[PATCH v7] net/idpf: update for new mempool cache algorithm

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

As a consequence of the improved mempool cache algorithm, the PMD was
updated regarding how much to backfill the mempool cache in the AVX512
code path.

Signed-off-by: Morten Brørup <mb@smartsharesystems.com>
---
v7:
* Rebased.
v6:
* Moved driver changes out as separate patches, for easier review. (Bruce)
---
Depends-on: patch-164745 ("mempool: improve cache behaviour and performance")
---
 .../net/intel/idpf/idpf_common_rxtx_avx512.c  | 52 +++++++++++++++----
 1 file changed, 42 insertions(+), 10 deletions(-)

diff --git a/drivers/net/intel/idpf/idpf_common_rxtx_avx512.c b/drivers/net/intel/idpf/idpf_common_rxtx_avx512.c
index 8db4c64106..5788a009ab 100644
--- a/drivers/net/intel/idpf/idpf_common_rxtx_avx512.c
+++ b/drivers/net/intel/idpf/idpf_common_rxtx_avx512.c
@@ -148,15 +148,31 @@ idpf_singleq_rearm(struct idpf_rx_queue *rxq)
 	/* Can this be satisfied from the cache? */
 	if (cache->len < IDPF_RXQ_REARM_THRESH) {
 		/* No. Backfill the cache first, and then fill from it */
-		uint32_t req = IDPF_RXQ_REARM_THRESH + (cache->size -
-							cache->len);
 
-		/* How many do we require i.e. number to fill the cache + the request */
+		/* Backfill would exceed the cache bounce buffer limit? */
+		__rte_assume(cache->size / 2 <= RTE_MEMPOOL_CACHE_MAX_SIZE / 2);
+		if (unlikely(cache->size / 2 < IDPF_RXQ_REARM_THRESH)) {
+			idpf_singleq_rearm_common(rxq);
+			return;
+		}
+
+		/*
+		 * Backfill the cache from the backend;
+		 * move up the hot objects in the cache to the top half of the cache,
+		 * and fetch (size / 2) objects to the bottom of the cache.
+		 */
+		__rte_assume(cache->len < cache->size / 2);
+		rte_memcpy(&cache->objs[cache->size / 2], &cache->objs[0],
+				sizeof(void *) * cache->len);
 		int ret = rte_mempool_ops_dequeue_bulk
-				(rxq->mp, &cache->objs[cache->len], req);
+				(rxq->mp, &cache->objs[0], cache->size / 2);
 		if (ret == 0) {
-			cache->len += req;
+			cache->len += cache->size / 2;
 		} else {
+			/*
+			 * No further action is required for roll back, as the objects moved
+			 * in the cache were actually copied, and the cache remains intact.
+			 */
 			if (rxq->rxrearm_nb + IDPF_RXQ_REARM_THRESH >=
 			    rxq->nb_rx_desc) {
 				__m128i dma_addr0;
@@ -565,15 +581,31 @@ idpf_splitq_rearm(struct idpf_rx_queue *rx_bufq)
 	/* Can this be satisfied from the cache? */
 	if (cache->len < IDPF_RXQ_REARM_THRESH) {
 		/* No. Backfill the cache first, and then fill from it */
-		uint32_t req = IDPF_RXQ_REARM_THRESH + (cache->size -
-							cache->len);
 
-		/* How many do we require i.e. number to fill the cache + the request */
+		/* Backfill would exceed the cache bounce buffer limit? */
+		__rte_assume(cache->size / 2 <= RTE_MEMPOOL_CACHE_MAX_SIZE / 2);
+		if (unlikely(cache->size / 2 < IDPF_RXQ_REARM_THRESH)) {
+			idpf_splitq_rearm_common(rx_bufq);
+			return;
+		}
+
+		/*
+		 * Backfill the cache from the backend;
+		 * move up the hot objects in the cache to the top half of the cache,
+		 * and fetch (size / 2) objects to the bottom of the cache.
+		 */
+		__rte_assume(cache->len < cache->size / 2);
+		rte_memcpy(&cache->objs[cache->size / 2], &cache->objs[0],
+				sizeof(void *) * cache->len);
 		int ret = rte_mempool_ops_dequeue_bulk
-				(rx_bufq->mp, &cache->objs[cache->len], req);
+				(rx_bufq->mp, &cache->objs[0], cache->size / 2);
 		if (ret == 0) {
-			cache->len += req;
+			cache->len += cache->size / 2;
 		} else {
+			/*
+			 * No further action is required for roll back, as the objects moved
+			 * in the cache were actually copied, and the cache remains intact.
+			 */
 			if (rx_bufq->rxrearm_nb + IDPF_RXQ_REARM_THRESH >=
 			    rx_bufq->nb_rx_desc) {
 				__m128i dma_addr0;
-- 
2.43.0