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 7FB3EA0543; Fri, 8 Jul 2022 02:16:35 +0200 (CEST) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 3CEB04282E; Fri, 8 Jul 2022 02:16:10 +0200 (CEST) Received: from mga17.intel.com (mga17.intel.com [192.55.52.151]) by mails.dpdk.org (Postfix) with ESMTP id 7C54840A7B for ; Fri, 8 Jul 2022 02:16:06 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1657239366; x=1688775366; h=from:to:cc:subject:date:message-id:in-reply-to: references; bh=fHeTvnQ79x1ALOavbyqJ6tKrFn3Pgc+402TadMQ1ieM=; b=hguhzIrGBoTXw5UCm9hw3OhftjwIMTRcFzo//3PvRztwhIs2TPuXWxN2 zxL+kUFcsONaesRNJKb0173YJIGif0IIdQaLuaV1EdLzNlDILuqbrWqAz RYokMmE70H0NMil9RVOMY9Izrg5m8C0xPYTRKbjtJqvGJ2zlG3dvfcGhS tizpoUWrLyC8qNCDs0cx7ypKo0QPOGnn7H3BZZsalvAOYZ9sAjkzcbJyG aiFNUrgCWjX4WOR1nb5VMleVBSsMaPVqy2Q5ANGB4y/ik0b1QH5H0xSuM hh20/xjQbuZufq0tc9DzWUGQzfu4dMfVk81ckSe0nZ9jwcLh4kM3XxvuW A==; X-IronPort-AV: E=McAfee;i="6400,9594,10401"; a="264563082" X-IronPort-AV: E=Sophos;i="5.92,253,1650956400"; d="scan'208";a="264563082" Received: from orsmga007.jf.intel.com ([10.7.209.58]) by fmsmga107.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 07 Jul 2022 17:16:04 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.92,253,1650956400"; d="scan'208";a="591387534" Received: from skx-5gnr-sc12-4.sc.intel.com ([172.25.69.210]) by orsmga007.jf.intel.com with ESMTP; 07 Jul 2022 17:16:03 -0700 From: Nicolas Chautru To: dev@dpdk.org, thomas@monjalon.net, gakhil@marvell.com, hemant.agrawal@nxp.com, trix@redhat.com Cc: maxime.coquelin@redhat.com, mdr@ashroe.eu, bruce.richardson@intel.com, david.marchand@redhat.com, stephen@networkplumber.org, Nicolas Chautru Subject: [PATCH v1 04/10] baseband/acc200: add queue configuration Date: Thu, 7 Jul 2022 17:01:37 -0700 Message-Id: <1657238503-143836-5-git-send-email-nicolas.chautru@intel.com> X-Mailer: git-send-email 1.8.3.1 In-Reply-To: <1657238503-143836-1-git-send-email-nicolas.chautru@intel.com> References: <1657238503-143836-1-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 Adding fuinction to create and configure queues for the device. Signed-off-by: Nicolas Chautru --- drivers/baseband/acc200/acc200_pmd.h | 62 ++++ drivers/baseband/acc200/rte_acc200_pmd.c | 506 ++++++++++++++++++++++++++++++- 2 files changed, 567 insertions(+), 1 deletion(-) diff --git a/drivers/baseband/acc200/acc200_pmd.h b/drivers/baseband/acc200/acc200_pmd.h index 91e0798..47ad00e 100644 --- a/drivers/baseband/acc200/acc200_pmd.h +++ b/drivers/baseband/acc200/acc200_pmd.h @@ -615,14 +615,76 @@ struct acc200_registry_addr { .pmon_ctrl_c = HWVfPmCCntrlRegVf, }; +/* Structure associated with each queue. */ +struct __rte_cache_aligned acc200_queue { + union acc200_dma_desc *ring_addr; /* Virtual address of sw ring */ + rte_iova_t ring_addr_iova; /* IOVA address of software ring */ + uint32_t sw_ring_head; /* software ring head */ + uint32_t sw_ring_tail; /* software ring tail */ + /* software ring size (descriptors, not bytes) */ + uint32_t sw_ring_depth; + /* mask used to wrap enqueued descriptors on the sw ring */ + uint32_t sw_ring_wrap_mask; + /* Virtual address of companion ring */ + struct acc200_ptrs *companion_ring_addr; + /* MMIO register used to enqueue descriptors */ + void *mmio_reg_enqueue; + uint8_t vf_id; /* VF ID (max = 63) */ + uint8_t qgrp_id; /* Queue Group ID */ + uint16_t aq_id; /* Atomic Queue ID */ + uint16_t aq_depth; /* Depth of atomic queue */ + uint32_t aq_enqueued; /* Count how many "batches" have been enqueued */ + uint32_t aq_dequeued; /* Count how many "batches" have been dequeued */ + uint32_t irq_enable; /* Enable ops dequeue interrupts if set to 1 */ + struct rte_mempool *fcw_mempool; /* FCW mempool */ + enum rte_bbdev_op_type op_type; /* Type of this Queue: TE or TD */ + /* Internal Buffers for loopback input */ + uint8_t *lb_in; + uint8_t *lb_out; + rte_iova_t lb_in_addr_iova; + rte_iova_t lb_out_addr_iova; + struct acc200_device *d; +}; /* Private data structure for each ACC200 device */ struct acc200_device { void *mmio_base; /**< Base address of MMIO registers (BAR0) */ + void *sw_rings_base; /* Base addr of un-aligned memory for sw rings */ + void *sw_rings; /* 64MBs of 64MB aligned memory for sw rings */ + rte_iova_t sw_rings_iova; /* IOVA address of sw_rings */ + /* Virtual address of the info memory routed to the this function under + * operation, whether it is PF or VF. + * HW may DMA information data at this location asynchronously + */ + union acc200_info_ring_data *info_ring; + + union acc200_harq_layout_data *harq_layout; + /* Virtual Info Ring head */ + uint16_t info_ring_head; + /* Number of bytes available for each queue in device, depending on + * how many queues are enabled with configure() + */ + uint32_t sw_ring_size; uint32_t ddr_size; /* Size in kB */ + uint32_t *tail_ptrs; /* Base address of response tail pointer buffer */ + rte_iova_t tail_ptr_iova; /* IOVA address of tail pointers */ + /* Max number of entries available for each queue in device, depending + * on how many queues are enabled with configure() + */ + uint32_t sw_ring_max_depth; struct rte_acc200_conf acc200_conf; /* ACC200 Initial configuration */ + /* Bitmap capturing which Queues have already been assigned */ + uint16_t q_assigned_bit_map[ACC200_NUM_QGRPS]; bool pf_device; /**< True if this is a PF ACC200 device */ bool configured; /**< True if this ACC200 device is configured */ }; +/** + * Structure with details about RTE_BBDEV_EVENT_DEQUEUE event. It's passed to + * the callback function. + */ +struct acc200_deq_intr_details { + uint16_t queue_id; +}; + #endif /* _RTE_ACC200_PMD_H_ */ diff --git a/drivers/baseband/acc200/rte_acc200_pmd.c b/drivers/baseband/acc200/rte_acc200_pmd.c index ce72654..ec082f1 100644 --- a/drivers/baseband/acc200/rte_acc200_pmd.c +++ b/drivers/baseband/acc200/rte_acc200_pmd.c @@ -29,6 +29,22 @@ RTE_LOG_REGISTER_DEFAULT(acc200_logtype, NOTICE); #endif +/* Write to MMIO register address */ +static inline void +mmio_write(void *addr, uint32_t value) +{ + *((volatile uint32_t *)(addr)) = rte_cpu_to_le_32(value); +} + +/* Write a register of a ACC200 device */ +static inline void +acc200_reg_write(struct acc200_device *d, uint32_t offset, uint32_t value) +{ + void *reg_addr = RTE_PTR_ADD(d->mmio_base, offset); + mmio_write(reg_addr, value); + usleep(ACC200_LONG_WAIT); +} + /* Read a register of a ACC200 device */ static inline uint32_t acc200_reg_read(struct acc200_device *d, uint32_t offset) @@ -39,6 +55,22 @@ return rte_le_to_cpu_32(ret); } +/* Basic Implementation of Log2 for exact 2^N */ +static inline uint32_t +log2_basic(uint32_t value) +{ + return (value == 0) ? 0 : rte_bsf32(value); +} + +/* Calculate memory alignment offset assuming alignment is 2^N */ +static inline uint32_t +calc_mem_alignment_offset(void *unaligned_virt_mem, uint32_t alignment) +{ + rte_iova_t unaligned_phy_mem = rte_malloc_virt2iova(unaligned_virt_mem); + return (uint32_t)(alignment - + (unaligned_phy_mem & (alignment-1))); +} + /* Calculate the offset of the enqueue register */ static inline uint32_t queue_offset(bool pf_device, uint8_t vf_id, uint8_t qgrp_id, uint16_t aq_id) @@ -230,16 +262,484 @@ acc200_conf->q_fft.aq_depth_log2); } +static void +free_base_addresses(void **base_addrs, int size) +{ + int i; + for (i = 0; i < size; i++) + rte_free(base_addrs[i]); +} + +static inline uint32_t +get_desc_len(void) +{ + return sizeof(union acc200_dma_desc); +} + +/* Allocate the 2 * 64MB block for the sw rings */ +static int +alloc_2x64mb_sw_rings_mem(struct rte_bbdev *dev, struct acc200_device *d, + int socket) +{ + uint32_t sw_ring_size = ACC200_SIZE_64MBYTE; + d->sw_rings_base = rte_zmalloc_socket(dev->device->driver->name, + 2 * sw_ring_size, RTE_CACHE_LINE_SIZE, socket); + if (d->sw_rings_base == NULL) { + rte_bbdev_log(ERR, "Failed to allocate memory for %s:%u", + dev->device->driver->name, + dev->data->dev_id); + return -ENOMEM; + } + uint32_t next_64mb_align_offset = calc_mem_alignment_offset( + d->sw_rings_base, ACC200_SIZE_64MBYTE); + d->sw_rings = RTE_PTR_ADD(d->sw_rings_base, next_64mb_align_offset); + d->sw_rings_iova = rte_malloc_virt2iova(d->sw_rings_base) + + next_64mb_align_offset; + d->sw_ring_size = ACC200_MAX_QUEUE_DEPTH * get_desc_len(); + d->sw_ring_max_depth = ACC200_MAX_QUEUE_DEPTH; + + return 0; +} + +/* Attempt to allocate minimised memory space for sw rings */ +static void +alloc_sw_rings_min_mem(struct rte_bbdev *dev, struct acc200_device *d, + uint16_t num_queues, int socket) +{ + rte_iova_t sw_rings_base_iova, next_64mb_align_addr_iova; + uint32_t next_64mb_align_offset; + rte_iova_t sw_ring_iova_end_addr; + void *base_addrs[ACC200_SW_RING_MEM_ALLOC_ATTEMPTS]; + void *sw_rings_base; + int i = 0; + uint32_t q_sw_ring_size = ACC200_MAX_QUEUE_DEPTH * get_desc_len(); + uint32_t dev_sw_ring_size = q_sw_ring_size * num_queues; + /* Free first in case this is a reconfiguration */ + rte_free(d->sw_rings_base); + + /* Find an aligned block of memory to store sw rings */ + while (i < ACC200_SW_RING_MEM_ALLOC_ATTEMPTS) { + /* + * sw_ring allocated memory is guaranteed to be aligned to + * q_sw_ring_size at the condition that the requested size is + * less than the page size + */ + sw_rings_base = rte_zmalloc_socket( + dev->device->driver->name, + dev_sw_ring_size, q_sw_ring_size, socket); + + if (sw_rings_base == NULL) { + rte_bbdev_log(ERR, + "Failed to allocate memory for %s:%u", + dev->device->driver->name, + dev->data->dev_id); + break; + } + + sw_rings_base_iova = rte_malloc_virt2iova(sw_rings_base); + next_64mb_align_offset = calc_mem_alignment_offset( + sw_rings_base, ACC200_SIZE_64MBYTE); + next_64mb_align_addr_iova = sw_rings_base_iova + + next_64mb_align_offset; + sw_ring_iova_end_addr = sw_rings_base_iova + dev_sw_ring_size; + + /* Check if the end of the sw ring memory block is before the + * start of next 64MB aligned mem address + */ + if (sw_ring_iova_end_addr < next_64mb_align_addr_iova) { + d->sw_rings_iova = sw_rings_base_iova; + d->sw_rings = sw_rings_base; + d->sw_rings_base = sw_rings_base; + d->sw_ring_size = q_sw_ring_size; + d->sw_ring_max_depth = ACC200_MAX_QUEUE_DEPTH; + break; + } + /* Store the address of the unaligned mem block */ + base_addrs[i] = sw_rings_base; + i++; + } + + /* Free all unaligned blocks of mem allocated in the loop */ + free_base_addresses(base_addrs, i); +} + +/* 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 acc200_device *d = dev->data->dev_private; + const struct acc200_registry_addr *reg_addr; + + if (d->pf_device && !d->acc200_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->acc200_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 & ~(ACC200_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++) { + acc200_reg_write(d, reg_addr->pmon_ctrl_a, value); + acc200_reg_write(d, reg_addr->pmon_ctrl_b, value); + acc200_reg_write(d, reg_addr->pmon_ctrl_c, value); + } + + /* Release AXI from PF */ + if (d->pf_device) + acc200_reg_write(d, HWPfDmaAxiControl, 1); + + acc200_reg_write(d, reg_addr->dma_ring_ul5g_hi, phys_high); + acc200_reg_write(d, reg_addr->dma_ring_ul5g_lo, phys_low); + acc200_reg_write(d, reg_addr->dma_ring_dl5g_hi, phys_high); + acc200_reg_write(d, reg_addr->dma_ring_dl5g_lo, phys_low); + acc200_reg_write(d, reg_addr->dma_ring_ul4g_hi, phys_high); + acc200_reg_write(d, reg_addr->dma_ring_ul4g_lo, phys_low); + acc200_reg_write(d, reg_addr->dma_ring_dl4g_hi, phys_high); + acc200_reg_write(d, reg_addr->dma_ring_dl4g_lo, phys_low); + acc200_reg_write(d, reg_addr->dma_ring_fft_hi, phys_high); + acc200_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); + acc200_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); + acc200_reg_write(d, reg_addr->tail_ptrs_ul5g_hi, phys_high); + acc200_reg_write(d, reg_addr->tail_ptrs_ul5g_lo, phys_low); + acc200_reg_write(d, reg_addr->tail_ptrs_dl5g_hi, phys_high); + acc200_reg_write(d, reg_addr->tail_ptrs_dl5g_lo, phys_low); + acc200_reg_write(d, reg_addr->tail_ptrs_ul4g_hi, phys_high); + acc200_reg_write(d, reg_addr->tail_ptrs_ul4g_lo, phys_low); + acc200_reg_write(d, reg_addr->tail_ptrs_dl4g_hi, phys_high); + acc200_reg_write(d, reg_addr->tail_ptrs_dl4g_lo, phys_low); + acc200_reg_write(d, reg_addr->tail_ptrs_fft_hi, phys_high); + acc200_reg_write(d, reg_addr->tail_ptrs_fft_lo, phys_low); + + if (d->harq_layout == NULL) + d->harq_layout = rte_zmalloc_socket("HARQ Layout", + ACC200_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 acc200_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(ACC200_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 acc200_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_acc200_queue_topology *qtop = NULL; + + qtopFromAcc(&qtop, acc, &(d->acc200_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 acc200_device *d = dev->data->dev_private; + struct acc200_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 acc200_dma_desc *desc = NULL; + unsigned int desc_idx, b_idx; + int fcw_len = (conf->op_type == RTE_BBDEV_OP_LDPC_ENC ? + ACC200_FCW_LE_BLEN : (conf->op_type == RTE_BBDEV_OP_TURBO_DEC ? + ACC200_FCW_TD_BLEN : (conf->op_type == RTE_BBDEV_OP_LDPC_DEC ? + ACC200_FCW_LD_BLEN : ACC200_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 = ACC200_DMA_DESC_TYPE; + desc->req.word1 = 0; /**< Timestamp */ + desc->req.word2 = 0; + desc->req.word3 = 0; + uint64_t fcw_offset = (desc_idx << 8) + ACC200_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 = ACC200_DMA_BLKID_FCW; + desc->req.data_ptrs[0].last = 0; + desc->req.data_ptrs[0].dma_ext = 0; + for (b_idx = 1; b_idx < ACC200_DMA_MAX_NUM_POINTERS - 1; + b_idx++) { + desc->req.data_ptrs[b_idx].blkid = ACC200_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 = + ACC200_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 = ACC200_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->acc200_conf.q_ul_4g.aq_depth_log2); + else if (conf->op_type == RTE_BBDEV_OP_TURBO_ENC) + q->aq_depth = (1 << d->acc200_conf.q_dl_4g.aq_depth_log2); + else if (conf->op_type == RTE_BBDEV_OP_LDPC_DEC) + q->aq_depth = (1 << d->acc200_conf.q_ul_5g.aq_depth_log2); + else if (conf->op_type == RTE_BBDEV_OP_LDPC_ENC) + q->aq_depth = (1 << d->acc200_conf.q_dl_5g.aq_depth_log2); + else if (conf->op_type == RTE_BBDEV_OP_FFT) + q->aq_depth = (1 << d->acc200_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 +acc200_queue_stop(struct rte_bbdev *dev, uint16_t queue_id) +{ + struct acc200_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 acc200_device *d = dev->data->dev_private; + struct acc200_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, @@ -289,8 +789,12 @@ } 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 = acc200_queue_stop, }; /* ACC200 PCI PF address map */ -- 1.8.3.1