On all architectures except Power, the NUMA topology is never
reconfigured after a CPU has been associated with a NUMA node in the
system lifetime.
Even on Power, we can assume that NUMA topology reconfiguration happens
rarely, and therefore we do not expect it to happen while the NUMA test
is running.
This test validates that the mapping between a mm_numa_cid and a numa
node id remains valid for the process lifetime. In other words, it
validates that if any thread within the process running on behalf of a
mm_numa_cid N observes a NUMA node id M, all threads within this process
will always observe the same NUMA node id value when running on behalf
of that same mm_numa_cid.
This characteristic is important for NUMA locality.
This test is skipped on architectures that do not implement
rseq_load_u32_u32.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
---
tools/testing/selftests/rseq/.gitignore | 1 +
tools/testing/selftests/rseq/Makefile | 2 +-
.../testing/selftests/rseq/basic_numa_test.c | 117 ++++++++++++++++++
3 files changed, 119 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/rseq/basic_numa_test.c
@@ -1,4 +1,5 @@
# SPDX-License-Identifier: GPL-2.0-only
+basic_numa_test
basic_percpu_ops_test
basic_percpu_ops_mm_cid_test
basic_test
@@ -12,7 +12,7 @@ LDLIBS += -lpthread -ldl
# still track changes to header files and depend on shared object.
OVERRIDE_TARGETS = 1
-TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \
+TEST_GEN_PROGS = basic_test basic_numa_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \
param_test_benchmark param_test_compare_twice param_test_mm_cid \
param_test_mm_cid_benchmark param_test_mm_cid_compare_twice
new file mode 100644
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Basic rseq NUMA test. Validate that (mm_numa_cid, numa_node_id) pairs
+ * are invariant. The only known scenario where this is untrue is on Power
+ * which can reconfigure the NUMA topology on CPU hotunplug/hotplug sequence.
+ */
+
+#define _GNU_SOURCE
+#include <assert.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/time.h>
+
+#include "rseq.h"
+
+#define NR_LOOPS 100000000
+#define NR_THREADS 16
+
+#ifdef RSEQ_ARCH_HAS_LOAD_U32_U32
+
+static
+int cpu_numa_id[CPU_SETSIZE];
+
+static
+void numa_id_init(void)
+{
+ int i;
+
+ for (i = 0; i < CPU_SETSIZE; i++)
+ cpu_numa_id[i] = -1;
+}
+
+static
+void *test_thread(void *arg)
+{
+ int i;
+
+ if (rseq_register_current_thread()) {
+ fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+ errno, strerror(errno));
+ abort();
+ }
+
+ for (i = 0; i < NR_LOOPS; i++) {
+ uint32_t mm_numa_cid, node;
+ int cached_node_id;
+
+ while (rseq_load_u32_u32(RSEQ_MO_RELAXED, &mm_numa_cid,
+ &rseq_get_abi()->mm_numa_cid,
+ &node, &rseq_get_abi()->node_id) != 0) {
+ /* Retry. */
+ }
+ cached_node_id = RSEQ_READ_ONCE(cpu_numa_id[mm_numa_cid]);
+ if (cached_node_id == -1) {
+ RSEQ_WRITE_ONCE(cpu_numa_id[mm_numa_cid], node);
+ } else {
+ if (node != cached_node_id) {
+ fprintf(stderr, "Error: NUMA node id discrepancy: mm_numa_cid %u cached node id %d node id %u.\n",
+ mm_numa_cid, cached_node_id, node);
+ fprintf(stderr, "This is likely a kernel bug, or caused by a concurrent NUMA topology reconfiguration.\n");
+ abort();
+ }
+ }
+ }
+
+ if (rseq_unregister_current_thread()) {
+ fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+ errno, strerror(errno));
+ abort();
+ }
+ return NULL;
+}
+
+static
+int test_numa(void)
+{
+ pthread_t tid[NR_THREADS];
+ int err, i;
+ void *tret;
+
+ numa_id_init();
+
+ printf("testing rseq (mm_numa_cid, numa_node_id) invariant, single thread\n");
+
+ (void) test_thread(NULL);
+
+ printf("testing rseq (mm_numa_cid, numa_node_id) invariant, multi-threaded\n");
+
+ for (i = 0; i < NR_THREADS; i++) {
+ err = pthread_create(&tid[i], NULL, test_thread, NULL);
+ if (err != 0)
+ abort();
+ }
+
+ for (i = 0; i < NR_THREADS; i++) {
+ err = pthread_join(tid[i], &tret);
+ if (err != 0)
+ abort();
+ }
+
+ return 0;
+}
+#else
+static
+int test_numa(void)
+{
+ fprintf(stderr, "rseq_load_u32_u32 is not implemented on this architecture. Skipping numa test.\n");
+ return 0;
+}
+#endif
+
+int main(int argc, char **argv)
+{
+ return test_numa();
+}