Merge branch 'for-next' of https://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git

6 files changed, 300 insertions, 13 deletions

diff --git a/tools/testing/selftests/cgroup/lib/include/cgroup_util.h b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
index febc1723d090..8ebb2b4d4ec0 100644
--- a/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
+++ b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
@@ -8,6 +8,7 @@
 
 #define MB(x) (x << 20)
 
+#define NSEC_PER_USEC	1000L
 #define USEC_PER_SEC	1000000L
 #define NSEC_PER_SEC	1000000000L
 
diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c
index 88ca832d4fc1..8e3f9b391e44 100644
--- a/tools/testing/selftests/cgroup/test_core.c
+++ b/tools/testing/selftests/cgroup/test_core.c
@@ -427,7 +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)
diff --git a/tools/testing/selftests/cgroup/test_cpu.c b/tools/testing/selftests/cgroup/test_cpu.c
index 7a40d76b9548..a5eccfcabef5 100644
--- a/tools/testing/selftests/cgroup/test_cpu.c
+++ b/tools/testing/selftests/cgroup/test_cpu.c
@@ -640,21 +640,49 @@ 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 +698,8 @@ 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 +738,18 @@ 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 +772,8 @@ 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,
 	};
diff --git a/tools/testing/selftests/cgroup/test_cpuset.c b/tools/testing/selftests/cgroup/test_cpuset.c
index c5cf8b56ceb8..8c2d4d4ef1fc 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
 
diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
index 0d41aa0d343d..ca9bc38fdb95 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
@@ -495,13 +495,20 @@ REMOTE_TEST_MATRIX=(
 	# 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 \
+	      .      .     .       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 \
+	      .      .     P0      C2-3    .       .     p1:1,4|c11:1|c12:2-3 \
 							 p1:P1|c11:P0|c12:P2 2-3"
+	# 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"
 )
 
 #
diff --git a/tools/testing/selftests/cgroup/test_hugetlb_memcg.c b/tools/testing/selftests/cgroup/test_hugetlb_memcg.c
index b627d84358b1..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)
@@ -211,7 +214,7 @@ 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))
@@ -233,10 +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();
 }