diff options
Diffstat (limited to 'drivers/net/ethernet/intel/i40evf')
| -rw-r--r-- | drivers/net/ethernet/intel/i40evf/i40e_adminq.c | 5 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h | 87 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/i40evf/i40e_common.c | 125 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/i40evf/i40e_prototype.h | 15 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 826 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/i40evf/i40e_txrx.h | 80 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/i40evf/i40evf.h | 7 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c | 124 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/i40evf/i40evf_main.c | 121 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c | 6 |
10 files changed, 954 insertions, 442 deletions
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c index 3f65e39b3..44f7ed758 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c @@ -1,7 +1,7 @@ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2014 Intel Corporation. + * Copyright(c) 2013 - 2016 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -887,6 +887,9 @@ i40e_status i40evf_clean_arq_element(struct i40e_hw *hw, u16 flags; u16 ntu; + /* pre-clean the event info */ + memset(&e->desc, 0, sizeof(e->desc)); + /* take the lock before we start messing with the ring */ mutex_lock(&hw->aq.arq_mutex); diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h index f5b2b369d..aad8d6277 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h @@ -1,7 +1,7 @@ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2014 Intel Corporation. + * Copyright(c) 2013 - 2016 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -34,7 +34,7 @@ */ #define I40E_FW_API_VERSION_MAJOR 0x0001 -#define I40E_FW_API_VERSION_MINOR 0x0004 +#define I40E_FW_API_VERSION_MINOR 0x0005 struct i40e_aq_desc { __le16 flags; @@ -145,6 +145,9 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_remove_statistics = 0x0202, i40e_aqc_opc_set_port_parameters = 0x0203, i40e_aqc_opc_get_switch_resource_alloc = 0x0204, + i40e_aqc_opc_set_switch_config = 0x0205, + i40e_aqc_opc_rx_ctl_reg_read = 0x0206, + i40e_aqc_opc_rx_ctl_reg_write = 0x0207, i40e_aqc_opc_add_vsi = 0x0210, i40e_aqc_opc_update_vsi_parameters = 0x0211, @@ -220,6 +223,7 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_get_phy_wol_caps = 0x0621, i40e_aqc_opc_set_phy_debug = 0x0622, i40e_aqc_opc_upload_ext_phy_fm = 0x0625, + i40e_aqc_opc_run_phy_activity = 0x0626, /* NVM commands */ i40e_aqc_opc_nvm_read = 0x0701, @@ -228,6 +232,7 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_nvm_config_read = 0x0704, i40e_aqc_opc_nvm_config_write = 0x0705, i40e_aqc_opc_oem_post_update = 0x0720, + i40e_aqc_opc_thermal_sensor = 0x0721, /* virtualization commands */ i40e_aqc_opc_send_msg_to_pf = 0x0801, @@ -399,6 +404,7 @@ struct i40e_aqc_list_capabilities_element_resp { #define I40E_AQ_CAP_ID_OS2BMC_CAP 0x0004 #define I40E_AQ_CAP_ID_FUNCTIONS_VALID 0x0005 #define I40E_AQ_CAP_ID_ALTERNATE_RAM 0x0006 +#define I40E_AQ_CAP_ID_WOL_AND_PROXY 0x0008 #define I40E_AQ_CAP_ID_SRIOV 0x0012 #define I40E_AQ_CAP_ID_VF 0x0013 #define I40E_AQ_CAP_ID_VMDQ 0x0014 @@ -419,6 +425,7 @@ struct i40e_aqc_list_capabilities_element_resp { #define I40E_AQ_CAP_ID_LED 0x0061 #define I40E_AQ_CAP_ID_SDP 0x0062 #define I40E_AQ_CAP_ID_MDIO 0x0063 +#define I40E_AQ_CAP_ID_WSR_PROT 0x0064 #define I40E_AQ_CAP_ID_FLEX10 0x00F1 #define I40E_AQ_CAP_ID_CEM 0x00F2 @@ -677,6 +684,31 @@ struct i40e_aqc_switch_resource_alloc_element_resp { I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_resource_alloc_element_resp); +/* Set Switch Configuration (direct 0x0205) */ +struct i40e_aqc_set_switch_config { + __le16 flags; +#define I40E_AQ_SET_SWITCH_CFG_PROMISC 0x0001 +#define I40E_AQ_SET_SWITCH_CFG_L2_FILTER 0x0002 + __le16 valid_flags; + u8 reserved[12]; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_set_switch_config); + +/* Read Receive control registers (direct 0x0206) + * Write Receive control registers (direct 0x0207) + * used for accessing Rx control registers that can be + * slow and need special handling when under high Rx load + */ +struct i40e_aqc_rx_ctl_reg_read_write { + __le32 reserved1; + __le32 address; + __le32 reserved2; + __le32 value; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_rx_ctl_reg_read_write); + /* Add VSI (indirect 0x0210) * this indirect command uses struct i40e_aqc_vsi_properties_data * as the indirect buffer (128 bytes) @@ -903,7 +935,8 @@ struct i40e_aqc_add_veb { I40E_AQC_ADD_VEB_PORT_TYPE_SHIFT) #define I40E_AQC_ADD_VEB_PORT_TYPE_DEFAULT 0x2 #define I40E_AQC_ADD_VEB_PORT_TYPE_DATA 0x4 -#define I40E_AQC_ADD_VEB_ENABLE_L2_FILTER 0x8 +#define I40E_AQC_ADD_VEB_ENABLE_L2_FILTER 0x8 /* deprecated */ +#define I40E_AQC_ADD_VEB_ENABLE_DISABLE_STATS 0x10 u8 enable_tcs; u8 reserved[9]; }; @@ -970,6 +1003,7 @@ struct i40e_aqc_add_macvlan_element_data { #define I40E_AQC_MACVLAN_ADD_HASH_MATCH 0x0002 #define I40E_AQC_MACVLAN_ADD_IGNORE_VLAN 0x0004 #define I40E_AQC_MACVLAN_ADD_TO_QUEUE 0x0008 +#define I40E_AQC_MACVLAN_ADD_USE_SHARED_MAC 0x0010 __le16 queue_number; #define I40E_AQC_MACVLAN_CMD_QUEUE_SHIFT 0 #define I40E_AQC_MACVLAN_CMD_QUEUE_MASK (0x7FF << \ @@ -1066,6 +1100,7 @@ struct i40e_aqc_set_vsi_promiscuous_modes { #define I40E_AQC_SET_VSI_PROMISC_BROADCAST 0x04 #define I40E_AQC_SET_VSI_DEFAULT 0x08 #define I40E_AQC_SET_VSI_PROMISC_VLAN 0x10 +#define I40E_AQC_SET_VSI_PROMISC_TX 0x8000 __le16 seid; #define I40E_AQC_VSI_PROM_CMD_SEID_MASK 0x3FF __le16 vlan_tag; @@ -1254,10 +1289,16 @@ struct i40e_aqc_add_remove_cloud_filters_element_data { #define I40E_AQC_ADD_CLOUD_TNL_TYPE_SHIFT 9 #define I40E_AQC_ADD_CLOUD_TNL_TYPE_MASK 0x1E00 -#define I40E_AQC_ADD_CLOUD_TNL_TYPE_XVLAN 0 +#define I40E_AQC_ADD_CLOUD_TNL_TYPE_VXLAN 0 #define I40E_AQC_ADD_CLOUD_TNL_TYPE_NVGRE_OMAC 1 -#define I40E_AQC_ADD_CLOUD_TNL_TYPE_NGE 2 +#define I40E_AQC_ADD_CLOUD_TNL_TYPE_GENEVE 2 #define I40E_AQC_ADD_CLOUD_TNL_TYPE_IP 3 +#define I40E_AQC_ADD_CLOUD_TNL_TYPE_RESERVED 4 +#define I40E_AQC_ADD_CLOUD_TNL_TYPE_VXLAN_GPE 5 + +#define I40E_AQC_ADD_CLOUD_FLAGS_SHARED_OUTER_MAC 0x2000 +#define I40E_AQC_ADD_CLOUD_FLAGS_SHARED_INNER_MAC 0x4000 +#define I40E_AQC_ADD_CLOUD_FLAGS_SHARED_OUTER_IP 0x8000 __le32 tenant_id; u8 reserved[4]; @@ -1752,7 +1793,12 @@ struct i40e_aqc_get_link_status { u8 config; #define I40E_AQ_CONFIG_CRC_ENA 0x04 #define I40E_AQ_CONFIG_PACING_MASK 0x78 - u8 reserved[5]; + u8 external_power_ability; +#define I40E_AQ_LINK_POWER_CLASS_1 0x00 +#define I40E_AQ_LINK_POWER_CLASS_2 0x01 +#define I40E_AQ_LINK_POWER_CLASS_3 0x02 +#define I40E_AQ_LINK_POWER_CLASS_4 0x03 + u8 reserved[4]; }; I40E_CHECK_CMD_LENGTH(i40e_aqc_get_link_status); @@ -1820,6 +1866,18 @@ enum i40e_aq_phy_reg_type { I40E_AQC_PHY_REG_EXERNAL_MODULE = 0x3 }; +/* Run PHY Activity (0x0626) */ +struct i40e_aqc_run_phy_activity { + __le16 activity_id; + u8 flags; + u8 reserved1; + __le32 control; + __le32 data; + u8 reserved2[4]; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_run_phy_activity); + /* NVM Read command (indirect 0x0701) * NVM Erase commands (direct 0x0702) * NVM Update commands (indirect 0x0703) @@ -1909,6 +1967,22 @@ struct i40e_aqc_nvm_oem_post_update_buffer { I40E_CHECK_STRUCT_LEN(0x28, i40e_aqc_nvm_oem_post_update_buffer); +/* Thermal Sensor (indirect 0x0721) + * read or set thermal sensor configs and values + * takes a sensor and command specific data buffer, not detailed here + */ +struct i40e_aqc_thermal_sensor { + u8 sensor_action; +#define I40E_AQ_THERMAL_SENSOR_READ_CONFIG 0 +#define I40E_AQ_THERMAL_SENSOR_SET_CONFIG 1 +#define I40E_AQ_THERMAL_SENSOR_READ_TEMP 2 + u8 reserved[7]; + __le32 addr_high; + __le32 addr_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_thermal_sensor); + /* Send to PF command (indirect 0x0801) id is only used by PF * Send to VF command (indirect 0x0802) id is only used by PF * Send to Peer PF command (indirect 0x0803) @@ -2083,6 +2157,7 @@ struct i40e_aqc_add_udp_tunnel { #define I40E_AQC_TUNNEL_TYPE_VXLAN 0x00 #define I40E_AQC_TUNNEL_TYPE_NGE 0x01 #define I40E_AQC_TUNNEL_TYPE_TEREDO 0x10 +#define I40E_AQC_TUNNEL_TYPE_VXLAN_GPE 0x11 u8 reserved1[10]; }; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c index 938783e0b..771ac6ad8 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_common.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c @@ -904,6 +904,131 @@ struct i40e_rx_ptype_decoded i40evf_ptype_lookup[] = { }; /** + * i40evf_aq_rx_ctl_read_register - use FW to read from an Rx control register + * @hw: pointer to the hw struct + * @reg_addr: register address + * @reg_val: ptr to register value + * @cmd_details: pointer to command details structure or NULL + * + * Use the firmware to read the Rx control register, + * especially useful if the Rx unit is under heavy pressure + **/ +i40e_status i40evf_aq_rx_ctl_read_register(struct i40e_hw *hw, + u32 reg_addr, u32 *reg_val, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_rx_ctl_reg_read_write *cmd_resp = + (struct i40e_aqc_rx_ctl_reg_read_write *)&desc.params.raw; + i40e_status status; + + if (!reg_val) + return I40E_ERR_PARAM; + + i40evf_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_rx_ctl_reg_read); + + cmd_resp->address = cpu_to_le32(reg_addr); + + status = i40evf_asq_send_command(hw, &desc, NULL, 0, cmd_details); + + if (status == 0) + *reg_val = le32_to_cpu(cmd_resp->value); + + return status; +} + +/** + * i40evf_read_rx_ctl - read from an Rx control register + * @hw: pointer to the hw struct + * @reg_addr: register address + **/ +u32 i40evf_read_rx_ctl(struct i40e_hw *hw, u32 reg_addr) +{ + i40e_status status = 0; + bool use_register; + int retry = 5; + u32 val = 0; + + use_register = (hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver < 5); + if (!use_register) { +do_retry: + status = i40evf_aq_rx_ctl_read_register(hw, reg_addr, + &val, NULL); + if (hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN && retry) { + usleep_range(1000, 2000); + retry--; + goto do_retry; + } + } + + /* if the AQ access failed, try the old-fashioned way */ + if (status || use_register) + val = rd32(hw, reg_addr); + + return val; +} + +/** + * i40evf_aq_rx_ctl_write_register + * @hw: pointer to the hw struct + * @reg_addr: register address + * @reg_val: register value + * @cmd_details: pointer to command details structure or NULL + * + * Use the firmware to write to an Rx control register, + * especially useful if the Rx unit is under heavy pressure + **/ +i40e_status i40evf_aq_rx_ctl_write_register(struct i40e_hw *hw, + u32 reg_addr, u32 reg_val, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_rx_ctl_reg_read_write *cmd = + (struct i40e_aqc_rx_ctl_reg_read_write *)&desc.params.raw; + i40e_status status; + + i40evf_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_rx_ctl_reg_write); + + cmd->address = cpu_to_le32(reg_addr); + cmd->value = cpu_to_le32(reg_val); + + status = i40evf_asq_send_command(hw, &desc, NULL, 0, cmd_details); + + return status; +} + +/** + * i40evf_write_rx_ctl - write to an Rx control register + * @hw: pointer to the hw struct + * @reg_addr: register address + * @reg_val: register value + **/ +void i40evf_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val) +{ + i40e_status status = 0; + bool use_register; + int retry = 5; + + use_register = (hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver < 5); + if (!use_register) { +do_retry: + status = i40evf_aq_rx_ctl_write_register(hw, reg_addr, + reg_val, NULL); + if (hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN && retry) { + usleep_range(1000, 2000); + retry--; + goto do_retry; + } + } + + /* if the AQ access failed, try the old-fashioned way */ + if (status || use_register) + wr32(hw, reg_addr, reg_val); +} + +/** * i40e_aq_send_msg_to_pf * @hw: pointer to the hardware structure * @v_opcode: opcodes for VF-PF communication diff --git a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h index cbd9a1b07..d89d52109 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h @@ -103,4 +103,19 @@ i40e_status i40e_aq_add_rem_control_packet_filter(struct i40e_hw *hw, struct i40e_asq_cmd_details *cmd_details); void i40e_add_filter_to_drop_tx_flow_control_frames(struct i40e_hw *hw, u16 vsi_seid); +i40e_status i40evf_aq_rx_ctl_read_register(struct i40e_hw *hw, + u32 reg_addr, u32 *reg_val, + struct i40e_asq_cmd_details *cmd_details); +u32 i40evf_read_rx_ctl(struct i40e_hw *hw, u32 reg_addr); +i40e_status i40evf_aq_rx_ctl_write_register(struct i40e_hw *hw, + u32 reg_addr, u32 reg_val, + struct i40e_asq_cmd_details *cmd_details); +void i40evf_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val); +i40e_status i40e_read_phy_register(struct i40e_hw *hw, u8 page, + u16 reg, u8 phy_addr, u16 *value); +i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page, + u16 reg, u8 phy_addr, u16 value); +u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num); +i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw, + u32 time, u32 interval); #endif /* _I40E_PROTOTYPE_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 7a00657da..cea97daa8 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -1,7 +1,7 @@ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2014 Intel Corporation. + * Copyright(c) 2013 - 2016 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -129,15 +129,19 @@ void i40evf_free_tx_resources(struct i40e_ring *tx_ring) /** * i40evf_get_tx_pending - how many Tx descriptors not processed * @tx_ring: the ring of descriptors + * @in_sw: is tx_pending being checked in SW or HW * * Since there is no access to the ring head register * in XL710, we need to use our local copies **/ -u32 i40evf_get_tx_pending(struct i40e_ring *ring) +u32 i40evf_get_tx_pending(struct i40e_ring *ring, bool in_sw) { u32 head, tail; - head = i40e_get_head(ring); + if (!in_sw) + head = i40e_get_head(ring); + else + head = ring->next_to_clean; tail = readl(ring->tail); if (head != tail) @@ -252,6 +256,22 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget) tx_ring->q_vector->tx.total_bytes += total_bytes; tx_ring->q_vector->tx.total_packets += total_packets; + if (tx_ring->flags & I40E_TXR_FLAGS_WB_ON_ITR) { + unsigned int j = 0; + /* check to see if there are < 4 descriptors + * waiting to be written back, then kick the hardware to force + * them to be written back in case we stay in NAPI. + * In this mode on X722 we do not enable Interrupt. + */ + j = i40evf_get_tx_pending(tx_ring, false); + + if (budget && + ((j / (WB_STRIDE + 1)) == 0) && (j > 0) && + !test_bit(__I40E_DOWN, &tx_ring->vsi->state) && + (I40E_DESC_UNUSED(tx_ring) != tx_ring->count)) + tx_ring->arm_wb = true; + } + netdev_tx_completed_queue(netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index), total_packets, total_bytes); @@ -276,39 +296,49 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget) } /** - * i40evf_force_wb -Arm hardware to do a wb on noncache aligned descriptors + * i40evf_enable_wb_on_itr - Arm hardware to do a wb, interrupts are not enabled * @vsi: the VSI we care about - * @q_vector: the vector on which to force writeback + * @q_vector: the vector on which to enable writeback * **/ -static void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) +static void i40e_enable_wb_on_itr(struct i40e_vsi *vsi, + struct i40e_q_vector *q_vector) { u16 flags = q_vector->tx.ring[0].flags; + u32 val; - if (flags & I40E_TXR_FLAGS_WB_ON_ITR) { - u32 val; + if (!(flags & I40E_TXR_FLAGS_WB_ON_ITR)) + return; - if (q_vector->arm_wb_state) - return; + if (q_vector->arm_wb_state) + return; - val = I40E_VFINT_DYN_CTLN1_WB_ON_ITR_MASK; + val = I40E_VFINT_DYN_CTLN1_WB_ON_ITR_MASK | + I40E_VFINT_DYN_CTLN1_ITR_INDX_MASK; /* set noitr */ - wr32(&vsi->back->hw, - I40E_VFINT_DYN_CTLN1(q_vector->v_idx + - vsi->base_vector - 1), - val); - q_vector->arm_wb_state = true; - } else { - u32 val = I40E_VFINT_DYN_CTLN1_INTENA_MASK | - I40E_VFINT_DYN_CTLN1_ITR_INDX_MASK | /* set noitr */ - I40E_VFINT_DYN_CTLN1_SWINT_TRIG_MASK | - I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_MASK; - /* allow 00 to be written to the index */ - - wr32(&vsi->back->hw, - I40E_VFINT_DYN_CTLN1(q_vector->v_idx + - vsi->base_vector - 1), val); - } + wr32(&vsi->back->hw, + I40E_VFINT_DYN_CTLN1(q_vector->v_idx + + vsi->base_vector - 1), val); + q_vector->arm_wb_state = true; +} + +/** + * i40evf_force_wb - Issue SW Interrupt so HW does a wb + * @vsi: the VSI we care about + * @q_vector: the vector on which to force writeback + * + **/ +void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) +{ + u32 val = I40E_VFINT_DYN_CTLN1_INTENA_MASK | + I40E_VFINT_DYN_CTLN1_ITR_INDX_MASK | /* set noitr */ + I40E_VFINT_DYN_CTLN1_SWINT_TRIG_MASK | + I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_MASK + /* allow 00 to be written to the index */; + + wr32(&vsi->back->hw, + I40E_VFINT_DYN_CTLN1(q_vector->v_idx + vsi->base_vector - 1), + val); } /** @@ -506,7 +536,7 @@ void i40evf_clean_rx_ring(struct i40e_ring *rx_ring) if (rx_bi->page_dma) { dma_unmap_page(dev, rx_bi->page_dma, - PAGE_SIZE / 2, + PAGE_SIZE, DMA_FROM_DEVICE); rx_bi->page_dma = 0; } @@ -641,16 +671,19 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val) * i40evf_alloc_rx_buffers_ps - Replace used receive buffers; packet split * @rx_ring: ring to place buffers on * @cleaned_count: number of buffers to replace + * + * Returns true if any errors on allocation **/ -void i40evf_alloc_rx_buffers_ps(struct i40e_ring *rx_ring, u16 cleaned_count) +bool i40evf_alloc_rx_buffers_ps(struct i40e_ring *rx_ring, u16 cleaned_count) { u16 i = rx_ring->next_to_use; union i40e_rx_desc *rx_desc; struct i40e_rx_buffer *bi; + const int current_node = numa_node_id(); /* do nothing if no valid netdev defined */ if (!rx_ring->netdev || !cleaned_count) - return; + return false; while (cleaned_count--) { rx_desc = I40E_RX_DESC(rx_ring, i); @@ -658,56 +691,79 @@ void i40evf_alloc_rx_buffers_ps(struct i40e_ring *rx_ring, u16 cleaned_count) if (bi->skb) /* desc is in use */ goto no_buffers; + + /* If we've been moved to a different NUMA node, release the + * page so we can get a new one on the current node. + */ + if (bi->page && page_to_nid(bi->page) != current_node) { + dma_unmap_page(rx_ring->dev, + bi->page_dma, + PAGE_SIZE, + DMA_FROM_DEVICE); + __free_page(bi->page); + bi->page = NULL; + bi->page_dma = 0; + rx_ring->rx_stats.realloc_count++; + } else if (bi->page) { + rx_ring->rx_stats.page_reuse_count++; + } + if (!bi->page) { bi->page = alloc_page(GFP_ATOMIC); if (!bi->page) { rx_ring->rx_stats.alloc_page_failed++; goto no_buffers; } - } - - if (!bi->page_dma) { - /* use a half page if we're re-using */ - bi->page_offset ^= PAGE_SIZE / 2; bi->page_dma = dma_map_page(rx_ring->dev, bi->page, - bi->page_offset, - PAGE_SIZE / 2, + 0, + PAGE_SIZE, DMA_FROM_DEVICE); - if (dma_mapping_error(rx_ring->dev, - bi->page_dma)) { + if (dma_mapping_error(rx_ring->dev, bi->page_dma)) { rx_ring->rx_stats.alloc_page_failed++; + __free_page(bi->page); + bi->page = NULL; bi->page_dma = 0; + bi->page_offset = 0; goto no_buffers; } + bi->page_offset = 0; } - dma_sync_single_range_for_device(rx_ring->dev, - bi->dma, - 0, - rx_ring->rx_hdr_len, - 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->page_dma); + rx_desc->read.pkt_addr = + cpu_to_le64(bi->page_dma + bi->page_offset); rx_desc->read.hdr_addr = cpu_to_le64(bi->dma); i++; if (i == rx_ring->count) i = 0; } + if (rx_ring->next_to_use != i) + i40e_release_rx_desc(rx_ring, i); + + return false; + no_buffers: if (rx_ring->next_to_use != i) i40e_release_rx_desc(rx_ring, i); + + /* make sure to come back via polling to try again after + * allocation failure + */ + return true; } /** * i40evf_alloc_rx_buffers_1buf - Replace used receive buffers; single buffer * @rx_ring: ring to place buffers on * @cleaned_count: number of buffers to replace + * + * Returns true if any errors on allocation **/ -void i40evf_alloc_rx_buffers_1buf(struct i40e_ring *rx_ring, u16 cleaned_count) +bool i40evf_alloc_rx_buffers_1buf(struct i40e_ring *rx_ring, u16 cleaned_count) { u16 i = rx_ring->next_to_use; union i40e_rx_desc *rx_desc; @@ -716,7 +772,7 @@ void i40evf_alloc_rx_buffers_1buf(struct i40e_ring *rx_ring, u16 cleaned_count) /* do nothing if no valid netdev defined */ if (!rx_ring->netdev || !cleaned_count) - return; + return false; while (cleaned_count--) { rx_desc = I40E_RX_DESC(rx_ring, i); @@ -724,8 +780,10 @@ void i40evf_alloc_rx_buffers_1buf(struct i40e_ring *rx_ring, u16 cleaned_count) skb = bi->skb; if (!skb) { - skb = netdev_alloc_skb_ip_align(rx_ring->netdev, - rx_ring->rx_buf_len); + skb = __netdev_alloc_skb_ip_align(rx_ring->netdev, + rx_ring->rx_buf_len, + GFP_ATOMIC | + __GFP_NOWARN); if (!skb) { rx_ring->rx_stats.alloc_buff_failed++; goto no_buffers; @@ -743,6 +801,8 @@ void i40evf_alloc_rx_buffers_1buf(struct i40e_ring *rx_ring, u16 cleaned_count) if (dma_mapping_error(rx_ring->dev, bi->dma)) { rx_ring->rx_stats.alloc_buff_failed++; bi->dma = 0; + dev_kfree_skb(bi->skb); + bi->skb = NULL; goto no_buffers; } } @@ -754,9 +814,19 @@ void i40evf_alloc_rx_buffers_1buf(struct i40e_ring *rx_ring, u16 cleaned_count) i = 0; } + if (rx_ring->next_to_use != i) + i40e_release_rx_desc(rx_ring, i); + + return false; + no_buffers: if (rx_ring->next_to_use != i) i40e_release_rx_desc(rx_ring, i); + + /* make sure to come back via polling to try again after + * allocation failure + */ + return true; } /** @@ -791,16 +861,7 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, u16 rx_ptype) { struct i40e_rx_ptype_decoded decoded = decode_rx_desc_ptype(rx_ptype); - bool ipv4 = false, ipv6 = false; - bool ipv4_tunnel, ipv6_tunnel; - __wsum rx_udp_csum; - struct iphdr *iph; - __sum16 csum; - - ipv4_tunnel = (rx_ptype >= I40E_RX_PTYPE_GRENAT4_MAC_PAY3) && - (rx_ptype <= I40E_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4); - ipv6_tunnel = (rx_ptype >= I40E_RX_PTYPE_GRENAT6_MAC_PAY3) && - (rx_ptype <= I40E_RX_PTYPE_GRENAT6_MACVLAN_IPV6_ICMP_PAY4); + bool ipv4, ipv6, ipv4_tunnel, ipv6_tunnel; skb->ip_summed = CHECKSUM_NONE; @@ -816,12 +877,10 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, if (!(decoded.known && decoded.outer_ip)) return; - if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP && - decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV4) - ipv4 = true; - else if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP && - decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV6) - ipv6 = true; + ipv4 = (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP) && + (decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV4); + ipv6 = (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP) && + (decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV6); if (ipv4 && (rx_error & (BIT(I40E_RX_DESC_ERROR_IPE_SHIFT) | @@ -845,36 +904,17 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, if (rx_error & BIT(I40E_RX_DESC_ERROR_PPRS_SHIFT)) return; - /* If VXLAN traffic has an outer UDPv4 checksum we need to check - * it in the driver, hardware does not do it for us. - * Since L3L4P bit was set we assume a valid IHL value (>=5) - * so the total length of IPv4 header is IHL*4 bytes - * The UDP_0 bit *may* bet set if the *inner* header is UDP + /* The hardware supported by this driver does not validate outer + * checksums for tunneled VXLAN or GENEVE frames. I don't agree + * with it but the specification states that you "MAY validate", it + * doesn't make it a hard requirement so if we have validated the + * inner checksum report CHECKSUM_UNNECESSARY. */ - if (ipv4_tunnel) { - skb->transport_header = skb->mac_header + - sizeof(struct ethhdr) + - (ip_hdr(skb)->ihl * 4); - - /* Add 4 bytes for VLAN tagged packets */ - skb->transport_header += (skb->protocol == htons(ETH_P_8021Q) || - skb->protocol == htons(ETH_P_8021AD)) - ? VLAN_HLEN : 0; - - if ((ip_hdr(skb)->protocol == IPPROTO_UDP) && - (udp_hdr(skb)->check != 0)) { - rx_udp_csum = udp_csum(skb); - iph = ip_hdr(skb); - csum = csum_tcpudp_magic(iph->saddr, iph->daddr, - (skb->len - - skb_transport_offset(skb)), - IPPROTO_UDP, rx_udp_csum); - - if (udp_hdr(skb)->check != csum) - goto checksum_fail; - - } /* else its GRE and so no outer UDP header */ - } + + ipv4_tunnel = (rx_ptype >= I40E_RX_PTYPE_GRENAT4_MAC_PAY3) && + (rx_ptype <= I40E_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4); + ipv6_tunnel = (rx_ptype >= I40E_RX_PTYPE_GRENAT6_MAC_PAY3) && + (rx_ptype <= I40E_RX_PTYPE_GRENAT6_MACVLAN_IPV6_ICMP_PAY4); skb->ip_summed = CHECKSUM_UNNECESSARY; skb->csum_level = ipv4_tunnel || ipv6_tunnel; @@ -939,18 +979,19 @@ static inline void i40e_rx_hash(struct i40e_ring *ring, * * Returns true if there's any budget left (e.g. the clean is finished) **/ -static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget) +static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, const int budget) { unsigned int total_rx_bytes = 0, total_rx_packets = 0; u16 rx_packet_len, rx_header_len, rx_sph, rx_hbo; u16 cleaned_count = I40E_DESC_UNUSED(rx_ring); - const int current_node = numa_mem_id(); struct i40e_vsi *vsi = rx_ring->vsi; u16 i = rx_ring->next_to_clean; union i40e_rx_desc *rx_desc; u32 rx_error, rx_status; + bool failure = false; u8 rx_ptype; u64 qword; + u32 copysize; do { struct i40e_rx_buffer *rx_bi; @@ -958,7 +999,9 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget) u16 vlan_tag; /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= I40E_RX_BUFFER_WRITE) { - i40evf_alloc_rx_buffers_ps(rx_ring, cleaned_count); + failure = failure || + i40evf_alloc_rx_buffers_ps(rx_ring, + cleaned_count); cleaned_count = 0; } @@ -976,13 +1019,22 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget) * DD bit is set. */ dma_rmb(); + /* sync header buffer for reading */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_ring->rx_bi[0].dma, + i * rx_ring->rx_hdr_len, + rx_ring->rx_hdr_len, + DMA_FROM_DEVICE); rx_bi = &rx_ring->rx_bi[i]; skb = rx_bi->skb; if (likely(!skb)) { - skb = netdev_alloc_skb_ip_align(rx_ring->netdev, - rx_ring->rx_hdr_len); + skb = __netdev_alloc_skb_ip_align(rx_ring->netdev, + rx_ring->rx_hdr_len, + GFP_ATOMIC | + __GFP_NOWARN); if (!skb) { rx_ring->rx_stats.alloc_buff_failed++; + failure = true; break; } @@ -990,8 +1042,8 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget) skb_record_rx_queue(skb, rx_ring->queue_index); /* we are reusing so sync this buffer for CPU use */ dma_sync_single_range_for_cpu(rx_ring->dev, - rx_bi->dma, - 0, + rx_ring->rx_bi[0].dma, + i * rx_ring->rx_hdr_len, rx_ring->rx_hdr_len, DMA_FROM_DEVICE); } @@ -1009,9 +1061,16 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget) rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >> I40E_RXD_QW1_PTYPE_SHIFT; - prefetch(rx_bi->page); + /* sync half-page for reading */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_bi->page_dma, + rx_bi->page_offset, + PAGE_SIZE / 2, + DMA_FROM_DEVICE); + prefetch(page_address(rx_bi->page) + rx_bi->page_offset); rx_bi->skb = NULL; cleaned_count++; + copysize = 0; if (rx_hbo || rx_sph) { int len; @@ -1022,38 +1081,50 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget) memcpy(__skb_put(skb, len), rx_bi->hdr_buf, len); } else if (skb->len == 0) { int len; + unsigned char *va = page_address(rx_bi->page) + + rx_bi->page_offset; - len = (rx_packet_len > skb_headlen(skb) ? - skb_headlen(skb) : rx_packet_len); - memcpy(__skb_put(skb, len), - rx_bi->page + rx_bi->page_offset, - len); - rx_bi->page_offset += len; + len = min(rx_packet_len, rx_ring->rx_hdr_len); + memcpy(__skb_put(skb, len), va, len); + copysize = len; rx_packet_len -= len; } - /* Get the rest of the data if this was a header split */ if (rx_packet_len) { - skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags, - rx_bi->page, - rx_bi->page_offset, - rx_packet_len); - - skb->len += rx_packet_len; - skb->data_len += rx_packet_len; - skb->truesize += rx_packet_len; - - if ((page_count(rx_bi->page) == 1) && - (page_to_nid(rx_bi->page) == current_node)) - get_page(rx_bi->page); - else + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, + rx_bi->page, + rx_bi->page_offset + copysize, + rx_packet_len, I40E_RXBUFFER_2048); + + /* If the page count is more than 2, then both halves + * of the page are used and we need to free it. Do it + * here instead of in the alloc code. Otherwise one + * of the half-pages might be released between now and + * then, and we wouldn't know which one to use. + * Don't call get_page and free_page since those are + * both expensive atomic operations that just change + * the refcount in opposite directions. Just give the + * page to the stack; he can have our refcount. + */ + if (page_count(rx_bi->page) > 2) { + dma_unmap_page(rx_ring->dev, + rx_bi->page_dma, + PAGE_SIZE, + DMA_FROM_DEVICE); rx_bi->page = NULL; + rx_bi->page_dma = 0; + rx_ring->rx_stats.realloc_count++; + } else { + get_page(rx_bi->page); + /* switch to the other half-page here; the + * allocation code programs the right addr + * into HW. If we haven't used this half-page, + * the address won't be changed, and HW can + * just use it next time through. + */ + rx_bi->page_offset ^= PAGE_SIZE / 2; + } - dma_unmap_page(rx_ring->dev, - rx_bi->page_dma, - PAGE_SIZE / 2, - DMA_FROM_DEVICE); - rx_bi->page_dma = 0; } I40E_RX_INCREMENT(rx_ring, i); @@ -1105,7 +1176,7 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget) rx_ring->q_vector->rx.total_packets += total_rx_packets; rx_ring->q_vector->rx.total_bytes += total_rx_bytes; - return total_rx_packets; + return failure ? budget : total_rx_packets; } /** @@ -1123,6 +1194,7 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget) union i40e_rx_desc *rx_desc; u32 rx_error, rx_status; u16 rx_packet_len; + bool failure = false; u8 rx_ptype; u64 qword; u16 i; @@ -1133,7 +1205,9 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget) u16 vlan_tag; /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= I40E_RX_BUFFER_WRITE) { - i40evf_alloc_rx_buffers_1buf(rx_ring, cleaned_count); + failure = failure || + i40evf_alloc_rx_buffers_1buf(rx_ring, + cleaned_count); cleaned_count = 0; } @@ -1214,7 +1288,7 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget) rx_ring->q_vector->rx.total_packets += total_rx_packets; rx_ring->q_vector->rx.total_bytes += total_rx_bytes; - return total_rx_packets; + return failure ? budget : total_rx_packets; } static u32 i40e_buildreg_itr(const int type, const u16 itr) @@ -1222,7 +1296,9 @@ static u32 i40e_buildreg_itr(const int type, const u16 itr) u32 val; val = I40E_VFINT_DYN_CTLN1_INTENA_MASK | - I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK | + /* Don't clear PBA because that can cause lost interrupts that + * came in while we were cleaning/polling + */ (type << I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) | (itr << I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT); @@ -1335,7 +1411,8 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) * budget and be more aggressive about cleaning up the Tx descriptors. */ i40e_for_each_ring(ring, q_vector->tx) { - clean_complete &= i40e_clean_tx_irq(ring, vsi->work_limit); + clean_complete = clean_complete && + i40e_clean_tx_irq(ring, vsi->work_limit); arm_wb = arm_wb || ring->arm_wb; ring->arm_wb = false; } @@ -1359,7 +1436,7 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) work_done += cleaned; /* if we didn't clean as many as budgeted, we must be done */ - clean_complete &= (budget_per_ring != cleaned); + clean_complete = clean_complete && (budget_per_ring > cleaned); } /* If work not completed, return budget and polling will return */ @@ -1367,7 +1444,7 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) tx_only: if (arm_wb) { q_vector->tx.ring[0].tx_stats.tx_force_wb++; - i40evf_force_wb(vsi, q_vector); + i40e_enable_wb_on_itr(vsi, q_vector); } return budget; } @@ -1447,13 +1524,23 @@ out: static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb, u8 *hdr_len, u64 *cd_type_cmd_tso_mss) { - u32 cd_cmd, cd_tso_len, cd_mss; - struct ipv6hdr *ipv6h; - struct tcphdr *tcph; - struct iphdr *iph; - u32 l4len; + u64 cd_cmd, cd_tso_len, cd_mss; + 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; @@ -1461,35 +1548,60 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb, if (err < 0) return err; - iph = skb->encapsulation ? inner_ip_hdr(skb) : ip_hdr(skb); - ipv6h = skb->encapsulation ? inner_ipv6_hdr(skb) : ipv6_hdr(skb); - - if (iph->version == 4) { - tcph = skb->encapsulation ? inner_tcp_hdr(skb) : tcp_hdr(skb); - iph->tot_len = 0; - iph->check = 0; - tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, - 0, IPPROTO_TCP, 0); - } else if (ipv6h->version == 6) { - tcph = skb->encapsulation ? inner_tcp_hdr(skb) : tcp_hdr(skb); - ipv6h->payload_len = 0; - tcph->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, - 0, IPPROTO_TCP, 0); + ip.hdr = skb_network_header(skb); + l4.hdr = skb_transport_header(skb); + + /* initialize outer IP header fields */ + if (ip.v4->version == 4) { + ip.v4->tot_len = 0; + ip.v4->check = 0; + } else { + ip.v6->payload_len = 0; + } + + if (skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_GRE | + SKB_GSO_UDP_TUNNEL_CSUM)) { + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM) { + /* determine offset of outer transport header */ + l4_offset = l4.hdr - skb->data; + + /* remove payload length from outer checksum */ + paylen = (__force u16)l4.udp->check; + paylen += ntohs(1) * (u16)~(skb->len - l4_offset); + l4.udp->check = ~csum_fold((__force __wsum)paylen); + } + + /* reset pointers to inner headers */ + ip.hdr = skb_inner_network_header(skb); + l4.hdr = skb_inner_transport_header(skb); + + /* initialize inner IP header fields */ + if (ip.v4->version == 4) { + ip.v4->tot_len = 0; + ip.v4->check = 0; + } else { + ip.v6->payload_len = 0; + } } - l4len = skb->encapsulation ? inner_tcp_hdrlen(skb) : tcp_hdrlen(skb); - *hdr_len = (skb->encapsulation - ? (skb_inner_transport_header(skb) - skb->data) - : skb_transport_offset(skb)) + l4len; + /* determine offset of inner transport header */ + l4_offset = l4.hdr - skb->data; + + /* remove payload length from inner checksum */ + paylen = (__force u16)l4.tcp->check; + paylen += ntohs(1) * (u16)~(skb->len - l4_offset); + l4.tcp->check = ~csum_fold((__force __wsum)paylen); + + /* compute length of segmentation header */ + *hdr_len = (l4.tcp->doff * 4) + l4_offset; /* find the field values */ cd_cmd = I40E_TX_CTX_DESC_TSO; cd_tso_len = skb->len - *hdr_len; cd_mss = skb_shinfo(skb)->gso_size; - *cd_type_cmd_tso_mss |= ((u64)cd_cmd << I40E_TXD_CTX_QW1_CMD_SHIFT) | - ((u64)cd_tso_len << - I40E_TXD_CTX_QW1_TSO_LEN_SHIFT) | - ((u64)cd_mss << I40E_TXD_CTX_QW1_MSS_SHIFT); + *cd_type_cmd_tso_mss |= (cd_cmd << I40E_TXD_CTX_QW1_CMD_SHIFT) | + (cd_tso_len << I40E_TXD_CTX_QW1_TSO_LEN_SHIFT) | + (cd_mss << I40E_TXD_CTX_QW1_MSS_SHIFT); return 1; } @@ -1499,129 +1611,157 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb, * @tx_flags: pointer to Tx flags currently set * @td_cmd: Tx descriptor command bits to set * @td_offset: Tx descriptor header offsets to set + * @tx_ring: Tx descriptor ring * @cd_tunneling: ptr to context desc bits **/ -static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, - u32 *td_cmd, u32 *td_offset, - struct i40e_ring *tx_ring, - u32 *cd_tunneling) +static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, + u32 *td_cmd, u32 *td_offset, + struct i40e_ring *tx_ring, + u32 *cd_tunneling) { - struct ipv6hdr *this_ipv6_hdr; - unsigned int this_tcp_hdrlen; - struct iphdr *this_ip_hdr; - u32 network_hdr_len; - u8 l4_hdr = 0; - struct udphdr *oudph; - struct iphdr *oiph; - u32 l4_tunnel = 0; + union { + struct iphdr *v4; + struct ipv6hdr *v6; + unsigned char *hdr; + } ip; + union { + struct tcphdr *tcp; + struct udphdr *udp; + unsigned char *hdr; + } l4; + unsigned char *exthdr; + u32 offset, cmd = 0, tunnel = 0; + __be16 frag_off; + u8 l4_proto = 0; + + if (skb->ip_summed != CHECKSUM_PARTIAL) + return 0; + + ip.hdr = skb_network_header(skb); + l4.hdr = skb_transport_header(skb); + + /* compute outer L2 header size */ + offset = ((ip.hdr - skb->data) / 2) << I40E_TX_DESC_LENGTH_MACLEN_SHIFT; if (skb->encapsulation) { - switch (ip_hdr(skb)->protocol) { + /* define outer network header type */ + if (*tx_flags & I40E_TX_FLAGS_IPV4) { + tunnel |= (*tx_flags & I40E_TX_FLAGS_TSO) ? + I40E_TX_CTX_EXT_IP_IPV4 : + I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM; + + l4_proto = ip.v4->protocol; + } else if (*tx_flags & I40E_TX_FLAGS_IPV6) { + tunnel |= I40E_TX_CTX_EXT_IP_IPV6; + + exthdr = ip.hdr + sizeof(*ip.v6); + l4_proto = ip.v6->nexthdr; + if (l4.hdr != exthdr) + ipv6_skip_exthdr(skb, exthdr - skb->data, + &l4_proto, &frag_off); + } + + /* compute outer L3 header size */ + tunnel |= ((l4.hdr - ip.hdr) / 4) << + I40E_TXD_CTX_QW0_EXT_IPLEN_SHIFT; + + /* switch IP header pointer from outer to inner header */ + ip.hdr = skb_inner_network_header(skb); + + /* define outer transport */ + switch (l4_proto) { case IPPROTO_UDP: - oudph = udp_hdr(skb); - oiph = ip_hdr(skb); - l4_tunnel = I40E_TXD_CTX_UDP_TUNNELING; + tunnel |= I40E_TXD_CTX_UDP_TUNNELING; + *tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL; + break; + case IPPROTO_GRE: + tunnel |= I40E_TXD_CTX_GRE_TUNNELING; *tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL; break; default: - return; - } - network_hdr_len = skb_inner_network_header_len(skb); - this_ip_hdr = inner_ip_hdr(skb); - this_ipv6_hdr = inner_ipv6_hdr(skb); - this_tcp_hdrlen = inner_tcp_hdrlen(skb); - - if (*tx_flags & I40E_TX_FLAGS_IPV4) { - if (*tx_flags & I40E_TX_FLAGS_TSO) { - *cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV4; - ip_hdr(skb)->check = 0; - } else { - *cd_tunneling |= - I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM; - } - } else if (*tx_flags & I40E_TX_FLAGS_IPV6) { - *cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6; if (*tx_flags & I40E_TX_FLAGS_TSO) - ip_hdr(skb)->check = 0; - } + return -1; - /* Now set the ctx descriptor fields */ - *cd_tunneling |= (skb_network_header_len(skb) >> 2) << - I40E_TXD_CTX_QW0_EXT_IPLEN_SHIFT | - l4_tunnel | - ((skb_inner_network_offset(skb) - - skb_transport_offset(skb)) >> 1) << - I40E_TXD_CTX_QW0_NATLEN_SHIFT; - if (this_ip_hdr->version == 6) { - *tx_flags &= ~I40E_TX_FLAGS_IPV4; - *tx_flags |= I40E_TX_FLAGS_IPV6; + skb_checksum_help(skb); + return 0; } - if ((tx_ring->flags & I40E_TXR_FLAGS_OUTER_UDP_CSUM) && - (l4_tunnel == I40E_TXD_CTX_UDP_TUNNELING) && - (*cd_tunneling & I40E_TXD_CTX_QW0_EXT_IP_MASK)) { - oudph->check = ~csum_tcpudp_magic(oiph->saddr, - oiph->daddr, - (skb->len - skb_transport_offset(skb)), - IPPROTO_UDP, 0); - *cd_tunneling |= I40E_TXD_CTX_QW0_L4T_CS_MASK; - } - } else { - network_hdr_len = skb_network_header_len(skb); - this_ip_hdr = ip_hdr(skb); - this_ipv6_hdr = ipv6_hdr(skb); - this_tcp_hdrlen = tcp_hdrlen(skb); + /* compute tunnel header size */ + tunnel |= ((ip.hdr - l4.hdr) / 2) << + I40E_TXD_CTX_QW0_NATLEN_SHIFT; + + /* indicate if we need to offload outer UDP header */ + if ((*tx_flags & I40E_TX_FLAGS_TSO) && + (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM)) + tunnel |= I40E_TXD_CTX_QW0_L4T_CS_MASK; + + /* record tunnel offload values */ + *cd_tunneling |= tunnel; + + /* switch L4 header pointer from outer to inner */ + l4.hdr = skb_inner_transport_header(skb); + l4_proto = 0; + + /* reset type as we transition from outer to inner headers */ + *tx_flags &= ~(I40E_TX_FLAGS_IPV4 | I40E_TX_FLAGS_IPV6); + if (ip.v4->version == 4) + *tx_flags |= I40E_TX_FLAGS_IPV4; + if (ip.v6->version == 6) + *tx_flags |= I40E_TX_FLAGS_IPV6; } /* Enable IP checksum offloads */ if (*tx_flags & I40E_TX_FLAGS_IPV4) { - l4_hdr = this_ip_hdr->protocol; + l4_proto = ip.v4->protocol; /* the stack computes the IP header already, the only time we * need the hardware to recompute it is in the case of TSO. */ - if (*tx_flags & I40E_TX_FLAGS_TSO) { - *td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4_CSUM; - this_ip_hdr->check = 0; - } else { - *td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4; - } - /* Now set the td_offset for IP header length */ - *td_offset = (network_hdr_len >> 2) << - I40E_TX_DESC_LENGTH_IPLEN_SHIFT; + cmd |= (*tx_flags & I40E_TX_FLAGS_TSO) ? + I40E_TX_DESC_CMD_IIPT_IPV4_CSUM : + I40E_TX_DESC_CMD_IIPT_IPV4; } else if (*tx_flags & I40E_TX_FLAGS_IPV6) { - l4_hdr = this_ipv6_hdr->nexthdr; - *td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV6; - /* Now set the td_offset for IP header length */ - *td_offset = (network_hdr_len >> 2) << - I40E_TX_DESC_LENGTH_IPLEN_SHIFT; + cmd |= I40E_TX_DESC_CMD_IIPT_IPV6; + + exthdr = ip.hdr + sizeof(*ip.v6); + l4_proto = ip.v6->nexthdr; + if (l4.hdr != exthdr) + ipv6_skip_exthdr(skb, exthdr - skb->data, + &l4_proto, &frag_off); } - /* words in MACLEN + dwords in IPLEN + dwords in L4Len */ - *td_offset |= (skb_network_offset(skb) >> 1) << - I40E_TX_DESC_LENGTH_MACLEN_SHIFT; + + /* compute inner L3 header size */ + offset |= ((l4.hdr - ip.hdr) / 4) << I40E_TX_DESC_LENGTH_IPLEN_SHIFT; /* Enable L4 checksum offloads */ - switch (l4_hdr) { + switch (l4_proto) { case IPPROTO_TCP: /* enable checksum offloads */ - *td_cmd |= I40E_TX_DESC_CMD_L4T_EOFT_TCP; - *td_offset |= (this_tcp_hdrlen >> 2) << - I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT; + cmd |= I40E_TX_DESC_CMD_L4T_EOFT_TCP; + offset |= l4.tcp->doff << I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT; break; case IPPROTO_SCTP: /* enable SCTP checksum offload */ - *td_cmd |= I40E_TX_DESC_CMD_L4T_EOFT_SCTP; - *td_offset |= (sizeof(struct sctphdr) >> 2) << - I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT; + cmd |= I40E_TX_DESC_CMD_L4T_EOFT_SCTP; + offset |= (sizeof(struct sctphdr) >> 2) << + I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT; break; case IPPROTO_UDP: /* enable UDP checksum offload */ - *td_cmd |= I40E_TX_DESC_CMD_L4T_EOFT_UDP; - *td_offset |= (sizeof(struct udphdr) >> 2) << - I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT; + cmd |= I40E_TX_DESC_CMD_L4T_EOFT_UDP; + offset |= (sizeof(struct udphdr) >> 2) << + I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT; break; default: - break; + if (*tx_flags & I40E_TX_FLAGS_TSO) + return -1; + skb_checksum_help(skb); + return 0; } + + *td_cmd |= cmd; + *td_offset |= offset; + + return 1; } /** @@ -1656,59 +1796,70 @@ static void i40e_create_tx_ctx(struct i40e_ring *tx_ring, } /** - * i40e_chk_linearize - Check if there are more than 8 fragments per packet + * __i40evf_chk_linearize - Check if there are more than 8 buffers per packet * @skb: send buffer - * @tx_flags: collected send information * - * Note: Our HW can't scatter-gather more than 8 fragments to build - * a packet on the wire and so we need to figure out the cases where we - * need to linearize the skb. + * Note: Our HW can't DMA more than 8 buffers to build a packet on the wire + * and so we need to figure out the cases where we need to linearize the skb. + * + * For TSO we need to count the TSO header and segment payload separately. + * As such we need to check cases where we have 7 fragments or more as we + * can potentially require 9 DMA transactions, 1 for the TSO header, 1 for + * the segment payload in the first descriptor, and another 7 for the + * fragments. **/ -static bool i40e_chk_linearize(struct sk_buff *skb, u32 tx_flags) +bool __i40evf_chk_linearize(struct sk_buff *skb) { - struct skb_frag_struct *frag; - bool linearize = false; - unsigned int size = 0; - u16 num_frags; - u16 gso_segs; + const struct skb_frag_struct *frag, *stale; + int nr_frags, sum; - num_frags = skb_shinfo(skb)->nr_frags; - gso_segs = skb_shinfo(skb)->gso_segs; + /* no need to check if number of frags is less than 7 */ + nr_frags = skb_shinfo(skb)->nr_frags; + if (nr_frags < (I40E_MAX_BUFFER_TXD - 1)) + return false; - if (tx_flags & (I40E_TX_FLAGS_TSO | I40E_TX_FLAGS_FSO)) { - u16 j = 0; + /* We need to walk through the list and validate that each group + * of 6 fragments totals at least gso_size. However we don't need + * to perform such validation on the last 6 since the last 6 cannot + * inherit any data from a descriptor after them. + */ + nr_frags -= I40E_MAX_BUFFER_TXD - 2; + frag = &skb_shinfo(skb)->frags[0]; + + /* Initialize size to the negative value of gso_size minus 1. We + * use this as the worst case scenerio in which the frag ahead + * of us only provides one byte which is why we are limited to 6 + * descriptors for a single transmit as the header and previous + * fragment are already consuming 2 descriptors. + */ + sum = 1 - skb_shinfo(skb)->gso_size; - if (num_frags < (I40E_MAX_BUFFER_TXD)) - goto linearize_chk_done; - /* try the simple math, if we have too many frags per segment */ - if (DIV_ROUND_UP((num_frags + gso_segs), gso_segs) > - I40E_MAX_BUFFER_TXD) { - linearize = true; - goto linearize_chk_done; - } - frag = &skb_shinfo(skb)->frags[0]; - /* we might still have more fragments per segment */ - do { - size += skb_frag_size(frag); - frag++; j++; - if ((size >= skb_shinfo(skb)->gso_size) && - (j < I40E_MAX_BUFFER_TXD)) { - size = (size % skb_shinfo(skb)->gso_size); - j = (size) ? 1 : 0; - } - if (j == I40E_MAX_BUFFER_TXD) { - linearize = true; - break; - } - num_frags--; - } while (num_frags); - } else { - if (num_frags >= I40E_MAX_BUFFER_TXD) - linearize = true; + /* Add size of frags 0 through 4 to create our initial sum */ + sum += skb_frag_size(frag++); + sum += skb_frag_size(frag++); + sum += skb_frag_size(frag++); + sum += skb_frag_size(frag++); + sum += skb_frag_size(frag++); + + /* Walk through fragments adding latest fragment, testing it, and + * then removing stale fragments from the sum. + */ + stale = &skb_shinfo(skb)->frags[0]; + for (;;) { + sum += skb_frag_size(frag++); + + /* if sum is negative we failed to make sufficient progress */ + if (sum < 0) + return true; + + /* use pre-decrement to avoid processing last fragment */ + if (!--nr_frags) + break; + + sum -= skb_frag_size(stale++); } -linearize_chk_done: - return linearize; + return false; } /** @@ -1718,7 +1869,7 @@ linearize_chk_done: * * Returns -EBUSY if a stop is needed, else 0 **/ -static inline int __i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size) +int __i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size) { netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index); /* Memory barrier before checking head and tail */ @@ -1735,20 +1886,6 @@ static inline int __i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size) } /** - * i40evf_maybe_stop_tx - 1st level check for tx stop conditions - * @tx_ring: the ring to be checked - * @size: the size buffer we want to assure is available - * - * Returns 0 if stop is not needed - **/ -static inline int i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size) -{ - if (likely(I40E_DESC_UNUSED(tx_ring) >= size)) - return 0; - return __i40evf_maybe_stop_tx(tx_ring, size); -} - -/** * i40evf_tx_map - Build the Tx descriptor * @tx_ring: ring to send buffer on * @skb: send buffer @@ -1863,7 +2000,7 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, netdev_tx_sent_queue(netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index), first->bytecount); - i40evf_maybe_stop_tx(tx_ring, DESC_NEEDED); + i40e_maybe_stop_tx(tx_ring, DESC_NEEDED); /* Algorithm to optimize tail and RS bit setting: * if xmit_more is supported @@ -1946,38 +2083,6 @@ dma_error: } /** - * i40evf_xmit_descriptor_count - calculate number of tx descriptors needed - * @skb: send buffer - * @tx_ring: ring to send buffer on - * - * Returns number of data descriptors needed for this skb. Returns 0 to indicate - * there is not enough descriptors available in this ring since we need at least - * one descriptor. - **/ -static inline int i40evf_xmit_descriptor_count(struct sk_buff *skb, - struct i40e_ring *tx_ring) -{ - unsigned int f; - int count = 0; - - /* need: 1 descriptor per page * PAGE_SIZE/I40E_MAX_DATA_PER_TXD, - * + 1 desc for skb_head_len/I40E_MAX_DATA_PER_TXD, - * + 4 desc gap to avoid the cache line where head is, - * + 1 desc for context descriptor, - * otherwise try next time - */ - for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) - count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size); - - count += TXD_USE_COUNT(skb_headlen(skb)); - if (i40evf_maybe_stop_tx(tx_ring, count + 4 + 1)) { - tx_ring->tx_stats.tx_busy++; - return 0; - } - return count; -} - -/** * i40e_xmit_frame_ring - Sends buffer on Tx ring * @skb: send buffer * @tx_ring: ring to send buffer on @@ -1995,13 +2100,29 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, __be16 protocol; u32 td_cmd = 0; u8 hdr_len = 0; - int tso; + int tso, count; /* prefetch the data, we'll need it later */ prefetch(skb->data); - if (0 == i40evf_xmit_descriptor_count(skb, tx_ring)) + count = i40e_xmit_descriptor_count(skb); + if (i40e_chk_linearize(skb, count)) { + if (__skb_linearize(skb)) + goto out_drop; + count = TXD_USE_COUNT(skb->len); + tx_ring->tx_stats.tx_linearize++; + } + + /* need: 1 descriptor per page * PAGE_SIZE/I40E_MAX_DATA_PER_TXD, + * + 1 desc for skb_head_len/I40E_MAX_DATA_PER_TXD, + * + 4 desc gap to avoid the cache line where head is, + * + 1 desc for context descriptor, + * otherwise try next time + */ + if (i40e_maybe_stop_tx(tx_ring, count + 4 + 1)) { + tx_ring->tx_stats.tx_busy++; return NETDEV_TX_BUSY; + } /* prepare the xmit flags */ if (i40evf_tx_prepare_vlan_flags(skb, tx_ring, &tx_flags)) @@ -2026,24 +2147,17 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, else if (tso) tx_flags |= I40E_TX_FLAGS_TSO; - if (i40e_chk_linearize(skb, tx_flags)) { - if (skb_linearize(skb)) - goto out_drop; - tx_ring->tx_stats.tx_linearize++; - } + /* Always offload the checksum, since it's in the data descriptor */ + tso = i40e_tx_enable_csum(skb, &tx_flags, &td_cmd, &td_offset, + tx_ring, &cd_tunneling); + if (tso < 0) + goto out_drop; + skb_tx_timestamp(skb); /* always enable CRC insertion offload */ td_cmd |= I40E_TX_DESC_CMD_ICRC; - /* Always offload the checksum, since it's in the data descriptor */ - if (skb->ip_summed == CHECKSUM_PARTIAL) { - tx_flags |= I40E_TX_FLAGS_CSUM; - - i40e_tx_enable_csum(skb, &tx_flags, &td_cmd, &td_offset, - tx_ring, &cd_tunneling); - } - i40e_create_tx_ctx(tx_ring, cd_type_cmd_tso_mss, cd_tunneling, cd_l2tag2); diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index e29bb3e86..0429553fe 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -1,7 +1,7 @@ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2014 Intel Corporation. + * Copyright(c) 2013 - 2016 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -153,7 +153,6 @@ enum i40e_dyn_idx_t { #define DESC_NEEDED (MAX_SKB_FRAGS + 4) #define I40E_MIN_DESC_PENDING 4 -#define I40E_TX_FLAGS_CSUM BIT(0) #define I40E_TX_FLAGS_HW_VLAN BIT(1) #define I40E_TX_FLAGS_SW_VLAN BIT(2) #define I40E_TX_FLAGS_TSO BIT(3) @@ -202,12 +201,15 @@ struct i40e_tx_queue_stats { u64 tx_done_old; u64 tx_linearize; u64 tx_force_wb; + u64 tx_lost_interrupt; }; struct i40e_rx_queue_stats { u64 non_eop_descs; u64 alloc_page_failed; u64 alloc_buff_failed; + u64 page_reuse_count; + u64 realloc_count; }; enum i40e_ring_state_t { @@ -253,7 +255,6 @@ struct i40e_ring { #define I40E_RX_DTYPE_NO_SPLIT 0 #define I40E_RX_DTYPE_HEADER_SPLIT 1 #define I40E_RX_DTYPE_SPLIT_ALWAYS 2 - u8 hsplit; #define I40E_RX_SPLIT_L2 0x1 #define I40E_RX_SPLIT_IP 0x2 #define I40E_RX_SPLIT_TCP_UDP 0x4 @@ -273,7 +274,6 @@ struct i40e_ring { u16 flags; #define I40E_TXR_FLAGS_WB_ON_ITR BIT(0) -#define I40E_TXR_FLAGS_OUTER_UDP_CSUM BIT(1) /* stats structs */ struct i40e_queue_stats stats; @@ -313,8 +313,8 @@ struct i40e_ring_container { #define i40e_for_each_ring(pos, head) \ for (pos = (head).ring; pos != NULL; pos = pos->next) -void i40evf_alloc_rx_buffers_ps(struct i40e_ring *rxr, u16 cleaned_count); -void i40evf_alloc_rx_buffers_1buf(struct i40e_ring *rxr, u16 cleaned_count); +bool i40evf_alloc_rx_buffers_ps(struct i40e_ring *rxr, u16 cleaned_count); +bool i40evf_alloc_rx_buffers_1buf(struct i40e_ring *rxr, u16 cleaned_count); void i40evf_alloc_rx_headers(struct i40e_ring *rxr); netdev_tx_t i40evf_xmit_frame(struct sk_buff *skb, struct net_device *netdev); void i40evf_clean_tx_ring(struct i40e_ring *tx_ring); @@ -324,7 +324,10 @@ int i40evf_setup_rx_descriptors(struct i40e_ring *rx_ring); void i40evf_free_tx_resources(struct i40e_ring *tx_ring); void i40evf_free_rx_resources(struct i40e_ring *rx_ring); int i40evf_napi_poll(struct napi_struct *napi, int budget); -u32 i40evf_get_tx_pending(struct i40e_ring *ring); +void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector); +u32 i40evf_get_tx_pending(struct i40e_ring *ring, bool in_sw); +int __i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size); +bool __i40evf_chk_linearize(struct sk_buff *skb); /** * i40e_get_head - Retrieve head from head writeback @@ -339,4 +342,67 @@ static inline u32 i40e_get_head(struct i40e_ring *tx_ring) return le32_to_cpu(*(volatile __le32 *)head); } + +/** + * i40e_xmit_descriptor_count - calculate number of Tx descriptors needed + * @skb: send buffer + * @tx_ring: ring to send buffer on + * + * Returns number of data descriptors needed for this skb. Returns 0 to indicate + * there is not enough descriptors available in this ring since we need at least + * one descriptor. + **/ +static inline int i40e_xmit_descriptor_count(struct sk_buff *skb) +{ + const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; + unsigned int nr_frags = skb_shinfo(skb)->nr_frags; + int count = 0, size = skb_headlen(skb); + + for (;;) { + count += TXD_USE_COUNT(size); + + if (!nr_frags--) + break; + + size = skb_frag_size(frag++); + } + + return count; +} + +/** + * i40e_maybe_stop_tx - 1st level check for Tx stop conditions + * @tx_ring: the ring to be checked + * @size: the size buffer we want to assure is available + * + * Returns 0 if stop is not needed + **/ +static inline int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size) +{ + if (likely(I40E_DESC_UNUSED(tx_ring) >= size)) + return 0; + return __i40evf_maybe_stop_tx(tx_ring, size); +} + +/** + * i40e_chk_linearize - Check if there are more than 8 fragments per packet + * @skb: send buffer + * @count: number of buffers used + * + * Note: Our HW can't scatter-gather more than 8 fragments to build + * a packet on the wire and so we need to figure out the cases where we + * need to linearize the skb. + **/ +static inline bool i40e_chk_linearize(struct sk_buff *skb, int count) +{ + /* Both TSO and single send will work if count is less than 8 */ + if (likely(count < I40E_MAX_BUFFER_TXD)) + return false; + + if (skb_is_gso(skb)) + return __i40evf_chk_linearize(skb); + + /* we can support up to 8 data buffers for a single send */ + return count != I40E_MAX_BUFFER_TXD; +} #endif /* _I40E_TXRX_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h index be1b72b93..e657eccd2 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ b/drivers/net/ethernet/intel/i40evf/i40evf.h @@ -1,7 +1,7 @@ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2014 Intel Corporation. + * Copyright(c) 2013 - 2016 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -173,6 +173,7 @@ enum i40evf_state_t { __I40EVF_RESETTING, /* in reset */ /* Below here, watchdog is running */ __I40EVF_DOWN, /* ready, can be opened */ + __I40EVF_DOWN_PENDING, /* descending, waiting for watchdog */ __I40EVF_TESTING, /* in ethtool self-test */ __I40EVF_RUNNING, /* opened, working */ }; @@ -273,6 +274,9 @@ struct i40evf_adapter { }; +/* Ethtool Private Flags */ +#define I40EVF_PRIV_FLAGS_PS BIT(0) + /* needed by i40evf_ethtool.c */ extern char i40evf_driver_name[]; extern const char i40evf_driver_version[]; @@ -280,6 +284,7 @@ extern const char i40evf_driver_version[]; int i40evf_up(struct i40evf_adapter *adapter); void i40evf_down(struct i40evf_adapter *adapter); int i40evf_process_config(struct i40evf_adapter *adapter); +void i40evf_schedule_reset(struct i40evf_adapter *adapter); void i40evf_reset(struct i40evf_adapter *adapter); void i40evf_set_ethtool_ops(struct net_device *netdev); void i40evf_update_stats(struct i40evf_adapter *adapter); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c index a4c9feb58..dd4430aae 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c @@ -1,7 +1,7 @@ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2015 Intel Corporation. + * Copyright(c) 2013 - 2016 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -63,6 +63,12 @@ static const struct i40evf_stats i40evf_gstrings_stats[] = { #define I40EVF_STATS_LEN(_dev) \ (I40EVF_GLOBAL_STATS_LEN + I40EVF_QUEUE_STATS_LEN(_dev)) +static const char i40evf_priv_flags_strings[][ETH_GSTRING_LEN] = { + "packet-split", +}; + +#define I40EVF_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40evf_priv_flags_strings) + /** * i40evf_get_settings - Get Link Speed and Duplex settings * @netdev: network interface device structure @@ -97,6 +103,8 @@ static int i40evf_get_sset_count(struct net_device *netdev, int sset) { if (sset == ETH_SS_STATS) return I40EVF_STATS_LEN(netdev); + else if (sset == ETH_SS_PRIV_FLAGS) + return I40EVF_PRIV_FLAGS_STR_LEN; else return -EINVAL; } @@ -162,6 +170,12 @@ static void i40evf_get_strings(struct net_device *netdev, u32 sset, u8 *data) snprintf(p, ETH_GSTRING_LEN, "rx-%u.bytes", i); p += ETH_GSTRING_LEN; } + } else if (sset == ETH_SS_PRIV_FLAGS) { + for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) { + memcpy(data, i40evf_priv_flags_strings[i], + ETH_GSTRING_LEN); + data += ETH_GSTRING_LEN; + } } } @@ -211,6 +225,7 @@ static void i40evf_get_drvinfo(struct net_device *netdev, strlcpy(drvinfo->version, i40evf_driver_version, 32); strlcpy(drvinfo->fw_version, "N/A", 4); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), 32); + drvinfo->n_priv_flags = I40EVF_PRIV_FLAGS_STR_LEN; } /** @@ -459,6 +474,7 @@ static int i40evf_set_rss_hash_opt(struct i40evf_adapter *adapter, struct ethtool_rxnfc *nfc) { struct i40e_hw *hw = &adapter->hw; + u32 flags = adapter->vf_res->vf_offload_flags; u64 hena = (u64)rd32(hw, I40E_VFQF_HENA(0)) | ((u64)rd32(hw, I40E_VFQF_HENA(1)) << 32); @@ -477,54 +493,50 @@ static int i40evf_set_rss_hash_opt(struct i40evf_adapter *adapter, switch (nfc->flow_type) { case TCP_V4_FLOW: - switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { - case 0: - hena &= ~BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP); - break; - case (RXH_L4_B_0_1 | RXH_L4_B_2_3): + if (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { + if (flags & I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2) + hena |= + BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK); + hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP); - break; - default: + } else { return -EINVAL; } break; case TCP_V6_FLOW: - switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { - case 0: - hena &= ~BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP); - break; - case (RXH_L4_B_0_1 | RXH_L4_B_2_3): + if (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { + if (flags & I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2) + hena |= + BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK); + hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP); - break; - default: + } else { return -EINVAL; } break; case UDP_V4_FLOW: - switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { - case 0: - hena &= ~(BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_UDP) | - BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4)); - break; - case (RXH_L4_B_0_1 | RXH_L4_B_2_3): + if (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { + if (flags & I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2) + hena |= + BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | + BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP); + hena |= (BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_UDP) | BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4)); - break; - default: + } else { return -EINVAL; } break; case UDP_V6_FLOW: - switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { - case 0: - hena &= ~(BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_UDP) | - BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6)); - break; - case (RXH_L4_B_0_1 | RXH_L4_B_2_3): + if (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { + if (flags & I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2) + hena |= + BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | + BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP); + hena |= (BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_UDP) | BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6)); - break; - default: + } else { return -EINVAL; } break; @@ -713,6 +725,54 @@ static int i40evf_set_rxfh(struct net_device *netdev, const u32 *indir, I40EVF_HLUT_ARRAY_SIZE); } +/** + * i40evf_get_priv_flags - report device private flags + * @dev: network interface device structure + * + * The get string set count and the string set should be matched for each + * flag returned. Add new strings for each flag to the i40e_priv_flags_strings + * array. + * + * Returns a u32 bitmap of flags. + **/ +static u32 i40evf_get_priv_flags(struct net_device *dev) +{ + struct i40evf_adapter *adapter = netdev_priv(dev); + u32 ret_flags = 0; + + ret_flags |= adapter->flags & I40EVF_FLAG_RX_PS_ENABLED ? + I40EVF_PRIV_FLAGS_PS : 0; + + return ret_flags; +} + +/** + * i40evf_set_priv_flags - set private flags + * @dev: network interface device structure + * @flags: bit flags to be set + **/ +static int i40evf_set_priv_flags(struct net_device *dev, u32 flags) +{ + struct i40evf_adapter *adapter = netdev_priv(dev); + bool reset_required = false; + + if ((flags & I40EVF_PRIV_FLAGS_PS) && + !(adapter->flags & I40EVF_FLAG_RX_PS_ENABLED)) { + adapter->flags |= I40EVF_FLAG_RX_PS_ENABLED; + reset_required = true; + } else if (!(flags & I40EVF_PRIV_FLAGS_PS) && + (adapter->flags & I40EVF_FLAG_RX_PS_ENABLED)) { + adapter->flags &= ~I40EVF_FLAG_RX_PS_ENABLED; + reset_required = true; + } + + /* if needed, issue reset to cause things to take effect */ + if (reset_required) + i40evf_schedule_reset(adapter); + + return 0; +} + static const struct ethtool_ops i40evf_ethtool_ops = { .get_settings = i40evf_get_settings, .get_drvinfo = i40evf_get_drvinfo, @@ -722,6 +782,8 @@ static const struct ethtool_ops i40evf_ethtool_ops = { .get_strings = i40evf_get_strings, .get_ethtool_stats = i40evf_get_ethtool_stats, .get_sset_count = i40evf_get_sset_count, + .get_priv_flags = i40evf_get_priv_flags, + .set_priv_flags = i40evf_set_priv_flags, .get_msglevel = i40evf_get_msglevel, .set_msglevel = i40evf_set_msglevel, .get_coalesce = i40evf_get_coalesce, diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index 94da913b1..4b70aae2f 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -1,7 +1,7 @@ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2015 Intel Corporation. + * Copyright(c) 2013 - 2016 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -32,13 +32,13 @@ static int i40evf_close(struct net_device *netdev); char i40evf_driver_name[] = "i40evf"; static const char i40evf_driver_string[] = - "Intel(R) XL710/X710 Virtual Function Network Driver"; + "Intel(R) 40-10 Gigabit Virtual Function Network Driver"; #define DRV_KERN "-k" #define DRV_VERSION_MAJOR 1 #define DRV_VERSION_MINOR 4 -#define DRV_VERSION_BUILD 4 +#define DRV_VERSION_BUILD 15 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) \ @@ -69,6 +69,8 @@ MODULE_DESCRIPTION("Intel(R) XL710 X710 Virtual Function Network Driver"); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); +static struct workqueue_struct *i40evf_wq; + /** * i40evf_allocate_dma_mem_d - OS specific memory alloc for shared code * @hw: pointer to the HW structure @@ -171,6 +173,19 @@ void i40evf_debug_d(void *hw, u32 mask, char *fmt_str, ...) } /** + * i40evf_schedule_reset - Set the flags and schedule a reset event + * @adapter: board private structure + **/ +void i40evf_schedule_reset(struct i40evf_adapter *adapter) +{ + if (!(adapter->flags & + (I40EVF_FLAG_RESET_PENDING | I40EVF_FLAG_RESET_NEEDED))) { + adapter->flags |= I40EVF_FLAG_RESET_NEEDED; + schedule_work(&adapter->reset_task); + } +} + +/** * i40evf_tx_timeout - Respond to a Tx Hang * @netdev: network interface device structure **/ @@ -179,11 +194,7 @@ static void i40evf_tx_timeout(struct net_device *netdev) struct i40evf_adapter *adapter = netdev_priv(netdev); adapter->tx_timeout_count++; - if (!(adapter->flags & (I40EVF_FLAG_RESET_PENDING | - I40EVF_FLAG_RESET_NEEDED))) { - adapter->flags |= I40EVF_FLAG_RESET_NEEDED; - schedule_work(&adapter->reset_task); - } + i40evf_schedule_reset(adapter); } /** @@ -636,35 +647,22 @@ static void i40evf_configure_rx(struct i40evf_adapter *adapter) int rx_buf_len; - adapter->flags &= ~I40EVF_FLAG_RX_PS_CAPABLE; - adapter->flags |= I40EVF_FLAG_RX_1BUF_CAPABLE; - - /* Decide whether to use packet split mode or not */ - if (netdev->mtu > ETH_DATA_LEN) { - if (adapter->flags & I40EVF_FLAG_RX_PS_CAPABLE) - adapter->flags |= I40EVF_FLAG_RX_PS_ENABLED; - else - adapter->flags &= ~I40EVF_FLAG_RX_PS_ENABLED; - } else { - if (adapter->flags & I40EVF_FLAG_RX_1BUF_CAPABLE) - adapter->flags &= ~I40EVF_FLAG_RX_PS_ENABLED; - else - adapter->flags |= I40EVF_FLAG_RX_PS_ENABLED; - } - /* Set the RX buffer length according to the mode */ - if (adapter->flags & I40EVF_FLAG_RX_PS_ENABLED) { - rx_buf_len = I40E_RX_HDR_SIZE; - } else { - if (netdev->mtu <= ETH_DATA_LEN) - rx_buf_len = I40EVF_RXBUFFER_2048; - else - rx_buf_len = ALIGN(max_frame, 1024); - } + if (adapter->flags & I40EVF_FLAG_RX_PS_ENABLED || + netdev->mtu <= ETH_DATA_LEN) + rx_buf_len = I40EVF_RXBUFFER_2048; + else + rx_buf_len = ALIGN(max_frame, 1024); for (i = 0; i < adapter->num_active_queues; i++) { adapter->rx_rings[i].tail = hw->hw_addr + I40E_QRX_TAIL1(i); adapter->rx_rings[i].rx_buf_len = rx_buf_len; + if (adapter->flags & I40EVF_FLAG_RX_PS_ENABLED) { + set_ring_ps_enabled(&adapter->rx_rings[i]); + adapter->rx_rings[i].rx_hdr_len = I40E_RX_HDR_SIZE; + } else { + clear_ring_ps_enabled(&adapter->rx_rings[i]); + } } } @@ -1001,7 +999,12 @@ static void i40evf_configure(struct i40evf_adapter *adapter) for (i = 0; i < adapter->num_active_queues; i++) { struct i40e_ring *ring = &adapter->rx_rings[i]; + if (adapter->flags & I40EVF_FLAG_RX_PS_ENABLED) { + i40evf_alloc_rx_headers(ring); + i40evf_alloc_rx_buffers_ps(ring, ring->count); + } else { i40evf_alloc_rx_buffers_1buf(ring, ring->count); + } ring->next_to_use = ring->count - 1; writel(ring->next_to_use, ring->tail); } @@ -1032,7 +1035,7 @@ void i40evf_down(struct i40evf_adapter *adapter) struct net_device *netdev = adapter->netdev; struct i40evf_mac_filter *f; - if (adapter->state == __I40EVF_DOWN) + if (adapter->state <= __I40EVF_DOWN_PENDING) return; while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK, @@ -1122,7 +1125,9 @@ static void i40evf_free_queues(struct i40evf_adapter *adapter) if (!adapter->vsi_res) return; kfree(adapter->tx_rings); + adapter->tx_rings = NULL; kfree(adapter->rx_rings); + adapter->rx_rings = NULL; } /** @@ -1454,7 +1459,11 @@ static int i40evf_init_rss(struct i40evf_adapter *adapter) int ret; /* Enable PCTYPES for RSS, TCP/UDP with IPv4/IPv6 */ - hena = I40E_DEFAULT_RSS_HENA; + if (adapter->vf_res->vf_offload_flags & + I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2) + hena = I40E_DEFAULT_RSS_HENA_EXPANDED; + else + hena = I40E_DEFAULT_RSS_HENA; wr32(hw, I40E_VFQF_HENA(0), (u32)hena); wr32(hw, I40E_VFQF_HENA(1), (u32)(hena >> 32)); @@ -1829,6 +1838,7 @@ static void i40evf_reset_task(struct work_struct *work) break; msleep(I40EVF_RESET_WAIT_MS); } + pci_set_master(adapter->pdev); /* extra wait to make sure minimum wait is met */ msleep(I40EVF_RESET_WAIT_MS); if (i == I40EVF_RESET_WAIT_COUNT) { @@ -1873,6 +1883,7 @@ static void i40evf_reset_task(struct work_struct *work) adapter->netdev->flags &= ~IFF_UP; clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); adapter->flags &= ~I40EVF_FLAG_RESET_PENDING; + adapter->state = __I40EVF_DOWN; dev_info(&adapter->pdev->dev, "Reset task did not complete, VF disabled\n"); return; /* Do not attempt to reinit. It's dead, Jim. */ } @@ -2142,7 +2153,8 @@ static int i40evf_open(struct net_device *netdev) dev_err(&adapter->pdev->dev, "Unable to open device due to PF driver failure.\n"); return -EIO; } - if (adapter->state != __I40EVF_DOWN || adapter->aq_required) + + if (adapter->state != __I40EVF_DOWN) return -EBUSY; /* allocate transmit descriptors */ @@ -2197,14 +2209,14 @@ static int i40evf_close(struct net_device *netdev) { struct i40evf_adapter *adapter = netdev_priv(netdev); - if (adapter->state <= __I40EVF_DOWN) + if (adapter->state <= __I40EVF_DOWN_PENDING) return 0; set_bit(__I40E_DOWN, &adapter->vsi.state); i40evf_down(adapter); - adapter->state = __I40EVF_DOWN; + adapter->state = __I40EVF_DOWN_PENDING; i40evf_free_traffic_irqs(adapter); return 0; @@ -2325,9 +2337,24 @@ int i40evf_process_config(struct i40evf_adapter *adapter) NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO6 | + NETIF_F_TSO_ECN | + NETIF_F_GSO_GRE | + NETIF_F_GSO_UDP_TUNNEL | NETIF_F_RXCSUM | NETIF_F_GRO; + netdev->hw_enc_features |= NETIF_F_IP_CSUM | + NETIF_F_IPV6_CSUM | + NETIF_F_TSO | + NETIF_F_TSO6 | + NETIF_F_TSO_ECN | + NETIF_F_GSO_GRE | + NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM; + + if (adapter->flags & I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE) + netdev->features |= NETIF_F_GSO_UDP_TUNNEL_CSUM; + /* copy netdev features into list of user selectable features */ netdev->hw_features |= netdev->features; netdev->hw_features &= ~NETIF_F_RXCSUM; @@ -2466,11 +2493,20 @@ static void i40evf_init_task(struct work_struct *work) default: goto err_alloc; } + + if (hw->mac.type == I40E_MAC_X722_VF) + adapter->flags |= I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE; + if (i40evf_process_config(adapter)) goto err_alloc; adapter->current_op = I40E_VIRTCHNL_OP_UNKNOWN; adapter->flags |= I40EVF_FLAG_RX_CSUM_ENABLED; + adapter->flags |= I40EVF_FLAG_RX_1BUF_CAPABLE; + adapter->flags |= I40EVF_FLAG_RX_PS_CAPABLE; + + /* Default to single buffer rx, can be changed through ethtool. */ + adapter->flags &= ~I40EVF_FLAG_RX_PS_ENABLED; netdev->netdev_ops = &i40evf_netdev_ops; i40evf_set_ethtool_ops(netdev); @@ -2502,10 +2538,9 @@ static void i40evf_init_task(struct work_struct *work) goto err_sw_init; i40evf_map_rings_to_vectors(adapter); if (adapter->vf_res->vf_offload_flags & - I40E_VIRTCHNL_VF_OFFLOAD_WB_ON_ITR) + I40E_VIRTCHNL_VF_OFFLOAD_WB_ON_ITR) adapter->flags |= I40EVF_FLAG_WB_ON_ITR_CAPABLE; - if (!RSS_AQ(adapter)) - i40evf_init_rss(adapter); + err = i40evf_request_misc_irq(adapter); if (err) goto err_sw_init; @@ -2885,6 +2920,11 @@ static int __init i40evf_init_module(void) pr_info("%s\n", i40evf_copyright); + i40evf_wq = create_singlethread_workqueue(i40evf_driver_name); + if (!i40evf_wq) { + pr_err("%s: Failed to create workqueue\n", i40evf_driver_name); + return -ENOMEM; + } ret = pci_register_driver(&i40evf_driver); return ret; } @@ -2900,6 +2940,7 @@ module_init(i40evf_init_module); static void __exit i40evf_exit_module(void) { pci_unregister_driver(&i40evf_driver); + destroy_workqueue(i40evf_wq); } module_exit(i40evf_exit_module); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c index c1c526283..488e738f7 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c @@ -270,6 +270,10 @@ void i40evf_configure_queues(struct i40evf_adapter *adapter) vqpi->rxq.max_pkt_size = adapter->netdev->mtu + ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN; vqpi->rxq.databuffer_size = adapter->rx_rings[i].rx_buf_len; + if (adapter->flags & I40EVF_FLAG_RX_PS_ENABLED) { + vqpi->rxq.splithdr_enabled = true; + vqpi->rxq.hdr_size = I40E_RX_HDR_SIZE; + } vqpi++; } @@ -804,6 +808,8 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, case I40E_VIRTCHNL_OP_DISABLE_QUEUES: i40evf_free_all_tx_resources(adapter); i40evf_free_all_rx_resources(adapter); + if (adapter->state == __I40EVF_DOWN_PENDING) + adapter->state = __I40EVF_DOWN; break; case I40E_VIRTCHNL_OP_VERSION: case I40E_VIRTCHNL_OP_CONFIG_IRQ_MAP: |