lkml.org 
[lkml]   [2007]   [Mar]   [12]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[patch] change futex_wait() to hrtimers

* Roland McGrath <roland@redhat.com> wrote:

> I agree it should restart. But I don't think this is quite right in
> the timeout case. It will increase the total maximum real time spent
> arbitrarily by the amount of time elapsed in signal handlers. Other
> restartable, timed calls have to convert to an absolute timeout for
> the restart block (and convert back when doing the restart).

i dont think we should try to do this. We should not and cannot do
anything about all of the artifacts that comes with the use of relative
timeouts and schedule_timeout().

basically, using jiffies here (which schedule_timeout() does) is
/fundamentally/ imprecise. If you get many interrupts, rounding errors
sum up - and there's nothing we can do about it!

the only correct approach is the use of hrtimers, and a patch exists for
that - see below. This has been included in -rt for quite some time.

so i'd suggest for Nick to add restart processing ontop of this patch:
hrtimers use absolute timeouts and hence there are neither rounding nor
signal processing delay artifacts.

Ingo

-------------->
From: S�bastien Dugu� <sebastien.dugue@bull.net>
Subject: [patch] change futex_wait() to hrtimers
This patch modifies futex_wait() to use an hrtimer + schedule() in place
of schedule_timeout().

schedule_timeout() is tick based, therefore the timeout granularity is
the tick (1 ms, 4 ms or 10 ms depending on HZ). By using a high
resolution timer for timeout wakeup, we can attain a much finer timeout
granularity (in the microsecond range). This parallels what is already
done for futex_lock_pi().

The timeout passed to the syscall is no longer converted to jiffies and
is therefore passed to do_futex() and futex_wait() as a timespec
therefore keeping nanosecond resolution.

Also this removes the need to pass the nanoseconds timeout part to
futex_lock_pi() in val2.

In futex_wait(), if the timeout is zero then a regular schedule() is
performed. Otherwise, an hrtimer is fired before schedule() is called.

Signed-off-by: S�bastien Dugu� <sebastien.dugue@bull.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

include/linux/futex.h | 2 -
kernel/futex.c | 61 +++++++++++++++++++++++++++++++++-----------------
kernel/futex_compat.c | 11 +--------
3 files changed, 44 insertions(+), 30 deletions(-)
Index: linux/include/linux/futex.h
===================================================================
--- linux.orig/include/linux/futex.h
+++ linux/include/linux/futex.h
@@ -94,7 +94,7 @@ struct robust_list_head {
#define ROBUST_LIST_LIMIT 2048

#ifdef __KERNEL__
-long do_futex(u32 __user *uaddr, int op, u32 val, unsigned long timeout,
+long do_futex(u32 __user *uaddr, int op, u32 val, struct timespec *timeout,
u32 __user *uaddr2, u32 val2, u32 val3);

extern int
Index: linux/kernel/futex.c
===================================================================
--- linux.orig/kernel/futex.c
+++ linux/kernel/futex.c
@@ -49,6 +49,7 @@
#include <linux/syscalls.h>
#include <linux/signal.h>
#include <asm/futex.h>
+#include <linux/hrtimer.h>

#include "rtmutex_common.h"

@@ -1000,7 +1001,7 @@ static void unqueue_me_pi(struct futex_q
drop_key_refs(&q->key);
}

-static int futex_wait(u32 __user *uaddr, u32 val, unsigned long time)
+static int futex_wait(u32 __user *uaddr, u32 val, struct timespec *time)
{
struct task_struct *curr = current;
DECLARE_WAITQUEUE(wait, curr);
@@ -1008,6 +1009,8 @@ static int futex_wait(u32 __user *uaddr,
struct futex_q q;
u32 uval;
int ret;
+ struct hrtimer_sleeper t;
+ int rem = 0;

q.pi_state = NULL;
retry:
@@ -1085,8 +1088,33 @@ static int futex_wait(u32 __user *uaddr,
* !list_empty() is safe here without any lock.
* q.lock_ptr != 0 is not safe, because of ordering against wakeup.
*/
- if (likely(!list_empty(&q.list)))
- time = schedule_timeout(time);
+ if (likely(!list_empty(&q.list))) {
+ if (time->tv_sec == 0 && time->tv_nsec == 0)
+ schedule();
+ else {
+
+ hrtimer_init(&t.timer, CLOCK_MONOTONIC,
+ HRTIMER_MODE_REL);
+ hrtimer_init_sleeper(&t, current);
+ t.timer.expires = timespec_to_ktime(*time);
+
+ hrtimer_start(&t.timer, t.timer.expires,
+ HRTIMER_MODE_REL);
+
+ /*
+ * the timer could have already expired, in which
+ * case current would be flagged for rescheduling.
+ * Don't bother calling schedule.
+ */
+ if (likely(t.task))
+ schedule();
+
+ hrtimer_cancel(&t.timer);
+
+ /* Flag if a timeout occured */
+ rem = (t.task == NULL);
+ }
+ }
__set_current_state(TASK_RUNNING);

/*
@@ -1097,7 +1125,7 @@ static int futex_wait(u32 __user *uaddr,
/* If we were woken (and unqueued), we succeeded, whatever. */
if (!unqueue_me(&q))
return 0;
- if (time == 0)
+ if (rem)
return -ETIMEDOUT;
/*
* We expect signal_pending(current), but another thread may
@@ -1119,8 +1147,8 @@ static int futex_wait(u32 __user *uaddr,
* if there are waiters then it will block, it does PI, etc. (Due to
* races the kernel might see a 0 value of the futex too.)
*/
-static int futex_lock_pi(u32 __user *uaddr, int detect, unsigned long sec,
- long nsec, int trylock)
+static int futex_lock_pi(u32 __user *uaddr, int detect, struct timespec *time,
+ int trylock)
{
struct hrtimer_sleeper timeout, *to = NULL;
struct task_struct *curr = current;
@@ -1132,11 +1160,11 @@ static int futex_lock_pi(u32 __user *uad
if (refill_pi_state_cache())
return -ENOMEM;

- if (sec != MAX_SCHEDULE_TIMEOUT) {
+ if (time->tv_sec || time->tv_nsec) {
to = &timeout;
hrtimer_init(&to->timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
hrtimer_init_sleeper(to, current);
- to->timer.expires = ktime_set(sec, nsec);
+ to->timer.expires = timespec_to_ktime(*time);
}

q.pi_state = NULL;
@@ -1772,7 +1800,7 @@ void exit_robust_list(struct task_struct
}
}

-long do_futex(u32 __user *uaddr, int op, u32 val, unsigned long timeout,
+long do_futex(u32 __user *uaddr, int op, u32 val, struct timespec *timeout,
u32 __user *uaddr2, u32 val2, u32 val3)
{
int ret;
@@ -1798,13 +1826,13 @@ long do_futex(u32 __user *uaddr, int op,
ret = futex_wake_op(uaddr, uaddr2, val, val2, val3);
break;
case FUTEX_LOCK_PI:
- ret = futex_lock_pi(uaddr, val, timeout, val2, 0);
+ ret = futex_lock_pi(uaddr, val, timeout, 0);
break;
case FUTEX_UNLOCK_PI:
ret = futex_unlock_pi(uaddr);
break;
case FUTEX_TRYLOCK_PI:
- ret = futex_lock_pi(uaddr, 0, timeout, val2, 1);
+ ret = futex_lock_pi(uaddr, 0, timeout, 1);
break;
default:
ret = -ENOSYS;
@@ -1817,8 +1845,7 @@ asmlinkage long sys_futex(u32 __user *ua
struct timespec __user *utime, u32 __user *uaddr2,
u32 val3)
{
- struct timespec t;
- unsigned long timeout = MAX_SCHEDULE_TIMEOUT;
+ struct timespec t = {.tv_sec=0, .tv_nsec=0};
u32 val2 = 0;

if (utime && (op == FUTEX_WAIT || op == FUTEX_LOCK_PI)) {
@@ -1826,12 +1853,6 @@ asmlinkage long sys_futex(u32 __user *ua
return -EFAULT;
if (!timespec_valid(&t))
return -EINVAL;
- if (op == FUTEX_WAIT)
- timeout = timespec_to_jiffies(&t) + 1;
- else {
- timeout = t.tv_sec;
- val2 = t.tv_nsec;
- }
}
/*
* requeue parameter in 'utime' if op == FUTEX_REQUEUE.
@@ -1839,7 +1860,7 @@ asmlinkage long sys_futex(u32 __user *ua
if (op == FUTEX_REQUEUE || op == FUTEX_CMP_REQUEUE)
val2 = (u32) (unsigned long) utime;

- return do_futex(uaddr, op, val, timeout, uaddr2, val2, val3);
+ return do_futex(uaddr, op, val, &t, uaddr2, val2, val3);
}

static int futexfs_get_sb(struct file_system_type *fs_type,
Index: linux/kernel/futex_compat.c
===================================================================
--- linux.orig/kernel/futex_compat.c
+++ linux/kernel/futex_compat.c
@@ -141,8 +141,7 @@ asmlinkage long compat_sys_futex(u32 __u
struct compat_timespec __user *utime, u32 __user *uaddr2,
u32 val3)
{
- struct timespec t;
- unsigned long timeout = MAX_SCHEDULE_TIMEOUT;
+ struct timespec t = {.tv_sec = 0, .tv_nsec = 0};
int val2 = 0;

if (utime && (op == FUTEX_WAIT || op == FUTEX_LOCK_PI)) {
@@ -150,15 +149,9 @@ asmlinkage long compat_sys_futex(u32 __u
return -EFAULT;
if (!timespec_valid(&t))
return -EINVAL;
- if (op == FUTEX_WAIT)
- timeout = timespec_to_jiffies(&t) + 1;
- else {
- timeout = t.tv_sec;
- val2 = t.tv_nsec;
- }
}
if (op == FUTEX_REQUEUE || op == FUTEX_CMP_REQUEUE)
val2 = (int) (unsigned long) utime;

- return do_futex(uaddr, op, val, timeout, uaddr2, val2, val3);
+ return do_futex(uaddr, op, val, &t, uaddr2, val2, val3);
}
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
\
 
 \ /
  Last update: 2007-03-12 10:13    [from the cache]
©2003-2011 Jasper Spaans