[PATCH v1 3/9] baseband/acc101: add info get function

[Nicolas Chautru <nicolas.chautru@intel.com>]

Add the info get function to allow to query
device null capabilities.
Linking to bbdev-test.

Signed-off-by: Nicolas Chautru <nicolas.chautru@intel.com>
---
 app/test-bbdev/meson.build               |   3 +
 drivers/baseband/acc101/rte_acc101_cfg.h |  96 +++++++++++++
 drivers/baseband/acc101/rte_acc101_pmd.c | 226 +++++++++++++++++++++++++++++++
 drivers/baseband/acc101/rte_acc101_pmd.h |   2 +
 4 files changed, 327 insertions(+)
 create mode 100644 drivers/baseband/acc101/rte_acc101_cfg.h

diff --git a/app/test-bbdev/meson.build b/app/test-bbdev/meson.build
index 76d4c26..9cbee5a 100644
--- a/app/test-bbdev/meson.build
+++ b/app/test-bbdev/meson.build
@@ -23,6 +23,9 @@ endif
 if dpdk_conf.has('RTE_BASEBAND_ACC100')
     deps += ['baseband_acc100']
 endif
+if dpdk_conf.has('RTE_BASEBAND_ACC101')
+    deps += ['baseband_acc101']
+endif
 if dpdk_conf.has('RTE_LIBRTE_PMD_BBDEV_LA12XX')
     deps += ['baseband_la12xx']
 endif
diff --git a/drivers/baseband/acc101/rte_acc101_cfg.h b/drivers/baseband/acc101/rte_acc101_cfg.h
new file mode 100644
index 0000000..4881cd6
--- /dev/null
+++ b/drivers/baseband/acc101/rte_acc101_cfg.h
@@ -0,0 +1,96 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2020 Intel Corporation
+ */
+
+#ifndef _RTE_ACC101_CFG_H_
+#define _RTE_ACC101_CFG_H_
+
+/**
+ * @file rte_acc101_cfg.h
+ *
+ * Functions for configuring ACC101 HW, exposed directly to applications.
+ * Configuration related to encoding/decoding is done through the
+ * librte_bbdev library.
+ *
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice
+ */
+
+#include <stdint.h>
+#include <stdbool.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+/**< Number of Virtual Functions ACC101 supports */
+#define RTE_ACC101_NUM_VFS 16
+
+/**
+ * Definition of Queue Topology for ACC101 Configuration
+ * Some level of details is abstracted out to expose a clean interface
+ * given that comprehensive flexibility is not required
+ */
+struct rte_acc101_queue_topology {
+	/** Number of QGroups in incremental order of priority */
+	uint16_t num_qgroups;
+	/**
+	 * All QGroups have the same number of AQs here.
+	 * Note : Could be made a 16-array if more flexibility is really
+	 * required
+	 */
+	uint16_t num_aqs_per_groups;
+	/**
+	 * Depth of the AQs is the same of all QGroups here. Log2 Enum : 2^N
+	 * Note : Could be made a 16-array if more flexibility is really
+	 * required
+	 */
+	uint16_t aq_depth_log2;
+	/**
+	 * Index of the first Queue Group Index - assuming contiguity
+	 * Initialized as -1
+	 */
+	int8_t first_qgroup_index;
+};
+
+/**
+ * Definition of Arbitration related parameters for ACC101 Configuration
+ */
+struct rte_acc101_arbitration {
+	/** Default Weight for VF Fairness Arbitration */
+	uint16_t round_robin_weight;
+	uint32_t gbr_threshold1; /**< Guaranteed Bitrate Threshold 1 */
+	uint32_t gbr_threshold2; /**< Guaranteed Bitrate Threshold 2 */
+};
+
+/**
+ * Structure to pass ACC101 configuration.
+ * Note: all VF Bundles will have the same configuration.
+ */
+struct rte_acc101_conf {
+	bool pf_mode_en; /**< 1 if PF is used for dataplane, 0 for VFs */
+	/** 1 if input '1' bit is represented by a positive LLR value, 0 if '1'
+	 * bit is represented by a negative value.
+	 */
+	bool input_pos_llr_1_bit;
+	/** 1 if output '1' bit is represented by a positive value, 0 if '1'
+	 * bit is represented by a negative value.
+	 */
+	bool output_pos_llr_1_bit;
+	uint16_t num_vf_bundles; /**< Number of VF bundles to setup */
+	/** Queue topology for each operation type */
+	struct rte_acc101_queue_topology q_ul_4g;
+	struct rte_acc101_queue_topology q_dl_4g;
+	struct rte_acc101_queue_topology q_ul_5g;
+	struct rte_acc101_queue_topology q_dl_5g;
+	/** Arbitration configuration for each operation type */
+	struct rte_acc101_arbitration arb_ul_4g[RTE_ACC101_NUM_VFS];
+	struct rte_acc101_arbitration arb_dl_4g[RTE_ACC101_NUM_VFS];
+	struct rte_acc101_arbitration arb_ul_5g[RTE_ACC101_NUM_VFS];
+	struct rte_acc101_arbitration arb_dl_5g[RTE_ACC101_NUM_VFS];
+};
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_ACC101_CFG_H_ */
diff --git a/drivers/baseband/acc101/rte_acc101_pmd.c b/drivers/baseband/acc101/rte_acc101_pmd.c
index dff3834..9518a9e 100644
--- a/drivers/baseband/acc101/rte_acc101_pmd.c
+++ b/drivers/baseband/acc101/rte_acc101_pmd.c
@@ -29,6 +29,187 @@
 RTE_LOG_REGISTER_DEFAULT(acc101_logtype, NOTICE);
 #endif
 
+/* Read a register of a ACC101 device */
+static inline uint32_t
+acc101_reg_read(struct acc101_device *d, uint32_t offset)
+{
+	void *reg_addr = RTE_PTR_ADD(d->mmio_base, offset);
+	uint32_t ret = *((volatile uint32_t *)(reg_addr));
+	return rte_le_to_cpu_32(ret);
+}
+
+/* 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)
+{
+	if (pf_device)
+		return ((vf_id << 12) + (qgrp_id << 7) + (aq_id << 3) +
+				HWPfQmgrIngressAq);
+	else
+		return ((qgrp_id << 7) + (aq_id << 3) +
+				HWVfQmgrIngressAq);
+}
+
+enum {UL_4G = 0, UL_5G, DL_4G, DL_5G, NUM_ACC};
+
+/* Return the queue topology for a Queue Group Index */
+static inline void
+qtopFromAcc(struct rte_acc101_queue_topology **qtop, int acc_enum,
+		struct rte_acc101_conf *acc101_conf)
+{
+	struct rte_acc101_queue_topology *p_qtop;
+	p_qtop = NULL;
+	switch (acc_enum) {
+	case UL_4G:
+		p_qtop = &(acc101_conf->q_ul_4g);
+		break;
+	case UL_5G:
+		p_qtop = &(acc101_conf->q_ul_5g);
+		break;
+	case DL_4G:
+		p_qtop = &(acc101_conf->q_dl_4g);
+		break;
+	case DL_5G:
+		p_qtop = &(acc101_conf->q_dl_5g);
+		break;
+	default:
+		/* NOTREACHED */
+		rte_bbdev_log(ERR, "Unexpected error evaluating qtopFromAcc");
+		break;
+	}
+	*qtop = p_qtop;
+}
+
+static void
+initQTop(struct rte_acc101_conf *acc101_conf)
+{
+	acc101_conf->q_ul_4g.num_aqs_per_groups = 0;
+	acc101_conf->q_ul_4g.num_qgroups = 0;
+	acc101_conf->q_ul_4g.first_qgroup_index = -1;
+	acc101_conf->q_ul_5g.num_aqs_per_groups = 0;
+	acc101_conf->q_ul_5g.num_qgroups = 0;
+	acc101_conf->q_ul_5g.first_qgroup_index = -1;
+	acc101_conf->q_dl_4g.num_aqs_per_groups = 0;
+	acc101_conf->q_dl_4g.num_qgroups = 0;
+	acc101_conf->q_dl_4g.first_qgroup_index = -1;
+	acc101_conf->q_dl_5g.num_aqs_per_groups = 0;
+	acc101_conf->q_dl_5g.num_qgroups = 0;
+	acc101_conf->q_dl_5g.first_qgroup_index = -1;
+}
+
+static inline void
+updateQtop(uint8_t acc, uint8_t qg, struct rte_acc101_conf *acc101_conf,
+		struct acc101_device *d) {
+	uint32_t reg;
+	struct rte_acc101_queue_topology *q_top = NULL;
+	qtopFromAcc(&q_top, acc, acc101_conf);
+	if (unlikely(q_top == NULL))
+		return;
+	uint16_t aq;
+	q_top->num_qgroups++;
+	if (q_top->first_qgroup_index == -1) {
+		q_top->first_qgroup_index = qg;
+		/* Can be optimized to assume all are enabled by default */
+		reg = acc101_reg_read(d, queue_offset(d->pf_device,
+				0, qg, ACC101_NUM_AQS - 1));
+		if (reg & ACC101_QUEUE_ENABLE) {
+			q_top->num_aqs_per_groups = ACC101_NUM_AQS;
+			return;
+		}
+		q_top->num_aqs_per_groups = 0;
+		for (aq = 0; aq < ACC101_NUM_AQS; aq++) {
+			reg = acc101_reg_read(d, queue_offset(d->pf_device,
+					0, qg, aq));
+			if (reg & ACC101_QUEUE_ENABLE)
+				q_top->num_aqs_per_groups++;
+		}
+	}
+}
+
+/* Fetch configuration enabled for the PF/VF using MMIO Read (slow) */
+static inline void
+fetch_acc101_config(struct rte_bbdev *dev)
+{
+	struct acc101_device *d = dev->data->dev_private;
+	struct rte_acc101_conf *acc101_conf = &d->acc101_conf;
+	const struct acc101_registry_addr *reg_addr;
+	uint8_t acc, qg;
+	uint32_t reg, reg_aq, reg_len0, reg_len1;
+	uint32_t reg_mode;
+
+	/* No need to retrieve the configuration is already done */
+	if (d->configured)
+		return;
+
+	/* Choose correct registry addresses for the device type */
+	if (d->pf_device)
+		reg_addr = &pf_reg_addr;
+	else
+		reg_addr = &vf_reg_addr;
+
+	d->ddr_size = (1 + acc101_reg_read(d, reg_addr->ddr_range)) << 10;
+
+	/* Single VF Bundle by VF */
+	acc101_conf->num_vf_bundles = 1;
+	initQTop(acc101_conf);
+
+	struct rte_acc101_queue_topology *q_top = NULL;
+	int qman_func_id[ACC101_NUM_ACCS] = {ACC101_ACCMAP_0, ACC101_ACCMAP_1,
+			ACC101_ACCMAP_2, ACC101_ACCMAP_3, ACC101_ACCMAP_4};
+	reg = acc101_reg_read(d, reg_addr->qman_group_func);
+	for (qg = 0; qg < ACC101_NUM_QGRPS_PER_WORD; qg++) {
+		reg_aq = acc101_reg_read(d,
+				queue_offset(d->pf_device, 0, qg, 0));
+		if (reg_aq & ACC101_QUEUE_ENABLE) {
+			uint32_t idx = (reg >> (qg * 4)) & 0x7;
+			if (idx < ACC101_NUM_ACCS) {
+				acc = qman_func_id[idx];
+				updateQtop(acc, qg, acc101_conf, d);
+			}
+		}
+	}
+
+	/* Check the depth of the AQs*/
+	reg_len0 = acc101_reg_read(d, reg_addr->depth_log0_offset);
+	reg_len1 = acc101_reg_read(d, reg_addr->depth_log1_offset);
+	for (acc = 0; acc < NUM_ACC; acc++) {
+		qtopFromAcc(&q_top, acc, acc101_conf);
+		if (q_top->first_qgroup_index < ACC101_NUM_QGRPS_PER_WORD)
+			q_top->aq_depth_log2 = (reg_len0 >>
+					(q_top->first_qgroup_index * 4))
+					& 0xF;
+		else
+			q_top->aq_depth_log2 = (reg_len1 >>
+					((q_top->first_qgroup_index -
+					ACC101_NUM_QGRPS_PER_WORD) * 4))
+					& 0xF;
+	}
+
+	/* Read PF mode */
+	if (d->pf_device) {
+		reg_mode = acc101_reg_read(d, HWPfHiPfMode);
+		acc101_conf->pf_mode_en = (reg_mode == ACC101_PF_VAL) ? 1 : 0;
+	}
+
+	rte_bbdev_log_debug(
+			"%s Config LLR SIGN IN/OUT %s %s QG %u %u %u %u AQ %u %u %u %u Len %u %u %u %u\n",
+			(d->pf_device) ? "PF" : "VF",
+			(acc101_conf->input_pos_llr_1_bit) ? "POS" : "NEG",
+			(acc101_conf->output_pos_llr_1_bit) ? "POS" : "NEG",
+			acc101_conf->q_ul_4g.num_qgroups,
+			acc101_conf->q_dl_4g.num_qgroups,
+			acc101_conf->q_ul_5g.num_qgroups,
+			acc101_conf->q_dl_5g.num_qgroups,
+			acc101_conf->q_ul_4g.num_aqs_per_groups,
+			acc101_conf->q_dl_4g.num_aqs_per_groups,
+			acc101_conf->q_ul_5g.num_aqs_per_groups,
+			acc101_conf->q_dl_5g.num_aqs_per_groups,
+			acc101_conf->q_ul_4g.aq_depth_log2,
+			acc101_conf->q_dl_4g.aq_depth_log2,
+			acc101_conf->q_ul_5g.aq_depth_log2,
+			acc101_conf->q_dl_5g.aq_depth_log2);
+}
+
 /* Free memory used for software rings */
 static int
 acc101_dev_close(struct rte_bbdev *dev)
@@ -37,8 +218,53 @@
 	return 0;
 }
 
+/* Get ACC101 device info */
+static void
+acc101_dev_info_get(struct rte_bbdev *dev,
+		struct rte_bbdev_driver_info *dev_info)
+{
+	struct acc101_device *d = dev->data->dev_private;
+	static const struct rte_bbdev_op_cap bbdev_capabilities[] = {
+		RTE_BBDEV_END_OF_CAPABILITIES_LIST()
+	};
+
+	static struct rte_bbdev_queue_conf default_queue_conf;
+	default_queue_conf.socket = dev->data->socket_id;
+	default_queue_conf.queue_size = ACC101_MAX_QUEUE_DEPTH;
+
+	dev_info->driver_name = dev->device->driver->name;
+
+	/* Read and save the populated config from ACC101 registers */
+	fetch_acc101_config(dev);
+	/* This isn't ideal because it reports the maximum number of queues but
+	 * does not provide info on how many can be uplink/downlink or different
+	 * priorities
+	 */
+	dev_info->max_num_queues =
+			d->acc101_conf.q_dl_5g.num_aqs_per_groups *
+			d->acc101_conf.q_dl_5g.num_qgroups +
+			d->acc101_conf.q_ul_5g.num_aqs_per_groups *
+			d->acc101_conf.q_ul_5g.num_qgroups +
+			d->acc101_conf.q_dl_4g.num_aqs_per_groups *
+			d->acc101_conf.q_dl_4g.num_qgroups +
+			d->acc101_conf.q_ul_4g.num_aqs_per_groups *
+			d->acc101_conf.q_ul_4g.num_qgroups;
+	dev_info->queue_size_lim = ACC101_MAX_QUEUE_DEPTH;
+	dev_info->hardware_accelerated = true;
+	dev_info->max_dl_queue_priority =
+			d->acc101_conf.q_dl_4g.num_qgroups - 1;
+	dev_info->max_ul_queue_priority =
+			d->acc101_conf.q_ul_4g.num_qgroups - 1;
+	dev_info->default_queue_conf = default_queue_conf;
+	dev_info->cpu_flag_reqs = NULL;
+	dev_info->min_alignment = 64;
+	dev_info->capabilities = bbdev_capabilities;
+	dev_info->harq_buffer_size = 0;
+}
+
 static const struct rte_bbdev_ops acc101_bbdev_ops = {
 	.close = acc101_dev_close,
+	.info_get = acc101_dev_info_get,
 };
 
 /* ACC101 PCI PF address map */
diff --git a/drivers/baseband/acc101/rte_acc101_pmd.h b/drivers/baseband/acc101/rte_acc101_pmd.h
index 66641f3..9c0e711 100644
--- a/drivers/baseband/acc101/rte_acc101_pmd.h
+++ b/drivers/baseband/acc101/rte_acc101_pmd.h
@@ -7,6 +7,7 @@
 
 #include "acc101_pf_enum.h"
 #include "acc101_vf_enum.h"
+#include "rte_acc101_cfg.h"
 
 /* Helper macro for logging */
 #define rte_bbdev_log(level, fmt, ...) \
@@ -497,6 +498,7 @@ struct acc101_device {
 	 * on how many queues are enabled with configure()
 	 */
 	uint32_t sw_ring_max_depth;
+	struct rte_acc101_conf acc101_conf; /* ACC101 Initial configuration */
 	/* Bitmap capturing which Queues have already been assigned */
 	uint16_t q_assigned_bit_map[ACC101_NUM_QGRPS];
 	bool pf_device; /**< True if this is a PF ACC101 device */
-- 
1.8.3.1