[PATCH v5 2/3] graph: add node error counters

[<pbhagavatula@marvell.com>]

From: Pavan Nikhilesh <pbhagavatula@marvell.com>

Add node fastpath error counters advertised during node
registration.
Add support for retrieving/printing stats for node specific
errors using rte_graph_cluster_stats_get().
Add `rte_node_error_increment` API to increment node specific
error counters.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Acked-by: Kiran Kumar K <kirankumark@marvell.com>
Reviewed-by: Robin Jarry <rjarry@redhat.com>
---
 lib/graph/graph_populate.c          | 20 +++++++-
 lib/graph/graph_private.h           |  2 +
 lib/graph/graph_stats.c             | 78 ++++++++++++++++++++++++++++-
 lib/graph/rte_graph.h               |  4 ++
 lib/graph/rte_graph_worker_common.h | 23 +++++++++
 lib/graph/version.map               |  7 +++
 6 files changed, 131 insertions(+), 3 deletions(-)

diff --git a/lib/graph/graph_populate.c b/lib/graph/graph_populate.c
index ed596a7711..1246f72d0f 100644
--- a/lib/graph/graph_populate.c
+++ b/lib/graph/graph_populate.c
@@ -39,6 +39,15 @@ graph_fp_mem_calc_size(struct graph *graph)
 		/* Pointer to next nodes(edges) */
 		sz += sizeof(struct rte_node *) * graph_node->node->nb_edges;
 	}
+	sz = RTE_ALIGN(sz, RTE_CACHE_LINE_SIZE);
+	graph->errors_start = sz;
+	/* For 0..N node objects with error counters */
+	STAILQ_FOREACH(graph_node, &graph->node_list, next) {
+		if (graph_node->node->errs == NULL)
+			continue;
+		sz = RTE_ALIGN(sz, RTE_CACHE_LINE_SIZE);
+		sz += sizeof(uint64_t) * graph_node->node->errs->nb_errors;
+	}

 	graph->mem_sz = sz;
 	return sz;
@@ -64,6 +73,7 @@ graph_header_popluate(struct graph *_graph)
 static void
 graph_nodes_populate(struct graph *_graph)
 {
+	rte_graph_off_t err_off = _graph->errors_start;
 	rte_graph_off_t off = _graph->nodes_start;
 	struct rte_graph *graph = _graph->graph;
 	struct graph_node *graph_node;
@@ -99,6 +109,12 @@ graph_nodes_populate(struct graph *_graph)
 						     ->adjacency_list[count]
 						     ->node->name[0];

+		if (graph_node->node->errs != NULL) {
+			node->err_off = err_off - off;
+			err_off += sizeof(uint64_t) * graph_node->node->errs->nb_errors;
+			err_off = RTE_ALIGN(err_off, RTE_CACHE_LINE_SIZE);
+		}
+
 		off += sizeof(struct rte_node *) * nb_edges;
 		off = RTE_ALIGN(off, RTE_CACHE_LINE_SIZE);
 		node->next = off;
@@ -158,7 +174,7 @@ graph_node_nexts_populate(struct graph *_graph)
 }

 static int
-graph_src_nodes_populate(struct graph *_graph)
+graph_src_nodes_offset_populate(struct graph *_graph)
 {
 	struct rte_graph *graph = _graph->graph;
 	struct graph_node *graph_node;
@@ -193,7 +209,7 @@ graph_fp_mem_populate(struct graph *graph)
 		graph_pcap_init(graph);
 	graph_nodes_populate(graph);
 	rc = graph_node_nexts_populate(graph);
-	rc |= graph_src_nodes_populate(graph);
+	rc |= graph_src_nodes_offset_populate(graph);

 	return rc;
 }
diff --git a/lib/graph/graph_private.h b/lib/graph/graph_private.h
index e663b04d8b..01921b254c 100644
--- a/lib/graph/graph_private.h
+++ b/lib/graph/graph_private.h
@@ -103,6 +103,8 @@ struct graph {
 	/**< Memzone to store graph data. */
 	rte_graph_off_t nodes_start;
 	/**< Node memory start offset in graph reel. */
+	rte_graph_off_t errors_start;
+	/**< Node error memory start offset in graph reel. */
 	rte_node_t src_node_count;
 	/**< Number of source nodes in a graph. */
 	struct rte_graph *graph;
diff --git a/lib/graph/graph_stats.c b/lib/graph/graph_stats.c
index d71451a17b..44a3ea03a7 100644
--- a/lib/graph/graph_stats.c
+++ b/lib/graph/graph_stats.c
@@ -121,6 +121,24 @@ print_node(FILE *f, const struct rte_graph_cluster_node_stats *stat, bool dispat
 	}
 }

+static inline void
+print_err(FILE *f, const struct rte_graph_cluster_node_stats *stat, bool dispatch)
+{
+	int i;
+
+	if (dispatch) {
+		for (i = 0; i < stat->error_cntrs; i++)
+			fprintf(f,
+				"|\t%-24s|%15s|%-15" PRIu64 "|%15s|%15s|%15s|%15s|%15s|%11.4s|\n",
+				stat->error_desc[i], "", stat->error_count[i], "", "", "", "", "",
+				"");
+	} else {
+		for (i = 0; i < stat->error_cntrs; i++)
+			fprintf(f, "|\t%-24s|%15s|%-15" PRIu64 "|%15s|%15.3s|%15.6s|%11.4s|\n",
+				stat->error_desc[i], "", stat->error_count[i], "", "", "", "");
+	}
+}
+
 static int
 graph_cluster_stats_cb(bool dispatch, bool is_first, bool is_last, void *cookie,
 		       const struct rte_graph_cluster_node_stats *stat)
@@ -129,8 +147,11 @@ graph_cluster_stats_cb(bool dispatch, bool is_first, bool is_last, void *cookie,

 	if (unlikely(is_first))
 		print_banner(f, dispatch);
-	if (stat->objs)
+	if (stat->objs) {
 		print_node(f, stat, dispatch);
+		if (stat->error_cntrs)
+			print_err(f, stat, dispatch);
+	}
 	if (unlikely(is_last)) {
 		if (dispatch)
 			boarder_model_dispatch();
@@ -203,6 +224,7 @@ stats_mem_populate(struct rte_graph_cluster_stats **stats_in,
 	struct cluster_node *cluster;
 	struct rte_node *node;
 	rte_node_t count;
+	uint8_t i;

 	cluster = stats->clusters;

@@ -240,6 +262,36 @@ stats_mem_populate(struct rte_graph_cluster_stats **stats_in,
 		SET_ERR_JMP(ENOENT, free, "Failed to find node %s in graph %s",
 			    graph_node->node->name, graph->name);
 	cluster->nodes[cluster->nb_nodes++] = node;
+	if (graph_node->node->errs) {
+		cluster->stat.error_cntrs = graph_node->node->errs->nb_errors;
+		cluster->stat.error_count = rte_zmalloc_socket(
+			NULL, sizeof(uint64_t) * graph_node->node->errs->nb_errors,
+			RTE_CACHE_LINE_SIZE, stats->socket_id);
+		if (cluster->stat.error_count == NULL)
+			SET_ERR_JMP(ENOMEM, free, "Failed to allocate memory node %s graph %s",
+				    graph_node->node->name, graph->name);
+
+		cluster->stat.error_desc = rte_zmalloc_socket(
+			NULL, sizeof(RTE_NODE_ERROR_DESC_SIZE) * graph_node->node->errs->nb_errors,
+			RTE_CACHE_LINE_SIZE, stats->socket_id);
+		if (cluster->stat.error_desc == NULL) {
+			rte_free(cluster->stat.error_count);
+			SET_ERR_JMP(ENOMEM, free, "Failed to allocate memory node %s graph %s",
+				    graph_node->node->name, graph->name);
+		}
+
+		for (i = 0; i < cluster->stat.error_cntrs; i++) {
+			if (rte_strscpy(cluster->stat.error_desc[i],
+					graph_node->node->errs->err_desc[i],
+					RTE_NODE_ERROR_DESC_SIZE) < 0) {
+				rte_free(cluster->stat.error_count);
+				rte_free(cluster->stat.error_desc);
+				SET_ERR_JMP(E2BIG, free,
+					    "Error description overflow node %s graph %s",
+					    graph_node->node->name, graph->name);
+			}
+		}
+	}

 	stats->sz += stats->cluster_node_size;
 	stats->max_nodes++;
@@ -388,6 +440,18 @@ rte_graph_cluster_stats_create(const struct rte_graph_cluster_stats_param *prm)
 void
 rte_graph_cluster_stats_destroy(struct rte_graph_cluster_stats *stat)
 {
+	struct cluster_node *cluster;
+	rte_node_t count;
+
+	cluster = stat->clusters;
+	for (count = 0; count < stat->max_nodes; count++) {
+		if (cluster->stat.error_cntrs) {
+			rte_free(cluster->stat.error_count);
+			rte_free(cluster->stat.error_desc);
+		}
+
+		cluster = RTE_PTR_ADD(cluster, stat->cluster_node_size);
+	}
 	return rte_free(stat);
 }

@@ -399,7 +463,10 @@ cluster_node_arregate_stats(struct cluster_node *cluster, bool dispatch)
 	uint64_t sched_objs = 0, sched_fail = 0;
 	struct rte_node *node;
 	rte_node_t count;
+	uint64_t *err;
+	uint8_t i;

+	memset(stat->error_count, 0, sizeof(uint64_t) * stat->error_cntrs);
 	for (count = 0; count < cluster->nb_nodes; count++) {
 		node = cluster->nodes[count];

@@ -412,6 +479,12 @@ cluster_node_arregate_stats(struct cluster_node *cluster, bool dispatch)
 		objs += node->total_objs;
 		cycles += node->total_cycles;
 		realloc_count += node->realloc_count;
+
+		if (node->err_off == 0)
+			continue;
+		err = RTE_PTR_ADD(node, node->err_off);
+		for (i = 0; i < stat->error_cntrs; i++)
+			stat->error_count[i] += err[i];
 	}

 	stat->calls = calls;
@@ -464,6 +537,7 @@ rte_graph_cluster_stats_reset(struct rte_graph_cluster_stats *stat)
 {
 	struct cluster_node *cluster;
 	rte_node_t count;
+	uint8_t i;

 	cluster = stat->clusters;

@@ -479,6 +553,8 @@ rte_graph_cluster_stats_reset(struct rte_graph_cluster_stats *stat)
 		node->prev_objs = 0;
 		node->prev_cycles = 0;
 		node->realloc_count = 0;
+		for (i = 0; i < node->error_cntrs; i++)
+			node->error_count[i] = 0;
 		cluster = RTE_PTR_ADD(cluster, stat->cluster_node_size);
 	}
 }
diff --git a/lib/graph/rte_graph.h b/lib/graph/rte_graph.h
index b28143d737..6a9620c2d4 100644
--- a/lib/graph/rte_graph.h
+++ b/lib/graph/rte_graph.h
@@ -223,6 +223,10 @@ struct __rte_cache_aligned rte_graph_cluster_node_stats {

 	uint64_t realloc_count; /**< Realloc count. */

+	uint8_t error_cntrs;			      /**< Number of Node error counters. */
+	char (*error_desc)[RTE_NODE_ERROR_DESC_SIZE]; /**< Names of the Node error counters. */
+	uint64_t *error_count;			      /**< Total error count per each error. */
+
 	rte_node_t id;	/**< Node identifier of stats. */
 	uint64_t hz;	/**< Cycles per seconds. */
 	char name[RTE_NODE_NAMESIZE];	/**< Name of the node. */
diff --git a/lib/graph/rte_graph_worker_common.h b/lib/graph/rte_graph_worker_common.h
index 8d8956fddd..ae3282fb66 100644
--- a/lib/graph/rte_graph_worker_common.h
+++ b/lib/graph/rte_graph_worker_common.h
@@ -112,6 +112,7 @@ struct __rte_cache_aligned rte_node {
 			uint64_t total_sched_fail; /**< Number of scheduled failure. */
 		} dispatch;
 	};
+	rte_graph_off_t err_off; /**< Offset to error counters. */
 	/* Fast path area  */
 	__extension__ struct __rte_cache_aligned {
 #define RTE_NODE_CTX_SZ 16
@@ -584,6 +585,28 @@ uint8_t rte_graph_worker_model_no_check_get(struct rte_graph *graph)
 	return graph->model;
 }

+/**
+ * Increment Node error count.
+ *
+ * Increment the error count of an error for a given node.
+ *
+ * @param node
+ *   Pointer to the node.
+ * @param err_id
+ *   Error ID.
+ * @param value
+ *   Value to increment.
+ */
+__rte_experimental
+static inline void
+rte_node_error_increment(struct rte_node *node, uint16_t err_id, uint64_t value)
+{
+	if (rte_graph_has_stats_feature()) {
+		uint64_t *errors = (uint64_t *)RTE_PTR_ADD(node, node->err_off);
+		errors[err_id] += value;
+	}
+}
+
 #ifdef __cplusplus
 }
 #endif
diff --git a/lib/graph/version.map b/lib/graph/version.map
index 2c83425ddc..b79aca6b3d 100644
--- a/lib/graph/version.map
+++ b/lib/graph/version.map
@@ -52,3 +52,10 @@ DPDK_25 {

 	local: *;
 };
+
+EXPERIMENTAL {
+	global:
+
+	# added in 24.11
+	rte_node_error_increment;
+};
--
2.25.1