From 2e27e793e280ff12cb5c202a1214c08b0d3a0f26 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 27 May 2021 12:01:22 -0700 Subject: clocksource: Reduce clocksource-skew threshold Currently, WATCHDOG_THRESHOLD is set to detect a 62.5-millisecond skew in a 500-millisecond WATCHDOG_INTERVAL. This requires that clocks be skewed by more than 12.5% in order to be marked unstable. Except that a clock that is skewed by that much is probably destroying unsuspecting software right and left. And given that there are now checks for false-positive skews due to delays between reading the two clocks, it should be possible to greatly decrease WATCHDOG_THRESHOLD, at least for fine-grained clocks such as TSC. Therefore, add a new uncertainty_margin field to the clocksource structure that contains the maximum uncertainty in nanoseconds for the corresponding clock. This field may be initialized manually, as it is for clocksource_tsc_early and clocksource_jiffies, which is copied to refined_jiffies. If the field is not initialized manually, it will be computed at clock-registry time as the period of the clock in question based on the scale and freq parameters to __clocksource_update_freq_scale() function. If either of those two parameters are zero, the tens-of-milliseconds WATCHDOG_THRESHOLD is used as a cowardly alternative to dividing by zero. No matter how the uncertainty_margin field is calculated, it is bounded below by twice WATCHDOG_MAX_SKEW, that is, by 100 microseconds. Note that manually initialized uncertainty_margin fields are not adjusted, but there is a WARN_ON_ONCE() that triggers if any such field is less than twice WATCHDOG_MAX_SKEW. This WARN_ON_ONCE() is intended to discourage production use of the one-nanosecond uncertainty_margin values that are used to test the clock-skew code itself. The actual clock-skew check uses the sum of the uncertainty_margin fields of the two clocksource structures being compared. Integer overflow is avoided because the largest computed value of the uncertainty_margin fields is one billion (10^9), and double that value fits into an unsigned int. However, if someone manually specifies (say) UINT_MAX, they will get what they deserve. Note that the refined_jiffies uncertainty_margin field is initialized to TICK_NSEC, which means that skew checks involving this clocksource will be sufficently forgiving. In a similar vein, the clocksource_tsc_early uncertainty_margin field is initialized to 32*NSEC_PER_MSEC, which replicates the current behavior and allows custom setting if needed in order to address the rare skews detected for this clocksource in current mainline. Suggested-by: Thomas Gleixner Signed-off-by: Paul E. McKenney Signed-off-by: Thomas Gleixner Acked-by: Feng Tang Link: https://lore.kernel.org/r/20210527190124.440372-4-paulmck@kernel.org --- kernel/time/clocksource.c | 48 +++++++++++++++++++++++++++++++++++++---------- kernel/time/jiffies.c | 15 ++++++++------- 2 files changed, 46 insertions(+), 17 deletions(-) (limited to 'kernel') 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); -- cgit v1.2.3