Merge tag 'cgroup-for-6.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - The locking around cpuset hotplug processing has always been a bit of
   mess which was worked around by making hotplug processing
   asynchronous. The asynchronity isn't great and led to other issues.

   We tried to make the behavior synchronous a while ago but that led to
   lockdep splats. Waiman took another stab at cleaning up and making it
   synchronous. The patch has been in -next for well over a month and
   there haven't been any complaints, so fingers crossed.

 - Tracepoints added to help understanding rstat lock contentions.

 - A bunch of minor changes - doc updates, code cleanups and selftests.

* tag 'cgroup-for-6.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (24 commits)
  cgroup/rstat: add cgroup_rstat_cpu_lock helpers and tracepoints
  selftests/cgroup: Drop define _GNU_SOURCE
  docs: cgroup-v1: Update page cache removal functions
  selftests/cgroup: fix uninitialized variables in test_zswap.c
  selftests/cgroup: cpu_hogger init: use {} instead of {NULL}
  selftests/cgroup: fix clang warnings: uninitialized fd variable
  selftests/cgroup: fix clang build failures for abs() calls
  cgroup/cpuset: Remove outdated comment in sched_partition_write()
  cgroup/cpuset: Fix incorrect top_cpuset flags
  cgroup/cpuset: Avoid clearing CS_SCHED_LOAD_BALANCE twice
  cgroup/cpuset: Statically initialize more members of top_cpuset
  cgroup: Avoid unnecessary looping in cgroup_no_v1()
  cgroup, legacy_freezer: update comment for freezer_css_offline()
  docs, cgroup: add entries for pids to cgroup-v2.rst
  cgroup: don't call cgroup1_pidlist_destroy_all() for v2
  cgroup_freezer: update comment for freezer_css_online()
  cgroup/rstat: desc member cgrp in cgroup_rstat_flush_release
  cgroup/rstat: add cgroup_rstat_lock helpers and tracepoints
  cgroup/pids: Remove superfluous zeroing
  docs: cgroup-v1: Fix description for css_online
  ...

13 files changed, 77 insertions, 37 deletions

diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile
index 00b441928909..16461dc0ffdf 100644
--- a/tools/testing/selftests/cgroup/Makefile
+++ b/tools/testing/selftests/cgroup/Makefile
@@ -4,7 +4,7 @@ CFLAGS += -Wall -pthread
 all: ${HELPER_PROGS}
 
 TEST_FILES     := with_stress.sh
-TEST_PROGS     := test_stress.sh test_cpuset_prs.sh
+TEST_PROGS     := test_stress.sh test_cpuset_prs.sh test_cpuset_v1_hp.sh
 TEST_GEN_FILES := wait_inotify
 TEST_GEN_PROGS = test_memcontrol
 TEST_GEN_PROGS += test_kmem
diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c
index 0340d4ca8f51..ce16a50ecff8 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/cgroup_util.c
@@ -1,7 +1,4 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-
-#define _GNU_SOURCE
-
 #include <errno.h>
 #include <fcntl.h>
 #include <linux/limits.h>
@@ -195,10 +192,10 @@ int cg_write_numeric(const char *cgroup, const char *control, long value)
 	return cg_write(cgroup, control, buf);
 }
 
-int cg_find_unified_root(char *root, size_t len)
+int cg_find_unified_root(char *root, size_t len, bool *nsdelegate)
 {
 	char buf[10 * PAGE_SIZE];
-	char *fs, *mount, *type;
+	char *fs, *mount, *type, *options;
 	const char delim[] = "\n\t ";
 
 	if (read_text("/proc/self/mounts", buf, sizeof(buf)) <= 0)
@@ -211,12 +208,14 @@ int cg_find_unified_root(char *root, size_t len)
 	for (fs = strtok(buf, delim); fs; fs = strtok(NULL, delim)) {
 		mount = strtok(NULL, delim);
 		type = strtok(NULL, delim);
-		strtok(NULL, delim);
+		options = strtok(NULL, delim);
 		strtok(NULL, delim);
 		strtok(NULL, delim);
 
 		if (strcmp(type, "cgroup2") == 0) {
 			strncpy(root, mount, len);
+			if (nsdelegate)
+				*nsdelegate = !!strstr(options, "nsdelegate");
 			return 0;
 		}
 	}
diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h
index 1df7f202214a..e8d04ac9e3d2 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.h
+++ b/tools/testing/selftests/cgroup/cgroup_util.h
@@ -18,10 +18,10 @@
  */
 static inline int values_close(long a, long b, int err)
 {
-	return abs(a - b) <= (a + b) / 100 * err;
+	return labs(a - b) <= (a + b) / 100 * err;
 }
 
-extern int cg_find_unified_root(char *root, size_t len);
+extern int cg_find_unified_root(char *root, size_t len, bool *nsdelegate);
 extern char *cg_name(const char *root, const char *name);
 extern char *cg_name_indexed(const char *root, const char *name, int index);
 extern char *cg_control(const char *cgroup, const char *control);
diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c
index 80aa6b2373b9..de8baad46022 100644
--- a/tools/testing/selftests/cgroup/test_core.c
+++ b/tools/testing/selftests/cgroup/test_core.c
@@ -1,6 +1,4 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-
-#define _GNU_SOURCE
 #include <linux/limits.h>
 #include <linux/sched.h>
 #include <sys/types.h>
@@ -18,6 +16,8 @@
 #include "../kselftest.h"
 #include "cgroup_util.h"
 
+static bool nsdelegate;
+
 static int touch_anon(char *buf, size_t size)
 {
 	int fd;
@@ -775,6 +775,9 @@ static int test_cgcore_lesser_ns_open(const char *root)
 	pid_t pid;
 	int status;
 
+	if (!nsdelegate)
+		return KSFT_SKIP;
+
 	cg_test_a = cg_name(root, "cg_test_a");
 	cg_test_b = cg_name(root, "cg_test_b");
 
@@ -862,7 +865,7 @@ int main(int argc, char *argv[])
 	char root[PATH_MAX];
 	int i, ret = EXIT_SUCCESS;
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	if (cg_find_unified_root(root, sizeof(root), &nsdelegate))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
 	if (cg_read_strstr(root, "cgroup.subtree_control", "memory"))
diff --git a/tools/testing/selftests/cgroup/test_cpu.c b/tools/testing/selftests/cgroup/test_cpu.c
index 24020a2c68dc..5a4a314f6af7 100644
--- a/tools/testing/selftests/cgroup/test_cpu.c
+++ b/tools/testing/selftests/cgroup/test_cpu.c
@@ -1,6 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0
-
-#define _GNU_SOURCE
 #include <linux/limits.h>
 #include <sys/sysinfo.h>
 #include <sys/wait.h>
@@ -237,7 +235,7 @@ run_cpucg_weight_test(
 {
 	int ret = KSFT_FAIL, i;
 	char *parent = NULL;
-	struct cpu_hogger children[3] = {NULL};
+	struct cpu_hogger children[3] = {};
 
 	parent = cg_name(root, "cpucg_test_0");
 	if (!parent)
@@ -408,7 +406,7 @@ run_cpucg_nested_weight_test(const char *root, bool overprovisioned)
 {
 	int ret = KSFT_FAIL, i;
 	char *parent = NULL, *child = NULL;
-	struct cpu_hogger leaf[3] = {NULL};
+	struct cpu_hogger leaf[3] = {};
 	long nested_leaf_usage, child_usage;
 	int nprocs = get_nprocs();
 
@@ -700,7 +698,7 @@ int main(int argc, char *argv[])
 	char root[PATH_MAX];
 	int i, ret = EXIT_SUCCESS;
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
 	if (cg_read_strstr(root, "cgroup.subtree_control", "cpu"))
diff --git a/tools/testing/selftests/cgroup/test_cpuset.c b/tools/testing/selftests/cgroup/test_cpuset.c
index b061ed1e05b4..4034d14ba69a 100644
--- a/tools/testing/selftests/cgroup/test_cpuset.c
+++ b/tools/testing/selftests/cgroup/test_cpuset.c
@@ -249,7 +249,7 @@ int main(int argc, char *argv[])
 	char root[PATH_MAX];
 	int i, ret = EXIT_SUCCESS;
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
 	if (cg_read_strstr(root, "cgroup.subtree_control", "cpuset"))
diff --git a/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh b/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh
new file mode 100755
index 000000000000..3f45512fb512
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh
@@ -0,0 +1,46 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test the special cpuset v1 hotplug case where a cpuset become empty of
+# CPUs will force migration of tasks out to an ancestor.
+#
+
+skip_test() {
+	echo "$1"
+	echo "Test SKIPPED"
+	exit 4 # ksft_skip
+}
+
+[[ $(id -u) -eq 0 ]] || skip_test "Test must be run as root!"
+
+# Find cpuset v1 mount point
+CPUSET=$(mount -t cgroup | grep cpuset | head -1 | awk -e '{print $3}')
+[[ -n "$CPUSET" ]] || skip_test "cpuset v1 mount point not found!"
+
+#
+# Create a test cpuset, put a CPU and a task there and offline that CPU
+#
+TDIR=test$$
+[[ -d $CPUSET/$TDIR ]] || mkdir $CPUSET/$TDIR
+echo 1 > $CPUSET/$TDIR/cpuset.cpus
+echo 0 > $CPUSET/$TDIR/cpuset.mems
+sleep 10&
+TASK=$!
+echo $TASK > $CPUSET/$TDIR/tasks
+NEWCS=$(cat /proc/$TASK/cpuset)
+[[ $NEWCS != "/$TDIR" ]] && {
+	echo "Unexpected cpuset $NEWCS, test FAILED!"
+	exit 1
+}
+
+echo 0 > /sys/devices/system/cpu/cpu1/online
+sleep 0.5
+echo 1 > /sys/devices/system/cpu/cpu1/online
+NEWCS=$(cat /proc/$TASK/cpuset)
+rmdir $CPUSET/$TDIR
+[[ $NEWCS != "/" ]] && {
+	echo "cpuset $NEWCS, test FAILED!"
+	exit 1
+}
+echo "Test PASSED"
+exit 0
diff --git a/tools/testing/selftests/cgroup/test_freezer.c b/tools/testing/selftests/cgroup/test_freezer.c
index 8845353aca53..8730645d363a 100644
--- a/tools/testing/selftests/cgroup/test_freezer.c
+++ b/tools/testing/selftests/cgroup/test_freezer.c
@@ -827,7 +827,7 @@ int main(int argc, char *argv[])
 	char root[PATH_MAX];
 	int i, ret = EXIT_SUCCESS;
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		switch (tests[i].fn(root)) {
diff --git a/tools/testing/selftests/cgroup/test_hugetlb_memcg.c b/tools/testing/selftests/cgroup/test_hugetlb_memcg.c
index f0fefeb4cc24..80d05d50a42d 100644
--- a/tools/testing/selftests/cgroup/test_hugetlb_memcg.c
+++ b/tools/testing/selftests/cgroup/test_hugetlb_memcg.c
@@ -1,6 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0
-#define _GNU_SOURCE
-
 #include <linux/limits.h>
 #include <sys/mman.h>
 #include <stdio.h>
@@ -214,7 +212,7 @@ int main(int argc, char **argv)
 		return ret;
 	}
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
 	switch (test_hugetlb_memcg(root)) {
diff --git a/tools/testing/selftests/cgroup/test_kill.c b/tools/testing/selftests/cgroup/test_kill.c
index 6153690319c9..0e5bb6c7307a 100644
--- a/tools/testing/selftests/cgroup/test_kill.c
+++ b/tools/testing/selftests/cgroup/test_kill.c
@@ -276,7 +276,7 @@ int main(int argc, char *argv[])
 	char root[PATH_MAX];
 	int i, ret = EXIT_SUCCESS;
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		switch (tests[i].fn(root)) {
diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c
index c82f974b85c9..2e453ac50c0d 100644
--- a/tools/testing/selftests/cgroup/test_kmem.c
+++ b/tools/testing/selftests/cgroup/test_kmem.c
@@ -1,6 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0
-#define _GNU_SOURCE
-
 #include <linux/limits.h>
 #include <fcntl.h>
 #include <stdio.h>
@@ -192,7 +190,7 @@ static int test_kmem_memcg_deletion(const char *root)
 		goto cleanup;
 
 	sum = anon + file + kernel + sock;
-	if (abs(sum - current) < MAX_VMSTAT_ERROR) {
+	if (labs(sum - current) < MAX_VMSTAT_ERROR) {
 		ret = KSFT_PASS;
 	} else {
 		printf("memory.current = %ld\n", current);
@@ -380,7 +378,7 @@ static int test_percpu_basic(const char *root)
 	current = cg_read_long(parent, "memory.current");
 	percpu = cg_read_key_long(parent, "memory.stat", "percpu ");
 
-	if (current > 0 && percpu > 0 && abs(current - percpu) <
+	if (current > 0 && percpu > 0 && labs(current - percpu) <
 	    MAX_VMSTAT_ERROR)
 		ret = KSFT_PASS;
 	else
@@ -420,7 +418,7 @@ int main(int argc, char **argv)
 	char root[PATH_MAX];
 	int i, ret = EXIT_SUCCESS;
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
 	/*
diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c
index c7c9572003a8..c871630d62a3 100644
--- a/tools/testing/selftests/cgroup/test_memcontrol.c
+++ b/tools/testing/selftests/cgroup/test_memcontrol.c
@@ -1,6 +1,4 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#define _GNU_SOURCE
-
 #include <linux/limits.h>
 #include <linux/oom.h>
 #include <fcntl.h>
@@ -716,7 +714,9 @@ static bool reclaim_until(const char *memcg, long goal)
  */
 static int test_memcg_reclaim(const char *root)
 {
-	int ret = KSFT_FAIL, fd, retries;
+	int ret = KSFT_FAIL;
+	int fd = -1;
+	int retries;
 	char *memcg;
 	long current, expected_usage;
 
@@ -1314,7 +1314,7 @@ int main(int argc, char **argv)
 	char root[PATH_MAX];
 	int i, proc_status, ret = EXIT_SUCCESS;
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
 	/*
diff --git a/tools/testing/selftests/cgroup/test_zswap.c b/tools/testing/selftests/cgroup/test_zswap.c
index f0e488ed90d8..8418a8d7439f 100644
--- a/tools/testing/selftests/cgroup/test_zswap.c
+++ b/tools/testing/selftests/cgroup/test_zswap.c
@@ -1,6 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0
-#define _GNU_SOURCE
-
 #include <linux/limits.h>
 #include <unistd.h>
 #include <stdio.h>
@@ -257,7 +255,7 @@ static int test_no_invasive_cgroup_shrink(const char *root)
 {
 	int ret = KSFT_FAIL;
 	size_t control_allocation_size = MB(10);
-	char *control_allocation, *wb_group = NULL, *control_group = NULL;
+	char *control_allocation = NULL, *wb_group = NULL, *control_group = NULL;
 
 	wb_group = setup_test_group_1M(root, "per_memcg_wb_test1");
 	if (!wb_group)
@@ -342,7 +340,7 @@ static int test_no_kmem_bypass(const char *root)
 	struct sysinfo sys_info;
 	int ret = KSFT_FAIL;
 	int child_status;
-	char *test_group;
+	char *test_group = NULL;
 	pid_t child_pid;
 
 	/* Read sys info and compute test values accordingly */
@@ -440,7 +438,7 @@ int main(int argc, char **argv)
 	char root[PATH_MAX];
 	int i, ret = EXIT_SUCCESS;
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
 	if (!zswap_configured())