linux-kernel - Re: Stopping the tick on a fully loaded system

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

Message-ID: <20230726161432.GW4253@hirez.programming.kicks-ass.net>
Date:   Wed, 26 Jul 2023 18:14:32 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     "Rafael J. Wysocki" <rafael@...nel.org>,
        g@...ez.programming.kicks-ass.net
Cc:     Anna-Maria Behnsen <anna-maria@...utronix.de>,
        Frederic Weisbecker <frederic@...nel.org>,
        Vincent Guittot <vincent.guittot@...aro.org>,
        linux-kernel@...r.kernel.org, Thomas Gleixner <tglx@...utronix.de>,
        "Gautham R. Shenoy" <gautham.shenoy@....com>,
        Ingo Molnar <mingo@...hat.com>,
        Juri Lelli <juri.lelli@...hat.com>,
        Dietmar Eggemann <dietmar.eggemann@....com>,
        Steven Rostedt <rostedt@...dmis.org>,
        Ben Segall <bsegall@...gle.com>, Mel Gorman <mgorman@...e.de>,
        Daniel Bristot de Oliveira <bristot@...hat.com>,
        Valentin Schneider <vschneid@...hat.com>
Subject: Re: Stopping the tick on a fully loaded system

On Wed, Jul 26, 2023 at 05:53:46PM +0200, Rafael J. Wysocki wrote:

> > > That means we don't track nearly enough data to reliably tell anything
> > > about disabling the tick or not. We should have at least one bucket
> > > beyond TICK_NSEC for this.
> >
> > Quite likely.
> 
> So the reasoning here was that those additional bins would not be
> necessary for idle state selection, but the problem of whether or not
> to stop the tick is kind of separate from the idle state selection
> problem if the target residency values for all of the idle states are
> relatively short.  And so it should be addressed separately which
> currently it is not.  Admittedly, this is a mistake.

Right, the C state buckets are enough to pick a state, but not to handle
the tick thing.

The below hack boots on my ivb-ep with extra (disabled) states. Now let
me go hack up teo to make use of that.

name		residency

POLL		0
C1              1
C1E             80
C3              156
C6              300
TICK            1000
POST-TICK       2000


---
diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c
index d9cda7f6ccb9..5f435fb8b89f 100644
--- a/drivers/cpuidle/driver.c
+++ b/drivers/cpuidle/driver.c
@@ -147,13 +147,37 @@ static void cpuidle_setup_broadcast_timer(void *arg)
 		tick_broadcast_disable();
 }
 
+static int tick_enter(struct cpuidle_device *dev,
+		      struct cpuidle_driver *drv,
+		      int index)
+{
+	return -ENODEV;
+}
+
+static void __cpuidle_state_init_tick(struct cpuidle_state *s)
+{
+	strcpy(s->name, "TICK");
+	strcpy(s->desc, "(no-op)");
+
+	s->target_residency_ns = TICK_NSEC;
+	s->target_residency = div_u64(TICK_NSEC, NSEC_PER_USEC);
+
+	s->exit_latency_ns = 0;
+	s->exit_latency = 0;
+
+	s->flags |= CPUIDLE_FLAG_UNUSABLE;
+
+	s->enter = tick_enter;
+	s->enter_s2idle = tick_enter;
+}
+
 /**
  * __cpuidle_driver_init - initialize the driver's internal data
  * @drv: a valid pointer to a struct cpuidle_driver
  */
 static void __cpuidle_driver_init(struct cpuidle_driver *drv)
 {
-	int i;
+	int tick = 0, post_tick = 0, i;
 
 	/*
 	 * Use all possible CPUs as the default, because if the kernel boots
@@ -192,6 +216,39 @@ static void __cpuidle_driver_init(struct cpuidle_driver *drv)
 			s->exit_latency_ns =  0;
 		else
 			s->exit_latency = div_u64(s->exit_latency_ns, NSEC_PER_USEC);
+
+		if (!tick && s->target_residency_ns >= TICK_NSEC) {
+			tick = 1;
+
+			if (s->target_residency_ns == TICK_NSEC)
+				continue;
+
+			post_tick = 1;
+
+			memmove(&drv->states[i+1], &drv->states[i],
+				sizeof(struct cpuidle_state) * (CPUIDLE_STATE_MAX - i - 1));
+			drv->state_count++;
+
+			__cpuidle_state_init_tick(s);
+			i++;
+		}
+	}
+
+	if (!tick) {
+		struct cpuidle_state *s = &drv->states[i];
+		__cpuidle_state_init_tick(s);
+		drv->state_count++;
+		i++;
+	}
+
+	if (!post_tick) {
+		struct cpuidle_state *s = &drv->states[i];
+		__cpuidle_state_init_tick(s);
+		strcpy(s->name, "POST-TICK");
+		s->target_residency_ns *= 2;
+		s->target_residency *= 2;
+		drv->state_count++;
+		i++;
 	}
 }
 
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 3183aeb7f5b4..a642ee9e916c 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -16,7 +16,7 @@
 #include <linux/hrtimer.h>
 #include <linux/context_tracking.h>
 
-#define CPUIDLE_STATE_MAX	10
+#define CPUIDLE_STATE_MAX	16
 #define CPUIDLE_NAME_LEN	16
 #define CPUIDLE_DESC_LEN	32