linux-kernel - [PATCH v3] sched: Micro optimization in pick_next_task() and in check_preempt

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: <47a00e0e-69c0-2a2f-6ae1-1a8ec9b01ede@virtuozzo.com>
Date:   Thu, 19 Dec 2019 20:12:15 +0000
From:   Kirill Tkhai <ktkhai@...tuozzo.com>
To:     Steven Rostedt <rostedt@...dmis.org>,
        "mingo@...hat.com" <mingo@...hat.com>,
        "peterz@...radead.org" <peterz@...radead.org>
CC:     LKML <linux-kernel@...r.kernel.org>,
        "juri.lelli@...hat.com" <juri.lelli@...hat.com>,
        "vincent.guittot@...aro.org" <vincent.guittot@...aro.org>,
        "dietmar.eggemann@....com" <dietmar.eggemann@....com>,
        "bsegall@...gle.com" <bsegall@...gle.com>,
        Mel Gorman <mgorman@...e.de>
Subject: [PATCH v3] sched: Micro optimization in pick_next_task() and in
 check_preempt_curr()

This introduces an optimization based on xxx_sched_class addresses
in two hot scheduler functions: pick_next_task() and check_preempt_curr().

It is possible to compare pointers to sched classes to check, which
of them has a higher priority, instead of current iterations using
for_each_class().

One more result of the patch is that size of object file becomes a little
less (excluding added BUG_ON(), which goes in __init section):

$size kernel/sched/core.o
         text     data      bss	    dec	    hex	filename
before:  66446    18957	    676	  86079	  1503f	kernel/sched/core.o
after:   66398    18957	    676	  86031	  1500f	kernel/sched/core.o

Signed-off-by: Kirill Tkhai <ktkhai@...tuozzo.com>
---
 kernel/sched/core.c |   24 +++++++++---------------
 1 file changed, 9 insertions(+), 15 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 15508c202bf5..befdd7158b27 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1416,20 +1416,10 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
 
 void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 {
-	const struct sched_class *class;
-
-	if (p->sched_class == rq->curr->sched_class) {
+	if (p->sched_class == rq->curr->sched_class)
 		rq->curr->sched_class->check_preempt_curr(rq, p, flags);
-	} else {
-		for_each_class(class) {
-			if (class == rq->curr->sched_class)
-				break;
-			if (class == p->sched_class) {
-				resched_curr(rq);
-				break;
-			}
-		}
-	}
+	else if (p->sched_class > rq->curr->sched_class)
+		resched_curr(rq);
 
 	/*
 	 * A queue event has occurred, and we're going to schedule.  In
@@ -3914,8 +3904,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	 * higher scheduling class, because otherwise those loose the
 	 * opportunity to pull in more work from other CPUs.
 	 */
-	if (likely((prev->sched_class == &idle_sched_class ||
-		    prev->sched_class == &fair_sched_class) &&
+	if (likely(prev->sched_class <= &fair_sched_class &&
 		   rq->nr_running == rq->cfs.h_nr_running)) {
 
 		p = pick_next_task_fair(rq, prev, rf);
@@ -6569,6 +6558,11 @@ void __init sched_init(void)
 	unsigned long ptr = 0;
 	int i;
 
+	BUG_ON(&idle_sched_class > &fair_sched_class ||
+		&fair_sched_class > &rt_sched_class ||
+		&rt_sched_class > &dl_sched_class ||
+		&dl_sched_class > &stop_sched_class);
+
 	wait_bit_init();
 
 #ifdef CONFIG_FAIR_GROUP_SCHED