--- zzzz-none-000/linux-3.10.107/drivers/net/ethernet/intel/e1000e/netdev.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/drivers/net/ethernet/intel/e1000e/netdev.c 2021-02-04 17:41:59.000000000 +0000 @@ -1,30 +1,23 @@ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - 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 - -*******************************************************************************/ +/* Intel PRO/1000 Linux driver + * Copyright(c) 1999 - 2015 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. + * + * 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 + */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -55,7 +48,7 @@ #define DRV_EXTRAVERSION "-k" -#define DRV_VERSION "2.3.2" DRV_EXTRAVERSION +#define DRV_VERSION "3.2.6" DRV_EXTRAVERSION char e1000e_driver_name[] = "e1000e"; const char e1000e_driver_version[] = DRV_VERSION; @@ -64,8 +57,6 @@ module_param(debug, int, 0); MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); -static void e1000e_disable_aspm(struct pci_dev *pdev, u16 state); - static const struct e1000_info *e1000_info_tbl[] = { [board_82571] = &e1000_82571_info, [board_82572] = &e1000_82572_info, @@ -79,6 +70,7 @@ [board_pchlan] = &e1000_pch_info, [board_pch2lan] = &e1000_pch2_info, [board_pch_lpt] = &e1000_pch_lpt_info, + [board_pch_spt] = &e1000_pch_spt_info, }; struct e1000_reg_info { @@ -133,6 +125,36 @@ }; /** + * __ew32_prepare - prepare to write to MAC CSR register on certain parts + * @hw: pointer to the HW structure + * + * When updating the MAC CSR registers, the Manageability Engine (ME) could + * be accessing the registers at the same time. Normally, this is handled in + * h/w by an arbiter but on some parts there is a bug that acknowledges Host + * accesses later than it should which could result in the register to have + * an incorrect value. Workaround this by checking the FWSM register which + * has bit 24 set while ME is accessing MAC CSR registers, wait if it is set + * and try again a number of times. + **/ +s32 __ew32_prepare(struct e1000_hw *hw) +{ + s32 i = E1000_ICH_FWSM_PCIM2PCI_COUNT; + + while ((er32(FWSM) & E1000_ICH_FWSM_PCIM2PCI) && --i) + udelay(50); + + return i; +} + +void __ew32(struct e1000_hw *hw, unsigned long reg, u32 val) +{ + if (hw->adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA) + __ew32_prepare(hw); + + writel(val, hw->hw_addr + reg); +} + +/** * e1000_regdump - register printout routine * @hw: pointer to the HW structure * @reginfo: pointer to the register info table @@ -608,6 +630,7 @@ if (unlikely(!ret_val && (i != readl(rx_ring->tail)))) { u32 rctl = er32(RCTL); + ew32(RCTL, rctl & ~E1000_RCTL_EN); e_err("ME firmware caused invalid RDT - resetting\n"); schedule_work(&adapter->reset_task); @@ -624,6 +647,7 @@ if (unlikely(!ret_val && (i != readl(tx_ring->tail)))) { u32 tctl = er32(TCTL); + ew32(TCTL, tctl & ~E1000_TCTL_EN); e_err("ME firmware caused invalid TDT - resetting\n"); schedule_work(&adapter->reset_task); @@ -887,7 +911,7 @@ struct sk_buff *skb) { if (netdev->features & NETIF_F_RXHASH) - skb->rxhash = le32_to_cpu(rss); + skb_set_hash(skb, le32_to_cpu(rss), PKT_HASH_TYPE_L3); } /** @@ -923,7 +947,7 @@ if (*work_done >= work_to_do) break; (*work_done)++; - rmb(); /* read descriptor and rx_buffer_info after status DD */ + dma_rmb(); /* read descriptor and rx_buffer_info after status DD */ skb = buffer_info->skb; buffer_info->skb = NULL; @@ -993,7 +1017,7 @@ */ if (length < copybreak) { struct sk_buff *new_skb = - netdev_alloc_skb_ip_align(netdev, length); + napi_alloc_skb(&adapter->napi, length); if (new_skb) { skb_copy_to_linear_data_offset(new_skb, -NET_IP_ALIGN, @@ -1099,8 +1123,14 @@ adapter->tx_hang_recheck = true; return; } - /* Real hang detected */ adapter->tx_hang_recheck = false; + + if (er32(TDH(0)) == er32(TDT(0))) { + e_dbg("false hang detected, ignoring\n"); + return; + } + + /* Real hang detected */ netif_stop_queue(netdev); e1e_rphy(hw, MII_BMSR, &phy_status); @@ -1130,6 +1160,8 @@ eop, jiffies, eop_desc->upper.fields.status, er32(STATUS), phy_status, phy_1000t_status, phy_ext_status, pci_status); + e1000e_dump(adapter); + /* Suggest workaround for known h/w issue */ if ((hw->mac.type == e1000_pchlan) && (er32(CTRL) & E1000_CTRL_TFCE)) e_err("Try turning off Tx pause (flow control) via ethtool\n"); @@ -1149,9 +1181,6 @@ tx_hwtstamp_work); struct e1000_hw *hw = &adapter->hw; - if (!adapter->tx_hwtstamp_skb) - return; - if (er32(TSYNCTXCTL) & E1000_TSYNCTXCTL_VALID) { struct skb_shared_hwtstamps shhwtstamps; u64 txstmp; @@ -1164,6 +1193,12 @@ skb_tstamp_tx(adapter->tx_hwtstamp_skb, &shhwtstamps); dev_kfree_skb_any(adapter->tx_hwtstamp_skb); adapter->tx_hwtstamp_skb = NULL; + } else if (time_after(jiffies, adapter->tx_hwtstamp_start + + adapter->tx_timeout_factor * HZ)) { + dev_kfree_skb_any(adapter->tx_hwtstamp_skb); + adapter->tx_hwtstamp_skb = NULL; + adapter->tx_hwtstamp_timeouts++; + e_warn("clearing Tx timestamp hang\n"); } else { /* reschedule to check later */ schedule_work(&adapter->tx_hwtstamp_work); @@ -1196,7 +1231,8 @@ while ((eop_desc->upper.data & cpu_to_le32(E1000_TXD_STAT_DD)) && (count < tx_ring->count)) { bool cleaned = false; - rmb(); /* read buffer_info after eop_desc */ + + dma_rmb(); /* read buffer_info after eop_desc */ for (; !cleaned; count++) { tx_desc = E1000_TX_DESC(*tx_ring, i); buffer_info = &tx_ring->buffer_info[i]; @@ -1296,7 +1332,7 @@ break; (*work_done)++; skb = buffer_info->skb; - rmb(); /* read descriptor and rx_buffer_info after status DD */ + dma_rmb(); /* read descriptor and rx_buffer_info after status DD */ /* in the packet split case this is header only */ prefetch(skb->data - NET_IP_ALIGN); @@ -1385,7 +1421,7 @@ skb_put(skb, l1); goto copydone; - } /* if */ + } /* if */ } for (j = 0; j < PS_PAGE_BUFFERS; j++) { @@ -1500,7 +1536,7 @@ if (*work_done >= work_to_do) break; (*work_done)++; - rmb(); /* read descriptor and rx_buffer_info after status DD */ + dma_rmb(); /* read descriptor and rx_buffer_info after status DD */ skb = buffer_info->skb; buffer_info->skb = NULL; @@ -1701,12 +1737,6 @@ rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; adapter->flags2 &= ~FLAG2_IS_DISCARDING; - - writel(0, rx_ring->head); - if (rx_ring->adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA) - e1000e_update_rdt_wa(rx_ring, 0); - else - writel(0, rx_ring->tail); } static void e1000e_downshift_workaround(struct work_struct *work) @@ -1751,6 +1781,7 @@ adapter->flags & FLAG_RX_NEEDS_RESTART) { /* disable receives */ u32 rctl = er32(RCTL); + ew32(RCTL, rctl & ~E1000_RCTL_EN); adapter->flags |= FLAG_RESTART_NOW; } @@ -1760,7 +1791,8 @@ } /* Reset on uncorrectable ECC error */ - if ((icr & E1000_ICR_ECCER) && (hw->mac.type == e1000_pch_lpt)) { + if ((icr & E1000_ICR_ECCER) && ((hw->mac.type == e1000_pch_lpt) || + (hw->mac.type == e1000_pch_spt))) { u32 pbeccsts = er32(PBECCSTS); adapter->corr_errors += @@ -1800,7 +1832,7 @@ u32 rctl, icr = er32(ICR); if (!icr || test_bit(__E1000_DOWN, &adapter->state)) - return IRQ_NONE; /* Not our interrupt */ + 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 @@ -1840,7 +1872,8 @@ } /* Reset on uncorrectable ECC error */ - if ((icr & E1000_ICR_ECCER) && (hw->mac.type == e1000_pch_lpt)) { + if ((icr & E1000_ICR_ECCER) && ((hw->mac.type == e1000_pch_lpt) || + (hw->mac.type == e1000_pch_spt))) { u32 pbeccsts = er32(PBECCSTS); adapter->corr_errors += @@ -1926,8 +1959,10 @@ * previous interrupt. */ if (rx_ring->set_itr) { - writel(1000000000 / (rx_ring->itr_val * 256), - rx_ring->itr_register); + u32 itr = rx_ring->itr_val ? + 1000000000 / (rx_ring->itr_val * 256) : 0; + + writel(itr, rx_ring->itr_register); rx_ring->set_itr = 0; } @@ -1958,6 +1993,7 @@ /* Workaround issue with spurious interrupts on 82574 in MSI-X mode */ if (hw->mac.type == e1000_82574) { u32 rfctl = er32(RFCTL); + rfctl |= E1000_RFCTL_ACK_DIS; ew32(RFCTL, rfctl); } @@ -2040,13 +2076,16 @@ msix_entry), GFP_KERNEL); if (adapter->msix_entries) { + struct e1000_adapter *a = adapter; + for (i = 0; i < adapter->num_vectors; i++) adapter->msix_entries[i].entry = i; - err = pci_enable_msix(adapter->pdev, - adapter->msix_entries, - adapter->num_vectors); - if (err == 0) + err = pci_enable_msix_range(a->pdev, + a->msix_entries, + a->num_vectors, + a->num_vectors); + if (err > 0) return; } /* MSI-X failed, so fall through and try MSI */ @@ -2199,6 +2238,7 @@ if (adapter->msix_entries) { int i; + for (i = 0; i < adapter->num_vectors; i++) synchronize_irq(adapter->msix_entries[i].vector); } else { @@ -2216,7 +2256,8 @@ if (adapter->msix_entries) { ew32(EIAC_82574, adapter->eiac_mask & E1000_EIAC_MASK_82574); ew32(IMS, adapter->eiac_mask | E1000_IMS_OTHER | E1000_IMS_LSC); - } else if (hw->mac.type == e1000_pch_lpt) { + } else if ((hw->mac.type == e1000_pch_lpt) || + (hw->mac.type == e1000_pch_spt)) { ew32(IMS, IMS_ENABLE_MASK | E1000_IMS_ECCER); } else { ew32(IMS, IMS_ENABLE_MASK); @@ -2402,12 +2443,6 @@ tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; - - writel(0, tx_ring->head); - if (tx_ring->adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA) - e1000e_update_tdt_wa(tx_ring, 0); - else - writel(0, tx_ring->tail); } /** @@ -2487,7 +2522,7 @@ else if ((packets < 5) && (bytes > 512)) retval = low_latency; break; - case low_latency: /* 50 usec aka 20000 ints/s */ + case low_latency: /* 50 usec aka 20000 ints/s */ if (bytes > 10000) { /* this if handles the TSO accounting */ if (bytes / packets > 8000) @@ -2502,7 +2537,7 @@ retval = lowest_latency; } break; - case bulk_latency: /* 250 usec aka 4000 ints/s */ + case bulk_latency: /* 250 usec aka 4000 ints/s */ if (bytes > 25000) { if (packets > 35) retval = low_latency; @@ -2554,7 +2589,7 @@ new_itr = 70000; break; case low_latency: - new_itr = 20000; /* aka hwitr = ~200 */ + new_itr = 20000; /* aka hwitr = ~200 */ break; case bulk_latency: new_itr = 4000; @@ -2660,7 +2695,7 @@ if (work_done < weight) { if (adapter->itr_setting & 3) e1000_set_itr(adapter); - napi_complete(napi); + napi_complete_done(napi, work_done); if (!test_bit(__E1000_DOWN, &adapter->state)) { if (adapter->msix_entries) ew32(IMS, adapter->rx_ring->ims_val); @@ -2673,7 +2708,7 @@ } static int e1000_vlan_rx_add_vid(struct net_device *netdev, - __be16 proto, u16 vid) + __always_unused __be16 proto, u16 vid) { struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; @@ -2699,7 +2734,7 @@ } static int e1000_vlan_rx_kill_vid(struct net_device *netdev, - __be16 proto, u16 vid) + __always_unused __be16 proto, u16 vid) { struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; @@ -2896,7 +2931,7 @@ struct e1000_hw *hw = &adapter->hw; struct e1000_ring *tx_ring = adapter->tx_ring; u64 tdba; - u32 tdlen, tarc; + u32 tdlen, tctl, tarc; /* Setup the HW Tx Head and Tail descriptor pointers */ tdba = tx_ring->dma; @@ -2909,6 +2944,12 @@ tx_ring->head = adapter->hw.hw_addr + E1000_TDH(0); tx_ring->tail = adapter->hw.hw_addr + E1000_TDT(0); + writel(0, tx_ring->head); + if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA) + e1000e_update_tdt_wa(tx_ring, 0); + else + writel(0, tx_ring->tail); + /* Set the Tx Interrupt Delay register */ ew32(TIDV, adapter->tx_int_delay); /* Tx irq moderation */ @@ -2916,6 +2957,7 @@ if (adapter->flags2 & FLAG2_DMA_BURST) { u32 txdctl = er32(TXDCTL(0)); + txdctl &= ~(E1000_TXDCTL_PTHRESH | E1000_TXDCTL_HTHRESH | E1000_TXDCTL_WTHRESH); /* set up some performance related parameters to encourage the @@ -2933,6 +2975,12 @@ /* erratum work around: set txdctl the same for both queues */ ew32(TXDCTL(1), er32(TXDCTL(0))); + /* 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 (adapter->flags & FLAG_TARC_SPEED_MODE_BIT) { tarc = er32(TARC(0)); /* set the speed mode bit, we'll clear it if we're not at @@ -2963,7 +3011,22 @@ /* enable Report Status bit */ adapter->txd_cmd |= E1000_TXD_CMD_RS; + ew32(TCTL, tctl); + hw->mac.ops.config_collision_dist(hw); + + /* SPT Si errata workaround to avoid data corruption */ + if (hw->mac.type == e1000_pch_spt) { + u32 reg_val; + + reg_val = er32(IOSFPC); + reg_val |= E1000_RCTL_RDMTS_HEX; + ew32(IOSFPC, reg_val); + + reg_val = er32(TARC(0)); + reg_val |= E1000_TARC0_CB_MULTIQ_3_REQ; + ew32(TARC(0), reg_val); + } } /** @@ -2978,7 +3041,10 @@ u32 rctl, rfctl; u32 pages = 0; - /* Workaround Si errata on PCHx - configure jumbo frame flow */ + /* Workaround Si errata on PCHx - configure jumbo frame flow. + * If jumbo frames not set, program related MAC/PHY registers + * to h/w defaults + */ if (hw->mac.type >= e1000_pch2lan) { s32 ret_val; @@ -2988,7 +3054,7 @@ ret_val = e1000_lv_jumbo_workaround_ich8lan(hw, false); if (ret_val) - e_dbg("failed to enable jumbo frame workaround mode\n"); + e_dbg("failed to enable|disable jumbo frame workaround mode\n"); } /* Program MC offset vector base */ @@ -3104,13 +3170,13 @@ /* UPE and MPE will be handled by normal PROMISC logic * in e1000e_set_rx_mode */ - rctl |= (E1000_RCTL_SBP | /* Receive bad packets */ - E1000_RCTL_BAM | /* RX All Bcast Pkts */ - E1000_RCTL_PMCF); /* RX All MAC Ctrl Pkts */ - - rctl &= ~(E1000_RCTL_VFE | /* Disable VLAN filter */ - E1000_RCTL_DPF | /* Allow filtered pause */ - E1000_RCTL_CFIEN); /* Dis VLAN CFIEN Filter */ + rctl |= (E1000_RCTL_SBP | /* Receive bad packets */ + E1000_RCTL_BAM | /* RX All Bcast Pkts */ + E1000_RCTL_PMCF); /* RX All MAC Ctrl Pkts */ + + rctl &= ~(E1000_RCTL_VFE | /* Disable VLAN filter */ + E1000_RCTL_DPF | /* Allow filtered pause */ + E1000_RCTL_CFIEN); /* Dis VLAN CFIEN Filter */ /* Do not mess with E1000_CTRL_VME, it affects transmit as well, * and that breaks VLANs. */ @@ -3205,6 +3271,12 @@ rx_ring->head = adapter->hw.hw_addr + E1000_RDH(0); rx_ring->tail = adapter->hw.hw_addr + E1000_RDT(0); + writel(0, rx_ring->head); + if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA) + e1000e_update_rdt_wa(rx_ring, 0); + else + writel(0, rx_ring->tail); + /* Enable Receive Checksum Offload for TCP and UDP */ rxcsum = er32(RXCSUM); if (adapter->netdev->features & NETIF_F_RXCSUM) @@ -3223,12 +3295,13 @@ if (adapter->flags & FLAG_IS_ICH) { u32 rxdctl = er32(RXDCTL(0)); + ew32(RXDCTL(0), rxdctl | 0x3); } - pm_qos_update_request(&adapter->netdev->pm_qos_req, lat); + pm_qos_update_request(&adapter->pm_qos_req, lat); } else { - pm_qos_update_request(&adapter->netdev->pm_qos_req, + pm_qos_update_request(&adapter->pm_qos_req, PM_QOS_DEFAULT_VALUE); } @@ -3287,9 +3360,11 @@ { struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; - unsigned int rar_entries = hw->mac.rar_entry_count; + unsigned int rar_entries; int count = 0; + rar_entries = hw->mac.ops.rar_get_count(hw); + /* save a rar entry for our hardware address */ rar_entries--; @@ -3308,9 +3383,13 @@ * combining */ netdev_for_each_uc_addr(ha, netdev) { + int rval; + if (!rar_entries) break; - hw->mac.ops.rar_set(hw, ha->addr, rar_entries--); + rval = hw->mac.ops.rar_set(hw, ha->addr, rar_entries--); + if (rval < 0) + return -ENOMEM; count++; } } @@ -3340,6 +3419,9 @@ struct e1000_hw *hw = &adapter->hw; u32 rctl; + if (pm_runtime_suspended(netdev->dev.parent)) + return; + /* Check for Promiscuous and All Multicast modes */ rctl = er32(RCTL); @@ -3386,15 +3468,12 @@ { struct e1000_hw *hw = &adapter->hw; u32 mrqc, rxcsum; + u32 rss_key[10]; int i; - static const u32 rsskey[10] = { - 0xda565a6d, 0xc20e5b25, 0x3d256741, 0xb08fa343, 0xcb2bcad0, - 0xb4307bae, 0xa32dcb77, 0x0cf23080, 0x3bb7426a, 0xfa01acbe - }; - /* Fill out hash function seed */ + netdev_rss_key_fill(rss_key, sizeof(rss_key)); for (i = 0; i < 10; i++) - ew32(RSSRK(i), rsskey[i]); + ew32(RSSRK(i), rss_key[i]); /* Direct all traffic to queue 0 */ for (i = 0; i < 32; i++) @@ -3430,8 +3509,11 @@ struct e1000_hw *hw = &adapter->hw; u32 incvalue, incperiod, shift; - /* Make sure clock is enabled on I217 before checking the frequency */ - if ((hw->mac.type == e1000_pch_lpt) && + /* Make sure clock is enabled on I217/I218/I219 before checking + * the frequency + */ + if (((hw->mac.type == e1000_pch_lpt) || + (hw->mac.type == e1000_pch_spt)) && !(er32(TSYNCTXCTL) & E1000_TSYNCTXCTL_ENABLED) && !(er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_ENABLED)) { u32 fextnvm7 = er32(FEXTNVM7); @@ -3445,19 +3527,30 @@ switch (hw->mac.type) { case e1000_pch2lan: case e1000_pch_lpt: - /* On I217, the clock frequency is 25MHz or 96MHz as - * indicated by the System Clock Frequency Indication - */ - if ((hw->mac.type != e1000_pch_lpt) || - (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)) { + if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) { /* Stable 96MHz frequency */ incperiod = INCPERIOD_96MHz; incvalue = INCVALUE_96MHz; shift = INCVALUE_SHIFT_96MHz; adapter->cc.shift = shift + INCPERIOD_SHIFT_96MHz; + } else { + /* Stable 25MHz frequency */ + incperiod = INCPERIOD_25MHz; + incvalue = INCVALUE_25MHz; + shift = INCVALUE_SHIFT_25MHz; + adapter->cc.shift = shift; + } + break; + case e1000_pch_spt: + if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) { + /* Stable 24MHz frequency */ + incperiod = INCPERIOD_24MHz; + incvalue = INCVALUE_24MHz; + shift = INCVALUE_SHIFT_24MHz; + adapter->cc.shift = shift; break; } - /* fall-through */ + return -EINVAL; case e1000_82574: case e1000_82583: /* Stable 25MHz frequency */ @@ -3491,10 +3584,10 @@ * specified. Matching the kind of event packet is not supported, with the * exception of "all V2 events regardless of level 2 or 4". **/ -static int e1000e_config_hwtstamp(struct e1000_adapter *adapter) +static int e1000e_config_hwtstamp(struct e1000_adapter *adapter, + struct hwtstamp_config *config) { struct e1000_hw *hw = &adapter->hw; - struct hwtstamp_config *config = &adapter->hwtstamp_config; u32 tsync_tx_ctl = E1000_TSYNCTXCTL_ENABLED; u32 tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED; u32 rxmtrl = 0; @@ -3595,6 +3688,8 @@ return -ERANGE; } + adapter->hwtstamp_config = *config; + /* enable/disable Tx h/w time stamping */ regval = er32(TSYNCTXCTL); regval &= ~E1000_TSYNCTXCTL_ENABLED; @@ -3698,15 +3793,113 @@ */ static void e1000_power_down_phy(struct e1000_adapter *adapter) { - /* WoL is enabled */ - if (adapter->wol) - return; - if (adapter->hw.phy.ops.power_down) adapter->hw.phy.ops.power_down(&adapter->hw); } /** + * e1000_flush_tx_ring - remove all descriptors from the tx_ring + * + * We want to clear all pending descriptors from the TX ring. + * zeroing happens when the HW reads the regs. We assign the ring itself as + * the data of the next descriptor. We don't care about the data we are about + * to reset the HW. + */ +static void e1000_flush_tx_ring(struct e1000_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + struct e1000_ring *tx_ring = adapter->tx_ring; + struct e1000_tx_desc *tx_desc = NULL; + u32 tdt, tctl, txd_lower = E1000_TXD_CMD_IFCS; + u16 size = 512; + + tctl = er32(TCTL); + ew32(TCTL, tctl | E1000_TCTL_EN); + tdt = er32(TDT(0)); + BUG_ON(tdt != tx_ring->next_to_use); + tx_desc = E1000_TX_DESC(*tx_ring, tx_ring->next_to_use); + tx_desc->buffer_addr = tx_ring->dma; + + tx_desc->lower.data = cpu_to_le32(txd_lower | size); + tx_desc->upper.data = 0; + /* flush descriptors to memory before notifying the HW */ + wmb(); + tx_ring->next_to_use++; + if (tx_ring->next_to_use == tx_ring->count) + tx_ring->next_to_use = 0; + ew32(TDT(0), tx_ring->next_to_use); + mmiowb(); + usleep_range(200, 250); +} + +/** + * e1000_flush_rx_ring - remove all descriptors from the rx_ring + * + * Mark all descriptors in the RX ring as consumed and disable the rx ring + */ +static void e1000_flush_rx_ring(struct e1000_adapter *adapter) +{ + u32 rctl, rxdctl; + struct e1000_hw *hw = &adapter->hw; + + rctl = er32(RCTL); + ew32(RCTL, rctl & ~E1000_RCTL_EN); + e1e_flush(); + usleep_range(100, 150); + + rxdctl = er32(RXDCTL(0)); + /* zero the lower 14 bits (prefetch and host thresholds) */ + rxdctl &= 0xffffc000; + + /* update thresholds: prefetch threshold to 31, host threshold to 1 + * and make sure the granularity is "descriptors" and not "cache lines" + */ + rxdctl |= (0x1F | (1 << 8) | E1000_RXDCTL_THRESH_UNIT_DESC); + + ew32(RXDCTL(0), rxdctl); + /* momentarily enable the RX ring for the changes to take effect */ + ew32(RCTL, rctl | E1000_RCTL_EN); + e1e_flush(); + usleep_range(100, 150); + ew32(RCTL, rctl & ~E1000_RCTL_EN); +} + +/** + * e1000_flush_desc_rings - remove all descriptors from the descriptor rings + * + * In i219, the descriptor rings must be emptied before resetting the HW + * or before changing the device state to D3 during runtime (runtime PM). + * + * Failure to do this will cause the HW to enter a unit hang state which can + * only be released by PCI reset on the device + * + */ + +static void e1000_flush_desc_rings(struct e1000_adapter *adapter) +{ + u16 hang_state; + u32 fext_nvm11, tdlen; + struct e1000_hw *hw = &adapter->hw; + + /* First, disable MULR fix in FEXTNVM11 */ + fext_nvm11 = er32(FEXTNVM11); + fext_nvm11 |= E1000_FEXTNVM11_DISABLE_MULR_FIX; + ew32(FEXTNVM11, fext_nvm11); + /* do nothing if we're not in faulty state, or if the queue is empty */ + tdlen = er32(TDLEN(0)); + pci_read_config_word(adapter->pdev, PCICFG_DESC_RING_STATUS, + &hang_state); + if (!(hang_state & FLUSH_DESC_REQUIRED) || !tdlen) + return; + e1000_flush_tx_ring(adapter); + /* recheck, maybe the fault is caused by the rx ring */ + pci_read_config_word(adapter->pdev, PCICFG_DESC_RING_STATUS, + &hang_state); + if (hang_state & FLUSH_DESC_REQUIRED) + e1000_flush_rx_ring(adapter); +} + +/** * e1000e_reset - bring the hardware into a known good state * * This function boots the hardware and enables some settings that @@ -3726,7 +3919,7 @@ /* reset Packet Buffer Allocation to default */ ew32(PBA, pba); - if (adapter->max_frame_size > ETH_FRAME_LEN + ETH_FCS_LEN) { + if (adapter->max_frame_size > (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN)) { /* To maintain wire speed transmits, the Tx FIFO should be * large enough to accommodate two full transmit packets, * rounded up to the next 1KB and expressed in KB. Likewise, @@ -3799,7 +3992,7 @@ hwm = min(((pba << 10) * 9 / 10), ((pba << 10) - adapter->max_frame_size)); - fc->high_water = hwm & E1000_FCRTH_RTH; /* 8-byte granularity */ + fc->high_water = hwm & E1000_FCRTH_RTH; /* 8-byte granularity */ fc->low_water = fc->high_water - 8; break; case e1000_pchlan: @@ -3808,15 +4001,16 @@ */ if (adapter->netdev->mtu > ETH_DATA_LEN) { fc->high_water = 0x3500; - fc->low_water = 0x1500; + fc->low_water = 0x1500; } else { fc->high_water = 0x5000; - fc->low_water = 0x3000; + fc->low_water = 0x3000; } fc->refresh_time = 0x1000; break; case e1000_pch2lan: case e1000_pch_lpt: + case e1000_pch_spt: fc->refresh_time = 0x0400; if (adapter->netdev->mtu <= ETH_DATA_LEN) { @@ -3826,6 +4020,8 @@ break; } + pba = 14; + ew32(PBA, pba); fc->high_water = ((pba << 10) * 9 / 10) & E1000_FCRTH_RTH; fc->low_water = ((pba << 10) * 8 / 10) & E1000_FCRTL_RTL; break; @@ -3859,6 +4055,8 @@ } } + if (hw->mac.type == e1000_pch_spt) + e1000_flush_desc_rings(adapter); /* Allow time for pending master requests to run */ mac->ops.reset_hw(hw); @@ -3881,7 +4079,7 @@ e1000e_reset_adaptive(hw); /* initialize systim and reset the ns time counter */ - e1000e_config_hwtstamp(adapter); + e1000e_config_hwtstamp(adapter, &adapter->hwtstamp_config); /* Set EEE advertisement as appropriate */ if (adapter->flags2 & FLAG2_HAS_EEE) { @@ -3916,10 +4114,8 @@ } if (!netif_running(adapter->netdev) && - !test_bit(__E1000_TESTING, &adapter->state)) { + !test_bit(__E1000_TESTING, &adapter->state)) e1000_power_down_phy(adapter); - return; - } e1000_get_phy_info(hw); @@ -3934,6 +4130,20 @@ phy_data &= ~IGP02E1000_PM_SPD; e1e_wphy(hw, IGP02E1000_PHY_POWER_MGMT, phy_data); } + if (hw->mac.type == e1000_pch_spt && adapter->int_mode == 0) { + u32 reg; + + /* Fextnvm7 @ 0xe4[2] = 1 */ + reg = er32(FEXTNVM7); + reg |= E1000_FEXTNVM7_SIDE_CLK_UNGATE; + ew32(FEXTNVM7, reg); + /* Fextnvm9 @ 0x5bb4[13:12] = 11 */ + reg = er32(FEXTNVM9); + reg |= E1000_FEXTNVM9_IOSFSB_CLKGATE_DIS | + E1000_FEXTNVM9_IOSFSB_CLKREQ_DIS; + ew32(FEXTNVM9, reg); + } + } int e1000e_up(struct e1000_adapter *adapter) @@ -3986,7 +4196,12 @@ static void e1000e_update_stats(struct e1000_adapter *adapter); -void e1000e_down(struct e1000_adapter *adapter) +/** + * e1000e_down - quiesce the device and optionally reset the hardware + * @adapter: board private structure + * @reset: boolean flag to reset the hardware or not + */ +void e1000e_down(struct e1000_adapter *adapter, bool reset) { struct net_device *netdev = adapter->netdev; struct e1000_hw *hw = &adapter->hw; @@ -3997,6 +4212,8 @@ */ set_bit(__E1000_DOWN, &adapter->state); + netif_carrier_off(netdev); + /* disable receives in the hardware */ rctl = er32(RCTL); if (!(adapter->flags2 & FLAG2_NO_DISABLE_RX)) @@ -4021,25 +4238,29 @@ del_timer_sync(&adapter->watchdog_timer); del_timer_sync(&adapter->phy_info_timer); - netif_carrier_off(netdev); - spin_lock(&adapter->stats64_lock); e1000e_update_stats(adapter); spin_unlock(&adapter->stats64_lock); e1000e_flush_descriptors(adapter); - e1000_clean_tx_ring(adapter->tx_ring); - e1000_clean_rx_ring(adapter->rx_ring); adapter->link_speed = 0; adapter->link_duplex = 0; - if (!pci_channel_offline(adapter->pdev)) - e1000e_reset(adapter); - - /* TODO: for power management, we could drop the link and - * pci_disable_device here. - */ + /* Disable Si errata workaround on PCHx for jumbo frame flow */ + if ((hw->mac.type >= e1000_pch2lan) && + (adapter->netdev->mtu > ETH_DATA_LEN) && + e1000_lv_jumbo_workaround_ich8lan(hw, false)) + e_dbg("failed to disable jumbo frame workaround mode\n"); + + if (!pci_channel_offline(adapter->pdev)) { + if (reset) + e1000e_reset(adapter); + else if (hw->mac.type == e1000_pch_spt) + e1000_flush_desc_rings(adapter); + } + e1000_clean_tx_ring(adapter->tx_ring); + e1000_clean_rx_ring(adapter->rx_ring); } void e1000e_reinit_locked(struct e1000_adapter *adapter) @@ -4047,7 +4268,7 @@ might_sleep(); while (test_and_set_bit(__E1000_RESETTING, &adapter->state)) usleep_range(1000, 2000); - e1000e_down(adapter); + e1000e_down(adapter, true); e1000e_up(adapter); clear_bit(__E1000_RESETTING, &adapter->state); } @@ -4061,12 +4282,55 @@ struct e1000_adapter *adapter = container_of(cc, struct e1000_adapter, cc); struct e1000_hw *hw = &adapter->hw; - cycle_t systim; + u32 systimel_1, systimel_2, systimeh; + cycle_t systim, systim_next; + /* SYSTIMH latching upon SYSTIML read does not work well. + * This means that if SYSTIML overflows after we read it but before + * we read SYSTIMH, the value of SYSTIMH has been incremented and we + * will experience a huge non linear increment in the systime value + * to fix that we test for overflow and if true, we re-read systime. + */ + systimel_1 = er32(SYSTIML); + systimeh = er32(SYSTIMH); + systimel_2 = er32(SYSTIML); + /* Check for overflow. If there was no overflow, use the values */ + if (systimel_1 < systimel_2) { + systim = (cycle_t)systimel_1; + systim |= (cycle_t)systimeh << 32; + } else { + /* There was an overflow, read again SYSTIMH, and use + * systimel_2 + */ + systimeh = er32(SYSTIMH); + systim = (cycle_t)systimel_2; + systim |= (cycle_t)systimeh << 32; + } + + if ((hw->mac.type == e1000_82574) || (hw->mac.type == e1000_82583)) { + u64 incvalue, time_delta, rem, temp; + int i; + + /* errata for 82574/82583 possible bad bits read from SYSTIMH/L + * check to see that the time is incrementing at a reasonable + * rate and is a multiple of incvalue + */ + incvalue = er32(TIMINCA) & E1000_TIMINCA_INCVALUE_MASK; + for (i = 0; i < E1000_MAX_82574_SYSTIM_REREADS; i++) { + /* latch SYSTIMH on read of SYSTIML */ + systim_next = (cycle_t)er32(SYSTIML); + systim_next |= (cycle_t)er32(SYSTIMH) << 32; + + time_delta = systim_next - systim; + temp = time_delta; + rem = do_div(temp, incvalue); - /* latch SYSTIMH on read of SYSTIML */ - systim = (cycle_t)er32(SYSTIML); - systim |= (cycle_t)er32(SYSTIMH) << 32; + systim = systim_next; + if ((time_delta < E1000_82574_SYSTIM_EPSILON) && + (rem == 0)) + break; + } + } return systim; } @@ -4082,9 +4346,9 @@ { struct net_device *netdev = adapter->netdev; - adapter->rx_buffer_len = ETH_FRAME_LEN + VLAN_HLEN + ETH_FCS_LEN; + adapter->rx_buffer_len = VLAN_ETH_FRAME_LEN + ETH_FCS_LEN; adapter->rx_ps_bsize0 = 128; - adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN; + adapter->max_frame_size = netdev->mtu + VLAN_ETH_HLEN + ETH_FCS_LEN; adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN; adapter->tx_ring_count = E1000_DEFAULT_TXD; adapter->rx_ring_count = E1000_DEFAULT_RXD; @@ -4099,7 +4363,7 @@ /* Setup hardware time stamping cyclecounter */ if (adapter->flags & FLAG_HAS_HW_TIMESTAMP) { adapter->cc.read = e1000e_cyclecounter_read; - adapter->cc.mask = CLOCKSOURCE_MASK(64); + adapter->cc.mask = CYCLECOUNTER_MASK(64); adapter->cc.mult = 1; /* cc.shift set in e1000e_get_base_tininca() */ @@ -4289,7 +4553,7 @@ e1000_update_mng_vlan(adapter); /* DMA latency requirement to workaround jumbo issue */ - pm_qos_add_request(&adapter->netdev->pm_qos_req, PM_QOS_CPU_DMA_LATENCY, + pm_qos_add_request(&adapter->pm_qos_req, PM_QOS_CPU_DMA_LATENCY, PM_QOS_DEFAULT_VALUE); /* before we allocate an interrupt, we must be ready to handle it. @@ -4325,7 +4589,6 @@ adapter->tx_hang_recheck = false; netif_start_queue(netdev); - adapter->idle_check = true; hw->mac.get_link_status = true; pm_runtime_put(&pdev->dev); @@ -4338,6 +4601,7 @@ return 0; err_req_irq: + pm_qos_remove_request(&adapter->pm_qos_req); e1000e_release_hw_control(adapter); e1000_power_down_phy(adapter); e1000e_free_rx_resources(adapter->rx_ring); @@ -4375,14 +4639,15 @@ pm_runtime_get_sync(&pdev->dev); if (!test_bit(__E1000_DOWN, &adapter->state)) { - e1000e_down(adapter); + e1000e_down(adapter, true); e1000_free_irq(adapter); + + /* Link status message must follow this format */ + pr_info("%s NIC Link is Down\n", adapter->netdev->name); } napi_disable(&adapter->napi); - e1000_power_down_phy(adapter); - e1000e_free_tx_resources(adapter->tx_ring); e1000e_free_rx_resources(adapter->rx_ring); @@ -4400,7 +4665,7 @@ !test_bit(__E1000_TESTING, &adapter->state)) e1000e_release_hw_control(adapter); - pm_qos_remove_request(&adapter->netdev->pm_qos_req); + pm_qos_remove_request(&adapter->pm_qos_req); pm_runtime_put_sync(&pdev->dev); @@ -4459,11 +4724,16 @@ struct e1000_adapter *adapter = container_of(work, struct e1000_adapter, update_phy_task); + struct e1000_hw *hw = &adapter->hw; if (test_bit(__E1000_DOWN, &adapter->state)) return; - e1000_get_phy_info(&adapter->hw); + e1000_get_phy_info(hw); + + /* Enable EEE on 82579 after link up */ + if (hw->phy.type >= e1000_phy_82579) + e1000_set_eee_pchlan(hw); } /** @@ -4581,7 +4851,7 @@ adapter->stats.crcerrs += er32(CRCERRS); adapter->stats.gprc += er32(GPRC); adapter->stats.gorc += er32(GORCL); - er32(GORCH); /* Clear gorc */ + er32(GORCH); /* Clear gorc */ adapter->stats.bprc += er32(BPRC); adapter->stats.mprc += er32(MPRC); adapter->stats.roc += er32(ROC); @@ -4614,7 +4884,7 @@ adapter->stats.xofftxc += er32(XOFFTXC); adapter->stats.gptc += er32(GPTC); adapter->stats.gotc += er32(GOTCL); - er32(GOTCH); /* Clear gotc */ + er32(GOTCH); /* Clear gotc */ adapter->stats.rnbc += er32(RNBC); adapter->stats.ruc += er32(RUC); @@ -4664,8 +4934,10 @@ adapter->stats.mgpdc += er32(MGTPDC); /* Correctable ECC Errors */ - if (hw->mac.type == e1000_pch_lpt) { + if ((hw->mac.type == e1000_pch_lpt) || + (hw->mac.type == e1000_pch_spt)) { u32 pbeccsts = er32(PBECCSTS); + adapter->corr_errors += pbeccsts & E1000_PBECCSTS_CORR_ERR_CNT_MASK; adapter->uncorr_errors += @@ -4683,11 +4955,11 @@ struct e1000_hw *hw = &adapter->hw; struct e1000_phy_regs *phy = &adapter->phy_regs; - if ((er32(STATUS) & E1000_STATUS_LU) && + if (!pm_runtime_suspended((&adapter->pdev->dev)->parent) && + (er32(STATUS) & E1000_STATUS_LU) && (adapter->hw.phy.media_type == e1000_media_type_copper)) { int ret_val; - pm_runtime_get_sync(&adapter->pdev->dev); ret_val = e1e_rphy(hw, MII_BMCR, &phy->bmcr); ret_val |= e1e_rphy(hw, MII_BMSR, &phy->bmsr); ret_val |= e1e_rphy(hw, MII_ADVERTISE, &phy->advertise); @@ -4698,7 +4970,6 @@ ret_val |= e1e_rphy(hw, MII_ESTATUS, &phy->estatus); if (ret_val) e_warn("Error reading PHY register\n"); - pm_runtime_put_sync(&adapter->pdev->dev); } else { /* Do not read PHY registers if link is not up * Set values to typical power-on defaults @@ -4780,6 +5051,7 @@ (adapter->flags & FLAG_RESTART_NOW)) { struct e1000_hw *hw = &adapter->hw; u32 rctl = er32(RCTL); + ew32(RCTL, rctl | E1000_RCTL_EN); adapter->flags &= ~FLAG_RESTART_NOW; } @@ -4799,6 +5071,7 @@ if (adapter->phy_hang_count > 1) { adapter->phy_hang_count = 0; + e_dbg("PHY appears hung - resetting\n"); schedule_work(&adapter->reset_task); } } @@ -4870,7 +5143,7 @@ */ if ((hw->phy.type == e1000_phy_igp_3 || hw->phy.type == e1000_phy_bm) && - (hw->mac.autoneg == true) && + hw->mac.autoneg && (adapter->link_speed == SPEED_10 || adapter->link_speed == SPEED_100) && (adapter->link_duplex == HALF_DUPLEX)) { @@ -4901,6 +5174,7 @@ if ((adapter->flags & FLAG_TARC_SPEED_MODE_BIT) && !txb2b) { u32 tarc0; + tarc0 = er32(TARC(0)); tarc0 &= ~SPEED_MODE_BIT; ew32(TARC(0), tarc0); @@ -4957,15 +5231,11 @@ mod_timer(&adapter->phy_info_timer, round_jiffies(jiffies + 2 * HZ)); - /* The link is lost so the controller stops DMA. - * If there is queued Tx work that cannot be done - * or if on an 8000ES2LAN which requires a Rx packet - * buffer work-around on link down event, reset the - * controller to flush the Tx/Rx packet buffers. - * (Do the reset outside of interrupt context). + /* 8000ES2LAN requires a Rx packet buffer work-around + * on link down event; reset the controller to flush + * the Rx packet buffer. */ - if ((adapter->flags & FLAG_RX_NEEDS_RESTART) || - (e1000_desc_unused(tx_ring) + 1 < tx_ring->count)) + if (adapter->flags & FLAG_RX_NEEDS_RESTART) adapter->flags |= FLAG_RESTART_NOW; else pm_schedule_suspend(netdev->dev.parent, @@ -4988,6 +5258,15 @@ adapter->gotc_old = adapter->stats.gotc; spin_unlock(&adapter->stats64_lock); + /* If the link is lost the controller stops DMA, but + * if there is queued Tx work it cannot be done. So + * reset the controller to flush the Tx packet buffers. + */ + if (!netif_carrier_ok(netdev) && + (e1000_desc_unused(tx_ring) + 1 < tx_ring->count)) + adapter->flags |= FLAG_RESTART_NOW; + + /* If reset is necessary, do it outside of interrupt context. */ if (adapter->flags & FLAG_RESTART_NOW) { schedule_work(&adapter->reset_task); /* return immediately since reset is imminent */ @@ -5058,7 +5337,8 @@ #define E1000_TX_FLAGS_VLAN_MASK 0xffff0000 #define E1000_TX_FLAGS_VLAN_SHIFT 16 -static int e1000_tso(struct e1000_ring *tx_ring, struct sk_buff *skb) +static int e1000_tso(struct e1000_ring *tx_ring, struct sk_buff *skb, + __be16 protocol) { struct e1000_context_desc *context_desc; struct e1000_buffer *buffer_info; @@ -5066,20 +5346,18 @@ u32 cmd_length = 0; u16 ipcse = 0, mss; u8 ipcss, ipcso, tucss, tucso, hdr_len; + int err; if (!skb_is_gso(skb)) return 0; - if (skb_header_cloned(skb)) { - int err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); - - if (err) - return err; - } + err = skb_cow_head(skb, 0); + if (err < 0) + return err; hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); mss = skb_shinfo(skb)->gso_size; - if (skb->protocol == htons(ETH_P_IP)) { + if (protocol == htons(ETH_P_IP)) { struct iphdr *iph = ip_hdr(skb); iph->tot_len = 0; iph->check = 0; @@ -5106,13 +5384,13 @@ 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->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 = 0; - context_desc->tcp_seg_setup.fields.mss = cpu_to_le16(mss); + 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); @@ -5127,7 +5405,8 @@ return 1; } -static bool e1000_tx_csum(struct e1000_ring *tx_ring, struct sk_buff *skb) +static bool e1000_tx_csum(struct e1000_ring *tx_ring, struct sk_buff *skb, + __be16 protocol) { struct e1000_adapter *adapter = tx_ring->adapter; struct e1000_context_desc *context_desc; @@ -5135,15 +5414,9 @@ unsigned int i; u8 css; u32 cmd_len = E1000_TXD_CMD_DEXT; - __be16 protocol; if (skb->ip_summed != CHECKSUM_PARTIAL) - return 0; - - if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) - protocol = vlan_eth_hdr(skb)->h_vlan_encapsulated_proto; - else - protocol = skb->protocol; + return false; switch (protocol) { case cpu_to_be16(ETH_P_IP): @@ -5183,7 +5456,7 @@ i = 0; tx_ring->next_to_use = i; - return 1; + return true; } static int e1000_tx_map(struct e1000_ring *tx_ring, struct sk_buff *skb, @@ -5347,27 +5620,17 @@ wmb(); tx_ring->next_to_use = i; - - if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA) - e1000e_update_tdt_wa(tx_ring, i); - else - writel(i, tx_ring->tail); - - /* we need this if more than one processor can write to our tail - * at a time, it synchronizes IO on IA64/Altix systems - */ - mmiowb(); } #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; + struct e1000_hw *hw = &adapter->hw; u16 length, offset; - if (vlan_tx_tag_present(skb) && - !((vlan_tx_tag_get(skb) == adapter->hw.mng_cookie.vlan_id) && + if (skb_vlan_tag_present(skb) && + !((skb_vlan_tag_get(skb) == adapter->hw.mng_cookie.vlan_id) && (adapter->hw.mng_cookie.status & E1000_MNG_DHCP_COOKIE_STATUS_VLAN))) return 0; @@ -5442,6 +5705,7 @@ int count = 0; int tso; unsigned int f; + __be16 protocol = vlan_get_protocol(skb); if (test_bit(__E1000_DOWN, &adapter->state)) { dev_kfree_skb_any(skb); @@ -5456,12 +5720,8 @@ /* The minimum packet size with TCTL.PSP set is 17 bytes so * pad skb in order to meet this minimum size requirement */ - if (unlikely(skb->len < 17)) { - if (skb_pad(skb, 17 - skb->len)) - return NETDEV_TX_OK; - skb->len = 17; - skb_set_tail_pointer(skb, 17); - } + if (skb_put_padto(skb, 17)) + return NETDEV_TX_OK; mss = skb_shinfo(skb)->gso_size; if (mss) { @@ -5509,14 +5769,15 @@ if (e1000_maybe_stop_tx(tx_ring, count + 2)) return NETDEV_TX_BUSY; - if (vlan_tx_tag_present(skb)) { + if (skb_vlan_tag_present(skb)) { tx_flags |= E1000_TX_FLAGS_VLAN; - tx_flags |= (vlan_tx_tag_get(skb) << E1000_TX_FLAGS_VLAN_SHIFT); + tx_flags |= (skb_vlan_tag_get(skb) << + E1000_TX_FLAGS_VLAN_SHIFT); } first = tx_ring->next_to_use; - tso = e1000_tso(tx_ring, skb); + tso = e1000_tso(tx_ring, skb, protocol); if (tso < 0) { dev_kfree_skb_any(skb); return NETDEV_TX_OK; @@ -5524,14 +5785,14 @@ if (tso) tx_flags |= E1000_TX_FLAGS_TSO; - else if (e1000_tx_csum(tx_ring, skb)) + else if (e1000_tx_csum(tx_ring, skb, protocol)) 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 (skb->protocol == htons(ETH_P_IP)) + if (protocol == htons(ETH_P_IP)) tx_flags |= E1000_TX_FLAGS_IPV4; if (unlikely(skb->no_fcs)) @@ -5541,11 +5802,13 @@ count = e1000_tx_map(tx_ring, skb, first, adapter->tx_fifo_limit, nr_frags); if (count) { - if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && - !adapter->tx_hwtstamp_skb)) { + if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && + (adapter->flags & FLAG_HAS_HW_TIMESTAMP) && + !adapter->tx_hwtstamp_skb) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; tx_flags |= E1000_TX_FLAGS_HWTSTAMP; adapter->tx_hwtstamp_skb = skb_get(skb); + adapter->tx_hwtstamp_start = jiffies; schedule_work(&adapter->tx_hwtstamp_work); } else { skb_tx_timestamp(skb); @@ -5558,6 +5821,21 @@ (MAX_SKB_FRAGS * DIV_ROUND_UP(PAGE_SIZE, adapter->tx_fifo_limit) + 2)); + + if (!skb->xmit_more || + netif_xmit_stopped(netdev_get_tx_queue(netdev, 0))) { + if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA) + e1000e_update_tdt_wa(tx_ring, + tx_ring->next_to_use); + else + writel(tx_ring->next_to_use, tx_ring->tail); + + /* we need this if more than one processor can write + * to our tail at a time, it synchronizes IO on + *IA64/Altix systems + */ + mmiowb(); + } } else { dev_kfree_skb_any(skb); tx_ring->buffer_info[first].time_stamp = 0; @@ -5654,17 +5932,17 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu) { struct e1000_adapter *adapter = netdev_priv(netdev); - int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN; + int max_frame = new_mtu + VLAN_ETH_HLEN + ETH_FCS_LEN; /* Jumbo frame support */ - if ((max_frame > ETH_FRAME_LEN + ETH_FCS_LEN) && + if ((max_frame > (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN)) && !(adapter->flags & FLAG_HAS_JUMBO_FRAMES)) { e_err("Jumbo Frames not supported.\n"); return -EINVAL; } /* Supported frame sizes */ - if ((new_mtu < ETH_ZLEN + ETH_FCS_LEN + VLAN_HLEN) || + if ((new_mtu < (VLAN_ETH_ZLEN + ETH_FCS_LEN)) || (max_frame > adapter->max_hw_frame_size)) { e_err("Unsupported MTU setting\n"); return -EINVAL; @@ -5684,8 +5962,11 @@ adapter->max_frame_size = max_frame; e_info("changing MTU from %d to %d\n", netdev->mtu, new_mtu); netdev->mtu = new_mtu; + + pm_runtime_get_sync(netdev->dev.parent); + if (netif_running(netdev)) - e1000e_down(adapter); + e1000e_down(adapter, true); /* 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 @@ -5701,16 +5982,16 @@ adapter->rx_buffer_len = 4096; /* adjust allocation if LPE protects us, and we aren't using SBP */ - if ((max_frame == ETH_FRAME_LEN + ETH_FCS_LEN) || - (max_frame == ETH_FRAME_LEN + VLAN_HLEN + ETH_FCS_LEN)) - adapter->rx_buffer_len = ETH_FRAME_LEN + VLAN_HLEN - + ETH_FCS_LEN; + if (max_frame <= (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN)) + adapter->rx_buffer_len = VLAN_ETH_FRAME_LEN + ETH_FCS_LEN; if (netif_running(netdev)) e1000e_up(adapter); else e1000e_reset(adapter); + pm_runtime_put_sync(netdev->dev.parent); + clear_bit(__E1000_RESETTING, &adapter->state); return 0; @@ -5790,7 +6071,7 @@ * specified. Matching the kind of event packet is not supported, with the * exception of "all V2 events regardless of level 2 or 4". **/ -static int e1000e_hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr) +static int e1000e_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr) { struct e1000_adapter *adapter = netdev_priv(netdev); struct hwtstamp_config config; @@ -5799,14 +6080,10 @@ if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) return -EFAULT; - adapter->hwtstamp_config = config; - - ret_val = e1000e_config_hwtstamp(adapter); + ret_val = e1000e_config_hwtstamp(adapter, &config); if (ret_val) return ret_val; - config = adapter->hwtstamp_config; - switch (config.rx_filter) { case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: @@ -5829,6 +6106,14 @@ sizeof(config)) ? -EFAULT : 0; } +static int e1000e_hwtstamp_get(struct net_device *netdev, struct ifreq *ifr) +{ + struct e1000_adapter *adapter = netdev_priv(netdev); + + return copy_to_user(ifr->ifr_data, &adapter->hwtstamp_config, + sizeof(adapter->hwtstamp_config)) ? -EFAULT : 0; +} + static int e1000_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) { switch (cmd) { @@ -5837,7 +6122,9 @@ case SIOCSMIIREG: return e1000_mii_ioctl(netdev, ifr, cmd); case SIOCSHWTSTAMP: - return e1000e_hwtstamp_ioctl(netdev, ifr); + return e1000e_hwtstamp_set(netdev, ifr); + case SIOCGHWTSTAMP: + return e1000e_hwtstamp_get(netdev, ifr); default: return -EOPNOTSUPP; } @@ -5846,7 +6133,7 @@ static int e1000_init_phy_wakeup(struct e1000_adapter *adapter, u32 wufc) { struct e1000_hw *hw = &adapter->hw; - u32 i, mac_reg; + u32 i, mac_reg, wuc; u16 phy_reg, wuc_enable; int retval; @@ -5893,13 +6180,18 @@ phy_reg |= BM_RCTL_RFCE; hw->phy.ops.write_reg_page(&adapter->hw, BM_RCTL, phy_reg); + wuc = E1000_WUC_PME_EN; + if (wufc & (E1000_WUFC_MAG | E1000_WUFC_LNKC)) + wuc |= E1000_WUC_APME; + /* enable PHY wakeup in MAC register */ ew32(WUFC, wufc); - ew32(WUC, E1000_WUC_PHY_WAKE | E1000_WUC_PME_EN); + ew32(WUC, (E1000_WUC_PHY_WAKE | E1000_WUC_APMPME | + E1000_WUC_PME_STATUS | wuc)); /* configure and enable PHY wakeup in PHY registers */ hw->phy.ops.write_reg_page(&adapter->hw, BM_WUFC, wufc); - hw->phy.ops.write_reg_page(&adapter->hw, BM_WUC, E1000_WUC_PME_EN); + hw->phy.ops.write_reg_page(&adapter->hw, BM_WUC, wuc); /* activate PHY wakeup */ wuc_enable |= BM_WUC_ENABLE_BIT | BM_WUC_HOST_WU_BIT; @@ -5912,15 +6204,32 @@ return retval; } -static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) +static void e1000e_flush_lpic(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 ctrl, ctrl_ext, rctl, status; - /* Runtime suspend should only enable wakeup for link changes */ - u32 wufc = runtime ? E1000_WUFC_LNKC : adapter->wol; - int retval = 0; + u32 ret_val; + + pm_runtime_get_sync(netdev->dev.parent); + + ret_val = hw->phy.ops.acquire(hw); + if (ret_val) + goto fl_out; + + pr_info("EEE TX LPI TIMER: %08X\n", + er32(LPIC) >> E1000_LPIC_LPIET_SHIFT); + + hw->phy.ops.release(hw); + +fl_out: + pm_runtime_put_sync(netdev->dev.parent); +} + +static int e1000e_pm_freeze(struct device *dev) +{ + struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); + struct e1000_adapter *adapter = netdev_priv(netdev); netif_device_detach(netdev); @@ -5931,11 +6240,29 @@ usleep_range(10000, 20000); WARN_ON(test_bit(__E1000_RESETTING, &adapter->state)); - e1000e_down(adapter); + + /* Quiesce the device without resetting the hardware */ + e1000e_down(adapter, false); e1000_free_irq(adapter); } e1000e_reset_interrupt_capability(adapter); + /* Allow time for pending master requests to run */ + e1000e_disable_pcie_master(&adapter->hw); + + return 0; +} + +static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) +{ + 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; + /* Runtime suspend should only enable wakeup for link changes */ + u32 wufc = runtime ? E1000_WUFC_LNKC : adapter->wol; + int retval = 0; + status = er32(STATUS); if (status & E1000_STATUS_LU) wufc &= ~E1000_WUFC_LNKC; @@ -5966,12 +6293,12 @@ ew32(CTRL_EXT, ctrl_ext); } + if (!runtime) + e1000e_power_up_phy(adapter); + if (adapter->flags & FLAG_IS_ICH) e1000_suspend_workarounds_ich8lan(&adapter->hw); - /* Allow time for pending master requests to run */ - e1000e_disable_pcie_master(&adapter->hw); - if (adapter->flags2 & FLAG2_HAS_PHY_WAKEUP) { /* enable wakeup by the PHY */ retval = e1000_init_phy_wakeup(adapter, wufc); @@ -5985,25 +6312,75 @@ } else { ew32(WUC, 0); ew32(WUFC, 0); + + e1000_power_down_phy(adapter); } - if (adapter->hw.phy.type == e1000_phy_igp_3) + if (adapter->hw.phy.type == e1000_phy_igp_3) { e1000e_igp3_phy_powerdown_workaround_ich8lan(&adapter->hw); + } else if ((hw->mac.type == e1000_pch_lpt) || + (hw->mac.type == e1000_pch_spt)) { + if (!(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC))) + /* ULP does not support wake from unicast, multicast + * or broadcast. + */ + retval = e1000_enable_ulp_lpt_lp(hw, !runtime); + + if (retval) + return retval; + } + + /* Ensure that the appropriate bits are set in LPI_CTRL + * for EEE in Sx + */ + if ((hw->phy.type >= e1000_phy_i217) && + adapter->eee_advert && hw->dev_spec.ich8lan.eee_lp_ability) { + u16 lpi_ctrl = 0; + + retval = hw->phy.ops.acquire(hw); + if (!retval) { + retval = e1e_rphy_locked(hw, I82579_LPI_CTRL, + &lpi_ctrl); + if (!retval) { + if (adapter->eee_advert & + hw->dev_spec.ich8lan.eee_lp_ability & + I82579_EEE_100_SUPPORTED) + lpi_ctrl |= I82579_LPI_CTRL_100_ENABLE; + if (adapter->eee_advert & + hw->dev_spec.ich8lan.eee_lp_ability & + I82579_EEE_1000_SUPPORTED) + lpi_ctrl |= I82579_LPI_CTRL_1000_ENABLE; + + retval = e1e_wphy_locked(hw, I82579_LPI_CTRL, + lpi_ctrl); + } + } + hw->phy.ops.release(hw); + } /* Release control of h/w to f/w. If f/w is AMT enabled, this * would have already happened in close and is redundant. */ e1000e_release_hw_control(adapter); + pci_clear_master(pdev); + /* The pci-e switch on some quad port adapters will report a * correctable error when the MAC transitions from D0 to D3. To * prevent this we need to mask off the correctable errors on the * downstream port of the pci-e switch. + * + * We don't have the associated upstream bridge while assigning + * the PCI device into guest. For example, the KVM on power is + * one of the cases. */ if (adapter->flags & FLAG_IS_QUAD_PORT) { struct pci_dev *us_dev = pdev->bus->self; u16 devctl; + if (!us_dev) + return 0; + pcie_capability_read_word(us_dev, PCI_EXP_DEVCTL, &devctl); pcie_capability_write_word(us_dev, PCI_EXP_DEVCTL, (devctl & ~PCI_EXP_DEVCTL_CERE)); @@ -6017,53 +6394,112 @@ return 0; } +/** + * __e1000e_disable_aspm - Disable ASPM states + * @pdev: pointer to PCI device struct + * @state: bit-mask of ASPM states to disable + * @locked: indication if this context holds pci_bus_sem locked. + * + * Some devices *must* have certain ASPM states disabled per hardware errata. + **/ +static void __e1000e_disable_aspm(struct pci_dev *pdev, u16 state, int locked) +{ + struct pci_dev *parent = pdev->bus->self; + u16 aspm_dis_mask = 0; + u16 pdev_aspmc, parent_aspmc; + + switch (state) { + case PCIE_LINK_STATE_L0S: + case PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1: + aspm_dis_mask |= PCI_EXP_LNKCTL_ASPM_L0S; + /* fall-through - can't have L1 without L0s */ + case PCIE_LINK_STATE_L1: + aspm_dis_mask |= PCI_EXP_LNKCTL_ASPM_L1; + break; + default: + return; + } + + pcie_capability_read_word(pdev, PCI_EXP_LNKCTL, &pdev_aspmc); + pdev_aspmc &= PCI_EXP_LNKCTL_ASPMC; + + if (parent) { + pcie_capability_read_word(parent, PCI_EXP_LNKCTL, + &parent_aspmc); + parent_aspmc &= PCI_EXP_LNKCTL_ASPMC; + } + + /* Nothing to do if the ASPM states to be disabled already are */ + if (!(pdev_aspmc & aspm_dis_mask) && + (!parent || !(parent_aspmc & aspm_dis_mask))) + return; + + dev_info(&pdev->dev, "Disabling ASPM %s %s\n", + (aspm_dis_mask & pdev_aspmc & PCI_EXP_LNKCTL_ASPM_L0S) ? + "L0s" : "", + (aspm_dis_mask & pdev_aspmc & PCI_EXP_LNKCTL_ASPM_L1) ? + "L1" : ""); + #ifdef CONFIG_PCIEASPM -static void __e1000e_disable_aspm(struct pci_dev *pdev, u16 state) -{ - pci_disable_link_state_locked(pdev, state); -} -#else -static void __e1000e_disable_aspm(struct pci_dev *pdev, u16 state) -{ - u16 aspm_ctl = 0; + if (locked) + pci_disable_link_state_locked(pdev, state); + else + pci_disable_link_state(pdev, state); + + /* Double-check ASPM control. If not disabled by the above, the + * BIOS is preventing that from happening (or CONFIG_PCIEASPM is + * not enabled); override by writing PCI config space directly. + */ + pcie_capability_read_word(pdev, PCI_EXP_LNKCTL, &pdev_aspmc); + pdev_aspmc &= PCI_EXP_LNKCTL_ASPMC; - if (state & PCIE_LINK_STATE_L0S) - aspm_ctl |= PCI_EXP_LNKCTL_ASPM_L0S; - if (state & PCIE_LINK_STATE_L1) - aspm_ctl |= PCI_EXP_LNKCTL_ASPM_L1; + if (!(aspm_dis_mask & pdev_aspmc)) + return; +#endif /* Both device and parent should have the same ASPM setting. * Disable ASPM in downstream component first and then upstream. */ - pcie_capability_clear_word(pdev, PCI_EXP_LNKCTL, aspm_ctl); + pcie_capability_clear_word(pdev, PCI_EXP_LNKCTL, aspm_dis_mask); - if (pdev->bus->self) - pcie_capability_clear_word(pdev->bus->self, PCI_EXP_LNKCTL, - aspm_ctl); + if (parent) + pcie_capability_clear_word(parent, PCI_EXP_LNKCTL, + aspm_dis_mask); } -#endif + +/** + * e1000e_disable_aspm - Disable ASPM states. + * @pdev: pointer to PCI device struct + * @state: bit-mask of ASPM states to disable + * + * This function acquires the pci_bus_sem! + * Some devices *must* have certain ASPM states disabled per hardware errata. + **/ static void e1000e_disable_aspm(struct pci_dev *pdev, u16 state) { - dev_info(&pdev->dev, "Disabling ASPM %s %s\n", - (state & PCIE_LINK_STATE_L0S) ? "L0s" : "", - (state & PCIE_LINK_STATE_L1) ? "L1" : ""); - - __e1000e_disable_aspm(pdev, state); + __e1000e_disable_aspm(pdev, state, 0); } -#ifdef CONFIG_PM -static bool e1000e_pm_ready(struct e1000_adapter *adapter) +/** + * e1000e_disable_aspm_locked Disable ASPM states. + * @pdev: pointer to PCI device struct + * @state: bit-mask of ASPM states to disable + * + * This function must be called with pci_bus_sem acquired! + * Some devices *must* have certain ASPM states disabled per hardware errata. + **/ +static void e1000e_disable_aspm_locked(struct pci_dev *pdev, u16 state) { - return !!adapter->tx_ring->buffer_info; + __e1000e_disable_aspm(pdev, state, 1); } +#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; u16 aspm_disable_flag = 0; - u32 err; if (adapter->flags2 & FLAG2_DISABLE_ASPM_L0S) aspm_disable_flag = PCIE_LINK_STATE_L0S; @@ -6074,13 +6510,6 @@ pci_set_master(pdev); - e1000e_set_interrupt_capability(adapter); - if (netif_running(netdev)) { - err = e1000_request_irq(adapter); - if (err) - return err; - } - if (hw->mac.type >= e1000_pch2lan) e1000_resume_workarounds_pchlan(&adapter->hw); @@ -6103,6 +6532,7 @@ e1e_wphy(&adapter->hw, BM_WUS, ~0); } else { u32 wus = er32(WUS); + if (wus) { e_info("MAC Wakeup cause - %s\n", wus & E1000_WUS_EX ? "Unicast Packet" : @@ -6119,11 +6549,6 @@ e1000_init_manageability_pt(adapter); - if (netif_running(netdev)) - e1000e_up(adapter); - - netif_device_attach(netdev); - /* If the controller has 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. @@ -6135,74 +6560,117 @@ } #ifdef CONFIG_PM_SLEEP -static int e1000_suspend(struct device *dev) +static int e1000e_pm_thaw(struct device *dev) +{ + struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); + struct e1000_adapter *adapter = netdev_priv(netdev); + + e1000e_set_interrupt_capability(adapter); + if (netif_running(netdev)) { + u32 err = e1000_request_irq(adapter); + + if (err) + return err; + + e1000e_up(adapter); + } + + netif_device_attach(netdev); + + return 0; +} + +static int e1000e_pm_suspend(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); + e1000e_flush_lpic(pdev); + + e1000e_pm_freeze(dev); + return __e1000_shutdown(pdev, false); } -static int e1000_resume(struct device *dev) +static int e1000e_pm_resume(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); - struct net_device *netdev = pci_get_drvdata(pdev); - struct e1000_adapter *adapter = netdev_priv(netdev); + int rc; - if (e1000e_pm_ready(adapter)) - adapter->idle_check = true; + rc = __e1000_resume(pdev); + if (rc) + return rc; - return __e1000_resume(pdev); + return e1000e_pm_thaw(dev); } #endif /* CONFIG_PM_SLEEP */ -#ifdef CONFIG_PM_RUNTIME -static int e1000_runtime_suspend(struct device *dev) +static int e1000e_pm_runtime_idle(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); struct e1000_adapter *adapter = netdev_priv(netdev); + u16 eee_lp; - if (!e1000e_pm_ready(adapter)) - return 0; + eee_lp = adapter->hw.dev_spec.ich8lan.eee_lp_ability; - return __e1000_shutdown(pdev, true); + if (!e1000e_has_link(adapter)) { + adapter->hw.dev_spec.ich8lan.eee_lp_ability = eee_lp; + pm_schedule_suspend(dev, 5 * MSEC_PER_SEC); + } + + return -EBUSY; } -static int e1000_idle(struct device *dev) +static int e1000e_pm_runtime_resume(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); struct e1000_adapter *adapter = netdev_priv(netdev); + int rc; - if (!e1000e_pm_ready(adapter)) - return 0; + rc = __e1000_resume(pdev); + if (rc) + return rc; - if (adapter->idle_check) { - adapter->idle_check = false; - if (!e1000e_has_link(adapter)) - pm_schedule_suspend(dev, MSEC_PER_SEC); - } + if (netdev->flags & IFF_UP) + rc = e1000e_up(adapter); - return -EBUSY; + return rc; } -static int e1000_runtime_resume(struct device *dev) +static int e1000e_pm_runtime_suspend(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); struct e1000_adapter *adapter = netdev_priv(netdev); - if (!e1000e_pm_ready(adapter)) - return 0; + if (netdev->flags & IFF_UP) { + int count = E1000_CHECK_RESET_COUNT; + + while (test_bit(__E1000_RESETTING, &adapter->state) && count--) + usleep_range(10000, 20000); - adapter->idle_check = !dev->power.runtime_auto; - return __e1000_resume(pdev); + WARN_ON(test_bit(__E1000_RESETTING, &adapter->state)); + + /* Down the device without resetting the hardware */ + e1000e_down(adapter, false); + } + + if (__e1000_shutdown(pdev, true)) { + e1000e_pm_runtime_resume(dev); + return -EBUSY; + } + + return 0; } -#endif /* CONFIG_PM_RUNTIME */ #endif /* CONFIG_PM */ static void e1000_shutdown(struct pci_dev *pdev) { + e1000e_flush_lpic(pdev); + + e1000e_pm_freeze(&pdev->dev); + __e1000_shutdown(pdev, false); } @@ -6259,7 +6727,7 @@ e1000_intr_msi(adapter->pdev->irq, netdev); enable_irq(adapter->pdev->irq); break; - default: /* E1000E_INT_MODE_LEGACY */ + default: /* E1000E_INT_MODE_LEGACY */ disable_irq(adapter->pdev->irq); e1000_intr(adapter->pdev->irq, netdev); enable_irq(adapter->pdev->irq); @@ -6288,7 +6756,7 @@ return PCI_ERS_RESULT_DISCONNECT; if (netif_running(netdev)) - e1000e_down(adapter); + e1000e_down(adapter, true); pci_disable_device(pdev); /* Request a slot slot reset. */ @@ -6300,7 +6768,7 @@ * @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. + * resembles the first-half of the e1000e_pm_resume routine. */ static pci_ers_result_t e1000_io_slot_reset(struct pci_dev *pdev) { @@ -6316,7 +6784,7 @@ if (adapter->flags2 & FLAG2_DISABLE_ASPM_L1) aspm_disable_flag |= PCIE_LINK_STATE_L1; if (aspm_disable_flag) - e1000e_disable_aspm(pdev, aspm_disable_flag); + e1000e_disable_aspm_locked(pdev, aspm_disable_flag); err = pci_enable_device_mem(pdev); if (err) { @@ -6347,7 +6815,7 @@ * * 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. + * second-half of the e1000e_pm_resume routine. */ static void e1000_io_resume(struct pci_dev *pdev) { @@ -6416,6 +6884,19 @@ } } +static netdev_features_t e1000_fix_features(struct net_device *netdev, + netdev_features_t features) +{ + struct e1000_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + + /* Jumbo frame workaround on 82579 and newer requires CRC be stripped */ + if ((hw->mac.type >= e1000_pch2lan) && (netdev->mtu > ETH_DATA_LEN)) + features &= ~NETIF_F_RXFCS; + + return features; +} + static int e1000_set_features(struct net_device *netdev, netdev_features_t features) { @@ -6472,6 +6953,8 @@ .ndo_poll_controller = e1000_netpoll, #endif .ndo_set_features = e1000_set_features, + .ndo_fix_features = e1000_fix_features, + .ndo_features_check = passthru_features_check, }; /** @@ -6498,6 +6981,7 @@ int bars, i, err, pci_using_dac; u16 eeprom_data = 0; u16 eeprom_apme_mask = E1000_EEPROM_APME; + s32 rval = 0; if (ei->flags2 & FLAG2_DISABLE_ASPM_L0S) aspm_disable_flag = PCIE_LINK_STATE_L0S; @@ -6511,21 +6995,15 @@ return err; pci_using_dac = 0; - err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (!err) { - err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64)); - if (!err) - pci_using_dac = 1; + pci_using_dac = 1; } else { - err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (err) { - err = dma_set_coherent_mask(&pdev->dev, - DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "No usable DMA configuration, aborting\n"); - goto err_dma; - } + dev_err(&pdev->dev, + "No usable DMA configuration, aborting\n"); + goto err_dma; } } @@ -6576,7 +7054,8 @@ goto err_ioremap; if ((adapter->flags & FLAG_HAS_FLASH) && - (pci_resource_flags(pdev, 1) & IORESOURCE_MEM)) { + (pci_resource_flags(pdev, 1) & IORESOURCE_MEM) && + (hw->mac.type < e1000_pch_spt)) { flash_start = pci_resource_start(pdev, 1); flash_len = pci_resource_len(pdev, 1); adapter->hw.flash_address = ioremap(flash_start, flash_len); @@ -6589,9 +7068,9 @@ adapter->eee_advert = MDIO_EEE_100TX | MDIO_EEE_1000T; /* construct the net_device struct */ - netdev->netdev_ops = &e1000e_netdev_ops; + netdev->netdev_ops = &e1000e_netdev_ops; e1000e_set_ethtool_ops(netdev); - netdev->watchdog_timeo = 5 * HZ; + netdev->watchdog_timeo = 5 * HZ; netif_napi_add(netdev, &adapter->napi, e1000e_poll, 64); strlcpy(netdev->name, pci_name(pdev), sizeof(netdev->name)); @@ -6616,7 +7095,8 @@ goto err_hw_init; if ((adapter->flags & FLAG_IS_ICH) && - (adapter->flags & FLAG_READ_ONLY_NVM)) + (adapter->flags & FLAG_READ_ONLY_NVM) && + (hw->mac.type < e1000_pch_spt)) e1000e_write_protect_nvm_ich8lan(&adapter->hw); hw->mac.ops.get_bus_info(&adapter->hw); @@ -6723,10 +7203,6 @@ adapter->hw.fc.current_mode = e1000_fc_default; adapter->hw.phy.autoneg_advertised = 0x2f; - /* ring size defaults */ - adapter->rx_ring->count = E1000_DEFAULT_RXD; - adapter->tx_ring->count = E1000_DEFAULT_TXD; - /* Initial Wake on LAN setting - If APM wake is enabled in * the EEPROM, enable the ACPI Magic Packet filter */ @@ -6740,15 +7216,19 @@ } else if (adapter->flags & FLAG_APME_IN_CTRL3) { if (adapter->flags & FLAG_APME_CHECK_PORT_B && (adapter->hw.bus.func == 1)) - e1000_read_nvm(&adapter->hw, NVM_INIT_CONTROL3_PORT_B, - 1, &eeprom_data); + rval = e1000_read_nvm(&adapter->hw, + NVM_INIT_CONTROL3_PORT_B, + 1, &eeprom_data); else - e1000_read_nvm(&adapter->hw, NVM_INIT_CONTROL3_PORT_A, - 1, &eeprom_data); + rval = e1000_read_nvm(&adapter->hw, + NVM_INIT_CONTROL3_PORT_A, + 1, &eeprom_data); } /* fetch WoL from EEPROM */ - if (eeprom_data & eeprom_apme_mask) + if (rval) + e_dbg("NVM read error getting WoL initial values: %d\n", rval); + else if (eeprom_data & eeprom_apme_mask) adapter->eeprom_wol |= E1000_WUFC_MAG; /* now that we have the eeprom settings, apply the special cases @@ -6767,7 +7247,12 @@ device_wakeup_enable(&pdev->dev); /* save off EEPROM version number */ - e1000_read_nvm(&adapter->hw, 5, 1, &adapter->eeprom_vers); + rval = e1000_read_nvm(&adapter->hw, 5, 1, &adapter->eeprom_vers); + + if (rval) { + e_dbg("NVM read error getting EEPROM version: %d\n", rval); + adapter->eeprom_vers = 0; + } /* reset the hardware with the new settings */ e1000e_reset(adapter); @@ -6807,7 +7292,7 @@ kfree(adapter->tx_ring); kfree(adapter->rx_ring); err_sw_init: - if (adapter->hw.flash_address) + if ((adapter->hw.flash_address) && (hw->mac.type < e1000_pch_spt)) iounmap(adapter->hw.flash_address); e1000e_reset_interrupt_capability(adapter); err_flashmap: @@ -6862,9 +7347,6 @@ } } - if (!(netdev->flags & IFF_UP)) - e1000_power_down_phy(adapter); - /* Don't lie to e1000_close() down the road. */ if (!down) clear_bit(__E1000_DOWN, &adapter->state); @@ -6883,7 +7365,8 @@ kfree(adapter->rx_ring); iounmap(adapter->hw.hw_addr); - if (adapter->hw.flash_address) + if ((adapter->hw.flash_address) && + (adapter->hw.mac.type < e1000_pch_spt)) iounmap(adapter->hw.flash_address); pci_release_selected_regions(pdev, pci_select_bars(pdev, IORESOURCE_MEM)); @@ -6903,7 +7386,7 @@ .resume = e1000_io_resume, }; -static DEFINE_PCI_DEVICE_TABLE(e1000_pci_tbl) = { +static const struct pci_device_id e1000_pci_tbl[] = { { PCI_VDEVICE(INTEL, E1000_DEV_ID_82571EB_COPPER), board_82571 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_82571EB_FIBER), board_82571 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_82571EB_QUAD_COPPER), board_82571 }, @@ -6976,18 +7459,31 @@ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LPT_I217_V), board_pch_lpt }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LPTLP_I218_LM), board_pch_lpt }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LPTLP_I218_V), board_pch_lpt }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_I218_LM2), board_pch_lpt }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_I218_V2), board_pch_lpt }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_I218_LM3), board_pch_lpt }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_I218_V3), board_pch_lpt }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_SPT_I219_LM), board_pch_spt }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_SPT_I219_V), board_pch_spt }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_SPT_I219_LM2), board_pch_spt }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_SPT_I219_V2), board_pch_spt }, { 0, 0, 0, 0, 0, 0, 0 } /* terminate list */ }; MODULE_DEVICE_TABLE(pci, e1000_pci_tbl); -#ifdef CONFIG_PM static const struct dev_pm_ops e1000_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(e1000_suspend, e1000_resume) - SET_RUNTIME_PM_OPS(e1000_runtime_suspend, e1000_runtime_resume, - e1000_idle) -}; +#ifdef CONFIG_PM_SLEEP + .suspend = e1000e_pm_suspend, + .resume = e1000e_pm_resume, + .freeze = e1000e_pm_freeze, + .thaw = e1000e_pm_thaw, + .poweroff = e1000e_pm_suspend, + .restore = e1000e_pm_resume, #endif + SET_RUNTIME_PM_OPS(e1000e_pm_runtime_suspend, e1000e_pm_runtime_resume, + e1000e_pm_runtime_idle) +}; /* PCI Device API Driver */ static struct pci_driver e1000_driver = { @@ -6995,11 +7491,9 @@ .id_table = e1000_pci_tbl, .probe = e1000_probe, .remove = e1000_remove, -#ifdef CONFIG_PM .driver = { .pm = &e1000_pm_ops, }, -#endif .shutdown = e1000_shutdown, .err_handler = &e1000_err_handler }; @@ -7013,9 +7507,10 @@ static int __init e1000_init_module(void) { int ret; + pr_info("Intel(R) PRO/1000 Network Driver - %s\n", e1000e_driver_version); - pr_info("Copyright(c) 1999 - 2013 Intel Corporation.\n"); + pr_info("Copyright(c) 1999 - 2015 Intel Corporation.\n"); ret = pci_register_driver(&e1000_driver); return ret; @@ -7034,7 +7529,6 @@ } module_exit(e1000_exit_module); - MODULE_AUTHOR("Intel Corporation, "); MODULE_DESCRIPTION("Intel(R) PRO/1000 Network Driver"); MODULE_LICENSE("GPL");