GIT 117a3e18419d0fcfb95fd2708fc4323188f7cd74 git+ssh://master.kernel.org/pub/scm/linux/kernel/git/tglx/linux-2.6-hrt.git#mm commit Author: Jonathan Corbet Date: Mon Oct 29 09:39:38 2007 +0100 hrtimers: use hrtimers so that msleep() sleeps for the requested time The problem being addressed here is that the current msleep() will stop for a minimum of two jiffies, meaning that, on a HZ=100 system, msleep(1) delays for for about 20ms. In a driver with one such delay for each of 150 or so register setting operations, the extra time adds up to a few seconds. This patch addresses the situation by using hrtimers. On tickless systems with working timers, msleep(1) now sleeps for 1ms, even with HZ=100. Most comments last time were favorable. The one dissenter was Roman, who worries about the overhead of using hrtimers for this operation; my understanding is that he would rather see a really_msleep() function for those who actually want millisecond resolution. I'm not sure how to characterize what the cost could be, but it can only be buried by the fact that every call sleeps for some number of milliseconds. On my system, the several hundred total msleep() calls can't cause any real overhead, and almost all happen at initialization time. I still think it would be useful for msleep() to do what it says it does and not vastly oversleep with small arguments. A quick grep turns up 450 msleep(1) calls in the current mainline. Andrew, if you agree, can you drop this into -mm? If not, I guess I'll let it go. Current msleep() snoozes for at least two jiffies, causing msleep(1) to sleep for at least 20ms on HZ=100 systems. Using hrtimers allows msleep() to sleep for something much closer to the requested time. Signed-off-by: Jonathan Corbet Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner kernel/timer.c | 47 ++++++++++++++++++++++++++++++++++++++--------- 1 files changed, 38 insertions(+), 9 deletions(-) diff --git a/kernel/timer.c b/kernel/timer.c index a05817c..110554e 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1360,18 +1360,43 @@ void __init init_timers(void) open_softirq(TIMER_SOFTIRQ, run_timer_softirq, NULL); } + + + +static void do_msleep(unsigned int msecs, struct hrtimer_sleeper *sleeper, + int sigs) +{ + enum hrtimer_mode mode = HRTIMER_MODE_REL; + int state = sigs ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE; + + /* + * This is really just a reworked and simplified version + * of do_nanosleep(). + */ + hrtimer_init(&sleeper->timer, CLOCK_MONOTONIC, mode); + sleeper->timer.expires = ktime_set(0, msecs*NSEC_PER_MSEC); + hrtimer_init_sleeper(sleeper, current); + + do { + set_current_state(state); + hrtimer_start(&sleeper->timer, sleeper->timer.expires, mode); + if (sleeper->task) + schedule(); + hrtimer_cancel(&sleeper->timer); + mode = HRTIMER_MODE_ABS; + } while (sleeper->task && !(sigs && signal_pending(current))); +} + /** * msleep - sleep safely even with waitqueue interruptions * @msecs: Time in milliseconds to sleep for */ void msleep(unsigned int msecs) { - unsigned long timeout = msecs_to_jiffies(msecs) + 1; + struct hrtimer_sleeper sleeper; - while (timeout) - timeout = schedule_timeout_uninterruptible(timeout); + do_msleep(msecs, &sleeper, 0); } - EXPORT_SYMBOL(msleep); /** @@ -1380,11 +1405,15 @@ EXPORT_SYMBOL(msleep); */ unsigned long msleep_interruptible(unsigned int msecs) { - unsigned long timeout = msecs_to_jiffies(msecs) + 1; + struct hrtimer_sleeper sleeper; + ktime_t left; - while (timeout && !signal_pending(current)) - timeout = schedule_timeout_interruptible(timeout); - return jiffies_to_msecs(timeout); -} + do_msleep(msecs, &sleeper, 1); + if (!sleeper.task) + return 0; + left = ktime_sub(sleeper.timer.expires, + sleeper.timer.base->get_time()); + return max(((long) ktime_to_ns(left))/NSEC_PER_MSEC, 1L); +} EXPORT_SYMBOL(msleep_interruptible);