diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-11 08:27:49 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-11 08:27:49 +0000 |
commit | ace9429bb58fd418f0c81d4c2835699bddf6bde6 (patch) | |
tree | b2d64bc10158fdd5497876388cd68142ca374ed3 /drivers/net/ethernet/intel/igb | |
parent | Initial commit. (diff) | |
download | linux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.tar.xz linux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.zip |
Adding upstream version 6.6.15.upstream/6.6.15
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'drivers/net/ethernet/intel/igb')
21 files changed, 28367 insertions, 0 deletions
diff --git a/drivers/net/ethernet/intel/igb/Makefile b/drivers/net/ethernet/intel/igb/Makefile new file mode 100644 index 0000000000..394c1e0656 --- /dev/null +++ b/drivers/net/ethernet/intel/igb/Makefile @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright(c) 1999 - 2018 Intel Corporation. +# +# Makefile for the Intel(R) 82575 PCI-Express ethernet driver +# + +obj-$(CONFIG_IGB) += igb.o + +igb-objs := igb_main.o igb_ethtool.o e1000_82575.o \ + e1000_mac.o e1000_nvm.o e1000_phy.o e1000_mbx.o \ + e1000_i210.o igb_ptp.o igb_hwmon.o diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c new file mode 100644 index 0000000000..8d6e44ee18 --- /dev/null +++ b/drivers/net/ethernet/intel/igb/e1000_82575.c @@ -0,0 +1,2927 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2007 - 2018 Intel Corporation. */ + +/* e1000_82575 + * e1000_82576 + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/types.h> +#include <linux/if_ether.h> +#include <linux/i2c.h> + +#include "e1000_mac.h" +#include "e1000_82575.h" +#include "e1000_i210.h" +#include "igb.h" + +static s32 igb_get_invariants_82575(struct e1000_hw *); +static s32 igb_acquire_phy_82575(struct e1000_hw *); +static void igb_release_phy_82575(struct e1000_hw *); +static s32 igb_acquire_nvm_82575(struct e1000_hw *); +static void igb_release_nvm_82575(struct e1000_hw *); +static s32 igb_check_for_link_82575(struct e1000_hw *); +static s32 igb_get_cfg_done_82575(struct e1000_hw *); +static s32 igb_init_hw_82575(struct e1000_hw *); +static s32 igb_phy_hw_reset_sgmii_82575(struct e1000_hw *); +static s32 igb_read_phy_reg_sgmii_82575(struct e1000_hw *, u32, u16 *); +static s32 igb_reset_hw_82575(struct e1000_hw *); +static s32 igb_reset_hw_82580(struct e1000_hw *); +static s32 igb_set_d0_lplu_state_82575(struct e1000_hw *, bool); +static s32 igb_set_d0_lplu_state_82580(struct e1000_hw *, bool); +static s32 igb_set_d3_lplu_state_82580(struct e1000_hw *, bool); +static s32 igb_setup_copper_link_82575(struct e1000_hw *); +static s32 igb_setup_serdes_link_82575(struct e1000_hw *); +static s32 igb_write_phy_reg_sgmii_82575(struct e1000_hw *, u32, u16); +static void igb_clear_hw_cntrs_82575(struct e1000_hw *); +static s32 igb_acquire_swfw_sync_82575(struct e1000_hw *, u16); +static s32 igb_get_pcs_speed_and_duplex_82575(struct e1000_hw *, u16 *, + u16 *); +static s32 igb_get_phy_id_82575(struct e1000_hw *); +static void igb_release_swfw_sync_82575(struct e1000_hw *, u16); +static bool igb_sgmii_active_82575(struct e1000_hw *); +static s32 igb_reset_init_script_82575(struct e1000_hw *); +static s32 igb_read_mac_addr_82575(struct e1000_hw *); +static s32 igb_set_pcie_completion_timeout(struct e1000_hw *hw); +static s32 igb_reset_mdicnfg_82580(struct e1000_hw *hw); +static s32 igb_validate_nvm_checksum_82580(struct e1000_hw *hw); +static s32 igb_update_nvm_checksum_82580(struct e1000_hw *hw); +static s32 igb_validate_nvm_checksum_i350(struct e1000_hw *hw); +static s32 igb_update_nvm_checksum_i350(struct e1000_hw *hw); +static const u16 e1000_82580_rxpbs_table[] = { + 36, 72, 144, 1, 2, 4, 8, 16, 35, 70, 140 }; + +/* Due to a hw errata, if the host tries to configure the VFTA register + * while performing queries from the BMC or DMA, then the VFTA in some + * cases won't be written. + */ + +/** + * igb_write_vfta_i350 - Write value to VLAN filter table + * @hw: pointer to the HW structure + * @offset: register offset in VLAN filter table + * @value: register value written to VLAN filter table + * + * Writes value at the given offset in the register array which stores + * the VLAN filter table. + **/ +static void igb_write_vfta_i350(struct e1000_hw *hw, u32 offset, u32 value) +{ + struct igb_adapter *adapter = hw->back; + int i; + + for (i = 10; i--;) + array_wr32(E1000_VFTA, offset, value); + + wrfl(); + adapter->shadow_vfta[offset] = value; +} + +/** + * igb_sgmii_uses_mdio_82575 - Determine if I2C pins are for external MDIO + * @hw: pointer to the HW structure + * + * Called to determine if the I2C pins are being used for I2C or as an + * external MDIO interface since the two options are mutually exclusive. + **/ +static bool igb_sgmii_uses_mdio_82575(struct e1000_hw *hw) +{ + u32 reg = 0; + bool ext_mdio = false; + + switch (hw->mac.type) { + case e1000_82575: + case e1000_82576: + reg = rd32(E1000_MDIC); + ext_mdio = !!(reg & E1000_MDIC_DEST); + break; + case e1000_82580: + case e1000_i350: + case e1000_i354: + case e1000_i210: + case e1000_i211: + reg = rd32(E1000_MDICNFG); + ext_mdio = !!(reg & E1000_MDICNFG_EXT_MDIO); + break; + default: + break; + } + return ext_mdio; +} + +/** + * igb_check_for_link_media_swap - Check which M88E1112 interface linked + * @hw: pointer to the HW structure + * + * Poll the M88E1112 interfaces to see which interface achieved link. + */ +static s32 igb_check_for_link_media_swap(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 data; + u8 port = 0; + + /* Check the copper medium. */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1112_PAGE_ADDR, 0); + if (ret_val) + return ret_val; + + ret_val = phy->ops.read_reg(hw, E1000_M88E1112_STATUS, &data); + if (ret_val) + return ret_val; + + if (data & E1000_M88E1112_STATUS_LINK) + port = E1000_MEDIA_PORT_COPPER; + + /* Check the other medium. */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1112_PAGE_ADDR, 1); + if (ret_val) + return ret_val; + + ret_val = phy->ops.read_reg(hw, E1000_M88E1112_STATUS, &data); + if (ret_val) + return ret_val; + + + if (data & E1000_M88E1112_STATUS_LINK) + port = E1000_MEDIA_PORT_OTHER; + + /* Determine if a swap needs to happen. */ + if (port && (hw->dev_spec._82575.media_port != port)) { + hw->dev_spec._82575.media_port = port; + hw->dev_spec._82575.media_changed = true; + } + + if (port == E1000_MEDIA_PORT_COPPER) { + /* reset page to 0 */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1112_PAGE_ADDR, 0); + if (ret_val) + return ret_val; + igb_check_for_link_82575(hw); + } else { + igb_check_for_link_82575(hw); + /* reset page to 0 */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1112_PAGE_ADDR, 0); + if (ret_val) + return ret_val; + } + + return 0; +} + +/** + * igb_init_phy_params_82575 - Init PHY func ptrs. + * @hw: pointer to the HW structure + **/ +static s32 igb_init_phy_params_82575(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val = 0; + u32 ctrl_ext; + + if (hw->phy.media_type != e1000_media_type_copper) { + phy->type = e1000_phy_none; + goto out; + } + + phy->autoneg_mask = AUTONEG_ADVERTISE_SPEED_DEFAULT; + phy->reset_delay_us = 100; + + ctrl_ext = rd32(E1000_CTRL_EXT); + + if (igb_sgmii_active_82575(hw)) { + phy->ops.reset = igb_phy_hw_reset_sgmii_82575; + ctrl_ext |= E1000_CTRL_I2C_ENA; + } else { + phy->ops.reset = igb_phy_hw_reset; + ctrl_ext &= ~E1000_CTRL_I2C_ENA; + } + + wr32(E1000_CTRL_EXT, ctrl_ext); + igb_reset_mdicnfg_82580(hw); + + if (igb_sgmii_active_82575(hw) && !igb_sgmii_uses_mdio_82575(hw)) { + phy->ops.read_reg = igb_read_phy_reg_sgmii_82575; + phy->ops.write_reg = igb_write_phy_reg_sgmii_82575; + } else { + switch (hw->mac.type) { + case e1000_82580: + case e1000_i350: + case e1000_i354: + case e1000_i210: + case e1000_i211: + phy->ops.read_reg = igb_read_phy_reg_82580; + phy->ops.write_reg = igb_write_phy_reg_82580; + break; + default: + phy->ops.read_reg = igb_read_phy_reg_igp; + phy->ops.write_reg = igb_write_phy_reg_igp; + } + } + + /* set lan id */ + hw->bus.func = (rd32(E1000_STATUS) & E1000_STATUS_FUNC_MASK) >> + E1000_STATUS_FUNC_SHIFT; + + /* Set phy->phy_addr and phy->id. */ + ret_val = igb_get_phy_id_82575(hw); + if (ret_val) + return ret_val; + + /* Verify phy id and set remaining function pointers */ + switch (phy->id) { + case M88E1543_E_PHY_ID: + case M88E1512_E_PHY_ID: + case I347AT4_E_PHY_ID: + case M88E1112_E_PHY_ID: + case M88E1111_I_PHY_ID: + phy->type = e1000_phy_m88; + phy->ops.check_polarity = igb_check_polarity_m88; + phy->ops.get_phy_info = igb_get_phy_info_m88; + if (phy->id != M88E1111_I_PHY_ID) + phy->ops.get_cable_length = + igb_get_cable_length_m88_gen2; + else + phy->ops.get_cable_length = igb_get_cable_length_m88; + phy->ops.force_speed_duplex = igb_phy_force_speed_duplex_m88; + /* Check if this PHY is configured for media swap. */ + if (phy->id == M88E1112_E_PHY_ID) { + u16 data; + + ret_val = phy->ops.write_reg(hw, + E1000_M88E1112_PAGE_ADDR, + 2); + if (ret_val) + goto out; + + ret_val = phy->ops.read_reg(hw, + E1000_M88E1112_MAC_CTRL_1, + &data); + if (ret_val) + goto out; + + data = (data & E1000_M88E1112_MAC_CTRL_1_MODE_MASK) >> + E1000_M88E1112_MAC_CTRL_1_MODE_SHIFT; + if (data == E1000_M88E1112_AUTO_COPPER_SGMII || + data == E1000_M88E1112_AUTO_COPPER_BASEX) + hw->mac.ops.check_for_link = + igb_check_for_link_media_swap; + } + if (phy->id == M88E1512_E_PHY_ID) { + ret_val = igb_initialize_M88E1512_phy(hw); + if (ret_val) + goto out; + } + if (phy->id == M88E1543_E_PHY_ID) { + ret_val = igb_initialize_M88E1543_phy(hw); + if (ret_val) + goto out; + } + break; + case IGP03E1000_E_PHY_ID: + phy->type = e1000_phy_igp_3; + phy->ops.get_phy_info = igb_get_phy_info_igp; + phy->ops.get_cable_length = igb_get_cable_length_igp_2; + phy->ops.force_speed_duplex = igb_phy_force_speed_duplex_igp; + phy->ops.set_d0_lplu_state = igb_set_d0_lplu_state_82575; + phy->ops.set_d3_lplu_state = igb_set_d3_lplu_state; + break; + case I82580_I_PHY_ID: + case I350_I_PHY_ID: + phy->type = e1000_phy_82580; + phy->ops.force_speed_duplex = + igb_phy_force_speed_duplex_82580; + phy->ops.get_cable_length = igb_get_cable_length_82580; + phy->ops.get_phy_info = igb_get_phy_info_82580; + phy->ops.set_d0_lplu_state = igb_set_d0_lplu_state_82580; + phy->ops.set_d3_lplu_state = igb_set_d3_lplu_state_82580; + break; + case I210_I_PHY_ID: + phy->type = e1000_phy_i210; + phy->ops.check_polarity = igb_check_polarity_m88; + phy->ops.get_cfg_done = igb_get_cfg_done_i210; + phy->ops.get_phy_info = igb_get_phy_info_m88; + phy->ops.get_cable_length = igb_get_cable_length_m88_gen2; + phy->ops.set_d0_lplu_state = igb_set_d0_lplu_state_82580; + phy->ops.set_d3_lplu_state = igb_set_d3_lplu_state_82580; + phy->ops.force_speed_duplex = igb_phy_force_speed_duplex_m88; + break; + case BCM54616_E_PHY_ID: + phy->type = e1000_phy_bcm54616; + break; + default: + ret_val = -E1000_ERR_PHY; + goto out; + } + +out: + return ret_val; +} + +/** + * igb_init_nvm_params_82575 - Init NVM func ptrs. + * @hw: pointer to the HW structure + **/ +static s32 igb_init_nvm_params_82575(struct e1000_hw *hw) +{ + struct e1000_nvm_info *nvm = &hw->nvm; + u32 eecd = rd32(E1000_EECD); + u16 size; + + size = (u16)((eecd & E1000_EECD_SIZE_EX_MASK) >> + E1000_EECD_SIZE_EX_SHIFT); + + /* Added to a constant, "size" becomes the left-shift value + * for setting word_size. + */ + size += NVM_WORD_SIZE_BASE_SHIFT; + + /* Just in case size is out of range, cap it to the largest + * EEPROM size supported + */ + if (size > 15) + size = 15; + + nvm->word_size = BIT(size); + nvm->opcode_bits = 8; + nvm->delay_usec = 1; + + switch (nvm->override) { + case e1000_nvm_override_spi_large: + nvm->page_size = 32; + nvm->address_bits = 16; + break; + case e1000_nvm_override_spi_small: + nvm->page_size = 8; + nvm->address_bits = 8; + break; + default: + nvm->page_size = eecd & E1000_EECD_ADDR_BITS ? 32 : 8; + nvm->address_bits = eecd & E1000_EECD_ADDR_BITS ? + 16 : 8; + break; + } + if (nvm->word_size == BIT(15)) + nvm->page_size = 128; + + nvm->type = e1000_nvm_eeprom_spi; + + /* NVM Function Pointers */ + nvm->ops.acquire = igb_acquire_nvm_82575; + nvm->ops.release = igb_release_nvm_82575; + nvm->ops.write = igb_write_nvm_spi; + nvm->ops.validate = igb_validate_nvm_checksum; + nvm->ops.update = igb_update_nvm_checksum; + if (nvm->word_size < BIT(15)) + nvm->ops.read = igb_read_nvm_eerd; + else + nvm->ops.read = igb_read_nvm_spi; + + /* override generic family function pointers for specific descendants */ + switch (hw->mac.type) { + case e1000_82580: + nvm->ops.validate = igb_validate_nvm_checksum_82580; + nvm->ops.update = igb_update_nvm_checksum_82580; + break; + case e1000_i354: + case e1000_i350: + nvm->ops.validate = igb_validate_nvm_checksum_i350; + nvm->ops.update = igb_update_nvm_checksum_i350; + break; + default: + break; + } + + return 0; +} + +/** + * igb_init_mac_params_82575 - Init MAC func ptrs. + * @hw: pointer to the HW structure + **/ +static s32 igb_init_mac_params_82575(struct e1000_hw *hw) +{ + struct e1000_mac_info *mac = &hw->mac; + struct e1000_dev_spec_82575 *dev_spec = &hw->dev_spec._82575; + + /* Set mta register count */ + mac->mta_reg_count = 128; + /* Set uta register count */ + mac->uta_reg_count = (hw->mac.type == e1000_82575) ? 0 : 128; + /* Set rar entry count */ + switch (mac->type) { + case e1000_82576: + mac->rar_entry_count = E1000_RAR_ENTRIES_82576; + break; + case e1000_82580: + mac->rar_entry_count = E1000_RAR_ENTRIES_82580; + break; + case e1000_i350: + case e1000_i354: + mac->rar_entry_count = E1000_RAR_ENTRIES_I350; + break; + default: + mac->rar_entry_count = E1000_RAR_ENTRIES_82575; + break; + } + /* reset */ + if (mac->type >= e1000_82580) + mac->ops.reset_hw = igb_reset_hw_82580; + else + mac->ops.reset_hw = igb_reset_hw_82575; + + if (mac->type >= e1000_i210) { + mac->ops.acquire_swfw_sync = igb_acquire_swfw_sync_i210; + mac->ops.release_swfw_sync = igb_release_swfw_sync_i210; + + } else { + mac->ops.acquire_swfw_sync = igb_acquire_swfw_sync_82575; + mac->ops.release_swfw_sync = igb_release_swfw_sync_82575; + } + + if ((hw->mac.type == e1000_i350) || (hw->mac.type == e1000_i354)) + mac->ops.write_vfta = igb_write_vfta_i350; + else + mac->ops.write_vfta = igb_write_vfta; + + /* Set if part includes ASF firmware */ + mac->asf_firmware_present = true; + /* Set if manageability features are enabled. */ + mac->arc_subsystem_valid = + (rd32(E1000_FWSM) & E1000_FWSM_MODE_MASK) + ? true : false; + /* enable EEE on i350 parts and later parts */ + if (mac->type >= e1000_i350) + dev_spec->eee_disable = false; + else + dev_spec->eee_disable = true; + /* Allow a single clear of the SW semaphore on I210 and newer */ + if (mac->type >= e1000_i210) + dev_spec->clear_semaphore_once = true; + /* physical interface link setup */ + mac->ops.setup_physical_interface = + (hw->phy.media_type == e1000_media_type_copper) + ? igb_setup_copper_link_82575 + : igb_setup_serdes_link_82575; + + if (mac->type == e1000_82580 || mac->type == e1000_i350) { + switch (hw->device_id) { + /* feature not supported on these id's */ + case E1000_DEV_ID_DH89XXCC_SGMII: + case E1000_DEV_ID_DH89XXCC_SERDES: + case E1000_DEV_ID_DH89XXCC_BACKPLANE: + case E1000_DEV_ID_DH89XXCC_SFP: + break; + default: + hw->dev_spec._82575.mas_capable = true; + break; + } + } + return 0; +} + +/** + * igb_set_sfp_media_type_82575 - derives SFP module media type. + * @hw: pointer to the HW structure + * + * The media type is chosen based on SFP module. + * compatibility flags retrieved from SFP ID EEPROM. + **/ +static s32 igb_set_sfp_media_type_82575(struct e1000_hw *hw) +{ + s32 ret_val = E1000_ERR_CONFIG; + u32 ctrl_ext = 0; + struct e1000_dev_spec_82575 *dev_spec = &hw->dev_spec._82575; + struct e1000_sfp_flags *eth_flags = &dev_spec->eth_flags; + u8 tranceiver_type = 0; + s32 timeout = 3; + + /* Turn I2C interface ON and power on sfp cage */ + ctrl_ext = rd32(E1000_CTRL_EXT); + ctrl_ext &= ~E1000_CTRL_EXT_SDP3_DATA; + wr32(E1000_CTRL_EXT, ctrl_ext | E1000_CTRL_I2C_ENA); + + wrfl(); + + /* Read SFP module data */ + while (timeout) { + ret_val = igb_read_sfp_data_byte(hw, + E1000_I2CCMD_SFP_DATA_ADDR(E1000_SFF_IDENTIFIER_OFFSET), + &tranceiver_type); + if (ret_val == 0) + break; + msleep(100); + timeout--; + } + if (ret_val != 0) + goto out; + + ret_val = igb_read_sfp_data_byte(hw, + E1000_I2CCMD_SFP_DATA_ADDR(E1000_SFF_ETH_FLAGS_OFFSET), + (u8 *)eth_flags); + if (ret_val != 0) + goto out; + + /* Check if there is some SFP module plugged and powered */ + if ((tranceiver_type == E1000_SFF_IDENTIFIER_SFP) || + (tranceiver_type == E1000_SFF_IDENTIFIER_SFF)) { + dev_spec->module_plugged = true; + if (eth_flags->e1000_base_lx || eth_flags->e1000_base_sx) { + hw->phy.media_type = e1000_media_type_internal_serdes; + } else if (eth_flags->e100_base_fx || eth_flags->e100_base_lx) { + dev_spec->sgmii_active = true; + hw->phy.media_type = e1000_media_type_internal_serdes; + } else if (eth_flags->e1000_base_t) { + dev_spec->sgmii_active = true; + hw->phy.media_type = e1000_media_type_copper; + } else { + hw->phy.media_type = e1000_media_type_unknown; + hw_dbg("PHY module has not been recognized\n"); + goto out; + } + } else { + hw->phy.media_type = e1000_media_type_unknown; + } + ret_val = 0; +out: + /* Restore I2C interface setting */ + wr32(E1000_CTRL_EXT, ctrl_ext); + return ret_val; +} + +static s32 igb_get_invariants_82575(struct e1000_hw *hw) +{ + struct e1000_mac_info *mac = &hw->mac; + struct e1000_dev_spec_82575 *dev_spec = &hw->dev_spec._82575; + s32 ret_val; + u32 ctrl_ext = 0; + u32 link_mode = 0; + + switch (hw->device_id) { + case E1000_DEV_ID_82575EB_COPPER: + case E1000_DEV_ID_82575EB_FIBER_SERDES: + case E1000_DEV_ID_82575GB_QUAD_COPPER: + mac->type = e1000_82575; + break; + case E1000_DEV_ID_82576: + case E1000_DEV_ID_82576_NS: + case E1000_DEV_ID_82576_NS_SERDES: + case E1000_DEV_ID_82576_FIBER: + case E1000_DEV_ID_82576_SERDES: + case E1000_DEV_ID_82576_QUAD_COPPER: + case E1000_DEV_ID_82576_QUAD_COPPER_ET2: + case E1000_DEV_ID_82576_SERDES_QUAD: + mac->type = e1000_82576; + break; + case E1000_DEV_ID_82580_COPPER: + case E1000_DEV_ID_82580_FIBER: + case E1000_DEV_ID_82580_QUAD_FIBER: + case E1000_DEV_ID_82580_SERDES: + case E1000_DEV_ID_82580_SGMII: + case E1000_DEV_ID_82580_COPPER_DUAL: + case E1000_DEV_ID_DH89XXCC_SGMII: + case E1000_DEV_ID_DH89XXCC_SERDES: + case E1000_DEV_ID_DH89XXCC_BACKPLANE: + case E1000_DEV_ID_DH89XXCC_SFP: + mac->type = e1000_82580; + break; + case E1000_DEV_ID_I350_COPPER: + case E1000_DEV_ID_I350_FIBER: + case E1000_DEV_ID_I350_SERDES: + case E1000_DEV_ID_I350_SGMII: + mac->type = e1000_i350; + break; + case E1000_DEV_ID_I210_COPPER: + case E1000_DEV_ID_I210_FIBER: + case E1000_DEV_ID_I210_SERDES: + case E1000_DEV_ID_I210_SGMII: + case E1000_DEV_ID_I210_COPPER_FLASHLESS: + case E1000_DEV_ID_I210_SERDES_FLASHLESS: + mac->type = e1000_i210; + break; + case E1000_DEV_ID_I211_COPPER: + mac->type = e1000_i211; + break; + case E1000_DEV_ID_I354_BACKPLANE_1GBPS: + case E1000_DEV_ID_I354_SGMII: + case E1000_DEV_ID_I354_BACKPLANE_2_5GBPS: + mac->type = e1000_i354; + break; + default: + return -E1000_ERR_MAC_INIT; + } + + /* Set media type */ + /* The 82575 uses bits 22:23 for link mode. The mode can be changed + * based on the EEPROM. We cannot rely upon device ID. There + * is no distinguishable difference between fiber and internal + * SerDes mode on the 82575. There can be an external PHY attached + * on the SGMII interface. For this, we'll set sgmii_active to true. + */ + hw->phy.media_type = e1000_media_type_copper; + dev_spec->sgmii_active = false; + dev_spec->module_plugged = false; + + ctrl_ext = rd32(E1000_CTRL_EXT); + + link_mode = ctrl_ext & E1000_CTRL_EXT_LINK_MODE_MASK; + switch (link_mode) { + case E1000_CTRL_EXT_LINK_MODE_1000BASE_KX: + hw->phy.media_type = e1000_media_type_internal_serdes; + break; + case E1000_CTRL_EXT_LINK_MODE_SGMII: + /* Get phy control interface type set (MDIO vs. I2C)*/ + if (igb_sgmii_uses_mdio_82575(hw)) { + hw->phy.media_type = e1000_media_type_copper; + dev_spec->sgmii_active = true; + break; + } + fallthrough; /* for I2C based SGMII */ + case E1000_CTRL_EXT_LINK_MODE_PCIE_SERDES: + /* read media type from SFP EEPROM */ + ret_val = igb_set_sfp_media_type_82575(hw); + if ((ret_val != 0) || + (hw->phy.media_type == e1000_media_type_unknown)) { + /* If media type was not identified then return media + * type defined by the CTRL_EXT settings. + */ + hw->phy.media_type = e1000_media_type_internal_serdes; + + if (link_mode == E1000_CTRL_EXT_LINK_MODE_SGMII) { + hw->phy.media_type = e1000_media_type_copper; + dev_spec->sgmii_active = true; + } + + break; + } + + /* change current link mode setting */ + ctrl_ext &= ~E1000_CTRL_EXT_LINK_MODE_MASK; + + if (dev_spec->sgmii_active) + ctrl_ext |= E1000_CTRL_EXT_LINK_MODE_SGMII; + else + ctrl_ext |= E1000_CTRL_EXT_LINK_MODE_PCIE_SERDES; + + wr32(E1000_CTRL_EXT, ctrl_ext); + + break; + default: + break; + } + + /* mac initialization and operations */ + ret_val = igb_init_mac_params_82575(hw); + if (ret_val) + goto out; + + /* NVM initialization */ + ret_val = igb_init_nvm_params_82575(hw); + switch (hw->mac.type) { + case e1000_i210: + case e1000_i211: + ret_val = igb_init_nvm_params_i210(hw); + break; + default: + break; + } + + if (ret_val) + goto out; + + /* if part supports SR-IOV then initialize mailbox parameters */ + switch (mac->type) { + case e1000_82576: + case e1000_i350: + igb_init_mbx_params_pf(hw); + break; + default: + break; + } + + /* setup PHY parameters */ + ret_val = igb_init_phy_params_82575(hw); + +out: + return ret_val; +} + +/** + * igb_acquire_phy_82575 - Acquire rights to access PHY + * @hw: pointer to the HW structure + * + * Acquire access rights to the correct PHY. This is a + * function pointer entry point called by the api module. + **/ +static s32 igb_acquire_phy_82575(struct e1000_hw *hw) +{ + u16 mask = E1000_SWFW_PHY0_SM; + + if (hw->bus.func == E1000_FUNC_1) + mask = E1000_SWFW_PHY1_SM; + else if (hw->bus.func == E1000_FUNC_2) + mask = E1000_SWFW_PHY2_SM; + else if (hw->bus.func == E1000_FUNC_3) + mask = E1000_SWFW_PHY3_SM; + + return hw->mac.ops.acquire_swfw_sync(hw, mask); +} + +/** + * igb_release_phy_82575 - Release rights to access PHY + * @hw: pointer to the HW structure + * + * A wrapper to release access rights to the correct PHY. This is a + * function pointer entry point called by the api module. + **/ +static void igb_release_phy_82575(struct e1000_hw *hw) +{ + u16 mask = E1000_SWFW_PHY0_SM; + + if (hw->bus.func == E1000_FUNC_1) + mask = E1000_SWFW_PHY1_SM; + else if (hw->bus.func == E1000_FUNC_2) + mask = E1000_SWFW_PHY2_SM; + else if (hw->bus.func == E1000_FUNC_3) + mask = E1000_SWFW_PHY3_SM; + + hw->mac.ops.release_swfw_sync(hw, mask); +} + +/** + * igb_read_phy_reg_sgmii_82575 - Read PHY register using sgmii + * @hw: pointer to the HW structure + * @offset: register offset to be read + * @data: pointer to the read data + * + * Reads the PHY register at offset using the serial gigabit media independent + * interface and stores the retrieved information in data. + **/ +static s32 igb_read_phy_reg_sgmii_82575(struct e1000_hw *hw, u32 offset, + u16 *data) +{ + s32 ret_val = -E1000_ERR_PARAM; + + if (offset > E1000_MAX_SGMII_PHY_REG_ADDR) { + hw_dbg("PHY Address %u is out of range\n", offset); + goto out; + } + + ret_val = hw->phy.ops.acquire(hw); + if (ret_val) + goto out; + + ret_val = igb_read_phy_reg_i2c(hw, offset, data); + + hw->phy.ops.release(hw); + +out: + return ret_val; +} + +/** + * igb_write_phy_reg_sgmii_82575 - Write PHY register using sgmii + * @hw: pointer to the HW structure + * @offset: register offset to write to + * @data: data to write at register offset + * + * Writes the data to PHY register at the offset using the serial gigabit + * media independent interface. + **/ +static s32 igb_write_phy_reg_sgmii_82575(struct e1000_hw *hw, u32 offset, + u16 data) +{ + s32 ret_val = -E1000_ERR_PARAM; + + + if (offset > E1000_MAX_SGMII_PHY_REG_ADDR) { + hw_dbg("PHY Address %d is out of range\n", offset); + goto out; + } + + ret_val = hw->phy.ops.acquire(hw); + if (ret_val) + goto out; + + ret_val = igb_write_phy_reg_i2c(hw, offset, data); + + hw->phy.ops.release(hw); + +out: + return ret_val; +} + +/** + * igb_get_phy_id_82575 - Retrieve PHY addr and id + * @hw: pointer to the HW structure + * + * Retrieves the PHY address and ID for both PHY's which do and do not use + * sgmi interface. + **/ +static s32 igb_get_phy_id_82575(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val = 0; + u16 phy_id; + u32 ctrl_ext; + u32 mdic; + + /* Extra read required for some PHY's on i354 */ + if (hw->mac.type == e1000_i354) + igb_get_phy_id(hw); + + /* For SGMII PHYs, we try the list of possible addresses until + * we find one that works. For non-SGMII PHYs + * (e.g. integrated copper PHYs), an address of 1 should + * work. The result of this function should mean phy->phy_addr + * and phy->id are set correctly. + */ + if (!(igb_sgmii_active_82575(hw))) { + phy->addr = 1; + ret_val = igb_get_phy_id(hw); + goto out; + } + + if (igb_sgmii_uses_mdio_82575(hw)) { + switch (hw->mac.type) { + case e1000_82575: + case e1000_82576: + mdic = rd32(E1000_MDIC); + mdic &= E1000_MDIC_PHY_MASK; + phy->addr = mdic >> E1000_MDIC_PHY_SHIFT; + break; + case e1000_82580: + case e1000_i350: + case e1000_i354: + case e1000_i210: + case e1000_i211: + mdic = rd32(E1000_MDICNFG); + mdic &= E1000_MDICNFG_PHY_MASK; + phy->addr = mdic >> E1000_MDICNFG_PHY_SHIFT; + break; + default: + ret_val = -E1000_ERR_PHY; + goto out; + } + ret_val = igb_get_phy_id(hw); + goto out; + } + + /* Power on sgmii phy if it is disabled */ + ctrl_ext = rd32(E1000_CTRL_EXT); + wr32(E1000_CTRL_EXT, ctrl_ext & ~E1000_CTRL_EXT_SDP3_DATA); + wrfl(); + msleep(300); + + /* The address field in the I2CCMD register is 3 bits and 0 is invalid. + * Therefore, we need to test 1-7 + */ + for (phy->addr = 1; phy->addr < 8; phy->addr++) { + ret_val = igb_read_phy_reg_sgmii_82575(hw, PHY_ID1, &phy_id); + if (ret_val == 0) { + hw_dbg("Vendor ID 0x%08X read at address %u\n", + phy_id, phy->addr); + /* At the time of this writing, The M88 part is + * the only supported SGMII PHY product. + */ + if (phy_id == M88_VENDOR) + break; + } else { + hw_dbg("PHY address %u was unreadable\n", phy->addr); + } + } + + /* A valid PHY type couldn't be found. */ + if (phy->addr == 8) { + phy->addr = 0; + ret_val = -E1000_ERR_PHY; + goto out; + } else { + ret_val = igb_get_phy_id(hw); + } + + /* restore previous sfp cage power state */ + wr32(E1000_CTRL_EXT, ctrl_ext); + +out: + return ret_val; +} + +/** + * igb_phy_hw_reset_sgmii_82575 - Performs a PHY reset + * @hw: pointer to the HW structure + * + * Resets the PHY using the serial gigabit media independent interface. + **/ +static s32 igb_phy_hw_reset_sgmii_82575(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + + /* This isn't a true "hard" reset, but is the only reset + * available to us at this time. + */ + + hw_dbg("Soft resetting SGMII attached PHY...\n"); + + /* SFP documentation requires the following to configure the SPF module + * to work on SGMII. No further documentation is given. + */ + ret_val = hw->phy.ops.write_reg(hw, 0x1B, 0x8084); + if (ret_val) + goto out; + + ret_val = igb_phy_sw_reset(hw); + if (ret_val) + goto out; + + if (phy->id == M88E1512_E_PHY_ID) + ret_val = igb_initialize_M88E1512_phy(hw); + if (phy->id == M88E1543_E_PHY_ID) + ret_val = igb_initialize_M88E1543_phy(hw); +out: + return ret_val; +} + +/** + * igb_set_d0_lplu_state_82575 - Set Low Power Linkup D0 state + * @hw: pointer to the HW structure + * @active: true to enable LPLU, false to disable + * + * Sets the LPLU D0 state according to the active flag. When + * activating LPLU this function also disables smart speed + * and vice versa. LPLU will not be activated unless the + * device autonegotiation advertisement meets standards of + * either 10 or 10/100 or 10/100/1000 at all duplexes. + * This is a function pointer entry point only called by + * PHY setup routines. + **/ +static s32 igb_set_d0_lplu_state_82575(struct e1000_hw *hw, bool active) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 data; + + ret_val = phy->ops.read_reg(hw, IGP02E1000_PHY_POWER_MGMT, &data); + if (ret_val) + goto out; + + if (active) { + data |= IGP02E1000_PM_D0_LPLU; + ret_val = phy->ops.write_reg(hw, IGP02E1000_PHY_POWER_MGMT, + data); + if (ret_val) + goto out; + + /* When LPLU is enabled, we should disable SmartSpeed */ + ret_val = phy->ops.read_reg(hw, IGP01E1000_PHY_PORT_CONFIG, + &data); + data &= ~IGP01E1000_PSCFR_SMART_SPEED; + ret_val = phy->ops.write_reg(hw, IGP01E1000_PHY_PORT_CONFIG, + data); + if (ret_val) + goto out; + } else { + data &= ~IGP02E1000_PM_D0_LPLU; + ret_val = phy->ops.write_reg(hw, IGP02E1000_PHY_POWER_MGMT, + data); + /* LPLU and SmartSpeed are mutually exclusive. LPLU is used + * during Dx states where the power conservation is most + * important. During driver activity we should enable + * SmartSpeed, so performance is maintained. + */ + if (phy->smart_speed == e1000_smart_speed_on) { + ret_val = phy->ops.read_reg(hw, + IGP01E1000_PHY_PORT_CONFIG, &data); + if (ret_val) + goto out; + + data |= IGP01E1000_PSCFR_SMART_SPEED; + ret_val = phy->ops.write_reg(hw, + IGP01E1000_PHY_PORT_CONFIG, data); + if (ret_val) + goto out; + } else if (phy->smart_speed == e1000_smart_speed_off) { + ret_val = phy->ops.read_reg(hw, + IGP01E1000_PHY_PORT_CONFIG, &data); + if (ret_val) + goto out; + + data &= ~IGP01E1000_PSCFR_SMART_SPEED; + ret_val = phy->ops.write_reg(hw, + IGP01E1000_PHY_PORT_CONFIG, data); + if (ret_val) + goto out; + } + } + +out: + return ret_val; +} + +/** + * igb_set_d0_lplu_state_82580 - Set Low Power Linkup D0 state + * @hw: pointer to the HW structure + * @active: true to enable LPLU, false to disable + * + * Sets the LPLU D0 state according to the active flag. When + * activating LPLU this function also disables smart speed + * and vice versa. LPLU will not be activated unless the + * device autonegotiation advertisement meets standards of + * either 10 or 10/100 or 10/100/1000 at all duplexes. + * This is a function pointer entry point only called by + * PHY setup routines. + **/ +static s32 igb_set_d0_lplu_state_82580(struct e1000_hw *hw, bool active) +{ + struct e1000_phy_info *phy = &hw->phy; + u16 data; + + data = rd32(E1000_82580_PHY_POWER_MGMT); + + if (active) { + data |= E1000_82580_PM_D0_LPLU; + + /* When LPLU is enabled, we should disable SmartSpeed */ + data &= ~E1000_82580_PM_SPD; + } else { + data &= ~E1000_82580_PM_D0_LPLU; + + /* LPLU and SmartSpeed are mutually exclusive. LPLU is used + * during Dx states where the power conservation is most + * important. During driver activity we should enable + * SmartSpeed, so performance is maintained. + */ + if (phy->smart_speed == e1000_smart_speed_on) + data |= E1000_82580_PM_SPD; + else if (phy->smart_speed == e1000_smart_speed_off) + data &= ~E1000_82580_PM_SPD; } + + wr32(E1000_82580_PHY_POWER_MGMT, data); + return 0; +} + +/** + * igb_set_d3_lplu_state_82580 - Sets low power link up state for D3 + * @hw: pointer to the HW structure + * @active: boolean used to enable/disable lplu + * + * Success returns 0, Failure returns 1 + * + * The low power link up (lplu) state is set to the power management level D3 + * and SmartSpeed is disabled when active is true, else clear lplu for D3 + * and enable Smartspeed. LPLU and Smartspeed are mutually exclusive. LPLU + * is used during Dx states where the power conservation is most important. + * During driver activity, SmartSpeed should be enabled so performance is + * maintained. + **/ +static s32 igb_set_d3_lplu_state_82580(struct e1000_hw *hw, bool active) +{ + struct e1000_phy_info *phy = &hw->phy; + u16 data; + + data = rd32(E1000_82580_PHY_POWER_MGMT); + + if (!active) { + data &= ~E1000_82580_PM_D3_LPLU; + /* LPLU and SmartSpeed are mutually exclusive. LPLU is used + * during Dx states where the power conservation is most + * important. During driver activity we should enable + * SmartSpeed, so performance is maintained. + */ + if (phy->smart_speed == e1000_smart_speed_on) + data |= E1000_82580_PM_SPD; + else if (phy->smart_speed == e1000_smart_speed_off) + data &= ~E1000_82580_PM_SPD; + } else if ((phy->autoneg_advertised == E1000_ALL_SPEED_DUPLEX) || + (phy->autoneg_advertised == E1000_ALL_NOT_GIG) || + (phy->autoneg_advertised == E1000_ALL_10_SPEED)) { + data |= E1000_82580_PM_D3_LPLU; + /* When LPLU is enabled, we should disable SmartSpeed */ + data &= ~E1000_82580_PM_SPD; + } + + wr32(E1000_82580_PHY_POWER_MGMT, data); + return 0; +} + +/** + * igb_acquire_nvm_82575 - Request for access to EEPROM + * @hw: pointer to the HW structure + * + * Acquire the necessary semaphores for exclusive access to the EEPROM. + * Set the EEPROM access request bit and wait for EEPROM access grant bit. + * Return successful if access grant bit set, else clear the request for + * EEPROM access and return -E1000_ERR_NVM (-1). + **/ +static s32 igb_acquire_nvm_82575(struct e1000_hw *hw) +{ + s32 ret_val; + + ret_val = hw->mac.ops.acquire_swfw_sync(hw, E1000_SWFW_EEP_SM); + if (ret_val) + goto out; + + ret_val = igb_acquire_nvm(hw); + + if (ret_val) + hw->mac.ops.release_swfw_sync(hw, E1000_SWFW_EEP_SM); + +out: + return ret_val; +} + +/** + * igb_release_nvm_82575 - Release exclusive access to EEPROM + * @hw: pointer to the HW structure + * + * Stop any current commands to the EEPROM and clear the EEPROM request bit, + * then release the semaphores acquired. + **/ +static void igb_release_nvm_82575(struct e1000_hw *hw) +{ + igb_release_nvm(hw); + hw->mac.ops.release_swfw_sync(hw, E1000_SWFW_EEP_SM); +} + +/** + * igb_acquire_swfw_sync_82575 - Acquire SW/FW semaphore + * @hw: pointer to the HW structure + * @mask: specifies which semaphore to acquire + * + * Acquire the SW/FW semaphore to access the PHY or NVM. The mask + * will also specify which port we're acquiring the lock for. + **/ +static s32 igb_acquire_swfw_sync_82575(struct e1000_hw *hw, u16 mask) +{ + u32 swfw_sync; + u32 swmask = mask; + u32 fwmask = mask << 16; + s32 ret_val = 0; + s32 i = 0, timeout = 200; + + while (i < timeout) { + if (igb_get_hw_semaphore(hw)) { + ret_val = -E1000_ERR_SWFW_SYNC; + goto out; + } + + swfw_sync = rd32(E1000_SW_FW_SYNC); + if (!(swfw_sync & (fwmask | swmask))) + break; + + /* Firmware currently using resource (fwmask) + * or other software thread using resource (swmask) + */ + igb_put_hw_semaphore(hw); + mdelay(5); + i++; + } + + if (i == timeout) { + hw_dbg("Driver can't access resource, SW_FW_SYNC timeout.\n"); + ret_val = -E1000_ERR_SWFW_SYNC; + goto out; + } + + swfw_sync |= swmask; + wr32(E1000_SW_FW_SYNC, swfw_sync); + + igb_put_hw_semaphore(hw); + +out: + return ret_val; +} + +/** + * igb_release_swfw_sync_82575 - Release SW/FW semaphore + * @hw: pointer to the HW structure + * @mask: specifies which semaphore to acquire + * + * Release the SW/FW semaphore used to access the PHY or NVM. The mask + * will also specify which port we're releasing the lock for. + **/ +static void igb_release_swfw_sync_82575(struct e1000_hw *hw, u16 mask) +{ + u32 swfw_sync; + + while (igb_get_hw_semaphore(hw) != 0) + ; /* Empty */ + + swfw_sync = rd32(E1000_SW_FW_SYNC); + swfw_sync &= ~mask; + wr32(E1000_SW_FW_SYNC, swfw_sync); + + igb_put_hw_semaphore(hw); +} + +/** + * igb_get_cfg_done_82575 - Read config done bit + * @hw: pointer to the HW structure + * + * Read the management control register for the config done bit for + * completion status. NOTE: silicon which is EEPROM-less will fail trying + * to read the config done bit, so an error is *ONLY* logged and returns + * 0. If we were to return with error, EEPROM-less silicon + * would not be able to be reset or change link. + **/ +static s32 igb_get_cfg_done_82575(struct e1000_hw *hw) +{ + s32 timeout = PHY_CFG_TIMEOUT; + u32 mask = E1000_NVM_CFG_DONE_PORT_0; + + if (hw->bus.func == 1) + mask = E1000_NVM_CFG_DONE_PORT_1; + else if (hw->bus.func == E1000_FUNC_2) + mask = E1000_NVM_CFG_DONE_PORT_2; + else if (hw->bus.func == E1000_FUNC_3) + mask = E1000_NVM_CFG_DONE_PORT_3; + + while (timeout) { + if (rd32(E1000_EEMNGCTL) & mask) + break; + usleep_range(1000, 2000); + timeout--; + } + if (!timeout) + hw_dbg("MNG configuration cycle has not completed.\n"); + + /* If EEPROM is not marked present, init the PHY manually */ + if (((rd32(E1000_EECD) & E1000_EECD_PRES) == 0) && + (hw->phy.type == e1000_phy_igp_3)) + igb_phy_init_script_igp3(hw); + + return 0; +} + +/** + * igb_get_link_up_info_82575 - Get link speed/duplex info + * @hw: pointer to the HW structure + * @speed: stores the current speed + * @duplex: stores the current duplex + * + * This is a wrapper function, if using the serial gigabit media independent + * interface, use PCS to retrieve the link speed and duplex information. + * Otherwise, use the generic function to get the link speed and duplex info. + **/ +static s32 igb_get_link_up_info_82575(struct e1000_hw *hw, u16 *speed, + u16 *duplex) +{ + s32 ret_val; + + if (hw->phy.media_type != e1000_media_type_copper) + ret_val = igb_get_pcs_speed_and_duplex_82575(hw, speed, + duplex); + else + ret_val = igb_get_speed_and_duplex_copper(hw, speed, + duplex); + + return ret_val; +} + +/** + * igb_check_for_link_82575 - Check for link + * @hw: pointer to the HW structure + * + * If sgmii is enabled, then use the pcs register to determine link, otherwise + * use the generic interface for determining link. + **/ +static s32 igb_check_for_link_82575(struct e1000_hw *hw) +{ + s32 ret_val; + u16 speed, duplex; + + if (hw->phy.media_type != e1000_media_type_copper) { + ret_val = igb_get_pcs_speed_and_duplex_82575(hw, &speed, + &duplex); + /* Use this flag to determine if link needs to be checked or + * not. If we have link clear the flag so that we do not + * continue to check for link. + */ + hw->mac.get_link_status = !hw->mac.serdes_has_link; + + /* Configure Flow Control now that Auto-Neg has completed. + * First, we need to restore the desired flow control + * settings because we may have had to re-autoneg with a + * different link partner. + */ + ret_val = igb_config_fc_after_link_up(hw); + if (ret_val) + hw_dbg("Error configuring flow control\n"); + } else { + ret_val = igb_check_for_copper_link(hw); + } + + return ret_val; +} + +/** + * igb_power_up_serdes_link_82575 - Power up the serdes link after shutdown + * @hw: pointer to the HW structure + **/ +void igb_power_up_serdes_link_82575(struct e1000_hw *hw) +{ + u32 reg; + + + if ((hw->phy.media_type != e1000_media_type_internal_serdes) && + !igb_sgmii_active_82575(hw)) + return; + + /* Enable PCS to turn on link */ + reg = rd32(E1000_PCS_CFG0); + reg |= E1000_PCS_CFG_PCS_EN; + wr32(E1000_PCS_CFG0, reg); + + /* Power up the laser */ + reg = rd32(E1000_CTRL_EXT); + reg &= ~E1000_CTRL_EXT_SDP3_DATA; + wr32(E1000_CTRL_EXT, reg); + + /* flush the write to verify completion */ + wrfl(); + usleep_range(1000, 2000); +} + +/** + * igb_get_pcs_speed_and_duplex_82575 - Retrieve current speed/duplex + * @hw: pointer to the HW structure + * @speed: stores the current speed + * @duplex: stores the current duplex + * + * Using the physical coding sub-layer (PCS), retrieve the current speed and + * duplex, then store the values in the pointers provided. + **/ +static s32 igb_get_pcs_speed_and_duplex_82575(struct e1000_hw *hw, u16 *speed, + u16 *duplex) +{ + struct e1000_mac_info *mac = &hw->mac; + u32 pcs, status; + + /* Set up defaults for the return values of this function */ + mac->serdes_has_link = false; + *speed = 0; + *duplex = 0; + + /* Read the PCS Status register for link state. For non-copper mode, + * the status register is not accurate. The PCS status register is + * used instead. + */ + pcs = rd32(E1000_PCS_LSTAT); + + /* The link up bit determines when link is up on autoneg. The sync ok + * gets set once both sides sync up and agree upon link. Stable link + * can be determined by checking for both link up and link sync ok + */ + if ((pcs & E1000_PCS_LSTS_LINK_OK) && (pcs & E1000_PCS_LSTS_SYNK_OK)) { + mac->serdes_has_link = true; + + /* Detect and store PCS speed */ + if (pcs & E1000_PCS_LSTS_SPEED_1000) + *speed = SPEED_1000; + else if (pcs & E1000_PCS_LSTS_SPEED_100) + *speed = SPEED_100; + else + *speed = SPEED_10; + + /* Detect and store PCS duplex */ + if (pcs & E1000_PCS_LSTS_DUPLEX_FULL) + *duplex = FULL_DUPLEX; + else + *duplex = HALF_DUPLEX; + + /* Check if it is an I354 2.5Gb backplane connection. */ + if (mac->type == e1000_i354) { + status = rd32(E1000_STATUS); + if ((status & E1000_STATUS_2P5_SKU) && + !(status & E1000_STATUS_2P5_SKU_OVER)) { + *speed = SPEED_2500; + *duplex = FULL_DUPLEX; + hw_dbg("2500 Mbs, "); + hw_dbg("Full Duplex\n"); + } + } + + } + + return 0; +} + +/** + * igb_shutdown_serdes_link_82575 - Remove link during power down + * @hw: pointer to the HW structure + * + * In the case of fiber serdes, shut down optics and PCS on driver unload + * when management pass thru is not enabled. + **/ +void igb_shutdown_serdes_link_82575(struct e1000_hw *hw) +{ + u32 reg; + + if (hw->phy.media_type != e1000_media_type_internal_serdes && + igb_sgmii_active_82575(hw)) + return; + + if (!igb_enable_mng_pass_thru(hw)) { + /* Disable PCS to turn off link */ + reg = rd32(E1000_PCS_CFG0); + reg &= ~E1000_PCS_CFG_PCS_EN; + wr32(E1000_PCS_CFG0, reg); + + /* shutdown the laser */ + reg = rd32(E1000_CTRL_EXT); + reg |= E1000_CTRL_EXT_SDP3_DATA; + wr32(E1000_CTRL_EXT, reg); + + /* flush the write to verify completion */ + wrfl(); + usleep_range(1000, 2000); + } +} + +/** + * igb_reset_hw_82575 - Reset hardware + * @hw: pointer to the HW structure + * + * This resets the hardware into a known state. This is a + * function pointer entry point called by the api module. + **/ +static s32 igb_reset_hw_82575(struct e1000_hw *hw) +{ + u32 ctrl; + s32 ret_val; + + /* Prevent the PCI-E bus from sticking if there is no TLP connection + * on the last TLP read/write transaction when MAC is reset. + */ + ret_val = igb_disable_pcie_master(hw); + if (ret_val) + hw_dbg("PCI-E Master disable polling has failed.\n"); + + /* set the completion timeout for interface */ + ret_val = igb_set_pcie_completion_timeout(hw); + if (ret_val) + hw_dbg("PCI-E Set completion timeout has failed.\n"); + + hw_dbg("Masking off all interrupts\n"); + wr32(E1000_IMC, 0xffffffff); + + wr32(E1000_RCTL, 0); + wr32(E1000_TCTL, E1000_TCTL_PSP); + wrfl(); + + usleep_range(10000, 20000); + + ctrl = rd32(E1000_CTRL); + + hw_dbg("Issuing a global reset to MAC\n"); + wr32(E1000_CTRL, ctrl | E1000_CTRL_RST); + + ret_val = igb_get_auto_rd_done(hw); + if (ret_val) { + /* When auto config read does not complete, do not + * return with an error. This can happen in situations + * where there is no eeprom and prevents getting link. + */ + hw_dbg("Auto Read Done did not complete\n"); + } + + /* If EEPROM is not present, run manual init scripts */ + if ((rd32(E1000_EECD) & E1000_EECD_PRES) == 0) + igb_reset_init_script_82575(hw); + + /* Clear any pending interrupt events. */ + wr32(E1000_IMC, 0xffffffff); + rd32(E1000_ICR); + + /* Install any alternate MAC address into RAR0 */ + ret_val = igb_check_alt_mac_addr(hw); + + return ret_val; +} + +/** + * igb_init_hw_82575 - Initialize hardware + * @hw: pointer to the HW structure + * + * This inits the hardware readying it for operation. + **/ +static s32 igb_init_hw_82575(struct e1000_hw *hw) +{ + struct e1000_mac_info *mac = &hw->mac; + s32 ret_val; + u16 i, rar_count = mac->rar_entry_count; + + if ((hw->mac.type >= e1000_i210) && + !(igb_get_flash_presence_i210(hw))) { + ret_val = igb_pll_workaround_i210(hw); + if (ret_val) + return ret_val; + } + + /* Initialize identification LED */ + ret_val = igb_id_led_init(hw); + if (ret_val) { + hw_dbg("Error initializing identification LED\n"); + /* This is not fatal and we should not stop init due to this */ + } + + /* Disabling VLAN filtering */ + hw_dbg("Initializing the IEEE VLAN\n"); + igb_clear_vfta(hw); + + /* Setup the receive address */ + igb_init_rx_addrs(hw, rar_count); + + /* Zero out the Multicast HASH table */ + hw_dbg("Zeroing the MTA\n"); + for (i = 0; i < mac->mta_reg_count; i++) + array_wr32(E1000_MTA, i, 0); + + /* Zero out the Unicast HASH table */ + hw_dbg("Zeroing the UTA\n"); + for (i = 0; i < mac->uta_reg_count; i++) + array_wr32(E1000_UTA, i, 0); + + /* Setup link and flow control */ + ret_val = igb_setup_link(hw); + + /* Clear all of the statistics registers (clear on read). It is + * important that we do this after we have tried to establish link + * because the symbol error count will increment wildly if there + * is no link. + */ + igb_clear_hw_cntrs_82575(hw); + return ret_val; +} + +/** + * igb_setup_copper_link_82575 - Configure copper link settings + * @hw: pointer to the HW structure + * + * Configures the link for auto-neg or forced speed and duplex. Then we check + * for link, once link is established calls to configure collision distance + * and flow control are called. + **/ +static s32 igb_setup_copper_link_82575(struct e1000_hw *hw) +{ + u32 ctrl; + s32 ret_val; + u32 phpm_reg; + + ctrl = rd32(E1000_CTRL); + ctrl |= E1000_CTRL_SLU; + ctrl &= ~(E1000_CTRL_FRCSPD | E1000_CTRL_FRCDPX); + wr32(E1000_CTRL, ctrl); + + /* Clear Go Link Disconnect bit on supported devices */ + switch (hw->mac.type) { + case e1000_82580: + case e1000_i350: + case e1000_i210: + case e1000_i211: + phpm_reg = rd32(E1000_82580_PHY_POWER_MGMT); + phpm_reg &= ~E1000_82580_PM_GO_LINKD; + wr32(E1000_82580_PHY_POWER_MGMT, phpm_reg); + break; + default: + break; + } + + ret_val = igb_setup_serdes_link_82575(hw); + if (ret_val) + goto out; + + if (igb_sgmii_active_82575(hw) && !hw->phy.reset_disable) { + /* allow time for SFP cage time to power up phy */ + msleep(300); + + ret_val = hw->phy.ops.reset(hw); + if (ret_val) { + hw_dbg("Error resetting the PHY.\n"); + goto out; + } + } + switch (hw->phy.type) { + case e1000_phy_i210: + case e1000_phy_m88: + switch (hw->phy.id) { + case I347AT4_E_PHY_ID: + case M88E1112_E_PHY_ID: + case M88E1543_E_PHY_ID: + case M88E1512_E_PHY_ID: + case I210_I_PHY_ID: + ret_val = igb_copper_link_setup_m88_gen2(hw); + break; + default: + ret_val = igb_copper_link_setup_m88(hw); + break; + } + break; + case e1000_phy_igp_3: + ret_val = igb_copper_link_setup_igp(hw); + break; + case e1000_phy_82580: + ret_val = igb_copper_link_setup_82580(hw); + break; + case e1000_phy_bcm54616: + ret_val = 0; + break; + default: + ret_val = -E1000_ERR_PHY; + break; + } + + if (ret_val) + goto out; + + ret_val = igb_setup_copper_link(hw); +out: + return ret_val; +} + +/** + * igb_setup_serdes_link_82575 - Setup link for serdes + * @hw: pointer to the HW structure + * + * Configure the physical coding sub-layer (PCS) link. The PCS link is + * used on copper connections where the serialized gigabit media independent + * interface (sgmii), or serdes fiber is being used. Configures the link + * for auto-negotiation or forces speed/duplex. + **/ +static s32 igb_setup_serdes_link_82575(struct e1000_hw *hw) +{ + u32 ctrl_ext, ctrl_reg, reg, anadv_reg; + bool pcs_autoneg; + s32 ret_val = 0; + u16 data; + + if ((hw->phy.media_type != e1000_media_type_internal_serdes) && + !igb_sgmii_active_82575(hw)) + return ret_val; + + + /* On the 82575, SerDes loopback mode persists until it is + * explicitly turned off or a power cycle is performed. A read to + * the register does not indicate its status. Therefore, we ensure + * loopback mode is disabled during initialization. + */ + wr32(E1000_SCTL, E1000_SCTL_DISABLE_SERDES_LOOPBACK); + + /* power on the sfp cage if present and turn on I2C */ + ctrl_ext = rd32(E1000_CTRL_EXT); + ctrl_ext &= ~E1000_CTRL_EXT_SDP3_DATA; + ctrl_ext |= E1000_CTRL_I2C_ENA; + wr32(E1000_CTRL_EXT, ctrl_ext); + + ctrl_reg = rd32(E1000_CTRL); + ctrl_reg |= E1000_CTRL_SLU; + + if (hw->mac.type == e1000_82575 || hw->mac.type == e1000_82576) { + /* set both sw defined pins */ + ctrl_reg |= E1000_CTRL_SWDPIN0 | E1000_CTRL_SWDPIN1; + + /* Set switch control to serdes energy detect */ + reg = rd32(E1000_CONNSW); + reg |= E1000_CONNSW_ENRGSRC; + wr32(E1000_CONNSW, reg); + } + + reg = rd32(E1000_PCS_LCTL); + + /* default pcs_autoneg to the same setting as mac autoneg */ + pcs_autoneg = hw->mac.autoneg; + + switch (ctrl_ext & E1000_CTRL_EXT_LINK_MODE_MASK) { + case E1000_CTRL_EXT_LINK_MODE_SGMII: + /* sgmii mode lets the phy handle forcing speed/duplex */ + pcs_autoneg = true; + /* autoneg time out should be disabled for SGMII mode */ + reg &= ~(E1000_PCS_LCTL_AN_TIMEOUT); + break; + case E1000_CTRL_EXT_LINK_MODE_1000BASE_KX: + /* disable PCS autoneg and support parallel detect only */ + pcs_autoneg = false; + fallthrough; + default: + if (hw->mac.type == e1000_82575 || + hw->mac.type == e1000_82576) { + ret_val = hw->nvm.ops.read(hw, NVM_COMPAT, 1, &data); + if (ret_val) { + hw_dbg(KERN_DEBUG "NVM Read Error\n\n"); + return ret_val; + } + + if (data & E1000_EEPROM_PCS_AUTONEG_DISABLE_BIT) + pcs_autoneg = false; + } + + /* non-SGMII modes only supports a speed of 1000/Full for the + * link so it is best to just force the MAC and let the pcs + * link either autoneg or be forced to 1000/Full + */ + ctrl_reg |= E1000_CTRL_SPD_1000 | E1000_CTRL_FRCSPD | + E1000_CTRL_FD | E1000_CTRL_FRCDPX; + + /* set speed of 1000/Full if speed/duplex is forced */ + reg |= E1000_PCS_LCTL_FSV_1000 | E1000_PCS_LCTL_FDV_FULL; + break; + } + + wr32(E1000_CTRL, ctrl_reg); + + /* New SerDes mode allows for forcing speed or autonegotiating speed + * at 1gb. Autoneg should be default set by most drivers. This is the + * mode that will be compatible with older link partners and switches. + * However, both are supported by the hardware and some drivers/tools. + */ + reg &= ~(E1000_PCS_LCTL_AN_ENABLE | E1000_PCS_LCTL_FLV_LINK_UP | + E1000_PCS_LCTL_FSD | E1000_PCS_LCTL_FORCE_LINK); + + if (pcs_autoneg) { + /* Set PCS register for autoneg */ + reg |= E1000_PCS_LCTL_AN_ENABLE | /* Enable Autoneg */ + E1000_PCS_LCTL_AN_RESTART; /* Restart autoneg */ + + /* Disable force flow control for autoneg */ + reg &= ~E1000_PCS_LCTL_FORCE_FCTRL; + + /* Configure flow control advertisement for autoneg */ + anadv_reg = rd32(E1000_PCS_ANADV); + anadv_reg &= ~(E1000_TXCW_ASM_DIR | E1000_TXCW_PAUSE); + switch (hw->fc.requested_mode) { + case e1000_fc_full: + case e1000_fc_rx_pause: + anadv_reg |= E1000_TXCW_ASM_DIR; + anadv_reg |= E1000_TXCW_PAUSE; + break; + case e1000_fc_tx_pause: + anadv_reg |= E1000_TXCW_ASM_DIR; + break; + default: + break; + } + wr32(E1000_PCS_ANADV, anadv_reg); + + hw_dbg("Configuring Autoneg:PCS_LCTL=0x%08X\n", reg); + } else { + /* Set PCS register for forced link */ + reg |= E1000_PCS_LCTL_FSD; /* Force Speed */ + + /* Force flow control for forced link */ + reg |= E1000_PCS_LCTL_FORCE_FCTRL; + + hw_dbg("Configuring Forced Link:PCS_LCTL=0x%08X\n", reg); + } + + wr32(E1000_PCS_LCTL, reg); + + if (!pcs_autoneg && !igb_sgmii_active_82575(hw)) + igb_force_mac_fc(hw); + + return ret_val; +} + +/** + * igb_sgmii_active_82575 - Return sgmii state + * @hw: pointer to the HW structure + * + * 82575 silicon has a serialized gigabit media independent interface (sgmii) + * which can be enabled for use in the embedded applications. Simply + * return the current state of the sgmii interface. + **/ +static bool igb_sgmii_active_82575(struct e1000_hw *hw) +{ + struct e1000_dev_spec_82575 *dev_spec = &hw->dev_spec._82575; + return dev_spec->sgmii_active; +} + +/** + * igb_reset_init_script_82575 - Inits HW defaults after reset + * @hw: pointer to the HW structure + * + * Inits recommended HW defaults after a reset when there is no EEPROM + * detected. This is only for the 82575. + **/ +static s32 igb_reset_init_script_82575(struct e1000_hw *hw) +{ + if (hw->mac.type == e1000_82575) { + hw_dbg("Running reset init script for 82575\n"); + /* SerDes configuration via SERDESCTRL */ + igb_write_8bit_ctrl_reg(hw, E1000_SCTL, 0x00, 0x0C); + igb_write_8bit_ctrl_reg(hw, E1000_SCTL, 0x01, 0x78); + igb_write_8bit_ctrl_reg(hw, E1000_SCTL, 0x1B, 0x23); + igb_write_8bit_ctrl_reg(hw, E1000_SCTL, 0x23, 0x15); + + /* CCM configuration via CCMCTL register */ + igb_write_8bit_ctrl_reg(hw, E1000_CCMCTL, 0x14, 0x00); + igb_write_8bit_ctrl_reg(hw, E1000_CCMCTL, 0x10, 0x00); + + /* PCIe lanes configuration */ + igb_write_8bit_ctrl_reg(hw, E1000_GIOCTL, 0x00, 0xEC); + igb_write_8bit_ctrl_reg(hw, E1000_GIOCTL, 0x61, 0xDF); + igb_write_8bit_ctrl_reg(hw, E1000_GIOCTL, 0x34, 0x05); + igb_write_8bit_ctrl_reg(hw, E1000_GIOCTL, 0x2F, 0x81); + + /* PCIe PLL Configuration */ + igb_write_8bit_ctrl_reg(hw, E1000_SCCTL, 0x02, 0x47); + igb_write_8bit_ctrl_reg(hw, E1000_SCCTL, 0x14, 0x00); + igb_write_8bit_ctrl_reg(hw, E1000_SCCTL, 0x10, 0x00); + } + + return 0; +} + +/** + * igb_read_mac_addr_82575 - Read device MAC address + * @hw: pointer to the HW structure + **/ +static s32 igb_read_mac_addr_82575(struct e1000_hw *hw) +{ + s32 ret_val = 0; + + /* If there's an alternate MAC address place it in RAR0 + * so that it will override the Si installed default perm + * address. + */ + ret_val = igb_check_alt_mac_addr(hw); + if (ret_val) + goto out; + + ret_val = igb_read_mac_addr(hw); + +out: + return ret_val; +} + +/** + * igb_power_down_phy_copper_82575 - Remove link during PHY power down + * @hw: pointer to the HW structure + * + * In the case of a PHY power down to save power, or to turn off link during a + * driver unload, or wake on lan is not enabled, remove the link. + **/ +void igb_power_down_phy_copper_82575(struct e1000_hw *hw) +{ + /* If the management interface is not enabled, then power down */ + if (!(igb_enable_mng_pass_thru(hw) || igb_check_reset_block(hw))) + igb_power_down_phy_copper(hw); +} + +/** + * igb_clear_hw_cntrs_82575 - Clear device specific hardware counters + * @hw: pointer to the HW structure + * + * Clears the hardware counters by reading the counter registers. + **/ +static void igb_clear_hw_cntrs_82575(struct e1000_hw *hw) +{ + igb_clear_hw_cntrs_base(hw); + + rd32(E1000_PRC64); + rd32(E1000_PRC127); + rd32(E1000_PRC255); + rd32(E1000_PRC511); + rd32(E1000_PRC1023); + rd32(E1000_PRC1522); + rd32(E1000_PTC64); + rd32(E1000_PTC127); + rd32(E1000_PTC255); + rd32(E1000_PTC511); + rd32(E1000_PTC1023); + rd32(E1000_PTC1522); + + rd32(E1000_ALGNERRC); + rd32(E1000_RXERRC); + rd32(E1000_TNCRS); + rd32(E1000_CEXTERR); + rd32(E1000_TSCTC); + rd32(E1000_TSCTFC); + + rd32(E1000_MGTPRC); + rd32(E1000_MGTPDC); + rd32(E1000_MGTPTC); + + rd32(E1000_IAC); + rd32(E1000_ICRXOC); + + rd32(E1000_ICRXPTC); + rd32(E1000_ICRXATC); + rd32(E1000_ICTXPTC); + rd32(E1000_ICTXATC); + rd32(E1000_ICTXQEC); + rd32(E1000_ICTXQMTC); + rd32(E1000_ICRXDMTC); + + rd32(E1000_CBTMPC); + rd32(E1000_HTDPMC); + rd32(E1000_CBRMPC); + rd32(E1000_RPTHC); + rd32(E1000_HGPTC); + rd32(E1000_HTCBDPC); + rd32(E1000_HGORCL); + rd32(E1000_HGORCH); + rd32(E1000_HGOTCL); + rd32(E1000_HGOTCH); + rd32(E1000_LENERRS); + + /* This register should not be read in copper configurations */ + if (hw->phy.media_type == e1000_media_type_internal_serdes || + igb_sgmii_active_82575(hw)) + rd32(E1000_SCVPC); +} + +/** + * igb_rx_fifo_flush_82575 - Clean rx fifo after RX enable + * @hw: pointer to the HW structure + * + * After rx enable if manageability is enabled then there is likely some + * bad data at the start of the fifo and possibly in the DMA fifo. This + * function clears the fifos and flushes any packets that came in as rx was + * being enabled. + **/ +void igb_rx_fifo_flush_82575(struct e1000_hw *hw) +{ + u32 rctl, rlpml, rxdctl[4], rfctl, temp_rctl, rx_enabled; + int i, ms_wait; + + /* disable IPv6 options as per hardware errata */ + rfctl = rd32(E1000_RFCTL); + rfctl |= E1000_RFCTL_IPV6_EX_DIS; + wr32(E1000_RFCTL, rfctl); + + if (hw->mac.type != e1000_82575 || + !(rd32(E1000_MANC) & E1000_MANC_RCV_TCO_EN)) + return; + + /* Disable all RX queues */ + for (i = 0; i < 4; i++) { + rxdctl[i] = rd32(E1000_RXDCTL(i)); + wr32(E1000_RXDCTL(i), + rxdctl[i] & ~E1000_RXDCTL_QUEUE_ENABLE); + } + /* Poll all queues to verify they have shut down */ + for (ms_wait = 0; ms_wait < 10; ms_wait++) { + usleep_range(1000, 2000); + rx_enabled = 0; + for (i = 0; i < 4; i++) + rx_enabled |= rd32(E1000_RXDCTL(i)); + if (!(rx_enabled & E1000_RXDCTL_QUEUE_ENABLE)) + break; + } + + if (ms_wait == 10) + hw_dbg("Queue disable timed out after 10ms\n"); + + /* Clear RLPML, RCTL.SBP, RFCTL.LEF, and set RCTL.LPE so that all + * incoming packets are rejected. Set enable and wait 2ms so that + * any packet that was coming in as RCTL.EN was set is flushed + */ + wr32(E1000_RFCTL, rfctl & ~E1000_RFCTL_LEF); + + rlpml = rd32(E1000_RLPML); + wr32(E1000_RLPML, 0); + + rctl = rd32(E1000_RCTL); + temp_rctl = rctl & ~(E1000_RCTL_EN | E1000_RCTL_SBP); + temp_rctl |= E1000_RCTL_LPE; + + wr32(E1000_RCTL, temp_rctl); + wr32(E1000_RCTL, temp_rctl | E1000_RCTL_EN); + wrfl(); + usleep_range(2000, 3000); + + /* Enable RX queues that were previously enabled and restore our + * previous state + */ + for (i = 0; i < 4; i++) + wr32(E1000_RXDCTL(i), rxdctl[i]); + wr32(E1000_RCTL, rctl); + wrfl(); + + wr32(E1000_RLPML, rlpml); + wr32(E1000_RFCTL, rfctl); + + /* Flush receive errors generated by workaround */ + rd32(E1000_ROC); + rd32(E1000_RNBC); + rd32(E1000_MPC); +} + +/** + * igb_set_pcie_completion_timeout - set pci-e completion timeout + * @hw: pointer to the HW structure + * + * The defaults for 82575 and 82576 should be in the range of 50us to 50ms, + * however the hardware default for these parts is 500us to 1ms which is less + * than the 10ms recommended by the pci-e spec. To address this we need to + * increase the value to either 10ms to 200ms for capability version 1 config, + * or 16ms to 55ms for version 2. + **/ +static s32 igb_set_pcie_completion_timeout(struct e1000_hw *hw) +{ + u32 gcr = rd32(E1000_GCR); + s32 ret_val = 0; + u16 pcie_devctl2; + + /* only take action if timeout value is defaulted to 0 */ + if (gcr & E1000_GCR_CMPL_TMOUT_MASK) + goto out; + + /* if capabilities version is type 1 we can write the + * timeout of 10ms to 200ms through the GCR register + */ + if (!(gcr & E1000_GCR_CAP_VER2)) { + gcr |= E1000_GCR_CMPL_TMOUT_10ms; + goto out; + } + + /* for version 2 capabilities we need to write the config space + * directly in order to set the completion timeout value for + * 16ms to 55ms + */ + ret_val = igb_read_pcie_cap_reg(hw, PCIE_DEVICE_CONTROL2, + &pcie_devctl2); + if (ret_val) + goto out; + + pcie_devctl2 |= PCIE_DEVICE_CONTROL2_16ms; + + ret_val = igb_write_pcie_cap_reg(hw, PCIE_DEVICE_CONTROL2, + &pcie_devctl2); +out: + /* disable completion timeout resend */ + gcr &= ~E1000_GCR_CMPL_TMOUT_RESEND; + + wr32(E1000_GCR, gcr); + return ret_val; +} + +/** + * igb_vmdq_set_anti_spoofing_pf - enable or disable anti-spoofing + * @hw: pointer to the hardware struct + * @enable: state to enter, either enabled or disabled + * @pf: Physical Function pool - do not set anti-spoofing for the PF + * + * enables/disables L2 switch anti-spoofing functionality. + **/ +void igb_vmdq_set_anti_spoofing_pf(struct e1000_hw *hw, bool enable, int pf) +{ + u32 reg_val, reg_offset; + + switch (hw->mac.type) { + case e1000_82576: + reg_offset = E1000_DTXSWC; + break; + case e1000_i350: + case e1000_i354: + reg_offset = E1000_TXSWC; + break; + default: + return; + } + + reg_val = rd32(reg_offset); + if (enable) { + reg_val |= (E1000_DTXSWC_MAC_SPOOF_MASK | + E1000_DTXSWC_VLAN_SPOOF_MASK); + /* The PF can spoof - it has to in order to + * support emulation mode NICs + */ + reg_val ^= (BIT(pf) | BIT(pf + MAX_NUM_VFS)); + } else { + reg_val &= ~(E1000_DTXSWC_MAC_SPOOF_MASK | + E1000_DTXSWC_VLAN_SPOOF_MASK); + } + wr32(reg_offset, reg_val); +} + +/** + * igb_vmdq_set_loopback_pf - enable or disable vmdq loopback + * @hw: pointer to the hardware struct + * @enable: state to enter, either enabled or disabled + * + * enables/disables L2 switch loopback functionality. + **/ +void igb_vmdq_set_loopback_pf(struct e1000_hw *hw, bool enable) +{ + u32 dtxswc; + + switch (hw->mac.type) { + case e1000_82576: + dtxswc = rd32(E1000_DTXSWC); + if (enable) + dtxswc |= E1000_DTXSWC_VMDQ_LOOPBACK_EN; + else + dtxswc &= ~E1000_DTXSWC_VMDQ_LOOPBACK_EN; + wr32(E1000_DTXSWC, dtxswc); + break; + case e1000_i354: + case e1000_i350: + dtxswc = rd32(E1000_TXSWC); + if (enable) + dtxswc |= E1000_DTXSWC_VMDQ_LOOPBACK_EN; + else + dtxswc &= ~E1000_DTXSWC_VMDQ_LOOPBACK_EN; + wr32(E1000_TXSWC, dtxswc); + break; + default: + /* Currently no other hardware supports loopback */ + break; + } + +} + +/** + * igb_vmdq_set_replication_pf - enable or disable vmdq replication + * @hw: pointer to the hardware struct + * @enable: state to enter, either enabled or disabled + * + * enables/disables replication of packets across multiple pools. + **/ +void igb_vmdq_set_replication_pf(struct e1000_hw *hw, bool enable) +{ + u32 vt_ctl = rd32(E1000_VT_CTL); + + if (enable) + vt_ctl |= E1000_VT_CTL_VM_REPL_EN; + else + vt_ctl &= ~E1000_VT_CTL_VM_REPL_EN; + + wr32(E1000_VT_CTL, vt_ctl); +} + +/** + * igb_read_phy_reg_82580 - Read 82580 MDI control register + * @hw: pointer to the HW structure + * @offset: register offset to be read + * @data: pointer to the read data + * + * Reads the MDI control register in the PHY at offset and stores the + * information read to data. + **/ +s32 igb_read_phy_reg_82580(struct e1000_hw *hw, u32 offset, u16 *data) +{ + s32 ret_val; + + ret_val = hw->phy.ops.acquire(hw); + if (ret_val) + goto out; + + ret_val = igb_read_phy_reg_mdic(hw, offset, data); + + hw->phy.ops.release(hw); + +out: + return ret_val; +} + +/** + * igb_write_phy_reg_82580 - Write 82580 MDI control register + * @hw: pointer to the HW structure + * @offset: register offset to write to + * @data: data to write to register at offset + * + * Writes data to MDI control register in the PHY at offset. + **/ +s32 igb_write_phy_reg_82580(struct e1000_hw *hw, u32 offset, u16 data) +{ + s32 ret_val; + + + ret_val = hw->phy.ops.acquire(hw); + if (ret_val) + goto out; + + ret_val = igb_write_phy_reg_mdic(hw, offset, data); + + hw->phy.ops.release(hw); + +out: + return ret_val; +} + +/** + * igb_reset_mdicnfg_82580 - Reset MDICNFG destination and com_mdio bits + * @hw: pointer to the HW structure + * + * This resets the MDICNFG.Destination and MDICNFG.Com_MDIO bits based on + * the values found in the EEPROM. This addresses an issue in which these + * bits are not restored from EEPROM after reset. + **/ +static s32 igb_reset_mdicnfg_82580(struct e1000_hw *hw) +{ + s32 ret_val = 0; + u32 mdicnfg; + u16 nvm_data = 0; + + if (hw->mac.type != e1000_82580) + goto out; + if (!igb_sgmii_active_82575(hw)) + goto out; + + ret_val = hw->nvm.ops.read(hw, NVM_INIT_CONTROL3_PORT_A + + NVM_82580_LAN_FUNC_OFFSET(hw->bus.func), 1, + &nvm_data); + if (ret_val) { + hw_dbg("NVM Read Error\n"); + goto out; + } + + mdicnfg = rd32(E1000_MDICNFG); + if (nvm_data & NVM_WORD24_EXT_MDIO) + mdicnfg |= E1000_MDICNFG_EXT_MDIO; + if (nvm_data & NVM_WORD24_COM_MDIO) + mdicnfg |= E1000_MDICNFG_COM_MDIO; + wr32(E1000_MDICNFG, mdicnfg); +out: + return ret_val; +} + +/** + * igb_reset_hw_82580 - Reset hardware + * @hw: pointer to the HW structure + * + * This resets function or entire device (all ports, etc.) + * to a known state. + **/ +static s32 igb_reset_hw_82580(struct e1000_hw *hw) +{ + s32 ret_val = 0; + /* BH SW mailbox bit in SW_FW_SYNC */ + u16 swmbsw_mask = E1000_SW_SYNCH_MB; + u32 ctrl; + bool global_device_reset = hw->dev_spec._82575.global_device_reset; + + hw->dev_spec._82575.global_device_reset = false; + + /* due to hw errata, global device reset doesn't always + * work on 82580 + */ + if (hw->mac.type == e1000_82580) + global_device_reset = false; + + /* Get current control state. */ + ctrl = rd32(E1000_CTRL); + + /* Prevent the PCI-E bus from sticking if there is no TLP connection + * on the last TLP read/write transaction when MAC is reset. + */ + ret_val = igb_disable_pcie_master(hw); + if (ret_val) + hw_dbg("PCI-E Master disable polling has failed.\n"); + + hw_dbg("Masking off all interrupts\n"); + wr32(E1000_IMC, 0xffffffff); + wr32(E1000_RCTL, 0); + wr32(E1000_TCTL, E1000_TCTL_PSP); + wrfl(); + + usleep_range(10000, 11000); + + /* Determine whether or not a global dev reset is requested */ + if (global_device_reset && + hw->mac.ops.acquire_swfw_sync(hw, swmbsw_mask)) + global_device_reset = false; + + if (global_device_reset && + !(rd32(E1000_STATUS) & E1000_STAT_DEV_RST_SET)) + ctrl |= E1000_CTRL_DEV_RST; + else + ctrl |= E1000_CTRL_RST; + + wr32(E1000_CTRL, ctrl); + wrfl(); + + /* Add delay to insure DEV_RST has time to complete */ + if (global_device_reset) + usleep_range(5000, 6000); + + ret_val = igb_get_auto_rd_done(hw); + if (ret_val) { + /* When auto config read does not complete, do not + * return with an error. This can happen in situations + * where there is no eeprom and prevents getting link. + */ + hw_dbg("Auto Read Done did not complete\n"); + } + + /* clear global device reset status bit */ + wr32(E1000_STATUS, E1000_STAT_DEV_RST_SET); + + /* Clear any pending interrupt events. */ + wr32(E1000_IMC, 0xffffffff); + rd32(E1000_ICR); + + ret_val = igb_reset_mdicnfg_82580(hw); + if (ret_val) + hw_dbg("Could not reset MDICNFG based on EEPROM\n"); + + /* Install any alternate MAC address into RAR0 */ + ret_val = igb_check_alt_mac_addr(hw); + + /* Release semaphore */ + if (global_device_reset) + hw->mac.ops.release_swfw_sync(hw, swmbsw_mask); + + return ret_val; +} + +/** + * igb_rxpbs_adjust_82580 - adjust RXPBS value to reflect actual RX PBA size + * @data: data received by reading RXPBS register + * + * The 82580 uses a table based approach for packet buffer allocation sizes. + * This function converts the retrieved value into the correct table value + * 0x0 0x1 0x2 0x3 0x4 0x5 0x6 0x7 + * 0x0 36 72 144 1 2 4 8 16 + * 0x8 35 70 140 rsv rsv rsv rsv rsv + */ +u16 igb_rxpbs_adjust_82580(u32 data) +{ + u16 ret_val = 0; + + if (data < ARRAY_SIZE(e1000_82580_rxpbs_table)) + ret_val = e1000_82580_rxpbs_table[data]; + + return ret_val; +} + +/** + * igb_validate_nvm_checksum_with_offset - Validate EEPROM + * checksum + * @hw: pointer to the HW structure + * @offset: offset in words of the checksum protected region + * + * Calculates the EEPROM checksum by reading/adding each word of the EEPROM + * and then verifies that the sum of the EEPROM is equal to 0xBABA. + **/ +static s32 igb_validate_nvm_checksum_with_offset(struct e1000_hw *hw, + u16 offset) +{ + s32 ret_val = 0; + u16 checksum = 0; + u16 i, nvm_data; + + for (i = offset; i < ((NVM_CHECKSUM_REG + offset) + 1); i++) { + ret_val = hw->nvm.ops.read(hw, i, 1, &nvm_data); + if (ret_val) { + hw_dbg("NVM Read Error\n"); + goto out; + } + checksum += nvm_data; + } + + if (checksum != (u16) NVM_SUM) { + hw_dbg("NVM Checksum Invalid\n"); + ret_val = -E1000_ERR_NVM; + goto out; + } + +out: + return ret_val; +} + +/** + * igb_update_nvm_checksum_with_offset - Update EEPROM + * checksum + * @hw: pointer to the HW structure + * @offset: offset in words of the checksum protected region + * + * Updates the EEPROM checksum by reading/adding each word of the EEPROM + * up to the checksum. Then calculates the EEPROM checksum and writes the + * value to the EEPROM. + **/ +static s32 igb_update_nvm_checksum_with_offset(struct e1000_hw *hw, u16 offset) +{ + s32 ret_val; + u16 checksum = 0; + u16 i, nvm_data; + + for (i = offset; i < (NVM_CHECKSUM_REG + offset); i++) { + ret_val = hw->nvm.ops.read(hw, i, 1, &nvm_data); + if (ret_val) { + hw_dbg("NVM Read Error while updating checksum.\n"); + goto out; + } + checksum += nvm_data; + } + checksum = (u16) NVM_SUM - checksum; + ret_val = hw->nvm.ops.write(hw, (NVM_CHECKSUM_REG + offset), 1, + &checksum); + if (ret_val) + hw_dbg("NVM Write Error while updating checksum.\n"); + +out: + return ret_val; +} + +/** + * igb_validate_nvm_checksum_82580 - Validate EEPROM checksum + * @hw: pointer to the HW structure + * + * Calculates the EEPROM section checksum by reading/adding each word of + * the EEPROM and then verifies that the sum of the EEPROM is + * equal to 0xBABA. + **/ +static s32 igb_validate_nvm_checksum_82580(struct e1000_hw *hw) +{ + s32 ret_val = 0; + u16 eeprom_regions_count = 1; + u16 j, nvm_data; + u16 nvm_offset; + + ret_val = hw->nvm.ops.read(hw, NVM_COMPATIBILITY_REG_3, 1, &nvm_data); + if (ret_val) { + hw_dbg("NVM Read Error\n"); + goto out; + } + + if (nvm_data & NVM_COMPATIBILITY_BIT_MASK) { + /* if checksums compatibility bit is set validate checksums + * for all 4 ports. + */ + eeprom_regions_count = 4; + } + + for (j = 0; j < eeprom_regions_count; j++) { + nvm_offset = NVM_82580_LAN_FUNC_OFFSET(j); + ret_val = igb_validate_nvm_checksum_with_offset(hw, + nvm_offset); + if (ret_val != 0) + goto out; + } + +out: + return ret_val; +} + +/** + * igb_update_nvm_checksum_82580 - Update EEPROM checksum + * @hw: pointer to the HW structure + * + * Updates the EEPROM section checksums for all 4 ports by reading/adding + * each word of the EEPROM up to the checksum. Then calculates the EEPROM + * checksum and writes the value to the EEPROM. + **/ +static s32 igb_update_nvm_checksum_82580(struct e1000_hw *hw) +{ + s32 ret_val; + u16 j, nvm_data; + u16 nvm_offset; + + ret_val = hw->nvm.ops.read(hw, NVM_COMPATIBILITY_REG_3, 1, &nvm_data); + if (ret_val) { + hw_dbg("NVM Read Error while updating checksum compatibility bit.\n"); + goto out; + } + + if ((nvm_data & NVM_COMPATIBILITY_BIT_MASK) == 0) { + /* set compatibility bit to validate checksums appropriately */ + nvm_data = nvm_data | NVM_COMPATIBILITY_BIT_MASK; + ret_val = hw->nvm.ops.write(hw, NVM_COMPATIBILITY_REG_3, 1, + &nvm_data); + if (ret_val) { + hw_dbg("NVM Write Error while updating checksum compatibility bit.\n"); + goto out; + } + } + + for (j = 0; j < 4; j++) { + nvm_offset = NVM_82580_LAN_FUNC_OFFSET(j); + ret_val = igb_update_nvm_checksum_with_offset(hw, nvm_offset); + if (ret_val) + goto out; + } + +out: + return ret_val; +} + +/** + * igb_validate_nvm_checksum_i350 - Validate EEPROM checksum + * @hw: pointer to the HW structure + * + * Calculates the EEPROM section checksum by reading/adding each word of + * the EEPROM and then verifies that the sum of the EEPROM is + * equal to 0xBABA. + **/ +static s32 igb_validate_nvm_checksum_i350(struct e1000_hw *hw) +{ + s32 ret_val = 0; + u16 j; + u16 nvm_offset; + + for (j = 0; j < 4; j++) { + nvm_offset = NVM_82580_LAN_FUNC_OFFSET(j); + ret_val = igb_validate_nvm_checksum_with_offset(hw, + nvm_offset); + if (ret_val != 0) + goto out; + } + +out: + return ret_val; +} + +/** + * igb_update_nvm_checksum_i350 - Update EEPROM checksum + * @hw: pointer to the HW structure + * + * Updates the EEPROM section checksums for all 4 ports by reading/adding + * each word of the EEPROM up to the checksum. Then calculates the EEPROM + * checksum and writes the value to the EEPROM. + **/ +static s32 igb_update_nvm_checksum_i350(struct e1000_hw *hw) +{ + s32 ret_val = 0; + u16 j; + u16 nvm_offset; + + for (j = 0; j < 4; j++) { + nvm_offset = NVM_82580_LAN_FUNC_OFFSET(j); + ret_val = igb_update_nvm_checksum_with_offset(hw, nvm_offset); + if (ret_val != 0) + goto out; + } + +out: + return ret_val; +} + +/** + * __igb_access_emi_reg - Read/write EMI register + * @hw: pointer to the HW structure + * @address: EMI address to program + * @data: pointer to value to read/write from/to the EMI address + * @read: boolean flag to indicate read or write + **/ +static s32 __igb_access_emi_reg(struct e1000_hw *hw, u16 address, + u16 *data, bool read) +{ + s32 ret_val = 0; + + ret_val = hw->phy.ops.write_reg(hw, E1000_EMIADD, address); + if (ret_val) + return ret_val; + + if (read) + ret_val = hw->phy.ops.read_reg(hw, E1000_EMIDATA, data); + else + ret_val = hw->phy.ops.write_reg(hw, E1000_EMIDATA, *data); + + return ret_val; +} + +/** + * igb_read_emi_reg - Read Extended Management Interface register + * @hw: pointer to the HW structure + * @addr: EMI address to program + * @data: value to be read from the EMI address + **/ +s32 igb_read_emi_reg(struct e1000_hw *hw, u16 addr, u16 *data) +{ + return __igb_access_emi_reg(hw, addr, data, true); +} + +/** + * igb_set_eee_i350 - Enable/disable EEE support + * @hw: pointer to the HW structure + * @adv1G: boolean flag enabling 1G EEE advertisement + * @adv100M: boolean flag enabling 100M EEE advertisement + * + * Enable/disable EEE based on setting in dev_spec structure. + * + **/ +s32 igb_set_eee_i350(struct e1000_hw *hw, bool adv1G, bool adv100M) +{ + u32 ipcnfg, eeer; + + if ((hw->mac.type < e1000_i350) || + (hw->phy.media_type != e1000_media_type_copper)) + goto out; + ipcnfg = rd32(E1000_IPCNFG); + eeer = rd32(E1000_EEER); + + /* enable or disable per user setting */ + if (!(hw->dev_spec._82575.eee_disable)) { + u32 eee_su = rd32(E1000_EEE_SU); + + if (adv100M) + ipcnfg |= E1000_IPCNFG_EEE_100M_AN; + else + ipcnfg &= ~E1000_IPCNFG_EEE_100M_AN; + + if (adv1G) + ipcnfg |= E1000_IPCNFG_EEE_1G_AN; + else + ipcnfg &= ~E1000_IPCNFG_EEE_1G_AN; + + eeer |= (E1000_EEER_TX_LPI_EN | E1000_EEER_RX_LPI_EN | + E1000_EEER_LPI_FC); + + /* This bit should not be set in normal operation. */ + if (eee_su & E1000_EEE_SU_LPI_CLK_STP) + hw_dbg("LPI Clock Stop Bit should not be set!\n"); + + } else { + ipcnfg &= ~(E1000_IPCNFG_EEE_1G_AN | + E1000_IPCNFG_EEE_100M_AN); + eeer &= ~(E1000_EEER_TX_LPI_EN | + E1000_EEER_RX_LPI_EN | + E1000_EEER_LPI_FC); + } + wr32(E1000_IPCNFG, ipcnfg); + wr32(E1000_EEER, eeer); + rd32(E1000_IPCNFG); + rd32(E1000_EEER); +out: + + return 0; +} + +/** + * igb_set_eee_i354 - Enable/disable EEE support + * @hw: pointer to the HW structure + * @adv1G: boolean flag enabling 1G EEE advertisement + * @adv100M: boolean flag enabling 100M EEE advertisement + * + * Enable/disable EEE legacy mode based on setting in dev_spec structure. + * + **/ +s32 igb_set_eee_i354(struct e1000_hw *hw, bool adv1G, bool adv100M) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val = 0; + u16 phy_data; + + if ((hw->phy.media_type != e1000_media_type_copper) || + ((phy->id != M88E1543_E_PHY_ID) && + (phy->id != M88E1512_E_PHY_ID))) + goto out; + + if (!hw->dev_spec._82575.eee_disable) { + /* Switch to PHY page 18. */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1543_PAGE_ADDR, 18); + if (ret_val) + goto out; + + ret_val = phy->ops.read_reg(hw, E1000_M88E1543_EEE_CTRL_1, + &phy_data); + if (ret_val) + goto out; + + phy_data |= E1000_M88E1543_EEE_CTRL_1_MS; + ret_val = phy->ops.write_reg(hw, E1000_M88E1543_EEE_CTRL_1, + phy_data); + if (ret_val) + goto out; + + /* Return the PHY to page 0. */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1543_PAGE_ADDR, 0); + if (ret_val) + goto out; + + /* Turn on EEE advertisement. */ + ret_val = igb_read_xmdio_reg(hw, E1000_EEE_ADV_ADDR_I354, + E1000_EEE_ADV_DEV_I354, + &phy_data); + if (ret_val) + goto out; + + if (adv100M) + phy_data |= E1000_EEE_ADV_100_SUPPORTED; + else + phy_data &= ~E1000_EEE_ADV_100_SUPPORTED; + + if (adv1G) + phy_data |= E1000_EEE_ADV_1000_SUPPORTED; + else + phy_data &= ~E1000_EEE_ADV_1000_SUPPORTED; + + ret_val = igb_write_xmdio_reg(hw, E1000_EEE_ADV_ADDR_I354, + E1000_EEE_ADV_DEV_I354, + phy_data); + } else { + /* Turn off EEE advertisement. */ + ret_val = igb_read_xmdio_reg(hw, E1000_EEE_ADV_ADDR_I354, + E1000_EEE_ADV_DEV_I354, + &phy_data); + if (ret_val) + goto out; + + phy_data &= ~(E1000_EEE_ADV_100_SUPPORTED | + E1000_EEE_ADV_1000_SUPPORTED); + ret_val = igb_write_xmdio_reg(hw, E1000_EEE_ADV_ADDR_I354, + E1000_EEE_ADV_DEV_I354, + phy_data); + } + +out: + return ret_val; +} + +/** + * igb_get_eee_status_i354 - Get EEE status + * @hw: pointer to the HW structure + * @status: EEE status + * + * Get EEE status by guessing based on whether Tx or Rx LPI indications have + * been received. + **/ +s32 igb_get_eee_status_i354(struct e1000_hw *hw, bool *status) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val = 0; + u16 phy_data; + + /* Check if EEE is supported on this device. */ + if ((hw->phy.media_type != e1000_media_type_copper) || + ((phy->id != M88E1543_E_PHY_ID) && + (phy->id != M88E1512_E_PHY_ID))) + goto out; + + ret_val = igb_read_xmdio_reg(hw, E1000_PCS_STATUS_ADDR_I354, + E1000_PCS_STATUS_DEV_I354, + &phy_data); + if (ret_val) + goto out; + + *status = phy_data & (E1000_PCS_STATUS_TX_LPI_RCVD | + E1000_PCS_STATUS_RX_LPI_RCVD) ? true : false; + +out: + return ret_val; +} + +#ifdef CONFIG_IGB_HWMON +static const u8 e1000_emc_temp_data[4] = { + E1000_EMC_INTERNAL_DATA, + E1000_EMC_DIODE1_DATA, + E1000_EMC_DIODE2_DATA, + E1000_EMC_DIODE3_DATA +}; +static const u8 e1000_emc_therm_limit[4] = { + E1000_EMC_INTERNAL_THERM_LIMIT, + E1000_EMC_DIODE1_THERM_LIMIT, + E1000_EMC_DIODE2_THERM_LIMIT, + E1000_EMC_DIODE3_THERM_LIMIT +}; + +/** + * igb_get_thermal_sensor_data_generic - Gathers thermal sensor data + * @hw: pointer to hardware structure + * + * Updates the temperatures in mac.thermal_sensor_data + **/ +static s32 igb_get_thermal_sensor_data_generic(struct e1000_hw *hw) +{ + u16 ets_offset; + u16 ets_cfg; + u16 ets_sensor; + u8 num_sensors; + u8 sensor_index; + u8 sensor_location; + u8 i; + struct e1000_thermal_sensor_data *data = &hw->mac.thermal_sensor_data; + + if ((hw->mac.type != e1000_i350) || (hw->bus.func != 0)) + return E1000_NOT_IMPLEMENTED; + + data->sensor[0].temp = (rd32(E1000_THMJT) & 0xFF); + + /* Return the internal sensor only if ETS is unsupported */ + hw->nvm.ops.read(hw, NVM_ETS_CFG, 1, &ets_offset); + if ((ets_offset == 0x0000) || (ets_offset == 0xFFFF)) + return 0; + + hw->nvm.ops.read(hw, ets_offset, 1, &ets_cfg); + if (((ets_cfg & NVM_ETS_TYPE_MASK) >> NVM_ETS_TYPE_SHIFT) + != NVM_ETS_TYPE_EMC) + return E1000_NOT_IMPLEMENTED; + + num_sensors = (ets_cfg & NVM_ETS_NUM_SENSORS_MASK); + if (num_sensors > E1000_MAX_SENSORS) + num_sensors = E1000_MAX_SENSORS; + + for (i = 1; i < num_sensors; i++) { + hw->nvm.ops.read(hw, (ets_offset + i), 1, &ets_sensor); + sensor_index = ((ets_sensor & NVM_ETS_DATA_INDEX_MASK) >> + NVM_ETS_DATA_INDEX_SHIFT); + sensor_location = ((ets_sensor & NVM_ETS_DATA_LOC_MASK) >> + NVM_ETS_DATA_LOC_SHIFT); + + if (sensor_location != 0) + hw->phy.ops.read_i2c_byte(hw, + e1000_emc_temp_data[sensor_index], + E1000_I2C_THERMAL_SENSOR_ADDR, + &data->sensor[i].temp); + } + return 0; +} + +/** + * igb_init_thermal_sensor_thresh_generic - Sets thermal sensor thresholds + * @hw: pointer to hardware structure + * + * Sets the thermal sensor thresholds according to the NVM map + * and save off the threshold and location values into mac.thermal_sensor_data + **/ +static s32 igb_init_thermal_sensor_thresh_generic(struct e1000_hw *hw) +{ + u16 ets_offset; + u16 ets_cfg; + u16 ets_sensor; + u8 low_thresh_delta; + u8 num_sensors; + u8 sensor_index; + u8 sensor_location; + u8 therm_limit; + u8 i; + struct e1000_thermal_sensor_data *data = &hw->mac.thermal_sensor_data; + + if ((hw->mac.type != e1000_i350) || (hw->bus.func != 0)) + return E1000_NOT_IMPLEMENTED; + + memset(data, 0, sizeof(struct e1000_thermal_sensor_data)); + + data->sensor[0].location = 0x1; + data->sensor[0].caution_thresh = + (rd32(E1000_THHIGHTC) & 0xFF); + data->sensor[0].max_op_thresh = + (rd32(E1000_THLOWTC) & 0xFF); + + /* Return the internal sensor only if ETS is unsupported */ + hw->nvm.ops.read(hw, NVM_ETS_CFG, 1, &ets_offset); + if ((ets_offset == 0x0000) || (ets_offset == 0xFFFF)) + return 0; + + hw->nvm.ops.read(hw, ets_offset, 1, &ets_cfg); + if (((ets_cfg & NVM_ETS_TYPE_MASK) >> NVM_ETS_TYPE_SHIFT) + != NVM_ETS_TYPE_EMC) + return E1000_NOT_IMPLEMENTED; + + low_thresh_delta = ((ets_cfg & NVM_ETS_LTHRES_DELTA_MASK) >> + NVM_ETS_LTHRES_DELTA_SHIFT); + num_sensors = (ets_cfg & NVM_ETS_NUM_SENSORS_MASK); + + for (i = 1; i <= num_sensors; i++) { + hw->nvm.ops.read(hw, (ets_offset + i), 1, &ets_sensor); + sensor_index = ((ets_sensor & NVM_ETS_DATA_INDEX_MASK) >> + NVM_ETS_DATA_INDEX_SHIFT); + sensor_location = ((ets_sensor & NVM_ETS_DATA_LOC_MASK) >> + NVM_ETS_DATA_LOC_SHIFT); + therm_limit = ets_sensor & NVM_ETS_DATA_HTHRESH_MASK; + + hw->phy.ops.write_i2c_byte(hw, + e1000_emc_therm_limit[sensor_index], + E1000_I2C_THERMAL_SENSOR_ADDR, + therm_limit); + + if ((i < E1000_MAX_SENSORS) && (sensor_location != 0)) { + data->sensor[i].location = sensor_location; + data->sensor[i].caution_thresh = therm_limit; + data->sensor[i].max_op_thresh = therm_limit - + low_thresh_delta; + } + } + return 0; +} + +#endif +static struct e1000_mac_operations e1000_mac_ops_82575 = { + .init_hw = igb_init_hw_82575, + .check_for_link = igb_check_for_link_82575, + .rar_set = igb_rar_set, + .read_mac_addr = igb_read_mac_addr_82575, + .get_speed_and_duplex = igb_get_link_up_info_82575, +#ifdef CONFIG_IGB_HWMON + .get_thermal_sensor_data = igb_get_thermal_sensor_data_generic, + .init_thermal_sensor_thresh = igb_init_thermal_sensor_thresh_generic, +#endif +}; + +static const struct e1000_phy_operations e1000_phy_ops_82575 = { + .acquire = igb_acquire_phy_82575, + .get_cfg_done = igb_get_cfg_done_82575, + .release = igb_release_phy_82575, + .write_i2c_byte = igb_write_i2c_byte, + .read_i2c_byte = igb_read_i2c_byte, +}; + +static struct e1000_nvm_operations e1000_nvm_ops_82575 = { + .acquire = igb_acquire_nvm_82575, + .read = igb_read_nvm_eerd, + .release = igb_release_nvm_82575, + .write = igb_write_nvm_spi, +}; + +const struct e1000_info e1000_82575_info = { + .get_invariants = igb_get_invariants_82575, + .mac_ops = &e1000_mac_ops_82575, + .phy_ops = &e1000_phy_ops_82575, + .nvm_ops = &e1000_nvm_ops_82575, +}; + diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.h b/drivers/net/ethernet/intel/igb/e1000_82575.h new file mode 100644 index 0000000000..63ec253ac7 --- /dev/null +++ b/drivers/net/ethernet/intel/igb/e1000_82575.h @@ -0,0 +1,265 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ + +#ifndef _E1000_82575_H_ +#define _E1000_82575_H_ + +void igb_shutdown_serdes_link_82575(struct e1000_hw *hw); +void igb_power_up_serdes_link_82575(struct e1000_hw *hw); +void igb_power_down_phy_copper_82575(struct e1000_hw *hw); +void igb_rx_fifo_flush_82575(struct e1000_hw *hw); +s32 igb_read_i2c_byte(struct e1000_hw *hw, u8 byte_offset, u8 dev_addr, + u8 *data); +s32 igb_write_i2c_byte(struct e1000_hw *hw, u8 byte_offset, u8 dev_addr, + u8 data); + +#define ID_LED_DEFAULT_82575_SERDES ((ID_LED_DEF1_DEF2 << 12) | \ + (ID_LED_DEF1_DEF2 << 8) | \ + (ID_LED_DEF1_DEF2 << 4) | \ + (ID_LED_OFF1_ON2)) + +#define E1000_RAR_ENTRIES_82575 16 +#define E1000_RAR_ENTRIES_82576 24 +#define E1000_RAR_ENTRIES_82580 24 +#define E1000_RAR_ENTRIES_I350 32 + +#define E1000_SW_SYNCH_MB 0x00000100 +#define E1000_STAT_DEV_RST_SET 0x00100000 +#define E1000_CTRL_DEV_RST 0x20000000 + +/* SRRCTL bit definitions */ +#define E1000_SRRCTL_BSIZEPKT_SHIFT 10 /* Shift _right_ */ +#define E1000_SRRCTL_BSIZEHDRSIZE_SHIFT 2 /* Shift _left_ */ +#define E1000_SRRCTL_DESCTYPE_ADV_ONEBUF 0x02000000 +#define E1000_SRRCTL_DESCTYPE_HDR_SPLIT_ALWAYS 0x0A000000 +#define E1000_SRRCTL_DROP_EN 0x80000000 +#define E1000_SRRCTL_TIMESTAMP 0x40000000 + + +#define E1000_MRQC_ENABLE_RSS_MQ 0x00000002 +#define E1000_MRQC_ENABLE_VMDQ 0x00000003 +#define E1000_MRQC_RSS_FIELD_IPV4_UDP 0x00400000 +#define E1000_MRQC_ENABLE_VMDQ_RSS_MQ 0x00000005 +#define E1000_MRQC_RSS_FIELD_IPV6_UDP 0x00800000 +#define E1000_MRQC_RSS_FIELD_IPV6_UDP_EX 0x01000000 + +#define E1000_EICR_TX_QUEUE ( \ + E1000_EICR_TX_QUEUE0 | \ + E1000_EICR_TX_QUEUE1 | \ + E1000_EICR_TX_QUEUE2 | \ + E1000_EICR_TX_QUEUE3) + +#define E1000_EICR_RX_QUEUE ( \ + E1000_EICR_RX_QUEUE0 | \ + E1000_EICR_RX_QUEUE1 | \ + E1000_EICR_RX_QUEUE2 | \ + E1000_EICR_RX_QUEUE3) + +/* Immediate Interrupt Rx (A.K.A. Low Latency Interrupt) */ +#define E1000_IMIREXT_SIZE_BP 0x00001000 /* Packet size bypass */ +#define E1000_IMIREXT_CTRL_BP 0x00080000 /* Bypass check of ctrl bits */ + +/* Receive Descriptor - Advanced */ +union e1000_adv_rx_desc { + struct { + __le64 pkt_addr; /* Packet buffer address */ + __le64 hdr_addr; /* Header buffer address */ + } read; + struct { + struct { + struct { + __le16 pkt_info; /* RSS type, Packet type */ + __le16 hdr_info; /* Split Head, buf len */ + } lo_dword; + union { + __le32 rss; /* RSS Hash */ + struct { + __le16 ip_id; /* IP id */ + __le16 csum; /* Packet Checksum */ + } csum_ip; + } hi_dword; + } lower; + struct { + __le32 status_error; /* ext status/error */ + __le16 length; /* Packet length */ + __le16 vlan; /* VLAN tag */ + } upper; + } wb; /* writeback */ +}; + +#define E1000_RXDADV_HDRBUFLEN_MASK 0x7FE0 +#define E1000_RXDADV_HDRBUFLEN_SHIFT 5 +#define E1000_RXDADV_STAT_TS 0x10000 /* Pkt was time stamped */ +#define E1000_RXDADV_STAT_TSIP 0x08000 /* timestamp in packet */ + +/* Transmit Descriptor - Advanced */ +union e1000_adv_tx_desc { + struct { + __le64 buffer_addr; /* Address of descriptor's data buf */ + __le32 cmd_type_len; + __le32 olinfo_status; + } read; + struct { + __le64 rsvd; /* Reserved */ + __le32 nxtseq_seed; + __le32 status; + } wb; +}; + +/* Adv Transmit Descriptor Config Masks */ +#define E1000_ADVTXD_MAC_TSTAMP 0x00080000 /* IEEE1588 Timestamp packet */ +#define E1000_ADVTXD_DTYP_CTXT 0x00200000 /* Advanced Context Descriptor */ +#define E1000_ADVTXD_DTYP_DATA 0x00300000 /* Advanced Data Descriptor */ +#define E1000_ADVTXD_DCMD_EOP 0x01000000 /* End of Packet */ +#define E1000_ADVTXD_DCMD_IFCS 0x02000000 /* Insert FCS (Ethernet CRC) */ +#define E1000_ADVTXD_DCMD_RS 0x08000000 /* Report Status */ +#define E1000_ADVTXD_DCMD_DEXT 0x20000000 /* Descriptor extension (1=Adv) */ +#define E1000_ADVTXD_DCMD_VLE 0x40000000 /* VLAN pkt enable */ +#define E1000_ADVTXD_DCMD_TSE 0x80000000 /* TCP Seg enable */ +#define E1000_ADVTXD_PAYLEN_SHIFT 14 /* Adv desc PAYLEN shift */ + +/* Context descriptors */ +struct e1000_adv_tx_context_desc { + __le32 vlan_macip_lens; + __le32 seqnum_seed; + __le32 type_tucmd_mlhl; + __le32 mss_l4len_idx; +}; + +#define E1000_ADVTXD_MACLEN_SHIFT 9 /* Adv ctxt desc mac len shift */ +#define E1000_ADVTXD_TUCMD_L4T_UDP 0x00000000 /* L4 Packet TYPE of UDP */ +#define E1000_ADVTXD_TUCMD_IPV4 0x00000400 /* IP Packet Type: 1=IPv4 */ +#define E1000_ADVTXD_TUCMD_L4T_TCP 0x00000800 /* L4 Packet TYPE of TCP */ +#define E1000_ADVTXD_TUCMD_L4T_SCTP 0x00001000 /* L4 packet TYPE of SCTP */ +/* IPSec Encrypt Enable for ESP */ +#define E1000_ADVTXD_L4LEN_SHIFT 8 /* Adv ctxt L4LEN shift */ +#define E1000_ADVTXD_MSS_SHIFT 16 /* Adv ctxt MSS shift */ +/* Adv ctxt IPSec SA IDX mask */ +/* Adv ctxt IPSec ESP len mask */ + +/* Additional Transmit Descriptor Control definitions */ +#define E1000_TXDCTL_QUEUE_ENABLE 0x02000000 /* Enable specific Tx Queue */ +/* Tx Queue Arbitration Priority 0=low, 1=high */ + +/* Additional Receive Descriptor Control definitions */ +#define E1000_RXDCTL_QUEUE_ENABLE 0x02000000 /* Enable specific Rx Queue */ + +/* Direct Cache Access (DCA) definitions */ +#define E1000_DCA_CTRL_DCA_MODE_DISABLE 0x01 /* DCA Disable */ +#define E1000_DCA_CTRL_DCA_MODE_CB2 0x02 /* DCA Mode CB2 */ + +#define E1000_DCA_RXCTRL_CPUID_MASK 0x0000001F /* Rx CPUID Mask */ +#define E1000_DCA_RXCTRL_DESC_DCA_EN BIT(5) /* DCA Rx Desc enable */ +#define E1000_DCA_RXCTRL_HEAD_DCA_EN BIT(6) /* DCA Rx Desc header enable */ +#define E1000_DCA_RXCTRL_DATA_DCA_EN BIT(7) /* DCA Rx Desc payload enable */ +#define E1000_DCA_RXCTRL_DESC_RRO_EN BIT(9) /* DCA Rx rd Desc Relax Order */ + +#define E1000_DCA_TXCTRL_CPUID_MASK 0x0000001F /* Tx CPUID Mask */ +#define E1000_DCA_TXCTRL_DESC_DCA_EN BIT(5) /* DCA Tx Desc enable */ +#define E1000_DCA_TXCTRL_DESC_RRO_EN BIT(9) /* Tx rd Desc Relax Order */ +#define E1000_DCA_TXCTRL_TX_WB_RO_EN BIT(11) /* Tx Desc writeback RO bit */ +#define E1000_DCA_TXCTRL_DATA_RRO_EN BIT(13) /* Tx rd data Relax Order */ + +/* Additional DCA related definitions, note change in position of CPUID */ +#define E1000_DCA_TXCTRL_CPUID_MASK_82576 0xFF000000 /* Tx CPUID Mask */ +#define E1000_DCA_RXCTRL_CPUID_MASK_82576 0xFF000000 /* Rx CPUID Mask */ +#define E1000_DCA_TXCTRL_CPUID_SHIFT 24 /* Tx CPUID now in the last byte */ +#define E1000_DCA_RXCTRL_CPUID_SHIFT 24 /* Rx CPUID now in the last byte */ + +/* ETQF register bit definitions */ +#define E1000_ETQF_FILTER_ENABLE BIT(26) +#define E1000_ETQF_1588 BIT(30) +#define E1000_ETQF_IMM_INT BIT(29) +#define E1000_ETQF_QUEUE_ENABLE BIT(31) +#define E1000_ETQF_QUEUE_SHIFT 16 +#define E1000_ETQF_QUEUE_MASK 0x00070000 +#define E1000_ETQF_ETYPE_MASK 0x0000FFFF + +/* FTQF register bit definitions */ +#define E1000_FTQF_VF_BP 0x00008000 +#define E1000_FTQF_1588_TIME_STAMP 0x08000000 +#define E1000_FTQF_MASK 0xF0000000 +#define E1000_FTQF_MASK_PROTO_BP 0x10000000 +#define E1000_FTQF_MASK_SOURCE_PORT_BP 0x80000000 + +#define E1000_NVM_APME_82575 0x0400 +#define MAX_NUM_VFS 8 + +#define E1000_DTXSWC_MAC_SPOOF_MASK 0x000000FF /* Per VF MAC spoof control */ +#define E1000_DTXSWC_VLAN_SPOOF_MASK 0x0000FF00 /* Per VF VLAN spoof control */ +#define E1000_DTXSWC_LLE_MASK 0x00FF0000 /* Per VF Local LB enables */ +#define E1000_DTXSWC_VLAN_SPOOF_SHIFT 8 +#define E1000_DTXSWC_VMDQ_LOOPBACK_EN BIT(31) /* global VF LB enable */ + +/* Easy defines for setting default pool, would normally be left a zero */ +#define E1000_VT_CTL_DEFAULT_POOL_SHIFT 7 +#define E1000_VT_CTL_DEFAULT_POOL_MASK (0x7 << E1000_VT_CTL_DEFAULT_POOL_SHIFT) + +/* Other useful VMD_CTL register defines */ +#define E1000_VT_CTL_IGNORE_MAC BIT(28) +#define E1000_VT_CTL_DISABLE_DEF_POOL BIT(29) +#define E1000_VT_CTL_VM_REPL_EN BIT(30) + +/* Per VM Offload register setup */ +#define E1000_VMOLR_RLPML_MASK 0x00003FFF /* Long Packet Maximum Length mask */ +#define E1000_VMOLR_LPE 0x00010000 /* Accept Long packet */ +#define E1000_VMOLR_RSSE 0x00020000 /* Enable RSS */ +#define E1000_VMOLR_AUPE 0x01000000 /* Accept untagged packets */ +#define E1000_VMOLR_ROMPE 0x02000000 /* Accept overflow multicast */ +#define E1000_VMOLR_ROPE 0x04000000 /* Accept overflow unicast */ +#define E1000_VMOLR_BAM 0x08000000 /* Accept Broadcast packets */ +#define E1000_VMOLR_MPME 0x10000000 /* Multicast promiscuous mode */ +#define E1000_VMOLR_STRVLAN 0x40000000 /* Vlan stripping enable */ +#define E1000_VMOLR_STRCRC 0x80000000 /* CRC stripping enable */ + +#define E1000_DVMOLR_HIDEVLAN 0x20000000 /* Hide vlan enable */ +#define E1000_DVMOLR_STRVLAN 0x40000000 /* Vlan stripping enable */ +#define E1000_DVMOLR_STRCRC 0x80000000 /* CRC stripping enable */ + +#define E1000_VLVF_ARRAY_SIZE 32 +#define E1000_VLVF_VLANID_MASK 0x00000FFF +#define E1000_VLVF_POOLSEL_SHIFT 12 +#define E1000_VLVF_POOLSEL_MASK (0xFF << E1000_VLVF_POOLSEL_SHIFT) +#define E1000_VLVF_LVLAN 0x00100000 +#define E1000_VLVF_VLANID_ENABLE 0x80000000 + +#define E1000_VMVIR_VLANA_DEFAULT 0x40000000 /* Always use default VLAN */ +#define E1000_VMVIR_VLANA_NEVER 0x80000000 /* Never insert VLAN tag */ + +#define E1000_IOVCTL 0x05BBC +#define E1000_IOVCTL_REUSE_VFQ 0x00000001 + +#define E1000_RPLOLR_STRVLAN 0x40000000 +#define E1000_RPLOLR_STRCRC 0x80000000 + +#define E1000_DTXCTL_8023LL 0x0004 +#define E1000_DTXCTL_VLAN_ADDED 0x0008 +#define E1000_DTXCTL_OOS_ENABLE 0x0010 +#define E1000_DTXCTL_MDP_EN 0x0020 +#define E1000_DTXCTL_SPOOF_INT 0x0040 + +#define E1000_EEPROM_PCS_AUTONEG_DISABLE_BIT BIT(14) + +#define ALL_QUEUES 0xFFFF + +/* RX packet buffer size defines */ +#define E1000_RXPBS_SIZE_MASK_82576 0x0000007F +void igb_vmdq_set_anti_spoofing_pf(struct e1000_hw *, bool, int); +void igb_vmdq_set_loopback_pf(struct e1000_hw *, bool); +void igb_vmdq_set_replication_pf(struct e1000_hw *, bool); +u16 igb_rxpbs_adjust_82580(u32 data); +s32 igb_read_emi_reg(struct e1000_hw *, u16 addr, u16 *data); +s32 igb_set_eee_i350(struct e1000_hw *, bool adv1G, bool adv100M); +s32 igb_set_eee_i354(struct e1000_hw *, bool adv1G, bool adv100M); +s32 igb_get_eee_status_i354(struct e1000_hw *hw, bool *status); + +#define E1000_I2C_THERMAL_SENSOR_ADDR 0xF8 +#define E1000_EMC_INTERNAL_DATA 0x00 +#define E1000_EMC_INTERNAL_THERM_LIMIT 0x20 +#define E1000_EMC_DIODE1_DATA 0x01 +#define E1000_EMC_DIODE1_THERM_LIMIT 0x19 +#define E1000_EMC_DIODE2_DATA 0x23 +#define E1000_EMC_DIODE2_THERM_LIMIT 0x1A +#define E1000_EMC_DIODE3_DATA 0x2A +#define E1000_EMC_DIODE3_THERM_LIMIT 0x30 +#endif diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h new file mode 100644 index 0000000000..fa02892848 --- /dev/null +++ b/drivers/net/ethernet/intel/igb/e1000_defines.h @@ -0,0 +1,1075 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ + +#ifndef _E1000_DEFINES_H_ +#define _E1000_DEFINES_H_ + +/* Number of Transmit and Receive Descriptors must be a multiple of 8 */ +#define REQ_TX_DESCRIPTOR_MULTIPLE 8 +#define REQ_RX_DESCRIPTOR_MULTIPLE 8 + +/* Definitions for power management and wakeup registers */ +/* Wake Up Control */ +#define E1000_WUC_PME_EN 0x00000002 /* PME Enable */ + +/* Wake Up Filter Control */ +#define E1000_WUFC_LNKC 0x00000001 /* Link Status Change Wakeup Enable */ +#define E1000_WUFC_MAG 0x00000002 /* Magic Packet Wakeup Enable */ +#define E1000_WUFC_EX 0x00000004 /* Directed Exact Wakeup Enable */ +#define E1000_WUFC_MC 0x00000008 /* Directed Multicast Wakeup Enable */ +#define E1000_WUFC_BC 0x00000010 /* Broadcast Wakeup Enable */ + +/* Wake Up Status */ +#define E1000_WUS_EX 0x00000004 /* Directed Exact */ +#define E1000_WUS_ARPD 0x00000020 /* Directed ARP Request */ +#define E1000_WUS_IPV4 0x00000040 /* Directed IPv4 */ +#define E1000_WUS_IPV6 0x00000080 /* Directed IPv6 */ +#define E1000_WUS_NSD 0x00000400 /* Directed IPv6 Neighbor Solicitation */ + +/* Packet types that are enabled for wake packet delivery */ +#define WAKE_PKT_WUS ( \ + E1000_WUS_EX | \ + E1000_WUS_ARPD | \ + E1000_WUS_IPV4 | \ + E1000_WUS_IPV6 | \ + E1000_WUS_NSD) + +/* Wake Up Packet Length */ +#define E1000_WUPL_MASK 0x00000FFF + +/* Wake Up Packet Memory stores the first 128 bytes of the wake up packet */ +#define E1000_WUPM_BYTES 128 + +/* Extended Device Control */ +#define E1000_CTRL_EXT_SDP2_DATA 0x00000040 /* Value of SW Defineable Pin 2 */ +#define E1000_CTRL_EXT_SDP3_DATA 0x00000080 /* Value of SW Defineable Pin 3 */ +#define E1000_CTRL_EXT_SDP2_DIR 0x00000400 /* SDP2 Data direction */ +#define E1000_CTRL_EXT_SDP3_DIR 0x00000800 /* SDP3 Data direction */ + +/* Physical Func Reset Done Indication */ +#define E1000_CTRL_EXT_PFRSTD 0x00004000 +#define E1000_CTRL_EXT_SDLPE 0X00040000 /* SerDes Low Power Enable */ +#define E1000_CTRL_EXT_LINK_MODE_MASK 0x00C00000 +#define E1000_CTRL_EXT_LINK_MODE_PCIE_SERDES 0x00C00000 +#define E1000_CTRL_EXT_LINK_MODE_1000BASE_KX 0x00400000 +#define E1000_CTRL_EXT_LINK_MODE_SGMII 0x00800000 +#define E1000_CTRL_EXT_LINK_MODE_GMII 0x00000000 +#define E1000_CTRL_EXT_EIAME 0x01000000 +#define E1000_CTRL_EXT_IRCA 0x00000001 +/* Interrupt delay cancellation */ +/* Driver loaded bit for FW */ +#define E1000_CTRL_EXT_DRV_LOAD 0x10000000 +/* Interrupt acknowledge Auto-mask */ +/* Clear Interrupt timers after IMS clear */ +/* packet buffer parity error detection enabled */ +/* descriptor FIFO parity error detection enable */ +#define E1000_CTRL_EXT_PBA_CLR 0x80000000 /* PBA Clear */ +#define E1000_CTRL_EXT_PHYPDEN 0x00100000 +#define E1000_I2CCMD_REG_ADDR_SHIFT 16 +#define E1000_I2CCMD_PHY_ADDR_SHIFT 24 +#define E1000_I2CCMD_OPCODE_READ 0x08000000 +#define E1000_I2CCMD_OPCODE_WRITE 0x00000000 +#define E1000_I2CCMD_READY 0x20000000 +#define E1000_I2CCMD_ERROR 0x80000000 +#define E1000_I2CCMD_SFP_DATA_ADDR(a) (0x0000 + (a)) +#define E1000_I2CCMD_SFP_DIAG_ADDR(a) (0x0100 + (a)) +#define E1000_MAX_SGMII_PHY_REG_ADDR 255 +#define E1000_I2CCMD_PHY_TIMEOUT 200 +#define E1000_IVAR_VALID 0x80 +#define E1000_GPIE_NSICR 0x00000001 +#define E1000_GPIE_MSIX_MODE 0x00000010 +#define E1000_GPIE_EIAME 0x40000000 +#define E1000_GPIE_PBA 0x80000000 + +/* Receive Descriptor bit definitions */ +#define E1000_RXD_STAT_DD 0x01 /* Descriptor Done */ +#define E1000_RXD_STAT_EOP 0x02 /* End of Packet */ +#define E1000_RXD_STAT_IXSM 0x04 /* Ignore checksum */ +#define E1000_RXD_STAT_VP 0x08 /* IEEE VLAN Packet */ +#define E1000_RXD_STAT_UDPCS 0x10 /* UDP xsum calculated */ +#define E1000_RXD_STAT_TCPCS 0x20 /* TCP xsum calculated */ +#define E1000_RXD_STAT_TS 0x10000 /* Pkt was time stamped */ + +#define E1000_RXDEXT_STATERR_LB 0x00040000 +#define E1000_RXDEXT_STATERR_CE 0x01000000 +#define E1000_RXDEXT_STATERR_SE 0x02000000 +#define E1000_RXDEXT_STATERR_SEQ 0x04000000 +#define E1000_RXDEXT_STATERR_CXE 0x10000000 +#define E1000_RXDEXT_STATERR_TCPE 0x20000000 +#define E1000_RXDEXT_STATERR_IPE 0x40000000 +#define E1000_RXDEXT_STATERR_RXE 0x80000000 + +/* Same mask, but for extended and packet split descriptors */ +#define E1000_RXDEXT_ERR_FRAME_ERR_MASK ( \ + E1000_RXDEXT_STATERR_CE | \ + E1000_RXDEXT_STATERR_SE | \ + E1000_RXDEXT_STATERR_SEQ | \ + E1000_RXDEXT_STATERR_CXE | \ + E1000_RXDEXT_STATERR_RXE) + +#define E1000_MRQC_RSS_FIELD_IPV4_TCP 0x00010000 +#define E1000_MRQC_RSS_FIELD_IPV4 0x00020000 +#define E1000_MRQC_RSS_FIELD_IPV6_TCP_EX 0x00040000 +#define E1000_MRQC_RSS_FIELD_IPV6 0x00100000 +#define E1000_MRQC_RSS_FIELD_IPV6_TCP 0x00200000 + + +/* Management Control */ +#define E1000_MANC_SMBUS_EN 0x00000001 /* SMBus Enabled - RO */ +#define E1000_MANC_ASF_EN 0x00000002 /* ASF Enabled - RO */ +#define E1000_MANC_EN_BMC2OS 0x10000000 /* OSBMC is Enabled or not */ +/* Enable Neighbor Discovery Filtering */ +#define E1000_MANC_RCV_TCO_EN 0x00020000 /* Receive TCO Packets Enabled */ +#define E1000_MANC_BLK_PHY_RST_ON_IDE 0x00040000 /* Block phy resets */ +/* Enable MAC address filtering */ +#define E1000_MANC_EN_MAC_ADDR_FILTER 0x00100000 + +/* Receive Control */ +#define E1000_RCTL_EN 0x00000002 /* enable */ +#define E1000_RCTL_SBP 0x00000004 /* store bad packet */ +#define E1000_RCTL_UPE 0x00000008 /* unicast promiscuous enable */ +#define E1000_RCTL_MPE 0x00000010 /* multicast promiscuous enab */ +#define E1000_RCTL_LPE 0x00000020 /* long packet enable */ +#define E1000_RCTL_LBM_MAC 0x00000040 /* MAC loopback mode */ +#define E1000_RCTL_LBM_TCVR 0x000000C0 /* tcvr loopback mode */ +#define E1000_RCTL_RDMTS_HALF 0x00000000 /* rx desc min threshold size */ +#define E1000_RCTL_MO_SHIFT 12 /* multicast offset shift */ +#define E1000_RCTL_BAM 0x00008000 /* broadcast enable */ +#define E1000_RCTL_SZ_512 0x00020000 /* rx buffer size 512 */ +#define E1000_RCTL_SZ_256 0x00030000 /* rx buffer size 256 */ +#define E1000_RCTL_VFE 0x00040000 /* vlan filter enable */ +#define E1000_RCTL_CFIEN 0x00080000 /* canonical form enable */ +#define E1000_RCTL_DPF 0x00400000 /* Discard Pause Frames */ +#define E1000_RCTL_PMCF 0x00800000 /* pass MAC control frames */ +#define E1000_RCTL_SECRC 0x04000000 /* Strip Ethernet CRC */ + +/* Use byte values for the following shift parameters + * Usage: + * psrctl |= (((ROUNDUP(value0, 128) >> E1000_PSRCTL_BSIZE0_SHIFT) & + * E1000_PSRCTL_BSIZE0_MASK) | + * ((ROUNDUP(value1, 1024) >> E1000_PSRCTL_BSIZE1_SHIFT) & + * E1000_PSRCTL_BSIZE1_MASK) | + * ((ROUNDUP(value2, 1024) << E1000_PSRCTL_BSIZE2_SHIFT) & + * E1000_PSRCTL_BSIZE2_MASK) | + * ((ROUNDUP(value3, 1024) << E1000_PSRCTL_BSIZE3_SHIFT) |; + * E1000_PSRCTL_BSIZE3_MASK)) + * where value0 = [128..16256], default=256 + * value1 = [1024..64512], default=4096 + * value2 = [0..64512], default=4096 + * value3 = [0..64512], default=0 + */ + +#define E1000_PSRCTL_BSIZE0_MASK 0x0000007F +#define E1000_PSRCTL_BSIZE1_MASK 0x00003F00 +#define E1000_PSRCTL_BSIZE2_MASK 0x003F0000 +#define E1000_PSRCTL_BSIZE3_MASK 0x3F000000 + +#define E1000_PSRCTL_BSIZE0_SHIFT 7 /* Shift _right_ 7 */ +#define E1000_PSRCTL_BSIZE1_SHIFT 2 /* Shift _right_ 2 */ +#define E1000_PSRCTL_BSIZE2_SHIFT 6 /* Shift _left_ 6 */ +#define E1000_PSRCTL_BSIZE3_SHIFT 14 /* Shift _left_ 14 */ + +/* SWFW_SYNC Definitions */ +#define E1000_SWFW_EEP_SM 0x1 +#define E1000_SWFW_PHY0_SM 0x2 +#define E1000_SWFW_PHY1_SM 0x4 +#define E1000_SWFW_PHY2_SM 0x20 +#define E1000_SWFW_PHY3_SM 0x40 + +/* FACTPS Definitions */ +/* Device Control */ +#define E1000_CTRL_FD 0x00000001 /* Full duplex.0=half; 1=full */ +#define E1000_CTRL_GIO_MASTER_DISABLE 0x00000004 /*Blocks new Master requests */ +#define E1000_CTRL_LRST 0x00000008 /* Link reset. 0=normal,1=reset */ +#define E1000_CTRL_ASDE 0x00000020 /* Auto-speed detect enable */ +#define E1000_CTRL_SLU 0x00000040 /* Set link up (Force Link) */ +#define E1000_CTRL_ILOS 0x00000080 /* Invert Loss-Of Signal */ +#define E1000_CTRL_SPD_SEL 0x00000300 /* Speed Select Mask */ +#define E1000_CTRL_SPD_100 0x00000100 /* Force 100Mb */ +#define E1000_CTRL_SPD_1000 0x00000200 /* Force 1Gb */ +#define E1000_CTRL_FRCSPD 0x00000800 /* Force Speed */ +#define E1000_CTRL_FRCDPX 0x00001000 /* Force Duplex */ +/* Defined polarity of Dock/Undock indication in SDP[0] */ +/* Reset both PHY ports, through PHYRST_N pin */ +/* enable link status from external LINK_0 and LINK_1 pins */ +#define E1000_CTRL_SWDPIN0 0x00040000 /* SWDPIN 0 value */ +#define E1000_CTRL_SWDPIN1 0x00080000 /* SWDPIN 1 value */ +#define E1000_CTRL_ADVD3WUC 0x00100000 /* D3 WUC */ +#define E1000_CTRL_EN_PHY_PWR_MGMT 0x00200000 /* PHY PM enable */ +#define E1000_CTRL_SDP0_DIR 0x00400000 /* SDP0 Data direction */ +#define E1000_CTRL_SDP1_DIR 0x00800000 /* SDP1 Data direction */ +#define E1000_CTRL_RST 0x04000000 /* Global reset */ +#define E1000_CTRL_RFCE 0x08000000 /* Receive Flow Control enable */ +#define E1000_CTRL_TFCE 0x10000000 /* Transmit flow control enable */ +#define E1000_CTRL_VME 0x40000000 /* IEEE VLAN mode enable */ +#define E1000_CTRL_PHY_RST 0x80000000 /* PHY Reset */ +/* Initiate an interrupt to manageability engine */ +#define E1000_CTRL_I2C_ENA 0x02000000 /* I2C enable */ + +/* Bit definitions for the Management Data IO (MDIO) and Management Data + * Clock (MDC) pins in the Device Control Register. + */ + +#define E1000_CONNSW_ENRGSRC 0x4 +#define E1000_CONNSW_PHYSD 0x400 +#define E1000_CONNSW_PHY_PDN 0x800 +#define E1000_CONNSW_SERDESD 0x200 +#define E1000_CONNSW_AUTOSENSE_CONF 0x2 +#define E1000_CONNSW_AUTOSENSE_EN 0x1 +#define E1000_PCS_CFG_PCS_EN 8 +#define E1000_PCS_LCTL_FLV_LINK_UP 1 +#define E1000_PCS_LCTL_FSV_100 2 +#define E1000_PCS_LCTL_FSV_1000 4 +#define E1000_PCS_LCTL_FDV_FULL 8 +#define E1000_PCS_LCTL_FSD 0x10 +#define E1000_PCS_LCTL_FORCE_LINK 0x20 +#define E1000_PCS_LCTL_FORCE_FCTRL 0x80 +#define E1000_PCS_LCTL_AN_ENABLE 0x10000 +#define E1000_PCS_LCTL_AN_RESTART 0x20000 +#define E1000_PCS_LCTL_AN_TIMEOUT 0x40000 +#define E1000_ENABLE_SERDES_LOOPBACK 0x0410 + +#define E1000_PCS_LSTS_LINK_OK 1 +#define E1000_PCS_LSTS_SPEED_100 2 +#define E1000_PCS_LSTS_SPEED_1000 4 +#define E1000_PCS_LSTS_DUPLEX_FULL 8 +#define E1000_PCS_LSTS_SYNK_OK 0x10 + +/* Device Status */ +#define E1000_STATUS_FD 0x00000001 /* Full duplex.0=half,1=full */ +#define E1000_STATUS_LU 0x00000002 /* Link up.0=no,1=link */ +#define E1000_STATUS_FUNC_MASK 0x0000000C /* PCI Function Mask */ +#define E1000_STATUS_FUNC_SHIFT 2 +#define E1000_STATUS_FUNC_1 0x00000004 /* Function 1 */ +#define E1000_STATUS_TXOFF 0x00000010 /* transmission paused */ +#define E1000_STATUS_SPEED_100 0x00000040 /* Speed 100Mb/s */ +#define E1000_STATUS_SPEED_1000 0x00000080 /* Speed 1000Mb/s */ +/* Change in Dock/Undock state. Clear on write '0'. */ +/* Status of Master requests. */ +#define E1000_STATUS_GIO_MASTER_ENABLE 0x00080000 +/* BMC external code execution disabled */ + +#define E1000_STATUS_2P5_SKU 0x00001000 /* Val of 2.5GBE SKU strap */ +#define E1000_STATUS_2P5_SKU_OVER 0x00002000 /* Val of 2.5GBE SKU Over */ +/* Constants used to intrepret the masked PCI-X bus speed. */ + +#define SPEED_10 10 +#define SPEED_100 100 +#define SPEED_1000 1000 +#define SPEED_2500 2500 +#define HALF_DUPLEX 1 +#define FULL_DUPLEX 2 + + +#define ADVERTISE_10_HALF 0x0001 +#define ADVERTISE_10_FULL 0x0002 +#define ADVERTISE_100_HALF 0x0004 +#define ADVERTISE_100_FULL 0x0008 +#define ADVERTISE_1000_HALF 0x0010 /* Not used, just FYI */ +#define ADVERTISE_1000_FULL 0x0020 + +/* 1000/H is not supported, nor spec-compliant. */ +#define E1000_ALL_SPEED_DUPLEX (ADVERTISE_10_HALF | ADVERTISE_10_FULL | \ + ADVERTISE_100_HALF | ADVERTISE_100_FULL | \ + ADVERTISE_1000_FULL) +#define E1000_ALL_NOT_GIG (ADVERTISE_10_HALF | ADVERTISE_10_FULL | \ + ADVERTISE_100_HALF | ADVERTISE_100_FULL) +#define E1000_ALL_100_SPEED (ADVERTISE_100_HALF | ADVERTISE_100_FULL) +#define E1000_ALL_10_SPEED (ADVERTISE_10_HALF | ADVERTISE_10_FULL) +#define E1000_ALL_FULL_DUPLEX (ADVERTISE_10_FULL | ADVERTISE_100_FULL | \ + ADVERTISE_1000_FULL) +#define E1000_ALL_HALF_DUPLEX (ADVERTISE_10_HALF | ADVERTISE_100_HALF) + +#define AUTONEG_ADVERTISE_SPEED_DEFAULT E1000_ALL_SPEED_DUPLEX + +/* LED Control */ +#define E1000_LEDCTL_LED0_MODE_SHIFT 0 +#define E1000_LEDCTL_LED0_BLINK 0x00000080 +#define E1000_LEDCTL_LED0_MODE_MASK 0x0000000F +#define E1000_LEDCTL_LED0_IVRT 0x00000040 + +#define E1000_LEDCTL_MODE_LED_ON 0xE +#define E1000_LEDCTL_MODE_LED_OFF 0xF + +/* Transmit Descriptor bit definitions */ +#define E1000_TXD_POPTS_IXSM 0x01 /* Insert IP checksum */ +#define E1000_TXD_POPTS_TXSM 0x02 /* Insert TCP/UDP checksum */ +#define E1000_TXD_CMD_EOP 0x01000000 /* End of Packet */ +#define E1000_TXD_CMD_IFCS 0x02000000 /* Insert FCS (Ethernet CRC) */ +#define E1000_TXD_CMD_RS 0x08000000 /* Report Status */ +#define E1000_TXD_CMD_DEXT 0x20000000 /* Descriptor extension (0 = legacy) */ +#define E1000_TXD_STAT_DD 0x00000001 /* Descriptor Done */ +/* Extended desc bits for Linksec and timesync */ + +/* Transmit Control */ +#define E1000_TCTL_EN 0x00000002 /* enable tx */ +#define E1000_TCTL_PSP 0x00000008 /* pad short packets */ +#define E1000_TCTL_CT 0x00000ff0 /* collision threshold */ +#define E1000_TCTL_COLD 0x003ff000 /* collision distance */ +#define E1000_TCTL_RTLC 0x01000000 /* Re-transmit on late collision */ + +/* DMA Coalescing register fields */ +#define E1000_DMACR_DMACWT_MASK 0x00003FFF /* DMA Coal Watchdog Timer */ +#define E1000_DMACR_DMACTHR_MASK 0x00FF0000 /* DMA Coal Rx Threshold */ +#define E1000_DMACR_DMACTHR_SHIFT 16 +#define E1000_DMACR_DMAC_LX_MASK 0x30000000 /* Lx when no PCIe trans */ +#define E1000_DMACR_DMAC_LX_SHIFT 28 +#define E1000_DMACR_DMAC_EN 0x80000000 /* Enable DMA Coalescing */ +/* DMA Coalescing BMC-to-OS Watchdog Enable */ +#define E1000_DMACR_DC_BMC2OSW_EN 0x00008000 + +#define E1000_DMCTXTH_DMCTTHR_MASK 0x00000FFF /* DMA Coal Tx Threshold */ + +#define E1000_DMCTLX_TTLX_MASK 0x00000FFF /* Time to LX request */ + +#define E1000_DMCRTRH_UTRESH_MASK 0x0007FFFF /* Rx Traffic Rate Thresh */ +#define E1000_DMCRTRH_LRPRCW 0x80000000 /* Rx pkt rate curr window */ + +#define E1000_DMCCNT_CCOUNT_MASK 0x01FFFFFF /* DMA Coal Rx Current Cnt */ + +#define E1000_FCRTC_RTH_COAL_MASK 0x0003FFF0 /* FC Rx Thresh High val */ +#define E1000_FCRTC_RTH_COAL_SHIFT 4 +#define E1000_PCIEMISC_LX_DECISION 0x00000080 /* Lx power decision */ + +/* Timestamp in Rx buffer */ +#define E1000_RXPBS_CFG_TS_EN 0x80000000 + +#define I210_RXPBSIZE_DEFAULT 0x000000A2 /* RXPBSIZE default */ +#define I210_RXPBSIZE_MASK 0x0000003F +#define I210_RXPBSIZE_PB_30KB 0x0000001E +#define I210_RXPBSIZE_PB_32KB 0x00000020 +#define I210_TXPBSIZE_DEFAULT 0x04000014 /* TXPBSIZE default */ +#define I210_TXPBSIZE_MASK 0xC0FFFFFF +#define I210_TXPBSIZE_PB0_6KB (6 << 0) +#define I210_TXPBSIZE_PB1_6KB (6 << 6) +#define I210_TXPBSIZE_PB2_6KB (6 << 12) +#define I210_TXPBSIZE_PB3_6KB (6 << 18) + +#define I210_DTXMXPKTSZ_DEFAULT 0x00000098 + +#define I210_SR_QUEUES_NUM 2 + +/* SerDes Control */ +#define E1000_SCTL_DISABLE_SERDES_LOOPBACK 0x0400 + +/* Receive Checksum Control */ +#define E1000_RXCSUM_IPOFL 0x00000100 /* IPv4 checksum offload */ +#define E1000_RXCSUM_TUOFL 0x00000200 /* TCP / UDP checksum offload */ +#define E1000_RXCSUM_CRCOFL 0x00000800 /* CRC32 offload enable */ +#define E1000_RXCSUM_PCSD 0x00002000 /* packet checksum disabled */ + +/* Header split receive */ +#define E1000_RFCTL_IPV6_EX_DIS 0x00010000 +#define E1000_RFCTL_LEF 0x00040000 + +/* Collision related configuration parameters */ +#define E1000_COLLISION_THRESHOLD 15 +#define E1000_CT_SHIFT 4 +#define E1000_COLLISION_DISTANCE 63 +#define E1000_COLD_SHIFT 12 + +/* Ethertype field values */ +#define ETHERNET_IEEE_VLAN_TYPE 0x8100 /* 802.3ac packet */ + +/* As per the EAS the maximum supported size is 9.5KB (9728 bytes) */ +#define MAX_JUMBO_FRAME_SIZE 0x2600 +#define MAX_STD_JUMBO_FRAME_SIZE 9216 + +/* PBA constants */ +#define E1000_PBA_34K 0x0022 +#define E1000_PBA_64K 0x0040 /* 64KB */ + +/* SW Semaphore Register */ +#define E1000_SWSM_SMBI 0x00000001 /* Driver Semaphore bit */ +#define E1000_SWSM_SWESMBI 0x00000002 /* FW Semaphore bit */ + +/* Interrupt Cause Read */ +#define E1000_ICR_TXDW 0x00000001 /* Transmit desc written back */ +#define E1000_ICR_LSC 0x00000004 /* Link Status Change */ +#define E1000_ICR_RXSEQ 0x00000008 /* rx sequence error */ +#define E1000_ICR_RXDMT0 0x00000010 /* rx desc min. threshold (0) */ +#define E1000_ICR_RXT0 0x00000080 /* rx timer intr (ring 0) */ +#define E1000_ICR_VMMB 0x00000100 /* VM MB event */ +#define E1000_ICR_TS 0x00080000 /* Time Sync Interrupt */ +#define E1000_ICR_DRSTA 0x40000000 /* Device Reset Asserted */ +/* If this bit asserted, the driver should claim the interrupt */ +#define E1000_ICR_INT_ASSERTED 0x80000000 +/* LAN connected device generates an interrupt */ +#define E1000_ICR_DOUTSYNC 0x10000000 /* NIC DMA out of sync */ + +/* Extended Interrupt Cause Read */ +#define E1000_EICR_RX_QUEUE0 0x00000001 /* Rx Queue 0 Interrupt */ +#define E1000_EICR_RX_QUEUE1 0x00000002 /* Rx Queue 1 Interrupt */ +#define E1000_EICR_RX_QUEUE2 0x00000004 /* Rx Queue 2 Interrupt */ +#define E1000_EICR_RX_QUEUE3 0x00000008 /* Rx Queue 3 Interrupt */ +#define E1000_EICR_TX_QUEUE0 0x00000100 /* Tx Queue 0 Interrupt */ +#define E1000_EICR_TX_QUEUE1 0x00000200 /* Tx Queue 1 Interrupt */ +#define E1000_EICR_TX_QUEUE2 0x00000400 /* Tx Queue 2 Interrupt */ +#define E1000_EICR_TX_QUEUE3 0x00000800 /* Tx Queue 3 Interrupt */ +#define E1000_EICR_OTHER 0x80000000 /* Interrupt Cause Active */ +/* TCP Timer */ + +/* This defines the bits that are set in the Interrupt Mask + * Set/Read Register. Each bit is documented below: + * o RXT0 = Receiver Timer Interrupt (ring 0) + * o TXDW = Transmit Descriptor Written Back + * o RXDMT0 = Receive Descriptor Minimum Threshold hit (ring 0) + * o RXSEQ = Receive Sequence Error + * o LSC = Link Status Change + */ +#define IMS_ENABLE_MASK ( \ + E1000_IMS_RXT0 | \ + E1000_IMS_TXDW | \ + E1000_IMS_RXDMT0 | \ + E1000_IMS_RXSEQ | \ + E1000_IMS_LSC | \ + E1000_IMS_DOUTSYNC) + +/* Interrupt Mask Set */ +#define E1000_IMS_TXDW E1000_ICR_TXDW /* Transmit desc written back */ +#define E1000_IMS_LSC E1000_ICR_LSC /* Link Status Change */ +#define E1000_IMS_VMMB E1000_ICR_VMMB /* Mail box activity */ +#define E1000_IMS_TS E1000_ICR_TS /* Time Sync Interrupt */ +#define E1000_IMS_RXSEQ E1000_ICR_RXSEQ /* rx sequence error */ +#define E1000_IMS_RXDMT0 E1000_ICR_RXDMT0 /* rx desc min. threshold */ +#define E1000_IMS_RXT0 E1000_ICR_RXT0 /* rx timer intr */ +#define E1000_IMS_DRSTA E1000_ICR_DRSTA /* Device Reset Asserted */ +#define E1000_IMS_DOUTSYNC E1000_ICR_DOUTSYNC /* NIC DMA out of sync */ + +/* Extended Interrupt Mask Set */ +#define E1000_EIMS_OTHER E1000_EICR_OTHER /* Interrupt Cause Active */ + +/* Interrupt Cause Set */ +#define E1000_ICS_LSC E1000_ICR_LSC /* Link Status Change */ +#define E1000_ICS_RXDMT0 E1000_ICR_RXDMT0 /* rx desc min. threshold */ +#define E1000_ICS_DRSTA E1000_ICR_DRSTA /* Device Reset Aserted */ + +/* Extended Interrupt Cause Set */ +/* E1000_EITR_CNT_IGNR is only for 82576 and newer */ +#define E1000_EITR_CNT_IGNR 0x80000000 /* Don't reset counters on write */ + + +/* Transmit Descriptor Control */ +/* Enable the counting of descriptors still to be processed. */ + +/* Flow Control Constants */ +#define FLOW_CONTROL_ADDRESS_LOW 0x00C28001 +#define FLOW_CONTROL_ADDRESS_HIGH 0x00000100 +#define FLOW_CONTROL_TYPE 0x8808 + +/* Transmit Config Word */ +#define E1000_TXCW_ASM_DIR 0x00000100 /* TXCW astm pause direction */ +#define E1000_TXCW_PAUSE 0x00000080 /* TXCW sym pause request */ + +/* 802.1q VLAN Packet Size */ +#define VLAN_TAG_SIZE 4 /* 802.3ac tag (not DMA'd) */ +#define E1000_VLAN_FILTER_TBL_SIZE 128 /* VLAN Filter Table (4096 bits) */ + +/* Receive Address */ +/* Number of high/low register pairs in the RAR. The RAR (Receive Address + * Registers) holds the directed and multicast addresses that we monitor. + * Technically, we have 16 spots. However, we reserve one of these spots + * (RAR[15]) for our directed address used by controllers with + * manageability enabled, allowing us room for 15 multicast addresses. + */ +#define E1000_RAH_AV 0x80000000 /* Receive descriptor valid */ +#define E1000_RAH_ASEL_SRC_ADDR 0x00010000 +#define E1000_RAH_QSEL_ENABLE 0x10000000 +#define E1000_RAL_MAC_ADDR_LEN 4 +#define E1000_RAH_MAC_ADDR_LEN 2 +#define E1000_RAH_POOL_MASK 0x03FC0000 +#define E1000_RAH_POOL_1 0x00040000 + +/* Error Codes */ +#define E1000_ERR_NVM 1 +#define E1000_ERR_PHY 2 +#define E1000_ERR_CONFIG 3 +#define E1000_ERR_PARAM 4 +#define E1000_ERR_MAC_INIT 5 +#define E1000_ERR_RESET 9 +#define E1000_ERR_MASTER_REQUESTS_PENDING 10 +#define E1000_BLK_PHY_RESET 12 +#define E1000_ERR_SWFW_SYNC 13 +#define E1000_NOT_IMPLEMENTED 14 +#define E1000_ERR_MBX 15 +#define E1000_ERR_INVALID_ARGUMENT 16 +#define E1000_ERR_NO_SPACE 17 +#define E1000_ERR_NVM_PBA_SECTION 18 +#define E1000_ERR_INVM_VALUE_NOT_FOUND 19 +#define E1000_ERR_I2C 20 + +/* Loop limit on how long we wait for auto-negotiation to complete */ +#define COPPER_LINK_UP_LIMIT 10 +#define PHY_AUTO_NEG_LIMIT 45 +#define PHY_FORCE_LIMIT 20 +/* Number of 100 microseconds we wait for PCI Express master disable */ +#define MASTER_DISABLE_TIMEOUT 800 +/* Number of milliseconds we wait for PHY configuration done after MAC reset */ +#define PHY_CFG_TIMEOUT 100 +/* Number of 2 milliseconds we wait for acquiring MDIO ownership. */ +/* Number of milliseconds for NVM auto read done after MAC reset. */ +#define AUTO_READ_DONE_TIMEOUT 10 + +/* Flow Control */ +#define E1000_FCRTL_XONE 0x80000000 /* Enable XON frame transmission */ + +#define E1000_TSYNCTXCTL_VALID 0x00000001 /* tx timestamp valid */ +#define E1000_TSYNCTXCTL_ENABLED 0x00000010 /* enable tx timestampping */ + +#define E1000_TSYNCRXCTL_VALID 0x00000001 /* rx timestamp valid */ +#define E1000_TSYNCRXCTL_TYPE_MASK 0x0000000E /* rx type mask */ +#define E1000_TSYNCRXCTL_TYPE_L2_V2 0x00 +#define E1000_TSYNCRXCTL_TYPE_L4_V1 0x02 +#define E1000_TSYNCRXCTL_TYPE_L2_L4_V2 0x04 +#define E1000_TSYNCRXCTL_TYPE_ALL 0x08 +#define E1000_TSYNCRXCTL_TYPE_EVENT_V2 0x0A +#define E1000_TSYNCRXCTL_ENABLED 0x00000010 /* enable rx timestampping */ + +#define E1000_TSYNCRXCFG_PTP_V1_CTRLT_MASK 0x000000FF +#define E1000_TSYNCRXCFG_PTP_V1_SYNC_MESSAGE 0x00 +#define E1000_TSYNCRXCFG_PTP_V1_DELAY_REQ_MESSAGE 0x01 +#define E1000_TSYNCRXCFG_PTP_V1_FOLLOWUP_MESSAGE 0x02 +#define E1000_TSYNCRXCFG_PTP_V1_DELAY_RESP_MESSAGE 0x03 +#define E1000_TSYNCRXCFG_PTP_V1_MANAGEMENT_MESSAGE 0x04 + +#define E1000_TSYNCRXCFG_PTP_V2_MSGID_MASK 0x00000F00 +#define E1000_TSYNCRXCFG_PTP_V2_SYNC_MESSAGE 0x0000 +#define E1000_TSYNCRXCFG_PTP_V2_DELAY_REQ_MESSAGE 0x0100 +#define E1000_TSYNCRXCFG_PTP_V2_PATH_DELAY_REQ_MESSAGE 0x0200 +#define E1000_TSYNCRXCFG_PTP_V2_PATH_DELAY_RESP_MESSAGE 0x0300 +#define E1000_TSYNCRXCFG_PTP_V2_FOLLOWUP_MESSAGE 0x0800 +#define E1000_TSYNCRXCFG_PTP_V2_DELAY_RESP_MESSAGE 0x0900 +#define E1000_TSYNCRXCFG_PTP_V2_PATH_DELAY_FOLLOWUP_MESSAGE 0x0A00 +#define E1000_TSYNCRXCFG_PTP_V2_ANNOUNCE_MESSAGE 0x0B00 +#define E1000_TSYNCRXCFG_PTP_V2_SIGNALLING_MESSAGE 0x0C00 +#define E1000_TSYNCRXCFG_PTP_V2_MANAGEMENT_MESSAGE 0x0D00 + +#define E1000_TIMINCA_16NS_SHIFT 24 + +/* Time Sync Interrupt Cause/Mask Register Bits */ + +#define TSINTR_SYS_WRAP BIT(0) /* SYSTIM Wrap around. */ +#define TSINTR_TXTS BIT(1) /* Transmit Timestamp. */ +#define TSINTR_RXTS BIT(2) /* Receive Timestamp. */ +#define TSINTR_TT0 BIT(3) /* Target Time 0 Trigger. */ +#define TSINTR_TT1 BIT(4) /* Target Time 1 Trigger. */ +#define TSINTR_AUTT0 BIT(5) /* Auxiliary Timestamp 0 Taken. */ +#define TSINTR_AUTT1 BIT(6) /* Auxiliary Timestamp 1 Taken. */ +#define TSINTR_TADJ BIT(7) /* Time Adjust Done. */ + +#define TSYNC_INTERRUPTS TSINTR_TXTS +#define E1000_TSICR_TXTS TSINTR_TXTS + +/* TSAUXC Configuration Bits */ +#define TSAUXC_EN_TT0 BIT(0) /* Enable target time 0. */ +#define TSAUXC_EN_TT1 BIT(1) /* Enable target time 1. */ +#define TSAUXC_EN_CLK0 BIT(2) /* Enable Configurable Frequency Clock 0. */ +#define TSAUXC_SAMP_AUT0 BIT(3) /* Latch SYSTIML/H into AUXSTMPL/0. */ +#define TSAUXC_ST0 BIT(4) /* Start Clock 0 Toggle on Target Time 0. */ +#define TSAUXC_EN_CLK1 BIT(5) /* Enable Configurable Frequency Clock 1. */ +#define TSAUXC_SAMP_AUT1 BIT(6) /* Latch SYSTIML/H into AUXSTMPL/1. */ +#define TSAUXC_ST1 BIT(7) /* Start Clock 1 Toggle on Target Time 1. */ +#define TSAUXC_EN_TS0 BIT(8) /* Enable hardware timestamp 0. */ +#define TSAUXC_AUTT0 BIT(9) /* Auxiliary Timestamp Taken. */ +#define TSAUXC_EN_TS1 BIT(10) /* Enable hardware timestamp 0. */ +#define TSAUXC_AUTT1 BIT(11) /* Auxiliary Timestamp Taken. */ +#define TSAUXC_PLSG BIT(17) /* Generate a pulse. */ +#define TSAUXC_DISABLE BIT(31) /* Disable SYSTIM Count Operation. */ + +/* SDP Configuration Bits */ +#define AUX0_SEL_SDP0 (0u << 0) /* Assign SDP0 to auxiliary time stamp 0. */ +#define AUX0_SEL_SDP1 (1u << 0) /* Assign SDP1 to auxiliary time stamp 0. */ +#define AUX0_SEL_SDP2 (2u << 0) /* Assign SDP2 to auxiliary time stamp 0. */ +#define AUX0_SEL_SDP3 (3u << 0) /* Assign SDP3 to auxiliary time stamp 0. */ +#define AUX0_TS_SDP_EN (1u << 2) /* Enable auxiliary time stamp trigger 0. */ +#define AUX1_SEL_SDP0 (0u << 3) /* Assign SDP0 to auxiliary time stamp 1. */ +#define AUX1_SEL_SDP1 (1u << 3) /* Assign SDP1 to auxiliary time stamp 1. */ +#define AUX1_SEL_SDP2 (2u << 3) /* Assign SDP2 to auxiliary time stamp 1. */ +#define AUX1_SEL_SDP3 (3u << 3) /* Assign SDP3 to auxiliary time stamp 1. */ +#define AUX1_TS_SDP_EN (1u << 5) /* Enable auxiliary time stamp trigger 1. */ +#define TS_SDP0_SEL_TT0 (0u << 6) /* Target time 0 is output on SDP0. */ +#define TS_SDP0_SEL_TT1 (1u << 6) /* Target time 1 is output on SDP0. */ +#define TS_SDP0_SEL_FC0 (2u << 6) /* Freq clock 0 is output on SDP0. */ +#define TS_SDP0_SEL_FC1 (3u << 6) /* Freq clock 1 is output on SDP0. */ +#define TS_SDP0_EN (1u << 8) /* SDP0 is assigned to Tsync. */ +#define TS_SDP1_SEL_TT0 (0u << 9) /* Target time 0 is output on SDP1. */ +#define TS_SDP1_SEL_TT1 (1u << 9) /* Target time 1 is output on SDP1. */ +#define TS_SDP1_SEL_FC0 (2u << 9) /* Freq clock 0 is output on SDP1. */ +#define TS_SDP1_SEL_FC1 (3u << 9) /* Freq clock 1 is output on SDP1. */ +#define TS_SDP1_EN (1u << 11) /* SDP1 is assigned to Tsync. */ +#define TS_SDP2_SEL_TT0 (0u << 12) /* Target time 0 is output on SDP2. */ +#define TS_SDP2_SEL_TT1 (1u << 12) /* Target time 1 is output on SDP2. */ +#define TS_SDP2_SEL_FC0 (2u << 12) /* Freq clock 0 is output on SDP2. */ +#define TS_SDP2_SEL_FC1 (3u << 12) /* Freq clock 1 is output on SDP2. */ +#define TS_SDP2_EN (1u << 14) /* SDP2 is assigned to Tsync. */ +#define TS_SDP3_SEL_TT0 (0u << 15) /* Target time 0 is output on SDP3. */ +#define TS_SDP3_SEL_TT1 (1u << 15) /* Target time 1 is output on SDP3. */ +#define TS_SDP3_SEL_FC0 (2u << 15) /* Freq clock 0 is output on SDP3. */ +#define TS_SDP3_SEL_FC1 (3u << 15) /* Freq clock 1 is output on SDP3. */ +#define TS_SDP3_EN (1u << 17) /* SDP3 is assigned to Tsync. */ + +#define E1000_MDICNFG_EXT_MDIO 0x80000000 /* MDI ext/int destination */ +#define E1000_MDICNFG_COM_MDIO 0x40000000 /* MDI shared w/ lan 0 */ +#define E1000_MDICNFG_PHY_MASK 0x03E00000 +#define E1000_MDICNFG_PHY_SHIFT 21 + +#define E1000_MEDIA_PORT_COPPER 1 +#define E1000_MEDIA_PORT_OTHER 2 +#define E1000_M88E1112_AUTO_COPPER_SGMII 0x2 +#define E1000_M88E1112_AUTO_COPPER_BASEX 0x3 +#define E1000_M88E1112_STATUS_LINK 0x0004 /* Interface Link Bit */ +#define E1000_M88E1112_MAC_CTRL_1 0x10 +#define E1000_M88E1112_MAC_CTRL_1_MODE_MASK 0x0380 /* Mode Select */ +#define E1000_M88E1112_MAC_CTRL_1_MODE_SHIFT 7 +#define E1000_M88E1112_PAGE_ADDR 0x16 +#define E1000_M88E1112_STATUS 0x01 +#define E1000_M88E1512_CFG_REG_1 0x0010 +#define E1000_M88E1512_CFG_REG_2 0x0011 +#define E1000_M88E1512_CFG_REG_3 0x0007 +#define E1000_M88E1512_MODE 0x0014 + +/* PCI Express Control */ +#define E1000_GCR_CMPL_TMOUT_MASK 0x0000F000 +#define E1000_GCR_CMPL_TMOUT_10ms 0x00001000 +#define E1000_GCR_CMPL_TMOUT_RESEND 0x00010000 +#define E1000_GCR_CAP_VER2 0x00040000 + +/* mPHY Address Control and Data Registers */ +#define E1000_MPHY_ADDR_CTL 0x0024 /* mPHY Address Control Register */ +#define E1000_MPHY_ADDR_CTL_OFFSET_MASK 0xFFFF0000 +#define E1000_MPHY_DATA 0x0E10 /* mPHY Data Register */ + +/* mPHY PCS CLK Register */ +#define E1000_MPHY_PCS_CLK_REG_OFFSET 0x0004 /* mPHY PCS CLK AFE CSR Offset */ +/* mPHY Near End Digital Loopback Override Bit */ +#define E1000_MPHY_PCS_CLK_REG_DIGINELBEN 0x10 + +#define E1000_PCS_LCTL_FORCE_FCTRL 0x80 +#define E1000_PCS_LSTS_AN_COMPLETE 0x10000 + +/* PHY Control Register */ +#define MII_CR_FULL_DUPLEX 0x0100 /* FDX =1, half duplex =0 */ +#define MII_CR_RESTART_AUTO_NEG 0x0200 /* Restart auto negotiation */ +#define MII_CR_POWER_DOWN 0x0800 /* Power down */ +#define MII_CR_AUTO_NEG_EN 0x1000 /* Auto Neg Enable */ +#define MII_CR_LOOPBACK 0x4000 /* 0 = normal, 1 = loopback */ +#define MII_CR_RESET 0x8000 /* 0 = normal, 1 = PHY reset */ +#define MII_CR_SPEED_1000 0x0040 +#define MII_CR_SPEED_100 0x2000 +#define MII_CR_SPEED_10 0x0000 + +/* PHY Status Register */ +#define MII_SR_LINK_STATUS 0x0004 /* Link Status 1 = link */ +#define MII_SR_AUTONEG_COMPLETE 0x0020 /* Auto Neg Complete */ + +/* Autoneg Advertisement Register */ +#define NWAY_AR_10T_HD_CAPS 0x0020 /* 10T Half Duplex Capable */ +#define NWAY_AR_10T_FD_CAPS 0x0040 /* 10T Full Duplex Capable */ +#define NWAY_AR_100TX_HD_CAPS 0x0080 /* 100TX Half Duplex Capable */ +#define NWAY_AR_100TX_FD_CAPS 0x0100 /* 100TX Full Duplex Capable */ +#define NWAY_AR_PAUSE 0x0400 /* Pause operation desired */ +#define NWAY_AR_ASM_DIR 0x0800 /* Asymmetric Pause Direction bit */ + +/* Link Partner Ability Register (Base Page) */ +#define NWAY_LPAR_PAUSE 0x0400 /* LP Pause operation desired */ +#define NWAY_LPAR_ASM_DIR 0x0800 /* LP Asymmetric Pause Direction bit */ + +/* Autoneg Expansion Register */ + +/* 1000BASE-T Control Register */ +#define CR_1000T_HD_CAPS 0x0100 /* Advertise 1000T HD capability */ +#define CR_1000T_FD_CAPS 0x0200 /* Advertise 1000T FD capability */ +#define CR_1000T_MS_VALUE 0x0800 /* 1=Configure PHY as Master */ + /* 0=Configure PHY as Slave */ +#define CR_1000T_MS_ENABLE 0x1000 /* 1=Master/Slave manual config value */ + /* 0=Automatic Master/Slave config */ + +/* 1000BASE-T Status Register */ +#define SR_1000T_REMOTE_RX_STATUS 0x1000 /* Remote receiver OK */ +#define SR_1000T_LOCAL_RX_STATUS 0x2000 /* Local receiver OK */ + + +/* PHY 1000 MII Register/Bit Definitions */ +/* PHY Registers defined by IEEE */ +#define PHY_CONTROL 0x00 /* Control Register */ +#define PHY_STATUS 0x01 /* Status Register */ +#define PHY_ID1 0x02 /* Phy Id Reg (word 1) */ +#define PHY_ID2 0x03 /* Phy Id Reg (word 2) */ +#define PHY_AUTONEG_ADV 0x04 /* Autoneg Advertisement */ +#define PHY_LP_ABILITY 0x05 /* Link Partner Ability (Base Page) */ +#define PHY_1000T_CTRL 0x09 /* 1000Base-T Control Reg */ +#define PHY_1000T_STATUS 0x0A /* 1000Base-T Status Reg */ + +/* NVM Control */ +#define E1000_EECD_SK 0x00000001 /* NVM Clock */ +#define E1000_EECD_CS 0x00000002 /* NVM Chip Select */ +#define E1000_EECD_DI 0x00000004 /* NVM Data In */ +#define E1000_EECD_DO 0x00000008 /* NVM Data Out */ +#define E1000_EECD_REQ 0x00000040 /* NVM Access Request */ +#define E1000_EECD_GNT 0x00000080 /* NVM Access Grant */ +#define E1000_EECD_PRES 0x00000100 /* NVM Present */ +/* NVM Addressing bits based on type 0=small, 1=large */ +#define E1000_EECD_ADDR_BITS 0x00000400 +#define E1000_NVM_GRANT_ATTEMPTS 1000 /* NVM # attempts to gain grant */ +#define E1000_EECD_AUTO_RD 0x00000200 /* NVM Auto Read done */ +#define E1000_EECD_SIZE_EX_MASK 0x00007800 /* NVM Size */ +#define E1000_EECD_SIZE_EX_SHIFT 11 +#define E1000_EECD_FLUPD_I210 0x00800000 /* Update FLASH */ +#define E1000_EECD_FLUDONE_I210 0x04000000 /* Update FLASH done*/ +#define E1000_EECD_FLASH_DETECTED_I210 0x00080000 /* FLASH detected */ +#define E1000_FLUDONE_ATTEMPTS 20000 +#define E1000_EERD_EEWR_MAX_COUNT 512 /* buffered EEPROM words rw */ +#define E1000_I210_FIFO_SEL_RX 0x00 +#define E1000_I210_FIFO_SEL_TX_QAV(_i) (0x02 + (_i)) +#define E1000_I210_FIFO_SEL_TX_LEGACY E1000_I210_FIFO_SEL_TX_QAV(0) +#define E1000_I210_FIFO_SEL_BMC2OS_TX 0x06 +#define E1000_I210_FIFO_SEL_BMC2OS_RX 0x01 +#define E1000_I210_FLASH_SECTOR_SIZE 0x1000 /* 4KB FLASH sector unit size */ +/* Secure FLASH mode requires removing MSb */ +#define E1000_I210_FW_PTR_MASK 0x7FFF +/* Firmware code revision field word offset*/ +#define E1000_I210_FW_VER_OFFSET 328 +#define E1000_EECD_FLUPD_I210 0x00800000 /* Update FLASH */ +#define E1000_EECD_FLUDONE_I210 0x04000000 /* Update FLASH done*/ +#define E1000_FLUDONE_ATTEMPTS 20000 +#define E1000_EERD_EEWR_MAX_COUNT 512 /* buffered EEPROM words rw */ +#define E1000_I210_FIFO_SEL_RX 0x00 +#define E1000_I210_FIFO_SEL_TX_QAV(_i) (0x02 + (_i)) +#define E1000_I210_FIFO_SEL_TX_LEGACY E1000_I210_FIFO_SEL_TX_QAV(0) +#define E1000_I210_FIFO_SEL_BMC2OS_TX 0x06 +#define E1000_I210_FIFO_SEL_BMC2OS_RX 0x01 + + +/* Offset to data in NVM read/write registers */ +#define E1000_NVM_RW_REG_DATA 16 +#define E1000_NVM_RW_REG_DONE 2 /* Offset to READ/WRITE done bit */ +#define E1000_NVM_RW_REG_START 1 /* Start operation */ +#define E1000_NVM_RW_ADDR_SHIFT 2 /* Shift to the address bits */ +#define E1000_NVM_POLL_READ 0 /* Flag for polling for read complete */ + +/* NVM Word Offsets */ +#define NVM_COMPAT 0x0003 +#define NVM_ID_LED_SETTINGS 0x0004 /* SERDES output amplitude */ +#define NVM_VERSION 0x0005 +#define NVM_INIT_CONTROL2_REG 0x000F +#define NVM_INIT_CONTROL3_PORT_B 0x0014 +#define NVM_INIT_CONTROL3_PORT_A 0x0024 +#define NVM_ALT_MAC_ADDR_PTR 0x0037 +#define NVM_CHECKSUM_REG 0x003F +#define NVM_COMPATIBILITY_REG_3 0x0003 +#define NVM_COMPATIBILITY_BIT_MASK 0x8000 +#define NVM_MAC_ADDR 0x0000 +#define NVM_SUB_DEV_ID 0x000B +#define NVM_SUB_VEN_ID 0x000C +#define NVM_DEV_ID 0x000D +#define NVM_VEN_ID 0x000E +#define NVM_INIT_CTRL_2 0x000F +#define NVM_INIT_CTRL_4 0x0013 +#define NVM_LED_1_CFG 0x001C +#define NVM_LED_0_2_CFG 0x001F +#define NVM_ETRACK_WORD 0x0042 +#define NVM_ETRACK_HIWORD 0x0043 +#define NVM_COMB_VER_OFF 0x0083 +#define NVM_COMB_VER_PTR 0x003d + +/* NVM version defines */ +#define NVM_MAJOR_MASK 0xF000 +#define NVM_MINOR_MASK 0x0FF0 +#define NVM_IMAGE_ID_MASK 0x000F +#define NVM_COMB_VER_MASK 0x00FF +#define NVM_MAJOR_SHIFT 12 +#define NVM_MINOR_SHIFT 4 +#define NVM_COMB_VER_SHFT 8 +#define NVM_VER_INVALID 0xFFFF +#define NVM_ETRACK_SHIFT 16 +#define NVM_ETRACK_VALID 0x8000 +#define NVM_NEW_DEC_MASK 0x0F00 +#define NVM_HEX_CONV 16 +#define NVM_HEX_TENS 10 + +#define NVM_ETS_CFG 0x003E +#define NVM_ETS_LTHRES_DELTA_MASK 0x07C0 +#define NVM_ETS_LTHRES_DELTA_SHIFT 6 +#define NVM_ETS_TYPE_MASK 0x0038 +#define NVM_ETS_TYPE_SHIFT 3 +#define NVM_ETS_TYPE_EMC 0x000 +#define NVM_ETS_NUM_SENSORS_MASK 0x0007 +#define NVM_ETS_DATA_LOC_MASK 0x3C00 +#define NVM_ETS_DATA_LOC_SHIFT 10 +#define NVM_ETS_DATA_INDEX_MASK 0x0300 +#define NVM_ETS_DATA_INDEX_SHIFT 8 +#define NVM_ETS_DATA_HTHRESH_MASK 0x00FF + +#define E1000_NVM_CFG_DONE_PORT_0 0x040000 /* MNG config cycle done */ +#define E1000_NVM_CFG_DONE_PORT_1 0x080000 /* ...for second port */ +#define E1000_NVM_CFG_DONE_PORT_2 0x100000 /* ...for third port */ +#define E1000_NVM_CFG_DONE_PORT_3 0x200000 /* ...for fourth port */ + +#define NVM_82580_LAN_FUNC_OFFSET(a) (a ? (0x40 + (0x40 * a)) : 0) + +/* Mask bits for fields in Word 0x24 of the NVM */ +#define NVM_WORD24_COM_MDIO 0x0008 /* MDIO interface shared */ +#define NVM_WORD24_EXT_MDIO 0x0004 /* MDIO accesses routed external */ + +/* Mask bits for fields in Word 0x0f of the NVM */ +#define NVM_WORD0F_PAUSE_MASK 0x3000 +#define NVM_WORD0F_ASM_DIR 0x2000 + +/* Mask bits for fields in Word 0x1a of the NVM */ + +/* length of string needed to store part num */ +#define E1000_PBANUM_LENGTH 11 + +/* For checksumming, the sum of all words in the NVM should equal 0xBABA. */ +#define NVM_SUM 0xBABA + +#define NVM_PBA_OFFSET_0 8 +#define NVM_PBA_OFFSET_1 9 +#define NVM_RESERVED_WORD 0xFFFF +#define NVM_PBA_PTR_GUARD 0xFAFA +#define NVM_WORD_SIZE_BASE_SHIFT 6 + +/* NVM Commands - Microwire */ + +/* NVM Commands - SPI */ +#define NVM_MAX_RETRY_SPI 5000 /* Max wait of 5ms, for RDY signal */ +#define NVM_WRITE_OPCODE_SPI 0x02 /* NVM write opcode */ +#define NVM_READ_OPCODE_SPI 0x03 /* NVM read opcode */ +#define NVM_A8_OPCODE_SPI 0x08 /* opcode bit-3 = address bit-8 */ +#define NVM_WREN_OPCODE_SPI 0x06 /* NVM set Write Enable latch */ +#define NVM_RDSR_OPCODE_SPI 0x05 /* NVM read Status register */ + +/* SPI NVM Status Register */ +#define NVM_STATUS_RDY_SPI 0x01 + +/* Word definitions for ID LED Settings */ +#define ID_LED_RESERVED_0000 0x0000 +#define ID_LED_RESERVED_FFFF 0xFFFF +#define ID_LED_DEFAULT ((ID_LED_OFF1_ON2 << 12) | \ + (ID_LED_OFF1_OFF2 << 8) | \ + (ID_LED_DEF1_DEF2 << 4) | \ + (ID_LED_DEF1_DEF2)) +#define ID_LED_DEF1_DEF2 0x1 +#define ID_LED_DEF1_ON2 0x2 +#define ID_LED_DEF1_OFF2 0x3 +#define ID_LED_ON1_DEF2 0x4 +#define ID_LED_ON1_ON2 0x5 +#define ID_LED_ON1_OFF2 0x6 +#define ID_LED_OFF1_DEF2 0x7 +#define ID_LED_OFF1_ON2 0x8 +#define ID_LED_OFF1_OFF2 0x9 + +#define IGP_ACTIVITY_LED_MASK 0xFFFFF0FF +#define IGP_ACTIVITY_LED_ENABLE 0x0300 +#define IGP_LED3_MODE 0x07000000 + +/* PCI/PCI-X/PCI-EX Config space */ +#define PCIE_DEVICE_CONTROL2 0x28 +#define PCIE_DEVICE_CONTROL2_16ms 0x0005 + +#define PHY_REVISION_MASK 0xFFFFFFF0 +#define MAX_PHY_REG_ADDRESS 0x1F /* 5 bit address bus (0-0x1F) */ +#define MAX_PHY_MULTI_PAGE_REG 0xF + +/* Bit definitions for valid PHY IDs. */ +/* I = Integrated + * E = External + */ +#define M88E1111_I_PHY_ID 0x01410CC0 +#define M88E1112_E_PHY_ID 0x01410C90 +#define I347AT4_E_PHY_ID 0x01410DC0 +#define IGP03E1000_E_PHY_ID 0x02A80390 +#define I82580_I_PHY_ID 0x015403A0 +#define I350_I_PHY_ID 0x015403B0 +#define M88_VENDOR 0x0141 +#define I210_I_PHY_ID 0x01410C00 +#define M88E1543_E_PHY_ID 0x01410EA0 +#define M88E1512_E_PHY_ID 0x01410DD0 +#define BCM54616_E_PHY_ID 0x03625D10 + +/* M88E1000 Specific Registers */ +#define M88E1000_PHY_SPEC_CTRL 0x10 /* PHY Specific Control Register */ +#define M88E1000_PHY_SPEC_STATUS 0x11 /* PHY Specific Status Register */ +#define M88E1000_EXT_PHY_SPEC_CTRL 0x14 /* Extended PHY Specific Control */ + +#define M88E1000_PHY_PAGE_SELECT 0x1D /* Reg 29 for page number setting */ +#define M88E1000_PHY_GEN_CONTROL 0x1E /* Its meaning depends on reg 29 */ + +/* M88E1000 PHY Specific Control Register */ +#define M88E1000_PSCR_POLARITY_REVERSAL 0x0002 /* 1=Polarity Reversal enabled */ +/* 1=CLK125 low, 0=CLK125 toggling */ +#define M88E1000_PSCR_MDI_MANUAL_MODE 0x0000 /* MDI Crossover Mode bits 6:5 */ + /* Manual MDI configuration */ +#define M88E1000_PSCR_MDIX_MANUAL_MODE 0x0020 /* Manual MDIX configuration */ +/* 1000BASE-T: Auto crossover, 100BASE-TX/10BASE-T: MDI Mode */ +#define M88E1000_PSCR_AUTO_X_1000T 0x0040 +/* Auto crossover enabled all speeds */ +#define M88E1000_PSCR_AUTO_X_MODE 0x0060 +/* 1=Enable Extended 10BASE-T distance (Lower 10BASE-T Rx Threshold + * 0=Normal 10BASE-T Rx Threshold + */ +/* 1=5-bit interface in 100BASE-TX, 0=MII interface in 100BASE-TX */ +#define M88E1000_PSCR_ASSERT_CRS_ON_TX 0x0800 /* 1=Assert CRS on Transmit */ + +/* M88E1000 PHY Specific Status Register */ +#define M88E1000_PSSR_REV_POLARITY 0x0002 /* 1=Polarity reversed */ +#define M88E1000_PSSR_DOWNSHIFT 0x0020 /* 1=Downshifted */ +#define M88E1000_PSSR_MDIX 0x0040 /* 1=MDIX; 0=MDI */ +/* 0 = <50M + * 1 = 50-80M + * 2 = 80-110M + * 3 = 110-140M + * 4 = >140M + */ +#define M88E1000_PSSR_CABLE_LENGTH 0x0380 +#define M88E1000_PSSR_SPEED 0xC000 /* Speed, bits 14:15 */ +#define M88E1000_PSSR_1000MBS 0x8000 /* 10=1000Mbs */ + +#define M88E1000_PSSR_CABLE_LENGTH_SHIFT 7 + +/* M88E1000 Extended PHY Specific Control Register */ +/* 1 = Lost lock detect enabled. + * Will assert lost lock and bring + * link down if idle not seen + * within 1ms in 1000BASE-T + */ +/* Number of times we will attempt to autonegotiate before downshifting if we + * are the master + */ +#define M88E1000_EPSCR_MASTER_DOWNSHIFT_MASK 0x0C00 +#define M88E1000_EPSCR_MASTER_DOWNSHIFT_1X 0x0000 +/* Number of times we will attempt to autonegotiate before downshifting if we + * are the slave + */ +#define M88E1000_EPSCR_SLAVE_DOWNSHIFT_MASK 0x0300 +#define M88E1000_EPSCR_SLAVE_DOWNSHIFT_1X 0x0100 +#define M88E1000_EPSCR_TX_CLK_25 0x0070 /* 25 MHz TX_CLK */ + +/* Intel i347-AT4 Registers */ + +#define I347AT4_PCDL0 0x10 /* Pair 0 PHY Cable Diagnostics Length */ +#define I347AT4_PCDL1 0x11 /* Pair 1 PHY Cable Diagnostics Length */ +#define I347AT4_PCDL2 0x12 /* Pair 2 PHY Cable Diagnostics Length */ +#define I347AT4_PCDL3 0x13 /* Pair 3 PHY Cable Diagnostics Length */ +#define I347AT4_PCDC 0x15 /* PHY Cable Diagnostics Control */ +#define I347AT4_PAGE_SELECT 0x16 + +/* i347-AT4 Extended PHY Specific Control Register */ + +/* Number of times we will attempt to autonegotiate before downshifting if we + * are the master + */ +#define I347AT4_PSCR_DOWNSHIFT_ENABLE 0x0800 +#define I347AT4_PSCR_DOWNSHIFT_MASK 0x7000 +#define I347AT4_PSCR_DOWNSHIFT_1X 0x0000 +#define I347AT4_PSCR_DOWNSHIFT_2X 0x1000 +#define I347AT4_PSCR_DOWNSHIFT_3X 0x2000 +#define I347AT4_PSCR_DOWNSHIFT_4X 0x3000 +#define I347AT4_PSCR_DOWNSHIFT_5X 0x4000 +#define I347AT4_PSCR_DOWNSHIFT_6X 0x5000 +#define I347AT4_PSCR_DOWNSHIFT_7X 0x6000 +#define I347AT4_PSCR_DOWNSHIFT_8X 0x7000 + +/* i347-AT4 PHY Cable Diagnostics Control */ +#define I347AT4_PCDC_CABLE_LENGTH_UNIT 0x0400 /* 0=cm 1=meters */ + +/* Marvell 1112 only registers */ +#define M88E1112_VCT_DSP_DISTANCE 0x001A + +/* M88EC018 Rev 2 specific DownShift settings */ +#define M88EC018_EPSCR_DOWNSHIFT_COUNTER_MASK 0x0E00 +#define M88EC018_EPSCR_DOWNSHIFT_COUNTER_5X 0x0800 + +/* MDI Control */ +#define E1000_MDIC_DATA_MASK 0x0000FFFF +#define E1000_MDIC_REG_MASK 0x001F0000 +#define E1000_MDIC_REG_SHIFT 16 +#define E1000_MDIC_PHY_MASK 0x03E00000 +#define E1000_MDIC_PHY_SHIFT 21 +#define E1000_MDIC_OP_WRITE 0x04000000 +#define E1000_MDIC_OP_READ 0x08000000 +#define E1000_MDIC_READY 0x10000000 +#define E1000_MDIC_INT_EN 0x20000000 +#define E1000_MDIC_ERROR 0x40000000 +#define E1000_MDIC_DEST 0x80000000 + +/* Thermal Sensor */ +#define E1000_THSTAT_PWR_DOWN 0x00000001 /* Power Down Event */ +#define E1000_THSTAT_LINK_THROTTLE 0x00000002 /* Link Speed Throttle Event */ + +/* Energy Efficient Ethernet */ +#define E1000_IPCNFG_EEE_1G_AN 0x00000008 /* EEE Enable 1G AN */ +#define E1000_IPCNFG_EEE_100M_AN 0x00000004 /* EEE Enable 100M AN */ +#define E1000_EEER_TX_LPI_EN 0x00010000 /* EEE Tx LPI Enable */ +#define E1000_EEER_RX_LPI_EN 0x00020000 /* EEE Rx LPI Enable */ +#define E1000_EEER_FRC_AN 0x10000000 /* Enable EEE in loopback */ +#define E1000_EEER_LPI_FC 0x00040000 /* EEE Enable on FC */ +#define E1000_EEE_SU_LPI_CLK_STP 0X00800000 /* EEE LPI Clock Stop */ +#define E1000_EEER_EEE_NEG 0x20000000 /* EEE capability nego */ +#define E1000_EEE_LP_ADV_ADDR_I350 0x040F /* EEE LP Advertisement */ +#define E1000_EEE_LP_ADV_DEV_I210 7 /* EEE LP Adv Device */ +#define E1000_EEE_LP_ADV_ADDR_I210 61 /* EEE LP Adv Register */ +#define E1000_MMDAC_FUNC_DATA 0x4000 /* Data, no post increment */ +#define E1000_M88E1543_PAGE_ADDR 0x16 /* Page Offset Register */ +#define E1000_M88E1543_EEE_CTRL_1 0x0 +#define E1000_M88E1543_EEE_CTRL_1_MS 0x0001 /* EEE Master/Slave */ +#define E1000_M88E1543_FIBER_CTRL 0x0 +#define E1000_EEE_ADV_DEV_I354 7 +#define E1000_EEE_ADV_ADDR_I354 60 +#define E1000_EEE_ADV_100_SUPPORTED BIT(1) /* 100BaseTx EEE Supported */ +#define E1000_EEE_ADV_1000_SUPPORTED BIT(2) /* 1000BaseT EEE Supported */ +#define E1000_PCS_STATUS_DEV_I354 3 +#define E1000_PCS_STATUS_ADDR_I354 1 +#define E1000_PCS_STATUS_TX_LPI_IND 0x0200 /* Tx in LPI state */ +#define E1000_PCS_STATUS_RX_LPI_RCVD 0x0400 +#define E1000_PCS_STATUS_TX_LPI_RCVD 0x0800 + +/* SerDes Control */ +#define E1000_GEN_CTL_READY 0x80000000 +#define E1000_GEN_CTL_ADDRESS_SHIFT 8 +#define E1000_GEN_POLL_TIMEOUT 640 + +#define E1000_VFTA_ENTRY_SHIFT 5 +#define E1000_VFTA_ENTRY_MASK 0x7F +#define E1000_VFTA_ENTRY_BIT_SHIFT_MASK 0x1F + +/* Tx Rate-Scheduler Config fields */ +#define E1000_RTTBCNRC_RS_ENA 0x80000000 +#define E1000_RTTBCNRC_RF_DEC_MASK 0x00003FFF +#define E1000_RTTBCNRC_RF_INT_SHIFT 14 +#define E1000_RTTBCNRC_RF_INT_MASK \ + (E1000_RTTBCNRC_RF_DEC_MASK << E1000_RTTBCNRC_RF_INT_SHIFT) + +#define E1000_VLAPQF_QUEUE_SEL(_n, q_idx) (q_idx << ((_n) * 4)) +#define E1000_VLAPQF_P_VALID(_n) (0x1 << (3 + (_n) * 4)) +#define E1000_VLAPQF_QUEUE_MASK 0x03 + +/* TX Qav Control fields */ +#define E1000_TQAVCTRL_XMIT_MODE BIT(0) +#define E1000_TQAVCTRL_DATAFETCHARB BIT(4) +#define E1000_TQAVCTRL_DATATRANARB BIT(8) +#define E1000_TQAVCTRL_DATATRANTIM BIT(9) +#define E1000_TQAVCTRL_SP_WAIT_SR BIT(10) +/* Fetch Time Delta - bits 31:16 + * + * This field holds the value to be reduced from the launch time for + * fetch time decision. The FetchTimeDelta value is defined in 32 ns + * granularity. + * + * This field is 16 bits wide, and so the maximum value is: + * + * 65535 * 32 = 2097120 ~= 2.1 msec + * + * XXX: We are configuring the max value here since we couldn't come up + * with a reason for not doing so. + */ +#define E1000_TQAVCTRL_FETCHTIME_DELTA (0xFFFF << 16) + +/* TX Qav Credit Control fields */ +#define E1000_TQAVCC_IDLESLOPE_MASK 0xFFFF +#define E1000_TQAVCC_QUEUEMODE BIT(31) + +/* Transmit Descriptor Control fields */ +#define E1000_TXDCTL_PRIORITY BIT(27) + +#endif diff --git a/drivers/net/ethernet/intel/igb/e1000_hw.h b/drivers/net/ethernet/intel/igb/e1000_hw.h new file mode 100644 index 0000000000..44111f65af --- /dev/null +++ b/drivers/net/ethernet/intel/igb/e1000_hw.h @@ -0,0 +1,554 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ + +#ifndef _E1000_IGB_HW_H_ +#define _E1000_IGB_HW_H_ + +#include <linux/types.h> +#include <linux/delay.h> +#include <linux/io.h> +#include <linux/netdevice.h> + +#include "e1000_regs.h" +#include "e1000_defines.h" + +struct e1000_hw; + +#define E1000_DEV_ID_82576 0x10C9 +#define E1000_DEV_ID_82576_FIBER 0x10E6 +#define E1000_DEV_ID_82576_SERDES 0x10E7 +#define E1000_DEV_ID_82576_QUAD_COPPER 0x10E8 +#define E1000_DEV_ID_82576_QUAD_COPPER_ET2 0x1526 +#define E1000_DEV_ID_82576_NS 0x150A +#define E1000_DEV_ID_82576_NS_SERDES 0x1518 +#define E1000_DEV_ID_82576_SERDES_QUAD 0x150D +#define E1000_DEV_ID_82575EB_COPPER 0x10A7 +#define E1000_DEV_ID_82575EB_FIBER_SERDES 0x10A9 +#define E1000_DEV_ID_82575GB_QUAD_COPPER 0x10D6 +#define E1000_DEV_ID_82580_COPPER 0x150E +#define E1000_DEV_ID_82580_FIBER 0x150F +#define E1000_DEV_ID_82580_SERDES 0x1510 +#define E1000_DEV_ID_82580_SGMII 0x1511 +#define E1000_DEV_ID_82580_COPPER_DUAL 0x1516 +#define E1000_DEV_ID_82580_QUAD_FIBER 0x1527 +#define E1000_DEV_ID_DH89XXCC_SGMII 0x0438 +#define E1000_DEV_ID_DH89XXCC_SERDES 0x043A +#define E1000_DEV_ID_DH89XXCC_BACKPLANE 0x043C +#define E1000_DEV_ID_DH89XXCC_SFP 0x0440 +#define E1000_DEV_ID_I350_COPPER 0x1521 +#define E1000_DEV_ID_I350_FIBER 0x1522 +#define E1000_DEV_ID_I350_SERDES 0x1523 +#define E1000_DEV_ID_I350_SGMII 0x1524 +#define E1000_DEV_ID_I210_COPPER 0x1533 +#define E1000_DEV_ID_I210_FIBER 0x1536 +#define E1000_DEV_ID_I210_SERDES 0x1537 +#define E1000_DEV_ID_I210_SGMII 0x1538 +#define E1000_DEV_ID_I210_COPPER_FLASHLESS 0x157B +#define E1000_DEV_ID_I210_SERDES_FLASHLESS 0x157C +#define E1000_DEV_ID_I211_COPPER 0x1539 +#define E1000_DEV_ID_I354_BACKPLANE_1GBPS 0x1F40 +#define E1000_DEV_ID_I354_SGMII 0x1F41 +#define E1000_DEV_ID_I354_BACKPLANE_2_5GBPS 0x1F45 + +#define E1000_REVISION_2 2 +#define E1000_REVISION_4 4 + +#define E1000_FUNC_0 0 +#define E1000_FUNC_1 1 +#define E1000_FUNC_2 2 +#define E1000_FUNC_3 3 + +#define E1000_ALT_MAC_ADDRESS_OFFSET_LAN0 0 +#define E1000_ALT_MAC_ADDRESS_OFFSET_LAN1 3 +#define E1000_ALT_MAC_ADDRESS_OFFSET_LAN2 6 +#define E1000_ALT_MAC_ADDRESS_OFFSET_LAN3 9 + +enum e1000_mac_type { + e1000_undefined = 0, + e1000_82575, + e1000_82576, + e1000_82580, + e1000_i350, + e1000_i354, + e1000_i210, + e1000_i211, + e1000_num_macs /* List is 1-based, so subtract 1 for true count. */ +}; + +enum e1000_media_type { + e1000_media_type_unknown = 0, + e1000_media_type_copper = 1, + e1000_media_type_fiber = 2, + e1000_media_type_internal_serdes = 3, + e1000_num_media_types +}; + +enum e1000_nvm_type { + e1000_nvm_unknown = 0, + e1000_nvm_none, + e1000_nvm_eeprom_spi, + e1000_nvm_flash_hw, + e1000_nvm_invm, + e1000_nvm_flash_sw +}; + +enum e1000_nvm_override { + e1000_nvm_override_none = 0, + e1000_nvm_override_spi_small, + e1000_nvm_override_spi_large, +}; + +enum e1000_phy_type { + e1000_phy_unknown = 0, + e1000_phy_none, + e1000_phy_m88, + e1000_phy_igp, + e1000_phy_igp_2, + e1000_phy_gg82563, + e1000_phy_igp_3, + e1000_phy_ife, + e1000_phy_82580, + e1000_phy_i210, + e1000_phy_bcm54616, +}; + +enum e1000_bus_type { + e1000_bus_type_unknown = 0, + e1000_bus_type_pci, + e1000_bus_type_pcix, + e1000_bus_type_pci_express, + e1000_bus_type_reserved +}; + +enum e1000_bus_speed { + e1000_bus_speed_unknown = 0, + e1000_bus_speed_33, + e1000_bus_speed_66, + e1000_bus_speed_100, + e1000_bus_speed_120, + e1000_bus_speed_133, + e1000_bus_speed_2500, + e1000_bus_speed_5000, + e1000_bus_speed_reserved +}; + +enum e1000_bus_width { + e1000_bus_width_unknown = 0, + e1000_bus_width_pcie_x1, + e1000_bus_width_pcie_x2, + e1000_bus_width_pcie_x4 = 4, + e1000_bus_width_pcie_x8 = 8, + e1000_bus_width_32, + e1000_bus_width_64, + e1000_bus_width_reserved +}; + +enum e1000_1000t_rx_status { + e1000_1000t_rx_status_not_ok = 0, + e1000_1000t_rx_status_ok, + e1000_1000t_rx_status_undefined = 0xFF +}; + +enum e1000_rev_polarity { + e1000_rev_polarity_normal = 0, + e1000_rev_polarity_reversed, + e1000_rev_polarity_undefined = 0xFF +}; + +enum e1000_fc_mode { + e1000_fc_none = 0, + e1000_fc_rx_pause, + e1000_fc_tx_pause, + e1000_fc_full, + e1000_fc_default = 0xFF +}; + +/* Statistics counters collected by the MAC */ +struct e1000_hw_stats { + u64 crcerrs; + u64 algnerrc; + u64 symerrs; + u64 rxerrc; + u64 mpc; + u64 scc; + u64 ecol; + u64 mcc; + u64 latecol; + u64 colc; + u64 dc; + u64 tncrs; + u64 sec; + u64 cexterr; + u64 rlec; + u64 xonrxc; + u64 xontxc; + u64 xoffrxc; + u64 xofftxc; + u64 fcruc; + u64 prc64; + u64 prc127; + u64 prc255; + u64 prc511; + u64 prc1023; + u64 prc1522; + u64 gprc; + u64 bprc; + u64 mprc; + u64 gptc; + u64 gorc; + u64 gotc; + u64 rnbc; + u64 ruc; + u64 rfc; + u64 roc; + u64 rjc; + u64 mgprc; + u64 mgpdc; + u64 mgptc; + u64 tor; + u64 tot; + u64 tpr; + u64 tpt; + u64 ptc64; + u64 ptc127; + u64 ptc255; + u64 ptc511; + u64 ptc1023; + u64 ptc1522; + u64 mptc; + u64 bptc; + u64 tsctc; + u64 tsctfc; + u64 iac; + u64 icrxptc; + u64 icrxatc; + u64 ictxptc; + u64 ictxatc; + u64 ictxqec; + u64 ictxqmtc; + u64 icrxdmtc; + u64 icrxoc; + u64 cbtmpc; + u64 htdpmc; + u64 cbrdpc; + u64 cbrmpc; + u64 rpthc; + u64 hgptc; + u64 htcbdpc; + u64 hgorc; + u64 hgotc; + u64 lenerrs; + u64 scvpc; + u64 hrmpc; + u64 doosync; + u64 o2bgptc; + u64 o2bspc; + u64 b2ospc; + u64 b2ogprc; +}; + +struct e1000_host_mng_dhcp_cookie { + u32 signature; + u8 status; + u8 reserved0; + u16 vlan_id; + u32 reserved1; + u16 reserved2; + u8 reserved3; + u8 checksum; +}; + +/* Host Interface "Rev 1" */ +struct e1000_host_command_header { + u8 command_id; + u8 command_length; + u8 command_options; + u8 checksum; +}; + +#define E1000_HI_MAX_DATA_LENGTH 252 +struct e1000_host_command_info { + struct e1000_host_command_header command_header; + u8 command_data[E1000_HI_MAX_DATA_LENGTH]; +}; + +/* Host Interface "Rev 2" */ +struct e1000_host_mng_command_header { + u8 command_id; + u8 checksum; + u16 reserved1; + u16 reserved2; + u16 command_length; +}; + +#define E1000_HI_MAX_MNG_DATA_LENGTH 0x6F8 +struct e1000_host_mng_command_info { + struct e1000_host_mng_command_header command_header; + u8 command_data[E1000_HI_MAX_MNG_DATA_LENGTH]; +}; + +#include "e1000_mac.h" +#include "e1000_phy.h" +#include "e1000_nvm.h" +#include "e1000_mbx.h" + +struct e1000_mac_operations { + s32 (*check_for_link)(struct e1000_hw *); + s32 (*reset_hw)(struct e1000_hw *); + s32 (*init_hw)(struct e1000_hw *); + bool (*check_mng_mode)(struct e1000_hw *); + s32 (*setup_physical_interface)(struct e1000_hw *); + void (*rar_set)(struct e1000_hw *, u8 *, u32); + s32 (*read_mac_addr)(struct e1000_hw *); + s32 (*get_speed_and_duplex)(struct e1000_hw *, u16 *, u16 *); + s32 (*acquire_swfw_sync)(struct e1000_hw *, u16); + void (*release_swfw_sync)(struct e1000_hw *, u16); +#ifdef CONFIG_IGB_HWMON + s32 (*get_thermal_sensor_data)(struct e1000_hw *); + s32 (*init_thermal_sensor_thresh)(struct e1000_hw *); +#endif + void (*write_vfta)(struct e1000_hw *, u32, u32); +}; + +struct e1000_phy_operations { + s32 (*acquire)(struct e1000_hw *); + s32 (*check_polarity)(struct e1000_hw *); + s32 (*check_reset_block)(struct e1000_hw *); + s32 (*force_speed_duplex)(struct e1000_hw *); + s32 (*get_cfg_done)(struct e1000_hw *hw); + s32 (*get_cable_length)(struct e1000_hw *); + s32 (*get_phy_info)(struct e1000_hw *); + s32 (*read_reg)(struct e1000_hw *, u32, u16 *); + void (*release)(struct e1000_hw *); + s32 (*reset)(struct e1000_hw *); + s32 (*set_d0_lplu_state)(struct e1000_hw *, bool); + s32 (*set_d3_lplu_state)(struct e1000_hw *, bool); + s32 (*write_reg)(struct e1000_hw *, u32, u16); + s32 (*read_i2c_byte)(struct e1000_hw *, u8, u8, u8 *); + s32 (*write_i2c_byte)(struct e1000_hw *, u8, u8, u8); +}; + +struct e1000_nvm_operations { + s32 (*acquire)(struct e1000_hw *); + s32 (*read)(struct e1000_hw *, u16, u16, u16 *); + void (*release)(struct e1000_hw *); + s32 (*write)(struct e1000_hw *, u16, u16, u16 *); + s32 (*update)(struct e1000_hw *); + s32 (*validate)(struct e1000_hw *); + s32 (*valid_led_default)(struct e1000_hw *, u16 *); +}; + +#define E1000_MAX_SENSORS 3 + +struct e1000_thermal_diode_data { + u8 location; + u8 temp; + u8 caution_thresh; + u8 max_op_thresh; +}; + +struct e1000_thermal_sensor_data { + struct e1000_thermal_diode_data sensor[E1000_MAX_SENSORS]; +}; + +struct e1000_info { + s32 (*get_invariants)(struct e1000_hw *); + struct e1000_mac_operations *mac_ops; + const struct e1000_phy_operations *phy_ops; + struct e1000_nvm_operations *nvm_ops; +}; + +extern const struct e1000_info e1000_82575_info; + +struct e1000_mac_info { + struct e1000_mac_operations ops; + + u8 addr[6]; + u8 perm_addr[6]; + + enum e1000_mac_type type; + + u32 ledctl_default; + u32 ledctl_mode1; + u32 ledctl_mode2; + u32 mc_filter_type; + u32 txcw; + + u16 mta_reg_count; + u16 uta_reg_count; + + /* Maximum size of the MTA register table in all supported adapters */ + #define MAX_MTA_REG 128 + u32 mta_shadow[MAX_MTA_REG]; + u16 rar_entry_count; + + u8 forced_speed_duplex; + + bool adaptive_ifs; + bool arc_subsystem_valid; + bool asf_firmware_present; + bool autoneg; + bool autoneg_failed; + bool disable_hw_init_bits; + bool get_link_status; + bool ifs_params_forced; + bool in_ifs_mode; + bool report_tx_early; + bool serdes_has_link; + bool tx_pkt_filtering; + struct e1000_thermal_sensor_data thermal_sensor_data; +}; + +struct e1000_phy_info { + struct e1000_phy_operations ops; + + enum e1000_phy_type type; + + enum e1000_1000t_rx_status local_rx; + enum e1000_1000t_rx_status remote_rx; + enum e1000_ms_type ms_type; + enum e1000_ms_type original_ms_type; + enum e1000_rev_polarity cable_polarity; + enum e1000_smart_speed smart_speed; + + u32 addr; + u32 id; + u32 reset_delay_us; /* in usec */ + u32 revision; + + enum e1000_media_type media_type; + + u16 autoneg_advertised; + u16 autoneg_mask; + u16 cable_length; + u16 max_cable_length; + u16 min_cable_length; + u16 pair_length[4]; + + u8 mdix; + + bool disable_polarity_correction; + bool is_mdix; + bool polarity_correction; + bool reset_disable; + bool speed_downgraded; + bool autoneg_wait_to_complete; +}; + +struct e1000_nvm_info { + struct e1000_nvm_operations ops; + enum e1000_nvm_type type; + enum e1000_nvm_override override; + + u32 flash_bank_size; + u32 flash_base_addr; + + u16 word_size; + u16 delay_usec; + u16 address_bits; + u16 opcode_bits; + u16 page_size; +}; + +struct e1000_bus_info { + enum e1000_bus_type type; + enum e1000_bus_speed speed; + enum e1000_bus_width width; + + u32 snoop; + + u16 func; + u16 pci_cmd_word; +}; + +struct e1000_fc_info { + u32 high_water; /* Flow control high-water mark */ + u32 low_water; /* Flow control low-water mark */ + u16 pause_time; /* Flow control pause timer */ + bool send_xon; /* Flow control send XON */ + bool strict_ieee; /* Strict IEEE mode */ + enum e1000_fc_mode current_mode; /* Type of flow control */ + enum e1000_fc_mode requested_mode; +}; + +struct e1000_mbx_operations { + s32 (*init_params)(struct e1000_hw *hw); + s32 (*read)(struct e1000_hw *hw, u32 *msg, u16 size, u16 mbx_id, + bool unlock); + s32 (*write)(struct e1000_hw *hw, u32 *msg, u16 size, u16 mbx_id); + s32 (*read_posted)(struct e1000_hw *hw, u32 *msg, u16 size, u16 mbx_id); + s32 (*write_posted)(struct e1000_hw *hw, u32 *msg, u16 size, + u16 mbx_id); + s32 (*check_for_msg)(struct e1000_hw *hw, u16 mbx_id); + s32 (*check_for_ack)(struct e1000_hw *hw, u16 mbx_id); + s32 (*check_for_rst)(struct e1000_hw *hw, u16 mbx_id); + s32 (*unlock)(struct e1000_hw *hw, u16 mbx_id); +}; + +struct e1000_mbx_stats { + u32 msgs_tx; + u32 msgs_rx; + + u32 acks; + u32 reqs; + u32 rsts; +}; + +struct e1000_mbx_info { + struct e1000_mbx_operations ops; + struct e1000_mbx_stats stats; + u32 timeout; + u32 usec_delay; + u16 size; +}; + +struct e1000_dev_spec_82575 { + bool sgmii_active; + bool global_device_reset; + bool eee_disable; + bool clear_semaphore_once; + struct e1000_sfp_flags eth_flags; + bool module_plugged; + u8 media_port; + bool media_changed; + bool mas_capable; +}; + +struct e1000_hw { + void *back; + + u8 __iomem *hw_addr; + u8 __iomem *flash_address; + unsigned long io_base; + + struct e1000_mac_info mac; + struct e1000_fc_info fc; + struct e1000_phy_info phy; + struct e1000_nvm_info nvm; + struct e1000_bus_info bus; + struct e1000_mbx_info mbx; + struct e1000_host_mng_dhcp_cookie mng_cookie; + + union { + struct e1000_dev_spec_82575 _82575; + } dev_spec; + + u16 device_id; + u16 subsystem_vendor_id; + u16 subsystem_device_id; + u16 vendor_id; + + u8 revision_id; +}; + +struct net_device *igb_get_hw_dev(struct e1000_hw *hw); +#define hw_dbg(format, arg...) \ + netdev_dbg(igb_get_hw_dev(hw), format, ##arg) + +/* These functions must be implemented by drivers */ +s32 igb_read_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value); +s32 igb_write_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value); + +void igb_read_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value); +void igb_write_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value); +#endif /* _E1000_IGB_HW_H_ */ diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.c b/drivers/net/ethernet/intel/igb/e1000_i210.c new file mode 100644 index 0000000000..b9b9d35494 --- /dev/null +++ b/drivers/net/ethernet/intel/igb/e1000_i210.c @@ -0,0 +1,911 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2007 - 2018 Intel Corporation. */ + +/* e1000_i210 + * e1000_i211 + */ + +#include <linux/types.h> +#include <linux/if_ether.h> + +#include "e1000_hw.h" +#include "e1000_i210.h" + +static s32 igb_update_flash_i210(struct e1000_hw *hw); + +/** + * igb_get_hw_semaphore_i210 - Acquire hardware semaphore + * @hw: pointer to the HW structure + * + * Acquire the HW semaphore to access the PHY or NVM + */ +static s32 igb_get_hw_semaphore_i210(struct e1000_hw *hw) +{ + u32 swsm; + s32 timeout = hw->nvm.word_size + 1; + s32 i = 0; + + /* Get the SW semaphore */ + while (i < timeout) { + swsm = rd32(E1000_SWSM); + if (!(swsm & E1000_SWSM_SMBI)) + break; + + udelay(50); + i++; + } + + if (i == timeout) { + /* In rare circumstances, the SW semaphore may already be held + * unintentionally. Clear the semaphore once before giving up. + */ + if (hw->dev_spec._82575.clear_semaphore_once) { + hw->dev_spec._82575.clear_semaphore_once = false; + igb_put_hw_semaphore(hw); + for (i = 0; i < timeout; i++) { + swsm = rd32(E1000_SWSM); + if (!(swsm & E1000_SWSM_SMBI)) + break; + + udelay(50); + } + } + + /* If we do not have the semaphore here, we have to give up. */ + if (i == timeout) { + hw_dbg("Driver can't access device - SMBI bit is set.\n"); + return -E1000_ERR_NVM; + } + } + + /* Get the FW semaphore. */ + for (i = 0; i < timeout; i++) { + swsm = rd32(E1000_SWSM); + wr32(E1000_SWSM, swsm | E1000_SWSM_SWESMBI); + + /* Semaphore acquired if bit latched */ + if (rd32(E1000_SWSM) & E1000_SWSM_SWESMBI) + break; + + udelay(50); + } + + if (i == timeout) { + /* Release semaphores */ + igb_put_hw_semaphore(hw); + hw_dbg("Driver can't access the NVM\n"); + return -E1000_ERR_NVM; + } + + return 0; +} + +/** + * igb_acquire_nvm_i210 - Request for access to EEPROM + * @hw: pointer to the HW structure + * + * Acquire the necessary semaphores for exclusive access to the EEPROM. + * Set the EEPROM access request bit and wait for EEPROM access grant bit. + * Return successful if access grant bit set, else clear the request for + * EEPROM access and return -E1000_ERR_NVM (-1). + **/ +static s32 igb_acquire_nvm_i210(struct e1000_hw *hw) +{ + return igb_acquire_swfw_sync_i210(hw, E1000_SWFW_EEP_SM); +} + +/** + * igb_release_nvm_i210 - Release exclusive access to EEPROM + * @hw: pointer to the HW structure + * + * Stop any current commands to the EEPROM and clear the EEPROM request bit, + * then release the semaphores acquired. + **/ +static void igb_release_nvm_i210(struct e1000_hw *hw) +{ + igb_release_swfw_sync_i210(hw, E1000_SWFW_EEP_SM); +} + +/** + * igb_acquire_swfw_sync_i210 - Acquire SW/FW semaphore + * @hw: pointer to the HW structure + * @mask: specifies which semaphore to acquire + * + * Acquire the SW/FW semaphore to access the PHY or NVM. The mask + * will also specify which port we're acquiring the lock for. + **/ +s32 igb_acquire_swfw_sync_i210(struct e1000_hw *hw, u16 mask) +{ + u32 swfw_sync; + u32 swmask = mask; + u32 fwmask = mask << 16; + s32 ret_val = 0; + s32 i = 0, timeout = 200; /* FIXME: find real value to use here */ + + while (i < timeout) { + if (igb_get_hw_semaphore_i210(hw)) { + ret_val = -E1000_ERR_SWFW_SYNC; + goto out; + } + + swfw_sync = rd32(E1000_SW_FW_SYNC); + if (!(swfw_sync & (fwmask | swmask))) + break; + + /* Firmware currently using resource (fwmask) */ + igb_put_hw_semaphore(hw); + mdelay(5); + i++; + } + + if (i == timeout) { + hw_dbg("Driver can't access resource, SW_FW_SYNC timeout.\n"); + ret_val = -E1000_ERR_SWFW_SYNC; + goto out; + } + + swfw_sync |= swmask; + wr32(E1000_SW_FW_SYNC, swfw_sync); + + igb_put_hw_semaphore(hw); +out: + return ret_val; +} + +/** + * igb_release_swfw_sync_i210 - Release SW/FW semaphore + * @hw: pointer to the HW structure + * @mask: specifies which semaphore to acquire + * + * Release the SW/FW semaphore used to access the PHY or NVM. The mask + * will also specify which port we're releasing the lock for. + **/ +void igb_release_swfw_sync_i210(struct e1000_hw *hw, u16 mask) +{ + u32 swfw_sync; + + while (igb_get_hw_semaphore_i210(hw)) + ; /* Empty */ + + swfw_sync = rd32(E1000_SW_FW_SYNC); + swfw_sync &= ~mask; + wr32(E1000_SW_FW_SYNC, swfw_sync); + + igb_put_hw_semaphore(hw); +} + +/** + * igb_read_nvm_srrd_i210 - Reads Shadow Ram using EERD register + * @hw: pointer to the HW structure + * @offset: offset of word in the Shadow Ram to read + * @words: number of words to read + * @data: word read from the Shadow Ram + * + * Reads a 16 bit word from the Shadow Ram using the EERD register. + * Uses necessary synchronization semaphores. + **/ +static s32 igb_read_nvm_srrd_i210(struct e1000_hw *hw, u16 offset, u16 words, + u16 *data) +{ + s32 status = 0; + u16 i, count; + + /* We cannot hold synchronization semaphores for too long, + * because of forceful takeover procedure. However it is more efficient + * to read in bursts than synchronizing access for each word. + */ + for (i = 0; i < words; i += E1000_EERD_EEWR_MAX_COUNT) { + count = (words - i) / E1000_EERD_EEWR_MAX_COUNT > 0 ? + E1000_EERD_EEWR_MAX_COUNT : (words - i); + if (!(hw->nvm.ops.acquire(hw))) { + status = igb_read_nvm_eerd(hw, offset, count, + data + i); + hw->nvm.ops.release(hw); + } else { + status = E1000_ERR_SWFW_SYNC; + } + + if (status) + break; + } + + return status; +} + +/** + * igb_write_nvm_srwr - Write to Shadow Ram using EEWR + * @hw: pointer to the HW structure + * @offset: offset within the Shadow Ram to be written to + * @words: number of words to write + * @data: 16 bit word(s) to be written to the Shadow Ram + * + * Writes data to Shadow Ram at offset using EEWR register. + * + * If igb_update_nvm_checksum is not called after this function , the + * Shadow Ram will most likely contain an invalid checksum. + **/ +static s32 igb_write_nvm_srwr(struct e1000_hw *hw, u16 offset, u16 words, + u16 *data) +{ + struct e1000_nvm_info *nvm = &hw->nvm; + u32 i, k, eewr = 0; + u32 attempts = 100000; + s32 ret_val = 0; + + /* A check for invalid values: offset too large, too many words, + * too many words for the offset, and not enough words. + */ + if ((offset >= nvm->word_size) || (words > (nvm->word_size - offset)) || + (words == 0)) { + hw_dbg("nvm parameter(s) out of bounds\n"); + ret_val = -E1000_ERR_NVM; + goto out; + } + + for (i = 0; i < words; i++) { + eewr = ((offset+i) << E1000_NVM_RW_ADDR_SHIFT) | + (data[i] << E1000_NVM_RW_REG_DATA) | + E1000_NVM_RW_REG_START; + + wr32(E1000_SRWR, eewr); + + for (k = 0; k < attempts; k++) { + if (E1000_NVM_RW_REG_DONE & + rd32(E1000_SRWR)) { + ret_val = 0; + break; + } + udelay(5); + } + + if (ret_val) { + hw_dbg("Shadow RAM write EEWR timed out\n"); + break; + } + } + +out: + return ret_val; +} + +/** + * igb_write_nvm_srwr_i210 - Write to Shadow RAM using EEWR + * @hw: pointer to the HW structure + * @offset: offset within the Shadow RAM to be written to + * @words: number of words to write + * @data: 16 bit word(s) to be written to the Shadow RAM + * + * Writes data to Shadow RAM at offset using EEWR register. + * + * If e1000_update_nvm_checksum is not called after this function , the + * data will not be committed to FLASH and also Shadow RAM will most likely + * contain an invalid checksum. + * + * If error code is returned, data and Shadow RAM may be inconsistent - buffer + * partially written. + **/ +static s32 igb_write_nvm_srwr_i210(struct e1000_hw *hw, u16 offset, u16 words, + u16 *data) +{ + s32 status = 0; + u16 i, count; + + /* We cannot hold synchronization semaphores for too long, + * because of forceful takeover procedure. However it is more efficient + * to write in bursts than synchronizing access for each word. + */ + for (i = 0; i < words; i += E1000_EERD_EEWR_MAX_COUNT) { + count = (words - i) / E1000_EERD_EEWR_MAX_COUNT > 0 ? + E1000_EERD_EEWR_MAX_COUNT : (words - i); + if (!(hw->nvm.ops.acquire(hw))) { + status = igb_write_nvm_srwr(hw, offset, count, + data + i); + hw->nvm.ops.release(hw); + } else { + status = E1000_ERR_SWFW_SYNC; + } + + if (status) + break; + } + + return status; +} + +/** + * igb_read_invm_word_i210 - Reads OTP + * @hw: pointer to the HW structure + * @address: the word address (aka eeprom offset) to read + * @data: pointer to the data read + * + * Reads 16-bit words from the OTP. Return error when the word is not + * stored in OTP. + **/ +static s32 igb_read_invm_word_i210(struct e1000_hw *hw, u8 address, u16 *data) +{ + s32 status = -E1000_ERR_INVM_VALUE_NOT_FOUND; + u32 invm_dword; + u16 i; + u8 record_type, word_address; + + for (i = 0; i < E1000_INVM_SIZE; i++) { + invm_dword = rd32(E1000_INVM_DATA_REG(i)); + /* Get record type */ + record_type = INVM_DWORD_TO_RECORD_TYPE(invm_dword); + if (record_type == E1000_INVM_UNINITIALIZED_STRUCTURE) + break; + if (record_type == E1000_INVM_CSR_AUTOLOAD_STRUCTURE) + i += E1000_INVM_CSR_AUTOLOAD_DATA_SIZE_IN_DWORDS; + if (record_type == E1000_INVM_RSA_KEY_SHA256_STRUCTURE) + i += E1000_INVM_RSA_KEY_SHA256_DATA_SIZE_IN_DWORDS; + if (record_type == E1000_INVM_WORD_AUTOLOAD_STRUCTURE) { + word_address = INVM_DWORD_TO_WORD_ADDRESS(invm_dword); + if (word_address == address) { + *data = INVM_DWORD_TO_WORD_DATA(invm_dword); + hw_dbg("Read INVM Word 0x%02x = %x\n", + address, *data); + status = 0; + break; + } + } + } + if (status) + hw_dbg("Requested word 0x%02x not found in OTP\n", address); + return status; +} + +/** + * igb_read_invm_i210 - Read invm wrapper function for I210/I211 + * @hw: pointer to the HW structure + * @offset: offset to read from + * @words: number of words to read (unused) + * @data: pointer to the data read + * + * Wrapper function to return data formerly found in the NVM. + **/ +static s32 igb_read_invm_i210(struct e1000_hw *hw, u16 offset, + u16 __always_unused words, u16 *data) +{ + s32 ret_val = 0; + + /* Only the MAC addr is required to be present in the iNVM */ + switch (offset) { + case NVM_MAC_ADDR: + ret_val = igb_read_invm_word_i210(hw, (u8)offset, &data[0]); + ret_val |= igb_read_invm_word_i210(hw, (u8)offset+1, + &data[1]); + ret_val |= igb_read_invm_word_i210(hw, (u8)offset+2, + &data[2]); + if (ret_val) + hw_dbg("MAC Addr not found in iNVM\n"); + break; + case NVM_INIT_CTRL_2: + ret_val = igb_read_invm_word_i210(hw, (u8)offset, data); + if (ret_val) { + *data = NVM_INIT_CTRL_2_DEFAULT_I211; + ret_val = 0; + } + break; + case NVM_INIT_CTRL_4: + ret_val = igb_read_invm_word_i210(hw, (u8)offset, data); + if (ret_val) { + *data = NVM_INIT_CTRL_4_DEFAULT_I211; + ret_val = 0; + } + break; + case NVM_LED_1_CFG: + ret_val = igb_read_invm_word_i210(hw, (u8)offset, data); + if (ret_val) { + *data = NVM_LED_1_CFG_DEFAULT_I211; + ret_val = 0; + } + break; + case NVM_LED_0_2_CFG: + ret_val = igb_read_invm_word_i210(hw, (u8)offset, data); + if (ret_val) { + *data = NVM_LED_0_2_CFG_DEFAULT_I211; + ret_val = 0; + } + break; + case NVM_ID_LED_SETTINGS: + ret_val = igb_read_invm_word_i210(hw, (u8)offset, data); + if (ret_val) { + *data = ID_LED_RESERVED_FFFF; + ret_val = 0; + } + break; + case NVM_SUB_DEV_ID: + *data = hw->subsystem_device_id; + break; + case NVM_SUB_VEN_ID: + *data = hw->subsystem_vendor_id; + break; + case NVM_DEV_ID: + *data = hw->device_id; + break; + case NVM_VEN_ID: + *data = hw->vendor_id; + break; + default: + hw_dbg("NVM word 0x%02x is not mapped.\n", offset); + *data = NVM_RESERVED_WORD; + break; + } + return ret_val; +} + +/** + * igb_read_invm_version - Reads iNVM version and image type + * @hw: pointer to the HW structure + * @invm_ver: version structure for the version read + * + * Reads iNVM version and image type. + **/ +s32 igb_read_invm_version(struct e1000_hw *hw, + struct e1000_fw_version *invm_ver) { + u32 *record = NULL; + u32 *next_record = NULL; + u32 i = 0; + u32 invm_dword = 0; + u32 invm_blocks = E1000_INVM_SIZE - (E1000_INVM_ULT_BYTES_SIZE / + E1000_INVM_RECORD_SIZE_IN_BYTES); + u32 buffer[E1000_INVM_SIZE]; + s32 status = -E1000_ERR_INVM_VALUE_NOT_FOUND; + u16 version = 0; + + /* Read iNVM memory */ + for (i = 0; i < E1000_INVM_SIZE; i++) { + invm_dword = rd32(E1000_INVM_DATA_REG(i)); + buffer[i] = invm_dword; + } + + /* Read version number */ + for (i = 1; i < invm_blocks; i++) { + record = &buffer[invm_blocks - i]; + next_record = &buffer[invm_blocks - i + 1]; + + /* Check if we have first version location used */ + if ((i == 1) && ((*record & E1000_INVM_VER_FIELD_ONE) == 0)) { + version = 0; + status = 0; + break; + } + /* Check if we have second version location used */ + else if ((i == 1) && + ((*record & E1000_INVM_VER_FIELD_TWO) == 0)) { + version = (*record & E1000_INVM_VER_FIELD_ONE) >> 3; + status = 0; + break; + } + /* Check if we have odd version location + * used and it is the last one used + */ + else if ((((*record & E1000_INVM_VER_FIELD_ONE) == 0) && + ((*record & 0x3) == 0)) || (((*record & 0x3) != 0) && + (i != 1))) { + version = (*next_record & E1000_INVM_VER_FIELD_TWO) + >> 13; + status = 0; + break; + } + /* Check if we have even version location + * used and it is the last one used + */ + else if (((*record & E1000_INVM_VER_FIELD_TWO) == 0) && + ((*record & 0x3) == 0)) { + version = (*record & E1000_INVM_VER_FIELD_ONE) >> 3; + status = 0; + break; + } + } + + if (!status) { + invm_ver->invm_major = (version & E1000_INVM_MAJOR_MASK) + >> E1000_INVM_MAJOR_SHIFT; + invm_ver->invm_minor = version & E1000_INVM_MINOR_MASK; + } + /* Read Image Type */ + for (i = 1; i < invm_blocks; i++) { + record = &buffer[invm_blocks - i]; + next_record = &buffer[invm_blocks - i + 1]; + + /* Check if we have image type in first location used */ + if ((i == 1) && ((*record & E1000_INVM_IMGTYPE_FIELD) == 0)) { + invm_ver->invm_img_type = 0; + status = 0; + break; + } + /* Check if we have image type in first location used */ + else if ((((*record & 0x3) == 0) && + ((*record & E1000_INVM_IMGTYPE_FIELD) == 0)) || + ((((*record & 0x3) != 0) && (i != 1)))) { + invm_ver->invm_img_type = + (*next_record & E1000_INVM_IMGTYPE_FIELD) >> 23; + status = 0; + break; + } + } + return status; +} + +/** + * igb_validate_nvm_checksum_i210 - Validate EEPROM checksum + * @hw: pointer to the HW structure + * + * Calculates the EEPROM checksum by reading/adding each word of the EEPROM + * and then verifies that the sum of the EEPROM is equal to 0xBABA. + **/ +static s32 igb_validate_nvm_checksum_i210(struct e1000_hw *hw) +{ + s32 status = 0; + s32 (*read_op_ptr)(struct e1000_hw *, u16, u16, u16 *); + + if (!(hw->nvm.ops.acquire(hw))) { + + /* Replace the read function with semaphore grabbing with + * the one that skips this for a while. + * We have semaphore taken already here. + */ + read_op_ptr = hw->nvm.ops.read; + hw->nvm.ops.read = igb_read_nvm_eerd; + + status = igb_validate_nvm_checksum(hw); + + /* Revert original read operation. */ + hw->nvm.ops.read = read_op_ptr; + + hw->nvm.ops.release(hw); + } else { + status = E1000_ERR_SWFW_SYNC; + } + + return status; +} + +/** + * igb_update_nvm_checksum_i210 - Update EEPROM checksum + * @hw: pointer to the HW structure + * + * Updates the EEPROM checksum by reading/adding each word of the EEPROM + * up to the checksum. Then calculates the EEPROM checksum and writes the + * value to the EEPROM. Next commit EEPROM data onto the Flash. + **/ +static s32 igb_update_nvm_checksum_i210(struct e1000_hw *hw) +{ + s32 ret_val = 0; + u16 checksum = 0; + u16 i, nvm_data; + + /* Read the first word from the EEPROM. If this times out or fails, do + * not continue or we could be in for a very long wait while every + * EEPROM read fails + */ + ret_val = igb_read_nvm_eerd(hw, 0, 1, &nvm_data); + if (ret_val) { + hw_dbg("EEPROM read failed\n"); + goto out; + } + + if (!(hw->nvm.ops.acquire(hw))) { + /* Do not use hw->nvm.ops.write, hw->nvm.ops.read + * because we do not want to take the synchronization + * semaphores twice here. + */ + + for (i = 0; i < NVM_CHECKSUM_REG; i++) { + ret_val = igb_read_nvm_eerd(hw, i, 1, &nvm_data); + if (ret_val) { + hw->nvm.ops.release(hw); + hw_dbg("NVM Read Error while updating checksum.\n"); + goto out; + } + checksum += nvm_data; + } + checksum = (u16) NVM_SUM - checksum; + ret_val = igb_write_nvm_srwr(hw, NVM_CHECKSUM_REG, 1, + &checksum); + if (ret_val) { + hw->nvm.ops.release(hw); + hw_dbg("NVM Write Error while updating checksum.\n"); + goto out; + } + + hw->nvm.ops.release(hw); + + ret_val = igb_update_flash_i210(hw); + } else { + ret_val = -E1000_ERR_SWFW_SYNC; + } +out: + return ret_val; +} + +/** + * igb_pool_flash_update_done_i210 - Pool FLUDONE status. + * @hw: pointer to the HW structure + * + **/ +static s32 igb_pool_flash_update_done_i210(struct e1000_hw *hw) +{ + s32 ret_val = -E1000_ERR_NVM; + u32 i, reg; + + for (i = 0; i < E1000_FLUDONE_ATTEMPTS; i++) { + reg = rd32(E1000_EECD); + if (reg & E1000_EECD_FLUDONE_I210) { + ret_val = 0; + break; + } + udelay(5); + } + + return ret_val; +} + +/** + * igb_get_flash_presence_i210 - Check if flash device is detected. + * @hw: pointer to the HW structure + * + **/ +bool igb_get_flash_presence_i210(struct e1000_hw *hw) +{ + u32 eec = 0; + bool ret_val = false; + + eec = rd32(E1000_EECD); + if (eec & E1000_EECD_FLASH_DETECTED_I210) + ret_val = true; + + return ret_val; +} + +/** + * igb_update_flash_i210 - Commit EEPROM to the flash + * @hw: pointer to the HW structure + * + **/ +static s32 igb_update_flash_i210(struct e1000_hw *hw) +{ + s32 ret_val = 0; + u32 flup; + + ret_val = igb_pool_flash_update_done_i210(hw); + if (ret_val == -E1000_ERR_NVM) { + hw_dbg("Flash update time out\n"); + goto out; + } + + flup = rd32(E1000_EECD) | E1000_EECD_FLUPD_I210; + wr32(E1000_EECD, flup); + + ret_val = igb_pool_flash_update_done_i210(hw); + if (ret_val) + hw_dbg("Flash update time out\n"); + else + hw_dbg("Flash update complete\n"); + +out: + return ret_val; +} + +/** + * igb_valid_led_default_i210 - Verify a valid default LED config + * @hw: pointer to the HW structure + * @data: pointer to the NVM (EEPROM) + * + * Read the EEPROM for the current default LED configuration. If the + * LED configuration is not valid, set to a valid LED configuration. + **/ +s32 igb_valid_led_default_i210(struct e1000_hw *hw, u16 *data) +{ + s32 ret_val; + + ret_val = hw->nvm.ops.read(hw, NVM_ID_LED_SETTINGS, 1, data); + if (ret_val) { + hw_dbg("NVM Read Error\n"); + goto out; + } + + if (*data == ID_LED_RESERVED_0000 || *data == ID_LED_RESERVED_FFFF) { + switch (hw->phy.media_type) { + case e1000_media_type_internal_serdes: + *data = ID_LED_DEFAULT_I210_SERDES; + break; + case e1000_media_type_copper: + default: + *data = ID_LED_DEFAULT_I210; + break; + } + } +out: + return ret_val; +} + +/** + * __igb_access_xmdio_reg - Read/write XMDIO register + * @hw: pointer to the HW structure + * @address: XMDIO address to program + * @dev_addr: device address to program + * @data: pointer to value to read/write from/to the XMDIO address + * @read: boolean flag to indicate read or write + **/ +static s32 __igb_access_xmdio_reg(struct e1000_hw *hw, u16 address, + u8 dev_addr, u16 *data, bool read) +{ + s32 ret_val = 0; + + ret_val = hw->phy.ops.write_reg(hw, E1000_MMDAC, dev_addr); + if (ret_val) + return ret_val; + + ret_val = hw->phy.ops.write_reg(hw, E1000_MMDAAD, address); + if (ret_val) + return ret_val; + + ret_val = hw->phy.ops.write_reg(hw, E1000_MMDAC, E1000_MMDAC_FUNC_DATA | + dev_addr); + if (ret_val) + return ret_val; + + if (read) + ret_val = hw->phy.ops.read_reg(hw, E1000_MMDAAD, data); + else + ret_val = hw->phy.ops.write_reg(hw, E1000_MMDAAD, *data); + if (ret_val) + return ret_val; + + /* Recalibrate the device back to 0 */ + ret_val = hw->phy.ops.write_reg(hw, E1000_MMDAC, 0); + if (ret_val) + return ret_val; + + return ret_val; +} + +/** + * igb_read_xmdio_reg - Read XMDIO register + * @hw: pointer to the HW structure + * @addr: XMDIO address to program + * @dev_addr: device address to program + * @data: value to be read from the EMI address + **/ +s32 igb_read_xmdio_reg(struct e1000_hw *hw, u16 addr, u8 dev_addr, u16 *data) +{ + return __igb_access_xmdio_reg(hw, addr, dev_addr, data, true); +} + +/** + * igb_write_xmdio_reg - Write XMDIO register + * @hw: pointer to the HW structure + * @addr: XMDIO address to program + * @dev_addr: device address to program + * @data: value to be written to the XMDIO address + **/ +s32 igb_write_xmdio_reg(struct e1000_hw *hw, u16 addr, u8 dev_addr, u16 data) +{ + return __igb_access_xmdio_reg(hw, addr, dev_addr, &data, false); +} + +/** + * igb_init_nvm_params_i210 - Init NVM func ptrs. + * @hw: pointer to the HW structure + **/ +s32 igb_init_nvm_params_i210(struct e1000_hw *hw) +{ + struct e1000_nvm_info *nvm = &hw->nvm; + + nvm->ops.acquire = igb_acquire_nvm_i210; + nvm->ops.release = igb_release_nvm_i210; + nvm->ops.valid_led_default = igb_valid_led_default_i210; + + /* NVM Function Pointers */ + if (igb_get_flash_presence_i210(hw)) { + hw->nvm.type = e1000_nvm_flash_hw; + nvm->ops.read = igb_read_nvm_srrd_i210; + nvm->ops.write = igb_write_nvm_srwr_i210; + nvm->ops.validate = igb_validate_nvm_checksum_i210; + nvm->ops.update = igb_update_nvm_checksum_i210; + } else { + hw->nvm.type = e1000_nvm_invm; + nvm->ops.read = igb_read_invm_i210; + nvm->ops.write = NULL; + nvm->ops.validate = NULL; + nvm->ops.update = NULL; + } + return 0; +} + +/** + * igb_pll_workaround_i210 + * @hw: pointer to the HW structure + * + * Works around an errata in the PLL circuit where it occasionally + * provides the wrong clock frequency after power up. + **/ +s32 igb_pll_workaround_i210(struct e1000_hw *hw) +{ + s32 ret_val; + u32 wuc, mdicnfg, ctrl, ctrl_ext, reg_val; + u16 nvm_word, phy_word, pci_word, tmp_nvm; + int i; + + /* Get and set needed register values */ + wuc = rd32(E1000_WUC); + mdicnfg = rd32(E1000_MDICNFG); + reg_val = mdicnfg & ~E1000_MDICNFG_EXT_MDIO; + wr32(E1000_MDICNFG, reg_val); + + /* Get data from NVM, or set default */ + ret_val = igb_read_invm_word_i210(hw, E1000_INVM_AUTOLOAD, + &nvm_word); + if (ret_val) + nvm_word = E1000_INVM_DEFAULT_AL; + tmp_nvm = nvm_word | E1000_INVM_PLL_WO_VAL; + igb_write_phy_reg_82580(hw, I347AT4_PAGE_SELECT, E1000_PHY_PLL_FREQ_PAGE); + phy_word = E1000_PHY_PLL_UNCONF; + for (i = 0; i < E1000_MAX_PLL_TRIES; i++) { + /* check current state directly from internal PHY */ + igb_read_phy_reg_82580(hw, E1000_PHY_PLL_FREQ_REG, &phy_word); + if ((phy_word & E1000_PHY_PLL_UNCONF) + != E1000_PHY_PLL_UNCONF) { + ret_val = 0; + break; + } else { + ret_val = -E1000_ERR_PHY; + } + /* directly reset the internal PHY */ + ctrl = rd32(E1000_CTRL); + wr32(E1000_CTRL, ctrl|E1000_CTRL_PHY_RST); + + ctrl_ext = rd32(E1000_CTRL_EXT); + ctrl_ext |= (E1000_CTRL_EXT_PHYPDEN | E1000_CTRL_EXT_SDLPE); + wr32(E1000_CTRL_EXT, ctrl_ext); + + wr32(E1000_WUC, 0); + reg_val = (E1000_INVM_AUTOLOAD << 4) | (tmp_nvm << 16); + wr32(E1000_EEARBC_I210, reg_val); + + igb_read_pci_cfg(hw, E1000_PCI_PMCSR, &pci_word); + pci_word |= E1000_PCI_PMCSR_D3; + igb_write_pci_cfg(hw, E1000_PCI_PMCSR, &pci_word); + usleep_range(1000, 2000); + pci_word &= ~E1000_PCI_PMCSR_D3; + igb_write_pci_cfg(hw, E1000_PCI_PMCSR, &pci_word); + reg_val = (E1000_INVM_AUTOLOAD << 4) | (nvm_word << 16); + wr32(E1000_EEARBC_I210, reg_val); + + /* restore WUC register */ + wr32(E1000_WUC, wuc); + } + igb_write_phy_reg_82580(hw, I347AT4_PAGE_SELECT, 0); + /* restore MDICNFG setting */ + wr32(E1000_MDICNFG, mdicnfg); + return ret_val; +} + +/** + * igb_get_cfg_done_i210 - Read config done bit + * @hw: pointer to the HW structure + * + * Read the management control register for the config done bit for + * completion status. NOTE: silicon which is EEPROM-less will fail trying + * to read the config done bit, so an error is *ONLY* logged and returns + * 0. If we were to return with error, EEPROM-less silicon + * would not be able to be reset or change link. + **/ +s32 igb_get_cfg_done_i210(struct e1000_hw *hw) +{ + s32 timeout = PHY_CFG_TIMEOUT; + u32 mask = E1000_NVM_CFG_DONE_PORT_0; + + while (timeout) { + if (rd32(E1000_EEMNGCTL_I210) & mask) + break; + usleep_range(1000, 2000); + timeout--; + } + if (!timeout) + hw_dbg("MNG configuration cycle has not completed.\n"); + + return 0; +} diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.h b/drivers/net/ethernet/intel/igb/e1000_i210.h new file mode 100644 index 0000000000..5c437fdc49 --- /dev/null +++ b/drivers/net/ethernet/intel/igb/e1000_i210.h @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ + +#ifndef _E1000_I210_H_ +#define _E1000_I210_H_ + +s32 igb_acquire_swfw_sync_i210(struct e1000_hw *hw, u16 mask); +void igb_release_swfw_sync_i210(struct e1000_hw *hw, u16 mask); +s32 igb_valid_led_default_i210(struct e1000_hw *hw, u16 *data); +s32 igb_read_invm_version(struct e1000_hw *hw, + struct e1000_fw_version *invm_ver); +s32 igb_read_xmdio_reg(struct e1000_hw *hw, u16 addr, u8 dev_addr, u16 *data); +s32 igb_write_xmdio_reg(struct e1000_hw *hw, u16 addr, u8 dev_addr, u16 data); +s32 igb_init_nvm_params_i210(struct e1000_hw *hw); +bool igb_get_flash_presence_i210(struct e1000_hw *hw); +s32 igb_pll_workaround_i210(struct e1000_hw *hw); +s32 igb_get_cfg_done_i210(struct e1000_hw *hw); + +#define E1000_STM_OPCODE 0xDB00 +#define E1000_EEPROM_FLASH_SIZE_WORD 0x11 + +#define INVM_DWORD_TO_RECORD_TYPE(invm_dword) \ + (u8)((invm_dword) & 0x7) +#define INVM_DWORD_TO_WORD_ADDRESS(invm_dword) \ + (u8)(((invm_dword) & 0x0000FE00) >> 9) +#define INVM_DWORD_TO_WORD_DATA(invm_dword) \ + (u16)(((invm_dword) & 0xFFFF0000) >> 16) + +enum E1000_INVM_STRUCTURE_TYPE { + E1000_INVM_UNINITIALIZED_STRUCTURE = 0x00, + E1000_INVM_WORD_AUTOLOAD_STRUCTURE = 0x01, + E1000_INVM_CSR_AUTOLOAD_STRUCTURE = 0x02, + E1000_INVM_PHY_REGISTER_AUTOLOAD_STRUCTURE = 0x03, + E1000_INVM_RSA_KEY_SHA256_STRUCTURE = 0x04, + E1000_INVM_INVALIDATED_STRUCTURE = 0x0F, +}; + +#define E1000_INVM_RSA_KEY_SHA256_DATA_SIZE_IN_DWORDS 8 +#define E1000_INVM_CSR_AUTOLOAD_DATA_SIZE_IN_DWORDS 1 +#define E1000_INVM_ULT_BYTES_SIZE 8 +#define E1000_INVM_RECORD_SIZE_IN_BYTES 4 +#define E1000_INVM_VER_FIELD_ONE 0x1FF8 +#define E1000_INVM_VER_FIELD_TWO 0x7FE000 +#define E1000_INVM_IMGTYPE_FIELD 0x1F800000 + +#define E1000_INVM_MAJOR_MASK 0x3F0 +#define E1000_INVM_MINOR_MASK 0xF +#define E1000_INVM_MAJOR_SHIFT 4 + +#define ID_LED_DEFAULT_I210 ((ID_LED_OFF1_ON2 << 8) | \ + (ID_LED_DEF1_DEF2 << 4) | \ + (ID_LED_OFF1_OFF2)) +#define ID_LED_DEFAULT_I210_SERDES ((ID_LED_DEF1_DEF2 << 8) | \ + (ID_LED_DEF1_DEF2 << 4) | \ + (ID_LED_OFF1_ON2)) + +/* NVM offset defaults for i211 device */ +#define NVM_INIT_CTRL_2_DEFAULT_I211 0X7243 +#define NVM_INIT_CTRL_4_DEFAULT_I211 0x00C1 +#define NVM_LED_1_CFG_DEFAULT_I211 0x0184 +#define NVM_LED_0_2_CFG_DEFAULT_I211 0x200C + +/* PLL Defines */ +#define E1000_PCI_PMCSR 0x44 +#define E1000_PCI_PMCSR_D3 0x03 +#define E1000_MAX_PLL_TRIES 5 +#define E1000_PHY_PLL_UNCONF 0xFF +#define E1000_PHY_PLL_FREQ_PAGE 0xFC +#define E1000_PHY_PLL_FREQ_REG 0x000E +#define E1000_INVM_DEFAULT_AL 0x202F +#define E1000_INVM_AUTOLOAD 0x0A +#define E1000_INVM_PLL_WO_VAL 0x0010 + +#endif diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.c b/drivers/net/ethernet/intel/igb/e1000_mac.c new file mode 100644 index 0000000000..caf91c6f52 --- /dev/null +++ b/drivers/net/ethernet/intel/igb/e1000_mac.c @@ -0,0 +1,1685 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2007 - 2018 Intel Corporation. */ + +#include <linux/if_ether.h> +#include <linux/delay.h> +#include <linux/pci.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> + +#include "e1000_mac.h" + +#include "igb.h" + +static s32 igb_set_default_fc(struct e1000_hw *hw); +static void igb_set_fc_watermarks(struct e1000_hw *hw); + +/** + * igb_get_bus_info_pcie - Get PCIe bus information + * @hw: pointer to the HW structure + * + * Determines and stores the system bus information for a particular + * network interface. The following bus information is determined and stored: + * bus speed, bus width, type (PCIe), and PCIe function. + **/ +s32 igb_get_bus_info_pcie(struct e1000_hw *hw) +{ + struct e1000_bus_info *bus = &hw->bus; + s32 ret_val; + u32 reg; + u16 pcie_link_status; + + bus->type = e1000_bus_type_pci_express; + + ret_val = igb_read_pcie_cap_reg(hw, + PCI_EXP_LNKSTA, + &pcie_link_status); + if (ret_val) { + bus->width = e1000_bus_width_unknown; + bus->speed = e1000_bus_speed_unknown; + } else { + switch (pcie_link_status & PCI_EXP_LNKSTA_CLS) { + case PCI_EXP_LNKSTA_CLS_2_5GB: + bus->speed = e1000_bus_speed_2500; + break; + case PCI_EXP_LNKSTA_CLS_5_0GB: + bus->speed = e1000_bus_speed_5000; + break; + default: + bus->speed = e1000_bus_speed_unknown; + break; + } + + bus->width = (enum e1000_bus_width)((pcie_link_status & + PCI_EXP_LNKSTA_NLW) >> + PCI_EXP_LNKSTA_NLW_SHIFT); + } + + reg = rd32(E1000_STATUS); + bus->func = (reg & E1000_STATUS_FUNC_MASK) >> E1000_STATUS_FUNC_SHIFT; + + return 0; +} + +/** + * igb_clear_vfta - Clear VLAN filter table + * @hw: pointer to the HW structure + * + * Clears the register array which contains the VLAN filter table by + * setting all the values to 0. + **/ +void igb_clear_vfta(struct e1000_hw *hw) +{ + u32 offset; + + for (offset = E1000_VLAN_FILTER_TBL_SIZE; offset--;) + hw->mac.ops.write_vfta(hw, offset, 0); +} + +/** + * igb_write_vfta - Write value to VLAN filter table + * @hw: pointer to the HW structure + * @offset: register offset in VLAN filter table + * @value: register value written to VLAN filter table + * + * Writes value at the given offset in the register array which stores + * the VLAN filter table. + **/ +void igb_write_vfta(struct e1000_hw *hw, u32 offset, u32 value) +{ + struct igb_adapter *adapter = hw->back; + + array_wr32(E1000_VFTA, offset, value); + wrfl(); + + adapter->shadow_vfta[offset] = value; +} + +/** + * igb_init_rx_addrs - Initialize receive address's + * @hw: pointer to the HW structure + * @rar_count: receive address registers + * + * Setups the receive address registers by setting the base receive address + * register to the devices MAC address and clearing all the other receive + * address registers to 0. + **/ +void igb_init_rx_addrs(struct e1000_hw *hw, u16 rar_count) +{ + u32 i; + u8 mac_addr[ETH_ALEN] = {0}; + + /* Setup the receive address */ + hw_dbg("Programming MAC Address into RAR[0]\n"); + + hw->mac.ops.rar_set(hw, hw->mac.addr, 0); + + /* Zero out the other (rar_entry_count - 1) receive addresses */ + hw_dbg("Clearing RAR[1-%u]\n", rar_count-1); + for (i = 1; i < rar_count; i++) + hw->mac.ops.rar_set(hw, mac_addr, i); +} + +/** + * igb_find_vlvf_slot - find the VLAN id or the first empty slot + * @hw: pointer to hardware structure + * @vlan: VLAN id to write to VLAN filter + * @vlvf_bypass: skip VLVF if no match is found + * + * return the VLVF index where this VLAN id should be placed + * + **/ +static s32 igb_find_vlvf_slot(struct e1000_hw *hw, u32 vlan, bool vlvf_bypass) +{ + s32 regindex, first_empty_slot; + u32 bits; + + /* short cut the special case */ + if (vlan == 0) + return 0; + + /* if vlvf_bypass is set we don't want to use an empty slot, we + * will simply bypass the VLVF if there are no entries present in the + * VLVF that contain our VLAN + */ + first_empty_slot = vlvf_bypass ? -E1000_ERR_NO_SPACE : 0; + + /* Search for the VLAN id in the VLVF entries. Save off the first empty + * slot found along the way. + * + * pre-decrement loop covering (IXGBE_VLVF_ENTRIES - 1) .. 1 + */ + for (regindex = E1000_VLVF_ARRAY_SIZE; --regindex > 0;) { + bits = rd32(E1000_VLVF(regindex)) & E1000_VLVF_VLANID_MASK; + if (bits == vlan) + return regindex; + if (!first_empty_slot && !bits) + first_empty_slot = regindex; + } + + return first_empty_slot ? : -E1000_ERR_NO_SPACE; +} + +/** + * igb_vfta_set - enable or disable vlan in VLAN filter table + * @hw: pointer to the HW structure + * @vlan: VLAN id to add or remove + * @vind: VMDq output index that maps queue to VLAN id + * @vlan_on: if true add filter, if false remove + * @vlvf_bypass: skip VLVF if no match is found + * + * Sets or clears a bit in the VLAN filter table array based on VLAN id + * and if we are adding or removing the filter + **/ +s32 igb_vfta_set(struct e1000_hw *hw, u32 vlan, u32 vind, + bool vlan_on, bool vlvf_bypass) +{ + struct igb_adapter *adapter = hw->back; + u32 regidx, vfta_delta, vfta, bits; + s32 vlvf_index; + + if ((vlan > 4095) || (vind > 7)) + return -E1000_ERR_PARAM; + + /* this is a 2 part operation - first the VFTA, then the + * VLVF and VLVFB if VT Mode is set + * We don't write the VFTA until we know the VLVF part succeeded. + */ + + /* Part 1 + * The VFTA is a bitstring made up of 128 32-bit registers + * that enable the particular VLAN id, much like the MTA: + * bits[11-5]: which register + * bits[4-0]: which bit in the register + */ + regidx = vlan / 32; + vfta_delta = BIT(vlan % 32); + vfta = adapter->shadow_vfta[regidx]; + + /* vfta_delta represents the difference between the current value + * of vfta and the value we want in the register. Since the diff + * is an XOR mask we can just update vfta using an XOR. + */ + vfta_delta &= vlan_on ? ~vfta : vfta; + vfta ^= vfta_delta; + + /* Part 2 + * If VT Mode is set + * Either vlan_on + * make sure the VLAN is in VLVF + * set the vind bit in the matching VLVFB + * Or !vlan_on + * clear the pool bit and possibly the vind + */ + if (!adapter->vfs_allocated_count) + goto vfta_update; + + vlvf_index = igb_find_vlvf_slot(hw, vlan, vlvf_bypass); + if (vlvf_index < 0) { + if (vlvf_bypass) + goto vfta_update; + return vlvf_index; + } + + bits = rd32(E1000_VLVF(vlvf_index)); + + /* set the pool bit */ + bits |= BIT(E1000_VLVF_POOLSEL_SHIFT + vind); + if (vlan_on) + goto vlvf_update; + + /* clear the pool bit */ + bits ^= BIT(E1000_VLVF_POOLSEL_SHIFT + vind); + + if (!(bits & E1000_VLVF_POOLSEL_MASK)) { + /* Clear VFTA first, then disable VLVF. Otherwise + * we run the risk of stray packets leaking into + * the PF via the default pool + */ + if (vfta_delta) + hw->mac.ops.write_vfta(hw, regidx, vfta); + + /* disable VLVF and clear remaining bit from pool */ + wr32(E1000_VLVF(vlvf_index), 0); + + return 0; + } + + /* If there are still bits set in the VLVFB registers + * for the VLAN ID indicated we need to see if the + * caller is requesting that we clear the VFTA entry bit. + * If the caller has requested that we clear the VFTA + * entry bit but there are still pools/VFs using this VLAN + * ID entry then ignore the request. We're not worried + * about the case where we're turning the VFTA VLAN ID + * entry bit on, only when requested to turn it off as + * there may be multiple pools and/or VFs using the + * VLAN ID entry. In that case we cannot clear the + * VFTA bit until all pools/VFs using that VLAN ID have also + * been cleared. This will be indicated by "bits" being + * zero. + */ + vfta_delta = 0; + +vlvf_update: + /* record pool change and enable VLAN ID if not already enabled */ + wr32(E1000_VLVF(vlvf_index), bits | vlan | E1000_VLVF_VLANID_ENABLE); + +vfta_update: + /* bit was set/cleared before we started */ + if (vfta_delta) + hw->mac.ops.write_vfta(hw, regidx, vfta); + + return 0; +} + +/** + * igb_check_alt_mac_addr - Check for alternate MAC addr + * @hw: pointer to the HW structure + * + * Checks the nvm for an alternate MAC address. An alternate MAC address + * can be setup by pre-boot software and must be treated like a permanent + * address and must override the actual permanent MAC address. If an + * alternate MAC address is found it is saved in the hw struct and + * programmed into RAR0 and the function returns success, otherwise the + * function returns an error. + **/ +s32 igb_check_alt_mac_addr(struct e1000_hw *hw) +{ + u32 i; + s32 ret_val = 0; + u16 offset, nvm_alt_mac_addr_offset, nvm_data; + u8 alt_mac_addr[ETH_ALEN]; + + /* Alternate MAC address is handled by the option ROM for 82580 + * and newer. SW support not required. + */ + if (hw->mac.type >= e1000_82580) + goto out; + + ret_val = hw->nvm.ops.read(hw, NVM_ALT_MAC_ADDR_PTR, 1, + &nvm_alt_mac_addr_offset); + if (ret_val) { + hw_dbg("NVM Read Error\n"); + goto out; + } + + if ((nvm_alt_mac_addr_offset == 0xFFFF) || + (nvm_alt_mac_addr_offset == 0x0000)) + /* There is no Alternate MAC Address */ + goto out; + + if (hw->bus.func == E1000_FUNC_1) + nvm_alt_mac_addr_offset += E1000_ALT_MAC_ADDRESS_OFFSET_LAN1; + if (hw->bus.func == E1000_FUNC_2) + nvm_alt_mac_addr_offset += E1000_ALT_MAC_ADDRESS_OFFSET_LAN2; + + if (hw->bus.func == E1000_FUNC_3) + nvm_alt_mac_addr_offset += E1000_ALT_MAC_ADDRESS_OFFSET_LAN3; + for (i = 0; i < ETH_ALEN; i += 2) { + offset = nvm_alt_mac_addr_offset + (i >> 1); + ret_val = hw->nvm.ops.read(hw, offset, 1, &nvm_data); + if (ret_val) { + hw_dbg("NVM Read Error\n"); + goto out; + } + + alt_mac_addr[i] = (u8)(nvm_data & 0xFF); + alt_mac_addr[i + 1] = (u8)(nvm_data >> 8); + } + + /* if multicast bit is set, the alternate address will not be used */ + if (is_multicast_ether_addr(alt_mac_addr)) { + hw_dbg("Ignoring Alternate Mac Address with MC bit set\n"); + goto out; + } + + /* We have a valid alternate MAC address, and we want to treat it the + * same as the normal permanent MAC address stored by the HW into the + * RAR. Do this by mapping this address into RAR0. + */ + hw->mac.ops.rar_set(hw, alt_mac_addr, 0); + +out: + return ret_val; +} + +/** + * igb_rar_set - Set receive address register + * @hw: pointer to the HW structure + * @addr: pointer to the receive address + * @index: receive address array register + * + * Sets the receive address array register at index to the address passed + * in by addr. + **/ +void igb_rar_set(struct e1000_hw *hw, u8 *addr, u32 index) +{ + u32 rar_low, rar_high; + + /* HW expects these in little endian so we reverse the byte order + * from network order (big endian) to little endian + */ + rar_low = ((u32) addr[0] | + ((u32) addr[1] << 8) | + ((u32) addr[2] << 16) | ((u32) addr[3] << 24)); + + rar_high = ((u32) addr[4] | ((u32) addr[5] << 8)); + + /* If MAC address zero, no need to set the AV bit */ + if (rar_low || rar_high) + rar_high |= E1000_RAH_AV; + + /* Some bridges will combine consecutive 32-bit writes into + * a single burst write, which will malfunction on some parts. + * The flushes avoid this. + */ + wr32(E1000_RAL(index), rar_low); + wrfl(); + wr32(E1000_RAH(index), rar_high); + wrfl(); +} + +/** + * igb_mta_set - Set multicast filter table address + * @hw: pointer to the HW structure + * @hash_value: determines the MTA register and bit to set + * + * The multicast table address is a register array of 32-bit registers. + * The hash_value is used to determine what register the bit is in, the + * current value is read, the new bit is OR'd in and the new value is + * written back into the register. + **/ +void igb_mta_set(struct e1000_hw *hw, u32 hash_value) +{ + u32 hash_bit, hash_reg, mta; + + /* The MTA is a register array of 32-bit registers. It is + * treated like an array of (32*mta_reg_count) bits. We want to + * set bit BitArray[hash_value]. So we figure out what register + * the bit is in, read it, OR in the new bit, then write + * back the new value. The (hw->mac.mta_reg_count - 1) serves as a + * mask to bits 31:5 of the hash value which gives us the + * register we're modifying. The hash bit within that register + * is determined by the lower 5 bits of the hash value. + */ + hash_reg = (hash_value >> 5) & (hw->mac.mta_reg_count - 1); + hash_bit = hash_value & 0x1F; + + mta = array_rd32(E1000_MTA, hash_reg); + + mta |= BIT(hash_bit); + + array_wr32(E1000_MTA, hash_reg, mta); + wrfl(); +} + +/** + * igb_hash_mc_addr - Generate a multicast hash value + * @hw: pointer to the HW structure + * @mc_addr: pointer to a multicast address + * + * Generates a multicast address hash value which is used to determine + * the multicast filter table array address and new table value. See + * igb_mta_set() + **/ +static u32 igb_hash_mc_addr(struct e1000_hw *hw, u8 *mc_addr) +{ + u32 hash_value, hash_mask; + u8 bit_shift = 1; + + /* Register count multiplied by bits per register */ + hash_mask = (hw->mac.mta_reg_count * 32) - 1; + + /* For a mc_filter_type of 0, bit_shift is the number of left-shifts + * where 0xFF would still fall within the hash mask. + */ + while (hash_mask >> bit_shift != 0xFF && bit_shift < 4) + bit_shift++; + + /* The portion of the address that is used for the hash table + * is determined by the mc_filter_type setting. + * The algorithm is such that there is a total of 8 bits of shifting. + * The bit_shift for a mc_filter_type of 0 represents the number of + * left-shifts where the MSB of mc_addr[5] would still fall within + * the hash_mask. Case 0 does this exactly. Since there are a total + * of 8 bits of shifting, then mc_addr[4] will shift right the + * remaining number of bits. Thus 8 - bit_shift. The rest of the + * cases are a variation of this algorithm...essentially raising the + * number of bits to shift mc_addr[5] left, while still keeping the + * 8-bit shifting total. + * + * For example, given the following Destination MAC Address and an + * mta register count of 128 (thus a 4096-bit vector and 0xFFF mask), + * we can see that the bit_shift for case 0 is 4. These are the hash + * values resulting from each mc_filter_type... + * [0] [1] [2] [3] [4] [5] + * 01 AA 00 12 34 56 + * LSB MSB + * + * case 0: hash_value = ((0x34 >> 4) | (0x56 << 4)) & 0xFFF = 0x563 + * case 1: hash_value = ((0x34 >> 3) | (0x56 << 5)) & 0xFFF = 0xAC6 + * case 2: hash_value = ((0x34 >> 2) | (0x56 << 6)) & 0xFFF = 0x163 + * case 3: hash_value = ((0x34 >> 0) | (0x56 << 8)) & 0xFFF = 0x634 + */ + switch (hw->mac.mc_filter_type) { + default: + case 0: + break; + case 1: + bit_shift += 1; + break; + case 2: + bit_shift += 2; + break; + case 3: + bit_shift += 4; + break; + } + + hash_value = hash_mask & (((mc_addr[4] >> (8 - bit_shift)) | + (((u16) mc_addr[5]) << bit_shift))); + + return hash_value; +} + +/** + * igb_i21x_hw_doublecheck - double checks potential HW issue in i21X + * @hw: pointer to the HW structure + * + * Checks if multicast array is wrote correctly + * If not then rewrites again to register + **/ +static void igb_i21x_hw_doublecheck(struct e1000_hw *hw) +{ + int failed_cnt = 3; + bool is_failed; + int i; + + do { + is_failed = false; + for (i = hw->mac.mta_reg_count - 1; i >= 0; i--) { + if (array_rd32(E1000_MTA, i) != hw->mac.mta_shadow[i]) { + is_failed = true; + array_wr32(E1000_MTA, i, hw->mac.mta_shadow[i]); + wrfl(); + } + } + if (is_failed && --failed_cnt <= 0) { + hw_dbg("Failed to update MTA_REGISTER, too many retries"); + break; + } + } while (is_failed); +} + +/** + * igb_update_mc_addr_list - Update Multicast addresses + * @hw: pointer to the HW structure + * @mc_addr_list: array of multicast addresses to program + * @mc_addr_count: number of multicast addresses to program + * + * Updates entire Multicast Table Array. + * The caller must have a packed mc_addr_list of multicast addresses. + **/ +void igb_update_mc_addr_list(struct e1000_hw *hw, + u8 *mc_addr_list, u32 mc_addr_count) +{ + u32 hash_value, hash_bit, hash_reg; + int i; + + /* clear mta_shadow */ + memset(&hw->mac.mta_shadow, 0, sizeof(hw->mac.mta_shadow)); + + /* update mta_shadow from mc_addr_list */ + for (i = 0; (u32) i < mc_addr_count; i++) { + hash_value = igb_hash_mc_addr(hw, mc_addr_list); + + hash_reg = (hash_value >> 5) & (hw->mac.mta_reg_count - 1); + hash_bit = hash_value & 0x1F; + + hw->mac.mta_shadow[hash_reg] |= BIT(hash_bit); + mc_addr_list += (ETH_ALEN); + } + + /* replace the entire MTA table */ + for (i = hw->mac.mta_reg_count - 1; i >= 0; i--) + array_wr32(E1000_MTA, i, hw->mac.mta_shadow[i]); + wrfl(); + if (hw->mac.type == e1000_i210 || hw->mac.type == e1000_i211) + igb_i21x_hw_doublecheck(hw); +} + +/** + * igb_clear_hw_cntrs_base - Clear base hardware counters + * @hw: pointer to the HW structure + * + * Clears the base hardware counters by reading the counter registers. + **/ +void igb_clear_hw_cntrs_base(struct e1000_hw *hw) +{ + rd32(E1000_CRCERRS); + rd32(E1000_SYMERRS); + rd32(E1000_MPC); + rd32(E1000_SCC); + rd32(E1000_ECOL); + rd32(E1000_MCC); + rd32(E1000_LATECOL); + rd32(E1000_COLC); + rd32(E1000_DC); + rd32(E1000_SEC); + rd32(E1000_RLEC); + rd32(E1000_XONRXC); + rd32(E1000_XONTXC); + rd32(E1000_XOFFRXC); + rd32(E1000_XOFFTXC); + rd32(E1000_FCRUC); + rd32(E1000_GPRC); + rd32(E1000_BPRC); + rd32(E1000_MPRC); + rd32(E1000_GPTC); + rd32(E1000_GORCL); + rd32(E1000_GORCH); + rd32(E1000_GOTCL); + rd32(E1000_GOTCH); + rd32(E1000_RNBC); + rd32(E1000_RUC); + rd32(E1000_RFC); + rd32(E1000_ROC); + rd32(E1000_RJC); + rd32(E1000_TORL); + rd32(E1000_TORH); + rd32(E1000_TOTL); + rd32(E1000_TOTH); + rd32(E1000_TPR); + rd32(E1000_TPT); + rd32(E1000_MPTC); + rd32(E1000_BPTC); +} + +/** + * igb_check_for_copper_link - Check for link (Copper) + * @hw: pointer to the HW structure + * + * Checks to see of the link status of the hardware has changed. If a + * change in link status has been detected, then we read the PHY registers + * to get the current speed/duplex if link exists. + **/ +s32 igb_check_for_copper_link(struct e1000_hw *hw) +{ + struct e1000_mac_info *mac = &hw->mac; + s32 ret_val; + bool link; + + /* We only want to go out to the PHY registers to see if Auto-Neg + * has completed and/or if our link status has changed. The + * get_link_status flag is set upon receiving a Link Status + * Change or Rx Sequence Error interrupt. + */ + if (!mac->get_link_status) { + ret_val = 0; + goto out; + } + + /* First we want to see if the MII Status Register reports + * link. If so, then we want to get the current speed/duplex + * of the PHY. + */ + ret_val = igb_phy_has_link(hw, 1, 0, &link); + if (ret_val) + goto out; + + if (!link) + goto out; /* No link detected */ + + mac->get_link_status = false; + + /* Check if there was DownShift, must be checked + * immediately after link-up + */ + igb_check_downshift(hw); + + /* If we are forcing speed/duplex, then we simply return since + * we have already determined whether we have link or not. + */ + if (!mac->autoneg) { + ret_val = -E1000_ERR_CONFIG; + goto out; + } + + /* Auto-Neg is enabled. Auto Speed Detection takes care + * of MAC speed/duplex configuration. So we only need to + * configure Collision Distance in the MAC. + */ + igb_config_collision_dist(hw); + + /* Configure Flow Control now that Auto-Neg has completed. + * First, we need to restore the desired flow control + * settings because we may have had to re-autoneg with a + * different link partner. + */ + ret_val = igb_config_fc_after_link_up(hw); + if (ret_val) + hw_dbg("Error configuring flow control\n"); + +out: + return ret_val; +} + +/** + * igb_setup_link - Setup flow control and link settings + * @hw: pointer to the HW structure + * + * Determines which flow control settings to use, then configures flow + * control. Calls the appropriate media-specific link configuration + * function. Assuming the adapter has a valid link partner, a valid link + * should be established. Assumes the hardware has previously been reset + * and the transmitter and receiver are not enabled. + **/ +s32 igb_setup_link(struct e1000_hw *hw) +{ + s32 ret_val = 0; + + /* In the case of the phy reset being blocked, we already have a link. + * We do not need to set it up again. + */ + if (igb_check_reset_block(hw)) + goto out; + + /* If requested flow control is set to default, set flow control + * based on the EEPROM flow control settings. + */ + if (hw->fc.requested_mode == e1000_fc_default) { + ret_val = igb_set_default_fc(hw); + if (ret_val) + goto out; + } + + /* We want to save off the original Flow Control configuration just + * in case we get disconnected and then reconnected into a different + * hub or switch with different Flow Control capabilities. + */ + hw->fc.current_mode = hw->fc.requested_mode; + + hw_dbg("After fix-ups FlowControl is now = %x\n", hw->fc.current_mode); + + /* Call the necessary media_type subroutine to configure the link. */ + ret_val = hw->mac.ops.setup_physical_interface(hw); + if (ret_val) + goto out; + + /* Initialize the flow control address, type, and PAUSE timer + * registers to their default values. This is done even if flow + * control is disabled, because it does not hurt anything to + * initialize these registers. + */ + hw_dbg("Initializing the Flow Control address, type and timer regs\n"); + wr32(E1000_FCT, FLOW_CONTROL_TYPE); + wr32(E1000_FCAH, FLOW_CONTROL_ADDRESS_HIGH); + wr32(E1000_FCAL, FLOW_CONTROL_ADDRESS_LOW); + + wr32(E1000_FCTTV, hw->fc.pause_time); + + igb_set_fc_watermarks(hw); + +out: + + return ret_val; +} + +/** + * igb_config_collision_dist - Configure collision distance + * @hw: pointer to the HW structure + * + * Configures the collision distance to the default value and is used + * during link setup. Currently no func pointer exists and all + * implementations are handled in the generic version of this function. + **/ +void igb_config_collision_dist(struct e1000_hw *hw) +{ + u32 tctl; + + tctl = rd32(E1000_TCTL); + + tctl &= ~E1000_TCTL_COLD; + tctl |= E1000_COLLISION_DISTANCE << E1000_COLD_SHIFT; + + wr32(E1000_TCTL, tctl); + wrfl(); +} + +/** + * igb_set_fc_watermarks - Set flow control high/low watermarks + * @hw: pointer to the HW structure + * + * Sets the flow control high/low threshold (watermark) registers. If + * flow control XON frame transmission is enabled, then set XON frame + * tansmission as well. + **/ +static void igb_set_fc_watermarks(struct e1000_hw *hw) +{ + u32 fcrtl = 0, fcrth = 0; + + /* Set the flow control receive threshold registers. Normally, + * these registers will be set to a default threshold that may be + * adjusted later by the driver's runtime code. However, if the + * ability to transmit pause frames is not enabled, then these + * registers will be set to 0. + */ + if (hw->fc.current_mode & e1000_fc_tx_pause) { + /* We need to set up the Receive Threshold high and low water + * marks as well as (optionally) enabling the transmission of + * XON frames. + */ + fcrtl = hw->fc.low_water; + if (hw->fc.send_xon) + fcrtl |= E1000_FCRTL_XONE; + + fcrth = hw->fc.high_water; + } + wr32(E1000_FCRTL, fcrtl); + wr32(E1000_FCRTH, fcrth); +} + +/** + * igb_set_default_fc - Set flow control default values + * @hw: pointer to the HW structure + * + * Read the EEPROM for the default values for flow control and store the + * values. + **/ +static s32 igb_set_default_fc(struct e1000_hw *hw) +{ + s32 ret_val = 0; + u16 lan_offset; + u16 nvm_data; + + /* Read and store word 0x0F of the EEPROM. This word contains bits + * that determine the hardware's default PAUSE (flow control) mode, + * a bit that determines whether the HW defaults to enabling or + * disabling auto-negotiation, and the direction of the + * SW defined pins. If there is no SW over-ride of the flow + * control setting, then the variable hw->fc will + * be initialized based on a value in the EEPROM. + */ + if (hw->mac.type == e1000_i350) + lan_offset = NVM_82580_LAN_FUNC_OFFSET(hw->bus.func); + else + lan_offset = 0; + + ret_val = hw->nvm.ops.read(hw, NVM_INIT_CONTROL2_REG + lan_offset, + 1, &nvm_data); + if (ret_val) { + hw_dbg("NVM Read Error\n"); + goto out; + } + + if ((nvm_data & NVM_WORD0F_PAUSE_MASK) == 0) + hw->fc.requested_mode = e1000_fc_none; + else if ((nvm_data & NVM_WORD0F_PAUSE_MASK) == NVM_WORD0F_ASM_DIR) + hw->fc.requested_mode = e1000_fc_tx_pause; + else + hw->fc.requested_mode = e1000_fc_full; + +out: + return ret_val; +} + +/** + * igb_force_mac_fc - Force the MAC's flow control settings + * @hw: pointer to the HW structure + * + * Force the MAC's flow control settings. Sets the TFCE and RFCE bits in the + * device control register to reflect the adapter settings. TFCE and RFCE + * need to be explicitly set by software when a copper PHY is used because + * autonegotiation is managed by the PHY rather than the MAC. Software must + * also configure these bits when link is forced on a fiber connection. + **/ +s32 igb_force_mac_fc(struct e1000_hw *hw) +{ + u32 ctrl; + s32 ret_val = 0; + + ctrl = rd32(E1000_CTRL); + + /* Because we didn't get link via the internal auto-negotiation + * mechanism (we either forced link or we got link via PHY + * auto-neg), we have to manually enable/disable transmit an + * receive flow control. + * + * The "Case" statement below enables/disable flow control + * according to the "hw->fc.current_mode" parameter. + * + * The possible values of the "fc" parameter are: + * 0: Flow control is completely disabled + * 1: Rx flow control is enabled (we can receive pause + * frames but not send pause frames). + * 2: Tx flow control is enabled (we can send pause frames + * but we do not receive pause frames). + * 3: Both Rx and TX flow control (symmetric) is enabled. + * other: No other values should be possible at this point. + */ + hw_dbg("hw->fc.current_mode = %u\n", hw->fc.current_mode); + + switch (hw->fc.current_mode) { + case e1000_fc_none: + ctrl &= (~(E1000_CTRL_TFCE | E1000_CTRL_RFCE)); + break; + case e1000_fc_rx_pause: + ctrl &= (~E1000_CTRL_TFCE); + ctrl |= E1000_CTRL_RFCE; + break; + case e1000_fc_tx_pause: + ctrl &= (~E1000_CTRL_RFCE); + ctrl |= E1000_CTRL_TFCE; + break; + case e1000_fc_full: + ctrl |= (E1000_CTRL_TFCE | E1000_CTRL_RFCE); + break; + default: + hw_dbg("Flow control param set incorrectly\n"); + ret_val = -E1000_ERR_CONFIG; + goto out; + } + + wr32(E1000_CTRL, ctrl); + +out: + return ret_val; +} + +/** + * igb_config_fc_after_link_up - Configures flow control after link + * @hw: pointer to the HW structure + * + * Checks the status of auto-negotiation after link up to ensure that the + * speed and duplex were not forced. If the link needed to be forced, then + * flow control needs to be forced also. If auto-negotiation is enabled + * and did not fail, then we configure flow control based on our link + * partner. + **/ +s32 igb_config_fc_after_link_up(struct e1000_hw *hw) +{ + struct e1000_mac_info *mac = &hw->mac; + s32 ret_val = 0; + u32 pcs_status_reg, pcs_adv_reg, pcs_lp_ability_reg, pcs_ctrl_reg; + u16 mii_status_reg, mii_nway_adv_reg, mii_nway_lp_ability_reg; + u16 speed, duplex; + + /* Check for the case where we have fiber media and auto-neg failed + * so we had to force link. In this case, we need to force the + * configuration of the MAC to match the "fc" parameter. + */ + if (mac->autoneg_failed) { + if (hw->phy.media_type == e1000_media_type_internal_serdes) + ret_val = igb_force_mac_fc(hw); + } else { + if (hw->phy.media_type == e1000_media_type_copper) + ret_val = igb_force_mac_fc(hw); + } + + if (ret_val) { + hw_dbg("Error forcing flow control settings\n"); + goto out; + } + + /* Check for the case where we have copper media and auto-neg is + * enabled. In this case, we need to check and see if Auto-Neg + * has completed, and if so, how the PHY and link partner has + * flow control configured. + */ + if ((hw->phy.media_type == e1000_media_type_copper) && mac->autoneg) { + /* Read the MII Status Register and check to see if AutoNeg + * has completed. We read this twice because this reg has + * some "sticky" (latched) bits. + */ + ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, + &mii_status_reg); + if (ret_val) + goto out; + ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, + &mii_status_reg); + if (ret_val) + goto out; + + if (!(mii_status_reg & MII_SR_AUTONEG_COMPLETE)) { + hw_dbg("Copper PHY and Auto Neg has not completed.\n"); + goto out; + } + + /* The AutoNeg process has completed, so we now need to + * read both the Auto Negotiation Advertisement + * Register (Address 4) and the Auto_Negotiation Base + * Page Ability Register (Address 5) to determine how + * flow control was negotiated. + */ + ret_val = hw->phy.ops.read_reg(hw, PHY_AUTONEG_ADV, + &mii_nway_adv_reg); + if (ret_val) + goto out; + ret_val = hw->phy.ops.read_reg(hw, PHY_LP_ABILITY, + &mii_nway_lp_ability_reg); + if (ret_val) + goto out; + + /* Two bits in the Auto Negotiation Advertisement Register + * (Address 4) and two bits in the Auto Negotiation Base + * Page Ability Register (Address 5) determine flow control + * for both the PHY and the link partner. The following + * table, taken out of the IEEE 802.3ab/D6.0 dated March 25, + * 1999, describes these PAUSE resolution bits and how flow + * control is determined based upon these settings. + * NOTE: DC = Don't Care + * + * LOCAL DEVICE | LINK PARTNER + * PAUSE | ASM_DIR | PAUSE | ASM_DIR | NIC Resolution + *-------|---------|-------|---------|-------------------- + * 0 | 0 | DC | DC | e1000_fc_none + * 0 | 1 | 0 | DC | e1000_fc_none + * 0 | 1 | 1 | 0 | e1000_fc_none + * 0 | 1 | 1 | 1 | e1000_fc_tx_pause + * 1 | 0 | 0 | DC | e1000_fc_none + * 1 | DC | 1 | DC | e1000_fc_full + * 1 | 1 | 0 | 0 | e1000_fc_none + * 1 | 1 | 0 | 1 | e1000_fc_rx_pause + * + * Are both PAUSE bits set to 1? If so, this implies + * Symmetric Flow Control is enabled at both ends. The + * ASM_DIR bits are irrelevant per the spec. + * + * For Symmetric Flow Control: + * + * LOCAL DEVICE | LINK PARTNER + * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result + *-------|---------|-------|---------|-------------------- + * 1 | DC | 1 | DC | E1000_fc_full + * + */ + if ((mii_nway_adv_reg & NWAY_AR_PAUSE) && + (mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE)) { + /* Now we need to check if the user selected RX ONLY + * of pause frames. In this case, we had to advertise + * FULL flow control because we could not advertise RX + * ONLY. Hence, we must now check to see if we need to + * turn OFF the TRANSMISSION of PAUSE frames. + */ + if (hw->fc.requested_mode == e1000_fc_full) { + hw->fc.current_mode = e1000_fc_full; + hw_dbg("Flow Control = FULL.\n"); + } else { + hw->fc.current_mode = e1000_fc_rx_pause; + hw_dbg("Flow Control = RX PAUSE frames only.\n"); + } + } + /* For receiving PAUSE frames ONLY. + * + * LOCAL DEVICE | LINK PARTNER + * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result + *-------|---------|-------|---------|-------------------- + * 0 | 1 | 1 | 1 | e1000_fc_tx_pause + */ + else if (!(mii_nway_adv_reg & NWAY_AR_PAUSE) && + (mii_nway_adv_reg & NWAY_AR_ASM_DIR) && + (mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE) && + (mii_nway_lp_ability_reg & NWAY_LPAR_ASM_DIR)) { + hw->fc.current_mode = e1000_fc_tx_pause; + hw_dbg("Flow Control = TX PAUSE frames only.\n"); + } + /* For transmitting PAUSE frames ONLY. + * + * LOCAL DEVICE | LINK PARTNER + * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result + *-------|---------|-------|---------|-------------------- + * 1 | 1 | 0 | 1 | e1000_fc_rx_pause + */ + else if ((mii_nway_adv_reg & NWAY_AR_PAUSE) && + (mii_nway_adv_reg & NWAY_AR_ASM_DIR) && + !(mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE) && + (mii_nway_lp_ability_reg & NWAY_LPAR_ASM_DIR)) { + hw->fc.current_mode = e1000_fc_rx_pause; + hw_dbg("Flow Control = RX PAUSE frames only.\n"); + } + /* Per the IEEE spec, at this point flow control should be + * disabled. However, we want to consider that we could + * be connected to a legacy switch that doesn't advertise + * desired flow control, but can be forced on the link + * partner. So if we advertised no flow control, that is + * what we will resolve to. If we advertised some kind of + * receive capability (Rx Pause Only or Full Flow Control) + * and the link partner advertised none, we will configure + * ourselves to enable Rx Flow Control only. We can do + * this safely for two reasons: If the link partner really + * didn't want flow control enabled, and we enable Rx, no + * harm done since we won't be receiving any PAUSE frames + * anyway. If the intent on the link partner was to have + * flow control enabled, then by us enabling RX only, we + * can at least receive pause frames and process them. + * This is a good idea because in most cases, since we are + * predominantly a server NIC, more times than not we will + * be asked to delay transmission of packets than asking + * our link partner to pause transmission of frames. + */ + else if ((hw->fc.requested_mode == e1000_fc_none) || + (hw->fc.requested_mode == e1000_fc_tx_pause) || + (hw->fc.strict_ieee)) { + hw->fc.current_mode = e1000_fc_none; + hw_dbg("Flow Control = NONE.\n"); + } else { + hw->fc.current_mode = e1000_fc_rx_pause; + hw_dbg("Flow Control = RX PAUSE frames only.\n"); + } + + /* Now we need to do one last check... If we auto- + * negotiated to HALF DUPLEX, flow control should not be + * enabled per IEEE 802.3 spec. + */ + ret_val = hw->mac.ops.get_speed_and_duplex(hw, &speed, &duplex); + if (ret_val) { + hw_dbg("Error getting link speed and duplex\n"); + goto out; + } + + if (duplex == HALF_DUPLEX) + hw->fc.current_mode = e1000_fc_none; + + /* Now we call a subroutine to actually force the MAC + * controller to use the correct flow control settings. + */ + ret_val = igb_force_mac_fc(hw); + if (ret_val) { + hw_dbg("Error forcing flow control settings\n"); + goto out; + } + } + /* Check for the case where we have SerDes media and auto-neg is + * enabled. In this case, we need to check and see if Auto-Neg + * has completed, and if so, how the PHY and link partner has + * flow control configured. + */ + if ((hw->phy.media_type == e1000_media_type_internal_serdes) + && mac->autoneg) { + /* Read the PCS_LSTS and check to see if AutoNeg + * has completed. + */ + pcs_status_reg = rd32(E1000_PCS_LSTAT); + + if (!(pcs_status_reg & E1000_PCS_LSTS_AN_COMPLETE)) { + hw_dbg("PCS Auto Neg has not completed.\n"); + return ret_val; + } + + /* The AutoNeg process has completed, so we now need to + * read both the Auto Negotiation Advertisement + * Register (PCS_ANADV) and the Auto_Negotiation Base + * Page Ability Register (PCS_LPAB) to determine how + * flow control was negotiated. + */ + pcs_adv_reg = rd32(E1000_PCS_ANADV); + pcs_lp_ability_reg = rd32(E1000_PCS_LPAB); + + /* Two bits in the Auto Negotiation Advertisement Register + * (PCS_ANADV) and two bits in the Auto Negotiation Base + * Page Ability Register (PCS_LPAB) determine flow control + * for both the PHY and the link partner. The following + * table, taken out of the IEEE 802.3ab/D6.0 dated March 25, + * 1999, describes these PAUSE resolution bits and how flow + * control is determined based upon these settings. + * NOTE: DC = Don't Care + * + * LOCAL DEVICE | LINK PARTNER + * PAUSE | ASM_DIR | PAUSE | ASM_DIR | NIC Resolution + *-------|---------|-------|---------|-------------------- + * 0 | 0 | DC | DC | e1000_fc_none + * 0 | 1 | 0 | DC | e1000_fc_none + * 0 | 1 | 1 | 0 | e1000_fc_none + * 0 | 1 | 1 | 1 | e1000_fc_tx_pause + * 1 | 0 | 0 | DC | e1000_fc_none + * 1 | DC | 1 | DC | e1000_fc_full + * 1 | 1 | 0 | 0 | e1000_fc_none + * 1 | 1 | 0 | 1 | e1000_fc_rx_pause + * + * Are both PAUSE bits set to 1? If so, this implies + * Symmetric Flow Control is enabled at both ends. The + * ASM_DIR bits are irrelevant per the spec. + * + * For Symmetric Flow Control: + * + * LOCAL DEVICE | LINK PARTNER + * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result + *-------|---------|-------|---------|-------------------- + * 1 | DC | 1 | DC | e1000_fc_full + * + */ + if ((pcs_adv_reg & E1000_TXCW_PAUSE) && + (pcs_lp_ability_reg & E1000_TXCW_PAUSE)) { + /* Now we need to check if the user selected Rx ONLY + * of pause frames. In this case, we had to advertise + * FULL flow control because we could not advertise Rx + * ONLY. Hence, we must now check to see if we need to + * turn OFF the TRANSMISSION of PAUSE frames. + */ + if (hw->fc.requested_mode == e1000_fc_full) { + hw->fc.current_mode = e1000_fc_full; + hw_dbg("Flow Control = FULL.\n"); + } else { + hw->fc.current_mode = e1000_fc_rx_pause; + hw_dbg("Flow Control = Rx PAUSE frames only.\n"); + } + } + /* For receiving PAUSE frames ONLY. + * + * LOCAL DEVICE | LINK PARTNER + * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result + *-------|---------|-------|---------|-------------------- + * 0 | 1 | 1 | 1 | e1000_fc_tx_pause + */ + else if (!(pcs_adv_reg & E1000_TXCW_PAUSE) && + (pcs_adv_reg & E1000_TXCW_ASM_DIR) && + (pcs_lp_ability_reg & E1000_TXCW_PAUSE) && + (pcs_lp_ability_reg & E1000_TXCW_ASM_DIR)) { + hw->fc.current_mode = e1000_fc_tx_pause; + hw_dbg("Flow Control = Tx PAUSE frames only.\n"); + } + /* For transmitting PAUSE frames ONLY. + * + * LOCAL DEVICE | LINK PARTNER + * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result + *-------|---------|-------|---------|-------------------- + * 1 | 1 | 0 | 1 | e1000_fc_rx_pause + */ + else if ((pcs_adv_reg & E1000_TXCW_PAUSE) && + (pcs_adv_reg & E1000_TXCW_ASM_DIR) && + !(pcs_lp_ability_reg & E1000_TXCW_PAUSE) && + (pcs_lp_ability_reg & E1000_TXCW_ASM_DIR)) { + hw->fc.current_mode = e1000_fc_rx_pause; + hw_dbg("Flow Control = Rx PAUSE frames only.\n"); + } else { + /* Per the IEEE spec, at this point flow control + * should be disabled. + */ + hw->fc.current_mode = e1000_fc_none; + hw_dbg("Flow Control = NONE.\n"); + } + + /* Now we call a subroutine to actually force the MAC + * controller to use the correct flow control settings. + */ + pcs_ctrl_reg = rd32(E1000_PCS_LCTL); + pcs_ctrl_reg |= E1000_PCS_LCTL_FORCE_FCTRL; + wr32(E1000_PCS_LCTL, pcs_ctrl_reg); + + ret_val = igb_force_mac_fc(hw); + if (ret_val) { + hw_dbg("Error forcing flow control settings\n"); + return ret_val; + } + } + +out: + return ret_val; +} + +/** + * igb_get_speed_and_duplex_copper - Retrieve current speed/duplex + * @hw: pointer to the HW structure + * @speed: stores the current speed + * @duplex: stores the current duplex + * + * Read the status register for the current speed/duplex and store the current + * speed and duplex for copper connections. + **/ +s32 igb_get_speed_and_duplex_copper(struct e1000_hw *hw, u16 *speed, + u16 *duplex) +{ + u32 status; + + status = rd32(E1000_STATUS); + if (status & E1000_STATUS_SPEED_1000) { + *speed = SPEED_1000; + hw_dbg("1000 Mbs, "); + } else if (status & E1000_STATUS_SPEED_100) { + *speed = SPEED_100; + hw_dbg("100 Mbs, "); + } else { + *speed = SPEED_10; + hw_dbg("10 Mbs, "); + } + + if (status & E1000_STATUS_FD) { + *duplex = FULL_DUPLEX; + hw_dbg("Full Duplex\n"); + } else { + *duplex = HALF_DUPLEX; + hw_dbg("Half Duplex\n"); + } + + return 0; +} + +/** + * igb_get_hw_semaphore - Acquire hardware semaphore + * @hw: pointer to the HW structure + * + * Acquire the HW semaphore to access the PHY or NVM + **/ +s32 igb_get_hw_semaphore(struct e1000_hw *hw) +{ + u32 swsm; + s32 ret_val = 0; + s32 timeout = hw->nvm.word_size + 1; + s32 i = 0; + + /* Get the SW semaphore */ + while (i < timeout) { + swsm = rd32(E1000_SWSM); + if (!(swsm & E1000_SWSM_SMBI)) + break; + + udelay(50); + i++; + } + + if (i == timeout) { + hw_dbg("Driver can't access device - SMBI bit is set.\n"); + ret_val = -E1000_ERR_NVM; + goto out; + } + + /* Get the FW semaphore. */ + for (i = 0; i < timeout; i++) { + swsm = rd32(E1000_SWSM); + wr32(E1000_SWSM, swsm | E1000_SWSM_SWESMBI); + + /* Semaphore acquired if bit latched */ + if (rd32(E1000_SWSM) & E1000_SWSM_SWESMBI) + break; + + udelay(50); + } + + if (i == timeout) { + /* Release semaphores */ + igb_put_hw_semaphore(hw); + hw_dbg("Driver can't access the NVM\n"); + ret_val = -E1000_ERR_NVM; + goto out; + } + +out: + return ret_val; +} + +/** + * igb_put_hw_semaphore - Release hardware semaphore + * @hw: pointer to the HW structure + * + * Release hardware semaphore used to access the PHY or NVM + **/ +void igb_put_hw_semaphore(struct e1000_hw *hw) +{ + u32 swsm; + + swsm = rd32(E1000_SWSM); + + swsm &= ~(E1000_SWSM_SMBI | E1000_SWSM_SWESMBI); + + wr32(E1000_SWSM, swsm); +} + +/** + * igb_get_auto_rd_done - Check for auto read completion + * @hw: pointer to the HW structure + * + * Check EEPROM for Auto Read done bit. + **/ +s32 igb_get_auto_rd_done(struct e1000_hw *hw) +{ + s32 i = 0; + s32 ret_val = 0; + + + while (i < AUTO_READ_DONE_TIMEOUT) { + if (rd32(E1000_EECD) & E1000_EECD_AUTO_RD) + break; + usleep_range(1000, 2000); + i++; + } + + if (i == AUTO_READ_DONE_TIMEOUT) { + hw_dbg("Auto read by HW from NVM has not completed.\n"); + ret_val = -E1000_ERR_RESET; + goto out; + } + +out: + return ret_val; +} + +/** + * igb_valid_led_default - Verify a valid default LED config + * @hw: pointer to the HW structure + * @data: pointer to the NVM (EEPROM) + * + * Read the EEPROM for the current default LED configuration. If the + * LED configuration is not valid, set to a valid LED configuration. + **/ +static s32 igb_valid_led_default(struct e1000_hw *hw, u16 *data) +{ + s32 ret_val; + + ret_val = hw->nvm.ops.read(hw, NVM_ID_LED_SETTINGS, 1, data); + if (ret_val) { + hw_dbg("NVM Read Error\n"); + goto out; + } + + if (*data == ID_LED_RESERVED_0000 || *data == ID_LED_RESERVED_FFFF) { + switch (hw->phy.media_type) { + case e1000_media_type_internal_serdes: + *data = ID_LED_DEFAULT_82575_SERDES; + break; + case e1000_media_type_copper: + default: + *data = ID_LED_DEFAULT; + break; + } + } +out: + return ret_val; +} + +/** + * igb_id_led_init - + * @hw: pointer to the HW structure + * + **/ +s32 igb_id_led_init(struct e1000_hw *hw) +{ + struct e1000_mac_info *mac = &hw->mac; + s32 ret_val; + const u32 ledctl_mask = 0x000000FF; + const u32 ledctl_on = E1000_LEDCTL_MODE_LED_ON; + const u32 ledctl_off = E1000_LEDCTL_MODE_LED_OFF; + u16 data, i, temp; + const u16 led_mask = 0x0F; + + /* i210 and i211 devices have different LED mechanism */ + if ((hw->mac.type == e1000_i210) || + (hw->mac.type == e1000_i211)) + ret_val = igb_valid_led_default_i210(hw, &data); + else + ret_val = igb_valid_led_default(hw, &data); + + if (ret_val) + goto out; + + mac->ledctl_default = rd32(E1000_LEDCTL); + mac->ledctl_mode1 = mac->ledctl_default; + mac->ledctl_mode2 = mac->ledctl_default; + + for (i = 0; i < 4; i++) { + temp = (data >> (i << 2)) & led_mask; + switch (temp) { + case ID_LED_ON1_DEF2: + case ID_LED_ON1_ON2: + case ID_LED_ON1_OFF2: + mac->ledctl_mode1 &= ~(ledctl_mask << (i << 3)); + mac->ledctl_mode1 |= ledctl_on << (i << 3); + break; + case ID_LED_OFF1_DEF2: + case ID_LED_OFF1_ON2: + case ID_LED_OFF1_OFF2: + mac->ledctl_mode1 &= ~(ledctl_mask << (i << 3)); + mac->ledctl_mode1 |= ledctl_off << (i << 3); + break; + default: + /* Do nothing */ + break; + } + switch (temp) { + case ID_LED_DEF1_ON2: + case ID_LED_ON1_ON2: + case ID_LED_OFF1_ON2: + mac->ledctl_mode2 &= ~(ledctl_mask << (i << 3)); + mac->ledctl_mode2 |= ledctl_on << (i << 3); + break; + case ID_LED_DEF1_OFF2: + case ID_LED_ON1_OFF2: + case ID_LED_OFF1_OFF2: + mac->ledctl_mode2 &= ~(ledctl_mask << (i << 3)); + mac->ledctl_mode2 |= ledctl_off << (i << 3); + break; + default: + /* Do nothing */ + break; + } + } + +out: + return ret_val; +} + +/** + * igb_cleanup_led - Set LED config to default operation + * @hw: pointer to the HW structure + * + * Remove the current LED configuration and set the LED configuration + * to the default value, saved from the EEPROM. + **/ +s32 igb_cleanup_led(struct e1000_hw *hw) +{ + wr32(E1000_LEDCTL, hw->mac.ledctl_default); + return 0; +} + +/** + * igb_blink_led - Blink LED + * @hw: pointer to the HW structure + * + * Blink the led's which are set to be on. + **/ +s32 igb_blink_led(struct e1000_hw *hw) +{ + u32 ledctl_blink = 0; + u32 i; + + if (hw->phy.media_type == e1000_media_type_fiber) { + /* always blink LED0 for PCI-E fiber */ + ledctl_blink = E1000_LEDCTL_LED0_BLINK | + (E1000_LEDCTL_MODE_LED_ON << E1000_LEDCTL_LED0_MODE_SHIFT); + } else { + /* Set the blink bit for each LED that's "on" (0x0E) + * (or "off" if inverted) in ledctl_mode2. The blink + * logic in hardware only works when mode is set to "on" + * so it must be changed accordingly when the mode is + * "off" and inverted. + */ + ledctl_blink = hw->mac.ledctl_mode2; + for (i = 0; i < 32; i += 8) { + u32 mode = (hw->mac.ledctl_mode2 >> i) & + E1000_LEDCTL_LED0_MODE_MASK; + u32 led_default = hw->mac.ledctl_default >> i; + + if ((!(led_default & E1000_LEDCTL_LED0_IVRT) && + (mode == E1000_LEDCTL_MODE_LED_ON)) || + ((led_default & E1000_LEDCTL_LED0_IVRT) && + (mode == E1000_LEDCTL_MODE_LED_OFF))) { + ledctl_blink &= + ~(E1000_LEDCTL_LED0_MODE_MASK << i); + ledctl_blink |= (E1000_LEDCTL_LED0_BLINK | + E1000_LEDCTL_MODE_LED_ON) << i; + } + } + } + + wr32(E1000_LEDCTL, ledctl_blink); + + return 0; +} + +/** + * igb_led_off - Turn LED off + * @hw: pointer to the HW structure + * + * Turn LED off. + **/ +s32 igb_led_off(struct e1000_hw *hw) +{ + switch (hw->phy.media_type) { + case e1000_media_type_copper: + wr32(E1000_LEDCTL, hw->mac.ledctl_mode1); + break; + default: + break; + } + + return 0; +} + +/** + * igb_disable_pcie_master - Disables PCI-express master access + * @hw: pointer to the HW structure + * + * Returns 0 (0) if successful, else returns -10 + * (-E1000_ERR_MASTER_REQUESTS_PENDING) if master disable bit has not caused + * the master requests to be disabled. + * + * Disables PCI-Express master access and verifies there are no pending + * requests. + **/ +s32 igb_disable_pcie_master(struct e1000_hw *hw) +{ + u32 ctrl; + s32 timeout = MASTER_DISABLE_TIMEOUT; + s32 ret_val = 0; + + if (hw->bus.type != e1000_bus_type_pci_express) + goto out; + + ctrl = rd32(E1000_CTRL); + ctrl |= E1000_CTRL_GIO_MASTER_DISABLE; + wr32(E1000_CTRL, ctrl); + + while (timeout) { + if (!(rd32(E1000_STATUS) & + E1000_STATUS_GIO_MASTER_ENABLE)) + break; + udelay(100); + timeout--; + } + + if (!timeout) { + hw_dbg("Master requests are pending.\n"); + ret_val = -E1000_ERR_MASTER_REQUESTS_PENDING; + goto out; + } + +out: + return ret_val; +} + +/** + * igb_validate_mdi_setting - Verify MDI/MDIx settings + * @hw: pointer to the HW structure + * + * Verify that when not using auto-negotitation that MDI/MDIx is correctly + * set, which is forced to MDI mode only. + **/ +s32 igb_validate_mdi_setting(struct e1000_hw *hw) +{ + s32 ret_val = 0; + + /* All MDI settings are supported on 82580 and newer. */ + if (hw->mac.type >= e1000_82580) + goto out; + + if (!hw->mac.autoneg && (hw->phy.mdix == 0 || hw->phy.mdix == 3)) { + hw_dbg("Invalid MDI setting detected\n"); + hw->phy.mdix = 1; + ret_val = -E1000_ERR_CONFIG; + goto out; + } + +out: + return ret_val; +} + +/** + * igb_write_8bit_ctrl_reg - Write a 8bit CTRL register + * @hw: pointer to the HW structure + * @reg: 32bit register offset such as E1000_SCTL + * @offset: register offset to write to + * @data: data to write at register offset + * + * Writes an address/data control type register. There are several of these + * and they all have the format address << 8 | data and bit 31 is polled for + * completion. + **/ +s32 igb_write_8bit_ctrl_reg(struct e1000_hw *hw, u32 reg, + u32 offset, u8 data) +{ + u32 i, regvalue = 0; + s32 ret_val = 0; + + /* Set up the address and data */ + regvalue = ((u32)data) | (offset << E1000_GEN_CTL_ADDRESS_SHIFT); + wr32(reg, regvalue); + + /* Poll the ready bit to see if the MDI read completed */ + for (i = 0; i < E1000_GEN_POLL_TIMEOUT; i++) { + udelay(5); + regvalue = rd32(reg); + if (regvalue & E1000_GEN_CTL_READY) + break; + } + if (!(regvalue & E1000_GEN_CTL_READY)) { + hw_dbg("Reg %08x did not indicate ready\n", reg); + ret_val = -E1000_ERR_PHY; + goto out; + } + +out: + return ret_val; +} + +/** + * igb_enable_mng_pass_thru - Enable processing of ARP's + * @hw: pointer to the HW structure + * + * Verifies the hardware needs to leave interface enabled so that frames can + * be directed to and from the management interface. + **/ +bool igb_enable_mng_pass_thru(struct e1000_hw *hw) +{ + u32 manc; + u32 fwsm, factps; + bool ret_val = false; + + if (!hw->mac.asf_firmware_present) + goto out; + + manc = rd32(E1000_MANC); + + if (!(manc & E1000_MANC_RCV_TCO_EN)) + goto out; + + if (hw->mac.arc_subsystem_valid) { + fwsm = rd32(E1000_FWSM); + factps = rd32(E1000_FACTPS); + + if (!(factps & E1000_FACTPS_MNGCG) && + ((fwsm & E1000_FWSM_MODE_MASK) == + (e1000_mng_mode_pt << E1000_FWSM_MODE_SHIFT))) { + ret_val = true; + goto out; + } + } else { + if ((manc & E1000_MANC_SMBUS_EN) && + !(manc & E1000_MANC_ASF_EN)) { + ret_val = true; + goto out; + } + } + +out: + return ret_val; +} diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.h b/drivers/net/ethernet/intel/igb/e1000_mac.h new file mode 100644 index 0000000000..6e110f28f9 --- /dev/null +++ b/drivers/net/ethernet/intel/igb/e1000_mac.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ + +#ifndef _E1000_MAC_H_ +#define _E1000_MAC_H_ + +#include "e1000_hw.h" + +#include "e1000_phy.h" +#include "e1000_nvm.h" +#include "e1000_defines.h" +#include "e1000_i210.h" + +/* Functions that should not be called directly from drivers but can be used + * by other files in this 'shared code' + */ +s32 igb_blink_led(struct e1000_hw *hw); +s32 igb_check_for_copper_link(struct e1000_hw *hw); +s32 igb_cleanup_led(struct e1000_hw *hw); +s32 igb_config_fc_after_link_up(struct e1000_hw *hw); +s32 igb_disable_pcie_master(struct e1000_hw *hw); +s32 igb_force_mac_fc(struct e1000_hw *hw); +s32 igb_get_auto_rd_done(struct e1000_hw *hw); +s32 igb_get_bus_info_pcie(struct e1000_hw *hw); +s32 igb_get_hw_semaphore(struct e1000_hw *hw); +s32 igb_get_speed_and_duplex_copper(struct e1000_hw *hw, u16 *speed, + u16 *duplex); +s32 igb_id_led_init(struct e1000_hw *hw); +s32 igb_led_off(struct e1000_hw *hw); +void igb_update_mc_addr_list(struct e1000_hw *hw, + u8 *mc_addr_list, u32 mc_addr_count); +s32 igb_setup_link(struct e1000_hw *hw); +s32 igb_validate_mdi_setting(struct e1000_hw *hw); +s32 igb_write_8bit_ctrl_reg(struct e1000_hw *hw, u32 reg, + u32 offset, u8 data); + +void igb_clear_hw_cntrs_base(struct e1000_hw *hw); +void igb_clear_vfta(struct e1000_hw *hw); +void igb_write_vfta(struct e1000_hw *hw, u32 offset, u32 value); +s32 igb_vfta_set(struct e1000_hw *hw, u32 vid, u32 vind, + bool vlan_on, bool vlvf_bypass); +void igb_config_collision_dist(struct e1000_hw *hw); +void igb_init_rx_addrs(struct e1000_hw *hw, u16 rar_count); +void igb_mta_set(struct e1000_hw *hw, u32 hash_value); +void igb_put_hw_semaphore(struct e1000_hw *hw); +void igb_rar_set(struct e1000_hw *hw, u8 *addr, u32 index); +s32 igb_check_alt_mac_addr(struct e1000_hw *hw); + +bool igb_enable_mng_pass_thru(struct e1000_hw *hw); + +enum e1000_mng_mode { + e1000_mng_mode_none = 0, + e1000_mng_mode_asf, + e1000_mng_mode_pt, + e1000_mng_mode_ipmi, + e1000_mng_mode_host_if_only +}; + +#define E1000_FACTPS_MNGCG 0x20000000 + +#define E1000_FWSM_MODE_MASK 0xE +#define E1000_FWSM_MODE_SHIFT 1 + +#define E1000_MNG_DHCP_COOKIE_STATUS_VLAN 0x2 + +void e1000_init_function_pointers_82575(struct e1000_hw *hw); + +#endif diff --git a/drivers/net/ethernet/intel/igb/e1000_mbx.c b/drivers/net/ethernet/intel/igb/e1000_mbx.c new file mode 100644 index 0000000000..29383112bc --- /dev/null +++ b/drivers/net/ethernet/intel/igb/e1000_mbx.c @@ -0,0 +1,475 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2007 - 2018 Intel Corporation. */ + +#include "e1000_mbx.h" + +/** + * igb_read_mbx - Reads a message from the mailbox + * @hw: pointer to the HW structure + * @msg: The message buffer + * @size: Length of buffer + * @mbx_id: id of mailbox to read + * @unlock: skip locking or not + * + * returns SUCCESS if it successfully read message from buffer + **/ +s32 igb_read_mbx(struct e1000_hw *hw, u32 *msg, u16 size, u16 mbx_id, + bool unlock) +{ + struct e1000_mbx_info *mbx = &hw->mbx; + s32 ret_val = -E1000_ERR_MBX; + + /* limit read to size of mailbox */ + if (size > mbx->size) + size = mbx->size; + + if (mbx->ops.read) + ret_val = mbx->ops.read(hw, msg, size, mbx_id, unlock); + + return ret_val; +} + +/** + * igb_write_mbx - Write a message to the mailbox + * @hw: pointer to the HW structure + * @msg: The message buffer + * @size: Length of buffer + * @mbx_id: id of mailbox to write + * + * returns SUCCESS if it successfully copied message into the buffer + **/ +s32 igb_write_mbx(struct e1000_hw *hw, u32 *msg, u16 size, u16 mbx_id) +{ + struct e1000_mbx_info *mbx = &hw->mbx; + s32 ret_val = 0; + + if (size > mbx->size) + ret_val = -E1000_ERR_MBX; + + else if (mbx->ops.write) + ret_val = mbx->ops.write(hw, msg, size, mbx_id); + + return ret_val; +} + +/** + * igb_check_for_msg - checks to see if someone sent us mail + * @hw: pointer to the HW structure + * @mbx_id: id of mailbox to check + * + * returns SUCCESS if the Status bit was found or else ERR_MBX + **/ +s32 igb_check_for_msg(struct e1000_hw *hw, u16 mbx_id) +{ + struct e1000_mbx_info *mbx = &hw->mbx; + s32 ret_val = -E1000_ERR_MBX; + + if (mbx->ops.check_for_msg) + ret_val = mbx->ops.check_for_msg(hw, mbx_id); + + return ret_val; +} + +/** + * igb_check_for_ack - checks to see if someone sent us ACK + * @hw: pointer to the HW structure + * @mbx_id: id of mailbox to check + * + * returns SUCCESS if the Status bit was found or else ERR_MBX + **/ +s32 igb_check_for_ack(struct e1000_hw *hw, u16 mbx_id) +{ + struct e1000_mbx_info *mbx = &hw->mbx; + s32 ret_val = -E1000_ERR_MBX; + + if (mbx->ops.check_for_ack) + ret_val = mbx->ops.check_for_ack(hw, mbx_id); + + return ret_val; +} + +/** + * igb_check_for_rst - checks to see if other side has reset + * @hw: pointer to the HW structure + * @mbx_id: id of mailbox to check + * + * returns SUCCESS if the Status bit was found or else ERR_MBX + **/ +s32 igb_check_for_rst(struct e1000_hw *hw, u16 mbx_id) +{ + struct e1000_mbx_info *mbx = &hw->mbx; + s32 ret_val = -E1000_ERR_MBX; + + if (mbx->ops.check_for_rst) + ret_val = mbx->ops.check_for_rst(hw, mbx_id); + + return ret_val; +} + +/** + * igb_unlock_mbx - unlock the mailbox + * @hw: pointer to the HW structure + * @mbx_id: id of mailbox to check + * + * returns SUCCESS if the mailbox was unlocked or else ERR_MBX + **/ +s32 igb_unlock_mbx(struct e1000_hw *hw, u16 mbx_id) +{ + struct e1000_mbx_info *mbx = &hw->mbx; + s32 ret_val = -E1000_ERR_MBX; + + if (mbx->ops.unlock) + ret_val = mbx->ops.unlock(hw, mbx_id); + + return ret_val; +} + +/** + * igb_poll_for_msg - Wait for message notification + * @hw: pointer to the HW structure + * @mbx_id: id of mailbox to write + * + * returns SUCCESS if it successfully received a message notification + **/ +static s32 igb_poll_for_msg(struct e1000_hw *hw, u16 mbx_id) +{ + struct e1000_mbx_info *mbx = &hw->mbx; + int countdown = mbx->timeout; + + if (!countdown || !mbx->ops.check_for_msg) + goto out; + + while (countdown && mbx->ops.check_for_msg(hw, mbx_id)) { + countdown--; + if (!countdown) + break; + udelay(mbx->usec_delay); + } + + /* if we failed, all future posted messages fail until reset */ + if (!countdown) + mbx->timeout = 0; +out: + return countdown ? 0 : -E1000_ERR_MBX; +} + +/** + * igb_poll_for_ack - Wait for message acknowledgement + * @hw: pointer to the HW structure + * @mbx_id: id of mailbox to write + * + * returns SUCCESS if it successfully received a message acknowledgement + **/ +static s32 igb_poll_for_ack(struct e1000_hw *hw, u16 mbx_id) +{ + struct e1000_mbx_info *mbx = &hw->mbx; + int countdown = mbx->timeout; + + if (!countdown || !mbx->ops.check_for_ack) + goto out; + + while (countdown && mbx->ops.check_for_ack(hw, mbx_id)) { + countdown--; + if (!countdown) + break; + udelay(mbx->usec_delay); + } + + /* if we failed, all future posted messages fail until reset */ + if (!countdown) + mbx->timeout = 0; +out: + return countdown ? 0 : -E1000_ERR_MBX; +} + +/** + * igb_read_posted_mbx - Wait for message notification and receive message + * @hw: pointer to the HW structure + * @msg: The message buffer + * @size: Length of buffer + * @mbx_id: id of mailbox to write + * + * returns SUCCESS if it successfully received a message notification and + * copied it into the receive buffer. + **/ +static s32 igb_read_posted_mbx(struct e1000_hw *hw, u32 *msg, u16 size, + u16 mbx_id) +{ + struct e1000_mbx_info *mbx = &hw->mbx; + s32 ret_val = -E1000_ERR_MBX; + + if (!mbx->ops.read) + goto out; + + ret_val = igb_poll_for_msg(hw, mbx_id); + + if (!ret_val) + ret_val = mbx->ops.read(hw, msg, size, mbx_id, true); +out: + return ret_val; +} + +/** + * igb_write_posted_mbx - Write a message to the mailbox, wait for ack + * @hw: pointer to the HW structure + * @msg: The message buffer + * @size: Length of buffer + * @mbx_id: id of mailbox to write + * + * returns SUCCESS if it successfully copied message into the buffer and + * received an ack to that message within delay * timeout period + **/ +static s32 igb_write_posted_mbx(struct e1000_hw *hw, u32 *msg, u16 size, + u16 mbx_id) +{ + struct e1000_mbx_info *mbx = &hw->mbx; + s32 ret_val = -E1000_ERR_MBX; + + /* exit if either we can't write or there isn't a defined timeout */ + if (!mbx->ops.write || !mbx->timeout) + goto out; + + /* send msg */ + ret_val = mbx->ops.write(hw, msg, size, mbx_id); + + /* if msg sent wait until we receive an ack */ + if (!ret_val) + ret_val = igb_poll_for_ack(hw, mbx_id); +out: + return ret_val; +} + +static s32 igb_check_for_bit_pf(struct e1000_hw *hw, u32 mask) +{ + u32 mbvficr = rd32(E1000_MBVFICR); + s32 ret_val = -E1000_ERR_MBX; + + if (mbvficr & mask) { + ret_val = 0; + wr32(E1000_MBVFICR, mask); + } + + return ret_val; +} + +/** + * igb_check_for_msg_pf - checks to see if the VF has sent mail + * @hw: pointer to the HW structure + * @vf_number: the VF index + * + * returns SUCCESS if the VF has set the Status bit or else ERR_MBX + **/ +static s32 igb_check_for_msg_pf(struct e1000_hw *hw, u16 vf_number) +{ + s32 ret_val = -E1000_ERR_MBX; + + if (!igb_check_for_bit_pf(hw, E1000_MBVFICR_VFREQ_VF1 << vf_number)) { + ret_val = 0; + hw->mbx.stats.reqs++; + } + + return ret_val; +} + +/** + * igb_check_for_ack_pf - checks to see if the VF has ACKed + * @hw: pointer to the HW structure + * @vf_number: the VF index + * + * returns SUCCESS if the VF has set the Status bit or else ERR_MBX + **/ +static s32 igb_check_for_ack_pf(struct e1000_hw *hw, u16 vf_number) +{ + s32 ret_val = -E1000_ERR_MBX; + + if (!igb_check_for_bit_pf(hw, E1000_MBVFICR_VFACK_VF1 << vf_number)) { + ret_val = 0; + hw->mbx.stats.acks++; + } + + return ret_val; +} + +/** + * igb_check_for_rst_pf - checks to see if the VF has reset + * @hw: pointer to the HW structure + * @vf_number: the VF index + * + * returns SUCCESS if the VF has set the Status bit or else ERR_MBX + **/ +static s32 igb_check_for_rst_pf(struct e1000_hw *hw, u16 vf_number) +{ + u32 vflre = rd32(E1000_VFLRE); + s32 ret_val = -E1000_ERR_MBX; + + if (vflre & BIT(vf_number)) { + ret_val = 0; + wr32(E1000_VFLRE, BIT(vf_number)); + hw->mbx.stats.rsts++; + } + + return ret_val; +} + +/** + * igb_obtain_mbx_lock_pf - obtain mailbox lock + * @hw: pointer to the HW structure + * @vf_number: the VF index + * + * return SUCCESS if we obtained the mailbox lock + **/ +static s32 igb_obtain_mbx_lock_pf(struct e1000_hw *hw, u16 vf_number) +{ + s32 ret_val = -E1000_ERR_MBX; + u32 p2v_mailbox; + int count = 10; + + do { + /* Take ownership of the buffer */ + wr32(E1000_P2VMAILBOX(vf_number), E1000_P2VMAILBOX_PFU); + + /* reserve mailbox for vf use */ + p2v_mailbox = rd32(E1000_P2VMAILBOX(vf_number)); + if (p2v_mailbox & E1000_P2VMAILBOX_PFU) { + ret_val = 0; + break; + } + udelay(1000); + } while (count-- > 0); + + return ret_val; +} + +/** + * igb_release_mbx_lock_pf - release mailbox lock + * @hw: pointer to the HW structure + * @vf_number: the VF index + * + * return SUCCESS if we released the mailbox lock + **/ +static s32 igb_release_mbx_lock_pf(struct e1000_hw *hw, u16 vf_number) +{ + u32 p2v_mailbox; + + /* drop PF lock of mailbox, if set */ + p2v_mailbox = rd32(E1000_P2VMAILBOX(vf_number)); + if (p2v_mailbox & E1000_P2VMAILBOX_PFU) + wr32(E1000_P2VMAILBOX(vf_number), + p2v_mailbox & ~E1000_P2VMAILBOX_PFU); + + return 0; +} + +/** + * igb_write_mbx_pf - Places a message in the mailbox + * @hw: pointer to the HW structure + * @msg: The message buffer + * @size: Length of buffer + * @vf_number: the VF index + * + * returns SUCCESS if it successfully copied message into the buffer + **/ +static s32 igb_write_mbx_pf(struct e1000_hw *hw, u32 *msg, u16 size, + u16 vf_number) +{ + s32 ret_val; + u16 i; + + /* lock the mailbox to prevent pf/vf race condition */ + ret_val = igb_obtain_mbx_lock_pf(hw, vf_number); + if (ret_val) + goto out_no_write; + + /* flush msg and acks as we are overwriting the message buffer */ + igb_check_for_msg_pf(hw, vf_number); + igb_check_for_ack_pf(hw, vf_number); + + /* copy the caller specified message to the mailbox memory buffer */ + for (i = 0; i < size; i++) + array_wr32(E1000_VMBMEM(vf_number), i, msg[i]); + + /* Interrupt VF to tell it a message has been sent and release buffer*/ + wr32(E1000_P2VMAILBOX(vf_number), E1000_P2VMAILBOX_STS); + + /* update stats */ + hw->mbx.stats.msgs_tx++; + +out_no_write: + return ret_val; + +} + +/** + * igb_read_mbx_pf - Read a message from the mailbox + * @hw: pointer to the HW structure + * @msg: The message buffer + * @size: Length of buffer + * @vf_number: the VF index + * @unlock: unlock the mailbox when done? + * + * This function copies a message from the mailbox buffer to the caller's + * memory buffer. The presumption is that the caller knows that there was + * a message due to a VF request so no polling for message is needed. + **/ +static s32 igb_read_mbx_pf(struct e1000_hw *hw, u32 *msg, u16 size, + u16 vf_number, bool unlock) +{ + s32 ret_val; + u16 i; + + /* lock the mailbox to prevent pf/vf race condition */ + ret_val = igb_obtain_mbx_lock_pf(hw, vf_number); + if (ret_val) + goto out_no_read; + + /* copy the message to the mailbox memory buffer */ + for (i = 0; i < size; i++) + msg[i] = array_rd32(E1000_VMBMEM(vf_number), i); + + /* Acknowledge the message and release mailbox lock (or not) */ + if (unlock) + wr32(E1000_P2VMAILBOX(vf_number), E1000_P2VMAILBOX_ACK); + else + wr32(E1000_P2VMAILBOX(vf_number), + E1000_P2VMAILBOX_ACK | E1000_P2VMAILBOX_PFU); + + /* update stats */ + hw->mbx.stats.msgs_rx++; + +out_no_read: + return ret_val; +} + +/** + * igb_init_mbx_params_pf - set initial values for pf mailbox + * @hw: pointer to the HW structure + * + * Initializes the hw->mbx struct to correct values for pf mailbox + */ +s32 igb_init_mbx_params_pf(struct e1000_hw *hw) +{ + struct e1000_mbx_info *mbx = &hw->mbx; + + mbx->timeout = 0; + mbx->usec_delay = 0; + + mbx->size = E1000_VFMAILBOX_SIZE; + + mbx->ops.read = igb_read_mbx_pf; + mbx->ops.write = igb_write_mbx_pf; + mbx->ops.read_posted = igb_read_posted_mbx; + mbx->ops.write_posted = igb_write_posted_mbx; + mbx->ops.check_for_msg = igb_check_for_msg_pf; + mbx->ops.check_for_ack = igb_check_for_ack_pf; + mbx->ops.check_for_rst = igb_check_for_rst_pf; + mbx->ops.unlock = igb_release_mbx_lock_pf; + + mbx->stats.msgs_tx = 0; + mbx->stats.msgs_rx = 0; + mbx->stats.reqs = 0; + mbx->stats.acks = 0; + mbx->stats.rsts = 0; + + return 0; +} + diff --git a/drivers/net/ethernet/intel/igb/e1000_mbx.h b/drivers/net/ethernet/intel/igb/e1000_mbx.h new file mode 100644 index 0000000000..178e60ec71 --- /dev/null +++ b/drivers/net/ethernet/intel/igb/e1000_mbx.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ + +#ifndef _E1000_MBX_H_ +#define _E1000_MBX_H_ + +#include "e1000_hw.h" + +#define E1000_P2VMAILBOX_STS 0x00000001 /* Initiate message send to VF */ +#define E1000_P2VMAILBOX_ACK 0x00000002 /* Ack message recv'd from VF */ +#define E1000_P2VMAILBOX_VFU 0x00000004 /* VF owns the mailbox buffer */ +#define E1000_P2VMAILBOX_PFU 0x00000008 /* PF owns the mailbox buffer */ +#define E1000_P2VMAILBOX_RVFU 0x00000010 /* Reset VFU - used when VF stuck */ + +#define E1000_MBVFICR_VFREQ_MASK 0x000000FF /* bits for VF messages */ +#define E1000_MBVFICR_VFREQ_VF1 0x00000001 /* bit for VF 1 message */ +#define E1000_MBVFICR_VFACK_MASK 0x00FF0000 /* bits for VF acks */ +#define E1000_MBVFICR_VFACK_VF1 0x00010000 /* bit for VF 1 ack */ + +#define E1000_VFMAILBOX_SIZE 16 /* 16 32 bit words - 64 bytes */ + +/* If it's a E1000_VF_* msg then it originates in the VF and is sent to the + * PF. The reverse is true if it is E1000_PF_*. + * Message ACK's are the value or'd with 0xF0000000 + */ +/* Messages below or'd with this are the ACK */ +#define E1000_VT_MSGTYPE_ACK 0x80000000 +/* Messages below or'd with this are the NACK */ +#define E1000_VT_MSGTYPE_NACK 0x40000000 +/* Indicates that VF is still clear to send requests */ +#define E1000_VT_MSGTYPE_CTS 0x20000000 +#define E1000_VT_MSGINFO_SHIFT 16 +/* bits 23:16 are used for exra info for certain messages */ +#define E1000_VT_MSGINFO_MASK (0xFF << E1000_VT_MSGINFO_SHIFT) + +#define E1000_VF_RESET 0x01 /* VF requests reset */ +#define E1000_VF_SET_MAC_ADDR 0x02 /* VF requests to set MAC addr */ +/* VF requests to clear all unicast MAC filters */ +#define E1000_VF_MAC_FILTER_CLR (0x01 << E1000_VT_MSGINFO_SHIFT) +/* VF requests to add unicast MAC filter */ +#define E1000_VF_MAC_FILTER_ADD (0x02 << E1000_VT_MSGINFO_SHIFT) +#define E1000_VF_SET_MULTICAST 0x03 /* VF requests to set MC addr */ +#define E1000_VF_SET_VLAN 0x04 /* VF requests to set VLAN */ +#define E1000_VF_SET_LPE 0x05 /* VF requests to set VMOLR.LPE */ +#define E1000_VF_SET_PROMISC 0x06 /*VF requests to clear VMOLR.ROPE/MPME*/ +#define E1000_VF_SET_PROMISC_MULTICAST (0x02 << E1000_VT_MSGINFO_SHIFT) + +#define E1000_PF_CONTROL_MSG 0x0100 /* PF control message */ + +s32 igb_read_mbx(struct e1000_hw *hw, u32 *msg, u16 size, u16 mbx_id, + bool unlock); +s32 igb_write_mbx(struct e1000_hw *hw, u32 *msg, u16 size, u16 mbx_id); +s32 igb_check_for_msg(struct e1000_hw *hw, u16 mbx_id); +s32 igb_check_for_ack(struct e1000_hw *hw, u16 mbx_id); +s32 igb_check_for_rst(struct e1000_hw *hw, u16 mbx_id); +s32 igb_unlock_mbx(struct e1000_hw *hw, u16 mbx_id); +s32 igb_init_mbx_params_pf(struct e1000_hw *hw); + +#endif /* _E1000_MBX_H_ */ diff --git a/drivers/net/ethernet/intel/igb/e1000_nvm.c b/drivers/net/ethernet/intel/igb/e1000_nvm.c new file mode 100644 index 0000000000..fa136e6e93 --- /dev/null +++ b/drivers/net/ethernet/intel/igb/e1000_nvm.c @@ -0,0 +1,782 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2007 - 2018 Intel Corporation. */ + +#include <linux/if_ether.h> +#include <linux/delay.h> + +#include "e1000_mac.h" +#include "e1000_nvm.h" + +/** + * igb_raise_eec_clk - Raise EEPROM clock + * @hw: pointer to the HW structure + * @eecd: pointer to the EEPROM + * + * Enable/Raise the EEPROM clock bit. + **/ +static void igb_raise_eec_clk(struct e1000_hw *hw, u32 *eecd) +{ + *eecd = *eecd | E1000_EECD_SK; + wr32(E1000_EECD, *eecd); + wrfl(); + udelay(hw->nvm.delay_usec); +} + +/** + * igb_lower_eec_clk - Lower EEPROM clock + * @hw: pointer to the HW structure + * @eecd: pointer to the EEPROM + * + * Clear/Lower the EEPROM clock bit. + **/ +static void igb_lower_eec_clk(struct e1000_hw *hw, u32 *eecd) +{ + *eecd = *eecd & ~E1000_EECD_SK; + wr32(E1000_EECD, *eecd); + wrfl(); + udelay(hw->nvm.delay_usec); +} + +/** + * igb_shift_out_eec_bits - Shift data bits our to the EEPROM + * @hw: pointer to the HW structure + * @data: data to send to the EEPROM + * @count: number of bits to shift out + * + * We need to shift 'count' bits out to the EEPROM. So, the value in the + * "data" parameter will be shifted out to the EEPROM one bit at a time. + * In order to do this, "data" must be broken down into bits. + **/ +static void igb_shift_out_eec_bits(struct e1000_hw *hw, u16 data, u16 count) +{ + struct e1000_nvm_info *nvm = &hw->nvm; + u32 eecd = rd32(E1000_EECD); + u32 mask; + + mask = 1u << (count - 1); + if (nvm->type == e1000_nvm_eeprom_spi) + eecd |= E1000_EECD_DO; + + do { + eecd &= ~E1000_EECD_DI; + + if (data & mask) + eecd |= E1000_EECD_DI; + + wr32(E1000_EECD, eecd); + wrfl(); + + udelay(nvm->delay_usec); + + igb_raise_eec_clk(hw, &eecd); + igb_lower_eec_clk(hw, &eecd); + + mask >>= 1; + } while (mask); + + eecd &= ~E1000_EECD_DI; + wr32(E1000_EECD, eecd); +} + +/** + * igb_shift_in_eec_bits - Shift data bits in from the EEPROM + * @hw: pointer to the HW structure + * @count: number of bits to shift in + * + * In order to read a register from the EEPROM, we need to shift 'count' bits + * in from the EEPROM. Bits are "shifted in" by raising the clock input to + * the EEPROM (setting the SK bit), and then reading the value of the data out + * "DO" bit. During this "shifting in" process the data in "DI" bit should + * always be clear. + **/ +static u16 igb_shift_in_eec_bits(struct e1000_hw *hw, u16 count) +{ + u32 eecd; + u32 i; + u16 data; + + eecd = rd32(E1000_EECD); + + eecd &= ~(E1000_EECD_DO | E1000_EECD_DI); + data = 0; + + for (i = 0; i < count; i++) { + data <<= 1; + igb_raise_eec_clk(hw, &eecd); + + eecd = rd32(E1000_EECD); + + eecd &= ~E1000_EECD_DI; + if (eecd & E1000_EECD_DO) + data |= 1; + + igb_lower_eec_clk(hw, &eecd); + } + + return data; +} + +/** + * igb_poll_eerd_eewr_done - Poll for EEPROM read/write completion + * @hw: pointer to the HW structure + * @ee_reg: EEPROM flag for polling + * + * Polls the EEPROM status bit for either read or write completion based + * upon the value of 'ee_reg'. + **/ +static s32 igb_poll_eerd_eewr_done(struct e1000_hw *hw, int ee_reg) +{ + u32 attempts = 100000; + u32 i, reg = 0; + s32 ret_val = -E1000_ERR_NVM; + + for (i = 0; i < attempts; i++) { + if (ee_reg == E1000_NVM_POLL_READ) + reg = rd32(E1000_EERD); + else + reg = rd32(E1000_EEWR); + + if (reg & E1000_NVM_RW_REG_DONE) { + ret_val = 0; + break; + } + + udelay(5); + } + + return ret_val; +} + +/** + * igb_acquire_nvm - Generic request for access to EEPROM + * @hw: pointer to the HW structure + * + * Set the EEPROM access request bit and wait for EEPROM access grant bit. + * Return successful if access grant bit set, else clear the request for + * EEPROM access and return -E1000_ERR_NVM (-1). + **/ +s32 igb_acquire_nvm(struct e1000_hw *hw) +{ + u32 eecd = rd32(E1000_EECD); + s32 timeout = E1000_NVM_GRANT_ATTEMPTS; + s32 ret_val = 0; + + + wr32(E1000_EECD, eecd | E1000_EECD_REQ); + eecd = rd32(E1000_EECD); + + while (timeout) { + if (eecd & E1000_EECD_GNT) + break; + udelay(5); + eecd = rd32(E1000_EECD); + timeout--; + } + + if (!timeout) { + eecd &= ~E1000_EECD_REQ; + wr32(E1000_EECD, eecd); + hw_dbg("Could not acquire NVM grant\n"); + ret_val = -E1000_ERR_NVM; + } + + return ret_val; +} + +/** + * igb_standby_nvm - Return EEPROM to standby state + * @hw: pointer to the HW structure + * + * Return the EEPROM to a standby state. + **/ +static void igb_standby_nvm(struct e1000_hw *hw) +{ + struct e1000_nvm_info *nvm = &hw->nvm; + u32 eecd = rd32(E1000_EECD); + + if (nvm->type == e1000_nvm_eeprom_spi) { + /* Toggle CS to flush commands */ + eecd |= E1000_EECD_CS; + wr32(E1000_EECD, eecd); + wrfl(); + udelay(nvm->delay_usec); + eecd &= ~E1000_EECD_CS; + wr32(E1000_EECD, eecd); + wrfl(); + udelay(nvm->delay_usec); + } +} + +/** + * e1000_stop_nvm - Terminate EEPROM command + * @hw: pointer to the HW structure + * + * Terminates the current command by inverting the EEPROM's chip select pin. + **/ +static void e1000_stop_nvm(struct e1000_hw *hw) +{ + u32 eecd; + + eecd = rd32(E1000_EECD); + if (hw->nvm.type == e1000_nvm_eeprom_spi) { + /* Pull CS high */ + eecd |= E1000_EECD_CS; + igb_lower_eec_clk(hw, &eecd); + } +} + +/** + * igb_release_nvm - Release exclusive access to EEPROM + * @hw: pointer to the HW structure + * + * Stop any current commands to the EEPROM and clear the EEPROM request bit. + **/ +void igb_release_nvm(struct e1000_hw *hw) +{ + u32 eecd; + + e1000_stop_nvm(hw); + + eecd = rd32(E1000_EECD); + eecd &= ~E1000_EECD_REQ; + wr32(E1000_EECD, eecd); +} + +/** + * igb_ready_nvm_eeprom - Prepares EEPROM for read/write + * @hw: pointer to the HW structure + * + * Setups the EEPROM for reading and writing. + **/ +static s32 igb_ready_nvm_eeprom(struct e1000_hw *hw) +{ + struct e1000_nvm_info *nvm = &hw->nvm; + u32 eecd = rd32(E1000_EECD); + s32 ret_val = 0; + u16 timeout = 0; + u8 spi_stat_reg; + + + if (nvm->type == e1000_nvm_eeprom_spi) { + /* Clear SK and CS */ + eecd &= ~(E1000_EECD_CS | E1000_EECD_SK); + wr32(E1000_EECD, eecd); + wrfl(); + udelay(1); + timeout = NVM_MAX_RETRY_SPI; + + /* Read "Status Register" repeatedly until the LSB is cleared. + * The EEPROM will signal that the command has been completed + * by clearing bit 0 of the internal status register. If it's + * not cleared within 'timeout', then error out. + */ + while (timeout) { + igb_shift_out_eec_bits(hw, NVM_RDSR_OPCODE_SPI, + hw->nvm.opcode_bits); + spi_stat_reg = (u8)igb_shift_in_eec_bits(hw, 8); + if (!(spi_stat_reg & NVM_STATUS_RDY_SPI)) + break; + + udelay(5); + igb_standby_nvm(hw); + timeout--; + } + + if (!timeout) { + hw_dbg("SPI NVM Status error\n"); + ret_val = -E1000_ERR_NVM; + goto out; + } + } + +out: + return ret_val; +} + +/** + * igb_read_nvm_spi - Read EEPROM's using SPI + * @hw: pointer to the HW structure + * @offset: offset of word in the EEPROM to read + * @words: number of words to read + * @data: word read from the EEPROM + * + * Reads a 16 bit word from the EEPROM. + **/ +s32 igb_read_nvm_spi(struct e1000_hw *hw, u16 offset, u16 words, u16 *data) +{ + struct e1000_nvm_info *nvm = &hw->nvm; + u32 i = 0; + s32 ret_val; + u16 word_in; + u8 read_opcode = NVM_READ_OPCODE_SPI; + + /* A check for invalid values: offset too large, too many words, + * and not enough words. + */ + if ((offset >= nvm->word_size) || (words > (nvm->word_size - offset)) || + (words == 0)) { + hw_dbg("nvm parameter(s) out of bounds\n"); + ret_val = -E1000_ERR_NVM; + goto out; + } + + ret_val = nvm->ops.acquire(hw); + if (ret_val) + goto out; + + ret_val = igb_ready_nvm_eeprom(hw); + if (ret_val) + goto release; + + igb_standby_nvm(hw); + + if ((nvm->address_bits == 8) && (offset >= 128)) + read_opcode |= NVM_A8_OPCODE_SPI; + + /* Send the READ command (opcode + addr) */ + igb_shift_out_eec_bits(hw, read_opcode, nvm->opcode_bits); + igb_shift_out_eec_bits(hw, (u16)(offset*2), nvm->address_bits); + + /* Read the data. SPI NVMs increment the address with each byte + * read and will roll over if reading beyond the end. This allows + * us to read the whole NVM from any offset + */ + for (i = 0; i < words; i++) { + word_in = igb_shift_in_eec_bits(hw, 16); + data[i] = (word_in >> 8) | (word_in << 8); + } + +release: + nvm->ops.release(hw); + +out: + return ret_val; +} + +/** + * igb_read_nvm_eerd - Reads EEPROM using EERD register + * @hw: pointer to the HW structure + * @offset: offset of word in the EEPROM to read + * @words: number of words to read + * @data: word read from the EEPROM + * + * Reads a 16 bit word from the EEPROM using the EERD register. + **/ +s32 igb_read_nvm_eerd(struct e1000_hw *hw, u16 offset, u16 words, u16 *data) +{ + struct e1000_nvm_info *nvm = &hw->nvm; + u32 i, eerd = 0; + s32 ret_val = 0; + + /* A check for invalid values: offset too large, too many words, + * and not enough words. + */ + if ((offset >= nvm->word_size) || (words > (nvm->word_size - offset)) || + (words == 0)) { + hw_dbg("nvm parameter(s) out of bounds\n"); + ret_val = -E1000_ERR_NVM; + goto out; + } + + for (i = 0; i < words; i++) { + eerd = ((offset+i) << E1000_NVM_RW_ADDR_SHIFT) + + E1000_NVM_RW_REG_START; + + wr32(E1000_EERD, eerd); + ret_val = igb_poll_eerd_eewr_done(hw, E1000_NVM_POLL_READ); + if (ret_val) + break; + + data[i] = (rd32(E1000_EERD) >> + E1000_NVM_RW_REG_DATA); + } + +out: + return ret_val; +} + +/** + * igb_write_nvm_spi - Write to EEPROM using SPI + * @hw: pointer to the HW structure + * @offset: offset within the EEPROM to be written to + * @words: number of words to write + * @data: 16 bit word(s) to be written to the EEPROM + * + * Writes data to EEPROM at offset using SPI interface. + * + * If e1000_update_nvm_checksum is not called after this function , the + * EEPROM will most likley contain an invalid checksum. + **/ +s32 igb_write_nvm_spi(struct e1000_hw *hw, u16 offset, u16 words, u16 *data) +{ + struct e1000_nvm_info *nvm = &hw->nvm; + s32 ret_val = -E1000_ERR_NVM; + u16 widx = 0; + + /* A check for invalid values: offset too large, too many words, + * and not enough words. + */ + if ((offset >= nvm->word_size) || (words > (nvm->word_size - offset)) || + (words == 0)) { + hw_dbg("nvm parameter(s) out of bounds\n"); + return ret_val; + } + + while (widx < words) { + u8 write_opcode = NVM_WRITE_OPCODE_SPI; + + ret_val = nvm->ops.acquire(hw); + if (ret_val) + return ret_val; + + ret_val = igb_ready_nvm_eeprom(hw); + if (ret_val) { + nvm->ops.release(hw); + return ret_val; + } + + igb_standby_nvm(hw); + + /* Send the WRITE ENABLE command (8 bit opcode) */ + igb_shift_out_eec_bits(hw, NVM_WREN_OPCODE_SPI, + nvm->opcode_bits); + + igb_standby_nvm(hw); + + /* Some SPI eeproms use the 8th address bit embedded in the + * opcode + */ + if ((nvm->address_bits == 8) && (offset >= 128)) + write_opcode |= NVM_A8_OPCODE_SPI; + + /* Send the Write command (8-bit opcode + addr) */ + igb_shift_out_eec_bits(hw, write_opcode, nvm->opcode_bits); + igb_shift_out_eec_bits(hw, (u16)((offset + widx) * 2), + nvm->address_bits); + + /* Loop to allow for up to whole page write of eeprom */ + while (widx < words) { + u16 word_out = data[widx]; + + word_out = (word_out >> 8) | (word_out << 8); + igb_shift_out_eec_bits(hw, word_out, 16); + widx++; + + if ((((offset + widx) * 2) % nvm->page_size) == 0) { + igb_standby_nvm(hw); + break; + } + } + usleep_range(1000, 2000); + nvm->ops.release(hw); + } + + return ret_val; +} + +/** + * igb_read_part_string - Read device part number + * @hw: pointer to the HW structure + * @part_num: pointer to device part number + * @part_num_size: size of part number buffer + * + * Reads the product board assembly (PBA) number from the EEPROM and stores + * the value in part_num. + **/ +s32 igb_read_part_string(struct e1000_hw *hw, u8 *part_num, u32 part_num_size) +{ + s32 ret_val; + u16 nvm_data; + u16 pointer; + u16 offset; + u16 length; + + if (part_num == NULL) { + hw_dbg("PBA string buffer was null\n"); + ret_val = E1000_ERR_INVALID_ARGUMENT; + goto out; + } + + ret_val = hw->nvm.ops.read(hw, NVM_PBA_OFFSET_0, 1, &nvm_data); + if (ret_val) { + hw_dbg("NVM Read Error\n"); + goto out; + } + + ret_val = hw->nvm.ops.read(hw, NVM_PBA_OFFSET_1, 1, &pointer); + if (ret_val) { + hw_dbg("NVM Read Error\n"); + goto out; + } + + /* if nvm_data is not ptr guard the PBA must be in legacy format which + * means pointer is actually our second data word for the PBA number + * and we can decode it into an ascii string + */ + if (nvm_data != NVM_PBA_PTR_GUARD) { + hw_dbg("NVM PBA number is not stored as string\n"); + + /* we will need 11 characters to store the PBA */ + if (part_num_size < 11) { + hw_dbg("PBA string buffer too small\n"); + return E1000_ERR_NO_SPACE; + } + + /* extract hex string from data and pointer */ + part_num[0] = (nvm_data >> 12) & 0xF; + part_num[1] = (nvm_data >> 8) & 0xF; + part_num[2] = (nvm_data >> 4) & 0xF; + part_num[3] = nvm_data & 0xF; + part_num[4] = (pointer >> 12) & 0xF; + part_num[5] = (pointer >> 8) & 0xF; + part_num[6] = '-'; + part_num[7] = 0; + part_num[8] = (pointer >> 4) & 0xF; + part_num[9] = pointer & 0xF; + + /* put a null character on the end of our string */ + part_num[10] = '\0'; + + /* switch all the data but the '-' to hex char */ + for (offset = 0; offset < 10; offset++) { + if (part_num[offset] < 0xA) + part_num[offset] += '0'; + else if (part_num[offset] < 0x10) + part_num[offset] += 'A' - 0xA; + } + + goto out; + } + + ret_val = hw->nvm.ops.read(hw, pointer, 1, &length); + if (ret_val) { + hw_dbg("NVM Read Error\n"); + goto out; + } + + if (length == 0xFFFF || length == 0) { + hw_dbg("NVM PBA number section invalid length\n"); + ret_val = E1000_ERR_NVM_PBA_SECTION; + goto out; + } + /* check if part_num buffer is big enough */ + if (part_num_size < (((u32)length * 2) - 1)) { + hw_dbg("PBA string buffer too small\n"); + ret_val = E1000_ERR_NO_SPACE; + goto out; + } + + /* trim pba length from start of string */ + pointer++; + length--; + + for (offset = 0; offset < length; offset++) { + ret_val = hw->nvm.ops.read(hw, pointer + offset, 1, &nvm_data); + if (ret_val) { + hw_dbg("NVM Read Error\n"); + goto out; + } + part_num[offset * 2] = (u8)(nvm_data >> 8); + part_num[(offset * 2) + 1] = (u8)(nvm_data & 0xFF); + } + part_num[offset * 2] = '\0'; + +out: + return ret_val; +} + +/** + * igb_read_mac_addr - Read device MAC address + * @hw: pointer to the HW structure + * + * Reads the device MAC address from the EEPROM and stores the value. + * Since devices with two ports use the same EEPROM, we increment the + * last bit in the MAC address for the second port. + **/ +s32 igb_read_mac_addr(struct e1000_hw *hw) +{ + u32 rar_high; + u32 rar_low; + u16 i; + + rar_high = rd32(E1000_RAH(0)); + rar_low = rd32(E1000_RAL(0)); + + for (i = 0; i < E1000_RAL_MAC_ADDR_LEN; i++) + hw->mac.perm_addr[i] = (u8)(rar_low >> (i*8)); + + for (i = 0; i < E1000_RAH_MAC_ADDR_LEN; i++) + hw->mac.perm_addr[i+4] = (u8)(rar_high >> (i*8)); + + for (i = 0; i < ETH_ALEN; i++) + hw->mac.addr[i] = hw->mac.perm_addr[i]; + + return 0; +} + +/** + * igb_validate_nvm_checksum - Validate EEPROM checksum + * @hw: pointer to the HW structure + * + * Calculates the EEPROM checksum by reading/adding each word of the EEPROM + * and then verifies that the sum of the EEPROM is equal to 0xBABA. + **/ +s32 igb_validate_nvm_checksum(struct e1000_hw *hw) +{ + s32 ret_val = 0; + u16 checksum = 0; + u16 i, nvm_data; + + for (i = 0; i < (NVM_CHECKSUM_REG + 1); i++) { + ret_val = hw->nvm.ops.read(hw, i, 1, &nvm_data); + if (ret_val) { + hw_dbg("NVM Read Error\n"); + goto out; + } + checksum += nvm_data; + } + + if (checksum != (u16) NVM_SUM) { + hw_dbg("NVM Checksum Invalid\n"); + ret_val = -E1000_ERR_NVM; + goto out; + } + +out: + return ret_val; +} + +/** + * igb_update_nvm_checksum - Update EEPROM checksum + * @hw: pointer to the HW structure + * + * Updates the EEPROM checksum by reading/adding each word of the EEPROM + * up to the checksum. Then calculates the EEPROM checksum and writes the + * value to the EEPROM. + **/ +s32 igb_update_nvm_checksum(struct e1000_hw *hw) +{ + s32 ret_val; + u16 checksum = 0; + u16 i, nvm_data; + + for (i = 0; i < NVM_CHECKSUM_REG; i++) { + ret_val = hw->nvm.ops.read(hw, i, 1, &nvm_data); + if (ret_val) { + hw_dbg("NVM Read Error while updating checksum.\n"); + goto out; + } + checksum += nvm_data; + } + checksum = (u16) NVM_SUM - checksum; + ret_val = hw->nvm.ops.write(hw, NVM_CHECKSUM_REG, 1, &checksum); + if (ret_val) + hw_dbg("NVM Write Error while updating checksum.\n"); + +out: + return ret_val; +} + +/** + * igb_get_fw_version - Get firmware version information + * @hw: pointer to the HW structure + * @fw_vers: pointer to output structure + * + * unsupported MAC types will return all 0 version structure + **/ +void igb_get_fw_version(struct e1000_hw *hw, struct e1000_fw_version *fw_vers) +{ + u16 eeprom_verh, eeprom_verl, etrack_test, fw_version; + u8 q, hval, rem, result; + u16 comb_verh, comb_verl, comb_offset; + + memset(fw_vers, 0, sizeof(struct e1000_fw_version)); + + /* basic eeprom version numbers and bits used vary by part and by tool + * used to create the nvm images. Check which data format we have. + */ + hw->nvm.ops.read(hw, NVM_ETRACK_HIWORD, 1, &etrack_test); + switch (hw->mac.type) { + case e1000_i211: + igb_read_invm_version(hw, fw_vers); + return; + case e1000_82575: + case e1000_82576: + case e1000_82580: + /* Use this format, unless EETRACK ID exists, + * then use alternate format + */ + if ((etrack_test & NVM_MAJOR_MASK) != NVM_ETRACK_VALID) { + hw->nvm.ops.read(hw, NVM_VERSION, 1, &fw_version); + fw_vers->eep_major = (fw_version & NVM_MAJOR_MASK) + >> NVM_MAJOR_SHIFT; + fw_vers->eep_minor = (fw_version & NVM_MINOR_MASK) + >> NVM_MINOR_SHIFT; + fw_vers->eep_build = (fw_version & NVM_IMAGE_ID_MASK); + goto etrack_id; + } + break; + case e1000_i210: + if (!(igb_get_flash_presence_i210(hw))) { + igb_read_invm_version(hw, fw_vers); + return; + } + fallthrough; + case e1000_i350: + /* find combo image version */ + hw->nvm.ops.read(hw, NVM_COMB_VER_PTR, 1, &comb_offset); + if ((comb_offset != 0x0) && + (comb_offset != NVM_VER_INVALID)) { + + hw->nvm.ops.read(hw, (NVM_COMB_VER_OFF + comb_offset + + 1), 1, &comb_verh); + hw->nvm.ops.read(hw, (NVM_COMB_VER_OFF + comb_offset), + 1, &comb_verl); + + /* get Option Rom version if it exists and is valid */ + if ((comb_verh && comb_verl) && + ((comb_verh != NVM_VER_INVALID) && + (comb_verl != NVM_VER_INVALID))) { + + fw_vers->or_valid = true; + fw_vers->or_major = + comb_verl >> NVM_COMB_VER_SHFT; + fw_vers->or_build = + (comb_verl << NVM_COMB_VER_SHFT) + | (comb_verh >> NVM_COMB_VER_SHFT); + fw_vers->or_patch = + comb_verh & NVM_COMB_VER_MASK; + } + } + break; + default: + return; + } + hw->nvm.ops.read(hw, NVM_VERSION, 1, &fw_version); + fw_vers->eep_major = (fw_version & NVM_MAJOR_MASK) + >> NVM_MAJOR_SHIFT; + + /* check for old style version format in newer images*/ + if ((fw_version & NVM_NEW_DEC_MASK) == 0x0) { + eeprom_verl = (fw_version & NVM_COMB_VER_MASK); + } else { + eeprom_verl = (fw_version & NVM_MINOR_MASK) + >> NVM_MINOR_SHIFT; + } + /* Convert minor value to hex before assigning to output struct + * Val to be converted will not be higher than 99, per tool output + */ + q = eeprom_verl / NVM_HEX_CONV; + hval = q * NVM_HEX_TENS; + rem = eeprom_verl % NVM_HEX_CONV; + result = hval + rem; + fw_vers->eep_minor = result; + +etrack_id: + if ((etrack_test & NVM_MAJOR_MASK) == NVM_ETRACK_VALID) { + hw->nvm.ops.read(hw, NVM_ETRACK_WORD, 1, &eeprom_verl); + hw->nvm.ops.read(hw, (NVM_ETRACK_WORD + 1), 1, &eeprom_verh); + fw_vers->etrack_id = (eeprom_verh << NVM_ETRACK_SHIFT) + | eeprom_verl; + } +} diff --git a/drivers/net/ethernet/intel/igb/e1000_nvm.h b/drivers/net/ethernet/intel/igb/e1000_nvm.h new file mode 100644 index 0000000000..091cddf4ad --- /dev/null +++ b/drivers/net/ethernet/intel/igb/e1000_nvm.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ + +#ifndef _E1000_NVM_H_ +#define _E1000_NVM_H_ + +s32 igb_acquire_nvm(struct e1000_hw *hw); +void igb_release_nvm(struct e1000_hw *hw); +s32 igb_read_mac_addr(struct e1000_hw *hw); +s32 igb_read_part_num(struct e1000_hw *hw, u32 *part_num); +s32 igb_read_part_string(struct e1000_hw *hw, u8 *part_num, + u32 part_num_size); +s32 igb_read_nvm_eerd(struct e1000_hw *hw, u16 offset, u16 words, u16 *data); +s32 igb_read_nvm_spi(struct e1000_hw *hw, u16 offset, u16 words, u16 *data); +s32 igb_write_nvm_spi(struct e1000_hw *hw, u16 offset, u16 words, u16 *data); +s32 igb_validate_nvm_checksum(struct e1000_hw *hw); +s32 igb_update_nvm_checksum(struct e1000_hw *hw); + +struct e1000_fw_version { + u32 etrack_id; + u16 eep_major; + u16 eep_minor; + u16 eep_build; + + u8 invm_major; + u8 invm_minor; + u8 invm_img_type; + + bool or_valid; + u16 or_major; + u16 or_build; + u16 or_patch; +}; +void igb_get_fw_version(struct e1000_hw *hw, struct e1000_fw_version *fw_vers); + +#endif diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c new file mode 100644 index 0000000000..a018000f7d --- /dev/null +++ b/drivers/net/ethernet/intel/igb/e1000_phy.c @@ -0,0 +1,2631 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2007 - 2018 Intel Corporation. */ + +#include <linux/if_ether.h> +#include <linux/delay.h> + +#include "e1000_mac.h" +#include "e1000_phy.h" + +static s32 igb_phy_setup_autoneg(struct e1000_hw *hw); +static void igb_phy_force_speed_duplex_setup(struct e1000_hw *hw, + u16 *phy_ctrl); +static s32 igb_wait_autoneg(struct e1000_hw *hw); +static s32 igb_set_master_slave_mode(struct e1000_hw *hw); + +/* Cable length tables */ +static const u16 e1000_m88_cable_length_table[] = { + 0, 50, 80, 110, 140, 140, E1000_CABLE_LENGTH_UNDEFINED }; + +static const u16 e1000_igp_2_cable_length_table[] = { + 0, 0, 0, 0, 0, 0, 0, 0, 3, 5, 8, 11, 13, 16, 18, 21, + 0, 0, 0, 3, 6, 10, 13, 16, 19, 23, 26, 29, 32, 35, 38, 41, + 6, 10, 14, 18, 22, 26, 30, 33, 37, 41, 44, 48, 51, 54, 58, 61, + 21, 26, 31, 35, 40, 44, 49, 53, 57, 61, 65, 68, 72, 75, 79, 82, + 40, 45, 51, 56, 61, 66, 70, 75, 79, 83, 87, 91, 94, 98, 101, 104, + 60, 66, 72, 77, 82, 87, 92, 96, 100, 104, 108, 111, 114, 117, 119, 121, + 83, 89, 95, 100, 105, 109, 113, 116, 119, 122, 124, + 104, 109, 114, 118, 121, 124}; + +/** + * igb_check_reset_block - Check if PHY reset is blocked + * @hw: pointer to the HW structure + * + * Read the PHY management control register and check whether a PHY reset + * is blocked. If a reset is not blocked return 0, otherwise + * return E1000_BLK_PHY_RESET (12). + **/ +s32 igb_check_reset_block(struct e1000_hw *hw) +{ + u32 manc; + + manc = rd32(E1000_MANC); + + return (manc & E1000_MANC_BLK_PHY_RST_ON_IDE) ? E1000_BLK_PHY_RESET : 0; +} + +/** + * igb_get_phy_id - Retrieve the PHY ID and revision + * @hw: pointer to the HW structure + * + * Reads the PHY registers and stores the PHY ID and possibly the PHY + * revision in the hardware structure. + **/ +s32 igb_get_phy_id(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val = 0; + u16 phy_id; + + /* ensure PHY page selection to fix misconfigured i210 */ + if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211)) + phy->ops.write_reg(hw, I347AT4_PAGE_SELECT, 0); + + ret_val = phy->ops.read_reg(hw, PHY_ID1, &phy_id); + if (ret_val) + goto out; + + phy->id = (u32)(phy_id << 16); + udelay(20); + ret_val = phy->ops.read_reg(hw, PHY_ID2, &phy_id); + if (ret_val) + goto out; + + phy->id |= (u32)(phy_id & PHY_REVISION_MASK); + phy->revision = (u32)(phy_id & ~PHY_REVISION_MASK); + +out: + return ret_val; +} + +/** + * igb_phy_reset_dsp - Reset PHY DSP + * @hw: pointer to the HW structure + * + * Reset the digital signal processor. + **/ +static s32 igb_phy_reset_dsp(struct e1000_hw *hw) +{ + s32 ret_val = 0; + + if (!(hw->phy.ops.write_reg)) + goto out; + + ret_val = hw->phy.ops.write_reg(hw, M88E1000_PHY_GEN_CONTROL, 0xC1); + if (ret_val) + goto out; + + ret_val = hw->phy.ops.write_reg(hw, M88E1000_PHY_GEN_CONTROL, 0); + +out: + return ret_val; +} + +/** + * igb_read_phy_reg_mdic - Read MDI control register + * @hw: pointer to the HW structure + * @offset: register offset to be read + * @data: pointer to the read data + * + * Reads the MDI control register in the PHY at offset and stores the + * information read to data. + **/ +s32 igb_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data) +{ + struct e1000_phy_info *phy = &hw->phy; + u32 i, mdic = 0; + s32 ret_val = 0; + + if (offset > MAX_PHY_REG_ADDRESS) { + hw_dbg("PHY Address %d is out of range\n", offset); + ret_val = -E1000_ERR_PARAM; + goto out; + } + + /* Set up Op-code, Phy Address, and register offset in the MDI + * Control register. The MAC will take care of interfacing with the + * PHY to retrieve the desired data. + */ + mdic = ((offset << E1000_MDIC_REG_SHIFT) | + (phy->addr << E1000_MDIC_PHY_SHIFT) | + (E1000_MDIC_OP_READ)); + + wr32(E1000_MDIC, mdic); + + /* Poll the ready bit to see if the MDI read completed + * Increasing the time out as testing showed failures with + * the lower time out + */ + for (i = 0; i < (E1000_GEN_POLL_TIMEOUT * 3); i++) { + udelay(50); + mdic = rd32(E1000_MDIC); + if (mdic & E1000_MDIC_READY) + break; + } + if (!(mdic & E1000_MDIC_READY)) { + hw_dbg("MDI Read did not complete\n"); + ret_val = -E1000_ERR_PHY; + goto out; + } + if (mdic & E1000_MDIC_ERROR) { + hw_dbg("MDI Error\n"); + ret_val = -E1000_ERR_PHY; + goto out; + } + *data = (u16) mdic; + +out: + return ret_val; +} + +/** + * igb_write_phy_reg_mdic - Write MDI control register + * @hw: pointer to the HW structure + * @offset: register offset to write to + * @data: data to write to register at offset + * + * Writes data to MDI control register in the PHY at offset. + **/ +s32 igb_write_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 data) +{ + struct e1000_phy_info *phy = &hw->phy; + u32 i, mdic = 0; + s32 ret_val = 0; + + if (offset > MAX_PHY_REG_ADDRESS) { + hw_dbg("PHY Address %d is out of range\n", offset); + ret_val = -E1000_ERR_PARAM; + goto out; + } + + /* Set up Op-code, Phy Address, and register offset in the MDI + * Control register. The MAC will take care of interfacing with the + * PHY to retrieve the desired data. + */ + mdic = (((u32)data) | + (offset << E1000_MDIC_REG_SHIFT) | + (phy->addr << E1000_MDIC_PHY_SHIFT) | + (E1000_MDIC_OP_WRITE)); + + wr32(E1000_MDIC, mdic); + + /* Poll the ready bit to see if the MDI read completed + * Increasing the time out as testing showed failures with + * the lower time out + */ + for (i = 0; i < (E1000_GEN_POLL_TIMEOUT * 3); i++) { + udelay(50); + mdic = rd32(E1000_MDIC); + if (mdic & E1000_MDIC_READY) + break; + } + if (!(mdic & E1000_MDIC_READY)) { + hw_dbg("MDI Write did not complete\n"); + ret_val = -E1000_ERR_PHY; + goto out; + } + if (mdic & E1000_MDIC_ERROR) { + hw_dbg("MDI Error\n"); + ret_val = -E1000_ERR_PHY; + goto out; + } + +out: + return ret_val; +} + +/** + * igb_read_phy_reg_i2c - Read PHY register using i2c + * @hw: pointer to the HW structure + * @offset: register offset to be read + * @data: pointer to the read data + * + * Reads the PHY register at offset using the i2c interface and stores the + * retrieved information in data. + **/ +s32 igb_read_phy_reg_i2c(struct e1000_hw *hw, u32 offset, u16 *data) +{ + struct e1000_phy_info *phy = &hw->phy; + u32 i, i2ccmd = 0; + + /* Set up Op-code, Phy Address, and register address in the I2CCMD + * register. The MAC will take care of interfacing with the + * PHY to retrieve the desired data. + */ + i2ccmd = ((offset << E1000_I2CCMD_REG_ADDR_SHIFT) | + (phy->addr << E1000_I2CCMD_PHY_ADDR_SHIFT) | + (E1000_I2CCMD_OPCODE_READ)); + + wr32(E1000_I2CCMD, i2ccmd); + + /* Poll the ready bit to see if the I2C read completed */ + for (i = 0; i < E1000_I2CCMD_PHY_TIMEOUT; i++) { + udelay(50); + i2ccmd = rd32(E1000_I2CCMD); + if (i2ccmd & E1000_I2CCMD_READY) + break; + } + if (!(i2ccmd & E1000_I2CCMD_READY)) { + hw_dbg("I2CCMD Read did not complete\n"); + return -E1000_ERR_PHY; + } + if (i2ccmd & E1000_I2CCMD_ERROR) { + hw_dbg("I2CCMD Error bit set\n"); + return -E1000_ERR_PHY; + } + + /* Need to byte-swap the 16-bit value. */ + *data = ((i2ccmd >> 8) & 0x00FF) | ((i2ccmd << 8) & 0xFF00); + + return 0; +} + +/** + * igb_write_phy_reg_i2c - Write PHY register using i2c + * @hw: pointer to the HW structure + * @offset: register offset to write to + * @data: data to write at register offset + * + * Writes the data to PHY register at the offset using the i2c interface. + **/ +s32 igb_write_phy_reg_i2c(struct e1000_hw *hw, u32 offset, u16 data) +{ + struct e1000_phy_info *phy = &hw->phy; + u32 i, i2ccmd = 0; + u16 phy_data_swapped; + + /* Prevent overwriting SFP I2C EEPROM which is at A0 address.*/ + if ((hw->phy.addr == 0) || (hw->phy.addr > 7)) { + hw_dbg("PHY I2C Address %d is out of range.\n", + hw->phy.addr); + return -E1000_ERR_CONFIG; + } + + /* Swap the data bytes for the I2C interface */ + phy_data_swapped = ((data >> 8) & 0x00FF) | ((data << 8) & 0xFF00); + + /* Set up Op-code, Phy Address, and register address in the I2CCMD + * register. The MAC will take care of interfacing with the + * PHY to retrieve the desired data. + */ + i2ccmd = ((offset << E1000_I2CCMD_REG_ADDR_SHIFT) | + (phy->addr << E1000_I2CCMD_PHY_ADDR_SHIFT) | + E1000_I2CCMD_OPCODE_WRITE | + phy_data_swapped); + + wr32(E1000_I2CCMD, i2ccmd); + + /* Poll the ready bit to see if the I2C read completed */ + for (i = 0; i < E1000_I2CCMD_PHY_TIMEOUT; i++) { + udelay(50); + i2ccmd = rd32(E1000_I2CCMD); + if (i2ccmd & E1000_I2CCMD_READY) + break; + } + if (!(i2ccmd & E1000_I2CCMD_READY)) { + hw_dbg("I2CCMD Write did not complete\n"); + return -E1000_ERR_PHY; + } + if (i2ccmd & E1000_I2CCMD_ERROR) { + hw_dbg("I2CCMD Error bit set\n"); + return -E1000_ERR_PHY; + } + + return 0; +} + +/** + * igb_read_sfp_data_byte - Reads SFP module data. + * @hw: pointer to the HW structure + * @offset: byte location offset to be read + * @data: read data buffer pointer + * + * Reads one byte from SFP module data stored + * in SFP resided EEPROM memory or SFP diagnostic area. + * Function should be called with + * E1000_I2CCMD_SFP_DATA_ADDR(<byte offset>) for SFP module database access + * E1000_I2CCMD_SFP_DIAG_ADDR(<byte offset>) for SFP diagnostics parameters + * access + **/ +s32 igb_read_sfp_data_byte(struct e1000_hw *hw, u16 offset, u8 *data) +{ + u32 i = 0; + u32 i2ccmd = 0; + u32 data_local = 0; + + if (offset > E1000_I2CCMD_SFP_DIAG_ADDR(255)) { + hw_dbg("I2CCMD command address exceeds upper limit\n"); + return -E1000_ERR_PHY; + } + + /* Set up Op-code, EEPROM Address,in the I2CCMD + * register. The MAC will take care of interfacing with the + * EEPROM to retrieve the desired data. + */ + i2ccmd = ((offset << E1000_I2CCMD_REG_ADDR_SHIFT) | + E1000_I2CCMD_OPCODE_READ); + + wr32(E1000_I2CCMD, i2ccmd); + + /* Poll the ready bit to see if the I2C read completed */ + for (i = 0; i < E1000_I2CCMD_PHY_TIMEOUT; i++) { + udelay(50); + data_local = rd32(E1000_I2CCMD); + if (data_local & E1000_I2CCMD_READY) + break; + } + if (!(data_local & E1000_I2CCMD_READY)) { + hw_dbg("I2CCMD Read did not complete\n"); + return -E1000_ERR_PHY; + } + if (data_local & E1000_I2CCMD_ERROR) { + hw_dbg("I2CCMD Error bit set\n"); + return -E1000_ERR_PHY; + } + *data = (u8) data_local & 0xFF; + + return 0; +} + +/** + * igb_read_phy_reg_igp - Read igp PHY register + * @hw: pointer to the HW structure + * @offset: register offset to be read + * @data: pointer to the read data + * + * Acquires semaphore, if necessary, then reads the PHY register at offset + * and storing the retrieved information in data. Release any acquired + * semaphores before exiting. + **/ +s32 igb_read_phy_reg_igp(struct e1000_hw *hw, u32 offset, u16 *data) +{ + s32 ret_val = 0; + + if (!(hw->phy.ops.acquire)) + goto out; + + ret_val = hw->phy.ops.acquire(hw); + if (ret_val) + goto out; + + if (offset > MAX_PHY_MULTI_PAGE_REG) { + ret_val = igb_write_phy_reg_mdic(hw, + IGP01E1000_PHY_PAGE_SELECT, + (u16)offset); + if (ret_val) { + hw->phy.ops.release(hw); + goto out; + } + } + + ret_val = igb_read_phy_reg_mdic(hw, MAX_PHY_REG_ADDRESS & offset, + data); + + hw->phy.ops.release(hw); + +out: + return ret_val; +} + +/** + * igb_write_phy_reg_igp - Write igp PHY register + * @hw: pointer to the HW structure + * @offset: register offset to write to + * @data: data to write at register offset + * + * Acquires semaphore, if necessary, then writes the data to PHY register + * at the offset. Release any acquired semaphores before exiting. + **/ +s32 igb_write_phy_reg_igp(struct e1000_hw *hw, u32 offset, u16 data) +{ + s32 ret_val = 0; + + if (!(hw->phy.ops.acquire)) + goto out; + + ret_val = hw->phy.ops.acquire(hw); + if (ret_val) + goto out; + + if (offset > MAX_PHY_MULTI_PAGE_REG) { + ret_val = igb_write_phy_reg_mdic(hw, + IGP01E1000_PHY_PAGE_SELECT, + (u16)offset); + if (ret_val) { + hw->phy.ops.release(hw); + goto out; + } + } + + ret_val = igb_write_phy_reg_mdic(hw, MAX_PHY_REG_ADDRESS & offset, + data); + + hw->phy.ops.release(hw); + +out: + return ret_val; +} + +/** + * igb_copper_link_setup_82580 - Setup 82580 PHY for copper link + * @hw: pointer to the HW structure + * + * Sets up Carrier-sense on Transmit and downshift values. + **/ +s32 igb_copper_link_setup_82580(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 phy_data; + + if (phy->reset_disable) { + ret_val = 0; + goto out; + } + + if (phy->type == e1000_phy_82580) { + ret_val = hw->phy.ops.reset(hw); + if (ret_val) { + hw_dbg("Error resetting the PHY.\n"); + goto out; + } + } + + /* Enable CRS on TX. This must be set for half-duplex operation. */ + ret_val = phy->ops.read_reg(hw, I82580_CFG_REG, &phy_data); + if (ret_val) + goto out; + + phy_data |= I82580_CFG_ASSERT_CRS_ON_TX; + + /* Enable downshift */ + phy_data |= I82580_CFG_ENABLE_DOWNSHIFT; + + ret_val = phy->ops.write_reg(hw, I82580_CFG_REG, phy_data); + if (ret_val) + goto out; + + /* Set MDI/MDIX mode */ + ret_val = phy->ops.read_reg(hw, I82580_PHY_CTRL_2, &phy_data); + if (ret_val) + goto out; + phy_data &= ~I82580_PHY_CTRL2_MDIX_CFG_MASK; + /* Options: + * 0 - Auto (default) + * 1 - MDI mode + * 2 - MDI-X mode + */ + switch (hw->phy.mdix) { + case 1: + break; + case 2: + phy_data |= I82580_PHY_CTRL2_MANUAL_MDIX; + break; + case 0: + default: + phy_data |= I82580_PHY_CTRL2_AUTO_MDI_MDIX; + break; + } + ret_val = hw->phy.ops.write_reg(hw, I82580_PHY_CTRL_2, phy_data); + +out: + return ret_val; +} + +/** + * igb_copper_link_setup_m88 - Setup m88 PHY's for copper link + * @hw: pointer to the HW structure + * + * Sets up MDI/MDI-X and polarity for m88 PHY's. If necessary, transmit clock + * and downshift values are set also. + **/ +s32 igb_copper_link_setup_m88(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 phy_data; + + if (phy->reset_disable) { + ret_val = 0; + goto out; + } + + /* Enable CRS on TX. This must be set for half-duplex operation. */ + ret_val = phy->ops.read_reg(hw, M88E1000_PHY_SPEC_CTRL, &phy_data); + if (ret_val) + goto out; + + phy_data |= M88E1000_PSCR_ASSERT_CRS_ON_TX; + + /* Options: + * MDI/MDI-X = 0 (default) + * 0 - Auto for all speeds + * 1 - MDI mode + * 2 - MDI-X mode + * 3 - Auto for 1000Base-T only (MDI-X for 10/100Base-T modes) + */ + phy_data &= ~M88E1000_PSCR_AUTO_X_MODE; + + switch (phy->mdix) { + case 1: + phy_data |= M88E1000_PSCR_MDI_MANUAL_MODE; + break; + case 2: + phy_data |= M88E1000_PSCR_MDIX_MANUAL_MODE; + break; + case 3: + phy_data |= M88E1000_PSCR_AUTO_X_1000T; + break; + case 0: + default: + phy_data |= M88E1000_PSCR_AUTO_X_MODE; + break; + } + + /* Options: + * disable_polarity_correction = 0 (default) + * Automatic Correction for Reversed Cable Polarity + * 0 - Disabled + * 1 - Enabled + */ + phy_data &= ~M88E1000_PSCR_POLARITY_REVERSAL; + if (phy->disable_polarity_correction == 1) + phy_data |= M88E1000_PSCR_POLARITY_REVERSAL; + + ret_val = phy->ops.write_reg(hw, M88E1000_PHY_SPEC_CTRL, phy_data); + if (ret_val) + goto out; + + if (phy->revision < E1000_REVISION_4) { + /* Force TX_CLK in the Extended PHY Specific Control Register + * to 25MHz clock. + */ + ret_val = phy->ops.read_reg(hw, M88E1000_EXT_PHY_SPEC_CTRL, + &phy_data); + if (ret_val) + goto out; + + phy_data |= M88E1000_EPSCR_TX_CLK_25; + + if ((phy->revision == E1000_REVISION_2) && + (phy->id == M88E1111_I_PHY_ID)) { + /* 82573L PHY - set the downshift counter to 5x. */ + phy_data &= ~M88EC018_EPSCR_DOWNSHIFT_COUNTER_MASK; + phy_data |= M88EC018_EPSCR_DOWNSHIFT_COUNTER_5X; + } else { + /* Configure Master and Slave downshift values */ + phy_data &= ~(M88E1000_EPSCR_MASTER_DOWNSHIFT_MASK | + M88E1000_EPSCR_SLAVE_DOWNSHIFT_MASK); + phy_data |= (M88E1000_EPSCR_MASTER_DOWNSHIFT_1X | + M88E1000_EPSCR_SLAVE_DOWNSHIFT_1X); + } + ret_val = phy->ops.write_reg(hw, M88E1000_EXT_PHY_SPEC_CTRL, + phy_data); + if (ret_val) + goto out; + } + + /* Commit the changes. */ + ret_val = igb_phy_sw_reset(hw); + if (ret_val) { + hw_dbg("Error committing the PHY changes\n"); + goto out; + } + +out: + return ret_val; +} + +/** + * igb_copper_link_setup_m88_gen2 - Setup m88 PHY's for copper link + * @hw: pointer to the HW structure + * + * Sets up MDI/MDI-X and polarity for i347-AT4, m88e1322 and m88e1112 PHY's. + * Also enables and sets the downshift parameters. + **/ +s32 igb_copper_link_setup_m88_gen2(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 phy_data; + + if (phy->reset_disable) + return 0; + + /* Enable CRS on Tx. This must be set for half-duplex operation. */ + ret_val = phy->ops.read_reg(hw, M88E1000_PHY_SPEC_CTRL, &phy_data); + if (ret_val) + return ret_val; + + /* Options: + * MDI/MDI-X = 0 (default) + * 0 - Auto for all speeds + * 1 - MDI mode + * 2 - MDI-X mode + * 3 - Auto for 1000Base-T only (MDI-X for 10/100Base-T modes) + */ + phy_data &= ~M88E1000_PSCR_AUTO_X_MODE; + + switch (phy->mdix) { + case 1: + phy_data |= M88E1000_PSCR_MDI_MANUAL_MODE; + break; + case 2: + phy_data |= M88E1000_PSCR_MDIX_MANUAL_MODE; + break; + case 3: + /* M88E1112 does not support this mode) */ + if (phy->id != M88E1112_E_PHY_ID) { + phy_data |= M88E1000_PSCR_AUTO_X_1000T; + break; + } + fallthrough; + case 0: + default: + phy_data |= M88E1000_PSCR_AUTO_X_MODE; + break; + } + + /* Options: + * disable_polarity_correction = 0 (default) + * Automatic Correction for Reversed Cable Polarity + * 0 - Disabled + * 1 - Enabled + */ + phy_data &= ~M88E1000_PSCR_POLARITY_REVERSAL; + if (phy->disable_polarity_correction == 1) + phy_data |= M88E1000_PSCR_POLARITY_REVERSAL; + + /* Enable downshift and setting it to X6 */ + if (phy->id == M88E1543_E_PHY_ID) { + phy_data &= ~I347AT4_PSCR_DOWNSHIFT_ENABLE; + ret_val = + phy->ops.write_reg(hw, M88E1000_PHY_SPEC_CTRL, phy_data); + if (ret_val) + return ret_val; + + ret_val = igb_phy_sw_reset(hw); + if (ret_val) { + hw_dbg("Error committing the PHY changes\n"); + return ret_val; + } + } + + phy_data &= ~I347AT4_PSCR_DOWNSHIFT_MASK; + phy_data |= I347AT4_PSCR_DOWNSHIFT_6X; + phy_data |= I347AT4_PSCR_DOWNSHIFT_ENABLE; + + ret_val = phy->ops.write_reg(hw, M88E1000_PHY_SPEC_CTRL, phy_data); + if (ret_val) + return ret_val; + + /* Commit the changes. */ + ret_val = igb_phy_sw_reset(hw); + if (ret_val) { + hw_dbg("Error committing the PHY changes\n"); + return ret_val; + } + ret_val = igb_set_master_slave_mode(hw); + if (ret_val) + return ret_val; + + return 0; +} + +/** + * igb_copper_link_setup_igp - Setup igp PHY's for copper link + * @hw: pointer to the HW structure + * + * Sets up LPLU, MDI/MDI-X, polarity, Smartspeed and Master/Slave config for + * igp PHY's. + **/ +s32 igb_copper_link_setup_igp(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 data; + + if (phy->reset_disable) { + ret_val = 0; + goto out; + } + + ret_val = phy->ops.reset(hw); + if (ret_val) { + hw_dbg("Error resetting the PHY.\n"); + goto out; + } + + /* Wait 100ms for MAC to configure PHY from NVM settings, to avoid + * timeout issues when LFS is enabled. + */ + msleep(100); + + /* The NVM settings will configure LPLU in D3 for + * non-IGP1 PHYs. + */ + if (phy->type == e1000_phy_igp) { + /* disable lplu d3 during driver init */ + if (phy->ops.set_d3_lplu_state) + ret_val = phy->ops.set_d3_lplu_state(hw, false); + if (ret_val) { + hw_dbg("Error Disabling LPLU D3\n"); + goto out; + } + } + + /* disable lplu d0 during driver init */ + ret_val = phy->ops.set_d0_lplu_state(hw, false); + if (ret_val) { + hw_dbg("Error Disabling LPLU D0\n"); + goto out; + } + /* Configure mdi-mdix settings */ + ret_val = phy->ops.read_reg(hw, IGP01E1000_PHY_PORT_CTRL, &data); + if (ret_val) + goto out; + + data &= ~IGP01E1000_PSCR_AUTO_MDIX; + + switch (phy->mdix) { + case 1: + data &= ~IGP01E1000_PSCR_FORCE_MDI_MDIX; + break; + case 2: + data |= IGP01E1000_PSCR_FORCE_MDI_MDIX; + break; + case 0: + default: + data |= IGP01E1000_PSCR_AUTO_MDIX; + break; + } + ret_val = phy->ops.write_reg(hw, IGP01E1000_PHY_PORT_CTRL, data); + if (ret_val) + goto out; + + /* set auto-master slave resolution settings */ + if (hw->mac.autoneg) { + /* when autonegotiation advertisement is only 1000Mbps then we + * should disable SmartSpeed and enable Auto MasterSlave + * resolution as hardware default. + */ + if (phy->autoneg_advertised == ADVERTISE_1000_FULL) { + /* Disable SmartSpeed */ + ret_val = phy->ops.read_reg(hw, + IGP01E1000_PHY_PORT_CONFIG, + &data); + if (ret_val) + goto out; + + data &= ~IGP01E1000_PSCFR_SMART_SPEED; + ret_val = phy->ops.write_reg(hw, + IGP01E1000_PHY_PORT_CONFIG, + data); + if (ret_val) + goto out; + + /* Set auto Master/Slave resolution process */ + ret_val = phy->ops.read_reg(hw, PHY_1000T_CTRL, &data); + if (ret_val) + goto out; + + data &= ~CR_1000T_MS_ENABLE; + ret_val = phy->ops.write_reg(hw, PHY_1000T_CTRL, data); + if (ret_val) + goto out; + } + + ret_val = phy->ops.read_reg(hw, PHY_1000T_CTRL, &data); + if (ret_val) + goto out; + + /* load defaults for future use */ + phy->original_ms_type = (data & CR_1000T_MS_ENABLE) ? + ((data & CR_1000T_MS_VALUE) ? + e1000_ms_force_master : + e1000_ms_force_slave) : + e1000_ms_auto; + + switch (phy->ms_type) { + case e1000_ms_force_master: + data |= (CR_1000T_MS_ENABLE | CR_1000T_MS_VALUE); + break; + case e1000_ms_force_slave: + data |= CR_1000T_MS_ENABLE; + data &= ~(CR_1000T_MS_VALUE); + break; + case e1000_ms_auto: + data &= ~CR_1000T_MS_ENABLE; + break; + default: + break; + } + ret_val = phy->ops.write_reg(hw, PHY_1000T_CTRL, data); + if (ret_val) + goto out; + } + +out: + return ret_val; +} + +/** + * igb_copper_link_autoneg - Setup/Enable autoneg for copper link + * @hw: pointer to the HW structure + * + * Performs initial bounds checking on autoneg advertisement parameter, then + * configure to advertise the full capability. Setup the PHY to autoneg + * and restart the negotiation process between the link partner. If + * autoneg_wait_to_complete, then wait for autoneg to complete before exiting. + **/ +static s32 igb_copper_link_autoneg(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 phy_ctrl; + + /* Perform some bounds checking on the autoneg advertisement + * parameter. + */ + phy->autoneg_advertised &= phy->autoneg_mask; + + /* If autoneg_advertised is zero, we assume it was not defaulted + * by the calling code so we set to advertise full capability. + */ + if (phy->autoneg_advertised == 0) + phy->autoneg_advertised = phy->autoneg_mask; + + hw_dbg("Reconfiguring auto-neg advertisement params\n"); + ret_val = igb_phy_setup_autoneg(hw); + if (ret_val) { + hw_dbg("Error Setting up Auto-Negotiation\n"); + goto out; + } + hw_dbg("Restarting Auto-Neg\n"); + + /* Restart auto-negotiation by setting the Auto Neg Enable bit and + * the Auto Neg Restart bit in the PHY control register. + */ + ret_val = phy->ops.read_reg(hw, PHY_CONTROL, &phy_ctrl); + if (ret_val) + goto out; + + phy_ctrl |= (MII_CR_AUTO_NEG_EN | MII_CR_RESTART_AUTO_NEG); + ret_val = phy->ops.write_reg(hw, PHY_CONTROL, phy_ctrl); + if (ret_val) + goto out; + + /* Does the user want to wait for Auto-Neg to complete here, or + * check at a later time (for example, callback routine). + */ + if (phy->autoneg_wait_to_complete) { + ret_val = igb_wait_autoneg(hw); + if (ret_val) { + hw_dbg("Error while waiting for autoneg to complete\n"); + goto out; + } + } + + hw->mac.get_link_status = true; + +out: + return ret_val; +} + +/** + * igb_phy_setup_autoneg - Configure PHY for auto-negotiation + * @hw: pointer to the HW structure + * + * Reads the MII auto-neg advertisement register and/or the 1000T control + * register and if the PHY is already setup for auto-negotiation, then + * return successful. Otherwise, setup advertisement and flow control to + * the appropriate values for the wanted auto-negotiation. + **/ +static s32 igb_phy_setup_autoneg(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 mii_autoneg_adv_reg; + u16 mii_1000t_ctrl_reg = 0; + + phy->autoneg_advertised &= phy->autoneg_mask; + + /* Read the MII Auto-Neg Advertisement Register (Address 4). */ + ret_val = phy->ops.read_reg(hw, PHY_AUTONEG_ADV, &mii_autoneg_adv_reg); + if (ret_val) + goto out; + + if (phy->autoneg_mask & ADVERTISE_1000_FULL) { + /* Read the MII 1000Base-T Control Register (Address 9). */ + ret_val = phy->ops.read_reg(hw, PHY_1000T_CTRL, + &mii_1000t_ctrl_reg); + if (ret_val) + goto out; + } + + /* Need to parse both autoneg_advertised and fc and set up + * the appropriate PHY registers. First we will parse for + * autoneg_advertised software override. Since we can advertise + * a plethora of combinations, we need to check each bit + * individually. + */ + + /* First we clear all the 10/100 mb speed bits in the Auto-Neg + * Advertisement Register (Address 4) and the 1000 mb speed bits in + * the 1000Base-T Control Register (Address 9). + */ + mii_autoneg_adv_reg &= ~(NWAY_AR_100TX_FD_CAPS | + NWAY_AR_100TX_HD_CAPS | + NWAY_AR_10T_FD_CAPS | + NWAY_AR_10T_HD_CAPS); + mii_1000t_ctrl_reg &= ~(CR_1000T_HD_CAPS | CR_1000T_FD_CAPS); + + hw_dbg("autoneg_advertised %x\n", phy->autoneg_advertised); + + /* Do we want to advertise 10 Mb Half Duplex? */ + if (phy->autoneg_advertised & ADVERTISE_10_HALF) { + hw_dbg("Advertise 10mb Half duplex\n"); + mii_autoneg_adv_reg |= NWAY_AR_10T_HD_CAPS; + } + + /* Do we want to advertise 10 Mb Full Duplex? */ + if (phy->autoneg_advertised & ADVERTISE_10_FULL) { + hw_dbg("Advertise 10mb Full duplex\n"); + mii_autoneg_adv_reg |= NWAY_AR_10T_FD_CAPS; + } + + /* Do we want to advertise 100 Mb Half Duplex? */ + if (phy->autoneg_advertised & ADVERTISE_100_HALF) { + hw_dbg("Advertise 100mb Half duplex\n"); + mii_autoneg_adv_reg |= NWAY_AR_100TX_HD_CAPS; + } + + /* Do we want to advertise 100 Mb Full Duplex? */ + if (phy->autoneg_advertised & ADVERTISE_100_FULL) { + hw_dbg("Advertise 100mb Full duplex\n"); + mii_autoneg_adv_reg |= NWAY_AR_100TX_FD_CAPS; + } + + /* We do not allow the Phy to advertise 1000 Mb Half Duplex */ + if (phy->autoneg_advertised & ADVERTISE_1000_HALF) + hw_dbg("Advertise 1000mb Half duplex request denied!\n"); + + /* Do we want to advertise 1000 Mb Full Duplex? */ + if (phy->autoneg_advertised & ADVERTISE_1000_FULL) { + hw_dbg("Advertise 1000mb Full duplex\n"); + mii_1000t_ctrl_reg |= CR_1000T_FD_CAPS; + } + + /* Check for a software override of the flow control settings, and + * setup the PHY advertisement registers accordingly. If + * auto-negotiation is enabled, then software will have to set the + * "PAUSE" bits to the correct value in the Auto-Negotiation + * Advertisement Register (PHY_AUTONEG_ADV) and re-start auto- + * negotiation. + * + * The possible values of the "fc" parameter are: + * 0: Flow control is completely disabled + * 1: Rx flow control is enabled (we can receive pause frames + * but not send pause frames). + * 2: Tx flow control is enabled (we can send pause frames + * but we do not support receiving pause frames). + * 3: Both Rx and TX flow control (symmetric) are enabled. + * other: No software override. The flow control configuration + * in the EEPROM is used. + */ + switch (hw->fc.current_mode) { + case e1000_fc_none: + /* Flow control (RX & TX) is completely disabled by a + * software over-ride. + */ + mii_autoneg_adv_reg &= ~(NWAY_AR_ASM_DIR | NWAY_AR_PAUSE); + break; + case e1000_fc_rx_pause: + /* RX Flow control is enabled, and TX Flow control is + * disabled, by a software over-ride. + * + * Since there really isn't a way to advertise that we are + * capable of RX Pause ONLY, we will advertise that we + * support both symmetric and asymmetric RX PAUSE. Later + * (in e1000_config_fc_after_link_up) we will disable the + * hw's ability to send PAUSE frames. + */ + mii_autoneg_adv_reg |= (NWAY_AR_ASM_DIR | NWAY_AR_PAUSE); + break; + case e1000_fc_tx_pause: + /* TX Flow control is enabled, and RX Flow control is + * disabled, by a software over-ride. + */ + mii_autoneg_adv_reg |= NWAY_AR_ASM_DIR; + mii_autoneg_adv_reg &= ~NWAY_AR_PAUSE; + break; + case e1000_fc_full: + /* Flow control (both RX and TX) is enabled by a software + * over-ride. + */ + mii_autoneg_adv_reg |= (NWAY_AR_ASM_DIR | NWAY_AR_PAUSE); + break; + default: + hw_dbg("Flow control param set incorrectly\n"); + ret_val = -E1000_ERR_CONFIG; + goto out; + } + + ret_val = phy->ops.write_reg(hw, PHY_AUTONEG_ADV, mii_autoneg_adv_reg); + if (ret_val) + goto out; + + hw_dbg("Auto-Neg Advertising %x\n", mii_autoneg_adv_reg); + + if (phy->autoneg_mask & ADVERTISE_1000_FULL) { + ret_val = phy->ops.write_reg(hw, + PHY_1000T_CTRL, + mii_1000t_ctrl_reg); + if (ret_val) + goto out; + } + +out: + return ret_val; +} + +/** + * igb_setup_copper_link - Configure copper link settings + * @hw: pointer to the HW structure + * + * Calls the appropriate function to configure the link for auto-neg or forced + * speed and duplex. Then we check for link, once link is established calls + * to configure collision distance and flow control are called. If link is + * not established, we return -E1000_ERR_PHY (-2). + **/ +s32 igb_setup_copper_link(struct e1000_hw *hw) +{ + s32 ret_val; + bool link; + + if (hw->mac.autoneg) { + /* Setup autoneg and flow control advertisement and perform + * autonegotiation. + */ + ret_val = igb_copper_link_autoneg(hw); + if (ret_val) + goto out; + } else { + /* PHY will be set to 10H, 10F, 100H or 100F + * depending on user settings. + */ + hw_dbg("Forcing Speed and Duplex\n"); + ret_val = hw->phy.ops.force_speed_duplex(hw); + if (ret_val) { + hw_dbg("Error Forcing Speed and Duplex\n"); + goto out; + } + } + + /* Check link status. Wait up to 100 microseconds for link to become + * valid. + */ + ret_val = igb_phy_has_link(hw, COPPER_LINK_UP_LIMIT, 10, &link); + if (ret_val) + goto out; + + if (link) { + hw_dbg("Valid link established!!!\n"); + igb_config_collision_dist(hw); + ret_val = igb_config_fc_after_link_up(hw); + } else { + hw_dbg("Unable to establish link!!!\n"); + } + +out: + return ret_val; +} + +/** + * igb_phy_force_speed_duplex_igp - Force speed/duplex for igp PHY + * @hw: pointer to the HW structure + * + * Calls the PHY setup function to force speed and duplex. Clears the + * auto-crossover to force MDI manually. Waits for link and returns + * successful if link up is successful, else -E1000_ERR_PHY (-2). + **/ +s32 igb_phy_force_speed_duplex_igp(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 phy_data; + bool link; + + ret_val = phy->ops.read_reg(hw, PHY_CONTROL, &phy_data); + if (ret_val) + goto out; + + igb_phy_force_speed_duplex_setup(hw, &phy_data); + + ret_val = phy->ops.write_reg(hw, PHY_CONTROL, phy_data); + if (ret_val) + goto out; + + /* Clear Auto-Crossover to force MDI manually. IGP requires MDI + * forced whenever speed and duplex are forced. + */ + ret_val = phy->ops.read_reg(hw, IGP01E1000_PHY_PORT_CTRL, &phy_data); + if (ret_val) + goto out; + + phy_data &= ~IGP01E1000_PSCR_AUTO_MDIX; + phy_data &= ~IGP01E1000_PSCR_FORCE_MDI_MDIX; + + ret_val = phy->ops.write_reg(hw, IGP01E1000_PHY_PORT_CTRL, phy_data); + if (ret_val) + goto out; + + hw_dbg("IGP PSCR: %X\n", phy_data); + + udelay(1); + + if (phy->autoneg_wait_to_complete) { + hw_dbg("Waiting for forced speed/duplex link on IGP phy.\n"); + + ret_val = igb_phy_has_link(hw, PHY_FORCE_LIMIT, 10000, &link); + if (ret_val) + goto out; + + if (!link) + hw_dbg("Link taking longer than expected.\n"); + + /* Try once more */ + ret_val = igb_phy_has_link(hw, PHY_FORCE_LIMIT, 10000, &link); + if (ret_val) + goto out; + } + +out: + return ret_val; +} + +/** + * igb_phy_force_speed_duplex_m88 - Force speed/duplex for m88 PHY + * @hw: pointer to the HW structure + * + * Calls the PHY setup function to force speed and duplex. Clears the + * auto-crossover to force MDI manually. Resets the PHY to commit the + * changes. If time expires while waiting for link up, we reset the DSP. + * After reset, TX_CLK and CRS on TX must be set. Return successful upon + * successful completion, else return corresponding error code. + **/ +s32 igb_phy_force_speed_duplex_m88(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 phy_data; + bool link; + + /* I210 and I211 devices support Auto-Crossover in forced operation. */ + if (phy->type != e1000_phy_i210) { + /* Clear Auto-Crossover to force MDI manually. M88E1000 + * requires MDI forced whenever speed and duplex are forced. + */ + ret_val = phy->ops.read_reg(hw, M88E1000_PHY_SPEC_CTRL, + &phy_data); + if (ret_val) + goto out; + + phy_data &= ~M88E1000_PSCR_AUTO_X_MODE; + ret_val = phy->ops.write_reg(hw, M88E1000_PHY_SPEC_CTRL, + phy_data); + if (ret_val) + goto out; + + hw_dbg("M88E1000 PSCR: %X\n", phy_data); + } + + ret_val = phy->ops.read_reg(hw, PHY_CONTROL, &phy_data); + if (ret_val) + goto out; + + igb_phy_force_speed_duplex_setup(hw, &phy_data); + + ret_val = phy->ops.write_reg(hw, PHY_CONTROL, phy_data); + if (ret_val) + goto out; + + /* Reset the phy to commit changes. */ + ret_val = igb_phy_sw_reset(hw); + if (ret_val) + goto out; + + if (phy->autoneg_wait_to_complete) { + hw_dbg("Waiting for forced speed/duplex link on M88 phy.\n"); + + ret_val = igb_phy_has_link(hw, PHY_FORCE_LIMIT, 100000, &link); + if (ret_val) + goto out; + + if (!link) { + bool reset_dsp = true; + + switch (hw->phy.id) { + case I347AT4_E_PHY_ID: + case M88E1112_E_PHY_ID: + case M88E1543_E_PHY_ID: + case M88E1512_E_PHY_ID: + case I210_I_PHY_ID: + reset_dsp = false; + break; + default: + if (hw->phy.type != e1000_phy_m88) + reset_dsp = false; + break; + } + if (!reset_dsp) { + hw_dbg("Link taking longer than expected.\n"); + } else { + /* We didn't get link. + * Reset the DSP and cross our fingers. + */ + ret_val = phy->ops.write_reg(hw, + M88E1000_PHY_PAGE_SELECT, + 0x001d); + if (ret_val) + goto out; + ret_val = igb_phy_reset_dsp(hw); + if (ret_val) + goto out; + } + } + + /* Try once more */ + ret_val = igb_phy_has_link(hw, PHY_FORCE_LIMIT, + 100000, &link); + if (ret_val) + goto out; + } + + if (hw->phy.type != e1000_phy_m88 || + hw->phy.id == I347AT4_E_PHY_ID || + hw->phy.id == M88E1112_E_PHY_ID || + hw->phy.id == M88E1543_E_PHY_ID || + hw->phy.id == M88E1512_E_PHY_ID || + hw->phy.id == I210_I_PHY_ID) + goto out; + + ret_val = phy->ops.read_reg(hw, M88E1000_EXT_PHY_SPEC_CTRL, &phy_data); + if (ret_val) + goto out; + + /* Resetting the phy means we need to re-force TX_CLK in the + * Extended PHY Specific Control Register to 25MHz clock from + * the reset value of 2.5MHz. + */ + phy_data |= M88E1000_EPSCR_TX_CLK_25; + ret_val = phy->ops.write_reg(hw, M88E1000_EXT_PHY_SPEC_CTRL, phy_data); + if (ret_val) + goto out; + + /* In addition, we must re-enable CRS on Tx for both half and full + * duplex. + */ + ret_val = phy->ops.read_reg(hw, M88E1000_PHY_SPEC_CTRL, &phy_data); + if (ret_val) + goto out; + + phy_data |= M88E1000_PSCR_ASSERT_CRS_ON_TX; + ret_val = phy->ops.write_reg(hw, M88E1000_PHY_SPEC_CTRL, phy_data); + +out: + return ret_val; +} + +/** + * igb_phy_force_speed_duplex_setup - Configure forced PHY speed/duplex + * @hw: pointer to the HW structure + * @phy_ctrl: pointer to current value of PHY_CONTROL + * + * Forces speed and duplex on the PHY by doing the following: disable flow + * control, force speed/duplex on the MAC, disable auto speed detection, + * disable auto-negotiation, configure duplex, configure speed, configure + * the collision distance, write configuration to CTRL register. The + * caller must write to the PHY_CONTROL register for these settings to + * take affect. + **/ +static void igb_phy_force_speed_duplex_setup(struct e1000_hw *hw, + u16 *phy_ctrl) +{ + struct e1000_mac_info *mac = &hw->mac; + u32 ctrl; + + /* Turn off flow control when forcing speed/duplex */ + hw->fc.current_mode = e1000_fc_none; + + /* Force speed/duplex on the mac */ + ctrl = rd32(E1000_CTRL); + ctrl |= (E1000_CTRL_FRCSPD | E1000_CTRL_FRCDPX); + ctrl &= ~E1000_CTRL_SPD_SEL; + + /* Disable Auto Speed Detection */ + ctrl &= ~E1000_CTRL_ASDE; + + /* Disable autoneg on the phy */ + *phy_ctrl &= ~MII_CR_AUTO_NEG_EN; + + /* Forcing Full or Half Duplex? */ + if (mac->forced_speed_duplex & E1000_ALL_HALF_DUPLEX) { + ctrl &= ~E1000_CTRL_FD; + *phy_ctrl &= ~MII_CR_FULL_DUPLEX; + hw_dbg("Half Duplex\n"); + } else { + ctrl |= E1000_CTRL_FD; + *phy_ctrl |= MII_CR_FULL_DUPLEX; + hw_dbg("Full Duplex\n"); + } + + /* Forcing 10mb or 100mb? */ + if (mac->forced_speed_duplex & E1000_ALL_100_SPEED) { + ctrl |= E1000_CTRL_SPD_100; + *phy_ctrl |= MII_CR_SPEED_100; + *phy_ctrl &= ~(MII_CR_SPEED_1000 | MII_CR_SPEED_10); + hw_dbg("Forcing 100mb\n"); + } else { + ctrl &= ~(E1000_CTRL_SPD_1000 | E1000_CTRL_SPD_100); + *phy_ctrl |= MII_CR_SPEED_10; + *phy_ctrl &= ~(MII_CR_SPEED_1000 | MII_CR_SPEED_100); + hw_dbg("Forcing 10mb\n"); + } + + igb_config_collision_dist(hw); + + wr32(E1000_CTRL, ctrl); +} + +/** + * igb_set_d3_lplu_state - Sets low power link up state for D3 + * @hw: pointer to the HW structure + * @active: boolean used to enable/disable lplu + * + * Success returns 0, Failure returns 1 + * + * The low power link up (lplu) state is set to the power management level D3 + * and SmartSpeed is disabled when active is true, else clear lplu for D3 + * and enable Smartspeed. LPLU and Smartspeed are mutually exclusive. LPLU + * is used during Dx states where the power conservation is most important. + * During driver activity, SmartSpeed should be enabled so performance is + * maintained. + **/ +s32 igb_set_d3_lplu_state(struct e1000_hw *hw, bool active) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val = 0; + u16 data; + + if (!(hw->phy.ops.read_reg)) + goto out; + + ret_val = phy->ops.read_reg(hw, IGP02E1000_PHY_POWER_MGMT, &data); + if (ret_val) + goto out; + + if (!active) { + data &= ~IGP02E1000_PM_D3_LPLU; + ret_val = phy->ops.write_reg(hw, IGP02E1000_PHY_POWER_MGMT, + data); + if (ret_val) + goto out; + /* LPLU and SmartSpeed are mutually exclusive. LPLU is used + * during Dx states where the power conservation is most + * important. During driver activity we should enable + * SmartSpeed, so performance is maintained. + */ + if (phy->smart_speed == e1000_smart_speed_on) { + ret_val = phy->ops.read_reg(hw, + IGP01E1000_PHY_PORT_CONFIG, + &data); + if (ret_val) + goto out; + + data |= IGP01E1000_PSCFR_SMART_SPEED; + ret_val = phy->ops.write_reg(hw, + IGP01E1000_PHY_PORT_CONFIG, + data); + if (ret_val) + goto out; + } else if (phy->smart_speed == e1000_smart_speed_off) { + ret_val = phy->ops.read_reg(hw, + IGP01E1000_PHY_PORT_CONFIG, + &data); + if (ret_val) + goto out; + + data &= ~IGP01E1000_PSCFR_SMART_SPEED; + ret_val = phy->ops.write_reg(hw, + IGP01E1000_PHY_PORT_CONFIG, + data); + if (ret_val) + goto out; + } + } else if ((phy->autoneg_advertised == E1000_ALL_SPEED_DUPLEX) || + (phy->autoneg_advertised == E1000_ALL_NOT_GIG) || + (phy->autoneg_advertised == E1000_ALL_10_SPEED)) { + data |= IGP02E1000_PM_D3_LPLU; + ret_val = phy->ops.write_reg(hw, IGP02E1000_PHY_POWER_MGMT, + data); + if (ret_val) + goto out; + + /* When LPLU is enabled, we should disable SmartSpeed */ + ret_val = phy->ops.read_reg(hw, IGP01E1000_PHY_PORT_CONFIG, + &data); + if (ret_val) + goto out; + + data &= ~IGP01E1000_PSCFR_SMART_SPEED; + ret_val = phy->ops.write_reg(hw, IGP01E1000_PHY_PORT_CONFIG, + data); + } + +out: + return ret_val; +} + +/** + * igb_check_downshift - Checks whether a downshift in speed occurred + * @hw: pointer to the HW structure + * + * Success returns 0, Failure returns 1 + * + * A downshift is detected by querying the PHY link health. + **/ +s32 igb_check_downshift(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 phy_data, offset, mask; + + switch (phy->type) { + case e1000_phy_i210: + case e1000_phy_m88: + case e1000_phy_gg82563: + offset = M88E1000_PHY_SPEC_STATUS; + mask = M88E1000_PSSR_DOWNSHIFT; + break; + case e1000_phy_igp_2: + case e1000_phy_igp: + case e1000_phy_igp_3: + offset = IGP01E1000_PHY_LINK_HEALTH; + mask = IGP01E1000_PLHR_SS_DOWNGRADE; + break; + default: + /* speed downshift not supported */ + phy->speed_downgraded = false; + ret_val = 0; + goto out; + } + + ret_val = phy->ops.read_reg(hw, offset, &phy_data); + + if (!ret_val) + phy->speed_downgraded = (phy_data & mask) ? true : false; + +out: + return ret_val; +} + +/** + * igb_check_polarity_m88 - Checks the polarity. + * @hw: pointer to the HW structure + * + * Success returns 0, Failure returns -E1000_ERR_PHY (-2) + * + * Polarity is determined based on the PHY specific status register. + **/ +s32 igb_check_polarity_m88(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 data; + + ret_val = phy->ops.read_reg(hw, M88E1000_PHY_SPEC_STATUS, &data); + + if (!ret_val) + phy->cable_polarity = (data & M88E1000_PSSR_REV_POLARITY) + ? e1000_rev_polarity_reversed + : e1000_rev_polarity_normal; + + return ret_val; +} + +/** + * igb_check_polarity_igp - Checks the polarity. + * @hw: pointer to the HW structure + * + * Success returns 0, Failure returns -E1000_ERR_PHY (-2) + * + * Polarity is determined based on the PHY port status register, and the + * current speed (since there is no polarity at 100Mbps). + **/ +static s32 igb_check_polarity_igp(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 data, offset, mask; + + /* Polarity is determined based on the speed of + * our connection. + */ + ret_val = phy->ops.read_reg(hw, IGP01E1000_PHY_PORT_STATUS, &data); + if (ret_val) + goto out; + + if ((data & IGP01E1000_PSSR_SPEED_MASK) == + IGP01E1000_PSSR_SPEED_1000MBPS) { + offset = IGP01E1000_PHY_PCS_INIT_REG; + mask = IGP01E1000_PHY_POLARITY_MASK; + } else { + /* This really only applies to 10Mbps since + * there is no polarity for 100Mbps (always 0). + */ + offset = IGP01E1000_PHY_PORT_STATUS; + mask = IGP01E1000_PSSR_POLARITY_REVERSED; + } + + ret_val = phy->ops.read_reg(hw, offset, &data); + + if (!ret_val) + phy->cable_polarity = (data & mask) + ? e1000_rev_polarity_reversed + : e1000_rev_polarity_normal; + +out: + return ret_val; +} + +/** + * igb_wait_autoneg - Wait for auto-neg completion + * @hw: pointer to the HW structure + * + * Waits for auto-negotiation to complete or for the auto-negotiation time + * limit to expire, which ever happens first. + **/ +static s32 igb_wait_autoneg(struct e1000_hw *hw) +{ + s32 ret_val = 0; + u16 i, phy_status; + + /* Break after autoneg completes or PHY_AUTO_NEG_LIMIT expires. */ + for (i = PHY_AUTO_NEG_LIMIT; i > 0; i--) { + ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, &phy_status); + if (ret_val) + break; + ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, &phy_status); + if (ret_val) + break; + if (phy_status & MII_SR_AUTONEG_COMPLETE) + break; + msleep(100); + } + + /* PHY_AUTO_NEG_TIME expiration doesn't guarantee auto-negotiation + * has completed. + */ + return ret_val; +} + +/** + * igb_phy_has_link - Polls PHY for link + * @hw: pointer to the HW structure + * @iterations: number of times to poll for link + * @usec_interval: delay between polling attempts + * @success: pointer to whether polling was successful or not + * + * Polls the PHY status register for link, 'iterations' number of times. + **/ +s32 igb_phy_has_link(struct e1000_hw *hw, u32 iterations, + u32 usec_interval, bool *success) +{ + s32 ret_val = 0; + u16 i, phy_status; + + for (i = 0; i < iterations; i++) { + /* Some PHYs require the PHY_STATUS register to be read + * twice due to the link bit being sticky. No harm doing + * it across the board. + */ + ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, &phy_status); + if (ret_val && usec_interval > 0) { + /* If the first read fails, another entity may have + * ownership of the resources, wait and try again to + * see if they have relinquished the resources yet. + */ + if (usec_interval >= 1000) + mdelay(usec_interval/1000); + else + udelay(usec_interval); + } + ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, &phy_status); + if (ret_val) + break; + if (phy_status & MII_SR_LINK_STATUS) + break; + if (usec_interval >= 1000) + mdelay(usec_interval/1000); + else + udelay(usec_interval); + } + + *success = (i < iterations) ? true : false; + + return ret_val; +} + +/** + * igb_get_cable_length_m88 - Determine cable length for m88 PHY + * @hw: pointer to the HW structure + * + * Reads the PHY specific status register to retrieve the cable length + * information. The cable length is determined by averaging the minimum and + * maximum values to get the "average" cable length. The m88 PHY has four + * possible cable length values, which are: + * Register Value Cable Length + * 0 < 50 meters + * 1 50 - 80 meters + * 2 80 - 110 meters + * 3 110 - 140 meters + * 4 > 140 meters + **/ +s32 igb_get_cable_length_m88(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 phy_data, index; + + ret_val = phy->ops.read_reg(hw, M88E1000_PHY_SPEC_STATUS, &phy_data); + if (ret_val) + goto out; + + index = (phy_data & M88E1000_PSSR_CABLE_LENGTH) >> + M88E1000_PSSR_CABLE_LENGTH_SHIFT; + if (index >= ARRAY_SIZE(e1000_m88_cable_length_table) - 1) { + ret_val = -E1000_ERR_PHY; + goto out; + } + + phy->min_cable_length = e1000_m88_cable_length_table[index]; + phy->max_cable_length = e1000_m88_cable_length_table[index + 1]; + + phy->cable_length = (phy->min_cable_length + phy->max_cable_length) / 2; + +out: + return ret_val; +} + +s32 igb_get_cable_length_m88_gen2(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 phy_data, phy_data2, index, default_page, is_cm; + int len_tot = 0; + u16 len_min; + u16 len_max; + + switch (hw->phy.id) { + case M88E1543_E_PHY_ID: + case M88E1512_E_PHY_ID: + case I347AT4_E_PHY_ID: + case I210_I_PHY_ID: + /* Remember the original page select and set it to 7 */ + ret_val = phy->ops.read_reg(hw, I347AT4_PAGE_SELECT, + &default_page); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, I347AT4_PAGE_SELECT, 0x07); + if (ret_val) + goto out; + + /* Check if the unit of cable length is meters or cm */ + ret_val = phy->ops.read_reg(hw, I347AT4_PCDC, &phy_data2); + if (ret_val) + goto out; + + is_cm = !(phy_data2 & I347AT4_PCDC_CABLE_LENGTH_UNIT); + + /* Get cable length from Pair 0 length Regs */ + ret_val = phy->ops.read_reg(hw, I347AT4_PCDL0, &phy_data); + if (ret_val) + goto out; + + phy->pair_length[0] = phy_data / (is_cm ? 100 : 1); + len_tot = phy->pair_length[0]; + len_min = phy->pair_length[0]; + len_max = phy->pair_length[0]; + + /* Get cable length from Pair 1 length Regs */ + ret_val = phy->ops.read_reg(hw, I347AT4_PCDL1, &phy_data); + if (ret_val) + goto out; + + phy->pair_length[1] = phy_data / (is_cm ? 100 : 1); + len_tot += phy->pair_length[1]; + len_min = min(len_min, phy->pair_length[1]); + len_max = max(len_max, phy->pair_length[1]); + + /* Get cable length from Pair 2 length Regs */ + ret_val = phy->ops.read_reg(hw, I347AT4_PCDL2, &phy_data); + if (ret_val) + goto out; + + phy->pair_length[2] = phy_data / (is_cm ? 100 : 1); + len_tot += phy->pair_length[2]; + len_min = min(len_min, phy->pair_length[2]); + len_max = max(len_max, phy->pair_length[2]); + + /* Get cable length from Pair 3 length Regs */ + ret_val = phy->ops.read_reg(hw, I347AT4_PCDL3, &phy_data); + if (ret_val) + goto out; + + phy->pair_length[3] = phy_data / (is_cm ? 100 : 1); + len_tot += phy->pair_length[3]; + len_min = min(len_min, phy->pair_length[3]); + len_max = max(len_max, phy->pair_length[3]); + + /* Populate the phy structure with cable length in meters */ + phy->min_cable_length = len_min; + phy->max_cable_length = len_max; + phy->cable_length = len_tot / 4; + + /* Reset the page selec to its original value */ + ret_val = phy->ops.write_reg(hw, I347AT4_PAGE_SELECT, + default_page); + if (ret_val) + goto out; + break; + case M88E1112_E_PHY_ID: + /* Remember the original page select and set it to 5 */ + ret_val = phy->ops.read_reg(hw, I347AT4_PAGE_SELECT, + &default_page); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, I347AT4_PAGE_SELECT, 0x05); + if (ret_val) + goto out; + + ret_val = phy->ops.read_reg(hw, M88E1112_VCT_DSP_DISTANCE, + &phy_data); + if (ret_val) + goto out; + + index = (phy_data & M88E1000_PSSR_CABLE_LENGTH) >> + M88E1000_PSSR_CABLE_LENGTH_SHIFT; + if (index >= ARRAY_SIZE(e1000_m88_cable_length_table) - 1) { + ret_val = -E1000_ERR_PHY; + goto out; + } + + phy->min_cable_length = e1000_m88_cable_length_table[index]; + phy->max_cable_length = e1000_m88_cable_length_table[index + 1]; + + phy->cable_length = (phy->min_cable_length + + phy->max_cable_length) / 2; + + /* Reset the page select to its original value */ + ret_val = phy->ops.write_reg(hw, I347AT4_PAGE_SELECT, + default_page); + if (ret_val) + goto out; + + break; + default: + ret_val = -E1000_ERR_PHY; + goto out; + } + +out: + return ret_val; +} + +/** + * igb_get_cable_length_igp_2 - Determine cable length for igp2 PHY + * @hw: pointer to the HW structure + * + * The automatic gain control (agc) normalizes the amplitude of the + * received signal, adjusting for the attenuation produced by the + * cable. By reading the AGC registers, which represent the + * combination of coarse and fine gain value, the value can be put + * into a lookup table to obtain the approximate cable length + * for each channel. + **/ +s32 igb_get_cable_length_igp_2(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val = 0; + u16 phy_data, i, agc_value = 0; + u16 cur_agc_index, max_agc_index = 0; + u16 min_agc_index = ARRAY_SIZE(e1000_igp_2_cable_length_table) - 1; + static const u16 agc_reg_array[IGP02E1000_PHY_CHANNEL_NUM] = { + IGP02E1000_PHY_AGC_A, + IGP02E1000_PHY_AGC_B, + IGP02E1000_PHY_AGC_C, + IGP02E1000_PHY_AGC_D + }; + + /* Read the AGC registers for all channels */ + for (i = 0; i < IGP02E1000_PHY_CHANNEL_NUM; i++) { + ret_val = phy->ops.read_reg(hw, agc_reg_array[i], &phy_data); + if (ret_val) + goto out; + + /* Getting bits 15:9, which represent the combination of + * coarse and fine gain values. The result is a number + * that can be put into the lookup table to obtain the + * approximate cable length. + */ + cur_agc_index = (phy_data >> IGP02E1000_AGC_LENGTH_SHIFT) & + IGP02E1000_AGC_LENGTH_MASK; + + /* Array index bound check. */ + if ((cur_agc_index >= ARRAY_SIZE(e1000_igp_2_cable_length_table)) || + (cur_agc_index == 0)) { + ret_val = -E1000_ERR_PHY; + goto out; + } + + /* Remove min & max AGC values from calculation. */ + if (e1000_igp_2_cable_length_table[min_agc_index] > + e1000_igp_2_cable_length_table[cur_agc_index]) + min_agc_index = cur_agc_index; + if (e1000_igp_2_cable_length_table[max_agc_index] < + e1000_igp_2_cable_length_table[cur_agc_index]) + max_agc_index = cur_agc_index; + + agc_value += e1000_igp_2_cable_length_table[cur_agc_index]; + } + + agc_value -= (e1000_igp_2_cable_length_table[min_agc_index] + + e1000_igp_2_cable_length_table[max_agc_index]); + agc_value /= (IGP02E1000_PHY_CHANNEL_NUM - 2); + + /* Calculate cable length with the error range of +/- 10 meters. */ + phy->min_cable_length = ((agc_value - IGP02E1000_AGC_RANGE) > 0) ? + (agc_value - IGP02E1000_AGC_RANGE) : 0; + phy->max_cable_length = agc_value + IGP02E1000_AGC_RANGE; + + phy->cable_length = (phy->min_cable_length + phy->max_cable_length) / 2; + +out: + return ret_val; +} + +/** + * igb_get_phy_info_m88 - Retrieve PHY information + * @hw: pointer to the HW structure + * + * Valid for only copper links. Read the PHY status register (sticky read) + * to verify that link is up. Read the PHY special control register to + * determine the polarity and 10base-T extended distance. Read the PHY + * special status register to determine MDI/MDIx and current speed. If + * speed is 1000, then determine cable length, local and remote receiver. + **/ +s32 igb_get_phy_info_m88(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 phy_data; + bool link; + + if (phy->media_type != e1000_media_type_copper) { + hw_dbg("Phy info is only valid for copper media\n"); + ret_val = -E1000_ERR_CONFIG; + goto out; + } + + ret_val = igb_phy_has_link(hw, 1, 0, &link); + if (ret_val) + goto out; + + if (!link) { + hw_dbg("Phy info is only valid if link is up\n"); + ret_val = -E1000_ERR_CONFIG; + goto out; + } + + ret_val = phy->ops.read_reg(hw, M88E1000_PHY_SPEC_CTRL, &phy_data); + if (ret_val) + goto out; + + phy->polarity_correction = (phy_data & M88E1000_PSCR_POLARITY_REVERSAL) + ? true : false; + + ret_val = igb_check_polarity_m88(hw); + if (ret_val) + goto out; + + ret_val = phy->ops.read_reg(hw, M88E1000_PHY_SPEC_STATUS, &phy_data); + if (ret_val) + goto out; + + phy->is_mdix = (phy_data & M88E1000_PSSR_MDIX) ? true : false; + + if ((phy_data & M88E1000_PSSR_SPEED) == M88E1000_PSSR_1000MBS) { + ret_val = phy->ops.get_cable_length(hw); + if (ret_val) + goto out; + + ret_val = phy->ops.read_reg(hw, PHY_1000T_STATUS, &phy_data); + if (ret_val) + goto out; + + phy->local_rx = (phy_data & SR_1000T_LOCAL_RX_STATUS) + ? e1000_1000t_rx_status_ok + : e1000_1000t_rx_status_not_ok; + + phy->remote_rx = (phy_data & SR_1000T_REMOTE_RX_STATUS) + ? e1000_1000t_rx_status_ok + : e1000_1000t_rx_status_not_ok; + } else { + /* Set values to "undefined" */ + phy->cable_length = E1000_CABLE_LENGTH_UNDEFINED; + phy->local_rx = e1000_1000t_rx_status_undefined; + phy->remote_rx = e1000_1000t_rx_status_undefined; + } + +out: + return ret_val; +} + +/** + * igb_get_phy_info_igp - Retrieve igp PHY information + * @hw: pointer to the HW structure + * + * Read PHY status to determine if link is up. If link is up, then + * set/determine 10base-T extended distance and polarity correction. Read + * PHY port status to determine MDI/MDIx and speed. Based on the speed, + * determine on the cable length, local and remote receiver. + **/ +s32 igb_get_phy_info_igp(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 data; + bool link; + + ret_val = igb_phy_has_link(hw, 1, 0, &link); + if (ret_val) + goto out; + + if (!link) { + hw_dbg("Phy info is only valid if link is up\n"); + ret_val = -E1000_ERR_CONFIG; + goto out; + } + + phy->polarity_correction = true; + + ret_val = igb_check_polarity_igp(hw); + if (ret_val) + goto out; + + ret_val = phy->ops.read_reg(hw, IGP01E1000_PHY_PORT_STATUS, &data); + if (ret_val) + goto out; + + phy->is_mdix = (data & IGP01E1000_PSSR_MDIX) ? true : false; + + if ((data & IGP01E1000_PSSR_SPEED_MASK) == + IGP01E1000_PSSR_SPEED_1000MBPS) { + ret_val = phy->ops.get_cable_length(hw); + if (ret_val) + goto out; + + ret_val = phy->ops.read_reg(hw, PHY_1000T_STATUS, &data); + if (ret_val) + goto out; + + phy->local_rx = (data & SR_1000T_LOCAL_RX_STATUS) + ? e1000_1000t_rx_status_ok + : e1000_1000t_rx_status_not_ok; + + phy->remote_rx = (data & SR_1000T_REMOTE_RX_STATUS) + ? e1000_1000t_rx_status_ok + : e1000_1000t_rx_status_not_ok; + } else { + phy->cable_length = E1000_CABLE_LENGTH_UNDEFINED; + phy->local_rx = e1000_1000t_rx_status_undefined; + phy->remote_rx = e1000_1000t_rx_status_undefined; + } + +out: + return ret_val; +} + +/** + * igb_phy_sw_reset - PHY software reset + * @hw: pointer to the HW structure + * + * Does a software reset of the PHY by reading the PHY control register and + * setting/write the control register reset bit to the PHY. + **/ +s32 igb_phy_sw_reset(struct e1000_hw *hw) +{ + s32 ret_val = 0; + u16 phy_ctrl; + + if (!(hw->phy.ops.read_reg)) + goto out; + + ret_val = hw->phy.ops.read_reg(hw, PHY_CONTROL, &phy_ctrl); + if (ret_val) + goto out; + + phy_ctrl |= MII_CR_RESET; + ret_val = hw->phy.ops.write_reg(hw, PHY_CONTROL, phy_ctrl); + if (ret_val) + goto out; + + udelay(1); + +out: + return ret_val; +} + +/** + * igb_phy_hw_reset - PHY hardware reset + * @hw: pointer to the HW structure + * + * Verify the reset block is not blocking us from resetting. Acquire + * semaphore (if necessary) and read/set/write the device control reset + * bit in the PHY. Wait the appropriate delay time for the device to + * reset and release the semaphore (if necessary). + **/ +s32 igb_phy_hw_reset(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u32 ctrl; + + ret_val = igb_check_reset_block(hw); + if (ret_val) { + ret_val = 0; + goto out; + } + + ret_val = phy->ops.acquire(hw); + if (ret_val) + goto out; + + ctrl = rd32(E1000_CTRL); + wr32(E1000_CTRL, ctrl | E1000_CTRL_PHY_RST); + wrfl(); + + udelay(phy->reset_delay_us); + + wr32(E1000_CTRL, ctrl); + wrfl(); + + udelay(150); + + phy->ops.release(hw); + + ret_val = phy->ops.get_cfg_done(hw); + +out: + return ret_val; +} + +/** + * igb_phy_init_script_igp3 - Inits the IGP3 PHY + * @hw: pointer to the HW structure + * + * Initializes a Intel Gigabit PHY3 when an EEPROM is not present. + **/ +s32 igb_phy_init_script_igp3(struct e1000_hw *hw) +{ + hw_dbg("Running IGP 3 PHY init script\n"); + + /* PHY init IGP 3 */ + /* Enable rise/fall, 10-mode work in class-A */ + hw->phy.ops.write_reg(hw, 0x2F5B, 0x9018); + /* Remove all caps from Replica path filter */ + hw->phy.ops.write_reg(hw, 0x2F52, 0x0000); + /* Bias trimming for ADC, AFE and Driver (Default) */ + hw->phy.ops.write_reg(hw, 0x2FB1, 0x8B24); + /* Increase Hybrid poly bias */ + hw->phy.ops.write_reg(hw, 0x2FB2, 0xF8F0); + /* Add 4% to TX amplitude in Giga mode */ + hw->phy.ops.write_reg(hw, 0x2010, 0x10B0); + /* Disable trimming (TTT) */ + hw->phy.ops.write_reg(hw, 0x2011, 0x0000); + /* Poly DC correction to 94.6% + 2% for all channels */ + hw->phy.ops.write_reg(hw, 0x20DD, 0x249A); + /* ABS DC correction to 95.9% */ + hw->phy.ops.write_reg(hw, 0x20DE, 0x00D3); + /* BG temp curve trim */ + hw->phy.ops.write_reg(hw, 0x28B4, 0x04CE); + /* Increasing ADC OPAMP stage 1 currents to max */ + hw->phy.ops.write_reg(hw, 0x2F70, 0x29E4); + /* Force 1000 ( required for enabling PHY regs configuration) */ + hw->phy.ops.write_reg(hw, 0x0000, 0x0140); + /* Set upd_freq to 6 */ + hw->phy.ops.write_reg(hw, 0x1F30, 0x1606); + /* Disable NPDFE */ + hw->phy.ops.write_reg(hw, 0x1F31, 0xB814); + /* Disable adaptive fixed FFE (Default) */ + hw->phy.ops.write_reg(hw, 0x1F35, 0x002A); + /* Enable FFE hysteresis */ + hw->phy.ops.write_reg(hw, 0x1F3E, 0x0067); + /* Fixed FFE for short cable lengths */ + hw->phy.ops.write_reg(hw, 0x1F54, 0x0065); + /* Fixed FFE for medium cable lengths */ + hw->phy.ops.write_reg(hw, 0x1F55, 0x002A); + /* Fixed FFE for long cable lengths */ + hw->phy.ops.write_reg(hw, 0x1F56, 0x002A); + /* Enable Adaptive Clip Threshold */ + hw->phy.ops.write_reg(hw, 0x1F72, 0x3FB0); + /* AHT reset limit to 1 */ + hw->phy.ops.write_reg(hw, 0x1F76, 0xC0FF); + /* Set AHT master delay to 127 msec */ + hw->phy.ops.write_reg(hw, 0x1F77, 0x1DEC); + /* Set scan bits for AHT */ + hw->phy.ops.write_reg(hw, 0x1F78, 0xF9EF); + /* Set AHT Preset bits */ + hw->phy.ops.write_reg(hw, 0x1F79, 0x0210); + /* Change integ_factor of channel A to 3 */ + hw->phy.ops.write_reg(hw, 0x1895, 0x0003); + /* Change prop_factor of channels BCD to 8 */ + hw->phy.ops.write_reg(hw, 0x1796, 0x0008); + /* Change cg_icount + enable integbp for channels BCD */ + hw->phy.ops.write_reg(hw, 0x1798, 0xD008); + /* Change cg_icount + enable integbp + change prop_factor_master + * to 8 for channel A + */ + hw->phy.ops.write_reg(hw, 0x1898, 0xD918); + /* Disable AHT in Slave mode on channel A */ + hw->phy.ops.write_reg(hw, 0x187A, 0x0800); + /* Enable LPLU and disable AN to 1000 in non-D0a states, + * Enable SPD+B2B + */ + hw->phy.ops.write_reg(hw, 0x0019, 0x008D); + /* Enable restart AN on an1000_dis change */ + hw->phy.ops.write_reg(hw, 0x001B, 0x2080); + /* Enable wh_fifo read clock in 10/100 modes */ + hw->phy.ops.write_reg(hw, 0x0014, 0x0045); + /* Restart AN, Speed selection is 1000 */ + hw->phy.ops.write_reg(hw, 0x0000, 0x1340); + + return 0; +} + +/** + * igb_initialize_M88E1512_phy - Initialize M88E1512 PHY + * @hw: pointer to the HW structure + * + * Initialize Marvel 1512 to work correctly with Avoton. + **/ +s32 igb_initialize_M88E1512_phy(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val = 0; + + /* Switch to PHY page 0xFF. */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1543_PAGE_ADDR, 0x00FF); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_2, 0x214B); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_1, 0x2144); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_2, 0x0C28); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_1, 0x2146); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_2, 0xB233); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_1, 0x214D); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_2, 0xCC0C); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_1, 0x2159); + if (ret_val) + goto out; + + /* Switch to PHY page 0xFB. */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1543_PAGE_ADDR, 0x00FB); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_3, 0x000D); + if (ret_val) + goto out; + + /* Switch to PHY page 0x12. */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1543_PAGE_ADDR, 0x12); + if (ret_val) + goto out; + + /* Change mode to SGMII-to-Copper */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_MODE, 0x8001); + if (ret_val) + goto out; + + /* Return the PHY to page 0. */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1543_PAGE_ADDR, 0); + if (ret_val) + goto out; + + ret_val = igb_phy_sw_reset(hw); + if (ret_val) { + hw_dbg("Error committing the PHY changes\n"); + return ret_val; + } + + /* msec_delay(1000); */ + usleep_range(1000, 2000); +out: + return ret_val; +} + +/** + * igb_initialize_M88E1543_phy - Initialize M88E1512 PHY + * @hw: pointer to the HW structure + * + * Initialize Marvell 1543 to work correctly with Avoton. + **/ +s32 igb_initialize_M88E1543_phy(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val = 0; + + /* Switch to PHY page 0xFF. */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1543_PAGE_ADDR, 0x00FF); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_2, 0x214B); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_1, 0x2144); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_2, 0x0C28); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_1, 0x2146); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_2, 0xB233); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_1, 0x214D); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_2, 0xDC0C); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_1, 0x2159); + if (ret_val) + goto out; + + /* Switch to PHY page 0xFB. */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1543_PAGE_ADDR, 0x00FB); + if (ret_val) + goto out; + + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_CFG_REG_3, 0x0C0D); + if (ret_val) + goto out; + + /* Switch to PHY page 0x12. */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1543_PAGE_ADDR, 0x12); + if (ret_val) + goto out; + + /* Change mode to SGMII-to-Copper */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1512_MODE, 0x8001); + if (ret_val) + goto out; + + /* Switch to PHY page 1. */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1543_PAGE_ADDR, 0x1); + if (ret_val) + goto out; + + /* Change mode to 1000BASE-X/SGMII and autoneg enable */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1543_FIBER_CTRL, 0x9140); + if (ret_val) + goto out; + + /* Return the PHY to page 0. */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1543_PAGE_ADDR, 0); + if (ret_val) + goto out; + + ret_val = igb_phy_sw_reset(hw); + if (ret_val) { + hw_dbg("Error committing the PHY changes\n"); + return ret_val; + } + + /* msec_delay(1000); */ + usleep_range(1000, 2000); +out: + return ret_val; +} + +/** + * igb_power_up_phy_copper - Restore copper link in case of PHY power down + * @hw: pointer to the HW structure + * + * In the case of a PHY power down to save power, or to turn off link during a + * driver unload, restore the link to previous settings. + **/ +void igb_power_up_phy_copper(struct e1000_hw *hw) +{ + u16 mii_reg = 0; + + /* The PHY will retain its settings across a power down/up cycle */ + hw->phy.ops.read_reg(hw, PHY_CONTROL, &mii_reg); + mii_reg &= ~MII_CR_POWER_DOWN; + hw->phy.ops.write_reg(hw, PHY_CONTROL, mii_reg); +} + +/** + * igb_power_down_phy_copper - Power down copper PHY + * @hw: pointer to the HW structure + * + * Power down PHY to save power when interface is down and wake on lan + * is not enabled. + **/ +void igb_power_down_phy_copper(struct e1000_hw *hw) +{ + u16 mii_reg = 0; + + /* The PHY will retain its settings across a power down/up cycle */ + hw->phy.ops.read_reg(hw, PHY_CONTROL, &mii_reg); + mii_reg |= MII_CR_POWER_DOWN; + hw->phy.ops.write_reg(hw, PHY_CONTROL, mii_reg); + usleep_range(1000, 2000); +} + +/** + * igb_check_polarity_82580 - Checks the polarity. + * @hw: pointer to the HW structure + * + * Success returns 0, Failure returns -E1000_ERR_PHY (-2) + * + * Polarity is determined based on the PHY specific status register. + **/ +static s32 igb_check_polarity_82580(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 data; + + + ret_val = phy->ops.read_reg(hw, I82580_PHY_STATUS_2, &data); + + if (!ret_val) + phy->cable_polarity = (data & I82580_PHY_STATUS2_REV_POLARITY) + ? e1000_rev_polarity_reversed + : e1000_rev_polarity_normal; + + return ret_val; +} + +/** + * igb_phy_force_speed_duplex_82580 - Force speed/duplex for I82580 PHY + * @hw: pointer to the HW structure + * + * Calls the PHY setup function to force speed and duplex. Clears the + * auto-crossover to force MDI manually. Waits for link and returns + * successful if link up is successful, else -E1000_ERR_PHY (-2). + **/ +s32 igb_phy_force_speed_duplex_82580(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 phy_data; + bool link; + + ret_val = phy->ops.read_reg(hw, PHY_CONTROL, &phy_data); + if (ret_val) + goto out; + + igb_phy_force_speed_duplex_setup(hw, &phy_data); + + ret_val = phy->ops.write_reg(hw, PHY_CONTROL, phy_data); + if (ret_val) + goto out; + + /* Clear Auto-Crossover to force MDI manually. 82580 requires MDI + * forced whenever speed and duplex are forced. + */ + ret_val = phy->ops.read_reg(hw, I82580_PHY_CTRL_2, &phy_data); + if (ret_val) + goto out; + + phy_data &= ~I82580_PHY_CTRL2_MDIX_CFG_MASK; + + ret_val = phy->ops.write_reg(hw, I82580_PHY_CTRL_2, phy_data); + if (ret_val) + goto out; + + hw_dbg("I82580_PHY_CTRL_2: %X\n", phy_data); + + udelay(1); + + if (phy->autoneg_wait_to_complete) { + hw_dbg("Waiting for forced speed/duplex link on 82580 phy\n"); + + ret_val = igb_phy_has_link(hw, PHY_FORCE_LIMIT, 100000, &link); + if (ret_val) + goto out; + + if (!link) + hw_dbg("Link taking longer than expected.\n"); + + /* Try once more */ + ret_val = igb_phy_has_link(hw, PHY_FORCE_LIMIT, 100000, &link); + if (ret_val) + goto out; + } + +out: + return ret_val; +} + +/** + * igb_get_phy_info_82580 - Retrieve I82580 PHY information + * @hw: pointer to the HW structure + * + * Read PHY status to determine if link is up. If link is up, then + * set/determine 10base-T extended distance and polarity correction. Read + * PHY port status to determine MDI/MDIx and speed. Based on the speed, + * determine on the cable length, local and remote receiver. + **/ +s32 igb_get_phy_info_82580(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 data; + bool link; + + ret_val = igb_phy_has_link(hw, 1, 0, &link); + if (ret_val) + goto out; + + if (!link) { + hw_dbg("Phy info is only valid if link is up\n"); + ret_val = -E1000_ERR_CONFIG; + goto out; + } + + phy->polarity_correction = true; + + ret_val = igb_check_polarity_82580(hw); + if (ret_val) + goto out; + + ret_val = phy->ops.read_reg(hw, I82580_PHY_STATUS_2, &data); + if (ret_val) + goto out; + + phy->is_mdix = (data & I82580_PHY_STATUS2_MDIX) ? true : false; + + if ((data & I82580_PHY_STATUS2_SPEED_MASK) == + I82580_PHY_STATUS2_SPEED_1000MBPS) { + ret_val = hw->phy.ops.get_cable_length(hw); + if (ret_val) + goto out; + + ret_val = phy->ops.read_reg(hw, PHY_1000T_STATUS, &data); + if (ret_val) + goto out; + + phy->local_rx = (data & SR_1000T_LOCAL_RX_STATUS) + ? e1000_1000t_rx_status_ok + : e1000_1000t_rx_status_not_ok; + + phy->remote_rx = (data & SR_1000T_REMOTE_RX_STATUS) + ? e1000_1000t_rx_status_ok + : e1000_1000t_rx_status_not_ok; + } else { + phy->cable_length = E1000_CABLE_LENGTH_UNDEFINED; + phy->local_rx = e1000_1000t_rx_status_undefined; + phy->remote_rx = e1000_1000t_rx_status_undefined; + } + +out: + return ret_val; +} + +/** + * igb_get_cable_length_82580 - Determine cable length for 82580 PHY + * @hw: pointer to the HW structure + * + * Reads the diagnostic status register and verifies result is valid before + * placing it in the phy_cable_length field. + **/ +s32 igb_get_cable_length_82580(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 phy_data, length; + + ret_val = phy->ops.read_reg(hw, I82580_PHY_DIAG_STATUS, &phy_data); + if (ret_val) + goto out; + + length = (phy_data & I82580_DSTATUS_CABLE_LENGTH) >> + I82580_DSTATUS_CABLE_LENGTH_SHIFT; + + if (length == E1000_CABLE_LENGTH_UNDEFINED) + ret_val = -E1000_ERR_PHY; + + phy->cable_length = length; + +out: + return ret_val; +} + +/** + * igb_set_master_slave_mode - Setup PHY for Master/slave mode + * @hw: pointer to the HW structure + * + * Sets up Master/slave mode + **/ +static s32 igb_set_master_slave_mode(struct e1000_hw *hw) +{ + s32 ret_val; + u16 phy_data; + + /* Resolve Master/Slave mode */ + ret_val = hw->phy.ops.read_reg(hw, PHY_1000T_CTRL, &phy_data); + if (ret_val) + return ret_val; + + /* load defaults for future use */ + hw->phy.original_ms_type = (phy_data & CR_1000T_MS_ENABLE) ? + ((phy_data & CR_1000T_MS_VALUE) ? + e1000_ms_force_master : + e1000_ms_force_slave) : e1000_ms_auto; + + switch (hw->phy.ms_type) { + case e1000_ms_force_master: + phy_data |= (CR_1000T_MS_ENABLE | CR_1000T_MS_VALUE); + break; + case e1000_ms_force_slave: + phy_data |= CR_1000T_MS_ENABLE; + phy_data &= ~(CR_1000T_MS_VALUE); + break; + case e1000_ms_auto: + phy_data &= ~CR_1000T_MS_ENABLE; + fallthrough; + default: + break; + } + + return hw->phy.ops.write_reg(hw, PHY_1000T_CTRL, phy_data); +} diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.h b/drivers/net/ethernet/intel/igb/e1000_phy.h new file mode 100644 index 0000000000..5894e4b1d0 --- /dev/null +++ b/drivers/net/ethernet/intel/igb/e1000_phy.h @@ -0,0 +1,145 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ + +#ifndef _E1000_PHY_H_ +#define _E1000_PHY_H_ + +enum e1000_ms_type { + e1000_ms_hw_default = 0, + e1000_ms_force_master, + e1000_ms_force_slave, + e1000_ms_auto +}; + +enum e1000_smart_speed { + e1000_smart_speed_default = 0, + e1000_smart_speed_on, + e1000_smart_speed_off +}; + +s32 igb_check_downshift(struct e1000_hw *hw); +s32 igb_check_reset_block(struct e1000_hw *hw); +s32 igb_copper_link_setup_igp(struct e1000_hw *hw); +s32 igb_copper_link_setup_m88(struct e1000_hw *hw); +s32 igb_copper_link_setup_m88_gen2(struct e1000_hw *hw); +s32 igb_phy_force_speed_duplex_igp(struct e1000_hw *hw); +s32 igb_phy_force_speed_duplex_m88(struct e1000_hw *hw); +s32 igb_get_cable_length_m88(struct e1000_hw *hw); +s32 igb_get_cable_length_m88_gen2(struct e1000_hw *hw); +s32 igb_get_cable_length_igp_2(struct e1000_hw *hw); +s32 igb_get_phy_id(struct e1000_hw *hw); +s32 igb_get_phy_info_igp(struct e1000_hw *hw); +s32 igb_get_phy_info_m88(struct e1000_hw *hw); +s32 igb_phy_sw_reset(struct e1000_hw *hw); +s32 igb_phy_hw_reset(struct e1000_hw *hw); +s32 igb_read_phy_reg_igp(struct e1000_hw *hw, u32 offset, u16 *data); +s32 igb_set_d3_lplu_state(struct e1000_hw *hw, bool active); +s32 igb_setup_copper_link(struct e1000_hw *hw); +s32 igb_write_phy_reg_igp(struct e1000_hw *hw, u32 offset, u16 data); +s32 igb_phy_has_link(struct e1000_hw *hw, u32 iterations, + u32 usec_interval, bool *success); +void igb_power_up_phy_copper(struct e1000_hw *hw); +void igb_power_down_phy_copper(struct e1000_hw *hw); +s32 igb_phy_init_script_igp3(struct e1000_hw *hw); +s32 igb_initialize_M88E1512_phy(struct e1000_hw *hw); +s32 igb_initialize_M88E1543_phy(struct e1000_hw *hw); +s32 igb_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data); +s32 igb_write_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 data); +s32 igb_read_phy_reg_i2c(struct e1000_hw *hw, u32 offset, u16 *data); +s32 igb_write_phy_reg_i2c(struct e1000_hw *hw, u32 offset, u16 data); +s32 igb_read_sfp_data_byte(struct e1000_hw *hw, u16 offset, u8 *data); +s32 igb_copper_link_setup_82580(struct e1000_hw *hw); +s32 igb_get_phy_info_82580(struct e1000_hw *hw); +s32 igb_phy_force_speed_duplex_82580(struct e1000_hw *hw); +s32 igb_get_cable_length_82580(struct e1000_hw *hw); +s32 igb_read_phy_reg_82580(struct e1000_hw *hw, u32 offset, u16 *data); +s32 igb_write_phy_reg_82580(struct e1000_hw *hw, u32 offset, u16 data); +s32 igb_check_polarity_m88(struct e1000_hw *hw); + +/* IGP01E1000 Specific Registers */ +#define IGP01E1000_PHY_PORT_CONFIG 0x10 /* Port Config */ +#define IGP01E1000_PHY_PORT_STATUS 0x11 /* Status */ +#define IGP01E1000_PHY_PORT_CTRL 0x12 /* Control */ +#define IGP01E1000_PHY_LINK_HEALTH 0x13 /* PHY Link Health */ +#define IGP02E1000_PHY_POWER_MGMT 0x19 /* Power Management */ +#define IGP01E1000_PHY_PAGE_SELECT 0x1F /* Page Select */ +#define IGP01E1000_PHY_PCS_INIT_REG 0x00B4 +#define IGP01E1000_PHY_POLARITY_MASK 0x0078 +#define IGP01E1000_PSCR_AUTO_MDIX 0x1000 +#define IGP01E1000_PSCR_FORCE_MDI_MDIX 0x2000 /* 0=MDI, 1=MDIX */ +#define IGP01E1000_PSCFR_SMART_SPEED 0x0080 + +#define I82580_ADDR_REG 16 +#define I82580_CFG_REG 22 +#define I82580_CFG_ASSERT_CRS_ON_TX BIT(15) +#define I82580_CFG_ENABLE_DOWNSHIFT (3u << 10) /* auto downshift 100/10 */ +#define I82580_CTRL_REG 23 +#define I82580_CTRL_DOWNSHIFT_MASK (7u << 10) + +/* 82580 specific PHY registers */ +#define I82580_PHY_CTRL_2 18 +#define I82580_PHY_LBK_CTRL 19 +#define I82580_PHY_STATUS_2 26 +#define I82580_PHY_DIAG_STATUS 31 + +/* I82580 PHY Status 2 */ +#define I82580_PHY_STATUS2_REV_POLARITY 0x0400 +#define I82580_PHY_STATUS2_MDIX 0x0800 +#define I82580_PHY_STATUS2_SPEED_MASK 0x0300 +#define I82580_PHY_STATUS2_SPEED_1000MBPS 0x0200 +#define I82580_PHY_STATUS2_SPEED_100MBPS 0x0100 + +/* I82580 PHY Control 2 */ +#define I82580_PHY_CTRL2_MANUAL_MDIX 0x0200 +#define I82580_PHY_CTRL2_AUTO_MDI_MDIX 0x0400 +#define I82580_PHY_CTRL2_MDIX_CFG_MASK 0x0600 + +/* I82580 PHY Diagnostics Status */ +#define I82580_DSTATUS_CABLE_LENGTH 0x03FC +#define I82580_DSTATUS_CABLE_LENGTH_SHIFT 2 + +/* 82580 PHY Power Management */ +#define E1000_82580_PHY_POWER_MGMT 0xE14 +#define E1000_82580_PM_SPD 0x0001 /* Smart Power Down */ +#define E1000_82580_PM_D0_LPLU 0x0002 /* For D0a states */ +#define E1000_82580_PM_D3_LPLU 0x0004 /* For all other states */ +#define E1000_82580_PM_GO_LINKD 0x0020 /* Go Link Disconnect */ + +/* Enable flexible speed on link-up */ +#define IGP02E1000_PM_D0_LPLU 0x0002 /* For D0a states */ +#define IGP02E1000_PM_D3_LPLU 0x0004 /* For all other states */ +#define IGP01E1000_PLHR_SS_DOWNGRADE 0x8000 +#define IGP01E1000_PSSR_POLARITY_REVERSED 0x0002 +#define IGP01E1000_PSSR_MDIX 0x0800 +#define IGP01E1000_PSSR_SPEED_MASK 0xC000 +#define IGP01E1000_PSSR_SPEED_1000MBPS 0xC000 +#define IGP02E1000_PHY_CHANNEL_NUM 4 +#define IGP02E1000_PHY_AGC_A 0x11B1 +#define IGP02E1000_PHY_AGC_B 0x12B1 +#define IGP02E1000_PHY_AGC_C 0x14B1 +#define IGP02E1000_PHY_AGC_D 0x18B1 +#define IGP02E1000_AGC_LENGTH_SHIFT 9 /* Course - 15:13, Fine - 12:9 */ +#define IGP02E1000_AGC_LENGTH_MASK 0x7F +#define IGP02E1000_AGC_RANGE 15 + +#define E1000_CABLE_LENGTH_UNDEFINED 0xFF + +/* SFP modules ID memory locations */ +#define E1000_SFF_IDENTIFIER_OFFSET 0x00 +#define E1000_SFF_IDENTIFIER_SFF 0x02 +#define E1000_SFF_IDENTIFIER_SFP 0x03 + +#define E1000_SFF_ETH_FLAGS_OFFSET 0x06 +/* Flags for SFP modules compatible with ETH up to 1Gb */ +struct e1000_sfp_flags { + u8 e1000_base_sx:1; + u8 e1000_base_lx:1; + u8 e1000_base_cx:1; + u8 e1000_base_t:1; + u8 e100_base_lx:1; + u8 e100_base_fx:1; + u8 e10_base_bx10:1; + u8 e10_base_px:1; +}; + +#endif diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h new file mode 100644 index 0000000000..eb9f6da920 --- /dev/null +++ b/drivers/net/ethernet/intel/igb/e1000_regs.h @@ -0,0 +1,418 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ + +#ifndef _E1000_REGS_H_ +#define _E1000_REGS_H_ + +#define E1000_CTRL 0x00000 /* Device Control - RW */ +#define E1000_STATUS 0x00008 /* Device Status - RO */ +#define E1000_EECD 0x00010 /* EEPROM/Flash Control - RW */ +#define E1000_EERD 0x00014 /* EEPROM Read - RW */ +#define E1000_CTRL_EXT 0x00018 /* Extended Device Control - RW */ +#define E1000_MDIC 0x00020 /* MDI Control - RW */ +#define E1000_MDICNFG 0x00E04 /* MDI Config - RW */ +#define E1000_SCTL 0x00024 /* SerDes Control - RW */ +#define E1000_FCAL 0x00028 /* Flow Control Address Low - RW */ +#define E1000_FCAH 0x0002C /* Flow Control Address High -RW */ +#define E1000_FCT 0x00030 /* Flow Control Type - RW */ +#define E1000_CONNSW 0x00034 /* Copper/Fiber switch control - RW */ +#define E1000_VET 0x00038 /* VLAN Ether Type - RW */ +#define E1000_TSSDP 0x0003C /* Time Sync SDP Configuration Register - RW */ +#define E1000_ICR 0x000C0 /* Interrupt Cause Read - R/clr */ +#define E1000_ITR 0x000C4 /* Interrupt Throttling Rate - RW */ +#define E1000_ICS 0x000C8 /* Interrupt Cause Set - WO */ +#define E1000_IMS 0x000D0 /* Interrupt Mask Set - RW */ +#define E1000_IMC 0x000D8 /* Interrupt Mask Clear - WO */ +#define E1000_IAM 0x000E0 /* Interrupt Acknowledge Auto Mask */ +#define E1000_RCTL 0x00100 /* RX Control - RW */ +#define E1000_FCTTV 0x00170 /* Flow Control Transmit Timer Value - RW */ +#define E1000_TXCW 0x00178 /* TX Configuration Word - RW */ +#define E1000_EICR 0x01580 /* Ext. Interrupt Cause Read - R/clr */ +#define E1000_EITR(_n) (0x01680 + (0x4 * (_n))) +#define E1000_EICS 0x01520 /* Ext. Interrupt Cause Set - W0 */ +#define E1000_EIMS 0x01524 /* Ext. Interrupt Mask Set/Read - RW */ +#define E1000_EIMC 0x01528 /* Ext. Interrupt Mask Clear - WO */ +#define E1000_EIAC 0x0152C /* Ext. Interrupt Auto Clear - RW */ +#define E1000_EIAM 0x01530 /* Ext. Interrupt Ack Auto Clear Mask - RW */ +#define E1000_GPIE 0x01514 /* General Purpose Interrupt Enable - RW */ +#define E1000_IVAR0 0x01700 /* Interrupt Vector Allocation (array) - RW */ +#define E1000_IVAR_MISC 0x01740 /* IVAR for "other" causes - RW */ +#define E1000_TCTL 0x00400 /* TX Control - RW */ +#define E1000_TCTL_EXT 0x00404 /* Extended TX Control - RW */ +#define E1000_TIPG 0x00410 /* TX Inter-packet gap -RW */ +#define E1000_AIT 0x00458 /* Adaptive Interframe Spacing Throttle - RW */ +#define E1000_LEDCTL 0x00E00 /* LED Control - RW */ +#define E1000_LEDMUX 0x08130 /* LED MUX Control */ +#define E1000_PBA 0x01000 /* Packet Buffer Allocation - RW */ +#define E1000_PBS 0x01008 /* Packet Buffer Size */ +#define E1000_EEMNGCTL 0x01010 /* MNG EEprom Control */ +#define E1000_EEMNGCTL_I210 0x12030 /* MNG EEprom Control */ +#define E1000_EEARBC_I210 0x12024 /* EEPROM Auto Read Bus Control */ +#define E1000_EEWR 0x0102C /* EEPROM Write Register - RW */ +#define E1000_I2CCMD 0x01028 /* SFPI2C Command Register - RW */ +#define E1000_FRTIMER 0x01048 /* Free Running Timer - RW */ +#define E1000_TCPTIMER 0x0104C /* TCP Timer - RW */ +#define E1000_FCRTL 0x02160 /* Flow Control Receive Threshold Low - RW */ +#define E1000_FCRTH 0x02168 /* Flow Control Receive Threshold High - RW */ +#define E1000_FCRTV 0x02460 /* Flow Control Refresh Timer Value - RW */ +#define E1000_I2CPARAMS 0x0102C /* SFPI2C Parameters Register - RW */ +#define E1000_I2CBB_EN 0x00000100 /* I2C - Bit Bang Enable */ +#define E1000_I2C_CLK_OUT 0x00000200 /* I2C- Clock */ +#define E1000_I2C_DATA_OUT 0x00000400 /* I2C- Data Out */ +#define E1000_I2C_DATA_OE_N 0x00000800 /* I2C- Data Output Enable */ +#define E1000_I2C_DATA_IN 0x00001000 /* I2C- Data In */ +#define E1000_I2C_CLK_OE_N 0x00002000 /* I2C- Clock Output Enable */ +#define E1000_I2C_CLK_IN 0x00004000 /* I2C- Clock In */ +#define E1000_MPHY_ADDR_CTRL 0x0024 /* GbE MPHY Address Control */ +#define E1000_MPHY_DATA 0x0E10 /* GBE MPHY Data */ +#define E1000_MPHY_STAT 0x0E0C /* GBE MPHY Statistics */ + +/* IEEE 1588 TIMESYNCH */ +#define E1000_TSYNCRXCTL 0x0B620 /* Rx Time Sync Control register - RW */ +#define E1000_TSYNCTXCTL 0x0B614 /* Tx Time Sync Control register - RW */ +#define E1000_TSYNCRXCFG 0x05F50 /* Time Sync Rx Configuration - RW */ +#define E1000_RXSTMPL 0x0B624 /* Rx timestamp Low - RO */ +#define E1000_RXSTMPH 0x0B628 /* Rx timestamp High - RO */ +#define E1000_RXSATRL 0x0B62C /* Rx timestamp attribute low - RO */ +#define E1000_RXSATRH 0x0B630 /* Rx timestamp attribute high - RO */ +#define E1000_TXSTMPL 0x0B618 /* Tx timestamp value Low - RO */ +#define E1000_TXSTMPH 0x0B61C /* Tx timestamp value High - RO */ +#define E1000_SYSTIML 0x0B600 /* System time register Low - RO */ +#define E1000_SYSTIMH 0x0B604 /* System time register High - RO */ +#define E1000_TIMINCA 0x0B608 /* Increment attributes register - RW */ +#define E1000_TSAUXC 0x0B640 /* Timesync Auxiliary Control register */ +#define E1000_TRGTTIML0 0x0B644 /* Target Time Register 0 Low - RW */ +#define E1000_TRGTTIMH0 0x0B648 /* Target Time Register 0 High - RW */ +#define E1000_TRGTTIML1 0x0B64C /* Target Time Register 1 Low - RW */ +#define E1000_TRGTTIMH1 0x0B650 /* Target Time Register 1 High - RW */ +#define E1000_FREQOUT0 0x0B654 /* Frequency Out 0 Control Register - RW */ +#define E1000_FREQOUT1 0x0B658 /* Frequency Out 1 Control Register - RW */ +#define E1000_AUXSTMPL0 0x0B65C /* Auxiliary Time Stamp 0 Register Low - RO */ +#define E1000_AUXSTMPH0 0x0B660 /* Auxiliary Time Stamp 0 Register High - RO */ +#define E1000_AUXSTMPL1 0x0B664 /* Auxiliary Time Stamp 1 Register Low - RO */ +#define E1000_AUXSTMPH1 0x0B668 /* Auxiliary Time Stamp 1 Register High - RO */ +#define E1000_SYSTIMR 0x0B6F8 /* System time register Residue */ +#define E1000_TSICR 0x0B66C /* Interrupt Cause Register */ +#define E1000_TSIM 0x0B674 /* Interrupt Mask Register */ + +/* Filtering Registers */ +#define E1000_SAQF(_n) (0x5980 + 4 * (_n)) +#define E1000_DAQF(_n) (0x59A0 + 4 * (_n)) +#define E1000_SPQF(_n) (0x59C0 + 4 * (_n)) +#define E1000_FTQF(_n) (0x59E0 + 4 * (_n)) +#define E1000_SAQF0 E1000_SAQF(0) +#define E1000_DAQF0 E1000_DAQF(0) +#define E1000_SPQF0 E1000_SPQF(0) +#define E1000_FTQF0 E1000_FTQF(0) +#define E1000_SYNQF(_n) (0x055FC + (4 * (_n))) /* SYN Packet Queue Fltr */ +#define E1000_ETQF(_n) (0x05CB0 + (4 * (_n))) /* EType Queue Fltr */ + +#define E1000_RQDPC(_n) (0x0C030 + ((_n) * 0x40)) + +/* DMA Coalescing registers */ +#define E1000_DMACR 0x02508 /* Control Register */ +#define E1000_DMCTXTH 0x03550 /* Transmit Threshold */ +#define E1000_DMCTLX 0x02514 /* Time to Lx Request */ +#define E1000_DMCRTRH 0x05DD0 /* Receive Packet Rate Threshold */ +#define E1000_DMCCNT 0x05DD4 /* Current Rx Count */ +#define E1000_FCRTC 0x02170 /* Flow Control Rx high watermark */ + +/* TX Rate Limit Registers */ +#define E1000_RTTDQSEL 0x3604 /* Tx Desc Plane Queue Select - WO */ +#define E1000_RTTBCNRM 0x3690 /* Tx BCN Rate-scheduler MMW */ +#define E1000_RTTBCNRC 0x36B0 /* Tx BCN Rate-Scheduler Config - WO */ + +/* Split and Replication RX Control - RW */ +#define E1000_RXPBS 0x02404 /* Rx Packet Buffer Size - RW */ + +/* Thermal sensor configuration and status registers */ +#define E1000_THMJT 0x08100 /* Junction Temperature */ +#define E1000_THLOWTC 0x08104 /* Low Threshold Control */ +#define E1000_THMIDTC 0x08108 /* Mid Threshold Control */ +#define E1000_THHIGHTC 0x0810C /* High Threshold Control */ +#define E1000_THSTAT 0x08110 /* Thermal Sensor Status */ + +/* Convenience macros + * + * Note: "_n" is the queue number of the register to be written to. + * + * Example usage: + * E1000_RDBAL_REG(current_rx_queue) + */ +#define E1000_RDBAL(_n) ((_n) < 4 ? (0x02800 + ((_n) * 0x100)) \ + : (0x0C000 + ((_n) * 0x40))) +#define E1000_RDBAH(_n) ((_n) < 4 ? (0x02804 + ((_n) * 0x100)) \ + : (0x0C004 + ((_n) * 0x40))) +#define E1000_RDLEN(_n) ((_n) < 4 ? (0x02808 + ((_n) * 0x100)) \ + : (0x0C008 + ((_n) * 0x40))) +#define E1000_SRRCTL(_n) ((_n) < 4 ? (0x0280C + ((_n) * 0x100)) \ + : (0x0C00C + ((_n) * 0x40))) +#define E1000_RDH(_n) ((_n) < 4 ? (0x02810 + ((_n) * 0x100)) \ + : (0x0C010 + ((_n) * 0x40))) +#define E1000_RDT(_n) ((_n) < 4 ? (0x02818 + ((_n) * 0x100)) \ + : (0x0C018 + ((_n) * 0x40))) +#define E1000_RXDCTL(_n) ((_n) < 4 ? (0x02828 + ((_n) * 0x100)) \ + : (0x0C028 + ((_n) * 0x40))) +#define E1000_TDBAL(_n) ((_n) < 4 ? (0x03800 + ((_n) * 0x100)) \ + : (0x0E000 + ((_n) * 0x40))) +#define E1000_TDBAH(_n) ((_n) < 4 ? (0x03804 + ((_n) * 0x100)) \ + : (0x0E004 + ((_n) * 0x40))) +#define E1000_TDLEN(_n) ((_n) < 4 ? (0x03808 + ((_n) * 0x100)) \ + : (0x0E008 + ((_n) * 0x40))) +#define E1000_TDH(_n) ((_n) < 4 ? (0x03810 + ((_n) * 0x100)) \ + : (0x0E010 + ((_n) * 0x40))) +#define E1000_TDT(_n) ((_n) < 4 ? (0x03818 + ((_n) * 0x100)) \ + : (0x0E018 + ((_n) * 0x40))) +#define E1000_TXDCTL(_n) ((_n) < 4 ? (0x03828 + ((_n) * 0x100)) \ + : (0x0E028 + ((_n) * 0x40))) +#define E1000_RXCTL(_n) ((_n) < 4 ? (0x02814 + ((_n) * 0x100)) : \ + (0x0C014 + ((_n) * 0x40))) +#define E1000_DCA_RXCTRL(_n) E1000_RXCTL(_n) +#define E1000_TXCTL(_n) ((_n) < 4 ? (0x03814 + ((_n) * 0x100)) : \ + (0x0E014 + ((_n) * 0x40))) +#define E1000_DCA_TXCTRL(_n) E1000_TXCTL(_n) +#define E1000_TDWBAL(_n) ((_n) < 4 ? (0x03838 + ((_n) * 0x100)) \ + : (0x0E038 + ((_n) * 0x40))) +#define E1000_TDWBAH(_n) ((_n) < 4 ? (0x0383C + ((_n) * 0x100)) \ + : (0x0E03C + ((_n) * 0x40))) + +#define E1000_RXPBS 0x02404 /* Rx Packet Buffer Size - RW */ +#define E1000_TXPBS 0x03404 /* Tx Packet Buffer Size - RW */ + +#define E1000_TDFH 0x03410 /* TX Data FIFO Head - RW */ +#define E1000_TDFT 0x03418 /* TX Data FIFO Tail - RW */ +#define E1000_TDFHS 0x03420 /* TX Data FIFO Head Saved - RW */ +#define E1000_TDFPC 0x03430 /* TX Data FIFO Packet Count - RW */ +#define E1000_DTXCTL 0x03590 /* DMA TX Control - RW */ +#define E1000_CRCERRS 0x04000 /* CRC Error Count - R/clr */ +#define E1000_ALGNERRC 0x04004 /* Alignment Error Count - R/clr */ +#define E1000_SYMERRS 0x04008 /* Symbol Error Count - R/clr */ +#define E1000_RXERRC 0x0400C /* Receive Error Count - R/clr */ +#define E1000_MPC 0x04010 /* Missed Packet Count - R/clr */ +#define E1000_SCC 0x04014 /* Single Collision Count - R/clr */ +#define E1000_ECOL 0x04018 /* Excessive Collision Count - R/clr */ +#define E1000_MCC 0x0401C /* Multiple Collision Count - R/clr */ +#define E1000_LATECOL 0x04020 /* Late Collision Count - R/clr */ +#define E1000_COLC 0x04028 /* Collision Count - R/clr */ +#define E1000_DC 0x04030 /* Defer Count - R/clr */ +#define E1000_TNCRS 0x04034 /* TX-No CRS - R/clr */ +#define E1000_SEC 0x04038 /* Sequence Error Count - R/clr */ +#define E1000_CEXTERR 0x0403C /* Carrier Extension Error Count - R/clr */ +#define E1000_RLEC 0x04040 /* Receive Length Error Count - R/clr */ +#define E1000_XONRXC 0x04048 /* XON RX Count - R/clr */ +#define E1000_XONTXC 0x0404C /* XON TX Count - R/clr */ +#define E1000_XOFFRXC 0x04050 /* XOFF RX Count - R/clr */ +#define E1000_XOFFTXC 0x04054 /* XOFF TX Count - R/clr */ +#define E1000_FCRUC 0x04058 /* Flow Control RX Unsupported Count- R/clr */ +#define E1000_PRC64 0x0405C /* Packets RX (64 bytes) - R/clr */ +#define E1000_PRC127 0x04060 /* Packets RX (65-127 bytes) - R/clr */ +#define E1000_PRC255 0x04064 /* Packets RX (128-255 bytes) - R/clr */ +#define E1000_PRC511 0x04068 /* Packets RX (255-511 bytes) - R/clr */ +#define E1000_PRC1023 0x0406C /* Packets RX (512-1023 bytes) - R/clr */ +#define E1000_PRC1522 0x04070 /* Packets RX (1024-1522 bytes) - R/clr */ +#define E1000_GPRC 0x04074 /* Good Packets RX Count - R/clr */ +#define E1000_BPRC 0x04078 /* Broadcast Packets RX Count - R/clr */ +#define E1000_MPRC 0x0407C /* Multicast Packets RX Count - R/clr */ +#define E1000_GPTC 0x04080 /* Good Packets TX Count - R/clr */ +#define E1000_GORCL 0x04088 /* Good Octets RX Count Low - R/clr */ +#define E1000_GORCH 0x0408C /* Good Octets RX Count High - R/clr */ +#define E1000_GOTCL 0x04090 /* Good Octets TX Count Low - R/clr */ +#define E1000_GOTCH 0x04094 /* Good Octets TX Count High - R/clr */ +#define E1000_RNBC 0x040A0 /* RX No Buffers Count - R/clr */ +#define E1000_RUC 0x040A4 /* RX Undersize Count - R/clr */ +#define E1000_RFC 0x040A8 /* RX Fragment Count - R/clr */ +#define E1000_ROC 0x040AC /* RX Oversize Count - R/clr */ +#define E1000_RJC 0x040B0 /* RX Jabber Count - R/clr */ +#define E1000_MGTPRC 0x040B4 /* Management Packets RX Count - R/clr */ +#define E1000_MGTPDC 0x040B8 /* Management Packets Dropped Count - R/clr */ +#define E1000_MGTPTC 0x040BC /* Management Packets TX Count - R/clr */ +#define E1000_TORL 0x040C0 /* Total Octets RX Low - R/clr */ +#define E1000_TORH 0x040C4 /* Total Octets RX High - R/clr */ +#define E1000_TOTL 0x040C8 /* Total Octets TX Low - R/clr */ +#define E1000_TOTH 0x040CC /* Total Octets TX High - R/clr */ +#define E1000_TPR 0x040D0 /* Total Packets RX - R/clr */ +#define E1000_TPT 0x040D4 /* Total Packets TX - R/clr */ +#define E1000_PTC64 0x040D8 /* Packets TX (64 bytes) - R/clr */ +#define E1000_PTC127 0x040DC /* Packets TX (65-127 bytes) - R/clr */ +#define E1000_PTC255 0x040E0 /* Packets TX (128-255 bytes) - R/clr */ +#define E1000_PTC511 0x040E4 /* Packets TX (256-511 bytes) - R/clr */ +#define E1000_PTC1023 0x040E8 /* Packets TX (512-1023 bytes) - R/clr */ +#define E1000_PTC1522 0x040EC /* Packets TX (1024-1522 Bytes) - R/clr */ +#define E1000_MPTC 0x040F0 /* Multicast Packets TX Count - R/clr */ +#define E1000_BPTC 0x040F4 /* Broadcast Packets TX Count - R/clr */ +#define E1000_TSCTC 0x040F8 /* TCP Segmentation Context TX - R/clr */ +#define E1000_TSCTFC 0x040FC /* TCP Segmentation Context TX Fail - R/clr */ +#define E1000_IAC 0x04100 /* Interrupt Assertion Count */ +/* Interrupt Cause Rx Packet Timer Expire Count */ +#define E1000_ICRXPTC 0x04104 +/* Interrupt Cause Rx Absolute Timer Expire Count */ +#define E1000_ICRXATC 0x04108 +/* Interrupt Cause Tx Packet Timer Expire Count */ +#define E1000_ICTXPTC 0x0410C +/* Interrupt Cause Tx Absolute Timer Expire Count */ +#define E1000_ICTXATC 0x04110 +/* Interrupt Cause Tx Queue Empty Count */ +#define E1000_ICTXQEC 0x04118 +/* Interrupt Cause Tx Queue Minimum Threshold Count */ +#define E1000_ICTXQMTC 0x0411C +/* Interrupt Cause Rx Descriptor Minimum Threshold Count */ +#define E1000_ICRXDMTC 0x04120 +#define E1000_ICRXOC 0x04124 /* Interrupt Cause Receiver Overrun Count */ +#define E1000_PCS_CFG0 0x04200 /* PCS Configuration 0 - RW */ +#define E1000_PCS_LCTL 0x04208 /* PCS Link Control - RW */ +#define E1000_PCS_LSTAT 0x0420C /* PCS Link Status - RO */ +#define E1000_CBTMPC 0x0402C /* Circuit Breaker TX Packet Count */ +#define E1000_HTDPMC 0x0403C /* Host Transmit Discarded Packets */ +#define E1000_CBRMPC 0x040FC /* Circuit Breaker RX Packet Count */ +#define E1000_RPTHC 0x04104 /* Rx Packets To Host */ +#define E1000_HGPTC 0x04118 /* Host Good Packets TX Count */ +#define E1000_HTCBDPC 0x04124 /* Host TX Circuit Breaker Dropped Count */ +#define E1000_HGORCL 0x04128 /* Host Good Octets Received Count Low */ +#define E1000_HGORCH 0x0412C /* Host Good Octets Received Count High */ +#define E1000_HGOTCL 0x04130 /* Host Good Octets Transmit Count Low */ +#define E1000_HGOTCH 0x04134 /* Host Good Octets Transmit Count High */ +#define E1000_LENERRS 0x04138 /* Length Errors Count */ +#define E1000_SCVPC 0x04228 /* SerDes/SGMII Code Violation Pkt Count */ +#define E1000_PCS_ANADV 0x04218 /* AN advertisement - RW */ +#define E1000_PCS_LPAB 0x0421C /* Link Partner Ability - RW */ +#define E1000_PCS_NPTX 0x04220 /* AN Next Page Transmit - RW */ +#define E1000_PCS_LPABNP 0x04224 /* Link Partner Ability Next Page - RW */ +#define E1000_RXCSUM 0x05000 /* RX Checksum Control - RW */ +#define E1000_RLPML 0x05004 /* RX Long Packet Max Length */ +#define E1000_RFCTL 0x05008 /* Receive Filter Control*/ +#define E1000_MTA 0x05200 /* Multicast Table Array - RW Array */ +#define E1000_RA 0x05400 /* Receive Address - RW Array */ +#define E1000_RA2 0x054E0 /* 2nd half of Rx address array - RW Array */ +#define E1000_PSRTYPE(_i) (0x05480 + ((_i) * 4)) +#define E1000_RAL(_i) (((_i) <= 15) ? (0x05400 + ((_i) * 8)) : \ + (0x054E0 + ((_i - 16) * 8))) +#define E1000_RAH(_i) (((_i) <= 15) ? (0x05404 + ((_i) * 8)) : \ + (0x054E4 + ((_i - 16) * 8))) +#define E1000_VLAPQF 0x055B0 /* VLAN Priority Queue Filter VLAPQF */ +#define E1000_IP4AT_REG(_i) (0x05840 + ((_i) * 8)) +#define E1000_IP6AT_REG(_i) (0x05880 + ((_i) * 4)) +#define E1000_WUPM_REG(_i) (0x05A00 + ((_i) * 4)) +#define E1000_FFMT_REG(_i) (0x09000 + ((_i) * 8)) +#define E1000_FFVT_REG(_i) (0x09800 + ((_i) * 8)) +#define E1000_FFLT_REG(_i) (0x05F00 + ((_i) * 8)) +#define E1000_VFTA 0x05600 /* VLAN Filter Table Array - RW Array */ +#define E1000_VT_CTL 0x0581C /* VMDq Control - RW */ +#define E1000_WUC 0x05800 /* Wakeup Control - RW */ +#define E1000_WUFC 0x05808 /* Wakeup Filter Control - RW */ +#define E1000_WUS 0x05810 /* Wakeup Status - R/W1C */ +#define E1000_MANC 0x05820 /* Management Control - RW */ +#define E1000_IPAV 0x05838 /* IP Address Valid - RW */ +#define E1000_WUPL 0x05900 /* Wakeup Packet Length - RW */ + +#define E1000_SW_FW_SYNC 0x05B5C /* Software-Firmware Synchronization - RW */ +#define E1000_CCMCTL 0x05B48 /* CCM Control Register */ +#define E1000_GIOCTL 0x05B44 /* GIO Analog Control Register */ +#define E1000_SCCTL 0x05B4C /* PCIc PLL Configuration Register */ +#define E1000_GCR 0x05B00 /* PCI-Ex Control */ +#define E1000_FACTPS 0x05B30 /* Function Active and Power State to MNG */ +#define E1000_SWSM 0x05B50 /* SW Semaphore */ +#define E1000_FWSM 0x05B54 /* FW Semaphore */ +#define E1000_DCA_CTRL 0x05B74 /* DCA Control - RW */ + +/* RSS registers */ +#define E1000_MRQC 0x05818 /* Multiple Receive Control - RW */ +#define E1000_IMIR(_i) (0x05A80 + ((_i) * 4)) /* Immediate Interrupt */ +#define E1000_IMIREXT(_i) (0x05AA0 + ((_i) * 4)) /* Immediate Interrupt Ext*/ +#define E1000_IMIRVP 0x05AC0 /* Immediate Interrupt RX VLAN Priority - RW */ +/* MSI-X Allocation Register (_i) - RW */ +#define E1000_MSIXBM(_i) (0x01600 + ((_i) * 4)) +/* Redirection Table - RW Array */ +#define E1000_RETA(_i) (0x05C00 + ((_i) * 4)) +#define E1000_RSSRK(_i) (0x05C80 + ((_i) * 4)) /* RSS Random Key - RW Array */ + +/* VT Registers */ +#define E1000_MBVFICR 0x00C80 /* Mailbox VF Cause - RWC */ +#define E1000_MBVFIMR 0x00C84 /* Mailbox VF int Mask - RW */ +#define E1000_VFLRE 0x00C88 /* VF Register Events - RWC */ +#define E1000_VFRE 0x00C8C /* VF Receive Enables */ +#define E1000_VFTE 0x00C90 /* VF Transmit Enables */ +#define E1000_QDE 0x02408 /* Queue Drop Enable - RW */ +#define E1000_DTXSWC 0x03500 /* DMA Tx Switch Control - RW */ +#define E1000_WVBR 0x03554 /* VM Wrong Behavior - RWS */ +#define E1000_RPLOLR 0x05AF0 /* Replication Offload - RW */ +#define E1000_UTA 0x0A000 /* Unicast Table Array - RW */ +#define E1000_IOVTCL 0x05BBC /* IOV Control Register */ +#define E1000_TXSWC 0x05ACC /* Tx Switch Control */ +#define E1000_LVMMC 0x03548 /* Last VM Misbehavior cause */ +/* These act per VF so an array friendly macro is used */ +#define E1000_P2VMAILBOX(_n) (0x00C00 + (4 * (_n))) +#define E1000_VMBMEM(_n) (0x00800 + (64 * (_n))) +#define E1000_VMOLR(_n) (0x05AD0 + (4 * (_n))) +#define E1000_DVMOLR(_n) (0x0C038 + (64 * (_n))) +#define E1000_VLVF(_n) (0x05D00 + (4 * (_n))) /* VLAN VM Filter */ +#define E1000_VMVIR(_n) (0x03700 + (4 * (_n))) + +struct e1000_hw; + +u32 igb_rd32(struct e1000_hw *hw, u32 reg); + +/* write operations, indexed using DWORDS */ +#define wr32(reg, val) \ +do { \ + u8 __iomem *hw_addr = READ_ONCE((hw)->hw_addr); \ + if (!E1000_REMOVED(hw_addr)) \ + writel((val), &hw_addr[(reg)]); \ +} while (0) + +#define rd32(reg) (igb_rd32(hw, reg)) + +#define wrfl() ((void)rd32(E1000_STATUS)) + +#define array_wr32(reg, offset, value) \ + wr32((reg) + ((offset) << 2), (value)) + +#define array_rd32(reg, offset) (igb_rd32(hw, reg + ((offset) << 2))) + +/* DMA Coalescing registers */ +#define E1000_PCIEMISC 0x05BB8 /* PCIE misc config register */ + +/* Energy Efficient Ethernet "EEE" register */ +#define E1000_IPCNFG 0x0E38 /* Internal PHY Configuration */ +#define E1000_EEER 0x0E30 /* Energy Efficient Ethernet */ +#define E1000_EEE_SU 0X0E34 /* EEE Setup */ +#define E1000_EMIADD 0x10 /* Extended Memory Indirect Address */ +#define E1000_EMIDATA 0x11 /* Extended Memory Indirect Data */ +#define E1000_MMDAC 13 /* MMD Access Control */ +#define E1000_MMDAAD 14 /* MMD Access Address/Data */ + +/* Thermal Sensor Register */ +#define E1000_THSTAT 0x08110 /* Thermal Sensor Status */ + +/* OS2BMC Registers */ +#define E1000_B2OSPC 0x08FE0 /* BMC2OS packets sent by BMC */ +#define E1000_B2OGPRC 0x04158 /* BMC2OS packets received by host */ +#define E1000_O2BGPTC 0x08FE4 /* OS2BMC packets received by BMC */ +#define E1000_O2BSPC 0x0415C /* OS2BMC packets transmitted by host */ + +#define E1000_SRWR 0x12018 /* Shadow Ram Write Register - RW */ +#define E1000_I210_FLMNGCTL 0x12038 +#define E1000_I210_FLMNGDATA 0x1203C +#define E1000_I210_FLMNGCNT 0x12040 + +#define E1000_I210_FLSWCTL 0x12048 +#define E1000_I210_FLSWDATA 0x1204C +#define E1000_I210_FLSWCNT 0x12050 + +#define E1000_I210_FLA 0x1201C + +#define E1000_I210_DTXMXPKTSZ 0x355C + +#define E1000_I210_TXDCTL(_n) (0x0E028 + ((_n) * 0x40)) + +#define E1000_I210_TQAVCTRL 0x3570 +#define E1000_I210_TQAVCC(_n) (0x3004 + ((_n) * 0x40)) +#define E1000_I210_TQAVHC(_n) (0x300C + ((_n) * 0x40)) + +#define E1000_I210_RR2DCDELAY 0x5BF4 + +#define E1000_INVM_DATA_REG(_n) (0x12120 + 4*(_n)) +#define E1000_INVM_SIZE 64 /* Number of INVM Data Registers */ + +#define E1000_REMOVED(h) unlikely(!(h)) + +#endif diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h new file mode 100644 index 0000000000..a2b759531c --- /dev/null +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -0,0 +1,810 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ + +/* Linux PRO/1000 Ethernet Driver main header file */ + +#ifndef _IGB_H_ +#define _IGB_H_ + +#include "e1000_mac.h" +#include "e1000_82575.h" + +#include <linux/timecounter.h> +#include <linux/net_tstamp.h> +#include <linux/ptp_clock_kernel.h> +#include <linux/bitops.h> +#include <linux/if_vlan.h> +#include <linux/i2c.h> +#include <linux/i2c-algo-bit.h> +#include <linux/pci.h> +#include <linux/mdio.h> + +#include <net/xdp.h> + +struct igb_adapter; + +#define E1000_PCS_CFG_IGN_SD 1 + +/* Interrupt defines */ +#define IGB_START_ITR 648 /* ~6000 ints/sec */ +#define IGB_4K_ITR 980 +#define IGB_20K_ITR 196 +#define IGB_70K_ITR 56 + +/* TX/RX descriptor defines */ +#define IGB_DEFAULT_TXD 256 +#define IGB_DEFAULT_TX_WORK 128 +#define IGB_MIN_TXD 64 +#define IGB_MAX_TXD 4096 + +#define IGB_DEFAULT_RXD 256 +#define IGB_MIN_RXD 64 +#define IGB_MAX_RXD 4096 + +#define IGB_DEFAULT_ITR 3 /* dynamic */ +#define IGB_MAX_ITR_USECS 10000 +#define IGB_MIN_ITR_USECS 10 +#define NON_Q_VECTORS 1 +#define MAX_Q_VECTORS 8 +#define MAX_MSIX_ENTRIES 10 + +/* Transmit and receive queues */ +#define IGB_MAX_RX_QUEUES 8 +#define IGB_MAX_RX_QUEUES_82575 4 +#define IGB_MAX_RX_QUEUES_I211 2 +#define IGB_MAX_TX_QUEUES 8 +#define IGB_MAX_VF_MC_ENTRIES 30 +#define IGB_MAX_VF_FUNCTIONS 8 +#define IGB_MAX_VFTA_ENTRIES 128 +#define IGB_82576_VF_DEV_ID 0x10CA +#define IGB_I350_VF_DEV_ID 0x1520 + +/* NVM version defines */ +#define IGB_MAJOR_MASK 0xF000 +#define IGB_MINOR_MASK 0x0FF0 +#define IGB_BUILD_MASK 0x000F +#define IGB_COMB_VER_MASK 0x00FF +#define IGB_MAJOR_SHIFT 12 +#define IGB_MINOR_SHIFT 4 +#define IGB_COMB_VER_SHFT 8 +#define IGB_NVM_VER_INVALID 0xFFFF +#define IGB_ETRACK_SHIFT 16 +#define NVM_ETRACK_WORD 0x0042 +#define NVM_COMB_VER_OFF 0x0083 +#define NVM_COMB_VER_PTR 0x003d + +/* Transmit and receive latency (for PTP timestamps) */ +#define IGB_I210_TX_LATENCY_10 9542 +#define IGB_I210_TX_LATENCY_100 1024 +#define IGB_I210_TX_LATENCY_1000 178 +#define IGB_I210_RX_LATENCY_10 20662 +#define IGB_I210_RX_LATENCY_100 2213 +#define IGB_I210_RX_LATENCY_1000 448 + +/* XDP */ +#define IGB_XDP_PASS 0 +#define IGB_XDP_CONSUMED BIT(0) +#define IGB_XDP_TX BIT(1) +#define IGB_XDP_REDIR BIT(2) + +struct vf_data_storage { + unsigned char vf_mac_addresses[ETH_ALEN]; + u16 vf_mc_hashes[IGB_MAX_VF_MC_ENTRIES]; + u16 num_vf_mc_hashes; + u32 flags; + unsigned long last_nack; + u16 pf_vlan; /* When set, guest VLAN config not allowed. */ + u16 pf_qos; + u16 tx_rate; + bool spoofchk_enabled; + bool trusted; +}; + +/* Number of unicast MAC filters reserved for the PF in the RAR registers */ +#define IGB_PF_MAC_FILTERS_RESERVED 3 + +struct vf_mac_filter { + struct list_head l; + int vf; + bool free; + u8 vf_mac[ETH_ALEN]; +}; + +#define IGB_VF_FLAG_CTS 0x00000001 /* VF is clear to send data */ +#define IGB_VF_FLAG_UNI_PROMISC 0x00000002 /* VF has unicast promisc */ +#define IGB_VF_FLAG_MULTI_PROMISC 0x00000004 /* VF has multicast promisc */ +#define IGB_VF_FLAG_PF_SET_MAC 0x00000008 /* PF has set MAC address */ + +/* RX descriptor control thresholds. + * PTHRESH - MAC will consider prefetch if it has fewer than this number of + * descriptors available in its onboard memory. + * Setting this to 0 disables RX descriptor prefetch. + * HTHRESH - MAC will only prefetch if there are at least this many descriptors + * available in host memory. + * If PTHRESH is 0, this should also be 0. + * WTHRESH - RX descriptor writeback threshold - MAC will delay writing back + * descriptors until either it has this many to write back, or the + * ITR timer expires. + */ +#define IGB_RX_PTHRESH ((hw->mac.type == e1000_i354) ? 12 : 8) +#define IGB_RX_HTHRESH 8 +#define IGB_TX_PTHRESH ((hw->mac.type == e1000_i354) ? 20 : 8) +#define IGB_TX_HTHRESH 1 +#define IGB_RX_WTHRESH ((hw->mac.type == e1000_82576 && \ + (adapter->flags & IGB_FLAG_HAS_MSIX)) ? 1 : 4) +#define IGB_TX_WTHRESH ((hw->mac.type == e1000_82576 && \ + (adapter->flags & IGB_FLAG_HAS_MSIX)) ? 1 : 16) + +/* this is the size past which hardware will drop packets when setting LPE=0 */ +#define MAXIMUM_ETHERNET_VLAN_SIZE 1522 + +#define IGB_ETH_PKT_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2)) + +/* Supported Rx Buffer Sizes */ +#define IGB_RXBUFFER_256 256 +#define IGB_RXBUFFER_1536 1536 +#define IGB_RXBUFFER_2048 2048 +#define IGB_RXBUFFER_3072 3072 +#define IGB_RX_HDR_LEN IGB_RXBUFFER_256 +#define IGB_TS_HDR_LEN 16 + +/* Attempt to maximize the headroom available for incoming frames. We + * use a 2K buffer for receives and need 1536/1534 to store the data for + * the frame. This leaves us with 512 bytes of room. From that we need + * to deduct the space needed for the shared info and the padding needed + * to IP align the frame. + * + * Note: For cache line sizes 256 or larger this value is going to end + * up negative. In these cases we should fall back to the 3K + * buffers. + */ +#if (PAGE_SIZE < 8192) +#define IGB_MAX_FRAME_BUILD_SKB (IGB_RXBUFFER_1536 - NET_IP_ALIGN) +#define IGB_2K_TOO_SMALL_WITH_PADDING \ +((NET_SKB_PAD + IGB_TS_HDR_LEN + IGB_RXBUFFER_1536) > SKB_WITH_OVERHEAD(IGB_RXBUFFER_2048)) + +static inline int igb_compute_pad(int rx_buf_len) +{ + int page_size, pad_size; + + page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2); + pad_size = SKB_WITH_OVERHEAD(page_size) - rx_buf_len; + + return pad_size; +} + +static inline int igb_skb_pad(void) +{ + int rx_buf_len; + + /* If a 2K buffer cannot handle a standard Ethernet frame then + * optimize padding for a 3K buffer instead of a 1.5K buffer. + * + * For a 3K buffer we need to add enough padding to allow for + * tailroom due to NET_IP_ALIGN possibly shifting us out of + * cache-line alignment. + */ + if (IGB_2K_TOO_SMALL_WITH_PADDING) + rx_buf_len = IGB_RXBUFFER_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN); + else + rx_buf_len = IGB_RXBUFFER_1536; + + /* if needed make room for NET_IP_ALIGN */ + rx_buf_len -= NET_IP_ALIGN; + + return igb_compute_pad(rx_buf_len); +} + +#define IGB_SKB_PAD igb_skb_pad() +#else +#define IGB_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) +#endif + +/* How many Rx Buffers do we bundle into one write to the hardware ? */ +#define IGB_RX_BUFFER_WRITE 16 /* Must be power of 2 */ + +#define IGB_RX_DMA_ATTR \ + (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) + +#define AUTO_ALL_MODES 0 +#define IGB_EEPROM_APME 0x0400 + +#ifndef IGB_MASTER_SLAVE +/* Switch to override PHY master/slave setting */ +#define IGB_MASTER_SLAVE e1000_ms_hw_default +#endif + +#define IGB_MNG_VLAN_NONE -1 + +enum igb_tx_flags { + /* cmd_type flags */ + IGB_TX_FLAGS_VLAN = 0x01, + IGB_TX_FLAGS_TSO = 0x02, + IGB_TX_FLAGS_TSTAMP = 0x04, + + /* olinfo flags */ + IGB_TX_FLAGS_IPV4 = 0x10, + IGB_TX_FLAGS_CSUM = 0x20, +}; + +/* VLAN info */ +#define IGB_TX_FLAGS_VLAN_MASK 0xffff0000 +#define IGB_TX_FLAGS_VLAN_SHIFT 16 + +/* 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 (1u << IGB_MAX_TXD_PWR) + +/* Tx Descriptors needed, worst case */ +#define TXD_USE_COUNT(S) DIV_ROUND_UP((S), IGB_MAX_DATA_PER_TXD) +#define DESC_NEEDED (MAX_SKB_FRAGS + 4) + +/* EEPROM byte offsets */ +#define IGB_SFF_8472_SWAP 0x5C +#define IGB_SFF_8472_COMP 0x5E + +/* Bitmasks */ +#define IGB_SFF_ADDRESSING_MODE 0x4 +#define IGB_SFF_8472_UNSUP 0x00 + +/* TX resources are shared between XDP and netstack + * and we need to tag the buffer type to distinguish them + */ +enum igb_tx_buf_type { + IGB_TYPE_SKB = 0, + IGB_TYPE_XDP, +}; + +/* wrapper around a pointer to a socket buffer, + * so a DMA handle can be stored along with the buffer + */ +struct igb_tx_buffer { + union e1000_adv_tx_desc *next_to_watch; + unsigned long time_stamp; + enum igb_tx_buf_type type; + union { + struct sk_buff *skb; + struct xdp_frame *xdpf; + }; + unsigned int bytecount; + u16 gso_segs; + __be16 protocol; + + DEFINE_DMA_UNMAP_ADDR(dma); + DEFINE_DMA_UNMAP_LEN(len); + u32 tx_flags; +}; + +struct igb_rx_buffer { + dma_addr_t dma; + struct page *page; +#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536) + __u32 page_offset; +#else + __u16 page_offset; +#endif + __u16 pagecnt_bias; +}; + +struct igb_tx_queue_stats { + u64 packets; + u64 bytes; + u64 restart_queue; + u64 restart_queue2; +}; + +struct igb_rx_queue_stats { + u64 packets; + u64 bytes; + u64 drops; + u64 csum_err; + u64 alloc_failed; +}; + +struct igb_ring_container { + struct igb_ring *ring; /* pointer to linked list of rings */ + unsigned int total_bytes; /* total bytes processed this int */ + unsigned int total_packets; /* total packets processed this int */ + u16 work_limit; /* total work allowed per interrupt */ + u8 count; /* total number of rings in vector */ + u8 itr; /* current ITR setting for ring */ +}; + +struct igb_ring { + struct igb_q_vector *q_vector; /* backlink to q_vector */ + struct net_device *netdev; /* back pointer to net_device */ + struct bpf_prog *xdp_prog; + struct device *dev; /* device pointer for dma mapping */ + union { /* array of buffer info structs */ + struct igb_tx_buffer *tx_buffer_info; + struct igb_rx_buffer *rx_buffer_info; + }; + void *desc; /* descriptor ring memory */ + unsigned long flags; /* ring specific flags */ + void __iomem *tail; /* pointer to ring tail register */ + dma_addr_t dma; /* phys address of the ring */ + unsigned int size; /* length of desc. ring in bytes */ + + u16 count; /* number of desc. in the ring */ + u8 queue_index; /* logical index of the ring*/ + u8 reg_idx; /* physical index of the ring */ + bool launchtime_enable; /* true if LaunchTime is enabled */ + bool cbs_enable; /* indicates if CBS is enabled */ + s32 idleslope; /* idleSlope in kbps */ + s32 sendslope; /* sendSlope in kbps */ + s32 hicredit; /* hiCredit in bytes */ + s32 locredit; /* loCredit in bytes */ + + /* everything past this point are written often */ + u16 next_to_clean; + u16 next_to_use; + u16 next_to_alloc; + + union { + /* TX */ + struct { + struct igb_tx_queue_stats tx_stats; + struct u64_stats_sync tx_syncp; + struct u64_stats_sync tx_syncp2; + }; + /* RX */ + struct { + struct sk_buff *skb; + struct igb_rx_queue_stats rx_stats; + struct u64_stats_sync rx_syncp; + }; + }; + struct xdp_rxq_info xdp_rxq; +} ____cacheline_internodealigned_in_smp; + +struct igb_q_vector { + struct igb_adapter *adapter; /* backlink */ + int cpu; /* CPU for DCA */ + u32 eims_value; /* EIMS mask value */ + + u16 itr_val; + u8 set_itr; + void __iomem *itr_register; + + struct igb_ring_container rx, tx; + + struct napi_struct napi; + struct rcu_head rcu; /* to avoid race with update stats on free */ + char name[IFNAMSIZ + 9]; + + /* for dynamic allocation of rings associated with this q_vector */ + struct igb_ring ring[] ____cacheline_internodealigned_in_smp; +}; + +enum e1000_ring_flags_t { + IGB_RING_FLAG_RX_3K_BUFFER, + IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, + IGB_RING_FLAG_RX_SCTP_CSUM, + IGB_RING_FLAG_RX_LB_VLAN_BSWAP, + IGB_RING_FLAG_TX_CTX_IDX, + IGB_RING_FLAG_TX_DETECT_HANG +}; + +#define ring_uses_large_buffer(ring) \ + test_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags) +#define set_ring_uses_large_buffer(ring) \ + set_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags) +#define clear_ring_uses_large_buffer(ring) \ + clear_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags) + +#define ring_uses_build_skb(ring) \ + test_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) +#define set_ring_build_skb_enabled(ring) \ + set_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) +#define clear_ring_build_skb_enabled(ring) \ + clear_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) + +static inline unsigned int igb_rx_bufsz(struct igb_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring_uses_large_buffer(ring)) + return IGB_RXBUFFER_3072; + + if (ring_uses_build_skb(ring)) + return IGB_MAX_FRAME_BUILD_SKB; +#endif + return IGB_RXBUFFER_2048; +} + +static inline unsigned int igb_rx_pg_order(struct igb_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring_uses_large_buffer(ring)) + return 1; +#endif + return 0; +} + +#define igb_rx_pg_size(_ring) (PAGE_SIZE << igb_rx_pg_order(_ring)) + +#define IGB_TXD_DCMD (E1000_ADVTXD_DCMD_EOP | E1000_ADVTXD_DCMD_RS) + +#define IGB_RX_DESC(R, i) \ + (&(((union e1000_adv_rx_desc *)((R)->desc))[i])) +#define IGB_TX_DESC(R, i) \ + (&(((union e1000_adv_tx_desc *)((R)->desc))[i])) +#define IGB_TX_CTXTDESC(R, i) \ + (&(((struct e1000_adv_tx_context_desc *)((R)->desc))[i])) + +/* igb_test_staterr - tests bits within Rx descriptor status and error fields */ +static inline __le32 igb_test_staterr(union e1000_adv_rx_desc *rx_desc, + const u32 stat_err_bits) +{ + return rx_desc->wb.upper.status_error & cpu_to_le32(stat_err_bits); +} + +/* igb_desc_unused - calculate if we have unused descriptors */ +static inline int igb_desc_unused(struct igb_ring *ring) +{ + if (ring->next_to_clean > ring->next_to_use) + return ring->next_to_clean - ring->next_to_use - 1; + + return ring->count + ring->next_to_clean - ring->next_to_use - 1; +} + +#ifdef CONFIG_IGB_HWMON + +#define IGB_HWMON_TYPE_LOC 0 +#define IGB_HWMON_TYPE_TEMP 1 +#define IGB_HWMON_TYPE_CAUTION 2 +#define IGB_HWMON_TYPE_MAX 3 + +struct hwmon_attr { + struct device_attribute dev_attr; + struct e1000_hw *hw; + struct e1000_thermal_diode_data *sensor; + char name[12]; + }; + +struct hwmon_buff { + struct attribute_group group; + const struct attribute_group *groups[2]; + struct attribute *attrs[E1000_MAX_SENSORS * 4 + 1]; + struct hwmon_attr hwmon_list[E1000_MAX_SENSORS * 4]; + unsigned int n_hwmon; + }; +#endif + +/* The number of L2 ether-type filter registers, Index 3 is reserved + * for PTP 1588 timestamp + */ +#define MAX_ETYPE_FILTER (4 - 1) +/* ETQF filter list: one static filter per filter consumer. This is + * to avoid filter collisions later. Add new filters here!! + * + * Current filters: Filter 3 + */ +#define IGB_ETQF_FILTER_1588 3 + +#define IGB_N_EXTTS 2 +#define IGB_N_PEROUT 2 +#define IGB_N_SDP 4 +#define IGB_RETA_SIZE 128 + +enum igb_filter_match_flags { + IGB_FILTER_FLAG_ETHER_TYPE = 0x1, + IGB_FILTER_FLAG_VLAN_TCI = 0x2, + IGB_FILTER_FLAG_SRC_MAC_ADDR = 0x4, + IGB_FILTER_FLAG_DST_MAC_ADDR = 0x8, +}; + +#define IGB_MAX_RXNFC_FILTERS 16 + +/* RX network flow classification data structure */ +struct igb_nfc_input { + /* Byte layout in order, all values with MSB first: + * match_flags - 1 byte + * etype - 2 bytes + * vlan_tci - 2 bytes + */ + u8 match_flags; + __be16 etype; + __be16 vlan_tci; + u8 src_addr[ETH_ALEN]; + u8 dst_addr[ETH_ALEN]; +}; + +struct igb_nfc_filter { + struct hlist_node nfc_node; + struct igb_nfc_input filter; + unsigned long cookie; + u16 etype_reg_index; + u16 sw_idx; + u16 action; +}; + +struct igb_mac_addr { + u8 addr[ETH_ALEN]; + u8 queue; + u8 state; /* bitmask */ +}; + +#define IGB_MAC_STATE_DEFAULT 0x1 +#define IGB_MAC_STATE_IN_USE 0x2 +#define IGB_MAC_STATE_SRC_ADDR 0x4 +#define IGB_MAC_STATE_QUEUE_STEERING 0x8 + +/* board specific private data structure */ +struct igb_adapter { + unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + + struct net_device *netdev; + struct bpf_prog *xdp_prog; + + unsigned long state; + unsigned int flags; + + unsigned int num_q_vectors; + struct msix_entry msix_entries[MAX_MSIX_ENTRIES]; + + /* Interrupt Throttle Rate */ + u32 rx_itr_setting; + u32 tx_itr_setting; + u16 tx_itr; + u16 rx_itr; + + /* TX */ + u16 tx_work_limit; + u32 tx_timeout_count; + int num_tx_queues; + struct igb_ring *tx_ring[16]; + + /* RX */ + int num_rx_queues; + struct igb_ring *rx_ring[16]; + + u32 max_frame_size; + u32 min_frame_size; + + struct timer_list watchdog_timer; + struct timer_list phy_info_timer; + + u16 mng_vlan_id; + u32 bd_number; + u32 wol; + u32 en_mng_pt; + u16 link_speed; + u16 link_duplex; + + u8 __iomem *io_addr; /* Mainly for iounmap use */ + + struct work_struct reset_task; + struct work_struct watchdog_task; + bool fc_autoneg; + u8 tx_timeout_factor; + struct timer_list blink_timer; + unsigned long led_status; + + /* OS defined structs */ + struct pci_dev *pdev; + + spinlock_t stats64_lock; + struct rtnl_link_stats64 stats64; + + /* structs defined in e1000_hw.h */ + struct e1000_hw hw; + struct e1000_hw_stats stats; + struct e1000_phy_info phy_info; + + u32 test_icr; + struct igb_ring test_tx_ring; + struct igb_ring test_rx_ring; + + int msg_enable; + + struct igb_q_vector *q_vector[MAX_Q_VECTORS]; + u32 eims_enable_mask; + u32 eims_other; + + /* to not mess up cache alignment, always add to the bottom */ + u16 tx_ring_count; + u16 rx_ring_count; + unsigned int vfs_allocated_count; + struct vf_data_storage *vf_data; + int vf_rate_link_speed; + u32 rss_queues; + u32 wvbr; + u32 *shadow_vfta; + + struct ptp_clock *ptp_clock; + struct ptp_clock_info ptp_caps; + struct delayed_work ptp_overflow_work; + struct work_struct ptp_tx_work; + struct sk_buff *ptp_tx_skb; + struct hwtstamp_config tstamp_config; + unsigned long ptp_tx_start; + unsigned long last_rx_ptp_check; + unsigned long last_rx_timestamp; + unsigned int ptp_flags; + spinlock_t tmreg_lock; + struct cyclecounter cc; + struct timecounter tc; + u32 tx_hwtstamp_timeouts; + u32 tx_hwtstamp_skipped; + u32 rx_hwtstamp_cleared; + bool pps_sys_wrap_on; + + struct ptp_pin_desc sdp_config[IGB_N_SDP]; + struct { + struct timespec64 start; + struct timespec64 period; + } perout[IGB_N_PEROUT]; + + char fw_version[32]; +#ifdef CONFIG_IGB_HWMON + struct hwmon_buff *igb_hwmon_buff; + bool ets; +#endif + struct i2c_algo_bit_data i2c_algo; + struct i2c_adapter i2c_adap; + struct i2c_client *i2c_client; + u32 rss_indir_tbl_init; + u8 rss_indir_tbl[IGB_RETA_SIZE]; + + unsigned long link_check_timeout; + int copper_tries; + struct e1000_info ei; + u16 eee_advert; + + /* RX network flow classification support */ + struct hlist_head nfc_filter_list; + struct hlist_head cls_flower_list; + unsigned int nfc_filter_count; + /* lock for RX network flow classification filter */ + spinlock_t nfc_lock; + bool etype_bitmap[MAX_ETYPE_FILTER]; + + struct igb_mac_addr *mac_table; + struct vf_mac_filter vf_macs; + struct vf_mac_filter *vf_mac_list; + /* lock for VF resources */ + spinlock_t vfs_lock; +}; + +/* flags controlling PTP/1588 function */ +#define IGB_PTP_ENABLED BIT(0) +#define IGB_PTP_OVERFLOW_CHECK BIT(1) + +#define IGB_FLAG_HAS_MSI BIT(0) +#define IGB_FLAG_DCA_ENABLED BIT(1) +#define IGB_FLAG_QUAD_PORT_A BIT(2) +#define IGB_FLAG_QUEUE_PAIRS BIT(3) +#define IGB_FLAG_DMAC BIT(4) +#define IGB_FLAG_RSS_FIELD_IPV4_UDP BIT(6) +#define IGB_FLAG_RSS_FIELD_IPV6_UDP BIT(7) +#define IGB_FLAG_WOL_SUPPORTED BIT(8) +#define IGB_FLAG_NEED_LINK_UPDATE BIT(9) +#define IGB_FLAG_MEDIA_RESET BIT(10) +#define IGB_FLAG_MAS_CAPABLE BIT(11) +#define IGB_FLAG_MAS_ENABLE BIT(12) +#define IGB_FLAG_HAS_MSIX BIT(13) +#define IGB_FLAG_EEE BIT(14) +#define IGB_FLAG_VLAN_PROMISC BIT(15) +#define IGB_FLAG_RX_LEGACY BIT(16) +#define IGB_FLAG_FQTSS BIT(17) + +/* Media Auto Sense */ +#define IGB_MAS_ENABLE_0 0X0001 +#define IGB_MAS_ENABLE_1 0X0002 +#define IGB_MAS_ENABLE_2 0X0004 +#define IGB_MAS_ENABLE_3 0X0008 + +/* DMA Coalescing defines */ +#define IGB_MIN_TXPBSIZE 20408 +#define IGB_TX_BUF_4096 4096 +#define IGB_DMCTLX_DCFLUSH_DIS 0x80000000 /* Disable DMA Coal Flush */ + +#define IGB_82576_TSYNC_SHIFT 19 +enum e1000_state_t { + __IGB_TESTING, + __IGB_RESETTING, + __IGB_DOWN, + __IGB_PTP_TX_IN_PROGRESS, +}; + +enum igb_boards { + board_82575, +}; + +extern char igb_driver_name[]; + +int igb_xmit_xdp_ring(struct igb_adapter *adapter, + struct igb_ring *ring, + struct xdp_frame *xdpf); +int igb_open(struct net_device *netdev); +int igb_close(struct net_device *netdev); +int igb_up(struct igb_adapter *); +void igb_down(struct igb_adapter *); +void igb_reinit_locked(struct igb_adapter *); +void igb_reset(struct igb_adapter *); +int igb_reinit_queues(struct igb_adapter *); +void igb_write_rss_indir_tbl(struct igb_adapter *); +int igb_set_spd_dplx(struct igb_adapter *, u32, u8); +int igb_setup_tx_resources(struct igb_ring *); +int igb_setup_rx_resources(struct igb_ring *); +void igb_free_tx_resources(struct igb_ring *); +void igb_free_rx_resources(struct igb_ring *); +void igb_configure_tx_ring(struct igb_adapter *, struct igb_ring *); +void igb_configure_rx_ring(struct igb_adapter *, struct igb_ring *); +void igb_setup_tctl(struct igb_adapter *); +void igb_setup_rctl(struct igb_adapter *); +void igb_setup_srrctl(struct igb_adapter *, struct igb_ring *); +netdev_tx_t igb_xmit_frame_ring(struct sk_buff *, struct igb_ring *); +void igb_alloc_rx_buffers(struct igb_ring *, u16); +void igb_update_stats(struct igb_adapter *); +bool igb_has_link(struct igb_adapter *adapter); +void igb_set_ethtool_ops(struct net_device *); +void igb_power_up_link(struct igb_adapter *); +void igb_set_fw_version(struct igb_adapter *); +void igb_ptp_init(struct igb_adapter *adapter); +void igb_ptp_stop(struct igb_adapter *adapter); +void igb_ptp_reset(struct igb_adapter *adapter); +void igb_ptp_suspend(struct igb_adapter *adapter); +void igb_ptp_rx_hang(struct igb_adapter *adapter); +void igb_ptp_tx_hang(struct igb_adapter *adapter); +void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb); +int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, + ktime_t *timestamp); +int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr); +int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr); +void igb_set_flag_queue_pairs(struct igb_adapter *, const u32); +unsigned int igb_get_max_rss_queues(struct igb_adapter *); +#ifdef CONFIG_IGB_HWMON +void igb_sysfs_exit(struct igb_adapter *adapter); +int igb_sysfs_init(struct igb_adapter *adapter); +#endif +static inline s32 igb_reset_phy(struct e1000_hw *hw) +{ + if (hw->phy.ops.reset) + return hw->phy.ops.reset(hw); + + return 0; +} + +static inline s32 igb_read_phy_reg(struct e1000_hw *hw, u32 offset, u16 *data) +{ + if (hw->phy.ops.read_reg) + return hw->phy.ops.read_reg(hw, offset, data); + + return 0; +} + +static inline s32 igb_write_phy_reg(struct e1000_hw *hw, u32 offset, u16 data) +{ + if (hw->phy.ops.write_reg) + return hw->phy.ops.write_reg(hw, offset, data); + + return 0; +} + +static inline s32 igb_get_phy_info(struct e1000_hw *hw) +{ + if (hw->phy.ops.get_phy_info) + return hw->phy.ops.get_phy_info(hw); + + return 0; +} + +static inline struct netdev_queue *txring_txq(const struct igb_ring *tx_ring) +{ + return netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index); +} + +int igb_add_filter(struct igb_adapter *adapter, + struct igb_nfc_filter *input); +int igb_erase_filter(struct igb_adapter *adapter, + struct igb_nfc_filter *input); + +int igb_add_mac_steering_filter(struct igb_adapter *adapter, + const u8 *addr, u8 queue, u8 flags); +int igb_del_mac_steering_filter(struct igb_adapter *adapter, + const u8 *addr, u8 queue, u8 flags); + +#endif /* _IGB_H_ */ diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c new file mode 100644 index 0000000000..4ee849985e --- /dev/null +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -0,0 +1,3511 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2007 - 2018 Intel Corporation. */ + +/* ethtool support for igb */ + +#include <linux/vmalloc.h> +#include <linux/netdevice.h> +#include <linux/pci.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/if_ether.h> +#include <linux/ethtool.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/pm_runtime.h> +#include <linux/highmem.h> +#include <linux/mdio.h> + +#include "igb.h" + +struct igb_stats { + char stat_string[ETH_GSTRING_LEN]; + int sizeof_stat; + int stat_offset; +}; + +#define IGB_STAT(_name, _stat) { \ + .stat_string = _name, \ + .sizeof_stat = sizeof_field(struct igb_adapter, _stat), \ + .stat_offset = offsetof(struct igb_adapter, _stat) \ +} +static const struct igb_stats igb_gstrings_stats[] = { + IGB_STAT("rx_packets", stats.gprc), + IGB_STAT("tx_packets", stats.gptc), + IGB_STAT("rx_bytes", stats.gorc), + IGB_STAT("tx_bytes", stats.gotc), + IGB_STAT("rx_broadcast", stats.bprc), + IGB_STAT("tx_broadcast", stats.bptc), + IGB_STAT("rx_multicast", stats.mprc), + IGB_STAT("tx_multicast", stats.mptc), + IGB_STAT("multicast", stats.mprc), + IGB_STAT("collisions", stats.colc), + IGB_STAT("rx_crc_errors", stats.crcerrs), + IGB_STAT("rx_no_buffer_count", stats.rnbc), + IGB_STAT("rx_missed_errors", stats.mpc), + IGB_STAT("tx_aborted_errors", stats.ecol), + IGB_STAT("tx_carrier_errors", stats.tncrs), + IGB_STAT("tx_window_errors", stats.latecol), + IGB_STAT("tx_abort_late_coll", stats.latecol), + IGB_STAT("tx_deferred_ok", stats.dc), + IGB_STAT("tx_single_coll_ok", stats.scc), + IGB_STAT("tx_multi_coll_ok", stats.mcc), + IGB_STAT("tx_timeout_count", tx_timeout_count), + IGB_STAT("rx_long_length_errors", stats.roc), + IGB_STAT("rx_short_length_errors", stats.ruc), + IGB_STAT("rx_align_errors", stats.algnerrc), + IGB_STAT("tx_tcp_seg_good", stats.tsctc), + IGB_STAT("tx_tcp_seg_failed", stats.tsctfc), + IGB_STAT("rx_flow_control_xon", stats.xonrxc), + IGB_STAT("rx_flow_control_xoff", stats.xoffrxc), + IGB_STAT("tx_flow_control_xon", stats.xontxc), + IGB_STAT("tx_flow_control_xoff", stats.xofftxc), + IGB_STAT("rx_long_byte_count", stats.gorc), + IGB_STAT("tx_dma_out_of_sync", stats.doosync), + IGB_STAT("tx_smbus", stats.mgptc), + IGB_STAT("rx_smbus", stats.mgprc), + IGB_STAT("dropped_smbus", stats.mgpdc), + IGB_STAT("os2bmc_rx_by_bmc", stats.o2bgptc), + IGB_STAT("os2bmc_tx_by_bmc", stats.b2ospc), + IGB_STAT("os2bmc_tx_by_host", stats.o2bspc), + IGB_STAT("os2bmc_rx_by_host", stats.b2ogprc), + IGB_STAT("tx_hwtstamp_timeouts", tx_hwtstamp_timeouts), + IGB_STAT("tx_hwtstamp_skipped", tx_hwtstamp_skipped), + IGB_STAT("rx_hwtstamp_cleared", rx_hwtstamp_cleared), +}; + +#define IGB_NETDEV_STAT(_net_stat) { \ + .stat_string = __stringify(_net_stat), \ + .sizeof_stat = sizeof_field(struct rtnl_link_stats64, _net_stat), \ + .stat_offset = offsetof(struct rtnl_link_stats64, _net_stat) \ +} +static const struct igb_stats igb_gstrings_net_stats[] = { + IGB_NETDEV_STAT(rx_errors), + IGB_NETDEV_STAT(tx_errors), + IGB_NETDEV_STAT(tx_dropped), + IGB_NETDEV_STAT(rx_length_errors), + IGB_NETDEV_STAT(rx_over_errors), + IGB_NETDEV_STAT(rx_frame_errors), + IGB_NETDEV_STAT(rx_fifo_errors), + IGB_NETDEV_STAT(tx_fifo_errors), + IGB_NETDEV_STAT(tx_heartbeat_errors) +}; + +#define IGB_GLOBAL_STATS_LEN \ + (sizeof(igb_gstrings_stats) / sizeof(struct igb_stats)) +#define IGB_NETDEV_STATS_LEN \ + (sizeof(igb_gstrings_net_stats) / sizeof(struct igb_stats)) +#define IGB_RX_QUEUE_STATS_LEN \ + (sizeof(struct igb_rx_queue_stats) / sizeof(u64)) + +#define IGB_TX_QUEUE_STATS_LEN 3 /* packets, bytes, restart_queue */ + +#define IGB_QUEUE_STATS_LEN \ + ((((struct igb_adapter *)netdev_priv(netdev))->num_rx_queues * \ + IGB_RX_QUEUE_STATS_LEN) + \ + (((struct igb_adapter *)netdev_priv(netdev))->num_tx_queues * \ + IGB_TX_QUEUE_STATS_LEN)) +#define IGB_STATS_LEN \ + (IGB_GLOBAL_STATS_LEN + IGB_NETDEV_STATS_LEN + IGB_QUEUE_STATS_LEN) + +enum igb_diagnostics_results { + TEST_REG = 0, + TEST_EEP, + TEST_IRQ, + TEST_LOOP, + TEST_LINK +}; + +static const char igb_gstrings_test[][ETH_GSTRING_LEN] = { + [TEST_REG] = "Register test (offline)", + [TEST_EEP] = "Eeprom test (offline)", + [TEST_IRQ] = "Interrupt test (offline)", + [TEST_LOOP] = "Loopback test (offline)", + [TEST_LINK] = "Link test (on/offline)" +}; +#define IGB_TEST_LEN (sizeof(igb_gstrings_test) / ETH_GSTRING_LEN) + +static const char igb_priv_flags_strings[][ETH_GSTRING_LEN] = { +#define IGB_PRIV_FLAGS_LEGACY_RX BIT(0) + "legacy-rx", +}; + +#define IGB_PRIV_FLAGS_STR_LEN ARRAY_SIZE(igb_priv_flags_strings) + +static int igb_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + struct e1000_dev_spec_82575 *dev_spec = &hw->dev_spec._82575; + struct e1000_sfp_flags *eth_flags = &dev_spec->eth_flags; + u32 status; + u32 speed; + u32 supported, advertising; + + status = pm_runtime_suspended(&adapter->pdev->dev) ? + 0 : rd32(E1000_STATUS); + if (hw->phy.media_type == e1000_media_type_copper) { + + supported = (SUPPORTED_10baseT_Half | + SUPPORTED_10baseT_Full | + SUPPORTED_100baseT_Half | + SUPPORTED_100baseT_Full | + SUPPORTED_1000baseT_Full| + SUPPORTED_Autoneg | + SUPPORTED_TP | + SUPPORTED_Pause); + advertising = ADVERTISED_TP; + + if (hw->mac.autoneg == 1) { + advertising |= ADVERTISED_Autoneg; + /* the e1000 autoneg seems to match ethtool nicely */ + advertising |= hw->phy.autoneg_advertised; + } + + cmd->base.port = PORT_TP; + cmd->base.phy_address = hw->phy.addr; + } else { + supported = (SUPPORTED_FIBRE | + SUPPORTED_1000baseKX_Full | + SUPPORTED_Autoneg | + SUPPORTED_Pause); + advertising = (ADVERTISED_FIBRE | + ADVERTISED_1000baseKX_Full); + if (hw->mac.type == e1000_i354) { + if ((hw->device_id == + E1000_DEV_ID_I354_BACKPLANE_2_5GBPS) && + !(status & E1000_STATUS_2P5_SKU_OVER)) { + supported |= SUPPORTED_2500baseX_Full; + supported &= ~SUPPORTED_1000baseKX_Full; + advertising |= ADVERTISED_2500baseX_Full; + advertising &= ~ADVERTISED_1000baseKX_Full; + } + } + if (eth_flags->e100_base_fx || eth_flags->e100_base_lx) { + supported |= SUPPORTED_100baseT_Full; + advertising |= ADVERTISED_100baseT_Full; + } + if (hw->mac.autoneg == 1) + advertising |= ADVERTISED_Autoneg; + + cmd->base.port = PORT_FIBRE; + } + if (hw->mac.autoneg != 1) + advertising &= ~(ADVERTISED_Pause | + ADVERTISED_Asym_Pause); + + switch (hw->fc.requested_mode) { + case e1000_fc_full: + advertising |= ADVERTISED_Pause; + break; + case e1000_fc_rx_pause: + advertising |= (ADVERTISED_Pause | + ADVERTISED_Asym_Pause); + break; + case e1000_fc_tx_pause: + advertising |= ADVERTISED_Asym_Pause; + break; + default: + advertising &= ~(ADVERTISED_Pause | + ADVERTISED_Asym_Pause); + } + if (status & E1000_STATUS_LU) { + if ((status & E1000_STATUS_2P5_SKU) && + !(status & E1000_STATUS_2P5_SKU_OVER)) { + speed = SPEED_2500; + } else if (status & E1000_STATUS_SPEED_1000) { + speed = SPEED_1000; + } else if (status & E1000_STATUS_SPEED_100) { + speed = SPEED_100; + } else { + speed = SPEED_10; + } + if ((status & E1000_STATUS_FD) || + hw->phy.media_type != e1000_media_type_copper) + cmd->base.duplex = DUPLEX_FULL; + else + cmd->base.duplex = DUPLEX_HALF; + } else { + speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; + } + cmd->base.speed = speed; + if ((hw->phy.media_type == e1000_media_type_fiber) || + hw->mac.autoneg) + cmd->base.autoneg = AUTONEG_ENABLE; + else + cmd->base.autoneg = AUTONEG_DISABLE; + + /* MDI-X => 2; MDI =>1; Invalid =>0 */ + if (hw->phy.media_type == e1000_media_type_copper) + cmd->base.eth_tp_mdix = hw->phy.is_mdix ? ETH_TP_MDI_X : + ETH_TP_MDI; + else + cmd->base.eth_tp_mdix = ETH_TP_MDI_INVALID; + + if (hw->phy.mdix == AUTO_ALL_MODES) + cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO; + else + cmd->base.eth_tp_mdix_ctrl = hw->phy.mdix; + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); + + return 0; +} + +static int igb_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *cmd) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + u32 advertising; + + /* When SoL/IDER sessions are active, autoneg/speed/duplex + * cannot be changed + */ + if (igb_check_reset_block(hw)) { + dev_err(&adapter->pdev->dev, + "Cannot change link characteristics when SoL/IDER is active.\n"); + return -EINVAL; + } + + /* MDI setting is only allowed when autoneg enabled because + * some hardware doesn't allow MDI setting when speed or + * duplex is forced. + */ + if (cmd->base.eth_tp_mdix_ctrl) { + if (hw->phy.media_type != e1000_media_type_copper) + return -EOPNOTSUPP; + + if ((cmd->base.eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) && + (cmd->base.autoneg != AUTONEG_ENABLE)) { + dev_err(&adapter->pdev->dev, "forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n"); + return -EINVAL; + } + } + + while (test_and_set_bit(__IGB_RESETTING, &adapter->state)) + usleep_range(1000, 2000); + + ethtool_convert_link_mode_to_legacy_u32(&advertising, + cmd->link_modes.advertising); + + if (cmd->base.autoneg == AUTONEG_ENABLE) { + hw->mac.autoneg = 1; + if (hw->phy.media_type == e1000_media_type_fiber) { + hw->phy.autoneg_advertised = advertising | + ADVERTISED_FIBRE | + ADVERTISED_Autoneg; + switch (adapter->link_speed) { + case SPEED_2500: + hw->phy.autoneg_advertised = + ADVERTISED_2500baseX_Full; + break; + case SPEED_1000: + hw->phy.autoneg_advertised = + ADVERTISED_1000baseT_Full; + break; + case SPEED_100: + hw->phy.autoneg_advertised = + ADVERTISED_100baseT_Full; + break; + default: + break; + } + } else { + hw->phy.autoneg_advertised = advertising | + ADVERTISED_TP | + ADVERTISED_Autoneg; + } + advertising = hw->phy.autoneg_advertised; + if (adapter->fc_autoneg) + hw->fc.requested_mode = e1000_fc_default; + } else { + u32 speed = cmd->base.speed; + /* calling this overrides forced MDI setting */ + if (igb_set_spd_dplx(adapter, speed, cmd->base.duplex)) { + clear_bit(__IGB_RESETTING, &adapter->state); + return -EINVAL; + } + } + + /* MDI-X => 2; MDI => 1; Auto => 3 */ + if (cmd->base.eth_tp_mdix_ctrl) { + /* fix up the value for auto (3 => 0) as zero is mapped + * internally to auto + */ + if (cmd->base.eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO) + hw->phy.mdix = AUTO_ALL_MODES; + else + hw->phy.mdix = cmd->base.eth_tp_mdix_ctrl; + } + + /* reset the link */ + if (netif_running(adapter->netdev)) { + igb_down(adapter); + igb_up(adapter); + } else + igb_reset(adapter); + + clear_bit(__IGB_RESETTING, &adapter->state); + return 0; +} + +static u32 igb_get_link(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_mac_info *mac = &adapter->hw.mac; + + /* If the link is not reported up to netdev, interrupts are disabled, + * and so the physical link state may have changed since we last + * looked. Set get_link_status to make sure that the true link + * state is interrogated, rather than pulling a cached and possibly + * stale link state from the driver. + */ + if (!netif_carrier_ok(netdev)) + mac->get_link_status = 1; + + return igb_has_link(adapter); +} + +static void igb_get_pauseparam(struct net_device *netdev, + struct ethtool_pauseparam *pause) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + + pause->autoneg = + (adapter->fc_autoneg ? AUTONEG_ENABLE : AUTONEG_DISABLE); + + if (hw->fc.current_mode == e1000_fc_rx_pause) + pause->rx_pause = 1; + else if (hw->fc.current_mode == e1000_fc_tx_pause) + pause->tx_pause = 1; + else if (hw->fc.current_mode == e1000_fc_full) { + pause->rx_pause = 1; + pause->tx_pause = 1; + } +} + +static int igb_set_pauseparam(struct net_device *netdev, + struct ethtool_pauseparam *pause) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + int retval = 0; + int i; + + /* 100basefx does not support setting link flow control */ + if (hw->dev_spec._82575.eth_flags.e100_base_fx) + return -EINVAL; + + adapter->fc_autoneg = pause->autoneg; + + while (test_and_set_bit(__IGB_RESETTING, &adapter->state)) + usleep_range(1000, 2000); + + if (adapter->fc_autoneg == AUTONEG_ENABLE) { + hw->fc.requested_mode = e1000_fc_default; + if (netif_running(adapter->netdev)) { + igb_down(adapter); + igb_up(adapter); + } else { + igb_reset(adapter); + } + } else { + if (pause->rx_pause && pause->tx_pause) + hw->fc.requested_mode = e1000_fc_full; + else if (pause->rx_pause && !pause->tx_pause) + hw->fc.requested_mode = e1000_fc_rx_pause; + else if (!pause->rx_pause && pause->tx_pause) + hw->fc.requested_mode = e1000_fc_tx_pause; + else if (!pause->rx_pause && !pause->tx_pause) + hw->fc.requested_mode = e1000_fc_none; + + hw->fc.current_mode = hw->fc.requested_mode; + + retval = ((hw->phy.media_type == e1000_media_type_copper) ? + igb_force_mac_fc(hw) : igb_setup_link(hw)); + + /* Make sure SRRCTL considers new fc settings for each ring */ + for (i = 0; i < adapter->num_rx_queues; i++) { + struct igb_ring *ring = adapter->rx_ring[i]; + + igb_setup_srrctl(adapter, ring); + } + } + + clear_bit(__IGB_RESETTING, &adapter->state); + return retval; +} + +static u32 igb_get_msglevel(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + return adapter->msg_enable; +} + +static void igb_set_msglevel(struct net_device *netdev, u32 data) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + adapter->msg_enable = data; +} + +static int igb_get_regs_len(struct net_device *netdev) +{ +#define IGB_REGS_LEN 740 + return IGB_REGS_LEN * sizeof(u32); +} + +static void igb_get_regs(struct net_device *netdev, + struct ethtool_regs *regs, void *p) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + u32 *regs_buff = p; + u8 i; + + memset(p, 0, IGB_REGS_LEN * sizeof(u32)); + + regs->version = (1u << 24) | (hw->revision_id << 16) | hw->device_id; + + /* General Registers */ + regs_buff[0] = rd32(E1000_CTRL); + regs_buff[1] = rd32(E1000_STATUS); + regs_buff[2] = rd32(E1000_CTRL_EXT); + regs_buff[3] = rd32(E1000_MDIC); + regs_buff[4] = rd32(E1000_SCTL); + regs_buff[5] = rd32(E1000_CONNSW); + regs_buff[6] = rd32(E1000_VET); + regs_buff[7] = rd32(E1000_LEDCTL); + regs_buff[8] = rd32(E1000_PBA); + regs_buff[9] = rd32(E1000_PBS); + regs_buff[10] = rd32(E1000_FRTIMER); + regs_buff[11] = rd32(E1000_TCPTIMER); + + /* NVM Register */ + regs_buff[12] = rd32(E1000_EECD); + + /* Interrupt */ + /* Reading EICS for EICR because they read the + * same but EICS does not clear on read + */ + regs_buff[13] = rd32(E1000_EICS); + regs_buff[14] = rd32(E1000_EICS); + regs_buff[15] = rd32(E1000_EIMS); + regs_buff[16] = rd32(E1000_EIMC); + regs_buff[17] = rd32(E1000_EIAC); + regs_buff[18] = rd32(E1000_EIAM); + /* Reading ICS for ICR because they read the + * same but ICS does not clear on read + */ + regs_buff[19] = rd32(E1000_ICS); + regs_buff[20] = rd32(E1000_ICS); + regs_buff[21] = rd32(E1000_IMS); + regs_buff[22] = rd32(E1000_IMC); + regs_buff[23] = rd32(E1000_IAC); + regs_buff[24] = rd32(E1000_IAM); + regs_buff[25] = rd32(E1000_IMIRVP); + + /* Flow Control */ + regs_buff[26] = rd32(E1000_FCAL); + regs_buff[27] = rd32(E1000_FCAH); + regs_buff[28] = rd32(E1000_FCTTV); + regs_buff[29] = rd32(E1000_FCRTL); + regs_buff[30] = rd32(E1000_FCRTH); + regs_buff[31] = rd32(E1000_FCRTV); + + /* Receive */ + regs_buff[32] = rd32(E1000_RCTL); + regs_buff[33] = rd32(E1000_RXCSUM); + regs_buff[34] = rd32(E1000_RLPML); + regs_buff[35] = rd32(E1000_RFCTL); + regs_buff[36] = rd32(E1000_MRQC); + regs_buff[37] = rd32(E1000_VT_CTL); + + /* Transmit */ + regs_buff[38] = rd32(E1000_TCTL); + regs_buff[39] = rd32(E1000_TCTL_EXT); + regs_buff[40] = rd32(E1000_TIPG); + regs_buff[41] = rd32(E1000_DTXCTL); + + /* Wake Up */ + regs_buff[42] = rd32(E1000_WUC); + regs_buff[43] = rd32(E1000_WUFC); + regs_buff[44] = rd32(E1000_WUS); + regs_buff[45] = rd32(E1000_IPAV); + regs_buff[46] = rd32(E1000_WUPL); + + /* MAC */ + regs_buff[47] = rd32(E1000_PCS_CFG0); + regs_buff[48] = rd32(E1000_PCS_LCTL); + regs_buff[49] = rd32(E1000_PCS_LSTAT); + regs_buff[50] = rd32(E1000_PCS_ANADV); + regs_buff[51] = rd32(E1000_PCS_LPAB); + regs_buff[52] = rd32(E1000_PCS_NPTX); + regs_buff[53] = rd32(E1000_PCS_LPABNP); + + /* Statistics */ + regs_buff[54] = adapter->stats.crcerrs; + regs_buff[55] = adapter->stats.algnerrc; + regs_buff[56] = adapter->stats.symerrs; + regs_buff[57] = adapter->stats.rxerrc; + regs_buff[58] = adapter->stats.mpc; + regs_buff[59] = adapter->stats.scc; + regs_buff[60] = adapter->stats.ecol; + regs_buff[61] = adapter->stats.mcc; + regs_buff[62] = adapter->stats.latecol; + regs_buff[63] = adapter->stats.colc; + regs_buff[64] = adapter->stats.dc; + regs_buff[65] = adapter->stats.tncrs; + regs_buff[66] = adapter->stats.sec; + regs_buff[67] = adapter->stats.htdpmc; + regs_buff[68] = adapter->stats.rlec; + regs_buff[69] = adapter->stats.xonrxc; + regs_buff[70] = adapter->stats.xontxc; + regs_buff[71] = adapter->stats.xoffrxc; + regs_buff[72] = adapter->stats.xofftxc; + regs_buff[73] = adapter->stats.fcruc; + regs_buff[74] = adapter->stats.prc64; + regs_buff[75] = adapter->stats.prc127; + regs_buff[76] = adapter->stats.prc255; + regs_buff[77] = adapter->stats.prc511; + regs_buff[78] = adapter->stats.prc1023; + regs_buff[79] = adapter->stats.prc1522; + regs_buff[80] = adapter->stats.gprc; + regs_buff[81] = adapter->stats.bprc; + regs_buff[82] = adapter->stats.mprc; + regs_buff[83] = adapter->stats.gptc; + regs_buff[84] = adapter->stats.gorc; + regs_buff[86] = adapter->stats.gotc; + regs_buff[88] = adapter->stats.rnbc; + regs_buff[89] = adapter->stats.ruc; + regs_buff[90] = adapter->stats.rfc; + regs_buff[91] = adapter->stats.roc; + regs_buff[92] = adapter->stats.rjc; + regs_buff[93] = adapter->stats.mgprc; + regs_buff[94] = adapter->stats.mgpdc; + regs_buff[95] = adapter->stats.mgptc; + regs_buff[96] = adapter->stats.tor; + regs_buff[98] = adapter->stats.tot; + regs_buff[100] = adapter->stats.tpr; + regs_buff[101] = adapter->stats.tpt; + regs_buff[102] = adapter->stats.ptc64; + regs_buff[103] = adapter->stats.ptc127; + regs_buff[104] = adapter->stats.ptc255; + regs_buff[105] = adapter->stats.ptc511; + regs_buff[106] = adapter->stats.ptc1023; + regs_buff[107] = adapter->stats.ptc1522; + regs_buff[108] = adapter->stats.mptc; + regs_buff[109] = adapter->stats.bptc; + regs_buff[110] = adapter->stats.tsctc; + regs_buff[111] = adapter->stats.iac; + regs_buff[112] = adapter->stats.rpthc; + regs_buff[113] = adapter->stats.hgptc; + regs_buff[114] = adapter->stats.hgorc; + regs_buff[116] = adapter->stats.hgotc; + regs_buff[118] = adapter->stats.lenerrs; + regs_buff[119] = adapter->stats.scvpc; + regs_buff[120] = adapter->stats.hrmpc; + + for (i = 0; i < 4; i++) + regs_buff[121 + i] = rd32(E1000_SRRCTL(i)); + for (i = 0; i < 4; i++) + regs_buff[125 + i] = rd32(E1000_PSRTYPE(i)); + for (i = 0; i < 4; i++) + regs_buff[129 + i] = rd32(E1000_RDBAL(i)); + for (i = 0; i < 4; i++) + regs_buff[133 + i] = rd32(E1000_RDBAH(i)); + for (i = 0; i < 4; i++) + regs_buff[137 + i] = rd32(E1000_RDLEN(i)); + for (i = 0; i < 4; i++) + regs_buff[141 + i] = rd32(E1000_RDH(i)); + for (i = 0; i < 4; i++) + regs_buff[145 + i] = rd32(E1000_RDT(i)); + for (i = 0; i < 4; i++) + regs_buff[149 + i] = rd32(E1000_RXDCTL(i)); + + for (i = 0; i < 10; i++) + regs_buff[153 + i] = rd32(E1000_EITR(i)); + for (i = 0; i < 8; i++) + regs_buff[163 + i] = rd32(E1000_IMIR(i)); + for (i = 0; i < 8; i++) + regs_buff[171 + i] = rd32(E1000_IMIREXT(i)); + for (i = 0; i < 16; i++) + regs_buff[179 + i] = rd32(E1000_RAL(i)); + for (i = 0; i < 16; i++) + regs_buff[195 + i] = rd32(E1000_RAH(i)); + + for (i = 0; i < 4; i++) + regs_buff[211 + i] = rd32(E1000_TDBAL(i)); + for (i = 0; i < 4; i++) + regs_buff[215 + i] = rd32(E1000_TDBAH(i)); + for (i = 0; i < 4; i++) + regs_buff[219 + i] = rd32(E1000_TDLEN(i)); + for (i = 0; i < 4; i++) + regs_buff[223 + i] = rd32(E1000_TDH(i)); + for (i = 0; i < 4; i++) + regs_buff[227 + i] = rd32(E1000_TDT(i)); + for (i = 0; i < 4; i++) + regs_buff[231 + i] = rd32(E1000_TXDCTL(i)); + for (i = 0; i < 4; i++) + regs_buff[235 + i] = rd32(E1000_TDWBAL(i)); + for (i = 0; i < 4; i++) + regs_buff[239 + i] = rd32(E1000_TDWBAH(i)); + for (i = 0; i < 4; i++) + regs_buff[243 + i] = rd32(E1000_DCA_TXCTRL(i)); + + for (i = 0; i < 4; i++) + regs_buff[247 + i] = rd32(E1000_IP4AT_REG(i)); + for (i = 0; i < 4; i++) + regs_buff[251 + i] = rd32(E1000_IP6AT_REG(i)); + for (i = 0; i < 32; i++) + regs_buff[255 + i] = rd32(E1000_WUPM_REG(i)); + for (i = 0; i < 128; i++) + regs_buff[287 + i] = rd32(E1000_FFMT_REG(i)); + for (i = 0; i < 128; i++) + regs_buff[415 + i] = rd32(E1000_FFVT_REG(i)); + for (i = 0; i < 4; i++) + regs_buff[543 + i] = rd32(E1000_FFLT_REG(i)); + + regs_buff[547] = rd32(E1000_TDFH); + regs_buff[548] = rd32(E1000_TDFT); + regs_buff[549] = rd32(E1000_TDFHS); + regs_buff[550] = rd32(E1000_TDFPC); + + if (hw->mac.type > e1000_82580) { + regs_buff[551] = adapter->stats.o2bgptc; + regs_buff[552] = adapter->stats.b2ospc; + regs_buff[553] = adapter->stats.o2bspc; + regs_buff[554] = adapter->stats.b2ogprc; + } + + if (hw->mac.type == e1000_82576) { + for (i = 0; i < 12; i++) + regs_buff[555 + i] = rd32(E1000_SRRCTL(i + 4)); + for (i = 0; i < 4; i++) + regs_buff[567 + i] = rd32(E1000_PSRTYPE(i + 4)); + for (i = 0; i < 12; i++) + regs_buff[571 + i] = rd32(E1000_RDBAL(i + 4)); + for (i = 0; i < 12; i++) + regs_buff[583 + i] = rd32(E1000_RDBAH(i + 4)); + for (i = 0; i < 12; i++) + regs_buff[595 + i] = rd32(E1000_RDLEN(i + 4)); + for (i = 0; i < 12; i++) + regs_buff[607 + i] = rd32(E1000_RDH(i + 4)); + for (i = 0; i < 12; i++) + regs_buff[619 + i] = rd32(E1000_RDT(i + 4)); + for (i = 0; i < 12; i++) + regs_buff[631 + i] = rd32(E1000_RXDCTL(i + 4)); + + for (i = 0; i < 12; i++) + regs_buff[643 + i] = rd32(E1000_TDBAL(i + 4)); + for (i = 0; i < 12; i++) + regs_buff[655 + i] = rd32(E1000_TDBAH(i + 4)); + for (i = 0; i < 12; i++) + regs_buff[667 + i] = rd32(E1000_TDLEN(i + 4)); + for (i = 0; i < 12; i++) + regs_buff[679 + i] = rd32(E1000_TDH(i + 4)); + for (i = 0; i < 12; i++) + regs_buff[691 + i] = rd32(E1000_TDT(i + 4)); + for (i = 0; i < 12; i++) + regs_buff[703 + i] = rd32(E1000_TXDCTL(i + 4)); + for (i = 0; i < 12; i++) + regs_buff[715 + i] = rd32(E1000_TDWBAL(i + 4)); + for (i = 0; i < 12; i++) + regs_buff[727 + i] = rd32(E1000_TDWBAH(i + 4)); + } + + if (hw->mac.type == e1000_i210 || hw->mac.type == e1000_i211) + regs_buff[739] = rd32(E1000_I210_RR2DCDELAY); +} + +static int igb_get_eeprom_len(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + return adapter->hw.nvm.word_size * 2; +} + +static int igb_get_eeprom(struct net_device *netdev, + struct ethtool_eeprom *eeprom, u8 *bytes) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + u16 *eeprom_buff; + int first_word, last_word; + int ret_val = 0; + u16 i; + + if (eeprom->len == 0) + return -EINVAL; + + eeprom->magic = hw->vendor_id | (hw->device_id << 16); + + first_word = eeprom->offset >> 1; + last_word = (eeprom->offset + eeprom->len - 1) >> 1; + + eeprom_buff = kmalloc_array(last_word - first_word + 1, sizeof(u16), + GFP_KERNEL); + if (!eeprom_buff) + return -ENOMEM; + + if (hw->nvm.type == e1000_nvm_eeprom_spi) + ret_val = hw->nvm.ops.read(hw, first_word, + last_word - first_word + 1, + eeprom_buff); + else { + for (i = 0; i < last_word - first_word + 1; i++) { + ret_val = hw->nvm.ops.read(hw, first_word + i, 1, + &eeprom_buff[i]); + if (ret_val) + break; + } + } + + /* Device's eeprom is always little-endian, word addressable */ + for (i = 0; i < last_word - first_word + 1; i++) + le16_to_cpus(&eeprom_buff[i]); + + memcpy(bytes, (u8 *)eeprom_buff + (eeprom->offset & 1), + eeprom->len); + kfree(eeprom_buff); + + return ret_val; +} + +static int igb_set_eeprom(struct net_device *netdev, + struct ethtool_eeprom *eeprom, u8 *bytes) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + u16 *eeprom_buff; + void *ptr; + int max_len, first_word, last_word, ret_val = 0; + u16 i; + + if (eeprom->len == 0) + return -EOPNOTSUPP; + + if ((hw->mac.type >= e1000_i210) && + !igb_get_flash_presence_i210(hw)) { + return -EOPNOTSUPP; + } + + if (eeprom->magic != (hw->vendor_id | (hw->device_id << 16))) + return -EFAULT; + + max_len = hw->nvm.word_size * 2; + + first_word = eeprom->offset >> 1; + last_word = (eeprom->offset + eeprom->len - 1) >> 1; + eeprom_buff = kmalloc(max_len, GFP_KERNEL); + if (!eeprom_buff) + return -ENOMEM; + + ptr = (void *)eeprom_buff; + + if (eeprom->offset & 1) { + /* need read/modify/write of first changed EEPROM word + * only the second byte of the word is being modified + */ + ret_val = hw->nvm.ops.read(hw, first_word, 1, + &eeprom_buff[0]); + ptr++; + } + if (((eeprom->offset + eeprom->len) & 1) && (ret_val == 0)) { + /* need read/modify/write of last changed EEPROM word + * only the first byte of the word is being modified + */ + ret_val = hw->nvm.ops.read(hw, last_word, 1, + &eeprom_buff[last_word - first_word]); + if (ret_val) + goto out; + } + + /* Device's eeprom is always little-endian, word addressable */ + for (i = 0; i < last_word - first_word + 1; i++) + le16_to_cpus(&eeprom_buff[i]); + + memcpy(ptr, bytes, eeprom->len); + + for (i = 0; i < last_word - first_word + 1; i++) + cpu_to_le16s(&eeprom_buff[i]); + + ret_val = hw->nvm.ops.write(hw, first_word, + last_word - first_word + 1, eeprom_buff); + + /* Update the checksum if nvm write succeeded */ + if (ret_val == 0) + hw->nvm.ops.update(hw); + + igb_set_fw_version(adapter); +out: + kfree(eeprom_buff); + return ret_val; +} + +static void igb_get_drvinfo(struct net_device *netdev, + struct ethtool_drvinfo *drvinfo) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + + strscpy(drvinfo->driver, igb_driver_name, sizeof(drvinfo->driver)); + + /* EEPROM image version # is reported as firmware version # for + * 82575 controllers + */ + strscpy(drvinfo->fw_version, adapter->fw_version, + sizeof(drvinfo->fw_version)); + strscpy(drvinfo->bus_info, pci_name(adapter->pdev), + sizeof(drvinfo->bus_info)); + + drvinfo->n_priv_flags = IGB_PRIV_FLAGS_STR_LEN; +} + +static void igb_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + + ring->rx_max_pending = IGB_MAX_RXD; + ring->tx_max_pending = IGB_MAX_TXD; + ring->rx_pending = adapter->rx_ring_count; + ring->tx_pending = adapter->tx_ring_count; +} + +static int igb_set_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct igb_ring *temp_ring; + int i, err = 0; + u16 new_rx_count, new_tx_count; + + if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) + return -EINVAL; + + new_rx_count = min_t(u32, ring->rx_pending, IGB_MAX_RXD); + new_rx_count = max_t(u16, new_rx_count, IGB_MIN_RXD); + new_rx_count = ALIGN(new_rx_count, REQ_RX_DESCRIPTOR_MULTIPLE); + + new_tx_count = min_t(u32, ring->tx_pending, IGB_MAX_TXD); + new_tx_count = max_t(u16, new_tx_count, IGB_MIN_TXD); + new_tx_count = ALIGN(new_tx_count, REQ_TX_DESCRIPTOR_MULTIPLE); + + if ((new_tx_count == adapter->tx_ring_count) && + (new_rx_count == adapter->rx_ring_count)) { + /* nothing to do */ + return 0; + } + + while (test_and_set_bit(__IGB_RESETTING, &adapter->state)) + usleep_range(1000, 2000); + + if (!netif_running(adapter->netdev)) { + for (i = 0; i < adapter->num_tx_queues; i++) + adapter->tx_ring[i]->count = new_tx_count; + for (i = 0; i < adapter->num_rx_queues; i++) + adapter->rx_ring[i]->count = new_rx_count; + adapter->tx_ring_count = new_tx_count; + adapter->rx_ring_count = new_rx_count; + goto clear_reset; + } + + if (adapter->num_tx_queues > adapter->num_rx_queues) + temp_ring = vmalloc(array_size(sizeof(struct igb_ring), + adapter->num_tx_queues)); + else + temp_ring = vmalloc(array_size(sizeof(struct igb_ring), + adapter->num_rx_queues)); + + if (!temp_ring) { + err = -ENOMEM; + goto clear_reset; + } + + igb_down(adapter); + + /* We can't just free everything and then setup again, + * because the ISRs in MSI-X mode get passed pointers + * to the Tx and Rx ring structs. + */ + if (new_tx_count != adapter->tx_ring_count) { + for (i = 0; i < adapter->num_tx_queues; i++) { + memcpy(&temp_ring[i], adapter->tx_ring[i], + sizeof(struct igb_ring)); + + temp_ring[i].count = new_tx_count; + err = igb_setup_tx_resources(&temp_ring[i]); + if (err) { + while (i) { + i--; + igb_free_tx_resources(&temp_ring[i]); + } + goto err_setup; + } + } + + for (i = 0; i < adapter->num_tx_queues; i++) { + igb_free_tx_resources(adapter->tx_ring[i]); + + memcpy(adapter->tx_ring[i], &temp_ring[i], + sizeof(struct igb_ring)); + } + + adapter->tx_ring_count = new_tx_count; + } + + if (new_rx_count != adapter->rx_ring_count) { + for (i = 0; i < adapter->num_rx_queues; i++) { + memcpy(&temp_ring[i], adapter->rx_ring[i], + sizeof(struct igb_ring)); + + temp_ring[i].count = new_rx_count; + err = igb_setup_rx_resources(&temp_ring[i]); + if (err) { + while (i) { + i--; + igb_free_rx_resources(&temp_ring[i]); + } + goto err_setup; + } + + } + + for (i = 0; i < adapter->num_rx_queues; i++) { + igb_free_rx_resources(adapter->rx_ring[i]); + + memcpy(adapter->rx_ring[i], &temp_ring[i], + sizeof(struct igb_ring)); + } + + adapter->rx_ring_count = new_rx_count; + } +err_setup: + igb_up(adapter); + vfree(temp_ring); +clear_reset: + clear_bit(__IGB_RESETTING, &adapter->state); + return err; +} + +/* ethtool register test data */ +struct igb_reg_test { + u16 reg; + u16 reg_offset; + u16 array_len; + u16 test_type; + u32 mask; + u32 write; +}; + +/* In the hardware, registers are laid out either singly, in arrays + * spaced 0x100 bytes apart, or in contiguous tables. We assume + * most tests take place on arrays or single registers (handled + * as a single-element array) and special-case the tables. + * Table tests are always pattern tests. + * + * We also make provision for some required setup steps by specifying + * registers to be written without any read-back testing. + */ + +#define PATTERN_TEST 1 +#define SET_READ_TEST 2 +#define WRITE_NO_TEST 3 +#define TABLE32_TEST 4 +#define TABLE64_TEST_LO 5 +#define TABLE64_TEST_HI 6 + +/* i210 reg test */ +static struct igb_reg_test reg_test_i210[] = { + { E1000_FCAL, 0x100, 1, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_FCAH, 0x100, 1, PATTERN_TEST, 0x0000FFFF, 0xFFFFFFFF }, + { E1000_FCT, 0x100, 1, PATTERN_TEST, 0x0000FFFF, 0xFFFFFFFF }, + { E1000_RDBAL(0), 0x100, 4, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFFFF }, + { E1000_RDBAH(0), 0x100, 4, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_RDLEN(0), 0x100, 4, PATTERN_TEST, 0x000FFF80, 0x000FFFFF }, + /* RDH is read-only for i210, only test RDT. */ + { E1000_RDT(0), 0x100, 4, PATTERN_TEST, 0x0000FFFF, 0x0000FFFF }, + { E1000_FCRTH, 0x100, 1, PATTERN_TEST, 0x0000FFF0, 0x0000FFF0 }, + { E1000_FCTTV, 0x100, 1, PATTERN_TEST, 0x0000FFFF, 0x0000FFFF }, + { E1000_TIPG, 0x100, 1, PATTERN_TEST, 0x3FFFFFFF, 0x3FFFFFFF }, + { E1000_TDBAL(0), 0x100, 4, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFFFF }, + { E1000_TDBAH(0), 0x100, 4, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_TDLEN(0), 0x100, 4, PATTERN_TEST, 0x000FFF80, 0x000FFFFF }, + { E1000_TDT(0), 0x100, 4, PATTERN_TEST, 0x0000FFFF, 0x0000FFFF }, + { E1000_RCTL, 0x100, 1, SET_READ_TEST, 0xFFFFFFFF, 0x00000000 }, + { E1000_RCTL, 0x100, 1, SET_READ_TEST, 0x04CFB0FE, 0x003FFFFB }, + { E1000_RCTL, 0x100, 1, SET_READ_TEST, 0x04CFB0FE, 0xFFFFFFFF }, + { E1000_TCTL, 0x100, 1, SET_READ_TEST, 0xFFFFFFFF, 0x00000000 }, + { E1000_RA, 0, 16, TABLE64_TEST_LO, + 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_RA, 0, 16, TABLE64_TEST_HI, + 0x900FFFFF, 0xFFFFFFFF }, + { E1000_MTA, 0, 128, TABLE32_TEST, + 0xFFFFFFFF, 0xFFFFFFFF }, + { 0, 0, 0, 0, 0 } +}; + +/* i350 reg test */ +static struct igb_reg_test reg_test_i350[] = { + { E1000_FCAL, 0x100, 1, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_FCAH, 0x100, 1, PATTERN_TEST, 0x0000FFFF, 0xFFFFFFFF }, + { E1000_FCT, 0x100, 1, PATTERN_TEST, 0x0000FFFF, 0xFFFFFFFF }, + { E1000_VET, 0x100, 1, PATTERN_TEST, 0xFFFF0000, 0xFFFF0000 }, + { E1000_RDBAL(0), 0x100, 4, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFFFF }, + { E1000_RDBAH(0), 0x100, 4, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_RDLEN(0), 0x100, 4, PATTERN_TEST, 0x000FFF80, 0x000FFFFF }, + { E1000_RDBAL(4), 0x40, 4, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFFFF }, + { E1000_RDBAH(4), 0x40, 4, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_RDLEN(4), 0x40, 4, PATTERN_TEST, 0x000FFF80, 0x000FFFFF }, + /* RDH is read-only for i350, only test RDT. */ + { E1000_RDT(0), 0x100, 4, PATTERN_TEST, 0x0000FFFF, 0x0000FFFF }, + { E1000_RDT(4), 0x40, 4, PATTERN_TEST, 0x0000FFFF, 0x0000FFFF }, + { E1000_FCRTH, 0x100, 1, PATTERN_TEST, 0x0000FFF0, 0x0000FFF0 }, + { E1000_FCTTV, 0x100, 1, PATTERN_TEST, 0x0000FFFF, 0x0000FFFF }, + { E1000_TIPG, 0x100, 1, PATTERN_TEST, 0x3FFFFFFF, 0x3FFFFFFF }, + { E1000_TDBAL(0), 0x100, 4, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFFFF }, + { E1000_TDBAH(0), 0x100, 4, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_TDLEN(0), 0x100, 4, PATTERN_TEST, 0x000FFF80, 0x000FFFFF }, + { E1000_TDBAL(4), 0x40, 4, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFFFF }, + { E1000_TDBAH(4), 0x40, 4, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_TDLEN(4), 0x40, 4, PATTERN_TEST, 0x000FFF80, 0x000FFFFF }, + { E1000_TDT(0), 0x100, 4, PATTERN_TEST, 0x0000FFFF, 0x0000FFFF }, + { E1000_TDT(4), 0x40, 4, PATTERN_TEST, 0x0000FFFF, 0x0000FFFF }, + { E1000_RCTL, 0x100, 1, SET_READ_TEST, 0xFFFFFFFF, 0x00000000 }, + { E1000_RCTL, 0x100, 1, SET_READ_TEST, 0x04CFB0FE, 0x003FFFFB }, + { E1000_RCTL, 0x100, 1, SET_READ_TEST, 0x04CFB0FE, 0xFFFFFFFF }, + { E1000_TCTL, 0x100, 1, SET_READ_TEST, 0xFFFFFFFF, 0x00000000 }, + { E1000_RA, 0, 16, TABLE64_TEST_LO, + 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_RA, 0, 16, TABLE64_TEST_HI, + 0xC3FFFFFF, 0xFFFFFFFF }, + { E1000_RA2, 0, 16, TABLE64_TEST_LO, + 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_RA2, 0, 16, TABLE64_TEST_HI, + 0xC3FFFFFF, 0xFFFFFFFF }, + { E1000_MTA, 0, 128, TABLE32_TEST, + 0xFFFFFFFF, 0xFFFFFFFF }, + { 0, 0, 0, 0 } +}; + +/* 82580 reg test */ +static struct igb_reg_test reg_test_82580[] = { + { E1000_FCAL, 0x100, 1, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_FCAH, 0x100, 1, PATTERN_TEST, 0x0000FFFF, 0xFFFFFFFF }, + { E1000_FCT, 0x100, 1, PATTERN_TEST, 0x0000FFFF, 0xFFFFFFFF }, + { E1000_VET, 0x100, 1, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_RDBAL(0), 0x100, 4, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFFFF }, + { E1000_RDBAH(0), 0x100, 4, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_RDLEN(0), 0x100, 4, PATTERN_TEST, 0x000FFFF0, 0x000FFFFF }, + { E1000_RDBAL(4), 0x40, 4, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFFFF }, + { E1000_RDBAH(4), 0x40, 4, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_RDLEN(4), 0x40, 4, PATTERN_TEST, 0x000FFFF0, 0x000FFFFF }, + /* RDH is read-only for 82580, only test RDT. */ + { E1000_RDT(0), 0x100, 4, PATTERN_TEST, 0x0000FFFF, 0x0000FFFF }, + { E1000_RDT(4), 0x40, 4, PATTERN_TEST, 0x0000FFFF, 0x0000FFFF }, + { E1000_FCRTH, 0x100, 1, PATTERN_TEST, 0x0000FFF0, 0x0000FFF0 }, + { E1000_FCTTV, 0x100, 1, PATTERN_TEST, 0x0000FFFF, 0x0000FFFF }, + { E1000_TIPG, 0x100, 1, PATTERN_TEST, 0x3FFFFFFF, 0x3FFFFFFF }, + { E1000_TDBAL(0), 0x100, 4, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFFFF }, + { E1000_TDBAH(0), 0x100, 4, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_TDLEN(0), 0x100, 4, PATTERN_TEST, 0x000FFFF0, 0x000FFFFF }, + { E1000_TDBAL(4), 0x40, 4, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFFFF }, + { E1000_TDBAH(4), 0x40, 4, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_TDLEN(4), 0x40, 4, PATTERN_TEST, 0x000FFFF0, 0x000FFFFF }, + { E1000_TDT(0), 0x100, 4, PATTERN_TEST, 0x0000FFFF, 0x0000FFFF }, + { E1000_TDT(4), 0x40, 4, PATTERN_TEST, 0x0000FFFF, 0x0000FFFF }, + { E1000_RCTL, 0x100, 1, SET_READ_TEST, 0xFFFFFFFF, 0x00000000 }, + { E1000_RCTL, 0x100, 1, SET_READ_TEST, 0x04CFB0FE, 0x003FFFFB }, + { E1000_RCTL, 0x100, 1, SET_READ_TEST, 0x04CFB0FE, 0xFFFFFFFF }, + { E1000_TCTL, 0x100, 1, SET_READ_TEST, 0xFFFFFFFF, 0x00000000 }, + { E1000_RA, 0, 16, TABLE64_TEST_LO, + 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_RA, 0, 16, TABLE64_TEST_HI, + 0x83FFFFFF, 0xFFFFFFFF }, + { E1000_RA2, 0, 8, TABLE64_TEST_LO, + 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_RA2, 0, 8, TABLE64_TEST_HI, + 0x83FFFFFF, 0xFFFFFFFF }, + { E1000_MTA, 0, 128, TABLE32_TEST, + 0xFFFFFFFF, 0xFFFFFFFF }, + { 0, 0, 0, 0 } +}; + +/* 82576 reg test */ +static struct igb_reg_test reg_test_82576[] = { + { E1000_FCAL, 0x100, 1, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_FCAH, 0x100, 1, PATTERN_TEST, 0x0000FFFF, 0xFFFFFFFF }, + { E1000_FCT, 0x100, 1, PATTERN_TEST, 0x0000FFFF, 0xFFFFFFFF }, + { E1000_VET, 0x100, 1, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_RDBAL(0), 0x100, 4, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFFFF }, + { E1000_RDBAH(0), 0x100, 4, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_RDLEN(0), 0x100, 4, PATTERN_TEST, 0x000FFFF0, 0x000FFFFF }, + { E1000_RDBAL(4), 0x40, 12, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFFFF }, + { E1000_RDBAH(4), 0x40, 12, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_RDLEN(4), 0x40, 12, PATTERN_TEST, 0x000FFFF0, 0x000FFFFF }, + /* Enable all RX queues before testing. */ + { E1000_RXDCTL(0), 0x100, 4, WRITE_NO_TEST, 0, + E1000_RXDCTL_QUEUE_ENABLE }, + { E1000_RXDCTL(4), 0x40, 12, WRITE_NO_TEST, 0, + E1000_RXDCTL_QUEUE_ENABLE }, + /* RDH is read-only for 82576, only test RDT. */ + { E1000_RDT(0), 0x100, 4, PATTERN_TEST, 0x0000FFFF, 0x0000FFFF }, + { E1000_RDT(4), 0x40, 12, PATTERN_TEST, 0x0000FFFF, 0x0000FFFF }, + { E1000_RXDCTL(0), 0x100, 4, WRITE_NO_TEST, 0, 0 }, + { E1000_RXDCTL(4), 0x40, 12, WRITE_NO_TEST, 0, 0 }, + { E1000_FCRTH, 0x100, 1, PATTERN_TEST, 0x0000FFF0, 0x0000FFF0 }, + { E1000_FCTTV, 0x100, 1, PATTERN_TEST, 0x0000FFFF, 0x0000FFFF }, + { E1000_TIPG, 0x100, 1, PATTERN_TEST, 0x3FFFFFFF, 0x3FFFFFFF }, + { E1000_TDBAL(0), 0x100, 4, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFFFF }, + { E1000_TDBAH(0), 0x100, 4, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_TDLEN(0), 0x100, 4, PATTERN_TEST, 0x000FFFF0, 0x000FFFFF }, + { E1000_TDBAL(4), 0x40, 12, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFFFF }, + { E1000_TDBAH(4), 0x40, 12, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_TDLEN(4), 0x40, 12, PATTERN_TEST, 0x000FFFF0, 0x000FFFFF }, + { E1000_RCTL, 0x100, 1, SET_READ_TEST, 0xFFFFFFFF, 0x00000000 }, + { E1000_RCTL, 0x100, 1, SET_READ_TEST, 0x04CFB0FE, 0x003FFFFB }, + { E1000_RCTL, 0x100, 1, SET_READ_TEST, 0x04CFB0FE, 0xFFFFFFFF }, + { E1000_TCTL, 0x100, 1, SET_READ_TEST, 0xFFFFFFFF, 0x00000000 }, + { E1000_RA, 0, 16, TABLE64_TEST_LO, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_RA, 0, 16, TABLE64_TEST_HI, 0x83FFFFFF, 0xFFFFFFFF }, + { E1000_RA2, 0, 8, TABLE64_TEST_LO, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_RA2, 0, 8, TABLE64_TEST_HI, 0x83FFFFFF, 0xFFFFFFFF }, + { E1000_MTA, 0, 128, TABLE32_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { 0, 0, 0, 0 } +}; + +/* 82575 register test */ +static struct igb_reg_test reg_test_82575[] = { + { E1000_FCAL, 0x100, 1, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_FCAH, 0x100, 1, PATTERN_TEST, 0x0000FFFF, 0xFFFFFFFF }, + { E1000_FCT, 0x100, 1, PATTERN_TEST, 0x0000FFFF, 0xFFFFFFFF }, + { E1000_VET, 0x100, 1, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_RDBAL(0), 0x100, 4, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFFFF }, + { E1000_RDBAH(0), 0x100, 4, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_RDLEN(0), 0x100, 4, PATTERN_TEST, 0x000FFF80, 0x000FFFFF }, + /* Enable all four RX queues before testing. */ + { E1000_RXDCTL(0), 0x100, 4, WRITE_NO_TEST, 0, + E1000_RXDCTL_QUEUE_ENABLE }, + /* RDH is read-only for 82575, only test RDT. */ + { E1000_RDT(0), 0x100, 4, PATTERN_TEST, 0x0000FFFF, 0x0000FFFF }, + { E1000_RXDCTL(0), 0x100, 4, WRITE_NO_TEST, 0, 0 }, + { E1000_FCRTH, 0x100, 1, PATTERN_TEST, 0x0000FFF0, 0x0000FFF0 }, + { E1000_FCTTV, 0x100, 1, PATTERN_TEST, 0x0000FFFF, 0x0000FFFF }, + { E1000_TIPG, 0x100, 1, PATTERN_TEST, 0x3FFFFFFF, 0x3FFFFFFF }, + { E1000_TDBAL(0), 0x100, 4, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFFFF }, + { E1000_TDBAH(0), 0x100, 4, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_TDLEN(0), 0x100, 4, PATTERN_TEST, 0x000FFF80, 0x000FFFFF }, + { E1000_RCTL, 0x100, 1, SET_READ_TEST, 0xFFFFFFFF, 0x00000000 }, + { E1000_RCTL, 0x100, 1, SET_READ_TEST, 0x04CFB3FE, 0x003FFFFB }, + { E1000_RCTL, 0x100, 1, SET_READ_TEST, 0x04CFB3FE, 0xFFFFFFFF }, + { E1000_TCTL, 0x100, 1, SET_READ_TEST, 0xFFFFFFFF, 0x00000000 }, + { E1000_TXCW, 0x100, 1, PATTERN_TEST, 0xC000FFFF, 0x0000FFFF }, + { E1000_RA, 0, 16, TABLE64_TEST_LO, 0xFFFFFFFF, 0xFFFFFFFF }, + { E1000_RA, 0, 16, TABLE64_TEST_HI, 0x800FFFFF, 0xFFFFFFFF }, + { E1000_MTA, 0, 128, TABLE32_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { 0, 0, 0, 0 } +}; + +static bool reg_pattern_test(struct igb_adapter *adapter, u64 *data, + int reg, u32 mask, u32 write) +{ + struct e1000_hw *hw = &adapter->hw; + u32 pat, val; + static const u32 _test[] = { + 0x5A5A5A5A, 0xA5A5A5A5, 0x00000000, 0xFFFFFFFF}; + for (pat = 0; pat < ARRAY_SIZE(_test); pat++) { + wr32(reg, (_test[pat] & write)); + val = rd32(reg) & mask; + if (val != (_test[pat] & write & mask)) { + dev_err(&adapter->pdev->dev, + "pattern test reg %04X failed: got 0x%08X expected 0x%08X\n", + reg, val, (_test[pat] & write & mask)); + *data = reg; + return true; + } + } + + return false; +} + +static bool reg_set_and_check(struct igb_adapter *adapter, u64 *data, + int reg, u32 mask, u32 write) +{ + struct e1000_hw *hw = &adapter->hw; + u32 val; + + wr32(reg, write & mask); + val = rd32(reg); + if ((write & mask) != (val & mask)) { + dev_err(&adapter->pdev->dev, + "set/check reg %04X test failed: got 0x%08X expected 0x%08X\n", + reg, (val & mask), (write & mask)); + *data = reg; + return true; + } + + return false; +} + +#define REG_PATTERN_TEST(reg, mask, write) \ + do { \ + if (reg_pattern_test(adapter, data, reg, mask, write)) \ + return 1; \ + } while (0) + +#define REG_SET_AND_CHECK(reg, mask, write) \ + do { \ + if (reg_set_and_check(adapter, data, reg, mask, write)) \ + return 1; \ + } while (0) + +static int igb_reg_test(struct igb_adapter *adapter, u64 *data) +{ + struct e1000_hw *hw = &adapter->hw; + struct igb_reg_test *test; + u32 value, before, after; + u32 i, toggle; + + switch (adapter->hw.mac.type) { + case e1000_i350: + case e1000_i354: + test = reg_test_i350; + toggle = 0x7FEFF3FF; + break; + case e1000_i210: + case e1000_i211: + test = reg_test_i210; + toggle = 0x7FEFF3FF; + break; + case e1000_82580: + test = reg_test_82580; + toggle = 0x7FEFF3FF; + break; + case e1000_82576: + test = reg_test_82576; + toggle = 0x7FFFF3FF; + break; + default: + test = reg_test_82575; + toggle = 0x7FFFF3FF; + break; + } + + /* Because the status register is such a special case, + * we handle it separately from the rest of the register + * tests. Some bits are read-only, some toggle, and some + * are writable on newer MACs. + */ + before = rd32(E1000_STATUS); + value = (rd32(E1000_STATUS) & toggle); + wr32(E1000_STATUS, toggle); + after = rd32(E1000_STATUS) & toggle; + if (value != after) { + dev_err(&adapter->pdev->dev, + "failed STATUS register test got: 0x%08X expected: 0x%08X\n", + after, value); + *data = 1; + return 1; + } + /* restore previous status */ + wr32(E1000_STATUS, before); + + /* Perform the remainder of the register test, looping through + * the test table until we either fail or reach the null entry. + */ + while (test->reg) { + for (i = 0; i < test->array_len; i++) { + switch (test->test_type) { + case PATTERN_TEST: + REG_PATTERN_TEST(test->reg + + (i * test->reg_offset), + test->mask, + test->write); + break; + case SET_READ_TEST: + REG_SET_AND_CHECK(test->reg + + (i * test->reg_offset), + test->mask, + test->write); + break; + case WRITE_NO_TEST: + writel(test->write, + (adapter->hw.hw_addr + test->reg) + + (i * test->reg_offset)); + break; + case TABLE32_TEST: + REG_PATTERN_TEST(test->reg + (i * 4), + test->mask, + test->write); + break; + case TABLE64_TEST_LO: + REG_PATTERN_TEST(test->reg + (i * 8), + test->mask, + test->write); + break; + case TABLE64_TEST_HI: + REG_PATTERN_TEST((test->reg + 4) + (i * 8), + test->mask, + test->write); + break; + } + } + test++; + } + + *data = 0; + return 0; +} + +static int igb_eeprom_test(struct igb_adapter *adapter, u64 *data) +{ + struct e1000_hw *hw = &adapter->hw; + + *data = 0; + + /* Validate eeprom on all parts but flashless */ + switch (hw->mac.type) { + case e1000_i210: + case e1000_i211: + if (igb_get_flash_presence_i210(hw)) { + if (adapter->hw.nvm.ops.validate(&adapter->hw) < 0) + *data = 2; + } + break; + default: + if (adapter->hw.nvm.ops.validate(&adapter->hw) < 0) + *data = 2; + break; + } + + return *data; +} + +static irqreturn_t igb_test_intr(int irq, void *data) +{ + struct igb_adapter *adapter = (struct igb_adapter *) data; + struct e1000_hw *hw = &adapter->hw; + + adapter->test_icr |= rd32(E1000_ICR); + + return IRQ_HANDLED; +} + +static int igb_intr_test(struct igb_adapter *adapter, u64 *data) +{ + struct e1000_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; + u32 mask, ics_mask, i = 0, shared_int = true; + u32 irq = adapter->pdev->irq; + + *data = 0; + + /* Hook up test interrupt handler just for this test */ + if (adapter->flags & IGB_FLAG_HAS_MSIX) { + if (request_irq(adapter->msix_entries[0].vector, + igb_test_intr, 0, netdev->name, adapter)) { + *data = 1; + return -1; + } + wr32(E1000_IVAR_MISC, E1000_IVAR_VALID << 8); + wr32(E1000_EIMS, BIT(0)); + } else if (adapter->flags & IGB_FLAG_HAS_MSI) { + shared_int = false; + if (request_irq(irq, + igb_test_intr, 0, netdev->name, adapter)) { + *data = 1; + return -1; + } + } else if (!request_irq(irq, igb_test_intr, IRQF_PROBE_SHARED, + netdev->name, adapter)) { + shared_int = false; + } else if (request_irq(irq, igb_test_intr, IRQF_SHARED, + netdev->name, adapter)) { + *data = 1; + return -1; + } + dev_info(&adapter->pdev->dev, "testing %s interrupt\n", + (shared_int ? "shared" : "unshared")); + + /* Disable all the interrupts */ + wr32(E1000_IMC, ~0); + wrfl(); + usleep_range(10000, 11000); + + /* Define all writable bits for ICS */ + switch (hw->mac.type) { + case e1000_82575: + ics_mask = 0x37F47EDD; + break; + case e1000_82576: + ics_mask = 0x77D4FBFD; + break; + case e1000_82580: + ics_mask = 0x77DCFED5; + break; + case e1000_i350: + case e1000_i354: + case e1000_i210: + case e1000_i211: + ics_mask = 0x77DCFED5; + break; + default: + ics_mask = 0x7FFFFFFF; + break; + } + + /* Test each interrupt */ + for (; i < 31; i++) { + /* Interrupt to test */ + mask = BIT(i); + + if (!(mask & ics_mask)) + continue; + + if (!shared_int) { + /* Disable the interrupt to be reported in + * the cause register and then force the same + * interrupt and see if one gets posted. If + * an interrupt was posted to the bus, the + * test failed. + */ + adapter->test_icr = 0; + + /* Flush any pending interrupts */ + wr32(E1000_ICR, ~0); + + wr32(E1000_IMC, mask); + wr32(E1000_ICS, mask); + wrfl(); + usleep_range(10000, 11000); + + if (adapter->test_icr & mask) { + *data = 3; + break; + } + } + + /* Enable the interrupt to be reported in + * the cause register and then force the same + * interrupt and see if one gets posted. If + * an interrupt was not posted to the bus, the + * test failed. + */ + adapter->test_icr = 0; + + /* Flush any pending interrupts */ + wr32(E1000_ICR, ~0); + + wr32(E1000_IMS, mask); + wr32(E1000_ICS, mask); + wrfl(); + usleep_range(10000, 11000); + + if (!(adapter->test_icr & mask)) { + *data = 4; + break; + } + + if (!shared_int) { + /* Disable the other interrupts to be reported in + * the cause register and then force the other + * interrupts and see if any get posted. If + * an interrupt was posted to the bus, the + * test failed. + */ + adapter->test_icr = 0; + + /* Flush any pending interrupts */ + wr32(E1000_ICR, ~0); + + wr32(E1000_IMC, ~mask); + wr32(E1000_ICS, ~mask); + wrfl(); + usleep_range(10000, 11000); + + if (adapter->test_icr & mask) { + *data = 5; + break; + } + } + } + + /* Disable all the interrupts */ + wr32(E1000_IMC, ~0); + wrfl(); + usleep_range(10000, 11000); + + /* Unhook test interrupt handler */ + if (adapter->flags & IGB_FLAG_HAS_MSIX) + free_irq(adapter->msix_entries[0].vector, adapter); + else + free_irq(irq, adapter); + + return *data; +} + +static void igb_free_desc_rings(struct igb_adapter *adapter) +{ + igb_free_tx_resources(&adapter->test_tx_ring); + igb_free_rx_resources(&adapter->test_rx_ring); +} + +static int igb_setup_desc_rings(struct igb_adapter *adapter) +{ + struct igb_ring *tx_ring = &adapter->test_tx_ring; + struct igb_ring *rx_ring = &adapter->test_rx_ring; + struct e1000_hw *hw = &adapter->hw; + int ret_val; + + /* Setup Tx descriptor ring and Tx buffers */ + tx_ring->count = IGB_DEFAULT_TXD; + tx_ring->dev = &adapter->pdev->dev; + tx_ring->netdev = adapter->netdev; + tx_ring->reg_idx = adapter->vfs_allocated_count; + + if (igb_setup_tx_resources(tx_ring)) { + ret_val = 1; + goto err_nomem; + } + + igb_setup_tctl(adapter); + igb_configure_tx_ring(adapter, tx_ring); + + /* Setup Rx descriptor ring and Rx buffers */ + rx_ring->count = IGB_DEFAULT_RXD; + rx_ring->dev = &adapter->pdev->dev; + rx_ring->netdev = adapter->netdev; + rx_ring->reg_idx = adapter->vfs_allocated_count; + + if (igb_setup_rx_resources(rx_ring)) { + ret_val = 3; + goto err_nomem; + } + + /* set the default queue to queue 0 of PF */ + wr32(E1000_MRQC, adapter->vfs_allocated_count << 3); + + /* enable receive ring */ + igb_setup_rctl(adapter); + igb_configure_rx_ring(adapter, rx_ring); + + igb_alloc_rx_buffers(rx_ring, igb_desc_unused(rx_ring)); + + return 0; + +err_nomem: + igb_free_desc_rings(adapter); + return ret_val; +} + +static void igb_phy_disable_receiver(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + + /* Write out to PHY registers 29 and 30 to disable the Receiver. */ + igb_write_phy_reg(hw, 29, 0x001F); + igb_write_phy_reg(hw, 30, 0x8FFC); + igb_write_phy_reg(hw, 29, 0x001A); + igb_write_phy_reg(hw, 30, 0x8FF0); +} + +static int igb_integrated_phy_loopback(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 ctrl_reg = 0; + + hw->mac.autoneg = false; + + if (hw->phy.type == e1000_phy_m88) { + if (hw->phy.id != I210_I_PHY_ID) { + /* Auto-MDI/MDIX Off */ + igb_write_phy_reg(hw, M88E1000_PHY_SPEC_CTRL, 0x0808); + /* reset to update Auto-MDI/MDIX */ + igb_write_phy_reg(hw, PHY_CONTROL, 0x9140); + /* autoneg off */ + igb_write_phy_reg(hw, PHY_CONTROL, 0x8140); + } else { + /* force 1000, set loopback */ + igb_write_phy_reg(hw, I347AT4_PAGE_SELECT, 0); + igb_write_phy_reg(hw, PHY_CONTROL, 0x4140); + } + } else if (hw->phy.type == e1000_phy_82580) { + /* enable MII loopback */ + igb_write_phy_reg(hw, I82580_PHY_LBK_CTRL, 0x8041); + } + + /* add small delay to avoid loopback test failure */ + msleep(50); + + /* force 1000, set loopback */ + igb_write_phy_reg(hw, PHY_CONTROL, 0x4140); + + /* Now set up the MAC to the same speed/duplex as the PHY. */ + ctrl_reg = rd32(E1000_CTRL); + ctrl_reg &= ~E1000_CTRL_SPD_SEL; /* Clear the speed sel bits */ + ctrl_reg |= (E1000_CTRL_FRCSPD | /* Set the Force Speed Bit */ + E1000_CTRL_FRCDPX | /* Set the Force Duplex Bit */ + E1000_CTRL_SPD_1000 |/* Force Speed to 1000 */ + E1000_CTRL_FD | /* Force Duplex to FULL */ + E1000_CTRL_SLU); /* Set link up enable bit */ + + if (hw->phy.type == e1000_phy_m88) + ctrl_reg |= E1000_CTRL_ILOS; /* Invert Loss of Signal */ + + wr32(E1000_CTRL, ctrl_reg); + + /* Disable the receiver on the PHY so when a cable is plugged in, the + * PHY does not begin to autoneg when a cable is reconnected to the NIC. + */ + if (hw->phy.type == e1000_phy_m88) + igb_phy_disable_receiver(adapter); + + msleep(500); + return 0; +} + +static int igb_set_phy_loopback(struct igb_adapter *adapter) +{ + return igb_integrated_phy_loopback(adapter); +} + +static int igb_setup_loopback_test(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 reg; + + reg = rd32(E1000_CTRL_EXT); + + /* use CTRL_EXT to identify link type as SGMII can appear as copper */ + if (reg & E1000_CTRL_EXT_LINK_MODE_MASK) { + if ((hw->device_id == E1000_DEV_ID_DH89XXCC_SGMII) || + (hw->device_id == E1000_DEV_ID_DH89XXCC_SERDES) || + (hw->device_id == E1000_DEV_ID_DH89XXCC_BACKPLANE) || + (hw->device_id == E1000_DEV_ID_DH89XXCC_SFP) || + (hw->device_id == E1000_DEV_ID_I354_SGMII) || + (hw->device_id == E1000_DEV_ID_I354_BACKPLANE_2_5GBPS)) { + /* Enable DH89xxCC MPHY for near end loopback */ + reg = rd32(E1000_MPHY_ADDR_CTL); + reg = (reg & E1000_MPHY_ADDR_CTL_OFFSET_MASK) | + E1000_MPHY_PCS_CLK_REG_OFFSET; + wr32(E1000_MPHY_ADDR_CTL, reg); + + reg = rd32(E1000_MPHY_DATA); + reg |= E1000_MPHY_PCS_CLK_REG_DIGINELBEN; + wr32(E1000_MPHY_DATA, reg); + } + + reg = rd32(E1000_RCTL); + reg |= E1000_RCTL_LBM_TCVR; + wr32(E1000_RCTL, reg); + + wr32(E1000_SCTL, E1000_ENABLE_SERDES_LOOPBACK); + + reg = rd32(E1000_CTRL); + reg &= ~(E1000_CTRL_RFCE | + E1000_CTRL_TFCE | + E1000_CTRL_LRST); + reg |= E1000_CTRL_SLU | + E1000_CTRL_FD; + wr32(E1000_CTRL, reg); + + /* Unset switch control to serdes energy detect */ + reg = rd32(E1000_CONNSW); + reg &= ~E1000_CONNSW_ENRGSRC; + wr32(E1000_CONNSW, reg); + + /* Unset sigdetect for SERDES loopback on + * 82580 and newer devices. + */ + if (hw->mac.type >= e1000_82580) { + reg = rd32(E1000_PCS_CFG0); + reg |= E1000_PCS_CFG_IGN_SD; + wr32(E1000_PCS_CFG0, reg); + } + + /* Set PCS register for forced speed */ + reg = rd32(E1000_PCS_LCTL); + reg &= ~E1000_PCS_LCTL_AN_ENABLE; /* Disable Autoneg*/ + reg |= E1000_PCS_LCTL_FLV_LINK_UP | /* Force link up */ + E1000_PCS_LCTL_FSV_1000 | /* Force 1000 */ + E1000_PCS_LCTL_FDV_FULL | /* SerDes Full duplex */ + E1000_PCS_LCTL_FSD | /* Force Speed */ + E1000_PCS_LCTL_FORCE_LINK; /* Force Link */ + wr32(E1000_PCS_LCTL, reg); + + return 0; + } + + return igb_set_phy_loopback(adapter); +} + +static void igb_loopback_cleanup(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 rctl; + u16 phy_reg; + + if ((hw->device_id == E1000_DEV_ID_DH89XXCC_SGMII) || + (hw->device_id == E1000_DEV_ID_DH89XXCC_SERDES) || + (hw->device_id == E1000_DEV_ID_DH89XXCC_BACKPLANE) || + (hw->device_id == E1000_DEV_ID_DH89XXCC_SFP) || + (hw->device_id == E1000_DEV_ID_I354_SGMII)) { + u32 reg; + + /* Disable near end loopback on DH89xxCC */ + reg = rd32(E1000_MPHY_ADDR_CTL); + reg = (reg & E1000_MPHY_ADDR_CTL_OFFSET_MASK) | + E1000_MPHY_PCS_CLK_REG_OFFSET; + wr32(E1000_MPHY_ADDR_CTL, reg); + + reg = rd32(E1000_MPHY_DATA); + reg &= ~E1000_MPHY_PCS_CLK_REG_DIGINELBEN; + wr32(E1000_MPHY_DATA, reg); + } + + rctl = rd32(E1000_RCTL); + rctl &= ~(E1000_RCTL_LBM_TCVR | E1000_RCTL_LBM_MAC); + wr32(E1000_RCTL, rctl); + + hw->mac.autoneg = true; + igb_read_phy_reg(hw, PHY_CONTROL, &phy_reg); + if (phy_reg & MII_CR_LOOPBACK) { + phy_reg &= ~MII_CR_LOOPBACK; + igb_write_phy_reg(hw, PHY_CONTROL, phy_reg); + igb_phy_sw_reset(hw); + } +} + +static void igb_create_lbtest_frame(struct sk_buff *skb, + unsigned int frame_size) +{ + memset(skb->data, 0xFF, frame_size); + frame_size /= 2; + memset(&skb->data[frame_size], 0xAA, frame_size - 1); + skb->data[frame_size + 10] = 0xBE; + skb->data[frame_size + 12] = 0xAF; +} + +static int igb_check_lbtest_frame(struct igb_rx_buffer *rx_buffer, + unsigned int frame_size) +{ + unsigned char *data; + bool match = true; + + frame_size >>= 1; + + data = kmap_local_page(rx_buffer->page); + + if (data[3] != 0xFF || + data[frame_size + 10] != 0xBE || + data[frame_size + 12] != 0xAF) + match = false; + + kunmap_local(data); + + return match; +} + +static int igb_clean_test_rings(struct igb_ring *rx_ring, + struct igb_ring *tx_ring, + unsigned int size) +{ + union e1000_adv_rx_desc *rx_desc; + struct igb_rx_buffer *rx_buffer_info; + struct igb_tx_buffer *tx_buffer_info; + u16 rx_ntc, tx_ntc, count = 0; + + /* initialize next to clean and descriptor values */ + rx_ntc = rx_ring->next_to_clean; + tx_ntc = tx_ring->next_to_clean; + rx_desc = IGB_RX_DESC(rx_ring, rx_ntc); + + while (rx_desc->wb.upper.length) { + /* check Rx buffer */ + rx_buffer_info = &rx_ring->rx_buffer_info[rx_ntc]; + + /* sync Rx buffer for CPU read */ + dma_sync_single_for_cpu(rx_ring->dev, + rx_buffer_info->dma, + size, + DMA_FROM_DEVICE); + + /* verify contents of skb */ + if (igb_check_lbtest_frame(rx_buffer_info, size)) + count++; + + /* sync Rx buffer for device write */ + dma_sync_single_for_device(rx_ring->dev, + rx_buffer_info->dma, + size, + DMA_FROM_DEVICE); + + /* unmap buffer on Tx side */ + tx_buffer_info = &tx_ring->tx_buffer_info[tx_ntc]; + + /* Free all the Tx ring sk_buffs */ + dev_kfree_skb_any(tx_buffer_info->skb); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer_info, dma), + dma_unmap_len(tx_buffer_info, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer_info, len, 0); + + /* increment Rx/Tx next to clean counters */ + rx_ntc++; + if (rx_ntc == rx_ring->count) + rx_ntc = 0; + tx_ntc++; + if (tx_ntc == tx_ring->count) + tx_ntc = 0; + + /* fetch next descriptor */ + rx_desc = IGB_RX_DESC(rx_ring, rx_ntc); + } + + netdev_tx_reset_queue(txring_txq(tx_ring)); + + /* re-map buffers to ring, store next to clean values */ + igb_alloc_rx_buffers(rx_ring, count); + rx_ring->next_to_clean = rx_ntc; + tx_ring->next_to_clean = tx_ntc; + + return count; +} + +static int igb_run_loopback_test(struct igb_adapter *adapter) +{ + struct igb_ring *tx_ring = &adapter->test_tx_ring; + struct igb_ring *rx_ring = &adapter->test_rx_ring; + u16 i, j, lc, good_cnt; + int ret_val = 0; + unsigned int size = IGB_RX_HDR_LEN; + netdev_tx_t tx_ret_val; + struct sk_buff *skb; + + /* allocate test skb */ + skb = alloc_skb(size, GFP_KERNEL); + if (!skb) + return 11; + + /* place data into test skb */ + igb_create_lbtest_frame(skb, size); + skb_put(skb, size); + + /* Calculate the loop count based on the largest descriptor ring + * The idea is to wrap the largest ring a number of times using 64 + * send/receive pairs during each loop + */ + + if (rx_ring->count <= tx_ring->count) + lc = ((tx_ring->count / 64) * 2) + 1; + else + lc = ((rx_ring->count / 64) * 2) + 1; + + for (j = 0; j <= lc; j++) { /* loop count loop */ + /* reset count of good packets */ + good_cnt = 0; + + /* place 64 packets on the transmit queue*/ + for (i = 0; i < 64; i++) { + skb_get(skb); + tx_ret_val = igb_xmit_frame_ring(skb, tx_ring); + if (tx_ret_val == NETDEV_TX_OK) + good_cnt++; + } + + if (good_cnt != 64) { + ret_val = 12; + break; + } + + /* allow 200 milliseconds for packets to go from Tx to Rx */ + msleep(200); + + good_cnt = igb_clean_test_rings(rx_ring, tx_ring, size); + if (good_cnt != 64) { + ret_val = 13; + break; + } + } /* end loop count loop */ + + /* free the original skb */ + kfree_skb(skb); + + return ret_val; +} + +static int igb_loopback_test(struct igb_adapter *adapter, u64 *data) +{ + /* PHY loopback cannot be performed if SoL/IDER + * sessions are active + */ + if (igb_check_reset_block(&adapter->hw)) { + dev_err(&adapter->pdev->dev, + "Cannot do PHY loopback test when SoL/IDER is active.\n"); + *data = 0; + goto out; + } + + if (adapter->hw.mac.type == e1000_i354) { + dev_info(&adapter->pdev->dev, + "Loopback test not supported on i354.\n"); + *data = 0; + goto out; + } + *data = igb_setup_desc_rings(adapter); + if (*data) + goto out; + *data = igb_setup_loopback_test(adapter); + if (*data) + goto err_loopback; + *data = igb_run_loopback_test(adapter); + igb_loopback_cleanup(adapter); + +err_loopback: + igb_free_desc_rings(adapter); +out: + return *data; +} + +static int igb_link_test(struct igb_adapter *adapter, u64 *data) +{ + struct e1000_hw *hw = &adapter->hw; + *data = 0; + if (hw->phy.media_type == e1000_media_type_internal_serdes) { + int i = 0; + + hw->mac.serdes_has_link = false; + + /* On some blade server designs, link establishment + * could take as long as 2-3 minutes + */ + do { + hw->mac.ops.check_for_link(&adapter->hw); + if (hw->mac.serdes_has_link) + return *data; + msleep(20); + } while (i++ < 3750); + + *data = 1; + } else { + hw->mac.ops.check_for_link(&adapter->hw); + if (hw->mac.autoneg) + msleep(5000); + + if (!(rd32(E1000_STATUS) & E1000_STATUS_LU)) + *data = 1; + } + return *data; +} + +static void igb_diag_test(struct net_device *netdev, + struct ethtool_test *eth_test, u64 *data) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + u16 autoneg_advertised; + u8 forced_speed_duplex, autoneg; + bool if_running = netif_running(netdev); + + set_bit(__IGB_TESTING, &adapter->state); + + /* can't do offline tests on media switching devices */ + if (adapter->hw.dev_spec._82575.mas_capable) + eth_test->flags &= ~ETH_TEST_FL_OFFLINE; + if (eth_test->flags == ETH_TEST_FL_OFFLINE) { + /* Offline tests */ + + /* save speed, duplex, autoneg settings */ + autoneg_advertised = adapter->hw.phy.autoneg_advertised; + forced_speed_duplex = adapter->hw.mac.forced_speed_duplex; + autoneg = adapter->hw.mac.autoneg; + + dev_info(&adapter->pdev->dev, "offline testing starting\n"); + + /* power up link for link test */ + igb_power_up_link(adapter); + + /* Link test performed before hardware reset so autoneg doesn't + * interfere with test result + */ + if (igb_link_test(adapter, &data[TEST_LINK])) + eth_test->flags |= ETH_TEST_FL_FAILED; + + if (if_running) + /* indicate we're in test mode */ + igb_close(netdev); + else + igb_reset(adapter); + + if (igb_reg_test(adapter, &data[TEST_REG])) + eth_test->flags |= ETH_TEST_FL_FAILED; + + igb_reset(adapter); + if (igb_eeprom_test(adapter, &data[TEST_EEP])) + eth_test->flags |= ETH_TEST_FL_FAILED; + + igb_reset(adapter); + if (igb_intr_test(adapter, &data[TEST_IRQ])) + eth_test->flags |= ETH_TEST_FL_FAILED; + + igb_reset(adapter); + /* power up link for loopback test */ + igb_power_up_link(adapter); + if (igb_loopback_test(adapter, &data[TEST_LOOP])) + eth_test->flags |= ETH_TEST_FL_FAILED; + + /* restore speed, duplex, autoneg settings */ + adapter->hw.phy.autoneg_advertised = autoneg_advertised; + adapter->hw.mac.forced_speed_duplex = forced_speed_duplex; + adapter->hw.mac.autoneg = autoneg; + + /* force this routine to wait until autoneg complete/timeout */ + adapter->hw.phy.autoneg_wait_to_complete = true; + igb_reset(adapter); + adapter->hw.phy.autoneg_wait_to_complete = false; + + clear_bit(__IGB_TESTING, &adapter->state); + if (if_running) + igb_open(netdev); + } else { + dev_info(&adapter->pdev->dev, "online testing starting\n"); + + /* PHY is powered down when interface is down */ + if (if_running && igb_link_test(adapter, &data[TEST_LINK])) + eth_test->flags |= ETH_TEST_FL_FAILED; + else + data[TEST_LINK] = 0; + + /* Online tests aren't run; pass by default */ + data[TEST_REG] = 0; + data[TEST_EEP] = 0; + data[TEST_IRQ] = 0; + data[TEST_LOOP] = 0; + + clear_bit(__IGB_TESTING, &adapter->state); + } + msleep_interruptible(4 * 1000); +} + +static void igb_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + + wol->wolopts = 0; + + if (!(adapter->flags & IGB_FLAG_WOL_SUPPORTED)) + return; + + wol->supported = WAKE_UCAST | WAKE_MCAST | + WAKE_BCAST | WAKE_MAGIC | + WAKE_PHY; + + /* apply any specific unsupported masks here */ + switch (adapter->hw.device_id) { + default: + break; + } + + if (adapter->wol & E1000_WUFC_EX) + wol->wolopts |= WAKE_UCAST; + if (adapter->wol & E1000_WUFC_MC) + wol->wolopts |= WAKE_MCAST; + if (adapter->wol & E1000_WUFC_BC) + wol->wolopts |= WAKE_BCAST; + if (adapter->wol & E1000_WUFC_MAG) + wol->wolopts |= WAKE_MAGIC; + if (adapter->wol & E1000_WUFC_LNKC) + wol->wolopts |= WAKE_PHY; +} + +static int igb_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + + if (wol->wolopts & (WAKE_ARP | WAKE_MAGICSECURE | WAKE_FILTER)) + return -EOPNOTSUPP; + + if (!(adapter->flags & IGB_FLAG_WOL_SUPPORTED)) + return wol->wolopts ? -EOPNOTSUPP : 0; + + /* these settings will always override what we currently have */ + adapter->wol = 0; + + if (wol->wolopts & WAKE_UCAST) + adapter->wol |= E1000_WUFC_EX; + if (wol->wolopts & WAKE_MCAST) + adapter->wol |= E1000_WUFC_MC; + if (wol->wolopts & WAKE_BCAST) + adapter->wol |= E1000_WUFC_BC; + if (wol->wolopts & WAKE_MAGIC) + adapter->wol |= E1000_WUFC_MAG; + if (wol->wolopts & WAKE_PHY) + adapter->wol |= E1000_WUFC_LNKC; + device_set_wakeup_enable(&adapter->pdev->dev, adapter->wol); + + return 0; +} + +/* bit defines for adapter->led_status */ +#define IGB_LED_ON 0 + +static int igb_set_phys_id(struct net_device *netdev, + enum ethtool_phys_id_state state) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + + switch (state) { + case ETHTOOL_ID_ACTIVE: + igb_blink_led(hw); + return 2; + case ETHTOOL_ID_ON: + igb_blink_led(hw); + break; + case ETHTOOL_ID_OFF: + igb_led_off(hw); + break; + case ETHTOOL_ID_INACTIVE: + igb_led_off(hw); + clear_bit(IGB_LED_ON, &adapter->led_status); + igb_cleanup_led(hw); + break; + } + + return 0; +} + +static int igb_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + int i; + + if ((ec->rx_coalesce_usecs > IGB_MAX_ITR_USECS) || + ((ec->rx_coalesce_usecs > 3) && + (ec->rx_coalesce_usecs < IGB_MIN_ITR_USECS)) || + (ec->rx_coalesce_usecs == 2)) + return -EINVAL; + + if ((ec->tx_coalesce_usecs > IGB_MAX_ITR_USECS) || + ((ec->tx_coalesce_usecs > 3) && + (ec->tx_coalesce_usecs < IGB_MIN_ITR_USECS)) || + (ec->tx_coalesce_usecs == 2)) + return -EINVAL; + + if ((adapter->flags & IGB_FLAG_QUEUE_PAIRS) && ec->tx_coalesce_usecs) + return -EINVAL; + + /* If ITR is disabled, disable DMAC */ + if (ec->rx_coalesce_usecs == 0) { + if (adapter->flags & IGB_FLAG_DMAC) + adapter->flags &= ~IGB_FLAG_DMAC; + } + + /* convert to rate of irq's per second */ + if (ec->rx_coalesce_usecs && ec->rx_coalesce_usecs <= 3) + adapter->rx_itr_setting = ec->rx_coalesce_usecs; + else + adapter->rx_itr_setting = ec->rx_coalesce_usecs << 2; + + /* convert to rate of irq's per second */ + if (adapter->flags & IGB_FLAG_QUEUE_PAIRS) + adapter->tx_itr_setting = adapter->rx_itr_setting; + else if (ec->tx_coalesce_usecs && ec->tx_coalesce_usecs <= 3) + adapter->tx_itr_setting = ec->tx_coalesce_usecs; + else + adapter->tx_itr_setting = ec->tx_coalesce_usecs << 2; + + for (i = 0; i < adapter->num_q_vectors; i++) { + struct igb_q_vector *q_vector = adapter->q_vector[i]; + q_vector->tx.work_limit = adapter->tx_work_limit; + if (q_vector->rx.ring) + q_vector->itr_val = adapter->rx_itr_setting; + else + q_vector->itr_val = adapter->tx_itr_setting; + if (q_vector->itr_val && q_vector->itr_val <= 3) + q_vector->itr_val = IGB_START_ITR; + q_vector->set_itr = 1; + } + + return 0; +} + +static int igb_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + + if (adapter->rx_itr_setting <= 3) + ec->rx_coalesce_usecs = adapter->rx_itr_setting; + else + ec->rx_coalesce_usecs = adapter->rx_itr_setting >> 2; + + if (!(adapter->flags & IGB_FLAG_QUEUE_PAIRS)) { + if (adapter->tx_itr_setting <= 3) + ec->tx_coalesce_usecs = adapter->tx_itr_setting; + else + ec->tx_coalesce_usecs = adapter->tx_itr_setting >> 2; + } + + return 0; +} + +static int igb_nway_reset(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + if (netif_running(netdev)) + igb_reinit_locked(adapter); + return 0; +} + +static int igb_get_sset_count(struct net_device *netdev, int sset) +{ + switch (sset) { + case ETH_SS_STATS: + return IGB_STATS_LEN; + case ETH_SS_TEST: + return IGB_TEST_LEN; + case ETH_SS_PRIV_FLAGS: + return IGB_PRIV_FLAGS_STR_LEN; + default: + return -ENOTSUPP; + } +} + +static void igb_get_ethtool_stats(struct net_device *netdev, + struct ethtool_stats *stats, u64 *data) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct rtnl_link_stats64 *net_stats = &adapter->stats64; + unsigned int start; + struct igb_ring *ring; + int i, j; + char *p; + + spin_lock(&adapter->stats64_lock); + igb_update_stats(adapter); + + for (i = 0; i < IGB_GLOBAL_STATS_LEN; i++) { + p = (char *)adapter + igb_gstrings_stats[i].stat_offset; + data[i] = (igb_gstrings_stats[i].sizeof_stat == + sizeof(u64)) ? *(u64 *)p : *(u32 *)p; + } + for (j = 0; j < IGB_NETDEV_STATS_LEN; j++, i++) { + p = (char *)net_stats + igb_gstrings_net_stats[j].stat_offset; + data[i] = (igb_gstrings_net_stats[j].sizeof_stat == + sizeof(u64)) ? *(u64 *)p : *(u32 *)p; + } + for (j = 0; j < adapter->num_tx_queues; j++) { + u64 restart2; + + ring = adapter->tx_ring[j]; + do { + start = u64_stats_fetch_begin(&ring->tx_syncp); + data[i] = ring->tx_stats.packets; + data[i+1] = ring->tx_stats.bytes; + data[i+2] = ring->tx_stats.restart_queue; + } while (u64_stats_fetch_retry(&ring->tx_syncp, start)); + do { + start = u64_stats_fetch_begin(&ring->tx_syncp2); + restart2 = ring->tx_stats.restart_queue2; + } while (u64_stats_fetch_retry(&ring->tx_syncp2, start)); + data[i+2] += restart2; + + i += IGB_TX_QUEUE_STATS_LEN; + } + for (j = 0; j < adapter->num_rx_queues; j++) { + ring = adapter->rx_ring[j]; + do { + start = u64_stats_fetch_begin(&ring->rx_syncp); + data[i] = ring->rx_stats.packets; + data[i+1] = ring->rx_stats.bytes; + data[i+2] = ring->rx_stats.drops; + data[i+3] = ring->rx_stats.csum_err; + data[i+4] = ring->rx_stats.alloc_failed; + } while (u64_stats_fetch_retry(&ring->rx_syncp, start)); + i += IGB_RX_QUEUE_STATS_LEN; + } + spin_unlock(&adapter->stats64_lock); +} + +static void igb_get_strings(struct net_device *netdev, u32 stringset, u8 *data) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + u8 *p = data; + int i; + + switch (stringset) { + case ETH_SS_TEST: + memcpy(data, igb_gstrings_test, sizeof(igb_gstrings_test)); + break; + case ETH_SS_STATS: + for (i = 0; i < IGB_GLOBAL_STATS_LEN; i++) + ethtool_sprintf(&p, + igb_gstrings_stats[i].stat_string); + for (i = 0; i < IGB_NETDEV_STATS_LEN; i++) + ethtool_sprintf(&p, + igb_gstrings_net_stats[i].stat_string); + for (i = 0; i < adapter->num_tx_queues; i++) { + ethtool_sprintf(&p, "tx_queue_%u_packets", i); + ethtool_sprintf(&p, "tx_queue_%u_bytes", i); + ethtool_sprintf(&p, "tx_queue_%u_restart", i); + } + for (i = 0; i < adapter->num_rx_queues; i++) { + ethtool_sprintf(&p, "rx_queue_%u_packets", i); + ethtool_sprintf(&p, "rx_queue_%u_bytes", i); + ethtool_sprintf(&p, "rx_queue_%u_drops", i); + ethtool_sprintf(&p, "rx_queue_%u_csum_err", i); + ethtool_sprintf(&p, "rx_queue_%u_alloc_failed", i); + } + /* BUG_ON(p - data != IGB_STATS_LEN * ETH_GSTRING_LEN); */ + break; + case ETH_SS_PRIV_FLAGS: + memcpy(data, igb_priv_flags_strings, + IGB_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN); + break; + } +} + +static int igb_get_ts_info(struct net_device *dev, + struct ethtool_ts_info *info) +{ + struct igb_adapter *adapter = netdev_priv(dev); + + if (adapter->ptp_clock) + info->phc_index = ptp_clock_index(adapter->ptp_clock); + else + info->phc_index = -1; + + switch (adapter->hw.mac.type) { + case e1000_82575: + info->so_timestamping = + SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + return 0; + case e1000_82576: + case e1000_82580: + case e1000_i350: + case e1000_i354: + case e1000_i210: + case e1000_i211: + info->so_timestamping = + SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + + info->tx_types = + BIT(HWTSTAMP_TX_OFF) | + BIT(HWTSTAMP_TX_ON); + + info->rx_filters = BIT(HWTSTAMP_FILTER_NONE); + + /* 82576 does not support timestamping all packets. */ + if (adapter->hw.mac.type >= e1000_82580) + info->rx_filters |= BIT(HWTSTAMP_FILTER_ALL); + else + info->rx_filters |= + BIT(HWTSTAMP_FILTER_PTP_V1_L4_SYNC) | + BIT(HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) | + BIT(HWTSTAMP_FILTER_PTP_V2_EVENT); + + return 0; + default: + return -EOPNOTSUPP; + } +} + +#define ETHER_TYPE_FULL_MASK ((__force __be16)~0) +static int igb_get_ethtool_nfc_entry(struct igb_adapter *adapter, + struct ethtool_rxnfc *cmd) +{ + struct ethtool_rx_flow_spec *fsp = &cmd->fs; + struct igb_nfc_filter *rule = NULL; + + /* report total rule count */ + cmd->data = IGB_MAX_RXNFC_FILTERS; + + hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) { + if (fsp->location <= rule->sw_idx) + break; + } + + if (!rule || fsp->location != rule->sw_idx) + return -EINVAL; + + if (rule->filter.match_flags) { + fsp->flow_type = ETHER_FLOW; + fsp->ring_cookie = rule->action; + if (rule->filter.match_flags & IGB_FILTER_FLAG_ETHER_TYPE) { + fsp->h_u.ether_spec.h_proto = rule->filter.etype; + fsp->m_u.ether_spec.h_proto = ETHER_TYPE_FULL_MASK; + } + if (rule->filter.match_flags & IGB_FILTER_FLAG_VLAN_TCI) { + fsp->flow_type |= FLOW_EXT; + fsp->h_ext.vlan_tci = rule->filter.vlan_tci; + fsp->m_ext.vlan_tci = htons(VLAN_PRIO_MASK); + } + if (rule->filter.match_flags & IGB_FILTER_FLAG_DST_MAC_ADDR) { + ether_addr_copy(fsp->h_u.ether_spec.h_dest, + rule->filter.dst_addr); + /* As we only support matching by the full + * mask, return the mask to userspace + */ + eth_broadcast_addr(fsp->m_u.ether_spec.h_dest); + } + if (rule->filter.match_flags & IGB_FILTER_FLAG_SRC_MAC_ADDR) { + ether_addr_copy(fsp->h_u.ether_spec.h_source, + rule->filter.src_addr); + /* As we only support matching by the full + * mask, return the mask to userspace + */ + eth_broadcast_addr(fsp->m_u.ether_spec.h_source); + } + + return 0; + } + return -EINVAL; +} + +static int igb_get_ethtool_nfc_all(struct igb_adapter *adapter, + struct ethtool_rxnfc *cmd, + u32 *rule_locs) +{ + struct igb_nfc_filter *rule; + int cnt = 0; + + /* report total rule count */ + cmd->data = IGB_MAX_RXNFC_FILTERS; + + hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) { + if (cnt == cmd->rule_cnt) + return -EMSGSIZE; + rule_locs[cnt] = rule->sw_idx; + cnt++; + } + + cmd->rule_cnt = cnt; + + return 0; +} + +static int igb_get_rss_hash_opts(struct igb_adapter *adapter, + struct ethtool_rxnfc *cmd) +{ + cmd->data = 0; + + /* Report default options for RSS on igb */ + switch (cmd->flow_type) { + case TCP_V4_FLOW: + cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + fallthrough; + case UDP_V4_FLOW: + if (adapter->flags & IGB_FLAG_RSS_FIELD_IPV4_UDP) + cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + fallthrough; + case SCTP_V4_FLOW: + case AH_ESP_V4_FLOW: + case AH_V4_FLOW: + case ESP_V4_FLOW: + case IPV4_FLOW: + cmd->data |= RXH_IP_SRC | RXH_IP_DST; + break; + case TCP_V6_FLOW: + cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + fallthrough; + case UDP_V6_FLOW: + if (adapter->flags & IGB_FLAG_RSS_FIELD_IPV6_UDP) + cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + fallthrough; + case SCTP_V6_FLOW: + case AH_ESP_V6_FLOW: + case AH_V6_FLOW: + case ESP_V6_FLOW: + case IPV6_FLOW: + cmd->data |= RXH_IP_SRC | RXH_IP_DST; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int igb_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, + u32 *rule_locs) +{ + struct igb_adapter *adapter = netdev_priv(dev); + int ret = -EOPNOTSUPP; + + switch (cmd->cmd) { + case ETHTOOL_GRXRINGS: + cmd->data = adapter->num_rx_queues; + ret = 0; + break; + case ETHTOOL_GRXCLSRLCNT: + cmd->rule_cnt = adapter->nfc_filter_count; + ret = 0; + break; + case ETHTOOL_GRXCLSRULE: + ret = igb_get_ethtool_nfc_entry(adapter, cmd); + break; + case ETHTOOL_GRXCLSRLALL: + ret = igb_get_ethtool_nfc_all(adapter, cmd, rule_locs); + break; + case ETHTOOL_GRXFH: + ret = igb_get_rss_hash_opts(adapter, cmd); + break; + default: + break; + } + + return ret; +} + +#define UDP_RSS_FLAGS (IGB_FLAG_RSS_FIELD_IPV4_UDP | \ + IGB_FLAG_RSS_FIELD_IPV6_UDP) +static int igb_set_rss_hash_opt(struct igb_adapter *adapter, + struct ethtool_rxnfc *nfc) +{ + u32 flags = adapter->flags; + + /* RSS does not support anything other than hashing + * to queues on src and dst IPs and ports + */ + if (nfc->data & ~(RXH_IP_SRC | RXH_IP_DST | + RXH_L4_B_0_1 | RXH_L4_B_2_3)) + return -EINVAL; + + switch (nfc->flow_type) { + case TCP_V4_FLOW: + case TCP_V6_FLOW: + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST) || + !(nfc->data & RXH_L4_B_0_1) || + !(nfc->data & RXH_L4_B_2_3)) + return -EINVAL; + break; + case UDP_V4_FLOW: + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST)) + return -EINVAL; + switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { + case 0: + flags &= ~IGB_FLAG_RSS_FIELD_IPV4_UDP; + break; + case (RXH_L4_B_0_1 | RXH_L4_B_2_3): + flags |= IGB_FLAG_RSS_FIELD_IPV4_UDP; + break; + default: + return -EINVAL; + } + break; + case UDP_V6_FLOW: + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST)) + return -EINVAL; + switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { + case 0: + flags &= ~IGB_FLAG_RSS_FIELD_IPV6_UDP; + break; + case (RXH_L4_B_0_1 | RXH_L4_B_2_3): + flags |= IGB_FLAG_RSS_FIELD_IPV6_UDP; + break; + default: + return -EINVAL; + } + break; + case AH_ESP_V4_FLOW: + case AH_V4_FLOW: + case ESP_V4_FLOW: + case SCTP_V4_FLOW: + case AH_ESP_V6_FLOW: + case AH_V6_FLOW: + case ESP_V6_FLOW: + case SCTP_V6_FLOW: + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST) || + (nfc->data & RXH_L4_B_0_1) || + (nfc->data & RXH_L4_B_2_3)) + return -EINVAL; + break; + default: + return -EINVAL; + } + + /* if we changed something we need to update flags */ + if (flags != adapter->flags) { + struct e1000_hw *hw = &adapter->hw; + u32 mrqc = rd32(E1000_MRQC); + + if ((flags & UDP_RSS_FLAGS) && + !(adapter->flags & UDP_RSS_FLAGS)) + dev_err(&adapter->pdev->dev, + "enabling UDP RSS: fragmented packets may arrive out of order to the stack above\n"); + + adapter->flags = flags; + + /* Perform hash on these packet types */ + mrqc |= E1000_MRQC_RSS_FIELD_IPV4 | + E1000_MRQC_RSS_FIELD_IPV4_TCP | + E1000_MRQC_RSS_FIELD_IPV6 | + E1000_MRQC_RSS_FIELD_IPV6_TCP; + + mrqc &= ~(E1000_MRQC_RSS_FIELD_IPV4_UDP | + E1000_MRQC_RSS_FIELD_IPV6_UDP); + + if (flags & IGB_FLAG_RSS_FIELD_IPV4_UDP) + mrqc |= E1000_MRQC_RSS_FIELD_IPV4_UDP; + + if (flags & IGB_FLAG_RSS_FIELD_IPV6_UDP) + mrqc |= E1000_MRQC_RSS_FIELD_IPV6_UDP; + + wr32(E1000_MRQC, mrqc); + } + + return 0; +} + +static int igb_rxnfc_write_etype_filter(struct igb_adapter *adapter, + struct igb_nfc_filter *input) +{ + struct e1000_hw *hw = &adapter->hw; + u8 i; + u32 etqf; + u16 etype; + + /* find an empty etype filter register */ + for (i = 0; i < MAX_ETYPE_FILTER; ++i) { + if (!adapter->etype_bitmap[i]) + break; + } + if (i == MAX_ETYPE_FILTER) { + dev_err(&adapter->pdev->dev, "ethtool -N: etype filters are all used.\n"); + return -EINVAL; + } + + adapter->etype_bitmap[i] = true; + + etqf = rd32(E1000_ETQF(i)); + etype = ntohs(input->filter.etype & ETHER_TYPE_FULL_MASK); + + etqf |= E1000_ETQF_FILTER_ENABLE; + etqf &= ~E1000_ETQF_ETYPE_MASK; + etqf |= (etype & E1000_ETQF_ETYPE_MASK); + + etqf &= ~E1000_ETQF_QUEUE_MASK; + etqf |= ((input->action << E1000_ETQF_QUEUE_SHIFT) + & E1000_ETQF_QUEUE_MASK); + etqf |= E1000_ETQF_QUEUE_ENABLE; + + wr32(E1000_ETQF(i), etqf); + + input->etype_reg_index = i; + + return 0; +} + +static int igb_rxnfc_write_vlan_prio_filter(struct igb_adapter *adapter, + struct igb_nfc_filter *input) +{ + struct e1000_hw *hw = &adapter->hw; + u8 vlan_priority; + u16 queue_index; + u32 vlapqf; + + vlapqf = rd32(E1000_VLAPQF); + vlan_priority = (ntohs(input->filter.vlan_tci) & VLAN_PRIO_MASK) + >> VLAN_PRIO_SHIFT; + queue_index = (vlapqf >> (vlan_priority * 4)) & E1000_VLAPQF_QUEUE_MASK; + + /* check whether this vlan prio is already set */ + if ((vlapqf & E1000_VLAPQF_P_VALID(vlan_priority)) && + (queue_index != input->action)) { + dev_err(&adapter->pdev->dev, "ethtool rxnfc set vlan prio filter failed.\n"); + return -EEXIST; + } + + vlapqf |= E1000_VLAPQF_P_VALID(vlan_priority); + vlapqf |= E1000_VLAPQF_QUEUE_SEL(vlan_priority, input->action); + + wr32(E1000_VLAPQF, vlapqf); + + return 0; +} + +int igb_add_filter(struct igb_adapter *adapter, struct igb_nfc_filter *input) +{ + struct e1000_hw *hw = &adapter->hw; + int err = -EINVAL; + + if (hw->mac.type == e1000_i210 && + !(input->filter.match_flags & ~IGB_FILTER_FLAG_SRC_MAC_ADDR)) { + dev_err(&adapter->pdev->dev, + "i210 doesn't support flow classification rules specifying only source addresses.\n"); + return -EOPNOTSUPP; + } + + if (input->filter.match_flags & IGB_FILTER_FLAG_ETHER_TYPE) { + err = igb_rxnfc_write_etype_filter(adapter, input); + if (err) + return err; + } + + if (input->filter.match_flags & IGB_FILTER_FLAG_DST_MAC_ADDR) { + err = igb_add_mac_steering_filter(adapter, + input->filter.dst_addr, + input->action, 0); + err = min_t(int, err, 0); + if (err) + return err; + } + + if (input->filter.match_flags & IGB_FILTER_FLAG_SRC_MAC_ADDR) { + err = igb_add_mac_steering_filter(adapter, + input->filter.src_addr, + input->action, + IGB_MAC_STATE_SRC_ADDR); + err = min_t(int, err, 0); + if (err) + return err; + } + + if (input->filter.match_flags & IGB_FILTER_FLAG_VLAN_TCI) + err = igb_rxnfc_write_vlan_prio_filter(adapter, input); + + return err; +} + +static void igb_clear_etype_filter_regs(struct igb_adapter *adapter, + u16 reg_index) +{ + struct e1000_hw *hw = &adapter->hw; + u32 etqf = rd32(E1000_ETQF(reg_index)); + + etqf &= ~E1000_ETQF_QUEUE_ENABLE; + etqf &= ~E1000_ETQF_QUEUE_MASK; + etqf &= ~E1000_ETQF_FILTER_ENABLE; + + wr32(E1000_ETQF(reg_index), etqf); + + adapter->etype_bitmap[reg_index] = false; +} + +static void igb_clear_vlan_prio_filter(struct igb_adapter *adapter, + u16 vlan_tci) +{ + struct e1000_hw *hw = &adapter->hw; + u8 vlan_priority; + u32 vlapqf; + + vlan_priority = (vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; + + vlapqf = rd32(E1000_VLAPQF); + vlapqf &= ~E1000_VLAPQF_P_VALID(vlan_priority); + vlapqf &= ~E1000_VLAPQF_QUEUE_SEL(vlan_priority, + E1000_VLAPQF_QUEUE_MASK); + + wr32(E1000_VLAPQF, vlapqf); +} + +int igb_erase_filter(struct igb_adapter *adapter, struct igb_nfc_filter *input) +{ + if (input->filter.match_flags & IGB_FILTER_FLAG_ETHER_TYPE) + igb_clear_etype_filter_regs(adapter, + input->etype_reg_index); + + if (input->filter.match_flags & IGB_FILTER_FLAG_VLAN_TCI) + igb_clear_vlan_prio_filter(adapter, + ntohs(input->filter.vlan_tci)); + + if (input->filter.match_flags & IGB_FILTER_FLAG_SRC_MAC_ADDR) + igb_del_mac_steering_filter(adapter, input->filter.src_addr, + input->action, + IGB_MAC_STATE_SRC_ADDR); + + if (input->filter.match_flags & IGB_FILTER_FLAG_DST_MAC_ADDR) + igb_del_mac_steering_filter(adapter, input->filter.dst_addr, + input->action, 0); + + return 0; +} + +static int igb_update_ethtool_nfc_entry(struct igb_adapter *adapter, + struct igb_nfc_filter *input, + u16 sw_idx) +{ + struct igb_nfc_filter *rule, *parent; + int err = -EINVAL; + + parent = NULL; + rule = NULL; + + hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) { + /* hash found, or no matching entry */ + if (rule->sw_idx >= sw_idx) + break; + parent = rule; + } + + /* if there is an old rule occupying our place remove it */ + if (rule && (rule->sw_idx == sw_idx)) { + if (!input) + err = igb_erase_filter(adapter, rule); + + hlist_del(&rule->nfc_node); + kfree(rule); + adapter->nfc_filter_count--; + } + + /* If no input this was a delete, err should be 0 if a rule was + * successfully found and removed from the list else -EINVAL + */ + if (!input) + return err; + + /* initialize node */ + INIT_HLIST_NODE(&input->nfc_node); + + /* add filter to the list */ + if (parent) + hlist_add_behind(&input->nfc_node, &parent->nfc_node); + else + hlist_add_head(&input->nfc_node, &adapter->nfc_filter_list); + + /* update counts */ + adapter->nfc_filter_count++; + + return 0; +} + +static int igb_add_ethtool_nfc_entry(struct igb_adapter *adapter, + struct ethtool_rxnfc *cmd) +{ + struct net_device *netdev = adapter->netdev; + struct ethtool_rx_flow_spec *fsp = + (struct ethtool_rx_flow_spec *)&cmd->fs; + struct igb_nfc_filter *input, *rule; + int err = 0; + + if (!(netdev->hw_features & NETIF_F_NTUPLE)) + return -EOPNOTSUPP; + + /* Don't allow programming if the action is a queue greater than + * the number of online Rx queues. + */ + if ((fsp->ring_cookie == RX_CLS_FLOW_DISC) || + (fsp->ring_cookie >= adapter->num_rx_queues)) { + dev_err(&adapter->pdev->dev, "ethtool -N: The specified action is invalid\n"); + return -EINVAL; + } + + /* Don't allow indexes to exist outside of available space */ + if (fsp->location >= IGB_MAX_RXNFC_FILTERS) { + dev_err(&adapter->pdev->dev, "Location out of range\n"); + return -EINVAL; + } + + if ((fsp->flow_type & ~FLOW_EXT) != ETHER_FLOW) + return -EINVAL; + + input = kzalloc(sizeof(*input), GFP_KERNEL); + if (!input) + return -ENOMEM; + + if (fsp->m_u.ether_spec.h_proto == ETHER_TYPE_FULL_MASK) { + input->filter.etype = fsp->h_u.ether_spec.h_proto; + input->filter.match_flags = IGB_FILTER_FLAG_ETHER_TYPE; + } + + /* Only support matching addresses by the full mask */ + if (is_broadcast_ether_addr(fsp->m_u.ether_spec.h_source)) { + input->filter.match_flags |= IGB_FILTER_FLAG_SRC_MAC_ADDR; + ether_addr_copy(input->filter.src_addr, + fsp->h_u.ether_spec.h_source); + } + + /* Only support matching addresses by the full mask */ + if (is_broadcast_ether_addr(fsp->m_u.ether_spec.h_dest)) { + input->filter.match_flags |= IGB_FILTER_FLAG_DST_MAC_ADDR; + ether_addr_copy(input->filter.dst_addr, + fsp->h_u.ether_spec.h_dest); + } + + if ((fsp->flow_type & FLOW_EXT) && fsp->m_ext.vlan_tci) { + if (fsp->m_ext.vlan_tci != htons(VLAN_PRIO_MASK)) { + err = -EINVAL; + goto err_out; + } + input->filter.vlan_tci = fsp->h_ext.vlan_tci; + input->filter.match_flags |= IGB_FILTER_FLAG_VLAN_TCI; + } + + input->action = fsp->ring_cookie; + input->sw_idx = fsp->location; + + spin_lock(&adapter->nfc_lock); + + hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) { + if (!memcmp(&input->filter, &rule->filter, + sizeof(input->filter))) { + err = -EEXIST; + dev_err(&adapter->pdev->dev, + "ethtool: this filter is already set\n"); + goto err_out_w_lock; + } + } + + err = igb_add_filter(adapter, input); + if (err) + goto err_out_w_lock; + + err = igb_update_ethtool_nfc_entry(adapter, input, input->sw_idx); + if (err) + goto err_out_input_filter; + + spin_unlock(&adapter->nfc_lock); + return 0; + +err_out_input_filter: + igb_erase_filter(adapter, input); +err_out_w_lock: + spin_unlock(&adapter->nfc_lock); +err_out: + kfree(input); + return err; +} + +static int igb_del_ethtool_nfc_entry(struct igb_adapter *adapter, + struct ethtool_rxnfc *cmd) +{ + struct ethtool_rx_flow_spec *fsp = + (struct ethtool_rx_flow_spec *)&cmd->fs; + int err; + + spin_lock(&adapter->nfc_lock); + err = igb_update_ethtool_nfc_entry(adapter, NULL, fsp->location); + spin_unlock(&adapter->nfc_lock); + + return err; +} + +static int igb_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) +{ + struct igb_adapter *adapter = netdev_priv(dev); + int ret = -EOPNOTSUPP; + + switch (cmd->cmd) { + case ETHTOOL_SRXFH: + ret = igb_set_rss_hash_opt(adapter, cmd); + break; + case ETHTOOL_SRXCLSRLINS: + ret = igb_add_ethtool_nfc_entry(adapter, cmd); + break; + case ETHTOOL_SRXCLSRLDEL: + ret = igb_del_ethtool_nfc_entry(adapter, cmd); + break; + default: + break; + } + + return ret; +} + +static int igb_get_eee(struct net_device *netdev, struct ethtool_eee *edata) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + u32 ret_val; + u16 phy_data; + + if ((hw->mac.type < e1000_i350) || + (hw->phy.media_type != e1000_media_type_copper)) + return -EOPNOTSUPP; + + edata->supported = (SUPPORTED_1000baseT_Full | + SUPPORTED_100baseT_Full); + if (!hw->dev_spec._82575.eee_disable) + edata->advertised = + mmd_eee_adv_to_ethtool_adv_t(adapter->eee_advert); + + /* The IPCNFG and EEER registers are not supported on I354. */ + if (hw->mac.type == e1000_i354) { + igb_get_eee_status_i354(hw, (bool *)&edata->eee_active); + } else { + u32 eeer; + + eeer = rd32(E1000_EEER); + + /* EEE status on negotiated link */ + if (eeer & E1000_EEER_EEE_NEG) + edata->eee_active = true; + + if (eeer & E1000_EEER_TX_LPI_EN) + edata->tx_lpi_enabled = true; + } + + /* EEE Link Partner Advertised */ + switch (hw->mac.type) { + case e1000_i350: + ret_val = igb_read_emi_reg(hw, E1000_EEE_LP_ADV_ADDR_I350, + &phy_data); + if (ret_val) + return -ENODATA; + + edata->lp_advertised = mmd_eee_adv_to_ethtool_adv_t(phy_data); + break; + case e1000_i354: + case e1000_i210: + case e1000_i211: + ret_val = igb_read_xmdio_reg(hw, E1000_EEE_LP_ADV_ADDR_I210, + E1000_EEE_LP_ADV_DEV_I210, + &phy_data); + if (ret_val) + return -ENODATA; + + edata->lp_advertised = mmd_eee_adv_to_ethtool_adv_t(phy_data); + + break; + default: + break; + } + + edata->eee_enabled = !hw->dev_spec._82575.eee_disable; + + if ((hw->mac.type == e1000_i354) && + (edata->eee_enabled)) + edata->tx_lpi_enabled = true; + + /* Report correct negotiated EEE status for devices that + * wrongly report EEE at half-duplex + */ + if (adapter->link_duplex == HALF_DUPLEX) { + edata->eee_enabled = false; + edata->eee_active = false; + edata->tx_lpi_enabled = false; + edata->advertised &= ~edata->advertised; + } + + return 0; +} + +static int igb_set_eee(struct net_device *netdev, + struct ethtool_eee *edata) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + struct ethtool_eee eee_curr; + bool adv1g_eee = true, adv100m_eee = true; + s32 ret_val; + + if ((hw->mac.type < e1000_i350) || + (hw->phy.media_type != e1000_media_type_copper)) + return -EOPNOTSUPP; + + memset(&eee_curr, 0, sizeof(struct ethtool_eee)); + + ret_val = igb_get_eee(netdev, &eee_curr); + if (ret_val) + return ret_val; + + if (eee_curr.eee_enabled) { + if (eee_curr.tx_lpi_enabled != edata->tx_lpi_enabled) { + dev_err(&adapter->pdev->dev, + "Setting EEE tx-lpi is not supported\n"); + return -EINVAL; + } + + /* Tx LPI timer is not implemented currently */ + if (edata->tx_lpi_timer) { + dev_err(&adapter->pdev->dev, + "Setting EEE Tx LPI timer is not supported\n"); + return -EINVAL; + } + + if (!edata->advertised || (edata->advertised & + ~(ADVERTISE_100_FULL | ADVERTISE_1000_FULL))) { + dev_err(&adapter->pdev->dev, + "EEE Advertisement supports only 100Tx and/or 100T full duplex\n"); + return -EINVAL; + } + adv100m_eee = !!(edata->advertised & ADVERTISE_100_FULL); + adv1g_eee = !!(edata->advertised & ADVERTISE_1000_FULL); + + } else if (!edata->eee_enabled) { + dev_err(&adapter->pdev->dev, + "Setting EEE options are not supported with EEE disabled\n"); + return -EINVAL; + } + + adapter->eee_advert = ethtool_adv_to_mmd_eee_adv_t(edata->advertised); + if (hw->dev_spec._82575.eee_disable != !edata->eee_enabled) { + hw->dev_spec._82575.eee_disable = !edata->eee_enabled; + adapter->flags |= IGB_FLAG_EEE; + + /* reset link */ + if (netif_running(netdev)) + igb_reinit_locked(adapter); + else + igb_reset(adapter); + } + + if (hw->mac.type == e1000_i354) + ret_val = igb_set_eee_i354(hw, adv1g_eee, adv100m_eee); + else + ret_val = igb_set_eee_i350(hw, adv1g_eee, adv100m_eee); + + if (ret_val) { + dev_err(&adapter->pdev->dev, + "Problem setting EEE advertisement options\n"); + return -EINVAL; + } + + return 0; +} + +static int igb_get_module_info(struct net_device *netdev, + struct ethtool_modinfo *modinfo) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + u32 status = 0; + u16 sff8472_rev, addr_mode; + bool page_swap = false; + + if ((hw->phy.media_type == e1000_media_type_copper) || + (hw->phy.media_type == e1000_media_type_unknown)) + return -EOPNOTSUPP; + + /* Check whether we support SFF-8472 or not */ + status = igb_read_phy_reg_i2c(hw, IGB_SFF_8472_COMP, &sff8472_rev); + if (status) + return -EIO; + + /* addressing mode is not supported */ + status = igb_read_phy_reg_i2c(hw, IGB_SFF_8472_SWAP, &addr_mode); + if (status) + return -EIO; + + /* addressing mode is not supported */ + if ((addr_mode & 0xFF) & IGB_SFF_ADDRESSING_MODE) { + hw_dbg("Address change required to access page 0xA2, but not supported. Please report the module type to the driver maintainers.\n"); + page_swap = true; + } + + if ((sff8472_rev & 0xFF) == IGB_SFF_8472_UNSUP || page_swap) { + /* We have an SFP, but it does not support SFF-8472 */ + modinfo->type = ETH_MODULE_SFF_8079; + modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN; + } else { + /* We have an SFP which supports a revision of SFF-8472 */ + modinfo->type = ETH_MODULE_SFF_8472; + modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; + } + + return 0; +} + +static int igb_get_module_eeprom(struct net_device *netdev, + struct ethtool_eeprom *ee, u8 *data) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + u32 status = 0; + u16 *dataword; + u16 first_word, last_word; + int i = 0; + + if (ee->len == 0) + return -EINVAL; + + first_word = ee->offset >> 1; + last_word = (ee->offset + ee->len - 1) >> 1; + + dataword = kmalloc_array(last_word - first_word + 1, sizeof(u16), + GFP_KERNEL); + if (!dataword) + return -ENOMEM; + + /* Read EEPROM block, SFF-8079/SFF-8472, word at a time */ + for (i = 0; i < last_word - first_word + 1; i++) { + status = igb_read_phy_reg_i2c(hw, (first_word + i) * 2, + &dataword[i]); + if (status) { + /* Error occurred while reading module */ + kfree(dataword); + return -EIO; + } + + be16_to_cpus(&dataword[i]); + } + + memcpy(data, (u8 *)dataword + (ee->offset & 1), ee->len); + kfree(dataword); + + return 0; +} + +static int igb_ethtool_begin(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + pm_runtime_get_sync(&adapter->pdev->dev); + return 0; +} + +static void igb_ethtool_complete(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + pm_runtime_put(&adapter->pdev->dev); +} + +static u32 igb_get_rxfh_indir_size(struct net_device *netdev) +{ + return IGB_RETA_SIZE; +} + +static int igb_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, + u8 *hfunc) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + int i; + + if (hfunc) + *hfunc = ETH_RSS_HASH_TOP; + if (!indir) + return 0; + for (i = 0; i < IGB_RETA_SIZE; i++) + indir[i] = adapter->rss_indir_tbl[i]; + + return 0; +} + +void igb_write_rss_indir_tbl(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 reg = E1000_RETA(0); + u32 shift = 0; + int i = 0; + + 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; + break; + default: + break; + } + + while (i < IGB_RETA_SIZE) { + u32 val = 0; + int j; + + for (j = 3; j >= 0; j--) { + val <<= 8; + val |= adapter->rss_indir_tbl[i + j]; + } + + wr32(reg, val << shift); + reg += 4; + i += 4; + } +} + +static int igb_set_rxfh(struct net_device *netdev, const u32 *indir, + const u8 *key, const u8 hfunc) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + int i; + u32 num_queues; + + /* We do not allow change in unsupported parameters */ + if (key || + (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)) + return -EOPNOTSUPP; + if (!indir) + return 0; + + num_queues = adapter->rss_queues; + + switch (hw->mac.type) { + case e1000_82576: + /* 82576 supports 2 RSS queues for SR-IOV */ + if (adapter->vfs_allocated_count) + num_queues = 2; + break; + default: + break; + } + + /* Verify user input. */ + for (i = 0; i < IGB_RETA_SIZE; i++) + if (indir[i] >= num_queues) + return -EINVAL; + + + for (i = 0; i < IGB_RETA_SIZE; i++) + adapter->rss_indir_tbl[i] = indir[i]; + + igb_write_rss_indir_tbl(adapter); + + return 0; +} + +static unsigned int igb_max_channels(struct igb_adapter *adapter) +{ + return igb_get_max_rss_queues(adapter); +} + +static void igb_get_channels(struct net_device *netdev, + struct ethtool_channels *ch) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + + /* Report maximum channels */ + ch->max_combined = igb_max_channels(adapter); + + /* Report info for other vector */ + if (adapter->flags & IGB_FLAG_HAS_MSIX) { + ch->max_other = NON_Q_VECTORS; + ch->other_count = NON_Q_VECTORS; + } + + ch->combined_count = adapter->rss_queues; +} + +static int igb_set_channels(struct net_device *netdev, + struct ethtool_channels *ch) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + unsigned int count = ch->combined_count; + unsigned int max_combined = 0; + + /* Verify they are not requesting separate vectors */ + if (!count || ch->rx_count || ch->tx_count) + return -EINVAL; + + /* Verify other_count is valid and has not been changed */ + if (ch->other_count != NON_Q_VECTORS) + return -EINVAL; + + /* Verify the number of channels doesn't exceed hw limits */ + max_combined = igb_max_channels(adapter); + if (count > max_combined) + return -EINVAL; + + if (count != adapter->rss_queues) { + adapter->rss_queues = count; + igb_set_flag_queue_pairs(adapter, max_combined); + + /* Hardware has to reinitialize queues and interrupts to + * match the new configuration. + */ + return igb_reinit_queues(adapter); + } + + return 0; +} + +static u32 igb_get_priv_flags(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + u32 priv_flags = 0; + + if (adapter->flags & IGB_FLAG_RX_LEGACY) + priv_flags |= IGB_PRIV_FLAGS_LEGACY_RX; + + return priv_flags; +} + +static int igb_set_priv_flags(struct net_device *netdev, u32 priv_flags) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + unsigned int flags = adapter->flags; + + flags &= ~IGB_FLAG_RX_LEGACY; + if (priv_flags & IGB_PRIV_FLAGS_LEGACY_RX) + flags |= IGB_FLAG_RX_LEGACY; + + if (flags != adapter->flags) { + adapter->flags = flags; + + /* reset interface to repopulate queues */ + if (netif_running(netdev)) + igb_reinit_locked(adapter); + } + + return 0; +} + +static const struct ethtool_ops igb_ethtool_ops = { + .supported_coalesce_params = ETHTOOL_COALESCE_USECS, + .get_drvinfo = igb_get_drvinfo, + .get_regs_len = igb_get_regs_len, + .get_regs = igb_get_regs, + .get_wol = igb_get_wol, + .set_wol = igb_set_wol, + .get_msglevel = igb_get_msglevel, + .set_msglevel = igb_set_msglevel, + .nway_reset = igb_nway_reset, + .get_link = igb_get_link, + .get_eeprom_len = igb_get_eeprom_len, + .get_eeprom = igb_get_eeprom, + .set_eeprom = igb_set_eeprom, + .get_ringparam = igb_get_ringparam, + .set_ringparam = igb_set_ringparam, + .get_pauseparam = igb_get_pauseparam, + .set_pauseparam = igb_set_pauseparam, + .self_test = igb_diag_test, + .get_strings = igb_get_strings, + .set_phys_id = igb_set_phys_id, + .get_sset_count = igb_get_sset_count, + .get_ethtool_stats = igb_get_ethtool_stats, + .get_coalesce = igb_get_coalesce, + .set_coalesce = igb_set_coalesce, + .get_ts_info = igb_get_ts_info, + .get_rxnfc = igb_get_rxnfc, + .set_rxnfc = igb_set_rxnfc, + .get_eee = igb_get_eee, + .set_eee = igb_set_eee, + .get_module_info = igb_get_module_info, + .get_module_eeprom = igb_get_module_eeprom, + .get_rxfh_indir_size = igb_get_rxfh_indir_size, + .get_rxfh = igb_get_rxfh, + .set_rxfh = igb_set_rxfh, + .get_channels = igb_get_channels, + .set_channels = igb_set_channels, + .get_priv_flags = igb_get_priv_flags, + .set_priv_flags = igb_set_priv_flags, + .begin = igb_ethtool_begin, + .complete = igb_ethtool_complete, + .get_link_ksettings = igb_get_link_ksettings, + .set_link_ksettings = igb_set_link_ksettings, +}; + +void igb_set_ethtool_ops(struct net_device *netdev) +{ + netdev->ethtool_ops = &igb_ethtool_ops; +} diff --git a/drivers/net/ethernet/intel/igb/igb_hwmon.c b/drivers/net/ethernet/intel/igb/igb_hwmon.c new file mode 100644 index 0000000000..21a29a0ca7 --- /dev/null +++ b/drivers/net/ethernet/intel/igb/igb_hwmon.c @@ -0,0 +1,229 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2007 - 2018 Intel Corporation. */ + +#include "igb.h" +#include "e1000_82575.h" +#include "e1000_hw.h" + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/sysfs.h> +#include <linux/kobject.h> +#include <linux/device.h> +#include <linux/netdevice.h> +#include <linux/hwmon.h> +#include <linux/pci.h> + +#ifdef CONFIG_IGB_HWMON +static struct i2c_board_info i350_sensor_info = { + I2C_BOARD_INFO("i350bb", (0Xf8 >> 1)), +}; + +/* hwmon callback functions */ +static ssize_t igb_hwmon_show_location(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct hwmon_attr *igb_attr = container_of(attr, struct hwmon_attr, + dev_attr); + return sprintf(buf, "loc%u\n", + igb_attr->sensor->location); +} + +static ssize_t igb_hwmon_show_temp(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct hwmon_attr *igb_attr = container_of(attr, struct hwmon_attr, + dev_attr); + unsigned int value; + + /* reset the temp field */ + igb_attr->hw->mac.ops.get_thermal_sensor_data(igb_attr->hw); + + value = igb_attr->sensor->temp; + + /* display millidegree */ + value *= 1000; + + return sprintf(buf, "%u\n", value); +} + +static ssize_t igb_hwmon_show_cautionthresh(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct hwmon_attr *igb_attr = container_of(attr, struct hwmon_attr, + dev_attr); + unsigned int value = igb_attr->sensor->caution_thresh; + + /* display millidegree */ + value *= 1000; + + return sprintf(buf, "%u\n", value); +} + +static ssize_t igb_hwmon_show_maxopthresh(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct hwmon_attr *igb_attr = container_of(attr, struct hwmon_attr, + dev_attr); + unsigned int value = igb_attr->sensor->max_op_thresh; + + /* display millidegree */ + value *= 1000; + + return sprintf(buf, "%u\n", value); +} + +/* igb_add_hwmon_attr - Create hwmon attr table for a hwmon sysfs file. + * @ adapter: pointer to the adapter structure + * @ offset: offset in the eeprom sensor data table + * @ type: type of sensor data to display + * + * For each file we want in hwmon's sysfs interface we need a device_attribute + * This is included in our hwmon_attr struct that contains the references to + * the data structures we need to get the data to display. + */ +static int igb_add_hwmon_attr(struct igb_adapter *adapter, + unsigned int offset, int type) +{ + int rc; + unsigned int n_attr; + struct hwmon_attr *igb_attr; + + n_attr = adapter->igb_hwmon_buff->n_hwmon; + igb_attr = &adapter->igb_hwmon_buff->hwmon_list[n_attr]; + + switch (type) { + case IGB_HWMON_TYPE_LOC: + igb_attr->dev_attr.show = igb_hwmon_show_location; + snprintf(igb_attr->name, sizeof(igb_attr->name), + "temp%u_label", offset + 1); + break; + case IGB_HWMON_TYPE_TEMP: + igb_attr->dev_attr.show = igb_hwmon_show_temp; + snprintf(igb_attr->name, sizeof(igb_attr->name), + "temp%u_input", offset + 1); + break; + case IGB_HWMON_TYPE_CAUTION: + igb_attr->dev_attr.show = igb_hwmon_show_cautionthresh; + snprintf(igb_attr->name, sizeof(igb_attr->name), + "temp%u_max", offset + 1); + break; + case IGB_HWMON_TYPE_MAX: + igb_attr->dev_attr.show = igb_hwmon_show_maxopthresh; + snprintf(igb_attr->name, sizeof(igb_attr->name), + "temp%u_crit", offset + 1); + break; + default: + rc = -EPERM; + return rc; + } + + /* These always the same regardless of type */ + igb_attr->sensor = + &adapter->hw.mac.thermal_sensor_data.sensor[offset]; + igb_attr->hw = &adapter->hw; + igb_attr->dev_attr.store = NULL; + igb_attr->dev_attr.attr.mode = 0444; + igb_attr->dev_attr.attr.name = igb_attr->name; + sysfs_attr_init(&igb_attr->dev_attr.attr); + + adapter->igb_hwmon_buff->attrs[n_attr] = &igb_attr->dev_attr.attr; + + ++adapter->igb_hwmon_buff->n_hwmon; + + return 0; +} + +static void igb_sysfs_del_adapter(struct igb_adapter *adapter) +{ +} + +/* called from igb_main.c */ +void igb_sysfs_exit(struct igb_adapter *adapter) +{ + igb_sysfs_del_adapter(adapter); +} + +/* called from igb_main.c */ +int igb_sysfs_init(struct igb_adapter *adapter) +{ + struct hwmon_buff *igb_hwmon; + struct i2c_client *client; + struct device *hwmon_dev; + unsigned int i; + int rc = 0; + + /* If this method isn't defined we don't support thermals */ + if (adapter->hw.mac.ops.init_thermal_sensor_thresh == NULL) + goto exit; + + /* Don't create thermal hwmon interface if no sensors present */ + rc = (adapter->hw.mac.ops.init_thermal_sensor_thresh(&adapter->hw)); + if (rc) + goto exit; + + igb_hwmon = devm_kzalloc(&adapter->pdev->dev, sizeof(*igb_hwmon), + GFP_KERNEL); + if (!igb_hwmon) { + rc = -ENOMEM; + goto exit; + } + adapter->igb_hwmon_buff = igb_hwmon; + + for (i = 0; i < E1000_MAX_SENSORS; i++) { + + /* Only create hwmon sysfs entries for sensors that have + * meaningful data. + */ + if (adapter->hw.mac.thermal_sensor_data.sensor[i].location == 0) + continue; + + /* Bail if any hwmon attr struct fails to initialize */ + rc = igb_add_hwmon_attr(adapter, i, IGB_HWMON_TYPE_CAUTION); + if (rc) + goto exit; + rc = igb_add_hwmon_attr(adapter, i, IGB_HWMON_TYPE_LOC); + if (rc) + goto exit; + rc = igb_add_hwmon_attr(adapter, i, IGB_HWMON_TYPE_TEMP); + if (rc) + goto exit; + rc = igb_add_hwmon_attr(adapter, i, IGB_HWMON_TYPE_MAX); + if (rc) + goto exit; + } + + /* init i2c_client */ + client = i2c_new_client_device(&adapter->i2c_adap, &i350_sensor_info); + if (IS_ERR(client)) { + dev_info(&adapter->pdev->dev, + "Failed to create new i2c device.\n"); + rc = PTR_ERR(client); + goto exit; + } + adapter->i2c_client = client; + + igb_hwmon->groups[0] = &igb_hwmon->group; + igb_hwmon->group.attrs = igb_hwmon->attrs; + + hwmon_dev = devm_hwmon_device_register_with_groups(&adapter->pdev->dev, + client->name, + igb_hwmon, + igb_hwmon->groups); + if (IS_ERR(hwmon_dev)) { + rc = PTR_ERR(hwmon_dev); + goto err; + } + + goto exit; + +err: + igb_sysfs_del_adapter(adapter); +exit: + return rc; +} +#endif diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c new file mode 100644 index 0000000000..76b34cee1d --- /dev/null +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -0,0 +1,10176 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2007 - 2018 Intel Corporation. */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/init.h> +#include <linux/bitops.h> +#include <linux/vmalloc.h> +#include <linux/pagemap.h> +#include <linux/netdevice.h> +#include <linux/ipv6.h> +#include <linux/slab.h> +#include <net/checksum.h> +#include <net/ip6_checksum.h> +#include <net/pkt_sched.h> +#include <net/pkt_cls.h> +#include <linux/net_tstamp.h> +#include <linux/mii.h> +#include <linux/ethtool.h> +#include <linux/if.h> +#include <linux/if_vlan.h> +#include <linux/pci.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/ip.h> +#include <linux/tcp.h> +#include <linux/sctp.h> +#include <linux/if_ether.h> +#include <linux/prefetch.h> +#include <linux/bpf.h> +#include <linux/bpf_trace.h> +#include <linux/pm_runtime.h> +#include <linux/etherdevice.h> +#ifdef CONFIG_IGB_DCA +#include <linux/dca.h> +#endif +#include <linux/i2c.h> +#include "igb.h" + +enum queue_mode { + QUEUE_MODE_STRICT_PRIORITY, + QUEUE_MODE_STREAM_RESERVATION, +}; + +enum tx_queue_prio { + TX_QUEUE_PRIO_HIGH, + TX_QUEUE_PRIO_LOW, +}; + +char igb_driver_name[] = "igb"; +static const char igb_driver_string[] = + "Intel(R) Gigabit Ethernet Network Driver"; +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 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 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_I350_SGMII), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_COPPER), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_FIBER), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_QUAD_FIBER), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_SERDES), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_SGMII), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_COPPER_DUAL), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_DH89XXCC_SGMII), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_DH89XXCC_SERDES), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_DH89XXCC_BACKPLANE), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_DH89XXCC_SFP), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82576), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82576_NS), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82576_NS_SERDES), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82576_FIBER), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82576_SERDES), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82576_SERDES_QUAD), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82576_QUAD_COPPER_ET2), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82576_QUAD_COPPER), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82575EB_COPPER), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82575EB_FIBER_SERDES), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82575GB_QUAD_COPPER), board_82575 }, + /* required last entry */ + {0, } +}; + +MODULE_DEVICE_TABLE(pci, igb_pci_tbl); + +static int igb_setup_all_tx_resources(struct igb_adapter *); +static int igb_setup_all_rx_resources(struct igb_adapter *); +static void igb_free_all_tx_resources(struct igb_adapter *); +static void igb_free_all_rx_resources(struct igb_adapter *); +static void igb_setup_mrqc(struct igb_adapter *); +static int igb_probe(struct pci_dev *, const struct pci_device_id *); +static void igb_remove(struct pci_dev *pdev); +static void igb_init_queue_configuration(struct igb_adapter *adapter); +static int igb_sw_init(struct igb_adapter *); +int igb_open(struct net_device *); +int igb_close(struct net_device *); +static void igb_configure(struct igb_adapter *); +static void igb_configure_tx(struct igb_adapter *); +static void igb_configure_rx(struct igb_adapter *); +static void igb_clean_all_tx_rings(struct igb_adapter *); +static void igb_clean_all_rx_rings(struct igb_adapter *); +static void igb_clean_tx_ring(struct igb_ring *); +static void igb_clean_rx_ring(struct igb_ring *); +static void igb_set_rx_mode(struct net_device *); +static void igb_update_phy_info(struct timer_list *); +static void igb_watchdog(struct timer_list *); +static void igb_watchdog_task(struct work_struct *); +static netdev_tx_t igb_xmit_frame(struct sk_buff *skb, struct net_device *); +static void igb_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *stats); +static int igb_change_mtu(struct net_device *, int); +static int igb_set_mac(struct net_device *, void *); +static void igb_set_uta(struct igb_adapter *adapter, bool set); +static irqreturn_t igb_intr(int irq, void *); +static irqreturn_t igb_intr_msi(int irq, void *); +static irqreturn_t igb_msix_other(int irq, void *); +static irqreturn_t igb_msix_ring(int irq, void *); +#ifdef CONFIG_IGB_DCA +static void igb_update_dca(struct igb_q_vector *); +static void igb_setup_dca(struct igb_adapter *); +#endif /* CONFIG_IGB_DCA */ +static int igb_poll(struct napi_struct *, int); +static bool igb_clean_tx_irq(struct igb_q_vector *, int); +static int 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 *, unsigned int txqueue); +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 *, __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_index(struct igb_adapter *, u32); +static void igb_ping_all_vfs(struct igb_adapter *); +static void igb_msg_task(struct igb_adapter *); +static void igb_vmm_control(struct igb_adapter *); +static int igb_set_vf_mac(struct igb_adapter *, int, unsigned char *); +static void igb_flush_mac_table(struct igb_adapter *); +static int igb_available_rars(struct igb_adapter *, u8); +static void igb_set_default_mac_filter(struct igb_adapter *); +static int igb_uc_sync(struct net_device *, const unsigned char *); +static int igb_uc_unsync(struct net_device *, const unsigned char *); +static void igb_restore_vf_multicasts(struct igb_adapter *adapter); +static int igb_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac); +static int igb_ndo_set_vf_vlan(struct net_device *netdev, + int vf, u16 vlan, u8 qos, __be16 vlan_proto); +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_set_vf_trust(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 *); +static void igb_nfc_filter_exit(struct igb_adapter *adapter); +static void igb_nfc_filter_restore(struct igb_adapter *adapter); + +#ifdef CONFIG_PCI_IOV +static int igb_vf_configure(struct igb_adapter *adapter, int vf); +static int igb_disable_sriov(struct pci_dev *dev, bool reinit); +#endif + +static int igb_suspend(struct device *); +static int igb_resume(struct device *); +static int igb_runtime_suspend(struct device *dev); +static int igb_runtime_resume(struct device *dev); +static int igb_runtime_idle(struct device *dev); +#ifdef CONFIG_PM +static const struct dev_pm_ops igb_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(igb_suspend, igb_resume) + SET_RUNTIME_PM_OPS(igb_runtime_suspend, igb_runtime_resume, + igb_runtime_idle) +}; +#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 = { + .notifier_call = igb_notify_dca, + .next = NULL, + .priority = 0 +}; +#endif +#ifdef CONFIG_PCI_IOV +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"); +#endif /* CONFIG_PCI_IOV */ + +static pci_ers_result_t igb_io_error_detected(struct pci_dev *, + pci_channel_state_t); +static pci_ers_result_t igb_io_slot_reset(struct pci_dev *); +static void igb_io_resume(struct pci_dev *); + +static const struct pci_error_handlers igb_err_handler = { + .error_detected = igb_io_error_detected, + .slot_reset = igb_io_slot_reset, + .resume = igb_io_resume, +}; + +static void igb_init_dmac(struct igb_adapter *adapter, u32 pba); + +static struct pci_driver igb_driver = { + .name = igb_driver_name, + .id_table = igb_pci_tbl, + .probe = igb_probe, + .remove = igb_remove, +#ifdef CONFIG_PM + .driver.pm = &igb_pm_ops, +#endif + .shutdown = igb_shutdown, + .sriov_configure = igb_pci_sriov_configure, + .err_handler = &igb_err_handler +}; + +MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>"); +MODULE_DESCRIPTION("Intel(R) Gigabit Ethernet Network Driver"); +MODULE_LICENSE("GPL v2"); + +#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK) +static int debug = -1; +module_param(debug, int, 0); +MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); + +struct igb_reg_info { + u32 ofs; + char *name; +}; + +static const struct igb_reg_info igb_reg_info_tbl[] = { + + /* General Registers */ + {E1000_CTRL, "CTRL"}, + {E1000_STATUS, "STATUS"}, + {E1000_CTRL_EXT, "CTRL_EXT"}, + + /* Interrupt Registers */ + {E1000_ICR, "ICR"}, + + /* RX Registers */ + {E1000_RCTL, "RCTL"}, + {E1000_RDLEN(0), "RDLEN"}, + {E1000_RDH(0), "RDH"}, + {E1000_RDT(0), "RDT"}, + {E1000_RXDCTL(0), "RXDCTL"}, + {E1000_RDBAL(0), "RDBAL"}, + {E1000_RDBAH(0), "RDBAH"}, + + /* TX Registers */ + {E1000_TCTL, "TCTL"}, + {E1000_TDBAL(0), "TDBAL"}, + {E1000_TDBAH(0), "TDBAH"}, + {E1000_TDLEN(0), "TDLEN"}, + {E1000_TDH(0), "TDH"}, + {E1000_TDT(0), "TDT"}, + {E1000_TXDCTL(0), "TXDCTL"}, + {E1000_TDFH, "TDFH"}, + {E1000_TDFT, "TDFT"}, + {E1000_TDFHS, "TDFHS"}, + {E1000_TDFPC, "TDFPC"}, + + /* List Terminator */ + {} +}; + +/* igb_regdump - register printout routine */ +static void igb_regdump(struct e1000_hw *hw, struct igb_reg_info *reginfo) +{ + int n = 0; + char rname[16]; + u32 regs[8]; + + switch (reginfo->ofs) { + case E1000_RDLEN(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_RDLEN(n)); + break; + case E1000_RDH(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_RDH(n)); + break; + case E1000_RDT(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_RDT(n)); + break; + case E1000_RXDCTL(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_RXDCTL(n)); + break; + case E1000_RDBAL(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_RDBAL(n)); + break; + case E1000_RDBAH(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_RDBAH(n)); + break; + case E1000_TDBAL(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_TDBAL(n)); + break; + case E1000_TDBAH(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_TDBAH(n)); + break; + case E1000_TDLEN(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_TDLEN(n)); + break; + case E1000_TDH(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_TDH(n)); + break; + case E1000_TDT(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_TDT(n)); + break; + case E1000_TXDCTL(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(E1000_TXDCTL(n)); + break; + default: + pr_info("%-15s %08x\n", reginfo->name, rd32(reginfo->ofs)); + return; + } + + snprintf(rname, 16, "%s%s", reginfo->name, "[0-3]"); + pr_info("%-15s %08x %08x %08x %08x\n", rname, regs[0], regs[1], + regs[2], regs[3]); +} + +/* igb_dump - Print registers, Tx-rings and Rx-rings */ +static void igb_dump(struct igb_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct e1000_hw *hw = &adapter->hw; + struct igb_reg_info *reginfo; + struct igb_ring *tx_ring; + union e1000_adv_tx_desc *tx_desc; + struct my_u0 { __le64 a; __le64 b; } *u0; + struct igb_ring *rx_ring; + union e1000_adv_rx_desc *rx_desc; + u32 staterr; + u16 i, n; + + if (!netif_msg_hw(adapter)) + return; + + /* Print netdevice Info */ + if (netdev) { + dev_info(&adapter->pdev->dev, "Net device Info\n"); + pr_info("Device Name state trans_start\n"); + pr_info("%-15s %016lX %016lX\n", netdev->name, + netdev->state, dev_trans_start(netdev)); + } + + /* Print Registers */ + dev_info(&adapter->pdev->dev, "Register Dump\n"); + pr_info(" Register Name Value\n"); + for (reginfo = (struct igb_reg_info *)igb_reg_info_tbl; + reginfo->name; reginfo++) { + igb_regdump(hw, reginfo); + } + + /* Print TX Ring Summary */ + if (!netdev || !netif_running(netdev)) + goto exit; + + dev_info(&adapter->pdev->dev, "TX Rings Summary\n"); + pr_info("Queue [NTU] [NTC] [bi(ntc)->dma ] leng ntw timestamp\n"); + for (n = 0; n < adapter->num_tx_queues; n++) { + struct igb_tx_buffer *buffer_info; + tx_ring = adapter->tx_ring[n]; + buffer_info = &tx_ring->tx_buffer_info[tx_ring->next_to_clean]; + pr_info(" %5d %5X %5X %016llX %04X %p %016llX\n", + n, tx_ring->next_to_use, tx_ring->next_to_clean, + (u64)dma_unmap_addr(buffer_info, dma), + dma_unmap_len(buffer_info, len), + buffer_info->next_to_watch, + (u64)buffer_info->time_stamp); + } + + /* Print TX Rings */ + if (!netif_msg_tx_done(adapter)) + goto rx_ring_summary; + + dev_info(&adapter->pdev->dev, "TX Rings Dump\n"); + + /* Transmit Descriptor Formats + * + * Advanced Transmit Descriptor + * +--------------------------------------------------------------+ + * 0 | Buffer Address [63:0] | + * +--------------------------------------------------------------+ + * 8 | PAYLEN | PORTS |CC|IDX | STA | DCMD |DTYP|MAC|RSV| DTALEN | + * +--------------------------------------------------------------+ + * 63 46 45 40 39 38 36 35 32 31 24 15 0 + */ + + for (n = 0; n < adapter->num_tx_queues; n++) { + tx_ring = adapter->tx_ring[n]; + 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"); + + for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) { + const char *next_desc; + struct igb_tx_buffer *buffer_info; + tx_desc = IGB_TX_DESC(tx_ring, i); + buffer_info = &tx_ring->tx_buffer_info[i]; + u0 = (struct my_u0 *)tx_desc; + if (i == tx_ring->next_to_use && + i == tx_ring->next_to_clean) + next_desc = " NTC/U"; + else if (i == tx_ring->next_to_use) + next_desc = " NTU"; + else if (i == tx_ring->next_to_clean) + next_desc = " NTC"; + else + next_desc = ""; + + 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), + buffer_info->next_to_watch, + (u64)buffer_info->time_stamp, + buffer_info->skb, next_desc); + + if (netif_msg_pktdata(adapter) && buffer_info->skb) + print_hex_dump(KERN_INFO, "", + DUMP_PREFIX_ADDRESS, + 16, 1, buffer_info->skb->data, + dma_unmap_len(buffer_info, len), + true); + } + } + + /* Print RX Rings Summary */ +rx_ring_summary: + dev_info(&adapter->pdev->dev, "RX Rings Summary\n"); + pr_info("Queue [NTU] [NTC]\n"); + for (n = 0; n < adapter->num_rx_queues; n++) { + rx_ring = adapter->rx_ring[n]; + pr_info(" %5d %5X %5X\n", + n, rx_ring->next_to_use, rx_ring->next_to_clean); + } + + /* Print RX Rings */ + if (!netif_msg_rx_status(adapter)) + goto exit; + + dev_info(&adapter->pdev->dev, "RX Rings Dump\n"); + + /* Advanced Receive Descriptor (Read) Format + * 63 1 0 + * +-----------------------------------------------------+ + * 0 | Packet Buffer Address [63:1] |A0/NSE| + * +----------------------------------------------+------+ + * 8 | Header Buffer Address [63:1] | DD | + * +-----------------------------------------------------+ + * + * + * Advanced Receive Descriptor (Write-Back) Format + * + * 63 48 47 32 31 30 21 20 17 16 4 3 0 + * +------------------------------------------------------+ + * 0 | Packet IP |SPH| HDR_LEN | RSV|Packet| RSS | + * | Checksum Ident | | | | Type | Type | + * +------------------------------------------------------+ + * 8 | VLAN Tag | Length | Extended Error | Extended Status | + * +------------------------------------------------------+ + * 63 48 47 32 31 20 19 0 + */ + + for (n = 0; n < adapter->num_rx_queues; n++) { + rx_ring = adapter->rx_ring[n]; + 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"); + + for (i = 0; i < rx_ring->count; i++) { + const char *next_desc; + struct igb_rx_buffer *buffer_info; + buffer_info = &rx_ring->rx_buffer_info[i]; + rx_desc = IGB_RX_DESC(rx_ring, i); + u0 = (struct my_u0 *)rx_desc; + staterr = le32_to_cpu(rx_desc->wb.upper.status_error); + + if (i == rx_ring->next_to_use) + next_desc = " NTU"; + else if (i == rx_ring->next_to_clean) + next_desc = " NTC"; + else + next_desc = ""; + + if (staterr & E1000_RXD_STAT_DD) { + /* Descriptor Done */ + pr_info("%s[0x%03X] %016llX %016llX ---------------- %s\n", + "RWB", i, + le64_to_cpu(u0->a), + le64_to_cpu(u0->b), + next_desc); + } else { + pr_info("%s[0x%03X] %016llX %016llX %016llX %s\n", + "R ", i, + le64_to_cpu(u0->a), + le64_to_cpu(u0->b), + (u64)buffer_info->dma, + next_desc); + + if (netif_msg_pktdata(adapter) && + buffer_info->dma && buffer_info->page) { + print_hex_dump(KERN_INFO, "", + DUMP_PREFIX_ADDRESS, + 16, 1, + page_address(buffer_info->page) + + buffer_info->page_offset, + igb_rx_bufsz(rx_ring), true); + } + } + } + } + +exit: + return; +} + +/** + * igb_get_i2c_data - Reads the I2C SDA data bit + * @data: opaque pointer to adapter struct + * + * 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 | E1000_I2C_DATA_OE_N; + } else { + i2cctl &= ~E1000_I2C_DATA_OE_N; + i2cctl &= ~E1000_I2C_DATA_OUT; + } + + 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 | 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) +{ + struct igb_adapter *adapter = hw->back; + return adapter->netdev; +} + +/** + * igb_init_module - Driver Registration Routine + * + * igb_init_module is the first routine called when the driver is + * loaded. All it does is register with the PCI subsystem. + **/ +static int __init igb_init_module(void) +{ + int ret; + + pr_info("%s\n", igb_driver_string); + pr_info("%s\n", igb_copyright); + +#ifdef CONFIG_IGB_DCA + dca_register_notify(&dca_notifier); +#endif + ret = pci_register_driver(&igb_driver); + return ret; +} + +module_init(igb_init_module); + +/** + * igb_exit_module - Driver Exit Cleanup Routine + * + * igb_exit_module is called just before the driver is removed + * from memory. + **/ +static void __exit igb_exit_module(void) +{ +#ifdef CONFIG_IGB_DCA + dca_unregister_notify(&dca_notifier); +#endif + pci_unregister_driver(&igb_driver); +} + +module_exit(igb_exit_module); + +#define Q_IDX_82576(i) (((i & 0x1) << 3) + (i >> 1)) +/** + * igb_cache_ring_register - Descriptor ring to register mapping + * @adapter: board private structure to initialize + * + * Once we know the feature-set enabled for the device, we'll cache + * the register offset the descriptor ring is assigned to. + **/ +static void igb_cache_ring_register(struct igb_adapter *adapter) +{ + int i = 0, j = 0; + u32 rbase_offset = adapter->vfs_allocated_count; + + switch (adapter->hw.mac.type) { + case e1000_82576: + /* The queues are allocated for virtualization such that VF 0 + * is allocated queues 0 and 8, VF 1 queues 1 and 9, etc. + * In order to avoid collision we start at the first free queue + * and continue consuming queues in the same sequence + */ + if (adapter->vfs_allocated_count) { + for (; i < adapter->rss_queues; i++) + adapter->rx_ring[i]->reg_idx = rbase_offset + + Q_IDX_82576(i); + } + fallthrough; + case e1000_82575: + case e1000_82580: + case e1000_i350: + case e1000_i354: + case e1000_i210: + case e1000_i211: + default: + for (; i < adapter->num_rx_queues; i++) + adapter->rx_ring[i]->reg_idx = rbase_offset + i; + for (; j < adapter->num_tx_queues; j++) + adapter->tx_ring[j]->reg_idx = rbase_offset + j; + break; + } +} + +u32 igb_rd32(struct e1000_hw *hw, u32 reg) +{ + struct igb_adapter *igb = container_of(hw, struct igb_adapter, hw); + u8 __iomem *hw_addr = READ_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; + netdev_err(netdev, "PCIe link lost\n"); + WARN(pci_device_is_present(igb->pdev), + "igb: Failed to read reg 0x%x!\n", reg); + } + + return value; +} + +/** + * igb_write_ivar - configure ivar for given MSI-X vector + * @hw: pointer to the HW structure + * @msix_vector: vector number we are allocating to a given ring + * @index: row index of IVAR register to write within IVAR table + * @offset: column offset of in IVAR, should be multiple of 8 + * + * This function is intended to handle the writing of the IVAR register + * for adapters 82576 and newer. The IVAR table consists of 2 columns, + * each containing an cause allocation for an Rx and Tx ring, and a + * variable number of rows depending on the number of queues supported. + **/ +static void igb_write_ivar(struct e1000_hw *hw, int msix_vector, + int index, int offset) +{ + u32 ivar = array_rd32(E1000_IVAR0, index); + + /* clear any bits that are currently set */ + ivar &= ~((u32)0xFF << offset); + + /* write vector and valid bit */ + ivar |= (msix_vector | E1000_IVAR_VALID) << offset; + + array_wr32(E1000_IVAR0, index, ivar); +} + +#define IGB_N0_QUEUE -1 +static void igb_assign_vector(struct igb_q_vector *q_vector, int msix_vector) +{ + struct igb_adapter *adapter = q_vector->adapter; + struct e1000_hw *hw = &adapter->hw; + int rx_queue = IGB_N0_QUEUE; + int tx_queue = IGB_N0_QUEUE; + u32 msixbm = 0; + + if (q_vector->rx.ring) + rx_queue = q_vector->rx.ring->reg_idx; + if (q_vector->tx.ring) + tx_queue = q_vector->tx.ring->reg_idx; + + switch (hw->mac.type) { + case e1000_82575: + /* The 82575 assigns vectors using a bitmask, which matches the + * bitmask for the EICR/EIMS/EIMC registers. To assign one + * or more queues to a vector, we write the appropriate bits + * into the MSIXBM register for that vector. + */ + if (rx_queue > IGB_N0_QUEUE) + msixbm = E1000_EICR_RX_QUEUE0 << rx_queue; + if (tx_queue > IGB_N0_QUEUE) + msixbm |= E1000_EICR_TX_QUEUE0 << tx_queue; + if (!(adapter->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 + * with 8 rows. The ordering is column-major so we use the + * lower 3 bits as the row index, and the 4th bit as the + * column offset. + */ + if (rx_queue > IGB_N0_QUEUE) + igb_write_ivar(hw, msix_vector, + rx_queue & 0x7, + (rx_queue & 0x8) << 1); + if (tx_queue > IGB_N0_QUEUE) + igb_write_ivar(hw, msix_vector, + tx_queue & 0x7, + ((tx_queue & 0x8) << 1) + 8); + q_vector->eims_value = BIT(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 + * however instead of ordering column-major we have things + * ordered row-major. So we traverse the table by using + * bit 0 as the column offset, and the remaining bits as the + * row index. + */ + if (rx_queue > IGB_N0_QUEUE) + igb_write_ivar(hw, msix_vector, + rx_queue >> 1, + (rx_queue & 0x1) << 4); + if (tx_queue > IGB_N0_QUEUE) + igb_write_ivar(hw, msix_vector, + tx_queue >> 1, + ((tx_queue & 0x1) << 4) + 8); + q_vector->eims_value = BIT(msix_vector); + break; + default: + BUG(); + break; + } + + /* add q_vector eims value to global eims_enable_mask */ + adapter->eims_enable_mask |= q_vector->eims_value; + + /* configure q_vector to set itr on first interrupt */ + q_vector->set_itr = 1; +} + +/** + * igb_configure_msix - Configure MSI-X hardware + * @adapter: board private structure to initialize + * + * igb_configure_msix sets up the hardware to properly + * generate MSI-X interrupts. + **/ +static void igb_configure_msix(struct igb_adapter *adapter) +{ + u32 tmp; + int i, vector = 0; + struct e1000_hw *hw = &adapter->hw; + + adapter->eims_enable_mask = 0; + + /* set vector for other causes, i.e. link changes */ + switch (hw->mac.type) { + case e1000_82575: + tmp = rd32(E1000_CTRL_EXT); + /* enable MSI-X PBA support*/ + tmp |= E1000_CTRL_EXT_PBA_CLR; + + /* Auto-Mask interrupts upon ICR read. */ + tmp |= E1000_CTRL_EXT_EIAME; + tmp |= E1000_CTRL_EXT_IRCA; + + wr32(E1000_CTRL_EXT, tmp); + + /* enable msix_other interrupt */ + array_wr32(E1000_MSIXBM(0), vector++, E1000_EIMS_OTHER); + adapter->eims_other = E1000_EIMS_OTHER; + + break; + + case e1000_82576: + case e1000_82580: + case e1000_i350: + 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. + */ + wr32(E1000_GPIE, E1000_GPIE_MSIX_MODE | + E1000_GPIE_PBA | E1000_GPIE_EIAME | + E1000_GPIE_NSICR); + + /* enable msix_other interrupt */ + adapter->eims_other = BIT(vector); + tmp = (vector++ | E1000_IVAR_VALID) << 8; + + wr32(E1000_IVAR_MISC, tmp); + break; + default: + /* do nothing, since nothing else supports MSI-X */ + break; + } /* switch (hw->mac.type) */ + + adapter->eims_enable_mask |= adapter->eims_other; + + for (i = 0; i < adapter->num_q_vectors; i++) + igb_assign_vector(adapter->q_vector[i], vector++); + + wrfl(); +} + +/** + * igb_request_msix - Initialize MSI-X interrupts + * @adapter: board private structure to initialize + * + * igb_request_msix allocates MSI-X vectors and requests interrupts from the + * kernel. + **/ +static int igb_request_msix(struct igb_adapter *adapter) +{ + unsigned int num_q_vectors = adapter->num_q_vectors; + struct net_device *netdev = adapter->netdev; + int i, err = 0, vector = 0, free_vector = 0; + + err = request_irq(adapter->msix_entries[vector].vector, + igb_msix_other, 0, netdev->name, adapter); + if (err) + goto err_out; + + if (num_q_vectors > MAX_Q_VECTORS) { + num_q_vectors = MAX_Q_VECTORS; + dev_warn(&adapter->pdev->dev, + "The number of queue vectors (%d) is higher than max allowed (%d)\n", + adapter->num_q_vectors, MAX_Q_VECTORS); + } + for (i = 0; i < num_q_vectors; i++) { + struct igb_q_vector *q_vector = adapter->q_vector[i]; + + vector++; + + q_vector->itr_register = adapter->io_addr + E1000_EITR(vector); + + if (q_vector->rx.ring && q_vector->tx.ring) + sprintf(q_vector->name, "%s-TxRx-%u", netdev->name, + q_vector->rx.ring->queue_index); + else if (q_vector->tx.ring) + sprintf(q_vector->name, "%s-tx-%u", netdev->name, + q_vector->tx.ring->queue_index); + else if (q_vector->rx.ring) + sprintf(q_vector->name, "%s-rx-%u", netdev->name, + q_vector->rx.ring->queue_index); + else + sprintf(q_vector->name, "%s-unused", netdev->name); + + err = request_irq(adapter->msix_entries[vector].vector, + igb_msix_ring, 0, q_vector->name, + q_vector); + if (err) + goto err_free; + } + + igb_configure_msix(adapter); + return 0; + +err_free: + /* free already assigned IRQs */ + free_irq(adapter->msix_entries[free_vector++].vector, adapter); + + vector--; + for (i = 0; i < vector; i++) { + free_irq(adapter->msix_entries[free_vector++].vector, + adapter->q_vector[i]); + } +err_out: + return err; +} + +/** + * 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) +{ + 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. + */ + if (q_vector) + kfree_rcu(q_vector, rcu); +} + +/** + * igb_reset_q_vector - Reset config for interrupt vector + * @adapter: board private structure to initialize + * @v_idx: Index of vector to be reset + * + * If NAPI is enabled it will delete any references to the + * NAPI struct. This is preparation for igb_free_q_vector. + **/ +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->rx_ring[q_vector->rx.ring->queue_index] = NULL; + + netif_napi_del(&q_vector->napi); + +} + +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 + * + * This function frees the memory allocated to the q_vectors. In addition if + * NAPI is enabled it will delete any references to the NAPI struct prior + * to freeing the q_vector. + **/ +static void igb_free_q_vectors(struct igb_adapter *adapter) +{ + int v_idx = adapter->num_q_vectors; + + adapter->num_tx_queues = 0; + adapter->num_rx_queues = 0; + adapter->num_q_vectors = 0; + + 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 + * @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. + */ +static void igb_clear_interrupt_scheme(struct igb_adapter *adapter) +{ + igb_free_q_vectors(adapter); + igb_reset_interrupt_capability(adapter); +} + +/** + * 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. + **/ +static void igb_set_interrupt_capability(struct igb_adapter *adapter, bool msix) +{ + int err; + int numvecs, i; + + if (!msix) + goto msi_only; + adapter->flags |= IGB_FLAG_HAS_MSIX; + + /* Number of supported queues. */ + adapter->num_rx_queues = adapter->rss_queues; + if (adapter->vfs_allocated_count) + adapter->num_tx_queues = 1; + else + adapter->num_tx_queues = adapter->rss_queues; + + /* start with one vector for every Rx queue */ + numvecs = adapter->num_rx_queues; + + /* if Tx handler is separate add 1 for every Tx queue */ + if (!(adapter->flags & IGB_FLAG_QUEUE_PAIRS)) + numvecs += adapter->num_tx_queues; + + /* store the number of vectors reserved for queues */ + adapter->num_q_vectors = numvecs; + + /* add 1 vector for link status interrupts */ + numvecs++; + for (i = 0; i < numvecs; i++) + adapter->msix_entries[i].entry = i; + + 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) { + struct e1000_hw *hw = &adapter->hw; + /* disable iov and allow time for transactions to clear */ + pci_disable_sriov(adapter->pdev); + msleep(500); + + kfree(adapter->vf_mac_list); + adapter->vf_mac_list = NULL; + kfree(adapter->vf_data); + adapter->vf_data = NULL; + wr32(E1000_IOVCTL, E1000_IOVCTL_REUSE_VFQ); + wrfl(); + msleep(100); + dev_info(&adapter->pdev->dev, "IOV Disabled\n"); + } +#endif + adapter->vfs_allocated_count = 0; + adapter->rss_queues = 1; + adapter->flags |= IGB_FLAG_QUEUE_PAIRS; + adapter->num_rx_queues = 1; + adapter->num_tx_queues = 1; + adapter->num_q_vectors = 1; + if (!pci_enable_msi(adapter->pdev)) + adapter->flags |= IGB_FLAG_HAS_MSI; +} + +static void igb_add_ring(struct igb_ring *ring, + struct igb_ring_container *head) +{ + head->ring = ring; + head->count++; +} + +/** + * 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. + **/ +static int igb_alloc_q_vector(struct igb_adapter *adapter, + int v_count, int v_idx, + int txr_count, int txr_idx, + int rxr_count, int rxr_idx) +{ + struct igb_q_vector *q_vector; + struct igb_ring *ring; + int ring_count; + size_t size; + + /* igb only supports 1 Tx and/or 1 Rx queue per vector */ + if (txr_count > 1 || rxr_count > 1) + return -ENOMEM; + + ring_count = txr_count + rxr_count; + size = kmalloc_size_roundup(struct_size(q_vector, ring, ring_count)); + + /* allocate q_vector and rings */ + q_vector = adapter->q_vector[v_idx]; + if (!q_vector) { + q_vector = kzalloc(size, GFP_KERNEL); + } else if (size > ksize(q_vector)) { + struct igb_q_vector *new_q_vector; + + new_q_vector = kzalloc(size, GFP_KERNEL); + if (new_q_vector) + kfree_rcu(q_vector, rcu); + q_vector = new_q_vector; + } else { + memset(q_vector, 0, size); + } + if (!q_vector) + return -ENOMEM; + + /* initialize NAPI */ + netif_napi_add(adapter->netdev, &q_vector->napi, igb_poll); + + /* tie q_vector and adapter together */ + adapter->q_vector[v_idx] = q_vector; + q_vector->adapter = adapter; + + /* initialize work limits */ + q_vector->tx.work_limit = adapter->tx_work_limit; + + /* initialize ITR configuration */ + q_vector->itr_register = adapter->io_addr + E1000_EITR(0); + q_vector->itr_val = IGB_START_ITR; + + /* 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; + ring->netdev = adapter->netdev; + + /* configure backlink on ring */ + ring->q_vector = q_vector; + + /* update q_vector Tx values */ + igb_add_ring(ring, &q_vector->tx); + + /* For 82575, context index must be unique per ring. */ + if (adapter->hw.mac.type == e1000_82575) + set_bit(IGB_RING_FLAG_TX_CTX_IDX, &ring->flags); + + /* apply Tx specific ring traits */ + ring->count = adapter->tx_ring_count; + ring->queue_index = txr_idx; + + ring->cbs_enable = false; + ring->idleslope = 0; + ring->sendslope = 0; + ring->hicredit = 0; + ring->locredit = 0; + + u64_stats_init(&ring->tx_syncp); + u64_stats_init(&ring->tx_syncp2); + + /* assign ring to adapter */ + adapter->tx_ring[txr_idx] = ring; + + /* push pointer to next ring */ + ring++; + } + + if (rxr_count) { + /* assign generic ring traits */ + ring->dev = &adapter->pdev->dev; + ring->netdev = adapter->netdev; + + /* configure backlink on ring */ + ring->q_vector = q_vector; + + /* update q_vector Rx values */ + igb_add_ring(ring, &q_vector->rx); + + /* set flag indicating ring supports SCTP checksum offload */ + if (adapter->hw.mac.type >= e1000_82576) + set_bit(IGB_RING_FLAG_RX_SCTP_CSUM, &ring->flags); + + /* On i350, 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); + + /* apply Rx specific ring traits */ + 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; + } + + return 0; +} + + +/** + * igb_alloc_q_vectors - Allocate memory for interrupt vectors + * @adapter: board private structure to initialize + * + * We allocate one q_vector per queue interrupt. If allocation fails we + * return -ENOMEM. + **/ +static int igb_alloc_q_vectors(struct igb_adapter *adapter) +{ + int q_vectors = adapter->num_q_vectors; + int rxr_remaining = adapter->num_rx_queues; + int txr_remaining = adapter->num_tx_queues; + int rxr_idx = 0, txr_idx = 0, v_idx = 0; + int err; + + if (q_vectors >= (rxr_remaining + txr_remaining)) { + for (; rxr_remaining; v_idx++) { + err = igb_alloc_q_vector(adapter, q_vectors, v_idx, + 0, 0, 1, rxr_idx); + + if (err) + goto err_out; + + /* update counts and index */ + rxr_remaining--; + rxr_idx++; + } + } + + 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); + + if (err) + goto err_out; + + /* update counts and index */ + rxr_remaining -= rqpv; + txr_remaining -= tqpv; + rxr_idx++; + txr_idx++; + } + + return 0; + +err_out: + adapter->num_tx_queues = 0; + adapter->num_rx_queues = 0; + adapter->num_q_vectors = 0; + + while (v_idx--) + igb_free_q_vector(adapter, v_idx); + + return -ENOMEM; +} + +/** + * 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. + **/ +static int igb_init_interrupt_scheme(struct igb_adapter *adapter, bool msix) +{ + struct pci_dev *pdev = adapter->pdev; + int err; + + igb_set_interrupt_capability(adapter, msix); + + err = igb_alloc_q_vectors(adapter); + if (err) { + dev_err(&pdev->dev, "Unable to allocate memory for vectors\n"); + goto err_alloc_q_vectors; + } + + igb_cache_ring_register(adapter); + + return 0; + +err_alloc_q_vectors: + igb_reset_interrupt_capability(adapter); + return err; +} + +/** + * 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. + **/ +static int igb_request_irq(struct igb_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct pci_dev *pdev = adapter->pdev; + int err = 0; + + if (adapter->flags & IGB_FLAG_HAS_MSIX) { + err = igb_request_msix(adapter); + if (!err) + goto request_done; + /* fall back to MSI */ + igb_free_all_tx_resources(adapter); + igb_free_all_rx_resources(adapter); + + igb_clear_interrupt_scheme(adapter); + err = igb_init_interrupt_scheme(adapter, false); + if (err) + goto request_done; + + igb_setup_all_tx_resources(adapter); + igb_setup_all_rx_resources(adapter); + igb_configure(adapter); + } + + igb_assign_vector(adapter->q_vector[0], 0); + + if (adapter->flags & IGB_FLAG_HAS_MSI) { + err = request_irq(pdev->irq, igb_intr_msi, 0, + netdev->name, adapter); + if (!err) + goto request_done; + + /* fall back to legacy interrupts */ + igb_reset_interrupt_capability(adapter); + adapter->flags &= ~IGB_FLAG_HAS_MSI; + } + + err = request_irq(pdev->irq, igb_intr, IRQF_SHARED, + netdev->name, adapter); + + if (err) + dev_err(&pdev->dev, "Error %d getting interrupt\n", + err); + +request_done: + return err; +} + +static void igb_free_irq(struct igb_adapter *adapter) +{ + if (adapter->flags & IGB_FLAG_HAS_MSIX) { + int vector = 0, i; + + free_irq(adapter->msix_entries[vector++].vector, adapter); + + for (i = 0; i < adapter->num_q_vectors; i++) + free_irq(adapter->msix_entries[vector++].vector, + adapter->q_vector[i]); + } else { + free_irq(adapter->pdev->irq, adapter); + } +} + +/** + * igb_irq_disable - Mask off interrupt generation on the NIC + * @adapter: board private structure + **/ +static void igb_irq_disable(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + + /* we need to be careful when disabling interrupts. The VFs are also + * mapped into these registers and so clearing the bits can cause + * issues on the VF drivers so we only need to clear what we set + */ + if (adapter->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); + wr32(E1000_EIAC, regval & ~adapter->eims_enable_mask); + } + + wr32(E1000_IAM, 0); + wr32(E1000_IMC, ~0); + wrfl(); + 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 { + synchronize_irq(adapter->pdev->irq); + } +} + +/** + * igb_irq_enable - Enable default interrupt generation settings + * @adapter: board private structure + **/ +static void igb_irq_enable(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + + if (adapter->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); + wr32(E1000_EIMS, adapter->eims_enable_mask); + if (adapter->vfs_allocated_count) { + wr32(E1000_MBVFIMR, 0xFF); + ims |= E1000_IMS_VMMB; + } + wr32(E1000_IMS, ims); + } else { + wr32(E1000_IMS, IMS_ENABLE_MASK | + E1000_IMS_DRSTA); + wr32(E1000_IAM, IMS_ENABLE_MASK | + E1000_IMS_DRSTA); + } +} + +static void igb_update_mng_vlan(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u16 pf_id = adapter->vfs_allocated_count; + u16 vid = adapter->hw.mng_cookie.vlan_id; + u16 old_vid = adapter->mng_vlan_id; + + if (hw->mng_cookie.status & E1000_MNG_DHCP_COOKIE_STATUS_VLAN) { + /* add VID to filter table */ + igb_vfta_set(hw, vid, pf_id, true, true); + adapter->mng_vlan_id = vid; + } else { + adapter->mng_vlan_id = IGB_MNG_VLAN_NONE; + } + + if ((old_vid != (u16)IGB_MNG_VLAN_NONE) && + (vid != old_vid) && + !test_bit(old_vid, adapter->active_vlans)) { + /* remove VID from filter table */ + igb_vfta_set(hw, vid, pf_id, false, true); + } +} + +/** + * igb_release_hw_control - release control of the h/w to f/w + * @adapter: address of board private structure + * + * igb_release_hw_control resets CTRL_EXT:DRV_LOAD bit. + * For ASF and Pass Through versions of f/w this means that the + * driver is no longer loaded. + **/ +static void igb_release_hw_control(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 ctrl_ext; + + /* Let firmware take over control of h/w */ + ctrl_ext = rd32(E1000_CTRL_EXT); + wr32(E1000_CTRL_EXT, + ctrl_ext & ~E1000_CTRL_EXT_DRV_LOAD); +} + +/** + * igb_get_hw_control - get control of the h/w from f/w + * @adapter: address of board private structure + * + * igb_get_hw_control sets CTRL_EXT:DRV_LOAD bit. + * For ASF and Pass Through versions of f/w this means that + * the driver is loaded. + **/ +static void igb_get_hw_control(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 ctrl_ext; + + /* Let firmware know the driver has taken over */ + ctrl_ext = rd32(E1000_CTRL_EXT); + wr32(E1000_CTRL_EXT, + ctrl_ext | E1000_CTRL_EXT_DRV_LOAD); +} + +static void enable_fqtss(struct igb_adapter *adapter, bool enable) +{ + struct net_device *netdev = adapter->netdev; + struct e1000_hw *hw = &adapter->hw; + + WARN_ON(hw->mac.type != e1000_i210); + + if (enable) + adapter->flags |= IGB_FLAG_FQTSS; + else + adapter->flags &= ~IGB_FLAG_FQTSS; + + if (netif_running(netdev)) + schedule_work(&adapter->reset_task); +} + +static bool is_fqtss_enabled(struct igb_adapter *adapter) +{ + return (adapter->flags & IGB_FLAG_FQTSS) ? true : false; +} + +static void set_tx_desc_fetch_prio(struct e1000_hw *hw, int queue, + enum tx_queue_prio prio) +{ + u32 val; + + WARN_ON(hw->mac.type != e1000_i210); + WARN_ON(queue < 0 || queue > 4); + + val = rd32(E1000_I210_TXDCTL(queue)); + + if (prio == TX_QUEUE_PRIO_HIGH) + val |= E1000_TXDCTL_PRIORITY; + else + val &= ~E1000_TXDCTL_PRIORITY; + + wr32(E1000_I210_TXDCTL(queue), val); +} + +static void set_queue_mode(struct e1000_hw *hw, int queue, enum queue_mode mode) +{ + u32 val; + + WARN_ON(hw->mac.type != e1000_i210); + WARN_ON(queue < 0 || queue > 1); + + val = rd32(E1000_I210_TQAVCC(queue)); + + if (mode == QUEUE_MODE_STREAM_RESERVATION) + val |= E1000_TQAVCC_QUEUEMODE; + else + val &= ~E1000_TQAVCC_QUEUEMODE; + + wr32(E1000_I210_TQAVCC(queue), val); +} + +static bool is_any_cbs_enabled(struct igb_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) { + if (adapter->tx_ring[i]->cbs_enable) + return true; + } + + return false; +} + +static bool is_any_txtime_enabled(struct igb_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) { + if (adapter->tx_ring[i]->launchtime_enable) + return true; + } + + return false; +} + +/** + * igb_config_tx_modes - Configure "Qav Tx mode" features on igb + * @adapter: pointer to adapter struct + * @queue: queue number + * + * Configure CBS and Launchtime for a given hardware queue. + * Parameters are retrieved from the correct Tx ring, so + * igb_save_cbs_params() and igb_save_txtime_params() should be used + * for setting those correctly prior to this function being called. + **/ +static void igb_config_tx_modes(struct igb_adapter *adapter, int queue) +{ + struct net_device *netdev = adapter->netdev; + struct e1000_hw *hw = &adapter->hw; + struct igb_ring *ring; + u32 tqavcc, tqavctrl; + u16 value; + + WARN_ON(hw->mac.type != e1000_i210); + WARN_ON(queue < 0 || queue > 1); + ring = adapter->tx_ring[queue]; + + /* If any of the Qav features is enabled, configure queues as SR and + * with HIGH PRIO. If none is, then configure them with LOW PRIO and + * as SP. + */ + if (ring->cbs_enable || ring->launchtime_enable) { + set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH); + set_queue_mode(hw, queue, QUEUE_MODE_STREAM_RESERVATION); + } else { + set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_LOW); + set_queue_mode(hw, queue, QUEUE_MODE_STRICT_PRIORITY); + } + + /* If CBS is enabled, set DataTranARB and config its parameters. */ + if (ring->cbs_enable || queue == 0) { + /* i210 does not allow the queue 0 to be in the Strict + * Priority mode while the Qav mode is enabled, so, + * instead of disabling strict priority mode, we give + * queue 0 the maximum of credits possible. + * + * See section 8.12.19 of the i210 datasheet, "Note: + * Queue0 QueueMode must be set to 1b when + * TransmitMode is set to Qav." + */ + if (queue == 0 && !ring->cbs_enable) { + /* max "linkspeed" idleslope in kbps */ + ring->idleslope = 1000000; + ring->hicredit = ETH_FRAME_LEN; + } + + /* Always set data transfer arbitration to credit-based + * shaper algorithm on TQAVCTRL if CBS is enabled for any of + * the queues. + */ + tqavctrl = rd32(E1000_I210_TQAVCTRL); + tqavctrl |= E1000_TQAVCTRL_DATATRANARB; + wr32(E1000_I210_TQAVCTRL, tqavctrl); + + /* According to i210 datasheet section 7.2.7.7, we should set + * the 'idleSlope' field from TQAVCC register following the + * equation: + * + * For 100 Mbps link speed: + * + * value = BW * 0x7735 * 0.2 (E1) + * + * For 1000Mbps link speed: + * + * value = BW * 0x7735 * 2 (E2) + * + * E1 and E2 can be merged into one equation as shown below. + * Note that 'link-speed' is in Mbps. + * + * value = BW * 0x7735 * 2 * link-speed + * -------------- (E3) + * 1000 + * + * 'BW' is the percentage bandwidth out of full link speed + * which can be found with the following equation. Note that + * idleSlope here is the parameter from this function which + * is in kbps. + * + * BW = idleSlope + * ----------------- (E4) + * link-speed * 1000 + * + * That said, we can come up with a generic equation to + * calculate the value we should set it TQAVCC register by + * replacing 'BW' in E3 by E4. The resulting equation is: + * + * value = idleSlope * 0x7735 * 2 * link-speed + * ----------------- -------------- (E5) + * link-speed * 1000 1000 + * + * 'link-speed' is present in both sides of the fraction so + * it is canceled out. The final equation is the following: + * + * value = idleSlope * 61034 + * ----------------- (E6) + * 1000000 + * + * NOTE: For i210, given the above, we can see that idleslope + * is represented in 16.38431 kbps units by the value at + * the TQAVCC register (1Gbps / 61034), which reduces + * the granularity for idleslope increments. + * For instance, if you want to configure a 2576kbps + * idleslope, the value to be written on the register + * would have to be 157.23. If rounded down, you end + * up with less bandwidth available than originally + * required (~2572 kbps). If rounded up, you end up + * with a higher bandwidth (~2589 kbps). Below the + * approach we take is to always round up the + * calculated value, so the resulting bandwidth might + * be slightly higher for some configurations. + */ + value = DIV_ROUND_UP_ULL(ring->idleslope * 61034ULL, 1000000); + + tqavcc = rd32(E1000_I210_TQAVCC(queue)); + tqavcc &= ~E1000_TQAVCC_IDLESLOPE_MASK; + tqavcc |= value; + wr32(E1000_I210_TQAVCC(queue), tqavcc); + + wr32(E1000_I210_TQAVHC(queue), + 0x80000000 + ring->hicredit * 0x7735); + } else { + + /* Set idleSlope to zero. */ + tqavcc = rd32(E1000_I210_TQAVCC(queue)); + tqavcc &= ~E1000_TQAVCC_IDLESLOPE_MASK; + wr32(E1000_I210_TQAVCC(queue), tqavcc); + + /* Set hiCredit to zero. */ + wr32(E1000_I210_TQAVHC(queue), 0); + + /* If CBS is not enabled for any queues anymore, then return to + * the default state of Data Transmission Arbitration on + * TQAVCTRL. + */ + if (!is_any_cbs_enabled(adapter)) { + tqavctrl = rd32(E1000_I210_TQAVCTRL); + tqavctrl &= ~E1000_TQAVCTRL_DATATRANARB; + wr32(E1000_I210_TQAVCTRL, tqavctrl); + } + } + + /* If LaunchTime is enabled, set DataTranTIM. */ + if (ring->launchtime_enable) { + /* Always set DataTranTIM on TQAVCTRL if LaunchTime is enabled + * for any of the SR queues, and configure fetchtime delta. + * XXX NOTE: + * - LaunchTime will be enabled for all SR queues. + * - A fixed offset can be added relative to the launch + * time of all packets if configured at reg LAUNCH_OS0. + * We are keeping it as 0 for now (default value). + */ + tqavctrl = rd32(E1000_I210_TQAVCTRL); + tqavctrl |= E1000_TQAVCTRL_DATATRANTIM | + E1000_TQAVCTRL_FETCHTIME_DELTA; + wr32(E1000_I210_TQAVCTRL, tqavctrl); + } else { + /* If Launchtime is not enabled for any SR queues anymore, + * then clear DataTranTIM on TQAVCTRL and clear fetchtime delta, + * effectively disabling Launchtime. + */ + if (!is_any_txtime_enabled(adapter)) { + tqavctrl = rd32(E1000_I210_TQAVCTRL); + tqavctrl &= ~E1000_TQAVCTRL_DATATRANTIM; + tqavctrl &= ~E1000_TQAVCTRL_FETCHTIME_DELTA; + wr32(E1000_I210_TQAVCTRL, tqavctrl); + } + } + + /* XXX: In i210 controller the sendSlope and loCredit parameters from + * CBS are not configurable by software so we don't do any 'controller + * configuration' in respect to these parameters. + */ + + netdev_dbg(netdev, "Qav Tx mode: cbs %s, launchtime %s, queue %d idleslope %d sendslope %d hiCredit %d locredit %d\n", + ring->cbs_enable ? "enabled" : "disabled", + ring->launchtime_enable ? "enabled" : "disabled", + queue, + ring->idleslope, ring->sendslope, + ring->hicredit, ring->locredit); +} + +static int igb_save_txtime_params(struct igb_adapter *adapter, int queue, + bool enable) +{ + struct igb_ring *ring; + + if (queue < 0 || queue > adapter->num_tx_queues) + return -EINVAL; + + ring = adapter->tx_ring[queue]; + ring->launchtime_enable = enable; + + return 0; +} + +static int igb_save_cbs_params(struct igb_adapter *adapter, int queue, + bool enable, int idleslope, int sendslope, + int hicredit, int locredit) +{ + struct igb_ring *ring; + + if (queue < 0 || queue > adapter->num_tx_queues) + return -EINVAL; + + ring = adapter->tx_ring[queue]; + + ring->cbs_enable = enable; + ring->idleslope = idleslope; + ring->sendslope = sendslope; + ring->hicredit = hicredit; + ring->locredit = locredit; + + return 0; +} + +/** + * igb_setup_tx_mode - Switch to/from Qav Tx mode when applicable + * @adapter: pointer to adapter struct + * + * Configure TQAVCTRL register switching the controller's Tx mode + * if FQTSS mode is enabled or disabled. Additionally, will issue + * a call to igb_config_tx_modes() per queue so any previously saved + * Tx parameters are applied. + **/ +static void igb_setup_tx_mode(struct igb_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct e1000_hw *hw = &adapter->hw; + u32 val; + + /* Only i210 controller supports changing the transmission mode. */ + if (hw->mac.type != e1000_i210) + return; + + if (is_fqtss_enabled(adapter)) { + int i, max_queue; + + /* Configure TQAVCTRL register: set transmit mode to 'Qav', + * set data fetch arbitration to 'round robin', set SP_WAIT_SR + * so SP queues wait for SR ones. + */ + val = rd32(E1000_I210_TQAVCTRL); + val |= E1000_TQAVCTRL_XMIT_MODE | E1000_TQAVCTRL_SP_WAIT_SR; + val &= ~E1000_TQAVCTRL_DATAFETCHARB; + wr32(E1000_I210_TQAVCTRL, val); + + /* Configure Tx and Rx packet buffers sizes as described in + * i210 datasheet section 7.2.7.7. + */ + val = rd32(E1000_TXPBS); + val &= ~I210_TXPBSIZE_MASK; + val |= I210_TXPBSIZE_PB0_6KB | I210_TXPBSIZE_PB1_6KB | + I210_TXPBSIZE_PB2_6KB | I210_TXPBSIZE_PB3_6KB; + wr32(E1000_TXPBS, val); + + val = rd32(E1000_RXPBS); + val &= ~I210_RXPBSIZE_MASK; + val |= I210_RXPBSIZE_PB_30KB; + wr32(E1000_RXPBS, val); + + /* Section 8.12.9 states that MAX_TPKT_SIZE from DTXMXPKTSZ + * register should not exceed the buffer size programmed in + * TXPBS. The smallest buffer size programmed in TXPBS is 4kB + * so according to the datasheet we should set MAX_TPKT_SIZE to + * 4kB / 64. + * + * However, when we do so, no frame from queue 2 and 3 are + * transmitted. It seems the MAX_TPKT_SIZE should not be great + * or _equal_ to the buffer size programmed in TXPBS. For this + * reason, we set MAX_ TPKT_SIZE to (4kB - 1) / 64. + */ + val = (4096 - 1) / 64; + wr32(E1000_I210_DTXMXPKTSZ, val); + + /* Since FQTSS mode is enabled, apply any CBS configuration + * previously set. If no previous CBS configuration has been + * done, then the initial configuration is applied, which means + * CBS is disabled. + */ + max_queue = (adapter->num_tx_queues < I210_SR_QUEUES_NUM) ? + adapter->num_tx_queues : I210_SR_QUEUES_NUM; + + for (i = 0; i < max_queue; i++) { + igb_config_tx_modes(adapter, i); + } + } else { + wr32(E1000_RXPBS, I210_RXPBSIZE_DEFAULT); + wr32(E1000_TXPBS, I210_TXPBSIZE_DEFAULT); + wr32(E1000_I210_DTXMXPKTSZ, I210_DTXMXPKTSZ_DEFAULT); + + val = rd32(E1000_I210_TQAVCTRL); + /* According to Section 8.12.21, the other flags we've set when + * enabling FQTSS are not relevant when disabling FQTSS so we + * don't set they here. + */ + val &= ~E1000_TQAVCTRL_XMIT_MODE; + wr32(E1000_I210_TQAVCTRL, val); + } + + netdev_dbg(netdev, "FQTSS %s\n", (is_fqtss_enabled(adapter)) ? + "enabled" : "disabled"); +} + +/** + * igb_configure - configure the hardware for RX and TX + * @adapter: private board structure + **/ +static void igb_configure(struct igb_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + int i; + + igb_get_hw_control(adapter); + igb_set_rx_mode(netdev); + igb_setup_tx_mode(adapter); + + igb_restore_vlan(adapter); + + igb_setup_tctl(adapter); + igb_setup_mrqc(adapter); + igb_setup_rctl(adapter); + + igb_nfc_filter_restore(adapter); + igb_configure_tx(adapter); + igb_configure_rx(adapter); + + igb_rx_fifo_flush_82575(&adapter->hw); + + /* call igb_desc_unused which always leaves + * at least 1 descriptor unused to make sure + * next_to_use != next_to_clean + */ + for (i = 0; i < adapter->num_rx_queues; i++) { + struct igb_ring *ring = adapter->rx_ring[i]; + igb_alloc_rx_buffers(ring, igb_desc_unused(ring)); + } +} + +/** + * igb_power_up_link - Power up the phy/serdes link + * @adapter: address of board private structure + **/ +void igb_power_up_link(struct igb_adapter *adapter) +{ + igb_reset_phy(&adapter->hw); + + if (adapter->hw.phy.media_type == e1000_media_type_copper) + igb_power_up_phy_copper(&adapter->hw); + else + igb_power_up_serdes_link_82575(&adapter->hw); + + igb_setup_link(&adapter->hw); +} + +/** + * igb_power_down_link - Power down the phy/serdes link + * @adapter: address of board private structure + */ +static void igb_power_down_link(struct igb_adapter *adapter) +{ + if (adapter->hw.phy.media_type == e1000_media_type_copper) + igb_power_down_phy_copper_82575(&adapter->hw); + else + igb_shutdown_serdes_link_82575(&adapter->hw); +} + +/** + * igb_check_swap_media - 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 ((hw->phy.media_type != e1000_media_type_copper) && + !(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) +{ + struct e1000_hw *hw = &adapter->hw; + int i; + + /* hardware has been reset, we need to reload some things */ + igb_configure(adapter); + + clear_bit(__IGB_DOWN, &adapter->state); + + for (i = 0; i < adapter->num_q_vectors; i++) + napi_enable(&(adapter->q_vector[i]->napi)); + + if (adapter->flags & IGB_FLAG_HAS_MSIX) + igb_configure_msix(adapter); + else + igb_assign_vector(adapter->q_vector[0], 0); + + /* Clear any pending interrupts. */ + rd32(E1000_TSICR); + rd32(E1000_ICR); + igb_irq_enable(adapter); + + /* notify VFs that reset has been completed */ + if (adapter->vfs_allocated_count) { + u32 reg_data = rd32(E1000_CTRL_EXT); + + reg_data |= E1000_CTRL_EXT_PFRSTD; + wr32(E1000_CTRL_EXT, reg_data); + } + + netif_tx_start_all_queues(adapter->netdev); + + /* start the watchdog. */ + hw->mac.get_link_status = 1; + schedule_work(&adapter->watchdog_task); + + if ((adapter->flags & IGB_FLAG_EEE) && + (!hw->dev_spec._82575.eee_disable)) + adapter->eee_advert = MDIO_EEE_100TX | MDIO_EEE_1000T; + + return 0; +} + +void igb_down(struct igb_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct e1000_hw *hw = &adapter->hw; + u32 tctl, rctl; + int i; + + /* signal that we're down so the interrupt handler does not + * reschedule our watchdog timer + */ + set_bit(__IGB_DOWN, &adapter->state); + + /* disable receives in the hardware */ + rctl = rd32(E1000_RCTL); + wr32(E1000_RCTL, rctl & ~E1000_RCTL_EN); + /* flush and sleep below */ + + igb_nfc_filter_exit(adapter); + + netif_carrier_off(netdev); + netif_tx_stop_all_queues(netdev); + + /* disable transmits in the hardware */ + tctl = rd32(E1000_TCTL); + tctl &= ~E1000_TCTL_EN; + wr32(E1000_TCTL, tctl); + /* flush both disables and wait for them to finish */ + wrfl(); + usleep_range(10000, 11000); + + igb_irq_disable(adapter); + + adapter->flags &= ~IGB_FLAG_NEED_LINK_UPDATE; + + for (i = 0; i < adapter->num_q_vectors; i++) { + if (adapter->q_vector[i]) { + napi_synchronize(&adapter->q_vector[i]->napi); + napi_disable(&adapter->q_vector[i]->napi); + } + } + + del_timer_sync(&adapter->watchdog_timer); + del_timer_sync(&adapter->phy_info_timer); + + /* record the stats before reset*/ + spin_lock(&adapter->stats64_lock); + igb_update_stats(adapter); + spin_unlock(&adapter->stats64_lock); + + adapter->link_speed = 0; + adapter->link_duplex = 0; + + if (!pci_channel_offline(adapter->pdev)) + igb_reset(adapter); + + /* clear VLAN promisc flag so VFTA will be updated if necessary */ + adapter->flags &= ~IGB_FLAG_VLAN_PROMISC; + + igb_clean_all_tx_rings(adapter); + igb_clean_all_rx_rings(adapter); +#ifdef CONFIG_IGB_DCA + + /* since we reset the hardware DCA settings were cleared */ + igb_setup_dca(adapter); +#endif +} + +void igb_reinit_locked(struct igb_adapter *adapter) +{ + while (test_and_set_bit(__IGB_RESETTING, &adapter->state)) + 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 void igb_enable_mas(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 connsw = rd32(E1000_CONNSW); + + /* configure for SerDes media detect */ + if ((hw->phy.media_type == e1000_media_type_copper) && + (!(connsw & E1000_CONNSW_SERDESD))) { + connsw |= E1000_CONNSW_ENRGSRC; + connsw |= E1000_CONNSW_AUTOSENSE_EN; + wr32(E1000_CONNSW, connsw); + wrfl(); + } +} + +#ifdef CONFIG_IGB_HWMON +/** + * igb_set_i2c_bb - Init I2C interface + * @hw: pointer to hardware structure + **/ +static void igb_set_i2c_bb(struct e1000_hw *hw) +{ + u32 ctrl_ext; + s32 i2cctl; + + ctrl_ext = rd32(E1000_CTRL_EXT); + ctrl_ext |= E1000_CTRL_I2C_ENA; + wr32(E1000_CTRL_EXT, ctrl_ext); + wrfl(); + + i2cctl = rd32(E1000_I2CPARAMS); + i2cctl |= E1000_I2CBB_EN + | E1000_I2C_CLK_OE_N + | E1000_I2C_DATA_OE_N; + wr32(E1000_I2CPARAMS, i2cctl); + wrfl(); +} +#endif + +void igb_reset(struct igb_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + struct e1000_hw *hw = &adapter->hw; + struct e1000_mac_info *mac = &hw->mac; + struct e1000_fc_info *fc = &hw->fc; + u32 pba, hwm; + + /* Repartition Pba for greater than 9k mtu + * To take effect CTRL.RST is required. + */ + switch (mac->type) { + case e1000_i350: + case e1000_i354: + case e1000_82580: + pba = rd32(E1000_RXPBS); + pba = igb_rxpbs_adjust_82580(pba); + break; + case e1000_82576: + pba = rd32(E1000_RXPBS); + pba &= E1000_RXPBS_SIZE_MASK_82576; + break; + case e1000_82575: + case e1000_i210: + case e1000_i211: + default: + pba = E1000_PBA_34K; + break; + } + + if (mac->type == e1000_82575) { + u32 min_rx_space, min_tx_space, needed_tx_space; + + /* write Rx PBA so that hardware can report correct Tx PBA */ + wr32(E1000_PBA, pba); + + /* To maintain wire speed transmits, the Tx FIFO should be + * large enough to accommodate two full transmit packets, + * rounded up to the next 1KB and expressed in KB. Likewise, + * the Rx FIFO should be large enough to accommodate at least + * one full receive packet and is similarly rounded up and + * expressed in KB. + */ + min_rx_space = DIV_ROUND_UP(MAX_JUMBO_FRAME_SIZE, 1024); + + /* The Tx FIFO also stores 16 bytes of information about the Tx + * but don't include Ethernet FCS because hardware appends it. + * We only need to round down to the nearest 512 byte block + * count since the value we care about is 2 frames, not 1. + */ + min_tx_space = adapter->max_frame_size; + min_tx_space += sizeof(union e1000_adv_tx_desc) - ETH_FCS_LEN; + min_tx_space = DIV_ROUND_UP(min_tx_space, 512); + + /* upper 16 bits has Tx packet buffer allocation size in KB */ + needed_tx_space = min_tx_space - (rd32(E1000_PBA) >> 16); + + /* If current Tx allocation is less than the min Tx FIFO size, + * and the min Tx FIFO size is less than the current Rx FIFO + * allocation, take space away from current Rx allocation. + */ + if (needed_tx_space < pba) { + pba -= needed_tx_space; + + /* if short on Rx space, Rx wins and must trump Tx + * adjustment + */ + if (pba < min_rx_space) + pba = min_rx_space; + } + + /* adjust PBA for jumbo frames */ + wr32(E1000_PBA, pba); + } + + /* flow control settings + * The high water mark must be low enough to fit one full frame + * after transmitting the pause frame. As such we must have enough + * space to allow for us to complete our current transmit and then + * receive the frame that is in progress from the link partner. + * Set it to: + * - the full Rx FIFO size minus one full Tx plus one full Rx frame + */ + hwm = (pba << 10) - (adapter->max_frame_size + MAX_JUMBO_FRAME_SIZE); + + fc->high_water = hwm & 0xFFFFFFF0; /* 16-byte granularity */ + fc->low_water = fc->high_water - 16; + fc->pause_time = 0xFFFF; + fc->send_xon = 1; + fc->current_mode = fc->requested_mode; + + /* disable receive for all VFs and wait one second */ + if (adapter->vfs_allocated_count) { + int i; + + for (i = 0 ; i < adapter->vfs_allocated_count; i++) + adapter->vf_data[i].flags &= IGB_VF_FLAG_PF_SET_MAC; + + /* ping all the active vfs to let them know we are going down */ + igb_ping_all_vfs(adapter); + + /* disable transmits and receives */ + wr32(E1000_VFRE, 0); + wr32(E1000_VFTE, 0); + } + + /* Allow time for pending master requests to run */ + hw->mac.ops.reset_hw(hw); + wr32(E1000_WUC, 0); + + if (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 ((mac->type == e1000_82575 || mac->type == e1000_i350) && + (adapter->flags & IGB_FLAG_MAS_ENABLE)) { + igb_enable_mas(adapter); + } + if (hw->mac.ops.init_hw(hw)) + dev_err(&pdev->dev, "Hardware Error\n"); + + /* RAR registers were cleared during init_hw, clear mac table */ + igb_flush_mac_table(adapter); + __dev_uc_unsync(adapter->netdev, NULL); + + /* Recover default RAR entry */ + igb_set_default_mac_filter(adapter); + + /* 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) + igb_set_i2c_bb(hw); + 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, true, true); + break; + case e1000_i354: + igb_set_eee_i354(hw, true, true); + break; + default: + break; + } + } + if (!netif_running(adapter->netdev)) + igb_power_down_link(adapter); + + igb_update_mng_vlan(adapter); + + /* Enable h/w to recognize an 802.1Q VLAN Ethernet packet */ + wr32(E1000_VET, ETHERNET_IEEE_VLAN_TYPE); + + /* Re-enable PTP, where applicable. */ + if (adapter->ptp_flags & IGB_PTP_ENABLED) + igb_ptp_reset(adapter); + + igb_get_phy_info(hw); +} + +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. + */ + if (features & NETIF_F_HW_VLAN_CTAG_RX) + features |= NETIF_F_HW_VLAN_CTAG_TX; + else + features &= ~NETIF_F_HW_VLAN_CTAG_TX; + + return features; +} + +static int igb_set_features(struct net_device *netdev, + netdev_features_t features) +{ + netdev_features_t changed = netdev->features ^ features; + struct igb_adapter *adapter = netdev_priv(netdev); + + if (changed & NETIF_F_HW_VLAN_CTAG_RX) + igb_vlan_mode(netdev, features); + + if (!(changed & (NETIF_F_RXALL | NETIF_F_NTUPLE))) + return 0; + + if (!(features & NETIF_F_NTUPLE)) { + struct hlist_node *node2; + struct igb_nfc_filter *rule; + + spin_lock(&adapter->nfc_lock); + hlist_for_each_entry_safe(rule, node2, + &adapter->nfc_filter_list, nfc_node) { + igb_erase_filter(adapter, rule); + hlist_del(&rule->nfc_node); + kfree(rule); + } + spin_unlock(&adapter->nfc_lock); + adapter->nfc_filter_count = 0; + } + + netdev->features = features; + + if (netif_running(netdev)) + igb_reinit_locked(adapter); + else + igb_reset(adapter); + + return 1; +} + +static int igb_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, u16 vid, + u16 flags, + struct netlink_ext_ack *extack) +{ + /* guarantee we can provide a unique filter for the unicast address */ + if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) { + struct igb_adapter *adapter = netdev_priv(dev); + int vfn = adapter->vfs_allocated_count; + + if (netdev_uc_count(dev) >= igb_available_rars(adapter, vfn)) + return -ENOMEM; + } + + return ndo_dflt_fdb_add(ndm, tb, dev, addr, vid, flags); +} + +#define IGB_MAX_MAC_HDR_LEN 127 +#define IGB_MAX_NETWORK_HDR_LEN 511 + +static netdev_features_t +igb_features_check(struct sk_buff *skb, struct net_device *dev, + netdev_features_t features) +{ + unsigned int network_hdr_len, mac_hdr_len; + + /* Make certain the headers can be described by a context descriptor */ + mac_hdr_len = skb_network_header(skb) - skb->data; + if (unlikely(mac_hdr_len > IGB_MAX_MAC_HDR_LEN)) + return features & ~(NETIF_F_HW_CSUM | + NETIF_F_SCTP_CRC | + NETIF_F_GSO_UDP_L4 | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_TSO | + NETIF_F_TSO6); + + network_hdr_len = skb_checksum_start(skb) - skb_network_header(skb); + if (unlikely(network_hdr_len > IGB_MAX_NETWORK_HDR_LEN)) + return features & ~(NETIF_F_HW_CSUM | + NETIF_F_SCTP_CRC | + NETIF_F_GSO_UDP_L4 | + NETIF_F_TSO | + NETIF_F_TSO6); + + /* We can only support IPV4 TSO in tunnels if we can mangle the + * inner IP ID field, so strip TSO if MANGLEID is not supported. + */ + if (skb->encapsulation && !(features & NETIF_F_TSO_MANGLEID)) + features &= ~NETIF_F_TSO; + + return features; +} + +static void igb_offload_apply(struct igb_adapter *adapter, s32 queue) +{ + if (!is_fqtss_enabled(adapter)) { + enable_fqtss(adapter, true); + return; + } + + igb_config_tx_modes(adapter, queue); + + if (!is_any_cbs_enabled(adapter) && !is_any_txtime_enabled(adapter)) + enable_fqtss(adapter, false); +} + +static int igb_offload_cbs(struct igb_adapter *adapter, + struct tc_cbs_qopt_offload *qopt) +{ + struct e1000_hw *hw = &adapter->hw; + int err; + + /* CBS offloading is only supported by i210 controller. */ + if (hw->mac.type != e1000_i210) + return -EOPNOTSUPP; + + /* CBS offloading is only supported by queue 0 and queue 1. */ + if (qopt->queue < 0 || qopt->queue > 1) + return -EINVAL; + + err = igb_save_cbs_params(adapter, qopt->queue, qopt->enable, + qopt->idleslope, qopt->sendslope, + qopt->hicredit, qopt->locredit); + if (err) + return err; + + igb_offload_apply(adapter, qopt->queue); + + return 0; +} + +#define ETHER_TYPE_FULL_MASK ((__force __be16)~0) +#define VLAN_PRIO_FULL_MASK (0x07) + +static int igb_parse_cls_flower(struct igb_adapter *adapter, + struct flow_cls_offload *f, + int traffic_class, + struct igb_nfc_filter *input) +{ + struct flow_rule *rule = flow_cls_offload_flow_rule(f); + struct flow_dissector *dissector = rule->match.dissector; + struct netlink_ext_ack *extack = f->common.extack; + + if (dissector->used_keys & + ~(BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN))) { + NL_SET_ERR_MSG_MOD(extack, + "Unsupported key used, only BASIC, CONTROL, ETH_ADDRS and VLAN are supported"); + return -EOPNOTSUPP; + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_match_eth_addrs match; + + flow_rule_match_eth_addrs(rule, &match); + if (!is_zero_ether_addr(match.mask->dst)) { + if (!is_broadcast_ether_addr(match.mask->dst)) { + NL_SET_ERR_MSG_MOD(extack, "Only full masks are supported for destination MAC address"); + return -EINVAL; + } + + input->filter.match_flags |= + IGB_FILTER_FLAG_DST_MAC_ADDR; + ether_addr_copy(input->filter.dst_addr, match.key->dst); + } + + if (!is_zero_ether_addr(match.mask->src)) { + if (!is_broadcast_ether_addr(match.mask->src)) { + NL_SET_ERR_MSG_MOD(extack, "Only full masks are supported for source MAC address"); + return -EINVAL; + } + + input->filter.match_flags |= + IGB_FILTER_FLAG_SRC_MAC_ADDR; + ether_addr_copy(input->filter.src_addr, match.key->src); + } + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; + + flow_rule_match_basic(rule, &match); + if (match.mask->n_proto) { + if (match.mask->n_proto != ETHER_TYPE_FULL_MASK) { + NL_SET_ERR_MSG_MOD(extack, "Only full mask is supported for EtherType filter"); + return -EINVAL; + } + + input->filter.match_flags |= IGB_FILTER_FLAG_ETHER_TYPE; + input->filter.etype = match.key->n_proto; + } + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; + + flow_rule_match_vlan(rule, &match); + if (match.mask->vlan_priority) { + if (match.mask->vlan_priority != VLAN_PRIO_FULL_MASK) { + NL_SET_ERR_MSG_MOD(extack, "Only full mask is supported for VLAN priority"); + return -EINVAL; + } + + input->filter.match_flags |= IGB_FILTER_FLAG_VLAN_TCI; + input->filter.vlan_tci = + (__force __be16)match.key->vlan_priority; + } + } + + input->action = traffic_class; + input->cookie = f->cookie; + + return 0; +} + +static int igb_configure_clsflower(struct igb_adapter *adapter, + struct flow_cls_offload *cls_flower) +{ + struct netlink_ext_ack *extack = cls_flower->common.extack; + struct igb_nfc_filter *filter, *f; + int err, tc; + + tc = tc_classid_to_hwtc(adapter->netdev, cls_flower->classid); + if (tc < 0) { + NL_SET_ERR_MSG_MOD(extack, "Invalid traffic class"); + return -EINVAL; + } + + filter = kzalloc(sizeof(*filter), GFP_KERNEL); + if (!filter) + return -ENOMEM; + + err = igb_parse_cls_flower(adapter, cls_flower, tc, filter); + if (err < 0) + goto err_parse; + + spin_lock(&adapter->nfc_lock); + + hlist_for_each_entry(f, &adapter->nfc_filter_list, nfc_node) { + if (!memcmp(&f->filter, &filter->filter, sizeof(f->filter))) { + err = -EEXIST; + NL_SET_ERR_MSG_MOD(extack, + "This filter is already set in ethtool"); + goto err_locked; + } + } + + hlist_for_each_entry(f, &adapter->cls_flower_list, nfc_node) { + if (!memcmp(&f->filter, &filter->filter, sizeof(f->filter))) { + err = -EEXIST; + NL_SET_ERR_MSG_MOD(extack, + "This filter is already set in cls_flower"); + goto err_locked; + } + } + + err = igb_add_filter(adapter, filter); + if (err < 0) { + NL_SET_ERR_MSG_MOD(extack, "Could not add filter to the adapter"); + goto err_locked; + } + + hlist_add_head(&filter->nfc_node, &adapter->cls_flower_list); + + spin_unlock(&adapter->nfc_lock); + + return 0; + +err_locked: + spin_unlock(&adapter->nfc_lock); + +err_parse: + kfree(filter); + + return err; +} + +static int igb_delete_clsflower(struct igb_adapter *adapter, + struct flow_cls_offload *cls_flower) +{ + struct igb_nfc_filter *filter; + int err; + + spin_lock(&adapter->nfc_lock); + + hlist_for_each_entry(filter, &adapter->cls_flower_list, nfc_node) + if (filter->cookie == cls_flower->cookie) + break; + + if (!filter) { + err = -ENOENT; + goto out; + } + + err = igb_erase_filter(adapter, filter); + if (err < 0) + goto out; + + hlist_del(&filter->nfc_node); + kfree(filter); + +out: + spin_unlock(&adapter->nfc_lock); + + return err; +} + +static int igb_setup_tc_cls_flower(struct igb_adapter *adapter, + struct flow_cls_offload *cls_flower) +{ + switch (cls_flower->command) { + case FLOW_CLS_REPLACE: + return igb_configure_clsflower(adapter, cls_flower); + case FLOW_CLS_DESTROY: + return igb_delete_clsflower(adapter, cls_flower); + case FLOW_CLS_STATS: + return -EOPNOTSUPP; + default: + return -EOPNOTSUPP; + } +} + +static int igb_setup_tc_block_cb(enum tc_setup_type type, void *type_data, + void *cb_priv) +{ + struct igb_adapter *adapter = cb_priv; + + if (!tc_cls_can_offload_and_chain0(adapter->netdev, type_data)) + return -EOPNOTSUPP; + + switch (type) { + case TC_SETUP_CLSFLOWER: + return igb_setup_tc_cls_flower(adapter, type_data); + + default: + return -EOPNOTSUPP; + } +} + +static int igb_offload_txtime(struct igb_adapter *adapter, + struct tc_etf_qopt_offload *qopt) +{ + struct e1000_hw *hw = &adapter->hw; + int err; + + /* Launchtime offloading is only supported by i210 controller. */ + if (hw->mac.type != e1000_i210) + return -EOPNOTSUPP; + + /* Launchtime offloading is only supported by queues 0 and 1. */ + if (qopt->queue < 0 || qopt->queue > 1) + return -EINVAL; + + err = igb_save_txtime_params(adapter, qopt->queue, qopt->enable); + if (err) + return err; + + igb_offload_apply(adapter, qopt->queue); + + return 0; +} + +static int igb_tc_query_caps(struct igb_adapter *adapter, + struct tc_query_caps_base *base) +{ + switch (base->type) { + case TC_SETUP_QDISC_TAPRIO: { + struct tc_taprio_caps *caps = base->caps; + + caps->broken_mqprio = true; + + return 0; + } + default: + return -EOPNOTSUPP; + } +} + +static LIST_HEAD(igb_block_cb_list); + +static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) +{ + struct igb_adapter *adapter = netdev_priv(dev); + + switch (type) { + case TC_QUERY_CAPS: + return igb_tc_query_caps(adapter, type_data); + case TC_SETUP_QDISC_CBS: + return igb_offload_cbs(adapter, type_data); + case TC_SETUP_BLOCK: + return flow_block_cb_setup_simple(type_data, + &igb_block_cb_list, + igb_setup_tc_block_cb, + adapter, adapter, true); + + case TC_SETUP_QDISC_ETF: + return igb_offload_txtime(adapter, type_data); + + default: + return -EOPNOTSUPP; + } +} + +static int igb_xdp_setup(struct net_device *dev, struct netdev_bpf *bpf) +{ + int i, frame_size = dev->mtu + IGB_ETH_PKT_HDR_PAD; + struct igb_adapter *adapter = netdev_priv(dev); + struct bpf_prog *prog = bpf->prog, *old_prog; + bool running = netif_running(dev); + bool need_reset; + + /* verify igb ring attributes are sufficient for XDP */ + for (i = 0; i < adapter->num_rx_queues; i++) { + struct igb_ring *ring = adapter->rx_ring[i]; + + if (frame_size > igb_rx_bufsz(ring)) { + NL_SET_ERR_MSG_MOD(bpf->extack, + "The RX buffer size is too small for the frame size"); + netdev_warn(dev, "XDP RX buffer size %d is too small for the frame size %d\n", + igb_rx_bufsz(ring), frame_size); + return -EINVAL; + } + } + + old_prog = xchg(&adapter->xdp_prog, prog); + need_reset = (!!prog != !!old_prog); + + /* device is up and bpf is added/removed, must setup the RX queues */ + if (need_reset && running) { + igb_close(dev); + } else { + for (i = 0; i < adapter->num_rx_queues; i++) + (void)xchg(&adapter->rx_ring[i]->xdp_prog, + adapter->xdp_prog); + } + + if (old_prog) + bpf_prog_put(old_prog); + + /* bpf is just replaced, RXQ and MTU are already setup */ + if (!need_reset) { + return 0; + } else { + if (prog) + xdp_features_set_redirect_target(dev, true); + else + xdp_features_clear_redirect_target(dev); + } + + if (running) + igb_open(dev); + + return 0; +} + +static int igb_xdp(struct net_device *dev, struct netdev_bpf *xdp) +{ + switch (xdp->command) { + case XDP_SETUP_PROG: + return igb_xdp_setup(dev, xdp); + default: + return -EINVAL; + } +} + +static void igb_xdp_ring_update_tail(struct igb_ring *ring) +{ + /* Force memory writes to complete before letting h/w know there + * are new descriptors to fetch. + */ + wmb(); + writel(ring->next_to_use, ring->tail); +} + +static struct igb_ring *igb_xdp_tx_queue_mapping(struct igb_adapter *adapter) +{ + unsigned int r_idx = smp_processor_id(); + + if (r_idx >= adapter->num_tx_queues) + r_idx = r_idx % adapter->num_tx_queues; + + return adapter->tx_ring[r_idx]; +} + +static int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp) +{ + struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp); + int cpu = smp_processor_id(); + struct igb_ring *tx_ring; + struct netdev_queue *nq; + u32 ret; + + if (unlikely(!xdpf)) + return IGB_XDP_CONSUMED; + + /* During program transitions its possible adapter->xdp_prog is assigned + * but ring has not been configured yet. In this case simply abort xmit. + */ + tx_ring = adapter->xdp_prog ? igb_xdp_tx_queue_mapping(adapter) : NULL; + if (unlikely(!tx_ring)) + return IGB_XDP_CONSUMED; + + nq = txring_txq(tx_ring); + __netif_tx_lock(nq, cpu); + /* Avoid transmit queue timeout since we share it with the slow path */ + txq_trans_cond_update(nq); + ret = igb_xmit_xdp_ring(adapter, tx_ring, xdpf); + __netif_tx_unlock(nq); + + return ret; +} + +static int igb_xdp_xmit(struct net_device *dev, int n, + struct xdp_frame **frames, u32 flags) +{ + struct igb_adapter *adapter = netdev_priv(dev); + int cpu = smp_processor_id(); + struct igb_ring *tx_ring; + struct netdev_queue *nq; + int nxmit = 0; + int i; + + if (unlikely(test_bit(__IGB_DOWN, &adapter->state))) + return -ENETDOWN; + + if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) + return -EINVAL; + + /* During program transitions its possible adapter->xdp_prog is assigned + * but ring has not been configured yet. In this case simply abort xmit. + */ + tx_ring = adapter->xdp_prog ? igb_xdp_tx_queue_mapping(adapter) : NULL; + if (unlikely(!tx_ring)) + return -ENXIO; + + nq = txring_txq(tx_ring); + __netif_tx_lock(nq, cpu); + + /* Avoid transmit queue timeout since we share it with the slow path */ + txq_trans_cond_update(nq); + + for (i = 0; i < n; i++) { + struct xdp_frame *xdpf = frames[i]; + int err; + + err = igb_xmit_xdp_ring(adapter, tx_ring, xdpf); + if (err != IGB_XDP_TX) + break; + nxmit++; + } + + __netif_tx_unlock(nq); + + if (unlikely(flags & XDP_XMIT_FLUSH)) + igb_xdp_ring_update_tail(tx_ring); + + return nxmit; +} + +static const struct net_device_ops igb_netdev_ops = { + .ndo_open = igb_open, + .ndo_stop = igb_close, + .ndo_start_xmit = igb_xmit_frame, + .ndo_get_stats64 = igb_get_stats64, + .ndo_set_rx_mode = igb_set_rx_mode, + .ndo_set_mac_address = igb_set_mac, + .ndo_change_mtu = igb_change_mtu, + .ndo_eth_ioctl = igb_ioctl, + .ndo_tx_timeout = igb_tx_timeout, + .ndo_validate_addr = eth_validate_addr, + .ndo_vlan_rx_add_vid = igb_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = igb_vlan_rx_kill_vid, + .ndo_set_vf_mac = igb_ndo_set_vf_mac, + .ndo_set_vf_vlan = igb_ndo_set_vf_vlan, + .ndo_set_vf_rate = igb_ndo_set_vf_bw, + .ndo_set_vf_spoofchk = igb_ndo_set_vf_spoofchk, + .ndo_set_vf_trust = igb_ndo_set_vf_trust, + .ndo_get_vf_config = igb_ndo_get_vf_config, + .ndo_fix_features = igb_fix_features, + .ndo_set_features = igb_set_features, + .ndo_fdb_add = igb_ndo_fdb_add, + .ndo_features_check = igb_features_check, + .ndo_setup_tc = igb_setup_tc, + .ndo_bpf = igb_xdp, + .ndo_xdp_xmit = igb_xdp_xmit, +}; + +/** + * igb_set_fw_version - Configure version string for ethtool + * @adapter: adapter struct + **/ +void igb_set_fw_version(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + struct e1000_fw_version fw; + + igb_get_fw_version(hw, &fw); + + switch (hw->mac.type) { + case e1000_i210: + case e1000_i211: + 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; + } + fallthrough; + default: + /* if option is rom valid, display its version too */ + if (fw.or_valid) { + snprintf(adapter->fw_version, + sizeof(adapter->fw_version), + "%d.%d, 0x%08x, %d.%d.%d", + fw.eep_major, fw.eep_minor, fw.etrack_id, + fw.or_major, fw.or_build, fw.or_patch); + /* no option rom */ + } 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); + } else { + snprintf(adapter->fw_version, + sizeof(adapter->fw_version), + "%d.%d.%d", + fw.eep_major, fw.eep_minor, fw.eep_build); + } + break; + } +} + +/** + * 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 structure 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; + strscpy(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 + * + * 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) +{ + struct net_device *netdev; + struct igb_adapter *adapter; + struct e1000_hw *hw; + u16 eeprom_data = 0; + s32 ret_val; + static int global_quad_port_a; /* global quad port a indication */ + const struct e1000_info *ei = igb_info_tbl[ent->driver_data]; + u8 part_str[E1000_PBANUM_LENGTH]; + int err; + + /* Catch broken hardware that put the wrong VF device ID in + * the PCIe SR-IOV capability. + */ + if (pdev->is_virtfn) { + WARN(1, KERN_ERR "%s (%x:%x) should not be a VF!\n", + pci_name(pdev), pdev->vendor, pdev->device); + return -EINVAL; + } + + err = pci_enable_device_mem(pdev); + if (err) + return err; + + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (err) { + dev_err(&pdev->dev, + "No usable DMA configuration, aborting\n"); + goto err_dma; + } + + err = pci_request_mem_regions(pdev, igb_driver_name); + if (err) + goto err_pci_reg; + + pci_set_master(pdev); + pci_save_state(pdev); + + err = -ENOMEM; + netdev = alloc_etherdev_mq(sizeof(struct igb_adapter), + IGB_MAX_TX_QUEUES); + if (!netdev) + goto err_alloc_etherdev; + + SET_NETDEV_DEV(netdev, &pdev->dev); + + pci_set_drvdata(pdev, netdev); + adapter = netdev_priv(netdev); + adapter->netdev = netdev; + adapter->pdev = pdev; + hw = &adapter->hw; + hw->back = adapter; + adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE); + + err = -EIO; + adapter->io_addr = pci_iomap(pdev, 0, 0); + if (!adapter->io_addr) + goto err_ioremap; + /* hw->hw_addr can be altered, we'll use adapter->io_addr for unmap */ + hw->hw_addr = adapter->io_addr; + + netdev->netdev_ops = &igb_netdev_ops; + igb_set_ethtool_ops(netdev); + netdev->watchdog_timeo = 5 * HZ; + + strncpy(netdev->name, pci_name(pdev), sizeof(netdev->name) - 1); + + netdev->mem_start = pci_resource_start(pdev, 0); + netdev->mem_end = pci_resource_end(pdev, 0); + + /* PCI config space info */ + hw->vendor_id = pdev->vendor; + hw->device_id = pdev->device; + hw->revision_id = pdev->revision; + hw->subsystem_vendor_id = pdev->subsystem_vendor; + hw->subsystem_device_id = pdev->subsystem_device; + + /* Copy the default MAC, PHY and NVM function pointers */ + memcpy(&hw->mac.ops, ei->mac_ops, sizeof(hw->mac.ops)); + memcpy(&hw->phy.ops, ei->phy_ops, sizeof(hw->phy.ops)); + memcpy(&hw->nvm.ops, ei->nvm_ops, sizeof(hw->nvm.ops)); + /* Initialize skew-specific constants */ + err = ei->get_invariants(hw); + if (err) + goto err_sw_init; + + /* setup the private structure */ + err = igb_sw_init(adapter); + if (err) + goto err_sw_init; + + igb_get_bus_info_pcie(hw); + + hw->phy.autoneg_wait_to_complete = false; + + /* Copper options */ + if (hw->phy.media_type == e1000_media_type_copper) { + hw->phy.mdix = AUTO_ALL_MODES; + hw->phy.disable_polarity_correction = false; + hw->phy.ms_type = e1000_ms_hw_default; + } + + if (igb_check_reset_block(hw)) + dev_info(&pdev->dev, + "PHY reset is blocked due to SOL/IDER session.\n"); + + /* features is initialized to 0 in allocation, it might have bits + * set by igb_sw_init so we should use an or instead of an + * assignment. + */ + netdev->features |= NETIF_F_SG | + NETIF_F_TSO | + NETIF_F_TSO6 | + NETIF_F_RXHASH | + NETIF_F_RXCSUM | + NETIF_F_HW_CSUM; + + if (hw->mac.type >= e1000_82576) + netdev->features |= NETIF_F_SCTP_CRC | NETIF_F_GSO_UDP_L4; + + if (hw->mac.type >= e1000_i350) + netdev->features |= NETIF_F_HW_TC; + +#define IGB_GSO_PARTIAL_FEATURES (NETIF_F_GSO_GRE | \ + NETIF_F_GSO_GRE_CSUM | \ + NETIF_F_GSO_IPXIP4 | \ + NETIF_F_GSO_IPXIP6 | \ + NETIF_F_GSO_UDP_TUNNEL | \ + NETIF_F_GSO_UDP_TUNNEL_CSUM) + + netdev->gso_partial_features = IGB_GSO_PARTIAL_FEATURES; + netdev->features |= NETIF_F_GSO_PARTIAL | IGB_GSO_PARTIAL_FEATURES; + + /* copy netdev features into list of user selectable features */ + netdev->hw_features |= netdev->features | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_RXALL; + + if (hw->mac.type >= e1000_i350) + netdev->hw_features |= NETIF_F_NTUPLE; + + netdev->features |= NETIF_F_HIGHDMA; + + netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID; + netdev->mpls_features |= NETIF_F_HW_CSUM; + netdev->hw_enc_features |= netdev->vlan_features; + + /* set this bit last since it cannot be part of vlan_features */ + netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_TX; + + netdev->priv_flags |= IFF_SUPP_NOFCS; + + netdev->priv_flags |= IFF_UNICAST_FLT; + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT; + + /* MTU range: 68 - 9216 */ + netdev->min_mtu = ETH_MIN_MTU; + netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE; + + adapter->en_mng_pt = igb_enable_mng_pass_thru(hw); + + /* before reading the NVM, reset the controller to put the device in a + * known good starting state + */ + hw->mac.ops.reset_hw(hw); + + /* make sure the NVM is good , i211/i210 parts can have special NVM + * that doesn't contain a checksum + */ + 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; + } + + if (eth_platform_get_mac_address(&pdev->dev, hw->mac.addr)) { + /* copy the MAC address out of the NVM */ + if (hw->mac.ops.read_mac_addr(hw)) + dev_err(&pdev->dev, "NVM Read Error\n"); + } + + eth_hw_addr_set(netdev, hw->mac.addr); + + if (!is_valid_ether_addr(netdev->dev_addr)) { + dev_err(&pdev->dev, "Invalid MAC Address\n"); + err = -EIO; + goto err_eeprom; + } + + igb_set_default_mac_filter(adapter); + + /* 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); + } + + timer_setup(&adapter->watchdog_timer, igb_watchdog, 0); + timer_setup(&adapter->phy_info_timer, igb_update_phy_info, 0); + + INIT_WORK(&adapter->reset_task, igb_reset_task); + INIT_WORK(&adapter->watchdog_task, igb_watchdog_task); + + /* Initialize link properties that are user-changeable */ + adapter->fc_autoneg = true; + hw->mac.autoneg = true; + hw->phy.autoneg_advertised = 0x2f; + + hw->fc.requested_mode = e1000_fc_default; + hw->fc.current_mode = e1000_fc_default; + + igb_validate_mdi_setting(hw); + + /* By default, support wake on port A */ + if (hw->bus.func == 0) + adapter->flags |= IGB_FLAG_WOL_SUPPORTED; + + /* 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); + else if (hw->bus.func == 1) + hw->nvm.ops.read(hw, NVM_INIT_CONTROL3_PORT_B, 1, &eeprom_data); + + if (eeprom_data & IGB_EEPROM_APME) + adapter->flags |= IGB_FLAG_WOL_SUPPORTED; + + /* now that we have the eeprom settings, apply the special cases where + * the eeprom may be wrong or the board simply won't support wake on + * lan on a particular port + */ + switch (pdev->device) { + case E1000_DEV_ID_82575GB_QUAD_COPPER: + adapter->flags &= ~IGB_FLAG_WOL_SUPPORTED; + break; + case E1000_DEV_ID_82575EB_FIBER_SERDES: + case E1000_DEV_ID_82576_FIBER: + case E1000_DEV_ID_82576_SERDES: + /* Wake events only supported on port A for dual fiber + * regardless of eeprom setting + */ + if (rd32(E1000_STATUS) & E1000_STATUS_FUNC_1) + adapter->flags &= ~IGB_FLAG_WOL_SUPPORTED; + break; + case E1000_DEV_ID_82576_QUAD_COPPER: + case E1000_DEV_ID_82576_QUAD_COPPER_ET2: + /* if quad port adapter, disable WoL on all but port A */ + if (global_quad_port_a != 0) + adapter->flags &= ~IGB_FLAG_WOL_SUPPORTED; + else + adapter->flags |= IGB_FLAG_QUAD_PORT_A; + /* Reset for multiple quad port adapters */ + if (++global_quad_port_a == 4) + global_quad_port_a = 0; + break; + default: + /* If the device can't wake, don't set software support */ + if (!device_can_wakeup(&adapter->pdev->dev)) + adapter->flags &= ~IGB_FLAG_WOL_SUPPORTED; + } + + /* initialize the wol settings based on the eeprom settings */ + if (adapter->flags & IGB_FLAG_WOL_SUPPORTED) + adapter->wol |= E1000_WUFC_MAG; + + /* Some vendors want WoL disabled by default, but still supported */ + if ((hw->mac.type == e1000_i350) && + (pdev->subsystem_vendor == PCI_VENDOR_ID_HP)) { + adapter->flags |= IGB_FLAG_WOL_SUPPORTED; + adapter->wol = 0; + } + + /* Some vendors want the ability to Use the EEPROM setting as + * enable/disable only, and not for capability + */ + if (((hw->mac.type == e1000_i350) || + (hw->mac.type == e1000_i354)) && + (pdev->subsystem_vendor == PCI_VENDOR_ID_DELL)) { + adapter->flags |= IGB_FLAG_WOL_SUPPORTED; + adapter->wol = 0; + } + if (hw->mac.type == e1000_i350) { + if (((pdev->subsystem_device == 0x5001) || + (pdev->subsystem_device == 0x5002)) && + (hw->bus.func == 0)) { + adapter->flags |= IGB_FLAG_WOL_SUPPORTED; + adapter->wol = 0; + } + if (pdev->subsystem_device == 0x1F52) + adapter->flags |= IGB_FLAG_WOL_SUPPORTED; + } + + device_set_wakeup_enable(&adapter->pdev->dev, + adapter->flags & IGB_FLAG_WOL_SUPPORTED); + + /* 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. + */ + igb_get_hw_control(adapter); + + strcpy(netdev->name, "eth%d"); + err = register_netdev(netdev); + if (err) + goto err_register; + + /* carrier off reporting is important to ethtool even BEFORE open */ + netif_carrier_off(netdev); + +#ifdef CONFIG_IGB_DCA + if (dca_add_requester(&pdev->dev) == 0) { + adapter->flags |= IGB_FLAG_DCA_ENABLED; + dev_info(&pdev->dev, "DCA enabled\n"); + igb_setup_dca(adapter); + } + +#endif +#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; + /* Only enable I2C bit banging if an external thermal + * sensor is supported. + */ + if (adapter->ets) + igb_set_i2c_bb(hw); + hw->mac.ops.init_thermal_sensor_thresh(hw); + 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, 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_82576 && + rd32(E1000_EECD) & E1000_EECD_PRES) || + (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->flags & IGB_FLAG_HAS_MSIX) ? "MSI-X" : + (adapter->flags & IGB_FLAG_HAS_MSI) ? "MSI" : "legacy", + adapter->num_rx_queues, adapter->num_tx_queues); + 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, true, true); + 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, true, true); + 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; + } + } + + dev_pm_set_driver_flags(&pdev->dev, DPM_FLAG_NO_DIRECT_COMPLETE); + + 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); + + if (hw->flash_address) + iounmap(hw->flash_address); +err_sw_init: + kfree(adapter->mac_table); + kfree(adapter->shadow_vfta); + igb_clear_interrupt_scheme(adapter); +#ifdef CONFIG_PCI_IOV + igb_disable_sriov(pdev, false); +#endif + pci_iounmap(pdev, adapter->io_addr); +err_ioremap: + free_netdev(netdev); +err_alloc_etherdev: + pci_release_mem_regions(pdev); +err_pci_reg: +err_dma: + pci_disable_device(pdev); + return err; +} + +#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)) { + rtnl_unlock(); + 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_disable_sriov(struct pci_dev *pdev, bool reinit) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + unsigned long flags; + + /* 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); + } + spin_lock_irqsave(&adapter->vfs_lock, flags); + kfree(adapter->vf_mac_list); + adapter->vf_mac_list = NULL; + kfree(adapter->vf_data); + adapter->vf_data = NULL; + adapter->vfs_allocated_count = 0; + spin_unlock_irqrestore(&adapter->vfs_lock, flags); + 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 reinit ? igb_sriov_reinit(pdev) : 0; +} + +static int igb_enable_sriov(struct pci_dev *pdev, int num_vfs, bool reinit) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct igb_adapter *adapter = netdev_priv(netdev); + int old_vfs = pci_num_vf(pdev); + struct vf_mac_filter *mac_list; + int err = 0; + int num_vf_mac_filters, 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; + err = -ENOMEM; + goto out; + } + + /* Due to the limited number of RAR entries calculate potential + * number of MAC filters available for the VFs. Reserve entries + * for PF default MAC, PF MAC filters and at least one RAR entry + * for each VF for VF MAC. + */ + num_vf_mac_filters = adapter->hw.mac.rar_entry_count - + (1 + IGB_PF_MAC_FILTERS_RESERVED + + adapter->vfs_allocated_count); + + adapter->vf_mac_list = kcalloc(num_vf_mac_filters, + sizeof(struct vf_mac_filter), + GFP_KERNEL); + + mac_list = adapter->vf_mac_list; + INIT_LIST_HEAD(&adapter->vf_macs.l); + + if (adapter->vf_mac_list) { + /* Initialize list of VF MAC filters */ + for (i = 0; i < num_vf_mac_filters; i++) { + mac_list->vf = -1; + mac_list->free = true; + list_add(&mac_list->l, &adapter->vf_macs.l); + mac_list++; + } + } else { + /* If we could not allocate memory for the VF MAC filters + * we can continue without this feature but warn user. + */ + dev_err(&pdev->dev, + "Unable to allocate memory for VF MAC filter list\n"); + } + + 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; + + if (reinit) { + err = igb_sriov_reinit(pdev); + if (err) + goto err_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; + } + + goto out; + +err_out: + kfree(adapter->vf_mac_list); + adapter->vf_mac_list = NULL; + 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 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) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct igb_adapter *adapter = netdev_priv(netdev); + 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 + * disable watchdog from being rescheduled. + */ + set_bit(__IGB_DOWN, &adapter->state); + del_timer_sync(&adapter->watchdog_timer); + del_timer_sync(&adapter->phy_info_timer); + + cancel_work_sync(&adapter->reset_task); + cancel_work_sync(&adapter->watchdog_task); + +#ifdef CONFIG_IGB_DCA + if (adapter->flags & IGB_FLAG_DCA_ENABLED) { + dev_info(&pdev->dev, "DCA disabled\n"); + dca_remove_requester(&pdev->dev); + adapter->flags &= ~IGB_FLAG_DCA_ENABLED; + wr32(E1000_DCA_CTRL, E1000_DCA_CTRL_DCA_MODE_DISABLE); + } +#endif + + /* Release control of h/w to f/w. If f/w is AMT enabled, this + * would have already happened in close and is redundant. + */ + igb_release_hw_control(adapter); + +#ifdef CONFIG_PCI_IOV + igb_disable_sriov(pdev, false); +#endif + + unregister_netdev(netdev); + + igb_clear_interrupt_scheme(adapter); + + pci_iounmap(pdev, adapter->io_addr); + if (hw->flash_address) + iounmap(hw->flash_address); + pci_release_mem_regions(pdev); + + kfree(adapter->mac_table); + kfree(adapter->shadow_vfta); + free_netdev(netdev); + + pci_disable_device(pdev); +} + +/** + * igb_probe_vfs - Initialize vf data storage and add VFs to pci config space + * @adapter: board private structure to initialize + * + * This function initializes the vf specific data storage and then attempts to + * allocate the VFs. The reason for ordering it this way is because it is much + * mor expensive time wise to disable SR-IOV than it is to allocate and free + * the memory for the VFs. + **/ +static void igb_probe_vfs(struct igb_adapter *adapter) +{ +#ifdef CONFIG_PCI_IOV + struct pci_dev *pdev = adapter->pdev; + struct e1000_hw *hw = &adapter->hw; + + /* Virtualization features not supported on i210 and 82580 family. */ + if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211) || + (hw->mac.type == e1000_82580)) + return; + + /* Of the below we really only want the effect of getting + * IGB_FLAG_HAS_MSIX set (if available), without which + * igb_enable_sriov() has no effect. + */ + igb_set_interrupt_capability(adapter, true); + igb_reset_interrupt_capability(adapter); + + pci_sriov_set_totalvfs(pdev, 7); + igb_enable_sriov(pdev, max_vfs, false); + +#endif /* CONFIG_PCI_IOV */ +} + +unsigned int igb_get_max_rss_queues(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + unsigned int max_rss_queues; + + /* Determine the maximum number of RSS queues supported. */ + switch (hw->mac.type) { + case e1000_i211: + max_rss_queues = IGB_MAX_RX_QUEUES_I211; + break; + case e1000_82575: + case e1000_i210: + max_rss_queues = IGB_MAX_RX_QUEUES_82575; + break; + case e1000_i350: + /* I350 cannot do RSS and SR-IOV at the same time */ + if (!!adapter->vfs_allocated_count) { + max_rss_queues = 1; + break; + } + fallthrough; + case e1000_82576: + if (!!adapter->vfs_allocated_count) { + max_rss_queues = 2; + break; + } + fallthrough; + case e1000_82580: + case e1000_i354: + default: + max_rss_queues = IGB_MAX_RX_QUEUES; + break; + } + + return max_rss_queues; +} + +static void igb_init_queue_configuration(struct igb_adapter *adapter) +{ + u32 max_rss_queues; + + max_rss_queues = igb_get_max_rss_queues(adapter); + adapter->rss_queues = min_t(u32, max_rss_queues, num_online_cpus()); + + igb_set_flag_queue_pairs(adapter, max_rss_queues); +} + +void igb_set_flag_queue_pairs(struct igb_adapter *adapter, + const u32 max_rss_queues) +{ + struct e1000_hw *hw = &adapter->hw; + + /* Determine if we need to pair queues. */ + switch (hw->mac.type) { + case e1000_82575: + case e1000_i211: + /* Device supports enough interrupts without queue pairing. */ + break; + case e1000_82576: + 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 + * order to conserve interrupts due to limited supply. + */ + if (adapter->rss_queues > (max_rss_queues / 2)) + adapter->flags |= IGB_FLAG_QUEUE_PAIRS; + else + 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 + IGB_ETH_PKT_HDR_PAD; + adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN; + + spin_lock_init(&adapter->nfc_lock); + spin_lock_init(&adapter->stats64_lock); + + /* init spinlock to avoid concurrency of VF resources */ + spin_lock_init(&adapter->vfs_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 */ + + /* Assume MSI-X interrupts, will be checked during IRQ allocation */ + adapter->flags |= IGB_FLAG_HAS_MSIX; + + adapter->mac_table = kcalloc(hw->mac.rar_entry_count, + sizeof(struct igb_mac_addr), + GFP_KERNEL); + if (!adapter->mac_table) + return -ENOMEM; + + igb_probe_vfs(adapter); + + igb_init_queue_configuration(adapter); + + /* Setup and initialize a copy of the hw vlan table array */ + adapter->shadow_vfta = kcalloc(E1000_VLAN_FILTER_TBL_SIZE, sizeof(u32), + GFP_KERNEL); + if (!adapter->shadow_vfta) + return -ENOMEM; + + /* This call may decrease the number of queues */ + if (igb_init_interrupt_scheme(adapter, true)) { + dev_err(&pdev->dev, "Unable to allocate memory for queues\n"); + return -ENOMEM; + } + + /* Explicitly disable IRQ since the NIC can be in any state. */ + igb_irq_disable(adapter); + + if (hw->mac.type >= e1000_i350) + adapter->flags &= ~IGB_FLAG_DMAC; + + set_bit(__IGB_DOWN, &adapter->state); + return 0; +} + +/** + * __igb_open - Called when a network interface is made active + * @netdev: network interface device structure + * @resuming: indicates whether we are in a resume call + * + * Returns 0 on success, negative value on failure + * + * The open entry point is called when a network interface is made + * active by the system (IFF_UP). At this point all resources needed + * for transmit and receive operations are allocated, the interrupt + * handler is registered with the OS, the watchdog timer is started, + * and the stack is notified that the interface is ready. + **/ +static int __igb_open(struct net_device *netdev, bool resuming) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + struct pci_dev *pdev = adapter->pdev; + int err; + int i; + + /* disallow open during test */ + if (test_bit(__IGB_TESTING, &adapter->state)) { + WARN_ON(resuming); + return -EBUSY; + } + + if (!resuming) + pm_runtime_get_sync(&pdev->dev); + + netif_carrier_off(netdev); + + /* allocate transmit descriptors */ + err = igb_setup_all_tx_resources(adapter); + if (err) + goto err_setup_tx; + + /* allocate receive descriptors */ + err = igb_setup_all_rx_resources(adapter); + if (err) + goto err_setup_rx; + + igb_power_up_link(adapter); + + /* before we allocate an interrupt, we must be ready to handle it. + * Setting DEBUG_SHIRQ in the kernel makes it fire an interrupt + * as soon as we call pci_request_irq, so we have to setup our + * clean_rx handler before we do so. + */ + igb_configure(adapter); + + err = igb_request_irq(adapter); + if (err) + goto err_req_irq; + + /* Notify the stack of the actual queue counts. */ + err = netif_set_real_num_tx_queues(adapter->netdev, + adapter->num_tx_queues); + if (err) + goto err_set_queues; + + err = netif_set_real_num_rx_queues(adapter->netdev, + adapter->num_rx_queues); + if (err) + goto err_set_queues; + + /* From here on the code is the same as igb_up() */ + clear_bit(__IGB_DOWN, &adapter->state); + + for (i = 0; i < adapter->num_q_vectors; i++) + napi_enable(&(adapter->q_vector[i]->napi)); + + /* Clear any pending interrupts. */ + rd32(E1000_TSICR); + rd32(E1000_ICR); + + igb_irq_enable(adapter); + + /* notify VFs that reset has been completed */ + if (adapter->vfs_allocated_count) { + u32 reg_data = rd32(E1000_CTRL_EXT); + + reg_data |= E1000_CTRL_EXT_PFRSTD; + wr32(E1000_CTRL_EXT, reg_data); + } + + netif_tx_start_all_queues(netdev); + + if (!resuming) + pm_runtime_put(&pdev->dev); + + /* start the watchdog. */ + hw->mac.get_link_status = 1; + schedule_work(&adapter->watchdog_task); + + return 0; + +err_set_queues: + igb_free_irq(adapter); +err_req_irq: + igb_release_hw_control(adapter); + igb_power_down_link(adapter); + igb_free_all_rx_resources(adapter); +err_setup_rx: + igb_free_all_tx_resources(adapter); +err_setup_tx: + igb_reset(adapter); + if (!resuming) + pm_runtime_put(&pdev->dev); + + return err; +} + +int igb_open(struct net_device *netdev) +{ + return __igb_open(netdev, false); +} + +/** + * __igb_close - Disables a network interface + * @netdev: network interface device structure + * @suspending: indicates we are in a suspend call + * + * Returns 0, this is not allowed to fail + * + * The close entry point is called when an interface is de-activated + * by the OS. The hardware is still under the driver's control, but + * needs to be disabled. A global MAC reset is issued to stop the + * hardware, and all transmit and receive resources are freed. + **/ +static int __igb_close(struct net_device *netdev, bool suspending) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct pci_dev *pdev = adapter->pdev; + + WARN_ON(test_bit(__IGB_RESETTING, &adapter->state)); + + if (!suspending) + pm_runtime_get_sync(&pdev->dev); + + igb_down(adapter); + igb_free_irq(adapter); + + igb_free_all_tx_resources(adapter); + igb_free_all_rx_resources(adapter); + + if (!suspending) + pm_runtime_put_sync(&pdev->dev); + return 0; +} + +int igb_close(struct net_device *netdev) +{ + if (netif_device_present(netdev) || netdev->dismantle) + return __igb_close(netdev, false); + return 0; +} + +/** + * igb_setup_tx_resources - allocate Tx resources (Descriptors) + * @tx_ring: tx descriptor ring (for a specific queue) to setup + * + * Return 0 on success, negative on failure + **/ +int igb_setup_tx_resources(struct igb_ring *tx_ring) +{ + struct device *dev = tx_ring->dev; + int size; + + size = sizeof(struct igb_tx_buffer) * tx_ring->count; + + tx_ring->tx_buffer_info = vmalloc(size); + if (!tx_ring->tx_buffer_info) + goto err; + + /* round up to nearest 4K */ + tx_ring->size = tx_ring->count * sizeof(union e1000_adv_tx_desc); + tx_ring->size = ALIGN(tx_ring->size, 4096); + + tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size, + &tx_ring->dma, GFP_KERNEL); + if (!tx_ring->desc) + goto err; + + tx_ring->next_to_use = 0; + tx_ring->next_to_clean = 0; + + return 0; + +err: + vfree(tx_ring->tx_buffer_info); + tx_ring->tx_buffer_info = NULL; + dev_err(dev, "Unable to allocate memory for the Tx descriptor ring\n"); + return -ENOMEM; +} + +/** + * igb_setup_all_tx_resources - wrapper to allocate Tx resources + * (Descriptors) for all queues + * @adapter: board private structure + * + * Return 0 on success, negative on failure + **/ +static int igb_setup_all_tx_resources(struct igb_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + int i, err = 0; + + for (i = 0; i < adapter->num_tx_queues; i++) { + err = igb_setup_tx_resources(adapter->tx_ring[i]); + if (err) { + dev_err(&pdev->dev, + "Allocation for Tx Queue %u failed\n", i); + for (i--; i >= 0; i--) + igb_free_tx_resources(adapter->tx_ring[i]); + break; + } + } + + return err; +} + +/** + * igb_setup_tctl - configure the transmit control registers + * @adapter: Board private structure + **/ +void igb_setup_tctl(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 tctl; + + /* disable queue 0 which is enabled by default on 82575 and 82576 */ + wr32(E1000_TXDCTL(0), 0); + + /* Program the Transmit Control Register */ + tctl = rd32(E1000_TCTL); + tctl &= ~E1000_TCTL_CT; + tctl |= E1000_TCTL_PSP | E1000_TCTL_RTLC | + (E1000_COLLISION_THRESHOLD << E1000_CT_SHIFT); + + igb_config_collision_dist(hw); + + /* Enable transmits */ + tctl |= E1000_TCTL_EN; + + wr32(E1000_TCTL, tctl); +} + +/** + * igb_configure_tx_ring - Configure transmit ring after Reset + * @adapter: board private structure + * @ring: tx ring to configure + * + * Configure a transmit ring after a reset. + **/ +void igb_configure_tx_ring(struct igb_adapter *adapter, + struct igb_ring *ring) +{ + struct e1000_hw *hw = &adapter->hw; + u32 txdctl = 0; + u64 tdba = ring->dma; + int reg_idx = ring->reg_idx; + + wr32(E1000_TDLEN(reg_idx), + ring->count * sizeof(union e1000_adv_tx_desc)); + wr32(E1000_TDBAL(reg_idx), + tdba & 0x00000000ffffffffULL); + wr32(E1000_TDBAH(reg_idx), tdba >> 32); + + ring->tail = adapter->io_addr + E1000_TDT(reg_idx); + wr32(E1000_TDH(reg_idx), 0); + writel(0, ring->tail); + + txdctl |= IGB_TX_PTHRESH; + txdctl |= IGB_TX_HTHRESH << 8; + txdctl |= IGB_TX_WTHRESH << 16; + + /* reinitialize tx_buffer_info */ + memset(ring->tx_buffer_info, 0, + sizeof(struct igb_tx_buffer) * ring->count); + + txdctl |= E1000_TXDCTL_QUEUE_ENABLE; + wr32(E1000_TXDCTL(reg_idx), txdctl); +} + +/** + * igb_configure_tx - Configure transmit Unit after Reset + * @adapter: board private structure + * + * Configure the Tx unit of the MAC after a reset. + **/ +static void igb_configure_tx(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + int i; + + /* disable the queues */ + for (i = 0; i < adapter->num_tx_queues; i++) + wr32(E1000_TXDCTL(adapter->tx_ring[i]->reg_idx), 0); + + wrfl(); + usleep_range(10000, 20000); + + for (i = 0; i < adapter->num_tx_queues; i++) + igb_configure_tx_ring(adapter, adapter->tx_ring[i]); +} + +/** + * igb_setup_rx_resources - allocate Rx resources (Descriptors) + * @rx_ring: Rx descriptor ring (for a specific queue) to setup + * + * Returns 0 on success, negative on failure + **/ +int igb_setup_rx_resources(struct igb_ring *rx_ring) +{ + struct igb_adapter *adapter = netdev_priv(rx_ring->netdev); + struct device *dev = rx_ring->dev; + int size, res; + + /* XDP RX-queue info */ + if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); + res = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, + rx_ring->queue_index, 0); + if (res < 0) { + dev_err(dev, "Failed to register xdp_rxq index %u\n", + rx_ring->queue_index); + return res; + } + + size = sizeof(struct igb_rx_buffer) * rx_ring->count; + + rx_ring->rx_buffer_info = vmalloc(size); + if (!rx_ring->rx_buffer_info) + goto err; + + /* Round up to nearest 4K */ + rx_ring->size = rx_ring->count * sizeof(union e1000_adv_rx_desc); + rx_ring->size = ALIGN(rx_ring->size, 4096); + + rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size, + &rx_ring->dma, GFP_KERNEL); + if (!rx_ring->desc) + goto err; + + rx_ring->next_to_alloc = 0; + rx_ring->next_to_clean = 0; + rx_ring->next_to_use = 0; + + rx_ring->xdp_prog = adapter->xdp_prog; + + return 0; + +err: + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); + vfree(rx_ring->rx_buffer_info); + rx_ring->rx_buffer_info = NULL; + dev_err(dev, "Unable to allocate memory for the Rx descriptor ring\n"); + return -ENOMEM; +} + +/** + * igb_setup_all_rx_resources - wrapper to allocate Rx resources + * (Descriptors) for all queues + * @adapter: board private structure + * + * Return 0 on success, negative on failure + **/ +static int igb_setup_all_rx_resources(struct igb_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + int i, err = 0; + + for (i = 0; i < adapter->num_rx_queues; i++) { + err = igb_setup_rx_resources(adapter->rx_ring[i]); + if (err) { + dev_err(&pdev->dev, + "Allocation for Rx Queue %u failed\n", i); + for (i--; i >= 0; i--) + igb_free_rx_resources(adapter->rx_ring[i]); + break; + } + } + + return err; +} + +/** + * igb_setup_mrqc - configure the multiple receive queue control registers + * @adapter: Board private structure + **/ +static void igb_setup_mrqc(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 mrqc, rxcsum; + u32 j, num_rx_queues; + u32 rss_key[10]; + + netdev_rss_key_fill(rss_key, sizeof(rss_key)); + for (j = 0; j < 10; j++) + wr32(E1000_RSSRK(j), rss_key[j]); + + num_rx_queues = adapter->rss_queues; + + switch (hw->mac.type) { + case e1000_82576: + /* 82576 supports 2 RSS queues for SR-IOV */ + if (adapter->vfs_allocated_count) + num_rx_queues = 2; + break; + default: + break; + } + + 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 + * descriptor on writeback. No need to enable TCP/UDP/IP checksum + * offloads as they are enabled by default + */ + rxcsum = rd32(E1000_RXCSUM); + rxcsum |= E1000_RXCSUM_PCSD; + + if (adapter->hw.mac.type >= e1000_82576) + /* Enable Receive Checksum Offload for SCTP */ + rxcsum |= E1000_RXCSUM_CRCOFL; + + /* Don't need to set TUOFL or IPOFL, they default to 1 */ + wr32(E1000_RXCSUM, rxcsum); + + /* Generate RSS hash based on packet types, TCP/UDP + * port numbers and/or IPv4/v6 src and dst addresses + */ + mrqc = E1000_MRQC_RSS_FIELD_IPV4 | + E1000_MRQC_RSS_FIELD_IPV4_TCP | + E1000_MRQC_RSS_FIELD_IPV6 | + E1000_MRQC_RSS_FIELD_IPV6_TCP | + E1000_MRQC_RSS_FIELD_IPV6_TCP_EX; + + if (adapter->flags & IGB_FLAG_RSS_FIELD_IPV4_UDP) + mrqc |= E1000_MRQC_RSS_FIELD_IPV4_UDP; + if (adapter->flags & IGB_FLAG_RSS_FIELD_IPV6_UDP) + mrqc |= E1000_MRQC_RSS_FIELD_IPV6_UDP; + + /* If VMDq is enabled then we set the appropriate mode for that, else + * we default to RSS so that an RSS hash is calculated per packet even + * if we are only using one queue + */ + if (adapter->vfs_allocated_count) { + if (hw->mac.type > e1000_82575) { + /* Set the default pool for the PF's first queue */ + u32 vtctl = rd32(E1000_VT_CTL); + + vtctl &= ~(E1000_VT_CTL_DEFAULT_POOL_MASK | + E1000_VT_CTL_DISABLE_DEF_POOL); + vtctl |= adapter->vfs_allocated_count << + E1000_VT_CTL_DEFAULT_POOL_SHIFT; + wr32(E1000_VT_CTL, vtctl); + } + if (adapter->rss_queues > 1) + mrqc |= E1000_MRQC_ENABLE_VMDQ_RSS_MQ; + else + mrqc |= E1000_MRQC_ENABLE_VMDQ; + } else { + mrqc |= E1000_MRQC_ENABLE_RSS_MQ; + } + igb_vmm_control(adapter); + + wr32(E1000_MRQC, mrqc); +} + +/** + * igb_setup_rctl - configure the receive control registers + * @adapter: Board private structure + **/ +void igb_setup_rctl(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 rctl; + + rctl = rd32(E1000_RCTL); + + rctl &= ~(3 << E1000_RCTL_MO_SHIFT); + rctl &= ~(E1000_RCTL_LBM_TCVR | E1000_RCTL_LBM_MAC); + + rctl |= E1000_RCTL_EN | E1000_RCTL_BAM | E1000_RCTL_RDMTS_HALF | + (hw->mac.mc_filter_type << E1000_RCTL_MO_SHIFT); + + /* enable stripping of CRC. It's unlikely this will break BMC + * redirection as it did with e1000. Newer features require + * that the HW strips the CRC. + */ + rctl |= E1000_RCTL_SECRC; + + /* disable store bad packets and clear size bits. */ + rctl &= ~(E1000_RCTL_SBP | E1000_RCTL_SZ_256); + + /* enable LPE to allow for reception of jumbo frames */ + rctl |= E1000_RCTL_LPE; + + /* disable queue 0 to prevent tail write w/o re-config */ + wr32(E1000_RXDCTL(0), 0); + + /* Attention!!! For SR-IOV PF driver operations you must enable + * queue drop for all VF and PF queues to prevent head of line blocking + * if an un-trusted VF does not provide descriptors to hardware. + */ + if (adapter->vfs_allocated_count) { + /* set all queue drop enable bits */ + wr32(E1000_QDE, ALL_QUEUES); + } + + /* 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 + */ + rctl |= (E1000_RCTL_SBP | /* Receive bad packets */ + E1000_RCTL_BAM | /* RX All Bcast Pkts */ + E1000_RCTL_PMCF); /* RX All MAC Ctrl Pkts */ + + rctl &= ~(E1000_RCTL_DPF | /* Allow filtered pause */ + E1000_RCTL_CFIEN); /* Dis VLAN CFIEN Filter */ + /* Do not mess with E1000_CTRL_VME, it affects transmit as well, + * and that breaks VLANs. + */ + } + + wr32(E1000_RCTL, rctl); +} + +static inline int igb_set_vf_rlpml(struct igb_adapter *adapter, int size, + int vfn) +{ + struct e1000_hw *hw = &adapter->hw; + u32 vmolr; + + if (size > MAX_JUMBO_FRAME_SIZE) + size = MAX_JUMBO_FRAME_SIZE; + + vmolr = rd32(E1000_VMOLR(vfn)); + vmolr &= ~E1000_VMOLR_RLPML_MASK; + vmolr |= size | E1000_VMOLR_LPE; + wr32(E1000_VMOLR(vfn), vmolr); + + return 0; +} + +static inline void igb_set_vf_vlan_strip(struct igb_adapter *adapter, + int vfn, bool enable) +{ + struct e1000_hw *hw = &adapter->hw; + u32 val, reg; + + if (hw->mac.type < e1000_82576) + return; + + if (hw->mac.type == e1000_i350) + reg = E1000_DVMOLR(vfn); + else + reg = E1000_VMOLR(vfn); + + val = rd32(reg); + if (enable) + val |= E1000_VMOLR_STRVLAN; + else + val &= ~(E1000_VMOLR_STRVLAN); + wr32(reg, val); +} + +static inline void igb_set_vmolr(struct igb_adapter *adapter, + int vfn, bool aupe) +{ + struct e1000_hw *hw = &adapter->hw; + u32 vmolr; + + /* This register exists only on 82576 and newer so if we are older then + * we should exit and do nothing + */ + if (hw->mac.type < e1000_82576) + return; + + vmolr = rd32(E1000_VMOLR(vfn)); + if (aupe) + vmolr |= E1000_VMOLR_AUPE; /* Accept untagged packets */ + else + vmolr &= ~(E1000_VMOLR_AUPE); /* Tagged packets ONLY */ + + /* clear all bits that might not be set */ + vmolr &= ~(E1000_VMOLR_BAM | E1000_VMOLR_RSSE); + + if (adapter->rss_queues > 1 && vfn == adapter->vfs_allocated_count) + vmolr |= E1000_VMOLR_RSSE; /* enable RSS */ + /* for VMDq only allow the VFs and pool 0 to accept broadcast and + * multicast packets + */ + if (vfn <= adapter->vfs_allocated_count) + vmolr |= E1000_VMOLR_BAM; /* Accept broadcast */ + + wr32(E1000_VMOLR(vfn), vmolr); +} + +/** + * igb_setup_srrctl - configure the split and replication receive control + * registers + * @adapter: Board private structure + * @ring: receive ring to be configured + **/ +void igb_setup_srrctl(struct igb_adapter *adapter, struct igb_ring *ring) +{ + struct e1000_hw *hw = &adapter->hw; + int reg_idx = ring->reg_idx; + u32 srrctl = 0; + + srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT; + if (ring_uses_large_buffer(ring)) + srrctl |= IGB_RXBUFFER_3072 >> E1000_SRRCTL_BSIZEPKT_SHIFT; + else + srrctl |= IGB_RXBUFFER_2048 >> E1000_SRRCTL_BSIZEPKT_SHIFT; + srrctl |= E1000_SRRCTL_DESCTYPE_ADV_ONEBUF; + if (hw->mac.type >= e1000_82580) + srrctl |= E1000_SRRCTL_TIMESTAMP; + /* Only set Drop Enable if VFs allocated, or we are supporting multiple + * queues and rx flow control is disabled + */ + if (adapter->vfs_allocated_count || + (!(hw->fc.current_mode & e1000_fc_rx_pause) && + adapter->num_rx_queues > 1)) + srrctl |= E1000_SRRCTL_DROP_EN; + + wr32(E1000_SRRCTL(reg_idx), srrctl); +} + +/** + * igb_configure_rx_ring - Configure a receive ring after Reset + * @adapter: board private structure + * @ring: receive ring to be configured + * + * Configure the Rx unit of the MAC after a reset. + **/ +void igb_configure_rx_ring(struct igb_adapter *adapter, + struct igb_ring *ring) +{ + struct e1000_hw *hw = &adapter->hw; + union e1000_adv_rx_desc *rx_desc; + u64 rdba = ring->dma; + int reg_idx = ring->reg_idx; + u32 rxdctl = 0; + + xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); + WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_PAGE_SHARED, NULL)); + + /* disable the queue */ + wr32(E1000_RXDCTL(reg_idx), 0); + + /* Set DMA base address registers */ + wr32(E1000_RDBAL(reg_idx), + rdba & 0x00000000ffffffffULL); + wr32(E1000_RDBAH(reg_idx), rdba >> 32); + wr32(E1000_RDLEN(reg_idx), + ring->count * sizeof(union e1000_adv_rx_desc)); + + /* initialize head and tail */ + ring->tail = adapter->io_addr + E1000_RDT(reg_idx); + wr32(E1000_RDH(reg_idx), 0); + writel(0, ring->tail); + + /* set descriptor configuration */ + igb_setup_srrctl(adapter, ring); + + /* set filtering for VMDQ pools */ + igb_set_vmolr(adapter, reg_idx & 0x7, true); + + rxdctl |= IGB_RX_PTHRESH; + rxdctl |= IGB_RX_HTHRESH << 8; + rxdctl |= IGB_RX_WTHRESH << 16; + + /* initialize rx_buffer_info */ + memset(ring->rx_buffer_info, 0, + sizeof(struct igb_rx_buffer) * ring->count); + + /* initialize Rx descriptor 0 */ + rx_desc = IGB_RX_DESC(ring, 0); + rx_desc->wb.upper.length = 0; + + /* enable receive descriptor fetching */ + rxdctl |= E1000_RXDCTL_QUEUE_ENABLE; + wr32(E1000_RXDCTL(reg_idx), rxdctl); +} + +static void igb_set_rx_buffer_len(struct igb_adapter *adapter, + struct igb_ring *rx_ring) +{ +#if (PAGE_SIZE < 8192) + struct e1000_hw *hw = &adapter->hw; +#endif + + /* set build_skb and buffer size flags */ + clear_ring_build_skb_enabled(rx_ring); + clear_ring_uses_large_buffer(rx_ring); + + if (adapter->flags & IGB_FLAG_RX_LEGACY) + return; + + set_ring_build_skb_enabled(rx_ring); + +#if (PAGE_SIZE < 8192) + if (adapter->max_frame_size > IGB_MAX_FRAME_BUILD_SKB || + rd32(E1000_RCTL) & E1000_RCTL_SBP) + set_ring_uses_large_buffer(rx_ring); +#endif +} + +/** + * igb_configure_rx - Configure receive Unit after Reset + * @adapter: board private structure + * + * Configure the Rx unit of the MAC after a reset. + **/ +static void igb_configure_rx(struct igb_adapter *adapter) +{ + int i; + + /* set the correct pool for the PF default MAC address in entry 0 */ + igb_set_default_mac_filter(adapter); + + /* Setup the HW Rx Head and Tail Descriptor Pointers and + * the Base and Length of the Rx Descriptor Ring + */ + for (i = 0; i < adapter->num_rx_queues; i++) { + struct igb_ring *rx_ring = adapter->rx_ring[i]; + + igb_set_rx_buffer_len(adapter, rx_ring); + igb_configure_rx_ring(adapter, rx_ring); + } +} + +/** + * igb_free_tx_resources - Free Tx Resources per Queue + * @tx_ring: Tx descriptor ring for a specific queue + * + * Free all transmit software resources + **/ +void igb_free_tx_resources(struct igb_ring *tx_ring) +{ + igb_clean_tx_ring(tx_ring); + + vfree(tx_ring->tx_buffer_info); + tx_ring->tx_buffer_info = NULL; + + /* if not set, then don't free */ + if (!tx_ring->desc) + return; + + dma_free_coherent(tx_ring->dev, tx_ring->size, + tx_ring->desc, tx_ring->dma); + + tx_ring->desc = NULL; +} + +/** + * igb_free_all_tx_resources - Free Tx Resources for All Queues + * @adapter: board private structure + * + * Free all transmit software resources + **/ +static void igb_free_all_tx_resources(struct igb_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) + if (adapter->tx_ring[i]) + igb_free_tx_resources(adapter->tx_ring[i]); +} + +/** + * igb_clean_tx_ring - Free Tx Buffers + * @tx_ring: ring to be cleaned + **/ +static void igb_clean_tx_ring(struct igb_ring *tx_ring) +{ + u16 i = tx_ring->next_to_clean; + struct igb_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i]; + + while (i != tx_ring->next_to_use) { + union e1000_adv_tx_desc *eop_desc, *tx_desc; + + /* Free all the Tx ring sk_buffs or xdp frames */ + if (tx_buffer->type == IGB_TYPE_SKB) + dev_kfree_skb_any(tx_buffer->skb); + else + xdp_return_frame(tx_buffer->xdpf); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + + /* check for eop_desc to determine the end of the packet */ + eop_desc = tx_buffer->next_to_watch; + tx_desc = IGB_TX_DESC(tx_ring, i); + + /* unmap remaining buffers */ + while (tx_desc != eop_desc) { + tx_buffer++; + tx_desc++; + i++; + if (unlikely(i == tx_ring->count)) { + i = 0; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = IGB_TX_DESC(tx_ring, 0); + } + + /* unmap any remaining paged data */ + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + } + + tx_buffer->next_to_watch = NULL; + + /* move us one more past the eop_desc for start of next pkt */ + tx_buffer++; + i++; + if (unlikely(i == tx_ring->count)) { + i = 0; + tx_buffer = tx_ring->tx_buffer_info; + } + } + + /* reset BQL for queue */ + netdev_tx_reset_queue(txring_txq(tx_ring)); + + /* reset next_to_use and next_to_clean */ + tx_ring->next_to_use = 0; + tx_ring->next_to_clean = 0; +} + +/** + * igb_clean_all_tx_rings - Free Tx Buffers for all queues + * @adapter: board private structure + **/ +static void igb_clean_all_tx_rings(struct igb_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) + if (adapter->tx_ring[i]) + igb_clean_tx_ring(adapter->tx_ring[i]); +} + +/** + * igb_free_rx_resources - Free Rx Resources + * @rx_ring: ring to clean the resources from + * + * Free all receive software resources + **/ +void igb_free_rx_resources(struct igb_ring *rx_ring) +{ + igb_clean_rx_ring(rx_ring); + + rx_ring->xdp_prog = NULL; + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); + vfree(rx_ring->rx_buffer_info); + rx_ring->rx_buffer_info = NULL; + + /* if not set, then don't free */ + if (!rx_ring->desc) + return; + + dma_free_coherent(rx_ring->dev, rx_ring->size, + rx_ring->desc, rx_ring->dma); + + rx_ring->desc = NULL; +} + +/** + * igb_free_all_rx_resources - Free Rx Resources for All Queues + * @adapter: board private structure + * + * Free all receive software resources + **/ +static void igb_free_all_rx_resources(struct igb_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_rx_queues; i++) + if (adapter->rx_ring[i]) + igb_free_rx_resources(adapter->rx_ring[i]); +} + +/** + * igb_clean_rx_ring - Free Rx Buffers per Queue + * @rx_ring: ring to free buffers from + **/ +static void igb_clean_rx_ring(struct igb_ring *rx_ring) +{ + u16 i = rx_ring->next_to_clean; + + dev_kfree_skb(rx_ring->skb); + rx_ring->skb = NULL; + + /* Free all the Rx ring sk_buffs */ + while (i != rx_ring->next_to_alloc) { + struct igb_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i]; + + /* Invalidate cache lines that may have been written to by + * device so that we avoid corrupting memory. + */ + dma_sync_single_range_for_cpu(rx_ring->dev, + buffer_info->dma, + buffer_info->page_offset, + igb_rx_bufsz(rx_ring), + DMA_FROM_DEVICE); + + /* free resources associated with mapping */ + dma_unmap_page_attrs(rx_ring->dev, + buffer_info->dma, + igb_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IGB_RX_DMA_ATTR); + __page_frag_cache_drain(buffer_info->page, + buffer_info->pagecnt_bias); + + i++; + if (i == rx_ring->count) + i = 0; + } + + rx_ring->next_to_alloc = 0; + rx_ring->next_to_clean = 0; + rx_ring->next_to_use = 0; +} + +/** + * igb_clean_all_rx_rings - Free Rx Buffers for all queues + * @adapter: board private structure + **/ +static void igb_clean_all_rx_rings(struct igb_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_rx_queues; i++) + if (adapter->rx_ring[i]) + igb_clean_rx_ring(adapter->rx_ring[i]); +} + +/** + * igb_set_mac - Change the Ethernet Address of the NIC + * @netdev: network interface device structure + * @p: pointer to an address structure + * + * Returns 0 on success, negative on failure + **/ +static int igb_set_mac(struct net_device *netdev, void *p) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + struct sockaddr *addr = p; + + if (!is_valid_ether_addr(addr->sa_data)) + return -EADDRNOTAVAIL; + + eth_hw_addr_set(netdev, addr->sa_data); + memcpy(hw->mac.addr, addr->sa_data, netdev->addr_len); + + /* set the correct pool for the new PF MAC address in entry 0 */ + igb_set_default_mac_filter(adapter); + + return 0; +} + +/** + * igb_write_mc_addr_list - write multicast addresses to MTA + * @netdev: network interface device structure + * + * Writes multicast address list to the MTA hash table. + * Returns: -ENOMEM on failure + * 0 on no addresses written + * X on writing X addresses to MTA + **/ +static int igb_write_mc_addr_list(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + struct netdev_hw_addr *ha; + u8 *mta_list; + int i; + + if (netdev_mc_empty(netdev)) { + /* nothing to program, so clear mc list */ + igb_update_mc_addr_list(hw, NULL, 0); + igb_restore_vf_multicasts(adapter); + return 0; + } + + mta_list = kcalloc(netdev_mc_count(netdev), 6, GFP_ATOMIC); + if (!mta_list) + return -ENOMEM; + + /* The shared function expects a packed array of only addresses. */ + i = 0; + netdev_for_each_mc_addr(ha, netdev) + memcpy(mta_list + (i++ * ETH_ALEN), ha->addr, ETH_ALEN); + + igb_update_mc_addr_list(hw, mta_list, i); + kfree(mta_list); + + return netdev_mc_count(netdev); +} + +static int igb_vlan_promisc_enable(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 i, pf_id; + + switch (hw->mac.type) { + case e1000_i210: + case e1000_i211: + case e1000_i350: + /* VLAN filtering needed for VLAN prio filter */ + if (adapter->netdev->features & NETIF_F_NTUPLE) + break; + fallthrough; + case e1000_82576: + case e1000_82580: + case e1000_i354: + /* VLAN filtering needed for pool filtering */ + if (adapter->vfs_allocated_count) + break; + fallthrough; + default: + return 1; + } + + /* We are already in VLAN promisc, nothing to do */ + if (adapter->flags & IGB_FLAG_VLAN_PROMISC) + return 0; + + if (!adapter->vfs_allocated_count) + goto set_vfta; + + /* Add PF to all active pools */ + pf_id = adapter->vfs_allocated_count + E1000_VLVF_POOLSEL_SHIFT; + + for (i = E1000_VLVF_ARRAY_SIZE; --i;) { + u32 vlvf = rd32(E1000_VLVF(i)); + + vlvf |= BIT(pf_id); + wr32(E1000_VLVF(i), vlvf); + } + +set_vfta: + /* Set all bits in the VLAN filter table array */ + for (i = E1000_VLAN_FILTER_TBL_SIZE; i--;) + hw->mac.ops.write_vfta(hw, i, ~0U); + + /* Set flag so we don't redo unnecessary work */ + adapter->flags |= IGB_FLAG_VLAN_PROMISC; + + return 0; +} + +#define VFTA_BLOCK_SIZE 8 +static void igb_scrub_vfta(struct igb_adapter *adapter, u32 vfta_offset) +{ + struct e1000_hw *hw = &adapter->hw; + u32 vfta[VFTA_BLOCK_SIZE] = { 0 }; + u32 vid_start = vfta_offset * 32; + u32 vid_end = vid_start + (VFTA_BLOCK_SIZE * 32); + u32 i, vid, word, bits, pf_id; + + /* guarantee that we don't scrub out management VLAN */ + vid = adapter->mng_vlan_id; + if (vid >= vid_start && vid < vid_end) + vfta[(vid - vid_start) / 32] |= BIT(vid % 32); + + if (!adapter->vfs_allocated_count) + goto set_vfta; + + pf_id = adapter->vfs_allocated_count + E1000_VLVF_POOLSEL_SHIFT; + + for (i = E1000_VLVF_ARRAY_SIZE; --i;) { + u32 vlvf = rd32(E1000_VLVF(i)); + + /* pull VLAN ID from VLVF */ + vid = vlvf & VLAN_VID_MASK; + + /* only concern ourselves with a certain range */ + if (vid < vid_start || vid >= vid_end) + continue; + + if (vlvf & E1000_VLVF_VLANID_ENABLE) { + /* record VLAN ID in VFTA */ + vfta[(vid - vid_start) / 32] |= BIT(vid % 32); + + /* if PF is part of this then continue */ + if (test_bit(vid, adapter->active_vlans)) + continue; + } + + /* remove PF from the pool */ + bits = ~BIT(pf_id); + bits &= rd32(E1000_VLVF(i)); + wr32(E1000_VLVF(i), bits); + } + +set_vfta: + /* extract values from active_vlans and write back to VFTA */ + for (i = VFTA_BLOCK_SIZE; i--;) { + vid = (vfta_offset + i) * 32; + word = vid / BITS_PER_LONG; + bits = vid % BITS_PER_LONG; + + vfta[i] |= adapter->active_vlans[word] >> bits; + + hw->mac.ops.write_vfta(hw, vfta_offset + i, vfta[i]); + } +} + +static void igb_vlan_promisc_disable(struct igb_adapter *adapter) +{ + u32 i; + + /* We are not in VLAN promisc, nothing to do */ + if (!(adapter->flags & IGB_FLAG_VLAN_PROMISC)) + return; + + /* Set flag so we don't redo unnecessary work */ + adapter->flags &= ~IGB_FLAG_VLAN_PROMISC; + + for (i = 0; i < E1000_VLAN_FILTER_TBL_SIZE; i += VFTA_BLOCK_SIZE) + igb_scrub_vfta(adapter, i); +} + +/** + * igb_set_rx_mode - Secondary Unicast, Multicast and Promiscuous mode set + * @netdev: network interface device structure + * + * The set_rx_mode entry point is called whenever the unicast or multicast + * address lists or the network interface flags are updated. This routine is + * responsible for configuring the hardware for proper unicast, multicast, + * promiscuous mode, and all-multi behavior. + **/ +static void igb_set_rx_mode(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + unsigned int vfn = adapter->vfs_allocated_count; + u32 rctl = 0, vmolr = 0, rlpml = MAX_JUMBO_FRAME_SIZE; + int count; + + /* Check for Promiscuous and All Multicast modes */ + if (netdev->flags & IFF_PROMISC) { + rctl |= E1000_RCTL_UPE | E1000_RCTL_MPE; + vmolr |= E1000_VMOLR_MPME; + + /* enable use of UTA filter to force packets to default pool */ + if (hw->mac.type == e1000_82576) + vmolr |= E1000_VMOLR_ROPE; + } else { + if (netdev->flags & IFF_ALLMULTI) { + rctl |= E1000_RCTL_MPE; + vmolr |= E1000_VMOLR_MPME; + } else { + /* Write addresses to the MTA, if the attempt fails + * then we should just turn on promiscuous mode so + * that we can at least receive multicast traffic + */ + count = igb_write_mc_addr_list(netdev); + if (count < 0) { + rctl |= E1000_RCTL_MPE; + vmolr |= E1000_VMOLR_MPME; + } else if (count) { + vmolr |= E1000_VMOLR_ROMPE; + } + } + } + + /* Write addresses to available RAR registers, if there is not + * sufficient space to store all the addresses then enable + * unicast promiscuous mode + */ + if (__dev_uc_sync(netdev, igb_uc_sync, igb_uc_unsync)) { + rctl |= E1000_RCTL_UPE; + vmolr |= E1000_VMOLR_ROPE; + } + + /* enable VLAN filtering by default */ + rctl |= E1000_RCTL_VFE; + + /* disable VLAN filtering for modes that require it */ + if ((netdev->flags & IFF_PROMISC) || + (netdev->features & NETIF_F_RXALL)) { + /* if we fail to set all rules then just clear VFE */ + if (igb_vlan_promisc_enable(adapter)) + rctl &= ~E1000_RCTL_VFE; + } else { + igb_vlan_promisc_disable(adapter); + } + + /* update state of unicast, multicast, and VLAN filtering modes */ + rctl |= rd32(E1000_RCTL) & ~(E1000_RCTL_UPE | E1000_RCTL_MPE | + E1000_RCTL_VFE); + wr32(E1000_RCTL, rctl); + +#if (PAGE_SIZE < 8192) + if (!adapter->vfs_allocated_count) { + if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB) + rlpml = IGB_MAX_FRAME_BUILD_SKB; + } +#endif + wr32(E1000_RLPML, rlpml); + + /* In order to support SR-IOV and eventually VMDq it is necessary to set + * the VMOLR to enable the appropriate modes. Without this workaround + * we will have issues with VLAN tag stripping not being done for frames + * that are only arriving because we are the default pool + */ + if ((hw->mac.type < e1000_82576) || (hw->mac.type > e1000_i350)) + return; + + /* set UTA to appropriate mode */ + igb_set_uta(adapter, !!(vmolr & E1000_VMOLR_ROPE)); + + vmolr |= rd32(E1000_VMOLR(vfn)) & + ~(E1000_VMOLR_ROPE | E1000_VMOLR_MPME | E1000_VMOLR_ROMPE); + + /* enable Rx jumbo frames, restrict as needed to support build_skb */ + vmolr &= ~E1000_VMOLR_RLPML_MASK; +#if (PAGE_SIZE < 8192) + if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB) + vmolr |= IGB_MAX_FRAME_BUILD_SKB; + else +#endif + vmolr |= MAX_JUMBO_FRAME_SIZE; + vmolr |= E1000_VMOLR_LPE; + + wr32(E1000_VMOLR(vfn), vmolr); + + igb_restore_vf_multicasts(adapter); +} + +static void igb_check_wvbr(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 wvbr = 0; + + switch (hw->mac.type) { + case e1000_82576: + case e1000_i350: + wvbr = rd32(E1000_WVBR); + if (!wvbr) + return; + break; + default: + break; + } + + adapter->wvbr |= wvbr; +} + +#define IGB_STAGGERED_QUEUE_OFFSET 8 + +static void igb_spoof_check(struct igb_adapter *adapter) +{ + int j; + + if (!adapter->wvbr) + return; + + for (j = 0; j < adapter->vfs_allocated_count; j++) { + if (adapter->wvbr & BIT(j) || + adapter->wvbr & BIT(j + IGB_STAGGERED_QUEUE_OFFSET)) { + dev_warn(&adapter->pdev->dev, + "Spoof event(s) detected on VF %d\n", j); + adapter->wvbr &= + ~(BIT(j) | + BIT(j + IGB_STAGGERED_QUEUE_OFFSET)); + } + } +} + +/* Need to wait a few seconds after link up to get diagnostic information from + * the phy + */ +static void igb_update_phy_info(struct timer_list *t) +{ + struct igb_adapter *adapter = from_timer(adapter, t, phy_info_timer); + igb_get_phy_info(&adapter->hw); +} + +/** + * igb_has_link - check shared code for link and determine up/down + * @adapter: pointer to driver private info + **/ +bool igb_has_link(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + bool link_active = false; + + /* get_link_status is set on LSC (link status) interrupt or + * rx sequence error interrupt. get_link_status will stay + * false until the e1000_check_for_link establishes link + * for copper adapters ONLY + */ + switch (hw->phy.media_type) { + case e1000_media_type_copper: + if (!hw->mac.get_link_status) + return true; + fallthrough; + case e1000_media_type_internal_serdes: + 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; +} + +static bool igb_thermal_sensor_event(struct e1000_hw *hw, u32 event) +{ + bool ret = false; + u32 ctrl_ext, thstat; + + /* check for thermal sensor event on i350 copper only */ + if (hw->mac.type == e1000_i350) { + thstat = rd32(E1000_THSTAT); + ctrl_ext = rd32(E1000_CTRL_EXT); + + if ((hw->phy.media_type == e1000_media_type_copper) && + !(ctrl_ext & E1000_CTRL_EXT_LINK_MODE_SGMII)) + ret = !!(thstat & event); + } + + return ret; +} + +/** + * igb_check_lvmmc - check for malformed packets received + * and indicated in LVMMC register + * @adapter: pointer to adapter + **/ +static void igb_check_lvmmc(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 lvmmc; + + lvmmc = rd32(E1000_LVMMC); + if (lvmmc) { + if (unlikely(net_ratelimit())) { + netdev_warn(adapter->netdev, + "malformed Tx packet detected and dropped, LVMMC:0x%08x\n", + lvmmc); + } + } +} + +/** + * igb_watchdog - Timer Call-back + * @t: pointer to timer_list containing our private info pointer + **/ +static void igb_watchdog(struct timer_list *t) +{ + struct igb_adapter *adapter = from_timer(adapter, t, watchdog_timer); + /* Do the rest outside of interrupt context */ + schedule_work(&adapter->watchdog_task); +} + +static void igb_watchdog_task(struct work_struct *work) +{ + struct igb_adapter *adapter = container_of(work, + struct igb_adapter, + watchdog_task); + struct e1000_hw *hw = &adapter->hw; + struct e1000_phy_info *phy = &hw->phy; + struct net_device *netdev = adapter->netdev; + u32 link; + int i; + u32 connsw; + u16 phy_data, retry_count = 20; + + 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); + + ctrl = rd32(E1000_CTRL); + /* Links status message must follow this format */ + 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 ? + "Full" : "Half", + (ctrl & E1000_CTRL_TFCE) && + (ctrl & E1000_CTRL_RFCE) ? "RX/TX" : + (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"); + + /* adjust timeout factor according to speed/duplex */ + adapter->tx_timeout_factor = 1; + switch (adapter->link_speed) { + case SPEED_10: + adapter->tx_timeout_factor = 14; + break; + case SPEED_100: + /* maybe add some timeout factor ? */ + break; + } + + if (adapter->link_speed != SPEED_1000 || + !hw->phy.ops.read_reg) + goto no_wait; + + /* wait for Remote receiver status OK */ +retry_read_status: + if (!igb_read_phy_reg(hw, PHY_1000T_STATUS, + &phy_data)) { + if (!(phy_data & SR_1000T_REMOTE_RX_STATUS) && + retry_count) { + msleep(100); + retry_count--; + goto retry_read_status; + } else if (!retry_count) { + dev_err(&adapter->pdev->dev, "exceed max 2 second\n"); + } + } else { + dev_err(&adapter->pdev->dev, "read 1000Base-T Status Reg\n"); + } +no_wait: + netif_carrier_on(netdev); + + igb_ping_all_vfs(adapter); + igb_check_vf_rate_limit(adapter); + + /* link state has changed, schedule phy info update */ + if (!test_bit(__IGB_DOWN, &adapter->state)) + mod_timer(&adapter->phy_info_timer, + round_jiffies(jiffies + 2 * HZ)); + } + } else { + if (netif_carrier_ok(netdev)) { + adapter->link_speed = 0; + adapter->link_duplex = 0; + + /* check for thermal sensor event */ + if (igb_thermal_sensor_event(hw, + E1000_THSTAT_PWR_DOWN)) { + netdev_err(netdev, "The network adapter was stopped because it overheated\n"); + } + + /* Links status message must follow this format */ + netdev_info(netdev, "igb: %s NIC Link is Down\n", + netdev->name); + netif_carrier_off(netdev); + + igb_ping_all_vfs(adapter); + + /* link state has changed, schedule phy info update */ + if (!test_bit(__IGB_DOWN, &adapter->state)) + mod_timer(&adapter->phy_info_timer, + round_jiffies(jiffies + 2 * HZ)); + + /* 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; + } + } + } + + spin_lock(&adapter->stats64_lock); + igb_update_stats(adapter); + spin_unlock(&adapter->stats64_lock); + + for (i = 0; i < adapter->num_tx_queues; i++) { + struct igb_ring *tx_ring = adapter->tx_ring[i]; + if (!netif_carrier_ok(netdev)) { + /* We've lost link, so the controller stops DMA, + * but we've got queued Tx work that's never going + * to get done, so reset controller to flush Tx. + * (Do the reset outside of interrupt context). + */ + if (igb_desc_unused(tx_ring) + 1 < tx_ring->count) { + adapter->tx_timeout_count++; + schedule_work(&adapter->reset_task); + /* return immediately since reset is imminent */ + return; + } + } + + /* Force detection of hung controller every watchdog period */ + set_bit(IGB_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags); + } + + /* Cause software interrupt to ensure Rx ring is cleaned */ + if (adapter->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); + } else { + wr32(E1000_ICS, E1000_ICS_RXDMT0); + } + + igb_spoof_check(adapter); + igb_ptp_rx_hang(adapter); + igb_ptp_tx_hang(adapter); + + /* Check LVMMC register on i350/i354 only */ + if ((adapter->hw.mac.type == e1000_i350) || + (adapter->hw.mac.type == e1000_i354)) + igb_check_lvmmc(adapter); + + /* Reset the timer */ + 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 { + lowest_latency = 0, + low_latency = 1, + bulk_latency = 2, + latency_invalid = 255 +}; + +/** + * igb_update_ring_itr - update the dynamic ITR value based on packet size + * @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) +{ + int new_val = q_vector->itr_val; + int avg_wire_size = 0; + struct igb_adapter *adapter = q_vector->adapter; + unsigned int packets; + + /* For non-gigabit speeds, just fix the interrupt rate at 4000 + * ints/sec - ITR timer value of 120 ticks. + */ + if (adapter->link_speed != SPEED_1000) { + new_val = IGB_4K_ITR; + goto set_itr_val; + } + + packets = q_vector->rx.total_packets; + if (packets) + avg_wire_size = q_vector->rx.total_bytes / packets; + + packets = q_vector->tx.total_packets; + if (packets) + avg_wire_size = max_t(u32, avg_wire_size, + q_vector->tx.total_bytes / packets); + + /* if avg_wire_size isn't set no work was done */ + if (!avg_wire_size) + goto clear_counts; + + /* Add 24 bytes to size to account for CRC, preamble, and gap */ + avg_wire_size += 24; + + /* Don't starve jumbo frames */ + avg_wire_size = min(avg_wire_size, 3000); + + /* Give a little boost to mid-size frames */ + if ((avg_wire_size > 300) && (avg_wire_size < 1200)) + new_val = avg_wire_size / 3; + else + new_val = avg_wire_size / 2; + + /* conservative mode (itr 3) eliminates the lowest_latency setting */ + if (new_val < IGB_20K_ITR && + ((q_vector->rx.ring && adapter->rx_itr_setting == 3) || + (!q_vector->rx.ring && adapter->tx_itr_setting == 3))) + new_val = IGB_20K_ITR; + +set_itr_val: + if (new_val != q_vector->itr_val) { + q_vector->itr_val = new_val; + q_vector->set_itr = 1; + } +clear_counts: + q_vector->rx.total_bytes = 0; + q_vector->rx.total_packets = 0; + q_vector->tx.total_bytes = 0; + q_vector->tx.total_packets = 0; +} + +/** + * igb_update_itr - update the dynamic ITR value based on statistics + * @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) +{ + unsigned int packets = ring_container->total_packets; + unsigned int bytes = ring_container->total_bytes; + u8 itrval = ring_container->itr; + + /* no packets, exit with status unchanged */ + if (packets == 0) + return; + + switch (itrval) { + case lowest_latency: + /* handle TSO and jumbo frames */ + if (bytes/packets > 8000) + itrval = bulk_latency; + else if ((packets < 5) && (bytes > 512)) + itrval = low_latency; + break; + case low_latency: /* 50 usec aka 20000 ints/s */ + if (bytes > 10000) { + /* this if handles the TSO accounting */ + if (bytes/packets > 8000) + itrval = bulk_latency; + else if ((packets < 10) || ((bytes/packets) > 1200)) + itrval = bulk_latency; + else if ((packets > 35)) + itrval = lowest_latency; + } else if (bytes/packets > 2000) { + itrval = bulk_latency; + } else if (packets <= 2 && bytes < 512) { + itrval = lowest_latency; + } + break; + case bulk_latency: /* 250 usec aka 4000 ints/s */ + if (bytes > 25000) { + if (packets > 35) + itrval = low_latency; + } else if (bytes < 1500) { + itrval = low_latency; + } + break; + } + + /* clear work counters since we have the values we need */ + ring_container->total_bytes = 0; + ring_container->total_packets = 0; + + /* write updated itr to ring container */ + ring_container->itr = itrval; +} + +static void igb_set_itr(struct igb_q_vector *q_vector) +{ + struct igb_adapter *adapter = q_vector->adapter; + u32 new_itr = q_vector->itr_val; + u8 current_itr = 0; + + /* for non-gigabit speeds, just fix the interrupt rate at 4000 */ + if (adapter->link_speed != SPEED_1000) { + current_itr = 0; + new_itr = IGB_4K_ITR; + goto set_itr_now; + } + + igb_update_itr(q_vector, &q_vector->tx); + igb_update_itr(q_vector, &q_vector->rx); + + current_itr = max(q_vector->rx.itr, q_vector->tx.itr); + + /* conservative mode (itr 3) eliminates the lowest_latency setting */ + if (current_itr == lowest_latency && + ((q_vector->rx.ring && adapter->rx_itr_setting == 3) || + (!q_vector->rx.ring && adapter->tx_itr_setting == 3))) + current_itr = low_latency; + + switch (current_itr) { + /* counts and packets in update_itr are dependent on these numbers */ + case lowest_latency: + new_itr = IGB_70K_ITR; /* 70,000 ints/sec */ + break; + case low_latency: + new_itr = IGB_20K_ITR; /* 20,000 ints/sec */ + break; + case bulk_latency: + new_itr = IGB_4K_ITR; /* 4,000 ints/sec */ + break; + default: + break; + } + +set_itr_now: + if (new_itr != q_vector->itr_val) { + /* this attempts to bias the interrupt rate towards Bulk + * by adding intermediate steps when interrupt rate is + * increasing + */ + new_itr = new_itr > q_vector->itr_val ? + max((new_itr * q_vector->itr_val) / + (new_itr + (q_vector->itr_val >> 2)), + new_itr) : new_itr; + /* Don't write the value here; it resets the adapter's + * internal timer, and causes us to delay far longer than + * we should between interrupts. Instead, we write the ITR + * value at the beginning of the next interrupt so the timing + * ends up being correct. + */ + q_vector->itr_val = new_itr; + q_vector->set_itr = 1; + } +} + +static void igb_tx_ctxtdesc(struct igb_ring *tx_ring, + struct igb_tx_buffer *first, + u32 vlan_macip_lens, u32 type_tucmd, + u32 mss_l4len_idx) +{ + struct e1000_adv_tx_context_desc *context_desc; + u16 i = tx_ring->next_to_use; + struct timespec64 ts; + + context_desc = IGB_TX_CTXTDESC(tx_ring, i); + + i++; + tx_ring->next_to_use = (i < tx_ring->count) ? i : 0; + + /* set bits to identify this as an advanced context descriptor */ + type_tucmd |= E1000_TXD_CMD_DEXT | E1000_ADVTXD_DTYP_CTXT; + + /* For 82575, context index must be unique per ring. */ + if (test_bit(IGB_RING_FLAG_TX_CTX_IDX, &tx_ring->flags)) + mss_l4len_idx |= tx_ring->reg_idx << 4; + + context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens); + context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd); + context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx); + + /* We assume there is always a valid tx time available. Invalid times + * should have been handled by the upper layers. + */ + if (tx_ring->launchtime_enable) { + ts = ktime_to_timespec64(first->skb->tstamp); + skb_txtime_consumed(first->skb); + context_desc->seqnum_seed = cpu_to_le32(ts.tv_nsec / 32); + } else { + context_desc->seqnum_seed = 0; + } +} + +static int igb_tso(struct igb_ring *tx_ring, + struct igb_tx_buffer *first, + u8 *hdr_len) +{ + u32 vlan_macip_lens, type_tucmd, mss_l4len_idx; + struct sk_buff *skb = first->skb; + union { + struct iphdr *v4; + struct ipv6hdr *v6; + unsigned char *hdr; + } ip; + union { + struct tcphdr *tcp; + struct udphdr *udp; + unsigned char *hdr; + } l4; + u32 paylen, l4_offset; + int err; + + if (skb->ip_summed != CHECKSUM_PARTIAL) + return 0; + + if (!skb_is_gso(skb)) + return 0; + + err = skb_cow_head(skb, 0); + if (err < 0) + return err; + + ip.hdr = skb_network_header(skb); + l4.hdr = skb_checksum_start(skb); + + /* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */ + type_tucmd = (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) ? + E1000_ADVTXD_TUCMD_L4T_UDP : E1000_ADVTXD_TUCMD_L4T_TCP; + + /* initialize outer IP header fields */ + if (ip.v4->version == 4) { + unsigned char *csum_start = skb_checksum_start(skb); + unsigned char *trans_start = ip.hdr + (ip.v4->ihl * 4); + + /* IP header will have to cancel out any data that + * is not a part of the outer IP header + */ + ip.v4->check = csum_fold(csum_partial(trans_start, + csum_start - trans_start, + 0)); + type_tucmd |= E1000_ADVTXD_TUCMD_IPV4; + + ip.v4->tot_len = 0; + first->tx_flags |= IGB_TX_FLAGS_TSO | + IGB_TX_FLAGS_CSUM | + IGB_TX_FLAGS_IPV4; + } else { + ip.v6->payload_len = 0; + first->tx_flags |= IGB_TX_FLAGS_TSO | + IGB_TX_FLAGS_CSUM; + } + + /* determine offset of inner transport header */ + l4_offset = l4.hdr - skb->data; + + /* remove payload length from inner checksum */ + paylen = skb->len - l4_offset; + if (type_tucmd & E1000_ADVTXD_TUCMD_L4T_TCP) { + /* compute length of segmentation header */ + *hdr_len = (l4.tcp->doff * 4) + l4_offset; + csum_replace_by_diff(&l4.tcp->check, + (__force __wsum)htonl(paylen)); + } else { + /* compute length of segmentation header */ + *hdr_len = sizeof(*l4.udp) + l4_offset; + csum_replace_by_diff(&l4.udp->check, + (__force __wsum)htonl(paylen)); + } + + /* update gso size and bytecount with header size */ + first->gso_segs = skb_shinfo(skb)->gso_segs; + first->bytecount += (first->gso_segs - 1) * *hdr_len; + + /* MSS L4LEN IDX */ + mss_l4len_idx = (*hdr_len - l4_offset) << E1000_ADVTXD_L4LEN_SHIFT; + mss_l4len_idx |= skb_shinfo(skb)->gso_size << E1000_ADVTXD_MSS_SHIFT; + + /* VLAN MACLEN IPLEN */ + vlan_macip_lens = l4.hdr - ip.hdr; + vlan_macip_lens |= (ip.hdr - skb->data) << E1000_ADVTXD_MACLEN_SHIFT; + vlan_macip_lens |= first->tx_flags & IGB_TX_FLAGS_VLAN_MASK; + + igb_tx_ctxtdesc(tx_ring, first, vlan_macip_lens, + type_tucmd, mss_l4len_idx); + + return 1; +} + +static void igb_tx_csum(struct igb_ring *tx_ring, struct igb_tx_buffer *first) +{ + struct sk_buff *skb = first->skb; + u32 vlan_macip_lens = 0; + u32 type_tucmd = 0; + + if (skb->ip_summed != CHECKSUM_PARTIAL) { +csum_failed: + if (!(first->tx_flags & IGB_TX_FLAGS_VLAN) && + !tx_ring->launchtime_enable) + return; + goto no_csum; + } + + switch (skb->csum_offset) { + case offsetof(struct tcphdr, check): + type_tucmd = E1000_ADVTXD_TUCMD_L4T_TCP; + fallthrough; + case offsetof(struct udphdr, check): + break; + case offsetof(struct sctphdr, checksum): + /* validate that this is actually an SCTP request */ + if (skb_csum_is_sctp(skb)) { + type_tucmd = E1000_ADVTXD_TUCMD_L4T_SCTP; + break; + } + fallthrough; + default: + skb_checksum_help(skb); + goto csum_failed; + } + + /* update TX checksum flag */ + first->tx_flags |= IGB_TX_FLAGS_CSUM; + vlan_macip_lens = skb_checksum_start_offset(skb) - + skb_network_offset(skb); +no_csum: + vlan_macip_lens |= skb_network_offset(skb) << E1000_ADVTXD_MACLEN_SHIFT; + vlan_macip_lens |= first->tx_flags & IGB_TX_FLAGS_VLAN_MASK; + + igb_tx_ctxtdesc(tx_ring, first, vlan_macip_lens, type_tucmd, 0); +} + +#define IGB_SET_FLAG(_input, _flag, _result) \ + ((_flag <= _result) ? \ + ((u32)(_input & _flag) * (_result / _flag)) : \ + ((u32)(_input & _flag) / (_flag / _result))) + +static u32 igb_tx_cmd_type(struct sk_buff *skb, u32 tx_flags) +{ + /* set type for advanced descriptor with frame checksum insertion */ + u32 cmd_type = E1000_ADVTXD_DTYP_DATA | + E1000_ADVTXD_DCMD_DEXT | + E1000_ADVTXD_DCMD_IFCS; + + /* set HW vlan bit if vlan is present */ + cmd_type |= IGB_SET_FLAG(tx_flags, IGB_TX_FLAGS_VLAN, + (E1000_ADVTXD_DCMD_VLE)); + + /* set segmentation bits for TSO */ + cmd_type |= IGB_SET_FLAG(tx_flags, IGB_TX_FLAGS_TSO, + (E1000_ADVTXD_DCMD_TSE)); + + /* set timestamp bit if present */ + cmd_type |= IGB_SET_FLAG(tx_flags, IGB_TX_FLAGS_TSTAMP, + (E1000_ADVTXD_MAC_TSTAMP)); + + /* insert frame checksum */ + cmd_type ^= IGB_SET_FLAG(skb->no_fcs, 1, E1000_ADVTXD_DCMD_IFCS); + + return cmd_type; +} + +static void igb_tx_olinfo_status(struct igb_ring *tx_ring, + union e1000_adv_tx_desc *tx_desc, + u32 tx_flags, unsigned int paylen) +{ + u32 olinfo_status = paylen << E1000_ADVTXD_PAYLEN_SHIFT; + + /* 82575 requires a unique index per ring */ + if (test_bit(IGB_RING_FLAG_TX_CTX_IDX, &tx_ring->flags)) + olinfo_status |= tx_ring->reg_idx << 4; + + /* insert L4 checksum */ + olinfo_status |= IGB_SET_FLAG(tx_flags, + IGB_TX_FLAGS_CSUM, + (E1000_TXD_POPTS_TXSM << 8)); + + /* insert IPv4 checksum */ + olinfo_status |= IGB_SET_FLAG(tx_flags, + IGB_TX_FLAGS_IPV4, + (E1000_TXD_POPTS_IXSM << 8)); + + tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); +} + +static int __igb_maybe_stop_tx(struct igb_ring *tx_ring, const u16 size) +{ + struct net_device *netdev = tx_ring->netdev; + + netif_stop_subqueue(netdev, tx_ring->queue_index); + + /* Herbert's original patch had: + * smp_mb__after_netif_stop_queue(); + * but since that doesn't exist yet, just open code it. + */ + smp_mb(); + + /* We need to check again in a case another CPU has just + * made room available. + */ + if (igb_desc_unused(tx_ring) < size) + return -EBUSY; + + /* A reprieve! */ + netif_wake_subqueue(netdev, tx_ring->queue_index); + + u64_stats_update_begin(&tx_ring->tx_syncp2); + tx_ring->tx_stats.restart_queue2++; + u64_stats_update_end(&tx_ring->tx_syncp2); + + return 0; +} + +static inline int igb_maybe_stop_tx(struct igb_ring *tx_ring, const u16 size) +{ + if (igb_desc_unused(tx_ring) >= size) + return 0; + return __igb_maybe_stop_tx(tx_ring, size); +} + +static int igb_tx_map(struct igb_ring *tx_ring, + struct igb_tx_buffer *first, + const u8 hdr_len) +{ + struct sk_buff *skb = first->skb; + struct igb_tx_buffer *tx_buffer; + union e1000_adv_tx_desc *tx_desc; + skb_frag_t *frag; + dma_addr_t dma; + unsigned int data_len, size; + u32 tx_flags = first->tx_flags; + u32 cmd_type = igb_tx_cmd_type(skb, tx_flags); + u16 i = tx_ring->next_to_use; + + tx_desc = IGB_TX_DESC(tx_ring, i); + + igb_tx_olinfo_status(tx_ring, tx_desc, tx_flags, skb->len - hdr_len); + + size = skb_headlen(skb); + data_len = skb->data_len; + + dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE); + + tx_buffer = first; + + for (frag = &skb_shinfo(skb)->frags[0];; frag++) { + if (dma_mapping_error(tx_ring->dev, dma)) + goto dma_error; + + /* record length, and DMA address */ + dma_unmap_len_set(tx_buffer, len, size); + dma_unmap_addr_set(tx_buffer, dma, dma); + + tx_desc->read.buffer_addr = cpu_to_le64(dma); + + while (unlikely(size > IGB_MAX_DATA_PER_TXD)) { + tx_desc->read.cmd_type_len = + cpu_to_le32(cmd_type ^ IGB_MAX_DATA_PER_TXD); + + i++; + tx_desc++; + if (i == tx_ring->count) { + tx_desc = IGB_TX_DESC(tx_ring, 0); + i = 0; + } + tx_desc->read.olinfo_status = 0; + + dma += IGB_MAX_DATA_PER_TXD; + size -= IGB_MAX_DATA_PER_TXD; + + tx_desc->read.buffer_addr = cpu_to_le64(dma); + } + + if (likely(!data_len)) + break; + + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type ^ size); + + i++; + tx_desc++; + if (i == tx_ring->count) { + tx_desc = IGB_TX_DESC(tx_ring, 0); + i = 0; + } + tx_desc->read.olinfo_status = 0; + + size = skb_frag_size(frag); + data_len -= size; + + dma = skb_frag_dma_map(tx_ring->dev, frag, 0, + size, DMA_TO_DEVICE); + + tx_buffer = &tx_ring->tx_buffer_info[i]; + } + + /* write last descriptor with RS and EOP bits */ + cmd_type |= size | IGB_TXD_DCMD; + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); + + netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount); + + /* set the timestamp */ + first->time_stamp = jiffies; + + skb_tx_timestamp(skb); + + /* Force memory writes to complete before letting h/w know there + * are new descriptors to fetch. (Only applicable for weak-ordered + * memory model archs, such as IA-64). + * + * We also need this memory barrier to make certain all of the + * status bits have been updated before next_to_watch is written. + */ + dma_wmb(); + + /* set next_to_watch value indicating a packet is present */ + first->next_to_watch = tx_desc; + + i++; + if (i == tx_ring->count) + i = 0; + + tx_ring->next_to_use = i; + + /* Make sure there is space in the ring for the next send. */ + igb_maybe_stop_tx(tx_ring, DESC_NEEDED); + + if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) { + writel(i, tx_ring->tail); + } + return 0; + +dma_error: + dev_err(tx_ring->dev, "TX DMA map failed\n"); + tx_buffer = &tx_ring->tx_buffer_info[i]; + + /* clear dma mappings for failed tx_buffer_info map */ + while (tx_buffer != first) { + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + + if (i-- == 0) + i += tx_ring->count; + tx_buffer = &tx_ring->tx_buffer_info[i]; + } + + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + + dev_kfree_skb_any(tx_buffer->skb); + tx_buffer->skb = NULL; + + tx_ring->next_to_use = i; + + return -1; +} + +int igb_xmit_xdp_ring(struct igb_adapter *adapter, + struct igb_ring *tx_ring, + struct xdp_frame *xdpf) +{ + struct skb_shared_info *sinfo = xdp_get_shared_info_from_frame(xdpf); + u8 nr_frags = unlikely(xdp_frame_has_frags(xdpf)) ? sinfo->nr_frags : 0; + u16 count, i, index = tx_ring->next_to_use; + struct igb_tx_buffer *tx_head = &tx_ring->tx_buffer_info[index]; + struct igb_tx_buffer *tx_buffer = tx_head; + union e1000_adv_tx_desc *tx_desc = IGB_TX_DESC(tx_ring, index); + u32 len = xdpf->len, cmd_type, olinfo_status; + void *data = xdpf->data; + + count = TXD_USE_COUNT(len); + for (i = 0; i < nr_frags; i++) + count += TXD_USE_COUNT(skb_frag_size(&sinfo->frags[i])); + + if (igb_maybe_stop_tx(tx_ring, count + 3)) + return IGB_XDP_CONSUMED; + + i = 0; + /* record the location of the first descriptor for this packet */ + tx_head->bytecount = xdp_get_frame_len(xdpf); + tx_head->type = IGB_TYPE_XDP; + tx_head->gso_segs = 1; + tx_head->xdpf = xdpf; + + olinfo_status = tx_head->bytecount << E1000_ADVTXD_PAYLEN_SHIFT; + /* 82575 requires a unique index per ring */ + if (test_bit(IGB_RING_FLAG_TX_CTX_IDX, &tx_ring->flags)) + olinfo_status |= tx_ring->reg_idx << 4; + tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); + + for (;;) { + dma_addr_t dma; + + dma = dma_map_single(tx_ring->dev, data, len, DMA_TO_DEVICE); + if (dma_mapping_error(tx_ring->dev, dma)) + goto unmap; + + /* record length, and DMA address */ + dma_unmap_len_set(tx_buffer, len, len); + dma_unmap_addr_set(tx_buffer, dma, dma); + + /* put descriptor type bits */ + cmd_type = E1000_ADVTXD_DTYP_DATA | E1000_ADVTXD_DCMD_DEXT | + E1000_ADVTXD_DCMD_IFCS | len; + + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); + tx_desc->read.buffer_addr = cpu_to_le64(dma); + + tx_buffer->protocol = 0; + + if (++index == tx_ring->count) + index = 0; + + if (i == nr_frags) + break; + + tx_buffer = &tx_ring->tx_buffer_info[index]; + tx_desc = IGB_TX_DESC(tx_ring, index); + tx_desc->read.olinfo_status = 0; + + data = skb_frag_address(&sinfo->frags[i]); + len = skb_frag_size(&sinfo->frags[i]); + i++; + } + tx_desc->read.cmd_type_len |= cpu_to_le32(IGB_TXD_DCMD); + + netdev_tx_sent_queue(txring_txq(tx_ring), tx_head->bytecount); + /* set the timestamp */ + tx_head->time_stamp = jiffies; + + /* Avoid any potential race with xdp_xmit and cleanup */ + smp_wmb(); + + /* set next_to_watch value indicating a packet is present */ + tx_head->next_to_watch = tx_desc; + tx_ring->next_to_use = index; + + /* Make sure there is space in the ring for the next send. */ + igb_maybe_stop_tx(tx_ring, DESC_NEEDED); + + if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) + writel(index, tx_ring->tail); + + return IGB_XDP_TX; + +unmap: + for (;;) { + tx_buffer = &tx_ring->tx_buffer_info[index]; + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + if (tx_buffer == tx_head) + break; + + if (!index) + index += tx_ring->count; + index--; + } + + return IGB_XDP_CONSUMED; +} + +netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, + struct igb_ring *tx_ring) +{ + struct igb_tx_buffer *first; + int tso; + u32 tx_flags = 0; + unsigned short f; + u16 count = TXD_USE_COUNT(skb_headlen(skb)); + __be16 protocol = vlan_get_protocol(skb); + u8 hdr_len = 0; + + /* 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 context descriptor, + * otherwise try next time + */ + for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) + count += TXD_USE_COUNT(skb_frag_size( + &skb_shinfo(skb)->frags[f])); + + if (igb_maybe_stop_tx(tx_ring, count + 3)) { + /* this is a hard error */ + return NETDEV_TX_BUSY; + } + + /* record the location of the first descriptor for this packet */ + first = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + first->type = IGB_TYPE_SKB; + first->skb = skb; + first->bytecount = skb->len; + first->gso_segs = 1; + + if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { + struct igb_adapter *adapter = netdev_priv(tx_ring->netdev); + + if (adapter->tstamp_config.tx_type == HWTSTAMP_TX_ON && + !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); + } else { + adapter->tx_hwtstamp_skipped++; + } + } + + if (skb_vlan_tag_present(skb)) { + tx_flags |= IGB_TX_FLAGS_VLAN; + tx_flags |= (skb_vlan_tag_get(skb) << IGB_TX_FLAGS_VLAN_SHIFT); + } + + /* record initial flags and protocol */ + first->tx_flags = tx_flags; + first->protocol = protocol; + + tso = igb_tso(tx_ring, first, &hdr_len); + if (tso < 0) + goto out_drop; + else if (!tso) + igb_tx_csum(tx_ring, first); + + if (igb_tx_map(tx_ring, first, hdr_len)) + goto cleanup_tx_tstamp; + + return NETDEV_TX_OK; + +out_drop: + dev_kfree_skb_any(first->skb); + first->skb = NULL; +cleanup_tx_tstamp: + if (unlikely(tx_flags & IGB_TX_FLAGS_TSTAMP)) { + struct igb_adapter *adapter = netdev_priv(tx_ring->netdev); + + dev_kfree_skb_any(adapter->ptp_tx_skb); + adapter->ptp_tx_skb = NULL; + if (adapter->hw.mac.type == e1000_82576) + cancel_work_sync(&adapter->ptp_tx_work); + clear_bit_unlock(__IGB_PTP_TX_IN_PROGRESS, &adapter->state); + } + + return NETDEV_TX_OK; +} + +static inline struct igb_ring *igb_tx_queue_mapping(struct igb_adapter *adapter, + struct sk_buff *skb) +{ + unsigned int r_idx = skb->queue_mapping; + + if (r_idx >= adapter->num_tx_queues) + r_idx = r_idx % adapter->num_tx_queues; + + return adapter->tx_ring[r_idx]; +} + +static netdev_tx_t igb_xmit_frame(struct sk_buff *skb, + struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + + /* The minimum packet size with TCTL.PSP set is 17 so pad the skb + * in order to meet this minimum size requirement. + */ + if (skb_put_padto(skb, 17)) + return NETDEV_TX_OK; + + return igb_xmit_frame_ring(skb, igb_tx_queue_mapping(adapter, skb)); +} + +/** + * igb_tx_timeout - Respond to a Tx Hang + * @netdev: network interface device structure + * @txqueue: number of the Tx queue that hung (unused) + **/ +static void igb_tx_timeout(struct net_device *netdev, unsigned int __always_unused txqueue) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + + /* Do the reset outside of interrupt context */ + adapter->tx_timeout_count++; + + if (hw->mac.type >= e1000_82580) + hw->dev_spec._82575.global_device_reset = true; + + schedule_work(&adapter->reset_task); + wr32(E1000_EICS, + (adapter->eims_enable_mask & ~adapter->eims_other)); +} + +static void igb_reset_task(struct work_struct *work) +{ + struct igb_adapter *adapter; + adapter = container_of(work, struct igb_adapter, reset_task); + + rtnl_lock(); + /* If we're already down or resetting, just bail */ + if (test_bit(__IGB_DOWN, &adapter->state) || + test_bit(__IGB_RESETTING, &adapter->state)) { + rtnl_unlock(); + return; + } + + igb_dump(adapter); + netdev_err(adapter->netdev, "Reset adapter\n"); + igb_reinit_locked(adapter); + rtnl_unlock(); +} + +/** + * igb_get_stats64 - Get System Network Statistics + * @netdev: network interface device structure + * @stats: rtnl_link_stats64 pointer + **/ +static void igb_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + + spin_lock(&adapter->stats64_lock); + igb_update_stats(adapter); + memcpy(stats, &adapter->stats64, sizeof(*stats)); + spin_unlock(&adapter->stats64_lock); +} + +/** + * igb_change_mtu - Change the Maximum Transfer Unit + * @netdev: network interface device structure + * @new_mtu: new value for maximum frame size + * + * Returns 0 on success, negative on failure + **/ +static int igb_change_mtu(struct net_device *netdev, int new_mtu) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + int max_frame = new_mtu + IGB_ETH_PKT_HDR_PAD; + + if (adapter->xdp_prog) { + int i; + + for (i = 0; i < adapter->num_rx_queues; i++) { + struct igb_ring *ring = adapter->rx_ring[i]; + + if (max_frame > igb_rx_bufsz(ring)) { + netdev_warn(adapter->netdev, + "Requested MTU size is not supported with XDP. Max frame size is %d\n", + max_frame); + 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)) + usleep_range(1000, 2000); + + /* igb_down has a dependency on max_frame_size */ + adapter->max_frame_size = max_frame; + + if (netif_running(netdev)) + igb_down(adapter); + + netdev_dbg(netdev, "changing MTU from %d to %d\n", + netdev->mtu, new_mtu); + netdev->mtu = new_mtu; + + if (netif_running(netdev)) + igb_up(adapter); + else + igb_reset(adapter); + + clear_bit(__IGB_RESETTING, &adapter->state); + + return 0; +} + +/** + * igb_update_stats - Update the board statistics counters + * @adapter: board private structure + **/ +void igb_update_stats(struct igb_adapter *adapter) +{ + struct rtnl_link_stats64 *net_stats = &adapter->stats64; + struct e1000_hw *hw = &adapter->hw; + struct pci_dev *pdev = adapter->pdev; + u32 reg, mpc; + int i; + u64 bytes, packets; + unsigned int start; + u64 _bytes, _packets; + + /* Prevent stats update while adapter is being reset, or if the pci + * connection is down. + */ + if (adapter->link_speed == 0) + return; + if (pci_channel_offline(pdev)) + return; + + bytes = 0; + packets = 0; + + rcu_read_lock(); + for (i = 0; i < adapter->num_rx_queues; 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; + net_stats->rx_fifo_errors += rqdpc; + } + + do { + start = u64_stats_fetch_begin(&ring->rx_syncp); + _bytes = ring->rx_stats.bytes; + _packets = ring->rx_stats.packets; + } while (u64_stats_fetch_retry(&ring->rx_syncp, start)); + bytes += _bytes; + packets += _packets; + } + + net_stats->rx_bytes = bytes; + net_stats->rx_packets = packets; + + bytes = 0; + packets = 0; + for (i = 0; i < adapter->num_tx_queues; i++) { + struct igb_ring *ring = adapter->tx_ring[i]; + do { + start = u64_stats_fetch_begin(&ring->tx_syncp); + _bytes = ring->tx_stats.bytes; + _packets = ring->tx_stats.packets; + } while (u64_stats_fetch_retry(&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); + adapter->stats.gprc += rd32(E1000_GPRC); + adapter->stats.gorc += rd32(E1000_GORCL); + rd32(E1000_GORCH); /* clear GORCL */ + adapter->stats.bprc += rd32(E1000_BPRC); + adapter->stats.mprc += rd32(E1000_MPRC); + adapter->stats.roc += rd32(E1000_ROC); + + adapter->stats.prc64 += rd32(E1000_PRC64); + adapter->stats.prc127 += rd32(E1000_PRC127); + adapter->stats.prc255 += rd32(E1000_PRC255); + adapter->stats.prc511 += rd32(E1000_PRC511); + adapter->stats.prc1023 += rd32(E1000_PRC1023); + adapter->stats.prc1522 += rd32(E1000_PRC1522); + adapter->stats.symerrs += rd32(E1000_SYMERRS); + adapter->stats.sec += rd32(E1000_SEC); + + mpc = rd32(E1000_MPC); + adapter->stats.mpc += mpc; + net_stats->rx_fifo_errors += mpc; + adapter->stats.scc += rd32(E1000_SCC); + adapter->stats.ecol += rd32(E1000_ECOL); + adapter->stats.mcc += rd32(E1000_MCC); + adapter->stats.latecol += rd32(E1000_LATECOL); + adapter->stats.dc += rd32(E1000_DC); + adapter->stats.rlec += rd32(E1000_RLEC); + adapter->stats.xonrxc += rd32(E1000_XONRXC); + adapter->stats.xontxc += rd32(E1000_XONTXC); + adapter->stats.xoffrxc += rd32(E1000_XOFFRXC); + adapter->stats.xofftxc += rd32(E1000_XOFFTXC); + adapter->stats.fcruc += rd32(E1000_FCRUC); + adapter->stats.gptc += rd32(E1000_GPTC); + adapter->stats.gotc += rd32(E1000_GOTCL); + rd32(E1000_GOTCH); /* clear GOTCL */ + adapter->stats.rnbc += rd32(E1000_RNBC); + adapter->stats.ruc += rd32(E1000_RUC); + adapter->stats.rfc += rd32(E1000_RFC); + adapter->stats.rjc += rd32(E1000_RJC); + adapter->stats.tor += rd32(E1000_TORH); + adapter->stats.tot += rd32(E1000_TOTH); + adapter->stats.tpr += rd32(E1000_TPR); + + adapter->stats.ptc64 += rd32(E1000_PTC64); + adapter->stats.ptc127 += rd32(E1000_PTC127); + adapter->stats.ptc255 += rd32(E1000_PTC255); + adapter->stats.ptc511 += rd32(E1000_PTC511); + adapter->stats.ptc1023 += rd32(E1000_PTC1023); + adapter->stats.ptc1522 += rd32(E1000_PTC1522); + + adapter->stats.mptc += rd32(E1000_MPTC); + adapter->stats.bptc += rd32(E1000_BPTC); + + adapter->stats.tpt += rd32(E1000_TPT); + adapter->stats.colc += rd32(E1000_COLC); + + adapter->stats.algnerrc += rd32(E1000_ALGNERRC); + /* read internal phy specific stats */ + reg = rd32(E1000_CTRL_EXT); + if (!(reg & E1000_CTRL_EXT_LINK_MODE_MASK)) { + adapter->stats.rxerrc += rd32(E1000_RXERRC); + + /* this stat has invalid values on i210/i211 */ + if ((hw->mac.type != e1000_i210) && + (hw->mac.type != e1000_i211)) + adapter->stats.tncrs += rd32(E1000_TNCRS); + } + + adapter->stats.tsctc += rd32(E1000_TSCTC); + adapter->stats.tsctfc += rd32(E1000_TSCTFC); + + adapter->stats.iac += rd32(E1000_IAC); + adapter->stats.icrxoc += rd32(E1000_ICRXOC); + adapter->stats.icrxptc += rd32(E1000_ICRXPTC); + adapter->stats.icrxatc += rd32(E1000_ICRXATC); + adapter->stats.ictxptc += rd32(E1000_ICTXPTC); + adapter->stats.ictxatc += rd32(E1000_ICTXATC); + adapter->stats.ictxqec += rd32(E1000_ICTXQEC); + adapter->stats.ictxqmtc += rd32(E1000_ICTXQMTC); + adapter->stats.icrxdmtc += rd32(E1000_ICRXDMTC); + + /* Fill out the OS statistics structure */ + net_stats->multicast = adapter->stats.mprc; + net_stats->collisions = adapter->stats.colc; + + /* Rx Errors */ + + /* RLEC on some newer hardware can be incorrect so build + * our own version based on RUC and ROC + */ + net_stats->rx_errors = adapter->stats.rxerrc + + adapter->stats.crcerrs + adapter->stats.algnerrc + + adapter->stats.ruc + adapter->stats.roc + + adapter->stats.cexterr; + net_stats->rx_length_errors = adapter->stats.ruc + + adapter->stats.roc; + net_stats->rx_crc_errors = adapter->stats.crcerrs; + net_stats->rx_frame_errors = adapter->stats.algnerrc; + net_stats->rx_missed_errors = adapter->stats.mpc; + + /* Tx Errors */ + net_stats->tx_errors = adapter->stats.ecol + + adapter->stats.latecol; + net_stats->tx_aborted_errors = adapter->stats.ecol; + net_stats->tx_window_errors = adapter->stats.latecol; + net_stats->tx_carrier_errors = adapter->stats.tncrs; + + /* Tx Dropped needs to be maintained elsewhere */ + + /* Management Stats */ + adapter->stats.mgptc += rd32(E1000_MGTPTC); + adapter->stats.mgprc += rd32(E1000_MGTPRC); + adapter->stats.mgpdc += rd32(E1000_MGTPDC); + + /* OS2BMC Stats */ + reg = rd32(E1000_MANC); + if (reg & E1000_MANC_EN_BMC2OS) { + adapter->stats.o2bgptc += rd32(E1000_O2BGPTC); + adapter->stats.o2bspc += rd32(E1000_O2BSPC); + adapter->stats.b2ospc += rd32(E1000_B2OSPC); + adapter->stats.b2ogprc += rd32(E1000_B2OGPRC); + } +} + +static void igb_perout(struct igb_adapter *adapter, int tsintr_tt) +{ + int pin = ptp_find_pin(adapter->ptp_clock, PTP_PF_PEROUT, tsintr_tt); + struct e1000_hw *hw = &adapter->hw; + struct timespec64 ts; + u32 tsauxc; + + if (pin < 0 || pin >= IGB_N_SDP) + return; + + spin_lock(&adapter->tmreg_lock); + + if (hw->mac.type == e1000_82580 || + hw->mac.type == e1000_i354 || + hw->mac.type == e1000_i350) { + s64 ns = timespec64_to_ns(&adapter->perout[tsintr_tt].period); + u32 systiml, systimh, level_mask, level, rem; + u64 systim, now; + + /* read systim registers in sequence */ + rd32(E1000_SYSTIMR); + systiml = rd32(E1000_SYSTIML); + systimh = rd32(E1000_SYSTIMH); + systim = (((u64)(systimh & 0xFF)) << 32) | ((u64)systiml); + now = timecounter_cyc2time(&adapter->tc, systim); + + if (pin < 2) { + level_mask = (tsintr_tt == 1) ? 0x80000 : 0x40000; + level = (rd32(E1000_CTRL) & level_mask) ? 1 : 0; + } else { + level_mask = (tsintr_tt == 1) ? 0x80 : 0x40; + level = (rd32(E1000_CTRL_EXT) & level_mask) ? 1 : 0; + } + + div_u64_rem(now, ns, &rem); + systim = systim + (ns - rem); + + /* synchronize pin level with rising/falling edges */ + div_u64_rem(now, ns << 1, &rem); + if (rem < ns) { + /* first half of period */ + if (level == 0) { + /* output is already low, skip this period */ + systim += ns; + pr_notice("igb: periodic output on %s missed falling edge\n", + adapter->sdp_config[pin].name); + } + } else { + /* second half of period */ + if (level == 1) { + /* output is already high, skip this period */ + systim += ns; + pr_notice("igb: periodic output on %s missed rising edge\n", + adapter->sdp_config[pin].name); + } + } + + /* for this chip family tv_sec is the upper part of the binary value, + * so not seconds + */ + ts.tv_nsec = (u32)systim; + ts.tv_sec = ((u32)(systim >> 32)) & 0xFF; + } else { + ts = timespec64_add(adapter->perout[tsintr_tt].start, + adapter->perout[tsintr_tt].period); + } + + /* u32 conversion of tv_sec is safe until y2106 */ + wr32((tsintr_tt == 1) ? E1000_TRGTTIML1 : E1000_TRGTTIML0, ts.tv_nsec); + wr32((tsintr_tt == 1) ? E1000_TRGTTIMH1 : E1000_TRGTTIMH0, (u32)ts.tv_sec); + tsauxc = rd32(E1000_TSAUXC); + tsauxc |= TSAUXC_EN_TT0; + wr32(E1000_TSAUXC, tsauxc); + adapter->perout[tsintr_tt].start = ts; + + spin_unlock(&adapter->tmreg_lock); +} + +static void igb_extts(struct igb_adapter *adapter, int tsintr_tt) +{ + int pin = ptp_find_pin(adapter->ptp_clock, PTP_PF_EXTTS, tsintr_tt); + int auxstmpl = (tsintr_tt == 1) ? E1000_AUXSTMPL1 : E1000_AUXSTMPL0; + int auxstmph = (tsintr_tt == 1) ? E1000_AUXSTMPH1 : E1000_AUXSTMPH0; + struct e1000_hw *hw = &adapter->hw; + struct ptp_clock_event event; + struct timespec64 ts; + unsigned long flags; + + if (pin < 0 || pin >= IGB_N_SDP) + return; + + if (hw->mac.type == e1000_82580 || + hw->mac.type == e1000_i354 || + hw->mac.type == e1000_i350) { + u64 ns = rd32(auxstmpl); + + ns += ((u64)(rd32(auxstmph) & 0xFF)) << 32; + spin_lock_irqsave(&adapter->tmreg_lock, flags); + ns = timecounter_cyc2time(&adapter->tc, ns); + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + ts = ns_to_timespec64(ns); + } else { + ts.tv_nsec = rd32(auxstmpl); + ts.tv_sec = rd32(auxstmph); + } + + event.type = PTP_CLOCK_EXTTS; + event.index = tsintr_tt; + event.timestamp = ts.tv_sec * 1000000000ULL + ts.tv_nsec; + ptp_clock_event(adapter->ptp_clock, &event); +} + +static void igb_tsync_interrupt(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 ack = 0, tsicr = rd32(E1000_TSICR); + struct ptp_clock_event event; + + if (tsicr & TSINTR_SYS_WRAP) { + event.type = PTP_CLOCK_PPS; + if (adapter->ptp_caps.pps) + ptp_clock_event(adapter->ptp_clock, &event); + ack |= TSINTR_SYS_WRAP; + } + + if (tsicr & E1000_TSICR_TXTS) { + /* retrieve hardware timestamp */ + schedule_work(&adapter->ptp_tx_work); + ack |= E1000_TSICR_TXTS; + } + + if (tsicr & TSINTR_TT0) { + igb_perout(adapter, 0); + ack |= TSINTR_TT0; + } + + if (tsicr & TSINTR_TT1) { + igb_perout(adapter, 1); + ack |= TSINTR_TT1; + } + + if (tsicr & TSINTR_AUTT0) { + igb_extts(adapter, 0); + ack |= TSINTR_AUTT0; + } + + if (tsicr & TSINTR_AUTT1) { + igb_extts(adapter, 1); + ack |= TSINTR_AUTT1; + } + + /* acknowledge the interrupts */ + wr32(E1000_TSICR, ack); +} + +static irqreturn_t igb_msix_other(int irq, void *data) +{ + struct igb_adapter *adapter = data; + struct e1000_hw *hw = &adapter->hw; + u32 icr = rd32(E1000_ICR); + /* reading ICR causes bit 31 of EICR to be cleared */ + + if (icr & E1000_ICR_DRSTA) + schedule_work(&adapter->reset_task); + + if (icr & E1000_ICR_DOUTSYNC) { + /* HW is reporting DMA is out of sync */ + adapter->stats.doosync++; + /* The DMA Out of Sync is also indication of a spoof event + * in IOV mode. Check the Wrong VM Behavior register to + * see if it is really a spoof event. + */ + igb_check_wvbr(adapter); + } + + /* Check for a mailbox event */ + if (icr & E1000_ICR_VMMB) + igb_msg_task(adapter); + + if (icr & E1000_ICR_LSC) { + hw->mac.get_link_status = 1; + /* guard against interrupt when we're going down */ + if (!test_bit(__IGB_DOWN, &adapter->state)) + mod_timer(&adapter->watchdog_timer, jiffies + 1); + } + + if (icr & E1000_ICR_TS) + igb_tsync_interrupt(adapter); + + wr32(E1000_EIMS, adapter->eims_other); + + return IRQ_HANDLED; +} + +static void igb_write_itr(struct igb_q_vector *q_vector) +{ + struct igb_adapter *adapter = q_vector->adapter; + u32 itr_val = q_vector->itr_val & 0x7FFC; + + if (!q_vector->set_itr) + return; + + if (!itr_val) + itr_val = 0x4; + + if (adapter->hw.mac.type == e1000_82575) + itr_val |= itr_val << 16; + else + itr_val |= E1000_EITR_CNT_IGNR; + + writel(itr_val, q_vector->itr_register); + q_vector->set_itr = 0; +} + +static irqreturn_t igb_msix_ring(int irq, void *data) +{ + struct igb_q_vector *q_vector = data; + + /* Write the ITR value calculated from the previous interrupt. */ + igb_write_itr(q_vector); + + napi_schedule(&q_vector->napi); + + return IRQ_HANDLED; +} + +#ifdef CONFIG_IGB_DCA +static void igb_update_tx_dca(struct igb_adapter *adapter, + struct igb_ring *tx_ring, + int cpu) +{ + struct e1000_hw *hw = &adapter->hw; + u32 txctrl = dca3_get_tag(tx_ring->dev, cpu); + + if (hw->mac.type != e1000_82575) + txctrl <<= E1000_DCA_TXCTRL_CPUID_SHIFT; + + /* 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. + */ + txctrl |= E1000_DCA_TXCTRL_DESC_RRO_EN | + E1000_DCA_TXCTRL_DATA_RRO_EN | + E1000_DCA_TXCTRL_DESC_DCA_EN; + + wr32(E1000_DCA_TXCTRL(tx_ring->reg_idx), txctrl); +} + +static void igb_update_rx_dca(struct igb_adapter *adapter, + struct igb_ring *rx_ring, + int cpu) +{ + struct e1000_hw *hw = &adapter->hw; + u32 rxctrl = dca3_get_tag(&adapter->pdev->dev, cpu); + + if (hw->mac.type != e1000_82575) + rxctrl <<= E1000_DCA_RXCTRL_CPUID_SHIFT; + + /* 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. + */ + rxctrl |= E1000_DCA_RXCTRL_DESC_RRO_EN | + E1000_DCA_RXCTRL_DESC_DCA_EN; + + wr32(E1000_DCA_RXCTRL(rx_ring->reg_idx), rxctrl); +} + +static void igb_update_dca(struct igb_q_vector *q_vector) +{ + struct igb_adapter *adapter = q_vector->adapter; + int cpu = get_cpu(); + + if (q_vector->cpu == cpu) + goto out_no_update; + + if (q_vector->tx.ring) + igb_update_tx_dca(adapter, q_vector->tx.ring, cpu); + + if (q_vector->rx.ring) + igb_update_rx_dca(adapter, q_vector->rx.ring, cpu); + + q_vector->cpu = cpu; +out_no_update: + put_cpu(); +} + +static void igb_setup_dca(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + int i; + + if (!(adapter->flags & IGB_FLAG_DCA_ENABLED)) + return; + + /* Always use CB2 mode, difference is masked in the CB driver. */ + wr32(E1000_DCA_CTRL, E1000_DCA_CTRL_DCA_MODE_CB2); + + for (i = 0; i < adapter->num_q_vectors; i++) { + adapter->q_vector[i]->cpu = -1; + igb_update_dca(adapter->q_vector[i]); + } +} + +static int __igb_notify_dca(struct device *dev, void *data) +{ + struct net_device *netdev = dev_get_drvdata(dev); + struct igb_adapter *adapter = netdev_priv(netdev); + struct pci_dev *pdev = adapter->pdev; + struct e1000_hw *hw = &adapter->hw; + unsigned long event = *(unsigned long *)data; + + switch (event) { + case DCA_PROVIDER_ADD: + /* if already enabled, don't do it again */ + if (adapter->flags & IGB_FLAG_DCA_ENABLED) + break; + if (dca_add_requester(dev) == 0) { + adapter->flags |= IGB_FLAG_DCA_ENABLED; + dev_info(&pdev->dev, "DCA enabled\n"); + igb_setup_dca(adapter); + break; + } + fallthrough; /* since DCA is disabled. */ + case DCA_PROVIDER_REMOVE: + if (adapter->flags & IGB_FLAG_DCA_ENABLED) { + /* without this a class_device is left + * hanging around in the sysfs model + */ + dca_remove_requester(dev); + dev_info(&pdev->dev, "DCA disabled\n"); + adapter->flags &= ~IGB_FLAG_DCA_ENABLED; + wr32(E1000_DCA_CTRL, E1000_DCA_CTRL_DCA_MODE_DISABLE); + } + break; + } + + return 0; +} + +static int igb_notify_dca(struct notifier_block *nb, unsigned long event, + void *p) +{ + int ret_val; + + ret_val = driver_for_each_device(&igb_driver.driver, NULL, &event, + __igb_notify_dca); + + return ret_val ? NOTIFY_BAD : NOTIFY_DONE; +} +#endif /* CONFIG_IGB_DCA */ + +#ifdef CONFIG_PCI_IOV +static int igb_vf_configure(struct igb_adapter *adapter, int vf) +{ + unsigned char mac_addr[ETH_ALEN]; + + eth_zero_addr(mac_addr); + igb_set_vf_mac(adapter, vf, mac_addr); + + /* By default spoof check is enabled for all VFs */ + adapter->vf_data[vf].spoofchk_enabled = true; + + /* By default VFs are not trusted */ + adapter->vf_data[vf].trusted = false; + + return 0; +} + +#endif +static void igb_ping_all_vfs(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 ping; + int i; + + for (i = 0 ; i < adapter->vfs_allocated_count; i++) { + ping = E1000_PF_CONTROL_MSG; + if (adapter->vf_data[i].flags & IGB_VF_FLAG_CTS) + ping |= E1000_VT_MSGTYPE_CTS; + igb_write_mbx(hw, &ping, 1, i); + } +} + +static int igb_set_vf_promisc(struct igb_adapter *adapter, u32 *msgbuf, u32 vf) +{ + struct e1000_hw *hw = &adapter->hw; + u32 vmolr = rd32(E1000_VMOLR(vf)); + struct vf_data_storage *vf_data = &adapter->vf_data[vf]; + + vf_data->flags &= ~(IGB_VF_FLAG_UNI_PROMISC | + IGB_VF_FLAG_MULTI_PROMISC); + vmolr &= ~(E1000_VMOLR_ROPE | E1000_VMOLR_ROMPE | E1000_VMOLR_MPME); + + if (*msgbuf & E1000_VF_SET_PROMISC_MULTICAST) { + vmolr |= E1000_VMOLR_MPME; + vf_data->flags |= IGB_VF_FLAG_MULTI_PROMISC; + *msgbuf &= ~E1000_VF_SET_PROMISC_MULTICAST; + } else { + /* if we have hashes and we are clearing a multicast promisc + * flag we need to write the hashes to the MTA as this step + * was previously skipped + */ + if (vf_data->num_vf_mc_hashes > 30) { + vmolr |= E1000_VMOLR_MPME; + } else if (vf_data->num_vf_mc_hashes) { + int j; + + vmolr |= E1000_VMOLR_ROMPE; + for (j = 0; j < vf_data->num_vf_mc_hashes; j++) + igb_mta_set(hw, vf_data->vf_mc_hashes[j]); + } + } + + wr32(E1000_VMOLR(vf), vmolr); + + /* there are flags left unprocessed, likely not supported */ + if (*msgbuf & E1000_VT_MSGINFO_MASK) + return -EINVAL; + + return 0; +} + +static int igb_set_vf_multicasts(struct igb_adapter *adapter, + u32 *msgbuf, u32 vf) +{ + int n = (msgbuf[0] & E1000_VT_MSGINFO_MASK) >> E1000_VT_MSGINFO_SHIFT; + u16 *hash_list = (u16 *)&msgbuf[1]; + struct vf_data_storage *vf_data = &adapter->vf_data[vf]; + int i; + + /* salt away the number of multicast addresses assigned + * to this VF for later use to restore when the PF multi cast + * list changes + */ + vf_data->num_vf_mc_hashes = n; + + /* only up to 30 hash values supported */ + if (n > 30) + n = 30; + + /* store the hashes for later use */ + for (i = 0; i < n; i++) + vf_data->vf_mc_hashes[i] = hash_list[i]; + + /* Flush and reset the mta with the new values */ + igb_set_rx_mode(adapter->netdev); + + return 0; +} + +static void igb_restore_vf_multicasts(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + struct vf_data_storage *vf_data; + int i, j; + + for (i = 0; i < adapter->vfs_allocated_count; i++) { + u32 vmolr = rd32(E1000_VMOLR(i)); + + vmolr &= ~(E1000_VMOLR_ROMPE | E1000_VMOLR_MPME); + + vf_data = &adapter->vf_data[i]; + + if ((vf_data->num_vf_mc_hashes > 30) || + (vf_data->flags & IGB_VF_FLAG_MULTI_PROMISC)) { + vmolr |= E1000_VMOLR_MPME; + } else if (vf_data->num_vf_mc_hashes) { + vmolr |= E1000_VMOLR_ROMPE; + for (j = 0; j < vf_data->num_vf_mc_hashes; j++) + igb_mta_set(hw, vf_data->vf_mc_hashes[j]); + } + wr32(E1000_VMOLR(i), vmolr); + } +} + +static void igb_clear_vf_vfta(struct igb_adapter *adapter, u32 vf) +{ + struct e1000_hw *hw = &adapter->hw; + u32 pool_mask, vlvf_mask, i; + + /* create mask for VF and other pools */ + pool_mask = E1000_VLVF_POOLSEL_MASK; + vlvf_mask = BIT(E1000_VLVF_POOLSEL_SHIFT + vf); + + /* drop PF from pool bits */ + pool_mask &= ~BIT(E1000_VLVF_POOLSEL_SHIFT + + adapter->vfs_allocated_count); + + /* Find the vlan filter for this id */ + for (i = E1000_VLVF_ARRAY_SIZE; i--;) { + u32 vlvf = rd32(E1000_VLVF(i)); + u32 vfta_mask, vid, vfta; + + /* remove the vf from the pool */ + if (!(vlvf & vlvf_mask)) + continue; + + /* clear out bit from VLVF */ + vlvf ^= vlvf_mask; + + /* if other pools are present, just remove ourselves */ + if (vlvf & pool_mask) + goto update_vlvfb; + + /* if PF is present, leave VFTA */ + if (vlvf & E1000_VLVF_POOLSEL_MASK) + goto update_vlvf; + + vid = vlvf & E1000_VLVF_VLANID_MASK; + vfta_mask = BIT(vid % 32); + + /* clear bit from VFTA */ + vfta = adapter->shadow_vfta[vid / 32]; + if (vfta & vfta_mask) + hw->mac.ops.write_vfta(hw, vid / 32, vfta ^ vfta_mask); +update_vlvf: + /* clear pool selection enable */ + if (adapter->flags & IGB_FLAG_VLAN_PROMISC) + vlvf &= E1000_VLVF_POOLSEL_MASK; + else + vlvf = 0; +update_vlvfb: + /* clear pool bits */ + wr32(E1000_VLVF(i), vlvf); + } +} + +static int igb_find_vlvf_entry(struct e1000_hw *hw, u32 vlan) +{ + u32 vlvf; + int idx; + + /* short cut the special case */ + if (vlan == 0) + return 0; + + /* Search for the VLAN id in the VLVF entries */ + for (idx = E1000_VLVF_ARRAY_SIZE; --idx;) { + vlvf = rd32(E1000_VLVF(idx)); + if ((vlvf & VLAN_VID_MASK) == vlan) + break; + } + + return idx; +} + +static void igb_update_pf_vlvf(struct igb_adapter *adapter, u32 vid) +{ + struct e1000_hw *hw = &adapter->hw; + u32 bits, pf_id; + int idx; + + idx = igb_find_vlvf_entry(hw, vid); + if (!idx) + return; + + /* See if any other pools are set for this VLAN filter + * entry other than the PF. + */ + pf_id = adapter->vfs_allocated_count + E1000_VLVF_POOLSEL_SHIFT; + bits = ~BIT(pf_id) & E1000_VLVF_POOLSEL_MASK; + bits &= rd32(E1000_VLVF(idx)); + + /* Disable the filter so this falls into the default pool. */ + if (!bits) { + if (adapter->flags & IGB_FLAG_VLAN_PROMISC) + wr32(E1000_VLVF(idx), BIT(pf_id)); + else + wr32(E1000_VLVF(idx), 0); + } +} + +static s32 igb_set_vf_vlan(struct igb_adapter *adapter, u32 vid, + bool add, u32 vf) +{ + int pf_id = adapter->vfs_allocated_count; + struct e1000_hw *hw = &adapter->hw; + int err; + + /* If VLAN overlaps with one the PF is currently monitoring make + * sure that we are able to allocate a VLVF entry. This may be + * redundant but it guarantees PF will maintain visibility to + * the VLAN. + */ + if (add && test_bit(vid, adapter->active_vlans)) { + err = igb_vfta_set(hw, vid, pf_id, true, false); + if (err) + return err; + } + + err = igb_vfta_set(hw, vid, vf, add, false); + + if (add && !err) + return err; + + /* If we failed to add the VF VLAN or we are removing the VF VLAN + * we may need to drop the PF pool bit in order to allow us to free + * up the VLVF resources. + */ + if (test_bit(vid, adapter->active_vlans) || + (adapter->flags & IGB_FLAG_VLAN_PROMISC)) + igb_update_pf_vlvf(adapter, vid); + + return err; +} + +static void igb_set_vmvir(struct igb_adapter *adapter, u32 vid, u32 vf) +{ + struct e1000_hw *hw = &adapter->hw; + + if (vid) + wr32(E1000_VMVIR(vf), (vid | E1000_VMVIR_VLANA_DEFAULT)); + else + wr32(E1000_VMVIR(vf), 0); +} + +static int igb_enable_port_vlan(struct igb_adapter *adapter, int vf, + u16 vlan, u8 qos) +{ + int err; + + err = igb_set_vf_vlan(adapter, vlan, true, vf); + if (err) + return err; + + igb_set_vmvir(adapter, vlan | (qos << VLAN_PRIO_SHIFT), vf); + igb_set_vmolr(adapter, vf, !vlan); + + /* revoke access to previous VLAN */ + if (vlan != adapter->vf_data[vf].pf_vlan) + igb_set_vf_vlan(adapter, adapter->vf_data[vf].pf_vlan, + false, vf); + + adapter->vf_data[vf].pf_vlan = vlan; + adapter->vf_data[vf].pf_qos = qos; + igb_set_vf_vlan_strip(adapter, vf, true); + dev_info(&adapter->pdev->dev, + "Setting VLAN %d, QOS 0x%x on VF %d\n", vlan, qos, vf); + if (test_bit(__IGB_DOWN, &adapter->state)) { + dev_warn(&adapter->pdev->dev, + "The VF VLAN has been set, but the PF device is not up.\n"); + dev_warn(&adapter->pdev->dev, + "Bring the PF device up before attempting to use the VF device.\n"); + } + + return err; +} + +static int igb_disable_port_vlan(struct igb_adapter *adapter, int vf) +{ + /* Restore tagless access via VLAN 0 */ + igb_set_vf_vlan(adapter, 0, true, vf); + + igb_set_vmvir(adapter, 0, vf); + igb_set_vmolr(adapter, vf, true); + + /* Remove any PF assigned VLAN */ + if (adapter->vf_data[vf].pf_vlan) + igb_set_vf_vlan(adapter, adapter->vf_data[vf].pf_vlan, + false, vf); + + adapter->vf_data[vf].pf_vlan = 0; + adapter->vf_data[vf].pf_qos = 0; + igb_set_vf_vlan_strip(adapter, vf, false); + + return 0; +} + +static int igb_ndo_set_vf_vlan(struct net_device *netdev, int vf, + u16 vlan, u8 qos, __be16 vlan_proto) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + + if ((vf >= adapter->vfs_allocated_count) || (vlan > 4095) || (qos > 7)) + return -EINVAL; + + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + + return (vlan || qos) ? igb_enable_port_vlan(adapter, vf, vlan, qos) : + igb_disable_port_vlan(adapter, vf); +} + +static int igb_set_vf_vlan_msg(struct igb_adapter *adapter, u32 *msgbuf, u32 vf) +{ + int add = (msgbuf[0] & E1000_VT_MSGINFO_MASK) >> E1000_VT_MSGINFO_SHIFT; + int vid = (msgbuf[1] & E1000_VLVF_VLANID_MASK); + int ret; + + if (adapter->vf_data[vf].pf_vlan) + return -1; + + /* VLAN 0 is a special case, don't allow it to be removed */ + if (!vid && !add) + return 0; + + ret = igb_set_vf_vlan(adapter, vid, !!add, vf); + if (!ret) + igb_set_vf_vlan_strip(adapter, vf, !!vid); + return ret; +} + +static inline void igb_vf_reset(struct igb_adapter *adapter, u32 vf) +{ + struct vf_data_storage *vf_data = &adapter->vf_data[vf]; + + /* clear flags - except flag that indicates PF has set the MAC */ + vf_data->flags &= IGB_VF_FLAG_PF_SET_MAC; + vf_data->last_nack = jiffies; + + /* reset vlans for device */ + igb_clear_vf_vfta(adapter, vf); + igb_set_vf_vlan(adapter, vf_data->pf_vlan, true, vf); + igb_set_vmvir(adapter, vf_data->pf_vlan | + (vf_data->pf_qos << VLAN_PRIO_SHIFT), vf); + igb_set_vmolr(adapter, vf, !vf_data->pf_vlan); + igb_set_vf_vlan_strip(adapter, vf, !!(vf_data->pf_vlan)); + + /* reset multicast table array for vf */ + adapter->vf_data[vf].num_vf_mc_hashes = 0; + + /* Flush and reset the mta with the new values */ + igb_set_rx_mode(adapter->netdev); +} + +static void igb_vf_reset_event(struct igb_adapter *adapter, u32 vf) +{ + unsigned char *vf_mac = adapter->vf_data[vf].vf_mac_addresses; + + /* clear mac address as we were hotplug removed/added */ + if (!(adapter->vf_data[vf].flags & IGB_VF_FLAG_PF_SET_MAC)) + eth_zero_addr(vf_mac); + + /* process remaining reset events */ + igb_vf_reset(adapter, vf); +} + +static void igb_vf_reset_msg(struct igb_adapter *adapter, u32 vf) +{ + struct e1000_hw *hw = &adapter->hw; + unsigned char *vf_mac = adapter->vf_data[vf].vf_mac_addresses; + u32 reg, msgbuf[3] = {}; + u8 *addr = (u8 *)(&msgbuf[1]); + + /* process all the same items cleared in a function level reset */ + igb_vf_reset(adapter, vf); + + /* set vf mac address */ + igb_set_vf_mac(adapter, vf, vf_mac); + + /* enable transmit and receive for vf */ + reg = rd32(E1000_VFTE); + wr32(E1000_VFTE, reg | BIT(vf)); + reg = rd32(E1000_VFRE); + wr32(E1000_VFRE, reg | BIT(vf)); + + adapter->vf_data[vf].flags |= IGB_VF_FLAG_CTS; + + /* reply to reset with ack and vf mac address */ + if (!is_zero_ether_addr(vf_mac)) { + msgbuf[0] = E1000_VF_RESET | E1000_VT_MSGTYPE_ACK; + memcpy(addr, vf_mac, ETH_ALEN); + } else { + msgbuf[0] = E1000_VF_RESET | E1000_VT_MSGTYPE_NACK; + } + igb_write_mbx(hw, msgbuf, 3, vf); +} + +static void igb_flush_mac_table(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + int i; + + for (i = 0; i < hw->mac.rar_entry_count; i++) { + adapter->mac_table[i].state &= ~IGB_MAC_STATE_IN_USE; + eth_zero_addr(adapter->mac_table[i].addr); + adapter->mac_table[i].queue = 0; + igb_rar_set_index(adapter, i); + } +} + +static int igb_available_rars(struct igb_adapter *adapter, u8 queue) +{ + struct e1000_hw *hw = &adapter->hw; + /* do not count rar entries reserved for VFs MAC addresses */ + int rar_entries = hw->mac.rar_entry_count - + adapter->vfs_allocated_count; + int i, count = 0; + + for (i = 0; i < rar_entries; i++) { + /* do not count default entries */ + if (adapter->mac_table[i].state & IGB_MAC_STATE_DEFAULT) + continue; + + /* do not count "in use" entries for different queues */ + if ((adapter->mac_table[i].state & IGB_MAC_STATE_IN_USE) && + (adapter->mac_table[i].queue != queue)) + continue; + + count++; + } + + return count; +} + +/* Set default MAC address for the PF in the first RAR entry */ +static void igb_set_default_mac_filter(struct igb_adapter *adapter) +{ + struct igb_mac_addr *mac_table = &adapter->mac_table[0]; + + ether_addr_copy(mac_table->addr, adapter->hw.mac.addr); + mac_table->queue = adapter->vfs_allocated_count; + mac_table->state = IGB_MAC_STATE_DEFAULT | IGB_MAC_STATE_IN_USE; + + igb_rar_set_index(adapter, 0); +} + +/* If the filter to be added and an already existing filter express + * the same address and address type, it should be possible to only + * override the other configurations, for example the queue to steer + * traffic. + */ +static bool igb_mac_entry_can_be_used(const struct igb_mac_addr *entry, + const u8 *addr, const u8 flags) +{ + if (!(entry->state & IGB_MAC_STATE_IN_USE)) + return true; + + if ((entry->state & IGB_MAC_STATE_SRC_ADDR) != + (flags & IGB_MAC_STATE_SRC_ADDR)) + return false; + + if (!ether_addr_equal(addr, entry->addr)) + return false; + + return true; +} + +/* Add a MAC filter for 'addr' directing matching traffic to 'queue', + * 'flags' is used to indicate what kind of match is made, match is by + * default for the destination address, if matching by source address + * is desired the flag IGB_MAC_STATE_SRC_ADDR can be used. + */ +static int igb_add_mac_filter_flags(struct igb_adapter *adapter, + const u8 *addr, const u8 queue, + const u8 flags) +{ + struct e1000_hw *hw = &adapter->hw; + int rar_entries = hw->mac.rar_entry_count - + adapter->vfs_allocated_count; + int i; + + if (is_zero_ether_addr(addr)) + return -EINVAL; + + /* Search for the first empty entry in the MAC table. + * Do not touch entries at the end of the table reserved for the VF MAC + * addresses. + */ + for (i = 0; i < rar_entries; i++) { + if (!igb_mac_entry_can_be_used(&adapter->mac_table[i], + addr, flags)) + continue; + + ether_addr_copy(adapter->mac_table[i].addr, addr); + adapter->mac_table[i].queue = queue; + adapter->mac_table[i].state |= IGB_MAC_STATE_IN_USE | flags; + + igb_rar_set_index(adapter, i); + return i; + } + + return -ENOSPC; +} + +static int igb_add_mac_filter(struct igb_adapter *adapter, const u8 *addr, + const u8 queue) +{ + return igb_add_mac_filter_flags(adapter, addr, queue, 0); +} + +/* Remove a MAC filter for 'addr' directing matching traffic to + * 'queue', 'flags' is used to indicate what kind of match need to be + * removed, match is by default for the destination address, if + * matching by source address is to be removed the flag + * IGB_MAC_STATE_SRC_ADDR can be used. + */ +static int igb_del_mac_filter_flags(struct igb_adapter *adapter, + const u8 *addr, const u8 queue, + const u8 flags) +{ + struct e1000_hw *hw = &adapter->hw; + int rar_entries = hw->mac.rar_entry_count - + adapter->vfs_allocated_count; + int i; + + if (is_zero_ether_addr(addr)) + return -EINVAL; + + /* Search for matching entry in the MAC table based on given address + * and queue. Do not touch entries at the end of the table reserved + * for the VF MAC addresses. + */ + for (i = 0; i < rar_entries; i++) { + if (!(adapter->mac_table[i].state & IGB_MAC_STATE_IN_USE)) + continue; + if ((adapter->mac_table[i].state & flags) != flags) + continue; + if (adapter->mac_table[i].queue != queue) + continue; + if (!ether_addr_equal(adapter->mac_table[i].addr, addr)) + continue; + + /* When a filter for the default address is "deleted", + * we return it to its initial configuration + */ + if (adapter->mac_table[i].state & IGB_MAC_STATE_DEFAULT) { + adapter->mac_table[i].state = + IGB_MAC_STATE_DEFAULT | IGB_MAC_STATE_IN_USE; + adapter->mac_table[i].queue = + adapter->vfs_allocated_count; + } else { + adapter->mac_table[i].state = 0; + adapter->mac_table[i].queue = 0; + eth_zero_addr(adapter->mac_table[i].addr); + } + + igb_rar_set_index(adapter, i); + return 0; + } + + return -ENOENT; +} + +static int igb_del_mac_filter(struct igb_adapter *adapter, const u8 *addr, + const u8 queue) +{ + return igb_del_mac_filter_flags(adapter, addr, queue, 0); +} + +int igb_add_mac_steering_filter(struct igb_adapter *adapter, + const u8 *addr, u8 queue, u8 flags) +{ + struct e1000_hw *hw = &adapter->hw; + + /* In theory, this should be supported on 82575 as well, but + * that part wasn't easily accessible during development. + */ + if (hw->mac.type != e1000_i210) + return -EOPNOTSUPP; + + return igb_add_mac_filter_flags(adapter, addr, queue, + IGB_MAC_STATE_QUEUE_STEERING | flags); +} + +int igb_del_mac_steering_filter(struct igb_adapter *adapter, + const u8 *addr, u8 queue, u8 flags) +{ + return igb_del_mac_filter_flags(adapter, addr, queue, + IGB_MAC_STATE_QUEUE_STEERING | flags); +} + +static int igb_uc_sync(struct net_device *netdev, const unsigned char *addr) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + int ret; + + ret = igb_add_mac_filter(adapter, addr, adapter->vfs_allocated_count); + + return min_t(int, ret, 0); +} + +static int igb_uc_unsync(struct net_device *netdev, const unsigned char *addr) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + + igb_del_mac_filter(adapter, addr, adapter->vfs_allocated_count); + + return 0; +} + +static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf, + const u32 info, const u8 *addr) +{ + struct pci_dev *pdev = adapter->pdev; + struct vf_data_storage *vf_data = &adapter->vf_data[vf]; + struct list_head *pos; + struct vf_mac_filter *entry = NULL; + int ret = 0; + + if ((vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) && + !vf_data->trusted) { + dev_warn(&pdev->dev, + "VF %d requested MAC filter but is administratively denied\n", + vf); + return -EINVAL; + } + if (!is_valid_ether_addr(addr)) { + dev_warn(&pdev->dev, + "VF %d attempted to set invalid MAC filter\n", + vf); + return -EINVAL; + } + + switch (info) { + case E1000_VF_MAC_FILTER_CLR: + /* remove all unicast MAC filters related to the current VF */ + list_for_each(pos, &adapter->vf_macs.l) { + entry = list_entry(pos, struct vf_mac_filter, l); + if (entry->vf == vf) { + entry->vf = -1; + entry->free = true; + igb_del_mac_filter(adapter, entry->vf_mac, vf); + } + } + break; + case E1000_VF_MAC_FILTER_ADD: + /* try to find empty slot in the list */ + list_for_each(pos, &adapter->vf_macs.l) { + entry = list_entry(pos, struct vf_mac_filter, l); + if (entry->free) + break; + } + + if (entry && entry->free) { + entry->free = false; + entry->vf = vf; + ether_addr_copy(entry->vf_mac, addr); + + ret = igb_add_mac_filter(adapter, addr, vf); + ret = min_t(int, ret, 0); + } else { + ret = -ENOSPC; + } + + if (ret == -ENOSPC) + dev_warn(&pdev->dev, + "VF %d has requested MAC filter but there is no space for it\n", + vf); + break; + default: + ret = -EINVAL; + break; + } + + return ret; +} + +static int igb_set_vf_mac_addr(struct igb_adapter *adapter, u32 *msg, int vf) +{ + struct pci_dev *pdev = adapter->pdev; + struct vf_data_storage *vf_data = &adapter->vf_data[vf]; + u32 info = msg[0] & E1000_VT_MSGINFO_MASK; + + /* 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 = (unsigned char *)&msg[1]; + int ret = 0; + + if (!info) { + if ((vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) && + !vf_data->trusted) { + dev_warn(&pdev->dev, + "VF %d attempted to override administratively set MAC address\nReload the VF driver to resume operations\n", + vf); + return -EINVAL; + } + + if (!is_valid_ether_addr(addr)) { + dev_warn(&pdev->dev, + "VF %d attempted to set invalid MAC\n", + vf); + return -EINVAL; + } + + ret = igb_set_vf_mac(adapter, vf, addr); + } else { + ret = igb_set_vf_mac_filter(adapter, vf, info, addr); + } + + return ret; +} + +static void igb_rcv_ack_from_vf(struct igb_adapter *adapter, u32 vf) +{ + struct e1000_hw *hw = &adapter->hw; + struct vf_data_storage *vf_data = &adapter->vf_data[vf]; + u32 msg = E1000_VT_MSGTYPE_NACK; + + /* if device isn't clear to send it shouldn't be reading either */ + if (!(vf_data->flags & IGB_VF_FLAG_CTS) && + time_after(jiffies, vf_data->last_nack + (2 * HZ))) { + igb_write_mbx(hw, &msg, 1, vf); + vf_data->last_nack = jiffies; + } +} + +static void igb_rcv_msg_from_vf(struct igb_adapter *adapter, u32 vf) +{ + struct pci_dev *pdev = adapter->pdev; + u32 msgbuf[E1000_VFMAILBOX_SIZE]; + struct e1000_hw *hw = &adapter->hw; + struct vf_data_storage *vf_data = &adapter->vf_data[vf]; + s32 retval; + + retval = igb_read_mbx(hw, msgbuf, E1000_VFMAILBOX_SIZE, vf, false); + + if (retval) { + /* if receive failed revoke VF CTS stats and restart init */ + dev_err(&pdev->dev, "Error receiving message from VF\n"); + vf_data->flags &= ~IGB_VF_FLAG_CTS; + if (!time_after(jiffies, vf_data->last_nack + (2 * HZ))) + goto unlock; + goto out; + } + + /* this is a message we already processed, do nothing */ + if (msgbuf[0] & (E1000_VT_MSGTYPE_ACK | E1000_VT_MSGTYPE_NACK)) + goto unlock; + + /* until the vf completes a reset it should not be + * allowed to start any configuration. + */ + if (msgbuf[0] == E1000_VF_RESET) { + /* unlocks mailbox */ + igb_vf_reset_msg(adapter, vf); + return; + } + + if (!(vf_data->flags & IGB_VF_FLAG_CTS)) { + if (!time_after(jiffies, vf_data->last_nack + (2 * HZ))) + goto unlock; + retval = -1; + goto out; + } + + switch ((msgbuf[0] & 0xFFFF)) { + case E1000_VF_SET_MAC_ADDR: + retval = igb_set_vf_mac_addr(adapter, msgbuf, vf); + break; + case E1000_VF_SET_PROMISC: + retval = igb_set_vf_promisc(adapter, msgbuf, vf); + break; + case E1000_VF_SET_MULTICAST: + retval = igb_set_vf_multicasts(adapter, msgbuf, vf); + break; + case E1000_VF_SET_LPE: + retval = igb_set_vf_rlpml(adapter, msgbuf[1], vf); + break; + case E1000_VF_SET_VLAN: + retval = -1; + if (vf_data->pf_vlan) + dev_warn(&pdev->dev, + "VF %d attempted to override administratively set VLAN tag\nReload the VF driver to resume operations\n", + vf); + else + retval = igb_set_vf_vlan_msg(adapter, msgbuf, vf); + break; + default: + dev_err(&pdev->dev, "Unhandled Msg %08x\n", msgbuf[0]); + retval = -1; + break; + } + + msgbuf[0] |= E1000_VT_MSGTYPE_CTS; +out: + /* notify the VF of the results of what it sent us */ + if (retval) + msgbuf[0] |= E1000_VT_MSGTYPE_NACK; + else + msgbuf[0] |= E1000_VT_MSGTYPE_ACK; + + /* unlocks mailbox */ + igb_write_mbx(hw, msgbuf, 1, vf); + return; + +unlock: + igb_unlock_mbx(hw, vf); +} + +static void igb_msg_task(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + unsigned long flags; + u32 vf; + + spin_lock_irqsave(&adapter->vfs_lock, flags); + for (vf = 0; vf < adapter->vfs_allocated_count; vf++) { + /* process any reset requests */ + if (!igb_check_for_rst(hw, vf)) + igb_vf_reset_event(adapter, vf); + + /* process any messages pending */ + if (!igb_check_for_msg(hw, vf)) + igb_rcv_msg_from_vf(adapter, vf); + + /* process any acks */ + if (!igb_check_for_ack(hw, vf)) + igb_rcv_ack_from_vf(adapter, vf); + } + spin_unlock_irqrestore(&adapter->vfs_lock, flags); +} + +/** + * igb_set_uta - Set unicast filter table address + * @adapter: board private structure + * @set: boolean indicating if we are setting or clearing bits + * + * The unicast table address is a register array of 32-bit registers. + * The table is meant to be used in a way similar to how the MTA is used + * however due to certain limitations in the hardware it is necessary to + * set all the hash bits to 1 and use the VMOLR ROPE bit as a promiscuous + * enable bit to allow vlan tag stripping when promiscuous mode is enabled + **/ +static void igb_set_uta(struct igb_adapter *adapter, bool set) +{ + struct e1000_hw *hw = &adapter->hw; + u32 uta = set ? ~0 : 0; + int i; + + /* we only need to do this if VMDq is enabled */ + if (!adapter->vfs_allocated_count) + return; + + for (i = hw->mac.uta_reg_count; i--;) + array_wr32(E1000_UTA, i, uta); +} + +/** + * igb_intr_msi - Interrupt Handler + * @irq: interrupt number + * @data: pointer to a network interface device structure + **/ +static irqreturn_t igb_intr_msi(int irq, void *data) +{ + struct igb_adapter *adapter = data; + struct igb_q_vector *q_vector = adapter->q_vector[0]; + struct e1000_hw *hw = &adapter->hw; + /* read ICR disables interrupts using IAM */ + u32 icr = rd32(E1000_ICR); + + igb_write_itr(q_vector); + + if (icr & E1000_ICR_DRSTA) + schedule_work(&adapter->reset_task); + + if (icr & E1000_ICR_DOUTSYNC) { + /* HW is reporting DMA is out of sync */ + adapter->stats.doosync++; + } + + if (icr & (E1000_ICR_RXSEQ | E1000_ICR_LSC)) { + hw->mac.get_link_status = 1; + if (!test_bit(__IGB_DOWN, &adapter->state)) + mod_timer(&adapter->watchdog_timer, jiffies + 1); + } + + if (icr & E1000_ICR_TS) + igb_tsync_interrupt(adapter); + + napi_schedule(&q_vector->napi); + + return IRQ_HANDLED; +} + +/** + * igb_intr - Legacy Interrupt Handler + * @irq: interrupt number + * @data: pointer to a network interface device structure + **/ +static irqreturn_t igb_intr(int irq, void *data) +{ + struct igb_adapter *adapter = data; + struct igb_q_vector *q_vector = adapter->q_vector[0]; + struct e1000_hw *hw = &adapter->hw; + /* Interrupt Auto-Mask...upon reading ICR, interrupts are masked. No + * need for the IMC write + */ + u32 icr = rd32(E1000_ICR); + + /* IMS will not auto-mask if INT_ASSERTED is not set, and if it is + * not set, then the adapter didn't send an interrupt + */ + if (!(icr & E1000_ICR_INT_ASSERTED)) + return IRQ_NONE; + + igb_write_itr(q_vector); + + if (icr & E1000_ICR_DRSTA) + schedule_work(&adapter->reset_task); + + if (icr & E1000_ICR_DOUTSYNC) { + /* HW is reporting DMA is out of sync */ + adapter->stats.doosync++; + } + + if (icr & (E1000_ICR_RXSEQ | E1000_ICR_LSC)) { + hw->mac.get_link_status = 1; + /* guard against interrupt when we're going down */ + if (!test_bit(__IGB_DOWN, &adapter->state)) + mod_timer(&adapter->watchdog_timer, jiffies + 1); + } + + if (icr & E1000_ICR_TS) + igb_tsync_interrupt(adapter); + + napi_schedule(&q_vector->napi); + + return IRQ_HANDLED; +} + +static void igb_ring_irq_enable(struct igb_q_vector *q_vector) +{ + struct igb_adapter *adapter = q_vector->adapter; + struct e1000_hw *hw = &adapter->hw; + + if ((q_vector->rx.ring && (adapter->rx_itr_setting & 3)) || + (!q_vector->rx.ring && (adapter->tx_itr_setting & 3))) { + if ((adapter->num_q_vectors == 1) && !adapter->vf_data) + igb_set_itr(q_vector); + else + igb_update_ring_itr(q_vector); + } + + if (!test_bit(__IGB_DOWN, &adapter->state)) { + if (adapter->flags & IGB_FLAG_HAS_MSIX) + wr32(E1000_EIMS, q_vector->eims_value); + else + igb_irq_enable(adapter); + } +} + +/** + * igb_poll - NAPI Rx polling callback + * @napi: napi polling structure + * @budget: count of how many packets we should handle + **/ +static int igb_poll(struct napi_struct *napi, int budget) +{ + struct igb_q_vector *q_vector = container_of(napi, + struct igb_q_vector, + napi); + bool clean_complete = true; + int work_done = 0; + +#ifdef CONFIG_IGB_DCA + if (q_vector->adapter->flags & IGB_FLAG_DCA_ENABLED) + igb_update_dca(q_vector); +#endif + if (q_vector->tx.ring) + clean_complete = igb_clean_tx_irq(q_vector, budget); + + if (q_vector->rx.ring) { + int cleaned = igb_clean_rx_irq(q_vector, budget); + + work_done += cleaned; + if (cleaned >= budget) + clean_complete = false; + } + + /* If all work not completed, return budget and keep polling */ + if (!clean_complete) + return budget; + + /* Exit the polling mode, but don't re-enable interrupts if stack might + * poll us due to busy-polling + */ + if (likely(napi_complete_done(napi, work_done))) + igb_ring_irq_enable(q_vector); + + return work_done; +} + +/** + * igb_clean_tx_irq - Reclaim resources after transmit completes + * @q_vector: pointer to q_vector containing needed info + * @napi_budget: Used to determine if we are in netpoll + * + * returns true if ring is completely cleaned + **/ +static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) +{ + struct igb_adapter *adapter = q_vector->adapter; + struct igb_ring *tx_ring = q_vector->tx.ring; + struct igb_tx_buffer *tx_buffer; + union e1000_adv_tx_desc *tx_desc; + unsigned int total_bytes = 0, total_packets = 0; + unsigned int budget = q_vector->tx.work_limit; + unsigned int i = tx_ring->next_to_clean; + + if (test_bit(__IGB_DOWN, &adapter->state)) + return true; + + tx_buffer = &tx_ring->tx_buffer_info[i]; + tx_desc = IGB_TX_DESC(tx_ring, i); + i -= tx_ring->count; + + do { + union e1000_adv_tx_desc *eop_desc = tx_buffer->next_to_watch; + + /* if next_to_watch is not set then there is no work pending */ + if (!eop_desc) + break; + + /* prevent any other reads prior to eop_desc */ + smp_rmb(); + + /* if DD is not set pending work has not been completed */ + if (!(eop_desc->wb.status & cpu_to_le32(E1000_TXD_STAT_DD))) + break; + + /* clear next_to_watch to prevent false hangs */ + tx_buffer->next_to_watch = NULL; + + /* update the statistics for this packet */ + total_bytes += tx_buffer->bytecount; + total_packets += tx_buffer->gso_segs; + + /* free the skb */ + if (tx_buffer->type == IGB_TYPE_SKB) + napi_consume_skb(tx_buffer->skb, napi_budget); + else + xdp_return_frame(tx_buffer->xdpf); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + + /* clear tx_buffer data */ + dma_unmap_len_set(tx_buffer, len, 0); + + /* clear last DMA location and unmap remaining buffers */ + while (tx_desc != eop_desc) { + tx_buffer++; + tx_desc++; + i++; + if (unlikely(!i)) { + i -= tx_ring->count; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = IGB_TX_DESC(tx_ring, 0); + } + + /* unmap any remaining paged data */ + if (dma_unmap_len(tx_buffer, len)) { + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + } + } + + /* move us one more past the eop_desc for start of next pkt */ + tx_buffer++; + tx_desc++; + i++; + if (unlikely(!i)) { + i -= tx_ring->count; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = IGB_TX_DESC(tx_ring, 0); + } + + /* issue prefetch for next Tx descriptor */ + prefetch(tx_desc); + + /* update budget accounting */ + budget--; + } while (likely(budget)); + + netdev_tx_completed_queue(txring_txq(tx_ring), + total_packets, total_bytes); + i += tx_ring->count; + tx_ring->next_to_clean = i; + u64_stats_update_begin(&tx_ring->tx_syncp); + tx_ring->tx_stats.bytes += total_bytes; + tx_ring->tx_stats.packets += total_packets; + u64_stats_update_end(&tx_ring->tx_syncp); + q_vector->tx.total_bytes += total_bytes; + q_vector->tx.total_packets += total_packets; + + if (test_bit(IGB_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags)) { + struct e1000_hw *hw = &adapter->hw; + + /* Detect a transmit hang in hardware, this serializes the + * check with the clearing of time_stamp and movement of i + */ + clear_bit(IGB_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags); + if (tx_buffer->next_to_watch && + time_after(jiffies, tx_buffer->time_stamp + + (adapter->tx_timeout_factor * HZ)) && + !(rd32(E1000_STATUS) & E1000_STATUS_TXOFF)) { + + /* detected Tx unit hang */ + dev_err(tx_ring->dev, + "Detected Tx Unit Hang\n" + " Tx Queue <%d>\n" + " TDH <%x>\n" + " TDT <%x>\n" + " next_to_use <%x>\n" + " next_to_clean <%x>\n" + "buffer_info[next_to_clean]\n" + " time_stamp <%lx>\n" + " next_to_watch <%p>\n" + " jiffies <%lx>\n" + " desc.status <%x>\n", + tx_ring->queue_index, + rd32(E1000_TDH(tx_ring->reg_idx)), + readl(tx_ring->tail), + tx_ring->next_to_use, + tx_ring->next_to_clean, + tx_buffer->time_stamp, + tx_buffer->next_to_watch, + jiffies, + tx_buffer->next_to_watch->wb.status); + netif_stop_subqueue(tx_ring->netdev, + tx_ring->queue_index); + + /* we are about to reset, no point in enabling stuff */ + return true; + } + } + +#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2) + if (unlikely(total_packets && + 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. + */ + smp_mb(); + if (__netif_subqueue_stopped(tx_ring->netdev, + tx_ring->queue_index) && + !(test_bit(__IGB_DOWN, &adapter->state))) { + netif_wake_subqueue(tx_ring->netdev, + tx_ring->queue_index); + + u64_stats_update_begin(&tx_ring->tx_syncp); + tx_ring->tx_stats.restart_queue++; + u64_stats_update_end(&tx_ring->tx_syncp); + } + } + + return !!budget; +} + +/** + * 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 + **/ +static void igb_reuse_rx_page(struct igb_ring *rx_ring, + struct igb_rx_buffer *old_buff) +{ + struct igb_rx_buffer *new_buff; + u16 nta = rx_ring->next_to_alloc; + + new_buff = &rx_ring->rx_buffer_info[nta]; + + /* update, and store next to alloc */ + nta++; + rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; + + /* Transfer page from old buffer to new buffer. + * Move each member individually to avoid possible store + * forwarding stalls. + */ + new_buff->dma = old_buff->dma; + new_buff->page = old_buff->page; + new_buff->page_offset = old_buff->page_offset; + new_buff->pagecnt_bias = old_buff->pagecnt_bias; +} + +static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, + int rx_buf_pgcnt) +{ + unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; + struct page *page = rx_buffer->page; + + /* avoid re-using remote and pfmemalloc pages */ + if (!dev_page_is_reusable(page)) + return false; + +#if (PAGE_SIZE < 8192) + /* if we are only owner of page we can reuse it */ + if (unlikely((rx_buf_pgcnt - pagecnt_bias) > 1)) + return false; +#else +#define IGB_LAST_OFFSET \ + (SKB_WITH_OVERHEAD(PAGE_SIZE) - IGB_RXBUFFER_2048) + + if (rx_buffer->page_offset > IGB_LAST_OFFSET) + return false; +#endif + + /* If we have drained the page fragment pool we need to update + * the pagecnt_bias and page count so that we fully restock the + * number of references the driver holds. + */ + if (unlikely(pagecnt_bias == 1)) { + page_ref_add(page, USHRT_MAX - 1); + rx_buffer->pagecnt_bias = USHRT_MAX; + } + + 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 + * @skb: sk_buff to place the data into + * @size: size of buffer to be added + * + * This function will add the data contained in rx_buffer->page to the skb. + **/ +static void igb_add_rx_frag(struct igb_ring *rx_ring, + struct igb_rx_buffer *rx_buffer, + struct sk_buff *skb, + unsigned int size) +{ +#if (PAGE_SIZE < 8192) + unsigned int truesize = igb_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = ring_uses_build_skb(rx_ring) ? + SKB_DATA_ALIGN(IGB_SKB_PAD + size) : + SKB_DATA_ALIGN(size); +#endif + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, + rx_buffer->page_offset, size, truesize); +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif +} + +static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring, + struct igb_rx_buffer *rx_buffer, + struct xdp_buff *xdp, + ktime_t timestamp) +{ +#if (PAGE_SIZE < 8192) + unsigned int truesize = igb_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(xdp->data_end - + xdp->data_hard_start); +#endif + unsigned int size = xdp->data_end - xdp->data; + unsigned int headlen; + struct sk_buff *skb; + + /* prefetch first cache line of first page */ + net_prefetch(xdp->data); + + /* allocate a skb to store the frags */ + skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGB_RX_HDR_LEN); + if (unlikely(!skb)) + return NULL; + + if (timestamp) + skb_hwtstamps(skb)->hwtstamp = timestamp; + + /* Determine available headroom for copy */ + headlen = size; + if (headlen > IGB_RX_HDR_LEN) + headlen = eth_get_headlen(skb->dev, xdp->data, IGB_RX_HDR_LEN); + + /* align pull length to size of long to optimize memcpy performance */ + memcpy(__skb_put(skb, headlen), xdp->data, ALIGN(headlen, sizeof(long))); + + /* update all of the pointers */ + size -= headlen; + if (size) { + skb_add_rx_frag(skb, 0, rx_buffer->page, + (xdp->data + headlen) - page_address(rx_buffer->page), + size, truesize); +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif + } else { + rx_buffer->pagecnt_bias++; + } + + return skb; +} + +static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, + struct igb_rx_buffer *rx_buffer, + struct xdp_buff *xdp, + ktime_t timestamp) +{ +#if (PAGE_SIZE < 8192) + unsigned int truesize = igb_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + + SKB_DATA_ALIGN(xdp->data_end - + xdp->data_hard_start); +#endif + unsigned int metasize = xdp->data - xdp->data_meta; + struct sk_buff *skb; + + /* prefetch first cache line of first page */ + net_prefetch(xdp->data_meta); + + /* build an skb around the page buffer */ + skb = napi_build_skb(xdp->data_hard_start, truesize); + if (unlikely(!skb)) + return NULL; + + /* update pointers within the skb to store the data */ + skb_reserve(skb, xdp->data - xdp->data_hard_start); + __skb_put(skb, xdp->data_end - xdp->data); + + if (metasize) + skb_metadata_set(skb, metasize); + + if (timestamp) + skb_hwtstamps(skb)->hwtstamp = timestamp; + + /* update buffer offset */ +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif + + return skb; +} + +static struct sk_buff *igb_run_xdp(struct igb_adapter *adapter, + struct igb_ring *rx_ring, + struct xdp_buff *xdp) +{ + int err, result = IGB_XDP_PASS; + struct bpf_prog *xdp_prog; + u32 act; + + xdp_prog = READ_ONCE(rx_ring->xdp_prog); + + if (!xdp_prog) + goto xdp_out; + + prefetchw(xdp->data_hard_start); /* xdp_frame write */ + + act = bpf_prog_run_xdp(xdp_prog, xdp); + switch (act) { + case XDP_PASS: + break; + case XDP_TX: + result = igb_xdp_xmit_back(adapter, xdp); + if (result == IGB_XDP_CONSUMED) + goto out_failure; + break; + case XDP_REDIRECT: + err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog); + if (err) + goto out_failure; + result = IGB_XDP_REDIR; + break; + default: + bpf_warn_invalid_xdp_action(adapter->netdev, xdp_prog, act); + fallthrough; + case XDP_ABORTED: +out_failure: + trace_xdp_exception(rx_ring->netdev, xdp_prog, act); + fallthrough; + case XDP_DROP: + result = IGB_XDP_CONSUMED; + break; + } +xdp_out: + return ERR_PTR(-result); +} + +static unsigned int igb_rx_frame_truesize(struct igb_ring *rx_ring, + unsigned int size) +{ + unsigned int truesize; + +#if (PAGE_SIZE < 8192) + truesize = igb_rx_pg_size(rx_ring) / 2; /* Must be power-of-2 */ +#else + truesize = ring_uses_build_skb(rx_ring) ? + SKB_DATA_ALIGN(IGB_SKB_PAD + size) + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) : + SKB_DATA_ALIGN(size); +#endif + return truesize; +} + +static void igb_rx_buffer_flip(struct igb_ring *rx_ring, + struct igb_rx_buffer *rx_buffer, + unsigned int size) +{ + unsigned int truesize = igb_rx_frame_truesize(rx_ring, size); +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif +} + +static inline void igb_rx_checksum(struct igb_ring *ring, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + skb_checksum_none_assert(skb); + + /* Ignore Checksum bit is set */ + if (igb_test_staterr(rx_desc, E1000_RXD_STAT_IXSM)) + return; + + /* Rx checksum disabled via ethtool */ + if (!(ring->netdev->features & NETIF_F_RXCSUM)) + return; + + /* TCP/UDP checksum error bit is set */ + if (igb_test_staterr(rx_desc, + E1000_RXDEXT_STATERR_TCPE | + E1000_RXDEXT_STATERR_IPE)) { + /* work around errata with sctp packets where the TCPE aka + * L4E bit is set incorrectly on 64 byte (60 byte w/o crc) + * packets, (aka let the stack check the crc32c) + */ + if (!((skb->len == 60) && + test_bit(IGB_RING_FLAG_RX_SCTP_CSUM, &ring->flags))) { + u64_stats_update_begin(&ring->rx_syncp); + ring->rx_stats.csum_err++; + u64_stats_update_end(&ring->rx_syncp); + } + /* let the stack verify checksum errors */ + return; + } + /* It must be a TCP or UDP packet with a valid checksum */ + if (igb_test_staterr(rx_desc, E1000_RXD_STAT_TCPCS | + E1000_RXD_STAT_UDPCS)) + skb->ip_summed = CHECKSUM_UNNECESSARY; + + dev_dbg(ring->dev, "cksum success: bits %08X\n", + le32_to_cpu(rx_desc->wb.upper.status_error)); +} + +static inline void igb_rx_hash(struct igb_ring *ring, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + if (ring->netdev->features & NETIF_F_RXHASH) + skb_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 + * + * 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) +{ + u32 ntc = rx_ring->next_to_clean + 1; + + /* fetch, update, and store next to clean */ + ntc = (ntc < rx_ring->count) ? ntc : 0; + rx_ring->next_to_clean = ntc; + + prefetch(IGB_RX_DESC(rx_ring, ntc)); + + if (likely(igb_test_staterr(rx_desc, E1000_RXD_STAT_EOP))) + return false; + + return true; +} + +/** + * 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. + * + * 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. + **/ +static bool igb_cleanup_headers(struct igb_ring *rx_ring, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + /* XDP packets use error pointer so abort at this point */ + if (IS_ERR(skb)) + return true; + + if (unlikely((igb_test_staterr(rx_desc, + E1000_RXDEXT_ERR_FRAME_ERR_MASK)))) { + struct net_device *netdev = rx_ring->netdev; + if (!(netdev->features & NETIF_F_RXALL)) { + dev_kfree_skb_any(skb); + return true; + } + } + + /* if eth_skb_pad returns an error the skb was freed */ + if (eth_skb_pad(skb)) + return true; + + return false; +} + +/** + * 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. + **/ +static void igb_process_skb_fields(struct igb_ring *rx_ring, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + struct net_device *dev = rx_ring->netdev; + + igb_rx_hash(rx_ring, rx_desc, skb); + + igb_rx_checksum(rx_ring, 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_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((__force __be16)rx_desc->wb.upper.vlan); + else + vid = le16_to_cpu(rx_desc->wb.upper.vlan); + + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid); + } + + skb_record_rx_queue(skb, rx_ring->queue_index); + + skb->protocol = eth_type_trans(skb, rx_ring->netdev); +} + +static unsigned int igb_rx_offset(struct igb_ring *rx_ring) +{ + return ring_uses_build_skb(rx_ring) ? IGB_SKB_PAD : 0; +} + +static struct igb_rx_buffer *igb_get_rx_buffer(struct igb_ring *rx_ring, + const unsigned int size, int *rx_buf_pgcnt) +{ + struct igb_rx_buffer *rx_buffer; + + rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + *rx_buf_pgcnt = +#if (PAGE_SIZE < 8192) + page_count(rx_buffer->page); +#else + 0; +#endif + prefetchw(rx_buffer->page); + + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + size, + DMA_FROM_DEVICE); + + rx_buffer->pagecnt_bias--; + + return rx_buffer; +} + +static void igb_put_rx_buffer(struct igb_ring *rx_ring, + struct igb_rx_buffer *rx_buffer, int rx_buf_pgcnt) +{ + if (igb_can_reuse_rx_page(rx_buffer, rx_buf_pgcnt)) { + /* hand second half of page back to the ring */ + igb_reuse_rx_page(rx_ring, rx_buffer); + } else { + /* We are not reusing the buffer so unmap it and free + * any references we are holding to it + */ + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, + igb_rx_pg_size(rx_ring), DMA_FROM_DEVICE, + IGB_RX_DMA_ATTR); + __page_frag_cache_drain(rx_buffer->page, + rx_buffer->pagecnt_bias); + } + + /* clear contents of rx_buffer */ + rx_buffer->page = NULL; +} + +static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) +{ + struct igb_adapter *adapter = q_vector->adapter; + struct igb_ring *rx_ring = q_vector->rx.ring; + struct sk_buff *skb = rx_ring->skb; + unsigned int total_bytes = 0, total_packets = 0; + u16 cleaned_count = igb_desc_unused(rx_ring); + unsigned int xdp_xmit = 0; + struct xdp_buff xdp; + u32 frame_sz = 0; + int rx_buf_pgcnt; + + /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ +#if (PAGE_SIZE < 8192) + frame_sz = igb_rx_frame_truesize(rx_ring, 0); +#endif + xdp_init_buff(&xdp, frame_sz, &rx_ring->xdp_rxq); + + while (likely(total_packets < budget)) { + union e1000_adv_rx_desc *rx_desc; + struct igb_rx_buffer *rx_buffer; + ktime_t timestamp = 0; + int pkt_offset = 0; + unsigned int size; + void *pktbuf; + + /* return some buffers to hardware, one at a time is too slow */ + if (cleaned_count >= IGB_RX_BUFFER_WRITE) { + igb_alloc_rx_buffers(rx_ring, cleaned_count); + cleaned_count = 0; + } + + rx_desc = IGB_RX_DESC(rx_ring, rx_ring->next_to_clean); + size = le16_to_cpu(rx_desc->wb.upper.length); + if (!size) + break; + + /* This memory barrier is needed to keep us from reading + * any other fields out of the rx_desc until we know the + * descriptor has been written back + */ + dma_rmb(); + + rx_buffer = igb_get_rx_buffer(rx_ring, size, &rx_buf_pgcnt); + pktbuf = page_address(rx_buffer->page) + rx_buffer->page_offset; + + /* pull rx packet timestamp if available and valid */ + if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { + int ts_hdr_len; + + ts_hdr_len = igb_ptp_rx_pktstamp(rx_ring->q_vector, + pktbuf, ×tamp); + + pkt_offset += ts_hdr_len; + size -= ts_hdr_len; + } + + /* retrieve a buffer from the ring */ + if (!skb) { + unsigned char *hard_start = pktbuf - igb_rx_offset(rx_ring); + unsigned int offset = pkt_offset + igb_rx_offset(rx_ring); + + xdp_prepare_buff(&xdp, hard_start, offset, size, true); + xdp_buff_clear_frags_flag(&xdp); +#if (PAGE_SIZE > 4096) + /* At larger PAGE_SIZE, frame_sz depend on len size */ + xdp.frame_sz = igb_rx_frame_truesize(rx_ring, size); +#endif + skb = igb_run_xdp(adapter, rx_ring, &xdp); + } + + if (IS_ERR(skb)) { + unsigned int xdp_res = -PTR_ERR(skb); + + if (xdp_res & (IGB_XDP_TX | IGB_XDP_REDIR)) { + xdp_xmit |= xdp_res; + igb_rx_buffer_flip(rx_ring, rx_buffer, size); + } else { + rx_buffer->pagecnt_bias++; + } + total_packets++; + total_bytes += size; + } else if (skb) + igb_add_rx_frag(rx_ring, rx_buffer, skb, size); + else if (ring_uses_build_skb(rx_ring)) + skb = igb_build_skb(rx_ring, rx_buffer, &xdp, + timestamp); + else + skb = igb_construct_skb(rx_ring, rx_buffer, + &xdp, timestamp); + + /* exit if we failed to retrieve a buffer */ + if (!skb) { + rx_ring->rx_stats.alloc_failed++; + rx_buffer->pagecnt_bias++; + break; + } + + igb_put_rx_buffer(rx_ring, rx_buffer, rx_buf_pgcnt); + cleaned_count++; + + /* fetch next buffer in frame if non-eop */ + if (igb_is_non_eop(rx_ring, rx_desc)) + continue; + + /* verify the packet layout is correct */ + if (igb_cleanup_headers(rx_ring, rx_desc, skb)) { + skb = NULL; + continue; + } + + /* probably a little skewed due to removing CRC */ + total_bytes += skb->len; + + /* populate checksum, timestamp, VLAN, and protocol */ + igb_process_skb_fields(rx_ring, rx_desc, skb); + + napi_gro_receive(&q_vector->napi, skb); + + /* reset skb pointer */ + skb = NULL; + + /* update budget accounting */ + total_packets++; + } + + /* place incomplete frames back on ring for completion */ + rx_ring->skb = skb; + + if (xdp_xmit & IGB_XDP_REDIR) + xdp_do_flush(); + + if (xdp_xmit & IGB_XDP_TX) { + struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter); + + igb_xdp_ring_update_tail(tx_ring); + } + + u64_stats_update_begin(&rx_ring->rx_syncp); + rx_ring->rx_stats.packets += total_packets; + rx_ring->rx_stats.bytes += total_bytes; + u64_stats_update_end(&rx_ring->rx_syncp); + q_vector->rx.total_packets += total_packets; + q_vector->rx.total_bytes += total_bytes; + + if (cleaned_count) + igb_alloc_rx_buffers(rx_ring, cleaned_count); + + return total_packets; +} + +static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, + struct igb_rx_buffer *bi) +{ + struct page *page = bi->page; + dma_addr_t dma; + + /* since we are recycling buffers we should seldom need to alloc */ + if (likely(page)) + return true; + + /* alloc new page for storage */ + page = dev_alloc_pages(igb_rx_pg_order(rx_ring)); + if (unlikely(!page)) { + rx_ring->rx_stats.alloc_failed++; + return false; + } + + /* map page for use */ + dma = dma_map_page_attrs(rx_ring->dev, page, 0, + igb_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IGB_RX_DMA_ATTR); + + /* 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)) { + __free_pages(page, igb_rx_pg_order(rx_ring)); + + rx_ring->rx_stats.alloc_failed++; + return false; + } + + bi->dma = dma; + bi->page = page; + bi->page_offset = igb_rx_offset(rx_ring); + page_ref_add(page, USHRT_MAX - 1); + bi->pagecnt_bias = USHRT_MAX; + + return true; +} + +/** + * igb_alloc_rx_buffers - Replace used receive buffers + * @rx_ring: rx descriptor ring to allocate new receive buffers + * @cleaned_count: count of buffers to allocate + **/ +void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) +{ + union e1000_adv_rx_desc *rx_desc; + struct igb_rx_buffer *bi; + u16 i = rx_ring->next_to_use; + u16 bufsz; + + /* nothing to do */ + if (!cleaned_count) + return; + + rx_desc = IGB_RX_DESC(rx_ring, i); + bi = &rx_ring->rx_buffer_info[i]; + i -= rx_ring->count; + + bufsz = igb_rx_bufsz(rx_ring); + + do { + if (!igb_alloc_mapped_page(rx_ring, bi)) + break; + + /* sync the buffer for use by the device */ + dma_sync_single_range_for_device(rx_ring->dev, bi->dma, + bi->page_offset, bufsz, + DMA_FROM_DEVICE); + + /* 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); + + rx_desc++; + bi++; + i++; + if (unlikely(!i)) { + rx_desc = IGB_RX_DESC(rx_ring, 0); + bi = rx_ring->rx_buffer_info; + i -= rx_ring->count; + } + + /* clear the length for the next_to_use descriptor */ + rx_desc->wb.upper.length = 0; + + cleaned_count--; + } while (cleaned_count); + + i += rx_ring->count; + + if (rx_ring->next_to_use != i) { + /* record the next descriptor to use */ + rx_ring->next_to_use = i; + + /* 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 + * know there are new descriptors to fetch. (Only + * applicable for weak-ordered memory model archs, + * such as IA-64). + */ + dma_wmb(); + writel(i, rx_ring->tail); + } +} + +/** + * igb_mii_ioctl - + * @netdev: pointer to netdev struct + * @ifr: interface structure + * @cmd: ioctl command to execute + **/ +static int igb_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct mii_ioctl_data *data = if_mii(ifr); + + if (adapter->hw.phy.media_type != e1000_media_type_copper) + return -EOPNOTSUPP; + + switch (cmd) { + case SIOCGMIIPHY: + data->phy_id = adapter->hw.phy.addr; + break; + case SIOCGMIIREG: + if (igb_read_phy_reg(&adapter->hw, data->reg_num & 0x1F, + &data->val_out)) + return -EIO; + break; + case SIOCSMIIREG: + default: + return -EOPNOTSUPP; + } + return 0; +} + +/** + * igb_ioctl - + * @netdev: pointer to netdev struct + * @ifr: interface structure + * @cmd: ioctl command to execute + **/ +static int igb_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) +{ + switch (cmd) { + case SIOCGMIIPHY: + case SIOCGMIIREG: + case SIOCSMIIREG: + return igb_mii_ioctl(netdev, ifr, cmd); + case SIOCGHWTSTAMP: + return igb_ptp_get_ts_config(netdev, ifr); + case SIOCSHWTSTAMP: + 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; + + if (pcie_capability_read_word(adapter->pdev, reg, value)) + return -E1000_ERR_CONFIG; + + return 0; +} + +s32 igb_write_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value) +{ + struct igb_adapter *adapter = hw->back; + + if (pcie_capability_write_word(adapter->pdev, reg, *value)) + return -E1000_ERR_CONFIG; + + return 0; +} + +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_CTAG_RX); + + if (enable) { + /* enable VLAN tag insert/strip */ + ctrl = rd32(E1000_CTRL); + ctrl |= E1000_CTRL_VME; + wr32(E1000_CTRL, ctrl); + + /* Disable CFI check */ + rctl = rd32(E1000_RCTL); + rctl &= ~E1000_RCTL_CFIEN; + wr32(E1000_RCTL, rctl); + } else { + /* disable VLAN tag insert/strip */ + ctrl = rd32(E1000_CTRL); + ctrl &= ~E1000_CTRL_VME; + wr32(E1000_CTRL, ctrl); + } + + igb_set_vf_vlan_strip(adapter, adapter->vfs_allocated_count, enable); +} + +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; + int pf_id = adapter->vfs_allocated_count; + + /* add the filter since PF can receive vlans w/o entry in vlvf */ + if (!vid || !(adapter->flags & IGB_FLAG_VLAN_PROMISC)) + igb_vfta_set(hw, vid, pf_id, true, !!vid); + + set_bit(vid, adapter->active_vlans); + + return 0; +} + +static int igb_vlan_rx_kill_vid(struct net_device *netdev, + __be16 proto, u16 vid) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + int pf_id = adapter->vfs_allocated_count; + struct e1000_hw *hw = &adapter->hw; + + /* remove VID from filter table */ + if (vid && !(adapter->flags & IGB_FLAG_VLAN_PROMISC)) + igb_vfta_set(hw, vid, pf_id, false, true); + + clear_bit(vid, adapter->active_vlans); + + return 0; +} + +static void igb_restore_vlan(struct igb_adapter *adapter) +{ + u16 vid = 1; + + igb_vlan_mode(adapter->netdev, adapter->netdev->features); + igb_vlan_rx_add_vid(adapter->netdev, htons(ETH_P_8021Q), 0); + + for_each_set_bit_from(vid, adapter->active_vlans, VLAN_N_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) +{ + struct pci_dev *pdev = adapter->pdev; + struct e1000_mac_info *mac = &adapter->hw.mac; + + mac->autoneg = 0; + + /* Make sure dplx is at most 1 bit and lsb of speed is not set + * for the switch() below to work + */ + if ((spd & 1) || (dplx & ~1)) + goto err_inval; + + /* Fiber NIC's only allow 1000 gbps Full duplex + * 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: + mac->forced_speed_duplex = ADVERTISE_10_HALF; + break; + case SPEED_10 + DUPLEX_FULL: + mac->forced_speed_duplex = ADVERTISE_10_FULL; + break; + case SPEED_100 + DUPLEX_HALF: + mac->forced_speed_duplex = ADVERTISE_100_HALF; + break; + case SPEED_100 + DUPLEX_FULL: + mac->forced_speed_duplex = ADVERTISE_100_FULL; + break; + case SPEED_1000 + DUPLEX_FULL: + mac->autoneg = 1; + adapter->hw.phy.autoneg_advertised = ADVERTISE_1000_FULL; + break; + case SPEED_1000 + DUPLEX_HALF: /* not supported */ + default: + goto err_inval; + } + + /* clear MDI, MDI(-X) override is only allowed when autoneg enabled */ + adapter->hw.phy.mdix = AUTO_ALL_MODES; + + return 0; + +err_inval: + dev_err(&pdev->dev, "Unsupported Speed/Duplex configuration\n"); + return -EINVAL; +} + +static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake, + bool runtime) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + u32 ctrl, rctl, status; + u32 wufc = runtime ? E1000_WUFC_LNKC : adapter->wol; + bool wake; + + rtnl_lock(); + netif_device_detach(netdev); + + if (netif_running(netdev)) + __igb_close(netdev, true); + + igb_ptp_suspend(adapter); + + igb_clear_interrupt_scheme(adapter); + rtnl_unlock(); + + status = rd32(E1000_STATUS); + if (status & E1000_STATUS_LU) + wufc &= ~E1000_WUFC_LNKC; + + if (wufc) { + igb_setup_rctl(adapter); + igb_set_rx_mode(netdev); + + /* turn on all-multi mode if wake on multicast is enabled */ + if (wufc & E1000_WUFC_MC) { + rctl = rd32(E1000_RCTL); + rctl |= E1000_RCTL_MPE; + wr32(E1000_RCTL, rctl); + } + + ctrl = rd32(E1000_CTRL); + ctrl |= E1000_CTRL_ADVD3WUC; + wr32(E1000_CTRL, ctrl); + + /* Allow time for pending master requests to run */ + igb_disable_pcie_master(hw); + + wr32(E1000_WUC, E1000_WUC_PME_EN); + wr32(E1000_WUFC, wufc); + } else { + wr32(E1000_WUC, 0); + wr32(E1000_WUFC, 0); + } + + wake = wufc || adapter->en_mng_pt; + if (!wake) + igb_power_down_link(adapter); + else + igb_power_up_link(adapter); + + if (enable_wake) + *enable_wake = wake; + + /* Release control of h/w to f/w. If f/w is AMT enabled, this + * would have already happened in close and is redundant. + */ + igb_release_hw_control(adapter); + + pci_disable_device(pdev); + + return 0; +} + +static void igb_deliver_wake_packet(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + struct sk_buff *skb; + u32 wupl; + + wupl = rd32(E1000_WUPL) & E1000_WUPL_MASK; + + /* WUPM stores only the first 128 bytes of the wake packet. + * Read the packet only if we have the whole thing. + */ + if ((wupl == 0) || (wupl > E1000_WUPM_BYTES)) + return; + + skb = netdev_alloc_skb_ip_align(netdev, E1000_WUPM_BYTES); + if (!skb) + return; + + skb_put(skb, wupl); + + /* Ensure reads are 32-bit aligned */ + wupl = roundup(wupl, 4); + + memcpy_fromio(skb->data, hw->hw_addr + E1000_WUPM_REG(0), wupl); + + skb->protocol = eth_type_trans(skb, netdev); + netif_rx(skb); +} + +static int __maybe_unused igb_suspend(struct device *dev) +{ + return __igb_shutdown(to_pci_dev(dev), NULL, 0); +} + +static int __maybe_unused __igb_resume(struct device *dev, bool rpm) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct net_device *netdev = pci_get_drvdata(pdev); + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + u32 err, val; + + pci_set_power_state(pdev, PCI_D0); + pci_restore_state(pdev); + pci_save_state(pdev); + + if (!pci_device_is_present(pdev)) + return -ENODEV; + err = pci_enable_device_mem(pdev); + if (err) { + dev_err(&pdev->dev, + "igb: Cannot enable PCI device from suspend\n"); + return err; + } + pci_set_master(pdev); + + pci_enable_wake(pdev, PCI_D3hot, 0); + pci_enable_wake(pdev, PCI_D3cold, 0); + + if (igb_init_interrupt_scheme(adapter, true)) { + dev_err(&pdev->dev, "Unable to allocate memory for queues\n"); + return -ENOMEM; + } + + igb_reset(adapter); + + /* let the f/w know that the h/w is now under the control of the + * driver. + */ + igb_get_hw_control(adapter); + + val = rd32(E1000_WUS); + if (val & WAKE_PKT_WUS) + igb_deliver_wake_packet(netdev); + + wr32(E1000_WUS, ~0); + + if (!rpm) + rtnl_lock(); + if (!err && netif_running(netdev)) + err = __igb_open(netdev, true); + + if (!err) + netif_device_attach(netdev); + if (!rpm) + rtnl_unlock(); + + return err; +} + +static int __maybe_unused igb_resume(struct device *dev) +{ + return __igb_resume(dev, false); +} + +static int __maybe_unused igb_runtime_idle(struct device *dev) +{ + struct net_device *netdev = dev_get_drvdata(dev); + struct igb_adapter *adapter = netdev_priv(netdev); + + if (!igb_has_link(adapter)) + pm_schedule_suspend(dev, MSEC_PER_SEC * 5); + + return -EBUSY; +} + +static int __maybe_unused igb_runtime_suspend(struct device *dev) +{ + return __igb_shutdown(to_pci_dev(dev), NULL, 1); +} + +static int __maybe_unused igb_runtime_resume(struct device *dev) +{ + return __igb_resume(dev, true); +} + +static void igb_shutdown(struct pci_dev *pdev) +{ + bool wake; + + __igb_shutdown(pdev, &wake, 0); + + if (system_state == SYSTEM_POWER_OFF) { + pci_wake_from_d3(pdev, wake); + pci_set_power_state(pdev, PCI_D3hot); + } +} + +static int igb_pci_sriov_configure(struct pci_dev *dev, int num_vfs) +{ +#ifdef CONFIG_PCI_IOV + int err; + + if (num_vfs == 0) { + return igb_disable_sriov(dev, true); + } else { + err = igb_enable_sriov(dev, num_vfs, true); + return err ? err : num_vfs; + } +#endif + return 0; +} + +/** + * igb_io_error_detected - called when PCI error is detected + * @pdev: Pointer to PCI device + * @state: The current pci connection state + * + * This function is called after a PCI bus error affecting + * this device has been detected. + **/ +static pci_ers_result_t igb_io_error_detected(struct pci_dev *pdev, + pci_channel_state_t state) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct igb_adapter *adapter = netdev_priv(netdev); + + if (state == pci_channel_io_normal) { + dev_warn(&pdev->dev, "Non-correctable non-fatal error reported.\n"); + return PCI_ERS_RESULT_CAN_RECOVER; + } + + netif_device_detach(netdev); + + if (state == pci_channel_io_perm_failure) + return PCI_ERS_RESULT_DISCONNECT; + + if (netif_running(netdev)) + igb_down(adapter); + pci_disable_device(pdev); + + /* Request a slot reset. */ + return PCI_ERS_RESULT_NEED_RESET; +} + +/** + * igb_io_slot_reset - called after the pci bus has been reset. + * @pdev: Pointer to PCI device + * + * Restart the card from scratch, as if from a cold-boot. Implementation + * resembles the first-half of the __igb_resume routine. + **/ +static pci_ers_result_t igb_io_slot_reset(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + pci_ers_result_t result; + + if (pci_enable_device_mem(pdev)) { + dev_err(&pdev->dev, + "Cannot re-enable PCI device after reset.\n"); + result = PCI_ERS_RESULT_DISCONNECT; + } else { + pci_set_master(pdev); + pci_restore_state(pdev); + pci_save_state(pdev); + + pci_enable_wake(pdev, PCI_D3hot, 0); + pci_enable_wake(pdev, PCI_D3cold, 0); + + /* In case of PCI error, adapter lose its HW address + * so we should re-assign it here. + */ + hw->hw_addr = adapter->io_addr; + + igb_reset(adapter); + wr32(E1000_WUS, ~0); + result = PCI_ERS_RESULT_RECOVERED; + } + + return result; +} + +/** + * igb_io_resume - called when traffic can start flowing again. + * @pdev: Pointer to PCI device + * + * This callback is called when the error recovery driver tells us that + * its OK to resume normal operation. Implementation resembles the + * second-half of the __igb_resume routine. + */ +static void igb_io_resume(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct igb_adapter *adapter = netdev_priv(netdev); + + if (netif_running(netdev)) { + if (igb_up(adapter)) { + dev_err(&pdev->dev, "igb_up failed after reset\n"); + return; + } + } + + netif_device_attach(netdev); + + /* let the f/w know that the h/w is now under the control of the + * driver. + */ + igb_get_hw_control(adapter); +} + +/** + * igb_rar_set_index - Sync RAL[index] and RAH[index] registers with MAC table + * @adapter: Pointer to adapter structure + * @index: Index of the RAR entry which need to be synced with MAC table + **/ +static void igb_rar_set_index(struct igb_adapter *adapter, u32 index) +{ + struct e1000_hw *hw = &adapter->hw; + u32 rar_low, rar_high; + u8 *addr = adapter->mac_table[index].addr; + + /* HW expects these to be in network order when they are plugged + * into the registers which are little endian. In order to guarantee + * that ordering we need to do an leXX_to_cpup here in order to be + * ready for the byteswap that occurs with writel + */ + rar_low = le32_to_cpup((__le32 *)(addr)); + rar_high = le16_to_cpup((__le16 *)(addr + 4)); + + /* Indicate to hardware the Address is Valid. */ + if (adapter->mac_table[index].state & IGB_MAC_STATE_IN_USE) { + if (is_valid_ether_addr(addr)) + rar_high |= E1000_RAH_AV; + + if (adapter->mac_table[index].state & IGB_MAC_STATE_SRC_ADDR) + rar_high |= E1000_RAH_ASEL_SRC_ADDR; + + switch (hw->mac.type) { + case e1000_82575: + case e1000_i210: + if (adapter->mac_table[index].state & + IGB_MAC_STATE_QUEUE_STEERING) + rar_high |= E1000_RAH_QSEL_ENABLE; + + rar_high |= E1000_RAH_POOL_1 * + adapter->mac_table[index].queue; + break; + default: + rar_high |= E1000_RAH_POOL_1 << + adapter->mac_table[index].queue; + break; + } + } + + wr32(E1000_RAL(index), rar_low); + wrfl(); + wr32(E1000_RAH(index), rar_high); + wrfl(); +} + +static int igb_set_vf_mac(struct igb_adapter *adapter, + int vf, unsigned char *mac_addr) +{ + struct e1000_hw *hw = &adapter->hw; + /* VF MAC addresses start at end of receive addresses and moves + * towards the first, as a result a collision should not be possible + */ + int rar_entry = hw->mac.rar_entry_count - (vf + 1); + unsigned char *vf_mac_addr = adapter->vf_data[vf].vf_mac_addresses; + + ether_addr_copy(vf_mac_addr, mac_addr); + ether_addr_copy(adapter->mac_table[rar_entry].addr, mac_addr); + adapter->mac_table[rar_entry].queue = vf; + adapter->mac_table[rar_entry].state |= IGB_MAC_STATE_IN_USE; + igb_rar_set_index(adapter, rar_entry); + + return 0; +} + +static int igb_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + + if (vf >= adapter->vfs_allocated_count) + return -EINVAL; + + /* Setting the VF MAC to 0 reverts the IGB_VF_FLAG_PF_SET_MAC + * flag and allows to overwrite the MAC via VF netdev. This + * is necessary to allow libvirt a way to restore the original + * MAC after unbinding vfio-pci and reloading igbvf after shutting + * down a VM. + */ + if (is_zero_ether_addr(mac)) { + adapter->vf_data[vf].flags &= ~IGB_VF_FLAG_PF_SET_MAC; + dev_info(&adapter->pdev->dev, + "remove administratively set MAC on VF %d\n", + vf); + } else if (is_valid_ether_addr(mac)) { + 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."); + /* Generate additional warning if PF is down */ + 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"); + } + } else { + return -EINVAL; + } + return igb_set_vf_mac(adapter, vf, mac); +} + +static int igb_link_mbps(int internal_link_speed) +{ + switch (internal_link_speed) { + case SPEED_100: + return 100; + case SPEED_1000: + return 1000; + default: + return 0; + } +} + +static void igb_set_vf_rate_limit(struct e1000_hw *hw, int vf, int tx_rate, + int link_speed) +{ + int rf_dec, rf_int; + u32 bcnrc_val; + + if (tx_rate != 0) { + /* Calculate the rate factor values to set */ + rf_int = link_speed / tx_rate; + rf_dec = (link_speed - (rf_int * tx_rate)); + rf_dec = (rf_dec * BIT(E1000_RTTBCNRC_RF_INT_SHIFT)) / + tx_rate; + + bcnrc_val = E1000_RTTBCNRC_RS_ENA; + bcnrc_val |= ((rf_int << E1000_RTTBCNRC_RF_INT_SHIFT) & + E1000_RTTBCNRC_RF_INT_MASK); + bcnrc_val |= (rf_dec & E1000_RTTBCNRC_RF_DEC_MASK); + } else { + bcnrc_val = 0; + } + + wr32(E1000_RTTDQSEL, vf); /* vf X uses queue X */ + /* 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); + wr32(E1000_RTTBCNRC, bcnrc_val); +} + +static void igb_check_vf_rate_limit(struct igb_adapter *adapter) +{ + int actual_link_speed, i; + bool reset_rate = false; + + /* VF TX rate limit was not set or not supported */ + if ((adapter->vf_rate_link_speed == 0) || + (adapter->hw.mac.type != e1000_82576)) + return; + + actual_link_speed = igb_link_mbps(adapter->link_speed); + if (actual_link_speed != adapter->vf_rate_link_speed) { + reset_rate = true; + adapter->vf_rate_link_speed = 0; + dev_info(&adapter->pdev->dev, + "Link speed has been changed. VF Transmit rate is disabled\n"); + } + + for (i = 0; i < adapter->vfs_allocated_count; i++) { + if (reset_rate) + adapter->vf_data[i].tx_rate = 0; + + igb_set_vf_rate_limit(&adapter->hw, i, + adapter->vf_data[i].tx_rate, + actual_link_speed); + } +} + +static int igb_ndo_set_vf_bw(struct net_device *netdev, int vf, + int min_tx_rate, int max_tx_rate) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + int actual_link_speed; + + if (hw->mac.type != e1000_82576) + return -EOPNOTSUPP; + + 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)) || + (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)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 |= (BIT(vf) | + BIT(vf + E1000_DTXSWC_VLAN_SPOOF_SHIFT)); + else + reg_val &= ~(BIT(vf) | + BIT(vf + E1000_DTXSWC_VLAN_SPOOF_SHIFT)); + wr32(reg_offset, reg_val); + + adapter->vf_data[vf].spoofchk_enabled = setting; + return 0; +} + +static int igb_ndo_set_vf_trust(struct net_device *netdev, int vf, bool setting) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + + if (vf >= adapter->vfs_allocated_count) + return -EINVAL; + if (adapter->vf_data[vf].trusted == setting) + return 0; + + adapter->vf_data[vf].trusted = setting; + + dev_info(&adapter->pdev->dev, "VF %u is %strusted\n", + vf, setting ? "" : "not "); + return 0; +} + +static int igb_ndo_get_vf_config(struct net_device *netdev, + int vf, struct ifla_vf_info *ivi) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + if (vf >= adapter->vfs_allocated_count) + return -EINVAL; + ivi->vf = vf; + memcpy(&ivi->mac, adapter->vf_data[vf].vf_mac_addresses, ETH_ALEN); + ivi->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; + ivi->trusted = adapter->vf_data[vf].trusted; + return 0; +} + +static void igb_vmm_control(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 reg; + + switch (hw->mac.type) { + case e1000_82575: + case e1000_i210: + case e1000_i211: + case e1000_i354: + default: + /* replication is not supported for 82575 */ + return; + case e1000_82576: + /* notify HW that the MAC is adding vlan tags */ + reg = rd32(E1000_DTXCTL); + reg |= E1000_DTXCTL_VLAN_ADDED; + wr32(E1000_DTXCTL, reg); + fallthrough; + case e1000_82580: + /* enable replication vlan tag stripping */ + reg = rd32(E1000_RPLOLR); + reg |= E1000_RPLOLR_STRVLAN; + wr32(E1000_RPLOLR, reg); + fallthrough; + case e1000_i350: + /* none of the above registers are supported by i350 */ + break; + } + + if (adapter->vfs_allocated_count) { + igb_vmdq_set_loopback_pf(hw, true); + igb_vmdq_set_replication_pf(hw, true); + igb_vmdq_set_anti_spoofing_pf(hw, true, + adapter->vfs_allocated_count); + } else { + igb_vmdq_set_loopback_pf(hw, false); + igb_vmdq_set_replication_pf(hw, false); + } +} + +static void igb_init_dmac(struct igb_adapter *adapter, u32 pba) +{ + struct e1000_hw *hw = &adapter->hw; + u32 dmac_thr; + u16 hwm; + u32 reg; + + if (hw->mac.type > e1000_82580) { + if (adapter->flags & IGB_FLAG_DMAC) { + /* force threshold to 0. */ + wr32(E1000_DMCTXTH, 0); + + /* 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. + */ + hwm = 64 * (pba - 6); + reg = rd32(E1000_FCRTC); + reg &= ~E1000_FCRTC_RTH_COAL_MASK; + reg |= ((hwm << E1000_FCRTC_RTH_COAL_SHIFT) + & E1000_FCRTC_RTH_COAL_MASK); + wr32(E1000_FCRTC, reg); + + /* Set the DMA Coalescing Rx threshold to PBA - 2 * max + * frame size, capping it at PBA - 10KB. + */ + dmac_thr = pba - 10; + reg = rd32(E1000_DMACR); + reg &= ~E1000_DMACR_DMACTHR_MASK; + reg |= ((dmac_thr << E1000_DMACR_DMACTHR_SHIFT) + & E1000_DMACR_DMACTHR_MASK); + + /* transition to L0x or L1 if available..*/ + reg |= (E1000_DMACR_DMAC_EN | E1000_DMACR_DMAC_LX_MASK); + + /* watchdog timer= +-1000 usec in 32usec intervals */ + reg |= (1000 >> 5); + + /* Disable BMC-to-OS Watchdog Enable */ + if (hw->mac.type != e1000_i354) + reg &= ~E1000_DMACR_DC_BMC2OSW_EN; + wr32(E1000_DMACR, reg); + + /* no lower threshold to disable + * coalescing(smart fifb)-UTRESH=0 + */ + wr32(E1000_DMCRTRH, 0); + + reg = (IGB_DMCTLX_DCFLUSH_DIS | 0x4); + + wr32(E1000_DMCTLX, reg); + + /* free space in tx packet buffer to wake from + * DMA coal + */ + wr32(E1000_DMCTXTH, (IGB_MIN_TXPBSIZE - + (IGB_TX_BUF_4096 + adapter->max_frame_size)) >> 6); + } + + if (hw->mac.type >= e1000_i210 || + (adapter->flags & IGB_FLAG_DMAC)) { + reg = rd32(E1000_PCIEMISC); + reg |= E1000_PCIEMISC_LX_DECISION; + wr32(E1000_PCIEMISC, reg); + } /* endif adapter->dmac is not disabled */ + } else if (hw->mac.type == e1000_82580) { + u32 reg = rd32(E1000_PCIEMISC); + + wr32(E1000_PCIEMISC, reg & ~E1000_PCIEMISC_LX_DECISION); + wr32(E1000_DMACR, 0); + } +} + +/** + * igb_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; +} + +static void igb_nfc_filter_exit(struct igb_adapter *adapter) +{ + struct igb_nfc_filter *rule; + + spin_lock(&adapter->nfc_lock); + + hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) + igb_erase_filter(adapter, rule); + + hlist_for_each_entry(rule, &adapter->cls_flower_list, nfc_node) + igb_erase_filter(adapter, rule); + + spin_unlock(&adapter->nfc_lock); +} + +static void igb_nfc_filter_restore(struct igb_adapter *adapter) +{ + struct igb_nfc_filter *rule; + + spin_lock(&adapter->nfc_lock); + + hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) + igb_add_filter(adapter, rule); + + spin_unlock(&adapter->nfc_lock); +} +/* igb_main.c */ diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c new file mode 100644 index 0000000000..319c544b9f --- /dev/null +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -0,0 +1,1525 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Copyright (C) 2011 Richard Cochran <richardcochran@gmail.com> */ + +#include <linux/module.h> +#include <linux/device.h> +#include <linux/pci.h> +#include <linux/ptp_classify.h> + +#include "igb.h" + +#define INCVALUE_MASK 0x7fffffff +#define ISGN 0x80000000 + +/* The 82580 timesync updates the system timer every 8ns by 8ns, + * and this update value cannot be reprogrammed. + * + * Neither the 82576 nor the 82580 offer registers wide enough to hold + * nanoseconds time values for very long. For the 82580, SYSTIM always + * counts nanoseconds, but the upper 24 bits are not available. The + * frequency is adjusted by changing the 32 bit fractional nanoseconds + * register, TIMINCA. + * + * For the 82576, the SYSTIM register time unit is affect by the + * choice of the 24 bit TININCA:IV (incvalue) field. Five bits of this + * field are needed to provide the nominal 16 nanosecond period, + * leaving 19 bits for fractional nanoseconds. + * + * We scale the NIC clock cycle by a large factor so that relatively + * small clock corrections can be added or subtracted at each clock + * tick. The drawbacks of a large factor are a) that the clock + * register overflows more quickly (not such a big deal) and b) that + * the increment per tick has to fit into 24 bits. As a result we + * need to use a shift of 19 so we can fit a value of 16 into the + * TIMINCA register. + * + * + * SYSTIMH SYSTIML + * +--------------+ +---+---+------+ + * 82576 | 32 | | 8 | 5 | 19 | + * +--------------+ +---+---+------+ + * \________ 45 bits _______/ fract + * + * +----------+---+ +--------------+ + * 82580 | 24 | 8 | | 32 | + * +----------+---+ +--------------+ + * reserved \______ 40 bits _____/ + * + * + * The 45 bit 82576 SYSTIM overflows every + * 2^45 * 10^-9 / 3600 = 9.77 hours. + * + * The 40 bit 82580 SYSTIM overflows every + * 2^40 * 10^-9 / 60 = 18.3 minutes. + * + * SYSTIM is converted to real time using a timecounter. As + * timecounter_cyc2time() allows old timestamps, the timecounter needs + * to be updated at least once per half of the SYSTIM interval. + * Scheduling of delayed work is not very accurate, and also the NIC + * clock can be adjusted to run up to 6% faster and the system clock + * up to 10% slower, so we aim for 6 minutes to be sure the actual + * interval in the NIC time is shorter than 9.16 minutes. + */ + +#define IGB_SYSTIM_OVERFLOW_PERIOD (HZ * 60 * 6) +#define IGB_PTP_TX_TIMEOUT (HZ * 15) +#define INCPERIOD_82576 BIT(E1000_TIMINCA_16NS_SHIFT) +#define INCVALUE_82576_MASK GENMASK(E1000_TIMINCA_16NS_SHIFT - 1, 0) +#define INCVALUE_82576 (16u << IGB_82576_TSYNC_SHIFT) +#define IGB_NBITS_82580 40 +#define IGB_82580_BASE_PERIOD 0x800000000 + +static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter); +static void igb_ptp_sdp_init(struct igb_adapter *adapter); + +/* SYSTIM read access for the 82576 */ +static u64 igb_ptp_read_82576(const struct cyclecounter *cc) +{ + struct igb_adapter *igb = container_of(cc, struct igb_adapter, cc); + struct e1000_hw *hw = &igb->hw; + u64 val; + u32 lo, hi; + + lo = rd32(E1000_SYSTIML); + hi = rd32(E1000_SYSTIMH); + + val = ((u64) hi) << 32; + val |= lo; + + return val; +} + +/* SYSTIM read access for the 82580 */ +static u64 igb_ptp_read_82580(const struct cyclecounter *cc) +{ + struct igb_adapter *igb = container_of(cc, struct igb_adapter, cc); + struct e1000_hw *hw = &igb->hw; + u32 lo, hi; + u64 val; + + /* The timestamp latches on lowest register read. For the 82580 + * the lowest register is SYSTIMR instead of SYSTIML. However we only + * need to provide nanosecond resolution, so we just ignore it. + */ + rd32(E1000_SYSTIMR); + lo = rd32(E1000_SYSTIML); + hi = rd32(E1000_SYSTIMH); + + val = ((u64) hi) << 32; + val |= lo; + + return val; +} + +/* SYSTIM read access for I210/I211 */ +static void igb_ptp_read_i210(struct igb_adapter *adapter, + struct timespec64 *ts) +{ + struct e1000_hw *hw = &adapter->hw; + u32 sec, nsec; + + /* The timestamp latches on lowest register read. For I210/I211, the + * lowest register is SYSTIMR. Since we only need to provide nanosecond + * resolution, we can ignore it. + */ + rd32(E1000_SYSTIMR); + nsec = rd32(E1000_SYSTIML); + sec = rd32(E1000_SYSTIMH); + + ts->tv_sec = sec; + ts->tv_nsec = nsec; +} + +static void igb_ptp_write_i210(struct igb_adapter *adapter, + const struct timespec64 *ts) +{ + struct e1000_hw *hw = &adapter->hw; + + /* Writing the SYSTIMR register is not necessary as it only provides + * sub-nanosecond resolution. + */ + wr32(E1000_SYSTIML, ts->tv_nsec); + wr32(E1000_SYSTIMH, (u32)ts->tv_sec); +} + +/** + * igb_ptp_systim_to_hwtstamp - convert system time value to hw timestamp + * @adapter: board private structure + * @hwtstamps: timestamp structure to update + * @systim: unsigned 64bit system time value. + * + * We need to convert the system time value stored in the RX/TXSTMP registers + * into a hwtstamp which can be used by the upper level timestamping functions. + * + * The 'tmreg_lock' spinlock is used to protect the consistency of the + * system time value. This is needed because reading the 64 bit time + * value involves reading two (or three) 32 bit registers. The first + * read latches the value. Ditto for writing. + * + * In addition, here have extended the system time with an overflow + * counter in software. + **/ +static void igb_ptp_systim_to_hwtstamp(struct igb_adapter *adapter, + struct skb_shared_hwtstamps *hwtstamps, + u64 systim) +{ + unsigned long flags; + u64 ns; + + memset(hwtstamps, 0, sizeof(*hwtstamps)); + + switch (adapter->hw.mac.type) { + case e1000_82576: + case e1000_82580: + case e1000_i354: + case e1000_i350: + spin_lock_irqsave(&adapter->tmreg_lock, flags); + ns = timecounter_cyc2time(&adapter->tc, systim); + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + + hwtstamps->hwtstamp = ns_to_ktime(ns); + break; + case e1000_i210: + case e1000_i211: + /* Upper 32 bits contain s, lower 32 bits contain ns. */ + hwtstamps->hwtstamp = ktime_set(systim >> 32, + systim & 0xFFFFFFFF); + break; + default: + break; + } +} + +/* PTP clock operations */ +static int igb_ptp_adjfine_82576(struct ptp_clock_info *ptp, long scaled_ppm) +{ + struct igb_adapter *igb = container_of(ptp, struct igb_adapter, + ptp_caps); + struct e1000_hw *hw = &igb->hw; + u64 incvalue; + + incvalue = adjust_by_scaled_ppm(INCVALUE_82576, scaled_ppm); + + wr32(E1000_TIMINCA, INCPERIOD_82576 | (incvalue & INCVALUE_82576_MASK)); + + return 0; +} + +static int igb_ptp_adjfine_82580(struct ptp_clock_info *ptp, long scaled_ppm) +{ + struct igb_adapter *igb = container_of(ptp, struct igb_adapter, + ptp_caps); + struct e1000_hw *hw = &igb->hw; + bool neg_adj; + u64 rate; + u32 inca; + + neg_adj = diff_by_scaled_ppm(IGB_82580_BASE_PERIOD, scaled_ppm, &rate); + + inca = rate & INCVALUE_MASK; + if (neg_adj) + inca |= ISGN; + + wr32(E1000_TIMINCA, inca); + + return 0; +} + +static int igb_ptp_adjtime_82576(struct ptp_clock_info *ptp, s64 delta) +{ + struct igb_adapter *igb = container_of(ptp, struct igb_adapter, + ptp_caps); + unsigned long flags; + + spin_lock_irqsave(&igb->tmreg_lock, flags); + timecounter_adjtime(&igb->tc, delta); + spin_unlock_irqrestore(&igb->tmreg_lock, flags); + + return 0; +} + +static int igb_ptp_adjtime_i210(struct ptp_clock_info *ptp, s64 delta) +{ + struct igb_adapter *igb = container_of(ptp, struct igb_adapter, + ptp_caps); + unsigned long flags; + struct timespec64 now, then = ns_to_timespec64(delta); + + spin_lock_irqsave(&igb->tmreg_lock, flags); + + igb_ptp_read_i210(igb, &now); + now = timespec64_add(now, then); + igb_ptp_write_i210(igb, (const struct timespec64 *)&now); + + spin_unlock_irqrestore(&igb->tmreg_lock, flags); + + return 0; +} + +static int igb_ptp_gettimex_82576(struct ptp_clock_info *ptp, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + struct igb_adapter *igb = container_of(ptp, struct igb_adapter, + ptp_caps); + struct e1000_hw *hw = &igb->hw; + unsigned long flags; + u32 lo, hi; + u64 ns; + + spin_lock_irqsave(&igb->tmreg_lock, flags); + + ptp_read_system_prets(sts); + lo = rd32(E1000_SYSTIML); + ptp_read_system_postts(sts); + hi = rd32(E1000_SYSTIMH); + + ns = timecounter_cyc2time(&igb->tc, ((u64)hi << 32) | lo); + + spin_unlock_irqrestore(&igb->tmreg_lock, flags); + + *ts = ns_to_timespec64(ns); + + return 0; +} + +static int igb_ptp_gettimex_82580(struct ptp_clock_info *ptp, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + struct igb_adapter *igb = container_of(ptp, struct igb_adapter, + ptp_caps); + struct e1000_hw *hw = &igb->hw; + unsigned long flags; + u32 lo, hi; + u64 ns; + + spin_lock_irqsave(&igb->tmreg_lock, flags); + + ptp_read_system_prets(sts); + rd32(E1000_SYSTIMR); + ptp_read_system_postts(sts); + lo = rd32(E1000_SYSTIML); + hi = rd32(E1000_SYSTIMH); + + ns = timecounter_cyc2time(&igb->tc, ((u64)hi << 32) | lo); + + spin_unlock_irqrestore(&igb->tmreg_lock, flags); + + *ts = ns_to_timespec64(ns); + + return 0; +} + +static int igb_ptp_gettimex_i210(struct ptp_clock_info *ptp, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + struct igb_adapter *igb = container_of(ptp, struct igb_adapter, + ptp_caps); + struct e1000_hw *hw = &igb->hw; + unsigned long flags; + + spin_lock_irqsave(&igb->tmreg_lock, flags); + + ptp_read_system_prets(sts); + rd32(E1000_SYSTIMR); + ptp_read_system_postts(sts); + ts->tv_nsec = rd32(E1000_SYSTIML); + ts->tv_sec = rd32(E1000_SYSTIMH); + + spin_unlock_irqrestore(&igb->tmreg_lock, flags); + + return 0; +} + +static int igb_ptp_settime_82576(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct igb_adapter *igb = container_of(ptp, struct igb_adapter, + ptp_caps); + unsigned long flags; + u64 ns; + + ns = timespec64_to_ns(ts); + + spin_lock_irqsave(&igb->tmreg_lock, flags); + + timecounter_init(&igb->tc, &igb->cc, ns); + + spin_unlock_irqrestore(&igb->tmreg_lock, flags); + + return 0; +} + +static int igb_ptp_settime_i210(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct igb_adapter *igb = container_of(ptp, struct igb_adapter, + ptp_caps); + unsigned long flags; + + spin_lock_irqsave(&igb->tmreg_lock, flags); + + igb_ptp_write_i210(igb, ts); + + spin_unlock_irqrestore(&igb->tmreg_lock, flags); + + return 0; +} + +static void igb_pin_direction(int pin, int input, u32 *ctrl, u32 *ctrl_ext) +{ + u32 *ptr = pin < 2 ? ctrl : ctrl_ext; + static const u32 mask[IGB_N_SDP] = { + E1000_CTRL_SDP0_DIR, + E1000_CTRL_SDP1_DIR, + E1000_CTRL_EXT_SDP2_DIR, + E1000_CTRL_EXT_SDP3_DIR, + }; + + if (input) + *ptr &= ~mask[pin]; + else + *ptr |= mask[pin]; +} + +static void igb_pin_extts(struct igb_adapter *igb, int chan, int pin) +{ + static const u32 aux0_sel_sdp[IGB_N_SDP] = { + AUX0_SEL_SDP0, AUX0_SEL_SDP1, AUX0_SEL_SDP2, AUX0_SEL_SDP3, + }; + static const u32 aux1_sel_sdp[IGB_N_SDP] = { + AUX1_SEL_SDP0, AUX1_SEL_SDP1, AUX1_SEL_SDP2, AUX1_SEL_SDP3, + }; + static const u32 ts_sdp_en[IGB_N_SDP] = { + TS_SDP0_EN, TS_SDP1_EN, TS_SDP2_EN, TS_SDP3_EN, + }; + struct e1000_hw *hw = &igb->hw; + u32 ctrl, ctrl_ext, tssdp = 0; + + ctrl = rd32(E1000_CTRL); + ctrl_ext = rd32(E1000_CTRL_EXT); + tssdp = rd32(E1000_TSSDP); + + igb_pin_direction(pin, 1, &ctrl, &ctrl_ext); + + /* Make sure this pin is not enabled as an output. */ + tssdp &= ~ts_sdp_en[pin]; + + if (chan == 1) { + tssdp &= ~AUX1_SEL_SDP3; + tssdp |= aux1_sel_sdp[pin] | AUX1_TS_SDP_EN; + } else { + tssdp &= ~AUX0_SEL_SDP3; + tssdp |= aux0_sel_sdp[pin] | AUX0_TS_SDP_EN; + } + + wr32(E1000_TSSDP, tssdp); + wr32(E1000_CTRL, ctrl); + wr32(E1000_CTRL_EXT, ctrl_ext); +} + +static void igb_pin_perout(struct igb_adapter *igb, int chan, int pin, int freq) +{ + static const u32 aux0_sel_sdp[IGB_N_SDP] = { + AUX0_SEL_SDP0, AUX0_SEL_SDP1, AUX0_SEL_SDP2, AUX0_SEL_SDP3, + }; + static const u32 aux1_sel_sdp[IGB_N_SDP] = { + AUX1_SEL_SDP0, AUX1_SEL_SDP1, AUX1_SEL_SDP2, AUX1_SEL_SDP3, + }; + static const u32 ts_sdp_en[IGB_N_SDP] = { + TS_SDP0_EN, TS_SDP1_EN, TS_SDP2_EN, TS_SDP3_EN, + }; + static const u32 ts_sdp_sel_tt0[IGB_N_SDP] = { + TS_SDP0_SEL_TT0, TS_SDP1_SEL_TT0, + TS_SDP2_SEL_TT0, TS_SDP3_SEL_TT0, + }; + static const u32 ts_sdp_sel_tt1[IGB_N_SDP] = { + TS_SDP0_SEL_TT1, TS_SDP1_SEL_TT1, + TS_SDP2_SEL_TT1, TS_SDP3_SEL_TT1, + }; + static const u32 ts_sdp_sel_fc0[IGB_N_SDP] = { + TS_SDP0_SEL_FC0, TS_SDP1_SEL_FC0, + TS_SDP2_SEL_FC0, TS_SDP3_SEL_FC0, + }; + static const u32 ts_sdp_sel_fc1[IGB_N_SDP] = { + TS_SDP0_SEL_FC1, TS_SDP1_SEL_FC1, + TS_SDP2_SEL_FC1, TS_SDP3_SEL_FC1, + }; + static const u32 ts_sdp_sel_clr[IGB_N_SDP] = { + TS_SDP0_SEL_FC1, TS_SDP1_SEL_FC1, + TS_SDP2_SEL_FC1, TS_SDP3_SEL_FC1, + }; + struct e1000_hw *hw = &igb->hw; + u32 ctrl, ctrl_ext, tssdp = 0; + + ctrl = rd32(E1000_CTRL); + ctrl_ext = rd32(E1000_CTRL_EXT); + tssdp = rd32(E1000_TSSDP); + + igb_pin_direction(pin, 0, &ctrl, &ctrl_ext); + + /* Make sure this pin is not enabled as an input. */ + if ((tssdp & AUX0_SEL_SDP3) == aux0_sel_sdp[pin]) + tssdp &= ~AUX0_TS_SDP_EN; + + if ((tssdp & AUX1_SEL_SDP3) == aux1_sel_sdp[pin]) + tssdp &= ~AUX1_TS_SDP_EN; + + tssdp &= ~ts_sdp_sel_clr[pin]; + if (freq) { + if (chan == 1) + tssdp |= ts_sdp_sel_fc1[pin]; + else + tssdp |= ts_sdp_sel_fc0[pin]; + } else { + if (chan == 1) + tssdp |= ts_sdp_sel_tt1[pin]; + else + tssdp |= ts_sdp_sel_tt0[pin]; + } + tssdp |= ts_sdp_en[pin]; + + wr32(E1000_TSSDP, tssdp); + wr32(E1000_CTRL, ctrl); + wr32(E1000_CTRL_EXT, ctrl_ext); +} + +static int igb_ptp_feature_enable_82580(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, int on) +{ + struct igb_adapter *igb = + container_of(ptp, struct igb_adapter, ptp_caps); + u32 tsauxc, tsim, tsauxc_mask, tsim_mask, trgttiml, trgttimh, systiml, + systimh, level_mask, level, rem; + struct e1000_hw *hw = &igb->hw; + struct timespec64 ts, start; + unsigned long flags; + u64 systim, now; + int pin = -1; + s64 ns; + + switch (rq->type) { + case PTP_CLK_REQ_EXTTS: + /* Reject requests with unsupported flags */ + if (rq->extts.flags & ~(PTP_ENABLE_FEATURE | + PTP_RISING_EDGE | + PTP_FALLING_EDGE | + PTP_STRICT_FLAGS)) + return -EOPNOTSUPP; + + if (on) { + pin = ptp_find_pin(igb->ptp_clock, PTP_PF_EXTTS, + rq->extts.index); + if (pin < 0) + return -EBUSY; + } + if (rq->extts.index == 1) { + tsauxc_mask = TSAUXC_EN_TS1; + tsim_mask = TSINTR_AUTT1; + } else { + tsauxc_mask = TSAUXC_EN_TS0; + tsim_mask = TSINTR_AUTT0; + } + spin_lock_irqsave(&igb->tmreg_lock, flags); + tsauxc = rd32(E1000_TSAUXC); + tsim = rd32(E1000_TSIM); + if (on) { + igb_pin_extts(igb, rq->extts.index, pin); + tsauxc |= tsauxc_mask; + tsim |= tsim_mask; + } else { + tsauxc &= ~tsauxc_mask; + tsim &= ~tsim_mask; + } + wr32(E1000_TSAUXC, tsauxc); + wr32(E1000_TSIM, tsim); + spin_unlock_irqrestore(&igb->tmreg_lock, flags); + return 0; + + case PTP_CLK_REQ_PEROUT: + /* Reject requests with unsupported flags */ + if (rq->perout.flags) + return -EOPNOTSUPP; + + if (on) { + pin = ptp_find_pin(igb->ptp_clock, PTP_PF_PEROUT, + rq->perout.index); + if (pin < 0) + return -EBUSY; + } + ts.tv_sec = rq->perout.period.sec; + ts.tv_nsec = rq->perout.period.nsec; + ns = timespec64_to_ns(&ts); + ns = ns >> 1; + if (on && ns < 8LL) + return -EINVAL; + ts = ns_to_timespec64(ns); + if (rq->perout.index == 1) { + tsauxc_mask = TSAUXC_EN_TT1; + tsim_mask = TSINTR_TT1; + trgttiml = E1000_TRGTTIML1; + trgttimh = E1000_TRGTTIMH1; + } else { + tsauxc_mask = TSAUXC_EN_TT0; + tsim_mask = TSINTR_TT0; + trgttiml = E1000_TRGTTIML0; + trgttimh = E1000_TRGTTIMH0; + } + spin_lock_irqsave(&igb->tmreg_lock, flags); + tsauxc = rd32(E1000_TSAUXC); + tsim = rd32(E1000_TSIM); + if (rq->perout.index == 1) { + tsauxc &= ~(TSAUXC_EN_TT1 | TSAUXC_EN_CLK1 | TSAUXC_ST1); + tsim &= ~TSINTR_TT1; + } else { + tsauxc &= ~(TSAUXC_EN_TT0 | TSAUXC_EN_CLK0 | TSAUXC_ST0); + tsim &= ~TSINTR_TT0; + } + if (on) { + int i = rq->perout.index; + + /* read systim registers in sequence */ + rd32(E1000_SYSTIMR); + systiml = rd32(E1000_SYSTIML); + systimh = rd32(E1000_SYSTIMH); + systim = (((u64)(systimh & 0xFF)) << 32) | ((u64)systiml); + now = timecounter_cyc2time(&igb->tc, systim); + + if (pin < 2) { + level_mask = (i == 1) ? 0x80000 : 0x40000; + level = (rd32(E1000_CTRL) & level_mask) ? 1 : 0; + } else { + level_mask = (i == 1) ? 0x80 : 0x40; + level = (rd32(E1000_CTRL_EXT) & level_mask) ? 1 : 0; + } + + div_u64_rem(now, ns, &rem); + systim = systim + (ns - rem); + + /* synchronize pin level with rising/falling edges */ + div_u64_rem(now, ns << 1, &rem); + if (rem < ns) { + /* first half of period */ + if (level == 0) { + /* output is already low, skip this period */ + systim += ns; + } + } else { + /* second half of period */ + if (level == 1) { + /* output is already high, skip this period */ + systim += ns; + } + } + + start = ns_to_timespec64(systim + (ns - rem)); + igb_pin_perout(igb, i, pin, 0); + igb->perout[i].start.tv_sec = start.tv_sec; + igb->perout[i].start.tv_nsec = start.tv_nsec; + igb->perout[i].period.tv_sec = ts.tv_sec; + igb->perout[i].period.tv_nsec = ts.tv_nsec; + + wr32(trgttiml, (u32)systim); + wr32(trgttimh, ((u32)(systim >> 32)) & 0xFF); + tsauxc |= tsauxc_mask; + tsim |= tsim_mask; + } + wr32(E1000_TSAUXC, tsauxc); + wr32(E1000_TSIM, tsim); + spin_unlock_irqrestore(&igb->tmreg_lock, flags); + return 0; + + case PTP_CLK_REQ_PPS: + return -EOPNOTSUPP; + } + + return -EOPNOTSUPP; +} + +static int igb_ptp_feature_enable_i210(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, int on) +{ + struct igb_adapter *igb = + container_of(ptp, struct igb_adapter, ptp_caps); + struct e1000_hw *hw = &igb->hw; + u32 tsauxc, tsim, tsauxc_mask, tsim_mask, trgttiml, trgttimh, freqout; + unsigned long flags; + struct timespec64 ts; + int use_freq = 0, pin = -1; + s64 ns; + + switch (rq->type) { + case PTP_CLK_REQ_EXTTS: + /* Reject requests with unsupported flags */ + if (rq->extts.flags & ~(PTP_ENABLE_FEATURE | + PTP_RISING_EDGE | + PTP_FALLING_EDGE | + PTP_STRICT_FLAGS)) + return -EOPNOTSUPP; + + /* Reject requests failing to enable both edges. */ + if ((rq->extts.flags & PTP_STRICT_FLAGS) && + (rq->extts.flags & PTP_ENABLE_FEATURE) && + (rq->extts.flags & PTP_EXTTS_EDGES) != PTP_EXTTS_EDGES) + return -EOPNOTSUPP; + + if (on) { + pin = ptp_find_pin(igb->ptp_clock, PTP_PF_EXTTS, + rq->extts.index); + if (pin < 0) + return -EBUSY; + } + if (rq->extts.index == 1) { + tsauxc_mask = TSAUXC_EN_TS1; + tsim_mask = TSINTR_AUTT1; + } else { + tsauxc_mask = TSAUXC_EN_TS0; + tsim_mask = TSINTR_AUTT0; + } + spin_lock_irqsave(&igb->tmreg_lock, flags); + tsauxc = rd32(E1000_TSAUXC); + tsim = rd32(E1000_TSIM); + if (on) { + igb_pin_extts(igb, rq->extts.index, pin); + tsauxc |= tsauxc_mask; + tsim |= tsim_mask; + } else { + tsauxc &= ~tsauxc_mask; + tsim &= ~tsim_mask; + } + wr32(E1000_TSAUXC, tsauxc); + wr32(E1000_TSIM, tsim); + spin_unlock_irqrestore(&igb->tmreg_lock, flags); + return 0; + + case PTP_CLK_REQ_PEROUT: + /* Reject requests with unsupported flags */ + if (rq->perout.flags) + return -EOPNOTSUPP; + + if (on) { + pin = ptp_find_pin(igb->ptp_clock, PTP_PF_PEROUT, + rq->perout.index); + if (pin < 0) + return -EBUSY; + } + ts.tv_sec = rq->perout.period.sec; + ts.tv_nsec = rq->perout.period.nsec; + ns = timespec64_to_ns(&ts); + ns = ns >> 1; + if (on && ((ns <= 70000000LL) || (ns == 125000000LL) || + (ns == 250000000LL) || (ns == 500000000LL))) { + if (ns < 8LL) + return -EINVAL; + use_freq = 1; + } + ts = ns_to_timespec64(ns); + if (rq->perout.index == 1) { + if (use_freq) { + tsauxc_mask = TSAUXC_EN_CLK1 | TSAUXC_ST1; + tsim_mask = 0; + } else { + tsauxc_mask = TSAUXC_EN_TT1; + tsim_mask = TSINTR_TT1; + } + trgttiml = E1000_TRGTTIML1; + trgttimh = E1000_TRGTTIMH1; + freqout = E1000_FREQOUT1; + } else { + if (use_freq) { + tsauxc_mask = TSAUXC_EN_CLK0 | TSAUXC_ST0; + tsim_mask = 0; + } else { + tsauxc_mask = TSAUXC_EN_TT0; + tsim_mask = TSINTR_TT0; + } + trgttiml = E1000_TRGTTIML0; + trgttimh = E1000_TRGTTIMH0; + freqout = E1000_FREQOUT0; + } + spin_lock_irqsave(&igb->tmreg_lock, flags); + tsauxc = rd32(E1000_TSAUXC); + tsim = rd32(E1000_TSIM); + if (rq->perout.index == 1) { + tsauxc &= ~(TSAUXC_EN_TT1 | TSAUXC_EN_CLK1 | TSAUXC_ST1); + tsim &= ~TSINTR_TT1; + } else { + tsauxc &= ~(TSAUXC_EN_TT0 | TSAUXC_EN_CLK0 | TSAUXC_ST0); + tsim &= ~TSINTR_TT0; + } + if (on) { + int i = rq->perout.index; + igb_pin_perout(igb, i, pin, use_freq); + igb->perout[i].start.tv_sec = rq->perout.start.sec; + igb->perout[i].start.tv_nsec = rq->perout.start.nsec; + igb->perout[i].period.tv_sec = ts.tv_sec; + igb->perout[i].period.tv_nsec = ts.tv_nsec; + wr32(trgttimh, rq->perout.start.sec); + wr32(trgttiml, rq->perout.start.nsec); + if (use_freq) + wr32(freqout, ns); + tsauxc |= tsauxc_mask; + tsim |= tsim_mask; + } + wr32(E1000_TSAUXC, tsauxc); + wr32(E1000_TSIM, tsim); + spin_unlock_irqrestore(&igb->tmreg_lock, flags); + return 0; + + case PTP_CLK_REQ_PPS: + spin_lock_irqsave(&igb->tmreg_lock, flags); + tsim = rd32(E1000_TSIM); + if (on) + tsim |= TSINTR_SYS_WRAP; + else + tsim &= ~TSINTR_SYS_WRAP; + igb->pps_sys_wrap_on = !!on; + wr32(E1000_TSIM, tsim); + spin_unlock_irqrestore(&igb->tmreg_lock, flags); + return 0; + } + + return -EOPNOTSUPP; +} + +static int igb_ptp_feature_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, int on) +{ + return -EOPNOTSUPP; +} + +static int igb_ptp_verify_pin(struct ptp_clock_info *ptp, unsigned int pin, + enum ptp_pin_function func, unsigned int chan) +{ + switch (func) { + case PTP_PF_NONE: + case PTP_PF_EXTTS: + case PTP_PF_PEROUT: + break; + case PTP_PF_PHYSYNC: + return -1; + } + return 0; +} + +/** + * igb_ptp_tx_work + * @work: pointer to work struct + * + * This work function polls the TSYNCTXCTL valid bit to determine when a + * timestamp has been taken for the current stored skb. + **/ +static void igb_ptp_tx_work(struct work_struct *work) +{ + struct igb_adapter *adapter = container_of(work, struct igb_adapter, + ptp_tx_work); + struct e1000_hw *hw = &adapter->hw; + u32 tsynctxctl; + + if (!adapter->ptp_tx_skb) + return; + + if (time_is_before_jiffies(adapter->ptp_tx_start + + IGB_PTP_TX_TIMEOUT)) { + dev_kfree_skb_any(adapter->ptp_tx_skb); + adapter->ptp_tx_skb = NULL; + clear_bit_unlock(__IGB_PTP_TX_IN_PROGRESS, &adapter->state); + adapter->tx_hwtstamp_timeouts++; + /* Clear the tx valid bit in TSYNCTXCTL register to enable + * interrupt + */ + rd32(E1000_TXSTMPH); + dev_warn(&adapter->pdev->dev, "clearing Tx timestamp hang\n"); + return; + } + + tsynctxctl = rd32(E1000_TSYNCTXCTL); + if (tsynctxctl & E1000_TSYNCTXCTL_VALID) + igb_ptp_tx_hwtstamp(adapter); + else + /* reschedule to check later */ + schedule_work(&adapter->ptp_tx_work); +} + +static void igb_ptp_overflow_check(struct work_struct *work) +{ + struct igb_adapter *igb = + container_of(work, struct igb_adapter, ptp_overflow_work.work); + struct timespec64 ts; + u64 ns; + + /* Update the timecounter */ + ns = timecounter_read(&igb->tc); + + ts = ns_to_timespec64(ns); + pr_debug("igb overflow check at %lld.%09lu\n", + (long long) ts.tv_sec, ts.tv_nsec); + + schedule_delayed_work(&igb->ptp_overflow_work, + IGB_SYSTIM_OVERFLOW_PERIOD); +} + +/** + * igb_ptp_rx_hang - detect error case when Rx timestamp registers latched + * @adapter: private network adapter structure + * + * This watchdog task is scheduled to detect error case where hardware has + * dropped an Rx packet that was timestamped when the ring is full. The + * particular error is rare but leaves the device in a state unable to timestamp + * any future packets. + **/ +void igb_ptp_rx_hang(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 tsyncrxctl = rd32(E1000_TSYNCRXCTL); + unsigned long rx_event; + + /* Other hardware uses per-packet timestamps */ + if (hw->mac.type != e1000_82576) + return; + + /* If we don't have a valid timestamp in the registers, just update the + * timeout counter and exit + */ + if (!(tsyncrxctl & E1000_TSYNCRXCTL_VALID)) { + adapter->last_rx_ptp_check = jiffies; + return; + } + + /* Determine the most recent watchdog or rx_timestamp event */ + rx_event = adapter->last_rx_ptp_check; + if (time_after(adapter->last_rx_timestamp, rx_event)) + rx_event = adapter->last_rx_timestamp; + + /* Only need to read the high RXSTMP register to clear the lock */ + if (time_is_before_jiffies(rx_event + 5 * HZ)) { + rd32(E1000_RXSTMPH); + adapter->last_rx_ptp_check = jiffies; + adapter->rx_hwtstamp_cleared++; + dev_warn(&adapter->pdev->dev, "clearing Rx timestamp hang\n"); + } +} + +/** + * igb_ptp_tx_hang - detect error case where Tx timestamp never finishes + * @adapter: private network adapter structure + */ +void igb_ptp_tx_hang(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + bool timeout = time_is_before_jiffies(adapter->ptp_tx_start + + IGB_PTP_TX_TIMEOUT); + + if (!adapter->ptp_tx_skb) + return; + + if (!test_bit(__IGB_PTP_TX_IN_PROGRESS, &adapter->state)) + return; + + /* If we haven't received a timestamp within the timeout, it is + * reasonable to assume that it will never occur, so we can unlock the + * timestamp bit when this occurs. + */ + if (timeout) { + cancel_work_sync(&adapter->ptp_tx_work); + dev_kfree_skb_any(adapter->ptp_tx_skb); + adapter->ptp_tx_skb = NULL; + clear_bit_unlock(__IGB_PTP_TX_IN_PROGRESS, &adapter->state); + adapter->tx_hwtstamp_timeouts++; + /* Clear the tx valid bit in TSYNCTXCTL register to enable + * interrupt + */ + rd32(E1000_TXSTMPH); + dev_warn(&adapter->pdev->dev, "clearing Tx timestamp hang\n"); + } +} + +/** + * igb_ptp_tx_hwtstamp - utility function which checks for TX time stamp + * @adapter: Board private structure. + * + * If we were asked to do hardware stamping and such a time stamp is + * available, then it must have been for this skb here because we only + * allow only one such packet into the queue. + **/ +static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter) +{ + struct sk_buff *skb = adapter->ptp_tx_skb; + struct e1000_hw *hw = &adapter->hw; + struct skb_shared_hwtstamps shhwtstamps; + u64 regval; + int adjust = 0; + + regval = rd32(E1000_TXSTMPL); + regval |= (u64)rd32(E1000_TXSTMPH) << 32; + + igb_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval); + /* adjust timestamp for the TX latency based on link speed */ + if (adapter->hw.mac.type == e1000_i210) { + switch (adapter->link_speed) { + case SPEED_10: + adjust = IGB_I210_TX_LATENCY_10; + break; + case SPEED_100: + adjust = IGB_I210_TX_LATENCY_100; + break; + case SPEED_1000: + adjust = IGB_I210_TX_LATENCY_1000; + break; + } + } + + shhwtstamps.hwtstamp = + ktime_add_ns(shhwtstamps.hwtstamp, adjust); + + /* Clear the lock early before calling skb_tstamp_tx so that + * applications are not woken up before the lock bit is clear. We use + * a copy of the skb pointer to ensure other threads can't change it + * while we're notifying the stack. + */ + adapter->ptp_tx_skb = NULL; + clear_bit_unlock(__IGB_PTP_TX_IN_PROGRESS, &adapter->state); + + /* Notify the stack and free the skb after we've unlocked */ + skb_tstamp_tx(skb, &shhwtstamps); + dev_kfree_skb_any(skb); +} + +/** + * igb_ptp_rx_pktstamp - retrieve Rx per packet timestamp + * @q_vector: Pointer to interrupt specific structure + * @va: Pointer to address containing Rx buffer + * @timestamp: Pointer where timestamp will be stored + * + * This function is meant to retrieve a timestamp from the first buffer of an + * incoming frame. The value is stored in little endian format starting on + * byte 8 + * + * Returns: The timestamp header length or 0 if not available + **/ +int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, + ktime_t *timestamp) +{ + struct igb_adapter *adapter = q_vector->adapter; + struct skb_shared_hwtstamps ts; + __le64 *regval = (__le64 *)va; + int adjust = 0; + + if (!(adapter->ptp_flags & IGB_PTP_ENABLED)) + return 0; + + /* The timestamp is recorded in little endian format. + * DWORD: 0 1 2 3 + * Field: Reserved Reserved SYSTIML SYSTIMH + */ + + /* check reserved dwords are zero, be/le doesn't matter for zero */ + if (regval[0]) + return 0; + + igb_ptp_systim_to_hwtstamp(adapter, &ts, le64_to_cpu(regval[1])); + + /* adjust timestamp for the RX latency based on link speed */ + if (adapter->hw.mac.type == e1000_i210) { + switch (adapter->link_speed) { + case SPEED_10: + adjust = IGB_I210_RX_LATENCY_10; + break; + case SPEED_100: + adjust = IGB_I210_RX_LATENCY_100; + break; + case SPEED_1000: + adjust = IGB_I210_RX_LATENCY_1000; + break; + } + } + + *timestamp = ktime_sub_ns(ts.hwtstamp, adjust); + + return IGB_TS_HDR_LEN; +} + +/** + * igb_ptp_rx_rgtstamp - retrieve Rx timestamp stored in register + * @q_vector: Pointer to interrupt specific structure + * @skb: Buffer containing timestamp and packet + * + * This function is meant to retrieve a timestamp from the internal registers + * of the adapter and store it in the skb. + **/ +void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb) +{ + struct igb_adapter *adapter = q_vector->adapter; + struct e1000_hw *hw = &adapter->hw; + int adjust = 0; + u64 regval; + + if (!(adapter->ptp_flags & IGB_PTP_ENABLED)) + return; + + /* If this bit is set, then the RX registers contain the time stamp. No + * other packet will be time stamped until we read these registers, so + * read the registers to make them available again. Because only one + * packet can be time stamped at a time, we know that the register + * values must belong to this one here and therefore we don't need to + * compare any of the additional attributes stored for it. + * + * If nothing went wrong, then it should have a shared tx_flags that we + * can turn into a skb_shared_hwtstamps. + */ + if (!(rd32(E1000_TSYNCRXCTL) & E1000_TSYNCRXCTL_VALID)) + return; + + regval = rd32(E1000_RXSTMPL); + regval |= (u64)rd32(E1000_RXSTMPH) << 32; + + igb_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), regval); + + /* adjust timestamp for the RX latency based on link speed */ + if (adapter->hw.mac.type == e1000_i210) { + switch (adapter->link_speed) { + case SPEED_10: + adjust = IGB_I210_RX_LATENCY_10; + break; + case SPEED_100: + adjust = IGB_I210_RX_LATENCY_100; + break; + case SPEED_1000: + adjust = IGB_I210_RX_LATENCY_1000; + break; + } + } + skb_hwtstamps(skb)->hwtstamp = + ktime_sub_ns(skb_hwtstamps(skb)->hwtstamp, adjust); + + /* Update the last_rx_timestamp timer in order to enable watchdog check + * for error case of latched timestamp on a dropped packet. + */ + adapter->last_rx_timestamp = jiffies; +} + +/** + * igb_ptp_get_ts_config - get hardware time stamping config + * @netdev: netdev struct + * @ifr: interface struct + * + * Get the hwtstamp_config settings to return to the user. Rather than attempt + * to deconstruct the settings from the registers, just return a shadow copy + * of the last known settings. + **/ +int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct hwtstamp_config *config = &adapter->tstamp_config; + + return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ? + -EFAULT : 0; +} + +/** + * igb_ptp_set_timestamp_mode - setup hardware for timestamping + * @adapter: networking device structure + * @config: hwtstamp configuration + * + * Outgoing time stamping can be enabled and disabled. Play nice and + * disable it when requested, although it shouldn't case any overhead + * when no packet needs it. At most one packet in the queue may be + * marked for time stamping, otherwise it would be impossible to tell + * for sure to which packet the hardware time stamp belongs. + * + * Incoming time stamping has to be configured via the hardware + * filters. Not all combinations are supported, in particular event + * type has to be specified. Matching the kind of event packet is + * not supported, with the exception of "all V2 events regardless of + * level 2 or 4". + */ +static int igb_ptp_set_timestamp_mode(struct igb_adapter *adapter, + struct hwtstamp_config *config) +{ + struct e1000_hw *hw = &adapter->hw; + u32 tsync_tx_ctl = E1000_TSYNCTXCTL_ENABLED; + u32 tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED; + u32 tsync_rx_cfg = 0; + bool is_l4 = false; + bool is_l2 = false; + u32 regval; + + switch (config->tx_type) { + case HWTSTAMP_TX_OFF: + tsync_tx_ctl = 0; + break; + case HWTSTAMP_TX_ON: + break; + default: + return -ERANGE; + } + + switch (config->rx_filter) { + case HWTSTAMP_FILTER_NONE: + tsync_rx_ctl = 0; + break; + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L4_V1; + tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V1_SYNC_MESSAGE; + is_l4 = true; + break; + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L4_V1; + tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V1_DELAY_REQ_MESSAGE; + is_l4 = true; + break; + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_EVENT_V2; + config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + is_l2 = true; + is_l4 = true; + break; + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_NTP_ALL: + case HWTSTAMP_FILTER_ALL: + /* 82576 cannot timestamp all packets, which it needs to do to + * support both V1 Sync and Delay_Req messages + */ + if (hw->mac.type != e1000_82576) { + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_ALL; + config->rx_filter = HWTSTAMP_FILTER_ALL; + break; + } + fallthrough; + default: + config->rx_filter = HWTSTAMP_FILTER_NONE; + return -ERANGE; + } + + if (hw->mac.type == e1000_82575) { + if (tsync_rx_ctl | tsync_tx_ctl) + return -EINVAL; + return 0; + } + + /* Per-packet timestamping only works if all packets are + * timestamped, so enable timestamping in all packets as + * long as one Rx filter was configured. + */ + if ((hw->mac.type >= e1000_82580) && tsync_rx_ctl) { + tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED; + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_ALL; + config->rx_filter = HWTSTAMP_FILTER_ALL; + is_l2 = true; + is_l4 = true; + + if ((hw->mac.type == e1000_i210) || + (hw->mac.type == e1000_i211)) { + regval = rd32(E1000_RXPBS); + regval |= E1000_RXPBS_CFG_TS_EN; + wr32(E1000_RXPBS, regval); + } + } + + /* enable/disable TX */ + regval = rd32(E1000_TSYNCTXCTL); + regval &= ~E1000_TSYNCTXCTL_ENABLED; + regval |= tsync_tx_ctl; + wr32(E1000_TSYNCTXCTL, regval); + + /* enable/disable RX */ + regval = rd32(E1000_TSYNCRXCTL); + regval &= ~(E1000_TSYNCRXCTL_ENABLED | E1000_TSYNCRXCTL_TYPE_MASK); + regval |= tsync_rx_ctl; + wr32(E1000_TSYNCRXCTL, regval); + + /* define which PTP packets are time stamped */ + wr32(E1000_TSYNCRXCFG, tsync_rx_cfg); + + /* define ethertype filter for timestamped packets */ + if (is_l2) + wr32(E1000_ETQF(IGB_ETQF_FILTER_1588), + (E1000_ETQF_FILTER_ENABLE | /* enable filter */ + E1000_ETQF_1588 | /* enable timestamping */ + ETH_P_1588)); /* 1588 eth protocol type */ + else + wr32(E1000_ETQF(IGB_ETQF_FILTER_1588), 0); + + /* L4 Queue Filter[3]: filter by destination port and protocol */ + if (is_l4) { + u32 ftqf = (IPPROTO_UDP /* UDP */ + | E1000_FTQF_VF_BP /* VF not compared */ + | E1000_FTQF_1588_TIME_STAMP /* Enable Timestamping */ + | E1000_FTQF_MASK); /* mask all inputs */ + ftqf &= ~E1000_FTQF_MASK_PROTO_BP; /* enable protocol check */ + + wr32(E1000_IMIR(3), (__force unsigned int)htons(PTP_EV_PORT)); + wr32(E1000_IMIREXT(3), + (E1000_IMIREXT_SIZE_BP | E1000_IMIREXT_CTRL_BP)); + if (hw->mac.type == e1000_82576) { + /* enable source port check */ + wr32(E1000_SPQF(3), (__force unsigned int)htons(PTP_EV_PORT)); + ftqf &= ~E1000_FTQF_MASK_SOURCE_PORT_BP; + } + wr32(E1000_FTQF(3), ftqf); + } else { + wr32(E1000_FTQF(3), E1000_FTQF_MASK); + } + wrfl(); + + /* clear TX/RX time stamp registers, just to be sure */ + regval = rd32(E1000_TXSTMPL); + regval = rd32(E1000_TXSTMPH); + regval = rd32(E1000_RXSTMPL); + regval = rd32(E1000_RXSTMPH); + + return 0; +} + +/** + * igb_ptp_set_ts_config - set hardware time stamping config + * @netdev: netdev struct + * @ifr: interface struct + * + **/ +int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct hwtstamp_config config; + int err; + + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) + return -EFAULT; + + err = igb_ptp_set_timestamp_mode(adapter, &config); + if (err) + return err; + + /* save these settings for future reference */ + memcpy(&adapter->tstamp_config, &config, + sizeof(adapter->tstamp_config)); + + return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? + -EFAULT : 0; +} + +/** + * igb_ptp_init - Initialize PTP functionality + * @adapter: Board private structure + * + * This function is called at device probe to initialize the PTP + * functionality. + */ +void igb_ptp_init(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; + + switch (hw->mac.type) { + case e1000_82576: + snprintf(adapter->ptp_caps.name, 16, "%pm", netdev->dev_addr); + adapter->ptp_caps.owner = THIS_MODULE; + adapter->ptp_caps.max_adj = 999999881; + adapter->ptp_caps.n_ext_ts = 0; + adapter->ptp_caps.pps = 0; + adapter->ptp_caps.adjfine = igb_ptp_adjfine_82576; + adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576; + adapter->ptp_caps.gettimex64 = igb_ptp_gettimex_82576; + adapter->ptp_caps.settime64 = igb_ptp_settime_82576; + adapter->ptp_caps.enable = igb_ptp_feature_enable; + adapter->cc.read = igb_ptp_read_82576; + adapter->cc.mask = CYCLECOUNTER_MASK(64); + adapter->cc.mult = 1; + adapter->cc.shift = IGB_82576_TSYNC_SHIFT; + adapter->ptp_flags |= IGB_PTP_OVERFLOW_CHECK; + break; + case e1000_82580: + case e1000_i354: + case e1000_i350: + igb_ptp_sdp_init(adapter); + snprintf(adapter->ptp_caps.name, 16, "%pm", netdev->dev_addr); + adapter->ptp_caps.owner = THIS_MODULE; + adapter->ptp_caps.max_adj = 62499999; + adapter->ptp_caps.n_ext_ts = IGB_N_EXTTS; + adapter->ptp_caps.n_per_out = IGB_N_PEROUT; + adapter->ptp_caps.n_pins = IGB_N_SDP; + adapter->ptp_caps.pps = 0; + adapter->ptp_caps.pin_config = adapter->sdp_config; + adapter->ptp_caps.adjfine = igb_ptp_adjfine_82580; + adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576; + adapter->ptp_caps.gettimex64 = igb_ptp_gettimex_82580; + adapter->ptp_caps.settime64 = igb_ptp_settime_82576; + adapter->ptp_caps.enable = igb_ptp_feature_enable_82580; + adapter->ptp_caps.verify = igb_ptp_verify_pin; + adapter->cc.read = igb_ptp_read_82580; + adapter->cc.mask = CYCLECOUNTER_MASK(IGB_NBITS_82580); + adapter->cc.mult = 1; + adapter->cc.shift = 0; + adapter->ptp_flags |= IGB_PTP_OVERFLOW_CHECK; + break; + case e1000_i210: + case e1000_i211: + igb_ptp_sdp_init(adapter); + snprintf(adapter->ptp_caps.name, 16, "%pm", netdev->dev_addr); + adapter->ptp_caps.owner = THIS_MODULE; + adapter->ptp_caps.max_adj = 62499999; + adapter->ptp_caps.n_ext_ts = IGB_N_EXTTS; + adapter->ptp_caps.n_per_out = IGB_N_PEROUT; + adapter->ptp_caps.n_pins = IGB_N_SDP; + adapter->ptp_caps.pps = 1; + adapter->ptp_caps.pin_config = adapter->sdp_config; + adapter->ptp_caps.adjfine = igb_ptp_adjfine_82580; + adapter->ptp_caps.adjtime = igb_ptp_adjtime_i210; + adapter->ptp_caps.gettimex64 = igb_ptp_gettimex_i210; + adapter->ptp_caps.settime64 = igb_ptp_settime_i210; + adapter->ptp_caps.enable = igb_ptp_feature_enable_i210; + adapter->ptp_caps.verify = igb_ptp_verify_pin; + break; + default: + adapter->ptp_clock = NULL; + return; + } + + adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps, + &adapter->pdev->dev); + if (IS_ERR(adapter->ptp_clock)) { + adapter->ptp_clock = NULL; + dev_err(&adapter->pdev->dev, "ptp_clock_register failed\n"); + } else if (adapter->ptp_clock) { + dev_info(&adapter->pdev->dev, "added PHC on %s\n", + adapter->netdev->name); + adapter->ptp_flags |= IGB_PTP_ENABLED; + + spin_lock_init(&adapter->tmreg_lock); + INIT_WORK(&adapter->ptp_tx_work, igb_ptp_tx_work); + + if (adapter->ptp_flags & IGB_PTP_OVERFLOW_CHECK) + INIT_DELAYED_WORK(&adapter->ptp_overflow_work, + igb_ptp_overflow_check); + + adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; + adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF; + + igb_ptp_reset(adapter); + } +} + +/** + * igb_ptp_sdp_init - utility function which inits the SDP config structs + * @adapter: Board private structure. + **/ +void igb_ptp_sdp_init(struct igb_adapter *adapter) +{ + int i; + + for (i = 0; i < IGB_N_SDP; i++) { + struct ptp_pin_desc *ppd = &adapter->sdp_config[i]; + + snprintf(ppd->name, sizeof(ppd->name), "SDP%d", i); + ppd->index = i; + ppd->func = PTP_PF_NONE; + } +} + +/** + * igb_ptp_suspend - Disable PTP work items and prepare for suspend + * @adapter: Board private structure + * + * This function stops the overflow check work and PTP Tx timestamp work, and + * will prepare the device for OS suspend. + */ +void igb_ptp_suspend(struct igb_adapter *adapter) +{ + if (!(adapter->ptp_flags & IGB_PTP_ENABLED)) + return; + + if (adapter->ptp_flags & IGB_PTP_OVERFLOW_CHECK) + cancel_delayed_work_sync(&adapter->ptp_overflow_work); + + cancel_work_sync(&adapter->ptp_tx_work); + if (adapter->ptp_tx_skb) { + dev_kfree_skb_any(adapter->ptp_tx_skb); + adapter->ptp_tx_skb = NULL; + clear_bit_unlock(__IGB_PTP_TX_IN_PROGRESS, &adapter->state); + } +} + +/** + * igb_ptp_stop - Disable PTP device and stop the overflow check. + * @adapter: Board private structure. + * + * This function stops the PTP support and cancels the delayed work. + **/ +void igb_ptp_stop(struct igb_adapter *adapter) +{ + igb_ptp_suspend(adapter); + + if (adapter->ptp_clock) { + ptp_clock_unregister(adapter->ptp_clock); + dev_info(&adapter->pdev->dev, "removed PHC on %s\n", + adapter->netdev->name); + adapter->ptp_flags &= ~IGB_PTP_ENABLED; + } +} + +/** + * igb_ptp_reset - Re-enable the adapter for PTP following a reset. + * @adapter: Board private structure. + * + * This function handles the reset work required to re-enable the PTP device. + **/ +void igb_ptp_reset(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + unsigned long flags; + + /* reset the tstamp_config */ + igb_ptp_set_timestamp_mode(adapter, &adapter->tstamp_config); + + spin_lock_irqsave(&adapter->tmreg_lock, flags); + + switch (adapter->hw.mac.type) { + case e1000_82576: + /* Dial the nominal frequency. */ + wr32(E1000_TIMINCA, INCPERIOD_82576 | INCVALUE_82576); + break; + case e1000_82580: + case e1000_i354: + case e1000_i350: + case e1000_i210: + case e1000_i211: + wr32(E1000_TSAUXC, 0x0); + wr32(E1000_TSSDP, 0x0); + wr32(E1000_TSIM, + TSYNC_INTERRUPTS | + (adapter->pps_sys_wrap_on ? TSINTR_SYS_WRAP : 0)); + wr32(E1000_IMS, E1000_IMS_TS); + break; + default: + /* No work to do. */ + goto out; + } + + /* Re-initialize the timer. */ + if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211)) { + struct timespec64 ts = ktime_to_timespec64(ktime_get_real()); + + igb_ptp_write_i210(adapter, &ts); + } else { + timecounter_init(&adapter->tc, &adapter->cc, + ktime_to_ns(ktime_get_real())); + } +out: + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + + wrfl(); + + if (adapter->ptp_flags & IGB_PTP_OVERFLOW_CHECK) + schedule_delayed_work(&adapter->ptp_overflow_work, + IGB_SYSTIM_OVERFLOW_PERIOD); +} |