From: Joel Fernandes <joelagnelf@nvidia.com>
To: linux-kernel@vger.kernel.org, RCU <rcu@vger.kernel.org>,
"Paul E . McKenney" <paulmck@kernel.org>
Subject: Re: [PATCH v1 6/6] scftorture: Make invoker threads actually wait for all threads to start
Date: Sat, 18 Jul 2026 13:17:46 -0400 [thread overview]
Message-ID: <79343d8d-230b-4562-b0e0-bd797e11727f@nvidia.com> (raw)
In-Reply-To: <20260718171539.3781595-7-joelagnelf@nvidia.com>
Some reason my scripting missed rcu list for these last 2 patches. But they
are on the lkml list :) sorry.
Adding back rcu@.
On 7/18/2026 1:15 PM, Joel Fernandes wrote:
> Each scftorture_invoker() thread decrements n_started, which is
> initialized to the number of threads, and is then supposed to wait
> until all of its siblings have also checked in before starting the
> test proper. However, the wait loop is guarded by
> !atomic_dec_return(&n_started), which is true only for the final
> thread to arrive, and by then n_started is already zero, so the
> final thread does not wait either. The side-effect (possibly positive)
> is that no thread ever waits and the start-synchronization barrier is
> dead code, with early threads beginning to hammer smp_call_function*()
> while later threads are still being spawned.
>
> Invert the test so that every thread other than the last spins until
> n_started reaches zero, making the threads start testing together as
> intended. The existing torture_must_stop() check in the wait loop
> continues to bound the wait during shutdown.
>
> We can also drop the spinning entirely if the intent is to leave it as
> dead code, however for the current intent, this patches fixes the code.
>
> Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
> ---
> kernel/scftorture.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/kernel/scftorture.c b/kernel/scftorture.c
> index ffd6c83732ee..392df1b4d4ed 100644
> --- a/kernel/scftorture.c
> +++ b/kernel/scftorture.c
> @@ -497,7 +497,7 @@ static int scftorture_invoker(void *arg)
> "%s: Wanted CPU %d, running on %d, nr_cpu_ids = %d\n",
> __func__, scfp->cpu, curcpu, nr_cpu_ids);
>
> - if (!atomic_dec_return(&n_started))
> + if (atomic_dec_return(&n_started))
> while (atomic_read_acquire(&n_started)) {
> if (torture_must_stop()) {
> VERBOSE_SCFTORTOUT("scftorture_invoker %d ended before starting", scfp->cpu);
next prev parent reply other threads:[~2026-07-18 17:17 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-07-18 17:15 [PATCH v1 0/6] RCU and torture fixes and cleanups Joel Fernandes
2026-07-18 17:15 ` [PATCH v1 1/6] rcu: Remove unused expedited_need_qs field from rcu_state Joel Fernandes
2026-07-18 17:15 ` [PATCH v1 2/6] rcu: Remove unused rdp parameter from trace_rcu_this_gp() Joel Fernandes
2026-07-18 17:15 ` [PATCH v1 3/6] rcu: Remove unused func parameter from callback-enqueue functions Joel Fernandes
2026-07-18 17:15 ` [PATCH v1 4/6] torture: Don't leak shuffle_tmp_mask when shuffler kthread fails to start Joel Fernandes
2026-07-18 17:15 ` [PATCH v1 5/6] scftorture: Count single_rpc offline failures in statistics output Joel Fernandes
2026-07-18 17:17 ` Joel Fernandes
2026-07-18 17:15 ` [PATCH v1 6/6] scftorture: Make invoker threads actually wait for all threads to start Joel Fernandes
2026-07-18 17:17 ` Joel Fernandes [this message]
2026-07-20 15:52 ` [PATCH v1 0/6] RCU and torture fixes and cleanups Paul E. McKenney
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=79343d8d-230b-4562-b0e0-bd797e11727f@nvidia.com \
--to=joelagnelf@nvidia.com \
--cc=linux-kernel@vger.kernel.org \
--cc=paulmck@kernel.org \
--cc=rcu@vger.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
all inboxes | Powered by JetHome®