summaryrefslogtreecommitdiff
path: root/tools/testing/selftests/cgroup
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing/selftests/cgroup')
-rw-r--r--tools/testing/selftests/cgroup/lib/cgroup_util.c68
-rw-r--r--tools/testing/selftests/cgroup/lib/include/cgroup_util.h13
-rw-r--r--tools/testing/selftests/cgroup/test_core.c19
-rw-r--r--tools/testing/selftests/cgroup/test_cpu.c49
-rw-r--r--tools/testing/selftests/cgroup/test_cpuset.c249
-rwxr-xr-xtools/testing/selftests/cgroup/test_cpuset_prs.sh331
-rwxr-xr-xtools/testing/selftests/cgroup/test_cpuset_v1_base.sh2
-rwxr-xr-xtools/testing/selftests/cgroup/test_cpuset_v1_hp.sh2
-rw-r--r--tools/testing/selftests/cgroup/test_freezer.c6
-rw-r--r--tools/testing/selftests/cgroup/test_hugetlb_memcg.c18
-rw-r--r--tools/testing/selftests/cgroup/test_kill.c64
-rw-r--r--tools/testing/selftests/cgroup/test_kmem.c60
-rw-r--r--tools/testing/selftests/cgroup/test_memcontrol.c213
-rw-r--r--tools/testing/selftests/cgroup/test_pids.c2
-rw-r--r--tools/testing/selftests/cgroup/test_zswap.c356
15 files changed, 1163 insertions, 289 deletions
diff --git a/tools/testing/selftests/cgroup/lib/cgroup_util.c b/tools/testing/selftests/cgroup/lib/cgroup_util.c
index 44c52f620fda..2596c12cd864 100644
--- a/tools/testing/selftests/cgroup/lib/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/lib/cgroup_util.c
@@ -59,7 +59,8 @@ char *cg_name(const char *root, const char *name)
size_t len = strlen(root) + strlen(name) + 2;
char *ret = malloc(len);
- snprintf(ret, len, "%s/%s", root, name);
+ if (ret)
+ snprintf(ret, len, "%s/%s", root, name);
return ret;
}
@@ -69,7 +70,8 @@ char *cg_name_indexed(const char *root, const char *name, int index)
size_t len = strlen(root) + strlen(name) + 10;
char *ret = malloc(len);
- snprintf(ret, len, "%s/%s_%d", root, name, index);
+ if (ret)
+ snprintf(ret, len, "%s/%s_%d", root, name, index);
return ret;
}
@@ -79,7 +81,8 @@ char *cg_control(const char *cgroup, const char *control)
size_t len = strlen(cgroup) + strlen(control) + 2;
char *ret = malloc(len);
- snprintf(ret, len, "%s/%s", cgroup, control);
+ if (ret)
+ snprintf(ret, len, "%s/%s", cgroup, control);
return ret;
}
@@ -106,8 +109,9 @@ int cg_read_strcmp(const char *cgroup, const char *control,
/* Handle the case of comparing against empty string */
if (!expected)
return -1;
- else
- size = strlen(expected) + 1;
+
+ /* needs size > 1, otherwise cg_read() reads 0 bytes */
+ size = (expected[0] == '\0') ? 2 : strlen(expected) + 1;
buf = malloc(size);
if (!buf)
@@ -123,9 +127,24 @@ int cg_read_strcmp(const char *cgroup, const char *control,
return ret;
}
+int cg_read_strcmp_wait(const char *cgroup, const char *control,
+ const char *expected)
+{
+ int i, ret;
+
+ for (i = 0; i < 100; i++) {
+ ret = cg_read_strcmp(cgroup, control, expected);
+ if (!ret)
+ return ret;
+ usleep(10000);
+ }
+
+ return ret;
+}
+
int cg_read_strstr(const char *cgroup, const char *control, const char *needle)
{
- char buf[PAGE_SIZE];
+ char buf[BUF_SIZE];
if (cg_read(cgroup, control, buf, sizeof(buf)))
return -1;
@@ -155,7 +174,7 @@ long cg_read_long_fd(int fd)
long cg_read_key_long(const char *cgroup, const char *control, const char *key)
{
- char buf[PAGE_SIZE];
+ char buf[BUF_SIZE];
char *ptr;
if (cg_read(cgroup, control, buf, sizeof(buf)))
@@ -168,9 +187,30 @@ long cg_read_key_long(const char *cgroup, const char *control, const char *key)
return atol(ptr + strlen(key));
}
+long cg_read_key_long_poll(const char *cgroup, const char *control,
+ const char *key, long expected, int retries,
+ useconds_t wait_interval_us)
+{
+ long val = -1;
+ int i;
+
+ for (i = 0; i < retries; i++) {
+ val = cg_read_key_long(cgroup, control, key);
+ if (val < 0)
+ return val;
+
+ if (val == expected)
+ break;
+
+ usleep(wait_interval_us);
+ }
+
+ return val;
+}
+
long cg_read_lc(const char *cgroup, const char *control)
{
- char buf[PAGE_SIZE];
+ char buf[BUF_SIZE];
const char delim[] = "\n";
char *line;
long cnt = 0;
@@ -222,7 +262,7 @@ int cg_write_numeric(const char *cgroup, const char *control, long value)
static int cg_find_root(char *root, size_t len, const char *controller,
bool *nsdelegate)
{
- char buf[10 * PAGE_SIZE];
+ char buf[10 * BUF_SIZE];
char *fs, *mount, *type, *options;
const char delim[] = "\n\t ";
@@ -277,7 +317,7 @@ int cg_create(const char *cgroup)
int cg_wait_for_proc_count(const char *cgroup, int count)
{
- char buf[10 * PAGE_SIZE] = {0};
+ char buf[10 * BUF_SIZE] = {0};
int attempts;
char *ptr;
@@ -302,7 +342,7 @@ int cg_wait_for_proc_count(const char *cgroup, int count)
int cg_killall(const char *cgroup)
{
- char buf[PAGE_SIZE];
+ char buf[BUF_SIZE];
char *ptr = buf;
/* If cgroup.kill exists use it. */
@@ -512,7 +552,7 @@ int cg_run_nowait(const char *cgroup,
int proc_mount_contains(const char *option)
{
- char buf[4 * PAGE_SIZE];
+ char buf[4 * BUF_SIZE];
ssize_t read;
read = read_text("/proc/mounts", buf, sizeof(buf));
@@ -524,7 +564,7 @@ int proc_mount_contains(const char *option)
int cgroup_feature(const char *feature)
{
- char buf[PAGE_SIZE];
+ char buf[BUF_SIZE];
ssize_t read;
read = read_text("/sys/kernel/cgroup/features", buf, sizeof(buf));
@@ -551,7 +591,7 @@ ssize_t proc_read_text(int pid, bool thread, const char *item, char *buf, size_t
int proc_read_strstr(int pid, bool thread, const char *item, const char *needle)
{
- char buf[PAGE_SIZE];
+ char buf[BUF_SIZE];
if (proc_read_text(pid, thread, item, buf, sizeof(buf)) < 0)
return -1;
diff --git a/tools/testing/selftests/cgroup/lib/include/cgroup_util.h b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
index 7ab2824ed7b5..5d39c709ac7a 100644
--- a/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
+++ b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
@@ -2,12 +2,14 @@
#include <stdbool.h>
#include <stdlib.h>
-#ifndef PAGE_SIZE
-#define PAGE_SIZE 4096
+#ifndef BUF_SIZE
+#define BUF_SIZE 4096
#endif
#define MB(x) (x << 20)
+#define GB(x) ((unsigned long long)(x) << 30)
+#define NSEC_PER_USEC 1000L
#define USEC_PER_SEC 1000000L
#define NSEC_PER_SEC 1000000000L
@@ -17,6 +19,8 @@
#define CG_NAMED_NAME "selftest"
#define CG_PATH_FORMAT (!cg_test_v1_named ? "0::%s" : (":name=" CG_NAMED_NAME ":%s"))
+#define DEFAULT_WAIT_INTERVAL_US (100 * 1000) /* 100 ms */
+
/*
* Checks if two given values differ by less than err% of their sum.
*/
@@ -59,11 +63,16 @@ extern int cg_read(const char *cgroup, const char *control,
char *buf, size_t len);
extern int cg_read_strcmp(const char *cgroup, const char *control,
const char *expected);
+extern int cg_read_strcmp_wait(const char *cgroup, const char *control,
+ const char *expected);
extern int cg_read_strstr(const char *cgroup, const char *control,
const char *needle);
extern long cg_read_long(const char *cgroup, const char *control);
extern long cg_read_long_fd(int fd);
long cg_read_key_long(const char *cgroup, const char *control, const char *key);
+long cg_read_key_long_poll(const char *cgroup, const char *control,
+ const char *key, long expected, int retries,
+ useconds_t wait_interval_us);
extern long cg_read_lc(const char *cgroup, const char *control);
extern int cg_write(const char *cgroup, const char *control, char *buf);
extern int cg_open(const char *cgroup, const char *control, int flags);
diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c
index 102262555a59..20d2b63774c3 100644
--- a/tools/testing/selftests/cgroup/test_core.c
+++ b/tools/testing/selftests/cgroup/test_core.c
@@ -87,7 +87,7 @@ static int test_cgcore_destroy(const char *root)
int ret = KSFT_FAIL;
char *cg_test = NULL;
int child_pid;
- char buf[PAGE_SIZE];
+ char buf[BUF_SIZE];
cg_test = cg_name(root, "cg_test");
@@ -233,7 +233,8 @@ static int test_cgcore_populated(const char *root)
if (err)
goto cleanup;
- if (cg_read_strcmp(cg_test_d, "cgroup.events", "populated 0\n"))
+ if (cg_read_strcmp_wait(cg_test_d, "cgroup.events",
+ "populated 0\n"))
goto cleanup;
/* Remove cgroup. */
@@ -426,7 +427,6 @@ static int test_cgcore_no_internal_process_constraint_on_threads(const char *roo
cleanup:
cg_enter_current(root);
- cg_enter_current(root);
if (child)
cg_destroy(child);
if (parent)
@@ -794,10 +794,9 @@ static int lesser_ns_open_thread_fn(void *arg)
static int test_cgcore_lesser_ns_open(const char *root)
{
static char stack[65536];
- const uid_t test_euid = 65534; /* usually nobody, any !root is fine */
int ret = KSFT_FAIL;
char *cg_test_a = NULL, *cg_test_b = NULL;
- char *cg_test_a_procs = NULL, *cg_test_b_procs = NULL;
+ char *cg_test_b_procs = NULL;
int cg_test_b_procs_fd = -1;
struct lesser_ns_open_thread_arg targ = { .fd = -1 };
pid_t pid;
@@ -812,10 +811,9 @@ static int test_cgcore_lesser_ns_open(const char *root)
if (!cg_test_a || !cg_test_b)
goto cleanup;
- cg_test_a_procs = cg_name(cg_test_a, "cgroup.procs");
cg_test_b_procs = cg_name(cg_test_b, "cgroup.procs");
- if (!cg_test_a_procs || !cg_test_b_procs)
+ if (!cg_test_b_procs)
goto cleanup;
if (cg_create(cg_test_a) || cg_create(cg_test_b))
@@ -824,10 +822,6 @@ static int test_cgcore_lesser_ns_open(const char *root)
if (cg_enter_current(cg_test_b))
goto cleanup;
- if (chown(cg_test_a_procs, test_euid, -1) ||
- chown(cg_test_b_procs, test_euid, -1))
- goto cleanup;
-
targ.path = cg_test_b_procs;
pid = clone(lesser_ns_open_thread_fn, stack + sizeof(stack),
CLONE_NEWCGROUP | CLONE_FILES | CLONE_VM | SIGCHLD,
@@ -862,7 +856,6 @@ cleanup:
if (cg_test_a)
cg_destroy(cg_test_a);
free(cg_test_b_procs);
- free(cg_test_a_procs);
free(cg_test_b);
free(cg_test_a);
return ret;
@@ -926,7 +919,6 @@ int main(int argc, char *argv[])
int i;
ksft_print_header();
- ksft_set_plan(ARRAY_SIZE(tests));
if (cg_find_unified_root(root, sizeof(root), &nsdelegate)) {
if (setup_named_v1_root(root, sizeof(root), CG_NAMED_NAME))
ksft_exit_skip("cgroup v2 isn't mounted and could not setup named v1 hierarchy\n");
@@ -939,6 +931,7 @@ int main(int argc, char *argv[])
ksft_exit_skip("Failed to set memory controller\n");
post_v2_setup:
+ ksft_set_plan(ARRAY_SIZE(tests));
for (i = 0; i < ARRAY_SIZE(tests); i++) {
switch (tests[i].fn(root)) {
case KSFT_PASS:
diff --git a/tools/testing/selftests/cgroup/test_cpu.c b/tools/testing/selftests/cgroup/test_cpu.c
index c83f05438d7c..735a53bb222b 100644
--- a/tools/testing/selftests/cgroup/test_cpu.c
+++ b/tools/testing/selftests/cgroup/test_cpu.c
@@ -278,7 +278,7 @@ static int test_cpucg_nice(const char *root)
char buf[64];
snprintf(buf, sizeof(buf), "%d", getpid());
if (cg_write(cpucg, "cgroup.procs", buf))
- goto cleanup;
+ exit(EXIT_FAILURE);
/* Try to keep niced CPU usage as constrained to hog_cpu as possible */
nice(1);
@@ -291,6 +291,8 @@ static int test_cpucg_nice(const char *root)
user_usec = cg_read_key_long(cpucg, "cpu.stat", "user_usec");
nice_usec = cg_read_key_long(cpucg, "cpu.stat", "nice_usec");
+ if (user_usec <= 0)
+ goto cleanup;
if (!values_close_report(nice_usec, expected_nice_usec, 1))
goto cleanup;
@@ -640,21 +642,49 @@ test_cpucg_nested_weight_underprovisioned(const char *root)
}
/*
+ * Best effort attempt to get the kernel's HZ value from the config.
+ * Return the HZ value if found otherwise return 1000 (the default) to
+ * indicate failure.
+ */
+static long
+get_config_hz(void)
+{
+ long hz = 1000;
+ FILE *f;
+ char cmd[256] = "zcat /proc/config.gz 2>/dev/null | grep '^CONFIG_HZ='";
+
+ f = popen(cmd, "r");
+
+ if (!f)
+ return hz;
+
+ if (fscanf(f, "CONFIG_HZ=%ld", &hz) == EOF)
+ goto out;
+
+out:
+ pclose(f);
+ return hz;
+}
+
+/*
* This test creates a cgroup with some maximum value within a period, and
* verifies that a process in the cgroup is not overscheduled.
*/
static int test_cpucg_max(const char *root)
{
int ret = KSFT_FAIL;
+ long hz = get_config_hz();
long quota_usec = 1000;
long default_period_usec = 100000; /* cpu.max's default period */
long duration_seconds = 1;
- long duration_usec = duration_seconds * USEC_PER_SEC;
+ long duration_usec;
long usage_usec, n_periods, remainder_usec, expected_usage_usec;
char *cpucg;
char quota_buf[32];
+ duration_usec = duration_seconds * USEC_PER_SEC * 1000 / hz;
+
snprintf(quota_buf, sizeof(quota_buf), "%ld", quota_usec);
cpucg = cg_name(root, "cpucg_test");
@@ -670,8 +700,8 @@ static int test_cpucg_max(const char *root)
struct cpu_hog_func_param param = {
.nprocs = 1,
.ts = {
- .tv_sec = duration_seconds,
- .tv_nsec = 0,
+ .tv_sec = duration_usec / USEC_PER_SEC,
+ .tv_nsec = duration_usec % USEC_PER_SEC * NSEC_PER_USEC,
},
.clock_type = CPU_HOG_CLOCK_WALL,
};
@@ -710,15 +740,18 @@ cleanup:
static int test_cpucg_max_nested(const char *root)
{
int ret = KSFT_FAIL;
+ long hz = get_config_hz();
long quota_usec = 1000;
long default_period_usec = 100000; /* cpu.max's default period */
long duration_seconds = 1;
- long duration_usec = duration_seconds * USEC_PER_SEC;
+ long duration_usec;
long usage_usec, n_periods, remainder_usec, expected_usage_usec;
char *parent, *child;
char quota_buf[32];
+ duration_usec = duration_seconds * USEC_PER_SEC * 1000 / hz;
+
snprintf(quota_buf, sizeof(quota_buf), "%ld", quota_usec);
parent = cg_name(root, "cpucg_parent");
@@ -741,8 +774,8 @@ static int test_cpucg_max_nested(const char *root)
struct cpu_hog_func_param param = {
.nprocs = 1,
.ts = {
- .tv_sec = duration_seconds,
- .tv_nsec = 0,
+ .tv_sec = duration_usec / USEC_PER_SEC,
+ .tv_nsec = duration_usec % USEC_PER_SEC * NSEC_PER_USEC,
},
.clock_type = CPU_HOG_CLOCK_WALL,
};
@@ -799,7 +832,6 @@ int main(int argc, char *argv[])
int i;
ksft_print_header();
- ksft_set_plan(ARRAY_SIZE(tests));
if (cg_find_unified_root(root, sizeof(root), NULL))
ksft_exit_skip("cgroup v2 isn't mounted\n");
@@ -807,6 +839,7 @@ int main(int argc, char *argv[])
if (cg_write(root, "cgroup.subtree_control", "+cpu"))
ksft_exit_skip("Failed to set cpu controller\n");
+ ksft_set_plan(ARRAY_SIZE(tests));
for (i = 0; i < ARRAY_SIZE(tests); i++) {
switch (tests[i].fn(root)) {
case KSFT_PASS:
diff --git a/tools/testing/selftests/cgroup/test_cpuset.c b/tools/testing/selftests/cgroup/test_cpuset.c
index c5cf8b56ceb8..3dfadd280c1c 100644
--- a/tools/testing/selftests/cgroup/test_cpuset.c
+++ b/tools/testing/selftests/cgroup/test_cpuset.c
@@ -1,7 +1,13 @@
// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <assert.h>
#include <linux/limits.h>
+#include <pthread.h>
+#include <sched.h>
#include <signal.h>
+#include <sys/syscall.h>
+#include <unistd.h>
#include "kselftest.h"
#include "cgroup_util.h"
@@ -232,6 +238,246 @@ cleanup:
return ret;
}
+static int get_cpu_affinity(cpu_set_t *mask)
+{
+ CPU_ZERO(mask);
+ return sched_getaffinity(0, sizeof(*mask), mask);
+}
+
+static int cpu_set_equal(cpu_set_t *dst, unsigned long mask)
+{
+ cpu_set_t expected;
+
+ CPU_ZERO(&expected);
+ assert(sizeof(mask) < CPU_SETSIZE);
+
+ for (int cpu = 0; cpu < sizeof(mask) * 8; ++cpu)
+ if ((1UL << cpu) & mask)
+ CPU_SET(cpu, &expected);
+
+ return CPU_EQUAL(&expected, dst);
+}
+
+enum test_phase {
+ AFFINITY_SETUP,
+ AFFINITY_CONTROLLER_DISABLED,
+ AFFINITY_COMPLETE,
+ AFFINITY_ERROR
+};
+
+struct thread_args {
+ const char *cgroup;
+ cpu_set_t *affinity_before;
+ cpu_set_t *affinity_after;
+ int affinity_before_ready;
+};
+
+static pthread_mutex_t test_mutex = PTHREAD_MUTEX_INITIALIZER;
+static pthread_cond_t test_cond = PTHREAD_COND_INITIALIZER;
+static enum test_phase test_phase;
+
+static void *affinity_thread_fn(void *arg)
+{
+ struct thread_args *args = (struct thread_args *)arg;
+
+ if (cg_enter_current_thread(args->cgroup))
+ goto fail;
+
+ if (get_cpu_affinity(args->affinity_before) != 0)
+ goto fail;
+
+ pthread_mutex_lock(&test_mutex);
+ args->affinity_before_ready = 1;
+ pthread_cond_broadcast(&test_cond);
+
+ while (test_phase < AFFINITY_CONTROLLER_DISABLED)
+ pthread_cond_wait(&test_cond, &test_mutex);
+ pthread_mutex_unlock(&test_mutex);
+
+ if (get_cpu_affinity(args->affinity_after) != 0)
+ goto fail;
+
+
+ return NULL;
+
+fail:
+ pthread_mutex_lock(&test_mutex);
+ test_phase = AFFINITY_ERROR;
+ pthread_cond_broadcast(&test_cond);
+ pthread_mutex_unlock(&test_mutex);
+ return NULL;
+}
+
+/*
+ * Test that disabling cpuset controller properly updates thread affinity.
+ *
+ * This test exposes a bug in cpuset_attach() where threads in child cgroups
+ * don't get their affinity updated when the cpuset controller is disabled.
+ *
+ * Setup:
+ * - Create parent cgroup with cpuset.cpus=0-1
+ * - Create child A with cpuset.cpus=0-1
+ * - Create child B with cpuset.cpus=1
+ * - Place multithreaded process: group leader + thread_a in A, thread_b in B
+ * - Disable cpuset controller on parent
+ *
+ * Expected: thread_b's affinity should expand from {1} to {0-1}
+ * Buggy: thread_b's affinity remains {1}
+ */
+static int test_cpuset_affinity_on_controller_disable(const char *root)
+{
+ char *parent = NULL, *child_a = NULL, *child_b = NULL;
+ pthread_t thread_a, thread_b;
+ int thread_a_created = 0, thread_b_created = 0;
+ cpu_set_t affinity_a_before, affinity_a_after;
+ cpu_set_t affinity_b_before, affinity_b_after;
+ int ret = KSFT_FAIL;
+
+ parent = cg_name(root, "cpuset_affinity_test");
+ if (!parent)
+ goto cleanup;
+ if (cg_create(parent))
+ goto cleanup;
+ if (cg_write(parent, "cgroup.type", "threaded"))
+ goto cleanup;
+
+ child_a = cg_name(parent, "A");
+ if (!child_a)
+ goto cleanup;
+ if (cg_create(child_a))
+ goto cleanup;
+ if (cg_write(child_a, "cgroup.type", "threaded"))
+ goto cleanup;
+
+ child_b = cg_name(parent, "B");
+ if (!child_b)
+ goto cleanup;
+ if (cg_create(child_b))
+ goto cleanup;
+ if (cg_write(child_b, "cgroup.type", "threaded"))
+ goto cleanup;
+
+ /* Now enable cpuset controller in parent */
+ if (cg_write(parent, "cgroup.subtree_control", "+cpuset"))
+ goto skip;
+
+ /*
+ * Set CPU affinity constraints
+ * Skip the test if the setting of "cpuset.cpus" fails as the test
+ * system may not have CPU 1.
+ */
+ if (cg_write(parent, "cpuset.cpus", "0-1"))
+ goto skip;
+ if (cg_write(child_a, "cpuset.cpus", "0-1"))
+ goto skip;
+ if (cg_write(child_b, "cpuset.cpus", "1"))
+ goto skip;
+
+ /* Move group leader (main thread) to child A */
+ if (cg_enter_current(child_a))
+ goto cleanup;
+
+ /* Create threads - they will move themselves to their respective cgroups */
+ test_phase = AFFINITY_SETUP;
+
+ struct thread_args args_a = {
+ .cgroup = child_a,
+ .affinity_before = &affinity_a_before,
+ .affinity_after = &affinity_a_after,
+ .affinity_before_ready = 0,
+ };
+ if (pthread_create(&thread_a, NULL, affinity_thread_fn, &args_a))
+ goto cleanup;
+ thread_a_created = 1;
+
+ struct thread_args args_b = {
+ .cgroup = child_b,
+ .affinity_before = &affinity_b_before,
+ .affinity_after = &affinity_b_after,
+ .affinity_before_ready = 0,
+ };
+ if (pthread_create(&thread_b, NULL, affinity_thread_fn, &args_b))
+ goto cleanup_threads;
+ thread_b_created = 1;
+
+ pthread_mutex_lock(&test_mutex);
+ while ((test_phase < AFFINITY_ERROR) &&
+ (args_a.affinity_before_ready + args_b.affinity_before_ready < 2))
+ pthread_cond_wait(&test_cond, &test_mutex);
+
+ /* If a thread failed during setup, bail out */
+ if (test_phase == AFFINITY_ERROR) {
+ pthread_mutex_unlock(&test_mutex);
+ goto cleanup_threads;
+ }
+ pthread_mutex_unlock(&test_mutex);
+
+ if (!cpu_set_equal(&affinity_a_before, 0x3)) {
+ ksft_print_msg("FAIL: thread_a initial affinity incorrect\n");
+ goto cleanup_threads;
+ }
+
+ if (!cpu_set_equal(&affinity_b_before, 0x2)) {
+ ksft_print_msg("FAIL: thread_b initial affinity incorrect\n");
+ goto cleanup_threads;
+ }
+
+ /* Disable cpuset controller - this should trigger affinity update */
+ if (cg_write(parent, "cgroup.subtree_control", "-cpuset"))
+ goto cleanup_threads;
+
+ /* Signal threads to save their final affinity and exit */
+ pthread_mutex_lock(&test_mutex);
+ test_phase = AFFINITY_CONTROLLER_DISABLED;
+ pthread_cond_broadcast(&test_cond);
+ pthread_mutex_unlock(&test_mutex);
+
+ pthread_join(thread_a, NULL);
+ pthread_join(thread_b, NULL);
+
+ /* Verify thread affinities AFTER disabling controller */
+ if (!cpu_set_equal(&affinity_a_after, 0x3)) {
+ ksft_print_msg("FAIL: thread_a final affinity incorrect\n");
+ goto cleanup;
+ }
+
+ if (!cpu_set_equal(&affinity_b_after, 0x3)) {
+ ksft_print_msg("FAIL: thread_b affinity did not expand to {0-1}\n");
+ goto cleanup;
+ }
+
+ ret = KSFT_PASS;
+ goto cleanup;
+
+skip:
+ ret = KSFT_SKIP;
+ goto cleanup;
+
+cleanup_threads:
+ pthread_mutex_lock(&test_mutex);
+ test_phase = AFFINITY_COMPLETE;
+ pthread_cond_broadcast(&test_cond);
+ pthread_mutex_unlock(&test_mutex);
+
+ if (thread_a_created)
+ pthread_join(thread_a, NULL);
+ if (thread_b_created)
+ pthread_join(thread_b, NULL);
+
+cleanup:
+ /* Move back to root before cleanup */
+ cg_enter_current(root);
+
+ cg_destroy(child_b);
+ free(child_b);
+ cg_destroy(child_a);
+ free(child_a);
+ cg_destroy(parent);
+ free(parent);
+
+ return ret;
+}
+
#define T(x) { x, #x }
struct cpuset_test {
@@ -241,6 +487,7 @@ struct cpuset_test {
T(test_cpuset_perms_object_allow),
T(test_cpuset_perms_object_deny),
T(test_cpuset_perms_subtree),
+ T(test_cpuset_affinity_on_controller_disable),
};
#undef T
@@ -250,7 +497,6 @@ int main(int argc, char *argv[])
int i;
ksft_print_header();
- ksft_set_plan(ARRAY_SIZE(tests));
if (cg_find_unified_root(root, sizeof(root), NULL))
ksft_exit_skip("cgroup v2 isn't mounted\n");
@@ -258,6 +504,7 @@ int main(int argc, char *argv[])
if (cg_write(root, "cgroup.subtree_control", "+cpuset"))
ksft_exit_skip("Failed to set cpuset controller\n");
+ ksft_set_plan(ARRAY_SIZE(tests));
for (i = 0; i < ARRAY_SIZE(tests); i++) {
switch (tests[i].fn(root)) {
case KSFT_PASS:
diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
index a17256d9f88a..7efd5e645767 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
@@ -20,7 +20,7 @@ skip_test() {
WAIT_INOTIFY=$(cd $(dirname $0); pwd)/wait_inotify
# Find cgroup v2 mount point
-CGROUP2=$(mount -t cgroup2 | head -1 | awk -e '{print $3}')
+CGROUP2=$(mount -t cgroup2 | head -1 | awk '{print $3}')
[[ -n "$CGROUP2" ]] || skip_test "Cgroup v2 mount point not found!"
SUBPARTS_CPUS=$CGROUP2/.__DEBUG__.cpuset.cpus.subpartitions
CPULIST=$(cat $CGROUP2/cpuset.cpus.effective)
@@ -196,7 +196,6 @@ test_add_proc()
# P<v> = set cpus.partition (0:member, 1:root, 2:isolated)
# C<l> = add cpu-list to cpuset.cpus
# X<l> = add cpu-list to cpuset.cpus.exclusive
-# S<p> = use prefix in subtree_control
# T = put a task into cgroup
# CX<l> = add cpu-list to both cpuset.cpus and cpuset.cpus.exclusive
# O<c>=<v> = Write <v> to CPU online file of <c>
@@ -209,44 +208,46 @@ test_add_proc()
# sched-debug matching which includes offline CPUs and single-CPU partitions
# while the second one is for matching cpuset.cpus.isolated.
#
-SETUP_A123_PARTITIONS="C1-3:P1:S+ C2-3:P1:S+ C3:P1"
+SETUP_A123_PARTITIONS="C1-3:P1 C2-3:P1 C3:P1"
TEST_MATRIX=(
# old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
# ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
- " C0-1 . . C2-3 S+ C4-5 . . 0 A2:0-1"
+ " C0-1 . . C2-3 . C4-5 . . 0 A2:0-1"
" C0-1 . . C2-3 P1 . . . 0 "
- " C0-1 . . C2-3 P1:S+ C0-1:P1 . . 0 "
- " C0-1 . . C2-3 P1:S+ C1:P1 . . 0 "
- " C0-1:S+ . . C2-3 . . . P1 0 "
- " C0-1:P1 . . C2-3 S+ C1 . . 0 "
- " C0-1:P1 . . C2-3 S+ C1:P1 . . 0 "
- " C0-1:P1 . . C2-3 S+ C1:P1 . P1 0 "
+ " C0-1 . . C2-3 P1 C0-1:P1 . . 0 "
+ " C0-1 . . C2-3 P1 C1:P1 . . 0 "
+ " C0-1 . . C2-3 . . . P1 0 "
+ " C0-1:P1 . . C2-3 . C1 . . 0 "
+ " C0-1:P1 . . C2-3 . C1:P1 . . 0 "
+ " C0-1:P1 . . C2-3 . C1:P1 . P1 0 "
" C0-1:P1 . . C2-3 C4-5 . . . 0 A1:4-5"
- " C0-1:P1 . . C2-3 S+:C4-5 . . . 0 A1:4-5"
" C0-1 . . C2-3:P1 . . . C2 0 "
" C0-1 . . C2-3:P1 . . . C4-5 0 B1:4-5"
- "C0-3:P1:S+ C2-3:P1 . . . . . . 0 A1:0-1|A2:2-3|XA2:2-3"
- "C0-3:P1:S+ C2-3:P1 . . C1-3 . . . 0 A1:1|A2:2-3|XA2:2-3"
- "C2-3:P1:S+ C3:P1 . . C3 . . . 0 A1:|A2:3|XA2:3 A1:P1|A2:P1"
- "C2-3:P1:S+ C3:P1 . . C3 P0 . . 0 A1:3|A2:3 A1:P1|A2:P0"
- "C2-3:P1:S+ C2:P1 . . C2-4 . . . 0 A1:3-4|A2:2"
- "C2-3:P1:S+ C3:P1 . . C3 . . C0-2 0 A1:|B1:0-2 A1:P1|A2:P1"
+ " C0-3:P1 C2-3:P1 . . . . . . 0 A1:0-1|A2:2-3|XA2:2-3"
+ " C0-3:P1 C2-3:P1 . . C1-3 . . . 0 A1:1|A2:2-3|XA2:2-3"
+ " C2-3:P1 C3:P1 . . C3 . . . 0 A1:|A2:3|XA2:3 A1:P1|A2:P1"
+ " C2-3:P1 C3:P1 . . C3 P0 . . 0 A1:3|A2:3 A1:P1|A2:P0"
+ " C2-3:P1 C2:P1 . . C2-4 . . . 0 A1:3-4|A2:2"
+ " C2-3:P1 C3:P1 . . C3 . . C0-2 0 A1:|B1:0-2 A1:P1|A2:P1"
"$SETUP_A123_PARTITIONS . C2-3 . . . 0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
# CPU offlining cases:
- " C0-1 . . C2-3 S+ C4-5 . O2=0 0 A1:0-1|B1:3"
- "C0-3:P1:S+ C2-3:P1 . . O2=0 . . . 0 A1:0-1|A2:3"
- "C0-3:P1:S+ C2-3:P1 . . O2=0 O2=1 . . 0 A1:0-1|A2:2-3"
- "C0-3:P1:S+ C2-3:P1 . . O1=0 . . . 0 A1:0|A2:2-3"
- "C0-3:P1:S+ C2-3:P1 . . O1=0 O1=1 . . 0 A1:0-1|A2:2-3"
- "C2-3:P1:S+ C3:P1 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P1"
- "C2-3:P1:S+ C3:P2 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P2"
- "C2-3:P1:S+ C3:P1 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P1"
- "C2-3:P1:S+ C3:P2 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P2"
- "C2-3:P1:S+ C3:P1 . . O2=0 . . . 0 A1:|A2:3 A1:P1|A2:P1"
- "C2-3:P1:S+ C3:P1 . . O3=0 . . . 0 A1:2|A2: A1:P1|A2:P1"
- "C2-3:P1:S+ C3:P1 . . T:O2=0 . . . 0 A1:3|A2:3 A1:P1|A2:P-1"
- "C2-3:P1:S+ C3:P1 . . . T:O3=0 . . 0 A1:2|A2:2 A1:P1|A2:P-1"
+ " C0-1 . . C2-3 . C4-5 . O2=0 0 A1:0-1|B1:3"
+ " C0-3:P1 C2-3:P1 . . O2=0 . . . 0 A1:0-1|A2:3"
+ " C0-3:P1 C2-3:P1 . . O2=0 O2=1 . . 0 A1:0-1|A2:2-3"
+ " C0-3:P1 C2-3:P1 . . O1=0 . . . 0 A1:0|A2:2-3"
+ " C0-3:P1 C2-3:P1 . . O1=0 O1=1 . . 0 A1:0-1|A2:2-3"
+ " C2-3:P1 C3:P1 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P1"
+ " C2-3:P1 C3:P2 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P2"
+ " C2-3:P1 C3:P1 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P1"
+ " C2-3:P1 C3:P2 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P2"
+ " C2-3:P1 C3:P1 . . O2=0 . . . 0 A1:|A2:3 A1:P1|A2:P1"
+ " C2-3:P1 C3:P1 . . O3=0 . . . 0 A1:2|A2: A1:P1|A2:P1"
+ " C2-3:P1 C3:P1 . . T:O2=0 . . . 0 A1:3|A2:3 A1:P1|A2:P-1"
+ " C2-3:P1 C3:P1 . . . T:O3=0 . . 0 A1:2|A2:2 A1:P1|A2:P-1"
+ " C2-3:P1 C3:P2 . . T:O2=0 . . . 0 A1:3|A2:3 A1:P1|A2:P-2"
+ " C1-3:P1 C3:P2 . . . T:O3=0 . . 0 A1:1-2|A2:1-2 A1:P1|A2:P-2 3|"
+ " C1-3:P1 C3:P2 . . . T:O3=0 O3=1 . 0 A1:1-2|A2:3 A1:P1|A2:P2 3"
"$SETUP_A123_PARTITIONS . O1=0 . . . 0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
"$SETUP_A123_PARTITIONS . O2=0 . . . 0 A1:1|A2:|A3:3 A1:P1|A2:P1|A3:P1"
"$SETUP_A123_PARTITIONS . O3=0 . . . 0 A1:1|A2:2|A3: A1:P1|A2:P1|A3:P1"
@@ -264,88 +265,89 @@ TEST_MATRIX=(
#
# Remote partition and cpuset.cpus.exclusive tests
#
- " C0-3:S+ C1-3:S+ C2-3 . X2-3 . . . 0 A1:0-3|A2:1-3|A3:2-3|XA1:2-3"
- " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3:P2 . . 0 A1:0-1|A2:2-3|A3:2-3 A1:P0|A2:P2 2-3"
- " C0-3:S+ C1-3:S+ C2-3 . X2-3 X3:P2 . . 0 A1:0-2|A2:3|A3:3 A1:P0|A2:P2 3"
- " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
- " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:C3 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
- " C0-3:S+ C1-3:S+ C2-3 C2-3 . . . P2 0 A1:0-3|A2:1-3|A3:2-3|B1:2-3 A1:P0|A3:P0|B1:P-2"
- " C0-3:S+ C1-3:S+ C2-3 C4-5 . . . P2 0 B1:4-5 B1:P2 4-5"
- " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
- " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2:C1-3 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
- " C0-3:S+ C1-3:S+ C2-3 C4 X1-3 X1-3:P2 P2 . 0 A2:1|A3:2-3 A2:P2|A3:P2 1-3"
- " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2 P2:C4-5 0 A3:2-3|B1:4-5 A3:P2|B1:P2 2-5"
- " C4:X0-3:S+ X1-3:S+ X2-3 . . P2 . . 0 A1:4|A2:1-3|A3:1-3 A2:P2 1-3"
- " C4:X0-3:S+ X1-3:S+ X2-3 . . . P2 . 0 A1:4|A2:4|A3:2-3 A3:P2 2-3"
+ " C0-3 C1-3 C2-3 . X2-3 . . . 0 A1:0-3|A2:1-3|A3:2-3|XA1:2-3"
+ " C0-3 C1-3 C2-3 . X2-3 X2-3:P2 . . 0 A1:0-1|A2:2-3|A3:2-3 A1:P0|A2:P2 2-3"
+ " C0-3 C1-3 C2-3 . X2-3 X3:P2 . . 0 A1:0-2|A2:3|A3:3 A1:P0|A2:P2 3"
+ " C0-3 C1-3 C2-3 . X2-3 X2-3 X2-3:P2 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+ " C0-3 C1-3 C2-3 . X2-3 X2-3 X2-3:P2:C3 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+ " C0-3 C1-3 C2-3 C2-3 . . . P2 0 A1:0-1|A2:1|A3:1|B1:2-3 A1:P0|A3:P0|B1:P2"
+ " C0-3 C1-3 C2-3 C4-5 . . . P2 0 B1:4-5 B1:P2 4-5"
+ " C0-3 C1-3 C2-3 C4 X2-3 X2-3 X2-3:P2 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
+ " C0-3 C1-3 C2-3 C4 X2-3 X2-3 X2-3:P2:C1-3 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
+ " C0-3 C1-3 C2-3 C4 X1-3 X1-3:P2 P2 . 0 A2:1|A3:2-3 A2:P2|A3:P2 1-3"
+ " C0-3 C1-3 C2-3 C4 X2-3 X2-3 X2-3:P2 P2:C4-5 0 A3:2-3|B1:4-5 A3:P2|B1:P2 2-5"
+ " C4:X0-3 X1-3 X2-3 . . P2 . . 0 A1:4|A2:1-3|A3:1-3 A2:P2 1-3"
+ " C4:X0-3 X1-3 X2-3 . . . P2 . 0 A1:4|A2:4|A3:2-3 A3:P2 2-3"
# Nested remote/local partition tests
- " C0-3:S+ C1-3:S+ C2-3 C4-5 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4-5 \
+ " C0-3 C1-3 C2-3 C4-5 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4-5 \
A1:P0|A2:P1|A3:P2|B1:P1 2-3"
- " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4 \
+ " C0-3 C1-3 C2-3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4 \
A1:P0|A2:P1|A3:P2|B1:P1 2-4|2-3"
- " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3:P1 . P1 0 A1:0-1|A2:2-3|A3:2-3|B1:4 \
+ " C0-3 C1-3 C2-3 C4 X2-3 X2-3:P1 . P1 0 A1:0-1|A2:2-3|A3:2-3|B1:4 \
A1:P0|A2:P1|A3:P0|B1:P1"
- " C0-3:S+ C1-3:S+ C3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:2|A3:3|B1:4 \
+ " C0-3 C1-3 C3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:2|A3:3|B1:4 \
A1:P0|A2:P1|A3:P2|B1:P1 2-4|3"
- " C0-4:S+ C1-4:S+ C2-4 . X2-4 X2-4:P2 X4:P1 . 0 A1:0-1|A2:2-3|A3:4 \
+ " C0-4 C1-4 C2-4 . X2-4 X2-4:P2 X4:P1 . 0 A1:0-1|A2:2-3|A3:4 \
A1:P0|A2:P2|A3:P1 2-4|2-3"
- " C0-4:S+ C1-4:S+ C2-4 . X2-4 X2-4:P2 X3-4:P1 . 0 A1:0-1|A2:2|A3:3-4 \
+ " C0-4 C1-4 C2-4 . X2-4 X2-4:P2 X3-4:P1 . 0 A1:0-1|A2:2|A3:3-4 \
A1:P0|A2:P2|A3:P1 2"
- " C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \
+ " C0-4:X2-4 C1-4:X2-4:P2 C2-4:X4:P1 \
. . X5 . . 0 A1:0-4|A2:1-4|A3:2-4 \
A1:P0|A2:P-2|A3:P-1 ."
- " C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \
+ " C0-4:X2-4 C1-4:X2-4:P2 C2-4:X4:P1 \
. . . X1 . 0 A1:0-1|A2:2-4|A3:2-4 \
A1:P0|A2:P2|A3:P-1 2-4"
+ " CX1-3:P1 CX1-3 CX1-3 . . . P1 . 0 A1:1-3|A2:1-3|A3:1-3 \
+ A1:P1|A2:P0|A3:P-1"
# Remote partition offline tests
- " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:O2=0 . 0 A1:0-1|A2:1|A3:3 A1:P0|A3:P2 2-3"
- " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
- " C0-3:S+ C1-3:S+ C3 . X2-3 X2-3 P2:O3=0 . 0 A1:0-2|A2:1-2|A3: A1:P0|A3:P2 3"
- " C0-3:S+ C1-3:S+ C3 . X2-3 X2-3 T:P2:O3=0 . 0 A1:0-2|A2:1-2|A3:1-2 A1:P0|A3:P-2 3|"
+ " C0-3 C1-3 C2-3 . X2-3 X2-3 X2-3:P2:O2=0 . 0 A1:0-1|A2:1|A3:3 A1:P0|A3:P2 2-3"
+ " C0-3 C1-3 C2-3 . X2-3 X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+ " C0-3 C1-3 C3 . X2-3 X2-3 P2:O3=0 . 0 A1:0-2|A2:1-2|A3: A1:P0|A3:P2 3"
+ " C0-3 C1-3 C3 . X2-3 X2-3 T:P2:O3=0 . 0 A1:0-2|A2:1-2|A3:1-2 A1:P0|A3:P-2 3|"
# An invalidated remote partition cannot self-recover from hotplug
- " C0-3:S+ C1-3:S+ C2 . X2-3 X2-3 T:P2:O2=0 O2=1 0 A1:0-3|A2:1-3|A3:2 A1:P0|A3:P-2 ."
+ " C0-3 C1-3 C2 . X2-3 X2-3 T:P2:O2=0 O2=1 0 A1:0-3|A2:1-3|A3:2 A1:P0|A3:P-2 ."
# cpus.exclusive.effective clearing test
- " C0-3:S+ C1-3:S+ C2 . X2-3:X . . . 0 A1:0-3|A2:1-3|A3:2|XA1:"
+ " C0-3 C1-3 C2 . X2-3:X . . . 0 A1:0-3|A2:1-3|A3:2|XA1:"
# Invalid to valid remote partition transition test
- " C0-3:S+ C1-3 . . . X3:P2 . . 0 A1:0-3|A2:1-3|XA2: A2:P-2 ."
- " C0-3:S+ C1-3:X3:P2
- . . X2-3 P2 . . 0 A1:0-2|A2:3|XA2:3 A2:P2 3"
+ " C0-3 C1-3 . . . X3:P2 . . 0 A1:0-3|A2:1-3|XA2: A2:P-2 ."
+ " C0-3 C1-3:X3:P2 . . X2-3 P2 . . 0 A1:0-2|A2:3|XA2:3 A2:P2 3"
# Invalid to valid local partition direct transition tests
- " C1-3:S+:P2 X4:P2 . . . . . . 0 A1:1-3|XA1:1-3|A2:1-3:XA2: A1:P2|A2:P-2 1-3"
- " C1-3:S+:P2 X4:P2 . . . X3:P2 . . 0 A1:1-2|XA1:1-3|A2:3:XA2:3 A1:P2|A2:P2 1-3"
- " C0-3:P2 . . C4-6 C0-4 . . . 0 A1:0-4|B1:4-6 A1:P-2|B1:P0"
- " C0-3:P2 . . C4-6 C0-4:C0-3 . . . 0 A1:0-3|B1:4-6 A1:P2|B1:P0 0-3"
+ " C1-3:P2 X4:P2 . . . . . . 0 A1:1-3|XA1:1-3|A2:1-3:XA2: A1:P2|A2:P-2 1-3"
+ " C1-3:P2 X4:P2 . . . X3:P2 . . 0 A1:1-2|XA1:1-3|A2:3:XA2:3 A1:P2|A2:P2 1-3"
+ " C0-3:P2 . . C4-6 C0-4 . . . 0 A1:0-4|B1:5-6 A1:P2|B1:P0"
+ " C0-3:P2 . . C4-6 C0-4:C0-3 . . . 0 A1:0-3|B1:4-6 A1:P2|B1:P0 0-3"
# Local partition invalidation tests
- " C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
+ " C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \
. . . . . 0 A1:1|A2:2|A3:3 A1:P2|A2:P2|A3:P2 1-3"
- " C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
+ " C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \
. . X4 . . 0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3"
- " C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
+ " C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \
. . C4:X . . 0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3"
# Local partition CPU change tests
- " C0-5:S+:P2 C4-5:S+:P1 . . . C3-5 . . 0 A1:0-2|A2:3-5 A1:P2|A2:P1 0-2"
- " C0-5:S+:P2 C4-5:S+:P1 . . C1-5 . . . 0 A1:1-3|A2:4-5 A1:P2|A2:P1 1-3"
+ " C0-5:P2 C4-5:P1 . . . C3-5 . . 0 A1:0-2|A2:3-5 A1:P2|A2:P1 0-2"
+ " C0-5:P2 C4-5:P1 . . C1-5 . . . 0 A1:1-3|A2:4-5 A1:P2|A2:P1 1-3"
# cpus_allowed/exclusive_cpus update tests
- " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
+ " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \
. X:C4 . P2 . 0 A1:4|A2:4|XA2:|XA3:|A3:4 \
A1:P0|A3:P-2 ."
- " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
+ " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \
. X1 . P2 . 0 A1:0-3|A2:1-3|XA1:1|XA2:|XA3:|A3:2-3 \
A1:P0|A3:P-2 ."
- " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
+ " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \
. . X3 P2 . 0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3 \
A1:P0|A3:P2 3"
- " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \
+ " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3:P2 \
. . X3 . . 0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3|XA3:3 \
A1:P0|A3:P2 3"
- " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \
+ " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3:P2 \
. X4 . . . 0 A1:0-3|A2:1-3|A3:2-3|XA1:4|XA2:|XA3 \
A1:P0|A3:P-2"
@@ -356,78 +358,89 @@ TEST_MATRIX=(
#
# Adding CPUs to partition root that are not in parent's
# cpuset.cpus is allowed, but those extra CPUs are ignored.
- "C2-3:P1:S+ C3:P1 . . . C2-4 . . 0 A1:|A2:2-3 A1:P1|A2:P1"
+ " C2-3:P1 C3:P1 . . . C2-4 . . 0 A1:|A2:2-3 A1:P1|A2:P1"
# Taking away all CPUs from parent or itself if there are tasks
# will make the partition invalid.
- "C2-3:P1:S+ C3:P1 . . T C2-3 . . 0 A1:2-3|A2:2-3 A1:P1|A2:P-1"
- " C3:P1:S+ C3 . . T P1 . . 0 A1:3|A2:3 A1:P1|A2:P-1"
+ " C2-3:P1 C3:P1 . . T C2-3 . . 0 A1:2-3|A2:2-3 A1:P1|A2:P-1"
+ " C3:P1 C3 . . T P1 . . 0 A1:3|A2:3 A1:P1|A2:P-1"
"$SETUP_A123_PARTITIONS . T:C2-3 . . . 0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P-1|A3:P-1"
"$SETUP_A123_PARTITIONS . T:C2-3:C1-3 . . . 0 A1:1|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
# Changing a partition root to member makes child partitions invalid
- "C2-3:P1:S+ C3:P1 . . P0 . . . 0 A1:2-3|A2:3 A1:P0|A2:P-1"
+ " C2-3:P1 C3:P1 . . P0 . . . 0 A1:2-3|A2:3 A1:P0|A2:P-1"
"$SETUP_A123_PARTITIONS . C2-3 P0 . . 0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P0|A3:P-1"
# cpuset.cpus can contains cpus not in parent's cpuset.cpus as long
# as they overlap.
- "C2-3:P1:S+ . . . . C3-4:P1 . . 0 A1:2|A2:3 A1:P1|A2:P1"
+ " C2-3:P1 . . . . C3-4:P1 . . 0 A1:2|A2:3 A1:P1|A2:P1"
# Deletion of CPUs distributed to child cgroup is allowed.
- "C0-1:P1:S+ C1 . C2-3 C4-5 . . . 0 A1:4-5|A2:4-5"
+ " C0-1:P1 C1 . C2-3 C4-5 . . . 0 A1:4-5|A2:4-5"
# To become a valid partition root, cpuset.cpus must overlap parent's
# cpuset.cpus.
- " C0-1:P1 . . C2-3 S+ C4-5:P1 . . 0 A1:0-1|A2:0-1 A1:P1|A2:P-1"
+ " C0-1:P1 . . C2-3 . C4-5:P1 . . 0 A1:0-1|A2:0-1 A1:P1|A2:P-1"
# Enabling partition with child cpusets is allowed
- " C0-1:S+ C1 . C2-3 P1 . . . 0 A1:0-1|A2:1 A1:P1"
+ " C0-1 C1 . C2-3 P1 . . . 0 A1:0-1|A2:1 A1:P1"
# A partition root with non-partition root parent is invalid| but it
# can be made valid if its parent becomes a partition root too.
- " C0-1:S+ C1 . C2-3 . P2 . . 0 A1:0-1|A2:1 A1:P0|A2:P-2"
- " C0-1:S+ C1:P2 . C2-3 P1 . . . 0 A1:0|A2:1 A1:P1|A2:P2 0-1|1"
+ " C0-1 C1 . C2-3 . P2 . . 0 A1:0-1|A2:1 A1:P0|A2:P-2"
+ " C0-1 C1:P2 . C2-3 P1 . . . 0 A1:0|A2:1 A1:P1|A2:P2 0-1|1"
- # A non-exclusive cpuset.cpus change will invalidate partition and its siblings
- " C0-1:P1 . . C2-3 C0-2 . . . 0 A1:0-2|B1:2-3 A1:P-1|B1:P0"
- " C0-1:P1 . . P1:C2-3 C0-2 . . . 0 A1:0-2|B1:2-3 A1:P-1|B1:P-1"
- " C0-1 . . P1:C2-3 C0-2 . . . 0 A1:0-2|B1:2-3 A1:P0|B1:P-1"
+ # A non-exclusive cpuset.cpus change will not invalidate its siblings partition.
+ " C0-1:P1 . . C2-3 C0-2 . . . 0 A1:0-2|B1:3 A1:P1|B1:P0"
+ " C0-1:P1 . . P1:C2-3 C0-2 . . . 0 A1:0-1|XA1:0-1|B1:2-3 A1:P1|B1:P1"
+ " C0-1 . . P1:C2-3 C0-2 . . . 0 A1:0-1|B1:2-3 A1:P0|B1:P1"
# cpuset.cpus can overlap with sibling cpuset.cpus.exclusive but not subsumed by it
" C0-3 . . C4-5 X5 . . . 0 A1:0-3|B1:4-5"
# Child partition root that try to take all CPUs from parent partition
# with tasks will remain invalid.
- " C1-4:P1:S+ P1 . . . . . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
- " C1-4:P1:S+ P1 . . . C1-4 . . 0 A1|A2:1-4 A1:P1|A2:P1"
- " C1-4:P1:S+ P1 . . T C1-4 . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
+ " C1-4:P1 P1 . . . . . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
+ " C1-4:P1 P1 . . . C1-4 . . 0 A1|A2:1-4 A1:P1|A2:P1"
+ " C1-4:P1 P1 . . T C1-4 . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
# Clearing of cpuset.cpus with a preset cpuset.cpus.exclusive shouldn't
# affect cpuset.cpus.exclusive.effective.
- " C1-4:X3:S+ C1:X3 . . . C . . 0 A2:1-4|XA2:3"
+ " C1-4:X3 C1:X3 . . . C . . 0 A2:1-4|XA2:3"
# cpuset.cpus can contain CPUs that overlap a sibling cpuset with cpus.exclusive
# but creating a local partition out of it is not allowed. Similarly and change
# in cpuset.cpus of a local partition that overlaps sibling exclusive CPUs will
# invalidate it.
- " CX1-4:S+ CX2-4:P2 . C5-6 . . . P1 0 A1:1|A2:2-4|B1:5-6|XB1:5-6 \
+ " CX1-4 CX2-4:P2 . C5-6 . . . P1 0 A1:1|A2:2-4|B1:5-6|XB1:5-6 \
A1:P0|A2:P2:B1:P1 2-4"
- " CX1-4:S+ CX2-4:P2 . C3-6 . . . P1 0 A1:1|A2:2-4|B1:5-6 \
+ " CX1-4 CX2-4:P2 . C3-6 . . . P1 0 A1:1|A2:2-4|B1:5-6 \
A1:P0|A2:P2:B1:P-1 2-4"
- " CX1-4:S+ CX2-4:P2 . C5-6 . . . P1:C3-6 0 A1:1|A2:2-4|B1:5-6 \
+ " CX1-4 CX2-4:P2 . C5-6 . . . P1:C3-6 0 A1:1|A2:2-4|B1:5-6 \
A1:P0|A2:P2:B1:P-1 2-4"
+ # When multiple partitions with conflicting cpuset.cpus are created, the
+ # latter created ones will only get what are left of the available exclusive
+ # CPUs.
+ " C1-3:P1 . . . . . . C3-5:P1 0 A1:1-3|B1:4-5:XB1:4-5 A1:P1|B1:P1"
+
+ # cpuset.cpus can be set to a subset of sibling's cpuset.cpus.exclusive
+ " C1-3:X1-3 . . C4-5 . . . C1-2 0 A1:1-3|B1:1-2"
+
+ # cpuset.cpus can become empty with task in it as it inherits parent's effective CPUs
+ " C1-3 C2 . . . T:C . . 0 A1:1-3|A2:1-3"
+
# old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
# ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
# Failure cases:
# A task cannot be added to a partition with no cpu
- "C2-3:P1:S+ C3:P1 . . O2=0:T . . . 1 A1:|A2:3 A1:P1|A2:P1"
+ " C2-3:P1 C3:P1 . . O2=0:T . . . 1 A1:|A2:3 A1:P1|A2:P1"
# Changes to cpuset.cpus.exclusive that violate exclusivity rule is rejected
" C0-3 . . C4-5 X0-3 . . X3-5 1 A1:0-3|B1:4-5"
- # cpuset.cpus cannot be a subset of sibling cpuset.cpus.exclusive
+ # cpuset.cpus.exclusive cannot be set to a superset of sibling's cpuset.cpus
" C0-3 . . C4-5 X3-5 . . . 1 A1:0-3|B1:4-5"
)
@@ -454,29 +467,56 @@ REMOTE_TEST_MATRIX=(
# old-p1 old-p2 old-c11 old-c12 old-c21 old-c22
# new-p1 new-p2 new-c11 new-c12 new-c21 new-c22 ECPUs Pstate ISOLCPUS
# ------ ------ ------- ------- ------- ------- ----- ------ --------
- " X1-3:S+ X4-6:S+ X1-2 X3 X4-5 X6 \
+ " X1-3 X4-6 X1-2 X3 X4-5 X6 \
. . P2 P2 P2 P2 c11:1-2|c12:3|c21:4-5|c22:6 \
c11:P2|c12:P2|c21:P2|c22:P2 1-6"
- " CX1-4:S+ . X1-2:P2 C3 . . \
+ " CX1-4 . X1-2:P2 C3 . . \
. . . C3-4 . . p1:3-4|c11:1-2|c12:3-4 \
p1:P0|c11:P2|c12:P0 1-2"
- " CX1-4:S+ . X1-2:P2 . . . \
+ " CX1-4 . X1-2:P2 . . . \
X2-4 . . . . . p1:1,3-4|c11:2 \
p1:P0|c11:P2 2"
- " CX1-5:S+ . X1-2:P2 X3-5:P1 . . \
+ " CX1-5 . X1-2:P2 X3-5:P1 . . \
X2-4 . . . . . p1:1,5|c11:2|c12:3-4 \
p1:P0|c11:P2|c12:P1 2"
- " CX1-4:S+ . X1-2:P2 X3-4:P1 . . \
+ " CX1-4 . X1-2:P2 X3-4:P1 . . \
. . X2 . . . p1:1|c11:2|c12:3-4 \
p1:P0|c11:P2|c12:P1 2"
# p1 as member, will get its effective CPUs from its parent rtest
- " CX1-4:S+ . X1-2:P2 X3-4:P1 . . \
+ " CX1-4 . X1-2:P2 X3-4:P1 . . \
. . X1 CX2-4 . . p1:5-7|c11:1|c12:2-4 \
p1:P0|c11:P2|c12:P1 1"
- " CX1-4:S+ X5-6:P1:S+ . . . . \
- . . X1-2:P2 X4-5:P1 . X1-7:P2 p1:3|c11:1-2|c12:4:c22:5-6 \
+ " CX1-4 X5-6:P1 . . . . \
+ . . X1-2:P2 X4-5:P1 . X1-7:P2 p1:3|c11:1-2|c12:4:c22:5-6 \
p1:P0|p2:P1|c11:P2|c12:P1|c22:P2 \
1-2,4-6|1-2,5-6"
+ # c12 whose cpuset.cpus CPUs are all granted to c11 will become invalid partition
+ " C1-5:P1 . C1-4:P1 C2-3 . . \
+ . . . P1 . . p1:5|c11:1-4|c12:5 \
+ p1:P1|c11:P1|c12:P-1"
+ # Narrowing cpuset.cpus to previously sibling-excluded CPUs should
+ # not return CPUs that were never actually owned.
+ " C1-4:P1 . C1-2:P1 C1-3:P2 . . \
+ . . . C3 . . p1:4|c11:1-2|c12:3 \
+ p1:P1|c11:P1|c12:P2 3"
+ # Expanding cpuset.cpus to include a previously sibling-excluded CPU
+ # after the sibling has become a member should correctly request it.
+ " C1-4:P1 . C1-2:P1 C1-3:P2 . . \
+ . . P0 C2-3 . . p1:1,4|c11:1|c12:2-3 \
+ p1:P1|c11:P0|c12:P2 2-3"
+ # Changing a sibling partition's cpuset.cpus to overlap with another
+ # sibling partition should invalidate itself and return only actually
+ # allocated CPUs (effective_xcpus) to the parent.
+ " C1-4:P1 . C1-2:P1 C2-4:P2 . . \
+ . . . C1-2 . . p1:3-4|c11:1-2|c12:3-4 \
+ p1:P1|c11:P1|c12:P-2"
+ # Cpusets with empty cpuset.cpus should inherit parent's effective_cpus
+ " C1-4:P1 C5-6 C1-2 . C5 . \
+ . P1 P1 . . . p1:3-4|p2:5-6|c11:1-2|c12:3-4|c21:5|c22:5-6 \
+ p1:P1|p2:P1|c11:P1"
+ " C1-4:P1 C5-6 C1-2 . C5 . \
+ . P1 P1 . O5=0 . p1:3-4|p2:6|c11:1-2|c12:3-4|c21:6|c22:6 \
+ p1:P1|p2:P1|c11:P1"
)
#
@@ -488,6 +528,7 @@ write_cpu_online()
CPU=${1%=*}
VAL=${1#*=}
CPUFILE=//sys/devices/system/cpu/cpu${CPU}/online
+ echo $VAL > $CPUFILE || return 1
if [[ $VAL -eq 0 ]]
then
OFFLINE_CPUS="$OFFLINE_CPUS $CPU"
@@ -497,7 +538,6 @@ write_cpu_online()
sort | uniq -u)
}
fi
- echo $VAL > $CPUFILE
pause 0.05
}
@@ -515,7 +555,6 @@ set_ctrl_state()
CGRP=$1
STATE=$2
SHOWERR=${3}
- CTRL=${CTRL:=$CONTROLLER}
HASERR=0
REDIRECT="2> $TMPMSG"
[[ -z "$STATE" || "$STATE" = '.' ]] && return 0
@@ -525,15 +564,16 @@ set_ctrl_state()
for CMD in $(echo $STATE | sed -e "s/:/ /g")
do
TFILE=$CGRP/cgroup.procs
- SFILE=$CGRP/cgroup.subtree_control
PFILE=$CGRP/cpuset.cpus.partition
CFILE=$CGRP/cpuset.cpus
XFILE=$CGRP/cpuset.cpus.exclusive
- case $CMD in
- S*) PREFIX=${CMD#?}
- COMM="echo ${PREFIX}${CTRL} > $SFILE"
+
+ # Enable cpuset controller if not enabled yet
+ [[ -f $CFILE ]] || {
+ COMM="echo +cpuset > $CGRP/../cgroup.subtree_control"
eval $COMM $REDIRECT
- ;;
+ }
+ case $CMD in
X*)
CPUS=${CMD#?}
COMM="echo $CPUS > $XFILE"
@@ -565,7 +605,8 @@ set_ctrl_state()
eval $COMM $REDIRECT
;;
O*) VAL=${CMD#?}
- write_cpu_online $VAL
+ COMM="write_cpu_online $VAL"
+ eval $COMM $REDIRECT
;;
T*) COMM="echo 0 > $TFILE"
eval $COMM $REDIRECT
@@ -602,7 +643,7 @@ set_ctrl_state_noerr()
online_cpus()
{
- [[ -n "OFFLINE_CPUS" ]] && {
+ [[ -n "$OFFLINE_CPUS" ]] && {
for C in $OFFLINE_CPUS
do
write_cpu_online ${C}=1
@@ -749,7 +790,7 @@ check_cgroup_states()
# only CPUs in isolated partitions as well as those that are isolated at
# boot time.
#
-# $1 - expected isolated cpu list(s) <isolcpus1>{,<isolcpus2>}
+# $1 - expected isolated cpu list(s) <isolcpus1>{|<isolcpus2>}
# <isolcpus1> - expected sched/domains value
# <isolcpus2> - cpuset.cpus.isolated value = <isolcpus1> if not defined
#
@@ -932,7 +973,6 @@ check_test_results()
run_state_test()
{
TEST=$1
- CONTROLLER=cpuset
CGROUP_LIST=". A1 A1/A2 A1/A2/A3 B1"
RESET_LIST="A1/A2/A3 A1/A2 A1 B1"
I=0
@@ -988,7 +1028,6 @@ run_state_test()
run_remote_state_test()
{
TEST=$1
- CONTROLLER=cpuset
[[ -d rtest ]] || mkdir rtest
cd rtest
echo +cpuset > cgroup.subtree_control
@@ -1119,6 +1158,63 @@ test_isolated()
}
#
+# Select an online CPU isolated from scheduler domains at boot.
+# $1: test name used in the skip message
+#
+get_boot_isolated_cpu()
+{
+ TEST_NAME=$1
+ BOOT_ISOLATED_FILE=/sys/devices/system/cpu/isolated
+
+ [[ -r $BOOT_ISOLATED_FILE ]] || {
+ echo "$TEST_NAME test SKIPPED: boot isolation state unavailable"
+ return 1
+ }
+ BOOT_CPUS=$(cat $BOOT_ISOLATED_FILE)
+ [[ -n "$BOOT_CPUS" ]] || {
+ echo "$TEST_NAME test SKIPPED: no boot-isolated CPU"
+ return 1
+ }
+
+ BOOT_CPU=$(echo "$BOOT_CPUS" | sed -e 's/[,-].*//')
+ CPU_ONLINE=/sys/devices/system/cpu/cpu${BOOT_CPU}/online
+ [[ ! -e $CPU_ONLINE || $(cat $CPU_ONLINE) -eq 1 ]] || {
+ echo "$TEST_NAME test SKIPPED: CPU $BOOT_CPU is offline"
+ return 1
+ }
+}
+
+#
+# A CPU isolated at boot must stay isolated after it is released by a dynamic
+# isolated partition.
+#
+test_boot_isolated()
+{
+ TEST_NAME="Boot-isolated CPU partition release"
+ get_boot_isolated_cpu "$TEST_NAME" || return 0
+ echo "Running $TEST_NAME test ..."
+
+ cd $CGROUP2/test
+ echo member > cpuset.cpus.partition
+ echo $BOOT_CPU > cpuset.cpus
+ [[ $(cat cpuset.cpus.effective) = "$BOOT_CPU" ]] || {
+ echo "$TEST_NAME test SKIPPED: CPU $BOOT_CPU is unavailable"
+ echo "" > cpuset.cpus
+ cd $CGROUP2
+ return 0
+ }
+ test_partition isolated
+ test_partition member
+ check_isolcpus "." || {
+ echo "Boot-isolated CPU $BOOT_CPU was lost after partition release"
+ exit 1
+ }
+ echo "" > cpuset.cpus
+ cd $CGROUP2
+ echo "$TEST_NAME test PASSED."
+}
+
+#
# Wait for inotify event for the given file and read it
# $1: cgroup file to wait for
# $2: file to store the read result
@@ -1189,5 +1285,6 @@ trap cleanup 0 2 3 6
run_state_test TEST_MATRIX
run_remote_state_test REMOTE_TEST_MATRIX
test_isolated
+test_boot_isolated
test_inotify
echo "All tests PASSED."
diff --git a/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh b/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh
index 42a6628fb8bc..1c0444729e70 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh
@@ -18,7 +18,7 @@ write_test() {
echo "testing $interface $value"
echo $value > $dir/$interface
new=$(cat $dir/$interface)
- [[ $value -ne $(cat $dir/$interface) ]] && {
+ [[ "$value" != "$new" ]] && {
echo "$interface write $value failed: new:$new"
exit 1
}
diff --git a/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh b/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh
index 7406c24be1ac..da97f1643f9a 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh
@@ -14,7 +14,7 @@ skip_test() {
[[ $(id -u) -eq 0 ]] || skip_test "Test must be run as root!"
# Find cpuset v1 mount point
-CPUSET=$(mount -t cgroup | grep cpuset | head -1 | awk -e '{print $3}')
+CPUSET=$(mount -t cgroup | grep cpuset | head -1 | awk '{print $3}')
[[ -n "$CPUSET" ]] || skip_test "cpuset v1 mount point not found!"
#
diff --git a/tools/testing/selftests/cgroup/test_freezer.c b/tools/testing/selftests/cgroup/test_freezer.c
index 97fae92c8387..f28bb02e9783 100644
--- a/tools/testing/selftests/cgroup/test_freezer.c
+++ b/tools/testing/selftests/cgroup/test_freezer.c
@@ -642,7 +642,7 @@ cleanup:
*/
static int proc_check_stopped(int pid)
{
- char buf[PAGE_SIZE];
+ char buf[BUF_SIZE];
int len;
len = proc_read_text(pid, 0, "stat", buf, sizeof(buf));
@@ -1353,7 +1353,7 @@ static int test_cgfreezer_time_child(const char *root)
}
if (ctime <= ptime) {
- debug("Expect ctime (%ld) <= ptime (%ld)\n", ctime, ptime);
+ debug("Expect ctime (%ld) > ptime (%ld)\n", ctime, ptime);
goto cleanup;
}
@@ -1491,9 +1491,9 @@ int main(int argc, char *argv[])
int i;
ksft_print_header();
- ksft_set_plan(ARRAY_SIZE(tests));
if (cg_find_unified_root(root, sizeof(root), NULL))
ksft_exit_skip("cgroup v2 isn't mounted\n");
+ ksft_set_plan(ARRAY_SIZE(tests));
for (i = 0; i < ARRAY_SIZE(tests); i++) {
switch (tests[i].fn(root)) {
case KSFT_PASS:
diff --git a/tools/testing/selftests/cgroup/test_hugetlb_memcg.c b/tools/testing/selftests/cgroup/test_hugetlb_memcg.c
index f451aa449be6..8c5aced813b6 100644
--- a/tools/testing/selftests/cgroup/test_hugetlb_memcg.c
+++ b/tools/testing/selftests/cgroup/test_hugetlb_memcg.c
@@ -199,7 +199,10 @@ out:
int main(int argc, char **argv)
{
char root[PATH_MAX];
- int ret = EXIT_SUCCESS, has_memory_hugetlb_acc;
+ int has_memory_hugetlb_acc;
+
+ ksft_print_header();
+ ksft_set_plan(1);
has_memory_hugetlb_acc = proc_mount_contains("memory_hugetlb_accounting");
if (has_memory_hugetlb_acc < 0)
@@ -211,12 +214,20 @@ int main(int argc, char **argv)
if (get_hugepage_size() != 2048) {
ksft_print_msg("test_hugetlb_memcg requires 2MB hugepages\n");
ksft_test_result_skip("test_hugetlb_memcg\n");
- return ret;
+ ksft_finished();
}
if (cg_find_unified_root(root, sizeof(root), NULL))
ksft_exit_skip("cgroup v2 isn't mounted\n");
+ if (cg_read_strstr(root, "cgroup.controllers", "memory"))
+ ksft_exit_skip("memory controller isn't available\n");
+
+ if (cg_read_strstr(root, "cgroup.subtree_control", "memory")) {
+ if (cg_write(root, "cgroup.subtree_control", "+memory"))
+ ksft_exit_skip("Failed to set memory controller\n");
+ }
+
switch (test_hugetlb_memcg(root)) {
case KSFT_PASS:
ksft_test_result_pass("test_hugetlb_memcg\n");
@@ -225,10 +236,9 @@ int main(int argc, char **argv)
ksft_test_result_skip("test_hugetlb_memcg\n");
break;
default:
- ret = EXIT_FAILURE;
ksft_test_result_fail("test_hugetlb_memcg\n");
break;
}
- return ret;
+ ksft_finished();
}
diff --git a/tools/testing/selftests/cgroup/test_kill.c b/tools/testing/selftests/cgroup/test_kill.c
index c8c9d306925b..bac1ddd8cb94 100644
--- a/tools/testing/selftests/cgroup/test_kill.c
+++ b/tools/testing/selftests/cgroup/test_kill.c
@@ -7,6 +7,7 @@
#include <stdlib.h>
#include <string.h>
#include <sys/types.h>
+#include <sys/wait.h>
#include <unistd.h>
#include "kselftest.h"
@@ -86,7 +87,7 @@ cleanup:
wait_for_pid(pids[i]);
if (ret == KSFT_PASS &&
- cg_read_strcmp(cgroup, "cgroup.events", "populated 0\n"))
+ cg_read_strcmp_wait(cgroup, "cgroup.events", "populated 0\n"))
ret = KSFT_FAIL;
if (cgroup)
@@ -190,7 +191,8 @@ cleanup:
wait_for_pid(pids[i]);
if (ret == KSFT_PASS &&
- cg_read_strcmp(cgroup[0], "cgroup.events", "populated 0\n"))
+ cg_read_strcmp_wait(cgroup[0], "cgroup.events",
+ "populated 0\n"))
ret = KSFT_FAIL;
for (i = 9; i >= 0 && cgroup[i]; i--) {
@@ -251,7 +253,7 @@ cleanup:
wait_for_pid(pid);
if (ret == KSFT_PASS &&
- cg_read_strcmp(cgroup, "cgroup.events", "populated 0\n"))
+ cg_read_strcmp_wait(cgroup, "cgroup.events", "populated 0\n"))
ret = KSFT_FAIL;
if (cgroup)
@@ -260,6 +262,59 @@ cleanup:
return ret;
}
+/*
+ * Test that a cgroup that was killed in the past can still be the target
+ * of clone3(CLONE_INTO_CGROUP): writing cgroup.kill must only kill the
+ * tasks in the cgroup at the time of the write, not tasks cloned into
+ * it afterwards.
+ */
+static int test_cgkill_clone_into_killed(const char *root)
+{
+ pid_t pid;
+ int cgroup_fd = -EBADF;
+ int ret = KSFT_FAIL;
+ char *cgroup = NULL;
+
+ cgroup = cg_name(root, "cg_test_clone_into_killed");
+ if (!cgroup)
+ goto cleanup;
+
+ if (cg_create(cgroup))
+ goto cleanup;
+
+ /* Kill the cgroup while it is still empty. */
+ if (cg_write(cgroup, "cgroup.kill", "1"))
+ goto cleanup;
+
+ cgroup_fd = dirfd_open_opath(cgroup);
+ if (cgroup_fd < 0)
+ goto cleanup;
+
+ pid = clone_into_cgroup(cgroup_fd);
+ if (pid < 0) {
+ if (errno == ENOSYS)
+ ret = KSFT_SKIP;
+ goto cleanup;
+ }
+
+ if (pid == 0)
+ exit(EXIT_SUCCESS);
+
+ /* The child must not be SIGKILLed; it has to exit cleanly. */
+ if (clone_reap(pid, WEXITED) != EXIT_SUCCESS)
+ goto cleanup;
+
+ ret = KSFT_PASS;
+
+cleanup:
+ if (cgroup_fd >= 0)
+ close(cgroup_fd);
+ if (cgroup)
+ cg_destroy(cgroup);
+ free(cgroup);
+ return ret;
+}
+
#define T(x) { x, #x }
struct cgkill_test {
int (*fn)(const char *root);
@@ -268,6 +323,7 @@ struct cgkill_test {
T(test_cgkill_simple),
T(test_cgkill_tree),
T(test_cgkill_forkbomb),
+ T(test_cgkill_clone_into_killed),
};
#undef T
@@ -277,9 +333,9 @@ int main(int argc, char *argv[])
int i;
ksft_print_header();
- ksft_set_plan(ARRAY_SIZE(tests));
if (cg_find_unified_root(root, sizeof(root), NULL))
ksft_exit_skip("cgroup v2 isn't mounted\n");
+ ksft_set_plan(ARRAY_SIZE(tests));
for (i = 0; i < ARRAY_SIZE(tests); i++) {
switch (tests[i].fn(root)) {
case KSFT_PASS:
diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c
index ca38525484e3..437f2d35f205 100644
--- a/tools/testing/selftests/cgroup/test_kmem.c
+++ b/tools/testing/selftests/cgroup/test_kmem.c
@@ -24,8 +24,9 @@
* the maximum discrepancy between charge and vmstat entries is number
* of cpus multiplied by 64 pages.
*/
-#define MAX_VMSTAT_ERROR (4096 * 64 * get_nprocs())
+#define MAX_VMSTAT_ERROR (sysconf(_SC_PAGESIZE) * 64 * get_nprocs())
+#define KMEM_DEAD_WAIT_RETRIES 80
static int alloc_dcache(const char *cgroup, void *arg)
{
@@ -144,7 +145,7 @@ static int cg_run_in_subcgroups(const char *parent,
return -1;
}
- if (cg_run(child, fn, NULL)) {
+ if (cg_run(child, fn, arg)) {
cg_destroy(child);
free(child);
return -1;
@@ -306,9 +307,7 @@ static int test_kmem_dead_cgroups(const char *root)
{
int ret = KSFT_FAIL;
char *parent;
- long dead;
- int i;
- int max_time = 20;
+ long dead = -1;
parent = cg_name(root, "kmem_dead_cgroups_test");
if (!parent)
@@ -323,21 +322,19 @@ static int test_kmem_dead_cgroups(const char *root)
if (cg_run_in_subcgroups(parent, alloc_dcache, (void *)100, 30))
goto cleanup;
- for (i = 0; i < max_time; i++) {
- dead = cg_read_key_long(parent, "cgroup.stat",
- "nr_dying_descendants ");
- if (dead == 0) {
- ret = KSFT_PASS;
- break;
- }
- /*
- * Reclaiming cgroups might take some time,
- * let's wait a bit and repeat.
- */
- sleep(1);
- if (i > 5)
- printf("Waiting time longer than 5s; wait: %ds (dead: %ld)\n", i, dead);
- }
+ /*
+ * Allow up to ~8s for reclaim of dying descendants to complete.
+ * This is a generous upper bound derived from stress testing, not
+ * from a specific kernel constant, and can be adjusted if reclaim
+ * behavior changes in the future.
+ */
+ dead = cg_read_key_long_poll(parent, "cgroup.stat",
+ "nr_dying_descendants ", 0, KMEM_DEAD_WAIT_RETRIES,
+ DEFAULT_WAIT_INTERVAL_US);
+ if (dead)
+ goto cleanup;
+
+ ret = KSFT_PASS;
cleanup:
cg_destroy(parent);
@@ -356,7 +353,7 @@ static int test_percpu_basic(const char *root)
{
int ret = KSFT_FAIL;
char *parent, *child;
- long current, percpu;
+ long current, percpu, slab;
int i;
parent = cg_name(root, "percpu_basic_test");
@@ -371,24 +368,29 @@ static int test_percpu_basic(const char *root)
for (i = 0; i < 1000; i++) {
child = cg_name_indexed(parent, "child", i);
- if (!child)
- return -1;
+ if (!child) {
+ ret = -1;
+ goto cleanup_children;
+ }
- if (cg_create(child))
+ if (cg_create(child)) {
+ free(child);
goto cleanup_children;
+ }
free(child);
}
current = cg_read_long(parent, "memory.current");
percpu = cg_read_key_long(parent, "memory.stat", "percpu ");
+ slab = cg_read_key_long(parent, "memory.stat", "slab ");
- if (current > 0 && percpu > 0 && labs(current - percpu) <
- MAX_VMSTAT_ERROR)
+ if (current > 0 && percpu > 0 && slab >= 0 &&
+ labs(current - (percpu + slab)) < MAX_VMSTAT_ERROR)
ret = KSFT_PASS;
else
- printf("memory.current %ld\npercpu %ld\n",
- current, percpu);
+ printf("memory.current %ld\npercpu %ld\nslab %ld\ndelta %ld\n",
+ current, percpu, slab, current - (percpu + slab));
cleanup_children:
for (i = 0; i < 1000; i++) {
@@ -424,7 +426,6 @@ int main(int argc, char **argv)
int i;
ksft_print_header();
- ksft_set_plan(ARRAY_SIZE(tests));
if (cg_find_unified_root(root, sizeof(root), NULL))
ksft_exit_skip("cgroup v2 isn't mounted\n");
@@ -439,6 +440,7 @@ int main(int argc, char **argv)
if (cg_write(root, "cgroup.subtree_control", "+memory"))
ksft_exit_skip("Failed to set memory controller\n");
+ ksft_set_plan(ARRAY_SIZE(tests));
for (i = 0; i < ARRAY_SIZE(tests); i++) {
switch (tests[i].fn(root)) {
case KSFT_PASS:
diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c
index 4e1647568c5b..0ed82347044e 100644
--- a/tools/testing/selftests/cgroup/test_memcontrol.c
+++ b/tools/testing/selftests/cgroup/test_memcontrol.c
@@ -10,6 +10,7 @@
#include <sys/stat.h>
#include <sys/types.h>
#include <unistd.h>
+#include <sys/inotify.h>
#include <sys/socket.h>
#include <sys/wait.h>
#include <arpa/inet.h>
@@ -21,17 +22,20 @@
#include "kselftest.h"
#include "cgroup_util.h"
+#define MEMCG_SOCKSTAT_WAIT_RETRIES 30
+
static bool has_localevents;
static bool has_recursiveprot;
+static int page_size;
int get_temp_fd(void)
{
- return open(".", O_TMPFILE | O_RDWR | O_EXCL);
+ return open(".", O_TMPFILE | O_RDWR | O_EXCL, 0600);
}
int alloc_pagecache(int fd, size_t size)
{
- char buf[PAGE_SIZE];
+ char buf[BUF_SIZE];
struct stat st;
int i;
@@ -52,22 +56,38 @@ cleanup:
return -1;
}
-int alloc_anon(const char *cgroup, void *arg)
+static char *alloc_and_populate_anon(size_t size)
{
- size_t size = (unsigned long)arg;
char *buf, *ptr;
buf = malloc(size);
- for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
+ if (buf == NULL) {
+ fprintf(stderr, "malloc() failed\n");
+ return NULL;
+ }
+
+ for (ptr = buf; ptr < buf + size; ptr += page_size)
*ptr = 0;
+ return buf;
+}
+
+int alloc_anon(const char *cgroup, void *arg)
+{
+ size_t size = (unsigned long)arg;
+ char *buf;
+
+ buf = alloc_and_populate_anon(size);
+ if (!buf)
+ return -1;
+
free(buf);
return 0;
}
int is_swap_enabled(void)
{
- char buf[PAGE_SIZE];
+ char buf[BUF_SIZE];
const char delim[] = "\n";
int cnt = 0;
char *line;
@@ -110,7 +130,7 @@ static int test_memcg_subtree_control(const char *root)
{
char *parent, *child, *parent2 = NULL, *child2 = NULL;
int ret = KSFT_FAIL;
- char buf[PAGE_SIZE];
+ char buf[BUF_SIZE];
/* Create two nested cgroups with the memory controller enabled */
parent = cg_name(root, "memcg_test_0");
@@ -171,18 +191,13 @@ cleanup_free:
static int alloc_anon_50M_check(const char *cgroup, void *arg)
{
size_t size = MB(50);
- char *buf, *ptr;
+ char *buf;
long anon, current;
int ret = -1;
- buf = malloc(size);
- if (buf == NULL) {
- fprintf(stderr, "malloc() failed\n");
+ buf = alloc_and_populate_anon(size);
+ if (!buf)
return -1;
- }
-
- for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
- *ptr = 0;
current = cg_read_long(cgroup, "memory.current");
if (current < size)
@@ -403,16 +418,11 @@ static int alloc_anon_noexit(const char *cgroup, void *arg)
{
int ppid = getppid();
size_t size = (unsigned long)arg;
- char *buf, *ptr;
+ char *buf;
- buf = malloc(size);
- if (buf == NULL) {
- fprintf(stderr, "malloc() failed\n");
+ buf = alloc_and_populate_anon(size);
+ if (!buf)
return -1;
- }
-
- for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
- *ptr = 0;
while (getppid() == ppid)
sleep(1);
@@ -987,18 +997,13 @@ static int alloc_anon_50M_check_swap(const char *cgroup, void *arg)
{
long mem_max = (long)arg;
size_t size = MB(50);
- char *buf, *ptr;
+ char *buf;
long mem_current, swap_current;
int ret = -1;
- buf = malloc(size);
- if (buf == NULL) {
- fprintf(stderr, "malloc() failed\n");
+ buf = alloc_and_populate_anon(size);
+ if (!buf)
return -1;
- }
-
- for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
- *ptr = 0;
mem_current = cg_read_long(cgroup, "memory.current");
if (!mem_current || !values_close(mem_current, mem_max, 3))
@@ -1278,8 +1283,11 @@ static int tcp_server(const char *cgroup, void *arg)
saddr.sin6_port = htons(srv_args->port);
sk = socket(AF_INET6, SOCK_STREAM, 0);
- if (sk < 0)
+ if (sk < 0) {
+ /* Pass back errno to the ctl_fd */
+ write(ctl_fd, &errno, sizeof(errno));
return ret;
+ }
if (setsockopt(sk, SOL_SOCKET, SO_REUSEADDR, &yes, sizeof(yes)) < 0)
goto cleanup;
@@ -1384,6 +1392,7 @@ static int test_memcg_sock(const char *root)
int bind_retries = 5, ret = KSFT_FAIL, pid, err;
unsigned short port;
char *memcg;
+ long sock_post = -1;
memcg = cg_name(root, "memcg_test");
if (!memcg)
@@ -1409,6 +1418,12 @@ static int test_memcg_sock(const char *root)
goto cleanup;
close(args.ctl[0]);
+ /* Skip if address family not supported by protocol */
+ if (err == EAFNOSUPPORT) {
+ ret = KSFT_SKIP;
+ goto cleanup;
+ }
+
if (!err)
break;
if (err != EADDRINUSE)
@@ -1432,7 +1447,22 @@ static int test_memcg_sock(const char *root)
if (cg_read_long(memcg, "memory.current") < 0)
goto cleanup;
- if (cg_read_key_long(memcg, "memory.stat", "sock "))
+ /*
+ * memory.stat is updated asynchronously via the memcg rstat
+ * flushing worker, which runs periodically (every 2 seconds,
+ * see FLUSH_TIME). On a busy system, the "sock " counter may
+ * stay non-zero for a short period of time after the TCP
+ * connection is closed and all socket memory has been
+ * uncharged.
+ *
+ * Poll memory.stat for up to 3 seconds (~FLUSH_TIME plus some
+ * scheduling slack) and require that the "sock " counter
+ * eventually drops to zero.
+ */
+ sock_post = cg_read_key_long_poll(memcg, "memory.stat", "sock ", 0,
+ MEMCG_SOCKSTAT_WAIT_RETRIES,
+ DEFAULT_WAIT_INTERVAL_US);
+ if (sock_post)
goto cleanup;
ret = KSFT_PASS;
@@ -1625,6 +1655,115 @@ cleanup:
return ret;
}
+static int read_event(int inotify_fd, int expected_event, int expected_wd)
+{
+ struct inotify_event event;
+ ssize_t len = 0;
+
+ len = read(inotify_fd, &event, sizeof(event));
+ if (len < (ssize_t)sizeof(event))
+ return -1;
+
+ if (event.mask != expected_event || event.wd != expected_wd) {
+ fprintf(stderr,
+ "event does not match expected values: mask %d (expected %d) wd %d (expected %d)\n",
+ event.mask, expected_event, event.wd, expected_wd);
+ return -1;
+ }
+
+ return 0;
+}
+
+static int test_memcg_inotify_delete_file(const char *root)
+{
+ int ret = KSFT_FAIL;
+ char *memcg = NULL;
+ int fd, wd;
+
+ memcg = cg_name(root, "memcg_test_0");
+
+ if (!memcg)
+ goto cleanup;
+
+ if (cg_create(memcg))
+ goto cleanup;
+
+ fd = inotify_init1(0);
+ if (fd == -1)
+ goto cleanup;
+
+ wd = inotify_add_watch(fd, cg_control(memcg, "memory.events"), IN_DELETE_SELF);
+ if (wd == -1)
+ goto cleanup;
+
+ if (cg_destroy(memcg))
+ goto cleanup;
+ free(memcg);
+ memcg = NULL;
+
+ if (read_event(fd, IN_DELETE_SELF, wd))
+ goto cleanup;
+
+ if (read_event(fd, IN_IGNORED, wd))
+ goto cleanup;
+
+ ret = KSFT_PASS;
+
+cleanup:
+ if (fd >= 0)
+ close(fd);
+ if (memcg)
+ cg_destroy(memcg);
+ free(memcg);
+
+ return ret;
+}
+
+static int test_memcg_inotify_delete_dir(const char *root)
+{
+ int ret = KSFT_FAIL;
+ char *memcg = NULL;
+ int fd, wd;
+
+ memcg = cg_name(root, "memcg_test_0");
+
+ if (!memcg)
+ goto cleanup;
+
+ if (cg_create(memcg))
+ goto cleanup;
+
+ fd = inotify_init1(0);
+ if (fd == -1)
+ goto cleanup;
+
+ wd = inotify_add_watch(fd, memcg, IN_DELETE_SELF);
+ if (wd == -1)
+ goto cleanup;
+
+ if (cg_destroy(memcg))
+ goto cleanup;
+ free(memcg);
+ memcg = NULL;
+
+ if (read_event(fd, IN_DELETE_SELF, wd))
+ goto cleanup;
+
+ if (read_event(fd, IN_IGNORED, wd))
+ goto cleanup;
+
+ ret = KSFT_PASS;
+
+cleanup:
+ if (fd >= 0)
+ close(fd);
+ if (memcg)
+ cg_destroy(memcg);
+ free(memcg);
+
+ return ret;
+}
+
#define T(x) { x, #x }
struct memcg_test {
int (*fn)(const char *root);
@@ -1644,6 +1783,8 @@ struct memcg_test {
T(test_memcg_oom_group_leaf_events),
T(test_memcg_oom_group_parent_events),
T(test_memcg_oom_group_score_events),
+ T(test_memcg_inotify_delete_file),
+ T(test_memcg_inotify_delete_dir),
};
#undef T
@@ -1652,8 +1793,11 @@ int main(int argc, char **argv)
char root[PATH_MAX];
int i, proc_status;
+ page_size = sysconf(_SC_PAGE_SIZE);
+ if (page_size <= 0)
+ page_size = BUF_SIZE;
+
ksft_print_header();
- ksft_set_plan(ARRAY_SIZE(tests));
if (cg_find_unified_root(root, sizeof(root), NULL))
ksft_exit_skip("cgroup v2 isn't mounted\n");
@@ -1678,6 +1822,7 @@ int main(int argc, char **argv)
ksft_exit_skip("Failed to query cgroup mount option\n");
has_localevents = proc_status;
+ ksft_set_plan(ARRAY_SIZE(tests));
for (i = 0; i < ARRAY_SIZE(tests); i++) {
switch (tests[i].fn(root)) {
case KSFT_PASS:
diff --git a/tools/testing/selftests/cgroup/test_pids.c b/tools/testing/selftests/cgroup/test_pids.c
index 9a387c815d2c..710109b53dfe 100644
--- a/tools/testing/selftests/cgroup/test_pids.c
+++ b/tools/testing/selftests/cgroup/test_pids.c
@@ -148,7 +148,6 @@ int main(int argc, char **argv)
char root[PATH_MAX];
ksft_print_header();
- ksft_set_plan(ARRAY_SIZE(tests));
if (cg_find_unified_root(root, sizeof(root), NULL))
ksft_exit_skip("cgroup v2 isn't mounted\n");
@@ -163,6 +162,7 @@ int main(int argc, char **argv)
if (cg_write(root, "cgroup.subtree_control", "+pids"))
ksft_exit_skip("Failed to set pids controller\n");
+ ksft_set_plan(ARRAY_SIZE(tests));
for (int i = 0; i < ARRAY_SIZE(tests); i++) {
switch (tests[i].fn(root)) {
case KSFT_PASS:
diff --git a/tools/testing/selftests/cgroup/test_zswap.c b/tools/testing/selftests/cgroup/test_zswap.c
index 64ebc3f3f203..8df54b59513a 100644
--- a/tools/testing/selftests/cgroup/test_zswap.c
+++ b/tools/testing/selftests/cgroup/test_zswap.c
@@ -5,14 +5,24 @@
#include <unistd.h>
#include <stdio.h>
#include <signal.h>
+#include <errno.h>
+#include <fcntl.h>
#include <sys/sysinfo.h>
#include <string.h>
#include <sys/wait.h>
#include <sys/mman.h>
+#include <sys/random.h>
#include "kselftest.h"
#include "cgroup_util.h"
+static int page_size;
+
+#define PATH_ZSWAP "/sys/module/zswap"
+#define PATH_ZSWAP_ENABLED "/sys/module/zswap/parameters/enabled"
+#define PATH_ZSWAP_SHRINKER_ENABLED "/sys/module/zswap/parameters/shrinker_enabled"
+#define PATH_ZSWAP_STORED_PAGES "/sys/kernel/debug/zswap/stored_pages"
+
static int read_int(const char *path, size_t *value)
{
FILE *file;
@@ -47,7 +57,7 @@ static int read_min_free_kb(size_t *value)
static int get_zswap_stored_pages(size_t *value)
{
- return read_int("/sys/kernel/debug/zswap/stored_pages", value);
+ return read_int(PATH_ZSWAP_STORED_PAGES, value);
}
static long get_cg_wb_count(const char *cg)
@@ -68,11 +78,11 @@ static int allocate_and_read_bytes(const char *cgroup, void *arg)
if (!mem)
return -1;
- for (int i = 0; i < size; i += 4095)
+ for (int i = 0; i < size; i += page_size)
mem[i] = 'a';
/* Go through the allocated memory to (z)swap in and out pages */
- for (int i = 0; i < size; i += 4095) {
+ for (int i = 0; i < size; i += page_size) {
if (mem[i] != 'a')
ret = -1;
}
@@ -88,7 +98,7 @@ static int allocate_bytes(const char *cgroup, void *arg)
if (!mem)
return -1;
- for (int i = 0; i < size; i += 4095)
+ for (int i = 0; i < size; i += page_size)
mem[i] = 'a';
free(mem);
return 0;
@@ -113,6 +123,27 @@ fail:
}
/*
+ * Writeback is asynchronous; poll until at least one writeback has
+ * been recorded for @cg, or until @timeout_ms has elapsed.
+ */
+static long wait_for_writeback(const char *cg, int timeout_ms)
+{
+ long elapsed, count;
+ for (elapsed = 0; elapsed < timeout_ms; elapsed += 100) {
+ count = get_cg_wb_count(cg);
+
+ if (count < 0)
+ return -1;
+ if (count > 0)
+ return count;
+
+ usleep(100000);
+ }
+
+ return 0;
+}
+
+/*
* Sanity test to check that pages are written into zswap.
*/
static int test_zswap_usage(const char *root)
@@ -160,21 +191,25 @@ out:
static int test_swapin_nozswap(const char *root)
{
int ret = KSFT_FAIL;
- char *test_group;
- long swap_peak, zswpout;
+ char *test_group, mem_max_buf[32];
+ long swap_peak, zswpout, min_swap;
+ size_t allocation_size = page_size * 512;
+
+ min_swap = allocation_size / 4;
+ snprintf(mem_max_buf, sizeof(mem_max_buf), "%zu", allocation_size * 3/4);
test_group = cg_name(root, "no_zswap_test");
if (!test_group)
goto out;
if (cg_create(test_group))
goto out;
- if (cg_write(test_group, "memory.max", "8M"))
+ if (cg_write(test_group, "memory.max", mem_max_buf))
goto out;
if (cg_write(test_group, "memory.zswap.max", "0"))
goto out;
/* Allocate and read more than memory.max to trigger swapin */
- if (cg_run(test_group, allocate_and_read_bytes, (void *)MB(32)))
+ if (cg_run(test_group, allocate_and_read_bytes, (void *)allocation_size))
goto out;
/* Verify that pages are swapped out, but no zswap happened */
@@ -184,8 +219,9 @@ static int test_swapin_nozswap(const char *root)
goto out;
}
- if (swap_peak < MB(24)) {
- ksft_print_msg("at least 24MB of memory should be swapped out\n");
+ if (swap_peak < min_swap) {
+ ksft_print_msg("at least %ldKB of memory should be swapped out\n",
+ min_swap / 1024);
goto out;
}
@@ -235,7 +271,7 @@ static int test_zswapin(const char *root)
goto out;
}
- if (zswpin < MB(24) / PAGE_SIZE) {
+ if (zswpin < MB(24) / page_size) {
ksft_print_msg("at least 24MB should be brought back from zswap\n");
goto out;
}
@@ -255,16 +291,15 @@ out:
This will move it into zswap.
* 3. Save current zswap usage.
* 4. Move the memory allocated in step 1 back in from zswap.
- * 5. Set zswap.max to half the amount that was recorded in step 3.
+ * 5. Set zswap.max to 1/4 of the amount that was recorded in step 3.
* 6. Attempt to reclaim memory equal to the amount that was allocated,
this will either trigger writeback if it's enabled, or reclamation
will fail if writeback is disabled as there isn't enough zswap space.
*/
static int attempt_writeback(const char *cgroup, void *arg)
{
- long pagesize = sysconf(_SC_PAGESIZE);
- size_t memsize = MB(4);
- char buf[pagesize];
+ size_t memsize = page_size * 1024;
+ char buf[page_size];
long zswap_usage;
bool wb_enabled = *(bool *) arg;
int ret = -1;
@@ -279,11 +314,11 @@ static int attempt_writeback(const char *cgroup, void *arg)
* half empty, this will result in data that is still compressible
* and ends up in zswap, with material zswap usage.
*/
- for (int i = 0; i < pagesize; i++)
- buf[i] = i < pagesize/2 ? (char) i : 0;
+ for (int i = 0; i < page_size; i++)
+ buf[i] = i < page_size/2 ? (char) i : 0;
- for (int i = 0; i < memsize; i += pagesize)
- memcpy(&mem[i], buf, pagesize);
+ for (int i = 0; i < memsize; i += page_size)
+ memcpy(&mem[i], buf, page_size);
/* Try and reclaim allocated memory */
if (cg_write_numeric(cgroup, "memory.reclaim", memsize)) {
@@ -294,19 +329,19 @@ static int attempt_writeback(const char *cgroup, void *arg)
zswap_usage = cg_read_long(cgroup, "memory.zswap.current");
/* zswpin */
- for (int i = 0; i < memsize; i += pagesize) {
- if (memcmp(&mem[i], buf, pagesize)) {
+ for (int i = 0; i < memsize; i += page_size) {
+ if (memcmp(&mem[i], buf, page_size)) {
ksft_print_msg("invalid memory\n");
goto out;
}
}
- if (cg_write_numeric(cgroup, "memory.zswap.max", zswap_usage/2))
+ if (cg_write_numeric(cgroup, "memory.zswap.max", zswap_usage/4))
goto out;
/*
* If writeback is enabled, trying to reclaim memory now will trigger a
- * writeback as zswap.max is half of what was needed when reclaim ran the first time.
+ * writeback as zswap.max is 1/4 of what was needed when reclaim ran the first time.
* If writeback is disabled, memory reclaim will fail as zswap is limited and
* it can't writeback to swap.
*/
@@ -333,7 +368,10 @@ static int test_zswap_writeback_one(const char *cgroup, bool wb)
return -1;
/* Verify that zswap writeback occurred only if writeback was enabled */
- zswpwb_after = get_cg_wb_count(cgroup);
+ if (wb)
+ zswpwb_after = wait_for_writeback(cgroup, 5000);
+ else
+ zswpwb_after = get_cg_wb_count(cgroup);
if (zswpwb_after < 0)
return -1;
@@ -407,6 +445,16 @@ static int test_zswap_writeback_disabled(const char *root)
return test_zswap_writeback(root, false);
}
+static bool zswap_shrinker_enabled(void)
+{
+ char value[2];
+
+ if (read_text(PATH_ZSWAP_SHRINKER_ENABLED, value, sizeof(value)) <= 0)
+ return 0;
+
+ return value[0] == 'Y';
+}
+
/*
* When trying to store a memcg page in zswap, if the memcg hits its memory
* limit in zswap, writeback should affect only the zswapped pages of that
@@ -415,44 +463,84 @@ static int test_zswap_writeback_disabled(const char *root)
static int test_no_invasive_cgroup_shrink(const char *root)
{
int ret = KSFT_FAIL;
- size_t control_allocation_size = MB(10);
- char *control_allocation = NULL, *wb_group = NULL, *control_group = NULL;
+ unsigned int off;
+ long zswpwb_before, zswpwb_after, zswpwb_target;
+ size_t allocation_size = page_size * 1024;
+ unsigned int nr_pages = allocation_size / page_size;
+ char zswap_max_buf[32], mem_max_buf[32];
+ char *zw_allocation = NULL, *wb_allocation = NULL;
+ char *zw_group = NULL, *wb_group = NULL;
+
+ snprintf(zswap_max_buf, sizeof(zswap_max_buf), "%d", page_size);
+ snprintf(mem_max_buf, sizeof(mem_max_buf), "%zu", allocation_size / 2);
wb_group = setup_test_group_1M(root, "per_memcg_wb_test1");
if (!wb_group)
return KSFT_FAIL;
- if (cg_write(wb_group, "memory.zswap.max", "10K"))
+ if (cg_write(wb_group, "memory.zswap.max", zswap_max_buf))
goto out;
- control_group = setup_test_group_1M(root, "per_memcg_wb_test2");
- if (!control_group)
+ if (cg_write(wb_group, "memory.max", mem_max_buf))
goto out;
- /* Push some test_group2 memory into zswap */
- if (cg_enter_current(control_group))
+ zw_group = setup_test_group_1M(root, "per_memcg_wb_test2");
+ if (!zw_group)
goto out;
- control_allocation = malloc(control_allocation_size);
- for (int i = 0; i < control_allocation_size; i += 4095)
- control_allocation[i] = 'a';
- if (cg_read_key_long(control_group, "memory.stat", "zswapped") < 1)
+ if (cg_write(zw_group, "memory.max", mem_max_buf))
+ goto out;
+
+ /* Push some zw_group memory into zswap (simple data, easy to compress) */
+ if (cg_enter_current(zw_group))
goto out;
+ zw_allocation = malloc(allocation_size);
+ for (int i = 0; i < nr_pages; i++) {
+ off = (unsigned long)i * page_size;
+ memset(&zw_allocation[off], 0, page_size);
+ memset(&zw_allocation[off], 'a', page_size/4);
+ }
+ if (cg_read_key_long(zw_group, "memory.stat", "zswapped") < 1)
+ goto out;
+
+ /* If the shrinker is enabled, try to let the writebacks finish first */
+ if (zswap_shrinker_enabled())
+ sleep(5);
- /* Allocate 10x memory.max to push wb_group memory into zswap and trigger wb */
- if (cg_run(wb_group, allocate_bytes, (void *)MB(10)))
+ zswpwb_before = get_cg_wb_count(zw_group);
+ if (zswpwb_before < 0)
goto out;
- /* Verify that only zswapped memory from gwb_group has been written back */
- if (get_cg_wb_count(wb_group) > 0 && get_cg_wb_count(control_group) == 0)
+ /* Push wb_group memory into zswap with hard-to-compress data to trigger wb */
+ if (cg_enter_current(wb_group))
+ goto out;
+ wb_allocation = malloc(allocation_size);
+ if (!wb_allocation)
+ goto out;
+ for (int i = 0; i < nr_pages; i++) {
+ off = (unsigned long)i * page_size;
+ memset(&wb_allocation[off], 0, page_size);
+ getrandom(&wb_allocation[off], page_size/4, 0);
+ }
+
+ /* Verify that only zswapped memory from wb_group has been written back */
+ zswpwb_target = wait_for_writeback(wb_group, 5000);
+ zswpwb_after = get_cg_wb_count(zw_group);
+
+ if (zswpwb_target > 0 && zswpwb_before == zswpwb_after)
ret = KSFT_PASS;
+
out:
cg_enter_current(root);
- if (control_group) {
- cg_destroy(control_group);
- free(control_group);
+ if (zw_group) {
+ cg_destroy(zw_group);
+ free(zw_group);
+ }
+ if (wb_group) {
+ cg_destroy(wb_group);
+ free(wb_group);
}
- cg_destroy(wb_group);
- free(wb_group);
- if (control_allocation)
- free(control_allocation);
+ if (zw_allocation)
+ free(zw_allocation);
+ if (wb_allocation)
+ free(wb_allocation);
return ret;
}
@@ -471,7 +559,7 @@ static int no_kmem_bypass_child(const char *cgroup, void *arg)
values->child_allocated = true;
return -1;
}
- for (long i = 0; i < values->target_alloc_bytes; i += 4095)
+ for (long i = 0; i < values->target_alloc_bytes; i += page_size)
((char *)allocation)[i] = 'a';
values->child_allocated = true;
pause();
@@ -507,8 +595,16 @@ static int test_no_kmem_bypass(const char *root)
/* Read sys info and compute test values accordingly */
if (sysinfo(&sys_info) != 0)
return KSFT_FAIL;
- if (sys_info.totalram > 5000000000)
+ if (sys_info.totalram > GB(4)) {
+ ksft_print_msg(
+ "requires less than 4GB total ram, sys_info.totalram: %.1fGB\n",
+ (double)sys_info.totalram / GB(1));
return KSFT_SKIP;
+ }
+ if (access(PATH_ZSWAP_STORED_PAGES, R_OK)) {
+ ksft_print_msg("debugfs not mounted at /sys/kernel/debug\n");
+ return KSFT_SKIP;
+ }
values = mmap(0, sizeof(struct no_kmem_bypass_child_args), PROT_READ |
PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0);
if (values == MAP_FAILED)
@@ -519,7 +615,7 @@ static int test_no_kmem_bypass(const char *root)
min_free_kb_low = sys_info.totalram / 500000;
values->target_alloc_bytes = (sys_info.totalram - min_free_kb_high * 1000) +
sys_info.totalram * 5 / 100;
- stored_pages_threshold = sys_info.totalram / 5 / 4096;
+ stored_pages_threshold = sys_info.totalram / 5 / page_size;
trigger_allocation_size = sys_info.totalram / 20;
/* Set up test memcg */
@@ -546,7 +642,7 @@ static int test_no_kmem_bypass(const char *root)
if (!trigger_allocation)
break;
- for (int i = 0; i < trigger_allocation_size; i += 4095)
+ for (int i = 0; i < trigger_allocation_size; i += page_size)
trigger_allocation[i] = 'b';
usleep(100000);
free(trigger_allocation);
@@ -557,8 +653,8 @@ static int test_no_kmem_bypass(const char *root)
/* If memory was pushed to zswap, verify it belongs to memcg */
if (stored_pages > stored_pages_threshold) {
int zswapped = cg_read_key_long(test_group, "memory.stat", "zswapped ");
- int delta = stored_pages * 4096 - zswapped;
- int result_ok = delta < stored_pages * 4096 / 4;
+ int delta = stored_pages * page_size - zswapped;
+ int result_ok = delta < stored_pages * page_size / 4;
ret = result_ok ? KSFT_PASS : KSFT_FAIL;
break;
@@ -574,6 +670,139 @@ out:
return ret;
}
+struct incomp_child_args {
+ size_t size;
+ int pipefd[2];
+ int madvise_ret;
+ int madvise_errno;
+};
+
+static int allocate_random_and_wait(const char *cgroup, void *arg)
+{
+ struct incomp_child_args *values = arg;
+ size_t size = values->size;
+ char *mem;
+ int fd;
+ ssize_t n;
+
+ close(values->pipefd[0]);
+
+ mem = mmap(NULL, size, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ if (mem == MAP_FAILED)
+ return -1;
+
+ /* Fill with random data from /dev/urandom - incompressible */
+ fd = open("/dev/urandom", O_RDONLY);
+ if (fd < 0) {
+ munmap(mem, size);
+ return -1;
+ }
+
+ for (size_t i = 0; i < size; ) {
+ n = read(fd, mem + i, size - i);
+ if (n <= 0)
+ break;
+ i += n;
+ }
+ close(fd);
+
+ /* Touch all pages to ensure they're faulted in */
+ for (size_t i = 0; i < size; i += page_size)
+ mem[i] = mem[i];
+
+ /* Use MADV_PAGEOUT to push pages into zswap */
+ values->madvise_ret = madvise(mem, size, MADV_PAGEOUT);
+ values->madvise_errno = errno;
+
+ /* Notify parent that allocation and pageout are done */
+ write(values->pipefd[1], "x", 1);
+ close(values->pipefd[1]);
+
+ /* Keep memory alive for parent to check stats */
+ pause();
+ munmap(mem, size);
+ return 0;
+}
+
+static long get_zswap_incomp(const char *cgroup)
+{
+ return cg_read_key_long(cgroup, "memory.stat", "zswap_incomp ");
+}
+
+/*
+ * Test that incompressible pages (random data) are tracked by zswap_incomp.
+ *
+ * The child process allocates random data within memory.max, then uses
+ * MADV_PAGEOUT to push pages into zswap. The parent waits on a pipe for
+ * the child to finish, then checks the zswap_incomp stat before the child
+ * exits (zswap_incomp is a gauge that decreases on free).
+ */
+static int test_zswap_incompressible(const char *root)
+{
+ int ret = KSFT_FAIL;
+ struct incomp_child_args *values;
+ char *test_group;
+ long zswap_incomp;
+ pid_t child_pid;
+ int child_status;
+ char buf;
+
+ values = mmap(0, sizeof(struct incomp_child_args), PROT_READ |
+ PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+ if (values == MAP_FAILED)
+ return KSFT_FAIL;
+
+ if (pipe(values->pipefd)) {
+ munmap(values, sizeof(struct incomp_child_args));
+ return KSFT_FAIL;
+ }
+
+ test_group = cg_name(root, "zswap_incompressible_test");
+ if (!test_group)
+ goto out;
+ if (cg_create(test_group))
+ goto out;
+ if (cg_write(test_group, "memory.max", "32M"))
+ goto out;
+
+ values->size = MB(4);
+ child_pid = cg_run_nowait(test_group, allocate_random_and_wait, values);
+ if (child_pid < 0)
+ goto out;
+
+ close(values->pipefd[1]);
+
+ /* Wait for child to finish allocating and pageout */
+ read(values->pipefd[0], &buf, 1);
+ close(values->pipefd[0]);
+
+ zswap_incomp = get_zswap_incomp(test_group);
+ if (zswap_incomp <= 0) {
+ long zswpout = get_zswpout(test_group);
+ long zswapped = cg_read_key_long(test_group, "memory.stat", "zswapped ");
+ long zswap_b = cg_read_key_long(test_group, "memory.stat", "zswap ");
+
+ ksft_print_msg("zswap_incomp not increased: %ld\n", zswap_incomp);
+ ksft_print_msg("debug: zswpout=%ld zswapped=%ld zswap_b=%ld\n",
+ zswpout, zswapped, zswap_b);
+ ksft_print_msg("debug: madvise ret=%d errno=%d\n",
+ values->madvise_ret, values->madvise_errno);
+ goto out_kill;
+ }
+
+ ret = KSFT_PASS;
+
+out_kill:
+ kill(child_pid, SIGTERM);
+ waitpid(child_pid, &child_status, 0);
+out:
+ cg_destroy(test_group);
+ free(test_group);
+ munmap(values, sizeof(struct incomp_child_args));
+ return ret;
+}
+
#define T(x) { x, #x }
struct zswap_test {
int (*fn)(const char *root);
@@ -586,12 +815,22 @@ struct zswap_test {
T(test_zswap_writeback_disabled),
T(test_no_kmem_bypass),
T(test_no_invasive_cgroup_shrink),
+ T(test_zswap_incompressible),
};
#undef T
-static bool zswap_configured(void)
+static void check_zswap_enabled(void)
{
- return access("/sys/module/zswap", F_OK) == 0;
+ char value[2];
+
+ if (access(PATH_ZSWAP, F_OK))
+ ksft_exit_skip("zswap isn't configured\n");
+
+ if (read_text(PATH_ZSWAP_ENABLED, value, sizeof(value)) <= 0)
+ ksft_exit_fail_msg("Failed to read " PATH_ZSWAP_ENABLED "\n");
+
+ if (value[0] == 'N')
+ ksft_exit_skip("zswap is disabled (hint: echo 1 > " PATH_ZSWAP_ENABLED ")\n");
}
int main(int argc, char **argv)
@@ -599,13 +838,15 @@ int main(int argc, char **argv)
char root[PATH_MAX];
int i;
+ page_size = sysconf(_SC_PAGE_SIZE);
+ if (page_size <= 0)
+ page_size = BUF_SIZE;
+
ksft_print_header();
- ksft_set_plan(ARRAY_SIZE(tests));
if (cg_find_unified_root(root, sizeof(root), NULL))
ksft_exit_skip("cgroup v2 isn't mounted\n");
- if (!zswap_configured())
- ksft_exit_skip("zswap isn't configured\n");
+ check_zswap_enabled();
/*
* Check that memory controller is available:
@@ -618,6 +859,7 @@ int main(int argc, char **argv)
if (cg_write(root, "cgroup.subtree_control", "+memory"))
ksft_exit_skip("Failed to set memory controller\n");
+ ksft_set_plan(ARRAY_SIZE(tests));
for (i = 0; i < ARRAY_SIZE(tests); i++) {
switch (tests[i].fn(root)) {
case KSFT_PASS:
generated by cgit v1.2.3 (git 2.0.4) at 2026-09-28 00:38:26 +0000