The Linux Kernel Mailing List
 help / color / mirror / Atom feed
From: sashiko-bot@kernel.org
To: "Mathieu Desnoyers" <mathieu.desnoyers@efficios.com>
Cc: linux-rt-devel@lists.linux.dev, tj@kernel.org,
	hannes@cmpxchg.org, mkoutny@suse.com,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH v8 05/33] selftests/sched: Test SCHED_DEADLINE bandwidth across a root domain rebuild
Date: Thu, 19 Nov 2026 20:28:50 +0000	[thread overview]
Message-ID: <sashiko-outbox-224022@kernel.org> (raw)
In-Reply-To: <2c85e2efab1ae7eb89b6d6e334c933348486c542.1795116790.git.mathieu.desnoyers@efficios.com>

Thank you for your contribution! Sashiko AI review found 4 potential
issues to consider:
- [Medium] selftests/sched: missing isolated/sparse CPU handling and
  code duplication
- [Low] selftests/sched: missing 0-lag wait on early exit in
  test_rebuild()
- [Low] selftests/sched: undersized path buffer in make_partition()
- [Low] selftests/sched: missing PR_SET_PDEATHSIG in departing() and
  sleeper()
--

commit 61b9ca4442ef766ed51f3c6ad77a1ac959261741
Author: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>

selftests/sched: Test SCHED_DEADLINE bandwidth across a root domain rebuild

This commit adds the deadline_rebuild_test selftest to verify that
SCHED_DEADLINE bandwidth of tasks that exit or leave the policy before
their 0-lag time is preserved across cpuset partition root domain
rebuilds.

> diff --git a/tools/testing/selftests/sched/deadline/deadline_rebuild_test.c b/tools/testing/selftests/sched/deadline/deadline_rebuild_test.c
> new file mode 100644
> index 0000000000000..714a0ff03f1b9
> --- /dev/null
> +++ b/tools/testing/selftests/sched/deadline/deadline_rebuild_test.c
> @@ -0,0 +1,497 @@

[ ... ]

> +/* Make @cg a partition root of CPU @cpu alone. Return 0, or -1 on error. */
> +static int make_partition(const char *cg, int cpu)
> +{
> +	char path[PATH_MAX], buf[32];
> +
> +	if (mkdir(cg, 0755) && errno != EEXIST)
> +		return -1;
> +	snprintf(buf, sizeof(buf), "%d", cpu);
> +	if (write_file(cg, "cpuset.cpus", buf) || write_file(cg, "cpuset.cpus.partition", "root"))
> +		return -1;
> +	snprintf(path, sizeof(path), "%s/cpuset.cpus.partition", cg);
> +	if (read_file(path, buf, sizeof(buf)) || strcmp(buf, "root\n"))
> +		return -1;
> +	return 0;
> +}

[Severity: Low]
Can snprintf() truncate path[] here and trigger a -Wformat-truncation
warning when make_partition() is inlined with cg_p or cg_q (which are
sized PATH_MAX)?  Sizing path[] to PATH_MAX + 32, as main() does for
cgroup.subtree_control, avoids the truncation warning.

[ ... ]

> +static pid_t departing(const char *cg, enum depart how, int fd[2])
> +{
> +	pid_t pid = fork();
> +
> +	if (pid < 0)
> +		ksft_print_msg("fork: %s\n", strerror(errno));
> +	if (!pid) {
> +		uint64_t t0;
> +
> +		close(fd[0]);
> +		if (cg && enter(cg, getpid()))
> +			_exit(2);
> +		if (set_deadline(0, 400 * NSEC_PER_MSEC))
> +			_exit(3);
> +		t0 = cpu_time_ns();
> +		while (cpu_time_ns() - t0 < 380 * NSEC_PER_MSEC)
> +			;
> +		if (how == DIES)
> +			_exit(0);
> +		if (set_other(0) || write(fd[1], "x", 1) != 1)
> +			_exit(4);
> +		for (;;)
> +			pause();
> +	}

[ ... ]

> +static pid_t sleeper(const char *cg)
> +{
> +	int fd[2];
> +	pid_t pid;
> +	char c;
> +
> +	if (pipe(fd))
> +		return -1;
> +	pid = fork();
> +	if (pid < 0)
> +		ksft_print_msg("fork: %s\n", strerror(errno));
> +	if (!pid) {
> +		close(fd[0]);
> +		if (enter(cg, getpid()) || write(fd[1], "x", 1) != 1)
> +			_exit(1);
> +		for (;;)
> +			pause();
> +	}

[Severity: Low]
If the test runner is killed by a signal or kselftest timeout while
children from departing() or sleeper() are alive, will those children stay
blocked in pause() inside cg_p holding SCHED_DEADLINE bandwidth and
preventing cg_p from being removed?  Using a fork_child() helper with
prctl(PR_SET_PDEATHSIG, SIGKILL), like deadline_switch_test.c and
deadline_bw_test.c do, ensures children exit with the test.

[ ... ]

> +static int test_rebuild(enum depart how)
> +{
> +	int ret = KSFT_FAIL, fd[2], err;
> +	pid_t pid = -1;
> +
> +	if (pipe(fd))
> +		return KSFT_FAIL;
> +	if (make_partition(cg_p, ncpus - 1)) {
> +		ksft_print_msg("no partition root on CPU %d\n", ncpus - 1);
> +		ret = KSFT_SKIP;
> +		goto out;
> +	}
> +	pid = departing(cg_p, how, fd);
> +	err = departed(&pid, how, fd[0]);
> +	if (err) {
> +		ksft_print_msg("the deadline task failed (%d)\n", err);
> +		goto out;
> +	}
> +	if (make_partition(cg_q, ncpus - 2)) {
> +		ksft_print_msg("no partition root on CPU %d\n", ncpus - 2);
> +		ret = KSFT_SKIP;
> +		goto out;
> +	}
> +	/*
> +	 * Wait past the 0-lag time. In the SWITCHED_OUT case the task is still
> +	 * alive then: it sleeps in P as a SCHED_OTHER task.
> +	 */
> +	sleep_ns(1500 * NSEC_PER_MSEC);
> +	ret = check_p();
> +out:
> +	reap(pid);
> +	remove_partition(cg_q);
> +	remove_partition(cg_p);
> +	close(fd[0]);
> +	if (fd[1] >= 0)
> +		close(fd[1]);
> +	return ret;
> +}
> +
> +/*
> + * Have a task outside P switch to SCHED_OTHER and sleep. Before its 0-lag
> + * time, move it into P and kill it. Then check P.
> + */
> +static int test_move(void)
> +{
> +	int ret = KSFT_FAIL, fd[2], err;
> +	pid_t pid = -1;
> +
> +	if (pipe(fd))
> +		return KSFT_FAIL;
> +	if (make_partition(cg_p, ncpus - 1)) {
> +		ksft_print_msg("no partition root on CPU %d\n", ncpus - 1);
> +		ret = KSFT_SKIP;
> +		goto out;
> +	}
> +	pid = departing(NULL, SWITCHED_OUT, fd);
> +	err = departed(&pid, SWITCHED_OUT, fd[0]);
> +	if (err) {
> +		ksft_print_msg("the deadline task failed (%d)\n", err);
> +		goto out;
> +	}
> +	if (enter(cg_p, pid)) {
> +		ksft_print_msg("the task cannot move into P\n");
> +		goto out;
> +	}

[Severity: Low]
If make_partition(cg_q, ncpus - 2) in test_rebuild() or enter(cg_p, pid)
in test_move() fails after departed() has succeeded, does jumping directly
to out skip waiting for the departed task's 0-lag inactive timer?  The
next test case in main() would then start while the 400ms/1000ms bandwidth
is still pending removal from the root domain.

[ ... ]

> +int main(void)
> +{
> +	char buf[256], path[PATH_MAX + 32];
> +	int added;
> +
> +	ksft_print_header();
> +	if (geteuid())
> +		ksft_exit_skip("needs root\n");
> +	ncpus = get_nprocs();
> +	if (ncpus < 3)
> +		ksft_exit_skip("needs 3 CPUs\n");

[Severity: Medium]
Can picking CPUs ncpus - 1 and ncpus - 2 from get_nprocs() fail when
online CPU numbering has gaps or when isolcpus=domain is configured?

Unlike deadline_bw_test.c, which reads /sys/devices/system/cpu/online and
/sys/devices/system/cpu/isolated, picks online non-isolated CPUs, and
restricts task affinity away from isolated CPUs, this test assumes online
CPUs are contiguously numbered 0..ncpus-1 and none are isolated.  When
isolcpus=domain is used (which deadline_bw_test.c requires for many of its
cases), ncpus - 1 or ncpus - 2 can be isolated or offline, and in
test_move() the child spawned by departing(NULL, SWITCHED_OUT, fd)
inherits root-cgroup affinity that includes isolated CPUs, causing
set_deadline() to fail.

Since roughly half of this file duplicates the cgroup v2, partition, and
SCHED_DEADLINE helpers from deadline_bw_test.c in the same directory,
could these helpers be shared (or these three cases folded into
deadline_bw_test.c) so online and isolated CPUs are handled consistently?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/cover.1795116790.git.mathieu.desnoyers@efficios.com?part=5

  reply	other threads:[~2026-11-19 20:28 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-19 20:15 [PATCH v8 00/33] sched/deadline: bandwidth accounting fixes and selftests Mathieu Desnoyers
2026-11-19 20:15 ` [PATCH v8 01/33] sched/deadline: Keep departing bandwidth across a root domain rebuild Mathieu Desnoyers
2026-11-19 20:15 ` [PATCH v8 02/33] sched/deadline: Rebuild the root domains' accounting from the task list Mathieu Desnoyers
2026-11-19 20:15 ` [PATCH v8 03/33] sched/deadline: Record the root domain holding a task's bandwidth Mathieu Desnoyers
2026-11-19 20:51   ` sashiko-bot
2026-11-19 20:15 ` [PATCH v8 04/33] sched/deadline: Leave a dying task out of a rebuild of the accounting Mathieu Desnoyers
2026-11-19 20:15 ` [PATCH v8 05/33] selftests/sched: Test SCHED_DEADLINE bandwidth across a root domain rebuild Mathieu Desnoyers
2026-11-19 20:28   ` sashiko-bot [this message]
2026-11-19 20:15 ` [PATCH v8 06/33] selftests/sched: Test the root domain rebuild in deadline_bw_test Mathieu Desnoyers
2026-11-19 20:15 ` [PATCH v8 07/33] sched/deadline: Move a task's bandwidth only where room was made Mathieu Desnoyers
2026-11-19 20:15 ` [PATCH v8 08/33] cgroup/cpuset: Wait for an attach before rebuilding the sched domains Mathieu Desnoyers
2026-11-19 20:15 ` [PATCH v8 09/33] sched: Make deadline policy and affinity changes wait for a cpuset attach Mathieu Desnoyers
2026-11-19 20:15 ` [PATCH v8 10/33] cgroup/cpuset: Give back the bandwidth an attach did not move Mathieu Desnoyers
2026-11-19 20:15 ` [PATCH v8 11/33] cgroup/cpuset: Reserve the bandwidth in the root domain a task moves to Mathieu Desnoyers
2026-11-19 20:15 ` [PATCH v8 12/33] selftests/sched: Test cpuset moves in deadline_bw_test Mathieu Desnoyers
2026-11-19 20:15 ` [PATCH v8 13/33] sched/deadline: Make a rebuild count a task in the root domain it runs in Mathieu Desnoyers
2026-11-19 20:15 ` [PATCH v8 14/33] sched/deadline: Move a task's bandwidth to " Mathieu Desnoyers
2026-11-19 20:53   ` sashiko-bot
2026-11-19 20:15 ` [PATCH v8 15/33] sched/deadline: Keep a task in the root domain that counts its bandwidth Mathieu Desnoyers
2026-11-19 20:55   ` sashiko-bot
2026-11-19 20:15 ` [PATCH v8 16/33] sched/deadline: Keep the last CPU a task has in its root domain Mathieu Desnoyers
2026-11-19 20:22   ` Mathieu Desnoyers
2026-11-19 20:48   ` sashiko-bot
2026-11-19 20:15 ` [PATCH v8 17/33] cgroup/cpuset: Refuse to take a deadline task out of " Mathieu Desnoyers
2026-11-19 20:43   ` sashiko-bot
2026-11-19 20:15 ` [PATCH v8 18/33] selftests/sched: Test the root domain of a task in deadline_bw_test Mathieu Desnoyers
2026-11-19 20:27   ` sashiko-bot
2026-11-19 20:15 ` [PATCH v8 19/33] sched/deadline: Count only active CPUs when spreading extra_bw Mathieu Desnoyers
2026-11-19 20:15 ` [PATCH v8 20/33] rtmutex: Continue the chain walk when a waiter's deadline donor changes Mathieu Desnoyers
2026-11-19 20:16 ` [PATCH v8 21/33] rtmutex: Continue the walk when the owner's top waiter changes lock Mathieu Desnoyers
2026-11-19 20:16 ` [PATCH v8 22/33] selftests/sched: Test the rtmutex chain walk in deadline_bw_test Mathieu Desnoyers
2026-11-19 20:16 ` [PATCH v8 23/33] sched/deadline: Reset the donor's runtime at a deboost in the class Mathieu Desnoyers
2026-11-19 20:53   ` sashiko-bot
2026-11-19 20:16 ` [PATCH v8 24/33] sched/deadline: Replenish a throttled task boosted while asleep Mathieu Desnoyers
2026-11-19 20:16 ` [PATCH v8 25/33] sched/deadline: Count the bandwidth a boosted task is given Mathieu Desnoyers
2026-11-19 20:16 ` [PATCH v8 26/33] sched/deadline: Start a period for a task that enters the class blocked Mathieu Desnoyers
2026-11-19 20:57   ` sashiko-bot
2026-11-19 20:16 ` [PATCH v8 27/33] sched/deadline: Start a period at a deboost out of the class Mathieu Desnoyers
2026-11-19 20:47   ` sashiko-bot
2026-11-19 20:16 ` [PATCH v8 28/33] selftests/sched: Test deadline boosts in deadline_bw_test Mathieu Desnoyers
2026-11-19 20:16 ` [PATCH v8 29/33] sched/deadline: Cancel the replenishment timer with the parameters Mathieu Desnoyers
2026-11-19 20:16 ` [PATCH v8 30/33] sched/deadline: Cap the runtime left of a constrained task at dl_runtime Mathieu Desnoyers
2026-11-19 20:16 ` [PATCH v8 31/33] sched/deadline: Check the runtime of a task that comes back runnable Mathieu Desnoyers
2026-11-19 20:16 ` [PATCH v8 32/33] sched/deadline: Check the runtime of a task whose parameters change Mathieu Desnoyers
2026-11-19 20:59   ` sashiko-bot
2026-11-19 20:16 ` [PATCH v8 33/33] selftests/sched: Test parameter changes in deadline_bw_test Mathieu Desnoyers

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=sashiko-outbox-224022@kernel.org \
    --to=sashiko-bot@kernel.org \
    --cc=hannes@cmpxchg.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rt-devel@lists.linux.dev \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=mkoutny@suse.com \
    --cc=sashiko-reviews@lists.linux.dev \
    --cc=tj@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox