[dpdk-dev] [PATCH 1/1] event/dlb2: fix vector based dequeue

["McDaniel, Timothy" <timothy.mcdaniel@intel.com>]

From: Timothy McDaniel <timothy.mcdaniel@intel.com>

This commit fixes the following bugs in the vector based
dequeue path:
- extract hw sched type
- update xstats

The default mode of operation was also changed from vector
optimized mode to scalar mode.

Fixes: 000a7b8e7582 ("event/dlb2: optimize dequeue operation")
Cc: timothy.mcdaniel@intel.com

Signed-off-by: Timothy McDaniel <timothy.mcdaniel@intel.com>
---
 drivers/event/dlb2/dlb2.c      | 40 ++++++++++++++++++++++++----------
 drivers/event/dlb2/dlb2_priv.h |  7 +++---
 2 files changed, 31 insertions(+), 16 deletions(-)

diff --git a/drivers/event/dlb2/dlb2.c b/drivers/event/dlb2/dlb2.c
index 3570678b9..b5745f6f4 100644
--- a/drivers/event/dlb2/dlb2.c
+++ b/drivers/event/dlb2/dlb2.c
@@ -376,11 +376,11 @@ set_default_depth_thresh(const char *key __rte_unused,
 }
 
 static int
-set_vector_opts_disab(const char *key __rte_unused,
+set_vector_opts_enab(const char *key __rte_unused,
 	const char *value,
 	void *opaque)
 {
-	bool *dlb2_vector_opts_disabled = opaque;
+	bool *dlb2_vector_opts_enabled = opaque;
 
 	if (value == NULL || opaque == NULL) {
 		DLB2_LOG_ERR("NULL pointer\n");
@@ -388,9 +388,9 @@ set_vector_opts_disab(const char *key __rte_unused,
 	}
 
 	if ((*value == 'y') || (*value == 'Y'))
-		*dlb2_vector_opts_disabled = true;
+		*dlb2_vector_opts_enabled = true;
 	else
-		*dlb2_vector_opts_disabled = false;
+		*dlb2_vector_opts_enabled = false;
 
 	return 0;
 }
@@ -1469,7 +1469,7 @@ dlb2_hw_create_ldb_port(struct dlb2_eventdev *dlb2,
 #else
 	if ((qm_port->cq_depth > 64) ||
 	    (!rte_is_power_of_2(qm_port->cq_depth)) ||
-	    (dlb2->vector_opts_disabled == true))
+	    (dlb2->vector_opts_enabled == false))
 		qm_port->use_scalar = true;
 #endif
 
@@ -1665,7 +1665,7 @@ dlb2_hw_create_dir_port(struct dlb2_eventdev *dlb2,
 #else
 	if ((qm_port->cq_depth > 64) ||
 	    (!rte_is_power_of_2(qm_port->cq_depth)) ||
-	    (dlb2->vector_opts_disabled == true))
+	    (dlb2->vector_opts_enabled == false))
 		qm_port->use_scalar = true;
 #endif
 
@@ -3561,6 +3561,11 @@ _process_deq_qes_vec_impl(struct dlb2_port *qm_port,
 	int ev_qid2 = qm_port->qid_mappings[hw_qid2];
 	int ev_qid3 = qm_port->qid_mappings[hw_qid3];
 
+	int hw_sched0 = _mm_extract_epi8(v_qe_meta, 3) & 3ul;
+	int hw_sched1 = _mm_extract_epi8(v_qe_meta, 7) & 3ul;
+	int hw_sched2 = _mm_extract_epi8(v_qe_meta, 11) & 3ul;
+	int hw_sched3 = _mm_extract_epi8(v_qe_meta, 15) & 3ul;
+
 	v_qid_done = _mm_insert_epi8(v_qid_done, ev_qid0, 2);
 	v_qid_done = _mm_insert_epi8(v_qid_done, ev_qid1, 6);
 	v_qid_done = _mm_insert_epi8(v_qid_done, ev_qid2, 10);
@@ -3682,19 +3687,30 @@ _process_deq_qes_vec_impl(struct dlb2_port *qm_port,
 		v_ev_3 = _mm_blend_epi16(v_unpk_ev_23, v_qe_3, 0x0F);
 		v_ev_3 = _mm_alignr_epi8(v_ev_3, v_ev_3, 8);
 		_mm_storeu_si128((__m128i *)&events[3], v_ev_3);
+		DLB2_INC_STAT(qm_port->ev_port->stats.rx_sched_cnt[hw_sched3],
+			      1);
+
 		/* fallthrough */
 	case 3:
 		v_ev_2 = _mm_unpacklo_epi64(v_unpk_ev_23, v_qe_2);
 		_mm_storeu_si128((__m128i *)&events[2], v_ev_2);
+		DLB2_INC_STAT(qm_port->ev_port->stats.rx_sched_cnt[hw_sched2],
+					      1);
 		/* fallthrough */
 	case 2:
 		v_ev_1 = _mm_blend_epi16(v_unpk_ev_01, v_qe_1, 0x0F);
 		v_ev_1 = _mm_alignr_epi8(v_ev_1, v_ev_1, 8);
 		_mm_storeu_si128((__m128i *)&events[1], v_ev_1);
+		DLB2_INC_STAT(qm_port->ev_port->stats.rx_sched_cnt[hw_sched1],
+		1);
+
 		/* fallthrough */
 	case 1:
 		v_ev_0 = _mm_unpacklo_epi64(v_unpk_ev_01, v_qe_0);
 		_mm_storeu_si128((__m128i *)&events[0], v_ev_0);
+		DLB2_INC_STAT(qm_port->ev_port->stats.rx_sched_cnt[hw_sched0],
+			      1);
+
 	}
 }
 
@@ -4421,7 +4437,7 @@ dlb2_primary_eventdev_probe(struct rte_eventdev *dev,
 	dlb2->poll_interval = dlb2_args->poll_interval;
 	dlb2->sw_credit_quanta = dlb2_args->sw_credit_quanta;
 	dlb2->default_depth_thresh = dlb2_args->default_depth_thresh;
-	dlb2->vector_opts_disabled = dlb2_args->vector_opts_disabled;
+	dlb2->vector_opts_enabled = dlb2_args->vector_opts_enabled;
 
 	err = dlb2_iface_open(&dlb2->qm_instance, name);
 	if (err < 0) {
@@ -4525,7 +4541,7 @@ dlb2_parse_params(const char *params,
 					     DLB2_POLL_INTERVAL_ARG,
 					     DLB2_SW_CREDIT_QUANTA_ARG,
 					     DLB2_DEPTH_THRESH_ARG,
-					     DLB2_VECTOR_OPTS_DISAB_ARG,
+					     DLB2_VECTOR_OPTS_ENAB_ARG,
 					     NULL };
 
 	if (params != NULL && params[0] != '\0') {
@@ -4640,11 +4656,11 @@ dlb2_parse_params(const char *params,
 			}
 
 			ret = rte_kvargs_process(kvlist,
-					DLB2_VECTOR_OPTS_DISAB_ARG,
-					set_vector_opts_disab,
-					&dlb2_args->vector_opts_disabled);
+					DLB2_VECTOR_OPTS_ENAB_ARG,
+					set_vector_opts_enab,
+					&dlb2_args->vector_opts_enabled);
 			if (ret != 0) {
-				DLB2_LOG_ERR("%s: Error parsing vector opts disabled",
+				DLB2_LOG_ERR("%s: Error parsing vector opts enabled",
 					     name);
 				rte_kvargs_free(kvlist);
 				return ret;
diff --git a/drivers/event/dlb2/dlb2_priv.h b/drivers/event/dlb2/dlb2_priv.h
index 3140764a5..e23702100 100644
--- a/drivers/event/dlb2/dlb2_priv.h
+++ b/drivers/event/dlb2/dlb2_priv.h
@@ -32,13 +32,12 @@
 #define DLB2_MAX_NUM_EVENTS "max_num_events"
 #define DLB2_NUM_DIR_CREDITS "num_dir_credits"
 #define DEV_ID_ARG "dev_id"
-#define DLB2_DEFER_SCHED_ARG "defer_sched"
 #define DLB2_QID_DEPTH_THRESH_ARG "qid_depth_thresh"
 #define DLB2_COS_ARG "cos"
 #define DLB2_POLL_INTERVAL_ARG "poll_interval"
 #define DLB2_SW_CREDIT_QUANTA_ARG "sw_credit_quanta"
 #define DLB2_DEPTH_THRESH_ARG "default_depth_thresh"
-#define DLB2_VECTOR_OPTS_DISAB_ARG "vector_opts_disable"
+#define DLB2_VECTOR_OPTS_ENAB_ARG "vector_opts_enable"
 
 /* Begin HW related defines and structs */
 
@@ -566,7 +565,7 @@ struct dlb2_eventdev {
 	uint32_t new_event_limit;
 	int max_num_events_override;
 	int num_dir_credits_override;
-	bool vector_opts_disabled;
+	bool vector_opts_enabled;
 	volatile enum dlb2_run_state run_state;
 	uint16_t num_dir_queues; /* total num of evdev dir queues requested */
 	union {
@@ -626,7 +625,7 @@ struct dlb2_devargs {
 	int poll_interval;
 	int sw_credit_quanta;
 	int default_depth_thresh;
-	bool vector_opts_disabled;
+	bool vector_opts_enabled;
 };
 
 /* End Eventdev related defines and structs */
-- 
2.23.0