All of lore.kernel.org
 help / color / mirror / Atom feed
From: Ingo Molnar <mingo@elte.hu>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-kernel@vger.kernel.org,
	"Paul E. McKenney" <paulmck@us.ibm.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Andrew Morton <akpm@linux-foundation.org>
Subject: [GIT PULL] core kernel fixes
Date: Sat, 15 Jan 2011 16:15:15 +0100	[thread overview]
Message-ID: <20110115151515.GA11124@elte.hu> (raw)

Linus,

Please pull the latest core-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git core-fixes-for-linus

 Thanks,

	Ingo

------------------>
Paul E. McKenney (2):
      rcu: demote SRCU_SYNCHRONIZE_DELAY from kernel-parameter status
      rcu: avoid pointless blocked-task warnings

Steven Rostedt (1):
      rtmutex: Fix comment about why new_owner can be NULL in wake_futex_pi()


 init/Kconfig     |   15 ---------------
 kernel/futex.c   |    7 +++----
 kernel/rcutiny.c |    3 ++-
 kernel/srcu.c    |   15 +++++++++++++--
 4 files changed, 18 insertions(+), 22 deletions(-)

diff --git a/init/Kconfig b/init/Kconfig
index 8dfd094..bd1ea92 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -497,21 +497,6 @@ config RCU_BOOST_DELAY
 
 	  Accept the default if unsure.
 
-config SRCU_SYNCHRONIZE_DELAY
-	int "Microseconds to delay before waiting for readers"
-	range 0 20
-	default 10
-	help
-	  This option controls how long SRCU delays before entering its
-	  loop waiting on SRCU readers.  The purpose of this loop is
-	  to avoid the unconditional context-switch penalty that would
-	  otherwise be incurred if there was an active SRCU reader,
-	  in a manner similar to adaptive locking schemes.  This should
-	  be set to be a bit longer than the common-case SRCU read-side
-	  critical-section overhead.
-
-	  Accept the default if unsure.
-
 endmenu # "RCU Subsystem"
 
 config IKCONFIG
diff --git a/kernel/futex.c b/kernel/futex.c
index 3019b92..5696d38 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -791,10 +791,9 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
 	new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
 
 	/*
-	 * This happens when we have stolen the lock and the original
-	 * pending owner did not enqueue itself back on the rt_mutex.
-	 * Thats not a tragedy. We know that way, that a lock waiter
-	 * is on the fly. We make the futex_q waiter the pending owner.
+	 * It is possible that the next waiter (the one that brought
+	 * this owner to the kernel) timed out and is no longer
+	 * waiting on the lock.
 	 */
 	if (!new_owner)
 		new_owner = this->task;
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index 0344937..0c343b9 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -189,7 +189,8 @@ static int rcu_kthread(void *arg)
 	unsigned long flags;
 
 	for (;;) {
-		wait_event(rcu_kthread_wq, have_rcu_kthread_work != 0);
+		wait_event_interruptible(rcu_kthread_wq,
+					 have_rcu_kthread_work != 0);
 		morework = rcu_boost();
 		local_irq_save(flags);
 		work = have_rcu_kthread_work;
diff --git a/kernel/srcu.c b/kernel/srcu.c
index 98d8c1e..73ce23f 100644
--- a/kernel/srcu.c
+++ b/kernel/srcu.c
@@ -156,6 +156,16 @@ void __srcu_read_unlock(struct srcu_struct *sp, int idx)
 EXPORT_SYMBOL_GPL(__srcu_read_unlock);
 
 /*
+ * We use an adaptive strategy for synchronize_srcu() and especially for
+ * synchronize_srcu_expedited().  We spin for a fixed time period
+ * (defined below) to allow SRCU readers to exit their read-side critical
+ * sections.  If there are still some readers after 10 microseconds,
+ * we repeatedly block for 1-millisecond time periods.  This approach
+ * has done well in testing, so there is no need for a config parameter.
+ */
+#define SYNCHRONIZE_SRCU_READER_DELAY 10
+
+/*
  * Helper function for synchronize_srcu() and synchronize_srcu_expedited().
  */
 static void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void))
@@ -207,11 +217,12 @@ static void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void))
 	 * will have finished executing.  We initially give readers
 	 * an arbitrarily chosen 10 microseconds to get out of their
 	 * SRCU read-side critical sections, then loop waiting 1/HZ
-	 * seconds per iteration.
+	 * seconds per iteration.  The 10-microsecond value has done
+	 * very well in testing.
 	 */
 
 	if (srcu_readers_active_idx(sp, idx))
-		udelay(CONFIG_SRCU_SYNCHRONIZE_DELAY);
+		udelay(SYNCHRONIZE_SRCU_READER_DELAY);
 	while (srcu_readers_active_idx(sp, idx))
 		schedule_timeout_interruptible(1);
 

             reply	other threads:[~2011-01-15 15:15 UTC|newest]

Thread overview: 79+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-01-15 15:15 Ingo Molnar [this message]
  -- strict thread matches above, loose matches on Subject: below --
2012-10-23 10:57 [GIT PULL] core kernel fixes Ingo Molnar
2012-08-03 16:31 Ingo Molnar
2012-08-03 16:55 ` Darren Hart
2012-08-03 17:01   ` Ingo Molnar
2012-08-03 17:24     ` Darren Hart
2012-06-15 18:45 Ingo Molnar
2012-01-26 18:05 Ingo Molnar
2011-08-04 20:45 Ingo Molnar
2011-04-02 10:21 Ingo Molnar
2011-03-25 12:52 Ingo Molnar
2011-01-21  2:11 Ingo Molnar
2010-10-05 19:12 Ingo Molnar
2010-10-05 20:15 ` Linus Torvalds
2010-10-05 21:09   ` Paul E. McKenney
2010-10-05 21:45     ` Linus Torvalds
2010-10-05 22:05       ` Paul E. McKenney
2010-10-06  2:56         ` Eric Dumazet
2010-10-06  4:59           ` Paul E. McKenney
2010-10-06 18:20             ` Ingo Molnar
2010-10-06 21:27               ` Paul E. McKenney
2010-10-07  8:11                 ` Ingo Molnar
2010-10-07 17:42                   ` Paul E. McKenney
2010-09-08 13:04 Ingo Molnar
2010-03-26 14:53 Ingo Molnar
2010-03-13 16:35 Ingo Molnar
2009-12-18 18:52 Ingo Molnar
2009-11-10 17:53 Ingo Molnar
2009-10-23 14:53 Ingo Molnar
2009-10-13 18:29 Ingo Molnar
2009-10-08 19:06 Ingo Molnar
2009-10-08 19:16 ` Linus Torvalds
2009-10-08 19:20   ` Ingo Molnar
2009-09-21 13:13 Ingo Molnar
2009-08-13 18:54 Ingo Molnar
2009-08-09 16:07 Ingo Molnar
2009-08-09 18:41 ` Darren Hart
2009-07-10 16:28 Ingo Molnar
2009-07-10 19:06 ` Linus Torvalds
2009-07-10 19:31   ` Ingo Molnar
2009-07-10 19:52     ` Linus Torvalds
2009-07-10 20:02       ` Ingo Molnar
2009-07-13 14:52   ` Joerg Roedel
2009-06-20 17:30 Ingo Molnar
2009-06-20 18:49 ` Linus Torvalds
2009-06-20 19:01   ` Linus Torvalds
2009-06-20 20:27     ` Ingo Molnar
2009-06-21 17:12     ` Thomas Gleixner
2009-06-21 17:37       ` Linus Torvalds
2009-06-21 17:57         ` Linus Torvalds
2009-06-21 19:26           ` Thomas Gleixner
2009-05-18 14:23 Ingo Molnar
2009-05-18 15:48 ` Linus Torvalds
2009-05-18 19:20   ` Thomas Gleixner
2009-05-19 20:52     ` Linus Torvalds
2009-05-19 21:45       ` Thomas Gleixner
2009-05-19 22:20     ` Darren Hart
2009-05-05  9:33 Ingo Molnar
2009-01-30 23:12 [git pull] " Ingo Molnar
2009-01-26 17:24 Ingo Molnar
2009-01-11 14:36 Ingo Molnar
2008-12-04 19:39 Ingo Molnar
2008-11-29 19:36 Ingo Molnar
2008-11-18 14:14 Ingo Molnar
2008-11-07 16:28 Ingo Molnar
2008-10-30 23:29 Ingo Molnar
2008-10-15 12:50 [git pull] core kernel updates for v2.6.28 Ingo Molnar
2008-10-16 22:32 ` Linus Torvalds
2008-10-17  6:23   ` [git pull] core kernel fixes Ingo Molnar
2008-08-28 11:44 Ingo Molnar
2008-08-18 18:35 Ingo Molnar
2008-07-24 15:13 Ingo Molnar
2008-06-30 15:32 Ingo Molnar
2008-06-30 17:02 ` Vegard Nossum
2008-06-30 18:20   ` Ingo Molnar
2008-06-30 18:43     ` Vegard Nossum
2008-06-30 19:46       ` Thomas Gleixner
2008-06-30 19:51         ` Vegard Nossum
2008-06-30 19:54           ` Thomas Gleixner
2008-06-23 19:45 Ingo Molnar
2008-06-19 15:16 Ingo Molnar

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=20110115151515.GA11124@elte.hu \
    --to=mingo@elte.hu \
    --cc=a.p.zijlstra@chello.nl \
    --cc=akpm@linux-foundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=paulmck@us.ibm.com \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.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.