[PATCH v3 2/3] mempool: add stats for unregistered non-EAL threads

["Morten Brørup" <mb@smartsharesystems.com>]

This patch adds statistics for unregistered non-EAL threads, which was
previously not included in the statistics.

Add one more entry to the stats array, and use the last index for
unregistered non-EAL threads.

The unregistered non-EAL thread statistics are incremented atomically.

In theory, the EAL thread counters should also be accessed atomically to
avoid tearing on 32 bit architectures. However, it was decided to avoid
the performance cost of using atomic operations, because:
1. these are debug counters, and
2. statistics counters in DPDK are usually incremented non-atomically.

v3 (feedback from Mattias Rönnblom):
* Use correct terminology: Unregistered non-EAL threads.
* Use atomic counting for the unregistered non-EAL threads.
* Reintroduce the conditional instead of offsetting the index by one.
v2:
* New. No v1 of this patch in the series.

Suggested-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Morten Brørup <mb@smartsharesystems.com>
---
 lib/mempool/rte_mempool.c |  2 +-
 lib/mempool/rte_mempool.h | 19 ++++++++++++-------
 2 files changed, 13 insertions(+), 8 deletions(-)

diff --git a/lib/mempool/rte_mempool.c b/lib/mempool/rte_mempool.c
index 62d1ce764e..e6208125e0 100644
--- a/lib/mempool/rte_mempool.c
+++ b/lib/mempool/rte_mempool.c
@@ -1272,7 +1272,7 @@ rte_mempool_dump(FILE *f, struct rte_mempool *mp)
 #ifdef RTE_LIBRTE_MEMPOOL_STATS
 	rte_mempool_ops_get_info(mp, &info);
 	memset(&sum, 0, sizeof(sum));
-	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
+	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE + 1; lcore_id++) {
 		sum.put_bulk += mp->stats[lcore_id].put_bulk;
 		sum.put_objs += mp->stats[lcore_id].put_objs;
 		sum.put_common_pool_bulk += mp->stats[lcore_id].put_common_pool_bulk;
diff --git a/lib/mempool/rte_mempool.h b/lib/mempool/rte_mempool.h
index 2afe332097..de6fceac5e 100644
--- a/lib/mempool/rte_mempool.h
+++ b/lib/mempool/rte_mempool.h
@@ -238,8 +238,11 @@ struct rte_mempool {
 	struct rte_mempool_memhdr_list mem_list; /**< List of memory chunks */
 
 #ifdef RTE_LIBRTE_MEMPOOL_STATS
-	/** Per-lcore statistics. */
-	struct rte_mempool_debug_stats stats[RTE_MAX_LCORE];
+	/** Per-lcore statistics.
+	 *
+	 * Plus one, for unregistered non-EAL threads.
+	 */
+	struct rte_mempool_debug_stats stats[RTE_MAX_LCORE + 1];
 #endif
 }  __rte_cache_aligned;
 
@@ -303,11 +306,13 @@ struct rte_mempool {
  *   Number to add to the statistics.
  */
 #ifdef RTE_LIBRTE_MEMPOOL_STATS
-#define RTE_MEMPOOL_STAT_ADD(mp, name, n) do {                  \
-		unsigned __lcore_id = rte_lcore_id();           \
-		if (__lcore_id < RTE_MAX_LCORE) {               \
-			mp->stats[__lcore_id].name += n;        \
-		}                                               \
+#define RTE_MEMPOOL_STAT_ADD(mp, name, n) do {                                  \
+		unsigned int __lcore_id = rte_lcore_id();                       \
+		if (likely(__lcore_id < RTE_MAX_LCORE))                         \
+			(mp)->stats[__lcore_id].name += n;                      \
+		else                                                            \
+			__atomic_fetch_add(&((mp)->stats[RTE_MAX_LCORE].name),  \
+					   n, __ATOMIC_RELAXED);                \
 	} while (0)
 #else
 #define RTE_MEMPOOL_STAT_ADD(mp, name, n) do {} while (0)
-- 
2.17.1