diff options
Diffstat (limited to 'drivers/net/ethernet/intel/igb/igb_main.c')
| -rw-r--r-- | drivers/net/ethernet/intel/igb/igb_main.c | 6890 |
1 files changed, 6890 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 00000000000..40d4c405fd7 --- /dev/null +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -0,0 +1,6890 @@ +/******************************************************************************* + + 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_vlan.h> +#include <linux/pci.h> +#include <linux/pci-aspm.h> +#include <linux/delay.h> +#include <linux/interrupt.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 0 +#define BUILD 6 +#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_adv(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 bool igb_clean_tx_irq(struct igb_q_vector *); +static int igb_poll(struct napi_struct *, int); +static bool igb_clean_rx_irq_adv(struct igb_q_vector *, int *, 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_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 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; + int n = 0; + struct igb_ring *tx_ring; + union e1000_adv_tx_desc *tx_desc; + struct my_u0 { u64 a; u64 b; } *u0; + struct igb_buffer *buffer_info; + struct igb_ring *rx_ring; + union e1000_adv_rx_desc *rx_desc; + u32 staterr; + int i = 0; + + 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++) { + tx_ring = adapter->tx_ring[n]; + buffer_info = &tx_ring->buffer_info[tx_ring->next_to_clean]; + printk(KERN_INFO " %5d %5X %5X %016llX %04X %3X %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++) { + tx_desc = E1000_TX_DESC_ADV(*tx_ring, i); + buffer_info = &tx_ring->buffer_info[i]; + u0 = (struct my_u0 *)tx_desc; + printk(KERN_INFO "T [0x%03X] %016llX %016llX %016llX" + " %04X %3X %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++) { + buffer_info = &rx_ring->buffer_info[i]; + rx_desc = E1000_RX_DESC_ADV(*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), + rx_ring->rx_buffer_len, true); + if (rx_ring->rx_buffer_len + < IGB_RXBUFFER_1024) + 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; + + for (i = 0; i < adapter->num_tx_queues; i++) { + 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; + /* For 82575, context index must be unique per ring. */ + if (adapter->hw.mac.type == e1000_82575) + ring->flags = IGB_RING_FLAG_TX_CTX_IDX; + adapter->tx_ring[i] = ring; + } + + for (i = 0; i < adapter->num_rx_queues; i++) { + 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->rx_buffer_len = MAXIMUM_ETHERNET_VLAN_SIZE; + ring->flags = IGB_RING_FLAG_RX_CSUM; /* enable rx checksum */ + /* set flag indicating ring supports SCTP checksum offload */ + if (adapter->hw.mac.type >= e1000_82576) + ring->flags |= IGB_RING_FLAG_RX_SCTP_CSUM; + adapter->rx_ring[i] = ring; + } + + igb_cache_ring_register(adapter); + + return 0; + +err: + igb_free_queues(adapter); + + return -ENOMEM; +} + +#define IGB_N0_QUEUE -1 +static void igb_assign_vector(struct igb_q_vector *q_vector, int msix_vector) +{ + u32 msixbm = 0; + struct igb_adapter *adapter = q_vector->adapter; + struct e1000_hw *hw = &adapter->hw; + u32 ivar, index; + int rx_queue = IGB_N0_QUEUE; + int tx_queue = IGB_N0_QUEUE; + + 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-based method for assigning vectors. + Each queue has a single entry in the table to which we write + a vector number along with a "valid" bit. Sadly, the layout + of the table is somewhat counterintuitive. */ + if (rx_queue > IGB_N0_QUEUE) { + index = (rx_queue & 0x7); + ivar = array_rd32(E1000_IVAR0, index); + if (rx_queue < 8) { + /* vector goes into low byte of register */ + ivar = ivar & 0xFFFFFF00; + ivar |= msix_vector | E1000_IVAR_VALID; + } else { + /* vector goes into third byte of register */ + ivar = ivar & 0xFF00FFFF; + ivar |= (msix_vector | E1000_IVAR_VALID) << 16; + } + array_wr32(E1000_IVAR0, index, ivar); + } + if (tx_queue > IGB_N0_QUEUE) { + index = (tx_queue & 0x7); + ivar = array_rd32(E1000_IVAR0, index); + if (tx_queue < 8) { + /* vector goes into second byte of register */ + ivar = ivar & 0xFFFF00FF; + ivar |= (msix_vector | E1000_IVAR_VALID) << 8; + } else { + /* vector goes into high byte of register */ + ivar = ivar & 0x00FFFFFF; + ivar |= (msix_vector | E1000_IVAR_VALID) << 24; + } + array_wr32(E1000_IVAR0, index, ivar); + } + q_vector->eims_value = 1 << msix_vector; + break; + case e1000_82580: + case e1000_i350: + /* 82580 uses the same table-based approach as 82576 but has fewer + entries as a result we carry over for queues greater than 4. */ + if (rx_queue > IGB_N0_QUEUE) { + index = (rx_queue >> 1); + ivar = array_rd32(E1000_IVAR0, index); + if (rx_queue & 0x1) { + /* vector goes into third byte of register */ + ivar = ivar & 0xFF00FFFF; + ivar |= (msix_vector | E1000_IVAR_VALID) << 16; + } else { + /* vector goes into low byte of register */ + ivar = ivar & 0xFFFFFF00; + ivar |= msix_vector | E1000_IVAR_VALID; + } + array_wr32(E1000_IVAR0, index, ivar); + } + if (tx_queue > IGB_N0_QUEUE) { + index = (tx_queue >> 1); + ivar = array_rd32(E1000_IVAR0, index); + if (tx_queue & 0x1) { + /* vector goes into high byte of register */ + ivar = ivar & 0x00FFFFFF; + ivar |= (msix_vector | E1000_IVAR_VALID) << 24; + } else { + /* vector goes into second byte of register */ + ivar = ivar & 0xFFFF00FF; + ivar |= (msix_vector | E1000_IVAR_VALID) << 8; + } + array_wr32(E1000_IVAR0, index, ivar); + } + 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; + + for (v_idx |