From 53f087febfd12e74ba9f1082e71e9a45adc039ad Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 1 Feb 2006 05:56:41 -0500 Subject: [PATCH] timer.c NULL noise removal Signed-off-by: Al Viro --- kernel/timer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/timer.c') diff --git a/kernel/timer.c b/kernel/timer.c index 4f1cb0ab525..b9dad399467 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -495,7 +495,7 @@ unsigned long next_timer_interrupt(void) base = &__get_cpu_var(tvec_bases); spin_lock(&base->t_base.lock); expires = base->timer_jiffies + (LONG_MAX >> 1); - list = 0; + list = NULL; /* Look for timer events in tv1. */ j = base->timer_jiffies & TVR_MASK; -- cgit v1.2.3-70-g09d2 From 726c14bf499e91e7ede4f1728830aba05c675061 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Fri, 17 Feb 2006 10:30:23 +1100 Subject: [PATCH] Provide an interface for getting the current tick length This provides an interface for arch code to find out how many nanoseconds are going to be added on to xtime by the next call to do_timer. The value returned is a fixed-point number in 52.12 format in nanoseconds. The reason for this format is that it gives the full precision that the timekeeping code is using internally. The motivation for this is to fix a problem that has arisen on 32-bit powerpc in that the value returned by do_gettimeofday drifts apart from xtime if NTP is being used. PowerPC is now using a lockless do_gettimeofday based on reading the timebase register and performing some simple arithmetic. (This method of getting the time is also exported to userspace via the VDSO.) However, the factor and offset it uses were calculated based on the nominal tick length and weren't being adjusted when NTP varied the tick length. Note that 64-bit powerpc has had the lockless do_gettimeofday for a long time now. It also had an extremely hairy routine that got called from the 32-bit compat routine for adjtimex, which adjusted the factor and offset according to what it thought the timekeeping code was going to do. Not only was this only called if a 32-bit task did adjtimex (i.e. not if a 64-bit task did adjtimex), it was also duplicating computations from kernel/timer.c and it wasn't clear that it was (still) correct. The simple solution is to ask the timekeeping code how long the current jiffy will be on each timer interrupt, after calling do_timer. If this jiffy will be a different length from the last one, we then need to compute new values for the factor and offset used in the lockless do_gettimeofday. In this way we can keep xtime and do_gettimeofday in sync, even when NTP is varying the tick length. Note that when adjtimex varies the tick length, it almost always introduces the variation from the next tick on. The only case I could see where adjtimex would vary the length of the current tick is when an old-style adjtime adjustment is being cancelled. (It's not clear to me why the adjustment has to be cancelled immediately rather than from the next tick on.) Thus I don't see any real need for a hook in adjtimex; the rare case of an old-style adjustment being cancelled can be fixed up at the next tick. Signed-off-by: Paul Mackerras Acked-by: john stultz Signed-off-by: Linus Torvalds --- include/linux/timex.h | 3 +++ kernel/timer.c | 39 ++++++++++++++++++++++++++++++++++----- 2 files changed, 37 insertions(+), 5 deletions(-) (limited to 'kernel/timer.c') diff --git a/include/linux/timex.h b/include/linux/timex.h index 04a4a8cb4ed..b7ca1204e42 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -345,6 +345,9 @@ time_interpolator_reset(void) #endif /* !CONFIG_TIME_INTERPOLATION */ +/* Returns how long ticks are at present, in ns / 2^(SHIFT_SCALE-10). */ +extern u64 current_tick_length(void); + #endif /* KERNEL */ #endif /* LINUX_TIMEX_H */ diff --git a/kernel/timer.c b/kernel/timer.c index b9dad399467..fe3a9a9f832 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -717,12 +717,16 @@ static void second_overflow(void) #endif } -/* in the NTP reference this is called "hardclock()" */ -static void update_wall_time_one_tick(void) +/* + * Returns how many microseconds we need to add to xtime this tick + * in doing an adjustment requested with adjtime. + */ +static long adjtime_adjustment(void) { - long time_adjust_step, delta_nsec; + long time_adjust_step; - if ((time_adjust_step = time_adjust) != 0 ) { + time_adjust_step = time_adjust; + if (time_adjust_step) { /* * We are doing an adjtime thing. Prepare time_adjust_step to * be within bounds. Note that a positive time_adjust means we @@ -733,10 +737,19 @@ static void update_wall_time_one_tick(void) */ time_adjust_step = min(time_adjust_step, (long)tickadj); time_adjust_step = max(time_adjust_step, (long)-tickadj); + } + return time_adjust_step; +} +/* in the NTP reference this is called "hardclock()" */ +static void update_wall_time_one_tick(void) +{ + long time_adjust_step, delta_nsec; + + time_adjust_step = adjtime_adjustment(); + if (time_adjust_step) /* Reduce by this step the amount of time left */ time_adjust -= time_adjust_step; - } delta_nsec = tick_nsec + time_adjust_step * 1000; /* * Advance the phase, once it gets to one microsecond, then @@ -758,6 +771,22 @@ static void update_wall_time_one_tick(void) } } +/* + * Return how long ticks are at the moment, that is, how much time + * update_wall_time_one_tick will add to xtime next time we call it + * (assuming no calls to do_adjtimex in the meantime). + * The return value is in fixed-point nanoseconds with SHIFT_SCALE-10 + * bits to the right of the binary point. + * This function has no side-effects. + */ +u64 current_tick_length(void) +{ + long delta_nsec; + + delta_nsec = tick_nsec + adjtime_adjustment() * 1000; + return ((u64) delta_nsec << (SHIFT_SCALE - 10)) + time_adj; +} + /* * Using a loop looks inefficient, but "ticks" is * usually just one (we shouldn't be losing ticks, -- cgit v1.2.3-70-g09d2 From 685db65e422bfa523b8a9dacb5a658b42b254f05 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 2 Mar 2006 02:54:35 -0800 Subject: [PATCH] time_interpolator: Use readq_relaxed() instead of readq(). On some platforms readq performs additional work to make sure I/O is done in a coherent way. This is not needed for time retrieval as done by the time interpolator. So we can use readq_relaxed instead which will improve performance. It affects sparc64 and ia64 only. Apparently it makes a significant difference on ia64. Signed-off-by: Christoph Lameter Cc: john stultz Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/timer.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/timer.c') diff --git a/kernel/timer.c b/kernel/timer.c index fe3a9a9f832..fc6646fd5aa 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1351,10 +1351,10 @@ static inline u64 time_interpolator_get_cycles(unsigned int src) return x(); case TIME_SOURCE_MMIO64 : - return readq((void __iomem *) time_interpolator->addr); + return readq_relaxed((void __iomem *)time_interpolator->addr); case TIME_SOURCE_MMIO32 : - return readl((void __iomem *) time_interpolator->addr); + return readl_relaxed((void __iomem *)time_interpolator->addr); default: return get_cycles(); } -- cgit v1.2.3-70-g09d2 From 69239749e1ac4f3496906aa4267cb9f61ce52c9c Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 6 Mar 2006 15:42:45 -0800 Subject: [PATCH] fix next_timer_interrupt() for hrtimer Also from Thomas Gleixner Function next_timer_interrupt() got broken with a recent patch 6ba1b91213e81aa92b5cf7539f7d2a94ff54947c as sys_nanosleep() was moved to hrtimer. This broke things as next_timer_interrupt() did not check hrtimer tree for next event. Function next_timer_interrupt() is needed with dyntick (CONFIG_NO_IDLE_HZ, VST) implementations, as the system can be in idle when next hrtimer event was supposed to happen. At least ARM and S390 currently use next_timer_interrupt(). Signed-off-by: Thomas Gleixner Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/kernel/time.c | 10 ++++++---- include/linux/hrtimer.h | 4 ++++ kernel/hrtimer.c | 35 +++++++++++++++++++++++++++++++++++ kernel/timer.c | 16 ++++++++++++++++ 4 files changed, 61 insertions(+), 4 deletions(-) (limited to 'kernel/timer.c') diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c index d7d932c0286..d6bd435a685 100644 --- a/arch/arm/kernel/time.c +++ b/arch/arm/kernel/time.c @@ -422,12 +422,14 @@ static int timer_dyn_tick_disable(void) void timer_dyn_reprogram(void) { struct dyn_tick_timer *dyn_tick = system_timer->dyn_tick; + unsigned long next, seq; - if (dyn_tick) { - write_seqlock(&xtime_lock); - if (dyn_tick->state & DYN_TICK_ENABLED) + if (dyn_tick && (dyn_tick->state & DYN_TICK_ENABLED)) { + next = next_timer_interrupt(); + do { + seq = read_seqbegin(&xtime_lock); dyn_tick->reprogram(next_timer_interrupt() - jiffies); - write_sequnlock(&xtime_lock); + } while (read_seqretry(&xtime_lock, seq)); } } diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 6361544bb6a..6401c31d6ad 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -116,6 +116,10 @@ extern int hrtimer_try_to_cancel(struct hrtimer *timer); extern ktime_t hrtimer_get_remaining(const struct hrtimer *timer); extern int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp); +#ifdef CONFIG_NO_IDLE_HZ +extern ktime_t hrtimer_get_next_event(void); +#endif + static inline int hrtimer_active(const struct hrtimer *timer) { return timer->state == HRTIMER_PENDING; diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 5ae51f1bc7c..14bc9cfa639 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -505,6 +505,41 @@ ktime_t hrtimer_get_remaining(const struct hrtimer *timer) return rem; } +#ifdef CONFIG_NO_IDLE_HZ +/** + * hrtimer_get_next_event - get the time until next expiry event + * + * Returns the delta to the next expiry event or KTIME_MAX if no timer + * is pending. + */ +ktime_t hrtimer_get_next_event(void) +{ + struct hrtimer_base *base = __get_cpu_var(hrtimer_bases); + ktime_t delta, mindelta = { .tv64 = KTIME_MAX }; + unsigned long flags; + int i; + + for (i = 0; i < MAX_HRTIMER_BASES; i++, base++) { + struct hrtimer *timer; + + spin_lock_irqsave(&base->lock, flags); + if (!base->first) { + spin_unlock_irqrestore(&base->lock, flags); + continue; + } + timer = rb_entry(base->first, struct hrtimer, node); + delta.tv64 = timer->expires.tv64; + spin_unlock_irqrestore(&base->lock, flags); + delta = ktime_sub(delta, base->get_time()); + if (delta.tv64 < mindelta.tv64) + mindelta.tv64 = delta.tv64; + } + if (mindelta.tv64 < 0) + mindelta.tv64 = 0; + return mindelta; +} +#endif + /** * hrtimer_init - initialize a timer to the given clock * diff --git a/kernel/timer.c b/kernel/timer.c index fc6646fd5aa..8256f3f5ec0 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -489,9 +489,21 @@ unsigned long next_timer_interrupt(void) struct list_head *list; struct timer_list *nte; unsigned long expires; + unsigned long hr_expires = MAX_JIFFY_OFFSET; + ktime_t hr_delta; tvec_t *varray[4]; int i, j; + hr_delta = hrtimer_get_next_event(); + if (hr_delta.tv64 != KTIME_MAX) { + struct timespec tsdelta; + tsdelta = ktime_to_timespec(hr_delta); + hr_expires = timespec_to_jiffies(&tsdelta); + if (hr_expires < 3) + return hr_expires + jiffies; + } + hr_expires += jiffies; + base = &__get_cpu_var(tvec_bases); spin_lock(&base->t_base.lock); expires = base->timer_jiffies + (LONG_MAX >> 1); @@ -542,6 +554,10 @@ found: } } spin_unlock(&base->t_base.lock); + + if (time_before(hr_expires, expires)) + return hr_expires; + return expires; } #endif -- cgit v1.2.3-70-g09d2 From 5aee405c662ca644980c184774277fc6d0769a84 Mon Sep 17 00:00:00 2001 From: Atsushi Nemoto Date: Mon, 6 Mar 2006 15:42:51 -0800 Subject: [PATCH] time: add barrier after updating jiffies_64 Add a compiler barrier so that we don't read jiffies before updating jiffies_64. Signed-off-by: Atsushi Nemoto Cc: Ralf Baechle Cc: Paul Mackerras Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/timer.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/timer.c') diff --git a/kernel/timer.c b/kernel/timer.c index 8256f3f5ec0..bf7c4193b93 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -941,6 +941,8 @@ static inline void update_times(void) void do_timer(struct pt_regs *regs) { jiffies_64++; + /* prevent loading jiffies before storing new jiffies_64 value. */ + barrier(); update_times(); softlockup_tick(regs); } -- cgit v1.2.3-70-g09d2