Merge branch 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull the leap second fixes from Thomas Gleixner: "It's a rather large series, but well discussed, refined and reviewed. It got a massive testing by John, Prarit and tip. In theory we could split it into two parts. The first two patches f55a6faa3843: hrtimer: Provide clock_was_set_delayed() 4873fa070ae8: timekeeping: Fix leapsecond triggered load spike issue are merely preventing the stuff loops forever issues, which people have observed. But there is no point in delaying the other 4 commits which achieve full correctness into 3.6 as they are tagged for stable anyway. And I rather prefer to have the full fixes merged in bulk than a "prevent the observable wreckage and deal with the hidden fallout later" approach." * 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: hrtimer: Update hrtimer base offsets each hrtimer_interrupt timekeeping: Provide hrtimer update function hrtimers: Move lock held region in hrtimer_interrupt() timekeeping: Maintain ktime_t based offsets for hrtimers timekeeping: Fix leapsecond triggered load spike issue hrtimer: Provide clock_was_set_delayed()
This commit is contained in:
commit
d55e5bd020
|
@ -165,6 +165,7 @@ enum hrtimer_base_type {
|
|||
* @lock: lock protecting the base and associated clock bases
|
||||
* and timers
|
||||
* @active_bases: Bitfield to mark bases with active timers
|
||||
* @clock_was_set: Indicates that clock was set from irq context.
|
||||
* @expires_next: absolute time of the next event which was scheduled
|
||||
* via clock_set_next_event()
|
||||
* @hres_active: State of high resolution mode
|
||||
|
@ -177,7 +178,8 @@ enum hrtimer_base_type {
|
|||
*/
|
||||
struct hrtimer_cpu_base {
|
||||
raw_spinlock_t lock;
|
||||
unsigned long active_bases;
|
||||
unsigned int active_bases;
|
||||
unsigned int clock_was_set;
|
||||
#ifdef CONFIG_HIGH_RES_TIMERS
|
||||
ktime_t expires_next;
|
||||
int hres_active;
|
||||
|
@ -286,6 +288,8 @@ extern void hrtimer_peek_ahead_timers(void);
|
|||
# define MONOTONIC_RES_NSEC HIGH_RES_NSEC
|
||||
# define KTIME_MONOTONIC_RES KTIME_HIGH_RES
|
||||
|
||||
extern void clock_was_set_delayed(void);
|
||||
|
||||
#else
|
||||
|
||||
# define MONOTONIC_RES_NSEC LOW_RES_NSEC
|
||||
|
@ -306,6 +310,9 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer)
|
|||
{
|
||||
return 0;
|
||||
}
|
||||
|
||||
static inline void clock_was_set_delayed(void) { }
|
||||
|
||||
#endif
|
||||
|
||||
extern void clock_was_set(void);
|
||||
|
@ -320,6 +327,7 @@ extern ktime_t ktime_get(void);
|
|||
extern ktime_t ktime_get_real(void);
|
||||
extern ktime_t ktime_get_boottime(void);
|
||||
extern ktime_t ktime_get_monotonic_offset(void);
|
||||
extern ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot);
|
||||
|
||||
DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
|
||||
|
||||
|
|
|
@ -657,6 +657,14 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
|
|||
return 0;
|
||||
}
|
||||
|
||||
static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
|
||||
{
|
||||
ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
|
||||
ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
|
||||
|
||||
return ktime_get_update_offsets(offs_real, offs_boot);
|
||||
}
|
||||
|
||||
/*
|
||||
* Retrigger next event is called after clock was set
|
||||
*
|
||||
|
@ -665,22 +673,12 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
|
|||
static void retrigger_next_event(void *arg)
|
||||
{
|
||||
struct hrtimer_cpu_base *base = &__get_cpu_var(hrtimer_bases);
|
||||
struct timespec realtime_offset, xtim, wtm, sleep;
|
||||
|
||||
if (!hrtimer_hres_active())
|
||||
return;
|
||||
|
||||
/* Optimized out for !HIGH_RES */
|
||||
get_xtime_and_monotonic_and_sleep_offset(&xtim, &wtm, &sleep);
|
||||
set_normalized_timespec(&realtime_offset, -wtm.tv_sec, -wtm.tv_nsec);
|
||||
|
||||
/* Adjust CLOCK_REALTIME offset */
|
||||
raw_spin_lock(&base->lock);
|
||||
base->clock_base[HRTIMER_BASE_REALTIME].offset =
|
||||
timespec_to_ktime(realtime_offset);
|
||||
base->clock_base[HRTIMER_BASE_BOOTTIME].offset =
|
||||
timespec_to_ktime(sleep);
|
||||
|
||||
hrtimer_update_base(base);
|
||||
hrtimer_force_reprogram(base, 0);
|
||||
raw_spin_unlock(&base->lock);
|
||||
}
|
||||
|
@ -710,13 +708,25 @@ static int hrtimer_switch_to_hres(void)
|
|||
base->clock_base[i].resolution = KTIME_HIGH_RES;
|
||||
|
||||
tick_setup_sched_timer();
|
||||
|
||||
/* "Retrigger" the interrupt to get things going */
|
||||
retrigger_next_event(NULL);
|
||||
local_irq_restore(flags);
|
||||
return 1;
|
||||
}
|
||||
|
||||
/*
|
||||
* Called from timekeeping code to reprogramm the hrtimer interrupt
|
||||
* device. If called from the timer interrupt context we defer it to
|
||||
* softirq context.
|
||||
*/
|
||||
void clock_was_set_delayed(void)
|
||||
{
|
||||
struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
|
||||
|
||||
cpu_base->clock_was_set = 1;
|
||||
__raise_softirq_irqoff(HRTIMER_SOFTIRQ);
|
||||
}
|
||||
|
||||
#else
|
||||
|
||||
static inline int hrtimer_hres_active(void) { return 0; }
|
||||
|
@ -1250,11 +1260,10 @@ void hrtimer_interrupt(struct clock_event_device *dev)
|
|||
cpu_base->nr_events++;
|
||||
dev->next_event.tv64 = KTIME_MAX;
|
||||
|
||||
entry_time = now = ktime_get();
|
||||
raw_spin_lock(&cpu_base->lock);
|
||||
entry_time = now = hrtimer_update_base(cpu_base);
|
||||
retry:
|
||||
expires_next.tv64 = KTIME_MAX;
|
||||
|
||||
raw_spin_lock(&cpu_base->lock);
|
||||
/*
|
||||
* We set expires_next to KTIME_MAX here with cpu_base->lock
|
||||
* held to prevent that a timer is enqueued in our queue via
|
||||
|
@ -1330,8 +1339,12 @@ retry:
|
|||
* We need to prevent that we loop forever in the hrtimer
|
||||
* interrupt routine. We give it 3 attempts to avoid
|
||||
* overreacting on some spurious event.
|
||||
*
|
||||
* Acquire base lock for updating the offsets and retrieving
|
||||
* the current time.
|
||||
*/
|
||||
now = ktime_get();
|
||||
raw_spin_lock(&cpu_base->lock);
|
||||
now = hrtimer_update_base(cpu_base);
|
||||
cpu_base->nr_retries++;
|
||||
if (++retries < 3)
|
||||
goto retry;
|
||||
|
@ -1343,6 +1356,7 @@ retry:
|
|||
*/
|
||||
cpu_base->nr_hangs++;
|
||||
cpu_base->hang_detected = 1;
|
||||
raw_spin_unlock(&cpu_base->lock);
|
||||
delta = ktime_sub(now, entry_time);
|
||||
if (delta.tv64 > cpu_base->max_hang_time.tv64)
|
||||
cpu_base->max_hang_time = delta;
|
||||
|
@ -1395,6 +1409,13 @@ void hrtimer_peek_ahead_timers(void)
|
|||
|
||||
static void run_hrtimer_softirq(struct softirq_action *h)
|
||||
{
|
||||
struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
|
||||
|
||||
if (cpu_base->clock_was_set) {
|
||||
cpu_base->clock_was_set = 0;
|
||||
clock_was_set();
|
||||
}
|
||||
|
||||
hrtimer_peek_ahead_timers();
|
||||
}
|
||||
|
||||
|
|
|
@ -70,6 +70,12 @@ struct timekeeper {
|
|||
/* The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */
|
||||
struct timespec raw_time;
|
||||
|
||||
/* Offset clock monotonic -> clock realtime */
|
||||
ktime_t offs_real;
|
||||
|
||||
/* Offset clock monotonic -> clock boottime */
|
||||
ktime_t offs_boot;
|
||||
|
||||
/* Seqlock for all timekeeper values */
|
||||
seqlock_t lock;
|
||||
};
|
||||
|
@ -172,6 +178,14 @@ static inline s64 timekeeping_get_ns_raw(void)
|
|||
return clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift);
|
||||
}
|
||||
|
||||
static void update_rt_offset(void)
|
||||
{
|
||||
struct timespec tmp, *wtm = &timekeeper.wall_to_monotonic;
|
||||
|
||||
set_normalized_timespec(&tmp, -wtm->tv_sec, -wtm->tv_nsec);
|
||||
timekeeper.offs_real = timespec_to_ktime(tmp);
|
||||
}
|
||||
|
||||
/* must hold write on timekeeper.lock */
|
||||
static void timekeeping_update(bool clearntp)
|
||||
{
|
||||
|
@ -179,6 +193,7 @@ static void timekeeping_update(bool clearntp)
|
|||
timekeeper.ntp_error = 0;
|
||||
ntp_clear();
|
||||
}
|
||||
update_rt_offset();
|
||||
update_vsyscall(&timekeeper.xtime, &timekeeper.wall_to_monotonic,
|
||||
timekeeper.clock, timekeeper.mult);
|
||||
}
|
||||
|
@ -604,6 +619,7 @@ void __init timekeeping_init(void)
|
|||
}
|
||||
set_normalized_timespec(&timekeeper.wall_to_monotonic,
|
||||
-boot.tv_sec, -boot.tv_nsec);
|
||||
update_rt_offset();
|
||||
timekeeper.total_sleep_time.tv_sec = 0;
|
||||
timekeeper.total_sleep_time.tv_nsec = 0;
|
||||
write_sequnlock_irqrestore(&timekeeper.lock, flags);
|
||||
|
@ -612,6 +628,12 @@ void __init timekeeping_init(void)
|
|||
/* time in seconds when suspend began */
|
||||
static struct timespec timekeeping_suspend_time;
|
||||
|
||||
static void update_sleep_time(struct timespec t)
|
||||
{
|
||||
timekeeper.total_sleep_time = t;
|
||||
timekeeper.offs_boot = timespec_to_ktime(t);
|
||||
}
|
||||
|
||||
/**
|
||||
* __timekeeping_inject_sleeptime - Internal function to add sleep interval
|
||||
* @delta: pointer to a timespec delta value
|
||||
|
@ -630,8 +652,7 @@ static void __timekeeping_inject_sleeptime(struct timespec *delta)
|
|||
timekeeper.xtime = timespec_add(timekeeper.xtime, *delta);
|
||||
timekeeper.wall_to_monotonic =
|
||||
timespec_sub(timekeeper.wall_to_monotonic, *delta);
|
||||
timekeeper.total_sleep_time = timespec_add(
|
||||
timekeeper.total_sleep_time, *delta);
|
||||
update_sleep_time(timespec_add(timekeeper.total_sleep_time, *delta));
|
||||
}
|
||||
|
||||
|
||||
|
@ -963,6 +984,8 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
|
|||
leap = second_overflow(timekeeper.xtime.tv_sec);
|
||||
timekeeper.xtime.tv_sec += leap;
|
||||
timekeeper.wall_to_monotonic.tv_sec -= leap;
|
||||
if (leap)
|
||||
clock_was_set_delayed();
|
||||
}
|
||||
|
||||
/* Accumulate raw time */
|
||||
|
@ -1079,6 +1102,8 @@ static void update_wall_time(void)
|
|||
leap = second_overflow(timekeeper.xtime.tv_sec);
|
||||
timekeeper.xtime.tv_sec += leap;
|
||||
timekeeper.wall_to_monotonic.tv_sec -= leap;
|
||||
if (leap)
|
||||
clock_was_set_delayed();
|
||||
}
|
||||
|
||||
timekeeping_update(false);
|
||||
|
@ -1246,6 +1271,40 @@ void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
|
|||
} while (read_seqretry(&timekeeper.lock, seq));
|
||||
}
|
||||
|
||||
#ifdef CONFIG_HIGH_RES_TIMERS
|
||||
/**
|
||||
* ktime_get_update_offsets - hrtimer helper
|
||||
* @offs_real: pointer to storage for monotonic -> realtime offset
|
||||
* @offs_boot: pointer to storage for monotonic -> boottime offset
|
||||
*
|
||||
* Returns current monotonic time and updates the offsets
|
||||
* Called from hrtimer_interupt() or retrigger_next_event()
|
||||
*/
|
||||
ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot)
|
||||
{
|
||||
ktime_t now;
|
||||
unsigned int seq;
|
||||
u64 secs, nsecs;
|
||||
|
||||
do {
|
||||
seq = read_seqbegin(&timekeeper.lock);
|
||||
|
||||
secs = timekeeper.xtime.tv_sec;
|
||||
nsecs = timekeeper.xtime.tv_nsec;
|
||||
nsecs += timekeeping_get_ns();
|
||||
/* If arch requires, add in gettimeoffset() */
|
||||
nsecs += arch_gettimeoffset();
|
||||
|
||||
*offs_real = timekeeper.offs_real;
|
||||
*offs_boot = timekeeper.offs_boot;
|
||||
} while (read_seqretry(&timekeeper.lock, seq));
|
||||
|
||||
now = ktime_add_ns(ktime_set(secs, 0), nsecs);
|
||||
now = ktime_sub(now, *offs_real);
|
||||
return now;
|
||||
}
|
||||
#endif
|
||||
|
||||
/**
|
||||
* ktime_get_monotonic_offset() - get wall_to_monotonic in ktime_t format
|
||||
*/
|
||||
|
|
Loading…
Reference in New Issue