linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Srivatsa S. Bhat" <srivatsa.bhat@linux.vnet.ibm.com>
To: tglx@linutronix.de, peterz@infradead.org,
	paulmck@linux.vnet.ibm.com, rusty@rustcorp.com.au,
	mingo@kernel.org, akpm@linux-foundation.org, namhyung@kernel.org,
	vincent.guittot@linaro.org
Cc: sbw@mit.edu, tj@kernel.org, amit.kucheria@linaro.org,
	rostedt@goodmis.org, rjw@sisk.pl,
	srivatsa.bhat@linux.vnet.ibm.com, wangyun@linux.vnet.ibm.com,
	xiaoguangrong@linux.vnet.ibm.com, nikunj@linux.vnet.ibm.com,
	linux-pm@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [RFC PATCH 10/10] cpu: No more __stop_machine() in _cpu_down()
Date: Tue, 04 Dec 2012 14:26:21 +0530	[thread overview]
Message-ID: <20121204085615.25919.98054.stgit@srivatsabhat.in.ibm.com> (raw)
In-Reply-To: <20121204085149.25919.29920.stgit@srivatsabhat.in.ibm.com>

From: Paul E. McKenney <paul.mckenney@linaro.org>

The _cpu_down() function invoked as part of the CPU-hotplug offlining
process currently invokes __stop_machine(), which is slow and inflicts
substantial real-time latencies on the entire system.  This patch
substitutes stop_cpus() for __stop_machine() in order to improve
both performance and real-time latency.

This is currently unsafe, because there are a number of uses of
preempt_disable() that are intended to block CPU-hotplug offlining.
These will be fixed by using get/put_online_cpus_stable_atomic(), but in the
meantime, this commit is one way to help locate them.

Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ Srivatsa: Refer to get/put_online_cpus_stable_atomic() in the changelog ]
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
---

 kernel/cpu.c |    9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/kernel/cpu.c b/kernel/cpu.c
index aaf2393..59592e5 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -352,15 +352,20 @@ static int __ref take_cpu_down(void *_param)
 {
 	struct take_cpu_down_param *param = _param;
 	int err, cpu = (long)(param->hcpu);
+	unsigned long flags;
 
 	prepare_cpu_take_down(cpu);
 
 	/* Ensure this CPU doesn't handle any more interrupts. */
+	local_irq_save(flags);
 	err = __cpu_disable();
-	if (err < 0)
+	if (err < 0) {
+		local_irq_restore(flags);
 		return err;
+	}
 
 	cpu_notify(CPU_DYING | param->mod, param->hcpu);
+	local_irq_restore(flags);
 	return 0;
 }
 
@@ -393,7 +398,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	}
 	smpboot_park_threads(cpu);
 
-	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
+	err = stop_cpus(cpumask_of(cpu), take_cpu_down, &tcd_param);
 	if (err) {
 		/* CPU didn't die: tell everyone.  Can't complain. */
 		smpboot_unpark_threads(cpu);


      parent reply	other threads:[~2012-12-04  8:57 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-12-04  8:53 [RFC PATCH 00/10] CPU hotplug: stop_machine()-free CPU hotplug Srivatsa S. Bhat
2012-12-04  8:53 ` [RFC PATCH 01/10] CPU hotplug: Introduce "stable" cpu online mask, for atomic hotplug readers Srivatsa S. Bhat
2012-12-04 15:17   ` Tejun Heo
2012-12-04 21:14     ` Srivatsa S. Bhat
2012-12-04 22:10   ` Andrew Morton
2012-12-05  2:56     ` Michael Wang
2012-12-05  3:28       ` Michael Wang
2012-12-05 12:38     ` Srivatsa S. Bhat
2012-12-04  8:54 ` [RFC PATCH 02/10] smp, cpu hotplug: Fix smp_call_function_*() to prevent CPU offline properly Srivatsa S. Bhat
2012-12-04 22:17   ` Andrew Morton
2012-12-05 12:41     ` Srivatsa S. Bhat
2012-12-04 23:39   ` Rusty Russell
2012-12-05 12:44     ` Srivatsa S. Bhat
2012-12-04  8:54 ` [RFC PATCH 03/10] smp, cpu hotplug: Fix on_each_cpu_*() " Srivatsa S. Bhat
2012-12-04  8:54 ` [RFC PATCH 04/10] sched, cpu hotplug: Use stable online cpus in try_to_wake_up() & select_task_rq() Srivatsa S. Bhat
2012-12-04  8:55 ` [RFC PATCH 05/10] kick_process(), cpu-hotplug: Prevent offlining of target CPU properly Srivatsa S. Bhat
2012-12-04  8:55 ` [RFC PATCH 06/10] yield_to(), cpu-hotplug: Prevent offlining of other CPUs properly Srivatsa S. Bhat
2012-12-04  8:55 ` [RFC PATCH 07/10] KVM: VMX: fix invalid cpu passed to smp_call_function_single Srivatsa S. Bhat
2012-12-04  8:55 ` [RFC PATCH 08/10] KVM: VMX: fix memory order between loading vmcs and clearing vmcs Srivatsa S. Bhat
2012-12-04  8:56 ` [RFC PATCH 09/10] KVM: VMX: fix unsyc vmcs status when cpu is going down Srivatsa S. Bhat
2012-12-04  8:56 ` Srivatsa S. Bhat [this message]

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=20121204085615.25919.98054.stgit@srivatsabhat.in.ibm.com \
    --to=srivatsa.bhat@linux.vnet.ibm.com \
    --cc=akpm@linux-foundation.org \
    --cc=amit.kucheria@linaro.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=namhyung@kernel.org \
    --cc=nikunj@linux.vnet.ibm.com \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=peterz@infradead.org \
    --cc=rjw@sisk.pl \
    --cc=rostedt@goodmis.org \
    --cc=rusty@rustcorp.com.au \
    --cc=sbw@mit.edu \
    --cc=tglx@linutronix.de \
    --cc=tj@kernel.org \
    --cc=vincent.guittot@linaro.org \
    --cc=wangyun@linux.vnet.ibm.com \
    --cc=xiaoguangrong@linux.vnet.ibm.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).