diff options
Diffstat (limited to 'drivers/net/ethernet/intel/i40e/i40e_main.c')
-rw-r--r-- | drivers/net/ethernet/intel/i40e/i40e_main.c | 422 |
1 files changed, 269 insertions, 153 deletions
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 8f3b53e0dc46..70d9605a0d9e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1,7 +1,7 @@ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2015 Intel Corporation. + * Copyright(c) 2013 - 2016 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, @@ -28,11 +28,6 @@ #include <linux/of_net.h> #include <linux/pci.h> -#ifdef CONFIG_SPARC -#include <asm/idprom.h> -#include <asm/prom.h> -#endif - /* Local includes */ #include "i40e.h" #include "i40e_diag.h" @@ -51,7 +46,7 @@ static const char i40e_driver_string[] = #define DRV_VERSION_MAJOR 1 #define DRV_VERSION_MINOR 4 -#define DRV_VERSION_BUILD 8 +#define DRV_VERSION_BUILD 25 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) DRV_KERN @@ -90,6 +85,8 @@ static const struct pci_device_id i40e_pci_tbl[] = { {PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T4), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2), 0}, + {PCI_VDEVICE(INTEL, I40E_DEV_ID_KX_X722), 0}, + {PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_X722), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_SFP_X722), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_1G_BASE_T_X722), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T_X722), 0}, @@ -110,6 +107,8 @@ MODULE_DESCRIPTION("Intel(R) Ethernet Connection XL710 Network Driver"); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); +static struct workqueue_struct *i40e_wq; + /** * i40e_allocate_dma_mem_d - OS specific memory alloc for shared code * @hw: pointer to the HW structure @@ -295,7 +294,7 @@ static void i40e_service_event_schedule(struct i40e_pf *pf) if (!test_bit(__I40E_DOWN, &pf->state) && !test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state) && !test_and_set_bit(__I40E_SERVICE_SCHED, &pf->state)) - schedule_work(&pf->service_task); + queue_work(i40e_wq, &pf->service_task); } /** @@ -769,7 +768,7 @@ static void i40e_update_fcoe_stats(struct i40e_vsi *vsi) if (vsi->type != I40E_VSI_FCOE) return; - idx = (pf->pf_seid - I40E_BASE_PF_SEID) + I40E_FCOE_PF_STAT_OFFSET; + idx = hw->pf_id + I40E_FCOE_PF_STAT_OFFSET; fs = &vsi->fcoe_stats; ofs = &vsi->fcoe_stats_offsets; @@ -820,6 +819,7 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) struct i40e_eth_stats *oes; struct i40e_eth_stats *es; /* device's eth stats */ u32 tx_restart, tx_busy; + u64 tx_lost_interrupt; struct i40e_ring *p; u32 rx_page, rx_buf; u64 bytes, packets; @@ -845,6 +845,7 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) rx_b = rx_p = 0; tx_b = tx_p = 0; tx_restart = tx_busy = tx_linearize = tx_force_wb = 0; + tx_lost_interrupt = 0; rx_page = 0; rx_buf = 0; rcu_read_lock(); @@ -863,6 +864,7 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) tx_busy += p->tx_stats.tx_busy; tx_linearize += p->tx_stats.tx_linearize; tx_force_wb += p->tx_stats.tx_force_wb; + tx_lost_interrupt += p->tx_stats.tx_lost_interrupt; /* Rx queue is part of the same block as Tx queue */ p = &p[1]; @@ -881,6 +883,7 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) vsi->tx_busy = tx_busy; vsi->tx_linearize = tx_linearize; vsi->tx_force_wb = tx_force_wb; + vsi->tx_lost_interrupt = tx_lost_interrupt; vsi->rx_page_failed = rx_page; vsi->rx_buf_failed = rx_buf; @@ -1368,7 +1371,7 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi, f->changed = true; INIT_LIST_HEAD(&f->list); - list_add(&f->list, &vsi->mac_filter_list); + list_add_tail(&f->list, &vsi->mac_filter_list); } /* increment counter and add a new flag if needed */ @@ -1538,7 +1541,11 @@ static int i40e_set_mac(struct net_device *netdev, void *p) ether_addr_copy(netdev->dev_addr, addr->sa_data); - return i40e_sync_vsi_filters(vsi); + /* schedule our worker thread which will take care of + * applying the new filter changes + */ + i40e_service_event_schedule(vsi->back); + return 0; } /** @@ -1762,6 +1769,11 @@ bottom_of_search_loop: 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); } /** @@ -1933,7 +1945,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) sizeof(struct i40e_aqc_remove_macvlan_element_data); del_list_size = filter_list_len * sizeof(struct i40e_aqc_remove_macvlan_element_data); - del_list = kzalloc(del_list_size, GFP_KERNEL); + del_list = kzalloc(del_list_size, GFP_ATOMIC); if (!del_list) { i40e_cleanup_add_list(&tmp_add_list); @@ -2011,7 +2023,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) sizeof(struct i40e_aqc_add_macvlan_element_data), add_list_size = filter_list_len * sizeof(struct i40e_aqc_add_macvlan_element_data); - add_list = kzalloc(add_list_size, GFP_KERNEL); + add_list = kzalloc(add_list_size, GFP_ATOMIC); if (!add_list) { /* Purge element from temporary lists */ i40e_cleanup_add_list(&tmp_add_list); @@ -2110,7 +2122,9 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) cur_promisc = (!!(vsi->current_netdev_flags & IFF_PROMISC) || test_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state)); - if (vsi->type == I40E_VSI_MAIN && pf->lan_veb != I40E_NO_VEB) { + if ((vsi->type == I40E_VSI_MAIN) && + (pf->lan_veb != I40E_NO_VEB) && + !(pf->flags & I40E_FLAG_MFP_ENABLED)) { /* set defport ON for Main VSI instead of true promisc * this way we will get all unicast/multicast and VLAN * promisc behavior but will not get VF or VMDq traffic @@ -2160,6 +2174,10 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) } } out: + /* if something went wrong then set the changed flag so we try again */ + if (retval) + vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; + clear_bit(__I40E_CONFIG_BUSY, &vsi->state); return retval; } @@ -3106,11 +3124,11 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi) struct i40e_q_vector *q_vector = vsi->q_vectors[i]; q_vector->itr_countdown = ITR_COUNTDOWN_START; - q_vector->rx.itr = ITR_TO_REG(vsi->rx_itr_setting); + q_vector->rx.itr = ITR_TO_REG(vsi->rx_rings[i]->rx_itr_setting); q_vector->rx.latency_range = I40E_LOW_LATENCY; wr32(hw, I40E_PFINT_ITRN(I40E_RX_ITR, vector - 1), q_vector->rx.itr); - q_vector->tx.itr = ITR_TO_REG(vsi->tx_itr_setting); + q_vector->tx.itr = ITR_TO_REG(vsi->tx_rings[i]->tx_itr_setting); q_vector->tx.latency_range = I40E_LOW_LATENCY; wr32(hw, I40E_PFINT_ITRN(I40E_TX_ITR, vector - 1), q_vector->tx.itr); @@ -3202,10 +3220,10 @@ static void i40e_configure_msi_and_legacy(struct i40e_vsi *vsi) /* set the ITR configuration */ q_vector->itr_countdown = ITR_COUNTDOWN_START; - q_vector->rx.itr = ITR_TO_REG(vsi->rx_itr_setting); + q_vector->rx.itr = ITR_TO_REG(vsi->rx_rings[0]->rx_itr_setting); q_vector->rx.latency_range = I40E_LOW_LATENCY; wr32(hw, I40E_PFINT_ITR0(I40E_RX_ITR), q_vector->rx.itr); - q_vector->tx.itr = ITR_TO_REG(vsi->tx_itr_setting); + q_vector->tx.itr = ITR_TO_REG(vsi->tx_rings[0]->tx_itr_setting); q_vector->tx.latency_range = I40E_LOW_LATENCY; wr32(hw, I40E_PFINT_ITR0(I40E_TX_ITR), q_vector->tx.itr); @@ -3245,14 +3263,15 @@ 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) +void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf, bool clearpba) { struct i40e_hw *hw = &pf->hw; u32 val; val = I40E_PFINT_DYN_CTL0_INTENA_MASK | - I40E_PFINT_DYN_CTL0_CLEARPBA_MASK | + (clearpba ? I40E_PFINT_DYN_CTL0_CLEARPBA_MASK : 0) | (I40E_ITR_NONE << I40E_PFINT_DYN_CTL0_ITR_INDX_SHIFT); wr32(hw, I40E_PFINT_DYN_CTL0, val); @@ -3260,22 +3279,6 @@ void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf) } /** - * i40e_irq_dynamic_disable - Disable default interrupt generation settings - * @vsi: pointer to a vsi - * @vector: disable a particular Hw Interrupt vector - **/ -void i40e_irq_dynamic_disable(struct i40e_vsi *vsi, int vector) -{ - struct i40e_pf *pf = vsi->back; - struct i40e_hw *hw = &pf->hw; - u32 val; - - val = I40E_ITR_NONE << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT; - wr32(hw, I40E_PFINT_DYN_CTLN(vector - 1), val); - i40e_flush(hw); -} - -/** * i40e_msix_clean_rings - MSIX mode Interrupt Handler * @irq: interrupt number * @data: pointer to a q_vector @@ -3400,7 +3403,7 @@ 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); + i40e_irq_dynamic_enable_icr0(pf, true); } i40e_flush(&pf->hw); @@ -3459,16 +3462,12 @@ static irqreturn_t i40e_intr(int irq, void *data) struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; struct i40e_q_vector *q_vector = vsi->q_vectors[0]; - /* temporarily disable queue cause for NAPI processing */ - u32 qval = rd32(hw, I40E_QINT_RQCTL(0)); - - qval &= ~I40E_QINT_RQCTL_CAUSE_ENA_MASK; - wr32(hw, I40E_QINT_RQCTL(0), qval); - - qval = rd32(hw, I40E_QINT_TQCTL(0)); - qval &= ~I40E_QINT_TQCTL_CAUSE_ENA_MASK; - wr32(hw, I40E_QINT_TQCTL(0), qval); - + /* We do not have a way to disarm Queue causes while leaving + * interrupt enabled for all other causes, ideally + * interrupt should be disabled while we are in NAPI but + * this is not a performance path and napi_schedule() + * can deal with rescheduling. + */ if (!test_bit(__I40E_DOWN, &pf->state)) napi_schedule_irqoff(&q_vector->napi); } @@ -3476,6 +3475,7 @@ static irqreturn_t i40e_intr(int irq, void *data) if (icr0 & I40E_PFINT_ICR0_ADMINQ_MASK) { ena_mask &= ~I40E_PFINT_ICR0_ENA_ADMINQ_MASK; set_bit(__I40E_ADMINQ_EVENT_PENDING, &pf->state); + i40e_debug(&pf->hw, I40E_DEBUG_NVM, "AdminQ event\n"); } if (icr0 & I40E_PFINT_ICR0_MAL_DETECT_MASK) { @@ -3546,7 +3546,7 @@ 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); + i40e_irq_dynamic_enable_icr0(pf, false); } return ret; @@ -3750,7 +3750,7 @@ static int i40e_vsi_request_irq(struct i40e_vsi *vsi, char *basename) #ifdef CONFIG_NET_POLL_CONTROLLER /** - * i40e_netpoll - A Polling 'interrupt'handler + * i40e_netpoll - A Polling 'interrupt' handler * @netdev: network interface device structure * * This is used by netconsole to send skbs without having to re-enable @@ -3929,6 +3929,9 @@ static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable) else rx_reg &= ~I40E_QRX_ENA_QENA_REQ_MASK; wr32(hw, I40E_QRX_ENA(pf_q), rx_reg); + /* No waiting for the Tx queue to disable */ + if (!enable && test_bit(__I40E_PORT_TX_SUSPENDED, &pf->state)) + continue; /* wait for the change to finish */ ret = i40e_pf_rxq_wait(pf, pf_q, enable); @@ -4287,12 +4290,12 @@ static void i40e_pf_unquiesce_all_vsi(struct i40e_pf *pf) #ifdef CONFIG_I40E_DCB /** - * i40e_vsi_wait_txq_disabled - Wait for VSI's queues to be disabled + * i40e_vsi_wait_queues_disabled - Wait for VSI's queues to be disabled * @vsi: the VSI being configured * - * This function waits for the given VSI's Tx queues to be disabled. + * This function waits for the given VSI's queues to be disabled. **/ -static int i40e_vsi_wait_txq_disabled(struct i40e_vsi *vsi) +static int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi) { struct i40e_pf *pf = vsi->back; int i, pf_q, ret; @@ -4309,24 +4312,36 @@ static int i40e_vsi_wait_txq_disabled(struct i40e_vsi *vsi) } } + pf_q = vsi->base_queue; + for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) { + /* Check and wait for the disable status of the queue */ + ret = i40e_pf_rxq_wait(pf, pf_q, false); + if (ret) { + dev_info(&pf->pdev->dev, + "VSI seid %d Rx ring %d disable timeout\n", + vsi->seid, pf_q); + return ret; + } + } + return 0; } /** - * i40e_pf_wait_txq_disabled - Wait for all queues of PF VSIs to be disabled + * i40e_pf_wait_queues_disabled - Wait for all queues of PF VSIs to be disabled * @pf: the PF * - * This function waits for the Tx queues to be in disabled state for all the + * This function waits for the queues to be in disabled state for all the * VSIs that are managed by this PF. **/ -static int i40e_pf_wait_txq_disabled(struct i40e_pf *pf) +static int i40e_pf_wait_queues_disabled(struct i40e_pf *pf) { int v, ret = 0; for (v = 0; v < pf->hw.func_caps.num_vsis; v++) { /* No need to wait for FCoE VSI queues */ if (pf->vsi[v] && pf->vsi[v]->type != I40E_VSI_FCOE) { - ret = i40e_vsi_wait_txq_disabled(pf->vsi[v]); + ret = i40e_vsi_wait_queues_disabled(pf->vsi[v]); if (ret) break; } @@ -4352,7 +4367,7 @@ static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi) { struct i40e_ring *tx_ring = NULL; struct i40e_pf *pf; - u32 head, val, tx_pending; + u32 head, val, tx_pending_hw; int i; pf = vsi->back; @@ -4378,16 +4393,9 @@ static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi) else val = rd32(&pf->hw, I40E_PFINT_DYN_CTL0); - /* Bail out if interrupts are disabled because napi_poll - * execution in-progress or will get scheduled soon. - * napi_poll cleans TX and RX queues and updates 'next_to_clean'. - */ - if (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK)) - return; - head = i40e_get_head(tx_ring); - tx_pending = i40e_get_tx_pending(tx_ring); + tx_pending_hw = i40e_get_tx_pending(tx_ring, false); /* HW is done executing descriptors, updated HEAD write back, * but SW hasn't processed those descriptors. If interrupt is @@ -4395,12 +4403,12 @@ static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi) * dev_watchdog detecting timeout on those netdev_queue, * hence proactively trigger SW interrupt. */ - if (tx_pending) { + if (tx_pending_hw && (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK))) { /* NAPI Poll didn't run and clear since it was set */ if (test_and_clear_bit(I40E_Q_VECTOR_HUNG_DETECT, &tx_ring->q_vector->hung_detected)) { - netdev_info(vsi->netdev, "VSI_seid %d, Hung TX queue %d, tx_pending: %d, NTC:0x%x, HWB: 0x%x, NTU: 0x%x, TAIL: 0x%x\n", - vsi->seid, q_idx, tx_pending, + netdev_info(vsi->netdev, "VSI_seid %d, Hung TX queue %d, tx_pending_hw: %d, NTC:0x%x, HWB: 0x%x, NTU: 0x%x, TAIL: 0x%x\n", + vsi->seid, q_idx, tx_pending_hw, tx_ring->next_to_clean, head, tx_ring->next_to_use, readl(tx_ring->tail)); @@ -4413,6 +4421,17 @@ static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi) &tx_ring->q_vector->hung_detected); } } + + /* This is the case where we have interrupts missing, + * so the tx_pending in HW will most likely be 0, but we + * will have tx_pending in SW since the WB happened but the + * interrupt got lost. + */ + if ((!tx_pending_hw) && i40e_get_tx_pending(tx_ring, true) && + (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK))) { + if (napi_reschedule(&tx_ring->q_vector->napi)) + tx_ring->tx_stats.tx_lost_interrupt++; + } } /** @@ -5016,8 +5035,7 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf) int err = 0; /* Do not enable DCB for SW1 and SW2 images even if the FW is capable */ - if (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 33)) || - (pf->hw.aq.fw_maj_ver < 4)) + if (pf->flags & I40E_FLAG_NO_DCB_SUPPORT) goto out; /* Get the initial DCB configuration */ @@ -5249,11 +5267,7 @@ void i40e_down(struct i40e_vsi *vsi) * @netdev: net device to configure * @tc: number of traffic classes to enable **/ -#ifdef I40E_FCOE -int i40e_setup_tc(struct net_device *netdev, u8 tc) -#else static int i40e_setup_tc(struct net_device *netdev, u8 tc) -#endif { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; @@ -5306,6 +5320,19 @@ exit: return ret; } +#ifdef I40E_FCOE +int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto, + struct tc_to_netdev *tc) +#else +static int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto, + struct tc_to_netdev *tc) +#endif +{ + if (handle != TC_H_ROOT || tc->type != TC_SETUP_MQPRIO) + return -EINVAL; + return i40e_setup_tc(netdev, tc->tc); +} + /** * i40e_open - Called when a network interface is made active * @netdev: network interface device structure @@ -5348,7 +5375,8 @@ int i40e_open(struct net_device *netdev) vxlan_get_rx_port(netdev); #endif #ifdef CONFIG_I40E_GENEVE - geneve_get_rx_port(netdev); + if (pf->flags & I40E_FLAG_GENEVE_OFFLOAD_CAPABLE) + geneve_get_rx_port(netdev); #endif return 0; @@ -5713,8 +5741,8 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf, if (ret) goto exit; - /* Wait for the PF's Tx queues to be disabled */ - ret = i40e_pf_wait_txq_disabled(pf); + /* Wait for the PF's queues to be disabled */ + ret = i40e_pf_wait_queues_disabled(pf); if (ret) { /* Schedule PF reset to recover */ set_bit(__I40E_PF_RESET_REQUESTED, &pf->state); @@ -6244,6 +6272,7 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf) if (hw->debug_mask & I40E_DEBUG_AQ) dev_info(&pf->pdev->dev, "ARQ Overflow Error detected\n"); val &= ~I40E_PF_ARQLEN_ARQOVFL_MASK; + pf->arq_overflows++; } if (val & I40E_PF_ARQLEN_ARQCRIT_MASK) { if (hw->debug_mask & I40E_DEBUG_AQ) @@ -6319,7 +6348,9 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf) case i40e_aqc_opc_nvm_erase: case i40e_aqc_opc_nvm_update: case i40e_aqc_opc_oem_post_update: - i40e_debug(&pf->hw, I40E_DEBUG_NVM, "ARQ NVM operation completed\n"); + i40e_debug(&pf->hw, I40E_DEBUG_NVM, + "ARQ NVM operation 0x%04x completed\n", + opcode); break; default: dev_info(&pf->pdev->dev, @@ -6803,12 +6834,12 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit) if (ret) goto end_core_reset; - /* driver is only interested in link up/down and module qualification - * reports from firmware + /* The driver only wants link up/down and module qualification + * reports from firmware. Note the negative logic. */ ret = i40e_aq_set_phy_int_mask(&pf->hw, - I40E_AQ_EVENT_LINK_UPDOWN | - I40E_AQ_EVENT_MODULE_QUAL_FAIL, NULL); + ~(I40E_AQ_EVENT_LINK_UPDOWN | + I40E_AQ_EVENT_MODULE_QUAL_FAIL), NULL); if (ret) dev_info(&pf->pdev->dev, "set phy mask fail, err %s aq_err %s\n", i40e_stat_str(&pf->hw, ret), @@ -6889,8 +6920,7 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit) wr32(hw, I40E_REG_MSS, val); } - if (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 33)) || - (pf->hw.aq.fw_maj_ver < 4)) { + if (pf->flags & I40E_FLAG_RESTART_AUTONEG) { msleep(75); ret = i40e_aq_set_link_restart_an(&pf->hw, true, NULL); if (ret) @@ -7079,12 +7109,13 @@ static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf) ret = i40e_aq_del_udp_tunnel(hw, i, NULL); if (ret) { - dev_info(&pf->pdev->dev, - "%s vxlan port %d, index %d failed, err %s aq_err %s\n", - port ? "add" : "delete", - ntohs(port), i, - i40e_stat_str(&pf->hw, ret), - i40e_aq_str(&pf->hw, + dev_dbg(&pf->pdev->dev, + "%s %s port %d, index %d failed, err %s aq_err %s\n", + pf->udp_ports[i].type ? "vxlan" : "geneve", + port ? "add" : "delete", + ntohs(port), i, + i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); pf->udp_ports[i].index = 0; } @@ -7111,6 +7142,7 @@ static void i40e_service_task(struct work_struct *work) } i40e_detect_recover_hung(pf); + i40e_sync_filters_subtask(pf); i40e_reset_subtask(pf); i40e_handle_mdd_event(pf); i40e_vc_process_vflr_event(pf); @@ -7290,8 +7322,6 @@ static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type) set_bit(__I40E_DOWN, &vsi->state); vsi->flags = 0; vsi->idx = vsi_idx; - vsi->rx_itr_setting = pf->rx_itr_default; - vsi->tx_itr_setting = pf->tx_itr_default; vsi->int_rate_limit = 0; vsi->rss_table_size = (vsi->type == I40E_VSI_MAIN) ? pf->rss_table_size : 64; @@ -7458,8 +7488,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi) tx_ring->dcb_tc = 0; if (vsi->back->flags & I40E_FLAG_WB_ON_ITR_CAPABLE) tx_ring->flags = I40E_TXR_FLAGS_WB_ON_ITR; - if (vsi->back->flags & I40E_FLAG_OUTER_UDP_CSUM_CAPABLE) - tx_ring->flags |= I40E_TXR_FLAGS_OUTER_UDP_CSUM; + tx_ring->tx_itr_setting = pf->tx_itr_default; vsi->tx_rings[i] = tx_ring; rx_ring = &tx_ring[1]; @@ -7476,6 +7505,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi) set_ring_16byte_desc_enabled(rx_ring); else clear_ring_16byte_desc_enabled(rx_ring); + rx_ring->rx_itr_setting = pf->rx_itr_default; vsi->rx_rings[i] = rx_ring; } @@ -7852,7 +7882,7 @@ static int i40e_setup_misc_vector(struct i40e_pf *pf) i40e_flush(hw); - i40e_irq_dynamic_enable_icr0(pf); + i40e_irq_dynamic_enable_icr0(pf, true); return err; } @@ -7936,6 +7966,52 @@ static int i40e_vsi_config_rss(struct i40e_vsi *vsi) } /** + * 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 + * @lut: Buffer to store the lookup table entries + * @lut_size: Size of buffer to store the lookup table entries + * + * Return 0 on success, negative on failure + */ +static int i40e_get_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) { + ret = i40e_aq_get_rss_key(hw, vsi->id, + (struct i40e_aqc_get_set_rss_key_data *)seed); + if (ret) { + dev_info(&pf->pdev->dev, + "Cannot get RSS key, 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; + } + } + + if (lut) { + bool pf_lut = vsi->type == I40E_VSI_MAIN ? true : false; + + ret = i40e_aq_get_rss_lut(hw, vsi->id, pf_lut, lut, lut_size); + if (ret) { + dev_info(&pf->pdev->dev, + "Cannot get RSS lut, 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 ret; +} + +/** * i40e_config_rss_reg - Configure RSS keys and lut by writing registers * @vsi: Pointer to vsi structure * @seed: RSS hash seed @@ -7956,7 +8032,7 @@ static int i40e_config_rss_reg(struct i40e_vsi *vsi, const u8 *seed, u32 *seed_dw = (u32 *)seed; for (i = 0; i <= I40E_PFQF_HKEY_MAX_INDEX; i++) - wr32(hw, I40E_PFQF_HKEY(i), seed_dw[i]); + i40e_write_rx_ctl(hw, I40E_PFQF_HKEY(i), seed_dw[i]); } if (lut) { @@ -7993,7 +8069,7 @@ static int i40e_get_rss_reg(struct i40e_vsi *vsi, u8 *seed, u32 *seed_dw = (u32 *)seed; for (i = 0; i <= I40E_PFQF_HKEY_MAX_INDEX; i++) - seed_dw[i] = rd32(hw, I40E_PFQF_HKEY(i)); + seed_dw[i] = i40e_read_rx_ctl(hw, I40E_PFQF_HKEY(i)); } if (lut) { u32 *lut_dw = (u32 *)lut; @@ -8037,7 +8113,12 @@ int i40e_config_rss(struct i40e_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size) */ int i40e_get_rss(struct i40e_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size) { - return i40e_get_rss_reg(vsi, seed, lut, lut_size); + struct i40e_pf *pf = vsi->back; + + if (pf->flags & I40E_FLAG_RSS_AQ_CAPABLE) + return i40e_get_rss_aq(vsi, seed, lut, lut_size); + else + return i40e_get_rss_reg(vsi, seed, lut, lut_size); } /** @@ -8071,19 +8152,19 @@ static int i40e_pf_config_rss(struct i40e_pf *pf) int ret; /* By default we enable TCP/UDP with IPv4/IPv6 ptypes */ - hena = (u64)rd32(hw, I40E_PFQF_HENA(0)) | - ((u64)rd32(hw, I40E_PFQF_HENA(1)) << 32); + hena = (u64)i40e_read_rx_ctl(hw, I40E_PFQF_HENA(0)) | + ((u64)i40e_read_rx_ctl(hw, I40E_PFQF_HENA(1)) << 32); hena |= i40e_pf_get_default_rss_hena(pf); - wr32(hw, I40E_PFQF_HENA(0), (u32)hena); - wr32(hw, I40E_PFQF_HENA(1), (u32)(hena >> 32)); + i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), (u32)hena); + i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), (u32)(hena >> 32)); /* Determine the RSS table size based on the hardware capabilities */ - reg_val = rd32(hw, I40E_PFQF_CTL_0); + reg_val = i40e_read_rx_ctl(hw, I40E_PFQF_CTL_0); reg_val = (pf->rss_table_size == 512) ? (reg_val | I40E_PFQF_CTL_0_HASHLUTSIZE_512) : (reg_val & ~I40E_PFQF_CTL_0_HASHLUTSIZE_512); - wr32(hw, I40E_PFQF_CTL_0, reg_val); + i40e_write_rx_ctl(hw, I40E_PFQF_CTL_0, reg_val); /* Determine the RSS size of the VSI */ if (!vsi->rss_size) @@ -8367,6 +8448,26 @@ static int i40e_sw_init(struct i40e_pf *pf) pf->hw.func_caps.fd_filters_best_effort; } + if (i40e_is_mac_710(&pf->hw) && + (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 33)) || + (pf->hw.aq.fw_maj_ver < 4))) { + pf->flags |= I40E_FLAG_RESTART_AUTONEG; + /* No DCB support for FW < v4.33 */ + pf->flags |= I40E_FLAG_NO_DCB_SUPPORT; + } + + /* Disable FW LLDP if FW < v4.3 */ + if (i40e_is_mac_710(&pf->hw) && + (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 3)) || + (pf->hw.aq.fw_maj_ver < 4))) + pf->flags |= I40E_FLAG_STOP_FW_LLDP; + + /* Use the FW Set LLDP MIB API if FW > v4.40 */ + if (i40e_is_mac_710(&pf->hw) && + (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver >= 40)) || + (pf->hw.aq.fw_maj_ver >= 5))) + pf->flags |= I40E_FLAG_USE_SET_LLDP_MIB; + if (pf->hw.func_caps.vmdq) { pf->num_vmdq_vsis = I40E_DEFAULT_NUM_VMDQ_VSI; pf->flags |= I40E_FLAG_VMDQ_ENABLED; @@ -8393,8 +8494,19 @@ static int i40e_sw_init(struct i40e_pf *pf) I40E_FLAG_OUTER_UDP_CSUM_CAPABLE | I40E_FLAG_WB_ON_ITR_CAPABLE | I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE | + I40E_FLAG_100M_SGMII_CAPABLE | + I40E_FLAG_USE_SET_LLDP_MIB | I40E_FLAG_GENEVE_OFFLOAD_CAPABLE; + } else if ((pf->hw.aq.api_maj_ver > 1) || + ((pf->hw.aq.api_maj_ver == 1) && + (pf->hw.aq.api_min_ver > 4))) { + /* Supported in FW API version higher than 1.4 */ + pf->flags |= I40E_FLAG_GENEVE_OFFLOAD_CAPABLE; + pf->auto_disable_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE; + } else { + pf->auto_disable_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE; } + pf->eeprom_version = 0xDEAD; pf->lan_veb = I40E_NO_VEB; pf->lan_vsi = I40E_NO_VSI; @@ -8530,9 +8642,6 @@ static void i40e_add_vxlan_port(struct net_device *netdev, u8 next_idx; u8 idx; - if (sa_family == AF_INET6) - return; - idx = i40e_get_udp_port_idx(pf, port); /* Check if port already exists */ @@ -8572,9 +8681,6 @@ static void i40e_del_vxlan_port(struct net_device *netdev, struct i40e_pf *pf = vsi->back; u8 idx; - if (sa_family == AF_INET6) - return; - idx = i40e_get_udp_port_idx(pf, port); /* Check if port already exists */ @@ -8608,7 +8714,7 @@ static void i40e_add_geneve_port(struct net_device *netdev, u8 next_idx; u8 idx; - if (sa_family == AF_INET6) + if (!(pf->flags & I40E_FLAG_GENEVE_OFFLOAD_CAPABLE)) return; idx = i40e_get_udp_port_idx(pf, port); @@ -8652,7 +8758,7 @@ static void i40e_del_geneve_port(struct net_device *netdev, struct i40e_pf *pf = vsi->back; u8 idx; - if (sa_family == AF_INET6) + if (!(pf->flags & I40E_FLAG_GENEVE_OFFLOAD_CAPABLE)) return; idx = i40e_get_udp_port_idx(pf, port); @@ -8890,7 +8996,7 @@ static const struct net_device_ops i40e_netdev_ops = { #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = i40e_netpoll, #endif - .ndo_setup_tc = i40e_setup_tc, + .ndo_setup_tc = __i40e_setup_tc, #ifdef I40E_FCOE .ndo_fcoe_enable = i40e_fcoe_enable, .ndo_fcoe_disable = i40e_fcoe_disable, @@ -8942,11 +9048,15 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) np = netdev_priv(netdev); np->vsi = vsi; - netdev->hw_enc_features |= NETIF_F_IP_CSUM | - NETIF_F_RXCSUM | - NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_GRE | - NETIF_F_TSO; + netdev->hw_enc_features |= NETIF_F_IP_CSUM | + NETIF_F_IPV6_CSUM | + NETIF_F_TSO | + NETIF_F_TSO6 | + NETIF_F_TSO_ECN | + NETIF_F_GSO_GRE | + NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM | + 0; netdev->features = NETIF_F_SG | NETIF_F_IP_CSUM | @@ -8967,6 +9077,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) if (!(pf->flags & I40E_FLAG_MFP_ENABLED)) netdev->features |= NETIF_F_NTUPLE; + if (pf->flags & I40E_FLAG_OUTER_UDP_CSUM_CAPABLE) + netdev->features |= NETIF_F_GSO_UDP_TUNNEL_CSUM; /* copy netdev features into list of user selectable features */ netdev->hw_features |= netdev->features; @@ -9471,10 +9583,15 @@ vector_setup_out: **/ static struct i40e_vsi *i40e_vsi_reinit_setup(struct i40e_vsi *vsi) { - struct i40e_pf *pf = vsi->back; + struct i40e_pf *pf; u8 enabled_tc; int ret; + if (!vsi) + return NULL; + + pf = vsi->back; + i40e_put_lump(pf->qp_pile, vsi->base_queue, vsi->idx); i40e_vsi_clear_rings(vsi); @@ -9975,13 +10092,13 @@ static int i40e_add_veb(struct i40e_veb *veb, struct i40e_vsi *vsi) { struct i40e_pf *pf = veb->pf; bool is_default = veb->pf->cur_promisc; - bool is_cloud = false; + bool enable_stats = !!(pf->flags & I40E_FLAG_VEB_STATS_ENABLED); int ret; /* get a VEB from the hardware */ ret = i40e_aq_add_veb(&pf->hw, veb->uplink_seid, vsi->seid, veb->enabled_tc, is_default, - is_cloud, &veb->seid, NULL); + &veb->seid, enable_stats, NULL); if (ret) { dev_info(&pf->pdev->dev, "couldn't add VEB, err %s aq_err %s\n", @@ -10538,21 +10655,9 @@ static void i40e_print_features(struct i40e_pf *pf) **/ static void i40e_get_platform_mac_addr(struct pci_dev *pdev, struct i40e_pf *pf) { - struct device_node *dp = pci_device_to_OF_node(pdev); - const unsigned char *addr; - u8 *mac_addr = pf->hw.mac.addr; - pf->flags &= ~I40E_FLAG_PF_MAC; - addr = of_get_mac_address(dp); - if (addr) { - ether_addr_copy(mac_addr, addr); + if (!eth_platform_get_mac_address(&pdev->dev, pf->hw.mac.addr)) pf->flags |= I40E_FLAG_PF_MAC; -#ifdef CONFIG_SPARC - } else { - ether_addr_copy(mac_addr, idprom->id_ethaddr); - pf->flags |= I40E_FLAG_PF_MAC; -#endif /* CONFIG_SPARC */ - } } /** @@ -10575,7 +10680,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) u16 wol_nvm_bits; u16 link_status; int err; - u32 len; u32 val; u32 i; u8 set_fc_aq_fail; @@ -10758,8 +10862,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * Ignore error return codes because if it was already disabled via * hardware settings this will fail */ - if (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 3)) || - (pf->hw.aq.fw_maj_ver < 4)) { + if (pf->flags & I40E_FLAG_STOP_FW_LLDP) { dev_info(&pdev->dev, "Stopping firmware LLDP agent.\n"); i40e_aq_stop_lldp(hw, true, NULL); } @@ -10834,8 +10937,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pf->num_alloc_vsi = pf->hw.func_caps.num_vsis; /* Set up the *vsi struct and our local tracking of the MAIN PF vsi. */ - len = sizeof(struct i40e_vsi *) * pf->num_alloc_vsi; - pf->vsi = kzalloc(len, GFP_KERNEL); + pf->vsi = kcalloc(pf->num_alloc_vsi, sizeof(struct i40e_vsi *), + GFP_KERNEL); if (!pf->vsi) { err = -ENOMEM; goto err_switch_setup; @@ -10882,12 +10985,12 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) } } - /* driver is only interested in link up/down and module qualification - * reports from firmware + /* The driver only wants link up/down and module qualification + * reports from firmware. Note the negative logic. */ err = i40e_aq_set_phy_int_mask(&pf->hw, - I40E_AQ_EVENT_LINK_UPDOWN | - I40E_AQ_EVENT_MODULE_QUAL_FAIL, NULL); + ~(I40E_AQ_EVENT_LINK_UPDOWN | + I40E_AQ_EVENT_MODULE_QUAL_FAIL), NULL); if (err) dev_info(&pf->pdev->dev, "set phy mask fail, err %s aq_err %s\n", i40e_stat_str(&pf->hw, err), @@ -10904,8 +11007,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) wr32(hw, I40E_REG_MSS, val); } - if (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 33)) || - (pf->hw.aq.fw_maj_ver < 4)) { + if (pf->flags & I40E_FLAG_RESTART_AUTONEG) { msleep(75); err = i40e_aq_set_link_restart_an(&pf->hw, true, NULL); if (err) @@ -10939,8 +11041,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if ((pf->flags & I40E_FLAG_SRIOV_ENABLED) && (pf->flags & I40E_FLAG_MSIX_ENABLED) && !test_bit(__I40E_BAD_EEPROM, &pf->state)) { - u32 val; - /* disable link interrupts for VFs */ val = rd32(hw, I40E_PFGEN_PORTMDIO_NUM); val &= ~I40E_PFGEN_PORTMDIO_NUM_VFLINK_STAT_ENA_MASK; @@ -11051,6 +11151,10 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) i40e_add_filter_to_drop_tx_flow_control_frames(&pf->hw, pf->main_vsi_seid); + if ((pf->hw.device_id == I40E_DEV_ID_10G_BASE_T) || + (pf->hw.device_id == I40E_DEV_ID_10G_BASE_T4)) + pf->flags |= I40E_FLAG_HAVE_10GBASET_PHY; + /* print a string summarizing features */ i40e_print_features(pf); @@ -11107,10 +11211,11 @@ static void i40e_remove(struct pci_dev *pdev) i40e_ptp_stop(pf); /* Disable RSS in hw */ - wr32(hw, I40E_PFQF_HENA(0), 0); - wr32(hw, I40E_PFQF_HENA(1), 0); + i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), 0); + i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), 0); /* no more scheduling of any task */ + set_bit(__I40E_SUSPENDED, &pf->state); set_bit(__I40E_DOWN, &pf->state); del_timer_sync(&pf->service_timer); cancel_work_sync(&pf->service_task); @@ -11141,8 +11246,8 @@ static void i40e_remove(struct pci_dev *pdev) i40e_vsi_release(pf->vsi[pf->lan_vsi]); /* shutdown and destroy the HMC */ - if (pf->hw.hmc.hmc_obj) { - ret_code = i40e_shutdown_lan_hmc(&pf->hw); + if (hw->hmc.hmc_obj) { + ret_code = i40e_shutdown_lan_hmc(hw); if (ret_code) dev_warn(&pdev->dev, "Failed to destroy the HMC resources: %d\n", @@ -11150,7 +11255,7 @@ static void i40e_remove(struct pci_dev *pdev) } /* shutdown the adminq */ - ret_code = i40e_shutdown_adminq(&pf->hw); + ret_code = i40e_shutdown_adminq(hw); if (ret_code) dev_warn(&pdev->dev, "Failed to destroy the Admin Queue resources: %d\n", @@ -11178,7 +11283,7 @@ static void i40e_remove(struct pci_dev *pdev) kfree(pf->qp_pile); kfree(pf->vsi); - iounmap(pf->hw.hw_addr); + iounmap(hw->hw_addr); kfree(pf); pci_release_selected_regions(pdev, pci_select_bars(pdev, IORESOURCE_MEM)); @@ -11413,6 +11518,16 @@ static int __init i40e_init_module(void) i40e_driver_string, i40e_driver_version_str); pr_info("%s: %s\n", i40e_driver_name, i40e_copyright); + /* we will see if single thread per module is enough for now, + * it can't be any worse than using the system workqueue which + * was already single threaded + */ + i40e_wq = create_singlethread_workqueue(i40e_driver_name); + if (!i40e_wq) { + pr_err("%s: Failed to create workqueue\n", i40e_driver_name); + return -ENOMEM; + } + i40e_dbg_init(); return pci_register_driver(&i40e_driver); } @@ -11427,6 +11542,7 @@ module_init(i40e_init_module); static void __exit i40e_exit_module(void) { pci_unregister_driver(&i40e_driver); + destroy_workqueue(i40e_wq); i40e_dbg_exit(); } module_exit(i40e_exit_module); |