| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20090602075409.GA19294@linux-sh.org>
Date: Tue, 2 Jun 2009 16:54:09 +0900
From: Paul Mundt <lethal@...ux-sh.org>
To: Peter Zijlstra <peterz@...radead.org>
Cc: Ingo Molnar <mingo@...e.hu>, Thomas Gleixner <tglx@...utronix.de>,
Daniel Walker <dwalker@...o99.com>,
Linus Walleij <linus.ml.walleij@...il.com>,
Andrew Victor <linux@...im.org.za>,
Haavard Skinnemoen <hskinnemoen@...el.com>,
Andrew Morton <akpm@...ux-foundation.org>,
John Stultz <johnstul@...ux.vnet.ibm.com>,
linux-arm-kernel@...ts.arm.linux.org.uk, linux-sh@...r.kernel.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH] sched: sched_clock() clocksource handling.
On Tue, Jun 02, 2009 at 09:41:35AM +0200, Peter Zijlstra wrote:
> On Tue, 2009-06-02 at 16:35 +0900, Paul Mundt wrote:
> >
> > We already do via select_clocksource(), if we are unregistering the
> > current one then a new one with the flag set is selected. Before that,
> > the override is likewise given preference, and we fall back on jiffies if
> > there is nothing else. I suppose we could try and find the "best" one,
> > but I think the override and manual clocksource selection should be fine
> > for this.
>
> Ah, ok. So unregister calls select_clocksource again? That does leave us
> a small window with jiffies, but I guess that's ok.
>
A synchronize_rcu() would fix that up, but I think a small window with
jiffies is less painful than sorting out RCU ordering and synchronization
for a corner case of a corner case ;-)
> > Now that you mention it though, the sched_clocksource() assignment within
> > select_clocksource() happens underneath the clocksource_lock, but is not
> > using rcu_assign_pointer().
>
> Right, that would want fixing indeed.
>
> > If the assignment there needs to use
> > rcu_assign_pointer() then presumably all of the unlock paths that do
> > select_clocksource() will have to synchronize_rcu()?
>
> No, you only have to do sync_rcu() when stuff that could have referenced
> is going away and you cannot use call_rcu().
>
> So when selecting a new clocksource, you don't need synchonization
> because stuff doesn't go away (I think :-)
Ok, that keeps things more simplified then. How does this look?
---
include/linux/clocksource.h | 4 +++-
kernel/sched_clock.c | 13 +++++++++++--
kernel/time/clocksource.c | 19 +++++++++++++++++++
kernel/time/jiffies.c | 2 +-
4 files changed, 34 insertions(+), 4 deletions(-)
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index c56457c..2109940 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -202,7 +202,8 @@ struct clocksource {
#endif
};
-extern struct clocksource *clock; /* current clocksource */
+extern struct clocksource *clock; /* current clocksource */
+extern struct clocksource *sched_clocksource; /* sched_clock() clocksource */
/*
* Clock source flags bits::
@@ -212,6 +213,7 @@ extern struct clocksource *clock; /* current clocksource */
#define CLOCK_SOURCE_WATCHDOG 0x10
#define CLOCK_SOURCE_VALID_FOR_HRES 0x20
+#define CLOCK_SOURCE_USE_FOR_SCHED_CLOCK 0x40
/* simplify initialization of mask field */
#define CLOCKSOURCE_MASK(bits) (cycle_t)((bits) < 64 ? ((1ULL<<(bits))-1) : -1)
diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
index e1d16c9..b51d48d 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -30,6 +30,8 @@
#include <linux/percpu.h>
#include <linux/ktime.h>
#include <linux/sched.h>
+#include <linux/clocksource.h>
+#include <linux/rcupdate.h>
/*
* Scheduler clock - returns current time in nanosec units.
@@ -38,8 +40,15 @@
*/
unsigned long long __attribute__((weak)) sched_clock(void)
{
- return (unsigned long long)(jiffies - INITIAL_JIFFIES)
- * (NSEC_PER_SEC / HZ);
+ unsigned long long time;
+ struct clocksource *clock;
+
+ rcu_read_lock();
+ clock = rcu_dereference(sched_clocksource);
+ time = cyc2ns(clock, clocksource_read(clock));
+ rcu_read_unlock();
+
+ return time;
}
static __read_mostly int sched_clock_running;
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 80189f6..f7243f2 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -25,6 +25,7 @@
*/
#include <linux/clocksource.h>
+#include <linux/rcupdate.h>
#include <linux/sysdev.h>
#include <linux/init.h>
#include <linux/module.h>
@@ -109,6 +110,7 @@ EXPORT_SYMBOL(timecounter_cyc2time);
/* XXX - Would like a better way for initializing curr_clocksource */
extern struct clocksource clocksource_jiffies;
+struct clocksource *sched_clocksource = &clocksource_jiffies;
/*[Clocksource internal variables]---------
* curr_clocksource:
@@ -362,6 +364,9 @@ static struct clocksource *select_clocksource(void)
if (next == curr_clocksource)
return NULL;
+ if (next->flags & CLOCK_SOURCE_USE_FOR_SCHED_CLOCK)
+ rcu_assign_pointer(sched_clocksource, next);
+
return next;
}
@@ -440,7 +445,21 @@ void clocksource_unregister(struct clocksource *cs)
list_del(&cs->list);
if (clocksource_override == cs)
clocksource_override = NULL;
+
next_clocksource = select_clocksource();
+
+ /*
+ * If select_clocksource() fails to find another suitable
+ * clocksource for sched_clocksource and we are unregistering
+ * it, switch back to jiffies.
+ */
+ if (sched_clocksource == cs) {
+ rcu_assign_pointer(sched_clocksource, &clocksource_jiffies);
+ spin_unlock_irqrestore(&clocksource_lock, flags);
+ synchronize_rcu();
+ return;
+ }
+
spin_unlock_irqrestore(&clocksource_lock, flags);
}
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index c3f6c30..727d881 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -52,7 +52,7 @@
static cycle_t jiffies_read(struct clocksource *cs)
{
- return (cycle_t) jiffies;
+ return (cycle_t) (jiffies - INITIAL_JIFFIES);
}
struct clocksource clocksource_jiffies = {
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists