All of lore.kernel.org
 help / color / mirror / Atom feed
From: Frederic Weisbecker <fweisbec@gmail.com>
To: LKML <linux-kernel@vger.kernel.org>, linaro-sched-sig@lists.linaro.org
Cc: Frederic Weisbecker <fweisbec@gmail.com>,
	Alessio Igor Bogani <abogani@kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Avi Kivity <avi@redhat.com>, Chris Metcalf <cmetcalf@tilera.com>,
	Christoph Lameter <cl@linux.com>,
	Daniel Lezcano <daniel.lezcano@linaro.org>,
	Geoff Levand <geoff@infradead.org>,
	Gilad Ben Yossef <gilad@benyossef.com>,
	Ingo Molnar <mingo@kernel.org>,
	Max Krasnyansky <maxk@qualcomm.com>,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Stephen Hemminger <shemminger@vyatta.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Sven-Thorsten Dietrich <thebigcorporation@gmail.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Zen Lin <zen@openhuawei.org>
Subject: [PATCH 30/32] rcu: Switch to extended quiescent state in userspace from nohz cpuset
Date: Wed, 21 Mar 2012 14:58:36 +0100	[thread overview]
Message-ID: <1332338318-5958-32-git-send-email-fweisbec@gmail.com> (raw)
In-Reply-To: <1332338318-5958-1-git-send-email-fweisbec@gmail.com>

When we switch to adaptive nohz mode and we run in userspace,
we can still receive IPIs from the RCU core if a grace period
has been started by another CPU because we need to take part
of its completion.

However running in userspace is similar to that of running in
idle because we don't make use of RCU there, thus we can be
considered as running in RCU extended quiescent state. The
benefit when running into that mode is that we are not
anymore disturbed by needless IPIs coming from the RCU core.

To perform this, we just to use the RCU extended quiescent state
APIs on the following points:

- kernel exit or tick stop in userspace: here we switch to extended
quiescent state because we run in userspace without the tick.

- kernel entry or tick restart: here we exit the extended quiescent
state because either we enter the kernel and we may make use of RCU
read side critical section anytime, or we need the timer tick for some
reason and that takes care of RCU grace period in a traditional way.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Alessio Igor Bogani <abogani@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Avi Kivity <avi@redhat.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Geoff Levand <geoff@infradead.org>
Cc: Gilad Ben Yossef <gilad@benyossef.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Max Krasnyansky <maxk@qualcomm.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephen Hemminger <shemminger@vyatta.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Sven-Thorsten Dietrich <thebigcorporation@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Zen Lin <zen@openhuawei.org>
---
 include/linux/tick.h     |    3 +++
 kernel/time/tick-sched.c |   27 +++++++++++++++++++++++++--
 2 files changed, 28 insertions(+), 2 deletions(-)

diff --git a/include/linux/tick.h b/include/linux/tick.h
index 3c31d6e..e2a49ad 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -153,6 +153,8 @@ static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; }
 # endif /* !NO_HZ */
 
 #ifdef CONFIG_CPUSETS_NO_HZ
+DECLARE_PER_CPU(int, nohz_task_ext_qs);
+
 extern void tick_nohz_enter_kernel(void);
 extern void tick_nohz_exit_kernel(void);
 extern void tick_nohz_enter_exception(struct pt_regs *regs);
@@ -160,6 +162,7 @@ extern void tick_nohz_exit_exception(struct pt_regs *regs);
 extern void tick_nohz_check_adaptive(void);
 extern void tick_nohz_pre_schedule(void);
 extern void tick_nohz_post_schedule(void);
+extern void tick_nohz_cpu_exit_qs(void);
 extern bool tick_nohz_account_tick(void);
 extern void tick_nohz_flush_current_times(bool restart_tick);
 #else /* !CPUSETS_NO_HZ */
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 4b9bdfb..6c66977 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -565,10 +565,13 @@ static void tick_nohz_cpuset_stop_tick(struct tick_sched *ts)
 
 	if (!was_stopped && ts->tick_stopped) {
 		WARN_ON_ONCE(ts->saved_jiffies_whence != JIFFIES_SAVED_NONE);
-		if (user)
+		if (user) {
 			ts->saved_jiffies_whence = JIFFIES_SAVED_USER;
-		else if (!current->mm)
+			__get_cpu_var(nohz_task_ext_qs) = 1;
+			rcu_user_enter_irq();
+		} else if (!current->mm) {
 			ts->saved_jiffies_whence = JIFFIES_SAVED_SYS;
+		}
 
 		ts->saved_jiffies = jiffies;
 		set_thread_flag(TIF_NOHZ);
@@ -897,6 +900,8 @@ void tick_check_idle(int cpu)
 }
 
 #ifdef CONFIG_CPUSETS_NO_HZ
+DEFINE_PER_CPU(int, nohz_task_ext_qs);
+
 void tick_nohz_exit_kernel(void)
 {
 	unsigned long flags;
@@ -920,6 +925,9 @@ void tick_nohz_exit_kernel(void)
 	ts->saved_jiffies = jiffies;
 	ts->saved_jiffies_whence = JIFFIES_SAVED_USER;
 
+	__get_cpu_var(nohz_task_ext_qs) = 1;
+	rcu_user_enter();
+
 	local_irq_restore(flags);
 }
 
@@ -938,6 +946,11 @@ void tick_nohz_enter_kernel(void)
 		return;
 	}
 
+	if (__get_cpu_var(nohz_task_ext_qs) == 1) {
+		__get_cpu_var(nohz_task_ext_qs) = 0;
+		rcu_user_exit();
+	}
+
 	WARN_ON_ONCE(ts->saved_jiffies_whence != JIFFIES_SAVED_USER);
 
 	delta_jiffies = jiffies - ts->saved_jiffies;
@@ -949,6 +962,14 @@ void tick_nohz_enter_kernel(void)
 	local_irq_restore(flags);
 }
 
+void tick_nohz_cpu_exit_qs(void)
+{
+	if (__get_cpu_var(nohz_task_ext_qs)) {
+		rcu_user_exit_irq();
+		__get_cpu_var(nohz_task_ext_qs) = 0;
+	}
+}
+
 void tick_nohz_enter_exception(struct pt_regs *regs)
 {
 	if (user_mode(regs))
@@ -984,6 +1005,7 @@ static void tick_nohz_restart_adaptive(void)
 	tick_nohz_flush_current_times(true);
 	tick_nohz_restart_sched_tick();
 	clear_thread_flag(TIF_NOHZ);
+	tick_nohz_cpu_exit_qs();
 }
 
 void tick_nohz_check_adaptive(void)
@@ -1021,6 +1043,7 @@ void tick_nohz_pre_schedule(void)
 	if (ts->tick_stopped) {
 		tick_nohz_flush_current_times(true);
 		clear_thread_flag(TIF_NOHZ);
+		/* FIXME: warn if we are in RCU idle mode */
 	}
 }
 
-- 
1.7.5.4


  parent reply	other threads:[~2012-03-21 14:00 UTC|newest]

Thread overview: 97+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-03-21 13:58 [RFC][PATCH 00/32] Nohz cpusets v2 (adaptive tickless kernel) Frederic Weisbecker
2012-03-21 13:58 ` Frederic Weisbecker
2012-04-04 15:33   ` warning in tick_nohz_irq_exit Stephen Hemminger
2012-04-04 20:45     ` Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 01/32] nohz: Separate idle sleeping time accounting from nohz logic Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 02/32] nohz: Make nohz API agnostic against idle ticks cputime accounting Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 03/32] nohz: Rename ts->idle_tick to ts->last_tick Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 04/32] nohz: Move nohz load balancer selection into idle logic Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 05/32] nohz: Move ts->idle_calls incrementation into strict " Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 06/32] nohz: Move next idle expiry time record into idle logic area Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 07/32] cpuset: Set up interface for nohz flag Frederic Weisbecker
2012-03-21 14:50   ` Christoph Lameter
2012-03-22  4:03     ` Mike Galbraith
2012-03-22 16:26       ` Christoph Lameter
2012-03-22 19:20         ` Mike Galbraith
2012-03-27 11:22       ` Frederic Weisbecker
2012-03-27 11:53         ` Mike Galbraith
2012-03-27 11:56           ` Frederic Weisbecker
2012-03-27 12:31             ` Mike Galbraith
2012-03-27 11:19     ` Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 08/32] nohz: Try not to give the timekeeping duty to an adaptive tickless cpu Frederic Weisbecker
2012-03-21 14:52   ` Christoph Lameter
2012-03-27 10:50     ` Frederic Weisbecker
2012-03-27 16:08       ` Christoph Lameter
2012-03-27 16:47         ` Peter Zijlstra
2012-03-28  1:12           ` Christoph Lameter
2012-03-28  8:39             ` Peter Zijlstra
2012-03-28 13:11               ` Dimitri Sivanich
2012-03-28 15:51               ` Chris Metcalf
2012-03-30  1:34         ` Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 09/32] x86: New cpuset nohz irq vector Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 10/32] nohz: Adaptive tick stop and restart on nohz cpuset Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 11/32] nohz/cpuset: Don't turn off the tick if rcu needs it Frederic Weisbecker
2012-03-21 14:54   ` Christoph Lameter
2012-03-22  7:38     ` Gilad Ben-Yossef
2012-03-22 16:18       ` Christoph Lameter
2012-03-27 15:21         ` Gilad Ben-Yossef
2012-03-28 12:39           ` Frederic Weisbecker
2012-03-28 12:57             ` Gilad Ben-Yossef
2012-03-28 13:38               ` Frederic Weisbecker
2012-03-22 17:18       ` Chris Metcalf
2012-03-27 15:31         ` Gilad Ben-Yossef
2012-03-27 15:43           ` Chris Metcalf
2012-03-28  8:36             ` Gilad Ben-Yossef
2012-03-27 12:13     ` Frederic Weisbecker
2012-03-27 16:13       ` Christoph Lameter
2012-03-27 16:24         ` Steven Rostedt
2012-03-28  0:42           ` Christoph Lameter
2012-03-28  1:06             ` Steven Rostedt
2012-03-28  1:19               ` Christoph Lameter
2012-03-28  1:35                 ` Steven Rostedt
2012-03-28  3:17                   ` Steven Rostedt
2012-03-28  7:55                     ` Gilad Ben-Yossef
2012-03-28 12:21                       ` Frederic Weisbecker
2012-03-28 12:41                         ` Gilad Ben-Yossef
2012-03-28 14:02                       ` Steven Rostedt
2012-03-28 11:53         ` Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 12/32] nohz/cpuset: Wake up adaptive nohz CPU when a timer gets enqueued Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 13/32] nohz/cpuset: Don't stop the tick if posix cpu timers are running Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 14/32] nohz/cpuset: Restart tick when nohz flag is cleared on cpuset Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 15/32] nohz/cpuset: Restart the tick if printk needs it Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 16/32] rcu: Restart the tick on non-responding adaptive nohz CPUs Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 17/32] rcu: Restart tick if we enqueue a callback in a nohz/cpuset CPU Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 18/32] nohz: Generalize tickless cpu time accounting Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 19/32] nohz/cpuset: Account user and system times in adaptive nohz mode Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 20/32] nohz/cpuset: New API to flush cputimes on nohz cpusets Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 21/32] nohz/cpuset: Flush cputime on threads in nohz cpusets when waiting leader Frederic Weisbecker
2012-03-27 14:10   ` Gilad Ben-Yossef
2012-03-27 14:23     ` Gilad Ben-Yossef
2012-03-28 11:20       ` Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 22/32] nohz/cpuset: Flush cputimes on procfs stat file read Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 23/32] nohz/cpuset: Flush cputimes for getrusage() and times() syscalls Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 24/32] x86: Syscall hooks for nohz cpusets Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 25/32] x86: Exception " Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 26/32] x86: Add adaptive tickless hooks on do_notify_resume() Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 27/32] nohz: Don't restart the tick before scheduling to idle Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 28/32] rcu: New rcu_user_enter() and rcu_user_exit() APIs Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 29/32] rcu: New rcu_user_enter_irq() and rcu_user_exit_irq() APIs Frederic Weisbecker
2012-03-21 13:58 ` Frederic Weisbecker [this message]
2012-03-21 13:58 ` [PATCH 31/32] nohz: Exit RCU idle mode when we schedule before resuming userspace Frederic Weisbecker
2012-03-21 13:58 ` [PATCH 32/32] nohz/cpuset: Disable under some configs Frederic Weisbecker
2012-03-27 15:02 ` [RFC][PATCH 00/32] Nohz cpusets v2 (adaptive tickless kernel) Gilad Ben-Yossef
2012-03-27 15:04   ` Gilad Ben-Yossef
2012-03-27 15:05     ` Gilad Ben-Yossef
2012-03-27 16:22       ` Christoph Lameter
2012-03-28  6:47         ` Gilad Ben-Yossef
2012-03-27 15:10   ` Peter Zijlstra
2012-03-27 15:18     ` Gilad Ben-Yossef
2012-05-22 21:31     ` Thomas Gleixner
2012-05-22 21:50       ` Steven Rostedt
2012-05-22 22:22         ` Thomas Gleixner
2012-03-28 11:43   ` Frederic Weisbecker
2012-03-30  0:33 ` Kevin Hilman
2012-03-30  0:45   ` Frederic Weisbecker
2012-03-30  2:07     ` Geoff Levand
2012-03-30 14:10       ` Kevin Hilman
2012-10-29 20:27 [PATCH 00/32] [RFC] nohz/cpuset: Start discussions on nohz CPUs Steven Rostedt
2012-10-29 20:27 ` [PATCH 30/32] rcu: Switch to extended quiescent state in userspace from nohz cpuset Steven Rostedt

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=1332338318-5958-32-git-send-email-fweisbec@gmail.com \
    --to=fweisbec@gmail.com \
    --cc=abogani@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=avi@redhat.com \
    --cc=cl@linux.com \
    --cc=cmetcalf@tilera.com \
    --cc=daniel.lezcano@linaro.org \
    --cc=geoff@infradead.org \
    --cc=gilad@benyossef.com \
    --cc=linaro-sched-sig@lists.linaro.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=maxk@qualcomm.com \
    --cc=mingo@kernel.org \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=shemminger@vyatta.com \
    --cc=tglx@linutronix.de \
    --cc=thebigcorporation@gmail.com \
    --cc=zen@openhuawei.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.