linux-arch.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Frederic Weisbecker <frederic-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
To: Alex Belits <abelits-eYqpPyKDWXRBDgjK7y7TUQ@public.gmane.org>
Cc: "rostedt-nx8X9YLhiw1AfugRpC6u6w@public.gmane.org"
	<rostedt-nx8X9YLhiw1AfugRpC6u6w@public.gmane.org>,
	"mingo-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org"
	<mingo-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>,
	"peterz-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org"
	<peterz-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>,
	"linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org"
	<linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
	Prasun Kapoor <pkapoor-eYqpPyKDWXRBDgjK7y7TUQ@public.gmane.org>,
	"tglx-hfZtesqFncYOwBW4kG4KsQ@public.gmane.org"
	<tglx-hfZtesqFncYOwBW4kG4KsQ@public.gmane.org>,
	"linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org"
	<linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
	"linux-mm-u79uwXL29TY76Z2rM5mHXA@public.gmane.org"
	<linux-mm-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
	"linux-arch-u79uwXL29TY76Z2rM5mHXA@public.gmane.org"
	<linux-arch-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>
Subject: Re: [PATCH 11/12] task_isolation: kick_all_cpus_sync: don't kick isolated cpus
Date: Fri, 6 Mar 2020 16:34:47 +0100	[thread overview]
Message-ID: <20200306153446.GC8590@lenoir> (raw)
In-Reply-To: <dfa5e0e9f34e6ff0ef048c81bc70496354f31300.camel-eYqpPyKDWXRBDgjK7y7TUQ@public.gmane.org>

On Wed, Mar 04, 2020 at 04:15:24PM +0000, Alex Belits wrote:
> From: Yuri Norov <ynorov-eYqpPyKDWXRBDgjK7y7TUQ@public.gmane.org>
> 
> Make sure that kick_all_cpus_sync() does not call CPUs that are running
> isolated tasks.
> 
> Signed-off-by: Alex Belits <abelits-eYqpPyKDWXRBDgjK7y7TUQ@public.gmane.org>
> ---
>  kernel/smp.c | 14 +++++++++++++-
>  1 file changed, 13 insertions(+), 1 deletion(-)
> 
> diff --git a/kernel/smp.c b/kernel/smp.c
> index 3a8bcbdd4ce6..d9b4b2fedfed 100644
> --- a/kernel/smp.c
> +++ b/kernel/smp.c
> @@ -731,9 +731,21 @@ static void do_nothing(void *unused)
>   */
>  void kick_all_cpus_sync(void)
>  {
> +	struct cpumask mask;
> +
>  	/* Make sure the change is visible before we kick the cpus */
>  	smp_mb();
> -	smp_call_function(do_nothing, NULL, 1);
> +
> +	preempt_disable();
> +#ifdef CONFIG_TASK_ISOLATION
> +	cpumask_clear(&mask);
> +	task_isolation_cpumask(&mask);
> +	cpumask_complement(&mask, &mask);
> +#else
> +	cpumask_setall(&mask);
> +#endif
> +	smp_call_function_many(&mask, do_nothing, NULL, 1);
> +	preempt_enable();
>  }

That looks very dangerous, the callers of kick_all_cpus_sync() want to
sync all CPUs for a reason. You will rather need to fix the callers.

Thanks.

>  EXPORT_SYMBOL_GPL(kick_all_cpus_sync);
>  
> -- 
> 2.20.1
> 

WARNING: multiple messages have this Message-ID (diff)
From: Frederic Weisbecker <frederic@kernel.org>
To: Alex Belits <abelits@marvell.com>
Cc: "rostedt@goodmis.org" <rostedt@goodmis.org>,
	"mingo@kernel.org" <mingo@kernel.org>,
	"peterz@infradead.org" <peterz@infradead.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	Prasun Kapoor <pkapoor@marvell.com>,
	"tglx@linutronix.de" <tglx@linutronix.de>,
	"linux-api@vger.kernel.org" <linux-api@vger.kernel.org>,
	"linux-mm@vger.kernel.org" <linux-mm@vger.kernel.org>,
	"linux-arch@vger.kernel.org" <linux-arch@vger.kernel.org>
Subject: Re: [PATCH 11/12] task_isolation: kick_all_cpus_sync: don't kick isolated cpus
Date: Fri, 6 Mar 2020 16:34:47 +0100	[thread overview]
Message-ID: <20200306153446.GC8590@lenoir> (raw)
Message-ID: <20200306153447.NZkvVMTsIB8ukxGfKxUox7jPx9H9LH4WDqK_XT5F14M@z> (raw)
In-Reply-To: <dfa5e0e9f34e6ff0ef048c81bc70496354f31300.camel@marvell.com>

On Wed, Mar 04, 2020 at 04:15:24PM +0000, Alex Belits wrote:
> From: Yuri Norov <ynorov@marvell.com>
> 
> Make sure that kick_all_cpus_sync() does not call CPUs that are running
> isolated tasks.
> 
> Signed-off-by: Alex Belits <abelits@marvell.com>
> ---
>  kernel/smp.c | 14 +++++++++++++-
>  1 file changed, 13 insertions(+), 1 deletion(-)
> 
> diff --git a/kernel/smp.c b/kernel/smp.c
> index 3a8bcbdd4ce6..d9b4b2fedfed 100644
> --- a/kernel/smp.c
> +++ b/kernel/smp.c
> @@ -731,9 +731,21 @@ static void do_nothing(void *unused)
>   */
>  void kick_all_cpus_sync(void)
>  {
> +	struct cpumask mask;
> +
>  	/* Make sure the change is visible before we kick the cpus */
>  	smp_mb();
> -	smp_call_function(do_nothing, NULL, 1);
> +
> +	preempt_disable();
> +#ifdef CONFIG_TASK_ISOLATION
> +	cpumask_clear(&mask);
> +	task_isolation_cpumask(&mask);
> +	cpumask_complement(&mask, &mask);
> +#else
> +	cpumask_setall(&mask);
> +#endif
> +	smp_call_function_many(&mask, do_nothing, NULL, 1);
> +	preempt_enable();
>  }

That looks very dangerous, the callers of kick_all_cpus_sync() want to
sync all CPUs for a reason. You will rather need to fix the callers.

Thanks.

>  EXPORT_SYMBOL_GPL(kick_all_cpus_sync);
>  
> -- 
> 2.20.1
> 

  parent reply	other threads:[~2020-03-06 15:34 UTC|newest]

Thread overview: 113+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-04 16:01 [PATCH 00/12] "Task_isolation" mode Alex Belits
     [not found] ` <4473787e1b6bc3cc226067e8d122092a678b63de.camel-eYqpPyKDWXRBDgjK7y7TUQ@public.gmane.org>
2020-03-04 16:03   ` [PATCH 01/12] task_isolation: vmstat: add quiet_vmstat_sync function Alex Belits
2020-03-04 16:03     ` Alex Belits
2020-03-04 16:04   ` [PATCH 02/12] task_isolation: vmstat: add vmstat_idle function Alex Belits
2020-03-04 16:04     ` Alex Belits
2020-03-04 16:08   ` [PATCH 04/12] task_isolation: Add task isolation hooks to arch-independent code Alex Belits
2020-03-04 16:08     ` Alex Belits
2020-03-04 16:10   ` [PATCH 06/12] task_isolation: arch/arm64: enable task isolation functionality Alex Belits
2020-03-04 16:10     ` Alex Belits
2020-03-04 16:31     ` Mark Rutland
2020-03-08  4:48       ` [EXT] " Alex Belits
2020-03-08  4:48         ` Alex Belits
2020-03-04 16:11   ` [PATCH 07/12] task_isolation: arch/arm: " Alex Belits
2020-03-04 16:11     ` Alex Belits
2020-03-04 16:12   ` [PATCH 08/12] task_isolation: don't interrupt CPUs with tick_nohz_full_kick_cpu() Alex Belits
2020-03-04 16:12     ` Alex Belits
     [not found]     ` <d7ce01e57d4a35b126e1cb96a63109eaa9781cb6.camel-eYqpPyKDWXRBDgjK7y7TUQ@public.gmane.org>
2020-03-06 16:03       ` Frederic Weisbecker
2020-03-06 16:03         ` Frederic Weisbecker
2020-03-08  7:28         ` [EXT] " Alex Belits
2020-03-08  7:28           ` Alex Belits
     [not found]           ` <646a22fd24e8dfeb1eb3101ae7be2b88e91dbfa3.camel-eYqpPyKDWXRBDgjK7y7TUQ@public.gmane.org>
2020-03-09  2:38             ` Frederic Weisbecker
2020-03-09  2:38               ` Frederic Weisbecker
2020-03-04 16:16   ` [PATCH 12/12] task_isolation: CONFIG_TASK_ISOLATION prevents distribution of jobs to non-housekeeping CPUs Alex Belits
2020-03-04 16:16     ` Alex Belits
2020-03-04 16:07 ` [PATCH 03/12] task_isolation: userspace hard isolation from kernel Alex Belits
2020-03-05 18:33   ` Frederic Weisbecker
2020-03-08  5:32     ` [EXT] " Alex Belits
2020-04-28 14:12     ` Marcelo Tosatti
2020-04-28 14:12       ` Marcelo Tosatti
2020-03-06 15:26   ` Frederic Weisbecker
2020-03-08  6:06     ` [EXT] " Alex Belits
2020-03-06 16:00   ` Frederic Weisbecker
2020-03-08  7:16     ` [EXT] " Alex Belits
2020-03-08  7:16       ` Alex Belits
2020-03-04 16:09 ` [PATCH 05/12] task_isolation: arch/x86: enable task isolation functionality Alex Belits
2020-03-04 16:13 ` [PATCH 09/12] task_isolation: net: don't flush backlog on CPUs running isolated tasks Alex Belits
2020-03-04 16:14 ` [PATCH 10/12] task_isolation: ringbuffer: don't interrupt CPUs running isolated tasks on buffer resize Alex Belits
2020-03-04 16:14   ` Alex Belits
2020-03-04 16:15 ` [PATCH 11/12] task_isolation: kick_all_cpus_sync: don't kick isolated cpus Alex Belits
     [not found]   ` <dfa5e0e9f34e6ff0ef048c81bc70496354f31300.camel-eYqpPyKDWXRBDgjK7y7TUQ@public.gmane.org>
2020-03-06 15:34     ` Frederic Weisbecker [this message]
2020-03-06 15:34       ` Frederic Weisbecker
2020-03-08  6:48       ` [EXT] " Alex Belits
2020-03-08  6:48         ` Alex Belits
2020-03-09  2:28         ` Frederic Weisbecker
2020-03-09  2:28           ` Frederic Weisbecker
2020-03-08  3:42 ` [PATCH v2 00/12] "Task_isolation" mode Alex Belits
2020-03-08  3:44   ` [PATCH v2 01/12] task_isolation: vmstat: add quiet_vmstat_sync function Alex Belits
2020-03-08  3:44     ` Alex Belits
2020-03-08  3:46   ` [PATCH v2 02/12] task_isolation: vmstat: add vmstat_idle function Alex Belits
2020-03-08  3:47   ` [PATCH v2 03/12] task_isolation: userspace hard isolation from kernel Alex Belits
2020-03-08  3:47     ` Alex Belits
     [not found]     ` <20200307214254.7a8f6c22@hermes.lan>
2020-03-08  7:33       ` [EXT] " Alex Belits
2020-03-08  7:33         ` Alex Belits
2020-03-27  8:42     ` Marta Rybczynska
2020-03-27  8:42       ` Marta Rybczynska
2020-04-06  4:31     ` Kevyn-Alexandre Paré
     [not found]     ` <105f17f25e90a9a58299a7ed644bdd0f36434c87.camel-eYqpPyKDWXRBDgjK7y7TUQ@public.gmane.org>
2020-04-06  4:43       ` Kevyn-Alexandre Paré
2020-04-06  4:43         ` Kevyn-Alexandre Paré
2020-03-08  3:49   ` [PATCH v2 05/12] task_isolation: arch/x86: enable task isolation functionality Alex Belits
2020-03-08  3:52   ` [PATCH v2 07/12] task_isolation: arch/arm: " Alex Belits
     [not found]   ` <aed12dd15ea2981bc9554cfa8b5e273c1342c756.camel-eYqpPyKDWXRBDgjK7y7TUQ@public.gmane.org>
2020-03-08  3:48     ` [PATCH v2 04/12] task_isolation: Add task isolation hooks to arch-independent code Alex Belits
2020-03-08  3:48       ` Alex Belits
2020-03-08  3:50     ` [PATCH v2 06/12] task_isolation: arch/arm64: enable task isolation functionality Alex Belits
2020-03-08  3:50       ` Alex Belits
2020-03-09 16:59       ` Mark Rutland
2020-03-09 16:59         ` Mark Rutland
2020-03-08  3:53     ` [PATCH v2 08/12] task_isolation: don't interrupt CPUs with tick_nohz_full_kick_cpu() Alex Belits
2020-03-08  3:53       ` Alex Belits
2020-03-08  3:54     ` [PATCH v2 09/12] task_isolation: net: don't flush backlog on CPUs running isolated tasks Alex Belits
2020-03-08  3:54       ` Alex Belits
2020-03-08  3:55   ` [PATCH v2 10/12] task_isolation: ringbuffer: don't interrupt CPUs running isolated tasks on buffer resize Alex Belits
2020-04-06  4:27     ` Kevyn-Alexandre Paré
2020-04-06  4:27       ` Kevyn-Alexandre Paré
2020-03-08  3:56   ` [PATCH v2 11/12] task_isolation: kick_all_cpus_sync: don't kick isolated cpus Alex Belits
2020-03-08  3:57   ` [PATCH v2 12/12] task_isolation: CONFIG_TASK_ISOLATION prevents distribution of jobs to non-housekeeping CPUs Alex Belits
2020-04-09 15:09   ` [PATCH v3 00/13] "Task_isolation" mode Alex Belits
2020-04-09 15:15     ` [PATCH 01/13] task_isolation: vmstat: add quiet_vmstat_sync function Alex Belits
2020-04-09 15:16     ` [PATCH 02/13] task_isolation: vmstat: add vmstat_idle function Alex Belits
     [not found]     ` <07c25c246c55012981ec0296eee23e68c719333a.camel-eYqpPyKDWXRBDgjK7y7TUQ@public.gmane.org>
2020-04-09 15:17       ` [PATCH v3 03/13] task_isolation: add instruction synchronization memory barrier Alex Belits
2020-04-09 15:17         ` Alex Belits
2020-04-15 12:44         ` Mark Rutland
     [not found]           ` <20200415124427.GB28304-NxAhncQ8SJbILnBEAk/BfazUEOm+Xw19@public.gmane.org>
2020-04-19  5:02             ` [EXT] " Alex Belits
2020-04-19  5:02               ` Alex Belits
2020-04-20 12:23               ` Will Deacon
2020-04-20 12:23                 ` Will Deacon
2020-04-20 12:36                 ` Mark Rutland
2020-04-20 12:36                   ` Mark Rutland
     [not found]                   ` <20200420123628.GB69441-NxAhncQ8SJbILnBEAk/BfazUEOm+Xw19@public.gmane.org>
2020-04-20 13:55                     ` Will Deacon
2020-04-20 13:55                       ` Will Deacon
2020-04-21  7:41                       ` Will Deacon
2020-04-20 12:45               ` Mark Rutland
2020-04-09 15:27       ` [PATCH v3 12/13] task_isolation: kick_all_cpus_sync: don't kick isolated cpus Alex Belits
2020-04-09 15:27         ` Alex Belits
2020-04-09 15:28       ` [PATCH v3 13/13] task_isolation: CONFIG_TASK_ISOLATION prevents distribution of jobs to non-housekeeping CPUs Alex Belits
2020-04-09 15:28         ` Alex Belits
2020-04-09 15:20     ` [PATCH v3 04/13] task_isolation: userspace hard isolation from kernel Alex Belits
2020-04-09 15:20       ` Alex Belits
2020-04-09 18:00       ` Andy Lutomirski
2020-04-19  5:07         ` Alex Belits
2020-04-19  5:07           ` Alex Belits
2020-04-09 15:21     ` [PATCH 05/13] task_isolation: Add task isolation hooks to arch-independent code Alex Belits
2020-04-09 15:21       ` Alex Belits
2020-04-09 15:22     ` [PATCH 06/13] task_isolation: arch/x86: enable task isolation functionality Alex Belits
2020-04-09 15:22       ` Alex Belits
2020-04-09 15:23     ` [PATCH v3 07/13] task_isolation: arch/arm64: " Alex Belits
2020-04-22 12:08       ` Catalin Marinas
2020-04-09 15:24     ` [PATCH v3 08/13] task_isolation: arch/arm: " Alex Belits
2020-04-09 15:24       ` Alex Belits
2020-04-09 15:25     ` [PATCH v3 09/13] task_isolation: don't interrupt CPUs with tick_nohz_full_kick_cpu() Alex Belits
2020-04-09 15:25       ` Alex Belits
2020-04-09 15:26     ` [PATCH v3 10/13] task_isolation: net: don't flush backlog on CPUs running isolated tasks Alex Belits
2020-04-09 15:26       ` Alex Belits
2020-04-09 15:27     ` [PATCH v3 11/13] task_isolation: ringbuffer: don't interrupt CPUs running isolated tasks on buffer resize Alex Belits

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=20200306153446.GC8590@lenoir \
    --to=frederic-dgejt+ai2ygdnm+yrofe0a@public.gmane.org \
    --cc=abelits-eYqpPyKDWXRBDgjK7y7TUQ@public.gmane.org \
    --cc=linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=linux-arch-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=linux-mm-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=mingo-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org \
    --cc=peterz-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org \
    --cc=pkapoor-eYqpPyKDWXRBDgjK7y7TUQ@public.gmane.org \
    --cc=rostedt-nx8X9YLhiw1AfugRpC6u6w@public.gmane.org \
    --cc=tglx-hfZtesqFncYOwBW4kG4KsQ@public.gmane.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;
as well as URLs for NNTP newsgroup(s).