All of lore.kernel.org
 help / color / mirror / Atom feed
From: Lai Jiangshan <laijs@cn.fujitsu.com>
To: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Peter Zijlstra <peterz@infradead.org>,
	linux-kernel@vger.kernel.org
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>,
	Dipankar Sarma <dipankar@in.ibm.com>
Subject: [PATCH 3/8] rcu: keep irqs disabled in rcu_read_unlock_special()
Date: Wed, 7 Aug 2013 18:24:59 +0800	[thread overview]
Message-ID: <1375871104-10688-4-git-send-email-laijs@cn.fujitsu.com> (raw)
In-Reply-To: <1375871104-10688-1-git-send-email-laijs@cn.fujitsu.com>

rcu_read_unlock_special() may enable irqs temporarily before it finish its
last work. It doesn't introduce any extremely bad things. but it does
add more task rcu machine states and add more complexity, bad to review.

And if the task is preempted when it enables irqs,
the synchronize_rcu_expedited() will be slowed down, and it can't get help
from rcu_boost.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
---
 kernel/rcutree_plugin.h |   13 ++++++++-----
 1 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 54f7e45..6b23b6f 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -338,7 +338,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 	int empty;
 	int empty_exp;
 	int empty_exp_now;
-	unsigned long flags;
+	unsigned long flags, irq_disabled_flags;
 	struct list_head *np;
 #ifdef CONFIG_RCU_BOOST
 	struct rt_mutex *rbmp = NULL;
@@ -351,6 +351,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 		return;
 
 	local_irq_save(flags);
+	local_save_flags(irq_disabled_flags);
 
 	/*
 	 * If RCU core is waiting for this CPU to exit critical section,
@@ -414,9 +415,12 @@ void rcu_read_unlock_special(struct task_struct *t)
 							 rnp->grplo,
 							 rnp->grphi,
 							 !!rnp->gp_tasks);
-			rcu_report_unblock_qs_rnp(rnp, flags);
+			rcu_report_unblock_qs_rnp(rnp, irq_disabled_flags);
+			/* irqs remain disabled. */
 		} else {
-			raw_spin_unlock_irqrestore(&rnp->lock, flags);
+			raw_spin_unlock_irqrestore(&rnp->lock,
+						   irq_disabled_flags);
+			/* irqs remain disabled. */
 		}
 
 #ifdef CONFIG_RCU_BOOST
@@ -431,9 +435,8 @@ void rcu_read_unlock_special(struct task_struct *t)
 		 */
 		if (!empty_exp && empty_exp_now)
 			rcu_report_exp_rnp(&rcu_preempt_state, rnp, true);
-	} else {
-		local_irq_restore(flags);
 	}
+	local_irq_restore(flags);
 }
 
 #ifdef CONFIG_RCU_CPU_STALL_VERBOSE
-- 
1.7.4.4


  parent reply	other threads:[~2013-08-07 10:21 UTC|newest]

Thread overview: 49+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-08-07 10:24 [PATCH 0/8] rcu: Ensure rcu read site is deadlock-immunity Lai Jiangshan
2013-08-07 10:24 ` [PATCH 1/8] rcu: add a warn to rcu_preempt_note_context_switch() Lai Jiangshan
2013-10-30 11:02   ` Paul E. McKenney
2013-08-07 10:24 ` [PATCH 2/8] rcu: remove irq/softirq context check in rcu_read_unlock_special() Lai Jiangshan
2013-10-30 11:18   ` Paul E. McKenney
2013-08-07 10:24 ` Lai Jiangshan [this message]
2013-08-07 10:25 ` [PATCH 4/8] rcu: delay task rcu state cleanup in exit_rcu() Lai Jiangshan
2013-08-07 10:25 ` [PATCH 5/8] rcu: eliminate deadlock for rcu read site Lai Jiangshan
2013-08-08 20:40   ` Paul E. McKenney
2013-08-09  9:31     ` Lai Jiangshan
2013-08-09 17:58       ` Paul E. McKenney
2013-08-12 13:55       ` Peter Zijlstra
2013-08-12 15:16         ` Paul E. McKenney
2013-08-12 16:21           ` Peter Zijlstra
2013-08-12 16:44             ` Paul E. McKenney
2013-08-10  3:43     ` Lai Jiangshan
2013-08-10 15:07       ` Paul E. McKenney
2013-08-10 15:08         ` Paul E. McKenney
2013-08-21  3:17         ` Paul E. McKenney
2013-08-21  3:25           ` Lai Jiangshan
2013-08-21 13:42             ` Paul E. McKenney
2013-08-12 13:53       ` Peter Zijlstra
2013-08-12 14:10         ` Steven Rostedt
2013-08-12 14:14           ` Peter Zijlstra
     [not found]           ` <CACvQF51-oAGkdxwku+orKSQ=SZd1A4saXzkrgcRGi+KnZUZYxQ@mail.gmail.com>
2013-08-22 14:34             ` Steven Rostedt
2013-08-22 14:41               ` Steven Rostedt
2013-08-23  6:26               ` Lai Jiangshan
     [not found]                 ` <CACvQF51kcLrJsa=zBKhLkJfFBh109TW+Zrepm+tRxmEp0gALbQ@mail.gmail.com>
2013-08-25 17:43                   ` Paul E. McKenney
2013-08-26  2:39                     ` Lai Jiangshan
2013-08-30  2:05                       ` Paul E. McKenney
2013-09-05 15:22                 ` Steven Rostedt
2013-08-07 10:25 ` [PATCH 6/8] rcu: call rcu_read_unlock_special() in rcu_preempt_check_callbacks() Lai Jiangshan
2013-08-07 10:25 ` [PATCH 7/8] rcu: add # of deferred _special() statistics Lai Jiangshan
2013-08-07 16:42   ` Paul E. McKenney
2013-08-07 10:25 ` [PATCH 8/8] rcu: remove irq work for rsp_wakeup() Lai Jiangshan
2013-08-07 12:38 ` [PATCH 0/8] rcu: Ensure rcu read site is deadlock-immunity Paul E. McKenney
2013-08-07 19:29   ` Carsten Emde
2013-08-07 19:52     ` Paul E. McKenney
2013-08-08  1:17     ` Lai Jiangshan
2013-08-08  0:36   ` Paul E. McKenney
2013-08-08  1:47     ` Lai Jiangshan
2013-08-08  2:12       ` Steven Rostedt
2013-08-08  2:33         ` Lai Jiangshan
2013-08-08  2:33           ` Paul E. McKenney
2013-08-08  3:10             ` Lai Jiangshan
2013-08-08  4:18               ` Paul E. McKenney
2013-08-08  5:27                 ` Lai Jiangshan
2013-08-08  7:05                   ` Paul E. McKenney
2013-08-08  2:45         ` Lai Jiangshan

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=1375871104-10688-4-git-send-email-laijs@cn.fujitsu.com \
    --to=laijs@cn.fujitsu.com \
    --cc=dipankar@in.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.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.