linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
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, fweisbec@gmail.com,
	sbw@mit.edu, patches@linaro.org,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Subject: [PATCH tip/core/rcu 03/23] rcu: Move RCU grace-period cleanup into kthread
Date: Thu, 30 Aug 2012 11:18:18 -0700	[thread overview]
Message-ID: <1346350718-30937-3-git-send-email-paulmck@linux.vnet.ibm.com> (raw)
In-Reply-To: <1346350718-30937-1-git-send-email-paulmck@linux.vnet.ibm.com>

From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>

As a first step towards allowing grace-period cleanup to be preemptible,
this commit moves the RCU grace-period cleanup into the same kthread
that is now used to initialize grace periods.  This is needed to keep
scheduling latency down to a dull roar.

Reported-by: Mike Galbraith <mgalbraith@suse.de>
Reported-by: Dimitri Sivanich <sivanich@sgi.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcutree.c |  112 ++++++++++++++++++++++++++++++------------------------
 1 files changed, 62 insertions(+), 50 deletions(-)

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index ef56aa3..9fad21c 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1045,6 +1045,7 @@ rcu_start_gp_per_cpu(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_dat
 static int rcu_gp_kthread(void *arg)
 {
 	unsigned long flags;
+	unsigned long gp_duration;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
 	struct rcu_state *rsp = arg;
@@ -1135,6 +1136,65 @@ static int rcu_gp_kthread(void *arg)
 		rsp->fqs_state = RCU_SIGNAL_INIT;
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		put_online_cpus();
+
+		/* Handle grace-period end. */
+		rnp = rcu_get_root(rsp);
+		for (;;) {
+			wait_event_interruptible(rsp->gp_wq,
+						 !ACCESS_ONCE(rnp->qsmask) &&
+						 !rcu_preempt_blocked_readers_cgp(rnp));
+			if (!ACCESS_ONCE(rnp->qsmask) &&
+			    !rcu_preempt_blocked_readers_cgp(rnp))
+				break;
+			flush_signals(current);
+		}
+
+		raw_spin_lock_irqsave(&rnp->lock, flags);
+		gp_duration = jiffies - rsp->gp_start;
+		if (gp_duration > rsp->gp_max)
+			rsp->gp_max = gp_duration;
+
+		/*
+		 * We know the grace period is complete, but to everyone else
+		 * it appears to still be ongoing.  But it is also the case
+		 * that to everyone else it looks like there is nothing that
+		 * they can do to advance the grace period.  It is therefore
+		 * safe for us to drop the lock in order to mark the grace
+		 * period as completed in all of the rcu_node structures.
+		 *
+		 * But if this CPU needs another grace period, it will take
+		 * care of this while initializing the next grace period.
+		 * We use RCU_WAIT_TAIL instead of the usual RCU_DONE_TAIL
+		 * because the callbacks have not yet been advanced: Those
+		 * callbacks are waiting on the grace period that just now
+		 * completed.
+		 */
+		if (*rdp->nxttail[RCU_WAIT_TAIL] == NULL) {
+			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
+
+			/*
+			 * Propagate new ->completed value to rcu_node
+			 * structures so that other CPUs don't have to
+			 * wait until the start of the next grace period
+			 * to process their callbacks.
+			 */
+			rcu_for_each_node_breadth_first(rsp, rnp) {
+				/* irqs already disabled. */
+				raw_spin_lock(&rnp->lock);
+				rnp->completed = rsp->gpnum;
+				/* irqs remain disabled. */
+				raw_spin_unlock(&rnp->lock);
+			}
+			rnp = rcu_get_root(rsp);
+			raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+		}
+
+		rsp->completed = rsp->gpnum; /* Declare grace period done. */
+		trace_rcu_grace_period(rsp->name, rsp->completed, "end");
+		rsp->fqs_state = RCU_GP_IDLE;
+		if (cpu_needs_another_gp(rsp, rdp))
+			rsp->gp_flags = 1;
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	}
 	return 0;
 }
@@ -1182,57 +1242,9 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
 static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
 	__releases(rcu_get_root(rsp)->lock)
 {
-	unsigned long gp_duration;
-	struct rcu_node *rnp = rcu_get_root(rsp);
-	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
-
 	WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
-
-	/*
-	 * Ensure that all grace-period and pre-grace-period activity
-	 * is seen before the assignment to rsp->completed.
-	 */
-	smp_mb(); /* See above block comment. */
-	gp_duration = jiffies - rsp->gp_start;
-	if (gp_duration > rsp->gp_max)
-		rsp->gp_max = gp_duration;
-
-	/*
-	 * We know the grace period is complete, but to everyone else
-	 * it appears to still be ongoing.  But it is also the case
-	 * that to everyone else it looks like there is nothing that
-	 * they can do to advance the grace period.  It is therefore
-	 * safe for us to drop the lock in order to mark the grace
-	 * period as completed in all of the rcu_node structures.
-	 *
-	 * But if this CPU needs another grace period, it will take
-	 * care of this while initializing the next grace period.
-	 * We use RCU_WAIT_TAIL instead of the usual RCU_DONE_TAIL
-	 * because the callbacks have not yet been advanced: Those
-	 * callbacks are waiting on the grace period that just now
-	 * completed.
-	 */
-	if (*rdp->nxttail[RCU_WAIT_TAIL] == NULL) {
-		raw_spin_unlock(&rnp->lock);	 /* irqs remain disabled. */
-
-		/*
-		 * Propagate new ->completed value to rcu_node structures
-		 * so that other CPUs don't have to wait until the start
-		 * of the next grace period to process their callbacks.
-		 */
-		rcu_for_each_node_breadth_first(rsp, rnp) {
-			raw_spin_lock(&rnp->lock); /* irqs already disabled. */
-			rnp->completed = rsp->gpnum;
-			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
-		}
-		rnp = rcu_get_root(rsp);
-		raw_spin_lock(&rnp->lock); /* irqs already disabled. */
-	}
-
-	rsp->completed = rsp->gpnum;  /* Declare the grace period complete. */
-	trace_rcu_grace_period(rsp->name, rsp->completed, "end");
-	rsp->fqs_state = RCU_GP_IDLE;
-	rcu_start_gp(rsp, flags);  /* releases root node's rnp->lock. */
+	raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
+	wake_up(&rsp->gp_wq);  /* Memory barrier implied by wake_up() path. */
 }
 
 /*
-- 
1.7.8


  parent reply	other threads:[~2012-08-30 18:19 UTC|newest]

Thread overview: 85+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-08-30 18:18 [PATCH tip/core/rcu 0/23] Improvements to RT response on big systems and expedited functions Paul E. McKenney
2012-08-30 18:18 ` [PATCH tip/core/rcu 01/23] rcu: Move RCU grace-period initialization into a kthread Paul E. McKenney
2012-08-30 18:18   ` [PATCH tip/core/rcu 02/23] rcu: Allow RCU grace-period initialization to be preempted Paul E. McKenney
2012-09-02  1:09     ` Josh Triplett
2012-09-05  1:22       ` Paul E. McKenney
2012-08-30 18:18   ` Paul E. McKenney [this message]
2012-09-02  1:22     ` [PATCH tip/core/rcu 03/23] rcu: Move RCU grace-period cleanup into kthread Josh Triplett
2012-09-06 13:34     ` Peter Zijlstra
2012-09-06 17:29       ` Paul E. McKenney
2012-08-30 18:18   ` [PATCH tip/core/rcu 04/23] rcu: Allow RCU grace-period cleanup to be preempted Paul E. McKenney
2012-09-02  1:36     ` Josh Triplett
2012-08-30 18:18   ` [PATCH tip/core/rcu 05/23] rcu: Prevent offline CPUs from executing RCU core code Paul E. McKenney
2012-09-02  1:45     ` Josh Triplett
2012-08-30 18:18   ` [PATCH tip/core/rcu 06/23] rcu: Break up rcu_gp_kthread() into subfunctions Paul E. McKenney
2012-09-02  2:11     ` Josh Triplett
2012-09-06 13:39     ` Peter Zijlstra
2012-09-06 17:32       ` Paul E. McKenney
2012-09-06 18:49         ` Josh Triplett
2012-09-06 19:09           ` Peter Zijlstra
2012-09-06 20:30             ` Paul E. McKenney
2012-09-06 20:30           ` Paul E. McKenney
2012-08-30 18:18   ` [PATCH tip/core/rcu 07/23] rcu: Provide OOM handler to motivate lazy RCU callbacks Paul E. McKenney
2012-09-02  2:13     ` Josh Triplett
2012-09-03  9:08     ` Lai Jiangshan
2012-09-05 17:45       ` Paul E. McKenney
2012-09-06 13:46     ` Peter Zijlstra
2012-09-06 13:52       ` Steven Rostedt
2012-09-06 17:41         ` Paul E. McKenney
2012-09-06 17:46           ` Peter Zijlstra
2012-09-06 20:32             ` Paul E. McKenney
2012-08-30 18:18   ` [PATCH tip/core/rcu 08/23] rcu: Segregate rcu_state fields to improve cache locality Paul E. McKenney
2012-09-02  2:51     ` Josh Triplett
2012-08-30 18:18   ` [PATCH tip/core/rcu 09/23] rcu: Move quiescent-state forcing into kthread Paul E. McKenney
2012-08-30 18:18   ` [PATCH tip/core/rcu 10/23] rcu: Allow RCU quiescent-state forcing to be preempted Paul E. McKenney
2012-09-02  5:23     ` Josh Triplett
2012-08-30 18:18   ` [PATCH tip/core/rcu 11/23] rcu: Adjust debugfs tracing for kthread-based quiescent-state forcing Paul E. McKenney
2012-09-02  6:05     ` Josh Triplett
2012-08-30 18:18   ` [PATCH tip/core/rcu 12/23] rcu: Prevent force_quiescent_state() memory contention Paul E. McKenney
2012-09-02 10:47     ` Josh Triplett
2012-08-30 18:18   ` [PATCH tip/core/rcu 13/23] rcu: Control grace-period duration from sysfs Paul E. McKenney
2012-09-03  9:30     ` Josh Triplett
2012-09-03  9:31       ` Josh Triplett
2012-09-06 14:15     ` Peter Zijlstra
2012-09-06 17:53       ` Paul E. McKenney
2012-09-06 18:28         ` Peter Zijlstra
2012-09-06 20:37           ` Paul E. McKenney
2012-08-30 18:18   ` [PATCH tip/core/rcu 14/23] rcu: Remove now-unused rcu_state fields Paul E. McKenney
2012-09-03  9:31     ` Josh Triplett
2012-09-06 14:17     ` Peter Zijlstra
2012-09-06 18:02       ` Paul E. McKenney
2012-08-30 18:18   ` [PATCH tip/core/rcu 15/23] rcu: Make rcutree module parameters visible in sysfs Paul E. McKenney
2012-09-03  9:32     ` Josh Triplett
2012-08-30 18:18   ` [PATCH tip/core/rcu 16/23] rcu: Prevent initialization-time quiescent-state race Paul E. McKenney
2012-09-03  9:37     ` Josh Triplett
2012-09-05 18:19       ` Paul E. McKenney
2012-09-05 18:55         ` Josh Triplett
2012-09-05 19:49           ` Paul E. McKenney
2012-09-06 14:21         ` Peter Zijlstra
2012-09-06 16:18           ` Paul E. McKenney
2012-09-06 16:22             ` Peter Zijlstra
2012-08-30 18:18   ` [PATCH tip/core/rcu 17/23] rcu: Fix day-zero grace-period initialization/cleanup race Paul E. McKenney
2012-09-03  9:39     ` Josh Triplett
2012-09-06 14:24     ` Peter Zijlstra
2012-09-06 18:06       ` Paul E. McKenney
2012-08-30 18:18   ` [PATCH tip/core/rcu 18/23] rcu: Add random PROVE_RCU_DELAY to grace-period initialization Paul E. McKenney
2012-09-03  9:41     ` Josh Triplett
2012-09-06 14:27     ` Peter Zijlstra
2012-09-06 18:25       ` Paul E. McKenney
2012-08-30 18:18   ` [PATCH tip/core/rcu 19/23] rcu: Adjust for unconditional ->completed assignment Paul E. McKenney
2012-09-03  9:42     ` Josh Triplett
2012-08-30 18:18   ` [PATCH tip/core/rcu 20/23] rcu: Remove callback acceleration from grace-period initialization Paul E. McKenney
2012-09-03  9:42     ` Josh Triplett
2012-08-30 18:18   ` [PATCH tip/core/rcu 21/23] rcu: Eliminate signed overflow in synchronize_rcu_expedited() Paul E. McKenney
2012-09-03  9:43     ` Josh Triplett
2012-08-30 18:18   ` [PATCH tip/core/rcu 22/23] rcu: Reduce synchronize_rcu_expedited() latency Paul E. McKenney
2012-09-03  9:46     ` Josh Triplett
2012-08-30 18:18   ` [PATCH tip/core/rcu 23/23] rcu: Simplify quiescent-state detection Paul E. McKenney
2012-09-03  9:56     ` Josh Triplett
2012-09-06 14:36     ` Peter Zijlstra
2012-09-06 20:01       ` Paul E. McKenney
2012-09-06 21:18         ` Mathieu Desnoyers
2012-09-06 21:31           ` Paul E. McKenney
2012-09-02  1:04   ` [PATCH tip/core/rcu 01/23] rcu: Move RCU grace-period initialization into a kthread Josh Triplett
2012-09-06 13:32   ` Peter Zijlstra
2012-09-06 17:00     ` 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=1346350718-30937-3-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=eric.dumazet@gmail.com \
    --cc=fweisbec@gmail.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=sbw@mit.edu \
    --cc=tglx@linutronix.de \
    --subject='Re: [PATCH tip/core/rcu 03/23] rcu: Move RCU grace-period cleanup into kthread' \
    /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

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).