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,
	patches@linaro.org,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
	"Paul E. McKenney" <paul.mckenney@linaro.org>
Subject: [PATCH RFC tip/core/rcu 1/3] rcu: Allow nesting of rcu_idle_enter() and rcu_idle_exit()
Date: Thu,  2 Feb 2012 17:12:46 -0800	[thread overview]
Message-ID: <1328231568-2971-1-git-send-email-paulmck@linux.vnet.ibm.com> (raw)
In-Reply-To: <20120203011208.GA2004@linux.vnet.ibm.com>

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

Use of RCU in the idle loop is incorrect, quite a few instances of
just that have made their way into mainline, primarily event tracing.
The problem with RCU read-side critical sections on CPUs that RCU believes
to be idle is that RCU is completely ignoring the CPU, along with any
attempts and RCU read-side critical sections.

The approaches of eliminating the offending uses and of pushing the
definition of idle down beyond the offending uses have both proved
impractical.  The new approach is to encapsulate offending uses of RCU
with rcu_idle_exit() and rcu_idle_enter(), but this requires nesting
for code that is invoked both during idle and and during normal execution.
Therefore, this commit modifies rcu_idle_enter() and rcu_idle_exit() to
permit nesting.

Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

Conflicts:

	kernel/rcutree.c
---
 kernel/rcu.h     |   18 +++++++++++++++++-
 kernel/rcutiny.c |   16 ++++++++++++----
 kernel/rcutree.c |   19 +++++++++++++------
 3 files changed, 42 insertions(+), 11 deletions(-)

diff --git a/kernel/rcu.h b/kernel/rcu.h
index 30876f4..0d0f9e8 100644
--- a/kernel/rcu.h
+++ b/kernel/rcu.h
@@ -33,8 +33,24 @@
  * Process-level increment to ->dynticks_nesting field.  This allows for
  * architectures that use half-interrupts and half-exceptions from
  * process context.
+ *
+ * DYNTICK_TASK_NESTING_MASK is a three-bit field that counts the number
+ * of process-based reasons why RCU cannot consider the corresponding CPU
+ * to be idle, and DYNTICK_TASK_NESTING_VALUE is the value used to increment
+ * or decrement this three-bit field.  The rest of the bits could in
+ * principle be used to count interrupts, but this would mean that a
+ * negative-one value in the interrupt field could incorrectly zero out
+ * the DYNTICK_TASK_NESTING_MASK field.  We therefore provide a two-bit
+ * guard field defined by DYNTICK_TASK_MASK that is set to DYNTICK_TASK_FLAG
+ * upon initial exit from idle.  The DYNTICK_TASK_EXIT_IDLE value is
+ * thus the combined value used upon initial exit from idle.
  */
-#define DYNTICK_TASK_NESTING (LLONG_MAX / 2 - 1)
+#define DYNTICK_TASK_NESTING_VALUE (LLONG_MAX / 8 + 1)
+#define DYNTICK_TASK_NESTING_MASK  (LLONG_MAX - DYNTICK_TASK_NESTING_VALUE + 1)
+#define DYNTICK_TASK_FLAG	   ((DYNTICK_TASK_NESTING_VALUE / 8) * 2)
+#define DYNTICK_TASK_MASK	   ((DYNTICK_TASK_NESTING_VALUE / 8) * 3)
+#define DYNTICK_TASK_EXIT_IDLE	   (DYNTICK_TASK_NESTING_VALUE + \
+				    DYNTICK_TASK_FLAG)
 
 /*
  * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index 4eb34fc..5098aea 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -53,7 +53,7 @@ static void __call_rcu(struct rcu_head *head,
 
 #include "rcutiny_plugin.h"
 
-static long long rcu_dynticks_nesting = DYNTICK_TASK_NESTING;
+static long long rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
 
 /* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcutree.c. */
 static void rcu_idle_enter_common(long long oldval)
@@ -88,7 +88,12 @@ void rcu_idle_enter(void)
 
 	local_irq_save(flags);
 	oldval = rcu_dynticks_nesting;
-	rcu_dynticks_nesting = 0;
+	WARN_ON_ONCE((rcu_dynticks_nesting & DYNTICK_TASK_NESTING_MASK) == 0);
+	if ((rcu_dynticks_nesting & DYNTICK_TASK_NESTING_MASK) ==
+	    DYNTICK_TASK_NESTING_VALUE)
+		rcu_dynticks_nesting = 0;
+	else
+		rcu_dynticks_nesting  -= DYNTICK_TASK_NESTING_VALUE;
 	rcu_idle_enter_common(oldval);
 	local_irq_restore(flags);
 }
@@ -140,8 +145,11 @@ void rcu_idle_exit(void)
 
 	local_irq_save(flags);
 	oldval = rcu_dynticks_nesting;
-	WARN_ON_ONCE(oldval != 0);
-	rcu_dynticks_nesting = DYNTICK_TASK_NESTING;
+	WARN_ON_ONCE(rcu_dynticks_nesting < 0);
+	if (rcu_dynticks_nesting & DYNTICK_TASK_NESTING_MASK)
+		rcu_dynticks_nesting += DYNTICK_TASK_NESTING_VALUE;
+	else
+		rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
 	rcu_idle_exit_common(oldval);
 	local_irq_restore(flags);
 }
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index df0e3c1..e81298a 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -198,7 +198,7 @@ void rcu_note_context_switch(int cpu)
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);
 
 DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
-	.dynticks_nesting = DYNTICK_TASK_NESTING,
+	.dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
 	.dynticks = ATOMIC_INIT(1),
 };
 
@@ -394,7 +394,11 @@ void rcu_idle_enter(void)
 	local_irq_save(flags);
 	rdtp = &__get_cpu_var(rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
-	rdtp->dynticks_nesting = 0;
+	WARN_ON_ONCE((oldval & DYNTICK_TASK_NESTING_MASK) == 0);
+	if ((oldval & DYNTICK_TASK_NESTING_MASK) == DYNTICK_TASK_NESTING_VALUE)
+		rdtp->dynticks_nesting = 0;
+	else
+		rdtp->dynticks_nesting -= DYNTICK_TASK_NESTING_VALUE;
 	rcu_idle_enter_common(rdtp, oldval);
 	local_irq_restore(flags);
 }
@@ -481,8 +485,11 @@ void rcu_idle_exit(void)
 	local_irq_save(flags);
 	rdtp = &__get_cpu_var(rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
-	WARN_ON_ONCE(oldval != 0);
-	rdtp->dynticks_nesting = DYNTICK_TASK_NESTING;
+	WARN_ON_ONCE(oldval < 0);
+	if (oldval & DYNTICK_TASK_NESTING_MASK)
+		rdtp->dynticks_nesting += DYNTICK_TASK_NESTING_VALUE;
+	else
+		rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
 	rcu_idle_exit_common(rdtp, oldval);
 	local_irq_restore(flags);
 }
@@ -2253,7 +2260,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->qlen_lazy = 0;
 	rdp->qlen = 0;
 	rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
-	WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_NESTING);
+	WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE);
 	WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1);
 	rdp->cpu = cpu;
 	rdp->rsp = rsp;
@@ -2281,7 +2288,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible)
 	rdp->qlen_last_fqs_check = 0;
 	rdp->n_force_qs_snap = rsp->n_force_qs;
 	rdp->blimit = blimit;
-	rdp->dynticks->dynticks_nesting = DYNTICK_TASK_NESTING;
+	rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
 	atomic_set(&rdp->dynticks->dynticks,
 		   (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1);
 	rcu_prepare_for_idle_init(cpu);
-- 
1.7.8


  reply	other threads:[~2012-02-03  1:13 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-02-03  1:12 [PATCH RFC 0/3] Fix cpuidle_idle_call() RCU usage Paul E. McKenney
2012-02-03  1:12 ` Paul E. McKenney [this message]
2012-02-03  1:12   ` [PATCH RFC tip/core/rcu 2/3] rcu: Add RCU_NONIDLE() for idle-loop RCU read-side critical sections Paul E. McKenney
2012-02-03  1:12   ` [PATCH RFC tip/core/rcu 3/3] cpuidle: Inform RCU of " Paul E. McKenney
2012-02-03 11:02     ` Deepthi Dharwar
2012-02-03  2:43 ` [PATCH RFC 0/3] Fix cpuidle_idle_call() RCU usage Josh Triplett

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=1328231568-2971-1-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=paul.mckenney@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;
as well as URLs for NNTP newsgroup(s).