diff options
Diffstat (limited to 'drivers/net/ethernet/intel/igb/igb_main.c')
| -rw-r--r-- | drivers/net/ethernet/intel/igb/igb_main.c | 7119 |
1 files changed, 7119 insertions, 0 deletions
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c new file mode 100644 index 000000000000..ced544499f1b --- /dev/null +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -0,0 +1,7119 @@ +/******************************************************************************* + + Intel(R) Gigabit Ethernet Linux driver + Copyright(c) 2007-2011 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, + version 2, as published by the Free Software Foundation. + + This program is distributed in the hope it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + more details. + + You should have received a copy of the GNU General Public License along with + this program; if not, write to the Free Software Foundation, Inc., + 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + + The full GNU General Public License is included in this distribution in + the file called "COPYING". + + Contact Information: + e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + +*******************************************************************************/ + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/init.h> +#include <linux/bitops.h> +#include <linux/vmalloc.h> +#include <linux/pagemap.h> +#include <linux/netdevice.h> +#include <linux/ipv6.h> +#include <linux/slab.h> +#include <net/checksum.h> +#include <net/ip6_checksum.h> +#include <linux/net_tstamp.h> +#include <linux/mii.h> +#include <linux/ethtool.h> +#include <linux/if.h> +#include <linux/if_vlan.h> +#include <linux/pci.h> +#include <linux/pci-aspm.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/ip.h> +#include <linux/tcp.h> +#include <linux/sctp.h> +#include <linux/if_ether.h> +#include <linux/aer.h> +#include <linux/prefetch.h> +#ifdef CONFIG_IGB_DCA +#include <linux/dca.h> +#endif +#include "igb.h" + +#define MAJ 3 +#define MIN 2 +#define BUILD 10 +#define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) "." \ +__stringify(BUILD) "-k" +char igb_driver_name[] = "igb"; +char igb_driver_version[] = DRV_VERSION; +static const char igb_driver_string[] = + "Intel(R) Gigabit Ethernet Network Driver"; +static const char igb_copyright[] = "Copyright (c) 2007-2011 Intel Corporation."; + +static const struct e1000_info *igb_info_tbl[] = { + [board_82575] = &e1000_82575_info, +}; + +static DEFINE_PCI_DEVICE_TABLE(igb_pci_tbl) = { + { PCI_VDEVICE(INTEL, E1000_DEV_ID_I350_COPPER), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_I350_FIBER), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_I350_SERDES), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_I350_SGMII), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_COPPER), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_FIBER), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_QUAD_FIBER), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_SERDES), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_SGMII), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_COPPER_DUAL), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_DH89XXCC_SGMII), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_DH89XXCC_SERDES), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_DH89XXCC_BACKPLANE), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_DH89XXCC_SFP), board_82575 }, + { 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_ET2), 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 }, + /* required last entry */ + {0, } +}; + +MODULE_DEVICE_TABLE(pci, igb_pci_tbl); + +void igb_reset(struct igb_adapter *); +static int igb_setup_all_tx_resources(struct igb_adapter *); +static int igb_setup_all_rx_resources(struct igb_adapter *); +static void igb_free_all_tx_resources(struct igb_adapter *); +static void igb_free_all_rx_resources(struct igb_adapter *); +static void igb_setup_mrqc(struct igb_adapter *); +static int igb_probe(struct pci_dev *, const struct pci_device_id *); +static void __devexit igb_remove(struct pci_dev *pdev); +static void igb_init_hw_timer(struct igb_adapter *adapter); +static int igb_sw_init(struct igb_adapter *); +static int igb_open(struct net_device *); +static int igb_close(struct net_device *); +static void igb_configure_tx(struct igb_adapter *); +static void igb_configure_rx(struct igb_adapter *); +static void igb_clean_all_tx_rings(struct igb_adapter *); +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_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 netdev_tx_t igb_xmit_frame(struct sk_buff *skb, struct net_device *); +static struct rtnl_link_stats64 *igb_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *stats); +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 irqreturn_t igb_msix_ring(int irq, void *); +#ifdef CONFIG_IGB_DCA +static void igb_update_dca(struct igb_q_vector *); +static void igb_setup_dca(struct igb_adapter *); +#endif /* CONFIG_IGB_DCA */ +static int igb_poll(struct napi_struct *, int); +static bool igb_clean_tx_irq(struct igb_q_vector *); +static bool igb_clean_rx_irq(struct igb_q_vector *, int); +static int igb_ioctl(struct net_device *, struct ifreq *, int cmd); +static void igb_tx_timeout(struct net_device *); +static void igb_reset_task(struct work_struct *); +static void igb_vlan_mode(struct net_device *netdev, u32 features); +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 void igb_vmm_control(struct igb_adapter *); +static int igb_set_vf_mac(struct igb_adapter *, int, unsigned char *); +static void igb_restore_vf_multicasts(struct igb_adapter *adapter); +static int igb_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac); +static int igb_ndo_set_vf_vlan(struct net_device *netdev, + int vf, u16 vlan, u8 qos); +static int igb_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate); +static int igb_ndo_get_vf_config(struct net_device *netdev, int vf, + struct ifla_vf_info *ivi); +static void igb_check_vf_rate_limit(struct igb_adapter *); + +#ifdef CONFIG_PCI_IOV +static int igb_vf_configure(struct igb_adapter *adapter, int vf); +static int igb_find_enabled_vfs(struct igb_adapter *adapter); +static int igb_check_vf_assignment(struct igb_adapter *adapter); +#endif + +#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 *); +#ifdef CONFIG_IGB_DCA +static int igb_notify_dca(struct notifier_block *, unsigned long, void *); +static struct notifier_block dca_notifier = { + .notifier_call = igb_notify_dca, + .next = NULL, + .priority = 0 +}; +#endif +#ifdef CONFIG_NET_POLL_CONTROLLER +/* for netdump / net console */ +static void igb_netpoll(struct net_device *); +#endif +#ifdef CONFIG_PCI_IOV +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 *); +static void igb_io_resume(struct pci_dev *); + +static struct pci_error_handlers igb_err_handler = { + .error_detected = igb_io_error_detected, + .slot_reset = igb_io_slot_reset, + .resume = igb_io_resume, +}; + +static void igb_init_dmac(struct igb_adapter *adapter, u32 pba); + +static struct pci_driver igb_driver = { + .name = igb_driver_name, + .id_table = igb_pci_tbl, + .probe = igb_probe, + .remove = __devexit_p(igb_remove), +#ifdef CONFIG_PM + /* Power Management Hooks */ + .suspend = igb_suspend, + .resume = igb_resume, +#endif + .shutdown = igb_shutdown, + .err_handler = &igb_err_handler +}; + +MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>"); +MODULE_DESCRIPTION("Intel(R) Gigabit Ethernet Network Driver"); +MODULE_LICENSE("GPL"); +MODULE_VERSION(DRV_VERSION); + +struct igb_reg_info { + u32 ofs; + char *name; +}; + +static const struct igb_reg_info igb_reg_info_tbl[] = { + + /* General Registers */ + {E1000_CTRL, "CTRL"}, + {E1000_STATUS, "STATUS"}, + {E1000_CTRL_EXT, "CTRL_EXT"}, + + /* Interrupt Registers */ + {E1000_ICR, "ICR"}, + + /* RX Registers */ + {E1000_RCTL, "RCTL"}, + {E1000_RDLEN(0), "RDLEN"}, + {E1000_RDH(0), "RDH"}, + {E1000_RDT(0), "RDT"}, + {E1000_RXDCTL(0), "RXDCTL"}, + {E1000_RDBAL(0), "RDBAL"}, + {E1000_RDBAH(0), "RDBAH"}, + + /* TX Registers */ + {E1000_TCTL, "TCTL"}, + {E1000_TDBAL(0), "TDBAL"}, + {E1000_TDBAH(0), "TDBAH"}, + {E1000_TDLEN(0), "TDLEN"}, + {E1000_TDH(0), "TDH"}, + {E1000_TDT(0), "TDT"}, + {E1000_TXDCTL(0), "TXDCTL"}, + {E1000_TDFH, "TDFH"}, + {E1000_TDFT, "TDFT"}, + {E1000_TDFHS, "TDFHS"}, + {E1000_TDFPC, "TDFPC"}, + + /* List Terminator */ + {} +}; + +/* + * igb_regdump - register printout routine + */ +static void igb_regdump(struct e1000_hw *hw, struct igb_reg_info *reginfo) +{ + int n = 0; + char rname[16]; + u32 regs[8]; + + switch (reginfo->ofs) { + case E1000_RDLEN(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_RDLEN(n)); + break; + case E1000_RDH(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_RDH(n)); + break; + case E1000_RDT(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_RDT(n)); + break; + case E1000_RXDCTL(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_RXDCTL(n)); + break; + case E1000_RDBAL(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_RDBAL(n)); + break; + case E1000_RDBAH(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_RDBAH(n)); + break; + case E1000_TDBAL(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_RDBAL(n)); + break; + case E1000_TDBAH(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_TDBAH(n)); + break; + case E1000_TDLEN(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_TDLEN(n)); + break; + case E1000_TDH(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_TDH(n)); + break; + case E1000_TDT(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_TDT(n)); + break; + case E1000_TXDCTL(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_TXDCTL(n)); + break; + default: + printk(KERN_INFO "%-15s %08x\n", + reginfo->name, rd32(reginfo->ofs)); + return; + } + + snprintf(rname, 16, "%s%s", reginfo->name, "[0-3]"); + printk(KERN_INFO "%-15s ", rname); + for (n = 0; n < 4; n++) + printk(KERN_CONT "%08x ", regs[n]); + printk(KERN_CONT "\n"); +} + +/* + * igb_dump - Print registers, tx-rings and rx-rings + */ +static void igb_dump(struct igb_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct e1000_hw *hw = &adapter->hw; + struct igb_reg_info *reginfo; + struct igb_ring *tx_ring; + union e1000_adv_tx_desc *tx_desc; + struct my_u0 { u64 a; u64 b; } *u0; + struct igb_ring *rx_ring; + union e1000_adv_rx_desc *rx_desc; + u32 staterr; + u16 i, n; + + if (!netif_msg_hw(adapter)) + return; + + /* Print netdevice Info */ + if (netdev) { + dev_info(&adapter->pdev->dev, "Net device Info\n"); + printk(KERN_INFO "Device Name state " + "trans_start last_rx\n"); + printk(KERN_INFO "%-15s %016lX %016lX %016lX\n", + netdev->name, + netdev->state, + netdev->trans_start, + netdev->last_rx); + } + + /* Print Registers */ + dev_info(&adapter->pdev->dev, "Register Dump\n"); + printk(KERN_INFO " Register Name Value\n"); + for (reginfo = (struct igb_reg_info *)igb_reg_info_tbl; + reginfo->name; reginfo++) { + igb_regdump(hw, reginfo); + } + + /* Print TX Ring Summary */ + if (!netdev || !netif_running(netdev)) + goto exit; + + dev_info(&adapter->pdev->dev, "TX Rings Summary\n"); + printk(KERN_INFO "Queue [NTU] [NTC] [bi(ntc)->dma ]" + " leng ntw timestamp\n"); + for (n = 0; n < adapter->num_tx_queues; n++) { + struct igb_tx_buffer *buffer_info; + tx_ring = adapter->tx_ring[n]; + buffer_info = &tx_ring->tx_buffer_info[tx_ring->next_to_clean]; + printk(KERN_INFO " %5d %5X %5X %016llX %04X %p %016llX\n", + n, tx_ring->next_to_use, tx_ring->next_to_clean, + (u64)buffer_info->dma, + buffer_info->length, + buffer_info->next_to_watch, + (u64)buffer_info->time_stamp); + } + + /* Print TX Rings */ + if (!netif_msg_tx_done(adapter)) + goto rx_ring_summary; + + dev_info(&adapter->pdev->dev, "TX Rings Dump\n"); + + /* Transmit Descriptor Formats + * + * Advanced Transmit Descriptor + * +--------------------------------------------------------------+ + * 0 | Buffer Address [63:0] | + * +--------------------------------------------------------------+ + * 8 | PAYLEN | PORTS |CC|IDX | STA | DCMD |DTYP|MAC|RSV| DTALEN | + * +--------------------------------------------------------------+ + * 63 46 45 40 39 38 36 35 32 31 24 15 0 + */ + + for (n = 0; n < adapter->num_tx_queues; n++) { + tx_ring = adapter->tx_ring[n]; + printk(KERN_INFO "------------------------------------\n"); + printk(KERN_INFO "TX QUEUE INDEX = %d\n", tx_ring->queue_index); + printk(KERN_INFO "------------------------------------\n"); + printk(KERN_INFO "T [desc] [address 63:0 ] " + "[PlPOCIStDDM Ln] [bi->dma ] " + "leng ntw timestamp bi->skb\n"); + + for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) { + struct igb_tx_buffer *buffer_info; + tx_desc = IGB_TX_DESC(tx_ring, i); + buffer_info = &tx_ring->tx_buffer_info[i]; + u0 = (struct my_u0 *)tx_desc; + printk(KERN_INFO "T [0x%03X] %016llX %016llX %016llX" + " %04X %p %016llX %p", i, + le64_to_cpu(u0->a), + le64_to_cpu(u0->b), + (u64)buffer_info->dma, + buffer_info->length, + buffer_info->next_to_watch, + (u64)buffer_info->time_stamp, + buffer_info->skb); + if (i == tx_ring->next_to_use && + i == tx_ring->next_to_clean) + printk(KERN_CONT " NTC/U\n"); + else if (i == tx_ring->next_to_use) + printk(KERN_CONT " NTU\n"); + else if (i == tx_ring->next_to_clean) + printk(KERN_CONT " NTC\n"); + else + printk(KERN_CONT "\n"); + + if (netif_msg_pktdata(adapter) && buffer_info->dma != 0) + print_hex_dump(KERN_INFO, "", + DUMP_PREFIX_ADDRESS, + 16, 1, phys_to_virt(buffer_info->dma), + buffer_info->length, true); + } + } + + /* Print RX Rings Summary */ +rx_ring_summary: + dev_info(&adapter->pdev->dev, "RX Rings Summary\n"); + printk(KERN_INFO "Queue [NTU] [NTC]\n"); + for (n = 0; n < adapter->num_rx_queues; n++) { + rx_ring = adapter->rx_ring[n]; + printk(KERN_INFO " %5d %5X %5X\n", n, + rx_ring->next_to_use, rx_ring->next_to_clean); + } + + /* Print RX Rings */ + if (!netif_msg_rx_status(adapter)) + goto exit; + + dev_info(&adapter->pdev->dev, "RX Rings Dump\n"); + + /* Advanced Receive Descriptor (Read) Format + * 63 1 0 + * +-----------------------------------------------------+ + * 0 | Packet Buffer Address [63:1] |A0/NSE| + * +----------------------------------------------+------+ + * 8 | Header Buffer Address [63:1] | DD | + * +-----------------------------------------------------+ + * + * + * Advanced Receive Descriptor (Write-Back) Format + * + * 63 48 47 32 31 30 21 20 17 16 4 3 0 + * +------------------------------------------------------+ + * 0 | Packet IP |SPH| HDR_LEN | RSV|Packet| RSS | + * | Checksum Ident | | | | Type | Type | + * +------------------------------------------------------+ + * 8 | VLAN Tag | Length | Extended Error | Extended Status | + * +------------------------------------------------------+ + * 63 48 47 32 31 20 19 0 + */ + + for (n = 0; n < adapter->num_rx_queues; n++) { + rx_ring = adapter->rx_ring[n]; + printk(KERN_INFO "------------------------------------\n"); + printk(KERN_INFO "RX QUEUE INDEX = %d\n", rx_ring->queue_index); + printk(KERN_INFO "------------------------------------\n"); + printk(KERN_INFO "R [desc] [ PktBuf A0] " + "[ HeadBuf DD] [bi->dma ] [bi->skb] " + "<-- Adv Rx Read format\n"); + printk(KERN_INFO "RWB[desc] [PcsmIpSHl PtRs] " + "[vl er S cks ln] ---------------- [bi->skb] " + "<-- Adv Rx Write-Back format\n"); + + for (i = 0; i < rx_ring->count; i++) { + struct igb_rx_buffer *buffer_info; + buffer_info = &rx_ring->rx_buffer_info[i]; + rx_desc = IGB_RX_DESC(rx_ring, i); + u0 = (struct my_u0 *)rx_desc; + staterr = le32_to_cpu(rx_desc->wb.upper.status_error); + if (staterr & E1000_RXD_STAT_DD) { + /* Descriptor Done */ + printk(KERN_INFO "RWB[0x%03X] %016llX " + "%016llX ---------------- %p", i, + le64_to_cpu(u0->a), + le64_to_cpu(u0->b), + buffer_info->skb); + } else { + printk(KERN_INFO "R [0x%03X] %016llX " + "%016llX %016llX %p", i, + le64_to_cpu(u0->a), + le64_to_cpu(u0->b), + (u64)buffer_info->dma, + buffer_info->skb); + + if (netif_msg_pktdata(adapter)) { + print_hex_dump(KERN_INFO, "", + DUMP_PREFIX_ADDRESS, + 16, 1, + phys_to_virt(buffer_info->dma), + IGB_RX_HDR_LEN, true); + print_hex_dump(KERN_INFO, "", + DUMP_PREFIX_ADDRESS, + 16, 1, + phys_to_virt( + buffer_info->page_dma + + buffer_info->page_offset), + PAGE_SIZE/2, true); + } + } + + if (i == rx_ring->next_to_use) + printk(KERN_CONT " NTU\n"); + else if (i == rx_ring->next_to_clean) + printk(KERN_CONT " NTC\n"); + else + printk(KERN_CONT "\n"); + + } + } + +exit: + return; +} + + +/** + * igb_read_clock - read raw cycle counter (to be used by time counter) + */ +static cycle_t igb_read_clock(const struct cyclecounter *tc) +{ + struct igb_adapter *adapter = + container_of(tc, struct igb_adapter, cycles); + struct e1000_hw *hw = &adapter->hw; + u64 stamp = 0; + int shift = 0; + + /* + * The timestamp latches on lowest register read. For the 82580 + * the lowest register is SYSTIMR instead of SYSTIML. However we never + * adjusted TIMINCA so SYSTIMR will just read as all 0s so ignore it. + */ + if (hw->mac.type >= e1000_82580) { + stamp = rd32(E1000_SYSTIMR) >> 8; + shift = IGB_82580_TSYNC_SHIFT; + } + + stamp |= (u64)rd32(E1000_SYSTIML) << shift; + stamp |= (u64)rd32(E1000_SYSTIMH) << (shift + 32); + return stamp; +} + +/** + * igb_get_hw_dev - return device + * used by hardware layer to print debugging information + **/ +struct net_device *igb_get_hw_dev(struct e1000_hw *hw) +{ + struct igb_adapter *adapter = hw->back; + return adapter->netdev; +} + +/** + * igb_init_module - Driver Registration Routine + * + * igb_init_module is the first routine called when the driver is + * loaded. All it does is register with the PCI subsystem. + **/ +static int __init igb_init_module(void) +{ + int ret; + printk(KERN_INFO "%s - version %s\n", + igb_driver_string, igb_driver_version); + + printk(KERN_INFO "%s\n", igb_copyright); + +#ifdef CONFIG_IGB_DCA + dca_register_notify(&dca_notifier); +#endif + ret = pci_register_driver(&igb_driver); + return ret; +} + +module_init(igb_init_module); + +/** + * igb_exit_module - Driver Exit Cleanup Routine + * + * igb_exit_module is called just before the driver is removed + * from memory. + **/ +static void __exit igb_exit_module(void) +{ +#ifdef CONFIG_IGB_DCA + dca_unregister_notify(&dca_notifier); +#endif + pci_unregister_driver(&igb_driver); +} + +module_exit(igb_exit_module); + +#define Q_IDX_82576(i) (((i & 0x1) << 3) + (i >> 1)) +/** + * igb_cache_ring_register - Descriptor ring to register mapping + * @adapter: board private structure to initialize + * + * Once we know the feature-set enabled for the device, we'll cache + * the register offset the descriptor ring is assigned to. + **/ +static void igb_cache_ring_register(struct igb_adapter *adapter) +{ + int i = 0, j = 0; + u32 rbase_offset = adapter->vfs_allocated_count; + + switch (adapter->hw.mac.type) { + case e1000_82576: + /* The queues are allocated for virtualization such that VF 0 + * is allocated queues 0 and 8, VF 1 queues 1 and 9, etc. + * In order to avoid collision we start at the first free queue + * and continue consuming queues in the same sequence + */ + if (adapter->vfs_allocated_count) { + for (; i < adapter->rss_queues; i++) + adapter->rx_ring[i]->reg_idx = rbase_offset + + Q_IDX_82576(i); + } + case e1000_82575: + case e1000_82580: + case e1000_i350: + default: + for (; i < adapter->num_rx_queues; i++) + adapter->rx_ring[i]->reg_idx = rbase_offset + i; + for (; j < adapter->num_tx_queues; j++) + adapter->tx_ring[j]->reg_idx = rbase_offset + j; + break; + } +} + +static void igb_free_queues(struct igb_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) { + kfree(adapter->tx_ring[i]); + adapter->tx_ring[i] = NULL; + } + for (i = 0; i < adapter->num_rx_queues; i++) { + kfree(adapter->rx_ring[i]); + adapter->rx_ring[i] = NULL; + } + adapter->num_rx_queues = 0; + adapter->num_tx_queues = 0; +} + +/** + * igb_alloc_queues - Allocate memory for all rings + * @adapter: board private structure to initialize + * + * We allocate one ring per queue at run-time since we don't know the + * number of queues at compile-time. + **/ +static int igb_alloc_queues(struct igb_adapter *adapter) +{ + struct igb_ring *ring; + int i; + int orig_node = adapter->node; + + for (i = 0; i < adapter->num_tx_queues; i++) { + if (orig_node == -1) { + int cur_node = next_online_node(adapter->node); + if (cur_node == MAX_NUMNODES) + cur_node = first_online_node; + adapter->node = cur_node; + } + ring = kzalloc_node(sizeof(struct igb_ring), GFP_KERNEL, + adapter->node); + if (!ring) + ring = kzalloc(sizeof(struct igb_ring), GFP_KERNEL); + if (!ring) + goto err; + ring->count = adapter->tx_ring_count; + ring->queue_index = i; + ring->dev = &adapter->pdev->dev; + ring->netdev = adapter->netdev; + ring->numa_node = adapter->node; + /* For 82575, context index must be unique per ring. */ + if (adapter->hw.mac.type == e1000_82575) + set_bit(IGB_RING_FLAG_TX_CTX_IDX, &ring->flags); + adapter->tx_ring[i] = ring; + } + /* Restore the adapter's original node */ + adapter->node = orig_node; + + for (i = 0; i < adapter->num_rx_queues; i++) { + if (orig_node == -1) { + int cur_node = next_online_node(adapter->node); + if (cur_node == MAX_NUMNODES) + cur_node = first_online_node; + adapter->node = cur_node; + } + ring = kzalloc_node(sizeof(struct igb_ring), GFP_KERNEL, + adapter->node); + if (!ring) + ring = kzalloc(sizeof(struct igb_ring), GFP_KERNEL); + if (!ring) + goto err; + ring->count = adapter->rx_ring_count; + ring->queue_index = i; + ring->dev = &adapter->pdev->dev; + ring->netdev = adapter->netdev; + ring->numa_node = adapter->node; + /* set flag indicating ring supports SCTP checksum offload */ + if (adapter->hw.mac.type >= e1000_82576) + set_bit(IGB_RING_FLAG_RX_SCTP_CSUM, &ring->flags); + + /* On i350, loopback VLAN packets have the tag byte-swapped. */ + if (adapter->hw.mac.type == e1000_i350) + set_bit(IGB_RING_FLAG_RX_LB_VLAN_BSWAP, &ring->flags); + + adapter->rx_ring[i] = ring; + } + /* Restore the adapter's original node */ + adapter->node = orig_node; + + igb_cache_ring_register(adapter); + + return 0; + +err: + /* Restore the adapter's original node */ + adapter->node = orig_node; + igb_free_queues(adapter); + + return -ENOMEM; +} + +/** + * igb_write_ivar - configure ivar for given MSI-X vector + * @hw: pointer to the HW structure + * @msix_vector: vector number we are allocating to a given ring + * @index: row index of IVAR register to write within IVAR table + * @offset: column offset of in IVAR, should be multiple of 8 + * + * This function is intended to handle the writing of the IVAR register + * for adapters 82576 and newer. The IVAR table consists of 2 columns, + * each containing an cause allocation for an Rx and Tx ring, and a + * variable number of rows depending on the number of queues supported. + **/ +static void igb_write_ivar(struct e1000_hw *hw, int msix_vector, + int index, int offset) +{ + u32 ivar = array_rd32(E1000_IVAR0, index); + + /* clear any bits that are currently set */ + ivar &= ~((u32)0xFF << offset); + + /* write vector and valid bit */ + ivar |= (msix_vector | E1000_IVAR_VALID) << offset; + + array_wr32(E1000_IVAR0, index, ivar); +} + +#define IGB_N0_QUEUE -1 +static void igb_assign_vector(struct igb_q_vector *q_vector, int msix_vector) +{ + struct igb_adapter *adapter = q_vector->adapter; + struct e1000_hw *hw = &adapter->hw; + int rx_queue = IGB_N0_QUEUE; + int tx_queue = IGB_N0_QUEUE; + u32 msixbm = 0; + + if (q_vector->rx.ring) + rx_queue = q_vector->rx.ring->reg_idx; + if (q_vector->tx.ring) + tx_queue = q_vector->tx.ring->reg_idx; + + switch (hw->mac.type) { + case e1000_82575: + /* The 82575 assigns vectors using a bitmask, which matches the + bitmask for the EICR/EIMS/EIMC registers. To assign one + or more queues to a vector, we write the appropriate bits + into the MSIXBM register for that vector. */ + if (rx_queue > IGB_N0_QUEUE) + msixbm = E1000_EICR_RX_QUEUE0 << rx_queue; + if (tx_queue > IGB_N0_QUEUE) + msixbm |= E1000_EICR_TX_QUEUE0 << tx_queue; + if (!adapter->msix_entries && msix_vector == 0) + msixbm |= E1000_EIMS_OTHER; + array_wr32(E1000_MSIXBM(0), msix_vector, msixbm); + q_vector->eims_value = msixbm; + break; + case e1000_82576: + /* + * 82576 uses a table that essentially consists of 2 columns + * with 8 rows. The ordering is column-major so we use the + * lower 3 bits as the row index, and the 4th bit as the + * column offset. + */ + if (rx_queue > IGB_N0_QUEUE) + igb_write_ivar(hw, msix_vector, + rx_queue & 0x7, + (rx_queue & 0x8) << 1); + if (tx_queue > IGB_N0_QUEUE) + igb_write_ivar(hw, msix_vector, + tx_queue & 0x7, + ((tx_queue & 0x8) << 1) + 8); + q_vector->eims_value = 1 << msix_vector; + break; + case e1000_82580: + case e1000_i350: + /* + * On 82580 and newer adapters the scheme is similar to 82576 + * however instead of ordering column-major we have things + * ordered row-major. So we traverse the table by using + * bit 0 as the column offset, and the remaining bits as the + * row index. + */ + if (rx_queue > IGB_N0_QUEUE) + igb_write_ivar(hw, msix_vector, + rx_queue >> 1, + (rx_queue & 0x1) << 4); + if (tx_queue > IGB_N0_QUEUE) + igb_write_ivar(hw, msix_vector, + tx_queue >> 1, + ((tx_queue & 0x1) << 4) + 8); + q_vector->eims_value = 1 << msix_vector; + break; + default: + BUG(); + break; + } + + /* add q_vector eims value to global eims_enable_mask */ + adapter->eims_enable_mask |= q_vector->eims_value; + + /* configure q_vector to set itr on first interrupt */ + q_vector->set_itr = 1; +} + +/** + * igb_configure_msix - Configure MSI-X hardware + * + * igb_configure_msix sets up the hardware to properly + * generate MSI-X interrupts. + **/ +static void igb_configure_msix(struct igb_adapter *adapter) +{ + u32 tmp; + int i, vector = 0; + struct e1000_hw *hw = &adapter->hw; + + adapter->eims_enable_mask = 0; + + /* set vector for other causes, i.e. link changes */ + switch (hw->mac.type) { + case e1000_82575: + tmp = rd32(E1000_CTRL_EXT); + /* enable MSI-X PBA support*/ + tmp |= E1000_CTRL_EXT_PBA_CLR; + + /* Auto-Mask interrupts upon ICR read. */ + tmp |= E1000_CTRL_EXT_EIAME; + tmp |= E1000_CTRL_EXT_IRCA; + + wr32(E1000_CTRL_EXT, tmp); + + /* enable msix_other interrupt */ + array_wr32(E1000_MSIXBM(0), vector++, + E1000_EIMS_OTHER); + adapter->eims_other = E1000_EIMS_OTHER; + + break; + + case e1000_82576: + case e1000_82580: + case e1000_i350: + /* Turn on MSI-X capability first, or our settings + * won't stick. And it will take days to debug. */ + wr32(E1000_GPIE, E1000_GPIE_MSIX_MODE | + E1000_GPIE_PBA | E1000_GPIE_EIAME | + E1000_GPIE_NSICR); + + /* enable msix_other interrupt */ + adapter->eims_other = 1 << vector; + tmp = (vector++ | E1000_IVAR_VALID) << 8; + + wr32(E1000_IVAR_MISC, tmp); + break; + default: + /* do nothing, since nothing else supports MSI-X */ + break; + } /* switch (hw->mac.type) */ + + adapter->eims_enable_mask |= adapter->eims_other; + + for (i = 0; i < adapter->num_q_vectors; i++) + igb_assign_vector(adapter->q_vector[i], vector++); + + wrfl(); +} + +/** + * igb_request_msix - Initialize MSI-X interrupts + * + * igb_request_msix allocates MSI-X vectors and requests interrupts from the + * kernel. + **/ +static int igb_request_msix(struct igb_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct e1000_hw *hw = &adapter->hw; + int i, err = 0, vector = 0; + + err = request_irq(adapter->msix_entries[vector].vector, + igb_msix_other, 0, netdev->name, adapter); + if (err) + goto out; + vector++; + + for (i = 0; i < adapter->num_q_vectors; i++) { + struct igb_q_vector *q_vector = adapter->q_vector[i]; + + q_vector->itr_register = hw->hw_addr + E1000_EITR(vector); + + if (q_vector->rx.ring && q_vector->tx.ring) + sprintf(q_vector->name, "%s-TxRx-%u", netdev->name, + q_vector->rx.ring->queue_index); + else if (q_vector->tx.ring) + sprintf(q_vector->name, "%s-tx-%u", netdev->name, + q_vector->tx.ring->queue_index); + else if (q_vector->rx.ring) + sprintf(q_vector->name, "%s-rx-%u", netdev->name, + q_vector->rx.ring->queue_index); + else + sprintf(q_vector->name, "%s-unused", netdev->name); + + err = request_irq(adapter->msix_entries[vector].vector, + igb_msix_ring, 0, q_vector->name, + q_vector); + if (err) + goto out; + vector++; + } + + igb_configure_msix(adapter); + return 0; +out: + return err; +} + +static void igb_reset_interrupt_capability(struct igb_adapter *adapter) +{ + if (adapter->msix_entries) { + pci_disable_msix(adapter->pdev); + kfree(adapter->msix_entries); + adapter->msix_entries = NULL; + } else if (adapter->flags & IGB_FLAG_HAS_MSI) { + pci_disable_msi(adapter->pdev); + } +} + +/** + * igb_free_q_vectors - Free memory allocated for interrupt vectors + * @adapter: board private structure to initialize + * + * This function frees the memory allocated to the q_vectors. In addition if + * NAPI is enabled it will delete any references to the NAPI struct prior + * to freeing the q_vector. + **/ +static void igb_free_q_vectors(struct igb_adapter *adapter) +{ + int v_idx; + + for (v_idx = 0; v_idx < adapter->num_q_vectors; v_idx++) { + struct igb_q_vector *q_vector = adapter->q_vector[v_idx]; + adapter->q_vector[v_idx] = NULL; + if (!q_vector) + continue; + netif_napi_del(&q_vector->napi); + kfree(q_vector); + } + adapter->num_q_vectors = 0; +} + +/** + * igb_clear_interrupt_scheme - reset the device to a state of no interrupts + * + * This function resets the device so that it has 0 rx queues, tx queues, and + * MSI-X interrupts allocated. + */ +static void igb_clear_interrupt_scheme(struct igb_adapter *adapter) +{ + igb_free_queues(adapter); + igb_free_q_vectors(adapter); + igb_reset_interrupt_capability(adapter); +} + +/** + * igb_set_interrupt_capability - set MSI or MSI-X if supported + * + * Attempt to configure interrupts using the best available + * capabilities of the hardware and kernel. + **/ +static int igb_set_interrupt_capability(struct igb_adapter *adapter) +{ + int err; + int numvecs, i; + + /* Number of supported queues. */ + adapter->num_rx_queues = adapter->rss_queues; + if (adapter->vfs_allocated_count) + adapter->num_tx_queues = 1; + else + adapter->num_tx_queues = adapter->rss_queues; + + /* start with one vector for every rx queue */ + numvecs = adapter->num_rx_queues; + + /* if tx handler is separate add 1 for every tx queue */ + if (!(adapter->flags & IGB_FLAG_QUEUE_PAIRS)) + numvecs += adapter->num_tx_queues; + + /* store the number of vectors reserved for queues */ + adapter->num_q_vectors = numvecs; + + /* add 1 vector for link status interrupts */ + numvecs++; + adapter->msix_entries = kcalloc(numvecs, sizeof(struct msix_entry), + GFP_KERNEL); + if (!adapter->msix_entries) + goto msi_only; + + for (i = 0; i < numvecs; i++) + adapter->msix_entries[i].entry = i; + + err = pci_enable_msix(adapter->pdev, + adapter->msix_entries, + numvecs); + if (err == 0) + goto out; + + igb_reset_interrupt_capability(adapter); + + /* 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); + wrfl(); + msleep(100); + dev_info(&adapter->pdev->dev, "IOV Disabled\n"); + } +#endif + adapter->vfs_allocated_count = 0; + adapter->rss_queues = 1; + adapter->flags |= IGB_FLAG_QUEUE_PAIRS; + adapter->num_rx_queues = 1; + adapter->num_tx_queues = 1; + adapter->num_q_vectors = 1; + if (!pci_enable_msi(adapter->pdev)) + adapter->flags |= IGB_FLAG_HAS_MSI; +out: + /* Notify the stack of the (possibly) reduced queue counts. */ + netif_set_real_num_tx_queues(adapter->netdev, adapter->num_tx_queues); + return netif_set_real_num_rx_queues(adapter->netdev, + adapter->num_rx_queues); +} + +/** + * igb_alloc_q_vectors - Allocate memory for interrupt vectors + * @adapter: board private structure to initialize + * + * We allocate one q_vector per queue interrupt. If allocation fails we + * return -ENOMEM. + **/ +static int igb_alloc_q_vectors(struct igb_adapter *adapter) +{ + struct igb_q_vector *q_vector; + struct e1000_hw *hw = &adapter->hw; + int v_idx; + int orig_node = adapter->node; + + for (v_idx = 0; v_idx < adapter->num_q_vectors; v_idx++) { + if ((adapter->num_q_vectors == (adapter->num_rx_queues + + adapter->num_tx_queues)) && + (adapter->num_rx_queues == v_idx)) + adapter->node = orig_node; + if (orig_node == -1) { + int cur_node = next_online_node(adapter->node); + if (cur_node == MAX_NUMNODES) + cur_node = first_online_node; + adapter->node = cur_node; + } + q_vector = kzalloc_node(sizeof(struct igb_q_vector), GFP_KERNEL, + adapter->node); + if (!q_vector) + q_vector = kzalloc(sizeof(struct igb_q_vector), + GFP_KERNEL); + if (!q_vector) + goto err_out; + q_vector->adapter = adapter; + q_vector->itr_register = hw->hw_addr + E1000_EITR(0); + q_vector->itr_val = IGB_START_ITR; + netif_napi_add(adapter->netdev, &q_vector->napi, igb_poll, 64); + adapter->q_vector[v_idx] = q_vector; + } + /* Restore the adapter's original node */ + adapter->node = orig_node; + + return 0; + +err_out: + /* Restore the adapter's original node */ + adapter->node = orig_node; + igb_free_q_vectors(adapter); + return -ENOMEM; +} + +static void igb_map_rx_ring_to_vector(struct igb_adapter *adapter, + int ring_idx, int v_idx) +{ + struct igb_q_vector *q_vector = adapter->q_vector[v_idx]; + + q_vector->rx.ring = adapter->rx_ring[ring_idx]; + q_vector->rx.ring->q_vector = q_vector; + q_vector->rx.count++; + q_vector->itr_val = adapter->rx_itr_setting; + if (q_vector->itr_val && q_vector->itr_val <= 3) + q_vector->itr_val = IGB_START_ITR; +} + +static void igb_map_tx_ring_to_vector(struct igb_adapter *adapter, + int ring_idx, int v_idx) +{ + struct igb_q_vector *q_vector = adapter->q_vector[v_idx]; + + q_vector->tx.ring = adapter->tx_ring[ring_idx]; + q_vector->tx.ring->q_vector = q_vector; + q_vector->tx.count++; + q_vector->itr_val = adapter->tx_itr_setting; + q_vector->tx.work_limit = adapter->tx_work_limit; + if (q_vector->itr_val && q_vector->itr_val <= 3) + q_vector->itr_val = IGB_START_ITR; +} + +/** + * igb_map_ring_to_vector - maps allocated queues to vectors + * + * This function maps the recently allocated queues to vectors. + **/ +static int igb_map_ring_to_vector(struct igb_adapter *adapter) +{ + int i; + int v_idx = 0; + + if ((adapter->num_q_vectors < adapter->num_rx_queues) || + (adapter->num_q_vectors < adapter->num_tx_queues)) + return -ENOMEM; + + if (adapter->num_q_vectors >= + (adapter->num_rx_queues + adapter->num_tx_queues)) { + for (i = 0; i < adapter->num_rx_queues; i++) + igb_map_rx_ring_to_vector(adapter, i, v_idx++); + for (i = 0; i < adapter->num_tx_queues; i++) + igb_map_tx_ring_to_vector(adapter, i, v_idx++); + } else { + for (i = 0; i < adapter->num_rx_queues; i++) { + if (i < adapter->num_tx_queues) + igb_map_tx_ring_to_vector(adapter, i, v_idx); + igb_map_rx_ring_to_vector(adapter, i, v_idx++); + } + for (; i < adapter->num_tx_queues; i++) + igb_map_tx_ring_to_vector(adapter, i, v_idx++); + } + return 0; +} + +/** + * igb_init_interrupt_scheme - initialize interrupts, allocate queues/vectors + * + * This function initializes the interrupts and allocates all of the queues. + **/ +static int igb_init_interrupt_scheme(struct igb_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + int err; + + err = igb_set_interrupt_capability(adapter); + if (err) + return err; + + err = igb_alloc_q_vectors(adapter); + if (err) { + dev_err(&pdev->dev, "Unable to allocate memory for vectors\n"); + goto err_alloc_q_vectors; + } + + err = igb_alloc_queues(adapter); + if (err) { + dev_err(&pdev->dev, "Unable to allocate memory for queues\n"); + goto err_alloc_queues; + } + + err = igb_map_ring_to_vector(adapter); + if (err) { + dev_err(&pdev->dev, "Invalid q_vector to ring mapping\n"); + goto err_map_queues; + } + + + return 0; +err_map_queues: + igb_free_queues(adapter); +err_alloc_queues: + igb_free_q_vectors(adapter); +err_alloc_q_vectors: + igb_reset_interrupt_capability(adapter); + return err; +} + +/** + * igb_request_irq - initialize interrupts + * + * Attempts to configure interrupts using the best available + * capabilities of the hardware and kernel. + **/ +static int igb_request_irq(struct igb_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct pci_dev *pdev = adapter->pdev; + int err = 0; + + if (adapter->msix_entries) { + err = igb_request_msix(adapter); + if (!err) + goto request_done; + /* fall back to MSI */ + igb_clear_interrupt_scheme(adapter); + if (!pci_enable_msi(pdev)) + adapter->flags |= IGB_FLAG_HAS_MSI; + igb_free_all_tx_resources(adapter); + igb_free_all_rx_resources(adapter); + adapter->num_tx_queues = 1; + adapter->num_rx_queues = 1; + adapter->num_q_vectors = 1; + err = igb_alloc_q_vectors(adapter); + if (err) { + dev_err(&pdev->dev, + "Unable to allocate memory for vectors\n"); + goto request_done; + } + err = igb_alloc_queues(adapter); + if (err) { + dev_err(&pdev->dev, + "Unable to allocate memory for queues\n"); + igb_free_q_vectors(adapter); + goto request_done; + } + igb_setup_all_tx_resources(adapter); + igb_setup_all_rx_resources(adapter); + } + + igb_assign_vector(adapter->q_vector[0], 0); + + if (adapter->flags & IGB_FLAG_HAS_MSI) { + err = request_irq(pdev->irq, igb_intr_msi, 0, + netdev->name, adapter); + if (!err) + goto request_done; + + /* fall back to legacy interrupts */ + igb_reset_interrupt_capability(adapter); + adapter->flags &= ~IGB_FLAG_HAS_MSI; + } + + err = request_irq(pdev->irq, igb_intr, IRQF_SHARED, + netdev->name, adapter); + + if (err) + dev_err(&pdev->dev, "Error %d getting interrupt\n", + err); + +request_done: + return err; +} + +static void igb_free_irq(struct igb_adapter *adapter) +{ + if (adapter->msix_entries) { + int vector = 0, i; + + free_irq(adapter->msix_entries[vector++].vector, adapter); + + for (i = 0; i < adapter->num_q_vectors; i++) + free_irq(adapter->msix_entries[vector++].vector, + adapter->q_vector[i]); + } else { + free_irq(adapter->pdev->irq, adapter); + } +} + +/** + * igb_irq_disable - Mask off interrupt generation on the NIC + * @adapter: board private structure + **/ +static void igb_irq_disable(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + + /* + * we need to be careful when disabling interrupts. The VFs are also + * mapped into these registers and so clearing the bits can cause + * issues on the VF drivers so we only need to clear what we set + */ + if (adapter->msix_entries) { + 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); + wr32(E1000_IMC, ~0); + wrfl(); + if (adapter->msix_entries) { + int i; + for (i = 0; i < adapter->num_q_vectors; i++) + synchronize_irq(adapter->msix_entries[i].vector); + } else { + synchronize_irq(adapter->pdev->irq); + } +} + +/** + * igb_irq_enable - Enable default interrupt generation settings + * @adapter: board private structure + **/ +static void igb_irq_enable(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + + if (adapter->msix_entries) { + u32 ims = E1000_IMS_LSC | E1000_IMS_DOUTSYNC | E1000_IMS_DRSTA; + 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); + ims |= E1000_IMS_VMMB; + } + wr32(E1000_IMS, ims); + } else { + wr32(E1000_IMS, IMS_ENABLE_MASK | + E1000_IMS_DRSTA); + wr32(E1000_IAM, IMS_ENABLE_MASK | + E1000_IMS_DRSTA); + } +} + +static void igb_update_mng_vlan(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u16 vid = adapter->hw.mng_cookie.vlan_id; + u16 old_vid = adapter->mng_vlan_id; + + if (hw->mng_cookie.status & E1000_MNG_DHCP_COOKIE_STATUS_VLAN) { + /* add VID to filter table */ + igb_vfta_set(hw, vid, true); + adapter->mng_vlan_id = vid; + } else { + adapter->mng_vlan_id = IGB_MNG_VLAN_NONE; + } + + if ((old_vid != (u16)IGB_MNG_VLAN_NONE) && + (vid != old_vid) && + !test_bit(old_vid, adapter->active_vlans)) { + /* remove VID from filter table */ + igb_vfta_set(hw, old_vid, false); + } +} + +/** + * igb_release_hw_control - release control of the h/w to f/w + * @adapter: address of board private structure + * + * igb_release_hw_control resets CTRL_EXT:DRV_LOAD bit. + * For ASF and Pass Through versions of f/w this means that the + * driver is no longer loaded. + * + **/ +static void igb_release_hw_control(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 ctrl_ext; + + /* Let firmware take over control of h/w */ + ctrl_ext = rd32(E1000_CTRL_EXT); + wr32(E1000_CTRL_EXT, + ctrl_ext & ~E1000_CTRL_EXT_DRV_LOAD); +} + +/** + * igb_get_hw_control - get control of the h/w from f/w + * @adapter: address of board private structure + * + * igb_get_hw_control sets CTRL_EXT:DRV_LOAD bit. + * For ASF and Pass Through versions of f/w this means that + * the driver is loaded. + * + **/ +static void igb_get_hw_control(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 ctrl_ext; + + /* Let firmware know the driver has taken over */ + ctrl_ext = rd32(E1000_CTRL_EXT); + wr32(E1000_CTRL_EXT, + ctrl_ext | E1000_CTRL_EXT_DRV_LOAD); +} + +/** + * igb_configure - configure the hardware for RX and TX + * @adapter: private board structure + **/ +static void igb_configure(struct igb_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + int i; + + igb_get_hw_control(adapter); + igb_set_rx_mode(netdev); + + igb_restore_vlan(adapter); + + igb_setup_tctl(adapter); + igb_setup_mrqc(adapter); + igb_setup_rctl(adapter); + + igb_configure_tx(adapter); + igb_configure_rx(adapter); + + igb_rx_fifo_flush_82575(&adapter->hw); + + /* 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(ring, igb_desc_unused(ring)); + } +} + +/** + * igb_power_up_link - Power up the phy/serdes link + * @adapter: address of board private structure + **/ +void igb_power_up_link(struct igb_adapter *adapter) +{ + if (adapter->hw.phy.media_type == e1000_media_type_copper) + igb_power_up_phy_copper(&adapter->hw); + else + igb_power_up_serdes_link_82575(&adapter->hw); +} + +/** + * igb_power_down_link - Power down the phy/serdes link + * @adapter: address of board private structure + */ +static void igb_power_down_link(struct igb_adapter *adapter) +{ + if (adapter->hw.phy.media_type == e1000_media_type_copper) + igb_power_down_phy_copper_82575(&adapter->hw); + else + igb_shutdown_serdes_link_82575(&adapter->hw); +} + +/** + * igb_up - Open the interface and prepare it to handle traffic + * @adapter: board private structure + **/ +int igb_up(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + int i; + + /* hardware has been reset, we need to reload some things */ + igb_configure(adapter); + + clear_bit(__IGB_DOWN, &adapter->state); + + for (i = 0; i < adapter->num_q_vectors; i++) + napi_enable(&(adapter->q_vector[i]->napi)); + + if (adapter->msix_entries) + igb_configure_msix(adapter); + else + igb_assign_vector(adapter->q_vector[0], 0); + + /* Clear any pending interrupts. */ + rd32(E1000_ICR); + igb_irq_enable(adapter); + + /* notify VFs that reset has been completed */ + if (adapter->vfs_allocated_count) { + u32 reg_data = rd32(E1000_CTRL_EXT); + reg_data |= E1000_CTRL_EXT_PFRSTD; + wr32(E1000_CTRL_EXT, reg_data); + } + + netif_tx_start_all_queues(adapter->netdev); + + /* start the watchdog. */ + hw->mac.get_link_status = 1; + schedule_work(&adapter->watchdog_task); + + return 0; +} + +void igb_down(struct igb_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct e1000_hw *hw = &adapter->hw; + u32 tctl, rctl; + int i; + + /* signal that we're down so the interrupt handler does not + * reschedule our watchdog timer */ + set_bit(__IGB_DOWN, &adapter->state); + + /* disable receives in the hardware */ + rctl = rd32(E1000_RCTL); + wr32(E1000_RCTL, rctl & ~E1000_RCTL_EN); + /* flush and sleep below */ + + netif_tx_stop_all_queues(netdev); + + /* disable transmits in the hardware */ + tctl = rd32(E1000_TCTL); + tctl &= ~E1000_TCTL_EN; + wr32(E1000_TCTL, tctl); + /* flush both disables and wait for them to finish */ + wrfl(); + msleep(10); + + for (i = 0; i < adapter->num_q_vectors; i++) + napi_disable(&(adapter->q_vector[i]->napi)); + + igb_irq_disable(adapter); + + del_timer_sync(&adapter->watchdog_timer); + del_timer_sync(&adapter->phy_info_timer); + + netif_carrier_off(netdev); + + /* record the stats before reset*/ + spin_lock(&adapter->stats64_lock); + igb_update_stats(adapter, &adapter->stats64); + spin_unlock(&adapter->stats64_lock); + + adapter->link_speed = 0; + adapter->link_duplex = 0; + + if (!pci_channel_offline(adapter->pdev)) + 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) +{ + WARN_ON(in_interrupt()); + while (test_and_set_bit(__IGB_RESETTING, &adapter->state)) + msleep(1); + igb_down(adapter); + igb_up(adapter); + clear_bit(__IGB_RESETTING, &adapter->state); +} + +void igb_reset(struct igb_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + struct e1000_hw *hw = &adapter->hw; + struct e1000_mac_info *mac = &hw->mac; + struct e1000_fc_info *fc = &hw->fc; + u32 pba = 0, tx_space, min_tx_space, min_rx_space; + u16 hwm; + + /* Repartition Pba for greater than 9k mtu + * To take effect CTRL.RST is required. + */ + switch (mac->type) { + case e1000_i350: + case e1000_82580: + pba = rd32(E1000_RXPBS); + pba = igb_rxpbs_adjust_82580(pba); + break; + case e1000_82576: + pba = rd32(E1000_RXPBS); + pba &= E1000_RXPBS_SIZE_MASK_82576; + break; + case e1000_82575: + default: + pba = E1000_PBA_34K; + break; + } + + if ((adapter->max_frame_size > ETH_FRAME_LEN + ETH_FCS_LEN) && + (mac->type < e1000_82576)) { + /* adjust PBA for jumbo frames */ + wr32(E1000_PBA, pba); + + /* To maintain wire speed transmits, the Tx FIFO should be + * large enough to accommodate two full transmit packets, + * rounded up to the next 1KB and expressed in KB. Likewise, + * the Rx FIFO should be large enough to accommodate at least + * one full receive packet and is similarly rounded up and + * expressed in KB. */ + pba = rd32(E1000_PBA); + /* upper 16 bits has Tx packet buffer allocation size in KB */ + tx_space = pba >> 16; + /* lower 16 bits has Rx packet buffer allocation size in KB */ + pba &= 0xffff; + /* the tx fifo also stores 16 bytes of information about the tx + * but don't include ethernet FCS because hardware appends it */ + min_tx_space = (adapter->max_frame_size + + sizeof(union e1000_adv_tx_desc) - + ETH_FCS_LEN) * 2; + min_tx_space = ALIGN(min_tx_space, 1024); + min_tx_space >>= 10; + /* software strips receive CRC, so leave room for it */ + min_rx_space = adapter->max_frame_size; + min_rx_space = ALIGN(min_rx_space, 1024); + min_rx_space >>= 10; + + /* If current Tx allocation is less than the min Tx FIFO size, + * and the min Tx FIFO size is less than the current Rx FIFO + * allocation, take space away from current Rx allocation */ + if (tx_space < min_tx_space && + ((min_tx_space - tx_space) < pba)) { + pba = pba - (min_tx_space - tx_space); + + /* if short on rx space, rx wins and must trump tx + * adjustment */ + if (pba < min_rx_space) + pba = min_rx_space; + } + wr32(E1000_PBA, pba); + } + + /* flow control settings */ + /* The high water mark must be low enough to fit one full frame + * (or the size used for early receive) above it in the Rx FIFO. + * Set it to the lower of: + * - 90% of the Rx FIFO size, or + * - the full Rx FIFO size minus one full frame */ + hwm = min(((pba << 10) * 9 / 10), + ((pba << 10) - 2 * adapter->max_frame_size)); + + fc->high_water = hwm & 0xFFF0; /* 16-byte granularity */ + fc->low_water = fc->high_water - 16; + fc->pause_time = 0xFFFF; + fc->send_xon = 1; + fc->current_mode = fc->requested_mode; + + /* disable receive for all VFs and wait one second */ + if (adapter->vfs_allocated_count) { + int i; + for (i = 0 ; i < adapter->vfs_allocated_count; i++) + adapter->vf_data[i].flags &= IGB_VF_FLAG_PF_SET_MAC; + + /* ping all the active vfs to let them know we are going down */ + igb_ping_all_vfs(adapter); + + /* disable transmits and receives */ + wr32(E1000_VFRE, 0); + wr32(E1000_VFTE, 0); + } + + /* Allow time for pending master requests to run */ + hw->mac.ops.reset_hw(hw); + wr32(E1000_WUC, 0); + + if (hw->mac.ops.init_hw(hw)) + dev_err(&pdev->dev, "Hardware Error\n"); + + igb_init_dmac(adapter, pba); + if (!netif_running(adapter->netdev)) + igb_power_down_link(adapter); + + igb_update_mng_vlan(adapter); + + /* Enable h/w to recognize an 802.1Q VLAN Ethernet packet */ + wr32(E1000_VET, ETHERNET_IEEE_VLAN_TYPE); + + igb_get_phy_info(hw); +} + +static u32 igb_fix_features(struct net_device *netdev, u32 features) +{ + /* + * Since there is no support for separate rx/tx vlan accel + * enable/disable make sure tx flag is always in same state as rx. + */ + if (features & NETIF_F_HW_VLAN_RX) + features |= NETIF_F_HW_VLAN_TX; + else + features &= ~NETIF_F_HW_VLAN_TX; + + return features; +} + +static int igb_set_features(struct net_device *netdev, u32 features) +{ + u32 changed = netdev->features ^ features; + + if (changed & NETIF_F_HW_VLAN_RX) + igb_vlan_mode(netdev, features); + + return 0; +} + +static const struct net_device_ops igb_netdev_ops = { + .ndo_open = igb_open, + .ndo_stop = igb_close, + .ndo_start_xmit = igb_xmit_frame, + .ndo_get_stats64 = igb_get_stats64, + .ndo_set_rx_mode = igb_set_rx_mode, + .ndo_set_mac_address = igb_set_mac, + .ndo_change_mtu = igb_change_mtu, + .ndo_do_ioctl = igb_ioctl, + .ndo_tx_timeout = igb_tx_timeout, + .ndo_validate_addr = eth_validate_addr, + .ndo_vlan_rx_add_vid = igb_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = igb_vlan_rx_kill_vid, + .ndo_set_vf_mac = igb_ndo_set_vf_mac, + .ndo_set_vf_vlan = igb_ndo_set_vf_vlan, + .ndo_set_vf_tx_rate = igb_ndo_set_vf_bw, + .ndo_get_vf_config = igb_ndo_get_vf_config, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = igb_netpoll, +#endif + .ndo_fix_features = igb_fix_features, + .ndo_set_features = igb_set_features, +}; + +/** + * igb_probe - Device Initialization Routine + * @pdev: PCI device information struct + * @ent: entry in igb_pci_tbl + * + * Returns 0 on success, negative on failure + * + * igb_probe initializes an adapter identified by a pci_dev structure. + * The OS initialization, configuring of the adapter private structure, + * and a hardware reset occur. + **/ +static int __devinit igb_probe(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + struct net_device *netdev; + struct igb_adapter *adapter; + struct e1000_hw *hw; + u16 eeprom_data = 0; + s32 ret_val; + static int global_quad_port_a; /* global quad port a indication */ + const struct e1000_info *ei = igb_info_tbl[ent->driver_data]; + unsigned long mmio_start, mmio_len; + int err, pci_using_dac; + u16 eeprom_apme_mask = IGB_EEPROM_APME; + u8 part_str[E1000_PBANUM_LENGTH]; + + /* Catch broken hardware that put the wrong VF device ID in + * the PCIe SR-IOV capability. + */ + if (pdev->is_virtfn) { + WARN(1, KERN_ERR "%s (%hx:%hx) should not be a VF!\n", + pci_name(pdev), pdev->vendor, pdev->device); + return -EINVAL; + } + + err = pci_enable_device_mem(pdev); + if (err) + return err; + + pci_using_dac = 0; + err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)); + if (!err) { + err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64)); + if (!err) + pci_using_dac = 1; + } else { + err = dma_set_mask(&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; + } + } + } + + err = pci_request_selected_regions(pdev, pci_select_bars(pdev, + IORESOURCE_MEM), + igb_driver_name); + if (err) + goto err_pci_reg; + + pci_enable_pcie_error_reporting(pdev); + + pci_set_master(pdev); + pci_save_state(pdev); + + err = -ENOMEM; + netdev = alloc_etherdev_mq(sizeof(struct igb_adapter), + IGB_MAX_TX_QUEUES); + if (!netdev) + goto err_alloc_etherdev; + + SET_NETDEV_DEV(netdev, &pdev->dev); + + pci_set_drvdata(pdev, netdev); + adapter = netdev_priv(netdev); + adapter->netdev = netdev; + adapter->pdev = pdev; + hw = &adapter->hw; + hw->back = adapter; + adapter->msg_enable = NETIF_MSG_DRV | NETIF_MSG_PROBE; + + mmio_start = pci_resource_start(pdev, 0); + mmio_len = pci_resource_len(pdev, 0); + + err = -EIO; + hw->hw_addr = ioremap(mmio_start, mmio_len); + if (!hw->hw_addr) + goto err_ioremap; + + netdev->netdev_ops = &igb_netdev_ops; + igb_set_ethtool_ops(netdev); + netdev->watchdog_timeo = 5 * HZ; + + strncpy(netdev->name, pci_name(pdev), sizeof(netdev->name) - 1); + + netdev->mem_start = mmio_start; + netdev->mem_end = mmio_start + mmio_len; + + /* PCI config space info */ + hw->vendor_id = pdev->vendor; + hw->device_id = pdev->device; + hw->revision_id = pdev->revision; + hw->subsystem_vendor_id = pdev->subsystem_vendor; + hw->subsystem_device_id = pdev->subsystem_device; + + /* Copy the default MAC, PHY and NVM function pointers */ + memcpy(&hw->mac.ops, ei->mac_ops, sizeof(hw->mac.ops)); + memcpy(&hw->phy.ops, ei->phy_ops, sizeof(hw->phy.ops)); + memcpy(&hw->nvm.ops, ei->nvm_ops, sizeof(hw->nvm.ops)); + /* Initialize skew-specific constants */ + err = ei->get_invariants(hw); + if (err) + goto err_sw_init; + + /* setup the private structure */ + err = igb_sw_init(adapter); + if (err) + goto err_sw_init; + + igb_get_bus_info_pcie(hw); + + hw->phy.autoneg_wait_to_complete = false; + + /* Copper options */ + if (hw->phy.media_type == e1000_media_type_copper) { + hw->phy.mdix = AUTO_ALL_MODES; + hw->phy.disable_polarity_correction = false; + hw->phy.ms_type = e1000_ms_hw_default; + } + + if (igb_check_reset_block(hw)) + dev_info(&pdev->dev, + "PHY reset is blocked due to SOL/IDER session.\n"); + + /* + * features is initialized to 0 in allocation, it might have bits + * set by igb_sw_init so we should use an or instead of an + * assignment. + */ + netdev->features |= NETIF_F_SG | + NETIF_F_IP_CSUM | + NETIF_F_IPV6_CSUM | + NETIF_F_TSO | + NETIF_F_TSO6 | + NETIF_F_RXHASH | + NETIF_F_RXCSUM | + NETIF_F_HW_VLAN_RX | + NETIF_F_HW_VLAN_TX; + + /* copy netdev features into list of user selectable features */ + netdev->hw_features |= netdev->features; + + /* set this bit last since it cannot be part of hw_features */ + netdev->features |= NETIF_F_HW_VLAN_FILTER; + + netdev->vlan_features |= NETIF_F_TSO | + NETIF_F_TSO6 | + NETIF_F_IP_CSUM | + NETIF_F_IPV6_CSUM | + NETIF_F_SG; + + if (pci_using_dac) { + netdev->features |= NETIF_F_HIGHDMA; + netdev->vlan_features |= NETIF_F_HIGHDMA; + } + + if (hw->mac.type >= e1000_82576) { + netdev->hw_features |= NETIF_F_SCTP_CSUM; + netdev->features |= NETIF_F_SCTP_CSUM; + } + + netdev->priv_flags |= IFF_UNICAST_FLT; + + adapter->en_mng_pt = igb_enable_mng_pass_thru(hw); + + /* before reading the NVM, reset the controller to put the device in a + * known good starting state */ + hw->mac.ops.reset_hw(hw); + + /* make sure the NVM is good */ + if (hw->nvm.ops.validate(hw) < 0) { + dev_err(&pdev->dev, "The NVM Checksum Is Not Valid\n"); + err = -EIO; + goto err_eeprom; + } + + /* copy the MAC address out of the NVM */ + if (hw->mac.ops.read_mac_addr(hw)) + dev_err(&pdev->dev, "NVM Read Error\n"); + + memcpy(netdev->dev_addr, hw->mac.addr, netdev->addr_len); + memcpy(netdev->perm_addr, hw->mac.addr, netdev->addr_len); + + if (!is_valid_ether_addr(netdev->perm_addr)) { + dev_err(&pdev->dev, "Invalid MAC Address\n"); + err = -EIO; + goto err_eeprom; + } + + 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); + + /* Initialize link properties that are user-changeable */ + adapter->fc_autoneg = true; + hw->mac.autoneg = true; + hw->phy.autoneg_advertised = 0x2f; + + hw->fc.requested_mode = e1000_fc_default; + hw->fc.current_mode = e1000_fc_default; + + igb_validate_mdi_setting(hw); + + /* 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->nvm.ops.read(hw, NVM_INIT_CONTROL3_PORT_A, 1, &eeprom_data); + else if (hw->mac.type >= e1000_82580) + hw->nvm.ops.read(hw, NVM_INIT_CONTROL3_PORT_A + + NVM_82580_LAN_FUNC_OFFSET(hw->bus.func), 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; + + /* now that we have the eeprom settings, apply the special cases where + * the eeprom may be wrong or the board simply won't support wake on + * lan on a particular port */ + switch (pdev->device) { + case E1000_DEV_ID_82575GB_QUAD_COPPER: + adapter->eeprom_wol = 0; + break; + case E1000_DEV_ID_82575EB_FIBER_SERDES: + case E1000_DEV_ID_82576_FIBER: + case E1000_DEV_ID_82576_SERDES: + /* Wake events only supported on port A for dual fiber + * regardless of eeprom setting */ + if (rd32(E1000_STATUS) & E1000_STATUS_FUNC_1) + adapter->eeprom_wol = 0; + break; + case E1000_DEV_ID_82576_QUAD_COPPER: + case E1000_DEV_ID_82576_QUAD_COPPER_ET2: + /* 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 */ + adapter->wol = adapter->eeprom_wol; + device_set_wakeup_enable(&adapter->pdev->dev, adapter->wol); + + /* reset the hardware with the new settings */ + igb_reset(adapter); + + /* let the f/w know that the h/w is now under the control of the + * driver. */ + igb_get_hw_control(adapter); + + strcpy(netdev->name, "eth%d"); + err = register_netdev(netdev); + if (err) + goto err_register; + + /* carrier off reporting is important to ethtool even BEFORE open */ + netif_carrier_off(netdev); + +#ifdef CONFIG_IGB_DCA + if (dca_add_requester(&pdev->dev) == 0) { + adapter->flags |= IGB_FLAG_DCA_ENABLED; + dev_info(&pdev->dev, "DCA enabled\n"); + igb_setup_dca(adapter); + } + +#endif + /* do hw tstamp init after resetting */ + igb_init_hw_timer(adapter); + + dev_info(&pdev->dev, "Intel(R) Gigabit Ethernet Network Connection\n"); + /* print bus type/speed/width info */ + dev_info(&pdev->dev, "%s: (PCIe:%s:%s) %pM\n", + netdev->name, + ((hw->bus.speed == e1000_bus_speed_2500) ? "2.5Gb/s" : + (hw->bus.speed == e1000_bus_speed_5000) ? "5.0Gb/s" : + "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); + + ret_val = igb_read_part_string(hw, part_str, E1000_PBANUM_LENGTH); + if (ret_val) + strcpy(part_str, "Unknown"); + dev_info(&pdev->dev, "%s: PBA No: %s\n", netdev->name, part_str); + dev_info(&pdev->dev, + "Using %s interrupts. %d rx queue(s), %d tx queue(s)\n", + adapter->msix_entries ? "MSI-X" : + (adapter->flags & IGB_FLAG_HAS_MSI) ? "MSI" : "legacy", + adapter->num_rx_queues, adapter->num_tx_queues); + switch (hw->mac.type) { + case e1000_i350: + igb_set_eee_i350(hw); + break; + default: + break; + } + return 0; + +err_register: + igb_release_hw_control(adapter); +err_eeprom: + if (!igb_check_reset_block(hw)) + igb_reset_phy(hw); + + if (hw->flash_address) + iounmap(hw->flash_address); +err_sw_init: + igb_clear_interrupt_scheme(adapter); + iounmap(hw->hw_addr); +err_ioremap: + free_netdev(netdev); +err_alloc_etherdev: + pci_release_selected_regions(pdev, + pci_select_bars(pdev, IORESOURCE_MEM)); +err_pci_reg: +err_dma: + pci_disable_device(pdev); + return err; +} + +/** + * igb_remove - Device Removal Routine + * @pdev: PCI device information struct + * + * igb_remove is called by the PCI subsystem to alert the driver + * that it should release a PCI device. The could be caused by a + * Hot-Plug event, or because the driver is going to be removed from + * memory. + **/ +static void __devexit igb_remove(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + + /* + * The watchdog timer may be rescheduled, so explicitly + * disable watchdog from being rescheduled. + */ + set_bit(__IGB_DOWN, &adapter->state); + del_timer_sync(&adapter->watchdog_timer); + del_timer_sync(&adapter->phy_info_timer); + + cancel_work_sync(&adapter->reset_task); + cancel_work_sync(&adapter->watchdog_task); + +#ifdef CONFIG_IGB_DCA + if (adapter->flags & IGB_FLAG_DCA_ENABLED) { + dev_info(&pdev->dev, "DCA disabled\n"); + dca_remove_requester(&pdev->dev); + adapter->flags &= ~IGB_FLAG_DCA_ENABLED; + wr32(E1000_DCA_CTRL, E1000_DCA_CTRL_DCA_MODE_DISABLE); + } +#endif + + /* Release control of h/w to f/w. If f/w is AMT enabled, this + * would have already happened in close and is redundant. */ + igb_release_hw_control(adapter); + + unregister_netdev(netdev); + + igb_clear_interrupt_scheme(adapter); + +#ifdef CONFIG_PCI_IOV + /* reclaim resources allocated to VFs */ + if (adapter->vf_data) { + /* disable iov and allow time for transactions to clear */ + if (!igb_check_vf_assignment(adapter)) { + pci_disable_sriov(pdev); + msleep(500); + } else { + dev_info(&pdev->dev, "VF(s) assigned to guests!\n"); + } + + kfree(adapter->vf_data); + adapter->vf_data = NULL; + wr32(E1000_IOVCTL, E1000_IOVCTL_REUSE_VFQ); + wrfl(); + msleep(100); + dev_info(&pdev->dev, "IOV Disabled\n"); + } +#endif + + iounmap(hw->hw_addr); + if (hw->flash_address) + iounmap(hw->flash_address); + pci_release_selected_regions(pdev, + pci_select_bars(pdev, IORESOURCE_MEM)); + + kfree(adapter->shadow_vfta); + free_netdev(netdev); + + pci_disable_pcie_error_reporting(pdev); + + pci_disable_device(pdev); +} + +/** + * igb_probe_vfs - Initialize vf data storage and add VFs to pci config space + * @adapter: board private structure to initialize + * + * This function initializes the vf specific data storage and then attempts to + * allocate the VFs. The reason for ordering it this way is because it is much + * mor expensive time wise to disable SR-IOV than it is to allocate and free + * the memory for the VFs. + **/ +static void __devinit igb_probe_vfs(struct igb_adapter * adapter) +{ +#ifdef CONFIG_PCI_IOV + struct pci_dev *pdev = adapter->pdev; + int old_vfs = igb_find_enabled_vfs(adapter); + int i; + + if (old_vfs) { + dev_info(&pdev->dev, "%d pre-allocated VFs found - override " + "max_vfs setting of %d\n", old_vfs, max_vfs); + adapter->vfs_allocated_count = old_vfs; + } + + if (!adapter->vfs_allocated_count) + return; + + adapter->vf_data = kcalloc(adapter->vfs_allocated_count, + sizeof(struct vf_data_storage), GFP_KERNEL); + /* if allocation failed then we do not support SR-IOV */ + if (!adapter->vf_data) { + adapter->vfs_allocated_count = 0; + dev_err(&pdev->dev, "Unable to allocate memory for VF " + "Data Storage\n"); + goto out; + } + + if (!old_vfs) { + if (pci_enable_sriov(pdev, adapter->vfs_allocated_count)) + goto err_out; + } + dev_info(&pdev->dev, "%d VFs allocated\n", + adapter->vfs_allocated_count); + for (i = 0; i < adapter->vfs_allocated_count; i++) + igb_vf_configure(adapter, i); + + /* DMA Coalescing is not supported in IOV mode. */ + adapter->flags &= ~IGB_FLAG_DMAC; + goto out; +err_out: + kfree(adapter->vf_data); + adapter->vf_data = NULL; + adapter->vfs_allocated_count = 0; +out: + return; +#endif /* CONFIG_PCI_IOV */ +} + +/** + * igb_init_hw_timer - Initialize hardware timer used with IEEE 1588 timestamp + * @adapter: board private structure to initialize + * + * igb_init_hw_timer initializes the function pointer and values for the hw + * timer found in hardware. + **/ +static void igb_init_hw_timer(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + + switch (hw->mac.type) { + case e1000_i350: + case e1000_82580: + memset(&adapter->cycles, 0, sizeof(adapter->cycles)); + adapter->cycles.read = igb_read_clock; + adapter->cycles.mask = CLOCKSOURCE_MASK(64); + adapter->cycles.mult = 1; + /* + * The 82580 timesync updates the system timer every 8ns by 8ns + * and the value cannot be shifted. Instead we need to shift + * the registers to generate a 64bit timer value. As a result + * SYSTIMR/L/H, TXSTMPL/H, RXSTMPL/H all have to be shifted by + * 24 in order to generate a larger value for synchronization. + */ + adapter->cycles.shift = IGB_82580_TSYNC_SHIFT; + /* disable system timer temporarily by setting bit 31 */ + wr32(E1000_TSAUXC, 0x80000000); + wrfl(); + + /* Set registers so that rollover occurs soon to test this. */ + wr32(E1000_SYSTIMR, 0x00000000); + wr32(E1000_SYSTIML, 0x80000000); + wr32(E1000_SYSTIMH, 0x000000FF); + wrfl(); + + /* enable system timer by clearing bit 31 */ + wr32(E1000_TSAUXC, 0x0); + wrfl(); + + timecounter_init(&adapter->clock, + &adapter->cycles, + ktime_to_ns(ktime_get_real())); + /* + * Synchronize our NIC clock against system wall clock. NIC + * time stamp reading requires ~3us per sample, each sample + * was pretty stable even under load => only require 10 + * samples for each offset comparison. + */ + memset(&adapter->compare, 0, sizeof(adapter->compare)); + adapter->compare.source = &adapter->clock; + adapter->compare.target = ktime_get_real; + adapter->compare.num_samples = 10; + timecompare_update(&adapter->compare, 0); + break; + case e1000_82576: + /* + * Initialize hardware timer: we keep it running just in case + * that some program needs it later on. + */ + memset(&adapter->cycles, 0, sizeof(adapter->cycles)); + adapter->cycles.read = igb_read_clock; + adapter->cycles.mask = CLOCKSOURCE_MASK(64); + adapter->cycles.mult = 1; + /** + * Scale the NIC clock cycle by a large factor so that + * relatively small clock corrections can be added or + * subtracted at each clock tick. The drawbacks of a large + * factor are a) that the clock register overflows more quickly + * (not such a big deal) and b) that the increment per tick has + * to fit into 24 bits. As a result we need to use a shift of + * 19 so we can fit a value of 16 into the TIMINCA register. + */ + adapter->cycles.shift = IGB_82576_TSYNC_SHIFT; + wr32(E1000_TIMINCA, + (1 << E1000_TIMINCA_16NS_SHIFT) | + (16 << IGB_82576_TSYNC_SHIFT)); + + /* Set registers so that rollover occurs soon to test this. */ + wr32(E1000_SYSTIML, 0x00000000); + wr32(E1000_SYSTIMH, 0xFF800000); + wrfl(); + + timecounter_init(&adapter->clock, + &adapter->cycles, + ktime_to_ns(ktime_get_real())); + /* + * Synchronize our NIC clock against system wall clock. NIC + * time stamp reading requires ~3us per sample, each sample + * was pretty stable even under load => only require 10 + * samples for each offset comparison. + */ + memset(&adapter->compare, 0, sizeof(adapter->compare)); + adapter->compare.source = &adapter->clock; + adapter->compare.target = ktime_get_real; + adapter->compare.num_samples = 10; + timecompare_update(&adapter->compare, 0); + break; + case e1000_82575: + /* 82575 does not support timesync */ + default: + break; + } + +} + +/** + * igb_sw_init - Initialize general software structures (struct igb_adapter) + * @adapter: board private structure to initialize + * + * igb_sw_init initializes the Adapter private data structure. + * Fields are initialized based on PCI device information and + * OS network device settings (MTU size). + **/ +static int __devinit igb_sw_init(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; + struct pci_dev *pdev = adapter->pdev; + + pci_read_config_word(pdev, PCI_COMMAND, &hw->bus.pci_cmd_word); + + /* set default ring sizes */ + adapter->tx_ring_count = IGB_DEFAULT_TXD; + adapter->rx_ring_count = IGB_DEFAULT_RXD; + + /* set default ITR values */ + adapter->rx_itr_setting = IGB_DEFAULT_ITR; + adapter->tx_itr_setting = IGB_DEFAULT_ITR; + + /* set default work limits */ + adapter->tx_work_limit = IGB_DEFAULT_TX_WORK; + + adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN + + VLAN_HLEN; + adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN; + + adapter->node = -1; + + spin_lock_init(&adapter->stats64_lock); +#ifdef CONFIG_PCI_IOV + switch (hw->mac.type) { + case e1000_82576: + case e1000_i350: + if (max_vfs > 7) { + dev_warn(&pdev->dev, + "Maximum of 7 VFs per PF, using max\n"); + adapter->vfs_allocated_count = 7; + } else + adapter->vfs_allocated_count = max_vfs; + break; + default: + break; + } +#endif /* CONFIG_PCI_IOV */ + adapter->rss_queues = min_t(u32, IGB_MAX_RX_QUEUES, num_online_cpus()); + /* i350 cannot do RSS and SR-IOV at the same time */ + if (hw->mac.type == e1000_i350 && adapter->vfs_allocated_count) + adapter->rss_queues = 1; + + /* + * if rss_queues > 4 or vfs are going to be allocated with rss_queues + * then we should combine the queues into a queue pair in order to + * conserve interrupts due to limited supply + */ + if ((adapter->rss_queues > 4) || + ((adapter->rss_queues > 1) && (adapter->vfs_allocated_count > 6))) + adapter->flags |= IGB_FLAG_QUEUE_PAIRS; + + /* Setup and initialize a copy of the hw vlan table array */ + adapter->shadow_vfta = kzalloc(sizeof(u32) * + E1000_VLAN_FILTER_TBL_SIZE, + GFP_ATOMIC); + + /* This call may decrease the number of queues */ + if (igb_init_interrupt_scheme(adapter)) { + dev_err(&pdev->dev, "Unable to allocate memory for queues\n"); + return -ENOMEM; + } + + igb_probe_vfs(adapter); + + /* Explicitly disable IRQ since the NIC can be in any state. */ + igb_irq_disable(adapter); + + if (hw->mac.type == e1000_i350) + adapter->flags &= ~IGB_FLAG_DMAC; + + set_bit(__IGB_DOWN, &adapter->state); + return 0; +} + +/** + * igb_open - Called when a network interface is made active + * @netdev: network interface device structure + * + * Returns 0 on success, negative value on failure + * + * The open entry point is called when a network interface is made + * active by the system (IFF_UP). At this point all resources needed + * for transmit and receive operations are allocated, the interrupt + * handler is registered with the OS, the watchdog timer is started, + * and the stack is notified that the interface is ready. + **/ +static int igb_open(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + int err; + int i; + + /* disallow open during test */ + 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) + goto err_setup_tx; + + /* allocate receive descriptors */ + err = igb_setup_all_rx_resources(adapter); + if (err) + goto err_setup_rx; + + igb_power_up_link(adapter); + + /* before we allocate an interrupt, we must be ready to handle it. + * Setting DEBUG_SHIRQ in the kernel makes it fire an interrupt + * as soon as we call pci_request_irq, so we have to setup our + * clean_rx handler before we do so. */ + igb_configure(adapter); + + err = igb_request_irq(adapter); + if (err) + goto err_req_irq; + + /* From here on the code is the same as igb_up() */ + clear_bit(__IGB_DOWN, &adapter->state); + + for (i = 0; i < adapter->num_q_vectors; i++) + napi_enable(&(adapter->q_vector[i]->napi)); + + /* Clear any pending interrupts. */ + rd32(E1000_ICR); + + igb_irq_enable(adapter); + + /* notify VFs that reset has been completed */ + if (adapter->vfs_allocated_count) { + u32 reg_data = rd32(E1000_CTRL_EXT); + reg_data |= E1000_CTRL_EXT_PFRSTD; + wr32(E1000_CTRL_EXT, reg_data); + } + + netif_tx_start_all_queues(netdev); + + /* start the watchdog. */ + hw->mac.get_link_status = 1; + schedule_work(&adapter->watchdog_task); + + return 0; + +err_req_irq: + igb_release_hw_control(adapter); + igb_power_down_link(adapter); + igb_free_all_rx_resources(adapter); +err_setup_rx: + igb_free_all_tx_resources(adapter); +err_setup_tx: + igb_reset(adapter); + + return err; +} + +/** + * igb_close - Disables a network interface + * @netdev: network interface device structure + * + * Returns 0, this is not allowed to fail + * + * The close entry point is called when an interface is de-activated + * by the OS. The hardware is still under the driver's control, but + * needs to be disabled. A global MAC reset is issued to stop the + * hardware, and all transmit and receive resources are freed. + **/ +static int igb_close(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + + WARN_ON(test_bit(__IGB_RESETTING, &adapter->state)); + igb_down(adapter); + + igb_free_irq(adapter); + + igb_free_all_tx_resources(adapter); + igb_free_all_rx_resources(adapter); + + return 0; +} + +/** + * igb_setup_tx_resources - allocate Tx resources (Descriptors) + * @tx_ring: tx descriptor ring (for a specific queue) to setup + * + * Return 0 on success, negative on failure + **/ +int igb_setup_tx_resources(struct igb_ring *tx_ring) +{ + struct device *dev = tx_ring->dev; + int orig_node = dev_to_node(dev); + int size; + + size = sizeof(struct igb_tx_buffer) * tx_ring->count; + tx_ring->tx_buffer_info = vzalloc_node(size, tx_ring->numa_node); + if (!tx_ring->tx_buffer_info) + tx_ring->tx_buffer_info = vzalloc(size); + if (!tx_ring->tx_buffer_info) + goto err; + + /* round up to nearest 4K */ + tx_ring->size = tx_ring->count * sizeof(union e1000_adv_tx_desc); + tx_ring->size = ALIGN(tx_ring->size, 4096); + + set_dev_node(dev, tx_ring->numa_node); + tx_ring->desc = dma_alloc_coherent(dev, + tx_ring->size, + &tx_ring->dma, + GFP_KERNEL); + set_dev_node(dev, orig_node); + if (!tx_ring->desc) + tx_ring->desc = dma_alloc_coherent(dev, + tx_ring->size, + &tx_ring->dma, + GFP_KERNEL); + + if (!tx_ring->desc) + goto err; + + tx_ring->next_to_use = 0; + tx_ring->next_to_clean = 0; + + return 0; + +err: + vfree(tx_ring->tx_buffer_info); + dev_err(dev, + "Unable to allocate memory for the transmit descriptor ring\n"); + return -ENOMEM; +} + +/** + * igb_setup_all_tx_resources - wrapper to allocate Tx resources + * (Descriptors) for all queues + * @adapter: board private structure + * + * Return 0 on success, negative on failure + **/ +static int igb_setup_all_tx_resources(struct igb_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + int i, err = 0; + + for (i = 0; i < adapter->num_tx_queues; i++) { + err = igb_setup_tx_resources(adapter->tx_ring[i]); + if (err) { + dev_err(&pdev->dev, + "Allocation for Tx Queue %u failed\n", i); + for (i--; i >= 0; i--) + igb_free_tx_resources(adapter->tx_ring[i]); + break; + } + } + + return err; +} + +/** + * igb_setup_tctl - configure the transmit control registers + * @adapter: Board private structure + **/ +void igb_setup_tctl(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 tctl; + + /* disable queue 0 which is enabled by default on 82575 and 82576 */ + wr32(E1000_TXDCTL(0), 0); + + /* Program the Transmit Control Register */ + tctl = rd32(E1000_TCTL); + tctl &= ~E1000_TCTL_CT; + tctl |= E1000_TCTL_PSP | E1000_TCTL_RTLC | + (E1000_COLLISION_THRESHOLD << E1000_CT_SHIFT); + + igb_config_collision_dist(hw); + + /* Enable transmits */ + tctl |= E1000_TCTL_EN; + + wr32(E1000_TCTL, tctl); +} + +/** + * igb_configure_tx_ring - Configure transmit ring after Reset + * @adapter: board private structure + * @ring: tx ring to configure + * + * Configure a transmit ring after a reset. + **/ +void igb_configure_tx_ring(struct igb_adapter *adapter, + struct igb_ring *ring) +{ + struct e1000_hw *hw = &adapter->hw; + u32 txdctl = 0; + u64 tdba = ring->dma; + int reg_idx = ring->reg_idx; + + /* disable the queue */ + wr32(E1000_TXDCTL(reg_idx), 0); + wrfl(); + mdelay(10); + + wr32(E1000_TDLEN(reg_idx), + ring->count * sizeof(union e1000_adv_tx_desc)); + wr32(E1000_TDBAL(reg_idx), + tdba & 0x00000000ffffffffULL); + wr32(E1000_TDBAH(reg_idx), tdba >> 32); + + ring->tail = hw->hw_addr + E1000_TDT(reg_idx); + wr32(E1000_TDH(reg_idx), 0); + writel(0, ring->tail); + + txdctl |= IGB_TX_PTHRESH; + txdctl |= IGB_TX_HTHRESH << 8; + txdctl |= IGB_TX_WTHRESH << 16; + + txdctl |= E1000_TXDCTL_QUEUE_ENABLE; + wr32(E1000_TXDCTL(reg_idx), txdctl); +} + +/** + * igb_configure_tx - Configure transmit Unit after Reset + * @adapter: board private structure + * + * Configure the Tx unit of the MAC after a reset. + **/ +static void igb_configure_tx(struct igb_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) + igb_configure_tx_ring(adapter, adapter->tx_ring[i]); +} + +/** + * igb_setup_rx_resources - allocate Rx resources (Descriptors) + * @rx_ring: rx descriptor ring (for a specific queue) to setup + * + * Returns 0 on success, negative on failure + **/ +int igb_setup_rx_resources(struct igb_ring *rx_ring) +{ + struct device *dev = rx_ring->dev; + int orig_node = dev_to_node(dev); + int size, desc_len; + + size = sizeof(struct igb_rx_buffer) * rx_ring->count; + rx_ring->rx_buffer_info = vzalloc_node(size, rx_ring->numa_node); + if (!rx_ring->rx_buffer_info) + rx_ring->rx_buffer_info = vzalloc(size); + if (!rx_ring->rx_buffer_info) + goto err; + + desc_len = sizeof(union e1000_adv_rx_desc); + + /* Round up to nearest 4K */ + rx_ring->size = rx_ring->count * desc_len; + rx_ring->size = ALIGN(rx_ring->size, 4096); + + set_dev_node(dev, rx_ring->numa_node); + rx_ring->desc = dma_alloc_coherent(dev, + rx_ring->size, + &rx_ring->dma, + GFP_KERNEL); + set_dev_node(dev, orig_node); + if (!rx_ring->desc) + rx_ring->desc = dma_alloc_coherent(dev, + rx_ring->size, + &rx_ring->dma, + GFP_KERNEL); + + if (!rx_ring->desc) + goto err; + + rx_ring->next_to_clean = 0; + rx_ring->next_to_use = 0; + + return 0; + +err: + vfree(rx_ring->rx_buffer_info); + rx_ring->rx_buffer_info = NULL; + dev_err(dev, "Unable to allocate memory for the receive descriptor" + " ring\n"); + return -ENOMEM; +} + +/** + * igb_setup_all_rx_resources - wrapper to allocate Rx resources + * (Descriptors) for all queues + * @adapter: board private structure + * + * Return 0 on success, negative on failure + **/ +static int igb_setup_all_rx_resources(struct igb_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + int i, err = 0; + + for (i = 0; i < adapter->num_rx_queues; i++) { + err = igb_setup_rx_resources(adapter->rx_ring[i]); + if (err) { + dev_err(&pdev->dev, + "Allocation for Rx Queue %u failed\n", i); + for (i--; i >= 0; i--) + igb_free_rx_resources(adapter->rx_ring[i]); + break; + } + } + + return err; +} + +/** + * igb_setup_mrqc - configure the multiple receive queue control registers + * @adapter: Board private structure + **/ +static void igb_setup_mrqc(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 mrqc, rxcsum; + u32 j, num_rx_queues, shift = 0, shift2 = 0; + union e1000_reta { + u32 dword; + u8 bytes[4]; + } reta; + static const u8 rsshash[40] = { + 0x6d, 0x5a, 0x56, 0xda, 0x25, 0x5b, 0x0e, 0xc2, 0x41, 0x67, + 0x25, 0x3d, 0x43, 0xa3, 0x8f, 0xb0, 0xd0, 0xca, 0x2b, 0xcb, + 0xae, 0x7b, 0x30, 0xb4, 0x77, 0xcb, 0x2d, 0xa3, 0x80, 0x30, + 0xf2, 0x0c, 0x6a, 0x42, 0xb7, 0x3b, 0xbe, 0xac, 0x01, 0xfa }; + + /* Fill out hash function seeds */ + for (j = 0; j < 10; j++) { + u32 rsskey = rsshash[(j * 4)]; + rsskey |= rsshash[(j * 4) + 1] << 8; + rsskey |= rsshash[(j * 4) + 2] << 16; + rsskey |= rsshash[(j * 4) + 3] << 24; + array_wr32(E1000_RSSRK(0), j, rsskey); + } + + num_rx_queues = adapter->rss_queues; + + if (adapter->vfs_allocated_count) { + /* 82575 and 82576 supports 2 RSS queues for VMDq */ + switch (hw->mac.type) { + case e1000_i350: + case e1000_82580: + num_rx_queues = 1; + shift = 0; + break; + case e1000_82576: + shift = 3; + num_rx_queues = 2; + break; + case e1000_82575: + shift = 2; + shift2 = 6; + default: + break; + } + } else { + if (hw->mac.type == e1000_82575) + shift = 6; + } + + for (j = 0; j < (32 * 4); j++) { + reta.bytes[j & 3] = (j % num_rx_queues) << shift; + if (shift2) + reta.bytes[j & 3] |= num_rx_queues << shift2; + if ((j & 3) == 3) + wr32(E1000_RETA(j >> 2), reta.dword); + } + + /* + * Disable raw packet checksumming so that RSS hash is placed in + * descriptor on writeback. No need to enable TCP/UDP/IP checksum + * offloads as they are enabled by default + */ + rxcsum = rd32(E1000_RXCSUM); + 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); + + /* If VMDq is enabled then we set the appropriate mode for that, else + * we default to RSS so that an RSS hash is calculated per packet even + * if we are only using one queue */ + if (adapter->vfs_allocated_count) { + if (hw->mac.type > e1000_82575) { + /* Set the default pool for the PF's first queue */ + u32 vtctl = rd32(E1000_VT_CTL); + vtctl &= ~(E1000_VT_CTL_DEFAULT_POOL_MASK | + E1000_VT_CTL_DISABLE_DEF_POOL); + vtctl |= adapter->vfs_allocated_count << + E1000_VT_CTL_DEFAULT_POOL_SHIFT; + wr32(E1000_VT_CTL, vtctl); + } + if (adapter->rss_queues > 1) + mrqc = E1000_MRQC_ENABLE_VMDQ_RSS_2Q; + else + mrqc = E1000_MRQC_ENABLE_VMDQ; + } else { + mrqc = E1000_MRQC_ENABLE_RSS_4Q; + } + igb_vmm_control(adapter); + + /* + * Generate RSS hash based on TCP port numbers and/or + * IPv4/v6 src and dst addresses since UDP cannot be + * hashed reliably due to IP fragmentation + */ + mrqc |= E1000_MRQC_RSS_FIELD_IPV4 | + E1000_MRQC_RSS_FIELD_IPV4_TCP | + E1000_MRQC_RSS_FIELD_IPV6 | + E1000_MRQC_RSS_FIELD_IPV6_TCP | + E1000_MRQC_RSS_FIELD_IPV6_TCP_EX; + + wr32(E1000_MRQC, mrqc); +} + +/** + * igb_setup_rctl - configure the receive control registers + * @adapter: Board private structure + **/ +void igb_setup_rctl(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 rctl; + + rctl = rd32(E1000_RCTL); + + rctl &= ~(3 << E1000_RCTL_MO_SHIFT); + rctl &= ~(E1000_RCTL_LBM_TCVR | E1000_RCTL_LBM_MAC); + + rctl |= E1000_RCTL_EN | E1000_RCTL_BAM | E1000_RCTL_RDMTS_HALF | + (hw->mac.mc_filter_type << E1000_RCTL_MO_SHIFT); + + /* + * enable stripping of CRC. It's unlikely this will break BMC + * redirection as it did with e1000. Newer features require + * that the HW strips the CRC. + */ + rctl |= E1000_RCTL_SECRC; + + /* disable store bad packets and clear size bits. */ + rctl &= ~(E1000_RCTL_SBP | E1000_RCTL_SZ_256); + + /* enable LPE to prevent packets larger than max_frame_size */ + rctl |= E1000_RCTL_LPE; + + /* disable queue 0 to prevent tail write w/o re-config */ + wr32(E1000_RXDCTL(0), 0); + + /* Attention!!! For SR-IOV PF driver operations you must enable + * queue drop for all VF and PF queues to prevent head of line blocking + * if an un-trusted VF does not provide descriptors to hardware. + */ + if (adapter->vfs_allocated_count) { + /* set all queue drop enable bits */ + wr32(E1000_QDE, ALL_QUEUES); + } + + wr32(E1000_RCTL, rctl); +} + +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; +} + +/** + * igb_rlpml_set - set maximum receive packet size + * @adapter: board private structure + * + * Configure maximum receivable packet size. + **/ +static void igb_rlpml_set(struct igb_adapter *adapter) +{ + u32 max_frame_size = adapter->max_frame_size; + struct e1000_hw *hw = &adapter->hw; + u16 pf_id = adapter->vfs_allocated_count; + + if (pf_id) { + igb_set_vf_rlpml(adapter, max_frame_size, pf_id); + /* + * If we're in VMDQ or SR-IOV mode, then set global RLPML + * to our max jumbo frame size, in case we need to enable + * jumbo frames on one of the rings later. + * This will not pass over-length frames into the default + * queue because it's gated by the VMOLR.RLPML. + */ + max_frame_size = MAX_JUMBO_FRAME_SIZE; + } + + wr32(E1000_RLPML, max_frame_size); +} + +static inline void igb_set_vmolr(struct igb_adapter *adapter, + int vfn, bool aupe) +{ + struct e1000_hw *hw = &adapter->hw; + u32 vmolr; + + /* + * This register exists only on 82576 and newer so if we are older then + * we should exit and do nothing + */ + if (hw->mac.type < e1000_82576) + return; + + vmolr = rd32(E1000_VMOLR(vfn)); + vmolr |= E1000_VMOLR_STRVLAN; /* Strip vlan tags */ + if (aupe) + vmolr |= E1000_VMOLR_AUPE; /* Accept untagged packets */ + else + vmolr &= ~(E1000_VMOLR_AUPE); /* Tagged packets ONLY */ + + /* clear all bits that might not be set */ + vmolr &= ~(E1000_VMOLR_BAM | E1000_VMOLR_RSSE); + + if (adapter->rss_queues > 1 && vfn == adapter->vfs_allocated_count) + vmolr |= E1000_VMOLR_RSSE; /* enable RSS */ + /* + * for VMDq only allow the VFs and pool 0 to accept broadcast and + * multicast packets + */ + if (vfn <= adapter->vfs_allocated_count) + vmolr |= E1000_VMOLR_BAM; /* Accept broadcast */ + + wr32(E1000_VMOLR(vfn), vmolr); +} + +/** + * igb_configure_rx_ring - Configure a receive ring after Reset + * @adapter: board private structure + * @ring: receive ring to be configured + * + * Configure the Rx unit of the MAC after a reset. + **/ +void igb_configure_rx_ring(struct igb_adapter *adapter, + struct igb_ring *ring) +{ + struct e1000_hw *hw = &adapter->hw; + u64 rdba = ring->dma; + int reg_idx = ring->reg_idx; + u32 srrctl = 0, rxdctl = 0; + + /* disable the queue */ + wr32(E1000_RXDCTL(reg_idx), 0); + + /* Set DMA base address registers */ + wr32(E1000_RDBAL(reg_idx), + rdba & 0x00000000ffffffffULL); + wr32(E1000_RDBAH(reg_idx), rdba >> 32); + wr32(E1000_RDLEN(reg_idx), + ring->count * sizeof(union e1000_adv_rx_desc)); + + /* initialize head and tail */ + ring->tail = hw->hw_addr + E1000_RDT(reg_idx); + wr32(E1000_RDH(reg_idx), 0); + writel(0, ring->tail); + + /* set descriptor configuration */ + srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT; +#if (PAGE_SIZE / 2) > IGB_RXBUFFER_16384 + srrctl |= IGB_RXBUFFER_16384 >> E1000_SRRCTL_BSIZEPKT_SHIFT; +#else + srrctl |= (PAGE_SIZE / 2) >> E1000_SRRCTL_BSIZEPKT_SHIFT; +#endif + srrctl |= E1000_SRRCTL_DESCTYPE_HDR_SPLIT_ALWAYS; + if (hw->mac.type >= e1000_82580) + srrctl |= E1000_SRRCTL_TIMESTAMP; + /* Only set Drop Enable if we are supporting multiple queues */ + if (adapter->vfs_allocated_count || adapter->num_rx_queues > 1) + srrctl |= E1000_SRRCTL_DROP_EN; + + wr32(E1000_SRRCTL(reg_idx), srrctl); + + /* set filtering for VMDQ pools */ + igb_set_vmolr(adapter, reg_idx & 0x7, true); + + rxdctl |= IGB_RX_PTHRESH; + rxdctl |= IGB_RX_HTHRESH << 8; + rxdctl |= IGB_RX_WTHRESH << 16; + + /* enable receive descriptor fetching */ + rxdctl |= E1000_RXDCTL_QUEUE_ENABLE; + wr32(E1000_RXDCTL(reg_idx), rxdctl); +} + +/** + * igb_configure_rx - Configure receive Unit after Reset + * @adapter: board private structure + * + * Configure the Rx unit of the MAC after a reset. + **/ +static void igb_configure_rx(struct igb_adapter *adapter) +{ + int i; + + /* 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); + + /* Setup the HW Rx Head and Tail Descriptor Pointers and + * the Base and Length of the Rx Descriptor Ring */ + for (i = 0; i < adapter->num_rx_queues; i++) + igb_configure_rx_ring(adapter, adapter->rx_ring[i]); +} + +/** + * igb_free_tx_resources - Free Tx Resources per Queue + * @tx_ring: Tx descriptor ring for a specific queue + * + * Free all transmit software resources + **/ +void igb_free_tx_resources(struct igb_ring *tx_ring) +{ + igb_clean_tx_ring(tx_ring); + + vfree(tx_ring->tx_buffer_info); + tx_ring->tx_buffer_info = NULL; + + /* if not set, then don't free */ + if (!tx_ring->desc) + return; + + dma_free_coherent(tx_ring->dev, tx_ring->size, + tx_ring->desc, tx_ring->dma); + + tx_ring->desc = NULL; +} + +/** + * igb_free_all_tx_resources - Free Tx Resources for All Queues + * @adapter: board private structure + * + * Free all transmit software resources + **/ +static void igb_free_all_tx_resources(struct igb_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) + igb_free_tx_resources(adapter->tx_ring[i]); +} + +void igb_unmap_and_free_tx_resource(struct igb_ring *ring, + struct igb_tx_buffer *tx_buffer) +{ + if (tx_buffer->skb) { + dev_kfree_skb_any(tx_buffer->skb); + if (tx_buffer->dma) + dma_unmap_single(ring->dev, + tx_buffer->dma, + tx_buffer->length, + DMA_TO_DEVICE); + } else if (tx_buffer->dma) { + dma_unmap_page(ring->dev, + tx_buffer->dma, + tx_buffer->length, + DMA_TO_DEVICE); + } + tx_buffer->next_to_watch = NULL; + tx_buffer->skb = NULL; + tx_buffer->dma = 0; + /* buffer_info must be completely set up in the transmit path */ +} + +/** + * igb_clean_tx_ring - Free Tx Buffers + * @tx_ring: ring to be cleaned + **/ +static void igb_clean_tx_ring(struct igb_ring *tx_ring) +{ + struct igb_tx_buffer *buffer_info; + unsigned long size; + u16 i; + + if (!tx_ring->tx_buffer_info) + return; + /* Free all the Tx ring sk_buffs */ + + for (i = 0; i < tx_ring->count; i++) { + buffer_info = &tx_ring->tx_buffer_info[i]; + igb_unmap_and_free_tx_resource(tx_ring, buffer_info); + } + + size = sizeof(struct igb_tx_buffer) * tx_ring->count; + memset(tx_ring->tx_buffer_info, 0, size); + + /* Zero out the descriptor ring */ + memset(tx_ring->desc, 0, tx_ring->size); + + tx_ring->next_to_use = 0; + tx_ring->next_to_clean = 0; +} + +/** + * igb_clean_all_tx_rings - Free Tx Buffers for all queues + * @adapter: board private structure + **/ +static void igb_clean_all_tx_rings(struct igb_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) + igb_clean_tx_ring(adapter->tx_ring[i]); +} + +/** + * igb_free_rx_resources - Free Rx Resources + * @rx_ring: ring to clean the resources from + * + * Free all receive software resources + **/ +void igb_free_rx_resources(struct igb_ring *rx_ring) +{ + igb_clean_rx_ring(rx_ring); + + vfree(rx_ring->rx_buffer_info); + rx_ring->rx_buffer_info = NULL; + + /* if not set, then don't free */ + if (!rx_ring->desc) + return; + + dma_free_coherent(rx_ring->dev, rx_ring->size, + rx_ring->desc, rx_ring->dma); + + rx_ring->desc = NULL; +} + +/** + * igb_free_all_rx_resources - Free Rx Resources for All Queues + * @adapter: board private structure + * + * Free all receive software resources + **/ +static void igb_free_all_rx_resources(struct igb_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_rx_queues; i++) + igb_free_rx_resources(adapter->rx_ring[i]); +} + +/** + * igb_clean_rx_ring - Free Rx Buffers per Queue + * @rx_ring: ring to free buffers from + **/ +static void igb_clean_rx_ring(struct igb_ring *rx_ring) +{ + unsigned long size; + u16 i; + + if (!rx_ring->rx_buffer_info) + return; + + /* Free all the Rx ring sk_buffs */ + for (i = 0; i < rx_ring->count; i++) { + struct igb_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i]; + if (buffer_info->dma) { + dma_unmap_single(rx_ring->dev, + buffer_info->dma, + IGB_RX_HDR_LEN, + DMA_FROM_DEVICE); + buffer_info->dma = 0; + } + + if (buffer_info->skb) { + dev_kfree_skb(buffer_info->skb); + buffer_info->skb = NULL; + } + if (buffer_info->page_dma) { + dma_unmap_page(rx_ring->dev, + buffer_info->page_dma, + PAGE_SIZE / 2, + DMA_FROM_DEVICE); + buffer_info->page_dma = 0; + } + if (buffer_info->page) { + put_page(buffer_info->page); + buffer_info->page = NULL; + buffer_info->page_offset = 0; + } + } + + size = sizeof(struct igb_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_clean = 0; + rx_ring->next_to_use = 0; +} + +/** + * igb_clean_all_rx_rings - Free Rx Buffers for all queues + * @adapter: board private structure + **/ +static void igb_clean_all_rx_rings(struct igb_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_rx_queues; i++) + igb_clean_rx_ring(adapter->rx_ring[i]); +} + +/** + * igb_set_mac - Change the Ethernet Address of the NIC + * @netdev: network interface device structure + * @p: pointer to an address structure + * + * Returns 0 on success, negative on failure + **/ +static int igb_set_mac(struct net_device *netdev, void *p) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + struct sockaddr *addr = p; + + if (!is_valid_ether_addr(addr->sa_data)) + return -EADDRNOTAVAIL; + + memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); + memcpy(hw->mac.addr, addr->sa_data, netdev->addr_len); + + /* 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_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 igb_write_mc_addr_list(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + struct netdev_hw_addr *ha; + u8 *mta_list; + int i; + + if (netdev_mc_empty(netdev)) { + /* nothing to program, so clear mc list */ + igb_update_mc_addr_list(hw, NULL, 0); + igb_restore_vf_multicasts(adapter); + return 0; + } + + mta_list = kzalloc(netdev_mc_count(netdev) * 6, GFP_ATOMIC); + if (!mta_list) + return -ENOMEM; + + /* The shared function expects a packed array of only addresses. */ + i = 0; + netdev_for_each_mc_addr(ha, netdev) + memcpy(mta_list + (i++ * ETH_ALEN), ha->addr, ETH_ALEN); + + igb_update_mc_addr_list(hw, mta_list, i); + kfree(mta_list); + + return netdev_mc_count(netdev); +} + +/** + * 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(netdev) > rar_entries) + return -ENOMEM; + + if (!netdev_uc_empty(netdev) && rar_entries) { + struct netdev_hw_addr *ha; + + netdev_for_each_uc_addr(ha, netdev) { + 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 promiscuous 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 promiscuous 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); +} + +static void igb_check_wvbr(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 wvbr = 0; + + switch (hw->mac.type) { + case e1000_82576: + case e1000_i350: + if (!(wvbr = rd32(E1000_WVBR))) + return; + break; + default: + break; + } + + adapter->wvbr |= wvbr; +} + +#define IGB_STAGGERED_QUEUE_OFFSET 8 + +static void igb_spoof_check(struct igb_adapter *adapter) +{ + int j; + + if (!adapter->wvbr) + return; + + for(j = 0; j < adapter->vfs_allocated_count; j++) { + if (adapter->wvbr & (1 << j) || + adapter->wvbr & (1 << (j + IGB_STAGGERED_QUEUE_OFFSET))) { + dev_warn(&adapter->pdev->dev, + "Spoof event(s) detected on VF %d\n", j); + adapter->wvbr &= + ~((1 << j) | + (1 << (j + IGB_STAGGERED_QUEUE_OFFSET))); + } + } +} + +/* Need to wait a few seconds after link up to get diagnostic information from + * the phy */ +static void igb_update_phy_info(unsigned long data) +{ + struct igb_adapter *adapter = (struct igb_adapter *) data; + igb_get_phy_info(&adapter->hw); +} + +/** + * igb_has_link - check shared code for link and determine up/down + * @adapter: pointer to driver private info + **/ +bool igb_has_link(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + bool link_active = false; + s32 ret_val = 0; + + /* get_link_status is set on LSC (link status) interrupt or + * rx sequence error interrupt. get_link_status will stay + * false until the e1000_check_for_link establishes link + * for copper adapters ONLY + */ + switch (hw->phy.media_type) { + case e1000_media_type_copper: + if (hw->mac.get_link_status) { + ret_val = hw->mac.ops.check_for_link(hw); + link_active = !hw->mac.get_link_status; + } else { + link_active = true; + } + break; + case e1000_media_type_internal_serdes: + ret_val = hw->mac.ops.check_for_link(hw); + link_active = hw->mac.serdes_has_link; + break; + default: + case e1000_media_type_unknown: + break; + } + + return link_active; +} + +static bool igb_thermal_sensor_event(struct e1000_hw *hw, u32 event) +{ + bool ret = false; + u32 ctrl_ext, thstat; + + /* check for thermal sensor event on i350, copper only */ + if (hw->mac.type == e1000_i350) { + thstat = rd32(E1000_THSTAT); + ctrl_ext = rd32(E1000_CTRL_EXT); + + if ((hw->phy.media_type == e1000_media_type_copper) && + !(ctrl_ext & E1000_CTRL_EXT_LINK_MODE_SGMII)) { + ret = !!(thstat & event); + } + } + + return ret; +} + +/** + * igb_watchdog - Timer Call-back + * @data: pointer to adapter cast into an unsigned long + **/ +static void igb_watchdog(unsigned long data) +{ + struct igb_adapter *adapter = (struct igb_adapter *)data; + /* Do the rest outside of interrupt context */ + schedule_work(&adapter->watchdog_task); +} + +static void igb_watchdog_task(struct work_struct *work) +{ + struct igb_adapter *adapter = container_of(work, + struct igb_adapter, + watchdog_task); + struct e1000_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; + u32 link; + int i; + + link = igb_has_link(adapter); + if (link) { + if (!netif_carrier_ok(netdev)) { + u32 ctrl; + hw->mac.ops.get_speed_and_duplex(hw, + &adapter->link_speed, + &adapter->link_duplex); + + ctrl = rd32(E1000_CTRL); + /* Links status message must follow this format */ + printk(KERN_INFO "igb: %s NIC Link is Up %d Mbps %s, " + "Flow Control: %s\n", + netdev->name, + adapter->link_speed, + adapter->link_duplex == FULL_DUPLEX ? + "Full Duplex" : "Half Duplex", + ((ctrl & E1000_CTRL_TFCE) && + (ctrl & E1000_CTRL_RFCE)) ? "RX/TX" : + ((ctrl & E1000_CTRL_RFCE) ? "RX" : + ((ctrl & E1000_CTRL_TFCE) ? "TX" : "None"))); + + /* check for thermal sensor event */ + if (igb_thermal_sensor_event(hw, E1000_THSTAT_LINK_THROTTLE)) { + printk(KERN_INFO "igb: %s The network adapter " + "link speed was downshifted " + "because it overheated.\n", + netdev->name); + } + + /* adjust timeout factor according to speed/duplex */ + adapter->tx_timeout_factor = 1; + switch (adapter->link_speed) { + case SPEED_10: + adapter->tx_timeout_factor = 14; + break; + case SPEED_100: + /* maybe add some timeout factor ? */ + break; + } + + netif_carrier_on(netdev); + + igb_ping_all_vfs(adapter); + igb_check_vf_rate_limit(adapter); + + /* link state has changed, schedule phy info update */ + if (!test_bit(__IGB_DOWN, &adapter->state)) + mod_timer(&adapter->phy_info_timer, + round_jiffies(jiffies + 2 * HZ)); + } + } else { + if (netif_carrier_ok(netdev)) { + adapter->link_speed = 0; + adapter->link_duplex = 0; + + /* check for thermal sensor event */ + if (igb_thermal_sensor_event(hw, E1000_THSTAT_PWR_DOWN)) { + printk(KERN_ERR "igb: %s The network adapter " + "was stopped because it " + "overheated.\n", + netdev->name); + } + + /* Links status message must follow this format */ + printk(KERN_INFO "igb: %s NIC Link is Down\n", + netdev->name); + netif_carrier_off(netdev); + + igb_ping_all_vfs(adapter); + + /* link state has changed, schedule phy info update */ + if (!test_bit(__IGB_DOWN, &adapter->state)) + mod_timer(&adapter->phy_info_timer, + round_jiffies(jiffies + 2 * HZ)); + } + } + + spin_lock(&adapter->stats64_lock); + igb_update_stats(adapter, &adapter->stats64); + spin_unlock(&adapter->stats64_lock); + + for (i = 0; i < adapter->num_tx_queues; i++) { + struct igb_ring *tx_ring = adapter->tx_ring[i]; + if (!netif_carrier_ok(netdev)) { + /* 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). */ + if (igb_desc_unused(tx_ring) + 1 < tx_ring->count) { + adapter->tx_timeout_count++; + schedule_work(&adapter->reset_task); + /* return immediately since reset is imminent */ + return; + } + } + + /* Force detection of hung controller every watchdog period */ + set_bit(IGB_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags); + } + + /* Cause software interrupt to ensure rx ring is cleaned */ + if (adapter->msix_entries) { + u32 eics = 0; + for (i = 0; i < adapter->num_q_vectors; i++) + eics |= adapter->q_vector[i]->eims_value; + wr32(E1000_EICS, eics); + } else { + wr32(E1000_ICS, E1000_ICS_RXDMT0); + } + + igb_spoof_check(adapter); + + /* Reset the timer */ + if (!test_bit(__IGB_DOWN, &adapter->state)) + mod_timer(&adapter->watchdog_timer, + round_jiffies(jiffies + 2 * HZ)); +} + +enum latency_range { + lowest_latency = 0, + low_latency = 1, + bulk_latency = 2, + latency_invalid = 255 +}; + +/** + * igb_update_ring_itr - update the dynamic ITR value based on packet size + * + * Stores a new ITR value based on strictly on packet size. This + * algorithm is less sophisticated than that used in igb_update_itr, + * due to the difficulty of synchronizing statistics across multiple + * receive rings. The divisors and thresholds used by this function + * were determined based on theoretical maximum wire speed and testing + * data, in order to minimize response time while increasing bulk + * throughput. + * This functionality is controlled by the InterruptThrottleRate module + * parameter (see igb_param.c) + * NOTE: This function is called only when operating in a multiqueue + * receive environment. + * @q_vector: pointer to q_vector + **/ +static void igb_update_ring_itr(struct igb_q_vector *q_vector) +{ + int new_val = q_vector->itr_val; + int avg_wire_size = 0; + struct igb_adapter *adapter = q_vector->adapter; + unsigned int packets; + + /* For non-gigabit speeds, just fix the interrupt rate at 4000 + * ints/sec - ITR timer value of 120 ticks. + */ + if (adapter->link_speed != SPEED_1000) { + new_val = IGB_4K_ITR; + goto set_itr_val; + } + + packets = q_vector->rx.total_packets; + if (packets) + avg_wire_size = q_vector->rx.total_bytes / packets; + + packets = q_vector->tx.total_packets; + if (packets) + avg_wire_size = max_t(u32, avg_wire_size, + q_vector->tx.total_bytes / packets); + + /* if avg_wire_size isn't set no work was done */ + if (!avg_wire_size) + goto clear_counts; + + /* Add 24 bytes to size to account for CRC, preamble, and gap */ + avg_wire_size += 24; + + /* Don't starve jumbo frames */ + avg_wire_size = min(avg_wire_size, 3000); + + /* Give a little boost to mid-size frames */ + if ((avg_wire_size > 300) && (avg_wire_size < 1200)) + new_val = avg_wire_size / 3; + else + new_val = avg_wire_size / 2; + + /* conservative mode (itr 3) eliminates the lowest_latency setting */ + if (new_val < IGB_20K_ITR && + ((q_vector->rx.ring && adapter->rx_itr_setting == 3) || + (!q_vector->rx.ring && adapter->tx_itr_setting == 3))) + new_val = IGB_20K_ITR; + +set_itr_val: + if (new_val != q_vector->itr_val) { + q_vector->itr_val = new_val; + q_vector->set_itr = 1; + } +clear_counts: + q_vector->rx.total_bytes = 0; + q_vector->rx.total_packets = 0; + q_vector->tx.total_bytes = 0; + q_vector->tx.total_packets = 0; +} + +/** + * igb_update_itr - update the dynamic ITR value based on statistics + * Stores a new ITR value based on packets and byte + * counts during the last interrupt. The advantage of per interrupt + * computation is faster updates and more accurate ITR for the current + * traffic pattern. Constants in this function were computed + * based on theoretical maximum wire speed and thresholds were set based + * on testing data as well as attempting to minimize response time + * while increasing bulk throughput. + * this functionality is controlled by the InterruptThrottleRate module + * parameter (see igb_param.c) + * NOTE: These calculations are only valid when operating in a single- + * queue environment. + * @q_vector: pointer to q_vector + * @ring_container: ring info to update the itr for + **/ +static void igb_update_itr(struct igb_q_vector *q_vector, + struct igb_ring_container *ring_container) +{ + unsigned int packets = ring_container->total_packets; + unsigned int bytes = ring_container->total_bytes; + u8 itrval = ring_container->itr; + + /* no packets, exit with status unchanged */ + if (packets == 0) + return; + + switch (itrval) { + case lowest_latency: + /* handle TSO and jumbo frames */ + if (bytes/packets > 8000) + itrval = bulk_latency; + else if ((packets < 5) && (bytes > 512)) + itrval = low_latency; + break; + case low_latency: /* 50 usec aka 20000 ints/s */ + if (bytes > 10000) { + /* this if handles the TSO accounting */ + if (bytes/packets > 8000) { + itrval = bulk_latency; + } else if ((packets < 10) || ((bytes/packets) > 1200)) { + itrval = bulk_latency; + } else if ((packets > 35)) { + itrval = lowest_latency; + } + } else if (bytes/packets > 2000) { + itrval = bulk_latency; + } else if (packets <= 2 && bytes < 512) { + itrval = lowest_latency; + } + break; + case bulk_latency: /* 250 usec aka 4000 ints/s */ + if (bytes > 25000) { + if (packets > 35) + itrval = low_latency; + } else if (bytes < 1500) { + itrval = low_latency; + } + break; + } + + /* clear work counters since we have the values we need */ + ring_container->total_bytes = 0; + ring_container->total_packets = 0; + + /* write updated itr to ring container */ + ring_container->itr = itrval; +} + +static void igb_set_itr(struct igb_q_vector *q_vector) +{ + struct igb_adapter *adapter = q_vector->adapter; + u32 new_itr = q_vector->itr_val; + u8 current_itr = 0; + + /* for non-gigabit speeds, just fix the interrupt rate at 4000 */ + if (adapter->link_speed != SPEED_1000) { + current_itr = 0; + new_itr = IGB_4K_ITR; + goto set_itr_now; + } + + igb_update_itr(q_vector, &q_vector->tx); + igb_update_itr(q_vector, &q_vector->rx); + + current_itr = max(q_vector->rx.itr, q_vector->tx.itr); + + /* conservative mode (itr 3) eliminates the lowest_latency setting */ + if (current_itr == lowest_latency && + ((q_vector->rx.ring && adapter->rx_itr_setting == 3) || + (!q_vector->rx.ring && adapter->tx_itr_setting == 3))) + current_itr = low_latency; + + switch (current_itr) { + /* counts and packets in update_itr are dependent on these numbers */ + case lowest_latency: + new_itr = IGB_70K_ITR; /* 70,000 ints/sec */ + break; + case low_latency: + new_itr = IGB_20K_ITR; /* 20,000 ints/sec */ + break; + case bulk_latency: + new_itr = IGB_4K_ITR; /* 4,000 ints/sec */ + break; + default: + break; + } + +set_itr_now: + if (new_itr != q_vector->itr_val) { + /* this attempts to bias the interrupt rate towards Bulk + * by adding intermediate steps when interrupt rate is + * increasing */ + new_itr = new_itr > q_vector->itr_val ? + max((new_itr * q_vector->itr_val) / + (new_itr + (q_vector->itr_val >> 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 + * we should between interrupts. Instead, we write the ITR + * value at the beginning of the next interrupt so the timing + * ends up being correct. + */ + q_vector->itr_val = new_itr; + q_vector->set_itr = 1; + } +} + +void igb_tx_ctxtdesc(struct igb_ring *tx_ring, u32 vlan_macip_lens, + u32 type_tucmd, u32 mss_l4len_idx) +{ + struct e1000_adv_tx_context_desc *context_desc; + u16 i = tx_ring->next_to_use; + + context_desc = IGB_TX_CTXTDESC(tx_ring, i); + + i++; + tx_ring->next_to_use = (i < tx_ring->count) ? i : 0; + + /* set bits to identify this as an advanced context descriptor */ + type_tucmd |= E1000_TXD_CMD_DEXT | E1000_ADVTXD_DTYP_CTXT; + + /* For 82575, context index must be unique per ring. */ + if (test_bit(IGB_RING_FLAG_TX_CTX_IDX, &tx_ring->flags)) + mss_l4len_idx |= tx_ring->reg_idx << 4; + + context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens); + context_desc->seqnum_seed = 0; + context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd); + context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx); +} + +static int igb_tso(struct igb_ring *tx_ring, + struct igb_tx_buffer *first, + u8 *hdr_len) +{ + struct sk_buff *skb = first->skb; + u32 vlan_macip_lens, type_tucmd; + u32 mss_l4len_idx, l4len; + + 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; + } + + /* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */ + type_tucmd = E1000_ADVTXD_TUCMD_L4T_TCP; + + if (first->protocol == __constant_htons(ETH_P_IP)) { + struct iphdr *iph = ip_hdr(skb); + iph->tot_len = 0; + iph->check = 0; + tcp_hdr(skb)->check = ~csum_tcpudp_magic(iph->saddr, + iph->daddr, 0, + IPPROTO_TCP, + 0); + type_tucmd |= E1000_ADVTXD_TUCMD_IPV4; + first->tx_flags |= IGB_TX_FLAGS_TSO | + IGB_TX_FLAGS_CSUM | + IGB_TX_FLAGS_IPV4; + } else if (skb_is_gso_v6(skb)) { + ipv6_hdr(skb)->payload_len = 0; + tcp_hdr(skb)->check = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + 0, IPPROTO_TCP, 0); + first->tx_flags |= IGB_TX_FLAGS_TSO | + IGB_TX_FLAGS_CSUM; + } + + /* compute header lengths */ + l4len = tcp_hdrlen(skb); + *hdr_len = skb_transport_offset(skb) + l4len; + + /* update gso size and bytecount with header size */ + first->gso_segs = skb_shinfo(skb)->gso_segs; + first->bytecount += (first->gso_segs - 1) * *hdr_len; + + /* MSS L4LEN IDX */ + mss_l4len_idx = l4len << E1000_ADVTXD_L4LEN_SHIFT; + mss_l4len_idx |= skb_shinfo(skb)->gso_size << E1000_ADVTXD_MSS_SHIFT; + + /* VLAN MACLEN IPLEN */ + vlan_macip_lens = skb_network_header_len(skb); + vlan_macip_lens |= skb_network_offset(skb) << E1000_ADVTXD_MACLEN_SHIFT; + vlan_macip_lens |= first->tx_flags & IGB_TX_FLAGS_VLAN_MASK; + + igb_tx_ctxtdesc(tx_ring, vlan_macip_lens, type_tucmd, mss_l4len_idx); + + return 1; +} + +static void igb_tx_csum(struct igb_ring *tx_ring, struct igb_tx_buffer *first) +{ + struct sk_buff *skb = first->skb; + u32 vlan_macip_lens = 0; + u32 mss_l4len_idx = 0; + u32 type_tucmd = 0; + + if (skb->ip_summed != CHECKSUM_PARTIAL) { + if (!(first->tx_flags & IGB_TX_FLAGS_VLAN)) + return; + } else { + u8 l4_hdr = 0; + switch (first->protocol) { + case __constant_htons(ETH_P_IP): + vlan_macip_lens |= skb_network_header_len(skb); + type_tucmd |= E1000_ADVTXD_TUCMD_IPV4; + l4_hdr = ip_hdr(skb)->protocol; + break; + case __constant_htons(ETH_P_IPV6): + vlan_macip_lens |= skb_network_header_len(skb); + l4_hdr = ipv6_hdr(skb)->nexthdr; + break; + default: + if (unlikely(net_ratelimit())) { + dev_warn(tx_ring->dev, + "partial checksum but proto=%x!\n", + first->protocol); + } + break; + } + + switch (l4_hdr) { + case IPPROTO_TCP: + type_tucmd |= E1000_ADVTXD_TUCMD_L4T_TCP; + mss_l4len_idx = tcp_hdrlen(skb) << + E1000_ADVTXD_L4LEN_SHIFT; + break; + case IPPROTO_SCTP: + type_tucmd |= E1000_ADVTXD_TUCMD_L4T_SCTP; + mss_l4len_idx = sizeof(struct sctphdr) << + E1000_ADVTXD_L4LEN_SHIFT; + break; + case IPPROTO_UDP: + mss_l4len_idx = sizeof(struct udphdr) << + E1000_ADVTXD_L4LEN_SHIFT; + break; + default: + if (unlikely(net_ratelimit())) { + dev_warn(tx_ring->dev, + "partial checksum but l4 proto=%x!\n", + l4_hdr); + } + break; + } + + /* update TX checksum flag */ + first->tx_flags |= IGB_TX_FLAGS_CSUM; + } + + vlan_macip_lens |= skb_network_offset(skb) << E1000_ADVTXD_MACLEN_SHIFT; + vlan_macip_lens |= first->tx_flags & IGB_TX_FLAGS_VLAN_MASK; + + igb_tx_ctxtdesc(tx_ring, vlan_macip_lens, type_tucmd, mss_l4len_idx); +} + +static __le32 igb_tx_cmd_type(u32 tx_flags) +{ + /* set type for advanced descriptor with frame checksum insertion */ + __le32 cmd_type = cpu_to_le32(E1000_ADVTXD_DTYP_DATA | + E1000_ADVTXD_DCMD_IFCS | + E1000_ADVTXD_DCMD_DEXT); + + /* set HW vlan bit if vlan is present */ + if (tx_flags & IGB_TX_FLAGS_VLAN) + cmd_type |= cpu_to_le32(E1000_ADVTXD_DCMD_VLE); + + /* set timestamp bit if present */ + if (tx_flags & IGB_TX_FLAGS_TSTAMP) + cmd_type |= cpu_to_le32(E1000_ADVTXD_MAC_TSTAMP); + + /* set segmentation bits for TSO */ + if (tx_flags & IGB_TX_FLAGS_TSO) + cmd_type |= cpu_to_le32(E1000_ADVTXD_DCMD_TSE); + + return cmd_type; +} + +static void igb_tx_olinfo_status(struct igb_ring *tx_ring, + union e1000_adv_tx_desc *tx_desc, + u32 tx_flags, unsigned int paylen) +{ + u32 olinfo_status = paylen << E1000_ADVTXD_PAYLEN_SHIFT; + + /* 82575 requires a unique index per ring if any offload is enabled */ + if ((tx_flags & (IGB_TX_FLAGS_CSUM | IGB_TX_FLAGS_VLAN)) && + test_bit(IGB_RING_FLAG_TX_CTX_IDX, &tx_ring->flags)) + olinfo_status |= tx_ring->reg_idx << 4; + + /* insert L4 checksum */ + if (tx_flags & IGB_TX_FLAGS_CSUM) { + olinfo_status |= E1000_TXD_POPTS_TXSM << 8; + + /* insert IPv4 checksum */ + if (tx_flags & IGB_TX_FLAGS_IPV4) + olinfo_status |= E1000_TXD_POPTS_IXSM << 8; + } + + tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); +} + +/* + * The largest size we can write to the descriptor is 65535. In order to + * maintain a power of two alignment we have to limit ourselves to 32K. + */ +#define IGB_MAX_TXD_PWR 15 +#define IGB_MAX_DATA_PER_TXD (1<<IGB_MAX_TXD_PWR) + +static void igb_tx_map(struct igb_ring *tx_ring, + struct igb_tx_buffer *first, + const u8 hdr_len) +{ + struct sk_buff *skb = first->skb; + struct igb_tx_buffer *tx_buffer_info; + union e1000_adv_tx_desc *tx_desc; + dma_addr_t dma; + struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; + unsigned int data_len = skb->data_len; + unsigned int size = skb_headlen(skb); + unsigned int paylen = skb->len - hdr_len; + __le32 cmd_type; + u32 tx_flags = first->tx_flags; + u16 i = tx_ring->next_to_use; + + tx_desc = IGB_TX_DESC(tx_ring, i); + + igb_tx_olinfo_status(tx_ring, tx_desc, tx_flags, paylen); + cmd_type = igb_tx_cmd_type(tx_flags); + + dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE); + if (dma_mapping_error(tx_ring->dev, dma)) + goto dma_error; + + /* record length, and DMA address */ + first->length = size; + first->dma = dma; + tx_desc->read.buffer_addr = cpu_to_le64(dma); + + for (;;) { + while (unlikely(size > IGB_MAX_DATA_PER_TXD)) { + tx_desc->read.cmd_type_len = + cmd_type | cpu_to_le32(IGB_MAX_DATA_PER_TXD); + + i++; + tx_desc++; + if (i == tx_ring->count) { + tx_desc = IGB_TX_DESC(tx_ring, 0); + i = 0; + } + + dma += IGB_MAX_DATA_PER_TXD; + size -= IGB_MAX_DATA_PER_TXD; + + tx_desc->read.olinfo_status = 0; + tx_desc->read.buffer_addr = cpu_to_le64(dma); + } + + if (likely(!data_len)) + break; + + tx_desc->read.cmd_type_len = cmd_type | cpu_to_le32(size); + + i++; + tx_desc++; + if (i == tx_ring->count) { + tx_desc = IGB_TX_DESC(tx_ring, 0); + i = 0; + } + + size = skb_frag_size(frag); + data_len -= size; + + dma = skb_frag_dma_map(tx_ring->dev, frag, 0, + size, DMA_TO_DEVICE); + if (dma_mapping_error(tx_ring->dev, dma)) + goto dma_error; + + tx_buffer_info = &tx_ring->tx_buffer_info[i]; + tx_buffer_info->length = size; + tx_buffer_info->dma = dma; + + tx_desc->read.olinfo_status = 0; + tx_desc->read.buffer_addr = cpu_to_le64(dma); + + frag++; + } + + /* write last descriptor with RS and EOP bits */ + cmd_type |= cpu_to_le32(size) | cpu_to_le32(IGB_TXD_DCMD); + tx_desc->read.cmd_type_len = cmd_type; + + /* set the timestamp */ + first->time_stamp = jiffies; + + /* + * Force memory writes to complete before letting h/w know there + * are new descriptors to fetch. (Only applicable for weak-ordered + * memory model archs, such as IA-64). + * + * We also need this memory barrier to make certain all of the + * status bits have been updated before next_to_watch is written. + */ + wmb(); + + /* set next_to_watch value indicating a packet is present */ + first->next_to_watch = tx_desc; + + i++; + if (i == tx_ring->count) + i = 0; + + tx_ring->next_to_use = i; + + writel(i, tx_ring->tail); + + /* we need this if more than one processor can write to our tail + * at a time, it syncronizes IO on IA64/Altix systems */ + mmiowb(); + + return; + +dma_error: + dev_err(tx_ring->dev, "TX DMA map failed\n"); + + /* clear dma mappings for failed tx_buffer_info map */ + for (;;) { + tx_buffer_info = &tx_ring->tx_buffer_info[i]; + igb_unmap_and_free_tx_resource(tx_ring, tx_buffer_info); + if (tx_buffer_info == first) + break; + if (i == 0) + i = tx_ring->count; + i--; + } + + tx_ring->next_to_use = i; +} + +static int __igb_maybe_stop_tx(struct igb_ring *tx_ring, const u16 size) +{ + struct net_device *netdev = tx_ring->netdev; + + netif_stop_subqueue(netdev, tx_ring->queue_index); + + /* Herbert's original patch had: + * smp_mb__after_netif_stop_queue(); + * but since that doesn't exist yet, just open code it. */ + smp_mb(); + + /* We need to check again in a case another CPU has just + * made room available. */ + if (igb_desc_unused(tx_ring) < size) + return -EBUSY; + + /* A reprieve! */ + netif_wake_subqueue(netdev, tx_ring->queue_index); + + u64_stats_update_begin(&tx_ring->tx_syncp2); + tx_ring->tx_stats.restart_queue2++; + u64_stats_update_end(&tx_ring->tx_syncp2); + + return 0; +} + +static inline int igb_maybe_stop_tx(struct igb_ring *tx_ring, const u16 size) +{ + if (igb_desc_unused(tx_ring) >= size) + return 0; + return __igb_maybe_stop_tx(tx_ring, size); +} + +netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, + struct igb_ring *tx_ring) +{ + struct igb_tx_buffer *first; + int tso; + u32 tx_flags = 0; + __be16 protocol = vlan_get_protocol(skb); + u8 hdr_len = 0; + + /* need: 1 descriptor per page, + * + 2 desc gap to keep tail from touching head, + * + 1 desc for skb->data, + * + 1 desc for context descriptor, + * otherwise try next time */ + if (igb_maybe_stop_tx(tx_ring, skb_shinfo(skb)->nr_frags + 4)) { + /* this is a hard error */ + return NETDEV_TX_BUSY; + } + + /* record the location of the first descriptor for this packet */ + first = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + first->skb = skb; + first->bytecount = skb->len; + first->gso_segs = 1; + + if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + tx_flags |= IGB_TX_FLAGS_TSTAMP; + } + + if (vlan_tx_tag_present(skb)) { + tx_flags |= IGB_TX_FLAGS_VLAN; + tx_flags |= (vlan_tx_tag_get(skb) << IGB_TX_FLAGS_VLAN_SHIFT); + } + + /* record initial flags and protocol */ + first->tx_flags = tx_flags; + first->protocol = protocol; + + tso = igb_tso(tx_ring, first, &hdr_len); + if (tso < 0) + goto out_drop; + else if (!tso) + igb_tx_csum(tx_ring, first); + + igb_tx_map(tx_ring, first, hdr_len); + + /* Make sure there is space in the ring for the next send. */ + igb_maybe_stop_tx(tx_ring, MAX_SKB_FRAGS + 4); + + return NETDEV_TX_OK; + +out_drop: + igb_unmap_and_free_tx_resource(tx_ring, first); + + return NETDEV_TX_OK; +} + +static inline struct igb_ring *igb_tx_queue_mapping(struct igb_adapter *adapter, + struct sk_buff *skb) +{ + unsigned int r_idx = skb->queue_mapping; + + if (r_idx >= adapter->num_tx_queues) + r_idx = r_idx % adapter->num_tx_queues; + + return adapter->tx_ring[r_idx]; +} + +static netdev_tx_t igb_xmit_frame(struct sk_buff *skb, + struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + + if (test_bit(__IGB_DOWN, &adapter->state)) { + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } + + if (skb->len <= 0) { + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } + + /* + * The minimum packet size with TCTL.PSP set is 17 so pad the skb + * in order to meet this minimum size requirement. + */ + if (skb->len < 17) { + if (skb_padto(skb, 17)) + return NETDEV_TX_OK; + skb->len = 17; + } + + return igb_xmit_frame_ring(skb, igb_tx_queue_mapping(adapter, skb)); +} + +/** + * igb_tx_timeout - Respond to a Tx Hang + * @netdev: network interface device structure + **/ +static void igb_tx_timeout(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + + /* Do the reset outside of interrupt context */ + adapter->tx_timeout_count++; + + if (hw->mac.type >= e1000_82580) + hw->dev_spec._82575.global_device_reset = true; + + schedule_work(&adapter->reset_task); + wr32(E1000_EICS, + (adapter->eims_enable_mask & ~adapter->eims_other)); +} + +static void igb_reset_task(struct work_struct *work) +{ + struct igb_adapter *adapter; + adapter = container_of(work, struct igb_adapter, reset_task); + + igb_dump(adapter); + netdev_err(adapter->netdev, "Reset adapter\n"); + igb_reinit_locked(adapter); +} + +/** + * igb_get_stats64 - Get System Network Statistics + * @netdev: network interface device structure + * @stats: rtnl_link_stats64 pointer + * + **/ +static struct rtnl_link_stats64 *igb_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + + spin_lock(&adapter->stats64_lock); + igb_update_stats(adapter, &adapter->stats64); + memcpy(stats, &adapter->stats64, sizeof(*stats)); + spin_unlock(&adapter->stats64_lock); + + return stats; +} + +/** + * igb_change_mtu - Change the Maximum Transfer Unit + * @netdev: network interface device structure + * @new_mtu: new value for maximum frame size + * + * Returns 0 on success, negative on failure + **/ +static int igb_change_mtu(struct net_device *netdev, int new_mtu) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct pci_dev *pdev = adapter->pdev; + int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; + + if ((new_mtu < 68) || (max_frame > MAX_JUMBO_FRAME_SIZE)) { + dev_err(&pdev->dev, "Invalid MTU setting\n"); + return -EINVAL; + } + +#define MAX_STD_JUMBO_FRAME_SIZE 9238 + if (max_frame > MAX_STD_JUMBO_FRAME_SIZE) { + dev_err(&pdev->dev, "MTU > 9216 not supported.\n"); + return -EINVAL; + } + + while (test_and_set_bit(__IGB_RESETTING, &adapter->state)) + msleep(1); + + /* igb_down has a dependency on max_frame_size */ + adapter->max_frame_size = max_frame; + + if (netif_running(netdev)) + igb_down(adapter); + + dev_info(&pdev->dev, "changing MTU from %d to %d\n", + netdev->mtu, new_mtu); + netdev->mtu = new_mtu; + + if (netif_running(netdev)) + igb_up(adapter); + else + igb_reset(adapter); + + clear_bit(__IGB_RESETTING, &adapter->state); + + return 0; +} + +/** + * igb_update_stats - Update the board statistics counters + * @adapter: board private structure + **/ + +void igb_update_stats(struct igb_adapter *adapter, + struct rtnl_link_stats64 *net_stats) +{ + struct e1000_hw *hw = &adapter->hw; + struct pci_dev *pdev = adapter->pdev; + u32 reg, mpc; + u16 phy_tmp; + int i; + u64 bytes, packets; + unsigned int start; + u64 _bytes, _packets; + +#define PHY_IDLE_ERROR_COUNT_MASK 0x00FF + + /* + * Prevent stats update while adapter is being reset, or if the pci + * connection is down. + */ + if (adapter->link_speed == 0) + return; + if (pci_channel_offline(pdev)) + return; + + bytes = 0; + packets = 0; + for (i = 0; i < adapter->num_rx_queues; i++) { + u32 rqdpc_tmp = rd32(E1000_RQDPC(i)) & 0x0FFF; + struct igb_ring *ring = adapter->rx_ring[i]; + + ring->rx_stats.drops += rqdpc_tmp; + net_stats->rx_fifo_errors += rqdpc_tmp; + + do { + start = u64_stats_fetch_begin_bh(&ring->rx_syncp); + _bytes = ring->rx_stats.bytes; + _packets = ring->rx_stats.packets; + } while (u64_stats_fetch_retry_bh(&ring->rx_syncp, start)); + bytes += _bytes; + packets += _packets; + } + + net_stats->rx_bytes = bytes; + net_stats->rx_packets = packets; + + bytes = 0; + packets = 0; + for (i = 0; i < adapter->num_tx_queues; i++) { + struct igb_ring *ring = adapter->tx_ring[i]; + do { + start = u64_stats_fetch_begin_bh(&ring->tx_syncp); + _bytes = ring->tx_stats.bytes; + _packets = ring->tx_stats.packets; + } while (u64_stats_fetch_retry_bh(&ring->tx_syncp, start)); + bytes += _bytes; + packets += _packets; + } + net_stats->tx_bytes = bytes; + net_stats->tx_packets = packets; + + /* read stats registers */ + adapter->stats.crcerrs += rd32(E1000_CRCERRS); + adapter->stats.gprc += rd32(E1000_GPRC); + adapter->stats.gorc += rd32(E1000_GORCL); + rd32(E1000_GORCH); /* clear GORCL */ + adapter->stats.bprc += rd32(E1000_BPRC); + adapter->stats.mprc += rd32(E1000_MPRC); + adapter->stats.roc += rd32(E1000_ROC); + + adapter->stats.prc64 += rd32(E1000_PRC64); + adapter->stats.prc127 += rd32(E1000_PRC127); + adapter->stats.prc255 += rd32(E1000_PRC255); + adapter->stats.prc511 += rd32(E1000_PRC511); + adapter->stats.prc1023 += rd32(E1000_PRC1023); + adapter->stats.prc1522 += rd32(E1000_PRC1522); + adapter->stats.symerrs += rd32(E1000_SYMERRS); + adapter->stats.sec += rd32(E1000_SEC); + + mpc = rd32(E1000_MPC); + adapter->stats.mpc += mpc; + net_stats->rx_fifo_errors += mpc; + adapter->stats.scc += rd32(E1000_SCC); + adapter->stats.ecol += rd32(E1000_ECOL); + adapter->stats.mcc += rd32(E1000_MCC); + adapter->stats.latecol += rd32(E1000_LATECOL); + adapter->stats.dc += rd32(E1000_DC); + adapter->stats.rlec += rd32(E1000_RLEC); + adapter->stats.xonrxc += rd32(E1000_XONRXC); + adapter->stats.xontxc += rd32(E1000_XONTXC); + adapter->stats.xoffrxc += rd32(E1000_XOFFRXC); + adapter->stats.xofftxc += rd32(E1000_XOFFTXC); + adapter->stats.fcruc += rd32(E1000_FCRUC); + adapter->stats.gptc += rd32(E1000_GPTC); + adapter->stats.gotc += rd32(E1000_GOTCL); + rd32(E1000_GOTCH); /* clear GOTCL */ + adapter->stats.rnbc += rd32(E1000_RNBC); + adapter->stats.ruc += rd32(E1000_RUC); + adapter->stats.rfc += rd32(E1000_RFC); + adapter->stats.rjc += rd32(E1000_RJC); + adapter->stats.tor += rd32(E1000_TORH); + adapter->stats.tot += rd32(E1000_TOTH); + adapter->stats.tpr += rd32(E1000_TPR); + + adapter->stats.ptc64 += rd32(E1000_PTC64); + adapter->stats.ptc127 += rd32(E1000_PTC127); + adapter->stats.ptc255 += rd32(E1000_PTC255); + adapter->stats.ptc511 += rd32(E1000_PTC511); + adapter->stats.ptc1023 += rd32(E1000_PTC1023); + adapter->stats.ptc1522 += rd32(E1000_PTC1522); + + adapter->stats.mptc += rd32(E1000_MPTC); + adapter->stats.bptc += rd32(E1000_BPTC); + + adapter->stats.tpt += rd32(E1000_TPT); + adapter->stats.colc += rd32(E1000_COLC); + + adapter->stats.algnerrc += rd32(E1000_ALGNERRC); + /* read internal phy specific stats */ + reg = rd32(E1000_CTRL_EXT); + if (!(reg & E1000_CTRL_EXT_LINK_MODE_MASK)) { + adapter->stats.rxerrc += rd32(E1000_RXERRC); + adapter->stats.tncrs += rd32(E1000_TNCRS); + } + + adapter->stats.tsctc += rd32(E1000_TSCTC); + adapter->stats.tsctfc += rd32(E1000_TSCTFC); + + adapter->stats.iac += rd32(E1000_IAC); + adapter->stats.icrxoc += rd32(E1000_ICRXOC); + adapter->stats.icrxptc += rd32(E1000_ICRXPTC); + adapter->stats.icrxatc += rd32(E1000_ICRXATC); + adapter->stats.ictxptc += rd32(E1000_ICTXPTC); + adapter->stats.ictxatc += rd32(E1000_ICTXATC); + adapter->stats.ictxqec += rd32(E1000_ICTXQEC); + adapter->stats.ictxqmtc += rd32(E1000_ICTXQMTC); + adapter->stats.icrxdmtc += rd32(E1000_ICRXDMTC); + + /* Fill out the OS statistics structure */ + net_stats->multicast = adapter->stats.mprc; + net_stats->collisions = adapter->stats.colc; + + /* Rx Errors */ + + /* RLEC on some newer hardware can be incorrect so build + * our own version based on RUC and ROC */ + net_stats->rx_errors = adapter->stats.rxerrc + + adapter->stats.crcerrs + adapter->stats.algnerrc + + adapter->stats.ruc + adapter->stats.roc + + adapter->stats.cexterr; + net_stats->rx_length_errors = adapter->stats.ruc + + adapter->stats.roc; + net_stats->rx_crc_errors = adapter->stats.crcerrs; + net_stats->rx_frame_errors = adapter->stats.algnerrc; + net_stats->rx_missed_errors = adapter->stats.mpc; + + /* Tx Errors */ + net_stats->tx_errors = adapter->stats.ecol + + adapter->stats.latecol; + net_stats->tx_aborted_errors = adapter->stats.ecol; + net_stats->tx_window_errors = adapter->stats.latecol; + net_stats->tx_carrier_errors = adapter->stats.tncrs; + + /* Tx Dropped needs to be maintained elsewhere */ + + /* Phy Stats */ + if (hw->phy.media_type == e1000_media_type_copper) { + if ((adapter->link_speed == SPEED_1000) && + (!igb_read_phy_reg(hw, PHY_1000T_STATUS, &phy_tmp))) { + phy_tmp &= PHY_IDLE_ERROR_COUNT_MASK; + adapter->phy_stats.idle_errors += phy_tmp; + } + } + + /* Management Stats */ + adapter->stats.mgptc += rd32(E1000_MGTPTC); + adapter->stats.mgprc += rd32(E1000_MGTPRC); + adapter->stats.mgpdc += rd32(E1000_MGTPDC); + + /* OS2BMC Stats */ + reg = rd32(E1000_MANC); + if (reg & E1000_MANC_EN_BMC2OS) { + adapter->stats.o2bgptc += rd32(E1000_O2BGPTC); + adapter->stats.o2bspc += rd32(E1000_O2BSPC); + adapter->stats.b2ospc += rd32(E1000_B2OSPC); + adapter->stats.b2ogprc += rd32(E1000_B2OGPRC); + } +} + +static irqreturn_t igb_msix_other(int irq, void *data) +{ + struct igb_adapter *adapter = data; + struct e1000_hw *hw = &adapter->hw; + u32 icr = rd32(E1000_ICR); + /* reading ICR causes bit 31 of EICR to be cleared */ + + if (icr & E1000_ICR_DRSTA) + schedule_work(&adapter->reset_task); + + if (icr & E1000_ICR_DOUTSYNC) { + /* HW is reporting DMA is out of sync */ + adapter->stats.doosync++; + /* The DMA Out of Sync is also indication of a spoof event + * in IOV mode. Check the Wrong VM Behavior register to + * see if it is really a spoof event. */ + igb_check_wvbr(adapter); + } + + /* Check for a mailbox event */ + if (icr & E1000_ICR_VMMB) + igb_msg_task(adapter); + + if (icr & E1000_ICR_LSC) { + hw->mac.get_link_status = 1; + /* guard against interrupt when we're going down */ + if (!test_bit(__IGB_DOWN, &adapter->state)) + mod_timer(&adapter->watchdog_timer, jiffies + 1); + } + + wr32(E1000_EIMS, adapter->eims_other); + + return IRQ_HANDLED; +} + +static void igb_write_itr(struct igb_q_vector *q_vector) +{ + struct igb_adapter *adapter = q_vector->adapter; + u32 itr_val = q_vector->itr_val & 0x7FFC; + + if (!q_vector->set_itr) + return; + + if (!itr_val) + itr_val = 0x4; + + if (adapter->hw.mac.type == e1000_82575) + itr_val |= itr_val << 16; + else + itr_val |= E1000_EITR_CNT_IGNR; + + writel(itr_val, q_vector->itr_register); + q_vector->set_itr = 0; +} + +static irqreturn_t igb_msix_ring(int irq, void *data) +{ + struct igb_q_vector *q_vector = data; + + /* Write the ITR value calculated from the previous interrupt. */ + igb_write_itr(q_vector); + + napi_schedule(&q_vector->napi); + + return IRQ_HANDLED; +} + +#ifdef CONFIG_IGB_DCA +static void igb_update_dca(struct igb_q_vector *q_vector) +{ + struct igb_adapter *adapter = q_vector->adapter; + struct e1000_hw *hw = &adapter->hw; + int cpu = get_cpu(); + + if (q_vector->cpu == cpu) + goto out_no_update; + + if (q_vector->tx.ring) { + int q = q_vector->tx.ring->reg_idx; + u32 dca_txctrl = rd32(E1000_DCA_TXCTRL(q)); + if (hw->mac.type == e1000_82575) { + dca_txctrl &= ~E1000_DCA_TXCTRL_CPUID_MASK; + dca_txctrl |= dca3_get_tag(&adapter->pdev->dev, cpu); + } else { + dca_txctrl &= ~E1000_DCA_TXCTRL_CPUID_MASK_82576; + dca_txctrl |= dca3_get_tag(&adapter->pdev->dev, cpu) << + E1000_DCA_TXCTRL_CPUID_SHIFT; + } + dca_txctrl |= E1000_DCA_TXCTRL_DESC_DCA_EN; + wr32(E1000_DCA_TXCTRL(q), dca_txctrl); + } + if (q_vector->rx.ring) { + int q = q_vector->rx.ring->reg_idx; + u32 dca_rxctrl = rd32(E1000_DCA_RXCTRL(q)); + if (hw->mac.type == e1000_82575) { + dca_rxctrl &= ~E1000_DCA_RXCTRL_CPUID_MASK; + dca_rxctrl |= dca3_get_tag(&adapter->pdev->dev, cpu); + } else { + dca_rxctrl &= ~E1000_DCA_RXCTRL_CPUID_MASK_82576; + dca_rxctrl |= dca3_get_tag(&adapter->pdev->dev, cpu) << + E1000_DCA_RXCTRL_CPUID_SHIFT; + } + dca_rxctrl |= E1000_DCA_RXCTRL_DESC_DCA_EN; + dca_rxctrl |= E1000_DCA_RXCTRL_HEAD_DCA_EN; + dca_rxctrl |= E1000_DCA_RXCTRL_DATA_DCA_EN; + wr32(E1000_DCA_RXCTRL(q), dca_rxctrl); + } + q_vector->cpu = cpu; +out_no_update: + put_cpu(); +} + +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_q_vectors; i++) { + adapter->q_vector[i]->cpu = -1; + igb_update_dca(adapter->q_vector[i]); + } +} + +static int __igb_notify_dca(struct device *dev, void *data) +{ + struct net_device *netdev = dev_get_drvdata(dev); + struct igb_adapter *adapter = netdev_priv(netdev); + struct pci_dev *pdev = adapter->pdev; + struct e1000_hw *hw = &adapter->hw; + unsigned long event = *(unsigned long *)data; + + switch (event) { + case DCA_PROVIDER_ADD: + /* if already enabled, don't do it again */ + if (adapter->flags & IGB_FLAG_DCA_ENABLED) + break; + if (dca_add_requester(dev) == 0) { + adapter->flags |= IGB_FLAG_DCA_ENABLED; + dev_info(&pdev->dev, "DCA enabled\n"); + igb_setup_dca(adapter); + break; + } + /* Fall Through since DCA is disabled. */ + case DCA_PROVIDER_REMOVE: + if (adapter->flags & IGB_FLAG_DCA_ENABLED) { + /* without this a class_device is left + * hanging around in the sysfs model */ + dca_remove_requester(dev); + dev_info(&pdev->dev, "DCA disabled\n"); + adapter->flags &= ~IGB_FLAG_DCA_ENABLED; + wr32(E1000_DCA_CTRL, E1000_DCA_CTRL_DCA_MODE_DISABLE); + } + break; + } + + return 0; +} + +static int igb_notify_dca(struct notifier_block *nb, unsigned long event, + void *p) +{ + int ret_val; + + ret_val = driver_for_each_device(&igb_driver.driver, NULL, &event, + __igb_notify_dca); + + return ret_val ? NOTIFY_BAD : NOTIFY_DONE; +} +#endif /* CONFIG_IGB_DCA */ + +#ifdef CONFIG_PCI_IOV +static int igb_vf_configure(struct igb_adapter *adapter, int vf) +{ + unsigned char mac_addr[ETH_ALEN]; + struct pci_dev *pdev = adapter->pdev; + struct e1000_hw *hw = &adapter->hw; + struct pci_dev *pvfdev; + unsigned int device_id; + u16 thisvf_devfn; + + random_ether_addr(mac_addr); + igb_set_vf_mac(adapter, vf, mac_addr); + + switch (adapter->hw.mac.type) { + case e1000_82576: + device_id = IGB_82576_VF_DEV_ID; + /* VF Stride for 82576 is 2 */ + thisvf_devfn = (pdev->devfn + 0x80 + (vf << 1)) | + (pdev->devfn & 1); + break; + case e1000_i350: + device_id = IGB_I350_VF_DEV_ID; + /* VF Stride for I350 is 4 */ + thisvf_devfn = (pdev->devfn + 0x80 + (vf << 2)) | + (pdev->devfn & 3); + break; + default: + device_id = 0; + thisvf_devfn = 0; + break; + } + + pvfdev = pci_get_device(hw->vendor_id, device_id, NULL); + while (pvfdev) { + if (pvfdev->devfn == thisvf_devfn) + break; + pvfdev = pci_get_device(hw->vendor_id, + device_id, pvfdev); + } + + if (pvfdev) + adapter->vf_data[vf].vfdev = pvfdev; + else + dev_err(&pdev->dev, + "Couldn't find pci dev ptr for VF %4.4x\n", + thisvf_devfn); + return pvfdev != NULL; +} + +static int igb_find_enabled_vfs(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + struct pci_dev *pdev = adapter->pdev; + struct pci_dev *pvfdev; + u16 vf_devfn = 0; + u16 vf_stride; + unsigned int device_id; + int vfs_found = 0; + + switch (adapter->hw.mac.type) { + case e1000_82576: + device_id = IGB_82576_VF_DEV_ID; + /* VF Stride for 82576 is 2 */ + vf_stride = 2; + break; + case e1000_i350: + device_id = IGB_I350_VF_DEV_ID; + /* VF Stride for I350 is 4 */ + vf_stride = 4; + break; + default: + device_id = 0; + vf_stride = 0; + break; + } + + vf_devfn = pdev->devfn + 0x80; + pvfdev = pci_get_device(hw->vendor_id, device_id, NULL); + while (pvfdev) { + if (pvfdev->devfn == vf_devfn) + vfs_found++; + vf_devfn += vf_stride; + pvfdev = pci_get_device(hw->vendor_id, + device_id, pvfdev); + } + + return vfs_found; +} + +static int igb_check_vf_assignment(struct igb_adapter *adapter) +{ + int i; + for (i = 0; i < adapter->vfs_allocated_count; i++) { + if (adapter->vf_data[i].vfdev) { + if (adapter->vf_data[i].vfdev->dev_flags & + PCI_DEV_FLAGS_ASSIGNED) + return true; + } + } + return false; +} + +#endif +static void igb_ping_all_vfs(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 ping; + int i; + + for (i = 0 ; i < adapter->vfs_allocated_count; i++) { + ping = E1000_PF_CONTROL_MSG; + if (adapter->vf_data[i].flags & IGB_VF_FLAG_CTS) + ping |= E1000_VT_MSGTYPE_CTS; + igb_write_mbx(hw, &ping, 1, i); + } +} + +static int igb_set_vf_promisc(struct igb_adapter *adapter, u32 *msgbuf, u32 vf) +{ + struct e1000_hw *hw = &adapter->hw; + u32 vmolr = rd32(E1000_VMOLR(vf)); + struct vf_data_storage *vf_data = &adapter->vf_data[vf]; + + vf_data->flags &= ~(IGB_VF_FLAG_UNI_PROMISC | + IGB_VF_FLAG_MULTI_PROMISC); + vmolr &= ~(E1000_VMOLR_ROPE | E1000_VMOLR_ROMPE | E1000_VMOLR_MPME); + + if (*msgbuf & E1000_VF_SET_PROMISC_MULTICAST) { + vmolr |= E1000_VMOLR_MPME; + vf_data->flags |= IGB_VF_FLAG_MULTI_PROMISC; + *msgbuf &= ~E1000_VF_SET_PROMISC_MULTICAST; + } else { + /* + * if we have hashes and we are clearing a multicast promisc + * flag we need to write the hashes to the MTA as this step + * was previously skipped + */ + if (vf_data->num_vf_mc_hashes > 30) { + vmolr |= E1000_VMOLR_MPME; + } else if (vf_data->num_vf_mc_hashes) { + int j; + vmolr |= E1000_VMOLR_ROMPE; + for (j = 0; j < vf_data->num_vf_mc_hashes; j++) + igb_mta_set(hw, vf_data->vf_mc_hashes[j]); + } + } + + wr32(E1000_VMOLR(vf), vmolr); + + /* there are flags left unprocessed, likely not supported */ + if (*msgbuf & E1000_VT_MSGINFO_MASK) + return -EINVAL; + + return 0; + +} + +static int igb_set_vf_multicasts(struct igb_adapter *adapter, + u32 *msgbuf, u32 vf) +{ + int n = (msgbuf[0] & E1000_VT_MSGINFO_MASK) >> E1000_VT_MSGINFO_SHIFT; + u16 *hash_list = (u16 *)&msgbuf[1]; + struct vf_data_storage *vf_data = &adapter->vf_data[vf]; + int i; + + /* salt away the number of multicast addresses assigned + * to this VF for later use to restore when the PF multi cast + * list changes + */ + vf_data->num_vf_mc_hashes = n; + + /* only up to 30 hash values supported */ + if (n > 30) + n = 30; + + /* store the hashes for later use */ + for (i = 0; i < n; i++) + vf_data->vf_mc_hashes[i] = hash_list[i]; + + /* Flush and reset the mta with the new values */ + igb_set_rx_mode(adapter->netdev); + + return 0; +} + +static void igb_restore_vf_multicasts(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + struct vf_data_storage *vf_data; + int i, j; + + for (i = 0; i < adapter->vfs_allocated_count; i++) { + u32 vmolr = rd32(E1000_VMOLR(i)); + vmolr &= ~(E1000_VMOLR_ROMPE | E1000_VMOLR_MPME); + + vf_data = &adapter->vf_data[i]; + + if ((vf_data->num_vf_mc_hashes > 30) || + (vf_data->flags & IGB_VF_FLAG_MULTI_PROMISC)) { + vmolr |= E1000_VMOLR_MPME; + } else if (vf_data->num_vf_mc_hashes) { + vmolr |= E1000_VMOLR_ROMPE; + for (j = 0; j < vf_data->num_vf_mc_hashes; j++) + igb_mta_set(hw, vf_data->vf_mc_hashes[j]); + } + wr32(E1000_VMOLR(i), vmolr); + } +} + +static void igb_clear_vf_vfta(struct igb_adapter *adapter, u32 vf) +{ + struct e1000_hw *hw = &adapter->hw; + u32 pool_mask, reg, vid; + int i; + + pool_mask = 1 << (E1000_VLVF_POOLSEL_SHIFT + vf); + + /* Find the vlan filter for this id */ + for (i = 0; i < E1000_VLVF_ARRAY_SIZE; i++) { + reg = rd32(E1000_VLVF(i)); + + /* remove the vf from the pool */ + reg &= ~pool_mask; + + /* if pool is empty then remove entry from vfta */ + if (!(reg & E1000_VLVF_POOLSEL_MASK) && + (reg & E1000_VLVF_VLANID_ENABLE)) { + reg = 0; + vid = reg & E1000_VLVF_VLANID_MASK; + igb_vfta_set(hw, vid, false); + } + + 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) +{ + struct e1000_hw *hw = &adapter->hw; + u32 reg, i; + + /* The vlvf table only exists on 82576 hardware and newer */ + if (hw->mac.type < e1000_82576) + return -1; + + /* we only need to do this if VMDq is enabled */ + if (!adapter->vfs_allocated_count) + return -1; + + /* Find the vlan filter for this id */ + for (i = 0; i < E1000_VLVF_ARRAY_SIZE; i++) { + reg = rd32(E1000_VLVF(i)); + if ((reg & E1000_VLVF_VLANID_ENABLE) && + vid == (reg & E1000_VLVF_VLANID_MASK)) + break; + } + + if (add) { + if (i == E1000_VLVF_ARRAY_SIZE) { + /* Did not find a matching VLAN ID entry that was + * enabled. Search for a free filter entry, i.e. + * one without the enable bit set + */ + for (i = 0; i < E1000_VLVF_ARRAY_SIZE; i++) { + reg = rd32(E1000_VLVF(i)); + if (!(reg & E1000_VLVF_VLANID_ENABLE)) + break; + } + } + if (i < E1000_VLVF_ARRAY_SIZE) { + /* Found an enabled/available entry */ + reg |= 1 << (E1000_VLVF_POOLSEL_SHIFT + 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); + 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++; + } + } else { + if (i < E1000_VLVF_ARRAY_SIZE) { + /* remove vf from the pool */ + reg &= ~(1 << (E1000_VLVF_POOLSEL_SHIFT + vf)); + /* if pool is empty then remove entry from vfta */ + if (!(reg & E1000_VLVF_POOLSEL_MASK)) { + reg = 0; + 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; +} + +static void igb_set_vmvir(struct igb_adapter *adapter, u32 vid, u32 vf) +{ + struct e1000_hw *hw = &adapter->hw; + + if (vid) + wr32(E1000_VMVIR(vf), (vid | E1000_VMVIR_VLANA_DEFAULT)); + else + wr32(E1000_VMVIR(vf), 0); +} + +static int igb_ndo_set_vf_vlan(struct net_device *netdev, + int vf, u16 vlan, u8 qos) +{ + int err = 0; + struct igb_adapter *adapter = netdev_priv(netdev); + + if ((vf >= adapter->vfs_allocated_count) || (vlan > 4095) || (qos > 7)) + return -EINVAL; + if (vlan || qos) { + err = igb_vlvf_set(adapter, vlan, !!vlan, vf); + if (err) + goto out; + igb_set_vmvir(adapter, vlan | (qos << VLAN_PRIO_SHIFT), vf); + igb_set_vmolr(adapter, vf, !vlan); + adapter->vf_data[vf].pf_vlan = vlan; + adapter->vf_data[vf].pf_qos = qos; + dev_info(&adapter->pdev->dev, + "Setting VLAN %d, QOS 0x%x on VF %d\n", vlan, qos, vf); + if (test_bit(__IGB_DOWN, &adapter->state)) { + dev_warn(&adapter->pdev->dev, + "The VF VLAN has been set," + " but the PF device is not up.\n"); + dev_warn(&adapter->pdev->dev, + "Bring the PF device up before" + " attempting to use the VF device.\n"); + } + } else { + igb_vlvf_set(adapter, adapter->vf_data[vf].pf_vlan, + false, vf); + igb_set_vmvir(adapter, vlan, vf); + igb_set_vmolr(adapter, vf, true); + adapter->vf_data[vf].pf_vlan = 0; + adapter->vf_data[vf].pf_qos = 0; + } +out: + return err; +} + +static int igb_set_vf_vlan(struct igb_adapter *adapter, u32 *msgbuf, u32 vf) +{ + int add = (msgbuf[0] & E1000_VT_MSGINFO_MASK) >> E1000_VT_MSGINFO_SHIFT; + int vid = (msgbuf[1] & E1000_VLVF_VLANID_MASK); + + return igb_vlvf_set(adapter, vid, add, vf); +} + +static inline void igb_vf_reset(struct igb_adapter *adapter, u32 vf) +{ + /* clear flags - except flag that indicates PF has set the MAC */ + adapter->vf_data[vf].flags &= IGB_VF_FLAG_PF_SET_MAC; + adapter->vf_data[vf].last_nack = jiffies; + + /* reset offloads to defaults */ + igb_set_vmolr(adapter, vf, true); + + /* reset vlans for device */ + igb_clear_vf_vfta(adapter, vf); + if (adapter->vf_data[vf].pf_vlan) + igb_ndo_set_vf_vlan(adapter->netdev, vf, + adapter->vf_data[vf].pf_vlan, + adapter->vf_data[vf].pf_qos); + else + igb_clear_vf_vfta(adapter, vf); + + /* reset multicast table array for vf */ + adapter->vf_data[vf].num_vf_mc_hashes = 0; + + /* Flush and reset the mta with the new values */ + igb_set_rx_mode(adapter->netdev); +} + +static void igb_vf_reset_event(struct igb_adapter *adapter, u32 vf) +{ + unsigned char *vf_mac = adapter->vf_data[vf].vf_mac_addresses; + + /* generate a new mac address as we were hotplug removed/added */ + if (!(adapter->vf_data[vf].flags & IGB_VF_FLAG_PF_SET_MAC)) + random_ether_addr(vf_mac); + + /* process remaining reset events */ + igb_vf_reset(adapter, vf); +} + +static 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]); + + /* process all the same items cleared in a function level reset */ + igb_vf_reset(adapter, vf); + + /* set vf mac address */ + igb_rar_set_qsel(adapter, vf_mac, rar_entry, vf); + + /* enable transmit and receive for vf */ + reg = rd32(E1000_VFTE); + wr32(E1000_VFTE, reg | (1 << vf)); + reg = rd32(E1000_VFRE); + wr32(E1000_VFRE, reg | (1 << vf)); + + adapter->vf_data[vf].flags |= IGB_VF_FLAG_CTS; + + /* reply to reset with ack and vf mac address */ + msgbuf[0] = E1000_VF_RESET | E1000_VT_MSGTYPE_ACK; + memcpy(addr, vf_mac, 6); + igb_write_mbx(hw, msgbuf, 3, vf); +} + +static int igb_set_vf_mac_addr(struct igb_adapter *adapter, u32 *msg, int vf) +{ + /* + * The VF MAC Address is stored in a packed array of bytes + * starting at the second 32 bit word of the msg array + */ + unsigned char *addr = (char *)&msg[1]; + int err = -1; + + if (is_valid_ether_addr(addr)) + err = igb_set_vf_mac(adapter, vf, addr); + + return err; +} + +static void igb_rcv_ack_from_vf(struct igb_adapter *adapter, u32 vf) +{ + struct e1000_hw *hw = &adapter->hw; + struct vf_data_storage *vf_data = &adapter->vf_data[vf]; + u32 msg = E1000_VT_MSGTYPE_NACK; + + /* if device isn't clear to send it shouldn't be reading either */ + if (!(vf_data->flags & IGB_VF_FLAG_CTS) && + time_after(jiffies, vf_data->last_nack + (2 * HZ))) { + igb_write_mbx(hw, &msg, 1, vf); + vf_data->last_nack = jiffies; + } +} + +static void igb_rcv_msg_from_vf(struct igb_adapter *adapter, u32 vf) +{ + struct pci_dev *pdev = adapter->pdev; + u32 msgbuf[E1000_VFMAILBOX_SIZE]; + struct e1000_hw *hw = &adapter->hw; + struct vf_data_storage *vf_data = &adapter->vf_data[vf]; + s32 retval; + + retval = igb_read_mbx(hw, msgbuf, E1000_VFMAILBOX_SIZE, vf); + + if (retval) { + /* if receive failed revoke VF CTS stats and restart init */ + dev_err(&pdev->dev, "Error receiving message from VF\n"); + vf_data->flags &= ~IGB_VF_FLAG_CTS; + if (!time_after(jiffies, vf_data->last_nack + (2 * HZ))) + return; + goto out; + } + + /* this is a message we already processed, do nothing */ + if (msgbuf[0] & (E1000_VT_MSGTYPE_ACK | E1000_VT_MSGTYPE_NACK)) + return; + + /* + * until the vf completes a reset it should not be + * allowed to start any configuration. + */ + + if (msgbuf[0] == E1000_VF_RESET) { + igb_vf_reset_msg(adapter, vf); + return; + } + + if (!(vf_data->flags & IGB_VF_FLAG_CTS)) { + if (!time_after(jiffies, vf_data->last_nack + (2 * HZ))) + return; + retval = -1; + goto out; + } + + switch ((msgbuf[0] & 0xFFFF)) { + case E1000_VF_SET_MAC_ADDR: + retval = -EINVAL; + if (!(vf_data->flags & IGB_VF_FLAG_PF_SET_MAC)) + retval = igb_set_vf_mac_addr(adapter, msgbuf, vf); + else + dev_warn(&pdev->dev, + "VF %d attempted to override administratively " + "set MAC address\nReload the VF driver to " + "resume operations\n", vf); + break; + case E1000_VF_SET_PROMISC: + retval = igb_set_vf_promisc(adapter, msgbuf, vf); + break; + case E1000_VF_SET_MULTICAST: + retval = igb_set_vf_multicasts(adapter, msgbuf, vf); + break; + case E1000_VF_SET_LPE: + retval = igb_set_vf_rlpml(adapter, msgbuf[1], vf); + break; + case E1000_VF_SET_VLAN: + retval = -1; + if (vf_data->pf_vlan) + dev_warn(&pdev->dev, + "VF %d attempted to override administratively " + "set VLAN tag\nReload the VF driver to " + "resume operations\n", vf); + else + retval = igb_set_vf_vlan(adapter, msgbuf, vf); + break; + default: + dev_err(&pdev->dev, "Unhandled Msg %08x\n", msgbuf[0]); + retval = -1; + break; + } + + msgbuf[0] |= E1000_VT_MSGTYPE_CTS; +out: + /* notify the VF of the results of what it sent us */ + if (retval) + msgbuf[0] |= E1000_VT_MSGTYPE_NACK; + else + msgbuf[0] |= E1000_VT_MSGTYPE_ACK; + + igb_write_mbx(hw, msgbuf, 1, vf); +} + +static void igb_msg_task(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 vf; + + for (vf = 0; vf < adapter->vfs_allocated_count; vf++) { + /* process any reset requests */ + if (!igb_check_for_rst(hw, vf)) + igb_vf_reset_event(adapter, vf); + + /* process any messages pending */ + if (!igb_check_for_msg(hw, vf)) + igb_rcv_msg_from_vf(adapter, vf); + + /* process any acks */ + if (!igb_check_for_ack(hw, vf)) + igb_rcv_ack_from_vf(adapter, vf); + } +} + +/** + * 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 promiscuous + * enable bit to allow vlan tag stripping when promiscuous 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 irqreturn_t igb_intr_msi(int irq, void *data) +{ + struct igb_adapter *adapter = data; + struct igb_q_vector *q_vector = adapter->q_vector[0]; + struct e1000_hw *hw = &adapter->hw; + /* read ICR disables interrupts using IAM */ + u32 icr = rd32(E1000_ICR); + + igb_write_itr(q_vector); + + if (icr & E1000_ICR_DRSTA) + schedule_work(&adapter->reset_task); + + if (icr & E1000_ICR_DOUTSYNC) { + /* HW is reporting DMA is out of sync */ + adapter->stats.doosync++; + } + + if (icr & (E1000_ICR_RXSEQ | E1000_ICR_LSC)) { + hw->mac.get_link_status = 1; + if (!test_bit(__IGB_DOWN, &adapter->state)) + mod_timer(&adapter->watchdog_timer, jiffies + 1); + } + + napi_schedule(&q_vector->napi); + + return IRQ_HANDLED; +} + +/** + * igb_intr - Legacy Interrupt Handler + * @irq: interrupt number + * @data: pointer to a network interface device structure + **/ +static irqreturn_t igb_intr(int irq, void *data) +{ + struct igb_adapter *adapter = data; + struct igb_q_vector *q_vector = adapter->q_vector[0]; + struct e1000_hw *hw = &adapter->hw; + /* Interrupt Auto-Mask...upon reading ICR, interrupts are masked. No + * need for the IMC write */ + u32 icr = rd32(E1000_ICR); + + /* IMS will not auto-mask if INT_ASSERTED is not set, and if it is + * not set, then the adapter didn't send an interrupt */ + if (!(icr & E1000_ICR_INT_ASSERTED)) + return IRQ_NONE; + + igb_write_itr(q_vector); + + if (icr & E1000_ICR_DRSTA) + schedule_work(&adapter->reset_task); + + if (icr & E1000_ICR_DOUTSYNC) { + /* HW is reporting DMA is out of sync */ + adapter->stats.doosync++; + } + + if (icr & (E1000_ICR_RXSEQ | E1000_ICR_LSC)) { + hw->mac.get_link_status = 1; + /* guard against interrupt when we're going down */ + if (!test_bit(__IGB_DOWN, &adapter->state)) + mod_timer(&adapter->watchdog_timer, jiffies + 1); + } + + napi_schedule(&q_vector->napi); + + return IRQ_HANDLED; +} + +void igb_ring_irq_enable(struct igb_q_vector *q_vector) +{ + struct igb_adapter *adapter = q_vector->adapter; + struct e1000_hw *hw = &adapter->hw; + + if ((q_vector->rx.ring && (adapter->rx_itr_setting & 3)) || + (!q_vector->rx.ring && (adapter->tx_itr_setting & 3))) { + if ((adapter->num_q_vectors == 1) && !adapter->vf_data) + igb_set_itr(q_vector); + else + igb_update_ring_itr(q_vector); + } + + if (!test_bit(__IGB_DOWN, &adapter->state)) { + if (adapter->msix_entries) + wr32(E1000_EIMS, q_vector->eims_value); + else + igb_irq_enable(adapter); + } +} + +/** + * igb_poll - NAPI Rx polling callback + * @napi: napi polling structure + * @budget: count of how many packets we should handle + **/ +static int igb_poll(struct napi_struct *napi, int budget) +{ + struct igb_q_vector *q_vector = container_of(napi, + struct igb_q_vector, + napi); + bool clean_complete = true; + +#ifdef CONFIG_IGB_DCA + if (q_vector->adapter->flags & IGB_FLAG_DCA_ENABLED) + igb_update_dca(q_vector); +#endif + if (q_vector->tx.ring) + clean_complete = igb_clean_tx_irq(q_vector); + + if (q_vector->rx.ring) + clean_complete &= igb_clean_rx_irq(q_vector, budget); + + /* If all work not completed, return budget and keep polling */ + if (!clean_complete) + return budget; + + /* If not enough Rx work done, exit the polling mode */ + napi_complete(napi); + igb_ring_irq_enable(q_vector); + + return 0; +} + +/** + * igb_systim_to_hwtstamp - convert system time value to hw timestamp + * @adapter: board private structure + * @shhwtstamps: timestamp structure to update + * @regval: unsigned 64bit system time value. + * + * We need to convert the system time value stored in the RX/TXSTMP registers + * into a hwtstamp which can be used by the upper level timestamping functions + */ +static void igb_systim_to_hwtstamp(struct igb_adapter *adapter, + struct skb_shared_hwtstamps *shhwtstamps, + u64 regval) +{ + u64 ns; + + /* + * The 82580 starts with 1ns at bit 0 in RX/TXSTMPL, shift this up to + * 24 to match clock shift we setup earlier. + */ + if (adapter->hw.mac.type >= e1000_82580) + regval <<= IGB_82580_TSYNC_SHIFT; + + ns = timecounter_cyc2time(&adapter->clock, regval); + timecompare_update(&adapter->compare, ns); + memset(shhwtstamps, 0, sizeof(struct skb_shared_hwtstamps)); + shhwtstamps->hwtstamp = ns_to_ktime(ns); + shhwtstamps->syststamp = timecompare_transform(&adapter->compare, ns); +} + +/** + * igb_tx_hwtstamp - utility function which checks for TX time stamp + * @q_vector: pointer to q_vector containing needed info + * @buffer: pointer to igb_tx_buffer structure + * + * If we were asked to do hardware stamping and such a time stamp is + * available, then it must have been for this skb here because we only + * allow only one such packet into the queue. + */ +static void igb_tx_hwtstamp(struct igb_q_vector *q_vector, + struct igb_tx_buffer *buffer_info) +{ + struct igb_adapter *adapter = q_vector->adapter; + struct e1000_hw *hw = &adapter->hw; + struct skb_shared_hwtstamps shhwtstamps; + u64 regval; + + /* if skb does not support hw timestamp or TX stamp not valid exit */ + if (likely(!(buffer_info->tx_flags & IGB_TX_FLAGS_TSTAMP)) || + !(rd32(E1000_TSYNCTXCTL) & E1000_TSYNCTXCTL_VALID)) + return; + + regval = rd32(E1000_TXSTMPL); + regval |= (u64)rd32(E1000_TXSTMPH) << 32; + + igb_systim_to_hwtstamp(adapter, &shhwtstamps, regval); + skb_tstamp_tx(buffer_info->skb, &shhwtstamps); +} + +/** + * igb_clean_tx_irq - Reclaim resources after transmit completes + * @q_vector: pointer to q_vector containing needed info + * returns true if ring is completely cleaned + **/ +static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) +{ + struct igb_adapter *adapter = q_vector->adapter; + struct igb_ring *tx_ring = q_vector->tx.ring; + struct igb_tx_buffer *tx_buffer; + union e1000_adv_tx_desc *tx_desc, *eop_desc; + unsigned int total_bytes = 0, total_packets = 0; + unsigned int budget = q_vector->tx.work_limit; + unsigned int i = tx_ring->next_to_clean; + + if (test_bit(__IGB_DOWN, &adapter->state)) + return true; + + tx_buffer = &tx_ring->tx_buffer_info[i]; + tx_desc = IGB_TX_DESC(tx_ring, i); + i -= tx_ring->count; + + for (; budget; budget--) { + eop_desc = tx_buffer->next_to_watch; + + /* prevent any other reads prior to eop_desc */ + rmb(); + + /* if next_to_watch is not set then there is no work pending */ + if (!eop_desc) + break; + + /* if DD is not set pending work has not been completed */ + if (!(eop_desc->wb.status & cpu_to_le32(E1000_TXD_STAT_DD))) + break; + + /* clear next_to_watch to prevent false hangs */ + tx_buffer->next_to_watch = NULL; + + /* update the statistics for this packet */ + total_bytes += tx_buffer->bytecount; + total_packets += tx_buffer->gso_segs; + + /* retrieve hardware timestamp */ + igb_tx_hwtstamp(q_vector, tx_buffer); + + /* free the skb */ + dev_kfree_skb_any(tx_buffer->skb); + tx_buffer->skb = NULL; + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + tx_buffer->dma, + tx_buffer->length, + DMA_TO_DEVICE); + + /* clear last DMA location and unmap remaining buffers */ + while (tx_desc != eop_desc) { + tx_buffer->dma = 0; + + tx_buffer++; + tx_desc++; + i++; + if (unlikely(!i)) { + i -= tx_ring->count; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = IGB_TX_DESC(tx_ring, 0); + } + + /* unmap any remaining paged data */ + if (tx_buffer->dma) { + dma_unmap_page(tx_ring->dev, + tx_buffer->dma, + tx_buffer->length, + DMA_TO_DEVICE); + } + } + + /* clear last DMA location */ + tx_buffer->dma = 0; + + /* move us one more past the eop_desc for start of next pkt */ + tx_buffer++; + tx_desc++; + i++; + if (unlikely(!i)) { + i -= tx_ring->count; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = IGB_TX_DESC(tx_ring, 0); + } + } + + i += tx_ring->count; + tx_ring->next_to_clean = i; + u64_stats_update_begin(&tx_ring->tx_syncp); + tx_ring->tx_stats.bytes += total_bytes; + tx_ring->tx_stats.packets += total_packets; + u64_stats_update_end(&tx_ring->tx_syncp); + q_vector->tx.total_bytes += total_bytes; + q_vector->tx.total_packets += total_packets; + + if (test_bit(IGB_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags)) { + struct e1000_hw *hw = &adapter->hw; + + eop_desc = tx_buffer->next_to_watch; + + /* Detect a transmit hang in hardware, this serializes the + * check with the clearing of time_stamp and movement of i */ + clear_bit(IGB_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags); + if (eop_desc && + time_after(jiffies, tx_buffer->time_stamp + + (adapter->tx_timeout_factor * HZ)) && + !(rd32(E1000_STATUS) & E1000_STATUS_TXOFF)) { + + /* detected Tx unit hang */ + dev_err(tx_ring->dev, + "Detected Tx Unit Hang\n" + " Tx Queue <%d>\n" + " TDH <%x>\n" + " TDT <%x>\n" + " next_to_use <%x>\n" + " next_to_clean <%x>\n" + "buffer_info[next_to_clean]\n" + " time_stamp <%lx>\n" + " next_to_watch <%p>\n" + " jiffies <%lx>\n" + " desc.status <%x>\n", + tx_ring->queue_index, + rd32(E1000_TDH(tx_ring->reg_idx)), + readl(tx_ring->tail), + tx_ring->next_to_use, + tx_ring->next_to_clean, + tx_buffer->time_stamp, + eop_desc, + jiffies, + eop_desc->wb.status); + netif_stop_subqueue(tx_ring->netdev, + tx_ring->queue_index); + + /* we are about to reset, no point in enabling stuff */ + return true; + } + } + + if (unlikely(total_packets && + netif_carrier_ok(tx_ring->netdev) && + igb_desc_unused(tx_ring) >= IGB_TX_QUEUE_WAKE)) { + /* Make sure that anybody stopping the queue after this + * sees the new next_to_clean. + */ + smp_mb(); + if (__netif_subqueue_stopped(tx_ring->netdev, + tx_ring->queue_index) && + !(test_bit(__IGB_DOWN, &adapter->state))) { + netif_wake_subqueue(tx_ring->netdev, + tx_ring->queue_index); + + u64_stats_update_begin(&tx_ring->tx_syncp); + tx_ring->tx_stats.restart_queue++; + u64_stats_update_end(&tx_ring->tx_syncp); + } + } + + return !!budget; +} + +static inline void igb_rx_checksum(struct igb_ring *ring, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + skb_checksum_none_assert(skb); + + /* Ignore Checksum bit is set */ + if (igb_test_staterr(rx_desc, E1000_RXD_STAT_IXSM)) + return; + + /* Rx checksum disabled via ethtool */ + if (!(ring->netdev->features & NETIF_F_RXCSUM)) + return; + + /* TCP/UDP checksum error bit is set */ + if (igb_test_staterr(rx_desc, + 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 (!((skb->len == 60) && + test_bit(IGB_RING_FLAG_RX_SCTP_CSUM, &ring->flags))) { + u64_stats_update_begin(&ring->rx_syncp); + ring->rx_stats.csum_err++; + u64_stats_update_end(&ring->rx_syncp); + } + /* let the stack verify checksum errors */ + return; + } + /* It must be a TCP or UDP packet with a valid checksum */ + if (igb_test_staterr(rx_desc, E1000_RXD_STAT_TCPCS | + E1000_RXD_STAT_UDPCS)) + skb->ip_summed = CHECKSUM_UNNECESSARY; + + dev_dbg(ring->dev, "cksum success: bits %08X\n", + le32_to_cpu(rx_desc->wb.upper.status_error)); +} + +static inline void igb_rx_hash(struct igb_ring *ring, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + if (ring->netdev->features & NETIF_F_RXHASH) + skb->rxhash = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss); +} + +static void igb_rx_hwtstamp(struct igb_q_vector *q_vector, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + struct igb_adapter *adapter = q_vector->adapter; + struct e1000_hw *hw = &adapter->hw; + u64 regval; + + if (!igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP | + E1000_RXDADV_STAT_TS)) + return; + + /* + * If this bit is set, then the RX registers contain the time stamp. No + * other packet will be time stamped until we read these registers, so + * read the registers to make them available again. Because only one + * packet can be time stamped at a time, we know that the register + * values must belong to this one here and therefore we don't need to + * compare any of the additional attributes stored for it. + * + * If nothing went wrong, then it should have a shared tx_flags that we + * can turn into a skb_shared_hwtstamps. + */ + if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { + u32 *stamp = (u32 *)skb->data; + regval = le32_to_cpu(*(stamp + 2)); + regval |= (u64)le32_to_cpu(*(stamp + 3)) << 32; + skb_pull(skb, IGB_TS_HDR_LEN); + } else { + if(!(rd32(E1000_TSYNCRXCTL) & E1000_TSYNCRXCTL_VALID)) + return; + + regval = rd32(E1000_RXSTMPL); + regval |= (u64)rd32(E1000_RXSTMPH) << 32; + } + + igb_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), regval); +} + +static void igb_rx_vlan(struct igb_ring *ring, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + if (igb_test_staterr(rx_desc, E1000_RXD_STAT_VP)) { + u16 vid; + if (igb_test_staterr(rx_desc, E1000_RXDEXT_STATERR_LB) && + test_bit(IGB_RING_FLAG_RX_LB_VLAN_BSWAP, &ring->flags)) + vid = be16_to_cpu(rx_desc->wb.upper.vlan); + else + vid = le16_to_cpu(rx_desc->wb.upper.vlan); + + __vlan_hwaccel_put_tag(skb, vid); + } +} + +static inline u16 igb_get_hlen(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 > IGB_RX_HDR_LEN) + hlen = IGB_RX_HDR_LEN; + return hlen; +} + +static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, int budget) +{ + struct igb_ring *rx_ring = q_vector->rx.ring; + union e1000_adv_rx_desc *rx_desc; + const int current_node = numa_node_id(); + unsigned int total_bytes = 0, total_packets = 0; + u16 cleaned_count = igb_desc_unused(rx_ring); + u16 i = rx_ring->next_to_clean; + + rx_desc = IGB_RX_DESC(rx_ring, i); + + while (igb_test_staterr(rx_desc, E1000_RXD_STAT_DD)) { + struct igb_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i]; + struct sk_buff *skb = buffer_info->skb; + union e1000_adv_rx_desc *next_rxd; + + buffer_info->skb = NULL; + prefetch(skb->data); + + i++; + if (i == rx_ring->count) + i = 0; + + next_rxd = IGB_RX_DESC(rx_ring, i); + prefetch(next_rxd); + + /* + * This memory barrier is needed to keep us from reading + * any other fields out of the rx_desc until we know the + * RXD_STAT_DD bit is set + */ + rmb(); + + if (!skb_is_nonlinear(skb)) { + __skb_put(skb, igb_get_hlen(rx_desc)); + dma_unmap_single(rx_ring->dev, buffer_info->dma, + IGB_RX_HDR_LEN, + DMA_FROM_DEVICE); + buffer_info->dma = 0; + } + + if (rx_desc->wb.upper.length) { + u16 length = le16_to_cpu(rx_desc->wb.upper.length); + + skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags, + buffer_info->page, + buffer_info->page_offset, + length); + + skb->len += length; + skb->data_len += length; + skb->truesize += PAGE_SIZE / 2; + + if ((page_count(buffer_info->page) != 1) || + (page_to_nid(buffer_info->page) != current_node)) + buffer_info->page = NULL; + else + get_page(buffer_info->page); + + dma_unmap_page(rx_ring->dev, buffer_info->page_dma, + PAGE_SIZE / 2, DMA_FROM_DEVICE); + buffer_info->page_dma = 0; + } + + if (!igb_test_staterr(rx_desc, E1000_RXD_STAT_EOP)) { + struct igb_rx_buffer *next_buffer; + next_buffer = &rx_ring->rx_buffer_info[i]; + buffer_info->skb = next_buffer->skb; + buffer_info->dma = next_buffer->dma; + next_buffer->skb = skb; + next_buffer->dma = 0; + goto next_desc; + } + + if (igb_test_staterr(rx_desc, + E1000_RXDEXT_ERR_FRAME_ERR_MASK)) { + dev_kfree_skb_any(skb); + goto next_desc; + } + + igb_rx_hwtstamp(q_vector, rx_desc, skb); + igb_rx_hash(rx_ring, rx_desc, skb); + igb_rx_checksum(rx_ring, rx_desc, skb); + igb_rx_vlan(rx_ring, rx_desc, skb); + + total_bytes += skb->len; + total_packets++; + + skb->protocol = eth_type_trans(skb, rx_ring->netdev); + + napi_gro_receive(&q_vector->napi, skb); + + budget--; +next_desc: + if (!budget) + break; + + cleaned_count++; + /* return some buffers to hardware, one at a time is too slow */ + if (cleaned_count >= IGB_RX_BUFFER_WRITE) { + igb_alloc_rx_buffers(rx_ring, cleaned_count); + cleaned_count = 0; + } + + /* use prefetched values */ + rx_desc = next_rxd; + } + + rx_ring->next_to_clean = i; + u64_stats_update_begin(&rx_ring->rx_syncp); + rx_ring->rx_stats.packets += total_packets; + rx_ring->rx_stats.bytes += total_bytes; + u64_stats_update_end(&rx_ring->rx_syncp); + q_vector->rx.total_packets += total_packets; + q_vector->rx.total_bytes += total_bytes; + + if (cleaned_count) + igb_alloc_rx_buffers(rx_ring, cleaned_count); + + return !!budget; +} + +static bool igb_alloc_mapped_skb(struct igb_ring *rx_ring, + struct igb_rx_buffer *bi) +{ + struct sk_buff *skb = bi->skb; + dma_addr_t dma = bi->dma; + + if (dma) + return true; + + if (likely(!skb)) { + skb = netdev_alloc_skb_ip_align(rx_ring->netdev, + IGB_RX_HDR_LEN); + bi->skb = skb; + if (!skb) { + rx_ring->rx_stats.alloc_failed++; + return false; + } + + /* initialize skb for ring */ + skb_record_rx_queue(skb, rx_ring->queue_index); + } + + dma = dma_map_single(rx_ring->dev, skb->data, + IGB_RX_HDR_LEN, DMA_FROM_DEVICE); + + if (dma_mapping_error(rx_ring->dev, dma)) { + rx_ring->rx_stats.alloc_failed++; + return false; + } + + bi->dma = dma; + return true; +} + +static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, + struct igb_rx_buffer *bi) +{ + struct page *page = bi->page; + dma_addr_t page_dma = bi->page_dma; + unsigned int page_offset = bi->page_offset ^ (PAGE_SIZE / 2); + + if (page_dma) + return true; + + if (!page) { + page = netdev_alloc_page(rx_ring->netdev); + bi->page = page; + if (unlikely(!page)) { + rx_ring->rx_stats.alloc_failed++; + return false; + } + } + + page_dma = dma_map_page(rx_ring->dev, page, + page_offset, PAGE_SIZE / 2, + DMA_FROM_DEVICE); + + if (dma_mapping_error(rx_ring->dev, page_dma)) { + rx_ring->rx_stats.alloc_failed++; + return false; + } + + bi->page_dma = page_dma; + bi->page_offset = page_offset; + return true; +} + +/** + * igb_alloc_rx_buffers - Replace used receive buffers; packet split + * @adapter: address of board private structure + **/ +void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) +{ + union e1000_adv_rx_desc *rx_desc; + struct igb_rx_buffer *bi; + u16 i = rx_ring->next_to_use; + + rx_desc = IGB_RX_DESC(rx_ring, i); + bi = &rx_ring->rx_buffer_info[i]; + i -= rx_ring->count; + + while (cleaned_count--) { + if (!igb_alloc_mapped_skb(rx_ring, bi)) + break; + + /* Refresh the desc even if buffer_addrs didn't change + * because each write-back erases this info. */ + rx_desc->read.hdr_addr = cpu_to_le64(bi->dma); + + if (!igb_alloc_mapped_page(rx_ring, bi)) + break; + + rx_desc->read.pkt_addr = cpu_to_le64(bi->page_dma); + + rx_desc++; + bi++; + i++; + if (unlikely(!i)) { + rx_desc = IGB_RX_DESC(rx_ring, 0); + bi = rx_ring->rx_buffer_info; + i -= rx_ring->count; + } + + /* clear the hdr_addr for the next_to_use descriptor */ + rx_desc->read.hdr_addr = 0; + } + + i += rx_ring->count; + + if (rx_ring->next_to_use != i) { + rx_ring->next_to_use = i; + + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. (Only + * applicable for weak-ordered memory model archs, + * such as IA-64). */ + wmb(); + writel(i, rx_ring->tail); + } +} + +/** + * igb_mii_ioctl - + * @netdev: + * @ifreq: + * @cmd: + **/ +static int igb_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct mii_ioctl_data *data = if_mii(ifr); + + if (adapter->hw.phy.media_type != e1000_media_type_copper) + return -EOPNOTSUPP; + + switch (cmd) { + case SIOCGMIIPHY: + data->phy_id = adapter->hw.phy.addr; + break; + case SIOCGMIIREG: + if (igb_read_phy_reg(&adapter->hw, data->reg_num & 0x1F, + &data->val_out)) + return -EIO; + break; + case SIOCSMIIREG: + default: + return -EOPNOTSUPP; + } + return 0; +} + +/** + * igb_hwtstamp_ioctl - control hardware time stamping + * @netdev: + * @ifreq: + * @cmd: + * + * Outgoing time stamping can be enabled and disabled. Play nice and + * disable it when requested, although it shouldn't case any overhead + * when no packet needs it. At most one packet in the queue may be + * marked for time stamping, otherwise it would be impossible to tell + * for sure to which packet the hardware time stamp belongs. + * + * Incoming time stamping has to be configured via the hardware + * filters. Not all combinations are supported, in particular event + * type has to be specified. Matching the kind of event packet is + * not supported, with the exception of "all V2 events regardless of + * level 2 or 4". + * + **/ +static int igb_hwtstamp_ioctl(struct net_device *netdev, + struct ifreq *ifr, int cmd) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + struct hwtstamp_config config; + u32 tsync_tx_ctl = E1000_TSYNCTXCTL_ENABLED; + u32 tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED; + u32 tsync_rx_cfg = 0; + bool is_l4 = false; + bool is_l2 = false; + u32 regval; + + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) + return -EFAULT; + + /* reserved for future extensions */ + if (config.flags) + return -EINVAL; + + switch (config.tx_type) { + case HWTSTAMP_TX_OFF: + tsync_tx_ctl = 0; + case HWTSTAMP_TX_ON: + break; + default: + return -ERANGE; + } + + switch (config.rx_filter) { + case HWTSTAMP_FILTER_NONE: + tsync_rx_ctl = 0; + break; + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_ALL: + /* + * register TSYNCRXCFG must be set, therefore it is not + * possible to time stamp both Sync and Delay_Req messages + * => fall back to time stamping all packets + */ + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_ALL; + config.rx_filter = HWTSTAMP_FILTER_ALL; + break; + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L4_V1; + tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V1_SYNC_MESSAGE; + is_l4 = true; + break; + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L4_V1; + tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V1_DELAY_REQ_MESSAGE; + is_l4 = true; + break; + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L2_L4_V2; + tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V2_SYNC_MESSAGE; + is_l2 = true; + is_l4 = true; + config.rx_filter = HWTSTAMP_FILTER_SOME; + break; + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L2_L4_V2; + tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V2_DELAY_REQ_MESSAGE; + is_l2 = true; + is_l4 = true; + config.rx_filter = HWTSTAMP_FILTER_SOME; + break; + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_EVENT_V2; + config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + is_l2 = true; + is_l4 = true; + break; + default: + return -ERANGE; + } + + if (hw->mac.type == e1000_82575) { + if (tsync_rx_ctl | tsync_tx_ctl) + return -EINVAL; + return 0; + } + + /* + * Per-packet timestamping only works if all packets are + * timestamped, so enable timestamping in all packets as + * long as one rx filter was configured. + */ + if ((hw->mac.type >= e1000_82580) && tsync_rx_ctl) { + tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED; + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_ALL; + } + + /* enable/disable TX */ + regval = rd32(E1000_TSYNCTXCTL); + regval &= ~E1000_TSYNCTXCTL_ENABLED; + regval |= tsync_tx_ctl; + wr32(E1000_TSYNCTXCTL, regval); + + /* enable/disable RX */ + regval = rd32(E1000_TSYNCRXCTL); + regval &= ~(E1000_TSYNCRXCTL_ENABLED | E1000_TSYNCRXCTL_TYPE_MASK); + regval |= tsync_rx_ctl; + wr32(E1000_TSYNCRXCTL, regval); + + /* define which PTP packets are time stamped */ + wr32(E1000_TSYNCRXCFG, tsync_rx_cfg); + + /* define ethertype filter for timestamped packets */ + if (is_l2) + wr32(E1000_ETQF(3), + (E1000_ETQF_FILTER_ENABLE | /* enable filter */ + E1000_ETQF_1588 | /* enable timestamping */ + ETH_P_1588)); /* 1588 eth protocol type */ + else + wr32(E1000_ETQF(3), 0); + +#define PTP_PORT 319 + /* L4 Queue Filter[3]: filter by destination port and protocol */ + if (is_l4) { + u32 ftqf = (IPPROTO_UDP /* UDP */ + | E1000_FTQF_VF_BP /* VF not compared */ + | E1000_FTQF_1588_TIME_STAMP /* Enable Timestamping */ + | E1000_FTQF_MASK); /* mask all inputs */ + ftqf &= ~E1000_FTQF_MASK_PROTO_BP; /* enable protocol check */ + + wr32(E1000_IMIR(3), htons(PTP_PORT)); + wr32(E1000_IMIREXT(3), + (E1000_IMIREXT_SIZE_BP | E1000_IMIREXT_CTRL_BP)); + if (hw->mac.type == e1000_82576) { + /* enable source port check */ + wr32(E1000_SPQF(3), htons(PTP_PORT)); + ftqf &= ~E1000_FTQF_MASK_SOURCE_PORT_BP; + } + wr32(E1000_FTQF(3), ftqf); + } else { + wr32(E1000_FTQF(3), E1000_FTQF_MASK); + } + wrfl(); + + adapter->hwtstamp_config = config; + + /* clear TX/RX time stamp registers, just to be sure */ + regval = rd32(E1000_TXSTMPH); + regval = rd32(E1000_RXSTMPH); + + return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? + -EFAULT : 0; +} + +/** + * igb_ioctl - + * @netdev: + * @ifreq: + * @cmd: + **/ +static int igb_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) +{ + switch (cmd) { + case SIOCGMIIPHY: + case SIOCGMIIREG: + case SIOCSMIIREG: + return igb_mii_ioctl(netdev, ifr, cmd); + case SIOCSHWTSTAMP: + return igb_hwtstamp_ioctl(netdev, ifr, cmd); + default: + return -EOPNOTSUPP; + } +} + +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 = adapter->pdev->pcie_cap; + 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 = adapter->pdev->pcie_cap; + if (!cap_offset) + return -E1000_ERR_CONFIG; + + pci_write_config_word(adapter->pdev, cap_offset + reg, *value); + + return 0; +} + +static void igb_vlan_mode(struct net_device *netdev, u32 features) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + u32 ctrl, rctl; + bool enable = !!(features & NETIF_F_HW_VLAN_RX); + + if (enable) { + /* enable VLAN tag insert/strip */ + ctrl = rd32(E1000_CTRL); + ctrl |= E1000_CTRL_VME; + wr32(E1000_CTRL, ctrl); + + /* Disable CFI check */ + rctl = rd32(E1000_RCTL); + rctl &= ~E1000_RCTL_CFIEN; + wr32(E1000_RCTL, rctl); + } else { + /* disable VLAN tag insert/strip */ + ctrl = rd32(E1000_CTRL); + ctrl &= ~E1000_CTRL_VME; + wr32(E1000_CTRL, ctrl); + } + + igb_rlpml_set(adapter); +} + +static void igb_vlan_rx_add_vid(struct net_device *netdev, u16 vid) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + int pf_id = adapter->vfs_allocated_count; + + /* attempt to add filter to vlvf array */ + igb_vlvf_set(adapter, vid, true, pf_id); + + /* add the filter since PF can receive vlans w/o entry in vlvf */ + igb_vfta_set(hw, vid, true); + + set_bit(vid, adapter->active_vlans); +} + +static void igb_vlan_rx_kill_vid(struct net_device *netdev, u16 vid) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + int pf_id = adapter->vfs_allocated_count; + s32 err; + + /* remove vlan from VLVF table array */ + err = igb_vlvf_set(adapter, vid, false, pf_id); + + /* if vid was not present in VLVF just remove it from table */ + if (err) + igb_vfta_set(hw, vid, false); + + clear_bit(vid, adapter->active_vlans); +} + +static void igb_restore_vlan(struct igb_adapter *adapter) +{ + u16 vid; + + igb_vlan_mode(adapter->netdev, adapter->netdev->features); + + for_each_set_bit(vid, adapter->active_vlans, VLAN_N_VID) + igb_vlan_rx_add_vid(adapter->netdev, vid); +} + +int igb_set_spd_dplx(struct igb_adapter *adapter, u32 spd, u8 dplx) +{ + struct pci_dev *pdev = adapter->pdev; + struct e1000_mac_info *mac = &adapter->hw.mac; + + mac->autoneg = 0; + + /* Make sure dplx is at most 1 bit and lsb of speed is not set + * for the switch() below to work */ + if ((spd & 1) || (dplx & ~1)) + goto err_inval; + + /* Fiber NIC's only allow 1000 Gbps Full duplex */ + if ((adapter->hw.phy.media_type == e1000_media_type_internal_serdes) && + spd != SPEED_1000 && + dplx != DUPLEX_FULL) + goto err_inval; + + switch (spd + dplx) { + case SPEED_10 + DUPLEX_HALF: + mac->forced_speed_duplex = ADVERTISE_10_HALF; + break; + case SPEED_10 + DUPLEX_FULL: + mac->forced_speed_duplex = ADVERTISE_10_FULL; + break; + case SPEED_100 + DUPLEX_HALF: + mac->forced_speed_duplex = ADVERTISE_100_HALF; + break; + case SPEED_100 + DUPLEX_FULL: + mac->forced_speed_duplex = ADVERTISE_100_FULL; + break; + case SPEED_1000 + DUPLEX_FULL: + mac->autoneg = 1; + adapter->hw.phy.autoneg_advertised = ADVERTISE_1000_FULL; + break; + case SPEED_1000 + DUPLEX_HALF: /* not supported */ + default: + goto err_inval; + } + return 0; + +err_inval: + dev_err(&pdev->dev, "Unsupported Speed/Duplex configuration\n"); + return -EINVAL; +} + +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); + struct e1000_hw *hw = &adapter->hw; + u32 ctrl, rctl, status; + u32 wufc = adapter->wol; +#ifdef CONFIG_PM + int retval = 0; +#endif + + netif_device_detach(netdev); + + if (netif_running(netdev)) + igb_close(netdev); + + igb_clear_interrupt_scheme(adapter); + +#ifdef CONFIG_PM + retval = pci_save_state(pdev); + if (retval) + return retval; +#endif + + status = rd32(E1000_STATUS); + if (status & E1000_STATUS_LU) + wufc &= ~E1000_WUFC_LNKC; + + if (wufc) { + igb_setup_rctl(adapter); + igb_set_rx_mode(netdev); + + /* turn on all-multi mode if wake on multicast is enabled */ + if (wufc & E1000_WUFC_MC) { + rctl = rd32(E1000_RCTL); + rctl |= E1000_RCTL_MPE; + wr32(E1000_RCTL, rctl); + } + + ctrl = rd32(E1000_CTRL); + /* advertise wake from D3Cold */ + #define E1000_CTRL_ADVD3WUC 0x00100000 + /* phy power management enable */ + #define E1000_CTRL_EN_PHY_PWR_MGMT 0x00200000 + ctrl |= E1000_CTRL_ADVD3WUC; + wr32(E1000_CTRL, ctrl); + + /* Allow time for pending master requests to run */ + igb_disable_pcie_master(hw); + + wr32(E1000_WUC, E1000_WUC_PME_EN); + wr32(E1000_WUFC, wufc); + } else { + wr32(E1000_WUC, 0); + wr32(E1000_WUFC, 0); + } + + *enable_wake = wufc || adapter->en_mng_pt; + if (!*enable_wake) + igb_power_down_link(adapter); + else + igb_power_up_link(adapter); + + /* Release control of h/w to f/w. If f/w is AMT enabled, this + * would have already happened in close and is redundant. */ + igb_release_hw_control(adapter); + + pci_disable_device(pdev); + + 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); + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + u32 err; + + pci_set_power_state(pdev, PCI_D0); + pci_restore_state(pdev); + pci_save_state(pdev); + + err = pci_enable_device_mem(pdev); + if (err) { + dev_err(&pdev->dev, + "igb: Cannot enable PCI device from suspend\n"); + return err; + } + pci_set_master(pdev); + + pci_enable_wake(pdev, PCI_D3hot, 0); + pci_enable_wake(pdev, PCI_D3cold, 0); + + if (igb_init_interrupt_scheme(adapter)) { + dev_err(&pdev->dev, "Unable to allocate memory for queues\n"); + return -ENOMEM; + } + + igb_reset(adapter); + + /* let the f/w know that the h/w is now under the control of the + * driver. */ + igb_get_hw_control(adapter); + + wr32(E1000_WUS, ~0); + + if (netif_running(netdev)) { + err = igb_open(netdev); + if (err) + return err; + } + + netif_device_attach(netdev); + + return 0; +} +#endif + +static void igb_shutdown(struct pci_dev *pdev) +{ + 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 +/* + * Polling 'interrupt' - used by things like netconsole to send skbs + * without having to re-enable interrupts. It's not called while + * the interrupt routine is executing. + */ +static void igb_netpoll(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + struct igb_q_vector *q_vector; + int i; + + for (i = 0; i < adapter->num_q_vectors; i++) { + q_vector = adapter->q_vector[i]; + if (adapter->msix_entries) + wr32(E1000_EIMC, q_vector->eims_value); + else + igb_irq_disable(adapter); + napi_schedule(&q_vector->napi); + } +} +#endif /* CONFIG_NET_POLL_CONTROLLER */ + +/** + * igb_io_error_detected - called when PCI error is detected + * @pdev: Pointer to PCI device + * @state: The current pci connection state + * + * This function is called after a PCI bus error affecting + * this device has been detected. + */ +static pci_ers_result_t igb_io_error_detected(struct pci_dev *pdev, + pci_channel_state_t state) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct igb_adapter *adapter = netdev_priv(netdev); + + 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); + + /* Request a slot slot reset. */ + return PCI_ERS_RESULT_NEED_RESET; +} + +/** + * igb_io_slot_reset - called after the pci bus has been reset. + * @pdev: Pointer to PCI device + * + * Restart the card from scratch, as if from a cold-boot. Implementation + * resembles the first-half of the igb_resume routine. + */ +static pci_ers_result_t igb_io_slot_reset(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + pci_ers_result_t result; + int err; + + if (pci_enable_device_mem(pdev)) { + dev_err(&pdev->dev, + "Cannot re-enable PCI device after reset.\n"); + result = PCI_ERS_RESULT_DISCONNECT; + } else { + pci_set_master(pdev); + pci_restore_state(pdev); + pci_save_state(pdev); + + pci_enable_wake(pdev, PCI_D3hot, 0); + pci_enable_wake(pdev, PCI_D3cold, 0); + + igb_reset(adapter); + wr32(E1000_WUS, ~0); + result = PCI_ERS_RESULT_RECOVERED; + } + + err = pci_cleanup_aer_uncorrect_error_status(pdev); + if (err) { + dev_err(&pdev->dev, "pci_cleanup_aer_uncorrect_error_status " + "failed 0x%0x\n", err); + /* non-fatal, continue */ + } + + return result; +} + +/** + * igb_io_resume - called when traffic can start flowing again. + * @pdev: Pointer to PCI device + * + * This callback is called when the error recovery driver tells us that + * its OK to resume normal operation. Implementation resembles the + * second-half of the igb_resume routine. + */ +static void igb_io_resume(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct igb_adapter *adapter = netdev_priv(netdev); + + if (netif_running(netdev)) { + if (igb_up(adapter)) { + dev_err(&pdev->dev, "igb_up failed after reset\n"); + return; + } + } + + netif_device_attach(netdev); + + /* let the f/w know that the h/w is now under the control of the + * driver. */ + igb_get_hw_control(adapter); +} + +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; + + /* 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)); + + /* Indicate to hardware the Address is Valid. */ + rar_high |= E1000_RAH_AV; + + if (hw->mac.type == e1000_82575) + rar_high |= E1000_RAH_POOL_1 * qsel; + else + rar_high |= E1000_RAH_POOL_1 << qsel; + + 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; + /* 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_rar_set_qsel(adapter, mac_addr, rar_entry, vf); + + return 0; +} + +static int igb_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + if (!is_valid_ether_addr(mac) || (vf >= adapter->vfs_allocated_count)) + return -EINVAL; + adapter->vf_data[vf].flags |= IGB_VF_FLAG_PF_SET_MAC; + dev_info(&adapter->pdev->dev, "setting MAC %pM on VF %d\n", mac, vf); + dev_info(&adapter->pdev->dev, "Reload the VF driver to make this" + " change effective."); + if (test_bit(__IGB_DOWN, &adapter->state)) { + dev_warn(&adapter->pdev->dev, "The VF MAC address has been set," + " but the PF device is not up.\n"); + dev_warn(&adapter->pdev->dev, "Bring the PF device up before" + " attempting to use the VF device.\n"); + } + return igb_set_vf_mac(adapter, vf, mac); +} + +static int igb_link_mbps(int internal_link_speed) +{ + switch (internal_link_speed) { + case SPEED_100: + return 100; + case SPEED_1000: + return 1000; + default: + return 0; + } +} + +static void igb_set_vf_rate_limit(struct e1000_hw *hw, int vf, int tx_rate, + int link_speed) +{ + int rf_dec, rf_int; + u32 bcnrc_val; + + if (tx_rate != 0) { + /* Calculate the rate factor values to set */ + rf_int = link_speed / tx_rate; + rf_dec = (link_speed - (rf_int * tx_rate)); + rf_dec = (rf_dec * (1<<E1000_RTTBCNRC_RF_INT_SHIFT)) / tx_rate; + + bcnrc_val = E1000_RTTBCNRC_RS_ENA; + bcnrc_val |= ((rf_int<<E1000_RTTBCNRC_RF_INT_SHIFT) & + E1000_RTTBCNRC_RF_INT_MASK); + bcnrc_val |= (rf_dec & E1000_RTTBCNRC_RF_DEC_MASK); + } else { + bcnrc_val = 0; + } + + wr32(E1000_RTTDQSEL, vf); /* vf X uses queue X */ + wr32(E1000_RTTBCNRC, bcnrc_val); +} + +static void igb_check_vf_rate_limit(struct igb_adapter *adapter) +{ + int actual_link_speed, i; + bool reset_rate = false; + + /* VF TX rate limit was not set or not supported */ + if ((adapter->vf_rate_link_speed == 0) || + (adapter->hw.mac.type != e1000_82576)) + return; + + actual_link_speed = igb_link_mbps(adapter->link_speed); + if (actual_link_speed != adapter->vf_rate_link_speed) { + reset_rate = true; + adapter->vf_rate_link_speed = 0; + dev_info(&adapter->pdev->dev, + "Link speed has been changed. VF Transmit " + "rate is disabled\n"); + } + + for (i = 0; i < adapter->vfs_allocated_count; i++) { + if (reset_rate) + adapter->vf_data[i].tx_rate = 0; + + igb_set_vf_rate_limit(&adapter->hw, i, + adapter->vf_data[i].tx_rate, + actual_link_speed); + } +} + +static int igb_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + int actual_link_speed; + + if (hw->mac.type != e1000_82576) + return -EOPNOTSUPP; + + actual_link_speed = igb_link_mbps(adapter->link_speed); + if ((vf >= adapter->vfs_allocated_count) || + (!(rd32(E1000_STATUS) & E1000_STATUS_LU)) || + (tx_rate < 0) || (tx_rate > actual_link_speed)) + return -EINVAL; + + adapter->vf_rate_link_speed = actual_link_speed; + adapter->vf_data[vf].tx_rate = (u16)tx_rate; + igb_set_vf_rate_limit(hw, vf, tx_rate, actual_link_speed); + + return 0; +} + +static int igb_ndo_get_vf_config(struct net_device *netdev, + int vf, struct ifla_vf_info *ivi) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + if (vf >= adapter->vfs_allocated_count) + return -EINVAL; + ivi->vf = vf; + memcpy(&ivi->mac, adapter->vf_data[vf].vf_mac_addresses, ETH_ALEN); + ivi->tx_rate = adapter->vf_data[vf].tx_rate; + ivi->vlan = adapter->vf_data[vf].pf_vlan; + ivi->qos = adapter->vf_data[vf].pf_qos; + return 0; +} + +static void igb_vmm_control(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 reg; + + switch (hw->mac.type) { + case e1000_82575: + default: + /* replication is not supported for 82575 */ + return; + case e1000_82576: + /* notify HW that the MAC is adding vlan tags */ + reg = rd32(E1000_DTXCTL); + reg |= E1000_DTXCTL_VLAN_ADDED; + wr32(E1000_DTXCTL, reg); + case e1000_82580: + /* enable replication vlan tag stripping */ + reg = rd32(E1000_RPLOLR); + reg |= E1000_RPLOLR_STRVLAN; + wr32(E1000_RPLOLR, reg); + case e1000_i350: + /* none of the above registers are supported by i350 */ + break; + } + + if (adapter->vfs_allocated_count) { + igb_vmdq_set_loopback_pf(hw, true); + igb_vmdq_set_replication_pf(hw, true); + igb_vmdq_set_anti_spoofing_pf(hw, true, + adapter->vfs_allocated_count); + } else { + igb_vmdq_set_loopback_pf(hw, false); + igb_vmdq_set_replication_pf(hw, false); + } +} + +static void igb_init_dmac(struct igb_adapter *adapter, u32 pba) +{ + struct e1000_hw *hw = &adapter->hw; + u32 dmac_thr; + u16 hwm; + + if (hw->mac.type > e1000_82580) { + if (adapter->flags & IGB_FLAG_DMAC) { + u32 reg; + + /* force threshold to 0. */ + wr32(E1000_DMCTXTH, 0); + + /* + * DMA Coalescing high water mark needs to be higher + * than the RX threshold. set hwm to PBA - 2 * max + * frame size + */ + hwm = pba - (2 * adapter->max_frame_size); + reg = rd32(E1000_DMACR); + reg &= ~E1000_DMACR_DMACTHR_MASK; + dmac_thr = pba - 4; + + reg |= ((dmac_thr << E1000_DMACR_DMACTHR_SHIFT) + & E1000_DMACR_DMACTHR_MASK); + + /* transition to L0x or L1 if available..*/ + reg |= (E1000_DMACR_DMAC_EN | E1000_DMACR_DMAC_LX_MASK); + + /* watchdog timer= +-1000 usec in 32usec intervals */ + reg |= (1000 >> 5); + wr32(E1000_DMACR, reg); + + /* + * no lower threshold to disable + * coalescing(smart fifb)-UTRESH=0 + */ + wr32(E1000_DMCRTRH, 0); + wr32(E1000_FCRTC, hwm); + + reg = (IGB_DMCTLX_DCFLUSH_DIS | 0x4); + + wr32(E1000_DMCTLX, reg); + + /* + * free space in tx packet buffer to wake from + * DMA coal + */ + wr32(E1000_DMCTXTH, (IGB_MIN_TXPBSIZE - + (IGB_TX_BUF_4096 + adapter->max_frame_size)) >> 6); + + /* + * make low power state decision controlled + * by DMA coal + */ + reg = rd32(E1000_PCIEMISC); + reg &= ~E1000_PCIEMISC_LX_DECISION; + wr32(E1000_PCIEMISC, reg); + } /* endif adapter->dmac is not disabled */ + } else if (hw->mac.type == e1000_82580) { + u32 reg = rd32(E1000_PCIEMISC); + wr32(E1000_PCIEMISC, reg & ~E1000_PCIEMISC_LX_DECISION); + wr32(E1000_DMACR, 0); + } +} + +/* igb_main.c */ |