: generic device information structure **/ -static int i40e_suspend(struct pci_dev *pdev, pm_message_t state) +static int __maybe_unused i40e_suspend(struct device *dev) { + struct pci_dev *pdev = to_pci_dev(dev); struct i40e_pf *pf = pci_get_drvdata(pdev); struct i40e_hw *hw = &pf->hw; - int retval = 0; - set_bit(__I40E_SUSPENDED, pf->state); + /* If we're already suspended, then there is nothing to do */ + if (test_and_set_bit(__I40E_SUSPENDED, pf->state)) + return 0; + set_bit(__I40E_DOWN, pf->state); + /* Ensure service task will not be running */ + del_timer_sync(&pf->service_timer); + cancel_work_sync(&pf->service_task); + if (pf->wol_en && (pf->hw_features & I40E_HW_WOL_MC_MAGIC_PKT_WAKE)) i40e_enable_mc_magic_wake(pf); @@ -12068,81 +14235,70 @@ static int i40e_suspend(struct pci_dev *pdev, pm_message_t state) wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0)); wr32(hw, I40E_PFPM_WUFC, (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0)); - i40e_stop_misc_vector(pf); - if (pf->msix_entries) { - synchronize_irq(pf->msix_entries[0].vector); - free_irq(pf->msix_entries[0].vector, pf); - } - retval = pci_save_state(pdev); - if (retval) - return retval; - - pci_wake_from_d3(pdev, pf->wol_en); - pci_set_power_state(pdev, PCI_D3hot); + /* Clear the interrupt scheme and release our IRQs so that the system + * can safely hibernate even when there are a large number of CPUs. + * Otherwise hibernation might fail when mapping all the vectors back + * to CPU0. + */ + i40e_clear_interrupt_scheme(pf); - return retval; + return 0; } /** - * i40e_resume - PCI callback for waking up from D3 - * @pdev: PCI device information struct + * i40e_resume - PM callback for waking up from D3 + * @dev: generic device information structure **/ -static int i40e_resume(struct pci_dev *pdev) +static int __maybe_unused i40e_resume(struct device *dev) { + struct pci_dev *pdev = to_pci_dev(dev); struct i40e_pf *pf = pci_get_drvdata(pdev); - u32 err; + int err; - pci_set_power_state(pdev, PCI_D0); - pci_restore_state(pdev); - /* pci_restore_state() clears dev->state_saves, so - * call pci_save_state() again to restore it. - */ - pci_save_state(pdev); + /* If we're not suspended, then there is nothing to do */ + if (!test_bit(__I40E_SUSPENDED, pf->state)) + return 0; - err = pci_enable_device_mem(pdev); + /* We cleared the interrupt scheme when we suspended, so we need to + * restore it now to resume device functionality. + */ + err = i40e_restore_interrupt_scheme(pf); if (err) { - dev_err(&pdev->dev, "Cannot enable PCI device from suspend\n"); - return err; + dev_err(&pdev->dev, "Cannot restore interrupt scheme: %d\n", + err); } - pci_set_master(pdev); - /* no wakeup events while running */ - pci_wake_from_d3(pdev, false); - - /* handling the reset will rebuild the device state */ - if (test_and_clear_bit(__I40E_SUSPENDED, pf->state)) { - clear_bit(__I40E_DOWN, pf->state); - if (pf->msix_entries) { - err = request_irq(pf->msix_entries[0].vector, - i40e_intr, 0, pf->int_name, pf); - if (err) { - dev_err(&pf->pdev->dev, - "request_irq for %s failed: %d\n", - pf->int_name, err); - } - } - i40e_reset_and_rebuild(pf, false, false); - } + clear_bit(__I40E_DOWN, pf->state); + i40e_reset_and_rebuild(pf, false, false); + + /* Clear suspended state last after everything is recovered */ + clear_bit(__I40E_SUSPENDED, pf->state); + + /* Restart the service task */ + mod_timer(&pf->service_timer, + round_jiffies(jiffies + pf->service_timer_period)); return 0; } -#endif 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, }; +static SIMPLE_DEV_PM_OPS(i40e_pm_ops, i40e_suspend, i40e_resume); + static struct pci_driver i40e_driver = { .name = i40e_driver_name, .id_table = i40e_pci_tbl, .probe = i40e_probe, .remove = i40e_remove, -#ifdef CONFIG_PM - .suspend = i40e_suspend, - .resume = i40e_resume, -#endif + .driver = { + .pm = &i40e_pm_ops, + }, .shutdown = i40e_shutdown, .err_handler = &i40e_err_handler, .sriov_configure = i40e_pci_sriov_configure, diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c index d591b3e6bd7c..0ccab0a5d717 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_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index a39b13197891..3bb6659db822 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -190,7 +190,7 @@ i40e_status i40e_aq_get_switch_config(struct i40e_hw *hw, struct i40e_asq_cmd_details *cmd_details); enum i40e_status_code i40e_aq_set_switch_config(struct i40e_hw *hw, u16 flags, - u16 valid_flags, + u16 valid_flags, u8 mode, struct i40e_asq_cmd_details *cmd_details); i40e_status i40e_aq_request_resource(struct i40e_hw *hw, enum i40e_aq_resources_ids resource, @@ -283,6 +283,22 @@ i40e_status i40e_aq_query_switch_comp_bw_config(struct i40e_hw *hw, struct i40e_asq_cmd_details *cmd_details); i40e_status i40e_aq_resume_port_tx(struct i40e_hw *hw, struct i40e_asq_cmd_details *cmd_details); +i40e_status +i40e_aq_add_cloud_filters_bb(struct i40e_hw *hw, u16 seid, + struct i40e_aqc_cloud_filters_element_bb *filters, + u8 filter_count); +enum i40e_status_code +i40e_aq_add_cloud_filters(struct i40e_hw *hw, u16 vsi, + struct i40e_aqc_cloud_filters_element_data *filters, + u8 filter_count); +enum i40e_status_code +i40e_aq_rem_cloud_filters(struct i40e_hw *hw, u16 vsi, + struct i40e_aqc_cloud_filters_element_data *filters, + u8 filter_count); +i40e_status +i40e_aq_rem_cloud_filters_bb(struct i40e_hw *hw, u16 seid, + struct i40e_aqc_cloud_filters_element_bb *filters, + u8 filter_count); i40e_status i40e_read_lldp_cfg(struct i40e_hw *hw, struct i40e_lldp_variables *lldp_cfg); /* i40e_common */ @@ -360,6 +376,15 @@ i40e_status i40e_aq_rx_ctl_write_register(struct i40e_hw *hw, u32 reg_addr, u32 reg_val, struct i40e_asq_cmd_details *cmd_details); void i40e_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val); +i40e_status i40e_aq_set_phy_register(struct i40e_hw *hw, + u8 phy_select, u8 dev_addr, + u32 reg_addr, u32 reg_val, + struct i40e_asq_cmd_details *cmd_details); +i40e_status i40e_aq_get_phy_register(struct i40e_hw *hw, + u8 phy_select, u8 dev_addr, + u32 reg_addr, u32 *reg_val, + struct i40e_asq_cmd_details *cmd_details); + i40e_status i40e_read_phy_register_clause22(struct i40e_hw *hw, u16 reg, u8 phy_addr, u16 *value); i40e_status i40e_write_phy_register_clause22(struct i40e_hw *hw, 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 120c68f78951..d6d352a6e6ea 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -960,14 +960,14 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) { enum i40e_latency_range new_latency_range = rc->latency_range; u32 new_itr = rc->itr; - int bytes_per_int; + int bytes_per_usec; unsigned int usecs, estimated_usecs; if (rc->total_packets == 0 || !rc->itr) return false; usecs = (rc->itr << 1) * ITR_COUNTDOWN_START; - bytes_per_int = rc->total_bytes / usecs; + bytes_per_usec = rc->total_bytes / usecs; /* The calculations in this algorithm depend on interrupts actually * firing at the ITR rate. This may not happen if the packet rate is @@ -993,18 +993,18 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) */ switch (new_latency_range) { case I40E_LOWEST_LATENCY: - if (bytes_per_int > 10) + if (bytes_per_usec > 10) new_latency_range = I40E_LOW_LATENCY; break; case I40E_LOW_LATENCY: - if (bytes_per_int > 20) + if (bytes_per_usec > 20) new_latency_range = I40E_BULK_LATENCY; - else if (bytes_per_int <= 10) + else if (bytes_per_usec <= 10) new_latency_range = I40E_LOWEST_LATENCY; break; case I40E_BULK_LATENCY: default: - if (bytes_per_int <= 20) + if (bytes_per_usec <= 20) new_latency_range = I40E_LOW_LATENCY; break; } @@ -2117,6 +2117,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) if (!skb) { xdp.data = page_address(rx_buffer->page) + rx_buffer->page_offset; + xdp_set_data_meta_invalid(&xdp); xdp.data_hard_start = xdp.data - i40e_rx_offset(rx_ring); xdp.data_end = xdp.data + size; @@ -2211,9 +2212,7 @@ 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); @@ -2250,7 +2249,7 @@ 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; } @@ -3176,38 +3175,12 @@ 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; @@ -3228,7 +3201,7 @@ 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 fd4bbdd88b57..00d4833e9925 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 { @@ -276,6 +283,16 @@ struct i40e_hw_capabilities { #define I40E_NVM_IMAGE_TYPE_CLOUD 0x2 #define I40E_NVM_IMAGE_TYPE_UDP_CLOUD 0x3 + /* Cloud filter modes: + * Mode1: Filter on L4 port only + * Mode2: Filter for non-tunneled traffic + * Mode3: Filter for tunnel traffic + */ +#define I40E_CLOUD_FILTER_MODE1 0x6 +#define I40E_CLOUD_FILTER_MODE2 0x7 +#define I40E_CLOUD_FILTER_MODE3 0x8 +#define I40E_SWITCH_MODE_MASK 0xF + u32 management_mode; u32 mng_protocols_over_mctp; #define I40E_MNG_PROTOCOL_PLDM 0x2 @@ -428,6 +445,18 @@ struct i40e_nvm_access { u8 data[1]; }; +/* (Q)SFP module access definitions */ +#define I40E_I2C_EEPROM_DEV_ADDR 0xA0 +#define I40E_I2C_EEPROM_DEV_ADDR2 0xA2 +#define I40E_MODULE_TYPE_ADDR 0x00 +#define I40E_MODULE_REVISION_ADDR 0x01 +#define I40E_MODULE_SFF_8472_COMP 0x5E +#define I40E_MODULE_SFF_8472_SWAP 0x5C +#define I40E_MODULE_SFF_ADDR_MODE 0x04 +#define I40E_MODULE_TYPE_QSFP_PLUS 0x0D +#define I40E_MODULE_TYPE_QSFP28 0x11 +#define I40E_MODULE_QSFP_MAX_LEN 640 + /* PCI bus types */ enum i40e_bus_type { i40e_bus_type_unknown = 0, @@ -598,8 +627,15 @@ struct i40e_hw { struct i40e_dcbx_config desired_dcbx_config; /* CEE Desired Cfg */ #define I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE BIT_ULL(0) +#define I40E_HW_FLAG_802_1AD_CAPABLE BIT_ULL(1) +#define I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE BIT_ULL(2) u64 flags; + /* Used in set switch config AQ command */ + u16 switch_tag; + u16 first_tag; + u16 second_tag; + /* debug mask */ u32 debug_mask; char err_str[16]; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 4d1e670f490e..f8a794b72462 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -154,15 +154,30 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf) /** * i40e_vc_disable_vf - * @pf: pointer to the PF info * @vf: pointer to the VF info * - * Disable the VF through a SW reset + * Disable the VF through a SW reset. **/ -static inline void i40e_vc_disable_vf(struct i40e_pf *pf, struct i40e_vf *vf) +static inline void i40e_vc_disable_vf(struct i40e_vf *vf) { + int i; + i40e_vc_notify_vf_reset(vf); - i40e_reset_vf(vf, false); + + /* We want to ensure that an actual reset occurs initiated after this + * function was called. However, we do not want to wait forever, so + * we'll give a reasonable time and print a message if we failed to + * ensure a reset. + */ + for (i = 0; i < 20; i++) { + if (i40e_reset_vf(vf, false)) + return; + usleep_range(10000, 20000); + } + + dev_warn(&vf->pf->pdev->dev, + "Failed to initiate reset for VF %d after 200 milliseconds\n", + vf->vf_id); } /** @@ -258,7 +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; @@ -288,9 +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); @@ -298,7 +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); @@ -312,12 +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, @@ -423,6 +436,9 @@ static int i40e_config_iwarp_qvlist(struct i40e_vf *vf, (sizeof(struct virtchnl_iwarp_qv_info) * (qvlist_info->num_vectors - 1)); vf->qvlist_info = kzalloc(size, GFP_KERNEL); + if (!vf->qvlist_info) + return -ENOMEM; + vf->qvlist_info->num_vectors = qvlist_info->num_vectors; msix_vf = pf->hw.func_caps.num_msix_vectors_vf; @@ -621,7 +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; @@ -815,6 +831,14 @@ static void i40e_free_vf_res(struct i40e_vf *vf) */ clear_bit(I40E_VF_STATE_INIT, &vf->vf_states); + /* It's possible the VF had requeuested more queues than the default so + * do the accounting here when we're about to free them. + */ + if (vf->num_queue_pairs > I40E_DEFAULT_QUEUES_PER_VF) { + pf->queues_left += vf->num_queue_pairs - + I40E_DEFAULT_QUEUES_PER_VF; + } + /* free vsi & disconnect it from the parent uplink */ if (vf->lan_vsi_idx) { i40e_vsi_release(pf->vsi[vf->lan_vsi_idx]); @@ -853,7 +877,8 @@ static void i40e_free_vf_res(struct i40e_vf *vf) } /* reset some of the state variables keeping track of the resources */ vf->num_queue_pairs = 0; - vf->vf_states = 0; + clear_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states); + clear_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states); } /** @@ -868,12 +893,27 @@ static int i40e_alloc_vf_res(struct i40e_vf *vf) int total_queue_pairs = 0; int ret; + if (vf->num_req_queues && + vf->num_req_queues <= pf->queues_left + I40E_DEFAULT_QUEUES_PER_VF) + pf->num_vf_qps = vf->num_req_queues; + else + pf->num_vf_qps = I40E_DEFAULT_QUEUES_PER_VF; + /* allocate hw vsi context & associated resources */ ret = i40e_alloc_vsi_res(vf, I40E_VSI_SRIOV); if (ret) goto error_alloc; total_queue_pairs += pf->vsi[vf->lan_vsi_idx]->alloc_queue_pairs; + /* We account for each VF to get a default number of queue pairs. If + * the VF has now requested more, we need to account for that to make + * certain we never request more queues than we actually have left in + * HW. + */ + if (total_queue_pairs > I40E_DEFAULT_QUEUES_PER_VF) + pf->queues_left -= + total_queue_pairs - I40E_DEFAULT_QUEUES_PER_VF; + if (vf->trusted) set_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps); else @@ -1008,8 +1048,8 @@ static void i40e_cleanup_reset_vf(struct i40e_vf *vf) set_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states); clear_bit(I40E_VF_STATE_DISABLED, &vf->vf_states); /* Do not notify the client during VF init */ - if (test_and_clear_bit(I40E_VF_STATE_PRE_ENABLE, - &vf->vf_states)) + if (!test_and_clear_bit(I40E_VF_STATE_PRE_ENABLE, + &vf->vf_states)) i40e_notify_client_of_vf_reset(pf, abs_vf_id); vf->num_vlan = 0; } @@ -1026,9 +1066,9 @@ static void i40e_cleanup_reset_vf(struct i40e_vf *vf) * @vf: pointer to the VF structure * @flr: VFLR was issued or not * - * reset the VF + * Returns true if the VF is reset, false otherwise. **/ -void i40e_reset_vf(struct i40e_vf *vf, bool flr) +bool i40e_reset_vf(struct i40e_vf *vf, bool flr) { struct i40e_pf *pf = vf->pf; struct i40e_hw *hw = &pf->hw; @@ -1036,9 +1076,11 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr) u32 reg; int i; - /* If VFs have been disabled, there is no need to reset */ + /* If the VFs have been disabled, this means something else is + * resetting the VF, so we shouldn't continue. + */ if (test_and_set_bit(__I40E_VF_DISABLE, pf->state)) - return; + return false; i40e_trigger_vf_reset(vf, flr); @@ -1075,6 +1117,8 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr) i40e_flush(hw); clear_bit(__I40E_VF_DISABLE, pf->state); + + return true; } /** @@ -1086,8 +1130,10 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr) * VF, then do all the waiting in one chunk, and finally finish restoring each * VF after the wait. This is useful during PF routines which need to reset * all VFs, as otherwise it must perform these resets in a serialized fashion. + * + * Returns true if any VFs were reset, and false otherwise. **/ -void i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) +bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) { struct i40e_hw *hw = &pf->hw; struct i40e_vf *vf; @@ -1096,11 +1142,11 @@ void i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) /* If we don't have any VFs, then there is nothing to reset */ if (!pf->num_alloc_vfs) - return; + return false; /* If VFs have been disabled, there is no need to reset */ if (test_and_set_bit(__I40E_VF_DISABLE, pf->state)) - return; + return false; /* Begin reset on all VFs at once */ for (v = 0; v < pf->num_alloc_vfs; v++) @@ -1175,6 +1221,8 @@ void i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) i40e_flush(hw); clear_bit(__I40E_VF_DISABLE, pf->state); + + return true; } /** @@ -1308,7 +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; } @@ -1377,8 +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); } @@ -1386,7 +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; @@ -1537,6 +1584,8 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_IWARP)) { vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_IWARP; set_bit(I40E_VF_STATE_IWARPENA, &vf->vf_states); + } else { + clear_bit(I40E_VF_STATE_IWARPENA, &vf->vf_states); } if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) { @@ -1579,6 +1628,9 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) VIRTCHNL_VF_OFFLOAD_WB_ON_ITR; } + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_REQ_QUEUES) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_REQ_QUEUES; + vfres->num_vsis = num_vsis; vfres->num_queue_pairs = vf->num_queue_pairs; vfres->max_vectors = pf->hw.func_caps.num_msix_vectors_vf; @@ -1987,6 +2039,57 @@ error_param: } /** + * i40e_vc_request_queues_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * @msglen: msg length + * + * VFs get a default number of queues but can use this message to request a + * 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) +{ + struct virtchnl_vf_res_request *vfres = + (struct virtchnl_vf_res_request *)msg; + int req_pairs = vfres->num_queue_pairs; + int cur_pairs = vf->num_queue_pairs; + struct i40e_pf *pf = vf->pf; + + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) + return -EINVAL; + + if (req_pairs <= 0) { + dev_err(&pf->pdev->dev, + "VF %d tried to request %d queues. Ignoring.\n", + vf->vf_id, req_pairs); + } else if (req_pairs > I40E_MAX_VF_QUEUES) { + dev_err(&pf->pdev->dev, + "VF %d tried to request more than %d queues.\n", + vf->vf_id, + I40E_MAX_VF_QUEUES); + vfres->num_queue_pairs = I40E_MAX_VF_QUEUES; + } else if (req_pairs - cur_pairs > pf->queues_left) { + dev_warn(&pf->pdev->dev, + "VF %d requested %d more queues, but only %d left.\n", + vf->vf_id, + req_pairs - cur_pairs, + 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, + (u8 *)vfres, sizeof(vfres)); +} + +/** * i40e_vc_get_stats_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -2708,6 +2811,9 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode, case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING: ret = i40e_vc_disable_vlan_stripping(vf, msg, msglen); break; + case VIRTCHNL_OP_REQUEST_QUEUES: + ret = i40e_vc_request_queues_msg(vf, msg, msglen); + break; case VIRTCHNL_OP_UNKNOWN: default: @@ -2779,6 +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 */ @@ -2817,7 +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); @@ -2840,7 +2947,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) } /* Force the VF driver stop so it has to reload with new MAC address */ - i40e_vc_disable_vf(pf, vf); + i40e_vc_disable_vf(vf); dev_info(&pf->pdev->dev, "Reload the VF driver to make this change effective.\n"); error_param: @@ -2848,6 +2955,34 @@ error_param: } /** + * i40e_vsi_has_vlans - True if VSI has configured VLANs + * @vsi: pointer to the vsi + * + * Check if a VSI has configured any VLANs. False if we have a port VLAN or if + * we have no configured VLANs. Do not call while holding the + * mac_filter_hash_lock. + */ +static bool i40e_vsi_has_vlans(struct i40e_vsi *vsi) +{ + bool have_vlans; + + /* If we have a port VLAN, then the VSI cannot have any VLANs + * configured, as all MAC/VLAN filters will be assigned to the PVID. + */ + if (vsi->info.pvid) + return false; + + /* Since we don't have a PVID, we know that if the device is in VLAN + * mode it must be because of a VLAN filter configured on this VSI. + */ + spin_lock_bh(&vsi->mac_filter_hash_lock); + have_vlans = i40e_is_vsi_in_vlan(vsi); + spin_unlock_bh(&vsi->mac_filter_hash_lock); + + return have_vlans; +} + +/** * i40e_ndo_set_vf_port_vlan * @netdev: network interface device structure * @vf_id: VF identifier @@ -2899,10 +3034,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, /* duplicate request, so just return success */ goto error_pvid; - /* Locked once because multiple functions below iterate list */ - spin_lock_bh(&vsi->mac_filter_hash_lock); - - if (le16_to_cpu(vsi->info.pvid) == 0 && i40e_is_vsi_in_vlan(vsi)) { + if (i40e_vsi_has_vlans(vsi)) { dev_err(&pf->pdev->dev, "VF %d has already configured VLAN filters and the administrator is requesting a port VLAN override.\nPlease unload and reload the VF driver for this change to take effect.\n", vf_id); @@ -2910,11 +3042,14 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, * the right thing by reconfiguring his network correctly * and then reloading the VF driver. */ - i40e_vc_disable_vf(pf, vf); + i40e_vc_disable_vf(vf); /* During reset the VF got a new VSI, so refresh the pointer. */ vsi = pf->vsi[vf->lan_vsi_idx]; } + /* Locked once because multiple functions below iterate list */ + spin_lock_bh(&vsi->mac_filter_hash_lock); + /* Check for condition where there was already a port VLAN ID * filter set and now it is being deleted by setting it to zero. * Additionally check for the condition where there was a port @@ -2987,8 +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 @@ -3004,7 +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 */ @@ -3029,48 +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; @@ -3279,14 +3373,11 @@ int i40e_ndo_set_vf_trust(struct net_device *netdev, int vf_id, bool setting) vf = &pf->vf[vf_id]; - if (!vf) - return -EINVAL; if (setting == vf->trusted) goto out; vf->trusted = setting; - i40e_vc_notify_vf_reset(vf); - i40e_reset_vf(vf, false); + i40e_vc_disable_vf(vf); dev_info(&pf->pdev->dev, "VF %u is now %strusted\n", vf_id, setting ? "" : "un"); out: diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 1f4b0c504368..5efc4f92bb37 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -56,7 +56,6 @@ enum i40e_vf_states { I40E_VF_STATE_INIT = 0, I40E_VF_STATE_ACTIVE, I40E_VF_STATE_IWARPENA, - I40E_VF_STATE_FCOEENA, I40E_VF_STATE_DISABLED, I40E_VF_STATE_MC_PROMISC, I40E_VF_STATE_UC_PROMISC, @@ -97,6 +96,7 @@ struct i40e_vf { u16 lan_vsi_id; /* ID as used by firmware */ u8 num_queue_pairs; /* num of qps assigned to VF vsis */ + u8 num_req_queues; /* num of requested qps */ u64 num_mdd_events; /* num of mdd events detected */ /* num of continuous malformed or invalid msgs detected */ u64 num_invalid_msgs; @@ -121,8 +121,8 @@ int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs); int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen); int i40e_vc_process_vflr_event(struct i40e_pf *pf); -void i40e_reset_vf(struct i40e_vf *vf, bool flr); -void i40e_reset_all_vfs(struct i40e_pf *pf, bool flr); +bool i40e_reset_vf(struct i40e_vf *vf, bool flr); +bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr); void i40e_vc_notify_vf_reset(struct i40e_vf *vf); /* VF configuration related iplink handlers */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h index 83e63e55c4b4..06b04572c518 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h @@ -34,7 +34,15 @@ */ #define I40E_FW_API_VERSION_MAJOR 0x0001 -#define I40E_FW_API_VERSION_MINOR 0x0005 +#define I40E_FW_API_VERSION_MINOR_X722 0x0005 +#define I40E_FW_API_VERSION_MINOR_X710 0x0007 + +#define I40E_FW_MINOR_VERSION(_h) ((_h)->mac.type == I40E_MAC_XL710 ? \ + I40E_FW_API_VERSION_MINOR_X710 : \ + I40E_FW_API_VERSION_MINOR_X722) + +/* API version 1.7 implements additional link and PHY-specific APIs */ +#define I40E_MINOR_VER_GET_LINK_INFO_XL710 0x0007 struct i40e_aq_desc { __le16 flags; @@ -236,6 +244,8 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_set_phy_debug = 0x0622, i40e_aqc_opc_upload_ext_phy_fm = 0x0625, i40e_aqc_opc_run_phy_activity = 0x0626, + i40e_aqc_opc_set_phy_register = 0x0628, + i40e_aqc_opc_get_phy_register = 0x0629, /* NVM commands */ i40e_aqc_opc_nvm_read = 0x0701, @@ -761,7 +771,22 @@ struct i40e_aqc_set_switch_config { #define I40E_AQ_SET_SWITCH_CFG_PROMISC 0x0001 #define I40E_AQ_SET_SWITCH_CFG_L2_FILTER 0x0002 __le16 valid_flags; - u8 reserved[12]; + /* The ethertype in switch_tag is dropped on ingress and used + * internally by the switch. Set this to zero for the default + * of 0x88a8 (802.1ad). Should be zero for firmware API + * versions lower than 1.7. + */ + __le16 switch_tag; + /* The ethertypes in first_tag and second_tag are used to + * match the outer and inner VLAN tags (respectively) when HW + * double VLAN tagging is enabled via the set port parameters + * AQ command. Otherwise these are both ignored. Set them to + * zero for their defaults of 0x8100 (802.1Q). Should be zero + * for firmware API versions lower than 1.7. + */ + __le16 first_tag; + __le16 second_tag; + u8 reserved[6]; }; I40E_CHECK_CMD_LENGTH(i40e_aqc_set_switch_config); @@ -1314,14 +1339,16 @@ struct i40e_aqc_add_remove_cloud_filters { #define I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_SHIFT 0 #define I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_MASK (0x3FF << \ I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_SHIFT) - u8 reserved2[4]; + u8 big_buffer_flag; +#define I40E_AQC_ADD_CLOUD_CMD_BB 1 + u8 reserved2[3]; __le32 addr_high; __le32 addr_low; }; I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_cloud_filters); -struct i40e_aqc_add_remove_cloud_filters_element_data { +struct i40e_aqc_cloud_filters_element_data { u8 outer_mac[6]; u8 inner_mac[6]; __le16 inner_vlan; @@ -1333,6 +1360,9 @@ struct i40e_aqc_add_remove_cloud_filters_element_data { struct { u8 data[16]; } v6; + struct { + __le16 data[8]; + } raw_v6; } ipaddr; __le16 flags; #define I40E_AQC_ADD_CLOUD_FILTER_SHIFT 0 @@ -1351,6 +1381,10 @@ struct i40e_aqc_add_remove_cloud_filters_element_data { #define I40E_AQC_ADD_CLOUD_FILTER_IMAC 0x000A #define I40E_AQC_ADD_CLOUD_FILTER_OMAC_TEN_ID_IMAC 0x000B #define I40E_AQC_ADD_CLOUD_FILTER_IIP 0x000C +/* 0x0010 to 0x0017 is for custom filters */ +#define I40E_AQC_ADD_CLOUD_FILTER_IP_PORT 0x0010 /* Dest IP + L4 Port */ +#define I40E_AQC_ADD_CLOUD_FILTER_MAC_PORT 0x0011 /* Dest MAC + L4 Port */ +#define I40E_AQC_ADD_CLOUD_FILTER_MAC_VLAN_PORT 0x0012 /* Dest MAC + VLAN + L4 Port */ #define I40E_AQC_ADD_CLOUD_FLAGS_TO_QUEUE 0x0080 #define I40E_AQC_ADD_CLOUD_VNK_SHIFT 6 @@ -1385,6 +1419,49 @@ struct i40e_aqc_add_remove_cloud_filters_element_data { u8 response_reserved[7]; }; +I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_cloud_filters_element_data); + +/* i40e_aqc_cloud_filters_element_bb is used when + * I40E_AQC_ADD_CLOUD_CMD_BB flag is set. + */ +struct i40e_aqc_cloud_filters_element_bb { + struct i40e_aqc_cloud_filters_element_data element; + u16 general_fields[32]; +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD0 0 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD1 1 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD2 2 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD0 3 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD1 4 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD2 5 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD0 6 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD1 7 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD2 8 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD0 9 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD1 10 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD2 11 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD0 12 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD1 13 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD2 14 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD0 15 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD1 16 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD2 17 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD3 18 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD4 19 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD5 20 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD6 21 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD7 22 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD0 23 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD1 24 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD2 25 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD3 26 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD4 27 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD5 28 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD6 29 +#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD7 30 +}; + +I40E_CHECK_STRUCT_LEN(0x80, i40e_aqc_cloud_filters_element_bb); + struct i40e_aqc_remove_cloud_filters_completion { __le16 perfect_ovlan_used; __le16 perfect_ovlan_free; @@ -1396,6 +1473,60 @@ struct i40e_aqc_remove_cloud_filters_completion { I40E_CHECK_CMD_LENGTH(i40e_aqc_remove_cloud_filters_completion); +/* Replace filter Command 0x025F + * uses the i40e_aqc_replace_cloud_filters, + * and the generic indirect completion structure + */ +struct i40e_filter_data { + u8 filter_type; + u8 input[3]; +}; + +I40E_CHECK_STRUCT_LEN(4, i40e_filter_data); + +struct i40e_aqc_replace_cloud_filters_cmd { + u8 valid_flags; +#define I40E_AQC_REPLACE_L1_FILTER 0x0 +#define I40E_AQC_REPLACE_CLOUD_FILTER 0x1 +#define I40E_AQC_GET_CLOUD_FILTERS 0x2 +#define I40E_AQC_MIRROR_CLOUD_FILTER 0x4 +#define I40E_AQC_HIGH_PRIORITY_CLOUD_FILTER 0x8 + u8 old_filter_type; + u8 new_filter_type; + u8 tr_bit; + u8 reserved[4]; + __le32 addr_high; + __le32 addr_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_replace_cloud_filters_cmd); + +struct i40e_aqc_replace_cloud_filters_cmd_buf { + u8 data[32]; +/* Filter type INPUT codes*/ +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_ENTRIES_MAX 3 +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_VALIDATED BIT(7) + +/* Field Vector offsets */ +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_MAC_DA 0 +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_ETH 6 +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG 7 +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_VLAN 8 +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_OVLAN 9 +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_IVLAN 10 +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_TUNNLE_KEY 11 +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_IMAC 12 +/* big FLU */ +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_IP_DA 14 +/* big FLU */ +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_OIP_DA 15 + +#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_INNER_VLAN 37 + struct i40e_filter_data filters[8]; +}; + +I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_replace_cloud_filters_cmd_buf); + /* Add Mirror Rule (indirect or direct 0x0260) * Delete Mirror Rule (indirect or direct 0x0261) * note: some rule types (4,5) do not use an external buffer. @@ -1722,6 +1853,8 @@ enum i40e_aq_phy_type { I40E_PHY_TYPE_10GBASE_CR1_CU = 0xB, I40E_PHY_TYPE_10GBASE_AOC = 0xC, I40E_PHY_TYPE_40GBASE_AOC = 0xD, + I40E_PHY_TYPE_UNRECOGNIZED = 0xE, + I40E_PHY_TYPE_UNSUPPORTED = 0xF, I40E_PHY_TYPE_100BASE_TX = 0x11, I40E_PHY_TYPE_1000BASE_T = 0x12, I40E_PHY_TYPE_10GBASE_T = 0x13, @@ -1740,7 +1873,12 @@ 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_MAX + 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, }; #define I40E_LINK_SPEED_100MB_SHIFT 0x1 @@ -1797,6 +1935,8 @@ 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 @@ -1930,19 +2070,31 @@ struct i40e_aqc_get_link_status { #define I40E_AQ_25G_SERDES_UCODE_ERR 0X04 #define I40E_AQ_25G_NIMB_UCODE_ERR 0X05 u8 loopback; /* use defines from i40e_aqc_set_lb_mode */ +/* Since firmware API 1.7 loopback field keeps power class info as well */ +#define I40E_AQ_LOOPBACK_MASK 0x07 +#define I40E_AQ_PWR_CLASS_SHIFT_LB 6 +#define I40E_AQ_PWR_CLASS_MASK_LB (0x03 << I40E_AQ_PWR_CLASS_SHIFT_LB) __le16 max_frame_size; u8 config; #define I40E_AQ_CONFIG_FEC_KR_ENA 0x01 #define I40E_AQ_CONFIG_FEC_RS_ENA 0x02 #define I40E_AQ_CONFIG_CRC_ENA 0x04 #define I40E_AQ_CONFIG_PACING_MASK 0x78 - u8 power_desc; + union { + struct { + u8 power_desc; #define I40E_AQ_LINK_POWER_CLASS_1 0x00 #define I40E_AQ_LINK_POWER_CLASS_2 0x01 #define I40E_AQ_LINK_POWER_CLASS_3 0x02 #define I40E_AQ_LINK_POWER_CLASS_4 0x03 #define I40E_AQ_PWR_CLASS_MASK 0x03 - u8 reserved[4]; + u8 reserved[4]; + }; + struct { + u8 link_type[4]; + u8 link_type_ext; + }; + }; }; I40E_CHECK_CMD_LENGTH(i40e_aqc_get_link_status); @@ -2022,6 +2174,22 @@ struct i40e_aqc_run_phy_activity { I40E_CHECK_CMD_LENGTH(i40e_aqc_run_phy_activity); +/* Set PHY Register command (0x0628) */ +/* Get PHY Register command (0x0629) */ +struct i40e_aqc_phy_register_access { + u8 phy_interface; +#define I40E_AQ_PHY_REG_ACCESS_INTERNAL 0 +#define I40E_AQ_PHY_REG_ACCESS_EXTERNAL 1 +#define I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE 2 + u8 dev_address; + u8 reserved1[2]; + __le32 reg_address; + __le32 reg_value; + u8 reserved2[4]; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_phy_register_access); + /* NVM Read command (indirect 0x0701) * NVM Erase commands (direct 0x0702) * NVM Update commands (indirect 0x0703) diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c index 8d3a2bfe186a..7d70bf69b249 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_common.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c @@ -1042,6 +1042,75 @@ do_retry: } /** + * i40evf_aq_set_phy_register + * @hw: pointer to the hw struct + * @phy_select: select which phy should be accessed + * @dev_addr: PHY device address + * @reg_addr: PHY register address + * @reg_val: new register value + * @cmd_details: pointer to command details structure or NULL + * + * Reset the external PHY. + **/ +i40e_status i40evf_aq_set_phy_register(struct i40e_hw *hw, + u8 phy_select, u8 dev_addr, + u32 reg_addr, u32 reg_val, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_phy_register_access *cmd = + (struct i40e_aqc_phy_register_access *)&desc.params.raw; + i40e_status status; + + i40evf_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_set_phy_register); + + cmd->phy_interface = phy_select; + cmd->dev_address = dev_addr; + cmd->reg_address = cpu_to_le32(reg_addr); + cmd->reg_value = cpu_to_le32(reg_val); + + status = i40evf_asq_send_command(hw, &desc, NULL, 0, cmd_details); + + return status; +} + +/** + * i40evf_aq_get_phy_register + * @hw: pointer to the hw struct + * @phy_select: select which phy should be accessed + * @dev_addr: PHY device address + * @reg_addr: PHY register address + * @reg_val: read register value + * @cmd_details: pointer to command details structure or NULL + * + * Reset the external PHY. + **/ +i40e_status i40evf_aq_get_phy_register(struct i40e_hw *hw, + u8 phy_select, u8 dev_addr, + u32 reg_addr, u32 *reg_val, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_phy_register_access *cmd = + (struct i40e_aqc_phy_register_access *)&desc.params.raw; + i40e_status status; + + i40evf_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_get_phy_register); + + cmd->phy_interface = phy_select; + cmd->dev_address = dev_addr; + cmd->reg_address = cpu_to_le32(reg_addr); + + status = i40evf_asq_send_command(hw, &desc, NULL, 0, cmd_details); + if (!status) + *reg_val = le32_to_cpu(cmd->reg_value); + + return status; +} + +/** * i40e_aq_send_msg_to_pf * @hw: pointer to the hardware structure * @v_opcode: opcodes for VF-PF communication diff --git a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h index c9836bba487d..b624b5994075 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h @@ -111,6 +111,15 @@ i40e_status i40evf_aq_rx_ctl_write_register(struct i40e_hw *hw, u32 reg_addr, u32 reg_val, struct i40e_asq_cmd_details *cmd_details); void i40evf_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val); +i40e_status i40e_aq_set_phy_register(struct i40e_hw *hw, + u8 phy_select, u8 dev_addr, + u32 reg_addr, u32 reg_val, + struct i40e_asq_cmd_details *cmd_details); +i40e_status i40e_aq_get_phy_register(struct i40e_hw *hw, + u8 phy_select, u8 dev_addr, + u32 reg_addr, u32 *reg_val, + struct i40e_asq_cmd_details *cmd_details); + i40e_status i40e_read_phy_register(struct i40e_hw *hw, u8 page, u16 reg, u8 phy_addr, u16 *value); i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page, diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index c32c62462c84..fe817e2b6fef 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -358,14 +358,14 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) { enum i40e_latency_range new_latency_range = rc->latency_range; u32 new_itr = rc->itr; - int bytes_per_int; + int bytes_per_usec; unsigned int usecs, estimated_usecs; if (rc->total_packets == 0 || !rc->itr) return false; usecs = (rc->itr << 1) * ITR_COUNTDOWN_START; - bytes_per_int = rc->total_bytes / usecs; + bytes_per_usec = rc->total_bytes / usecs; /* The calculations in this algorithm depend on interrupts actually * firing at the ITR rate. This may not happen if the packet rate is @@ -391,18 +391,18 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) */ switch (new_latency_range) { case I40E_LOWEST_LATENCY: - if (bytes_per_int > 10) + if (bytes_per_usec > 10) new_latency_range = I40E_LOW_LATENCY; break; case I40E_LOW_LATENCY: - if (bytes_per_int > 20) + if (bytes_per_usec > 20) new_latency_range = I40E_BULK_LATENCY; - else if (bytes_per_int <= 10) + else if (bytes_per_usec <= 10) new_latency_range = I40E_LOWEST_LATENCY; break; case I40E_BULK_LATENCY: default: - if (bytes_per_int <= 20) + if (bytes_per_usec <= 20) new_latency_range = I40E_LOW_LATENCY; break; } @@ -1409,9 +1409,7 @@ 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 2ea919d9cdcf..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) @@ -401,6 +404,18 @@ struct i40e_nvm_access { u8 data[1]; }; +/* (Q)SFP module access definitions */ +#define I40E_I2C_EEPROM_DEV_ADDR 0xA0 +#define I40E_I2C_EEPROM_DEV_ADDR2 0xA2 +#define I40E_MODULE_TYPE_ADDR 0x00 +#define I40E_MODULE_REVISION_ADDR 0x01 +#define I40E_MODULE_SFF_8472_COMP 0x5E +#define I40E_MODULE_SFF_8472_SWAP 0x5C +#define I40E_MODULE_SFF_ADDR_MODE 0x04 +#define I40E_MODULE_TYPE_QSFP_PLUS 0x0D +#define I40E_MODULE_TYPE_QSFP28 0x11 +#define I40E_MODULE_QSFP_MAX_LEN 640 + /* PCI bus types */ enum i40e_bus_type { i40e_bus_type_unknown = 0, @@ -556,11 +571,19 @@ struct i40e_hw { /* LLDP/DCBX Status */ u16 dcbx_status; +#define I40E_HW_FLAG_802_1AD_CAPABLE BIT_ULL(1) +#define I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE BIT_ULL(2) + /* DCBX info */ struct i40e_dcbx_config local_dcbx_config; /* Oper/Local Cfg */ struct i40e_dcbx_config remote_dcbx_config; /* Peer Cfg */ struct i40e_dcbx_config desired_dcbx_config; /* CEE Desired Cfg */ + /* Used in set switch config AQ command */ + u16 switch_tag; + u16 first_tag; + u16 second_tag; + /* debug mask */ u32 debug_mask; char err_str[16]; diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h index 82f69031e5cd..de0af521d602 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ b/drivers/net/ethernet/intel/i40evf/i40evf.h @@ -102,6 +102,7 @@ struct i40e_vsi { #define I40E_TX_CTXTDESC(R, i) \ (&(((struct i40e_tx_context_desc *)((R)->desc))[i])) #define MAX_QUEUES 16 +#define I40EVF_MAX_REQ_QUEUES 4 #define I40EVF_HKEY_ARRAY_SIZE ((I40E_VFQF_HKEY_MAX_INDEX + 1) * 4) #define I40EVF_HLUT_ARRAY_SIZE ((I40E_VFQF_HLUT_MAX_INDEX + 1) * 4) @@ -200,6 +201,7 @@ struct i40evf_adapter { struct list_head vlan_filter_list; char misc_vector_name[IFNAMSIZ + 9]; int num_active_queues; + int num_req_queues; /* TX */ struct i40e_ring *tx_rings; @@ -220,21 +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_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 @@ -349,6 +352,7 @@ void i40evf_deconfigure_queues(struct i40evf_adapter *adapter); void i40evf_enable_queues(struct i40evf_adapter *adapter); void i40evf_disable_queues(struct i40evf_adapter *adapter); void i40evf_map_queues(struct i40evf_adapter *adapter); +int i40evf_request_queues(struct i40evf_adapter *adapter, int num); void i40evf_add_ether_addrs(struct i40evf_adapter *adapter); void i40evf_del_ether_addrs(struct i40evf_adapter *adapter); void i40evf_add_vlans(struct i40evf_adapter *adapter); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c index 65874d6b3ab9..da006fa3fec1 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c @@ -669,7 +669,7 @@ static void i40evf_get_channels(struct net_device *netdev, struct i40evf_adapter *adapter = netdev_priv(netdev); /* Report maximum channels */ - ch->max_combined = adapter->num_active_queues; + ch->max_combined = I40EVF_MAX_REQ_QUEUES; ch->max_other = NONQ_VECS; ch->other_count = NONQ_VECS; @@ -678,6 +678,41 @@ static void i40evf_get_channels(struct net_device *netdev, } /** + * i40evf_set_channels: set the new channel count + * @netdev: network interface device structure + * @ch: channel information structure + * + * Negotiate a new number of channels with the PF then do a reset. During + * reset we'll realloc queues and fix the RSS table. Returns 0 on success, + * negative on failure. + **/ +static int i40evf_set_channels(struct net_device *netdev, + struct ethtool_channels *ch) +{ + struct i40evf_adapter *adapter = netdev_priv(netdev); + int num_req = ch->combined_count; + + if (num_req != adapter->num_active_queues && + !(adapter->vf_res->vf_cap_flags & + VIRTCHNL_VF_OFFLOAD_REQ_QUEUES)) { + dev_info(&adapter->pdev->dev, "PF is not capable of queue negotiation.\n"); + return -EINVAL; + } + + /* All of these should have already been checked by ethtool before this + * even gets to us, but just to be sure. + */ + if (num_req <= 0 || num_req > I40EVF_MAX_REQ_QUEUES) + return -EINVAL; + + if (ch->rx_count || ch->tx_count || ch->other_count != NONQ_VECS) + return -EINVAL; + + adapter->num_req_queues = num_req; + return i40evf_request_queues(adapter, num_req); +} + +/** * i40evf_get_rxfh_key_size - get the RSS hash key size * @netdev: network interface device structure * @@ -785,6 +820,7 @@ static const struct ethtool_ops i40evf_ethtool_ops = { .get_rxfh = i40evf_get_rxfh, .set_rxfh = i40evf_set_rxfh, .get_channels = i40evf_get_channels, + .set_channels = i40evf_set_channels, .get_rxfh_key_size = i40evf_get_rxfh_key_size, .get_link_ksettings = i40evf_get_link_ksettings, }; diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index 1825d956bb00..ca2ebdbd24d7 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -46,7 +46,7 @@ static const char i40evf_driver_string[] = #define DRV_VERSION_MAJOR 3 #define DRV_VERSION_MINOR 0 -#define DRV_VERSION_BUILD 0 +#define DRV_VERSION_BUILD 1 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) \ @@ -430,57 +430,26 @@ i40evf_map_vector_to_txq(struct i40evf_adapter *adapter, int v_idx, int t_idx) * group the rings as "efficiently" as possible. You would add new * mapping configurations in here. **/ -static int i40evf_map_rings_to_vectors(struct i40evf_adapter *adapter) +static void i40evf_map_rings_to_vectors(struct i40evf_adapter *adapter) { + int rings_remaining = adapter->num_active_queues; + int ridx = 0, vidx = 0; int q_vectors; - int v_start = 0; - int rxr_idx = 0, txr_idx = 0; - int rxr_remaining = adapter->num_active_queues; - int txr_remaining = adapter->num_active_queues; - int i, j; - int rqpv, tqpv; - int err = 0; q_vectors = adapter->num_msix_vectors - NONQ_VECS; - /* The ideal configuration... - * We have enough vectors to map one per queue. - */ - if (q_vectors >= (rxr_remaining * 2)) { - for (; rxr_idx < rxr_remaining; v_start++, rxr_idx++) - i40evf_map_vector_to_rxq(adapter, v_start, rxr_idx); - - for (; txr_idx < txr_remaining; v_start++, txr_idx++) - i40evf_map_vector_to_txq(adapter, v_start, txr_idx); - goto out; - } + for (; ridx < rings_remaining; ridx++) { + i40evf_map_vector_to_rxq(adapter, vidx, ridx); + i40evf_map_vector_to_txq(adapter, vidx, ridx); - /* If we don't have enough vectors for a 1-to-1 - * mapping, we'll have to group them so there are - * multiple queues per vector. - * Re-adjusting *qpv takes care of the remainder. - */ - for (i = v_start; i < q_vectors; i++) { - rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - i); - for (j = 0; j < rqpv; j++) { - i40evf_map_vector_to_rxq(adapter, i, rxr_idx); - rxr_idx++; - rxr_remaining--; - } - } - for (i = v_start; i < q_vectors; i++) { - tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - i); - for (j = 0; j < tqpv; j++) { - i40evf_map_vector_to_txq(adapter, i, txr_idx); - txr_idx++; - txr_remaining--; - } + /* In the case where we have more queues than vectors, continue + * round-robin on vectors until all queues are mapped. + */ + if (++vidx >= q_vectors) + vidx = 0; } -out: adapter->aq_required |= I40EVF_FLAG_AQ_MAP_VECTORS; - - return err; } #ifdef CONFIG_NET_POLL_CONTROLLER @@ -546,6 +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 */ @@ -584,10 +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; @@ -908,6 +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); @@ -1217,9 +1191,18 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) { int i, num_active_queues; - num_active_queues = min_t(int, - adapter->vsi_res->num_queue_pairs, - (int)(num_online_cpus())); + /* If we're in reset reallocating queues we don't actually know yet for + * certain the PF gave us the number of queues we asked for but we'll + * assume it did. Once basic reset is finished we'll confirm once we + * start negotiating config with PF. + */ + if (adapter->num_req_queues) + num_active_queues = adapter->num_req_queues; + else + num_active_queues = min_t(int, + adapter->vsi_res->num_queue_pairs, + (int)(num_online_cpus())); + adapter->tx_rings = kcalloc(num_active_queues, sizeof(struct i40e_ring), GFP_KERNEL); @@ -1240,7 +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; @@ -1249,7 +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; @@ -1568,12 +1551,53 @@ static void i40evf_free_rss(struct i40evf_adapter *adapter) } /** + * i40evf_reinit_interrupt_scheme - Reallocate queues and vectors + * @adapter: board private structure + * + * Returns 0 on success, negative on failure + **/ +static int i40evf_reinit_interrupt_scheme(struct i40evf_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + int err; + + if (netif_running(netdev)) + i40evf_free_traffic_irqs(adapter); + i40evf_free_misc_irq(adapter); + i40evf_reset_interrupt_capability(adapter); + i40evf_free_q_vectors(adapter); + i40evf_free_queues(adapter); + + err = i40evf_init_interrupt_scheme(adapter); + if (err) + goto err; + + netif_tx_stop_all_queues(netdev); + + err = i40evf_request_misc_irq(adapter); + if (err) + goto err; + + set_bit(__I40E_VSI_DOWN, adapter->vsi.state); + + i40evf_map_rings_to_vectors(adapter); + + if (RSS_AQ(adapter)) + adapter->aq_required |= I40EVF_FLAG_AQ_CONFIGURE_RSS; + else + err = i40evf_init_rss(adapter); +err: + return 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 */ @@ -1913,8 +1937,15 @@ continue_reset: if (err) dev_info(&adapter->pdev->dev, "Failed to init adminq: %d\n", err); + adapter->aq_required = 0; - adapter->aq_required = I40EVF_FLAG_AQ_GET_CONFIG; + if (adapter->flags & I40EVF_FLAG_REINIT_ITR_NEEDED) { + err = i40evf_reinit_interrupt_scheme(adapter); + if (err) + goto reset_err; + } + + adapter->aq_required |= I40EVF_FLAG_AQ_GET_CONFIG; adapter->aq_required |= I40EVF_FLAG_AQ_MAP_VECTORS; /* re-add all MAC filters */ @@ -1944,6 +1975,15 @@ continue_reset: if (err) goto reset_err; + if (adapter->flags & I40EVF_FLAG_REINIT_ITR_NEEDED) { + err = i40evf_request_traffic_irqs(adapter, + netdev->name); + if (err) + goto reset_err; + + adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; + } + i40evf_configure(adapter); i40evf_up_complete(adapter); @@ -2386,10 +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 @@ -2402,9 +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; } @@ -2459,9 +2497,9 @@ static int i40evf_check_reset_complete(struct i40e_hw *hw) int i40evf_process_config(struct i40evf_adapter *adapter) { struct virtchnl_vf_resource *vfres = adapter->vf_res; + int i, num_req_queues = adapter->num_req_queues; struct net_device *netdev = adapter->netdev; struct i40e_vsi *vsi = &adapter->vsi; - int i; netdev_features_t hw_enc_features; netdev_features_t hw_features; @@ -2475,6 +2513,23 @@ int i40evf_process_config(struct i40evf_adapter *adapter) return -ENODEV; } + if (num_req_queues && + num_req_queues != adapter->vsi_res->num_queue_pairs) { + /* Problem. The PF gave us fewer queues than what we had + * negotiated in our request. Need a reset to see if we can't + * get back to a working state. + */ + dev_err(&adapter->pdev->dev, + "Requested %d queues, but PF only gave us %d.\n", + num_req_queues, + adapter->vsi_res->num_queue_pairs); + adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->num_req_queues = adapter->vsi_res->num_queue_pairs; + i40evf_schedule_reset(adapter); + return -ENODEV; + } + adapter->num_req_queues = 0; + hw_enc_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | @@ -2518,9 +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; @@ -2686,9 +2749,7 @@ static void i40evf_init_task(struct work_struct *work) ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); } - init_timer(&adapter->watchdog_timer); - adapter->watchdog_timer.function = &i40evf_watchdog_timer; - adapter->watchdog_timer.data = (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 85876f4fb1fb..46c8b8a3907c 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c @@ -52,7 +52,7 @@ static int i40evf_send_pf_msg(struct i40evf_adapter *adapter, err = i40e_aq_send_msg_to_pf(hw, op, 0, msg, len, NULL); if (err) - dev_err(&adapter->pdev->dev, "Unable to send opcode %d to PF, err %s, aq_err %s\n", + dev_dbg(&adapter->pdev->dev, "Unable to send opcode %d to PF, err %s, aq_err %s\n", op, i40evf_stat_str(hw, err), i40evf_aq_str(hw, hw->aq.asq_last_status)); return err; @@ -160,7 +160,8 @@ int i40evf_send_vf_config_msg(struct i40evf_adapter *adapter) VIRTCHNL_VF_OFFLOAD_WB_ON_ITR | VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 | VIRTCHNL_VF_OFFLOAD_ENCAP | - VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM; + VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM | + VIRTCHNL_VF_OFFLOAD_REQ_QUEUES; adapter->current_op = VIRTCHNL_OP_GET_VF_RESOURCES; adapter->aq_required &= ~I40EVF_FLAG_AQ_GET_CONFIG; @@ -385,6 +386,33 @@ void i40evf_map_queues(struct i40evf_adapter *adapter) } /** + * i40evf_request_queues + * @adapter: adapter structure + * @num: number of requested queues + * + * We get a default number of queues from the PF. This enables us to request a + * different number. Returns 0 on success, negative on failure + **/ +int i40evf_request_queues(struct i40evf_adapter *adapter, int num) +{ + struct virtchnl_vf_res_request vfres; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot request queues, command %d pending\n", + adapter->current_op); + return -EBUSY; + } + + 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)); +} + +/** * i40evf_add_ether_addrs * @adapter: adapter structure * @addrs: the MAC address filters to add (contiguous) @@ -1068,6 +1096,19 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, "Invalid message %d from PF\n", v_opcode); } break; + 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) { + 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; default: if (adapter->current_op && (v_opcode != adapter->current_op)) dev_warn(&adapter->pdev->dev, "Expected response %d from PF, received %d\n", diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h index 1de82f247312..83cabff1e0ab 100644 --- a/drivers/net/ethernet/intel/igb/e1000_defines.h +++ b/drivers/net/ethernet/intel/igb/e1000_defines.h @@ -353,7 +353,18 @@ #define E1000_RXPBS_CFG_TS_EN 0x80000000 #define I210_RXPBSIZE_DEFAULT 0x000000A2 /* RXPBSIZE default */ +#define I210_RXPBSIZE_MASK 0x0000003F +#define I210_RXPBSIZE_PB_32KB 0x00000020 #define I210_TXPBSIZE_DEFAULT 0x04000014 /* TXPBSIZE default */ +#define I210_TXPBSIZE_MASK 0xC0FFFFFF +#define I210_TXPBSIZE_PB0_8KB (8 << 0) +#define I210_TXPBSIZE_PB1_8KB (8 << 6) +#define I210_TXPBSIZE_PB2_4KB (4 << 12) +#define I210_TXPBSIZE_PB3_4KB (4 << 18) + +#define I210_DTXMXPKTSZ_DEFAULT 0x00000098 + +#define I210_SR_QUEUES_NUM 2 /* SerDes Control */ #define E1000_SCTL_DISABLE_SERDES_LOOPBACK 0x0400 @@ -1051,4 +1062,16 @@ #define E1000_VLAPQF_P_VALID(_n) (0x1 << (3 + (_n) * 4)) #define E1000_VLAPQF_QUEUE_MASK 0x03 +/* TX Qav Control fields */ +#define E1000_TQAVCTRL_XMIT_MODE BIT(0) +#define E1000_TQAVCTRL_DATAFETCHARB BIT(4) +#define E1000_TQAVCTRL_DATATRANARB BIT(8) + +/* TX Qav Credit Control fields */ +#define E1000_TQAVCC_IDLESLOPE_MASK 0xFFFF +#define E1000_TQAVCC_QUEUEMODE BIT(31) + +/* Transmit Descriptor Control fields */ +#define E1000_TXDCTL_PRIORITY BIT(27) + #endif diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h index 31a3f09df9f7..568c96842f28 100644 --- a/drivers/net/ethernet/intel/igb/e1000_regs.h +++ b/drivers/net/ethernet/intel/igb/e1000_regs.h @@ -421,6 +421,14 @@ do { \ #define E1000_I210_FLA 0x1201C +#define E1000_I210_DTXMXPKTSZ 0x355C + +#define E1000_I210_TXDCTL(_n) (0x0E028 + ((_n) * 0x40)) + +#define E1000_I210_TQAVCTRL 0x3570 +#define E1000_I210_TQAVCC(_n) (0x3004 + ((_n) * 0x40)) +#define E1000_I210_TQAVHC(_n) (0x300C + ((_n) * 0x40)) + #define E1000_INVM_DATA_REG(_n) (0x12120 + 4*(_n)) #define E1000_INVM_SIZE 64 /* Number of INVM Data Registers */ diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 06ffb2bc713e..92845692087a 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -281,6 +281,11 @@ struct igb_ring { u16 count; /* number of desc. in the ring */ u8 queue_index; /* logical index of the ring*/ u8 reg_idx; /* physical index of the ring */ + bool cbs_enable; /* indicates if CBS is enabled */ + s32 idleslope; /* idleSlope in kbps */ + s32 sendslope; /* sendSlope in kbps */ + s32 hicredit; /* hiCredit in bytes */ + s32 locredit; /* loCredit in bytes */ /* everything past this point are written often */ u16 next_to_clean; @@ -621,6 +626,7 @@ struct igb_adapter { #define IGB_FLAG_EEE BIT(14) #define IGB_FLAG_VLAN_PROMISC BIT(15) #define IGB_FLAG_RX_LEGACY BIT(16) +#define IGB_FLAG_FQTSS BIT(17) /* Media Auto Sense */ #define IGB_MAS_ENABLE_0 0X0001 diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 18b6c25d4705..e94d3c256667 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -34,6 +34,7 @@ #include <linux/slab.h> #include <net/checksum.h> #include <net/ip6_checksum.h> +#include <net/pkt_sched.h> #include <linux/net_tstamp.h> #include <linux/mii.h> #include <linux/ethtool.h> @@ -62,6 +63,17 @@ #define BUILD 0 #define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) "." \ __stringify(BUILD) "-k" + +enum queue_mode { + QUEUE_MODE_STRICT_PRIORITY, + QUEUE_MODE_STREAM_RESERVATION, +}; + +enum tx_queue_prio { + TX_QUEUE_PRIO_HIGH, + TX_QUEUE_PRIO_LOW, +}; + char igb_driver_name[] = "igb"; char igb_driver_version[] = DRV_VERSION; static const char igb_driver_string[] = @@ -133,8 +145,8 @@ 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, @@ -1271,6 +1283,12 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter, ring->count = adapter->tx_ring_count; ring->queue_index = txr_idx; + ring->cbs_enable = false; + ring->idleslope = 0; + ring->sendslope = 0; + ring->hicredit = 0; + ring->locredit = 0; + u64_stats_init(&ring->tx_syncp); u64_stats_init(&ring->tx_syncp2); @@ -1598,6 +1616,284 @@ static void igb_get_hw_control(struct igb_adapter *adapter) ctrl_ext | E1000_CTRL_EXT_DRV_LOAD); } +static void enable_fqtss(struct igb_adapter *adapter, bool enable) +{ + struct net_device *netdev = adapter->netdev; + struct e1000_hw *hw = &adapter->hw; + + WARN_ON(hw->mac.type != e1000_i210); + + if (enable) + adapter->flags |= IGB_FLAG_FQTSS; + else + adapter->flags &= ~IGB_FLAG_FQTSS; + + if (netif_running(netdev)) + schedule_work(&adapter->reset_task); +} + +static bool is_fqtss_enabled(struct igb_adapter *adapter) +{ + return (adapter->flags & IGB_FLAG_FQTSS) ? true : false; +} + +static void set_tx_desc_fetch_prio(struct e1000_hw *hw, int queue, + enum tx_queue_prio prio) +{ + u32 val; + + WARN_ON(hw->mac.type != e1000_i210); + WARN_ON(queue < 0 || queue > 4); + + val = rd32(E1000_I210_TXDCTL(queue)); + + if (prio == TX_QUEUE_PRIO_HIGH) + val |= E1000_TXDCTL_PRIORITY; + else + val &= ~E1000_TXDCTL_PRIORITY; + + wr32(E1000_I210_TXDCTL(queue), val); +} + +static void set_queue_mode(struct e1000_hw *hw, int queue, enum queue_mode mode) +{ + u32 val; + + WARN_ON(hw->mac.type != e1000_i210); + WARN_ON(queue < 0 || queue > 1); + + val = rd32(E1000_I210_TQAVCC(queue)); + + if (mode == QUEUE_MODE_STREAM_RESERVATION) + val |= E1000_TQAVCC_QUEUEMODE; + else + val &= ~E1000_TQAVCC_QUEUEMODE; + + wr32(E1000_I210_TQAVCC(queue), val); +} + +/** + * igb_configure_cbs - Configure Credit-Based Shaper (CBS) + * @adapter: pointer to adapter struct + * @queue: queue number + * @enable: true = enable CBS, false = disable CBS + * @idleslope: idleSlope in kbps + * @sendslope: sendSlope in kbps + * @hicredit: hiCredit in bytes + * @locredit: loCredit in bytes + * + * Configure CBS for a given hardware queue. When disabling, idleslope, + * sendslope, hicredit, locredit arguments are ignored. Returns 0 if + * success. Negative otherwise. + **/ +static void igb_configure_cbs(struct igb_adapter *adapter, int queue, + bool enable, int idleslope, int sendslope, + int hicredit, int locredit) +{ + struct net_device *netdev = adapter->netdev; + struct e1000_hw *hw = &adapter->hw; + u32 tqavcc; + u16 value; + + WARN_ON(hw->mac.type != e1000_i210); + WARN_ON(queue < 0 || queue > 1); + + if (enable) { + set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH); + set_queue_mode(hw, queue, QUEUE_MODE_STREAM_RESERVATION); + + /* According to i210 datasheet section 7.2.7.7, we should set + * the 'idleSlope' field from TQAVCC register following the + * equation: + * + * For 100 Mbps link speed: + * + * value = BW * 0x7735 * 0.2 (E1) + * + * For 1000Mbps link speed: + * + * value = BW * 0x7735 * 2 (E2) + * + * E1 and E2 can be merged into one equation as shown below. + * Note that 'link-speed' is in Mbps. + * + * value = BW * 0x7735 * 2 * link-speed + * -------------- (E3) + * 1000 + * + * 'BW' is the percentage bandwidth out of full link speed + * which can be found with the following equation. Note that + * idleSlope here is the parameter from this function which + * is in kbps. + * + * BW = idleSlope + * ----------------- (E4) + * link-speed * 1000 + * + * That said, we can come up with a generic equation to + * calculate the value we should set it TQAVCC register by + * replacing 'BW' in E3 by E4. The resulting equation is: + * + * value = idleSlope * 0x7735 * 2 * link-speed + * ----------------- -------------- (E5) + * link-speed * 1000 1000 + * + * 'link-speed' is present in both sides of the fraction so + * it is canceled out. The final equation is the following: + * + * value = idleSlope * 61034 + * ----------------- (E6) + * 1000000 + */ + value = DIV_ROUND_UP_ULL(idleslope * 61034ULL, 1000000); + + tqavcc = rd32(E1000_I210_TQAVCC(queue)); + tqavcc &= ~E1000_TQAVCC_IDLESLOPE_MASK; + tqavcc |= value; + wr32(E1000_I210_TQAVCC(queue), tqavcc); + + wr32(E1000_I210_TQAVHC(queue), 0x80000000 + hicredit * 0x7735); + } else { + set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_LOW); + set_queue_mode(hw, queue, QUEUE_MODE_STRICT_PRIORITY); + + /* Set idleSlope to zero. */ + tqavcc = rd32(E1000_I210_TQAVCC(queue)); + tqavcc &= ~E1000_TQAVCC_IDLESLOPE_MASK; + wr32(E1000_I210_TQAVCC(queue), tqavcc); + + /* Set hiCredit to zero. */ + wr32(E1000_I210_TQAVHC(queue), 0); + } + + /* XXX: In i210 controller the sendSlope and loCredit parameters from + * CBS are not configurable by software so we don't do any 'controller + * configuration' in respect to these parameters. + */ + + netdev_dbg(netdev, "CBS %s: queue %d idleslope %d sendslope %d hiCredit %d locredit %d\n", + (enable) ? "enabled" : "disabled", queue, + idleslope, sendslope, hicredit, locredit); +} + +static int igb_save_cbs_params(struct igb_adapter *adapter, int queue, + bool enable, int idleslope, int sendslope, + int hicredit, int locredit) +{ + struct igb_ring *ring; + + if (queue < 0 || queue > adapter->num_tx_queues) + return -EINVAL; + + ring = adapter->tx_ring[queue]; + + ring->cbs_enable = enable; + ring->idleslope = idleslope; + ring->sendslope = sendslope; + ring->hicredit = hicredit; + ring->locredit = locredit; + + return 0; +} + +static bool is_any_cbs_enabled(struct igb_adapter *adapter) +{ + struct igb_ring *ring; + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) { + ring = adapter->tx_ring[i]; + + if (ring->cbs_enable) + return true; + } + + return false; +} + +static void igb_setup_tx_mode(struct igb_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct e1000_hw *hw = &adapter->hw; + u32 val; + + /* Only i210 controller supports changing the transmission mode. */ + if (hw->mac.type != e1000_i210) + return; + + if (is_fqtss_enabled(adapter)) { + int i, max_queue; + + /* Configure TQAVCTRL register: set transmit mode to 'Qav', + * set data fetch arbitration to 'round robin' and set data + * transfer arbitration to 'credit shaper algorithm. + */ + val = rd32(E1000_I210_TQAVCTRL); + val |= E1000_TQAVCTRL_XMIT_MODE | E1000_TQAVCTRL_DATATRANARB; + val &= ~E1000_TQAVCTRL_DATAFETCHARB; + wr32(E1000_I210_TQAVCTRL, val); + + /* Configure Tx and Rx packet buffers sizes as described in + * i210 datasheet section 7.2.7.7. + */ + val = rd32(E1000_TXPBS); + val &= ~I210_TXPBSIZE_MASK; + val |= I210_TXPBSIZE_PB0_8KB | I210_TXPBSIZE_PB1_8KB | + I210_TXPBSIZE_PB2_4KB | I210_TXPBSIZE_PB3_4KB; + wr32(E1000_TXPBS, val); + + val = rd32(E1000_RXPBS); + val &= ~I210_RXPBSIZE_MASK; + val |= I210_RXPBSIZE_PB_32KB; + wr32(E1000_RXPBS, val); + + /* Section 8.12.9 states that MAX_TPKT_SIZE from DTXMXPKTSZ + * register should not exceed the buffer size programmed in + * TXPBS. The smallest buffer size programmed in TXPBS is 4kB + * so according to the datasheet we should set MAX_TPKT_SIZE to + * 4kB / 64. + * + * However, when we do so, no frame from queue 2 and 3 are + * transmitted. It seems the MAX_TPKT_SIZE should not be great + * or _equal_ to the buffer size programmed in TXPBS. For this + * reason, we set set MAX_ TPKT_SIZE to (4kB - 1) / 64. + */ + val = (4096 - 1) / 64; + wr32(E1000_I210_DTXMXPKTSZ, val); + + /* Since FQTSS mode is enabled, apply any CBS configuration + * previously set. If no previous CBS configuration has been + * done, then the initial configuration is applied, which means + * CBS is disabled. + */ + max_queue = (adapter->num_tx_queues < I210_SR_QUEUES_NUM) ? + adapter->num_tx_queues : I210_SR_QUEUES_NUM; + + for (i = 0; i < max_queue; i++) { + struct igb_ring *ring = adapter->tx_ring[i]; + + igb_configure_cbs(adapter, i, ring->cbs_enable, + ring->idleslope, ring->sendslope, + ring->hicredit, ring->locredit); + } + } else { + wr32(E1000_RXPBS, I210_RXPBSIZE_DEFAULT); + wr32(E1000_TXPBS, I210_TXPBSIZE_DEFAULT); + wr32(E1000_I210_DTXMXPKTSZ, I210_DTXMXPKTSZ_DEFAULT); + + val = rd32(E1000_I210_TQAVCTRL); + /* According to Section 8.12.21, the other flags we've set when + * enabling FQTSS are not relevant when disabling FQTSS so we + * don't set they here. + */ + val &= ~E1000_TQAVCTRL_XMIT_MODE; + wr32(E1000_I210_TQAVCTRL, val); + } + + netdev_dbg(netdev, "FQTSS %s\n", (is_fqtss_enabled(adapter)) ? + "enabled" : "disabled"); +} + /** * igb_configure - configure the hardware for RX and TX * @adapter: private board structure @@ -1609,6 +1905,7 @@ static void igb_configure(struct igb_adapter *adapter) igb_get_hw_control(adapter); igb_set_rx_mode(netdev); + igb_setup_tx_mode(adapter); igb_restore_vlan(adapter); @@ -2150,6 +2447,55 @@ igb_features_check(struct sk_buff *skb, struct net_device *dev, return features; } +static int igb_offload_cbs(struct igb_adapter *adapter, + struct tc_cbs_qopt_offload *qopt) +{ + struct e1000_hw *hw = &adapter->hw; + int err; + + /* CBS offloading is only supported by i210 controller. */ + if (hw->mac.type != e1000_i210) + return -EOPNOTSUPP; + + /* CBS offloading is only supported by queue 0 and queue 1. */ + if (qopt->queue < 0 || qopt->queue > 1) + return -EINVAL; + + err = igb_save_cbs_params(adapter, qopt->queue, qopt->enable, + qopt->idleslope, qopt->sendslope, + qopt->hicredit, qopt->locredit); + if (err) + return err; + + if (is_fqtss_enabled(adapter)) { + igb_configure_cbs(adapter, qopt->queue, qopt->enable, + qopt->idleslope, qopt->sendslope, + qopt->hicredit, qopt->locredit); + + if (!is_any_cbs_enabled(adapter)) + enable_fqtss(adapter, false); + + } else { + enable_fqtss(adapter, true); + } + + return 0; +} + +static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) +{ + struct igb_adapter *adapter = netdev_priv(dev); + + switch (type) { + case TC_SETUP_QDISC_CBS: + return igb_offload_cbs(adapter, type_data); + + default: + return -EOPNOTSUPP; + } +} + static const struct net_device_ops igb_netdev_ops = { .ndo_open = igb_open, .ndo_stop = igb_close, @@ -2175,6 +2521,7 @@ static const struct net_device_ops igb_netdev_ops = { .ndo_set_features = igb_set_features, .ndo_fdb_add = igb_ndo_fdb_add, .ndo_features_check = igb_features_check, + .ndo_setup_tc = igb_setup_tc, }; /** @@ -2538,10 +2885,8 @@ 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 +3507,8 @@ 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 +4770,9 @@ 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 +4859,9 @@ 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 5a713199653c..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); @@ -508,9 +508,7 @@ ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) adapter->part_num = ixgb_get_ee_pba_number(&adapter->hw); - init_timer(&adapter->watchdog_timer); - adapter->watchdog_timer.function = ixgb_watchdog; - adapter->watchdog_timer.data = (unsigned long)adapter; + timer_setup(&adapter->watchdog_timer, ixgb_watchdog, 0); INIT_WORK(&adapter->tx_timeout_task, ixgb_tx_timeout_task); @@ -1152,9 +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_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 6e6ab6f6875e..9bef255f6a18 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -3781,10 +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, @@ -4081,8 +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 c3e7a8191128..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)}, @@ -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 935a2f15b0b0..ca06c3cc2ca8 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; } @@ -2133,6 +2134,21 @@ static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring, #if L1_CACHE_BYTES < 128 prefetch(xdp->data + L1_CACHE_BYTES); #endif + /* Note, we get here by enabling legacy-rx via: + * + * ethtool --set-priv-flags <dev> legacy-rx on + * + * In this mode, we currently get 0 extra XDP headroom as + * opposed to having legacy-rx off, where we process XDP + * packets going to stack via ixgbe_build_skb(). The latter + * provides us currently with 192 bytes of headroom. + * + * For ixgbe_construct_skb() mode it means that the + * xdp->data_meta will always point to xdp->data, since + * the helper cannot expand the head. Should this ever + * change in future for legacy-rx mode on, then lets also + * add xdp->data_meta handling here. + */ /* allocate a skb to store the frags */ skb = napi_alloc_skb(&rx_ring->q_vector->napi, IXGBE_RX_HDR_SIZE); @@ -2165,6 +2181,7 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, struct xdp_buff *xdp, union ixgbe_adv_rx_desc *rx_desc) { + unsigned int metasize = xdp->data - xdp->data_meta; #if (PAGE_SIZE < 8192) unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2; #else @@ -2174,10 +2191,14 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, #endif struct sk_buff *skb; - /* prefetch first cache line of first page */ - prefetch(xdp->data); + /* Prefetch first cache line of first page. If xdp->data_meta + * is unused, this points extactly as xdp->data, otherwise we + * likely have a consumer accessing first few bytes of meta + * data, and then actual data. + */ + prefetch(xdp->data_meta); #if L1_CACHE_BYTES < 128 - prefetch(xdp->data + L1_CACHE_BYTES); + prefetch(xdp->data_meta + L1_CACHE_BYTES); #endif /* build an skb to around the page buffer */ @@ -2188,6 +2209,8 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, /* update pointers within the skb to store the data */ skb_reserve(skb, xdp->data - xdp->data_hard_start); __skb_put(skb, xdp->data_end - xdp->data); + if (metasize) + skb_metadata_set(skb, metasize); /* record DMA address if this is the start of a chain of buffers */ if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)) @@ -2326,6 +2349,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, if (!skb) { xdp.data = page_address(rx_buffer->page) + rx_buffer->page_offset; + xdp.data_meta = xdp.data; xdp.data_hard_start = xdp.data - ixgbe_rx_offset(rx_ring); xdp.data_end = xdp.data + size; @@ -2516,50 +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; } /** @@ -2601,34 +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; @@ -6771,6 +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) || @@ -6791,6 +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; @@ -6798,6 +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; @@ -7554,9 +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 */ @@ -9223,13 +9359,10 @@ free_jump: return err; } -static int ixgbe_setup_tc_cls_u32(struct net_device *dev, +static int ixgbe_setup_tc_cls_u32(struct ixgbe_adapter *adapter, struct tc_cls_u32_offload *cls_u32) { - struct ixgbe_adapter *adapter = netdev_priv(dev); - - if (!is_classid_clsact_ingress(cls_u32->common.classid) || - cls_u32->common.chain_index) + if (cls_u32->common.chain_index) return -EOPNOTSUPP; switch (cls_u32->command) { @@ -9248,6 +9381,43 @@ static int ixgbe_setup_tc_cls_u32(struct net_device *dev, } } +static int ixgbe_setup_tc_block_cb(enum tc_setup_type type, void *type_data, + void *cb_priv) +{ + struct ixgbe_adapter *adapter = cb_priv; + + if (!tc_can_offload(adapter->netdev)) + return -EOPNOTSUPP; + + switch (type) { + case TC_SETUP_CLSU32: + return ixgbe_setup_tc_cls_u32(adapter, type_data); + default: + return -EOPNOTSUPP; + } +} + +static int ixgbe_setup_tc_block(struct net_device *dev, + struct tc_block_offload *f) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + + if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) + return -EOPNOTSUPP; + + switch (f->command) { + case TC_BLOCK_BIND: + return tcf_block_cb_register(f->block, ixgbe_setup_tc_block_cb, + adapter, adapter); + case TC_BLOCK_UNBIND: + tcf_block_cb_unregister(f->block, ixgbe_setup_tc_block_cb, + adapter); + return 0; + default: + return -EOPNOTSUPP; + } +} + static int ixgbe_setup_tc_mqprio(struct net_device *dev, struct tc_mqprio_qopt *mqprio) { @@ -9259,9 +9429,9 @@ static int __ixgbe_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { switch (type) { - case TC_SETUP_CLSU32: - return ixgbe_setup_tc_cls_u32(dev, type_data); - case TC_SETUP_MQPRIO: + case TC_SETUP_BLOCK: + return ixgbe_setup_tc_block(dev, type_data); + case TC_SETUP_QDISC_MQPRIO: return ixgbe_setup_tc_mqprio(dev, type_data); default: return -EOPNOTSUPP; @@ -9733,6 +9903,17 @@ 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, @@ -9823,7 +10004,7 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) return 0; } -static int ixgbe_xdp(struct net_device *dev, struct netdev_xdp *xdp) +static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp) { struct ixgbe_adapter *adapter = netdev_priv(dev); @@ -9932,7 +10113,7 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_udp_tunnel_add = ixgbe_add_udp_tunnel_port, .ndo_udp_tunnel_del = ixgbe_del_udp_tunnel_port, .ndo_features_check = ixgbe_features_check, - .ndo_xdp = ixgbe_xdp, + .ndo_bpf = ixgbe_xdp, .ndo_xdp_xmit = ixgbe_xdp_xmit, .ndo_xdp_flush = ixgbe_xdp_flush, }; @@ -10355,8 +10536,7 @@ 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; @@ -10712,6 +10892,9 @@ 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 cacb30682434..feed11bc9ddf 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); |