[dpdk-stable] [PATCH v4 4/7] app/flow-perf: fix report total stats for masked ports

[dpdk-stable] [PATCH v4 4/7] app/flow-perf: fix report total stats for masked ports

[Wisam Jaddo]

Take into consideration that the user may call portmask for
any run, thus the app should always check if port is needed
to collect and report or not.

Fixes: 070316d01d3e ("app/flow-perf: add multi-core rule insertion and deletion")
Fixes: d8099d7ecbd0 ("app/flow-perf: split dump functions")
Cc: dongzhou@nvidia.com
Cc: stable@dpdk.org

Signed-off-by: Wisam Jaddo <wisamm@nvidia.com>
Acked-by: Alexander Kozyrev <akozyrev@nvidia.com>
---
 app/test-flow-perf/main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/app/test-flow-perf/main.c b/app/test-flow-perf/main.c
index 01607881df..e32714131c 100644
--- a/app/test-flow-perf/main.c
+++ b/app/test-flow-perf/main.c
@@ -1437,6 +1437,9 @@ run_rte_flow_handler_cores(void *data __rte_unused)
 	rte_eal_mp_wait_lcore();
 
 	RTE_ETH_FOREACH_DEV(port) {
+		/* If port outside portmask */
+		if (!((ports_mask >> port) & 0x1))
+			continue;
 		if (has_meter())
 			dump_used_cpu_time("Meters:",
 				port, &mc_pool.meters_record);
-- 
2.17.1

[dpdk-stable] [PATCH v4 5/7] app/flow-perf: fix the incremental IPv6 src set

[Wisam Jaddo]

Currently the memset() will not set a correct src ip that represent
the incremental value of the counter.

This commit will fix this and each flow will have correct IPv6.src
that it's incremental from previous flow and equal to the decimal
values.

Fixes: bf3688f1e816 ("app/flow-perf: add insertion rate calculation")
Cc: wisamm@mellanox.com
Cc: stable@dpdk.org

Signed-off-by: Wisam Jaddo <wisamm@nvidia.com>
Acked-by: Alexander Kozyrev <akozyrev@nvidia.com>
---
 app/test-flow-perf/items_gen.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/app/test-flow-perf/items_gen.c b/app/test-flow-perf/items_gen.c
index ccebc08b39..a73de9031f 100644
--- a/app/test-flow-perf/items_gen.c
+++ b/app/test-flow-perf/items_gen.c
@@ -72,14 +72,15 @@ add_ipv6(struct rte_flow_item *items,
 	static struct rte_flow_item_ipv6 ipv6_specs[RTE_MAX_LCORE] __rte_cache_aligned;
 	static struct rte_flow_item_ipv6 ipv6_masks[RTE_MAX_LCORE] __rte_cache_aligned;
 	uint8_t ti = para.core_idx;
+	uint8_t i;
 
 	/** Set ipv6 src **/
-	memset(&ipv6_specs[ti].hdr.src_addr, para.src_ip,
-		sizeof(ipv6_specs->hdr.src_addr) / 2);
-
-	/** Full mask **/
-	memset(&ipv6_masks[ti].hdr.src_addr, 0xff,
-		sizeof(ipv6_specs->hdr.src_addr));
+	for (i = 0; i < 16; i++) {
+		/* Currently src_ip is limited to 32 bit */
+		if (i < 4)
+			ipv6_specs[ti].hdr.src_addr[15 - i] = para.src_ip >> (i * 8);
+		ipv6_masks[ti].hdr.src_addr[15 - i] = 0xff;
+	}
 
 	items[items_counter].type = RTE_FLOW_ITEM_TYPE_IPV6;
 	items[items_counter].spec = &ipv6_specs[ti];
-- 
2.17.1

[dpdk-stable] [PATCH v4 7/7] app/flow-perf: fix setting decap data for decap actions

[Wisam Jaddo]

When using decap actions it's been set to the data to decap
into the encap_data instead of decap_data, as a results we end
up with bad encap and decap data in many cases.

Fixes: 0c8f1f4ab90e ("app/flow-perf: support raw encap/decap actions")
Cc: stable@dpdk.org

Signed-off-by: Wisam Jaddo <wisamm@nvidia.com>
Acked-by: Alexander Kozyrev <akozyrev@nvidia.com>
---
 app/test-flow-perf/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/app/test-flow-perf/main.c b/app/test-flow-perf/main.c
index d33b00a89e..97a4d4ac63 100644
--- a/app/test-flow-perf/main.c
+++ b/app/test-flow-perf/main.c
@@ -730,7 +730,7 @@ args_parse(int argc, char **argv)
 					for (i = 0; i < RTE_DIM(flow_options); i++) {
 						if (strcmp(flow_options[i].str, token) == 0) {
 							printf("%s,", token);
-							encap_data |= flow_options[i].mask;
+							decap_data |= flow_options[i].mask;
 							break;
 						}
 						/* Reached last item with no match */
-- 
2.17.1