[PATCH v2 16/37] baseband/acc100: add ring companion address

[Hernan Vargas <hernan.vargas@intel.com>]

Store the virtual address of companion ring as part of queue
information. Use this address to calculate the op address.

Signed-off-by: Hernan Vargas <hernan.vargas@intel.com>
---
 drivers/baseband/acc100/acc100_pmd.h     |  12 ++
 drivers/baseband/acc100/rte_acc100_pmd.c | 143 ++++++++++++++---------
 2 files changed, 100 insertions(+), 55 deletions(-)

diff --git a/drivers/baseband/acc100/acc100_pmd.h b/drivers/baseband/acc100/acc100_pmd.h
index c98a182be6..20157e5886 100644
--- a/drivers/baseband/acc100/acc100_pmd.h
+++ b/drivers/baseband/acc100/acc100_pmd.h
@@ -126,6 +126,7 @@
 #define ACC100_5GUL_SIZE_0                16
 #define ACC100_5GUL_SIZE_1                40
 #define ACC100_5GUL_OFFSET_0              36
+#define ACC100_COMPANION_PTRS             8
 
 #define ACC100_FCW_VER         2
 #define ACC100_MUX_5GDL_DESC   6
@@ -375,6 +376,15 @@ struct __rte_packed acc100_fcw_le {
 	uint32_t res8;
 };
 
+struct __rte_packed acc100_pad_ptr {
+	void *op_addr;
+	uint64_t pad1;  /* pad to 64 bits */
+};
+
+struct __rte_packed acc100_ptrs {
+	struct acc100_pad_ptr ptr[ACC100_COMPANION_PTRS];
+};
+
 /* ACC100 DMA Request Descriptor */
 struct __rte_packed acc100_dma_req_desc {
 	union {
@@ -568,6 +578,8 @@ struct __rte_cache_aligned acc100_queue {
 	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 acc100_ptrs *companion_ring_addr;
 	/* MMIO register used to enqueue descriptors */
 	void *mmio_reg_enqueue;
 	uint8_t vf_id;  /* VF ID (max = 63) */
diff --git a/drivers/baseband/acc100/rte_acc100_pmd.c b/drivers/baseband/acc100/rte_acc100_pmd.c
index 69c0714a37..ea54152856 100644
--- a/drivers/baseband/acc100/rte_acc100_pmd.c
+++ b/drivers/baseband/acc100/rte_acc100_pmd.c
@@ -913,6 +913,17 @@ acc100_queue_setup(struct rte_bbdev *dev, uint16_t queue_id,
 		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->derm_buffer);
+		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
@@ -932,6 +943,7 @@ acc100_queue_setup(struct rte_bbdev *dev, uint16_t queue_id,
 
 	q_idx = acc100_find_free_queue_idx(dev, conf);
 	if (q_idx == -1) {
+		rte_free(q->companion_ring_addr);
 		rte_free(q->derm_buffer);
 		rte_free(q->lb_in);
 		rte_free(q->lb_out);
@@ -970,6 +982,7 @@ 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] &= (0xFFFFFFFF -
 				(1 << q->aq_id));
+		rte_free(q->companion_ring_addr);
 		rte_free(q->derm_buffer);
 		rte_free(q->lb_in);
 		rte_free(q->lb_out);
@@ -2889,6 +2902,10 @@ enqueue_ldpc_enc_n_op_cb(struct acc100_queue *q, struct rte_bbdev_enc_op **ops,
 	}
 
 	desc->req.op_addr = ops[0];
+	/* Keep track of pointers even when multiplexed in single descriptor */
+	struct acc100_ptrs *context_ptrs = q->companion_ring_addr + desc_idx;
+	for (i = 0; i < num; i++)
+		context_ptrs->ptr[i].op_addr = ops[i];
 
 #ifdef RTE_LIBRTE_BBDEV_DEBUG
 	rte_memdump(stderr, "FCW", &desc->req.fcw_le,
@@ -4517,15 +4534,16 @@ acc100_enqueue_ldpc_dec(struct rte_bbdev_queue_data *q_data,
 /* Dequeue one encode operations from ACC100 device in CB mode */
 static inline int
 dequeue_enc_one_op_cb(struct acc100_queue *q, struct rte_bbdev_enc_op **ref_op,
-		uint16_t total_dequeued_cbs, uint32_t *aq_dequeued)
+		uint16_t *dequeued_ops, uint32_t *aq_dequeued,
+		uint16_t *dequeued_descs)
 {
 	union acc100_dma_desc *desc, atom_desc;
 	union acc100_dma_rsp_desc rsp;
 	struct rte_bbdev_enc_op *op;
 	int i;
-
-	desc = q->ring_addr + ((q->sw_ring_tail + total_dequeued_cbs)
+	int desc_idx = ((q->sw_ring_tail + *dequeued_descs)
 			& q->sw_ring_wrap_mask);
+	desc = q->ring_addr + desc_idx;
 	atom_desc.atom_hdr = __atomic_load_n((uint64_t *)desc,
 			__ATOMIC_RELAXED);
 
@@ -4534,7 +4552,8 @@ dequeue_enc_one_op_cb(struct acc100_queue *q, struct rte_bbdev_enc_op **ref_op,
 		return -1;
 
 	rsp.val = atom_desc.rsp.val;
-	rte_bbdev_log_debug("Resp. desc %p: %x", desc, rsp.val);
+	rte_bbdev_log_debug("Resp. desc %p: %x num %d\n",
+			desc, rsp.val, desc->req.numCBs);
 
 	/* Dequeue */
 	op = desc->req.op_addr;
@@ -4552,27 +4571,32 @@ dequeue_enc_one_op_cb(struct acc100_queue *q, struct rte_bbdev_enc_op **ref_op,
 	desc->rsp.add_info_0 = 0; /*Reserved bits */
 	desc->rsp.add_info_1 = 0; /*Reserved bits */
 
-	/* Flag that the muxing cause loss of opaque data */
-	op->opaque_data = (void *)-1;
-	for (i = 0 ; i < desc->req.numCBs; i++)
-		ref_op[i] = op;
+	ref_op[0] = op;
+	struct acc100_ptrs *context_ptrs = q->companion_ring_addr + desc_idx;
+	for (i = 1 ; i < desc->req.numCBs; i++)
+		ref_op[i] = context_ptrs->ptr[i].op_addr;
 
-	/* One CB (op) was successfully dequeued */
+	/* One op was successfully dequeued */
+	(*dequeued_descs)++;
+	*dequeued_ops += desc->req.numCBs;
 	return desc->req.numCBs;
 }
 
-/* Dequeue one encode operations from ACC100 device in TB mode */
+/* Dequeue one LDPC encode operations from ACC100 device in TB mode
+ * That operation may cover multiple descriptors
+ */
 static inline int
 dequeue_enc_one_op_tb(struct acc100_queue *q, struct rte_bbdev_enc_op **ref_op,
-		uint16_t total_dequeued_cbs, uint32_t *aq_dequeued)
+		uint16_t *dequeued_ops, uint32_t *aq_dequeued,
+		uint16_t *dequeued_descs)
 {
 	union acc100_dma_desc *desc, *last_desc, atom_desc;
 	union acc100_dma_rsp_desc rsp;
 	struct rte_bbdev_enc_op *op;
 	uint8_t i = 0;
-	uint16_t current_dequeued_cbs = 0, cbs_in_tb;
+	uint16_t current_dequeued_descs = 0, descs_in_tb;
 
-	desc = q->ring_addr + ((q->sw_ring_tail + total_dequeued_cbs)
+	desc = q->ring_addr + ((q->sw_ring_tail + *dequeued_descs)
 			& q->sw_ring_wrap_mask);
 	atom_desc.atom_hdr = __atomic_load_n((uint64_t *)desc,
 			__ATOMIC_RELAXED);
@@ -4582,10 +4606,10 @@ dequeue_enc_one_op_tb(struct acc100_queue *q, struct rte_bbdev_enc_op **ref_op,
 		return -1;
 
 	/* Get number of CBs in dequeued TB */
-	cbs_in_tb = desc->req.cbs_in_tb;
+	descs_in_tb = desc->req.cbs_in_tb;
 	/* Get last CB */
 	last_desc = q->ring_addr + ((q->sw_ring_tail
-			+ total_dequeued_cbs + cbs_in_tb - 1)
+			+ *dequeued_descs + descs_in_tb - 1)
 			& q->sw_ring_wrap_mask);
 	/* Check if last CB in TB is ready to dequeue (and thus
 	 * the whole TB) - checking sdone bit. If not return.
@@ -4601,15 +4625,17 @@ dequeue_enc_one_op_tb(struct acc100_queue *q, struct rte_bbdev_enc_op **ref_op,
 	/* Clearing status, it will be set based on response */
 	op->status = 0;
 
-	while (i < cbs_in_tb) {
+	while (i < descs_in_tb) {
 		desc = q->ring_addr + ((q->sw_ring_tail
-				+ total_dequeued_cbs)
+				+ *dequeued_descs)
 				& q->sw_ring_wrap_mask);
 		atom_desc.atom_hdr = __atomic_load_n((uint64_t *)desc,
 				__ATOMIC_RELAXED);
 		rsp.val = atom_desc.rsp.val;
-		rte_bbdev_log_debug("Resp. desc %p: %x", desc,
-				rsp.val);
+		rte_bbdev_log_debug("Resp. desc %p: %x descs %d cbs %d\n",
+				desc,
+				rsp.val, descs_in_tb,
+				desc->req.numCBs);
 
 		op->status |= ((rsp.dma_err) ? (1 << RTE_BBDEV_DRV_ERROR) : 0);
 		op->status |= ((rsp.fcw_err) ? (1 << RTE_BBDEV_DRV_ERROR) : 0);
@@ -4621,14 +4647,14 @@ dequeue_enc_one_op_tb(struct acc100_queue *q, struct rte_bbdev_enc_op **ref_op,
 		desc->rsp.val = ACC100_DMA_DESC_TYPE;
 		desc->rsp.add_info_0 = 0;
 		desc->rsp.add_info_1 = 0;
-		total_dequeued_cbs++;
-		current_dequeued_cbs++;
+		(*dequeued_descs)++;
+		current_dequeued_descs++;
 		i++;
 	}
 
 	*ref_op = op;
-
-	return current_dequeued_cbs;
+	(*dequeued_ops)++;
+	return current_dequeued_descs;
 }
 
 /* Dequeue one decode operation from ACC100 device in CB mode */
@@ -4824,12 +4850,11 @@ acc100_dequeue_enc(struct rte_bbdev_queue_data *q_data,
 		struct rte_bbdev_enc_op **ops, uint16_t num)
 {
 	struct acc100_queue *q = q_data->queue_private;
-	uint16_t dequeue_num;
 	uint32_t avail = acc100_ring_avail_deq(q);
 	uint32_t aq_dequeued = 0;
-	uint16_t i, dequeued_cbs = 0;
-	struct rte_bbdev_enc_op *op;
+	uint16_t i, dequeued_ops = 0, dequeued_descs = 0;
 	int ret;
+	struct rte_bbdev_enc_op *op;
 	if (avail == 0)
 		return 0;
 #ifdef RTE_LIBRTE_BBDEV_DEBUG
@@ -4838,31 +4863,34 @@ acc100_dequeue_enc(struct rte_bbdev_queue_data *q_data,
 		return 0;
 	}
 #endif
+	op = (q->ring_addr + (q->sw_ring_tail &
+			q->sw_ring_wrap_mask))->req.op_addr;
+	if (unlikely(ops == NULL || op == NULL))
+		return 0;
 
-	dequeue_num = (avail < num) ? avail : num;
+	int cbm = op->turbo_enc.code_block_mode;
 
-	for (i = 0; i < dequeue_num; ++i) {
-		op = (q->ring_addr + ((q->sw_ring_tail + dequeued_cbs)
-			& q->sw_ring_wrap_mask))->req.op_addr;
-		if (op->turbo_enc.code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK)
-			ret = dequeue_enc_one_op_tb(q, &ops[i], dequeued_cbs,
-					&aq_dequeued);
+	for (i = 0; i < num; i++) {
+		if (cbm == RTE_BBDEV_TRANSPORT_BLOCK)
+			ret = dequeue_enc_one_op_tb(q, &ops[dequeued_ops],
+					&dequeued_ops, &aq_dequeued,
+					&dequeued_descs);
 		else
-			ret = dequeue_enc_one_op_cb(q, &ops[i], dequeued_cbs,
-					&aq_dequeued);
-
+			ret = dequeue_enc_one_op_cb(q, &ops[dequeued_ops],
+					&dequeued_ops, &aq_dequeued,
+					&dequeued_descs);
 		if (ret < 0)
 			break;
-		dequeued_cbs += ret;
+		if (dequeued_ops >= num)
+			break;
 	}
 
 	q->aq_dequeued += aq_dequeued;
-	q->sw_ring_tail += dequeued_cbs;
+	q->sw_ring_tail += dequeued_descs;
 
 	/* Update enqueue stats */
-	q_data->queue_stats.dequeued_count += i;
-
-	return i;
+	q_data->queue_stats.dequeued_count += dequeued_ops;
+	return dequeued_ops;
 }
 
 /* Dequeue LDPC encode operations from ACC100 device. */
@@ -4873,24 +4901,31 @@ acc100_dequeue_ldpc_enc(struct rte_bbdev_queue_data *q_data,
 	struct acc100_queue *q = q_data->queue_private;
 	uint32_t avail = acc100_ring_avail_deq(q);
 	uint32_t aq_dequeued = 0;
-	uint16_t dequeue_num, i, dequeued_cbs = 0, dequeued_descs = 0;
+	uint16_t i, dequeued_ops = 0, dequeued_descs = 0;
 	int ret;
-
+	struct rte_bbdev_enc_op *op;
 #ifdef RTE_LIBRTE_BBDEV_DEBUG
 	if (unlikely(ops == 0 && q == NULL))
 		return 0;
 #endif
+	op = (q->ring_addr + (q->sw_ring_tail &
+			q->sw_ring_wrap_mask))->req.op_addr;
+	if (unlikely(ops == NULL || op == NULL))
+		return 0;
+	int cbm = op->ldpc_enc.code_block_mode;
 
-	dequeue_num = RTE_MIN(avail, num);
-
-	for (i = 0; i < dequeue_num; i++) {
-		ret = dequeue_enc_one_op_cb(q, &ops[dequeued_cbs],
-				dequeued_descs, &aq_dequeued);
+	for (i = 0; i < avail; i++) {
+		if (cbm == RTE_BBDEV_TRANSPORT_BLOCK)
+			ret = dequeue_enc_one_op_tb(q, &ops[dequeued_ops],
+					&dequeued_ops, &aq_dequeued,
+					&dequeued_descs);
+		else
+			ret = dequeue_enc_one_op_cb(q, &ops[dequeued_ops],
+					&dequeued_ops, &aq_dequeued,
+					&dequeued_descs);
 		if (ret < 0)
 			break;
-		dequeued_cbs += ret;
-		dequeued_descs++;
-		if (dequeued_cbs >= num)
+		if (dequeued_ops >= num)
 			break;
 	}
 
@@ -4898,12 +4933,10 @@ acc100_dequeue_ldpc_enc(struct rte_bbdev_queue_data *q_data,
 	q->sw_ring_tail += dequeued_descs;
 
 	/* Update enqueue stats */
-	q_data->queue_stats.dequeued_count += dequeued_cbs;
-
-	return dequeued_cbs;
+	q_data->queue_stats.dequeued_count += dequeued_ops;
+	return dequeued_ops;
 }
 
-
 /* Dequeue decode operations from ACC100 device. */
 static uint16_t
 acc100_dequeue_dec(struct rte_bbdev_queue_data *q_data,
-- 
2.37.1