static struct pci_device_id igb_pci_tbl[] = {
{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82576), board_82575 },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_82576_NS), board_82575 },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_82576_NS_SERDES), board_82575 },
{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82576_FIBER), board_82575 },
{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82576_SERDES), board_82575 },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_82576_SERDES_QUAD), board_82575 },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_82576_QUAD_COPPER), board_82575 },
{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82575EB_COPPER), board_82575 },
{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82575EB_FIBER_SERDES), board_82575 },
{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82575GB_QUAD_COPPER), board_82575 },
static void igb_clean_all_rx_rings(struct igb_adapter *);
static void igb_clean_tx_ring(struct igb_ring *);
static void igb_clean_rx_ring(struct igb_ring *);
-static void igb_set_multi(struct net_device *);
+static void igb_set_rx_mode(struct net_device *);
static void igb_update_phy_info(unsigned long);
static void igb_watchdog(unsigned long);
static void igb_watchdog_task(struct work_struct *);
-static int igb_xmit_frame_ring_adv(struct sk_buff *, struct net_device *,
- struct igb_ring *);
-static int igb_xmit_frame_adv(struct sk_buff *skb, struct net_device *);
+static netdev_tx_t igb_xmit_frame_ring_adv(struct sk_buff *,
+ struct net_device *,
+ struct igb_ring *);
+static netdev_tx_t igb_xmit_frame_adv(struct sk_buff *skb,
+ struct net_device *);
static struct net_device_stats *igb_get_stats(struct net_device *);
static int igb_change_mtu(struct net_device *, int);
static int igb_set_mac(struct net_device *, void *);
+static void igb_set_uta(struct igb_adapter *adapter);
static irqreturn_t igb_intr(int irq, void *);
static irqreturn_t igb_intr_msi(int irq, void *);
static irqreturn_t igb_msix_other(int irq, void *);
static void igb_vlan_rx_add_vid(struct net_device *, u16);
static void igb_vlan_rx_kill_vid(struct net_device *, u16);
static void igb_restore_vlan(struct igb_adapter *);
+static void igb_rar_set_qsel(struct igb_adapter *, u8 *, u32 , u8);
static void igb_ping_all_vfs(struct igb_adapter *);
static void igb_msg_task(struct igb_adapter *);
static int igb_rcv_msg_from_vf(struct igb_adapter *, u32);
-static inline void igb_set_rah_pool(struct e1000_hw *, int , int);
-static void igb_set_mc_list_pools(struct igb_adapter *, int, u16);
static void igb_vmm_control(struct igb_adapter *);
-static inline void igb_set_vmolr(struct e1000_hw *, int);
-static inline int igb_set_vf_rlpml(struct igb_adapter *, int, int);
static int igb_set_vf_mac(struct igb_adapter *adapter, int, unsigned char *);
static void igb_restore_vf_multicasts(struct igb_adapter *adapter);
-static int igb_suspend(struct pci_dev *, pm_message_t);
+static inline void igb_set_vmolr(struct e1000_hw *hw, int vfn)
+{
+ u32 reg_data;
+
+ reg_data = rd32(E1000_VMOLR(vfn));
+ reg_data |= E1000_VMOLR_BAM | /* Accept broadcast */
+ E1000_VMOLR_ROMPE | /* Accept packets matched in MTA */
+ E1000_VMOLR_AUPE | /* Accept untagged packets */
+ E1000_VMOLR_STRVLAN; /* Strip vlan tags */
+ wr32(E1000_VMOLR(vfn), reg_data);
+}
+
+static inline int igb_set_vf_rlpml(struct igb_adapter *adapter, int size,
+ int vfn)
+{
+ struct e1000_hw *hw = &adapter->hw;
+ u32 vmolr;
+
+ /* if it isn't the PF check to see if VFs are enabled and
+ * increase the size to support vlan tags */
+ if (vfn < adapter->vfs_allocated_count &&
+ adapter->vf_data[vfn].vlans_enabled)
+ size += VLAN_TAG_SIZE;
+
+ vmolr = rd32(E1000_VMOLR(vfn));
+ vmolr &= ~E1000_VMOLR_RLPML_MASK;
+ vmolr |= size | E1000_VMOLR_LPE;
+ wr32(E1000_VMOLR(vfn), vmolr);
+
+ return 0;
+}
+
#ifdef CONFIG_PM
+static int igb_suspend(struct pci_dev *, pm_message_t);
static int igb_resume(struct pci_dev *);
#endif
static void igb_shutdown(struct pci_dev *);
/* for netdump / net console */
static void igb_netpoll(struct net_device *);
#endif
-
#ifdef CONFIG_PCI_IOV
-static ssize_t igb_set_num_vfs(struct device *, struct device_attribute *,
- const char *, size_t);
-static ssize_t igb_show_num_vfs(struct device *, struct device_attribute *,
- char *);
-DEVICE_ATTR(num_vfs, S_IRUGO | S_IWUSR, igb_show_num_vfs, igb_set_num_vfs);
-#endif
+static unsigned int max_vfs = 0;
+module_param(max_vfs, uint, 0);
+MODULE_PARM_DESC(max_vfs, "Maximum number of virtual functions to allocate "
+ "per physical function");
+#endif /* CONFIG_PCI_IOV */
+
static pci_ers_result_t igb_io_error_detected(struct pci_dev *,
pci_channel_state_t);
static pci_ers_result_t igb_io_slot_reset(struct pci_dev *);
#endif
/**
+ * igb_desc_unused - calculate if we have unused descriptors
+ **/
+static int igb_desc_unused(struct igb_ring *ring)
+{
+ if (ring->next_to_clean > ring->next_to_use)
+ return ring->next_to_clean - ring->next_to_use - 1;
+
+ return ring->count + ring->next_to_clean - ring->next_to_use - 1;
+}
+
+/**
* igb_init_module - Driver Registration Routine
*
* igb_init_module is the first routine called when the driver is
for (i = 0; i < adapter->num_rx_queues; i++)
netif_napi_del(&adapter->rx_ring[i].napi);
+ adapter->num_rx_queues = 0;
+ adapter->num_tx_queues = 0;
+
kfree(adapter->tx_ring);
kfree(adapter->rx_ring);
}
/* If we can't do MSI-X, try MSI */
msi_only:
+#ifdef CONFIG_PCI_IOV
+ /* disable SR-IOV for non MSI-X configurations */
+ if (adapter->vf_data) {
+ struct e1000_hw *hw = &adapter->hw;
+ /* disable iov and allow time for transactions to clear */
+ pci_disable_sriov(adapter->pdev);
+ msleep(500);
+
+ kfree(adapter->vf_data);
+ adapter->vf_data = NULL;
+ wr32(E1000_IOVCTL, E1000_IOVCTL_REUSE_VFQ);
+ msleep(100);
+ dev_info(&adapter->pdev->dev, "IOV Disabled\n");
+ }
+#endif
adapter->num_rx_queues = 1;
adapter->num_tx_queues = 1;
if (!pci_enable_msi(adapter->pdev))
struct e1000_hw *hw = &adapter->hw;
if (adapter->msix_entries) {
- wr32(E1000_EIAM, 0);
- wr32(E1000_EIMC, ~0);
- wr32(E1000_EIAC, 0);
+ u32 regval = rd32(E1000_EIAM);
+ wr32(E1000_EIAM, regval & ~adapter->eims_enable_mask);
+ wr32(E1000_EIMC, adapter->eims_enable_mask);
+ regval = rd32(E1000_EIAC);
+ wr32(E1000_EIAC, regval & ~adapter->eims_enable_mask);
}
wr32(E1000_IAM, 0);
struct e1000_hw *hw = &adapter->hw;
if (adapter->msix_entries) {
- wr32(E1000_EIAC, adapter->eims_enable_mask);
- wr32(E1000_EIAM, adapter->eims_enable_mask);
+ u32 regval = rd32(E1000_EIAC);
+ wr32(E1000_EIAC, regval | adapter->eims_enable_mask);
+ regval = rd32(E1000_EIAM);
+ wr32(E1000_EIAM, regval | adapter->eims_enable_mask);
wr32(E1000_EIMS, adapter->eims_enable_mask);
if (adapter->vfs_allocated_count)
wr32(E1000_MBVFIMR, 0xFF);
int i;
igb_get_hw_control(adapter);
- igb_set_multi(netdev);
+ igb_set_rx_mode(netdev);
igb_restore_vlan(adapter);
igb_rx_fifo_flush_82575(&adapter->hw);
- /* call IGB_DESC_UNUSED which always leaves
+ /* call igb_desc_unused which always leaves
* at least 1 descriptor unused to make sure
* next_to_use != next_to_clean */
for (i = 0; i < adapter->num_rx_queues; i++) {
struct igb_ring *ring = &adapter->rx_ring[i];
- igb_alloc_rx_buffers_adv(ring, IGB_DESC_UNUSED(ring));
+ igb_alloc_rx_buffers_adv(ring, igb_desc_unused(ring));
}
igb_configure_msix(adapter);
igb_vmm_control(adapter);
- igb_set_rah_pool(hw, adapter->vfs_allocated_count, 0);
igb_set_vmolr(hw, adapter->vfs_allocated_count);
/* Clear any pending interrupts. */
rd32(E1000_ICR);
igb_irq_enable(adapter);
+ netif_tx_start_all_queues(adapter->netdev);
+
/* Fire a link change interrupt to start the watchdog. */
wr32(E1000_ICS, E1000_ICS_LSC);
return 0;
igb_reset(adapter);
igb_clean_all_tx_rings(adapter);
igb_clean_all_rx_rings(adapter);
+#ifdef CONFIG_IGB_DCA
+
+ /* since we reset the hardware DCA settings were cleared */
+ igb_setup_dca(adapter);
+#endif
}
void igb_reinit_locked(struct igb_adapter *adapter)
}
fc->pause_time = 0xFFFF;
fc->send_xon = 1;
- fc->type = fc->original_type;
+ fc->current_mode = fc->requested_mode;
/* disable receive for all VFs and wait one second */
if (adapter->vfs_allocated_count) {
.ndo_stop = igb_close,
.ndo_start_xmit = igb_xmit_frame_adv,
.ndo_get_stats = igb_get_stats,
- .ndo_set_multicast_list = igb_set_multi,
+ .ndo_set_rx_mode = igb_set_rx_mode,
+ .ndo_set_multicast_list = igb_set_rx_mode,
.ndo_set_mac_address = igb_set_mac,
.ndo_change_mtu = igb_change_mtu,
.ndo_do_ioctl = igb_ioctl,
struct net_device *netdev;
struct igb_adapter *adapter;
struct e1000_hw *hw;
- struct pci_dev *us_dev;
const struct e1000_info *ei = igb_info_tbl[ent->driver_data];
unsigned long mmio_start, mmio_len;
- int err, pci_using_dac, pos;
- u16 eeprom_data = 0, state = 0;
+ int err, pci_using_dac;
+ u16 eeprom_data = 0;
u16 eeprom_apme_mask = IGB_EEPROM_APME;
u32 part_num;
return err;
pci_using_dac = 0;
- err = pci_set_dma_mask(pdev, DMA_64BIT_MASK);
+ err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
if (!err) {
- err = pci_set_consistent_dma_mask(pdev, DMA_64BIT_MASK);
+ err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
if (!err)
pci_using_dac = 1;
} else {
- err = pci_set_dma_mask(pdev, DMA_32BIT_MASK);
+ err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
if (err) {
- err = pci_set_consistent_dma_mask(pdev, DMA_32BIT_MASK);
+ err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
if (err) {
dev_err(&pdev->dev, "No usable DMA "
"configuration, aborting\n");
}
}
- /* 82575 requires that the pci-e link partner disable the L0s state */
- switch (pdev->device) {
- case E1000_DEV_ID_82575EB_COPPER:
- case E1000_DEV_ID_82575EB_FIBER_SERDES:
- case E1000_DEV_ID_82575GB_QUAD_COPPER:
- us_dev = pdev->bus->self;
- pos = pci_find_capability(us_dev, PCI_CAP_ID_EXP);
- if (pos) {
- pci_read_config_word(us_dev, pos + PCI_EXP_LNKCTL,
- &state);
- state &= ~PCIE_LINK_STATE_L0S;
- pci_write_config_word(us_dev, pos + PCI_EXP_LNKCTL,
- state);
- dev_info(&pdev->dev,
- "Disabling ASPM L0s upstream switch port %s\n",
- pci_name(us_dev));
- }
- default:
- break;
- }
-
err = pci_request_selected_regions(pdev, pci_select_bars(pdev,
IORESOURCE_MEM),
igb_driver_name);
if (err)
goto err_pci_reg;
- err = pci_enable_pcie_error_reporting(pdev);
- if (err) {
- dev_err(&pdev->dev, "pci_enable_pcie_error_reporting failed "
- "0x%x\n", err);
- /* non-fatal, continue */
- }
+ pci_enable_pcie_error_reporting(pdev);
pci_set_master(pdev);
pci_save_state(pdev);
if (err)
goto err_sw_init;
+#ifdef CONFIG_PCI_IOV
+ /* since iov functionality isn't critical to base device function we
+ * can accept failure. If it fails we don't allow iov to be enabled */
+ if (hw->mac.type == e1000_82576) {
+ /* 82576 supports a maximum of 7 VFs in addition to the PF */
+ unsigned int num_vfs = (max_vfs > 7) ? 7 : max_vfs;
+ int i;
+ unsigned char mac_addr[ETH_ALEN];
+
+ if (num_vfs) {
+ adapter->vf_data = kcalloc(num_vfs,
+ sizeof(struct vf_data_storage),
+ GFP_KERNEL);
+ if (!adapter->vf_data) {
+ dev_err(&pdev->dev,
+ "Could not allocate VF private data - "
+ "IOV enable failed\n");
+ } else {
+ err = pci_enable_sriov(pdev, num_vfs);
+ if (!err) {
+ adapter->vfs_allocated_count = num_vfs;
+ dev_info(&pdev->dev,
+ "%d vfs allocated\n",
+ num_vfs);
+ for (i = 0;
+ i < adapter->vfs_allocated_count;
+ i++) {
+ random_ether_addr(mac_addr);
+ igb_set_vf_mac(adapter, i,
+ mac_addr);
+ }
+ } else {
+ kfree(adapter->vf_data);
+ adapter->vf_data = NULL;
+ }
+ }
+ }
+ }
+
+#endif
/* setup the private structure */
err = igb_sw_init(adapter);
if (err)
netdev->vlan_features |= NETIF_F_TSO;
netdev->vlan_features |= NETIF_F_TSO6;
netdev->vlan_features |= NETIF_F_IP_CSUM;
+ netdev->vlan_features |= NETIF_F_IPV6_CSUM;
netdev->vlan_features |= NETIF_F_SG;
if (pci_using_dac)
netdev->features |= NETIF_F_HIGHDMA;
+ if (adapter->hw.mac.type == e1000_82576)
+ netdev->features |= NETIF_F_SCTP_CSUM;
+
adapter->en_mng_pt = igb_enable_mng_pass_thru(&adapter->hw);
/* before reading the NVM, reset the controller to put the device in a
goto err_eeprom;
}
- init_timer(&adapter->watchdog_timer);
- adapter->watchdog_timer.function = &igb_watchdog;
- adapter->watchdog_timer.data = (unsigned long) adapter;
-
- init_timer(&adapter->phy_info_timer);
- adapter->phy_info_timer.function = &igb_update_phy_info;
- adapter->phy_info_timer.data = (unsigned long) adapter;
+ setup_timer(&adapter->watchdog_timer, &igb_watchdog,
+ (unsigned long) adapter);
+ setup_timer(&adapter->phy_info_timer, &igb_update_phy_info,
+ (unsigned long) adapter);
INIT_WORK(&adapter->reset_task, igb_reset_task);
INIT_WORK(&adapter->watchdog_task, igb_watchdog_task);
hw->mac.autoneg = true;
hw->phy.autoneg_advertised = 0x2f;
- hw->fc.original_type = e1000_fc_default;
- hw->fc.type = e1000_fc_default;
+ hw->fc.requested_mode = e1000_fc_default;
+ hw->fc.current_mode = e1000_fc_default;
adapter->itr_setting = IGB_DEFAULT_ITR;
adapter->itr = IGB_START_ITR;
igb_validate_mdi_setting(hw);
- adapter->rx_csum = 1;
-
/* Initial Wake on LAN setting If APM wake is enabled in the EEPROM,
* enable the ACPI Magic Packet filter
*/
- if (hw->bus.func == 0 ||
- hw->device_id == E1000_DEV_ID_82575EB_COPPER)
+ if (hw->bus.func == 0)
hw->nvm.ops.read(hw, NVM_INIT_CONTROL3_PORT_A, 1, &eeprom_data);
+ else if (hw->bus.func == 1)
+ hw->nvm.ops.read(hw, NVM_INIT_CONTROL3_PORT_B, 1, &eeprom_data);
if (eeprom_data & eeprom_apme_mask)
adapter->eeprom_wol |= E1000_WUFC_MAG;
if (rd32(E1000_STATUS) & E1000_STATUS_FUNC_1)
adapter->eeprom_wol = 0;
break;
+ case E1000_DEV_ID_82576_QUAD_COPPER:
+ /* if quad port adapter, disable WoL on all but port A */
+ if (global_quad_port_a != 0)
+ adapter->eeprom_wol = 0;
+ else
+ adapter->flags |= IGB_FLAG_QUAD_PORT_A;
+ /* Reset for multiple quad port adapters */
+ if (++global_quad_port_a == 4)
+ global_quad_port_a = 0;
+ break;
}
/* initialize the wol settings based on the eeprom settings */
* driver. */
igb_get_hw_control(adapter);
- /* tell the stack to leave us alone until igb_open() is called */
- netif_carrier_off(netdev);
- netif_tx_stop_all_queues(netdev);
-
strcpy(netdev->name, "eth%d");
err = register_netdev(netdev);
if (err)
goto err_register;
-#ifdef CONFIG_PCI_IOV
- /* since iov functionality isn't critical to base device function we
- * can accept failure. If it fails we don't allow iov to be enabled */
- if (hw->mac.type == e1000_82576) {
- err = pci_enable_sriov(pdev, 0);
- if (!err)
- err = device_create_file(&netdev->dev,
- &dev_attr_num_vfs);
- if (err)
- dev_err(&pdev->dev, "Failed to initialize IOV\n");
- }
+ /* carrier off reporting is important to ethtool even BEFORE open */
+ netif_carrier_off(netdev);
-#endif
#ifdef CONFIG_IGB_DCA
if (dca_add_requester(&pdev->dev) == 0) {
adapter->flags |= IGB_FLAG_DCA_ENABLED;
dev_info(&pdev->dev, "DCA enabled\n");
- /* Always use CB2 mode, difference is masked
- * in the CB driver. */
- wr32(E1000_DCA_CTRL, E1000_DCA_CTRL_DCA_MODE_CB2);
igb_setup_dca(adapter);
}
#endif
netdev->name,
((hw->bus.speed == e1000_bus_speed_2500)
? "2.5Gb/s" : "unknown"),
- ((hw->bus.width == e1000_bus_width_pcie_x4)
- ? "Width x4" : (hw->bus.width == e1000_bus_width_pcie_x1)
- ? "Width x1" : "unknown"),
+ ((hw->bus.width == e1000_bus_width_pcie_x4) ? "Width x4" :
+ (hw->bus.width == e1000_bus_width_pcie_x2) ? "Width x2" :
+ (hw->bus.width == e1000_bus_width_pcie_x1) ? "Width x1" :
+ "unknown"),
netdev->dev_addr);
igb_read_part_num(hw, &part_num);
struct net_device *netdev = pci_get_drvdata(pdev);
struct igb_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
- int err;
/* flush_scheduled work may reschedule our watchdog task, so
* explicitly disable watchdog tasks from being rescheduled */
free_netdev(netdev);
- err = pci_disable_pcie_error_reporting(pdev);
- if (err)
- dev_err(&pdev->dev,
- "pci_disable_pcie_error_reporting failed 0x%x\n", err);
+ pci_disable_pcie_error_reporting(pdev);
pci_disable_device(pdev);
}
if (test_bit(__IGB_TESTING, &adapter->state))
return -EBUSY;
+ netif_carrier_off(netdev);
+
/* allocate transmit descriptors */
err = igb_setup_all_tx_resources(adapter);
if (err)
igb_configure(adapter);
igb_vmm_control(adapter);
- igb_set_rah_pool(hw, adapter->vfs_allocated_count, 0);
igb_set_vmolr(hw, adapter->vfs_allocated_count);
err = igb_request_irq(adapter);
struct e1000_hw *hw = &adapter->hw;
u32 rctl;
u32 srrctl = 0;
- int i, j;
+ int i;
rctl = rd32(E1000_RCTL);
if (adapter->vfs_allocated_count) {
u32 vmolr;
- j = adapter->rx_ring[0].reg_idx;
-
/* set all queue drop enable bits */
wr32(E1000_QDE, ALL_QUEUES);
srrctl |= E1000_SRRCTL_DROP_EN;
/* disable queue 0 to prevent tail write w/o re-config */
wr32(E1000_RXDCTL(0), 0);
- vmolr = rd32(E1000_VMOLR(j));
+ vmolr = rd32(E1000_VMOLR(adapter->vfs_allocated_count));
if (rctl & E1000_RCTL_LPE)
vmolr |= E1000_VMOLR_LPE;
- if (adapter->num_rx_queues > 0)
+ if (adapter->num_rx_queues > 1)
vmolr |= E1000_VMOLR_RSSE;
- wr32(E1000_VMOLR(j), vmolr);
+ wr32(E1000_VMOLR(adapter->vfs_allocated_count), vmolr);
}
for (i = 0; i < adapter->num_rx_queues; i++) {
- j = adapter->rx_ring[i].reg_idx;
+ int j = adapter->rx_ring[i].reg_idx;
wr32(E1000_SRRCTL(j), srrctl);
}
mrqc |= (E1000_MRQC_RSS_FIELD_IPV6_UDP_EX |
E1000_MRQC_RSS_FIELD_IPV6_TCP_EX);
-
wr32(E1000_MRQC, mrqc);
-
- /* Multiqueue and raw packet checksumming are mutually
- * exclusive. Note that this not the same as TCP/IP
- * checksumming, which works fine. */
- rxcsum = rd32(E1000_RXCSUM);
- rxcsum |= E1000_RXCSUM_PCSD;
- wr32(E1000_RXCSUM, rxcsum);
- } else {
+ } else if (adapter->vfs_allocated_count) {
/* Enable multi-queue for sr-iov */
- if (adapter->vfs_allocated_count)
- wr32(E1000_MRQC, E1000_MRQC_ENABLE_VMDQ);
- /* Enable Receive Checksum Offload for TCP and UDP */
- rxcsum = rd32(E1000_RXCSUM);
- if (adapter->rx_csum)
- rxcsum |= E1000_RXCSUM_TUOFL | E1000_RXCSUM_IPPCSE;
- else
- rxcsum &= ~(E1000_RXCSUM_TUOFL | E1000_RXCSUM_IPPCSE);
-
- wr32(E1000_RXCSUM, rxcsum);
+ wr32(E1000_MRQC, E1000_MRQC_ENABLE_VMDQ);
}
+ /* Enable Receive Checksum Offload for TCP and UDP */
+ rxcsum = rd32(E1000_RXCSUM);
+ /* Disable raw packet checksumming */
+ rxcsum |= E1000_RXCSUM_PCSD;
+
+ if (adapter->hw.mac.type == e1000_82576)
+ /* Enable Receive Checksum Offload for SCTP */
+ rxcsum |= E1000_RXCSUM_CRCOFL;
+
+ /* Don't need to set TUOFL or IPOFL, they default to 1 */
+ wr32(E1000_RXCSUM, rxcsum);
+
/* Set the default pool for the PF's first queue */
igb_configure_vt_default_pool(adapter);
+ /* set UTA to appropriate mode */
+ igb_set_uta(adapter);
+
+ /* set the correct pool for the PF default MAC address in entry 0 */
+ igb_rar_set_qsel(adapter, adapter->hw.mac.addr, 0,
+ adapter->vfs_allocated_count);
+
igb_rlpml_set(adapter);
/* Enable Receives */
static void igb_unmap_and_free_tx_resource(struct igb_adapter *adapter,
struct igb_buffer *buffer_info)
{
- if (buffer_info->dma) {
- pci_unmap_page(adapter->pdev,
- buffer_info->dma,
- buffer_info->length,
- PCI_DMA_TODEVICE);
- buffer_info->dma = 0;
- }
+ buffer_info->dma = 0;
if (buffer_info->skb) {
+ skb_dma_unmap(&adapter->pdev->dev, buffer_info->skb,
+ DMA_TO_DEVICE);
dev_kfree_skb_any(buffer_info->skb);
buffer_info->skb = NULL;
}
buffer_info->time_stamp = 0;
- buffer_info->next_to_watch = 0;
/* buffer_info must be completely set up in the transmit path */
}
memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
memcpy(hw->mac.addr, addr->sa_data, netdev->addr_len);
- hw->mac.ops.rar_set(hw, hw->mac.addr, 0);
-
- igb_set_rah_pool(hw, adapter->vfs_allocated_count, 0);
+ /* set the correct pool for the new PF MAC address in entry 0 */
+ igb_rar_set_qsel(adapter, hw->mac.addr, 0,
+ adapter->vfs_allocated_count);
return 0;
}
/**
- * igb_set_multi - Multicast and Promiscuous mode set
+ * igb_write_mc_addr_list - write multicast addresses to MTA
* @netdev: network interface device structure
*
- * The set_multi entry point is called whenever the multicast address
- * list or the network interface flags are updated. This routine is
- * responsible for configuring the hardware for proper multicast,
- * promiscuous mode, and all-multi behavior.
+ * 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 void igb_set_multi(struct net_device *netdev)
+static int igb_write_mc_addr_list(struct net_device *netdev)
{
struct igb_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
- struct e1000_mac_info *mac = &hw->mac;
- struct dev_mc_list *mc_ptr;
+ struct dev_mc_list *mc_ptr = netdev->mc_list;
u8 *mta_list;
- u32 rctl;
+ u32 vmolr = 0;
int i;
- /* Check for Promiscuous and All Multicast modes */
-
- rctl = rd32(E1000_RCTL);
-
- if (netdev->flags & IFF_PROMISC) {
- rctl |= (E1000_RCTL_UPE | E1000_RCTL_MPE);
- rctl &= ~E1000_RCTL_VFE;
- } else {
- if (netdev->flags & IFF_ALLMULTI) {
- rctl |= E1000_RCTL_MPE;
- rctl &= ~E1000_RCTL_UPE;
- } else
- rctl &= ~(E1000_RCTL_UPE | E1000_RCTL_MPE);
- rctl |= E1000_RCTL_VFE;
- }
- wr32(E1000_RCTL, rctl);
-
if (!netdev->mc_count) {
/* nothing to program, so clear mc list */
- igb_update_mc_addr_list(hw, NULL, 0, 1,
- mac->rar_entry_count);
- return;
+ igb_update_mc_addr_list(hw, NULL, 0);
+ igb_restore_vf_multicasts(adapter);
+ return 0;
}
mta_list = kzalloc(netdev->mc_count * 6, GFP_ATOMIC);
if (!mta_list)
- return;
+ return -ENOMEM;
+
+ /* set vmolr receive overflow multicast bit */
+ vmolr |= E1000_VMOLR_ROMPE;
/* The shared function expects a packed array of only addresses. */
mc_ptr = netdev->mc_list;
memcpy(mta_list + (i*ETH_ALEN), mc_ptr->dmi_addr, ETH_ALEN);
mc_ptr = mc_ptr->next;
}
- igb_update_mc_addr_list(hw, mta_list, i,
- adapter->vfs_allocated_count + 1,
- mac->rar_entry_count);
+ igb_update_mc_addr_list(hw, mta_list, i);
+ kfree(mta_list);
- igb_set_mc_list_pools(adapter, i, mac->rar_entry_count);
- igb_restore_vf_multicasts(adapter);
+ return netdev->mc_count;
+}
- kfree(mta_list);
+/**
+ * igb_write_uc_addr_list - write unicast addresses to RAR table
+ * @netdev: network interface device structure
+ *
+ * Writes unicast address list to the RAR table.
+ * Returns: -ENOMEM on failure/insufficient address space
+ * 0 on no addresses written
+ * X on writing X addresses to the RAR table
+ **/
+static int igb_write_uc_addr_list(struct net_device *netdev)
+{
+ struct igb_adapter *adapter = netdev_priv(netdev);
+ struct e1000_hw *hw = &adapter->hw;
+ unsigned int vfn = adapter->vfs_allocated_count;
+ unsigned int rar_entries = hw->mac.rar_entry_count - (vfn + 1);
+ int count = 0;
+
+ /* return ENOMEM indicating insufficient memory for addresses */
+ if (netdev->uc.count > rar_entries)
+ return -ENOMEM;
+
+ if (netdev->uc.count && rar_entries) {
+ struct netdev_hw_addr *ha;
+ list_for_each_entry(ha, &netdev->uc.list, list) {
+ if (!rar_entries)
+ break;
+ igb_rar_set_qsel(adapter, ha->addr,
+ rar_entries--,
+ vfn);
+ count++;
+ }
+ }
+ /* write the addresses in reverse order to avoid write combining */
+ for (; rar_entries > 0 ; rar_entries--) {
+ wr32(E1000_RAH(rar_entries), 0);
+ wr32(E1000_RAL(rar_entries), 0);
+ }
+ wrfl();
+
+ return count;
+}
+
+/**
+ * igb_set_rx_mode - Secondary Unicast, Multicast and Promiscuous mode set
+ * @netdev: network interface device structure
+ *
+ * The set_rx_mode entry point is called whenever the unicast or multicast
+ * address lists or the network interface flags are updated. This routine is
+ * responsible for configuring the hardware for proper unicast, multicast,
+ * promiscuous mode, and all-multi behavior.
+ **/
+static void igb_set_rx_mode(struct net_device *netdev)
+{
+ struct igb_adapter *adapter = netdev_priv(netdev);
+ struct e1000_hw *hw = &adapter->hw;
+ unsigned int vfn = adapter->vfs_allocated_count;
+ u32 rctl, vmolr = 0;
+ int count;
+
+ /* Check for Promiscuous and All Multicast modes */
+ rctl = rd32(E1000_RCTL);
+
+ /* clear the effected bits */
+ rctl &= ~(E1000_RCTL_UPE | E1000_RCTL_MPE | E1000_RCTL_VFE);
+
+ if (netdev->flags & IFF_PROMISC) {
+ rctl |= (E1000_RCTL_UPE | E1000_RCTL_MPE);
+ vmolr |= (E1000_VMOLR_ROPE | E1000_VMOLR_MPME);
+ } else {
+ if (netdev->flags & IFF_ALLMULTI) {
+ rctl |= E1000_RCTL_MPE;
+ vmolr |= E1000_VMOLR_MPME;
+ } else {
+ /*
+ * Write addresses to the MTA, if the attempt fails
+ * then we should just turn on promiscous mode so
+ * that we can at least receive multicast traffic
+ */
+ count = igb_write_mc_addr_list(netdev);
+ if (count < 0) {
+ rctl |= E1000_RCTL_MPE;
+ vmolr |= E1000_VMOLR_MPME;
+ } else if (count) {
+ vmolr |= E1000_VMOLR_ROMPE;
+ }
+ }
+ /*
+ * Write addresses to available RAR registers, if there is not
+ * sufficient space to store all the addresses then enable
+ * unicast promiscous mode
+ */
+ count = igb_write_uc_addr_list(netdev);
+ if (count < 0) {
+ rctl |= E1000_RCTL_UPE;
+ vmolr |= E1000_VMOLR_ROPE;
+ }
+ rctl |= E1000_RCTL_VFE;
+ }
+ wr32(E1000_RCTL, rctl);
+
+ /*
+ * In order to support SR-IOV and eventually VMDq it is necessary to set
+ * the VMOLR to enable the appropriate modes. Without this workaround
+ * we will have issues with VLAN tag stripping not being done for frames
+ * that are only arriving because we are the default pool
+ */
+ if (hw->mac.type < e1000_82576)
+ return;
+
+ vmolr |= rd32(E1000_VMOLR(vfn)) &
+ ~(E1000_VMOLR_ROPE | E1000_VMOLR_MPME | E1000_VMOLR_ROMPE);
+ wr32(E1000_VMOLR(vfn), vmolr);
+ igb_restore_vf_multicasts(adapter);
}
/* Need to wait a few seconds after link up to get diagnostic information from
link_active = true;
}
break;
- case e1000_media_type_fiber:
- ret_val = hw->mac.ops.check_for_link(hw);
- link_active = !!(rd32(E1000_STATUS) & E1000_STATUS_LU);
- break;
case e1000_media_type_internal_serdes:
ret_val = hw->mac.ops.check_for_link(hw);
link_active = hw->mac.serdes_has_link;
}
netif_carrier_on(netdev);
- netif_tx_wake_all_queues(netdev);
igb_ping_all_vfs(adapter);
printk(KERN_INFO "igb: %s NIC Link is Down\n",
netdev->name);
netif_carrier_off(netdev);
- netif_tx_stop_all_queues(netdev);
igb_ping_all_vfs(adapter);
igb_update_adaptive(&adapter->hw);
if (!netif_carrier_ok(netdev)) {
- if (IGB_DESC_UNUSED(tx_ring) + 1 < tx_ring->count) {
+ if (igb_desc_unused(tx_ring) + 1 < tx_ring->count) {
/* We've lost link, so the controller stops DMA,
* but we've got queued Tx work that's never going
* to get done, so reset controller to flush Tx.
* (Do the reset outside of interrupt context). */
adapter->tx_timeout_count++;
schedule_work(&adapter->reset_task);
+ /* return immediately since reset is imminent */
+ return;
}
}
switch (current_itr) {
/* counts and packets in update_itr are dependent on these numbers */
case lowest_latency:
- new_itr = 70000;
+ new_itr = 56; /* aka 70,000 ints/sec */
break;
case low_latency:
- new_itr = 20000; /* aka hwitr = ~200 */
+ new_itr = 196; /* aka 20,000 ints/sec */
break;
case bulk_latency:
- new_itr = 4000;
+ new_itr = 980; /* aka 4,000 ints/sec */
break;
default:
break;
* by adding intermediate steps when interrupt rate is
* increasing */
new_itr = new_itr > adapter->itr ?
- min(adapter->itr + (new_itr >> 2), new_itr) :
+ max((new_itr * adapter->itr) /
+ (new_itr + (adapter->itr >> 2)), new_itr) :
new_itr;
/* Don't write the value here; it resets the adapter's
* internal timer, and causes us to delay far longer than
* ends up being correct.
*/
adapter->itr = new_itr;
- adapter->rx_ring->itr_val = 1000000000 / (new_itr * 256);
+ adapter->rx_ring->itr_val = new_itr;
adapter->rx_ring->set_itr = 1;
}
tu_cmd |= (E1000_TXD_CMD_DEXT | E1000_ADVTXD_DTYP_CTXT);
if (skb->ip_summed == CHECKSUM_PARTIAL) {
- switch (skb->protocol) {
+ __be16 protocol;
+
+ if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
+ const struct vlan_ethhdr *vhdr =
+ (const struct vlan_ethhdr*)skb->data;
+
+ protocol = vhdr->h_vlan_encapsulated_proto;
+ } else {
+ protocol = skb->protocol;
+ }
+
+ switch (protocol) {
case cpu_to_be16(ETH_P_IP):
tu_cmd |= E1000_ADVTXD_TUCMD_IPV4;
if (ip_hdr(skb)->protocol == IPPROTO_TCP)
tu_cmd |= E1000_ADVTXD_TUCMD_L4T_TCP;
+ else if (ip_hdr(skb)->protocol == IPPROTO_SCTP)
+ tu_cmd |= E1000_ADVTXD_TUCMD_L4T_SCTP;
break;
case cpu_to_be16(ETH_P_IPV6):
/* XXX what about other V6 headers?? */
if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP)
tu_cmd |= E1000_ADVTXD_TUCMD_L4T_TCP;
+ else if (ipv6_hdr(skb)->nexthdr == IPPROTO_SCTP)
+ tu_cmd |= E1000_ADVTXD_TUCMD_L4T_SCTP;
break;
default:
if (unlikely(net_ratelimit()))
unsigned int len = skb_headlen(skb);
unsigned int count = 0, i;
unsigned int f;
+ dma_addr_t *map;
i = tx_ring->next_to_use;
+ if (skb_dma_map(&adapter->pdev->dev, skb, DMA_TO_DEVICE)) {
+ dev_err(&adapter->pdev->dev, "TX DMA map failed\n");
+ return 0;
+ }
+
+ map = skb_shinfo(skb)->dma_maps;
+
buffer_info = &tx_ring->buffer_info[i];
BUG_ON(len >= IGB_MAX_DATA_PER_TXD);
buffer_info->length = len;
/* set time_stamp *before* dma to help avoid a possible race */
buffer_info->time_stamp = jiffies;
buffer_info->next_to_watch = i;
- buffer_info->dma = pci_map_single(adapter->pdev, skb->data, len,
- PCI_DMA_TODEVICE);
- count++;
- i++;
- if (i == tx_ring->count)
- i = 0;
+ buffer_info->dma = skb_shinfo(skb)->dma_head;
for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) {
struct skb_frag_struct *frag;
+ i++;
+ if (i == tx_ring->count)
+ i = 0;
+
frag = &skb_shinfo(skb)->frags[f];
len = frag->size;
buffer_info->length = len;
buffer_info->time_stamp = jiffies;
buffer_info->next_to_watch = i;
- buffer_info->dma = pci_map_page(adapter->pdev,
- frag->page,
- frag->page_offset,
- len,
- PCI_DMA_TODEVICE);
-
+ buffer_info->dma = map[count];
count++;
- i++;
- if (i == tx_ring->count)
- i = 0;
}
- i = ((i == 0) ? tx_ring->count - 1 : i - 1);
tx_ring->buffer_info[i].skb = skb;
tx_ring->buffer_info[first].next_to_watch = i;
- return count;
+ return count + 1;
}
static inline void igb_tx_queue_adv(struct igb_adapter *adapter,
/* We need to check again in a case another CPU has just
* made room available. */
- if (IGB_DESC_UNUSED(tx_ring) < size)
+ if (igb_desc_unused(tx_ring) < size)
return -EBUSY;
/* A reprieve! */
static int igb_maybe_stop_tx(struct net_device *netdev,
struct igb_ring *tx_ring, int size)
{
- if (IGB_DESC_UNUSED(tx_ring) >= size)
+ if (igb_desc_unused(tx_ring) >= size)
return 0;
return __igb_maybe_stop_tx(netdev, tx_ring, size);
}
-static int igb_xmit_frame_ring_adv(struct sk_buff *skb,
- struct net_device *netdev,
- struct igb_ring *tx_ring)
+static netdev_tx_t igb_xmit_frame_ring_adv(struct sk_buff *skb,
+ struct net_device *netdev,
+ struct igb_ring *tx_ring)
{
struct igb_adapter *adapter = netdev_priv(netdev);
unsigned int first;
unsigned int tx_flags = 0;
u8 hdr_len = 0;
+ int count = 0;
int tso = 0;
union skb_shared_tx *shtx;
(skb->ip_summed == CHECKSUM_PARTIAL))
tx_flags |= IGB_TX_FLAGS_CSUM;
- igb_tx_queue_adv(adapter, tx_ring, tx_flags,
- igb_tx_map_adv(adapter, tx_ring, skb, first),
- skb->len, hdr_len);
-
- netdev->trans_start = jiffies;
+ /*
+ * count reflects descriptors mapped, if 0 then mapping error
+ * has occured and we need to rewind the descriptor queue
+ */
+ count = igb_tx_map_adv(adapter, tx_ring, skb, first);
- /* Make sure there is space in the ring for the next send. */
- igb_maybe_stop_tx(netdev, tx_ring, MAX_SKB_FRAGS + 4);
+ if (count) {
+ igb_tx_queue_adv(adapter, tx_ring, tx_flags, count,
+ skb->len, hdr_len);
+ /* Make sure there is space in the ring for the next send. */
+ igb_maybe_stop_tx(netdev, tx_ring, MAX_SKB_FRAGS + 4);
+ } else {
+ dev_kfree_skb_any(skb);
+ tx_ring->buffer_info[first].time_stamp = 0;
+ tx_ring->next_to_use = first;
+ }
return NETDEV_TX_OK;
}
-static int igb_xmit_frame_adv(struct sk_buff *skb, struct net_device *netdev)
+static netdev_tx_t igb_xmit_frame_adv(struct sk_buff *skb,
+ struct net_device *netdev)
{
struct igb_adapter *adapter = netdev_priv(netdev);
struct igb_ring *tx_ring;
* to a flow. Right now, performance is impacted slightly negatively
* if using multiple tx queues. If the stack breaks away from a
* single qdisc implementation, we can look at this again. */
- return (igb_xmit_frame_ring_adv(skb, netdev, tx_ring));
+ return igb_xmit_frame_ring_adv(skb, netdev, tx_ring);
}
/**
/* Rx Errors */
+ if (hw->mac.type != e1000_82575) {
+ u32 rqdpc_tmp;
+ u64 rqdpc_total = 0;
+ int i;
+ /* Read out drops stats per RX queue. Notice RQDPC (Receive
+ * Queue Drop Packet Count) stats only gets incremented, if
+ * the DROP_EN but it set (in the SRRCTL register for that
+ * queue). If DROP_EN bit is NOT set, then the some what
+ * equivalent count is stored in RNBC (not per queue basis).
+ * Also note the drop count is due to lack of available
+ * descriptors.
+ */
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ rqdpc_tmp = rd32(E1000_RQDPC(i)) & 0xFFF;
+ adapter->rx_ring[i].rx_stats.drops += rqdpc_tmp;
+ rqdpc_total += adapter->rx_ring[i].rx_stats.drops;
+ }
+ adapter->net_stats.rx_fifo_errors = rqdpc_total;
+ }
+
+ /* Note RNBC (Receive No Buffers Count) is an not an exact
+ * drop count as the hardware FIFO might save the day. Thats
+ * one of the reason for saving it in rx_fifo_errors, as its
+ * potentially not a true drop.
+ */
+ adapter->net_stats.rx_fifo_errors += adapter->stats.rnbc;
+
/* RLEC on some newer hardware can be incorrect so build
- * our own version based on RUC and ROC */
+ * our own version based on RUC and ROC */
adapter->net_stats.rx_errors = adapter->stats.rxerrc +
adapter->stats.crcerrs + adapter->stats.algnerrc +
adapter->stats.ruc + adapter->stats.roc +
static void igb_setup_dca(struct igb_adapter *adapter)
{
+ struct e1000_hw *hw = &adapter->hw;
int i;
if (!(adapter->flags & IGB_FLAG_DCA_ENABLED))
return;
+ /* Always use CB2 mode, difference is masked in the CB driver. */
+ wr32(E1000_DCA_CTRL, E1000_DCA_CTRL_DCA_MODE_CB2);
+
for (i = 0; i < adapter->num_tx_queues; i++) {
adapter->tx_ring[i].cpu = -1;
igb_update_tx_dca(&adapter->tx_ring[i]);
/* VFs are limited to using the MTA hash table for their multicast
* addresses */
for (i = 0; i < n; i++)
- vf_data->vf_mc_hashes[i] = hash_list[i];;
+ vf_data->vf_mc_hashes[i] = hash_list[i];
/* Flush and reset the mta with the new values */
- igb_set_multi(adapter->netdev);
+ igb_set_rx_mode(adapter->netdev);
return 0;
}
for (i = 0; i < adapter->vfs_allocated_count; i++) {
vf_data = &adapter->vf_data[i];
- for (j = 0; j < vf_data[i].num_vf_mc_hashes; j++)
+ for (j = 0; j < vf_data->num_vf_mc_hashes; j++)
igb_mta_set(hw, vf_data->vf_mc_hashes[j]);
}
}
wr32(E1000_VLVF(i), reg);
}
+
+ adapter->vf_data[vf].vlans_enabled = 0;
}
static s32 igb_vlvf_set(struct igb_adapter *adapter, u32 vid, bool add, u32 vf)
/* if !enabled we need to set this up in vfta */
if (!(reg & E1000_VLVF_VLANID_ENABLE)) {
- /* add VID to filter table */
- igb_vfta_set(hw, vid, true);
+ /* add VID to filter table, if bit already set
+ * PF must have added it outside of table */
+ if (igb_vfta_set(hw, vid, true))
+ reg |= 1 << (E1000_VLVF_POOLSEL_SHIFT +
+ adapter->vfs_allocated_count);
reg |= E1000_VLVF_VLANID_ENABLE;
}
+ reg &= ~E1000_VLVF_VLANID_MASK;
+ reg |= vid;
wr32(E1000_VLVF(i), reg);
+
+ /* do not modify RLPML for PF devices */
+ if (vf >= adapter->vfs_allocated_count)
+ return 0;
+
+ if (!adapter->vf_data[vf].vlans_enabled) {
+ u32 size;
+ reg = rd32(E1000_VMOLR(vf));
+ size = reg & E1000_VMOLR_RLPML_MASK;
+ size += 4;
+ reg &= ~E1000_VMOLR_RLPML_MASK;
+ reg |= size;
+ wr32(E1000_VMOLR(vf), reg);
+ }
+ adapter->vf_data[vf].vlans_enabled++;
+
return 0;
}
} else {
igb_vfta_set(hw, vid, false);
}
wr32(E1000_VLVF(i), reg);
+
+ /* do not modify RLPML for PF devices */
+ if (vf >= adapter->vfs_allocated_count)
+ return 0;
+
+ adapter->vf_data[vf].vlans_enabled--;
+ if (!adapter->vf_data[vf].vlans_enabled) {
+ u32 size;
+ reg = rd32(E1000_VMOLR(vf));
+ size = reg & E1000_VMOLR_RLPML_MASK;
+ size -= 4;
+ reg &= ~E1000_VMOLR_RLPML_MASK;
+ reg |= size;
+ wr32(E1000_VMOLR(vf), reg);
+ }
return 0;
}
}
adapter->vf_data[vf].num_vf_mc_hashes = 0;
/* Flush and reset the mta with the new values */
- igb_set_multi(adapter->netdev);
+ igb_set_rx_mode(adapter->netdev);
}
static inline void igb_vf_reset_msg(struct igb_adapter *adapter, u32 vf)
{
struct e1000_hw *hw = &adapter->hw;
unsigned char *vf_mac = adapter->vf_data[vf].vf_mac_addresses;
+ int rar_entry = hw->mac.rar_entry_count - (vf + 1);
u32 reg, msgbuf[3];
u8 *addr = (u8 *)(&msgbuf[1]);
igb_vf_reset_event(adapter, vf);
/* set vf mac address */
- igb_rar_set(hw, vf_mac, vf + 1);
- igb_set_rah_pool(hw, vf, vf + 1);
+ igb_rar_set_qsel(adapter, vf_mac, rar_entry, vf);
/* enable transmit and receive for vf */
reg = rd32(E1000_VFTE);
}
/**
+ * igb_set_uta - Set unicast filter table address
+ * @adapter: board private structure
+ *
+ * The unicast table address is a register array of 32-bit registers.
+ * The table is meant to be used in a way similar to how the MTA is used
+ * however due to certain limitations in the hardware it is necessary to
+ * set all the hash bits to 1 and use the VMOLR ROPE bit as a promiscous
+ * enable bit to allow vlan tag stripping when promiscous mode is enabled
+ **/
+static void igb_set_uta(struct igb_adapter *adapter)
+{
+ struct e1000_hw *hw = &adapter->hw;
+ int i;
+
+ /* The UTA table only exists on 82576 hardware and newer */
+ if (hw->mac.type < e1000_82576)
+ return;
+
+ /* we only need to do this if VMDq is enabled */
+ if (!adapter->vfs_allocated_count)
+ return;
+
+ for (i = 0; i < hw->mac.uta_reg_count; i++)
+ array_wr32(E1000_UTA, i, ~0);
+}
+
+/**
* igb_intr_msi - Interrupt Handler
* @irq: interrupt number
* @data: pointer to a network interface device structure
static int igb_poll(struct napi_struct *napi, int budget)
{
struct igb_ring *rx_ring = container_of(napi, struct igb_ring, napi);
- struct igb_adapter *adapter = rx_ring->adapter;
- struct net_device *netdev = adapter->netdev;
int work_done = 0;
#ifdef CONFIG_IGB_DCA
- if (adapter->flags & IGB_FLAG_DCA_ENABLED)
+ if (rx_ring->adapter->flags & IGB_FLAG_DCA_ENABLED)
igb_update_rx_dca(rx_ring);
#endif
igb_clean_rx_irq_adv(rx_ring, &work_done, budget);
if (rx_ring->buddy) {
#ifdef CONFIG_IGB_DCA
- if (adapter->flags & IGB_FLAG_DCA_ENABLED)
+ if (rx_ring->adapter->flags & IGB_FLAG_DCA_ENABLED)
igb_update_tx_dca(rx_ring->buddy);
#endif
if (!igb_clean_tx_irq(rx_ring->buddy))
}
/* If not enough Rx work done, exit the polling mode */
- if ((work_done < budget) || !netif_running(netdev)) {
+ if (work_done < budget) {
napi_complete(napi);
igb_rx_irq_enable(rx_ring);
}
if (unlikely(count &&
netif_carrier_ok(netdev) &&
- IGB_DESC_UNUSED(tx_ring) >= IGB_TX_QUEUE_WAKE)) {
+ igb_desc_unused(tx_ring) >= IGB_TX_QUEUE_WAKE)) {
/* Make sure that anybody stopping the queue after this
* sees the new next_to_clean.
*/
bool vlan_extracted = (adapter->vlgrp && (status & E1000_RXD_STAT_VP));
skb_record_rx_queue(skb, ring->queue_index);
- if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
- if (vlan_extracted)
- vlan_gro_receive(&ring->napi, adapter->vlgrp,
- le16_to_cpu(rx_desc->wb.upper.vlan),
- skb);
- else
- napi_gro_receive(&ring->napi, skb);
- } else {
- if (vlan_extracted)
- vlan_hwaccel_receive_skb(skb, adapter->vlgrp,
- le16_to_cpu(rx_desc->wb.upper.vlan));
- else
- netif_receive_skb(skb);
- }
+ if (vlan_extracted)
+ vlan_gro_receive(&ring->napi, adapter->vlgrp,
+ le16_to_cpu(rx_desc->wb.upper.vlan),
+ skb);
+ else
+ napi_gro_receive(&ring->napi, skb);
}
static inline void igb_rx_checksum_adv(struct igb_adapter *adapter,
skb->ip_summed = CHECKSUM_NONE;
/* Ignore Checksum bit is set or checksum is disabled through ethtool */
- if ((status_err & E1000_RXD_STAT_IXSM) || !adapter->rx_csum)
+ if ((status_err & E1000_RXD_STAT_IXSM) ||
+ (adapter->flags & IGB_FLAG_RX_CSUM_DISABLED))
return;
/* TCP/UDP checksum error bit is set */
if (status_err &
(E1000_RXDEXT_STATERR_TCPE | E1000_RXDEXT_STATERR_IPE)) {
+ /*
+ * work around errata with sctp packets where the TCPE aka
+ * L4E bit is set incorrectly on 64 byte (60 byte w/o crc)
+ * packets, (aka let the stack check the crc32c)
+ */
+ if (!((adapter->hw.mac.type == e1000_82576) &&
+ (skb->len == 60)))
+ adapter->hw_csum_err++;
/* let the stack verify checksum errors */
- adapter->hw_csum_err++;
return;
}
/* It must be a TCP or UDP packet with a valid checksum */
if (status_err & (E1000_RXD_STAT_TCPCS | E1000_RXD_STAT_UDPCS))
skb->ip_summed = CHECKSUM_UNNECESSARY;
+ dev_dbg(&adapter->pdev->dev, "cksum success: bits %08X\n", status_err);
adapter->hw_csum_good++;
}
+static inline u16 igb_get_hlen(struct igb_adapter *adapter,
+ union e1000_adv_rx_desc *rx_desc)
+{
+ /* HW will not DMA in data larger than the given buffer, even if it
+ * parses the (NFS, of course) header to be larger. In that case, it
+ * fills the header buffer and spills the rest into the page.
+ */
+ u16 hlen = (le16_to_cpu(rx_desc->wb.lower.lo_dword.hdr_info) &
+ E1000_RXDADV_HDRBUFLEN_MASK) >> E1000_RXDADV_HDRBUFLEN_SHIFT;
+ if (hlen > adapter->rx_ps_hdr_size)
+ hlen = adapter->rx_ps_hdr_size;
+ return hlen;
+}
+
static bool igb_clean_rx_irq_adv(struct igb_ring *rx_ring,
int *work_done, int budget)
{
int cleaned_count = 0;
unsigned int total_bytes = 0, total_packets = 0;
unsigned int i;
- u32 length, hlen, staterr;
+ u32 staterr;
+ u16 length;
i = rx_ring->next_to_clean;
buffer_info = &rx_ring->buffer_info[i];
cleaned = true;
cleaned_count++;
+ /* this is the fast path for the non-packet split case */
if (!adapter->rx_ps_hdr_size) {
pci_unmap_single(pdev, buffer_info->dma,
- adapter->rx_buffer_len +
- NET_IP_ALIGN,
+ adapter->rx_buffer_len,
PCI_DMA_FROMDEVICE);
+ buffer_info->dma = 0;
skb_put(skb, length);
goto send_up;
}
- /* HW will not DMA in data larger than the given buffer, even
- * if it parses the (NFS, of course) header to be larger. In
- * that case, it fills the header buffer and spills the rest
- * into the page.
- */
- hlen = (le16_to_cpu(rx_desc->wb.lower.lo_dword.hdr_info) &
- E1000_RXDADV_HDRBUFLEN_MASK) >> E1000_RXDADV_HDRBUFLEN_SHIFT;
- if (hlen > adapter->rx_ps_hdr_size)
- hlen = adapter->rx_ps_hdr_size;
-
- if (!skb_shinfo(skb)->nr_frags) {
+ if (buffer_info->dma) {
+ u16 hlen = igb_get_hlen(adapter, rx_desc);
pci_unmap_single(pdev, buffer_info->dma,
- adapter->rx_ps_hdr_size + NET_IP_ALIGN,
+ adapter->rx_ps_hdr_size,
PCI_DMA_FROMDEVICE);
+ buffer_info->dma = 0;
skb_put(skb, hlen);
}
}
rx_ring->next_to_clean = i;
- cleaned_count = IGB_DESC_UNUSED(rx_ring);
+ cleaned_count = igb_desc_unused(rx_ring);
if (cleaned_count)
igb_alloc_rx_buffers_adv(rx_ring, cleaned_count);
bufsz = adapter->rx_ps_hdr_size;
else
bufsz = adapter->rx_buffer_len;
- bufsz += NET_IP_ALIGN;
while (cleaned_count--) {
rx_desc = E1000_RX_DESC_ADV(*rx_ring, i);
}
if (!buffer_info->skb) {
- skb = netdev_alloc_skb(netdev, bufsz);
+ skb = netdev_alloc_skb(netdev, bufsz + NET_IP_ALIGN);
if (!skb) {
adapter->alloc_rx_buff_failed++;
goto no_buffers;
data->phy_id = adapter->hw.phy.addr;
break;
case SIOCGMIIREG:
- if (!capable(CAP_NET_ADMIN))
- return -EPERM;
if (igb_read_phy_reg(&adapter->hw, data->reg_num & 0x1F,
&data->val_out))
return -EIO;
}
}
+s32 igb_read_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value)
+{
+ struct igb_adapter *adapter = hw->back;
+ u16 cap_offset;
+
+ cap_offset = pci_find_capability(adapter->pdev, PCI_CAP_ID_EXP);
+ if (!cap_offset)
+ return -E1000_ERR_CONFIG;
+
+ pci_read_config_word(adapter->pdev, cap_offset + reg, value);
+
+ return 0;
+}
+
+s32 igb_write_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value)
+{
+ struct igb_adapter *adapter = hw->back;
+ u16 cap_offset;
+
+ cap_offset = pci_find_capability(adapter->pdev, PCI_CAP_ID_EXP);
+ if (!cap_offset)
+ return -E1000_ERR_CONFIG;
+
+ pci_write_config_word(adapter->pdev, cap_offset + reg, *value);
+
+ return 0;
+}
+
static void igb_vlan_rx_register(struct net_device *netdev,
struct vlan_group *grp)
{
mac->autoneg = 0;
- /* Fiber NICs only allow 1000 gbps Full duplex */
- if ((adapter->hw.phy.media_type == e1000_media_type_fiber) &&
- spddplx != (SPEED_1000 + DUPLEX_FULL)) {
- dev_err(&adapter->pdev->dev,
- "Unsupported Speed/Duplex configuration\n");
- return -EINVAL;
- }
-
switch (spddplx) {
case SPEED_10 + DUPLEX_HALF:
mac->forced_speed_duplex = ADVERTISE_10_HALF;
return 0;
}
-static int igb_suspend(struct pci_dev *pdev, pm_message_t state)
+static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake)
{
struct net_device *netdev = pci_get_drvdata(pdev);
struct igb_adapter *adapter = netdev_priv(netdev);
if (wufc) {
igb_setup_rctl(adapter);
- igb_set_multi(netdev);
+ igb_set_rx_mode(netdev);
/* turn on all-multi mode if wake on multicast is enabled */
if (wufc & E1000_WUFC_MC) {
wr32(E1000_WUFC, 0);
}
- /* make sure adapter isn't asleep if manageability/wol is enabled */
- if (wufc || adapter->en_mng_pt) {
- pci_enable_wake(pdev, PCI_D3hot, 1);
- pci_enable_wake(pdev, PCI_D3cold, 1);
- } else {
- igb_shutdown_fiber_serdes_link_82575(hw);
- pci_enable_wake(pdev, PCI_D3hot, 0);
- pci_enable_wake(pdev, PCI_D3cold, 0);
- }
+ *enable_wake = wufc || adapter->en_mng_pt;
+ if (!*enable_wake)
+ igb_shutdown_serdes_link_82575(hw);
/* Release control of h/w to f/w. If f/w is AMT enabled, this
* would have already happened in close and is redundant. */
pci_disable_device(pdev);
- pci_set_power_state(pdev, pci_choose_state(pdev, state));
-
return 0;
}
#ifdef CONFIG_PM
+static int igb_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+ int retval;
+ bool wake;
+
+ retval = __igb_shutdown(pdev, &wake);
+ if (retval)
+ return retval;
+
+ if (wake) {
+ pci_prepare_to_sleep(pdev);
+ } else {
+ pci_wake_from_d3(pdev, false);
+ pci_set_power_state(pdev, PCI_D3hot);
+ }
+
+ return 0;
+}
+
static int igb_resume(struct pci_dev *pdev)
{
struct net_device *netdev = pci_get_drvdata(pdev);
static void igb_shutdown(struct pci_dev *pdev)
{
- igb_suspend(pdev, PMSG_SUSPEND);
+ bool wake;
+
+ __igb_shutdown(pdev, &wake);
+
+ if (system_state == SYSTEM_POWER_OFF) {
+ pci_wake_from_d3(pdev, wake);
+ pci_set_power_state(pdev, PCI_D3hot);
+ }
}
#ifdef CONFIG_NET_POLL_CONTROLLER
netif_device_detach(netdev);
+ if (state == pci_channel_io_perm_failure)
+ return PCI_ERS_RESULT_DISCONNECT;
+
if (netif_running(netdev))
igb_down(adapter);
pci_disable_device(pdev);
igb_get_hw_control(adapter);
}
-static inline void igb_set_vmolr(struct e1000_hw *hw, int vfn)
-{
- u32 reg_data;
-
- reg_data = rd32(E1000_VMOLR(vfn));
- reg_data |= E1000_VMOLR_BAM | /* Accept broadcast */
- E1000_VMOLR_ROPE | /* Accept packets matched in UTA */
- E1000_VMOLR_ROMPE | /* Accept packets matched in MTA */
- E1000_VMOLR_AUPE | /* Accept untagged packets */
- E1000_VMOLR_STRVLAN; /* Strip vlan tags */
- wr32(E1000_VMOLR(vfn), reg_data);
-}
-
-static inline int igb_set_vf_rlpml(struct igb_adapter *adapter, int size,
- int vfn)
+static void igb_rar_set_qsel(struct igb_adapter *adapter, u8 *addr, u32 index,
+ u8 qsel)
{
+ u32 rar_low, rar_high;
struct e1000_hw *hw = &adapter->hw;
- u32 vmolr;
- vmolr = rd32(E1000_VMOLR(vfn));
- vmolr &= ~E1000_VMOLR_RLPML_MASK;
- vmolr |= size | E1000_VMOLR_LPE;
- wr32(E1000_VMOLR(vfn), vmolr);
-
- return 0;
-}
-
-static inline void igb_set_rah_pool(struct e1000_hw *hw, int pool, int entry)
-{
- u32 reg_data;
+ /* HW expects these in little endian so we reverse the byte order
+ * from network order (big endian) to little endian
+ */
+ rar_low = ((u32) addr[0] | ((u32) addr[1] << 8) |
+ ((u32) addr[2] << 16) | ((u32) addr[3] << 24));
+ rar_high = ((u32) addr[4] | ((u32) addr[5] << 8));
- reg_data = rd32(E1000_RAH(entry));
- reg_data &= ~E1000_RAH_POOL_MASK;
- reg_data |= E1000_RAH_POOL_1 << pool;;
- wr32(E1000_RAH(entry), reg_data);
-}
+ /* Indicate to hardware the Address is Valid. */
+ rar_high |= E1000_RAH_AV;
-static void igb_set_mc_list_pools(struct igb_adapter *adapter,
- int entry_count, u16 total_rar_filters)
-{
- struct e1000_hw *hw = &adapter->hw;
- int i = adapter->vfs_allocated_count + 1;
-
- if ((i + entry_count) < total_rar_filters)
- total_rar_filters = i + entry_count;
+ if (hw->mac.type == e1000_82575)
+ rar_high |= E1000_RAH_POOL_1 * qsel;
+ else
+ rar_high |= E1000_RAH_POOL_1 << qsel;
- for (; i < total_rar_filters; i++)
- igb_set_rah_pool(hw, adapter->vfs_allocated_count, i);
+ wr32(E1000_RAL(index), rar_low);
+ wrfl();
+ wr32(E1000_RAH(index), rar_high);
+ wrfl();
}
static int igb_set_vf_mac(struct igb_adapter *adapter,
int vf, unsigned char *mac_addr)
{
struct e1000_hw *hw = &adapter->hw;
- int rar_entry = vf + 1; /* VF MAC addresses start at entry 1 */
-
- igb_rar_set(hw, mac_addr, rar_entry);
+ /* VF MAC addresses start at end of receive addresses and moves
+ * torwards the first, as a result a collision should not be possible */
+ int rar_entry = hw->mac.rar_entry_count - (vf + 1);
memcpy(adapter->vf_data[vf].vf_mac_addresses, mac_addr, ETH_ALEN);
- igb_set_rah_pool(hw, vf, rar_entry);
+ igb_rar_set_qsel(adapter, mac_addr, rar_entry, vf);
return 0;
}
igb_vmdq_set_replication_pf(hw, true);
}
-#ifdef CONFIG_PCI_IOV
-static ssize_t igb_show_num_vfs(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct igb_adapter *adapter = netdev_priv(to_net_dev(dev));
-
- return sprintf(buf, "%d\n", adapter->vfs_allocated_count);
-}
-
-static ssize_t igb_set_num_vfs(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct net_device *netdev = to_net_dev(dev);
- struct igb_adapter *adapter = netdev_priv(netdev);
- struct e1000_hw *hw = &adapter->hw;
- struct pci_dev *pdev = adapter->pdev;
- unsigned int num_vfs, i;
- unsigned char mac_addr[ETH_ALEN];
- int err;
-
- sscanf(buf, "%u", &num_vfs);
-
- if (num_vfs > 7)
- num_vfs = 7;
-
- /* value unchanged do nothing */
- if (num_vfs == adapter->vfs_allocated_count)
- return count;
-
- if (netdev->flags & IFF_UP)
- igb_close(netdev);
-
- igb_reset_interrupt_capability(adapter);
- igb_free_queues(adapter);
- adapter->tx_ring = NULL;
- adapter->rx_ring = NULL;
- adapter->vfs_allocated_count = 0;
-
- /* reclaim resources allocated to VFs since we are changing count */
- if (adapter->vf_data) {
- /* disable iov and allow time for transactions to clear */
- pci_disable_sriov(pdev);
- msleep(500);
-
- kfree(adapter->vf_data);
- adapter->vf_data = NULL;
- wr32(E1000_IOVCTL, E1000_IOVCTL_REUSE_VFQ);
- msleep(100);
- dev_info(&pdev->dev, "IOV Disabled\n");
- }
-
- if (num_vfs) {
- adapter->vf_data = kcalloc(num_vfs,
- sizeof(struct vf_data_storage),
- GFP_KERNEL);
- if (!adapter->vf_data) {
- dev_err(&pdev->dev, "Could not allocate VF private "
- "data - IOV enable failed\n");
- } else {
- err = pci_enable_sriov(pdev, num_vfs);
- if (!err) {
- adapter->vfs_allocated_count = num_vfs;
- dev_info(&pdev->dev, "%d vfs allocated\n", num_vfs);
- for (i = 0; i < adapter->vfs_allocated_count; i++) {
- random_ether_addr(mac_addr);
- igb_set_vf_mac(adapter, i, mac_addr);
- }
- } else {
- kfree(adapter->vf_data);
- adapter->vf_data = NULL;
- }
- }
- }
-
- igb_set_interrupt_capability(adapter);
- igb_alloc_queues(adapter);
- igb_reset(adapter);
-
- if (netdev->flags & IFF_UP)
- igb_open(netdev);
-
- return count;
-}
-#endif /* CONFIG_PCI_IOV */
/* igb_main.c */