diff -r 2c22f3bea8ba -r a89e2bedf004 devices/e1000/e1000_main-2.6.27-orig.c --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/devices/e1000/e1000_main-2.6.27-orig.c Thu Apr 29 14:05:15 2010 +0200 @@ -0,0 +1,5257 @@ +/******************************************************************************* + + Intel PRO/1000 Linux driver + Copyright(c) 1999 - 2006 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: + Linux NICS + e1000-devel Mailing List + Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + +*******************************************************************************/ + +#include "e1000.h" +#include + +char e1000_driver_name[] = "e1000"; +static char e1000_driver_string[] = "Intel(R) PRO/1000 Network Driver"; +#define DRV_VERSION "7.3.21-k3-NAPI" +const char e1000_driver_version[] = DRV_VERSION; +static const char e1000_copyright[] = "Copyright (c) 1999-2006 Intel Corporation."; + +/* e1000_pci_tbl - PCI Device ID Table + * + * Last entry must be all 0s + * + * Macro expands to... + * {PCI_DEVICE(PCI_VENDOR_ID_INTEL, device_id)} + */ +static struct pci_device_id e1000_pci_tbl[] = { + INTEL_E1000_ETHERNET_DEVICE(0x1000), + INTEL_E1000_ETHERNET_DEVICE(0x1001), + INTEL_E1000_ETHERNET_DEVICE(0x1004), + INTEL_E1000_ETHERNET_DEVICE(0x1008), + INTEL_E1000_ETHERNET_DEVICE(0x1009), + INTEL_E1000_ETHERNET_DEVICE(0x100C), + INTEL_E1000_ETHERNET_DEVICE(0x100D), + INTEL_E1000_ETHERNET_DEVICE(0x100E), + INTEL_E1000_ETHERNET_DEVICE(0x100F), + INTEL_E1000_ETHERNET_DEVICE(0x1010), + INTEL_E1000_ETHERNET_DEVICE(0x1011), + INTEL_E1000_ETHERNET_DEVICE(0x1012), + INTEL_E1000_ETHERNET_DEVICE(0x1013), + INTEL_E1000_ETHERNET_DEVICE(0x1014), + INTEL_E1000_ETHERNET_DEVICE(0x1015), + INTEL_E1000_ETHERNET_DEVICE(0x1016), + INTEL_E1000_ETHERNET_DEVICE(0x1017), + INTEL_E1000_ETHERNET_DEVICE(0x1018), + INTEL_E1000_ETHERNET_DEVICE(0x1019), + INTEL_E1000_ETHERNET_DEVICE(0x101A), + INTEL_E1000_ETHERNET_DEVICE(0x101D), + INTEL_E1000_ETHERNET_DEVICE(0x101E), + INTEL_E1000_ETHERNET_DEVICE(0x1026), + INTEL_E1000_ETHERNET_DEVICE(0x1027), + INTEL_E1000_ETHERNET_DEVICE(0x1028), + INTEL_E1000_ETHERNET_DEVICE(0x1075), + INTEL_E1000_ETHERNET_DEVICE(0x1076), + INTEL_E1000_ETHERNET_DEVICE(0x1077), + INTEL_E1000_ETHERNET_DEVICE(0x1078), + INTEL_E1000_ETHERNET_DEVICE(0x1079), + INTEL_E1000_ETHERNET_DEVICE(0x107A), + INTEL_E1000_ETHERNET_DEVICE(0x107B), + INTEL_E1000_ETHERNET_DEVICE(0x107C), + INTEL_E1000_ETHERNET_DEVICE(0x108A), + INTEL_E1000_ETHERNET_DEVICE(0x1099), + INTEL_E1000_ETHERNET_DEVICE(0x10B5), + /* required last entry */ + {0,} +}; + +MODULE_DEVICE_TABLE(pci, e1000_pci_tbl); + +int e1000_up(struct e1000_adapter *adapter); +void e1000_down(struct e1000_adapter *adapter); +void e1000_reinit_locked(struct e1000_adapter *adapter); +void e1000_reset(struct e1000_adapter *adapter); +int e1000_set_spd_dplx(struct e1000_adapter *adapter, u16 spddplx); +int e1000_setup_all_tx_resources(struct e1000_adapter *adapter); +int e1000_setup_all_rx_resources(struct e1000_adapter *adapter); +void e1000_free_all_tx_resources(struct e1000_adapter *adapter); +void e1000_free_all_rx_resources(struct e1000_adapter *adapter); +static int e1000_setup_tx_resources(struct e1000_adapter *adapter, + struct e1000_tx_ring *txdr); +static int e1000_setup_rx_resources(struct e1000_adapter *adapter, + struct e1000_rx_ring *rxdr); +static void e1000_free_tx_resources(struct e1000_adapter *adapter, + struct e1000_tx_ring *tx_ring); +static void e1000_free_rx_resources(struct e1000_adapter *adapter, + struct e1000_rx_ring *rx_ring); +void e1000_update_stats(struct e1000_adapter *adapter); + +static int e1000_init_module(void); +static void e1000_exit_module(void); +static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent); +static void __devexit e1000_remove(struct pci_dev *pdev); +static int e1000_alloc_queues(struct e1000_adapter *adapter); +static int e1000_sw_init(struct e1000_adapter *adapter); +static int e1000_open(struct net_device *netdev); +static int e1000_close(struct net_device *netdev); +static void e1000_configure_tx(struct e1000_adapter *adapter); +static void e1000_configure_rx(struct e1000_adapter *adapter); +static void e1000_setup_rctl(struct e1000_adapter *adapter); +static void e1000_clean_all_tx_rings(struct e1000_adapter *adapter); +static void e1000_clean_all_rx_rings(struct e1000_adapter *adapter); +static void e1000_clean_tx_ring(struct e1000_adapter *adapter, + struct e1000_tx_ring *tx_ring); +static void e1000_clean_rx_ring(struct e1000_adapter *adapter, + struct e1000_rx_ring *rx_ring); +static void e1000_set_rx_mode(struct net_device *netdev); +static void e1000_update_phy_info(unsigned long data); +static void e1000_watchdog(unsigned long data); +static void e1000_82547_tx_fifo_stall(unsigned long data); +static int e1000_xmit_frame(struct sk_buff *skb, struct net_device *netdev); +static struct net_device_stats * e1000_get_stats(struct net_device *netdev); +static int e1000_change_mtu(struct net_device *netdev, int new_mtu); +static int e1000_set_mac(struct net_device *netdev, void *p); +static irqreturn_t e1000_intr(int irq, void *data); +static irqreturn_t e1000_intr_msi(int irq, void *data); +static bool e1000_clean_tx_irq(struct e1000_adapter *adapter, + struct e1000_tx_ring *tx_ring); +static int e1000_clean(struct napi_struct *napi, int budget); +static bool e1000_clean_rx_irq(struct e1000_adapter *adapter, + struct e1000_rx_ring *rx_ring, + int *work_done, int work_to_do); +static bool e1000_clean_rx_irq_ps(struct e1000_adapter *adapter, + struct e1000_rx_ring *rx_ring, + int *work_done, int work_to_do); +static void e1000_alloc_rx_buffers(struct e1000_adapter *adapter, + struct e1000_rx_ring *rx_ring, + int cleaned_count); +static void e1000_alloc_rx_buffers_ps(struct e1000_adapter *adapter, + struct e1000_rx_ring *rx_ring, + int cleaned_count); +static int e1000_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd); +static int e1000_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, + int cmd); +static void e1000_enter_82542_rst(struct e1000_adapter *adapter); +static void e1000_leave_82542_rst(struct e1000_adapter *adapter); +static void e1000_tx_timeout(struct net_device *dev); +static void e1000_reset_task(struct work_struct *work); +static void e1000_smartspeed(struct e1000_adapter *adapter); +static int e1000_82547_fifo_workaround(struct e1000_adapter *adapter, + struct sk_buff *skb); + +static void e1000_vlan_rx_register(struct net_device *netdev, struct vlan_group *grp); +static void e1000_vlan_rx_add_vid(struct net_device *netdev, u16 vid); +static void e1000_vlan_rx_kill_vid(struct net_device *netdev, u16 vid); +static void e1000_restore_vlan(struct e1000_adapter *adapter); + +static int e1000_suspend(struct pci_dev *pdev, pm_message_t state); +#ifdef CONFIG_PM +static int e1000_resume(struct pci_dev *pdev); +#endif +static void e1000_shutdown(struct pci_dev *pdev); + +#ifdef CONFIG_NET_POLL_CONTROLLER +/* for netdump / net console */ +static void e1000_netpoll (struct net_device *netdev); +#endif + +#define COPYBREAK_DEFAULT 256 +static unsigned int copybreak __read_mostly = COPYBREAK_DEFAULT; +module_param(copybreak, uint, 0644); +MODULE_PARM_DESC(copybreak, + "Maximum size of packet that is copied to a new buffer on receive"); + +static pci_ers_result_t e1000_io_error_detected(struct pci_dev *pdev, + pci_channel_state_t state); +static pci_ers_result_t e1000_io_slot_reset(struct pci_dev *pdev); +static void e1000_io_resume(struct pci_dev *pdev); + +static struct pci_error_handlers e1000_err_handler = { + .error_detected = e1000_io_error_detected, + .slot_reset = e1000_io_slot_reset, + .resume = e1000_io_resume, +}; + +static struct pci_driver e1000_driver = { + .name = e1000_driver_name, + .id_table = e1000_pci_tbl, + .probe = e1000_probe, + .remove = __devexit_p(e1000_remove), +#ifdef CONFIG_PM + /* Power Managment Hooks */ + .suspend = e1000_suspend, + .resume = e1000_resume, +#endif + .shutdown = e1000_shutdown, + .err_handler = &e1000_err_handler +}; + +MODULE_AUTHOR("Intel Corporation, "); +MODULE_DESCRIPTION("Intel(R) PRO/1000 Network Driver"); +MODULE_LICENSE("GPL"); +MODULE_VERSION(DRV_VERSION); + +static int debug = NETIF_MSG_DRV | NETIF_MSG_PROBE; +module_param(debug, int, 0); +MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); + +/** + * e1000_init_module - Driver Registration Routine + * + * e1000_init_module is the first routine called when the driver is + * loaded. All it does is register with the PCI subsystem. + **/ + +static int __init e1000_init_module(void) +{ + int ret; + printk(KERN_INFO "%s - version %s\n", + e1000_driver_string, e1000_driver_version); + + printk(KERN_INFO "%s\n", e1000_copyright); + + ret = pci_register_driver(&e1000_driver); + if (copybreak != COPYBREAK_DEFAULT) { + if (copybreak == 0) + printk(KERN_INFO "e1000: copybreak disabled\n"); + else + printk(KERN_INFO "e1000: copybreak enabled for " + "packets <= %u bytes\n", copybreak); + } + return ret; +} + +module_init(e1000_init_module); + +/** + * e1000_exit_module - Driver Exit Cleanup Routine + * + * e1000_exit_module is called just before the driver is removed + * from memory. + **/ + +static void __exit e1000_exit_module(void) +{ + pci_unregister_driver(&e1000_driver); +} + +module_exit(e1000_exit_module); + +static int e1000_request_irq(struct e1000_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; + irq_handler_t handler = e1000_intr; + int irq_flags = IRQF_SHARED; + int err; + + if (hw->mac_type >= e1000_82571) { + adapter->have_msi = !pci_enable_msi(adapter->pdev); + if (adapter->have_msi) { + handler = e1000_intr_msi; + irq_flags = 0; + } + } + + err = request_irq(adapter->pdev->irq, handler, irq_flags, netdev->name, + netdev); + if (err) { + if (adapter->have_msi) + pci_disable_msi(adapter->pdev); + DPRINTK(PROBE, ERR, + "Unable to allocate interrupt Error: %d\n", err); + } + + return err; +} + +static void e1000_free_irq(struct e1000_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + + free_irq(adapter->pdev->irq, netdev); + + if (adapter->have_msi) + pci_disable_msi(adapter->pdev); +} + +/** + * e1000_irq_disable - Mask off interrupt generation on the NIC + * @adapter: board private structure + **/ + +static void e1000_irq_disable(struct e1000_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + + ew32(IMC, ~0); + E1000_WRITE_FLUSH(); + synchronize_irq(adapter->pdev->irq); +} + +/** + * e1000_irq_enable - Enable default interrupt generation settings + * @adapter: board private structure + **/ + +static void e1000_irq_enable(struct e1000_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + + ew32(IMS, IMS_ENABLE_MASK); + E1000_WRITE_FLUSH(); +} + +static void e1000_update_mng_vlan(struct e1000_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; + u16 vid = hw->mng_cookie.vlan_id; + u16 old_vid = adapter->mng_vlan_id; + if (adapter->vlgrp) { + if (!vlan_group_get_device(adapter->vlgrp, vid)) { + if (hw->mng_cookie.status & + E1000_MNG_DHCP_COOKIE_STATUS_VLAN_SUPPORT) { + e1000_vlan_rx_add_vid(netdev, vid); + adapter->mng_vlan_id = vid; + } else + adapter->mng_vlan_id = E1000_MNG_VLAN_NONE; + + if ((old_vid != (u16)E1000_MNG_VLAN_NONE) && + (vid != old_vid) && + !vlan_group_get_device(adapter->vlgrp, old_vid)) + e1000_vlan_rx_kill_vid(netdev, old_vid); + } else + adapter->mng_vlan_id = vid; + } +} + +/** + * e1000_release_hw_control - release control of the h/w to f/w + * @adapter: address of board private structure + * + * e1000_release_hw_control resets {CTRL_EXT|FWSM}:DRV_LOAD bit. + * For ASF and Pass Through versions of f/w this means that the + * driver is no longer loaded. For AMT version (only with 82573) i + * of the f/w this means that the network i/f is closed. + * + **/ + +static void e1000_release_hw_control(struct e1000_adapter *adapter) +{ + u32 ctrl_ext; + u32 swsm; + struct e1000_hw *hw = &adapter->hw; + + /* Let firmware taken over control of h/w */ + switch (hw->mac_type) { + case e1000_82573: + swsm = er32(SWSM); + ew32(SWSM, swsm & ~E1000_SWSM_DRV_LOAD); + break; + case e1000_82571: + case e1000_82572: + case e1000_80003es2lan: + case e1000_ich8lan: + ctrl_ext = er32(CTRL_EXT); + ew32(CTRL_EXT, ctrl_ext & ~E1000_CTRL_EXT_DRV_LOAD); + break; + default: + break; + } +} + +/** + * e1000_get_hw_control - get control of the h/w from f/w + * @adapter: address of board private structure + * + * e1000_get_hw_control sets {CTRL_EXT|FWSM}:DRV_LOAD bit. + * For ASF and Pass Through versions of f/w this means that + * the driver is loaded. For AMT version (only with 82573) + * of the f/w this means that the network i/f is open. + * + **/ + +static void e1000_get_hw_control(struct e1000_adapter *adapter) +{ + u32 ctrl_ext; + u32 swsm; + struct e1000_hw *hw = &adapter->hw; + + /* Let firmware know the driver has taken over */ + switch (hw->mac_type) { + case e1000_82573: + swsm = er32(SWSM); + ew32(SWSM, swsm | E1000_SWSM_DRV_LOAD); + break; + case e1000_82571: + case e1000_82572: + case e1000_80003es2lan: + case e1000_ich8lan: + ctrl_ext = er32(CTRL_EXT); + ew32(CTRL_EXT, ctrl_ext | E1000_CTRL_EXT_DRV_LOAD); + break; + default: + break; + } +} + +static void e1000_init_manageability(struct e1000_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + + if (adapter->en_mng_pt) { + u32 manc = er32(MANC); + + /* disable hardware interception of ARP */ + manc &= ~(E1000_MANC_ARP_EN); + + /* enable receiving management packets to the host */ + /* this will probably generate destination unreachable messages + * from the host OS, but the packets will be handled on SMBUS */ + if (hw->has_manc2h) { + u32 manc2h = er32(MANC2H); + + manc |= E1000_MANC_EN_MNG2HOST; +#define E1000_MNG2HOST_PORT_623 (1 << 5) +#define E1000_MNG2HOST_PORT_664 (1 << 6) + manc2h |= E1000_MNG2HOST_PORT_623; + manc2h |= E1000_MNG2HOST_PORT_664; + ew32(MANC2H, manc2h); + } + + ew32(MANC, manc); + } +} + +static void e1000_release_manageability(struct e1000_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + + if (adapter->en_mng_pt) { + u32 manc = er32(MANC); + + /* re-enable hardware interception of ARP */ + manc |= E1000_MANC_ARP_EN; + + if (hw->has_manc2h) + manc &= ~E1000_MANC_EN_MNG2HOST; + + /* don't explicitly have to mess with MANC2H since + * MANC has an enable disable that gates MANC2H */ + + ew32(MANC, manc); + } +} + +/** + * e1000_configure - configure the hardware for RX and TX + * @adapter = private board structure + **/ +static void e1000_configure(struct e1000_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + int i; + + e1000_set_rx_mode(netdev); + + e1000_restore_vlan(adapter); + e1000_init_manageability(adapter); + + e1000_configure_tx(adapter); + e1000_setup_rctl(adapter); + e1000_configure_rx(adapter); + /* call E1000_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 e1000_rx_ring *ring = &adapter->rx_ring[i]; + adapter->alloc_rx_buf(adapter, ring, + E1000_DESC_UNUSED(ring)); + } + + adapter->tx_queue_len = netdev->tx_queue_len; +} + +int e1000_up(struct e1000_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + + /* hardware has been reset, we need to reload some things */ + e1000_configure(adapter); + + clear_bit(__E1000_DOWN, &adapter->flags); + + napi_enable(&adapter->napi); + + e1000_irq_enable(adapter); + + /* fire a link change interrupt to start the watchdog */ + ew32(ICS, E1000_ICS_LSC); + return 0; +} + +/** + * e1000_power_up_phy - restore link in case the phy was powered down + * @adapter: address of board private structure + * + * The phy may be powered down to save power and turn off link when the + * driver is unloaded and wake on lan is not enabled (among others) + * *** this routine MUST be followed by a call to e1000_reset *** + * + **/ + +void e1000_power_up_phy(struct e1000_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u16 mii_reg = 0; + + /* Just clear the power down bit to wake the phy back up */ + if (hw->media_type == e1000_media_type_copper) { + /* according to the manual, the phy will retain its + * settings across a power-down/up cycle */ + e1000_read_phy_reg(hw, PHY_CTRL, &mii_reg); + mii_reg &= ~MII_CR_POWER_DOWN; + e1000_write_phy_reg(hw, PHY_CTRL, mii_reg); + } +} + +static void e1000_power_down_phy(struct e1000_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + + /* Power down the PHY so no link is implied when interface is down * + * The PHY cannot be powered down if any of the following is true * + * (a) WoL is enabled + * (b) AMT is active + * (c) SoL/IDER session is active */ + if (!adapter->wol && hw->mac_type >= e1000_82540 && + hw->media_type == e1000_media_type_copper) { + u16 mii_reg = 0; + + switch (hw->mac_type) { + case e1000_82540: + case e1000_82545: + case e1000_82545_rev_3: + case e1000_82546: + case e1000_82546_rev_3: + case e1000_82541: + case e1000_82541_rev_2: + case e1000_82547: + case e1000_82547_rev_2: + if (er32(MANC) & E1000_MANC_SMBUS_EN) + goto out; + break; + case e1000_82571: + case e1000_82572: + case e1000_82573: + case e1000_80003es2lan: + case e1000_ich8lan: + if (e1000_check_mng_mode(hw) || + e1000_check_phy_reset_block(hw)) + goto out; + break; + default: + goto out; + } + e1000_read_phy_reg(hw, PHY_CTRL, &mii_reg); + mii_reg |= MII_CR_POWER_DOWN; + e1000_write_phy_reg(hw, PHY_CTRL, mii_reg); + mdelay(1); + } +out: + return; +} + +void e1000_down(struct e1000_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + + /* signal that we're down so the interrupt handler does not + * reschedule our watchdog timer */ + set_bit(__E1000_DOWN, &adapter->flags); + + napi_disable(&adapter->napi); + + e1000_irq_disable(adapter); + + del_timer_sync(&adapter->tx_fifo_stall_timer); + del_timer_sync(&adapter->watchdog_timer); + del_timer_sync(&adapter->phy_info_timer); + + netdev->tx_queue_len = adapter->tx_queue_len; + adapter->link_speed = 0; + adapter->link_duplex = 0; + netif_carrier_off(netdev); + netif_stop_queue(netdev); + + e1000_reset(adapter); + e1000_clean_all_tx_rings(adapter); + e1000_clean_all_rx_rings(adapter); +} + +void e1000_reinit_locked(struct e1000_adapter *adapter) +{ + WARN_ON(in_interrupt()); + while (test_and_set_bit(__E1000_RESETTING, &adapter->flags)) + msleep(1); + e1000_down(adapter); + e1000_up(adapter); + clear_bit(__E1000_RESETTING, &adapter->flags); +} + +void e1000_reset(struct e1000_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 pba = 0, tx_space, min_tx_space, min_rx_space; + u16 fc_high_water_mark = E1000_FC_HIGH_DIFF; + bool legacy_pba_adjust = false; + + /* Repartition Pba for greater than 9k mtu + * To take effect CTRL.RST is required. + */ + + switch (hw->mac_type) { + case e1000_82542_rev2_0: + case e1000_82542_rev2_1: + case e1000_82543: + case e1000_82544: + case e1000_82540: + case e1000_82541: + case e1000_82541_rev_2: + legacy_pba_adjust = true; + pba = E1000_PBA_48K; + break; + case e1000_82545: + case e1000_82545_rev_3: + case e1000_82546: + case e1000_82546_rev_3: + pba = E1000_PBA_48K; + break; + case e1000_82547: + case e1000_82547_rev_2: + legacy_pba_adjust = true; + pba = E1000_PBA_30K; + break; + case e1000_82571: + case e1000_82572: + case e1000_80003es2lan: + pba = E1000_PBA_38K; + break; + case e1000_82573: + pba = E1000_PBA_20K; + break; + case e1000_ich8lan: + pba = E1000_PBA_8K; + case e1000_undefined: + case e1000_num_macs: + break; + } + + if (legacy_pba_adjust) { + if (adapter->netdev->mtu > E1000_RXBUFFER_8192) + pba -= 8; /* allocate more FIFO for Tx */ + + if (hw->mac_type == e1000_82547) { + adapter->tx_fifo_head = 0; + adapter->tx_head_addr = pba << E1000_TX_HEAD_ADDR_SHIFT; + adapter->tx_fifo_size = + (E1000_PBA_40K - pba) << E1000_PBA_BYTES_SHIFT; + atomic_set(&adapter->tx_fifo_stall, 0); + } + } else if (hw->max_frame_size > MAXIMUM_ETHERNET_FRAME_SIZE) { + /* adjust PBA for jumbo frames */ + ew32(PBA, pba); + + /* To maintain wire speed transmits, the Tx FIFO should be + * large enough to accomodate two full transmit packets, + * rounded up to the next 1KB and expressed in KB. Likewise, + * the Rx FIFO should be large enough to accomodate at least + * one full receive packet and is similarly rounded up and + * expressed in KB. */ + pba = er32(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; + /* don't include ethernet FCS because hardware appends/strips */ + min_rx_space = adapter->netdev->mtu + ENET_HEADER_SIZE + + VLAN_TAG_SIZE; + min_tx_space = min_rx_space; + min_tx_space *= 2; + min_tx_space = ALIGN(min_tx_space, 1024); + min_tx_space >>= 10; + 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); + + /* PCI/PCIx hardware has PBA alignment constraints */ + switch (hw->mac_type) { + case e1000_82545 ... e1000_82546_rev_3: + pba &= ~(E1000_PBA_8K - 1); + break; + default: + break; + } + + /* if short on rx space, rx wins and must trump tx + * adjustment or use Early Receive if available */ + if (pba < min_rx_space) { + switch (hw->mac_type) { + case e1000_82573: + /* ERT enabled in e1000_configure_rx */ + break; + default: + pba = min_rx_space; + break; + } + } + } + } + + ew32(PBA, pba); + + /* flow control settings */ + /* Set the FC high water mark to 90% of the FIFO size. + * Required to clear last 3 LSB */ + fc_high_water_mark = ((pba * 9216)/10) & 0xFFF8; + /* We can't use 90% on small FIFOs because the remainder + * would be less than 1 full frame. In this case, we size + * it to allow at least a full frame above the high water + * mark. */ + if (pba < E1000_PBA_16K) + fc_high_water_mark = (pba * 1024) - 1600; + + hw->fc_high_water = fc_high_water_mark; + hw->fc_low_water = fc_high_water_mark - 8; + if (hw->mac_type == e1000_80003es2lan) + hw->fc_pause_time = 0xFFFF; + else + hw->fc_pause_time = E1000_FC_PAUSE_TIME; + hw->fc_send_xon = 1; + hw->fc = hw->original_fc; + + /* Allow time for pending master requests to run */ + e1000_reset_hw(hw); + if (hw->mac_type >= e1000_82544) + ew32(WUC, 0); + + if (e1000_init_hw(hw)) + DPRINTK(PROBE, ERR, "Hardware Error\n"); + e1000_update_mng_vlan(adapter); + + /* if (adapter->hwflags & HWFLAGS_PHY_PWR_BIT) { */ + if (hw->mac_type >= e1000_82544 && + hw->mac_type <= e1000_82547_rev_2 && + hw->autoneg == 1 && + hw->autoneg_advertised == ADVERTISE_1000_FULL) { + u32 ctrl = er32(CTRL); + /* clear phy power management bit if we are in gig only mode, + * which if enabled will attempt negotiation to 100Mb, which + * can cause a loss of link at power off or driver unload */ + ctrl &= ~E1000_CTRL_SWDPIN3; + ew32(CTRL, ctrl); + } + + /* Enable h/w to recognize an 802.1Q VLAN Ethernet packet */ + ew32(VET, ETHERNET_IEEE_VLAN_TYPE); + + e1000_reset_adaptive(hw); + e1000_phy_get_info(hw, &adapter->phy_info); + + if (!adapter->smart_power_down && + (hw->mac_type == e1000_82571 || + hw->mac_type == e1000_82572)) { + u16 phy_data = 0; + /* speed up time to link by disabling smart power down, ignore + * the return value of this function because there is nothing + * different we would do if it failed */ + e1000_read_phy_reg(hw, IGP02E1000_PHY_POWER_MGMT, + &phy_data); + phy_data &= ~IGP02E1000_PM_SPD; + e1000_write_phy_reg(hw, IGP02E1000_PHY_POWER_MGMT, + phy_data); + } + + e1000_release_manageability(adapter); +} + +/** + * Dump the eeprom for users having checksum issues + **/ +static void e1000_dump_eeprom(struct e1000_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct ethtool_eeprom eeprom; + const struct ethtool_ops *ops = netdev->ethtool_ops; + u8 *data; + int i; + u16 csum_old, csum_new = 0; + + eeprom.len = ops->get_eeprom_len(netdev); + eeprom.offset = 0; + + data = kmalloc(eeprom.len, GFP_KERNEL); + if (!data) { + printk(KERN_ERR "Unable to allocate memory to dump EEPROM" + " data\n"); + return; + } + + ops->get_eeprom(netdev, &eeprom, data); + + csum_old = (data[EEPROM_CHECKSUM_REG * 2]) + + (data[EEPROM_CHECKSUM_REG * 2 + 1] << 8); + for (i = 0; i < EEPROM_CHECKSUM_REG * 2; i += 2) + csum_new += data[i] + (data[i + 1] << 8); + csum_new = EEPROM_SUM - csum_new; + + printk(KERN_ERR "/*********************/\n"); + printk(KERN_ERR "Current EEPROM Checksum : 0x%04x\n", csum_old); + printk(KERN_ERR "Calculated : 0x%04x\n", csum_new); + + printk(KERN_ERR "Offset Values\n"); + printk(KERN_ERR "======== ======\n"); + print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 16, 1, data, 128, 0); + + printk(KERN_ERR "Include this output when contacting your support " + "provider.\n"); + printk(KERN_ERR "This is not a software error! Something bad " + "happened to your hardware or\n"); + printk(KERN_ERR "EEPROM image. Ignoring this " + "problem could result in further problems,\n"); + printk(KERN_ERR "possibly loss of data, corruption or system hangs!\n"); + printk(KERN_ERR "The MAC Address will be reset to 00:00:00:00:00:00, " + "which is invalid\n"); + printk(KERN_ERR "and requires you to set the proper MAC " + "address manually before continuing\n"); + printk(KERN_ERR "to enable this network device.\n"); + printk(KERN_ERR "Please inspect the EEPROM dump and report the issue " + "to your hardware vendor\n"); + printk(KERN_ERR "or Intel Customer Support.\n"); + printk(KERN_ERR "/*********************/\n"); + + kfree(data); +} + +/** + * e1000_is_need_ioport - determine if an adapter needs ioport resources or not + * @pdev: PCI device information struct + * + * Return true if an adapter needs ioport resources + **/ +static int e1000_is_need_ioport(struct pci_dev *pdev) +{ + switch (pdev->device) { + case E1000_DEV_ID_82540EM: + case E1000_DEV_ID_82540EM_LOM: + case E1000_DEV_ID_82540EP: + case E1000_DEV_ID_82540EP_LOM: + case E1000_DEV_ID_82540EP_LP: + case E1000_DEV_ID_82541EI: + case E1000_DEV_ID_82541EI_MOBILE: + case E1000_DEV_ID_82541ER: + case E1000_DEV_ID_82541ER_LOM: + case E1000_DEV_ID_82541GI: + case E1000_DEV_ID_82541GI_LF: + case E1000_DEV_ID_82541GI_MOBILE: + case E1000_DEV_ID_82544EI_COPPER: + case E1000_DEV_ID_82544EI_FIBER: + case E1000_DEV_ID_82544GC_COPPER: + case E1000_DEV_ID_82544GC_LOM: + case E1000_DEV_ID_82545EM_COPPER: + case E1000_DEV_ID_82545EM_FIBER: + case E1000_DEV_ID_82546EB_COPPER: + case E1000_DEV_ID_82546EB_FIBER: + case E1000_DEV_ID_82546EB_QUAD_COPPER: + return true; + default: + return false; + } +} + +/** + * e1000_probe - Device Initialization Routine + * @pdev: PCI device information struct + * @ent: entry in e1000_pci_tbl + * + * Returns 0 on success, negative on failure + * + * e1000_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 e1000_probe(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + struct net_device *netdev; + struct e1000_adapter *adapter; + struct e1000_hw *hw; + + static int cards_found = 0; + static int global_quad_port_a = 0; /* global ksp3 port a indication */ + int i, err, pci_using_dac; + u16 eeprom_data = 0; + u16 eeprom_apme_mask = E1000_EEPROM_APME; + int bars, need_ioport; + DECLARE_MAC_BUF(mac); + + /* do not allocate ioport bars when not needed */ + need_ioport = e1000_is_need_ioport(pdev); + if (need_ioport) { + bars = pci_select_bars(pdev, IORESOURCE_MEM | IORESOURCE_IO); + err = pci_enable_device(pdev); + } else { + bars = pci_select_bars(pdev, IORESOURCE_MEM); + err = pci_enable_device_mem(pdev); + } + if (err) + return err; + + if (!pci_set_dma_mask(pdev, DMA_64BIT_MASK) && + !pci_set_consistent_dma_mask(pdev, DMA_64BIT_MASK)) { + pci_using_dac = 1; + } else { + err = pci_set_dma_mask(pdev, DMA_32BIT_MASK); + if (err) { + err = pci_set_consistent_dma_mask(pdev, DMA_32BIT_MASK); + if (err) { + E1000_ERR("No usable DMA configuration, " + "aborting\n"); + goto err_dma; + } + } + pci_using_dac = 0; + } + + err = pci_request_selected_regions(pdev, bars, e1000_driver_name); + if (err) + goto err_pci_reg; + + pci_set_master(pdev); + + err = -ENOMEM; + netdev = alloc_etherdev(sizeof(struct e1000_adapter)); + 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; + adapter->msg_enable = (1 << debug) - 1; + adapter->bars = bars; + adapter->need_ioport = need_ioport; + + hw = &adapter->hw; + hw->back = adapter; + + err = -EIO; + hw->hw_addr = ioremap(pci_resource_start(pdev, BAR_0), + pci_resource_len(pdev, BAR_0)); + if (!hw->hw_addr) + goto err_ioremap; + + if (adapter->need_ioport) { + for (i = BAR_1; i <= BAR_5; i++) { + if (pci_resource_len(pdev, i) == 0) + continue; + if (pci_resource_flags(pdev, i) & IORESOURCE_IO) { + hw->io_base = pci_resource_start(pdev, i); + break; + } + } + } + + netdev->open = &e1000_open; + netdev->stop = &e1000_close; + netdev->hard_start_xmit = &e1000_xmit_frame; + netdev->get_stats = &e1000_get_stats; + netdev->set_rx_mode = &e1000_set_rx_mode; + netdev->set_mac_address = &e1000_set_mac; + netdev->change_mtu = &e1000_change_mtu; + netdev->do_ioctl = &e1000_ioctl; + e1000_set_ethtool_ops(netdev); + netdev->tx_timeout = &e1000_tx_timeout; + netdev->watchdog_timeo = 5 * HZ; + netif_napi_add(netdev, &adapter->napi, e1000_clean, 64); + netdev->vlan_rx_register = e1000_vlan_rx_register; + netdev->vlan_rx_add_vid = e1000_vlan_rx_add_vid; + netdev->vlan_rx_kill_vid = e1000_vlan_rx_kill_vid; +#ifdef CONFIG_NET_POLL_CONTROLLER + netdev->poll_controller = e1000_netpoll; +#endif + strncpy(netdev->name, pci_name(pdev), sizeof(netdev->name) - 1); + + adapter->bd_number = cards_found; + + /* setup the private structure */ + + err = e1000_sw_init(adapter); + if (err) + goto err_sw_init; + + err = -EIO; + /* Flash BAR mapping must happen after e1000_sw_init + * because it depends on mac_type */ + if ((hw->mac_type == e1000_ich8lan) && + (pci_resource_flags(pdev, 1) & IORESOURCE_MEM)) { + hw->flash_address = + ioremap(pci_resource_start(pdev, 1), + pci_resource_len(pdev, 1)); + if (!hw->flash_address) + goto err_flashmap; + } + + if (e1000_check_phy_reset_block(hw)) + DPRINTK(PROBE, INFO, "PHY reset is blocked due to SOL/IDER session.\n"); + + if (hw->mac_type >= e1000_82543) { + netdev->features = NETIF_F_SG | + NETIF_F_HW_CSUM | + NETIF_F_HW_VLAN_TX | + NETIF_F_HW_VLAN_RX | + NETIF_F_HW_VLAN_FILTER; + if (hw->mac_type == e1000_ich8lan) + netdev->features &= ~NETIF_F_HW_VLAN_FILTER; + } + + if ((hw->mac_type >= e1000_82544) && + (hw->mac_type != e1000_82547)) + netdev->features |= NETIF_F_TSO; + + if (hw->mac_type > e1000_82547_rev_2) + netdev->features |= NETIF_F_TSO6; + if (pci_using_dac) + netdev->features |= NETIF_F_HIGHDMA; + + netdev->features |= NETIF_F_LLTX; + + adapter->en_mng_pt = e1000_enable_mng_pass_thru(hw); + + /* initialize eeprom parameters */ + if (e1000_init_eeprom_params(hw)) { + E1000_ERR("EEPROM initialization failed\n"); + goto err_eeprom; + } + + /* before reading the EEPROM, reset the controller to + * put the device in a known good starting state */ + + e1000_reset_hw(hw); + + /* make sure the EEPROM is good */ + if (e1000_validate_eeprom_checksum(hw) < 0) { + DPRINTK(PROBE, ERR, "The EEPROM Checksum Is Not Valid\n"); + e1000_dump_eeprom(adapter); + /* + * set MAC address to all zeroes to invalidate and temporary + * disable this device for the user. This blocks regular + * traffic while still permitting ethtool ioctls from reaching + * the hardware as well as allowing the user to run the + * interface after manually setting a hw addr using + * `ip set address` + */ + memset(hw->mac_addr, 0, netdev->addr_len); + } else { + /* copy the MAC address out of the EEPROM */ + if (e1000_read_mac_addr(hw)) + DPRINTK(PROBE, ERR, "EEPROM Read Error\n"); + } + /* don't block initalization here due to bad MAC address */ + 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)) + DPRINTK(PROBE, ERR, "Invalid MAC Address\n"); + + e1000_get_bus_info(hw); + + init_timer(&adapter->tx_fifo_stall_timer); + adapter->tx_fifo_stall_timer.function = &e1000_82547_tx_fifo_stall; + adapter->tx_fifo_stall_timer.data = (unsigned long)adapter; + + init_timer(&adapter->watchdog_timer); + adapter->watchdog_timer.function = &e1000_watchdog; + adapter->watchdog_timer.data = (unsigned long) adapter; + + init_timer(&adapter->phy_info_timer); + adapter->phy_info_timer.function = &e1000_update_phy_info; + adapter->phy_info_timer.data = (unsigned long)adapter; + + INIT_WORK(&adapter->reset_task, e1000_reset_task); + + e1000_check_options(adapter); + + /* Initial Wake on LAN setting + * If APM wake is enabled in the EEPROM, + * enable the ACPI Magic Packet filter + */ + + switch (hw->mac_type) { + case e1000_82542_rev2_0: + case e1000_82542_rev2_1: + case e1000_82543: + break; + case e1000_82544: + e1000_read_eeprom(hw, + EEPROM_INIT_CONTROL2_REG, 1, &eeprom_data); + eeprom_apme_mask = E1000_EEPROM_82544_APM; + break; + case e1000_ich8lan: + e1000_read_eeprom(hw, + EEPROM_INIT_CONTROL1_REG, 1, &eeprom_data); + eeprom_apme_mask = E1000_EEPROM_ICH8_APME; + break; + case e1000_82546: + case e1000_82546_rev_3: + case e1000_82571: + case e1000_80003es2lan: + if (er32(STATUS) & E1000_STATUS_FUNC_1){ + e1000_read_eeprom(hw, + EEPROM_INIT_CONTROL3_PORT_B, 1, &eeprom_data); + break; + } + /* Fall Through */ + default: + e1000_read_eeprom(hw, + EEPROM_INIT_CONTROL3_PORT_A, 1, &eeprom_data); + break; + } + 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_82546GB_PCIE: + adapter->eeprom_wol = 0; + break; + case E1000_DEV_ID_82546EB_FIBER: + case E1000_DEV_ID_82546GB_FIBER: + case E1000_DEV_ID_82571EB_FIBER: + /* Wake events only supported on port A for dual fiber + * regardless of eeprom setting */ + if (er32(STATUS) & E1000_STATUS_FUNC_1) + adapter->eeprom_wol = 0; + break; + case E1000_DEV_ID_82546GB_QUAD_COPPER_KSP3: + case E1000_DEV_ID_82571EB_QUAD_COPPER: + case E1000_DEV_ID_82571EB_QUAD_FIBER: + case E1000_DEV_ID_82571EB_QUAD_COPPER_LOWPROFILE: + case E1000_DEV_ID_82571PT_QUAD_COPPER: + /* if quad port adapter, disable WoL on all but port A */ + if (global_quad_port_a != 0) + adapter->eeprom_wol = 0; + else + adapter->quad_port_a = 1; + /* 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); + + /* print bus type/speed/width info */ + DPRINTK(PROBE, INFO, "(PCI%s:%s:%s) ", + ((hw->bus_type == e1000_bus_type_pcix) ? "-X" : + (hw->bus_type == e1000_bus_type_pci_express ? " Express":"")), + ((hw->bus_speed == e1000_bus_speed_2500) ? "2.5Gb/s" : + (hw->bus_speed == e1000_bus_speed_133) ? "133MHz" : + (hw->bus_speed == e1000_bus_speed_120) ? "120MHz" : + (hw->bus_speed == e1000_bus_speed_100) ? "100MHz" : + (hw->bus_speed == e1000_bus_speed_66) ? "66MHz" : "33MHz"), + ((hw->bus_width == e1000_bus_width_64) ? "64-bit" : + (hw->bus_width == e1000_bus_width_pciex_4) ? "Width x4" : + (hw->bus_width == e1000_bus_width_pciex_1) ? "Width x1" : + "32-bit")); + + printk("%s\n", print_mac(mac, netdev->dev_addr)); + + if (hw->bus_type == e1000_bus_type_pci_express) { + DPRINTK(PROBE, WARNING, "This device (id %04x:%04x) will no " + "longer be supported by this driver in the future.\n", + pdev->vendor, pdev->device); + DPRINTK(PROBE, WARNING, "please use the \"e1000e\" " + "driver instead.\n"); + } + + /* reset the hardware with the new settings */ + e1000_reset(adapter); + + /* If the controller is 82573 and f/w is AMT, do not set + * DRV_LOAD until the interface is up. For all other cases, + * let the f/w know that the h/w is now under the control + * of the driver. */ + if (hw->mac_type != e1000_82573 || + !e1000_check_mng_mode(hw)) + e1000_get_hw_control(adapter); + + /* tell the stack to leave us alone until e1000_open() is called */ + netif_carrier_off(netdev); + netif_stop_queue(netdev); + + strcpy(netdev->name, "eth%d"); + err = register_netdev(netdev); + if (err) + goto err_register; + + DPRINTK(PROBE, INFO, "Intel(R) PRO/1000 Network Connection\n"); + + cards_found++; + return 0; + +err_register: + e1000_release_hw_control(adapter); +err_eeprom: + if (!e1000_check_phy_reset_block(hw)) + e1000_phy_hw_reset(hw); + + if (hw->flash_address) + iounmap(hw->flash_address); +err_flashmap: + for (i = 0; i < adapter->num_rx_queues; i++) + dev_put(&adapter->polling_netdev[i]); + + kfree(adapter->tx_ring); + kfree(adapter->rx_ring); + kfree(adapter->polling_netdev); +err_sw_init: + iounmap(hw->hw_addr); +err_ioremap: + free_netdev(netdev); +err_alloc_etherdev: + pci_release_selected_regions(pdev, bars); +err_pci_reg: +err_dma: + pci_disable_device(pdev); + return err; +} + +/** + * e1000_remove - Device Removal Routine + * @pdev: PCI device information struct + * + * e1000_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 e1000_remove(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct e1000_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + int i; + + cancel_work_sync(&adapter->reset_task); + + e1000_release_manageability(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. */ + e1000_release_hw_control(adapter); + + for (i = 0; i < adapter->num_rx_queues; i++) + dev_put(&adapter->polling_netdev[i]); + + unregister_netdev(netdev); + + if (!e1000_check_phy_reset_block(hw)) + e1000_phy_hw_reset(hw); + + kfree(adapter->tx_ring); + kfree(adapter->rx_ring); + kfree(adapter->polling_netdev); + + iounmap(hw->hw_addr); + if (hw->flash_address) + iounmap(hw->flash_address); + pci_release_selected_regions(pdev, adapter->bars); + + free_netdev(netdev); + + pci_disable_device(pdev); +} + +/** + * e1000_sw_init - Initialize general software structures (struct e1000_adapter) + * @adapter: board private structure to initialize + * + * e1000_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 e1000_sw_init(struct e1000_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; + struct pci_dev *pdev = adapter->pdev; + int i; + + /* PCI config space info */ + + hw->vendor_id = pdev->vendor; + hw->device_id = pdev->device; + hw->subsystem_vendor_id = pdev->subsystem_vendor; + hw->subsystem_id = pdev->subsystem_device; + hw->revision_id = pdev->revision; + + pci_read_config_word(pdev, PCI_COMMAND, &hw->pci_cmd_word); + + adapter->rx_buffer_len = MAXIMUM_ETHERNET_VLAN_SIZE; + adapter->rx_ps_bsize0 = E1000_RXBUFFER_128; + hw->max_frame_size = netdev->mtu + + ENET_HEADER_SIZE + ETHERNET_FCS_SIZE; + hw->min_frame_size = MINIMUM_ETHERNET_FRAME_SIZE; + + /* identify the MAC */ + + if (e1000_set_mac_type(hw)) { + DPRINTK(PROBE, ERR, "Unknown MAC Type\n"); + return -EIO; + } + + switch (hw->mac_type) { + default: + break; + case e1000_82541: + case e1000_82547: + case e1000_82541_rev_2: + case e1000_82547_rev_2: + hw->phy_init_script = 1; + break; + } + + e1000_set_media_type(hw); + + hw->wait_autoneg_complete = false; + hw->tbi_compatibility_en = true; + hw->adaptive_ifs = true; + + /* Copper options */ + + if (hw->media_type == e1000_media_type_copper) { + hw->mdix = AUTO_ALL_MODES; + hw->disable_polarity_correction = false; + hw->master_slave = E1000_MASTER_SLAVE; + } + + adapter->num_tx_queues = 1; + adapter->num_rx_queues = 1; + + if (e1000_alloc_queues(adapter)) { + DPRINTK(PROBE, ERR, "Unable to allocate memory for queues\n"); + return -ENOMEM; + } + + for (i = 0; i < adapter->num_rx_queues; i++) { + adapter->polling_netdev[i].priv = adapter; + dev_hold(&adapter->polling_netdev[i]); + set_bit(__LINK_STATE_START, &adapter->polling_netdev[i].state); + } + spin_lock_init(&adapter->tx_queue_lock); + + /* Explicitly disable IRQ since the NIC can be in any state. */ + e1000_irq_disable(adapter); + + spin_lock_init(&adapter->stats_lock); + + set_bit(__E1000_DOWN, &adapter->flags); + + return 0; +} + +/** + * e1000_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. The polling_netdev array is + * intended for Multiqueue, but should work fine with a single queue. + **/ + +static int __devinit e1000_alloc_queues(struct e1000_adapter *adapter) +{ + adapter->tx_ring = kcalloc(adapter->num_tx_queues, + sizeof(struct e1000_tx_ring), GFP_KERNEL); + if (!adapter->tx_ring) + return -ENOMEM; + + adapter->rx_ring = kcalloc(adapter->num_rx_queues, + sizeof(struct e1000_rx_ring), GFP_KERNEL); + if (!adapter->rx_ring) { + kfree(adapter->tx_ring); + return -ENOMEM; + } + + adapter->polling_netdev = kcalloc(adapter->num_rx_queues, + sizeof(struct net_device), + GFP_KERNEL); + if (!adapter->polling_netdev) { + kfree(adapter->tx_ring); + kfree(adapter->rx_ring); + return -ENOMEM; + } + + return E1000_SUCCESS; +} + +/** + * e1000_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 e1000_open(struct net_device *netdev) +{ + struct e1000_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + int err; + + /* disallow open during test */ + if (test_bit(__E1000_TESTING, &adapter->flags)) + return -EBUSY; + + /* allocate transmit descriptors */ + err = e1000_setup_all_tx_resources(adapter); + if (err) + goto err_setup_tx; + + /* allocate receive descriptors */ + err = e1000_setup_all_rx_resources(adapter); + if (err) + goto err_setup_rx; + + e1000_power_up_phy(adapter); + + adapter->mng_vlan_id = E1000_MNG_VLAN_NONE; + if ((hw->mng_cookie.status & + E1000_MNG_DHCP_COOKIE_STATUS_VLAN_SUPPORT)) { + e1000_update_mng_vlan(adapter); + } + + /* If AMT is enabled, let the firmware know that the network + * interface is now open */ + if (hw->mac_type == e1000_82573 && + e1000_check_mng_mode(hw)) + e1000_get_hw_control(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. */ + e1000_configure(adapter); + + err = e1000_request_irq(adapter); + if (err) + goto err_req_irq; + + /* From here on the code is the same as e1000_up() */ + clear_bit(__E1000_DOWN, &adapter->flags); + + napi_enable(&adapter->napi); + + e1000_irq_enable(adapter); + + netif_start_queue(netdev); + + /* fire a link status change interrupt to start the watchdog */ + ew32(ICS, E1000_ICS_LSC); + + return E1000_SUCCESS; + +err_req_irq: + e1000_release_hw_control(adapter); + e1000_power_down_phy(adapter); + e1000_free_all_rx_resources(adapter); +err_setup_rx: + e1000_free_all_tx_resources(adapter); +err_setup_tx: + e1000_reset(adapter); + + return err; +} + +/** + * e1000_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 drivers 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 e1000_close(struct net_device *netdev) +{ + struct e1000_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + + WARN_ON(test_bit(__E1000_RESETTING, &adapter->flags)); + e1000_down(adapter); + e1000_power_down_phy(adapter); + e1000_free_irq(adapter); + + e1000_free_all_tx_resources(adapter); + e1000_free_all_rx_resources(adapter); + + /* kill manageability vlan ID if supported, but not if a vlan with + * the same ID is registered on the host OS (let 8021q kill it) */ + if ((hw->mng_cookie.status & + E1000_MNG_DHCP_COOKIE_STATUS_VLAN_SUPPORT) && + !(adapter->vlgrp && + vlan_group_get_device(adapter->vlgrp, adapter->mng_vlan_id))) { + e1000_vlan_rx_kill_vid(netdev, adapter->mng_vlan_id); + } + + /* If AMT is enabled, let the firmware know that the network + * interface is now closed */ + if (hw->mac_type == e1000_82573 && + e1000_check_mng_mode(hw)) + e1000_release_hw_control(adapter); + + return 0; +} + +/** + * e1000_check_64k_bound - check that memory doesn't cross 64kB boundary + * @adapter: address of board private structure + * @start: address of beginning of memory + * @len: length of memory + **/ +static bool e1000_check_64k_bound(struct e1000_adapter *adapter, void *start, + unsigned long len) +{ + struct e1000_hw *hw = &adapter->hw; + unsigned long begin = (unsigned long)start; + unsigned long end = begin + len; + + /* First rev 82545 and 82546 need to not allow any memory + * write location to cross 64k boundary due to errata 23 */ + if (hw->mac_type == e1000_82545 || + hw->mac_type == e1000_82546) { + return ((begin ^ (end - 1)) >> 16) != 0 ? false : true; + } + + return true; +} + +/** + * e1000_setup_tx_resources - allocate Tx resources (Descriptors) + * @adapter: board private structure + * @txdr: tx descriptor ring (for a specific queue) to setup + * + * Return 0 on success, negative on failure + **/ + +static int e1000_setup_tx_resources(struct e1000_adapter *adapter, + struct e1000_tx_ring *txdr) +{ + struct pci_dev *pdev = adapter->pdev; + int size; + + size = sizeof(struct e1000_buffer) * txdr->count; + txdr->buffer_info = vmalloc(size); + if (!txdr->buffer_info) { + DPRINTK(PROBE, ERR, + "Unable to allocate memory for the transmit descriptor ring\n"); + return -ENOMEM; + } + memset(txdr->buffer_info, 0, size); + + /* round up to nearest 4K */ + + txdr->size = txdr->count * sizeof(struct e1000_tx_desc); + txdr->size = ALIGN(txdr->size, 4096); + + txdr->desc = pci_alloc_consistent(pdev, txdr->size, &txdr->dma); + if (!txdr->desc) { +setup_tx_desc_die: + vfree(txdr->buffer_info); + DPRINTK(PROBE, ERR, + "Unable to allocate memory for the transmit descriptor ring\n"); + return -ENOMEM; + } + + /* Fix for errata 23, can't cross 64kB boundary */ + if (!e1000_check_64k_bound(adapter, txdr->desc, txdr->size)) { + void *olddesc = txdr->desc; + dma_addr_t olddma = txdr->dma; + DPRINTK(TX_ERR, ERR, "txdr align check failed: %u bytes " + "at %p\n", txdr->size, txdr->desc); + /* Try again, without freeing the previous */ + txdr->desc = pci_alloc_consistent(pdev, txdr->size, &txdr->dma); + /* Failed allocation, critical failure */ + if (!txdr->desc) { + pci_free_consistent(pdev, txdr->size, olddesc, olddma); + goto setup_tx_desc_die; + } + + if (!e1000_check_64k_bound(adapter, txdr->desc, txdr->size)) { + /* give up */ + pci_free_consistent(pdev, txdr->size, txdr->desc, + txdr->dma); + pci_free_consistent(pdev, txdr->size, olddesc, olddma); + DPRINTK(PROBE, ERR, + "Unable to allocate aligned memory " + "for the transmit descriptor ring\n"); + vfree(txdr->buffer_info); + return -ENOMEM; + } else { + /* Free old allocation, new allocation was successful */ + pci_free_consistent(pdev, txdr->size, olddesc, olddma); + } + } + memset(txdr->desc, 0, txdr->size); + + txdr->next_to_use = 0; + txdr->next_to_clean = 0; + spin_lock_init(&txdr->tx_lock); + + return 0; +} + +/** + * e1000_setup_all_tx_resources - wrapper to allocate Tx resources + * (Descriptors) for all queues + * @adapter: board private structure + * + * Return 0 on success, negative on failure + **/ + +int e1000_setup_all_tx_resources(struct e1000_adapter *adapter) +{ + int i, err = 0; + + for (i = 0; i < adapter->num_tx_queues; i++) { + err = e1000_setup_tx_resources(adapter, &adapter->tx_ring[i]); + if (err) { + DPRINTK(PROBE, ERR, + "Allocation for Tx Queue %u failed\n", i); + for (i-- ; i >= 0; i--) + e1000_free_tx_resources(adapter, + &adapter->tx_ring[i]); + break; + } + } + + return err; +} + +/** + * e1000_configure_tx - Configure 8254x Transmit Unit after Reset + * @adapter: board private structure + * + * Configure the Tx unit of the MAC after a reset. + **/ + +static void e1000_configure_tx(struct e1000_adapter *adapter) +{ + u64 tdba; + struct e1000_hw *hw = &adapter->hw; + u32 tdlen, tctl, tipg, tarc; + u32 ipgr1, ipgr2; + + /* Setup the HW Tx Head and Tail descriptor pointers */ + + switch (adapter->num_tx_queues) { + case 1: + default: + tdba = adapter->tx_ring[0].dma; + tdlen = adapter->tx_ring[0].count * + sizeof(struct e1000_tx_desc); + ew32(TDLEN, tdlen); + ew32(TDBAH, (tdba >> 32)); + ew32(TDBAL, (tdba & 0x00000000ffffffffULL)); + ew32(TDT, 0); + ew32(TDH, 0); + adapter->tx_ring[0].tdh = ((hw->mac_type >= e1000_82543) ? E1000_TDH : E1000_82542_TDH); + adapter->tx_ring[0].tdt = ((hw->mac_type >= e1000_82543) ? E1000_TDT : E1000_82542_TDT); + break; + } + + /* Set the default values for the Tx Inter Packet Gap timer */ + if (hw->mac_type <= e1000_82547_rev_2 && + (hw->media_type == e1000_media_type_fiber || + hw->media_type == e1000_media_type_internal_serdes)) + tipg = DEFAULT_82543_TIPG_IPGT_FIBER; + else + tipg = DEFAULT_82543_TIPG_IPGT_COPPER; + + switch (hw->mac_type) { + case e1000_82542_rev2_0: + case e1000_82542_rev2_1: + tipg = DEFAULT_82542_TIPG_IPGT; + ipgr1 = DEFAULT_82542_TIPG_IPGR1; + ipgr2 = DEFAULT_82542_TIPG_IPGR2; + break; + case e1000_80003es2lan: + ipgr1 = DEFAULT_82543_TIPG_IPGR1; + ipgr2 = DEFAULT_80003ES2LAN_TIPG_IPGR2; + break; + default: + ipgr1 = DEFAULT_82543_TIPG_IPGR1; + ipgr2 = DEFAULT_82543_TIPG_IPGR2; + break; + } + tipg |= ipgr1 << E1000_TIPG_IPGR1_SHIFT; + tipg |= ipgr2 << E1000_TIPG_IPGR2_SHIFT; + ew32(TIPG, tipg); + + /* Set the Tx Interrupt Delay register */ + + ew32(TIDV, adapter->tx_int_delay); + if (hw->mac_type >= e1000_82540) + ew32(TADV, adapter->tx_abs_int_delay); + + /* Program the Transmit Control Register */ + + tctl = er32(TCTL); + tctl &= ~E1000_TCTL_CT; + tctl |= E1000_TCTL_PSP | E1000_TCTL_RTLC | + (E1000_COLLISION_THRESHOLD << E1000_CT_SHIFT); + + if (hw->mac_type == e1000_82571 || hw->mac_type == e1000_82572) { + tarc = er32(TARC0); + /* set the speed mode bit, we'll clear it if we're not at + * gigabit link later */ + tarc |= (1 << 21); + ew32(TARC0, tarc); + } else if (hw->mac_type == e1000_80003es2lan) { + tarc = er32(TARC0); + tarc |= 1; + ew32(TARC0, tarc); + tarc = er32(TARC1); + tarc |= 1; + ew32(TARC1, tarc); + } + + e1000_config_collision_dist(hw); + + /* Setup Transmit Descriptor Settings for eop descriptor */ + adapter->txd_cmd = E1000_TXD_CMD_EOP | E1000_TXD_CMD_IFCS; + + /* only set IDE if we are delaying interrupts using the timers */ + if (adapter->tx_int_delay) + adapter->txd_cmd |= E1000_TXD_CMD_IDE; + + if (hw->mac_type < e1000_82543) + adapter->txd_cmd |= E1000_TXD_CMD_RPS; + else + adapter->txd_cmd |= E1000_TXD_CMD_RS; + + /* Cache if we're 82544 running in PCI-X because we'll + * need this to apply a workaround later in the send path. */ + if (hw->mac_type == e1000_82544 && + hw->bus_type == e1000_bus_type_pcix) + adapter->pcix_82544 = 1; + + ew32(TCTL, tctl); + +} + +/** + * e1000_setup_rx_resources - allocate Rx resources (Descriptors) + * @adapter: board private structure + * @rxdr: rx descriptor ring (for a specific queue) to setup + * + * Returns 0 on success, negative on failure + **/ + +static int e1000_setup_rx_resources(struct e1000_adapter *adapter, + struct e1000_rx_ring *rxdr) +{ + struct e1000_hw *hw = &adapter->hw; + struct pci_dev *pdev = adapter->pdev; + int size, desc_len; + + size = sizeof(struct e1000_buffer) * rxdr->count; + rxdr->buffer_info = vmalloc(size); + if (!rxdr->buffer_info) { + DPRINTK(PROBE, ERR, + "Unable to allocate memory for the receive descriptor ring\n"); + return -ENOMEM; + } + memset(rxdr->buffer_info, 0, size); + + rxdr->ps_page = kcalloc(rxdr->count, sizeof(struct e1000_ps_page), + GFP_KERNEL); + if (!rxdr->ps_page) { + vfree(rxdr->buffer_info); + DPRINTK(PROBE, ERR, + "Unable to allocate memory for the receive descriptor ring\n"); + return -ENOMEM; + } + + rxdr->ps_page_dma = kcalloc(rxdr->count, + sizeof(struct e1000_ps_page_dma), + GFP_KERNEL); + if (!rxdr->ps_page_dma) { + vfree(rxdr->buffer_info); + kfree(rxdr->ps_page); + DPRINTK(PROBE, ERR, + "Unable to allocate memory for the receive descriptor ring\n"); + return -ENOMEM; + } + + if (hw->mac_type <= e1000_82547_rev_2) + desc_len = sizeof(struct e1000_rx_desc); + else + desc_len = sizeof(union e1000_rx_desc_packet_split); + + /* Round up to nearest 4K */ + + rxdr->size = rxdr->count * desc_len; + rxdr->size = ALIGN(rxdr->size, 4096); + + rxdr->desc = pci_alloc_consistent(pdev, rxdr->size, &rxdr->dma); + + if (!rxdr->desc) { + DPRINTK(PROBE, ERR, + "Unable to allocate memory for the receive descriptor ring\n"); +setup_rx_desc_die: + vfree(rxdr->buffer_info); + kfree(rxdr->ps_page); + kfree(rxdr->ps_page_dma); + return -ENOMEM; + } + + /* Fix for errata 23, can't cross 64kB boundary */ + if (!e1000_check_64k_bound(adapter, rxdr->desc, rxdr->size)) { + void *olddesc = rxdr->desc; + dma_addr_t olddma = rxdr->dma; + DPRINTK(RX_ERR, ERR, "rxdr align check failed: %u bytes " + "at %p\n", rxdr->size, rxdr->desc); + /* Try again, without freeing the previous */ + rxdr->desc = pci_alloc_consistent(pdev, rxdr->size, &rxdr->dma); + /* Failed allocation, critical failure */ + if (!rxdr->desc) { + pci_free_consistent(pdev, rxdr->size, olddesc, olddma); + DPRINTK(PROBE, ERR, + "Unable to allocate memory " + "for the receive descriptor ring\n"); + goto setup_rx_desc_die; + } + + if (!e1000_check_64k_bound(adapter, rxdr->desc, rxdr->size)) { + /* give up */ + pci_free_consistent(pdev, rxdr->size, rxdr->desc, + rxdr->dma); + pci_free_consistent(pdev, rxdr->size, olddesc, olddma); + DPRINTK(PROBE, ERR, + "Unable to allocate aligned memory " + "for the receive descriptor ring\n"); + goto setup_rx_desc_die; + } else { + /* Free old allocation, new allocation was successful */ + pci_free_consistent(pdev, rxdr->size, olddesc, olddma); + } + } + memset(rxdr->desc, 0, rxdr->size); + + rxdr->next_to_clean = 0; + rxdr->next_to_use = 0; + + return 0; +} + +/** + * e1000_setup_all_rx_resources - wrapper to allocate Rx resources + * (Descriptors) for all queues + * @adapter: board private structure + * + * Return 0 on success, negative on failure + **/ + +int e1000_setup_all_rx_resources(struct e1000_adapter *adapter) +{ + int i, err = 0; + + for (i = 0; i < adapter->num_rx_queues; i++) { + err = e1000_setup_rx_resources(adapter, &adapter->rx_ring[i]); + if (err) { + DPRINTK(PROBE, ERR, + "Allocation for Rx Queue %u failed\n", i); + for (i-- ; i >= 0; i--) + e1000_free_rx_resources(adapter, + &adapter->rx_ring[i]); + break; + } + } + + return err; +} + +/** + * e1000_setup_rctl - configure the receive control registers + * @adapter: Board private structure + **/ +#define PAGE_USE_COUNT(S) (((S) >> PAGE_SHIFT) + \ + (((S) & (PAGE_SIZE - 1)) ? 1 : 0)) +static void e1000_setup_rctl(struct e1000_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 rctl, rfctl; + u32 psrctl = 0; +#ifndef CONFIG_E1000_DISABLE_PACKET_SPLIT + u32 pages = 0; +#endif + + rctl = er32(RCTL); + + rctl &= ~(3 << E1000_RCTL_MO_SHIFT); + + rctl |= E1000_RCTL_EN | E1000_RCTL_BAM | + E1000_RCTL_LBM_NO | E1000_RCTL_RDMTS_HALF | + (hw->mc_filter_type << E1000_RCTL_MO_SHIFT); + + if (hw->tbi_compatibility_on == 1) + rctl |= E1000_RCTL_SBP; + else + rctl &= ~E1000_RCTL_SBP; + + if (adapter->netdev->mtu <= ETH_DATA_LEN) + rctl &= ~E1000_RCTL_LPE; + else + rctl |= E1000_RCTL_LPE; + + /* Setup buffer sizes */ + rctl &= ~E1000_RCTL_SZ_4096; + rctl |= E1000_RCTL_BSEX; + switch (adapter->rx_buffer_len) { + case E1000_RXBUFFER_256: + rctl |= E1000_RCTL_SZ_256; + rctl &= ~E1000_RCTL_BSEX; + break; + case E1000_RXBUFFER_512: + rctl |= E1000_RCTL_SZ_512; + rctl &= ~E1000_RCTL_BSEX; + break; + case E1000_RXBUFFER_1024: + rctl |= E1000_RCTL_SZ_1024; + rctl &= ~E1000_RCTL_BSEX; + break; + case E1000_RXBUFFER_2048: + default: + rctl |= E1000_RCTL_SZ_2048; + rctl &= ~E1000_RCTL_BSEX; + break; + case E1000_RXBUFFER_4096: + rctl |= E1000_RCTL_SZ_4096; + break; + case E1000_RXBUFFER_8192: + rctl |= E1000_RCTL_SZ_8192; + break; + case E1000_RXBUFFER_16384: + rctl |= E1000_RCTL_SZ_16384; + break; + } + +#ifndef CONFIG_E1000_DISABLE_PACKET_SPLIT + /* 82571 and greater support packet-split where the protocol + * header is placed in skb->data and the packet data is + * placed in pages hanging off of skb_shinfo(skb)->nr_frags. + * In the case of a non-split, skb->data is linearly filled, + * followed by the page buffers. Therefore, skb->data is + * sized to hold the largest protocol header. + */ + /* allocations using alloc_page take too long for regular MTU + * so only enable packet split for jumbo frames */ + pages = PAGE_USE_COUNT(adapter->netdev->mtu); + if ((hw->mac_type >= e1000_82571) && (pages <= 3) && + PAGE_SIZE <= 16384 && (rctl & E1000_RCTL_LPE)) + adapter->rx_ps_pages = pages; + else + adapter->rx_ps_pages = 0; +#endif + if (adapter->rx_ps_pages) { + /* Configure extra packet-split registers */ + rfctl = er32(RFCTL); + rfctl |= E1000_RFCTL_EXTEN; + /* disable packet split support for IPv6 extension headers, + * because some malformed IPv6 headers can hang the RX */ + rfctl |= (E1000_RFCTL_IPV6_EX_DIS | + E1000_RFCTL_NEW_IPV6_EXT_DIS); + + ew32(RFCTL, rfctl); + + rctl |= E1000_RCTL_DTYP_PS; + + psrctl |= adapter->rx_ps_bsize0 >> + E1000_PSRCTL_BSIZE0_SHIFT; + + switch (adapter->rx_ps_pages) { + case 3: + psrctl |= PAGE_SIZE << + E1000_PSRCTL_BSIZE3_SHIFT; + case 2: + psrctl |= PAGE_SIZE << + E1000_PSRCTL_BSIZE2_SHIFT; + case 1: + psrctl |= PAGE_SIZE >> + E1000_PSRCTL_BSIZE1_SHIFT; + break; + } + + ew32(PSRCTL, psrctl); + } + + ew32(RCTL, rctl); +} + +/** + * e1000_configure_rx - Configure 8254x Receive Unit after Reset + * @adapter: board private structure + * + * Configure the Rx unit of the MAC after a reset. + **/ + +static void e1000_configure_rx(struct e1000_adapter *adapter) +{ + u64 rdba; + struct e1000_hw *hw = &adapter->hw; + u32 rdlen, rctl, rxcsum, ctrl_ext; + + if (adapter->rx_ps_pages) { + /* this is a 32 byte descriptor */ + rdlen = adapter->rx_ring[0].count * + sizeof(union e1000_rx_desc_packet_split); + adapter->clean_rx = e1000_clean_rx_irq_ps; + adapter->alloc_rx_buf = e1000_alloc_rx_buffers_ps; + } else { + rdlen = adapter->rx_ring[0].count * + sizeof(struct e1000_rx_desc); + adapter->clean_rx = e1000_clean_rx_irq; + adapter->alloc_rx_buf = e1000_alloc_rx_buffers; + } + + /* disable receives while setting up the descriptors */ + rctl = er32(RCTL); + ew32(RCTL, rctl & ~E1000_RCTL_EN); + + /* set the Receive Delay Timer Register */ + ew32(RDTR, adapter->rx_int_delay); + + if (hw->mac_type >= e1000_82540) { + ew32(RADV, adapter->rx_abs_int_delay); + if (adapter->itr_setting != 0) + ew32(ITR, 1000000000 / (adapter->itr * 256)); + } + + if (hw->mac_type >= e1000_82571) { + ctrl_ext = er32(CTRL_EXT); + /* Reset delay timers after every interrupt */ + ctrl_ext |= E1000_CTRL_EXT_INT_TIMER_CLR; + /* Auto-Mask interrupts upon ICR access */ + ctrl_ext |= E1000_CTRL_EXT_IAME; + ew32(IAM, 0xffffffff); + ew32(CTRL_EXT, ctrl_ext); + E1000_WRITE_FLUSH(); + } + + /* Setup the HW Rx Head and Tail Descriptor Pointers and + * the Base and Length of the Rx Descriptor Ring */ + switch (adapter->num_rx_queues) { + case 1: + default: + rdba = adapter->rx_ring[0].dma; + ew32(RDLEN, rdlen); + ew32(RDBAH, (rdba >> 32)); + ew32(RDBAL, (rdba & 0x00000000ffffffffULL)); + ew32(RDT, 0); + ew32(RDH, 0); + adapter->rx_ring[0].rdh = ((hw->mac_type >= e1000_82543) ? E1000_RDH : E1000_82542_RDH); + adapter->rx_ring[0].rdt = ((hw->mac_type >= e1000_82543) ? E1000_RDT : E1000_82542_RDT); + break; + } + + /* Enable 82543 Receive Checksum Offload for TCP and UDP */ + if (hw->mac_type >= e1000_82543) { + rxcsum = er32(RXCSUM); + if (adapter->rx_csum) { + rxcsum |= E1000_RXCSUM_TUOFL; + + /* Enable 82571 IPv4 payload checksum for UDP fragments + * Must be used in conjunction with packet-split. */ + if ((hw->mac_type >= e1000_82571) && + (adapter->rx_ps_pages)) { + rxcsum |= E1000_RXCSUM_IPPCSE; + } + } else { + rxcsum &= ~E1000_RXCSUM_TUOFL; + /* don't need to clear IPPCSE as it defaults to 0 */ + } + ew32(RXCSUM, rxcsum); + } + + /* enable early receives on 82573, only takes effect if using > 2048 + * byte total frame size. for example only for jumbo frames */ +#define E1000_ERT_2048 0x100 + if (hw->mac_type == e1000_82573) + ew32(ERT, E1000_ERT_2048); + + /* Enable Receives */ + ew32(RCTL, rctl); +} + +/** + * e1000_free_tx_resources - Free Tx Resources per Queue + * @adapter: board private structure + * @tx_ring: Tx descriptor ring for a specific queue + * + * Free all transmit software resources + **/ + +static void e1000_free_tx_resources(struct e1000_adapter *adapter, + struct e1000_tx_ring *tx_ring) +{ + struct pci_dev *pdev = adapter->pdev; + + e1000_clean_tx_ring(adapter, tx_ring); + + vfree(tx_ring->buffer_info); + tx_ring->buffer_info = NULL; + + pci_free_consistent(pdev, tx_ring->size, tx_ring->desc, tx_ring->dma); + + tx_ring->desc = NULL; +} + +/** + * e1000_free_all_tx_resources - Free Tx Resources for All Queues + * @adapter: board private structure + * + * Free all transmit software resources + **/ + +void e1000_free_all_tx_resources(struct e1000_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) + e1000_free_tx_resources(adapter, &adapter->tx_ring[i]); +} + +static void e1000_unmap_and_free_tx_resource(struct e1000_adapter *adapter, + struct e1000_buffer *buffer_info) +{ + if (buffer_info->dma) { + pci_unmap_page(adapter->pdev, + buffer_info->dma, + buffer_info->length, + PCI_DMA_TODEVICE); + buffer_info->dma = 0; + } + if (buffer_info->skb) { + dev_kfree_skb_any(buffer_info->skb); + buffer_info->skb = NULL; + } + /* buffer_info must be completely set up in the transmit path */ +} + +/** + * e1000_clean_tx_ring - Free Tx Buffers + * @adapter: board private structure + * @tx_ring: ring to be cleaned + **/ + +static void e1000_clean_tx_ring(struct e1000_adapter *adapter, + struct e1000_tx_ring *tx_ring) +{ + struct e1000_hw *hw = &adapter->hw; + struct e1000_buffer *buffer_info; + unsigned long size; + unsigned int i; + + /* Free all the Tx ring sk_buffs */ + + for (i = 0; i < tx_ring->count; i++) { + buffer_info = &tx_ring->buffer_info[i]; + e1000_unmap_and_free_tx_resource(adapter, buffer_info); + } + + size = sizeof(struct e1000_buffer) * tx_ring->count; + memset(tx_ring->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; + tx_ring->last_tx_tso = 0; + + writel(0, hw->hw_addr + tx_ring->tdh); + writel(0, hw->hw_addr + tx_ring->tdt); +} + +/** + * e1000_clean_all_tx_rings - Free Tx Buffers for all queues + * @adapter: board private structure + **/ + +static void e1000_clean_all_tx_rings(struct e1000_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) + e1000_clean_tx_ring(adapter, &adapter->tx_ring[i]); +} + +/** + * e1000_free_rx_resources - Free Rx Resources + * @adapter: board private structure + * @rx_ring: ring to clean the resources from + * + * Free all receive software resources + **/ + +static void e1000_free_rx_resources(struct e1000_adapter *adapter, + struct e1000_rx_ring *rx_ring) +{ + struct pci_dev *pdev = adapter->pdev; + + e1000_clean_rx_ring(adapter, rx_ring); + + vfree(rx_ring->buffer_info); + rx_ring->buffer_info = NULL; + kfree(rx_ring->ps_page); + rx_ring->ps_page = NULL; + kfree(rx_ring->ps_page_dma); + rx_ring->ps_page_dma = NULL; + + pci_free_consistent(pdev, rx_ring->size, rx_ring->desc, rx_ring->dma); + + rx_ring->desc = NULL; +} + +/** + * e1000_free_all_rx_resources - Free Rx Resources for All Queues + * @adapter: board private structure + * + * Free all receive software resources + **/ + +void e1000_free_all_rx_resources(struct e1000_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_rx_queues; i++) + e1000_free_rx_resources(adapter, &adapter->rx_ring[i]); +} + +/** + * e1000_clean_rx_ring - Free Rx Buffers per Queue + * @adapter: board private structure + * @rx_ring: ring to free buffers from + **/ + +static void e1000_clean_rx_ring(struct e1000_adapter *adapter, + struct e1000_rx_ring *rx_ring) +{ + struct e1000_hw *hw = &adapter->hw; + struct e1000_buffer *buffer_info; + struct e1000_ps_page *ps_page; + struct e1000_ps_page_dma *ps_page_dma; + struct pci_dev *pdev = adapter->pdev; + unsigned long size; + unsigned int i, j; + + /* Free all the Rx ring sk_buffs */ + for (i = 0; i < rx_ring->count; i++) { + buffer_info = &rx_ring->buffer_info[i]; + if (buffer_info->skb) { + pci_unmap_single(pdev, + buffer_info->dma, + buffer_info->length, + PCI_DMA_FROMDEVICE); + + dev_kfree_skb(buffer_info->skb); + buffer_info->skb = NULL; + } + ps_page = &rx_ring->ps_page[i]; + ps_page_dma = &rx_ring->ps_page_dma[i]; + for (j = 0; j < adapter->rx_ps_pages; j++) { + if (!ps_page->ps_page[j]) break; + pci_unmap_page(pdev, + ps_page_dma->ps_page_dma[j], + PAGE_SIZE, PCI_DMA_FROMDEVICE); + ps_page_dma->ps_page_dma[j] = 0; + put_page(ps_page->ps_page[j]); + ps_page->ps_page[j] = NULL; + } + } + + size = sizeof(struct e1000_buffer) * rx_ring->count; + memset(rx_ring->buffer_info, 0, size); + size = sizeof(struct e1000_ps_page) * rx_ring->count; + memset(rx_ring->ps_page, 0, size); + size = sizeof(struct e1000_ps_page_dma) * rx_ring->count; + memset(rx_ring->ps_page_dma, 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; + + writel(0, hw->hw_addr + rx_ring->rdh); + writel(0, hw->hw_addr + rx_ring->rdt); +} + +/** + * e1000_clean_all_rx_rings - Free Rx Buffers for all queues + * @adapter: board private structure + **/ + +static void e1000_clean_all_rx_rings(struct e1000_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_rx_queues; i++) + e1000_clean_rx_ring(adapter, &adapter->rx_ring[i]); +} + +/* The 82542 2.0 (revision 2) needs to have the receive unit in reset + * and memory write and invalidate disabled for certain operations + */ +static void e1000_enter_82542_rst(struct e1000_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; + u32 rctl; + + e1000_pci_clear_mwi(hw); + + rctl = er32(RCTL); + rctl |= E1000_RCTL_RST; + ew32(RCTL, rctl); + E1000_WRITE_FLUSH(); + mdelay(5); + + if (netif_running(netdev)) + e1000_clean_all_rx_rings(adapter); +} + +static void e1000_leave_82542_rst(struct e1000_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; + u32 rctl; + + rctl = er32(RCTL); + rctl &= ~E1000_RCTL_RST; + ew32(RCTL, rctl); + E1000_WRITE_FLUSH(); + mdelay(5); + + if (hw->pci_cmd_word & PCI_COMMAND_INVALIDATE) + e1000_pci_set_mwi(hw); + + if (netif_running(netdev)) { + /* No need to loop, because 82542 supports only 1 queue */ + struct e1000_rx_ring *ring = &adapter->rx_ring[0]; + e1000_configure_rx(adapter); + adapter->alloc_rx_buf(adapter, ring, E1000_DESC_UNUSED(ring)); + } +} + +/** + * e1000_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 e1000_set_mac(struct net_device *netdev, void *p) +{ + struct e1000_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; + + /* 82542 2.0 needs to be in reset to write receive address registers */ + + if (hw->mac_type == e1000_82542_rev2_0) + e1000_enter_82542_rst(adapter); + + memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); + memcpy(hw->mac_addr, addr->sa_data, netdev->addr_len); + + e1000_rar_set(hw, hw->mac_addr, 0); + + /* With 82571 controllers, LAA may be overwritten (with the default) + * due to controller reset from the other port. */ + if (hw->mac_type == e1000_82571) { + /* activate the work around */ + hw->laa_is_present = 1; + + /* Hold a copy of the LAA in RAR[14] This is done so that + * between the time RAR[0] gets clobbered and the time it + * gets fixed (in e1000_watchdog), the actual LAA is in one + * of the RARs and no incoming packets directed to this port + * are dropped. Eventaully the LAA will be in RAR[0] and + * RAR[14] */ + e1000_rar_set(hw, hw->mac_addr, + E1000_RAR_ENTRIES - 1); + } + + if (hw->mac_type == e1000_82542_rev2_0) + e1000_leave_82542_rst(adapter); + + return 0; +} + +/** + * e1000_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 e1000_set_rx_mode(struct net_device *netdev) +{ + struct e1000_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + struct dev_addr_list *uc_ptr; + struct dev_addr_list *mc_ptr; + u32 rctl; + u32 hash_value; + int i, rar_entries = E1000_RAR_ENTRIES; + int mta_reg_count = (hw->mac_type == e1000_ich8lan) ? + E1000_NUM_MTA_REGISTERS_ICH8LAN : + E1000_NUM_MTA_REGISTERS; + + if (hw->mac_type == e1000_ich8lan) + rar_entries = E1000_RAR_ENTRIES_ICH8LAN; + + /* reserve RAR[14] for LAA over-write work-around */ + if (hw->mac_type == e1000_82571) + rar_entries--; + + /* Check for Promiscuous and All Multicast modes */ + + rctl = er32(RCTL); + + if (netdev->flags & IFF_PROMISC) { + rctl |= (E1000_RCTL_UPE | E1000_RCTL_MPE); + rctl &= ~E1000_RCTL_VFE; + } else { + if (netdev->flags & IFF_ALLMULTI) { + rctl |= E1000_RCTL_MPE; + } else { + rctl &= ~E1000_RCTL_MPE; + } + if (adapter->hw.mac_type != e1000_ich8lan) + rctl |= E1000_RCTL_VFE; + } + + uc_ptr = NULL; + if (netdev->uc_count > rar_entries - 1) { + rctl |= E1000_RCTL_UPE; + } else if (!(netdev->flags & IFF_PROMISC)) { + rctl &= ~E1000_RCTL_UPE; + uc_ptr = netdev->uc_list; + } + + ew32(RCTL, rctl); + + /* 82542 2.0 needs to be in reset to write receive address registers */ + + if (hw->mac_type == e1000_82542_rev2_0) + e1000_enter_82542_rst(adapter); + + /* load the first 14 addresses into the exact filters 1-14. Unicast + * addresses take precedence to avoid disabling unicast filtering + * when possible. + * + * RAR 0 is used for the station MAC adddress + * if there are not 14 addresses, go ahead and clear the filters + * -- with 82571 controllers only 0-13 entries are filled here + */ + mc_ptr = netdev->mc_list; + + for (i = 1; i < rar_entries; i++) { + if (uc_ptr) { + e1000_rar_set(hw, uc_ptr->da_addr, i); + uc_ptr = uc_ptr->next; + } else if (mc_ptr) { + e1000_rar_set(hw, mc_ptr->da_addr, i); + mc_ptr = mc_ptr->next; + } else { + E1000_WRITE_REG_ARRAY(hw, RA, i << 1, 0); + E1000_WRITE_FLUSH(); + E1000_WRITE_REG_ARRAY(hw, RA, (i << 1) + 1, 0); + E1000_WRITE_FLUSH(); + } + } + WARN_ON(uc_ptr != NULL); + + /* clear the old settings from the multicast hash table */ + + for (i = 0; i < mta_reg_count; i++) { + E1000_WRITE_REG_ARRAY(hw, MTA, i, 0); + E1000_WRITE_FLUSH(); + } + + /* load any remaining addresses into the hash table */ + + for (; mc_ptr; mc_ptr = mc_ptr->next) { + hash_value = e1000_hash_mc_addr(hw, mc_ptr->da_addr); + e1000_mta_set(hw, hash_value); + } + + if (hw->mac_type == e1000_82542_rev2_0) + e1000_leave_82542_rst(adapter); +} + +/* Need to wait a few seconds after link up to get diagnostic information from + * the phy */ + +static void e1000_update_phy_info(unsigned long data) +{ + struct e1000_adapter *adapter = (struct e1000_adapter *)data; + struct e1000_hw *hw = &adapter->hw; + e1000_phy_get_info(hw, &adapter->phy_info); +} + +/** + * e1000_82547_tx_fifo_stall - Timer Call-back + * @data: pointer to adapter cast into an unsigned long + **/ + +static void e1000_82547_tx_fifo_stall(unsigned long data) +{ + struct e1000_adapter *adapter = (struct e1000_adapter *)data; + struct e1000_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; + u32 tctl; + + if (atomic_read(&adapter->tx_fifo_stall)) { + if ((er32(TDT) == er32(TDH)) && + (er32(TDFT) == er32(TDFH)) && + (er32(TDFTS) == er32(TDFHS))) { + tctl = er32(TCTL); + ew32(TCTL, tctl & ~E1000_TCTL_EN); + ew32(TDFT, adapter->tx_head_addr); + ew32(TDFH, adapter->tx_head_addr); + ew32(TDFTS, adapter->tx_head_addr); + ew32(TDFHS, adapter->tx_head_addr); + ew32(TCTL, tctl); + E1000_WRITE_FLUSH(); + + adapter->tx_fifo_head = 0; + atomic_set(&adapter->tx_fifo_stall, 0); + netif_wake_queue(netdev); + } else { + mod_timer(&adapter->tx_fifo_stall_timer, jiffies + 1); + } + } +} + +/** + * e1000_watchdog - Timer Call-back + * @data: pointer to adapter cast into an unsigned long + **/ +static void e1000_watchdog(unsigned long data) +{ + struct e1000_adapter *adapter = (struct e1000_adapter *)data; + struct e1000_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; + struct e1000_tx_ring *txdr = adapter->tx_ring; + u32 link, tctl; + s32 ret_val; + + ret_val = e1000_check_for_link(hw); + if ((ret_val == E1000_ERR_PHY) && + (hw->phy_type == e1000_phy_igp_3) && + (er32(CTRL) & E1000_PHY_CTRL_GBE_DISABLE)) { + /* See e1000_kumeran_lock_loss_workaround() */ + DPRINTK(LINK, INFO, + "Gigabit has been disabled, downgrading speed\n"); + } + + if (hw->mac_type == e1000_82573) { + e1000_enable_tx_pkt_filtering(hw); + if (adapter->mng_vlan_id != hw->mng_cookie.vlan_id) + e1000_update_mng_vlan(adapter); + } + + if ((hw->media_type == e1000_media_type_internal_serdes) && + !(er32(TXCW) & E1000_TXCW_ANE)) + link = !hw->serdes_link_down; + else + link = er32(STATUS) & E1000_STATUS_LU; + + if (link) { + if (!netif_carrier_ok(netdev)) { + u32 ctrl; + bool txb2b = true; + e1000_get_speed_and_duplex(hw, + &adapter->link_speed, + &adapter->link_duplex); + + ctrl = er32(CTRL); + DPRINTK(LINK, INFO, "NIC Link is Up %d Mbps %s, " + "Flow Control: %s\n", + 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" ))); + + /* tweak tx_queue_len according to speed/duplex + * and adjust the timeout factor */ + netdev->tx_queue_len = adapter->tx_queue_len; + adapter->tx_timeout_factor = 1; + switch (adapter->link_speed) { + case SPEED_10: + txb2b = false; + netdev->tx_queue_len = 10; + adapter->tx_timeout_factor = 8; + break; + case SPEED_100: + txb2b = false; + netdev->tx_queue_len = 100; + /* maybe add some timeout factor ? */ + break; + } + + if ((hw->mac_type == e1000_82571 || + hw->mac_type == e1000_82572) && + !txb2b) { + u32 tarc0; + tarc0 = er32(TARC0); + tarc0 &= ~(1 << 21); + ew32(TARC0, tarc0); + } + + /* disable TSO for pcie and 10/100 speeds, to avoid + * some hardware issues */ + if (!adapter->tso_force && + hw->bus_type == e1000_bus_type_pci_express){ + switch (adapter->link_speed) { + case SPEED_10: + case SPEED_100: + DPRINTK(PROBE,INFO, + "10/100 speed: disabling TSO\n"); + netdev->features &= ~NETIF_F_TSO; + netdev->features &= ~NETIF_F_TSO6; + break; + case SPEED_1000: + netdev->features |= NETIF_F_TSO; + netdev->features |= NETIF_F_TSO6; + break; + default: + /* oops */ + break; + } + } + + /* enable transmits in the hardware, need to do this + * after setting TARC0 */ + tctl = er32(TCTL); + tctl |= E1000_TCTL_EN; + ew32(TCTL, tctl); + + netif_carrier_on(netdev); + netif_wake_queue(netdev); + mod_timer(&adapter->phy_info_timer, round_jiffies(jiffies + 2 * HZ)); + adapter->smartspeed = 0; + } else { + /* make sure the receive unit is started */ + if (hw->rx_needs_kicking) { + u32 rctl = er32(RCTL); + ew32(RCTL, rctl | E1000_RCTL_EN); + } + } + } else { + if (netif_carrier_ok(netdev)) { + adapter->link_speed = 0; + adapter->link_duplex = 0; + DPRINTK(LINK, INFO, "NIC Link is Down\n"); + netif_carrier_off(netdev); + netif_stop_queue(netdev); + mod_timer(&adapter->phy_info_timer, round_jiffies(jiffies + 2 * HZ)); + + /* 80003ES2LAN workaround-- + * For packet buffer work-around on link down event; + * disable receives in the ISR and + * reset device here in the watchdog + */ + if (hw->mac_type == e1000_80003es2lan) + /* reset device */ + schedule_work(&adapter->reset_task); + } + + e1000_smartspeed(adapter); + } + + e1000_update_stats(adapter); + + hw->tx_packet_delta = adapter->stats.tpt - adapter->tpt_old; + adapter->tpt_old = adapter->stats.tpt; + hw->collision_delta = adapter->stats.colc - adapter->colc_old; + adapter->colc_old = adapter->stats.colc; + + adapter->gorcl = adapter->stats.gorcl - adapter->gorcl_old; + adapter->gorcl_old = adapter->stats.gorcl; + adapter->gotcl = adapter->stats.gotcl - adapter->gotcl_old; + adapter->gotcl_old = adapter->stats.gotcl; + + e1000_update_adaptive(hw); + + if (!netif_carrier_ok(netdev)) { + if (E1000_DESC_UNUSED(txdr) + 1 < txdr->count) { + /* We've lost link, so the controller stops DMA, + * but we've got queued Tx work that's never going + * to get done, so reset controller to flush Tx. + * (Do the reset outside of interrupt context). */ + adapter->tx_timeout_count++; + schedule_work(&adapter->reset_task); + } + } + + /* Cause software interrupt to ensure rx ring is cleaned */ + ew32(ICS, E1000_ICS_RXDMT0); + + /* Force detection of hung controller every watchdog period */ + adapter->detect_tx_hung = true; + + /* With 82571 controllers, LAA may be overwritten due to controller + * reset from the other port. Set the appropriate LAA in RAR[0] */ + if (hw->mac_type == e1000_82571 && hw->laa_is_present) + e1000_rar_set(hw, hw->mac_addr, 0); + + /* Reset the timer */ + 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 +}; + +/** + * e1000_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 e1000_param.c) + * @adapter: pointer to adapter + * @itr_setting: current adapter->itr + * @packets: the number of packets during this measurement interval + * @bytes: the number of bytes during this measurement interval + **/ +static unsigned int e1000_update_itr(struct e1000_adapter *adapter, + u16 itr_setting, int packets, int bytes) +{ + unsigned int retval = itr_setting; + struct e1000_hw *hw = &adapter->hw; + + if (unlikely(hw->mac_type < e1000_82540)) + goto update_itr_done; + + if (packets == 0) + goto update_itr_done; + + switch (itr_setting) { + case lowest_latency: + /* jumbo frames get bulk treatment*/ + if (bytes/packets > 8000) + retval = bulk_latency; + else if ((packets < 5) && (bytes > 512)) + retval = low_latency; + break; + case low_latency: /* 50 usec aka 20000 ints/s */ + if (bytes > 10000) { + /* jumbo frames need bulk latency setting */ + if (bytes/packets > 8000) + retval = bulk_latency; + else if ((packets < 10) || ((bytes/packets) > 1200)) + retval = bulk_latency; + else if ((packets > 35)) + retval = lowest_latency; + } else if (bytes/packets > 2000) + retval = bulk_latency; + else if (packets <= 2 && bytes < 512) + retval = lowest_latency; + break; + case bulk_latency: /* 250 usec aka 4000 ints/s */ + if (bytes > 25000) { + if (packets > 35) + retval = low_latency; + } else if (bytes < 6000) { + retval = low_latency; + } + break; + } + +update_itr_done: + return retval; +} + +static void e1000_set_itr(struct e1000_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u16 current_itr; + u32 new_itr = adapter->itr; + + if (unlikely(hw->mac_type < e1000_82540)) + return; + + /* for non-gigabit speeds, just fix the interrupt rate at 4000 */ + if (unlikely(adapter->link_speed != SPEED_1000)) { + current_itr = 0; + new_itr = 4000; + goto set_itr_now; + } + + adapter->tx_itr = e1000_update_itr(adapter, + adapter->tx_itr, + adapter->total_tx_packets, + adapter->total_tx_bytes); + /* conservative mode (itr 3) eliminates the lowest_latency setting */ + if (adapter->itr_setting == 3 && adapter->tx_itr == lowest_latency) + adapter->tx_itr = low_latency; + + adapter->rx_itr = e1000_update_itr(adapter, + adapter->rx_itr, + adapter->total_rx_packets, + adapter->total_rx_bytes); + /* conservative mode (itr 3) eliminates the lowest_latency setting */ + if (adapter->itr_setting == 3 && adapter->rx_itr == lowest_latency) + adapter->rx_itr = low_latency; + + current_itr = max(adapter->rx_itr, adapter->tx_itr); + + switch (current_itr) { + /* counts and packets in update_itr are dependent on these numbers */ + case lowest_latency: + new_itr = 70000; + break; + case low_latency: + new_itr = 20000; /* aka hwitr = ~200 */ + break; + case bulk_latency: + new_itr = 4000; + break; + default: + break; + } + +set_itr_now: + if (new_itr != adapter->itr) { + /* this attempts to bias the interrupt rate towards Bulk + * by adding intermediate steps when interrupt rate is + * increasing */ + new_itr = new_itr > adapter->itr ? + min(adapter->itr + (new_itr >> 2), new_itr) : + new_itr; + adapter->itr = new_itr; + ew32(ITR, 1000000000 / (new_itr * 256)); + } + + return; +} + +#define E1000_TX_FLAGS_CSUM 0x00000001 +#define E1000_TX_FLAGS_VLAN 0x00000002 +#define E1000_TX_FLAGS_TSO 0x00000004 +#define E1000_TX_FLAGS_IPV4 0x00000008 +#define E1000_TX_FLAGS_VLAN_MASK 0xffff0000 +#define E1000_TX_FLAGS_VLAN_SHIFT 16 + +static int e1000_tso(struct e1000_adapter *adapter, + struct e1000_tx_ring *tx_ring, struct sk_buff *skb) +{ + struct e1000_context_desc *context_desc; + struct e1000_buffer *buffer_info; + unsigned int i; + u32 cmd_length = 0; + u16 ipcse = 0, tucse, mss; + u8 ipcss, ipcso, tucss, tucso, hdr_len; + int err; + + if (skb_is_gso(skb)) { + if (skb_header_cloned(skb)) { + err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); + if (err) + return err; + } + + hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); + mss = skb_shinfo(skb)->gso_size; + if (skb->protocol == 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); + cmd_length = E1000_TXD_CMD_IP; + ipcse = skb_transport_offset(skb) - 1; + } else if (skb->protocol == htons(ETH_P_IPV6)) { + 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); + ipcse = 0; + } + ipcss = skb_network_offset(skb); + ipcso = (void *)&(ip_hdr(skb)->check) - (void *)skb->data; + tucss = skb_transport_offset(skb); + tucso = (void *)&(tcp_hdr(skb)->check) - (void *)skb->data; + tucse = 0; + + cmd_length |= (E1000_TXD_CMD_DEXT | E1000_TXD_CMD_TSE | + E1000_TXD_CMD_TCP | (skb->len - (hdr_len))); + + i = tx_ring->next_to_use; + context_desc = E1000_CONTEXT_DESC(*tx_ring, i); + buffer_info = &tx_ring->buffer_info[i]; + + context_desc->lower_setup.ip_fields.ipcss = ipcss; + context_desc->lower_setup.ip_fields.ipcso = ipcso; + context_desc->lower_setup.ip_fields.ipcse = cpu_to_le16(ipcse); + context_desc->upper_setup.tcp_fields.tucss = tucss; + context_desc->upper_setup.tcp_fields.tucso = tucso; + context_desc->upper_setup.tcp_fields.tucse = cpu_to_le16(tucse); + context_desc->tcp_seg_setup.fields.mss = cpu_to_le16(mss); + context_desc->tcp_seg_setup.fields.hdr_len = hdr_len; + context_desc->cmd_and_length = cpu_to_le32(cmd_length); + + buffer_info->time_stamp = jiffies; + buffer_info->next_to_watch = i; + + if (++i == tx_ring->count) i = 0; + tx_ring->next_to_use = i; + + return true; + } + return false; +} + +static bool e1000_tx_csum(struct e1000_adapter *adapter, + struct e1000_tx_ring *tx_ring, struct sk_buff *skb) +{ + struct e1000_context_desc *context_desc; + struct e1000_buffer *buffer_info; + unsigned int i; + u8 css; + + if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) { + css = skb_transport_offset(skb); + + i = tx_ring->next_to_use; + buffer_info = &tx_ring->buffer_info[i]; + context_desc = E1000_CONTEXT_DESC(*tx_ring, i); + + context_desc->lower_setup.ip_config = 0; + context_desc->upper_setup.tcp_fields.tucss = css; + context_desc->upper_setup.tcp_fields.tucso = + css + skb->csum_offset; + context_desc->upper_setup.tcp_fields.tucse = 0; + context_desc->tcp_seg_setup.data = 0; + context_desc->cmd_and_length = cpu_to_le32(E1000_TXD_CMD_DEXT); + + buffer_info->time_stamp = jiffies; + buffer_info->next_to_watch = i; + + if (unlikely(++i == tx_ring->count)) i = 0; + tx_ring->next_to_use = i; + + return true; + } + + return false; +} + +#define E1000_MAX_TXD_PWR 12 +#define E1000_MAX_DATA_PER_TXD (1<hw; + struct e1000_buffer *buffer_info; + unsigned int len = skb->len; + unsigned int offset = 0, size, count = 0, i; + unsigned int f; + len -= skb->data_len; + + i = tx_ring->next_to_use; + + while (len) { + buffer_info = &tx_ring->buffer_info[i]; + size = min(len, max_per_txd); + /* Workaround for Controller erratum -- + * descriptor for non-tso packet in a linear SKB that follows a + * tso gets written back prematurely before the data is fully + * DMA'd to the controller */ + if (!skb->data_len && tx_ring->last_tx_tso && + !skb_is_gso(skb)) { + tx_ring->last_tx_tso = 0; + size -= 4; + } + + /* Workaround for premature desc write-backs + * in TSO mode. Append 4-byte sentinel desc */ + if (unlikely(mss && !nr_frags && size == len && size > 8)) + size -= 4; + /* work-around for errata 10 and it applies + * to all controllers in PCI-X mode + * The fix is to make sure that the first descriptor of a + * packet is smaller than 2048 - 16 - 16 (or 2016) bytes + */ + if (unlikely((hw->bus_type == e1000_bus_type_pcix) && + (size > 2015) && count == 0)) + size = 2015; + + /* Workaround for potential 82544 hang in PCI-X. Avoid + * terminating buffers within evenly-aligned dwords. */ + if (unlikely(adapter->pcix_82544 && + !((unsigned long)(skb->data + offset + size - 1) & 4) && + size > 4)) + size -= 4; + + buffer_info->length = size; + buffer_info->dma = + pci_map_single(adapter->pdev, + skb->data + offset, + size, + PCI_DMA_TODEVICE); + buffer_info->time_stamp = jiffies; + buffer_info->next_to_watch = i; + + len -= size; + offset += size; + count++; + if (unlikely(++i == tx_ring->count)) i = 0; + } + + for (f = 0; f < nr_frags; f++) { + struct skb_frag_struct *frag; + + frag = &skb_shinfo(skb)->frags[f]; + len = frag->size; + offset = frag->page_offset; + + while (len) { + buffer_info = &tx_ring->buffer_info[i]; + size = min(len, max_per_txd); + /* Workaround for premature desc write-backs + * in TSO mode. Append 4-byte sentinel desc */ + if (unlikely(mss && f == (nr_frags-1) && size == len && size > 8)) + size -= 4; + /* Workaround for potential 82544 hang in PCI-X. + * Avoid terminating buffers within evenly-aligned + * dwords. */ + if (unlikely(adapter->pcix_82544 && + !((unsigned long)(frag->page+offset+size-1) & 4) && + size > 4)) + size -= 4; + + buffer_info->length = size; + buffer_info->dma = + pci_map_page(adapter->pdev, + frag->page, + offset, + size, + PCI_DMA_TODEVICE); + buffer_info->time_stamp = jiffies; + buffer_info->next_to_watch = i; + + len -= size; + offset += size; + count++; + if (unlikely(++i == tx_ring->count)) i = 0; + } + } + + i = (i == 0) ? tx_ring->count - 1 : i - 1; + tx_ring->buffer_info[i].skb = skb; + tx_ring->buffer_info[first].next_to_watch = i; + + return count; +} + +static void e1000_tx_queue(struct e1000_adapter *adapter, + struct e1000_tx_ring *tx_ring, int tx_flags, + int count) +{ + struct e1000_hw *hw = &adapter->hw; + struct e1000_tx_desc *tx_desc = NULL; + struct e1000_buffer *buffer_info; + u32 txd_upper = 0, txd_lower = E1000_TXD_CMD_IFCS; + unsigned int i; + + if (likely(tx_flags & E1000_TX_FLAGS_TSO)) { + txd_lower |= E1000_TXD_CMD_DEXT | E1000_TXD_DTYP_D | + E1000_TXD_CMD_TSE; + txd_upper |= E1000_TXD_POPTS_TXSM << 8; + + if (likely(tx_flags & E1000_TX_FLAGS_IPV4)) + txd_upper |= E1000_TXD_POPTS_IXSM << 8; + } + + if (likely(tx_flags & E1000_TX_FLAGS_CSUM)) { + txd_lower |= E1000_TXD_CMD_DEXT | E1000_TXD_DTYP_D; + txd_upper |= E1000_TXD_POPTS_TXSM << 8; + } + + if (unlikely(tx_flags & E1000_TX_FLAGS_VLAN)) { + txd_lower |= E1000_TXD_CMD_VLE; + txd_upper |= (tx_flags & E1000_TX_FLAGS_VLAN_MASK); + } + + i = tx_ring->next_to_use; + + while (count--) { + buffer_info = &tx_ring->buffer_info[i]; + tx_desc = E1000_TX_DESC(*tx_ring, i); + tx_desc->buffer_addr = cpu_to_le64(buffer_info->dma); + tx_desc->lower.data = + cpu_to_le32(txd_lower | buffer_info->length); + tx_desc->upper.data = cpu_to_le32(txd_upper); + if (unlikely(++i == tx_ring->count)) i = 0; + } + + tx_desc->lower.data |= cpu_to_le32(adapter->txd_cmd); + + /* 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(); + + tx_ring->next_to_use = i; + writel(i, hw->hw_addr + tx_ring->tdt); + /* we need this if more than one processor can write to our tail + * at a time, it syncronizes IO on IA64/Altix systems */ + mmiowb(); +} + +/** + * 82547 workaround to avoid controller hang in half-duplex environment. + * The workaround is to avoid queuing a large packet that would span + * the internal Tx FIFO ring boundary by notifying the stack to resend + * the packet at a later time. This gives the Tx FIFO an opportunity to + * flush all packets. When that occurs, we reset the Tx FIFO pointers + * to the beginning of the Tx FIFO. + **/ + +#define E1000_FIFO_HDR 0x10 +#define E1000_82547_PAD_LEN 0x3E0 + +static int e1000_82547_fifo_workaround(struct e1000_adapter *adapter, + struct sk_buff *skb) +{ + u32 fifo_space = adapter->tx_fifo_size - adapter->tx_fifo_head; + u32 skb_fifo_len = skb->len + E1000_FIFO_HDR; + + skb_fifo_len = ALIGN(skb_fifo_len, E1000_FIFO_HDR); + + if (adapter->link_duplex != HALF_DUPLEX) + goto no_fifo_stall_required; + + if (atomic_read(&adapter->tx_fifo_stall)) + return 1; + + if (skb_fifo_len >= (E1000_82547_PAD_LEN + fifo_space)) { + atomic_set(&adapter->tx_fifo_stall, 1); + return 1; + } + +no_fifo_stall_required: + adapter->tx_fifo_head += skb_fifo_len; + if (adapter->tx_fifo_head >= adapter->tx_fifo_size) + adapter->tx_fifo_head -= adapter->tx_fifo_size; + return 0; +} + +#define MINIMUM_DHCP_PACKET_SIZE 282 +static int e1000_transfer_dhcp_info(struct e1000_adapter *adapter, + struct sk_buff *skb) +{ + struct e1000_hw *hw = &adapter->hw; + u16 length, offset; + if (vlan_tx_tag_present(skb)) { + if (!((vlan_tx_tag_get(skb) == hw->mng_cookie.vlan_id) && + ( hw->mng_cookie.status & + E1000_MNG_DHCP_COOKIE_STATUS_VLAN_SUPPORT)) ) + return 0; + } + if (skb->len > MINIMUM_DHCP_PACKET_SIZE) { + struct ethhdr *eth = (struct ethhdr *)skb->data; + if ((htons(ETH_P_IP) == eth->h_proto)) { + const struct iphdr *ip = + (struct iphdr *)((u8 *)skb->data+14); + if (IPPROTO_UDP == ip->protocol) { + struct udphdr *udp = + (struct udphdr *)((u8 *)ip + + (ip->ihl << 2)); + if (ntohs(udp->dest) == 67) { + offset = (u8 *)udp + 8 - skb->data; + length = skb->len - offset; + + return e1000_mng_write_dhcp_info(hw, + (u8 *)udp + 8, + length); + } + } + } + } + return 0; +} + +static int __e1000_maybe_stop_tx(struct net_device *netdev, int size) +{ + struct e1000_adapter *adapter = netdev_priv(netdev); + struct e1000_tx_ring *tx_ring = adapter->tx_ring; + + netif_stop_queue(netdev); + /* 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 (likely(E1000_DESC_UNUSED(tx_ring) < size)) + return -EBUSY; + + /* A reprieve! */ + netif_start_queue(netdev); + ++adapter->restart_queue; + return 0; +} + +static int e1000_maybe_stop_tx(struct net_device *netdev, + struct e1000_tx_ring *tx_ring, int size) +{ + if (likely(E1000_DESC_UNUSED(tx_ring) >= size)) + return 0; + return __e1000_maybe_stop_tx(netdev, size); +} + +#define TXD_USE_COUNT(S, X) (((S) >> (X)) + 1 ) +static int e1000_xmit_frame(struct sk_buff *skb, struct net_device *netdev) +{ + struct e1000_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + struct e1000_tx_ring *tx_ring; + unsigned int first, max_per_txd = E1000_MAX_DATA_PER_TXD; + unsigned int max_txd_pwr = E1000_MAX_TXD_PWR; + unsigned int tx_flags = 0; + unsigned int len = skb->len - skb->data_len; + unsigned long flags; + unsigned int nr_frags; + unsigned int mss; + int count = 0; + int tso; + unsigned int f; + + /* This goes back to the question of how to logically map a tx queue + * to a flow. Right now, performance is impacted slightly negatively + * if using multiple tx queues. If the stack breaks away from a + * single qdisc implementation, we can look at this again. */ + tx_ring = adapter->tx_ring; + + if (unlikely(skb->len <= 0)) { + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } + + /* 82571 and newer doesn't need the workaround that limited descriptor + * length to 4kB */ + if (hw->mac_type >= e1000_82571) + max_per_txd = 8192; + + mss = skb_shinfo(skb)->gso_size; + /* The controller does a simple calculation to + * make sure there is enough room in the FIFO before + * initiating the DMA for each buffer. The calc is: + * 4 = ceil(buffer len/mss). To make sure we don't + * overrun the FIFO, adjust the max buffer len if mss + * drops. */ + if (mss) { + u8 hdr_len; + max_per_txd = min(mss << 2, max_per_txd); + max_txd_pwr = fls(max_per_txd) - 1; + + /* TSO Workaround for 82571/2/3 Controllers -- if skb->data + * points to just header, pull a few bytes of payload from + * frags into skb->data */ + hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); + if (skb->data_len && hdr_len == len) { + switch (hw->mac_type) { + unsigned int pull_size; + case e1000_82544: + /* Make sure we have room to chop off 4 bytes, + * and that the end alignment will work out to + * this hardware's requirements + * NOTE: this is a TSO only workaround + * if end byte alignment not correct move us + * into the next dword */ + if ((unsigned long)(skb_tail_pointer(skb) - 1) & 4) + break; + /* fall through */ + case e1000_82571: + case e1000_82572: + case e1000_82573: + case e1000_ich8lan: + pull_size = min((unsigned int)4, skb->data_len); + if (!__pskb_pull_tail(skb, pull_size)) { + DPRINTK(DRV, ERR, + "__pskb_pull_tail failed.\n"); + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } + len = skb->len - skb->data_len; + break; + default: + /* do nothing */ + break; + } + } + } + + /* reserve a descriptor for the offload context */ + if ((mss) || (skb->ip_summed == CHECKSUM_PARTIAL)) + count++; + count++; + + /* Controller Erratum workaround */ + if (!skb->data_len && tx_ring->last_tx_tso && !skb_is_gso(skb)) + count++; + + count += TXD_USE_COUNT(len, max_txd_pwr); + + if (adapter->pcix_82544) + count++; + + /* work-around for errata 10 and it applies to all controllers + * in PCI-X mode, so add one more descriptor to the count + */ + if (unlikely((hw->bus_type == e1000_bus_type_pcix) && + (len > 2015))) + count++; + + nr_frags = skb_shinfo(skb)->nr_frags; + for (f = 0; f < nr_frags; f++) + count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size, + max_txd_pwr); + if (adapter->pcix_82544) + count += nr_frags; + + + if (hw->tx_pkt_filtering && + (hw->mac_type == e1000_82573)) + e1000_transfer_dhcp_info(adapter, skb); + + if (!spin_trylock_irqsave(&tx_ring->tx_lock, flags)) + /* Collision - tell upper layer to requeue */ + return NETDEV_TX_LOCKED; + + /* need: count + 2 desc gap to keep tail from touching + * head, otherwise try next time */ + if (unlikely(e1000_maybe_stop_tx(netdev, tx_ring, count + 2))) { + spin_unlock_irqrestore(&tx_ring->tx_lock, flags); + return NETDEV_TX_BUSY; + } + + if (unlikely(hw->mac_type == e1000_82547)) { + if (unlikely(e1000_82547_fifo_workaround(adapter, skb))) { + netif_stop_queue(netdev); + mod_timer(&adapter->tx_fifo_stall_timer, jiffies + 1); + spin_unlock_irqrestore(&tx_ring->tx_lock, flags); + return NETDEV_TX_BUSY; + } + } + + if (unlikely(adapter->vlgrp && vlan_tx_tag_present(skb))) { + tx_flags |= E1000_TX_FLAGS_VLAN; + tx_flags |= (vlan_tx_tag_get(skb) << E1000_TX_FLAGS_VLAN_SHIFT); + } + + first = tx_ring->next_to_use; + + tso = e1000_tso(adapter, tx_ring, skb); + if (tso < 0) { + dev_kfree_skb_any(skb); + spin_unlock_irqrestore(&tx_ring->tx_lock, flags); + return NETDEV_TX_OK; + } + + if (likely(tso)) { + tx_ring->last_tx_tso = 1; + tx_flags |= E1000_TX_FLAGS_TSO; + } else if (likely(e1000_tx_csum(adapter, tx_ring, skb))) + tx_flags |= E1000_TX_FLAGS_CSUM; + + /* Old method was to assume IPv4 packet by default if TSO was enabled. + * 82571 hardware supports TSO capabilities for IPv6 as well... + * no longer assume, we must. */ + if (likely(skb->protocol == htons(ETH_P_IP))) + tx_flags |= E1000_TX_FLAGS_IPV4; + + e1000_tx_queue(adapter, tx_ring, tx_flags, + e1000_tx_map(adapter, tx_ring, skb, first, + max_per_txd, nr_frags, mss)); + + netdev->trans_start = jiffies; + + /* Make sure there is space in the ring for the next send. */ + e1000_maybe_stop_tx(netdev, tx_ring, MAX_SKB_FRAGS + 2); + + spin_unlock_irqrestore(&tx_ring->tx_lock, flags); + return NETDEV_TX_OK; +} + +/** + * e1000_tx_timeout - Respond to a Tx Hang + * @netdev: network interface device structure + **/ + +static void e1000_tx_timeout(struct net_device *netdev) +{ + struct e1000_adapter *adapter = netdev_priv(netdev); + + /* Do the reset outside of interrupt context */ + adapter->tx_timeout_count++; + schedule_work(&adapter->reset_task); +} + +static void e1000_reset_task(struct work_struct *work) +{ + struct e1000_adapter *adapter = + container_of(work, struct e1000_adapter, reset_task); + + e1000_reinit_locked(adapter); +} + +/** + * e1000_get_stats - Get System Network Statistics + * @netdev: network interface device structure + * + * Returns the address of the device statistics structure. + * The statistics are actually updated from the timer callback. + **/ + +static struct net_device_stats *e1000_get_stats(struct net_device *netdev) +{ + struct e1000_adapter *adapter = netdev_priv(netdev); + + /* only return the current stats */ + return &adapter->net_stats; +} + +/** + * e1000_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 e1000_change_mtu(struct net_device *netdev, int new_mtu) +{ + struct e1000_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + int max_frame = new_mtu + ENET_HEADER_SIZE + ETHERNET_FCS_SIZE; + u16 eeprom_data = 0; + + if ((max_frame < MINIMUM_ETHERNET_FRAME_SIZE) || + (max_frame > MAX_JUMBO_FRAME_SIZE)) { + DPRINTK(PROBE, ERR, "Invalid MTU setting\n"); + return -EINVAL; + } + + /* Adapter-specific max frame size limits. */ + switch (hw->mac_type) { + case e1000_undefined ... e1000_82542_rev2_1: + case e1000_ich8lan: + if (max_frame > MAXIMUM_ETHERNET_FRAME_SIZE) { + DPRINTK(PROBE, ERR, "Jumbo Frames not supported.\n"); + return -EINVAL; + } + break; + case e1000_82573: + /* Jumbo Frames not supported if: + * - this is not an 82573L device + * - ASPM is enabled in any way (0x1A bits 3:2) */ + e1000_read_eeprom(hw, EEPROM_INIT_3GIO_3, 1, + &eeprom_data); + if ((hw->device_id != E1000_DEV_ID_82573L) || + (eeprom_data & EEPROM_WORD1A_ASPM_MASK)) { + if (max_frame > MAXIMUM_ETHERNET_FRAME_SIZE) { + DPRINTK(PROBE, ERR, + "Jumbo Frames not supported.\n"); + return -EINVAL; + } + break; + } + /* ERT will be enabled later to enable wire speed receives */ + + /* fall through to get support */ + case e1000_82571: + case e1000_82572: + case e1000_80003es2lan: +#define MAX_STD_JUMBO_FRAME_SIZE 9234 + if (max_frame > MAX_STD_JUMBO_FRAME_SIZE) { + DPRINTK(PROBE, ERR, "MTU > 9216 not supported.\n"); + return -EINVAL; + } + break; + default: + /* Capable of supporting up to MAX_JUMBO_FRAME_SIZE limit. */ + break; + } + + /* NOTE: netdev_alloc_skb reserves 16 bytes, and typically NET_IP_ALIGN + * means we reserve 2 more, this pushes us to allocate from the next + * larger slab size + * i.e. RXBUFFER_2048 --> size-4096 slab */ + + if (max_frame <= E1000_RXBUFFER_256) + adapter->rx_buffer_len = E1000_RXBUFFER_256; + else if (max_frame <= E1000_RXBUFFER_512) + adapter->rx_buffer_len = E1000_RXBUFFER_512; + else if (max_frame <= E1000_RXBUFFER_1024) + adapter->rx_buffer_len = E1000_RXBUFFER_1024; + else if (max_frame <= E1000_RXBUFFER_2048) + adapter->rx_buffer_len = E1000_RXBUFFER_2048; + else if (max_frame <= E1000_RXBUFFER_4096) + adapter->rx_buffer_len = E1000_RXBUFFER_4096; + else if (max_frame <= E1000_RXBUFFER_8192) + adapter->rx_buffer_len = E1000_RXBUFFER_8192; + else if (max_frame <= E1000_RXBUFFER_16384) + adapter->rx_buffer_len = E1000_RXBUFFER_16384; + + /* adjust allocation if LPE protects us, and we aren't using SBP */ + if (!hw->tbi_compatibility_on && + ((max_frame == MAXIMUM_ETHERNET_FRAME_SIZE) || + (max_frame == MAXIMUM_ETHERNET_VLAN_SIZE))) + adapter->rx_buffer_len = MAXIMUM_ETHERNET_VLAN_SIZE; + + netdev->mtu = new_mtu; + hw->max_frame_size = max_frame; + + if (netif_running(netdev)) + e1000_reinit_locked(adapter); + + return 0; +} + +/** + * e1000_update_stats - Update the board statistics counters + * @adapter: board private structure + **/ + +void e1000_update_stats(struct e1000_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + struct pci_dev *pdev = adapter->pdev; + unsigned long flags; + u16 phy_tmp; + +#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; + + spin_lock_irqsave(&adapter->stats_lock, flags); + + /* these counters are modified from e1000_tbi_adjust_stats, + * called from the interrupt context, so they must only + * be written while holding adapter->stats_lock + */ + + adapter->stats.crcerrs += er32(CRCERRS); + adapter->stats.gprc += er32(GPRC); + adapter->stats.gorcl += er32(GORCL); + adapter->stats.gorch += er32(GORCH); + adapter->stats.bprc += er32(BPRC); + adapter->stats.mprc += er32(MPRC); + adapter->stats.roc += er32(ROC); + + if (hw->mac_type != e1000_ich8lan) { + adapter->stats.prc64 += er32(PRC64); + adapter->stats.prc127 += er32(PRC127); + adapter->stats.prc255 += er32(PRC255); + adapter->stats.prc511 += er32(PRC511); + adapter->stats.prc1023 += er32(PRC1023); + adapter->stats.prc1522 += er32(PRC1522); + } + + adapter->stats.symerrs += er32(SYMERRS); + adapter->stats.mpc += er32(MPC); + adapter->stats.scc += er32(SCC); + adapter->stats.ecol += er32(ECOL); + adapter->stats.mcc += er32(MCC); + adapter->stats.latecol += er32(LATECOL); + adapter->stats.dc += er32(DC); + adapter->stats.sec += er32(SEC); + adapter->stats.rlec += er32(RLEC); + adapter->stats.xonrxc += er32(XONRXC); + adapter->stats.xontxc += er32(XONTXC); + adapter->stats.xoffrxc += er32(XOFFRXC); + adapter->stats.xofftxc += er32(XOFFTXC); + adapter->stats.fcruc += er32(FCRUC); + adapter->stats.gptc += er32(GPTC); + adapter->stats.gotcl += er32(GOTCL); + adapter->stats.gotch += er32(GOTCH); + adapter->stats.rnbc += er32(RNBC); + adapter->stats.ruc += er32(RUC); + adapter->stats.rfc += er32(RFC); + adapter->stats.rjc += er32(RJC); + adapter->stats.torl += er32(TORL); + adapter->stats.torh += er32(TORH); + adapter->stats.totl += er32(TOTL); + adapter->stats.toth += er32(TOTH); + adapter->stats.tpr += er32(TPR); + + if (hw->mac_type != e1000_ich8lan) { + adapter->stats.ptc64 += er32(PTC64); + adapter->stats.ptc127 += er32(PTC127); + adapter->stats.ptc255 += er32(PTC255); + adapter->stats.ptc511 += er32(PTC511); + adapter->stats.ptc1023 += er32(PTC1023); + adapter->stats.ptc1522 += er32(PTC1522); + } + + adapter->stats.mptc += er32(MPTC); + adapter->stats.bptc += er32(BPTC); + + /* used for adaptive IFS */ + + hw->tx_packet_delta = er32(TPT); + adapter->stats.tpt += hw->tx_packet_delta; + hw->collision_delta = er32(COLC); + adapter->stats.colc += hw->collision_delta; + + if (hw->mac_type >= e1000_82543) { + adapter->stats.algnerrc += er32(ALGNERRC); + adapter->stats.rxerrc += er32(RXERRC); + adapter->stats.tncrs += er32(TNCRS); + adapter->stats.cexterr += er32(CEXTERR); + adapter->stats.tsctc += er32(TSCTC); + adapter->stats.tsctfc += er32(TSCTFC); + } + if (hw->mac_type > e1000_82547_rev_2) { + adapter->stats.iac += er32(IAC); + adapter->stats.icrxoc += er32(ICRXOC); + + if (hw->mac_type != e1000_ich8lan) { + adapter->stats.icrxptc += er32(ICRXPTC); + adapter->stats.icrxatc += er32(ICRXATC); + adapter->stats.ictxptc += er32(ICTXPTC); + adapter->stats.ictxatc += er32(ICTXATC); + adapter->stats.ictxqec += er32(ICTXQEC); + adapter->stats.ictxqmtc += er32(ICTXQMTC); + adapter->stats.icrxdmtc += er32(ICRXDMTC); + } + } + + /* Fill out the OS statistics structure */ + adapter->net_stats.multicast = adapter->stats.mprc; + adapter->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 */ + adapter->net_stats.rx_errors = adapter->stats.rxerrc + + adapter->stats.crcerrs + adapter->stats.algnerrc + + adapter->stats.ruc + adapter->stats.roc + + adapter->stats.cexterr; + adapter->stats.rlerrc = adapter->stats.ruc + adapter->stats.roc; + adapter->net_stats.rx_length_errors = adapter->stats.rlerrc; + adapter->net_stats.rx_crc_errors = adapter->stats.crcerrs; + adapter->net_stats.rx_frame_errors = adapter->stats.algnerrc; + adapter->net_stats.rx_missed_errors = adapter->stats.mpc; + + /* Tx Errors */ + adapter->stats.txerrc = adapter->stats.ecol + adapter->stats.latecol; + adapter->net_stats.tx_errors = adapter->stats.txerrc; + adapter->net_stats.tx_aborted_errors = adapter->stats.ecol; + adapter->net_stats.tx_window_errors = adapter->stats.latecol; + adapter->net_stats.tx_carrier_errors = adapter->stats.tncrs; + if (hw->bad_tx_carr_stats_fd && + adapter->link_duplex == FULL_DUPLEX) { + adapter->net_stats.tx_carrier_errors = 0; + adapter->stats.tncrs = 0; + } + + /* Tx Dropped needs to be maintained elsewhere */ + + /* Phy Stats */ + if (hw->media_type == e1000_media_type_copper) { + if ((adapter->link_speed == SPEED_1000) && + (!e1000_read_phy_reg(hw, PHY_1000T_STATUS, &phy_tmp))) { + phy_tmp &= PHY_IDLE_ERROR_COUNT_MASK; + adapter->phy_stats.idle_errors += phy_tmp; + } + + if ((hw->mac_type <= e1000_82546) && + (hw->phy_type == e1000_phy_m88) && + !e1000_read_phy_reg(hw, M88E1000_RX_ERR_CNTR, &phy_tmp)) + adapter->phy_stats.receive_errors += phy_tmp; + } + + /* Management Stats */ + if (hw->has_smbus) { + adapter->stats.mgptc += er32(MGTPTC); + adapter->stats.mgprc += er32(MGTPRC); + adapter->stats.mgpdc += er32(MGTPDC); + } + + spin_unlock_irqrestore(&adapter->stats_lock, flags); +} + +/** + * e1000_intr_msi - Interrupt Handler + * @irq: interrupt number + * @data: pointer to a network interface device structure + **/ + +static irqreturn_t e1000_intr_msi(int irq, void *data) +{ + struct net_device *netdev = data; + struct e1000_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + u32 icr = er32(ICR); + + /* in NAPI mode read ICR disables interrupts using IAM */ + + if (icr & (E1000_ICR_RXSEQ | E1000_ICR_LSC)) { + hw->get_link_status = 1; + /* 80003ES2LAN workaround-- For packet buffer work-around on + * link down event; disable receives here in the ISR and reset + * adapter in watchdog */ + if (netif_carrier_ok(netdev) && + (hw->mac_type == e1000_80003es2lan)) { + /* disable receives */ + u32 rctl = er32(RCTL); + ew32(RCTL, rctl & ~E1000_RCTL_EN); + } + /* guard against interrupt when we're going down */ + if (!test_bit(__E1000_DOWN, &adapter->flags)) + mod_timer(&adapter->watchdog_timer, jiffies + 1); + } + + if (likely(netif_rx_schedule_prep(netdev, &adapter->napi))) { + adapter->total_tx_bytes = 0; + adapter->total_tx_packets = 0; + adapter->total_rx_bytes = 0; + adapter->total_rx_packets = 0; + __netif_rx_schedule(netdev, &adapter->napi); + } else + e1000_irq_enable(adapter); + + return IRQ_HANDLED; +} + +/** + * e1000_intr - Interrupt Handler + * @irq: interrupt number + * @data: pointer to a network interface device structure + **/ + +static irqreturn_t e1000_intr(int irq, void *data) +{ + struct net_device *netdev = data; + struct e1000_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + u32 rctl, icr = er32(ICR); + + if (unlikely((!icr) || test_bit(__E1000_RESETTING, &adapter->flags))) + return IRQ_NONE; /* Not our interrupt */ + + /* 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 (unlikely(hw->mac_type >= e1000_82571 && + !(icr & E1000_ICR_INT_ASSERTED))) + return IRQ_NONE; + + /* Interrupt Auto-Mask...upon reading ICR, interrupts are masked. No + * need for the IMC write */ + + if (unlikely(icr & (E1000_ICR_RXSEQ | E1000_ICR_LSC))) { + hw->get_link_status = 1; + /* 80003ES2LAN workaround-- + * For packet buffer work-around on link down event; + * disable receives here in the ISR and + * reset adapter in watchdog + */ + if (netif_carrier_ok(netdev) && + (hw->mac_type == e1000_80003es2lan)) { + /* disable receives */ + rctl = er32(RCTL); + ew32(RCTL, rctl & ~E1000_RCTL_EN); + } + /* guard against interrupt when we're going down */ + if (!test_bit(__E1000_DOWN, &adapter->flags)) + mod_timer(&adapter->watchdog_timer, jiffies + 1); + } + + if (unlikely(hw->mac_type < e1000_82571)) { + /* disable interrupts, without the synchronize_irq bit */ + ew32(IMC, ~0); + E1000_WRITE_FLUSH(); + } + if (likely(netif_rx_schedule_prep(netdev, &adapter->napi))) { + adapter->total_tx_bytes = 0; + adapter->total_tx_packets = 0; + adapter->total_rx_bytes = 0; + adapter->total_rx_packets = 0; + __netif_rx_schedule(netdev, &adapter->napi); + } else + /* this really should not happen! if it does it is basically a + * bug, but not a hard error, so enable ints and continue */ + e1000_irq_enable(adapter); + + return IRQ_HANDLED; +} + +/** + * e1000_clean - NAPI Rx polling callback + * @adapter: board private structure + **/ +static int e1000_clean(struct napi_struct *napi, int budget) +{ + struct e1000_adapter *adapter = container_of(napi, struct e1000_adapter, napi); + struct net_device *poll_dev = adapter->netdev; + int tx_cleaned = 0, work_done = 0; + + /* Must NOT use netdev_priv macro here. */ + adapter = poll_dev->priv; + + /* e1000_clean is called per-cpu. This lock protects + * tx_ring[0] from being cleaned by multiple cpus + * simultaneously. A failure obtaining the lock means + * tx_ring[0] is currently being cleaned anyway. */ + if (spin_trylock(&adapter->tx_queue_lock)) { + tx_cleaned = e1000_clean_tx_irq(adapter, + &adapter->tx_ring[0]); + spin_unlock(&adapter->tx_queue_lock); + } + + adapter->clean_rx(adapter, &adapter->rx_ring[0], + &work_done, budget); + + if (tx_cleaned) + work_done = budget; + + /* If budget not fully consumed, exit the polling mode */ + if (work_done < budget) { + if (likely(adapter->itr_setting & 3)) + e1000_set_itr(adapter); + netif_rx_complete(poll_dev, napi); + e1000_irq_enable(adapter); + } + + return work_done; +} + +/** + * e1000_clean_tx_irq - Reclaim resources after transmit completes + * @adapter: board private structure + **/ +static bool e1000_clean_tx_irq(struct e1000_adapter *adapter, + struct e1000_tx_ring *tx_ring) +{ + struct e1000_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; + struct e1000_tx_desc *tx_desc, *eop_desc; + struct e1000_buffer *buffer_info; + unsigned int i, eop; + unsigned int count = 0; + bool cleaned = false; + unsigned int total_tx_bytes=0, total_tx_packets=0; + + i = tx_ring->next_to_clean; + eop = tx_ring->buffer_info[i].next_to_watch; + eop_desc = E1000_TX_DESC(*tx_ring, eop); + + while (eop_desc->upper.data & cpu_to_le32(E1000_TXD_STAT_DD)) { + for (cleaned = false; !cleaned; ) { + tx_desc = E1000_TX_DESC(*tx_ring, i); + buffer_info = &tx_ring->buffer_info[i]; + cleaned = (i == eop); + + if (cleaned) { + struct sk_buff *skb = buffer_info->skb; + unsigned int segs, bytecount; + segs = skb_shinfo(skb)->gso_segs ?: 1; + /* multiply data chunks by size of headers */ + bytecount = ((segs - 1) * skb_headlen(skb)) + + skb->len; + total_tx_packets += segs; + total_tx_bytes += bytecount; + } + e1000_unmap_and_free_tx_resource(adapter, buffer_info); + tx_desc->upper.data = 0; + + if (unlikely(++i == tx_ring->count)) i = 0; + } + + eop = tx_ring->buffer_info[i].next_to_watch; + eop_desc = E1000_TX_DESC(*tx_ring, eop); +#define E1000_TX_WEIGHT 64 + /* weight of a sort for tx, to avoid endless transmit cleanup */ + if (count++ == E1000_TX_WEIGHT) + break; + } + + tx_ring->next_to_clean = i; + +#define TX_WAKE_THRESHOLD 32 + if (unlikely(cleaned && netif_carrier_ok(netdev) && + E1000_DESC_UNUSED(tx_ring) >= TX_WAKE_THRESHOLD)) { + /* Make sure that anybody stopping the queue after this + * sees the new next_to_clean. + */ + smp_mb(); + if (netif_queue_stopped(netdev)) { + netif_wake_queue(netdev); + ++adapter->restart_queue; + } + } + + if (adapter->detect_tx_hung) { + /* Detect a transmit hang in hardware, this serializes the + * check with the clearing of time_stamp and movement of i */ + adapter->detect_tx_hung = false; + if (tx_ring->buffer_info[eop].dma && + time_after(jiffies, tx_ring->buffer_info[eop].time_stamp + + (adapter->tx_timeout_factor * HZ)) + && !(er32(STATUS) & E1000_STATUS_TXOFF)) { + + /* detected Tx unit hang */ + DPRINTK(DRV, ERR, "Detected Tx Unit Hang\n" + " Tx Queue <%lu>\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 <%x>\n" + " jiffies <%lx>\n" + " next_to_watch.status <%x>\n", + (unsigned long)((tx_ring - adapter->tx_ring) / + sizeof(struct e1000_tx_ring)), + readl(hw->hw_addr + tx_ring->tdh), + readl(hw->hw_addr + tx_ring->tdt), + tx_ring->next_to_use, + tx_ring->next_to_clean, + tx_ring->buffer_info[eop].time_stamp, + eop, + jiffies, + eop_desc->upper.fields.status); + netif_stop_queue(netdev); + } + } + adapter->total_tx_bytes += total_tx_bytes; + adapter->total_tx_packets += total_tx_packets; + adapter->net_stats.tx_bytes += total_tx_bytes; + adapter->net_stats.tx_packets += total_tx_packets; + return cleaned; +} + +/** + * e1000_rx_checksum - Receive Checksum Offload for 82543 + * @adapter: board private structure + * @status_err: receive descriptor status and error fields + * @csum: receive descriptor csum field + * @sk_buff: socket buffer with received data + **/ + +static void e1000_rx_checksum(struct e1000_adapter *adapter, u32 status_err, + u32 csum, struct sk_buff *skb) +{ + struct e1000_hw *hw = &adapter->hw; + u16 status = (u16)status_err; + u8 errors = (u8)(status_err >> 24); + skb->ip_summed = CHECKSUM_NONE; + + /* 82543 or newer only */ + if (unlikely(hw->mac_type < e1000_82543)) return; + /* Ignore Checksum bit is set */ + if (unlikely(status & E1000_RXD_STAT_IXSM)) return; + /* TCP/UDP checksum error bit is set */ + if (unlikely(errors & E1000_RXD_ERR_TCPE)) { + /* let the stack verify checksum errors */ + adapter->hw_csum_err++; + return; + } + /* TCP/UDP Checksum has not been calculated */ + if (hw->mac_type <= e1000_82547_rev_2) { + if (!(status & E1000_RXD_STAT_TCPCS)) + return; + } else { + if (!(status & (E1000_RXD_STAT_TCPCS | E1000_RXD_STAT_UDPCS))) + return; + } + /* It must be a TCP or UDP packet with a valid checksum */ + if (likely(status & E1000_RXD_STAT_TCPCS)) { + /* TCP checksum is good */ + skb->ip_summed = CHECKSUM_UNNECESSARY; + } else if (hw->mac_type > e1000_82547_rev_2) { + /* IP fragment with UDP payload */ + /* Hardware complements the payload checksum, so we undo it + * and then put the value in host order for further stack use. + */ + __sum16 sum = (__force __sum16)htons(csum); + skb->csum = csum_unfold(~sum); + skb->ip_summed = CHECKSUM_COMPLETE; + } + adapter->hw_csum_good++; +} + +/** + * e1000_clean_rx_irq - Send received data up the network stack; legacy + * @adapter: board private structure + **/ +static bool e1000_clean_rx_irq(struct e1000_adapter *adapter, + struct e1000_rx_ring *rx_ring, + int *work_done, int work_to_do) +{ + struct e1000_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; + struct pci_dev *pdev = adapter->pdev; + struct e1000_rx_desc *rx_desc, *next_rxd; + struct e1000_buffer *buffer_info, *next_buffer; + unsigned long flags; + u32 length; + u8 last_byte; + unsigned int i; + int cleaned_count = 0; + bool cleaned = false; + unsigned int total_rx_bytes=0, total_rx_packets=0; + + i = rx_ring->next_to_clean; + rx_desc = E1000_RX_DESC(*rx_ring, i); + buffer_info = &rx_ring->buffer_info[i]; + + while (rx_desc->status & E1000_RXD_STAT_DD) { + struct sk_buff *skb; + u8 status; + + if (*work_done >= work_to_do) + break; + (*work_done)++; + + status = rx_desc->status; + skb = buffer_info->skb; + buffer_info->skb = NULL; + + prefetch(skb->data - NET_IP_ALIGN); + + if (++i == rx_ring->count) i = 0; + next_rxd = E1000_RX_DESC(*rx_ring, i); + prefetch(next_rxd); + + next_buffer = &rx_ring->buffer_info[i]; + + cleaned = true; + cleaned_count++; + pci_unmap_single(pdev, + buffer_info->dma, + buffer_info->length, + PCI_DMA_FROMDEVICE); + + length = le16_to_cpu(rx_desc->length); + /* !EOP means multiple descriptors were used to store a single + * packet, if thats the case we need to toss it. In fact, we + * to toss every packet with the EOP bit clear and the next + * frame that _does_ have the EOP bit set, as it is by + * definition only a frame fragment + */ + if (unlikely(!(status & E1000_RXD_STAT_EOP))) + set_bit(__E1000_DISCARDING, &adapter->flags); + + if (test_bit(__E1000_DISCARDING, &adapter->flags)) { + /* All receives must fit into a single buffer */ + E1000_DBG("%s: Receive packet consumed multiple" + " buffers\n", netdev->name); + /* recycle */ + buffer_info->skb = skb; + if (status & E1000_RXD_STAT_EOP) + clear_bit(__E1000_DISCARDING, &adapter->flags); + goto next_desc; + } + + if (unlikely(rx_desc->errors & E1000_RXD_ERR_FRAME_ERR_MASK)) { + last_byte = *(skb->data + length - 1); + if (TBI_ACCEPT(hw, status, rx_desc->errors, length, + last_byte)) { + spin_lock_irqsave(&adapter->stats_lock, flags); + e1000_tbi_adjust_stats(hw, &adapter->stats, + length, skb->data); + spin_unlock_irqrestore(&adapter->stats_lock, + flags); + length--; + } else { + /* recycle */ + buffer_info->skb = skb; + goto next_desc; + } + } + + /* adjust length to remove Ethernet CRC, this must be + * done after the TBI_ACCEPT workaround above */ + length -= 4; + + /* probably a little skewed due to removing CRC */ + total_rx_bytes += length; + total_rx_packets++; + + /* code added for copybreak, this should improve + * performance for small packets with large amounts + * of reassembly being done in the stack */ + if (length < copybreak) { + struct sk_buff *new_skb = + netdev_alloc_skb(netdev, length + NET_IP_ALIGN); + if (new_skb) { + skb_reserve(new_skb, NET_IP_ALIGN); + skb_copy_to_linear_data_offset(new_skb, + -NET_IP_ALIGN, + (skb->data - + NET_IP_ALIGN), + (length + + NET_IP_ALIGN)); + /* save the skb in buffer_info as good */ + buffer_info->skb = skb; + skb = new_skb; + } + /* else just continue with the old one */ + } + /* end copybreak code */ + skb_put(skb, length); + + /* Receive Checksum Offload */ + e1000_rx_checksum(adapter, + (u32)(status) | + ((u32)(rx_desc->errors) << 24), + le16_to_cpu(rx_desc->csum), skb); + + skb->protocol = eth_type_trans(skb, netdev); + + if (unlikely(adapter->vlgrp && + (status & E1000_RXD_STAT_VP))) { + vlan_hwaccel_receive_skb(skb, adapter->vlgrp, + le16_to_cpu(rx_desc->special)); + } else { + netif_receive_skb(skb); + } + + netdev->last_rx = jiffies; + +next_desc: + rx_desc->status = 0; + + /* return some buffers to hardware, one at a time is too slow */ + if (unlikely(cleaned_count >= E1000_RX_BUFFER_WRITE)) { + adapter->alloc_rx_buf(adapter, rx_ring, cleaned_count); + cleaned_count = 0; + } + + /* use prefetched values */ + rx_desc = next_rxd; + buffer_info = next_buffer; + } + rx_ring->next_to_clean = i; + + cleaned_count = E1000_DESC_UNUSED(rx_ring); + if (cleaned_count) + adapter->alloc_rx_buf(adapter, rx_ring, cleaned_count); + + adapter->total_rx_packets += total_rx_packets; + adapter->total_rx_bytes += total_rx_bytes; + adapter->net_stats.rx_bytes += total_rx_bytes; + adapter->net_stats.rx_packets += total_rx_packets; + return cleaned; +} + +/** + * e1000_clean_rx_irq_ps - Send received data up the network stack; packet split + * @adapter: board private structure + **/ + +static bool e1000_clean_rx_irq_ps(struct e1000_adapter *adapter, + struct e1000_rx_ring *rx_ring, + int *work_done, int work_to_do) +{ + union e1000_rx_desc_packet_split *rx_desc, *next_rxd; + struct net_device *netdev = adapter->netdev; + struct pci_dev *pdev = adapter->pdev; + struct e1000_buffer *buffer_info, *next_buffer; + struct e1000_ps_page *ps_page; + struct e1000_ps_page_dma *ps_page_dma; + struct sk_buff *skb; + unsigned int i, j; + u32 length, staterr; + int cleaned_count = 0; + bool cleaned = false; + unsigned int total_rx_bytes=0, total_rx_packets=0; + + i = rx_ring->next_to_clean; + rx_desc = E1000_RX_DESC_PS(*rx_ring, i); + staterr = le32_to_cpu(rx_desc->wb.middle.status_error); + buffer_info = &rx_ring->buffer_info[i]; + + while (staterr & E1000_RXD_STAT_DD) { + ps_page = &rx_ring->ps_page[i]; + ps_page_dma = &rx_ring->ps_page_dma[i]; + + if (unlikely(*work_done >= work_to_do)) + break; + (*work_done)++; + + skb = buffer_info->skb; + + /* in the packet split case this is header only */ + prefetch(skb->data - NET_IP_ALIGN); + + if (++i == rx_ring->count) i = 0; + next_rxd = E1000_RX_DESC_PS(*rx_ring, i); + prefetch(next_rxd); + + next_buffer = &rx_ring->buffer_info[i]; + + cleaned = true; + cleaned_count++; + pci_unmap_single(pdev, buffer_info->dma, + buffer_info->length, + PCI_DMA_FROMDEVICE); + + if (unlikely(!(staterr & E1000_RXD_STAT_EOP))) { + E1000_DBG("%s: Packet Split buffers didn't pick up" + " the full packet\n", netdev->name); + dev_kfree_skb_irq(skb); + goto next_desc; + } + + if (unlikely(staterr & E1000_RXDEXT_ERR_FRAME_ERR_MASK)) { + dev_kfree_skb_irq(skb); + goto next_desc; + } + + length = le16_to_cpu(rx_desc->wb.middle.length0); + + if (unlikely(!length)) { + E1000_DBG("%s: Last part of the packet spanning" + " multiple descriptors\n", netdev->name); + dev_kfree_skb_irq(skb); + goto next_desc; + } + + /* Good Receive */ + skb_put(skb, length); + + { + /* this looks ugly, but it seems compiler issues make it + more efficient than reusing j */ + int l1 = le16_to_cpu(rx_desc->wb.upper.length[0]); + + /* page alloc/put takes too long and effects small packet + * throughput, so unsplit small packets and save the alloc/put*/ + if (l1 && (l1 <= copybreak) && ((length + l1) <= adapter->rx_ps_bsize0)) { + u8 *vaddr; + /* there is no documentation about how to call + * kmap_atomic, so we can't hold the mapping + * very long */ + pci_dma_sync_single_for_cpu(pdev, + ps_page_dma->ps_page_dma[0], + PAGE_SIZE, + PCI_DMA_FROMDEVICE); + vaddr = kmap_atomic(ps_page->ps_page[0], + KM_SKB_DATA_SOFTIRQ); + memcpy(skb_tail_pointer(skb), vaddr, l1); + kunmap_atomic(vaddr, KM_SKB_DATA_SOFTIRQ); + pci_dma_sync_single_for_device(pdev, + ps_page_dma->ps_page_dma[0], + PAGE_SIZE, PCI_DMA_FROMDEVICE); + /* remove the CRC */ + l1 -= 4; + skb_put(skb, l1); + goto copydone; + } /* if */ + } + + for (j = 0; j < adapter->rx_ps_pages; j++) { + length = le16_to_cpu(rx_desc->wb.upper.length[j]); + if (!length) + break; + pci_unmap_page(pdev, ps_page_dma->ps_page_dma[j], + PAGE_SIZE, PCI_DMA_FROMDEVICE); + ps_page_dma->ps_page_dma[j] = 0; + skb_add_rx_frag(skb, j, ps_page->ps_page[j], 0, length); + ps_page->ps_page[j] = NULL; + } + + /* strip the ethernet crc, problem is we're using pages now so + * this whole operation can get a little cpu intensive */ + pskb_trim(skb, skb->len - 4); + +copydone: + total_rx_bytes += skb->len; + total_rx_packets++; + + e1000_rx_checksum(adapter, staterr, + le16_to_cpu(rx_desc->wb.lower.hi_dword.csum_ip.csum), skb); + skb->protocol = eth_type_trans(skb, netdev); + + if (likely(rx_desc->wb.upper.header_status & + cpu_to_le16(E1000_RXDPS_HDRSTAT_HDRSP))) + adapter->rx_hdr_split++; + + if (unlikely(adapter->vlgrp && (staterr & E1000_RXD_STAT_VP))) { + vlan_hwaccel_receive_skb(skb, adapter->vlgrp, + le16_to_cpu(rx_desc->wb.middle.vlan)); + } else { + netif_receive_skb(skb); + } + + netdev->last_rx = jiffies; + +next_desc: + rx_desc->wb.middle.status_error &= cpu_to_le32(~0xFF); + buffer_info->skb = NULL; + + /* return some buffers to hardware, one at a time is too slow */ + if (unlikely(cleaned_count >= E1000_RX_BUFFER_WRITE)) { + adapter->alloc_rx_buf(adapter, rx_ring, cleaned_count); + cleaned_count = 0; + } + + /* use prefetched values */ + rx_desc = next_rxd; + buffer_info = next_buffer; + + staterr = le32_to_cpu(rx_desc->wb.middle.status_error); + } + rx_ring->next_to_clean = i; + + cleaned_count = E1000_DESC_UNUSED(rx_ring); + if (cleaned_count) + adapter->alloc_rx_buf(adapter, rx_ring, cleaned_count); + + adapter->total_rx_packets += total_rx_packets; + adapter->total_rx_bytes += total_rx_bytes; + adapter->net_stats.rx_bytes += total_rx_bytes; + adapter->net_stats.rx_packets += total_rx_packets; + return cleaned; +} + +/** + * e1000_alloc_rx_buffers - Replace used receive buffers; legacy & extended + * @adapter: address of board private structure + **/ + +static void e1000_alloc_rx_buffers(struct e1000_adapter *adapter, + struct e1000_rx_ring *rx_ring, + int cleaned_count) +{ + struct e1000_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; + struct pci_dev *pdev = adapter->pdev; + struct e1000_rx_desc *rx_desc; + struct e1000_buffer *buffer_info; + struct sk_buff *skb; + unsigned int i; + unsigned int bufsz = adapter->rx_buffer_len + NET_IP_ALIGN; + + i = rx_ring->next_to_use; + buffer_info = &rx_ring->buffer_info[i]; + + while (cleaned_count--) { + skb = buffer_info->skb; + if (skb) { + skb_trim(skb, 0); + goto map_skb; + } + + skb = netdev_alloc_skb(netdev, bufsz); + if (unlikely(!skb)) { + /* Better luck next round */ + adapter->alloc_rx_buff_failed++; + break; + } + + /* Fix for errata 23, can't cross 64kB boundary */ + if (!e1000_check_64k_bound(adapter, skb->data, bufsz)) { + struct sk_buff *oldskb = skb; + DPRINTK(RX_ERR, ERR, "skb align check failed: %u bytes " + "at %p\n", bufsz, skb->data); + /* Try again, without freeing the previous */ + skb = netdev_alloc_skb(netdev, bufsz); + /* Failed allocation, critical failure */ + if (!skb) { + dev_kfree_skb(oldskb); + break; + } + + if (!e1000_check_64k_bound(adapter, skb->data, bufsz)) { + /* give up */ + dev_kfree_skb(skb); + dev_kfree_skb(oldskb); + break; /* while !buffer_info->skb */ + } + + /* Use new allocation */ + dev_kfree_skb(oldskb); + } + /* Make buffer alignment 2 beyond a 16 byte boundary + * this will result in a 16 byte aligned IP header after + * the 14 byte MAC header is removed + */ + skb_reserve(skb, NET_IP_ALIGN); + + buffer_info->skb = skb; + buffer_info->length = adapter->rx_buffer_len; +map_skb: + buffer_info->dma = pci_map_single(pdev, + skb->data, + adapter->rx_buffer_len, + PCI_DMA_FROMDEVICE); + + /* Fix for errata 23, can't cross 64kB boundary */ + if (!e1000_check_64k_bound(adapter, + (void *)(unsigned long)buffer_info->dma, + adapter->rx_buffer_len)) { + DPRINTK(RX_ERR, ERR, + "dma align check failed: %u bytes at %p\n", + adapter->rx_buffer_len, + (void *)(unsigned long)buffer_info->dma); + dev_kfree_skb(skb); + buffer_info->skb = NULL; + + pci_unmap_single(pdev, buffer_info->dma, + adapter->rx_buffer_len, + PCI_DMA_FROMDEVICE); + + break; /* while !buffer_info->skb */ + } + rx_desc = E1000_RX_DESC(*rx_ring, i); + rx_desc->buffer_addr = cpu_to_le64(buffer_info->dma); + + if (unlikely(++i == rx_ring->count)) + i = 0; + buffer_info = &rx_ring->buffer_info[i]; + } + + if (likely(rx_ring->next_to_use != i)) { + rx_ring->next_to_use = i; + if (unlikely(i-- == 0)) + i = (rx_ring->count - 1); + + /* 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, hw->hw_addr + rx_ring->rdt); + } +} + +/** + * e1000_alloc_rx_buffers_ps - Replace used receive buffers; packet split + * @adapter: address of board private structure + **/ + +static void e1000_alloc_rx_buffers_ps(struct e1000_adapter *adapter, + struct e1000_rx_ring *rx_ring, + int cleaned_count) +{ + struct e1000_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; + struct pci_dev *pdev = adapter->pdev; + union e1000_rx_desc_packet_split *rx_desc; + struct e1000_buffer *buffer_info; + struct e1000_ps_page *ps_page; + struct e1000_ps_page_dma *ps_page_dma; + struct sk_buff *skb; + unsigned int i, j; + + i = rx_ring->next_to_use; + buffer_info = &rx_ring->buffer_info[i]; + ps_page = &rx_ring->ps_page[i]; + ps_page_dma = &rx_ring->ps_page_dma[i]; + + while (cleaned_count--) { + rx_desc = E1000_RX_DESC_PS(*rx_ring, i); + + for (j = 0; j < PS_PAGE_BUFFERS; j++) { + if (j < adapter->rx_ps_pages) { + if (likely(!ps_page->ps_page[j])) { + ps_page->ps_page[j] = + netdev_alloc_page(netdev); + if (unlikely(!ps_page->ps_page[j])) { + adapter->alloc_rx_buff_failed++; + goto no_buffers; + } + ps_page_dma->ps_page_dma[j] = + pci_map_page(pdev, + ps_page->ps_page[j], + 0, PAGE_SIZE, + PCI_DMA_FROMDEVICE); + } + /* Refresh the desc even if buffer_addrs didn't + * change because each write-back erases + * this info. + */ + rx_desc->read.buffer_addr[j+1] = + cpu_to_le64(ps_page_dma->ps_page_dma[j]); + } else + rx_desc->read.buffer_addr[j+1] = ~cpu_to_le64(0); + } + + skb = netdev_alloc_skb(netdev, + adapter->rx_ps_bsize0 + NET_IP_ALIGN); + + if (unlikely(!skb)) { + adapter->alloc_rx_buff_failed++; + break; + } + + /* Make buffer alignment 2 beyond a 16 byte boundary + * this will result in a 16 byte aligned IP header after + * the 14 byte MAC header is removed + */ + skb_reserve(skb, NET_IP_ALIGN); + + buffer_info->skb = skb; + buffer_info->length = adapter->rx_ps_bsize0; + buffer_info->dma = pci_map_single(pdev, skb->data, + adapter->rx_ps_bsize0, + PCI_DMA_FROMDEVICE); + + rx_desc->read.buffer_addr[0] = cpu_to_le64(buffer_info->dma); + + if (unlikely(++i == rx_ring->count)) i = 0; + buffer_info = &rx_ring->buffer_info[i]; + ps_page = &rx_ring->ps_page[i]; + ps_page_dma = &rx_ring->ps_page_dma[i]; + } + +no_buffers: + if (likely(rx_ring->next_to_use != i)) { + rx_ring->next_to_use = i; + if (unlikely(i-- == 0)) i = (rx_ring->count - 1); + + /* 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(); + /* Hardware increments by 16 bytes, but packet split + * descriptors are 32 bytes...so we increment tail + * twice as much. + */ + writel(i<<1, hw->hw_addr + rx_ring->rdt); + } +} + +/** + * e1000_smartspeed - Workaround for SmartSpeed on 82541 and 82547 controllers. + * @adapter: + **/ + +static void e1000_smartspeed(struct e1000_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u16 phy_status; + u16 phy_ctrl; + + if ((hw->phy_type != e1000_phy_igp) || !hw->autoneg || + !(hw->autoneg_advertised & ADVERTISE_1000_FULL)) + return; + + if (adapter->smartspeed == 0) { + /* If Master/Slave config fault is asserted twice, + * we assume back-to-back */ + e1000_read_phy_reg(hw, PHY_1000T_STATUS, &phy_status); + if (!(phy_status & SR_1000T_MS_CONFIG_FAULT)) return; + e1000_read_phy_reg(hw, PHY_1000T_STATUS, &phy_status); + if (!(phy_status & SR_1000T_MS_CONFIG_FAULT)) return; + e1000_read_phy_reg(hw, PHY_1000T_CTRL, &phy_ctrl); + if (phy_ctrl & CR_1000T_MS_ENABLE) { + phy_ctrl &= ~CR_1000T_MS_ENABLE; + e1000_write_phy_reg(hw, PHY_1000T_CTRL, + phy_ctrl); + adapter->smartspeed++; + if (!e1000_phy_setup_autoneg(hw) && + !e1000_read_phy_reg(hw, PHY_CTRL, + &phy_ctrl)) { + phy_ctrl |= (MII_CR_AUTO_NEG_EN | + MII_CR_RESTART_AUTO_NEG); + e1000_write_phy_reg(hw, PHY_CTRL, + phy_ctrl); + } + } + return; + } else if (adapter->smartspeed == E1000_SMARTSPEED_DOWNSHIFT) { + /* If still no link, perhaps using 2/3 pair cable */ + e1000_read_phy_reg(hw, PHY_1000T_CTRL, &phy_ctrl); + phy_ctrl |= CR_1000T_MS_ENABLE; + e1000_write_phy_reg(hw, PHY_1000T_CTRL, phy_ctrl); + if (!e1000_phy_setup_autoneg(hw) && + !e1000_read_phy_reg(hw, PHY_CTRL, &phy_ctrl)) { + phy_ctrl |= (MII_CR_AUTO_NEG_EN | + MII_CR_RESTART_AUTO_NEG); + e1000_write_phy_reg(hw, PHY_CTRL, phy_ctrl); + } + } + /* Restart process after E1000_SMARTSPEED_MAX iterations */ + if (adapter->smartspeed++ == E1000_SMARTSPEED_MAX) + adapter->smartspeed = 0; +} + +/** + * e1000_ioctl - + * @netdev: + * @ifreq: + * @cmd: + **/ + +static int e1000_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) +{ + switch (cmd) { + case SIOCGMIIPHY: + case SIOCGMIIREG: + case SIOCSMIIREG: + return e1000_mii_ioctl(netdev, ifr, cmd); + default: + return -EOPNOTSUPP; + } +} + +/** + * e1000_mii_ioctl - + * @netdev: + * @ifreq: + * @cmd: + **/ + +static int e1000_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, + int cmd) +{ + struct e1000_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + struct mii_ioctl_data *data = if_mii(ifr); + int retval; + u16 mii_reg; + u16 spddplx; + unsigned long flags; + + if (hw->media_type != e1000_media_type_copper) + return -EOPNOTSUPP; + + switch (cmd) { + case SIOCGMIIPHY: + data->phy_id = hw->phy_addr; + break; + case SIOCGMIIREG: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + spin_lock_irqsave(&adapter->stats_lock, flags); + if (e1000_read_phy_reg(hw, data->reg_num & 0x1F, + &data->val_out)) { + spin_unlock_irqrestore(&adapter->stats_lock, flags); + return -EIO; + } + spin_unlock_irqrestore(&adapter->stats_lock, flags); + break; + case SIOCSMIIREG: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (data->reg_num & ~(0x1F)) + return -EFAULT; + mii_reg = data->val_in; + spin_lock_irqsave(&adapter->stats_lock, flags); + if (e1000_write_phy_reg(hw, data->reg_num, + mii_reg)) { + spin_unlock_irqrestore(&adapter->stats_lock, flags); + return -EIO; + } + spin_unlock_irqrestore(&adapter->stats_lock, flags); + if (hw->media_type == e1000_media_type_copper) { + switch (data->reg_num) { + case PHY_CTRL: + if (mii_reg & MII_CR_POWER_DOWN) + break; + if (mii_reg & MII_CR_AUTO_NEG_EN) { + hw->autoneg = 1; + hw->autoneg_advertised = 0x2F; + } else { + if (mii_reg & 0x40) + spddplx = SPEED_1000; + else if (mii_reg & 0x2000) + spddplx = SPEED_100; + else + spddplx = SPEED_10; + spddplx += (mii_reg & 0x100) + ? DUPLEX_FULL : + DUPLEX_HALF; + retval = e1000_set_spd_dplx(adapter, + spddplx); + if (retval) + return retval; + } + if (netif_running(adapter->netdev)) + e1000_reinit_locked(adapter); + else + e1000_reset(adapter); + break; + case M88E1000_PHY_SPEC_CTRL: + case M88E1000_EXT_PHY_SPEC_CTRL: + if (e1000_phy_reset(hw)) + return -EIO; + break; + } + } else { + switch (data->reg_num) { + case PHY_CTRL: + if (mii_reg & MII_CR_POWER_DOWN) + break; + if (netif_running(adapter->netdev)) + e1000_reinit_locked(adapter); + else + e1000_reset(adapter); + break; + } + } + break; + default: + return -EOPNOTSUPP; + } + return E1000_SUCCESS; +} + +void e1000_pci_set_mwi(struct e1000_hw *hw) +{ + struct e1000_adapter *adapter = hw->back; + int ret_val = pci_set_mwi(adapter->pdev); + + if (ret_val) + DPRINTK(PROBE, ERR, "Error in setting MWI\n"); +} + +void e1000_pci_clear_mwi(struct e1000_hw *hw) +{ + struct e1000_adapter *adapter = hw->back; + + pci_clear_mwi(adapter->pdev); +} + +int e1000_pcix_get_mmrbc(struct e1000_hw *hw) +{ + struct e1000_adapter *adapter = hw->back; + return pcix_get_mmrbc(adapter->pdev); +} + +void e1000_pcix_set_mmrbc(struct e1000_hw *hw, int mmrbc) +{ + struct e1000_adapter *adapter = hw->back; + pcix_set_mmrbc(adapter->pdev, mmrbc); +} + +s32 e1000_read_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value) +{ + struct e1000_adapter *adapter = hw->back; + u16 cap_offset; + + cap_offset = pci_find_capability(adapter->pdev, PCI_CAP_ID_EXP); + if (!cap_offset) + return -E1000_ERR_CONFIG; + + pci_read_config_word(adapter->pdev, cap_offset + reg, value); + + return E1000_SUCCESS; +} + +void e1000_io_write(struct e1000_hw *hw, unsigned long port, u32 value) +{ + outl(value, port); +} + +static void e1000_vlan_rx_register(struct net_device *netdev, + struct vlan_group *grp) +{ + struct e1000_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + u32 ctrl, rctl; + + if (!test_bit(__E1000_DOWN, &adapter->flags)) + e1000_irq_disable(adapter); + adapter->vlgrp = grp; + + if (grp) { + /* enable VLAN tag insert/strip */ + ctrl = er32(CTRL); + ctrl |= E1000_CTRL_VME; + ew32(CTRL, ctrl); + + if (adapter->hw.mac_type != e1000_ich8lan) { + /* enable VLAN receive filtering */ + rctl = er32(RCTL); + rctl &= ~E1000_RCTL_CFIEN; + ew32(RCTL, rctl); + e1000_update_mng_vlan(adapter); + } + } else { + /* disable VLAN tag insert/strip */ + ctrl = er32(CTRL); + ctrl &= ~E1000_CTRL_VME; + ew32(CTRL, ctrl); + + if (adapter->hw.mac_type != e1000_ich8lan) { + if (adapter->mng_vlan_id != + (u16)E1000_MNG_VLAN_NONE) { + e1000_vlan_rx_kill_vid(netdev, + adapter->mng_vlan_id); + adapter->mng_vlan_id = E1000_MNG_VLAN_NONE; + } + } + } + + if (!test_bit(__E1000_DOWN, &adapter->flags)) + e1000_irq_enable(adapter); +} + +static void e1000_vlan_rx_add_vid(struct net_device *netdev, u16 vid) +{ + struct e1000_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + u32 vfta, index; + + if ((hw->mng_cookie.status & + E1000_MNG_DHCP_COOKIE_STATUS_VLAN_SUPPORT) && + (vid == adapter->mng_vlan_id)) + return; + /* add VID to filter table */ + index = (vid >> 5) & 0x7F; + vfta = E1000_READ_REG_ARRAY(hw, VFTA, index); + vfta |= (1 << (vid & 0x1F)); + e1000_write_vfta(hw, index, vfta); +} + +static void e1000_vlan_rx_kill_vid(struct net_device *netdev, u16 vid) +{ + struct e1000_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + u32 vfta, index; + + if (!test_bit(__E1000_DOWN, &adapter->flags)) + e1000_irq_disable(adapter); + vlan_group_set_device(adapter->vlgrp, vid, NULL); + if (!test_bit(__E1000_DOWN, &adapter->flags)) + e1000_irq_enable(adapter); + + if ((hw->mng_cookie.status & + E1000_MNG_DHCP_COOKIE_STATUS_VLAN_SUPPORT) && + (vid == adapter->mng_vlan_id)) { + /* release control to f/w */ + e1000_release_hw_control(adapter); + return; + } + + /* remove VID from filter table */ + index = (vid >> 5) & 0x7F; + vfta = E1000_READ_REG_ARRAY(hw, VFTA, index); + vfta &= ~(1 << (vid & 0x1F)); + e1000_write_vfta(hw, index, vfta); +} + +static void e1000_restore_vlan(struct e1000_adapter *adapter) +{ + e1000_vlan_rx_register(adapter->netdev, adapter->vlgrp); + + if (adapter->vlgrp) { + u16 vid; + for (vid = 0; vid < VLAN_GROUP_ARRAY_LEN; vid++) { + if (!vlan_group_get_device(adapter->vlgrp, vid)) + continue; + e1000_vlan_rx_add_vid(adapter->netdev, vid); + } + } +} + +int e1000_set_spd_dplx(struct e1000_adapter *adapter, u16 spddplx) +{ + struct e1000_hw *hw = &adapter->hw; + + hw->autoneg = 0; + + /* Fiber NICs only allow 1000 gbps Full duplex */ + if ((hw->media_type == e1000_media_type_fiber) && + spddplx != (SPEED_1000 + DUPLEX_FULL)) { + DPRINTK(PROBE, ERR, "Unsupported Speed/Duplex configuration\n"); + return -EINVAL; + } + + switch (spddplx) { + case SPEED_10 + DUPLEX_HALF: + hw->forced_speed_duplex = e1000_10_half; + break; + case SPEED_10 + DUPLEX_FULL: + hw->forced_speed_duplex = e1000_10_full; + break; + case SPEED_100 + DUPLEX_HALF: + hw->forced_speed_duplex = e1000_100_half; + break; + case SPEED_100 + DUPLEX_FULL: + hw->forced_speed_duplex = e1000_100_full; + break; + case SPEED_1000 + DUPLEX_FULL: + hw->autoneg = 1; + hw->autoneg_advertised = ADVERTISE_1000_FULL; + break; + case SPEED_1000 + DUPLEX_HALF: /* not supported */ + default: + DPRINTK(PROBE, ERR, "Unsupported Speed/Duplex configuration\n"); + return -EINVAL; + } + return 0; +} + +static int e1000_suspend(struct pci_dev *pdev, pm_message_t state) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct e1000_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + u32 ctrl, ctrl_ext, rctl, status; + u32 wufc = adapter->wol; +#ifdef CONFIG_PM + int retval = 0; +#endif + + netif_device_detach(netdev); + + if (netif_running(netdev)) { + WARN_ON(test_bit(__E1000_RESETTING, &adapter->flags)); + e1000_down(adapter); + } + +#ifdef CONFIG_PM + retval = pci_save_state(pdev); + if (retval) + return retval; +#endif + + status = er32(STATUS); + if (status & E1000_STATUS_LU) + wufc &= ~E1000_WUFC_LNKC; + + if (wufc) { + e1000_setup_rctl(adapter); + e1000_set_rx_mode(netdev); + + /* turn on all-multi mode if wake on multicast is enabled */ + if (wufc & E1000_WUFC_MC) { + rctl = er32(RCTL); + rctl |= E1000_RCTL_MPE; + ew32(RCTL, rctl); + } + + if (hw->mac_type >= e1000_82540) { + ctrl = er32(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 | + E1000_CTRL_EN_PHY_PWR_MGMT; + ew32(CTRL, ctrl); + } + + if (hw->media_type == e1000_media_type_fiber || + hw->media_type == e1000_media_type_internal_serdes) { + /* keep the laser running in D3 */ + ctrl_ext = er32(CTRL_EXT); + ctrl_ext |= E1000_CTRL_EXT_SDP7_DATA; + ew32(CTRL_EXT, ctrl_ext); + } + + /* Allow time for pending master requests to run */ + e1000_disable_pciex_master(hw); + + ew32(WUC, E1000_WUC_PME_EN); + ew32(WUFC, wufc); + pci_enable_wake(pdev, PCI_D3hot, 1); + pci_enable_wake(pdev, PCI_D3cold, 1); + } else { + ew32(WUC, 0); + ew32(WUFC, 0); + pci_enable_wake(pdev, PCI_D3hot, 0); + pci_enable_wake(pdev, PCI_D3cold, 0); + } + + e1000_release_manageability(adapter); + + /* make sure adapter isn't asleep if manageability is enabled */ + if (adapter->en_mng_pt) { + pci_enable_wake(pdev, PCI_D3hot, 1); + pci_enable_wake(pdev, PCI_D3cold, 1); + } + + if (hw->phy_type == e1000_phy_igp_3) + e1000_phy_powerdown_workaround(hw); + + if (netif_running(netdev)) + e1000_free_irq(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. */ + e1000_release_hw_control(adapter); + + pci_disable_device(pdev); + + pci_set_power_state(pdev, pci_choose_state(pdev, state)); + + return 0; +} + +#ifdef CONFIG_PM +static int e1000_resume(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct e1000_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + u32 err; + + pci_set_power_state(pdev, PCI_D0); + pci_restore_state(pdev); + + if (adapter->need_ioport) + err = pci_enable_device(pdev); + else + err = pci_enable_device_mem(pdev); + if (err) { + printk(KERN_ERR "e1000: 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 (netif_running(netdev)) { + err = e1000_request_irq(adapter); + if (err) + return err; + } + + e1000_power_up_phy(adapter); + e1000_reset(adapter); + ew32(WUS, ~0); + + e1000_init_manageability(adapter); + + if (netif_running(netdev)) + e1000_up(adapter); + + netif_device_attach(netdev); + + /* If the controller is 82573 and f/w is AMT, do not set + * DRV_LOAD until the interface is up. For all other cases, + * let the f/w know that the h/w is now under the control + * of the driver. */ + if (hw->mac_type != e1000_82573 || + !e1000_check_mng_mode(hw)) + e1000_get_hw_control(adapter); + + return 0; +} +#endif + +static void e1000_shutdown(struct pci_dev *pdev) +{ + e1000_suspend(pdev, PMSG_SUSPEND); +} + +#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 e1000_netpoll(struct net_device *netdev) +{ + struct e1000_adapter *adapter = netdev_priv(netdev); + + disable_irq(adapter->pdev->irq); + e1000_intr(adapter->pdev->irq, netdev); + enable_irq(adapter->pdev->irq); +} +#endif + +/** + * e1000_io_error_detected - called when PCI error is detected + * @pdev: Pointer to PCI device + * @state: The current pci conneection state + * + * This function is called after a PCI bus error affecting + * this device has been detected. + */ +static pci_ers_result_t e1000_io_error_detected(struct pci_dev *pdev, + pci_channel_state_t state) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct e1000_adapter *adapter = netdev->priv; + + netif_device_detach(netdev); + + if (state == pci_channel_io_perm_failure) + return PCI_ERS_RESULT_DISCONNECT; + + if (netif_running(netdev)) + e1000_down(adapter); + pci_disable_device(pdev); + + /* Request a slot slot reset. */ + return PCI_ERS_RESULT_NEED_RESET; +} + +/** + * e1000_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 e1000_resume routine. + */ +static pci_ers_result_t e1000_io_slot_reset(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct e1000_adapter *adapter = netdev->priv; + struct e1000_hw *hw = &adapter->hw; + int err; + + if (adapter->need_ioport) + err = pci_enable_device(pdev); + else + err = pci_enable_device_mem(pdev); + if (err) { + printk(KERN_ERR "e1000: Cannot re-enable PCI device after reset.\n"); + return PCI_ERS_RESULT_DISCONNECT; + } + pci_set_master(pdev); + + pci_enable_wake(pdev, PCI_D3hot, 0); + pci_enable_wake(pdev, PCI_D3cold, 0); + + e1000_reset(adapter); + ew32(WUS, ~0); + + return PCI_ERS_RESULT_RECOVERED; +} + +/** + * e1000_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 e1000_resume routine. + */ +static void e1000_io_resume(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct e1000_adapter *adapter = netdev->priv; + struct e1000_hw *hw = &adapter->hw; + + e1000_init_manageability(adapter); + + if (netif_running(netdev)) { + if (e1000_up(adapter)) { + printk("e1000: can't bring device back up after reset\n"); + return; + } + } + + netif_device_attach(netdev); + + /* If the controller is 82573 and f/w is AMT, do not set + * DRV_LOAD until the interface is up. For all other cases, + * let the f/w know that the h/w is now under the control + * of the driver. */ + if (hw->mac_type != e1000_82573 || + !e1000_check_mng_mode(hw)) + e1000_get_hw_control(adapter); + +} + +/* e1000_main.c */