linux/tools/testing/selftests/rseq/basic_percpu_ops_test.c
Mathieu Desnoyers d53271c059 selftests/rseq: Do not skip !allowed_cpus for mm_cid
Indexing with mm_cid is incompatible with skipping disallowed cpumask,
because concurrency IDs are based on a virtual ID allocation which is
unrelated to the physical CPU mask.

These issues can be reproduced by running the rseq selftests under a
taskset which excludes CPU 0, e.g.

  taskset -c 10-20 ./run_param_test.sh

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
2024-01-22 11:40:36 -07:00

354 lines
7.8 KiB
C

// 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 "../kselftest.h"
#include "rseq.h"
#ifdef BUILDOPT_RSEQ_PERCPU_MM_CID
# define RSEQ_PERCPU RSEQ_PERCPU_MM_CID
static
int get_current_cpu_id(void)
{
return rseq_current_mm_cid();
}
static
bool rseq_validate_cpu_id(void)
{
return rseq_mm_cid_available();
}
static
bool rseq_use_cpu_index(void)
{
return false; /* Use mm_cid */
}
#else
# define RSEQ_PERCPU RSEQ_PERCPU_CPU_ID
static
int get_current_cpu_id(void)
{
return rseq_cpu_start();
}
static
bool rseq_validate_cpu_id(void)
{
return rseq_current_cpu_raw() >= 0;
}
static
bool rseq_use_cpu_index(void)
{
return true; /* Use cpu_id as index. */
}
#endif
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 = get_current_cpu_id();
ret = rseq_cmpeqv_storev(RSEQ_MO_RELAXED, RSEQ_PERCPU,
&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 = get_current_cpu_id();
/* 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(RSEQ_MO_RELAXED, RSEQ_PERCPU,
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;
long offset;
int ret, cpu;
cpu = get_current_cpu_id();
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(RSEQ_MO_RELAXED, RSEQ_PERCPU,
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 (rseq_use_cpu_index() && !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 (rseq_use_cpu_index() && !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;
}
if (!rseq_validate_cpu_id()) {
fprintf(stderr, "Error: cpu id getter unavailable\n");
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;
}