X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fbaseband%2Facc100%2Frte_acc100_pmd.c;h=5e663a62dd6fc9ad3b09570386d376b277c2fca7;hb=57ddbf7edd9c5041603e224fbbb62c11ce423135;hp=e9aa07d3b2a6c11041c0ee129378fe7a81fab261;hpb=f404dfe35cc3cca8fb81ec0a05faadca9bf4df56;p=dpdk.git diff --git a/drivers/baseband/acc100/rte_acc100_pmd.c b/drivers/baseband/acc100/rte_acc100_pmd.c index e9aa07d3b2..5e663a62dd 100644 --- a/drivers/baseband/acc100/rte_acc100_pmd.c +++ b/drivers/baseband/acc100/rte_acc100_pmd.c @@ -38,10 +38,10 @@ mmio_write(void *addr, uint32_t value) /* Write a register of a ACC100 device */ static inline void -acc100_reg_write(struct acc100_device *d, uint32_t offset, uint32_t payload) +acc100_reg_write(struct acc100_device *d, uint32_t offset, uint32_t value) { void *reg_addr = RTE_PTR_ADD(d->mmio_base, offset); - mmio_write(reg_addr, payload); + mmio_write(reg_addr, value); usleep(ACC100_LONG_WAIT); } @@ -85,6 +85,26 @@ queue_offset(bool pf_device, uint8_t vf_id, uint8_t qgrp_id, uint16_t aq_id) enum {UL_4G = 0, UL_5G, DL_4G, DL_5G, NUM_ACC}; +/* Return the accelerator enum for a Queue Group Index */ +static inline int +accFromQgid(int qg_idx, const struct rte_acc100_conf *acc100_conf) +{ + int accQg[ACC100_NUM_QGRPS]; + int NumQGroupsPerFn[NUM_ACC]; + int acc, qgIdx, qgIndex = 0; + for (qgIdx = 0; qgIdx < ACC100_NUM_QGRPS; qgIdx++) + accQg[qgIdx] = 0; + NumQGroupsPerFn[UL_4G] = acc100_conf->q_ul_4g.num_qgroups; + NumQGroupsPerFn[UL_5G] = acc100_conf->q_ul_5g.num_qgroups; + NumQGroupsPerFn[DL_4G] = acc100_conf->q_dl_4g.num_qgroups; + NumQGroupsPerFn[DL_5G] = acc100_conf->q_dl_5g.num_qgroups; + for (acc = UL_4G; acc < NUM_ACC; acc++) + for (qgIdx = 0; qgIdx < NumQGroupsPerFn[acc]; qgIdx++) + accQg[qgIndex++] = acc; + acc = accQg[qg_idx]; + return acc; +} + /* Return the queue topology for a Queue Group Index */ static inline void qtopFromAcc(struct rte_acc100_queue_topology **qtop, int acc_enum, @@ -113,6 +133,30 @@ qtopFromAcc(struct rte_acc100_queue_topology **qtop, int acc_enum, *qtop = p_qtop; } +/* Return the AQ depth for a Queue Group Index */ +static inline int +aqDepth(int qg_idx, struct rte_acc100_conf *acc100_conf) +{ + struct rte_acc100_queue_topology *q_top = NULL; + int acc_enum = accFromQgid(qg_idx, acc100_conf); + qtopFromAcc(&q_top, acc_enum, acc100_conf); + if (unlikely(q_top == NULL)) + return 0; + return q_top->aq_depth_log2; +} + +/* Return the AQ depth for a Queue Group Index */ +static inline int +aqNum(int qg_idx, struct rte_acc100_conf *acc100_conf) +{ + struct rte_acc100_queue_topology *q_top = NULL; + int acc_enum = accFromQgid(qg_idx, acc100_conf); + qtopFromAcc(&q_top, acc_enum, acc100_conf); + if (unlikely(q_top == NULL)) + return 0; + return q_top->num_aqs_per_groups; +} + static void initQTop(struct rte_acc100_conf *acc100_conf) { @@ -342,13 +386,221 @@ alloc_sw_rings_min_mem(struct rte_bbdev *dev, struct acc100_device *d, free_base_addresses(base_addrs, i); } +/* + * Find queue_id of a device queue based on details from the Info Ring. + * If a queue isn't found UINT16_MAX is returned. + */ +static inline uint16_t +get_queue_id_from_ring_info(struct rte_bbdev_data *data, + const union acc100_info_ring_data ring_data) +{ + uint16_t queue_id; + + for (queue_id = 0; queue_id < data->num_queues; ++queue_id) { + struct acc100_queue *acc100_q = + data->queues[queue_id].queue_private; + if (acc100_q != NULL && acc100_q->aq_id == ring_data.aq_id && + acc100_q->qgrp_id == ring_data.qg_id && + acc100_q->vf_id == ring_data.vf_id) + return queue_id; + } + + return UINT16_MAX; +} + +/* Checks PF Info Ring to find the interrupt cause and handles it accordingly */ +static inline void +acc100_check_ir(struct acc100_device *acc100_dev) +{ + volatile union acc100_info_ring_data *ring_data; + uint16_t info_ring_head = acc100_dev->info_ring_head; + if (acc100_dev->info_ring == NULL) + return; + + ring_data = acc100_dev->info_ring + (acc100_dev->info_ring_head & + ACC100_INFO_RING_MASK); + + while (ring_data->valid) { + if ((ring_data->int_nb < ACC100_PF_INT_DMA_DL_DESC_IRQ) || ( + ring_data->int_nb > + ACC100_PF_INT_DMA_DL5G_DESC_IRQ)) + rte_bbdev_log(WARNING, "InfoRing: ITR:%d Info:0x%x", + ring_data->int_nb, ring_data->detailed_info); + /* Initialize Info Ring entry and move forward */ + ring_data->val = 0; + info_ring_head++; + ring_data = acc100_dev->info_ring + + (info_ring_head & ACC100_INFO_RING_MASK); + } +} + +/* Checks PF Info Ring to find the interrupt cause and handles it accordingly */ +static inline void +acc100_pf_interrupt_handler(struct rte_bbdev *dev) +{ + struct acc100_device *acc100_dev = dev->data->dev_private; + volatile union acc100_info_ring_data *ring_data; + struct acc100_deq_intr_details deq_intr_det; + + ring_data = acc100_dev->info_ring + (acc100_dev->info_ring_head & + ACC100_INFO_RING_MASK); + + while (ring_data->valid) { + + rte_bbdev_log_debug( + "ACC100 PF Interrupt received, Info Ring data: 0x%x", + ring_data->val); + + switch (ring_data->int_nb) { + case ACC100_PF_INT_DMA_DL_DESC_IRQ: + case ACC100_PF_INT_DMA_UL_DESC_IRQ: + case ACC100_PF_INT_DMA_UL5G_DESC_IRQ: + case ACC100_PF_INT_DMA_DL5G_DESC_IRQ: + deq_intr_det.queue_id = get_queue_id_from_ring_info( + dev->data, *ring_data); + if (deq_intr_det.queue_id == UINT16_MAX) { + rte_bbdev_log(ERR, + "Couldn't find queue: aq_id: %u, qg_id: %u, vf_id: %u", + ring_data->aq_id, + ring_data->qg_id, + ring_data->vf_id); + return; + } + rte_bbdev_pmd_callback_process(dev, + RTE_BBDEV_EVENT_DEQUEUE, &deq_intr_det); + break; + default: + rte_bbdev_pmd_callback_process(dev, + RTE_BBDEV_EVENT_ERROR, NULL); + break; + } + + /* Initialize Info Ring entry and move forward */ + ring_data->val = 0; + ++acc100_dev->info_ring_head; + ring_data = acc100_dev->info_ring + + (acc100_dev->info_ring_head & + ACC100_INFO_RING_MASK); + } +} + +/* Checks VF Info Ring to find the interrupt cause and handles it accordingly */ +static inline void +acc100_vf_interrupt_handler(struct rte_bbdev *dev) +{ + struct acc100_device *acc100_dev = dev->data->dev_private; + volatile union acc100_info_ring_data *ring_data; + struct acc100_deq_intr_details deq_intr_det; + + ring_data = acc100_dev->info_ring + (acc100_dev->info_ring_head & + ACC100_INFO_RING_MASK); + + while (ring_data->valid) { + + rte_bbdev_log_debug( + "ACC100 VF Interrupt received, Info Ring data: 0x%x", + ring_data->val); + + switch (ring_data->int_nb) { + case ACC100_VF_INT_DMA_DL_DESC_IRQ: + case ACC100_VF_INT_DMA_UL_DESC_IRQ: + case ACC100_VF_INT_DMA_UL5G_DESC_IRQ: + case ACC100_VF_INT_DMA_DL5G_DESC_IRQ: + /* VFs are not aware of their vf_id - it's set to 0 in + * queue structures. + */ + ring_data->vf_id = 0; + deq_intr_det.queue_id = get_queue_id_from_ring_info( + dev->data, *ring_data); + if (deq_intr_det.queue_id == UINT16_MAX) { + rte_bbdev_log(ERR, + "Couldn't find queue: aq_id: %u, qg_id: %u", + ring_data->aq_id, + ring_data->qg_id); + return; + } + rte_bbdev_pmd_callback_process(dev, + RTE_BBDEV_EVENT_DEQUEUE, &deq_intr_det); + break; + default: + rte_bbdev_pmd_callback_process(dev, + RTE_BBDEV_EVENT_ERROR, NULL); + break; + } + + /* Initialize Info Ring entry and move forward */ + ring_data->valid = 0; + ++acc100_dev->info_ring_head; + ring_data = acc100_dev->info_ring + (acc100_dev->info_ring_head + & ACC100_INFO_RING_MASK); + } +} + +/* Interrupt handler triggered by ACC100 dev for handling specific interrupt */ +static void +acc100_dev_interrupt_handler(void *cb_arg) +{ + struct rte_bbdev *dev = cb_arg; + struct acc100_device *acc100_dev = dev->data->dev_private; + + /* Read info ring */ + if (acc100_dev->pf_device) + acc100_pf_interrupt_handler(dev); + else + acc100_vf_interrupt_handler(dev); +} + +/* Allocate and setup inforing */ +static int +allocate_info_ring(struct rte_bbdev *dev) +{ + struct acc100_device *d = dev->data->dev_private; + const struct acc100_registry_addr *reg_addr; + rte_iova_t info_ring_iova; + uint32_t phys_low, phys_high; + + if (d->info_ring != NULL) + return 0; /* Already configured */ + + /* Choose correct registry addresses for the device type */ + if (d->pf_device) + reg_addr = &pf_reg_addr; + else + reg_addr = &vf_reg_addr; + /* Allocate InfoRing */ + d->info_ring = rte_zmalloc_socket("Info Ring", + ACC100_INFO_RING_NUM_ENTRIES * + sizeof(*d->info_ring), RTE_CACHE_LINE_SIZE, + dev->data->socket_id); + if (d->info_ring == NULL) { + rte_bbdev_log(ERR, + "Failed to allocate Info Ring for %s:%u", + dev->device->driver->name, + dev->data->dev_id); + return -ENOMEM; + } + info_ring_iova = rte_malloc_virt2iova(d->info_ring); + + /* Setup Info Ring */ + phys_high = (uint32_t)(info_ring_iova >> 32); + phys_low = (uint32_t)(info_ring_iova); + acc100_reg_write(d, reg_addr->info_ring_hi, phys_high); + acc100_reg_write(d, reg_addr->info_ring_lo, phys_low); + acc100_reg_write(d, reg_addr->info_ring_en, ACC100_REG_IRQ_EN_ALL); + d->info_ring_head = (acc100_reg_read(d, reg_addr->info_ring_ptr) & + 0xFFF) / sizeof(union acc100_info_ring_data); + return 0; +} + + /* Allocate 64MB memory used for all software rings */ static int acc100_setup_queues(struct rte_bbdev *dev, uint16_t num_queues, int socket_id) { - uint32_t phys_low, phys_high, payload; + uint32_t phys_low, phys_high, value; struct acc100_device *d = dev->data->dev_private; const struct acc100_registry_addr *reg_addr; + int ret; if (d->pf_device && !d->acc100_conf.pf_mode_en) { rte_bbdev_log(NOTICE, @@ -404,8 +656,8 @@ acc100_setup_queues(struct rte_bbdev *dev, uint16_t num_queues, int socket_id) * Configure Ring Size to the max queue ring size * (used for wrapping purpose) */ - payload = log2_basic(d->sw_ring_size / 64); - acc100_reg_write(d, reg_addr->ring_size, payload); + value = log2_basic(d->sw_ring_size / 64); + acc100_reg_write(d, reg_addr->ring_size, value); /* Configure tail pointer for use when SDONE enabled */ d->tail_ptrs = rte_zmalloc_socket( @@ -432,6 +684,14 @@ acc100_setup_queues(struct rte_bbdev *dev, uint16_t num_queues, int socket_id) acc100_reg_write(d, reg_addr->tail_ptrs_dl4g_hi, phys_high); acc100_reg_write(d, reg_addr->tail_ptrs_dl4g_lo, phys_low); + ret = allocate_info_ring(dev); + if (ret < 0) { + rte_bbdev_log(ERR, "Failed to allocate info_ring for %s:%u", + dev->device->driver->name, + dev->data->dev_id); + /* Continue */ + } + d->harq_layout = rte_zmalloc_socket("HARQ Layout", ACC100_HARQ_LAYOUT * sizeof(*d->harq_layout), RTE_CACHE_LINE_SIZE, dev->data->socket_id); @@ -453,13 +713,59 @@ acc100_setup_queues(struct rte_bbdev *dev, uint16_t num_queues, int socket_id) return 0; } +static int +acc100_intr_enable(struct rte_bbdev *dev) +{ + int ret; + struct acc100_device *d = dev->data->dev_private; + + /* Only MSI are currently supported */ + if (dev->intr_handle->type == RTE_INTR_HANDLE_VFIO_MSI || + dev->intr_handle->type == RTE_INTR_HANDLE_UIO) { + + ret = allocate_info_ring(dev); + if (ret < 0) { + rte_bbdev_log(ERR, + "Couldn't allocate info ring for device: %s", + dev->data->name); + return ret; + } + + ret = rte_intr_enable(dev->intr_handle); + if (ret < 0) { + rte_bbdev_log(ERR, + "Couldn't enable interrupts for device: %s", + dev->data->name); + rte_free(d->info_ring); + return ret; + } + ret = rte_intr_callback_register(dev->intr_handle, + acc100_dev_interrupt_handler, dev); + if (ret < 0) { + rte_bbdev_log(ERR, + "Couldn't register interrupt callback for device: %s", + dev->data->name); + rte_free(d->info_ring); + return ret; + } + + return 0; + } + + rte_bbdev_log(ERR, "ACC100 (%s) supports only VFIO MSI interrupts", + dev->data->name); + return -ENOTSUP; +} + /* Free memory used for software rings */ static int acc100_dev_close(struct rte_bbdev *dev) { struct acc100_device *d = dev->data->dev_private; + acc100_check_ir(d); if (d->sw_rings_base != NULL) { rte_free(d->tail_ptrs); + rte_free(d->info_ring); rte_free(d->sw_rings_base); d->sw_rings_base = NULL; } @@ -670,6 +976,7 @@ acc100_dev_info_get(struct rte_bbdev *dev, RTE_BBDEV_TURBO_CRC_TYPE_24B | RTE_BBDEV_TURBO_HALF_ITERATION_EVEN | RTE_BBDEV_TURBO_EARLY_TERMINATION | + RTE_BBDEV_TURBO_DEC_INTERRUPTS | RTE_BBDEV_TURBO_NEG_LLR_1_BIT_IN | RTE_BBDEV_TURBO_MAP_DEC | RTE_BBDEV_TURBO_DEC_TB_CRC_24B_KEEP | @@ -690,6 +997,7 @@ acc100_dev_info_get(struct rte_bbdev *dev, RTE_BBDEV_TURBO_CRC_24B_ATTACH | RTE_BBDEV_TURBO_RV_INDEX_BYPASS | RTE_BBDEV_TURBO_RATE_MATCH | + RTE_BBDEV_TURBO_ENC_INTERRUPTS | RTE_BBDEV_TURBO_ENC_SCATTER_GATHER, .num_buffers_src = RTE_BBDEV_TURBO_MAX_CODE_BLOCKS, @@ -703,7 +1011,8 @@ acc100_dev_info_get(struct rte_bbdev *dev, .capability_flags = RTE_BBDEV_LDPC_RATE_MATCH | RTE_BBDEV_LDPC_CRC_24B_ATTACH | - RTE_BBDEV_LDPC_INTERLEAVER_BYPASS, + RTE_BBDEV_LDPC_INTERLEAVER_BYPASS | + RTE_BBDEV_LDPC_ENC_INTERRUPTS, .num_buffers_src = RTE_BBDEV_LDPC_MAX_CODE_BLOCKS, .num_buffers_dst = @@ -728,7 +1037,8 @@ acc100_dev_info_get(struct rte_bbdev *dev, RTE_BBDEV_LDPC_DECODE_BYPASS | RTE_BBDEV_LDPC_DEC_SCATTER_GATHER | RTE_BBDEV_LDPC_HARQ_6BIT_COMPRESSION | - RTE_BBDEV_LDPC_LLR_COMPRESSION, + RTE_BBDEV_LDPC_LLR_COMPRESSION | + RTE_BBDEV_LDPC_DEC_INTERRUPTS, .llr_size = 8, .llr_decimals = 1, .num_buffers_src = @@ -778,14 +1088,44 @@ acc100_dev_info_get(struct rte_bbdev *dev, #else dev_info->harq_buffer_size = 0; #endif + acc100_check_ir(d); +} + +static int +acc100_queue_intr_enable(struct rte_bbdev *dev, uint16_t queue_id) +{ + struct acc100_queue *q = dev->data->queues[queue_id].queue_private; + + if (dev->intr_handle->type != RTE_INTR_HANDLE_VFIO_MSI && + dev->intr_handle->type != RTE_INTR_HANDLE_UIO) + return -ENOTSUP; + + q->irq_enable = 1; + return 0; +} + +static int +acc100_queue_intr_disable(struct rte_bbdev *dev, uint16_t queue_id) +{ + struct acc100_queue *q = dev->data->queues[queue_id].queue_private; + + if (dev->intr_handle->type != RTE_INTR_HANDLE_VFIO_MSI && + dev->intr_handle->type != RTE_INTR_HANDLE_UIO) + return -ENOTSUP; + + q->irq_enable = 0; + return 0; } static const struct rte_bbdev_ops acc100_bbdev_ops = { .setup_queues = acc100_setup_queues, + .intr_enable = acc100_intr_enable, .close = acc100_dev_close, .info_get = acc100_dev_info_get, .queue_setup = acc100_queue_setup, .queue_release = acc100_queue_release, + .queue_intr_enable = acc100_queue_intr_enable, + .queue_intr_disable = acc100_queue_intr_disable }; /* ACC100 PCI PF address map */ @@ -1698,6 +2038,243 @@ acc100_dma_enqueue(struct acc100_queue *q, uint16_t n, } +#ifdef RTE_LIBRTE_BBDEV_DEBUG +/* Validates turbo encoder parameters */ +static inline int +validate_enc_op(struct rte_bbdev_enc_op *op) +{ + struct rte_bbdev_op_turbo_enc *turbo_enc = &op->turbo_enc; + struct rte_bbdev_op_enc_turbo_cb_params *cb = NULL; + struct rte_bbdev_op_enc_turbo_tb_params *tb = NULL; + uint16_t kw, kw_neg, kw_pos; + + if (op->mempool == NULL) { + rte_bbdev_log(ERR, "Invalid mempool pointer"); + return -1; + } + if (turbo_enc->input.data == NULL) { + rte_bbdev_log(ERR, "Invalid input pointer"); + return -1; + } + if (turbo_enc->output.data == NULL) { + rte_bbdev_log(ERR, "Invalid output pointer"); + return -1; + } + if (turbo_enc->rv_index > 3) { + rte_bbdev_log(ERR, + "rv_index (%u) is out of range 0 <= value <= 3", + turbo_enc->rv_index); + return -1; + } + if (turbo_enc->code_block_mode != 0 && + turbo_enc->code_block_mode != 1) { + rte_bbdev_log(ERR, + "code_block_mode (%u) is out of range 0 <= value <= 1", + turbo_enc->code_block_mode); + return -1; + } + + if (turbo_enc->code_block_mode == 0) { + tb = &turbo_enc->tb_params; + if ((tb->k_neg < RTE_BBDEV_TURBO_MIN_CB_SIZE + || tb->k_neg > RTE_BBDEV_TURBO_MAX_CB_SIZE) + && tb->c_neg > 0) { + rte_bbdev_log(ERR, + "k_neg (%u) is out of range %u <= value <= %u", + tb->k_neg, RTE_BBDEV_TURBO_MIN_CB_SIZE, + RTE_BBDEV_TURBO_MAX_CB_SIZE); + return -1; + } + if (tb->k_pos < RTE_BBDEV_TURBO_MIN_CB_SIZE + || tb->k_pos > RTE_BBDEV_TURBO_MAX_CB_SIZE) { + rte_bbdev_log(ERR, + "k_pos (%u) is out of range %u <= value <= %u", + tb->k_pos, RTE_BBDEV_TURBO_MIN_CB_SIZE, + RTE_BBDEV_TURBO_MAX_CB_SIZE); + return -1; + } + if (tb->c_neg > (RTE_BBDEV_TURBO_MAX_CODE_BLOCKS - 1)) + rte_bbdev_log(ERR, + "c_neg (%u) is out of range 0 <= value <= %u", + tb->c_neg, + RTE_BBDEV_TURBO_MAX_CODE_BLOCKS - 1); + if (tb->c < 1 || tb->c > RTE_BBDEV_TURBO_MAX_CODE_BLOCKS) { + rte_bbdev_log(ERR, + "c (%u) is out of range 1 <= value <= %u", + tb->c, RTE_BBDEV_TURBO_MAX_CODE_BLOCKS); + return -1; + } + if (tb->cab > tb->c) { + rte_bbdev_log(ERR, + "cab (%u) is greater than c (%u)", + tb->cab, tb->c); + return -1; + } + if ((tb->ea < RTE_BBDEV_TURBO_MIN_CB_SIZE || (tb->ea % 2)) + && tb->r < tb->cab) { + rte_bbdev_log(ERR, + "ea (%u) is less than %u or it is not even", + tb->ea, RTE_BBDEV_TURBO_MIN_CB_SIZE); + return -1; + } + if ((tb->eb < RTE_BBDEV_TURBO_MIN_CB_SIZE || (tb->eb % 2)) + && tb->c > tb->cab) { + rte_bbdev_log(ERR, + "eb (%u) is less than %u or it is not even", + tb->eb, RTE_BBDEV_TURBO_MIN_CB_SIZE); + return -1; + } + + kw_neg = 3 * RTE_ALIGN_CEIL(tb->k_neg + 4, + RTE_BBDEV_TURBO_C_SUBBLOCK); + if (tb->ncb_neg < tb->k_neg || tb->ncb_neg > kw_neg) { + rte_bbdev_log(ERR, + "ncb_neg (%u) is out of range (%u) k_neg <= value <= (%u) kw_neg", + tb->ncb_neg, tb->k_neg, kw_neg); + return -1; + } + + kw_pos = 3 * RTE_ALIGN_CEIL(tb->k_pos + 4, + RTE_BBDEV_TURBO_C_SUBBLOCK); + if (tb->ncb_pos < tb->k_pos || tb->ncb_pos > kw_pos) { + rte_bbdev_log(ERR, + "ncb_pos (%u) is out of range (%u) k_pos <= value <= (%u) kw_pos", + tb->ncb_pos, tb->k_pos, kw_pos); + return -1; + } + if (tb->r > (tb->c - 1)) { + rte_bbdev_log(ERR, + "r (%u) is greater than c - 1 (%u)", + tb->r, tb->c - 1); + return -1; + } + } else { + cb = &turbo_enc->cb_params; + if (cb->k < RTE_BBDEV_TURBO_MIN_CB_SIZE + || cb->k > RTE_BBDEV_TURBO_MAX_CB_SIZE) { + rte_bbdev_log(ERR, + "k (%u) is out of range %u <= value <= %u", + cb->k, RTE_BBDEV_TURBO_MIN_CB_SIZE, + RTE_BBDEV_TURBO_MAX_CB_SIZE); + return -1; + } + + if (cb->e < RTE_BBDEV_TURBO_MIN_CB_SIZE || (cb->e % 2)) { + rte_bbdev_log(ERR, + "e (%u) is less than %u or it is not even", + cb->e, RTE_BBDEV_TURBO_MIN_CB_SIZE); + return -1; + } + + kw = RTE_ALIGN_CEIL(cb->k + 4, RTE_BBDEV_TURBO_C_SUBBLOCK) * 3; + if (cb->ncb < cb->k || cb->ncb > kw) { + rte_bbdev_log(ERR, + "ncb (%u) is out of range (%u) k <= value <= (%u) kw", + cb->ncb, cb->k, kw); + return -1; + } + } + + return 0; +} +/* Validates LDPC encoder parameters */ +static inline int +validate_ldpc_enc_op(struct rte_bbdev_enc_op *op) +{ + struct rte_bbdev_op_ldpc_enc *ldpc_enc = &op->ldpc_enc; + + if (op->mempool == NULL) { + rte_bbdev_log(ERR, "Invalid mempool pointer"); + return -1; + } + if (ldpc_enc->input.data == NULL) { + rte_bbdev_log(ERR, "Invalid input pointer"); + return -1; + } + if (ldpc_enc->output.data == NULL) { + rte_bbdev_log(ERR, "Invalid output pointer"); + return -1; + } + if (ldpc_enc->input.length > + RTE_BBDEV_LDPC_MAX_CB_SIZE >> 3) { + rte_bbdev_log(ERR, "CB size (%u) is too big, max: %d", + ldpc_enc->input.length, + RTE_BBDEV_LDPC_MAX_CB_SIZE); + return -1; + } + if ((ldpc_enc->basegraph > 2) || (ldpc_enc->basegraph == 0)) { + rte_bbdev_log(ERR, + "BG (%u) is out of range 1 <= value <= 2", + ldpc_enc->basegraph); + return -1; + } + if (ldpc_enc->rv_index > 3) { + rte_bbdev_log(ERR, + "rv_index (%u) is out of range 0 <= value <= 3", + ldpc_enc->rv_index); + return -1; + } + if (ldpc_enc->code_block_mode > 1) { + rte_bbdev_log(ERR, + "code_block_mode (%u) is out of range 0 <= value <= 1", + ldpc_enc->code_block_mode); + return -1; + } + int K = (ldpc_enc->basegraph == 1 ? 22 : 10) * ldpc_enc->z_c; + if (ldpc_enc->n_filler >= K) { + rte_bbdev_log(ERR, + "K and F are not compatible %u %u", + K, ldpc_enc->n_filler); + return -1; + } + return 0; +} + +/* Validates LDPC decoder parameters */ +static inline int +validate_ldpc_dec_op(struct rte_bbdev_dec_op *op) +{ + struct rte_bbdev_op_ldpc_dec *ldpc_dec = &op->ldpc_dec; + + if (op->mempool == NULL) { + rte_bbdev_log(ERR, "Invalid mempool pointer"); + return -1; + } + if ((ldpc_dec->basegraph > 2) || (ldpc_dec->basegraph == 0)) { + rte_bbdev_log(ERR, + "BG (%u) is out of range 1 <= value <= 2", + ldpc_dec->basegraph); + return -1; + } + if (ldpc_dec->iter_max == 0) { + rte_bbdev_log(ERR, + "iter_max (%u) is equal to 0", + ldpc_dec->iter_max); + return -1; + } + if (ldpc_dec->rv_index > 3) { + rte_bbdev_log(ERR, + "rv_index (%u) is out of range 0 <= value <= 3", + ldpc_dec->rv_index); + return -1; + } + if (ldpc_dec->code_block_mode > 1) { + rte_bbdev_log(ERR, + "code_block_mode (%u) is out of range 0 <= value <= 1", + ldpc_dec->code_block_mode); + return -1; + } + int K = (ldpc_dec->basegraph == 1 ? 22 : 10) * ldpc_dec->z_c; + if (ldpc_dec->n_filler >= K) { + rte_bbdev_log(ERR, + "K and F are not compatible %u %u", + K, ldpc_dec->n_filler); + return -1; + } + return 0; +} +#endif + /* Enqueue one encode operations for ACC100 device in CB mode */ static inline int enqueue_enc_one_op_cb(struct acc100_queue *q, struct rte_bbdev_enc_op *op, @@ -1709,6 +2286,14 @@ enqueue_enc_one_op_cb(struct acc100_queue *q, struct rte_bbdev_enc_op *op, seg_total_left; struct rte_mbuf *input, *output_head, *output; +#ifdef RTE_LIBRTE_BBDEV_DEBUG + /* Validate op structure */ + if (validate_enc_op(op) == -1) { + rte_bbdev_log(ERR, "Turbo encoder validation failed"); + return -EINVAL; + } +#endif + uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs) & q->sw_ring_wrap_mask); desc = q->ring_addr + desc_idx; @@ -1755,6 +2340,14 @@ enqueue_ldpc_enc_n_op_cb(struct acc100_queue *q, struct rte_bbdev_enc_op **ops, uint16_t in_length_in_bytes; struct rte_bbdev_op_ldpc_enc *enc = &ops[0]->ldpc_enc; +#ifdef RTE_LIBRTE_BBDEV_DEBUG + /* Validate op structure */ + if (validate_ldpc_enc_op(ops[0]) == -1) { + rte_bbdev_log(ERR, "LDPC encoder validation failed"); + return -EINVAL; + } +#endif + uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs) & q->sw_ring_wrap_mask); desc = q->ring_addr + desc_idx; @@ -1809,6 +2402,14 @@ enqueue_ldpc_enc_one_op_cb(struct acc100_queue *q, struct rte_bbdev_enc_op *op, seg_total_left; struct rte_mbuf *input, *output_head, *output; +#ifdef RTE_LIBRTE_BBDEV_DEBUG + /* Validate op structure */ + if (validate_ldpc_enc_op(op) == -1) { + rte_bbdev_log(ERR, "LDPC encoder validation failed"); + return -EINVAL; + } +#endif + uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs) & q->sw_ring_wrap_mask); desc = q->ring_addr + desc_idx; @@ -1858,6 +2459,14 @@ enqueue_enc_one_op_tb(struct acc100_queue *q, struct rte_bbdev_enc_op *op, struct rte_mbuf *input, *output_head, *output; uint16_t current_enqueued_cbs = 0; +#ifdef RTE_LIBRTE_BBDEV_DEBUG + /* Validate op structure */ + if (validate_enc_op(op) == -1) { + rte_bbdev_log(ERR, "Turbo encoder validation failed"); + return -EINVAL; + } +#endif + uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs) & q->sw_ring_wrap_mask); desc = q->ring_addr + desc_idx; @@ -1910,9 +2519,6 @@ enqueue_enc_one_op_tb(struct acc100_queue *q, struct rte_bbdev_enc_op *op, r++; } - if (unlikely(desc == NULL)) - return current_enqueued_cbs; - #ifdef RTE_LIBRTE_BBDEV_DEBUG if (check_mbuf_total_left(mbuf_total_left) != 0) return -EINVAL; @@ -1925,6 +2531,142 @@ enqueue_enc_one_op_tb(struct acc100_queue *q, struct rte_bbdev_enc_op *op, return current_enqueued_cbs; } +#ifdef RTE_LIBRTE_BBDEV_DEBUG +/* Validates turbo decoder parameters */ +static inline int +validate_dec_op(struct rte_bbdev_dec_op *op) +{ + struct rte_bbdev_op_turbo_dec *turbo_dec = &op->turbo_dec; + struct rte_bbdev_op_dec_turbo_cb_params *cb = NULL; + struct rte_bbdev_op_dec_turbo_tb_params *tb = NULL; + + if (op->mempool == NULL) { + rte_bbdev_log(ERR, "Invalid mempool pointer"); + return -1; + } + if (turbo_dec->input.data == NULL) { + rte_bbdev_log(ERR, "Invalid input pointer"); + return -1; + } + if (turbo_dec->hard_output.data == NULL) { + rte_bbdev_log(ERR, "Invalid hard_output pointer"); + return -1; + } + if (check_bit(turbo_dec->op_flags, RTE_BBDEV_TURBO_SOFT_OUTPUT) && + turbo_dec->soft_output.data == NULL) { + rte_bbdev_log(ERR, "Invalid soft_output pointer"); + return -1; + } + if (turbo_dec->rv_index > 3) { + rte_bbdev_log(ERR, + "rv_index (%u) is out of range 0 <= value <= 3", + turbo_dec->rv_index); + return -1; + } + if (turbo_dec->iter_min < 1) { + rte_bbdev_log(ERR, + "iter_min (%u) is less than 1", + turbo_dec->iter_min); + return -1; + } + if (turbo_dec->iter_max <= 2) { + rte_bbdev_log(ERR, + "iter_max (%u) is less than or equal to 2", + turbo_dec->iter_max); + return -1; + } + if (turbo_dec->iter_min > turbo_dec->iter_max) { + rte_bbdev_log(ERR, + "iter_min (%u) is greater than iter_max (%u)", + turbo_dec->iter_min, turbo_dec->iter_max); + return -1; + } + if (turbo_dec->code_block_mode != 0 && + turbo_dec->code_block_mode != 1) { + rte_bbdev_log(ERR, + "code_block_mode (%u) is out of range 0 <= value <= 1", + turbo_dec->code_block_mode); + return -1; + } + + if (turbo_dec->code_block_mode == 0) { + tb = &turbo_dec->tb_params; + if ((tb->k_neg < RTE_BBDEV_TURBO_MIN_CB_SIZE + || tb->k_neg > RTE_BBDEV_TURBO_MAX_CB_SIZE) + && tb->c_neg > 0) { + rte_bbdev_log(ERR, + "k_neg (%u) is out of range %u <= value <= %u", + tb->k_neg, RTE_BBDEV_TURBO_MIN_CB_SIZE, + RTE_BBDEV_TURBO_MAX_CB_SIZE); + return -1; + } + if ((tb->k_pos < RTE_BBDEV_TURBO_MIN_CB_SIZE + || tb->k_pos > RTE_BBDEV_TURBO_MAX_CB_SIZE) + && tb->c > tb->c_neg) { + rte_bbdev_log(ERR, + "k_pos (%u) is out of range %u <= value <= %u", + tb->k_pos, RTE_BBDEV_TURBO_MIN_CB_SIZE, + RTE_BBDEV_TURBO_MAX_CB_SIZE); + return -1; + } + if (tb->c_neg > (RTE_BBDEV_TURBO_MAX_CODE_BLOCKS - 1)) + rte_bbdev_log(ERR, + "c_neg (%u) is out of range 0 <= value <= %u", + tb->c_neg, + RTE_BBDEV_TURBO_MAX_CODE_BLOCKS - 1); + if (tb->c < 1 || tb->c > RTE_BBDEV_TURBO_MAX_CODE_BLOCKS) { + rte_bbdev_log(ERR, + "c (%u) is out of range 1 <= value <= %u", + tb->c, RTE_BBDEV_TURBO_MAX_CODE_BLOCKS); + return -1; + } + if (tb->cab > tb->c) { + rte_bbdev_log(ERR, + "cab (%u) is greater than c (%u)", + tb->cab, tb->c); + return -1; + } + if (check_bit(turbo_dec->op_flags, RTE_BBDEV_TURBO_EQUALIZER) && + (tb->ea < RTE_BBDEV_TURBO_MIN_CB_SIZE + || (tb->ea % 2)) + && tb->cab > 0) { + rte_bbdev_log(ERR, + "ea (%u) is less than %u or it is not even", + tb->ea, RTE_BBDEV_TURBO_MIN_CB_SIZE); + return -1; + } + if (check_bit(turbo_dec->op_flags, RTE_BBDEV_TURBO_EQUALIZER) && + (tb->eb < RTE_BBDEV_TURBO_MIN_CB_SIZE + || (tb->eb % 2)) + && tb->c > tb->cab) { + rte_bbdev_log(ERR, + "eb (%u) is less than %u or it is not even", + tb->eb, RTE_BBDEV_TURBO_MIN_CB_SIZE); + } + } else { + cb = &turbo_dec->cb_params; + if (cb->k < RTE_BBDEV_TURBO_MIN_CB_SIZE + || cb->k > RTE_BBDEV_TURBO_MAX_CB_SIZE) { + rte_bbdev_log(ERR, + "k (%u) is out of range %u <= value <= %u", + cb->k, RTE_BBDEV_TURBO_MIN_CB_SIZE, + RTE_BBDEV_TURBO_MAX_CB_SIZE); + return -1; + } + if (check_bit(turbo_dec->op_flags, RTE_BBDEV_TURBO_EQUALIZER) && + (cb->e < RTE_BBDEV_TURBO_MIN_CB_SIZE || + (cb->e % 2))) { + rte_bbdev_log(ERR, + "e (%u) is less than %u or it is not even", + cb->e, RTE_BBDEV_TURBO_MIN_CB_SIZE); + return -1; + } + } + + return 0; +} +#endif + /** Enqueue one decode operations for ACC100 device in CB mode */ static inline int enqueue_dec_one_op_cb(struct acc100_queue *q, struct rte_bbdev_dec_op *op, @@ -1937,6 +2679,14 @@ enqueue_dec_one_op_cb(struct acc100_queue *q, struct rte_bbdev_dec_op *op, struct rte_mbuf *input, *h_output_head, *h_output, *s_output_head, *s_output; +#ifdef RTE_LIBRTE_BBDEV_DEBUG + /* Validate op structure */ + if (validate_dec_op(op) == -1) { + rte_bbdev_log(ERR, "Turbo decoder validation failed"); + return -EINVAL; + } +#endif + uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs) & q->sw_ring_wrap_mask); desc = q->ring_addr + desc_idx; @@ -2154,6 +2904,13 @@ enqueue_ldpc_dec_one_op_cb(struct acc100_queue *q, struct rte_bbdev_dec_op *op, return ret; } +#ifdef RTE_LIBRTE_BBDEV_DEBUG + /* Validate op structure */ + if (validate_ldpc_dec_op(op) == -1) { + rte_bbdev_log(ERR, "LDPC decoder validation failed"); + return -EINVAL; + } +#endif union acc100_dma_desc *desc; uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs) & q->sw_ring_wrap_mask); @@ -2251,6 +3008,14 @@ enqueue_ldpc_dec_one_op_tb(struct acc100_queue *q, struct rte_bbdev_dec_op *op, struct rte_mbuf *input, *h_output_head, *h_output; uint16_t current_enqueued_cbs = 0; +#ifdef RTE_LIBRTE_BBDEV_DEBUG + /* Validate op structure */ + if (validate_ldpc_dec_op(op) == -1) { + rte_bbdev_log(ERR, "LDPC decoder validation failed"); + return -EINVAL; + } +#endif + uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs) & q->sw_ring_wrap_mask); desc = q->ring_addr + desc_idx; @@ -2308,9 +3073,6 @@ enqueue_ldpc_dec_one_op_tb(struct acc100_queue *q, struct rte_bbdev_dec_op *op, r++; } - if (unlikely(desc == NULL)) - return current_enqueued_cbs; - #ifdef RTE_LIBRTE_BBDEV_DEBUG if (check_mbuf_total_left(mbuf_total_left) != 0) return -EINVAL; @@ -2336,6 +3098,14 @@ enqueue_dec_one_op_tb(struct acc100_queue *q, struct rte_bbdev_dec_op *op, *s_output_head, *s_output; uint16_t current_enqueued_cbs = 0; +#ifdef RTE_LIBRTE_BBDEV_DEBUG + /* Validate op structure */ + if (validate_dec_op(op) == -1) { + rte_bbdev_log(ERR, "Turbo decoder validation failed"); + return -EINVAL; + } +#endif + uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs) & q->sw_ring_wrap_mask); desc = q->ring_addr + desc_idx; @@ -2405,9 +3175,6 @@ enqueue_dec_one_op_tb(struct acc100_queue *q, struct rte_bbdev_dec_op *op, r++; } - if (unlikely(desc == NULL)) - return current_enqueued_cbs; - #ifdef RTE_LIBRTE_BBDEV_DEBUG if (check_mbuf_total_left(mbuf_total_left) != 0) return -EINVAL; @@ -3018,8 +3785,10 @@ dequeue_dec_one_op_cb(struct rte_bbdev_queue_data *q_data, ? (1 << RTE_BBDEV_DATA_ERROR) : 0); op->status |= ((rsp.dma_err) ? (1 << RTE_BBDEV_DRV_ERROR) : 0); op->status |= ((rsp.fcw_err) ? (1 << RTE_BBDEV_DRV_ERROR) : 0); - if (op->status != 0) + if (op->status != 0) { q_data->queue_stats.dequeue_err_count++; + acc100_check_ir(q->d); + } /* CRC invalid if error exists */ if (!op->status) @@ -3076,6 +3845,9 @@ dequeue_ldpc_dec_one_op_cb(struct rte_bbdev_queue_data *q_data, op->status |= 1 << RTE_BBDEV_SYNDROME_ERROR; op->ldpc_dec.iter_count = (uint8_t) rsp.iter_cnt; + if (op->status & (1 << RTE_BBDEV_DRV_ERROR)) + acc100_check_ir(q->d); + /* Check if this is the last desc in batch (Atomic Queue) */ if (desc->req.last_desc_in_batch) { (*aq_dequeued)++; @@ -3472,3 +4244,475 @@ RTE_PMD_REGISTER_PCI(ACC100PF_DRIVER_NAME, acc100_pci_pf_driver); RTE_PMD_REGISTER_PCI_TABLE(ACC100PF_DRIVER_NAME, pci_id_acc100_pf_map); RTE_PMD_REGISTER_PCI(ACC100VF_DRIVER_NAME, acc100_pci_vf_driver); RTE_PMD_REGISTER_PCI_TABLE(ACC100VF_DRIVER_NAME, pci_id_acc100_vf_map); + +/* + * Workaround implementation to fix the power on status of some 5GUL engines + * This requires DMA permission if ported outside DPDK + * It consists in resolving the state of these engines by running a + * dummy operation and resetting the engines to ensure state are reliably + * defined. + */ +static void +poweron_cleanup(struct rte_bbdev *bbdev, struct acc100_device *d, + struct rte_acc100_conf *conf) +{ + int i, template_idx, qg_idx; + uint32_t address, status, value; + printf("Need to clear power-on 5GUL status in internal memory\n"); + /* Reset LDPC Cores */ + for (i = 0; i < ACC100_ENGINES_MAX; i++) + acc100_reg_write(d, HWPfFecUl5gCntrlReg + + ACC100_ENGINE_OFFSET * i, ACC100_RESET_HI); + usleep(ACC100_LONG_WAIT); + for (i = 0; i < ACC100_ENGINES_MAX; i++) + acc100_reg_write(d, HWPfFecUl5gCntrlReg + + ACC100_ENGINE_OFFSET * i, ACC100_RESET_LO); + usleep(ACC100_LONG_WAIT); + /* Prepare dummy workload */ + alloc_2x64mb_sw_rings_mem(bbdev, d, 0); + /* Set base addresses */ + uint32_t phys_high = (uint32_t)(d->sw_rings_iova >> 32); + uint32_t phys_low = (uint32_t)(d->sw_rings_iova & + ~(ACC100_SIZE_64MBYTE-1)); + acc100_reg_write(d, HWPfDmaFec5GulDescBaseHiRegVf, phys_high); + acc100_reg_write(d, HWPfDmaFec5GulDescBaseLoRegVf, phys_low); + + /* Descriptor for a dummy 5GUL code block processing*/ + union acc100_dma_desc *desc = NULL; + desc = d->sw_rings; + desc->req.data_ptrs[0].address = d->sw_rings_iova + + ACC100_DESC_FCW_OFFSET; + desc->req.data_ptrs[0].blen = ACC100_FCW_LD_BLEN; + desc->req.data_ptrs[0].blkid = ACC100_DMA_BLKID_FCW; + desc->req.data_ptrs[0].last = 0; + desc->req.data_ptrs[0].dma_ext = 0; + desc->req.data_ptrs[1].address = d->sw_rings_iova + 512; + desc->req.data_ptrs[1].blkid = ACC100_DMA_BLKID_IN; + desc->req.data_ptrs[1].last = 1; + desc->req.data_ptrs[1].dma_ext = 0; + desc->req.data_ptrs[1].blen = 44; + desc->req.data_ptrs[2].address = d->sw_rings_iova + 1024; + desc->req.data_ptrs[2].blkid = ACC100_DMA_BLKID_OUT_ENC; + desc->req.data_ptrs[2].last = 1; + desc->req.data_ptrs[2].dma_ext = 0; + desc->req.data_ptrs[2].blen = 5; + /* Dummy FCW */ + desc->req.fcw_ld.FCWversion = ACC100_FCW_VER; + desc->req.fcw_ld.qm = 1; + desc->req.fcw_ld.nfiller = 30; + desc->req.fcw_ld.BG = 2 - 1; + desc->req.fcw_ld.Zc = 7; + desc->req.fcw_ld.ncb = 350; + desc->req.fcw_ld.rm_e = 4; + desc->req.fcw_ld.itmax = 10; + desc->req.fcw_ld.gain_i = 1; + desc->req.fcw_ld.gain_h = 1; + + int engines_to_restart[ACC100_SIG_UL_5G_LAST + 1] = {0}; + int num_failed_engine = 0; + /* Detect engines in undefined state */ + for (template_idx = ACC100_SIG_UL_5G; + template_idx <= ACC100_SIG_UL_5G_LAST; + template_idx++) { + /* Check engine power-on status */ + address = HwPfFecUl5gIbDebugReg + + ACC100_ENGINE_OFFSET * template_idx; + status = (acc100_reg_read(d, address) >> 4) & 0xF; + if (status == 0) { + engines_to_restart[num_failed_engine] = template_idx; + num_failed_engine++; + } + } + + int numQqsAcc = conf->q_ul_5g.num_qgroups; + int numQgs = conf->q_ul_5g.num_qgroups; + value = 0; + for (qg_idx = numQqsAcc; qg_idx < (numQgs + numQqsAcc); qg_idx++) + value |= (1 << qg_idx); + /* Force each engine which is in unspecified state */ + for (i = 0; i < num_failed_engine; i++) { + int failed_engine = engines_to_restart[i]; + printf("Force engine %d\n", failed_engine); + for (template_idx = ACC100_SIG_UL_5G; + template_idx <= ACC100_SIG_UL_5G_LAST; + template_idx++) { + address = HWPfQmgrGrpTmplateReg4Indx + + ACC100_BYTES_IN_WORD * template_idx; + if (template_idx == failed_engine) + acc100_reg_write(d, address, value); + else + acc100_reg_write(d, address, 0); + } + /* Reset descriptor header */ + desc->req.word0 = ACC100_DMA_DESC_TYPE; + desc->req.word1 = 0; + desc->req.word2 = 0; + desc->req.word3 = 0; + desc->req.numCBs = 1; + desc->req.m2dlen = 2; + desc->req.d2mlen = 1; + /* Enqueue the code block for processing */ + union acc100_enqueue_reg_fmt enq_req; + enq_req.val = 0; + enq_req.addr_offset = ACC100_DESC_OFFSET; + enq_req.num_elem = 1; + enq_req.req_elem_addr = 0; + rte_wmb(); + acc100_reg_write(d, HWPfQmgrIngressAq + 0x100, enq_req.val); + usleep(ACC100_LONG_WAIT * 100); + if (desc->req.word0 != 2) + printf("DMA Response %#"PRIx32"\n", desc->req.word0); + } + + /* Reset LDPC Cores */ + for (i = 0; i < ACC100_ENGINES_MAX; i++) + acc100_reg_write(d, HWPfFecUl5gCntrlReg + + ACC100_ENGINE_OFFSET * i, + ACC100_RESET_HI); + usleep(ACC100_LONG_WAIT); + for (i = 0; i < ACC100_ENGINES_MAX; i++) + acc100_reg_write(d, HWPfFecUl5gCntrlReg + + ACC100_ENGINE_OFFSET * i, + ACC100_RESET_LO); + usleep(ACC100_LONG_WAIT); + acc100_reg_write(d, HWPfHi5GHardResetReg, ACC100_RESET_HARD); + usleep(ACC100_LONG_WAIT); + int numEngines = 0; + /* Check engine power-on status again */ + for (template_idx = ACC100_SIG_UL_5G; + template_idx <= ACC100_SIG_UL_5G_LAST; + template_idx++) { + address = HwPfFecUl5gIbDebugReg + + ACC100_ENGINE_OFFSET * template_idx; + status = (acc100_reg_read(d, address) >> 4) & 0xF; + address = HWPfQmgrGrpTmplateReg4Indx + + ACC100_BYTES_IN_WORD * template_idx; + if (status == 1) { + acc100_reg_write(d, address, value); + numEngines++; + } else + acc100_reg_write(d, address, 0); + } + printf("Number of 5GUL engines %d\n", numEngines); + + if (d->sw_rings_base != NULL) + rte_free(d->sw_rings_base); + usleep(ACC100_LONG_WAIT); +} + +/* Initial configuration of a ACC100 device prior to running configure() */ +int +rte_acc100_configure(const char *dev_name, struct rte_acc100_conf *conf) +{ + rte_bbdev_log(INFO, "rte_acc100_configure"); + uint32_t value, address, status; + int qg_idx, template_idx, vf_idx, acc, i; + struct rte_bbdev *bbdev = rte_bbdev_get_named_dev(dev_name); + + /* Compile time checks */ + RTE_BUILD_BUG_ON(sizeof(struct acc100_dma_req_desc) != 256); + RTE_BUILD_BUG_ON(sizeof(union acc100_dma_desc) != 256); + RTE_BUILD_BUG_ON(sizeof(struct acc100_fcw_td) != 24); + RTE_BUILD_BUG_ON(sizeof(struct acc100_fcw_te) != 32); + + if (bbdev == NULL) { + rte_bbdev_log(ERR, + "Invalid dev_name (%s), or device is not yet initialised", + dev_name); + return -ENODEV; + } + struct acc100_device *d = bbdev->data->dev_private; + + /* Store configuration */ + rte_memcpy(&d->acc100_conf, conf, sizeof(d->acc100_conf)); + + /* PCIe Bridge configuration */ + acc100_reg_write(d, HwPfPcieGpexBridgeControl, ACC100_CFG_PCI_BRIDGE); + for (i = 1; i < ACC100_GPEX_AXIMAP_NUM; i++) + acc100_reg_write(d, + HwPfPcieGpexAxiAddrMappingWindowPexBaseHigh + + i * 16, 0); + + /* Prevent blocking AXI read on BRESP for AXI Write */ + address = HwPfPcieGpexAxiPioControl; + value = ACC100_CFG_PCI_AXI; + acc100_reg_write(d, address, value); + + /* 5GDL PLL phase shift */ + acc100_reg_write(d, HWPfChaDl5gPllPhshft0, 0x1); + + /* Explicitly releasing AXI as this may be stopped after PF FLR/BME */ + address = HWPfDmaAxiControl; + value = 1; + acc100_reg_write(d, address, value); + + /* DDR Configuration */ + address = HWPfDdrBcTim6; + value = acc100_reg_read(d, address); + value &= 0xFFFFFFFB; /* Bit 2 */ +#ifdef ACC100_DDR_ECC_ENABLE + value |= 0x4; +#endif + acc100_reg_write(d, address, value); + address = HWPfDdrPhyDqsCountNum; +#ifdef ACC100_DDR_ECC_ENABLE + value = 9; +#else + value = 8; +#endif + acc100_reg_write(d, address, value); + + /* Set default descriptor signature */ + address = HWPfDmaDescriptorSignatuture; + value = 0; + acc100_reg_write(d, address, value); + + /* Enable the Error Detection in DMA */ + value = ACC100_CFG_DMA_ERROR; + address = HWPfDmaErrorDetectionEn; + acc100_reg_write(d, address, value); + + /* AXI Cache configuration */ + value = ACC100_CFG_AXI_CACHE; + address = HWPfDmaAxcacheReg; + acc100_reg_write(d, address, value); + + /* Default DMA Configuration (Qmgr Enabled) */ + address = HWPfDmaConfig0Reg; + value = 0; + acc100_reg_write(d, address, value); + address = HWPfDmaQmanen; + value = 0; + acc100_reg_write(d, address, value); + + /* Default RLIM/ALEN configuration */ + address = HWPfDmaConfig1Reg; + value = (1 << 31) + (23 << 8) + (1 << 6) + 7; + acc100_reg_write(d, address, value); + + /* Configure DMA Qmanager addresses */ + address = HWPfDmaQmgrAddrReg; + value = HWPfQmgrEgressQueuesTemplate; + acc100_reg_write(d, address, value); + + /* ===== Qmgr Configuration ===== */ + /* Configuration of the AQueue Depth QMGR_GRP_0_DEPTH_LOG2 for UL */ + int totalQgs = conf->q_ul_4g.num_qgroups + + conf->q_ul_5g.num_qgroups + + conf->q_dl_4g.num_qgroups + + conf->q_dl_5g.num_qgroups; + for (qg_idx = 0; qg_idx < totalQgs; qg_idx++) { + address = HWPfQmgrDepthLog2Grp + + ACC100_BYTES_IN_WORD * qg_idx; + value = aqDepth(qg_idx, conf); + acc100_reg_write(d, address, value); + address = HWPfQmgrTholdGrp + + ACC100_BYTES_IN_WORD * qg_idx; + value = (1 << 16) + (1 << (aqDepth(qg_idx, conf) - 1)); + acc100_reg_write(d, address, value); + } + + /* Template Priority in incremental order */ + for (template_idx = 0; template_idx < ACC100_NUM_TMPL; + template_idx++) { + address = HWPfQmgrGrpTmplateReg0Indx + + ACC100_BYTES_IN_WORD * (template_idx % 8); + value = ACC100_TMPL_PRI_0; + acc100_reg_write(d, address, value); + address = HWPfQmgrGrpTmplateReg1Indx + + ACC100_BYTES_IN_WORD * (template_idx % 8); + value = ACC100_TMPL_PRI_1; + acc100_reg_write(d, address, value); + address = HWPfQmgrGrpTmplateReg2indx + + ACC100_BYTES_IN_WORD * (template_idx % 8); + value = ACC100_TMPL_PRI_2; + acc100_reg_write(d, address, value); + address = HWPfQmgrGrpTmplateReg3Indx + + ACC100_BYTES_IN_WORD * (template_idx % 8); + value = ACC100_TMPL_PRI_3; + acc100_reg_write(d, address, value); + } + + address = HWPfQmgrGrpPriority; + value = ACC100_CFG_QMGR_HI_P; + acc100_reg_write(d, address, value); + + /* Template Configuration */ + for (template_idx = 0; template_idx < ACC100_NUM_TMPL; + template_idx++) { + value = 0; + address = HWPfQmgrGrpTmplateReg4Indx + + ACC100_BYTES_IN_WORD * template_idx; + acc100_reg_write(d, address, value); + } + /* 4GUL */ + int numQgs = conf->q_ul_4g.num_qgroups; + int numQqsAcc = 0; + value = 0; + for (qg_idx = numQqsAcc; qg_idx < (numQgs + numQqsAcc); qg_idx++) + value |= (1 << qg_idx); + for (template_idx = ACC100_SIG_UL_4G; + template_idx <= ACC100_SIG_UL_4G_LAST; + template_idx++) { + address = HWPfQmgrGrpTmplateReg4Indx + + ACC100_BYTES_IN_WORD * template_idx; + acc100_reg_write(d, address, value); + } + /* 5GUL */ + numQqsAcc += numQgs; + numQgs = conf->q_ul_5g.num_qgroups; + value = 0; + int numEngines = 0; + for (qg_idx = numQqsAcc; qg_idx < (numQgs + numQqsAcc); qg_idx++) + value |= (1 << qg_idx); + for (template_idx = ACC100_SIG_UL_5G; + template_idx <= ACC100_SIG_UL_5G_LAST; + template_idx++) { + /* Check engine power-on status */ + address = HwPfFecUl5gIbDebugReg + + ACC100_ENGINE_OFFSET * template_idx; + status = (acc100_reg_read(d, address) >> 4) & 0xF; + address = HWPfQmgrGrpTmplateReg4Indx + + ACC100_BYTES_IN_WORD * template_idx; + if (status == 1) { + acc100_reg_write(d, address, value); + numEngines++; + } else + acc100_reg_write(d, address, 0); +#if RTE_ACC100_SINGLE_FEC == 1 + value = 0; +#endif + } + printf("Number of 5GUL engines %d\n", numEngines); + /* 4GDL */ + numQqsAcc += numQgs; + numQgs = conf->q_dl_4g.num_qgroups; + value = 0; + for (qg_idx = numQqsAcc; qg_idx < (numQgs + numQqsAcc); qg_idx++) + value |= (1 << qg_idx); + for (template_idx = ACC100_SIG_DL_4G; + template_idx <= ACC100_SIG_DL_4G_LAST; + template_idx++) { + address = HWPfQmgrGrpTmplateReg4Indx + + ACC100_BYTES_IN_WORD * template_idx; + acc100_reg_write(d, address, value); +#if RTE_ACC100_SINGLE_FEC == 1 + value = 0; +#endif + } + /* 5GDL */ + numQqsAcc += numQgs; + numQgs = conf->q_dl_5g.num_qgroups; + value = 0; + for (qg_idx = numQqsAcc; qg_idx < (numQgs + numQqsAcc); qg_idx++) + value |= (1 << qg_idx); + for (template_idx = ACC100_SIG_DL_5G; + template_idx <= ACC100_SIG_DL_5G_LAST; + template_idx++) { + address = HWPfQmgrGrpTmplateReg4Indx + + ACC100_BYTES_IN_WORD * template_idx; + acc100_reg_write(d, address, value); +#if RTE_ACC100_SINGLE_FEC == 1 + value = 0; +#endif + } + + /* Queue Group Function mapping */ + int qman_func_id[5] = {0, 2, 1, 3, 4}; + address = HWPfQmgrGrpFunction0; + value = 0; + for (qg_idx = 0; qg_idx < 8; qg_idx++) { + acc = accFromQgid(qg_idx, conf); + value |= qman_func_id[acc]<<(qg_idx * 4); + } + acc100_reg_write(d, address, value); + + /* Configuration of the Arbitration QGroup depth to 1 */ + for (qg_idx = 0; qg_idx < totalQgs; qg_idx++) { + address = HWPfQmgrArbQDepthGrp + + ACC100_BYTES_IN_WORD * qg_idx; + value = 0; + acc100_reg_write(d, address, value); + } + + /* Enabling AQueues through the Queue hierarchy*/ + for (vf_idx = 0; vf_idx < ACC100_NUM_VFS; vf_idx++) { + for (qg_idx = 0; qg_idx < ACC100_NUM_QGRPS; qg_idx++) { + value = 0; + if (vf_idx < conf->num_vf_bundles && + qg_idx < totalQgs) + value = (1 << aqNum(qg_idx, conf)) - 1; + address = HWPfQmgrAqEnableVf + + vf_idx * ACC100_BYTES_IN_WORD; + value += (qg_idx << 16); + acc100_reg_write(d, address, value); + } + } + + /* This pointer to ARAM (256kB) is shifted by 2 (4B per register) */ + uint32_t aram_address = 0; + for (qg_idx = 0; qg_idx < totalQgs; qg_idx++) { + for (vf_idx = 0; vf_idx < conf->num_vf_bundles; vf_idx++) { + address = HWPfQmgrVfBaseAddr + vf_idx + * ACC100_BYTES_IN_WORD + qg_idx + * ACC100_BYTES_IN_WORD * 64; + value = aram_address; + acc100_reg_write(d, address, value); + /* Offset ARAM Address for next memory bank + * - increment of 4B + */ + aram_address += aqNum(qg_idx, conf) * + (1 << aqDepth(qg_idx, conf)); + } + } + + if (aram_address > ACC100_WORDS_IN_ARAM_SIZE) { + rte_bbdev_log(ERR, "ARAM Configuration not fitting %d %d\n", + aram_address, ACC100_WORDS_IN_ARAM_SIZE); + return -EINVAL; + } + + /* ==== HI Configuration ==== */ + + /* Prevent Block on Transmit Error */ + address = HWPfHiBlockTransmitOnErrorEn; + value = 0; + acc100_reg_write(d, address, value); + /* Prevents to drop MSI */ + address = HWPfHiMsiDropEnableReg; + value = 0; + acc100_reg_write(d, address, value); + /* Set the PF Mode register */ + address = HWPfHiPfMode; + value = (conf->pf_mode_en) ? ACC100_PF_VAL : 0; + acc100_reg_write(d, address, value); + /* Enable Error Detection in HW */ + address = HWPfDmaErrorDetectionEn; + value = 0x3D7; + acc100_reg_write(d, address, value); + + /* QoS overflow init */ + value = 1; + address = HWPfQosmonAEvalOverflow0; + acc100_reg_write(d, address, value); + address = HWPfQosmonBEvalOverflow0; + acc100_reg_write(d, address, value); + + /* HARQ DDR Configuration */ + unsigned int ddrSizeInMb = 512; /* Fixed to 512 MB per VF for now */ + for (vf_idx = 0; vf_idx < conf->num_vf_bundles; vf_idx++) { + address = HWPfDmaVfDdrBaseRw + vf_idx + * 0x10; + value = ((vf_idx * (ddrSizeInMb / 64)) << 16) + + (ddrSizeInMb - 1); + acc100_reg_write(d, address, value); + } + usleep(ACC100_LONG_WAIT); + + /* Workaround in case some 5GUL engines are in an unexpected state */ + if (numEngines < (ACC100_SIG_UL_5G_LAST + 1)) + poweron_cleanup(bbdev, d, conf); + + rte_bbdev_log_debug("PF Tip configuration complete for %s", dev_name); + return 0; +}