linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Frederic Weisbecker <fweisbec@gmail.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
	linux-kernel@vger.kernel.org, mingo@elte.hu,
	laijs@cn.fujitsu.com, dipankar@in.ibm.com,
	akpm@linux-foundation.org, mathieu.desnoyers@polymtl.ca,
	josh@joshtriplett.org, niv@us.ibm.com, tglx@linutronix.de,
	rostedt@goodmis.org, Valdis.Kletnieks@vt.edu,
	dhowells@redhat.com, eric.dumazet@gmail.com, darren@dvhart.com,
	sbw@mit.edu, patches@linaro.org,
	Alessio Igor Bogani <abogani@kernel.org>,
	Avi Kivity <avi@redhat.com>, Chris Metcalf <cmetcalf@tilera.com>,
	Christoph Lameter <cl@linux.com>,
	Geoff Levand <geoff@infradead.org>,
	Gilad Ben Yossef <gilad@benyossef.com>,
	Hakan Akkan <hakanakkan@gmail.com>,
	"H. Peter Anvin" <hpa@zytor.com>, Ingo Molnar <mingo@kernel.org>,
	Kevin Hilman <khilman@ti.com>,
	Max Krasnyansky <maxk@qualcomm.com>,
	Stephen Hemminger <shemminger@vyatta.com>,
	Sven-Thorsten Dietrich <thebigcorporation@gmail.com>
Subject: Re: [PATCH tip/core/rcu 11/26] rcu: Exit RCU extended QS on user preemption
Date: Wed, 12 Sep 2012 11:33:33 +0200	[thread overview]
Message-ID: <1347442413.2124.70.camel@twins> (raw)
In-Reply-To: <20120910202611.GB19268@somewhere>

On Mon, 2012-09-10 at 22:26 +0200, Frederic Weisbecker wrote:

> > > OK, so colour me unconvinced.. why are we doing this?
> > > 
> > > Typically when we call schedule nr_running != 1 (we need current to be
> > > running and a possible target to switch to).
> > > 
> > > So I'd prefer to simply have schedule() disable all this adaptive tick
> > > nonsense and leave it at that.
> > 
> > In fact, the only way to get here is through ttwu(), which would have
> > done the nr_running increment and should have disabled all this adaptive
> > stuff.
> > 
> > So again,.. why?
> 
> Ok, indeed if the ttwu happened locally or even remotely through an IPI, the
> tick engine would stop the tick and exit that RCU extended quiescent state
> before we reach that place.
> 
> I just want to be sure I'm covering every case. There are some places
> around that call set_need_resched() even if no task is waiting for the CPU
> (RCU is such an example). In this case the nohz engine won't exit the RCU
> user mode before schedule().
> 
> Another example: a CPU does a remote wake up so it does set_need_resched()
> and sends the IPI. The target CPU could see the TIF_RESCHED before resuming
> userspace and call schedule_user() -> schedule() while the IPI has not
> yet arrived. In this case we need that rcu_user_exit() before schedule might
> make any use of RCU.
> 
> Also when the task returns from schedule(), if it's alone in the runqueue,
> the rcu_user_enter() that follows can be helpful to stop the tick and
> enter our RCU quiescent state.

So all that should have been in the Changelog.

So the only real problem I see is non IPI remote wakeups, those cannot
actually restart the tick on the target cpu like we want.

The rest could all be fixed to not need this.

Hrmm. still don't like the patch, but at least I see why its needed.

> Also I'm considering this RCU user extended quiescent state as a standalone
> feature for now. Indeed the only user of it is the adaptive tickless thing.
> But I'm treating that RCU part independantly for now so that it makes it
> easier to merge, piecewise.

But its semantics are very tightly tied to the requirements of adaptive
tick, so arguing about one without the other doesn't really make sense.


  reply	other threads:[~2012-09-12  9:34 UTC|newest]

Thread overview: 73+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-08-30 21:05 [PATCH tip/core/rcu 0/26] idle-related changes Paul E. McKenney
2012-08-30 21:05 ` [PATCH tip/core/rcu 01/26] rcu: New rcu_user_enter() and rcu_user_exit() APIs Paul E. McKenney
2012-08-30 21:05   ` [PATCH tip/core/rcu 02/26] rcu: New rcu_user_enter_irq() and rcu_user_exit_irq() APIs Paul E. McKenney
2012-08-31 19:13     ` Josh Triplett
2012-08-31 19:54       ` Frederic Weisbecker
2012-08-31 21:38         ` Josh Triplett
2012-08-30 21:05   ` [PATCH tip/core/rcu 03/26] rcu: Make RCU_FAST_NO_HZ handle adaptive ticks Paul E. McKenney
2012-08-31 23:40     ` Josh Triplett
2012-08-30 21:05   ` [PATCH tip/core/rcu 04/26] rcu: Settle config for userspace extended quiescent state Paul E. McKenney
2012-08-31 23:44     ` Josh Triplett
2012-09-05  0:34       ` Paul E. McKenney
2012-09-05  0:46         ` Josh Triplett
2012-09-10 21:35           ` Frederic Weisbecker
2012-08-30 21:05   ` [PATCH tip/core/rcu 05/26] rcu: Allow rcu_user_enter()/exit() to nest Paul E. McKenney
2012-08-31 23:45     ` Josh Triplett
2012-08-30 21:05   ` [PATCH tip/core/rcu 06/26] rcu: Ignore userspace extended quiescent state by default Paul E. McKenney
2012-08-31 23:46     ` Josh Triplett
2012-08-30 21:05   ` [PATCH tip/core/rcu 07/26] rcu: Switch task's syscall hooks on context switch Paul E. McKenney
2012-08-31 23:48     ` Josh Triplett
2012-08-30 21:05   ` [PATCH tip/core/rcu 08/26] x86: Syscall hooks for userspace RCU extended QS Paul E. McKenney
2012-08-31 23:59     ` Josh Triplett
2012-09-10 21:30       ` Frederic Weisbecker
2012-08-30 21:05   ` [PATCH tip/core/rcu 09/26] x86: Exception " Paul E. McKenney
2012-08-31 23:51     ` Josh Triplett
2012-08-30 21:05   ` [PATCH tip/core/rcu 10/26] rcu: Exit RCU extended QS on kernel preemption after irq/exception Paul E. McKenney
2012-08-31 23:51     ` Josh Triplett
2012-09-06 16:52     ` Peter Zijlstra
2012-09-10 20:31       ` Frederic Weisbecker
2012-08-30 21:05   ` [PATCH tip/core/rcu 11/26] rcu: Exit RCU extended QS on user preemption Paul E. McKenney
2012-08-31 23:52     ` Josh Triplett
2012-09-06 17:02     ` Peter Zijlstra
2012-09-06 17:13       ` Peter Zijlstra
2012-09-10 20:26         ` Frederic Weisbecker
2012-09-12  9:33           ` Peter Zijlstra [this message]
2012-09-12 12:06             ` Frederic Weisbecker
2012-09-12 12:41               ` Peter Zijlstra
2012-09-12 12:52                 ` Peter Zijlstra
2012-09-12 13:54                   ` Frederic Weisbecker
2012-09-12 14:09                     ` Peter Zijlstra
2012-09-12 13:52                 ` Frederic Weisbecker
2012-09-12 15:21                 ` Paul E. McKenney
2012-08-30 21:05   ` [PATCH tip/core/rcu 12/26] x86: Use the new schedule_user API on userspace preemption Paul E. McKenney
2012-08-31 23:53     ` Josh Triplett
2012-08-30 21:05   ` [PATCH tip/core/rcu 13/26] x86: Exit RCU extended QS on notify resume Paul E. McKenney
2012-08-31 23:54     ` Josh Triplett
2012-08-30 21:05   ` [PATCH tip/core/rcu 14/26] rcu: Userspace RCU extended QS selftest Paul E. McKenney
2012-08-31 23:54     ` Josh Triplett
2012-08-30 21:05   ` [PATCH tip/core/rcu 15/26] alpha: Fix preemption handling in idle loop Paul E. McKenney
2012-08-31 23:55     ` Josh Triplett
2012-08-30 21:05   ` [PATCH tip/core/rcu 16/26] alpha: Add missing RCU idle APIs on " Paul E. McKenney
2012-09-01  0:00     ` Josh Triplett
2012-08-30 21:05   ` [PATCH tip/core/rcu 17/26] cris: " Paul E. McKenney
2012-09-01  0:01     ` Josh Triplett
2012-08-30 21:05   ` [PATCH tip/core/rcu 18/26] frv: " Paul E. McKenney
2012-09-01  0:01     ` Josh Triplett
2012-08-30 21:05   ` [PATCH tip/core/rcu 19/26] h8300: " Paul E. McKenney
2012-09-01  0:02     ` Josh Triplett
2012-08-30 21:05   ` [PATCH tip/core/rcu 20/26] m32r: " Paul E. McKenney
2012-09-01  0:02     ` Josh Triplett
2012-08-30 21:05   ` [PATCH tip/core/rcu 21/26] m68k: " Paul E. McKenney
2012-09-01  0:02     ` Josh Triplett
2012-08-30 21:05   ` [PATCH tip/core/rcu 22/26] mn10300: " Paul E. McKenney
2012-09-01  0:03     ` Josh Triplett
2012-08-30 21:05   ` [PATCH tip/core/rcu 23/26] parisc: " Paul E. McKenney
2012-09-01  0:03     ` Josh Triplett
2012-08-30 21:05   ` [PATCH tip/core/rcu 24/26] score: " Paul E. McKenney
2012-09-01  0:04     ` Josh Triplett
2012-08-30 21:05   ` [PATCH tip/core/rcu 25/26] xtensa: " Paul E. McKenney
2012-09-01  0:05     ` Josh Triplett
2012-08-30 21:05   ` [PATCH tip/core/rcu 26/26] ia64: " Paul E. McKenney
2012-09-01  0:05     ` Josh Triplett
2012-08-31 19:07   ` [PATCH tip/core/rcu 01/26] rcu: New rcu_user_enter() and rcu_user_exit() APIs Josh Triplett
2012-09-05  1:04     ` Paul E. McKenney

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=1347442413.2124.70.camel@twins \
    --to=peterz@infradead.org \
    --cc=Valdis.Kletnieks@vt.edu \
    --cc=abogani@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=avi@redhat.com \
    --cc=cl@linux.com \
    --cc=cmetcalf@tilera.com \
    --cc=darren@dvhart.com \
    --cc=dhowells@redhat.com \
    --cc=dipankar@in.ibm.com \
    --cc=eric.dumazet@gmail.com \
    --cc=fweisbec@gmail.com \
    --cc=geoff@infradead.org \
    --cc=gilad@benyossef.com \
    --cc=hakanakkan@gmail.com \
    --cc=hpa@zytor.com \
    --cc=josh@joshtriplett.org \
    --cc=khilman@ti.com \
    --cc=laijs@cn.fujitsu.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mathieu.desnoyers@polymtl.ca \
    --cc=maxk@qualcomm.com \
    --cc=mingo@elte.hu \
    --cc=mingo@kernel.org \
    --cc=niv@us.ibm.com \
    --cc=patches@linaro.org \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=rostedt@goodmis.org \
    --cc=sbw@mit.edu \
    --cc=shemminger@vyatta.com \
    --cc=tglx@linutronix.de \
    --cc=thebigcorporation@gmail.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).