linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Morten Rasmussen <morten.rasmussen@arm.com>
To: peterz@infradead.org, mingo@redhat.com
Cc: dietmar.eggemann@arm.com, yuyang.du@intel.com,
	vincent.guittot@linaro.org, mgalbraith@suse.de,
	linux-kernel@vger.kernel.org,
	Morten Rasmussen <morten.rasmussen@arm.com>
Subject: [PATCH 02/16] sched/fair: Consistent use of prev_cpu in wakeup path
Date: Mon, 23 May 2016 11:58:44 +0100	[thread overview]
Message-ID: <1464001138-25063-3-git-send-email-morten.rasmussen@arm.com> (raw)
In-Reply-To: <1464001138-25063-1-git-send-email-morten.rasmussen@arm.com>

In commit ac66f5477239 ("sched/numa: Introduce migrate_swap()")
select_task_rq() got a 'cpu' argument to enable overriding of prev_cpu
in special cases (NUMA task swapping). However, the
select_task_rq_fair() helper functions: wake_affine() and
select_idle_sibling(), still use task_cpu(p) directly to work out
prev_cpu which leads to inconsistencies.

This patch passes prev_cpu (potentially overridden by NUMA code) into
the helper functions to ensure prev_cpu is indeed the same cpu
everywhere in the wakeup path.

cc: Ingo Molnar <mingo@redhat.com>
cc: Peter Zijlstra <peterz@infradead.org>

Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
---
 kernel/sched/fair.c | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 218f8e8..c49e25a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -656,7 +656,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 }
 
 #ifdef CONFIG_SMP
-static int select_idle_sibling(struct task_struct *p, int cpu);
+static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu);
 static unsigned long task_h_load(struct task_struct *p);
 
 /*
@@ -1502,7 +1502,8 @@ static void task_numa_compare(struct task_numa_env *env,
 	 * Call select_idle_sibling to maybe find a better one.
 	 */
 	if (!cur)
-		env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu);
+		env->dst_cpu = select_idle_sibling(env->p, env->src_cpu,
+						   env->dst_cpu);
 
 assign:
 	assigned = true;
@@ -5013,18 +5014,18 @@ static int wake_wide(struct task_struct *p)
 	return 1;
 }
 
-static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
+static int wake_affine(struct sched_domain *sd, struct task_struct *p,
+		       int prev_cpu, int sync)
 {
 	s64 this_load, load;
 	s64 this_eff_load, prev_eff_load;
-	int idx, this_cpu, prev_cpu;
+	int idx, this_cpu;
 	struct task_group *tg;
 	unsigned long weight;
 	int balanced;
 
 	idx	  = sd->wake_idx;
 	this_cpu  = smp_processor_id();
-	prev_cpu  = task_cpu(p);
 	load	  = source_load(prev_cpu, idx);
 	this_load = target_load(this_cpu, idx);
 
@@ -5189,11 +5190,10 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 /*
  * Try and locate an idle CPU in the sched_domain.
  */
-static int select_idle_sibling(struct task_struct *p, int target)
+static int select_idle_sibling(struct task_struct *p, int prev, int target)
 {
 	struct sched_domain *sd;
 	struct sched_group *sg;
-	int i = task_cpu(p);
 
 	if (idle_cpu(target))
 		return target;
@@ -5201,8 +5201,8 @@ static int select_idle_sibling(struct task_struct *p, int target)
 	/*
 	 * If the prevous cpu is cache affine and idle, don't be stupid.
 	 */
-	if (i != target && cpus_share_cache(i, target) && idle_cpu(i))
-		return i;
+	if (prev != target && cpus_share_cache(prev, target) && idle_cpu(prev))
+		return prev;
 
 	/*
 	 * Otherwise, iterate the domains and find an eligible idle cpu.
@@ -5223,6 +5223,8 @@ static int select_idle_sibling(struct task_struct *p, int target)
 	for_each_lower_domain(sd) {
 		sg = sd->groups;
 		do {
+			int i;
+
 			if (!cpumask_intersects(sched_group_cpus(sg),
 						tsk_cpus_allowed(p)))
 				goto next;
@@ -5331,13 +5333,13 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 
 	if (affine_sd) {
 		sd = NULL; /* Prefer wake_affine over balance flags */
-		if (cpu != prev_cpu && wake_affine(affine_sd, p, sync))
+		if (cpu != prev_cpu && wake_affine(affine_sd, p, prev_cpu, sync))
 			new_cpu = cpu;
 	}
 
 	if (!sd) {
 		if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */
-			new_cpu = select_idle_sibling(p, new_cpu);
+			new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
 
 	} else while (sd) {
 		struct sched_group *group;
-- 
1.9.1

  parent reply	other threads:[~2016-05-23 10:58 UTC|newest]

Thread overview: 61+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-05-23 10:58 [PATCH 00/16] sched: Clean-ups and asymmetric cpu capacity support Morten Rasmussen
2016-05-23 10:58 ` [PATCH 01/16] sched: Fix power to capacity renaming in comment Morten Rasmussen
2016-05-23 10:58 ` Morten Rasmussen [this message]
2016-06-01 19:49   ` [PATCH 02/16] sched/fair: Consistent use of prev_cpu in wakeup path Peter Zijlstra
2016-05-23 10:58 ` [PATCH 03/16] sched/fair: Disregard idle task wakee_flips in wake_wide Morten Rasmussen
2016-05-23 11:12   ` Mike Galbraith
2016-05-23 12:00     ` Morten Rasmussen
2016-05-23 13:00       ` Mike Galbraith
2016-05-23 14:10         ` Morten Rasmussen
2016-05-23 15:42           ` Mike Galbraith
2016-05-23 23:17             ` Yuyang Du
2016-05-23 23:04       ` Yuyang Du
2016-06-01 19:57       ` Peter Zijlstra
2016-06-02  8:05         ` Peter Zijlstra
2016-06-07 12:08           ` Morten Rasmussen
2016-05-23 10:58 ` [PATCH 04/16] sched/fair: Optimize find_idlest_cpu() when there is no choice Morten Rasmussen
2016-05-24  6:29   ` Mike Galbraith
2016-05-24  8:05     ` Morten Rasmussen
2016-05-24  8:12       ` Mike Galbraith
2016-06-01 19:59   ` Peter Zijlstra
2016-06-07 14:25     ` Morten Rasmussen
2016-05-23 10:58 ` [PATCH 05/16] sched: Introduce SD_ASYM_CPUCAPACITY sched_domain topology flag Morten Rasmussen
2016-05-23 10:58 ` [PATCH 06/16] sched: Disable WAKE_AFFINE for asymmetric configurations Morten Rasmussen
2016-05-24  9:10   ` Vincent Guittot
2016-05-24 10:29     ` Morten Rasmussen
2016-05-24 12:12       ` Vincent Guittot
2016-05-24 13:16         ` Morten Rasmussen
2016-05-24 13:27           ` Vincent Guittot
2016-05-24 13:36             ` Morten Rasmussen
2016-05-24 13:52               ` Vincent Guittot
2016-05-24 15:02                 ` Morten Rasmussen
2016-05-24 15:53                   ` Vincent Guittot
2016-05-25  9:12                     ` Morten Rasmussen
2016-05-26  6:45                       ` Vincent Guittot
2016-06-07 16:50                         ` Morten Rasmussen
2016-05-23 10:58 ` [PATCH 07/16] sched: Make SD_BALANCE_WAKE a topology flag Morten Rasmussen
2016-05-24 23:52   ` Yuyang Du
2016-05-25  9:27     ` Morten Rasmussen
2016-06-01 20:18   ` Peter Zijlstra
2016-06-08  8:45     ` Morten Rasmussen
2016-05-23 10:58 ` [PATCH 08/16] sched: Store maximum per-cpu capacity in root domain Morten Rasmussen
2016-05-23 10:58 ` [PATCH 09/16] sched/fair: Let asymmetric cpu configurations balance at wake-up Morten Rasmussen
2016-05-24  0:04   ` Yuyang Du
2016-05-24  8:10     ` Morten Rasmussen
2016-05-24  7:03   ` Mike Galbraith
2016-05-24  7:15     ` Mike Galbraith
2016-05-25  6:57   ` Wanpeng Li
2016-05-25  9:49     ` Morten Rasmussen
2016-05-25 10:29       ` Wanpeng Li
2016-05-25 10:54         ` Morten Rasmussen
2016-05-25 11:18           ` Wanpeng Li
2016-06-02 14:21   ` Peter Zijlstra
2016-06-08 11:29     ` Morten Rasmussen
2016-06-08 14:36       ` Peter Zijlstra
2016-05-23 10:58 ` [PATCH 10/16] sched/fair: Compute task/cpu utilization at wake-up more correctly Morten Rasmussen
2016-05-23 10:58 ` [PATCH 11/16] sched/fair: Consider spare capacity in find_idlest_group() Morten Rasmussen
2016-05-23 10:58 ` [PATCH 12/16] sched: Add per-cpu max capacity to sched_group_capacity Morten Rasmussen
2016-05-23 10:58 ` [PATCH 13/16] sched/fair: Avoid pulling tasks from non-overloaded higher capacity groups Morten Rasmussen
2016-05-23 10:58 ` [PATCH 14/16] arm: Set SD_ASYM_CPUCAPACITY for big.LITTLE platforms Morten Rasmussen
2016-05-23 10:58 ` [PATCH 15/16] arm: Set SD_BALANCE_WAKE flag for asymmetric capacity systems Morten Rasmussen
2016-05-23 10:58 ` [PATCH 16/16] arm: Update arch_scale_cpu_capacity() to reflect change to define Morten Rasmussen

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=1464001138-25063-3-git-send-email-morten.rasmussen@arm.com \
    --to=morten.rasmussen@arm.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mgalbraith@suse.de \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=vincent.guittot@linaro.org \
    --cc=yuyang.du@intel.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;
as well as URLs for NNTP newsgroup(s).