cgroup: Fixes for v7.3-rc1

- After cgroup.kill was written to a cgroup, every child cloned into it
   with CLONE_INTO_CGROUP was spuriously killed because the fork path
   snapshotted the kill counter before resolving the target cgroup.
 
 - Releasing an isolated cpuset partition dropped the isolation of CPUs
   isolated on the kernel command line.
 
 - Selftest and documentation fixes.
 -----BEGIN PGP SIGNATURE-----
 
 iIQEABYKACwWIQTfIjM1kS57o3GsC/uxYfJx3gVYGQUCapXm8w4cdGpAa2VybmVs
 Lm9yZwAKCRCxYfJx3gVYGbhtAQCfUc4oanF94uiAGzH2UAA2HIorLT4TDjuDj/oM
 qrqeLQEA1p2XQz56SYXhK8fG+fy+Ep3xxqS2gStmtYL20ie4lQc=
 =i4QU
 -----END PGP SIGNATURE-----

Merge tag 'cgroup-for-7.3-rc1-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup fixes from Tejun Heo:

 - After cgroup.kill was written to a cgroup, every child cloned into it
   with CLONE_INTO_CGROUP was spuriously killed because the fork path
   snapshotted the kill counter before resolving the target cgroup

 - Releasing an isolated cpuset partition dropped the isolation of CPUs
   isolated on the kernel command line

 - Selftest and documentation fixes

* tag 'cgroup-for-7.3-rc1-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  selftests/cgroup: test clone3() into a previously killed cgroup
  cgroup: fix spurious SIGKILL of CLONE_INTO_CGROUP children
  selftests/cgroup: Add test for preserving boot-isolated CPUs
  cgroup/cpuset: Preserve boot-isolated CPUs on partition release
  selftests/cgroup: Drop invalid boot isolation comparison
  docs: cgroup-v2: fix misc.events key format description
  selftests/cgroup: Fix cg_run_in_subcgroups ignoring arg parameter
  selftests/cgroup: set the test plan after the setup checks

Documentation/admin-guide/cgroup-v2.rst

@@ -3070,7 +3070,7 @@ resources (res_a and res_b) are registered then:
 	change in this file generates a file modified event. All fields in
 	this file are hierarchical.
 
-	  max
+	  <res>.max
 		The number of times the cgroup's resource usage was
 		about to go over the max boundary.
 

include/linux/cgroup-defs.h

@@ -527,7 +527,10 @@ struct cgroup {
 
 	int nr_threaded_children;	/* # of live threaded child cgroups */
 
-	/* sequence number for cgroup.kill, serialized by css_set_lock. */
+	/*
+	 * Sequence number for cgroup.kill. Incremented with both cgroup_mutex
+	 * and css_set_lock held. Readers hold either one.
+	 */
 	unsigned int kill_seq;
 
 	struct kernfs_node *kn;		/* cgroup kernfs entry */

kernel/cgroup/cgroup.c

@@ -6873,10 +6873,7 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs)
 	spin_lock_irq(&css_set_lock);
 	cset = task_css_set(current);
 	get_css_set(cset);
-	if (kargs->cgrp)
-		kargs->kill_seq = kargs->cgrp->kill_seq;
-	else
-		kargs->kill_seq = cset->dfl_cgrp->kill_seq;
+	kargs->kill_seq = cset->dfl_cgrp->kill_seq;
 	spin_unlock_irq(&css_set_lock);
 
 	if (!(kargs->flags & CLONE_INTO_CGROUP)) {
@@ -6940,6 +6937,7 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs)
 
 	put_css_set(cset);
 	kargs->cgrp = dst_cgrp;
+	kargs->kill_seq = dst_cgrp->kill_seq;
 	return ret;
 
 err:

kernel/cgroup/cpuset.c

@@ -1259,6 +1259,28 @@ static void reset_partition_data(struct cpuset *cs)
 		cpumask_copy(cs->effective_cpus, parent->effective_cpus);
 }
 
+/* Return true if isolated_cpus changes. */
+static bool isolated_cpu_update(int new_prs, int cpu)
+{
+	lockdep_assert_held(&callback_lock);
+	lockdep_assert_held(&cpuset_mutex);
+
+	if (new_prs == PRS_ISOLATED) {
+		if (cpumask_test_cpu(cpu, isolated_cpus))
+			return false;
+		cpumask_set_cpu(cpu, isolated_cpus);
+		return true;
+	}
+
+	/* CPUs isolated at boot must remain isolated. */
+	if (!cpumask_test_cpu(cpu,
+			      housekeeping_cpumask(HK_TYPE_DOMAIN_BOOT)) ||
+	    !cpumask_test_cpu(cpu, isolated_cpus))
+		return false;
+	cpumask_clear_cpu(cpu, isolated_cpus);
+	return true;
+}
+
 /*
  * isolated_cpus_update - Update the isolated_cpus mask
  * @old_prs: old partition_root_state
@@ -1267,19 +1289,16 @@ static void reset_partition_data(struct cpuset *cs)
  */
 static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus)
 {
+	bool updated = false;
+	int cpu;
+
 	WARN_ON_ONCE(old_prs == new_prs);
 	lockdep_assert_held(&callback_lock);
 	lockdep_assert_held(&cpuset_mutex);
-	if (new_prs == PRS_ISOLATED) {
-		if (cpumask_subset(xcpus, isolated_cpus))
-			return;
-		cpumask_or(isolated_cpus, isolated_cpus, xcpus);
-	} else {
-		if (!cpumask_intersects(xcpus, isolated_cpus))
-			return;
-		cpumask_andnot(isolated_cpus, isolated_cpus, xcpus);
-	}
-	update_housekeeping = true;
+	for_each_cpu(cpu, xcpus)
+		updated |= isolated_cpu_update(new_prs, cpu);
+	if (updated)
+		update_housekeeping = true;
 }
 
 /*

tools/testing/selftests/cgroup/test_core.c

@@ -919,7 +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");
@@ -932,6 +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:

tools/testing/selftests/cgroup/test_cpu.c

@@ -832,7 +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");
 
@@ -840,6 +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:

tools/testing/selftests/cgroup/test_cpuset.c

@@ -497,7 +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");
 
@@ -505,6 +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:

tools/testing/selftests/cgroup/test_cpuset_prs.sh

@@ -797,7 +797,6 @@ check_isolcpus()
 	EXPECTED_ISOLCPUS=$1
 	ISCPUS=${CGROUP2}/cpuset.cpus.isolated
 	ISOLCPUS=$(cat $ISCPUS)
-	HKICPUS=$(cat /sys/devices/system/cpu/isolated)
 	LASTISOLCPU=
 	SCHED_DOMAINS=/sys/kernel/debug/sched/domains
 	if [[ $EXPECTED_ISOLCPUS = . ]]
@@ -835,11 +834,6 @@ check_isolcpus()
 	ISOLCPUS=
 	EXPECTED_ISOLCPUS=$EXPECTED_SDOMAIN
 
-	#
-	# The inverse of HK_TYPE_DOMAIN cpumask in $HKICPUS should match $ISOLCPUS
-	#
-	[[ "$ISOLCPUS" != "$HKICPUS" ]] && return 1
-
 	#
 	# Use the sched domain in debugfs to check isolated CPUs, if available
 	#
@@ -1161,6 +1155,63 @@ test_isolated()
 	pause 0.05
 }
 
+#
+# 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
@@ -1232,5 +1283,6 @@ 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."

tools/testing/selftests/cgroup/test_freezer.c

@@ -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:

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"
@@ -261,6 +262,59 @@ static int test_cgkill_forkbomb(const char *root)
 	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);
@@ -269,6 +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
 
@@ -278,9 +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:

tools/testing/selftests/cgroup/test_kmem.c

@@ -145,7 +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;
@@ -426,7 +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");
 
@@ -441,6 +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:

tools/testing/selftests/cgroup/test_memcontrol.c

@@ -1798,7 +1798,6 @@ int main(int argc, char **argv)
 		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");
 
@@ -1823,6 +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:

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:

tools/testing/selftests/cgroup/test_zswap.c

@@ -819,7 +819,6 @@ int main(int argc, char **argv)
 		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");
 
@@ -836,6 +835,7 @@ 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: