+ selftests-acct-add-taskstats-tgid-retention-test.patch added to mm-nonmm-unstable branch

[Andrew Morton <akpm@linux-foundation.org>]

The patch titled
     Subject: selftests/acct: add taskstats TGID retention test
has been added to the -mm mm-nonmm-unstable branch.  Its filename is
     selftests-acct-add-taskstats-tgid-retention-test.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/selftests-acct-add-taskstats-tgid-retention-test.patch

This patch will later appear in the mm-nonmm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via various
branches at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there most days

------------------------------------------------------
From: Yiyang Chen <cyyzero16@gmail.com>
Subject: selftests/acct: add taskstats TGID retention test
Date: Mon, 13 Apr 2026 23:45:45 +0800

Add a kselftest for the taskstats TGID aggregation fix.

The test creates a worker thread, snapshots TGID taskstats while the
worker is still alive, lets the worker exit, and then verifies that the
TGID CPU total does not regress after the thread has been reaped.

The pass/fail check intentionally keys off ac_utime + ac_stime only, which
is the primary user-visible regression fixed by the taskstats change and
is less sensitive to scheduling noise than context-switch counters.

Link: https://lore.kernel.org/0d55354911c54cd1b9f10a09f6fd378af85c8d43.1776094300.git.cyyzero16@gmail.com
Signed-off-by: Yiyang Chen <cyyzero16@gmail.com>
Acked-by: Balbir Singh <balbirs@nvidia.com>
Cc: Dr. Thomas Orgis <thomas.orgis@uni-hamburg.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Wang Yaxin <wang.yaxin@zte.com.cn>
Cc: Yang Yang <yang.yang29@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 tools/testing/selftests/acct/.gitignore                  |    3 
 tools/testing/selftests/acct/Makefile                    |    5 
 tools/testing/selftests/acct/taskstats_fill_stats_tgid.c |  375 ++++++++++
 3 files changed, 381 insertions(+), 2 deletions(-)

--- a/tools/testing/selftests/acct/.gitignore~selftests-acct-add-taskstats-tgid-retention-test
+++ a/tools/testing/selftests/acct/.gitignore
@@ -1,3 +1,4 @@
 acct_syscall
+taskstats_fill_stats_tgid
 config
-process_log
\ No newline at end of file
+process_log
--- a/tools/testing/selftests/acct/Makefile~selftests-acct-add-taskstats-tgid-retention-test
+++ a/tools/testing/selftests/acct/Makefile
@@ -1,5 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 TEST_GEN_PROGS := acct_syscall
+TEST_GEN_PROGS += taskstats_fill_stats_tgid
+
 CFLAGS += -Wall
+LDLIBS += -lpthread
 
-include ../lib.mk
\ No newline at end of file
+include ../lib.mk
diff --git a/tools/testing/selftests/acct/taskstats_fill_stats_tgid.c a/tools/testing/selftests/acct/taskstats_fill_stats_tgid.c
new file mode 100644
--- /dev/null
+++ a/tools/testing/selftests/acct/taskstats_fill_stats_tgid.c
@@ -0,0 +1,375 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <linux/genetlink.h>
+#include <linux/netlink.h>
+#include <linux/taskstats.h>
+#include <pthread.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <time.h>
+#include <unistd.h>
+
+#include "kselftest.h"
+
+#ifndef NLA_ALIGN
+#define NLA_ALIGNTO 4
+#define NLA_ALIGN(len) (((len) + NLA_ALIGNTO - 1) & ~(NLA_ALIGNTO - 1))
+#define NLA_HDRLEN ((int)NLA_ALIGN(sizeof(struct nlattr)))
+#endif
+
+#define BUSY_NS (200ULL * 1000 * 1000)
+
+struct worker_ctx {
+	pthread_mutex_t lock;
+	pthread_cond_t cond;
+	bool ready;
+	bool release;
+};
+
+static unsigned long busy_sink;
+
+static void *taskstats_nla_data(const struct nlattr *na)
+{
+	return (void *)((char *)na + NLA_HDRLEN);
+}
+
+static bool taskstats_nla_ok(const struct nlattr *na, int remaining)
+{
+	return remaining >= (int)sizeof(*na) &&
+	       na->nla_len >= sizeof(*na) &&
+	       na->nla_len <= remaining;
+}
+
+static struct nlattr *taskstats_nla_next(const struct nlattr *na, int *remaining)
+{
+	int aligned_len = NLA_ALIGN(na->nla_len);
+
+	*remaining -= aligned_len;
+	return (struct nlattr *)((char *)na + aligned_len);
+}
+
+static uint64_t timespec_diff_ns(const struct timespec *start,
+				 const struct timespec *end)
+{
+	return (uint64_t)(end->tv_sec - start->tv_sec) * 1000000000ULL +
+	       (uint64_t)(end->tv_nsec - start->tv_nsec);
+}
+
+static void burn_cpu_for_ns(uint64_t runtime_ns)
+{
+	struct timespec start, now;
+	unsigned long acc = 0;
+
+	if (clock_gettime(CLOCK_MONOTONIC, &start)) {
+		perror("clock_gettime");
+		exit(EXIT_FAILURE);
+	}
+
+	do {
+		for (int i = 0; i < 100000; i++)
+			acc += i;
+		if (clock_gettime(CLOCK_MONOTONIC, &now)) {
+			perror("clock_gettime");
+			exit(EXIT_FAILURE);
+		}
+	} while (timespec_diff_ns(&start, &now) < runtime_ns);
+
+	busy_sink = acc;
+}
+
+static int netlink_open(void)
+{
+	struct sockaddr_nl addr = {
+		.nl_family = AF_NETLINK,
+		.nl_pid = getpid(),
+	};
+	int fd;
+
+	fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC);
+	if (fd < 0)
+		return -errno;
+
+	if (bind(fd, (struct sockaddr *)&addr, sizeof(addr)) < 0) {
+		int err = -errno;
+
+		close(fd);
+		return err;
+	}
+
+	return fd;
+}
+
+static int send_request(int fd, void *buf, size_t len)
+{
+	struct sockaddr_nl addr = {
+		.nl_family = AF_NETLINK,
+	};
+
+	if (sendto(fd, buf, len, 0, (struct sockaddr *)&addr, sizeof(addr)) < 0)
+		return -errno;
+
+	return 0;
+}
+
+static int get_family_id(int fd, const char *name)
+{
+	struct {
+		struct nlmsghdr nlh;
+		struct genlmsghdr genl;
+		char buf[256];
+	} req = { 0 };
+	char resp[8192];
+	struct nlmsghdr *nlh;
+	struct genlmsghdr *genl;
+	struct nlattr *na;
+	int len;
+	int rem;
+	int ret;
+
+	req.nlh.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN);
+	req.nlh.nlmsg_type = GENL_ID_CTRL;
+	req.nlh.nlmsg_flags = NLM_F_REQUEST;
+	req.nlh.nlmsg_seq = 1;
+	req.nlh.nlmsg_pid = getpid();
+
+	req.genl.cmd = CTRL_CMD_GETFAMILY;
+	req.genl.version = 1;
+
+	na = (struct nlattr *)((char *)&req + NLMSG_ALIGN(req.nlh.nlmsg_len));
+	na->nla_type = CTRL_ATTR_FAMILY_NAME;
+	na->nla_len = NLA_HDRLEN + strlen(name) + 1;
+	memcpy(taskstats_nla_data(na), name, strlen(name) + 1);
+	req.nlh.nlmsg_len = NLMSG_ALIGN(req.nlh.nlmsg_len) + NLA_ALIGN(na->nla_len);
+
+	ret = send_request(fd, &req, req.nlh.nlmsg_len);
+	if (ret)
+		return ret;
+
+	len = recv(fd, resp, sizeof(resp), 0);
+	if (len < 0)
+		return -errno;
+
+	for (nlh = (struct nlmsghdr *)resp; NLMSG_OK(nlh, len);
+	     nlh = NLMSG_NEXT(nlh, len)) {
+		if (nlh->nlmsg_type == NLMSG_ERROR) {
+			struct nlmsgerr *err = NLMSG_DATA(nlh);
+
+			return err->error ? err->error : -ENOENT;
+		}
+
+		genl = (struct genlmsghdr *)NLMSG_DATA(nlh);
+		rem = nlh->nlmsg_len - NLMSG_HDRLEN - GENL_HDRLEN;
+		na = (struct nlattr *)((char *)genl + GENL_HDRLEN);
+		while (taskstats_nla_ok(na, rem)) {
+			if (na->nla_type == CTRL_ATTR_FAMILY_ID)
+				return *(uint16_t *)taskstats_nla_data(na);
+			na = taskstats_nla_next(na, &rem);
+		}
+	}
+
+	return -ENOENT;
+}
+
+static int get_taskstats(int fd, int family_id, uint16_t attr_type, uint32_t id,
+			 struct taskstats *stats)
+{
+	struct {
+		struct nlmsghdr nlh;
+		struct genlmsghdr genl;
+		char buf[256];
+	} req = { 0 };
+	char resp[16384];
+	struct nlmsghdr *nlh;
+	struct genlmsghdr *genl;
+	struct nlattr *na;
+	struct nlattr *nested;
+	int len;
+	int rem;
+	int nrem;
+	int ret;
+
+	memset(stats, 0, sizeof(*stats));
+
+	req.nlh.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN);
+	req.nlh.nlmsg_type = family_id;
+	req.nlh.nlmsg_flags = NLM_F_REQUEST;
+	req.nlh.nlmsg_seq = 2;
+	req.nlh.nlmsg_pid = getpid();
+
+	req.genl.cmd = TASKSTATS_CMD_GET;
+	req.genl.version = 1;
+
+	na = (struct nlattr *)((char *)&req + NLMSG_ALIGN(req.nlh.nlmsg_len));
+	na->nla_type = attr_type;
+	na->nla_len = NLA_HDRLEN + sizeof(id);
+	memcpy(taskstats_nla_data(na), &id, sizeof(id));
+	req.nlh.nlmsg_len = NLMSG_ALIGN(req.nlh.nlmsg_len) + NLA_ALIGN(na->nla_len);
+
+	ret = send_request(fd, &req, req.nlh.nlmsg_len);
+	if (ret)
+		return ret;
+
+	len = recv(fd, resp, sizeof(resp), 0);
+	if (len < 0)
+		return -errno;
+
+	for (nlh = (struct nlmsghdr *)resp; NLMSG_OK(nlh, len);
+	     nlh = NLMSG_NEXT(nlh, len)) {
+		if (nlh->nlmsg_type == NLMSG_ERROR) {
+			struct nlmsgerr *err = NLMSG_DATA(nlh);
+
+			return err->error ? err->error : -ENOENT;
+		}
+
+		genl = (struct genlmsghdr *)NLMSG_DATA(nlh);
+		rem = nlh->nlmsg_len - NLMSG_HDRLEN - GENL_HDRLEN;
+		na = (struct nlattr *)((char *)genl + GENL_HDRLEN);
+		while (taskstats_nla_ok(na, rem)) {
+			if (na->nla_type == TASKSTATS_TYPE_AGGR_PID ||
+			    na->nla_type == TASKSTATS_TYPE_AGGR_TGID) {
+				nested = (struct nlattr *)taskstats_nla_data(na);
+				nrem = na->nla_len - NLA_HDRLEN;
+				while (taskstats_nla_ok(nested, nrem)) {
+					if (nested->nla_type == TASKSTATS_TYPE_STATS) {
+						memcpy(stats, taskstats_nla_data(nested),
+						       sizeof(*stats));
+						return 0;
+					}
+					nested = taskstats_nla_next(nested, &nrem);
+				}
+			}
+			na = taskstats_nla_next(na, &rem);
+		}
+	}
+
+	return -ENOENT;
+}
+
+static uint64_t cpu_total(const struct taskstats *stats)
+{
+	return (uint64_t)stats->ac_utime + (uint64_t)stats->ac_stime;
+}
+
+static void print_stats(const char *label, const struct taskstats *stats)
+{
+	ksft_print_msg("%s: cpu_total=%llu nvcsw=%llu nivcsw=%llu\n",
+		       label, (unsigned long long)cpu_total(stats),
+		       (unsigned long long)stats->nvcsw,
+		       (unsigned long long)stats->nivcsw);
+}
+
+static void *worker_thread(void *arg)
+{
+	struct worker_ctx *ctx = arg;
+
+	burn_cpu_for_ns(BUSY_NS);
+
+	pthread_mutex_lock(&ctx->lock);
+	ctx->ready = true;
+	pthread_cond_broadcast(&ctx->cond);
+	while (!ctx->release)
+		pthread_cond_wait(&ctx->cond, &ctx->lock);
+	pthread_mutex_unlock(&ctx->lock);
+
+	return NULL;
+}
+
+int main(void)
+{
+	struct worker_ctx ctx = {
+		.lock = PTHREAD_MUTEX_INITIALIZER,
+		.cond = PTHREAD_COND_INITIALIZER,
+	};
+	struct taskstats before, after;
+	pthread_t thread;
+	pid_t tgid = getpid();
+	int family_id;
+	int fd;
+	int ret;
+
+	ksft_print_header();
+	ksft_set_plan(1);
+
+	if (geteuid())
+		ksft_exit_skip("taskstats_fill_stats_tgid needs root\n");
+
+	fd = netlink_open();
+	if (fd < 0)
+		ksft_exit_skip("failed to open generic netlink socket: %s\n",
+			       strerror(-fd));
+
+	family_id = get_family_id(fd, TASKSTATS_GENL_NAME);
+	if (family_id < 0)
+		ksft_exit_skip("taskstats generic netlink family unavailable: %s\n",
+			       strerror(-family_id));
+
+	/* Create worker thread that burns 200ms of CPU */
+	if (pthread_create(&thread, NULL, worker_thread, &ctx) != 0)
+		ksft_exit_fail_msg("pthread_create failed: %s\n", strerror(errno));
+
+	/* Wait for worker to finish generating activity */
+	pthread_mutex_lock(&ctx.lock);
+	while (!ctx.ready)
+		pthread_cond_wait(&ctx.cond, &ctx.lock);
+	pthread_mutex_unlock(&ctx.lock);
+
+	/*
+	 * Snapshot A: TGID stats while worker is alive and sleeping.
+	 * Contains main thread + worker contributions.
+	 */
+	ret = get_taskstats(fd, family_id, TASKSTATS_CMD_ATTR_TGID, tgid, &before);
+	if (ret)
+		ksft_exit_fail_msg("TGID query before exit failed: %s\n",
+				   strerror(-ret));
+
+	/* Release worker so it can exit, then join (deterministic wait).
+	 *
+	 * Kernel exit path ordering guarantees:
+	 *   do_exit()
+	 *     taskstats_exit() -> fill_tgid_exit()  (accumulates worker into signal->stats)
+	 *     exit_notify()                         (releases the thread)
+	 *     do_task_dead() -> __schedule()        (wakes joiner)
+	 *
+	 * So pthread_join() returns only after fill_tgid_exit() has completed.
+	 */
+	pthread_mutex_lock(&ctx.lock);
+	ctx.release = true;
+	pthread_cond_broadcast(&ctx.cond);
+	pthread_mutex_unlock(&ctx.lock);
+
+	pthread_join(thread, NULL);
+
+	/*
+	 * Snapshot B: TGID stats after worker has exited.
+	 * fill_stats_for_tgid() does:
+	 *   memcpy(signal->stats)   <- includes fill_tgid_exit accumulation
+	 *   + scan live threads      <- only main thread now
+	 */
+	ret = get_taskstats(fd, family_id, TASKSTATS_CMD_ATTR_TGID, tgid, &after);
+	if (ret)
+		ksft_exit_fail_msg("TGID query after exit failed: %s\n",
+				   strerror(-ret));
+
+	print_stats("TGID before worker exit", &before);
+	print_stats("TGID after  worker exit", &after);
+
+	/*
+	 * The worker burned 200ms of CPU before the first snapshot.
+	 * If the kernel correctly retained its contribution via
+	 * fill_tgid_exit(), then the TGID CPU total after exit must be at
+	 * least as large as the TGID CPU total before exit.
+	 */
+	ksft_test_result(cpu_total(&after) >= cpu_total(&before),
+			 "TGID CPU stats should not regress after thread exit\n");
+
+	close(fd);
+	ksft_finished();
+	return ksft_get_fail_cnt() ? KSFT_FAIL : KSFT_PASS;
+}
_

Patches currently in -mm which might be from cyyzero16@gmail.com are

tools-accounting-getdelays-fix-wformat-truncation-warning-in-format_timespec.patch
taskstats-retain-dead-thread-stats-in-tgid-queries.patch
selftests-acct-add-taskstats-tgid-retention-test.patch