From: Peter Zijlstra <peterz@infradead.org>
To: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>,
Oleg Nesterov <oleg@redhat.com>,
linux-kernel@vger.kernel.org, mingo@kernel.org,
laijs@cn.fujitsu.com, dipankar@in.ibm.com,
akpm@linux-foundation.org, mathieu.desnoyers@efficios.com,
josh@joshtriplett.org, tglx@linutronix.de, dhowells@redhat.com,
edumazet@google.com, dvhart@linux.intel.com, fweisbec@gmail.com,
bobby.prani@gmail.com, masami.hiramatsu.pt@hitachi.com
Subject: Re: [PATCH v3 tip/core/rcu 3/9] rcu: Add synchronous grace-period waiting for RCU-tasks
Date: Fri, 8 Aug 2014 18:51:12 +0200 [thread overview]
Message-ID: <20140808165112.GI9918@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <20140808163905.GA5821@linux.vnet.ibm.com>
[-- Attachment #1: Type: text/plain, Size: 1448 bytes --]
On Fri, Aug 08, 2014 at 09:39:05AM -0700, Paul E. McKenney wrote:
> On Fri, Aug 08, 2014 at 06:27:14PM +0200, Peter Zijlstra wrote:
> > On Fri, Aug 08, 2014 at 10:58:58AM -0400, Steven Rostedt wrote:
> >
> > > > > No, they are also used by optimized kprobes. This is why optimized
> > > > > kprobes depend on !CONFIG_PREEMPT. [ added Masami to the discussion ].
> > > >
> > > > How do those work? Is that one where the INT3 relocates the instruction
> > > > stream into an alternative 'text' and that JMPs back into the original
> > > > stream at the end?
> > >
> > > No, it's where we replace the 'int3' with a jump to a trampoline that
> > > simulates an INT3. Speeds things up quite a bit.
> >
> > OK, so the trivial 'fix' for that is to patch the probe site like:
> >
> > preempt_disable(); INC GS:%__preempt_count
> > call trampoline; CALL 0xDEADBEEF
> > preempt_enable(); DEC GS:%__preempt_count
> > JNZ 1f
> > CALL ___preempt_schedule
> > 1f:
> >
> > At which point the preempt_disable/enable() are the read side primitives
> > and call_rcu_sched/synchronize_sched are sufficient to release it.
>
> Unless this is done in idle, at which point RCU-sched is studiously
> ignoring any preempt_disable() sections.
Well, given that kprobes is already using it, it 'must' be good ;-) I
suspect much of the idle loop is marked with __kprobe or so, or nobody
has been brave enough to try.
[-- Attachment #2: Type: application/pgp-signature, Size: 836 bytes --]
next prev parent reply other threads:[~2014-08-08 16:51 UTC|newest]
Thread overview: 122+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-07-31 21:54 [PATCH v3 tip/core/rcu 0/9 Paul E. McKenney
2014-07-31 21:55 ` [PATCH v3 tip/core/rcu 1/9] rcu: Add call_rcu_tasks() Paul E. McKenney
2014-07-31 21:55 ` [PATCH v3 tip/core/rcu 2/9] rcu: Provide cond_resched_rcu_qs() to force quiescent states in long loops Paul E. McKenney
2014-07-31 21:55 ` [PATCH v3 tip/core/rcu 3/9] rcu: Add synchronous grace-period waiting for RCU-tasks Paul E. McKenney
2014-08-01 15:09 ` Oleg Nesterov
2014-08-01 18:32 ` Paul E. McKenney
2014-08-01 19:44 ` Paul E. McKenney
2014-08-02 14:47 ` Oleg Nesterov
2014-08-02 22:58 ` Paul E. McKenney
2014-08-06 0:57 ` Steven Rostedt
2014-08-06 1:21 ` Paul E. McKenney
2014-08-06 8:47 ` Peter Zijlstra
2014-08-06 12:09 ` Paul E. McKenney
2014-08-06 16:30 ` Peter Zijlstra
2014-08-06 22:45 ` Paul E. McKenney
2014-08-07 8:45 ` Peter Zijlstra
2014-08-07 15:00 ` Paul E. McKenney
2014-08-07 15:26 ` Peter Zijlstra
2014-08-07 17:27 ` Peter Zijlstra
2014-08-07 18:46 ` Peter Zijlstra
2014-08-07 19:49 ` Steven Rostedt
2014-08-07 19:53 ` Steven Rostedt
2014-08-07 20:08 ` Peter Zijlstra
2014-08-07 21:18 ` Steven Rostedt
2014-08-08 6:40 ` Peter Zijlstra
2014-08-08 14:12 ` Steven Rostedt
2014-08-08 14:28 ` Paul E. McKenney
2014-08-09 10:56 ` Masami Hiramatsu
2014-08-08 14:34 ` Peter Zijlstra
2014-08-08 14:58 ` Steven Rostedt
2014-08-08 15:16 ` Peter Zijlstra
2014-08-08 15:39 ` Steven Rostedt
2014-08-08 16:01 ` Peter Zijlstra
2014-08-08 16:10 ` Steven Rostedt
2014-08-08 16:17 ` Peter Zijlstra
2014-08-08 16:40 ` Steven Rostedt
2014-08-08 16:52 ` Peter Zijlstra
2014-08-08 16:27 ` Peter Zijlstra
2014-08-08 16:39 ` Paul E. McKenney
2014-08-08 16:49 ` Steven Rostedt
2014-08-08 16:51 ` Peter Zijlstra [this message]
2014-08-08 17:09 ` Paul E. McKenney
2014-08-08 16:43 ` Steven Rostedt
2014-08-08 16:50 ` Peter Zijlstra
2014-08-08 17:27 ` Steven Rostedt
2014-08-09 10:36 ` Masami Hiramatsu
2014-08-07 20:06 ` Peter Zijlstra
2014-07-31 21:55 ` [PATCH v3 tip/core/rcu 4/9] rcu: Export RCU-tasks APIs to GPL modules Paul E. McKenney
2014-07-31 21:55 ` [PATCH v3 tip/core/rcu 5/9] rcutorture: Add torture tests for RCU-tasks Paul E. McKenney
2014-07-31 21:55 ` [PATCH v3 tip/core/rcu 6/9] rcutorture: Add RCU-tasks test cases Paul E. McKenney
2014-07-31 21:55 ` [PATCH v3 tip/core/rcu 7/9] rcu: Add stall-warning checks for RCU-tasks Paul E. McKenney
2014-07-31 21:55 ` [PATCH v3 tip/core/rcu 8/9] rcu: Improve RCU-tasks energy efficiency Paul E. McKenney
2014-07-31 21:55 ` [PATCH v3 tip/core/rcu 9/9] documentation: Add verbiage on RCU-tasks stall warning messages Paul E. McKenney
2014-07-31 23:57 ` [PATCH v3 tip/core/rcu 1/9] rcu: Add call_rcu_tasks() Frederic Weisbecker
2014-08-01 2:04 ` Paul E. McKenney
2014-08-01 15:06 ` Frederic Weisbecker
2014-08-01 1:15 ` Lai Jiangshan
2014-08-01 1:59 ` Paul E. McKenney
2014-08-01 1:31 ` Lai Jiangshan
2014-08-01 2:11 ` Paul E. McKenney
2014-08-01 14:11 ` Oleg Nesterov
2014-08-01 18:28 ` Paul E. McKenney
2014-08-01 18:40 ` Oleg Nesterov
2014-08-02 23:00 ` Paul E. McKenney
2014-08-03 12:57 ` Oleg Nesterov
2014-08-03 22:03 ` Paul E. McKenney
2014-08-04 13:29 ` Oleg Nesterov
2014-08-04 13:48 ` Paul E. McKenney
2014-08-01 18:57 ` Oleg Nesterov
2014-08-02 22:50 ` Paul E. McKenney
2014-08-02 14:56 ` Oleg Nesterov
2014-08-02 22:57 ` Paul E. McKenney
2014-08-03 13:33 ` Oleg Nesterov
2014-08-03 22:05 ` Paul E. McKenney
2014-08-04 0:37 ` Lai Jiangshan
2014-08-04 1:09 ` Paul E. McKenney
2014-08-04 13:25 ` Oleg Nesterov
2014-08-04 13:51 ` Paul E. McKenney
2014-08-04 13:52 ` Paul E. McKenney
2014-08-04 13:32 ` Oleg Nesterov
2014-08-04 19:28 ` Paul E. McKenney
2014-08-04 19:32 ` Oleg Nesterov
2014-08-04 1:28 ` Lai Jiangshan
2014-08-04 7:46 ` Peter Zijlstra
2014-08-04 8:18 ` Lai Jiangshan
2014-08-04 11:50 ` Paul E. McKenney
2014-08-04 12:25 ` Peter Zijlstra
2014-08-04 12:37 ` Paul E. McKenney
2014-08-04 14:56 ` Peter Zijlstra
2014-08-05 0:47 ` Lai Jiangshan
2014-08-05 21:55 ` Paul E. McKenney
2014-08-06 0:27 ` Lai Jiangshan
2014-08-06 0:48 ` Paul E. McKenney
2014-08-06 0:33 ` Lai Jiangshan
2014-08-06 0:51 ` Paul E. McKenney
2014-08-06 22:48 ` Paul E. McKenney
2014-08-07 8:49 ` Peter Zijlstra
2014-08-07 15:43 ` Paul E. McKenney
2014-08-07 16:32 ` Peter Zijlstra
2014-08-07 17:48 ` Paul E. McKenney
2014-08-08 19:13 ` Peter Zijlstra
2014-08-08 20:58 ` Paul E. McKenney
2014-08-09 6:15 ` Peter Zijlstra
2014-08-09 12:44 ` Steven Rostedt
2014-08-09 16:05 ` Paul E. McKenney
2014-08-09 16:01 ` Paul E. McKenney
2014-08-09 18:19 ` Peter Zijlstra
2014-08-09 18:24 ` Peter Zijlstra
2014-08-10 1:29 ` Paul E. McKenney
2014-08-10 8:14 ` Peter Zijlstra
2014-08-11 3:30 ` Paul E. McKenney
2014-08-11 11:57 ` Peter Zijlstra
2014-08-11 16:15 ` Paul E. McKenney
2014-08-10 1:26 ` Paul E. McKenney
2014-08-10 8:12 ` Peter Zijlstra
2014-08-10 16:46 ` Peter Zijlstra
2014-08-11 3:28 ` Paul E. McKenney
2014-08-11 3:23 ` Paul E. McKenney
2014-08-09 18:33 ` Peter Zijlstra
2014-08-10 1:38 ` Paul E. McKenney
2014-08-10 15:00 ` Peter Zijlstra
2014-08-11 3:37 ` 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=20140808165112.GI9918@twins.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=akpm@linux-foundation.org \
--cc=bobby.prani@gmail.com \
--cc=dhowells@redhat.com \
--cc=dipankar@in.ibm.com \
--cc=dvhart@linux.intel.com \
--cc=edumazet@google.com \
--cc=fweisbec@gmail.com \
--cc=josh@joshtriplett.org \
--cc=laijs@cn.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=masami.hiramatsu.pt@hitachi.com \
--cc=mathieu.desnoyers@efficios.com \
--cc=mingo@kernel.org \
--cc=oleg@redhat.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
/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.