diff options
Diffstat (limited to 'drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c')
| -rw-r--r-- | drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c | 874 |
1 files changed, 599 insertions, 275 deletions
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index dce48bf64d9..16b3a1cd9db 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2013 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 @@ -35,7 +36,7 @@ #include <linux/ip.h> #include <linux/tcp.h> #include <linux/ipv6.h> -#ifdef NETIF_F_HW_VLAN_TX +#ifdef NETIF_F_HW_VLAN_CTAG_TX #include <linux/if_vlan.h> #endif @@ -44,50 +45,11 @@ #include "ixgbe_sriov.h" #ifdef CONFIG_PCI_IOV -void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, - const struct ixgbe_info *ii) +static int __ixgbe_enable_sriov(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; int num_vf_macvlans, i; struct vf_macvlans *mv_list; - int pre_existing_vfs = 0; - - pre_existing_vfs = pci_num_vf(adapter->pdev); - if (!pre_existing_vfs && !adapter->num_vfs) - return; - - /* If there are pre-existing VFs then we have to force - * use of that many because they were not deleted the last - * time someone removed the PF driver. That would have - * been because they were allocated to guest VMs and can't - * be removed. Go ahead and just re-enable the old amount. - * If the user wants to change the number of VFs they can - * use ethtool while making sure no VFs are allocated to - * guest VMs... i.e. the right way. - */ - if (pre_existing_vfs) { - adapter->num_vfs = pre_existing_vfs; - dev_warn(&adapter->pdev->dev, "Virtual Functions already " - "enabled for this device - Please reload all " - "VF drivers to avoid spoofed packet errors\n"); - } else { - int err; - /* - * The 82599 supports up to 64 VFs per physical function - * but this implementation limits allocation to 63 so that - * basic networking resources are still available to the - * physical function. If the user requests greater thn - * 63 VFs then it is an error - reset to default of zero. - */ - adapter->num_vfs = min_t(unsigned int, adapter->num_vfs, 63); - - err = pci_enable_sriov(adapter->pdev, adapter->num_vfs); - if (err) { - e_err(probe, "Failed to enable PCI sriov: %d\n", err); - adapter->num_vfs = 0; - return; - } - } adapter->flags |= IXGBE_FLAG_SRIOV_ENABLED; e_info(probe, "SR-IOV enabled with %d VFs\n", adapter->num_vfs); @@ -110,13 +72,15 @@ void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, for (i = 0; i < num_vf_macvlans; i++) { mv_list->vf = -1; mv_list->free = true; - mv_list->rar_entry = hw->mac.num_rar_entries - - (i + adapter->num_vfs + 1); list_add(&mv_list->l, &adapter->vf_mvs.l); mv_list++; } } + /* Initialize default switching mode VEB */ + IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, IXGBE_PFDTXGSWC_VT_LBEN); + adapter->flags2 |= IXGBE_FLAG2_BRIDGE_MODE_VEB; + /* If call to enable VFs succeeded then allocate memory * for per VF control structures. */ @@ -124,12 +88,6 @@ void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, kcalloc(adapter->num_vfs, sizeof(struct vf_data_storage), GFP_KERNEL); if (adapter->vfinfo) { - /* Now that we're sure SR-IOV is enabled - * and memory allocated set up the mailbox parameters - */ - ixgbe_init_mbx_params_pf(hw); - memcpy(&hw->mbx.ops, ii->mbx_ops, sizeof(hw->mbx.ops)); - /* limit trafffic classes based on VFs enabled */ if ((adapter->hw.mac.type == ixgbe_mac_82599EB) && (adapter->num_vfs < 16)) { @@ -150,67 +108,73 @@ void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, adapter->flags2 &= ~(IXGBE_FLAG2_RSC_CAPABLE | IXGBE_FLAG2_RSC_ENABLED); -#ifdef IXGBE_FCOE - /* - * When SR-IOV is enabled 82599 cannot support jumbo frames - * so we must disable FCoE because we cannot support FCoE MTU. - */ - if (adapter->hw.mac.type == ixgbe_mac_82599EB) - adapter->flags &= ~(IXGBE_FLAG_FCOE_ENABLED | - IXGBE_FLAG_FCOE_CAPABLE); -#endif - /* enable spoof checking for all VFs */ for (i = 0; i < adapter->num_vfs; i++) adapter->vfinfo[i].spoofchk_enabled = true; - return; + return 0; } - /* Oh oh */ - e_err(probe, "Unable to allocate memory for VF Data Storage - " - "SRIOV disabled\n"); - ixgbe_disable_sriov(adapter); + return -ENOMEM; } -static bool ixgbe_vfs_are_assigned(struct ixgbe_adapter *adapter) +/* Note this function is called when the user wants to enable SR-IOV + * VFs using the now deprecated module parameter + */ +void ixgbe_enable_sriov(struct ixgbe_adapter *adapter) { - struct pci_dev *pdev = adapter->pdev; - struct pci_dev *vfdev; - int dev_id; + int pre_existing_vfs = 0; - switch (adapter->hw.mac.type) { - case ixgbe_mac_82599EB: - dev_id = IXGBE_DEV_ID_82599_VF; - break; - case ixgbe_mac_X540: - dev_id = IXGBE_DEV_ID_X540_VF; - break; - default: - return false; - } + pre_existing_vfs = pci_num_vf(adapter->pdev); + if (!pre_existing_vfs && !adapter->num_vfs) + return; - /* loop through all the VFs to see if we own any that are assigned */ - vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, dev_id, NULL); - while (vfdev) { - /* if we don't own it we don't care */ - if (vfdev->is_virtfn && vfdev->physfn == pdev) { - /* if it is assigned we cannot release it */ - if (vfdev->dev_flags & PCI_DEV_FLAGS_ASSIGNED) - return true; - } + /* If there are pre-existing VFs then we have to force + * use of that many - over ride any module parameter value. + * This may result from the user unloading the PF driver + * while VFs were assigned to guest VMs or because the VFs + * have been created via the new PCI SR-IOV sysfs interface. + */ + if (pre_existing_vfs) { + adapter->num_vfs = pre_existing_vfs; + dev_warn(&adapter->pdev->dev, + "Virtual Functions already enabled for this device - Please reload all VF drivers to avoid spoofed packet errors\n"); + } else { + int err; + /* + * The 82599 supports up to 64 VFs per physical function + * but this implementation limits allocation to 63 so that + * basic networking resources are still available to the + * physical function. If the user requests greater thn + * 63 VFs then it is an error - reset to default of zero. + */ + adapter->num_vfs = min_t(unsigned int, adapter->num_vfs, IXGBE_MAX_VFS_DRV_LIMIT); - vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, dev_id, vfdev); + err = pci_enable_sriov(adapter->pdev, adapter->num_vfs); + if (err) { + e_err(probe, "Failed to enable PCI sriov: %d\n", err); + adapter->num_vfs = 0; + return; + } } - return false; + if (!__ixgbe_enable_sriov(adapter)) + return; + + /* If we have gotten to this point then there is no memory available + * to manage the VF devices - print message and bail. + */ + e_err(probe, "Unable to allocate memory for VF Data Storage - " + "SRIOV disabled\n"); + ixgbe_disable_sriov(adapter); } #endif /* #ifdef CONFIG_PCI_IOV */ -void ixgbe_disable_sriov(struct ixgbe_adapter *adapter) +int ixgbe_disable_sriov(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; u32 gpie; u32 vmdctl; + int rss; /* set num VFs to 0 to prevent access to vfinfo */ adapter->num_vfs = 0; @@ -225,7 +189,7 @@ void ixgbe_disable_sriov(struct ixgbe_adapter *adapter) /* if SR-IOV is already disabled then there is nothing to do */ if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) - return; + return 0; #ifdef CONFIG_PCI_IOV /* @@ -233,9 +197,9 @@ void ixgbe_disable_sriov(struct ixgbe_adapter *adapter) * without causing issues, so just leave the hardware * available but disabled */ - if (ixgbe_vfs_are_assigned(adapter)) { + if (pci_vfs_assigned(adapter->pdev)) { e_dev_warn("Unloading driver while VFs are assigned - VFs will not be deallocated\n"); - return; + return -EPERM; } /* disable iov and allow time for transactions to clear */ pci_disable_sriov(adapter->pdev); @@ -254,25 +218,114 @@ void ixgbe_disable_sriov(struct ixgbe_adapter *adapter) IXGBE_WRITE_FLUSH(hw); /* Disable VMDq flag so device will be set in VM mode */ - if (adapter->ring_feature[RING_F_VMDQ].limit == 1) + if (adapter->ring_feature[RING_F_VMDQ].limit == 1) { adapter->flags &= ~IXGBE_FLAG_VMDQ_ENABLED; + adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED; + rss = min_t(int, IXGBE_MAX_RSS_INDICES, num_online_cpus()); + } else { + rss = min_t(int, IXGBE_MAX_L2A_QUEUES, num_online_cpus()); + } + adapter->ring_feature[RING_F_VMDQ].offset = 0; + adapter->ring_feature[RING_F_RSS].limit = rss; /* take a breather then clean up driver data */ msleep(100); + return 0; +} + +static int ixgbe_pci_sriov_enable(struct pci_dev *dev, int num_vfs) +{ +#ifdef CONFIG_PCI_IOV + struct ixgbe_adapter *adapter = pci_get_drvdata(dev); + int err = 0; + int i; + int pre_existing_vfs = pci_num_vf(dev); + + if (pre_existing_vfs && pre_existing_vfs != num_vfs) + err = ixgbe_disable_sriov(adapter); + else if (pre_existing_vfs && pre_existing_vfs == num_vfs) + goto out; + + if (err) + goto err_out; + + /* While the SR-IOV capability structure reports total VFs to be + * 64 we limit the actual number that can be allocated to 63 so + * that some transmit/receive resources can be reserved to the + * PF. The PCI bus driver already checks for other values out of + * range. + */ + if (num_vfs > IXGBE_MAX_VFS_DRV_LIMIT) { + err = -EPERM; + goto err_out; + } + + adapter->num_vfs = num_vfs; + + err = __ixgbe_enable_sriov(adapter); + if (err) + goto err_out; + + for (i = 0; i < adapter->num_vfs; i++) + ixgbe_vf_configuration(dev, (i | 0x10000000)); + + err = pci_enable_sriov(dev, num_vfs); + if (err) { + e_dev_warn("Failed to enable PCI sriov: %d\n", err); + goto err_out; + } + ixgbe_sriov_reinit(adapter); + +out: + return num_vfs; + +err_out: + return err; +#endif + return 0; +} + +static int ixgbe_pci_sriov_disable(struct pci_dev *dev) +{ + struct ixgbe_adapter *adapter = pci_get_drvdata(dev); + int err; +#ifdef CONFIG_PCI_IOV + u32 current_flags = adapter->flags; +#endif + + err = ixgbe_disable_sriov(adapter); + + /* Only reinit if no error and state changed */ +#ifdef CONFIG_PCI_IOV + if (!err && current_flags != adapter->flags) + ixgbe_sriov_reinit(adapter); +#endif + + return err; +} - adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED; +int ixgbe_pci_sriov_configure(struct pci_dev *dev, int num_vfs) +{ + if (num_vfs == 0) + return ixgbe_pci_sriov_disable(dev); + else + return ixgbe_pci_sriov_enable(dev, num_vfs); } static int ixgbe_set_vf_multicasts(struct ixgbe_adapter *adapter, - int entries, u16 *hash_list, u32 vf) + u32 *msgbuf, u32 vf) { + int entries = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) + >> IXGBE_VT_MSGINFO_SHIFT; + u16 *hash_list = (u16 *)&msgbuf[1]; struct vf_data_storage *vfinfo = &adapter->vfinfo[vf]; struct ixgbe_hw *hw = &adapter->hw; int i; u32 vector_bit; u32 vector_reg; u32 mta_reg; + u32 vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(vf)); /* only so many hash values supported */ entries = min(entries, IXGBE_MAX_VF_MC_ENTRIES); @@ -299,25 +352,13 @@ static int ixgbe_set_vf_multicasts(struct ixgbe_adapter *adapter, mta_reg |= (1 << vector_bit); IXGBE_WRITE_REG(hw, IXGBE_MTA(vector_reg), mta_reg); } + vmolr |= IXGBE_VMOLR_ROMPE; + IXGBE_WRITE_REG(hw, IXGBE_VMOLR(vf), vmolr); return 0; } -static void ixgbe_restore_vf_macvlans(struct ixgbe_adapter *adapter) -{ - struct ixgbe_hw *hw = &adapter->hw; - struct list_head *pos; - struct vf_macvlans *entry; - - list_for_each(pos, &adapter->vf_mvs.l) { - entry = list_entry(pos, struct vf_macvlans, l); - if (!entry->free) - hw->mac.ops.set_rar(hw, entry->rar_entry, - entry->vf_macvlan, - entry->vf, IXGBE_RAH_AV); - } -} - +#ifdef CONFIG_PCI_IOV void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; @@ -328,6 +369,7 @@ void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter) u32 mta_reg; for (i = 0; i < adapter->num_vfs; i++) { + u32 vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(i)); vfinfo = &adapter->vfinfo[i]; for (j = 0; j < vfinfo->num_vf_mc_hashes; j++) { hw->addr_ctrl.mta_in_use++; @@ -337,11 +379,18 @@ void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter) mta_reg |= (1 << vector_bit); IXGBE_WRITE_REG(hw, IXGBE_MTA(vector_reg), mta_reg); } + + if (vfinfo->num_vf_mc_hashes) + vmolr |= IXGBE_VMOLR_ROMPE; + else + vmolr &= ~IXGBE_VMOLR_ROMPE; + IXGBE_WRITE_REG(hw, IXGBE_VMOLR(i), vmolr); } /* Restore any VF macvlans */ - ixgbe_restore_vf_macvlans(adapter); + ixgbe_full_sync_mac_table(adapter); } +#endif static int ixgbe_set_vf_vlan(struct ixgbe_adapter *adapter, int add, int vid, u32 vf) @@ -353,38 +402,95 @@ static int ixgbe_set_vf_vlan(struct ixgbe_adapter *adapter, int add, int vid, return adapter->hw.mac.ops.set_vfta(&adapter->hw, vid, vf, (bool)add); } -static void ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 *msgbuf) +static s32 ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) { struct ixgbe_hw *hw = &adapter->hw; - int new_mtu = msgbuf[1]; + int max_frame = msgbuf[1]; u32 max_frs; - int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN; - /* Only X540 supports jumbo frames in IOV mode */ - if (adapter->hw.mac.type != ixgbe_mac_X540) - return; + /* + * For 82599EB we have to keep all PFs and VFs operating with + * the same max_frame value in order to avoid sending an oversize + * frame to a VF. In order to guarantee this is handled correctly + * for all cases we have several special exceptions to take into + * account before we can enable the VF for receive + */ + if (adapter->hw.mac.type == ixgbe_mac_82599EB) { + struct net_device *dev = adapter->netdev; + int pf_max_frame = dev->mtu + ETH_HLEN; + u32 reg_offset, vf_shift, vfre; + s32 err = 0; + +#ifdef CONFIG_FCOE + if (dev->features & NETIF_F_FCOE_MTU) + pf_max_frame = max_t(int, pf_max_frame, + IXGBE_FCOE_JUMBO_FRAME_SIZE); + +#endif /* CONFIG_FCOE */ + switch (adapter->vfinfo[vf].vf_api) { + case ixgbe_mbox_api_11: + /* + * Version 1.1 supports jumbo frames on VFs if PF has + * jumbo frames enabled which means legacy VFs are + * disabled + */ + if (pf_max_frame > ETH_FRAME_LEN) + break; + default: + /* + * If the PF or VF are running w/ jumbo frames enabled + * we need to shut down the VF Rx path as we cannot + * support jumbo frames on legacy VFs + */ + if ((pf_max_frame > ETH_FRAME_LEN) || + (max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN))) + err = -EINVAL; + break; + } + + /* determine VF receive enable location */ + vf_shift = vf % 32; + reg_offset = vf / 32; + + /* enable or disable receive depending on error */ + vfre = IXGBE_READ_REG(hw, IXGBE_VFRE(reg_offset)); + if (err) + vfre &= ~(1 << vf_shift); + else + vfre |= 1 << vf_shift; + IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset), vfre); + + if (err) { + e_err(drv, "VF max_frame %d out of range\n", max_frame); + return err; + } + } /* MTU < 68 is an error and causes problems on some kernels */ - if ((new_mtu < 68) || (max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE)) { - e_err(drv, "VF mtu %d out of range\n", new_mtu); - return; + if (max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE) { + e_err(drv, "VF max_frame %d out of range\n", max_frame); + return -EINVAL; } - max_frs = (IXGBE_READ_REG(hw, IXGBE_MAXFRS) & - IXGBE_MHADD_MFS_MASK) >> IXGBE_MHADD_MFS_SHIFT; - if (max_frs < new_mtu) { - max_frs = new_mtu << IXGBE_MHADD_MFS_SHIFT; + /* pull current max frame size from hardware */ + max_frs = IXGBE_READ_REG(hw, IXGBE_MAXFRS); + max_frs &= IXGBE_MHADD_MFS_MASK; + max_frs >>= IXGBE_MHADD_MFS_SHIFT; + + if (max_frs < max_frame) { + max_frs = max_frame << IXGBE_MHADD_MFS_SHIFT; IXGBE_WRITE_REG(hw, IXGBE_MAXFRS, max_frs); } - e_info(hw, "VF requests change max MTU to %d\n", new_mtu); + e_info(hw, "VF requests change max MTU to %d\n", max_frame); + + return 0; } static void ixgbe_set_vmolr(struct ixgbe_hw *hw, u32 vf, bool aupe) { u32 vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(vf)); - vmolr |= (IXGBE_VMOLR_ROMPE | - IXGBE_VMOLR_BAM); + vmolr |= IXGBE_VMOLR_BAM; if (aupe) vmolr |= IXGBE_VMOLR_AUPE; else @@ -392,35 +498,37 @@ static void ixgbe_set_vmolr(struct ixgbe_hw *hw, u32 vf, bool aupe) IXGBE_WRITE_REG(hw, IXGBE_VMOLR(vf), vmolr); } -static void ixgbe_set_vmvir(struct ixgbe_adapter *adapter, u32 vid, u32 vf) +static void ixgbe_clear_vmvir(struct ixgbe_adapter *adapter, u32 vf) { struct ixgbe_hw *hw = &adapter->hw; - if (vid) - IXGBE_WRITE_REG(hw, IXGBE_VMVIR(vf), - (vid | IXGBE_VMVIR_VLANA_DEFAULT)); - else - IXGBE_WRITE_REG(hw, IXGBE_VMVIR(vf), 0); + IXGBE_WRITE_REG(hw, IXGBE_VMVIR(vf), 0); } - static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf) { struct ixgbe_hw *hw = &adapter->hw; - int rar_entry = hw->mac.num_rar_entries - (vf + 1); + struct vf_data_storage *vfinfo = &adapter->vfinfo[vf]; + u8 num_tcs = netdev_get_num_tc(adapter->netdev); + + /* add PF assigned VLAN or VLAN 0 */ + ixgbe_set_vf_vlan(adapter, true, vfinfo->pf_vlan, vf); /* reset offloads to defaults */ - if (adapter->vfinfo[vf].pf_vlan) { - ixgbe_set_vf_vlan(adapter, true, - adapter->vfinfo[vf].pf_vlan, vf); - ixgbe_set_vmvir(adapter, - (adapter->vfinfo[vf].pf_vlan | - (adapter->vfinfo[vf].pf_qos << - VLAN_PRIO_SHIFT)), vf); - ixgbe_set_vmolr(hw, vf, false); + ixgbe_set_vmolr(hw, vf, !vfinfo->pf_vlan); + + /* set outgoing tags for VFs */ + if (!vfinfo->pf_vlan && !vfinfo->pf_qos && !num_tcs) { + ixgbe_clear_vmvir(adapter, vf); } else { - ixgbe_set_vf_vlan(adapter, true, 0, vf); - ixgbe_set_vmvir(adapter, 0, vf); - ixgbe_set_vmolr(hw, vf, true); + if (vfinfo->pf_qos || !num_tcs) + ixgbe_set_vmvir(adapter, vfinfo->pf_vlan, + vfinfo->pf_qos, vf); + else + ixgbe_set_vmvir(adapter, vfinfo->pf_vlan, + adapter->default_up, vf); + + if (vfinfo->spoofchk_enabled) + hw->mac.ops.set_vlan_anti_spoofing(hw, true, vf); } /* reset multicast table array for vf */ @@ -429,17 +537,18 @@ static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf) /* Flush and reset the mta with the new values */ ixgbe_set_rx_mode(adapter->netdev); - hw->mac.ops.clear_rar(hw, rar_entry); + ixgbe_del_mac_filter(adapter, adapter->vfinfo[vf].vf_mac_addresses, vf); + + /* reset VF api back to unknown */ + adapter->vfinfo[vf].vf_api = ixgbe_mbox_api_10; } static int ixgbe_set_vf_mac(struct ixgbe_adapter *adapter, int vf, unsigned char *mac_addr) { - struct ixgbe_hw *hw = &adapter->hw; - int rar_entry = hw->mac.num_rar_entries - (vf + 1); - - memcpy(adapter->vfinfo[vf].vf_mac_addresses, mac_addr, 6); - hw->mac.ops.set_rar(hw, rar_entry, mac_addr, vf, IXGBE_RAH_AV); + ixgbe_del_mac_filter(adapter, adapter->vfinfo[vf].vf_mac_addresses, vf); + memcpy(adapter->vfinfo[vf].vf_mac_addresses, mac_addr, ETH_ALEN); + ixgbe_add_mac_filter(adapter, adapter->vfinfo[vf].vf_mac_addresses, vf); return 0; } @@ -447,7 +556,6 @@ static int ixgbe_set_vf_mac(struct ixgbe_adapter *adapter, static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter, int vf, int index, unsigned char *mac_addr) { - struct ixgbe_hw *hw = &adapter->hw; struct list_head *pos; struct vf_macvlans *entry; @@ -458,7 +566,8 @@ static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter, entry->vf = -1; entry->free = true; entry->is_macvlan = false; - hw->mac.ops.clear_rar(hw, entry->rar_entry); + ixgbe_del_mac_filter(adapter, + entry->vf_macvlan, vf); } } } @@ -494,57 +603,336 @@ static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter, entry->vf = vf; memcpy(entry->vf_macvlan, mac_addr, ETH_ALEN); - hw->mac.ops.set_rar(hw, entry->rar_entry, mac_addr, vf, IXGBE_RAH_AV); + ixgbe_add_mac_filter(adapter, mac_addr, vf); return 0; } int ixgbe_vf_configuration(struct pci_dev *pdev, unsigned int event_mask) { - unsigned char vf_mac_addr[6]; struct ixgbe_adapter *adapter = pci_get_drvdata(pdev); unsigned int vfn = (event_mask & 0x3f); bool enable = ((event_mask & 0x10000000U) != 0); - if (enable) { - eth_random_addr(vf_mac_addr); - e_info(probe, "IOV: VF %d is enabled MAC %pM\n", - vfn, vf_mac_addr); - /* - * Store away the VF "permananet" MAC address, it will ask - * for it later. - */ - memcpy(adapter->vfinfo[vfn].vf_mac_addresses, vf_mac_addr, 6); - } + if (enable) + eth_zero_addr(adapter->vfinfo[vfn].vf_mac_addresses); return 0; } -static inline void ixgbe_vf_reset_msg(struct ixgbe_adapter *adapter, u32 vf) +static int ixgbe_vf_reset_msg(struct ixgbe_adapter *adapter, u32 vf) { + struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ]; struct ixgbe_hw *hw = &adapter->hw; - u32 reg; - u32 reg_offset, vf_shift; + unsigned char *vf_mac = adapter->vfinfo[vf].vf_mac_addresses; + u32 reg, reg_offset, vf_shift; + u32 msgbuf[4] = {0, 0, 0, 0}; + u8 *addr = (u8 *)(&msgbuf[1]); + u32 q_per_pool = __ALIGN_MASK(1, ~vmdq->mask); + int i; + + e_info(probe, "VF Reset msg received from vf %d\n", vf); + + /* reset the filters for the device */ + ixgbe_vf_reset_event(adapter, vf); + + /* set vf mac address */ + if (!is_zero_ether_addr(vf_mac)) + ixgbe_set_vf_mac(adapter, vf, vf_mac); vf_shift = vf % 32; reg_offset = vf / 32; - /* enable transmit and receive for vf */ + /* enable transmit for vf */ reg = IXGBE_READ_REG(hw, IXGBE_VFTE(reg_offset)); - reg |= (reg | (1 << vf_shift)); + reg |= 1 << vf_shift; IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset), reg); + /* force drop enable for all VF Rx queues */ + for (i = vf * q_per_pool; i < ((vf + 1) * q_per_pool); i++) { + /* flush previous write */ + IXGBE_WRITE_FLUSH(hw); + + /* indicate to hardware that we want to set drop enable */ + reg = IXGBE_QDE_WRITE | IXGBE_QDE_ENABLE; + reg |= i << IXGBE_QDE_IDX_SHIFT; + IXGBE_WRITE_REG(hw, IXGBE_QDE, reg); + } + + /* enable receive for vf */ reg = IXGBE_READ_REG(hw, IXGBE_VFRE(reg_offset)); - reg |= (reg | (1 << vf_shift)); + reg |= 1 << vf_shift; + /* + * The 82599 cannot support a mix of jumbo and non-jumbo PF/VFs. + * For more info take a look at ixgbe_set_vf_lpe + */ + if (adapter->hw.mac.type == ixgbe_mac_82599EB) { + struct net_device *dev = adapter->netdev; + int pf_max_frame = dev->mtu + ETH_HLEN; + +#ifdef CONFIG_FCOE + if (dev->features & NETIF_F_FCOE_MTU) + pf_max_frame = max_t(int, pf_max_frame, + IXGBE_FCOE_JUMBO_FRAME_SIZE); + +#endif /* CONFIG_FCOE */ + if (pf_max_frame > ETH_FRAME_LEN) + reg &= ~(1 << vf_shift); + } IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset), reg); + /* enable VF mailbox for further messages */ + adapter->vfinfo[vf].clear_to_send = true; + /* Enable counting of spoofed packets in the SSVPC register */ reg = IXGBE_READ_REG(hw, IXGBE_VMECM(reg_offset)); reg |= (1 << vf_shift); IXGBE_WRITE_REG(hw, IXGBE_VMECM(reg_offset), reg); - ixgbe_vf_reset_event(adapter, vf); + /* + * Reset the VFs TDWBAL and TDWBAH registers + * which are not cleared by an FLR + */ + for (i = 0; i < q_per_pool; i++) { + IXGBE_WRITE_REG(hw, IXGBE_PVFTDWBAHn(q_per_pool, vf, i), 0); + IXGBE_WRITE_REG(hw, IXGBE_PVFTDWBALn(q_per_pool, vf, i), 0); + } + + /* reply to reset with ack and vf mac address */ + msgbuf[0] = IXGBE_VF_RESET; + if (!is_zero_ether_addr(vf_mac)) { + msgbuf[0] |= IXGBE_VT_MSGTYPE_ACK; + memcpy(addr, vf_mac, ETH_ALEN); + } else { + msgbuf[0] |= IXGBE_VT_MSGTYPE_NACK; + dev_warn(&adapter->pdev->dev, + "VF %d has no MAC address assigned, you may have to assign one manually\n", + vf); + } + + /* + * Piggyback the multicast filter type so VF can compute the + * correct vectors + */ + msgbuf[3] = hw->mac.mc_filter_type; + ixgbe_write_mbx(hw, msgbuf, IXGBE_VF_PERMADDR_MSG_LEN, vf); + + return 0; +} + +static int ixgbe_set_vf_mac_addr(struct ixgbe_adapter *adapter, + u32 *msgbuf, u32 vf) +{ + u8 *new_mac = ((u8 *)(&msgbuf[1])); + + if (!is_valid_ether_addr(new_mac)) { + e_warn(drv, "VF %d attempted to set invalid mac\n", vf); + return -1; + } + + if (adapter->vfinfo[vf].pf_set_mac && + !ether_addr_equal(adapter->vfinfo[vf].vf_mac_addresses, new_mac)) { + e_warn(drv, + "VF %d attempted to override administratively set MAC address\n" + "Reload the VF driver to resume operations\n", + vf); + return -1; + } + + return ixgbe_set_vf_mac(adapter, vf, new_mac) < 0; +} + +static int ixgbe_find_vlvf_entry(struct ixgbe_hw *hw, u32 vlan) +{ + u32 vlvf; + s32 regindex; + + /* short cut the special case */ + if (vlan == 0) + return 0; + + /* Search for the vlan id in the VLVF entries */ + for (regindex = 1; regindex < IXGBE_VLVF_ENTRIES; regindex++) { + vlvf = IXGBE_READ_REG(hw, IXGBE_VLVF(regindex)); + if ((vlvf & VLAN_VID_MASK) == vlan) + break; + } + + /* Return a negative value if not found */ + if (regindex >= IXGBE_VLVF_ENTRIES) + regindex = -1; + + return regindex; +} + +static int ixgbe_set_vf_vlan_msg(struct ixgbe_adapter *adapter, + u32 *msgbuf, u32 vf) +{ + struct ixgbe_hw *hw = &adapter->hw; + int add = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) >> IXGBE_VT_MSGINFO_SHIFT; + int vid = (msgbuf[1] & IXGBE_VLVF_VLANID_MASK); + int err; + s32 reg_ndx; + u32 vlvf; + u32 bits; + u8 tcs = netdev_get_num_tc(adapter->netdev); + + if (adapter->vfinfo[vf].pf_vlan || tcs) { + e_warn(drv, + "VF %d attempted to override administratively set VLAN configuration\n" + "Reload the VF driver to resume operations\n", + vf); + return -1; + } + + if (add) + adapter->vfinfo[vf].vlan_count++; + else if (adapter->vfinfo[vf].vlan_count) + adapter->vfinfo[vf].vlan_count--; + + /* in case of promiscuous mode any VLAN filter set for a VF must + * also have the PF pool added to it. + */ + if (add && adapter->netdev->flags & IFF_PROMISC) + err = ixgbe_set_vf_vlan(adapter, add, vid, VMDQ_P(0)); + + err = ixgbe_set_vf_vlan(adapter, add, vid, vf); + if (!err && adapter->vfinfo[vf].spoofchk_enabled) + hw->mac.ops.set_vlan_anti_spoofing(hw, true, vf); + + /* Go through all the checks to see if the VLAN filter should + * be wiped completely. + */ + if (!add && adapter->netdev->flags & IFF_PROMISC) { + reg_ndx = ixgbe_find_vlvf_entry(hw, vid); + if (reg_ndx < 0) + goto out; + vlvf = IXGBE_READ_REG(hw, IXGBE_VLVF(reg_ndx)); + /* See if any other pools are set for this VLAN filter + * entry other than the PF. + */ + if (VMDQ_P(0) < 32) { + bits = IXGBE_READ_REG(hw, IXGBE_VLVFB(reg_ndx * 2)); + bits &= ~(1 << VMDQ_P(0)); + bits |= IXGBE_READ_REG(hw, + IXGBE_VLVFB(reg_ndx * 2) + 1); + } else { + bits = IXGBE_READ_REG(hw, + IXGBE_VLVFB(reg_ndx * 2) + 1); + bits &= ~(1 << (VMDQ_P(0) - 32)); + bits |= IXGBE_READ_REG(hw, IXGBE_VLVFB(reg_ndx * 2)); + } + + /* If the filter was removed then ensure PF pool bit + * is cleared if the PF only added itself to the pool + * because the PF is in promiscuous mode. + */ + if ((vlvf & VLAN_VID_MASK) == vid && + !test_bit(vid, adapter->active_vlans) && !bits) + ixgbe_set_vf_vlan(adapter, add, vid, VMDQ_P(0)); + } + +out: + + return err; +} + +static int ixgbe_set_vf_macvlan_msg(struct ixgbe_adapter *adapter, + u32 *msgbuf, u32 vf) +{ + u8 *new_mac = ((u8 *)(&msgbuf[1])); + int index = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) >> + IXGBE_VT_MSGINFO_SHIFT; + int err; + + if (adapter->vfinfo[vf].pf_set_mac && index > 0) { + e_warn(drv, + "VF %d requested MACVLAN filter but is administratively denied\n", + vf); + return -1; + } + + /* An non-zero index indicates the VF is setting a filter */ + if (index) { + if (!is_valid_ether_addr(new_mac)) { + e_warn(drv, "VF %d attempted to set invalid mac\n", vf); + return -1; + } + + /* + * If the VF is allowed to set MAC filters then turn off + * anti-spoofing to avoid false positives. + */ + if (adapter->vfinfo[vf].spoofchk_enabled) + ixgbe_ndo_set_vf_spoofchk(adapter->netdev, vf, false); + } + + err = ixgbe_set_vf_macvlan(adapter, vf, index, new_mac); + if (err == -ENOSPC) + e_warn(drv, + "VF %d has requested a MACVLAN filter but there is no space for it\n", + vf); + + return err < 0; +} + +static int ixgbe_negotiate_vf_api(struct ixgbe_adapter *adapter, + u32 *msgbuf, u32 vf) +{ + int api = msgbuf[1]; + + switch (api) { + case ixgbe_mbox_api_10: + case ixgbe_mbox_api_11: + adapter->vfinfo[vf].vf_api = api; + return 0; + default: + break; + } + + e_info(drv, "VF %d requested invalid api version %u\n", vf, api); + + return -1; +} + +static int ixgbe_get_vf_queues(struct ixgbe_adapter *adapter, + u32 *msgbuf, u32 vf) +{ + struct net_device *dev = adapter->netdev; + struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ]; + unsigned int default_tc = 0; + u8 num_tcs = netdev_get_num_tc(dev); + + /* verify the PF is supporting the correct APIs */ + switch (adapter->vfinfo[vf].vf_api) { + case ixgbe_mbox_api_20: + case ixgbe_mbox_api_11: + break; + default: + return -1; + } + + /* only allow 1 Tx queue for bandwidth limiting */ + msgbuf[IXGBE_VF_TX_QUEUES] = __ALIGN_MASK(1, ~vmdq->mask); + msgbuf[IXGBE_VF_RX_QUEUES] = __ALIGN_MASK(1, ~vmdq->mask); + + /* if TCs > 1 determine which TC belongs to default user priority */ + if (num_tcs > 1) + default_tc = netdev_get_prio_tc_map(dev, adapter->default_up); + + /* notify VF of need for VLAN tag stripping, and correct queue */ + if (num_tcs) + msgbuf[IXGBE_VF_TRANS_VLAN] = num_tcs; + else if (adapter->vfinfo[vf].pf_vlan || adapter->vfinfo[vf].pf_qos) + msgbuf[IXGBE_VF_TRANS_VLAN] = 1; + else + msgbuf[IXGBE_VF_TRANS_VLAN] = 0; + + /* notify VF of default queue */ + msgbuf[IXGBE_VF_DEF_QUEUE] = default_tc; + + return 0; } static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf) @@ -553,10 +941,6 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf) u32 msgbuf[IXGBE_VFMAILBOX_SIZE]; struct ixgbe_hw *hw = &adapter->hw; s32 retval; - int entries; - u16 *hash_list; - int add, vid, index; - u8 *new_mac; retval = ixgbe_read_mbx(hw, msgbuf, mbx_size, vf); @@ -572,39 +956,13 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf) /* flush the ack before we write any messages back */ IXGBE_WRITE_FLUSH(hw); + if (msgbuf[0] == IXGBE_VF_RESET) + return ixgbe_vf_reset_msg(adapter, vf); + /* * until the vf completes a virtual function reset it should not be * allowed to start any configuration. */ - - if (msgbuf[0] == IXGBE_VF_RESET) { - unsigned char *vf_mac = adapter->vfinfo[vf].vf_mac_addresses; - new_mac = (u8 *)(&msgbuf[1]); - e_info(probe, "VF Reset msg received from vf %d\n", vf); - adapter->vfinfo[vf].clear_to_send = false; - ixgbe_vf_reset_msg(adapter, vf); - adapter->vfinfo[vf].clear_to_send = true; - - if (is_valid_ether_addr(new_mac) && - !adapter->vfinfo[vf].pf_set_mac) - ixgbe_set_vf_mac(adapter, vf, vf_mac); - else - ixgbe_set_vf_mac(adapter, - vf, adapter->vfinfo[vf].vf_mac_addresses); - - /* reply to reset with ack and vf mac address */ - msgbuf[0] = IXGBE_VF_RESET | IXGBE_VT_MSGTYPE_ACK; - memcpy(new_mac, vf_mac, ETH_ALEN); - /* - * Piggyback the multicast filter type so VF can compute the - * correct vectors - */ - msgbuf[3] = hw->mac.mc_filter_type; - ixgbe_write_mbx(hw, msgbuf, IXGBE_VF_PERMADDR_MSG_LEN, vf); - - return retval; - } - if (!adapter->vfinfo[vf].clear_to_send) { msgbuf[0] |= IXGBE_VT_MSGTYPE_NACK; ixgbe_write_mbx(hw, msgbuf, 1, vf); @@ -613,70 +971,25 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf) switch ((msgbuf[0] & 0xFFFF)) { case IXGBE_VF_SET_MAC_ADDR: - new_mac = ((u8 *)(&msgbuf[1])); - if (is_valid_ether_addr(new_mac) && - !adapter->vfinfo[vf].pf_set_mac) { - ixgbe_set_vf_mac(adapter, vf, new_mac); - } else if (memcmp(adapter->vfinfo[vf].vf_mac_addresses, - new_mac, ETH_ALEN)) { - e_warn(drv, "VF %d attempted to override " - "administratively set MAC address\nReload " - "the VF driver to resume operations\n", vf); - retval = -1; - } + retval = ixgbe_set_vf_mac_addr(adapter, msgbuf, vf); break; case IXGBE_VF_SET_MULTICAST: - entries = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) - >> IXGBE_VT_MSGINFO_SHIFT; - hash_list = (u16 *)&msgbuf[1]; - retval = ixgbe_set_vf_multicasts(adapter, entries, - hash_list, vf); - break; - case IXGBE_VF_SET_LPE: - ixgbe_set_vf_lpe(adapter, msgbuf); + retval = ixgbe_set_vf_multicasts(adapter, msgbuf, vf); break; case IXGBE_VF_SET_VLAN: - add = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) - >> IXGBE_VT_MSGINFO_SHIFT; - vid = (msgbuf[1] & IXGBE_VLVF_VLANID_MASK); - if (adapter->vfinfo[vf].pf_vlan) { - e_warn(drv, "VF %d attempted to override " - "administratively set VLAN configuration\n" - "Reload the VF driver to resume operations\n", - vf); - retval = -1; - } else { - if (add) - adapter->vfinfo[vf].vlan_count++; - else if (adapter->vfinfo[vf].vlan_count) - adapter->vfinfo[vf].vlan_count--; - retval = ixgbe_set_vf_vlan(adapter, add, vid, vf); - if (!retval && adapter->vfinfo[vf].spoofchk_enabled) - hw->mac.ops.set_vlan_anti_spoofing(hw, true, vf); - } + retval = ixgbe_set_vf_vlan_msg(adapter, msgbuf, vf); + break; + case IXGBE_VF_SET_LPE: + retval = ixgbe_set_vf_lpe(adapter, msgbuf, vf); break; case IXGBE_VF_SET_MACVLAN: - index = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) >> - IXGBE_VT_MSGINFO_SHIFT; - if (adapter->vfinfo[vf].pf_set_mac && index > 0) { - e_warn(drv, "VF %d requested MACVLAN filter but is " - "administratively denied\n", vf); - retval = -1; - break; - } - /* - * If the VF is allowed to set MAC filters then turn off - * anti-spoofing to avoid false positives. An index - * greater than 0 will indicate the VF is setting a - * macvlan MAC filter. - */ - if (index > 0 && adapter->vfinfo[vf].spoofchk_enabled) - ixgbe_ndo_set_vf_spoofchk(adapter->netdev, vf, false); - retval = ixgbe_set_vf_macvlan(adapter, vf, index, - (unsigned char *)(&msgbuf[1])); - if (retval == -ENOSPC) - e_warn(drv, "VF %d has requested a MACVLAN filter " - "but there is no space for it\n", vf); + retval = ixgbe_set_vf_macvlan_msg(adapter, msgbuf, vf); + break; + case IXGBE_VF_API_NEGOTIATE: + retval = ixgbe_negotiate_vf_api(adapter, msgbuf, vf); + break; + case IXGBE_VF_GET_QUEUES: + retval = ixgbe_get_vf_queues(adapter, msgbuf, vf); break; default: e_err(drv, "Unhandled Msg %8.8x\n", msgbuf[0]); @@ -692,7 +1005,7 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf) msgbuf[0] |= IXGBE_VT_MSGTYPE_CTS; - ixgbe_write_mbx(hw, msgbuf, 1, vf); + ixgbe_write_mbx(hw, msgbuf, mbx_size, vf); return retval; } @@ -780,10 +1093,16 @@ int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos) if ((vf >= adapter->num_vfs) || (vlan > 4095) || (qos > 7)) return -EINVAL; if (vlan || qos) { + if (adapter->vfinfo[vf].pf_vlan) + err = ixgbe_set_vf_vlan(adapter, false, + adapter->vfinfo[vf].pf_vlan, + vf); + if (err) + goto out; err = ixgbe_set_vf_vlan(adapter, true, vlan, vf); if (err) goto out; - ixgbe_set_vmvir(adapter, vlan | (qos << VLAN_PRIO_SHIFT), vf); + ixgbe_set_vmvir(adapter, vlan, qos, vf); ixgbe_set_vmolr(hw, vf, false); if (adapter->vfinfo[vf].spoofchk_enabled) hw->mac.ops.set_vlan_anti_spoofing(hw, true, vf); @@ -803,16 +1122,16 @@ int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos) } else { err = ixgbe_set_vf_vlan(adapter, false, adapter->vfinfo[vf].pf_vlan, vf); - ixgbe_set_vmvir(adapter, vlan, vf); + ixgbe_clear_vmvir(adapter, vf); ixgbe_set_vmolr(hw, vf, true); hw->mac.ops.set_vlan_anti_spoofing(hw, false, vf); if (adapter->vfinfo[vf].vlan_count) adapter->vfinfo[vf].vlan_count--; adapter->vfinfo[vf].pf_vlan = 0; adapter->vfinfo[vf].pf_qos = 0; - } + } out: - return err; + return err; } static int ixgbe_link_mbps(struct ixgbe_adapter *adapter) @@ -903,7 +1222,8 @@ void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter) } } -int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate) +int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int min_tx_rate, + int max_tx_rate) { struct ixgbe_adapter *adapter = netdev_priv(netdev); int link_speed; @@ -921,13 +1241,16 @@ int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate) if (link_speed != 10000) return -EINVAL; + if (min_tx_rate) + return -EINVAL; + /* rate limit cannot be less than 10Mbs or greater than link speed */ - if (tx_rate && ((tx_rate <= 10) || (tx_rate > link_speed))) + if (max_tx_rate && ((max_tx_rate <= 10) || (max_tx_rate > link_speed))) return -EINVAL; /* store values */ adapter->vf_rate_link_speed = link_speed; - adapter->vfinfo[vf].tx_rate = tx_rate; + adapter->vfinfo[vf].tx_rate = max_tx_rate; /* update hardware configuration */ ixgbe_set_vf_rate_limit(adapter, vf); @@ -969,7 +1292,8 @@ int ixgbe_ndo_get_vf_config(struct net_device *netdev, return -EINVAL; ivi->vf = vf; memcpy(&ivi->mac, adapter->vfinfo[vf].vf_mac_addresses, ETH_ALEN); - ivi->tx_rate = adapter->vfinfo[vf].tx_rate; + ivi->max_tx_rate = adapter->vfinfo[vf].tx_rate; + ivi->min_tx_rate = 0; ivi->vlan = adapter->vfinfo[vf].pf_vlan; ivi->qos = adapter->vfinfo[vf].pf_qos; ivi->spoofchk = adapter->vfinfo[vf].spoofchk_enabled; |