Because of how the code flips between tsc-early and tsc clocksources it might need to mark one or both unstable. The current code in mark_tsc_unstable() only worked because previously it registered the tsc clocksource once and then never touched it. Since it now unregisters the tsc-early clocksource, it needs to know if a clocksource got unregistered and the current cs->mult test doesn't work for that. Instead use list_empty(&cs->list) to test for registration. Furthermore, since clocksource_mark_unstable() needs to place the cs on the wd_list, it links the cs->list and cs->wd_list serialization. It must not see a clocsource registered (!empty cs->list) but already past dequeue_watchdog(). So place {en,de}queue{,_watchdog}() under the same lock. Provided cs->list is initialized to empty, this then allows us to unconditionally use clocksource_mark_unstable(), regardless of the registration state. Cc: stable@kernel.org Tested-by: Diego Viola Signed-off-by: Peter Zijlstra (Intel) --- kernel/time/clocksource.c | 47 ++++++++++++++++++++++++++++++---------------- 1 file changed, 31 insertions(+), 16 deletions(-) --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -119,6 +119,16 @@ static DEFINE_SPINLOCK(watchdog_lock); static int watchdog_running; static atomic_t watchdog_reset_pending; +static void inline clocksource_watchdog_lock(unsigned long *flags) +{ + spin_lock_irqsave(&watchdog_lock, *flags); +} + +static void inline clocksource_watchdog_unlock(unsigned long *flags) +{ + spin_unlock_irqrestore(&watchdog_lock, *flags); +} + static int clocksource_watchdog_kthread(void *data); static void __clocksource_change_rating(struct clocksource *cs, int rating); @@ -142,6 +152,9 @@ static void __clocksource_unstable(struc cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG); cs->flags |= CLOCK_SOURCE_UNSTABLE; + if (list_empty(&cs->list)) + return; + if (cs->mark_unstable) cs->mark_unstable(cs); @@ -164,7 +177,7 @@ void clocksource_mark_unstable(struct cl spin_lock_irqsave(&watchdog_lock, flags); if (!(cs->flags & CLOCK_SOURCE_UNSTABLE)) { - if (list_empty(&cs->wd_list)) + if (!list_empty(&cs->list) && list_empty(&cs->wd_list)) list_add(&cs->wd_list, &watchdog_list); __clocksource_unstable(cs); } @@ -319,9 +332,6 @@ static void clocksource_resume_watchdog( static void clocksource_enqueue_watchdog(struct clocksource *cs) { - unsigned long flags; - - spin_lock_irqsave(&watchdog_lock, flags); if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) { /* cs is a clocksource to be watched. */ list_add(&cs->wd_list, &watchdog_list); @@ -331,7 +341,6 @@ static void clocksource_enqueue_watchdog if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES; } - spin_unlock_irqrestore(&watchdog_lock, flags); } static void clocksource_select_watchdog(bool fallback) @@ -373,9 +382,6 @@ static void clocksource_select_watchdog( static void clocksource_dequeue_watchdog(struct clocksource *cs) { - unsigned long flags; - - spin_lock_irqsave(&watchdog_lock, flags); if (cs != watchdog) { if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) { /* cs is a watched clocksource. */ @@ -384,21 +390,19 @@ static void clocksource_dequeue_watchdog clocksource_stop_watchdog(); } } - spin_unlock_irqrestore(&watchdog_lock, flags); } static int __clocksource_watchdog_kthread(void) { struct clocksource *cs, *tmp; unsigned long flags; - LIST_HEAD(unstable); int select = 0; spin_lock_irqsave(&watchdog_lock, flags); list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) { if (cs->flags & CLOCK_SOURCE_UNSTABLE) { list_del_init(&cs->wd_list); - list_add(&cs->wd_list, &unstable); + __clocksource_change_rating(cs, 0); select = 1; } if (cs->flags & CLOCK_SOURCE_RESELECT) { @@ -410,11 +414,6 @@ static int __clocksource_watchdog_kthrea clocksource_stop_watchdog(); spin_unlock_irqrestore(&watchdog_lock, flags); - /* Needs to be done outside of watchdog lock */ - list_for_each_entry_safe(cs, tmp, &unstable, wd_list) { - list_del_init(&cs->wd_list); - __clocksource_change_rating(cs, 0); - } return select; } @@ -779,14 +778,19 @@ EXPORT_SYMBOL_GPL(__clocksource_update_f */ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) { + unsigned long flags; /* Initialize mult/shift and max_idle_ns */ __clocksource_update_freq_scale(cs, scale, freq); /* Add clocksource to the clocksource list */ mutex_lock(&clocksource_mutex); + + clocksource_watchdog_lock(&flags); clocksource_enqueue(cs); clocksource_enqueue_watchdog(cs); + clocksource_watchdog_unlock(&flags); + clocksource_select(); clocksource_select_watchdog(false); mutex_unlock(&clocksource_mutex); @@ -808,8 +812,13 @@ static void __clocksource_change_rating( */ void clocksource_change_rating(struct clocksource *cs, int rating) { + unsigned long flags; + mutex_lock(&clocksource_mutex); + clocksource_watchdog_lock(&flags); __clocksource_change_rating(cs, rating); + clocksource_watchdog_unlock(&flags); + clocksource_select(); clocksource_select_watchdog(false); mutex_unlock(&clocksource_mutex); @@ -821,6 +830,8 @@ EXPORT_SYMBOL(clocksource_change_rating) */ static int clocksource_unbind(struct clocksource *cs) { + unsigned long flags; + if (clocksource_is_watchdog(cs)) { /* Select and try to install a replacement watchdog. */ clocksource_select_watchdog(true); @@ -834,8 +845,12 @@ static int clocksource_unbind(struct clo if (curr_clocksource == cs) return -EBUSY; } + + clocksource_watchdog_lock(&flags); clocksource_dequeue_watchdog(cs); list_del_init(&cs->list); + clocksource_watchdog_unlock(&flags); + return 0; }