diff options
Diffstat (limited to 'drivers/net/ethernet/intel/igb/igb_main.c')
| -rw-r--r-- | drivers/net/ethernet/intel/igb/igb_main.c | 2873 |
1 files changed, 1873 insertions, 1000 deletions
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 31cfe2ec75d..a9537ba7a5a 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -1,29 +1,25 @@ -/******************************************************************************* - - Intel(R) Gigabit Ethernet Linux driver - Copyright(c) 2007-2012 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Intel(R) Gigabit Ethernet Linux driver + * Copyright(c) 2007-2014 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, see <http://www.gnu.org/licenses/>. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -57,29 +53,36 @@ #ifdef CONFIG_IGB_DCA #include <linux/dca.h> #endif +#include <linux/i2c.h> #include "igb.h" -#define MAJ 4 -#define MIN 1 -#define BUILD 2 +#define MAJ 5 +#define MIN 0 +#define BUILD 5 #define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) "." \ __stringify(BUILD) "-k" char igb_driver_name[] = "igb"; char igb_driver_version[] = DRV_VERSION; static const char igb_driver_string[] = "Intel(R) Gigabit Ethernet Network Driver"; -static const char igb_copyright[] = "Copyright (c) 2007-2012 Intel Corporation."; +static const char igb_copyright[] = + "Copyright (c) 2007-2014 Intel Corporation."; static const struct e1000_info *igb_info_tbl[] = { [board_82575] = &e1000_82575_info, }; -static DEFINE_PCI_DEVICE_TABLE(igb_pci_tbl) = { +static const struct pci_device_id igb_pci_tbl[] = { + { PCI_VDEVICE(INTEL, E1000_DEV_ID_I354_BACKPLANE_1GBPS) }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_I354_SGMII) }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_I354_BACKPLANE_2_5GBPS) }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_I211_COPPER), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_I210_COPPER), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_I210_FIBER), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_I210_SERDES), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_I210_SGMII), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_I210_COPPER_FLASHLESS), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_I210_SERDES_FLASHLESS), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_I350_COPPER), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_I350_FIBER), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_I350_SERDES), board_82575 }, @@ -111,7 +114,6 @@ static DEFINE_PCI_DEVICE_TABLE(igb_pci_tbl) = { MODULE_DEVICE_TABLE(pci, igb_pci_tbl); -void igb_reset(struct igb_adapter *); static int igb_setup_all_tx_resources(struct igb_adapter *); static int igb_setup_all_rx_resources(struct igb_adapter *); static void igb_free_all_tx_resources(struct igb_adapter *); @@ -135,7 +137,7 @@ static void igb_watchdog(unsigned long); static void igb_watchdog_task(struct work_struct *); static netdev_tx_t igb_xmit_frame(struct sk_buff *skb, struct net_device *); static struct rtnl_link_stats64 *igb_get_stats64(struct net_device *dev, - struct rtnl_link_stats64 *stats); + struct rtnl_link_stats64 *stats); static int igb_change_mtu(struct net_device *, int); static int igb_set_mac(struct net_device *, void *); static void igb_set_uta(struct igb_adapter *adapter); @@ -153,9 +155,10 @@ static bool igb_clean_rx_irq(struct igb_q_vector *, int); static int igb_ioctl(struct net_device *, struct ifreq *, int cmd); static void igb_tx_timeout(struct net_device *); static void igb_reset_task(struct work_struct *); -static void igb_vlan_mode(struct net_device *netdev, netdev_features_t features); -static int igb_vlan_rx_add_vid(struct net_device *, u16); -static int igb_vlan_rx_kill_vid(struct net_device *, u16); +static void igb_vlan_mode(struct net_device *netdev, + netdev_features_t features); +static int igb_vlan_rx_add_vid(struct net_device *, __be16, u16); +static int igb_vlan_rx_kill_vid(struct net_device *, __be16, u16); static void igb_restore_vlan(struct igb_adapter *); static void igb_rar_set_qsel(struct igb_adapter *, u8 *, u32 , u8); static void igb_ping_all_vfs(struct igb_adapter *); @@ -166,14 +169,16 @@ static void igb_restore_vf_multicasts(struct igb_adapter *adapter); static int igb_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac); static int igb_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos); -static int igb_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate); +static int igb_ndo_set_vf_bw(struct net_device *, int, int, int); +static int igb_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, + bool setting); static int igb_ndo_get_vf_config(struct net_device *netdev, int vf, struct ifla_vf_info *ivi); static void igb_check_vf_rate_limit(struct igb_adapter *); #ifdef CONFIG_PCI_IOV static int igb_vf_configure(struct igb_adapter *adapter, int vf); -static bool igb_vfs_are_assigned(struct igb_adapter *adapter); +static int igb_pci_enable_sriov(struct pci_dev *dev, int num_vfs); #endif #ifdef CONFIG_PM @@ -193,6 +198,7 @@ static const struct dev_pm_ops igb_pm_ops = { }; #endif static void igb_shutdown(struct pci_dev *); +static int igb_pci_sriov_configure(struct pci_dev *dev, int num_vfs); #ifdef CONFIG_IGB_DCA static int igb_notify_dca(struct notifier_block *, unsigned long, void *); static struct notifier_block dca_notifier = { @@ -206,10 +212,9 @@ static struct notifier_block dca_notifier = { static void igb_netpoll(struct net_device *); #endif #ifdef CONFIG_PCI_IOV -static unsigned int max_vfs = 0; +static unsigned int max_vfs; module_param(max_vfs, uint, 0); -MODULE_PARM_DESC(max_vfs, "Maximum number of virtual functions to allocate " - "per physical function"); +MODULE_PARM_DESC(max_vfs, "Maximum number of virtual functions to allocate per physical function"); #endif /* CONFIG_PCI_IOV */ static pci_ers_result_t igb_io_error_detected(struct pci_dev *, @@ -234,6 +239,7 @@ static struct pci_driver igb_driver = { .driver.pm = &igb_pm_ops, #endif .shutdown = igb_shutdown, + .sriov_configure = igb_pci_sriov_configure, .err_handler = &igb_err_handler }; @@ -288,9 +294,7 @@ static const struct igb_reg_info igb_reg_info_tbl[] = { {} }; -/* - * igb_regdump - register printout routine - */ +/* igb_regdump - register printout routine */ static void igb_regdump(struct e1000_hw *hw, struct igb_reg_info *reginfo) { int n = 0; @@ -356,9 +360,7 @@ static void igb_regdump(struct e1000_hw *hw, struct igb_reg_info *reginfo) regs[2], regs[3]); } -/* - * igb_dump - Print registers, tx-rings and rx-rings - */ +/* igb_dump - Print registers, Tx-rings and Rx-rings */ static void igb_dump(struct igb_adapter *adapter) { struct net_device *netdev = adapter->netdev; @@ -378,8 +380,7 @@ static void igb_dump(struct igb_adapter *adapter) /* Print netdevice Info */ if (netdev) { dev_info(&adapter->pdev->dev, "Net device Info\n"); - pr_info("Device Name state trans_start " - "last_rx\n"); + pr_info("Device Name state trans_start last_rx\n"); pr_info("%-15s %016lX %016lX %016lX\n", netdev->name, netdev->state, netdev->trans_start, netdev->last_rx); } @@ -432,9 +433,7 @@ static void igb_dump(struct igb_adapter *adapter) pr_info("------------------------------------\n"); pr_info("TX QUEUE INDEX = %d\n", tx_ring->queue_index); pr_info("------------------------------------\n"); - pr_info("T [desc] [address 63:0 ] [PlPOCIStDDM Ln] " - "[bi->dma ] leng ntw timestamp " - "bi->skb\n"); + pr_info("T [desc] [address 63:0 ] [PlPOCIStDDM Ln] [bi->dma ] leng ntw timestamp bi->skb\n"); for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) { const char *next_desc; @@ -452,9 +451,8 @@ static void igb_dump(struct igb_adapter *adapter) else next_desc = ""; - pr_info("T [0x%03X] %016llX %016llX %016llX" - " %04X %p %016llX %p%s\n", i, - le64_to_cpu(u0->a), + pr_info("T [0x%03X] %016llX %016llX %016llX %04X %p %016llX %p%s\n", + i, le64_to_cpu(u0->a), le64_to_cpu(u0->b), (u64)dma_unmap_addr(buffer_info, dma), dma_unmap_len(buffer_info, len), @@ -513,10 +511,8 @@ rx_ring_summary: pr_info("------------------------------------\n"); pr_info("RX QUEUE INDEX = %d\n", rx_ring->queue_index); pr_info("------------------------------------\n"); - pr_info("R [desc] [ PktBuf A0] [ HeadBuf DD] " - "[bi->dma ] [bi->skb] <-- Adv Rx Read format\n"); - pr_info("RWB[desc] [PcsmIpSHl PtRs] [vl er S cks ln] -----" - "----------- [bi->skb] <-- Adv Rx Write-Back format\n"); + pr_info("R [desc] [ PktBuf A0] [ HeadBuf DD] [bi->dma ] [bi->skb] <-- Adv Rx Read format\n"); + pr_info("RWB[desc] [PcsmIpSHl PtRs] [vl er S cks ln] ---------------- [bi->skb] <-- Adv Rx Write-Back format\n"); for (i = 0; i < rx_ring->count; i++) { const char *next_desc; @@ -566,8 +562,99 @@ exit: } /** - * igb_get_hw_dev - return device - * used by hardware layer to print debugging information + * igb_get_i2c_data - Reads the I2C SDA data bit + * @hw: pointer to hardware structure + * @i2cctl: Current value of I2CCTL register + * + * Returns the I2C data bit value + **/ +static int igb_get_i2c_data(void *data) +{ + struct igb_adapter *adapter = (struct igb_adapter *)data; + struct e1000_hw *hw = &adapter->hw; + s32 i2cctl = rd32(E1000_I2CPARAMS); + + return !!(i2cctl & E1000_I2C_DATA_IN); +} + +/** + * igb_set_i2c_data - Sets the I2C data bit + * @data: pointer to hardware structure + * @state: I2C data value (0 or 1) to set + * + * Sets the I2C data bit + **/ +static void igb_set_i2c_data(void *data, int state) +{ + struct igb_adapter *adapter = (struct igb_adapter *)data; + struct e1000_hw *hw = &adapter->hw; + s32 i2cctl = rd32(E1000_I2CPARAMS); + + if (state) + i2cctl |= E1000_I2C_DATA_OUT; + else + i2cctl &= ~E1000_I2C_DATA_OUT; + + i2cctl &= ~E1000_I2C_DATA_OE_N; + i2cctl |= E1000_I2C_CLK_OE_N; + wr32(E1000_I2CPARAMS, i2cctl); + wrfl(); + +} + +/** + * igb_set_i2c_clk - Sets the I2C SCL clock + * @data: pointer to hardware structure + * @state: state to set clock + * + * Sets the I2C clock line to state + **/ +static void igb_set_i2c_clk(void *data, int state) +{ + struct igb_adapter *adapter = (struct igb_adapter *)data; + struct e1000_hw *hw = &adapter->hw; + s32 i2cctl = rd32(E1000_I2CPARAMS); + + if (state) { + i2cctl |= E1000_I2C_CLK_OUT; + i2cctl &= ~E1000_I2C_CLK_OE_N; + } else { + i2cctl &= ~E1000_I2C_CLK_OUT; + i2cctl &= ~E1000_I2C_CLK_OE_N; + } + wr32(E1000_I2CPARAMS, i2cctl); + wrfl(); +} + +/** + * igb_get_i2c_clk - Gets the I2C SCL clock state + * @data: pointer to hardware structure + * + * Gets the I2C clock state + **/ +static int igb_get_i2c_clk(void *data) +{ + struct igb_adapter *adapter = (struct igb_adapter *)data; + struct e1000_hw *hw = &adapter->hw; + s32 i2cctl = rd32(E1000_I2CPARAMS); + + return !!(i2cctl & E1000_I2C_CLK_IN); +} + +static const struct i2c_algo_bit_data igb_i2c_algo = { + .setsda = igb_set_i2c_data, + .setscl = igb_set_i2c_clk, + .getsda = igb_get_i2c_data, + .getscl = igb_get_i2c_clk, + .udelay = 5, + .timeout = 20, +}; + +/** + * igb_get_hw_dev - return device + * @hw: pointer to hardware structure + * + * used by hardware layer to print debugging information **/ struct net_device *igb_get_hw_dev(struct e1000_hw *hw) { @@ -576,17 +663,17 @@ struct net_device *igb_get_hw_dev(struct e1000_hw *hw) } /** - * igb_init_module - Driver Registration Routine + * igb_init_module - Driver Registration Routine * - * igb_init_module is the first routine called when the driver is - * loaded. All it does is register with the PCI subsystem. + * igb_init_module is the first routine called when the driver is + * loaded. All it does is register with the PCI subsystem. **/ static int __init igb_init_module(void) { int ret; + pr_info("%s - version %s\n", igb_driver_string, igb_driver_version); - pr_info("%s\n", igb_copyright); #ifdef CONFIG_IGB_DCA @@ -599,10 +686,10 @@ static int __init igb_init_module(void) module_init(igb_init_module); /** - * igb_exit_module - Driver Exit Cleanup Routine + * igb_exit_module - Driver Exit Cleanup Routine * - * igb_exit_module is called just before the driver is removed - * from memory. + * igb_exit_module is called just before the driver is removed + * from memory. **/ static void __exit igb_exit_module(void) { @@ -616,11 +703,11 @@ module_exit(igb_exit_module); #define Q_IDX_82576(i) (((i & 0x1) << 3) + (i >> 1)) /** - * igb_cache_ring_register - Descriptor ring to register mapping - * @adapter: board private structure to initialize + * igb_cache_ring_register - Descriptor ring to register mapping + * @adapter: board private structure to initialize * - * Once we know the feature-set enabled for the device, we'll cache - * the register offset the descriptor ring is assigned to. + * Once we know the feature-set enabled for the device, we'll cache + * the register offset the descriptor ring is assigned to. **/ static void igb_cache_ring_register(struct igb_adapter *adapter) { @@ -637,13 +724,16 @@ static void igb_cache_ring_register(struct igb_adapter *adapter) if (adapter->vfs_allocated_count) { for (; i < adapter->rss_queues; i++) adapter->rx_ring[i]->reg_idx = rbase_offset + - Q_IDX_82576(i); + Q_IDX_82576(i); } + /* Fall through */ case e1000_82575: case e1000_82580: case e1000_i350: + case e1000_i354: case e1000_i210: case e1000_i211: + /* Fall through */ default: for (; i < adapter->num_rx_queues; i++) adapter->rx_ring[i]->reg_idx = rbase_offset + i; @@ -653,6 +743,28 @@ static void igb_cache_ring_register(struct igb_adapter *adapter) } } +u32 igb_rd32(struct e1000_hw *hw, u32 reg) +{ + struct igb_adapter *igb = container_of(hw, struct igb_adapter, hw); + u8 __iomem *hw_addr = ACCESS_ONCE(hw->hw_addr); + u32 value = 0; + + if (E1000_REMOVED(hw_addr)) + return ~value; + + value = readl(&hw_addr[reg]); + + /* reads should not return all F's */ + if (!(~value) && (!reg || !(~readl(hw_addr)))) { + struct net_device *netdev = igb->netdev; + hw->hw_addr = NULL; + netif_device_detach(netdev); + netdev_err(netdev, "PCIe link lost, device now detached\n"); + } + + return value; +} + /** * igb_write_ivar - configure ivar for given MSI-X vector * @hw: pointer to the HW structure @@ -696,21 +808,21 @@ static void igb_assign_vector(struct igb_q_vector *q_vector, int msix_vector) switch (hw->mac.type) { case e1000_82575: /* The 82575 assigns vectors using a bitmask, which matches the - bitmask for the EICR/EIMS/EIMC registers. To assign one - or more queues to a vector, we write the appropriate bits - into the MSIXBM register for that vector. */ + * bitmask for the EICR/EIMS/EIMC registers. To assign one + * or more queues to a vector, we write the appropriate bits + * into the MSIXBM register for that vector. + */ if (rx_queue > IGB_N0_QUEUE) msixbm = E1000_EICR_RX_QUEUE0 << rx_queue; if (tx_queue > IGB_N0_QUEUE) msixbm |= E1000_EICR_TX_QUEUE0 << tx_queue; - if (!adapter->msix_entries && msix_vector == 0) + if (!(adapter->flags & IGB_FLAG_HAS_MSIX) && msix_vector == 0) msixbm |= E1000_EIMS_OTHER; array_wr32(E1000_MSIXBM(0), msix_vector, msixbm); q_vector->eims_value = msixbm; break; case e1000_82576: - /* - * 82576 uses a table that essentially consists of 2 columns + /* 82576 uses a table that essentially consists of 2 columns * with 8 rows. The ordering is column-major so we use the * lower 3 bits as the row index, and the 4th bit as the * column offset. @@ -727,10 +839,10 @@ static void igb_assign_vector(struct igb_q_vector *q_vector, int msix_vector) break; case e1000_82580: case e1000_i350: + case e1000_i354: case e1000_i210: case e1000_i211: - /* - * On 82580 and newer adapters the scheme is similar to 82576 + /* On 82580 and newer adapters the scheme is similar to 82576 * however instead of ordering column-major we have things * ordered row-major. So we traverse the table by using * bit 0 as the column offset, and the remaining bits as the @@ -759,10 +871,11 @@ static void igb_assign_vector(struct igb_q_vector *q_vector, int msix_vector) } /** - * igb_configure_msix - Configure MSI-X hardware + * igb_configure_msix - Configure MSI-X hardware + * @adapter: board private structure to initialize * - * igb_configure_msix sets up the hardware to properly - * generate MSI-X interrupts. + * igb_configure_msix sets up the hardware to properly + * generate MSI-X interrupts. **/ static void igb_configure_msix(struct igb_adapter *adapter) { @@ -786,8 +899,7 @@ static void igb_configure_msix(struct igb_adapter *adapter) wr32(E1000_CTRL_EXT, tmp); /* enable msix_other interrupt */ - array_wr32(E1000_MSIXBM(0), vector++, - E1000_EIMS_OTHER); + array_wr32(E1000_MSIXBM(0), vector++, E1000_EIMS_OTHER); adapter->eims_other = E1000_EIMS_OTHER; break; @@ -795,13 +907,15 @@ static void igb_configure_msix(struct igb_adapter *adapter) case e1000_82576: case e1000_82580: case e1000_i350: + case e1000_i354: case e1000_i210: case e1000_i211: /* Turn on MSI-X capability first, or our settings - * won't stick. And it will take days to debug. */ + * won't stick. And it will take days to debug. + */ wr32(E1000_GPIE, E1000_GPIE_MSIX_MODE | - E1000_GPIE_PBA | E1000_GPIE_EIAME | - E1000_GPIE_NSICR); + E1000_GPIE_PBA | E1000_GPIE_EIAME | + E1000_GPIE_NSICR); /* enable msix_other interrupt */ adapter->eims_other = 1 << vector; @@ -823,10 +937,11 @@ static void igb_configure_msix(struct igb_adapter *adapter) } /** - * igb_request_msix - Initialize MSI-X interrupts + * igb_request_msix - Initialize MSI-X interrupts + * @adapter: board private structure to initialize * - * igb_request_msix allocates MSI-X vectors and requests interrupts from the - * kernel. + * igb_request_msix allocates MSI-X vectors and requests interrupts from the + * kernel. **/ static int igb_request_msix(struct igb_adapter *adapter) { @@ -835,7 +950,7 @@ static int igb_request_msix(struct igb_adapter *adapter) int i, err = 0, vector = 0, free_vector = 0; err = request_irq(adapter->msix_entries[vector].vector, - igb_msix_other, 0, netdev->name, adapter); + igb_msix_other, 0, netdev->name, adapter); if (err) goto err_out; @@ -859,8 +974,8 @@ static int igb_request_msix(struct igb_adapter *adapter) sprintf(q_vector->name, "%s-unused", netdev->name); err = request_irq(adapter->msix_entries[vector].vector, - igb_msix_ring, 0, q_vector->name, - q_vector); + igb_msix_ring, 0, q_vector->name, + q_vector); if (err) goto err_free; } @@ -881,53 +996,73 @@ err_out: return err; } -static void igb_reset_interrupt_capability(struct igb_adapter *adapter) +/** + * igb_free_q_vector - Free memory allocated for specific interrupt vector + * @adapter: board private structure to initialize + * @v_idx: Index of vector to be freed + * + * This function frees the memory allocated to the q_vector. + **/ +static void igb_free_q_vector(struct igb_adapter *adapter, int v_idx) { - if (adapter->msix_entries) { - pci_disable_msix(adapter->pdev); - kfree(adapter->msix_entries); - adapter->msix_entries = NULL; - } else if (adapter->flags & IGB_FLAG_HAS_MSI) { - pci_disable_msi(adapter->pdev); - } + struct igb_q_vector *q_vector = adapter->q_vector[v_idx]; + + adapter->q_vector[v_idx] = NULL; + + /* igb_get_stats64() might access the rings on this vector, + * we must wait a grace period before freeing it. + */ + kfree_rcu(q_vector, rcu); } /** - * igb_free_q_vector - Free memory allocated for specific interrupt vector - * @adapter: board private structure to initialize - * @v_idx: Index of vector to be freed + * igb_reset_q_vector - Reset config for interrupt vector + * @adapter: board private structure to initialize + * @v_idx: Index of vector to be reset * - * This function frees the memory allocated to the q_vector. In addition if - * NAPI is enabled it will delete any references to the NAPI struct prior - * to freeing the q_vector. + * If NAPI is enabled it will delete any references to the + * NAPI struct. This is preparation for igb_free_q_vector. **/ -static void igb_free_q_vector(struct igb_adapter *adapter, int v_idx) +static void igb_reset_q_vector(struct igb_adapter *adapter, int v_idx) { struct igb_q_vector *q_vector = adapter->q_vector[v_idx]; + /* Coming from igb_set_interrupt_capability, the vectors are not yet + * allocated. So, q_vector is NULL so we should stop here. + */ + if (!q_vector) + return; + if (q_vector->tx.ring) adapter->tx_ring[q_vector->tx.ring->queue_index] = NULL; if (q_vector->rx.ring) adapter->tx_ring[q_vector->rx.ring->queue_index] = NULL; - adapter->q_vector[v_idx] = NULL; netif_napi_del(&q_vector->napi); - /* - * ixgbe_get_stats64() might access the rings on this vector, - * we must wait a grace period before freeing it. - */ - kfree_rcu(q_vector, rcu); +} + +static void igb_reset_interrupt_capability(struct igb_adapter *adapter) +{ + int v_idx = adapter->num_q_vectors; + + if (adapter->flags & IGB_FLAG_HAS_MSIX) + pci_disable_msix(adapter->pdev); + else if (adapter->flags & IGB_FLAG_HAS_MSI) + pci_disable_msi(adapter->pdev); + + while (v_idx--) + igb_reset_q_vector(adapter, v_idx); } /** - * igb_free_q_vectors - Free memory allocated for interrupt vectors - * @adapter: board private structure to initialize + * igb_free_q_vectors - Free memory allocated for interrupt vectors + * @adapter: board private structure to initialize * - * This function frees the memory allocated to the q_vectors. In addition if - * NAPI is enabled it will delete any references to the NAPI struct prior - * to freeing the q_vector. + * This function frees the memory allocated to the q_vectors. In addition if + * NAPI is enabled it will delete any references to the NAPI struct prior + * to freeing the q_vector. **/ static void igb_free_q_vectors(struct igb_adapter *adapter) { @@ -937,15 +1072,18 @@ static void igb_free_q_vectors(struct igb_adapter *adapter) adapter->num_rx_queues = 0; adapter->num_q_vectors = 0; - while (v_idx--) + while (v_idx--) { + igb_reset_q_vector(adapter, v_idx); igb_free_q_vector(adapter, v_idx); + } } /** - * igb_clear_interrupt_scheme - reset the device to a state of no interrupts + * igb_clear_interrupt_scheme - reset the device to a state of no interrupts + * @adapter: board private structure to initialize * - * This function resets the device so that it has 0 rx queues, tx queues, and - * MSI-X interrupts allocated. + * This function resets the device so that it has 0 Rx queues, Tx queues, and + * MSI-X interrupts allocated. */ static void igb_clear_interrupt_scheme(struct igb_adapter *adapter) { @@ -954,10 +1092,12 @@ static void igb_clear_interrupt_scheme(struct igb_adapter *adapter) } /** - * igb_set_interrupt_capability - set MSI or MSI-X if supported + * igb_set_interrupt_capability - set MSI or MSI-X if supported + * @adapter: board private structure to initialize + * @msix: boolean value of MSIX capability * - * Attempt to configure interrupts using the best available - * capabilities of the hardware and kernel. + * Attempt to configure interrupts using the best available + * capabilities of the hardware and kernel. **/ static void igb_set_interrupt_capability(struct igb_adapter *adapter, bool msix) { @@ -966,6 +1106,7 @@ static void igb_set_interrupt_capability(struct igb_adapter *adapter, bool msix) if (!msix) goto msi_only; + adapter->flags |= IGB_FLAG_HAS_MSIX; /* Number of supported queues. */ adapter->num_rx_queues = adapter->rss_queues; @@ -974,10 +1115,10 @@ static void igb_set_interrupt_capability(struct igb_adapter *adapter, bool msix) else adapter->num_tx_queues = adapter->rss_queues; - /* start with one vector for every rx queue */ + /* start with one vector for every Rx queue */ numvecs = adapter->num_rx_queues; - /* if tx handler is separate add 1 for every tx queue */ + /* if Tx handler is separate add 1 for every Tx queue */ if (!(adapter->flags & IGB_FLAG_QUEUE_PAIRS)) numvecs += adapter->num_tx_queues; @@ -986,25 +1127,21 @@ static void igb_set_interrupt_capability(struct igb_adapter *adapter, bool msix) /* add 1 vector for link status interrupts */ numvecs++; - adapter->msix_entries = kcalloc(numvecs, sizeof(struct msix_entry), - GFP_KERNEL); - - if (!adapter->msix_entries) - goto msi_only; - for (i = 0; i < numvecs; i++) adapter->msix_entries[i].entry = i; - err = pci_enable_msix(adapter->pdev, - adapter->msix_entries, - numvecs); - if (err == 0) + err = pci_enable_msix_range(adapter->pdev, + adapter->msix_entries, + numvecs, + numvecs); + if (err > 0) return; igb_reset_interrupt_capability(adapter); /* If we can't do MSI-X, try MSI */ msi_only: + adapter->flags &= ~IGB_FLAG_HAS_MSIX; #ifdef CONFIG_PCI_IOV /* disable SR-IOV for non MSI-X configurations */ if (adapter->vf_data) { @@ -1039,16 +1176,16 @@ static void igb_add_ring(struct igb_ring *ring, } /** - * igb_alloc_q_vector - Allocate memory for a single interrupt vector - * @adapter: board private structure to initialize - * @v_count: q_vectors allocated on adapter, used for ring interleaving - * @v_idx: index of vector in adapter struct - * @txr_count: total number of Tx rings to allocate - * @txr_idx: index of first Tx ring to allocate - * @rxr_count: total number of Rx rings to allocate - * @rxr_idx: index of first Rx ring to allocate + * igb_alloc_q_vector - Allocate memory for a single interrupt vector + * @adapter: board private structure to initialize + * @v_count: q_vectors allocated on adapter, used for ring interleaving + * @v_idx: index of vector in adapter struct + * @txr_count: total number of Tx rings to allocate + * @txr_idx: index of first Tx ring to allocate + * @rxr_count: total number of Rx rings to allocate + * @rxr_idx: index of first Rx ring to allocate * - * We allocate one q_vector. If allocation fails we return -ENOMEM. + * We allocate one q_vector. If allocation fails we return -ENOMEM. **/ static int igb_alloc_q_vector(struct igb_adapter *adapter, int v_count, int v_idx, @@ -1068,7 +1205,9 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter, (sizeof(struct igb_ring) * ring_count); /* allocate q_vector and rings */ - q_vector = kzalloc(size, GFP_KERNEL); + q_vector = adapter->q_vector[v_idx]; + if (!q_vector) + q_vector = kzalloc(size, GFP_KERNEL); if (!q_vector) return -ENOMEM; @@ -1090,6 +1229,17 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter, /* initialize pointer to rings */ ring = q_vector->ring; + /* intialize ITR */ + if (rxr_count) { + /* rx or rx/tx vector */ + if (!adapter->rx_itr_setting || adapter->rx_itr_setting > 3) + q_vector->itr_val = adapter->rx_itr_setting; + } else { + /* tx only vector */ + if (!adapter->tx_itr_setting || adapter->tx_itr_setting > 3) + q_vector->itr_val = adapter->tx_itr_setting; + } + if (txr_count) { /* assign generic ring traits */ ring->dev = &adapter->pdev->dev; @@ -1109,6 +1259,9 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter, ring->count = adapter->tx_ring_count; ring->queue_index = txr_idx; + u64_stats_init(&ring->tx_syncp); + u64_stats_init(&ring->tx_syncp2); + /* assign ring to adapter */ adapter->tx_ring[txr_idx] = ring; @@ -1131,10 +1284,9 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter, if (adapter->hw.mac.type >= e1000_82576) set_bit(IGB_RING_FLAG_RX_SCTP_CSUM, &ring->flags); - /* - * On i350, i210, and i211, loopback VLAN packets + /* On i350, i354, i210, and i211, loopback VLAN packets * have the tag byte-swapped. - * */ + */ if (adapter->hw.mac.type >= e1000_i350) set_bit(IGB_RING_FLAG_RX_LB_VLAN_BSWAP, &ring->flags); @@ -1142,6 +1294,8 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter, ring->count = adapter->rx_ring_count; ring->queue_index = rxr_idx; + u64_stats_init(&ring->rx_syncp); + /* assign ring to adapter */ adapter->rx_ring[rxr_idx] = ring; } @@ -1151,11 +1305,11 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter, /** - * igb_alloc_q_vectors - Allocate memory for interrupt vectors - * @adapter: board private structure to initialize + * igb_alloc_q_vectors - Allocate memory for interrupt vectors + * @adapter: board private structure to initialize * - * We allocate one q_vector per queue interrupt. If allocation fails we - * return -ENOMEM. + * We allocate one q_vector per queue interrupt. If allocation fails we + * return -ENOMEM. **/ static int igb_alloc_q_vectors(struct igb_adapter *adapter) { @@ -1182,6 +1336,7 @@ static int igb_alloc_q_vectors(struct igb_adapter *adapter) for (; v_idx < q_vectors; v_idx++) { int rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - v_idx); int tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - v_idx); + err = igb_alloc_q_vector(adapter, q_vectors, v_idx, tqpv, txr_idx, rqpv, rxr_idx); @@ -1209,9 +1364,11 @@ err_out: } /** - * igb_init_interrupt_scheme - initialize interrupts, allocate queues/vectors + * igb_init_interrupt_scheme - initialize interrupts, allocate queues/vectors + * @adapter: board private structure to initialize + * @msix: boolean value of MSIX capability * - * This function initializes the interrupts and allocates all of the queues. + * This function initializes the interrupts and allocates all of the queues. **/ static int igb_init_interrupt_scheme(struct igb_adapter *adapter, bool msix) { @@ -1236,10 +1393,11 @@ err_alloc_q_vectors: } /** - * igb_request_irq - initialize interrupts + * igb_request_irq - initialize interrupts + * @adapter: board private structure to initialize * - * Attempts to configure interrupts using the best available - * capabilities of the hardware and kernel. + * Attempts to configure interrupts using the best available + * capabilities of the hardware and kernel. **/ static int igb_request_irq(struct igb_adapter *adapter) { @@ -1247,7 +1405,7 @@ static int igb_request_irq(struct igb_adapter *adapter) struct pci_dev *pdev = adapter->pdev; int err = 0; - if (adapter->msix_entries) { + if (adapter->flags & IGB_FLAG_HAS_MSIX) { err = igb_request_msix(adapter); if (!err) goto request_done; @@ -1291,7 +1449,7 @@ request_done: static void igb_free_irq(struct igb_adapter *adapter) { - if (adapter->msix_entries) { + if (adapter->flags & IGB_FLAG_HAS_MSIX) { int vector = 0, i; free_irq(adapter->msix_entries[vector++].vector, adapter); @@ -1305,20 +1463,20 @@ static void igb_free_irq(struct igb_adapter *adapter) } /** - * igb_irq_disable - Mask off interrupt generation on the NIC - * @adapter: board private structure + * igb_irq_disable - Mask off interrupt generation on the NIC + * @adapter: board private structure **/ static void igb_irq_disable(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; - /* - * we need to be careful when disabling interrupts. The VFs are also + /* we need to be careful when disabling interrupts. The VFs are also * mapped into these registers and so clearing the bits can cause * issues on the VF drivers so we only need to clear what we set */ - if (adapter->msix_entries) { + if (adapter->flags & IGB_FLAG_HAS_MSIX) { u32 regval = rd32(E1000_EIAM); + wr32(E1000_EIAM, regval & ~adapter->eims_enable_mask); wr32(E1000_EIMC, adapter->eims_enable_mask); regval = rd32(E1000_EIAC); @@ -1328,8 +1486,9 @@ static void igb_irq_disable(struct igb_adapter *adapter) wr32(E1000_IAM, 0); wr32(E1000_IMC, ~0); wrfl(); - if (adapter->msix_entries) { + if (adapter->flags & IGB_FLAG_HAS_MSIX) { int i; + for (i = 0; i < adapter->num_q_vectors; i++) synchronize_irq(adapter->msix_entries[i].vector); } else { @@ -1338,16 +1497,17 @@ static void igb_irq_disable(struct igb_adapter *adapter) } /** - * igb_irq_enable - Enable default interrupt generation settings - * @adapter: board private structure + * igb_irq_enable - Enable default interrupt generation settings + * @adapter: board private structure **/ static void igb_irq_enable(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; - if (adapter->msix_entries) { + if (adapter->flags & IGB_FLAG_HAS_MSIX) { u32 ims = E1000_IMS_LSC | E1000_IMS_DOUTSYNC | E1000_IMS_DRSTA; u32 regval = rd32(E1000_EIAC); + wr32(E1000_EIAC, regval | adapter->eims_enable_mask); regval = rd32(E1000_EIAM); wr32(E1000_EIAM, regval | adapter->eims_enable_mask); @@ -1388,13 +1548,12 @@ static void igb_update_mng_vlan(struct igb_adapter *adapter) } /** - * igb_release_hw_control - release control of the h/w to f/w - * @adapter: address of board private structure - * - * igb_release_hw_control resets CTRL_EXT:DRV_LOAD bit. - * For ASF and Pass Through versions of f/w this means that the - * driver is no longer loaded. + * igb_release_hw_control - release control of the h/w to f/w + * @adapter: address of board private structure * + * igb_release_hw_control resets CTRL_EXT:DRV_LOAD bit. + * For ASF and Pass Through versions of f/w this means that the + * driver is no longer loaded. **/ static void igb_release_hw_control(struct igb_adapter *adapter) { @@ -1408,13 +1567,12 @@ static void igb_release_hw_control(struct igb_adapter *adapter) } /** - * igb_get_hw_control - get control of the h/w from f/w - * @adapter: address of board private structure - * - * igb_get_hw_control sets CTRL_EXT:DRV_LOAD bit. - * For ASF and Pass Through versions of f/w this means that - * the driver is loaded. + * igb_get_hw_control - get control of the h/w from f/w + * @adapter: address of board private structure * + * igb_get_hw_control sets CTRL_EXT:DRV_LOAD bit. + * For ASF and Pass Through versions of f/w this means that + * the driver is loaded. **/ static void igb_get_hw_control(struct igb_adapter *adapter) { @@ -1428,8 +1586,8 @@ static void igb_get_hw_control(struct igb_adapter *adapter) } /** - * igb_configure - configure the hardware for RX and TX - * @adapter: private board structure + * igb_configure - configure the hardware for RX and TX + * @adapter: private board structure **/ static void igb_configure(struct igb_adapter *adapter) { @@ -1452,7 +1610,8 @@ static void igb_configure(struct igb_adapter *adapter) /* call igb_desc_unused which always leaves * at least 1 descriptor unused to make sure - * next_to_use != next_to_clean */ + * next_to_use != next_to_clean + */ for (i = 0; i < adapter->num_rx_queues; i++) { struct igb_ring *ring = adapter->rx_ring[i]; igb_alloc_rx_buffers(ring, igb_desc_unused(ring)); @@ -1460,8 +1619,8 @@ static void igb_configure(struct igb_adapter *adapter) } /** - * igb_power_up_link - Power up the phy/serdes link - * @adapter: address of board private structure + * igb_power_up_link - Power up the phy/serdes link + * @adapter: address of board private structure **/ void igb_power_up_link(struct igb_adapter *adapter) { @@ -1474,8 +1633,8 @@ void igb_power_up_link(struct igb_adapter *adapter) } /** - * igb_power_down_link - Power down the phy/serdes link - * @adapter: address of board private structure + * igb_power_down_link - Power down the phy/serdes link + * @adapter: address of board private structure */ static void igb_power_down_link(struct igb_adapter *adapter) { @@ -1486,8 +1645,75 @@ static void igb_power_down_link(struct igb_adapter *adapter) } /** - * igb_up - Open the interface and prepare it to handle traffic - * @adapter: board private structure + * Detect and switch function for Media Auto Sense + * @adapter: address of the board private structure + **/ +static void igb_check_swap_media(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 ctrl_ext, connsw; + bool swap_now = false; + + ctrl_ext = rd32(E1000_CTRL_EXT); + connsw = rd32(E1000_CONNSW); + + /* need to live swap if current media is copper and we have fiber/serdes + * to go to. + */ + + if ((hw->phy.media_type == e1000_media_type_copper) && + (!(connsw & E1000_CONNSW_AUTOSENSE_EN))) { + swap_now = true; + } else if (!(connsw & E1000_CONNSW_SERDESD)) { + /* copper signal takes time to appear */ + if (adapter->copper_tries < 4) { + adapter->copper_tries++; + connsw |= E1000_CONNSW_AUTOSENSE_CONF; + wr32(E1000_CONNSW, connsw); + return; + } else { + adapter->copper_tries = 0; + if ((connsw & E1000_CONNSW_PHYSD) && + (!(connsw & E1000_CONNSW_PHY_PDN))) { + swap_now = true; + connsw &= ~E1000_CONNSW_AUTOSENSE_CONF; + wr32(E1000_CONNSW, connsw); + } + } + } + + if (!swap_now) + return; + + switch (hw->phy.media_type) { + case e1000_media_type_copper: + netdev_info(adapter->netdev, + "MAS: changing media to fiber/serdes\n"); + ctrl_ext |= + E1000_CTRL_EXT_LINK_MODE_PCIE_SERDES; + adapter->flags |= IGB_FLAG_MEDIA_RESET; + adapter->copper_tries = 0; + break; + case e1000_media_type_internal_serdes: + case e1000_media_type_fiber: + netdev_info(adapter->netdev, + "MAS: changing media to copper\n"); + ctrl_ext &= + ~E1000_CTRL_EXT_LINK_MODE_PCIE_SERDES; + adapter->flags |= IGB_FLAG_MEDIA_RESET; + break; + default: + /* shouldn't get here during regular operation */ + netdev_err(adapter->netdev, + "AMS: Invalid media type found, returning\n"); + break; + } + wr32(E1000_CTRL_EXT, ctrl_ext); +} + +/** + * igb_up - Open the interface and prepare it to handle traffic + * @adapter: board private structure **/ int igb_up(struct igb_adapter *adapter) { @@ -1502,7 +1728,7 @@ int igb_up(struct igb_adapter *adapter) for (i = 0; i < adapter->num_q_vectors; i++) napi_enable(&(adapter->q_vector[i]->napi)); - if (adapter->msix_entries) + if (adapter->flags & IGB_FLAG_HAS_MSIX) igb_configure_msix(adapter); else igb_assign_vector(adapter->q_vector[0], 0); @@ -1514,6 +1740,7 @@ int igb_up(struct igb_adapter *adapter) /* notify VFs that reset has been completed */ if (adapter->vfs_allocated_count) { u32 reg_data = rd32(E1000_CTRL_EXT); + reg_data |= E1000_CTRL_EXT_PFRSTD; wr32(E1000_CTRL_EXT, reg_data); } @@ -1524,6 +1751,10 @@ int igb_up(struct igb_adapter *adapter) hw->mac.get_link_status = 1; schedule_work(&adapter->watchdog_task); + if ((adapter->flags & IGB_FLAG_EEE) && + (!hw->dev_spec._82575.eee_disable)) + adapter->eee_advert = MDIO_EEE_100TX | MDIO_EEE_1000T; + return 0; } @@ -1535,7 +1766,8 @@ void igb_down(struct igb_adapter *adapter) int i; /* signal that we're down so the interrupt handler does not - * reschedule our watchdog timer */ + * reschedule our watchdog timer + */ set_bit(__IGB_DOWN, &adapter->state); /* disable receives in the hardware */ @@ -1551,12 +1783,17 @@ void igb_down(struct igb_adapter *adapter) wr32(E1000_TCTL, tctl); /* flush both disables and wait for them to finish */ wrfl(); - msleep(10); + usleep_range(10000, 11000); - for (i = 0; i < adapter->num_q_vectors; i++) + igb_irq_disable(adapter); + + adapter->flags &= ~IGB_FLAG_NEED_LINK_UPDATE; + + for (i = 0; i < adapter->num_q_vectors; i++) { + napi_synchronize(&(adapter->q_vector[i]->napi)); napi_disable(&(adapter->q_vector[i]->napi)); + } - igb_irq_disable(adapter); del_timer_sync(&adapter->watchdog_timer); del_timer_sync(&adapter->phy_info_timer); @@ -1586,12 +1823,43 @@ void igb_reinit_locked(struct igb_adapter *adapter) { WARN_ON(in_interrupt()); while (test_and_set_bit(__IGB_RESETTING, &adapter->state)) - msleep(1); + usleep_range(1000, 2000); igb_down(adapter); igb_up(adapter); clear_bit(__IGB_RESETTING, &adapter->state); } +/** igb_enable_mas - Media Autosense re-enable after swap + * + * @adapter: adapter struct + **/ +static s32 igb_enable_mas(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 connsw; + s32 ret_val = 0; + + connsw = rd32(E1000_CONNSW); + if (!(hw->phy.media_type == e1000_media_type_copper)) + return ret_val; + + /* configure for SerDes media detect */ + if (!(connsw & E1000_CONNSW_SERDESD)) { + connsw |= E1000_CONNSW_ENRGSRC; + connsw |= E1000_CONNSW_AUTOSENSE_EN; + wr32(E1000_CONNSW, connsw); + wrfl(); + } else if (connsw & E1000_CONNSW_SERDESD) { + /* already SerDes, no need to enable anything */ + return ret_val; + } else { + netdev_info(adapter->netdev, + "MAS: Unable to configure feature, disabling..\n"); + adapter->flags &= ~IGB_FLAG_MAS_ENABLE; + } + return ret_val; +} + void igb_reset(struct igb_adapter *adapter) { struct pci_dev *pdev = adapter->pdev; @@ -1605,6 +1873,7 @@ void igb_reset(struct igb_adapter *adapter) */ switch (mac->type) { case e1000_i350: + case e1000_i354: case e1000_82580: pba = rd32(E1000_RXPBS); pba = igb_rxpbs_adjust_82580(pba); @@ -1631,14 +1900,16 @@ void igb_reset(struct igb_adapter *adapter) * rounded up to the next 1KB and expressed in KB. Likewise, * the Rx FIFO should be large enough to accommodate at least * one full receive packet and is similarly rounded up and - * expressed in KB. */ + * expressed in KB. + */ pba = rd32(E1000_PBA); /* upper 16 bits has Tx packet buffer allocation size in KB */ tx_space = pba >> 16; /* lower 16 bits has Rx packet buffer allocation size in KB */ pba &= 0xffff; - /* the tx fifo also stores 16 bytes of information about the tx - * but don't include ethernet FCS because hardware appends it */ + /* the Tx fifo also stores 16 bytes of information about the Tx + * but don't include ethernet FCS because hardware appends it + */ min_tx_space = (adapter->max_frame_size + sizeof(union e1000_adv_tx_desc) - ETH_FCS_LEN) * 2; @@ -1651,13 +1922,15 @@ void igb_reset(struct igb_adapter *adapter) /* 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 */ + * allocation, take space away from current Rx allocation + */ if (tx_space < min_tx_space && ((min_tx_space - tx_space) < pba)) { pba = pba - (min_tx_space - tx_space); - /* if short on rx space, rx wins and must trump tx - * adjustment */ + /* if short on Rx space, Rx wins and must trump Tx + * adjustment + */ if (pba < min_rx_space) pba = min_rx_space; } @@ -1669,7 +1942,8 @@ void igb_reset(struct igb_adapter *adapter) * (or the size used for early receive) above it in the Rx FIFO. * Set it to the lower of: * - 90% of the Rx FIFO size, or - * - the full Rx FIFO size minus one full frame */ + * - the full Rx FIFO size minus one full frame + */ hwm = min(((pba << 10) * 9 / 10), ((pba << 10) - 2 * adapter->max_frame_size)); @@ -1682,6 +1956,7 @@ void igb_reset(struct igb_adapter *adapter) /* disable receive for all VFs and wait one second */ if (adapter->vfs_allocated_count) { int i; + for (i = 0 ; i < adapter->vfs_allocated_count; i++) adapter->vf_data[i].flags &= IGB_VF_FLAG_PF_SET_MAC; @@ -1697,17 +1972,53 @@ void igb_reset(struct igb_adapter *adapter) hw->mac.ops.reset_hw(hw); wr32(E1000_WUC, 0); + if (adapter->flags & IGB_FLAG_MEDIA_RESET) { + /* need to resetup here after media swap */ + adapter->ei.get_invariants(hw); + adapter->flags &= ~IGB_FLAG_MEDIA_RESET; + } + if (adapter->flags & IGB_FLAG_MAS_ENABLE) { + if (igb_enable_mas(adapter)) + dev_err(&pdev->dev, + "Error enabling Media Auto Sense\n"); + } if (hw->mac.ops.init_hw(hw)) dev_err(&pdev->dev, "Hardware Error\n"); - /* - * Flow control settings reset on hardware reset, so guarantee flow + /* Flow control settings reset on hardware reset, so guarantee flow * control is off when forcing speed. */ if (!hw->mac.autoneg) igb_force_mac_fc(hw); igb_init_dmac(adapter, pba); +#ifdef CONFIG_IGB_HWMON + /* Re-initialize the thermal sensor on i350 devices. */ + if (!test_bit(__IGB_DOWN, &adapter->state)) { + if (mac->type == e1000_i350 && hw->bus.func == 0) { + /* If present, re-initialize the external thermal sensor + * interface. + */ + if (adapter->ets) + mac->ops.init_thermal_sensor_thresh(hw); + } + } +#endif + /* Re-establish EEE setting */ + if (hw->phy.media_type == e1000_media_type_copper) { + switch (mac->type) { + case e1000_i350: + case e1000_i210: + case e1000_i211: + igb_set_eee_i350(hw); + break; + case e1000_i354: + igb_set_eee_i354(hw); + break; + default: + break; + } + } if (!netif_running(adapter->netdev)) igb_power_down_link(adapter); @@ -1725,14 +2036,13 @@ void igb_reset(struct igb_adapter *adapter) static netdev_features_t igb_fix_features(struct net_device *netdev, netdev_features_t features) { - /* - * Since there is no support for separate rx/tx vlan accel - * enable/disable make sure tx flag is always in same state as rx. + /* Since there is no support for separate Rx/Tx vlan accel + * enable/disable make sure Tx flag is always in same state as Rx. */ - if (features & NETIF_F_HW_VLAN_RX) - features |= NETIF_F_HW_VLAN_TX; + if (features & NETIF_F_HW_VLAN_CTAG_RX) + features |= NETIF_F_HW_VLAN_CTAG_TX; else - features &= ~NETIF_F_HW_VLAN_TX; + features &= ~NETIF_F_HW_VLAN_CTAG_TX; return features; } @@ -1743,7 +2053,7 @@ static int igb_set_features(struct net_device *netdev, netdev_features_t changed = netdev->features ^ features; struct igb_adapter *adapter = netdev_priv(netdev); - if (changed & NETIF_F_HW_VLAN_RX) + if (changed & NETIF_F_HW_VLAN_CTAG_RX) igb_vlan_mode(netdev, features); if (!(changed & NETIF_F_RXALL)) @@ -1774,7 +2084,8 @@ static const struct net_device_ops igb_netdev_ops = { .ndo_vlan_rx_kill_vid = igb_vlan_rx_kill_vid, .ndo_set_vf_mac = igb_ndo_set_vf_mac, .ndo_set_vf_vlan = igb_ndo_set_vf_vlan, - .ndo_set_vf_tx_rate = igb_ndo_set_vf_bw, + .ndo_set_vf_rate = igb_ndo_set_vf_bw, + .ndo_set_vf_spoofchk = igb_ndo_set_vf_spoofchk, .ndo_get_vf_config = igb_ndo_get_vf_config, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = igb_netpoll, @@ -1786,7 +2097,6 @@ static const struct net_device_ops igb_netdev_ops = { /** * igb_set_fw_version - Configure version string for ethtool * @adapter: adapter struct - * **/ void igb_set_fw_version(struct igb_adapter *adapter) { @@ -1796,12 +2106,17 @@ void igb_set_fw_version(struct igb_adapter *adapter) igb_get_fw_version(hw, &fw); switch (hw->mac.type) { + case e1000_i210: case e1000_i211: - snprintf(adapter->fw_version, sizeof(adapter->fw_version), - "%2d.%2d-%d", - fw.invm_major, fw.invm_minor, fw.invm_img_type); - break; - + if (!(igb_get_flash_presence_i210(hw))) { + snprintf(adapter->fw_version, + sizeof(adapter->fw_version), + "%2d.%2d-%d", + fw.invm_major, fw.invm_minor, + fw.invm_img_type); + break; + } + /* fall through */ default: /* if option is rom valid, display its version too */ if (fw.or_valid) { @@ -1811,27 +2126,110 @@ void igb_set_fw_version(struct igb_adapter *adapter) fw.eep_major, fw.eep_minor, fw.etrack_id, fw.or_major, fw.or_build, fw.or_patch); /* no option rom */ - } else { + } else if (fw.etrack_id != 0X0000) { snprintf(adapter->fw_version, - sizeof(adapter->fw_version), - "%d.%d, 0x%08x", - fw.eep_major, fw.eep_minor, fw.etrack_id); + sizeof(adapter->fw_version), + "%d.%d, 0x%08x", + fw.eep_major, fw.eep_minor, fw.etrack_id); + } else { + snprintf(adapter->fw_version, + sizeof(adapter->fw_version), + "%d.%d.%d", + fw.eep_major, fw.eep_minor, fw.eep_build); } break; } - return; } /** - * igb_probe - Device Initialization Routine - * @pdev: PCI device information struct - * @ent: entry in igb_pci_tbl + * igb_init_mas - init Media Autosense feature if enabled in the NVM + * + * @adapter: adapter struct + **/ +static void igb_init_mas(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u16 eeprom_data; + + hw->nvm.ops.read(hw, NVM_COMPAT, 1, &eeprom_data); + switch (hw->bus.func) { + case E1000_FUNC_0: + if (eeprom_data & IGB_MAS_ENABLE_0) { + adapter->flags |= IGB_FLAG_MAS_ENABLE; + netdev_info(adapter->netdev, + "MAS: Enabling Media Autosense for port %d\n", + hw->bus.func); + } + break; + case E1000_FUNC_1: + if (eeprom_data & IGB_MAS_ENABLE_1) { + adapter->flags |= IGB_FLAG_MAS_ENABLE; + netdev_info(adapter->netdev, + "MAS: Enabling Media Autosense for port %d\n", + hw->bus.func); + } + break; + case E1000_FUNC_2: + if (eeprom_data & IGB_MAS_ENABLE_2) { + adapter->flags |= IGB_FLAG_MAS_ENABLE; + netdev_info(adapter->netdev, + "MAS: Enabling Media Autosense for port %d\n", + hw->bus.func); + } + break; + case E1000_FUNC_3: + if (eeprom_data & IGB_MAS_ENABLE_3) { + adapter->flags |= IGB_FLAG_MAS_ENABLE; + netdev_info(adapter->netdev, + "MAS: Enabling Media Autosense for port %d\n", + hw->bus.func); + } + break; + default: + /* Shouldn't get here */ + netdev_err(adapter->netdev, + "MAS: Invalid port configuration, returning\n"); + break; + } +} + +/** + * igb_init_i2c - Init I2C interface + * @adapter: pointer to adapter structure + **/ +static s32 igb_init_i2c(struct igb_adapter *adapter) +{ + s32 status = 0; + + /* I2C interface supported on i350 devices */ + if (adapter->hw.mac.type != e1000_i350) + return 0; + + /* Initialize the i2c bus which is controlled by the registers. + * This bus will use the i2c_algo_bit structue that implements + * the protocol through toggling of the 4 bits in the register. + */ + adapter->i2c_adap.owner = THIS_MODULE; + adapter->i2c_algo = igb_i2c_algo; + adapter->i2c_algo.data = adapter; + adapter->i2c_adap.algo_data = &adapter->i2c_algo; + adapter->i2c_adap.dev.parent = &adapter->pdev->dev; + strlcpy(adapter->i2c_adap.name, "igb BB", + sizeof(adapter->i2c_adap.name)); + status = i2c_bit_add_bus(&adapter->i2c_adap); + return status; +} + +/** + * igb_probe - Device Initialization Routine + * @pdev: PCI device information struct + * @ent: entry in igb_pci_tbl * - * Returns 0 on success, negative on failure + * Returns 0 on success, negative on failure * - * igb_probe initializes an adapter identified by a pci_dev structure. - * The OS initialization, configuring of the adapter private structure, - * and a hardware reset occur. + * igb_probe initializes an adapter identified by a pci_dev structure. + * The OS initialization, configuring of the adapter private structure, + * and a hardware reset occur. **/ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { @@ -1842,7 +2240,6 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) s32 ret_val; static int global_quad_port_a; /* global quad port a indication */ const struct e1000_info *ei = igb_info_tbl[ent->driver_data]; - unsigned long mmio_start, mmio_len; int err, pci_using_dac; u8 part_str[E1000_PBANUM_LENGTH]; @@ -1860,26 +2257,21 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) 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; } } err = pci_request_selected_regions(pdev, pci_select_bars(pdev, - IORESOURCE_MEM), - igb_driver_name); + IORESOURCE_MEM), + igb_driver_name); if (err) goto err_pci_reg; @@ -1904,11 +2296,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->back = adapter; adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE); - mmio_start = pci_resource_start(pdev, 0); - mmio_len = pci_resource_len(pdev, 0); - err = -EIO; - hw->hw_addr = ioremap(mmio_start, mmio_len); + hw->hw_addr = pci_iomap(pdev, 0, 0); if (!hw->hw_addr) goto err_ioremap; @@ -1918,8 +2307,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) strncpy(netdev->name, pci_name(pdev), sizeof(netdev->name) - 1); - netdev->mem_start = mmio_start; - netdev->mem_end = mmio_start + mmio_len; + netdev->mem_start = pci_resource_start(pdev, 0); + netdev->mem_end = pci_resource_end(pdev, 0); /* PCI config space info */ hw->vendor_id = pdev->vendor; @@ -1957,8 +2346,7 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_info(&pdev->dev, "PHY reset is blocked due to SOL/IDER session.\n"); - /* - * features is initialized to 0 in allocation, it might have bits + /* features is initialized to 0 in allocation, it might have bits * set by igb_sw_init so we should use an or instead of an * assignment. */ @@ -1969,15 +2357,15 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) NETIF_F_TSO6 | NETIF_F_RXHASH | NETIF_F_RXCSUM | - NETIF_F_HW_VLAN_RX | - NETIF_F_HW_VLAN_TX; + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_TX; /* copy netdev features into list of user selectable features */ netdev->hw_features |= netdev->features; netdev->hw_features |= NETIF_F_RXALL; /* set this bit last since it cannot be part of hw_features */ - netdev->features |= NETIF_F_HW_VLAN_FILTER; + netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; netdev->vlan_features |= NETIF_F_TSO | NETIF_F_TSO6 | @@ -2002,19 +2390,32 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) adapter->en_mng_pt = igb_enable_mng_pass_thru(hw); /* before reading the NVM, reset the controller to put the device in a - * known good starting state */ + * known good starting state + */ hw->mac.ops.reset_hw(hw); - /* - * make sure the NVM is good , i211 parts have special NVM that - * doesn't contain a checksum + /* make sure the NVM is good , i211/i210 parts can have special NVM + * that doesn't contain a checksum */ - if (hw->mac.type != e1000_i211) { + switch (hw->mac.type) { + case e1000_i210: + case e1000_i211: + if (igb_get_flash_presence_i210(hw)) { + if (hw->nvm.ops.validate(hw) < 0) { + dev_err(&pdev->dev, + "The NVM Checksum Is Not Valid\n"); + err = -EIO; + goto err_eeprom; + } + } + break; + default: if (hw->nvm.ops.validate(hw) < 0) { dev_err(&pdev->dev, "The NVM Checksum Is Not Valid\n"); err = -EIO; goto err_eeprom; } + break; } /* copy the MAC address out of the NVM */ @@ -2022,9 +2423,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_err(&pdev->dev, "NVM Read Error\n"); memcpy(netdev->dev_addr, hw->mac.addr, netdev->addr_len); - memcpy(netdev->perm_addr, hw->mac.addr, netdev->addr_len); - if (!is_valid_ether_addr(netdev->perm_addr)) { + if (!is_valid_ether_addr(netdev->dev_addr)) { dev_err(&pdev->dev, "Invalid MAC Address\n"); err = -EIO; goto err_eeprom; @@ -2033,10 +2433,16 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* get firmware version for ethtool -i */ igb_set_fw_version(adapter); + /* configure RXPBSIZE and TXPBSIZE */ + if (hw->mac.type == e1000_i210) { + wr32(E1000_RXPBS, I210_RXPBSIZE_DEFAULT); + wr32(E1000_TXPBS, I210_TXPBSIZE_DEFAULT); + } + setup_timer(&adapter->watchdog_timer, igb_watchdog, - (unsigned long) adapter); + (unsigned long) adapter); setup_timer(&adapter->phy_info_timer, igb_update_phy_info, - (unsigned long) adapter); + (unsigned long) adapter); INIT_WORK(&adapter->reset_task, igb_reset_task); INIT_WORK(&adapter->watchdog_task, igb_watchdog_task); @@ -2058,8 +2464,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Check the NVM for wake support on non-port A ports */ if (hw->mac.type >= e1000_82580) hw->nvm.ops.read(hw, NVM_INIT_CONTROL3_PORT_A + - NVM_82580_LAN_FUNC_OFFSET(hw->bus.func), 1, - &eeprom_data); + NVM_82580_LAN_FUNC_OFFSET(hw->bus.func), 1, + &eeprom_data); else if (hw->bus.func == 1) hw->nvm.ops.read(hw, NVM_INIT_CONTROL3_PORT_B, 1, &eeprom_data); @@ -2068,7 +2474,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* 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 */ + * lan on a particular port + */ switch (pdev->device) { case E1000_DEV_ID_82575GB_QUAD_COPPER: adapter->flags &= ~IGB_FLAG_WOL_SUPPORTED; @@ -2077,7 +2484,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) case E1000_DEV_ID_82576_FIBER: case E1000_DEV_ID_82576_SERDES: /* Wake events only supported on port A for dual fiber - * regardless of eeprom setting */ + * regardless of eeprom setting + */ if (rd32(E1000_STATUS) & E1000_STATUS_FUNC_1) adapter->flags &= ~IGB_FLAG_WOL_SUPPORTED; break; @@ -2115,8 +2523,16 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* reset the hardware with the new settings */ igb_reset(adapter); + /* Init the I2C interface */ + err = igb_init_i2c(adapter); + if (err) { + dev_err(&pdev->dev, "failed to init i2c interface\n"); + goto err_eeprom; + } + /* let the f/w know that the h/w is now under the control of the - * driver. */ + * driver. + */ igb_get_hw_control(adapter); strcpy(netdev->name, "eth%d"); @@ -2135,47 +2551,102 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) } #endif +#ifdef CONFIG_IGB_HWMON + /* Initialize the thermal sensor on i350 devices. */ + if (hw->mac.type == e1000_i350 && hw->bus.func == 0) { + u16 ets_word; + + /* Read the NVM to determine if this i350 device supports an + * external thermal sensor. + */ + hw->nvm.ops.read(hw, NVM_ETS_CFG, 1, &ets_word); + if (ets_word != 0x0000 && ets_word != 0xFFFF) + adapter->ets = true; + else + adapter->ets = false; + if (igb_sysfs_init(adapter)) + dev_err(&pdev->dev, + "failed to allocate sysfs resources\n"); + } else { + adapter->ets = false; + } +#endif + /* Check if Media Autosense is enabled */ + adapter->ei = *ei; + if (hw->dev_spec._82575.mas_capable) + igb_init_mas(adapter); /* do hw tstamp init after resetting */ igb_ptp_init(adapter); dev_info(&pdev->dev, "Intel(R) Gigabit Ethernet Network Connection\n"); - /* print bus type/speed/width info */ - dev_info(&pdev->dev, "%s: (PCIe:%s:%s) %pM\n", - netdev->name, - ((hw->bus.speed == e1000_bus_speed_2500) ? "2.5Gb/s" : - (hw->bus.speed == e1000_bus_speed_5000) ? "5.0Gb/s" : - "unknown"), - ((hw->bus.width == e1000_bus_width_pcie_x4) ? "Width x4" : - (hw->bus.width == e1000_bus_width_pcie_x2) ? "Width x2" : - (hw->bus.width == e1000_bus_width_pcie_x1) ? "Width x1" : - "unknown"), - netdev->dev_addr); - - ret_val = igb_read_part_string(hw, part_str, E1000_PBANUM_LENGTH); + /* print bus type/speed/width info, not applicable to i354 */ + if (hw->mac.type != e1000_i354) { + dev_info(&pdev->dev, "%s: (PCIe:%s:%s) %pM\n", + netdev->name, + ((hw->bus.speed == e1000_bus_speed_2500) ? "2.5Gb/s" : + (hw->bus.speed == e1000_bus_speed_5000) ? "5.0Gb/s" : + "unknown"), + ((hw->bus.width == e1000_bus_width_pcie_x4) ? + "Width x4" : + (hw->bus.width == e1000_bus_width_pcie_x2) ? + "Width x2" : + (hw->bus.width == e1000_bus_width_pcie_x1) ? + "Width x1" : "unknown"), netdev->dev_addr); + } + + if ((hw->mac.type >= e1000_i210 || + igb_get_flash_presence_i210(hw))) { + ret_val = igb_read_part_string(hw, part_str, + E1000_PBANUM_LENGTH); + } else { + ret_val = -E1000_ERR_INVM_VALUE_NOT_FOUND; + } + if (ret_val) strcpy(part_str, "Unknown"); dev_info(&pdev->dev, "%s: PBA No: %s\n", netdev->name, part_str); dev_info(&pdev->dev, "Using %s interrupts. %d rx queue(s), %d tx queue(s)\n", - adapter->msix_entries ? "MSI-X" : + (adapter->flags & IGB_FLAG_HAS_MSIX) ? "MSI-X" : (adapter->flags & IGB_FLAG_HAS_MSI) ? "MSI" : "legacy", adapter->num_rx_queues, adapter->num_tx_queues); - switch (hw->mac.type) { - case e1000_i350: - case e1000_i210: - case e1000_i211: - igb_set_eee_i350(hw); - break; - default: - break; + if (hw->phy.media_type == e1000_media_type_copper) { + switch (hw->mac.type) { + case e1000_i350: + case e1000_i210: + case e1000_i211: + /* Enable EEE for internal copper PHY devices */ + err = igb_set_eee_i350(hw); + if ((!err) && + (!hw->dev_spec._82575.eee_disable)) { + adapter->eee_advert = + MDIO_EEE_100TX | MDIO_EEE_1000T; + adapter->flags |= IGB_FLAG_EEE; + } + break; + case e1000_i354: + if ((rd32(E1000_CTRL_EXT) & + E1000_CTRL_EXT_LINK_MODE_SGMII)) { + err = igb_set_eee_i354(hw); + if ((!err) && + (!hw->dev_spec._82575.eee_disable)) { + adapter->eee_advert = + MDIO_EEE_100TX | MDIO_EEE_1000T; + adapter->flags |= IGB_FLAG_EEE; + } + } + break; + default: + break; + } } - pm_runtime_put_noidle(&pdev->dev); return 0; err_register: igb_release_hw_control(adapter); + memset(&adapter->i2c_adap, 0, sizeof(adapter->i2c_adap)); err_eeprom: if (!igb_check_reset_block(hw)) igb_reset_phy(hw); @@ -2184,26 +2655,128 @@ err_eeprom: iounmap(hw->flash_address); err_sw_init: igb_clear_interrupt_scheme(adapter); - iounmap(hw->hw_addr); + pci_iounmap(pdev, hw->hw_addr); err_ioremap: free_netdev(netdev); err_alloc_etherdev: pci_release_selected_regions(pdev, - pci_select_bars(pdev, IORESOURCE_MEM)); + pci_select_bars(pdev, IORESOURCE_MEM)); err_pci_reg: err_dma: pci_disable_device(pdev); return err; } +#ifdef CONFIG_PCI_IOV +static int igb_disable_sriov(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + + /* reclaim resources allocated to VFs */ + if (adapter->vf_data) { + /* disable iov and allow time for transactions to clear */ + if (pci_vfs_assigned(pdev)) { + dev_warn(&pdev->dev, + "Cannot deallocate SR-IOV virtual functions while they are assigned - VFs will not be deallocated\n"); + return -EPERM; + } else { + pci_disable_sriov(pdev); + msleep(500); + } + + kfree(adapter->vf_data); + adapter->vf_data = NULL; + adapter->vfs_allocated_count = 0; + wr32(E1000_IOVCTL, E1000_IOVCTL_REUSE_VFQ); + wrfl(); + msleep(100); + dev_info(&pdev->dev, "IOV Disabled\n"); + + /* Re-enable DMA Coalescing flag since IOV is turned off */ + adapter->flags |= IGB_FLAG_DMAC; + } + + return 0; +} + +static int igb_enable_sriov(struct pci_dev *pdev, int num_vfs) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct igb_adapter *adapter = netdev_priv(netdev); + int old_vfs = pci_num_vf(pdev); + int err = 0; + int i; + + if (!(adapter->flags & IGB_FLAG_HAS_MSIX) || num_vfs > 7) { + err = -EPERM; + goto out; + } + if (!num_vfs) + goto out; + + if (old_vfs) { + dev_info(&pdev->dev, "%d pre-allocated VFs found - override max_vfs setting of %d\n", + old_vfs, max_vfs); + adapter->vfs_allocated_count = old_vfs; + } else + adapter->vfs_allocated_count = num_vfs; + + adapter->vf_data = kcalloc(adapter->vfs_allocated_count, + sizeof(struct vf_data_storage), GFP_KERNEL); + + /* if allocation failed then we do not support SR-IOV */ + if (!adapter->vf_data) { + adapter->vfs_allocated_count = 0; + dev_err(&pdev->dev, + "Unable to allocate memory for VF Data Storage\n"); + err = -ENOMEM; + goto out; + } + + /* only call pci_enable_sriov() if no VFs are allocated already */ + if (!old_vfs) { + err = pci_enable_sriov(pdev, adapter->vfs_allocated_count); + if (err) + goto err_out; + } + dev_info(&pdev->dev, "%d VFs allocated\n", + adapter->vfs_allocated_count); + for (i = 0; i < adapter->vfs_allocated_count; i++) + igb_vf_configure(adapter, i); + + /* DMA Coalescing is not supported in IOV mode. */ + adapter->flags &= ~IGB_FLAG_DMAC; + goto out; + +err_out: + kfree(adapter->vf_data); + adapter->vf_data = NULL; + adapter->vfs_allocated_count = 0; +out: + return err; +} + +#endif +/** + * igb_remove_i2c - Cleanup I2C interface + * @adapter: pointer to adapter structure + **/ +static void igb_remove_i2c(struct igb_adapter *adapter) +{ + /* free the adapter bus structure */ + i2c_del_adapter(&adapter->i2c_adap); +} + /** - * igb_remove - Device Removal Routine - * @pdev: PCI device information struct + * igb_remove - Device Removal Routine + * @pdev: PCI device information struct * - * igb_remove is called by the PCI subsystem to alert the driver - * that it should release a PCI device. The could be caused by a - * Hot-Plug event, or because the driver is going to be removed from - * memory. + * igb_remove is called by the PCI subsystem to alert the driver + * that it should release a PCI device. The could be caused by a + * Hot-Plug event, or because the driver is going to be removed from + * memory. **/ static void igb_remove(struct pci_dev *pdev) { @@ -2212,10 +2785,12 @@ static void igb_remove(struct pci_dev *pdev) struct e1000_hw *hw = &adapter->hw; pm_runtime_get_noresume(&pdev->dev); +#ifdef CONFIG_IGB_HWMON + igb_sysfs_exit(adapter); +#endif + igb_remove_i2c(adapter); igb_ptp_stop(adapter); - - /* - * The watchdog timer may be rescheduled, so explicitly + /* The watchdog timer may be rescheduled, so explicitly * disable watchdog from being rescheduled. */ set_bit(__IGB_DOWN, &adapter->state); @@ -2235,7 +2810,8 @@ static void igb_remove(struct pci_dev *pdev) #endif /* Release control of h/w to f/w. If f/w is AMT enabled, this - * would have already happened in close and is redundant. */ + * would have already happened in close and is redundant. + */ igb_release_hw_control(adapter); unregister_netdev(netdev); @@ -2243,30 +2819,14 @@ static void igb_remove(struct pci_dev *pdev) igb_clear_interrupt_scheme(adapter); #ifdef CONFIG_PCI_IOV - /* reclaim resources allocated to VFs */ - if (adapter->vf_data) { - /* disable iov and allow time for transactions to clear */ - if (igb_vfs_are_assigned(adapter)) { - dev_info(&pdev->dev, "Unloading driver while VFs are assigned - VFs will not be deallocated\n"); - } else { - pci_disable_sriov(pdev); - msleep(500); - } - - kfree(adapter->vf_data); - adapter->vf_data = NULL; - wr32(E1000_IOVCTL, E1000_IOVCTL_REUSE_VFQ); - wrfl(); - msleep(100); - dev_info(&pdev->dev, "IOV Disabled\n"); - } + igb_disable_sriov(pdev); #endif - iounmap(hw->hw_addr); + pci_iounmap(pdev, hw->hw_addr); if (hw->flash_address) iounmap(hw->flash_address); pci_release_selected_regions(pdev, - pci_select_bars(pdev, IORESOURCE_MEM)); + pci_select_bars(pdev, IORESOURCE_MEM)); kfree(adapter->shadow_vfta); free_netdev(netdev); @@ -2277,116 +2837,35 @@ static void igb_remove(struct pci_dev *pdev) } /** - * igb_probe_vfs - Initialize vf data storage and add VFs to pci config space - * @adapter: board private structure to initialize + * igb_probe_vfs - Initialize vf data storage and add VFs to pci config space + * @adapter: board private structure to initialize * - * This function initializes the vf specific data storage and then attempts to - * allocate the VFs. The reason for ordering it this way is because it is much - * mor expensive time wise to disable SR-IOV than it is to allocate and free - * the memory for the VFs. + * This function initializes the vf specific data storage and then attempts to + * allocate the VFs. The reason for ordering it this way is because it is much + * mor expensive time wise to disable SR-IOV than it is to allocate and free + * the memory for the VFs. **/ static void igb_probe_vfs(struct igb_adapter *adapter) { #ifdef CONFIG_PCI_IOV struct pci_dev *pdev = adapter->pdev; struct e1000_hw *hw = &adapter->hw; - int old_vfs = pci_num_vf(adapter->pdev); - int i; /* Virtualization features not supported on i210 family. */ if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211)) return; - if (old_vfs) { - dev_info(&pdev->dev, "%d pre-allocated VFs found - override " - "max_vfs setting of %d\n", old_vfs, max_vfs); - adapter->vfs_allocated_count = old_vfs; - } - - if (!adapter->vfs_allocated_count) - return; - - adapter->vf_data = kcalloc(adapter->vfs_allocated_count, - sizeof(struct vf_data_storage), GFP_KERNEL); - - /* if allocation failed then we do not support SR-IOV */ - if (!adapter->vf_data) { - adapter->vfs_allocated_count = 0; - dev_err(&pdev->dev, "Unable to allocate memory for VF " - "Data Storage\n"); - goto out; - } - - if (!old_vfs) { - if (pci_enable_sriov(pdev, adapter->vfs_allocated_count)) - goto err_out; - } - dev_info(&pdev->dev, "%d VFs allocated\n", - adapter->vfs_allocated_count); - for (i = 0; i < adapter->vfs_allocated_count; i++) - igb_vf_configure(adapter, i); + pci_sriov_set_totalvfs(pdev, 7); + igb_pci_enable_sriov(pdev, max_vfs); - /* DMA Coalescing is not supported in IOV mode. */ - adapter->flags &= ~IGB_FLAG_DMAC; - goto out; -err_out: - kfree(adapter->vf_data); - adapter->vf_data = NULL; - adapter->vfs_allocated_count = 0; -out: - return; #endif /* CONFIG_PCI_IOV */ } -/** - * igb_sw_init - Initialize general software structures (struct igb_adapter) - * @adapter: board private structure to initialize - * - * igb_sw_init initializes the Adapter private data structure. - * Fields are initialized based on PCI device information and - * OS network device settings (MTU size). - **/ -static int igb_sw_init(struct igb_adapter *adapter) +static void igb_init_queue_configuration(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; - struct net_device *netdev = adapter->netdev; - struct pci_dev *pdev = adapter->pdev; u32 max_rss_queues; - pci_read_config_word(pdev, PCI_COMMAND, &hw->bus.pci_cmd_word); - - /* set default ring sizes */ - adapter->tx_ring_count = IGB_DEFAULT_TXD; - adapter->rx_ring_count = IGB_DEFAULT_RXD; - - /* set default ITR values */ - adapter->rx_itr_setting = IGB_DEFAULT_ITR; - adapter->tx_itr_setting = IGB_DEFAULT_ITR; - - /* set default work limits */ - adapter->tx_work_limit = IGB_DEFAULT_TX_WORK; - - adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN + - VLAN_HLEN; - adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN; - - spin_lock_init(&adapter->stats64_lock); -#ifdef CONFIG_PCI_IOV - switch (hw->mac.type) { - case e1000_82576: - case e1000_i350: - if (max_vfs > 7) { - dev_warn(&pdev->dev, - "Maximum of 7 VFs per PF, using max\n"); - adapter->vfs_allocated_count = 7; - } else - adapter->vfs_allocated_count = max_vfs; - break; - default: - break; - } -#endif /* CONFIG_PCI_IOV */ - /* Determine the maximum number of RSS queues supported. */ switch (hw->mac.type) { case e1000_i211: @@ -2410,6 +2889,7 @@ static int igb_sw_init(struct igb_adapter *adapter) } /* fall through */ case e1000_82580: + case e1000_i354: default: max_rss_queues = IGB_MAX_RX_QUEUES; break; @@ -2424,8 +2904,7 @@ static int igb_sw_init(struct igb_adapter *adapter) /* Device supports enough interrupts without queue pairing. */ break; case e1000_82576: - /* - * If VFs are going to be allocated with RSS queues then we + /* If VFs are going to be allocated with RSS queues then we * should pair the queues in order to conserve interrupts due * to limited supply. */ @@ -2435,21 +2914,74 @@ static int igb_sw_init(struct igb_adapter *adapter) /* fall through */ case e1000_82580: case e1000_i350: + case e1000_i354: case e1000_i210: default: - /* - * If rss_queues > half of max_rss_queues, pair the queues in + /* If rss_queues > half of max_rss_queues, pair the queues in * order to conserve interrupts due to limited supply. */ if (adapter->rss_queues > (max_rss_queues / 2)) adapter->flags |= IGB_FLAG_QUEUE_PAIRS; break; } +} + +/** + * igb_sw_init - Initialize general software structures (struct igb_adapter) + * @adapter: board private structure to initialize + * + * igb_sw_init initializes the Adapter private data structure. + * Fields are initialized based on PCI device information and + * OS network device settings (MTU size). + **/ +static int igb_sw_init(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; + struct pci_dev *pdev = adapter->pdev; + + pci_read_config_word(pdev, PCI_COMMAND, &hw->bus.pci_cmd_word); + + /* set default ring sizes */ + adapter->tx_ring_count = IGB_DEFAULT_TXD; + adapter->rx_ring_count = IGB_DEFAULT_RXD; + + /* set default ITR values */ + adapter->rx_itr_setting = IGB_DEFAULT_ITR; + adapter->tx_itr_setting = IGB_DEFAULT_ITR; + + /* set default work limits */ + adapter->tx_work_limit = IGB_DEFAULT_TX_WORK; + + adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN + + VLAN_HLEN; + adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN; + + spin_lock_init(&adapter->stats64_lock); +#ifdef CONFIG_PCI_IOV + switch (hw->mac.type) { + case e1000_82576: + case e1000_i350: + if (max_vfs > 7) { + dev_warn(&pdev->dev, + "Maximum of 7 VFs per PF, using max\n"); + max_vfs = adapter->vfs_allocated_count = 7; + } else + adapter->vfs_allocated_count = max_vfs; + if (adapter->vfs_allocated_count) + dev_warn(&pdev->dev, + "Enabling SR-IOV VFs using the module parameter is deprecated - please use the pci sysfs interface.\n"); + break; + default: + break; + } +#endif /* CONFIG_PCI_IOV */ + + igb_init_queue_configuration(adapter); /* Setup and initialize a copy of the hw vlan table array */ - adapter->shadow_vfta = kzalloc(sizeof(u32) * - E1000_VLAN_FILTER_TBL_SIZE, - GFP_ATOMIC); + adapter->shadow_vfta = kcalloc(E1000_VLAN_FILTER_TBL_SIZE, sizeof(u32), + GFP_ATOMIC); /* This call may decrease the number of queues */ if (igb_init_interrupt_scheme(adapter, true)) { @@ -2470,16 +3002,16 @@ static int igb_sw_init(struct igb_adapter *adapter) } /** - * igb_open - Called when a network interface is made active - * @netdev: network interface device structure + * igb_open - Called when a network interface is made active + * @netdev: network interface device structure * - * Returns 0 on success, negative value on failure + * 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. + * The open entry point is called when a network interface is made + * active by the system (IFF_UP). At this point all resources needed + * for transmit and receive operations are allocated, the interrupt + * handler is registered with the OS, the watchdog timer is started, + * and the stack is notified that the interface is ready. **/ static int __igb_open(struct net_device *netdev, bool resuming) { @@ -2515,7 +3047,8 @@ static int __igb_open(struct net_device *netdev, bool resuming) /* 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. */ + * clean_rx handler before we do so. + */ igb_configure(adapter); err = igb_request_irq(adapter); @@ -2547,6 +3080,7 @@ static int __igb_open(struct net_device *netdev, bool resuming) /* notify VFs that reset has been completed */ if (adapter->vfs_allocated_count) { u32 reg_data = rd32(E1000_CTRL_EXT); + reg_data |= E1000_CTRL_EXT_PFRSTD; wr32(E1000_CTRL_EXT, reg_data); } @@ -2584,15 +3118,15 @@ static int igb_open(struct net_device *netdev) } /** - * igb_close - Disables a network interface - * @netdev: network interface device structure + * igb_close - Disables a network interface + * @netdev: network interface device structure * - * Returns 0, this is not allowed to fail + * Returns 0, this is not allowed to fail * - * The close entry point is called when an interface is de-activated - * by the OS. The hardware is still under the driver's control, but - * needs to be disabled. A global MAC reset is issued to stop the - * hardware, and all transmit and receive resources are freed. + * The close entry point is called when an interface is de-activated + * by the OS. The hardware is still under the driver's control, but + * needs to be disabled. A global MAC reset is issued to stop the + * hardware, and all transmit and receive resources are freed. **/ static int __igb_close(struct net_device *netdev, bool suspending) { @@ -2621,10 +3155,10 @@ static int igb_close(struct net_device *netdev) } /** - * igb_setup_tx_resources - allocate Tx resources (Descriptors) - * @tx_ring: tx descriptor ring (for a specific queue) to setup + * igb_setup_tx_resources - allocate Tx resources (Descriptors) + * @tx_ring: tx descriptor ring (for a specific queue) to setup * - * Return 0 on success, negative on failure + * Return 0 on success, negative on failure **/ int igb_setup_tx_resources(struct igb_ring *tx_ring) { @@ -2659,11 +3193,11 @@ err: } /** - * igb_setup_all_tx_resources - wrapper to allocate Tx resources - * (Descriptors) for all queues - * @adapter: board private structure + * igb_setup_all_tx_resources - wrapper to allocate Tx resources + * (Descriptors) for all queues + * @adapter: board private structure * - * Return 0 on success, negative on failure + * Return 0 on success, negative on failure **/ static int igb_setup_all_tx_resources(struct igb_adapter *adapter) { @@ -2685,8 +3219,8 @@ static int igb_setup_all_tx_resources(struct igb_adapter *adapter) } /** - * igb_setup_tctl - configure the transmit control registers - * @adapter: Board private structure + * igb_setup_tctl - configure the transmit control registers + * @adapter: Board private structure **/ void igb_setup_tctl(struct igb_adapter *adapter) { @@ -2711,14 +3245,14 @@ void igb_setup_tctl(struct igb_adapter *adapter) } /** - * igb_configure_tx_ring - Configure transmit ring after Reset - * @adapter: board private structure - * @ring: tx ring to configure + * igb_configure_tx_ring - Configure transmit ring after Reset + * @adapter: board private structure + * @ring: tx ring to configure * - * Configure a transmit ring after a reset. + * Configure a transmit ring after a reset. **/ void igb_configure_tx_ring(struct igb_adapter *adapter, - struct igb_ring *ring) + struct igb_ring *ring) { struct e1000_hw *hw = &adapter->hw; u32 txdctl = 0; @@ -2731,9 +3265,9 @@ void igb_configure_tx_ring(struct igb_adapter *adapter, mdelay(10); wr32(E1000_TDLEN(reg_idx), - ring->count * sizeof(union e1000_adv_tx_desc)); + ring->count * sizeof(union e1000_adv_tx_desc)); wr32(E1000_TDBAL(reg_idx), - tdba & 0x00000000ffffffffULL); + tdba & 0x00000000ffffffffULL); wr32(E1000_TDBAH(reg_idx), tdba >> 32); ring->tail = hw->hw_addr + E1000_TDT(reg_idx); @@ -2749,10 +3283,10 @@ void igb_configure_tx_ring(struct igb_adapter *adapter, } /** - * igb_configure_tx - Configure transmit Unit after Reset - * @adapter: board private structure + * igb_configure_tx - Configure transmit Unit after Reset + * @adapter: board private structure * - * Configure the Tx unit of the MAC after a reset. + * Configure the Tx unit of the MAC after a reset. **/ static void igb_configure_tx(struct igb_adapter *adapter) { @@ -2763,10 +3297,10 @@ static void igb_configure_tx(struct igb_adapter *adapter) } /** - * igb_setup_rx_resources - allocate Rx resources (Descriptors) - * @rx_ring: rx descriptor ring (for a specific queue) to setup + * igb_setup_rx_resources - allocate Rx resources (Descriptors) + * @rx_ring: Rx descriptor ring (for a specific queue) to setup * - * Returns 0 on success, negative on failure + * Returns 0 on success, negative on failure **/ int igb_setup_rx_resources(struct igb_ring *rx_ring) { @@ -2802,11 +3336,11 @@ err: } /** - * igb_setup_all_rx_resources - wrapper to allocate Rx resources - * (Descriptors) for all queues - * @adapter: board private structure + * igb_setup_all_rx_resources - wrapper to allocate Rx resources + * (Descriptors) for all queues + * @adapter: board private structure * - * Return 0 on success, negative on failure + * Return 0 on success, negative on failure **/ static int igb_setup_all_rx_resources(struct igb_adapter *adapter) { @@ -2828,14 +3362,14 @@ static int igb_setup_all_rx_resources(struct igb_adapter *adapter) } /** - * igb_setup_mrqc - configure the multiple receive queue control registers - * @adapter: Board private structure + * igb_setup_mrqc - configure the multiple receive queue control registers + * @adapter: Board private structure **/ static void igb_setup_mrqc(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; u32 mrqc, rxcsum; - u32 j, num_rx_queues, shift = 0; + u32 j, num_rx_queues; static const u32 rsskey[10] = { 0xDA565A6D, 0xC20E5B25, 0x3D256741, 0xB08FA343, 0xCB2BCAD0, 0xB4307BAE, 0xA32DCB77, 0x0CF23080, 0x3BB7426A, @@ -2848,39 +3382,24 @@ static void igb_setup_mrqc(struct igb_adapter *adapter) num_rx_queues = adapter->rss_queues; switch (hw->mac.type) { - case e1000_82575: - shift = 6; - break; case e1000_82576: /* 82576 supports 2 RSS queues for SR-IOV */ - if (adapter->vfs_allocated_count) { - shift = 3; + if (adapter->vfs_allocated_count) num_rx_queues = 2; - } break; default: break; } - /* - * Populate the indirection table 4 entries at a time. To do this - * we are generating the results for n and n+2 and then interleaving - * those with the results with n+1 and n+3. - */ - for (j = 0; j < 32; j++) { - /* first pass generates n and n+2 */ - u32 base = ((j * 0x00040004) + 0x00020000) * num_rx_queues; - u32 reta = (base & 0x07800780) >> (7 - shift); - - /* second pass generates n+1 and n+3 */ - base += 0x00010001 * num_rx_queues; - reta |= (base & 0x07800780) << (1 + shift); - - wr32(E1000_RETA(j), reta); + if (adapter->rss_indir_tbl_init != num_rx_queues) { + for (j = 0; j < IGB_RETA_SIZE; j++) + adapter->rss_indir_tbl[j] = + (j * num_rx_queues) / IGB_RETA_SIZE; + adapter->rss_indir_tbl_init = num_rx_queues; } + igb_write_rss_indir_tbl(adapter); - /* - * Disable raw packet checksumming so that RSS hash is placed in + /* Disable raw packet checksumming so that RSS hash is placed in * descriptor on writeback. No need to enable TCP/UDP/IP checksum * offloads as they are enabled by default */ @@ -2910,11 +3429,13 @@ static void igb_setup_mrqc(struct igb_adapter *adapter) /* If VMDq is enabled then we set the appropriate mode for that, else * we default to RSS so that an RSS hash is calculated per packet even - * if we are only using one queue */ + * if we are only using one queue + */ if (adapter->vfs_allocated_count) { if (hw->mac.type > e1000_82575) { /* Set the default pool for the PF's first queue */ u32 vtctl = rd32(E1000_VT_CTL); + vtctl &= ~(E1000_VT_CTL_DEFAULT_POOL_MASK | E1000_VT_CTL_DISABLE_DEF_POOL); vtctl |= adapter->vfs_allocated_count << @@ -2935,8 +3456,8 @@ static void igb_setup_mrqc(struct igb_adapter *adapter) } /** - * igb_setup_rctl - configure the receive control registers - * @adapter: Board private structure + * igb_setup_rctl - configure the receive control registers + * @adapter: Board private structure **/ void igb_setup_rctl(struct igb_adapter *adapter) { @@ -2951,8 +3472,7 @@ void igb_setup_rctl(struct igb_adapter *adapter) rctl |= E1000_RCTL_EN | E1000_RCTL_BAM | E1000_RCTL_RDMTS_HALF | (hw->mac.mc_filter_type << E1000_RCTL_MO_SHIFT); - /* - * enable stripping of CRC. It's unlikely this will break BMC + /* enable stripping of CRC. It's unlikely this will break BMC * redirection as it did with e1000. Newer features require * that the HW strips the CRC. */ @@ -2979,7 +3499,8 @@ void igb_setup_rctl(struct igb_adapter *adapter) /* This is useful for sniffing bad packets. */ if (adapter->netdev->features & NETIF_F_RXALL) { /* UPE and MPE will be handled by normal PROMISC logic - * in e1000e_set_rx_mode */ + * 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 */ @@ -2996,13 +3517,14 @@ void igb_setup_rctl(struct igb_adapter *adapter) } static inline int igb_set_vf_rlpml(struct igb_adapter *adapter, int size, - int vfn) + int vfn) { struct e1000_hw *hw = &adapter->hw; u32 vmolr; /* if it isn't the PF check to see if VFs are enabled and - * increase the size to support vlan tags */ + * increase the size to support vlan tags + */ if (vfn < adapter->vfs_allocated_count && adapter->vf_data[vfn].vlans_enabled) size += VLAN_TAG_SIZE; @@ -3016,10 +3538,10 @@ static inline int igb_set_vf_rlpml(struct igb_adapter *adapter, int size, } /** - * igb_rlpml_set - set maximum receive packet size - * @adapter: board private structure + * igb_rlpml_set - set maximum receive packet size + * @adapter: board private structure * - * Configure maximum receivable packet size. + * Configure maximum receivable packet size. **/ static void igb_rlpml_set(struct igb_adapter *adapter) { @@ -3029,8 +3551,7 @@ static void igb_rlpml_set(struct igb_adapter *adapter) if (pf_id) { igb_set_vf_rlpml(adapter, max_frame_size, pf_id); - /* - * If we're in VMDQ or SR-IOV mode, then set global RLPML + /* If we're in VMDQ or SR-IOV mode, then set global RLPML * to our max jumbo frame size, in case we need to enable * jumbo frames on one of the rings later. * This will not pass over-length frames into the default @@ -3048,17 +3569,23 @@ static inline void igb_set_vmolr(struct igb_adapter *adapter, struct e1000_hw *hw = &adapter->hw; u32 vmolr; - /* - * This register exists only on 82576 and newer so if we are older then + /* This register exists only on 82576 and newer so if we are older then * we should exit and do nothing */ if (hw->mac.type < e1000_82576) return; vmolr = rd32(E1000_VMOLR(vfn)); - vmolr |= E1000_VMOLR_STRVLAN; /* Strip vlan tags */ + vmolr |= E1000_VMOLR_STRVLAN; /* Strip vlan tags */ + if (hw->mac.type == e1000_i350) { + u32 dvmolr; + + dvmolr = rd32(E1000_DVMOLR(vfn)); + dvmolr |= E1000_DVMOLR_STRVLAN; + wr32(E1000_DVMOLR(vfn), dvmolr); + } if (aupe) - vmolr |= E1000_VMOLR_AUPE; /* Accept untagged packets */ + vmolr |= E1000_VMOLR_AUPE; /* Accept untagged packets */ else vmolr &= ~(E1000_VMOLR_AUPE); /* Tagged packets ONLY */ @@ -3067,25 +3594,24 @@ static inline void igb_set_vmolr(struct igb_adapter *adapter, if (adapter->rss_queues > 1 && vfn == adapter->vfs_allocated_count) vmolr |= E1000_VMOLR_RSSE; /* enable RSS */ - /* - * for VMDq only allow the VFs and pool 0 to accept broadcast and + /* for VMDq only allow the VFs and pool 0 to accept broadcast and * multicast packets */ if (vfn <= adapter->vfs_allocated_count) - vmolr |= E1000_VMOLR_BAM; /* Accept broadcast */ + vmolr |= E1000_VMOLR_BAM; /* Accept broadcast */ wr32(E1000_VMOLR(vfn), vmolr); } /** - * igb_configure_rx_ring - Configure a receive ring after Reset - * @adapter: board private structure - * @ring: receive ring to be configured + * igb_configure_rx_ring - Configure a receive ring after Reset + * @adapter: board private structure + * @ring: receive ring to be configured * - * Configure the Rx unit of the MAC after a reset. + * Configure the Rx unit of the MAC after a reset. **/ void igb_configure_rx_ring(struct igb_adapter *adapter, - struct igb_ring *ring) + struct igb_ring *ring) { struct e1000_hw *hw = &adapter->hw; u64 rdba = ring->dma; @@ -3100,7 +3626,7 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, rdba & 0x00000000ffffffffULL); wr32(E1000_RDBAH(reg_idx), rdba >> 32); wr32(E1000_RDLEN(reg_idx), - ring->count * sizeof(union e1000_adv_rx_desc)); + ring->count * sizeof(union e1000_adv_rx_desc)); /* initialize head and tail */ ring->tail = hw->hw_addr + E1000_RDT(reg_idx); @@ -3132,10 +3658,10 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, } /** - * igb_configure_rx - Configure receive Unit after Reset - * @adapter: board private structure + * igb_configure_rx - Configure receive Unit after Reset + * @adapter: board private structure * - * Configure the Rx unit of the MAC after a reset. + * Configure the Rx unit of the MAC after a reset. **/ static void igb_configure_rx(struct igb_adapter *adapter) { @@ -3146,19 +3672,20 @@ static void igb_configure_rx(struct igb_adapter *adapter) /* set the correct pool for the PF default MAC address in entry 0 */ igb_rar_set_qsel(adapter, adapter->hw.mac.addr, 0, - adapter->vfs_allocated_count); + adapter->vfs_allocated_count); /* Setup the HW Rx Head and Tail Descriptor Pointers and - * the Base and Length of the Rx Descriptor Ring */ + * the Base and Length of the Rx Descriptor Ring + */ for (i = 0; i < adapter->num_rx_queues; i++) igb_configure_rx_ring(adapter, adapter->rx_ring[i]); } /** - * igb_free_tx_resources - Free Tx Resources per Queue - * @tx_ring: Tx descriptor ring for a specific queue + * igb_free_tx_resources - Free Tx Resources per Queue + * @tx_ring: Tx descriptor ring for a specific queue * - * Free all transmit software resources + * Free all transmit software resources **/ void igb_free_tx_resources(struct igb_ring *tx_ring) { @@ -3178,10 +3705,10 @@ void igb_free_tx_resources(struct igb_ring *tx_ring) } /** - * igb_free_all_tx_resources - Free Tx Resources for All Queues - * @adapter: board private structure + * igb_free_all_tx_resources - Free Tx Resources for All Queues + * @adapter: board private structure * - * Free all transmit software resources + * Free all transmit software resources **/ static void igb_free_all_tx_resources(struct igb_adapter *adapter) { @@ -3214,8 +3741,8 @@ void igb_unmap_and_free_tx_resource(struct igb_ring *ring, } /** - * igb_clean_tx_ring - Free Tx Buffers - * @tx_ring: ring to be cleaned + * igb_clean_tx_ring - Free Tx Buffers + * @tx_ring: ring to be cleaned **/ static void igb_clean_tx_ring(struct igb_ring *tx_ring) { @@ -3245,8 +3772,8 @@ static void igb_clean_tx_ring(struct igb_ring *tx_ring) } /** - * igb_clean_all_tx_rings - Free Tx Buffers for all queues - * @adapter: board private structure + * igb_clean_all_tx_rings - Free Tx Buffers for all queues + * @adapter: board private structure **/ static void igb_clean_all_tx_rings(struct igb_adapter *adapter) { @@ -3257,10 +3784,10 @@ static void igb_clean_all_tx_rings(struct igb_adapter *adapter) } /** - * igb_free_rx_resources - Free Rx Resources - * @rx_ring: ring to clean the resources from + * igb_free_rx_resources - Free Rx Resources + * @rx_ring: ring to clean the resources from * - * Free all receive software resources + * Free all receive software resources **/ void igb_free_rx_resources(struct igb_ring *rx_ring) { @@ -3280,10 +3807,10 @@ void igb_free_rx_resources(struct igb_ring *rx_ring) } /** - * igb_free_all_rx_resources - Free Rx Resources for All Queues - * @adapter: board private structure + * igb_free_all_rx_resources - Free Rx Resources for All Queues + * @adapter: board private structure * - * Free all receive software resources + * Free all receive software resources **/ static void igb_free_all_rx_resources(struct igb_adapter *adapter) { @@ -3294,8 +3821,8 @@ static void igb_free_all_rx_resources(struct igb_adapter *adapter) } /** - * igb_clean_rx_ring - Free Rx Buffers per Queue - * @rx_ring: ring to free buffers from + * igb_clean_rx_ring - Free Rx Buffers per Queue + * @rx_ring: ring to free buffers from **/ static void igb_clean_rx_ring(struct igb_ring *rx_ring) { @@ -3337,8 +3864,8 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring) } /** - * igb_clean_all_rx_rings - Free Rx Buffers for all queues - * @adapter: board private structure + * igb_clean_all_rx_rings - Free Rx Buffers for all queues + * @adapter: board private structure **/ static void igb_clean_all_rx_rings(struct igb_adapter *adapter) { @@ -3349,11 +3876,11 @@ static void igb_clean_all_rx_rings(struct igb_adapter *adapter) } /** - * igb_set_mac - Change the Ethernet Address of the NIC - * @netdev: network interface device structure - * @p: pointer to an address structure + * igb_set_mac - Change the Ethernet Address of the NIC + * @netdev: network interface device structure + * @p: pointer to an address structure * - * Returns 0 on success, negative on failure + * Returns 0 on success, negative on failure **/ static int igb_set_mac(struct net_device *netdev, void *p) { @@ -3369,19 +3896,19 @@ static int igb_set_mac(struct net_device *netdev, void *p) /* set the correct pool for the new PF MAC address in entry 0 */ igb_rar_set_qsel(adapter, hw->mac.addr, 0, - adapter->vfs_allocated_count); + adapter->vfs_allocated_count); return 0; } /** - * igb_write_mc_addr_list - write multicast addresses to MTA - * @netdev: network interface device structure + * igb_write_mc_addr_list - write multicast addresses to MTA + * @netdev: network interface device structure * - * Writes multicast address list to the MTA hash table. - * Returns: -ENOMEM on failure - * 0 on no addresses written - * X on writing X addresses to MTA + * Writes multicast address list to the MTA hash table. + * Returns: -ENOMEM on failure + * 0 on no addresses written + * X on writing X addresses to MTA **/ static int igb_write_mc_addr_list(struct net_device *netdev) { @@ -3414,13 +3941,13 @@ static int igb_write_mc_addr_list(struct net_device *netdev) } /** - * igb_write_uc_addr_list - write unicast addresses to RAR table - * @netdev: network interface device structure + * igb_write_uc_addr_list - write unicast addresses to RAR table + * @netdev: network interface device structure * - * Writes unicast address list to the RAR table. - * Returns: -ENOMEM on failure/insufficient address space - * 0 on no addresses written - * X on writing X addresses to the RAR table + * Writes unicast address list to the RAR table. + * Returns: -ENOMEM on failure/insufficient address space + * 0 on no addresses written + * X on writing X addresses to the RAR table **/ static int igb_write_uc_addr_list(struct net_device *netdev) { @@ -3441,8 +3968,8 @@ static int igb_write_uc_addr_list(struct net_device *netdev) if (!rar_entries) break; igb_rar_set_qsel(adapter, ha->addr, - rar_entries--, - vfn); + rar_entries--, + vfn); count++; } } @@ -3457,13 +3984,13 @@ static int igb_write_uc_addr_list(struct net_device *netdev) } /** - * igb_set_rx_mode - Secondary Unicast, Multicast and Promiscuous mode set - * @netdev: network interface device structure + * igb_set_rx_mode - Secondary Unicast, Multicast and Promiscuous mode set + * @netdev: network interface device structure * - * The set_rx_mode entry point is called whenever the unicast or multicast - * address lists or the network interface flags are updated. This routine is - * responsible for configuring the hardware for proper unicast, multicast, - * promiscuous mode, and all-multi behavior. + * The set_rx_mode entry point is called whenever the unicast or multicast + * address lists or the network interface flags are updated. This routine is + * responsible for configuring the hardware for proper unicast, multicast, + * promiscuous mode, and all-multi behavior. **/ static void igb_set_rx_mode(struct net_device *netdev) { @@ -3480,6 +4007,9 @@ static void igb_set_rx_mode(struct net_device *netdev) rctl &= ~(E1000_RCTL_UPE | E1000_RCTL_MPE | E1000_RCTL_VFE); if (netdev->flags & IFF_PROMISC) { + /* retain VLAN HW filtering if in VT mode */ + if (adapter->vfs_allocated_count) + rctl |= E1000_RCTL_VFE; rctl |= (E1000_RCTL_UPE | E1000_RCTL_MPE); vmolr |= (E1000_VMOLR_ROPE | E1000_VMOLR_MPME); } else { @@ -3487,8 +4017,7 @@ static void igb_set_rx_mode(struct net_device *netdev) rctl |= E1000_RCTL_MPE; vmolr |= E1000_VMOLR_MPME; } else { - /* - * Write addresses to the MTA, if the attempt fails + /* Write addresses to the MTA, if the attempt fails * then we should just turn on promiscuous mode so * that we can at least receive multicast traffic */ @@ -3500,8 +4029,7 @@ static void igb_set_rx_mode(struct net_device *netdev) vmolr |= E1000_VMOLR_ROMPE; } } - /* - * Write addresses to available RAR registers, if there is not + /* Write addresses to available RAR registers, if there is not * sufficient space to store all the addresses then enable * unicast promiscuous mode */ @@ -3514,8 +4042,7 @@ static void igb_set_rx_mode(struct net_device *netdev) } wr32(E1000_RCTL, rctl); - /* - * In order to support SR-IOV and eventually VMDq it is necessary to set + /* In order to support SR-IOV and eventually VMDq it is necessary to set * the VMOLR to enable the appropriate modes. Without this workaround * we will have issues with VLAN tag stripping not being done for frames * that are only arriving because we are the default pool @@ -3524,7 +4051,7 @@ static void igb_set_rx_mode(struct net_device *netdev) return; vmolr |= rd32(E1000_VMOLR(vfn)) & - ~(E1000_VMOLR_ROPE | E1000_VMOLR_MPME | E1000_VMOLR_ROMPE); + ~(E1000_VMOLR_ROPE | E1000_VMOLR_MPME | E1000_VMOLR_ROMPE); wr32(E1000_VMOLR(vfn), vmolr); igb_restore_vf_multicasts(adapter); } @@ -3537,7 +4064,8 @@ static void igb_check_wvbr(struct igb_adapter *adapter) switch (hw->mac.type) { case e1000_82576: case e1000_i350: - if (!(wvbr = rd32(E1000_WVBR))) + wvbr = rd32(E1000_WVBR); + if (!wvbr) return; break; default: @@ -3556,7 +4084,7 @@ static void igb_spoof_check(struct igb_adapter *adapter) if (!adapter->wvbr) return; - for(j = 0; j < adapter->vfs_allocated_count; j++) { + for (j = 0; j < adapter->vfs_allocated_count; j++) { if (adapter->wvbr & (1 << j) || adapter->wvbr & (1 << (j + IGB_STAGGERED_QUEUE_OFFSET))) { dev_warn(&adapter->pdev->dev, @@ -3569,7 +4097,8 @@ static void igb_spoof_check(struct igb_adapter *adapter) } /* Need to wait a few seconds after link up to get diagnostic information from - * the phy */ + * the phy + */ static void igb_update_phy_info(unsigned long data) { struct igb_adapter *adapter = (struct igb_adapter *) data; @@ -3577,14 +4106,13 @@ static void igb_update_phy_info(unsigned long data) } /** - * igb_has_link - check shared code for link and determine up/down - * @adapter: pointer to driver private info + * igb_has_link - check shared code for link and determine up/down + * @adapter: pointer to driver private info **/ bool igb_has_link(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; bool link_active = false; - s32 ret_val = 0; /* get_link_status is set on LSC (link status) interrupt or * rx sequence error interrupt. get_link_status will stay @@ -3593,22 +4121,28 @@ bool igb_has_link(struct igb_adapter *adapter) */ switch (hw->phy.media_type) { case e1000_media_type_copper: - if (hw->mac.get_link_status) { - ret_val = hw->mac.ops.check_for_link(hw); - link_active = !hw->mac.get_link_status; - } else { - link_active = true; - } - break; + if (!hw->mac.get_link_status) + return true; case e1000_media_type_internal_serdes: - ret_val = hw->mac.ops.check_for_link(hw); - link_active = hw->mac.serdes_has_link; + hw->mac.ops.check_for_link(hw); + link_active = !hw->mac.get_link_status; break; default: case e1000_media_type_unknown: break; } + if (((hw->mac.type == e1000_i210) || + (hw->mac.type == e1000_i211)) && + (hw->phy.id == I210_I_PHY_ID)) { + if (!netif_carrier_ok(adapter->netdev)) { + adapter->flags &= ~IGB_FLAG_NEED_LINK_UPDATE; + } else if (!(adapter->flags & IGB_FLAG_NEED_LINK_UPDATE)) { + adapter->flags |= IGB_FLAG_NEED_LINK_UPDATE; + adapter->link_check_timeout = jiffies; + } + } + return link_active; } @@ -3623,17 +4157,16 @@ static bool igb_thermal_sensor_event(struct e1000_hw *hw, u32 event) ctrl_ext = rd32(E1000_CTRL_EXT); if ((hw->phy.media_type == e1000_media_type_copper) && - !(ctrl_ext & E1000_CTRL_EXT_LINK_MODE_SGMII)) { + !(ctrl_ext & E1000_CTRL_EXT_LINK_MODE_SGMII)) ret = !!(thstat & event); - } } return ret; } /** - * igb_watchdog - Timer Call-back - * @data: pointer to adapter cast into an unsigned long + * igb_watchdog - Timer Call-back + * @data: pointer to adapter cast into an unsigned long **/ static void igb_watchdog(unsigned long data) { @@ -3645,28 +4178,53 @@ static void igb_watchdog(unsigned long data) static void igb_watchdog_task(struct work_struct *work) { struct igb_adapter *adapter = container_of(work, - struct igb_adapter, - watchdog_task); + struct igb_adapter, + watchdog_task); struct e1000_hw *hw = &adapter->hw; + struct e1000_phy_info *phy = &hw->phy; struct net_device *netdev = adapter->netdev; u32 link; int i; + u32 connsw; link = igb_has_link(adapter); + + if (adapter->flags & IGB_FLAG_NEED_LINK_UPDATE) { + if (time_after(jiffies, (adapter->link_check_timeout + HZ))) + adapter->flags &= ~IGB_FLAG_NEED_LINK_UPDATE; + else + link = false; + } + + /* Force link down if we have fiber to swap to */ + if (adapter->flags & IGB_FLAG_MAS_ENABLE) { + if (hw->phy.media_type == e1000_media_type_copper) { + connsw = rd32(E1000_CONNSW); + if (!(connsw & E1000_CONNSW_AUTOSENSE_EN)) + link = 0; + } + } if (link) { + /* Perform a reset if the media type changed. */ + if (hw->dev_spec._82575.media_changed) { + hw->dev_spec._82575.media_changed = false; + adapter->flags |= IGB_FLAG_MEDIA_RESET; + igb_reset(adapter); + } /* Cancel scheduled suspend requests. */ pm_runtime_resume(netdev->dev.parent); if (!netif_carrier_ok(netdev)) { u32 ctrl; + hw->mac.ops.get_speed_and_duplex(hw, - &adapter->link_speed, - &adapter->link_duplex); + &adapter->link_speed, + &adapter->link_duplex); ctrl = rd32(E1000_CTRL); /* Links status message must follow this format */ - printk(KERN_INFO "igb: %s NIC Link is Up %d Mbps %s " - "Duplex, Flow Control: %s\n", + netdev_info(netdev, + "igb: %s NIC Link is Up %d Mbps %s Duplex, Flow Control: %s\n", netdev->name, adapter->link_speed, adapter->link_duplex == FULL_DUPLEX ? @@ -3676,13 +4234,24 @@ static void igb_watchdog_task(struct work_struct *work) (ctrl & E1000_CTRL_RFCE) ? "RX" : (ctrl & E1000_CTRL_TFCE) ? "TX" : "None"); + /* disable EEE if enabled */ + if ((adapter->flags & IGB_FLAG_EEE) && + (adapter->link_duplex == HALF_DUPLEX)) { + dev_info(&adapter->pdev->dev, + "EEE Disabled: unsupported at half duplex. Re-enable using ethtool when at full duplex.\n"); + adapter->hw.dev_spec._82575.eee_disable = true; + adapter->flags &= ~IGB_FLAG_EEE; + } + + /* check if SmartSpeed worked */ + igb_check_downshift(hw); + if (phy->speed_downgraded) + netdev_warn(netdev, "Link Speed was downgraded by SmartSpeed\n"); + /* check for thermal sensor event */ if (igb_thermal_sensor_event(hw, - E1000_THSTAT_LINK_THROTTLE)) { - netdev_info(netdev, "The network adapter link " - "speed was downshifted because it " - "overheated\n"); - } + E1000_THSTAT_LINK_THROTTLE)) + netdev_info(netdev, "The network adapter link speed was downshifted because it overheated\n"); /* adjust timeout factor according to speed/duplex */ adapter->tx_timeout_factor = 1; @@ -3713,12 +4282,11 @@ static void igb_watchdog_task(struct work_struct *work) /* check for thermal sensor event */ if (igb_thermal_sensor_event(hw, E1000_THSTAT_PWR_DOWN)) { - netdev_err(netdev, "The network adapter was " - "stopped because it overheated\n"); + netdev_err(netdev, "The network adapter was stopped because it overheated\n"); } /* Links status message must follow this format */ - printk(KERN_INFO "igb: %s NIC Link is Down\n", + netdev_info(netdev, "igb: %s NIC Link is Down\n", netdev->name); netif_carrier_off(netdev); @@ -3729,8 +4297,27 @@ static void igb_watchdog_task(struct work_struct *work) mod_timer(&adapter->phy_info_timer, round_jiffies(jiffies + 2 * HZ)); + /* link is down, time to check for alternate media */ + if (adapter->flags & IGB_FLAG_MAS_ENABLE) { + igb_check_swap_media(adapter); + if (adapter->flags & IGB_FLAG_MEDIA_RESET) { + schedule_work(&adapter->reset_task); + /* return immediately */ + return; + } + } pm_schedule_suspend(netdev->dev.parent, MSEC_PER_SEC * 5); + + /* also check for alternate media here */ + } else if (!netif_carrier_ok(netdev) && + (adapter->flags & IGB_FLAG_MAS_ENABLE)) { + igb_check_swap_media(adapter); + if (adapter->flags & IGB_FLAG_MEDIA_RESET) { + schedule_work(&adapter->reset_task); + /* return immediately */ + return; + } } } @@ -3744,7 +4331,8 @@ static void igb_watchdog_task(struct work_struct *work) /* 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). */ + * (Do the reset outside of interrupt context). + */ if (igb_desc_unused(tx_ring) + 1 < tx_ring->count) { adapter->tx_timeout_count++; schedule_work(&adapter->reset_task); @@ -3757,9 +4345,10 @@ static void igb_watchdog_task(struct work_struct *work) set_bit(IGB_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags); } - /* Cause software interrupt to ensure rx ring is cleaned */ - if (adapter->msix_entries) { + /* Cause software interrupt to ensure Rx ring is cleaned */ + if (adapter->flags & IGB_FLAG_HAS_MSIX) { u32 eics = 0; + for (i = 0; i < adapter->num_q_vectors; i++) eics |= adapter->q_vector[i]->eims_value; wr32(E1000_EICS, eics); @@ -3768,11 +4357,17 @@ static void igb_watchdog_task(struct work_struct *work) } igb_spoof_check(adapter); + igb_ptp_rx_hang(adapter); /* Reset the timer */ - if (!test_bit(__IGB_DOWN, &adapter->state)) - mod_timer(&adapter->watchdog_timer, - round_jiffies(jiffies + 2 * HZ)); + if (!test_bit(__IGB_DOWN, &adapter->state)) { + if (adapter->flags & IGB_FLAG_NEED_LINK_UPDATE) + mod_timer(&adapter->watchdog_timer, + round_jiffies(jiffies + HZ)); + else + mod_timer(&adapter->watchdog_timer, + round_jiffies(jiffies + 2 * HZ)); + } } enum latency_range { @@ -3783,20 +4378,19 @@ enum latency_range { }; /** - * igb_update_ring_itr - update the dynamic ITR value based on packet size + * igb_update_ring_itr - update the dynamic ITR value based on packet size + * @q_vector: pointer to q_vector * - * Stores a new ITR value based on strictly on packet size. This - * algorithm is less sophisticated than that used in igb_update_itr, - * due to the difficulty of synchronizing statistics across multiple - * receive rings. The divisors and thresholds used by this function - * were determined based on theoretical maximum wire speed and testing - * data, in order to minimize response time while increasing bulk - * throughput. - * This functionality is controlled by the InterruptThrottleRate module - * parameter (see igb_param.c) - * NOTE: This function is called only when operating in a multiqueue - * receive environment. - * @q_vector: pointer to q_vector + * Stores a new ITR value based on strictly on packet size. This + * algorithm is less sophisticated than that used in igb_update_itr, + * due to the difficulty of synchronizing statistics across multiple + * receive rings. The divisors and thresholds used by this function + * were determined based on theoretical maximum wire speed and testing + * data, in order to minimize response time while increasing bulk + * throughput. + * This functionality is controlled by ethtool's coalescing settings. + * NOTE: This function is called only when operating in a multiqueue + * receive environment. **/ static void igb_update_ring_itr(struct igb_q_vector *q_vector) { @@ -3857,20 +4451,20 @@ clear_counts: } /** - * igb_update_itr - update the dynamic ITR value based on statistics - * Stores a new ITR value based on packets and byte - * counts during the last interrupt. The advantage of per interrupt - * computation is faster updates and more accurate ITR for the current - * traffic pattern. Constants in this function were computed - * based on theoretical maximum wire speed and thresholds were set based - * on testing data as well as attempting to minimize response time - * while increasing bulk throughput. - * this functionality is controlled by the InterruptThrottleRate module - * parameter (see igb_param.c) - * NOTE: These calculations are only valid when operating in a single- - * queue environment. - * @q_vector: pointer to q_vector - * @ring_container: ring info to update the itr for + * igb_update_itr - update the dynamic ITR value based on statistics + * @q_vector: pointer to q_vector + * @ring_container: ring info to update the itr for + * + * 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 ethtool's coalescing settings. + * NOTE: These calculations are only valid when operating in a single- + * queue environment. **/ static void igb_update_itr(struct igb_q_vector *q_vector, struct igb_ring_container *ring_container) @@ -3894,13 +4488,12 @@ static void igb_update_itr(struct igb_q_vector *q_vector, case low_latency: /* 50 usec aka 20000 ints/s */ if (bytes > 10000) { /* this if handles the TSO accounting */ - if (bytes/packets > 8000) { + if (bytes/packets > 8000) itrval = bulk_latency; - } else if ((packets < 10) || ((bytes/packets) > 1200)) { + else if ((packets < 10) || ((bytes/packets) > 1200)) itrval = bulk_latency; - } else if ((packets > 35)) { + else if ((packets > 35)) itrval = lowest_latency; - } } else if (bytes/packets > 2000) { itrval = bulk_latency; } else if (packets <= 2 && bytes < 512) { @@ -3968,12 +4561,12 @@ set_itr_now: if (new_itr != q_vector->itr_val) { /* this attempts to bias the interrupt rate towards Bulk * by adding intermediate steps when interrupt rate is - * increasing */ + * increasing + */ new_itr = new_itr > q_vector->itr_val ? - max((new_itr * q_vector->itr_val) / - (new_itr + (q_vector->itr_val >> 2)), - new_itr) : - new_itr; + max((new_itr * q_vector->itr_val) / + (new_itr + (q_vector->itr_val >> 2)), + new_itr) : new_itr; /* Don't write the value here; it resets the adapter's * internal timer, and causes us to delay far longer than * we should between interrupts. Instead, we write the ITR @@ -4016,6 +4609,7 @@ static int igb_tso(struct igb_ring *tx_ring, struct sk_buff *skb = first->skb; u32 vlan_macip_lens, type_tucmd; u32 mss_l4len_idx, l4len; + int err; if (skb->ip_summed != CHECKSUM_PARTIAL) return 0; @@ -4023,16 +4617,14 @@ static int igb_tso(struct igb_ring *tx_ring, 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; /* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */ type_tucmd = E1000_ADVTXD_TUCMD_L4T_TCP; - if (first->protocol == __constant_htons(ETH_P_IP)) { + if (first->protocol == htons(ETH_P_IP)) { struct iphdr *iph = ip_hdr(skb); iph->tot_len = 0; iph->check = 0; @@ -4087,21 +4679,22 @@ static void igb_tx_csum(struct igb_ring *tx_ring, struct igb_tx_buffer *first) return; } else { u8 l4_hdr = 0; + switch (first->protocol) { - case __constant_htons(ETH_P_IP): + case htons(ETH_P_IP): vlan_macip_lens |= skb_network_header_len(skb); type_tucmd |= E1000_ADVTXD_TUCMD_IPV4; l4_hdr = ip_hdr(skb)->protocol; break; - case __constant_htons(ETH_P_IPV6): + case htons(ETH_P_IPV6): vlan_macip_lens |= skb_network_header_len(skb); l4_hdr = ipv6_hdr(skb)->nexthdr; break; default: if (unlikely(net_ratelimit())) { dev_warn(tx_ring->dev, - "partial checksum but proto=%x!\n", - first->protocol); + "partial checksum but proto=%x!\n", + first->protocol); } break; } @@ -4124,8 +4717,8 @@ static void igb_tx_csum(struct igb_ring *tx_ring, struct igb_tx_buffer *first) default: if (unlikely(net_ratelimit())) { dev_warn(tx_ring->dev, - "partial checksum but l4 proto=%x!\n", - l4_hdr); + "partial checksum but l4 proto=%x!\n", + l4_hdr); } break; } @@ -4193,13 +4786,6 @@ static void igb_tx_olinfo_status(struct igb_ring *tx_ring, tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); } -/* - * The largest size we can write to the descriptor is 65535. In order to - * maintain a power of two alignment we have to limit ourselves to 32K. - */ -#define IGB_MAX_TXD_PWR 15 -#define IGB_MAX_DATA_PER_TXD (1<<IGB_MAX_TXD_PWR) - static void igb_tx_map(struct igb_ring *tx_ring, struct igb_tx_buffer *first, const u8 hdr_len) @@ -4284,8 +4870,7 @@ static void igb_tx_map(struct igb_ring *tx_ring, /* set the timestamp */ first->time_stamp = jiffies; - /* - * Force memory writes to complete before letting h/w know there + /* 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). * @@ -4306,7 +4891,8 @@ static void igb_tx_map(struct igb_ring *tx_ring, writel(i, tx_ring->tail); /* we need this if more than one processor can write to our tail - * at a time, it syncronizes IO on IA64/Altix systems */ + * at a time, it synchronizes IO on IA64/Altix systems + */ mmiowb(); return; @@ -4336,11 +4922,13 @@ static int __igb_maybe_stop_tx(struct igb_ring *tx_ring, const u16 size) /* Herbert's original patch had: * smp_mb__after_netif_stop_queue(); - * but since that doesn't exist yet, just open code it. */ + * 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. */ + * made room available. + */ if (igb_desc_unused(tx_ring) < size) return -EBUSY; @@ -4364,19 +4952,29 @@ static inline int igb_maybe_stop_tx(struct igb_ring *tx_ring, const u16 size) netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, struct igb_ring *tx_ring) { - struct igb_adapter *adapter = netdev_priv(tx_ring->netdev); struct igb_tx_buffer *first; int tso; u32 tx_flags = 0; + u16 count = TXD_USE_COUNT(skb_headlen(skb)); __be16 protocol = vlan_get_protocol(skb); u8 hdr_len = 0; - /* need: 1 descriptor per page, + /* need: 1 descriptor per page * PAGE_SIZE/IGB_MAX_DATA_PER_TXD, + * + 1 desc for skb_headlen/IGB_MAX_DATA_PER_TXD, * + 2 desc gap to keep tail from touching head, - * + 1 desc for skb->data, * + 1 desc for context descriptor, - * otherwise try next time */ - if (igb_maybe_stop_tx(tx_ring, skb_shinfo(skb)->nr_frags + 4)) { + * otherwise try next time + */ + if (NETDEV_FRAG_PAGE_MAX_SIZE > IGB_MAX_DATA_PER_TXD) { + unsigned short f; + + for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) + count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size); + } else { + count += skb_shinfo(skb)->nr_frags; + } + + if (igb_maybe_stop_tx(tx_ring, count + 3)) { /* this is a hard error */ return NETDEV_TX_BUSY; } @@ -4387,16 +4985,23 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, first->bytecount = skb->len; first->gso_segs = 1; - if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && - !(adapter->ptp_tx_skb))) { - skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; - tx_flags |= IGB_TX_FLAGS_TSTAMP; + if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { + struct igb_adapter *adapter = netdev_priv(tx_ring->netdev); - adapter->ptp_tx_skb = skb_get(skb); - if (adapter->hw.mac.type == e1000_82576) - schedule_work(&adapter->ptp_tx_work); + if (!test_and_set_bit_lock(__IGB_PTP_TX_IN_PROGRESS, + &adapter->state)) { + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + tx_flags |= IGB_TX_FLAGS_TSTAMP; + + adapter->ptp_tx_skb = skb_get(skb); + adapter->ptp_tx_start = jiffies; + if (adapter->hw.mac.type == e1000_82576) + schedule_work(&adapter->ptp_tx_work); + } } + skb_tx_timestamp(skb); + if (vlan_tx_tag_present(skb)) { tx_flags |= IGB_TX_FLAGS_VLAN; tx_flags |= (vlan_tx_tag_get(skb) << IGB_TX_FLAGS_VLAN_SHIFT); @@ -4415,7 +5020,7 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, igb_tx_map(tx_ring, first, hdr_len); /* Make sure there is space in the ring for the next send. */ - igb_maybe_stop_tx(tx_ring, MAX_SKB_FRAGS + 4); + igb_maybe_stop_tx(tx_ring, DESC_NEEDED); return NETDEV_TX_OK; @@ -4451,8 +5056,7 @@ static netdev_tx_t igb_xmit_frame(struct sk_buff *skb, return NETDEV_TX_OK; } - /* - * The minimum packet size with TCTL.PSP set is 17 so pad the skb + /* The minimum packet size with TCTL.PSP set is 17 so pad the skb * in order to meet this minimum size requirement. */ if (unlikely(skb->len < 17)) { @@ -4466,8 +5070,8 @@ static netdev_tx_t igb_xmit_frame(struct sk_buff *skb, } /** - * igb_tx_timeout - Respond to a Tx Hang - * @netdev: network interface device structure + * igb_tx_timeout - Respond to a Tx Hang + * @netdev: network interface device structure **/ static void igb_tx_timeout(struct net_device *netdev) { @@ -4496,13 +5100,12 @@ static void igb_reset_task(struct work_struct *work) } /** - * igb_get_stats64 - Get System Network Statistics - * @netdev: network interface device structure - * @stats: rtnl_link_stats64 pointer - * + * igb_get_stats64 - Get System Network Statistics + * @netdev: network interface device structure + * @stats: rtnl_link_stats64 pointer **/ static struct rtnl_link_stats64 *igb_get_stats64(struct net_device *netdev, - struct rtnl_link_stats64 *stats) + struct rtnl_link_stats64 *stats) { struct igb_adapter *adapter = netdev_priv(netdev); @@ -4515,11 +5118,11 @@ static struct rtnl_link_stats64 *igb_get_stats64(struct net_device *netdev, } /** - * igb_change_mtu - Change the Maximum Transfer Unit - * @netdev: network interface device structure - * @new_mtu: new value for maximum frame size + * igb_change_mtu - Change the Maximum Transfer Unit + * @netdev: network interface device structure + * @new_mtu: new value for maximum frame size * - * Returns 0 on success, negative on failure + * Returns 0 on success, negative on failure **/ static int igb_change_mtu(struct net_device *netdev, int new_mtu) { @@ -4538,8 +5141,12 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu) return -EINVAL; } + /* adjust max frame to be at least the size of a standard frame */ + if (max_frame < (ETH_FRAME_LEN + ETH_FCS_LEN)) + max_frame = ETH_FRAME_LEN + ETH_FCS_LEN; + while (test_and_set_bit(__IGB_RESETTING, &adapter->state)) - msleep(1); + usleep_range(1000, 2000); /* igb_down has a dependency on max_frame_size */ adapter->max_frame_size = max_frame; @@ -4562,10 +5169,9 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu) } /** - * igb_update_stats - Update the board statistics counters - * @adapter: board private structure + * igb_update_stats - Update the board statistics counters + * @adapter: board private structure **/ - void igb_update_stats(struct igb_adapter *adapter, struct rtnl_link_stats64 *net_stats) { @@ -4580,8 +5186,7 @@ void igb_update_stats(struct igb_adapter *adapter, #define PHY_IDLE_ERROR_COUNT_MASK 0x00FF - /* - * Prevent stats update while adapter is being reset, or if the pci + /* Prevent stats update while adapter is being reset, or if the pci * connection is down. */ if (adapter->link_speed == 0) @@ -4591,9 +5196,13 @@ void igb_update_stats(struct igb_adapter *adapter, bytes = 0; packets = 0; + + rcu_read_lock(); for (i = 0; i < adapter->num_rx_queues; i++) { - u32 rqdpc = rd32(E1000_RQDPC(i)); struct igb_ring *ring = adapter->rx_ring[i]; + u32 rqdpc = rd32(E1000_RQDPC(i)); + if (hw->mac.type >= e1000_i210) + wr32(E1000_RQDPC(i), 0); if (rqdpc) { ring->rx_stats.drops += rqdpc; @@ -4601,10 +5210,10 @@ void igb_update_stats(struct igb_adapter *adapter, } do { - start = u64_stats_fetch_begin_bh(&ring->rx_syncp); + start = u64_stats_fetch_begin_irq(&ring->rx_syncp); _bytes = ring->rx_stats.bytes; _packets = ring->rx_stats.packets; - } while (u64_stats_fetch_retry_bh(&ring->rx_syncp, start)); + } while (u64_stats_fetch_retry_irq(&ring->rx_syncp, start)); bytes += _bytes; packets += _packets; } @@ -4617,15 +5226,16 @@ void igb_update_stats(struct igb_adapter *adapter, for (i = 0; i < adapter->num_tx_queues; i++) { struct igb_ring *ring = adapter->tx_ring[i]; do { - start = u64_stats_fetch_begin_bh(&ring->tx_syncp); + start = u64_stats_fetch_begin_irq(&ring->tx_syncp); _bytes = ring->tx_stats.bytes; _packets = ring->tx_stats.packets; - } while (u64_stats_fetch_retry_bh(&ring->tx_syncp, start)); + } while (u64_stats_fetch_retry_irq(&ring->tx_syncp, start)); bytes += _bytes; packets += _packets; } net_stats->tx_bytes = bytes; net_stats->tx_packets = packets; + rcu_read_unlock(); /* read stats registers */ adapter->stats.crcerrs += rd32(E1000_CRCERRS); @@ -4715,7 +5325,8 @@ void igb_update_stats(struct igb_adapter *adapter, /* Rx Errors */ /* RLEC on some newer hardware can be incorrect so build - * our own version based on RUC and ROC */ + * our own version based on RUC and ROC + */ net_stats->rx_errors = adapter->stats.rxerrc + adapter->stats.crcerrs + adapter->stats.algnerrc + adapter->stats.ruc + adapter->stats.roc + @@ -4774,7 +5385,8 @@ static irqreturn_t igb_msix_other(int irq, void *data) adapter->stats.doosync++; /* The DMA Out of Sync is also indication of a spoof event * in IOV mode. Check the Wrong VM Behavior register to - * see if it is really a spoof event. */ + * see if it is really a spoof event. + */ igb_check_wvbr(adapter); } @@ -4848,8 +5460,7 @@ static void igb_update_tx_dca(struct igb_adapter *adapter, if (hw->mac.type != e1000_82575) txctrl <<= E1000_DCA_TXCTRL_CPUID_SHIFT; - /* - * We can enable relaxed ordering for reads, but not writes when + /* We can enable relaxed ordering for reads, but not writes when * DCA is enabled. This is due to a known issue in some chipsets * which will cause the DCA tag to be cleared. */ @@ -4870,8 +5481,7 @@ static void igb_update_rx_dca(struct igb_adapter *adapter, if (hw->mac.type != e1000_82575) rxctrl <<= E1000_DCA_RXCTRL_CPUID_SHIFT; - /* - * We can enable relaxed ordering for reads, but not writes when + /* We can enable relaxed ordering for reads, but not writes when * DCA is enabled. This is due to a known issue in some chipsets * which will cause the DCA tag to be cleared. */ @@ -4940,7 +5550,8 @@ static int __igb_notify_dca(struct device *dev, void *data) case DCA_PROVIDER_REMOVE: if (adapter->flags & IGB_FLAG_DCA_ENABLED) { /* without this a class_device is left - * hanging around in the sysfs model */ + * hanging around in the sysfs model + */ dca_remove_requester(dev); dev_info(&pdev->dev, "DCA disabled\n"); adapter->flags &= ~IGB_FLAG_DCA_ENABLED; @@ -4953,12 +5564,12 @@ static int __igb_notify_dca(struct device *dev, void *data) } static int igb_notify_dca(struct notifier_block *nb, unsigned long event, - void *p) + void *p) { int ret_val; ret_val = driver_for_each_device(&igb_driver.driver, NULL, &event, - __igb_notify_dca); + __igb_notify_dca); return ret_val ? NOTIFY_BAD : NOTIFY_DONE; } @@ -4969,43 +5580,13 @@ static int igb_vf_configure(struct igb_adapter *adapter, int vf) { unsigned char mac_addr[ETH_ALEN]; - eth_random_addr(mac_addr); + eth_zero_addr(mac_addr); igb_set_vf_mac(adapter, vf, mac_addr); - return 0; -} + /* By default spoof check is enabled for all VFs */ + adapter->vf_data[vf].spoofchk_enabled = true; -static bool igb_vfs_are_assigned(struct igb_adapter *adapter) -{ - struct pci_dev *pdev = adapter->pdev; - struct pci_dev *vfdev; - int dev_id; - - switch (adapter->hw.mac.type) { - case e1000_82576: - dev_id = IGB_82576_VF_DEV_ID; - break; - case e1000_i350: - dev_id = IGB_I350_VF_DEV_ID; - break; - default: - return false; - } - - /* loop through all the VFs to see if we own any that are assigned */ - vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, dev_id, NULL); - while (vfdev) { - /* if we don't own it we don't care */ - if (vfdev->is_virtfn && vfdev->physfn == pdev) { - /* if it is assigned we cannot release it */ - if (vfdev->dev_flags & PCI_DEV_FLAGS_ASSIGNED) - return true; - } - - vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, dev_id, vfdev); - } - - return false; + return 0; } #endif @@ -5030,7 +5611,7 @@ static int igb_set_vf_promisc(struct igb_adapter *adapter, u32 *msgbuf, u32 vf) struct vf_data_storage *vf_data = &adapter->vf_data[vf]; vf_data->flags &= ~(IGB_VF_FLAG_UNI_PROMISC | - IGB_VF_FLAG_MULTI_PROMISC); + IGB_VF_FLAG_MULTI_PROMISC); vmolr &= ~(E1000_VMOLR_ROPE | E1000_VMOLR_ROMPE | E1000_VMOLR_MPME); if (*msgbuf & E1000_VF_SET_PROMISC_MULTICAST) { @@ -5038,8 +5619,7 @@ static int igb_set_vf_promisc(struct igb_adapter *adapter, u32 *msgbuf, u32 vf) vf_data->flags |= IGB_VF_FLAG_MULTI_PROMISC; *msgbuf &= ~E1000_VF_SET_PROMISC_MULTICAST; } else { - /* - * if we have hashes and we are clearing a multicast promisc + /* if we have hashes and we are clearing a multicast promisc * flag we need to write the hashes to the MTA as this step * was previously skipped */ @@ -5047,6 +5627,7 @@ static int igb_set_vf_promisc(struct igb_adapter *adapter, u32 *msgbuf, u32 vf) vmolr |= E1000_VMOLR_MPME; } else if (vf_data->num_vf_mc_hashes) { int j; + vmolr |= E1000_VMOLR_ROMPE; for (j = 0; j < vf_data->num_vf_mc_hashes; j++) igb_mta_set(hw, vf_data->vf_mc_hashes[j]); @@ -5060,7 +5641,6 @@ static int igb_set_vf_promisc(struct igb_adapter *adapter, u32 *msgbuf, u32 vf) return -EINVAL; return 0; - } static int igb_set_vf_multicasts(struct igb_adapter *adapter, @@ -5099,6 +5679,7 @@ static void igb_restore_vf_multicasts(struct igb_adapter *adapter) for (i = 0; i < adapter->vfs_allocated_count; i++) { u32 vmolr = rd32(E1000_VMOLR(i)); + vmolr &= ~(E1000_VMOLR_ROMPE | E1000_VMOLR_MPME); vf_data = &adapter->vf_data[i]; @@ -5197,6 +5778,7 @@ static s32 igb_vlvf_set(struct igb_adapter *adapter, u32 vid, bool add, u32 vf) if (!adapter->vf_data[vf].vlans_enabled) { u32 size; + reg = rd32(E1000_VMOLR(vf)); size = reg & E1000_VMOLR_RLPML_MASK; size += 4; @@ -5225,6 +5807,7 @@ static s32 igb_vlvf_set(struct igb_adapter *adapter, u32 vid, bool add, u32 vf) adapter->vf_data[vf].vlans_enabled--; if (!adapter->vf_data[vf].vlans_enabled) { u32 size; + reg = rd32(E1000_VMOLR(vf)); size = reg & E1000_VMOLR_RLPML_MASK; size -= 4; @@ -5267,30 +5850,91 @@ static int igb_ndo_set_vf_vlan(struct net_device *netdev, "Setting VLAN %d, QOS 0x%x on VF %d\n", vlan, qos, vf); if (test_bit(__IGB_DOWN, &adapter->state)) { dev_warn(&adapter->pdev->dev, - "The VF VLAN has been set," - " but the PF device is not up.\n"); + "The VF VLAN has been set, but the PF device is not up.\n"); dev_warn(&adapter->pdev->dev, - "Bring the PF device up before" - " attempting to use the VF device.\n"); + "Bring the PF device up before attempting to use the VF device.\n"); } } else { igb_vlvf_set(adapter, adapter->vf_data[vf].pf_vlan, - false, vf); + false, vf); igb_set_vmvir(adapter, vlan, vf); igb_set_vmolr(adapter, vf, true); adapter->vf_data[vf].pf_vlan = 0; adapter->vf_data[vf].pf_qos = 0; - } + } out: - return err; + return err; +} + +static int igb_find_vlvf_entry(struct igb_adapter *adapter, int vid) +{ + struct e1000_hw *hw = &adapter->hw; + int i; + u32 reg; + + /* Find the vlan filter for this id */ + for (i = 0; i < E1000_VLVF_ARRAY_SIZE; i++) { + reg = rd32(E1000_VLVF(i)); + if ((reg & E1000_VLVF_VLANID_ENABLE) && + vid == (reg & E1000_VLVF_VLANID_MASK)) + break; + } + + if (i >= E1000_VLVF_ARRAY_SIZE) + i = -1; + + return i; } static int igb_set_vf_vlan(struct igb_adapter *adapter, u32 *msgbuf, u32 vf) { + struct e1000_hw *hw = &adapter->hw; int add = (msgbuf[0] & E1000_VT_MSGINFO_MASK) >> E1000_VT_MSGINFO_SHIFT; int vid = (msgbuf[1] & E1000_VLVF_VLANID_MASK); + int err = 0; + + /* If in promiscuous mode we need to make sure the PF also has + * the VLAN filter set. + */ + if (add && (adapter->netdev->flags & IFF_PROMISC)) + err = igb_vlvf_set(adapter, vid, add, + adapter->vfs_allocated_count); + if (err) + goto out; + + err = igb_vlvf_set(adapter, vid, add, vf); - return igb_vlvf_set(adapter, vid, add, vf); + if (err) + goto out; + + /* Go through all the checks to see if the VLAN filter should + * be wiped completely. + */ + if (!add && (adapter->netdev->flags & IFF_PROMISC)) { + u32 vlvf, bits; + int regndx = igb_find_vlvf_entry(adapter, vid); + + if (regndx < 0) + goto out; + /* See if any other pools are set for this VLAN filter + * entry other than the PF. + */ + vlvf = bits = rd32(E1000_VLVF(regndx)); + bits &= 1 << (E1000_VLVF_POOLSEL_SHIFT + + adapter->vfs_allocated_count); + /* If the filter was removed then ensure PF pool bit + * is cleared if the PF only added itself to the pool + * because the PF is in promiscuous mode. + */ + if ((vlvf & VLAN_VID_MASK) == vid && + !test_bit(vid, adapter->active_vlans) && + !bits) + igb_vlvf_set(adapter, vid, add, + adapter->vfs_allocated_count); + } + +out: + return err; } static inline void igb_vf_reset(struct igb_adapter *adapter, u32 vf) @@ -5322,9 +5966,9 @@ static void igb_vf_reset_event(struct igb_adapter *adapter, u32 vf) { unsigned char *vf_mac = adapter->vf_data[vf].vf_mac_addresses; - /* generate a new mac address as we were hotplug removed/added */ + /* clear mac address as we were hotplug removed/added */ if (!(adapter->vf_data[vf].flags & IGB_VF_FLAG_PF_SET_MAC)) - eth_random_addr(vf_mac); + eth_zero_addr(vf_mac); /* process remaining reset events */ igb_vf_reset(adapter, vf); @@ -5354,14 +5998,13 @@ static void igb_vf_reset_msg(struct igb_adapter *adapter, u32 vf) /* reply to reset with ack and vf mac address */ msgbuf[0] = E1000_VF_RESET | E1000_VT_MSGTYPE_ACK; - memcpy(addr, vf_mac, 6); + memcpy(addr, vf_mac, ETH_ALEN); igb_write_mbx(hw, msgbuf, 3, vf); } static int igb_set_vf_mac_addr(struct igb_adapter *adapter, u32 *msg, int vf) { - /* - * The VF MAC Address is stored in a packed array of bytes + /* The VF MAC Address is stored in a packed array of bytes * starting at the second 32 bit word of the msg array */ unsigned char *addr = (char *)&msg[1]; @@ -5410,11 +6053,9 @@ static void igb_rcv_msg_from_vf(struct igb_adapter *adapter, u32 vf) if (msgbuf[0] & (E1000_VT_MSGTYPE_ACK | E1000_VT_MSGTYPE_NACK)) return; - /* - * until the vf completes a reset it should not be + /* until the vf completes a reset it should not be * allowed to start any configuration. */ - if (msgbuf[0] == E1000_VF_RESET) { igb_vf_reset_msg(adapter, vf); return; @@ -5434,9 +6075,8 @@ static void igb_rcv_msg_from_vf(struct igb_adapter *adapter, u32 vf) retval = igb_set_vf_mac_addr(adapter, msgbuf, vf); else dev_warn(&pdev->dev, - "VF %d attempted to override administratively " - "set MAC address\nReload the VF driver to " - "resume operations\n", vf); + "VF %d attempted to override administratively set MAC address\nReload the VF driver to resume operations\n", + vf); break; case E1000_VF_SET_PROMISC: retval = igb_set_vf_promisc(adapter, msgbuf, vf); @@ -5451,9 +6091,8 @@ static void igb_rcv_msg_from_vf(struct igb_adapter *adapter, u32 vf) retval = -1; if (vf_data->pf_vlan) dev_warn(&pdev->dev, - "VF %d attempted to override administratively " - "set VLAN tag\nReload the VF driver to " - "resume operations\n", vf); + "VF %d attempted to override administratively set VLAN tag\nReload the VF driver to resume operations\n", + vf); else retval = igb_set_vf_vlan(adapter, msgbuf, vf); break; @@ -5522,9 +6161,9 @@ static void igb_set_uta(struct igb_adapter *adapter) } /** - * igb_intr_msi - Interrupt Handler - * @irq: interrupt number - * @data: pointer to a network interface device structure + * igb_intr_msi - Interrupt Handler + * @irq: interrupt number + * @data: pointer to a network interface device structure **/ static irqreturn_t igb_intr_msi(int irq, void *data) { @@ -5567,9 +6206,9 @@ static irqreturn_t igb_intr_msi(int irq, void *data) } /** - * igb_intr - Legacy Interrupt Handler - * @irq: interrupt number - * @data: pointer to a network interface device structure + * igb_intr - Legacy Interrupt Handler + * @irq: interrupt number + * @data: pointer to a network interface device structure **/ static irqreturn_t igb_intr(int irq, void *data) { @@ -5577,11 +6216,13 @@ static irqreturn_t igb_intr(int irq, void *data) struct igb_q_vector *q_vector = adapter->q_vector[0]; struct e1000_hw *hw = &adapter->hw; /* Interrupt Auto-Mask...upon reading ICR, interrupts are masked. No - * need for the IMC write */ + * need for the IMC write + */ u32 icr = rd32(E1000_ICR); /* IMS will not auto-mask if INT_ASSERTED is not set, and if it is - * not set, then the adapter didn't send an interrupt */ + * not set, then the adapter didn't send an interrupt + */ if (!(icr & E1000_ICR_INT_ASSERTED)) return IRQ_NONE; @@ -5632,7 +6273,7 @@ static void igb_ring_irq_enable(struct igb_q_vector *q_vector) } if (!test_bit(__IGB_DOWN, &adapter->state)) { - if (adapter->msix_entries) + if (adapter->flags & IGB_FLAG_HAS_MSIX) wr32(E1000_EIMS, q_vector->eims_value); else igb_irq_enable(adapter); @@ -5640,15 +6281,15 @@ static void igb_ring_irq_enable(struct igb_q_vector *q_vector) } /** - * igb_poll - NAPI Rx polling callback - * @napi: napi polling structure - * @budget: count of how many packets we should handle + * igb_poll - NAPI Rx polling callback + * @napi: napi polling structure + * @budget: count of how many packets we should handle **/ static int igb_poll(struct napi_struct *napi, int budget) { struct igb_q_vector *q_vector = container_of(napi, - struct igb_q_vector, - napi); + struct igb_q_vector, + napi); bool clean_complete = true; #ifdef CONFIG_IGB_DCA @@ -5673,10 +6314,10 @@ static int igb_poll(struct napi_struct *napi, int budget) } /** - * igb_clean_tx_irq - Reclaim resources after transmit completes - * @q_vector: pointer to q_vector containing needed info + * igb_clean_tx_irq - Reclaim resources after transmit completes + * @q_vector: pointer to q_vector containing needed info * - * returns true if ring is completely cleaned + * returns true if ring is completely cleaned **/ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) { @@ -5703,7 +6344,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) break; /* prevent any other reads prior to eop_desc */ - rmb(); + read_barrier_depends(); /* if DD is not set pending work has not been completed */ if (!(eop_desc->wb.status & cpu_to_le32(E1000_TXD_STAT_DD))) @@ -5782,7 +6423,8 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) struct e1000_hw *hw = &adapter->hw; /* Detect a transmit hang in hardware, this serializes the - * check with the clearing of time_stamp and movement of i */ + * check with the clearing of time_stamp and movement of i + */ clear_bit(IGB_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags); if (tx_buffer->next_to_watch && time_after(jiffies, tx_buffer->time_stamp + @@ -5819,9 +6461,10 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) } } +#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2) if (unlikely(total_packets && - netif_carrier_ok(tx_ring->netdev) && - igb_desc_unused(tx_ring) >= IGB_TX_QUEUE_WAKE)) { + netif_carrier_ok(tx_ring->netdev) && + igb_desc_unused(tx_ring) >= TX_WAKE_THRESHOLD)) { /* Make sure that anybody stopping the queue after this * sees the new next_to_clean. */ @@ -5842,11 +6485,11 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) } /** - * igb_reuse_rx_page - page flip buffer and store it back on the ring - * @rx_ring: rx descriptor ring to store buffers on - * @old_buff: donor buffer to have page reused + * igb_reuse_rx_page - page flip buffer and store it back on the ring + * @rx_ring: rx descriptor ring to store buffers on + * @old_buff: donor buffer to have page reused * - * Synchronizes page for reuse by the adapter + * Synchronizes page for reuse by the adapter **/ static void igb_reuse_rx_page(struct igb_ring *rx_ring, struct igb_rx_buffer *old_buff) @@ -5861,7 +6504,7 @@ static void igb_reuse_rx_page(struct igb_ring *rx_ring, rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; /* transfer page from old buffer to new buffer */ - memcpy(new_buff, old_buff, sizeof(struct igb_rx_buffer)); + *new_buff = *old_buff; /* sync the buffer for use by the device */ dma_sync_single_range_for_device(rx_ring->dev, old_buff->dma, @@ -5870,20 +6513,55 @@ static void igb_reuse_rx_page(struct igb_ring *rx_ring, DMA_FROM_DEVICE); } +static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, + struct page *page, + unsigned int truesize) +{ + /* avoid re-using remote pages */ + if (unlikely(page_to_nid(page) != numa_node_id())) + return false; + +#if (PAGE_SIZE < 8192) + /* if we are only owner of page we can reuse it */ + if (unlikely(page_count(page) != 1)) + return false; + + /* flip page offset to other buffer */ + rx_buffer->page_offset ^= IGB_RX_BUFSZ; + + /* since we are the only owner of the page and we need to + * increment it, just set the value to 2 in order to avoid + * an unnecessary locked operation + */ + atomic_set(&page->_count, 2); +#else + /* move offset up to the next cache line */ + rx_buffer->page_offset += truesize; + + if (rx_buffer->page_offset > (PAGE_SIZE - IGB_RX_BUFSZ)) + return false; + + /* bump ref count on page before it is given to the stack */ + get_page(page); +#endif + + return true; +} + /** - * igb_add_rx_frag - Add contents of Rx buffer to sk_buff - * @rx_ring: rx descriptor ring to transact packets on - * @rx_buffer: buffer containing page to add - * @rx_desc: descriptor containing length of buffer written by hardware - * @skb: sk_buff to place the data into + * igb_add_rx_frag - Add contents of Rx buffer to sk_buff + * @rx_ring: rx descriptor ring to transact packets on + * @rx_buffer: buffer containing page to add + * @rx_desc: descriptor containing length of buffer written by hardware + * @skb: sk_buff to place the data into * - * This function will add the data contained in rx_buffer->page to the skb. - * This is done either through a direct copy if the data in the buffer is - * less than the skb header size, otherwise it will just attach the page as - * a frag to the skb. + * This function will add the data contained in rx_buffer->page to the skb. + * This is done either through a direct copy if the data in the buffer is + * less than the skb header size, otherwise it will just attach the page as + * a frag to the skb. * - * The function will then update the page offset if necessary and return - * true if the buffer can be reused by the adapter. + * The function will then update the page offset if necessary and return + * true if the buffer can be reused by the adapter. **/ static bool igb_add_rx_frag(struct igb_ring *rx_ring, struct igb_rx_buffer *rx_buffer, @@ -5892,6 +6570,11 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring, { struct page *page = rx_buffer->page; unsigned int size = le16_to_cpu(rx_desc->wb.upper.length); +#if (PAGE_SIZE < 8192) + unsigned int truesize = IGB_RX_BUFSZ; +#else + unsigned int truesize = ALIGN(size, L1_CACHE_BYTES); +#endif if ((size <= IGB_RX_HDR_LEN) && !skb_is_nonlinear(skb)) { unsigned char *va = page_address(page) + rx_buffer->page_offset; @@ -5914,38 +6597,9 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring, } skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, - rx_buffer->page_offset, size, IGB_RX_BUFSZ); + rx_buffer->page_offset, size, truesize); - /* avoid re-using remote pages */ - if (unlikely(page_to_nid(page) != numa_node_id())) - return false; - -#if (PAGE_SIZE < 8192) - /* if we are only owner of page we can reuse it */ - if (unlikely(page_count(page) != 1)) - return false; - - /* flip page offset to other buffer */ - rx_buffer->page_offset ^= IGB_RX_BUFSZ; - - /* - * since we are the only owner of the page and we need to - * increment it, just set the value to 2 in order to avoid - * an unnecessary locked operation - */ - atomic_set(&page->_count, 2); -#else - /* move offset up to the next cache line */ - rx_buffer->page_offset += SKB_DATA_ALIGN(size); - - if (rx_buffer->page_offset > (PAGE_SIZE - IGB_RX_BUFSZ)) - return false; - - /* bump ref count on page before it is given to the stack */ - get_page(page); -#endif - - return true; + return igb_can_reuse_rx_page(rx_buffer, page, truesize); } static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring, @@ -5957,13 +6611,6 @@ static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring, rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; - /* - * This memory barrier is needed to keep us from reading - * any other fields out of the rx_desc until we know the - * RXD_STAT_DD bit is set - */ - rmb(); - page = rx_buffer->page; prefetchw(page); @@ -5985,8 +6632,7 @@ static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring, return NULL; } - /* - * we will be copying header into skb->data in + /* we will be copying header into skb->data in * pskb_may_pull so it is in our interest to prefetch * it now to avoid a possible cache miss */ @@ -6034,8 +6680,7 @@ static inline void igb_rx_checksum(struct igb_ring *ring, if (igb_test_staterr(rx_desc, E1000_RXDEXT_STATERR_TCPE | E1000_RXDEXT_STATERR_IPE)) { - /* - * work around errata with sctp packets where the TCPE aka + /* work around errata with sctp packets where the TCPE aka * L4E bit is set incorrectly on 64 byte (60 byte w/o crc) * packets, (aka let the stack check the crc32c) */ @@ -6062,19 +6707,21 @@ static inline void igb_rx_hash(struct igb_ring *ring, struct sk_buff *skb) { if (ring->netdev->features & NETIF_F_RXHASH) - skb->rxhash = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss); + skb_set_hash(skb, + le32_to_cpu(rx_desc->wb.lower.hi_dword.rss), + PKT_HASH_TYPE_L3); } /** - * igb_is_non_eop - process handling of non-EOP buffers - * @rx_ring: Rx ring being processed - * @rx_desc: Rx descriptor for current buffer - * @skb: current socket buffer containing buffer in progress + * igb_is_non_eop - process handling of non-EOP buffers + * @rx_ring: Rx ring being processed + * @rx_desc: Rx descriptor for current buffer + * @skb: current socket buffer containing buffer in progress * - * This function updates next to clean. If the buffer is an EOP buffer - * this function exits returning false, otherwise it will place the - * sk_buff in the next buffer to be chained and return true indicating - * that this is in fact a non-EOP buffer. + * This function updates next to clean. If the buffer is an EOP buffer + * this function exits returning false, otherwise it will place the + * sk_buff in the next buffer to be chained and return true indicating + * that this is in fact a non-EOP buffer. **/ static bool igb_is_non_eop(struct igb_ring *rx_ring, union e1000_adv_rx_desc *rx_desc) @@ -6094,15 +6741,15 @@ static bool igb_is_non_eop(struct igb_ring *rx_ring, } /** - * igb_get_headlen - determine size of header for LRO/GRO - * @data: pointer to the start of the headers - * @max_len: total length of section to find headers in + * igb_get_headlen - determine size of header for LRO/GRO + * @data: pointer to the start of the headers + * @max_len: total length of section to find headers in * - * This function is meant to determine the length of headers that will - * be recognized by hardware for LRO, and GRO offloads. The main - * motivation of doing this is to only perform one pull for IPv4 TCP - * packets so that we can do basic things like calculating the gso_size - * based on the average data per packet. + * This function is meant to determine the length of headers that will + * be recognized by hardware for LRO, and GRO offloads. The main + * motivation of doing this is to only perform one pull for IPv4 TCP + * packets so that we can do basic things like calculating the gso_size + * based on the average data per packet. **/ static unsigned int igb_get_headlen(unsigned char *data, unsigned int max_len) @@ -6132,7 +6779,7 @@ static unsigned int igb_get_headlen(unsigned char *data, hdr.network += ETH_HLEN; /* handle any vlan tag if present */ - if (protocol == __constant_htons(ETH_P_8021Q)) { + if (protocol == htons(ETH_P_8021Q)) { if ((hdr.network - data) > (max_len - VLAN_HLEN)) return max_len; @@ -6141,7 +6788,7 @@ static unsigned int igb_get_headlen(unsigned char *data, } /* handle L3 protocols */ - if (protocol == __constant_htons(ETH_P_IP)) { + if (protocol == htons(ETH_P_IP)) { if ((hdr.network - data) > (max_len - sizeof(struct iphdr))) return max_len; @@ -6153,9 +6800,9 @@ static unsigned int igb_get_headlen(unsigned char *data, return hdr.network - data; /* record next protocol if header is present */ - if (!hdr.ipv4->frag_off) + if (!(hdr.ipv4->frag_off & htons(IP_OFFSET))) nexthdr = hdr.ipv4->protocol; - } else if (protocol == __constant_htons(ETH_P_IPV6)) { + } else if (protocol == htons(ETH_P_IPV6)) { if ((hdr.network - data) > (max_len - sizeof(struct ipv6hdr))) return max_len; @@ -6189,8 +6836,7 @@ static unsigned int igb_get_headlen(unsigned char *data, hdr.network += sizeof(struct udphdr); } - /* - * If everything has gone correctly hdr.network should be the + /* If everything has gone correctly hdr.network should be the * data section of the packet and will be the end of the header. * If not then it probably represents the end of the last recognized * header. @@ -6202,17 +6848,17 @@ static unsigned int igb_get_headlen(unsigned char *data, } /** - * igb_pull_tail - igb specific version of skb_pull_tail - * @rx_ring: rx descriptor ring packet is being transacted on - * @rx_desc: pointer to the EOP Rx descriptor - * @skb: pointer to current skb being adjusted + * igb_pull_tail - igb specific version of skb_pull_tail + * @rx_ring: rx descriptor ring packet is being transacted on + * @rx_desc: pointer to the EOP Rx descriptor + * @skb: pointer to current skb being adjusted * - * This function is an igb specific version of __pskb_pull_tail. The - * main difference between this version and the original function is that - * this function can make several assumptions about the state of things - * that allow for significant optimizations versus the standard function. - * As a result we can do things like drop a frag and maintain an accurate - * truesize for the skb. + * This function is an igb specific version of __pskb_pull_tail. The + * main difference between this version and the original function is that + * this function can make several assumptions about the state of things + * that allow for significant optimizations versus the standard function. + * As a result we can do things like drop a frag and maintain an accurate + * truesize for the skb. */ static void igb_pull_tail(struct igb_ring *rx_ring, union e1000_adv_rx_desc *rx_desc, @@ -6222,8 +6868,7 @@ static void igb_pull_tail(struct igb_ring *rx_ring, unsigned char *va; unsigned int pull_len; - /* - * it is valid to use page_address instead of kmap since we are + /* it is valid to use page_address instead of kmap since we are * working with pages allocated out of the lomem pool per * alloc_page(GFP_ATOMIC) */ @@ -6243,8 +6888,7 @@ static void igb_pull_tail(struct igb_ring *rx_ring, va += IGB_TS_HDR_LEN; } - /* - * we need the header to contain the greater of either ETH_HLEN or + /* we need the header to contain the greater of either ETH_HLEN or * 60 bytes if the skb->len is less than 60 for skb_pad. */ pull_len = igb_get_headlen(va, IGB_RX_HDR_LEN); @@ -6260,24 +6904,23 @@ static void igb_pull_tail(struct igb_ring *rx_ring, } /** - * igb_cleanup_headers - Correct corrupted or empty headers - * @rx_ring: rx descriptor ring packet is being transacted on - * @rx_desc: pointer to the EOP Rx descriptor - * @skb: pointer to current skb being fixed + * igb_cleanup_headers - Correct corrupted or empty headers + * @rx_ring: rx descriptor ring packet is being transacted on + * @rx_desc: pointer to the EOP Rx descriptor + * @skb: pointer to current skb being fixed * - * Address the case where we are pulling data in on pages only - * and as such no data is present in the skb header. + * Address the case where we are pulling data in on pages only + * and as such no data is present in the skb header. * - * In addition if skb is not at least 60 bytes we need to pad it so that - * it is large enough to qualify as a valid Ethernet frame. + * In addition if skb is not at least 60 bytes we need to pad it so that + * it is large enough to qualify as a valid Ethernet frame. * - * Returns true if an error was encountered and skb was freed. + * Returns true if an error was encountered and skb was freed. **/ static bool igb_cleanup_headers(struct igb_ring *rx_ring, union e1000_adv_rx_desc *rx_desc, struct sk_buff *skb) { - if (unlikely((igb_test_staterr(rx_desc, E1000_RXDEXT_ERR_FRAME_ERR_MASK)))) { struct net_device *netdev = rx_ring->netdev; @@ -6304,14 +6947,14 @@ static bool igb_cleanup_headers(struct igb_ring *rx_ring, } /** - * igb_process_skb_fields - Populate skb header fields from Rx descriptor - * @rx_ring: rx descriptor ring packet is being transacted on - * @rx_desc: pointer to the EOP Rx descriptor - * @skb: pointer to current skb being populated + * igb_process_skb_fields - Populate skb header fields from Rx descriptor + * @rx_ring: rx descriptor ring packet is being transacted on + * @rx_desc: pointer to the EOP Rx descriptor + * @skb: pointer to current skb being populated * - * This function checks the ring, descriptor, and packet information in - * order to populate the hash, checksum, VLAN, timestamp, protocol, and - * other fields within the skb. + * This function checks the ring, descriptor, and packet information in + * order to populate the hash, checksum, VLAN, timestamp, protocol, and + * other fields within the skb. **/ static void igb_process_skb_fields(struct igb_ring *rx_ring, union e1000_adv_rx_desc *rx_desc, @@ -6323,18 +6966,21 @@ static void igb_process_skb_fields(struct igb_ring *rx_ring, igb_rx_checksum(rx_ring, rx_desc, skb); - igb_ptp_rx_hwtstamp(rx_ring->q_vector, rx_desc, skb); + if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TS) && + !igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) + igb_ptp_rx_rgtstamp(rx_ring->q_vector, skb); - if ((dev->features & NETIF_F_HW_VLAN_RX) && + if ((dev->features & NETIF_F_HW_VLAN_CTAG_RX) && igb_test_staterr(rx_desc, E1000_RXD_STAT_VP)) { u16 vid; + if (igb_test_staterr(rx_desc, E1000_RXDEXT_STATERR_LB) && test_bit(IGB_RING_FLAG_RX_LB_VLAN_BSWAP, &rx_ring->flags)) vid = be16_to_cpu(rx_desc->wb.upper.vlan); else vid = le16_to_cpu(rx_desc->wb.upper.vlan); - __vlan_hwaccel_put_tag(skb, vid); + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid); } skb_record_rx_queue(skb, rx_ring->queue_index); @@ -6349,7 +6995,7 @@ static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) unsigned int total_bytes = 0, total_packets = 0; u16 cleaned_count = igb_desc_unused(rx_ring); - do { + while (likely(total_packets < budget)) { union e1000_adv_rx_desc *rx_desc; /* return some buffers to hardware, one at a time is too slow */ @@ -6363,6 +7009,12 @@ static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) if (!igb_test_staterr(rx_desc, E1000_RXD_STAT_DD)) break; + /* This memory barrier is needed to keep us from reading + * any other fields out of the rx_desc until we know the + * RXD_STAT_DD bit is set + */ + rmb(); + /* retrieve a buffer from the ring */ skb = igb_fetch_rx_buffer(rx_ring, rx_desc, skb); @@ -6395,7 +7047,7 @@ static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) /* update budget accounting */ total_packets++; - } while (likely(total_packets < budget)); + } /* place incomplete frames back on ring for completion */ rx_ring->skb = skb; @@ -6410,7 +7062,7 @@ static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) if (cleaned_count) igb_alloc_rx_buffers(rx_ring, cleaned_count); - return (total_packets < budget); + return total_packets < budget; } static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, @@ -6433,8 +7085,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, /* map page for use */ dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE); - /* - * if mapping failed free memory back to system since + /* if mapping failed free memory back to system since * there isn't much point in holding memory we can't use */ if (dma_mapping_error(rx_ring->dev, dma)) { @@ -6452,8 +7103,8 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, } /** - * igb_alloc_rx_buffers - Replace used receive buffers; packet split - * @adapter: address of board private structure + * igb_alloc_rx_buffers - Replace used receive buffers; packet split + * @adapter: address of board private structure **/ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) { @@ -6473,8 +7124,7 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) if (!igb_alloc_mapped_page(rx_ring, bi)) break; - /* - * Refresh the desc even if buffer_addrs didn't change + /* Refresh the desc even if buffer_addrs didn't change * because each write-back erases this info. */ rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset); @@ -6503,8 +7153,7 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) /* update next to alloc since we have filled the ring */ rx_ring->next_to_alloc = i; - /* - * Force memory writes to complete before letting h/w + /* 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). @@ -6534,7 +7183,7 @@ static int igb_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) break; case SIOCGMIIREG: if (igb_read_phy_reg(&adapter->hw, data->reg_num & 0x1F, - &data->val_out)) + &data->val_out)) return -EIO; break; case SIOCSMIIREG: @@ -6557,13 +7206,29 @@ static int igb_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) case SIOCGMIIREG: case SIOCSMIIREG: return igb_mii_ioctl(netdev, ifr, cmd); + case SIOCGHWTSTAMP: + return igb_ptp_get_ts_config(netdev, ifr); case SIOCSHWTSTAMP: - return igb_ptp_hwtstamp_ioctl(netdev, ifr, cmd); + return igb_ptp_set_ts_config(netdev, ifr); default: return -EOPNOTSUPP; } } +void igb_read_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value) +{ + struct igb_adapter *adapter = hw->back; + + pci_read_config_word(adapter->pdev, reg, value); +} + +void igb_write_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value) +{ + struct igb_adapter *adapter = hw->back; + + pci_write_config_word(adapter->pdev, reg, *value); +} + s32 igb_read_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value) { struct igb_adapter *adapter = hw->back; @@ -6589,7 +7254,7 @@ static void igb_vlan_mode(struct net_device *netdev, netdev_features_t features) struct igb_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; u32 ctrl, rctl; - bool enable = !!(features & NETIF_F_HW_VLAN_RX); + bool enable = !!(features & NETIF_F_HW_VLAN_CTAG_RX); if (enable) { /* enable VLAN tag insert/strip */ @@ -6611,7 +7276,8 @@ static void igb_vlan_mode(struct net_device *netdev, netdev_features_t features) igb_rlpml_set(adapter); } -static int igb_vlan_rx_add_vid(struct net_device *netdev, u16 vid) +static int igb_vlan_rx_add_vid(struct net_device *netdev, + __be16 proto, u16 vid) { struct igb_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; @@ -6628,7 +7294,8 @@ static int igb_vlan_rx_add_vid(struct net_device *netdev, u16 vid) return 0; } -static int igb_vlan_rx_kill_vid(struct net_device *netdev, u16 vid) +static int igb_vlan_rx_kill_vid(struct net_device *netdev, + __be16 proto, u16 vid) { struct igb_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; @@ -6654,7 +7321,7 @@ static void igb_restore_vlan(struct igb_adapter *adapter) igb_vlan_mode(adapter->netdev, adapter->netdev->features); for_each_set_bit(vid, adapter->active_vlans, VLAN_N_VID) - igb_vlan_rx_add_vid(adapter->netdev, vid); + igb_vlan_rx_add_vid(adapter->netdev, htons(ETH_P_8021Q), vid); } int igb_set_spd_dplx(struct igb_adapter *adapter, u32 spd, u8 dplx) @@ -6665,15 +7332,24 @@ int igb_set_spd_dplx(struct igb_adapter *adapter, u32 spd, u8 dplx) mac->autoneg = 0; /* Make sure dplx is at most 1 bit and lsb of speed is not set - * for the switch() below to work */ + * for the switch() below to work + */ if ((spd & 1) || (dplx & ~1)) goto err_inval; - /* Fiber NIC's only allow 1000 Gbps Full duplex */ - if ((adapter->hw.phy.media_type == e1000_media_type_internal_serdes) && - spd != SPEED_1000 && - dplx != DUPLEX_FULL) - goto err_inval; + /* Fiber NIC's only allow 1000 gbps Full duplex + * and 100Mbps Full duplex for 100baseFx sfp + */ + if (adapter->hw.phy.media_type == e1000_media_type_internal_serdes) { + switch (spd + dplx) { + case SPEED_10 + DUPLEX_HALF: + case SPEED_10 + DUPLEX_FULL: + case SPEED_100 + DUPLEX_HALF: + goto err_inval; + default: + break; + } + } switch (spd + dplx) { case SPEED_10 + DUPLEX_HALF: @@ -6772,7 +7448,8 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake, igb_power_up_link(adapter); /* Release control of h/w to f/w. If f/w is AMT enabled, this - * would have already happened in close and is redundant. */ + * would have already happened in close and is redundant. + */ igb_release_hw_control(adapter); pci_disable_device(pdev); @@ -6834,7 +7511,8 @@ static int igb_resume(struct device *dev) igb_reset(adapter); /* let the f/w know that the h/w is now under the control of the - * driver. */ + * driver. + */ igb_get_hw_control(adapter); wr32(E1000_WUS, ~0); @@ -6903,9 +7581,76 @@ static void igb_shutdown(struct pci_dev *pdev) } } +#ifdef CONFIG_PCI_IOV +static int igb_sriov_reinit(struct pci_dev *dev) +{ + struct net_device *netdev = pci_get_drvdata(dev); + struct igb_adapter *adapter = netdev_priv(netdev); + struct pci_dev *pdev = adapter->pdev; + + rtnl_lock(); + + if (netif_running(netdev)) + igb_close(netdev); + else + igb_reset(adapter); + + igb_clear_interrupt_scheme(adapter); + + igb_init_queue_configuration(adapter); + + if (igb_init_interrupt_scheme(adapter, true)) { + dev_err(&pdev->dev, "Unable to allocate memory for queues\n"); + return -ENOMEM; + } + + if (netif_running(netdev)) + igb_open(netdev); + + rtnl_unlock(); + + return 0; +} + +static int igb_pci_disable_sriov(struct pci_dev *dev) +{ + int err = igb_disable_sriov(dev); + + if (!err) + err = igb_sriov_reinit(dev); + + return err; +} + +static int igb_pci_enable_sriov(struct pci_dev *dev, int num_vfs) +{ + int err = igb_enable_sriov(dev, num_vfs); + + if (err) + goto out; + + err = igb_sriov_reinit(dev); + if (!err) + return num_vfs; + +out: + return err; +} + +#endif +static int igb_pci_sriov_configure(struct pci_dev *dev, int num_vfs) +{ +#ifdef CONFIG_PCI_IOV + if (num_vfs == 0) + return igb_pci_disable_sriov(dev); + else + return igb_pci_enable_sriov(dev, num_vfs); +#endif + return 0; +} + #ifdef CONFIG_NET_POLL_CONTROLLER -/* - * Polling 'interrupt' - used by things like netconsole to send skbs +/* 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. */ @@ -6918,7 +7663,7 @@ static void igb_netpoll(struct net_device *netdev) for (i = 0; i < adapter->num_q_vectors; i++) { q_vector = adapter->q_vector[i]; - if (adapter->msix_entries) + if (adapter->flags & IGB_FLAG_HAS_MSIX) wr32(E1000_EIMC, q_vector->eims_value); else igb_irq_disable(adapter); @@ -6928,13 +7673,13 @@ static void igb_netpoll(struct net_device *netdev) #endif /* CONFIG_NET_POLL_CONTROLLER */ /** - * igb_io_error_detected - called when PCI error is detected - * @pdev: Pointer to PCI device - * @state: The current pci connection state + * igb_io_error_detected - called when PCI error is detected + * @pdev: Pointer to PCI device + * @state: The current pci connection state * - * This function is called after a PCI bus error affecting - * this device has been detected. - */ + * This function is called after a PCI bus error affecting + * this device has been detected. + **/ static pci_ers_result_t igb_io_error_detected(struct pci_dev *pdev, pci_channel_state_t state) { @@ -6955,12 +7700,12 @@ static pci_ers_result_t igb_io_error_detected(struct pci_dev *pdev, } /** - * igb_io_slot_reset - called after the pci bus has been reset. - * @pdev: Pointer to PCI device + * igb_io_slot_reset - called after the pci bus has been reset. + * @pdev: Pointer to PCI device * - * Restart the card from scratch, as if from a cold-boot. Implementation - * resembles the first-half of the igb_resume routine. - */ + * Restart the card from scratch, as if from a cold-boot. Implementation + * resembles the first-half of the igb_resume routine. + **/ static pci_ers_result_t igb_io_slot_reset(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); @@ -6988,8 +7733,9 @@ static pci_ers_result_t igb_io_slot_reset(struct pci_dev *pdev) err = pci_cleanup_aer_uncorrect_error_status(pdev); if (err) { - dev_err(&pdev->dev, "pci_cleanup_aer_uncorrect_error_status " - "failed 0x%0x\n", err); + dev_err(&pdev->dev, + "pci_cleanup_aer_uncorrect_error_status failed 0x%0x\n", + err); /* non-fatal, continue */ } @@ -6997,12 +7743,12 @@ static pci_ers_result_t igb_io_slot_reset(struct pci_dev *pdev) } /** - * igb_io_resume - called when traffic can start flowing again. - * @pdev: Pointer to PCI device + * igb_io_resume - called when traffic can start flowing again. + * @pdev: Pointer to PCI device * - * This callback is called when the error recovery driver tells us that - * its OK to resume normal operation. Implementation resembles the - * second-half of the igb_resume routine. + * This callback is called when the error recovery driver tells us that + * its OK to resume normal operation. Implementation resembles the + * second-half of the igb_resume routine. */ static void igb_io_resume(struct pci_dev *pdev) { @@ -7019,12 +7765,13 @@ static void igb_io_resume(struct pci_dev *pdev) netif_device_attach(netdev); /* let the f/w know that the h/w is now under the control of the - * driver. */ + * driver. + */ igb_get_hw_control(adapter); } static void igb_rar_set_qsel(struct igb_adapter *adapter, u8 *addr, u32 index, - u8 qsel) + u8 qsel) { u32 rar_low, rar_high; struct e1000_hw *hw = &adapter->hw; @@ -7033,7 +7780,7 @@ static void igb_rar_set_qsel(struct igb_adapter *adapter, u8 *addr, u32 index, * from network order (big endian) to little endian */ rar_low = ((u32) addr[0] | ((u32) addr[1] << 8) | - ((u32) addr[2] << 16) | ((u32) addr[3] << 24)); + ((u32) addr[2] << 16) | ((u32) addr[3] << 24)); rar_high = ((u32) addr[4] | ((u32) addr[5] << 8)); /* Indicate to hardware the Address is Valid. */ @@ -7051,11 +7798,12 @@ static void igb_rar_set_qsel(struct igb_adapter *adapter, u8 *addr, u32 index, } static int igb_set_vf_mac(struct igb_adapter *adapter, - int vf, unsigned char *mac_addr) + int vf, unsigned char *mac_addr) { struct e1000_hw *hw = &adapter->hw; /* VF MAC addresses start at end of receive addresses and moves - * torwards the first, as a result a collision should not be possible */ + * towards the first, as a result a collision should not be possible + */ int rar_entry = hw->mac.rar_entry_count - (vf + 1); memcpy(adapter->vf_data[vf].vf_mac_addresses, mac_addr, ETH_ALEN); @@ -7072,13 +7820,13 @@ static int igb_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) return -EINVAL; adapter->vf_data[vf].flags |= IGB_VF_FLAG_PF_SET_MAC; dev_info(&adapter->pdev->dev, "setting MAC %pM on VF %d\n", mac, vf); - dev_info(&adapter->pdev->dev, "Reload the VF driver to make this" - " change effective."); + dev_info(&adapter->pdev->dev, + "Reload the VF driver to make this change effective."); if (test_bit(__IGB_DOWN, &adapter->state)) { - dev_warn(&adapter->pdev->dev, "The VF MAC address has been set," - " but the PF device is not up.\n"); - dev_warn(&adapter->pdev->dev, "Bring the PF device up before" - " attempting to use the VF device.\n"); + dev_warn(&adapter->pdev->dev, + "The VF MAC address has been set, but the PF device is not up.\n"); + dev_warn(&adapter->pdev->dev, + "Bring the PF device up before attempting to use the VF device.\n"); } return igb_set_vf_mac(adapter, vf, mac); } @@ -7105,19 +7853,19 @@ static void igb_set_vf_rate_limit(struct e1000_hw *hw, int vf, int tx_rate, /* Calculate the rate factor values to set */ rf_int = link_speed / tx_rate; rf_dec = (link_speed - (rf_int * tx_rate)); - rf_dec = (rf_dec * (1<<E1000_RTTBCNRC_RF_INT_SHIFT)) / tx_rate; + rf_dec = (rf_dec * (1 << E1000_RTTBCNRC_RF_INT_SHIFT)) / + tx_rate; bcnrc_val = E1000_RTTBCNRC_RS_ENA; - bcnrc_val |= ((rf_int<<E1000_RTTBCNRC_RF_INT_SHIFT) & - E1000_RTTBCNRC_RF_INT_MASK); + bcnrc_val |= ((rf_int << E1000_RTTBCNRC_RF_INT_SHIFT) & + E1000_RTTBCNRC_RF_INT_MASK); bcnrc_val |= (rf_dec & E1000_RTTBCNRC_RF_DEC_MASK); } else { bcnrc_val = 0; } wr32(E1000_RTTDQSEL, vf); /* vf X uses queue X */ - /* - * Set global transmit compensation time to the MMW_SIZE in RTTBCNRM + /* Set global transmit compensation time to the MMW_SIZE in RTTBCNRM * register. MMW_SIZE=0x014 if 9728-byte jumbo is supported. */ wr32(E1000_RTTBCNRM, 0x14); @@ -7139,8 +7887,7 @@ static void igb_check_vf_rate_limit(struct igb_adapter *adapter) reset_rate = true; adapter->vf_rate_link_speed = 0; dev_info(&adapter->pdev->dev, - "Link speed has been changed. VF Transmit " - "rate is disabled\n"); + "Link speed has been changed. VF Transmit rate is disabled\n"); } for (i = 0; i < adapter->vfs_allocated_count; i++) { @@ -7148,12 +7895,13 @@ static void igb_check_vf_rate_limit(struct igb_adapter *adapter) adapter->vf_data[i].tx_rate = 0; igb_set_vf_rate_limit(&adapter->hw, i, - adapter->vf_data[i].tx_rate, - actual_link_speed); + adapter->vf_data[i].tx_rate, + actual_link_speed); } } -static int igb_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate) +static int igb_ndo_set_vf_bw(struct net_device *netdev, int vf, + int min_tx_rate, int max_tx_rate) { struct igb_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; @@ -7162,16 +7910,47 @@ static int igb_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate) if (hw->mac.type != e1000_82576) return -EOPNOTSUPP; + if (min_tx_rate) + return -EINVAL; + actual_link_speed = igb_link_mbps(adapter->link_speed); if ((vf >= adapter->vfs_allocated_count) || (!(rd32(E1000_STATUS) & E1000_STATUS_LU)) || - (tx_rate < 0) || (tx_rate > actual_link_speed)) + (max_tx_rate < 0) || + (max_tx_rate > actual_link_speed)) return -EINVAL; adapter->vf_rate_link_speed = actual_link_speed; - adapter->vf_data[vf].tx_rate = (u16)tx_rate; - igb_set_vf_rate_limit(hw, vf, tx_rate, actual_link_speed); + adapter->vf_data[vf].tx_rate = (u16)max_tx_rate; + igb_set_vf_rate_limit(hw, vf, max_tx_rate, actual_link_speed); + + return 0; +} + +static int igb_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, + bool setting) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + u32 reg_val, reg_offset; + + if (!adapter->vfs_allocated_count) + return -EOPNOTSUPP; + + if (vf >= adapter->vfs_allocated_count) + return -EINVAL; + reg_offset = (hw->mac.type == e1000_82576) ? E1000_DTXSWC : E1000_TXSWC; + reg_val = rd32(reg_offset); + if (setting) + reg_val |= ((1 << vf) | + (1 << (vf + E1000_DTXSWC_VLAN_SPOOF_SHIFT))); + else + reg_val &= ~((1 << vf) | + (1 << (vf + E1000_DTXSWC_VLAN_SPOOF_SHIFT))); + wr32(reg_offset, reg_val); + + adapter->vf_data[vf].spoofchk_enabled = setting; return 0; } @@ -7183,9 +7962,11 @@ static int igb_ndo_get_vf_config(struct net_device *netdev, return -EINVAL; ivi->vf = vf; memcpy(&ivi->mac, adapter->vf_data[vf].vf_mac_addresses, ETH_ALEN); - ivi->tx_rate = adapter->vf_data[vf].tx_rate; + ivi->max_tx_rate = adapter->vf_data[vf].tx_rate; + ivi->min_tx_rate = 0; ivi->vlan = adapter->vf_data[vf].pf_vlan; ivi->qos = adapter->vf_data[vf].pf_qos; + ivi->spoofchk = adapter->vf_data[vf].spoofchk_enabled; return 0; } @@ -7198,6 +7979,7 @@ static void igb_vmm_control(struct igb_adapter *adapter) case e1000_82575: case e1000_i210: case e1000_i211: + case e1000_i354: default: /* replication is not supported for 82575 */ return; @@ -7206,11 +7988,13 @@ static void igb_vmm_control(struct igb_adapter *adapter) reg = rd32(E1000_DTXCTL); reg |= E1000_DTXCTL_VLAN_ADDED; wr32(E1000_DTXCTL, reg); + /* Fall through */ case e1000_82580: /* enable replication vlan tag stripping */ reg = rd32(E1000_RPLOLR); reg |= E1000_RPLOLR_STRVLAN; wr32(E1000_RPLOLR, reg); + /* Fall through */ case e1000_i350: /* none of the above registers are supported by i350 */ break; @@ -7220,7 +8004,7 @@ static void igb_vmm_control(struct igb_adapter *adapter) igb_vmdq_set_loopback_pf(hw, true); igb_vmdq_set_replication_pf(hw, true); igb_vmdq_set_anti_spoofing_pf(hw, true, - adapter->vfs_allocated_count); + adapter->vfs_allocated_count); } else { igb_vmdq_set_loopback_pf(hw, false); igb_vmdq_set_replication_pf(hw, false); @@ -7240,8 +8024,7 @@ static void igb_init_dmac(struct igb_adapter *adapter, u32 pba) /* force threshold to 0. */ wr32(E1000_DMCTXTH, 0); - /* - * DMA Coalescing high water mark needs to be greater + /* DMA Coalescing high water mark needs to be greater * than the Rx threshold. Set hwm to PBA - max frame * size in 16B units, capping it at PBA - 6KB. */ @@ -7254,8 +8037,7 @@ static void igb_init_dmac(struct igb_adapter *adapter, u32 pba) & E1000_FCRTC_RTH_COAL_MASK); wr32(E1000_FCRTC, reg); - /* - * Set the DMA Coalescing Rx threshold to PBA - 2 * max + /* Set the DMA Coalescing Rx threshold to PBA - 2 * max * frame size, capping it at PBA - 10KB. */ dmac_thr = pba - adapter->max_frame_size / 512; @@ -7273,11 +8055,12 @@ static void igb_init_dmac(struct igb_adapter *adapter, u32 pba) reg |= (1000 >> 5); /* Disable BMC-to-OS Watchdog Enable */ - reg &= ~E1000_DMACR_DC_BMC2OSW_EN; + if (hw->mac.type != e1000_i354) + reg &= ~E1000_DMACR_DC_BMC2OSW_EN; + wr32(E1000_DMACR, reg); - /* - * no lower threshold to disable + /* no lower threshold to disable * coalescing(smart fifb)-UTRESH=0 */ wr32(E1000_DMCRTRH, 0); @@ -7286,15 +8069,13 @@ static void igb_init_dmac(struct igb_adapter *adapter, u32 pba) wr32(E1000_DMCTLX, reg); - /* - * free space in tx packet buffer to wake from + /* free space in tx packet buffer to wake from * DMA coal */ wr32(E1000_DMCTXTH, (IGB_MIN_TXPBSIZE - (IGB_TX_BUF_4096 + adapter->max_frame_size)) >> 6); - /* - * make low power state decision controlled + /* make low power state decision controlled * by DMA coal */ reg = rd32(E1000_PCIEMISC); @@ -7303,9 +8084,101 @@ static void igb_init_dmac(struct igb_adapter *adapter, u32 pba) } /* endif adapter->dmac is not disabled */ } else if (hw->mac.type == e1000_82580) { u32 reg = rd32(E1000_PCIEMISC); + wr32(E1000_PCIEMISC, reg & ~E1000_PCIEMISC_LX_DECISION); wr32(E1000_DMACR, 0); } } +/** + * igb_read_i2c_byte - Reads 8 bit word over I2C + * @hw: pointer to hardware structure + * @byte_offset: byte offset to read + * @dev_addr: device address + * @data: value read + * + * Performs byte read operation over I2C interface at + * a specified device address. + **/ +s32 igb_read_i2c_byte(struct e1000_hw *hw, u8 byte_offset, + u8 dev_addr, u8 *data) +{ + struct igb_adapter *adapter = container_of(hw, struct igb_adapter, hw); + struct i2c_client *this_client = adapter->i2c_client; + s32 status; + u16 swfw_mask = 0; + + if (!this_client) + return E1000_ERR_I2C; + + swfw_mask = E1000_SWFW_PHY0_SM; + + if (hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) + return E1000_ERR_SWFW_SYNC; + + status = i2c_smbus_read_byte_data(this_client, byte_offset); + hw->mac.ops.release_swfw_sync(hw, swfw_mask); + + if (status < 0) + return E1000_ERR_I2C; + else { + *data = status; + return 0; + } +} + +/** + * igb_write_i2c_byte - Writes 8 bit word over I2C + * @hw: pointer to hardware structure + * @byte_offset: byte offset to write + * @dev_addr: device address + * @data: value to write + * + * Performs byte write operation over I2C interface at + * a specified device address. + **/ +s32 igb_write_i2c_byte(struct e1000_hw *hw, u8 byte_offset, + u8 dev_addr, u8 data) +{ + struct igb_adapter *adapter = container_of(hw, struct igb_adapter, hw); + struct i2c_client *this_client = adapter->i2c_client; + s32 status; + u16 swfw_mask = E1000_SWFW_PHY0_SM; + + if (!this_client) + return E1000_ERR_I2C; + + if (hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) + return E1000_ERR_SWFW_SYNC; + status = i2c_smbus_write_byte_data(this_client, byte_offset, data); + hw->mac.ops.release_swfw_sync(hw, swfw_mask); + + if (status) + return E1000_ERR_I2C; + else + return 0; + +} + +int igb_reinit_queues(struct igb_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct pci_dev *pdev = adapter->pdev; + int err = 0; + + if (netif_running(netdev)) + igb_close(netdev); + + igb_reset_interrupt_capability(adapter); + + if (igb_init_interrupt_scheme(adapter, true)) { + dev_err(&pdev->dev, "Unable to allocate memory for queues\n"); + return -ENOMEM; + } + + if (netif_running(netdev)) + err = igb_open(netdev); + + return err; +} /* igb_main.c */ |