All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH] Make rcutorture more vicious: add stutter feature
@ 2008-06-18 12:21 Paul E. McKenney
  2008-06-18 13:08 ` Ingo Molnar
  2008-06-18 16:26 ` [PATCH] Make rcutorture more vicious: reinstate boot-time testing Paul E. McKenney
  0 siblings, 2 replies; 24+ messages in thread
From: Paul E. McKenney @ 2008-06-18 12:21 UTC (permalink / raw)
  To: linux-kernel
  Cc: mingo, josh, dvhltc, niv, dino, akpm, torvalds, vegard.nossum,
	adobriyan, oleg, bunk, rjw

Hello!

This patch takes a step towards making rcutorture more brutal by allowing
the test to be automatically periodically paused, with the default being
to run the test for five seconds then pause for five seconds and repeat.
This behavior can be controlled using a new "stutter" module parameter, so
that "stutter=0" gives the old default behavior of running continuously.

Starting and stopping rcutorture more heavily stresses RCU's interaction
with the scheduler, as well as exercising more paths through the
grace-period detection code.

Note that the default to "shuffle_interval" has also been adjusted from
5 seconds to 3 seconds to provide varying overlap with the "stutter"
interval.

I am still unable to provoke the failures that Alexey has been seeing,
even with this patch, but will be doing a few additional things to beef
up rcutorture.

Suggested-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---

 Documentation/RCU/torture.txt |    8 ++++-
 kernel/rcutorture.c           |   59 +++++++++++++++++++++++++++++++++++++++---
 2 files changed, 63 insertions(+), 4 deletions(-)

diff -urpNa -X dontdiff linux-2.6.26-rc4/Documentation/RCU/torture.txt linux-2.6.26-rc4-rcut1-stutter/Documentation/RCU/torture.txt
--- linux-2.6.26-rc4/Documentation/RCU/torture.txt	2008-04-16 19:49:44.000000000 -0700
+++ linux-2.6.26-rc4-rcut1-stutter/Documentation/RCU/torture.txt	2008-06-18 05:15:43.000000000 -0700
@@ -46,9 +46,15 @@ stat_interval	The number of seconds betw
 
 shuffle_interval
 		The number of seconds to keep the test threads affinitied
-		to a particular subset of the CPUs, defaults to 5 seconds.
+		to a particular subset of the CPUs, defaults to 3 seconds.
 		Used in conjunction with test_no_idle_hz.
 
+stutter		The length of time to run the test before pausing for this
+		same period of time.  Defaults to "stutter=5", so as
+		to run and pause for (roughly) five-second intervals.
+		Specifying "stutter=0" causes the test to run continuously
+		without pausing, which is the old default behavior.
+
 test_no_idle_hz	Whether or not to test the ability of RCU to operate in
 		a kernel that disables the scheduling-clock interrupt to
 		idle CPUs.  Boolean parameter, "1" to test, "0" otherwise.
diff -urpNa -X dontdiff linux-2.6.26-rc4/kernel/rcutorture.c linux-2.6.26-rc4-rcut1-stutter/kernel/rcutorture.c
--- linux-2.6.26-rc4/kernel/rcutorture.c	2008-05-30 04:39:01.000000000 -0700
+++ linux-2.6.26-rc4-rcut1-stutter/kernel/rcutorture.c	2008-06-18 04:54:41.000000000 -0700
@@ -57,7 +57,8 @@ static int stat_interval;	/* Interval be
 				/*  Defaults to "only at end of test". */
 static int verbose;		/* Print more debug info. */
 static int test_no_idle_hz;	/* Test RCU's support for tickless idle CPUs. */
-static int shuffle_interval = 5; /* Interval between shuffles (in sec)*/
+static int shuffle_interval = 3; /* Interval between shuffles (in sec)*/
+static int stutter = 5;		/* Start/stop testing interval (in sec) */
 static char *torture_type = "rcu"; /* What RCU implementation to torture. */
 
 module_param(nreaders, int, 0444);
@@ -72,6 +73,8 @@ module_param(test_no_idle_hz, bool, 0444
 MODULE_PARM_DESC(test_no_idle_hz, "Test support for tickless idle CPUs");
 module_param(shuffle_interval, int, 0444);
 MODULE_PARM_DESC(shuffle_interval, "Number of seconds between shuffles");
+module_param(stutter, int, 0444);
+MODULE_PARM_DESC(stutter, "Number of seconds to run/halt test");
 module_param(torture_type, charp, 0444);
 MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, srcu)");
 
@@ -91,6 +94,7 @@ static struct task_struct **fakewriter_t
 static struct task_struct **reader_tasks;
 static struct task_struct *stats_task;
 static struct task_struct *shuffler_task;
+static struct task_struct *stutter_task;
 
 #define RCU_TORTURE_PIPE_LEN 10
 
@@ -119,6 +123,8 @@ static atomic_t n_rcu_torture_mberror;
 static atomic_t n_rcu_torture_error;
 static struct list_head rcu_torture_removed;
 
+static int stutter_pause_test = 0;
+
 /*
  * Allocate an element from the rcu_tortures pool.
  */
@@ -179,6 +185,13 @@ rcu_random(struct rcu_random_state *rrsp
 	return swahw32(rrsp->rrs_state);
 }
 
+static void
+rcu_stutter_wait(void)
+{
+	while (stutter_pause_test)
+		schedule_timeout_interruptible(1);
+}
+
 /*
  * Operations vector for selecting different types of tests.
  */
@@ -537,6 +550,7 @@ rcu_torture_writer(void *arg)
 		}
 		rcu_torture_current_version++;
 		oldbatch = cur_ops->completed();
+		rcu_stutter_wait();
 	} while (!kthread_should_stop() && !fullstop);
 	VERBOSE_PRINTK_STRING("rcu_torture_writer task stopping");
 	while (!kthread_should_stop())
@@ -560,6 +574,7 @@ rcu_torture_fakewriter(void *arg)
 		schedule_timeout_uninterruptible(1 + rcu_random(&rand)%10);
 		udelay(rcu_random(&rand) & 0x3ff);
 		cur_ops->sync();
+		rcu_stutter_wait();
 	} while (!kthread_should_stop() && !fullstop);
 
 	VERBOSE_PRINTK_STRING("rcu_torture_fakewriter task stopping");
@@ -615,6 +630,7 @@ rcu_torture_reader(void *arg)
 		preempt_enable();
 		cur_ops->readunlock(idx);
 		schedule();
+		rcu_stutter_wait();
 	} while (!kthread_should_stop() && !fullstop);
 	VERBOSE_PRINTK_STRING("rcu_torture_reader task stopping");
 	while (!kthread_should_stop())
@@ -785,15 +801,34 @@ rcu_torture_shuffle(void *arg)
 	return 0;
 }
 
+/* Cause the rcutorture test to "stutter", starting and stopping all
+ * threads periodically.
+ */
+static int
+rcu_torture_stutter(void *arg)
+{
+	VERBOSE_PRINTK_STRING("rcu_torture_stutter task started");
+	do {
+		schedule_timeout_interruptible(stutter * HZ);
+		stutter_pause_test = 1;
+		if (!kthread_should_stop())
+			schedule_timeout_interruptible(stutter * HZ);
+		stutter_pause_test = 0;
+	} while (!kthread_should_stop());
+	VERBOSE_PRINTK_STRING("rcu_torture_stutter task stopping");
+	return 0;
+}
+
 static inline void
 rcu_torture_print_module_parms(char *tag)
 {
 	printk(KERN_ALERT "%s" TORTURE_FLAG
 		"--- %s: nreaders=%d nfakewriters=%d "
 		"stat_interval=%d verbose=%d test_no_idle_hz=%d "
-		"shuffle_interval = %d\n",
+		"shuffle_interval=%d stutter=%d\n",
 		torture_type, tag, nrealreaders, nfakewriters,
-		stat_interval, verbose, test_no_idle_hz, shuffle_interval);
+		stat_interval, verbose, test_no_idle_hz, shuffle_interval,
+		stutter);
 }
 
 static void
@@ -802,6 +837,11 @@ rcu_torture_cleanup(void)
 	int i;
 
 	fullstop = 1;
+	if (stutter_task) {
+		VERBOSE_PRINTK_STRING("Stopping rcu_torture_stutter task");
+		kthread_stop(stutter_task);
+	}
+	stutter_task = NULL;
 	if (shuffler_task) {
 		VERBOSE_PRINTK_STRING("Stopping rcu_torture_shuffle task");
 		kthread_stop(shuffler_task);
@@ -988,6 +1028,19 @@ rcu_torture_init(void)
 			goto unwind;
 		}
 	}
+	if (stutter < 0)
+		stutter = 0;
+	if (stutter) {
+		/* Create the stutter thread */
+		stutter_task = kthread_run(rcu_torture_stutter, NULL,
+					  "rcu_torture_stutter");
+		if (IS_ERR(stutter_task)) {
+			firsterr = PTR_ERR(stutter_task);
+			VERBOSE_PRINTK_ERRSTRING("Failed to create stutter");
+			stutter_task = NULL;
+			goto unwind;
+		}
+	}
 	return 0;
 
 unwind:

^ permalink raw reply	[flat|nested] 24+ messages in thread

* Re: [PATCH] Make rcutorture more vicious: add stutter feature
  2008-06-18 12:21 [PATCH] Make rcutorture more vicious: add stutter feature Paul E. McKenney
@ 2008-06-18 13:08 ` Ingo Molnar
  2008-06-18 16:26 ` [PATCH] Make rcutorture more vicious: reinstate boot-time testing Paul E. McKenney
  1 sibling, 0 replies; 24+ messages in thread
From: Ingo Molnar @ 2008-06-18 13:08 UTC (permalink / raw)
  To: Paul E. McKenney
  Cc: linux-kernel, josh, dvhltc, niv, dino, akpm, torvalds,
	vegard.nossum, adobriyan, oleg, bunk, rjw


* Paul E. McKenney <paulmck@linux.vnet.ibm.com> wrote:

> Hello!
> 
> This patch takes a step towards making rcutorture more brutal by 
> allowing the test to be automatically periodically paused, with the 
> default being to run the test for five seconds then pause for five 
> seconds and repeat. This behavior can be controlled using a new 
> "stutter" module parameter, so that "stutter=0" gives the old default 
> behavior of running continuously.
> 
> Starting and stopping rcutorture more heavily stresses RCU's 
> interaction with the scheduler, as well as exercising more paths 
> through the grace-period detection code.

cool! Applied to tip/core/rcu.

> Note that the default to "shuffle_interval" has also been adjusted 
> from 5 seconds to 3 seconds to provide varying overlap with the 
> "stutter" interval.
> 
> I am still unable to provoke the failures that Alexey has been seeing, 
> even with this patch, but will be doing a few additional things to 
> beef up rcutorture.

neither am i able to see any rcu-preempt+rcu-torture failures in my 
testing, despite having added the patch below to tip/core/rcu as well to 
make any failures more apparent.

	Ingo

------------------>
commit 5af970a48f3ba0dd96a036b196c79dc923f28231
Author: Ingo Molnar <mingo@elte.hu>
Date:   Wed Jun 18 10:09:48 2008 +0200

    rcutorture: WARN_ON_ONCE(1) when detecting an error
    
    this makes it easier for automated tests to pick up such failures.

diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 0334b6a..0ca7e9b 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -687,6 +687,7 @@ rcu_torture_printk(char *page)
 	if (i > 1) {
 		cnt += sprintf(&page[cnt], "!!! ");
 		atomic_inc(&n_rcu_torture_error);
+		WARN_ON_ONCE(1);
 	}
 	cnt += sprintf(&page[cnt], "Reader Pipe: ");
 	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)

^ permalink raw reply related	[flat|nested] 24+ messages in thread

* [PATCH] Make rcutorture more vicious: reinstate boot-time testing
  2008-06-18 12:21 [PATCH] Make rcutorture more vicious: add stutter feature Paul E. McKenney
  2008-06-18 13:08 ` Ingo Molnar
@ 2008-06-18 16:26 ` Paul E. McKenney
  2008-06-19  0:42   ` Josh Triplett
                     ` (2 more replies)
  1 sibling, 3 replies; 24+ messages in thread
From: Paul E. McKenney @ 2008-06-18 16:26 UTC (permalink / raw)
  To: linux-kernel
  Cc: mingo, josh, dvhltc, niv, dino, akpm, torvalds, vegard.nossum,
	adobriyan, oleg, bunk, rjw

Hello again!

This patch re-institutes the ability to build rcutorture directly into
the Linux kernel.  The reason that this capability was removed was that
this could result in your kernel being pretty much useless, as rcutorture
would be running starting from early boot.  This problem has been avoided
by (1) making rcutorture run only three seconds of every six by default,
(2) adding a CONFIG_RCU_TORTURE_TEST_RUNNABLE that permits rcutorture
to be quiesced at boot time, and (3) adding a sysctl in /proc named
/proc/sys/kernel/rcutorture_runnable that permits rcutorture to be
quiesced and unquiesced when built into the kernel.

Please note that this /proc file is -not- available when rcutorture
is built as a module.  Please also note that to get the earlier
take-no-prisoners behavior, you must use the boot command line to set
rcutorture's "stutter" parameter to zero.

The rcutorture quiescing mechanism is currently quite crude: loops
in each rcutorture process that poll a global variable once per tick.
Suggestions for improvement are welcome.  The default action will
be to reduce the polling rate to a few times per second.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Suggested-by: Ingo Molnar <mingo@elte.hu>
---

 Documentation/RCU/torture.txt |   21 ++++++++++++++-------
 kernel/rcutorture.c           |    9 ++++++++-
 kernel/sysctl.c               |   13 +++++++++++++
 lib/Kconfig.debug             |   20 +++++++++++++++++++-
 4 files changed, 54 insertions(+), 9 deletions(-)

diff -urpNa -X dontdiff linux-2.6.26-rc4-rcut1-stutter/Documentation/RCU/torture.txt linux-2.6.26-rc4-rcut2-proc/Documentation/RCU/torture.txt
--- linux-2.6.26-rc4-rcut1-stutter/Documentation/RCU/torture.txt	2008-06-18 05:15:43.000000000 -0700
+++ linux-2.6.26-rc4-rcut2-proc/Documentation/RCU/torture.txt	2008-06-18 08:11:19.000000000 -0700
@@ -10,13 +10,20 @@ status messages via printk(), which can 
 command (perhaps grepping for "torture").  The test is started
 when the module is loaded, and stops when the module is unloaded.
 
-However, actually setting this config option to "y" results in the system
-running the test immediately upon boot, and ending only when the system
-is taken down.  Normally, one will instead want to build the system
-with CONFIG_RCU_TORTURE_TEST=m and to use modprobe and rmmod to control
-the test, perhaps using a script similar to the one shown at the end of
-this document.  Note that you will need CONFIG_MODULE_UNLOAD in order
-to be able to end the test.
+CONFIG_RCU_TORTURE_TEST_RUNNABLE
+
+It is also possible to specify CONFIG_RCU_TORTURE_TEST=y, which will
+result in the tests being loaded into the base kernel.  In this case,
+the CONFIG_RCU_TORTURE_TEST_RUNNABLE config option is used to specify
+whether the RCU torture tests are to be started immediately during
+boot or whether the /proc/sys/kernel/rcutorture_runnable file is used
+to enable them.  This /proc file can be used to repeatedly pause and
+restart the tests, regardless of the initial state specified by the
+CONFIG_RCU_TORTURE_TEST_RUNNABLE config option.
+
+You will normally -not- want to start the RCU torture tests during boot
+(and thus the default is CONFIG_RCU_TORTURE_TEST_RUNNABLE=n), but doing
+this can sometimes be useful in finding boot-time bugs.
 
 
 MODULE PARAMETERS
diff -urpNa -X dontdiff linux-2.6.26-rc4-rcut1-stutter/kernel/rcutorture.c linux-2.6.26-rc4-rcut2-proc/kernel/rcutorture.c
--- linux-2.6.26-rc4-rcut1-stutter/kernel/rcutorture.c	2008-06-18 04:54:41.000000000 -0700
+++ linux-2.6.26-rc4-rcut2-proc/kernel/rcutorture.c	2008-06-18 07:38:11.000000000 -0700
@@ -125,6 +125,13 @@ static struct list_head rcu_torture_remo
 
 static int stutter_pause_test = 0;
 
+#if defined(MODULE) || defined(CONFIG_RCU_TORTURE_TEST_RUNNABLE)
+#define RCUTORTURE_RUNNABLE_INIT 1
+#else
+#define RCUTORTURE_RUNNABLE_INIT 0
+#endif
+int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT;
+
 /*
  * Allocate an element from the rcu_tortures pool.
  */
@@ -188,7 +195,7 @@ rcu_random(struct rcu_random_state *rrsp
 static void
 rcu_stutter_wait(void)
 {
-	while (stutter_pause_test)
+	while (stutter_pause_test || !rcutorture_runnable)
 		schedule_timeout_interruptible(1);
 }
 
diff -urpNa -X dontdiff linux-2.6.26-rc4-rcut1-stutter/kernel/sysctl.c linux-2.6.26-rc4-rcut2-proc/kernel/sysctl.c
--- linux-2.6.26-rc4-rcut1-stutter/kernel/sysctl.c	2008-05-30 04:39:01.000000000 -0700
+++ linux-2.6.26-rc4-rcut2-proc/kernel/sysctl.c	2008-06-18 07:35:26.000000000 -0700
@@ -82,6 +82,9 @@ extern int maps_protect;
 extern int sysctl_stat_interval;
 extern int latencytop_enabled;
 extern int sysctl_nr_open_min, sysctl_nr_open_max;
+#ifdef CONFIG_RCU_TORTURE_TEST
+extern int rcutorture_runnable;
+#endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
 
 /* Constants used for minimum and  maximum */
 #if defined(CONFIG_DETECT_SOFTLOCKUP) || defined(CONFIG_HIGHMEM)
@@ -813,6 +816,16 @@ static struct ctl_table kern_table[] = {
 		.child		= key_sysctls,
 	},
 #endif
+#ifdef CONFIG_RCU_TORTURE_TEST
+	{
+		.ctl_name       = CTL_UNNUMBERED,
+		.procname       = "rcutorture_runnable",
+		.data           = &rcutorture_runnable,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = &proc_dointvec,
+	},
+#endif
 /*
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt
diff -urpNa -X dontdiff linux-2.6.26-rc4-rcut1-stutter/lib/Kconfig.debug linux-2.6.26-rc4-rcut2-proc/lib/Kconfig.debug
--- linux-2.6.26-rc4-rcut1-stutter/lib/Kconfig.debug	2008-05-30 04:39:01.000000000 -0700
+++ linux-2.6.26-rc4-rcut2-proc/lib/Kconfig.debug	2008-06-18 06:32:48.000000000 -0700
@@ -531,16 +531,34 @@ config BOOT_PRINTK_DELAY
 config RCU_TORTURE_TEST
 	tristate "torture tests for RCU"
 	depends on DEBUG_KERNEL
-	depends on m
 	default n
 	help
 	  This option provides a kernel module that runs torture tests
 	  on the RCU infrastructure.  The kernel module may be built
 	  after the fact on the running kernel to be tested, if desired.
 
+	  Say Y here if you want RCU torture tests to be built into
+	  the kernel.
 	  Say M if you want the RCU torture tests to build as a module.
 	  Say N if you are unsure.
 
+config RCU_TORTURE_TEST_RUNNABLE
+	bool "torture tests for RCU runnable by default"
+	depends on RCU_TORTURE_TEST = y
+	default n
+	help
+	  This option provides a way to build the RCU torture tests
+	  directly into the kernel without them starting up at boot
+	  time.  You can use /proc/sys/kernel/rcutorture_runnable
+	  to manually override this setting.  This /proc file is
+	  available only when the RCU torture tests have been built
+	  into the kernel.
+
+	  Say Y here if you want the RCU torture tests to start during
+	  boot (you probably don't).
+	  Say N here if you want the RCU torture tests to start only
+	  after being manually enabled via /proc.
+
 config KPROBES_SANITY_TEST
 	bool "Kprobes sanity tests"
 	depends on DEBUG_KERNEL

^ permalink raw reply	[flat|nested] 24+ messages in thread

* Re: [PATCH] Make rcutorture more vicious: reinstate boot-time testing
  2008-06-18 16:26 ` [PATCH] Make rcutorture more vicious: reinstate boot-time testing Paul E. McKenney
@ 2008-06-19  0:42   ` Josh Triplett
  2008-06-19  9:29   ` Ingo Molnar
  2008-06-22 20:06   ` [PATCH -tip-rcu] Make rcutorture more vicious: make quiescent rcutorture less power-hungry Paul E. McKenney
  2 siblings, 0 replies; 24+ messages in thread
From: Josh Triplett @ 2008-06-19  0:42 UTC (permalink / raw)
  To: paulmck
  Cc: linux-kernel, mingo, dvhltc, niv, dino, akpm, torvalds,
	vegard.nossum, adobriyan, oleg, bunk, rjw

Paul E. McKenney wrote:
> Hello again!
> 
> This patch re-institutes the ability to build rcutorture directly into
> the Linux kernel.  The reason that this capability was removed was that
> this could result in your kernel being pretty much useless, as rcutorture
> would be running starting from early boot.  This problem has been avoided
> by (1) making rcutorture run only three seconds of every six by default,
> (2) adding a CONFIG_RCU_TORTURE_TEST_RUNNABLE that permits rcutorture
> to be quiesced at boot time, and (3) adding a sysctl in /proc named
> /proc/sys/kernel/rcutorture_runnable that permits rcutorture to be
> quiesced and unquiesced when built into the kernel.
> 
> Please note that this /proc file is -not- available when rcutorture
> is built as a module.  Please also note that to get the earlier
> take-no-prisoners behavior, you must use the boot command line to set
> rcutorture's "stutter" parameter to zero.
> 
> The rcutorture quiescing mechanism is currently quite crude: loops
> in each rcutorture process that poll a global variable once per tick.
> Suggestions for improvement are welcome.  The default action will
> be to reduce the polling rate to a few times per second.
> 
> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
> Suggested-by: Ingo Molnar <mingo@elte.hu>

This patch looks quite reasonable to me.

Signed-off-by: Josh Triplett <josh@kernel.org>

- Josh Triplett


^ permalink raw reply	[flat|nested] 24+ messages in thread

* Re: [PATCH] Make rcutorture more vicious: reinstate boot-time testing
  2008-06-18 16:26 ` [PATCH] Make rcutorture more vicious: reinstate boot-time testing Paul E. McKenney
  2008-06-19  0:42   ` Josh Triplett
@ 2008-06-19  9:29   ` Ingo Molnar
  2008-06-19 15:58     ` Paul E. McKenney
  2008-06-22 20:06   ` [PATCH -tip-rcu] Make rcutorture more vicious: make quiescent rcutorture less power-hungry Paul E. McKenney
  2 siblings, 1 reply; 24+ messages in thread
From: Ingo Molnar @ 2008-06-19  9:29 UTC (permalink / raw)
  To: Paul E. McKenney
  Cc: linux-kernel, josh, dvhltc, niv, dino, akpm, torvalds,
	vegard.nossum, adobriyan, oleg, bunk, rjw


* Paul E. McKenney <paulmck@linux.vnet.ibm.com> wrote:

> Hello again!
> 
> This patch re-institutes the ability to build rcutorture directly into 
> the Linux kernel.  The reason that this capability was removed was 
> that this could result in your kernel being pretty much useless, as 
> rcutorture would be running starting from early boot.  This problem 
> has been avoided by (1) making rcutorture run only three seconds of 
> every six by default, (2) adding a CONFIG_RCU_TORTURE_TEST_RUNNABLE 
> that permits rcutorture to be quiesced at boot time, and (3) adding a 
> sysctl in /proc named /proc/sys/kernel/rcutorture_runnable that 
> permits rcutorture to be quiesced and unquiesced when built into the 
> kernel.
> 
> Please note that this /proc file is -not- available when rcutorture is 
> built as a module.  Please also note that to get the earlier 
> take-no-prisoners behavior, you must use the boot command line to set 
> rcutorture's "stutter" parameter to zero.
> 
> The rcutorture quiescing mechanism is currently quite crude: loops in 
> each rcutorture process that poll a global variable once per tick. 
> Suggestions for improvement are welcome.  The default action will be 
> to reduce the polling rate to a few times per second.

applied to tip/core/rcu - thanks Paul!

FYI, yesterday's rcutorture-stutter feature survived a few hundred 
random bootup tests in -tip testing already.

a possible area for enhancement would be the following code:

static void
rcu_stutter_wait(void)
{
        while (stutter_pause_test || !rcutorture_runnable)
                schedule_timeout_interruptible(1);
}

will cause HZ number of IRQs on nohz systems, even if rcutorture is 
disabled. While it's fine to poll if rcutorture_runnable==1, the sleep 
should be at least 1 second when !rcutorture_runnable.

[ Or it might even make sense to completely stop the threads from a 
  sysctl handler - to make it event-driven and to cause no extra IRQs at 
  all when rcutorture is disabled via /proc. ]

	Ingo

^ permalink raw reply	[flat|nested] 24+ messages in thread

* Re: [PATCH] Make rcutorture more vicious: reinstate boot-time testing
  2008-06-19  9:29   ` Ingo Molnar
@ 2008-06-19 15:58     ` Paul E. McKenney
  2008-06-19 21:17       ` Randy Dunlap
  0 siblings, 1 reply; 24+ messages in thread
From: Paul E. McKenney @ 2008-06-19 15:58 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, josh, dvhltc, niv, dino, akpm, torvalds,
	vegard.nossum, adobriyan, oleg, bunk, rjw

On Thu, Jun 19, 2008 at 11:29:14AM +0200, Ingo Molnar wrote:
> 
> * Paul E. McKenney <paulmck@linux.vnet.ibm.com> wrote:
> 
> > Hello again!
> > 
> > This patch re-institutes the ability to build rcutorture directly into 
> > the Linux kernel.  The reason that this capability was removed was 
> > that this could result in your kernel being pretty much useless, as 
> > rcutorture would be running starting from early boot.  This problem 
> > has been avoided by (1) making rcutorture run only three seconds of 
> > every six by default, (2) adding a CONFIG_RCU_TORTURE_TEST_RUNNABLE 
> > that permits rcutorture to be quiesced at boot time, and (3) adding a 
> > sysctl in /proc named /proc/sys/kernel/rcutorture_runnable that 
> > permits rcutorture to be quiesced and unquiesced when built into the 
> > kernel.
> > 
> > Please note that this /proc file is -not- available when rcutorture is 
> > built as a module.  Please also note that to get the earlier 
> > take-no-prisoners behavior, you must use the boot command line to set 
> > rcutorture's "stutter" parameter to zero.
> > 
> > The rcutorture quiescing mechanism is currently quite crude: loops in 
> > each rcutorture process that poll a global variable once per tick. 
> > Suggestions for improvement are welcome.  The default action will be 
> > to reduce the polling rate to a few times per second.
> 
> applied to tip/core/rcu - thanks Paul!
> 
> FYI, yesterday's rcutorture-stutter feature survived a few hundred 
> random bootup tests in -tip testing already.
> 
> a possible area for enhancement would be the following code:
> 
> static void
> rcu_stutter_wait(void)
> {
>         while (stutter_pause_test || !rcutorture_runnable)
>                 schedule_timeout_interruptible(1);
> }
> 
> will cause HZ number of IRQs on nohz systems, even if rcutorture is 
> disabled. While it's fine to poll if rcutorture_runnable==1, the sleep 
> should be at least 1 second when !rcutorture_runnable.
> 
> [ Or it might even make sense to completely stop the threads from a 
>   sysctl handler - to make it event-driven and to cause no extra IRQs at 
>   all when rcutorture is disabled via /proc. ]

Here is a crude first cut (incorporated into an updated patch).

Thoughts?

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

 Documentation/RCU/torture.txt      |   21 
 Documentation/RCU/torture.txt.orig |    8 
 kernel/rcutorture.c                |   14 
 kernel/rcutorture.c.orig           |   59 
 kernel/sysctl.c                    |   13 
 kernel/sysctl.c.orig               | 2851 +++++++++++++++++++++++++++++++++++++
 lib/Kconfig.debug                  |   20 
 lib/Kconfig.debug.orig             |  679 ++++++++
 8 files changed, 3651 insertions(+), 14 deletions(-)

diff -urpNa linux-2.6.26-rc4-rcut1-stutter/Documentation/RCU/torture.txt linux-2.6.26-rc4-rcut2-proc/Documentation/RCU/torture.txt
--- linux-2.6.26-rc4-rcut1-stutter/Documentation/RCU/torture.txt	2008-06-18 05:15:43.000000000 -0700
+++ linux-2.6.26-rc4-rcut2-proc/Documentation/RCU/torture.txt	2008-06-18 08:11:19.000000000 -0700
@@ -10,13 +10,20 @@ status messages via printk(), which can 
 command (perhaps grepping for "torture").  The test is started
 when the module is loaded, and stops when the module is unloaded.
 
-However, actually setting this config option to "y" results in the system
-running the test immediately upon boot, and ending only when the system
-is taken down.  Normally, one will instead want to build the system
-with CONFIG_RCU_TORTURE_TEST=m and to use modprobe and rmmod to control
-the test, perhaps using a script similar to the one shown at the end of
-this document.  Note that you will need CONFIG_MODULE_UNLOAD in order
-to be able to end the test.
+CONFIG_RCU_TORTURE_TEST_RUNNABLE
+
+It is also possible to specify CONFIG_RCU_TORTURE_TEST=y, which will
+result in the tests being loaded into the base kernel.  In this case,
+the CONFIG_RCU_TORTURE_TEST_RUNNABLE config option is used to specify
+whether the RCU torture tests are to be started immediately during
+boot or whether the /proc/sys/kernel/rcutorture_runnable file is used
+to enable them.  This /proc file can be used to repeatedly pause and
+restart the tests, regardless of the initial state specified by the
+CONFIG_RCU_TORTURE_TEST_RUNNABLE config option.
+
+You will normally -not- want to start the RCU torture tests during boot
+(and thus the default is CONFIG_RCU_TORTURE_TEST_RUNNABLE=n), but doing
+this can sometimes be useful in finding boot-time bugs.
 
 
 MODULE PARAMETERS
diff -urpNa linux-2.6.26-rc4-rcut1-stutter/Documentation/RCU/torture.txt.orig linux-2.6.26-rc4-rcut2-proc/Documentation/RCU/torture.txt.orig
--- linux-2.6.26-rc4-rcut1-stutter/Documentation/RCU/torture.txt.orig	2008-04-16 19:49:44.000000000 -0700
+++ linux-2.6.26-rc4-rcut2-proc/Documentation/RCU/torture.txt.orig	2008-06-18 05:15:43.000000000 -0700
@@ -46,9 +46,15 @@ stat_interval	The number of seconds betw
 
 shuffle_interval
 		The number of seconds to keep the test threads affinitied
-		to a particular subset of the CPUs, defaults to 5 seconds.
+		to a particular subset of the CPUs, defaults to 3 seconds.
 		Used in conjunction with test_no_idle_hz.
 
+stutter		The length of time to run the test before pausing for this
+		same period of time.  Defaults to "stutter=5", so as
+		to run and pause for (roughly) five-second intervals.
+		Specifying "stutter=0" causes the test to run continuously
+		without pausing, which is the old default behavior.
+
 test_no_idle_hz	Whether or not to test the ability of RCU to operate in
 		a kernel that disables the scheduling-clock interrupt to
 		idle CPUs.  Boolean parameter, "1" to test, "0" otherwise.
diff -urpNa linux-2.6.26-rc4-rcut1-stutter/kernel/rcutorture.c linux-2.6.26-rc4-rcut2-proc/kernel/rcutorture.c
--- linux-2.6.26-rc4-rcut1-stutter/kernel/rcutorture.c	2008-06-18 04:54:41.000000000 -0700
+++ linux-2.6.26-rc4-rcut2-proc/kernel/rcutorture.c	2008-06-19 04:48:56.000000000 -0700
@@ -125,6 +125,13 @@ static struct list_head rcu_torture_remo
 
 static int stutter_pause_test = 0;
 
+#if defined(MODULE) || defined(CONFIG_RCU_TORTURE_TEST_RUNNABLE)
+#define RCUTORTURE_RUNNABLE_INIT 1
+#else
+#define RCUTORTURE_RUNNABLE_INIT 0
+#endif
+int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT;
+
 /*
  * Allocate an element from the rcu_tortures pool.
  */
@@ -188,8 +195,11 @@ rcu_random(struct rcu_random_state *rrsp
 static void
 rcu_stutter_wait(void)
 {
-	while (stutter_pause_test)
-		schedule_timeout_interruptible(1);
+	while (stutter_pause_test || !rcutorture_runnable)
+		if (rcutorture_runnable)
+			schedule_timeout_interruptible(1);
+		else
+			schedule_timeout_interruptible(HZ);
 }
 
 /*
diff -urpNa linux-2.6.26-rc4-rcut1-stutter/kernel/rcutorture.c.orig linux-2.6.26-rc4-rcut2-proc/kernel/rcutorture.c.orig
--- linux-2.6.26-rc4-rcut1-stutter/kernel/rcutorture.c.orig	2008-05-30 04:39:01.000000000 -0700
+++ linux-2.6.26-rc4-rcut2-proc/kernel/rcutorture.c.orig	2008-06-18 04:54:41.000000000 -0700
@@ -57,7 +57,8 @@ static int stat_interval;	/* Interval be
 				/*  Defaults to "only at end of test". */
 static int verbose;		/* Print more debug info. */
 static int test_no_idle_hz;	/* Test RCU's support for tickless idle CPUs. */
-static int shuffle_interval = 5; /* Interval between shuffles (in sec)*/
+static int shuffle_interval = 3; /* Interval between shuffles (in sec)*/
+static int stutter = 5;		/* Start/stop testing interval (in sec) */
 static char *torture_type = "rcu"; /* What RCU implementation to torture. */
 
 module_param(nreaders, int, 0444);
@@ -72,6 +73,8 @@ module_param(test_no_idle_hz, bool, 0444
 MODULE_PARM_DESC(test_no_idle_hz, "Test support for tickless idle CPUs");
 module_param(shuffle_interval, int, 0444);
 MODULE_PARM_DESC(shuffle_interval, "Number of seconds between shuffles");
+module_param(stutter, int, 0444);
+MODULE_PARM_DESC(stutter, "Number of seconds to run/halt test");
 module_param(torture_type, charp, 0444);
 MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, srcu)");
 
@@ -91,6 +94,7 @@ static struct task_struct **fakewriter_t
 static struct task_struct **reader_tasks;
 static struct task_struct *stats_task;
 static struct task_struct *shuffler_task;
+static struct task_struct *stutter_task;
 
 #define RCU_TORTURE_PIPE_LEN 10
 
@@ -119,6 +123,8 @@ static atomic_t n_rcu_torture_mberror;
 static atomic_t n_rcu_torture_error;
 static struct list_head rcu_torture_removed;
 
+static int stutter_pause_test = 0;
+
 /*
  * Allocate an element from the rcu_tortures pool.
  */
@@ -179,6 +185,13 @@ rcu_random(struct rcu_random_state *rrsp
 	return swahw32(rrsp->rrs_state);
 }
 
+static void
+rcu_stutter_wait(void)
+{
+	while (stutter_pause_test)
+		schedule_timeout_interruptible(1);
+}
+
 /*
  * Operations vector for selecting different types of tests.
  */
@@ -537,6 +550,7 @@ rcu_torture_writer(void *arg)
 		}
 		rcu_torture_current_version++;
 		oldbatch = cur_ops->completed();
+		rcu_stutter_wait();
 	} while (!kthread_should_stop() && !fullstop);
 	VERBOSE_PRINTK_STRING("rcu_torture_writer task stopping");
 	while (!kthread_should_stop())
@@ -560,6 +574,7 @@ rcu_torture_fakewriter(void *arg)
 		schedule_timeout_uninterruptible(1 + rcu_random(&rand)%10);
 		udelay(rcu_random(&rand) & 0x3ff);
 		cur_ops->sync();
+		rcu_stutter_wait();
 	} while (!kthread_should_stop() && !fullstop);
 
 	VERBOSE_PRINTK_STRING("rcu_torture_fakewriter task stopping");
@@ -615,6 +630,7 @@ rcu_torture_reader(void *arg)
 		preempt_enable();
 		cur_ops->readunlock(idx);
 		schedule();
+		rcu_stutter_wait();
 	} while (!kthread_should_stop() && !fullstop);
 	VERBOSE_PRINTK_STRING("rcu_torture_reader task stopping");
 	while (!kthread_should_stop())
@@ -785,15 +801,34 @@ rcu_torture_shuffle(void *arg)
 	return 0;
 }
 
+/* Cause the rcutorture test to "stutter", starting and stopping all
+ * threads periodically.
+ */
+static int
+rcu_torture_stutter(void *arg)
+{
+	VERBOSE_PRINTK_STRING("rcu_torture_stutter task started");
+	do {
+		schedule_timeout_interruptible(stutter * HZ);
+		stutter_pause_test = 1;
+		if (!kthread_should_stop())
+			schedule_timeout_interruptible(stutter * HZ);
+		stutter_pause_test = 0;
+	} while (!kthread_should_stop());
+	VERBOSE_PRINTK_STRING("rcu_torture_stutter task stopping");
+	return 0;
+}
+
 static inline void
 rcu_torture_print_module_parms(char *tag)
 {
 	printk(KERN_ALERT "%s" TORTURE_FLAG
 		"--- %s: nreaders=%d nfakewriters=%d "
 		"stat_interval=%d verbose=%d test_no_idle_hz=%d "
-		"shuffle_interval = %d\n",
+		"shuffle_interval=%d stutter=%d\n",
 		torture_type, tag, nrealreaders, nfakewriters,
-		stat_interval, verbose, test_no_idle_hz, shuffle_interval);
+		stat_interval, verbose, test_no_idle_hz, shuffle_interval,
+		stutter);
 }
 
 static void
@@ -802,6 +837,11 @@ rcu_torture_cleanup(void)
 	int i;
 
 	fullstop = 1;
+	if (stutter_task) {
+		VERBOSE_PRINTK_STRING("Stopping rcu_torture_stutter task");
+		kthread_stop(stutter_task);
+	}
+	stutter_task = NULL;
 	if (shuffler_task) {
 		VERBOSE_PRINTK_STRING("Stopping rcu_torture_shuffle task");
 		kthread_stop(shuffler_task);
@@ -988,6 +1028,19 @@ rcu_torture_init(void)
 			goto unwind;
 		}
 	}
+	if (stutter < 0)
+		stutter = 0;
+	if (stutter) {
+		/* Create the stutter thread */
+		stutter_task = kthread_run(rcu_torture_stutter, NULL,
+					  "rcu_torture_stutter");
+		if (IS_ERR(stutter_task)) {
+			firsterr = PTR_ERR(stutter_task);
+			VERBOSE_PRINTK_ERRSTRING("Failed to create stutter");
+			stutter_task = NULL;
+			goto unwind;
+		}
+	}
 	return 0;
 
 unwind:
diff -urpNa linux-2.6.26-rc4-rcut1-stutter/kernel/sysctl.c linux-2.6.26-rc4-rcut2-proc/kernel/sysctl.c
--- linux-2.6.26-rc4-rcut1-stutter/kernel/sysctl.c	2008-05-30 04:39:01.000000000 -0700
+++ linux-2.6.26-rc4-rcut2-proc/kernel/sysctl.c	2008-06-18 07:35:26.000000000 -0700
@@ -82,6 +82,9 @@ extern int maps_protect;
 extern int sysctl_stat_interval;
 extern int latencytop_enabled;
 extern int sysctl_nr_open_min, sysctl_nr_open_max;
+#ifdef CONFIG_RCU_TORTURE_TEST
+extern int rcutorture_runnable;
+#endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
 
 /* Constants used for minimum and  maximum */
 #if defined(CONFIG_DETECT_SOFTLOCKUP) || defined(CONFIG_HIGHMEM)
@@ -813,6 +816,16 @@ static struct ctl_table kern_table[] = {
 		.child		= key_sysctls,
 	},
 #endif
+#ifdef CONFIG_RCU_TORTURE_TEST
+	{
+		.ctl_name       = CTL_UNNUMBERED,
+		.procname       = "rcutorture_runnable",
+		.data           = &rcutorture_runnable,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = &proc_dointvec,
+	},
+#endif
 /*
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt
diff -urpNa linux-2.6.26-rc4-rcut1-stutter/kernel/sysctl.c.orig linux-2.6.26-rc4-rcut2-proc/kernel/sysctl.c.orig
--- linux-2.6.26-rc4-rcut1-stutter/kernel/sysctl.c.orig	1969-12-31 16:00:00.000000000 -0800
+++ linux-2.6.26-rc4-rcut2-proc/kernel/sysctl.c.orig	2008-05-30 04:39:01.000000000 -0700
@@ -0,0 +1,2851 @@
+/*
+ * sysctl.c: General linux system control interface
+ *
+ * Begun 24 March 1995, Stephen Tweedie
+ * Added /proc support, Dec 1995
+ * Added bdflush entry and intvec min/max checking, 2/23/96, Tom Dyas.
+ * Added hooks for /proc/sys/net (minor, minor patch), 96/4/1, Mike Shaver.
+ * Added kernel/java-{interpreter,appletviewer}, 96/5/10, Mike Shaver.
+ * Dynamic registration fixes, Stephen Tweedie.
+ * Added kswapd-interval, ctrl-alt-del, printk stuff, 1/8/97, Chris Horn.
+ * Made sysctl support optional via CONFIG_SYSCTL, 1/10/97, Chris
+ *  Horn.
+ * Added proc_doulongvec_ms_jiffies_minmax, 09/08/99, Carlos H. Bauer.
+ * Added proc_doulongvec_minmax, 09/08/99, Carlos H. Bauer.
+ * Changed linked lists to use list.h instead of lists.h, 02/24/00, Bill
+ *  Wendling.
+ * The list_for_each() macro wasn't appropriate for the sysctl loop.
+ *  Removed it and replaced it with older style, 03/23/00, Bill Wendling
+ */
+
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/slab.h>
+#include <linux/sysctl.h>
+#include <linux/proc_fs.h>
+#include <linux/security.h>
+#include <linux/ctype.h>
+#include <linux/utsname.h>
+#include <linux/smp_lock.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/kobject.h>
+#include <linux/net.h>
+#include <linux/sysrq.h>
+#include <linux/highuid.h>
+#include <linux/writeback.h>
+#include <linux/hugetlb.h>
+#include <linux/initrd.h>
+#include <linux/key.h>
+#include <linux/times.h>
+#include <linux/limits.h>
+#include <linux/dcache.h>
+#include <linux/syscalls.h>
+#include <linux/nfs_fs.h>
+#include <linux/acpi.h>
+#include <linux/reboot.h>
+
+#include <asm/uaccess.h>
+#include <asm/processor.h>
+
+#ifdef CONFIG_X86
+#include <asm/nmi.h>
+#include <asm/stacktrace.h>
+#include <asm/io.h>
+#endif
+
+static int deprecated_sysctl_warning(struct __sysctl_args *args);
+
+#if defined(CONFIG_SYSCTL)
+
+/* External variables not in a header file. */
+extern int C_A_D;
+extern int print_fatal_signals;
+extern int sysctl_overcommit_memory;
+extern int sysctl_overcommit_ratio;
+extern int sysctl_panic_on_oom;
+extern int sysctl_oom_kill_allocating_task;
+extern int sysctl_oom_dump_tasks;
+extern int max_threads;
+extern int core_uses_pid;
+extern int suid_dumpable;
+extern char core_pattern[];
+extern int pid_max;
+extern int min_free_kbytes;
+extern int pid_max_min, pid_max_max;
+extern int sysctl_drop_caches;
+extern int percpu_pagelist_fraction;
+extern int compat_log;
+extern int maps_protect;
+extern int sysctl_stat_interval;
+extern int latencytop_enabled;
+extern int sysctl_nr_open_min, sysctl_nr_open_max;
+
+/* Constants used for minimum and  maximum */
+#if defined(CONFIG_DETECT_SOFTLOCKUP) || defined(CONFIG_HIGHMEM)
+static int one = 1;
+#endif
+
+#ifdef CONFIG_DETECT_SOFTLOCKUP
+static int sixty = 60;
+#endif
+
+#ifdef CONFIG_MMU
+static int two = 2;
+#endif
+
+static int zero;
+static int one_hundred = 100;
+
+/* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
+static int maxolduid = 65535;
+static int minolduid;
+static int min_percpu_pagelist_fract = 8;
+
+static int ngroups_max = NGROUPS_MAX;
+
+#ifdef CONFIG_KMOD
+extern char modprobe_path[];
+#endif
+#ifdef CONFIG_CHR_DEV_SG
+extern int sg_big_buff;
+#endif
+
+#ifdef __sparc__
+extern char reboot_command [];
+extern int stop_a_enabled;
+extern int scons_pwroff;
+#endif
+
+#ifdef __hppa__
+extern int pwrsw_enabled;
+extern int unaligned_enabled;
+#endif
+
+#ifdef CONFIG_S390
+#ifdef CONFIG_MATHEMU
+extern int sysctl_ieee_emulation_warnings;
+#endif
+extern int sysctl_userprocess_debug;
+extern int spin_retry;
+#endif
+
+extern int sysctl_hz_timer;
+
+#ifdef CONFIG_BSD_PROCESS_ACCT
+extern int acct_parm[];
+#endif
+
+#ifdef CONFIG_IA64
+extern int no_unaligned_warning;
+#endif
+
+#ifdef CONFIG_RT_MUTEXES
+extern int max_lock_depth;
+#endif
+
+#ifdef CONFIG_PROC_SYSCTL
+static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp,
+		  void __user *buffer, size_t *lenp, loff_t *ppos);
+static int proc_dointvec_taint(struct ctl_table *table, int write, struct file *filp,
+			       void __user *buffer, size_t *lenp, loff_t *ppos);
+#endif
+
+static struct ctl_table root_table[];
+static struct ctl_table_root sysctl_table_root;
+static struct ctl_table_header root_table_header = {
+	.ctl_table = root_table,
+	.ctl_entry = LIST_HEAD_INIT(sysctl_table_root.header_list),
+	.root = &sysctl_table_root,
+};
+static struct ctl_table_root sysctl_table_root = {
+	.root_list = LIST_HEAD_INIT(sysctl_table_root.root_list),
+	.header_list = LIST_HEAD_INIT(root_table_header.ctl_entry),
+};
+
+static struct ctl_table kern_table[];
+static struct ctl_table vm_table[];
+static struct ctl_table fs_table[];
+static struct ctl_table debug_table[];
+static struct ctl_table dev_table[];
+extern struct ctl_table random_table[];
+#ifdef CONFIG_INOTIFY_USER
+extern struct ctl_table inotify_table[];
+#endif
+
+#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT
+int sysctl_legacy_va_layout;
+#endif
+
+extern int prove_locking;
+extern int lock_stat;
+
+/* The default sysctl tables: */
+
+static struct ctl_table root_table[] = {
+	{
+		.ctl_name	= CTL_KERN,
+		.procname	= "kernel",
+		.mode		= 0555,
+		.child		= kern_table,
+	},
+	{
+		.ctl_name	= CTL_VM,
+		.procname	= "vm",
+		.mode		= 0555,
+		.child		= vm_table,
+	},
+	{
+		.ctl_name	= CTL_FS,
+		.procname	= "fs",
+		.mode		= 0555,
+		.child		= fs_table,
+	},
+	{
+		.ctl_name	= CTL_DEBUG,
+		.procname	= "debug",
+		.mode		= 0555,
+		.child		= debug_table,
+	},
+	{
+		.ctl_name	= CTL_DEV,
+		.procname	= "dev",
+		.mode		= 0555,
+		.child		= dev_table,
+	},
+/*
+ * NOTE: do not add new entries to this table unless you have read
+ * Documentation/sysctl/ctl_unnumbered.txt
+ */
+	{ .ctl_name = 0 }
+};
+
+#ifdef CONFIG_SCHED_DEBUG
+static int min_sched_granularity_ns = 100000;		/* 100 usecs */
+static int max_sched_granularity_ns = NSEC_PER_SEC;	/* 1 second */
+static int min_wakeup_granularity_ns;			/* 0 usecs */
+static int max_wakeup_granularity_ns = NSEC_PER_SEC;	/* 1 second */
+#endif
+
+static struct ctl_table kern_table[] = {
+#ifdef CONFIG_SCHED_DEBUG
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_min_granularity_ns",
+		.data		= &sysctl_sched_min_granularity,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &sched_nr_latency_handler,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &min_sched_granularity_ns,
+		.extra2		= &max_sched_granularity_ns,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_latency_ns",
+		.data		= &sysctl_sched_latency,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &sched_nr_latency_handler,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &min_sched_granularity_ns,
+		.extra2		= &max_sched_granularity_ns,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_wakeup_granularity_ns",
+		.data		= &sysctl_sched_wakeup_granularity,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &min_wakeup_granularity_ns,
+		.extra2		= &max_wakeup_granularity_ns,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_child_runs_first",
+		.data		= &sysctl_sched_child_runs_first,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_features",
+		.data		= &sysctl_sched_features,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_migration_cost",
+		.data		= &sysctl_sched_migration_cost,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_nr_migrate",
+		.data		= &sysctl_sched_nr_migrate,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_rt_period_us",
+		.data		= &sysctl_sched_rt_period,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &sched_rt_handler,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_rt_runtime_us",
+		.data		= &sysctl_sched_rt_runtime,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &sched_rt_handler,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_compat_yield",
+		.data		= &sysctl_sched_compat_yield,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#ifdef CONFIG_PROVE_LOCKING
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "prove_locking",
+		.data		= &prove_locking,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+#ifdef CONFIG_LOCK_STAT
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "lock_stat",
+		.data		= &lock_stat,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+	{
+		.ctl_name	= KERN_PANIC,
+		.procname	= "panic",
+		.data		= &panic_timeout,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= KERN_CORE_USES_PID,
+		.procname	= "core_uses_pid",
+		.data		= &core_uses_pid,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= KERN_CORE_PATTERN,
+		.procname	= "core_pattern",
+		.data		= core_pattern,
+		.maxlen		= CORENAME_MAX_SIZE,
+		.mode		= 0644,
+		.proc_handler	= &proc_dostring,
+		.strategy	= &sysctl_string,
+	},
+#ifdef CONFIG_PROC_SYSCTL
+	{
+		.procname	= "tainted",
+		.data		= &tainted,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_taint,
+	},
+#endif
+#ifdef CONFIG_LATENCYTOP
+	{
+		.procname	= "latencytop",
+		.data		= &latencytop_enabled,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+#ifdef CONFIG_BLK_DEV_INITRD
+	{
+		.ctl_name	= KERN_REALROOTDEV,
+		.procname	= "real-root-dev",
+		.data		= &real_root_dev,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "print-fatal-signals",
+		.data		= &print_fatal_signals,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#ifdef __sparc__
+	{
+		.ctl_name	= KERN_SPARC_REBOOT,
+		.procname	= "reboot-cmd",
+		.data		= reboot_command,
+		.maxlen		= 256,
+		.mode		= 0644,
+		.proc_handler	= &proc_dostring,
+		.strategy	= &sysctl_string,
+	},
+	{
+		.ctl_name	= KERN_SPARC_STOP_A,
+		.procname	= "stop-a",
+		.data		= &stop_a_enabled,
+		.maxlen		= sizeof (int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= KERN_SPARC_SCONS_PWROFF,
+		.procname	= "scons-poweroff",
+		.data		= &scons_pwroff,
+		.maxlen		= sizeof (int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+#ifdef __hppa__
+	{
+		.ctl_name	= KERN_HPPA_PWRSW,
+		.procname	= "soft-power",
+		.data		= &pwrsw_enabled,
+		.maxlen		= sizeof (int),
+	 	.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= KERN_HPPA_UNALIGNED,
+		.procname	= "unaligned-trap",
+		.data		= &unaligned_enabled,
+		.maxlen		= sizeof (int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+	{
+		.ctl_name	= KERN_CTLALTDEL,
+		.procname	= "ctrl-alt-del",
+		.data		= &C_A_D,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#ifdef CONFIG_KMOD
+	{
+		.ctl_name	= KERN_MODPROBE,
+		.procname	= "modprobe",
+		.data		= &modprobe_path,
+		.maxlen		= KMOD_PATH_LEN,
+		.mode		= 0644,
+		.proc_handler	= &proc_dostring,
+		.strategy	= &sysctl_string,
+	},
+#endif
+#if defined(CONFIG_HOTPLUG) && defined(CONFIG_NET)
+	{
+		.ctl_name	= KERN_HOTPLUG,
+		.procname	= "hotplug",
+		.data		= &uevent_helper,
+		.maxlen		= UEVENT_HELPER_PATH_LEN,
+		.mode		= 0644,
+		.proc_handler	= &proc_dostring,
+		.strategy	= &sysctl_string,
+	},
+#endif
+#ifdef CONFIG_CHR_DEV_SG
+	{
+		.ctl_name	= KERN_SG_BIG_BUFF,
+		.procname	= "sg-big-buff",
+		.data		= &sg_big_buff,
+		.maxlen		= sizeof (int),
+		.mode		= 0444,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+#ifdef CONFIG_BSD_PROCESS_ACCT
+	{
+		.ctl_name	= KERN_ACCT,
+		.procname	= "acct",
+		.data		= &acct_parm,
+		.maxlen		= 3*sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+#ifdef CONFIG_MAGIC_SYSRQ
+	{
+		.ctl_name	= KERN_SYSRQ,
+		.procname	= "sysrq",
+		.data		= &__sysrq_enabled,
+		.maxlen		= sizeof (int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+#ifdef CONFIG_PROC_SYSCTL
+	{
+		.procname	= "cad_pid",
+		.data		= NULL,
+		.maxlen		= sizeof (int),
+		.mode		= 0600,
+		.proc_handler	= &proc_do_cad_pid,
+	},
+#endif
+	{
+		.ctl_name	= KERN_MAX_THREADS,
+		.procname	= "threads-max",
+		.data		= &max_threads,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= KERN_RANDOM,
+		.procname	= "random",
+		.mode		= 0555,
+		.child		= random_table,
+	},
+	{
+		.ctl_name	= KERN_OVERFLOWUID,
+		.procname	= "overflowuid",
+		.data		= &overflowuid,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &minolduid,
+		.extra2		= &maxolduid,
+	},
+	{
+		.ctl_name	= KERN_OVERFLOWGID,
+		.procname	= "overflowgid",
+		.data		= &overflowgid,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &minolduid,
+		.extra2		= &maxolduid,
+	},
+#ifdef CONFIG_S390
+#ifdef CONFIG_MATHEMU
+	{
+		.ctl_name	= KERN_IEEE_EMULATION_WARNINGS,
+		.procname	= "ieee_emulation_warnings",
+		.data		= &sysctl_ieee_emulation_warnings,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+#ifdef CONFIG_NO_IDLE_HZ
+	{
+		.ctl_name       = KERN_HZ_TIMER,
+		.procname       = "hz_timer",
+		.data           = &sysctl_hz_timer,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = &proc_dointvec,
+	},
+#endif
+	{
+		.ctl_name	= KERN_S390_USER_DEBUG_LOGGING,
+		.procname	= "userprocess_debug",
+		.data		= &sysctl_userprocess_debug,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+	{
+		.ctl_name	= KERN_PIDMAX,
+		.procname	= "pid_max",
+		.data		= &pid_max,
+		.maxlen		= sizeof (int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= sysctl_intvec,
+		.extra1		= &pid_max_min,
+		.extra2		= &pid_max_max,
+	},
+	{
+		.ctl_name	= KERN_PANIC_ON_OOPS,
+		.procname	= "panic_on_oops",
+		.data		= &panic_on_oops,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#if defined CONFIG_PRINTK
+	{
+		.ctl_name	= KERN_PRINTK,
+		.procname	= "printk",
+		.data		= &console_loglevel,
+		.maxlen		= 4*sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= KERN_PRINTK_RATELIMIT,
+		.procname	= "printk_ratelimit",
+		.data		= &printk_ratelimit_jiffies,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_jiffies,
+		.strategy	= &sysctl_jiffies,
+	},
+	{
+		.ctl_name	= KERN_PRINTK_RATELIMIT_BURST,
+		.procname	= "printk_ratelimit_burst",
+		.data		= &printk_ratelimit_burst,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+	{
+		.ctl_name	= KERN_NGROUPS_MAX,
+		.procname	= "ngroups_max",
+		.data		= &ngroups_max,
+		.maxlen		= sizeof (int),
+		.mode		= 0444,
+		.proc_handler	= &proc_dointvec,
+	},
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
+	{
+		.ctl_name       = KERN_UNKNOWN_NMI_PANIC,
+		.procname       = "unknown_nmi_panic",
+		.data           = &unknown_nmi_panic,
+		.maxlen         = sizeof (int),
+		.mode           = 0644,
+		.proc_handler   = &proc_dointvec,
+	},
+	{
+		.procname       = "nmi_watchdog",
+		.data           = &nmi_watchdog_enabled,
+		.maxlen         = sizeof (int),
+		.mode           = 0644,
+		.proc_handler   = &proc_nmi_enabled,
+	},
+#endif
+#if defined(CONFIG_X86)
+	{
+		.ctl_name	= KERN_PANIC_ON_NMI,
+		.procname	= "panic_on_unrecovered_nmi",
+		.data		= &panic_on_unrecovered_nmi,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= KERN_BOOTLOADER_TYPE,
+		.procname	= "bootloader_type",
+		.data		= &bootloader_type,
+		.maxlen		= sizeof (int),
+		.mode		= 0444,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "kstack_depth_to_print",
+		.data		= &kstack_depth_to_print,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "io_delay_type",
+		.data		= &io_delay_type,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+#if defined(CONFIG_MMU)
+	{
+		.ctl_name	= KERN_RANDOMIZE,
+		.procname	= "randomize_va_space",
+		.data		= &randomize_va_space,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+#if defined(CONFIG_S390) && defined(CONFIG_SMP)
+	{
+		.ctl_name	= KERN_SPIN_RETRY,
+		.procname	= "spin_retry",
+		.data		= &spin_retry,
+		.maxlen		= sizeof (int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+#if	defined(CONFIG_ACPI_SLEEP) && defined(CONFIG_X86)
+	{
+		.procname	= "acpi_video_flags",
+		.data		= &acpi_realmode_flags,
+		.maxlen		= sizeof (unsigned long),
+		.mode		= 0644,
+		.proc_handler	= &proc_doulongvec_minmax,
+	},
+#endif
+#ifdef CONFIG_IA64
+	{
+		.ctl_name	= KERN_IA64_UNALIGNED,
+		.procname	= "ignore-unaligned-usertrap",
+		.data		= &no_unaligned_warning,
+		.maxlen		= sizeof (int),
+	 	.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+#ifdef CONFIG_DETECT_SOFTLOCKUP
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "softlockup_thresh",
+		.data		= &softlockup_thresh,
+		.maxlen		= sizeof(unsigned long),
+		.mode		= 0644,
+		.proc_handler	= &proc_doulongvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &one,
+		.extra2		= &sixty,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "hung_task_check_count",
+		.data		= &sysctl_hung_task_check_count,
+		.maxlen		= sizeof(unsigned long),
+		.mode		= 0644,
+		.proc_handler	= &proc_doulongvec_minmax,
+		.strategy	= &sysctl_intvec,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "hung_task_timeout_secs",
+		.data		= &sysctl_hung_task_timeout_secs,
+		.maxlen		= sizeof(unsigned long),
+		.mode		= 0644,
+		.proc_handler	= &proc_doulongvec_minmax,
+		.strategy	= &sysctl_intvec,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "hung_task_warnings",
+		.data		= &sysctl_hung_task_warnings,
+		.maxlen		= sizeof(unsigned long),
+		.mode		= 0644,
+		.proc_handler	= &proc_doulongvec_minmax,
+		.strategy	= &sysctl_intvec,
+	},
+#endif
+#ifdef CONFIG_COMPAT
+	{
+		.ctl_name	= KERN_COMPAT_LOG,
+		.procname	= "compat-log",
+		.data		= &compat_log,
+		.maxlen		= sizeof (int),
+	 	.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+#ifdef CONFIG_RT_MUTEXES
+	{
+		.ctl_name	= KERN_MAX_LOCK_DEPTH,
+		.procname	= "max_lock_depth",
+		.data		= &max_lock_depth,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+#ifdef CONFIG_PROC_FS
+	{
+		.ctl_name       = CTL_UNNUMBERED,
+		.procname       = "maps_protect",
+		.data           = &maps_protect,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = &proc_dointvec,
+	},
+#endif
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "poweroff_cmd",
+		.data		= &poweroff_cmd,
+		.maxlen		= POWEROFF_CMD_PATH_LEN,
+		.mode		= 0644,
+		.proc_handler	= &proc_dostring,
+		.strategy	= &sysctl_string,
+	},
+#ifdef CONFIG_KEYS
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "keys",
+		.mode		= 0555,
+		.child		= key_sysctls,
+	},
+#endif
+/*
+ * NOTE: do not add new entries to this table unless you have read
+ * Documentation/sysctl/ctl_unnumbered.txt
+ */
+	{ .ctl_name = 0 }
+};
+
+static struct ctl_table vm_table[] = {
+	{
+		.ctl_name	= VM_OVERCOMMIT_MEMORY,
+		.procname	= "overcommit_memory",
+		.data		= &sysctl_overcommit_memory,
+		.maxlen		= sizeof(sysctl_overcommit_memory),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= VM_PANIC_ON_OOM,
+		.procname	= "panic_on_oom",
+		.data		= &sysctl_panic_on_oom,
+		.maxlen		= sizeof(sysctl_panic_on_oom),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "oom_kill_allocating_task",
+		.data		= &sysctl_oom_kill_allocating_task,
+		.maxlen		= sizeof(sysctl_oom_kill_allocating_task),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "oom_dump_tasks",
+		.data		= &sysctl_oom_dump_tasks,
+		.maxlen		= sizeof(sysctl_oom_dump_tasks),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= VM_OVERCOMMIT_RATIO,
+		.procname	= "overcommit_ratio",
+		.data		= &sysctl_overcommit_ratio,
+		.maxlen		= sizeof(sysctl_overcommit_ratio),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= VM_PAGE_CLUSTER,
+		.procname	= "page-cluster", 
+		.data		= &page_cluster,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= VM_DIRTY_BACKGROUND,
+		.procname	= "dirty_background_ratio",
+		.data		= &dirty_background_ratio,
+		.maxlen		= sizeof(dirty_background_ratio),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+		.extra2		= &one_hundred,
+	},
+	{
+		.ctl_name	= VM_DIRTY_RATIO,
+		.procname	= "dirty_ratio",
+		.data		= &vm_dirty_ratio,
+		.maxlen		= sizeof(vm_dirty_ratio),
+		.mode		= 0644,
+		.proc_handler	= &dirty_ratio_handler,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+		.extra2		= &one_hundred,
+	},
+	{
+		.procname	= "dirty_writeback_centisecs",
+		.data		= &dirty_writeback_interval,
+		.maxlen		= sizeof(dirty_writeback_interval),
+		.mode		= 0644,
+		.proc_handler	= &dirty_writeback_centisecs_handler,
+	},
+	{
+		.procname	= "dirty_expire_centisecs",
+		.data		= &dirty_expire_interval,
+		.maxlen		= sizeof(dirty_expire_interval),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_userhz_jiffies,
+	},
+	{
+		.ctl_name	= VM_NR_PDFLUSH_THREADS,
+		.procname	= "nr_pdflush_threads",
+		.data		= &nr_pdflush_threads,
+		.maxlen		= sizeof nr_pdflush_threads,
+		.mode		= 0444 /* read-only*/,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= VM_SWAPPINESS,
+		.procname	= "swappiness",
+		.data		= &vm_swappiness,
+		.maxlen		= sizeof(vm_swappiness),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+		.extra2		= &one_hundred,
+	},
+#ifdef CONFIG_HUGETLB_PAGE
+	 {
+		.procname	= "nr_hugepages",
+		.data		= &max_huge_pages,
+		.maxlen		= sizeof(unsigned long),
+		.mode		= 0644,
+		.proc_handler	= &hugetlb_sysctl_handler,
+		.extra1		= (void *)&hugetlb_zero,
+		.extra2		= (void *)&hugetlb_infinity,
+	 },
+	 {
+		.ctl_name	= VM_HUGETLB_GROUP,
+		.procname	= "hugetlb_shm_group",
+		.data		= &sysctl_hugetlb_shm_group,
+		.maxlen		= sizeof(gid_t),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	 },
+	 {
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "hugepages_treat_as_movable",
+		.data		= &hugepages_treat_as_movable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &hugetlb_treat_movable_handler,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "nr_overcommit_hugepages",
+		.data		= &sysctl_overcommit_huge_pages,
+		.maxlen		= sizeof(sysctl_overcommit_huge_pages),
+		.mode		= 0644,
+		.proc_handler	= &hugetlb_overcommit_handler,
+	},
+#endif
+	{
+		.ctl_name	= VM_LOWMEM_RESERVE_RATIO,
+		.procname	= "lowmem_reserve_ratio",
+		.data		= &sysctl_lowmem_reserve_ratio,
+		.maxlen		= sizeof(sysctl_lowmem_reserve_ratio),
+		.mode		= 0644,
+		.proc_handler	= &lowmem_reserve_ratio_sysctl_handler,
+		.strategy	= &sysctl_intvec,
+	},
+	{
+		.ctl_name	= VM_DROP_PAGECACHE,
+		.procname	= "drop_caches",
+		.data		= &sysctl_drop_caches,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= drop_caches_sysctl_handler,
+		.strategy	= &sysctl_intvec,
+	},
+	{
+		.ctl_name	= VM_MIN_FREE_KBYTES,
+		.procname	= "min_free_kbytes",
+		.data		= &min_free_kbytes,
+		.maxlen		= sizeof(min_free_kbytes),
+		.mode		= 0644,
+		.proc_handler	= &min_free_kbytes_sysctl_handler,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+	},
+	{
+		.ctl_name	= VM_PERCPU_PAGELIST_FRACTION,
+		.procname	= "percpu_pagelist_fraction",
+		.data		= &percpu_pagelist_fraction,
+		.maxlen		= sizeof(percpu_pagelist_fraction),
+		.mode		= 0644,
+		.proc_handler	= &percpu_pagelist_fraction_sysctl_handler,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &min_percpu_pagelist_fract,
+	},
+#ifdef CONFIG_MMU
+	{
+		.ctl_name	= VM_MAX_MAP_COUNT,
+		.procname	= "max_map_count",
+		.data		= &sysctl_max_map_count,
+		.maxlen		= sizeof(sysctl_max_map_count),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec
+	},
+#endif
+	{
+		.ctl_name	= VM_LAPTOP_MODE,
+		.procname	= "laptop_mode",
+		.data		= &laptop_mode,
+		.maxlen		= sizeof(laptop_mode),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_jiffies,
+		.strategy	= &sysctl_jiffies,
+	},
+	{
+		.ctl_name	= VM_BLOCK_DUMP,
+		.procname	= "block_dump",
+		.data		= &block_dump,
+		.maxlen		= sizeof(block_dump),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+	},
+	{
+		.ctl_name	= VM_VFS_CACHE_PRESSURE,
+		.procname	= "vfs_cache_pressure",
+		.data		= &sysctl_vfs_cache_pressure,
+		.maxlen		= sizeof(sysctl_vfs_cache_pressure),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+	},
+#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT
+	{
+		.ctl_name	= VM_LEGACY_VA_LAYOUT,
+		.procname	= "legacy_va_layout",
+		.data		= &sysctl_legacy_va_layout,
+		.maxlen		= sizeof(sysctl_legacy_va_layout),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+	},
+#endif
+#ifdef CONFIG_NUMA
+	{
+		.ctl_name	= VM_ZONE_RECLAIM_MODE,
+		.procname	= "zone_reclaim_mode",
+		.data		= &zone_reclaim_mode,
+		.maxlen		= sizeof(zone_reclaim_mode),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+	},
+	{
+		.ctl_name	= VM_MIN_UNMAPPED,
+		.procname	= "min_unmapped_ratio",
+		.data		= &sysctl_min_unmapped_ratio,
+		.maxlen		= sizeof(sysctl_min_unmapped_ratio),
+		.mode		= 0644,
+		.proc_handler	= &sysctl_min_unmapped_ratio_sysctl_handler,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+		.extra2		= &one_hundred,
+	},
+	{
+		.ctl_name	= VM_MIN_SLAB,
+		.procname	= "min_slab_ratio",
+		.data		= &sysctl_min_slab_ratio,
+		.maxlen		= sizeof(sysctl_min_slab_ratio),
+		.mode		= 0644,
+		.proc_handler	= &sysctl_min_slab_ratio_sysctl_handler,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+		.extra2		= &one_hundred,
+	},
+#endif
+#ifdef CONFIG_SMP
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "stat_interval",
+		.data		= &sysctl_stat_interval,
+		.maxlen		= sizeof(sysctl_stat_interval),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_jiffies,
+		.strategy	= &sysctl_jiffies,
+	},
+#endif
+#ifdef CONFIG_SECURITY
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "mmap_min_addr",
+		.data		= &mmap_min_addr,
+		.maxlen         = sizeof(unsigned long),
+		.mode		= 0644,
+		.proc_handler	= &proc_doulongvec_minmax,
+	},
+#endif
+#ifdef CONFIG_NUMA
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "numa_zonelist_order",
+		.data		= &numa_zonelist_order,
+		.maxlen		= NUMA_ZONELIST_ORDER_LEN,
+		.mode		= 0644,
+		.proc_handler	= &numa_zonelist_order_handler,
+		.strategy	= &sysctl_string,
+	},
+#endif
+#if (defined(CONFIG_X86_32) && !defined(CONFIG_UML))|| \
+   (defined(CONFIG_SUPERH) && defined(CONFIG_VSYSCALL))
+	{
+		.ctl_name	= VM_VDSO_ENABLED,
+		.procname	= "vdso_enabled",
+		.data		= &vdso_enabled,
+		.maxlen		= sizeof(vdso_enabled),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+	},
+#endif
+#ifdef CONFIG_HIGHMEM
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "highmem_is_dirtyable",
+		.data		= &vm_highmem_is_dirtyable,
+		.maxlen		= sizeof(vm_highmem_is_dirtyable),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+#endif
+/*
+ * NOTE: do not add new entries to this table unless you have read
+ * Documentation/sysctl/ctl_unnumbered.txt
+ */
+	{ .ctl_name = 0 }
+};
+
+#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
+static struct ctl_table binfmt_misc_table[] = {
+	{ .ctl_name = 0 }
+};
+#endif
+
+static struct ctl_table fs_table[] = {
+	{
+		.ctl_name	= FS_NRINODE,
+		.procname	= "inode-nr",
+		.data		= &inodes_stat,
+		.maxlen		= 2*sizeof(int),
+		.mode		= 0444,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= FS_STATINODE,
+		.procname	= "inode-state",
+		.data		= &inodes_stat,
+		.maxlen		= 7*sizeof(int),
+		.mode		= 0444,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.procname	= "file-nr",
+		.data		= &files_stat,
+		.maxlen		= 3*sizeof(int),
+		.mode		= 0444,
+		.proc_handler	= &proc_nr_files,
+	},
+	{
+		.ctl_name	= FS_MAXFILE,
+		.procname	= "file-max",
+		.data		= &files_stat.max_files,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "nr_open",
+		.data		= &sysctl_nr_open,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.extra1		= &sysctl_nr_open_min,
+		.extra2		= &sysctl_nr_open_max,
+	},
+	{
+		.ctl_name	= FS_DENTRY,
+		.procname	= "dentry-state",
+		.data		= &dentry_stat,
+		.maxlen		= 6*sizeof(int),
+		.mode		= 0444,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= FS_OVERFLOWUID,
+		.procname	= "overflowuid",
+		.data		= &fs_overflowuid,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &minolduid,
+		.extra2		= &maxolduid,
+	},
+	{
+		.ctl_name	= FS_OVERFLOWGID,
+		.procname	= "overflowgid",
+		.data		= &fs_overflowgid,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &minolduid,
+		.extra2		= &maxolduid,
+	},
+	{
+		.ctl_name	= FS_LEASES,
+		.procname	= "leases-enable",
+		.data		= &leases_enable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#ifdef CONFIG_DNOTIFY
+	{
+		.ctl_name	= FS_DIR_NOTIFY,
+		.procname	= "dir-notify-enable",
+		.data		= &dir_notify_enable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+#ifdef CONFIG_MMU
+	{
+		.ctl_name	= FS_LEASE_TIME,
+		.procname	= "lease-break-time",
+		.data		= &lease_break_time,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+		.extra2		= &two,
+	},
+	{
+		.procname	= "aio-nr",
+		.data		= &aio_nr,
+		.maxlen		= sizeof(aio_nr),
+		.mode		= 0444,
+		.proc_handler	= &proc_doulongvec_minmax,
+	},
+	{
+		.procname	= "aio-max-nr",
+		.data		= &aio_max_nr,
+		.maxlen		= sizeof(aio_max_nr),
+		.mode		= 0644,
+		.proc_handler	= &proc_doulongvec_minmax,
+	},
+#ifdef CONFIG_INOTIFY_USER
+	{
+		.ctl_name	= FS_INOTIFY,
+		.procname	= "inotify",
+		.mode		= 0555,
+		.child		= inotify_table,
+	},
+#endif	
+#endif
+	{
+		.ctl_name	= KERN_SETUID_DUMPABLE,
+		.procname	= "suid_dumpable",
+		.data		= &suid_dumpable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "binfmt_misc",
+		.mode		= 0555,
+		.child		= binfmt_misc_table,
+	},
+#endif
+/*
+ * NOTE: do not add new entries to this table unless you have read
+ * Documentation/sysctl/ctl_unnumbered.txt
+ */
+	{ .ctl_name = 0 }
+};
+
+static struct ctl_table debug_table[] = {
+#if defined(CONFIG_X86) || defined(CONFIG_PPC)
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "exception-trace",
+		.data		= &show_unhandled_signals,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+#endif
+	{ .ctl_name = 0 }
+};
+
+static struct ctl_table dev_table[] = {
+	{ .ctl_name = 0 }
+};
+
+static DEFINE_SPINLOCK(sysctl_lock);
+
+/* called under sysctl_lock */
+static int use_table(struct ctl_table_header *p)
+{
+	if (unlikely(p->unregistering))
+		return 0;
+	p->used++;
+	return 1;
+}
+
+/* called under sysctl_lock */
+static void unuse_table(struct ctl_table_header *p)
+{
+	if (!--p->used)
+		if (unlikely(p->unregistering))
+			complete(p->unregistering);
+}
+
+/* called under sysctl_lock, will reacquire if has to wait */
+static void start_unregistering(struct ctl_table_header *p)
+{
+	/*
+	 * if p->used is 0, nobody will ever touch that entry again;
+	 * we'll eliminate all paths to it before dropping sysctl_lock
+	 */
+	if (unlikely(p->used)) {
+		struct completion wait;
+		init_completion(&wait);
+		p->unregistering = &wait;
+		spin_unlock(&sysctl_lock);
+		wait_for_completion(&wait);
+		spin_lock(&sysctl_lock);
+	}
+	/*
+	 * do not remove from the list until nobody holds it; walking the
+	 * list in do_sysctl() relies on that.
+	 */
+	list_del_init(&p->ctl_entry);
+}
+
+void sysctl_head_finish(struct ctl_table_header *head)
+{
+	if (!head)
+		return;
+	spin_lock(&sysctl_lock);
+	unuse_table(head);
+	spin_unlock(&sysctl_lock);
+}
+
+static struct list_head *
+lookup_header_list(struct ctl_table_root *root, struct nsproxy *namespaces)
+{
+	struct list_head *header_list;
+	header_list = &root->header_list;
+	if (root->lookup)
+		header_list = root->lookup(root, namespaces);
+	return header_list;
+}
+
+struct ctl_table_header *__sysctl_head_next(struct nsproxy *namespaces,
+					    struct ctl_table_header *prev)
+{
+	struct ctl_table_root *root;
+	struct list_head *header_list;
+	struct ctl_table_header *head;
+	struct list_head *tmp;
+
+	spin_lock(&sysctl_lock);
+	if (prev) {
+		head = prev;
+		tmp = &prev->ctl_entry;
+		unuse_table(prev);
+		goto next;
+	}
+	tmp = &root_table_header.ctl_entry;
+	for (;;) {
+		head = list_entry(tmp, struct ctl_table_header, ctl_entry);
+
+		if (!use_table(head))
+			goto next;
+		spin_unlock(&sysctl_lock);
+		return head;
+	next:
+		root = head->root;
+		tmp = tmp->next;
+		header_list = lookup_header_list(root, namespaces);
+		if (tmp != header_list)
+			continue;
+
+		do {
+			root = list_entry(root->root_list.next,
+					struct ctl_table_root, root_list);
+			if (root == &sysctl_table_root)
+				goto out;
+			header_list = lookup_header_list(root, namespaces);
+		} while (list_empty(header_list));
+		tmp = header_list->next;
+	}
+out:
+	spin_unlock(&sysctl_lock);
+	return NULL;
+}
+
+struct ctl_table_header *sysctl_head_next(struct ctl_table_header *prev)
+{
+	return __sysctl_head_next(current->nsproxy, prev);
+}
+
+void register_sysctl_root(struct ctl_table_root *root)
+{
+	spin_lock(&sysctl_lock);
+	list_add_tail(&root->root_list, &sysctl_table_root.root_list);
+	spin_unlock(&sysctl_lock);
+}
+
+#ifdef CONFIG_SYSCTL_SYSCALL
+/* Perform the actual read/write of a sysctl table entry. */
+static int do_sysctl_strategy(struct ctl_table_root *root,
+			struct ctl_table *table,
+			int __user *name, int nlen,
+			void __user *oldval, size_t __user *oldlenp,
+			void __user *newval, size_t newlen)
+{
+	int op = 0, rc;
+
+	if (oldval)
+		op |= 004;
+	if (newval)
+		op |= 002;
+	if (sysctl_perm(root, table, op))
+		return -EPERM;
+
+	if (table->strategy) {
+		rc = table->strategy(table, name, nlen, oldval, oldlenp,
+				     newval, newlen);
+		if (rc < 0)
+			return rc;
+		if (rc > 0)
+			return 0;
+	}
+
+	/* If there is no strategy routine, or if the strategy returns
+	 * zero, proceed with automatic r/w */
+	if (table->data && table->maxlen) {
+		rc = sysctl_data(table, name, nlen, oldval, oldlenp,
+				 newval, newlen);
+		if (rc < 0)
+			return rc;
+	}
+	return 0;
+}
+
+static int parse_table(int __user *name, int nlen,
+		       void __user *oldval, size_t __user *oldlenp,
+		       void __user *newval, size_t newlen,
+		       struct ctl_table_root *root,
+		       struct ctl_table *table)
+{
+	int n;
+repeat:
+	if (!nlen)
+		return -ENOTDIR;
+	if (get_user(n, name))
+		return -EFAULT;
+	for ( ; table->ctl_name || table->procname; table++) {
+		if (!table->ctl_name)
+			continue;
+		if (n == table->ctl_name) {
+			int error;
+			if (table->child) {
+				if (sysctl_perm(root, table, 001))
+					return -EPERM;
+				name++;
+				nlen--;
+				table = table->child;
+				goto repeat;
+			}
+			error = do_sysctl_strategy(root, table, name, nlen,
+						   oldval, oldlenp,
+						   newval, newlen);
+			return error;
+		}
+	}
+	return -ENOTDIR;
+}
+
+int do_sysctl(int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp,
+	       void __user *newval, size_t newlen)
+{
+	struct ctl_table_header *head;
+	int error = -ENOTDIR;
+
+	if (nlen <= 0 || nlen >= CTL_MAXNAME)
+		return -ENOTDIR;
+	if (oldval) {
+		int old_len;
+		if (!oldlenp || get_user(old_len, oldlenp))
+			return -EFAULT;
+	}
+
+	for (head = sysctl_head_next(NULL); head;
+			head = sysctl_head_next(head)) {
+		error = parse_table(name, nlen, oldval, oldlenp, 
+					newval, newlen,
+					head->root, head->ctl_table);
+		if (error != -ENOTDIR) {
+			sysctl_head_finish(head);
+			break;
+		}
+	}
+	return error;
+}
+
+asmlinkage long sys_sysctl(struct __sysctl_args __user *args)
+{
+	struct __sysctl_args tmp;
+	int error;
+
+	if (copy_from_user(&tmp, args, sizeof(tmp)))
+		return -EFAULT;
+
+	error = deprecated_sysctl_warning(&tmp);
+	if (error)
+		goto out;
+
+	lock_kernel();
+	error = do_sysctl(tmp.name, tmp.nlen, tmp.oldval, tmp.oldlenp,
+			  tmp.newval, tmp.newlen);
+	unlock_kernel();
+out:
+	return error;
+}
+#endif /* CONFIG_SYSCTL_SYSCALL */
+
+/*
+ * sysctl_perm does NOT grant the superuser all rights automatically, because
+ * some sysctl variables are readonly even to root.
+ */
+
+static int test_perm(int mode, int op)
+{
+	if (!current->euid)
+		mode >>= 6;
+	else if (in_egroup_p(0))
+		mode >>= 3;
+	if ((mode & op & 0007) == op)
+		return 0;
+	return -EACCES;
+}
+
+int sysctl_perm(struct ctl_table_root *root, struct ctl_table *table, int op)
+{
+	int error;
+	int mode;
+
+	error = security_sysctl(table, op);
+	if (error)
+		return error;
+
+	if (root->permissions)
+		mode = root->permissions(root, current->nsproxy, table);
+	else
+		mode = table->mode;
+
+	return test_perm(mode, op);
+}
+
+static void sysctl_set_parent(struct ctl_table *parent, struct ctl_table *table)
+{
+	for (; table->ctl_name || table->procname; table++) {
+		table->parent = parent;
+		if (table->child)
+			sysctl_set_parent(table, table->child);
+	}
+}
+
+static __init int sysctl_init(void)
+{
+	sysctl_set_parent(NULL, root_table);
+#ifdef CONFIG_SYSCTL_SYSCALL_CHECK
+	{
+		int err;
+		err = sysctl_check_table(current->nsproxy, root_table);
+	}
+#endif
+	return 0;
+}
+
+core_initcall(sysctl_init);
+
+/**
+ * __register_sysctl_paths - register a sysctl hierarchy
+ * @root: List of sysctl headers to register on
+ * @namespaces: Data to compute which lists of sysctl entries are visible
+ * @path: The path to the directory the sysctl table is in.
+ * @table: the top-level table structure
+ *
+ * Register a sysctl table hierarchy. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * The members of the &struct ctl_table structure are used as follows:
+ *
+ * ctl_name - This is the numeric sysctl value used by sysctl(2). The number
+ *            must be unique within that level of sysctl
+ *
+ * procname - the name of the sysctl file under /proc/sys. Set to %NULL to not
+ *            enter a sysctl file
+ *
+ * data - a pointer to data for use by proc_handler
+ *
+ * maxlen - the maximum size in bytes of the data
+ *
+ * mode - the file permissions for the /proc/sys file, and for sysctl(2)
+ *
+ * child - a pointer to the child sysctl table if this entry is a directory, or
+ *         %NULL.
+ *
+ * proc_handler - the text handler routine (described below)
+ *
+ * strategy - the strategy routine (described below)
+ *
+ * de - for internal use by the sysctl routines
+ *
+ * extra1, extra2 - extra pointers usable by the proc handler routines
+ *
+ * Leaf nodes in the sysctl tree will be represented by a single file
+ * under /proc; non-leaf nodes will be represented by directories.
+ *
+ * sysctl(2) can automatically manage read and write requests through
+ * the sysctl table.  The data and maxlen fields of the ctl_table
+ * struct enable minimal validation of the values being written to be
+ * performed, and the mode field allows minimal authentication.
+ *
+ * More sophisticated management can be enabled by the provision of a
+ * strategy routine with the table entry.  This will be called before
+ * any automatic read or write of the data is performed.
+ *
+ * The strategy routine may return
+ *
+ * < 0 - Error occurred (error is passed to user process)
+ *
+ * 0   - OK - proceed with automatic read or write.
+ *
+ * > 0 - OK - read or write has been done by the strategy routine, so
+ *       return immediately.
+ *
+ * There must be a proc_handler routine for any terminal nodes
+ * mirrored under /proc/sys (non-terminals are handled by a built-in
+ * directory handler).  Several default handlers are available to
+ * cover common cases -
+ *
+ * proc_dostring(), proc_dointvec(), proc_dointvec_jiffies(),
+ * proc_dointvec_userhz_jiffies(), proc_dointvec_minmax(), 
+ * proc_doulongvec_ms_jiffies_minmax(), proc_doulongvec_minmax()
+ *
+ * It is the handler's job to read the input buffer from user memory
+ * and process it. The handler should return 0 on success.
+ *
+ * This routine returns %NULL on a failure to register, and a pointer
+ * to the table header on success.
+ */
+struct ctl_table_header *__register_sysctl_paths(
+	struct ctl_table_root *root,
+	struct nsproxy *namespaces,
+	const struct ctl_path *path, struct ctl_table *table)
+{
+	struct list_head *header_list;
+	struct ctl_table_header *header;
+	struct ctl_table *new, **prevp;
+	unsigned int n, npath;
+
+	/* Count the path components */
+	for (npath = 0; path[npath].ctl_name || path[npath].procname; ++npath)
+		;
+
+	/*
+	 * For each path component, allocate a 2-element ctl_table array.
+	 * The first array element will be filled with the sysctl entry
+	 * for this, the second will be the sentinel (ctl_name == 0).
+	 *
+	 * We allocate everything in one go so that we don't have to
+	 * worry about freeing additional memory in unregister_sysctl_table.
+	 */
+	header = kzalloc(sizeof(struct ctl_table_header) +
+			 (2 * npath * sizeof(struct ctl_table)), GFP_KERNEL);
+	if (!header)
+		return NULL;
+
+	new = (struct ctl_table *) (header + 1);
+
+	/* Now connect the dots */
+	prevp = &header->ctl_table;
+	for (n = 0; n < npath; ++n, ++path) {
+		/* Copy the procname */
+		new->procname = path->procname;
+		new->ctl_name = path->ctl_name;
+		new->mode     = 0555;
+
+		*prevp = new;
+		prevp = &new->child;
+
+		new += 2;
+	}
+	*prevp = table;
+	header->ctl_table_arg = table;
+
+	INIT_LIST_HEAD(&header->ctl_entry);
+	header->used = 0;
+	header->unregistering = NULL;
+	header->root = root;
+	sysctl_set_parent(NULL, header->ctl_table);
+#ifdef CONFIG_SYSCTL_SYSCALL_CHECK
+	if (sysctl_check_table(namespaces, header->ctl_table)) {
+		kfree(header);
+		return NULL;
+	}
+#endif
+	spin_lock(&sysctl_lock);
+	header_list = lookup_header_list(root, namespaces);
+	list_add_tail(&header->ctl_entry, header_list);
+	spin_unlock(&sysctl_lock);
+
+	return header;
+}
+
+/**
+ * register_sysctl_table_path - register a sysctl table hierarchy
+ * @path: The path to the directory the sysctl table is in.
+ * @table: the top-level table structure
+ *
+ * Register a sysctl table hierarchy. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * See __register_sysctl_paths for more details.
+ */
+struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path,
+						struct ctl_table *table)
+{
+	return __register_sysctl_paths(&sysctl_table_root, current->nsproxy,
+					path, table);
+}
+
+/**
+ * register_sysctl_table - register a sysctl table hierarchy
+ * @table: the top-level table structure
+ *
+ * Register a sysctl table hierarchy. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * See register_sysctl_paths for more details.
+ */
+struct ctl_table_header *register_sysctl_table(struct ctl_table *table)
+{
+	static const struct ctl_path null_path[] = { {} };
+
+	return register_sysctl_paths(null_path, table);
+}
+
+/**
+ * unregister_sysctl_table - unregister a sysctl table hierarchy
+ * @header: the header returned from register_sysctl_table
+ *
+ * Unregisters the sysctl table and all children. proc entries may not
+ * actually be removed until they are no longer used by anyone.
+ */
+void unregister_sysctl_table(struct ctl_table_header * header)
+{
+	might_sleep();
+
+	if (header == NULL)
+		return;
+
+	spin_lock(&sysctl_lock);
+	start_unregistering(header);
+	spin_unlock(&sysctl_lock);
+	kfree(header);
+}
+
+#else /* !CONFIG_SYSCTL */
+struct ctl_table_header *register_sysctl_table(struct ctl_table * table)
+{
+	return NULL;
+}
+
+struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path,
+						    struct ctl_table *table)
+{
+	return NULL;
+}
+
+void unregister_sysctl_table(struct ctl_table_header * table)
+{
+}
+
+#endif /* CONFIG_SYSCTL */
+
+/*
+ * /proc/sys support
+ */
+
+#ifdef CONFIG_PROC_SYSCTL
+
+static int _proc_do_string(void* data, int maxlen, int write,
+			   struct file *filp, void __user *buffer,
+			   size_t *lenp, loff_t *ppos)
+{
+	size_t len;
+	char __user *p;
+	char c;
+
+	if (!data || !maxlen || !*lenp) {
+		*lenp = 0;
+		return 0;
+	}
+
+	if (write) {
+		len = 0;
+		p = buffer;
+		while (len < *lenp) {
+			if (get_user(c, p++))
+				return -EFAULT;
+			if (c == 0 || c == '\n')
+				break;
+			len++;
+		}
+		if (len >= maxlen)
+			len = maxlen-1;
+		if(copy_from_user(data, buffer, len))
+			return -EFAULT;
+		((char *) data)[len] = 0;
+		*ppos += *lenp;
+	} else {
+		len = strlen(data);
+		if (len > maxlen)
+			len = maxlen;
+
+		if (*ppos > len) {
+			*lenp = 0;
+			return 0;
+		}
+
+		data += *ppos;
+		len  -= *ppos;
+
+		if (len > *lenp)
+			len = *lenp;
+		if (len)
+			if(copy_to_user(buffer, data, len))
+				return -EFAULT;
+		if (len < *lenp) {
+			if(put_user('\n', ((char __user *) buffer) + len))
+				return -EFAULT;
+			len++;
+		}
+		*lenp = len;
+		*ppos += len;
+	}
+	return 0;
+}
+
+/**
+ * proc_dostring - read a string sysctl
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @filp: the file structure
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes a string from/to the user buffer. If the kernel
+ * buffer provided is not large enough to hold the string, the
+ * string is truncated. The copied string is %NULL-terminated.
+ * If the string is being read by the user process, it is copied
+ * and a newline '\n' is added. It is truncated if the buffer is
+ * not large enough.
+ *
+ * Returns 0 on success.
+ */
+int proc_dostring(struct ctl_table *table, int write, struct file *filp,
+		  void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	return _proc_do_string(table->data, table->maxlen, write, filp,
+			       buffer, lenp, ppos);
+}
+
+
+static int do_proc_dointvec_conv(int *negp, unsigned long *lvalp,
+				 int *valp,
+				 int write, void *data)
+{
+	if (write) {
+		*valp = *negp ? -*lvalp : *lvalp;
+	} else {
+		int val = *valp;
+		if (val < 0) {
+			*negp = -1;
+			*lvalp = (unsigned long)-val;
+		} else {
+			*negp = 0;
+			*lvalp = (unsigned long)val;
+		}
+	}
+	return 0;
+}
+
+static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
+		  int write, struct file *filp, void __user *buffer,
+		  size_t *lenp, loff_t *ppos,
+		  int (*conv)(int *negp, unsigned long *lvalp, int *valp,
+			      int write, void *data),
+		  void *data)
+{
+#define TMPBUFLEN 21
+	int *i, vleft, first=1, neg, val;
+	unsigned long lval;
+	size_t left, len;
+	
+	char buf[TMPBUFLEN], *p;
+	char __user *s = buffer;
+	
+	if (!tbl_data || !table->maxlen || !*lenp ||
+	    (*ppos && !write)) {
+		*lenp = 0;
+		return 0;
+	}
+	
+	i = (int *) tbl_data;
+	vleft = table->maxlen / sizeof(*i);
+	left = *lenp;
+
+	if (!conv)
+		conv = do_proc_dointvec_conv;
+
+	for (; left && vleft--; i++, first=0) {
+		if (write) {
+			while (left) {
+				char c;
+				if (get_user(c, s))
+					return -EFAULT;
+				if (!isspace(c))
+					break;
+				left--;
+				s++;
+			}
+			if (!left)
+				break;
+			neg = 0;
+			len = left;
+			if (len > sizeof(buf) - 1)
+				len = sizeof(buf) - 1;
+			if (copy_from_user(buf, s, len))
+				return -EFAULT;
+			buf[len] = 0;
+			p = buf;
+			if (*p == '-' && left > 1) {
+				neg = 1;
+				p++;
+			}
+			if (*p < '0' || *p > '9')
+				break;
+
+			lval = simple_strtoul(p, &p, 0);
+
+			len = p-buf;
+			if ((len < left) && *p && !isspace(*p))
+				break;
+			if (neg)
+				val = -val;
+			s += len;
+			left -= len;
+
+			if (conv(&neg, &lval, i, 1, data))
+				break;
+		} else {
+			p = buf;
+			if (!first)
+				*p++ = '\t';
+	
+			if (conv(&neg, &lval, i, 0, data))
+				break;
+
+			sprintf(p, "%s%lu", neg ? "-" : "", lval);
+			len = strlen(buf);
+			if (len > left)
+				len = left;
+			if(copy_to_user(s, buf, len))
+				return -EFAULT;
+			left -= len;
+			s += len;
+		}
+	}
+
+	if (!write && !first && left) {
+		if(put_user('\n', s))
+			return -EFAULT;
+		left--, s++;
+	}
+	if (write) {
+		while (left) {
+			char c;
+			if (get_user(c, s++))
+				return -EFAULT;
+			if (!isspace(c))
+				break;
+			left--;
+		}
+	}
+	if (write && first)
+		return -EINVAL;
+	*lenp -= left;
+	*ppos += *lenp;
+	return 0;
+#undef TMPBUFLEN
+}
+
+static int do_proc_dointvec(struct ctl_table *table, int write, struct file *filp,
+		  void __user *buffer, size_t *lenp, loff_t *ppos,
+		  int (*conv)(int *negp, unsigned long *lvalp, int *valp,
+			      int write, void *data),
+		  void *data)
+{
+	return __do_proc_dointvec(table->data, table, write, filp,
+			buffer, lenp, ppos, conv, data);
+}
+
+/**
+ * proc_dointvec - read a vector of integers
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @filp: the file structure
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
+ * values from/to the user buffer, treated as an ASCII string. 
+ *
+ * Returns 0 on success.
+ */
+int proc_dointvec(struct ctl_table *table, int write, struct file *filp,
+		     void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+    return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
+		    	    NULL,NULL);
+}
+
+#define OP_SET	0
+#define OP_AND	1
+#define OP_OR	2
+
+static int do_proc_dointvec_bset_conv(int *negp, unsigned long *lvalp,
+				      int *valp,
+				      int write, void *data)
+{
+	int op = *(int *)data;
+	if (write) {
+		int val = *negp ? -*lvalp : *lvalp;
+		switch(op) {
+		case OP_SET:	*valp = val; break;
+		case OP_AND:	*valp &= val; break;
+		case OP_OR:	*valp |= val; break;
+		}
+	} else {
+		int val = *valp;
+		if (val < 0) {
+			*negp = -1;
+			*lvalp = (unsigned long)-val;
+		} else {
+			*negp = 0;
+			*lvalp = (unsigned long)val;
+		}
+	}
+	return 0;
+}
+
+/*
+ *	Taint values can only be increased
+ */
+static int proc_dointvec_taint(struct ctl_table *table, int write, struct file *filp,
+			       void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	int op;
+
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	op = OP_OR;
+	return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
+				do_proc_dointvec_bset_conv,&op);
+}
+
+struct do_proc_dointvec_minmax_conv_param {
+	int *min;
+	int *max;
+};
+
+static int do_proc_dointvec_minmax_conv(int *negp, unsigned long *lvalp, 
+					int *valp, 
+					int write, void *data)
+{
+	struct do_proc_dointvec_minmax_conv_param *param = data;
+	if (write) {
+		int val = *negp ? -*lvalp : *lvalp;
+		if ((param->min && *param->min > val) ||
+		    (param->max && *param->max < val))
+			return -EINVAL;
+		*valp = val;
+	} else {
+		int val = *valp;
+		if (val < 0) {
+			*negp = -1;
+			*lvalp = (unsigned long)-val;
+		} else {
+			*negp = 0;
+			*lvalp = (unsigned long)val;
+		}
+	}
+	return 0;
+}
+
+/**
+ * proc_dointvec_minmax - read a vector of integers with min/max values
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @filp: the file structure
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
+ * values from/to the user buffer, treated as an ASCII string.
+ *
+ * This routine will ensure the values are within the range specified by
+ * table->extra1 (min) and table->extra2 (max).
+ *
+ * Returns 0 on success.
+ */
+int proc_dointvec_minmax(struct ctl_table *table, int write, struct file *filp,
+		  void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct do_proc_dointvec_minmax_conv_param param = {
+		.min = (int *) table->extra1,
+		.max = (int *) table->extra2,
+	};
+	return do_proc_dointvec(table, write, filp, buffer, lenp, ppos,
+				do_proc_dointvec_minmax_conv, &param);
+}
+
+static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int write,
+				     struct file *filp,
+				     void __user *buffer,
+				     size_t *lenp, loff_t *ppos,
+				     unsigned long convmul,
+				     unsigned long convdiv)
+{
+#define TMPBUFLEN 21
+	unsigned long *i, *min, *max, val;
+	int vleft, first=1, neg;
+	size_t len, left;
+	char buf[TMPBUFLEN], *p;
+	char __user *s = buffer;
+	
+	if (!data || !table->maxlen || !*lenp ||
+	    (*ppos && !write)) {
+		*lenp = 0;
+		return 0;
+	}
+	
+	i = (unsigned long *) data;
+	min = (unsigned long *) table->extra1;
+	max = (unsigned long *) table->extra2;
+	vleft = table->maxlen / sizeof(unsigned long);
+	left = *lenp;
+	
+	for (; left && vleft--; i++, min++, max++, first=0) {
+		if (write) {
+			while (left) {
+				char c;
+				if (get_user(c, s))
+					return -EFAULT;
+				if (!isspace(c))
+					break;
+				left--;
+				s++;
+			}
+			if (!left)
+				break;
+			neg = 0;
+			len = left;
+			if (len > TMPBUFLEN-1)
+				len = TMPBUFLEN-1;
+			if (copy_from_user(buf, s, len))
+				return -EFAULT;
+			buf[len] = 0;
+			p = buf;
+			if (*p == '-' && left > 1) {
+				neg = 1;
+				p++;
+			}
+			if (*p < '0' || *p > '9')
+				break;
+			val = simple_strtoul(p, &p, 0) * convmul / convdiv ;
+			len = p-buf;
+			if ((len < left) && *p && !isspace(*p))
+				break;
+			if (neg)
+				val = -val;
+			s += len;
+			left -= len;
+
+			if(neg)
+				continue;
+			if ((min && val < *min) || (max && val > *max))
+				continue;
+			*i = val;
+		} else {
+			p = buf;
+			if (!first)
+				*p++ = '\t';
+			sprintf(p, "%lu", convdiv * (*i) / convmul);
+			len = strlen(buf);
+			if (len > left)
+				len = left;
+			if(copy_to_user(s, buf, len))
+				return -EFAULT;
+			left -= len;
+			s += len;
+		}
+	}
+
+	if (!write && !first && left) {
+		if(put_user('\n', s))
+			return -EFAULT;
+		left--, s++;
+	}
+	if (write) {
+		while (left) {
+			char c;
+			if (get_user(c, s++))
+				return -EFAULT;
+			if (!isspace(c))
+				break;
+			left--;
+		}
+	}
+	if (write && first)
+		return -EINVAL;
+	*lenp -= left;
+	*ppos += *lenp;
+	return 0;
+#undef TMPBUFLEN
+}
+
+static int do_proc_doulongvec_minmax(struct ctl_table *table, int write,
+				     struct file *filp,
+				     void __user *buffer,
+				     size_t *lenp, loff_t *ppos,
+				     unsigned long convmul,
+				     unsigned long convdiv)
+{
+	return __do_proc_doulongvec_minmax(table->data, table, write,
+			filp, buffer, lenp, ppos, convmul, convdiv);
+}
+
+/**
+ * proc_doulongvec_minmax - read a vector of long integers with min/max values
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @filp: the file structure
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned long) unsigned long
+ * values from/to the user buffer, treated as an ASCII string.
+ *
+ * This routine will ensure the values are within the range specified by
+ * table->extra1 (min) and table->extra2 (max).
+ *
+ * Returns 0 on success.
+ */
+int proc_doulongvec_minmax(struct ctl_table *table, int write, struct file *filp,
+			   void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+    return do_proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos, 1l, 1l);
+}
+
+/**
+ * proc_doulongvec_ms_jiffies_minmax - read a vector of millisecond values with min/max values
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @filp: the file structure
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned long) unsigned long
+ * values from/to the user buffer, treated as an ASCII string. The values
+ * are treated as milliseconds, and converted to jiffies when they are stored.
+ *
+ * This routine will ensure the values are within the range specified by
+ * table->extra1 (min) and table->extra2 (max).
+ *
+ * Returns 0 on success.
+ */
+int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
+				      struct file *filp,
+				      void __user *buffer,
+				      size_t *lenp, loff_t *ppos)
+{
+    return do_proc_doulongvec_minmax(table, write, filp, buffer,
+				     lenp, ppos, HZ, 1000l);
+}
+
+
+static int do_proc_dointvec_jiffies_conv(int *negp, unsigned long *lvalp,
+					 int *valp,
+					 int write, void *data)
+{
+	if (write) {
+		if (*lvalp > LONG_MAX / HZ)
+			return 1;
+		*valp = *negp ? -(*lvalp*HZ) : (*lvalp*HZ);
+	} else {
+		int val = *valp;
+		unsigned long lval;
+		if (val < 0) {
+			*negp = -1;
+			lval = (unsigned long)-val;
+		} else {
+			*negp = 0;
+			lval = (unsigned long)val;
+		}
+		*lvalp = lval / HZ;
+	}
+	return 0;
+}
+
+static int do_proc_dointvec_userhz_jiffies_conv(int *negp, unsigned long *lvalp,
+						int *valp,
+						int write, void *data)
+{
+	if (write) {
+		if (USER_HZ < HZ && *lvalp > (LONG_MAX / HZ) * USER_HZ)
+			return 1;
+		*valp = clock_t_to_jiffies(*negp ? -*lvalp : *lvalp);
+	} else {
+		int val = *valp;
+		unsigned long lval;
+		if (val < 0) {
+			*negp = -1;
+			lval = (unsigned long)-val;
+		} else {
+			*negp = 0;
+			lval = (unsigned long)val;
+		}
+		*lvalp = jiffies_to_clock_t(lval);
+	}
+	return 0;
+}
+
+static int do_proc_dointvec_ms_jiffies_conv(int *negp, unsigned long *lvalp,
+					    int *valp,
+					    int write, void *data)
+{
+	if (write) {
+		*valp = msecs_to_jiffies(*negp ? -*lvalp : *lvalp);
+	} else {
+		int val = *valp;
+		unsigned long lval;
+		if (val < 0) {
+			*negp = -1;
+			lval = (unsigned long)-val;
+		} else {
+			*negp = 0;
+			lval = (unsigned long)val;
+		}
+		*lvalp = jiffies_to_msecs(lval);
+	}
+	return 0;
+}
+
+/**
+ * proc_dointvec_jiffies - read a vector of integers as seconds
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @filp: the file structure
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
+ * values from/to the user buffer, treated as an ASCII string. 
+ * The values read are assumed to be in seconds, and are converted into
+ * jiffies.
+ *
+ * Returns 0 on success.
+ */
+int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp,
+			  void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+    return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
+		    	    do_proc_dointvec_jiffies_conv,NULL);
+}
+
+/**
+ * proc_dointvec_userhz_jiffies - read a vector of integers as 1/USER_HZ seconds
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @filp: the file structure
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: pointer to the file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
+ * values from/to the user buffer, treated as an ASCII string. 
+ * The values read are assumed to be in 1/USER_HZ seconds, and 
+ * are converted into jiffies.
+ *
+ * Returns 0 on success.
+ */
+int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file *filp,
+				 void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+    return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
+		    	    do_proc_dointvec_userhz_jiffies_conv,NULL);
+}
+
+/**
+ * proc_dointvec_ms_jiffies - read a vector of integers as 1 milliseconds
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @filp: the file structure
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ * @ppos: the current position in the file
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
+ * values from/to the user buffer, treated as an ASCII string. 
+ * The values read are assumed to be in 1/1000 seconds, and 
+ * are converted into jiffies.
+ *
+ * Returns 0 on success.
+ */
+int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, struct file *filp,
+			     void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	return do_proc_dointvec(table, write, filp, buffer, lenp, ppos,
+				do_proc_dointvec_ms_jiffies_conv, NULL);
+}
+
+static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp,
+			   void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct pid *new_pid;
+	pid_t tmp;
+	int r;
+
+	tmp = pid_vnr(cad_pid);
+
+	r = __do_proc_dointvec(&tmp, table, write, filp, buffer,
+			       lenp, ppos, NULL, NULL);
+	if (r || !write)
+		return r;
+
+	new_pid = find_get_pid(tmp);
+	if (!new_pid)
+		return -ESRCH;
+
+	put_pid(xchg(&cad_pid, new_pid));
+	return 0;
+}
+
+#else /* CONFIG_PROC_FS */
+
+int proc_dostring(struct ctl_table *table, int write, struct file *filp,
+		  void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	return -ENOSYS;
+}
+
+int proc_dointvec(struct ctl_table *table, int write, struct file *filp,
+		  void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	return -ENOSYS;
+}
+
+int proc_dointvec_minmax(struct ctl_table *table, int write, struct file *filp,
+		    void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	return -ENOSYS;
+}
+
+int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp,
+		    void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	return -ENOSYS;
+}
+
+int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file *filp,
+		    void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	return -ENOSYS;
+}
+
+int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, struct file *filp,
+			     void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	return -ENOSYS;
+}
+
+int proc_doulongvec_minmax(struct ctl_table *table, int write, struct file *filp,
+		    void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	return -ENOSYS;
+}
+
+int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
+				      struct file *filp,
+				      void __user *buffer,
+				      size_t *lenp, loff_t *ppos)
+{
+    return -ENOSYS;
+}
+
+
+#endif /* CONFIG_PROC_FS */
+
+
+#ifdef CONFIG_SYSCTL_SYSCALL
+/*
+ * General sysctl support routines 
+ */
+
+/* The generic sysctl data routine (used if no strategy routine supplied) */
+int sysctl_data(struct ctl_table *table, int __user *name, int nlen,
+		void __user *oldval, size_t __user *oldlenp,
+		void __user *newval, size_t newlen)
+{
+	size_t len;
+
+	/* Get out of I don't have a variable */
+	if (!table->data || !table->maxlen)
+		return -ENOTDIR;
+
+	if (oldval && oldlenp) {
+		if (get_user(len, oldlenp))
+			return -EFAULT;
+		if (len) {
+			if (len > table->maxlen)
+				len = table->maxlen;
+			if (copy_to_user(oldval, table->data, len))
+				return -EFAULT;
+			if (put_user(len, oldlenp))
+				return -EFAULT;
+		}
+	}
+
+	if (newval && newlen) {
+		if (newlen > table->maxlen)
+			newlen = table->maxlen;
+
+		if (copy_from_user(table->data, newval, newlen))
+			return -EFAULT;
+	}
+	return 1;
+}
+
+/* The generic string strategy routine: */
+int sysctl_string(struct ctl_table *table, int __user *name, int nlen,
+		  void __user *oldval, size_t __user *oldlenp,
+		  void __user *newval, size_t newlen)
+{
+	if (!table->data || !table->maxlen) 
+		return -ENOTDIR;
+	
+	if (oldval && oldlenp) {
+		size_t bufsize;
+		if (get_user(bufsize, oldlenp))
+			return -EFAULT;
+		if (bufsize) {
+			size_t len = strlen(table->data), copied;
+
+			/* This shouldn't trigger for a well-formed sysctl */
+			if (len > table->maxlen)
+				len = table->maxlen;
+
+			/* Copy up to a max of bufsize-1 bytes of the string */
+			copied = (len >= bufsize) ? bufsize - 1 : len;
+
+			if (copy_to_user(oldval, table->data, copied) ||
+			    put_user(0, (char __user *)(oldval + copied)))
+				return -EFAULT;
+			if (put_user(len, oldlenp))
+				return -EFAULT;
+		}
+	}
+	if (newval && newlen) {
+		size_t len = newlen;
+		if (len > table->maxlen)
+			len = table->maxlen;
+		if(copy_from_user(table->data, newval, len))
+			return -EFAULT;
+		if (len == table->maxlen)
+			len--;
+		((char *) table->data)[len] = 0;
+	}
+	return 1;
+}
+
+/*
+ * This function makes sure that all of the integers in the vector
+ * are between the minimum and maximum values given in the arrays
+ * table->extra1 and table->extra2, respectively.
+ */
+int sysctl_intvec(struct ctl_table *table, int __user *name, int nlen,
+		void __user *oldval, size_t __user *oldlenp,
+		void __user *newval, size_t newlen)
+{
+
+	if (newval && newlen) {
+		int __user *vec = (int __user *) newval;
+		int *min = (int *) table->extra1;
+		int *max = (int *) table->extra2;
+		size_t length;
+		int i;
+
+		if (newlen % sizeof(int) != 0)
+			return -EINVAL;
+
+		if (!table->extra1 && !table->extra2)
+			return 0;
+
+		if (newlen > table->maxlen)
+			newlen = table->maxlen;
+		length = newlen / sizeof(int);
+
+		for (i = 0; i < length; i++) {
+			int value;
+			if (get_user(value, vec + i))
+				return -EFAULT;
+			if (min && value < min[i])
+				return -EINVAL;
+			if (max && value > max[i])
+				return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+/* Strategy function to convert jiffies to seconds */ 
+int sysctl_jiffies(struct ctl_table *table, int __user *name, int nlen,
+		void __user *oldval, size_t __user *oldlenp,
+		void __user *newval, size_t newlen)
+{
+	if (oldval && oldlenp) {
+		size_t olen;
+
+		if (get_user(olen, oldlenp))
+			return -EFAULT;
+		if (olen) {
+			int val;
+
+			if (olen < sizeof(int))
+				return -EINVAL;
+
+			val = *(int *)(table->data) / HZ;
+			if (put_user(val, (int __user *)oldval))
+				return -EFAULT;
+			if (put_user(sizeof(int), oldlenp))
+				return -EFAULT;
+		}
+	}
+	if (newval && newlen) { 
+		int new;
+		if (newlen != sizeof(int))
+			return -EINVAL; 
+		if (get_user(new, (int __user *)newval))
+			return -EFAULT;
+		*(int *)(table->data) = new*HZ; 
+	}
+	return 1;
+}
+
+/* Strategy function to convert jiffies to seconds */ 
+int sysctl_ms_jiffies(struct ctl_table *table, int __user *name, int nlen,
+		void __user *oldval, size_t __user *oldlenp,
+		void __user *newval, size_t newlen)
+{
+	if (oldval && oldlenp) {
+		size_t olen;
+
+		if (get_user(olen, oldlenp))
+			return -EFAULT;
+		if (olen) {
+			int val;
+
+			if (olen < sizeof(int))
+				return -EINVAL;
+
+			val = jiffies_to_msecs(*(int *)(table->data));
+			if (put_user(val, (int __user *)oldval))
+				return -EFAULT;
+			if (put_user(sizeof(int), oldlenp))
+				return -EFAULT;
+		}
+	}
+	if (newval && newlen) { 
+		int new;
+		if (newlen != sizeof(int))
+			return -EINVAL; 
+		if (get_user(new, (int __user *)newval))
+			return -EFAULT;
+		*(int *)(table->data) = msecs_to_jiffies(new);
+	}
+	return 1;
+}
+
+
+
+#else /* CONFIG_SYSCTL_SYSCALL */
+
+
+asmlinkage long sys_sysctl(struct __sysctl_args __user *args)
+{
+	struct __sysctl_args tmp;
+	int error;
+
+	if (copy_from_user(&tmp, args, sizeof(tmp)))
+		return -EFAULT;
+
+	error = deprecated_sysctl_warning(&tmp);
+
+	/* If no error reading the parameters then just -ENOSYS ... */
+	if (!error)
+		error = -ENOSYS;
+
+	return error;
+}
+
+int sysctl_data(struct ctl_table *table, int __user *name, int nlen,
+		  void __user *oldval, size_t __user *oldlenp,
+		  void __user *newval, size_t newlen)
+{
+	return -ENOSYS;
+}
+
+int sysctl_string(struct ctl_table *table, int __user *name, int nlen,
+		  void __user *oldval, size_t __user *oldlenp,
+		  void __user *newval, size_t newlen)
+{
+	return -ENOSYS;
+}
+
+int sysctl_intvec(struct ctl_table *table, int __user *name, int nlen,
+		void __user *oldval, size_t __user *oldlenp,
+		void __user *newval, size_t newlen)
+{
+	return -ENOSYS;
+}
+
+int sysctl_jiffies(struct ctl_table *table, int __user *name, int nlen,
+		void __user *oldval, size_t __user *oldlenp,
+		void __user *newval, size_t newlen)
+{
+	return -ENOSYS;
+}
+
+int sysctl_ms_jiffies(struct ctl_table *table, int __user *name, int nlen,
+		void __user *oldval, size_t __user *oldlenp,
+		void __user *newval, size_t newlen)
+{
+	return -ENOSYS;
+}
+
+#endif /* CONFIG_SYSCTL_SYSCALL */
+
+static int deprecated_sysctl_warning(struct __sysctl_args *args)
+{
+	static int msg_count;
+	int name[CTL_MAXNAME];
+	int i;
+
+	/* Check args->nlen. */
+	if (args->nlen < 0 || args->nlen > CTL_MAXNAME)
+		return -ENOTDIR;
+
+	/* Read in the sysctl name for better debug message logging */
+	for (i = 0; i < args->nlen; i++)
+		if (get_user(name[i], args->name + i))
+			return -EFAULT;
+
+	/* Ignore accesses to kernel.version */
+	if ((args->nlen == 2) && (name[0] == CTL_KERN) && (name[1] == KERN_VERSION))
+		return 0;
+
+	if (msg_count < 5) {
+		msg_count++;
+		printk(KERN_INFO
+			"warning: process `%s' used the deprecated sysctl "
+			"system call with ", current->comm);
+		for (i = 0; i < args->nlen; i++)
+			printk("%d.", name[i]);
+		printk("\n");
+	}
+	return 0;
+}
+
+/*
+ * No sense putting this after each symbol definition, twice,
+ * exception granted :-)
+ */
+EXPORT_SYMBOL(proc_dointvec);
+EXPORT_SYMBOL(proc_dointvec_jiffies);
+EXPORT_SYMBOL(proc_dointvec_minmax);
+EXPORT_SYMBOL(proc_dointvec_userhz_jiffies);
+EXPORT_SYMBOL(proc_dointvec_ms_jiffies);
+EXPORT_SYMBOL(proc_dostring);
+EXPORT_SYMBOL(proc_doulongvec_minmax);
+EXPORT_SYMBOL(proc_doulongvec_ms_jiffies_minmax);
+EXPORT_SYMBOL(register_sysctl_table);
+EXPORT_SYMBOL(register_sysctl_paths);
+EXPORT_SYMBOL(sysctl_intvec);
+EXPORT_SYMBOL(sysctl_jiffies);
+EXPORT_SYMBOL(sysctl_ms_jiffies);
+EXPORT_SYMBOL(sysctl_string);
+EXPORT_SYMBOL(sysctl_data);
+EXPORT_SYMBOL(unregister_sysctl_table);
diff -urpNa linux-2.6.26-rc4-rcut1-stutter/lib/Kconfig.debug linux-2.6.26-rc4-rcut2-proc/lib/Kconfig.debug
--- linux-2.6.26-rc4-rcut1-stutter/lib/Kconfig.debug	2008-05-30 04:39:01.000000000 -0700
+++ linux-2.6.26-rc4-rcut2-proc/lib/Kconfig.debug	2008-06-18 06:32:48.000000000 -0700
@@ -531,16 +531,34 @@ config BOOT_PRINTK_DELAY
 config RCU_TORTURE_TEST
 	tristate "torture tests for RCU"
 	depends on DEBUG_KERNEL
-	depends on m
 	default n
 	help
 	  This option provides a kernel module that runs torture tests
 	  on the RCU infrastructure.  The kernel module may be built
 	  after the fact on the running kernel to be tested, if desired.
 
+	  Say Y here if you want RCU torture tests to be built into
+	  the kernel.
 	  Say M if you want the RCU torture tests to build as a module.
 	  Say N if you are unsure.
 
+config RCU_TORTURE_TEST_RUNNABLE
+	bool "torture tests for RCU runnable by default"
+	depends on RCU_TORTURE_TEST = y
+	default n
+	help
+	  This option provides a way to build the RCU torture tests
+	  directly into the kernel without them starting up at boot
+	  time.  You can use /proc/sys/kernel/rcutorture_runnable
+	  to manually override this setting.  This /proc file is
+	  available only when the RCU torture tests have been built
+	  into the kernel.
+
+	  Say Y here if you want the RCU torture tests to start during
+	  boot (you probably don't).
+	  Say N here if you want the RCU torture tests to start only
+	  after being manually enabled via /proc.
+
 config KPROBES_SANITY_TEST
 	bool "Kprobes sanity tests"
 	depends on DEBUG_KERNEL
diff -urpNa linux-2.6.26-rc4-rcut1-stutter/lib/Kconfig.debug.orig linux-2.6.26-rc4-rcut2-proc/lib/Kconfig.debug.orig
--- linux-2.6.26-rc4-rcut1-stutter/lib/Kconfig.debug.orig	1969-12-31 16:00:00.000000000 -0800
+++ linux-2.6.26-rc4-rcut2-proc/lib/Kconfig.debug.orig	2008-05-30 04:39:01.000000000 -0700
@@ -0,0 +1,679 @@
+
+config PRINTK_TIME
+	bool "Show timing information on printks"
+	depends on PRINTK
+	help
+	  Selecting this option causes timing information to be
+	  included in printk output.  This allows you to measure
+	  the interval between kernel operations, including bootup
+	  operations.  This is useful for identifying long delays
+	  in kernel startup.
+
+config ENABLE_WARN_DEPRECATED
+	bool "Enable __deprecated logic"
+	default y
+	help
+	  Enable the __deprecated logic in the kernel build.
+	  Disable this to suppress the "warning: 'foo' is deprecated
+	  (declared at kernel/power/somefile.c:1234)" messages.
+
+config ENABLE_MUST_CHECK
+	bool "Enable __must_check logic"
+	default y
+	help
+	  Enable the __must_check logic in the kernel build.  Disable this to
+	  suppress the "warning: ignoring return value of 'foo', declared with
+	  attribute warn_unused_result" messages.
+
+config FRAME_WARN
+	int "Warn for stack frames larger than (needs gcc 4.4)"
+	range 0 8192
+	default 1024 if !64BIT
+	default 2048 if 64BIT
+	help
+	  Tell gcc to warn at build time for stack frames larger than this.
+	  Setting this too low will cause a lot of warnings.
+	  Setting it to 0 disables the warning.
+	  Requires gcc 4.4
+
+config MAGIC_SYSRQ
+	bool "Magic SysRq key"
+	depends on !UML
+	help
+	  If you say Y here, you will have some control over the system even
+	  if the system crashes for example during kernel debugging (e.g., you
+	  will be able to flush the buffer cache to disk, reboot the system
+	  immediately or dump some status information). This is accomplished
+	  by pressing various keys while holding SysRq (Alt+PrintScreen). It
+	  also works on a serial console (on PC hardware at least), if you
+	  send a BREAK and then within 5 seconds a command keypress. The
+	  keys are documented in <file:Documentation/sysrq.txt>. Don't say Y
+	  unless you really know what this hack does.
+
+config UNUSED_SYMBOLS
+	bool "Enable unused/obsolete exported symbols"
+	default y if X86
+	help
+	  Unused but exported symbols make the kernel needlessly bigger.  For
+	  that reason most of these unused exports will soon be removed.  This
+	  option is provided temporarily to provide a transition period in case
+	  some external kernel module needs one of these symbols anyway. If you
+	  encounter such a case in your module, consider if you are actually
+	  using the right API.  (rationale: since nobody in the kernel is using
+	  this in a module, there is a pretty good chance it's actually the
+	  wrong interface to use).  If you really need the symbol, please send a
+	  mail to the linux kernel mailing list mentioning the symbol and why
+	  you really need it, and what the merge plan to the mainline kernel for
+	  your module is.
+
+config DEBUG_FS
+	bool "Debug Filesystem"
+	depends on SYSFS
+	help
+	  debugfs is a virtual file system that kernel developers use to put
+	  debugging files into.  Enable this option to be able to read and
+	  write to these files.
+
+	  If unsure, say N.
+
+config HEADERS_CHECK
+	bool "Run 'make headers_check' when building vmlinux"
+	depends on !UML
+	help
+	  This option will extract the user-visible kernel headers whenever
+	  building the kernel, and will run basic sanity checks on them to
+	  ensure that exported files do not attempt to include files which
+	  were not exported, etc.
+
+	  If you're making modifications to header files which are
+	  relevant for userspace, say 'Y', and check the headers
+	  exported to $(INSTALL_HDR_PATH) (usually 'usr/include' in
+	  your build tree), to make sure they're suitable.
+
+config DEBUG_SECTION_MISMATCH
+	bool "Enable full Section mismatch analysis"
+	depends on UNDEFINED
+	# This option is on purpose disabled for now.
+	# It will be enabled when we are down to a resonable number
+	# of section mismatch warnings (< 10 for an allyesconfig build)
+	help
+	  The section mismatch analysis checks if there are illegal
+	  references from one section to another section.
+	  Linux will during link or during runtime drop some sections
+	  and any use of code/data previously in these sections will
+	  most likely result in an oops.
+	  In the code functions and variables are annotated with
+	  __init, __devinit etc. (see full list in include/linux/init.h)
+	  which results in the code/data being placed in specific sections.
+	  The section mismatch analysis is always done after a full
+	  kernel build but enabling this option will in addition
+	  do the following:
+	  - Add the option -fno-inline-functions-called-once to gcc
+	    When inlining a function annotated __init in a non-init
+	    function we would lose the section information and thus
+	    the analysis would not catch the illegal reference.
+	    This option tells gcc to inline less but will also
+	    result in a larger kernel.
+	  - Run the section mismatch analysis for each module/built-in.o
+	    When we run the section mismatch analysis on vmlinux.o we
+	    lose valueble information about where the mismatch was
+	    introduced.
+	    Running the analysis for each module/built-in.o file
+	    will tell where the mismatch happens much closer to the
+	    source. The drawback is that we will report the same
+	    mismatch at least twice.
+	  - Enable verbose reporting from modpost to help solving
+	    the section mismatches reported.
+
+config DEBUG_KERNEL
+	bool "Kernel debugging"
+	help
+	  Say Y here if you are developing drivers or trying to debug and
+	  identify kernel problems.
+
+config DEBUG_SHIRQ
+	bool "Debug shared IRQ handlers"
+	depends on DEBUG_KERNEL && GENERIC_HARDIRQS
+	help
+	  Enable this to generate a spurious interrupt as soon as a shared
+	  interrupt handler is registered, and just before one is deregistered.
+	  Drivers ought to be able to handle interrupts coming in at those
+	  points; some don't and need to be caught.
+
+config DETECT_SOFTLOCKUP
+	bool "Detect Soft Lockups"
+	depends on DEBUG_KERNEL && !S390
+	default y
+	help
+	  Say Y here to enable the kernel to detect "soft lockups",
+	  which are bugs that cause the kernel to loop in kernel
+	  mode for more than 10 seconds, without giving other tasks a
+	  chance to run.
+
+	  When a soft-lockup is detected, the kernel will print the
+	  current stack trace (which you should report), but the
+	  system will stay locked up. This feature has negligible
+	  overhead.
+
+	  (Note that "hard lockups" are separate type of bugs that
+	   can be detected via the NMI-watchdog, on platforms that
+	   support it.)
+
+config SCHED_DEBUG
+	bool "Collect scheduler debugging info"
+	depends on DEBUG_KERNEL && PROC_FS
+	default y
+	help
+	  If you say Y here, the /proc/sched_debug file will be provided
+	  that can help debug the scheduler. The runtime overhead of this
+	  option is minimal.
+
+config SCHEDSTATS
+	bool "Collect scheduler statistics"
+	depends on DEBUG_KERNEL && PROC_FS
+	help
+	  If you say Y here, additional code will be inserted into the
+	  scheduler and related routines to collect statistics about
+	  scheduler behavior and provide them in /proc/schedstat.  These
+	  stats may be useful for both tuning and debugging the scheduler
+	  If you aren't debugging the scheduler or trying to tune a specific
+	  application, you can say N to avoid the very slight overhead
+	  this adds.
+
+config TIMER_STATS
+	bool "Collect kernel timers statistics"
+	depends on DEBUG_KERNEL && PROC_FS
+	help
+	  If you say Y here, additional code will be inserted into the
+	  timer routines to collect statistics about kernel timers being
+	  reprogrammed. The statistics can be read from /proc/timer_stats.
+	  The statistics collection is started by writing 1 to /proc/timer_stats,
+	  writing 0 stops it. This feature is useful to collect information
+	  about timer usage patterns in kernel and userspace. This feature
+	  is lightweight if enabled in the kernel config but not activated
+	  (it defaults to deactivated on bootup and will only be activated
+	  if some application like powertop activates it explicitly).
+
+config DEBUG_OBJECTS
+	bool "Debug object operations"
+	depends on DEBUG_KERNEL
+	help
+	  If you say Y here, additional code will be inserted into the
+	  kernel to track the life time of various objects and validate
+	  the operations on those objects.
+
+config DEBUG_OBJECTS_SELFTEST
+	bool "Debug objects selftest"
+	depends on DEBUG_OBJECTS
+	help
+	  This enables the selftest of the object debug code.
+
+config DEBUG_OBJECTS_FREE
+	bool "Debug objects in freed memory"
+	depends on DEBUG_OBJECTS
+	help
+	  This enables checks whether a k/v free operation frees an area
+	  which contains an object which has not been deactivated
+	  properly. This can make kmalloc/kfree-intensive workloads
+	  much slower.
+
+config DEBUG_OBJECTS_TIMERS
+	bool "Debug timer objects"
+	depends on DEBUG_OBJECTS
+	help
+	  If you say Y here, additional code will be inserted into the
+	  timer routines to track the life time of timer objects and
+	  validate the timer operations.
+
+config DEBUG_SLAB
+	bool "Debug slab memory allocations"
+	depends on DEBUG_KERNEL && SLAB
+	help
+	  Say Y here to have the kernel do limited verification on memory
+	  allocation as well as poisoning memory on free to catch use of freed
+	  memory. This can make kmalloc/kfree-intensive workloads much slower.
+
+config DEBUG_SLAB_LEAK
+	bool "Memory leak debugging"
+	depends on DEBUG_SLAB
+
+config SLUB_DEBUG_ON
+	bool "SLUB debugging on by default"
+	depends on SLUB && SLUB_DEBUG
+	default n
+	help
+	  Boot with debugging on by default. SLUB boots by default with
+	  the runtime debug capabilities switched off. Enabling this is
+	  equivalent to specifying the "slub_debug" parameter on boot.
+	  There is no support for more fine grained debug control like
+	  possible with slub_debug=xxx. SLUB debugging may be switched
+	  off in a kernel built with CONFIG_SLUB_DEBUG_ON by specifying
+	  "slub_debug=-".
+
+config SLUB_STATS
+	default n
+	bool "Enable SLUB performance statistics"
+	depends on SLUB && SLUB_DEBUG && SYSFS
+	help
+	  SLUB statistics are useful to debug SLUBs allocation behavior in
+	  order find ways to optimize the allocator. This should never be
+	  enabled for production use since keeping statistics slows down
+	  the allocator by a few percentage points. The slabinfo command
+	  supports the determination of the most active slabs to figure
+	  out which slabs are relevant to a particular load.
+	  Try running: slabinfo -DA
+
+config DEBUG_PREEMPT
+	bool "Debug preemptible kernel"
+	depends on DEBUG_KERNEL && PREEMPT && (TRACE_IRQFLAGS_SUPPORT || PPC64)
+	default y
+	help
+	  If you say Y here then the kernel will use a debug variant of the
+	  commonly used smp_processor_id() function and will print warnings
+	  if kernel code uses it in a preemption-unsafe way. Also, the kernel
+	  will detect preemption count underflows.
+
+config DEBUG_RT_MUTEXES
+	bool "RT Mutex debugging, deadlock detection"
+	depends on DEBUG_KERNEL && RT_MUTEXES
+	help
+	 This allows rt mutex semantics violations and rt mutex related
+	 deadlocks (lockups) to be detected and reported automatically.
+
+config DEBUG_PI_LIST
+	bool
+	default y
+	depends on DEBUG_RT_MUTEXES
+
+config RT_MUTEX_TESTER
+	bool "Built-in scriptable tester for rt-mutexes"
+	depends on DEBUG_KERNEL && RT_MUTEXES
+	help
+	  This option enables a rt-mutex tester.
+
+config DEBUG_SPINLOCK
+	bool "Spinlock and rw-lock debugging: basic checks"
+	depends on DEBUG_KERNEL
+	help
+	  Say Y here and build SMP to catch missing spinlock initialization
+	  and certain other kinds of spinlock errors commonly made.  This is
+	  best used in conjunction with the NMI watchdog so that spinlock
+	  deadlocks are also debuggable.
+
+config DEBUG_MUTEXES
+	bool "Mutex debugging: basic checks"
+	depends on DEBUG_KERNEL
+	help
+	 This feature allows mutex semantics violations to be detected and
+	 reported.
+
+config DEBUG_LOCK_ALLOC
+	bool "Lock debugging: detect incorrect freeing of live locks"
+	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
+	select DEBUG_SPINLOCK
+	select DEBUG_MUTEXES
+	select LOCKDEP
+	help
+	 This feature will check whether any held lock (spinlock, rwlock,
+	 mutex or rwsem) is incorrectly freed by the kernel, via any of the
+	 memory-freeing routines (kfree(), kmem_cache_free(), free_pages(),
+	 vfree(), etc.), whether a live lock is incorrectly reinitialized via
+	 spin_lock_init()/mutex_init()/etc., or whether there is any lock
+	 held during task exit.
+
+config PROVE_LOCKING
+	bool "Lock debugging: prove locking correctness"
+	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
+	select LOCKDEP
+	select DEBUG_SPINLOCK
+	select DEBUG_MUTEXES
+	select DEBUG_LOCK_ALLOC
+	default n
+	help
+	 This feature enables the kernel to prove that all locking
+	 that occurs in the kernel runtime is mathematically
+	 correct: that under no circumstance could an arbitrary (and
+	 not yet triggered) combination of observed locking
+	 sequences (on an arbitrary number of CPUs, running an
+	 arbitrary number of tasks and interrupt contexts) cause a
+	 deadlock.
+
+	 In short, this feature enables the kernel to report locking
+	 related deadlocks before they actually occur.
+
+	 The proof does not depend on how hard and complex a
+	 deadlock scenario would be to trigger: how many
+	 participant CPUs, tasks and irq-contexts would be needed
+	 for it to trigger. The proof also does not depend on
+	 timing: if a race and a resulting deadlock is possible
+	 theoretically (no matter how unlikely the race scenario
+	 is), it will be proven so and will immediately be
+	 reported by the kernel (once the event is observed that
+	 makes the deadlock theoretically possible).
+
+	 If a deadlock is impossible (i.e. the locking rules, as
+	 observed by the kernel, are mathematically correct), the
+	 kernel reports nothing.
+
+	 NOTE: this feature can also be enabled for rwlocks, mutexes
+	 and rwsems - in which case all dependencies between these
+	 different locking variants are observed and mapped too, and
+	 the proof of observed correctness is also maintained for an
+	 arbitrary combination of these separate locking variants.
+
+	 For more details, see Documentation/lockdep-design.txt.
+
+config LOCKDEP
+	bool
+	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
+	select STACKTRACE
+	select FRAME_POINTER if !X86 && !MIPS
+	select KALLSYMS
+	select KALLSYMS_ALL
+
+config LOCK_STAT
+	bool "Lock usage statistics"
+	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
+	select LOCKDEP
+	select DEBUG_SPINLOCK
+	select DEBUG_MUTEXES
+	select DEBUG_LOCK_ALLOC
+	default n
+	help
+	 This feature enables tracking lock contention points
+
+	 For more details, see Documentation/lockstat.txt
+
+config DEBUG_LOCKDEP
+	bool "Lock dependency engine debugging"
+	depends on DEBUG_KERNEL && LOCKDEP
+	help
+	  If you say Y here, the lock dependency engine will do
+	  additional runtime checks to debug itself, at the price
+	  of more runtime overhead.
+
+config TRACE_IRQFLAGS
+	depends on DEBUG_KERNEL
+	bool
+	default y
+	depends on TRACE_IRQFLAGS_SUPPORT
+	depends on PROVE_LOCKING
+
+config DEBUG_SPINLOCK_SLEEP
+	bool "Spinlock debugging: sleep-inside-spinlock checking"
+	depends on DEBUG_KERNEL
+	help
+	  If you say Y here, various routines which may sleep will become very
+	  noisy if they are called with a spinlock held.
+
+config DEBUG_LOCKING_API_SELFTESTS
+	bool "Locking API boot-time self-tests"
+	depends on DEBUG_KERNEL
+	help
+	  Say Y here if you want the kernel to run a short self-test during
+	  bootup. The self-test checks whether common types of locking bugs
+	  are detected by debugging mechanisms or not. (if you disable
+	  lock debugging then those bugs wont be detected of course.)
+	  The following locking APIs are covered: spinlocks, rwlocks,
+	  mutexes and rwsems.
+
+config STACKTRACE
+	bool
+	depends on DEBUG_KERNEL
+	depends on STACKTRACE_SUPPORT
+
+config DEBUG_KOBJECT
+	bool "kobject debugging"
+	depends on DEBUG_KERNEL
+	help
+	  If you say Y here, some extra kobject debugging messages will be sent
+	  to the syslog. 
+
+config DEBUG_HIGHMEM
+	bool "Highmem debugging"
+	depends on DEBUG_KERNEL && HIGHMEM
+	help
+	  This options enables addition error checking for high memory systems.
+	  Disable for production systems.
+
+config DEBUG_BUGVERBOSE
+	bool "Verbose BUG() reporting (adds 70K)" if DEBUG_KERNEL && EMBEDDED
+	depends on BUG
+	depends on ARM || AVR32 || M32R || M68K || SPARC32 || SPARC64 || \
+		   FRV || SUPERH || GENERIC_BUG || BLACKFIN || MN10300
+	default !EMBEDDED
+	help
+	  Say Y here to make BUG() panics output the file name and line number
+	  of the BUG call as well as the EIP and oops trace.  This aids
+	  debugging but costs about 70-100K of memory.
+
+config DEBUG_INFO
+	bool "Compile the kernel with debug info"
+	depends on DEBUG_KERNEL
+	help
+          If you say Y here the resulting kernel image will include
+	  debugging info resulting in a larger kernel image.
+	  This adds debug symbols to the kernel and modules (gcc -g), and
+	  is needed if you intend to use kernel crashdump or binary object
+	  tools like crash, kgdb, LKCD, gdb, etc on the kernel.
+	  Say Y here only if you plan to debug the kernel.
+
+	  If unsure, say N.
+
+config DEBUG_VM
+	bool "Debug VM"
+	depends on DEBUG_KERNEL
+	help
+	  Enable this to turn on extended checks in the virtual-memory system
+          that may impact performance.
+
+	  If unsure, say N.
+
+config DEBUG_WRITECOUNT
+	bool "Debug filesystem writers count"
+	depends on DEBUG_KERNEL
+	help
+	  Enable this to catch wrong use of the writers count in struct
+	  vfsmount.  This will increase the size of each file struct by
+	  32 bits.
+
+	  If unsure, say N.
+
+config DEBUG_LIST
+	bool "Debug linked list manipulation"
+	depends on DEBUG_KERNEL
+	help
+	  Enable this to turn on extended checks in the linked-list
+	  walking routines.
+
+	  If unsure, say N.
+
+config DEBUG_SG
+	bool "Debug SG table operations"
+	depends on DEBUG_KERNEL
+	help
+	  Enable this to turn on checks on scatter-gather tables. This can
+	  help find problems with drivers that do not properly initialize
+	  their sg tables.
+
+	  If unsure, say N.
+
+config FRAME_POINTER
+	bool "Compile the kernel with frame pointers"
+	depends on DEBUG_KERNEL && \
+		(X86 || CRIS || M68K || M68KNOMMU || FRV || UML || S390 || \
+		 AVR32 || SUPERH || BLACKFIN || MN10300)
+	default y if DEBUG_INFO && UML
+	help
+	  If you say Y here the resulting kernel image will be slightly larger
+	  and slower, but it might give very useful debugging information on
+	  some architectures or if you use external debuggers.
+	  If you don't debug the kernel, you can say N.
+
+config BOOT_PRINTK_DELAY
+	bool "Delay each boot printk message by N milliseconds"
+	depends on DEBUG_KERNEL && PRINTK && GENERIC_CALIBRATE_DELAY
+	help
+	  This build option allows you to read kernel boot messages
+	  by inserting a short delay after each one.  The delay is
+	  specified in milliseconds on the kernel command line,
+	  using "boot_delay=N".
+
+	  It is likely that you would also need to use "lpj=M" to preset
+	  the "loops per jiffie" value.
+	  See a previous boot log for the "lpj" value to use for your
+	  system, and then set "lpj=M" before setting "boot_delay=N".
+	  NOTE:  Using this option may adversely affect SMP systems.
+	  I.e., processors other than the first one may not boot up.
+	  BOOT_PRINTK_DELAY also may cause DETECT_SOFTLOCKUP to detect
+	  what it believes to be lockup conditions.
+
+config RCU_TORTURE_TEST
+	tristate "torture tests for RCU"
+	depends on DEBUG_KERNEL
+	depends on m
+	default n
+	help
+	  This option provides a kernel module that runs torture tests
+	  on the RCU infrastructure.  The kernel module may be built
+	  after the fact on the running kernel to be tested, if desired.
+
+	  Say M if you want the RCU torture tests to build as a module.
+	  Say N if you are unsure.
+
+config KPROBES_SANITY_TEST
+	bool "Kprobes sanity tests"
+	depends on DEBUG_KERNEL
+	depends on KPROBES
+	default n
+	help
+	  This option provides for testing basic kprobes functionality on
+	  boot. A sample kprobe, jprobe and kretprobe are inserted and
+	  verified for functionality.
+
+	  Say N if you are unsure.
+
+config BACKTRACE_SELF_TEST
+	tristate "Self test for the backtrace code"
+	depends on DEBUG_KERNEL
+	default n
+	help
+	  This option provides a kernel module that can be used to test
+	  the kernel stack backtrace code. This option is not useful
+	  for distributions or general kernels, but only for kernel
+	  developers working on architecture code.
+
+	  Say N if you are unsure.
+
+config LKDTM
+	tristate "Linux Kernel Dump Test Tool Module"
+	depends on DEBUG_KERNEL
+	depends on KPROBES
+	depends on BLOCK
+	default n
+	help
+	This module enables testing of the different dumping mechanisms by
+	inducing system failures at predefined crash points.
+	If you don't need it: say N
+	Choose M here to compile this code as a module. The module will be
+	called lkdtm.
+
+	Documentation on how to use the module can be found in
+	drivers/misc/lkdtm.c
+
+config FAULT_INJECTION
+	bool "Fault-injection framework"
+	depends on DEBUG_KERNEL
+	help
+	  Provide fault-injection framework.
+	  For more details, see Documentation/fault-injection/.
+
+config FAILSLAB
+	bool "Fault-injection capability for kmalloc"
+	depends on FAULT_INJECTION
+	help
+	  Provide fault-injection capability for kmalloc.
+
+config FAIL_PAGE_ALLOC
+	bool "Fault-injection capabilitiy for alloc_pages()"
+	depends on FAULT_INJECTION
+	help
+	  Provide fault-injection capability for alloc_pages().
+
+config FAIL_MAKE_REQUEST
+	bool "Fault-injection capability for disk IO"
+	depends on FAULT_INJECTION
+	help
+	  Provide fault-injection capability for disk IO.
+
+config FAULT_INJECTION_DEBUG_FS
+	bool "Debugfs entries for fault-injection capabilities"
+	depends on FAULT_INJECTION && SYSFS && DEBUG_FS
+	help
+	  Enable configuration of fault-injection capabilities via debugfs.
+
+config FAULT_INJECTION_STACKTRACE_FILTER
+	bool "stacktrace filter for fault-injection capabilities"
+	depends on FAULT_INJECTION_DEBUG_FS && STACKTRACE_SUPPORT
+	depends on !X86_64
+	select STACKTRACE
+	select FRAME_POINTER
+	help
+	  Provide stacktrace filter for fault-injection capabilities
+
+config LATENCYTOP
+	bool "Latency measuring infrastructure"
+	select FRAME_POINTER if !MIPS
+	select KALLSYMS
+	select KALLSYMS_ALL
+	select STACKTRACE
+	select SCHEDSTATS
+	select SCHED_DEBUG
+	depends on HAVE_LATENCYTOP_SUPPORT
+	help
+	  Enable this option if you want to use the LatencyTOP tool
+	  to find out which userspace is blocking on what kernel operations.
+
+config PROVIDE_OHCI1394_DMA_INIT
+	bool "Remote debugging over FireWire early on boot"
+	depends on PCI && X86
+	help
+	  If you want to debug problems which hang or crash the kernel early
+	  on boot and the crashing machine has a FireWire port, you can use
+	  this feature to remotely access the memory of the crashed machine
+	  over FireWire. This employs remote DMA as part of the OHCI1394
+	  specification which is now the standard for FireWire controllers.
+
+	  With remote DMA, you can monitor the printk buffer remotely using
+	  firescope and access all memory below 4GB using fireproxy from gdb.
+	  Even controlling a kernel debugger is possible using remote DMA.
+
+	  Usage:
+
+	  If ohci1394_dma=early is used as boot parameter, it will initialize
+	  all OHCI1394 controllers which are found in the PCI config space.
+
+	  As all changes to the FireWire bus such as enabling and disabling
+	  devices cause a bus reset and thereby disable remote DMA for all
+	  devices, be sure to have the cable plugged and FireWire enabled on
+	  the debugging host before booting the debug target for debugging.
+
+	  This code (~1k) is freed after boot. By then, the firewire stack
+	  in charge of the OHCI-1394 controllers should be used instead.
+
+	  See Documentation/debugging-via-ohci1394.txt for more information.
+
+config FIREWIRE_OHCI_REMOTE_DMA
+	bool "Remote debugging over FireWire with firewire-ohci"
+	depends on FIREWIRE_OHCI
+	help
+	  This option lets you use the FireWire bus for remote debugging
+	  with help of the firewire-ohci driver. It enables unfiltered
+	  remote DMA in firewire-ohci.
+	  See Documentation/debugging-via-ohci1394.txt for more information.
+
+	  If unsure, say N.
+
+source "samples/Kconfig"
+
+source "lib/Kconfig.kgdb"

^ permalink raw reply	[flat|nested] 24+ messages in thread

* Re: [PATCH] Make rcutorture more vicious: reinstate boot-time testing
  2008-06-19 15:58     ` Paul E. McKenney
@ 2008-06-19 21:17       ` Randy Dunlap
  2008-06-20  5:47         ` Paul E. McKenney
  0 siblings, 1 reply; 24+ messages in thread
From: Randy Dunlap @ 2008-06-19 21:17 UTC (permalink / raw)
  To: paulmck
  Cc: Ingo Molnar, linux-kernel, josh, dvhltc, niv, dino, akpm,
	torvalds, vegard.nossum, adobriyan, oleg, bunk, rjw

On Thu, 19 Jun 2008 08:58:54 -0700 Paul E. McKenney wrote:

> On Thu, Jun 19, 2008 at 11:29:14AM +0200, Ingo Molnar wrote:
> > 
> > * Paul E. McKenney <paulmck@linux.vnet.ibm.com> wrote:
> > 
> > > Hello again!
> > > 
> 
>  Documentation/RCU/torture.txt      |   21 
>  Documentation/RCU/torture.txt.orig |    8 
                                ~~~~~

>  kernel/rcutorture.c                |   14 
>  kernel/rcutorture.c.orig           |   59 
                       !!!!

>  kernel/sysctl.c                    |   13 
>  kernel/sysctl.c.orig               | 2851 +++++++++++++++++++++++++++++++++++++
                   ~~~~

>  lib/Kconfig.debug                  |   20 
>  lib/Kconfig.debug.orig             |  679 ++++++++
                     ~~~~

What's with all of these .orig files, eh??


>  8 files changed, 3651 insertions(+), 14 deletions(-)


---
~Randy
Linux Plumbers Conference, 17-19 September 2008, Portland, Oregon USA
http://linuxplumbersconf.org/

^ permalink raw reply	[flat|nested] 24+ messages in thread

* Re: [PATCH] Make rcutorture more vicious: reinstate boot-time testing
  2008-06-19 21:17       ` Randy Dunlap
@ 2008-06-20  5:47         ` Paul E. McKenney
  2008-06-21  1:39           ` Randy Dunlap
  0 siblings, 1 reply; 24+ messages in thread
From: Paul E. McKenney @ 2008-06-20  5:47 UTC (permalink / raw)
  To: Randy Dunlap
  Cc: Ingo Molnar, linux-kernel, josh, dvhltc, niv, dino, akpm,
	torvalds, vegard.nossum, adobriyan, oleg, bunk, rjw

On Thu, Jun 19, 2008 at 02:17:25PM -0700, Randy Dunlap wrote:
> On Thu, 19 Jun 2008 08:58:54 -0700 Paul E. McKenney wrote:
> 
> > On Thu, Jun 19, 2008 at 11:29:14AM +0200, Ingo Molnar wrote:
> > > 
> > > * Paul E. McKenney <paulmck@linux.vnet.ibm.com> wrote:
> > > 
> > > > Hello again!
> > > > 
> > 
> >  Documentation/RCU/torture.txt      |   21 
> >  Documentation/RCU/torture.txt.orig |    8 
>                                 ~~~~~
> 
> >  kernel/rcutorture.c                |   14 
> >  kernel/rcutorture.c.orig           |   59 
>                        !!!!
> 
> >  kernel/sysctl.c                    |   13 
> >  kernel/sysctl.c.orig               | 2851 +++++++++++++++++++++++++++++++++++++
>                    ~~~~
> 
> >  lib/Kconfig.debug                  |   20 
> >  lib/Kconfig.debug.orig             |  679 ++++++++
>                      ~~~~
> 
> What's with all of these .orig files, eh??

Gah, typos generating the diffs.  :-/

> >  8 files changed, 3651 insertions(+), 14 deletions(-)

How about the following instead?  (I expect to be following up with
a version that gets rid of the threads in response to writing a "0"
to /proc/sys/kernel/rcutorture_runnable later on.)

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

 Documentation/RCU/torture.txt |   21 ++++++++++++++-------
 kernel/rcutorture.c           |   14 ++++++++++++--
 kernel/sysctl.c               |   13 +++++++++++++
 lib/Kconfig.debug             |   20 +++++++++++++++++++-
 4 files changed, 58 insertions(+), 10 deletions(-)

diff -urpNa -X dontdiff linux-2.6.26-rc4-rcut1-stutter/Documentation/RCU/torture.txt linux-2.6.26-rc4-rcut2-proc/Documentation/RCU/torture.txt
--- linux-2.6.26-rc4-rcut1-stutter/Documentation/RCU/torture.txt	2008-06-18 05:15:43.000000000 -0700
+++ linux-2.6.26-rc4-rcut2-proc/Documentation/RCU/torture.txt	2008-06-18 08:11:19.000000000 -0700
@@ -10,13 +10,20 @@ status messages via printk(), which can 
 command (perhaps grepping for "torture").  The test is started
 when the module is loaded, and stops when the module is unloaded.
 
-However, actually setting this config option to "y" results in the system
-running the test immediately upon boot, and ending only when the system
-is taken down.  Normally, one will instead want to build the system
-with CONFIG_RCU_TORTURE_TEST=m and to use modprobe and rmmod to control
-the test, perhaps using a script similar to the one shown at the end of
-this document.  Note that you will need CONFIG_MODULE_UNLOAD in order
-to be able to end the test.
+CONFIG_RCU_TORTURE_TEST_RUNNABLE
+
+It is also possible to specify CONFIG_RCU_TORTURE_TEST=y, which will
+result in the tests being loaded into the base kernel.  In this case,
+the CONFIG_RCU_TORTURE_TEST_RUNNABLE config option is used to specify
+whether the RCU torture tests are to be started immediately during
+boot or whether the /proc/sys/kernel/rcutorture_runnable file is used
+to enable them.  This /proc file can be used to repeatedly pause and
+restart the tests, regardless of the initial state specified by the
+CONFIG_RCU_TORTURE_TEST_RUNNABLE config option.
+
+You will normally -not- want to start the RCU torture tests during boot
+(and thus the default is CONFIG_RCU_TORTURE_TEST_RUNNABLE=n), but doing
+this can sometimes be useful in finding boot-time bugs.
 
 
 MODULE PARAMETERS
diff -urpNa -X dontdiff linux-2.6.26-rc4-rcut1-stutter/kernel/rcutorture.c linux-2.6.26-rc4-rcut2-proc/kernel/rcutorture.c
--- linux-2.6.26-rc4-rcut1-stutter/kernel/rcutorture.c	2008-06-18 04:54:41.000000000 -0700
+++ linux-2.6.26-rc4-rcut2-proc/kernel/rcutorture.c	2008-06-19 04:48:56.000000000 -0700
@@ -125,6 +125,13 @@ static struct list_head rcu_torture_remo
 
 static int stutter_pause_test = 0;
 
+#if defined(MODULE) || defined(CONFIG_RCU_TORTURE_TEST_RUNNABLE)
+#define RCUTORTURE_RUNNABLE_INIT 1
+#else
+#define RCUTORTURE_RUNNABLE_INIT 0
+#endif
+int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT;
+
 /*
  * Allocate an element from the rcu_tortures pool.
  */
@@ -188,8 +195,11 @@ rcu_random(struct rcu_random_state *rrsp
 static void
 rcu_stutter_wait(void)
 {
-	while (stutter_pause_test)
-		schedule_timeout_interruptible(1);
+	while (stutter_pause_test || !rcutorture_runnable)
+		if (rcutorture_runnable)
+			schedule_timeout_interruptible(1);
+		else
+			schedule_timeout_interruptible(HZ);
 }
 
 /*
diff -urpNa -X dontdiff linux-2.6.26-rc4-rcut1-stutter/kernel/sysctl.c linux-2.6.26-rc4-rcut2-proc/kernel/sysctl.c
--- linux-2.6.26-rc4-rcut1-stutter/kernel/sysctl.c	2008-05-30 04:39:01.000000000 -0700
+++ linux-2.6.26-rc4-rcut2-proc/kernel/sysctl.c	2008-06-18 07:35:26.000000000 -0700
@@ -82,6 +82,9 @@ extern int maps_protect;
 extern int sysctl_stat_interval;
 extern int latencytop_enabled;
 extern int sysctl_nr_open_min, sysctl_nr_open_max;
+#ifdef CONFIG_RCU_TORTURE_TEST
+extern int rcutorture_runnable;
+#endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
 
 /* Constants used for minimum and  maximum */
 #if defined(CONFIG_DETECT_SOFTLOCKUP) || defined(CONFIG_HIGHMEM)
@@ -813,6 +816,16 @@ static struct ctl_table kern_table[] = {
 		.child		= key_sysctls,
 	},
 #endif
+#ifdef CONFIG_RCU_TORTURE_TEST
+	{
+		.ctl_name       = CTL_UNNUMBERED,
+		.procname       = "rcutorture_runnable",
+		.data           = &rcutorture_runnable,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = &proc_dointvec,
+	},
+#endif
 /*
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt
diff -urpNa -X dontdiff linux-2.6.26-rc4-rcut1-stutter/lib/Kconfig.debug linux-2.6.26-rc4-rcut2-proc/lib/Kconfig.debug
--- linux-2.6.26-rc4-rcut1-stutter/lib/Kconfig.debug	2008-05-30 04:39:01.000000000 -0700
+++ linux-2.6.26-rc4-rcut2-proc/lib/Kconfig.debug	2008-06-18 06:32:48.000000000 -0700
@@ -531,16 +531,34 @@ config BOOT_PRINTK_DELAY
 config RCU_TORTURE_TEST
 	tristate "torture tests for RCU"
 	depends on DEBUG_KERNEL
-	depends on m
 	default n
 	help
 	  This option provides a kernel module that runs torture tests
 	  on the RCU infrastructure.  The kernel module may be built
 	  after the fact on the running kernel to be tested, if desired.
 
+	  Say Y here if you want RCU torture tests to be built into
+	  the kernel.
 	  Say M if you want the RCU torture tests to build as a module.
 	  Say N if you are unsure.
 
+config RCU_TORTURE_TEST_RUNNABLE
+	bool "torture tests for RCU runnable by default"
+	depends on RCU_TORTURE_TEST = y
+	default n
+	help
+	  This option provides a way to build the RCU torture tests
+	  directly into the kernel without them starting up at boot
+	  time.  You can use /proc/sys/kernel/rcutorture_runnable
+	  to manually override this setting.  This /proc file is
+	  available only when the RCU torture tests have been built
+	  into the kernel.
+
+	  Say Y here if you want the RCU torture tests to start during
+	  boot (you probably don't).
+	  Say N here if you want the RCU torture tests to start only
+	  after being manually enabled via /proc.
+
 config KPROBES_SANITY_TEST
 	bool "Kprobes sanity tests"
 	depends on DEBUG_KERNEL

^ permalink raw reply	[flat|nested] 24+ messages in thread

* Re: [PATCH] Make rcutorture more vicious: reinstate boot-time testing
  2008-06-20  5:47         ` Paul E. McKenney
@ 2008-06-21  1:39           ` Randy Dunlap
  0 siblings, 0 replies; 24+ messages in thread
From: Randy Dunlap @ 2008-06-21  1:39 UTC (permalink / raw)
  To: paulmck
  Cc: Ingo Molnar, linux-kernel, josh, dvhltc, niv, dino, akpm,
	torvalds, vegard.nossum, adobriyan, oleg, bunk, rjw

On Thu, 19 Jun 2008 22:47:24 -0700 Paul E. McKenney wrote:

> On Thu, Jun 19, 2008 at 02:17:25PM -0700, Randy Dunlap wrote:
> > On Thu, 19 Jun 2008 08:58:54 -0700 Paul E. McKenney wrote:
> > 
> > > On Thu, Jun 19, 2008 at 11:29:14AM +0200, Ingo Molnar wrote:
> > > > 
> > > > * Paul E. McKenney <paulmck@linux.vnet.ibm.com> wrote:
> > > > 
> > > > > Hello again!
> > > > > 
> > > 
> > >  Documentation/RCU/torture.txt      |   21 
> > >  Documentation/RCU/torture.txt.orig |    8 
> >                                 ~~~~~
> > 
> > >  kernel/rcutorture.c                |   14 
> > >  kernel/rcutorture.c.orig           |   59 
> >                        !!!!
> > 
> > >  kernel/sysctl.c                    |   13 
> > >  kernel/sysctl.c.orig               | 2851 +++++++++++++++++++++++++++++++++++++
> >                    ~~~~
> > 
> > >  lib/Kconfig.debug                  |   20 
> > >  lib/Kconfig.debug.orig             |  679 ++++++++
> >                      ~~~~
> > 
> > What's with all of these .orig files, eh??
> 
> Gah, typos generating the diffs.  :-/
> 
> > >  8 files changed, 3651 insertions(+), 14 deletions(-)
> 
> How about the following instead?  (I expect to be following up with
> a version that gets rid of the threads in response to writing a "0"
> to /proc/sys/kernel/rcutorture_runnable later on.)

Yes, much better.  Thanks.

> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
> ---
> 
>  Documentation/RCU/torture.txt |   21 ++++++++++++++-------
>  kernel/rcutorture.c           |   14 ++++++++++++--
>  kernel/sysctl.c               |   13 +++++++++++++
>  lib/Kconfig.debug             |   20 +++++++++++++++++++-
>  4 files changed, 58 insertions(+), 10 deletions(-)
> 
> diff -urpNa -X dontdiff linux-2.6.26-rc4-rcut1-stutter/Documentation/RCU/torture.txt linux-2.6.26-rc4-rcut2-proc/Documentation/RCU/torture.txt
> --- linux-2.6.26-rc4-rcut1-stutter/Documentation/RCU/torture.txt	2008-06-18 05:15:43.000000000 -0700
> +++ linux-2.6.26-rc4-rcut2-proc/Documentation/RCU/torture.txt	2008-06-18 08:11:19.000000000 -0700
> @@ -10,13 +10,20 @@ status messages via printk(), which can 
>  command (perhaps grepping for "torture").  The test is started
>  when the module is loaded, and stops when the module is unloaded.
>  
> -However, actually setting this config option to "y" results in the system
> -running the test immediately upon boot, and ending only when the system
> -is taken down.  Normally, one will instead want to build the system
> -with CONFIG_RCU_TORTURE_TEST=m and to use modprobe and rmmod to control
> -the test, perhaps using a script similar to the one shown at the end of
> -this document.  Note that you will need CONFIG_MODULE_UNLOAD in order
> -to be able to end the test.
> +CONFIG_RCU_TORTURE_TEST_RUNNABLE
> +
> +It is also possible to specify CONFIG_RCU_TORTURE_TEST=y, which will
> +result in the tests being loaded into the base kernel.  In this case,
> +the CONFIG_RCU_TORTURE_TEST_RUNNABLE config option is used to specify
> +whether the RCU torture tests are to be started immediately during
> +boot or whether the /proc/sys/kernel/rcutorture_runnable file is used
> +to enable them.  This /proc file can be used to repeatedly pause and
> +restart the tests, regardless of the initial state specified by the
> +CONFIG_RCU_TORTURE_TEST_RUNNABLE config option.
> +
> +You will normally -not- want to start the RCU torture tests during boot
> +(and thus the default is CONFIG_RCU_TORTURE_TEST_RUNNABLE=n), but doing
> +this can sometimes be useful in finding boot-time bugs.
>  
>  
>  MODULE PARAMETERS
> diff -urpNa -X dontdiff linux-2.6.26-rc4-rcut1-stutter/kernel/rcutorture.c linux-2.6.26-rc4-rcut2-proc/kernel/rcutorture.c
> --- linux-2.6.26-rc4-rcut1-stutter/kernel/rcutorture.c	2008-06-18 04:54:41.000000000 -0700
> +++ linux-2.6.26-rc4-rcut2-proc/kernel/rcutorture.c	2008-06-19 04:48:56.000000000 -0700
> @@ -125,6 +125,13 @@ static struct list_head rcu_torture_remo
>  
>  static int stutter_pause_test = 0;
>  
> +#if defined(MODULE) || defined(CONFIG_RCU_TORTURE_TEST_RUNNABLE)
> +#define RCUTORTURE_RUNNABLE_INIT 1
> +#else
> +#define RCUTORTURE_RUNNABLE_INIT 0
> +#endif
> +int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT;
> +
>  /*
>   * Allocate an element from the rcu_tortures pool.
>   */
> @@ -188,8 +195,11 @@ rcu_random(struct rcu_random_state *rrsp
>  static void
>  rcu_stutter_wait(void)
>  {
> -	while (stutter_pause_test)
> -		schedule_timeout_interruptible(1);
> +	while (stutter_pause_test || !rcutorture_runnable)
> +		if (rcutorture_runnable)
> +			schedule_timeout_interruptible(1);
> +		else
> +			schedule_timeout_interruptible(HZ);
>  }
>  
>  /*
> diff -urpNa -X dontdiff linux-2.6.26-rc4-rcut1-stutter/kernel/sysctl.c linux-2.6.26-rc4-rcut2-proc/kernel/sysctl.c
> --- linux-2.6.26-rc4-rcut1-stutter/kernel/sysctl.c	2008-05-30 04:39:01.000000000 -0700
> +++ linux-2.6.26-rc4-rcut2-proc/kernel/sysctl.c	2008-06-18 07:35:26.000000000 -0700
> @@ -82,6 +82,9 @@ extern int maps_protect;
>  extern int sysctl_stat_interval;
>  extern int latencytop_enabled;
>  extern int sysctl_nr_open_min, sysctl_nr_open_max;
> +#ifdef CONFIG_RCU_TORTURE_TEST
> +extern int rcutorture_runnable;
> +#endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
>  
>  /* Constants used for minimum and  maximum */
>  #if defined(CONFIG_DETECT_SOFTLOCKUP) || defined(CONFIG_HIGHMEM)
> @@ -813,6 +816,16 @@ static struct ctl_table kern_table[] = {
>  		.child		= key_sysctls,
>  	},
>  #endif
> +#ifdef CONFIG_RCU_TORTURE_TEST
> +	{
> +		.ctl_name       = CTL_UNNUMBERED,
> +		.procname       = "rcutorture_runnable",
> +		.data           = &rcutorture_runnable,
> +		.maxlen         = sizeof(int),
> +		.mode           = 0644,
> +		.proc_handler   = &proc_dointvec,
> +	},
> +#endif
>  /*
>   * NOTE: do not add new entries to this table unless you have read
>   * Documentation/sysctl/ctl_unnumbered.txt
> diff -urpNa -X dontdiff linux-2.6.26-rc4-rcut1-stutter/lib/Kconfig.debug linux-2.6.26-rc4-rcut2-proc/lib/Kconfig.debug
> --- linux-2.6.26-rc4-rcut1-stutter/lib/Kconfig.debug	2008-05-30 04:39:01.000000000 -0700
> +++ linux-2.6.26-rc4-rcut2-proc/lib/Kconfig.debug	2008-06-18 06:32:48.000000000 -0700
> @@ -531,16 +531,34 @@ config BOOT_PRINTK_DELAY
>  config RCU_TORTURE_TEST
>  	tristate "torture tests for RCU"
>  	depends on DEBUG_KERNEL
> -	depends on m
>  	default n
>  	help
>  	  This option provides a kernel module that runs torture tests
>  	  on the RCU infrastructure.  The kernel module may be built
>  	  after the fact on the running kernel to be tested, if desired.
>  
> +	  Say Y here if you want RCU torture tests to be built into
> +	  the kernel.
>  	  Say M if you want the RCU torture tests to build as a module.
>  	  Say N if you are unsure.
>  
> +config RCU_TORTURE_TEST_RUNNABLE
> +	bool "torture tests for RCU runnable by default"
> +	depends on RCU_TORTURE_TEST = y
> +	default n
> +	help
> +	  This option provides a way to build the RCU torture tests
> +	  directly into the kernel without them starting up at boot
> +	  time.  You can use /proc/sys/kernel/rcutorture_runnable
> +	  to manually override this setting.  This /proc file is
> +	  available only when the RCU torture tests have been built
> +	  into the kernel.
> +
> +	  Say Y here if you want the RCU torture tests to start during
> +	  boot (you probably don't).
> +	  Say N here if you want the RCU torture tests to start only
> +	  after being manually enabled via /proc.
> +
>  config KPROBES_SANITY_TEST
>  	bool "Kprobes sanity tests"
>  	depends on DEBUG_KERNEL
> --

---
~Randy
Linux Plumbers Conference, 17-19 September 2008, Portland, Oregon USA
http://linuxplumbersconf.org/

^ permalink raw reply	[flat|nested] 24+ messages in thread

* [PATCH -tip-rcu] Make rcutorture more vicious: make quiescent rcutorture less power-hungry
  2008-06-18 16:26 ` [PATCH] Make rcutorture more vicious: reinstate boot-time testing Paul E. McKenney
  2008-06-19  0:42   ` Josh Triplett
  2008-06-19  9:29   ` Ingo Molnar
@ 2008-06-22 20:06   ` Paul E. McKenney
  2008-06-22 20:17     ` Arjan van de Ven
                       ` (2 more replies)
  2 siblings, 3 replies; 24+ messages in thread
From: Paul E. McKenney @ 2008-06-22 20:06 UTC (permalink / raw)
  To: linux-kernel
  Cc: mingo, josh, dvhltc, niv, dino, akpm, torvalds, vegard.nossum,
	adobriyan, oleg, bunk, rjw

This patch makes the non-module rcutorture a bit more friendly to
the power-conservation code.  This is a rather simple-minded approach.
More sophisticated approaches would get rid of the rcutorture tasks
while rcutorture execution was suppressed, but attempts thus far to
do this have not gone well -- calling rcu_torture_init() from a /proc
callout results in oopses.

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

 rcutorture.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff -urpNa -X dontdiff linux-2.6.26-rc4-rcut2-proc/kernel/rcutorture.c linux-2.6.26-rc4-rcut3-procq/kernel/rcutorture.c
--- linux-2.6.26-rc4-rcut2-proc/kernel/rcutorture.c	2008-06-22 10:29:04.000000000 -0700
+++ linux-2.6.26-rc4-rcut3-procq/kernel/rcutorture.c	2008-06-22 12:20:10.000000000 -0700
@@ -196,7 +196,10 @@ static void
 rcu_stutter_wait(void)
 {
 	while (stutter_pause_test || !rcutorture_runnable)
-		schedule_timeout_interruptible(1);
+		if (rcutorture_runnable)
+			schedule_timeout_interruptible(1);
+		else
+			schedule_timeout_interruptible(HZ);
 }
 
 /*

^ permalink raw reply	[flat|nested] 24+ messages in thread

* Re: [PATCH -tip-rcu] Make rcutorture more vicious: make quiescent rcutorture less power-hungry
  2008-06-22 20:06   ` [PATCH -tip-rcu] Make rcutorture more vicious: make quiescent rcutorture less power-hungry Paul E. McKenney
@ 2008-06-22 20:17     ` Arjan van de Ven
  2008-06-22 21:02       ` Paul E. McKenney
  2008-06-23 17:54       ` Darren Hart
  2008-06-22 20:58     ` Vegard Nossum
  2008-06-25 19:24     ` [PATCH -tip-rcu] Make rcutorture more vicious: invoke RCU readers from irq handlers (timers) Paul E. McKenney
  2 siblings, 2 replies; 24+ messages in thread
From: Arjan van de Ven @ 2008-06-22 20:17 UTC (permalink / raw)
  To: paulmck
  Cc: linux-kernel, mingo, josh, dvhltc, niv, dino, akpm, torvalds,
	vegard.nossum, adobriyan, oleg, bunk, rjw

On Sun, 22 Jun 2008 13:06:38 -0700
"Paul E. McKenney" <paulmck@linux.vnet.ibm.com> wrote:

> This patch makes the non-module rcutorture a bit more friendly to
> the power-conservation code.  This is a rather simple-minded approach.
> More sophisticated approaches would get rid of the rcutorture tasks
> while rcutorture execution was suppressed, but attempts thus far to
> do this have not gone well -- calling rcu_torture_init() from a /proc
> callout results in oopses.
> 
> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
> ---
> 
>  rcutorture.c |    5 ++++-
>  1 file changed, 4 insertions(+), 1 deletion(-)
> 
> diff -urpNa -X dontdiff
> linux-2.6.26-rc4-rcut2-proc/kernel/rcutorture.c
> linux-2.6.26-rc4-rcut3-procq/kernel/rcutorture.c ---
> linux-2.6.26-rc4-rcut2-proc/kernel/rcutorture.c	2008-06-22
> 10:29:04.000000000 -0700 +++
> linux-2.6.26-rc4-rcut3-procq/kernel/rcutorture.c	2008-06-22
> 12:20:10.000000000 -0700 @@ -196,7 +196,10 @@ static void
> rcu_stutter_wait(void) { while (stutter_pause_test
> || !rcutorture_runnable)
> -		schedule_timeout_interruptible(1);
> +		if (rcutorture_runnable)
> +			schedule_timeout_interruptible(1);
> +		else
> +			schedule_timeout_interruptible(HZ);
>  }

could you also make it use round_jiffies_relative() to make the power
impact even less.....
(by coalescing various "once a second" timers like this)



-- 
If you want to reach me at my work email, use arjan@linux.intel.com
For development, discussion and tips for power savings, 
visit http://www.lesswatts.org

^ permalink raw reply	[flat|nested] 24+ messages in thread

* Re: [PATCH -tip-rcu] Make rcutorture more vicious: make quiescent rcutorture less power-hungry
  2008-06-22 20:06   ` [PATCH -tip-rcu] Make rcutorture more vicious: make quiescent rcutorture less power-hungry Paul E. McKenney
  2008-06-22 20:17     ` Arjan van de Ven
@ 2008-06-22 20:58     ` Vegard Nossum
  2008-06-22 21:24       ` Vegard Nossum
  2008-06-25 19:24     ` [PATCH -tip-rcu] Make rcutorture more vicious: invoke RCU readers from irq handlers (timers) Paul E. McKenney
  2 siblings, 1 reply; 24+ messages in thread
From: Vegard Nossum @ 2008-06-22 20:58 UTC (permalink / raw)
  To: paulmck
  Cc: linux-kernel, mingo, josh, dvhltc, niv, dino, akpm, torvalds,
	adobriyan, oleg, bunk, rjw

On Sun, Jun 22, 2008 at 10:06 PM, Paul E. McKenney
<paulmck@linux.vnet.ibm.com> wrote:
> This patch makes the non-module rcutorture a bit more friendly to
> the power-conservation code.  This is a rather simple-minded approach.
> More sophisticated approaches would get rid of the rcutorture tasks
> while rcutorture execution was suppressed, but attempts thus far to
> do this have not gone well -- calling rcu_torture_init() from a /proc
> callout results in oopses.

Hi Paul,

I applied your three patches

[PATCH] Make rcutorture more vicious: add stutter feature
[PATCH] Make rcutorture more vicious: reinstate boot-time testing
[PATCH -tip-rcu] Make rcutorture more vicious: make quiescent
rcutorture less power-hungry

to v2.6.26-rc7 and gave it a quick testing in qemu. But it seems to
hang during gdb self-tests at boot:

rcu-torture:--- Start of test: nreaders=6 nfakewriters=4
stat_interval=0 verbose=0 test_no_idle_hz=0 shuffle_interval=3
stutter=5
Clocksource tsc unstable (delta = 617797275 ns)
Total HugeTLB memory allocated, 0
Installing knfsd (copyright (C) 1996 okir@monad.swb.de).
NTFS driver 2.1.29 [Flags: R/O].
msgmni has been set to 228
io scheduler noop registered
io scheduler anticipatory registered
io scheduler deadline registered
io scheduler cfq registered (default)
pci 0000:00:00.0: Limiting direct PCI/PCI transfers
pci 0000:00:01.0: PIIX3: Enabling Passive Release
pci 0000:00:01.0: Activating ISA DMA hang workarounds
pci 0000:00:02.0: Boot video device
Real Time Clock Driver v1.12ac
Linux agpgart interface v0.103
Serial: 8250/16550 driver $Revision: 1.90 $ 4 ports, IRQ sharing disabled
serial8250: ttyS0 at I/O 0x3f8 (irq = 4) is a 16450
FDC 0 is a S82078B
brd: module loaded
loop: module loaded
kgdb: Registered I/O driver kgdbts.
kgdbts:RUN plant and detach test

<--- full stop


gdb shows this:

kgdb_handle_exception (evector=0, signo=<value optimized out>,
    ecode=<value optimized out>, regs=0xc0769eec)
    at include/asm/processor.h:688
688             asm volatile("rep; nop" ::: "memory");
(gdb) bt
#0  kgdb_handle_exception (evector=0, signo=<value optimized out>,
    ecode=<value optimized out>, regs=0xc0769eec)
    at include/asm/processor.h:688
#1  0xc011ffa1 in kgdb_notify (self=<value optimized out>, cmd=9,
    ptr=0xc0769e30) at arch/x86/kernel/kgdb.c:478
#2  0xc014f527 in notifier_call_chain (nl=<value optimized out>, val=9,
    v=0xc0769e30, nr_to_call=-1, nr_calls=0x0) at kernel/notifier.c:85
#3  0xc014f925 in __atomic_notifier_call_chain (nh=<value optimized out>,
    val=9, v=0xc0769e30, nr_to_call=-1, nr_calls=0x0) at kernel/notifier.c:174
#4  0xc014f95a in atomic_notifier_call_chain (nh=0x2, val=0, v=0xffffffff)
    at kernel/notifier.c:183
#5  0xc014f98d in notify_die (val=0, str=<value optimized out>,
    regs=<value optimized out>, err=0, trap=0, sig=8) at kernel/notifier.c:564
#6  0xc010a8e8 in do_divide_error (regs=0xc0769eec, error_code=0)
    at arch/x86/kernel/traps_32.c:594
#7  0xc058cdba in page_fault ()
#8  0xc080f780 in per_cpu__init_tss ()
#9  0xc013c255 in do_softirq () at kernel/softirq.c:271
#10 0xc013c255 in do_softirq () at kernel/softirq.c:271
#11 0xc013c3f5 in irq_exit () at kernel/softirq.c:310
#12 0xc011db28 in smp_apic_timer_interrupt (regs=<value optimized out>)
    at arch/x86/kernel/apic_32.c:619
#13 0xc0108ed3 in apic_timer_interrupt () at include/asm/desc.h:309
#14 0xc0106ce0 in ?? () at arch/x86/kernel/process_32.c:466
#15 0xc0768000 in ?? ()
#16 0x00000000 in ?? ()

Without your patches, the kernel gets through here just fine.

These are my RCU-related options:

$ grep RCU .config
# CONFIG_CLASSIC_RCU is not set
CONFIG_PREEMPT_RCU=y
CONFIG_RCU_TRACE=y
CONFIG_RCU_TORTURE_TEST=y
CONFIG_RCU_TORTURE_TEST_RUNNABLE=y

As a convenience feature, it would be nice to have a boot option
controlling the run-at-boot as well, simply because it saves a
recompile for me :-) Actually, for some reason, the test still starts
at boot even when CONFIG_RCU_TORTURE_TEST_RUNNABLE=n. Is a hunk
missing from patch #2?


Vegard

-- 
"The animistic metaphor of the bug that maliciously sneaked in while
the programmer was not looking is intellectually dishonest as it
disguises that the error is the programmer's own creation."
	-- E. W. Dijkstra, EWD1036

^ permalink raw reply	[flat|nested] 24+ messages in thread

* Re: [PATCH -tip-rcu] Make rcutorture more vicious: make quiescent rcutorture less power-hungry
  2008-06-22 20:17     ` Arjan van de Ven
@ 2008-06-22 21:02       ` Paul E. McKenney
  2008-06-24 11:37         ` Ingo Molnar
  2008-06-23 17:54       ` Darren Hart
  1 sibling, 1 reply; 24+ messages in thread
From: Paul E. McKenney @ 2008-06-22 21:02 UTC (permalink / raw)
  To: Arjan van de Ven
  Cc: linux-kernel, mingo, josh, dvhltc, niv, dino, akpm, torvalds,
	vegard.nossum, adobriyan, oleg, bunk, rjw

On Sun, Jun 22, 2008 at 01:17:12PM -0700, Arjan van de Ven wrote:
> On Sun, 22 Jun 2008 13:06:38 -0700
> "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> wrote:
> 
> > This patch makes the non-module rcutorture a bit more friendly to
> > the power-conservation code.  This is a rather simple-minded approach.
> > More sophisticated approaches would get rid of the rcutorture tasks
> > while rcutorture execution was suppressed, but attempts thus far to
> > do this have not gone well -- calling rcu_torture_init() from a /proc
> > callout results in oopses.
> > 
> > Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
> > ---
> > 
> >  rcutorture.c |    5 ++++-
> >  1 file changed, 4 insertions(+), 1 deletion(-)
> > 
> > diff -urpNa -X dontdiff
> > linux-2.6.26-rc4-rcut2-proc/kernel/rcutorture.c
> > linux-2.6.26-rc4-rcut3-procq/kernel/rcutorture.c ---
> > linux-2.6.26-rc4-rcut2-proc/kernel/rcutorture.c	2008-06-22
> > 10:29:04.000000000 -0700 +++
> > linux-2.6.26-rc4-rcut3-procq/kernel/rcutorture.c	2008-06-22
> > 12:20:10.000000000 -0700 @@ -196,7 +196,10 @@ static void
> > rcu_stutter_wait(void) { while (stutter_pause_test
> > || !rcutorture_runnable)
> > -		schedule_timeout_interruptible(1);
> > +		if (rcutorture_runnable)
> > +			schedule_timeout_interruptible(1);
> > +		else
> > +			schedule_timeout_interruptible(HZ);
> >  }
> 
> could you also make it use round_jiffies_relative() to make the power
> impact even less.....
> (by coalescing various "once a second" timers like this)

Good point!!!  As follows, on top of the previous one.

This patch aligns the rcutorture wakeup times to align with all other
multiple-of-a-second wakeups to further decrease power consumption.

Suggested-by: Arjan van de Ven <arjan@infradead.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---

 rcutorture.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff -urpNa -X dontdiff linux-2.6.26-rc4-rcut3-procq/kernel/rcutorture.c linux-2.6.26-rc4-rcut4-procqp/kernel/rcutorture.c
--- linux-2.6.26-rc4-rcut3-procq/kernel/rcutorture.c	2008-06-22 12:20:10.000000000 -0700
+++ linux-2.6.26-rc4-rcut4-procqp/kernel/rcutorture.c	2008-06-22 13:53:22.000000000 -0700
@@ -1,3 +1,4 @@
+
 /*
  * Read-Copy Update module-based torture test facility
  *
@@ -199,7 +200,7 @@ rcu_stutter_wait(void)
 		if (rcutorture_runnable)
 			schedule_timeout_interruptible(1);
 		else
-			schedule_timeout_interruptible(HZ);
+			schedule_timeout_interruptible(round_jiffies_relative(HZ));
 }
 
 /*

^ permalink raw reply	[flat|nested] 24+ messages in thread

* Re: [PATCH -tip-rcu] Make rcutorture more vicious: make quiescent rcutorture less power-hungry
  2008-06-22 20:58     ` Vegard Nossum
@ 2008-06-22 21:24       ` Vegard Nossum
  0 siblings, 0 replies; 24+ messages in thread
From: Vegard Nossum @ 2008-06-22 21:24 UTC (permalink / raw)
  To: paulmck
  Cc: linux-kernel, mingo, josh, dvhltc, niv, dino, akpm, torvalds,
	adobriyan, oleg, bunk, rjw

On Sun, Jun 22, 2008 at 10:58 PM, Vegard Nossum <vegard.nossum@gmail.com> wrote:
> On Sun, Jun 22, 2008 at 10:06 PM, Paul E. McKenney
> <paulmck@linux.vnet.ibm.com> wrote:
>> This patch makes the non-module rcutorture a bit more friendly to
>> the power-conservation code.  This is a rather simple-minded approach.
>> More sophisticated approaches would get rid of the rcutorture tasks
>> while rcutorture execution was suppressed, but attempts thus far to
>> do this have not gone well -- calling rcu_torture_init() from a /proc
>> callout results in oopses.
>
> Hi Paul,
>
> I applied your three patches
>
> [PATCH] Make rcutorture more vicious: add stutter feature
> [PATCH] Make rcutorture more vicious: reinstate boot-time testing
> [PATCH -tip-rcu] Make rcutorture more vicious: make quiescent
> rcutorture less power-hungry
>
> to v2.6.26-rc7 and gave it a quick testing in qemu. But it seems to
> hang during gdb self-tests at boot:

Okay, you might disregard that. I'm typing on the very same kernel
running on a real machine now, so I assume that it's just qemu's
fault. (Actually, setting the number of cpus to 2 instead of 3 would
run the kgdb tests, but with a lot of warnings). But qemu is known to
have been buggy with these things before. (Sorry for the noise.)


Vegard

-- 
"The animistic metaphor of the bug that maliciously sneaked in while
the programmer was not looking is intellectually dishonest as it
disguises that the error is the programmer's own creation."
	-- E. W. Dijkstra, EWD1036

^ permalink raw reply	[flat|nested] 24+ messages in thread

* Re: [PATCH -tip-rcu] Make rcutorture more vicious: make quiescent rcutorture less power-hungry
  2008-06-22 20:17     ` Arjan van de Ven
  2008-06-22 21:02       ` Paul E. McKenney
@ 2008-06-23 17:54       ` Darren Hart
  2008-06-23 18:07         ` Arjan van de Ven
  1 sibling, 1 reply; 24+ messages in thread
From: Darren Hart @ 2008-06-23 17:54 UTC (permalink / raw)
  To: Arjan van de Ven
  Cc: paulmck, linux-kernel, mingo, josh, niv, dino, akpm, torvalds,
	vegard.nossum, adobriyan, oleg, bunk, rjw

On Sun, 2008-06-22 at 13:17 -0700, Arjan van de Ven wrote:
> On Sun, 22 Jun 2008 13:06:38 -0700
> "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> wrote:
> 
> > This patch makes the non-module rcutorture a bit more friendly to
> > the power-conservation code.  This is a rather simple-minded approach.
> > More sophisticated approaches would get rid of the rcutorture tasks
> > while rcutorture execution was suppressed, but attempts thus far to
> > do this have not gone well -- calling rcu_torture_init() from a /proc
> > callout results in oopses.
> > 
> > Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
> > ---
> > 
> >  rcutorture.c |    5 ++++-
> >  1 file changed, 4 insertions(+), 1 deletion(-)
> > 
> > diff -urpNa -X dontdiff
> > linux-2.6.26-rc4-rcut2-proc/kernel/rcutorture.c
> > linux-2.6.26-rc4-rcut3-procq/kernel/rcutorture.c ---
> > linux-2.6.26-rc4-rcut2-proc/kernel/rcutorture.c	2008-06-22
> > 10:29:04.000000000 -0700 +++
> > linux-2.6.26-rc4-rcut3-procq/kernel/rcutorture.c	2008-06-22
> > 12:20:10.000000000 -0700 @@ -196,7 +196,10 @@ static void
> > rcu_stutter_wait(void) { while (stutter_pause_test
> > || !rcutorture_runnable)
> > -		schedule_timeout_interruptible(1);
> > +		if (rcutorture_runnable)
> > +			schedule_timeout_interruptible(1);
> > +		else
> > +			schedule_timeout_interruptible(HZ);
> >  }
> 
> could you also make it use round_jiffies_relative() to make the power
> impact even less.....
> (by coalescing various "once a second" timers like this)

I'm a little concerned about how this will affect real-time performance,
as queueing up lots of timers all at once can lead to long running timer
expiration handlers.  If just a schedule_timeout, I suppose we are only
looking at a process wakeup, as opposed to a softirq context callback
function?

Thanks,

-- 
Darren Hart
Real-Time Linux Team Lead
IBM Linux Technology Center


^ permalink raw reply	[flat|nested] 24+ messages in thread

* Re: [PATCH -tip-rcu] Make rcutorture more vicious: make quiescent rcutorture less power-hungry
  2008-06-23 17:54       ` Darren Hart
@ 2008-06-23 18:07         ` Arjan van de Ven
  2008-06-23 20:02           ` Darren Hart
  0 siblings, 1 reply; 24+ messages in thread
From: Arjan van de Ven @ 2008-06-23 18:07 UTC (permalink / raw)
  To: Darren Hart
  Cc: paulmck, linux-kernel, mingo, josh, niv, dino, akpm, torvalds,
	vegard.nossum, adobriyan, oleg, bunk, rjw

On Mon, 23 Jun 2008 17:54:09 +0000
Darren Hart <dvhltc@us.ibm.com> wrote:

> I'm a little concerned about how this will affect real-time
> performance, as queueing up lots of timers all at once can lead to
> long running timer expiration handlers.  If just a schedule_timeout,
> I suppose we are only looking at a process wakeup, as opposed to a
> softirq context callback function?

in reality, the time it takes to deliver the interrupt (including
waking the CPU up etc), is likely to be an order or two of magnitude
higher than this kind of code loop.... 


-- 
If you want to reach me at my work email, use arjan@linux.intel.com
For development, discussion and tips for power savings, 
visit http://www.lesswatts.org

^ permalink raw reply	[flat|nested] 24+ messages in thread

* Re: [PATCH -tip-rcu] Make rcutorture more vicious: make quiescent rcutorture less power-hungry
  2008-06-23 18:07         ` Arjan van de Ven
@ 2008-06-23 20:02           ` Darren Hart
  2008-06-23 20:07             ` Arjan van de Ven
  2008-06-23 20:15             ` Paul E. McKenney
  0 siblings, 2 replies; 24+ messages in thread
From: Darren Hart @ 2008-06-23 20:02 UTC (permalink / raw)
  To: Arjan van de Ven
  Cc: paulmck, linux-kernel, mingo, josh, niv, dino, akpm, torvalds,
	vegard.nossum, adobriyan, oleg, bunk, rjw

On Mon, 2008-06-23 at 11:07 -0700, Arjan van de Ven wrote:
> On Mon, 23 Jun 2008 17:54:09 +0000
> Darren Hart <dvhltc@us.ibm.com> wrote:
> 
> > I'm a little concerned about how this will affect real-time
> > performance, as queueing up lots of timers all at once can lead to
> > long running timer expiration handlers.  If just a schedule_timeout,
> > I suppose we are only looking at a process wakeup, as opposed to a
> > softirq context callback function?
> 
> in reality, the time it takes to deliver the interrupt (including
> waking the CPU up etc), is likely to be an order or two of magnitude
> higher than this kind of code loop.... 

Sure, if we just look at one of them.  Any idea how many such items
we're looking at rounding up to fire at the same time?  Is it dozens,
hundreds, thousands?

Thanks,

-- 
Darren Hart
Real-Time Linux Team Lead
IBM Linux Technology Center


^ permalink raw reply	[flat|nested] 24+ messages in thread

* Re: [PATCH -tip-rcu] Make rcutorture more vicious: make quiescent rcutorture less power-hungry
  2008-06-23 20:02           ` Darren Hart
@ 2008-06-23 20:07             ` Arjan van de Ven
  2008-06-23 20:15             ` Paul E. McKenney
  1 sibling, 0 replies; 24+ messages in thread
From: Arjan van de Ven @ 2008-06-23 20:07 UTC (permalink / raw)
  To: Darren Hart
  Cc: paulmck, linux-kernel, mingo, josh, niv, dino, akpm, torvalds,
	vegard.nossum, adobriyan, oleg, bunk, rjw

On Mon, 23 Jun 2008 20:02:54 +0000
Darren Hart <dvhltc@us.ibm.com> wrote:

> On Mon, 2008-06-23 at 11:07 -0700, Arjan van de Ven wrote:
> > On Mon, 23 Jun 2008 17:54:09 +0000
> > Darren Hart <dvhltc@us.ibm.com> wrote:
> > 
> > > I'm a little concerned about how this will affect real-time
> > > performance, as queueing up lots of timers all at once can lead to
> > > long running timer expiration handlers.  If just a
> > > schedule_timeout, I suppose we are only looking at a process
> > > wakeup, as opposed to a softirq context callback function?
> > 
> > in reality, the time it takes to deliver the interrupt (including
> > waking the CPU up etc), is likely to be an order or two of magnitude
> > higher than this kind of code loop.... 
> 
> Sure, if we just look at one of them.  Any idea how many such items
> we're looking at rounding up to fire at the same time?  Is it dozens,
> hundreds, thousands?
> 

so far, in practice, it's still single-digit amounts.

There's not that many timers that run normally. 
(based on powertop data from many systems)

-- 
If you want to reach me at my work email, use arjan@linux.intel.com
For development, discussion and tips for power savings, 
visit http://www.lesswatts.org

^ permalink raw reply	[flat|nested] 24+ messages in thread

* Re: [PATCH -tip-rcu] Make rcutorture more vicious: make quiescent rcutorture less power-hungry
  2008-06-23 20:02           ` Darren Hart
  2008-06-23 20:07             ` Arjan van de Ven
@ 2008-06-23 20:15             ` Paul E. McKenney
  2008-06-23 21:28               ` Darren Hart
  1 sibling, 1 reply; 24+ messages in thread
From: Paul E. McKenney @ 2008-06-23 20:15 UTC (permalink / raw)
  To: Darren Hart
  Cc: Arjan van de Ven, linux-kernel, mingo, josh, niv, dino, akpm,
	torvalds, vegard.nossum, adobriyan, oleg, bunk, rjw

On Mon, Jun 23, 2008 at 08:02:54PM +0000, Darren Hart wrote:
> On Mon, 2008-06-23 at 11:07 -0700, Arjan van de Ven wrote:
> > On Mon, 23 Jun 2008 17:54:09 +0000
> > Darren Hart <dvhltc@us.ibm.com> wrote:
> > 
> > > I'm a little concerned about how this will affect real-time
> > > performance, as queueing up lots of timers all at once can lead to
> > > long running timer expiration handlers.  If just a schedule_timeout,
> > > I suppose we are only looking at a process wakeup, as opposed to a
> > > softirq context callback function?
> > 
> > in reality, the time it takes to deliver the interrupt (including
> > waking the CPU up etc), is likely to be an order or two of magnitude
> > higher than this kind of code loop.... 
> 
> Sure, if we just look at one of them.  Any idea how many such items
> we're looking at rounding up to fire at the same time?  Is it dozens,
> hundreds, thousands?

Hello, Darren,

Wouldn't these timers be running at low priority, so that high-priority
realtime tasks would preempt them?

							Thanx, Paul

^ permalink raw reply	[flat|nested] 24+ messages in thread

* Re: [PATCH -tip-rcu] Make rcutorture more vicious: make quiescent rcutorture less power-hungry
  2008-06-23 20:15             ` Paul E. McKenney
@ 2008-06-23 21:28               ` Darren Hart
  0 siblings, 0 replies; 24+ messages in thread
From: Darren Hart @ 2008-06-23 21:28 UTC (permalink / raw)
  To: paulmck
  Cc: Arjan van de Ven, linux-kernel, mingo, josh, niv, dino, akpm,
	torvalds, vegard.nossum, adobriyan, oleg, bunk, rjw

On Mon, 2008-06-23 at 13:15 -0700, Paul E. McKenney wrote:
> On Mon, Jun 23, 2008 at 08:02:54PM +0000, Darren Hart wrote:
> > On Mon, 2008-06-23 at 11:07 -0700, Arjan van de Ven wrote:
> > > On Mon, 23 Jun 2008 17:54:09 +0000
> > > Darren Hart <dvhltc@us.ibm.com> wrote:
> > > 
> > > > I'm a little concerned about how this will affect real-time
> > > > performance, as queueing up lots of timers all at once can lead to
> > > > long running timer expiration handlers.  If just a schedule_timeout,
> > > > I suppose we are only looking at a process wakeup, as opposed to a
> > > > softirq context callback function?
> > > 
> > > in reality, the time it takes to deliver the interrupt (including
> > > waking the CPU up etc), is likely to be an order or two of magnitude
> > > higher than this kind of code loop.... 
> > 
> > Sure, if we just look at one of them.  Any idea how many such items
> > we're looking at rounding up to fire at the same time?  Is it dozens,
> > hundreds, thousands?
> 
> Hello, Darren,
> 
> Wouldn't these timers be running at low priority, so that high-priority
> realtime tasks would preempt them?

The timers run from softirq context will run at the priority of the
softirq, so it is configurable, and only tasks equal to or lower in
priority to that should see direct effects.

> 
> 							Thanx, Paul
-- 
Darren Hart
Real-Time Linux Team Lead
IBM Linux Technology Center


^ permalink raw reply	[flat|nested] 24+ messages in thread

* Re: [PATCH -tip-rcu] Make rcutorture more vicious: make quiescent rcutorture less power-hungry
  2008-06-22 21:02       ` Paul E. McKenney
@ 2008-06-24 11:37         ` Ingo Molnar
  0 siblings, 0 replies; 24+ messages in thread
From: Ingo Molnar @ 2008-06-24 11:37 UTC (permalink / raw)
  To: Paul E. McKenney
  Cc: Arjan van de Ven, linux-kernel, josh, dvhltc, niv, dino, akpm,
	torvalds, vegard.nossum, adobriyan, oleg, bunk, rjw


* Paul E. McKenney <paulmck@linux.vnet.ibm.com> wrote:

> > could you also make it use round_jiffies_relative() to make the 
> > power impact even less..... (by coalescing various "once a second" 
> > timers like this)
> 
> Good point!!!  As follows, on top of the previous one.
> 
> This patch aligns the rcutorture wakeup times to align with all other 
> multiple-of-a-second wakeups to further decrease power consumption.
> 
> Suggested-by: Arjan van de Ven <arjan@infradead.org>
> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

applied to tip/core/rcu - thanks Paul.

	Ingo

^ permalink raw reply	[flat|nested] 24+ messages in thread

* [PATCH -tip-rcu] Make rcutorture more vicious: invoke RCU readers from irq handlers (timers)
  2008-06-22 20:06   ` [PATCH -tip-rcu] Make rcutorture more vicious: make quiescent rcutorture less power-hungry Paul E. McKenney
  2008-06-22 20:17     ` Arjan van de Ven
  2008-06-22 20:58     ` Vegard Nossum
@ 2008-06-25 19:24     ` Paul E. McKenney
  2008-06-26  7:22       ` Ingo Molnar
  2 siblings, 1 reply; 24+ messages in thread
From: Paul E. McKenney @ 2008-06-25 19:24 UTC (permalink / raw)
  To: linux-kernel
  Cc: mingo, josh, dvhltc, niv, dino, akpm, torvalds, vegard.nossum,
	adobriyan, oleg, bunk, rjw

This patch allows torturing RCU from irq handlers (timers, in this case).
A new module parameter irqreader enables such additional torturing,
and is enabled by default.  Variants of RCU that do not tolerate readers
being called from irq handlers (e.g., SRCU) ignore irqreader.

(No failures observed, but only short tests thus far.  And no failures
observed thus far from about 10 hours of running stock rcutorture in
parallel with 170 kernel builds on a two-CPU machine.)

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

 Documentation/RCU/torture.txt |   23 +++++++------
 kernel/rcutorture.c           |   74 +++++++++++++++++++++++++++++++++++++++---
 2 files changed, 84 insertions(+), 13 deletions(-)

diff -urpNa -X dontdiff linux-2.6.26-rc4-rcut4-procqp/Documentation/RCU/torture.txt linux-2.6.26-rc4-rcut5-timer/Documentation/RCU/torture.txt
--- linux-2.6.26-rc4-rcut4-procqp/Documentation/RCU/torture.txt	2008-06-22 10:29:04.000000000 -0700
+++ linux-2.6.26-rc4-rcut5-timer/Documentation/RCU/torture.txt	2008-06-25 11:44:51.000000000 -0700
@@ -30,10 +30,10 @@ MODULE PARAMETERS
 
 This module has the following parameters:
 
-nreaders	This is the number of RCU reading threads supported.
-		The default is twice the number of CPUs.  Why twice?
-		To properly exercise RCU implementations with preemptible
-		read-side critical sections.
+irqreaders	Says to invoke RCU readers from irq level.  This is currently
+		done via timers.  Defaults to "1" for variants of RCU that
+		permit this.  (Or, more accurately, variants of RCU that do
+		-not- permit this know to ignore this variable.)
 
 nfakewriters	This is the number of RCU fake writer threads to run.  Fake
 		writer threads repeatedly use the synchronous "wait for
@@ -44,6 +44,16 @@ nfakewriters	This is the number of RCU f
 		to trigger special cases caused by multiple writers, such as
 		the synchronize_srcu() early return optimization.
 
+nreaders	This is the number of RCU reading threads supported.
+		The default is twice the number of CPUs.  Why twice?
+		To properly exercise RCU implementations with preemptible
+		read-side critical sections.
+
+shuffle_interval
+		The number of seconds to keep the test threads affinitied
+		to a particular subset of the CPUs, defaults to 3 seconds.
+		Used in conjunction with test_no_idle_hz.
+
 stat_interval	The number of seconds between output of torture
 		statistics (via printk()).  Regardless of the interval,
 		statistics are printed when the module is unloaded.
@@ -51,11 +61,6 @@ stat_interval	The number of seconds betw
 		be printed -only- when the module is unloaded, and this
 		is the default.
 
-shuffle_interval
-		The number of seconds to keep the test threads affinitied
-		to a particular subset of the CPUs, defaults to 3 seconds.
-		Used in conjunction with test_no_idle_hz.
-
 stutter		The length of time to run the test before pausing for this
 		same period of time.  Defaults to "stutter=5", so as
 		to run and pause for (roughly) five-second intervals.
diff -urpNa -X dontdiff linux-2.6.26-rc4-rcut4-procqp/kernel/rcutorture.c linux-2.6.26-rc4-rcut5-timer/kernel/rcutorture.c
--- linux-2.6.26-rc4-rcut4-procqp/kernel/rcutorture.c	2008-06-25 11:39:58.000000000 -0700
+++ linux-2.6.26-rc4-rcut5-timer/kernel/rcutorture.c	2008-06-25 11:47:14.000000000 -0700
@@ -59,6 +59,7 @@ static int verbose;		/* Print more debug
 static int test_no_idle_hz;	/* Test RCU's support for tickless idle CPUs. */
 static int shuffle_interval = 3; /* Interval between shuffles (in sec)*/
 static int stutter = 5;		/* Start/stop testing interval (in sec) */
+static int irqreader = 1;	/* RCU readers from irq (timers). */
 static char *torture_type = "rcu"; /* What RCU implementation to torture. */
 
 module_param(nreaders, int, 0444);
@@ -75,6 +76,8 @@ module_param(shuffle_interval, int, 0444
 MODULE_PARM_DESC(shuffle_interval, "Number of seconds between shuffles");
 module_param(stutter, int, 0444);
 MODULE_PARM_DESC(stutter, "Number of seconds to run/halt test");
+module_param(irqreader, int, 0444);
+MODULE_PARM_DESC(irqreader, "Allow RCU readers from irq handlers");
 module_param(torture_type, charp, 0444);
 MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, srcu)");
 
@@ -121,6 +124,7 @@ static atomic_t n_rcu_torture_alloc_fail
 static atomic_t n_rcu_torture_free;
 static atomic_t n_rcu_torture_mberror;
 static atomic_t n_rcu_torture_error;
+static long n_rcu_torture_timers = 0;
 static struct list_head rcu_torture_removed;
 
 static int stutter_pause_test = 0;
@@ -216,6 +220,7 @@ struct rcu_torture_ops {
 	void (*deferredfree)(struct rcu_torture *p);
 	void (*sync)(void);
 	int (*stats)(char *page);
+	int irqcapable;
 	char *name;
 };
 static struct rcu_torture_ops *cur_ops = NULL;
@@ -289,6 +294,7 @@ static struct rcu_torture_ops rcu_ops = 
 	.deferredfree = rcu_torture_deferred_free,
 	.sync = synchronize_rcu,
 	.stats = NULL,
+	.irqcapable = 1,
 	.name = "rcu"
 };
 
@@ -328,6 +334,7 @@ static struct rcu_torture_ops rcu_sync_o
 	.deferredfree = rcu_sync_torture_deferred_free,
 	.sync = synchronize_rcu,
 	.stats = NULL,
+	.irqcapable = 1,
 	.name = "rcu_sync"
 };
 
@@ -388,6 +395,7 @@ static struct rcu_torture_ops rcu_bh_ops
 	.deferredfree = rcu_bh_torture_deferred_free,
 	.sync = rcu_bh_torture_synchronize,
 	.stats = NULL,
+	.irqcapable = 1,
 	.name = "rcu_bh"
 };
 
@@ -401,6 +409,7 @@ static struct rcu_torture_ops rcu_bh_syn
 	.deferredfree = rcu_sync_torture_deferred_free,
 	.sync = rcu_bh_torture_synchronize,
 	.stats = NULL,
+	.irqcapable = 1,
 	.name = "rcu_bh_sync"
 };
 
@@ -520,6 +529,7 @@ static struct rcu_torture_ops sched_ops 
 	.deferredfree = rcu_sync_torture_deferred_free,
 	.sync = sched_torture_synchronize,
 	.stats = NULL,
+	.irqcapable = 1,
 	.name = "sched"
 };
 
@@ -594,6 +604,52 @@ rcu_torture_fakewriter(void *arg)
 }
 
 /*
+ * RCU torture reader from timer handler.  Dereferences rcu_torture_current,
+ * incrementing the corresponding element of the pipeline array.  The
+ * counter in the element should never be greater than 1, otherwise, the
+ * RCU implementation is broken.
+ */
+static void rcu_torture_timer(unsigned long unused)
+{
+	int idx;
+	int completed;
+	static DEFINE_RCU_RANDOM(rand);
+	static DEFINE_SPINLOCK(rand_lock);
+	struct rcu_torture *p;
+	int pipe_count;
+
+	idx = cur_ops->readlock();
+	completed = cur_ops->completed();
+	p = rcu_dereference(rcu_torture_current);
+	if (p == NULL) {
+		/* Leave because rcu_torture_writer is not yet underway */
+		cur_ops->readunlock(idx);
+		return;
+	}
+	if (p->rtort_mbtest == 0)
+		atomic_inc(&n_rcu_torture_mberror);
+	spin_lock(&rand_lock);
+	cur_ops->readdelay(&rand);
+	n_rcu_torture_timers++;
+	spin_unlock(&rand_lock);
+	preempt_disable();
+	pipe_count = p->rtort_pipe_count;
+	if (pipe_count > RCU_TORTURE_PIPE_LEN) {
+		/* Should not happen, but... */
+		pipe_count = RCU_TORTURE_PIPE_LEN;
+	}
+	++__get_cpu_var(rcu_torture_count)[pipe_count];
+	completed = cur_ops->completed() - completed;
+	if (completed > RCU_TORTURE_PIPE_LEN) {
+		/* Should not happen, but... */
+		completed = RCU_TORTURE_PIPE_LEN;
+	}
+	++__get_cpu_var(rcu_torture_batch)[completed];
+	preempt_enable();
+	cur_ops->readunlock(idx);
+}
+
+/*
  * RCU torture reader kthread.  Repeatedly dereferences rcu_torture_current,
  * incrementing the corresponding element of the pipeline array.  The
  * counter in the element should never be greater than 1, otherwise, the
@@ -607,11 +663,18 @@ rcu_torture_reader(void *arg)
 	DEFINE_RCU_RANDOM(rand);
 	struct rcu_torture *p;
 	int pipe_count;
+	struct timer_list t;
 
 	VERBOSE_PRINTK_STRING("rcu_torture_reader task started");
 	set_user_nice(current, 19);
+	if (irqreader && cur_ops->irqcapable)
+		setup_timer_on_stack(&t, rcu_torture_timer, 0);
 
 	do {
+		if (irqreader && cur_ops->irqcapable) {
+			if (!timer_pending(&t))
+				mod_timer(&t, 1);
+		}
 		idx = cur_ops->readlock();
 		completed = cur_ops->completed();
 		p = rcu_dereference(rcu_torture_current);
@@ -643,6 +706,8 @@ rcu_torture_reader(void *arg)
 		rcu_stutter_wait();
 	} while (!kthread_should_stop() && !fullstop);
 	VERBOSE_PRINTK_STRING("rcu_torture_reader task stopping");
+	if (irqreader && cur_ops->irqcapable)
+		del_timer_sync(&t);
 	while (!kthread_should_stop())
 		schedule_timeout_uninterruptible(1);
 	return 0;
@@ -673,14 +738,15 @@ rcu_torture_printk(char *page)
 	cnt += sprintf(&page[cnt], "%s%s ", torture_type, TORTURE_FLAG);
 	cnt += sprintf(&page[cnt],
 		       "rtc: %p ver: %ld tfle: %d rta: %d rtaf: %d rtf: %d "
-		       "rtmbe: %d",
+		       "rtmbe: %d nt: %ld",
 		       rcu_torture_current,
 		       rcu_torture_current_version,
 		       list_empty(&rcu_torture_freelist),
 		       atomic_read(&n_rcu_torture_alloc),
 		       atomic_read(&n_rcu_torture_alloc_fail),
 		       atomic_read(&n_rcu_torture_free),
-		       atomic_read(&n_rcu_torture_mberror));
+		       atomic_read(&n_rcu_torture_mberror),
+		       n_rcu_torture_timers);
 	if (atomic_read(&n_rcu_torture_mberror) != 0)
 		cnt += sprintf(&page[cnt], " !!!");
 	cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
@@ -835,10 +901,10 @@ rcu_torture_print_module_parms(char *tag
 	printk(KERN_ALERT "%s" TORTURE_FLAG
 		"--- %s: nreaders=%d nfakewriters=%d "
 		"stat_interval=%d verbose=%d test_no_idle_hz=%d "
-		"shuffle_interval=%d stutter=%d\n",
+		"shuffle_interval=%d stutter=%d irqreader=%d\n",
 		torture_type, tag, nrealreaders, nfakewriters,
 		stat_interval, verbose, test_no_idle_hz, shuffle_interval,
-		stutter);
+		stutter, irqreader);
 }
 
 static void

^ permalink raw reply	[flat|nested] 24+ messages in thread

* Re: [PATCH -tip-rcu] Make rcutorture more vicious: invoke RCU readers from irq handlers (timers)
  2008-06-25 19:24     ` [PATCH -tip-rcu] Make rcutorture more vicious: invoke RCU readers from irq handlers (timers) Paul E. McKenney
@ 2008-06-26  7:22       ` Ingo Molnar
  2008-06-26 15:48         ` Paul E. McKenney
  0 siblings, 1 reply; 24+ messages in thread
From: Ingo Molnar @ 2008-06-26  7:22 UTC (permalink / raw)
  To: Paul E. McKenney
  Cc: linux-kernel, josh, dvhltc, niv, dino, akpm, torvalds,
	vegard.nossum, adobriyan, oleg, bunk, rjw


* Paul E. McKenney <paulmck@linux.vnet.ibm.com> wrote:

> This patch allows torturing RCU from irq handlers (timers, in this 
> case). A new module parameter irqreader enables such additional 
> torturing, and is enabled by default.  Variants of RCU that do not 
> tolerate readers being called from irq handlers (e.g., SRCU) ignore 
> irqreader.
> 
> (No failures observed, but only short tests thus far.  And no failures 
> observed thus far from about 10 hours of running stock rcutorture in 
> parallel with 170 kernel builds on a two-CPU machine.)

applied to tip/core/rcu - thanks Paul.

> +static int irqreader = 1;	/* RCU readers from irq (timers). */

Good - this means that in bzImage type of tests (built-in rcutorture, no 
modules) this new test variant will be activated by default, right?

	Ingo

^ permalink raw reply	[flat|nested] 24+ messages in thread

* Re: [PATCH -tip-rcu] Make rcutorture more vicious: invoke RCU readers from irq handlers (timers)
  2008-06-26  7:22       ` Ingo Molnar
@ 2008-06-26 15:48         ` Paul E. McKenney
  0 siblings, 0 replies; 24+ messages in thread
From: Paul E. McKenney @ 2008-06-26 15:48 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, josh, dvhltc, niv, dino, akpm, torvalds,
	vegard.nossum, adobriyan, oleg, bunk, rjw

On Thu, Jun 26, 2008 at 09:22:39AM +0200, Ingo Molnar wrote:
> 
> * Paul E. McKenney <paulmck@linux.vnet.ibm.com> wrote:
> 
> > This patch allows torturing RCU from irq handlers (timers, in this 
> > case). A new module parameter irqreader enables such additional 
> > torturing, and is enabled by default.  Variants of RCU that do not 
> > tolerate readers being called from irq handlers (e.g., SRCU) ignore 
> > irqreader.
> > 
> > (No failures observed, but only short tests thus far.  And no failures 
> > observed thus far from about 10 hours of running stock rcutorture in 
> > parallel with 170 kernel builds on a two-CPU machine.)
> 
> applied to tip/core/rcu - thanks Paul.
> 
> > +static int irqreader = 1;	/* RCU readers from irq (timers). */
> 
> Good - this means that in bzImage type of tests (built-in rcutorture, no 
> modules) this new test variant will be activated by default, right?

Ah, I knew I was forgetting to test something...

OK, checked it out by booting with rcutorture.stat_interval=100 so that
I can see the statistics.  I enabled rcutorture after the machine booted
with "echo 1 > /proc/sys/kernel/rcutorture_runnable".  Then I saw the
following in dmesg:

rcu-torture: rtc: ffffffff8098b9a0 ver: 16961 tfle: 0 rta: 16961 rtaf: 0 rtf: 16922 rtmbe: 0 nt: 121139
rcu-torture: Reader Pipe:  93315610 6300 0 0 0 0 0 0 0 0 0
rcu-torture: Reader Batch:  93315670 6240 0 0 0 0 0 0 0 0 0
rcu-torture: Free-Block Circulation:  16960 16960 16960 16960 16959 16951 16943 16936 16928 16922 0

The "nt: 121139" is the count of the number of times that an RCU read-side
critical section has been invoked from an rcutorture timer handler.

So yes, it does work.  ;-)

							Thanx, Paul

^ permalink raw reply	[flat|nested] 24+ messages in thread

end of thread, other threads:[~2008-06-26 15:48 UTC | newest]

Thread overview: 24+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2008-06-18 12:21 [PATCH] Make rcutorture more vicious: add stutter feature Paul E. McKenney
2008-06-18 13:08 ` Ingo Molnar
2008-06-18 16:26 ` [PATCH] Make rcutorture more vicious: reinstate boot-time testing Paul E. McKenney
2008-06-19  0:42   ` Josh Triplett
2008-06-19  9:29   ` Ingo Molnar
2008-06-19 15:58     ` Paul E. McKenney
2008-06-19 21:17       ` Randy Dunlap
2008-06-20  5:47         ` Paul E. McKenney
2008-06-21  1:39           ` Randy Dunlap
2008-06-22 20:06   ` [PATCH -tip-rcu] Make rcutorture more vicious: make quiescent rcutorture less power-hungry Paul E. McKenney
2008-06-22 20:17     ` Arjan van de Ven
2008-06-22 21:02       ` Paul E. McKenney
2008-06-24 11:37         ` Ingo Molnar
2008-06-23 17:54       ` Darren Hart
2008-06-23 18:07         ` Arjan van de Ven
2008-06-23 20:02           ` Darren Hart
2008-06-23 20:07             ` Arjan van de Ven
2008-06-23 20:15             ` Paul E. McKenney
2008-06-23 21:28               ` Darren Hart
2008-06-22 20:58     ` Vegard Nossum
2008-06-22 21:24       ` Vegard Nossum
2008-06-25 19:24     ` [PATCH -tip-rcu] Make rcutorture more vicious: invoke RCU readers from irq handlers (timers) Paul E. McKenney
2008-06-26  7:22       ` Ingo Molnar
2008-06-26 15:48         ` Paul E. McKenney

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.