[EXT] [PATCH v3 29/30] baseband/acc100: add workaround for deRM corner cases

[Akhil Goyal]

> Add function to support de-ratematch pre-processing for SW corner cases.
> 
Please add more meaningful description.
Title says adding workaround. You should explain the issue and then what is done in this patch.

> Signed-off-by: Hernan Vargas <hernan.vargas at intel.com>
> ---
>  drivers/baseband/acc/acc_common.h     |   8 ++
>  drivers/baseband/acc/meson.build      |  21 +++++
>  drivers/baseband/acc/rte_acc100_pmd.c | 108 +++++++++++++++++++++++++-
>  3 files changed, 134 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/baseband/acc/acc_common.h
> b/drivers/baseband/acc/acc_common.h
> index 5a9929c336..4b947280c9 100644
> --- a/drivers/baseband/acc/acc_common.h
> +++ b/drivers/baseband/acc/acc_common.h
> @@ -122,6 +122,14 @@
>  #define ACC_HARQ_ALIGN_64B          64
>  #define ACC_MAX_ZC                  384
> 
> +/* De-ratematch code rate limitation when padding is required */
> +#define ACC_LIM_03 2  /* 0.03 */
> +#define ACC_LIM_09 6  /* 0.09 */
> +#define ACC_LIM_14 9  /* 0.14 */
> +#define ACC_LIM_21 14 /* 0.21 */
> +#define ACC_LIM_31 20 /* 0.31 */
> +#define ACC_MAX_E (128 * 1024 - 2)
> +
>  /* Helper macro for logging */
>  #define rte_acc_log(level, fmt, ...) \
>  	rte_log(RTE_LOG_ ## level, RTE_LOG_NOTICE, fmt "\n", \
> diff --git a/drivers/baseband/acc/meson.build
> b/drivers/baseband/acc/meson.build
> index bece3a6e48..b147569d7e 100644
> --- a/drivers/baseband/acc/meson.build
> +++ b/drivers/baseband/acc/meson.build
> @@ -1,6 +1,27 @@
>  # SPDX-License-Identifier: BSD-3-Clause
>  # Copyright(c) 2020 Intel Corporation
> 
> +# Check for FlexRAN SDK libraries
> +dep_dec5g = dependency('flexran_sdk_ldpc_decoder_5gnr', required: false)
> +
> +if dep_dec5g.found()
> +    ext_deps += cc.find_library('libstdc++', required: true)
> +    ext_deps += cc.find_library('libirc', required: true)
> +    ext_deps += cc.find_library('libimf', required: true)
> +    ext_deps += cc.find_library('libipps', required: true)
> +    ext_deps += cc.find_library('libsvml', required: true)
> +    ext_deps += dep_dec5g
> +    ext_deps += dependency('flexran_sdk_ldpc_encoder_5gnr', required: true)
> +    ext_deps += dependency('flexran_sdk_LDPC_ratematch_5gnr', required:
> true)
> +    ext_deps += dependency('flexran_sdk_rate_dematching_5gnr', required:
> true)
> +    ext_deps += dependency('flexran_sdk_turbo', required: true)
> +    ext_deps += dependency('flexran_sdk_crc', required: true)
> +    ext_deps += dependency('flexran_sdk_rate_matching', required: true)
> +    ext_deps += dependency('flexran_sdk_common', required: true)
> +    cflags += ['-DRTE_BBDEV_SDK_AVX2']
> +    cflags += ['-DRTE_BBDEV_SDK_AVX512']
> +endif
> +
>  deps += ['bbdev', 'bus_pci']
> 
>  sources = files('rte_acc100_pmd.c', 'rte_acc200_pmd.c')
> diff --git a/drivers/baseband/acc/rte_acc100_pmd.c
> b/drivers/baseband/acc/rte_acc100_pmd.c
> index f93fd885a3..44fd0e9ad7 100644
> --- a/drivers/baseband/acc/rte_acc100_pmd.c
> +++ b/drivers/baseband/acc/rte_acc100_pmd.c
> @@ -24,6 +24,10 @@
>  #include "acc100_pmd.h"
>  #include "acc101_pmd.h"
> 
> +#ifdef RTE_BBDEV_SDK_AVX512
> +#include <phy_rate_dematching_5gnr.h>
> +#endif
> +
>  #ifdef RTE_LIBRTE_BBDEV_DEBUG
>  RTE_LOG_REGISTER_DEFAULT(acc100_logtype, DEBUG);
>  #else
> @@ -748,6 +752,14 @@ acc100_queue_setup(struct rte_bbdev *dev, uint16_t
> queue_id,
>  		ret = -ENOMEM;
>  		goto free_lb_out;
>  	}
> +	q->derm_buffer = rte_zmalloc_socket(dev->device->driver->name,
> +			RTE_BBDEV_TURBO_MAX_CB_SIZE * 10,
> +			RTE_CACHE_LINE_SIZE, conf->socket);
> +	if (q->derm_buffer == NULL) {
> +		rte_bbdev_log(ERR, "Failed to allocate derm_buffer memory");
> +		ret = -ENOMEM;
> +		goto free_companion_ring_addr;
> +	}
> 
>  	/*
>  	 * Software queue ring wraps synchronously with the HW when it
> reaches
> @@ -768,7 +780,7 @@ acc100_queue_setup(struct rte_bbdev *dev, uint16_t
> queue_id,
>  	q_idx = acc100_find_free_queue_idx(dev, conf);
>  	if (q_idx == -1) {
>  		ret = -EINVAL;
> -		goto free_companion_ring_addr;
> +		goto free_derm_buffer;
>  	}
> 
>  	q->qgrp_id = (q_idx >> ACC100_GRP_ID_SHIFT) & 0xF;
> @@ -796,6 +808,9 @@ acc100_queue_setup(struct rte_bbdev *dev, uint16_t
> queue_id,
>  	dev->data->queues[queue_id].queue_private = q;
>  	return 0;
> 
> +free_derm_buffer:
> +	rte_free(q->derm_buffer);
> +	q->derm_buffer = NULL;
>  free_companion_ring_addr:
>  	rte_free(q->companion_ring_addr);
>  	q->companion_ring_addr = NULL;
> @@ -882,6 +897,7 @@ acc100_queue_release(struct rte_bbdev *dev, uint16_t
> q_id)
>  		/* Mark the Queue as un-assigned */
>  		d->q_assigned_bit_map[q->qgrp_id] &= (0xFFFFFFFFFFFFFFFF -
>  				(uint64_t) (1 << q->aq_id));
> +		rte_free(q->derm_buffer);
>  		rte_free(q->companion_ring_addr);
>  		rte_free(q->lb_in);
>  		rte_free(q->lb_out);
> @@ -3102,10 +3118,44 @@ harq_loopback(struct acc_queue *q, struct
> rte_bbdev_dec_op *op,
>  	return 1;
>  }
> 
> +/** Assess whether a work around is required for the deRM corner cases */
> +static inline bool
> +derm_workaround_required(struct rte_bbdev_op_ldpc_dec *ldpc_dec, struct
> acc_queue *q)
> +{
> +	if (!is_acc100(q))
> +		return false;
> +	int32_t e = ldpc_dec->cb_params.e;
> +	int q_m = ldpc_dec->q_m;
> +	int z_c = ldpc_dec->z_c;
> +	int K = (ldpc_dec->basegraph == 1 ? ACC_K_ZC_1 : ACC_K_ZC_2)
> +			* z_c;
> +
> +	bool required = false;
> +	if (ldpc_dec->basegraph == 1) {
> +		if ((q_m == 4) && (z_c >= 320) && (e * ACC_LIM_31 > K * 64))
> +			required = true;
> +		else if ((e * ACC_LIM_21 > K * 64))
> +			required = true;
> +	} else {
> +		if (q_m <= 2) {
> +			if ((z_c >= 208) && (e * ACC_LIM_09 > K * 64))
> +				required = true;
> +			else if ((z_c < 208) && (e * ACC_LIM_03 > K * 64))
> +				required = true;
> +		} else if (e * ACC_LIM_14 > K * 64)
> +			required = true;
> +	}
> +	if (required)
> +		rte_bbdev_log(INFO, "Running deRM pre-processing in SW");
> +
> +	return required;
> +}
> +
>  /** Enqueue one decode operations for ACC100 device in CB mode */
>  static inline int
>  enqueue_ldpc_dec_one_op_cb(struct acc_queue *q, struct rte_bbdev_dec_op
> *op,
> -		uint16_t total_enqueued_cbs, bool same_op)
> +		uint16_t total_enqueued_cbs, bool same_op,
> +		struct rte_bbdev_queue_data *q_data)
>  {
>  	int ret;
>  	if (unlikely(check_bit(op->ldpc_dec.op_flags,
> @@ -3163,6 +3213,58 @@ enqueue_ldpc_dec_one_op_cb(struct acc_queue
> *q, struct rte_bbdev_dec_op *op,
>  	} else {
>  		struct acc_fcw_ld *fcw;
>  		uint32_t seg_total_left;
> +
> +		if (derm_workaround_required(&op->ldpc_dec, q)) {
> +			#ifdef RTE_BBDEV_SDK_AVX512
> +			struct rte_bbdev_op_ldpc_dec *dec = &op->ldpc_dec;
> +			struct bblib_rate_dematching_5gnr_request derm_req;
> +			struct bblib_rate_dematching_5gnr_response
> derm_resp;
> +			uint8_t *in;
> +
> +			/* Checking input size is matching with E */
> +			if (dec->input.data->data_len < dec->cb_params.e) {
> +				rte_bbdev_log(ERR, "deRM: Input size
> mismatch");
> +				return -EFAULT;
> +			}
> +			/* Run first deRM processing in SW */
> +			in = rte_pktmbuf_mtod_offset(dec->input.data, uint8_t
> *, in_offset);
> +			derm_req.p_in = (int8_t *) in;
> +			derm_req.p_harq = (int8_t *) q->derm_buffer;
> +			derm_req.base_graph = dec->basegraph;
> +			derm_req.zc = dec->z_c;
> +			derm_req.ncb = dec->n_cb;
> +			derm_req.e = dec->cb_params.e;
> +			if (derm_req.e > ACC_MAX_E) {
> +				rte_bbdev_log(WARNING,
> +						"deRM: E %d > %d max",
> +						derm_req.e, ACC_MAX_E);
> +				derm_req.e = ACC_MAX_E;
> +			}
> +			derm_req.k0 = 0; /* Actual output from SDK */
> +			derm_req.isretx = false;
> +			derm_req.rvid = dec->rv_index;
> +			derm_req.modulation_order = dec->q_m;
> +			derm_req.start_null_index =
> +					(dec->basegraph == 1 ? 22 : 10)
> +					* dec->z_c - 2 * dec->z_c
> +					- dec->n_filler;
> +			derm_req.num_of_null = dec->n_filler;
> +			bblib_rate_dematching_5gnr(&derm_req, &derm_resp);
> +			/* Force back the HW DeRM */
> +			dec->q_m = 1;
> +			dec->cb_params.e = dec->n_cb - dec->n_filler;
> +			dec->rv_index = 0;
> +			rte_memcpy(in, q->derm_buffer, dec->cb_params.e);
> +			/* Capture counter when pre-processing is used */
> +			q_data->queue_stats.enqueue_warn_count++;
> +			#else
> +			RTE_SET_USED(q_data);
> +			rte_bbdev_log(WARNING,
> +				"Corner case may require deRM pre-processing
> in SDK"
> +				);
> +			#endif
> +		}
> +
>  		fcw = &desc->req.fcw_ld;
>  		q->d->fcw_ld_fill(op, fcw, harq_layout);
> 
> @@ -3734,7 +3836,7 @@ acc100_enqueue_ldpc_dec_cb(struct
> rte_bbdev_queue_data *q_data,
>  			ops[i]->ldpc_dec.n_cb, ops[i]->ldpc_dec.q_m,
>  			ops[i]->ldpc_dec.n_filler, ops[i]-
> >ldpc_dec.cb_params.e,
>  			same_op);
> -		ret = enqueue_ldpc_dec_one_op_cb(q, ops[i], i, same_op);
> +		ret = enqueue_ldpc_dec_one_op_cb(q, ops[i], i, same_op,
> q_data);
>  		if (ret < 0) {
>  			acc_enqueue_invalid(q_data);
>  			break;
> --
> 2.37.1