mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Shrikanth Hegde <sshegde@linux.ibm.com>
To: Yury Norov <ynorov@nvidia.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>, Thomas Gleixner <tglx@kernel.org>,
	Juri Lelli <juri.lelli@redhat.com>,
	Vincent Guittot <vincent.guittot@linaro.org>
Cc: Yury Norov <yury.norov@gmail.com>,
	"Rafael J. Wysocki" <rafael@kernel.org>,
	Alexander Gordeev <agordeev@linux.ibm.com>,
	Andrea Righi <arighi@nvidia.com>, Ben Segall <bsegall@google.com>,
	Christian Borntraeger <borntraeger@linux.ibm.com>,
	Danilo Krummrich <dakr@kernel.org>,
	Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	Heiko Carstens <hca@linux.ibm.com>,
	Ilya Leoshkevich <iii@linux.ibm.com>,
	Johan Hovold <johan@kernel.org>, Jonathan Corbet <corbet@lwn.net>,
	K Prateek Nayak <kprateek.nayak@amd.com>,
	Maxim Kuvyrkov <maxim.kuvyrkov@grdncc.com>,
	Mel Gorman <mgorman@suse.de>, Mete Durlu <meted@linux.ibm.com>,
	Randy Dunlap <rdunlap@infradead.org>,
	Rasmus Villemoes <linux@rasmusvillemoes.dk>,
	Shuah Khan <skhan@linuxfoundation.org>,
	Steven Rostedt <rostedt@goodmis.org>,
	Sven Schnelle <svens@linux.ibm.com>,
	Valentin Schneider <vschneid@redhat.com>,
	Vasily Gorbik <gor@linux.ibm.com>,
	linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org,
	driver-core@lists.linux.dev, linux-s390@vger.kernel.org
Subject: Re: [PATCH 4/7] virt: steal_governor: serialize sampling against CPU hotplug
Date: Thu, 19 Nov 2026 11:52:19 +0530	[thread overview]
Message-ID: <1556d3b0-1c89-4d3d-b9e5-5921c5c9158b@linux.ibm.com> (raw)
In-Reply-To: <20261113184257.621707-5-ynorov@nvidia.com>



On 11/14/26 12:12 AM, Yury Norov wrote:
> Steal governor is not safe against a concurrent CPU hotplug operation
> because it can change active and preferred cpumasks during the governor
> sampling.
> 
> To address the race, the governor would take the cpus_write_lock(). But
> that may be impractical for the loadable module.
> 
> Instead, implement the following locking policy:
> 
>   - if the code takes cpus_write_lock(), it's enough to write-access
>     the preferred cpumask;
>   - if the code takes cpus_read_lock(), it must also take
>     cpu_preferred_mutex in order to modify the preferred mask.
> 
> The core scheduler and hotplug paths already modify the preferred cpumask
> under the cpus_write_lock(), so no change in core logic is required.
> 
> This provides a common update protocol for multiple policy drivers
> without requiring writers to take the broader CPU hotplug write lock.
> 

This is also necessary if there are multiple writers outside of core hotplug No?
So should it go with the write interface series?

> Fixes: 27d47ebce4d6 ("virt/steal_governor: Implement steal_governor policy loop")
> Signed-off-by: Yury Norov <ynorov@nvidia.com>
> ---
>   drivers/virt/steal_governor.c | 17 +++++++++++++----
>   include/linux/cpumask.h       | 11 ++++++++++-
>   lib/cpumask.c                 |  5 +++++
>   3 files changed, 28 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/virt/steal_governor.c b/drivers/virt/steal_governor.c
> index 26b6bcca27ed..8cd5c0f3e3ef 100644
> --- a/drivers/virt/steal_governor.c
> +++ b/drivers/virt/steal_governor.c
> @@ -23,6 +23,7 @@
>   #include <linux/ktime.h>
>   #include <linux/math64.h>
>   #include <linux/module.h>
> +#include <linux/mutex.h>
>   #include <linux/sched/isolation.h>
>   #include <linux/topology.h>
>   #include <linux/types.h>
> @@ -139,7 +140,8 @@ static void decrease_preferred_cpus(void)
>   	int target_cpu = nr_cpu_ids;
>   	int cpu;
>   
> -	guard(cpus_read_lock)();
> +	lockdep_assert_cpus_held();
> +	lockdep_assert_held(&cpu_preferred_mutex);
>   	cpu = cpumask_first_and(housekeeping_cpumask(HK_TYPE_KERNEL_NOISE),
>   				cpu_preferred_mask);
>   	if (cpu >= nr_cpu_ids)
> @@ -179,7 +181,8 @@ static void increase_preferred_cpus(void)
>   {
>   	int first_cpu, cpu;
>   
> -	guard(cpus_read_lock)();
> +	lockdep_assert_cpus_held();
> +	lockdep_assert_held(&cpu_preferred_mutex);
>   	first_cpu = cpumask_first_andnot(cpu_active_mask, cpu_preferred_mask);
>   
>   	/* All CPUs are preferred. Nothing to increase further */
> @@ -193,6 +196,9 @@ static void increase_preferred_cpus(void)
>   
>   static bool preferred_cpus_valid(void)
>   {
> +	lockdep_assert_cpus_held();
> +	lockdep_assert_held(&cpu_preferred_mutex);
> +
>   	if (cpumask_empty(cpu_preferred_mask)) {
>   		pr_err("empty preferred mask. stopping\n");
>   		return false;
> @@ -213,6 +219,9 @@ static void steal_governor_loop(struct work_struct *work)
>   	u64 curr_steal, delta_steal, delta_ns, steal_ratio;
>   	ktime_t now;
>   
> +	guard(cpus_read_lock)();
> +	guard(mutex)(&cpu_preferred_mutex);
> +
>   	now = ktime_get();
>   	delta_ns = ktime_to_ns(ktime_sub(now, sg_ctx.time));
>   
> @@ -238,8 +247,6 @@ static void steal_governor_loop(struct work_struct *work)
>   	 * module restores to active if CPU hotplug breaks those assumptions.
>   	 */
>   	if (!preferred_cpus_valid()) {
> -		guard(cpus_read_lock)();
> -
>   		reset_preferred_cpumask();
>   		return;
>   	}
> @@ -276,6 +283,8 @@ static void __exit steal_governor_exit(void)
>   {
>   	disable_delayed_work_sync(&sg_ctx.work);
>   	guard(cpus_read_lock)();
> +	guard(mutex)(&cpu_preferred_mutex);
> +
>   	reset_preferred_cpumask();
>   	pr_info("disabled\n");
>   }
> diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
> index b13d099474bc..3716213d0730 100644
> --- a/include/linux/cpumask.h
> +++ b/include/linux/cpumask.h
> @@ -124,6 +124,14 @@ extern struct cpumask __cpu_dying_mask;
>   
>   #ifdef CONFIG_PREFERRED_CPU
>   extern struct cpumask __cpu_preferred_mask;
> +
> +/*
> + * Drivers must take cpus_read_lock(), then cpu_preferred_mutex and
> + * hold both across mask validation and updates. If cpus_write_lock()
> + * is held, it guarantees the exclusive access to the mask, thus
> + * holding cpu_preferred_mutex isn't necessary.
> + */
> +extern struct mutex cpu_preferred_mutex;
>   #else
>   #define __cpu_preferred_mask __cpu_active_mask
>   #endif
> @@ -1199,7 +1207,8 @@ void init_cpu_possible(const struct cpumask *src);
>    * reset_preferred_cpumask - reset preferred CPUs to the active mask.
>    *
>    * Callers must serialize against CPU hotplug and other preferred cpumask
> - * writers.
> + * writers. Requires cpus_read_lock() and cpu_preferred_mutex; or
> + * cpus_write_lock().
>    */
>   static inline void reset_preferred_cpumask(void)
>   {
> diff --git a/lib/cpumask.c b/lib/cpumask.c
> index 5adb9874fbd0..2e16e19a2bdb 100644
> --- a/lib/cpumask.c
> +++ b/lib/cpumask.c
> @@ -166,3 +166,8 @@ unsigned int cpumask_any_distribute(const struct cpumask *srcp)
>   	return next;
>   }
>   EXPORT_SYMBOL(cpumask_any_distribute);
> +
> +#ifdef CONFIG_PREFERRED_CPU
> +DEFINE_MUTEX(cpu_preferred_mutex);
> +EXPORT_SYMBOL_GPL(cpu_preferred_mutex);
> +#endif


  reply	other threads:[~2026-11-19  6:23 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-13 18:42 [PATCH 0/7] Harden preferred CPUs management Yury Norov
2026-11-13 18:42 ` [PATCH 1/7] cpumask: add reset_preferred_cpumask() helper Yury Norov
2026-11-13 18:42 ` [PATCH 2/7] sched: restore preferred CPUs when hotplug removes the last one Yury Norov
2026-11-19  6:13   ` Shrikanth Hegde
2026-11-13 18:42 ` [PATCH 3/7] virt: steal_governor: remove the minimum elapsed-time check Yury Norov
2026-11-13 18:42 ` [PATCH 4/7] virt: steal_governor: serialize sampling against CPU hotplug Yury Norov
2026-11-19  6:22   ` Shrikanth Hegde [this message]
2026-11-13 18:42 ` [PATCH 5/7] virt: steal_governor: warn on unexpected preferred mask states Yury Norov
2026-11-13 18:42 ` [PATCH 6/7] virt: steal_governor: restart sampling immediately after CPU hotplug Yury Norov
2026-11-16  2:13   ` Yury Norov
2026-11-19  6:06   ` Shrikanth Hegde
2026-11-13 18:42 ` [PATCH 7/7] cpu: make preferred CPU policy writers mutually exclusive Yury Norov
2026-11-19  6:10   ` Shrikanth Hegde

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=1556d3b0-1c89-4d3d-b9e5-5921c5c9158b@linux.ibm.com \
    --to=sshegde@linux.ibm.com \
    --cc=agordeev@linux.ibm.com \
    --cc=arighi@nvidia.com \
    --cc=borntraeger@linux.ibm.com \
    --cc=bsegall@google.com \
    --cc=corbet@lwn.net \
    --cc=dakr@kernel.org \
    --cc=dietmar.eggemann@arm.com \
    --cc=driver-core@lists.linux.dev \
    --cc=gor@linux.ibm.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=hca@linux.ibm.com \
    --cc=iii@linux.ibm.com \
    --cc=johan@kernel.org \
    --cc=juri.lelli@redhat.com \
    --cc=kprateek.nayak@amd.com \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-s390@vger.kernel.org \
    --cc=linux@rasmusvillemoes.dk \
    --cc=maxim.kuvyrkov@grdncc.com \
    --cc=meted@linux.ibm.com \
    --cc=mgorman@suse.de \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rafael@kernel.org \
    --cc=rdunlap@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=skhan@linuxfoundation.org \
    --cc=svens@linux.ibm.com \
    --cc=tglx@kernel.org \
    --cc=vincent.guittot@linaro.org \
    --cc=vschneid@redhat.com \
    --cc=ynorov@nvidia.com \
    --cc=yury.norov@gmail.com \
    /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®