diff options
Diffstat (limited to 'drivers/net/ethernet/intel/fm10k/fm10k_pci.c')
| -rw-r--r-- | drivers/net/ethernet/intel/fm10k/fm10k_pci.c | 529 |
1 files changed, 261 insertions, 268 deletions
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 4eb7a6fa6..774a5654b 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -1,5 +1,5 @@ -/* Intel Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2015 Intel Corporation. +/* Intel(R) Ethernet Switch Host Interface Driver + * 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, @@ -99,7 +99,7 @@ void fm10k_service_event_schedule(struct fm10k_intfc *interface) static void fm10k_service_event_complete(struct fm10k_intfc *interface) { - BUG_ON(!test_bit(__FM10K_SERVICE_SCHED, &interface->state)); + WARN_ON(!test_bit(__FM10K_SERVICE_SCHED, &interface->state)); /* flush memory to make sure state is correct before next watchog */ smp_mb__before_atomic(); @@ -123,11 +123,24 @@ static void fm10k_service_timer(unsigned long data) 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); + interface->flags |= FM10K_FLAG_RESET_REQUESTED; + netdev_warn(netdev, "PCIe link restored, device now attached\n"); + return; + } + rtnl_lock(); if (netif_running(netdev)) @@ -136,16 +149,14 @@ static void fm10k_detach_subtask(struct fm10k_intfc *interface) rtnl_unlock(); } -static void fm10k_reinit(struct fm10k_intfc *interface) +static void fm10k_prepare_for_reset(struct fm10k_intfc *interface) { struct net_device *netdev = interface->netdev; - struct fm10k_hw *hw = &interface->hw; - int err; WARN_ON(in_interrupt()); /* put off any impending NetWatchDogTimeout */ - netdev->trans_start = jiffies; + netif_trans_update(netdev); while (test_and_set_bit(__FM10K_RESETTING, &interface->state)) usleep_range(1000, 2000); @@ -165,6 +176,19 @@ static void fm10k_reinit(struct fm10k_intfc *interface) /* delay any future reset requests */ interface->last_reset = jiffies + (10 * HZ); + rtnl_unlock(); +} + +static int fm10k_handle_reset(struct fm10k_intfc *interface) +{ + struct net_device *netdev = interface->netdev; + struct fm10k_hw *hw = &interface->hw; + int err; + + rtnl_lock(); + + pci_set_master(interface->pdev); + /* reset and initialize the hardware so it is in a known state */ err = hw->mac.ops.reset_hw(hw); if (err) { @@ -185,7 +209,7 @@ static void fm10k_reinit(struct fm10k_intfc *interface) goto reinit_err; } - /* reassociate interrupts */ + /* re-associate interrupts */ err = fm10k_mbx_request_irq(interface); if (err) goto err_mbx_irq; @@ -209,9 +233,6 @@ static void fm10k_reinit(struct fm10k_intfc *interface) netdev->features |= NETIF_F_HW_VLAN_CTAG_RX; } - /* reset clock */ - fm10k_ts_reset(interface); - err = netif_running(netdev) ? fm10k_open(netdev) : 0; if (err) goto err_open; @@ -222,7 +243,7 @@ static void fm10k_reinit(struct fm10k_intfc *interface) clear_bit(__FM10K_RESETTING, &interface->state); - return; + return err; err_open: fm10k_mbx_free_irq(interface); err_mbx_irq: @@ -233,6 +254,20 @@ reinit_err: rtnl_unlock(); clear_bit(__FM10K_RESETTING, &interface->state); + + return err; +} + +static void fm10k_reinit(struct fm10k_intfc *interface) +{ + int err; + + fm10k_prepare_for_reset(interface); + + err = fm10k_handle_reset(interface); + if (err) + dev_err(&interface->pdev->dev, + "fm10k_handle_reset failed: %d\n", err); } static void fm10k_reset_subtask(struct fm10k_intfc *interface) @@ -375,12 +410,19 @@ void fm10k_update_stats(struct fm10k_intfc *interface) u64 bytes, pkts; int i; + /* ensure only one thread updates stats at a time */ + if (test_and_set_bit(__FM10K_UPDATING_STATS, &interface->state)) + return; + /* do not allow stats update via service task for next second */ interface->next_stats_update = jiffies + HZ; /* gather some stats to the interface struct that are per queue */ for (bytes = 0, pkts = 0, i = 0; i < interface->num_tx_queues; i++) { - struct fm10k_ring *tx_ring = interface->tx_ring[i]; + struct fm10k_ring *tx_ring = READ_ONCE(interface->tx_ring[i]); + + if (!tx_ring) + continue; restart_queue += tx_ring->tx_stats.restart_queue; tx_busy += tx_ring->tx_stats.tx_busy; @@ -399,7 +441,10 @@ void fm10k_update_stats(struct fm10k_intfc *interface) /* gather some stats to the interface struct that are per queue */ for (bytes = 0, pkts = 0, i = 0; i < interface->num_rx_queues; i++) { - struct fm10k_ring *rx_ring = interface->rx_ring[i]; + struct fm10k_ring *rx_ring = READ_ONCE(interface->rx_ring[i]); + + if (!rx_ring) + continue; bytes += rx_ring->stats.bytes; pkts += rx_ring->stats.packets; @@ -446,6 +491,8 @@ void fm10k_update_stats(struct fm10k_intfc *interface) /* Fill out the OS statistics structure */ net_stats->rx_errors = rx_errors; net_stats->rx_dropped = interface->stats.nodesc_drop.count; + + clear_bit(__FM10K_UPDATING_STATS, &interface->state); } /** @@ -559,7 +606,6 @@ static void fm10k_service_task(struct work_struct *work) /* tasks only run when interface is up */ fm10k_watchdog_subtask(interface); fm10k_check_hang_subtask(interface); - fm10k_ts_tx_subtask(interface); /* release lock on service events to allow scheduling next event */ fm10k_service_event_complete(interface); @@ -579,7 +625,7 @@ static void fm10k_configure_tx_ring(struct fm10k_intfc *interface, u64 tdba = ring->dma; u32 size = ring->count * sizeof(struct fm10k_tx_desc); u32 txint = FM10K_INT_MAP_DISABLE; - u32 txdctl = FM10K_TXDCTL_ENABLE | (1 << FM10K_TXDCTL_MAX_TIME_SHIFT); + u32 txdctl = BIT(FM10K_TXDCTL_MAX_TIME_SHIFT) | FM10K_TXDCTL_ENABLE; u8 reg_idx = ring->reg_idx; /* disable queue to avoid issues while updating state */ @@ -730,7 +776,7 @@ static void fm10k_configure_rx_ring(struct fm10k_intfc *interface, if (interface->pfc_en) rx_pause = interface->pfc_en; #endif - if (!(rx_pause & (1 << ring->qos_pc))) + if (!(rx_pause & BIT(ring->qos_pc))) rxdctl |= FM10K_RXDCTL_DROP_ON_EMPTY; fm10k_write_reg(hw, FM10K_RXDCTL(reg_idx), rxdctl); @@ -779,7 +825,7 @@ void fm10k_update_rx_drop_en(struct fm10k_intfc *interface) u32 rxdctl = FM10K_RXDCTL_WRITE_BACK_MIN_DELAY; u8 reg_idx = ring->reg_idx; - if (!(rx_pause & (1 << ring->qos_pc))) + if (!(rx_pause & BIT(ring->qos_pc))) rxdctl |= FM10K_RXDCTL_DROP_ON_EMPTY; fm10k_write_reg(hw, FM10K_RXDCTL(reg_idx), rxdctl); @@ -903,8 +949,8 @@ static irqreturn_t fm10k_msix_mbx_vf(int __always_unused irq, void *data) /* re-enable mailbox interrupt and indicate 20us delay */ fm10k_write_reg(hw, FM10K_VFITR(FM10K_MBX_VECTOR), - FM10K_ITR_ENABLE | (FM10K_MBX_INT_DELAY >> - hw->mac.itr_scale)); + (FM10K_MBX_INT_DELAY >> hw->mac.itr_scale) | + FM10K_ITR_ENABLE); /* service upstream mailbox */ if (fm10k_mbx_trylock(interface)) { @@ -1065,7 +1111,7 @@ static void fm10k_reset_drop_on_empty(struct fm10k_intfc *interface, u32 eicr) if (maxholdq) fm10k_write_reg(hw, FM10K_MAXHOLDQ(7), maxholdq); for (q = 255;;) { - if (maxholdq & (1 << 31)) { + if (maxholdq & BIT(31)) { if (q < FM10K_MAX_QUEUES_PF) { interface->rx_overrun_pf++; fm10k_write_reg(hw, FM10K_RXDCTL(q), rxdctl); @@ -1135,22 +1181,24 @@ static irqreturn_t fm10k_msix_mbx_pf(int __always_unused irq, void *data) /* re-enable mailbox interrupt and indicate 20us delay */ fm10k_write_reg(hw, FM10K_ITR(FM10K_MBX_VECTOR), - FM10K_ITR_ENABLE | (FM10K_MBX_INT_DELAY >> - hw->mac.itr_scale)); + (FM10K_MBX_INT_DELAY >> hw->mac.itr_scale) | + FM10K_ITR_ENABLE); return IRQ_HANDLED; } void fm10k_mbx_free_irq(struct fm10k_intfc *interface) { - struct msix_entry *entry = &interface->msix_entries[FM10K_MBX_VECTOR]; struct fm10k_hw *hw = &interface->hw; + struct msix_entry *entry; int itr_reg; /* no mailbox IRQ to free if MSI-X is not enabled */ if (!interface->msix_entries) return; + entry = &interface->msix_entries[FM10K_MBX_VECTOR]; + /* disconnect the mailbox */ hw->mbx.ops.disconnect(hw, &hw->mbx); @@ -1202,25 +1250,6 @@ static s32 fm10k_mbx_mac_addr(struct fm10k_hw *hw, u32 **results, return 0; } -static s32 fm10k_1588_msg_vf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info __always_unused *mbx) -{ - struct fm10k_intfc *interface; - u64 timestamp; - s32 err; - - err = fm10k_tlv_attr_get_u64(results[FM10K_1588_MSG_TIMESTAMP], - ×tamp); - if (err) - return err; - - interface = container_of(hw, struct fm10k_intfc, hw); - - fm10k_ts_tx_hwtstamp(interface, 0, timestamp); - - return 0; -} - /* generic error handler for mailbox issues */ static s32 fm10k_mbx_error(struct fm10k_hw *hw, u32 **results, struct fm10k_mbx_info __always_unused *mbx) @@ -1241,7 +1270,6 @@ static const struct fm10k_msg_data vf_mbx_data[] = { FM10K_TLV_MSG_TEST_HANDLER(fm10k_tlv_msg_test), FM10K_VF_MSG_MAC_VLAN_HANDLER(fm10k_mbx_mac_addr), FM10K_VF_MSG_LPORT_STATE_HANDLER(fm10k_msg_lport_state_vf), - FM10K_VF_MSG_1588_HANDLER(fm10k_1588_msg_vf), FM10K_TLV_MSG_ERROR_HANDLER(fm10k_mbx_error), }; @@ -1253,7 +1281,7 @@ static int fm10k_mbx_request_irq_vf(struct fm10k_intfc *interface) int err; /* Use timer0 for interrupt moderation on the mailbox */ - u32 itr = FM10K_INT_MAP_TIMER0 | entry->entry; + u32 itr = entry->entry | FM10K_INT_MAP_TIMER0; /* register mailbox handlers */ err = hw->mbx.ops.register_handlers(&hw->mbx, vf_mbx_data); @@ -1285,11 +1313,40 @@ static s32 fm10k_lport_map(struct fm10k_hw *hw, u32 **results, u32 dglort_map = hw->mac.dglort_map; s32 err; + interface = container_of(hw, struct fm10k_intfc, hw); + + err = fm10k_msg_err_pf(hw, results, mbx); + if (!err && hw->swapi.status) { + /* force link down for a reasonable delay */ + interface->link_down_event = jiffies + (2 * HZ); + set_bit(__FM10K_LINK_DOWN, &interface->state); + + /* reset dglort_map back to no config */ + hw->mac.dglort_map = FM10K_DGLORTMAP_NONE; + + fm10k_service_event_schedule(interface); + + /* prevent overloading kernel message buffer */ + if (interface->lport_map_failed) + return 0; + + interface->lport_map_failed = true; + + if (hw->swapi.status == FM10K_MSG_ERR_PEP_NOT_SCHEDULED) + dev_warn(&interface->pdev->dev, + "cannot obtain link because the host interface is configured for a PCIe host interface bandwidth of zero\n"); + dev_warn(&interface->pdev->dev, + "request logical port map failed: %d\n", + hw->swapi.status); + + return 0; + } + err = fm10k_msg_lport_map_pf(hw, results, mbx); if (err) return err; - interface = container_of(hw, struct fm10k_intfc, hw); + interface->lport_map_failed = false; /* we need to reset if port count was just updated */ if (dglort_map != hw->mac.dglort_map) @@ -1339,68 +1396,6 @@ static s32 fm10k_update_pvid(struct fm10k_hw *hw, u32 **results, return 0; } -static s32 fm10k_1588_msg_pf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info __always_unused *mbx) -{ - struct fm10k_swapi_1588_timestamp timestamp; - struct fm10k_iov_data *iov_data; - struct fm10k_intfc *interface; - u16 sglort, vf_idx; - s32 err; - - err = fm10k_tlv_attr_get_le_struct( - results[FM10K_PF_ATTR_ID_1588_TIMESTAMP], - ×tamp, sizeof(timestamp)); - if (err) - return err; - - interface = container_of(hw, struct fm10k_intfc, hw); - - if (timestamp.dglort) { - fm10k_ts_tx_hwtstamp(interface, timestamp.dglort, - le64_to_cpu(timestamp.egress)); - return 0; - } - - /* either dglort or sglort must be set */ - if (!timestamp.sglort) - return FM10K_ERR_PARAM; - - /* verify GLORT is at least one of the ones we own */ - sglort = le16_to_cpu(timestamp.sglort); - if (!fm10k_glort_valid_pf(hw, sglort)) - return FM10K_ERR_PARAM; - - if (sglort == interface->glort) { - fm10k_ts_tx_hwtstamp(interface, 0, - le64_to_cpu(timestamp.ingress)); - return 0; - } - - /* if there is no iov_data then there is no mailboxes to process */ - if (!ACCESS_ONCE(interface->iov_data)) - return FM10K_ERR_PARAM; - - rcu_read_lock(); - - /* notify VF if this timestamp belongs to it */ - iov_data = interface->iov_data; - vf_idx = (hw->mac.dglort_map & FM10K_DGLORTMAP_NONE) - sglort; - - if (!iov_data || vf_idx >= iov_data->num_vfs) { - err = FM10K_ERR_PARAM; - goto err_unlock; - } - - err = hw->iov.ops.report_timestamp(hw, &iov_data->vf_info[vf_idx], - le64_to_cpu(timestamp.ingress)); - -err_unlock: - rcu_read_unlock(); - - return err; -} - static const struct fm10k_msg_data pf_mbx_data[] = { FM10K_PF_MSG_ERR_HANDLER(XCAST_MODES, fm10k_msg_err_pf), FM10K_PF_MSG_ERR_HANDLER(UPDATE_MAC_FWD_RULE, fm10k_msg_err_pf), @@ -1408,7 +1403,6 @@ static const struct fm10k_msg_data pf_mbx_data[] = { FM10K_PF_MSG_ERR_HANDLER(LPORT_CREATE, fm10k_msg_err_pf), FM10K_PF_MSG_ERR_HANDLER(LPORT_DELETE, fm10k_msg_err_pf), FM10K_PF_MSG_UPDATE_PVID_HANDLER(fm10k_update_pvid), - FM10K_PF_MSG_1588_TIMESTAMP_HANDLER(fm10k_1588_msg_pf), FM10K_TLV_MSG_ERROR_HANDLER(fm10k_mbx_error), }; @@ -1420,8 +1414,8 @@ static int fm10k_mbx_request_irq_pf(struct fm10k_intfc *interface) int err; /* Use timer0 for interrupt moderation on the mailbox */ - u32 mbx_itr = FM10K_INT_MAP_TIMER0 | entry->entry; - u32 other_itr = FM10K_INT_MAP_IMMEDIATE | entry->entry; + u32 mbx_itr = entry->entry | FM10K_INT_MAP_TIMER0; + u32 other_itr = entry->entry | FM10K_INT_MAP_IMMEDIATE; /* register mailbox handlers */ err = hw->mbx.ops.register_handlers(&hw->mbx, pf_mbx_data); @@ -1622,6 +1616,9 @@ void fm10k_up(struct fm10k_intfc *interface) /* configure interrupts */ hw->mac.ops.update_int_moderator(hw); + /* enable statistics capture again */ + clear_bit(__FM10K_UPDATING_STATS, &interface->state); + /* clear down bit to indicate we are ready to go */ clear_bit(__FM10K_DOWN, &interface->state); @@ -1654,9 +1651,11 @@ void fm10k_down(struct fm10k_intfc *interface) { struct net_device *netdev = interface->netdev; struct fm10k_hw *hw = &interface->hw; + int err, i = 0, count = 0; /* signal that we are down to the interrupt handler and service task */ - set_bit(__FM10K_DOWN, &interface->state); + if (test_and_set_bit(__FM10K_DOWN, &interface->state)) + return; /* call carrier off first to avoid false dev_watchdog timeouts */ netif_carrier_off(netdev); @@ -1668,17 +1667,58 @@ void fm10k_down(struct fm10k_intfc *interface) /* reset Rx filters */ fm10k_reset_rx_state(interface); - /* allow 10ms for device to quiesce */ - usleep_range(10000, 20000); - /* disable polling routines */ fm10k_napi_disable_all(interface); /* capture stats one last time before stopping interface */ fm10k_update_stats(interface); + /* prevent updating statistics while we're down */ + while (test_and_set_bit(__FM10K_UPDATING_STATS, &interface->state)) + usleep_range(1000, 2000); + + /* skip waiting for TX DMA if we lost PCIe link */ + if (FM10K_REMOVED(hw->hw_addr)) + goto skip_tx_dma_drain; + + /* In some rare circumstances it can take a while for Tx queues to + * quiesce and be fully disabled. Attempt to .stop_hw() first, and + * then if we get ERR_REQUESTS_PENDING, go ahead and wait in a loop + * until the Tx queues have emptied, or until a number of retries. If + * we fail to clear within the retry loop, we will issue a warning + * indicating that Tx DMA is probably hung. Note this means we call + * .stop_hw() twice but this shouldn't cause any problems. + */ + err = hw->mac.ops.stop_hw(hw); + if (err != FM10K_ERR_REQUESTS_PENDING) + goto skip_tx_dma_drain; + +#define TX_DMA_DRAIN_RETRIES 25 + for (count = 0; count < TX_DMA_DRAIN_RETRIES; count++) { + usleep_range(10000, 20000); + + /* start checking at the last ring to have pending Tx */ + for (; i < interface->num_tx_queues; i++) + if (fm10k_get_tx_pending(interface->tx_ring[i])) + break; + + /* if all the queues are drained, we can break now */ + if (i == interface->num_tx_queues) + break; + } + + if (count >= TX_DMA_DRAIN_RETRIES) + dev_err(&interface->pdev->dev, + "Tx queues failed to drain after %d tries. Tx DMA is probably hung.\n", + count); +skip_tx_dma_drain: /* Disable DMA engine for Tx/Rx */ - hw->mac.ops.stop_hw(hw); + err = hw->mac.ops.stop_hw(hw); + if (err == FM10K_ERR_REQUESTS_PENDING) + dev_err(&interface->pdev->dev, + "due to pending requests hw was not shut down gracefully\n"); + else if (err) + dev_err(&interface->pdev->dev, "stop_hw failed: %d\n", err); /* free any buffers still on the rings */ fm10k_clean_all_tx_rings(interface); @@ -1776,35 +1816,17 @@ static int fm10k_sw_init(struct fm10k_intfc *interface, netdev->addr_assign_type |= NET_ADDR_RANDOM; } - memcpy(netdev->dev_addr, hw->mac.addr, netdev->addr_len); - memcpy(netdev->perm_addr, hw->mac.addr, netdev->addr_len); + ether_addr_copy(netdev->dev_addr, hw->mac.addr); + ether_addr_copy(netdev->perm_addr, hw->mac.addr); if (!is_valid_ether_addr(netdev->perm_addr)) { dev_err(&pdev->dev, "Invalid MAC Address\n"); return -EIO; } - /* assign BAR 4 resources for use with PTP */ - if (fm10k_read_reg(hw, FM10K_CTRL) & FM10K_CTRL_BAR4_ALLOWED) - interface->sw_addr = ioremap(pci_resource_start(pdev, 4), - pci_resource_len(pdev, 4)); - hw->sw_addr = interface->sw_addr; - /* initialize DCBNL interface */ fm10k_dcbnl_set_ops(netdev); - /* Initialize service timer and service task */ - set_bit(__FM10K_SERVICE_DISABLE, &interface->state); - setup_timer(&interface->service_timer, &fm10k_service_timer, - (unsigned long)interface); - INIT_WORK(&interface->service_task, fm10k_service_task); - - /* kick off service timer now, even when interface is down */ - mod_timer(&interface->service_timer, (HZ * 2) + jiffies); - - /* Intitialize timestamp data */ - fm10k_ts_init(interface); - /* set default ring sizes */ interface->tx_ring_count = FM10K_DEFAULT_TXD; interface->rx_ring_count = FM10K_DEFAULT_RXD; @@ -1821,6 +1843,7 @@ static int fm10k_sw_init(struct fm10k_intfc *interface, /* Start off interface as being down */ set_bit(__FM10K_DOWN, &interface->state); + set_bit(__FM10K_UPDATING_STATS, &interface->state); return 0; } @@ -1940,10 +1963,7 @@ static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_dma; } - err = pci_request_selected_regions(pdev, - pci_select_bars(pdev, - IORESOURCE_MEM), - fm10k_driver_name); + err = pci_request_mem_regions(pdev, fm10k_driver_name); if (err) { dev_err(&pdev->dev, "pci_request_selected_regions failed: %d\n", err); @@ -1987,6 +2007,12 @@ static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto err_sw_init; + /* the mbx interrupt might attempt to schedule the service task, so we + * must ensure it is disabled since we haven't yet requested the timer + * or work item. + */ + set_bit(__FM10K_SERVICE_DISABLE, &interface->state); + err = fm10k_mbx_request_irq(interface); if (err) goto err_mbx_interrupt; @@ -2006,8 +2032,15 @@ static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* stop all the transmit queues from transmitting until link is up */ netif_tx_stop_all_queues(netdev); - /* Register PTP interface */ - fm10k_ptp_register(interface); + /* Initialize service timer and service task late in order to avoid + * cleanup issues. + */ + setup_timer(&interface->service_timer, &fm10k_service_timer, + (unsigned long)interface); + INIT_WORK(&interface->service_task, fm10k_service_task); + + /* kick off service timer now, even when interface is down */ + mod_timer(&interface->service_timer, (HZ * 2) + jiffies); /* print warning for non-optimal configurations */ fm10k_slot_warn(interface); @@ -2034,8 +2067,7 @@ err_sw_init: err_ioremap: free_netdev(netdev); err_alloc_netdev: - pci_release_selected_regions(pdev, - pci_select_bars(pdev, IORESOURCE_MEM)); + pci_release_mem_regions(pdev); err_pci_reg: err_dma: pci_disable_device(pdev); @@ -2065,9 +2097,6 @@ static void fm10k_remove(struct pci_dev *pdev) if (netdev->reg_state == NETREG_REGISTERED) unregister_netdev(netdev); - /* cleanup timestamp handling */ - fm10k_ptp_unregister(interface); - /* release VFs */ fm10k_iov_disable(pdev); @@ -2086,14 +2115,55 @@ static void fm10k_remove(struct pci_dev *pdev) free_netdev(netdev); - pci_release_selected_regions(pdev, - pci_select_bars(pdev, IORESOURCE_MEM)); + pci_release_mem_regions(pdev); pci_disable_pcie_error_reporting(pdev); pci_disable_device(pdev); } +static void fm10k_prepare_suspend(struct fm10k_intfc *interface) +{ + /* the watchdog task reads from registers, which might appear like + * a surprise remove if the PCIe device is disabled while we're + * stopped. We stop the watchdog task until after we resume software + * activity. + */ + set_bit(__FM10K_SERVICE_DISABLE, &interface->state); + cancel_work_sync(&interface->service_task); + + fm10k_prepare_for_reset(interface); +} + +static int fm10k_handle_resume(struct fm10k_intfc *interface) +{ + struct fm10k_hw *hw = &interface->hw; + int err; + + /* reset statistics starting values */ + hw->mac.ops.rebind_hw_stats(hw, &interface->stats); + + err = fm10k_handle_reset(interface); + if (err) + return err; + + /* assume host is not ready, to prevent race with watchdog in case we + * actually don't have connection to the switch + */ + interface->host_ready = false; + fm10k_watchdog_host_not_ready(interface); + + /* force link to stay down for a second to prevent link flutter */ + 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); + + return err; +} + #ifdef CONFIG_PM /** * fm10k_resume - Restore device to pre-sleep state @@ -2130,63 +2200,13 @@ static int fm10k_resume(struct pci_dev *pdev) /* refresh hw_addr in case it was dropped */ hw->hw_addr = interface->uc_addr; - /* reset hardware to known state */ - err = hw->mac.ops.init_hw(&interface->hw); - if (err) { - dev_err(&pdev->dev, "init_hw failed: %d\n", err); - return err; - } - - /* reset statistics starting values */ - hw->mac.ops.rebind_hw_stats(hw, &interface->stats); - - /* reset clock */ - fm10k_ts_reset(interface); - - rtnl_lock(); - - err = fm10k_init_queueing_scheme(interface); - if (err) - goto err_queueing_scheme; - - err = fm10k_mbx_request_irq(interface); - if (err) - goto err_mbx_irq; - - err = fm10k_hw_ready(interface); + err = fm10k_handle_resume(interface); if (err) - goto err_open; - - err = netif_running(netdev) ? fm10k_open(netdev) : 0; - if (err) - goto err_open; - - rtnl_unlock(); - - /* assume host is not ready, to prevent race with watchdog in case we - * actually don't have connection to the switch - */ - interface->host_ready = false; - fm10k_watchdog_host_not_ready(interface); - - /* clear the service task disable bit to allow service task to start */ - clear_bit(__FM10K_SERVICE_DISABLE, &interface->state); - fm10k_service_event_schedule(interface); - - /* restore SR-IOV interface */ - fm10k_iov_resume(pdev); + return err; netif_device_attach(netdev); return 0; -err_open: - fm10k_mbx_free_irq(interface); -err_mbx_irq: - fm10k_clear_queueing_scheme(interface); -err_queueing_scheme: - rtnl_unlock(); - - return err; } /** @@ -2206,27 +2226,7 @@ static int fm10k_suspend(struct pci_dev *pdev, netif_device_detach(netdev); - fm10k_iov_suspend(pdev); - - /* the watchdog tasks may read registers, which will appear like a - * surprise-remove event once the PCI device is disabled. This will - * cause us to close the netdevice, so we don't retain the open/closed - * state post-resume. Prevent this by disabling the service task while - * suspended, until we actually resume. - */ - set_bit(__FM10K_SERVICE_DISABLE, &interface->state); - cancel_work_sync(&interface->service_task); - - rtnl_lock(); - - if (netif_running(netdev)) - fm10k_close(netdev); - - fm10k_mbx_free_irq(interface); - - fm10k_clear_queueing_scheme(interface); - - rtnl_unlock(); + fm10k_prepare_suspend(interface); err = pci_save_state(pdev); if (err) @@ -2259,15 +2259,7 @@ static pci_ers_result_t fm10k_io_error_detected(struct pci_dev *pdev, if (state == pci_channel_io_perm_failure) return PCI_ERS_RESULT_DISCONNECT; - if (netif_running(netdev)) - fm10k_close(netdev); - - /* free interrupts */ - fm10k_clear_queueing_scheme(interface); - - fm10k_mbx_free_irq(interface); - - pci_disable_device(pdev); + fm10k_prepare_suspend(interface); /* Request a slot reset. */ return PCI_ERS_RESULT_NEED_RESET; @@ -2281,7 +2273,6 @@ static pci_ers_result_t fm10k_io_error_detected(struct pci_dev *pdev, */ static pci_ers_result_t fm10k_io_slot_reset(struct pci_dev *pdev) { - struct fm10k_intfc *interface = pci_get_drvdata(pdev); pci_ers_result_t result; if (pci_enable_device_mem(pdev)) { @@ -2299,12 +2290,6 @@ static pci_ers_result_t fm10k_io_slot_reset(struct pci_dev *pdev) pci_wake_from_d3(pdev, false); - /* refresh hw_addr in case it was dropped */ - interface->hw.hw_addr = interface->uc_addr; - - interface->flags |= FM10K_FLAG_RESET_REQUESTED; - fm10k_service_event_schedule(interface); - result = PCI_ERS_RESULT_RECOVERED; } @@ -2324,46 +2309,54 @@ static void fm10k_io_resume(struct pci_dev *pdev) { struct fm10k_intfc *interface = pci_get_drvdata(pdev); struct net_device *netdev = interface->netdev; - struct fm10k_hw *hw = &interface->hw; - int err = 0; - - /* reset hardware to known state */ - err = hw->mac.ops.init_hw(&interface->hw); - if (err) { - dev_err(&pdev->dev, "init_hw failed: %d\n", err); - return; - } - - /* reset statistics starting values */ - hw->mac.ops.rebind_hw_stats(hw, &interface->stats); + int err; - err = fm10k_init_queueing_scheme(interface); - if (err) { - dev_err(&interface->pdev->dev, - "init_queueing_scheme failed: %d\n", err); - return; - } + err = fm10k_handle_resume(interface); - /* reassociate interrupts */ - fm10k_mbx_request_irq(interface); + if (err) + dev_warn(&pdev->dev, + "fm10k_io_resume failed: %d\n", err); + else + netif_device_attach(netdev); +} - /* reset clock */ - fm10k_ts_reset(interface); +/** + * fm10k_io_reset_notify - called when PCI function is reset + * @pdev: Pointer to PCI device + * + * This callback is called when the PCI function is reset such as from + * /sys/class/net/<enpX>/device/reset or similar. When prepare is true, it + * means we should prepare for a function reset. If prepare is false, it means + * the function reset just occurred. + */ +static void fm10k_io_reset_notify(struct pci_dev *pdev, bool prepare) +{ + struct fm10k_intfc *interface = pci_get_drvdata(pdev); + int err = 0; - if (netif_running(netdev)) - err = fm10k_open(netdev); + if (prepare) { + /* warn incase we have any active VF devices */ + if (pci_num_vf(pdev)) + dev_warn(&pdev->dev, + "PCIe FLR may cause issues for any active VF devices\n"); - /* final check of hardware state before registering the interface */ - err = err ? : fm10k_hw_ready(interface); + fm10k_prepare_suspend(interface); + } else { + err = fm10k_handle_resume(interface); + } - if (!err) - netif_device_attach(netdev); + if (err) { + dev_warn(&pdev->dev, + "fm10k_io_reset_notify failed: %d\n", err); + netif_device_detach(interface->netdev); + } } static const struct pci_error_handlers fm10k_err_handler = { .error_detected = fm10k_io_error_detected, .slot_reset = fm10k_io_slot_reset, .resume = fm10k_io_resume, + .reset_notify = fm10k_io_reset_notify, }; static struct pci_driver fm10k_driver = { @@ -2382,7 +2375,7 @@ static struct pci_driver fm10k_driver = { /** * fm10k_register_pci_driver - register driver interface * - * This funciton is called on module load in order to register the driver. + * This function is called on module load in order to register the driver. **/ int fm10k_register_pci_driver(void) { @@ -2392,7 +2385,7 @@ int fm10k_register_pci_driver(void) /** * fm10k_unregister_pci_driver - unregister driver interface * - * This funciton is called on module unload in order to remove the driver. + * This function is called on module unload in order to remove the driver. **/ void fm10k_unregister_pci_driver(void) { |