From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: linux-kernel@vger.kernel.org
Cc: 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,
peterz@infradead.org, rostedt@goodmis.org,
Valdis.Kletnieks@vt.edu, dhowells@redhat.com,
eric.dumazet@gmail.com, darren@dvhart.com, patches@linaro.org,
greearb@candelatech.com, edt@aei.ca,
"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Subject: [PATCH tip/core/urgent 3/7] rcu: Streamline code produced by __rcu_read_unlock()
Date: Wed, 20 Jul 2011 11:26:19 -0700 [thread overview]
Message-ID: <1311186383-24819-3-git-send-email-paulmck@linux.vnet.ibm.com> (raw)
In-Reply-To: <20110720182512.GA22946@linux.vnet.ibm.com>
Given some common flag combinations, particularly -Os, gcc will inline
rcu_read_unlock_special() despite its being in an unlikely() clause.
Use noinline to prohibit this misoptimization.
In addition, move the second barrier() in __rcu_read_unlock() so that
it is not on the common-case code path. This will allow the compiler to
generate better code for the common-case path through __rcu_read_unlock().
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
---
kernel/rcutree_plugin.h | 12 ++++++------
1 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 3a0ae03..4d2c068 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -284,7 +284,7 @@ static struct list_head *rcu_next_node_entry(struct task_struct *t,
* notify RCU core processing or task having blocked during the RCU
* read-side critical section.
*/
-static void rcu_read_unlock_special(struct task_struct *t)
+static noinline void rcu_read_unlock_special(struct task_struct *t)
{
int empty;
int empty_exp;
@@ -391,11 +391,11 @@ void __rcu_read_unlock(void)
struct task_struct *t = current;
barrier(); /* needed if we ever invoke rcu_read_unlock in rcutree.c */
- --t->rcu_read_lock_nesting;
- barrier(); /* decrement before load of ->rcu_read_unlock_special */
- if (t->rcu_read_lock_nesting == 0 &&
- unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
- rcu_read_unlock_special(t);
+ if (--t->rcu_read_lock_nesting == 0) {
+ barrier(); /* decr before ->rcu_read_unlock_special load */
+ if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
+ rcu_read_unlock_special(t);
+ }
#ifdef CONFIG_PROVE_LOCKING
WARN_ON_ONCE(ACCESS_ONCE(t->rcu_read_lock_nesting) < 0);
#endif /* #ifdef CONFIG_PROVE_LOCKING */
--
1.7.3.2
next prev parent reply other threads:[~2011-07-20 18:26 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-07-20 0:17 [PATCH rcu/urgent 0/6] Fixes for RCU/scheduler/irq-threads trainwreck Paul E. McKenney
2011-07-20 0:18 ` [PATCH tip/core/urgent 1/7] rcu: decrease rcu_report_exp_rnp coupling with scheduler Paul E. McKenney
2011-07-20 2:40 ` Peter Zijlstra
2011-07-20 4:54 ` Paul E. McKenney
2011-07-20 11:23 ` Ed Tomlinson
2011-07-20 11:31 ` Ed Tomlinson
2011-07-20 12:35 ` Peter Zijlstra
2011-07-20 13:23 ` Paul E. McKenney
2011-07-20 0:18 ` [PATCH tip/core/urgent 2/7] rcu: Fix RCU_BOOST race handling current->rcu_read_unlock_special Paul E. McKenney
2011-07-20 0:18 ` [PATCH tip/core/urgent 3/7] rcu: Streamline code produced by __rcu_read_unlock() Paul E. McKenney
2011-07-20 0:18 ` [PATCH tip/core/urgent 4/7] rcu: protect __rcu_read_unlock() against scheduler-using irq handlers Paul E. McKenney
2011-07-20 12:54 ` Peter Zijlstra
2011-07-20 13:25 ` Paul E. McKenney
2011-07-20 0:18 ` [PATCH tip/core/urgent 5/7] sched: Add irq_{enter,exit}() to scheduler_ipi() Paul E. McKenney
2011-07-20 0:18 ` [PATCH tip/core/urgent 6/7] softirq,rcu: Inform RCU of irq_exit() activity Paul E. McKenney
2011-07-20 0:18 ` [PATCH tip/core/urgent 7/7] signal: align __lock_task_sighand() irq disabling and RCU Paul E. McKenney
2011-07-20 1:10 ` [PATCH rcu/urgent 0/6] Fixes for RCU/scheduler/irq-threads trainwreck Ben Greear
2011-07-20 1:30 ` Ed Tomlinson
2011-07-20 2:07 ` Ed Tomlinson
2011-07-20 4:44 ` Paul E. McKenney
2011-07-20 5:03 ` Linus Torvalds
2011-07-20 13:34 ` Paul E. McKenney
2011-07-20 17:02 ` Ben Greear
2011-07-20 17:15 ` Paul E. McKenney
2011-07-20 18:44 ` Ingo Molnar
2011-07-20 18:52 ` Peter Zijlstra
2011-07-20 19:01 ` Paul E. McKenney
2011-07-20 19:25 ` Peter Zijlstra
2011-07-20 20:06 ` Paul E. McKenney
2011-07-20 19:02 ` Linus Torvalds
2011-07-20 19:29 ` Paul E. McKenney
2011-07-20 19:39 ` Ingo Molnar
2011-07-20 19:57 ` Ingo Molnar
2011-07-20 20:33 ` Paul E. McKenney
2011-07-20 20:54 ` Ben Greear
2011-07-20 21:12 ` Paul E. McKenney
2011-07-21 3:25 ` Ben Greear
2011-07-21 16:04 ` Paul E. McKenney
2011-07-20 21:04 ` [GIT PULL] RCU fixes for v3.0 Ingo Molnar
2011-07-20 21:55 ` Ed Tomlinson
2011-07-20 22:06 ` Paul E. McKenney
2011-07-20 20:08 ` [PATCH rcu/urgent 0/6] Fixes for RCU/scheduler/irq-threads trainwreck Paul E. McKenney
2011-07-20 21:05 ` Peter Zijlstra
2011-07-20 21:39 ` Paul E. McKenney
2011-07-20 10:49 ` Ed Tomlinson
2011-07-20 18:25 ` [PATCH rcu/urgent 0/7 v2] " Paul E. McKenney
2011-07-20 18:26 ` [PATCH tip/core/urgent 1/7] rcu: decrease rcu_report_exp_rnp coupling with scheduler Paul E. McKenney
2011-07-20 18:26 ` [PATCH tip/core/urgent 2/7] rcu: Fix RCU_BOOST race handling current->rcu_read_unlock_special Paul E. McKenney
2011-07-20 18:26 ` Paul E. McKenney [this message]
2011-07-20 22:44 ` [PATCH tip/core/urgent 3/7] rcu: Streamline code produced by __rcu_read_unlock() Linus Torvalds
2011-07-21 5:09 ` Paul E. McKenney
2011-07-20 18:26 ` [PATCH tip/core/urgent 4/7] rcu: protect __rcu_read_unlock() against scheduler-using irq handlers Paul E. McKenney
2011-07-20 18:26 ` [PATCH tip/core/urgent 5/7] sched: Add irq_{enter,exit}() to scheduler_ipi() Paul E. McKenney
2011-07-20 18:26 ` [PATCH tip/core/urgent 6/7] softirq,rcu: Inform RCU of irq_exit() activity Paul E. McKenney
2011-07-20 18:26 ` [PATCH tip/core/urgent 7/7] signal: align __lock_task_sighand() irq disabling and RCU 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=1311186383-24819-3-git-send-email-paulmck@linux.vnet.ibm.com \
--to=paulmck@linux.vnet.ibm.com \
--cc=Valdis.Kletnieks@vt.edu \
--cc=akpm@linux-foundation.org \
--cc=darren@dvhart.com \
--cc=dhowells@redhat.com \
--cc=dipankar@in.ibm.com \
--cc=edt@aei.ca \
--cc=eric.dumazet@gmail.com \
--cc=greearb@candelatech.com \
--cc=josh@joshtriplett.org \
--cc=laijs@cn.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mathieu.desnoyers@polymtl.ca \
--cc=mingo@elte.hu \
--cc=niv@us.ibm.com \
--cc=patches@linaro.org \
--cc=peterz@infradead.org \
--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 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®