diff options
Diffstat (limited to 'drivers/net/ethernet/intel/ixgbe/ixgbe_main.c')
| -rw-r--r-- | drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 1231 |
1 files changed, 926 insertions, 305 deletions
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 0ade0cd5ef5..f5aa3311ea2 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. + Copyright(c) 1999 - 2014 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, @@ -20,6 +20,7 @@ the file called "COPYING". Contact Information: + Linux NICS <linux.nics@intel.com> e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 @@ -44,6 +45,7 @@ #include <linux/ethtool.h> #include <linux/if.h> #include <linux/if_vlan.h> +#include <linux/if_macvlan.h> #include <linux/if_bridge.h> #include <linux/prefetch.h> #include <scsi/fc/fc_fcoe.h> @@ -63,10 +65,10 @@ char ixgbe_default_device_descr[] = static char ixgbe_default_device_descr[] = "Intel(R) 10 Gigabit Network Connection"; #endif -#define DRV_VERSION "3.15.1-k" +#define DRV_VERSION "3.19.1-k" const char ixgbe_driver_version[] = DRV_VERSION; static const char ixgbe_copyright[] = - "Copyright (c) 1999-2013 Intel Corporation."; + "Copyright (c) 1999-2014 Intel Corporation."; static const struct ixgbe_info *ixgbe_info_tbl[] = { [board_82598] = &ixgbe_82598_info, @@ -132,7 +134,7 @@ static struct notifier_block dca_notifier = { static unsigned int max_vfs; module_param(max_vfs, uint, 0); MODULE_PARM_DESC(max_vfs, - "Maximum number of virtual functions to allocate per physical function - default is zero and maximum value is 63"); + "Maximum number of virtual functions to allocate per physical function - default is zero and maximum value is 63. (Deprecated)"); #endif /* CONFIG_PCI_IOV */ static unsigned int allow_unsupported_sfp; @@ -150,10 +152,11 @@ MODULE_DESCRIPTION("Intel(R) 10 Gigabit PCI Express Network Driver"); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); +static bool ixgbe_check_cfg_remove(struct ixgbe_hw *hw, struct pci_dev *pdev); + static int ixgbe_read_pci_cfg_word_parent(struct ixgbe_adapter *adapter, u32 reg, u16 *value) { - int pos = 0; struct pci_dev *parent_dev; struct pci_bus *parent_bus; @@ -165,11 +168,13 @@ static int ixgbe_read_pci_cfg_word_parent(struct ixgbe_adapter *adapter, if (!parent_dev) return -1; - pos = pci_find_capability(parent_dev, PCI_CAP_ID_EXP); - if (!pos) + if (!pci_is_pcie(parent_dev)) return -1; - pci_read_config_word(parent_dev, pos + reg, value); + pcie_capability_read_word(parent_dev, reg, value); + if (*value == IXGBE_FAILED_READ_CFG_WORD && + ixgbe_check_cfg_remove(&adapter->hw, parent_dev)) + return -1; return 0; } @@ -247,7 +252,7 @@ static void ixgbe_check_minimum_link(struct ixgbe_adapter *adapter, max_gts = 4 * width; break; case PCIE_SPEED_8_0GT: - /* 128b/130b encoding only reduces throughput by 1% */ + /* 128b/130b encoding reduces throughput by less than 2% */ max_gts = 8 * width; break; default: @@ -265,7 +270,7 @@ static void ixgbe_check_minimum_link(struct ixgbe_adapter *adapter, width, (speed == PCIE_SPEED_2_5GT ? "20%" : speed == PCIE_SPEED_5_0GT ? "20%" : - speed == PCIE_SPEED_8_0GT ? "N/a" : + speed == PCIE_SPEED_8_0GT ? "<2%" : "Unknown")); if (max_gts < expected_gts) { @@ -279,16 +284,125 @@ static void ixgbe_check_minimum_link(struct ixgbe_adapter *adapter, static void ixgbe_service_event_schedule(struct ixgbe_adapter *adapter) { if (!test_bit(__IXGBE_DOWN, &adapter->state) && + !test_bit(__IXGBE_REMOVING, &adapter->state) && !test_and_set_bit(__IXGBE_SERVICE_SCHED, &adapter->state)) schedule_work(&adapter->service_task); } +static void ixgbe_remove_adapter(struct ixgbe_hw *hw) +{ + struct ixgbe_adapter *adapter = hw->back; + + if (!hw->hw_addr) + return; + hw->hw_addr = NULL; + e_dev_err("Adapter removed\n"); + if (test_bit(__IXGBE_SERVICE_INITED, &adapter->state)) + ixgbe_service_event_schedule(adapter); +} + +static void ixgbe_check_remove(struct ixgbe_hw *hw, u32 reg) +{ + u32 value; + + /* The following check not only optimizes a bit by not + * performing a read on the status register when the + * register just read was a status register read that + * returned IXGBE_FAILED_READ_REG. It also blocks any + * potential recursion. + */ + if (reg == IXGBE_STATUS) { + ixgbe_remove_adapter(hw); + return; + } + value = ixgbe_read_reg(hw, IXGBE_STATUS); + if (value == IXGBE_FAILED_READ_REG) + ixgbe_remove_adapter(hw); +} + +/** + * ixgbe_read_reg - Read from device register + * @hw: hw specific details + * @reg: offset of register to read + * + * Returns : value read or IXGBE_FAILED_READ_REG if removed + * + * This function is used to read device registers. It checks for device + * removal by confirming any read that returns all ones by checking the + * status register value for all ones. This function avoids reading from + * the hardware if a removal was previously detected in which case it + * returns IXGBE_FAILED_READ_REG (all ones). + */ +u32 ixgbe_read_reg(struct ixgbe_hw *hw, u32 reg) +{ + u8 __iomem *reg_addr = ACCESS_ONCE(hw->hw_addr); + u32 value; + + if (ixgbe_removed(reg_addr)) + return IXGBE_FAILED_READ_REG; + value = readl(reg_addr + reg); + if (unlikely(value == IXGBE_FAILED_READ_REG)) + ixgbe_check_remove(hw, reg); + return value; +} + +static bool ixgbe_check_cfg_remove(struct ixgbe_hw *hw, struct pci_dev *pdev) +{ + u16 value; + + pci_read_config_word(pdev, PCI_VENDOR_ID, &value); + if (value == IXGBE_FAILED_READ_CFG_WORD) { + ixgbe_remove_adapter(hw); + return true; + } + return false; +} + +u16 ixgbe_read_pci_cfg_word(struct ixgbe_hw *hw, u32 reg) +{ + struct ixgbe_adapter *adapter = hw->back; + u16 value; + + if (ixgbe_removed(hw->hw_addr)) + return IXGBE_FAILED_READ_CFG_WORD; + pci_read_config_word(adapter->pdev, reg, &value); + if (value == IXGBE_FAILED_READ_CFG_WORD && + ixgbe_check_cfg_remove(hw, adapter->pdev)) + return IXGBE_FAILED_READ_CFG_WORD; + return value; +} + +#ifdef CONFIG_PCI_IOV +static u32 ixgbe_read_pci_cfg_dword(struct ixgbe_hw *hw, u32 reg) +{ + struct ixgbe_adapter *adapter = hw->back; + u32 value; + + if (ixgbe_removed(hw->hw_addr)) + return IXGBE_FAILED_READ_CFG_DWORD; + pci_read_config_dword(adapter->pdev, reg, &value); + if (value == IXGBE_FAILED_READ_CFG_DWORD && + ixgbe_check_cfg_remove(hw, adapter->pdev)) + return IXGBE_FAILED_READ_CFG_DWORD; + return value; +} +#endif /* CONFIG_PCI_IOV */ + +void ixgbe_write_pci_cfg_word(struct ixgbe_hw *hw, u32 reg, u16 value) +{ + struct ixgbe_adapter *adapter = hw->back; + + if (ixgbe_removed(hw->hw_addr)) + return; + pci_write_config_word(adapter->pdev, reg, value); +} + static void ixgbe_service_event_complete(struct ixgbe_adapter *adapter) { BUG_ON(!test_bit(__IXGBE_SERVICE_SCHED, &adapter->state)); /* flush memory to make sure state is correct before next watchdog */ - smp_mb__before_clear_bit(); + smp_mb__before_atomic(); clear_bit(__IXGBE_SERVICE_SCHED, &adapter->state); } @@ -872,11 +986,18 @@ static u64 ixgbe_get_tx_completed(struct ixgbe_ring *ring) static u64 ixgbe_get_tx_pending(struct ixgbe_ring *ring) { - struct ixgbe_adapter *adapter = netdev_priv(ring->netdev); - struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_adapter *adapter; + struct ixgbe_hw *hw; + u32 head, tail; + + if (ring->l2_accel_priv) + adapter = ring->l2_accel_priv->real_adapter; + else + adapter = netdev_priv(ring->netdev); - u32 head = IXGBE_READ_REG(hw, IXGBE_TDH(ring->reg_idx)); - u32 tail = IXGBE_READ_REG(hw, IXGBE_TDT(ring->reg_idx)); + hw = &adapter->hw; + head = IXGBE_READ_REG(hw, IXGBE_TDH(ring->reg_idx)); + tail = IXGBE_READ_REG(hw, IXGBE_TDT(ring->reg_idx)); if (head != tail) return (head < tail) ? @@ -1227,7 +1348,9 @@ static inline void ixgbe_rx_hash(struct ixgbe_ring *ring, struct sk_buff *skb) { if (ring->netdev->features & NETIF_F_RXHASH) - skb->rxhash = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss); + skb_set_hash(skb, + le32_to_cpu(rx_desc->wb.lower.hi_dword.rss), + PKT_HASH_TYPE_L3); } #ifdef IXGBE_FCOE @@ -1308,7 +1431,7 @@ static inline void ixgbe_release_rx_desc(struct ixgbe_ring *rx_ring, u32 val) * such as IA-64). */ wmb(); - writel(val, rx_ring->tail); + ixgbe_write_tail(rx_ring, val); } static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring, @@ -1443,7 +1566,7 @@ static unsigned int ixgbe_get_headlen(unsigned char *data, hdr.network += ETH_HLEN; /* handle any vlan tag if present */ - if (protocol == __constant_htons(ETH_P_8021Q)) { + if (protocol == htons(ETH_P_8021Q)) { if ((hdr.network - data) > (max_len - VLAN_HLEN)) return max_len; @@ -1452,7 +1575,7 @@ static unsigned int ixgbe_get_headlen(unsigned char *data, } /* handle L3 protocols */ - if (protocol == __constant_htons(ETH_P_IP)) { + if (protocol == htons(ETH_P_IP)) { if ((hdr.network - data) > (max_len - sizeof(struct iphdr))) return max_len; @@ -1466,7 +1589,7 @@ static unsigned int ixgbe_get_headlen(unsigned char *data, /* record next protocol if header is present */ if (!(hdr.ipv4->frag_off & htons(IP_OFFSET))) nexthdr = hdr.ipv4->protocol; - } else if (protocol == __constant_htons(ETH_P_IPV6)) { + } else if (protocol == htons(ETH_P_IPV6)) { if ((hdr.network - data) > (max_len - sizeof(struct ipv6hdr))) return max_len; @@ -1474,7 +1597,7 @@ static unsigned int ixgbe_get_headlen(unsigned char *data, nexthdr = hdr.ipv6->nexthdr; hlen = sizeof(struct ipv6hdr); #ifdef IXGBE_FCOE - } else if (protocol == __constant_htons(ETH_P_FCOE)) { + } else if (protocol == htons(ETH_P_FCOE)) { if ((hdr.network - data) > (max_len - FCOE_HEADER_LEN)) return max_len; hlen = FCOE_HEADER_LEN; @@ -1567,7 +1690,8 @@ static void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring, ixgbe_rx_checksum(rx_ring, rx_desc, skb); - ixgbe_ptp_rx_hwtstamp(rx_ring, rx_desc, skb); + if (unlikely(ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_STAT_TS))) + ixgbe_ptp_rx_hwtstamp(rx_ring->q_vector->adapter, skb); if ((dev->features & NETIF_F_HW_VLAN_CTAG_RX) && ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_VP)) { @@ -1585,7 +1709,7 @@ static void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector, { struct ixgbe_adapter *adapter = q_vector->adapter; - if (ixgbe_qv_ll_polling(q_vector)) + if (ixgbe_qv_busy_polling(q_vector)) netif_receive_skb(skb); else if (!(adapter->flags & IXGBE_FLAG_IN_NETPOLL)) napi_gro_receive(&q_vector->napi, skb); @@ -1989,7 +2113,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, #endif /* IXGBE_FCOE */ u16 cleaned_count = ixgbe_desc_unused(rx_ring); - do { + while (likely(total_rx_packets < budget)) { union ixgbe_adv_rx_desc *rx_desc; struct sk_buff *skb; @@ -2064,7 +2188,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, /* update budget accounting */ total_rx_packets++; - } while (likely(total_rx_packets < budget)); + } u64_stats_update_begin(&rx_ring->syncp); rx_ring->stats.packets += total_rx_packets; @@ -2097,7 +2221,7 @@ static int ixgbe_low_latency_recv(struct napi_struct *napi) ixgbe_for_each_ring(ring, q_vector->rx) { found = ixgbe_clean_rx_irq(q_vector, ring, 4); -#ifdef LL_EXTENDED_STATS +#ifdef BP_EXTENDED_STATS if (found) ring->stats.cleaned += found; else @@ -2593,9 +2717,12 @@ static irqreturn_t ixgbe_msix_other(int irq, void *data) switch (hw->mac.type) { case ixgbe_mac_82599EB: case ixgbe_mac_X540: - if (eicr & IXGBE_EICR_ECC) - e_info(link, "Received unrecoverable ECC Err, please " - "reboot\n"); + if (eicr & IXGBE_EICR_ECC) { + e_info(link, "Received ECC Err, initiating reset\n"); + adapter->flags2 |= IXGBE_FLAG2_RESET_REQUESTED; + ixgbe_service_event_schedule(adapter); + IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_ECC); + } /* Handle Flow Director Full threshold interrupt */ if (eicr & IXGBE_EICR_FLOW_DIR) { int reinit_count = 0; @@ -2809,9 +2936,12 @@ static irqreturn_t ixgbe_intr(int irq, void *data) ixgbe_check_sfp_event(adapter, eicr); /* Fall through */ case ixgbe_mac_X540: - if (eicr & IXGBE_EICR_ECC) - e_info(link, "Received unrecoverable ECC err, please " - "reboot\n"); + if (eicr & IXGBE_EICR_ECC) { + e_info(link, "Received ECC Err, initiating reset\n"); + adapter->flags2 |= IXGBE_FLAG2_RESET_REQUESTED; + ixgbe_service_event_schedule(adapter); + IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_ECC); + } ixgbe_check_overtemp_event(adapter, eicr); break; default: @@ -2963,7 +3093,7 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter, ring->count * sizeof(union ixgbe_adv_tx_desc)); IXGBE_WRITE_REG(hw, IXGBE_TDH(reg_idx), 0); IXGBE_WRITE_REG(hw, IXGBE_TDT(reg_idx), 0); - ring->tail = hw->hw_addr + IXGBE_TDT(reg_idx); + ring->tail = adapter->io_addr + IXGBE_TDT(reg_idx); /* * set WTHRESH to encourage burst writeback, it should not be set @@ -3005,7 +3135,7 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter, struct ixgbe_q_vector *q_vector = ring->q_vector; if (q_vector) - netif_set_xps_queue(adapter->netdev, + netif_set_xps_queue(ring->netdev, &q_vector->affinity_mask, ring->queue_index); } @@ -3302,6 +3432,8 @@ static void ixgbe_rx_desc_queue_enable(struct ixgbe_adapter *adapter, u32 rxdctl; u8 reg_idx = ring->reg_idx; + if (ixgbe_removed(hw->hw_addr)) + return; /* RXDCTL.EN will return 0 on 82598 if link is down, so skip it */ if (hw->mac.type == ixgbe_mac_82598EB && !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP)) @@ -3326,6 +3458,8 @@ void ixgbe_disable_rx_queue(struct ixgbe_adapter *adapter, u32 rxdctl; u8 reg_idx = ring->reg_idx; + if (ixgbe_removed(hw->hw_addr)) + return; rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx)); rxdctl &= ~IXGBE_RXDCTL_ENABLE; @@ -3366,7 +3500,7 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, ring->count * sizeof(union ixgbe_adv_rx_desc)); IXGBE_WRITE_REG(hw, IXGBE_RDH(reg_idx), 0); IXGBE_WRITE_REG(hw, IXGBE_RDT(reg_idx), 0); - ring->tail = hw->hw_addr + IXGBE_RDT(reg_idx); + ring->tail = adapter->io_addr + IXGBE_RDT(reg_idx); ixgbe_configure_srrctl(adapter, ring); ixgbe_configure_rscctl(adapter, ring); @@ -3395,7 +3529,7 @@ static void ixgbe_setup_psrtype(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; int rss_i = adapter->ring_feature[RING_F_RSS].indices; - int p; + u16 pool; /* PSRTYPE must be initialized in non 82598 adapters */ u32 psrtype = IXGBE_PSRTYPE_TCPHDR | @@ -3412,9 +3546,8 @@ static void ixgbe_setup_psrtype(struct ixgbe_adapter *adapter) else if (rss_i > 1) psrtype |= 1 << 29; - for (p = 0; p < adapter->num_rx_pools; p++) - IXGBE_WRITE_REG(hw, IXGBE_PSRTYPE(VMDQ_P(p)), - psrtype); + for_each_set_bit(pool, &adapter->fwd_bitmask, 32) + IXGBE_WRITE_REG(hw, IXGBE_PSRTYPE(VMDQ_P(pool)), psrtype); } static void ixgbe_configure_virtualization(struct ixgbe_adapter *adapter) @@ -3636,35 +3769,6 @@ static int ixgbe_vlan_rx_kill_vid(struct net_device *netdev, } /** - * ixgbe_vlan_filter_disable - helper to disable hw vlan filtering - * @adapter: driver data - */ -static void ixgbe_vlan_filter_disable(struct ixgbe_adapter *adapter) -{ - struct ixgbe_hw *hw = &adapter->hw; - u32 vlnctrl; - - vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); - vlnctrl &= ~(IXGBE_VLNCTRL_VFE | IXGBE_VLNCTRL_CFIEN); - IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl); -} - -/** - * ixgbe_vlan_filter_enable - helper to enable hw vlan filtering - * @adapter: driver data - */ -static void ixgbe_vlan_filter_enable(struct ixgbe_adapter *adapter) -{ - struct ixgbe_hw *hw = &adapter->hw; - u32 vlnctrl; - - vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); - vlnctrl |= IXGBE_VLNCTRL_VFE; - vlnctrl &= ~IXGBE_VLNCTRL_CFIEN; - IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl); -} - -/** * ixgbe_vlan_strip_disable - helper to disable hw vlan stripping * @adapter: driver data */ @@ -3683,7 +3787,11 @@ static void ixgbe_vlan_strip_disable(struct ixgbe_adapter *adapter) case ixgbe_mac_82599EB: case ixgbe_mac_X540: for (i = 0; i < adapter->num_rx_queues; i++) { - j = adapter->rx_ring[i]->reg_idx; + struct ixgbe_ring *ring = adapter->rx_ring[i]; + + if (ring->l2_accel_priv) + continue; + j = ring->reg_idx; vlnctrl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(j)); vlnctrl &= ~IXGBE_RXDCTL_VME; IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(j), vlnctrl); @@ -3713,7 +3821,11 @@ static void ixgbe_vlan_strip_enable(struct ixgbe_adapter *adapter) case ixgbe_mac_82599EB: case ixgbe_mac_X540: for (i = 0; i < adapter->num_rx_queues; i++) { - j = adapter->rx_ring[i]->reg_idx; + struct ixgbe_ring *ring = adapter->rx_ring[i]; + + if (ring->l2_accel_priv) + continue; + j = ring->reg_idx; vlnctrl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(j)); vlnctrl |= IXGBE_RXDCTL_VME; IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(j), vlnctrl); @@ -3735,6 +3847,158 @@ static void ixgbe_restore_vlan(struct ixgbe_adapter *adapter) } /** + * ixgbe_write_mc_addr_list - write multicast addresses to MTA + * @netdev: network interface device structure + * + * Writes multicast address list to the MTA hash table. + * Returns: -ENOMEM on failure + * 0 on no addresses written + * X on writing X addresses to MTA + **/ +static int ixgbe_write_mc_addr_list(struct net_device *netdev) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + + if (!netif_running(netdev)) + return 0; + + if (hw->mac.ops.update_mc_addr_list) + hw->mac.ops.update_mc_addr_list(hw, netdev); + else + return -ENOMEM; + +#ifdef CONFIG_PCI_IOV + ixgbe_restore_vf_multicasts(adapter); +#endif + + return netdev_mc_count(netdev); +} + +#ifdef CONFIG_PCI_IOV +void ixgbe_full_sync_mac_table(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int i; + for (i = 0; i < hw->mac.num_rar_entries; i++) { + if (adapter->mac_table[i].state & IXGBE_MAC_STATE_IN_USE) + hw->mac.ops.set_rar(hw, i, adapter->mac_table[i].addr, + adapter->mac_table[i].queue, + IXGBE_RAH_AV); + else + hw->mac.ops.clear_rar(hw, i); + + adapter->mac_table[i].state &= ~(IXGBE_MAC_STATE_MODIFIED); + } +} +#endif + +static void ixgbe_sync_mac_table(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int i; + for (i = 0; i < hw->mac.num_rar_entries; i++) { + if (adapter->mac_table[i].state & IXGBE_MAC_STATE_MODIFIED) { + if (adapter->mac_table[i].state & + IXGBE_MAC_STATE_IN_USE) + hw->mac.ops.set_rar(hw, i, + adapter->mac_table[i].addr, + adapter->mac_table[i].queue, + IXGBE_RAH_AV); + else + hw->mac.ops.clear_rar(hw, i); + + adapter->mac_table[i].state &= + ~(IXGBE_MAC_STATE_MODIFIED); + } + } +} + +static void ixgbe_flush_sw_mac_table(struct ixgbe_adapter *adapter) +{ + int i; + struct ixgbe_hw *hw = &adapter->hw; + + for (i = 0; i < hw->mac.num_rar_entries; i++) { + adapter->mac_table[i].state |= IXGBE_MAC_STATE_MODIFIED; + adapter->mac_table[i].state &= ~IXGBE_MAC_STATE_IN_USE; + memset(adapter->mac_table[i].addr, 0, ETH_ALEN); + adapter->mac_table[i].queue = 0; + } + ixgbe_sync_mac_table(adapter); +} + +static int ixgbe_available_rars(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int i, count = 0; + + for (i = 0; i < hw->mac.num_rar_entries; i++) { + if (adapter->mac_table[i].state == 0) + count++; + } + return count; +} + +/* this function destroys the first RAR entry */ +static void ixgbe_mac_set_default_filter(struct ixgbe_adapter *adapter, + u8 *addr) +{ + struct ixgbe_hw *hw = &adapter->hw; + + memcpy(&adapter->mac_table[0].addr, addr, ETH_ALEN); + adapter->mac_table[0].queue = VMDQ_P(0); + adapter->mac_table[0].state = (IXGBE_MAC_STATE_DEFAULT | + IXGBE_MAC_STATE_IN_USE); + hw->mac.ops.set_rar(hw, 0, adapter->mac_table[0].addr, + adapter->mac_table[0].queue, + IXGBE_RAH_AV); +} + +int ixgbe_add_mac_filter(struct ixgbe_adapter *adapter, u8 *addr, u16 queue) +{ + struct ixgbe_hw *hw = &adapter->hw; + int i; + + if (is_zero_ether_addr(addr)) + return -EINVAL; + + for (i = 0; i < hw->mac.num_rar_entries; i++) { + if (adapter->mac_table[i].state & IXGBE_MAC_STATE_IN_USE) + continue; + adapter->mac_table[i].state |= (IXGBE_MAC_STATE_MODIFIED | + IXGBE_MAC_STATE_IN_USE); + ether_addr_copy(adapter->mac_table[i].addr, addr); + adapter->mac_table[i].queue = queue; + ixgbe_sync_mac_table(adapter); + return i; + } + return -ENOMEM; +} + +int ixgbe_del_mac_filter(struct ixgbe_adapter *adapter, u8 *addr, u16 queue) +{ + /* search table for addr, if found, set to 0 and sync */ + int i; + struct ixgbe_hw *hw = &adapter->hw; + + if (is_zero_ether_addr(addr)) + return -EINVAL; + + for (i = 0; i < hw->mac.num_rar_entries; i++) { + if (ether_addr_equal(addr, adapter->mac_table[i].addr) && + adapter->mac_table[i].queue == queue) { + adapter->mac_table[i].state |= IXGBE_MAC_STATE_MODIFIED; + adapter->mac_table[i].state &= ~IXGBE_MAC_STATE_IN_USE; + memset(adapter->mac_table[i].addr, 0, ETH_ALEN); + adapter->mac_table[i].queue = 0; + ixgbe_sync_mac_table(adapter); + return 0; + } + } + return -ENOMEM; +} +/** * ixgbe_write_uc_addr_list - write unicast addresses to RAR table * @netdev: network interface device structure * @@ -3743,39 +4007,23 @@ static void ixgbe_restore_vlan(struct ixgbe_adapter *adapter) * 0 on no addresses written * X on writing X addresses to the RAR table **/ -static int ixgbe_write_uc_addr_list(struct net_device *netdev) +static int ixgbe_write_uc_addr_list(struct net_device *netdev, int vfn) { struct ixgbe_adapter *adapter = netdev_priv(netdev); - struct ixgbe_hw *hw = &adapter->hw; - unsigned int rar_entries = hw->mac.num_rar_entries - 1; int count = 0; - /* In SR-IOV mode significantly less RAR entries are available */ - if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) - rar_entries = IXGBE_MAX_PF_MACVLANS - 1; - /* return ENOMEM indicating insufficient memory for addresses */ - if (netdev_uc_count(netdev) > rar_entries) + if (netdev_uc_count(netdev) > ixgbe_available_rars(adapter)) return -ENOMEM; if (!netdev_uc_empty(netdev)) { struct netdev_hw_addr *ha; - /* return error if we do not support writing to RAR table */ - if (!hw->mac.ops.set_rar) - return -ENOMEM; - netdev_for_each_uc_addr(ha, netdev) { - if (!rar_entries) - break; - hw->mac.ops.set_rar(hw, rar_entries--, ha->addr, - VMDQ_P(0), IXGBE_RAH_AV); + ixgbe_del_mac_filter(adapter, ha->addr, vfn); + ixgbe_add_mac_filter(adapter, ha->addr, vfn); count++; } } - /* write the addresses in reverse order to avoid write combining */ - for (; rar_entries > 0 ; rar_entries--) - hw->mac.ops.clear_rar(hw, rar_entries); - return count; } @@ -3793,11 +4041,12 @@ void ixgbe_set_rx_mode(struct net_device *netdev) struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; u32 fctrl, vmolr = IXGBE_VMOLR_BAM | IXGBE_VMOLR_AUPE; + u32 vlnctrl; int count; /* Check for Promiscuous and All Multicast modes */ - fctrl = IXGBE_READ_REG(hw, IXGBE_FCTRL); + vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); /* set all bits that we expect to always be set */ fctrl &= ~IXGBE_FCTRL_SBP; /* disable store-bad-packets */ @@ -3807,34 +4056,24 @@ void ixgbe_set_rx_mode(struct net_device *netdev) /* clear the bits we are changing the status of */ fctrl &= ~(IXGBE_FCTRL_UPE | IXGBE_FCTRL_MPE); - + vlnctrl &= ~(IXGBE_VLNCTRL_VFE | IXGBE_VLNCTRL_CFIEN); if (netdev->flags & IFF_PROMISC) { hw->addr_ctrl.user_set_promisc = true; fctrl |= (IXGBE_FCTRL_UPE | IXGBE_FCTRL_MPE); - vmolr |= (IXGBE_VMOLR_ROPE | IXGBE_VMOLR_MPE); + vmolr |= IXGBE_VMOLR_MPE; /* Only disable hardware filter vlans in promiscuous mode * if SR-IOV and VMDQ are disabled - otherwise ensure * that hardware VLAN filters remain enabled. */ if (!(adapter->flags & (IXGBE_FLAG_VMDQ_ENABLED | IXGBE_FLAG_SRIOV_ENABLED))) - ixgbe_vlan_filter_disable(adapter); - else - ixgbe_vlan_filter_enable(adapter); + vlnctrl |= (IXGBE_VLNCTRL_VFE | IXGBE_VLNCTRL_CFIEN); } else { if (netdev->flags & IFF_ALLMULTI) { fctrl |= IXGBE_FCTRL_MPE; vmolr |= IXGBE_VMOLR_MPE; - } else { - /* - * Write addresses to the MTA, if the attempt fails - * then we should just turn on promiscuous mode so - * that we can at least receive multicast traffic - */ - hw->mac.ops.update_mc_addr_list(hw, netdev); - vmolr |= IXGBE_VMOLR_ROMPE; } - ixgbe_vlan_filter_enable(adapter); + vlnctrl |= IXGBE_VLNCTRL_VFE; hw->addr_ctrl.user_set_promisc = false; } @@ -3843,14 +4082,23 @@ void ixgbe_set_rx_mode(struct net_device *netdev) * sufficient space to store all the addresses then enable * unicast promiscuous mode */ - count = ixgbe_write_uc_addr_list(netdev); + count = ixgbe_write_uc_addr_list(netdev, VMDQ_P(0)); if (count < 0) { fctrl |= IXGBE_FCTRL_UPE; vmolr |= IXGBE_VMOLR_ROPE; } - if (adapter->num_vfs) - ixgbe_restore_vf_multicasts(adapter); + /* Write addresses to the MTA, if the attempt fails + * then we should just turn on promiscuous mode so + * that we can at least receive multicast traffic + */ + count = ixgbe_write_mc_addr_list(netdev); + if (count < 0) { + fctrl |= IXGBE_FCTRL_MPE; + vmolr |= IXGBE_VMOLR_MPE; + } else if (count) { + vmolr |= IXGBE_VMOLR_ROMPE; + } if (hw->mac.type != ixgbe_mac_82598EB) { vmolr |= IXGBE_READ_REG(hw, IXGBE_VMOLR(VMDQ_P(0))) & @@ -3871,6 +4119,7 @@ void ixgbe_set_rx_mode(struct net_device *netdev) /* NOTE: VLAN filtering is disabled by setting PROMISC */ } + IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl); IXGBE_WRITE_REG(hw, IXGBE_FCTRL, fctrl); if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX) @@ -3893,15 +4142,13 @@ static void ixgbe_napi_disable_all(struct ixgbe_adapter *adapter) { int q_idx; - local_bh_disable(); /* for ixgbe_qv_lock_napi() */ for (q_idx = 0; q_idx < adapter->num_q_vectors; q_idx++) { napi_disable(&adapter->q_vector[q_idx]->napi); - while (!ixgbe_qv_lock_napi(adapter->q_vector[q_idx])) { + while (!ixgbe_qv_disable(adapter->q_vector[q_idx])) { pr_info("QV %d locked\n", q_idx); - mdelay(1); + usleep_range(1000, 20000); } } - local_bh_enable(); } #ifdef CONFIG_IXGBE_DCB @@ -3989,8 +4236,8 @@ static int ixgbe_hpbthresh(struct ixgbe_adapter *adapter, int pb) (tc < IXGBE_FCOE_JUMBO_FRAME_SIZE) && (pb == ixgbe_fcoe_get_tc(adapter))) tc = IXGBE_FCOE_JUMBO_FRAME_SIZE; - #endif + /* Calculate delay value for device */ switch (hw->mac.type) { case ixgbe_mac_X540: @@ -4031,7 +4278,7 @@ static int ixgbe_hpbthresh(struct ixgbe_adapter *adapter, int pb) * @adapter: board private structure to calculate for * @pb: packet buffer to calculate */ -static int ixgbe_lpbthresh(struct ixgbe_adapter *adapter) +static int ixgbe_lpbthresh(struct ixgbe_adapter *adapter, int pb) { struct ixgbe_hw *hw = &adapter->hw; struct net_device *dev = adapter->netdev; @@ -4041,6 +4288,14 @@ static int ixgbe_lpbthresh(struct ixgbe_adapter *adapter) /* Calculate max LAN frame size */ tc = dev->mtu + ETH_HLEN + ETH_FCS_LEN; +#ifdef IXGBE_FCOE + /* FCoE traffic class uses FCOE jumbo frames */ + if ((dev->features & NETIF_F_FCOE_MTU) && + (tc < IXGBE_FCOE_JUMBO_FRAME_SIZE) && + (pb == netdev_get_prio_tc_map(dev, adapter->fcoe.up))) + tc = IXGBE_FCOE_JUMBO_FRAME_SIZE; +#endif + /* Calculate delay value for device */ switch (hw->mac.type) { case ixgbe_mac_X540: @@ -4067,15 +4322,17 @@ static void ixgbe_pbthresh_setup(struct ixgbe_adapter *adapter) if (!num_tc) num_tc = 1; - hw->fc.low_water = ixgbe_lpbthresh(adapter); - for (i = 0; i < num_tc; i++) { hw->fc.high_water[i] = ixgbe_hpbthresh(adapter, i); + hw->fc.low_water[i] = ixgbe_lpbthresh(adapter, i); /* Low water marks must not be larger than high water marks */ - if (hw->fc.low_water > hw->fc.high_water[i]) - hw->fc.low_water = 0; + if (hw->fc.low_water[i] > hw->fc.high_water[i]) + hw->fc.low_water[i] = 0; } + + for (; i < MAX_TRAFFIC_CLASS; i++) + hw->fc.high_water[i] = 0; } static void ixgbe_configure_pb(struct ixgbe_adapter *adapter) @@ -4118,6 +4375,218 @@ static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter) spin_unlock(&adapter->fdir_perfect_lock); } +static void ixgbe_macvlan_set_rx_mode(struct net_device *dev, unsigned int pool, + struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 vmolr; + + /* No unicast promiscuous support for VMDQ devices. */ + vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(pool)); + vmolr |= (IXGBE_VMOLR_ROMPE | IXGBE_VMOLR_BAM | IXGBE_VMOLR_AUPE); + + /* clear the affected bit */ + vmolr &= ~IXGBE_VMOLR_MPE; + + if (dev->flags & IFF_ALLMULTI) { + vmolr |= IXGBE_VMOLR_MPE; + } else { + vmolr |= IXGBE_VMOLR_ROMPE; + hw->mac.ops.update_mc_addr_list(hw, dev); + } + ixgbe_write_uc_addr_list(adapter->netdev, pool); + IXGBE_WRITE_REG(hw, IXGBE_VMOLR(pool), vmolr); +} + +static void ixgbe_fwd_psrtype(struct ixgbe_fwd_adapter *vadapter) +{ + struct ixgbe_adapter *adapter = vadapter->real_adapter; + int rss_i = adapter->num_rx_queues_per_pool; + struct ixgbe_hw *hw = &adapter->hw; + u16 pool = vadapter->pool; + u32 psrtype = IXGBE_PSRTYPE_TCPHDR | + IXGBE_PSRTYPE_UDPHDR | + IXGBE_PSRTYPE_IPV4HDR | + IXGBE_PSRTYPE_L2HDR | + IXGBE_PSRTYPE_IPV6HDR; + + if (hw->mac.type == ixgbe_mac_82598EB) + return; + + if (rss_i > 3) + psrtype |= 2 << 29; + else if (rss_i > 1) + psrtype |= 1 << 29; + + IXGBE_WRITE_REG(hw, IXGBE_PSRTYPE(VMDQ_P(pool)), psrtype); +} + +/** + * ixgbe_clean_rx_ring - Free Rx Buffers per Queue + * @rx_ring: ring to free buffers from + **/ +static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring) +{ + struct device *dev = rx_ring->dev; + unsigned long size; + u16 i; + + /* ring already cleared, nothing to do */ + if (!rx_ring->rx_buffer_info) + return; + + /* Free all the Rx ring sk_buffs */ + for (i = 0; i < rx_ring->count; i++) { + struct ixgbe_rx_buffer *rx_buffer; + + rx_buffer = &rx_ring->rx_buffer_info[i]; + if (rx_buffer->skb) { + struct sk_buff *skb = rx_buffer->skb; + if (IXGBE_CB(skb)->page_released) { + dma_unmap_page(dev, + IXGBE_CB(skb)->dma, + ixgbe_rx_bufsz(rx_ring), + DMA_FROM_DEVICE); + IXGBE_CB(skb)->page_released = false; + } + dev_kfree_skb(skb); + } + rx_buffer->skb = NULL; + if (rx_buffer->dma) + dma_unmap_page(dev, rx_buffer->dma, + ixgbe_rx_pg_size(rx_ring), + DMA_FROM_DEVICE); + rx_buffer->dma = 0; + if (rx_buffer->page) + __free_pages(rx_buffer->page, + ixgbe_rx_pg_order(rx_ring)); + rx_buffer->page = NULL; + } + + size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count; + memset(rx_ring->rx_buffer_info, 0, size); + + /* Zero out the descriptor ring */ + memset(rx_ring->desc, 0, rx_ring->size); + + rx_ring->next_to_alloc = 0; + rx_ring->next_to_clean = 0; + rx_ring->next_to_use = 0; +} + +static void ixgbe_disable_fwd_ring(struct ixgbe_fwd_adapter *vadapter, + struct ixgbe_ring *rx_ring) +{ + struct ixgbe_adapter *adapter = vadapter->real_adapter; + int index = rx_ring->queue_index + vadapter->rx_base_queue; + + /* shutdown specific queue receive and wait for dma to settle */ + ixgbe_disable_rx_queue(adapter, rx_ring); + usleep_range(10000, 20000); + ixgbe_irq_disable_queues(adapter, ((u64)1 << index)); + ixgbe_clean_rx_ring(rx_ring); + rx_ring->l2_accel_priv = NULL; +} + +static int ixgbe_fwd_ring_down(struct net_device *vdev, + struct ixgbe_fwd_adapter *accel) +{ + struct ixgbe_adapter *adapter = accel->real_adapter; + unsigned int rxbase = accel->rx_base_queue; + unsigned int txbase = accel->tx_base_queue; + int i; + + netif_tx_stop_all_queues(vdev); + + for (i = 0; i < adapter->num_rx_queues_per_pool; i++) { + ixgbe_disable_fwd_ring(accel, adapter->rx_ring[rxbase + i]); + adapter->rx_ring[rxbase + i]->netdev = adapter->netdev; + } + + for (i = 0; i < adapter->num_rx_queues_per_pool; i++) { + adapter->tx_ring[txbase + i]->l2_accel_priv = NULL; + adapter->tx_ring[txbase + i]->netdev = adapter->netdev; + } + + + return 0; +} + +static int ixgbe_fwd_ring_up(struct net_device *vdev, + struct ixgbe_fwd_adapter *accel) +{ + struct ixgbe_adapter *adapter = accel->real_adapter; + unsigned int rxbase, txbase, queues; + int i, baseq, err = 0; + + if (!test_bit(accel->pool, &adapter->fwd_bitmask)) + return 0; + + baseq = accel->pool * adapter->num_rx_queues_per_pool; + netdev_dbg(vdev, "pool %i:%i queues %i:%i VSI bitmask %lx\n", + accel->pool, adapter->num_rx_pools, + baseq, baseq + adapter->num_rx_queues_per_pool, + adapter->fwd_bitmask); + + accel->netdev = vdev; + accel->rx_base_queue = rxbase = baseq; + accel->tx_base_queue = txbase = baseq; + + for (i = 0; i < adapter->num_rx_queues_per_pool; i++) + ixgbe_disable_fwd_ring(accel, adapter->rx_ring[rxbase + i]); + + for (i = 0; i < adapter->num_rx_queues_per_pool; i++) { + adapter->rx_ring[rxbase + i]->netdev = vdev; + adapter->rx_ring[rxbase + i]->l2_accel_priv = accel; + ixgbe_configure_rx_ring(adapter, adapter->rx_ring[rxbase + i]); + } + + for (i = 0; i < adapter->num_rx_queues_per_pool; i++) { + adapter->tx_ring[txbase + i]->netdev = vdev; + adapter->tx_ring[txbase + i]->l2_accel_priv = accel; + } + + queues = min_t(unsigned int, + adapter->num_rx_queues_per_pool, vdev->num_tx_queues); + err = netif_set_real_num_tx_queues(vdev, queues); + if (err) + goto fwd_queue_err; + + err = netif_set_real_num_rx_queues(vdev, queues); + if (err) + goto fwd_queue_err; + + if (is_valid_ether_addr(vdev->dev_addr)) + ixgbe_add_mac_filter(adapter, vdev->dev_addr, accel->pool); + + ixgbe_fwd_psrtype(accel); + ixgbe_macvlan_set_rx_mode(vdev, accel->pool, adapter); + return err; +fwd_queue_err: + ixgbe_fwd_ring_down(vdev, accel); + return err; +} + +static void ixgbe_configure_dfwd(struct ixgbe_adapter *adapter) +{ + struct net_device *upper; + struct list_head *iter; + int err; + + netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) { + if (netif_is_macvlan(upper)) { + struct macvlan_dev *dfwd = netdev_priv(upper); + struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv; + + if (dfwd->fwd_priv) { + err = ixgbe_fwd_ring_up(upper, vadapter); + if (err) + continue; + } + } + } +} + static void ixgbe_configure(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; @@ -4169,6 +4638,7 @@ static void ixgbe_configure(struct ixgbe_adapter *adapter) #endif /* IXGBE_FCOE */ ixgbe_configure_tx(adapter); ixgbe_configure_rx(adapter); + ixgbe_configure_dfwd(adapter); } static inline bool ixgbe_is_sfp(struct ixgbe_hw *hw) @@ -4186,6 +4656,8 @@ static inline bool ixgbe_is_sfp(struct ixgbe_hw *hw) case ixgbe_phy_qsfp_active_unknown: case ixgbe_phy_qsfp_intel: case ixgbe_phy_qsfp_unknown: + /* ixgbe_phy_none is set when no SFP module is present */ + case ixgbe_phy_none: return true; case ixgbe_phy_nl: if (hw->mac.type == ixgbe_mac_82598EB) @@ -4337,6 +4809,7 @@ static void ixgbe_up_complete(struct ixgbe_adapter *adapter) if (hw->mac.ops.enable_tx_laser) hw->mac.ops.enable_tx_laser(hw); + smp_mb__before_atomic(); clear_bit(__IXGBE_DOWN, &adapter->state); ixgbe_napi_enable_all(adapter); @@ -4362,9 +4835,6 @@ static void ixgbe_up_complete(struct ixgbe_adapter *adapter) e_crit(drv, "Fan has stopped, replace the adapter\n"); } - /* enable transmits */ - netif_tx_start_all_queues(adapter->netdev); - /* bring the link up in the watchdog, this could race with our first * link up interrupt but shouldn't be a problem */ adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE; @@ -4409,8 +4879,12 @@ void ixgbe_up(struct ixgbe_adapter *adapter) void ixgbe_reset(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; int err; + u8 old_addr[ETH_ALEN]; + if (ixgbe_removed(hw->hw_addr)) + return; /* lock SFP init bit to prevent race conditions with the watchdog */ while (test_and_set_bit(__IXGBE_IN_SFP_INIT, &adapter->state)) usleep_range(1000, 2000); @@ -4443,9 +4917,10 @@ void ixgbe_reset(struct ixgbe_adapter *adapter) } clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state); - - /* reprogram the RAR[0] in case user changed it. */ - hw->mac.ops.set_rar(hw, 0, hw->mac.addr, VMDQ_P(0), IXGBE_RAH_AV); + /* do not flush user set addresses */ + memcpy(old_addr, &adapter->mac_table[0].addr, netdev->addr_len); + ixgbe_flush_sw_mac_table(adapter); + ixgbe_mac_set_default_filter(adapter, old_addr); /* update SAN MAC vmdq pool selection */ if (hw->mac.san_mac_rar_index) @@ -4456,59 +4931,6 @@ void ixgbe_reset(struct ixgbe_adapter *adapter) } /** - * ixgbe_clean_rx_ring - Free Rx Buffers per Queue - * @rx_ring: ring to free buffers from - **/ -static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring) -{ - struct device *dev = rx_ring->dev; - unsigned long size; - u16 i; - - /* ring already cleared, nothing to do */ - if (!rx_ring->rx_buffer_info) - return; - - /* Free all the Rx ring sk_buffs */ - for (i = 0; i < rx_ring->count; i++) { - struct ixgbe_rx_buffer *rx_buffer; - - rx_buffer = &rx_ring->rx_buffer_info[i]; - if (rx_buffer->skb) { - struct sk_buff *skb = rx_buffer->skb; - if (IXGBE_CB(skb)->page_released) { - dma_unmap_page(dev, - IXGBE_CB(skb)->dma, - ixgbe_rx_bufsz(rx_ring), - DMA_FROM_DEVICE); - IXGBE_CB(skb)->page_released = false; - } - dev_kfree_skb(skb); - } - rx_buffer->skb = NULL; - if (rx_buffer->dma) - dma_unmap_page(dev, rx_buffer->dma, - ixgbe_rx_pg_size(rx_ring), - DMA_FROM_DEVICE); - rx_buffer->dma = 0; - if (rx_buffer->page) - __free_pages(rx_buffer->page, - ixgbe_rx_pg_order(rx_ring)); - rx_buffer->page = NULL; - } - - size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count; - memset(rx_ring->rx_buffer_info, 0, size); - - /* Zero out the descriptor ring */ - memset(rx_ring->desc, 0, rx_ring->size); - - rx_ring->next_to_alloc = 0; - rx_ring->next_to_clean = 0; - rx_ring->next_to_use = 0; -} - -/** * ixgbe_clean_tx_ring - Free Tx Buffers * @tx_ring: ring to be cleaned **/ @@ -4585,11 +5007,14 @@ void ixgbe_down(struct ixgbe_adapter *adapter) { struct net_device *netdev = adapter->netdev; struct ixgbe_hw *hw = &adapter->hw; + struct net_device *upper; + struct list_head *iter; u32 rxctrl; int i; /* signal that we are down to the interrupt handler */ - set_bit(__IXGBE_DOWN, &adapter->state); + if (test_and_set_bit(__IXGBE_DOWN, &adapter->state)) + return; /* do nothing if already down */ /* disable receives */ rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL); @@ -4608,6 +5033,19 @@ void ixgbe_down(struct ixgbe_adapter *adapter) netif_carrier_off(netdev); netif_tx_disable(netdev); + /* disable any upper devices */ + netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) { + if (netif_is_macvlan(upper)) { + struct macvlan_dev *vlan = netdev_priv(upper); + + if (vlan->fwd_priv) { + netif_tx_stop_all_queues(upper); + netif_carrier_off(upper); + netif_tx_disable(upper); + } + } + } + ixgbe_irq_disable(adapter); ixgbe_napi_disable_all(adapter); @@ -4728,6 +5166,10 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter) #endif /* CONFIG_IXGBE_DCB */ #endif /* IXGBE_FCOE */ + adapter->mac_table = kzalloc(sizeof(struct ixgbe_mac_addr) * + hw->mac.num_rar_entries, + GFP_ATOMIC); + /* Set MAC specific capability flags and exceptions */ switch (hw->mac.type) { case ixgbe_mac_82598EB: @@ -4816,11 +5258,20 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter) hw->fc.disable_fc_autoneg = ixgbe_device_supports_autoneg_fc(hw); #ifdef CONFIG_PCI_IOV + if (max_vfs > 0) + e_dev_warn("Enabling SR-IOV VFs using the max_vfs module parameter is deprecated - please use the pci sysfs interface instead.\n"); + /* assign number of SR-IOV VFs */ - if (hw->mac.type != ixgbe_mac_82598EB) - adapter->num_vfs = (max_vfs > 63) ? 0 : max_vfs; + if (hw->mac.type != ixgbe_mac_82598EB) { + if (max_vfs > IXGBE_MAX_VFS_DRV_LIMIT) { + adapter->num_vfs = 0; + e_dev_warn("max_vfs parameter out of range. Not assigning any SR-IOV VFs\n"); + } else { + adapter->num_vfs = max_vfs; + } + } +#endif /* CONFIG_PCI_IOV */ -#endif /* enable itr by default in dynamic mode */ adapter->rx_itr_setting = 1; adapter->tx_itr_setting = 1; @@ -4838,6 +5289,8 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter) return -EIO; } + /* PF holds first pool slot */ + set_bit(0, &adapter->fwd_bitmask); set_bit(__IXGBE_DOWN, &adapter->state); return 0; @@ -4867,6 +5320,8 @@ int ixgbe_setup_tx_resources(struct ixgbe_ring *tx_ring) if (!tx_ring->tx_buffer_info) goto err; + u64_stats_init(&tx_ring->syncp); + /* round up to nearest 4K */ tx_ring->size = tx_ring->count * sizeof(union ixgbe_adv_tx_desc); tx_ring->size = ALIGN(tx_ring->size, 4096); @@ -4949,6 +5404,8 @@ int ixgbe_setup_rx_resources(struct ixgbe_ring *rx_ring) if (!rx_ring->rx_buffer_info) goto err; + u64_stats_init(&rx_ring->syncp); + /* Round up to nearest 4K */ rx_ring->size = rx_ring->count * sizeof(union ixgbe_adv_rx_desc); rx_ring->size = ALIGN(rx_ring->size, 4096); @@ -5143,7 +5600,7 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu) static int ixgbe_open(struct net_device *netdev) { struct ixgbe_adapter *adapter = netdev_priv(netdev); - int err; + int err, queues; /* disallow open during test */ if (test_bit(__IXGBE_TESTING, &adapter->state)) @@ -5168,16 +5625,21 @@ static int ixgbe_open(struct net_device *netdev) goto err_req_irq; /* Notify the stack of the actual queue counts. */ - err = netif_set_real_num_tx_queues(netdev, - adapter->num_rx_pools > 1 ? 1 : - adapter->num_tx_queues); + if (adapter->num_rx_pools > 1) + queues = adapter->num_rx_queues_per_pool; + else + queues = adapter->num_tx_queues; + + err = netif_set_real_num_tx_queues(netdev, queues); if (err) goto err_set_queues; - - err = netif_set_real_num_rx_queues(netdev, - adapter->num_rx_pools > 1 ? 1 : - adapter->num_rx_queues); + if (adapter->num_rx_pools > 1 && + adapter->num_rx_queues > IXGBE_MAX_L2A_QUEUES) + queues = IXGBE_MAX_L2A_QUEUES; + else + queues = adapter->num_rx_queues; + err = netif_set_real_num_rx_queues(netdev, queues); if (err) goto err_set_queues; @@ -5199,6 +5661,17 @@ err_setup_tx: return err; } +static void ixgbe_close_suspend(struct ixgbe_adapter *adapter) +{ + ixgbe_ptp_suspend(adapter); + + ixgbe_down(adapter); + ixgbe_free_irq(adapter); + + ixgbe_free_all_tx_resources(adapter); + ixgbe_free_all_rx_resources(adapter); +} + /** * ixgbe_close - Disables a network interface * @netdev: network interface device structure @@ -5216,14 +5689,10 @@ static int ixgbe_close(struct net_device *netdev) ixgbe_ptp_stop(adapter); - ixgbe_down(adapter); - ixgbe_free_irq(adapter); + ixgbe_close_suspend(adapter); ixgbe_fdir_filter_exit(adapter); - ixgbe_free_all_tx_resources(adapter); - ixgbe_free_all_rx_resources(adapter); - ixgbe_release_hw_control(adapter); return 0; @@ -5236,6 +5705,7 @@ static int ixgbe_resume(struct pci_dev *pdev) struct net_device *netdev = adapter->netdev; u32 err; + adapter->hw.hw_addr = adapter->io_addr; pci_set_power_state(pdev, PCI_D0); pci_restore_state(pdev); /* @@ -5249,6 +5719,8 @@ static int ixgbe_resume(struct pci_dev *pdev) e_dev_err("Cannot enable PCI device from suspend\n"); return err; } + smp_mb__before_atomic(); + clear_bit(__IXGBE_DISABLED, &adapter->state); pci_set_master(pdev); pci_wake_from_d3(pdev, false); @@ -5287,12 +5759,8 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake) netif_device_detach(netdev); rtnl_lock(); - if (netif_running(netdev)) { - ixgbe_down(adapter); - ixgbe_free_irq(adapter); - ixgbe_free_all_tx_resources(adapter); - ixgbe_free_all_rx_resources(adapter); - } + if (netif_running(netdev)) + ixgbe_close_suspend(adapter); rtnl_unlock(); ixgbe_clear_interrupt_scheme(adapter); @@ -5346,7 +5814,8 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake) ixgbe_release_hw_control(adapter); - pci_disable_device(pdev); + if (!test_and_set_bit(__IXGBE_DISABLED, &adapter->state)) + pci_disable_device(pdev); return 0; } @@ -5623,7 +6092,7 @@ static void ixgbe_fdir_reinit_subtask(struct ixgbe_adapter *adapter) if (ixgbe_reinit_fdir_tables_82599(hw) == 0) { for (i = 0; i < adapter->num_tx_queues; i++) set_bit(__IXGBE_TX_FDIR_INIT_DONE, - &(adapter->tx_ring[i]->state)); + &(adapter->tx_ring[i]->state)); /* re-enable flow director interrupts */ IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_FLOW_DIR); } else { @@ -5647,8 +6116,9 @@ static void ixgbe_check_hang_subtask(struct ixgbe_adapter *adapter) u64 eics = 0; int i; - /* If we're down or resetting, just bail */ + /* If we're down, removing or resetting, just bail */ if (test_bit(__IXGBE_DOWN, &adapter->state) || + test_bit(__IXGBE_REMOVING, &adapter->state) || test_bit(__IXGBE_RESETTING, &adapter->state)) return; @@ -5749,6 +6219,8 @@ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter) { struct net_device *netdev = adapter->netdev; struct ixgbe_hw *hw = &adapter->hw; + struct net_device *upper; + struct list_head *iter; u32 link_speed = adapter->link_speed; bool flow_rx, flow_tx; @@ -5800,6 +6272,21 @@ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter) netif_carrier_on(netdev); ixgbe_check_vf_rate_limit(adapter); + /* enable transmits */ + netif_tx_wake_all_queues(adapter->netdev); + + /* enable any upper devices */ + rtnl_lock(); + netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) { + if (netif_is_macvlan(upper)) { + struct macvlan_dev *vlan = netdev_priv(upper); + + if (vlan->fwd_priv) + netif_tx_wake_all_queues(upper); + } + } + rtnl_unlock(); + /* update the default user priority for VFs */ ixgbe_update_default_up(adapter); @@ -5895,8 +6382,9 @@ static void ixgbe_spoof_check(struct ixgbe_adapter *adapter) **/ static void ixgbe_watchdog_subtask(struct ixgbe_adapter *adapter) { - /* if interface is down do nothing */ + /* if interface is down, removing or resetting, do nothing */ if (test_bit(__IXGBE_DOWN, &adapter->state) || + test_bit(__IXGBE_REMOVING, &adapter->state) || test_bit(__IXGBE_RESETTING, &adapter->state)) return; @@ -6114,8 +6602,9 @@ static void ixgbe_reset_subtask(struct ixgbe_adapter *adapter) adapter->flags2 &= ~IXGBE_FLAG2_RESET_REQUESTED; - /* If we're already down or resetting, just bail */ + /* If we're already down, removing or resetting, just bail */ if (test_bit(__IXGBE_DOWN, &adapter->state) || + test_bit(__IXGBE_REMOVING, &adapter->state) || test_bit(__IXGBE_RESETTING, &adapter->state)) return; @@ -6123,7 +6612,9 @@ static void ixgbe_reset_subtask(struct ixgbe_adapter *adapter) netdev_err(adapter->netdev, "Reset adapter\n"); adapter->tx_timeout_count++; + rtnl_lock(); ixgbe_reinit_locked(adapter); + rtnl_unlock(); } /** @@ -6135,6 +6626,15 @@ static void ixgbe_service_task(struct work_struct *work) struct ixgbe_adapter *adapter = container_of(work, struct ixgbe_adapter, service_task); + if (ixgbe_removed(adapter->hw.hw_addr)) { + if (!test_bit(__IXGBE_DOWN, &adapter->state)) { + rtnl_lock(); + ixgbe_down(adapter); + rtnl_unlock(); + } + ixgbe_service_event_complete(adapter); + return; + } ixgbe_reset_subtask(adapter); ixgbe_sfp_detection_subtask(adapter); ixgbe_sfp_link_config_subtask(adapter); @@ -6158,6 +6658,7 @@ static int ixgbe_tso(struct ixgbe_ring *tx_ring, struct sk_buff *skb = first->skb; u32 vlan_macip_lens, type_tucmd; u32 mss_l4len_idx, l4len; + int err; if (skb->ip_summed != CHECKSUM_PARTIAL) return 0; @@ -6165,16 +6666,14 @@ static int ixgbe_tso(struct ixgbe_ring *tx_ring, if (!skb_is_gso(skb)) return 0; - if (skb_header_cloned(skb)) { - int err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); - if (err) - return err; - } + err = skb_cow_head(skb, 0); + if (err < 0) + return err; /* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */ type_tucmd = IXGBE_ADVTXD_TUCMD_L4T_TCP; - if (first->protocol == __constant_htons(ETH_P_IP)) { + if (first->protocol == htons(ETH_P_IP)) { struct iphdr *iph = ip_hdr(skb); iph->tot_len = 0; iph->check = 0; @@ -6234,12 +6733,12 @@ static void ixgbe_tx_csum(struct ixgbe_ring *tx_ring, } else { u8 l4_hdr = 0; switch (first->protocol) { - case __constant_htons(ETH_P_IP): + case htons(ETH_P_IP): vlan_macip_lens |= skb_network_header_len(skb); type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4; l4_hdr = ip_hdr(skb)->protocol; break; - case __constant_htons(ETH_P_IPV6): + case htons(ETH_P_IPV6): vlan_macip_lens |= skb_network_header_len(skb); l4_hdr = ipv6_hdr(skb)->nexthdr; break; @@ -6466,7 +6965,7 @@ static void ixgbe_tx_map(struct ixgbe_ring *tx_ring, tx_ring->next_to_use = i; /* notify HW of packet */ - writel(i, tx_ring->tail); + ixgbe_write_tail(tx_ring, i); return; dma_error: @@ -6514,9 +7013,9 @@ static void ixgbe_atr(struct ixgbe_ring *ring, hdr.network = skb_network_header(first->skb); /* Currently only IPv4/IPv6 with TCP is supported */ - if ((first->protocol != __constant_htons(ETH_P_IPV6) || + if ((first->protocol != htons(ETH_P_IPV6) || hdr.ipv6->nexthdr != IPPROTO_TCP) && - (first->protocol != __constant_htons(ETH_P_IP) || + (first->protocol != htons(ETH_P_IP) || hdr.ipv4->protocol != IPPROTO_TCP)) return; @@ -6549,12 +7048,12 @@ static void ixgbe_atr(struct ixgbe_ring *ring, * and write the value to source port portion of compressed dword */ if (first->tx_flags & (IXGBE_TX_FLAGS_SW_VLAN | IXGBE_TX_FLAGS_HW_VLAN)) - common.port.src ^= th->dest ^ __constant_htons(ETH_P_8021Q); + common.port.src ^= th->dest ^ htons(ETH_P_8021Q); else common.port.src ^= th->dest ^ first->protocol; common.port.dst ^= th->source; - if (first->protocol == __constant_htons(ETH_P_IP)) { + if (first->protocol == htons(ETH_P_IP)) { input.formatted.flow_type = IXGBE_ATR_FLOW_TYPE_TCPV4; common.ip ^= hdr.ipv4->saddr ^ hdr.ipv4->daddr; } else { @@ -6600,26 +7099,34 @@ static inline int ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size) return __ixgbe_maybe_stop_tx(tx_ring, size); } -#ifdef IXGBE_FCOE -static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb) +static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv, select_queue_fallback_t fallback) { + struct ixgbe_fwd_adapter *fwd_adapter = accel_priv; +#ifdef IXGBE_FCOE struct ixgbe_adapter *adapter; struct ixgbe_ring_feature *f; int txq; +#endif + + if (fwd_adapter) + return skb->queue_mapping + fwd_adapter->tx_base_queue; + +#ifdef IXGBE_FCOE /* * only execute the code below if protocol is FCoE * or FIP and we have FCoE enabled on the adapter */ switch (vlan_get_protocol(skb)) { - case __constant_htons(ETH_P_FCOE): - case __constant_htons(ETH_P_FIP): + case htons(ETH_P_FCOE): + case htons(ETH_P_FIP): adapter = netdev_priv(dev); if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) break; default: - return __netdev_pick_tx(dev, skb); + return fallback(dev, skb); } f = &adapter->ring_feature[RING_F_FCOE]; @@ -6631,9 +7138,11 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb) txq -= f->indices; return txq + f->offset; +#else + return fallback(dev, skb); +#endif } -#endif netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, struct ixgbe_adapter *adapter, struct ixgbe_ring *tx_ring) @@ -6672,7 +7181,7 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, tx_flags |= vlan_tx_tag_get(skb) << IXGBE_TX_FLAGS_VLAN_SHIFT; tx_flags |= IXGBE_TX_FLAGS_HW_VLAN; /* else if it is a SW VLAN check the next protocol and store the tag */ - } else if (protocol == __constant_htons(ETH_P_8021Q)) { + } else if (protocol == htons(ETH_P_8021Q)) { struct vlan_hdr *vhdr, _vhdr; vhdr = skb_header_pointer(skb, ETH_HLEN, sizeof(_vhdr), &_vhdr); if (!vhdr) @@ -6684,9 +7193,9 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, tx_flags |= IXGBE_TX_FLAGS_SW_VLAN; } - skb_tx_timestamp(skb); - - if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { + if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP && + !test_and_set_bit_lock(__IXGBE_PTP_TX_IN_PROGRESS, + &adapter->state))) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; tx_flags |= IXGBE_TX_FLAGS_TSTAMP; @@ -6696,6 +7205,8 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, schedule_work(&adapter->ptp_tx_work); } + skb_tx_timestamp(skb); + #ifdef CONFIG_PCI_IOV /* * Use the l2switch_enable flag - would be false if the DMA @@ -6714,8 +7225,8 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, IXGBE_TX_FLAGS_VLAN_PRIO_SHIFT; if (tx_flags & IXGBE_TX_FLAGS_SW_VLAN) { struct vlan_ethhdr *vhdr; - if (skb_header_cloned(skb) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + + if (skb_cow_head(skb, 0)) goto out_drop; vhdr = (struct vlan_ethhdr *)skb->data; vhdr->h_vlan_TCI = htons(tx_flags >> @@ -6731,7 +7242,7 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, #ifdef IXGBE_FCOE /* setup tx offload for FCoE */ - if ((protocol == __constant_htons(ETH_P_FCOE)) && + if ((protocol == htons(ETH_P_FCOE)) && (tx_ring->netdev->features & (NETIF_F_FSO | NETIF_F_FCOE_CRC))) { tso = ixgbe_fso(tx_ring, first, &hdr_len); if (tso < 0) @@ -6767,8 +7278,9 @@ out_drop: return NETDEV_TX_OK; } -static netdev_tx_t ixgbe_xmit_frame(struct sk_buff *skb, - struct net_device *netdev) +static netdev_tx_t __ixgbe_xmit_frame(struct sk_buff *skb, + struct net_device *netdev, + struct ixgbe_ring *ring) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_ring *tx_ring; @@ -6784,10 +7296,17 @@ static netdev_tx_t ixgbe_xmit_frame(struct sk_buff *skb, skb_set_tail_pointer(skb, 17); } - tx_ring = adapter->tx_ring[skb->queue_mapping]; + tx_ring = ring ? ring : adapter->tx_ring[skb->queue_mapping]; + return ixgbe_xmit_frame_ring(skb, adapter, tx_ring); } +static netdev_tx_t ixgbe_xmit_frame(struct sk_buff *skb, + struct net_device *netdev) +{ + return __ixgbe_xmit_frame(skb, netdev, NULL); +} + /** * ixgbe_set_mac - Change the Ethernet Address of the NIC * @netdev: network interface device structure @@ -6800,16 +7319,17 @@ static int ixgbe_set_mac(struct net_device *netdev, void *p) struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; struct sockaddr *addr = p; + int ret; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; + ixgbe_del_mac_filter(adapter, hw->mac.addr, VMDQ_P(0)); memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); memcpy(hw->mac.addr, addr->sa_data, netdev->addr_len); - hw->mac.ops.set_rar(hw, 0, hw->mac.addr, VMDQ_P(0), IXGBE_RAH_AV); - - return 0; + ret = ixgbe_add_mac_filter(adapter, hw->mac.addr, VMDQ_P(0)); + return ret > 0 ? 0 : ret; } static int @@ -6845,7 +7365,9 @@ static int ixgbe_ioctl(struct net_device *netdev, struct ifreq *req, int cmd) switch (cmd) { case SIOCSHWTSTAMP: - return ixgbe_ptp_hwtstamp_ioctl(adapter, req, cmd); + return ixgbe_ptp_set_ts_config(adapter, req); + case SIOCGHWTSTAMP: + return ixgbe_ptp_get_ts_config(adapter, req); default: return mdio_mii_ioctl(&adapter->hw.phy.mdio, if_mii(req), cmd); } @@ -6936,10 +7458,10 @@ static struct rtnl_link_stats64 *ixgbe_get_stats64(struct net_device *netdev, if (ring) { do { - start = u64_stats_fetch_begin_bh(&ring->syncp); + start = u64_stats_fetch_begin_irq(&ring->syncp); packets = ring->stats.packets; bytes = ring->stats.bytes; - } while (u64_stats_fetch_retry_bh(&ring->syncp, start)); + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); stats->rx_packets += packets; stats->rx_bytes += bytes; } @@ -6952,10 +7474,10 @@ static struct rtnl_link_stats64 *ixgbe_get_stats64(struct net_device *netdev, if (ring) { do { - start = u64_stats_fetch_begin_bh(&ring->syncp); + start = u64_stats_fetch_begin_irq(&ring->syncp); packets = ring->stats.packets; bytes = ring->stats.bytes; - } while (u64_stats_fetch_retry_bh(&ring->syncp, start)); + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); stats->tx_packets += packets; stats->tx_bytes += bytes; } @@ -7044,6 +7566,7 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc) { struct ixgbe_adapter *adapter = netdev_priv(dev); struct ixgbe_hw *hw = &adapter->hw; + bool pools; /* Hardware supports up to 8 traffic classes */ if (tc > adapter->dcb_cfg.num_tcs.pg_tcs || @@ -7051,6 +7574,10 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc) tc < MAX_TRAFFIC_CLASS)) return -EINVAL; + pools = (find_first_zero_bit(&adapter->fwd_bitmask, 32) > 1); + if (tc && pools && adapter->num_rx_pools > IXGBE_MAX_DCBMACVLANS) + return -EBUSY; + /* Hardware has to reinitialize queues and interrupts to * match packet buffer alignment. Unfortunately, the * hardware is not flexible enough to do this dynamically. @@ -7305,13 +7832,95 @@ static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, return ndo_dflt_bridge_getlink(skb, pid, seq, dev, mode); } +static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev) +{ + struct ixgbe_fwd_adapter *fwd_adapter = NULL; + struct ixgbe_adapter *adapter = netdev_priv(pdev); + unsigned int limit; + int pool, err; + +#ifdef CONFIG_RPS + if (vdev->num_rx_queues != vdev->num_tx_queues) { + netdev_info(pdev, "%s: Only supports a single queue count for TX and RX\n", + vdev->name); + return ERR_PTR(-EINVAL); + } +#endif + /* Check for hardware restriction on number of rx/tx queues */ + if (vdev->num_tx_queues > IXGBE_MAX_L2A_QUEUES || + vdev->num_tx_queues == IXGBE_BAD_L2A_QUEUE) { + netdev_info(pdev, + "%s: Supports RX/TX Queue counts 1,2, and 4\n", + pdev->name); + return ERR_PTR(-EINVAL); + } + + if (((adapter->flags & IXGBE_FLAG_DCB_ENABLED) && + adapter->num_rx_pools > IXGBE_MAX_DCBMACVLANS - 1) || + (adapter->num_rx_pools > IXGBE_MAX_MACVLANS)) + return ERR_PTR(-EBUSY); + + fwd_adapter = kcalloc(1, sizeof(struct ixgbe_fwd_adapter), GFP_KERNEL); + if (!fwd_adapter) + return ERR_PTR(-ENOMEM); + + pool = find_first_zero_bit(&adapter->fwd_bitmask, 32); + adapter->num_rx_pools++; + set_bit(pool, &adapter->fwd_bitmask); + limit = find_last_bit(&adapter->fwd_bitmask, 32); + + /* Enable VMDq flag so device will be set in VM mode */ + adapter->flags |= IXGBE_FLAG_VMDQ_ENABLED | IXGBE_FLAG_SRIOV_ENABLED; + adapter->ring_feature[RING_F_VMDQ].limit = limit + 1; + adapter->ring_feature[RING_F_RSS].limit = vdev->num_tx_queues; + + /* Force reinit of ring allocation with VMDQ enabled */ + err = ixgbe_setup_tc(pdev, netdev_get_num_tc(pdev)); + if (err) + goto fwd_add_err; + fwd_adapter->pool = pool; + fwd_adapter->real_adapter = adapter; + err = ixgbe_fwd_ring_up(vdev, fwd_adapter); + if (err) + goto fwd_add_err; + netif_tx_start_all_queues(vdev); + return fwd_adapter; +fwd_add_err: + /* unwind counter and free adapter struct */ + netdev_info(pdev, + "%s: dfwd hardware acceleration failed\n", vdev->name); + clear_bit(pool, &adapter->fwd_bitmask); + adapter->num_rx_pools--; + kfree(fwd_adapter); + return ERR_PTR(err); +} + +static void ixgbe_fwd_del(struct net_device *pdev, void *priv) +{ + struct ixgbe_fwd_adapter *fwd_adapter = priv; + struct ixgbe_adapter *adapter = fwd_adapter->real_adapter; + unsigned int limit; + + clear_bit(fwd_adapter->pool, &adapter->fwd_bitmask); + adapter->num_rx_pools--; + + 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); + 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, + fwd_adapter->rx_base_queue, + fwd_adapter->rx_base_queue + adapter->num_rx_queues_per_pool, + adapter->fwd_bitmask); + kfree(fwd_adapter); +} + static const struct net_device_ops ixgbe_netdev_ops = { .ndo_open = ixgbe_open, .ndo_stop = ixgbe_close, .ndo_start_xmit = ixgbe_xmit_frame, -#ifdef IXGBE_FCOE .ndo_select_queue = ixgbe_select_queue, -#endif .ndo_set_rx_mode = ixgbe_set_rx_mode, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = ixgbe_set_mac, @@ -7322,7 +7931,7 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_do_ioctl = ixgbe_ioctl, .ndo_set_vf_mac = ixgbe_ndo_set_vf_mac, .ndo_set_vf_vlan = ixgbe_ndo_set_vf_vlan, - .ndo_set_vf_tx_rate = ixgbe_ndo_set_vf_bw, + .ndo_set_vf_rate = ixgbe_ndo_set_vf_bw, .ndo_set_vf_spoofchk = ixgbe_ndo_set_vf_spoofchk, .ndo_get_vf_config = ixgbe_ndo_get_vf_config, .ndo_get_stats64 = ixgbe_get_stats64, @@ -7349,6 +7958,8 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_fdb_add = ixgbe_ndo_fdb_add, .ndo_bridge_setlink = ixgbe_ndo_bridge_setlink, .ndo_bridge_getlink = ixgbe_ndo_bridge_getlink, + .ndo_dfwd_add_station = ixgbe_fwd_add, + .ndo_dfwd_del_station = ixgbe_fwd_del, }; /** @@ -7362,19 +7973,16 @@ static const struct net_device_ops ixgbe_netdev_ops = { **/ static inline int ixgbe_enumerate_functions(struct ixgbe_adapter *adapter) { - struct ixgbe_hw *hw = &adapter->hw; struct list_head *entry; int physfns = 0; - /* Some cards can not use the generic count PCIe functions method, and - * so must be hardcoded to the correct value. + /* Some cards can not use the generic count PCIe functions method, + * because they are behind a parent switch, so we hardcode these with + * the correct number of functions. */ - switch (hw->device_id) { - case IXGBE_DEV_ID_82599_SFP_SF_QP: - case IXGBE_DEV_ID_82599_QSFP_SF_QP: + if (ixgbe_pcie_from_parent(&adapter->hw)) { physfns = 4; - break; - default: + } else { list_for_each(entry, &adapter->pdev->bus_list) { struct pci_dev *pdev = list_entry(entry, struct pci_dev, bus_list); @@ -7408,6 +8016,7 @@ int ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id, case IXGBE_DEV_ID_82599_SFP: /* Only these subdevices could supports WOL */ switch (subdevice_id) { + case IXGBE_SUBDEV_ID_82599_SFP_WOL0: case IXGBE_SUBDEV_ID_82599_560FLR: /* only support first port */ if (hw->bus.func != 0) @@ -7490,19 +8099,14 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) return err; - if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)) && - !dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64))) { + if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) { pci_using_dac = 1; } else { - err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (err) { - err = dma_set_coherent_mask(&pdev->dev, - DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "No usable DMA configuration, aborting\n"); - goto err_dma; - } + dev_err(&pdev->dev, + "No usable DMA configuration, aborting\n"); + goto err_dma; } pci_using_dac = 0; } @@ -7548,6 +8152,7 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->hw_addr = ioremap(pci_resource_start(pdev, 0), pci_resource_len(pdev, 0)); + adapter->io_addr = hw->hw_addr; if (!hw->hw_addr) { err = -EIO; goto err_ioremap; @@ -7567,6 +8172,10 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* EEPROM */ memcpy(&hw->eeprom.ops, ii->eeprom_ops, sizeof(hw->eeprom.ops)); eec = IXGBE_READ_REG(hw, IXGBE_EEC); + if (ixgbe_removed(hw->hw_addr)) { + err = -EIO; + goto err_ioremap; + } /* If EEPROM is valid (bit 8 = 1), use default otherwise use bit bang */ if (!(eec & (1 << 8))) hw->eeprom.ops.read = &ixgbe_read_eeprom_bit_bang_generic; @@ -7589,10 +8198,6 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto err_sw_init; - /* Cache if MNG FW is up so we don't have to read the REG later */ - if (hw->mac.ops.mng_fw_enabled) - hw->mng_fw_enabled = hw->mac.ops.mng_fw_enabled(hw); - /* Make it possible the adapter to be woken up via WOL */ switch (adapter->hw.mac.type) { case ixgbe_mac_82599EB: @@ -7639,8 +8244,8 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Mailbox */ ixgbe_init_mbx_params_pf(hw); memcpy(&hw->mbx.ops, ii->mbx_ops, sizeof(hw->mbx.ops)); + pci_sriov_set_totalvfs(pdev, IXGBE_MAX_VFS_DRV_LIMIT); ixgbe_enable_sriov(adapter); - pci_sriov_set_totalvfs(pdev, 63); skip_sriov: #endif @@ -7655,7 +8260,7 @@ skip_sriov: NETIF_F_RXHASH | NETIF_F_RXCSUM; - netdev->hw_features = netdev->features; + netdev->hw_features = netdev->features | NETIF_F_HW_L2FW_DOFFLOAD; switch (adapter->hw.mac.type) { case ixgbe_mac_82599EB: @@ -7730,10 +8335,17 @@ skip_sriov: goto err_sw_init; } + ixgbe_mac_set_default_filter(adapter, hw->mac.perm_addr); + setup_timer(&adapter->service_timer, &ixgbe_service_timer, (unsigned long) adapter); + if (ixgbe_removed(hw->hw_addr)) { + err = -EIO; + goto err_sw_init; + } INIT_WORK(&adapter->service_task, ixgbe_service_task); + set_bit(__IXGBE_SERVICE_INITED, &adapter->state); clear_bit(__IXGBE_SERVICE_SCHED, &adapter->state); err = ixgbe_init_interrupt_scheme(adapter); @@ -7759,29 +8371,6 @@ skip_sriov: if (ixgbe_pcie_from_parent(hw)) ixgbe_get_parent_bus_info(adapter); - /* print bus type/speed/width info */ - e_dev_info("(PCI Express:%s:%s) %pM\n", - (hw->bus.speed == ixgbe_bus_speed_8000 ? "8.0GT/s" : - hw->bus.speed == ixgbe_bus_speed_5000 ? "5.0GT/s" : - hw->bus.speed == ixgbe_bus_speed_2500 ? "2.5GT/s" : - "Unknown"), - (hw->bus.width == ixgbe_bus_width_pcie_x8 ? "Width x8" : - hw->bus.width == ixgbe_bus_width_pcie_x4 ? "Width x4" : - hw->bus.width == ixgbe_bus_width_pcie_x1 ? "Width x1" : - "Unknown"), - netdev->dev_addr); - - err = ixgbe_read_pba_string_generic(hw, part_str, IXGBE_PBANUM_LENGTH); - if (err) - strncpy(part_str, "Unknown", IXGBE_PBANUM_LENGTH); - if (ixgbe_is_sfp(hw) && hw->phy.sfp_type != ixgbe_sfp_type_not_present) - e_dev_info("MAC: %d, PHY: %d, SFP+: %d, PBA No: %s\n", - hw->mac.type, hw->phy.type, hw->phy.sfp_type, - part_str); - else - e_dev_info("MAC: %d, PHY: %d, PBA No: %s\n", - hw->mac.type, hw->phy.type, part_str); - /* calculate the expected PCIe bandwidth required for optimal * performance. Note that some older parts will never have enough * bandwidth due to being older generation PCIe parts. We clamp these @@ -7797,6 +8386,19 @@ skip_sriov: } ixgbe_check_minimum_link(adapter, expected_gts); + err = ixgbe_read_pba_string_generic(hw, part_str, IXGBE_PBANUM_LENGTH); + if (err) + strncpy(part_str, "Unknown", IXGBE_PBANUM_LENGTH); + if (ixgbe_is_sfp(hw) && hw->phy.sfp_type != ixgbe_sfp_type_not_present) + e_dev_info("MAC: %d, PHY: %d, SFP+: %d, PBA No: %s\n", + hw->mac.type, hw->phy.type, hw->phy.sfp_type, + part_str); + else + e_dev_info("MAC: %d, PHY: %d, PBA No: %s\n", + hw->mac.type, hw->phy.type, part_str); + + e_dev_info("%pM\n", netdev->dev_addr); + /* reset the hardware with the new settings */ err = hw->mac.ops.start_hw(hw); if (err == IXGBE_ERR_EEPROM_VERSION) { @@ -7852,8 +8454,8 @@ skip_sriov: ixgbe_dbg_adapter_init(adapter); - /* Need link setup for MNG FW, else wait for IXGBE_UP */ - if (hw->mng_fw_enabled && hw->mac.ops.setup_link) + /* setup link for SFP devices with MNG FW, else wait for IXGBE_UP */ + if (ixgbe_mng_enabled(hw) && ixgbe_is_sfp(hw) && hw->mac.ops.setup_link) hw->mac.ops.setup_link(hw, IXGBE_LINK_SPEED_10GB_FULL | IXGBE_LINK_SPEED_1GB_FULL, true); @@ -7866,7 +8468,8 @@ err_register: err_sw_init: ixgbe_disable_sriov(adapter); adapter->flags2 &= ~IXGBE_FLAG2_SEARCH_FOR_SFP; - iounmap(hw->hw_addr); + iounmap(adapter->io_addr); + kfree(adapter->mac_table); err_ioremap: free_netdev(netdev); err_alloc_etherdev: @@ -7874,7 +8477,8 @@ err_alloc_etherdev: pci_select_bars(pdev, IORESOURCE_MEM)); err_pci_reg: err_dma: - pci_disable_device(pdev); + if (!test_and_set_bit(__IXGBE_DISABLED, &adapter->state)) + pci_disable_device(pdev); return err; } @@ -7894,7 +8498,7 @@ static void ixgbe_remove(struct pci_dev *pdev) ixgbe_dbg_adapter_exit(adapter); - set_bit(__IXGBE_DOWN, &adapter->state); + set_bit(__IXGBE_REMOVING, &adapter->state); cancel_work_sync(&adapter->service_task); @@ -7933,17 +8537,19 @@ static void ixgbe_remove(struct pci_dev *pdev) kfree(adapter->ixgbe_ieee_ets); #endif - iounmap(adapter->hw.hw_addr); + iounmap(adapter->io_addr); pci_release_selected_regions(pdev, pci_select_bars(pdev, IORESOURCE_MEM)); e_dev_info("complete\n"); + kfree(adapter->mac_table); free_netdev(netdev); pci_disable_pcie_error_reporting(pdev); - pci_disable_device(pdev); + if (!test_and_set_bit(__IXGBE_DISABLED, &adapter->state)) + pci_disable_device(pdev); } /** @@ -7961,6 +8567,7 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev, struct net_device *netdev = adapter->netdev; #ifdef CONFIG_PCI_IOV + struct ixgbe_hw *hw = &adapter->hw; struct pci_dev *bdev, *vfdev; u32 dw0, dw1, dw2, dw3; int vf, pos; @@ -7981,10 +8588,12 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev, if (!pos) goto skip_bad_vf_detection; - pci_read_config_dword(bdev, pos + PCI_ERR_HEADER_LOG, &dw0); - pci_read_config_dword(bdev, pos + PCI_ERR_HEADER_LOG + 4, &dw1); - pci_read_config_dword(bdev, pos + PCI_ERR_HEADER_LOG + 8, &dw2); - pci_read_config_dword(bdev, pos + PCI_ERR_HEADER_LOG + 12, &dw3); + dw0 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG); + dw1 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG + 4); + dw2 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG + 8); + dw3 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG + 12); + if (ixgbe_removed(hw->hw_addr)) + goto skip_bad_vf_detection; req_id = dw1 >> 16; /* On the 82599 if bit 7 of the requestor ID is set then it's a VF */ @@ -8047,14 +8656,23 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev, skip_bad_vf_detection: #endif /* CONFIG_PCI_IOV */ + if (!test_bit(__IXGBE_SERVICE_INITED, &adapter->state)) + return PCI_ERS_RESULT_DISCONNECT; + + rtnl_lock(); netif_device_detach(netdev); - if (state == pci_channel_io_perm_failure) + if (state == pci_channel_io_perm_failure) { + rtnl_unlock(); return PCI_ERS_RESULT_DISCONNECT; + } if (netif_running(netdev)) ixgbe_down(adapter); - pci_disable_device(pdev); + + if (!test_and_set_bit(__IXGBE_DISABLED, &adapter->state)) + pci_disable_device(pdev); + rtnl_unlock(); /* Request a slot reset. */ return PCI_ERS_RESULT_NEED_RESET; @@ -8076,6 +8694,9 @@ static pci_ers_result_t ixgbe_io_slot_reset(struct pci_dev *pdev) e_err(probe, "Cannot re-enable PCI device after reset.\n"); result = PCI_ERS_RESULT_DISCONNECT; } else { + smp_mb__before_atomic(); + clear_bit(__IXGBE_DISABLED, &adapter->state); + adapter->hw.hw_addr = adapter->io_addr; pci_set_master(pdev); pci_restore_state(pdev); pci_save_state(pdev); |