[PATCH RFC 1/4] dmadev: add enqueue dequeue operations

[PATCH RFC 1/4] dmadev: add enqueue dequeue operations

[Kommula Shiva Shankar]

From: Pavan Nikhilesh <pbhagavatula@marvell.com>

Add enqueue/dequeue operations that use struct rte_dma_op
to communicate with the dma device.
These operations need to be enabled at dma device configuration
time by setting the flag rte_dma_conf::enable_enq_deq if the
device supports RTE_DMA_CAPA_OPS_ENQ_DEQ capability.
The enqueue dequeue operations are not compatible with
rte_dma_copy, rte_dma_copy_sg, rte_dma_fill, rte_dma_submit,
rte_dma_completed, rte_dma_completed_status range of APIs.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Change-Id: I6587b19608264a3511ea4dd3cf7b865cc5cac441
---
 lib/dmadev/rte_dmadev.c              |  18 ++++
 lib/dmadev/rte_dmadev.h              | 145 +++++++++++++++++++++++++++
 lib/dmadev/rte_dmadev_core.h         |  10 ++
 lib/dmadev/rte_dmadev_trace_fp.h     |  20 ++++
 lib/dmadev/rte_dmadev_trace_points.c |   6 ++
 5 files changed, 199 insertions(+)

diff --git a/lib/dmadev/rte_dmadev.c b/lib/dmadev/rte_dmadev.c
index 8bb7824aa1..4c108ef26e 100644
--- a/lib/dmadev/rte_dmadev.c
+++ b/lib/dmadev/rte_dmadev.c
@@ -921,6 +921,22 @@ dummy_burst_capacity(__rte_unused const void *dev_private,
 	return 0;
 }
 
+static uint16_t
+dummy_enqueue(__rte_unused void *dev_private, __rte_unused uint16_t vchan,
+	      __rte_unused struct rte_dma_op **ops, __rte_unused uint16_t nb_ops)
+{
+	RTE_DMA_LOG(ERR, "Enqueue not configured or not supported.");
+	return 0;
+}
+
+static uint16_t
+dummy_dequeue(__rte_unused void *dev_private, __rte_unused uint16_t vchan,
+	      __rte_unused struct rte_dma_op **ops, __rte_unused uint16_t nb_ops)
+{
+	RTE_DMA_LOG(ERR, "Enqueue not configured or not supported.");
+	return 0;
+}
+
 static void
 dma_fp_object_dummy(struct rte_dma_fp_object *obj)
 {
@@ -932,6 +948,8 @@ dma_fp_object_dummy(struct rte_dma_fp_object *obj)
 	obj->completed        = dummy_completed;
 	obj->completed_status = dummy_completed_status;
 	obj->burst_capacity   = dummy_burst_capacity;
+	obj->enqueue          = dummy_enqueue;
+	obj->dequeue          = dummy_dequeue;
 }
 
 static int
diff --git a/lib/dmadev/rte_dmadev.h b/lib/dmadev/rte_dmadev.h
index 2f9304a9db..e11bff64d8 100644
--- a/lib/dmadev/rte_dmadev.h
+++ b/lib/dmadev/rte_dmadev.h
@@ -265,6 +265,11 @@ int16_t rte_dma_next_dev(int16_t start_dev_id);
  * known from 'nb_priorities' field in struct rte_dma_info.
  */
 #define RTE_DMA_CAPA_PRI_POLICY_SP	RTE_BIT64(8)
+/** Support enqueue and dequeue operations.
+ *
+ * @see struct rte_dma_op
+ */
+#define RTE_DMA_CAPA_OPS_ENQ_DEQ        RTE_BIT64(9)
 
 /** Support copy operation.
  * This capability start with index of 32, so that it could leave gap between
@@ -351,6 +356,15 @@ struct rte_dma_conf {
 	 * Lowest value indicates higher priority and vice-versa.
 	 */
 	uint16_t priority;
+	/** Indicates whether to use enqueue dequeue operations using rte_dma_op.
+	 * false-default mode, true-enqueue, dequeue mode.
+	 * This value can be set to true only when ENQ_DEQ_OPS capability is
+	 * supported. When enabled, only calls to `rte_dma_enqueue_ops` and
+	 * `rte_dma_dequeue_ops` are valid.
+	 *
+	 * @see RTE_DMA_CAPA_OPS_ENQ_DEQ
+	 */
+	bool enable_enq_deq;
 };
 
 /**
@@ -791,6 +805,63 @@ struct rte_dma_sge {
 	uint32_t length; /**< The DMA operation length. */
 };
 
+/**
+ * A structure used to hold event based DMA operation entry. All the information
+ * required for a DMA transfer shall be populated in "struct rte_dma_op"
+ * instance.
+ */
+struct rte_dma_op {
+	uint64_t flags;
+	/**< Flags related to the operation.
+	 * @see RTE_DMA_OP_FLAG_*
+	 */
+	struct rte_mempool *op_mp;
+	/**< Mempool from which op is allocated. */
+	enum rte_dma_status_code status;
+	/**< Status code for this operation. */
+	uint32_t rsvd;
+	/**< Reserved for future use. */
+	uint64_t impl_opaque[2];
+	/**< Implementation-specific opaque data.
+	 * An dma device implementation use this field to hold
+	 * implementation specific values to share between dequeue and enqueue
+	 * operations.
+	 * The application should not modify this field.
+	 */
+	uint64_t user_meta;
+	/**<  Memory to store user specific metadata.
+	 * The dma device implementation should not modify this area.
+	 */
+	uint64_t event_meta;
+	/**< Event metadata of DMA completion event.
+	 * Used when RTE_EVENT_DMA_ADAPTER_CAP_INTERNAL_PORT_VCHAN_EV_BIND is not
+	 * supported in OP_NEW mode.
+	 * @see rte_event_dma_adapter_mode::RTE_EVENT_DMA_ADAPTER_OP_NEW
+	 * @see RTE_EVENT_DMA_ADAPTER_CAP_INTERNAL_PORT_VCHAN_EV_BIND
+	 *
+	 * Used when RTE_EVENT_DMA_ADAPTER_CAP_INTERNAL_PORT_OP_FWD is not
+	 * supported in OP_FWD mode.
+	 * @see rte_event_dma_adapter_mode::RTE_EVENT_DMA_ADAPTER_OP_FORWARD
+	 * @see RTE_EVENT_DMA_ADAPTER_CAP_INTERNAL_PORT_OP_FWD
+	 *
+	 * @see struct rte_event::event
+	 */
+	int16_t dma_dev_id;
+	/**< DMA device ID to be used with OP_FORWARD mode.
+	 * @see rte_event_dma_adapter_mode::RTE_EVENT_DMA_ADAPTER_OP_FORWARD
+	 */
+	uint16_t vchan;
+	/**< DMA vchan ID to be used with OP_FORWARD mode
+	 * @see rte_event_dma_adapter_mode::RTE_EVENT_DMA_ADAPTER_OP_FORWARD
+	 */
+	uint16_t nb_src;
+	/**< Number of source segments. */
+	uint16_t nb_dst;
+	/**< Number of destination segments. */
+	struct rte_dma_sge src_dst_seg[0];
+	/**< Source and destination segments. */
+};
+
 #ifdef __cplusplus
 }
 #endif
@@ -1154,6 +1225,80 @@ rte_dma_burst_capacity(int16_t dev_id, uint16_t vchan)
 	return ret;
 }
 
+/**
+ * Enqueue rte_dma_ops to DMA device, can only be used underlying supports
+ * RTE_DMA_CAPA_OPS_ENQ_DEQ and rte_dma_conf::enable_enq_deq is enabled in
+ * rte_dma_configure()
+ * The ops enqueued will be immediately submitted to the DMA device.
+ * The enqueue should be coupled with dequeue to retrieve completed ops, calls
+ * to rte_dma_submit(), rte_dma_completed() and rte_dma_completed_status()
+ * are not valid.
+ *
+ * @param dev_id
+ *   The identifier of the device.
+ * @param vchan
+ *   The identifier of virtual DMA channel.
+ * @param ops
+ *   Pointer to rte_dma_op array.
+ * @param nb_ops
+ *   Number of rte_dma_op in the ops array
+ * @return uint16_t
+ *   - Number of successfully submitted ops.
+ */
+static inline uint16_t
+rte_dma_enqueue_ops(int16_t dev_id, uint16_t vchan, struct rte_dma_op **ops, uint16_t nb_ops)
+{
+	struct rte_dma_fp_object *obj = &rte_dma_fp_objs[dev_id];
+	uint16_t ret;
+
+#ifdef RTE_DMADEV_DEBUG
+	if (!rte_dma_is_valid(dev_id))
+		return 0;
+	if (*obj->enqueue == NULL)
+		return 0;
+#endif
+
+	ret = (*obj->enqueue)(obj->dev_private, vchan, ops, nb_ops);
+	rte_dma_trace_enqueue_ops(dev_id, vchan, (void **)ops, nb_ops);
+
+	return ret;
+}
+
+/**
+ * Dequeue completed rte_dma_ops submitted to the DMA device, can only be used
+ * underlying supports RTE_DMA_CAPA_OPS_ENQ_DEQ and rte_dma_conf::enable_enq_deq
+ * is enabled in rte_dma_configure()
+ *
+ * @param dev_id
+ *   The identifier of the device.
+ * @param vchan
+ *   The identifier of virtual DMA channel.
+ * @param ops
+ *   Pointer to rte_dma_op array.
+ * @param nb_ops
+ *   Size of rte_dma_op array.
+ * @return
+ *   - Number of successfully completed ops. Should be less or equal to nb_ops.
+ */
+static inline uint16_t
+rte_dma_dequeue_ops(int16_t dev_id, uint16_t vchan, struct rte_dma_op **ops, uint16_t nb_ops)
+{
+	struct rte_dma_fp_object *obj = &rte_dma_fp_objs[dev_id];
+	uint16_t ret;
+
+#ifdef RTE_DMADEV_DEBUG
+	if (!rte_dma_is_valid(dev_id))
+		return 0;
+	if (*obj->dequeue == NULL)
+		return 0;
+#endif
+
+	ret = (*obj->dequeue)(obj->dev_private, vchan, ops, nb_ops);
+	rte_dma_trace_dequeue_ops(dev_id, vchan, (void **)ops, nb_ops);
+
+	return ret;
+}
+
 #ifdef __cplusplus
 }
 #endif
diff --git a/lib/dmadev/rte_dmadev_core.h b/lib/dmadev/rte_dmadev_core.h
index 29f52514d7..20a467178f 100644
--- a/lib/dmadev/rte_dmadev_core.h
+++ b/lib/dmadev/rte_dmadev_core.h
@@ -50,6 +50,14 @@ typedef uint16_t (*rte_dma_completed_status_t)(void *dev_private,
 /** @internal Used to check the remaining space in descriptor ring. */
 typedef uint16_t (*rte_dma_burst_capacity_t)(const void *dev_private, uint16_t vchan);
 
+/** @internal Used to enqueue a rte_dma_op to the dma engine. */
+typedef uint16_t (*rte_dma_enqueue_ops_t)(void *dev_private, uint16_t vchan,
+					  struct rte_dma_op **ops, uint16_t nb_ops);
+
+/** @internal Used to dequeue rte_dma_op from the dma engine. */
+typedef uint16_t (*rte_dma_dequeue_ops_t)(void *dev_private, uint16_t vchan,
+					  struct rte_dma_op **ops, uint16_t nb_ops);
+
 /**
  * @internal
  * Fast-path dmadev functions and related data are hold in a flat array.
@@ -73,6 +81,8 @@ struct __rte_cache_aligned rte_dma_fp_object {
 	rte_dma_completed_t        completed;
 	rte_dma_completed_status_t completed_status;
 	rte_dma_burst_capacity_t   burst_capacity;
+	rte_dma_enqueue_ops_t      enqueue;
+	rte_dma_dequeue_ops_t      dequeue;
 };
 
 extern struct rte_dma_fp_object *rte_dma_fp_objs;
diff --git a/lib/dmadev/rte_dmadev_trace_fp.h b/lib/dmadev/rte_dmadev_trace_fp.h
index f5b96838bc..5773617058 100644
--- a/lib/dmadev/rte_dmadev_trace_fp.h
+++ b/lib/dmadev/rte_dmadev_trace_fp.h
@@ -143,6 +143,26 @@ RTE_TRACE_POINT_FP(
 	rte_trace_point_emit_u16(ret);
 )
 
+RTE_TRACE_POINT_FP(
+	rte_dma_trace_enqueue_ops,
+	RTE_TRACE_POINT_ARGS(int16_t dev_id, uint16_t vchan, void **ops,
+			     uint16_t nb_ops),
+	rte_trace_point_emit_i16(dev_id);
+	rte_trace_point_emit_u16(vchan);
+	rte_trace_point_emit_ptr(ops);
+	rte_trace_point_emit_u16(nb_ops);
+)
+
+RTE_TRACE_POINT_FP(
+	rte_dma_trace_dequeue_ops,
+	RTE_TRACE_POINT_ARGS(int16_t dev_id, uint16_t vchan, void **ops,
+			     uint16_t nb_ops),
+	rte_trace_point_emit_i16(dev_id);
+	rte_trace_point_emit_u16(vchan);
+	rte_trace_point_emit_ptr(ops);
+	rte_trace_point_emit_u16(nb_ops);
+)
+
 #ifdef __cplusplus
 }
 #endif
diff --git a/lib/dmadev/rte_dmadev_trace_points.c b/lib/dmadev/rte_dmadev_trace_points.c
index 4c74356346..60a0de95d1 100644
--- a/lib/dmadev/rte_dmadev_trace_points.c
+++ b/lib/dmadev/rte_dmadev_trace_points.c
@@ -56,3 +56,9 @@ RTE_TRACE_POINT_REGISTER(rte_dma_trace_completed_status,
 
 RTE_TRACE_POINT_REGISTER(rte_dma_trace_burst_capacity,
 	lib.dmadev.burst_capacity)
+
+RTE_TRACE_POINT_REGISTER(rte_dma_trace_enqueue_ops,
+	lib.dmadev.enqueue_ops)
+
+RTE_TRACE_POINT_REGISTER(rte_dma_trace_dequeue_ops,
+	lib.dmadev.dequeue_ops)
-- 
2.43.0

[PATCH RFC 2/4] eventdev: refactor rte_event_dma_adapater_op calls

[Kommula Shiva Shankar]

From: Pavan Nikhilesh <pbhagavatula@marvell.com>

Migrate all invocations of rte_event_dma_adapter_op
API to rte_dma_op.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Change-Id: I56b6e61af72d119287b0d2ba6a9bbacc3ae808d6
---
 app/test-eventdev/test_perf_common.c |  6 +--
 app/test-eventdev/test_perf_common.h |  4 +-
 app/test/test_event_dma_adapter.c    |  6 +--
 drivers/dma/cnxk/cnxk_dmadev.c       |  2 +-
 drivers/dma/cnxk/cnxk_dmadev_fp.c    | 12 +++---
 lib/eventdev/rte_event_dma_adapter.c | 18 ++++-----
 lib/eventdev/rte_event_dma_adapter.h | 57 ----------------------------
 7 files changed, 24 insertions(+), 81 deletions(-)

diff --git a/app/test-eventdev/test_perf_common.c b/app/test-eventdev/test_perf_common.c
index 627f07caa1..4e0109db52 100644
--- a/app/test-eventdev/test_perf_common.c
+++ b/app/test-eventdev/test_perf_common.c
@@ -562,11 +562,11 @@ crypto_adapter_enq_op_fwd(struct prod_data *p)
 static inline void
 dma_adapter_enq_op_fwd(struct prod_data *p)
 {
-	struct rte_event_dma_adapter_op *ops[BURST_SIZE] = {NULL};
+	struct rte_dma_op *ops[BURST_SIZE] = {NULL};
 	struct test_perf *t = p->t;
 	const uint32_t nb_flows = t->nb_flows;
 	const uint64_t nb_pkts = t->nb_pkts;
-	struct rte_event_dma_adapter_op op;
+	struct rte_dma_op op;
 	struct rte_event evts[BURST_SIZE];
 	const uint8_t dev_id = p->dev_id;
 	struct evt_options *opt = t->opt;
@@ -2114,7 +2114,7 @@ perf_mempool_setup(struct evt_test *test, struct evt_options *opt)
 	} else if (opt->prod_type == EVT_PROD_TYPE_EVENT_DMA_ADPTR) {
 		t->pool = rte_mempool_create(test->name,   /* mempool name */
 					     opt->pool_sz, /* number of elements*/
-					     sizeof(struct rte_event_dma_adapter_op) +
+					     sizeof(struct rte_dma_op) +
 						     (sizeof(struct rte_dma_sge) * 2),
 					     cache_sz,		       /* cache size*/
 					     0, NULL, NULL, NULL,      /* obj constructor */
diff --git a/app/test-eventdev/test_perf_common.h b/app/test-eventdev/test_perf_common.h
index d7333ad390..63078b0ee2 100644
--- a/app/test-eventdev/test_perf_common.h
+++ b/app/test-eventdev/test_perf_common.h
@@ -139,7 +139,7 @@ perf_mark_fwd_latency(enum evt_prod_type prod_type, struct rte_event *const ev)
 		}
 		pe->timestamp = rte_get_timer_cycles();
 	} else if (prod_type == EVT_PROD_TYPE_EVENT_DMA_ADPTR) {
-		struct rte_event_dma_adapter_op *op = ev->event_ptr;
+		struct rte_dma_op *op = ev->event_ptr;
 
 		op->user_meta = rte_get_timer_cycles();
 	} else {
@@ -297,7 +297,7 @@ perf_process_last_stage_latency(struct rte_mempool *const pool, enum evt_prod_ty
 		tstamp = pe->timestamp;
 		rte_crypto_op_free(op);
 	} else if (prod_type == EVT_PROD_TYPE_EVENT_DMA_ADPTR) {
-		struct rte_event_dma_adapter_op *op = ev->event_ptr;
+		struct rte_dma_op *op = ev->event_ptr;
 
 		to_free_in_bulk = op;
 		tstamp = op->user_meta;
diff --git a/app/test/test_event_dma_adapter.c b/app/test/test_event_dma_adapter.c
index 9988d4fc7b..7f72a4e81d 100644
--- a/app/test/test_event_dma_adapter.c
+++ b/app/test/test_event_dma_adapter.c
@@ -234,7 +234,7 @@ test_op_forward_mode(void)
 {
 	struct rte_mbuf *src_mbuf[TEST_MAX_OP];
 	struct rte_mbuf *dst_mbuf[TEST_MAX_OP];
-	struct rte_event_dma_adapter_op *op;
+	struct rte_dma_op *op;
 	struct rte_event ev[TEST_MAX_OP];
 	int ret, i;
 
@@ -266,7 +266,7 @@ test_op_forward_mode(void)
 		op->vchan = TEST_DMA_VCHAN_ID;
 		op->event_meta = dma_response_info.event;
 
-		/* Fill in event info and update event_ptr with rte_event_dma_adapter_op */
+		/* Fill in event info and update event_ptr with rte_dma_op */
 		memset(&ev[i], 0, sizeof(struct rte_event));
 		ev[i].event = 0;
 		ev[i].op = RTE_EVENT_OP_NEW;
@@ -396,7 +396,7 @@ configure_dmadev(void)
 						       rte_socket_id());
 	RTE_TEST_ASSERT_NOT_NULL(params.dst_mbuf_pool, "Can't create DMA_DST_MBUFPOOL\n");
 
-	elt_size = sizeof(struct rte_event_dma_adapter_op) + (sizeof(struct rte_dma_sge) * 2);
+	elt_size = sizeof(struct rte_dma_op) + (sizeof(struct rte_dma_sge) * 2);
 	params.op_mpool = rte_mempool_create("EVENT_DMA_OP_POOL", DMA_OP_POOL_SIZE, elt_size, 0,
 					     0, NULL, NULL, NULL, NULL, rte_socket_id(), 0);
 	RTE_TEST_ASSERT_NOT_NULL(params.op_mpool, "Can't create DMA_OP_POOL\n");
diff --git a/drivers/dma/cnxk/cnxk_dmadev.c b/drivers/dma/cnxk/cnxk_dmadev.c
index e7be3767b2..60b3d28d65 100644
--- a/drivers/dma/cnxk/cnxk_dmadev.c
+++ b/drivers/dma/cnxk/cnxk_dmadev.c
@@ -591,7 +591,7 @@ cnxk_dmadev_probe(struct rte_pci_driver *pci_drv __rte_unused, struct rte_pci_de
 	rdpi = &dpivf->rdpi;
 
 	rdpi->pci_dev = pci_dev;
-	rc = roc_dpi_dev_init(rdpi, offsetof(struct rte_event_dma_adapter_op, impl_opaque));
+	rc = roc_dpi_dev_init(rdpi, offsetof(struct rte_dma_op, impl_opaque));
 	if (rc < 0)
 		goto err_out_free;
 
diff --git a/drivers/dma/cnxk/cnxk_dmadev_fp.c b/drivers/dma/cnxk/cnxk_dmadev_fp.c
index 26591235c6..340c7601d7 100644
--- a/drivers/dma/cnxk/cnxk_dmadev_fp.c
+++ b/drivers/dma/cnxk/cnxk_dmadev_fp.c
@@ -453,7 +453,7 @@ uint16_t
 cn10k_dma_adapter_enqueue(void *ws, struct rte_event ev[], uint16_t nb_events)
 {
 	const struct rte_dma_sge *src, *dst;
-	struct rte_event_dma_adapter_op *op;
+	struct rte_dma_op *op;
 	struct cnxk_dpi_conf *dpi_conf;
 	struct cnxk_dpi_vf_s *dpivf;
 	struct cn10k_sso_hws *work;
@@ -514,7 +514,7 @@ uint16_t
 cn9k_dma_adapter_dual_enqueue(void *ws, struct rte_event ev[], uint16_t nb_events)
 {
 	const struct rte_dma_sge *fptr, *lptr;
-	struct rte_event_dma_adapter_op *op;
+	struct rte_dma_op *op;
 	struct cn9k_sso_hws_dual *work;
 	struct cnxk_dpi_conf *dpi_conf;
 	struct cnxk_dpi_vf_s *dpivf;
@@ -530,7 +530,7 @@ cn9k_dma_adapter_dual_enqueue(void *ws, struct rte_event ev[], uint16_t nb_event
 	for (count = 0; count < nb_events; count++) {
 		op = ev[count].event_ptr;
 		rsp_info = (struct rte_event *)((uint8_t *)op +
-						sizeof(struct rte_event_dma_adapter_op));
+						sizeof(struct rte_dma_op));
 		dpivf = rte_dma_fp_objs[op->dma_dev_id].dev_private;
 		dpi_conf = &dpivf->conf[op->vchan];
 
@@ -586,7 +586,7 @@ uint16_t
 cn9k_dma_adapter_enqueue(void *ws, struct rte_event ev[], uint16_t nb_events)
 {
 	const struct rte_dma_sge *fptr, *lptr;
-	struct rte_event_dma_adapter_op *op;
+	struct rte_dma_op *op;
 	struct cnxk_dpi_conf *dpi_conf;
 	struct cnxk_dpi_vf_s *dpivf;
 	struct cn9k_sso_hws *work;
@@ -654,11 +654,11 @@ cn9k_dma_adapter_enqueue(void *ws, struct rte_event ev[], uint16_t nb_events)
 uintptr_t
 cnxk_dma_adapter_dequeue(uintptr_t get_work1)
 {
-	struct rte_event_dma_adapter_op *op;
+	struct rte_dma_op *op;
 	struct cnxk_dpi_conf *dpi_conf;
 	struct cnxk_dpi_vf_s *dpivf;
 
-	op = (struct rte_event_dma_adapter_op *)get_work1;
+	op = (struct rte_dma_op *)get_work1;
 	dpivf = rte_dma_fp_objs[op->dma_dev_id].dev_private;
 	dpi_conf = &dpivf->conf[op->vchan];
 
diff --git a/lib/eventdev/rte_event_dma_adapter.c b/lib/eventdev/rte_event_dma_adapter.c
index ff2bc408c1..7baa46e0a3 100644
--- a/lib/eventdev/rte_event_dma_adapter.c
+++ b/lib/eventdev/rte_event_dma_adapter.c
@@ -39,8 +39,8 @@ struct __rte_cache_aligned dma_ops_circular_buffer {
 	/* Size of circular buffer */
 	uint16_t size;
 
-	/* Pointer to hold rte_event_dma_adapter_op for processing */
-	struct rte_event_dma_adapter_op **op_buffer;
+	/* Pointer to hold rte_dma_op for processing */
+	struct rte_dma_op **op_buffer;
 };
 
 /* Vchan information */
@@ -201,7 +201,7 @@ edma_circular_buffer_space_for_batch(struct dma_ops_circular_buffer *bufp)
 static inline int
 edma_circular_buffer_init(const char *name, struct dma_ops_circular_buffer *buf, uint16_t sz)
 {
-	buf->op_buffer = rte_zmalloc(name, sizeof(struct rte_event_dma_adapter_op *) * sz, 0);
+	buf->op_buffer = rte_zmalloc(name, sizeof(struct rte_dma_op *) * sz, 0);
 	if (buf->op_buffer == NULL)
 		return -ENOMEM;
 
@@ -217,7 +217,7 @@ edma_circular_buffer_free(struct dma_ops_circular_buffer *buf)
 }
 
 static inline int
-edma_circular_buffer_add(struct dma_ops_circular_buffer *bufp, struct rte_event_dma_adapter_op *op)
+edma_circular_buffer_add(struct dma_ops_circular_buffer *bufp, struct rte_dma_op *op)
 {
 	uint16_t *tail = &bufp->tail;
 
@@ -235,7 +235,7 @@ edma_circular_buffer_flush_to_dma_dev(struct event_dma_adapter *adapter,
 				      struct dma_ops_circular_buffer *bufp, uint8_t dma_dev_id,
 				      uint16_t vchan, uint16_t *nb_ops_flushed)
 {
-	struct rte_event_dma_adapter_op *op;
+	struct rte_dma_op *op;
 	uint16_t *head = &bufp->head;
 	uint16_t *tail = &bufp->tail;
 	struct dma_vchan_info *tq;
@@ -498,7 +498,7 @@ edma_enq_to_dma_dev(struct event_dma_adapter *adapter, struct rte_event *ev, uns
 {
 	struct rte_event_dma_adapter_stats *stats = &adapter->dma_stats;
 	struct dma_vchan_info *vchan_qinfo = NULL;
-	struct rte_event_dma_adapter_op *dma_op;
+	struct rte_dma_op *dma_op;
 	uint16_t vchan, nb_enqueued = 0;
 	int16_t dma_dev_id;
 	unsigned int i, n;
@@ -641,7 +641,7 @@ edma_adapter_enq_run(struct event_dma_adapter *adapter, unsigned int max_enq)
 #define DMA_ADAPTER_MAX_EV_ENQ_RETRIES 100
 
 static inline uint16_t
-edma_ops_enqueue_burst(struct event_dma_adapter *adapter, struct rte_event_dma_adapter_op **ops,
+edma_ops_enqueue_burst(struct event_dma_adapter *adapter, struct rte_dma_op **ops,
 		       uint16_t num)
 {
 	struct rte_event_dma_adapter_stats *stats = &adapter->dma_stats;
@@ -687,7 +687,7 @@ edma_circular_buffer_flush_to_evdev(struct event_dma_adapter *adapter,
 				    struct dma_ops_circular_buffer *bufp,
 				    uint16_t *enqueue_count)
 {
-	struct rte_event_dma_adapter_op **ops = bufp->op_buffer;
+	struct rte_dma_op **ops = bufp->op_buffer;
 	uint16_t n = 0, nb_ops_flushed;
 	uint16_t *head = &bufp->head;
 	uint16_t *tail = &bufp->tail;
@@ -736,7 +736,7 @@ edma_adapter_deq_run(struct event_dma_adapter *adapter, unsigned int max_deq)
 	struct rte_event_dma_adapter_stats *stats = &adapter->dma_stats;
 	struct dma_vchan_info *vchan_info;
 	struct dma_ops_circular_buffer *tq_buf;
-	struct rte_event_dma_adapter_op *ops;
+	struct rte_dma_op *ops;
 	uint16_t n, nb_deq, nb_enqueued, i;
 	struct dma_device_info *dev_info;
 	uint16_t vchan, num_vchan;
diff --git a/lib/eventdev/rte_event_dma_adapter.h b/lib/eventdev/rte_event_dma_adapter.h
index 5c480b82ff..453754d13b 100644
--- a/lib/eventdev/rte_event_dma_adapter.h
+++ b/lib/eventdev/rte_event_dma_adapter.h
@@ -151,63 +151,6 @@
 extern "C" {
 #endif
 
-/**
- * A structure used to hold event based DMA operation entry. All the information
- * required for a DMA transfer shall be populated in "struct rte_event_dma_adapter_op"
- * instance.
- */
-struct rte_event_dma_adapter_op {
-	uint64_t flags;
-	/**< Flags related to the operation.
-	 * @see RTE_DMA_OP_FLAG_*
-	 */
-	struct rte_mempool *op_mp;
-	/**< Mempool from which op is allocated. */
-	enum rte_dma_status_code status;
-	/**< Status code for this operation. */
-	uint32_t rsvd;
-	/**< Reserved for future use. */
-	uint64_t impl_opaque[2];
-	/**< Implementation-specific opaque data.
-	 * An dma device implementation use this field to hold
-	 * implementation specific values to share between dequeue and enqueue
-	 * operations.
-	 * The application should not modify this field.
-	 */
-	uint64_t user_meta;
-	/**<  Memory to store user specific metadata.
-	 * The dma device implementation should not modify this area.
-	 */
-	uint64_t event_meta;
-	/**< Event metadata of DMA completion event.
-	 * Used when RTE_EVENT_DMA_ADAPTER_CAP_INTERNAL_PORT_VCHAN_EV_BIND is not
-	 * supported in OP_NEW mode.
-	 * @see rte_event_dma_adapter_mode::RTE_EVENT_DMA_ADAPTER_OP_NEW
-	 * @see RTE_EVENT_DMA_ADAPTER_CAP_INTERNAL_PORT_VCHAN_EV_BIND
-	 *
-	 * Used when RTE_EVENT_DMA_ADAPTER_CAP_INTERNAL_PORT_OP_FWD is not
-	 * supported in OP_FWD mode.
-	 * @see rte_event_dma_adapter_mode::RTE_EVENT_DMA_ADAPTER_OP_FORWARD
-	 * @see RTE_EVENT_DMA_ADAPTER_CAP_INTERNAL_PORT_OP_FWD
-	 *
-	 * @see struct rte_event::event
-	 */
-	int16_t dma_dev_id;
-	/**< DMA device ID to be used with OP_FORWARD mode.
-	 * @see rte_event_dma_adapter_mode::RTE_EVENT_DMA_ADAPTER_OP_FORWARD
-	 */
-	uint16_t vchan;
-	/**< DMA vchan ID to be used with OP_FORWARD mode
-	 * @see rte_event_dma_adapter_mode::RTE_EVENT_DMA_ADAPTER_OP_FORWARD
-	 */
-	uint16_t nb_src;
-	/**< Number of source segments. */
-	uint16_t nb_dst;
-	/**< Number of destination segments. */
-	struct rte_dma_sge src_dst_seg[];
-	/**< Source and destination segments. */
-};
-
 /**
  *  DMA event adapter mode
  */
-- 
2.43.0

[PATCH RFC 3/4] doc: update prog guide to use rte_dma_op

[Kommula Shiva Shankar]

From: Pavan Nikhilesh <pbhagavatula@marvell.com>

Update the documentation to replace all instances of
rte_event_dma_adapter_op with rte_dma_op

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Change-Id: I0fe65d18f4601709826c11c6738cacec8991515d
---
 doc/guides/prog_guide/eventdev/event_dma_adapter.rst | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/doc/guides/prog_guide/eventdev/event_dma_adapter.rst b/doc/guides/prog_guide/eventdev/event_dma_adapter.rst
index e040d89e8b..e8437a3297 100644
--- a/doc/guides/prog_guide/eventdev/event_dma_adapter.rst
+++ b/doc/guides/prog_guide/eventdev/event_dma_adapter.rst
@@ -144,7 +144,7 @@ on which it enqueues events towards the DMA adapter using ``rte_event_enqueue_bu
    uint32_t cap;
    int ret;
 
-   /* Fill in event info and update event_ptr with rte_event_dma_adapter_op */
+   /* Fill in event info and update event_ptr with rte_dma_op */
    memset(&ev, 0, sizeof(ev));
    .
    .
@@ -244,11 +244,11 @@ Set event response information
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 In the ``RTE_EVENT_DMA_ADAPTER_OP_FORWARD`` / ``RTE_EVENT_DMA_ADAPTER_OP_NEW`` mode,
-the application specifies the dmadev ID and vchan ID in ``struct rte_event_dma_adapter_op``
+the application specifies the dmadev ID and vchan ID in ``struct rte_dma_op``
 and the event information (response information)
 needed to enqueue an event after the DMA operation has completed.
 The response information is specified in ``struct rte_event``
-and appended to the ``struct rte_event_dma_adapter_op``.
+and appended to the ``struct rte_dma_op``.
 
 
 Start the adapter instance
-- 
2.43.0

[PATCH RFC 4/4] dma/cnxk: implement enqueue dequeue ops

[Kommula Shiva Shankar]

From: Pavan Nikhilesh <pbhagavatula@marvell.com>

Implement DMA enqueue/dequeue operations when
application enables it via configuration.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Change-Id: I57883ce5d358bf23a9d940ed513d0dc762227dcc
---
 drivers/dma/cnxk/cnxk_dmadev.c    |  25 +++++-
 drivers/dma/cnxk/cnxk_dmadev.h    |   7 ++
 drivers/dma/cnxk/cnxk_dmadev_fp.c | 140 ++++++++++++++++++++++++++++++
 3 files changed, 171 insertions(+), 1 deletion(-)

diff --git a/drivers/dma/cnxk/cnxk_dmadev.c b/drivers/dma/cnxk/cnxk_dmadev.c
index 60b3d28d65..18a4914013 100644
--- a/drivers/dma/cnxk/cnxk_dmadev.c
+++ b/drivers/dma/cnxk/cnxk_dmadev.c
@@ -19,7 +19,7 @@ cnxk_dmadev_info_get(const struct rte_dma_dev *dev, struct rte_dma_info *dev_inf
 	dev_info->dev_capa = RTE_DMA_CAPA_MEM_TO_MEM | RTE_DMA_CAPA_MEM_TO_DEV |
 			     RTE_DMA_CAPA_DEV_TO_MEM | RTE_DMA_CAPA_DEV_TO_DEV |
 			     RTE_DMA_CAPA_OPS_COPY | RTE_DMA_CAPA_OPS_COPY_SG |
-			     RTE_DMA_CAPA_M2D_AUTO_FREE;
+			     RTE_DMA_CAPA_M2D_AUTO_FREE | RTE_DMA_CAPA_OPS_ENQ_DEQ;
 	if (roc_feature_dpi_has_priority()) {
 		dev_info->dev_capa |= RTE_DMA_CAPA_PRI_POLICY_SP;
 		dev_info->nb_priorities = CN10K_DPI_MAX_PRI;
@@ -114,6 +114,21 @@ cnxk_dmadev_configure(struct rte_dma_dev *dev, const struct rte_dma_conf *conf,
 	if (roc_feature_dpi_has_priority())
 		dpivf->rdpi.priority = conf->priority;
 
+	if (conf->enable_enq_deq) {
+		dev->fp_obj->copy = NULL;
+		dev->fp_obj->fill = NULL;
+		dev->fp_obj->submit = NULL;
+		dev->fp_obj->copy_sg = NULL;
+		dev->fp_obj->completed = NULL;
+		dev->fp_obj->completed_status = NULL;
+
+		dev->fp_obj->enqueue = cnxk_dma_ops_enqueue;
+		dev->fp_obj->dequeue = cnxk_dma_ops_dequeue;
+
+		if (roc_model_is_cn10k())
+			dev->fp_obj->enqueue = cn10k_dma_ops_enqueue;
+	}
+
 	return 0;
 }
 
@@ -270,6 +285,14 @@ cnxk_dmadev_vchan_setup(struct rte_dma_dev *dev, uint16_t vchan,
 		return -ENOMEM;
 	}
 
+	size = (max_desc * sizeof(struct rte_dma_op *));
+	dpi_conf->c_desc.ops = rte_zmalloc(NULL, size, RTE_CACHE_LINE_SIZE);
+	if (dpi_conf->c_desc.ops == NULL) {
+		plt_err("Failed to allocate for ops array");
+		rte_free(dpi_conf->c_desc.compl_ptr);
+		return -ENOMEM;
+	}
+
 	for (i = 0; i < max_desc; i++)
 		dpi_conf->c_desc.compl_ptr[i * CNXK_DPI_COMPL_OFFSET] = CNXK_DPI_REQ_CDATA;
 
diff --git a/drivers/dma/cnxk/cnxk_dmadev.h b/drivers/dma/cnxk/cnxk_dmadev.h
index 39fd6afbe9..2615cb5b73 100644
--- a/drivers/dma/cnxk/cnxk_dmadev.h
+++ b/drivers/dma/cnxk/cnxk_dmadev.h
@@ -93,6 +93,7 @@ struct cnxk_dpi_cdesc_data_s {
 	uint16_t head;
 	uint16_t tail;
 	uint8_t *compl_ptr;
+	struct rte_dma_op **ops;
 };
 
 struct cnxk_dpi_conf {
@@ -132,5 +133,11 @@ int cn10k_dmadev_copy(void *dev_private, uint16_t vchan, rte_iova_t src, rte_iov
 int cn10k_dmadev_copy_sg(void *dev_private, uint16_t vchan, const struct rte_dma_sge *src,
 			 const struct rte_dma_sge *dst, uint16_t nb_src, uint16_t nb_dst,
 			 uint64_t flags);
+uint16_t cnxk_dma_ops_enqueue(void *dev_private, uint16_t vchan, struct rte_dma_op **ops,
+			      uint16_t nb_ops);
+uint16_t cn10k_dma_ops_enqueue(void *dev_private, uint16_t vchan, struct rte_dma_op **ops,
+			       uint16_t nb_ops);
+uint16_t cnxk_dma_ops_dequeue(void *dev_private, uint16_t vchan, struct rte_dma_op **ops,
+			      uint16_t nb_ops);
 
 #endif
diff --git a/drivers/dma/cnxk/cnxk_dmadev_fp.c b/drivers/dma/cnxk/cnxk_dmadev_fp.c
index 340c7601d7..ca9ae7cd3f 100644
--- a/drivers/dma/cnxk/cnxk_dmadev_fp.c
+++ b/drivers/dma/cnxk/cnxk_dmadev_fp.c
@@ -675,3 +675,143 @@ cnxk_dma_adapter_dequeue(uintptr_t get_work1)
 
 	return (uintptr_t)op;
 }
+
+uint16_t
+cnxk_dma_ops_enqueue(void *dev_private, uint16_t vchan, struct rte_dma_op **ops, uint16_t nb_ops)
+{
+	struct cnxk_dpi_vf_s *dpivf = dev_private;
+	struct cnxk_dpi_conf *dpi_conf = &dpivf->conf[vchan];
+	const struct rte_dma_sge *fptr, *lptr;
+	uint16_t src, dst, nwords = 0;
+	struct rte_dma_op *op;
+	uint16_t space, i;
+	uint8_t *comp_ptr;
+	uint64_t hdr[4];
+	int rc;
+
+	space = (dpi_conf->c_desc.max_cnt + 1) -
+		((dpi_conf->c_desc.tail - dpi_conf->c_desc.head) & dpi_conf->c_desc.max_cnt);
+	space = RTE_MIN(space, nb_ops);
+
+	for (i = 0; i < space; i++) {
+		op = ops[i];
+		comp_ptr =
+			&dpi_conf->c_desc.compl_ptr[dpi_conf->c_desc.tail * CNXK_DPI_COMPL_OFFSET];
+		dpi_conf->c_desc.ops[dpi_conf->c_desc.tail] = op;
+		CNXK_DPI_STRM_INC(dpi_conf->c_desc, tail);
+
+		hdr[1] = dpi_conf->cmd.u | ((op->flags & RTE_DMA_OP_FLAG_AUTO_FREE) << 37);
+		hdr[2] = (uint64_t)comp_ptr;
+
+		src = op->nb_src;
+		dst = op->nb_dst;
+		/*
+		 * For inbound case, src pointers are last pointers.
+		 * For all other cases, src pointers are first pointers.
+		 */
+		if (((dpi_conf->cmd.u >> 48) & DPI_HDR_XTYPE_MASK) == DPI_XTYPE_INBOUND) {
+			fptr = &op->src_dst_seg[src];
+			lptr = &op->src_dst_seg[0];
+			RTE_SWAP(src, dst);
+		} else {
+			fptr = &op->src_dst_seg[0];
+			lptr = &op->src_dst_seg[src];
+		}
+		hdr[0] = ((uint64_t)dst << 54) | (uint64_t)src << 48;
+
+		rc = __dpi_queue_write_sg(dpivf, hdr, fptr, lptr, src, dst);
+		if (rc) {
+			CNXK_DPI_STRM_DEC(dpi_conf->c_desc, tail);
+			goto done;
+		}
+		nwords += CNXK_DPI_CMD_LEN(src, dst);
+	}
+
+done:
+	if (nwords) {
+		rte_wmb();
+		plt_write64(nwords, dpivf->rdpi.rbase + DPI_VDMA_DBELL);
+		dpi_conf->stats.submitted += i;
+	}
+
+	return i;
+}
+
+uint16_t
+cn10k_dma_ops_enqueue(void *dev_private, uint16_t vchan, struct rte_dma_op **ops, uint16_t nb_ops)
+{
+	struct cnxk_dpi_vf_s *dpivf = dev_private;
+	struct cnxk_dpi_conf *dpi_conf = &dpivf->conf[vchan];
+	uint16_t space, i, nwords = 0;
+	struct rte_dma_op *op;
+	uint16_t src, dst;
+	uint8_t *comp_ptr;
+	uint64_t hdr[4];
+	int rc;
+
+	space = (dpi_conf->c_desc.max_cnt + 1) -
+		((dpi_conf->c_desc.tail - dpi_conf->c_desc.head) & dpi_conf->c_desc.max_cnt);
+	space = RTE_MIN(space, nb_ops);
+
+	for (i = 0; i < space; i++) {
+		op = ops[i];
+		src = op->nb_src;
+		dst = op->nb_dst;
+		comp_ptr =
+			&dpi_conf->c_desc.compl_ptr[dpi_conf->c_desc.tail * CNXK_DPI_COMPL_OFFSET];
+		dpi_conf->c_desc.ops[dpi_conf->c_desc.tail] = op;
+		CNXK_DPI_STRM_INC(dpi_conf->c_desc, tail);
+
+		hdr[0] = dpi_conf->cmd.u | (dst << 6) | src;
+		hdr[1] = (uint64_t)comp_ptr;
+		hdr[2] = (1UL << 47) | ((op->flags & RTE_DMA_OP_FLAG_AUTO_FREE) << 43);
+
+		rc = __dpi_queue_write_sg(dpivf, hdr, &op->src_dst_seg[0], &op->src_dst_seg[src],
+					  src, dst);
+		if (rc) {
+			CNXK_DPI_STRM_DEC(dpi_conf->c_desc, tail);
+			goto done;
+		}
+		nwords += CNXK_DPI_CMD_LEN(src, dst);
+	}
+
+done:
+	if (nwords) {
+		rte_wmb();
+		plt_write64(nwords, dpivf->rdpi.rbase + DPI_VDMA_DBELL);
+		dpi_conf->stats.submitted += i;
+	}
+
+	return i;
+}
+
+uint16_t
+cnxk_dma_ops_dequeue(void *dev_private, uint16_t vchan, struct rte_dma_op **ops, uint16_t nb_ops)
+{
+	struct cnxk_dpi_vf_s *dpivf = dev_private;
+	struct cnxk_dpi_conf *dpi_conf = &dpivf->conf[vchan];
+	struct cnxk_dpi_cdesc_data_s *c_desc = &dpi_conf->c_desc;
+	struct rte_dma_op *op;
+	uint16_t space, cnt;
+	uint8_t status;
+
+	space = (c_desc->tail - c_desc->head) & c_desc->max_cnt;
+	space = RTE_MIN(nb_ops, space);
+	for (cnt = 0; cnt < space; cnt++) {
+		status = c_desc->compl_ptr[c_desc->head * CNXK_DPI_COMPL_OFFSET];
+		op = c_desc->ops[c_desc->head];
+		op->status = status;
+		ops[cnt] = op;
+		if (status) {
+			if (status == CNXK_DPI_REQ_CDATA)
+				break;
+			dpi_conf->stats.errors++;
+		}
+		c_desc->compl_ptr[c_desc->head * CNXK_DPI_COMPL_OFFSET] = CNXK_DPI_REQ_CDATA;
+		CNXK_DPI_STRM_INC(*c_desc, head);
+	}
+
+	dpi_conf->stats.completed += cnt;
+
+	return cnt;
+}
-- 
2.43.0