diff options
| -rw-r--r-- | arch/x86/kernel/tsc.c | 1 | ||||
| -rw-r--r-- | include/linux/clocksource.h | 3 | ||||
| -rw-r--r-- | kernel/time/clocksource.c | 48 | ||||
| -rw-r--r-- | kernel/time/jiffies.c | 15 |
4 files changed, 50 insertions, 17 deletions
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 6eb1b097e97e..2e076a459a0c 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1128,6 +1128,7 @@ static int tsc_cs_enable(struct clocksource *cs) static struct clocksource clocksource_tsc_early = { .name = "tsc-early", .rating = 299, + .uncertainty_margin = 32 * NSEC_PER_MSEC, .read = read_tsc, .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS | diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 7f83d51c0fd7..895203727cb5 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -43,6 +43,8 @@ struct module; * @shift: Cycle to nanosecond divisor (power of two) * @max_idle_ns: Maximum idle time permitted by the clocksource (nsecs) * @maxadj: Maximum adjustment value to mult (~11%) + * @uncertainty_margin: Maximum uncertainty in nanoseconds per half second. + * Zero says to use default WATCHDOG_THRESHOLD. * @archdata: Optional arch-specific data * @max_cycles: Maximum safe cycle value which won't overflow on * multiplication @@ -98,6 +100,7 @@ struct clocksource { u32 shift; u64 max_idle_ns; u32 maxadj; + u32 uncertainty_margin; #ifdef CONFIG_ARCH_CLOCKSOURCE_DATA struct arch_clocksource_data archdata; #endif diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index e4beab21a1fa..9b27888a6e75 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -95,6 +95,20 @@ static char override_name[CS_NAME_LEN]; static int finished_booting; static u64 suspend_start; +/* + * Threshold: 0.0312s, when doubled: 0.0625s. + * Also a default for cs->uncertainty_margin when registering clocks. + */ +#define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 5) + +/* + * Maximum permissible delay between two readouts of the watchdog + * clocksource surrounding a read of the clocksource being validated. + * This delay could be due to SMIs, NMIs, or to VCPU preemptions. Used as + * a lower bound for cs->uncertainty_margin values when registering clocks. + */ +#define WATCHDOG_MAX_SKEW (50 * NSEC_PER_USEC) + #ifdef CONFIG_CLOCKSOURCE_WATCHDOG static void clocksource_watchdog_work(struct work_struct *work); static void clocksource_select(void); @@ -121,17 +135,9 @@ static int clocksource_watchdog_kthread(void *data); static void __clocksource_change_rating(struct clocksource *cs, int rating); /* - * Interval: 0.5sec Threshold: 0.0625s + * Interval: 0.5sec. */ #define WATCHDOG_INTERVAL (HZ >> 1) -#define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 4) - -/* - * Maximum permissible delay between two readouts of the watchdog - * clocksource surrounding a read of the clocksource being validated. - * This delay could be due to SMIs, NMIs, or to VCPU preemptions. - */ -#define WATCHDOG_MAX_SKEW (100 * NSEC_PER_USEC) static void clocksource_watchdog_work(struct work_struct *work) { @@ -348,6 +354,7 @@ static void clocksource_watchdog(struct timer_list *unused) int next_cpu, reset_pending; int64_t wd_nsec, cs_nsec; struct clocksource *cs; + u32 md; spin_lock(&watchdog_lock); if (!watchdog_running) @@ -394,7 +401,8 @@ static void clocksource_watchdog(struct timer_list *unused) continue; /* Check the deviation from the watchdog clocksource. */ - if (abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) { + md = cs->uncertainty_margin + watchdog->uncertainty_margin; + if (abs(cs_nsec - wd_nsec) > md) { pr_warn("timekeeping watchdog on CPU%d: Marking clocksource '%s' as unstable because the skew is too large:\n", smp_processor_id(), cs->name); pr_warn(" '%s' wd_now: %llx wd_last: %llx mask: %llx\n", @@ -1047,6 +1055,26 @@ void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq clocks_calc_mult_shift(&cs->mult, &cs->shift, freq, NSEC_PER_SEC / scale, sec * scale); } + + /* + * If the uncertainty margin is not specified, calculate it. + * If both scale and freq are non-zero, calculate the clock + * period, but bound below at 2*WATCHDOG_MAX_SKEW. However, + * if either of scale or freq is zero, be very conservative and + * take the tens-of-milliseconds WATCHDOG_THRESHOLD value for the + * uncertainty margin. Allow stupidly small uncertainty margins + * to be specified by the caller for testing purposes, but warn + * to discourage production use of this capability. + */ + if (scale && freq && !cs->uncertainty_margin) { + cs->uncertainty_margin = NSEC_PER_SEC / (scale * freq); + if (cs->uncertainty_margin < 2 * WATCHDOG_MAX_SKEW) + cs->uncertainty_margin = 2 * WATCHDOG_MAX_SKEW; + } else if (!cs->uncertainty_margin) { + cs->uncertainty_margin = WATCHDOG_THRESHOLD; + } + WARN_ON_ONCE(cs->uncertainty_margin < 2 * WATCHDOG_MAX_SKEW); + /* * Ensure clocksources that have large 'mult' values don't overflow * when adjusted. diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index a492e4da69ba..01935aafdb46 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -49,13 +49,14 @@ static u64 jiffies_read(struct clocksource *cs) * for "tick-less" systems. */ static struct clocksource clocksource_jiffies = { - .name = "jiffies", - .rating = 1, /* lowest valid rating*/ - .read = jiffies_read, - .mask = CLOCKSOURCE_MASK(32), - .mult = TICK_NSEC << JIFFIES_SHIFT, /* details above */ - .shift = JIFFIES_SHIFT, - .max_cycles = 10, + .name = "jiffies", + .rating = 1, /* lowest valid rating*/ + .uncertainty_margin = 32 * NSEC_PER_MSEC, + .read = jiffies_read, + .mask = CLOCKSOURCE_MASK(32), + .mult = TICK_NSEC << JIFFIES_SHIFT, /* details above */ + .shift = JIFFIES_SHIFT, + .max_cycles = 10, }; __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(jiffies_lock); |