linux-kernel - Re: [PATCH v3 28/36] hrtimer: Implement support for softirq based hrtimers

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <20171214104755.7bnfwfv6mer2toe2@breakpoint.cc>
Date:   Thu, 14 Dec 2017 11:47:56 +0100
From:   Sebastian Andrzej Siewior <sebastian@...akpoint.cc>
To:     Anna-Maria Gleixner <anna-maria@...utronix.de>
Cc:     LKML <linux-kernel@...r.kernel.org>,
        Thomas Gleixner <tglx@...utronix.de>,
        Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...hat.com>, keescook@...omium.org,
        Christoph Hellwig <hch@....de>,
        John Stultz <john.stultz@...aro.org>,
        bert schulze <spambemyguest@...glemail.com>
Subject: Re: [PATCH v3 28/36] hrtimer: Implement support for softirq based
 hrtimers

On 2017-11-29 16:30:53 [+0100], Anna-Maria Gleixner wrote:
> diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
> index 65211fd7288d..40b14f025829 100644
> --- a/kernel/time/hrtimer.c
> +++ b/kernel/time/hrtimer.c
> @@ -711,6 +768,28 @@ static void hrtimer_reprogram(struct hrtimer *timer)
>  	WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0);
>  
>  	/*
> +	 * CLOCK_REALTIME timer might be requested with an absolute
> +	 * expiry time which is less than base->offset. Set it to 0.
> +	 */
> +	if (expires < 0)
> +		expires = 0;
> +
> +	if (timer->is_soft) {
> +		if (cpu_base->softirq_activated)
> +			return;
> +
> +		if (!ktime_before(expires, cpu_base->softirq_expires_next))
> +			return;
> +
> +		cpu_base->softirq_next_timer = timer;
> +		cpu_base->softirq_expires_next = expires;
> +
> +		if (!ktime_before(expires, cpu_base->expires_next) ||
> +		    !reprogram)
> +			return;
> +	}
> +
> +	/*
>  	 * If the timer is not on the current cpu, we cannot reprogram
>  	 * the other cpus clock event device.
>  	 */


if the timer is enqueud on CPUX and we run on CPUY then we have to
update the cpu_base bits of the correct CPU. Not sure if this accounts
for all the pieces but it might be okay with the check we have in
hrtimer_check_target() (that we have nothing to do but just wait).

Without this, all "sleep 1" which are invoked on CPU1 but migrated to/
programmed on CPU0 (due to timer migration wth NOHZ_FULL) won't expire
as expected.

Reported-by: bert schulze <spambemyguest@...glemail.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@...utronix.de>
---
 kernel/time/hrtimer.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index af16a5af2269..c2c344fda487 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -801,16 +801,18 @@ static void hrtimer_reprogram(struct hrtimer *timer, bool reprogram)
 		expires = 0;
 
 	if (timer->is_soft) {
-		if (cpu_base->softirq_activated)
+		struct hrtimer_cpu_base *timer_cpu_base = base->cpu_base;
+
+		if (timer_cpu_base->softirq_activated)
 			return;
 
-		if (!ktime_before(expires, cpu_base->softirq_expires_next))
+		if (!ktime_before(expires, timer_cpu_base->softirq_expires_next))
 			return;
 
-		cpu_base->softirq_next_timer = timer;
-		cpu_base->softirq_expires_next = expires;
+		timer_cpu_base->softirq_next_timer = timer;
+		timer_cpu_base->softirq_expires_next = expires;
 
-		if (!ktime_before(expires, cpu_base->expires_next) ||
+		if (!ktime_before(expires, timer_cpu_base->expires_next) ||
 		    !reprogram)
 			return;
 	}
-- 
2.15.1