summaryrefslogtreecommitdiffstats
path: root/tools
diff options
context:
space:
mode:
authorMathieu Desnoyers <mathieu.desnoyers@efficios.com>2018-06-02 08:44:06 -0400
committerThomas Gleixner <tglx@linutronix.de>2018-06-06 11:58:35 +0200
commit01a5ec4217599fd78ba76fa7199a350c5fb4650f (patch)
tree1af689bd075fcee6ccf00453361d047817913d23 /tools
parent1badac4f80c3d325d6d1b9fc3b6344120aa799be (diff)
downloadlinux-stable-01a5ec4217599fd78ba76fa7199a350c5fb4650f.tar.gz
linux-stable-01a5ec4217599fd78ba76fa7199a350c5fb4650f.tar.bz2
linux-stable-01a5ec4217599fd78ba76fa7199a350c5fb4650f.zip
rseq/selftests: Provide basic percpu ops test
"basic_percpu_ops_test" is a slightly more "realistic" variant, implementing a few simple per-cpu operations and testing their correctness. Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Joel Fernandes <joelaf@google.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Watson <davejwatson@fb.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Shuah Khan <shuahkh@osg.samsung.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: linux-kselftest@vger.kernel.org Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Chris Lameter <cl@linux.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Andrew Hunter <ahh@google.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com> Cc: Paul Turner <pjt@google.com> Cc: Boqun Feng <boqun.feng@gmail.com> Cc: Josh Triplett <josh@joshtriplett.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Ben Maurer <bmaurer@fb.com> Cc: linux-api@vger.kernel.org Cc: Andy Lutomirski <luto@amacapital.net> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: https://lkml.kernel.org/r/20180602124408.8430-15-mathieu.desnoyers@efficios.com
Diffstat (limited to 'tools')
-rw-r--r--tools/testing/selftests/rseq/basic_percpu_ops_test.c312
1 files changed, 312 insertions, 0 deletions
diff --git a/tools/testing/selftests/rseq/basic_percpu_ops_test.c b/tools/testing/selftests/rseq/basic_percpu_ops_test.c
new file mode 100644
index 000000000000..eb3f6db36d36
--- /dev/null
+++ b/tools/testing/selftests/rseq/basic_percpu_ops_test.c
@@ -0,0 +1,312 @@
+// SPDX-License-Identifier: LGPL-2.1
+#define _GNU_SOURCE
+#include <assert.h>
+#include <pthread.h>
+#include <sched.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stddef.h>
+
+#include "rseq.h"
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+
+struct percpu_lock_entry {
+ intptr_t v;
+} __attribute__((aligned(128)));
+
+struct percpu_lock {
+ struct percpu_lock_entry c[CPU_SETSIZE];
+};
+
+struct test_data_entry {
+ intptr_t count;
+} __attribute__((aligned(128)));
+
+struct spinlock_test_data {
+ struct percpu_lock lock;
+ struct test_data_entry c[CPU_SETSIZE];
+ int reps;
+};
+
+struct percpu_list_node {
+ intptr_t data;
+ struct percpu_list_node *next;
+};
+
+struct percpu_list_entry {
+ struct percpu_list_node *head;
+} __attribute__((aligned(128)));
+
+struct percpu_list {
+ struct percpu_list_entry c[CPU_SETSIZE];
+};
+
+/* A simple percpu spinlock. Returns the cpu lock was acquired on. */
+int rseq_this_cpu_lock(struct percpu_lock *lock)
+{
+ int cpu;
+
+ for (;;) {
+ int ret;
+
+ cpu = rseq_cpu_start();
+ ret = rseq_cmpeqv_storev(&lock->c[cpu].v,
+ 0, 1, cpu);
+ if (rseq_likely(!ret))
+ break;
+ /* Retry if comparison fails or rseq aborts. */
+ }
+ /*
+ * Acquire semantic when taking lock after control dependency.
+ * Matches rseq_smp_store_release().
+ */
+ rseq_smp_acquire__after_ctrl_dep();
+ return cpu;
+}
+
+void rseq_percpu_unlock(struct percpu_lock *lock, int cpu)
+{
+ assert(lock->c[cpu].v == 1);
+ /*
+ * Release lock, with release semantic. Matches
+ * rseq_smp_acquire__after_ctrl_dep().
+ */
+ rseq_smp_store_release(&lock->c[cpu].v, 0);
+}
+
+void *test_percpu_spinlock_thread(void *arg)
+{
+ struct spinlock_test_data *data = arg;
+ int i, cpu;
+
+ if (rseq_register_current_thread()) {
+ fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+ errno, strerror(errno));
+ abort();
+ }
+ for (i = 0; i < data->reps; i++) {
+ cpu = rseq_this_cpu_lock(&data->lock);
+ data->c[cpu].count++;
+ rseq_percpu_unlock(&data->lock, cpu);
+ }
+ if (rseq_unregister_current_thread()) {
+ fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+ errno, strerror(errno));
+ abort();
+ }
+
+ return NULL;
+}
+
+/*
+ * A simple test which implements a sharded counter using a per-cpu
+ * lock. Obviously real applications might prefer to simply use a
+ * per-cpu increment; however, this is reasonable for a test and the
+ * lock can be extended to synchronize more complicated operations.
+ */
+void test_percpu_spinlock(void)
+{
+ const int num_threads = 200;
+ int i;
+ uint64_t sum;
+ pthread_t test_threads[num_threads];
+ struct spinlock_test_data data;
+
+ memset(&data, 0, sizeof(data));
+ data.reps = 5000;
+
+ for (i = 0; i < num_threads; i++)
+ pthread_create(&test_threads[i], NULL,
+ test_percpu_spinlock_thread, &data);
+
+ for (i = 0; i < num_threads; i++)
+ pthread_join(test_threads[i], NULL);
+
+ sum = 0;
+ for (i = 0; i < CPU_SETSIZE; i++)
+ sum += data.c[i].count;
+
+ assert(sum == (uint64_t)data.reps * num_threads);
+}
+
+void this_cpu_list_push(struct percpu_list *list,
+ struct percpu_list_node *node,
+ int *_cpu)
+{
+ int cpu;
+
+ for (;;) {
+ intptr_t *targetptr, newval, expect;
+ int ret;
+
+ cpu = rseq_cpu_start();
+ /* Load list->c[cpu].head with single-copy atomicity. */
+ expect = (intptr_t)RSEQ_READ_ONCE(list->c[cpu].head);
+ newval = (intptr_t)node;
+ targetptr = (intptr_t *)&list->c[cpu].head;
+ node->next = (struct percpu_list_node *)expect;
+ ret = rseq_cmpeqv_storev(targetptr, expect, newval, cpu);
+ if (rseq_likely(!ret))
+ break;
+ /* Retry if comparison fails or rseq aborts. */
+ }
+ if (_cpu)
+ *_cpu = cpu;
+}
+
+/*
+ * Unlike a traditional lock-less linked list; the availability of a
+ * rseq primitive allows us to implement pop without concerns over
+ * ABA-type races.
+ */
+struct percpu_list_node *this_cpu_list_pop(struct percpu_list *list,
+ int *_cpu)
+{
+ for (;;) {
+ struct percpu_list_node *head;
+ intptr_t *targetptr, expectnot, *load;
+ off_t offset;
+ int ret, cpu;
+
+ cpu = rseq_cpu_start();
+ targetptr = (intptr_t *)&list->c[cpu].head;
+ expectnot = (intptr_t)NULL;
+ offset = offsetof(struct percpu_list_node, next);
+ load = (intptr_t *)&head;
+ ret = rseq_cmpnev_storeoffp_load(targetptr, expectnot,
+ offset, load, cpu);
+ if (rseq_likely(!ret)) {
+ if (_cpu)
+ *_cpu = cpu;
+ return head;
+ }
+ if (ret > 0)
+ return NULL;
+ /* Retry if rseq aborts. */
+ }
+}
+
+/*
+ * __percpu_list_pop is not safe against concurrent accesses. Should
+ * only be used on lists that are not concurrently modified.
+ */
+struct percpu_list_node *__percpu_list_pop(struct percpu_list *list, int cpu)
+{
+ struct percpu_list_node *node;
+
+ node = list->c[cpu].head;
+ if (!node)
+ return NULL;
+ list->c[cpu].head = node->next;
+ return node;
+}
+
+void *test_percpu_list_thread(void *arg)
+{
+ int i;
+ struct percpu_list *list = (struct percpu_list *)arg;
+
+ if (rseq_register_current_thread()) {
+ fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+ errno, strerror(errno));
+ abort();
+ }
+
+ for (i = 0; i < 100000; i++) {
+ struct percpu_list_node *node;
+
+ node = this_cpu_list_pop(list, NULL);
+ sched_yield(); /* encourage shuffling */
+ if (node)
+ this_cpu_list_push(list, node, NULL);
+ }
+
+ if (rseq_unregister_current_thread()) {
+ fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+ errno, strerror(errno));
+ abort();
+ }
+
+ return NULL;
+}
+
+/* Simultaneous modification to a per-cpu linked list from many threads. */
+void test_percpu_list(void)
+{
+ int i, j;
+ uint64_t sum = 0, expected_sum = 0;
+ struct percpu_list list;
+ pthread_t test_threads[200];
+ cpu_set_t allowed_cpus;
+
+ memset(&list, 0, sizeof(list));
+
+ /* Generate list entries for every usable cpu. */
+ sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
+ for (i = 0; i < CPU_SETSIZE; i++) {
+ if (!CPU_ISSET(i, &allowed_cpus))
+ continue;
+ for (j = 1; j <= 100; j++) {
+ struct percpu_list_node *node;
+
+ expected_sum += j;
+
+ node = malloc(sizeof(*node));
+ assert(node);
+ node->data = j;
+ node->next = list.c[i].head;
+ list.c[i].head = node;
+ }
+ }
+
+ for (i = 0; i < 200; i++)
+ pthread_create(&test_threads[i], NULL,
+ test_percpu_list_thread, &list);
+
+ for (i = 0; i < 200; i++)
+ pthread_join(test_threads[i], NULL);
+
+ for (i = 0; i < CPU_SETSIZE; i++) {
+ struct percpu_list_node *node;
+
+ if (!CPU_ISSET(i, &allowed_cpus))
+ continue;
+
+ while ((node = __percpu_list_pop(&list, i))) {
+ sum += node->data;
+ free(node);
+ }
+ }
+
+ /*
+ * All entries should now be accounted for (unless some external
+ * actor is interfering with our allowed affinity while this
+ * test is running).
+ */
+ assert(sum == expected_sum);
+}
+
+int main(int argc, char **argv)
+{
+ if (rseq_register_current_thread()) {
+ fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+ errno, strerror(errno));
+ goto error;
+ }
+ printf("spinlock\n");
+ test_percpu_spinlock();
+ printf("percpu_list\n");
+ test_percpu_list();
+ if (rseq_unregister_current_thread()) {
+ fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+ errno, strerror(errno));
+ goto error;
+ }
+ return 0;
+
+error:
+ return -1;
+}