test/service: fix race condition on stopping lcore

This commit fixes a potential race condition in the tests
where the lcore running a service would increment a counter
that was already reset by the test-suite thread. The resulting
race-condition incremented value could cause CI failures, as
indicated by DPDK's CI.

This patch fixes the race-condition by making use of the
added rte_service_lcore_active() API, which indicates when
a service-core is no longer in the service-core polling loop.

The unit test makes use of the above function to detect when
all statistics increments are done in the service-core thread,
and then the unit test continues finalizing and checking state.

Fixes: f28f3594ded2 ("service: add attribute API")

Reported-by: David Marchand <david.marchand@redhat.com>
Signed-off-by: Harry van Haaren <harry.van.haaren@intel.com>
Reviewed-by: Phil Yang <phil.yang@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>

diff --git a/app/test/test_service_cores.c b/app/test/test_service_cores.c
index ef1d8fc..5d92bea 100644 (file)
--- a/app/test/test_service_cores.c
+++ b/app/test/test_service_cores.c
@@ -362,6 +362,9 @@ service_lcore_attr_get(void)
                        "Service core add did not return zero");
        TEST_ASSERT_EQUAL(0, rte_service_map_lcore_set(id, slcore_id, 1),
                        "Enabling valid service and core failed");
+       /* Ensure service is not active before starting */
+       TEST_ASSERT_EQUAL(0, rte_service_lcore_may_be_active(slcore_id),
+                       "Not-active service core reported as active");
        TEST_ASSERT_EQUAL(0, rte_service_lcore_start(slcore_id),
                        "Starting service core failed");
 
@@ -382,7 +385,23 @@ service_lcore_attr_get(void)
                        lcore_attr_id, &lcore_attr_value),
                        "Invalid lcore attr didn't return -EINVAL");
 
-       rte_service_lcore_stop(slcore_id);
+       /* Ensure service is active */
+       TEST_ASSERT_EQUAL(1, rte_service_lcore_may_be_active(slcore_id),
+                       "Active service core reported as not-active");
+
+       TEST_ASSERT_EQUAL(0, rte_service_map_lcore_set(id, slcore_id, 0),
+                       "Disabling valid service and core failed");
+       TEST_ASSERT_EQUAL(0, rte_service_lcore_stop(slcore_id),
+                       "Failed to stop service lcore");
+
+       /* Wait until service lcore not active, or for 100x SERVICE_DELAY */
+       int i;
+       for (i = 0; rte_service_lcore_may_be_active(slcore_id) == 1 &&
+                       i < 100; i++)
+               rte_delay_ms(SERVICE_DELAY);
+
+       TEST_ASSERT_EQUAL(0, rte_service_lcore_may_be_active(slcore_id),
+                         "Service lcore not stopped after waiting.");
 
        TEST_ASSERT_EQUAL(0, rte_service_lcore_attr_reset_all(slcore_id),
                          "Valid lcore_attr_reset_all() didn't return success");