mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Yuyang Du <yuyang.du@intel.com>
To: peterz@infradead.org, mingo@kernel.org, linux-kernel@vger.kernel.org
Cc: umgwanakikbuti@gmail.com, bsegall@google.com, pjt@google.com,
	morten.rasmussen@arm.com, vincent.guittot@linaro.org,
	dietmar.eggemann@arm.com, matt@codeblueprint.co.uk
Subject: [RFC PATCH 02/11] sched: Restructure destroy_sched_domain()
Date: Thu, 16 Jun 2016 09:49:26 +0800	[thread overview]
Message-ID: <1466041775-4528-3-git-send-email-yuyang.du@intel.com> (raw)
In-Reply-To: <1466041775-4528-1-git-send-email-yuyang.du@intel.com>

From: Peter Zijlstra <peterz@infradead.org>

There is no point in doing a call_rcu() for each domain, only do a
callback for the root sched domain and clean up the entire set in one
go.

Also make the entire call chain be called destroy_sched_domain*() to
remove confusion with the free_sched_domains() call, which does an
entirely different thing.

Both cpu_attach_domain() callers of destroy_sched_domain() can live
without the call_rcu() because at those points the sched_domain hasn't
been published yet.

This one seems to work much better; so much for last minute 'cleanups'.
---
 kernel/sched/core.c |   18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ab6e6cf..c4596e0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5833,10 +5833,8 @@ static void free_sched_groups(struct sched_group *sg, int free_sgc)
 	} while (sg != first);
 }
 
-static void free_sched_domain(struct rcu_head *rcu)
+static void destroy_sched_domain(struct sched_domain *sd)
 {
-	struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu);
-
 	/*
 	 * If its an overlapping domain it has private groups, iterate and
 	 * nuke them all.
@@ -5850,15 +5848,21 @@ static void free_sched_domain(struct rcu_head *rcu)
 	kfree(sd);
 }
 
-static void destroy_sched_domain(struct sched_domain *sd)
+static void destroy_sched_domains_rcu(struct rcu_head *rcu)
 {
-	call_rcu(&sd->rcu, free_sched_domain);
+	struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu);
+
+	while (sd) {
+		struct sched_domain *parent = sd->parent;
+		destroy_sched_domain(sd);
+		sd = parent;
+	}
 }
 
 static void destroy_sched_domains(struct sched_domain *sd)
 {
-	for (; sd; sd = sd->parent)
-		destroy_sched_domain(sd);
+	if (sd)
+		call_rcu(&sd->rcu, destroy_sched_domains_rcu);
 }
 
 /*
-- 
1.7.9.5

  parent reply	other threads:[~2016-06-16  9:49 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-06-16  1:49 [RFC PATCH 00/11] Refactor select_task_rq_fair() Yuyang Du
2016-06-16  1:49 ` [RFC PATCH 01/11] sched: Remove unused @cpu argument from destroy_sched_domain*() Yuyang Du
2016-06-16  1:49 ` Yuyang Du [this message]
2016-06-16  1:49 ` [RFC PATCH 03/11] sched: Introduce struct sched_domain_shared Yuyang Du
2016-06-16  1:49 ` [RFC PATCH 04/11] sched: Replace sd_busy/nr_busy_cpus with sched_domain_shared Yuyang Du
2016-06-16  1:49 ` [RFC PATCH 05/11] sched: Rewrite select_idle_siblings() Yuyang Du
2016-06-16  1:49 ` [RFC PATCH 06/11] sched: Optimize SCHED_SMT Yuyang Du
2016-06-16  1:49 ` [RFC PATCH 07/11] sched: Clean up SD_BALANCE_WAKE flags in sched domain build-up Yuyang Du
2016-06-16  1:49 ` [RFC PATCH 08/11] sched: Remove SD_WAKE_AFFINE flag and replace it with SD_BALANCE_WAKE Yuyang Du
2016-06-23 13:04   ` Matt Fleming
2016-06-23 13:54     ` Peter Zijlstra
2016-06-23 14:06     ` Mike Galbraith
2016-06-16  1:49 ` [RFC PATCH 09/11] sched: Add per CPU variable sd_socket_id to specify the CPU's socket Yuyang Du
2016-06-16  1:49 ` [RFC PATCH 10/11] sched: Add sched_llc_complete static key to specify whether the LLC covers all CPUs Yuyang Du
2016-06-16  1:49 ` [RFC PATCH 11/11] sched/fair: Refactor select_task_rq_fair() Yuyang Du
2016-06-16  1:57   ` Yuyang Du

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=1466041775-4528-3-git-send-email-yuyang.du@intel.com \
    --to=yuyang.du@intel.com \
    --cc=bsegall@google.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=matt@codeblueprint.co.uk \
    --cc=mingo@kernel.org \
    --cc=morten.rasmussen@arm.com \
    --cc=peterz@infradead.org \
    --cc=pjt@google.com \
    --cc=umgwanakikbuti@gmail.com \
    --cc=vincent.guittot@linaro.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

all inboxes | Powered by JetHome®