diff options
Diffstat (limited to 'drivers/net/ethernet/intel/iavf')
21 files changed, 14445 insertions, 0 deletions
diff --git a/drivers/net/ethernet/intel/iavf/Makefile b/drivers/net/ethernet/intel/iavf/Makefile new file mode 100644 index 000000000000..9cbb5743ed12 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/Makefile @@ -0,0 +1,15 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright(c) 2013 - 2018 Intel Corporation. +# +# Makefile for the Intel(R) Ethernet Adaptive Virtual Function (iavf) +# driver +# +# + +ccflags-y += -I$(src) +subdir-ccflags-y += -I$(src) + +obj-$(CONFIG_IAVF) += iavf.o + +iavf-objs := iavf_main.o iavf_ethtool.o iavf_virtchnl.o \ + iavf_txrx.o iavf_common.o i40e_adminq.o iavf_client.o diff --git a/drivers/net/ethernet/intel/iavf/i40e_adminq.c b/drivers/net/ethernet/intel/iavf/i40e_adminq.c new file mode 100644 index 000000000000..fca1ecfd9f71 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/i40e_adminq.c @@ -0,0 +1,936 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#include "iavf_status.h" +#include "iavf_type.h" +#include "iavf_register.h" +#include "i40e_adminq.h" +#include "iavf_prototype.h" + +/** + * i40e_adminq_init_regs - Initialize AdminQ registers + * @hw: pointer to the hardware structure + * + * This assumes the alloc_asq and alloc_arq functions have already been called + **/ +static void i40e_adminq_init_regs(struct iavf_hw *hw) +{ + /* set head and tail registers in our local struct */ + hw->aq.asq.tail = IAVF_VF_ATQT1; + hw->aq.asq.head = IAVF_VF_ATQH1; + hw->aq.asq.len = IAVF_VF_ATQLEN1; + hw->aq.asq.bal = IAVF_VF_ATQBAL1; + hw->aq.asq.bah = IAVF_VF_ATQBAH1; + hw->aq.arq.tail = IAVF_VF_ARQT1; + hw->aq.arq.head = IAVF_VF_ARQH1; + hw->aq.arq.len = IAVF_VF_ARQLEN1; + hw->aq.arq.bal = IAVF_VF_ARQBAL1; + hw->aq.arq.bah = IAVF_VF_ARQBAH1; +} + +/** + * i40e_alloc_adminq_asq_ring - Allocate Admin Queue send rings + * @hw: pointer to the hardware structure + **/ +static iavf_status i40e_alloc_adminq_asq_ring(struct iavf_hw *hw) +{ + iavf_status ret_code; + + ret_code = iavf_allocate_dma_mem(hw, &hw->aq.asq.desc_buf, + i40e_mem_atq_ring, + (hw->aq.num_asq_entries * + sizeof(struct i40e_aq_desc)), + IAVF_ADMINQ_DESC_ALIGNMENT); + if (ret_code) + return ret_code; + + ret_code = iavf_allocate_virt_mem(hw, &hw->aq.asq.cmd_buf, + (hw->aq.num_asq_entries * + sizeof(struct i40e_asq_cmd_details))); + if (ret_code) { + iavf_free_dma_mem(hw, &hw->aq.asq.desc_buf); + return ret_code; + } + + return ret_code; +} + +/** + * i40e_alloc_adminq_arq_ring - Allocate Admin Queue receive rings + * @hw: pointer to the hardware structure + **/ +static iavf_status i40e_alloc_adminq_arq_ring(struct iavf_hw *hw) +{ + iavf_status ret_code; + + ret_code = iavf_allocate_dma_mem(hw, &hw->aq.arq.desc_buf, + i40e_mem_arq_ring, + (hw->aq.num_arq_entries * + sizeof(struct i40e_aq_desc)), + IAVF_ADMINQ_DESC_ALIGNMENT); + + return ret_code; +} + +/** + * i40e_free_adminq_asq - Free Admin Queue send rings + * @hw: pointer to the hardware structure + * + * This assumes the posted send buffers have already been cleaned + * and de-allocated + **/ +static void i40e_free_adminq_asq(struct iavf_hw *hw) +{ + iavf_free_dma_mem(hw, &hw->aq.asq.desc_buf); +} + +/** + * i40e_free_adminq_arq - Free Admin Queue receive rings + * @hw: pointer to the hardware structure + * + * This assumes the posted receive buffers have already been cleaned + * and de-allocated + **/ +static void i40e_free_adminq_arq(struct iavf_hw *hw) +{ + iavf_free_dma_mem(hw, &hw->aq.arq.desc_buf); +} + +/** + * i40e_alloc_arq_bufs - Allocate pre-posted buffers for the receive queue + * @hw: pointer to the hardware structure + **/ +static iavf_status i40e_alloc_arq_bufs(struct iavf_hw *hw) +{ + struct i40e_aq_desc *desc; + struct iavf_dma_mem *bi; + iavf_status ret_code; + int i; + + /* We'll be allocating the buffer info memory first, then we can + * allocate the mapped buffers for the event processing + */ + + /* buffer_info structures do not need alignment */ + ret_code = iavf_allocate_virt_mem(hw, &hw->aq.arq.dma_head, + (hw->aq.num_arq_entries * + sizeof(struct iavf_dma_mem))); + if (ret_code) + goto alloc_arq_bufs; + hw->aq.arq.r.arq_bi = (struct iavf_dma_mem *)hw->aq.arq.dma_head.va; + + /* allocate the mapped buffers */ + for (i = 0; i < hw->aq.num_arq_entries; i++) { + bi = &hw->aq.arq.r.arq_bi[i]; + ret_code = iavf_allocate_dma_mem(hw, bi, + i40e_mem_arq_buf, + hw->aq.arq_buf_size, + IAVF_ADMINQ_DESC_ALIGNMENT); + if (ret_code) + goto unwind_alloc_arq_bufs; + + /* now configure the descriptors for use */ + desc = IAVF_ADMINQ_DESC(hw->aq.arq, i); + + desc->flags = cpu_to_le16(I40E_AQ_FLAG_BUF); + if (hw->aq.arq_buf_size > I40E_AQ_LARGE_BUF) + desc->flags |= cpu_to_le16(I40E_AQ_FLAG_LB); + desc->opcode = 0; + /* This is in accordance with Admin queue design, there is no + * register for buffer size configuration + */ + desc->datalen = cpu_to_le16((u16)bi->size); + desc->retval = 0; + desc->cookie_high = 0; + desc->cookie_low = 0; + desc->params.external.addr_high = + cpu_to_le32(upper_32_bits(bi->pa)); + desc->params.external.addr_low = + cpu_to_le32(lower_32_bits(bi->pa)); + desc->params.external.param0 = 0; + desc->params.external.param1 = 0; + } + +alloc_arq_bufs: + return ret_code; + +unwind_alloc_arq_bufs: + /* don't try to free the one that failed... */ + i--; + for (; i >= 0; i--) + iavf_free_dma_mem(hw, &hw->aq.arq.r.arq_bi[i]); + iavf_free_virt_mem(hw, &hw->aq.arq.dma_head); + + return ret_code; +} + +/** + * i40e_alloc_asq_bufs - Allocate empty buffer structs for the send queue + * @hw: pointer to the hardware structure + **/ +static iavf_status i40e_alloc_asq_bufs(struct iavf_hw *hw) +{ + struct iavf_dma_mem *bi; + iavf_status ret_code; + int i; + + /* No mapped memory needed yet, just the buffer info structures */ + ret_code = iavf_allocate_virt_mem(hw, &hw->aq.asq.dma_head, + (hw->aq.num_asq_entries * + sizeof(struct iavf_dma_mem))); + if (ret_code) + goto alloc_asq_bufs; + hw->aq.asq.r.asq_bi = (struct iavf_dma_mem *)hw->aq.asq.dma_head.va; + + /* allocate the mapped buffers */ + for (i = 0; i < hw->aq.num_asq_entries; i++) { + bi = &hw->aq.asq.r.asq_bi[i]; + ret_code = iavf_allocate_dma_mem(hw, bi, + i40e_mem_asq_buf, + hw->aq.asq_buf_size, + IAVF_ADMINQ_DESC_ALIGNMENT); + if (ret_code) + goto unwind_alloc_asq_bufs; + } +alloc_asq_bufs: + return ret_code; + +unwind_alloc_asq_bufs: + /* don't try to free the one that failed... */ + i--; + for (; i >= 0; i--) + iavf_free_dma_mem(hw, &hw->aq.asq.r.asq_bi[i]); + iavf_free_virt_mem(hw, &hw->aq.asq.dma_head); + + return ret_code; +} + +/** + * i40e_free_arq_bufs - Free receive queue buffer info elements + * @hw: pointer to the hardware structure + **/ +static void i40e_free_arq_bufs(struct iavf_hw *hw) +{ + int i; + + /* free descriptors */ + for (i = 0; i < hw->aq.num_arq_entries; i++) + iavf_free_dma_mem(hw, &hw->aq.arq.r.arq_bi[i]); + + /* free the descriptor memory */ + iavf_free_dma_mem(hw, &hw->aq.arq.desc_buf); + + /* free the dma header */ + iavf_free_virt_mem(hw, &hw->aq.arq.dma_head); +} + +/** + * i40e_free_asq_bufs - Free send queue buffer info elements + * @hw: pointer to the hardware structure + **/ +static void i40e_free_asq_bufs(struct iavf_hw *hw) +{ + int i; + + /* only unmap if the address is non-NULL */ + for (i = 0; i < hw->aq.num_asq_entries; i++) + if (hw->aq.asq.r.asq_bi[i].pa) + iavf_free_dma_mem(hw, &hw->aq.asq.r.asq_bi[i]); + + /* free the buffer info list */ + iavf_free_virt_mem(hw, &hw->aq.asq.cmd_buf); + + /* free the descriptor memory */ + iavf_free_dma_mem(hw, &hw->aq.asq.desc_buf); + + /* free the dma header */ + iavf_free_virt_mem(hw, &hw->aq.asq.dma_head); +} + +/** + * i40e_config_asq_regs - configure ASQ registers + * @hw: pointer to the hardware structure + * + * Configure base address and length registers for the transmit queue + **/ +static iavf_status i40e_config_asq_regs(struct iavf_hw *hw) +{ + iavf_status ret_code = 0; + u32 reg = 0; + + /* Clear Head and Tail */ + wr32(hw, hw->aq.asq.head, 0); + wr32(hw, hw->aq.asq.tail, 0); + + /* set starting point */ + wr32(hw, hw->aq.asq.len, (hw->aq.num_asq_entries | + IAVF_VF_ATQLEN1_ATQENABLE_MASK)); + wr32(hw, hw->aq.asq.bal, lower_32_bits(hw->aq.asq.desc_buf.pa)); + wr32(hw, hw->aq.asq.bah, upper_32_bits(hw->aq.asq.desc_buf.pa)); + + /* Check one register to verify that config was applied */ + reg = rd32(hw, hw->aq.asq.bal); + if (reg != lower_32_bits(hw->aq.asq.desc_buf.pa)) + ret_code = I40E_ERR_ADMIN_QUEUE_ERROR; + + return ret_code; +} + +/** + * i40e_config_arq_regs - ARQ register configuration + * @hw: pointer to the hardware structure + * + * Configure base address and length registers for the receive (event queue) + **/ +static iavf_status i40e_config_arq_regs(struct iavf_hw *hw) +{ + iavf_status ret_code = 0; + u32 reg = 0; + + /* Clear Head and Tail */ + wr32(hw, hw->aq.arq.head, 0); + wr32(hw, hw->aq.arq.tail, 0); + + /* set starting point */ + wr32(hw, hw->aq.arq.len, (hw->aq.num_arq_entries | + IAVF_VF_ARQLEN1_ARQENABLE_MASK)); + wr32(hw, hw->aq.arq.bal, lower_32_bits(hw->aq.arq.desc_buf.pa)); + wr32(hw, hw->aq.arq.bah, upper_32_bits(hw->aq.arq.desc_buf.pa)); + + /* Update tail in the HW to post pre-allocated buffers */ + wr32(hw, hw->aq.arq.tail, hw->aq.num_arq_entries - 1); + + /* Check one register to verify that config was applied */ + reg = rd32(hw, hw->aq.arq.bal); + if (reg != lower_32_bits(hw->aq.arq.desc_buf.pa)) + ret_code = I40E_ERR_ADMIN_QUEUE_ERROR; + + return ret_code; +} + +/** + * i40e_init_asq - main initialization routine for ASQ + * @hw: pointer to the hardware structure + * + * This is the main initialization routine for the Admin Send Queue + * Prior to calling this function, drivers *MUST* set the following fields + * in the hw->aq structure: + * - hw->aq.num_asq_entries + * - hw->aq.arq_buf_size + * + * Do *NOT* hold the lock when calling this as the memory allocation routines + * called are not going to be atomic context safe + **/ +static iavf_status i40e_init_asq(struct iavf_hw *hw) +{ + iavf_status ret_code = 0; + + if (hw->aq.asq.count > 0) { + /* queue already initialized */ + ret_code = I40E_ERR_NOT_READY; + goto init_adminq_exit; + } + + /* verify input for valid configuration */ + if ((hw->aq.num_asq_entries == 0) || + (hw->aq.asq_buf_size == 0)) { + ret_code = I40E_ERR_CONFIG; + goto init_adminq_exit; + } + + hw->aq.asq.next_to_use = 0; + hw->aq.asq.next_to_clean = 0; + + /* allocate the ring memory */ + ret_code = i40e_alloc_adminq_asq_ring(hw); + if (ret_code) + goto init_adminq_exit; + + /* allocate buffers in the rings */ + ret_code = i40e_alloc_asq_bufs(hw); + if (ret_code) + goto init_adminq_free_rings; + + /* initialize base registers */ + ret_code = i40e_config_asq_regs(hw); + if (ret_code) + goto init_adminq_free_rings; + + /* success! */ + hw->aq.asq.count = hw->aq.num_asq_entries; + goto init_adminq_exit; + +init_adminq_free_rings: + i40e_free_adminq_asq(hw); + +init_adminq_exit: + return ret_code; +} + +/** + * i40e_init_arq - initialize ARQ + * @hw: pointer to the hardware structure + * + * The main initialization routine for the Admin Receive (Event) Queue. + * Prior to calling this function, drivers *MUST* set the following fields + * in the hw->aq structure: + * - hw->aq.num_asq_entries + * - hw->aq.arq_buf_size + * + * Do *NOT* hold the lock when calling this as the memory allocation routines + * called are not going to be atomic context safe + **/ +static iavf_status i40e_init_arq(struct iavf_hw *hw) +{ + iavf_status ret_code = 0; + + if (hw->aq.arq.count > 0) { + /* queue already initialized */ + ret_code = I40E_ERR_NOT_READY; + goto init_adminq_exit; + } + + /* verify input for valid configuration */ + if ((hw->aq.num_arq_entries == 0) || + (hw->aq.arq_buf_size == 0)) { + ret_code = I40E_ERR_CONFIG; + goto init_adminq_exit; + } + + hw->aq.arq.next_to_use = 0; + hw->aq.arq.next_to_clean = 0; + + /* allocate the ring memory */ + ret_code = i40e_alloc_adminq_arq_ring(hw); + if (ret_code) + goto init_adminq_exit; + + /* allocate buffers in the rings */ + ret_code = i40e_alloc_arq_bufs(hw); + if (ret_code) + goto init_adminq_free_rings; + + /* initialize base registers */ + ret_code = i40e_config_arq_regs(hw); + if (ret_code) + goto init_adminq_free_rings; + + /* success! */ + hw->aq.arq.count = hw->aq.num_arq_entries; + goto init_adminq_exit; + +init_adminq_free_rings: + i40e_free_adminq_arq(hw); + +init_adminq_exit: + return ret_code; +} + +/** + * i40e_shutdown_asq - shutdown the ASQ + * @hw: pointer to the hardware structure + * + * The main shutdown routine for the Admin Send Queue + **/ +static iavf_status i40e_shutdown_asq(struct iavf_hw *hw) +{ + iavf_status ret_code = 0; + + mutex_lock(&hw->aq.asq_mutex); + + if (hw->aq.asq.count == 0) { + ret_code = I40E_ERR_NOT_READY; + goto shutdown_asq_out; + } + + /* Stop firmware AdminQ processing */ + wr32(hw, hw->aq.asq.head, 0); + wr32(hw, hw->aq.asq.tail, 0); + wr32(hw, hw->aq.asq.len, 0); + wr32(hw, hw->aq.asq.bal, 0); + wr32(hw, hw->aq.asq.bah, 0); + + hw->aq.asq.count = 0; /* to indicate uninitialized queue */ + + /* free ring buffers */ + i40e_free_asq_bufs(hw); + +shutdown_asq_out: + mutex_unlock(&hw->aq.asq_mutex); + return ret_code; +} + +/** + * i40e_shutdown_arq - shutdown ARQ + * @hw: pointer to the hardware structure + * + * The main shutdown routine for the Admin Receive Queue + **/ +static iavf_status i40e_shutdown_arq(struct iavf_hw *hw) +{ + iavf_status ret_code = 0; + + mutex_lock(&hw->aq.arq_mutex); + + if (hw->aq.arq.count == 0) { + ret_code = I40E_ERR_NOT_READY; + goto shutdown_arq_out; + } + + /* Stop firmware AdminQ processing */ + wr32(hw, hw->aq.arq.head, 0); + wr32(hw, hw->aq.arq.tail, 0); + wr32(hw, hw->aq.arq.len, 0); + wr32(hw, hw->aq.arq.bal, 0); + wr32(hw, hw->aq.arq.bah, 0); + + hw->aq.arq.count = 0; /* to indicate uninitialized queue */ + + /* free ring buffers */ + i40e_free_arq_bufs(hw); + +shutdown_arq_out: + mutex_unlock(&hw->aq.arq_mutex); + return ret_code; +} + +/** + * iavf_init_adminq - main initialization routine for Admin Queue + * @hw: pointer to the hardware structure + * + * Prior to calling this function, drivers *MUST* set the following fields + * in the hw->aq structure: + * - hw->aq.num_asq_entries + * - hw->aq.num_arq_entries + * - hw->aq.arq_buf_size + * - hw->aq.asq_buf_size + **/ +iavf_status iavf_init_adminq(struct iavf_hw *hw) +{ + iavf_status ret_code; + + /* verify input for valid configuration */ + if ((hw->aq.num_arq_entries == 0) || + (hw->aq.num_asq_entries == 0) || + (hw->aq.arq_buf_size == 0) || + (hw->aq.asq_buf_size == 0)) { + ret_code = I40E_ERR_CONFIG; + goto init_adminq_exit; + } + + /* Set up register offsets */ + i40e_adminq_init_regs(hw); + + /* setup ASQ command write back timeout */ + hw->aq.asq_cmd_timeout = I40E_ASQ_CMD_TIMEOUT; + + /* allocate the ASQ */ + ret_code = i40e_init_asq(hw); + if (ret_code) + goto init_adminq_destroy_locks; + + /* allocate the ARQ */ + ret_code = i40e_init_arq(hw); + if (ret_code) + goto init_adminq_free_asq; + + /* success! */ + goto init_adminq_exit; + +init_adminq_free_asq: + i40e_shutdown_asq(hw); +init_adminq_destroy_locks: + +init_adminq_exit: + return ret_code; +} + +/** + * iavf_shutdown_adminq - shutdown routine for the Admin Queue + * @hw: pointer to the hardware structure + **/ +iavf_status iavf_shutdown_adminq(struct iavf_hw *hw) +{ + iavf_status ret_code = 0; + + if (iavf_check_asq_alive(hw)) + iavf_aq_queue_shutdown(hw, true); + + i40e_shutdown_asq(hw); + i40e_shutdown_arq(hw); + + return ret_code; +} + +/** + * i40e_clean_asq - cleans Admin send queue + * @hw: pointer to the hardware structure + * + * returns the number of free desc + **/ +static u16 i40e_clean_asq(struct iavf_hw *hw) +{ + struct iavf_adminq_ring *asq = &hw->aq.asq; + struct i40e_asq_cmd_details *details; + u16 ntc = asq->next_to_clean; + struct i40e_aq_desc desc_cb; + struct i40e_aq_desc *desc; + + desc = IAVF_ADMINQ_DESC(*asq, ntc); + details = I40E_ADMINQ_DETAILS(*asq, ntc); + while (rd32(hw, hw->aq.asq.head) != ntc) { + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, + "ntc %d head %d.\n", ntc, rd32(hw, hw->aq.asq.head)); + + if (details->callback) { + I40E_ADMINQ_CALLBACK cb_func = + (I40E_ADMINQ_CALLBACK)details->callback; + desc_cb = *desc; + cb_func(hw, &desc_cb); + } + memset((void *)desc, 0, sizeof(struct i40e_aq_desc)); + memset((void *)details, 0, + sizeof(struct i40e_asq_cmd_details)); + ntc++; + if (ntc == asq->count) + ntc = 0; + desc = IAVF_ADMINQ_DESC(*asq, ntc); + details = I40E_ADMINQ_DETAILS(*asq, ntc); + } + + asq->next_to_clean = ntc; + + return IAVF_DESC_UNUSED(asq); +} + +/** + * iavf_asq_done - check if FW has processed the Admin Send Queue + * @hw: pointer to the hw struct + * + * Returns true if the firmware has processed all descriptors on the + * admin send queue. Returns false if there are still requests pending. + **/ +bool iavf_asq_done(struct iavf_hw *hw) +{ + /* AQ designers suggest use of head for better + * timing reliability than DD bit + */ + return rd32(hw, hw->aq.asq.head) == hw->aq.asq.next_to_use; +} + +/** + * iavf_asq_send_command - send command to Admin Queue + * @hw: pointer to the hw struct + * @desc: prefilled descriptor describing the command (non DMA mem) + * @buff: buffer to use for indirect commands + * @buff_size: size of buffer for indirect commands + * @cmd_details: pointer to command details structure + * + * This is the main send command driver routine for the Admin Queue send + * queue. It runs the queue, cleans the queue, etc + **/ +iavf_status iavf_asq_send_command(struct iavf_hw *hw, struct i40e_aq_desc *desc, + void *buff, /* can be NULL */ + u16 buff_size, + struct i40e_asq_cmd_details *cmd_details) +{ + struct iavf_dma_mem *dma_buff = NULL; + struct i40e_asq_cmd_details *details; + struct i40e_aq_desc *desc_on_ring; + bool cmd_completed = false; + iavf_status status = 0; + u16 retval = 0; + u32 val = 0; + + mutex_lock(&hw->aq.asq_mutex); + + if (hw->aq.asq.count == 0) { + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, + "AQTX: Admin queue not initialized.\n"); + status = I40E_ERR_QUEUE_EMPTY; + goto asq_send_command_error; + } + + hw->aq.asq_last_status = I40E_AQ_RC_OK; + + val = rd32(hw, hw->aq.asq.head); + if (val >= hw->aq.num_asq_entries) { + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, + "AQTX: head overrun at %d\n", val); + status = I40E_ERR_QUEUE_EMPTY; + goto asq_send_command_error; + } + + details = I40E_ADMINQ_DETAILS(hw->aq.asq, hw->aq.asq.next_to_use); + if (cmd_details) { + *details = *cmd_details; + + /* If the cmd_details are defined copy the cookie. The + * cpu_to_le32 is not needed here because the data is ignored + * by the FW, only used by the driver + */ + if (details->cookie) { + desc->cookie_high = + cpu_to_le32(upper_32_bits(details->cookie)); + desc->cookie_low = + cpu_to_le32(lower_32_bits(details->cookie)); + } + } else { + memset(details, 0, sizeof(struct i40e_asq_cmd_details)); + } + + /* clear requested flags and then set additional flags if defined */ + desc->flags &= ~cpu_to_le16(details->flags_dis); + desc->flags |= cpu_to_le16(details->flags_ena); + + if (buff_size > hw->aq.asq_buf_size) { + iavf_debug(hw, + IAVF_DEBUG_AQ_MESSAGE, + "AQTX: Invalid buffer size: %d.\n", + buff_size); + status = I40E_ERR_INVALID_SIZE; + goto asq_send_command_error; + } + + if (details->postpone && !details->async) { + iavf_debug(hw, + IAVF_DEBUG_AQ_MESSAGE, + "AQTX: Async flag not set along with postpone flag"); + status = I40E_ERR_PARAM; + goto asq_send_command_error; + } + + /* call clean and check queue available function to reclaim the + * descriptors that were processed by FW, the function returns the + * number of desc available + */ + /* the clean function called here could be called in a separate thread + * in case of asynchronous completions + */ + if (i40e_clean_asq(hw) == 0) { + iavf_debug(hw, + IAVF_DEBUG_AQ_MESSAGE, + "AQTX: Error queue is full.\n"); + status = I40E_ERR_ADMIN_QUEUE_FULL; + goto asq_send_command_error; + } + + /* initialize the temp desc pointer with the right desc */ + desc_on_ring = IAVF_ADMINQ_DESC(hw->aq.asq, hw->aq.asq.next_to_use); + + /* if the desc is available copy the temp desc to the right place */ + *desc_on_ring = *desc; + + /* if buff is not NULL assume indirect command */ + if (buff) { + dma_buff = &hw->aq.asq.r.asq_bi[hw->aq.asq.next_to_use]; + /* copy the user buff into the respective DMA buff */ + memcpy(dma_buff->va, buff, buff_size); + desc_on_ring->datalen = cpu_to_le16(buff_size); + + /* Update the address values in the desc with the pa value + * for respective buffer + */ + desc_on_ring->params.external.addr_high = + cpu_to_le32(upper_32_bits(dma_buff->pa)); + desc_on_ring->params.external.addr_low = + cpu_to_le32(lower_32_bits(dma_buff->pa)); + } + + /* bump the tail */ + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, "AQTX: desc and buffer:\n"); + iavf_debug_aq(hw, IAVF_DEBUG_AQ_COMMAND, (void *)desc_on_ring, + buff, buff_size); + (hw->aq.asq.next_to_use)++; + if (hw->aq.asq.next_to_use == hw->aq.asq.count) + hw->aq.asq.next_to_use = 0; + if (!details->postpone) + wr32(hw, hw->aq.asq.tail, hw->aq.asq.next_to_use); + + /* if cmd_details are not defined or async flag is not set, + * we need to wait for desc write back + */ + if (!details->async && !details->postpone) { + u32 total_delay = 0; + + do { + /* AQ designers suggest use of head for better + * timing reliability than DD bit + */ + if (iavf_asq_done(hw)) + break; + udelay(50); + total_delay += 50; + } while (total_delay < hw->aq.asq_cmd_timeout); + } + + /* if ready, copy the desc back to temp */ + if (iavf_asq_done(hw)) { + *desc = *desc_on_ring; + if (buff) + memcpy(buff, dma_buff->va, buff_size); + retval = le16_to_cpu(desc->retval); + if (retval != 0) { + iavf_debug(hw, + IAVF_DEBUG_AQ_MESSAGE, + "AQTX: Command completed with error 0x%X.\n", + retval); + + /* strip off FW internal code */ + retval &= 0xff; + } + cmd_completed = true; + if ((enum i40e_admin_queue_err)retval == I40E_AQ_RC_OK) + status = 0; + else if ((enum i40e_admin_queue_err)retval == I40E_AQ_RC_EBUSY) + status = I40E_ERR_NOT_READY; + else + status = I40E_ERR_ADMIN_QUEUE_ERROR; + hw->aq.asq_last_status = (enum i40e_admin_queue_err)retval; + } + + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, + "AQTX: desc and buffer writeback:\n"); + iavf_debug_aq(hw, IAVF_DEBUG_AQ_COMMAND, (void *)desc, buff, buff_size); + + /* save writeback aq if requested */ + if (details->wb_desc) + *details->wb_desc = *desc_on_ring; + + /* update the error if time out occurred */ + if ((!cmd_completed) && + (!details->async && !details->postpone)) { + if (rd32(hw, hw->aq.asq.len) & IAVF_VF_ATQLEN1_ATQCRIT_MASK) { + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, + "AQTX: AQ Critical error.\n"); + status = I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR; + } else { + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, + "AQTX: Writeback timeout.\n"); + status = I40E_ERR_ADMIN_QUEUE_TIMEOUT; + } + } + +asq_send_command_error: + mutex_unlock(&hw->aq.asq_mutex); + return status; +} + +/** + * iavf_fill_default_direct_cmd_desc - AQ descriptor helper function + * @desc: pointer to the temp descriptor (non DMA mem) + * @opcode: the opcode can be used to decide which flags to turn off or on + * + * Fill the desc with default values + **/ +void iavf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, u16 opcode) +{ + /* zero out the desc */ + memset((void *)desc, 0, sizeof(struct i40e_aq_desc)); + desc->opcode = cpu_to_le16(opcode); + desc->flags = cpu_to_le16(I40E_AQ_FLAG_SI); +} + +/** + * iavf_clean_arq_element + * @hw: pointer to the hw struct + * @e: event info from the receive descriptor, includes any buffers + * @pending: number of events that could be left to process + * + * This function cleans one Admin Receive Queue element and returns + * the contents through e. It can also return how many events are + * left to process through 'pending' + **/ +iavf_status iavf_clean_arq_element(struct iavf_hw *hw, + struct i40e_arq_event_info *e, + u16 *pending) +{ + u16 ntc = hw->aq.arq.next_to_clean; + struct i40e_aq_desc *desc; + iavf_status ret_code = 0; + struct iavf_dma_mem *bi; + u16 desc_idx; + u16 datalen; + 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); + + if (hw->aq.arq.count == 0) { + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, + "AQRX: Admin queue not initialized.\n"); + ret_code = I40E_ERR_QUEUE_EMPTY; + goto clean_arq_element_err; + } + + /* set next_to_use to head */ + ntu = rd32(hw, hw->aq.arq.head) & IAVF_VF_ARQH1_ARQH_MASK; + if (ntu == ntc) { + /* nothing to do - shouldn't need to update ring's values */ + ret_code = I40E_ERR_ADMIN_QUEUE_NO_WORK; + goto clean_arq_element_out; + } + + /* now clean the next descriptor */ + desc = IAVF_ADMINQ_DESC(hw->aq.arq, ntc); + desc_idx = ntc; + + hw->aq.arq_last_status = + (enum i40e_admin_queue_err)le16_to_cpu(desc->retval); + flags = le16_to_cpu(desc->flags); + if (flags & I40E_AQ_FLAG_ERR) { + ret_code = I40E_ERR_ADMIN_QUEUE_ERROR; + iavf_debug(hw, + IAVF_DEBUG_AQ_MESSAGE, + "AQRX: Event received with error 0x%X.\n", + hw->aq.arq_last_status); + } + + e->desc = *desc; + datalen = le16_to_cpu(desc->datalen); + e->msg_len = min(datalen, e->buf_len); + if (e->msg_buf && (e->msg_len != 0)) + memcpy(e->msg_buf, hw->aq.arq.r.arq_bi[desc_idx].va, + e->msg_len); + + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, "AQRX: desc and buffer:\n"); + iavf_debug_aq(hw, IAVF_DEBUG_AQ_COMMAND, (void *)desc, e->msg_buf, + hw->aq.arq_buf_size); + + /* Restore the original datalen and buffer address in the desc, + * FW updates datalen to indicate the event message + * size + */ + bi = &hw->aq.arq.r.arq_bi[ntc]; + memset((void *)desc, 0, sizeof(struct i40e_aq_desc)); + + desc->flags = cpu_to_le16(I40E_AQ_FLAG_BUF); + if (hw->aq.arq_buf_size > I40E_AQ_LARGE_BUF) + desc->flags |= cpu_to_le16(I40E_AQ_FLAG_LB); + desc->datalen = cpu_to_le16((u16)bi->size); + desc->params.external.addr_high = cpu_to_le32(upper_32_bits(bi->pa)); + desc->params.external.addr_low = cpu_to_le32(lower_32_bits(bi->pa)); + + /* set tail = the last cleaned desc index. */ + wr32(hw, hw->aq.arq.tail, ntc); + /* ntc is updated to tail + 1 */ + ntc++; + if (ntc == hw->aq.num_arq_entries) + ntc = 0; + hw->aq.arq.next_to_clean = ntc; + hw->aq.arq.next_to_use = ntu; + +clean_arq_element_out: + /* Set pending if needed, unlock and return */ + if (pending) + *pending = (ntc > ntu ? hw->aq.arq.count : 0) + (ntu - ntc); + +clean_arq_element_err: + mutex_unlock(&hw->aq.arq_mutex); + + return ret_code; +} diff --git a/drivers/net/ethernet/intel/iavf/i40e_adminq.h b/drivers/net/ethernet/intel/iavf/i40e_adminq.h new file mode 100644 index 000000000000..ee983889eab0 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/i40e_adminq.h @@ -0,0 +1,135 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _IAVF_ADMINQ_H_ +#define _IAVF_ADMINQ_H_ + +#include "iavf_osdep.h" +#include "iavf_status.h" +#include "i40e_adminq_cmd.h" + +#define IAVF_ADMINQ_DESC(R, i) \ + (&(((struct i40e_aq_desc *)((R).desc_buf.va))[i])) + +#define IAVF_ADMINQ_DESC_ALIGNMENT 4096 + +struct iavf_adminq_ring { + struct iavf_virt_mem dma_head; /* space for dma structures */ + struct iavf_dma_mem desc_buf; /* descriptor ring memory */ + struct iavf_virt_mem cmd_buf; /* command buffer memory */ + + union { + struct iavf_dma_mem *asq_bi; + struct iavf_dma_mem *arq_bi; + } r; + + u16 count; /* Number of descriptors */ + u16 rx_buf_len; /* Admin Receive Queue buffer length */ + + /* used for interrupt processing */ + u16 next_to_use; + u16 next_to_clean; + + /* used for queue tracking */ + u32 head; + u32 tail; + u32 len; + u32 bah; + u32 bal; +}; + +/* ASQ transaction details */ +struct i40e_asq_cmd_details { + void *callback; /* cast from type I40E_ADMINQ_CALLBACK */ + u64 cookie; + u16 flags_ena; + u16 flags_dis; + bool async; + bool postpone; + struct i40e_aq_desc *wb_desc; +}; + +#define I40E_ADMINQ_DETAILS(R, i) \ + (&(((struct i40e_asq_cmd_details *)((R).cmd_buf.va))[i])) + +/* ARQ event information */ +struct i40e_arq_event_info { + struct i40e_aq_desc desc; + u16 msg_len; + u16 buf_len; + u8 *msg_buf; +}; + +/* Admin Queue information */ +struct iavf_adminq_info { + struct iavf_adminq_ring arq; /* receive queue */ + struct iavf_adminq_ring asq; /* send queue */ + u32 asq_cmd_timeout; /* send queue cmd write back timeout*/ + u16 num_arq_entries; /* receive queue depth */ + u16 num_asq_entries; /* send queue depth */ + u16 arq_buf_size; /* receive queue buffer size */ + u16 asq_buf_size; /* send queue buffer size */ + u16 fw_maj_ver; /* firmware major version */ + u16 fw_min_ver; /* firmware minor version */ + u32 fw_build; /* firmware build number */ + u16 api_maj_ver; /* api major version */ + u16 api_min_ver; /* api minor version */ + + struct mutex asq_mutex; /* Send queue lock */ + struct mutex arq_mutex; /* Receive queue lock */ + + /* last status values on send and receive queues */ + enum i40e_admin_queue_err asq_last_status; + enum i40e_admin_queue_err arq_last_status; +}; + +/** + * i40e_aq_rc_to_posix - convert errors to user-land codes + * aq_ret: AdminQ handler error code can override aq_rc + * aq_rc: AdminQ firmware error code to convert + **/ +static inline int i40e_aq_rc_to_posix(int aq_ret, int aq_rc) +{ + int aq_to_posix[] = { + 0, /* I40E_AQ_RC_OK */ + -EPERM, /* I40E_AQ_RC_EPERM */ + -ENOENT, /* I40E_AQ_RC_ENOENT */ + -ESRCH, /* I40E_AQ_RC_ESRCH */ + -EINTR, /* I40E_AQ_RC_EINTR */ + -EIO, /* I40E_AQ_RC_EIO */ + -ENXIO, /* I40E_AQ_RC_ENXIO */ + -E2BIG, /* I40E_AQ_RC_E2BIG */ + -EAGAIN, /* I40E_AQ_RC_EAGAIN */ + -ENOMEM, /* I40E_AQ_RC_ENOMEM */ + -EACCES, /* I40E_AQ_RC_EACCES */ + -EFAULT, /* I40E_AQ_RC_EFAULT */ + -EBUSY, /* I40E_AQ_RC_EBUSY */ + -EEXIST, /* I40E_AQ_RC_EEXIST */ + -EINVAL, /* I40E_AQ_RC_EINVAL */ + -ENOTTY, /* I40E_AQ_RC_ENOTTY */ + -ENOSPC, /* I40E_AQ_RC_ENOSPC */ + -ENOSYS, /* I40E_AQ_RC_ENOSYS */ + -ERANGE, /* I40E_AQ_RC_ERANGE */ + -EPIPE, /* I40E_AQ_RC_EFLUSHED */ + -ESPIPE, /* I40E_AQ_RC_BAD_ADDR */ + -EROFS, /* I40E_AQ_RC_EMODE */ + -EFBIG, /* I40E_AQ_RC_EFBIG */ + }; + + /* aq_rc is invalid if AQ timed out */ + if (aq_ret == I40E_ERR_ADMIN_QUEUE_TIMEOUT) + return -EAGAIN; + + if (!((u32)aq_rc < (sizeof(aq_to_posix) / sizeof((aq_to_posix)[0])))) + return -ERANGE; + + return aq_to_posix[aq_rc]; +} + +/* general information */ +#define I40E_AQ_LARGE_BUF 512 +#define I40E_ASQ_CMD_TIMEOUT 250000 /* usecs */ + +void iavf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, u16 opcode); + +#endif /* _IAVF_ADMINQ_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/iavf/i40e_adminq_cmd.h new file mode 100644 index 000000000000..af4f94a6541e --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/i40e_adminq_cmd.h @@ -0,0 +1,530 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _I40E_ADMINQ_CMD_H_ +#define _I40E_ADMINQ_CMD_H_ + +/* This header file defines the i40e Admin Queue commands and is shared between + * i40e Firmware and Software. Do not change the names in this file to IAVF + * because this file should be diff-able against the i40e version, even + * though many parts have been removed in this VF version. + * + * This file needs to comply with the Linux Kernel coding style. + */ + +#define I40E_FW_API_VERSION_MAJOR 0x0001 +#define I40E_FW_API_VERSION_MINOR_X722 0x0005 +#define I40E_FW_API_VERSION_MINOR_X710 0x0007 + +#define I40E_FW_MINOR_VERSION(_h) ((_h)->mac.type == I40E_MAC_XL710 ? \ + I40E_FW_API_VERSION_MINOR_X710 : \ + I40E_FW_API_VERSION_MINOR_X722) + +/* API version 1.7 implements additional link and PHY-specific APIs */ +#define I40E_MINOR_VER_GET_LINK_INFO_XL710 0x0007 + +struct i40e_aq_desc { + __le16 flags; + __le16 opcode; + __le16 datalen; + __le16 retval; + __le32 cookie_high; + __le32 cookie_low; + union { + struct { + __le32 param0; + __le32 param1; + __le32 param2; + __le32 param3; + } internal; + struct { + __le32 param0; + __le32 param1; + __le32 addr_high; + __le32 addr_low; + } external; + u8 raw[16]; + } params; +}; + +/* Flags sub-structure + * |0 |1 |2 |3 |4 |5 |6 |7 |8 |9 |10 |11 |12 |13 |14 |15 | + * |DD |CMP|ERR|VFE| * * RESERVED * * |LB |RD |VFC|BUF|SI |EI |FE | + */ + +/* command flags and offsets*/ +#define I40E_AQ_FLAG_DD_SHIFT 0 +#define I40E_AQ_FLAG_CMP_SHIFT 1 +#define I40E_AQ_FLAG_ERR_SHIFT 2 +#define I40E_AQ_FLAG_VFE_SHIFT 3 +#define I40E_AQ_FLAG_LB_SHIFT 9 +#define I40E_AQ_FLAG_RD_SHIFT 10 +#define I40E_AQ_FLAG_VFC_SHIFT 11 +#define I40E_AQ_FLAG_BUF_SHIFT 12 +#define I40E_AQ_FLAG_SI_SHIFT 13 +#define I40E_AQ_FLAG_EI_SHIFT 14 +#define I40E_AQ_FLAG_FE_SHIFT 15 + +#define I40E_AQ_FLAG_DD BIT(I40E_AQ_FLAG_DD_SHIFT) /* 0x1 */ +#define I40E_AQ_FLAG_CMP BIT(I40E_AQ_FLAG_CMP_SHIFT) /* 0x2 */ +#define I40E_AQ_FLAG_ERR BIT(I40E_AQ_FLAG_ERR_SHIFT) /* 0x4 */ +#define I40E_AQ_FLAG_VFE BIT(I40E_AQ_FLAG_VFE_SHIFT) /* 0x8 */ +#define I40E_AQ_FLAG_LB BIT(I40E_AQ_FLAG_LB_SHIFT) /* 0x200 */ +#define I40E_AQ_FLAG_RD BIT(I40E_AQ_FLAG_RD_SHIFT) /* 0x400 */ +#define I40E_AQ_FLAG_VFC BIT(I40E_AQ_FLAG_VFC_SHIFT) /* 0x800 */ +#define I40E_AQ_FLAG_BUF BIT(I40E_AQ_FLAG_BUF_SHIFT) /* 0x1000 */ +#define I40E_AQ_FLAG_SI BIT(I40E_AQ_FLAG_SI_SHIFT) /* 0x2000 */ +#define I40E_AQ_FLAG_EI BIT(I40E_AQ_FLAG_EI_SHIFT) /* 0x4000 */ +#define I40E_AQ_FLAG_FE BIT(I40E_AQ_FLAG_FE_SHIFT) /* 0x8000 */ + +/* error codes */ +enum i40e_admin_queue_err { + I40E_AQ_RC_OK = 0, /* success */ + I40E_AQ_RC_EPERM = 1, /* Operation not permitted */ + I40E_AQ_RC_ENOENT = 2, /* No such element */ + I40E_AQ_RC_ESRCH = 3, /* Bad opcode */ + I40E_AQ_RC_EINTR = 4, /* operation interrupted */ + I40E_AQ_RC_EIO = 5, /* I/O error */ + I40E_AQ_RC_ENXIO = 6, /* No such resource */ + I40E_AQ_RC_E2BIG = 7, /* Arg too long */ + I40E_AQ_RC_EAGAIN = 8, /* Try again */ + I40E_AQ_RC_ENOMEM = 9, /* Out of memory */ + I40E_AQ_RC_EACCES = 10, /* Permission denied */ + I40E_AQ_RC_EFAULT = 11, /* Bad address */ + I40E_AQ_RC_EBUSY = 12, /* Device or resource busy */ + I40E_AQ_RC_EEXIST = 13, /* object already exists */ + I40E_AQ_RC_EINVAL = 14, /* Invalid argument */ + I40E_AQ_RC_ENOTTY = 15, /* Not a typewriter */ + I40E_AQ_RC_ENOSPC = 16, /* No space left or alloc failure */ + I40E_AQ_RC_ENOSYS = 17, /* Function not implemented */ + I40E_AQ_RC_ERANGE = 18, /* Parameter out of range */ + I40E_AQ_RC_EFLUSHED = 19, /* Cmd flushed due to prev cmd error */ + I40E_AQ_RC_BAD_ADDR = 20, /* Descriptor contains a bad pointer */ + I40E_AQ_RC_EMODE = 21, /* Op not allowed in current dev mode */ + I40E_AQ_RC_EFBIG = 22, /* File too large */ +}; + +/* Admin Queue command opcodes */ +enum i40e_admin_queue_opc { + /* aq commands */ + i40e_aqc_opc_get_version = 0x0001, + i40e_aqc_opc_driver_version = 0x0002, + i40e_aqc_opc_queue_shutdown = 0x0003, + i40e_aqc_opc_set_pf_context = 0x0004, + + /* resource ownership */ + i40e_aqc_opc_request_resource = 0x0008, + i40e_aqc_opc_release_resource = 0x0009, + + i40e_aqc_opc_list_func_capabilities = 0x000A, + i40e_aqc_opc_list_dev_capabilities = 0x000B, + + /* Proxy commands */ + i40e_aqc_opc_set_proxy_config = 0x0104, + i40e_aqc_opc_set_ns_proxy_table_entry = 0x0105, + + /* LAA */ + i40e_aqc_opc_mac_address_read = 0x0107, + i40e_aqc_opc_mac_address_write = 0x0108, + + /* PXE */ + i40e_aqc_opc_clear_pxe_mode = 0x0110, + + /* WoL commands */ + i40e_aqc_opc_set_wol_filter = 0x0120, + i40e_aqc_opc_get_wake_reason = 0x0121, + + /* internal switch commands */ + i40e_aqc_opc_get_switch_config = 0x0200, + i40e_aqc_opc_add_statistics = 0x0201, + 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, + i40e_aqc_opc_get_vsi_parameters = 0x0212, + + i40e_aqc_opc_add_pv = 0x0220, + i40e_aqc_opc_update_pv_parameters = 0x0221, + i40e_aqc_opc_get_pv_parameters = 0x0222, + + i40e_aqc_opc_add_veb = 0x0230, + i40e_aqc_opc_update_veb_parameters = 0x0231, + i40e_aqc_opc_get_veb_parameters = 0x0232, + + i40e_aqc_opc_delete_element = 0x0243, + + i40e_aqc_opc_add_macvlan = 0x0250, + i40e_aqc_opc_remove_macvlan = 0x0251, + i40e_aqc_opc_add_vlan = 0x0252, + i40e_aqc_opc_remove_vlan = 0x0253, + i40e_aqc_opc_set_vsi_promiscuous_modes = 0x0254, + i40e_aqc_opc_add_tag = 0x0255, + i40e_aqc_opc_remove_tag = 0x0256, + i40e_aqc_opc_add_multicast_etag = 0x0257, + i40e_aqc_opc_remove_multicast_etag = 0x0258, + i40e_aqc_opc_update_tag = 0x0259, + i40e_aqc_opc_add_control_packet_filter = 0x025A, + i40e_aqc_opc_remove_control_packet_filter = 0x025B, + i40e_aqc_opc_add_cloud_filters = 0x025C, + i40e_aqc_opc_remove_cloud_filters = 0x025D, + i40e_aqc_opc_clear_wol_switch_filters = 0x025E, + + i40e_aqc_opc_add_mirror_rule = 0x0260, + i40e_aqc_opc_delete_mirror_rule = 0x0261, + + /* Dynamic Device Personalization */ + i40e_aqc_opc_write_personalization_profile = 0x0270, + i40e_aqc_opc_get_personalization_profile_list = 0x0271, + + /* DCB commands */ + i40e_aqc_opc_dcb_ignore_pfc = 0x0301, + i40e_aqc_opc_dcb_updated = 0x0302, + i40e_aqc_opc_set_dcb_parameters = 0x0303, + + /* TX scheduler */ + i40e_aqc_opc_configure_vsi_bw_limit = 0x0400, + i40e_aqc_opc_configure_vsi_ets_sla_bw_limit = 0x0406, + i40e_aqc_opc_configure_vsi_tc_bw = 0x0407, + i40e_aqc_opc_query_vsi_bw_config = 0x0408, + i40e_aqc_opc_query_vsi_ets_sla_config = 0x040A, + i40e_aqc_opc_configure_switching_comp_bw_limit = 0x0410, + + i40e_aqc_opc_enable_switching_comp_ets = 0x0413, + i40e_aqc_opc_modify_switching_comp_ets = 0x0414, + i40e_aqc_opc_disable_switching_comp_ets = 0x0415, + i40e_aqc_opc_configure_switching_comp_ets_bw_limit = 0x0416, + i40e_aqc_opc_configure_switching_comp_bw_config = 0x0417, + i40e_aqc_opc_query_switching_comp_ets_config = 0x0418, + i40e_aqc_opc_query_port_ets_config = 0x0419, + i40e_aqc_opc_query_switching_comp_bw_config = 0x041A, + i40e_aqc_opc_suspend_port_tx = 0x041B, + i40e_aqc_opc_resume_port_tx = 0x041C, + i40e_aqc_opc_configure_partition_bw = 0x041D, + /* hmc */ + i40e_aqc_opc_query_hmc_resource_profile = 0x0500, + i40e_aqc_opc_set_hmc_resource_profile = 0x0501, + + /* phy commands*/ + i40e_aqc_opc_get_phy_abilities = 0x0600, + i40e_aqc_opc_set_phy_config = 0x0601, + i40e_aqc_opc_set_mac_config = 0x0603, + i40e_aqc_opc_set_link_restart_an = 0x0605, + i40e_aqc_opc_get_link_status = 0x0607, + i40e_aqc_opc_set_phy_int_mask = 0x0613, + i40e_aqc_opc_get_local_advt_reg = 0x0614, + i40e_aqc_opc_set_local_advt_reg = 0x0615, + i40e_aqc_opc_get_partner_advt = 0x0616, + i40e_aqc_opc_set_lb_modes = 0x0618, + 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, + i40e_aqc_opc_set_phy_register = 0x0628, + i40e_aqc_opc_get_phy_register = 0x0629, + + /* NVM commands */ + i40e_aqc_opc_nvm_read = 0x0701, + i40e_aqc_opc_nvm_erase = 0x0702, + i40e_aqc_opc_nvm_update = 0x0703, + 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, + i40e_aqc_opc_send_msg_to_vf = 0x0802, + i40e_aqc_opc_send_msg_to_peer = 0x0803, + + /* alternate structure */ + i40e_aqc_opc_alternate_write = 0x0900, + i40e_aqc_opc_alternate_write_indirect = 0x0901, + i40e_aqc_opc_alternate_read = 0x0902, + i40e_aqc_opc_alternate_read_indirect = 0x0903, + i40e_aqc_opc_alternate_write_done = 0x0904, + i40e_aqc_opc_alternate_set_mode = 0x0905, + i40e_aqc_opc_alternate_clear_port = 0x0906, + + /* LLDP commands */ + i40e_aqc_opc_lldp_get_mib = 0x0A00, + i40e_aqc_opc_lldp_update_mib = 0x0A01, + i40e_aqc_opc_lldp_add_tlv = 0x0A02, + i40e_aqc_opc_lldp_update_tlv = 0x0A03, + i40e_aqc_opc_lldp_delete_tlv = 0x0A04, + i40e_aqc_opc_lldp_stop = 0x0A05, + i40e_aqc_opc_lldp_start = 0x0A06, + + /* Tunnel commands */ + i40e_aqc_opc_add_udp_tunnel = 0x0B00, + i40e_aqc_opc_del_udp_tunnel = 0x0B01, + i40e_aqc_opc_set_rss_key = 0x0B02, + i40e_aqc_opc_set_rss_lut = 0x0B03, + i40e_aqc_opc_get_rss_key = 0x0B04, + i40e_aqc_opc_get_rss_lut = 0x0B05, + + /* Async Events */ + i40e_aqc_opc_event_lan_overflow = 0x1001, + + /* OEM commands */ + i40e_aqc_opc_oem_parameter_change = 0xFE00, + i40e_aqc_opc_oem_device_status_change = 0xFE01, + i40e_aqc_opc_oem_ocsd_initialize = 0xFE02, + i40e_aqc_opc_oem_ocbb_initialize = 0xFE03, + + /* debug commands */ + i40e_aqc_opc_debug_read_reg = 0xFF03, + i40e_aqc_opc_debug_write_reg = 0xFF04, + i40e_aqc_opc_debug_modify_reg = 0xFF07, + i40e_aqc_opc_debug_dump_internals = 0xFF08, +}; + +/* command structures and indirect data structures */ + +/* Structure naming conventions: + * - no suffix for direct command descriptor structures + * - _data for indirect sent data + * - _resp for indirect return data (data which is both will use _data) + * - _completion for direct return data + * - _element_ for repeated elements (may also be _data or _resp) + * + * Command structures are expected to overlay the params.raw member of the basic + * descriptor, and as such cannot exceed 16 bytes in length. + */ + +/* This macro is used to generate a compilation error if a structure + * is not exactly the correct length. It gives a divide by zero error if the + * structure is not of the correct size, otherwise it creates an enum that is + * never used. + */ +#define I40E_CHECK_STRUCT_LEN(n, X) enum i40e_static_assert_enum_##X \ + { i40e_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } + +/* This macro is used extensively to ensure that command structures are 16 + * bytes in length as they have to map to the raw array of that size. + */ +#define I40E_CHECK_CMD_LENGTH(X) I40E_CHECK_STRUCT_LEN(16, X) + +/* Queue Shutdown (direct 0x0003) */ +struct i40e_aqc_queue_shutdown { + __le32 driver_unloading; +#define I40E_AQ_DRIVER_UNLOADING 0x1 + u8 reserved[12]; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_queue_shutdown); + +struct i40e_aqc_vsi_properties_data { + /* first 96 byte are written by SW */ + __le16 valid_sections; +#define I40E_AQ_VSI_PROP_SWITCH_VALID 0x0001 +#define I40E_AQ_VSI_PROP_SECURITY_VALID 0x0002 +#define I40E_AQ_VSI_PROP_VLAN_VALID 0x0004 +#define I40E_AQ_VSI_PROP_CAS_PV_VALID 0x0008 +#define I40E_AQ_VSI_PROP_INGRESS_UP_VALID 0x0010 +#define I40E_AQ_VSI_PROP_EGRESS_UP_VALID 0x0020 +#define I40E_AQ_VSI_PROP_QUEUE_MAP_VALID 0x0040 +#define I40E_AQ_VSI_PROP_QUEUE_OPT_VALID 0x0080 +#define I40E_AQ_VSI_PROP_OUTER_UP_VALID 0x0100 +#define I40E_AQ_VSI_PROP_SCHED_VALID 0x0200 + /* switch section */ + __le16 switch_id; /* 12bit id combined with flags below */ +#define I40E_AQ_VSI_SW_ID_SHIFT 0x0000 +#define I40E_AQ_VSI_SW_ID_MASK (0xFFF << I40E_AQ_VSI_SW_ID_SHIFT) +#define I40E_AQ_VSI_SW_ID_FLAG_NOT_STAG 0x1000 +#define I40E_AQ_VSI_SW_ID_FLAG_ALLOW_LB 0x2000 +#define I40E_AQ_VSI_SW_ID_FLAG_LOCAL_LB 0x4000 + u8 sw_reserved[2]; + /* security section */ + u8 sec_flags; +#define I40E_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD 0x01 +#define I40E_AQ_VSI_SEC_FLAG_ENABLE_VLAN_CHK 0x02 +#define I40E_AQ_VSI_SEC_FLAG_ENABLE_MAC_CHK 0x04 + u8 sec_reserved; + /* VLAN section */ + __le16 pvid; /* VLANS include priority bits */ + __le16 fcoe_pvid; + u8 port_vlan_flags; +#define I40E_AQ_VSI_PVLAN_MODE_SHIFT 0x00 +#define I40E_AQ_VSI_PVLAN_MODE_MASK (0x03 << \ + I40E_AQ_VSI_PVLAN_MODE_SHIFT) +#define I40E_AQ_VSI_PVLAN_MODE_TAGGED 0x01 +#define I40E_AQ_VSI_PVLAN_MODE_UNTAGGED 0x02 +#define I40E_AQ_VSI_PVLAN_MODE_ALL 0x03 +#define I40E_AQ_VSI_PVLAN_INSERT_PVID 0x04 +#define I40E_AQ_VSI_PVLAN_EMOD_SHIFT 0x03 +#define I40E_AQ_VSI_PVLAN_EMOD_MASK (0x3 << \ + I40E_AQ_VSI_PVLAN_EMOD_SHIFT) +#define I40E_AQ_VSI_PVLAN_EMOD_STR_BOTH 0x0 +#define I40E_AQ_VSI_PVLAN_EMOD_STR_UP 0x08 +#define I40E_AQ_VSI_PVLAN_EMOD_STR 0x10 +#define I40E_AQ_VSI_PVLAN_EMOD_NOTHING 0x18 + u8 pvlan_reserved[3]; + /* ingress egress up sections */ + __le32 ingress_table; /* bitmap, 3 bits per up */ +#define I40E_AQ_VSI_UP_TABLE_UP0_SHIFT 0 +#define I40E_AQ_VSI_UP_TABLE_UP0_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP0_SHIFT) +#define I40E_AQ_VSI_UP_TABLE_UP1_SHIFT 3 +#define I40E_AQ_VSI_UP_TABLE_UP1_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP1_SHIFT) +#define I40E_AQ_VSI_UP_TABLE_UP2_SHIFT 6 +#define I40E_AQ_VSI_UP_TABLE_UP2_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP2_SHIFT) +#define I40E_AQ_VSI_UP_TABLE_UP3_SHIFT 9 +#define I40E_AQ_VSI_UP_TABLE_UP3_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP3_SHIFT) +#define I40E_AQ_VSI_UP_TABLE_UP4_SHIFT 12 +#define I40E_AQ_VSI_UP_TABLE_UP4_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP4_SHIFT) +#define I40E_AQ_VSI_UP_TABLE_UP5_SHIFT 15 +#define I40E_AQ_VSI_UP_TABLE_UP5_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP5_SHIFT) +#define I40E_AQ_VSI_UP_TABLE_UP6_SHIFT 18 +#define I40E_AQ_VSI_UP_TABLE_UP6_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP6_SHIFT) +#define I40E_AQ_VSI_UP_TABLE_UP7_SHIFT 21 +#define I40E_AQ_VSI_UP_TABLE_UP7_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP7_SHIFT) + __le32 egress_table; /* same defines as for ingress table */ + /* cascaded PV section */ + __le16 cas_pv_tag; + u8 cas_pv_flags; +#define I40E_AQ_VSI_CAS_PV_TAGX_SHIFT 0x00 +#define I40E_AQ_VSI_CAS_PV_TAGX_MASK (0x03 << \ + I40E_AQ_VSI_CAS_PV_TAGX_SHIFT) +#define I40E_AQ_VSI_CAS_PV_TAGX_LEAVE 0x00 +#define I40E_AQ_VSI_CAS_PV_TAGX_REMOVE 0x01 +#define I40E_AQ_VSI_CAS_PV_TAGX_COPY 0x02 +#define I40E_AQ_VSI_CAS_PV_INSERT_TAG 0x10 +#define I40E_AQ_VSI_CAS_PV_ETAG_PRUNE 0x20 +#define I40E_AQ_VSI_CAS_PV_ACCEPT_HOST_TAG 0x40 + u8 cas_pv_reserved; + /* queue mapping section */ + __le16 mapping_flags; +#define I40E_AQ_VSI_QUE_MAP_CONTIG 0x0 +#define I40E_AQ_VSI_QUE_MAP_NONCONTIG 0x1 + __le16 queue_mapping[16]; +#define I40E_AQ_VSI_QUEUE_SHIFT 0x0 +#define I40E_AQ_VSI_QUEUE_MASK (0x7FF << I40E_AQ_VSI_QUEUE_SHIFT) + __le16 tc_mapping[8]; +#define I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT 0 +#define I40E_AQ_VSI_TC_QUE_OFFSET_MASK (0x1FF << \ + I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT) +#define I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT 9 +#define I40E_AQ_VSI_TC_QUE_NUMBER_MASK (0x7 << \ + I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT) + /* queueing option section */ + u8 queueing_opt_flags; +#define I40E_AQ_VSI_QUE_OPT_MULTICAST_UDP_ENA 0x04 +#define I40E_AQ_VSI_QUE_OPT_UNICAST_UDP_ENA 0x08 +#define I40E_AQ_VSI_QUE_OPT_TCP_ENA 0x10 +#define I40E_AQ_VSI_QUE_OPT_FCOE_ENA 0x20 +#define I40E_AQ_VSI_QUE_OPT_RSS_LUT_PF 0x00 +#define I40E_AQ_VSI_QUE_OPT_RSS_LUT_VSI 0x40 + u8 queueing_opt_reserved[3]; + /* scheduler section */ + u8 up_enable_bits; + u8 sched_reserved; + /* outer up section */ + __le32 outer_up_table; /* same structure and defines as ingress tbl */ + u8 cmd_reserved[8]; + /* last 32 bytes are written by FW */ + __le16 qs_handle[8]; +#define I40E_AQ_VSI_QS_HANDLE_INVALID 0xFFFF + __le16 stat_counter_idx; + __le16 sched_id; + u8 resp_reserved[12]; +}; + +I40E_CHECK_STRUCT_LEN(128, i40e_aqc_vsi_properties_data); + +/* Get VEB Parameters (direct 0x0232) + * uses i40e_aqc_switch_seid for the descriptor + */ +struct i40e_aqc_get_veb_parameters_completion { + __le16 seid; + __le16 switch_id; + __le16 veb_flags; /* only the first/last flags from 0x0230 is valid */ + __le16 statistic_index; + __le16 vebs_used; + __le16 vebs_free; + u8 reserved[4]; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_get_veb_parameters_completion); + +#define I40E_LINK_SPEED_100MB_SHIFT 0x1 +#define I40E_LINK_SPEED_1000MB_SHIFT 0x2 +#define I40E_LINK_SPEED_10GB_SHIFT 0x3 +#define I40E_LINK_SPEED_40GB_SHIFT 0x4 +#define I40E_LINK_SPEED_20GB_SHIFT 0x5 +#define I40E_LINK_SPEED_25GB_SHIFT 0x6 + +enum i40e_aq_link_speed { + I40E_LINK_SPEED_UNKNOWN = 0, + I40E_LINK_SPEED_100MB = BIT(I40E_LINK_SPEED_100MB_SHIFT), + I40E_LINK_SPEED_1GB = BIT(I40E_LINK_SPEED_1000MB_SHIFT), + I40E_LINK_SPEED_10GB = BIT(I40E_LINK_SPEED_10GB_SHIFT), + I40E_LINK_SPEED_40GB = BIT(I40E_LINK_SPEED_40GB_SHIFT), + I40E_LINK_SPEED_20GB = BIT(I40E_LINK_SPEED_20GB_SHIFT), + I40E_LINK_SPEED_25GB = BIT(I40E_LINK_SPEED_25GB_SHIFT), +}; + +/* 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) + */ +struct i40e_aqc_pf_vf_message { + __le32 id; + u8 reserved[4]; + __le32 addr_high; + __le32 addr_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_pf_vf_message); + +struct i40e_aqc_get_set_rss_key { +#define I40E_AQC_SET_RSS_KEY_VSI_VALID BIT(15) +#define I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT 0 +#define I40E_AQC_SET_RSS_KEY_VSI_ID_MASK (0x3FF << \ + I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT) + __le16 vsi_id; + u8 reserved[6]; + __le32 addr_high; + __le32 addr_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_get_set_rss_key); + +struct i40e_aqc_get_set_rss_key_data { + u8 standard_rss_key[0x28]; + u8 extended_hash_key[0xc]; +}; + +I40E_CHECK_STRUCT_LEN(0x34, i40e_aqc_get_set_rss_key_data); + +struct i40e_aqc_get_set_rss_lut { +#define I40E_AQC_SET_RSS_LUT_VSI_VALID BIT(15) +#define I40E_AQC_SET_RSS_LUT_VSI_ID_SHIFT 0 +#define I40E_AQC_SET_RSS_LUT_VSI_ID_MASK (0x3FF << \ + I40E_AQC_SET_RSS_LUT_VSI_ID_SHIFT) + __le16 vsi_id; +#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT 0 +#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK \ + BIT(I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) + +#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_VSI 0 +#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_PF 1 + __le16 flags; + u8 reserved[4]; + __le32 addr_high; + __le32 addr_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_get_set_rss_lut); +#endif /* _I40E_ADMINQ_CMD_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h new file mode 100644 index 000000000000..272d76b733aa --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -0,0 +1,418 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _IAVF_H_ +#define _IAVF_H_ + +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/aer.h> +#include <linux/netdevice.h> +#include <linux/vmalloc.h> +#include <linux/interrupt.h> +#include <linux/ethtool.h> +#include <linux/if_vlan.h> +#include <linux/ip.h> +#include <linux/tcp.h> +#include <linux/sctp.h> +#include <linux/ipv6.h> +#include <linux/kernel.h> +#include <linux/bitops.h> +#include <linux/timer.h> +#include <linux/workqueue.h> +#include <linux/wait.h> +#include <linux/delay.h> +#include <linux/gfp.h> +#include <linux/skbuff.h> +#include <linux/dma-mapping.h> +#include <linux/etherdevice.h> +#include <linux/socket.h> +#include <linux/jiffies.h> +#include <net/ip6_checksum.h> +#include <net/pkt_cls.h> +#include <net/udp.h> +#include <net/tc_act/tc_gact.h> +#include <net/tc_act/tc_mirred.h> + +#include "iavf_type.h" +#include <linux/avf/virtchnl.h> +#include "iavf_txrx.h" + +#define DEFAULT_DEBUG_LEVEL_SHIFT 3 +#define PFX "iavf: " + +/* VSI state flags shared with common code */ +enum iavf_vsi_state_t { + __IAVF_VSI_DOWN, + /* This must be last as it determines the size of the BITMAP */ + __IAVF_VSI_STATE_SIZE__, +}; + +/* dummy struct to make common code less painful */ +struct iavf_vsi { + struct iavf_adapter *back; + struct net_device *netdev; + unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + u16 seid; + u16 id; + DECLARE_BITMAP(state, __IAVF_VSI_STATE_SIZE__); + int base_vector; + u16 work_limit; + u16 qs_handle; + void *priv; /* client driver data reference. */ +}; + +/* How many Rx Buffers do we bundle into one write to the hardware ? */ +#define IAVF_RX_BUFFER_WRITE 16 /* Must be power of 2 */ +#define IAVF_DEFAULT_TXD 512 +#define IAVF_DEFAULT_RXD 512 +#define IAVF_MAX_TXD 4096 +#define IAVF_MIN_TXD 64 +#define IAVF_MAX_RXD 4096 +#define IAVF_MIN_RXD 64 +#define IAVF_REQ_DESCRIPTOR_MULTIPLE 32 +#define IAVF_MAX_AQ_BUF_SIZE 4096 +#define IAVF_AQ_LEN 32 +#define IAVF_AQ_MAX_ERR 20 /* times to try before resetting AQ */ + +#define MAXIMUM_ETHERNET_VLAN_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN) + +#define IAVF_RX_DESC(R, i) (&(((union iavf_32byte_rx_desc *)((R)->desc))[i])) +#define IAVF_TX_DESC(R, i) (&(((struct iavf_tx_desc *)((R)->desc))[i])) +#define IAVF_TX_CTXTDESC(R, i) \ + (&(((struct iavf_tx_context_desc *)((R)->desc))[i])) +#define IAVF_MAX_REQ_QUEUES 4 + +#define IAVF_HKEY_ARRAY_SIZE ((IAVF_VFQF_HKEY_MAX_INDEX + 1) * 4) +#define IAVF_HLUT_ARRAY_SIZE ((IAVF_VFQF_HLUT_MAX_INDEX + 1) * 4) +#define IAVF_MBPS_DIVISOR 125000 /* divisor to convert to Mbps */ + +/* MAX_MSIX_Q_VECTORS of these are allocated, + * but we only use one per queue-specific vector. + */ +struct iavf_q_vector { + struct iavf_adapter *adapter; + struct iavf_vsi *vsi; + struct napi_struct napi; + struct iavf_ring_container rx; + struct iavf_ring_container tx; + u32 ring_mask; + u8 itr_countdown; /* when 0 should adjust adaptive ITR */ + u8 num_ringpairs; /* total number of ring pairs in vector */ + u16 v_idx; /* index in the vsi->q_vector array. */ + u16 reg_idx; /* register index of the interrupt */ + char name[IFNAMSIZ + 15]; + bool arm_wb_state; + cpumask_t affinity_mask; + struct irq_affinity_notify affinity_notify; +}; + +/* Helper macros to switch between ints/sec and what the register uses. + * And yes, it's the same math going both ways. The lowest value + * supported by all of the i40e hardware is 8. + */ +#define EITR_INTS_PER_SEC_TO_REG(_eitr) \ + ((_eitr) ? (1000000000 / ((_eitr) * 256)) : 8) +#define EITR_REG_TO_INTS_PER_SEC EITR_INTS_PER_SEC_TO_REG + +#define IAVF_DESC_UNUSED(R) \ + ((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \ + (R)->next_to_clean - (R)->next_to_use - 1) + +#define OTHER_VECTOR 1 +#define NONQ_VECS (OTHER_VECTOR) + +#define MIN_MSIX_Q_VECTORS 1 +#define MIN_MSIX_COUNT (MIN_MSIX_Q_VECTORS + NONQ_VECS) + +#define IAVF_QUEUE_END_OF_LIST 0x7FF +#define IAVF_FREE_VECTOR 0x7FFF +struct iavf_mac_filter { + struct list_head list; + u8 macaddr[ETH_ALEN]; + bool remove; /* filter needs to be removed */ + bool add; /* filter needs to be added */ +}; + +struct iavf_vlan_filter { + struct list_head list; + u16 vlan; + bool remove; /* filter needs to be removed */ + bool add; /* filter needs to be added */ +}; + +#define IAVF_MAX_TRAFFIC_CLASS 4 +/* State of traffic class creation */ +enum iavf_tc_state_t { + __IAVF_TC_INVALID, /* no traffic class, default state */ + __IAVF_TC_RUNNING, /* traffic classes have been created */ +}; + +/* channel info */ +struct iavf_channel_config { + struct virtchnl_channel_info ch_info[IAVF_MAX_TRAFFIC_CLASS]; + enum iavf_tc_state_t state; + u8 total_qps; +}; + +/* State of cloud filter */ +enum iavf_cloud_filter_state_t { + __IAVF_CF_INVALID, /* cloud filter not added */ + __IAVF_CF_ADD_PENDING, /* cloud filter pending add by the PF */ + __IAVF_CF_DEL_PENDING, /* cloud filter pending del by the PF */ + __IAVF_CF_ACTIVE, /* cloud filter is active */ +}; + +/* Driver state. The order of these is important! */ +enum iavf_state_t { + __IAVF_STARTUP, /* driver loaded, probe complete */ + __IAVF_REMOVE, /* driver is being unloaded */ + __IAVF_INIT_VERSION_CHECK, /* aq msg sent, awaiting reply */ + __IAVF_INIT_GET_RESOURCES, /* aq msg sent, awaiting reply */ + __IAVF_INIT_SW, /* got resources, setting up structs */ + __IAVF_RESETTING, /* in reset */ + /* Below here, watchdog is running */ + __IAVF_DOWN, /* ready, can be opened */ + __IAVF_DOWN_PENDING, /* descending, waiting for watchdog */ + __IAVF_TESTING, /* in ethtool self-test */ + __IAVF_RUNNING, /* opened, working */ +}; + +enum iavf_critical_section_t { + __IAVF_IN_CRITICAL_TASK, /* cannot be interrupted */ + __IAVF_IN_CLIENT_TASK, + __IAVF_IN_REMOVE_TASK, /* device being removed */ +}; + +#define IAVF_CLOUD_FIELD_OMAC 0x01 +#define IAVF_CLOUD_FIELD_IMAC 0x02 +#define IAVF_CLOUD_FIELD_IVLAN 0x04 +#define IAVF_CLOUD_FIELD_TEN_ID 0x08 +#define IAVF_CLOUD_FIELD_IIP 0x10 + +#define IAVF_CF_FLAGS_OMAC IAVF_CLOUD_FIELD_OMAC +#define IAVF_CF_FLAGS_IMAC IAVF_CLOUD_FIELD_IMAC +#define IAVF_CF_FLAGS_IMAC_IVLAN (IAVF_CLOUD_FIELD_IMAC |\ + IAVF_CLOUD_FIELD_IVLAN) +#define IAVF_CF_FLAGS_IMAC_TEN_ID (IAVF_CLOUD_FIELD_IMAC |\ + IAVF_CLOUD_FIELD_TEN_ID) +#define IAVF_CF_FLAGS_OMAC_TEN_ID_IMAC (IAVF_CLOUD_FIELD_OMAC |\ + IAVF_CLOUD_FIELD_IMAC |\ + IAVF_CLOUD_FIELD_TEN_ID) +#define IAVF_CF_FLAGS_IMAC_IVLAN_TEN_ID (IAVF_CLOUD_FIELD_IMAC |\ + IAVF_CLOUD_FIELD_IVLAN |\ + IAVF_CLOUD_FIELD_TEN_ID) +#define IAVF_CF_FLAGS_IIP IAVF_CLOUD_FIELD_IIP + +/* bookkeeping of cloud filters */ +struct iavf_cloud_filter { + enum iavf_cloud_filter_state_t state; + struct list_head list; + struct virtchnl_filter f; + unsigned long cookie; + bool del; /* filter needs to be deleted */ + bool add; /* filter needs to be added */ +}; + +/* board specific private data structure */ +struct iavf_adapter { + struct timer_list watchdog_timer; + struct work_struct reset_task; + struct work_struct adminq_task; + struct delayed_work client_task; + struct delayed_work init_task; + wait_queue_head_t down_waitqueue; + struct iavf_q_vector *q_vectors; + struct list_head vlan_filter_list; + struct list_head mac_filter_list; + /* Lock to protect accesses to MAC and VLAN lists */ + spinlock_t mac_vlan_list_lock; + char misc_vector_name[IFNAMSIZ + 9]; + int num_active_queues; + int num_req_queues; + + /* TX */ + struct iavf_ring *tx_rings; + u32 tx_timeout_count; + u32 tx_desc_count; + + /* RX */ + struct iavf_ring *rx_rings; + u64 hw_csum_rx_error; + u32 rx_desc_count; + int num_msix_vectors; + int num_iwarp_msix; + int iwarp_base_vector; + u32 client_pending; + struct i40e_client_instance *cinst; + struct msix_entry *msix_entries; + + u32 flags; +#define IAVF_FLAG_RX_CSUM_ENABLED BIT(0) +#define IAVF_FLAG_PF_COMMS_FAILED BIT(3) +#define IAVF_FLAG_RESET_PENDING BIT(4) +#define IAVF_FLAG_RESET_NEEDED BIT(5) +#define IAVF_FLAG_WB_ON_ITR_CAPABLE BIT(6) +#define IAVF_FLAG_ADDR_SET_BY_PF BIT(8) +#define IAVF_FLAG_SERVICE_CLIENT_REQUESTED BIT(9) +#define IAVF_FLAG_CLIENT_NEEDS_OPEN BIT(10) +#define IAVF_FLAG_CLIENT_NEEDS_CLOSE BIT(11) +#define IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS BIT(12) +#define IAVF_FLAG_PROMISC_ON BIT(13) +#define IAVF_FLAG_ALLMULTI_ON BIT(14) +#define IAVF_FLAG_LEGACY_RX BIT(15) +#define IAVF_FLAG_REINIT_ITR_NEEDED BIT(16) +#define IAVF_FLAG_QUEUES_DISABLED BIT(17) +/* duplicates for common code */ +#define IAVF_FLAG_DCB_ENABLED 0 + /* flags for admin queue service task */ + u32 aq_required; +#define IAVF_FLAG_AQ_ENABLE_QUEUES BIT(0) +#define IAVF_FLAG_AQ_DISABLE_QUEUES BIT(1) +#define IAVF_FLAG_AQ_ADD_MAC_FILTER BIT(2) +#define IAVF_FLAG_AQ_ADD_VLAN_FILTER BIT(3) +#define IAVF_FLAG_AQ_DEL_MAC_FILTER BIT(4) +#define IAVF_FLAG_AQ_DEL_VLAN_FILTER BIT(5) +#define IAVF_FLAG_AQ_CONFIGURE_QUEUES BIT(6) +#define IAVF_FLAG_AQ_MAP_VECTORS BIT(7) +#define IAVF_FLAG_AQ_HANDLE_RESET BIT(8) +#define IAVF_FLAG_AQ_CONFIGURE_RSS BIT(9) /* direct AQ config */ +#define IAVF_FLAG_AQ_GET_CONFIG BIT(10) +/* Newer style, RSS done by the PF so we can ignore hardware vagaries. */ +#define IAVF_FLAG_AQ_GET_HENA BIT(11) +#define IAVF_FLAG_AQ_SET_HENA BIT(12) +#define IAVF_FLAG_AQ_SET_RSS_KEY BIT(13) +#define IAVF_FLAG_AQ_SET_RSS_LUT BIT(14) +#define IAVF_FLAG_AQ_REQUEST_PROMISC BIT(15) +#define IAVF_FLAG_AQ_RELEASE_PROMISC BIT(16) +#define IAVF_FLAG_AQ_REQUEST_ALLMULTI BIT(17) +#define IAVF_FLAG_AQ_RELEASE_ALLMULTI BIT(18) +#define IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING BIT(19) +#define IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING BIT(20) +#define IAVF_FLAG_AQ_ENABLE_CHANNELS BIT(21) +#define IAVF_FLAG_AQ_DISABLE_CHANNELS BIT(22) +#define IAVF_FLAG_AQ_ADD_CLOUD_FILTER BIT(23) +#define IAVF_FLAG_AQ_DEL_CLOUD_FILTER BIT(24) + + /* OS defined structs */ + struct net_device *netdev; + struct pci_dev *pdev; + + struct iavf_hw hw; /* defined in iavf_type.h */ + + enum iavf_state_t state; + unsigned long crit_section; + + struct work_struct watchdog_task; + bool netdev_registered; + bool link_up; + enum virtchnl_link_speed link_speed; + enum virtchnl_ops current_op; +#define CLIENT_ALLOWED(_a) ((_a)->vf_res ? \ + (_a)->vf_res->vf_cap_flags & \ + VIRTCHNL_VF_OFFLOAD_IWARP : \ + 0) +#define CLIENT_ENABLED(_a) ((_a)->cinst) +/* RSS by the PF should be preferred over RSS via other methods. */ +#define RSS_PF(_a) ((_a)->vf_res->vf_cap_flags & \ + VIRTCHNL_VF_OFFLOAD_RSS_PF) +#define RSS_AQ(_a) ((_a)->vf_res->vf_cap_flags & \ + VIRTCHNL_VF_OFFLOAD_RSS_AQ) +#define RSS_REG(_a) (!((_a)->vf_res->vf_cap_flags & \ + (VIRTCHNL_VF_OFFLOAD_RSS_AQ | \ + VIRTCHNL_VF_OFFLOAD_RSS_PF))) +#define VLAN_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \ + VIRTCHNL_VF_OFFLOAD_VLAN) + struct virtchnl_vf_resource *vf_res; /* incl. all VSIs */ + struct virtchnl_vsi_resource *vsi_res; /* our LAN VSI */ + struct virtchnl_version_info pf_version; +#define PF_IS_V11(_a) (((_a)->pf_version.major == 1) && \ + ((_a)->pf_version.minor == 1)) + u16 msg_enable; + struct iavf_eth_stats current_stats; + struct iavf_vsi vsi; + u32 aq_wait_count; + /* RSS stuff */ + u64 hena; + u16 rss_key_size; + u16 rss_lut_size; + u8 *rss_key; + u8 *rss_lut; + /* ADQ related members */ + struct iavf_channel_config ch_config; + u8 num_tc; + struct list_head cloud_filter_list; + /* lock to protect access to the cloud filter list */ + spinlock_t cloud_filter_list_lock; + u16 num_cloud_filters; +}; + + +/* Ethtool Private Flags */ + +/* lan device, used by client interface */ +struct i40e_device { + struct list_head list; + struct iavf_adapter *vf; +}; + +/* needed by iavf_ethtool.c */ +extern char iavf_driver_name[]; +extern const char iavf_driver_version[]; + +int iavf_up(struct iavf_adapter *adapter); +void iavf_down(struct iavf_adapter *adapter); +int iavf_process_config(struct iavf_adapter *adapter); +void iavf_schedule_reset(struct iavf_adapter *adapter); +void iavf_reset(struct iavf_adapter *adapter); +void iavf_set_ethtool_ops(struct net_device *netdev); +void iavf_update_stats(struct iavf_adapter *adapter); +void iavf_reset_interrupt_capability(struct iavf_adapter *adapter); +int iavf_init_interrupt_scheme(struct iavf_adapter *adapter); +void iavf_irq_enable_queues(struct iavf_adapter *adapter, u32 mask); +void iavf_free_all_tx_resources(struct iavf_adapter *adapter); +void iavf_free_all_rx_resources(struct iavf_adapter *adapter); + +void iavf_napi_add_all(struct iavf_adapter *adapter); +void iavf_napi_del_all(struct iavf_adapter *adapter); + +int iavf_send_api_ver(struct iavf_adapter *adapter); +int iavf_verify_api_ver(struct iavf_adapter *adapter); +int iavf_send_vf_config_msg(struct iavf_adapter *adapter); +int iavf_get_vf_config(struct iavf_adapter *adapter); +void iavf_irq_enable(struct iavf_adapter *adapter, bool flush); +void iavf_configure_queues(struct iavf_adapter *adapter); +void iavf_deconfigure_queues(struct iavf_adapter *adapter); +void iavf_enable_queues(struct iavf_adapter *adapter); +void iavf_disable_queues(struct iavf_adapter *adapter); +void iavf_map_queues(struct iavf_adapter *adapter); +int iavf_request_queues(struct iavf_adapter *adapter, int num); +void iavf_add_ether_addrs(struct iavf_adapter *adapter); +void iavf_del_ether_addrs(struct iavf_adapter *adapter); +void iavf_add_vlans(struct iavf_adapter *adapter); +void iavf_del_vlans(struct iavf_adapter *adapter); +void iavf_set_promiscuous(struct iavf_adapter *adapter, int flags); +void iavf_request_stats(struct iavf_adapter *adapter); +void iavf_request_reset(struct iavf_adapter *adapter); +void iavf_get_hena(struct iavf_adapter *adapter); +void iavf_set_hena(struct iavf_adapter *adapter); +void iavf_set_rss_key(struct iavf_adapter *adapter); +void iavf_set_rss_lut(struct iavf_adapter *adapter); +void iavf_enable_vlan_stripping(struct iavf_adapter *adapter); +void iavf_disable_vlan_stripping(struct iavf_adapter *adapter); +void iavf_virtchnl_completion(struct iavf_adapter *adapter, + enum virtchnl_ops v_opcode, + iavf_status v_retval, u8 *msg, u16 msglen); +int iavf_config_rss(struct iavf_adapter *adapter); +int iavf_lan_add_device(struct iavf_adapter *adapter); +int iavf_lan_del_device(struct iavf_adapter *adapter); +void iavf_client_subtask(struct iavf_adapter *adapter); +void iavf_notify_client_message(struct iavf_vsi *vsi, u8 *msg, u16 len); +void iavf_notify_client_l2_params(struct iavf_vsi *vsi); +void iavf_notify_client_open(struct iavf_vsi *vsi); +void iavf_notify_client_close(struct iavf_vsi *vsi, bool reset); +void iavf_enable_channels(struct iavf_adapter *adapter); +void iavf_disable_channels(struct iavf_adapter *adapter); +void iavf_add_cloud_filter(struct iavf_adapter *adapter); +void iavf_del_cloud_filter(struct iavf_adapter *adapter); +#endif /* _IAVF_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_alloc.h b/drivers/net/ethernet/intel/iavf/iavf_alloc.h new file mode 100644 index 000000000000..bf2753146f30 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_alloc.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _IAVF_ALLOC_H_ +#define _IAVF_ALLOC_H_ + +struct iavf_hw; + +/* Memory allocation types */ +enum iavf_memory_type { + iavf_mem_arq_buf = 0, /* ARQ indirect command buffer */ + iavf_mem_asq_buf = 1, + iavf_mem_atq_buf = 2, /* ATQ indirect command buffer */ + iavf_mem_arq_ring = 3, /* ARQ descriptor ring */ + iavf_mem_atq_ring = 4, /* ATQ descriptor ring */ + iavf_mem_pd = 5, /* Page Descriptor */ + iavf_mem_bp = 6, /* Backing Page - 4KB */ + iavf_mem_bp_jumbo = 7, /* Backing Page - > 4KB */ + iavf_mem_reserved +}; + +/* prototype for functions used for dynamic memory allocation */ +iavf_status iavf_allocate_dma_mem(struct iavf_hw *hw, struct iavf_dma_mem *mem, + enum iavf_memory_type type, + u64 size, u32 alignment); +iavf_status iavf_free_dma_mem(struct iavf_hw *hw, struct iavf_dma_mem *mem); +iavf_status iavf_allocate_virt_mem(struct iavf_hw *hw, + struct iavf_virt_mem *mem, u32 size); +iavf_status iavf_free_virt_mem(struct iavf_hw *hw, struct iavf_virt_mem *mem); + +#endif /* _IAVF_ALLOC_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_client.c b/drivers/net/ethernet/intel/iavf/iavf_client.c new file mode 100644 index 000000000000..aea45364fd1c --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_client.c @@ -0,0 +1,579 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#include <linux/list.h> +#include <linux/errno.h> + +#include "iavf.h" +#include "iavf_prototype.h" +#include "iavf_client.h" + +static +const char iavf_client_interface_version_str[] = IAVF_CLIENT_VERSION_STR; +static struct i40e_client *vf_registered_client; +static LIST_HEAD(i40e_devices); +static DEFINE_MUTEX(iavf_device_mutex); + +static u32 iavf_client_virtchnl_send(struct i40e_info *ldev, + struct i40e_client *client, + u8 *msg, u16 len); + +static int iavf_client_setup_qvlist(struct i40e_info *ldev, + struct i40e_client *client, + struct i40e_qvlist_info *qvlist_info); + +static struct i40e_ops iavf_lan_ops = { + .virtchnl_send = iavf_client_virtchnl_send, + .setup_qvlist = iavf_client_setup_qvlist, +}; + +/** + * iavf_client_get_params - retrieve relevant client parameters + * @vsi: VSI with parameters + * @params: client param struct + **/ +static +void iavf_client_get_params(struct iavf_vsi *vsi, struct i40e_params *params) +{ + int i; + + memset(params, 0, sizeof(struct i40e_params)); + params->mtu = vsi->netdev->mtu; + params->link_up = vsi->back->link_up; + + for (i = 0; i < IAVF_MAX_USER_PRIORITY; i++) { + params->qos.prio_qos[i].tc = 0; + params->qos.prio_qos[i].qs_handle = vsi->qs_handle; + } +} + +/** + * iavf_notify_client_message - call the client message receive callback + * @vsi: the VSI associated with this client + * @msg: message buffer + * @len: length of message + * + * If there is a client to this VSI, call the client + **/ +void iavf_notify_client_message(struct iavf_vsi *vsi, u8 *msg, u16 len) +{ + struct i40e_client_instance *cinst; + + if (!vsi) + return; + + cinst = vsi->back->cinst; + if (!cinst || !cinst->client || !cinst->client->ops || + !cinst->client->ops->virtchnl_receive) { + dev_dbg(&vsi->back->pdev->dev, + "Cannot locate client instance virtchnl_receive function\n"); + return; + } + cinst->client->ops->virtchnl_receive(&cinst->lan_info, cinst->client, + msg, len); +} + +/** + * iavf_notify_client_l2_params - call the client notify callback + * @vsi: the VSI with l2 param changes + * + * If there is a client to this VSI, call the client + **/ +void iavf_notify_client_l2_params(struct iavf_vsi *vsi) +{ + struct i40e_client_instance *cinst; + struct i40e_params params; + + if (!vsi) + return; + + cinst = vsi->back->cinst; + + if (!cinst || !cinst->client || !cinst->client->ops || + !cinst->client->ops->l2_param_change) { + dev_dbg(&vsi->back->pdev->dev, + "Cannot locate client instance l2_param_change function\n"); + return; + } + iavf_client_get_params(vsi, ¶ms); + cinst->lan_info.params = params; + cinst->client->ops->l2_param_change(&cinst->lan_info, cinst->client, + ¶ms); +} + +/** + * iavf_notify_client_open - call the client open callback + * @vsi: the VSI with netdev opened + * + * If there is a client to this netdev, call the client with open + **/ +void iavf_notify_client_open(struct iavf_vsi *vsi) +{ + struct iavf_adapter *adapter = vsi->back; + struct i40e_client_instance *cinst = adapter->cinst; + int ret; + + if (!cinst || !cinst->client || !cinst->client->ops || + !cinst->client->ops->open) { + dev_dbg(&vsi->back->pdev->dev, + "Cannot locate client instance open function\n"); + return; + } + if (!(test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state))) { + ret = cinst->client->ops->open(&cinst->lan_info, cinst->client); + if (!ret) + set_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state); + } +} + +/** + * iavf_client_release_qvlist - send a message to the PF to release iwarp qv map + * @ldev: pointer to L2 context. + * + * Return 0 on success or < 0 on error + **/ +static int iavf_client_release_qvlist(struct i40e_info *ldev) +{ + struct iavf_adapter *adapter = ldev->vf; + iavf_status err; + + if (adapter->aq_required) + return -EAGAIN; + + err = iavf_aq_send_msg_to_pf(&adapter->hw, + VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP, + I40E_SUCCESS, NULL, 0, NULL); + + if (err) + dev_err(&adapter->pdev->dev, + "Unable to send iWarp vector release message to PF, error %d, aq status %d\n", + err, adapter->hw.aq.asq_last_status); + + return err; +} + +/** + * iavf_notify_client_close - call the client close callback + * @vsi: the VSI with netdev closed + * @reset: true when close called due to reset pending + * + * If there is a client to this netdev, call the client with close + **/ +void iavf_notify_client_close(struct iavf_vsi *vsi, bool reset) +{ + struct iavf_adapter *adapter = vsi->back; + struct i40e_client_instance *cinst = adapter->cinst; + + if (!cinst || !cinst->client || !cinst->client->ops || + !cinst->client->ops->close) { + dev_dbg(&vsi->back->pdev->dev, + "Cannot locate client instance close function\n"); + return; + } + cinst->client->ops->close(&cinst->lan_info, cinst->client, reset); + iavf_client_release_qvlist(&cinst->lan_info); + clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state); +} + +/** + * iavf_client_add_instance - add a client instance to the instance list + * @adapter: pointer to the board struct + * + * Returns cinst ptr on success, NULL on failure + **/ +static struct i40e_client_instance * +iavf_client_add_instance(struct iavf_adapter *adapter) +{ + struct i40e_client_instance *cinst = NULL; + struct iavf_vsi *vsi = &adapter->vsi; + struct netdev_hw_addr *mac = NULL; + struct i40e_params params; + + if (!vf_registered_client) + goto out; + + if (adapter->cinst) { + cinst = adapter->cinst; + goto out; + } + + cinst = kzalloc(sizeof(*cinst), GFP_KERNEL); + if (!cinst) + goto out; + + cinst->lan_info.vf = (void *)adapter; + cinst->lan_info.netdev = vsi->netdev; + cinst->lan_info.pcidev = adapter->pdev; + cinst->lan_info.fid = 0; + cinst->lan_info.ftype = I40E_CLIENT_FTYPE_VF; + cinst->lan_info.hw_addr = adapter->hw.hw_addr; + cinst->lan_info.ops = &iavf_lan_ops; + cinst->lan_info.version.major = IAVF_CLIENT_VERSION_MAJOR; + cinst->lan_info.version.minor = IAVF_CLIENT_VERSION_MINOR; + cinst->lan_info.version.build = IAVF_CLIENT_VERSION_BUILD; + iavf_client_get_params(vsi, ¶ms); + cinst->lan_info.params = params; + set_bit(__I40E_CLIENT_INSTANCE_NONE, &cinst->state); + + cinst->lan_info.msix_count = adapter->num_iwarp_msix; + cinst->lan_info.msix_entries = + &adapter->msix_entries[adapter->iwarp_base_vector]; + + mac = list_first_entry(&cinst->lan_info.netdev->dev_addrs.list, + struct netdev_hw_addr, list); + if (mac) + ether_addr_copy(cinst->lan_info.lanmac, mac->addr); + else + dev_err(&adapter->pdev->dev, "MAC address list is empty!\n"); + + cinst->client = vf_registered_client; + adapter->cinst = cinst; +out: + return cinst; +} + +/** + * iavf_client_del_instance - removes a client instance from the list + * @adapter: pointer to the board struct + * + **/ +static +void iavf_client_del_instance(struct iavf_adapter *adapter) +{ + kfree(adapter->cinst); + adapter->cinst = NULL; +} + +/** + * iavf_client_subtask - client maintenance work + * @adapter: board private structure + **/ +void iavf_client_subtask(struct iavf_adapter *adapter) +{ + struct i40e_client *client = vf_registered_client; + struct i40e_client_instance *cinst; + int ret = 0; + + if (adapter->state < __IAVF_DOWN) + return; + + /* first check client is registered */ + if (!client) + return; + + /* Add the client instance to the instance list */ + cinst = iavf_client_add_instance(adapter); + if (!cinst) + return; + + dev_info(&adapter->pdev->dev, "Added instance of Client %s\n", + client->name); + + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state)) { + /* Send an Open request to the client */ + + if (client->ops && client->ops->open) + ret = client->ops->open(&cinst->lan_info, client); + if (!ret) + set_bit(__I40E_CLIENT_INSTANCE_OPENED, + &cinst->state); + else + /* remove client instance */ + iavf_client_del_instance(adapter); + } +} + +/** + * iavf_lan_add_device - add a lan device struct to the list of lan devices + * @adapter: pointer to the board struct + * + * Returns 0 on success or none 0 on error + **/ +int iavf_lan_add_device(struct iavf_adapter *adapter) +{ + struct i40e_device *ldev; + int ret = 0; + + mutex_lock(&iavf_device_mutex); + list_for_each_entry(ldev, &i40e_devices, list) { + if (ldev->vf == adapter) { + ret = -EEXIST; + goto out; + } + } + ldev = kzalloc(sizeof(*ldev), GFP_KERNEL); + if (!ldev) { + ret = -ENOMEM; + goto out; + } + ldev->vf = adapter; + INIT_LIST_HEAD(&ldev->list); + list_add(&ldev->list, &i40e_devices); + dev_info(&adapter->pdev->dev, "Added LAN device bus=0x%02x dev=0x%02x func=0x%02x\n", + adapter->hw.bus.bus_id, adapter->hw.bus.device, + adapter->hw.bus.func); + + /* Since in some cases register may have happened before a device gets + * added, we can schedule a subtask to go initiate the clients. + */ + adapter->flags |= IAVF_FLAG_SERVICE_CLIENT_REQUESTED; + +out: + mutex_unlock(&iavf_device_mutex); + return ret; +} + +/** + * iavf_lan_del_device - removes a lan device from the device list + * @adapter: pointer to the board struct + * + * Returns 0 on success or non-0 on error + **/ +int iavf_lan_del_device(struct iavf_adapter *adapter) +{ + struct i40e_device *ldev, *tmp; + int ret = -ENODEV; + + mutex_lock(&iavf_device_mutex); + list_for_each_entry_safe(ldev, tmp, &i40e_devices, list) { + if (ldev->vf == adapter) { + dev_info(&adapter->pdev->dev, + "Deleted LAN device bus=0x%02x dev=0x%02x func=0x%02x\n", + adapter->hw.bus.bus_id, adapter->hw.bus.device, + adapter->hw.bus.func); + list_del(&ldev->list); + kfree(ldev); + ret = 0; + break; + } + } + + mutex_unlock(&iavf_device_mutex); + return ret; +} + +/** + * iavf_client_release - release client specific resources + * @client: pointer to the registered client + * + **/ +static void iavf_client_release(struct i40e_client *client) +{ + struct i40e_client_instance *cinst; + struct i40e_device *ldev; + struct iavf_adapter *adapter; + + mutex_lock(&iavf_device_mutex); + list_for_each_entry(ldev, &i40e_devices, list) { + adapter = ldev->vf; + cinst = adapter->cinst; + if (!cinst) + continue; + if (test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state)) { + if (client->ops && client->ops->close) + client->ops->close(&cinst->lan_info, client, + false); + iavf_client_release_qvlist(&cinst->lan_info); + clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state); + + dev_warn(&adapter->pdev->dev, + "Client %s instance closed\n", client->name); + } + /* delete the client instance */ + iavf_client_del_instance(adapter); + dev_info(&adapter->pdev->dev, "Deleted client instance of Client %s\n", + client->name); + } + mutex_unlock(&iavf_device_mutex); +} + +/** + * iavf_client_prepare - prepare client specific resources + * @client: pointer to the registered client + * + **/ +static void iavf_client_prepare(struct i40e_client *client) +{ + struct i40e_device *ldev; + struct iavf_adapter *adapter; + + mutex_lock(&iavf_device_mutex); + list_for_each_entry(ldev, &i40e_devices, list) { + adapter = ldev->vf; + /* Signal the watchdog to service the client */ + adapter->flags |= IAVF_FLAG_SERVICE_CLIENT_REQUESTED; + } + mutex_unlock(&iavf_device_mutex); +} + +/** + * iavf_client_virtchnl_send - send a message to the PF instance + * @ldev: pointer to L2 context. + * @client: Client pointer. + * @msg: pointer to message buffer + * @len: message length + * + * Return 0 on success or < 0 on error + **/ +static u32 iavf_client_virtchnl_send(struct i40e_info *ldev, + struct i40e_client *client, + u8 *msg, u16 len) +{ + struct iavf_adapter *adapter = ldev->vf; + iavf_status err; + + if (adapter->aq_required) + return -EAGAIN; + + err = iavf_aq_send_msg_to_pf(&adapter->hw, VIRTCHNL_OP_IWARP, + I40E_SUCCESS, msg, len, NULL); + if (err) + dev_err(&adapter->pdev->dev, "Unable to send iWarp message to PF, error %d, aq status %d\n", + err, adapter->hw.aq.asq_last_status); + + return err; +} + +/** + * iavf_client_setup_qvlist - send a message to the PF to setup iwarp qv map + * @ldev: pointer to L2 context. + * @client: Client pointer. + * @qvlist_info: queue and vector list + * + * Return 0 on success or < 0 on error + **/ +static int iavf_client_setup_qvlist(struct i40e_info *ldev, + struct i40e_client *client, + struct i40e_qvlist_info *qvlist_info) +{ + struct virtchnl_iwarp_qvlist_info *v_qvlist_info; + struct iavf_adapter *adapter = ldev->vf; + struct i40e_qv_info *qv_info; + iavf_status err; + u32 v_idx, i; + u32 msg_size; + + if (adapter->aq_required) + return -EAGAIN; + + /* A quick check on whether the vectors belong to the client */ + for (i = 0; i < qvlist_info->num_vectors; i++) { + qv_info = &qvlist_info->qv_info[i]; + if (!qv_info) + continue; + v_idx = qv_info->v_idx; + if ((v_idx >= + (adapter->iwarp_base_vector + adapter->num_iwarp_msix)) || + (v_idx < adapter->iwarp_base_vector)) + return -EINVAL; + } + + v_qvlist_info = (struct virtchnl_iwarp_qvlist_info *)qvlist_info; + msg_size = sizeof(struct virtchnl_iwarp_qvlist_info) + + (sizeof(struct virtchnl_iwarp_qv_info) * + (v_qvlist_info->num_vectors - 1)); + + adapter->client_pending |= BIT(VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP); + err = iavf_aq_send_msg_to_pf(&adapter->hw, + VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP, I40E_SUCCESS, + (u8 *)v_qvlist_info, msg_size, NULL); + + if (err) { + dev_err(&adapter->pdev->dev, + "Unable to send iWarp vector config message to PF, error %d, aq status %d\n", + err, adapter->hw.aq.asq_last_status); + goto out; + } + + err = -EBUSY; + for (i = 0; i < 5; i++) { + msleep(100); + if (!(adapter->client_pending & + BIT(VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP))) { + err = 0; + break; + } + } +out: + return err; +} + +/** + * iavf_register_client - Register a i40e client driver with the L2 driver + * @client: pointer to the i40e_client struct + * + * Returns 0 on success or non-0 on error + **/ +int iavf_register_client(struct i40e_client *client) +{ + int ret = 0; + + if (!client) { + ret = -EIO; + goto out; + } + + if (strlen(client->name) == 0) { + pr_info("iavf: Failed to register client with no name\n"); + ret = -EIO; + goto out; + } + + if (vf_registered_client) { + pr_info("iavf: Client %s has already been registered!\n", + client->name); + ret = -EEXIST; + goto out; + } + + if ((client->version.major != IAVF_CLIENT_VERSION_MAJOR) || + (client->version.minor != IAVF_CLIENT_VERSION_MINOR)) { + pr_info("iavf: Failed to register client %s due to mismatched client interface version\n", + client->name); + pr_info("Client is using version: %02d.%02d.%02d while LAN driver supports %s\n", + client->version.major, client->version.minor, + client->version.build, + iavf_client_interface_version_str); + ret = -EIO; + goto out; + } + + vf_registered_client = client; + + iavf_client_prepare(client); + + pr_info("iavf: Registered client %s with return code %d\n", + client->name, ret); +out: + return ret; +} +EXPORT_SYMBOL(iavf_register_client); + +/** + * iavf_unregister_client - Unregister a i40e client driver with the L2 driver + * @client: pointer to the i40e_client struct + * + * Returns 0 on success or non-0 on error + **/ +int iavf_unregister_client(struct i40e_client *client) +{ + int ret = 0; + + /* When a unregister request comes through we would have to send + * a close for each of the client instances that were opened. + * client_release function is called to handle this. + */ + iavf_client_release(client); + + if (vf_registered_client != client) { + pr_info("iavf: Client %s has not been registered\n", + client->name); + ret = -ENODEV; + goto out; + } + vf_registered_client = NULL; + pr_info("iavf: Unregistered client %s\n", client->name); +out: + return ret; +} +EXPORT_SYMBOL(iavf_unregister_client); diff --git a/drivers/net/ethernet/intel/iavf/iavf_client.h b/drivers/net/ethernet/intel/iavf/iavf_client.h new file mode 100644 index 000000000000..e216fc9dfd81 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_client.h @@ -0,0 +1,169 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _IAVF_CLIENT_H_ +#define _IAVF_CLIENT_H_ + +#define IAVF_CLIENT_STR_LENGTH 10 + +/* Client interface version should be updated anytime there is a change in the + * existing APIs or data structures. + */ +#define IAVF_CLIENT_VERSION_MAJOR 0 +#define IAVF_CLIENT_VERSION_MINOR 01 +#define IAVF_CLIENT_VERSION_BUILD 00 +#define IAVF_CLIENT_VERSION_STR \ + __stringify(IAVF_CLIENT_VERSION_MAJOR) "." \ + __stringify(IAVF_CLIENT_VERSION_MINOR) "." \ + __stringify(IAVF_CLIENT_VERSION_BUILD) + +struct i40e_client_version { + u8 major; + u8 minor; + u8 build; + u8 rsvd; +}; + +enum i40e_client_state { + __I40E_CLIENT_NULL, + __I40E_CLIENT_REGISTERED +}; + +enum i40e_client_instance_state { + __I40E_CLIENT_INSTANCE_NONE, + __I40E_CLIENT_INSTANCE_OPENED, +}; + +struct i40e_ops; +struct i40e_client; + +/* HW does not define a type value for AEQ; only for RX/TX and CEQ. + * In order for us to keep the interface simple, SW will define a + * unique type value for AEQ. + */ +#define I40E_QUEUE_TYPE_PE_AEQ 0x80 +#define I40E_QUEUE_INVALID_IDX 0xFFFF + +struct i40e_qv_info { + u32 v_idx; /* msix_vector */ + u16 ceq_idx; + u16 aeq_idx; + u8 itr_idx; +}; + +struct i40e_qvlist_info { + u32 num_vectors; + struct i40e_qv_info qv_info[1]; +}; + +#define I40E_CLIENT_MSIX_ALL 0xFFFFFFFF + +/* set of LAN parameters useful for clients managed by LAN */ + +/* Struct to hold per priority info */ +struct i40e_prio_qos_params { + u16 qs_handle; /* qs handle for prio */ + u8 tc; /* TC mapped to prio */ + u8 reserved; +}; + +#define I40E_CLIENT_MAX_USER_PRIORITY 8 +/* Struct to hold Client QoS */ +struct i40e_qos_params { + struct i40e_prio_qos_params prio_qos[I40E_CLIENT_MAX_USER_PRIORITY]; +}; + +struct i40e_params { + struct i40e_qos_params qos; + u16 mtu; + u16 link_up; /* boolean */ +}; + +/* Structure to hold LAN device info for a client device */ +struct i40e_info { + struct i40e_client_version version; + u8 lanmac[6]; + struct net_device *netdev; + struct pci_dev *pcidev; + u8 __iomem *hw_addr; + u8 fid; /* function id, PF id or VF id */ +#define I40E_CLIENT_FTYPE_PF 0 +#define I40E_CLIENT_FTYPE_VF 1 + u8 ftype; /* function type, PF or VF */ + void *vf; /* cast to iavf_adapter */ + + /* All L2 params that could change during the life span of the device + * and needs to be communicated to the client when they change + */ + struct i40e_params params; + struct i40e_ops *ops; + + u16 msix_count; /* number of msix vectors*/ + /* Array down below will be dynamically allocated based on msix_count */ + struct msix_entry *msix_entries; + u16 itr_index; /* Which ITR index the PE driver is suppose to use */ +}; + +struct i40e_ops { + /* setup_q_vector_list enables queues with a particular vector */ + int (*setup_qvlist)(struct i40e_info *ldev, struct i40e_client *client, + struct i40e_qvlist_info *qv_info); + + u32 (*virtchnl_send)(struct i40e_info *ldev, struct i40e_client *client, + u8 *msg, u16 len); + + /* If the PE Engine is unresponsive, RDMA driver can request a reset.*/ + void (*request_reset)(struct i40e_info *ldev, + struct i40e_client *client); +}; + +struct i40e_client_ops { + /* Should be called from register_client() or whenever the driver is + * ready to create a specific client instance. + */ + int (*open)(struct i40e_info *ldev, struct i40e_client *client); + + /* Should be closed when netdev is unavailable or when unregister + * call comes in. If the close happens due to a reset, set the reset + * bit to true. + */ + void (*close)(struct i40e_info *ldev, struct i40e_client *client, + bool reset); + + /* called when some l2 managed parameters changes - mss */ + void (*l2_param_change)(struct i40e_info *ldev, + struct i40e_client *client, + struct i40e_params *params); + + /* called when a message is received from the PF */ + int (*virtchnl_receive)(struct i40e_info *ldev, + struct i40e_client *client, + u8 *msg, u16 len); +}; + +/* Client device */ +struct i40e_client_instance { + struct list_head list; + struct i40e_info lan_info; + struct i40e_client *client; + unsigned long state; +}; + +struct i40e_client { + struct list_head list; /* list of registered clients */ + char name[IAVF_CLIENT_STR_LENGTH]; + struct i40e_client_version version; + unsigned long state; /* client state */ + atomic_t ref_cnt; /* Count of all the client devices of this kind */ + u32 flags; +#define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE BIT(0) +#define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS BIT(2) + u8 type; +#define I40E_CLIENT_IWARP 0 + struct i40e_client_ops *ops; /* client ops provided by the client */ +}; + +/* used by clients */ +int iavf_register_client(struct i40e_client *client); +int iavf_unregister_client(struct i40e_client *client); +#endif /* _IAVF_CLIENT_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_common.c b/drivers/net/ethernet/intel/iavf/iavf_common.c new file mode 100644 index 000000000000..768369c89e77 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_common.c @@ -0,0 +1,955 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#include "iavf_type.h" +#include "i40e_adminq.h" +#include "iavf_prototype.h" +#include <linux/avf/virtchnl.h> + +/** + * iavf_set_mac_type - Sets MAC type + * @hw: pointer to the HW structure + * + * This function sets the mac type of the adapter based on the + * vendor ID and device ID stored in the hw structure. + **/ +iavf_status iavf_set_mac_type(struct iavf_hw *hw) +{ + iavf_status status = 0; + + if (hw->vendor_id == PCI_VENDOR_ID_INTEL) { + switch (hw->device_id) { + case IAVF_DEV_ID_X722_VF: + hw->mac.type = IAVF_MAC_X722_VF; + break; + case IAVF_DEV_ID_VF: + case IAVF_DEV_ID_VF_HV: + case IAVF_DEV_ID_ADAPTIVE_VF: + hw->mac.type = IAVF_MAC_VF; + break; + default: + hw->mac.type = IAVF_MAC_GENERIC; + break; + } + } else { + status = I40E_ERR_DEVICE_NOT_SUPPORTED; + } + + hw_dbg(hw, "found mac: %d, returns: %d\n", hw->mac.type, status); + return status; +} + +/** + * iavf_aq_str - convert AQ err code to a string + * @hw: pointer to the HW structure + * @aq_err: the AQ error code to convert + **/ +const char *iavf_aq_str(struct iavf_hw *hw, enum i40e_admin_queue_err aq_err) +{ + switch (aq_err) { + case I40E_AQ_RC_OK: + return "OK"; + case I40E_AQ_RC_EPERM: + return "I40E_AQ_RC_EPERM"; + case I40E_AQ_RC_ENOENT: + return "I40E_AQ_RC_ENOENT"; + case I40E_AQ_RC_ESRCH: + return "I40E_AQ_RC_ESRCH"; + case I40E_AQ_RC_EINTR: + return "I40E_AQ_RC_EINTR"; + case I40E_AQ_RC_EIO: + return "I40E_AQ_RC_EIO"; + case I40E_AQ_RC_ENXIO: + return "I40E_AQ_RC_ENXIO"; + case I40E_AQ_RC_E2BIG: + return "I40E_AQ_RC_E2BIG"; + case I40E_AQ_RC_EAGAIN: + return "I40E_AQ_RC_EAGAIN"; + case I40E_AQ_RC_ENOMEM: + return "I40E_AQ_RC_ENOMEM"; + case I40E_AQ_RC_EACCES: + return "I40E_AQ_RC_EACCES"; + case I40E_AQ_RC_EFAULT: + return "I40E_AQ_RC_EFAULT"; + case I40E_AQ_RC_EBUSY: + return "I40E_AQ_RC_EBUSY"; + case I40E_AQ_RC_EEXIST: + return "I40E_AQ_RC_EEXIST"; + case I40E_AQ_RC_EINVAL: + return "I40E_AQ_RC_EINVAL"; + case I40E_AQ_RC_ENOTTY: + return "I40E_AQ_RC_ENOTTY"; + case I40E_AQ_RC_ENOSPC: + return "I40E_AQ_RC_ENOSPC"; + case I40E_AQ_RC_ENOSYS: + return "I40E_AQ_RC_ENOSYS"; + case I40E_AQ_RC_ERANGE: + return "I40E_AQ_RC_ERANGE"; + case I40E_AQ_RC_EFLUSHED: + return "I40E_AQ_RC_EFLUSHED"; + case I40E_AQ_RC_BAD_ADDR: + return "I40E_AQ_RC_BAD_ADDR"; + case I40E_AQ_RC_EMODE: + return "I40E_AQ_RC_EMODE"; + case I40E_AQ_RC_EFBIG: + return "I40E_AQ_RC_EFBIG"; + } + + snprintf(hw->err_str, sizeof(hw->err_str), "%d", aq_err); + return hw->err_str; +} + +/** + * iavf_stat_str - convert status err code to a string + * @hw: pointer to the HW structure + * @stat_err: the status error code to convert + **/ +const char *iavf_stat_str(struct iavf_hw *hw, iavf_status stat_err) +{ + switch (stat_err) { + case 0: + return "OK"; + case I40E_ERR_NVM: + return "I40E_ERR_NVM"; + case I40E_ERR_NVM_CHECKSUM: + return "I40E_ERR_NVM_CHECKSUM"; + case I40E_ERR_PHY: + return "I40E_ERR_PHY"; + case I40E_ERR_CONFIG: + return "I40E_ERR_CONFIG"; + case I40E_ERR_PARAM: + return "I40E_ERR_PARAM"; + case I40E_ERR_MAC_TYPE: + return "I40E_ERR_MAC_TYPE"; + case I40E_ERR_UNKNOWN_PHY: + return "I40E_ERR_UNKNOWN_PHY"; + case I40E_ERR_LINK_SETUP: + return "I40E_ERR_LINK_SETUP"; + case I40E_ERR_ADAPTER_STOPPED: + return "I40E_ERR_ADAPTER_STOPPED"; + case I40E_ERR_INVALID_MAC_ADDR: + return "I40E_ERR_INVALID_MAC_ADDR"; + case I40E_ERR_DEVICE_NOT_SUPPORTED: + return "I40E_ERR_DEVICE_NOT_SUPPORTED"; + case I40E_ERR_MASTER_REQUESTS_PENDING: + return "I40E_ERR_MASTER_REQUESTS_PENDING"; + case I40E_ERR_INVALID_LINK_SETTINGS: + return "I40E_ERR_INVALID_LINK_SETTINGS"; + case I40E_ERR_AUTONEG_NOT_COMPLETE: + return "I40E_ERR_AUTONEG_NOT_COMPLETE"; + case I40E_ERR_RESET_FAILED: + return "I40E_ERR_RESET_FAILED"; + case I40E_ERR_SWFW_SYNC: + return "I40E_ERR_SWFW_SYNC"; + case I40E_ERR_NO_AVAILABLE_VSI: + return "I40E_ERR_NO_AVAILABLE_VSI"; + case I40E_ERR_NO_MEMORY: + return "I40E_ERR_NO_MEMORY"; + case I40E_ERR_BAD_PTR: + return "I40E_ERR_BAD_PTR"; + case I40E_ERR_RING_FULL: + return "I40E_ERR_RING_FULL"; + case I40E_ERR_INVALID_PD_ID: + return "I40E_ERR_INVALID_PD_ID"; + case I40E_ERR_INVALID_QP_ID: + return "I40E_ERR_INVALID_QP_ID"; + case I40E_ERR_INVALID_CQ_ID: + return "I40E_ERR_INVALID_CQ_ID"; + case I40E_ERR_INVALID_CEQ_ID: + return "I40E_ERR_INVALID_CEQ_ID"; + case I40E_ERR_INVALID_AEQ_ID: + return "I40E_ERR_INVALID_AEQ_ID"; + case I40E_ERR_INVALID_SIZE: + return "I40E_ERR_INVALID_SIZE"; + case I40E_ERR_INVALID_ARP_INDEX: + return "I40E_ERR_INVALID_ARP_INDEX"; + case I40E_ERR_INVALID_FPM_FUNC_ID: + return "I40E_ERR_INVALID_FPM_FUNC_ID"; + case I40E_ERR_QP_INVALID_MSG_SIZE: + return "I40E_ERR_QP_INVALID_MSG_SIZE"; + case I40E_ERR_QP_TOOMANY_WRS_POSTED: + return "I40E_ERR_QP_TOOMANY_WRS_POSTED"; + case I40E_ERR_INVALID_FRAG_COUNT: + return "I40E_ERR_INVALID_FRAG_COUNT"; + case I40E_ERR_QUEUE_EMPTY: + return "I40E_ERR_QUEUE_EMPTY"; + case I40E_ERR_INVALID_ALIGNMENT: + return "I40E_ERR_INVALID_ALIGNMENT"; + case I40E_ERR_FLUSHED_QUEUE: + return "I40E_ERR_FLUSHED_QUEUE"; + case I40E_ERR_INVALID_PUSH_PAGE_INDEX: + return "I40E_ERR_INVALID_PUSH_PAGE_INDEX"; + case I40E_ERR_INVALID_IMM_DATA_SIZE: + return "I40E_ERR_INVALID_IMM_DATA_SIZE"; + case I40E_ERR_TIMEOUT: + return "I40E_ERR_TIMEOUT"; + case I40E_ERR_OPCODE_MISMATCH: + return "I40E_ERR_OPCODE_MISMATCH"; + case I40E_ERR_CQP_COMPL_ERROR: + return "I40E_ERR_CQP_COMPL_ERROR"; + case I40E_ERR_INVALID_VF_ID: + return "I40E_ERR_INVALID_VF_ID"; + case I40E_ERR_INVALID_HMCFN_ID: + return "I40E_ERR_INVALID_HMCFN_ID"; + case I40E_ERR_BACKING_PAGE_ERROR: + return "I40E_ERR_BACKING_PAGE_ERROR"; + case I40E_ERR_NO_PBLCHUNKS_AVAILABLE: + return "I40E_ERR_NO_PBLCHUNKS_AVAILABLE"; + case I40E_ERR_INVALID_PBLE_INDEX: + return "I40E_ERR_INVALID_PBLE_INDEX"; + case I40E_ERR_INVALID_SD_INDEX: + return "I40E_ERR_INVALID_SD_INDEX"; + case I40E_ERR_INVALID_PAGE_DESC_INDEX: + return "I40E_ERR_INVALID_PAGE_DESC_INDEX"; + case I40E_ERR_INVALID_SD_TYPE: + return "I40E_ERR_INVALID_SD_TYPE"; + case I40E_ERR_MEMCPY_FAILED: + return "I40E_ERR_MEMCPY_FAILED"; + case I40E_ERR_INVALID_HMC_OBJ_INDEX: + return "I40E_ERR_INVALID_HMC_OBJ_INDEX"; + case I40E_ERR_INVALID_HMC_OBJ_COUNT: + return "I40E_ERR_INVALID_HMC_OBJ_COUNT"; + case I40E_ERR_INVALID_SRQ_ARM_LIMIT: + return "I40E_ERR_INVALID_SRQ_ARM_LIMIT"; + case I40E_ERR_SRQ_ENABLED: + return "I40E_ERR_SRQ_ENABLED"; + case I40E_ERR_ADMIN_QUEUE_ERROR: + return "I40E_ERR_ADMIN_QUEUE_ERROR"; + case I40E_ERR_ADMIN_QUEUE_TIMEOUT: + return "I40E_ERR_ADMIN_QUEUE_TIMEOUT"; + case I40E_ERR_BUF_TOO_SHORT: + return "I40E_ERR_BUF_TOO_SHORT"; + case I40E_ERR_ADMIN_QUEUE_FULL: + return "I40E_ERR_ADMIN_QUEUE_FULL"; + case I40E_ERR_ADMIN_QUEUE_NO_WORK: + return "I40E_ERR_ADMIN_QUEUE_NO_WORK"; + case I40E_ERR_BAD_IWARP_CQE: + return "I40E_ERR_BAD_IWARP_CQE"; + case I40E_ERR_NVM_BLANK_MODE: + return "I40E_ERR_NVM_BLANK_MODE"; + case I40E_ERR_NOT_IMPLEMENTED: + return "I40E_ERR_NOT_IMPLEMENTED"; + case I40E_ERR_PE_DOORBELL_NOT_ENABLED: + return "I40E_ERR_PE_DOORBELL_NOT_ENABLED"; + case I40E_ERR_DIAG_TEST_FAILED: + return "I40E_ERR_DIAG_TEST_FAILED"; + case I40E_ERR_NOT_READY: + return "I40E_ERR_NOT_READY"; + case I40E_NOT_SUPPORTED: + return "I40E_NOT_SUPPORTED"; + case I40E_ERR_FIRMWARE_API_VERSION: + return "I40E_ERR_FIRMWARE_API_VERSION"; + case I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR: + return "I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR"; + } + + snprintf(hw->err_str, sizeof(hw->err_str), "%d", stat_err); + return hw->err_str; +} + +/** + * iavf_debug_aq + * @hw: debug mask related to admin queue + * @mask: debug mask + * @desc: pointer to admin queue descriptor + * @buffer: pointer to command buffer + * @buf_len: max length of buffer + * + * Dumps debug log about adminq command with descriptor contents. + **/ +void iavf_debug_aq(struct iavf_hw *hw, enum iavf_debug_mask mask, void *desc, + void *buffer, u16 buf_len) +{ + struct i40e_aq_desc *aq_desc = (struct i40e_aq_desc *)desc; + u8 *buf = (u8 *)buffer; + + if ((!(mask & hw->debug_mask)) || !desc) + return; + + iavf_debug(hw, mask, + "AQ CMD: opcode 0x%04X, flags 0x%04X, datalen 0x%04X, retval 0x%04X\n", + le16_to_cpu(aq_desc->opcode), + le16_to_cpu(aq_desc->flags), + le16_to_cpu(aq_desc->datalen), + le16_to_cpu(aq_desc->retval)); + iavf_debug(hw, mask, "\tcookie (h,l) 0x%08X 0x%08X\n", + le32_to_cpu(aq_desc->cookie_high), + le32_to_cpu(aq_desc->cookie_low)); + iavf_debug(hw, mask, "\tparam (0,1) 0x%08X 0x%08X\n", + le32_to_cpu(aq_desc->params.internal.param0), + le32_to_cpu(aq_desc->params.internal.param1)); + iavf_debug(hw, mask, "\taddr (h,l) 0x%08X 0x%08X\n", + le32_to_cpu(aq_desc->params.external.addr_high), + le32_to_cpu(aq_desc->params.external.addr_low)); + + if (buffer && aq_desc->datalen) { + u16 len = le16_to_cpu(aq_desc->datalen); + + iavf_debug(hw, mask, "AQ CMD Buffer:\n"); + if (buf_len < len) + len = buf_len; + /* write the full 16-byte chunks */ + if (hw->debug_mask & mask) { + char prefix[27]; + + snprintf(prefix, sizeof(prefix), + "iavf %02x:%02x.%x: \t0x", + hw->bus.bus_id, + hw->bus.device, + hw->bus.func); + + print_hex_dump(KERN_INFO, prefix, DUMP_PREFIX_OFFSET, + 16, 1, buf, len, false); + } + } +} + +/** + * iavf_check_asq_alive + * @hw: pointer to the hw struct + * + * Returns true if Queue is enabled else false. + **/ +bool iavf_check_asq_alive(struct iavf_hw *hw) +{ + if (hw->aq.asq.len) + return !!(rd32(hw, hw->aq.asq.len) & + IAVF_VF_ATQLEN1_ATQENABLE_MASK); + else + return false; +} + +/** + * iavf_aq_queue_shutdown + * @hw: pointer to the hw struct + * @unloading: is the driver unloading itself + * + * Tell the Firmware that we're shutting down the AdminQ and whether + * or not the driver is unloading as well. + **/ +iavf_status iavf_aq_queue_shutdown(struct iavf_hw *hw, bool unloading) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_queue_shutdown *cmd = + (struct i40e_aqc_queue_shutdown *)&desc.params.raw; + iavf_status status; + + iavf_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_queue_shutdown); + + if (unloading) + cmd->driver_unloading = cpu_to_le32(I40E_AQ_DRIVER_UNLOADING); + status = iavf_asq_send_command(hw, &desc, NULL, 0, NULL); + + return status; +} + +/** + * iavf_aq_get_set_rss_lut + * @hw: pointer to the hardware structure + * @vsi_id: vsi fw index + * @pf_lut: for PF table set true, for VSI table set false + * @lut: pointer to the lut buffer provided by the caller + * @lut_size: size of the lut buffer + * @set: set true to set the table, false to get the table + * + * Internal function to get or set RSS look up table + **/ +static iavf_status iavf_aq_get_set_rss_lut(struct iavf_hw *hw, + u16 vsi_id, bool pf_lut, + u8 *lut, u16 lut_size, + bool set) +{ + iavf_status status; + struct i40e_aq_desc desc; + struct i40e_aqc_get_set_rss_lut *cmd_resp = + (struct i40e_aqc_get_set_rss_lut *)&desc.params.raw; + + if (set) + iavf_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_set_rss_lut); + else + iavf_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_get_rss_lut); + + /* Indirect command */ + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD); + + cmd_resp->vsi_id = + cpu_to_le16((u16)((vsi_id << + I40E_AQC_SET_RSS_LUT_VSI_ID_SHIFT) & + I40E_AQC_SET_RSS_LUT_VSI_ID_MASK)); + cmd_resp->vsi_id |= cpu_to_le16((u16)I40E_AQC_SET_RSS_LUT_VSI_VALID); + + if (pf_lut) + cmd_resp->flags |= cpu_to_le16((u16) + ((I40E_AQC_SET_RSS_LUT_TABLE_TYPE_PF << + I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) & + I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK)); + else + cmd_resp->flags |= cpu_to_le16((u16) + ((I40E_AQC_SET_RSS_LUT_TABLE_TYPE_VSI << + I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) & + I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK)); + + status = iavf_asq_send_command(hw, &desc, lut, lut_size, NULL); + + return status; +} + +/** + * iavf_aq_get_rss_lut + * @hw: pointer to the hardware structure + * @vsi_id: vsi fw index + * @pf_lut: for PF table set true, for VSI table set false + * @lut: pointer to the lut buffer provided by the caller + * @lut_size: size of the lut buffer + * + * get the RSS lookup table, PF or VSI type + **/ +iavf_status iavf_aq_get_rss_lut(struct iavf_hw *hw, u16 vsi_id, + bool pf_lut, u8 *lut, u16 lut_size) +{ + return iavf_aq_get_set_rss_lut(hw, vsi_id, pf_lut, lut, lut_size, + false); +} + +/** + * iavf_aq_set_rss_lut + * @hw: pointer to the hardware structure + * @vsi_id: vsi fw index + * @pf_lut: for PF table set true, for VSI table set false + * @lut: pointer to the lut buffer provided by the caller + * @lut_size: size of the lut buffer + * + * set the RSS lookup table, PF or VSI type + **/ +iavf_status iavf_aq_set_rss_lut(struct iavf_hw *hw, u16 vsi_id, + bool pf_lut, u8 *lut, u16 lut_size) +{ + return iavf_aq_get_set_rss_lut(hw, vsi_id, pf_lut, lut, lut_size, true); +} + +/** + * iavf_aq_get_set_rss_key + * @hw: pointer to the hw struct + * @vsi_id: vsi fw index + * @key: pointer to key info struct + * @set: set true to set the key, false to get the key + * + * get the RSS key per VSI + **/ +static +iavf_status iavf_aq_get_set_rss_key(struct iavf_hw *hw, u16 vsi_id, + struct i40e_aqc_get_set_rss_key_data *key, + bool set) +{ + iavf_status status; + struct i40e_aq_desc desc; + struct i40e_aqc_get_set_rss_key *cmd_resp = + (struct i40e_aqc_get_set_rss_key *)&desc.params.raw; + u16 key_size = sizeof(struct i40e_aqc_get_set_rss_key_data); + + if (set) + iavf_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_set_rss_key); + else + iavf_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_get_rss_key); + + /* Indirect command */ + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD); + + cmd_resp->vsi_id = + cpu_to_le16((u16)((vsi_id << + I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT) & + I40E_AQC_SET_RSS_KEY_VSI_ID_MASK)); + cmd_resp->vsi_id |= cpu_to_le16((u16)I40E_AQC_SET_RSS_KEY_VSI_VALID); + + status = iavf_asq_send_command(hw, &desc, key, key_size, NULL); + + return status; +} + +/** + * iavf_aq_get_rss_key + * @hw: pointer to the hw struct + * @vsi_id: vsi fw index + * @key: pointer to key info struct + * + **/ +iavf_status iavf_aq_get_rss_key(struct iavf_hw *hw, u16 vsi_id, + struct i40e_aqc_get_set_rss_key_data *key) +{ + return iavf_aq_get_set_rss_key(hw, vsi_id, key, false); +} + +/** + * iavf_aq_set_rss_key + * @hw: pointer to the hw struct + * @vsi_id: vsi fw index + * @key: pointer to key info struct + * + * set the RSS key per VSI + **/ +iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 vsi_id, + struct i40e_aqc_get_set_rss_key_data *key) +{ + return iavf_aq_get_set_rss_key(hw, vsi_id, key, true); +} + +/* The iavf_ptype_lookup table is used to convert from the 8-bit ptype in the + * hardware to a bit-field that can be used by SW to more easily determine the + * packet type. + * + * Macros are used to shorten the table lines and make this table human + * readable. + * + * We store the PTYPE in the top byte of the bit field - this is just so that + * we can check that the table doesn't have a row missing, as the index into + * the table should be the PTYPE. + * + * Typical work flow: + * + * IF NOT iavf_ptype_lookup[ptype].known + * THEN + * Packet is unknown + * ELSE IF iavf_ptype_lookup[ptype].outer_ip == I40E_RX_PTYPE_OUTER_IP + * Use the rest of the fields to look at the tunnels, inner protocols, etc + * ELSE + * Use the enum iavf_rx_l2_ptype to decode the packet type + * ENDIF + */ + +/* macro to make the table lines short */ +#define IAVF_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\ + { PTYPE, \ + 1, \ + IAVF_RX_PTYPE_OUTER_##OUTER_IP, \ + IAVF_RX_PTYPE_OUTER_##OUTER_IP_VER, \ + IAVF_RX_PTYPE_##OUTER_FRAG, \ + IAVF_RX_PTYPE_TUNNEL_##T, \ + IAVF_RX_PTYPE_TUNNEL_END_##TE, \ + IAVF_RX_PTYPE_##TEF, \ + IAVF_RX_PTYPE_INNER_PROT_##I, \ + IAVF_RX_PTYPE_PAYLOAD_LAYER_##PL } + +#define IAVF_PTT_UNUSED_ENTRY(PTYPE) \ + { PTYPE, 0, 0, 0, 0, 0, 0, 0, 0, 0 } + +/* shorter macros makes the table fit but are terse */ +#define IAVF_RX_PTYPE_NOF IAVF_RX_PTYPE_NOT_FRAG +#define IAVF_RX_PTYPE_FRG IAVF_RX_PTYPE_FRAG +#define IAVF_RX_PTYPE_INNER_PROT_TS IAVF_RX_PTYPE_INNER_PROT_TIMESYNC + +/* Lookup table mapping the HW PTYPE to the bit field for decoding */ +struct iavf_rx_ptype_decoded iavf_ptype_lookup[] = { + /* L2 Packet types */ + IAVF_PTT_UNUSED_ENTRY(0), + IAVF_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + IAVF_PTT(2, L2, NONE, NOF, NONE, NONE, NOF, TS, PAY2), + IAVF_PTT(3, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + IAVF_PTT_UNUSED_ENTRY(4), + IAVF_PTT_UNUSED_ENTRY(5), + IAVF_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + IAVF_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + IAVF_PTT_UNUSED_ENTRY(8), + IAVF_PTT_UNUSED_ENTRY(9), + IAVF_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + IAVF_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), + IAVF_PTT(12, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(13, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(14, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(15, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(16, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(17, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(18, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(19, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(20, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(21, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + + /* Non Tunneled IPv4 */ + IAVF_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(25), + IAVF_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP, PAY4), + IAVF_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4), + IAVF_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4), + + /* IPv4 --> IPv4 */ + IAVF_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3), + IAVF_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3), + IAVF_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(32), + IAVF_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP, PAY4), + IAVF_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), + + /* IPv4 --> IPv6 */ + IAVF_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3), + IAVF_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3), + IAVF_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(39), + IAVF_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP, PAY4), + IAVF_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT */ + IAVF_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), + + /* IPv4 --> GRE/NAT --> IPv4 */ + IAVF_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), + IAVF_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), + IAVF_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(47), + IAVF_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), + IAVF_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT --> IPv6 */ + IAVF_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), + IAVF_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), + IAVF_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(54), + IAVF_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), + IAVF_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT --> MAC */ + IAVF_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), + + /* IPv4 --> GRE/NAT --> MAC --> IPv4 */ + IAVF_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), + IAVF_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), + IAVF_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(62), + IAVF_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), + IAVF_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT -> MAC --> IPv6 */ + IAVF_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), + IAVF_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), + IAVF_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(69), + IAVF_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), + IAVF_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT --> MAC/VLAN */ + IAVF_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), + + /* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */ + IAVF_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), + IAVF_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), + IAVF_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(77), + IAVF_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), + IAVF_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), + + /* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */ + IAVF_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), + IAVF_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), + IAVF_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(84), + IAVF_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), + IAVF_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), + + /* Non Tunneled IPv6 */ + IAVF_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY3), + IAVF_PTT_UNUSED_ENTRY(91), + IAVF_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP, PAY4), + IAVF_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4), + IAVF_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4), + + /* IPv6 --> IPv4 */ + IAVF_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3), + IAVF_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3), + IAVF_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(98), + IAVF_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP, PAY4), + IAVF_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> IPv6 */ + IAVF_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3), + IAVF_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3), + IAVF_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(105), + IAVF_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP, PAY4), + IAVF_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT */ + IAVF_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), + + /* IPv6 --> GRE/NAT -> IPv4 */ + IAVF_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), + IAVF_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), + IAVF_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(113), + IAVF_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), + IAVF_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> IPv6 */ + IAVF_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), + IAVF_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), + IAVF_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(120), + IAVF_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), + IAVF_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC */ + IAVF_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), + + /* IPv6 --> GRE/NAT -> MAC -> IPv4 */ + IAVF_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), + IAVF_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), + IAVF_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(128), + IAVF_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), + IAVF_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC -> IPv6 */ + IAVF_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), + IAVF_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), + IAVF_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(135), + IAVF_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), + IAVF_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC/VLAN */ + IAVF_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), + + /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */ + IAVF_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), + IAVF_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), + IAVF_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(143), + IAVF_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), + IAVF_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */ + IAVF_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), + IAVF_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), + IAVF_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(150), + IAVF_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), + IAVF_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), + + /* unused entries */ + IAVF_PTT_UNUSED_ENTRY(154), + IAVF_PTT_UNUSED_ENTRY(155), + IAVF_PTT_UNUSED_ENTRY(156), + IAVF_PTT_UNUSED_ENTRY(157), + IAVF_PTT_UNUSED_ENTRY(158), + IAVF_PTT_UNUSED_ENTRY(159), + + IAVF_PTT_UNUSED_ENTRY(160), + IAVF_PTT_UNUSED_ENTRY(161), + IAVF_PTT_UNUSED_ENTRY(162), + IAVF_PTT_UNUSED_ENTRY(163), + IAVF_PTT_UNUSED_ENTRY(164), + IAVF_PTT_UNUSED_ENTRY(165), + IAVF_PTT_UNUSED_ENTRY(166), + IAVF_PTT_UNUSED_ENTRY(167), + IAVF_PTT_UNUSED_ENTRY(168), + IAVF_PTT_UNUSED_ENTRY(169), + + IAVF_PTT_UNUSED_ENTRY(170), + IAVF_PTT_UNUSED_ENTRY(171), + IAVF_PTT_UNUSED_ENTRY(172), + IAVF_PTT_UNUSED_ENTRY(173), + IAVF_PTT_UNUSED_ENTRY(174), + IAVF_PTT_UNUSED_ENTRY(175), + IAVF_PTT_UNUSED_ENTRY(176), + IAVF_PTT_UNUSED_ENTRY(177), + IAVF_PTT_UNUSED_ENTRY(178), + IAVF_PTT_UNUSED_ENTRY(179), + + IAVF_PTT_UNUSED_ENTRY(180), + IAVF_PTT_UNUSED_ENTRY(181), + IAVF_PTT_UNUSED_ENTRY(182), + IAVF_PTT_UNUSED_ENTRY(183), + IAVF_PTT_UNUSED_ENTRY(184), + IAVF_PTT_UNUSED_ENTRY(185), + IAVF_PTT_UNUSED_ENTRY(186), + IAVF_PTT_UNUSED_ENTRY(187), + IAVF_PTT_UNUSED_ENTRY(188), + IAVF_PTT_UNUSED_ENTRY(189), + + IAVF_PTT_UNUSED_ENTRY(190), + IAVF_PTT_UNUSED_ENTRY(191), + IAVF_PTT_UNUSED_ENTRY(192), + IAVF_PTT_UNUSED_ENTRY(193), + IAVF_PTT_UNUSED_ENTRY(194), + IAVF_PTT_UNUSED_ENTRY(195), + IAVF_PTT_UNUSED_ENTRY(196), + IAVF_PTT_UNUSED_ENTRY(197), + IAVF_PTT_UNUSED_ENTRY(198), + IAVF_PTT_UNUSED_ENTRY(199), + + IAVF_PTT_UNUSED_ENTRY(200), + IAVF_PTT_UNUSED_ENTRY(201), + IAVF_PTT_UNUSED_ENTRY(202), + IAVF_PTT_UNUSED_ENTRY(203), + IAVF_PTT_UNUSED_ENTRY(204), + IAVF_PTT_UNUSED_ENTRY(205), + IAVF_PTT_UNUSED_ENTRY(206), + IAVF_PTT_UNUSED_ENTRY(207), + IAVF_PTT_UNUSED_ENTRY(208), + IAVF_PTT_UNUSED_ENTRY(209), + + IAVF_PTT_UNUSED_ENTRY(210), + IAVF_PTT_UNUSED_ENTRY(211), + IAVF_PTT_UNUSED_ENTRY(212), + IAVF_PTT_UNUSED_ENTRY(213), + IAVF_PTT_UNUSED_ENTRY(214), + IAVF_PTT_UNUSED_ENTRY(215), + IAVF_PTT_UNUSED_ENTRY(216), + IAVF_PTT_UNUSED_ENTRY(217), + IAVF_PTT_UNUSED_ENTRY(218), + IAVF_PTT_UNUSED_ENTRY(219), + + IAVF_PTT_UNUSED_ENTRY(220), + IAVF_PTT_UNUSED_ENTRY(221), + IAVF_PTT_UNUSED_ENTRY(222), + IAVF_PTT_UNUSED_ENTRY(223), + IAVF_PTT_UNUSED_ENTRY(224), + IAVF_PTT_UNUSED_ENTRY(225), + IAVF_PTT_UNUSED_ENTRY(226), + IAVF_PTT_UNUSED_ENTRY(227), + IAVF_PTT_UNUSED_ENTRY(228), + IAVF_PTT_UNUSED_ENTRY(229), + + IAVF_PTT_UNUSED_ENTRY(230), + IAVF_PTT_UNUSED_ENTRY(231), + IAVF_PTT_UNUSED_ENTRY(232), + IAVF_PTT_UNUSED_ENTRY(233), + IAVF_PTT_UNUSED_ENTRY(234), + IAVF_PTT_UNUSED_ENTRY(235), + IAVF_PTT_UNUSED_ENTRY(236), + IAVF_PTT_UNUSED_ENTRY(237), + IAVF_PTT_UNUSED_ENTRY(238), + IAVF_PTT_UNUSED_ENTRY(239), + + IAVF_PTT_UNUSED_ENTRY(240), + IAVF_PTT_UNUSED_ENTRY(241), + IAVF_PTT_UNUSED_ENTRY(242), + IAVF_PTT_UNUSED_ENTRY(243), + IAVF_PTT_UNUSED_ENTRY(244), + IAVF_PTT_UNUSED_ENTRY(245), + IAVF_PTT_UNUSED_ENTRY(246), + IAVF_PTT_UNUSED_ENTRY(247), + IAVF_PTT_UNUSED_ENTRY(248), + IAVF_PTT_UNUSED_ENTRY(249), + + IAVF_PTT_UNUSED_ENTRY(250), + IAVF_PTT_UNUSED_ENTRY(251), + IAVF_PTT_UNUSED_ENTRY(252), + IAVF_PTT_UNUSED_ENTRY(253), + IAVF_PTT_UNUSED_ENTRY(254), + IAVF_PTT_UNUSED_ENTRY(255) +}; + +/** + * iavf_aq_send_msg_to_pf + * @hw: pointer to the hardware structure + * @v_opcode: opcodes for VF-PF communication + * @v_retval: return error code + * @msg: pointer to the msg buffer + * @msglen: msg length + * @cmd_details: pointer to command details + * + * Send message to PF driver using admin queue. By default, this message + * is sent asynchronously, i.e. iavf_asq_send_command() does not wait for + * completion before returning. + **/ +iavf_status iavf_aq_send_msg_to_pf(struct iavf_hw *hw, + enum virtchnl_ops v_opcode, + iavf_status v_retval, u8 *msg, u16 msglen, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_asq_cmd_details details; + struct i40e_aq_desc desc; + iavf_status status; + + iavf_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_send_msg_to_pf); + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_SI); + desc.cookie_high = cpu_to_le32(v_opcode); + desc.cookie_low = cpu_to_le32(v_retval); + if (msglen) { + desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF + | I40E_AQ_FLAG_RD)); + if (msglen > I40E_AQ_LARGE_BUF) + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); + desc.datalen = cpu_to_le16(msglen); + } + if (!cmd_details) { + memset(&details, 0, sizeof(details)); + details.async = true; + cmd_details = &details; + } + status = iavf_asq_send_command(hw, &desc, msg, msglen, cmd_details); + return status; +} + +/** + * iavf_vf_parse_hw_config + * @hw: pointer to the hardware structure + * @msg: pointer to the virtual channel VF resource structure + * + * Given a VF resource message from the PF, populate the hw struct + * with appropriate information. + **/ +void iavf_vf_parse_hw_config(struct iavf_hw *hw, + struct virtchnl_vf_resource *msg) +{ + struct virtchnl_vsi_resource *vsi_res; + int i; + + vsi_res = &msg->vsi_res[0]; + + hw->dev_caps.num_vsis = msg->num_vsis; + hw->dev_caps.num_rx_qp = msg->num_queue_pairs; + hw->dev_caps.num_tx_qp = msg->num_queue_pairs; + hw->dev_caps.num_msix_vectors_vf = msg->max_vectors; + hw->dev_caps.dcb = msg->vf_cap_flags & + VIRTCHNL_VF_OFFLOAD_L2; + hw->dev_caps.fcoe = 0; + for (i = 0; i < msg->num_vsis; i++) { + if (vsi_res->vsi_type == VIRTCHNL_VSI_SRIOV) { + ether_addr_copy(hw->mac.perm_addr, + vsi_res->default_mac_addr); + ether_addr_copy(hw->mac.addr, + vsi_res->default_mac_addr); + } + vsi_res++; + } +} + +/** + * iavf_vf_reset + * @hw: pointer to the hardware structure + * + * Send a VF_RESET message to the PF. Does not wait for response from PF + * as none will be forthcoming. Immediately after calling this function, + * the admin queue should be shut down and (optionally) reinitialized. + **/ +iavf_status iavf_vf_reset(struct iavf_hw *hw) +{ + return iavf_aq_send_msg_to_pf(hw, VIRTCHNL_OP_RESET_VF, + 0, NULL, 0, NULL); +} diff --git a/drivers/net/ethernet/intel/iavf/iavf_devids.h b/drivers/net/ethernet/intel/iavf/iavf_devids.h new file mode 100644 index 000000000000..8eb7b697e96c --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_devids.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _IAVF_DEVIDS_H_ +#define _IAVF_DEVIDS_H_ + +/* Device IDs for the VF driver */ +#define IAVF_DEV_ID_VF 0x154C +#define IAVF_DEV_ID_VF_HV 0x1571 +#define IAVF_DEV_ID_ADAPTIVE_VF 0x1889 +#define IAVF_DEV_ID_X722_VF 0x37CD +#endif /* _IAVF_DEVIDS_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c new file mode 100644 index 000000000000..9f87304109fe --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -0,0 +1,1036 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +/* ethtool support for iavf */ +#include "iavf.h" + +#include <linux/uaccess.h> + +/* ethtool statistics helpers */ + +/** + * struct iavf_stats - definition for an ethtool statistic + * @stat_string: statistic name to display in ethtool -S output + * @sizeof_stat: the sizeof() the stat, must be no greater than sizeof(u64) + * @stat_offset: offsetof() the stat from a base pointer + * + * This structure defines a statistic to be added to the ethtool stats buffer. + * It defines a statistic as offset from a common base pointer. Stats should + * be defined in constant arrays using the IAVF_STAT macro, with every element + * of the array using the same _type for calculating the sizeof_stat and + * stat_offset. + * + * The @sizeof_stat is expected to be sizeof(u8), sizeof(u16), sizeof(u32) or + * sizeof(u64). Other sizes are not expected and will produce a WARN_ONCE from + * the iavf_add_ethtool_stat() helper function. + * + * The @stat_string is interpreted as a format string, allowing formatted + * values to be inserted while looping over multiple structures for a given + * statistics array. Thus, every statistic string in an array should have the + * same type and number of format specifiers, to be formatted by variadic + * arguments to the iavf_add_stat_string() helper function. + **/ +struct iavf_stats { + char stat_string[ETH_GSTRING_LEN]; + int sizeof_stat; + int stat_offset; +}; + +/* Helper macro to define an iavf_stat structure with proper size and type. + * Use this when defining constant statistics arrays. Note that @_type expects + * only a type name and is used multiple times. + */ +#define IAVF_STAT(_type, _name, _stat) { \ + .stat_string = _name, \ + .sizeof_stat = FIELD_SIZEOF(_type, _stat), \ + .stat_offset = offsetof(_type, _stat) \ +} + +/* Helper macro for defining some statistics related to queues */ +#define IAVF_QUEUE_STAT(_name, _stat) \ + IAVF_STAT(struct iavf_ring, _name, _stat) + +/* Stats associated with a Tx or Rx ring */ +static const struct iavf_stats iavf_gstrings_queue_stats[] = { + IAVF_QUEUE_STAT("%s-%u.packets", stats.packets), + IAVF_QUEUE_STAT("%s-%u.bytes", stats.bytes), +}; + +/** + * iavf_add_one_ethtool_stat - copy the stat into the supplied buffer + * @data: location to store the stat value + * @pointer: basis for where to copy from + * @stat: the stat definition + * + * Copies the stat data defined by the pointer and stat structure pair into + * the memory supplied as data. Used to implement iavf_add_ethtool_stats and + * iavf_add_queue_stats. If the pointer is null, data will be zero'd. + */ +static void +iavf_add_one_ethtool_stat(u64 *data, void *pointer, + const struct iavf_stats *stat) +{ + char *p; + + if (!pointer) { + /* ensure that the ethtool data buffer is zero'd for any stats + * which don't have a valid pointer. + */ + *data = 0; + return; + } + + p = (char *)pointer + stat->stat_offset; + switch (stat->sizeof_stat) { + case sizeof(u64): + *data = *((u64 *)p); + break; + case sizeof(u32): + *data = *((u32 *)p); + break; + case sizeof(u16): + *data = *((u16 *)p); + break; + case sizeof(u8): + *data = *((u8 *)p); + break; + default: + WARN_ONCE(1, "unexpected stat size for %s", + stat->stat_string); + *data = 0; + } +} + +/** + * __iavf_add_ethtool_stats - copy stats into the ethtool supplied buffer + * @data: ethtool stats buffer + * @pointer: location to copy stats from + * @stats: array of stats to copy + * @size: the size of the stats definition + * + * Copy the stats defined by the stats array using the pointer as a base into + * the data buffer supplied by ethtool. Updates the data pointer to point to + * the next empty location for successive calls to __iavf_add_ethtool_stats. + * If pointer is null, set the data values to zero and update the pointer to + * skip these stats. + **/ +static void +__iavf_add_ethtool_stats(u64 **data, void *pointer, + const struct iavf_stats stats[], + const unsigned int size) +{ + unsigned int i; + + for (i = 0; i < size; i++) + iavf_add_one_ethtool_stat((*data)++, pointer, &stats[i]); +} + +/** + * iavf_add_ethtool_stats - copy stats into ethtool supplied buffer + * @data: ethtool stats buffer + * @pointer: location where stats are stored + * @stats: static const array of stat definitions + * + * Macro to ease the use of __iavf_add_ethtool_stats by taking a static + * constant stats array and passing the ARRAY_SIZE(). This avoids typos by + * ensuring that we pass the size associated with the given stats array. + * + * The parameter @stats is evaluated twice, so parameters with side effects + * should be avoided. + **/ +#define iavf_add_ethtool_stats(data, pointer, stats) \ + __iavf_add_ethtool_stats(data, pointer, stats, ARRAY_SIZE(stats)) + +/** + * iavf_add_queue_stats - copy queue statistics into supplied buffer + * @data: ethtool stats buffer + * @ring: the ring to copy + * + * Queue statistics must be copied while protected by + * u64_stats_fetch_begin_irq, so we can't directly use iavf_add_ethtool_stats. + * Assumes that queue stats are defined in iavf_gstrings_queue_stats. If the + * ring pointer is null, zero out the queue stat values and update the data + * pointer. Otherwise safely copy the stats from the ring into the supplied + * buffer and update the data pointer when finished. + * + * This function expects to be called while under rcu_read_lock(). + **/ +static void +iavf_add_queue_stats(u64 **data, struct iavf_ring *ring) +{ + const unsigned int size = ARRAY_SIZE(iavf_gstrings_queue_stats); + const struct iavf_stats *stats = iavf_gstrings_queue_stats; + unsigned int start; + unsigned int i; + + /* To avoid invalid statistics values, ensure that we keep retrying + * the copy until we get a consistent value according to + * u64_stats_fetch_retry_irq. But first, make sure our ring is + * non-null before attempting to access its syncp. + */ + do { + start = !ring ? 0 : u64_stats_fetch_begin_irq(&ring->syncp); + for (i = 0; i < size; i++) + iavf_add_one_ethtool_stat(&(*data)[i], ring, &stats[i]); + } while (ring && u64_stats_fetch_retry_irq(&ring->syncp, start)); + + /* Once we successfully copy the stats in, update the data pointer */ + *data += size; +} + +/** + * __iavf_add_stat_strings - copy stat strings into ethtool buffer + * @p: ethtool supplied buffer + * @stats: stat definitions array + * @size: size of the stats array + * + * Format and copy the strings described by stats into the buffer pointed at + * by p. + **/ +static void __iavf_add_stat_strings(u8 **p, const struct iavf_stats stats[], + const unsigned int size, ...) +{ + unsigned int i; + + for (i = 0; i < size; i++) { + va_list args; + + va_start(args, size); + vsnprintf(*p, ETH_GSTRING_LEN, stats[i].stat_string, args); + *p += ETH_GSTRING_LEN; + va_end(args); + } +} + +/** + * iavf_add_stat_strings - copy stat strings into ethtool buffer + * @p: ethtool supplied buffer + * @stats: stat definitions array + * + * Format and copy the strings described by the const static stats value into + * the buffer pointed at by p. + * + * The parameter @stats is evaluated twice, so parameters with side effects + * should be avoided. Additionally, stats must be an array such that + * ARRAY_SIZE can be called on it. + **/ +#define iavf_add_stat_strings(p, stats, ...) \ + __iavf_add_stat_strings(p, stats, ARRAY_SIZE(stats), ## __VA_ARGS__) + +#define VF_STAT(_name, _stat) \ + IAVF_STAT(struct iavf_adapter, _name, _stat) + +static const struct iavf_stats iavf_gstrings_stats[] = { + VF_STAT("rx_bytes", current_stats.rx_bytes), + VF_STAT("rx_unicast", current_stats.rx_unicast), + VF_STAT("rx_multicast", current_stats.rx_multicast), + VF_STAT("rx_broadcast", current_stats.rx_broadcast), + VF_STAT("rx_discards", current_stats.rx_discards), + VF_STAT("rx_unknown_protocol", current_stats.rx_unknown_protocol), + VF_STAT("tx_bytes", current_stats.tx_bytes), + VF_STAT("tx_unicast", current_stats.tx_unicast), + VF_STAT("tx_multicast", current_stats.tx_multicast), + VF_STAT("tx_broadcast", current_stats.tx_broadcast), + VF_STAT("tx_discards", current_stats.tx_discards), + VF_STAT("tx_errors", current_stats.tx_errors), +}; + +#define IAVF_STATS_LEN ARRAY_SIZE(iavf_gstrings_stats) + +#define IAVF_QUEUE_STATS_LEN ARRAY_SIZE(iavf_gstrings_queue_stats) + +/* For now we have one and only one private flag and it is only defined + * when we have support for the SKIP_CPU_SYNC DMA attribute. Instead + * of leaving all this code sitting around empty we will strip it unless + * our one private flag is actually available. + */ +struct iavf_priv_flags { + char flag_string[ETH_GSTRING_LEN]; + u32 flag; + bool read_only; +}; + +#define IAVF_PRIV_FLAG(_name, _flag, _read_only) { \ + .flag_string = _name, \ + .flag = _flag, \ + .read_only = _read_only, \ +} + +static const struct iavf_priv_flags iavf_gstrings_priv_flags[] = { + IAVF_PRIV_FLAG("legacy-rx", IAVF_FLAG_LEGACY_RX, 0), +}; + +#define IAVF_PRIV_FLAGS_STR_LEN ARRAY_SIZE(iavf_gstrings_priv_flags) + +/** + * iavf_get_link_ksettings - Get Link Speed and Duplex settings + * @netdev: network interface device structure + * @cmd: ethtool command + * + * Reports speed/duplex settings. Because this is a VF, we don't know what + * kind of link we really have, so we fake it. + **/ +static int iavf_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + ethtool_link_ksettings_zero_link_mode(cmd, supported); + cmd->base.autoneg = AUTONEG_DISABLE; + cmd->base.port = PORT_NONE; + /* Set speed and duplex */ + switch (adapter->link_speed) { + case I40E_LINK_SPEED_40GB: + cmd->base.speed = SPEED_40000; + break; + case I40E_LINK_SPEED_25GB: +#ifdef SPEED_25000 + cmd->base.speed = SPEED_25000; +#else + netdev_info(netdev, + "Speed is 25G, display not supported by this version of ethtool.\n"); +#endif + break; + case I40E_LINK_SPEED_20GB: + cmd->base.speed = SPEED_20000; + break; + case I40E_LINK_SPEED_10GB: + cmd->base.speed = SPEED_10000; + break; + case I40E_LINK_SPEED_1GB: + cmd->base.speed = SPEED_1000; + break; + case I40E_LINK_SPEED_100MB: + cmd->base.speed = SPEED_100; + break; + default: + break; + } + cmd->base.duplex = DUPLEX_FULL; + + return 0; +} + +/** + * iavf_get_sset_count - Get length of string set + * @netdev: network interface device structure + * @sset: id of string set + * + * Reports size of various string tables. + **/ +static int iavf_get_sset_count(struct net_device *netdev, int sset) +{ + if (sset == ETH_SS_STATS) + return IAVF_STATS_LEN + + (IAVF_QUEUE_STATS_LEN * 2 * IAVF_MAX_REQ_QUEUES); + else if (sset == ETH_SS_PRIV_FLAGS) + return IAVF_PRIV_FLAGS_STR_LEN; + else + return -EINVAL; +} + +/** + * iavf_get_ethtool_stats - report device statistics + * @netdev: network interface device structure + * @stats: ethtool statistics structure + * @data: pointer to data buffer + * + * All statistics are added to the data buffer as an array of u64. + **/ +static void iavf_get_ethtool_stats(struct net_device *netdev, + struct ethtool_stats *stats, u64 *data) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + unsigned int i; + + iavf_add_ethtool_stats(&data, adapter, iavf_gstrings_stats); + + rcu_read_lock(); + for (i = 0; i < IAVF_MAX_REQ_QUEUES; i++) { + struct iavf_ring *ring; + + /* Avoid accessing un-allocated queues */ + ring = (i < adapter->num_active_queues ? + &adapter->tx_rings[i] : NULL); + iavf_add_queue_stats(&data, ring); + + /* Avoid accessing un-allocated queues */ + ring = (i < adapter->num_active_queues ? + &adapter->rx_rings[i] : NULL); + iavf_add_queue_stats(&data, ring); + } + rcu_read_unlock(); +} + +/** + * iavf_get_priv_flag_strings - Get private flag strings + * @netdev: network interface device structure + * @data: buffer for string data + * + * Builds the private flags string table + **/ +static void iavf_get_priv_flag_strings(struct net_device *netdev, u8 *data) +{ + unsigned int i; + + for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++) { + snprintf(data, ETH_GSTRING_LEN, "%s", + iavf_gstrings_priv_flags[i].flag_string); + data += ETH_GSTRING_LEN; + } +} + +/** + * iavf_get_stat_strings - Get stat strings + * @netdev: network interface device structure + * @data: buffer for string data + * + * Builds the statistics string table + **/ +static void iavf_get_stat_strings(struct net_device *netdev, u8 *data) +{ + unsigned int i; + + iavf_add_stat_strings(&data, iavf_gstrings_stats); + + /* Queues are always allocated in pairs, so we just use num_tx_queues + * for both Tx and Rx queues. + */ + for (i = 0; i < netdev->num_tx_queues; i++) { + iavf_add_stat_strings(&data, iavf_gstrings_queue_stats, + "tx", i); + iavf_add_stat_strings(&data, iavf_gstrings_queue_stats, + "rx", i); + } +} + +/** + * iavf_get_strings - Get string set + * @netdev: network interface device structure + * @sset: id of string set + * @data: buffer for string data + * + * Builds string tables for various string sets + **/ +static void iavf_get_strings(struct net_device *netdev, u32 sset, u8 *data) +{ + switch (sset) { + case ETH_SS_STATS: + iavf_get_stat_strings(netdev, data); + break; + case ETH_SS_PRIV_FLAGS: + iavf_get_priv_flag_strings(netdev, data); + break; + default: + break; + } +} + +/** + * iavf_get_priv_flags - report device private flags + * @netdev: 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 iavf_gstrings_priv_flags + * array. + * + * Returns a u32 bitmap of flags. + **/ +static u32 iavf_get_priv_flags(struct net_device *netdev) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + u32 i, ret_flags = 0; + + for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++) { + const struct iavf_priv_flags *priv_flags; + + priv_flags = &iavf_gstrings_priv_flags[i]; + + if (priv_flags->flag & adapter->flags) + ret_flags |= BIT(i); + } + + return ret_flags; +} + +/** + * iavf_set_priv_flags - set private flags + * @netdev: network interface device structure + * @flags: bit flags to be set + **/ +static int iavf_set_priv_flags(struct net_device *netdev, u32 flags) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + u32 orig_flags, new_flags, changed_flags; + u32 i; + + orig_flags = READ_ONCE(adapter->flags); + new_flags = orig_flags; + + for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++) { + const struct iavf_priv_flags *priv_flags; + + priv_flags = &iavf_gstrings_priv_flags[i]; + + if (flags & BIT(i)) + new_flags |= priv_flags->flag; + else + new_flags &= ~(priv_flags->flag); + + if (priv_flags->read_only && + ((orig_flags ^ new_flags) & ~BIT(i))) + return -EOPNOTSUPP; + } + + /* Before we finalize any flag changes, any checks which we need to + * perform to determine if the new flags will be supported should go + * here... + */ + + /* Compare and exchange the new flags into place. If we failed, that + * is if cmpxchg returns anything but the old value, this means + * something else must have modified the flags variable since we + * copied it. We'll just punt with an error and log something in the + * message buffer. + */ + if (cmpxchg(&adapter->flags, orig_flags, new_flags) != orig_flags) { + dev_warn(&adapter->pdev->dev, + "Unable to update adapter->flags as it was modified by another thread...\n"); + return -EAGAIN; + } + + changed_flags = orig_flags ^ new_flags; + + /* Process any additional changes needed as a result of flag changes. + * The changed_flags value reflects the list of bits that were changed + * in the code above. + */ + + /* issue a reset to force legacy-rx change to take effect */ + if (changed_flags & IAVF_FLAG_LEGACY_RX) { + if (netif_running(netdev)) { + adapter->flags |= IAVF_FLAG_RESET_NEEDED; + schedule_work(&adapter->reset_task); + } + } + + return 0; +} + +/** + * iavf_get_msglevel - Get debug message level + * @netdev: network interface device structure + * + * Returns current debug message level. + **/ +static u32 iavf_get_msglevel(struct net_device *netdev) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + return adapter->msg_enable; +} + +/** + * iavf_set_msglevel - Set debug message level + * @netdev: network interface device structure + * @data: message level + * + * Set current debug message level. Higher values cause the driver to + * be noisier. + **/ +static void iavf_set_msglevel(struct net_device *netdev, u32 data) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + if (IAVF_DEBUG_USER & data) + adapter->hw.debug_mask = data; + adapter->msg_enable = data; +} + +/** + * iavf_get_drvinfo - Get driver info + * @netdev: network interface device structure + * @drvinfo: ethool driver info structure + * + * Returns information about the driver and device for display to the user. + **/ +static void iavf_get_drvinfo(struct net_device *netdev, + struct ethtool_drvinfo *drvinfo) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + strlcpy(drvinfo->driver, iavf_driver_name, 32); + strlcpy(drvinfo->version, iavf_driver_version, 32); + strlcpy(drvinfo->fw_version, "N/A", 4); + strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), 32); + drvinfo->n_priv_flags = IAVF_PRIV_FLAGS_STR_LEN; +} + +/** + * iavf_get_ringparam - Get ring parameters + * @netdev: network interface device structure + * @ring: ethtool ringparam structure + * + * Returns current ring parameters. TX and RX rings are reported separately, + * but the number of rings is not reported. + **/ +static void iavf_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + ring->rx_max_pending = IAVF_MAX_RXD; + ring->tx_max_pending = IAVF_MAX_TXD; + ring->rx_pending = adapter->rx_desc_count; + ring->tx_pending = adapter->tx_desc_count; +} + +/** + * iavf_set_ringparam - Set ring parameters + * @netdev: network interface device structure + * @ring: ethtool ringparam structure + * + * Sets ring parameters. TX and RX rings are controlled separately, but the + * number of rings is not specified, so all rings get the same settings. + **/ +static int iavf_set_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + u32 new_rx_count, new_tx_count; + + if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) + return -EINVAL; + + new_tx_count = clamp_t(u32, ring->tx_pending, + IAVF_MIN_TXD, + IAVF_MAX_TXD); + new_tx_count = ALIGN(new_tx_count, IAVF_REQ_DESCRIPTOR_MULTIPLE); + + new_rx_count = clamp_t(u32, ring->rx_pending, + IAVF_MIN_RXD, + IAVF_MAX_RXD); + new_rx_count = ALIGN(new_rx_count, IAVF_REQ_DESCRIPTOR_MULTIPLE); + + /* if nothing to do return success */ + if ((new_tx_count == adapter->tx_desc_count) && + (new_rx_count == adapter->rx_desc_count)) + return 0; + + adapter->tx_desc_count = new_tx_count; + adapter->rx_desc_count = new_rx_count; + + if (netif_running(netdev)) { + adapter->flags |= IAVF_FLAG_RESET_NEEDED; + schedule_work(&adapter->reset_task); + } + + return 0; +} + +/** + * __iavf_get_coalesce - get per-queue coalesce settings + * @netdev: the netdev to check + * @ec: ethtool coalesce data structure + * @queue: which queue to pick + * + * Gets the per-queue settings for coalescence. Specifically Rx and Tx usecs + * are per queue. If queue is <0 then we default to queue 0 as the + * representative value. + **/ +static int __iavf_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, int queue) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_vsi *vsi = &adapter->vsi; + struct iavf_ring *rx_ring, *tx_ring; + + ec->tx_max_coalesced_frames = vsi->work_limit; + ec->rx_max_coalesced_frames = vsi->work_limit; + + /* Rx and Tx usecs per queue value. If user doesn't specify the + * queue, return queue 0's value to represent. + */ + if (queue < 0) + queue = 0; + else if (queue >= adapter->num_active_queues) + return -EINVAL; + + rx_ring = &adapter->rx_rings[queue]; + tx_ring = &adapter->tx_rings[queue]; + + if (ITR_IS_DYNAMIC(rx_ring->itr_setting)) + ec->use_adaptive_rx_coalesce = 1; + + if (ITR_IS_DYNAMIC(tx_ring->itr_setting)) + ec->use_adaptive_tx_coalesce = 1; + + ec->rx_coalesce_usecs = rx_ring->itr_setting & ~IAVF_ITR_DYNAMIC; + ec->tx_coalesce_usecs = tx_ring->itr_setting & ~IAVF_ITR_DYNAMIC; + + return 0; +} + +/** + * iavf_get_coalesce - Get interrupt coalescing settings + * @netdev: network interface device structure + * @ec: ethtool coalesce structure + * + * Returns current coalescing settings. This is referred to elsewhere in the + * driver as Interrupt Throttle Rate, as this is how the hardware describes + * this functionality. Note that if per-queue settings have been modified this + * only represents the settings of queue 0. + **/ +static int iavf_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec) +{ + return __iavf_get_coalesce(netdev, ec, -1); +} + +/** + * iavf_get_per_queue_coalesce - get coalesce values for specific queue + * @netdev: netdev to read + * @ec: coalesce settings from ethtool + * @queue: the queue to read + * + * Read specific queue's coalesce settings. + **/ +static int iavf_get_per_queue_coalesce(struct net_device *netdev, u32 queue, + struct ethtool_coalesce *ec) +{ + return __iavf_get_coalesce(netdev, ec, queue); +} + +/** + * iavf_set_itr_per_queue - set ITR values for specific queue + * @adapter: the VF adapter struct to set values for + * @ec: coalesce settings from ethtool + * @queue: the queue to modify + * + * Change the ITR settings for a specific queue. + **/ +static void iavf_set_itr_per_queue(struct iavf_adapter *adapter, + struct ethtool_coalesce *ec, int queue) +{ + struct iavf_ring *rx_ring = &adapter->rx_rings[queue]; + struct iavf_ring *tx_ring = &adapter->tx_rings[queue]; + struct iavf_q_vector *q_vector; + + rx_ring->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs); + tx_ring->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs); + + rx_ring->itr_setting |= IAVF_ITR_DYNAMIC; + if (!ec->use_adaptive_rx_coalesce) + rx_ring->itr_setting ^= IAVF_ITR_DYNAMIC; + + tx_ring->itr_setting |= IAVF_ITR_DYNAMIC; + if (!ec->use_adaptive_tx_coalesce) + tx_ring->itr_setting ^= IAVF_ITR_DYNAMIC; + + q_vector = rx_ring->q_vector; + q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting); + + q_vector = tx_ring->q_vector; + q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting); + + /* The interrupt handler itself will take care of programming + * the Tx and Rx ITR values based on the values we have entered + * into the q_vector, no need to write the values now. + */ +} + +/** + * __iavf_set_coalesce - set coalesce settings for particular queue + * @netdev: the netdev to change + * @ec: ethtool coalesce settings + * @queue: the queue to change + * + * Sets the coalesce settings for a particular queue. + **/ +static int __iavf_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, int queue) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_vsi *vsi = &adapter->vsi; + int i; + + if (ec->tx_max_coalesced_frames_irq || ec->rx_max_coalesced_frames_irq) + vsi->work_limit = ec->tx_max_coalesced_frames_irq; + + if (ec->rx_coalesce_usecs == 0) { + if (ec->use_adaptive_rx_coalesce) + netif_info(adapter, drv, netdev, "rx-usecs=0, need to disable adaptive-rx for a complete disable\n"); + } else if ((ec->rx_coalesce_usecs < IAVF_MIN_ITR) || + (ec->rx_coalesce_usecs > IAVF_MAX_ITR)) { + netif_info(adapter, drv, netdev, "Invalid value, rx-usecs range is 0-8160\n"); + return -EINVAL; + } else if (ec->tx_coalesce_usecs == 0) { + if (ec->use_adaptive_tx_coalesce) + netif_info(adapter, drv, netdev, "tx-usecs=0, need to disable adaptive-tx for a complete disable\n"); + } else if ((ec->tx_coalesce_usecs < IAVF_MIN_ITR) || + (ec->tx_coalesce_usecs > IAVF_MAX_ITR)) { + netif_info(adapter, drv, netdev, "Invalid value, tx-usecs range is 0-8160\n"); + return -EINVAL; + } + + /* Rx and Tx usecs has per queue value. If user doesn't specify the + * queue, apply to all queues. + */ + if (queue < 0) { + for (i = 0; i < adapter->num_active_queues; i++) + iavf_set_itr_per_queue(adapter, ec, i); + } else if (queue < adapter->num_active_queues) { + iavf_set_itr_per_queue(adapter, ec, queue); + } else { + netif_info(adapter, drv, netdev, "Invalid queue value, queue range is 0 - %d\n", + adapter->num_active_queues - 1); + return -EINVAL; + } + + return 0; +} + +/** + * iavf_set_coalesce - Set interrupt coalescing settings + * @netdev: network interface device structure + * @ec: ethtool coalesce structure + * + * Change current coalescing settings for every queue. + **/ +static int iavf_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec) +{ + return __iavf_set_coalesce(netdev, ec, -1); +} + +/** + * iavf_set_per_queue_coalesce - set specific queue's coalesce settings + * @netdev: the netdev to change + * @ec: ethtool's coalesce settings + * @queue: the queue to modify + * + * Modifies a specific queue's coalesce settings. + */ +static int iavf_set_per_queue_coalesce(struct net_device *netdev, u32 queue, + struct ethtool_coalesce *ec) +{ + return __iavf_set_coalesce(netdev, ec, queue); +} + +/** + * iavf_get_rxnfc - command to get RX flow classification rules + * @netdev: network interface device structure + * @cmd: ethtool rxnfc command + * @rule_locs: pointer to store rule locations + * + * Returns Success if the command is supported. + **/ +static int iavf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, + u32 *rule_locs) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + int ret = -EOPNOTSUPP; + + switch (cmd->cmd) { + case ETHTOOL_GRXRINGS: + cmd->data = adapter->num_active_queues; + ret = 0; + break; + case ETHTOOL_GRXFH: + netdev_info(netdev, + "RSS hash info is not available to vf, use pf.\n"); + break; + default: + break; + } + + return ret; +} +/** + * iavf_get_channels: get the number of channels supported by the device + * @netdev: network interface device structure + * @ch: channel information structure + * + * For the purposes of our device, we only use combined channels, i.e. a tx/rx + * queue pair. Report one extra channel to match our "other" MSI-X vector. + **/ +static void iavf_get_channels(struct net_device *netdev, + struct ethtool_channels *ch) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + /* Report maximum channels */ + ch->max_combined = IAVF_MAX_REQ_QUEUES; + + ch->max_other = NONQ_VECS; + ch->other_count = NONQ_VECS; + + ch->combined_count = adapter->num_active_queues; +} + +/** + * iavf_set_channels: set the new channel count + * @netdev: network interface device structure + * @ch: channel information structure + * + * Negotiate a new number of channels with the PF then do a reset. During + * reset we'll realloc queues and fix the RSS table. Returns 0 on success, + * negative on failure. + **/ +static int iavf_set_channels(struct net_device *netdev, + struct ethtool_channels *ch) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + int num_req = ch->combined_count; + + if (num_req != adapter->num_active_queues && + !(adapter->vf_res->vf_cap_flags & + VIRTCHNL_VF_OFFLOAD_REQ_QUEUES)) { + dev_info(&adapter->pdev->dev, "PF is not capable of queue negotiation.\n"); + return -EINVAL; + } + + if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && + adapter->num_tc) { + dev_info(&adapter->pdev->dev, "Cannot set channels since ADq is enabled.\n"); + return -EINVAL; + } + + /* All of these should have already been checked by ethtool before this + * even gets to us, but just to be sure. + */ + if (num_req <= 0 || num_req > IAVF_MAX_REQ_QUEUES) + return -EINVAL; + + if (ch->rx_count || ch->tx_count || ch->other_count != NONQ_VECS) + return -EINVAL; + + adapter->num_req_queues = num_req; + return iavf_request_queues(adapter, num_req); +} + +/** + * iavf_get_rxfh_key_size - get the RSS hash key size + * @netdev: network interface device structure + * + * Returns the table size. + **/ +static u32 iavf_get_rxfh_key_size(struct net_device *netdev) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + return adapter->rss_key_size; +} + +/** + * iavf_get_rxfh_indir_size - get the rx flow hash indirection table size + * @netdev: network interface device structure + * + * Returns the table size. + **/ +static u32 iavf_get_rxfh_indir_size(struct net_device *netdev) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + return adapter->rss_lut_size; +} + +/** + * iavf_get_rxfh - get the rx flow hash indirection table + * @netdev: network interface device structure + * @indir: indirection table + * @key: hash key + * @hfunc: hash function in use + * + * Reads the indirection table directly from the hardware. Always returns 0. + **/ +static int iavf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, + u8 *hfunc) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + u16 i; + + if (hfunc) + *hfunc = ETH_RSS_HASH_TOP; + if (!indir) + return 0; + + memcpy(key, adapter->rss_key, adapter->rss_key_size); + + /* Each 32 bits pointed by 'indir' is stored with a lut entry */ + for (i = 0; i < adapter->rss_lut_size; i++) + indir[i] = (u32)adapter->rss_lut[i]; + + return 0; +} + +/** + * iavf_set_rxfh - set the rx flow hash indirection table + * @netdev: network interface device structure + * @indir: indirection table + * @key: hash key + * @hfunc: hash function to use + * + * Returns -EINVAL if the table specifies an inavlid queue id, otherwise + * returns 0 after programming the table. + **/ +static int iavf_set_rxfh(struct net_device *netdev, const u32 *indir, + const u8 *key, const u8 hfunc) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + u16 i; + + /* 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; + + if (key) + memcpy(adapter->rss_key, key, adapter->rss_key_size); + + /* Each 32 bits pointed by 'indir' is stored with a lut entry */ + for (i = 0; i < adapter->rss_lut_size; i++) + adapter->rss_lut[i] = (u8)(indir[i]); + + return iavf_config_rss(adapter); +} + +static const struct ethtool_ops iavf_ethtool_ops = { + .get_drvinfo = iavf_get_drvinfo, + .get_link = ethtool_op_get_link, + .get_ringparam = iavf_get_ringparam, + .set_ringparam = iavf_set_ringparam, + .get_strings = iavf_get_strings, + .get_ethtool_stats = iavf_get_ethtool_stats, + .get_sset_count = iavf_get_sset_count, + .get_priv_flags = iavf_get_priv_flags, + .set_priv_flags = iavf_set_priv_flags, + .get_msglevel = iavf_get_msglevel, + .set_msglevel = iavf_set_msglevel, + .get_coalesce = iavf_get_coalesce, + .set_coalesce = iavf_set_coalesce, + .get_per_queue_coalesce = iavf_get_per_queue_coalesce, + .set_per_queue_coalesce = iavf_set_per_queue_coalesce, + .get_rxnfc = iavf_get_rxnfc, + .get_rxfh_indir_size = iavf_get_rxfh_indir_size, + .get_rxfh = iavf_get_rxfh, + .set_rxfh = iavf_set_rxfh, + .get_channels = iavf_get_channels, + .set_channels = iavf_set_channels, + .get_rxfh_key_size = iavf_get_rxfh_key_size, + .get_link_ksettings = iavf_get_link_ksettings, +}; + +/** + * iavf_set_ethtool_ops - Initialize ethtool ops struct + * @netdev: network interface device structure + * + * Sets ethtool ops struct in our netdev so that ethtool can call + * our functions. + **/ +void iavf_set_ethtool_ops(struct net_device *netdev) +{ + netdev->ethtool_ops = &iavf_ethtool_ops; +} diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c new file mode 100644 index 000000000000..9f2b7b7adf6b --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -0,0 +1,3984 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#include "iavf.h" +#include "iavf_prototype.h" +#include "iavf_client.h" +/* All iavf tracepoints are defined by the include below, which must + * be included exactly once across the whole kernel with + * CREATE_TRACE_POINTS defined + */ +#define CREATE_TRACE_POINTS +#include "iavf_trace.h" + +static int iavf_setup_all_tx_resources(struct iavf_adapter *adapter); +static int iavf_setup_all_rx_resources(struct iavf_adapter *adapter); +static int iavf_close(struct net_device *netdev); + +char iavf_driver_name[] = "iavf"; +static const char iavf_driver_string[] = + "Intel(R) Ethernet Adaptive Virtual Function Network Driver"; + +#define DRV_KERN "-k" + +#define DRV_VERSION_MAJOR 3 +#define DRV_VERSION_MINOR 2 +#define DRV_VERSION_BUILD 3 +#define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ + __stringify(DRV_VERSION_MINOR) "." \ + __stringify(DRV_VERSION_BUILD) \ + DRV_KERN +const char iavf_driver_version[] = DRV_VERSION; +static const char iavf_copyright[] = + "Copyright (c) 2013 - 2018 Intel Corporation."; + +/* iavf_pci_tbl - PCI Device ID Table + * + * Wildcard entries (PCI_ANY_ID) should come last + * Last entry must be all 0s + * + * { Vendor ID, Device ID, SubVendor ID, SubDevice ID, + * Class, Class Mask, private data (not used) } + */ +static const struct pci_device_id iavf_pci_tbl[] = { + {PCI_VDEVICE(INTEL, IAVF_DEV_ID_VF), 0}, + {PCI_VDEVICE(INTEL, IAVF_DEV_ID_VF_HV), 0}, + {PCI_VDEVICE(INTEL, IAVF_DEV_ID_X722_VF), 0}, + {PCI_VDEVICE(INTEL, IAVF_DEV_ID_ADAPTIVE_VF), 0}, + /* required last entry */ + {0, } +}; + +MODULE_DEVICE_TABLE(pci, iavf_pci_tbl); + +MODULE_ALIAS("i40evf"); +MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); +MODULE_DESCRIPTION("Intel(R) Ethernet Adaptive Virtual Function Network Driver"); +MODULE_LICENSE("GPL v2"); +MODULE_VERSION(DRV_VERSION); + +static struct workqueue_struct *iavf_wq; + +/** + * iavf_allocate_dma_mem_d - OS specific memory alloc for shared code + * @hw: pointer to the HW structure + * @mem: ptr to mem struct to fill out + * @size: size of memory requested + * @alignment: what to align the allocation to + **/ +iavf_status iavf_allocate_dma_mem_d(struct iavf_hw *hw, + struct iavf_dma_mem *mem, + u64 size, u32 alignment) +{ + struct iavf_adapter *adapter = (struct iavf_adapter *)hw->back; + + if (!mem) + return I40E_ERR_PARAM; + + mem->size = ALIGN(size, alignment); + mem->va = dma_alloc_coherent(&adapter->pdev->dev, mem->size, + (dma_addr_t *)&mem->pa, GFP_KERNEL); + if (mem->va) + return 0; + else + return I40E_ERR_NO_MEMORY; +} + +/** + * iavf_free_dma_mem_d - OS specific memory free for shared code + * @hw: pointer to the HW structure + * @mem: ptr to mem struct to free + **/ +iavf_status iavf_free_dma_mem_d(struct iavf_hw *hw, struct iavf_dma_mem *mem) +{ + struct iavf_adapter *adapter = (struct iavf_adapter *)hw->back; + + if (!mem || !mem->va) + return I40E_ERR_PARAM; + dma_free_coherent(&adapter->pdev->dev, mem->size, + mem->va, (dma_addr_t)mem->pa); + return 0; +} + +/** + * iavf_allocate_virt_mem_d - OS specific memory alloc for shared code + * @hw: pointer to the HW structure + * @mem: ptr to mem struct to fill out + * @size: size of memory requested + **/ +iavf_status iavf_allocate_virt_mem_d(struct iavf_hw *hw, + struct iavf_virt_mem *mem, u32 size) +{ + if (!mem) + return I40E_ERR_PARAM; + + mem->size = size; + mem->va = kzalloc(size, GFP_KERNEL); + + if (mem->va) + return 0; + else + return I40E_ERR_NO_MEMORY; +} + +/** + * iavf_free_virt_mem_d - OS specific memory free for shared code + * @hw: pointer to the HW structure + * @mem: ptr to mem struct to free + **/ +iavf_status iavf_free_virt_mem_d(struct iavf_hw *hw, struct iavf_virt_mem *mem) +{ + if (!mem) + return I40E_ERR_PARAM; + + /* it's ok to kfree a NULL pointer */ + kfree(mem->va); + + return 0; +} + +/** + * iavf_debug_d - OS dependent version of debug printing + * @hw: pointer to the HW structure + * @mask: debug level mask + * @fmt_str: printf-type format description + **/ +void iavf_debug_d(void *hw, u32 mask, char *fmt_str, ...) +{ + char buf[512]; + va_list argptr; + + if (!(mask & ((struct iavf_hw *)hw)->debug_mask)) + return; + + va_start(argptr, fmt_str); + vsnprintf(buf, sizeof(buf), fmt_str, argptr); + va_end(argptr); + + /* the debug string is already formatted with a newline */ + pr_info("%s", buf); +} + +/** + * iavf_schedule_reset - Set the flags and schedule a reset event + * @adapter: board private structure + **/ +void iavf_schedule_reset(struct iavf_adapter *adapter) +{ + if (!(adapter->flags & + (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED))) { + adapter->flags |= IAVF_FLAG_RESET_NEEDED; + schedule_work(&adapter->reset_task); + } +} + +/** + * iavf_tx_timeout - Respond to a Tx Hang + * @netdev: network interface device structure + **/ +static void iavf_tx_timeout(struct net_device *netdev) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + adapter->tx_timeout_count++; + iavf_schedule_reset(adapter); +} + +/** + * iavf_misc_irq_disable - Mask off interrupt generation on the NIC + * @adapter: board private structure + **/ +static void iavf_misc_irq_disable(struct iavf_adapter *adapter) +{ + struct iavf_hw *hw = &adapter->hw; + + if (!adapter->msix_entries) + return; + + wr32(hw, IAVF_VFINT_DYN_CTL01, 0); + + iavf_flush(hw); + + synchronize_irq(adapter->msix_entries[0].vector); +} + +/** + * iavf_misc_irq_enable - Enable default interrupt generation settings + * @adapter: board private structure + **/ +static void iavf_misc_irq_enable(struct iavf_adapter *adapter) +{ + struct iavf_hw *hw = &adapter->hw; + + wr32(hw, IAVF_VFINT_DYN_CTL01, IAVF_VFINT_DYN_CTL01_INTENA_MASK | + IAVF_VFINT_DYN_CTL01_ITR_INDX_MASK); + wr32(hw, IAVF_VFINT_ICR0_ENA1, IAVF_VFINT_ICR0_ENA1_ADMINQ_MASK); + + iavf_flush(hw); +} + +/** + * iavf_irq_disable - Mask off interrupt generation on the NIC + * @adapter: board private structure + **/ +static void iavf_irq_disable(struct iavf_adapter *adapter) +{ + int i; + struct iavf_hw *hw = &adapter->hw; + + if (!adapter->msix_entries) + return; + + for (i = 1; i < adapter->num_msix_vectors; i++) { + wr32(hw, IAVF_VFINT_DYN_CTLN1(i - 1), 0); + synchronize_irq(adapter->msix_entries[i].vector); + } + iavf_flush(hw); +} + +/** + * iavf_irq_enable_queues - Enable interrupt for specified queues + * @adapter: board private structure + * @mask: bitmap of queues to enable + **/ +void iavf_irq_enable_queues(struct iavf_adapter *adapter, u32 mask) +{ + struct iavf_hw *hw = &adapter->hw; + int i; + + for (i = 1; i < adapter->num_msix_vectors; i++) { + if (mask & BIT(i - 1)) { + wr32(hw, IAVF_VFINT_DYN_CTLN1(i - 1), + IAVF_VFINT_DYN_CTLN1_INTENA_MASK | + IAVF_VFINT_DYN_CTLN1_ITR_INDX_MASK); + } + } +} + +/** + * iavf_irq_enable - Enable default interrupt generation settings + * @adapter: board private structure + * @flush: boolean value whether to run rd32() + **/ +void iavf_irq_enable(struct iavf_adapter *adapter, bool flush) +{ + struct iavf_hw *hw = &adapter->hw; + + iavf_misc_irq_enable(adapter); + iavf_irq_enable_queues(adapter, ~0); + + if (flush) + iavf_flush(hw); +} + +/** + * iavf_msix_aq - Interrupt handler for vector 0 + * @irq: interrupt number + * @data: pointer to netdev + **/ +static irqreturn_t iavf_msix_aq(int irq, void *data) +{ + struct net_device *netdev = data; + struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_hw *hw = &adapter->hw; + + /* handle non-queue interrupts, these reads clear the registers */ + rd32(hw, IAVF_VFINT_ICR01); + rd32(hw, IAVF_VFINT_ICR0_ENA1); + + /* schedule work on the private workqueue */ + schedule_work(&adapter->adminq_task); + + return IRQ_HANDLED; +} + +/** + * iavf_msix_clean_rings - MSIX mode Interrupt Handler + * @irq: interrupt number + * @data: pointer to a q_vector + **/ +static irqreturn_t iavf_msix_clean_rings(int irq, void *data) +{ + struct iavf_q_vector *q_vector = data; + + if (!q_vector->tx.ring && !q_vector->rx.ring) + return IRQ_HANDLED; + + napi_schedule_irqoff(&q_vector->napi); + + return IRQ_HANDLED; +} + +/** + * iavf_map_vector_to_rxq - associate irqs with rx queues + * @adapter: board private structure + * @v_idx: interrupt number + * @r_idx: queue number + **/ +static void +iavf_map_vector_to_rxq(struct iavf_adapter *adapter, int v_idx, int r_idx) +{ + struct iavf_q_vector *q_vector = &adapter->q_vectors[v_idx]; + struct iavf_ring *rx_ring = &adapter->rx_rings[r_idx]; + struct iavf_hw *hw = &adapter->hw; + + rx_ring->q_vector = q_vector; + rx_ring->next = q_vector->rx.ring; + rx_ring->vsi = &adapter->vsi; + q_vector->rx.ring = rx_ring; + q_vector->rx.count++; + q_vector->rx.next_update = jiffies + 1; + q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting); + q_vector->ring_mask |= BIT(r_idx); + wr32(hw, IAVF_VFINT_ITRN1(IAVF_RX_ITR, q_vector->reg_idx), + q_vector->rx.current_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; +} + +/** + * iavf_map_vector_to_txq - associate irqs with tx queues + * @adapter: board private structure + * @v_idx: interrupt number + * @t_idx: queue number + **/ +static void +iavf_map_vector_to_txq(struct iavf_adapter *adapter, int v_idx, int t_idx) +{ + struct iavf_q_vector *q_vector = &adapter->q_vectors[v_idx]; + struct iavf_ring *tx_ring = &adapter->tx_rings[t_idx]; + struct iavf_hw *hw = &adapter->hw; + + tx_ring->q_vector = q_vector; + tx_ring->next = q_vector->tx.ring; + tx_ring->vsi = &adapter->vsi; + q_vector->tx.ring = tx_ring; + q_vector->tx.count++; + q_vector->tx.next_update = jiffies + 1; + q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting); + q_vector->num_ringpairs++; + wr32(hw, IAVF_VFINT_ITRN1(IAVF_TX_ITR, q_vector->reg_idx), + q_vector->tx.target_itr); + q_vector->tx.current_itr = q_vector->tx.target_itr; +} + +/** + * iavf_map_rings_to_vectors - Maps descriptor rings to vectors + * @adapter: board private structure to initialize + * + * This function maps descriptor rings to the queue-specific vectors + * we were allotted through the MSI-X enabling code. Ideally, we'd have + * one vector per ring/queue, but on a constrained vector budget, we + * group the rings as "efficiently" as possible. You would add new + * mapping configurations in here. + **/ +static void iavf_map_rings_to_vectors(struct iavf_adapter *adapter) +{ + int rings_remaining = adapter->num_active_queues; + int ridx = 0, vidx = 0; + int q_vectors; + + q_vectors = adapter->num_msix_vectors - NONQ_VECS; + + for (; ridx < rings_remaining; ridx++) { + iavf_map_vector_to_rxq(adapter, vidx, ridx); + iavf_map_vector_to_txq(adapter, vidx, ridx); + + /* In the case where we have more queues than vectors, continue + * round-robin on vectors until all queues are mapped. + */ + if (++vidx >= q_vectors) + vidx = 0; + } + + adapter->aq_required |= IAVF_FLAG_AQ_MAP_VECTORS; +} + +/** + * iavf_irq_affinity_notify - Callback for affinity changes + * @notify: context as to what irq was changed + * @mask: the new affinity mask + * + * This is a callback function used by the irq_set_affinity_notifier function + * so that we may register to receive changes to the irq affinity masks. + **/ +static void iavf_irq_affinity_notify(struct irq_affinity_notify *notify, + const cpumask_t *mask) +{ + struct iavf_q_vector *q_vector = + container_of(notify, struct iavf_q_vector, affinity_notify); + + cpumask_copy(&q_vector->affinity_mask, mask); +} + +/** + * iavf_irq_affinity_release - Callback for affinity notifier release + * @ref: internal core kernel usage + * + * This is a callback function used by the irq_set_affinity_notifier function + * to inform the current notification subscriber that they will no longer + * receive notifications. + **/ +static void iavf_irq_affinity_release(struct kref *ref) {} + +/** + * iavf_request_traffic_irqs - Initialize MSI-X interrupts + * @adapter: board private structure + * @basename: device basename + * + * Allocates MSI-X vectors for tx and rx handling, and requests + * interrupts from the kernel. + **/ +static int +iavf_request_traffic_irqs(struct iavf_adapter *adapter, char *basename) +{ + unsigned int vector, q_vectors; + unsigned int rx_int_idx = 0, tx_int_idx = 0; + int irq_num, err; + int cpu; + + iavf_irq_disable(adapter); + /* Decrement for Other and TCP Timer vectors */ + q_vectors = adapter->num_msix_vectors - NONQ_VECS; + + for (vector = 0; vector < q_vectors; vector++) { + struct iavf_q_vector *q_vector = &adapter->q_vectors[vector]; + + irq_num = adapter->msix_entries[vector + NONQ_VECS].vector; + + if (q_vector->tx.ring && q_vector->rx.ring) { + snprintf(q_vector->name, sizeof(q_vector->name), + "iavf-%s-TxRx-%d", basename, rx_int_idx++); + tx_int_idx++; + } else if (q_vector->rx.ring) { + snprintf(q_vector->name, sizeof(q_vector->name), + "iavf-%s-rx-%d", basename, rx_int_idx++); + } else if (q_vector->tx.ring) { + snprintf(q_vector->name, sizeof(q_vector->name), + "iavf-%s-tx-%d", basename, tx_int_idx++); + } else { + /* skip this unused q_vector */ + continue; + } + err = request_irq(irq_num, + iavf_msix_clean_rings, + 0, + q_vector->name, + q_vector); + if (err) { + dev_info(&adapter->pdev->dev, + "Request_irq failed, error: %d\n", err); + goto free_queue_irqs; + } + /* register for affinity change notifications */ + q_vector->affinity_notify.notify = iavf_irq_affinity_notify; + q_vector->affinity_notify.release = + iavf_irq_affinity_release; + irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify); + /* Spread the IRQ affinity hints across online CPUs. Note that + * get_cpu_mask returns a mask with a permanent lifetime so + * it's safe to use as a hint for irq_set_affinity_hint. + */ + cpu = cpumask_local_spread(q_vector->v_idx, -1); + irq_set_affinity_hint(irq_num, get_cpu_mask(cpu)); + } + + return 0; + +free_queue_irqs: + while (vector) { + vector--; + irq_num = adapter->msix_entries[vector + NONQ_VECS].vector; + irq_set_affinity_notifier(irq_num, NULL); + irq_set_affinity_hint(irq_num, NULL); + free_irq(irq_num, &adapter->q_vectors[vector]); + } + return err; +} + +/** + * iavf_request_misc_irq - Initialize MSI-X interrupts + * @adapter: board private structure + * + * Allocates MSI-X vector 0 and requests interrupts from the kernel. This + * vector is only for the admin queue, and stays active even when the netdev + * is closed. + **/ +static int iavf_request_misc_irq(struct iavf_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + int err; + + snprintf(adapter->misc_vector_name, + sizeof(adapter->misc_vector_name) - 1, "iavf-%s:mbx", + dev_name(&adapter->pdev->dev)); + err = request_irq(adapter->msix_entries[0].vector, + &iavf_msix_aq, 0, + adapter->misc_vector_name, netdev); + if (err) { + dev_err(&adapter->pdev->dev, + "request_irq for %s failed: %d\n", + adapter->misc_vector_name, err); + free_irq(adapter->msix_entries[0].vector, netdev); + } + return err; +} + +/** + * iavf_free_traffic_irqs - Free MSI-X interrupts + * @adapter: board private structure + * + * Frees all MSI-X vectors other than 0. + **/ +static void iavf_free_traffic_irqs(struct iavf_adapter *adapter) +{ + int vector, irq_num, q_vectors; + + if (!adapter->msix_entries) + return; + + q_vectors = adapter->num_msix_vectors - NONQ_VECS; + + for (vector = 0; vector < q_vectors; vector++) { + irq_num = adapter->msix_entries[vector + NONQ_VECS].vector; + irq_set_affinity_notifier(irq_num, NULL); + irq_set_affinity_hint(irq_num, NULL); + free_irq(irq_num, &adapter->q_vectors[vector]); + } +} + +/** + * iavf_free_misc_irq - Free MSI-X miscellaneous vector + * @adapter: board private structure + * + * Frees MSI-X vector 0. + **/ +static void iavf_free_misc_irq(struct iavf_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + + if (!adapter->msix_entries) + return; + + free_irq(adapter->msix_entries[0].vector, netdev); +} + +/** + * iavf_configure_tx - Configure Transmit Unit after Reset + * @adapter: board private structure + * + * Configure the Tx unit of the MAC after a reset. + **/ +static void iavf_configure_tx(struct iavf_adapter *adapter) +{ + struct iavf_hw *hw = &adapter->hw; + int i; + + for (i = 0; i < adapter->num_active_queues; i++) + adapter->tx_rings[i].tail = hw->hw_addr + IAVF_QTX_TAIL1(i); +} + +/** + * iavf_configure_rx - Configure Receive Unit after Reset + * @adapter: board private structure + * + * Configure the Rx unit of the MAC after a reset. + **/ +static void iavf_configure_rx(struct iavf_adapter *adapter) +{ + unsigned int rx_buf_len = IAVF_RXBUFFER_2048; + struct iavf_hw *hw = &adapter->hw; + int i; + + /* Legacy Rx will always default to a 2048 buffer size. */ +#if (PAGE_SIZE < 8192) + if (!(adapter->flags & IAVF_FLAG_LEGACY_RX)) { + struct net_device *netdev = adapter->netdev; + + /* For jumbo frames on systems with 4K pages we have to use + * an order 1 page, so we might as well increase the size + * of our Rx buffer to make better use of the available space + */ + rx_buf_len = IAVF_RXBUFFER_3072; + + /* We use a 1536 buffer size for configurations with + * standard Ethernet mtu. On x86 this gives us enough room + * for shared info and 192 bytes of padding. + */ + if (!IAVF_2K_TOO_SMALL_WITH_PADDING && + (netdev->mtu <= ETH_DATA_LEN)) + rx_buf_len = IAVF_RXBUFFER_1536 - NET_IP_ALIGN; + } +#endif + + for (i = 0; i < adapter->num_active_queues; i++) { + adapter->rx_rings[i].tail = hw->hw_addr + IAVF_QRX_TAIL1(i); + adapter->rx_rings[i].rx_buf_len = rx_buf_len; + + if (adapter->flags & IAVF_FLAG_LEGACY_RX) + clear_ring_build_skb_enabled(&adapter->rx_rings[i]); + else + set_ring_build_skb_enabled(&adapter->rx_rings[i]); + } +} + +/** + * iavf_find_vlan - Search filter list for specific vlan filter + * @adapter: board private structure + * @vlan: vlan tag + * + * Returns ptr to the filter object or NULL. Must be called while holding the + * mac_vlan_list_lock. + **/ +static struct +iavf_vlan_filter *iavf_find_vlan(struct iavf_adapter *adapter, u16 vlan) +{ + struct iavf_vlan_filter *f; + + list_for_each_entry(f, &adapter->vlan_filter_list, list) { + if (vlan == f->vlan) + return f; + } + return NULL; +} + +/** + * iavf_add_vlan - Add a vlan filter to the list + * @adapter: board private structure + * @vlan: VLAN tag + * + * Returns ptr to the filter object or NULL when no memory available. + **/ +static struct +iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter, u16 vlan) +{ + struct iavf_vlan_filter *f = NULL; + + spin_lock_bh(&adapter->mac_vlan_list_lock); + + f = iavf_find_vlan(adapter, vlan); + if (!f) { + f = kzalloc(sizeof(*f), GFP_KERNEL); + if (!f) + goto clearout; + + f->vlan = vlan; + + INIT_LIST_HEAD(&f->list); + list_add(&f->list, &adapter->vlan_filter_list); + f->add = true; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; + } + +clearout: + spin_unlock_bh(&adapter->mac_vlan_list_lock); + return f; +} + +/** + * iavf_del_vlan - Remove a vlan filter from the list + * @adapter: board private structure + * @vlan: VLAN tag + **/ +static void iavf_del_vlan(struct iavf_adapter *adapter, u16 vlan) +{ + struct iavf_vlan_filter *f; + + spin_lock_bh(&adapter->mac_vlan_list_lock); + + f = iavf_find_vlan(adapter, vlan); + if (f) { + f->remove = true; + adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER; + } + + spin_unlock_bh(&adapter->mac_vlan_list_lock); +} + +/** + * iavf_vlan_rx_add_vid - Add a VLAN filter to a device + * @netdev: network device struct + * @proto: unused protocol data + * @vid: VLAN tag + **/ +static int iavf_vlan_rx_add_vid(struct net_device *netdev, + __always_unused __be16 proto, u16 vid) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + if (!VLAN_ALLOWED(adapter)) + return -EIO; + if (iavf_add_vlan(adapter, vid) == NULL) + return -ENOMEM; + return 0; +} + +/** + * iavf_vlan_rx_kill_vid - Remove a VLAN filter from a device + * @netdev: network device struct + * @proto: unused protocol data + * @vid: VLAN tag + **/ +static int iavf_vlan_rx_kill_vid(struct net_device *netdev, + __always_unused __be16 proto, u16 vid) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + if (VLAN_ALLOWED(adapter)) { + iavf_del_vlan(adapter, vid); + return 0; + } + return -EIO; +} + +/** + * iavf_find_filter - Search filter list for specific mac filter + * @adapter: board private structure + * @macaddr: the MAC address + * + * Returns ptr to the filter object or NULL. Must be called while holding the + * mac_vlan_list_lock. + **/ +static struct +iavf_mac_filter *iavf_find_filter(struct iavf_adapter *adapter, + const u8 *macaddr) +{ + struct iavf_mac_filter *f; + + if (!macaddr) + return NULL; + + list_for_each_entry(f, &adapter->mac_filter_list, list) { + if (ether_addr_equal(macaddr, f->macaddr)) + return f; + } + return NULL; +} + +/** + * iavf_add_filter - Add a mac filter to the filter list + * @adapter: board private structure + * @macaddr: the MAC address + * + * Returns ptr to the filter object or NULL when no memory available. + **/ +static struct +iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter, + const u8 *macaddr) +{ + struct iavf_mac_filter *f; + + if (!macaddr) + return NULL; + + f = iavf_find_filter(adapter, macaddr); + if (!f) { + f = kzalloc(sizeof(*f), GFP_ATOMIC); + if (!f) + return f; + + ether_addr_copy(f->macaddr, macaddr); + + list_add_tail(&f->list, &adapter->mac_filter_list); + f->add = true; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER; + } else { + f->remove = false; + } + + return f; +} + +/** + * iavf_set_mac - NDO callback to set port mac address + * @netdev: network interface device structure + * @p: pointer to an address structure + * + * Returns 0 on success, negative on failure + **/ +static int iavf_set_mac(struct net_device *netdev, void *p) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_hw *hw = &adapter->hw; + struct iavf_mac_filter *f; + struct sockaddr *addr = p; + + if (!is_valid_ether_addr(addr->sa_data)) + return -EADDRNOTAVAIL; + + if (ether_addr_equal(netdev->dev_addr, addr->sa_data)) + return 0; + + if (adapter->flags & IAVF_FLAG_ADDR_SET_BY_PF) + return -EPERM; + + spin_lock_bh(&adapter->mac_vlan_list_lock); + + f = iavf_find_filter(adapter, hw->mac.addr); + if (f) { + f->remove = true; + adapter->aq_required |= IAVF_FLAG_AQ_DEL_MAC_FILTER; + } + + f = iavf_add_filter(adapter, addr->sa_data); + + spin_unlock_bh(&adapter->mac_vlan_list_lock); + + if (f) { + ether_addr_copy(hw->mac.addr, addr->sa_data); + ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr); + } + + return (f == NULL) ? -ENOMEM : 0; +} + +/** + * iavf_addr_sync - Callback for dev_(mc|uc)_sync to add address + * @netdev: the netdevice + * @addr: address to add + * + * Called by __dev_(mc|uc)_sync when an address needs to be added. We call + * __dev_(uc|mc)_sync from .set_rx_mode and guarantee to hold the hash lock. + */ +static int iavf_addr_sync(struct net_device *netdev, const u8 *addr) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + if (iavf_add_filter(adapter, addr)) + return 0; + else + return -ENOMEM; +} + +/** + * iavf_addr_unsync - Callback for dev_(mc|uc)_sync to remove address + * @netdev: the netdevice + * @addr: address to add + * + * Called by __dev_(mc|uc)_sync when an address needs to be removed. We call + * __dev_(uc|mc)_sync from .set_rx_mode and guarantee to hold the hash lock. + */ +static int iavf_addr_unsync(struct net_device *netdev, const u8 *addr) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_mac_filter *f; + + /* Under some circumstances, we might receive a request to delete + * our own device address from our uc list. Because we store the + * device address in the VSI's MAC/VLAN filter list, we need to ignore + * such requests and not delete our device address from this list. + */ + if (ether_addr_equal(addr, netdev->dev_addr)) + return 0; + + f = iavf_find_filter(adapter, addr); + if (f) { + f->remove = true; + adapter->aq_required |= IAVF_FLAG_AQ_DEL_MAC_FILTER; + } + return 0; +} + +/** + * iavf_set_rx_mode - NDO callback to set the netdev filters + * @netdev: network interface device structure + **/ +static void iavf_set_rx_mode(struct net_device *netdev) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + spin_lock_bh(&adapter->mac_vlan_list_lock); + __dev_uc_sync(netdev, iavf_addr_sync, iavf_addr_unsync); + __dev_mc_sync(netdev, iavf_addr_sync, iavf_addr_unsync); + spin_unlock_bh(&adapter->mac_vlan_list_lock); + + if (netdev->flags & IFF_PROMISC && + !(adapter->flags & IAVF_FLAG_PROMISC_ON)) + adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_PROMISC; + else if (!(netdev->flags & IFF_PROMISC) && + adapter->flags & IAVF_FLAG_PROMISC_ON) + adapter->aq_required |= IAVF_FLAG_AQ_RELEASE_PROMISC; + + if (netdev->flags & IFF_ALLMULTI && + !(adapter->flags & IAVF_FLAG_ALLMULTI_ON)) + adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_ALLMULTI; + else if (!(netdev->flags & IFF_ALLMULTI) && + adapter->flags & IAVF_FLAG_ALLMULTI_ON) + adapter->aq_required |= IAVF_FLAG_AQ_RELEASE_ALLMULTI; +} + +/** + * iavf_napi_enable_all - enable NAPI on all queue vectors + * @adapter: board private structure + **/ +static void iavf_napi_enable_all(struct iavf_adapter *adapter) +{ + int q_idx; + struct iavf_q_vector *q_vector; + int q_vectors = adapter->num_msix_vectors - NONQ_VECS; + + for (q_idx = 0; q_idx < q_vectors; q_idx++) { + struct napi_struct *napi; + + q_vector = &adapter->q_vectors[q_idx]; + napi = &q_vector->napi; + napi_enable(napi); + } +} + +/** + * iavf_napi_disable_all - disable NAPI on all queue vectors + * @adapter: board private structure + **/ +static void iavf_napi_disable_all(struct iavf_adapter *adapter) +{ + int q_idx; + struct iavf_q_vector *q_vector; + int q_vectors = adapter->num_msix_vectors - NONQ_VECS; + + for (q_idx = 0; q_idx < q_vectors; q_idx++) { + q_vector = &adapter->q_vectors[q_idx]; + napi_disable(&q_vector->napi); + } +} + +/** + * iavf_configure - set up transmit and receive data structures + * @adapter: board private structure + **/ +static void iavf_configure(struct iavf_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + int i; + + iavf_set_rx_mode(netdev); + + iavf_configure_tx(adapter); + iavf_configure_rx(adapter); + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_QUEUES; + + for (i = 0; i < adapter->num_active_queues; i++) { + struct iavf_ring *ring = &adapter->rx_rings[i]; + + iavf_alloc_rx_buffers(ring, IAVF_DESC_UNUSED(ring)); + } +} + +/** + * iavf_up_complete - Finish the last steps of bringing up a connection + * @adapter: board private structure + * + * Expects to be called while holding the __IAVF_IN_CRITICAL_TASK bit lock. + **/ +static void iavf_up_complete(struct iavf_adapter *adapter) +{ + adapter->state = __IAVF_RUNNING; + clear_bit(__IAVF_VSI_DOWN, adapter->vsi.state); + + iavf_napi_enable_all(adapter); + + adapter->aq_required |= IAVF_FLAG_AQ_ENABLE_QUEUES; + if (CLIENT_ENABLED(adapter)) + adapter->flags |= IAVF_FLAG_CLIENT_NEEDS_OPEN; + mod_timer_pending(&adapter->watchdog_timer, jiffies + 1); +} + +/** + * iavf_down - Shutdown the connection processing + * @adapter: board private structure + * + * Expects to be called while holding the __IAVF_IN_CRITICAL_TASK bit lock. + **/ +void iavf_down(struct iavf_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct iavf_vlan_filter *vlf; + struct iavf_mac_filter *f; + struct iavf_cloud_filter *cf; + + if (adapter->state <= __IAVF_DOWN_PENDING) + return; + + netif_carrier_off(netdev); + netif_tx_disable(netdev); + adapter->link_up = false; + iavf_napi_disable_all(adapter); + iavf_irq_disable(adapter); + + spin_lock_bh(&adapter->mac_vlan_list_lock); + + /* clear the sync flag on all filters */ + __dev_uc_unsync(adapter->netdev, NULL); + __dev_mc_unsync(adapter->netdev, NULL); + + /* remove all MAC filters */ + list_for_each_entry(f, &adapter->mac_filter_list, list) { + f->remove = true; + } + + /* remove all VLAN filters */ + list_for_each_entry(vlf, &adapter->vlan_filter_list, list) { + vlf->remove = true; + } + + spin_unlock_bh(&adapter->mac_vlan_list_lock); + + /* remove all cloud filters */ + spin_lock_bh(&adapter->cloud_filter_list_lock); + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + cf->del = true; + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); + + if (!(adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) && + adapter->state != __IAVF_RESETTING) { + /* cancel any current operation */ + adapter->current_op = VIRTCHNL_OP_UNKNOWN; + /* Schedule operations to close down the HW. Don't wait + * here for this to complete. The watchdog is still running + * and it will take care of this. + */ + adapter->aq_required = IAVF_FLAG_AQ_DEL_MAC_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_DEL_CLOUD_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_DISABLE_QUEUES; + } + + mod_timer_pending(&adapter->watchdog_timer, jiffies + 1); +} + +/** + * iavf_acquire_msix_vectors - Setup the MSIX capability + * @adapter: board private structure + * @vectors: number of vectors to request + * + * Work with the OS to set up the MSIX vectors needed. + * + * Returns 0 on success, negative on failure + **/ +static int +iavf_acquire_msix_vectors(struct iavf_adapter *adapter, int vectors) +{ + int err, vector_threshold; + + /* We'll want at least 3 (vector_threshold): + * 0) Other (Admin Queue and link, mostly) + * 1) TxQ[0] Cleanup + * 2) RxQ[0] Cleanup + */ + vector_threshold = MIN_MSIX_COUNT; + + /* The more we get, the more we will assign to Tx/Rx Cleanup + * for the separate queues...where Rx Cleanup >= Tx Cleanup. + * Right now, we simply care about how many we'll get; we'll + * set them up later while requesting irq's. + */ + err = pci_enable_msix_range(adapter->pdev, adapter->msix_entries, + vector_threshold, vectors); + if (err < 0) { + dev_err(&adapter->pdev->dev, "Unable to allocate MSI-X interrupts\n"); + kfree(adapter->msix_entries); + adapter->msix_entries = NULL; + return err; + } + + /* Adjust for only the vectors we'll use, which is minimum + * of max_msix_q_vectors + NONQ_VECS, or the number of + * vectors we were allocated. + */ + adapter->num_msix_vectors = err; + return 0; +} + +/** + * iavf_free_queues - Free memory for all rings + * @adapter: board private structure to initialize + * + * Free all of the memory associated with queue pairs. + **/ +static void iavf_free_queues(struct iavf_adapter *adapter) +{ + if (!adapter->vsi_res) + return; + adapter->num_active_queues = 0; + kfree(adapter->tx_rings); + adapter->tx_rings = NULL; + kfree(adapter->rx_rings); + adapter->rx_rings = NULL; +} + +/** + * iavf_alloc_queues - Allocate memory for all rings + * @adapter: board private structure to initialize + * + * We allocate one ring per queue at run-time since we don't know the + * number of queues at compile-time. The polling_netdev array is + * intended for Multiqueue, but should work fine with a single queue. + **/ +static int iavf_alloc_queues(struct iavf_adapter *adapter) +{ + int i, num_active_queues; + + /* If we're in reset reallocating queues we don't actually know yet for + * certain the PF gave us the number of queues we asked for but we'll + * assume it did. Once basic reset is finished we'll confirm once we + * start negotiating config with PF. + */ + if (adapter->num_req_queues) + num_active_queues = adapter->num_req_queues; + else if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && + adapter->num_tc) + num_active_queues = adapter->ch_config.total_qps; + else + num_active_queues = min_t(int, + adapter->vsi_res->num_queue_pairs, + (int)(num_online_cpus())); + + + adapter->tx_rings = kcalloc(num_active_queues, + sizeof(struct iavf_ring), GFP_KERNEL); + if (!adapter->tx_rings) + goto err_out; + adapter->rx_rings = kcalloc(num_active_queues, + sizeof(struct iavf_ring), GFP_KERNEL); + if (!adapter->rx_rings) + goto err_out; + + for (i = 0; i < num_active_queues; i++) { + struct iavf_ring *tx_ring; + struct iavf_ring *rx_ring; + + tx_ring = &adapter->tx_rings[i]; + + tx_ring->queue_index = i; + tx_ring->netdev = adapter->netdev; + tx_ring->dev = &adapter->pdev->dev; + tx_ring->count = adapter->tx_desc_count; + tx_ring->itr_setting = IAVF_ITR_TX_DEF; + if (adapter->flags & IAVF_FLAG_WB_ON_ITR_CAPABLE) + tx_ring->flags |= IAVF_TXR_FLAGS_WB_ON_ITR; + + rx_ring = &adapter->rx_rings[i]; + rx_ring->queue_index = i; + rx_ring->netdev = adapter->netdev; + rx_ring->dev = &adapter->pdev->dev; + rx_ring->count = adapter->rx_desc_count; + rx_ring->itr_setting = IAVF_ITR_RX_DEF; + } + + adapter->num_active_queues = num_active_queues; + + return 0; + +err_out: + iavf_free_queues(adapter); + return -ENOMEM; +} + +/** + * iavf_set_interrupt_capability - set MSI-X or FAIL if not supported + * @adapter: board private structure to initialize + * + * Attempt to configure the interrupts using the best available + * capabilities of the hardware and the kernel. + **/ +static int iavf_set_interrupt_capability(struct iavf_adapter *adapter) +{ + int vector, v_budget; + int pairs = 0; + int err = 0; + + if (!adapter->vsi_res) { + err = -EIO; + goto out; + } + pairs = adapter->num_active_queues; + + /* It's easy to be greedy for MSI-X vectors, but it really doesn't do + * us much good if we have more vectors than CPUs. However, we already + * limit the total number of queues by the number of CPUs so we do not + * need any further limiting here. + */ + v_budget = min_t(int, pairs + NONQ_VECS, + (int)adapter->vf_res->max_vectors); + + adapter->msix_entries = kcalloc(v_budget, + sizeof(struct msix_entry), GFP_KERNEL); + if (!adapter->msix_entries) { + err = -ENOMEM; + goto out; + } + + for (vector = 0; vector < v_budget; vector++) + adapter->msix_entries[vector].entry = vector; + + err = iavf_acquire_msix_vectors(adapter, v_budget); + +out: + netif_set_real_num_rx_queues(adapter->netdev, pairs); + netif_set_real_num_tx_queues(adapter->netdev, pairs); + return err; +} + +/** + * iavf_config_rss_aq - Configure RSS keys and lut by using AQ commands + * @adapter: board private structure + * + * Return 0 on success, negative on failure + **/ +static int iavf_config_rss_aq(struct iavf_adapter *adapter) +{ + struct i40e_aqc_get_set_rss_key_data *rss_key = + (struct i40e_aqc_get_set_rss_key_data *)adapter->rss_key; + struct iavf_hw *hw = &adapter->hw; + int ret = 0; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot configure RSS, command %d pending\n", + adapter->current_op); + return -EBUSY; + } + + ret = iavf_aq_set_rss_key(hw, adapter->vsi.id, rss_key); + if (ret) { + dev_err(&adapter->pdev->dev, "Cannot set RSS key, err %s aq_err %s\n", + iavf_stat_str(hw, ret), + iavf_aq_str(hw, hw->aq.asq_last_status)); + return ret; + + } + + ret = iavf_aq_set_rss_lut(hw, adapter->vsi.id, false, + adapter->rss_lut, adapter->rss_lut_size); + if (ret) { + dev_err(&adapter->pdev->dev, "Cannot set RSS lut, err %s aq_err %s\n", + iavf_stat_str(hw, ret), + iavf_aq_str(hw, hw->aq.asq_last_status)); + } + + return ret; + +} + +/** + * iavf_config_rss_reg - Configure RSS keys and lut by writing registers + * @adapter: board private structure + * + * Returns 0 on success, negative on failure + **/ +static int iavf_config_rss_reg(struct iavf_adapter *adapter) +{ + struct iavf_hw *hw = &adapter->hw; + u32 *dw; + u16 i; + + dw = (u32 *)adapter->rss_key; + for (i = 0; i <= adapter->rss_key_size / 4; i++) + wr32(hw, IAVF_VFQF_HKEY(i), dw[i]); + + dw = (u32 *)adapter->rss_lut; + for (i = 0; i <= adapter->rss_lut_size / 4; i++) + wr32(hw, IAVF_VFQF_HLUT(i), dw[i]); + + iavf_flush(hw); + + return 0; +} + +/** + * iavf_config_rss - Configure RSS keys and lut + * @adapter: board private structure + * + * Returns 0 on success, negative on failure + **/ +int iavf_config_rss(struct iavf_adapter *adapter) +{ + + if (RSS_PF(adapter)) { + adapter->aq_required |= IAVF_FLAG_AQ_SET_RSS_LUT | + IAVF_FLAG_AQ_SET_RSS_KEY; + return 0; + } else if (RSS_AQ(adapter)) { + return iavf_config_rss_aq(adapter); + } else { + return iavf_config_rss_reg(adapter); + } +} + +/** + * iavf_fill_rss_lut - Fill the lut with default values + * @adapter: board private structure + **/ +static void iavf_fill_rss_lut(struct iavf_adapter *adapter) +{ + u16 i; + + for (i = 0; i < adapter->rss_lut_size; i++) + adapter->rss_lut[i] = i % adapter->num_active_queues; +} + +/** + * iavf_init_rss - Prepare for RSS + * @adapter: board private structure + * + * Return 0 on success, negative on failure + **/ +static int iavf_init_rss(struct iavf_adapter *adapter) +{ + struct iavf_hw *hw = &adapter->hw; + int ret; + + if (!RSS_PF(adapter)) { + /* Enable PCTYPES for RSS, TCP/UDP with IPv4/IPv6 */ + if (adapter->vf_res->vf_cap_flags & + VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2) + adapter->hena = IAVF_DEFAULT_RSS_HENA_EXPANDED; + else + adapter->hena = IAVF_DEFAULT_RSS_HENA; + + wr32(hw, IAVF_VFQF_HENA(0), (u32)adapter->hena); + wr32(hw, IAVF_VFQF_HENA(1), (u32)(adapter->hena >> 32)); + } + + iavf_fill_rss_lut(adapter); + netdev_rss_key_fill((void *)adapter->rss_key, adapter->rss_key_size); + ret = iavf_config_rss(adapter); + + return ret; +} + +/** + * iavf_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 iavf_alloc_q_vectors(struct iavf_adapter *adapter) +{ + int q_idx = 0, num_q_vectors; + struct iavf_q_vector *q_vector; + + num_q_vectors = adapter->num_msix_vectors - NONQ_VECS; + adapter->q_vectors = kcalloc(num_q_vectors, sizeof(*q_vector), + GFP_KERNEL); + if (!adapter->q_vectors) + return -ENOMEM; + + for (q_idx = 0; q_idx < num_q_vectors; q_idx++) { + q_vector = &adapter->q_vectors[q_idx]; + q_vector->adapter = adapter; + q_vector->vsi = &adapter->vsi; + q_vector->v_idx = q_idx; + q_vector->reg_idx = q_idx; + cpumask_copy(&q_vector->affinity_mask, cpu_possible_mask); + netif_napi_add(adapter->netdev, &q_vector->napi, + iavf_napi_poll, NAPI_POLL_WEIGHT); + } + + return 0; +} + +/** + * iavf_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 iavf_free_q_vectors(struct iavf_adapter *adapter) +{ + int q_idx, num_q_vectors; + int napi_vectors; + + if (!adapter->q_vectors) + return; + + num_q_vectors = adapter->num_msix_vectors - NONQ_VECS; + napi_vectors = adapter->num_active_queues; + + for (q_idx = 0; q_idx < num_q_vectors; q_idx++) { + struct iavf_q_vector *q_vector = &adapter->q_vectors[q_idx]; + + if (q_idx < napi_vectors) + netif_napi_del(&q_vector->napi); + } + kfree(adapter->q_vectors); + adapter->q_vectors = NULL; +} + +/** + * iavf_reset_interrupt_capability - Reset MSIX setup + * @adapter: board private structure + * + **/ +void iavf_reset_interrupt_capability(struct iavf_adapter *adapter) +{ + if (!adapter->msix_entries) + return; + + pci_disable_msix(adapter->pdev); + kfree(adapter->msix_entries); + adapter->msix_entries = NULL; +} + +/** + * iavf_init_interrupt_scheme - Determine if MSIX is supported and init + * @adapter: board private structure to initialize + * + **/ +int iavf_init_interrupt_scheme(struct iavf_adapter *adapter) +{ + int err; + + err = iavf_alloc_queues(adapter); + if (err) { + dev_err(&adapter->pdev->dev, + "Unable to allocate memory for queues\n"); + goto err_alloc_queues; + } + + rtnl_lock(); + err = iavf_set_interrupt_capability(adapter); + rtnl_unlock(); + if (err) { + dev_err(&adapter->pdev->dev, + "Unable to setup interrupt capabilities\n"); + goto err_set_interrupt; + } + + err = iavf_alloc_q_vectors(adapter); + if (err) { + dev_err(&adapter->pdev->dev, + "Unable to allocate memory for queue vectors\n"); + goto err_alloc_q_vectors; + } + + /* If we've made it so far while ADq flag being ON, then we haven't + * bailed out anywhere in middle. And ADq isn't just enabled but actual + * resources have been allocated in the reset path. + * Now we can truly claim that ADq is enabled. + */ + if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && + adapter->num_tc) + dev_info(&adapter->pdev->dev, "ADq Enabled, %u TCs created", + adapter->num_tc); + + dev_info(&adapter->pdev->dev, "Multiqueue %s: Queue pair count = %u", + (adapter->num_active_queues > 1) ? "Enabled" : "Disabled", + adapter->num_active_queues); + + return 0; +err_alloc_q_vectors: + iavf_reset_interrupt_capability(adapter); +err_set_interrupt: + iavf_free_queues(adapter); +err_alloc_queues: + return err; +} + +/** + * iavf_free_rss - Free memory used by RSS structs + * @adapter: board private structure + **/ +static void iavf_free_rss(struct iavf_adapter *adapter) +{ + kfree(adapter->rss_key); + adapter->rss_key = NULL; + + kfree(adapter->rss_lut); + adapter->rss_lut = NULL; +} + +/** + * iavf_reinit_interrupt_scheme - Reallocate queues and vectors + * @adapter: board private structure + * + * Returns 0 on success, negative on failure + **/ +static int iavf_reinit_interrupt_scheme(struct iavf_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + int err; + + if (netif_running(netdev)) + iavf_free_traffic_irqs(adapter); + iavf_free_misc_irq(adapter); + iavf_reset_interrupt_capability(adapter); + iavf_free_q_vectors(adapter); + iavf_free_queues(adapter); + + err = iavf_init_interrupt_scheme(adapter); + if (err) + goto err; + + netif_tx_stop_all_queues(netdev); + + err = iavf_request_misc_irq(adapter); + if (err) + goto err; + + set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); + + iavf_map_rings_to_vectors(adapter); + + if (RSS_AQ(adapter)) + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_RSS; + else + err = iavf_init_rss(adapter); +err: + return err; +} + +/** + * iavf_watchdog_timer - Periodic call-back timer + * @data: pointer to adapter disguised as unsigned long + **/ +static void iavf_watchdog_timer(struct timer_list *t) +{ + struct iavf_adapter *adapter = from_timer(adapter, t, + watchdog_timer); + + schedule_work(&adapter->watchdog_task); + /* timer will be rescheduled in watchdog task */ +} + +/** + * iavf_watchdog_task - Periodic call-back task + * @work: pointer to work_struct + **/ +static void iavf_watchdog_task(struct work_struct *work) +{ + struct iavf_adapter *adapter = container_of(work, + struct iavf_adapter, + watchdog_task); + struct iavf_hw *hw = &adapter->hw; + u32 reg_val; + + if (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section)) + goto restart_watchdog; + + if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) { + reg_val = rd32(hw, IAVF_VFGEN_RSTAT) & + IAVF_VFGEN_RSTAT_VFR_STATE_MASK; + if ((reg_val == VIRTCHNL_VFR_VFACTIVE) || + (reg_val == VIRTCHNL_VFR_COMPLETED)) { + /* A chance for redemption! */ + dev_err(&adapter->pdev->dev, "Hardware came out of reset. Attempting reinit.\n"); + adapter->state = __IAVF_STARTUP; + adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; + schedule_delayed_work(&adapter->init_task, 10); + clear_bit(__IAVF_IN_CRITICAL_TASK, + &adapter->crit_section); + /* Don't reschedule the watchdog, since we've restarted + * the init task. When init_task contacts the PF and + * gets everything set up again, it'll restart the + * watchdog for us. Down, boy. Sit. Stay. Woof. + */ + return; + } + adapter->aq_required = 0; + adapter->current_op = VIRTCHNL_OP_UNKNOWN; + goto watchdog_done; + } + + if ((adapter->state < __IAVF_DOWN) || + (adapter->flags & IAVF_FLAG_RESET_PENDING)) + goto watchdog_done; + + /* check for reset */ + reg_val = rd32(hw, IAVF_VF_ARQLEN1) & IAVF_VF_ARQLEN1_ARQENABLE_MASK; + if (!(adapter->flags & IAVF_FLAG_RESET_PENDING) && !reg_val) { + adapter->state = __IAVF_RESETTING; + adapter->flags |= IAVF_FLAG_RESET_PENDING; + dev_err(&adapter->pdev->dev, "Hardware reset detected\n"); + schedule_work(&adapter->reset_task); + adapter->aq_required = 0; + adapter->current_op = VIRTCHNL_OP_UNKNOWN; + goto watchdog_done; + } + + /* Process admin queue tasks. After init, everything gets done + * here so we don't race on the admin queue. + */ + if (adapter->current_op) { + if (!iavf_asq_done(hw)) { + dev_dbg(&adapter->pdev->dev, "Admin queue timeout\n"); + iavf_send_api_ver(adapter); + } + goto watchdog_done; + } + if (adapter->aq_required & IAVF_FLAG_AQ_GET_CONFIG) { + iavf_send_vf_config_msg(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_QUEUES) { + iavf_disable_queues(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_MAP_VECTORS) { + iavf_map_queues(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_ADD_MAC_FILTER) { + iavf_add_ether_addrs(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_ADD_VLAN_FILTER) { + iavf_add_vlans(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_DEL_MAC_FILTER) { + iavf_del_ether_addrs(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_DEL_VLAN_FILTER) { + iavf_del_vlans(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING) { + iavf_enable_vlan_stripping(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING) { + iavf_disable_vlan_stripping(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_QUEUES) { + iavf_configure_queues(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_ENABLE_QUEUES) { + iavf_enable_queues(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_RSS) { + /* This message goes straight to the firmware, not the + * PF, so we don't have to set current_op as we will + * not get a response through the ARQ. + */ + iavf_init_rss(adapter); + adapter->aq_required &= ~IAVF_FLAG_AQ_CONFIGURE_RSS; + goto watchdog_done; + } + if (adapter->aq_required & IAVF_FLAG_AQ_GET_HENA) { + iavf_get_hena(adapter); + goto watchdog_done; + } + if (adapter->aq_required & IAVF_FLAG_AQ_SET_HENA) { + iavf_set_hena(adapter); + goto watchdog_done; + } + if (adapter->aq_required & IAVF_FLAG_AQ_SET_RSS_KEY) { + iavf_set_rss_key(adapter); + goto watchdog_done; + } + if (adapter->aq_required & IAVF_FLAG_AQ_SET_RSS_LUT) { + iavf_set_rss_lut(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_PROMISC) { + iavf_set_promiscuous(adapter, FLAG_VF_UNICAST_PROMISC | + FLAG_VF_MULTICAST_PROMISC); + goto watchdog_done; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_ALLMULTI) { + iavf_set_promiscuous(adapter, FLAG_VF_MULTICAST_PROMISC); + goto watchdog_done; + } + + if ((adapter->aq_required & IAVF_FLAG_AQ_RELEASE_PROMISC) && + (adapter->aq_required & IAVF_FLAG_AQ_RELEASE_ALLMULTI)) { + iavf_set_promiscuous(adapter, 0); + goto watchdog_done; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_ENABLE_CHANNELS) { + iavf_enable_channels(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_CHANNELS) { + iavf_disable_channels(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_ADD_CLOUD_FILTER) { + iavf_add_cloud_filter(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_DEL_CLOUD_FILTER) { + iavf_del_cloud_filter(adapter); + goto watchdog_done; + } + + schedule_delayed_work(&adapter->client_task, msecs_to_jiffies(5)); + + if (adapter->state == __IAVF_RUNNING) + iavf_request_stats(adapter); +watchdog_done: + if (adapter->state == __IAVF_RUNNING) + iavf_detect_recover_hung(&adapter->vsi); + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); +restart_watchdog: + if (adapter->state == __IAVF_REMOVE) + return; + if (adapter->aq_required) + mod_timer(&adapter->watchdog_timer, + jiffies + msecs_to_jiffies(20)); + else + mod_timer(&adapter->watchdog_timer, jiffies + (HZ * 2)); + schedule_work(&adapter->adminq_task); +} + +static void iavf_disable_vf(struct iavf_adapter *adapter) +{ + struct iavf_mac_filter *f, *ftmp; + struct iavf_vlan_filter *fv, *fvtmp; + struct iavf_cloud_filter *cf, *cftmp; + + adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED; + + /* We don't use netif_running() because it may be true prior to + * ndo_open() returning, so we can't assume it means all our open + * tasks have finished, since we're not holding the rtnl_lock here. + */ + if (adapter->state == __IAVF_RUNNING) { + set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); + netif_carrier_off(adapter->netdev); + netif_tx_disable(adapter->netdev); + adapter->link_up = false; + iavf_napi_disable_all(adapter); + iavf_irq_disable(adapter); + iavf_free_traffic_irqs(adapter); + iavf_free_all_tx_resources(adapter); + iavf_free_all_rx_resources(adapter); + } + + spin_lock_bh(&adapter->mac_vlan_list_lock); + + /* Delete all of the filters */ + list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, list) { + list_del(&f->list); + kfree(f); + } + + list_for_each_entry_safe(fv, fvtmp, &adapter->vlan_filter_list, list) { + list_del(&fv->list); + kfree(fv); + } + + spin_unlock_bh(&adapter->mac_vlan_list_lock); + + spin_lock_bh(&adapter->cloud_filter_list_lock); + list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, list) { + list_del(&cf->list); + kfree(cf); + adapter->num_cloud_filters--; + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); + + iavf_free_misc_irq(adapter); + iavf_reset_interrupt_capability(adapter); + iavf_free_queues(adapter); + iavf_free_q_vectors(adapter); + kfree(adapter->vf_res); + iavf_shutdown_adminq(&adapter->hw); + adapter->netdev->flags &= ~IFF_UP; + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); + adapter->flags &= ~IAVF_FLAG_RESET_PENDING; + adapter->state = __IAVF_DOWN; + wake_up(&adapter->down_waitqueue); + dev_info(&adapter->pdev->dev, "Reset task did not complete, VF disabled\n"); +} + +#define IAVF_RESET_WAIT_MS 10 +#define IAVF_RESET_WAIT_COUNT 500 +/** + * iavf_reset_task - Call-back task to handle hardware reset + * @work: pointer to work_struct + * + * During reset we need to shut down and reinitialize the admin queue + * before we can use it to communicate with the PF again. We also clear + * and reinit the rings because that context is lost as well. + **/ +static void iavf_reset_task(struct work_struct *work) +{ + struct iavf_adapter *adapter = container_of(work, + struct iavf_adapter, + reset_task); + struct virtchnl_vf_resource *vfres = adapter->vf_res; + struct net_device *netdev = adapter->netdev; + struct iavf_hw *hw = &adapter->hw; + struct iavf_vlan_filter *vlf; + struct iavf_cloud_filter *cf; + struct iavf_mac_filter *f; + u32 reg_val; + int i = 0, err; + bool running; + + /* When device is being removed it doesn't make sense to run the reset + * task, just return in such a case. + */ + if (test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) + return; + + while (test_and_set_bit(__IAVF_IN_CLIENT_TASK, + &adapter->crit_section)) + usleep_range(500, 1000); + if (CLIENT_ENABLED(adapter)) { + adapter->flags &= ~(IAVF_FLAG_CLIENT_NEEDS_OPEN | + IAVF_FLAG_CLIENT_NEEDS_CLOSE | + IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS | + IAVF_FLAG_SERVICE_CLIENT_REQUESTED); + cancel_delayed_work_sync(&adapter->client_task); + iavf_notify_client_close(&adapter->vsi, true); + } + iavf_misc_irq_disable(adapter); + if (adapter->flags & IAVF_FLAG_RESET_NEEDED) { + adapter->flags &= ~IAVF_FLAG_RESET_NEEDED; + /* Restart the AQ here. If we have been reset but didn't + * detect it, or if the PF had to reinit, our AQ will be hosed. + */ + iavf_shutdown_adminq(hw); + iavf_init_adminq(hw); + iavf_request_reset(adapter); + } + adapter->flags |= IAVF_FLAG_RESET_PENDING; + + /* poll until we see the reset actually happen */ + for (i = 0; i < IAVF_RESET_WAIT_COUNT; i++) { + reg_val = rd32(hw, IAVF_VF_ARQLEN1) & + IAVF_VF_ARQLEN1_ARQENABLE_MASK; + if (!reg_val) + break; + usleep_range(5000, 10000); + } + if (i == IAVF_RESET_WAIT_COUNT) { + dev_info(&adapter->pdev->dev, "Never saw reset\n"); + goto continue_reset; /* act like the reset happened */ + } + + /* wait until the reset is complete and the PF is responding to us */ + for (i = 0; i < IAVF_RESET_WAIT_COUNT; i++) { + /* sleep first to make sure a minimum wait time is met */ + msleep(IAVF_RESET_WAIT_MS); + + reg_val = rd32(hw, IAVF_VFGEN_RSTAT) & + IAVF_VFGEN_RSTAT_VFR_STATE_MASK; + if (reg_val == VIRTCHNL_VFR_VFACTIVE) + break; + } + + pci_set_master(adapter->pdev); + + if (i == IAVF_RESET_WAIT_COUNT) { + dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n", + reg_val); + iavf_disable_vf(adapter); + clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section); + return; /* Do not attempt to reinit. It's dead, Jim. */ + } + +continue_reset: + /* We don't use netif_running() because it may be true prior to + * ndo_open() returning, so we can't assume it means all our open + * tasks have finished, since we're not holding the rtnl_lock here. + */ + running = ((adapter->state == __IAVF_RUNNING) || + (adapter->state == __IAVF_RESETTING)); + + if (running) { + netif_carrier_off(netdev); + netif_tx_stop_all_queues(netdev); + adapter->link_up = false; + iavf_napi_disable_all(adapter); + } + iavf_irq_disable(adapter); + + adapter->state = __IAVF_RESETTING; + adapter->flags &= ~IAVF_FLAG_RESET_PENDING; + + /* free the Tx/Rx rings and descriptors, might be better to just + * re-use them sometime in the future + */ + iavf_free_all_rx_resources(adapter); + iavf_free_all_tx_resources(adapter); + + adapter->flags |= IAVF_FLAG_QUEUES_DISABLED; + /* kill and reinit the admin queue */ + iavf_shutdown_adminq(hw); + adapter->current_op = VIRTCHNL_OP_UNKNOWN; + err = iavf_init_adminq(hw); + if (err) + dev_info(&adapter->pdev->dev, "Failed to init adminq: %d\n", + err); + adapter->aq_required = 0; + + if (adapter->flags & IAVF_FLAG_REINIT_ITR_NEEDED) { + err = iavf_reinit_interrupt_scheme(adapter); + if (err) + goto reset_err; + } + + adapter->aq_required |= IAVF_FLAG_AQ_GET_CONFIG; + adapter->aq_required |= IAVF_FLAG_AQ_MAP_VECTORS; + + spin_lock_bh(&adapter->mac_vlan_list_lock); + + /* re-add all MAC filters */ + list_for_each_entry(f, &adapter->mac_filter_list, list) { + f->add = true; + } + /* re-add all VLAN filters */ + list_for_each_entry(vlf, &adapter->vlan_filter_list, list) { + vlf->add = true; + } + + spin_unlock_bh(&adapter->mac_vlan_list_lock); + + /* check if TCs are running and re-add all cloud filters */ + spin_lock_bh(&adapter->cloud_filter_list_lock); + if ((vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && + adapter->num_tc) { + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + cf->add = true; + } + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); + + adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_CLOUD_FILTER; + iavf_misc_irq_enable(adapter); + + mod_timer(&adapter->watchdog_timer, jiffies + 2); + + /* We were running when the reset started, so we need to restore some + * state here. + */ + if (running) { + /* allocate transmit descriptors */ + err = iavf_setup_all_tx_resources(adapter); + if (err) + goto reset_err; + + /* allocate receive descriptors */ + err = iavf_setup_all_rx_resources(adapter); + if (err) + goto reset_err; + + if (adapter->flags & IAVF_FLAG_REINIT_ITR_NEEDED) { + err = iavf_request_traffic_irqs(adapter, netdev->name); + if (err) + goto reset_err; + + adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; + } + + iavf_configure(adapter); + + iavf_up_complete(adapter); + + iavf_irq_enable(adapter, true); + } else { + adapter->state = __IAVF_DOWN; + wake_up(&adapter->down_waitqueue); + } + clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section); + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); + + return; +reset_err: + clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section); + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); + dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); + iavf_close(netdev); +} + +/** + * iavf_adminq_task - worker thread to clean the admin queue + * @work: pointer to work_struct containing our data + **/ +static void iavf_adminq_task(struct work_struct *work) +{ + struct iavf_adapter *adapter = + container_of(work, struct iavf_adapter, adminq_task); + struct iavf_hw *hw = &adapter->hw; + struct i40e_arq_event_info event; + enum virtchnl_ops v_op; + iavf_status ret, v_ret; + u32 val, oldval; + u16 pending; + + if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) + goto out; + + event.buf_len = IAVF_MAX_AQ_BUF_SIZE; + event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL); + if (!event.msg_buf) + goto out; + + do { + ret = iavf_clean_arq_element(hw, &event, &pending); + v_op = (enum virtchnl_ops)le32_to_cpu(event.desc.cookie_high); + v_ret = (iavf_status)le32_to_cpu(event.desc.cookie_low); + + if (ret || !v_op) + break; /* No event to process or error cleaning ARQ */ + + iavf_virtchnl_completion(adapter, v_op, v_ret, event.msg_buf, + event.msg_len); + if (pending != 0) + memset(event.msg_buf, 0, IAVF_MAX_AQ_BUF_SIZE); + } while (pending); + + if ((adapter->flags & + (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED)) || + adapter->state == __IAVF_RESETTING) + goto freedom; + + /* check for error indications */ + val = rd32(hw, hw->aq.arq.len); + if (val == 0xdeadbeef) /* indicates device in reset */ + goto freedom; + oldval = val; + if (val & IAVF_VF_ARQLEN1_ARQVFE_MASK) { + dev_info(&adapter->pdev->dev, "ARQ VF Error detected\n"); + val &= ~IAVF_VF_ARQLEN1_ARQVFE_MASK; + } + if (val & IAVF_VF_ARQLEN1_ARQOVFL_MASK) { + dev_info(&adapter->pdev->dev, "ARQ Overflow Error detected\n"); + val &= ~IAVF_VF_ARQLEN1_ARQOVFL_MASK; + } + if (val & IAVF_VF_ARQLEN1_ARQCRIT_MASK) { + dev_info(&adapter->pdev->dev, "ARQ Critical Error detected\n"); + val &= ~IAVF_VF_ARQLEN1_ARQCRIT_MASK; + } + if (oldval != val) + wr32(hw, hw->aq.arq.len, val); + + val = rd32(hw, hw->aq.asq.len); + oldval = val; + if (val & IAVF_VF_ATQLEN1_ATQVFE_MASK) { + dev_info(&adapter->pdev->dev, "ASQ VF Error detected\n"); + val &= ~IAVF_VF_ATQLEN1_ATQVFE_MASK; + } + if (val & IAVF_VF_ATQLEN1_ATQOVFL_MASK) { + dev_info(&adapter->pdev->dev, "ASQ Overflow Error detected\n"); + val &= ~IAVF_VF_ATQLEN1_ATQOVFL_MASK; + } + if (val & IAVF_VF_ATQLEN1_ATQCRIT_MASK) { + dev_info(&adapter->pdev->dev, "ASQ Critical Error detected\n"); + val &= ~IAVF_VF_ATQLEN1_ATQCRIT_MASK; + } + if (oldval != val) + wr32(hw, hw->aq.asq.len, val); + +freedom: + kfree(event.msg_buf); +out: + /* re-enable Admin queue interrupt cause */ + iavf_misc_irq_enable(adapter); +} + +/** + * iavf_client_task - worker thread to perform client work + * @work: pointer to work_struct containing our data + * + * This task handles client interactions. Because client calls can be + * reentrant, we can't handle them in the watchdog. + **/ +static void iavf_client_task(struct work_struct *work) +{ + struct iavf_adapter *adapter = + container_of(work, struct iavf_adapter, client_task.work); + + /* If we can't get the client bit, just give up. We'll be rescheduled + * later. + */ + + if (test_and_set_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section)) + return; + + if (adapter->flags & IAVF_FLAG_SERVICE_CLIENT_REQUESTED) { + iavf_client_subtask(adapter); + adapter->flags &= ~IAVF_FLAG_SERVICE_CLIENT_REQUESTED; + goto out; + } + if (adapter->flags & IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS) { + iavf_notify_client_l2_params(&adapter->vsi); + adapter->flags &= ~IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS; + goto out; + } + if (adapter->flags & IAVF_FLAG_CLIENT_NEEDS_CLOSE) { + iavf_notify_client_close(&adapter->vsi, false); + adapter->flags &= ~IAVF_FLAG_CLIENT_NEEDS_CLOSE; + goto out; + } + if (adapter->flags & IAVF_FLAG_CLIENT_NEEDS_OPEN) { + iavf_notify_client_open(&adapter->vsi); + adapter->flags &= ~IAVF_FLAG_CLIENT_NEEDS_OPEN; + } +out: + clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section); +} + +/** + * iavf_free_all_tx_resources - Free Tx Resources for All Queues + * @adapter: board private structure + * + * Free all transmit software resources + **/ +void iavf_free_all_tx_resources(struct iavf_adapter *adapter) +{ + int i; + + if (!adapter->tx_rings) + return; + + for (i = 0; i < adapter->num_active_queues; i++) + if (adapter->tx_rings[i].desc) + iavf_free_tx_resources(&adapter->tx_rings[i]); +} + +/** + * iavf_setup_all_tx_resources - allocate all queues Tx resources + * @adapter: board private structure + * + * If this function returns with an error, then it's possible one or + * more of the rings is populated (while the rest are not). It is the + * callers duty to clean those orphaned rings. + * + * Return 0 on success, negative on failure + **/ +static int iavf_setup_all_tx_resources(struct iavf_adapter *adapter) +{ + int i, err = 0; + + for (i = 0; i < adapter->num_active_queues; i++) { + adapter->tx_rings[i].count = adapter->tx_desc_count; + err = iavf_setup_tx_descriptors(&adapter->tx_rings[i]); + if (!err) + continue; + dev_err(&adapter->pdev->dev, + "Allocation for Tx Queue %u failed\n", i); + break; + } + + return err; +} + +/** + * iavf_setup_all_rx_resources - allocate all queues Rx resources + * @adapter: board private structure + * + * If this function returns with an error, then it's possible one or + * more of the rings is populated (while the rest are not). It is the + * callers duty to clean those orphaned rings. + * + * Return 0 on success, negative on failure + **/ +static int iavf_setup_all_rx_resources(struct iavf_adapter *adapter) +{ + int i, err = 0; + + for (i = 0; i < adapter->num_active_queues; i++) { + adapter->rx_rings[i].count = adapter->rx_desc_count; + err = iavf_setup_rx_descriptors(&adapter->rx_rings[i]); + if (!err) + continue; + dev_err(&adapter->pdev->dev, + "Allocation for Rx Queue %u failed\n", i); + break; + } + return err; +} + +/** + * iavf_free_all_rx_resources - Free Rx Resources for All Queues + * @adapter: board private structure + * + * Free all receive software resources + **/ +void iavf_free_all_rx_resources(struct iavf_adapter *adapter) +{ + int i; + + if (!adapter->rx_rings) + return; + + for (i = 0; i < adapter->num_active_queues; i++) + if (adapter->rx_rings[i].desc) + iavf_free_rx_resources(&adapter->rx_rings[i]); +} + +/** + * iavf_validate_tx_bandwidth - validate the max Tx bandwidth + * @adapter: board private structure + * @max_tx_rate: max Tx bw for a tc + **/ +static int iavf_validate_tx_bandwidth(struct iavf_adapter *adapter, + u64 max_tx_rate) +{ + int speed = 0, ret = 0; + + switch (adapter->link_speed) { + case I40E_LINK_SPEED_40GB: + speed = 40000; + break; + case I40E_LINK_SPEED_25GB: + speed = 25000; + break; + case I40E_LINK_SPEED_20GB: + speed = 20000; + break; + case I40E_LINK_SPEED_10GB: + speed = 10000; + break; + case I40E_LINK_SPEED_1GB: + speed = 1000; + break; + case I40E_LINK_SPEED_100MB: + speed = 100; + break; + default: + break; + } + + if (max_tx_rate > speed) { + dev_err(&adapter->pdev->dev, + "Invalid tx rate specified\n"); + ret = -EINVAL; + } + + return ret; +} + +/** + * iavf_validate_channel_config - validate queue mapping info + * @adapter: board private structure + * @mqprio_qopt: queue parameters + * + * This function validates if the config provided by the user to + * configure queue channels is valid or not. Returns 0 on a valid + * config. + **/ +static int iavf_validate_ch_config(struct iavf_adapter *adapter, + struct tc_mqprio_qopt_offload *mqprio_qopt) +{ + u64 total_max_rate = 0; + int i, num_qps = 0; + u64 tx_rate = 0; + int ret = 0; + + if (mqprio_qopt->qopt.num_tc > IAVF_MAX_TRAFFIC_CLASS || + mqprio_qopt->qopt.num_tc < 1) + return -EINVAL; + + for (i = 0; i <= mqprio_qopt->qopt.num_tc - 1; i++) { + if (!mqprio_qopt->qopt.count[i] || + mqprio_qopt->qopt.offset[i] != num_qps) + return -EINVAL; + if (mqprio_qopt->min_rate[i]) { + dev_err(&adapter->pdev->dev, + "Invalid min tx rate (greater than 0) specified\n"); + return -EINVAL; + } + /*convert to Mbps */ + tx_rate = div_u64(mqprio_qopt->max_rate[i], + IAVF_MBPS_DIVISOR); + total_max_rate += tx_rate; + num_qps += mqprio_qopt->qopt.count[i]; + } + if (num_qps > IAVF_MAX_REQ_QUEUES) + return -EINVAL; + + ret = iavf_validate_tx_bandwidth(adapter, total_max_rate); + return ret; +} + +/** + * iavf_del_all_cloud_filters - delete all cloud filters + * on the traffic classes + **/ +static void iavf_del_all_cloud_filters(struct iavf_adapter *adapter) +{ + struct iavf_cloud_filter *cf, *cftmp; + + spin_lock_bh(&adapter->cloud_filter_list_lock); + list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, + list) { + list_del(&cf->list); + kfree(cf); + adapter->num_cloud_filters--; + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); +} + +/** + * __iavf_setup_tc - configure multiple traffic classes + * @netdev: network interface device structure + * @type_date: tc offload data + * + * This function processes the config information provided by the + * user to configure traffic classes/queue channels and packages the + * information to request the PF to setup traffic classes. + * + * Returns 0 on success. + **/ +static int __iavf_setup_tc(struct net_device *netdev, void *type_data) +{ + struct tc_mqprio_qopt_offload *mqprio_qopt = type_data; + struct iavf_adapter *adapter = netdev_priv(netdev); + struct virtchnl_vf_resource *vfres = adapter->vf_res; + u8 num_tc = 0, total_qps = 0; + int ret = 0, netdev_tc = 0; + u64 max_tx_rate; + u16 mode; + int i; + + num_tc = mqprio_qopt->qopt.num_tc; + mode = mqprio_qopt->mode; + + /* delete queue_channel */ + if (!mqprio_qopt->qopt.hw) { + if (adapter->ch_config.state == __IAVF_TC_RUNNING) { + /* reset the tc configuration */ + netdev_reset_tc(netdev); + adapter->num_tc = 0; + netif_tx_stop_all_queues(netdev); + netif_tx_disable(netdev); + iavf_del_all_cloud_filters(adapter); + adapter->aq_required = IAVF_FLAG_AQ_DISABLE_CHANNELS; + goto exit; + } else { + return -EINVAL; + } + } + + /* add queue channel */ + if (mode == TC_MQPRIO_MODE_CHANNEL) { + if (!(vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ)) { + dev_err(&adapter->pdev->dev, "ADq not supported\n"); + return -EOPNOTSUPP; + } + if (adapter->ch_config.state != __IAVF_TC_INVALID) { + dev_err(&adapter->pdev->dev, "TC configuration already exists\n"); + return -EINVAL; + } + + ret = iavf_validate_ch_config(adapter, mqprio_qopt); + if (ret) + return ret; + /* Return if same TC config is requested */ + if (adapter->num_tc == num_tc) + return 0; + adapter->num_tc = num_tc; + + for (i = 0; i < IAVF_MAX_TRAFFIC_CLASS; i++) { + if (i < num_tc) { + adapter->ch_config.ch_info[i].count = + mqprio_qopt->qopt.count[i]; + adapter->ch_config.ch_info[i].offset = + mqprio_qopt->qopt.offset[i]; + total_qps += mqprio_qopt->qopt.count[i]; + max_tx_rate = mqprio_qopt->max_rate[i]; + /* convert to Mbps */ + max_tx_rate = div_u64(max_tx_rate, + IAVF_MBPS_DIVISOR); + adapter->ch_config.ch_info[i].max_tx_rate = + max_tx_rate; + } else { + adapter->ch_config.ch_info[i].count = 1; + adapter->ch_config.ch_info[i].offset = 0; + } + } + adapter->ch_config.total_qps = total_qps; + netif_tx_stop_all_queues(netdev); + netif_tx_disable(netdev); + adapter->aq_required |= IAVF_FLAG_AQ_ENABLE_CHANNELS; + netdev_reset_tc(netdev); + /* Report the tc mapping up the stack */ + netdev_set_num_tc(adapter->netdev, num_tc); + for (i = 0; i < IAVF_MAX_TRAFFIC_CLASS; i++) { + u16 qcount = mqprio_qopt->qopt.count[i]; + u16 qoffset = mqprio_qopt->qopt.offset[i]; + + if (i < num_tc) + netdev_set_tc_queue(netdev, netdev_tc++, qcount, + qoffset); + } + } +exit: + return ret; +} + +/** + * iavf_parse_cls_flower - Parse tc flower filters provided by kernel + * @adapter: board private structure + * @cls_flower: pointer to struct tc_cls_flower_offload + * @filter: pointer to cloud filter structure + */ +static int iavf_parse_cls_flower(struct iavf_adapter *adapter, + struct tc_cls_flower_offload *f, + struct iavf_cloud_filter *filter) +{ + u16 n_proto_mask = 0; + u16 n_proto_key = 0; + u8 field_flags = 0; + u16 addr_type = 0; + u16 n_proto = 0; + int i = 0; + struct virtchnl_filter *vf = &filter->f; + + if (f->dissector->used_keys & + ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | + BIT(FLOW_DISSECTOR_KEY_BASIC) | + BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_VLAN) | + BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_PORTS) | + BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) { + dev_err(&adapter->pdev->dev, "Unsupported key used: 0x%x\n", + f->dissector->used_keys); + return -EOPNOTSUPP; + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_dissector_key_keyid *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ENC_KEYID, + f->mask); + + if (mask->keyid != 0) + field_flags |= IAVF_CLOUD_FIELD_TEN_ID; + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_dissector_key_basic *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_BASIC, + f->key); + + struct flow_dissector_key_basic *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_BASIC, + f->mask); + n_proto_key = ntohs(key->n_proto); + n_proto_mask = ntohs(mask->n_proto); + + if (n_proto_key == ETH_P_ALL) { + n_proto_key = 0; + n_proto_mask = 0; + } + n_proto = n_proto_key & n_proto_mask; + if (n_proto != ETH_P_IP && n_proto != ETH_P_IPV6) + return -EINVAL; + if (n_proto == ETH_P_IPV6) { + /* specify flow type as TCP IPv6 */ + vf->flow_type = VIRTCHNL_TCP_V6_FLOW; + } + + if (key->ip_proto != IPPROTO_TCP) { + dev_info(&adapter->pdev->dev, "Only TCP transport is supported\n"); + return -EINVAL; + } + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_dissector_key_eth_addrs *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ETH_ADDRS, + f->key); + + struct flow_dissector_key_eth_addrs *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ETH_ADDRS, + f->mask); + /* use is_broadcast and is_zero to check for all 0xf or 0 */ + if (!is_zero_ether_addr(mask->dst)) { + if (is_broadcast_ether_addr(mask->dst)) { + field_flags |= IAVF_CLOUD_FIELD_OMAC; + } else { + dev_err(&adapter->pdev->dev, "Bad ether dest mask %pM\n", + mask->dst); + return I40E_ERR_CONFIG; + } + } + + if (!is_zero_ether_addr(mask->src)) { + if (is_broadcast_ether_addr(mask->src)) { + field_flags |= IAVF_CLOUD_FIELD_IMAC; + } else { + dev_err(&adapter->pdev->dev, "Bad ether src mask %pM\n", + mask->src); + return I40E_ERR_CONFIG; + } + } + + if (!is_zero_ether_addr(key->dst)) + if (is_valid_ether_addr(key->dst) || + is_multicast_ether_addr(key->dst)) { + /* set the mask if a valid dst_mac address */ + for (i = 0; i < ETH_ALEN; i++) + vf->mask.tcp_spec.dst_mac[i] |= 0xff; + ether_addr_copy(vf->data.tcp_spec.dst_mac, + key->dst); + } + + if (!is_zero_ether_addr(key->src)) + if (is_valid_ether_addr(key->src) || + is_multicast_ether_addr(key->src)) { + /* set the mask if a valid dst_mac address */ + for (i = 0; i < ETH_ALEN; i++) + vf->mask.tcp_spec.src_mac[i] |= 0xff; + ether_addr_copy(vf->data.tcp_spec.src_mac, + key->src); + } + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_dissector_key_vlan *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_VLAN, + f->key); + struct flow_dissector_key_vlan *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_VLAN, + f->mask); + + if (mask->vlan_id) { + if (mask->vlan_id == VLAN_VID_MASK) { + field_flags |= IAVF_CLOUD_FIELD_IVLAN; + } else { + dev_err(&adapter->pdev->dev, "Bad vlan mask %u\n", + mask->vlan_id); + return I40E_ERR_CONFIG; + } + } + vf->mask.tcp_spec.vlan_id |= cpu_to_be16(0xffff); + vf->data.tcp_spec.vlan_id = cpu_to_be16(key->vlan_id); + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_dissector_key_control *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_CONTROL, + f->key); + + addr_type = key->addr_type; + } + + if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + struct flow_dissector_key_ipv4_addrs *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS, + f->key); + struct flow_dissector_key_ipv4_addrs *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS, + f->mask); + + if (mask->dst) { + if (mask->dst == cpu_to_be32(0xffffffff)) { + field_flags |= IAVF_CLOUD_FIELD_IIP; + } else { + dev_err(&adapter->pdev->dev, "Bad ip dst mask 0x%08x\n", + be32_to_cpu(mask->dst)); + return I40E_ERR_CONFIG; + } + } + + if (mask->src) { + if (mask->src == cpu_to_be32(0xffffffff)) { + field_flags |= IAVF_CLOUD_FIELD_IIP; + } else { + dev_err(&adapter->pdev->dev, "Bad ip src mask 0x%08x\n", + be32_to_cpu(mask->dst)); + return I40E_ERR_CONFIG; + } + } + + if (field_flags & IAVF_CLOUD_FIELD_TEN_ID) { + dev_info(&adapter->pdev->dev, "Tenant id not allowed for ip filter\n"); + return I40E_ERR_CONFIG; + } + if (key->dst) { + vf->mask.tcp_spec.dst_ip[0] |= cpu_to_be32(0xffffffff); + vf->data.tcp_spec.dst_ip[0] = key->dst; + } + if (key->src) { + vf->mask.tcp_spec.src_ip[0] |= cpu_to_be32(0xffffffff); + vf->data.tcp_spec.src_ip[0] = key->src; + } + } + + if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + struct flow_dissector_key_ipv6_addrs *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS, + f->key); + struct flow_dissector_key_ipv6_addrs *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS, + f->mask); + + /* validate mask, make sure it is not IPV6_ADDR_ANY */ + if (ipv6_addr_any(&mask->dst)) { + dev_err(&adapter->pdev->dev, "Bad ipv6 dst mask 0x%02x\n", + IPV6_ADDR_ANY); + return I40E_ERR_CONFIG; + } + + /* src and dest IPv6 address should not be LOOPBACK + * (0:0:0:0:0:0:0:1) which can be represented as ::1 + */ + if (ipv6_addr_loopback(&key->dst) || + ipv6_addr_loopback(&key->src)) { + dev_err(&adapter->pdev->dev, + "ipv6 addr should not be loopback\n"); + return I40E_ERR_CONFIG; + } + if (!ipv6_addr_any(&mask->dst) || !ipv6_addr_any(&mask->src)) + field_flags |= IAVF_CLOUD_FIELD_IIP; + + for (i = 0; i < 4; i++) + vf->mask.tcp_spec.dst_ip[i] |= cpu_to_be32(0xffffffff); + memcpy(&vf->data.tcp_spec.dst_ip, &key->dst.s6_addr32, + sizeof(vf->data.tcp_spec.dst_ip)); + for (i = 0; i < 4; i++) + vf->mask.tcp_spec.src_ip[i] |= cpu_to_be32(0xffffffff); + memcpy(&vf->data.tcp_spec.src_ip, &key->src.s6_addr32, + sizeof(vf->data.tcp_spec.src_ip)); + } + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_dissector_key_ports *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_PORTS, + f->key); + struct flow_dissector_key_ports *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_PORTS, + f->mask); + + if (mask->src) { + if (mask->src == cpu_to_be16(0xffff)) { + field_flags |= IAVF_CLOUD_FIELD_IIP; + } else { + dev_err(&adapter->pdev->dev, "Bad src port mask %u\n", + be16_to_cpu(mask->src)); + return I40E_ERR_CONFIG; + } + } + + if (mask->dst) { + if (mask->dst == cpu_to_be16(0xffff)) { + field_flags |= IAVF_CLOUD_FIELD_IIP; + } else { + dev_err(&adapter->pdev->dev, "Bad dst port mask %u\n", + be16_to_cpu(mask->dst)); + return I40E_ERR_CONFIG; + } + } + if (key->dst) { + vf->mask.tcp_spec.dst_port |= cpu_to_be16(0xffff); + vf->data.tcp_spec.dst_port = key->dst; + } + + if (key->src) { + vf->mask.tcp_spec.src_port |= cpu_to_be16(0xffff); + vf->data.tcp_spec.src_port = key->src; + } + } + vf->field_flags = field_flags; + + return 0; +} + +/** + * iavf_handle_tclass - Forward to a traffic class on the device + * @adapter: board private structure + * @tc: traffic class index on the device + * @filter: pointer to cloud filter structure + */ +static int iavf_handle_tclass(struct iavf_adapter *adapter, u32 tc, + struct iavf_cloud_filter *filter) +{ + if (tc == 0) + return 0; + if (tc < adapter->num_tc) { + if (!filter->f.data.tcp_spec.dst_port) { + dev_err(&adapter->pdev->dev, + "Specify destination port to redirect to traffic class other than TC0\n"); + return -EINVAL; + } + } + /* redirect to a traffic class on the same device */ + filter->f.action = VIRTCHNL_ACTION_TC_REDIRECT; + filter->f.action_meta = tc; + return 0; +} + +/** + * iavf_configure_clsflower - Add tc flower filters + * @adapter: board private structure + * @cls_flower: Pointer to struct tc_cls_flower_offload + */ +static int iavf_configure_clsflower(struct iavf_adapter *adapter, + struct tc_cls_flower_offload *cls_flower) +{ + int tc = tc_classid_to_hwtc(adapter->netdev, cls_flower->classid); + struct iavf_cloud_filter *filter = NULL; + int err = -EINVAL, count = 50; + + if (tc < 0) { + dev_err(&adapter->pdev->dev, "Invalid traffic class\n"); + return -EINVAL; + } + + filter = kzalloc(sizeof(*filter), GFP_KERNEL); + if (!filter) + return -ENOMEM; + + while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, + &adapter->crit_section)) { + if (--count == 0) + goto err; + udelay(1); + } + + filter->cookie = cls_flower->cookie; + + /* set the mask to all zeroes to begin with */ + memset(&filter->f.mask.tcp_spec, 0, sizeof(struct virtchnl_l4_spec)); + /* start out with flow type and eth type IPv4 to begin with */ + filter->f.flow_type = VIRTCHNL_TCP_V4_FLOW; + err = iavf_parse_cls_flower(adapter, cls_flower, filter); + if (err < 0) + goto err; + + err = iavf_handle_tclass(adapter, tc, filter); + if (err < 0) + goto err; + + /* add filter to the list */ + spin_lock_bh(&adapter->cloud_filter_list_lock); + list_add_tail(&filter->list, &adapter->cloud_filter_list); + adapter->num_cloud_filters++; + filter->add = true; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_CLOUD_FILTER; + spin_unlock_bh(&adapter->cloud_filter_list_lock); +err: + if (err) + kfree(filter); + + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); + return err; +} + +/* iavf_find_cf - Find the cloud filter in the list + * @adapter: Board private structure + * @cookie: filter specific cookie + * + * Returns ptr to the filter object or NULL. Must be called while holding the + * cloud_filter_list_lock. + */ +static struct iavf_cloud_filter *iavf_find_cf(struct iavf_adapter *adapter, + unsigned long *cookie) +{ + struct iavf_cloud_filter *filter = NULL; + + if (!cookie) + return NULL; + + list_for_each_entry(filter, &adapter->cloud_filter_list, list) { + if (!memcmp(cookie, &filter->cookie, sizeof(filter->cookie))) + return filter; + } + return NULL; +} + +/** + * iavf_delete_clsflower - Remove tc flower filters + * @adapter: board private structure + * @cls_flower: Pointer to struct tc_cls_flower_offload + */ +static int iavf_delete_clsflower(struct iavf_adapter *adapter, + struct tc_cls_flower_offload *cls_flower) +{ + struct iavf_cloud_filter *filter = NULL; + int err = 0; + + spin_lock_bh(&adapter->cloud_filter_list_lock); + filter = iavf_find_cf(adapter, &cls_flower->cookie); + if (filter) { + filter->del = true; + adapter->aq_required |= IAVF_FLAG_AQ_DEL_CLOUD_FILTER; + } else { + err = -EINVAL; + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); + + return err; +} + +/** + * iavf_setup_tc_cls_flower - flower classifier offloads + * @netdev: net device to configure + * @type_data: offload data + */ +static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter, + struct tc_cls_flower_offload *cls_flower) +{ + if (cls_flower->common.chain_index) + return -EOPNOTSUPP; + + switch (cls_flower->command) { + case TC_CLSFLOWER_REPLACE: + return iavf_configure_clsflower(adapter, cls_flower); + case TC_CLSFLOWER_DESTROY: + return iavf_delete_clsflower(adapter, cls_flower); + case TC_CLSFLOWER_STATS: + return -EOPNOTSUPP; + default: + return -EOPNOTSUPP; + } +} + +/** + * iavf_setup_tc_block_cb - block callback for tc + * @type: type of offload + * @type_data: offload data + * @cb_priv: + * + * This function is the block callback for traffic classes + **/ +static int iavf_setup_tc_block_cb(enum tc_setup_type type, void *type_data, + void *cb_priv) +{ + switch (type) { + case TC_SETUP_CLSFLOWER: + return iavf_setup_tc_cls_flower(cb_priv, type_data); + default: + return -EOPNOTSUPP; + } +} + +/** + * iavf_setup_tc_block - register callbacks for tc + * @netdev: network interface device structure + * @f: tc offload data + * + * This function registers block callbacks for tc + * offloads + **/ +static int iavf_setup_tc_block(struct net_device *dev, + struct tc_block_offload *f) +{ + struct iavf_adapter *adapter = netdev_priv(dev); + + if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) + return -EOPNOTSUPP; + + switch (f->command) { + case TC_BLOCK_BIND: + return tcf_block_cb_register(f->block, iavf_setup_tc_block_cb, + adapter, adapter, f->extack); + case TC_BLOCK_UNBIND: + tcf_block_cb_unregister(f->block, iavf_setup_tc_block_cb, + adapter); + return 0; + default: + return -EOPNOTSUPP; + } +} + +/** + * iavf_setup_tc - configure multiple traffic classes + * @netdev: network interface device structure + * @type: type of offload + * @type_date: tc offload data + * + * This function is the callback to ndo_setup_tc in the + * netdev_ops. + * + * Returns 0 on success + **/ +static int iavf_setup_tc(struct net_device *netdev, enum tc_setup_type type, + void *type_data) +{ + switch (type) { + case TC_SETUP_QDISC_MQPRIO: + return __iavf_setup_tc(netdev, type_data); + case TC_SETUP_BLOCK: + return iavf_setup_tc_block(netdev, type_data); + default: + return -EOPNOTSUPP; + } +} + +/** + * iavf_open - Called when a network interface is made active + * @netdev: network interface device structure + * + * Returns 0 on success, negative value on failure + * + * The open entry point is called when a network interface is made + * active by the system (IFF_UP). At this point all resources needed + * for transmit and receive operations are allocated, the interrupt + * handler is registered with the OS, the watchdog timer is started, + * and the stack is notified that the interface is ready. + **/ +static int iavf_open(struct net_device *netdev) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + int err; + + if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) { + dev_err(&adapter->pdev->dev, "Unable to open device due to PF driver failure.\n"); + return -EIO; + } + + while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, + &adapter->crit_section)) + usleep_range(500, 1000); + + if (adapter->state != __IAVF_DOWN) { + err = -EBUSY; + goto err_unlock; + } + + /* allocate transmit descriptors */ + err = iavf_setup_all_tx_resources(adapter); + if (err) + goto err_setup_tx; + + /* allocate receive descriptors */ + err = iavf_setup_all_rx_resources(adapter); + if (err) + goto err_setup_rx; + + /* clear any pending interrupts, may auto mask */ + err = iavf_request_traffic_irqs(adapter, netdev->name); + if (err) + goto err_req_irq; + + spin_lock_bh(&adapter->mac_vlan_list_lock); + + iavf_add_filter(adapter, adapter->hw.mac.addr); + + spin_unlock_bh(&adapter->mac_vlan_list_lock); + + iavf_configure(adapter); + + iavf_up_complete(adapter); + + iavf_irq_enable(adapter, true); + + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); + + return 0; + +err_req_irq: + iavf_down(adapter); + iavf_free_traffic_irqs(adapter); +err_setup_rx: + iavf_free_all_rx_resources(adapter); +err_setup_tx: + iavf_free_all_tx_resources(adapter); +err_unlock: + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); + + return err; +} + +/** + * iavf_close - Disables a network interface + * @netdev: network interface device structure + * + * Returns 0, this is not allowed to fail + * + * The close entry point is called when an interface is de-activated + * by the OS. The hardware is still under the drivers control, but + * needs to be disabled. All IRQs except vector 0 (reserved for admin queue) + * are freed, along with all transmit and receive resources. + **/ +static int iavf_close(struct net_device *netdev) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + int status; + + if (adapter->state <= __IAVF_DOWN_PENDING) + return 0; + + while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, + &adapter->crit_section)) + usleep_range(500, 1000); + + set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); + if (CLIENT_ENABLED(adapter)) + adapter->flags |= IAVF_FLAG_CLIENT_NEEDS_CLOSE; + + iavf_down(adapter); + adapter->state = __IAVF_DOWN_PENDING; + iavf_free_traffic_irqs(adapter); + + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); + + /* We explicitly don't free resources here because the hardware is + * still active and can DMA into memory. Resources are cleared in + * iavf_virtchnl_completion() after we get confirmation from the PF + * driver that the rings have been stopped. + * + * Also, we wait for state to transition to __IAVF_DOWN before + * returning. State change occurs in iavf_virtchnl_completion() after + * VF resources are released (which occurs after PF driver processes and + * responds to admin queue commands). + */ + + status = wait_event_timeout(adapter->down_waitqueue, + adapter->state == __IAVF_DOWN, + msecs_to_jiffies(200)); + if (!status) + netdev_warn(netdev, "Device resources not yet released\n"); + return 0; +} + +/** + * iavf_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 iavf_change_mtu(struct net_device *netdev, int new_mtu) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + netdev->mtu = new_mtu; + if (CLIENT_ENABLED(adapter)) { + iavf_notify_client_l2_params(&adapter->vsi); + adapter->flags |= IAVF_FLAG_SERVICE_CLIENT_REQUESTED; + } + adapter->flags |= IAVF_FLAG_RESET_NEEDED; + schedule_work(&adapter->reset_task); + + return 0; +} + +/** + * iavf_set_features - set the netdev feature flags + * @netdev: ptr to the netdev being adjusted + * @features: the feature set that the stack is suggesting + * Note: expects to be called while under rtnl_lock() + **/ +static int iavf_set_features(struct net_device *netdev, + netdev_features_t features) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + /* Don't allow changing VLAN_RX flag when adapter is not capable + * of VLAN offload + */ + if (!VLAN_ALLOWED(adapter)) { + if ((netdev->features ^ features) & NETIF_F_HW_VLAN_CTAG_RX) + return -EINVAL; + } else if ((netdev->features ^ features) & NETIF_F_HW_VLAN_CTAG_RX) { + if (features & NETIF_F_HW_VLAN_CTAG_RX) + adapter->aq_required |= + IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING; + else + adapter->aq_required |= + IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING; + } + + return 0; +} + +/** + * iavf_features_check - Validate encapsulated packet conforms to limits + * @skb: skb buff + * @dev: This physical port's netdev + * @features: Offload features that the stack believes apply + **/ +static netdev_features_t iavf_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) +{ + size_t len; + + /* No point in doing any of this if neither checksum nor GSO are + * being requested for this frame. We can rule out both by just + * checking for CHECKSUM_PARTIAL + */ + if (skb->ip_summed != CHECKSUM_PARTIAL) + return features; + + /* We cannot support GSO if the MSS is going to be less than + * 64 bytes. If it is then we need to drop support for GSO. + */ + if (skb_is_gso(skb) && (skb_shinfo(skb)->gso_size < 64)) + features &= ~NETIF_F_GSO_MASK; + + /* MACLEN can support at most 63 words */ + len = skb_network_header(skb) - skb->data; + if (len & ~(63 * 2)) + goto out_err; + + /* IPLEN and EIPLEN can support at most 127 dwords */ + len = skb_transport_header(skb) - skb_network_header(skb); + if (len & ~(127 * 4)) + goto out_err; + + if (skb->encapsulation) { + /* L4TUNLEN can support 127 words */ + len = skb_inner_network_header(skb) - skb_transport_header(skb); + if (len & ~(127 * 2)) + goto out_err; + + /* IPLEN can support at most 127 dwords */ + len = skb_inner_transport_header(skb) - + skb_inner_network_header(skb); + if (len & ~(127 * 4)) + goto out_err; + } + + /* No need to validate L4LEN as TCP is the only protocol with a + * a flexible value and we support all possible values supported + * by TCP, which is at most 15 dwords + */ + + return features; +out_err: + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); +} + +/** + * iavf_fix_features - fix up the netdev feature bits + * @netdev: our net device + * @features: desired feature bits + * + * Returns fixed-up features bits + **/ +static netdev_features_t iavf_fix_features(struct net_device *netdev, + netdev_features_t features) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + if (!(adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)) + features &= ~(NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_FILTER); + + return features; +} + +static const struct net_device_ops iavf_netdev_ops = { + .ndo_open = iavf_open, + .ndo_stop = iavf_close, + .ndo_start_xmit = iavf_xmit_frame, + .ndo_set_rx_mode = iavf_set_rx_mode, + .ndo_validate_addr = eth_validate_addr, + .ndo_set_mac_address = iavf_set_mac, + .ndo_change_mtu = iavf_change_mtu, + .ndo_tx_timeout = iavf_tx_timeout, + .ndo_vlan_rx_add_vid = iavf_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = iavf_vlan_rx_kill_vid, + .ndo_features_check = iavf_features_check, + .ndo_fix_features = iavf_fix_features, + .ndo_set_features = iavf_set_features, + .ndo_setup_tc = iavf_setup_tc, +}; + +/** + * iavf_check_reset_complete - check that VF reset is complete + * @hw: pointer to hw struct + * + * Returns 0 if device is ready to use, or -EBUSY if it's in reset. + **/ +static int iavf_check_reset_complete(struct iavf_hw *hw) +{ + u32 rstat; + int i; + + for (i = 0; i < 100; i++) { + rstat = rd32(hw, IAVF_VFGEN_RSTAT) & + IAVF_VFGEN_RSTAT_VFR_STATE_MASK; + if ((rstat == VIRTCHNL_VFR_VFACTIVE) || + (rstat == VIRTCHNL_VFR_COMPLETED)) + return 0; + usleep_range(10, 20); + } + return -EBUSY; +} + +/** + * iavf_process_config - Process the config information we got from the PF + * @adapter: board private structure + * + * Verify that we have a valid config struct, and set up our netdev features + * and our VSI struct. + **/ +int iavf_process_config(struct iavf_adapter *adapter) +{ + struct virtchnl_vf_resource *vfres = adapter->vf_res; + int i, num_req_queues = adapter->num_req_queues; + struct net_device *netdev = adapter->netdev; + struct iavf_vsi *vsi = &adapter->vsi; + netdev_features_t hw_enc_features; + netdev_features_t hw_features; + + /* got VF config message back from PF, now we can parse it */ + for (i = 0; i < vfres->num_vsis; i++) { + if (vfres->vsi_res[i].vsi_type == VIRTCHNL_VSI_SRIOV) + adapter->vsi_res = &vfres->vsi_res[i]; + } + if (!adapter->vsi_res) { + dev_err(&adapter->pdev->dev, "No LAN VSI found\n"); + return -ENODEV; + } + + if (num_req_queues && + num_req_queues != adapter->vsi_res->num_queue_pairs) { + /* Problem. The PF gave us fewer queues than what we had + * negotiated in our request. Need a reset to see if we can't + * get back to a working state. + */ + dev_err(&adapter->pdev->dev, + "Requested %d queues, but PF only gave us %d.\n", + num_req_queues, + adapter->vsi_res->num_queue_pairs); + adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED; + adapter->num_req_queues = adapter->vsi_res->num_queue_pairs; + iavf_schedule_reset(adapter); + return -ENODEV; + } + adapter->num_req_queues = 0; + + hw_enc_features = NETIF_F_SG | + NETIF_F_IP_CSUM | + NETIF_F_IPV6_CSUM | + NETIF_F_HIGHDMA | + NETIF_F_SOFT_FEATURES | + NETIF_F_TSO | + NETIF_F_TSO_ECN | + NETIF_F_TSO6 | + NETIF_F_SCTP_CRC | + NETIF_F_RXHASH | + NETIF_F_RXCSUM | + 0; + + /* advertise to stack only if offloads for encapsulated packets is + * supported + */ + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ENCAP) { + hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_GRE | + NETIF_F_GSO_GRE_CSUM | + NETIF_F_GSO_IPXIP4 | + NETIF_F_GSO_IPXIP6 | + NETIF_F_GSO_UDP_TUNNEL_CSUM | + NETIF_F_GSO_PARTIAL | + 0; + + if (!(vfres->vf_cap_flags & + VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM)) + netdev->gso_partial_features |= + NETIF_F_GSO_UDP_TUNNEL_CSUM; + + netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM; + netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID; + netdev->hw_enc_features |= hw_enc_features; + } + /* record features VLANs can make use of */ + netdev->vlan_features |= hw_enc_features | NETIF_F_TSO_MANGLEID; + + /* Write features and hw_features separately to avoid polluting + * with, or dropping, features that are set when we registered. + */ + hw_features = hw_enc_features; + + /* Enable VLAN features if supported */ + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN) + hw_features |= (NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX); + /* Enable cloud filter if ADQ is supported */ + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) + hw_features |= NETIF_F_HW_TC; + + netdev->hw_features |= hw_features; + + netdev->features |= hw_features; + + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN) + netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + + netdev->priv_flags |= IFF_UNICAST_FLT; + + /* Do not turn on offloads when they are requested to be turned off. + * TSO needs minimum 576 bytes to work correctly. + */ + if (netdev->wanted_features) { + if (!(netdev->wanted_features & NETIF_F_TSO) || + netdev->mtu < 576) + netdev->features &= ~NETIF_F_TSO; + if (!(netdev->wanted_features & NETIF_F_TSO6) || + netdev->mtu < 576) + netdev->features &= ~NETIF_F_TSO6; + if (!(netdev->wanted_features & NETIF_F_TSO_ECN)) + netdev->features &= ~NETIF_F_TSO_ECN; + if (!(netdev->wanted_features & NETIF_F_GRO)) + netdev->features &= ~NETIF_F_GRO; + if (!(netdev->wanted_features & NETIF_F_GSO)) + netdev->features &= ~NETIF_F_GSO; + } + + adapter->vsi.id = adapter->vsi_res->vsi_id; + + adapter->vsi.back = adapter; + adapter->vsi.base_vector = 1; + adapter->vsi.work_limit = IAVF_DEFAULT_IRQ_WORK; + vsi->netdev = adapter->netdev; + vsi->qs_handle = adapter->vsi_res->qset_handle; + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PF) { + adapter->rss_key_size = vfres->rss_key_size; + adapter->rss_lut_size = vfres->rss_lut_size; + } else { + adapter->rss_key_size = IAVF_HKEY_ARRAY_SIZE; + adapter->rss_lut_size = IAVF_HLUT_ARRAY_SIZE; + } + + return 0; +} + +/** + * iavf_init_task - worker thread to perform delayed initialization + * @work: pointer to work_struct containing our data + * + * This task completes the work that was begun in probe. Due to the nature + * of VF-PF communications, we may need to wait tens of milliseconds to get + * responses back from the PF. Rather than busy-wait in probe and bog down the + * whole system, we'll do it in a task so we can sleep. + * This task only runs during driver init. Once we've established + * communications with the PF driver and set up our netdev, the watchdog + * takes over. + **/ +static void iavf_init_task(struct work_struct *work) +{ + struct iavf_adapter *adapter = container_of(work, + struct iavf_adapter, + init_task.work); + struct net_device *netdev = adapter->netdev; + struct iavf_hw *hw = &adapter->hw; + struct pci_dev *pdev = adapter->pdev; + int err, bufsz; + + switch (adapter->state) { + case __IAVF_STARTUP: + /* driver loaded, probe complete */ + adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; + adapter->flags &= ~IAVF_FLAG_RESET_PENDING; + err = iavf_set_mac_type(hw); + if (err) { + dev_err(&pdev->dev, "Failed to set MAC type (%d)\n", + err); + goto err; + } + err = iavf_check_reset_complete(hw); + if (err) { + dev_info(&pdev->dev, "Device is still in reset (%d), retrying\n", + err); + goto err; + } + hw->aq.num_arq_entries = IAVF_AQ_LEN; + hw->aq.num_asq_entries = IAVF_AQ_LEN; + hw->aq.arq_buf_size = IAVF_MAX_AQ_BUF_SIZE; + hw->aq.asq_buf_size = IAVF_MAX_AQ_BUF_SIZE; + + err = iavf_init_adminq(hw); + if (err) { + dev_err(&pdev->dev, "Failed to init Admin Queue (%d)\n", + err); + goto err; + } + err = iavf_send_api_ver(adapter); + if (err) { + dev_err(&pdev->dev, "Unable to send to PF (%d)\n", err); + iavf_shutdown_adminq(hw); + goto err; + } + adapter->state = __IAVF_INIT_VERSION_CHECK; + goto restart; + case __IAVF_INIT_VERSION_CHECK: + if (!iavf_asq_done(hw)) { + dev_err(&pdev->dev, "Admin queue command never completed\n"); + iavf_shutdown_adminq(hw); + adapter->state = __IAVF_STARTUP; + goto err; + } + + /* aq msg sent, awaiting reply */ + err = iavf_verify_api_ver(adapter); + if (err) { + if (err == I40E_ERR_ADMIN_QUEUE_NO_WORK) + err = iavf_send_api_ver(adapter); + else + dev_err(&pdev->dev, "Unsupported PF API version %d.%d, expected %d.%d\n", + adapter->pf_version.major, + adapter->pf_version.minor, + VIRTCHNL_VERSION_MAJOR, + VIRTCHNL_VERSION_MINOR); + goto err; + } + err = iavf_send_vf_config_msg(adapter); + if (err) { + dev_err(&pdev->dev, "Unable to send config request (%d)\n", + err); + goto err; + } + adapter->state = __IAVF_INIT_GET_RESOURCES; + goto restart; + case __IAVF_INIT_GET_RESOURCES: + /* aq msg sent, awaiting reply */ + if (!adapter->vf_res) { + bufsz = sizeof(struct virtchnl_vf_resource) + + (IAVF_MAX_VF_VSI * + sizeof(struct virtchnl_vsi_resource)); + adapter->vf_res = kzalloc(bufsz, GFP_KERNEL); + if (!adapter->vf_res) + goto err; + } + err = iavf_get_vf_config(adapter); + if (err == I40E_ERR_ADMIN_QUEUE_NO_WORK) { + err = iavf_send_vf_config_msg(adapter); + goto err; + } else if (err == I40E_ERR_PARAM) { + /* We only get ERR_PARAM if the device is in a very bad + * state or if we've been disabled for previous bad + * behavior. Either way, we're done now. + */ + iavf_shutdown_adminq(hw); + dev_err(&pdev->dev, "Unable to get VF config due to PF error condition, not retrying\n"); + return; + } + if (err) { + dev_err(&pdev->dev, "Unable to get VF config (%d)\n", + err); + goto err_alloc; + } + adapter->state = __IAVF_INIT_SW; + break; + default: + goto err_alloc; + } + + if (iavf_process_config(adapter)) + goto err_alloc; + adapter->current_op = VIRTCHNL_OP_UNKNOWN; + + adapter->flags |= IAVF_FLAG_RX_CSUM_ENABLED; + + netdev->netdev_ops = &iavf_netdev_ops; + iavf_set_ethtool_ops(netdev); + netdev->watchdog_timeo = 5 * HZ; + + /* MTU range: 68 - 9710 */ + netdev->min_mtu = ETH_MIN_MTU; + netdev->max_mtu = IAVF_MAX_RXBUFFER - IAVF_PACKET_HDR_PAD; + + if (!is_valid_ether_addr(adapter->hw.mac.addr)) { + dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n", + adapter->hw.mac.addr); + eth_hw_addr_random(netdev); + ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr); + } else { + adapter->flags |= IAVF_FLAG_ADDR_SET_BY_PF; + ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr); + ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); + } + + timer_setup(&adapter->watchdog_timer, iavf_watchdog_timer, 0); + mod_timer(&adapter->watchdog_timer, jiffies + 1); + + adapter->tx_desc_count = IAVF_DEFAULT_TXD; + adapter->rx_desc_count = IAVF_DEFAULT_RXD; + err = iavf_init_interrupt_scheme(adapter); + if (err) + goto err_sw_init; + iavf_map_rings_to_vectors(adapter); + if (adapter->vf_res->vf_cap_flags & + VIRTCHNL_VF_OFFLOAD_WB_ON_ITR) + adapter->flags |= IAVF_FLAG_WB_ON_ITR_CAPABLE; + + err = iavf_request_misc_irq(adapter); + if (err) + goto err_sw_init; + + netif_carrier_off(netdev); + adapter->link_up = false; + + if (!adapter->netdev_registered) { + err = register_netdev(netdev); + if (err) + goto err_register; + } + + adapter->netdev_registered = true; + + netif_tx_stop_all_queues(netdev); + if (CLIENT_ALLOWED(adapter)) { + err = iavf_lan_add_device(adapter); + if (err) + dev_info(&pdev->dev, "Failed to add VF to client API service list: %d\n", + err); + } + + dev_info(&pdev->dev, "MAC address: %pM\n", adapter->hw.mac.addr); + if (netdev->features & NETIF_F_GRO) + dev_info(&pdev->dev, "GRO is enabled\n"); + + adapter->state = __IAVF_DOWN; + set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); + iavf_misc_irq_enable(adapter); + wake_up(&adapter->down_waitqueue); + + adapter->rss_key = kzalloc(adapter->rss_key_size, GFP_KERNEL); + adapter->rss_lut = kzalloc(adapter->rss_lut_size, GFP_KERNEL); + if (!adapter->rss_key || !adapter->rss_lut) + goto err_mem; + + if (RSS_AQ(adapter)) { + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_RSS; + mod_timer_pending(&adapter->watchdog_timer, jiffies + 1); + } else { + iavf_init_rss(adapter); + } + return; +restart: + schedule_delayed_work(&adapter->init_task, msecs_to_jiffies(30)); + return; +err_mem: + iavf_free_rss(adapter); +err_register: + iavf_free_misc_irq(adapter); +err_sw_init: + iavf_reset_interrupt_capability(adapter); +err_alloc: + kfree(adapter->vf_res); + adapter->vf_res = NULL; +err: + /* Things went into the weeds, so try again later */ + if (++adapter->aq_wait_count > IAVF_AQ_MAX_ERR) { + dev_err(&pdev->dev, "Failed to communicate with PF; waiting before retry\n"); + adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED; + iavf_shutdown_adminq(hw); + adapter->state = __IAVF_STARTUP; + schedule_delayed_work(&adapter->init_task, HZ * 5); + return; + } + schedule_delayed_work(&adapter->init_task, HZ); +} + +/** + * iavf_shutdown - Shutdown the device in preparation for a reboot + * @pdev: pci device structure + **/ +static void iavf_shutdown(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct iavf_adapter *adapter = netdev_priv(netdev); + + netif_device_detach(netdev); + + if (netif_running(netdev)) + iavf_close(netdev); + + /* Prevent the watchdog from running. */ + adapter->state = __IAVF_REMOVE; + adapter->aq_required = 0; + +#ifdef CONFIG_PM + pci_save_state(pdev); + +#endif + pci_disable_device(pdev); +} + +/** + * iavf_probe - Device Initialization Routine + * @pdev: PCI device information struct + * @ent: entry in iavf_pci_tbl + * + * Returns 0 on success, negative on failure + * + * iavf_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 iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) +{ + struct net_device *netdev; + struct iavf_adapter *adapter = NULL; + struct iavf_hw *hw = NULL; + int err; + + err = pci_enable_device(pdev); + if (err) + return err; + + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (err) { + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (err) { + dev_err(&pdev->dev, + "DMA configuration failed: 0x%x\n", err); + goto err_dma; + } + } + + err = pci_request_regions(pdev, iavf_driver_name); + if (err) { + dev_err(&pdev->dev, + "pci_request_regions failed 0x%x\n", err); + goto err_pci_reg; + } + + pci_enable_pcie_error_reporting(pdev); + + pci_set_master(pdev); + + netdev = alloc_etherdev_mq(sizeof(struct iavf_adapter), + IAVF_MAX_REQ_QUEUES); + if (!netdev) { + err = -ENOMEM; + 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 = BIT(DEFAULT_DEBUG_LEVEL_SHIFT) - 1; + adapter->state = __IAVF_STARTUP; + + /* Call save state here because it relies on the adapter struct. */ + pci_save_state(pdev); + + hw->hw_addr = ioremap(pci_resource_start(pdev, 0), + pci_resource_len(pdev, 0)); + if (!hw->hw_addr) { + err = -EIO; + goto err_ioremap; + } + hw->vendor_id = pdev->vendor; + hw->device_id = pdev->device; + pci_read_config_byte(pdev, PCI_REVISION_ID, &hw->revision_id); + hw->subsystem_vendor_id = pdev->subsystem_vendor; + hw->subsystem_device_id = pdev->subsystem_device; + hw->bus.device = PCI_SLOT(pdev->devfn); + hw->bus.func = PCI_FUNC(pdev->devfn); + hw->bus.bus_id = pdev->bus->number; + + /* set up the locks for the AQ, do this only once in probe + * and destroy them only once in remove + */ + mutex_init(&hw->aq.asq_mutex); + mutex_init(&hw->aq.arq_mutex); + + spin_lock_init(&adapter->mac_vlan_list_lock); + spin_lock_init(&adapter->cloud_filter_list_lock); + + INIT_LIST_HEAD(&adapter->mac_filter_list); + INIT_LIST_HEAD(&adapter->vlan_filter_list); + INIT_LIST_HEAD(&adapter->cloud_filter_list); + + INIT_WORK(&adapter->reset_task, iavf_reset_task); + INIT_WORK(&adapter->adminq_task, iavf_adminq_task); + INIT_WORK(&adapter->watchdog_task, iavf_watchdog_task); + INIT_DELAYED_WORK(&adapter->client_task, iavf_client_task); + INIT_DELAYED_WORK(&adapter->init_task, iavf_init_task); + schedule_delayed_work(&adapter->init_task, + msecs_to_jiffies(5 * (pdev->devfn & 0x07))); + + /* Setup the wait queue for indicating transition to down status */ + init_waitqueue_head(&adapter->down_waitqueue); + + return 0; + +err_ioremap: + free_netdev(netdev); +err_alloc_etherdev: + pci_release_regions(pdev); +err_pci_reg: +err_dma: + pci_disable_device(pdev); + return err; +} + +#ifdef CONFIG_PM +/** + * iavf_suspend - Power management suspend routine + * @pdev: PCI device information struct + * @state: unused + * + * Called when the system (VM) is entering sleep/suspend. + **/ +static int iavf_suspend(struct pci_dev *pdev, pm_message_t state) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct iavf_adapter *adapter = netdev_priv(netdev); + int retval = 0; + + netif_device_detach(netdev); + + while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, + &adapter->crit_section)) + usleep_range(500, 1000); + + if (netif_running(netdev)) { + rtnl_lock(); + iavf_down(adapter); + rtnl_unlock(); + } + iavf_free_misc_irq(adapter); + iavf_reset_interrupt_capability(adapter); + + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); + + retval = pci_save_state(pdev); + if (retval) + return retval; + + pci_disable_device(pdev); + + return 0; +} + +/** + * iavf_resume - Power management resume routine + * @pdev: PCI device information struct + * + * Called when the system (VM) is resumed from sleep/suspend. + **/ +static int iavf_resume(struct pci_dev *pdev) +{ + struct iavf_adapter *adapter = pci_get_drvdata(pdev); + struct net_device *netdev = adapter->netdev; + u32 err; + + pci_set_power_state(pdev, PCI_D0); + pci_restore_state(pdev); + /* pci_restore_state clears dev->state_saved so call + * pci_save_state to restore it. + */ + pci_save_state(pdev); + + err = pci_enable_device_mem(pdev); + if (err) { + dev_err(&pdev->dev, "Cannot enable PCI device from suspend.\n"); + return err; + } + pci_set_master(pdev); + + rtnl_lock(); + err = iavf_set_interrupt_capability(adapter); + if (err) { + rtnl_unlock(); + dev_err(&pdev->dev, "Cannot enable MSI-X interrupts.\n"); + return err; + } + err = iavf_request_misc_irq(adapter); + rtnl_unlock(); + if (err) { + dev_err(&pdev->dev, "Cannot get interrupt vector.\n"); + return err; + } + + schedule_work(&adapter->reset_task); + + netif_device_attach(netdev); + + return err; +} + +#endif /* CONFIG_PM */ +/** + * iavf_remove - Device Removal Routine + * @pdev: PCI device information struct + * + * iavf_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 iavf_remove(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_vlan_filter *vlf, *vlftmp; + struct iavf_mac_filter *f, *ftmp; + struct iavf_cloud_filter *cf, *cftmp; + struct iavf_hw *hw = &adapter->hw; + int err; + /* Indicate we are in remove and not to run reset_task */ + set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section); + cancel_delayed_work_sync(&adapter->init_task); + cancel_work_sync(&adapter->reset_task); + cancel_delayed_work_sync(&adapter->client_task); + if (adapter->netdev_registered) { + unregister_netdev(netdev); + adapter->netdev_registered = false; + } + if (CLIENT_ALLOWED(adapter)) { + err = iavf_lan_del_device(adapter); + if (err) + dev_warn(&pdev->dev, "Failed to delete client device: %d\n", + err); + } + + /* Shut down all the garbage mashers on the detention level */ + adapter->state = __IAVF_REMOVE; + adapter->aq_required = 0; + adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; + iavf_request_reset(adapter); + msleep(50); + /* If the FW isn't responding, kick it once, but only once. */ + if (!iavf_asq_done(hw)) { + iavf_request_reset(adapter); + msleep(50); + } + iavf_free_all_tx_resources(adapter); + iavf_free_all_rx_resources(adapter); + iavf_misc_irq_disable(adapter); + iavf_free_misc_irq(adapter); + iavf_reset_interrupt_capability(adapter); + iavf_free_q_vectors(adapter); + + if (adapter->watchdog_timer.function) + del_timer_sync(&adapter->watchdog_timer); + + cancel_work_sync(&adapter->adminq_task); + + iavf_free_rss(adapter); + + if (hw->aq.asq.count) + iavf_shutdown_adminq(hw); + + /* destroy the locks only once, here */ + mutex_destroy(&hw->aq.arq_mutex); + mutex_destroy(&hw->aq.asq_mutex); + + iounmap(hw->hw_addr); + pci_release_regions(pdev); + iavf_free_all_tx_resources(adapter); + iavf_free_all_rx_resources(adapter); + iavf_free_queues(adapter); + kfree(adapter->vf_res); + spin_lock_bh(&adapter->mac_vlan_list_lock); + /* If we got removed before an up/down sequence, we've got a filter + * hanging out there that we need to get rid of. + */ + list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, list) { + list_del(&f->list); + kfree(f); + } + list_for_each_entry_safe(vlf, vlftmp, &adapter->vlan_filter_list, + list) { + list_del(&vlf->list); + kfree(vlf); + } + + spin_unlock_bh(&adapter->mac_vlan_list_lock); + + spin_lock_bh(&adapter->cloud_filter_list_lock); + list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, list) { + list_del(&cf->list); + kfree(cf); + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); + + free_netdev(netdev); + + pci_disable_pcie_error_reporting(pdev); + + pci_disable_device(pdev); +} + +static struct pci_driver iavf_driver = { + .name = iavf_driver_name, + .id_table = iavf_pci_tbl, + .probe = iavf_probe, + .remove = iavf_remove, +#ifdef CONFIG_PM + .suspend = iavf_suspend, + .resume = iavf_resume, +#endif + .shutdown = iavf_shutdown, +}; + +/** + * iavf_init_module - Driver Registration Routine + * + * iavf_init_module is the first routine called when the driver is + * loaded. All it does is register with the PCI subsystem. + **/ +static int __init iavf_init_module(void) +{ + int ret; + + pr_info("iavf: %s - version %s\n", iavf_driver_string, + iavf_driver_version); + + pr_info("%s\n", iavf_copyright); + + iavf_wq = alloc_workqueue("%s", WQ_UNBOUND | WQ_MEM_RECLAIM, 1, + iavf_driver_name); + if (!iavf_wq) { + pr_err("%s: Failed to create workqueue\n", iavf_driver_name); + return -ENOMEM; + } + ret = pci_register_driver(&iavf_driver); + return ret; +} + +module_init(iavf_init_module); + +/** + * iavf_exit_module - Driver Exit Cleanup Routine + * + * iavf_exit_module is called just before the driver is removed + * from memory. + **/ +static void __exit iavf_exit_module(void) +{ + pci_unregister_driver(&iavf_driver); + destroy_workqueue(iavf_wq); +} + +module_exit(iavf_exit_module); + +/* iavf_main.c */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_osdep.h b/drivers/net/ethernet/intel/iavf/iavf_osdep.h new file mode 100644 index 000000000000..e6e0b0328706 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_osdep.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _IAVF_OSDEP_H_ +#define _IAVF_OSDEP_H_ + +#include <linux/types.h> +#include <linux/if_ether.h> +#include <linux/if_vlan.h> +#include <linux/tcp.h> +#include <linux/pci.h> + +/* get readq/writeq support for 32 bit kernels, use the low-first version */ +#include <linux/io-64-nonatomic-lo-hi.h> + +/* File to be the magic between shared code and + * actual OS primitives + */ + +#define hw_dbg(hw, S, A...) do {} while (0) + +#define wr32(a, reg, value) writel((value), ((a)->hw_addr + (reg))) +#define rd32(a, reg) readl((a)->hw_addr + (reg)) + +#define wr64(a, reg, value) writeq((value), ((a)->hw_addr + (reg))) +#define rd64(a, reg) readq((a)->hw_addr + (reg)) +#define iavf_flush(a) readl((a)->hw_addr + IAVF_VFGEN_RSTAT) + +/* memory allocation tracking */ +struct iavf_dma_mem { + void *va; + dma_addr_t pa; + u32 size; +}; + +#define iavf_allocate_dma_mem(h, m, unused, s, a) \ + iavf_allocate_dma_mem_d(h, m, s, a) +#define iavf_free_dma_mem(h, m) iavf_free_dma_mem_d(h, m) + +struct iavf_virt_mem { + void *va; + u32 size; +}; +#define iavf_allocate_virt_mem(h, m, s) iavf_allocate_virt_mem_d(h, m, s) +#define iavf_free_virt_mem(h, m) iavf_free_virt_mem_d(h, m) + +#define iavf_debug(h, m, s, ...) iavf_debug_d(h, m, s, ##__VA_ARGS__) +extern void iavf_debug_d(void *hw, u32 mask, char *fmt_str, ...) + __attribute__ ((format(gnu_printf, 3, 4))); + +typedef enum iavf_status_code iavf_status; +#endif /* _IAVF_OSDEP_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_prototype.h b/drivers/net/ethernet/intel/iavf/iavf_prototype.h new file mode 100644 index 000000000000..d6685103af39 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_prototype.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _IAVF_PROTOTYPE_H_ +#define _IAVF_PROTOTYPE_H_ + +#include "iavf_type.h" +#include "iavf_alloc.h" +#include <linux/avf/virtchnl.h> + +/* Prototypes for shared code functions that are not in + * the standard function pointer structures. These are + * mostly because they are needed even before the init + * has happened and will assist in the early SW and FW + * setup. + */ + +/* adminq functions */ +iavf_status iavf_init_adminq(struct iavf_hw *hw); +iavf_status iavf_shutdown_adminq(struct iavf_hw *hw); +void i40e_adminq_init_ring_data(struct iavf_hw *hw); +iavf_status iavf_clean_arq_element(struct iavf_hw *hw, + struct i40e_arq_event_info *e, + u16 *events_pending); +iavf_status iavf_asq_send_command(struct iavf_hw *hw, struct i40e_aq_desc *desc, + void *buff, /* can be NULL */ + u16 buff_size, + struct i40e_asq_cmd_details *cmd_details); +bool iavf_asq_done(struct iavf_hw *hw); + +/* debug function for adminq */ +void iavf_debug_aq(struct iavf_hw *hw, enum iavf_debug_mask mask, + void *desc, void *buffer, u16 buf_len); + +void i40e_idle_aq(struct iavf_hw *hw); +void iavf_resume_aq(struct iavf_hw *hw); +bool iavf_check_asq_alive(struct iavf_hw *hw); +iavf_status iavf_aq_queue_shutdown(struct iavf_hw *hw, bool unloading); +const char *iavf_aq_str(struct iavf_hw *hw, enum i40e_admin_queue_err aq_err); +const char *iavf_stat_str(struct iavf_hw *hw, iavf_status stat_err); + +iavf_status iavf_aq_get_rss_lut(struct iavf_hw *hw, u16 seid, + bool pf_lut, u8 *lut, u16 lut_size); +iavf_status iavf_aq_set_rss_lut(struct iavf_hw *hw, u16 seid, + bool pf_lut, u8 *lut, u16 lut_size); +iavf_status iavf_aq_get_rss_key(struct iavf_hw *hw, u16 seid, + struct i40e_aqc_get_set_rss_key_data *key); +iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 seid, + struct i40e_aqc_get_set_rss_key_data *key); + +iavf_status iavf_set_mac_type(struct iavf_hw *hw); + +extern struct iavf_rx_ptype_decoded iavf_ptype_lookup[]; + +static inline struct iavf_rx_ptype_decoded decode_rx_desc_ptype(u8 ptype) +{ + return iavf_ptype_lookup[ptype]; +} + +void iavf_vf_parse_hw_config(struct iavf_hw *hw, + struct virtchnl_vf_resource *msg); +iavf_status iavf_vf_reset(struct iavf_hw *hw); +iavf_status iavf_aq_send_msg_to_pf(struct iavf_hw *hw, + enum virtchnl_ops v_opcode, + iavf_status v_retval, u8 *msg, u16 msglen, + struct i40e_asq_cmd_details *cmd_details); +#endif /* _IAVF_PROTOTYPE_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_register.h b/drivers/net/ethernet/intel/iavf/iavf_register.h new file mode 100644 index 000000000000..bf793332fc9d --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_register.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _IAVF_REGISTER_H_ +#define _IAVF_REGISTER_H_ + +#define IAVF_VF_ARQBAH1 0x00006000 /* Reset: EMPR */ +#define IAVF_VF_ARQBAL1 0x00006C00 /* Reset: EMPR */ +#define IAVF_VF_ARQH1 0x00007400 /* Reset: EMPR */ +#define IAVF_VF_ARQH1_ARQH_SHIFT 0 +#define IAVF_VF_ARQH1_ARQH_MASK IAVF_MASK(0x3FF, IAVF_VF_ARQH1_ARQH_SHIFT) +#define IAVF_VF_ARQLEN1 0x00008000 /* Reset: EMPR */ +#define IAVF_VF_ARQLEN1_ARQVFE_SHIFT 28 +#define IAVF_VF_ARQLEN1_ARQVFE_MASK IAVF_MASK(0x1, IAVF_VF_ARQLEN1_ARQVFE_SHIFT) +#define IAVF_VF_ARQLEN1_ARQOVFL_SHIFT 29 +#define IAVF_VF_ARQLEN1_ARQOVFL_MASK IAVF_MASK(0x1, IAVF_VF_ARQLEN1_ARQOVFL_SHIFT) +#define IAVF_VF_ARQLEN1_ARQCRIT_SHIFT 30 +#define IAVF_VF_ARQLEN1_ARQCRIT_MASK IAVF_MASK(0x1, IAVF_VF_ARQLEN1_ARQCRIT_SHIFT) +#define IAVF_VF_ARQLEN1_ARQENABLE_SHIFT 31 +#define IAVF_VF_ARQLEN1_ARQENABLE_MASK IAVF_MASK(0x1, IAVF_VF_ARQLEN1_ARQENABLE_SHIFT) +#define IAVF_VF_ARQT1 0x00007000 /* Reset: EMPR */ +#define IAVF_VF_ATQBAH1 0x00007800 /* Reset: EMPR */ +#define IAVF_VF_ATQBAL1 0x00007C00 /* Reset: EMPR */ +#define IAVF_VF_ATQH1 0x00006400 /* Reset: EMPR */ +#define IAVF_VF_ATQLEN1 0x00006800 /* Reset: EMPR */ +#define IAVF_VF_ATQLEN1_ATQVFE_SHIFT 28 +#define IAVF_VF_ATQLEN1_ATQVFE_MASK IAVF_MASK(0x1, IAVF_VF_ATQLEN1_ATQVFE_SHIFT) +#define IAVF_VF_ATQLEN1_ATQOVFL_SHIFT 29 +#define IAVF_VF_ATQLEN1_ATQOVFL_MASK IAVF_MASK(0x1, IAVF_VF_ATQLEN1_ATQOVFL_SHIFT) +#define IAVF_VF_ATQLEN1_ATQCRIT_SHIFT 30 +#define IAVF_VF_ATQLEN1_ATQCRIT_MASK IAVF_MASK(0x1, IAVF_VF_ATQLEN1_ATQCRIT_SHIFT) +#define IAVF_VF_ATQLEN1_ATQENABLE_SHIFT 31 +#define IAVF_VF_ATQLEN1_ATQENABLE_MASK IAVF_MASK(0x1, IAVF_VF_ATQLEN1_ATQENABLE_SHIFT) +#define IAVF_VF_ATQT1 0x00008400 /* Reset: EMPR */ +#define IAVF_VFGEN_RSTAT 0x00008800 /* Reset: VFR */ +#define IAVF_VFGEN_RSTAT_VFR_STATE_SHIFT 0 +#define IAVF_VFGEN_RSTAT_VFR_STATE_MASK IAVF_MASK(0x3, IAVF_VFGEN_RSTAT_VFR_STATE_SHIFT) +#define IAVF_VFINT_DYN_CTL01 0x00005C00 /* Reset: VFR */ +#define IAVF_VFINT_DYN_CTL01_INTENA_SHIFT 0 +#define IAVF_VFINT_DYN_CTL01_INTENA_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTL01_INTENA_SHIFT) +#define IAVF_VFINT_DYN_CTL01_ITR_INDX_SHIFT 3 +#define IAVF_VFINT_DYN_CTL01_ITR_INDX_MASK IAVF_MASK(0x3, IAVF_VFINT_DYN_CTL01_ITR_INDX_SHIFT) +#define IAVF_VFINT_DYN_CTLN1(_INTVF) (0x00003800 + ((_INTVF) * 4)) /* _i=0...15 */ /* Reset: VFR */ +#define IAVF_VFINT_DYN_CTLN1_INTENA_SHIFT 0 +#define IAVF_VFINT_DYN_CTLN1_INTENA_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTLN1_INTENA_SHIFT) +#define IAVF_VFINT_DYN_CTLN1_SWINT_TRIG_SHIFT 2 +#define IAVF_VFINT_DYN_CTLN1_SWINT_TRIG_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTLN1_SWINT_TRIG_SHIFT) +#define IAVF_VFINT_DYN_CTLN1_ITR_INDX_SHIFT 3 +#define IAVF_VFINT_DYN_CTLN1_ITR_INDX_MASK IAVF_MASK(0x3, IAVF_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) +#define IAVF_VFINT_DYN_CTLN1_INTERVAL_SHIFT 5 +#define IAVF_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_SHIFT 24 +#define IAVF_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_SHIFT) +#define IAVF_VFINT_ICR0_ENA1 0x00005000 /* Reset: CORER */ +#define IAVF_VFINT_ICR0_ENA1_ADMINQ_SHIFT 30 +#define IAVF_VFINT_ICR0_ENA1_ADMINQ_MASK IAVF_MASK(0x1, IAVF_VFINT_ICR0_ENA1_ADMINQ_SHIFT) +#define IAVF_VFINT_ICR0_ENA1_RSVD_SHIFT 31 +#define IAVF_VFINT_ICR01 0x00004800 /* Reset: CORER */ +#define IAVF_VFINT_ITRN1(_i, _INTVF) (0x00002800 + ((_i) * 64 + (_INTVF) * 4)) /* _i=0...2, _INTVF=0...15 */ /* Reset: VFR */ +#define IAVF_QRX_TAIL1(_Q) (0x00002000 + ((_Q) * 4)) /* _i=0...15 */ /* Reset: CORER */ +#define IAVF_QTX_TAIL1(_Q) (0x00000000 + ((_Q) * 4)) /* _i=0...15 */ /* Reset: PFR */ +#define IAVF_VFQF_HENA(_i) (0x0000C400 + ((_i) * 4)) /* _i=0...1 */ /* Reset: CORER */ +#define IAVF_VFQF_HKEY(_i) (0x0000CC00 + ((_i) * 4)) /* _i=0...12 */ /* Reset: CORER */ +#define IAVF_VFQF_HKEY_MAX_INDEX 12 +#define IAVF_VFQF_HLUT(_i) (0x0000D000 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */ +#define IAVF_VFQF_HLUT_MAX_INDEX 15 +#define IAVF_VFINT_DYN_CTLN1_WB_ON_ITR_SHIFT 30 +#define IAVF_VFINT_DYN_CTLN1_WB_ON_ITR_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTLN1_WB_ON_ITR_SHIFT) +#endif /* _IAVF_REGISTER_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_status.h b/drivers/net/ethernet/intel/iavf/iavf_status.h new file mode 100644 index 000000000000..46742fab7b8c --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_status.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _IAVF_STATUS_H_ +#define _IAVF_STATUS_H_ + +/* Error Codes */ +enum iavf_status_code { + I40E_SUCCESS = 0, + I40E_ERR_NVM = -1, + I40E_ERR_NVM_CHECKSUM = -2, + I40E_ERR_PHY = -3, + I40E_ERR_CONFIG = -4, + I40E_ERR_PARAM = -5, + I40E_ERR_MAC_TYPE = -6, + I40E_ERR_UNKNOWN_PHY = -7, + I40E_ERR_LINK_SETUP = -8, + I40E_ERR_ADAPTER_STOPPED = -9, + I40E_ERR_INVALID_MAC_ADDR = -10, + I40E_ERR_DEVICE_NOT_SUPPORTED = -11, + I40E_ERR_MASTER_REQUESTS_PENDING = -12, + I40E_ERR_INVALID_LINK_SETTINGS = -13, + I40E_ERR_AUTONEG_NOT_COMPLETE = -14, + I40E_ERR_RESET_FAILED = -15, + I40E_ERR_SWFW_SYNC = -16, + I40E_ERR_NO_AVAILABLE_VSI = -17, + I40E_ERR_NO_MEMORY = -18, + I40E_ERR_BAD_PTR = -19, + I40E_ERR_RING_FULL = -20, + I40E_ERR_INVALID_PD_ID = -21, + I40E_ERR_INVALID_QP_ID = -22, + I40E_ERR_INVALID_CQ_ID = -23, + I40E_ERR_INVALID_CEQ_ID = -24, + I40E_ERR_INVALID_AEQ_ID = -25, + I40E_ERR_INVALID_SIZE = -26, + I40E_ERR_INVALID_ARP_INDEX = -27, + I40E_ERR_INVALID_FPM_FUNC_ID = -28, + I40E_ERR_QP_INVALID_MSG_SIZE = -29, + I40E_ERR_QP_TOOMANY_WRS_POSTED = -30, + I40E_ERR_INVALID_FRAG_COUNT = -31, + I40E_ERR_QUEUE_EMPTY = -32, + I40E_ERR_INVALID_ALIGNMENT = -33, + I40E_ERR_FLUSHED_QUEUE = -34, + I40E_ERR_INVALID_PUSH_PAGE_INDEX = -35, + I40E_ERR_INVALID_IMM_DATA_SIZE = -36, + I40E_ERR_TIMEOUT = -37, + I40E_ERR_OPCODE_MISMATCH = -38, + I40E_ERR_CQP_COMPL_ERROR = -39, + I40E_ERR_INVALID_VF_ID = -40, + I40E_ERR_INVALID_HMCFN_ID = -41, + I40E_ERR_BACKING_PAGE_ERROR = -42, + I40E_ERR_NO_PBLCHUNKS_AVAILABLE = -43, + I40E_ERR_INVALID_PBLE_INDEX = -44, + I40E_ERR_INVALID_SD_INDEX = -45, + I40E_ERR_INVALID_PAGE_DESC_INDEX = -46, + I40E_ERR_INVALID_SD_TYPE = -47, + I40E_ERR_MEMCPY_FAILED = -48, + I40E_ERR_INVALID_HMC_OBJ_INDEX = -49, + I40E_ERR_INVALID_HMC_OBJ_COUNT = -50, + I40E_ERR_INVALID_SRQ_ARM_LIMIT = -51, + I40E_ERR_SRQ_ENABLED = -52, + I40E_ERR_ADMIN_QUEUE_ERROR = -53, + I40E_ERR_ADMIN_QUEUE_TIMEOUT = -54, + I40E_ERR_BUF_TOO_SHORT = -55, + I40E_ERR_ADMIN_QUEUE_FULL = -56, + I40E_ERR_ADMIN_QUEUE_NO_WORK = -57, + I40E_ERR_BAD_IWARP_CQE = -58, + I40E_ERR_NVM_BLANK_MODE = -59, + I40E_ERR_NOT_IMPLEMENTED = -60, + I40E_ERR_PE_DOORBELL_NOT_ENABLED = -61, + I40E_ERR_DIAG_TEST_FAILED = -62, + I40E_ERR_NOT_READY = -63, + I40E_NOT_SUPPORTED = -64, + I40E_ERR_FIRMWARE_API_VERSION = -65, + I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR = -66, +}; + +#endif /* _IAVF_STATUS_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_trace.h b/drivers/net/ethernet/intel/iavf/iavf_trace.h new file mode 100644 index 000000000000..1474f5539751 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_trace.h @@ -0,0 +1,209 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +/* Modeled on trace-events-sample.h */ + +/* The trace subsystem name for iavf will be "iavf". + * + * This file is named iavf_trace.h. + * + * Since this include file's name is different from the trace + * subsystem name, we'll have to define TRACE_INCLUDE_FILE at the end + * of this file. + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM iavf + +/* See trace-events-sample.h for a detailed description of why this + * guard clause is different from most normal include files. + */ +#if !defined(_I40E_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ) +#define _I40E_TRACE_H_ + +#include <linux/tracepoint.h> + +/** + * iavf_trace() macro enables shared code to refer to trace points + * like: + * + * trace_iavf{,vf}_example(args...) + * + * ... as: + * + * iavf_trace(example, args...) + * + * ... to resolve to the PF or VF version of the tracepoint without + * ifdefs, and to allow tracepoints to be disabled entirely at build + * time. + * + * Trace point should always be referred to in the driver via this + * macro. + * + * Similarly, iavf_trace_enabled(trace_name) wraps references to + * trace_iavf{,vf}_<trace_name>_enabled() functions. + */ +#define _IAVF_TRACE_NAME(trace_name) (trace_ ## iavf ## _ ## trace_name) +#define IAVF_TRACE_NAME(trace_name) _IAVF_TRACE_NAME(trace_name) + +#define iavf_trace(trace_name, args...) IAVF_TRACE_NAME(trace_name)(args) + +#define iavf_trace_enabled(trace_name) IAVF_TRACE_NAME(trace_name##_enabled)() + +/* Events common to PF and VF. Corresponding versions will be defined + * for both, named trace_iavf_* and trace_iavf_*. The iavf_trace() + * macro above will select the right trace point name for the driver + * being built from shared code. + */ + +/* Events related to a vsi & ring */ +DECLARE_EVENT_CLASS( + iavf_tx_template, + + TP_PROTO(struct iavf_ring *ring, + struct iavf_tx_desc *desc, + struct iavf_tx_buffer *buf), + + TP_ARGS(ring, desc, buf), + + /* The convention here is to make the first fields in the + * TP_STRUCT match the TP_PROTO exactly. This enables the use + * of the args struct generated by the tplist tool (from the + * bcc-tools package) to be used for those fields. To access + * fields other than the tracepoint args will require the + * tplist output to be adjusted. + */ + TP_STRUCT__entry( + __field(void*, ring) + __field(void*, desc) + __field(void*, buf) + __string(devname, ring->netdev->name) + ), + + TP_fast_assign( + __entry->ring = ring; + __entry->desc = desc; + __entry->buf = buf; + __assign_str(devname, ring->netdev->name); + ), + + TP_printk( + "netdev: %s ring: %p desc: %p buf %p", + __get_str(devname), __entry->ring, + __entry->desc, __entry->buf) +); + +DEFINE_EVENT( + iavf_tx_template, iavf_clean_tx_irq, + TP_PROTO(struct iavf_ring *ring, + struct iavf_tx_desc *desc, + struct iavf_tx_buffer *buf), + + TP_ARGS(ring, desc, buf)); + +DEFINE_EVENT( + iavf_tx_template, iavf_clean_tx_irq_unmap, + TP_PROTO(struct iavf_ring *ring, + struct iavf_tx_desc *desc, + struct iavf_tx_buffer *buf), + + TP_ARGS(ring, desc, buf)); + +DECLARE_EVENT_CLASS( + iavf_rx_template, + + TP_PROTO(struct iavf_ring *ring, + union iavf_32byte_rx_desc *desc, + struct sk_buff *skb), + + TP_ARGS(ring, desc, skb), + + TP_STRUCT__entry( + __field(void*, ring) + __field(void*, desc) + __field(void*, skb) + __string(devname, ring->netdev->name) + ), + + TP_fast_assign( + __entry->ring = ring; + __entry->desc = desc; + __entry->skb = skb; + __assign_str(devname, ring->netdev->name); + ), + + TP_printk( + "netdev: %s ring: %p desc: %p skb %p", + __get_str(devname), __entry->ring, + __entry->desc, __entry->skb) +); + +DEFINE_EVENT( + iavf_rx_template, iavf_clean_rx_irq, + TP_PROTO(struct iavf_ring *ring, + union iavf_32byte_rx_desc *desc, + struct sk_buff *skb), + + TP_ARGS(ring, desc, skb)); + +DEFINE_EVENT( + iavf_rx_template, iavf_clean_rx_irq_rx, + TP_PROTO(struct iavf_ring *ring, + union iavf_32byte_rx_desc *desc, + struct sk_buff *skb), + + TP_ARGS(ring, desc, skb)); + +DECLARE_EVENT_CLASS( + iavf_xmit_template, + + TP_PROTO(struct sk_buff *skb, + struct iavf_ring *ring), + + TP_ARGS(skb, ring), + + TP_STRUCT__entry( + __field(void*, skb) + __field(void*, ring) + __string(devname, ring->netdev->name) + ), + + TP_fast_assign( + __entry->skb = skb; + __entry->ring = ring; + __assign_str(devname, ring->netdev->name); + ), + + TP_printk( + "netdev: %s skb: %p ring: %p", + __get_str(devname), __entry->skb, + __entry->ring) +); + +DEFINE_EVENT( + iavf_xmit_template, iavf_xmit_frame_ring, + TP_PROTO(struct sk_buff *skb, + struct iavf_ring *ring), + + TP_ARGS(skb, ring)); + +DEFINE_EVENT( + iavf_xmit_template, iavf_xmit_frame_ring_drop, + TP_PROTO(struct sk_buff *skb, + struct iavf_ring *ring), + + TP_ARGS(skb, ring)); + +/* Events unique to the VF. */ + +#endif /* _IAVF_TRACE_H_ */ +/* This must be outside ifdef _IAVF_TRACE_H */ + +/* This trace include file is not located in the .../include/trace + * with the kernel tracepoint definitions, because we're a loadable + * module. + */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE iavf_trace +#include <trace/define_trace.h> diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c new file mode 100644 index 000000000000..edc349f49748 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -0,0 +1,2508 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#include <linux/prefetch.h> +#include <net/busy_poll.h> + +#include "iavf.h" +#include "iavf_trace.h" +#include "iavf_prototype.h" + +static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size, + u32 td_tag) +{ + return cpu_to_le64(IAVF_TX_DESC_DTYPE_DATA | + ((u64)td_cmd << IAVF_TXD_QW1_CMD_SHIFT) | + ((u64)td_offset << IAVF_TXD_QW1_OFFSET_SHIFT) | + ((u64)size << IAVF_TXD_QW1_TX_BUF_SZ_SHIFT) | + ((u64)td_tag << IAVF_TXD_QW1_L2TAG1_SHIFT)); +} + +#define IAVF_TXD_CMD (IAVF_TX_DESC_CMD_EOP | IAVF_TX_DESC_CMD_RS) + +/** + * iavf_unmap_and_free_tx_resource - Release a Tx buffer + * @ring: the ring that owns the buffer + * @tx_buffer: the buffer to free + **/ +static void iavf_unmap_and_free_tx_resource(struct iavf_ring *ring, + struct iavf_tx_buffer *tx_buffer) +{ + if (tx_buffer->skb) { + if (tx_buffer->tx_flags & IAVF_TX_FLAGS_FD_SB) + kfree(tx_buffer->raw_buf); + else + dev_kfree_skb_any(tx_buffer->skb); + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_single(ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + } else if (dma_unmap_len(tx_buffer, len)) { + dma_unmap_page(ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + } + + tx_buffer->next_to_watch = NULL; + tx_buffer->skb = NULL; + dma_unmap_len_set(tx_buffer, len, 0); + /* tx_buffer must be completely set up in the transmit path */ +} + +/** + * iavf_clean_tx_ring - Free any empty Tx buffers + * @tx_ring: ring to be cleaned + **/ +void iavf_clean_tx_ring(struct iavf_ring *tx_ring) +{ + unsigned long bi_size; + u16 i; + + /* ring already cleared, nothing to do */ + if (!tx_ring->tx_bi) + return; + + /* Free all the Tx ring sk_buffs */ + for (i = 0; i < tx_ring->count; i++) + iavf_unmap_and_free_tx_resource(tx_ring, &tx_ring->tx_bi[i]); + + bi_size = sizeof(struct iavf_tx_buffer) * tx_ring->count; + memset(tx_ring->tx_bi, 0, bi_size); + + /* Zero out the descriptor ring */ + memset(tx_ring->desc, 0, tx_ring->size); + + tx_ring->next_to_use = 0; + tx_ring->next_to_clean = 0; + + if (!tx_ring->netdev) + return; + + /* cleanup Tx queue statistics */ + netdev_tx_reset_queue(txring_txq(tx_ring)); +} + +/** + * iavf_free_tx_resources - Free Tx resources per queue + * @tx_ring: Tx descriptor ring for a specific queue + * + * Free all transmit software resources + **/ +void iavf_free_tx_resources(struct iavf_ring *tx_ring) +{ + iavf_clean_tx_ring(tx_ring); + kfree(tx_ring->tx_bi); + tx_ring->tx_bi = NULL; + + if (tx_ring->desc) { + dma_free_coherent(tx_ring->dev, tx_ring->size, + tx_ring->desc, tx_ring->dma); + tx_ring->desc = NULL; + } +} + +/** + * iavf_get_tx_pending - how many Tx descriptors not processed + * @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 iavf_get_tx_pending(struct iavf_ring *ring, bool in_sw) +{ + u32 head, tail; + + head = ring->next_to_clean; + tail = readl(ring->tail); + + if (head != tail) + return (head < tail) ? + tail - head : (tail + ring->count - head); + + return 0; +} + +/** + * iavf_detect_recover_hung - Function to detect and recover hung_queues + * @vsi: pointer to vsi struct with tx queues + * + * VSI has netdev and netdev has TX queues. This function is to check each of + * those TX queues if they are hung, trigger recovery by issuing SW interrupt. + **/ +void iavf_detect_recover_hung(struct iavf_vsi *vsi) +{ + struct iavf_ring *tx_ring = NULL; + struct net_device *netdev; + unsigned int i; + int packets; + + if (!vsi) + return; + + if (test_bit(__IAVF_VSI_DOWN, vsi->state)) + return; + + netdev = vsi->netdev; + if (!netdev) + return; + + if (!netif_carrier_ok(netdev)) + return; + + for (i = 0; i < vsi->back->num_active_queues; i++) { + tx_ring = &vsi->back->tx_rings[i]; + if (tx_ring && tx_ring->desc) { + /* If packet counter has not changed the queue is + * likely stalled, so force an interrupt for this + * queue. + * + * prev_pkt_ctr would be negative if there was no + * pending work. + */ + packets = tx_ring->stats.packets & INT_MAX; + if (tx_ring->tx_stats.prev_pkt_ctr == packets) { + iavf_force_wb(vsi, tx_ring->q_vector); + continue; + } + + /* Memory barrier between read of packet count and call + * to iavf_get_tx_pending() + */ + smp_rmb(); + tx_ring->tx_stats.prev_pkt_ctr = + iavf_get_tx_pending(tx_ring, true) ? packets : -1; + } + } +} + +#define WB_STRIDE 4 + +/** + * iavf_clean_tx_irq - Reclaim resources after transmit completes + * @vsi: the VSI we care about + * @tx_ring: Tx ring to clean + * @napi_budget: Used to determine if we are in netpoll + * + * Returns true if there's any budget left (e.g. the clean is finished) + **/ +static bool iavf_clean_tx_irq(struct iavf_vsi *vsi, + struct iavf_ring *tx_ring, int napi_budget) +{ + u16 i = tx_ring->next_to_clean; + struct iavf_tx_buffer *tx_buf; + struct iavf_tx_desc *tx_desc; + unsigned int total_bytes = 0, total_packets = 0; + unsigned int budget = vsi->work_limit; + + tx_buf = &tx_ring->tx_bi[i]; + tx_desc = IAVF_TX_DESC(tx_ring, i); + i -= tx_ring->count; + + do { + struct iavf_tx_desc *eop_desc = tx_buf->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(); + + iavf_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf); + /* if the descriptor isn't done, no work yet to do */ + if (!(eop_desc->cmd_type_offset_bsz & + cpu_to_le64(IAVF_TX_DESC_DTYPE_DESC_DONE))) + break; + + /* clear next_to_watch to prevent false hangs */ + tx_buf->next_to_watch = NULL; + + /* update the statistics for this packet */ + total_bytes += tx_buf->bytecount; + total_packets += tx_buf->gso_segs; + + /* free the skb */ + napi_consume_skb(tx_buf->skb, napi_budget); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buf, dma), + dma_unmap_len(tx_buf, len), + DMA_TO_DEVICE); + + /* clear tx_buffer data */ + tx_buf->skb = NULL; + dma_unmap_len_set(tx_buf, len, 0); + + /* unmap remaining buffers */ + while (tx_desc != eop_desc) { + iavf_trace(clean_tx_irq_unmap, + tx_ring, tx_desc, tx_buf); + + tx_buf++; + tx_desc++; + i++; + if (unlikely(!i)) { + i -= tx_ring->count; + tx_buf = tx_ring->tx_bi; + tx_desc = IAVF_TX_DESC(tx_ring, 0); + } + + /* unmap any remaining paged data */ + if (dma_unmap_len(tx_buf, len)) { + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buf, dma), + dma_unmap_len(tx_buf, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buf, len, 0); + } + } + + /* move us one more past the eop_desc for start of next pkt */ + tx_buf++; + tx_desc++; + i++; + if (unlikely(!i)) { + i -= tx_ring->count; + tx_buf = tx_ring->tx_bi; + tx_desc = IAVF_TX_DESC(tx_ring, 0); + } + + prefetch(tx_desc); + + /* update budget accounting */ + budget--; + } while (likely(budget)); + + i += tx_ring->count; + tx_ring->next_to_clean = i; + u64_stats_update_begin(&tx_ring->syncp); + tx_ring->stats.bytes += total_bytes; + tx_ring->stats.packets += total_packets; + u64_stats_update_end(&tx_ring->syncp); + tx_ring->q_vector->tx.total_bytes += total_bytes; + tx_ring->q_vector->tx.total_packets += total_packets; + + if (tx_ring->flags & IAVF_TXR_FLAGS_WB_ON_ITR) { + /* 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. + */ + unsigned int j = iavf_get_tx_pending(tx_ring, false); + + if (budget && + ((j / WB_STRIDE) == 0) && (j > 0) && + !test_bit(__IAVF_VSI_DOWN, vsi->state) && + (IAVF_DESC_UNUSED(tx_ring) != tx_ring->count)) + tx_ring->arm_wb = true; + } + + /* notify netdev of completed buffers */ + netdev_tx_completed_queue(txring_txq(tx_ring), + total_packets, total_bytes); + +#define TX_WAKE_THRESHOLD ((s16)(DESC_NEEDED * 2)) + if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) && + (IAVF_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(__IAVF_VSI_DOWN, vsi->state)) { + netif_wake_subqueue(tx_ring->netdev, + tx_ring->queue_index); + ++tx_ring->tx_stats.restart_queue; + } + } + + return !!budget; +} + +/** + * iavf_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 enable writeback + * + **/ +static void iavf_enable_wb_on_itr(struct iavf_vsi *vsi, + struct iavf_q_vector *q_vector) +{ + u16 flags = q_vector->tx.ring[0].flags; + u32 val; + + if (!(flags & IAVF_TXR_FLAGS_WB_ON_ITR)) + return; + + if (q_vector->arm_wb_state) + return; + + val = IAVF_VFINT_DYN_CTLN1_WB_ON_ITR_MASK | + IAVF_VFINT_DYN_CTLN1_ITR_INDX_MASK; /* set noitr */ + + wr32(&vsi->back->hw, + IAVF_VFINT_DYN_CTLN1(q_vector->reg_idx), val); + q_vector->arm_wb_state = true; +} + +/** + * iavf_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 iavf_force_wb(struct iavf_vsi *vsi, struct iavf_q_vector *q_vector) +{ + u32 val = IAVF_VFINT_DYN_CTLN1_INTENA_MASK | + IAVF_VFINT_DYN_CTLN1_ITR_INDX_MASK | /* set noitr */ + IAVF_VFINT_DYN_CTLN1_SWINT_TRIG_MASK | + IAVF_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_MASK + /* allow 00 to be written to the index */; + + wr32(&vsi->back->hw, + IAVF_VFINT_DYN_CTLN1(q_vector->reg_idx), + val); +} + +static inline bool iavf_container_is_rx(struct iavf_q_vector *q_vector, + struct iavf_ring_container *rc) +{ + return &q_vector->rx == rc; +} + +static inline unsigned int iavf_itr_divisor(struct iavf_q_vector *q_vector) +{ + unsigned int divisor; + + switch (q_vector->adapter->link_speed) { + case I40E_LINK_SPEED_40GB: + divisor = IAVF_ITR_ADAPTIVE_MIN_INC * 1024; + break; + case I40E_LINK_SPEED_25GB: + case I40E_LINK_SPEED_20GB: + divisor = IAVF_ITR_ADAPTIVE_MIN_INC * 512; + break; + default: + case I40E_LINK_SPEED_10GB: + divisor = IAVF_ITR_ADAPTIVE_MIN_INC * 256; + break; + case I40E_LINK_SPEED_1GB: + case I40E_LINK_SPEED_100MB: + divisor = IAVF_ITR_ADAPTIVE_MIN_INC * 32; + break; + } + + return divisor; +} + +/** + * iavf_update_itr - update the dynamic ITR value based on statistics + * @q_vector: structure containing interrupt and ring information + * @rc: structure containing ring performance data + * + * 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. + **/ +static void iavf_update_itr(struct iavf_q_vector *q_vector, + struct iavf_ring_container *rc) +{ + unsigned int avg_wire_size, packets, bytes, itr; + unsigned long next_update = jiffies; + + /* If we don't have any rings just leave ourselves set for maximum + * possible latency so we take ourselves out of the equation. + */ + if (!rc->ring || !ITR_IS_DYNAMIC(rc->ring->itr_setting)) + return; + + /* For Rx we want to push the delay up and default to low latency. + * for Tx we want to pull the delay down and default to high latency. + */ + itr = iavf_container_is_rx(q_vector, rc) ? + IAVF_ITR_ADAPTIVE_MIN_USECS | IAVF_ITR_ADAPTIVE_LATENCY : + IAVF_ITR_ADAPTIVE_MAX_USECS | IAVF_ITR_ADAPTIVE_LATENCY; + + /* If we didn't update within up to 1 - 2 jiffies we can assume + * that either packets are coming in so slow there hasn't been + * any work, or that there is so much work that NAPI is dealing + * with interrupt moderation and we don't need to do anything. + */ + if (time_after(next_update, rc->next_update)) + goto clear_counts; + + /* If itr_countdown is set it means we programmed an ITR within + * the last 4 interrupt cycles. This has a side effect of us + * potentially firing an early interrupt. In order to work around + * this we need to throw out any data received for a few + * interrupts following the update. + */ + if (q_vector->itr_countdown) { + itr = rc->target_itr; + goto clear_counts; + } + + packets = rc->total_packets; + bytes = rc->total_bytes; + + if (iavf_container_is_rx(q_vector, rc)) { + /* If Rx there are 1 to 4 packets and bytes are less than + * 9000 assume insufficient data to use bulk rate limiting + * approach unless Tx is already in bulk rate limiting. We + * are likely latency driven. + */ + if (packets && packets < 4 && bytes < 9000 && + (q_vector->tx.target_itr & IAVF_ITR_ADAPTIVE_LATENCY)) { + itr = IAVF_ITR_ADAPTIVE_LATENCY; + goto adjust_by_size; + } + } else if (packets < 4) { + /* If we have Tx and Rx ITR maxed and Tx ITR is running in + * bulk mode and we are receiving 4 or fewer packets just + * reset the ITR_ADAPTIVE_LATENCY bit for latency mode so + * that the Rx can relax. + */ + if (rc->target_itr == IAVF_ITR_ADAPTIVE_MAX_USECS && + (q_vector->rx.target_itr & IAVF_ITR_MASK) == + IAVF_ITR_ADAPTIVE_MAX_USECS) + goto clear_counts; + } else if (packets > 32) { + /* If we have processed over 32 packets in a single interrupt + * for Tx assume we need to switch over to "bulk" mode. + */ + rc->target_itr &= ~IAVF_ITR_ADAPTIVE_LATENCY; + } + + /* We have no packets to actually measure against. This means + * either one of the other queues on this vector is active or + * we are a Tx queue doing TSO with too high of an interrupt rate. + * + * Between 4 and 56 we can assume that our current interrupt delay + * is only slightly too low. As such we should increase it by a small + * fixed amount. + */ + if (packets < 56) { + itr = rc->target_itr + IAVF_ITR_ADAPTIVE_MIN_INC; + if ((itr & IAVF_ITR_MASK) > IAVF_ITR_ADAPTIVE_MAX_USECS) { + itr &= IAVF_ITR_ADAPTIVE_LATENCY; + itr += IAVF_ITR_ADAPTIVE_MAX_USECS; + } + goto clear_counts; + } + + if (packets <= 256) { + itr = min(q_vector->tx.current_itr, q_vector->rx.current_itr); + itr &= IAVF_ITR_MASK; + + /* Between 56 and 112 is our "goldilocks" zone where we are + * working out "just right". Just report that our current + * ITR is good for us. + */ + if (packets <= 112) + goto clear_counts; + + /* If packet count is 128 or greater we are likely looking + * at a slight overrun of the delay we want. Try halving + * our delay to see if that will cut the number of packets + * in half per interrupt. + */ + itr /= 2; + itr &= IAVF_ITR_MASK; + if (itr < IAVF_ITR_ADAPTIVE_MIN_USECS) + itr = IAVF_ITR_ADAPTIVE_MIN_USECS; + + goto clear_counts; + } + + /* The paths below assume we are dealing with a bulk ITR since + * number of packets is greater than 256. We are just going to have + * to compute a value and try to bring the count under control, + * though for smaller packet sizes there isn't much we can do as + * NAPI polling will likely be kicking in sooner rather than later. + */ + itr = IAVF_ITR_ADAPTIVE_BULK; + +adjust_by_size: + /* If packet counts are 256 or greater we can assume we have a gross + * overestimation of what the rate should be. Instead of trying to fine + * tune it just use the formula below to try and dial in an exact value + * give the current packet size of the frame. + */ + avg_wire_size = bytes / packets; + + /* The following is a crude approximation of: + * wmem_default / (size + overhead) = desired_pkts_per_int + * rate / bits_per_byte / (size + ethernet overhead) = pkt_rate + * (desired_pkt_rate / pkt_rate) * usecs_per_sec = ITR value + * + * Assuming wmem_default is 212992 and overhead is 640 bytes per + * packet, (256 skb, 64 headroom, 320 shared info), we can reduce the + * formula down to + * + * (170 * (size + 24)) / (size + 640) = ITR + * + * We first do some math on the packet size and then finally bitshift + * by 8 after rounding up. We also have to account for PCIe link speed + * difference as ITR scales based on this. + */ + if (avg_wire_size <= 60) { + /* Start at 250k ints/sec */ + avg_wire_size = 4096; + } else if (avg_wire_size <= 380) { + /* 250K ints/sec to 60K ints/sec */ + avg_wire_size *= 40; + avg_wire_size += 1696; + } else if (avg_wire_size <= 1084) { + /* 60K ints/sec to 36K ints/sec */ + avg_wire_size *= 15; + avg_wire_size += 11452; + } else if (avg_wire_size <= 1980) { + /* 36K ints/sec to 30K ints/sec */ + avg_wire_size *= 5; + avg_wire_size += 22420; + } else { + /* plateau at a limit of 30K ints/sec */ + avg_wire_size = 32256; + } + + /* If we are in low latency mode halve our delay which doubles the + * rate to somewhere between 100K to 16K ints/sec + */ + if (itr & IAVF_ITR_ADAPTIVE_LATENCY) + avg_wire_size /= 2; + + /* Resultant value is 256 times larger than it needs to be. This + * gives us room to adjust the value as needed to either increase + * or decrease the value based on link speeds of 10G, 2.5G, 1G, etc. + * + * Use addition as we have already recorded the new latency flag + * for the ITR value. + */ + itr += DIV_ROUND_UP(avg_wire_size, iavf_itr_divisor(q_vector)) * + IAVF_ITR_ADAPTIVE_MIN_INC; + + if ((itr & IAVF_ITR_MASK) > IAVF_ITR_ADAPTIVE_MAX_USECS) { + itr &= IAVF_ITR_ADAPTIVE_LATENCY; + itr += IAVF_ITR_ADAPTIVE_MAX_USECS; + } + +clear_counts: + /* write back value */ + rc->target_itr = itr; + + /* next update should occur within next jiffy */ + rc->next_update = next_update + 1; + + rc->total_bytes = 0; + rc->total_packets = 0; +} + +/** + * iavf_setup_tx_descriptors - Allocate the Tx descriptors + * @tx_ring: the tx ring to set up + * + * Return 0 on success, negative on error + **/ +int iavf_setup_tx_descriptors(struct iavf_ring *tx_ring) +{ + struct device *dev = tx_ring->dev; + int bi_size; + + if (!dev) + return -ENOMEM; + + /* warn if we are about to overwrite the pointer */ + WARN_ON(tx_ring->tx_bi); + bi_size = sizeof(struct iavf_tx_buffer) * tx_ring->count; + tx_ring->tx_bi = kzalloc(bi_size, GFP_KERNEL); + if (!tx_ring->tx_bi) + goto err; + + /* round up to nearest 4K */ + tx_ring->size = tx_ring->count * sizeof(struct iavf_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) { + dev_info(dev, "Unable to allocate memory for the Tx descriptor ring, size=%d\n", + tx_ring->size); + goto err; + } + + tx_ring->next_to_use = 0; + tx_ring->next_to_clean = 0; + tx_ring->tx_stats.prev_pkt_ctr = -1; + return 0; + +err: + kfree(tx_ring->tx_bi); + tx_ring->tx_bi = NULL; + return -ENOMEM; +} + +/** + * iavf_clean_rx_ring - Free Rx buffers + * @rx_ring: ring to be cleaned + **/ +void iavf_clean_rx_ring(struct iavf_ring *rx_ring) +{ + unsigned long bi_size; + u16 i; + + /* ring already cleared, nothing to do */ + if (!rx_ring->rx_bi) + return; + + if (rx_ring->skb) { + dev_kfree_skb(rx_ring->skb); + rx_ring->skb = NULL; + } + + /* Free all the Rx ring sk_buffs */ + for (i = 0; i < rx_ring->count; i++) { + struct iavf_rx_buffer *rx_bi = &rx_ring->rx_bi[i]; + + if (!rx_bi->page) + continue; + + /* 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, + rx_bi->dma, + rx_bi->page_offset, + rx_ring->rx_buf_len, + DMA_FROM_DEVICE); + + /* free resources associated with mapping */ + dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma, + iavf_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IAVF_RX_DMA_ATTR); + + __page_frag_cache_drain(rx_bi->page, rx_bi->pagecnt_bias); + + rx_bi->page = NULL; + rx_bi->page_offset = 0; + } + + bi_size = sizeof(struct iavf_rx_buffer) * rx_ring->count; + memset(rx_ring->rx_bi, 0, bi_size); + + /* Zero out the descriptor ring */ + memset(rx_ring->desc, 0, rx_ring->size); + + rx_ring->next_to_alloc = 0; + rx_ring->next_to_clean = 0; + rx_ring->next_to_use = 0; +} + +/** + * iavf_free_rx_resources - Free Rx resources + * @rx_ring: ring to clean the resources from + * + * Free all receive software resources + **/ +void iavf_free_rx_resources(struct iavf_ring *rx_ring) +{ + iavf_clean_rx_ring(rx_ring); + kfree(rx_ring->rx_bi); + rx_ring->rx_bi = NULL; + + if (rx_ring->desc) { + dma_free_coherent(rx_ring->dev, rx_ring->size, + rx_ring->desc, rx_ring->dma); + rx_ring->desc = NULL; + } +} + +/** + * iavf_setup_rx_descriptors - Allocate Rx descriptors + * @rx_ring: Rx descriptor ring (for a specific queue) to setup + * + * Returns 0 on success, negative on failure + **/ +int iavf_setup_rx_descriptors(struct iavf_ring *rx_ring) +{ + struct device *dev = rx_ring->dev; + int bi_size; + + /* warn if we are about to overwrite the pointer */ + WARN_ON(rx_ring->rx_bi); + bi_size = sizeof(struct iavf_rx_buffer) * rx_ring->count; + rx_ring->rx_bi = kzalloc(bi_size, GFP_KERNEL); + if (!rx_ring->rx_bi) + goto err; + + u64_stats_init(&rx_ring->syncp); + + /* Round up to nearest 4K */ + rx_ring->size = rx_ring->count * sizeof(union iavf_32byte_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) { + dev_info(dev, "Unable to allocate memory for the Rx descriptor ring, size=%d\n", + rx_ring->size); + goto err; + } + + rx_ring->next_to_alloc = 0; + rx_ring->next_to_clean = 0; + rx_ring->next_to_use = 0; + + return 0; +err: + kfree(rx_ring->rx_bi); + rx_ring->rx_bi = NULL; + return -ENOMEM; +} + +/** + * iavf_release_rx_desc - Store the new tail and head values + * @rx_ring: ring to bump + * @val: new head index + **/ +static inline void iavf_release_rx_desc(struct iavf_ring *rx_ring, u32 val) +{ + rx_ring->next_to_use = val; + + /* update next to alloc since we have filled the ring */ + rx_ring->next_to_alloc = val; + + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. (Only + * applicable for weak-ordered memory model archs, + * such as IA-64). + */ + wmb(); + writel(val, rx_ring->tail); +} + +/** + * iavf_rx_offset - Return expected offset into page to access data + * @rx_ring: Ring we are requesting offset of + * + * Returns the offset value for ring into the data buffer. + */ +static inline unsigned int iavf_rx_offset(struct iavf_ring *rx_ring) +{ + return ring_uses_build_skb(rx_ring) ? IAVF_SKB_PAD : 0; +} + +/** + * iavf_alloc_mapped_page - recycle or make a new page + * @rx_ring: ring to use + * @bi: rx_buffer struct to modify + * + * Returns true if the page was successfully allocated or + * reused. + **/ +static bool iavf_alloc_mapped_page(struct iavf_ring *rx_ring, + struct iavf_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)) { + rx_ring->rx_stats.page_reuse_count++; + return true; + } + + /* alloc new page for storage */ + page = dev_alloc_pages(iavf_rx_pg_order(rx_ring)); + if (unlikely(!page)) { + rx_ring->rx_stats.alloc_page_failed++; + return false; + } + + /* map page for use */ + dma = dma_map_page_attrs(rx_ring->dev, page, 0, + iavf_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IAVF_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, iavf_rx_pg_order(rx_ring)); + rx_ring->rx_stats.alloc_page_failed++; + return false; + } + + bi->dma = dma; + bi->page = page; + bi->page_offset = iavf_rx_offset(rx_ring); + + /* initialize pagecnt_bias to 1 representing we fully own page */ + bi->pagecnt_bias = 1; + + return true; +} + +/** + * iavf_receive_skb - Send a completed packet up the stack + * @rx_ring: rx ring in play + * @skb: packet to send up + * @vlan_tag: vlan tag for packet + **/ +static void iavf_receive_skb(struct iavf_ring *rx_ring, + struct sk_buff *skb, u16 vlan_tag) +{ + struct iavf_q_vector *q_vector = rx_ring->q_vector; + + if ((rx_ring->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) && + (vlan_tag & VLAN_VID_MASK)) + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag); + + napi_gro_receive(&q_vector->napi, skb); +} + +/** + * iavf_alloc_rx_buffers - Replace used receive buffers + * @rx_ring: ring to place buffers on + * @cleaned_count: number of buffers to replace + * + * Returns false if all allocations were successful, true if any fail + **/ +bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count) +{ + u16 ntu = rx_ring->next_to_use; + union iavf_rx_desc *rx_desc; + struct iavf_rx_buffer *bi; + + /* do nothing if no valid netdev defined */ + if (!rx_ring->netdev || !cleaned_count) + return false; + + rx_desc = IAVF_RX_DESC(rx_ring, ntu); + bi = &rx_ring->rx_bi[ntu]; + + do { + if (!iavf_alloc_mapped_page(rx_ring, bi)) + goto no_buffers; + + /* sync the buffer for use by the device */ + dma_sync_single_range_for_device(rx_ring->dev, bi->dma, + bi->page_offset, + rx_ring->rx_buf_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->dma + bi->page_offset); + + rx_desc++; + bi++; + ntu++; + if (unlikely(ntu == rx_ring->count)) { + rx_desc = IAVF_RX_DESC(rx_ring, 0); + bi = rx_ring->rx_bi; + ntu = 0; + } + + /* clear the status bits for the next_to_use descriptor */ + rx_desc->wb.qword1.status_error_len = 0; + + cleaned_count--; + } while (cleaned_count); + + if (rx_ring->next_to_use != ntu) + iavf_release_rx_desc(rx_ring, ntu); + + return false; + +no_buffers: + if (rx_ring->next_to_use != ntu) + iavf_release_rx_desc(rx_ring, ntu); + + /* make sure to come back via polling to try again after + * allocation failure + */ + return true; +} + +/** + * iavf_rx_checksum - Indicate in skb if hw indicated a good cksum + * @vsi: the VSI we care about + * @skb: skb currently being received and modified + * @rx_desc: the receive descriptor + **/ +static inline void iavf_rx_checksum(struct iavf_vsi *vsi, + struct sk_buff *skb, + union iavf_rx_desc *rx_desc) +{ + struct iavf_rx_ptype_decoded decoded; + u32 rx_error, rx_status; + bool ipv4, ipv6; + u8 ptype; + u64 qword; + + qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); + ptype = (qword & IAVF_RXD_QW1_PTYPE_MASK) >> IAVF_RXD_QW1_PTYPE_SHIFT; + rx_error = (qword & IAVF_RXD_QW1_ERROR_MASK) >> + IAVF_RXD_QW1_ERROR_SHIFT; + rx_status = (qword & IAVF_RXD_QW1_STATUS_MASK) >> + IAVF_RXD_QW1_STATUS_SHIFT; + decoded = decode_rx_desc_ptype(ptype); + + skb->ip_summed = CHECKSUM_NONE; + + skb_checksum_none_assert(skb); + + /* Rx csum enabled and ip headers found? */ + if (!(vsi->netdev->features & NETIF_F_RXCSUM)) + return; + + /* did the hardware decode the packet and checksum? */ + if (!(rx_status & BIT(IAVF_RX_DESC_STATUS_L3L4P_SHIFT))) + return; + + /* both known and outer_ip must be set for the below code to work */ + if (!(decoded.known && decoded.outer_ip)) + return; + + ipv4 = (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP) && + (decoded.outer_ip_ver == IAVF_RX_PTYPE_OUTER_IPV4); + ipv6 = (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP) && + (decoded.outer_ip_ver == IAVF_RX_PTYPE_OUTER_IPV6); + + if (ipv4 && + (rx_error & (BIT(IAVF_RX_DESC_ERROR_IPE_SHIFT) | + BIT(IAVF_RX_DESC_ERROR_EIPE_SHIFT)))) + goto checksum_fail; + + /* likely incorrect csum if alternate IP extension headers found */ + if (ipv6 && + rx_status & BIT(IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT)) + /* don't increment checksum err here, non-fatal err */ + return; + + /* there was some L4 error, count error and punt packet to the stack */ + if (rx_error & BIT(IAVF_RX_DESC_ERROR_L4E_SHIFT)) + goto checksum_fail; + + /* handle packets that were not able to be checksummed due + * to arrival speed, in this case the stack can compute + * the csum. + */ + if (rx_error & BIT(IAVF_RX_DESC_ERROR_PPRS_SHIFT)) + return; + + /* Only report checksum unnecessary for TCP, UDP, or SCTP */ + switch (decoded.inner_prot) { + case IAVF_RX_PTYPE_INNER_PROT_TCP: + case IAVF_RX_PTYPE_INNER_PROT_UDP: + case IAVF_RX_PTYPE_INNER_PROT_SCTP: + skb->ip_summed = CHECKSUM_UNNECESSARY; + /* fall though */ + default: + break; + } + + return; + +checksum_fail: + vsi->back->hw_csum_rx_error++; +} + +/** + * iavf_ptype_to_htype - get a hash type + * @ptype: the ptype value from the descriptor + * + * Returns a hash type to be used by skb_set_hash + **/ +static inline int iavf_ptype_to_htype(u8 ptype) +{ + struct iavf_rx_ptype_decoded decoded = decode_rx_desc_ptype(ptype); + + if (!decoded.known) + return PKT_HASH_TYPE_NONE; + + if (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP && + decoded.payload_layer == IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY4) + return PKT_HASH_TYPE_L4; + else if (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP && + decoded.payload_layer == IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY3) + return PKT_HASH_TYPE_L3; + else + return PKT_HASH_TYPE_L2; +} + +/** + * iavf_rx_hash - set the hash value in the skb + * @ring: descriptor ring + * @rx_desc: specific descriptor + * @skb: skb currently being received and modified + * @rx_ptype: Rx packet type + **/ +static inline void iavf_rx_hash(struct iavf_ring *ring, + union iavf_rx_desc *rx_desc, + struct sk_buff *skb, + u8 rx_ptype) +{ + u32 hash; + const __le64 rss_mask = + cpu_to_le64((u64)IAVF_RX_DESC_FLTSTAT_RSS_HASH << + IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT); + + if (ring->netdev->features & NETIF_F_RXHASH) + return; + + if ((rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask) { + hash = le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss); + skb_set_hash(skb, hash, iavf_ptype_to_htype(rx_ptype)); + } +} + +/** + * iavf_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 + * @rx_ptype: the packet type decoded by hardware + * + * This function checks the ring, descriptor, and packet information in + * order to populate the hash, checksum, VLAN, protocol, and + * other fields within the skb. + **/ +static inline +void iavf_process_skb_fields(struct iavf_ring *rx_ring, + union iavf_rx_desc *rx_desc, struct sk_buff *skb, + u8 rx_ptype) +{ + iavf_rx_hash(rx_ring, rx_desc, skb, rx_ptype); + + iavf_rx_checksum(rx_ring->vsi, skb, rx_desc); + + skb_record_rx_queue(skb, rx_ring->queue_index); + + /* modifies the skb - consumes the enet header */ + skb->protocol = eth_type_trans(skb, rx_ring->netdev); +} + +/** + * iavf_cleanup_headers - Correct empty headers + * @rx_ring: rx descriptor ring packet is being transacted on + * @skb: pointer to current skb being fixed + * + * Also 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 iavf_cleanup_headers(struct iavf_ring *rx_ring, struct sk_buff *skb) +{ + /* if eth_skb_pad returns an error the skb was freed */ + if (eth_skb_pad(skb)) + return true; + + return false; +} + +/** + * iavf_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 iavf_reuse_rx_page(struct iavf_ring *rx_ring, + struct iavf_rx_buffer *old_buff) +{ + struct iavf_rx_buffer *new_buff; + u16 nta = rx_ring->next_to_alloc; + + new_buff = &rx_ring->rx_bi[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 */ + 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; +} + +/** + * iavf_page_is_reusable - check if any reuse is possible + * @page: page struct to check + * + * A page is not reusable if it was allocated under low memory + * conditions, or it's not in the same NUMA node as this CPU. + */ +static inline bool iavf_page_is_reusable(struct page *page) +{ + return (page_to_nid(page) == numa_mem_id()) && + !page_is_pfmemalloc(page); +} + +/** + * iavf_can_reuse_rx_page - Determine if this page can be reused by + * the adapter for another receive + * + * @rx_buffer: buffer containing the page + * + * If page is reusable, rx_buffer->page_offset is adjusted to point to + * an unused region in the page. + * + * For small pages, @truesize will be a constant value, half the size + * of the memory at page. We'll attempt to alternate between high and + * low halves of the page, with one half ready for use by the hardware + * and the other half being consumed by the stack. We use the page + * ref count to determine whether the stack has finished consuming the + * portion of this page that was passed up with a previous packet. If + * the page ref count is >1, we'll assume the "other" half page is + * still busy, and this page cannot be reused. + * + * For larger pages, @truesize will be the actual space used by the + * received packet (adjusted upward to an even multiple of the cache + * line size). This will advance through the page by the amount + * actually consumed by the received packets while there is still + * space for a buffer. Each region of larger pages will be used at + * most once, after which the page will not be reused. + * + * In either case, if the page is reusable its refcount is increased. + **/ +static bool iavf_can_reuse_rx_page(struct iavf_rx_buffer *rx_buffer) +{ + unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; + struct page *page = rx_buffer->page; + + /* Is any reuse possible? */ + if (unlikely(!iavf_page_is_reusable(page))) + return false; + +#if (PAGE_SIZE < 8192) + /* if we are only owner of page we can reuse it */ + if (unlikely((page_count(page) - pagecnt_bias) > 1)) + return false; +#else +#define IAVF_LAST_OFFSET \ + (SKB_WITH_OVERHEAD(PAGE_SIZE) - IAVF_RXBUFFER_2048) + if (rx_buffer->page_offset > IAVF_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)) { + page_ref_add(page, USHRT_MAX); + rx_buffer->pagecnt_bias = USHRT_MAX; + } + + return true; +} + +/** + * iavf_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: packet length from rx_desc + * + * This function will add the data contained in rx_buffer->page to the skb. + * It will just attach the page as a frag to the skb. + * + * The function will then update the page offset. + **/ +static void iavf_add_rx_frag(struct iavf_ring *rx_ring, + struct iavf_rx_buffer *rx_buffer, + struct sk_buff *skb, + unsigned int size) +{ +#if (PAGE_SIZE < 8192) + unsigned int truesize = iavf_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(size + iavf_rx_offset(rx_ring)); +#endif + + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, + rx_buffer->page_offset, size, truesize); + + /* page is being used so we must update the page offset */ +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif +} + +/** + * iavf_get_rx_buffer - Fetch Rx buffer and synchronize data for use + * @rx_ring: rx descriptor ring to transact packets on + * @size: size of buffer to add to skb + * + * This function will pull an Rx buffer from the ring and synchronize it + * for use by the CPU. + */ +static struct iavf_rx_buffer *iavf_get_rx_buffer(struct iavf_ring *rx_ring, + const unsigned int size) +{ + struct iavf_rx_buffer *rx_buffer; + + rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean]; + 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); + + /* We have pulled a buffer for use, so decrement pagecnt_bias */ + rx_buffer->pagecnt_bias--; + + return rx_buffer; +} + +/** + * iavf_construct_skb - Allocate skb and populate it + * @rx_ring: rx descriptor ring to transact packets on + * @rx_buffer: rx buffer to pull data from + * @size: size of buffer to add to skb + * + * This function allocates an skb. It then populates it with the page + * data from the current receive descriptor, taking care to set up the + * skb correctly. + */ +static struct sk_buff *iavf_construct_skb(struct iavf_ring *rx_ring, + struct iavf_rx_buffer *rx_buffer, + unsigned int size) +{ + void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE < 8192) + unsigned int truesize = iavf_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(size); +#endif + unsigned int headlen; + struct sk_buff *skb; + + /* prefetch first cache line of first page */ + prefetch(va); +#if L1_CACHE_BYTES < 128 + prefetch(va + L1_CACHE_BYTES); +#endif + + /* allocate a skb to store the frags */ + skb = __napi_alloc_skb(&rx_ring->q_vector->napi, + IAVF_RX_HDR_SIZE, + GFP_ATOMIC | __GFP_NOWARN); + if (unlikely(!skb)) + return NULL; + + /* Determine available headroom for copy */ + headlen = size; + if (headlen > IAVF_RX_HDR_SIZE) + headlen = eth_get_headlen(va, IAVF_RX_HDR_SIZE); + + /* align pull length to size of long to optimize memcpy performance */ + memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); + + /* update all of the pointers */ + size -= headlen; + if (size) { + skb_add_rx_frag(skb, 0, rx_buffer->page, + rx_buffer->page_offset + headlen, + size, truesize); + + /* buffer is used by skb, update page_offset */ +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif + } else { + /* buffer is unused, reset bias back to rx_buffer */ + rx_buffer->pagecnt_bias++; + } + + return skb; +} + +/** + * iavf_build_skb - Build skb around an existing buffer + * @rx_ring: Rx descriptor ring to transact packets on + * @rx_buffer: Rx buffer to pull data from + * @size: size of buffer to add to skb + * + * This function builds an skb around an existing Rx buffer, taking care + * to set up the skb correctly and avoid any memcpy overhead. + */ +static struct sk_buff *iavf_build_skb(struct iavf_ring *rx_ring, + struct iavf_rx_buffer *rx_buffer, + unsigned int size) +{ + void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE < 8192) + unsigned int truesize = iavf_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + + SKB_DATA_ALIGN(IAVF_SKB_PAD + size); +#endif + struct sk_buff *skb; + + /* prefetch first cache line of first page */ + prefetch(va); +#if L1_CACHE_BYTES < 128 + prefetch(va + L1_CACHE_BYTES); +#endif + /* build an skb around the page buffer */ + skb = build_skb(va - IAVF_SKB_PAD, truesize); + if (unlikely(!skb)) + return NULL; + + /* update pointers within the skb to store the data */ + skb_reserve(skb, IAVF_SKB_PAD); + __skb_put(skb, size); + + /* buffer is used by skb, update page_offset */ +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif + + return skb; +} + +/** + * iavf_put_rx_buffer - Clean up used buffer and either recycle or free + * @rx_ring: rx descriptor ring to transact packets on + * @rx_buffer: rx buffer to pull data from + * + * This function will clean up the contents of the rx_buffer. It will + * either recycle the buffer or unmap it and free the associated resources. + */ +static void iavf_put_rx_buffer(struct iavf_ring *rx_ring, + struct iavf_rx_buffer *rx_buffer) +{ + if (iavf_can_reuse_rx_page(rx_buffer)) { + /* hand second half of page back to the ring */ + iavf_reuse_rx_page(rx_ring, rx_buffer); + rx_ring->rx_stats.page_reuse_count++; + } else { + /* we are not reusing the buffer so unmap it */ + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, + iavf_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, IAVF_RX_DMA_ATTR); + __page_frag_cache_drain(rx_buffer->page, + rx_buffer->pagecnt_bias); + } + + /* clear contents of buffer_info */ + rx_buffer->page = NULL; +} + +/** + * iavf_is_non_eop - process handling of non-EOP buffers + * @rx_ring: Rx ring being processed + * @rx_desc: Rx descriptor for current buffer + * @skb: Current socket buffer containing buffer in progress + * + * This function updates next to clean. If the buffer is an EOP buffer + * this function exits returning false, otherwise it will place the + * sk_buff in the next buffer to be chained and return true indicating + * that this is in fact a non-EOP buffer. + **/ +static bool iavf_is_non_eop(struct iavf_ring *rx_ring, + union iavf_rx_desc *rx_desc, + struct sk_buff *skb) +{ + 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(IAVF_RX_DESC(rx_ring, ntc)); + + /* if we are the last buffer then there is nothing else to do */ +#define IAVF_RXD_EOF BIT(IAVF_RX_DESC_STATUS_EOF_SHIFT) + if (likely(iavf_test_staterr(rx_desc, IAVF_RXD_EOF))) + return false; + + rx_ring->rx_stats.non_eop_descs++; + + return true; +} + +/** + * iavf_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf + * @rx_ring: rx descriptor ring to transact packets on + * @budget: Total limit on number of packets to process + * + * This function provides a "bounce buffer" approach to Rx interrupt + * processing. The advantage to this is that on systems that have + * expensive overhead for IOMMU access this provides a means of avoiding + * it by maintaining the mapping of the page to the system. + * + * Returns amount of work completed + **/ +static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget) +{ + unsigned int total_rx_bytes = 0, total_rx_packets = 0; + struct sk_buff *skb = rx_ring->skb; + u16 cleaned_count = IAVF_DESC_UNUSED(rx_ring); + bool failure = false; + + while (likely(total_rx_packets < (unsigned int)budget)) { + struct iavf_rx_buffer *rx_buffer; + union iavf_rx_desc *rx_desc; + unsigned int size; + u16 vlan_tag; + u8 rx_ptype; + u64 qword; + + /* return some buffers to hardware, one at a time is too slow */ + if (cleaned_count >= IAVF_RX_BUFFER_WRITE) { + failure = failure || + iavf_alloc_rx_buffers(rx_ring, cleaned_count); + cleaned_count = 0; + } + + rx_desc = IAVF_RX_DESC(rx_ring, rx_ring->next_to_clean); + + /* status_error_len will always be zero for unused descriptors + * because it's cleared in cleanup, and overlaps with hdr_addr + * which is always zero because packet split isn't used, if the + * hardware wrote DD then the length will be non-zero + */ + qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); + + /* This memory barrier is needed to keep us from reading + * any other fields out of the rx_desc until we have + * verified the descriptor has been written back. + */ + dma_rmb(); + + size = (qword & IAVF_RXD_QW1_LENGTH_PBUF_MASK) >> + IAVF_RXD_QW1_LENGTH_PBUF_SHIFT; + if (!size) + break; + + iavf_trace(clean_rx_irq, rx_ring, rx_desc, skb); + rx_buffer = iavf_get_rx_buffer(rx_ring, size); + + /* retrieve a buffer from the ring */ + if (skb) + iavf_add_rx_frag(rx_ring, rx_buffer, skb, size); + else if (ring_uses_build_skb(rx_ring)) + skb = iavf_build_skb(rx_ring, rx_buffer, size); + else + skb = iavf_construct_skb(rx_ring, rx_buffer, size); + + /* exit if we failed to retrieve a buffer */ + if (!skb) { + rx_ring->rx_stats.alloc_buff_failed++; + rx_buffer->pagecnt_bias++; + break; + } + + iavf_put_rx_buffer(rx_ring, rx_buffer); + cleaned_count++; + + if (iavf_is_non_eop(rx_ring, rx_desc, skb)) + continue; + + /* ERR_MASK will only have valid bits if EOP set, and + * what we are doing here is actually checking + * IAVF_RX_DESC_ERROR_RXE_SHIFT, since it is the zeroth bit in + * the error field + */ + if (unlikely(iavf_test_staterr(rx_desc, BIT(IAVF_RXD_QW1_ERROR_SHIFT)))) { + dev_kfree_skb_any(skb); + skb = NULL; + continue; + } + + if (iavf_cleanup_headers(rx_ring, skb)) { + skb = NULL; + continue; + } + + /* probably a little skewed due to removing CRC */ + total_rx_bytes += skb->len; + + qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); + rx_ptype = (qword & IAVF_RXD_QW1_PTYPE_MASK) >> + IAVF_RXD_QW1_PTYPE_SHIFT; + + /* populate checksum, VLAN, and protocol */ + iavf_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); + + + vlan_tag = (qword & BIT(IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT)) ? + le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0; + + iavf_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb); + iavf_receive_skb(rx_ring, skb, vlan_tag); + skb = NULL; + + /* update budget accounting */ + total_rx_packets++; + } + + rx_ring->skb = skb; + + u64_stats_update_begin(&rx_ring->syncp); + rx_ring->stats.packets += total_rx_packets; + rx_ring->stats.bytes += total_rx_bytes; + u64_stats_update_end(&rx_ring->syncp); + rx_ring->q_vector->rx.total_packets += total_rx_packets; + rx_ring->q_vector->rx.total_bytes += total_rx_bytes; + + /* guarantee a trip back through this routine if there was a failure */ + return failure ? budget : (int)total_rx_packets; +} + +static inline u32 iavf_buildreg_itr(const int type, u16 itr) +{ + u32 val; + + /* We don't bother with setting the CLEARPBA bit as the data sheet + * points out doing so is "meaningless since it was already + * auto-cleared". The auto-clearing happens when the interrupt is + * asserted. + * + * Hardware errata 28 for also indicates that writing to a + * xxINT_DYN_CTLx CSR with INTENA_MSK (bit 31) set to 0 will clear + * an event in the PBA anyway so we need to rely on the automask + * to hold pending events for us until the interrupt is re-enabled + * + * The itr value is reported in microseconds, and the register + * value is recorded in 2 microsecond units. For this reason we + * only need to shift by the interval shift - 1 instead of the + * full value. + */ + itr &= IAVF_ITR_MASK; + + val = IAVF_VFINT_DYN_CTLN1_INTENA_MASK | + (type << IAVF_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) | + (itr << (IAVF_VFINT_DYN_CTLN1_INTERVAL_SHIFT - 1)); + + return val; +} + +/* a small macro to shorten up some long lines */ +#define INTREG IAVF_VFINT_DYN_CTLN1 + +/* The act of updating the ITR will cause it to immediately trigger. In order + * to prevent this from throwing off adaptive update statistics we defer the + * update so that it can only happen so often. So after either Tx or Rx are + * updated we make the adaptive scheme wait until either the ITR completely + * expires via the next_update expiration or we have been through at least + * 3 interrupts. + */ +#define ITR_COUNTDOWN_START 3 + +/** + * iavf_update_enable_itr - Update itr and re-enable MSIX interrupt + * @vsi: the VSI we care about + * @q_vector: q_vector for which itr is being updated and interrupt enabled + * + **/ +static inline void iavf_update_enable_itr(struct iavf_vsi *vsi, + struct iavf_q_vector *q_vector) +{ + struct iavf_hw *hw = &vsi->back->hw; + u32 intval; + + /* These will do nothing if dynamic updates are not enabled */ + iavf_update_itr(q_vector, &q_vector->tx); + iavf_update_itr(q_vector, &q_vector->rx); + + /* This block of logic allows us to get away with only updating + * one ITR value with each interrupt. The idea is to perform a + * pseudo-lazy update with the following criteria. + * + * 1. Rx is given higher priority than Tx if both are in same state + * 2. If we must reduce an ITR that is given highest priority. + * 3. We then give priority to increasing ITR based on amount. + */ + if (q_vector->rx.target_itr < q_vector->rx.current_itr) { + /* Rx ITR needs to be reduced, this is highest priority */ + intval = iavf_buildreg_itr(IAVF_RX_ITR, + q_vector->rx.target_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; + q_vector->itr_countdown = ITR_COUNTDOWN_START; + } else if ((q_vector->tx.target_itr < q_vector->tx.current_itr) || + ((q_vector->rx.target_itr - q_vector->rx.current_itr) < + (q_vector->tx.target_itr - q_vector->tx.current_itr))) { + /* Tx ITR needs to be reduced, this is second priority + * Tx ITR needs to be increased more than Rx, fourth priority + */ + intval = iavf_buildreg_itr(IAVF_TX_ITR, + q_vector->tx.target_itr); + q_vector->tx.current_itr = q_vector->tx.target_itr; + q_vector->itr_countdown = ITR_COUNTDOWN_START; + } else if (q_vector->rx.current_itr != q_vector->rx.target_itr) { + /* Rx ITR needs to be increased, third priority */ + intval = iavf_buildreg_itr(IAVF_RX_ITR, + q_vector->rx.target_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; + q_vector->itr_countdown = ITR_COUNTDOWN_START; + } else { + /* No ITR update, lowest priority */ + intval = iavf_buildreg_itr(IAVF_ITR_NONE, 0); + if (q_vector->itr_countdown) + q_vector->itr_countdown--; + } + + if (!test_bit(__IAVF_VSI_DOWN, vsi->state)) + wr32(hw, INTREG(q_vector->reg_idx), intval); +} + +/** + * iavf_napi_poll - NAPI polling Rx/Tx cleanup routine + * @napi: napi struct with our devices info in it + * @budget: amount of work driver is allowed to do this pass, in packets + * + * This function will clean all queues associated with a q_vector. + * + * Returns the amount of work done + **/ +int iavf_napi_poll(struct napi_struct *napi, int budget) +{ + struct iavf_q_vector *q_vector = + container_of(napi, struct iavf_q_vector, napi); + struct iavf_vsi *vsi = q_vector->vsi; + struct iavf_ring *ring; + bool clean_complete = true; + bool arm_wb = false; + int budget_per_ring; + int work_done = 0; + + if (test_bit(__IAVF_VSI_DOWN, vsi->state)) { + napi_complete(napi); + return 0; + } + + /* Since the actual Tx work is minimal, we can give the Tx a larger + * budget and be more aggressive about cleaning up the Tx descriptors. + */ + iavf_for_each_ring(ring, q_vector->tx) { + if (!iavf_clean_tx_irq(vsi, ring, budget)) { + clean_complete = false; + continue; + } + arm_wb |= ring->arm_wb; + ring->arm_wb = false; + } + + /* Handle case where we are called by netpoll with a budget of 0 */ + if (budget <= 0) + goto tx_only; + + /* We attempt to distribute budget to each Rx queue fairly, but don't + * allow the budget to go below 1 because that would exit polling early. + */ + budget_per_ring = max(budget/q_vector->num_ringpairs, 1); + + iavf_for_each_ring(ring, q_vector->rx) { + int cleaned = iavf_clean_rx_irq(ring, budget_per_ring); + + work_done += cleaned; + /* if we clean as many as budgeted, we must not be done */ + if (cleaned >= budget_per_ring) + clean_complete = false; + } + + /* If work not completed, return budget and polling will return */ + if (!clean_complete) { + int cpu_id = smp_processor_id(); + + /* It is possible that the interrupt affinity has changed but, + * if the cpu is pegged at 100%, polling will never exit while + * traffic continues and the interrupt will be stuck on this + * cpu. We check to make sure affinity is correct before we + * continue to poll, otherwise we must stop polling so the + * interrupt can move to the correct cpu. + */ + if (!cpumask_test_cpu(cpu_id, &q_vector->affinity_mask)) { + /* Tell napi that we are done polling */ + napi_complete_done(napi, work_done); + + /* Force an interrupt */ + iavf_force_wb(vsi, q_vector); + + /* Return budget-1 so that polling stops */ + return budget - 1; + } +tx_only: + if (arm_wb) { + q_vector->tx.ring[0].tx_stats.tx_force_wb++; + iavf_enable_wb_on_itr(vsi, q_vector); + } + return budget; + } + + if (vsi->back->flags & IAVF_TXR_FLAGS_WB_ON_ITR) + q_vector->arm_wb_state = false; + + /* Work is done so exit the polling mode and re-enable the interrupt */ + napi_complete_done(napi, work_done); + + iavf_update_enable_itr(vsi, q_vector); + + return min(work_done, budget - 1); +} + +/** + * iavf_tx_prepare_vlan_flags - prepare generic TX VLAN tagging flags for HW + * @skb: send buffer + * @tx_ring: ring to send buffer on + * @flags: the tx flags to be set + * + * Checks the skb and set up correspondingly several generic transmit flags + * related to VLAN tagging for the HW, such as VLAN, DCB, etc. + * + * Returns error code indicate the frame should be dropped upon error and the + * otherwise returns 0 to indicate the flags has been set properly. + **/ +static inline int iavf_tx_prepare_vlan_flags(struct sk_buff *skb, + struct iavf_ring *tx_ring, + u32 *flags) +{ + __be16 protocol = skb->protocol; + u32 tx_flags = 0; + + if (protocol == htons(ETH_P_8021Q) && + !(tx_ring->netdev->features & NETIF_F_HW_VLAN_CTAG_TX)) { + /* When HW VLAN acceleration is turned off by the user the + * stack sets the protocol to 8021q so that the driver + * can take any steps required to support the SW only + * VLAN handling. In our case the driver doesn't need + * to take any further steps so just set the protocol + * to the encapsulated ethertype. + */ + skb->protocol = vlan_get_protocol(skb); + goto out; + } + + /* if we have a HW VLAN tag being added, default to the HW one */ + if (skb_vlan_tag_present(skb)) { + tx_flags |= skb_vlan_tag_get(skb) << IAVF_TX_FLAGS_VLAN_SHIFT; + tx_flags |= IAVF_TX_FLAGS_HW_VLAN; + /* else if it is a SW VLAN, check the next protocol and store the tag */ + } else if (protocol == htons(ETH_P_8021Q)) { + struct vlan_hdr *vhdr, _vhdr; + + vhdr = skb_header_pointer(skb, ETH_HLEN, sizeof(_vhdr), &_vhdr); + if (!vhdr) + return -EINVAL; + + protocol = vhdr->h_vlan_encapsulated_proto; + tx_flags |= ntohs(vhdr->h_vlan_TCI) << IAVF_TX_FLAGS_VLAN_SHIFT; + tx_flags |= IAVF_TX_FLAGS_SW_VLAN; + } + +out: + *flags = tx_flags; + return 0; +} + +/** + * iavf_tso - set up the tso context descriptor + * @first: pointer to first Tx buffer for xmit + * @hdr_len: ptr to the size of the packet header + * @cd_type_cmd_tso_mss: Quad Word 1 + * + * Returns 0 if no TSO can happen, 1 if tso is going, or error + **/ +static int iavf_tso(struct iavf_tx_buffer *first, u8 *hdr_len, + u64 *cd_type_cmd_tso_mss) +{ + struct sk_buff *skb = first->skb; + 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; + u16 gso_segs, gso_size; + 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_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_GRE | + SKB_GSO_GRE_CSUM | + SKB_GSO_IPXIP4 | + SKB_GSO_IPXIP6 | + SKB_GSO_UDP_TUNNEL | + SKB_GSO_UDP_TUNNEL_CSUM)) { + if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) && + (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM)) { + l4.udp->len = 0; + + /* determine offset of outer transport header */ + l4_offset = l4.hdr - skb->data; + + /* remove payload length from outer checksum */ + paylen = skb->len - l4_offset; + csum_replace_by_diff(&l4.udp->check, + (__force __wsum)htonl(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; + } + } + + /* determine offset of inner transport header */ + l4_offset = l4.hdr - skb->data; + + /* remove payload length from inner checksum */ + paylen = skb->len - l4_offset; + csum_replace_by_diff(&l4.tcp->check, (__force __wsum)htonl(paylen)); + + /* compute length of segmentation header */ + *hdr_len = (l4.tcp->doff * 4) + l4_offset; + + /* pull values out of skb_shinfo */ + gso_size = skb_shinfo(skb)->gso_size; + gso_segs = skb_shinfo(skb)->gso_segs; + + /* update GSO size and bytecount with header size */ + first->gso_segs = gso_segs; + first->bytecount += (first->gso_segs - 1) * *hdr_len; + + /* find the field values */ + cd_cmd = IAVF_TX_CTX_DESC_TSO; + cd_tso_len = skb->len - *hdr_len; + cd_mss = gso_size; + *cd_type_cmd_tso_mss |= (cd_cmd << IAVF_TXD_CTX_QW1_CMD_SHIFT) | + (cd_tso_len << IAVF_TXD_CTX_QW1_TSO_LEN_SHIFT) | + (cd_mss << IAVF_TXD_CTX_QW1_MSS_SHIFT); + return 1; +} + +/** + * iavf_tx_enable_csum - Enable Tx checksum offloads + * @skb: send buffer + * @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 int iavf_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, + u32 *td_cmd, u32 *td_offset, + struct iavf_ring *tx_ring, + u32 *cd_tunneling) +{ + 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; + __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) << IAVF_TX_DESC_LENGTH_MACLEN_SHIFT; + + if (skb->encapsulation) { + u32 tunnel = 0; + /* define outer network header type */ + if (*tx_flags & IAVF_TX_FLAGS_IPV4) { + tunnel |= (*tx_flags & IAVF_TX_FLAGS_TSO) ? + IAVF_TX_CTX_EXT_IP_IPV4 : + IAVF_TX_CTX_EXT_IP_IPV4_NO_CSUM; + + l4_proto = ip.v4->protocol; + } else if (*tx_flags & IAVF_TX_FLAGS_IPV6) { + tunnel |= IAVF_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); + } + + /* define outer transport */ + switch (l4_proto) { + case IPPROTO_UDP: + tunnel |= IAVF_TXD_CTX_UDP_TUNNELING; + *tx_flags |= IAVF_TX_FLAGS_VXLAN_TUNNEL; + break; + case IPPROTO_GRE: + tunnel |= IAVF_TXD_CTX_GRE_TUNNELING; + *tx_flags |= IAVF_TX_FLAGS_VXLAN_TUNNEL; + break; + case IPPROTO_IPIP: + case IPPROTO_IPV6: + *tx_flags |= IAVF_TX_FLAGS_VXLAN_TUNNEL; + l4.hdr = skb_inner_network_header(skb); + break; + default: + if (*tx_flags & IAVF_TX_FLAGS_TSO) + return -1; + + skb_checksum_help(skb); + return 0; + } + + /* compute outer L3 header size */ + tunnel |= ((l4.hdr - ip.hdr) / 4) << + IAVF_TXD_CTX_QW0_EXT_IPLEN_SHIFT; + + /* switch IP header pointer from outer to inner header */ + ip.hdr = skb_inner_network_header(skb); + + /* compute tunnel header size */ + tunnel |= ((ip.hdr - l4.hdr) / 2) << + IAVF_TXD_CTX_QW0_NATLEN_SHIFT; + + /* indicate if we need to offload outer UDP header */ + if ((*tx_flags & IAVF_TX_FLAGS_TSO) && + !(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) && + (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM)) + tunnel |= IAVF_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 &= ~(IAVF_TX_FLAGS_IPV4 | IAVF_TX_FLAGS_IPV6); + if (ip.v4->version == 4) + *tx_flags |= IAVF_TX_FLAGS_IPV4; + if (ip.v6->version == 6) + *tx_flags |= IAVF_TX_FLAGS_IPV6; + } + + /* Enable IP checksum offloads */ + if (*tx_flags & IAVF_TX_FLAGS_IPV4) { + 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. + */ + cmd |= (*tx_flags & IAVF_TX_FLAGS_TSO) ? + IAVF_TX_DESC_CMD_IIPT_IPV4_CSUM : + IAVF_TX_DESC_CMD_IIPT_IPV4; + } else if (*tx_flags & IAVF_TX_FLAGS_IPV6) { + cmd |= IAVF_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); + } + + /* compute inner L3 header size */ + offset |= ((l4.hdr - ip.hdr) / 4) << IAVF_TX_DESC_LENGTH_IPLEN_SHIFT; + + /* Enable L4 checksum offloads */ + switch (l4_proto) { + case IPPROTO_TCP: + /* enable checksum offloads */ + cmd |= IAVF_TX_DESC_CMD_L4T_EOFT_TCP; + offset |= l4.tcp->doff << IAVF_TX_DESC_LENGTH_L4_FC_LEN_SHIFT; + break; + case IPPROTO_SCTP: + /* enable SCTP checksum offload */ + cmd |= IAVF_TX_DESC_CMD_L4T_EOFT_SCTP; + offset |= (sizeof(struct sctphdr) >> 2) << + IAVF_TX_DESC_LENGTH_L4_FC_LEN_SHIFT; + break; + case IPPROTO_UDP: + /* enable UDP checksum offload */ + cmd |= IAVF_TX_DESC_CMD_L4T_EOFT_UDP; + offset |= (sizeof(struct udphdr) >> 2) << + IAVF_TX_DESC_LENGTH_L4_FC_LEN_SHIFT; + break; + default: + if (*tx_flags & IAVF_TX_FLAGS_TSO) + return -1; + skb_checksum_help(skb); + return 0; + } + + *td_cmd |= cmd; + *td_offset |= offset; + + return 1; +} + +/** + * iavf_create_tx_ctx Build the Tx context descriptor + * @tx_ring: ring to create the descriptor on + * @cd_type_cmd_tso_mss: Quad Word 1 + * @cd_tunneling: Quad Word 0 - bits 0-31 + * @cd_l2tag2: Quad Word 0 - bits 32-63 + **/ +static void iavf_create_tx_ctx(struct iavf_ring *tx_ring, + const u64 cd_type_cmd_tso_mss, + const u32 cd_tunneling, const u32 cd_l2tag2) +{ + struct iavf_tx_context_desc *context_desc; + int i = tx_ring->next_to_use; + + if ((cd_type_cmd_tso_mss == IAVF_TX_DESC_DTYPE_CONTEXT) && + !cd_tunneling && !cd_l2tag2) + return; + + /* grab the next descriptor */ + context_desc = IAVF_TX_CTXTDESC(tx_ring, i); + + i++; + tx_ring->next_to_use = (i < tx_ring->count) ? i : 0; + + /* cpu_to_le32 and assign to struct fields */ + context_desc->tunneling_params = cpu_to_le32(cd_tunneling); + context_desc->l2tag2 = cpu_to_le16(cd_l2tag2); + context_desc->rsvd = cpu_to_le16(0); + context_desc->type_cmd_tso_mss = cpu_to_le64(cd_type_cmd_tso_mss); +} + +/** + * __iavf_chk_linearize - Check if there are more than 8 buffers per packet + * @skb: send buffer + * + * 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. + **/ +bool __iavf_chk_linearize(struct sk_buff *skb) +{ + const struct skb_frag_struct *frag, *stale; + int nr_frags, sum; + + /* no need to check if number of frags is less than 7 */ + nr_frags = skb_shinfo(skb)->nr_frags; + if (nr_frags < (IAVF_MAX_BUFFER_TXD - 1)) + return false; + + /* We need to walk through the list and validate that each group + * of 6 fragments totals at least gso_size. + */ + nr_frags -= IAVF_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; + + /* 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. + */ + for (stale = &skb_shinfo(skb)->frags[0];; stale++) { + int stale_size = skb_frag_size(stale); + + sum += skb_frag_size(frag++); + + /* The stale fragment may present us with a smaller + * descriptor than the actual fragment size. To account + * for that we need to remove all the data on the front and + * figure out what the remainder would be in the last + * descriptor associated with the fragment. + */ + if (stale_size > IAVF_MAX_DATA_PER_TXD) { + int align_pad = -(stale->page_offset) & + (IAVF_MAX_READ_REQ_SIZE - 1); + + sum -= align_pad; + stale_size -= align_pad; + + do { + sum -= IAVF_MAX_DATA_PER_TXD_ALIGNED; + stale_size -= IAVF_MAX_DATA_PER_TXD_ALIGNED; + } while (stale_size > IAVF_MAX_DATA_PER_TXD); + } + + /* if sum is negative we failed to make sufficient progress */ + if (sum < 0) + return true; + + if (!nr_frags--) + break; + + sum -= stale_size; + } + + return false; +} + +/** + * __iavf_maybe_stop_tx - 2nd level check for tx stop conditions + * @tx_ring: the ring to be checked + * @size: the size buffer we want to assure is available + * + * Returns -EBUSY if a stop is needed, else 0 + **/ +int __iavf_maybe_stop_tx(struct iavf_ring *tx_ring, int size) +{ + netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index); + /* Memory barrier before checking head and tail */ + smp_mb(); + + /* Check again in a case another CPU has just made room available. */ + if (likely(IAVF_DESC_UNUSED(tx_ring) < size)) + return -EBUSY; + + /* A reprieve! - use start_queue because it doesn't call schedule */ + netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index); + ++tx_ring->tx_stats.restart_queue; + return 0; +} + +/** + * iavf_tx_map - Build the Tx descriptor + * @tx_ring: ring to send buffer on + * @skb: send buffer + * @first: first buffer info buffer to use + * @tx_flags: collected send information + * @hdr_len: size of the packet header + * @td_cmd: the command field in the descriptor + * @td_offset: offset for checksum or crc + **/ +static inline void iavf_tx_map(struct iavf_ring *tx_ring, struct sk_buff *skb, + struct iavf_tx_buffer *first, u32 tx_flags, + const u8 hdr_len, u32 td_cmd, u32 td_offset) +{ + unsigned int data_len = skb->data_len; + unsigned int size = skb_headlen(skb); + struct skb_frag_struct *frag; + struct iavf_tx_buffer *tx_bi; + struct iavf_tx_desc *tx_desc; + u16 i = tx_ring->next_to_use; + u32 td_tag = 0; + dma_addr_t dma; + + if (tx_flags & IAVF_TX_FLAGS_HW_VLAN) { + td_cmd |= IAVF_TX_DESC_CMD_IL2TAG1; + td_tag = (tx_flags & IAVF_TX_FLAGS_VLAN_MASK) >> + IAVF_TX_FLAGS_VLAN_SHIFT; + } + + first->tx_flags = tx_flags; + + dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE); + + tx_desc = IAVF_TX_DESC(tx_ring, i); + tx_bi = first; + + for (frag = &skb_shinfo(skb)->frags[0];; frag++) { + unsigned int max_data = IAVF_MAX_DATA_PER_TXD_ALIGNED; + + if (dma_mapping_error(tx_ring->dev, dma)) + goto dma_error; + + /* record length, and DMA address */ + dma_unmap_len_set(tx_bi, len, size); + dma_unmap_addr_set(tx_bi, dma, dma); + + /* align size to end of page */ + max_data += -dma & (IAVF_MAX_READ_REQ_SIZE - 1); + tx_desc->buffer_addr = cpu_to_le64(dma); + + while (unlikely(size > IAVF_MAX_DATA_PER_TXD)) { + tx_desc->cmd_type_offset_bsz = + build_ctob(td_cmd, td_offset, + max_data, td_tag); + + tx_desc++; + i++; + + if (i == tx_ring->count) { + tx_desc = IAVF_TX_DESC(tx_ring, 0); + i = 0; + } + + dma += max_data; + size -= max_data; + + max_data = IAVF_MAX_DATA_PER_TXD_ALIGNED; + tx_desc->buffer_addr = cpu_to_le64(dma); + } + + if (likely(!data_len)) + break; + + tx_desc->cmd_type_offset_bsz = build_ctob(td_cmd, td_offset, + size, td_tag); + + tx_desc++; + i++; + + if (i == tx_ring->count) { + tx_desc = IAVF_TX_DESC(tx_ring, 0); + i = 0; + } + + size = skb_frag_size(frag); + data_len -= size; + + dma = skb_frag_dma_map(tx_ring->dev, frag, 0, size, + DMA_TO_DEVICE); + + tx_bi = &tx_ring->tx_bi[i]; + } + + netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount); + + i++; + if (i == tx_ring->count) + i = 0; + + tx_ring->next_to_use = i; + + iavf_maybe_stop_tx(tx_ring, DESC_NEEDED); + + /* write last descriptor with RS and EOP bits */ + td_cmd |= IAVF_TXD_CMD; + tx_desc->cmd_type_offset_bsz = + build_ctob(td_cmd, td_offset, size, td_tag); + + /* Force memory writes to complete before letting h/w know there + * are new descriptors to fetch. + * + * We also use this memory barrier to make certain all of the + * status bits have been updated before next_to_watch is written. + */ + wmb(); + + /* set next_to_watch value indicating a packet is present */ + first->next_to_watch = tx_desc; + + /* notify HW of packet */ + if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { + writel(i, tx_ring->tail); + + /* we need this if more than one processor can write to our tail + * at a time, it synchronizes IO on IA64/Altix systems + */ + mmiowb(); + } + + return; + +dma_error: + dev_info(tx_ring->dev, "TX DMA map failed\n"); + + /* clear dma mappings for failed tx_bi map */ + for (;;) { + tx_bi = &tx_ring->tx_bi[i]; + iavf_unmap_and_free_tx_resource(tx_ring, tx_bi); + if (tx_bi == first) + break; + if (i == 0) + i = tx_ring->count; + i--; + } + + tx_ring->next_to_use = i; +} + +/** + * iavf_xmit_frame_ring - Sends buffer on Tx ring + * @skb: send buffer + * @tx_ring: ring to send buffer on + * + * Returns NETDEV_TX_OK if sent, else an error code + **/ +static netdev_tx_t iavf_xmit_frame_ring(struct sk_buff *skb, + struct iavf_ring *tx_ring) +{ + u64 cd_type_cmd_tso_mss = IAVF_TX_DESC_DTYPE_CONTEXT; + u32 cd_tunneling = 0, cd_l2tag2 = 0; + struct iavf_tx_buffer *first; + u32 td_offset = 0; + u32 tx_flags = 0; + __be16 protocol; + u32 td_cmd = 0; + u8 hdr_len = 0; + int tso, count; + + /* prefetch the data, we'll need it later */ + prefetch(skb->data); + + iavf_trace(xmit_frame_ring, skb, tx_ring); + + count = iavf_xmit_descriptor_count(skb); + if (iavf_chk_linearize(skb, count)) { + if (__skb_linearize(skb)) { + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } + count = iavf_txd_use_count(skb->len); + tx_ring->tx_stats.tx_linearize++; + } + + /* need: 1 descriptor per page * PAGE_SIZE/IAVF_MAX_DATA_PER_TXD, + * + 1 desc for skb_head_len/IAVF_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 (iavf_maybe_stop_tx(tx_ring, count + 4 + 1)) { + tx_ring->tx_stats.tx_busy++; + return NETDEV_TX_BUSY; + } + + /* record the location of the first descriptor for this packet */ + first = &tx_ring->tx_bi[tx_ring->next_to_use]; + first->skb = skb; + first->bytecount = skb->len; + first->gso_segs = 1; + + /* prepare the xmit flags */ + if (iavf_tx_prepare_vlan_flags(skb, tx_ring, &tx_flags)) + goto out_drop; + + /* obtain protocol of skb */ + protocol = vlan_get_protocol(skb); + + /* setup IPv4/IPv6 offloads */ + if (protocol == htons(ETH_P_IP)) + tx_flags |= IAVF_TX_FLAGS_IPV4; + else if (protocol == htons(ETH_P_IPV6)) + tx_flags |= IAVF_TX_FLAGS_IPV6; + + tso = iavf_tso(first, &hdr_len, &cd_type_cmd_tso_mss); + + if (tso < 0) + goto out_drop; + else if (tso) + tx_flags |= IAVF_TX_FLAGS_TSO; + + /* Always offload the checksum, since it's in the data descriptor */ + tso = iavf_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 |= IAVF_TX_DESC_CMD_ICRC; + + iavf_create_tx_ctx(tx_ring, cd_type_cmd_tso_mss, + cd_tunneling, cd_l2tag2); + + iavf_tx_map(tx_ring, skb, first, tx_flags, hdr_len, + td_cmd, td_offset); + + return NETDEV_TX_OK; + +out_drop: + iavf_trace(xmit_frame_ring_drop, first->skb, tx_ring); + dev_kfree_skb_any(first->skb); + first->skb = NULL; + return NETDEV_TX_OK; +} + +/** + * iavf_xmit_frame - Selects the correct VSI and Tx queue to send buffer + * @skb: send buffer + * @netdev: network interface device structure + * + * Returns NETDEV_TX_OK if sent, else an error code + **/ +netdev_tx_t iavf_xmit_frame(struct sk_buff *skb, struct net_device *netdev) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_ring *tx_ring = &adapter->tx_rings[skb->queue_mapping]; + + /* hardware can't handle really short frames, hardware padding works + * beyond this point + */ + if (unlikely(skb->len < IAVF_MIN_TX_LEN)) { + if (skb_pad(skb, IAVF_MIN_TX_LEN - skb->len)) + return NETDEV_TX_OK; + skb->len = IAVF_MIN_TX_LEN; + skb_set_tail_pointer(skb, IAVF_MIN_TX_LEN); + } + + return iavf_xmit_frame_ring(skb, tx_ring); +} diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h new file mode 100644 index 000000000000..71e7d090f8db --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h @@ -0,0 +1,523 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _IAVF_TXRX_H_ +#define _IAVF_TXRX_H_ + +/* Interrupt Throttling and Rate Limiting Goodies */ +#define IAVF_DEFAULT_IRQ_WORK 256 + +/* The datasheet for the X710 and XL710 indicate that the maximum value for + * the ITR is 8160usec which is then called out as 0xFF0 with a 2usec + * resolution. 8160 is 0x1FE0 when written out in hex. So instead of storing + * the register value which is divided by 2 lets use the actual values and + * avoid an excessive amount of translation. + */ +#define IAVF_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ +#define IAVF_ITR_MASK 0x1FFE /* mask for ITR register value */ +#define IAVF_MIN_ITR 2 /* reg uses 2 usec resolution */ +#define IAVF_ITR_100K 10 /* all values below must be even */ +#define IAVF_ITR_50K 20 +#define IAVF_ITR_20K 50 +#define IAVF_ITR_18K 60 +#define IAVF_ITR_8K 122 +#define IAVF_MAX_ITR 8160 /* maximum value as per datasheet */ +#define ITR_TO_REG(setting) ((setting) & ~IAVF_ITR_DYNAMIC) +#define ITR_REG_ALIGN(setting) __ALIGN_MASK(setting, ~IAVF_ITR_MASK) +#define ITR_IS_DYNAMIC(setting) (!!((setting) & IAVF_ITR_DYNAMIC)) + +#define IAVF_ITR_RX_DEF (IAVF_ITR_20K | IAVF_ITR_DYNAMIC) +#define IAVF_ITR_TX_DEF (IAVF_ITR_20K | IAVF_ITR_DYNAMIC) + +/* 0x40 is the enable bit for interrupt rate limiting, and must be set if + * the value of the rate limit is non-zero + */ +#define INTRL_ENA BIT(6) +#define IAVF_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ +#define INTRL_REG_TO_USEC(intrl) ((intrl & ~INTRL_ENA) << 2) +#define INTRL_USEC_TO_REG(set) ((set) ? ((set) >> 2) | INTRL_ENA : 0) +#define IAVF_INTRL_8K 125 /* 8000 ints/sec */ +#define IAVF_INTRL_62K 16 /* 62500 ints/sec */ +#define IAVF_INTRL_83K 12 /* 83333 ints/sec */ + +#define IAVF_QUEUE_END_OF_LIST 0x7FF + +/* this enum matches hardware bits and is meant to be used by DYN_CTLN + * registers and QINT registers or more generally anywhere in the manual + * mentioning ITR_INDX, ITR_NONE cannot be used as an index 'n' into any + * register but instead is a special value meaning "don't update" ITR0/1/2. + */ +enum iavf_dyn_idx_t { + IAVF_IDX_ITR0 = 0, + IAVF_IDX_ITR1 = 1, + IAVF_IDX_ITR2 = 2, + IAVF_ITR_NONE = 3 /* ITR_NONE must not be used as an index */ +}; + +/* these are indexes into ITRN registers */ +#define IAVF_RX_ITR IAVF_IDX_ITR0 +#define IAVF_TX_ITR IAVF_IDX_ITR1 +#define IAVF_PE_ITR IAVF_IDX_ITR2 + +/* Supported RSS offloads */ +#define IAVF_DEFAULT_RSS_HENA ( \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_UDP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_SCTP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_TCP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_OTHER) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_FRAG_IPV4) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_UDP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_TCP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_SCTP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_OTHER) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_FRAG_IPV6) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_L2_PAYLOAD)) + +#define IAVF_DEFAULT_RSS_HENA_EXPANDED (IAVF_DEFAULT_RSS_HENA | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP)) + +/* Supported Rx Buffer Sizes (a multiple of 128) */ +#define IAVF_RXBUFFER_256 256 +#define IAVF_RXBUFFER_1536 1536 /* 128B aligned standard Ethernet frame */ +#define IAVF_RXBUFFER_2048 2048 +#define IAVF_RXBUFFER_3072 3072 /* Used for large frames w/ padding */ +#define IAVF_MAX_RXBUFFER 9728 /* largest size for single descriptor */ + +/* NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we + * reserve 2 more, and skb_shared_info adds an additional 384 bytes more, + * this adds up to 512 bytes of extra data meaning the smallest allocation + * we could have is 1K. + * i.e. RXBUFFER_256 --> 960 byte skb (size-1024 slab) + * i.e. RXBUFFER_512 --> 1216 byte skb (size-2048 slab) + */ +#define IAVF_RX_HDR_SIZE IAVF_RXBUFFER_256 +#define IAVF_PACKET_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2)) +#define iavf_rx_desc iavf_32byte_rx_desc + +#define IAVF_RX_DMA_ATTR \ + (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) + +/* 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 legacy + * receive path. + */ +#if (PAGE_SIZE < 8192) +#define IAVF_2K_TOO_SMALL_WITH_PADDING \ +((NET_SKB_PAD + IAVF_RXBUFFER_1536) > SKB_WITH_OVERHEAD(IAVF_RXBUFFER_2048)) + +static inline int iavf_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 iavf_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 (IAVF_2K_TOO_SMALL_WITH_PADDING) + rx_buf_len = IAVF_RXBUFFER_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN); + else + rx_buf_len = IAVF_RXBUFFER_1536; + + /* if needed make room for NET_IP_ALIGN */ + rx_buf_len -= NET_IP_ALIGN; + + return iavf_compute_pad(rx_buf_len); +} + +#define IAVF_SKB_PAD iavf_skb_pad() +#else +#define IAVF_2K_TOO_SMALL_WITH_PADDING false +#define IAVF_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) +#endif + +/** + * iavf_test_staterr - tests bits in Rx descriptor status and error fields + * @rx_desc: pointer to receive descriptor (in le64 format) + * @stat_err_bits: value to mask + * + * This function does some fast chicanery in order to return the + * value of the mask which is really only used for boolean tests. + * The status_error_len doesn't need to be shifted because it begins + * at offset zero. + */ +static inline bool iavf_test_staterr(union iavf_rx_desc *rx_desc, + const u64 stat_err_bits) +{ + return !!(rx_desc->wb.qword1.status_error_len & + cpu_to_le64(stat_err_bits)); +} + +/* How many Rx Buffers do we bundle into one write to the hardware ? */ +#define IAVF_RX_INCREMENT(r, i) \ + do { \ + (i)++; \ + if ((i) == (r)->count) \ + i = 0; \ + r->next_to_clean = i; \ + } while (0) + +#define IAVF_RX_NEXT_DESC(r, i, n) \ + do { \ + (i)++; \ + if ((i) == (r)->count) \ + i = 0; \ + (n) = IAVF_RX_DESC((r), (i)); \ + } while (0) + +#define IAVF_RX_NEXT_DESC_PREFETCH(r, i, n) \ + do { \ + IAVF_RX_NEXT_DESC((r), (i), (n)); \ + prefetch((n)); \ + } while (0) + +#define IAVF_MAX_BUFFER_TXD 8 +#define IAVF_MIN_TX_LEN 17 + +/* The size limit for a transmit buffer in a descriptor is (16K - 1). + * In order to align with the read requests we will align the value to + * the nearest 4K which represents our maximum read request size. + */ +#define IAVF_MAX_READ_REQ_SIZE 4096 +#define IAVF_MAX_DATA_PER_TXD (16 * 1024 - 1) +#define IAVF_MAX_DATA_PER_TXD_ALIGNED \ + (IAVF_MAX_DATA_PER_TXD & ~(IAVF_MAX_READ_REQ_SIZE - 1)) + +/** + * iavf_txd_use_count - estimate the number of descriptors needed for Tx + * @size: transmit request size in bytes + * + * Due to hardware alignment restrictions (4K alignment), we need to + * assume that we can have no more than 12K of data per descriptor, even + * though each descriptor can take up to 16K - 1 bytes of aligned memory. + * Thus, we need to divide by 12K. But division is slow! Instead, + * we decompose the operation into shifts and one relatively cheap + * multiply operation. + * + * To divide by 12K, we first divide by 4K, then divide by 3: + * To divide by 4K, shift right by 12 bits + * To divide by 3, multiply by 85, then divide by 256 + * (Divide by 256 is done by shifting right by 8 bits) + * Finally, we add one to round up. Because 256 isn't an exact multiple of + * 3, we'll underestimate near each multiple of 12K. This is actually more + * accurate as we have 4K - 1 of wiggle room that we can fit into the last + * segment. For our purposes this is accurate out to 1M which is orders of + * magnitude greater than our largest possible GSO size. + * + * This would then be implemented as: + * return (((size >> 12) * 85) >> 8) + 1; + * + * Since multiplication and division are commutative, we can reorder + * operations into: + * return ((size * 85) >> 20) + 1; + */ +static inline unsigned int iavf_txd_use_count(unsigned int size) +{ + return ((size * 85) >> 20) + 1; +} + +/* Tx Descriptors needed, worst case */ +#define DESC_NEEDED (MAX_SKB_FRAGS + 6) +#define IAVF_MIN_DESC_PENDING 4 + +#define IAVF_TX_FLAGS_HW_VLAN BIT(1) +#define IAVF_TX_FLAGS_SW_VLAN BIT(2) +#define IAVF_TX_FLAGS_TSO BIT(3) +#define IAVF_TX_FLAGS_IPV4 BIT(4) +#define IAVF_TX_FLAGS_IPV6 BIT(5) +#define IAVF_TX_FLAGS_FCCRC BIT(6) +#define IAVF_TX_FLAGS_FSO BIT(7) +#define IAVF_TX_FLAGS_FD_SB BIT(9) +#define IAVF_TX_FLAGS_VXLAN_TUNNEL BIT(10) +#define IAVF_TX_FLAGS_VLAN_MASK 0xffff0000 +#define IAVF_TX_FLAGS_VLAN_PRIO_MASK 0xe0000000 +#define IAVF_TX_FLAGS_VLAN_PRIO_SHIFT 29 +#define IAVF_TX_FLAGS_VLAN_SHIFT 16 + +struct iavf_tx_buffer { + struct iavf_tx_desc *next_to_watch; + union { + struct sk_buff *skb; + void *raw_buf; + }; + unsigned int bytecount; + unsigned short gso_segs; + + DEFINE_DMA_UNMAP_ADDR(dma); + DEFINE_DMA_UNMAP_LEN(len); + u32 tx_flags; +}; + +struct iavf_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 iavf_queue_stats { + u64 packets; + u64 bytes; +}; + +struct iavf_tx_queue_stats { + u64 restart_queue; + u64 tx_busy; + u64 tx_done_old; + u64 tx_linearize; + u64 tx_force_wb; + int prev_pkt_ctr; + u64 tx_lost_interrupt; +}; + +struct iavf_rx_queue_stats { + u64 non_eop_descs; + u64 alloc_page_failed; + u64 alloc_buff_failed; + u64 page_reuse_count; + u64 realloc_count; +}; + +enum iavf_ring_state_t { + __IAVF_TX_FDIR_INIT_DONE, + __IAVF_TX_XPS_INIT_DONE, + __IAVF_RING_STATE_NBITS /* must be last */ +}; + +/* some useful defines for virtchannel interface, which + * is the only remaining user of header split + */ +#define IAVF_RX_DTYPE_NO_SPLIT 0 +#define IAVF_RX_DTYPE_HEADER_SPLIT 1 +#define IAVF_RX_DTYPE_SPLIT_ALWAYS 2 +#define IAVF_RX_SPLIT_L2 0x1 +#define IAVF_RX_SPLIT_IP 0x2 +#define IAVF_RX_SPLIT_TCP_UDP 0x4 +#define IAVF_RX_SPLIT_SCTP 0x8 + +/* struct that defines a descriptor ring, associated with a VSI */ +struct iavf_ring { + struct iavf_ring *next; /* pointer to next ring in q_vector */ + void *desc; /* Descriptor ring memory */ + struct device *dev; /* Used for DMA mapping */ + struct net_device *netdev; /* netdev ring maps to */ + union { + struct iavf_tx_buffer *tx_bi; + struct iavf_rx_buffer *rx_bi; + }; + DECLARE_BITMAP(state, __IAVF_RING_STATE_NBITS); + u16 queue_index; /* Queue number of ring */ + u8 dcb_tc; /* Traffic class of ring */ + u8 __iomem *tail; + + /* high bit set means dynamic, use accessors routines to read/write. + * hardware only supports 2us resolution for the ITR registers. + * these values always store the USER setting, and must be converted + * before programming to a register. + */ + u16 itr_setting; + + u16 count; /* Number of descriptors */ + u16 reg_idx; /* HW register index of the ring */ + u16 rx_buf_len; + + /* used in interrupt processing */ + u16 next_to_use; + u16 next_to_clean; + + u8 atr_sample_rate; + u8 atr_count; + + bool ring_active; /* is ring online or not */ + bool arm_wb; /* do something to arm write back */ + u8 packet_stride; + + u16 flags; +#define IAVF_TXR_FLAGS_WB_ON_ITR BIT(0) +#define IAVF_RXR_FLAGS_BUILD_SKB_ENABLED BIT(1) + + /* stats structs */ + struct iavf_queue_stats stats; + struct u64_stats_sync syncp; + union { + struct iavf_tx_queue_stats tx_stats; + struct iavf_rx_queue_stats rx_stats; + }; + + unsigned int size; /* length of descriptor ring in bytes */ + dma_addr_t dma; /* physical address of ring */ + + struct iavf_vsi *vsi; /* Backreference to associated VSI */ + struct iavf_q_vector *q_vector; /* Backreference to associated vector */ + + struct rcu_head rcu; /* to avoid race on free */ + u16 next_to_alloc; + struct sk_buff *skb; /* When iavf_clean_rx_ring_irq() must + * return before it sees the EOP for + * the current packet, we save that skb + * here and resume receiving this + * packet the next time + * iavf_clean_rx_ring_irq() is called + * for this ring. + */ +} ____cacheline_internodealigned_in_smp; + +static inline bool ring_uses_build_skb(struct iavf_ring *ring) +{ + return !!(ring->flags & IAVF_RXR_FLAGS_BUILD_SKB_ENABLED); +} + +static inline void set_ring_build_skb_enabled(struct iavf_ring *ring) +{ + ring->flags |= IAVF_RXR_FLAGS_BUILD_SKB_ENABLED; +} + +static inline void clear_ring_build_skb_enabled(struct iavf_ring *ring) +{ + ring->flags &= ~IAVF_RXR_FLAGS_BUILD_SKB_ENABLED; +} + +#define IAVF_ITR_ADAPTIVE_MIN_INC 0x0002 +#define IAVF_ITR_ADAPTIVE_MIN_USECS 0x0002 +#define IAVF_ITR_ADAPTIVE_MAX_USECS 0x007e +#define IAVF_ITR_ADAPTIVE_LATENCY 0x8000 +#define IAVF_ITR_ADAPTIVE_BULK 0x0000 +#define ITR_IS_BULK(x) (!((x) & IAVF_ITR_ADAPTIVE_LATENCY)) + +struct iavf_ring_container { + struct iavf_ring *ring; /* pointer to linked list of ring(s) */ + unsigned long next_update; /* jiffies value of next update */ + unsigned int total_bytes; /* total bytes processed this int */ + unsigned int total_packets; /* total packets processed this int */ + u16 count; + u16 target_itr; /* target ITR setting for ring(s) */ + u16 current_itr; /* current ITR setting for ring(s) */ +}; + +/* iterator for handling rings in ring container */ +#define iavf_for_each_ring(pos, head) \ + for (pos = (head).ring; pos != NULL; pos = pos->next) + +static inline unsigned int iavf_rx_pg_order(struct iavf_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring->rx_buf_len > (PAGE_SIZE / 2)) + return 1; +#endif + return 0; +} + +#define iavf_rx_pg_size(_ring) (PAGE_SIZE << iavf_rx_pg_order(_ring)) + +bool iavf_alloc_rx_buffers(struct iavf_ring *rxr, u16 cleaned_count); +netdev_tx_t iavf_xmit_frame(struct sk_buff *skb, struct net_device *netdev); +void iavf_clean_tx_ring(struct iavf_ring *tx_ring); +void iavf_clean_rx_ring(struct iavf_ring *rx_ring); +int iavf_setup_tx_descriptors(struct iavf_ring *tx_ring); +int iavf_setup_rx_descriptors(struct iavf_ring *rx_ring); +void iavf_free_tx_resources(struct iavf_ring *tx_ring); +void iavf_free_rx_resources(struct iavf_ring *rx_ring); +int iavf_napi_poll(struct napi_struct *napi, int budget); +void iavf_force_wb(struct iavf_vsi *vsi, struct iavf_q_vector *q_vector); +u32 iavf_get_tx_pending(struct iavf_ring *ring, bool in_sw); +void iavf_detect_recover_hung(struct iavf_vsi *vsi); +int __iavf_maybe_stop_tx(struct iavf_ring *tx_ring, int size); +bool __iavf_chk_linearize(struct sk_buff *skb); + +/** + * iavf_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 iavf_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 += iavf_txd_use_count(size); + + if (!nr_frags--) + break; + + size = skb_frag_size(frag++); + } + + return count; +} + +/** + * iavf_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 iavf_maybe_stop_tx(struct iavf_ring *tx_ring, int size) +{ + if (likely(IAVF_DESC_UNUSED(tx_ring) >= size)) + return 0; + return __iavf_maybe_stop_tx(tx_ring, size); +} + +/** + * iavf_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 iavf_chk_linearize(struct sk_buff *skb, int count) +{ + /* Both TSO and single send will work if count is less than 8 */ + if (likely(count < IAVF_MAX_BUFFER_TXD)) + return false; + + if (skb_is_gso(skb)) + return __iavf_chk_linearize(skb); + + /* we can support up to 8 data buffers for a single send */ + return count != IAVF_MAX_BUFFER_TXD; +} +/** + * @ring: Tx ring to find the netdev equivalent of + **/ +static inline struct netdev_queue *txring_txq(const struct iavf_ring *ring) +{ + return netdev_get_tx_queue(ring->netdev, ring->queue_index); +} +#endif /* _IAVF_TXRX_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h new file mode 100644 index 000000000000..ca89583613fb --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_type.h @@ -0,0 +1,688 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _IAVF_TYPE_H_ +#define _IAVF_TYPE_H_ + +#include "iavf_status.h" +#include "iavf_osdep.h" +#include "iavf_register.h" +#include "i40e_adminq.h" +#include "iavf_devids.h" + +#define IAVF_RXQ_CTX_DBUFF_SHIFT 7 + +/* IAVF_MASK is a macro used on 32 bit registers */ +#define IAVF_MASK(mask, shift) ((u32)(mask) << (shift)) + +#define IAVF_MAX_VSI_QP 16 +#define IAVF_MAX_VF_VSI 3 +#define IAVF_MAX_CHAINED_RX_BUFFERS 5 + +/* forward declaration */ +struct iavf_hw; +typedef void (*I40E_ADMINQ_CALLBACK)(struct iavf_hw *, struct i40e_aq_desc *); + +/* Data type manipulation macros. */ + +#define IAVF_DESC_UNUSED(R) \ + ((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \ + (R)->next_to_clean - (R)->next_to_use - 1) + +/* bitfields for Tx queue mapping in QTX_CTL */ +#define IAVF_QTX_CTL_VF_QUEUE 0x0 +#define IAVF_QTX_CTL_VM_QUEUE 0x1 +#define IAVF_QTX_CTL_PF_QUEUE 0x2 + +/* debug masks - set these bits in hw->debug_mask to control output */ +enum iavf_debug_mask { + IAVF_DEBUG_INIT = 0x00000001, + IAVF_DEBUG_RELEASE = 0x00000002, + + IAVF_DEBUG_LINK = 0x00000010, + IAVF_DEBUG_PHY = 0x00000020, + IAVF_DEBUG_HMC = 0x00000040, + IAVF_DEBUG_NVM = 0x00000080, + IAVF_DEBUG_LAN = 0x00000100, + IAVF_DEBUG_FLOW = 0x00000200, + IAVF_DEBUG_DCB = 0x00000400, + IAVF_DEBUG_DIAG = 0x00000800, + IAVF_DEBUG_FD = 0x00001000, + IAVF_DEBUG_PACKAGE = 0x00002000, + + IAVF_DEBUG_AQ_MESSAGE = 0x01000000, + IAVF_DEBUG_AQ_DESCRIPTOR = 0x02000000, + IAVF_DEBUG_AQ_DESC_BUFFER = 0x04000000, + IAVF_DEBUG_AQ_COMMAND = 0x06000000, + IAVF_DEBUG_AQ = 0x0F000000, + + IAVF_DEBUG_USER = 0xF0000000, + + IAVF_DEBUG_ALL = 0xFFFFFFFF +}; + +/* These are structs for managing the hardware information and the operations. + * The structures of function pointers are filled out at init time when we + * know for sure exactly which hardware we're working with. This gives us the + * flexibility of using the same main driver code but adapting to slightly + * different hardware needs as new parts are developed. For this architecture, + * the Firmware and AdminQ are intended to insulate the driver from most of the + * future changes, but these structures will also do part of the job. + */ +enum iavf_mac_type { + IAVF_MAC_UNKNOWN = 0, + IAVF_MAC_XL710, + IAVF_MAC_VF, + IAVF_MAC_X722, + IAVF_MAC_X722_VF, + IAVF_MAC_GENERIC, +}; + +enum iavf_vsi_type { + IAVF_VSI_MAIN = 0, + IAVF_VSI_VMDQ1 = 1, + IAVF_VSI_VMDQ2 = 2, + IAVF_VSI_CTRL = 3, + IAVF_VSI_FCOE = 4, + IAVF_VSI_MIRROR = 5, + IAVF_VSI_SRIOV = 6, + IAVF_VSI_FDIR = 7, + IAVF_VSI_TYPE_UNKNOWN +}; + +enum iavf_queue_type { + IAVF_QUEUE_TYPE_RX = 0, + IAVF_QUEUE_TYPE_TX, + IAVF_QUEUE_TYPE_PE_CEQ, + IAVF_QUEUE_TYPE_UNKNOWN +}; + +#define IAVF_HW_CAP_MAX_GPIO 30 +/* Capabilities of a PF or a VF or the whole device */ +struct iavf_hw_capabilities { + bool dcb; + bool fcoe; + u32 num_vsis; + u32 num_rx_qp; + u32 num_tx_qp; + u32 base_queue; + u32 num_msix_vectors_vf; +}; + +struct iavf_mac_info { + enum iavf_mac_type type; + u8 addr[ETH_ALEN]; + u8 perm_addr[ETH_ALEN]; + u8 san_addr[ETH_ALEN]; + u16 max_fcoeq; +}; + +/* PCI bus types */ +enum iavf_bus_type { + iavf_bus_type_unknown = 0, + iavf_bus_type_pci, + iavf_bus_type_pcix, + iavf_bus_type_pci_express, + iavf_bus_type_reserved +}; + +/* PCI bus speeds */ +enum iavf_bus_speed { + iavf_bus_speed_unknown = 0, + iavf_bus_speed_33 = 33, + iavf_bus_speed_66 = 66, + iavf_bus_speed_100 = 100, + iavf_bus_speed_120 = 120, + iavf_bus_speed_133 = 133, + iavf_bus_speed_2500 = 2500, + iavf_bus_speed_5000 = 5000, + iavf_bus_speed_8000 = 8000, + iavf_bus_speed_reserved +}; + +/* PCI bus widths */ +enum iavf_bus_width { + iavf_bus_width_unknown = 0, + iavf_bus_width_pcie_x1 = 1, + iavf_bus_width_pcie_x2 = 2, + iavf_bus_width_pcie_x4 = 4, + iavf_bus_width_pcie_x8 = 8, + iavf_bus_width_32 = 32, + iavf_bus_width_64 = 64, + iavf_bus_width_reserved +}; + +/* Bus parameters */ +struct iavf_bus_info { + enum iavf_bus_speed speed; + enum iavf_bus_width width; + enum iavf_bus_type type; + + u16 func; + u16 device; + u16 lan_id; + u16 bus_id; +}; + +#define IAVF_MAX_USER_PRIORITY 8 +/* Port hardware description */ +struct iavf_hw { + u8 __iomem *hw_addr; + void *back; + + /* subsystem structs */ + struct iavf_mac_info mac; + struct iavf_bus_info bus; + + /* pci info */ + u16 device_id; + u16 vendor_id; + u16 subsystem_device_id; + u16 subsystem_vendor_id; + u8 revision_id; + + /* capabilities for entire device and PCI func */ + struct iavf_hw_capabilities dev_caps; + + /* Admin Queue info */ + struct iavf_adminq_info aq; + + /* debug mask */ + u32 debug_mask; + char err_str[16]; +}; + +struct iavf_driver_version { + u8 major_version; + u8 minor_version; + u8 build_version; + u8 subbuild_version; + u8 driver_string[32]; +}; + +/* RX Descriptors */ +union iavf_16byte_rx_desc { + struct { + __le64 pkt_addr; /* Packet buffer address */ + __le64 hdr_addr; /* Header buffer address */ + } read; + struct { + struct { + struct { + union { + __le16 mirroring_status; + __le16 fcoe_ctx_id; + } mirr_fcoe; + __le16 l2tag1; + } lo_dword; + union { + __le32 rss; /* RSS Hash */ + __le32 fd_id; /* Flow director filter id */ + __le32 fcoe_param; /* FCoE DDP Context id */ + } hi_dword; + } qword0; + struct { + /* ext status/error/pktype/length */ + __le64 status_error_len; + } qword1; + } wb; /* writeback */ +}; + +union iavf_32byte_rx_desc { + struct { + __le64 pkt_addr; /* Packet buffer address */ + __le64 hdr_addr; /* Header buffer address */ + /* bit 0 of hdr_buffer_addr is DD bit */ + __le64 rsvd1; + __le64 rsvd2; + } read; + struct { + struct { + struct { + union { + __le16 mirroring_status; + __le16 fcoe_ctx_id; + } mirr_fcoe; + __le16 l2tag1; + } lo_dword; + union { + __le32 rss; /* RSS Hash */ + __le32 fcoe_param; /* FCoE DDP Context id */ + /* Flow director filter id in case of + * Programming status desc WB + */ + __le32 fd_id; + } hi_dword; + } qword0; + struct { + /* status/error/pktype/length */ + __le64 status_error_len; + } qword1; + struct { + __le16 ext_status; /* extended status */ + __le16 rsvd; + __le16 l2tag2_1; + __le16 l2tag2_2; + } qword2; + struct { + union { + __le32 flex_bytes_lo; + __le32 pe_status; + } lo_dword; + union { + __le32 flex_bytes_hi; + __le32 fd_id; + } hi_dword; + } qword3; + } wb; /* writeback */ +}; + +enum iavf_rx_desc_status_bits { + /* Note: These are predefined bit offsets */ + IAVF_RX_DESC_STATUS_DD_SHIFT = 0, + IAVF_RX_DESC_STATUS_EOF_SHIFT = 1, + IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT = 2, + IAVF_RX_DESC_STATUS_L3L4P_SHIFT = 3, + IAVF_RX_DESC_STATUS_CRCP_SHIFT = 4, + IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT = 5, /* 2 BITS */ + IAVF_RX_DESC_STATUS_TSYNVALID_SHIFT = 7, + /* Note: Bit 8 is reserved in X710 and XL710 */ + IAVF_RX_DESC_STATUS_EXT_UDP_0_SHIFT = 8, + IAVF_RX_DESC_STATUS_UMBCAST_SHIFT = 9, /* 2 BITS */ + IAVF_RX_DESC_STATUS_FLM_SHIFT = 11, + IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT = 12, /* 2 BITS */ + IAVF_RX_DESC_STATUS_LPBK_SHIFT = 14, + IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT = 15, + IAVF_RX_DESC_STATUS_RESERVED_SHIFT = 16, /* 2 BITS */ + /* Note: For non-tunnel packets INT_UDP_0 is the right status for + * UDP header + */ + IAVF_RX_DESC_STATUS_INT_UDP_0_SHIFT = 18, + IAVF_RX_DESC_STATUS_LAST /* this entry must be last!!! */ +}; + +#define IAVF_RXD_QW1_STATUS_SHIFT 0 +#define IAVF_RXD_QW1_STATUS_MASK ((BIT(IAVF_RX_DESC_STATUS_LAST) - 1) \ + << IAVF_RXD_QW1_STATUS_SHIFT) + +#define IAVF_RXD_QW1_STATUS_TSYNINDX_SHIFT IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT +#define IAVF_RXD_QW1_STATUS_TSYNINDX_MASK (0x3UL << \ + IAVF_RXD_QW1_STATUS_TSYNINDX_SHIFT) + +#define IAVF_RXD_QW1_STATUS_TSYNVALID_SHIFT IAVF_RX_DESC_STATUS_TSYNVALID_SHIFT +#define IAVF_RXD_QW1_STATUS_TSYNVALID_MASK \ + BIT_ULL(IAVF_RXD_QW1_STATUS_TSYNVALID_SHIFT) + +enum iavf_rx_desc_fltstat_values { + IAVF_RX_DESC_FLTSTAT_NO_DATA = 0, + IAVF_RX_DESC_FLTSTAT_RSV_FD_ID = 1, /* 16byte desc? FD_ID : RSV */ + IAVF_RX_DESC_FLTSTAT_RSV = 2, + IAVF_RX_DESC_FLTSTAT_RSS_HASH = 3, +}; + +#define IAVF_RXD_QW1_ERROR_SHIFT 19 +#define IAVF_RXD_QW1_ERROR_MASK (0xFFUL << IAVF_RXD_QW1_ERROR_SHIFT) + +enum iavf_rx_desc_error_bits { + /* Note: These are predefined bit offsets */ + IAVF_RX_DESC_ERROR_RXE_SHIFT = 0, + IAVF_RX_DESC_ERROR_RECIPE_SHIFT = 1, + IAVF_RX_DESC_ERROR_HBO_SHIFT = 2, + IAVF_RX_DESC_ERROR_L3L4E_SHIFT = 3, /* 3 BITS */ + IAVF_RX_DESC_ERROR_IPE_SHIFT = 3, + IAVF_RX_DESC_ERROR_L4E_SHIFT = 4, + IAVF_RX_DESC_ERROR_EIPE_SHIFT = 5, + IAVF_RX_DESC_ERROR_OVERSIZE_SHIFT = 6, + IAVF_RX_DESC_ERROR_PPRS_SHIFT = 7 +}; + +enum iavf_rx_desc_error_l3l4e_fcoe_masks { + IAVF_RX_DESC_ERROR_L3L4E_NONE = 0, + IAVF_RX_DESC_ERROR_L3L4E_PROT = 1, + IAVF_RX_DESC_ERROR_L3L4E_FC = 2, + IAVF_RX_DESC_ERROR_L3L4E_DMAC_ERR = 3, + IAVF_RX_DESC_ERROR_L3L4E_DMAC_WARN = 4 +}; + +#define IAVF_RXD_QW1_PTYPE_SHIFT 30 +#define IAVF_RXD_QW1_PTYPE_MASK (0xFFULL << IAVF_RXD_QW1_PTYPE_SHIFT) + +/* Packet type non-ip values */ +enum iavf_rx_l2_ptype { + IAVF_RX_PTYPE_L2_RESERVED = 0, + IAVF_RX_PTYPE_L2_MAC_PAY2 = 1, + IAVF_RX_PTYPE_L2_TIMESYNC_PAY2 = 2, + IAVF_RX_PTYPE_L2_FIP_PAY2 = 3, + IAVF_RX_PTYPE_L2_OUI_PAY2 = 4, + IAVF_RX_PTYPE_L2_MACCNTRL_PAY2 = 5, + IAVF_RX_PTYPE_L2_LLDP_PAY2 = 6, + IAVF_RX_PTYPE_L2_ECP_PAY2 = 7, + IAVF_RX_PTYPE_L2_EVB_PAY2 = 8, + IAVF_RX_PTYPE_L2_QCN_PAY2 = 9, + IAVF_RX_PTYPE_L2_EAPOL_PAY2 = 10, + IAVF_RX_PTYPE_L2_ARP = 11, + IAVF_RX_PTYPE_L2_FCOE_PAY3 = 12, + IAVF_RX_PTYPE_L2_FCOE_FCDATA_PAY3 = 13, + IAVF_RX_PTYPE_L2_FCOE_FCRDY_PAY3 = 14, + IAVF_RX_PTYPE_L2_FCOE_FCRSP_PAY3 = 15, + IAVF_RX_PTYPE_L2_FCOE_FCOTHER_PA = 16, + IAVF_RX_PTYPE_L2_FCOE_VFT_PAY3 = 17, + IAVF_RX_PTYPE_L2_FCOE_VFT_FCDATA = 18, + IAVF_RX_PTYPE_L2_FCOE_VFT_FCRDY = 19, + IAVF_RX_PTYPE_L2_FCOE_VFT_FCRSP = 20, + IAVF_RX_PTYPE_L2_FCOE_VFT_FCOTHER = 21, + IAVF_RX_PTYPE_GRENAT4_MAC_PAY3 = 58, + IAVF_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4 = 87, + IAVF_RX_PTYPE_GRENAT6_MAC_PAY3 = 124, + IAVF_RX_PTYPE_GRENAT6_MACVLAN_IPV6_ICMP_PAY4 = 153 +}; + +struct iavf_rx_ptype_decoded { + u32 ptype:8; + u32 known:1; + u32 outer_ip:1; + u32 outer_ip_ver:1; + u32 outer_frag:1; + u32 tunnel_type:3; + u32 tunnel_end_prot:2; + u32 tunnel_end_frag:1; + u32 inner_prot:4; + u32 payload_layer:3; +}; + +enum iavf_rx_ptype_outer_ip { + IAVF_RX_PTYPE_OUTER_L2 = 0, + IAVF_RX_PTYPE_OUTER_IP = 1 +}; + +enum iavf_rx_ptype_outer_ip_ver { + IAVF_RX_PTYPE_OUTER_NONE = 0, + IAVF_RX_PTYPE_OUTER_IPV4 = 0, + IAVF_RX_PTYPE_OUTER_IPV6 = 1 +}; + +enum iavf_rx_ptype_outer_fragmented { + IAVF_RX_PTYPE_NOT_FRAG = 0, + IAVF_RX_PTYPE_FRAG = 1 +}; + +enum iavf_rx_ptype_tunnel_type { + IAVF_RX_PTYPE_TUNNEL_NONE = 0, + IAVF_RX_PTYPE_TUNNEL_IP_IP = 1, + IAVF_RX_PTYPE_TUNNEL_IP_GRENAT = 2, + IAVF_RX_PTYPE_TUNNEL_IP_GRENAT_MAC = 3, + IAVF_RX_PTYPE_TUNNEL_IP_GRENAT_MAC_VLAN = 4, +}; + +enum iavf_rx_ptype_tunnel_end_prot { + IAVF_RX_PTYPE_TUNNEL_END_NONE = 0, + IAVF_RX_PTYPE_TUNNEL_END_IPV4 = 1, + IAVF_RX_PTYPE_TUNNEL_END_IPV6 = 2, +}; + +enum iavf_rx_ptype_inner_prot { + IAVF_RX_PTYPE_INNER_PROT_NONE = 0, + IAVF_RX_PTYPE_INNER_PROT_UDP = 1, + IAVF_RX_PTYPE_INNER_PROT_TCP = 2, + IAVF_RX_PTYPE_INNER_PROT_SCTP = 3, + IAVF_RX_PTYPE_INNER_PROT_ICMP = 4, + IAVF_RX_PTYPE_INNER_PROT_TIMESYNC = 5 +}; + +enum iavf_rx_ptype_payload_layer { + IAVF_RX_PTYPE_PAYLOAD_LAYER_NONE = 0, + IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY2 = 1, + IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY3 = 2, + IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY4 = 3, +}; + +#define IAVF_RXD_QW1_LENGTH_PBUF_SHIFT 38 +#define IAVF_RXD_QW1_LENGTH_PBUF_MASK (0x3FFFULL << \ + IAVF_RXD_QW1_LENGTH_PBUF_SHIFT) + +#define IAVF_RXD_QW1_LENGTH_HBUF_SHIFT 52 +#define IAVF_RXD_QW1_LENGTH_HBUF_MASK (0x7FFULL << \ + IAVF_RXD_QW1_LENGTH_HBUF_SHIFT) + +#define IAVF_RXD_QW1_LENGTH_SPH_SHIFT 63 +#define IAVF_RXD_QW1_LENGTH_SPH_MASK BIT_ULL(IAVF_RXD_QW1_LENGTH_SPH_SHIFT) + +enum iavf_rx_desc_ext_status_bits { + /* Note: These are predefined bit offsets */ + IAVF_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT = 0, + IAVF_RX_DESC_EXT_STATUS_L2TAG3P_SHIFT = 1, + IAVF_RX_DESC_EXT_STATUS_FLEXBL_SHIFT = 2, /* 2 BITS */ + IAVF_RX_DESC_EXT_STATUS_FLEXBH_SHIFT = 4, /* 2 BITS */ + IAVF_RX_DESC_EXT_STATUS_FDLONGB_SHIFT = 9, + IAVF_RX_DESC_EXT_STATUS_FCOELONGB_SHIFT = 10, + IAVF_RX_DESC_EXT_STATUS_PELONGB_SHIFT = 11, +}; + +enum iavf_rx_desc_pe_status_bits { + /* Note: These are predefined bit offsets */ + IAVF_RX_DESC_PE_STATUS_QPID_SHIFT = 0, /* 18 BITS */ + IAVF_RX_DESC_PE_STATUS_L4PORT_SHIFT = 0, /* 16 BITS */ + IAVF_RX_DESC_PE_STATUS_IPINDEX_SHIFT = 16, /* 8 BITS */ + IAVF_RX_DESC_PE_STATUS_QPIDHIT_SHIFT = 24, + IAVF_RX_DESC_PE_STATUS_APBVTHIT_SHIFT = 25, + IAVF_RX_DESC_PE_STATUS_PORTV_SHIFT = 26, + IAVF_RX_DESC_PE_STATUS_URG_SHIFT = 27, + IAVF_RX_DESC_PE_STATUS_IPFRAG_SHIFT = 28, + IAVF_RX_DESC_PE_STATUS_IPOPT_SHIFT = 29 +}; + +#define IAVF_RX_PROG_STATUS_DESC_LENGTH_SHIFT 38 +#define IAVF_RX_PROG_STATUS_DESC_LENGTH 0x2000000 + +#define IAVF_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT 2 +#define IAVF_RX_PROG_STATUS_DESC_QW1_PROGID_MASK (0x7UL << \ + IAVF_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT) + +#define IAVF_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT 19 +#define IAVF_RX_PROG_STATUS_DESC_QW1_ERROR_MASK (0x3FUL << \ + IAVF_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT) + +enum iavf_rx_prog_status_desc_status_bits { + /* Note: These are predefined bit offsets */ + IAVF_RX_PROG_STATUS_DESC_DD_SHIFT = 0, + IAVF_RX_PROG_STATUS_DESC_PROG_ID_SHIFT = 2 /* 3 BITS */ +}; + +enum iavf_rx_prog_status_desc_prog_id_masks { + IAVF_RX_PROG_STATUS_DESC_FD_FILTER_STATUS = 1, + IAVF_RX_PROG_STATUS_DESC_FCOE_CTXT_PROG_STATUS = 2, + IAVF_RX_PROG_STATUS_DESC_FCOE_CTXT_INVL_STATUS = 4, +}; + +enum iavf_rx_prog_status_desc_error_bits { + /* Note: These are predefined bit offsets */ + IAVF_RX_PROG_STATUS_DESC_FD_TBL_FULL_SHIFT = 0, + IAVF_RX_PROG_STATUS_DESC_NO_FD_ENTRY_SHIFT = 1, + IAVF_RX_PROG_STATUS_DESC_FCOE_TBL_FULL_SHIFT = 2, + IAVF_RX_PROG_STATUS_DESC_FCOE_CONFLICT_SHIFT = 3 +}; + +/* TX Descriptor */ +struct iavf_tx_desc { + __le64 buffer_addr; /* Address of descriptor's data buf */ + __le64 cmd_type_offset_bsz; +}; + +#define IAVF_TXD_QW1_DTYPE_SHIFT 0 +#define IAVF_TXD_QW1_DTYPE_MASK (0xFUL << IAVF_TXD_QW1_DTYPE_SHIFT) + +enum iavf_tx_desc_dtype_value { + IAVF_TX_DESC_DTYPE_DATA = 0x0, + IAVF_TX_DESC_DTYPE_NOP = 0x1, /* same as Context desc */ + IAVF_TX_DESC_DTYPE_CONTEXT = 0x1, + IAVF_TX_DESC_DTYPE_FCOE_CTX = 0x2, + IAVF_TX_DESC_DTYPE_FILTER_PROG = 0x8, + IAVF_TX_DESC_DTYPE_DDP_CTX = 0x9, + IAVF_TX_DESC_DTYPE_FLEX_DATA = 0xB, + IAVF_TX_DESC_DTYPE_FLEX_CTX_1 = 0xC, + IAVF_TX_DESC_DTYPE_FLEX_CTX_2 = 0xD, + IAVF_TX_DESC_DTYPE_DESC_DONE = 0xF +}; + +#define IAVF_TXD_QW1_CMD_SHIFT 4 +#define IAVF_TXD_QW1_CMD_MASK (0x3FFUL << IAVF_TXD_QW1_CMD_SHIFT) + +enum iavf_tx_desc_cmd_bits { + IAVF_TX_DESC_CMD_EOP = 0x0001, + IAVF_TX_DESC_CMD_RS = 0x0002, + IAVF_TX_DESC_CMD_ICRC = 0x0004, + IAVF_TX_DESC_CMD_IL2TAG1 = 0x0008, + IAVF_TX_DESC_CMD_DUMMY = 0x0010, + IAVF_TX_DESC_CMD_IIPT_NONIP = 0x0000, /* 2 BITS */ + IAVF_TX_DESC_CMD_IIPT_IPV6 = 0x0020, /* 2 BITS */ + IAVF_TX_DESC_CMD_IIPT_IPV4 = 0x0040, /* 2 BITS */ + IAVF_TX_DESC_CMD_IIPT_IPV4_CSUM = 0x0060, /* 2 BITS */ + IAVF_TX_DESC_CMD_FCOET = 0x0080, + IAVF_TX_DESC_CMD_L4T_EOFT_UNK = 0x0000, /* 2 BITS */ + IAVF_TX_DESC_CMD_L4T_EOFT_TCP = 0x0100, /* 2 BITS */ + IAVF_TX_DESC_CMD_L4T_EOFT_SCTP = 0x0200, /* 2 BITS */ + IAVF_TX_DESC_CMD_L4T_EOFT_UDP = 0x0300, /* 2 BITS */ + IAVF_TX_DESC_CMD_L4T_EOFT_EOF_N = 0x0000, /* 2 BITS */ + IAVF_TX_DESC_CMD_L4T_EOFT_EOF_T = 0x0100, /* 2 BITS */ + IAVF_TX_DESC_CMD_L4T_EOFT_EOF_NI = 0x0200, /* 2 BITS */ + IAVF_TX_DESC_CMD_L4T_EOFT_EOF_A = 0x0300, /* 2 BITS */ +}; + +#define IAVF_TXD_QW1_OFFSET_SHIFT 16 +#define IAVF_TXD_QW1_OFFSET_MASK (0x3FFFFULL << \ + IAVF_TXD_QW1_OFFSET_SHIFT) + +enum iavf_tx_desc_length_fields { + /* Note: These are predefined bit offsets */ + IAVF_TX_DESC_LENGTH_MACLEN_SHIFT = 0, /* 7 BITS */ + IAVF_TX_DESC_LENGTH_IPLEN_SHIFT = 7, /* 7 BITS */ + IAVF_TX_DESC_LENGTH_L4_FC_LEN_SHIFT = 14 /* 4 BITS */ +}; + +#define IAVF_TXD_QW1_TX_BUF_SZ_SHIFT 34 +#define IAVF_TXD_QW1_TX_BUF_SZ_MASK (0x3FFFULL << \ + IAVF_TXD_QW1_TX_BUF_SZ_SHIFT) + +#define IAVF_TXD_QW1_L2TAG1_SHIFT 48 +#define IAVF_TXD_QW1_L2TAG1_MASK (0xFFFFULL << IAVF_TXD_QW1_L2TAG1_SHIFT) + +/* Context descriptors */ +struct iavf_tx_context_desc { + __le32 tunneling_params; + __le16 l2tag2; + __le16 rsvd; + __le64 type_cmd_tso_mss; +}; + +#define IAVF_TXD_CTX_QW1_CMD_SHIFT 4 +#define IAVF_TXD_CTX_QW1_CMD_MASK (0xFFFFUL << IAVF_TXD_CTX_QW1_CMD_SHIFT) + +enum iavf_tx_ctx_desc_cmd_bits { + IAVF_TX_CTX_DESC_TSO = 0x01, + IAVF_TX_CTX_DESC_TSYN = 0x02, + IAVF_TX_CTX_DESC_IL2TAG2 = 0x04, + IAVF_TX_CTX_DESC_IL2TAG2_IL2H = 0x08, + IAVF_TX_CTX_DESC_SWTCH_NOTAG = 0x00, + IAVF_TX_CTX_DESC_SWTCH_UPLINK = 0x10, + IAVF_TX_CTX_DESC_SWTCH_LOCAL = 0x20, + IAVF_TX_CTX_DESC_SWTCH_VSI = 0x30, + IAVF_TX_CTX_DESC_SWPE = 0x40 +}; + +/* Packet Classifier Types for filters */ +enum iavf_filter_pctype { + /* Note: Values 0-28 are reserved for future use. + * Value 29, 30, 32 are not supported on XL710 and X710. + */ + IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP = 29, + IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP = 30, + IAVF_FILTER_PCTYPE_NONF_IPV4_UDP = 31, + IAVF_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK = 32, + IAVF_FILTER_PCTYPE_NONF_IPV4_TCP = 33, + IAVF_FILTER_PCTYPE_NONF_IPV4_SCTP = 34, + IAVF_FILTER_PCTYPE_NONF_IPV4_OTHER = 35, + IAVF_FILTER_PCTYPE_FRAG_IPV4 = 36, + /* Note: Values 37-38 are reserved for future use. + * Value 39, 40, 42 are not supported on XL710 and X710. + */ + IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP = 39, + IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP = 40, + IAVF_FILTER_PCTYPE_NONF_IPV6_UDP = 41, + IAVF_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK = 42, + IAVF_FILTER_PCTYPE_NONF_IPV6_TCP = 43, + IAVF_FILTER_PCTYPE_NONF_IPV6_SCTP = 44, + IAVF_FILTER_PCTYPE_NONF_IPV6_OTHER = 45, + IAVF_FILTER_PCTYPE_FRAG_IPV6 = 46, + /* Note: Value 47 is reserved for future use */ + IAVF_FILTER_PCTYPE_FCOE_OX = 48, + IAVF_FILTER_PCTYPE_FCOE_RX = 49, + IAVF_FILTER_PCTYPE_FCOE_OTHER = 50, + /* Note: Values 51-62 are reserved for future use */ + IAVF_FILTER_PCTYPE_L2_PAYLOAD = 63, +}; + +#define IAVF_TXD_CTX_QW1_TSO_LEN_SHIFT 30 +#define IAVF_TXD_CTX_QW1_TSO_LEN_MASK (0x3FFFFULL << \ + IAVF_TXD_CTX_QW1_TSO_LEN_SHIFT) + +#define IAVF_TXD_CTX_QW1_MSS_SHIFT 50 +#define IAVF_TXD_CTX_QW1_MSS_MASK (0x3FFFULL << \ + IAVF_TXD_CTX_QW1_MSS_SHIFT) + +#define IAVF_TXD_CTX_QW1_VSI_SHIFT 50 +#define IAVF_TXD_CTX_QW1_VSI_MASK (0x1FFULL << IAVF_TXD_CTX_QW1_VSI_SHIFT) + +#define IAVF_TXD_CTX_QW0_EXT_IP_SHIFT 0 +#define IAVF_TXD_CTX_QW0_EXT_IP_MASK (0x3ULL << \ + IAVF_TXD_CTX_QW0_EXT_IP_SHIFT) + +enum iavf_tx_ctx_desc_eipt_offload { + IAVF_TX_CTX_EXT_IP_NONE = 0x0, + IAVF_TX_CTX_EXT_IP_IPV6 = 0x1, + IAVF_TX_CTX_EXT_IP_IPV4_NO_CSUM = 0x2, + IAVF_TX_CTX_EXT_IP_IPV4 = 0x3 +}; + +#define IAVF_TXD_CTX_QW0_EXT_IPLEN_SHIFT 2 +#define IAVF_TXD_CTX_QW0_EXT_IPLEN_MASK (0x3FULL << \ + IAVF_TXD_CTX_QW0_EXT_IPLEN_SHIFT) + +#define IAVF_TXD_CTX_QW0_NATT_SHIFT 9 +#define IAVF_TXD_CTX_QW0_NATT_MASK (0x3ULL << IAVF_TXD_CTX_QW0_NATT_SHIFT) + +#define IAVF_TXD_CTX_UDP_TUNNELING BIT_ULL(IAVF_TXD_CTX_QW0_NATT_SHIFT) +#define IAVF_TXD_CTX_GRE_TUNNELING (0x2ULL << IAVF_TXD_CTX_QW0_NATT_SHIFT) + +#define IAVF_TXD_CTX_QW0_EIP_NOINC_SHIFT 11 +#define IAVF_TXD_CTX_QW0_EIP_NOINC_MASK \ + BIT_ULL(IAVF_TXD_CTX_QW0_EIP_NOINC_SHIFT) + +#define IAVF_TXD_CTX_EIP_NOINC_IPID_CONST IAVF_TXD_CTX_QW0_EIP_NOINC_MASK + +#define IAVF_TXD_CTX_QW0_NATLEN_SHIFT 12 +#define IAVF_TXD_CTX_QW0_NATLEN_MASK (0X7FULL << \ + IAVF_TXD_CTX_QW0_NATLEN_SHIFT) + +#define IAVF_TXD_CTX_QW0_DECTTL_SHIFT 19 +#define IAVF_TXD_CTX_QW0_DECTTL_MASK (0xFULL << \ + IAVF_TXD_CTX_QW0_DECTTL_SHIFT) + +#define IAVF_TXD_CTX_QW0_L4T_CS_SHIFT 23 +#define IAVF_TXD_CTX_QW0_L4T_CS_MASK BIT_ULL(IAVF_TXD_CTX_QW0_L4T_CS_SHIFT) + +/* Statistics collected by each port, VSI, VEB, and S-channel */ +struct iavf_eth_stats { + u64 rx_bytes; /* gorc */ + u64 rx_unicast; /* uprc */ + u64 rx_multicast; /* mprc */ + u64 rx_broadcast; /* bprc */ + u64 rx_discards; /* rdpc */ + u64 rx_unknown_protocol; /* rupp */ + u64 tx_bytes; /* gotc */ + u64 tx_unicast; /* uptc */ + u64 tx_multicast; /* mptc */ + u64 tx_broadcast; /* bptc */ + u64 tx_discards; /* tdpc */ + u64 tx_errors; /* tepc */ +}; +#endif /* _IAVF_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c new file mode 100644 index 000000000000..e64751da0921 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -0,0 +1,1452 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#include "iavf.h" +#include "iavf_prototype.h" +#include "iavf_client.h" + +/* busy wait delay in msec */ +#define IAVF_BUSY_WAIT_DELAY 10 +#define IAVF_BUSY_WAIT_COUNT 50 + +/** + * iavf_send_pf_msg + * @adapter: adapter structure + * @op: virtual channel opcode + * @msg: pointer to message buffer + * @len: message length + * + * Send message to PF and print status if failure. + **/ +static int iavf_send_pf_msg(struct iavf_adapter *adapter, + enum virtchnl_ops op, u8 *msg, u16 len) +{ + struct iavf_hw *hw = &adapter->hw; + iavf_status err; + + if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) + return 0; /* nothing to see here, move along */ + + err = iavf_aq_send_msg_to_pf(hw, op, 0, msg, len, NULL); + if (err) + dev_dbg(&adapter->pdev->dev, "Unable to send opcode %d to PF, err %s, aq_err %s\n", + op, iavf_stat_str(hw, err), + iavf_aq_str(hw, hw->aq.asq_last_status)); + return err; +} + +/** + * iavf_send_api_ver + * @adapter: adapter structure + * + * Send API version admin queue message to the PF. The reply is not checked + * in this function. Returns 0 if the message was successfully + * sent, or one of the I40E_ADMIN_QUEUE_ERROR_ statuses if not. + **/ +int iavf_send_api_ver(struct iavf_adapter *adapter) +{ + struct virtchnl_version_info vvi; + + vvi.major = VIRTCHNL_VERSION_MAJOR; + vvi.minor = VIRTCHNL_VERSION_MINOR; + + return iavf_send_pf_msg(adapter, VIRTCHNL_OP_VERSION, (u8 *)&vvi, + sizeof(vvi)); +} + +/** + * iavf_verify_api_ver + * @adapter: adapter structure + * + * Compare API versions with the PF. Must be called after admin queue is + * initialized. Returns 0 if API versions match, -EIO if they do not, + * I40E_ERR_ADMIN_QUEUE_NO_WORK if the admin queue is empty, and any errors + * from the firmware are propagated. + **/ +int iavf_verify_api_ver(struct iavf_adapter *adapter) +{ + struct virtchnl_version_info *pf_vvi; + struct iavf_hw *hw = &adapter->hw; + struct i40e_arq_event_info event; + enum virtchnl_ops op; + iavf_status err; + + event.buf_len = IAVF_MAX_AQ_BUF_SIZE; + event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL); + if (!event.msg_buf) { + err = -ENOMEM; + goto out; + } + + while (1) { + err = iavf_clean_arq_element(hw, &event, NULL); + /* When the AQ is empty, iavf_clean_arq_element will return + * nonzero and this loop will terminate. + */ + if (err) + goto out_alloc; + op = + (enum virtchnl_ops)le32_to_cpu(event.desc.cookie_high); + if (op == VIRTCHNL_OP_VERSION) + break; + } + + + err = (iavf_status)le32_to_cpu(event.desc.cookie_low); + if (err) + goto out_alloc; + + if (op != VIRTCHNL_OP_VERSION) { + dev_info(&adapter->pdev->dev, "Invalid reply type %d from PF\n", + op); + err = -EIO; + goto out_alloc; + } + + pf_vvi = (struct virtchnl_version_info *)event.msg_buf; + adapter->pf_version = *pf_vvi; + + if ((pf_vvi->major > VIRTCHNL_VERSION_MAJOR) || + ((pf_vvi->major == VIRTCHNL_VERSION_MAJOR) && + (pf_vvi->minor > VIRTCHNL_VERSION_MINOR))) + err = -EIO; + +out_alloc: + kfree(event.msg_buf); +out: + return err; +} + +/** + * iavf_send_vf_config_msg + * @adapter: adapter structure + * + * Send VF configuration request admin queue message to the PF. The reply + * is not checked in this function. Returns 0 if the message was + * successfully sent, or one of the I40E_ADMIN_QUEUE_ERROR_ statuses if not. + **/ +int iavf_send_vf_config_msg(struct iavf_adapter *adapter) +{ + u32 caps; + + caps = VIRTCHNL_VF_OFFLOAD_L2 | + VIRTCHNL_VF_OFFLOAD_RSS_PF | + VIRTCHNL_VF_OFFLOAD_RSS_AQ | + VIRTCHNL_VF_OFFLOAD_RSS_REG | + VIRTCHNL_VF_OFFLOAD_VLAN | + VIRTCHNL_VF_OFFLOAD_WB_ON_ITR | + VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 | + VIRTCHNL_VF_OFFLOAD_ENCAP | + VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM | + VIRTCHNL_VF_OFFLOAD_REQ_QUEUES | + VIRTCHNL_VF_OFFLOAD_ADQ; + + adapter->current_op = VIRTCHNL_OP_GET_VF_RESOURCES; + adapter->aq_required &= ~IAVF_FLAG_AQ_GET_CONFIG; + if (PF_IS_V11(adapter)) + return iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_VF_RESOURCES, + (u8 *)&caps, sizeof(caps)); + else + return iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_VF_RESOURCES, + NULL, 0); +} + +/** + * iavf_validate_num_queues + * @adapter: adapter structure + * + * Validate that the number of queues the PF has sent in + * VIRTCHNL_OP_GET_VF_RESOURCES is not larger than the VF can handle. + **/ +static void iavf_validate_num_queues(struct iavf_adapter *adapter) +{ + if (adapter->vf_res->num_queue_pairs > IAVF_MAX_REQ_QUEUES) { + struct virtchnl_vsi_resource *vsi_res; + int i; + + dev_info(&adapter->pdev->dev, "Received %d queues, but can only have a max of %d\n", + adapter->vf_res->num_queue_pairs, + IAVF_MAX_REQ_QUEUES); + dev_info(&adapter->pdev->dev, "Fixing by reducing queues to %d\n", + IAVF_MAX_REQ_QUEUES); + adapter->vf_res->num_queue_pairs = IAVF_MAX_REQ_QUEUES; + for (i = 0; i < adapter->vf_res->num_vsis; i++) { + vsi_res = &adapter->vf_res->vsi_res[i]; + vsi_res->num_queue_pairs = IAVF_MAX_REQ_QUEUES; + } + } +} + +/** + * iavf_get_vf_config + * @adapter: private adapter structure + * + * Get VF configuration from PF and populate hw structure. Must be called after + * admin queue is initialized. Busy waits until response is received from PF, + * with maximum timeout. Response from PF is returned in the buffer for further + * processing by the caller. + **/ +int iavf_get_vf_config(struct iavf_adapter *adapter) +{ + struct iavf_hw *hw = &adapter->hw; + struct i40e_arq_event_info event; + enum virtchnl_ops op; + iavf_status err; + u16 len; + + len = sizeof(struct virtchnl_vf_resource) + + IAVF_MAX_VF_VSI * sizeof(struct virtchnl_vsi_resource); + event.buf_len = len; + event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL); + if (!event.msg_buf) { + err = -ENOMEM; + goto out; + } + + while (1) { + /* When the AQ is empty, iavf_clean_arq_element will return + * nonzero and this loop will terminate. + */ + err = iavf_clean_arq_element(hw, &event, NULL); + if (err) + goto out_alloc; + op = + (enum virtchnl_ops)le32_to_cpu(event.desc.cookie_high); + if (op == VIRTCHNL_OP_GET_VF_RESOURCES) + break; + } + + err = (iavf_status)le32_to_cpu(event.desc.cookie_low); + memcpy(adapter->vf_res, event.msg_buf, min(event.msg_len, len)); + + /* some PFs send more queues than we should have so validate that + * we aren't getting too many queues + */ + if (!err) + iavf_validate_num_queues(adapter); + iavf_vf_parse_hw_config(hw, adapter->vf_res); +out_alloc: + kfree(event.msg_buf); +out: + return err; +} + +/** + * iavf_configure_queues + * @adapter: adapter structure + * + * Request that the PF set up our (previously allocated) queues. + **/ +void iavf_configure_queues(struct iavf_adapter *adapter) +{ + struct virtchnl_vsi_queue_config_info *vqci; + struct virtchnl_queue_pair_info *vqpi; + int pairs = adapter->num_active_queues; + int i, len, max_frame = IAVF_MAX_RXBUFFER; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot configure queues, command %d pending\n", + adapter->current_op); + return; + } + adapter->current_op = VIRTCHNL_OP_CONFIG_VSI_QUEUES; + len = sizeof(struct virtchnl_vsi_queue_config_info) + + (sizeof(struct virtchnl_queue_pair_info) * pairs); + vqci = kzalloc(len, GFP_KERNEL); + if (!vqci) + return; + + /* Limit maximum frame size when jumbo frames is not enabled */ + if (!(adapter->flags & IAVF_FLAG_LEGACY_RX) && + (adapter->netdev->mtu <= ETH_DATA_LEN)) + max_frame = IAVF_RXBUFFER_1536 - NET_IP_ALIGN; + + vqci->vsi_id = adapter->vsi_res->vsi_id; + vqci->num_queue_pairs = pairs; + vqpi = vqci->qpair; + /* Size check is not needed here - HW max is 16 queue pairs, and we + * can fit info for 31 of them into the AQ buffer before it overflows. + */ + for (i = 0; i < pairs; i++) { + vqpi->txq.vsi_id = vqci->vsi_id; + vqpi->txq.queue_id = i; + vqpi->txq.ring_len = adapter->tx_rings[i].count; + vqpi->txq.dma_ring_addr = adapter->tx_rings[i].dma; + vqpi->rxq.vsi_id = vqci->vsi_id; + vqpi->rxq.queue_id = i; + vqpi->rxq.ring_len = adapter->rx_rings[i].count; + vqpi->rxq.dma_ring_addr = adapter->rx_rings[i].dma; + vqpi->rxq.max_pkt_size = max_frame; + vqpi->rxq.databuffer_size = + ALIGN(adapter->rx_rings[i].rx_buf_len, + BIT_ULL(IAVF_RXQ_CTX_DBUFF_SHIFT)); + vqpi++; + } + + adapter->aq_required &= ~IAVF_FLAG_AQ_CONFIGURE_QUEUES; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_VSI_QUEUES, + (u8 *)vqci, len); + kfree(vqci); +} + +/** + * iavf_enable_queues + * @adapter: adapter structure + * + * Request that the PF enable all of our queues. + **/ +void iavf_enable_queues(struct iavf_adapter *adapter) +{ + struct virtchnl_queue_select vqs; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot enable queues, command %d pending\n", + adapter->current_op); + return; + } + adapter->current_op = VIRTCHNL_OP_ENABLE_QUEUES; + vqs.vsi_id = adapter->vsi_res->vsi_id; + vqs.tx_queues = BIT(adapter->num_active_queues) - 1; + vqs.rx_queues = vqs.tx_queues; + adapter->aq_required &= ~IAVF_FLAG_AQ_ENABLE_QUEUES; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_QUEUES, + (u8 *)&vqs, sizeof(vqs)); +} + +/** + * iavf_disable_queues + * @adapter: adapter structure + * + * Request that the PF disable all of our queues. + **/ +void iavf_disable_queues(struct iavf_adapter *adapter) +{ + struct virtchnl_queue_select vqs; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot disable queues, command %d pending\n", + adapter->current_op); + return; + } + adapter->current_op = VIRTCHNL_OP_DISABLE_QUEUES; + vqs.vsi_id = adapter->vsi_res->vsi_id; + vqs.tx_queues = BIT(adapter->num_active_queues) - 1; + vqs.rx_queues = vqs.tx_queues; + adapter->aq_required &= ~IAVF_FLAG_AQ_DISABLE_QUEUES; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_QUEUES, + (u8 *)&vqs, sizeof(vqs)); +} + +/** + * iavf_map_queues + * @adapter: adapter structure + * + * Request that the PF map queues to interrupt vectors. Misc causes, including + * admin queue, are always mapped to vector 0. + **/ +void iavf_map_queues(struct iavf_adapter *adapter) +{ + struct virtchnl_irq_map_info *vimi; + struct virtchnl_vector_map *vecmap; + int v_idx, q_vectors, len; + struct iavf_q_vector *q_vector; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot map queues to vectors, command %d pending\n", + adapter->current_op); + return; + } + adapter->current_op = VIRTCHNL_OP_CONFIG_IRQ_MAP; + + q_vectors = adapter->num_msix_vectors - NONQ_VECS; + + len = sizeof(struct virtchnl_irq_map_info) + + (adapter->num_msix_vectors * + sizeof(struct virtchnl_vector_map)); + vimi = kzalloc(len, GFP_KERNEL); + if (!vimi) + return; + + vimi->num_vectors = adapter->num_msix_vectors; + /* Queue vectors first */ + for (v_idx = 0; v_idx < q_vectors; v_idx++) { + q_vector = &adapter->q_vectors[v_idx]; + vecmap = &vimi->vecmap[v_idx]; + + vecmap->vsi_id = adapter->vsi_res->vsi_id; + vecmap->vector_id = v_idx + NONQ_VECS; + vecmap->txq_map = q_vector->ring_mask; + vecmap->rxq_map = q_vector->ring_mask; + vecmap->rxitr_idx = IAVF_RX_ITR; + vecmap->txitr_idx = IAVF_TX_ITR; + } + /* Misc vector last - this is only for AdminQ messages */ + vecmap = &vimi->vecmap[v_idx]; + vecmap->vsi_id = adapter->vsi_res->vsi_id; + vecmap->vector_id = 0; + vecmap->txq_map = 0; + vecmap->rxq_map = 0; + + adapter->aq_required &= ~IAVF_FLAG_AQ_MAP_VECTORS; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_IRQ_MAP, + (u8 *)vimi, len); + kfree(vimi); +} + +/** + * iavf_request_queues + * @adapter: adapter structure + * @num: number of requested queues + * + * We get a default number of queues from the PF. This enables us to request a + * different number. Returns 0 on success, negative on failure + **/ +int iavf_request_queues(struct iavf_adapter *adapter, int num) +{ + struct virtchnl_vf_res_request vfres; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot request queues, command %d pending\n", + adapter->current_op); + return -EBUSY; + } + + vfres.num_queue_pairs = num; + + adapter->current_op = VIRTCHNL_OP_REQUEST_QUEUES; + adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED; + return iavf_send_pf_msg(adapter, VIRTCHNL_OP_REQUEST_QUEUES, + (u8 *)&vfres, sizeof(vfres)); +} + +/** + * iavf_add_ether_addrs + * @adapter: adapter structure + * + * Request that the PF add one or more addresses to our filters. + **/ +void iavf_add_ether_addrs(struct iavf_adapter *adapter) +{ + struct virtchnl_ether_addr_list *veal; + int len, i = 0, count = 0; + struct iavf_mac_filter *f; + bool more = false; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot add filters, command %d pending\n", + adapter->current_op); + return; + } + + spin_lock_bh(&adapter->mac_vlan_list_lock); + + list_for_each_entry(f, &adapter->mac_filter_list, list) { + if (f->add) + count++; + } + if (!count) { + adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_MAC_FILTER; + spin_unlock_bh(&adapter->mac_vlan_list_lock); + return; + } + adapter->current_op = VIRTCHNL_OP_ADD_ETH_ADDR; + + len = sizeof(struct virtchnl_ether_addr_list) + + (count * sizeof(struct virtchnl_ether_addr)); + if (len > IAVF_MAX_AQ_BUF_SIZE) { + dev_warn(&adapter->pdev->dev, "Too many add MAC changes in one request\n"); + count = (IAVF_MAX_AQ_BUF_SIZE - + sizeof(struct virtchnl_ether_addr_list)) / + sizeof(struct virtchnl_ether_addr); + len = sizeof(struct virtchnl_ether_addr_list) + + (count * sizeof(struct virtchnl_ether_addr)); + more = true; + } + + veal = kzalloc(len, GFP_ATOMIC); + if (!veal) { + spin_unlock_bh(&adapter->mac_vlan_list_lock); + return; + } + + veal->vsi_id = adapter->vsi_res->vsi_id; + veal->num_elements = count; + list_for_each_entry(f, &adapter->mac_filter_list, list) { + if (f->add) { + ether_addr_copy(veal->list[i].addr, f->macaddr); + i++; + f->add = false; + if (i == count) + break; + } + } + if (!more) + adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_MAC_FILTER; + + spin_unlock_bh(&adapter->mac_vlan_list_lock); + + iavf_send_pf_msg(adapter, VIRTCHNL_OP_ADD_ETH_ADDR, (u8 *)veal, len); + kfree(veal); +} + +/** + * iavf_del_ether_addrs + * @adapter: adapter structure + * + * Request that the PF remove one or more addresses from our filters. + **/ +void iavf_del_ether_addrs(struct iavf_adapter *adapter) +{ + struct virtchnl_ether_addr_list *veal; + struct iavf_mac_filter *f, *ftmp; + int len, i = 0, count = 0; + bool more = false; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot remove filters, command %d pending\n", + adapter->current_op); + return; + } + + spin_lock_bh(&adapter->mac_vlan_list_lock); + + list_for_each_entry(f, &adapter->mac_filter_list, list) { + if (f->remove) + count++; + } + if (!count) { + adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_MAC_FILTER; + spin_unlock_bh(&adapter->mac_vlan_list_lock); + return; + } + adapter->current_op = VIRTCHNL_OP_DEL_ETH_ADDR; + + len = sizeof(struct virtchnl_ether_addr_list) + + (count * sizeof(struct virtchnl_ether_addr)); + if (len > IAVF_MAX_AQ_BUF_SIZE) { + dev_warn(&adapter->pdev->dev, "Too many delete MAC changes in one request\n"); + count = (IAVF_MAX_AQ_BUF_SIZE - + sizeof(struct virtchnl_ether_addr_list)) / + sizeof(struct virtchnl_ether_addr); + len = sizeof(struct virtchnl_ether_addr_list) + + (count * sizeof(struct virtchnl_ether_addr)); + more = true; + } + veal = kzalloc(len, GFP_ATOMIC); + if (!veal) { + spin_unlock_bh(&adapter->mac_vlan_list_lock); + return; + } + + veal->vsi_id = adapter->vsi_res->vsi_id; + veal->num_elements = count; + list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, list) { + if (f->remove) { + ether_addr_copy(veal->list[i].addr, f->macaddr); + i++; + list_del(&f->list); + kfree(f); + if (i == count) + break; + } + } + if (!more) + adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_MAC_FILTER; + + spin_unlock_bh(&adapter->mac_vlan_list_lock); + + iavf_send_pf_msg(adapter, VIRTCHNL_OP_DEL_ETH_ADDR, (u8 *)veal, len); + kfree(veal); +} + +/** + * iavf_add_vlans + * @adapter: adapter structure + * + * Request that the PF add one or more VLAN filters to our VSI. + **/ +void iavf_add_vlans(struct iavf_adapter *adapter) +{ + struct virtchnl_vlan_filter_list *vvfl; + int len, i = 0, count = 0; + struct iavf_vlan_filter *f; + bool more = false; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot add VLANs, command %d pending\n", + adapter->current_op); + return; + } + + spin_lock_bh(&adapter->mac_vlan_list_lock); + + list_for_each_entry(f, &adapter->vlan_filter_list, list) { + if (f->add) + count++; + } + if (!count) { + adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_VLAN_FILTER; + spin_unlock_bh(&adapter->mac_vlan_list_lock); + return; + } + adapter->current_op = VIRTCHNL_OP_ADD_VLAN; + + len = sizeof(struct virtchnl_vlan_filter_list) + + (count * sizeof(u16)); + if (len > IAVF_MAX_AQ_BUF_SIZE) { + dev_warn(&adapter->pdev->dev, "Too many add VLAN changes in one request\n"); + count = (IAVF_MAX_AQ_BUF_SIZE - + sizeof(struct virtchnl_vlan_filter_list)) / + sizeof(u16); + len = sizeof(struct virtchnl_vlan_filter_list) + + (count * sizeof(u16)); + more = true; + } + vvfl = kzalloc(len, GFP_ATOMIC); + if (!vvfl) { + spin_unlock_bh(&adapter->mac_vlan_list_lock); + return; + } + + vvfl->vsi_id = adapter->vsi_res->vsi_id; + vvfl->num_elements = count; + list_for_each_entry(f, &adapter->vlan_filter_list, list) { + if (f->add) { + vvfl->vlan_id[i] = f->vlan; + i++; + f->add = false; + if (i == count) + break; + } + } + if (!more) + adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_VLAN_FILTER; + + spin_unlock_bh(&adapter->mac_vlan_list_lock); + + iavf_send_pf_msg(adapter, VIRTCHNL_OP_ADD_VLAN, (u8 *)vvfl, len); + kfree(vvfl); +} + +/** + * iavf_del_vlans + * @adapter: adapter structure + * + * Request that the PF remove one or more VLAN filters from our VSI. + **/ +void iavf_del_vlans(struct iavf_adapter *adapter) +{ + struct virtchnl_vlan_filter_list *vvfl; + struct iavf_vlan_filter *f, *ftmp; + int len, i = 0, count = 0; + bool more = false; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot remove VLANs, command %d pending\n", + adapter->current_op); + return; + } + + spin_lock_bh(&adapter->mac_vlan_list_lock); + + list_for_each_entry(f, &adapter->vlan_filter_list, list) { + if (f->remove) + count++; + } + if (!count) { + adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_VLAN_FILTER; + spin_unlock_bh(&adapter->mac_vlan_list_lock); + return; + } + adapter->current_op = VIRTCHNL_OP_DEL_VLAN; + + len = sizeof(struct virtchnl_vlan_filter_list) + + (count * sizeof(u16)); + if (len > IAVF_MAX_AQ_BUF_SIZE) { + dev_warn(&adapter->pdev->dev, "Too many delete VLAN changes in one request\n"); + count = (IAVF_MAX_AQ_BUF_SIZE - + sizeof(struct virtchnl_vlan_filter_list)) / + sizeof(u16); + len = sizeof(struct virtchnl_vlan_filter_list) + + (count * sizeof(u16)); + more = true; + } + vvfl = kzalloc(len, GFP_ATOMIC); + if (!vvfl) { + spin_unlock_bh(&adapter->mac_vlan_list_lock); + return; + } + + vvfl->vsi_id = adapter->vsi_res->vsi_id; + vvfl->num_elements = count; + list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { + if (f->remove) { + vvfl->vlan_id[i] = f->vlan; + i++; + list_del(&f->list); + kfree(f); + if (i == count) + break; + } + } + if (!more) + adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_VLAN_FILTER; + + spin_unlock_bh(&adapter->mac_vlan_list_lock); + + iavf_send_pf_msg(adapter, VIRTCHNL_OP_DEL_VLAN, (u8 *)vvfl, len); + kfree(vvfl); +} + +/** + * iavf_set_promiscuous + * @adapter: adapter structure + * @flags: bitmask to control unicast/multicast promiscuous. + * + * Request that the PF enable promiscuous mode for our VSI. + **/ +void iavf_set_promiscuous(struct iavf_adapter *adapter, int flags) +{ + struct virtchnl_promisc_info vpi; + int promisc_all; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot set promiscuous mode, command %d pending\n", + adapter->current_op); + return; + } + + promisc_all = FLAG_VF_UNICAST_PROMISC | + FLAG_VF_MULTICAST_PROMISC; + if ((flags & promisc_all) == promisc_all) { + adapter->flags |= IAVF_FLAG_PROMISC_ON; + adapter->aq_required &= ~IAVF_FLAG_AQ_REQUEST_PROMISC; + dev_info(&adapter->pdev->dev, "Entering promiscuous mode\n"); + } + + if (flags & FLAG_VF_MULTICAST_PROMISC) { + adapter->flags |= IAVF_FLAG_ALLMULTI_ON; + adapter->aq_required &= ~IAVF_FLAG_AQ_REQUEST_ALLMULTI; + dev_info(&adapter->pdev->dev, "Entering multicast promiscuous mode\n"); + } + + if (!flags) { + adapter->flags &= ~(IAVF_FLAG_PROMISC_ON | + IAVF_FLAG_ALLMULTI_ON); + adapter->aq_required &= ~(IAVF_FLAG_AQ_RELEASE_PROMISC | + IAVF_FLAG_AQ_RELEASE_ALLMULTI); + dev_info(&adapter->pdev->dev, "Leaving promiscuous mode\n"); + } + + adapter->current_op = VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE; + vpi.vsi_id = adapter->vsi_res->vsi_id; + vpi.flags = flags; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE, + (u8 *)&vpi, sizeof(vpi)); +} + +/** + * iavf_request_stats + * @adapter: adapter structure + * + * Request VSI statistics from PF. + **/ +void iavf_request_stats(struct iavf_adapter *adapter) +{ + struct virtchnl_queue_select vqs; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* no error message, this isn't crucial */ + return; + } + adapter->current_op = VIRTCHNL_OP_GET_STATS; + vqs.vsi_id = adapter->vsi_res->vsi_id; + /* queue maps are ignored for this message - only the vsi is used */ + if (iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_STATS, (u8 *)&vqs, + sizeof(vqs))) + /* if the request failed, don't lock out others */ + adapter->current_op = VIRTCHNL_OP_UNKNOWN; +} + +/** + * iavf_get_hena + * @adapter: adapter structure + * + * Request hash enable capabilities from PF + **/ +void iavf_get_hena(struct iavf_adapter *adapter) +{ + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot get RSS hash capabilities, command %d pending\n", + adapter->current_op); + return; + } + adapter->current_op = VIRTCHNL_OP_GET_RSS_HENA_CAPS; + adapter->aq_required &= ~IAVF_FLAG_AQ_GET_HENA; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_RSS_HENA_CAPS, NULL, 0); +} + +/** + * iavf_set_hena + * @adapter: adapter structure + * + * Request the PF to set our RSS hash capabilities + **/ +void iavf_set_hena(struct iavf_adapter *adapter) +{ + struct virtchnl_rss_hena vrh; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot set RSS hash enable, command %d pending\n", + adapter->current_op); + return; + } + vrh.hena = adapter->hena; + adapter->current_op = VIRTCHNL_OP_SET_RSS_HENA; + adapter->aq_required &= ~IAVF_FLAG_AQ_SET_HENA; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_SET_RSS_HENA, (u8 *)&vrh, + sizeof(vrh)); +} + +/** + * iavf_set_rss_key + * @adapter: adapter structure + * + * Request the PF to set our RSS hash key + **/ +void iavf_set_rss_key(struct iavf_adapter *adapter) +{ + struct virtchnl_rss_key *vrk; + int len; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot set RSS key, command %d pending\n", + adapter->current_op); + return; + } + len = sizeof(struct virtchnl_rss_key) + + (adapter->rss_key_size * sizeof(u8)) - 1; + vrk = kzalloc(len, GFP_KERNEL); + if (!vrk) + return; + vrk->vsi_id = adapter->vsi.id; + vrk->key_len = adapter->rss_key_size; + memcpy(vrk->key, adapter->rss_key, adapter->rss_key_size); + + adapter->current_op = VIRTCHNL_OP_CONFIG_RSS_KEY; + adapter->aq_required &= ~IAVF_FLAG_AQ_SET_RSS_KEY; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_RSS_KEY, (u8 *)vrk, len); + kfree(vrk); +} + +/** + * iavf_set_rss_lut + * @adapter: adapter structure + * + * Request the PF to set our RSS lookup table + **/ +void iavf_set_rss_lut(struct iavf_adapter *adapter) +{ + struct virtchnl_rss_lut *vrl; + int len; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot set RSS LUT, command %d pending\n", + adapter->current_op); + return; + } + len = sizeof(struct virtchnl_rss_lut) + + (adapter->rss_lut_size * sizeof(u8)) - 1; + vrl = kzalloc(len, GFP_KERNEL); + if (!vrl) + return; + vrl->vsi_id = adapter->vsi.id; + vrl->lut_entries = adapter->rss_lut_size; + memcpy(vrl->lut, adapter->rss_lut, adapter->rss_lut_size); + adapter->current_op = VIRTCHNL_OP_CONFIG_RSS_LUT; + adapter->aq_required &= ~IAVF_FLAG_AQ_SET_RSS_LUT; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_RSS_LUT, (u8 *)vrl, len); + kfree(vrl); +} + +/** + * iavf_enable_vlan_stripping + * @adapter: adapter structure + * + * Request VLAN header stripping to be enabled + **/ +void iavf_enable_vlan_stripping(struct iavf_adapter *adapter) +{ + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot enable stripping, command %d pending\n", + adapter->current_op); + return; + } + adapter->current_op = VIRTCHNL_OP_ENABLE_VLAN_STRIPPING; + adapter->aq_required &= ~IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING, NULL, 0); +} + +/** + * iavf_disable_vlan_stripping + * @adapter: adapter structure + * + * Request VLAN header stripping to be disabled + **/ +void iavf_disable_vlan_stripping(struct iavf_adapter *adapter) +{ + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot disable stripping, command %d pending\n", + adapter->current_op); + return; + } + adapter->current_op = VIRTCHNL_OP_DISABLE_VLAN_STRIPPING; + adapter->aq_required &= ~IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING, NULL, 0); +} + +/** + * iavf_print_link_message - print link up or down + * @adapter: adapter structure + * + * Log a message telling the world of our wonderous link status + */ +static void iavf_print_link_message(struct iavf_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + char *speed = "Unknown "; + + if (!adapter->link_up) { + netdev_info(netdev, "NIC Link is Down\n"); + return; + } + + switch (adapter->link_speed) { + case I40E_LINK_SPEED_40GB: + speed = "40 G"; + break; + case I40E_LINK_SPEED_25GB: + speed = "25 G"; + break; + case I40E_LINK_SPEED_20GB: + speed = "20 G"; + break; + case I40E_LINK_SPEED_10GB: + speed = "10 G"; + break; + case I40E_LINK_SPEED_1GB: + speed = "1000 M"; + break; + case I40E_LINK_SPEED_100MB: + speed = "100 M"; + break; + default: + break; + } + + netdev_info(netdev, "NIC Link is Up %sbps Full Duplex\n", speed); +} + +/** + * iavf_enable_channel + * @adapter: adapter structure + * + * Request that the PF enable channels as specified by + * the user via tc tool. + **/ +void iavf_enable_channels(struct iavf_adapter *adapter) +{ + struct virtchnl_tc_info *vti = NULL; + u16 len; + int i; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot configure mqprio, command %d pending\n", + adapter->current_op); + return; + } + + len = (adapter->num_tc * sizeof(struct virtchnl_channel_info)) + + sizeof(struct virtchnl_tc_info); + + vti = kzalloc(len, GFP_KERNEL); + if (!vti) + return; + vti->num_tc = adapter->num_tc; + for (i = 0; i < vti->num_tc; i++) { + vti->list[i].count = adapter->ch_config.ch_info[i].count; + vti->list[i].offset = adapter->ch_config.ch_info[i].offset; + vti->list[i].pad = 0; + vti->list[i].max_tx_rate = + adapter->ch_config.ch_info[i].max_tx_rate; + } + + adapter->ch_config.state = __IAVF_TC_RUNNING; + adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED; + adapter->current_op = VIRTCHNL_OP_ENABLE_CHANNELS; + adapter->aq_required &= ~IAVF_FLAG_AQ_ENABLE_CHANNELS; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_CHANNELS, (u8 *)vti, len); + kfree(vti); +} + +/** + * iavf_disable_channel + * @adapter: adapter structure + * + * Request that the PF disable channels that are configured + **/ +void iavf_disable_channels(struct iavf_adapter *adapter) +{ + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot configure mqprio, command %d pending\n", + adapter->current_op); + return; + } + + adapter->ch_config.state = __IAVF_TC_INVALID; + adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED; + adapter->current_op = VIRTCHNL_OP_DISABLE_CHANNELS; + adapter->aq_required &= ~IAVF_FLAG_AQ_DISABLE_CHANNELS; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_CHANNELS, NULL, 0); +} + +/** + * iavf_print_cloud_filter + * @adapter: adapter structure + * @f: cloud filter to print + * + * Print the cloud filter + **/ +static void iavf_print_cloud_filter(struct iavf_adapter *adapter, + struct virtchnl_filter *f) +{ + switch (f->flow_type) { + case VIRTCHNL_TCP_V4_FLOW: + dev_info(&adapter->pdev->dev, "dst_mac: %pM src_mac: %pM vlan_id: %hu dst_ip: %pI4 src_ip %pI4 dst_port %hu src_port %hu\n", + &f->data.tcp_spec.dst_mac, + &f->data.tcp_spec.src_mac, + ntohs(f->data.tcp_spec.vlan_id), + &f->data.tcp_spec.dst_ip[0], + &f->data.tcp_spec.src_ip[0], + ntohs(f->data.tcp_spec.dst_port), + ntohs(f->data.tcp_spec.src_port)); + break; + case VIRTCHNL_TCP_V6_FLOW: + dev_info(&adapter->pdev->dev, "dst_mac: %pM src_mac: %pM vlan_id: %hu dst_ip: %pI6 src_ip %pI6 dst_port %hu src_port %hu\n", + &f->data.tcp_spec.dst_mac, + &f->data.tcp_spec.src_mac, + ntohs(f->data.tcp_spec.vlan_id), + &f->data.tcp_spec.dst_ip, + &f->data.tcp_spec.src_ip, + ntohs(f->data.tcp_spec.dst_port), + ntohs(f->data.tcp_spec.src_port)); + break; + } +} + +/** + * iavf_add_cloud_filter + * @adapter: adapter structure + * + * Request that the PF add cloud filters as specified + * by the user via tc tool. + **/ +void iavf_add_cloud_filter(struct iavf_adapter *adapter) +{ + struct iavf_cloud_filter *cf; + struct virtchnl_filter *f; + int len = 0, count = 0; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot add cloud filter, command %d pending\n", + adapter->current_op); + return; + } + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + if (cf->add) { + count++; + break; + } + } + if (!count) { + adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_CLOUD_FILTER; + return; + } + adapter->current_op = VIRTCHNL_OP_ADD_CLOUD_FILTER; + + len = sizeof(struct virtchnl_filter); + f = kzalloc(len, GFP_KERNEL); + if (!f) + return; + + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + if (cf->add) { + memcpy(f, &cf->f, sizeof(struct virtchnl_filter)); + cf->add = false; + cf->state = __IAVF_CF_ADD_PENDING; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_ADD_CLOUD_FILTER, + (u8 *)f, len); + } + } + kfree(f); +} + +/** + * iavf_del_cloud_filter + * @adapter: adapter structure + * + * Request that the PF delete cloud filters as specified + * by the user via tc tool. + **/ +void iavf_del_cloud_filter(struct iavf_adapter *adapter) +{ + struct iavf_cloud_filter *cf, *cftmp; + struct virtchnl_filter *f; + int len = 0, count = 0; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot remove cloud filter, command %d pending\n", + adapter->current_op); + return; + } + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + if (cf->del) { + count++; + break; + } + } + if (!count) { + adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_CLOUD_FILTER; + return; + } + adapter->current_op = VIRTCHNL_OP_DEL_CLOUD_FILTER; + + len = sizeof(struct virtchnl_filter); + f = kzalloc(len, GFP_KERNEL); + if (!f) + return; + + list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, list) { + if (cf->del) { + memcpy(f, &cf->f, sizeof(struct virtchnl_filter)); + cf->del = false; + cf->state = __IAVF_CF_DEL_PENDING; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_DEL_CLOUD_FILTER, + (u8 *)f, len); + } + } + kfree(f); +} + +/** + * iavf_request_reset + * @adapter: adapter structure + * + * Request that the PF reset this VF. No response is expected. + **/ +void iavf_request_reset(struct iavf_adapter *adapter) +{ + /* Don't check CURRENT_OP - this is always higher priority */ + iavf_send_pf_msg(adapter, VIRTCHNL_OP_RESET_VF, NULL, 0); + adapter->current_op = VIRTCHNL_OP_UNKNOWN; +} + +/** + * iavf_virtchnl_completion + * @adapter: adapter structure + * @v_opcode: opcode sent by PF + * @v_retval: retval sent by PF + * @msg: message sent by PF + * @msglen: message length + * + * Asynchronous completion function for admin queue messages. Rather than busy + * wait, we fire off our requests and assume that no errors will be returned. + * This function handles the reply messages. + **/ +void iavf_virtchnl_completion(struct iavf_adapter *adapter, + enum virtchnl_ops v_opcode, iavf_status v_retval, + u8 *msg, u16 msglen) +{ + struct net_device *netdev = adapter->netdev; + + if (v_opcode == VIRTCHNL_OP_EVENT) { + struct virtchnl_pf_event *vpe = + (struct virtchnl_pf_event *)msg; + bool link_up = vpe->event_data.link_event.link_status; + + switch (vpe->event) { + case VIRTCHNL_EVENT_LINK_CHANGE: + adapter->link_speed = + vpe->event_data.link_event.link_speed; + + /* we've already got the right link status, bail */ + if (adapter->link_up == link_up) + break; + + if (link_up) { + /* If we get link up message and start queues + * before our queues are configured it will + * trigger a TX hang. In that case, just ignore + * the link status message,we'll get another one + * after we enable queues and actually prepared + * to send traffic. + */ + if (adapter->state != __IAVF_RUNNING) + break; + + /* For ADq enabled VF, we reconfigure VSIs and + * re-allocate queues. Hence wait till all + * queues are enabled. + */ + if (adapter->flags & + IAVF_FLAG_QUEUES_DISABLED) + break; + } + + adapter->link_up = link_up; + if (link_up) { + netif_tx_start_all_queues(netdev); + netif_carrier_on(netdev); + } else { + netif_tx_stop_all_queues(netdev); + netif_carrier_off(netdev); + } + iavf_print_link_message(adapter); + break; + case VIRTCHNL_EVENT_RESET_IMPENDING: + dev_info(&adapter->pdev->dev, "Reset warning received from the PF\n"); + if (!(adapter->flags & IAVF_FLAG_RESET_PENDING)) { + adapter->flags |= IAVF_FLAG_RESET_PENDING; + dev_info(&adapter->pdev->dev, "Scheduling reset task\n"); + schedule_work(&adapter->reset_task); + } + break; + default: + dev_err(&adapter->pdev->dev, "Unknown event %d from PF\n", + vpe->event); + break; + } + return; + } + if (v_retval) { + switch (v_opcode) { + case VIRTCHNL_OP_ADD_VLAN: + dev_err(&adapter->pdev->dev, "Failed to add VLAN filter, error %s\n", + iavf_stat_str(&adapter->hw, v_retval)); + break; + case VIRTCHNL_OP_ADD_ETH_ADDR: + dev_err(&adapter->pdev->dev, "Failed to add MAC filter, error %s\n", + iavf_stat_str(&adapter->hw, v_retval)); + break; + case VIRTCHNL_OP_DEL_VLAN: + dev_err(&adapter->pdev->dev, "Failed to delete VLAN filter, error %s\n", + iavf_stat_str(&adapter->hw, v_retval)); + break; + case VIRTCHNL_OP_DEL_ETH_ADDR: + dev_err(&adapter->pdev->dev, "Failed to delete MAC filter, error %s\n", + iavf_stat_str(&adapter->hw, v_retval)); + break; + case VIRTCHNL_OP_ENABLE_CHANNELS: + dev_err(&adapter->pdev->dev, "Failed to configure queue channels, error %s\n", + iavf_stat_str(&adapter->hw, v_retval)); + adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; + adapter->ch_config.state = __IAVF_TC_INVALID; + netdev_reset_tc(netdev); + netif_tx_start_all_queues(netdev); + break; + case VIRTCHNL_OP_DISABLE_CHANNELS: + dev_err(&adapter->pdev->dev, "Failed to disable queue channels, error %s\n", + iavf_stat_str(&adapter->hw, v_retval)); + adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; + adapter->ch_config.state = __IAVF_TC_RUNNING; + netif_tx_start_all_queues(netdev); + break; + case VIRTCHNL_OP_ADD_CLOUD_FILTER: { + struct iavf_cloud_filter *cf, *cftmp; + + list_for_each_entry_safe(cf, cftmp, + &adapter->cloud_filter_list, + list) { + if (cf->state == __IAVF_CF_ADD_PENDING) { + cf->state = __IAVF_CF_INVALID; + dev_info(&adapter->pdev->dev, "Failed to add cloud filter, error %s\n", + iavf_stat_str(&adapter->hw, + v_retval)); + iavf_print_cloud_filter(adapter, + &cf->f); + list_del(&cf->list); + kfree(cf); + adapter->num_cloud_filters--; + } + } + } + break; + case VIRTCHNL_OP_DEL_CLOUD_FILTER: { + struct iavf_cloud_filter *cf; + + list_for_each_entry(cf, &adapter->cloud_filter_list, + list) { + if (cf->state == __IAVF_CF_DEL_PENDING) { + cf->state = __IAVF_CF_ACTIVE; + dev_info(&adapter->pdev->dev, "Failed to del cloud filter, error %s\n", + iavf_stat_str(&adapter->hw, + v_retval)); + iavf_print_cloud_filter(adapter, + &cf->f); + } + } + } + break; + default: + dev_err(&adapter->pdev->dev, "PF returned error %d (%s) to our request %d\n", + v_retval, iavf_stat_str(&adapter->hw, v_retval), + v_opcode); + } + } + switch (v_opcode) { + case VIRTCHNL_OP_GET_STATS: { + struct iavf_eth_stats *stats = + (struct iavf_eth_stats *)msg; + netdev->stats.rx_packets = stats->rx_unicast + + stats->rx_multicast + + stats->rx_broadcast; + netdev->stats.tx_packets = stats->tx_unicast + + stats->tx_multicast + + stats->tx_broadcast; + netdev->stats.rx_bytes = stats->rx_bytes; + netdev->stats.tx_bytes = stats->tx_bytes; + netdev->stats.tx_errors = stats->tx_errors; + netdev->stats.rx_dropped = stats->rx_discards; + netdev->stats.tx_dropped = stats->tx_discards; + adapter->current_stats = *stats; + } + break; + case VIRTCHNL_OP_GET_VF_RESOURCES: { + u16 len = sizeof(struct virtchnl_vf_resource) + + IAVF_MAX_VF_VSI * + sizeof(struct virtchnl_vsi_resource); + memcpy(adapter->vf_res, msg, min(msglen, len)); + iavf_validate_num_queues(adapter); + iavf_vf_parse_hw_config(&adapter->hw, adapter->vf_res); + if (is_zero_ether_addr(adapter->hw.mac.addr)) { + /* restore current mac address */ + ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr); + } else { + /* refresh current mac address if changed */ + ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr); + ether_addr_copy(netdev->perm_addr, + adapter->hw.mac.addr); + } + iavf_process_config(adapter); + } + break; + case VIRTCHNL_OP_ENABLE_QUEUES: + /* enable transmits */ + iavf_irq_enable(adapter, true); + adapter->flags &= ~IAVF_FLAG_QUEUES_DISABLED; + break; + case VIRTCHNL_OP_DISABLE_QUEUES: + iavf_free_all_tx_resources(adapter); + iavf_free_all_rx_resources(adapter); + if (adapter->state == __IAVF_DOWN_PENDING) { + adapter->state = __IAVF_DOWN; + wake_up(&adapter->down_waitqueue); + } + break; + case VIRTCHNL_OP_VERSION: + case VIRTCHNL_OP_CONFIG_IRQ_MAP: + /* Don't display an error if we get these out of sequence. + * If the firmware needed to get kicked, we'll get these and + * it's no problem. + */ + if (v_opcode != adapter->current_op) + return; + break; + case VIRTCHNL_OP_IWARP: + /* Gobble zero-length replies from the PF. They indicate that + * a previous message was received OK, and the client doesn't + * care about that. + */ + if (msglen && CLIENT_ENABLED(adapter)) + iavf_notify_client_message(&adapter->vsi, msg, msglen); + break; + + case VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP: + adapter->client_pending &= + ~(BIT(VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP)); + break; + case VIRTCHNL_OP_GET_RSS_HENA_CAPS: { + struct virtchnl_rss_hena *vrh = (struct virtchnl_rss_hena *)msg; + + if (msglen == sizeof(*vrh)) + adapter->hena = vrh->hena; + else + dev_warn(&adapter->pdev->dev, + "Invalid message %d from PF\n", v_opcode); + } + break; + case VIRTCHNL_OP_REQUEST_QUEUES: { + struct virtchnl_vf_res_request *vfres = + (struct virtchnl_vf_res_request *)msg; + + if (vfres->num_queue_pairs != adapter->num_req_queues) { + dev_info(&adapter->pdev->dev, + "Requested %d queues, PF can support %d\n", + adapter->num_req_queues, + vfres->num_queue_pairs); + adapter->num_req_queues = 0; + adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; + } + } + break; + case VIRTCHNL_OP_ADD_CLOUD_FILTER: { + struct iavf_cloud_filter *cf; + + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + if (cf->state == __IAVF_CF_ADD_PENDING) + cf->state = __IAVF_CF_ACTIVE; + } + } + break; + case VIRTCHNL_OP_DEL_CLOUD_FILTER: { + struct iavf_cloud_filter *cf, *cftmp; + + list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, + list) { + if (cf->state == __IAVF_CF_DEL_PENDING) { + cf->state = __IAVF_CF_INVALID; + list_del(&cf->list); + kfree(cf); + adapter->num_cloud_filters--; + } + } + } + break; + default: + if (adapter->current_op && (v_opcode != adapter->current_op)) + dev_warn(&adapter->pdev->dev, "Expected response %d from PF, received %d\n", + adapter->current_op, v_opcode); + break; + } /* switch v_opcode */ + adapter->current_op = VIRTCHNL_OP_UNKNOWN; +} |
