lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20221103200359.328736-23-mathieu.desnoyers@efficios.com>
Date:   Thu,  3 Nov 2022 16:03:57 -0400
From:   Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
To:     Peter Zijlstra <peterz@...radead.org>
Cc:     linux-kernel@...r.kernel.org, Thomas Gleixner <tglx@...utronix.de>,
        "Paul E . McKenney" <paulmck@...nel.org>,
        Boqun Feng <boqun.feng@...il.com>,
        "H . Peter Anvin" <hpa@...or.com>, Paul Turner <pjt@...gle.com>,
        linux-api@...r.kernel.org, Christian Brauner <brauner@...nel.org>,
        Florian Weimer <fw@...eb.enyo.de>, David.Laight@...LAB.COM,
        carlos@...hat.com, Peter Oskolkov <posk@...k.io>,
        Alexander Mikhalitsyn <alexander@...alicyn.com>,
        Chris Kennelly <ckennelly@...gle.com>,
        Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
Subject: [PATCH v5 22/24] selftests/rseq: Implement numa node id vs vm_vcpu_id invariant test

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 vm_vcpu_id 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
vm_vcpu_id 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 vm_vcpu_id.

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@...icios.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

diff --git a/tools/testing/selftests/rseq/.gitignore b/tools/testing/selftests/rseq/.gitignore
index db5c1a124c6c..9231abed69cc 100644
--- a/tools/testing/selftests/rseq/.gitignore
+++ b/tools/testing/selftests/rseq/.gitignore
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
+basic_numa_test
 basic_percpu_ops_test
 basic_percpu_ops_vm_vcpu_id_test
 basic_test
diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile
index 3eec8e166385..4bf5b7202254 100644
--- a/tools/testing/selftests/rseq/Makefile
+++ b/tools/testing/selftests/rseq/Makefile
@@ -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_vm_vcpu_id_test param_test \
+TEST_GEN_PROGS = basic_test basic_numa_test basic_percpu_ops_test basic_percpu_ops_vm_vcpu_id_test param_test \
 		param_test_benchmark param_test_compare_twice param_test_vm_vcpu_id \
 		param_test_vm_vcpu_id_benchmark param_test_vm_vcpu_id_compare_twice
 
diff --git a/tools/testing/selftests/rseq/basic_numa_test.c b/tools/testing/selftests/rseq/basic_numa_test.c
new file mode 100644
index 000000000000..45cb714b135c
--- /dev/null
+++ b/tools/testing/selftests/rseq/basic_numa_test.c
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Basic rseq NUMA test. Validate that (vm_vcpu_id, 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 vm_vcpu_id, node;
+		int cached_node_id;
+
+		while (rseq_load_u32_u32(RSEQ_MO_RELAXED, &vm_vcpu_id, &rseq_get_abi()->vm_vcpu_id,
+					 &node, &rseq_get_abi()->node_id) != 0) {
+			/* Retry. */
+		}
+		cached_node_id = RSEQ_READ_ONCE(cpu_numa_id[vm_vcpu_id]);
+		if (cached_node_id == -1) {
+			RSEQ_WRITE_ONCE(cpu_numa_id[vm_vcpu_id], node);
+		} else {
+			if (node != cached_node_id) {
+				fprintf(stderr, "Error: NUMA node id discrepancy: vm_vcpu_id %u cached node id %d node id %u.\n",
+					vm_vcpu_id, 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 (vm_vcpu_id, numa_node_id) invariant, single thread\n");
+
+	(void) test_thread(NULL);
+
+	printf("testing rseq (vm_vcpu_id, 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();
+}
-- 
2.25.1

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ