diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index a19ae163c058..dbb68067ba4e 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -567,6 +567,12 @@ loops can be debugged more effectively on production systems. + clocksource.max_cswd_read_retries= [KNL] + Number of clocksource_watchdog() retries due to + external delays before the clock will be marked + unstable. Defaults to three retries, that is, + four attempts to read the clock under test. + clearcpuid=BITNUM[,BITNUM...] [X86] Disable CPUID feature X for the kernel. See arch/x86/include/asm/cpufeatures.h for the valid bit diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 428beb69426a..6863a054c970 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -124,6 +124,13 @@ static void __clocksource_change_rating(struct clocksource *cs, int rating); #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) { /* @@ -184,12 +191,45 @@ void clocksource_mark_unstable(struct clocksource *cs) spin_unlock_irqrestore(&watchdog_lock, flags); } +static ulong max_cswd_read_retries = 3; +module_param(max_cswd_read_retries, ulong, 0644); + +static bool cs_watchdog_read(struct clocksource *cs, u64 *csnow, u64 *wdnow) +{ + unsigned int nretries; + u64 wd_end, wd_delta; + int64_t wd_delay; + + for (nretries = 0; nretries <= max_cswd_read_retries; nretries++) { + local_irq_disable(); + *wdnow = watchdog->read(watchdog); + *csnow = cs->read(cs); + wd_end = watchdog->read(watchdog); + local_irq_enable(); + + wd_delta = clocksource_delta(wd_end, *wdnow, watchdog->mask); + wd_delay = clocksource_cyc2ns(wd_delta, watchdog->mult, + watchdog->shift); + if (wd_delay <= WATCHDOG_MAX_SKEW) { + if (nretries > 1 || nretries >= max_cswd_read_retries) { + pr_warn("timekeeping watchdog on CPU%d: %s retried %d times before success\n", + smp_processor_id(), watchdog->name, nretries); + } + return true; + } + } + + pr_warn("timekeeping watchdog on CPU%d: %s read-back delay of %lldns, attempt %d, marking unstable\n", + smp_processor_id(), watchdog->name, wd_delay, nretries); + return false; +} + static void clocksource_watchdog(struct timer_list *unused) { - struct clocksource *cs; u64 csnow, wdnow, cslast, wdlast, delta; - int64_t wd_nsec, cs_nsec; int next_cpu, reset_pending; + int64_t wd_nsec, cs_nsec; + struct clocksource *cs; spin_lock(&watchdog_lock); if (!watchdog_running) @@ -206,10 +246,11 @@ static void clocksource_watchdog(struct timer_list *unused) continue; } - local_irq_disable(); - csnow = cs->read(cs); - wdnow = watchdog->read(watchdog); - local_irq_enable(); + if (!cs_watchdog_read(cs, &csnow, &wdnow)) { + /* Clock readout unreliable, so give it up. */ + __clocksource_unstable(cs); + continue; + } /* Clocksource initialized ? */ if (!(cs->flags & CLOCK_SOURCE_WATCHDOG) ||