From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 5A2EEA00C5; Mon, 12 Sep 2022 03:09:51 +0200 (CEST) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id A17AD42B73; Mon, 12 Sep 2022 03:09:21 +0200 (CEST) Received: from mga04.intel.com (mga04.intel.com [192.55.52.120]) by mails.dpdk.org (Postfix) with ESMTP id D7D7840A89 for ; Mon, 12 Sep 2022 03:09:15 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1662944956; x=1694480956; h=from:to:cc:subject:date:message-id:in-reply-to: references; bh=mBWIYd7+nqCa8pOplfPUtvZFvwQ15BNSx4c0GN8shYk=; b=Yr3V9ZUrmDQfCjKUT+Lj2lSF6HmJw+ZbTtBlTrbae6nZ1kL1ZGz2bZ0m vgMo44QhoK7n4cv6BQPfC7/vMvP6CBqeSxpX6KOnOX4SW0FfEru3S25JX DC/NdEt5csol3Kyow9nXOcWUANeQpS6lp077i4YDyaI73++y85cyd+WqM v49W6PJlDybEgQ2epNBudqwQDDLXP5ikhE1gzzrHw5Wq/LKpsqCep2GQP KvMwCtLFq7oYk3xn6OO3AB2YhaQ3alx+re/A5d9sztSa1Ig75XTskPWmF As9stsWfWzNr0cFVphq6tWWG+shadJcZ+o6joXwXKWEbCzHcH9Iojzo35 Q==; X-IronPort-AV: E=McAfee;i="6500,9779,10467"; a="296501691" X-IronPort-AV: E=Sophos;i="5.93,308,1654585200"; d="scan'208";a="296501691" Received: from orsmga004.jf.intel.com ([10.7.209.38]) by fmsmga104.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Sep 2022 18:09:14 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.93,308,1654585200"; d="scan'208";a="741617954" Received: from unknown (HELO icx-npg-scs1-cp1.localdomain) ([10.233.180.245]) by orsmga004.jf.intel.com with ESMTP; 11 Sep 2022 18:09:13 -0700 From: Nic Chautru To: dev@dpdk.org, thomas@monjalon.net, gakhil@marvell.com, hemant.agrawal@nxp.com Cc: maxime.coquelin@redhat.com, trix@redhat.com, mdr@ashroe.eu, bruce.richardson@intel.com, david.marchand@redhat.com, stephen@networkplumber.org, hernan.vargas@intel.com, Nicolas Chautru Subject: [PATCH v2 05/11] baseband/acc200: add queue configuration Date: Sun, 11 Sep 2022 18:08:52 -0700 Message-Id: <1662944938-32649-6-git-send-email-nicolas.chautru@intel.com> X-Mailer: git-send-email 1.8.3.1 In-Reply-To: <1662944938-32649-1-git-send-email-nicolas.chautru@intel.com> References: <1657238503-143836-2-git-send-email-nicolas.chautru@intel.com> <1662944938-32649-1-git-send-email-nicolas.chautru@intel.com> X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org From: Nicolas Chautru Adding fuinction to create and configure queues for the device. Signed-off-by: Nicolas Chautru --- drivers/baseband/acc200/rte_acc200_pmd.c | 373 ++++++++++++++++++++++++++++++- 1 file changed, 372 insertions(+), 1 deletion(-) diff --git a/drivers/baseband/acc200/rte_acc200_pmd.c b/drivers/baseband/acc200/rte_acc200_pmd.c index 43415eb..225bab9 100644 --- a/drivers/baseband/acc200/rte_acc200_pmd.c +++ b/drivers/baseband/acc200/rte_acc200_pmd.c @@ -220,16 +220,383 @@ acc_conf->q_fft.aq_depth_log2); } +/* Allocate 64MB memory used for all software rings */ +static int +acc200_setup_queues(struct rte_bbdev *dev, uint16_t num_queues, int socket_id) +{ + uint32_t phys_low, phys_high, value; + struct acc_device *d = dev->data->dev_private; + const struct acc200_registry_addr *reg_addr; + + if (d->pf_device && !d->acc_conf.pf_mode_en) { + rte_bbdev_log(NOTICE, + "%s has PF mode disabled. This PF can't be used.", + dev->data->name); + return -ENODEV; + } + if (!d->pf_device && d->acc_conf.pf_mode_en) { + rte_bbdev_log(NOTICE, + "%s has PF mode enabled. This VF can't be used.", + dev->data->name); + return -ENODEV; + } + + alloc_sw_rings_min_mem(dev, d, num_queues, socket_id); + + /* If minimal memory space approach failed, then allocate + * the 2 * 64MB block for the sw rings + */ + if (d->sw_rings == NULL) + alloc_2x64mb_sw_rings_mem(dev, d, socket_id); + + if (d->sw_rings == NULL) { + rte_bbdev_log(NOTICE, + "Failure allocating sw_rings memory"); + return -ENODEV; + } + + /* Configure ACC200 with the base address for DMA descriptor rings + * Same descriptor rings used for UL and DL DMA Engines + * Note : Assuming only VF0 bundle is used for PF mode + */ + phys_high = (uint32_t)(d->sw_rings_iova >> 32); + phys_low = (uint32_t)(d->sw_rings_iova & ~(ACC_SIZE_64MBYTE-1)); + + /* Choose correct registry addresses for the device type */ + if (d->pf_device) + reg_addr = &pf_reg_addr; + else + reg_addr = &vf_reg_addr; + + /* Read the populated cfg from ACC200 registers */ + fetch_acc200_config(dev); + + /* Start Pmon */ + for (value = 0; value <= 2; value++) { + acc_reg_write(d, reg_addr->pmon_ctrl_a, value); + acc_reg_write(d, reg_addr->pmon_ctrl_b, value); + acc_reg_write(d, reg_addr->pmon_ctrl_c, value); + } + + /* Release AXI from PF */ + if (d->pf_device) + acc_reg_write(d, HWPfDmaAxiControl, 1); + + acc_reg_write(d, reg_addr->dma_ring_ul5g_hi, phys_high); + acc_reg_write(d, reg_addr->dma_ring_ul5g_lo, phys_low); + acc_reg_write(d, reg_addr->dma_ring_dl5g_hi, phys_high); + acc_reg_write(d, reg_addr->dma_ring_dl5g_lo, phys_low); + acc_reg_write(d, reg_addr->dma_ring_ul4g_hi, phys_high); + acc_reg_write(d, reg_addr->dma_ring_ul4g_lo, phys_low); + acc_reg_write(d, reg_addr->dma_ring_dl4g_hi, phys_high); + acc_reg_write(d, reg_addr->dma_ring_dl4g_lo, phys_low); + acc_reg_write(d, reg_addr->dma_ring_fft_hi, phys_high); + acc_reg_write(d, reg_addr->dma_ring_fft_lo, phys_low); + /* + * Configure Ring Size to the max queue ring size + * (used for wrapping purpose) + */ + value = log2_basic(d->sw_ring_size / 64); + acc_reg_write(d, reg_addr->ring_size, value); + + /* Configure tail pointer for use when SDONE enabled */ + if (d->tail_ptrs == NULL) + d->tail_ptrs = rte_zmalloc_socket( + dev->device->driver->name, + ACC200_NUM_QGRPS * ACC200_NUM_AQS * sizeof(uint32_t), + RTE_CACHE_LINE_SIZE, socket_id); + if (d->tail_ptrs == NULL) { + rte_bbdev_log(ERR, "Failed to allocate tail ptr for %s:%u", + dev->device->driver->name, + dev->data->dev_id); + rte_free(d->sw_rings); + return -ENOMEM; + } + d->tail_ptr_iova = rte_malloc_virt2iova(d->tail_ptrs); + + phys_high = (uint32_t)(d->tail_ptr_iova >> 32); + phys_low = (uint32_t)(d->tail_ptr_iova); + acc_reg_write(d, reg_addr->tail_ptrs_ul5g_hi, phys_high); + acc_reg_write(d, reg_addr->tail_ptrs_ul5g_lo, phys_low); + acc_reg_write(d, reg_addr->tail_ptrs_dl5g_hi, phys_high); + acc_reg_write(d, reg_addr->tail_ptrs_dl5g_lo, phys_low); + acc_reg_write(d, reg_addr->tail_ptrs_ul4g_hi, phys_high); + acc_reg_write(d, reg_addr->tail_ptrs_ul4g_lo, phys_low); + acc_reg_write(d, reg_addr->tail_ptrs_dl4g_hi, phys_high); + acc_reg_write(d, reg_addr->tail_ptrs_dl4g_lo, phys_low); + acc_reg_write(d, reg_addr->tail_ptrs_fft_hi, phys_high); + acc_reg_write(d, reg_addr->tail_ptrs_fft_lo, phys_low); + + if (d->harq_layout == NULL) + d->harq_layout = rte_zmalloc_socket("HARQ Layout", + ACC_HARQ_LAYOUT * sizeof(*d->harq_layout), + RTE_CACHE_LINE_SIZE, dev->data->socket_id); + if (d->harq_layout == NULL) { + rte_bbdev_log(ERR, "Failed to allocate harq_layout for %s:%u", + dev->device->driver->name, + dev->data->dev_id); + rte_free(d->sw_rings); + return -ENOMEM; + } + + /* Mark as configured properly */ + d->configured = true; + + rte_bbdev_log_debug( + "ACC200 (%s) configured sw_rings = %p, sw_rings_iova = %#" + PRIx64, dev->data->name, d->sw_rings, d->sw_rings_iova); + + return 0; +} + /* Free memory used for software rings */ static int acc200_dev_close(struct rte_bbdev *dev) { - RTE_SET_USED(dev); + struct acc_device *d = dev->data->dev_private; + if (d->sw_rings_base != NULL) { + rte_free(d->tail_ptrs); + rte_free(d->sw_rings_base); + rte_free(d->harq_layout); + d->sw_rings_base = NULL; + d->tail_ptrs = NULL; + d->harq_layout = NULL; + } /* Ensure all in flight HW transactions are completed */ usleep(ACC_LONG_WAIT); return 0; } +/** + * Report a ACC200 queue index which is free + * Return 0 to 16k for a valid queue_idx or -1 when no queue is available + * Note : Only supporting VF0 Bundle for PF mode + */ +static int +acc200_find_free_queue_idx(struct rte_bbdev *dev, + const struct rte_bbdev_queue_conf *conf) +{ + struct acc_device *d = dev->data->dev_private; + int op_2_acc[6] = {0, UL_4G, DL_4G, UL_5G, DL_5G, FFT}; + int acc = op_2_acc[conf->op_type]; + struct rte_acc_queue_topology *qtop = NULL; + + qtopFromAcc(&qtop, acc, &(d->acc_conf)); + if (qtop == NULL) + return -1; + /* Identify matching QGroup Index which are sorted in priority order */ + uint16_t group_idx = qtop->first_qgroup_index; + group_idx += conf->priority; + if (group_idx >= ACC200_NUM_QGRPS || + conf->priority >= qtop->num_qgroups) { + rte_bbdev_log(INFO, "Invalid Priority on %s, priority %u", + dev->data->name, conf->priority); + return -1; + } + /* Find a free AQ_idx */ + uint16_t aq_idx; + for (aq_idx = 0; aq_idx < qtop->num_aqs_per_groups; aq_idx++) { + if (((d->q_assigned_bit_map[group_idx] >> aq_idx) & 0x1) == 0) { + /* Mark the Queue as assigned */ + d->q_assigned_bit_map[group_idx] |= (1 << aq_idx); + /* Report the AQ Index */ + return (group_idx << ACC200_GRP_ID_SHIFT) + aq_idx; + } + } + rte_bbdev_log(INFO, "Failed to find free queue on %s, priority %u", + dev->data->name, conf->priority); + return -1; +} + +/* Setup ACC200 queue */ +static int +acc200_queue_setup(struct rte_bbdev *dev, uint16_t queue_id, + const struct rte_bbdev_queue_conf *conf) +{ + struct acc_device *d = dev->data->dev_private; + struct acc_queue *q; + int16_t q_idx; + + if (d == NULL) { + rte_bbdev_log(ERR, "Undefined device"); + return -ENODEV; + } + /* Allocate the queue data structure. */ + q = rte_zmalloc_socket(dev->device->driver->name, sizeof(*q), + RTE_CACHE_LINE_SIZE, conf->socket); + if (q == NULL) { + rte_bbdev_log(ERR, "Failed to allocate queue memory"); + return -ENOMEM; + } + + q->d = d; + q->ring_addr = RTE_PTR_ADD(d->sw_rings, (d->sw_ring_size * queue_id)); + q->ring_addr_iova = d->sw_rings_iova + (d->sw_ring_size * queue_id); + + /* Prepare the Ring with default descriptor format */ + union acc_dma_desc *desc = NULL; + unsigned int desc_idx, b_idx; + int fcw_len = (conf->op_type == RTE_BBDEV_OP_LDPC_ENC ? + ACC_FCW_LE_BLEN : (conf->op_type == RTE_BBDEV_OP_TURBO_DEC ? + ACC_FCW_TD_BLEN : (conf->op_type == RTE_BBDEV_OP_LDPC_DEC ? + ACC_FCW_LD_BLEN : ACC_FCW_FFT_BLEN))); + + for (desc_idx = 0; desc_idx < d->sw_ring_max_depth; desc_idx++) { + desc = q->ring_addr + desc_idx; + desc->req.word0 = ACC_DMA_DESC_TYPE; + desc->req.word1 = 0; /**< Timestamp */ + desc->req.word2 = 0; + desc->req.word3 = 0; + uint64_t fcw_offset = (desc_idx << 8) + ACC_DESC_FCW_OFFSET; + desc->req.data_ptrs[0].address = q->ring_addr_iova + fcw_offset; + desc->req.data_ptrs[0].blen = fcw_len; + desc->req.data_ptrs[0].blkid = ACC_DMA_BLKID_FCW; + desc->req.data_ptrs[0].last = 0; + desc->req.data_ptrs[0].dma_ext = 0; + for (b_idx = 1; b_idx < ACC_DMA_MAX_NUM_POINTERS - 1; + b_idx++) { + desc->req.data_ptrs[b_idx].blkid = ACC_DMA_BLKID_IN; + desc->req.data_ptrs[b_idx].last = 1; + desc->req.data_ptrs[b_idx].dma_ext = 0; + b_idx++; + desc->req.data_ptrs[b_idx].blkid = + ACC_DMA_BLKID_OUT_ENC; + desc->req.data_ptrs[b_idx].last = 1; + desc->req.data_ptrs[b_idx].dma_ext = 0; + } + /* Preset some fields of LDPC FCW */ + desc->req.fcw_ld.FCWversion = ACC_FCW_VER; + desc->req.fcw_ld.gain_i = 1; + desc->req.fcw_ld.gain_h = 1; + } + + q->lb_in = rte_zmalloc_socket(dev->device->driver->name, + RTE_CACHE_LINE_SIZE, + RTE_CACHE_LINE_SIZE, conf->socket); + if (q->lb_in == NULL) { + rte_bbdev_log(ERR, "Failed to allocate lb_in memory"); + rte_free(q); + return -ENOMEM; + } + q->lb_in_addr_iova = rte_malloc_virt2iova(q->lb_in); + q->lb_out = rte_zmalloc_socket(dev->device->driver->name, + RTE_CACHE_LINE_SIZE, + RTE_CACHE_LINE_SIZE, conf->socket); + if (q->lb_out == NULL) { + rte_bbdev_log(ERR, "Failed to allocate lb_out memory"); + rte_free(q->lb_in); + rte_free(q); + return -ENOMEM; + } + q->lb_out_addr_iova = rte_malloc_virt2iova(q->lb_out); + q->companion_ring_addr = rte_zmalloc_socket(dev->device->driver->name, + d->sw_ring_max_depth * sizeof(*q->companion_ring_addr), + RTE_CACHE_LINE_SIZE, conf->socket); + if (q->companion_ring_addr == NULL) { + rte_bbdev_log(ERR, "Failed to allocate companion_ring memory"); + rte_free(q->lb_in); + rte_free(q->lb_out); + rte_free(q); + return -ENOMEM; + } + + /* + * Software queue ring wraps synchronously with the HW when it reaches + * the boundary of the maximum allocated queue size, no matter what the + * sw queue size is. This wrapping is guarded by setting the wrap_mask + * to represent the maximum queue size as allocated at the time when + * the device has been setup (in configure()). + * + * The queue depth is set to the queue size value (conf->queue_size). + * This limits the occupancy of the queue at any point of time, so that + * the queue does not get swamped with enqueue requests. + */ + q->sw_ring_depth = conf->queue_size; + q->sw_ring_wrap_mask = d->sw_ring_max_depth - 1; + + q->op_type = conf->op_type; + + q_idx = acc200_find_free_queue_idx(dev, conf); + if (q_idx == -1) { + rte_free(q->companion_ring_addr); + rte_free(q->lb_in); + rte_free(q->lb_out); + rte_free(q); + return -1; + } + + q->qgrp_id = (q_idx >> ACC200_GRP_ID_SHIFT) & 0xF; + q->vf_id = (q_idx >> ACC200_VF_ID_SHIFT) & 0x3F; + q->aq_id = q_idx & 0xF; + q->aq_depth = 0; + if (conf->op_type == RTE_BBDEV_OP_TURBO_DEC) + q->aq_depth = (1 << d->acc_conf.q_ul_4g.aq_depth_log2); + else if (conf->op_type == RTE_BBDEV_OP_TURBO_ENC) + q->aq_depth = (1 << d->acc_conf.q_dl_4g.aq_depth_log2); + else if (conf->op_type == RTE_BBDEV_OP_LDPC_DEC) + q->aq_depth = (1 << d->acc_conf.q_ul_5g.aq_depth_log2); + else if (conf->op_type == RTE_BBDEV_OP_LDPC_ENC) + q->aq_depth = (1 << d->acc_conf.q_dl_5g.aq_depth_log2); + else if (conf->op_type == RTE_BBDEV_OP_FFT) + q->aq_depth = (1 << d->acc_conf.q_fft.aq_depth_log2); + + q->mmio_reg_enqueue = RTE_PTR_ADD(d->mmio_base, + queue_offset(d->pf_device, + q->vf_id, q->qgrp_id, q->aq_id)); + + rte_bbdev_log_debug( + "Setup dev%u q%u: qgrp_id=%u, vf_id=%u, aq_id=%u, aq_depth=%u, mmio_reg_enqueue=%p base %p\n", + dev->data->dev_id, queue_id, q->qgrp_id, q->vf_id, + q->aq_id, q->aq_depth, q->mmio_reg_enqueue, + d->mmio_base); + + dev->data->queues[queue_id].queue_private = q; + return 0; +} + + +static int +acc_queue_stop(struct rte_bbdev *dev, uint16_t queue_id) +{ + struct acc_queue *q; + q = dev->data->queues[queue_id].queue_private; + rte_bbdev_log(INFO, "Queue Stop %d H/T/D %d %d %x OpType %d", + queue_id, q->sw_ring_head, q->sw_ring_tail, + q->sw_ring_depth, q->op_type); + /* ignore all operations in flight and clear counters */ + q->sw_ring_tail = q->sw_ring_head; + q->aq_enqueued = 0; + q->aq_dequeued = 0; + dev->data->queues[queue_id].queue_stats.enqueued_count = 0; + dev->data->queues[queue_id].queue_stats.dequeued_count = 0; + dev->data->queues[queue_id].queue_stats.enqueue_err_count = 0; + dev->data->queues[queue_id].queue_stats.dequeue_err_count = 0; + dev->data->queues[queue_id].queue_stats.enqueue_warn_count = 0; + dev->data->queues[queue_id].queue_stats.dequeue_warn_count = 0; + return 0; +} + +/* Release ACC200 queue */ +static int +acc200_queue_release(struct rte_bbdev *dev, uint16_t q_id) +{ + struct acc_device *d = dev->data->dev_private; + struct acc_queue *q = dev->data->queues[q_id].queue_private; + + if (q != NULL) { + /* Mark the Queue as un-assigned */ + d->q_assigned_bit_map[q->qgrp_id] &= (0xFFFFFFFF - + (1 << q->aq_id)); + rte_free(q->companion_ring_addr); + rte_free(q->lb_in); + rte_free(q->lb_out); + rte_free(q); + dev->data->queues[q_id].queue_private = NULL; + } + + return 0; +} + /* Get ACC200 device info */ static void acc200_dev_info_get(struct rte_bbdev *dev, @@ -279,8 +646,12 @@ } static const struct rte_bbdev_ops acc200_bbdev_ops = { + .setup_queues = acc200_setup_queues, .close = acc200_dev_close, .info_get = acc200_dev_info_get, + .queue_setup = acc200_queue_setup, + .queue_release = acc200_queue_release, + .queue_stop = acc_queue_stop, }; /* ACC200 PCI PF address map */ -- 1.8.3.1