From bd624d75db21ea5402f9ecf4450b311794d80352 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Fri, 13 Feb 2015 08:54:56 +0800 Subject: clockevents: Introduce mode specific callbacks It is not possible for the clockevents core to know which modes (other than those with a corresponding feature flag) are supported by a particular implementation. And drivers are expected to handle transition to all modes elegantly, as ->set_mode() would be issued for them unconditionally. Now, adding support for a new mode complicates things a bit if we want to use the legacy ->set_mode() callback. We need to closely review all clockevents drivers to see if they would break on addition of a new mode. And after such reviews, it is found that we have to do non-trivial changes to most of the drivers [1]. Introduce mode-specific set_mode_*() callbacks, some of which the drivers may or may not implement. A missing callback would clearly convey the message that the corresponding mode isn't supported. A driver may still choose to keep supporting the legacy ->set_mode() callback, but ->set_mode() wouldn't be supporting any new modes beyond RESUME. If a driver wants to benefit from using a new mode, it would be required to migrate to the mode specific callbacks. The legacy ->set_mode() callback and the newly introduced mode-specific callbacks are mutually exclusive. Only one of them should be supported by the driver. Sanity check is done at the time of registration to distinguish between optional and required callbacks and to make error recovery and handling simpler. If the legacy ->set_mode() callback is provided, all mode specific ones would be ignored by the core but a warning is thrown if they are present. Call sites calling ->set_mode() directly are also updated to use __clockevents_set_mode() instead, as ->set_mode() may not be available anymore for few drivers. [1] https://lkml.org/lkml/2014/12/9/605 [2] https://lkml.org/lkml/2015/1/23/255 Suggested-by: Thomas Gleixner [2] Signed-off-by: Viresh Kumar Signed-off-by: Peter Zijlstra (Intel) Cc: Daniel Lezcano Cc: Frederic Weisbecker Cc: John Stultz Cc: Kevin Hilman Cc: Linus Torvalds Cc: Preeti U Murthy Cc: linaro-kernel@lists.linaro.org Cc: linaro-networking@linaro.org Link: http://lkml.kernel.org/r/792d59a40423f0acffc9bb0bec9de1341a06fa02.1423788565.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar --- include/linux/clockchips.h | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 2e4cb67f6e56..59af26b54d15 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -39,6 +39,8 @@ enum clock_event_mode { CLOCK_EVT_MODE_PERIODIC, CLOCK_EVT_MODE_ONESHOT, CLOCK_EVT_MODE_RESUME, + + /* Legacy ->set_mode() callback doesn't support below modes */ }; /* @@ -81,7 +83,11 @@ enum clock_event_mode { * @mode: operating mode assigned by the management code * @features: features * @retries: number of forced programming retries - * @set_mode: set mode function + * @set_mode: legacy set mode function, only for modes <= CLOCK_EVT_MODE_RESUME. + * @set_mode_periodic: switch mode to periodic, if !set_mode + * @set_mode_oneshot: switch mode to oneshot, if !set_mode + * @set_mode_shutdown: switch mode to shutdown, if !set_mode + * @set_mode_resume: resume clkevt device, if !set_mode * @broadcast: function to broadcast events * @min_delta_ticks: minimum delta value in ticks stored for reconfiguration * @max_delta_ticks: maximum delta value in ticks stored for reconfiguration @@ -108,9 +114,20 @@ struct clock_event_device { unsigned int features; unsigned long retries; - void (*broadcast)(const struct cpumask *mask); + /* + * Mode transition callback(s): Only one of the two groups should be + * defined: + * - set_mode(), only for modes <= CLOCK_EVT_MODE_RESUME. + * - set_mode_{shutdown|periodic|oneshot|resume}(). + */ void (*set_mode)(enum clock_event_mode mode, struct clock_event_device *); + int (*set_mode_periodic)(struct clock_event_device *); + int (*set_mode_oneshot)(struct clock_event_device *); + int (*set_mode_shutdown)(struct clock_event_device *); + int (*set_mode_resume)(struct clock_event_device *); + + void (*broadcast)(const struct cpumask *mask); void (*suspend)(struct clock_event_device *); void (*resume)(struct clock_event_device *); unsigned long min_delta_ticks; -- cgit v1.2.3 From fb82fe2fe8588745edd73aa3a6229facac5c1e15 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 11 Mar 2015 21:16:31 -0700 Subject: clocksource: Add 'max_cycles' to 'struct clocksource' In order to facilitate clocksource validation, add a 'max_cycles' field to the clocksource structure which will hold the maximum cycle value that can safely be multiplied without potentially causing an overflow. Signed-off-by: John Stultz Cc: Dave Jones Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Prarit Bhargava Cc: Richard Cochran Cc: Stephen Boyd Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1426133800-29329-4-git-send-email-john.stultz@linaro.org Signed-off-by: Ingo Molnar --- include/linux/clocksource.h | 5 +++-- kernel/time/clocksource.c | 28 ++++++++++++++++------------ kernel/time/sched_clock.c | 2 +- 3 files changed, 20 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 9c78d15d33e4..16d048cadebb 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -56,6 +56,7 @@ struct module; * @shift: cycle to nanosecond divisor (power of two) * @max_idle_ns: max idle time permitted by the clocksource (nsecs) * @maxadj: maximum adjustment value to mult (~11%) + * @max_cycles: maximum safe cycle value which won't overflow on multiplication * @flags: flags describing special properties * @archdata: arch-specific data * @suspend: suspend function for the clocksource, if necessary @@ -76,7 +77,7 @@ struct clocksource { #ifdef CONFIG_ARCH_CLOCKSOURCE_DATA struct arch_clocksource_data archdata; #endif - + u64 max_cycles; const char *name; struct list_head list; int rating; @@ -189,7 +190,7 @@ extern struct clocksource * __init clocksource_default_clock(void); extern void clocksource_mark_unstable(struct clocksource *cs); extern u64 -clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask); +clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask, u64 *max_cycles); extern void clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 minsec); diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index ace95763b3a6..fc2a9de43ca1 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -469,11 +469,13 @@ static u32 clocksource_max_adjustment(struct clocksource *cs) * @shift: cycle to nanosecond divisor (power of two) * @maxadj: maximum adjustment value to mult (~11%) * @mask: bitmask for two's complement subtraction of non 64 bit counters + * @max_cyc: maximum cycle value before potential overflow (does not include + * any safety margin) * * NOTE: This function includes a safety margin of 50%, so that bad clock values * can be detected. */ -u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask) +u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask, u64 *max_cyc) { u64 max_nsecs, max_cycles; @@ -493,6 +495,10 @@ u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask) max_cycles = min(max_cycles, mask); max_nsecs = clocksource_cyc2ns(max_cycles, mult - maxadj, shift); + /* return the max_cycles value as well if requested */ + if (max_cyc) + *max_cyc = max_cycles; + /* Return 50% of the actual maximum, so we can detect bad values */ max_nsecs >>= 1; @@ -500,17 +506,15 @@ u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask) } /** - * clocksource_max_deferment - Returns max time the clocksource should be deferred - * @cs: Pointer to clocksource + * clocksource_update_max_deferment - Updates the clocksource max_idle_ns & max_cycles + * @cs: Pointer to clocksource to be updated * */ -static u64 clocksource_max_deferment(struct clocksource *cs) +static inline void clocksource_update_max_deferment(struct clocksource *cs) { - u64 max_nsecs; - - max_nsecs = clocks_calc_max_nsecs(cs->mult, cs->shift, cs->maxadj, - cs->mask); - return max_nsecs; + cs->max_idle_ns = clocks_calc_max_nsecs(cs->mult, cs->shift, + cs->maxadj, cs->mask, + &cs->max_cycles); } #ifndef CONFIG_ARCH_USES_GETTIMEOFFSET @@ -684,7 +688,7 @@ void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq) cs->maxadj = clocksource_max_adjustment(cs); } - cs->max_idle_ns = clocksource_max_deferment(cs); + clocksource_update_max_deferment(cs); } EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale); @@ -730,8 +734,8 @@ int clocksource_register(struct clocksource *cs) "Clocksource %s might overflow on 11%% adjustment\n", cs->name); - /* calculate max idle time permitted for this clocksource */ - cs->max_idle_ns = clocksource_max_deferment(cs); + /* Update max idle time permitted for this clocksource */ + clocksource_update_max_deferment(cs); mutex_lock(&clocksource_mutex); clocksource_enqueue(cs); diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index 3b8ae45020c1..ca3bc5c7027c 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -126,7 +126,7 @@ void __init sched_clock_register(u64 (*read)(void), int bits, new_mask = CLOCKSOURCE_MASK(bits); /* calculate how many nanosecs until we risk wrapping */ - wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask); + wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask, NULL); new_wrap_kt = ns_to_ktime(wrap); /* update epoch for new counter and update epoch_ns from old counter*/ -- cgit v1.2.3 From f8935983f110505daa38e8d36ee406807f83a069 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 11 Mar 2015 21:16:37 -0700 Subject: clocksource: Mostly kill clocksource_register() A long running project has been to clean up remaining uses of clocksource_register(), replacing it with the simpler clocksource_register_khz/hz() functions. However, there are a few cases where we need to self-define our mult/shift values, so switch the function to a more obviously internal __clocksource_register() name, and consolidate much of the internal logic so we don't have duplication. Signed-off-by: John Stultz Cc: Dave Jones Cc: David S. Miller Cc: Linus Torvalds Cc: Martin Schwidefsky Cc: Peter Zijlstra Cc: Prarit Bhargava Cc: Richard Cochran Cc: Stephen Boyd Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1426133800-29329-10-git-send-email-john.stultz@linaro.org [ Minor cleanups. ] Signed-off-by: Ingo Molnar --- arch/s390/kernel/time.c | 2 +- arch/sparc/kernel/time_32.c | 2 +- include/linux/clocksource.h | 10 +++++- kernel/time/clocksource.c | 81 +++++++++++++++++++-------------------------- kernel/time/jiffies.c | 4 +-- 5 files changed, 47 insertions(+), 52 deletions(-) (limited to 'include') diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 20660dddb2d6..6c273cd815bb 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -283,7 +283,7 @@ void __init time_init(void) if (register_external_irq(EXT_IRQ_TIMING_ALERT, timing_alert_interrupt)) panic("Couldn't request external interrupt 0x1406"); - if (clocksource_register(&clocksource_tod) != 0) + if (__clocksource_register(&clocksource_tod) != 0) panic("Could not register TOD clock source"); /* Enable TOD clock interrupts on the boot cpu. */ diff --git a/arch/sparc/kernel/time_32.c b/arch/sparc/kernel/time_32.c index 2f80d23a0a44..a31c0c822beb 100644 --- a/arch/sparc/kernel/time_32.c +++ b/arch/sparc/kernel/time_32.c @@ -191,7 +191,7 @@ static __init int setup_timer_cs(void) timer_cs.mult = clocksource_hz2mult(sparc_config.clock_rate, timer_cs.shift); - return clocksource_register(&timer_cs); + return __clocksource_register(&timer_cs); } #ifdef CONFIG_SMP diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 16d048cadebb..bd98eaa4d005 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -179,7 +179,6 @@ static inline s64 clocksource_cyc2ns(cycle_t cycles, u32 mult, u32 shift) } -extern int clocksource_register(struct clocksource*); extern int clocksource_unregister(struct clocksource*); extern void clocksource_touch_watchdog(void); extern struct clocksource* clocksource_get_next(void); @@ -203,6 +202,15 @@ __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq); extern void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq); +/* + * Don't call this unless you are a default clocksource + * (AKA: jiffies) and absolutely have to. + */ +static inline int __clocksource_register(struct clocksource *cs) +{ + return __clocksource_register_scale(cs, 1, 0); +} + static inline int clocksource_register_hz(struct clocksource *cs, u32 hz) { return __clocksource_register_scale(cs, 1, hz); diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index c4cc04bec698..5cdf17eb4fa6 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -656,38 +656,52 @@ static void clocksource_enqueue(struct clocksource *cs) void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq) { u64 sec; + /* - * Calc the maximum number of seconds which we can run before - * wrapping around. For clocksources which have a mask > 32bit - * we need to limit the max sleep time to have a good - * conversion precision. 10 minutes is still a reasonable - * amount. That results in a shift value of 24 for a - * clocksource with mask >= 40bit and f >= 4GHz. That maps to - * ~ 0.06ppm granularity for NTP. + * Default clocksources are *special* and self-define their mult/shift. + * But, you're not special, so you should specify a freq value. */ - sec = cs->mask; - do_div(sec, freq); - do_div(sec, scale); - if (!sec) - sec = 1; - else if (sec > 600 && cs->mask > UINT_MAX) - sec = 600; - - clocks_calc_mult_shift(&cs->mult, &cs->shift, freq, - NSEC_PER_SEC / scale, sec * scale); - + if (freq) { + /* + * Calc the maximum number of seconds which we can run before + * wrapping around. For clocksources which have a mask > 32-bit + * we need to limit the max sleep time to have a good + * conversion precision. 10 minutes is still a reasonable + * amount. That results in a shift value of 24 for a + * clocksource with mask >= 40-bit and f >= 4GHz. That maps to + * ~ 0.06ppm granularity for NTP. + */ + sec = cs->mask; + do_div(sec, freq); + do_div(sec, scale); + if (!sec) + sec = 1; + else if (sec > 600 && cs->mask > UINT_MAX) + sec = 600; + + clocks_calc_mult_shift(&cs->mult, &cs->shift, freq, + NSEC_PER_SEC / scale, sec * scale); + } /* * Ensure clocksources that have large 'mult' values don't overflow * when adjusted. */ cs->maxadj = clocksource_max_adjustment(cs); - while ((cs->mult + cs->maxadj < cs->mult) - || (cs->mult - cs->maxadj > cs->mult)) { + while (freq && ((cs->mult + cs->maxadj < cs->mult) + || (cs->mult - cs->maxadj > cs->mult))) { cs->mult >>= 1; cs->shift--; cs->maxadj = clocksource_max_adjustment(cs); } + /* + * Only warn for *special* clocksources that self-define + * their mult/shift values and don't specify a freq. + */ + WARN_ONCE(cs->mult + cs->maxadj < cs->mult, + "timekeeping: Clocksource %s might overflow on 11%% adjustment\n", + cs->name); + clocksource_update_max_deferment(cs); } EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale); @@ -719,33 +733,6 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) } EXPORT_SYMBOL_GPL(__clocksource_register_scale); - -/** - * clocksource_register - Used to install new clocksources - * @cs: clocksource to be registered - * - * Returns -EBUSY if registration fails, zero otherwise. - */ -int clocksource_register(struct clocksource *cs) -{ - /* calculate max adjustment for given mult/shift */ - cs->maxadj = clocksource_max_adjustment(cs); - WARN_ONCE(cs->mult + cs->maxadj < cs->mult, - "Clocksource %s might overflow on 11%% adjustment\n", - cs->name); - - /* Update max idle time permitted for this clocksource */ - clocksource_update_max_deferment(cs); - - mutex_lock(&clocksource_mutex); - clocksource_enqueue(cs); - clocksource_enqueue_watchdog(cs); - clocksource_select(); - mutex_unlock(&clocksource_mutex); - return 0; -} -EXPORT_SYMBOL(clocksource_register); - static void __clocksource_change_rating(struct clocksource *cs, int rating) { list_del(&cs->list); diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index 7e413902aa6a..c4bb518725b5 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -95,7 +95,7 @@ EXPORT_SYMBOL(jiffies); static int __init init_jiffies_clocksource(void) { - return clocksource_register(&clocksource_jiffies); + return __clocksource_register(&clocksource_jiffies); } core_initcall(init_jiffies_clocksource); @@ -131,6 +131,6 @@ int register_refined_jiffies(long cycles_per_second) refined_jiffies.mult = ((u32)nsec_per_tick) << JIFFIES_SHIFT; - clocksource_register(&refined_jiffies); + __clocksource_register(&refined_jiffies); return 0; } -- cgit v1.2.3 From fba9e07208c0f9d92d9f73761c99c8612039da44 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 11 Mar 2015 21:16:40 -0700 Subject: clocksource: Rename __clocksource_updatefreq_*() to __clocksource_update_freq_*() Ingo requested this function be renamed to improve readability, so I've renamed __clocksource_updatefreq_scale() as well as the __clocksource_updatefreq_hz/khz() functions to avoid squishedtogethernames. This touches some of the sh clocksources, which I've not tested. The arch/arm/plat-omap change is just a comment change for consistency. Signed-off-by: John Stultz Cc: Daniel Lezcano Cc: Dave Jones Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Prarit Bhargava Cc: Richard Cochran Cc: Stephen Boyd Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1426133800-29329-13-git-send-email-john.stultz@linaro.org Signed-off-by: Ingo Molnar --- arch/arm/plat-omap/counter_32k.c | 2 +- drivers/clocksource/em_sti.c | 2 +- drivers/clocksource/sh_cmt.c | 2 +- drivers/clocksource/sh_tmu.c | 2 +- include/linux/clocksource.h | 10 +++++----- kernel/time/clocksource.c | 11 ++++++----- 6 files changed, 15 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/arch/arm/plat-omap/counter_32k.c b/arch/arm/plat-omap/counter_32k.c index 61b4d705c267..43cf74561cfd 100644 --- a/arch/arm/plat-omap/counter_32k.c +++ b/arch/arm/plat-omap/counter_32k.c @@ -103,7 +103,7 @@ int __init omap_init_clocksource_32k(void __iomem *vbase) /* * 120000 rough estimate from the calculations in - * __clocksource_updatefreq_scale. + * __clocksource_update_freq_scale. */ clocks_calc_mult_shift(&persistent_mult, &persistent_shift, 32768, NSEC_PER_SEC, 120000); diff --git a/drivers/clocksource/em_sti.c b/drivers/clocksource/em_sti.c index d0a7bd66b8b9..dc3c6ee04aaa 100644 --- a/drivers/clocksource/em_sti.c +++ b/drivers/clocksource/em_sti.c @@ -210,7 +210,7 @@ static int em_sti_clocksource_enable(struct clocksource *cs) ret = em_sti_start(p, USER_CLOCKSOURCE); if (!ret) - __clocksource_updatefreq_hz(cs, p->rate); + __clocksource_update_freq_hz(cs, p->rate); return ret; } diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c index 2bd13b53b727..b8ff3c64cc45 100644 --- a/drivers/clocksource/sh_cmt.c +++ b/drivers/clocksource/sh_cmt.c @@ -641,7 +641,7 @@ static int sh_cmt_clocksource_enable(struct clocksource *cs) ret = sh_cmt_start(ch, FLAG_CLOCKSOURCE); if (!ret) { - __clocksource_updatefreq_hz(cs, ch->rate); + __clocksource_update_freq_hz(cs, ch->rate); ch->cs_enabled = true; } return ret; diff --git a/drivers/clocksource/sh_tmu.c b/drivers/clocksource/sh_tmu.c index f150ca82bfaf..b6b8fa3cd211 100644 --- a/drivers/clocksource/sh_tmu.c +++ b/drivers/clocksource/sh_tmu.c @@ -272,7 +272,7 @@ static int sh_tmu_clocksource_enable(struct clocksource *cs) ret = sh_tmu_enable(ch); if (!ret) { - __clocksource_updatefreq_hz(cs, ch->rate); + __clocksource_update_freq_hz(cs, ch->rate); ch->cs_enabled = true; } diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index bd98eaa4d005..135509821c39 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -200,7 +200,7 @@ clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 minsec); extern int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq); extern void -__clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq); +__clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq); /* * Don't call this unless you are a default clocksource @@ -221,14 +221,14 @@ static inline int clocksource_register_khz(struct clocksource *cs, u32 khz) return __clocksource_register_scale(cs, 1000, khz); } -static inline void __clocksource_updatefreq_hz(struct clocksource *cs, u32 hz) +static inline void __clocksource_update_freq_hz(struct clocksource *cs, u32 hz) { - __clocksource_updatefreq_scale(cs, 1, hz); + __clocksource_update_freq_scale(cs, 1, hz); } -static inline void __clocksource_updatefreq_khz(struct clocksource *cs, u32 khz) +static inline void __clocksource_update_freq_khz(struct clocksource *cs, u32 khz) { - __clocksource_updatefreq_scale(cs, 1000, khz); + __clocksource_update_freq_scale(cs, 1000, khz); } diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 1977ebabd922..c3be3c71bbad 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -643,7 +643,7 @@ static void clocksource_enqueue(struct clocksource *cs) } /** - * __clocksource_updatefreq_scale - Used update clocksource with new freq + * __clocksource_update_freq_scale - Used update clocksource with new freq * @cs: clocksource to be registered * @scale: Scale factor multiplied against freq to get clocksource hz * @freq: clocksource frequency (cycles per second) divided by scale @@ -651,9 +651,10 @@ static void clocksource_enqueue(struct clocksource *cs) * This should only be called from the clocksource->enable() method. * * This *SHOULD NOT* be called directly! Please use the - * clocksource_updatefreq_hz() or clocksource_updatefreq_khz helper functions. + * __clocksource_update_freq_hz() or __clocksource_update_freq_khz() helper + * functions. */ -void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq) +void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq) { u64 sec; @@ -707,7 +708,7 @@ void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq) pr_info("clocksource %s: mask: 0x%llx max_cycles: 0x%llx, max_idle_ns: %lld ns\n", cs->name, cs->mask, cs->max_cycles, cs->max_idle_ns); } -EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale); +EXPORT_SYMBOL_GPL(__clocksource_update_freq_scale); /** * __clocksource_register_scale - Used to install new clocksources @@ -724,7 +725,7 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) { /* Initialize mult/shift and max_idle_ns */ - __clocksource_updatefreq_scale(cs, scale, freq); + __clocksource_update_freq_scale(cs, scale, freq); /* Add clocksource to the clocksource list */ mutex_lock(&clocksource_mutex); -- cgit v1.2.3 From 876e78818def2983be55878b21f7152fbaebbd36 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 19 Mar 2015 10:09:06 +0100 Subject: time: Rename timekeeper::tkr to timekeeper::tkr_mono In preparation of adding another tkr field, rename this one to tkr_mono. Also rename tk_read_base::base_mono to tk_read_base::base, since the structure is not specific to CLOCK_MONOTONIC and the mono name got added to the tk_read_base instance. Lots of trivial churn. Signed-off-by: Peter Zijlstra (Intel) Acked-by: John Stultz Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20150319093400.344679419@infradead.org Signed-off-by: Ingo Molnar --- arch/arm64/kernel/vdso.c | 10 +-- arch/s390/kernel/time.c | 18 ++--- arch/tile/kernel/time.c | 24 +++--- arch/x86/kernel/vsyscall_gtod.c | 24 +++--- arch/x86/kvm/x86.c | 14 ++-- include/linux/timekeeper_internal.h | 12 +-- kernel/time/timekeeping.c | 150 ++++++++++++++++++------------------ 7 files changed, 126 insertions(+), 126 deletions(-) (limited to 'include') diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 32aeea083d93..ec37ab3f524f 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -200,7 +200,7 @@ up_fail: void update_vsyscall(struct timekeeper *tk) { struct timespec xtime_coarse; - u32 use_syscall = strcmp(tk->tkr.clock->name, "arch_sys_counter"); + u32 use_syscall = strcmp(tk->tkr_mono.clock->name, "arch_sys_counter"); ++vdso_data->tb_seq_count; smp_wmb(); @@ -213,11 +213,11 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->wtm_clock_nsec = tk->wall_to_monotonic.tv_nsec; if (!use_syscall) { - vdso_data->cs_cycle_last = tk->tkr.cycle_last; + vdso_data->cs_cycle_last = tk->tkr_mono.cycle_last; vdso_data->xtime_clock_sec = tk->xtime_sec; - vdso_data->xtime_clock_nsec = tk->tkr.xtime_nsec; - vdso_data->cs_mult = tk->tkr.mult; - vdso_data->cs_shift = tk->tkr.shift; + vdso_data->xtime_clock_nsec = tk->tkr_mono.xtime_nsec; + vdso_data->cs_mult = tk->tkr_mono.mult; + vdso_data->cs_shift = tk->tkr_mono.shift; } smp_wmb(); diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 6c273cd815bb..170ddd2018b3 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -215,20 +215,20 @@ void update_vsyscall(struct timekeeper *tk) { u64 nsecps; - if (tk->tkr.clock != &clocksource_tod) + if (tk->tkr_mono.clock != &clocksource_tod) return; /* Make userspace gettimeofday spin until we're done. */ ++vdso_data->tb_update_count; smp_wmb(); - vdso_data->xtime_tod_stamp = tk->tkr.cycle_last; + vdso_data->xtime_tod_stamp = tk->tkr_mono.cycle_last; vdso_data->xtime_clock_sec = tk->xtime_sec; - vdso_data->xtime_clock_nsec = tk->tkr.xtime_nsec; + vdso_data->xtime_clock_nsec = tk->tkr_mono.xtime_nsec; vdso_data->wtom_clock_sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; - vdso_data->wtom_clock_nsec = tk->tkr.xtime_nsec + - + ((u64) tk->wall_to_monotonic.tv_nsec << tk->tkr.shift); - nsecps = (u64) NSEC_PER_SEC << tk->tkr.shift; + vdso_data->wtom_clock_nsec = tk->tkr_mono.xtime_nsec + + + ((u64) tk->wall_to_monotonic.tv_nsec << tk->tkr_mono.shift); + nsecps = (u64) NSEC_PER_SEC << tk->tkr_mono.shift; while (vdso_data->wtom_clock_nsec >= nsecps) { vdso_data->wtom_clock_nsec -= nsecps; vdso_data->wtom_clock_sec++; @@ -236,7 +236,7 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->xtime_coarse_sec = tk->xtime_sec; vdso_data->xtime_coarse_nsec = - (long)(tk->tkr.xtime_nsec >> tk->tkr.shift); + (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); vdso_data->wtom_coarse_sec = vdso_data->xtime_coarse_sec + tk->wall_to_monotonic.tv_sec; vdso_data->wtom_coarse_nsec = @@ -246,8 +246,8 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->wtom_coarse_sec++; } - vdso_data->tk_mult = tk->tkr.mult; - vdso_data->tk_shift = tk->tkr.shift; + vdso_data->tk_mult = tk->tkr_mono.mult; + vdso_data->tk_shift = tk->tkr_mono.shift; smp_wmb(); ++vdso_data->tb_update_count; } diff --git a/arch/tile/kernel/time.c b/arch/tile/kernel/time.c index d412b0856c0a..00178ecf9aea 100644 --- a/arch/tile/kernel/time.c +++ b/arch/tile/kernel/time.c @@ -257,34 +257,34 @@ void update_vsyscall_tz(void) void update_vsyscall(struct timekeeper *tk) { - if (tk->tkr.clock != &cycle_counter_cs) + if (tk->tkr_mono.clock != &cycle_counter_cs) return; write_seqcount_begin(&vdso_data->tb_seq); - vdso_data->cycle_last = tk->tkr.cycle_last; - vdso_data->mask = tk->tkr.mask; - vdso_data->mult = tk->tkr.mult; - vdso_data->shift = tk->tkr.shift; + vdso_data->cycle_last = tk->tkr_mono.cycle_last; + vdso_data->mask = tk->tkr_mono.mask; + vdso_data->mult = tk->tkr_mono.mult; + vdso_data->shift = tk->tkr_mono.shift; vdso_data->wall_time_sec = tk->xtime_sec; - vdso_data->wall_time_snsec = tk->tkr.xtime_nsec; + vdso_data->wall_time_snsec = tk->tkr_mono.xtime_nsec; vdso_data->monotonic_time_sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; - vdso_data->monotonic_time_snsec = tk->tkr.xtime_nsec + vdso_data->monotonic_time_snsec = tk->tkr_mono.xtime_nsec + ((u64)tk->wall_to_monotonic.tv_nsec - << tk->tkr.shift); + << tk->tkr_mono.shift); while (vdso_data->monotonic_time_snsec >= - (((u64)NSEC_PER_SEC) << tk->tkr.shift)) { + (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) { vdso_data->monotonic_time_snsec -= - ((u64)NSEC_PER_SEC) << tk->tkr.shift; + ((u64)NSEC_PER_SEC) << tk->tkr_mono.shift; vdso_data->monotonic_time_sec++; } vdso_data->wall_time_coarse_sec = tk->xtime_sec; - vdso_data->wall_time_coarse_nsec = (long)(tk->tkr.xtime_nsec >> - tk->tkr.shift); + vdso_data->wall_time_coarse_nsec = (long)(tk->tkr_mono.xtime_nsec >> + tk->tkr_mono.shift); vdso_data->monotonic_time_coarse_sec = vdso_data->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec; diff --git a/arch/x86/kernel/vsyscall_gtod.c b/arch/x86/kernel/vsyscall_gtod.c index c7d791f32b98..51e330416995 100644 --- a/arch/x86/kernel/vsyscall_gtod.c +++ b/arch/x86/kernel/vsyscall_gtod.c @@ -31,30 +31,30 @@ void update_vsyscall(struct timekeeper *tk) gtod_write_begin(vdata); /* copy vsyscall data */ - vdata->vclock_mode = tk->tkr.clock->archdata.vclock_mode; - vdata->cycle_last = tk->tkr.cycle_last; - vdata->mask = tk->tkr.mask; - vdata->mult = tk->tkr.mult; - vdata->shift = tk->tkr.shift; + vdata->vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode; + vdata->cycle_last = tk->tkr_mono.cycle_last; + vdata->mask = tk->tkr_mono.mask; + vdata->mult = tk->tkr_mono.mult; + vdata->shift = tk->tkr_mono.shift; vdata->wall_time_sec = tk->xtime_sec; - vdata->wall_time_snsec = tk->tkr.xtime_nsec; + vdata->wall_time_snsec = tk->tkr_mono.xtime_nsec; vdata->monotonic_time_sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; - vdata->monotonic_time_snsec = tk->tkr.xtime_nsec + vdata->monotonic_time_snsec = tk->tkr_mono.xtime_nsec + ((u64)tk->wall_to_monotonic.tv_nsec - << tk->tkr.shift); + << tk->tkr_mono.shift); while (vdata->monotonic_time_snsec >= - (((u64)NSEC_PER_SEC) << tk->tkr.shift)) { + (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) { vdata->monotonic_time_snsec -= - ((u64)NSEC_PER_SEC) << tk->tkr.shift; + ((u64)NSEC_PER_SEC) << tk->tkr_mono.shift; vdata->monotonic_time_sec++; } vdata->wall_time_coarse_sec = tk->xtime_sec; - vdata->wall_time_coarse_nsec = (long)(tk->tkr.xtime_nsec >> - tk->tkr.shift); + vdata->wall_time_coarse_nsec = (long)(tk->tkr_mono.xtime_nsec >> + tk->tkr_mono.shift); vdata->monotonic_time_coarse_sec = vdata->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index bd7a70be41b3..d7a300e0147f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1070,19 +1070,19 @@ static void update_pvclock_gtod(struct timekeeper *tk) struct pvclock_gtod_data *vdata = &pvclock_gtod_data; u64 boot_ns; - boot_ns = ktime_to_ns(ktime_add(tk->tkr.base_mono, tk->offs_boot)); + boot_ns = ktime_to_ns(ktime_add(tk->tkr_mono.base, tk->offs_boot)); write_seqcount_begin(&vdata->seq); /* copy pvclock gtod data */ - vdata->clock.vclock_mode = tk->tkr.clock->archdata.vclock_mode; - vdata->clock.cycle_last = tk->tkr.cycle_last; - vdata->clock.mask = tk->tkr.mask; - vdata->clock.mult = tk->tkr.mult; - vdata->clock.shift = tk->tkr.shift; + vdata->clock.vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode; + vdata->clock.cycle_last = tk->tkr_mono.cycle_last; + vdata->clock.mask = tk->tkr_mono.mask; + vdata->clock.mult = tk->tkr_mono.mult; + vdata->clock.shift = tk->tkr_mono.shift; vdata->boot_ns = boot_ns; - vdata->nsec_base = tk->tkr.xtime_nsec; + vdata->nsec_base = tk->tkr_mono.xtime_nsec; write_seqcount_end(&vdata->seq); } diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 05af9a334893..73df17f1535f 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -16,16 +16,16 @@ * @read: Read function of @clock * @mask: Bitmask for two's complement subtraction of non 64bit clocks * @cycle_last: @clock cycle value at last update - * @mult: NTP adjusted multiplier for scaled math conversion + * @mult: (NTP adjusted) multiplier for scaled math conversion * @shift: Shift value for scaled math conversion * @xtime_nsec: Shifted (fractional) nano seconds offset for readout - * @base_mono: ktime_t (nanoseconds) base time for readout + * @base: ktime_t (nanoseconds) base time for readout * * This struct has size 56 byte on 64 bit. Together with a seqcount it * occupies a single 64byte cache line. * * The struct is separate from struct timekeeper as it is also used - * for a fast NMI safe accessor to clock monotonic. + * for a fast NMI safe accessors. */ struct tk_read_base { struct clocksource *clock; @@ -35,12 +35,12 @@ struct tk_read_base { u32 mult; u32 shift; u64 xtime_nsec; - ktime_t base_mono; + ktime_t base; }; /** * struct timekeeper - Structure holding internal timekeeping values. - * @tkr: The readout base structure + * @tkr_mono: The readout base structure for CLOCK_MONOTONIC * @xtime_sec: Current CLOCK_REALTIME time in seconds * @ktime_sec: Current CLOCK_MONOTONIC time in seconds * @wall_to_monotonic: CLOCK_REALTIME to CLOCK_MONOTONIC offset @@ -76,7 +76,7 @@ struct tk_read_base { * used instead. */ struct timekeeper { - struct tk_read_base tkr; + struct tk_read_base tkr_mono; u64 xtime_sec; unsigned long ktime_sec; struct timespec64 wall_to_monotonic; diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 892f6cbf1e67..1405091f3acb 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -68,8 +68,8 @@ bool __read_mostly persistent_clock_exist = false; static inline void tk_normalize_xtime(struct timekeeper *tk) { - while (tk->tkr.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr.shift)) { - tk->tkr.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr.shift; + while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) { + tk->tkr_mono.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec++; } } @@ -79,20 +79,20 @@ static inline struct timespec64 tk_xtime(struct timekeeper *tk) struct timespec64 ts; ts.tv_sec = tk->xtime_sec; - ts.tv_nsec = (long)(tk->tkr.xtime_nsec >> tk->tkr.shift); + ts.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); return ts; } static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec = ts->tv_sec; - tk->tkr.xtime_nsec = (u64)ts->tv_nsec << tk->tkr.shift; + tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift; } static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec += ts->tv_sec; - tk->tkr.xtime_nsec += (u64)ts->tv_nsec << tk->tkr.shift; + tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift; tk_normalize_xtime(tk); } @@ -136,8 +136,8 @@ static long timekeeping_last_warning; static void timekeeping_check_update(struct timekeeper *tk, cycle_t offset) { - cycle_t max_cycles = tk->tkr.clock->max_cycles; - const char *name = tk->tkr.clock->name; + cycle_t max_cycles = tk->tkr_mono.clock->max_cycles; + const char *name = tk->tkr_mono.clock->name; if (offset > max_cycles) { printk_deferred("WARNING: timekeeping: Cycle offset (%lld) is larger than allowed by the '%s' clock's max_cycles value (%lld): time overflow danger\n", @@ -246,11 +246,11 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) u64 tmp, ntpinterval; struct clocksource *old_clock; - old_clock = tk->tkr.clock; - tk->tkr.clock = clock; - tk->tkr.read = clock->read; - tk->tkr.mask = clock->mask; - tk->tkr.cycle_last = tk->tkr.read(clock); + old_clock = tk->tkr_mono.clock; + tk->tkr_mono.clock = clock; + tk->tkr_mono.read = clock->read; + tk->tkr_mono.mask = clock->mask; + tk->tkr_mono.cycle_last = tk->tkr_mono.read(clock); /* Do the ns -> cycle conversion first, using original mult */ tmp = NTP_INTERVAL_LENGTH; @@ -274,11 +274,11 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) if (old_clock) { int shift_change = clock->shift - old_clock->shift; if (shift_change < 0) - tk->tkr.xtime_nsec >>= -shift_change; + tk->tkr_mono.xtime_nsec >>= -shift_change; else - tk->tkr.xtime_nsec <<= shift_change; + tk->tkr_mono.xtime_nsec <<= shift_change; } - tk->tkr.shift = clock->shift; + tk->tkr_mono.shift = clock->shift; tk->ntp_error = 0; tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift; @@ -289,7 +289,7 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) * active clocksource. These value will be adjusted via NTP * to counteract clock drifting. */ - tk->tkr.mult = clock->mult; + tk->tkr_mono.mult = clock->mult; tk->ntp_err_mult = 0; } @@ -318,11 +318,11 @@ static inline s64 timekeeping_get_ns(struct tk_read_base *tkr) static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk) { - struct clocksource *clock = tk->tkr.clock; + struct clocksource *clock = tk->tkr_mono.clock; cycle_t delta; s64 nsec; - delta = timekeeping_get_delta(&tk->tkr); + delta = timekeeping_get_delta(&tk->tkr_mono); /* convert delta to nanoseconds. */ nsec = clocksource_cyc2ns(delta, clock->mult, clock->shift); @@ -428,7 +428,7 @@ u64 notrace ktime_get_mono_fast_ns(void) do { seq = raw_read_seqcount(&tk_fast_mono.seq); tkr = tk_fast_mono.base + (seq & 0x01); - now = ktime_to_ns(tkr->base_mono) + timekeeping_get_ns(tkr); + now = ktime_to_ns(tkr->base) + timekeeping_get_ns(tkr); } while (read_seqcount_retry(&tk_fast_mono.seq, seq)); return now; @@ -456,7 +456,7 @@ static cycle_t dummy_clock_read(struct clocksource *cs) static void halt_fast_timekeeper(struct timekeeper *tk) { static struct tk_read_base tkr_dummy; - struct tk_read_base *tkr = &tk->tkr; + struct tk_read_base *tkr = &tk->tkr_mono; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); cycles_at_suspend = tkr->read(tkr->clock); @@ -472,8 +472,8 @@ static inline void update_vsyscall(struct timekeeper *tk) xt = timespec64_to_timespec(tk_xtime(tk)); wm = timespec64_to_timespec(tk->wall_to_monotonic); - update_vsyscall_old(&xt, &wm, tk->tkr.clock, tk->tkr.mult, - tk->tkr.cycle_last); + update_vsyscall_old(&xt, &wm, tk->tkr_mono.clock, tk->tkr_mono.mult, + tk->tkr_mono.cycle_last); } static inline void old_vsyscall_fixup(struct timekeeper *tk) @@ -490,11 +490,11 @@ static inline void old_vsyscall_fixup(struct timekeeper *tk) * (shifted nanoseconds), and CONFIG_GENERIC_TIME_VSYSCALL_OLD * users are removed, this can be killed. */ - remainder = tk->tkr.xtime_nsec & ((1ULL << tk->tkr.shift) - 1); - tk->tkr.xtime_nsec -= remainder; - tk->tkr.xtime_nsec += 1ULL << tk->tkr.shift; + remainder = tk->tkr_mono.xtime_nsec & ((1ULL << tk->tkr_mono.shift) - 1); + tk->tkr_mono.xtime_nsec -= remainder; + tk->tkr_mono.xtime_nsec += 1ULL << tk->tkr_mono.shift; tk->ntp_error += remainder << tk->ntp_error_shift; - tk->ntp_error -= (1ULL << tk->tkr.shift) << tk->ntp_error_shift; + tk->ntp_error -= (1ULL << tk->tkr_mono.shift) << tk->ntp_error_shift; } #else #define old_vsyscall_fixup(tk) @@ -559,7 +559,7 @@ static inline void tk_update_ktime_data(struct timekeeper *tk) */ seconds = (u64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec); nsec = (u32) tk->wall_to_monotonic.tv_nsec; - tk->tkr.base_mono = ns_to_ktime(seconds * NSEC_PER_SEC + nsec); + tk->tkr_mono.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec); /* Update the monotonic raw base */ tk->base_raw = timespec64_to_ktime(tk->raw_time); @@ -569,7 +569,7 @@ static inline void tk_update_ktime_data(struct timekeeper *tk) * wall_to_monotonic can be greater/equal one second. Take * this into account before updating tk->ktime_sec. */ - nsec += (u32)(tk->tkr.xtime_nsec >> tk->tkr.shift); + nsec += (u32)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); if (nsec >= NSEC_PER_SEC) seconds++; tk->ktime_sec = seconds; @@ -592,7 +592,7 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) memcpy(&shadow_timekeeper, &tk_core.timekeeper, sizeof(tk_core.timekeeper)); - update_fast_timekeeper(&tk->tkr); + update_fast_timekeeper(&tk->tkr_mono); } /** @@ -604,18 +604,18 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) */ static void timekeeping_forward_now(struct timekeeper *tk) { - struct clocksource *clock = tk->tkr.clock; + struct clocksource *clock = tk->tkr_mono.clock; cycle_t cycle_now, delta; s64 nsec; - cycle_now = tk->tkr.read(clock); - delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, tk->tkr.mask); - tk->tkr.cycle_last = cycle_now; + cycle_now = tk->tkr_mono.read(clock); + delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask); + tk->tkr_mono.cycle_last = cycle_now; - tk->tkr.xtime_nsec += delta * tk->tkr.mult; + tk->tkr_mono.xtime_nsec += delta * tk->tkr_mono.mult; /* If arch requires, add in get_arch_timeoffset() */ - tk->tkr.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr.shift; + tk->tkr_mono.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr_mono.shift; tk_normalize_xtime(tk); @@ -640,7 +640,7 @@ int __getnstimeofday64(struct timespec64 *ts) seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; - nsecs = timekeeping_get_ns(&tk->tkr); + nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -680,8 +680,8 @@ ktime_t ktime_get(void) do { seq = read_seqcount_begin(&tk_core.seq); - base = tk->tkr.base_mono; - nsecs = timekeeping_get_ns(&tk->tkr); + base = tk->tkr_mono.base; + nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -706,8 +706,8 @@ ktime_t ktime_get_with_offset(enum tk_offsets offs) do { seq = read_seqcount_begin(&tk_core.seq); - base = ktime_add(tk->tkr.base_mono, *offset); - nsecs = timekeeping_get_ns(&tk->tkr); + base = ktime_add(tk->tkr_mono.base, *offset); + nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -777,7 +777,7 @@ void ktime_get_ts64(struct timespec64 *ts) do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; - nsec = timekeeping_get_ns(&tk->tkr); + nsec = timekeeping_get_ns(&tk->tkr_mono); tomono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -863,7 +863,7 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real) ts_real->tv_nsec = 0; nsecs_raw = timekeeping_get_ns_raw(tk); - nsecs_real = timekeeping_get_ns(&tk->tkr); + nsecs_real = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -1046,7 +1046,7 @@ static int change_clocksource(void *data) */ if (try_module_get(new->owner)) { if (!new->enable || new->enable(new) == 0) { - old = tk->tkr.clock; + old = tk->tkr_mono.clock; tk_setup_internals(tk, new); if (old->disable) old->disable(old); @@ -1074,11 +1074,11 @@ int timekeeping_notify(struct clocksource *clock) { struct timekeeper *tk = &tk_core.timekeeper; - if (tk->tkr.clock == clock) + if (tk->tkr_mono.clock == clock) return 0; stop_machine(change_clocksource, clock, NULL); tick_clock_notify(); - return tk->tkr.clock == clock ? 0 : -1; + return tk->tkr_mono.clock == clock ? 0 : -1; } /** @@ -1119,7 +1119,7 @@ int timekeeping_valid_for_hres(void) do { seq = read_seqcount_begin(&tk_core.seq); - ret = tk->tkr.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; + ret = tk->tkr_mono.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -1138,7 +1138,7 @@ u64 timekeeping_max_deferment(void) do { seq = read_seqcount_begin(&tk_core.seq); - ret = tk->tkr.clock->max_idle_ns; + ret = tk->tkr_mono.clock->max_idle_ns; } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -1303,7 +1303,7 @@ void timekeeping_inject_sleeptime64(struct timespec64 *delta) void timekeeping_resume(void) { struct timekeeper *tk = &tk_core.timekeeper; - struct clocksource *clock = tk->tkr.clock; + struct clocksource *clock = tk->tkr_mono.clock; unsigned long flags; struct timespec64 ts_new, ts_delta; struct timespec tmp; @@ -1331,16 +1331,16 @@ void timekeeping_resume(void) * The less preferred source will only be tried if there is no better * usable source. The rtc part is handled separately in rtc core code. */ - cycle_now = tk->tkr.read(clock); + cycle_now = tk->tkr_mono.read(clock); if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) && - cycle_now > tk->tkr.cycle_last) { + cycle_now > tk->tkr_mono.cycle_last) { u64 num, max = ULLONG_MAX; u32 mult = clock->mult; u32 shift = clock->shift; s64 nsec = 0; - cycle_delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, - tk->tkr.mask); + cycle_delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, + tk->tkr_mono.mask); /* * "cycle_delta * mutl" may cause 64 bits overflow, if the @@ -1366,7 +1366,7 @@ void timekeeping_resume(void) __timekeeping_inject_sleeptime(tk, &ts_delta); /* Re-base the last cycle value */ - tk->tkr.cycle_last = cycle_now; + tk->tkr_mono.cycle_last = cycle_now; tk->ntp_error = 0; timekeeping_suspended = 0; timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); @@ -1519,15 +1519,15 @@ static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk, * * XXX - TODO: Doc ntp_error calculation. */ - if ((mult_adj > 0) && (tk->tkr.mult + mult_adj < mult_adj)) { + if ((mult_adj > 0) && (tk->tkr_mono.mult + mult_adj < mult_adj)) { /* NTP adjustment caused clocksource mult overflow */ WARN_ON_ONCE(1); return; } - tk->tkr.mult += mult_adj; + tk->tkr_mono.mult += mult_adj; tk->xtime_interval += interval; - tk->tkr.xtime_nsec -= offset; + tk->tkr_mono.xtime_nsec -= offset; tk->ntp_error -= (interval - offset) << tk->ntp_error_shift; } @@ -1589,13 +1589,13 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) tk->ntp_err_mult = 0; } - if (unlikely(tk->tkr.clock->maxadj && - (abs(tk->tkr.mult - tk->tkr.clock->mult) - > tk->tkr.clock->maxadj))) { + if (unlikely(tk->tkr_mono.clock->maxadj && + (abs(tk->tkr_mono.mult - tk->tkr_mono.clock->mult) + > tk->tkr_mono.clock->maxadj))) { printk_once(KERN_WARNING "Adjusting %s more than 11%% (%ld vs %ld)\n", - tk->tkr.clock->name, (long)tk->tkr.mult, - (long)tk->tkr.clock->mult + tk->tkr.clock->maxadj); + tk->tkr_mono.clock->name, (long)tk->tkr_mono.mult, + (long)tk->tkr_mono.clock->mult + tk->tkr_mono.clock->maxadj); } /* @@ -1612,9 +1612,9 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) * We'll correct this error next time through this function, when * xtime_nsec is not as small. */ - if (unlikely((s64)tk->tkr.xtime_nsec < 0)) { - s64 neg = -(s64)tk->tkr.xtime_nsec; - tk->tkr.xtime_nsec = 0; + if (unlikely((s64)tk->tkr_mono.xtime_nsec < 0)) { + s64 neg = -(s64)tk->tkr_mono.xtime_nsec; + tk->tkr_mono.xtime_nsec = 0; tk->ntp_error += neg << tk->ntp_error_shift; } } @@ -1629,13 +1629,13 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) */ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk) { - u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr.shift; + u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr_mono.shift; unsigned int clock_set = 0; - while (tk->tkr.xtime_nsec >= nsecps) { + while (tk->tkr_mono.xtime_nsec >= nsecps) { int leap; - tk->tkr.xtime_nsec -= nsecps; + tk->tkr_mono.xtime_nsec -= nsecps; tk->xtime_sec++; /* Figure out if its a leap sec and apply if needed */ @@ -1680,9 +1680,9 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset, /* Accumulate one shifted interval */ offset -= interval; - tk->tkr.cycle_last += interval; + tk->tkr_mono.cycle_last += interval; - tk->tkr.xtime_nsec += tk->xtime_interval << shift; + tk->tkr_mono.xtime_nsec += tk->xtime_interval << shift; *clock_set |= accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ @@ -1725,8 +1725,8 @@ void update_wall_time(void) #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET offset = real_tk->cycle_interval; #else - offset = clocksource_delta(tk->tkr.read(tk->tkr.clock), - tk->tkr.cycle_last, tk->tkr.mask); + offset = clocksource_delta(tk->tkr_mono.read(tk->tkr_mono.clock), + tk->tkr_mono.cycle_last, tk->tkr_mono.mask); #endif /* Check if there's really nothing to do */ @@ -1890,8 +1890,8 @@ ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, ktime_t *offs_boot, do { seq = read_seqcount_begin(&tk_core.seq); - base = tk->tkr.base_mono; - nsecs = tk->tkr.xtime_nsec >> tk->tkr.shift; + base = tk->tkr_mono.base; + nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; *offs_real = tk->offs_real; *offs_boot = tk->offs_boot; @@ -1922,8 +1922,8 @@ ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, ktime_t *offs_boot, do { seq = read_seqcount_begin(&tk_core.seq); - base = tk->tkr.base_mono; - nsecs = timekeeping_get_ns(&tk->tkr); + base = tk->tkr_mono.base; + nsecs = timekeeping_get_ns(&tk->tkr_mono); *offs_real = tk->offs_real; *offs_boot = tk->offs_boot; -- cgit v1.2.3 From 4a4ad80d32cea69ee93bd4589f24dc478804cd80 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 19 Mar 2015 09:28:44 +0100 Subject: time: Add timerkeeper::tkr_raw Introduce tkr_raw and make use of it. base_raw -> tkr_raw.base clock->{mult,shift} -> tkr_raw.{mult.shift} Kill timekeeping_get_ns_raw() in favour of timekeeping_get_ns(&tkr_raw), this removes all mono_raw special casing. Duplicate the updates to tkr_mono.cycle_last into tkr_raw.cycle_last, both need the same value. Signed-off-by: Peter Zijlstra (Intel) Acked-by: John Stultz Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20150319093400.422589590@infradead.org Signed-off-by: Ingo Molnar --- include/linux/timekeeper_internal.h | 4 ++-- kernel/time/timekeeping.c | 41 +++++++++++++++++-------------------- 2 files changed, 21 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 73df17f1535f..fb86963859c7 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -41,6 +41,7 @@ struct tk_read_base { /** * struct timekeeper - Structure holding internal timekeeping values. * @tkr_mono: The readout base structure for CLOCK_MONOTONIC + * @tkr_raw: The readout base structure for CLOCK_MONOTONIC_RAW * @xtime_sec: Current CLOCK_REALTIME time in seconds * @ktime_sec: Current CLOCK_MONOTONIC time in seconds * @wall_to_monotonic: CLOCK_REALTIME to CLOCK_MONOTONIC offset @@ -48,7 +49,6 @@ struct tk_read_base { * @offs_boot: Offset clock monotonic -> clock boottime * @offs_tai: Offset clock monotonic -> clock tai * @tai_offset: The current UTC to TAI offset in seconds - * @base_raw: Monotonic raw base time in ktime_t format * @raw_time: Monotonic raw base time in timespec64 format * @cycle_interval: Number of clock cycles in one NTP interval * @xtime_interval: Number of clock shifted nano seconds in one NTP @@ -77,6 +77,7 @@ struct tk_read_base { */ struct timekeeper { struct tk_read_base tkr_mono; + struct tk_read_base tkr_raw; u64 xtime_sec; unsigned long ktime_sec; struct timespec64 wall_to_monotonic; @@ -84,7 +85,6 @@ struct timekeeper { ktime_t offs_boot; ktime_t offs_tai; s32 tai_offset; - ktime_t base_raw; struct timespec64 raw_time; /* The following members are for timekeeping internal use */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 1405091f3acb..cbb612ee813f 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -252,6 +252,11 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) tk->tkr_mono.mask = clock->mask; tk->tkr_mono.cycle_last = tk->tkr_mono.read(clock); + tk->tkr_raw.clock = clock; + tk->tkr_raw.read = clock->read; + tk->tkr_raw.mask = clock->mask; + tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last; + /* Do the ns -> cycle conversion first, using original mult */ tmp = NTP_INTERVAL_LENGTH; tmp <<= clock->shift; @@ -278,7 +283,10 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) else tk->tkr_mono.xtime_nsec <<= shift_change; } + tk->tkr_raw.xtime_nsec = 0; + tk->tkr_mono.shift = clock->shift; + tk->tkr_raw.shift = clock->shift; tk->ntp_error = 0; tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift; @@ -290,6 +298,7 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) * to counteract clock drifting. */ tk->tkr_mono.mult = clock->mult; + tk->tkr_raw.mult = clock->mult; tk->ntp_err_mult = 0; } @@ -316,21 +325,6 @@ static inline s64 timekeeping_get_ns(struct tk_read_base *tkr) return nsec + arch_gettimeoffset(); } -static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk) -{ - struct clocksource *clock = tk->tkr_mono.clock; - cycle_t delta; - s64 nsec; - - delta = timekeeping_get_delta(&tk->tkr_mono); - - /* convert delta to nanoseconds. */ - nsec = clocksource_cyc2ns(delta, clock->mult, clock->shift); - - /* If arch requires, add in get_arch_timeoffset() */ - return nsec + arch_gettimeoffset(); -} - /** * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper. * @tkr: Timekeeping readout base from which we take the update @@ -562,7 +556,7 @@ static inline void tk_update_ktime_data(struct timekeeper *tk) tk->tkr_mono.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec); /* Update the monotonic raw base */ - tk->base_raw = timespec64_to_ktime(tk->raw_time); + tk->tkr_raw.base = timespec64_to_ktime(tk->raw_time); /* * The sum of the nanoseconds portions of xtime and @@ -611,6 +605,7 @@ static void timekeeping_forward_now(struct timekeeper *tk) cycle_now = tk->tkr_mono.read(clock); delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask); tk->tkr_mono.cycle_last = cycle_now; + tk->tkr_raw.cycle_last = cycle_now; tk->tkr_mono.xtime_nsec += delta * tk->tkr_mono.mult; @@ -619,7 +614,7 @@ static void timekeeping_forward_now(struct timekeeper *tk) tk_normalize_xtime(tk); - nsec = clocksource_cyc2ns(delta, clock->mult, clock->shift); + nsec = clocksource_cyc2ns(delta, tk->tkr_raw.mult, tk->tkr_raw.shift); timespec64_add_ns(&tk->raw_time, nsec); } @@ -748,8 +743,8 @@ ktime_t ktime_get_raw(void) do { seq = read_seqcount_begin(&tk_core.seq); - base = tk->base_raw; - nsecs = timekeeping_get_ns_raw(tk); + base = tk->tkr_raw.base; + nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -862,7 +857,7 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real) ts_real->tv_sec = tk->xtime_sec; ts_real->tv_nsec = 0; - nsecs_raw = timekeeping_get_ns_raw(tk); + nsecs_raw = timekeeping_get_ns(&tk->tkr_raw); nsecs_real = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -1096,7 +1091,7 @@ void getrawmonotonic64(struct timespec64 *ts) do { seq = read_seqcount_begin(&tk_core.seq); - nsecs = timekeeping_get_ns_raw(tk); + nsecs = timekeeping_get_ns(&tk->tkr_raw); ts64 = tk->raw_time; } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -1217,7 +1212,6 @@ void __init timekeeping_init(void) tk_set_xtime(tk, &now); tk->raw_time.tv_sec = 0; tk->raw_time.tv_nsec = 0; - tk->base_raw.tv64 = 0; if (boot.tv_sec == 0 && boot.tv_nsec == 0) boot = tk_xtime(tk); @@ -1367,6 +1361,8 @@ void timekeeping_resume(void) /* Re-base the last cycle value */ tk->tkr_mono.cycle_last = cycle_now; + tk->tkr_raw.cycle_last = cycle_now; + tk->ntp_error = 0; timekeeping_suspended = 0; timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); @@ -1681,6 +1677,7 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset, /* Accumulate one shifted interval */ offset -= interval; tk->tkr_mono.cycle_last += interval; + tk->tkr_raw.cycle_last += interval; tk->tkr_mono.xtime_nsec += tk->xtime_interval << shift; *clock_set |= accumulate_nsecs_to_secs(tk); -- cgit v1.2.3 From f09cb9a1808e35ad7502ea39b6bfb443c7fa0f19 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 19 Mar 2015 09:39:08 +0100 Subject: time: Introduce tk_fast_raw Add the NMI safe CLOCK_MONOTONIC_RAW accessor.. Signed-off-by: Peter Zijlstra (Intel) Acked-by: John Stultz Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20150319093400.562746929@infradead.org Signed-off-by: Ingo Molnar --- include/linux/timekeeping.h | 1 + kernel/time/timekeeping.c | 13 +++++++++++++ 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 3eaae4754275..f36b1edf3f73 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -220,6 +220,7 @@ static inline u64 ktime_get_raw_ns(void) } extern u64 ktime_get_mono_fast_ns(void); +extern u64 ktime_get_raw_fast_ns(void); /* * Timespec interfaces utilizing the ktime based ones diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 278373edb472..c3fcff06d30a 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -59,6 +59,7 @@ struct tk_fast { }; static struct tk_fast tk_fast_mono ____cacheline_aligned; +static struct tk_fast tk_fast_raw ____cacheline_aligned; /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; @@ -434,6 +435,12 @@ u64 ktime_get_mono_fast_ns(void) } EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns); +u64 ktime_get_raw_fast_ns(void) +{ + return __ktime_get_fast_ns(&tk_fast_raw); +} +EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns); + /* Suspend-time cycles value for halted fast timekeeper. */ static cycle_t cycles_at_suspend; @@ -461,6 +468,11 @@ static void halt_fast_timekeeper(struct timekeeper *tk) cycles_at_suspend = tkr->read(tkr->clock); tkr_dummy.read = dummy_clock_read; update_fast_timekeeper(&tkr_dummy, &tk_fast_mono); + + tkr = &tk->tkr_raw; + memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); + tkr_dummy.read = dummy_clock_read; + update_fast_timekeeper(&tkr_dummy, &tk_fast_raw); } #ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD @@ -592,6 +604,7 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) sizeof(tk_core.timekeeper)); update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono); + update_fast_timekeeper(&tk->tkr_raw, &tk_fast_raw); } /** -- cgit v1.2.3 From fe5fba05b46c791c95a9f34228ac495f81f72fc0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 17 Mar 2015 12:39:10 +0100 Subject: time: Add ktime_get_tai_ns() Because it was the only clock for which we didn't have a _ns() accessor yet. Signed-off-by: Peter Zijlstra (Intel) Cc: John Stultz Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/timekeeping.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index f36b1edf3f73..5047b83483d6 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -214,6 +214,11 @@ static inline u64 ktime_get_boot_ns(void) return ktime_to_ns(ktime_get_boottime()); } +static inline u64 ktime_get_tai_ns(void) +{ + return ktime_to_ns(ktime_get_clocktai()); +} + static inline u64 ktime_get_raw_ns(void) { return ktime_to_ns(ktime_get_raw()); -- cgit v1.2.3 From 554ef3876c6acdff1331feab10275e9e9e0adb84 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Fri, 27 Feb 2015 17:21:32 +0530 Subject: clockevents: Handle tick device's resume separately Upcoming patch will redefine possible states of a clockevent device. The RESUME mode is a special case only for tick's clockevent devices. In future it can be replaced by ->resume() callback already available for clockevent devices. Lets handle it separately so that clockevents_set_mode() only handles states valid across all devices. This also renames set_mode_resume() to tick_resume() to make it more explicit. Signed-off-by: Viresh Kumar Acked-by: Peter Zijlstra Cc: Daniel Lezcano Cc: Frederic Weisbecker Cc: Kevin Hilman Cc: Peter Zijlstra Cc: Preeti U Murthy Cc: linaro-kernel@lists.linaro.org Cc: linaro-networking@linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/c1b0112410870f49e7bf06958e1483eac6c15e20.1425037853.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar --- include/linux/clockchips.h | 4 ++-- kernel/time/clockevents.c | 30 +++++++++++++++++++++--------- kernel/time/tick-broadcast.c | 2 +- kernel/time/tick-common.c | 2 +- kernel/time/tick-internal.h | 1 + kernel/time/timer_list.c | 4 ++-- 6 files changed, 28 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 59af26b54d15..a41749543d48 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -87,7 +87,7 @@ enum clock_event_mode { * @set_mode_periodic: switch mode to periodic, if !set_mode * @set_mode_oneshot: switch mode to oneshot, if !set_mode * @set_mode_shutdown: switch mode to shutdown, if !set_mode - * @set_mode_resume: resume clkevt device, if !set_mode + * @tick_resume: resume clkevt device, if !set_mode * @broadcast: function to broadcast events * @min_delta_ticks: minimum delta value in ticks stored for reconfiguration * @max_delta_ticks: maximum delta value in ticks stored for reconfiguration @@ -125,7 +125,7 @@ struct clock_event_device { int (*set_mode_periodic)(struct clock_event_device *); int (*set_mode_oneshot)(struct clock_event_device *); int (*set_mode_shutdown)(struct clock_event_device *); - int (*set_mode_resume)(struct clock_event_device *); + int (*tick_resume)(struct clock_event_device *); void (*broadcast)(const struct cpumask *mask); void (*suspend)(struct clock_event_device *); diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 489642b08d64..1b0ea63de69c 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -100,7 +100,7 @@ static int __clockevents_set_mode(struct clock_event_device *dev, /* Transition with legacy set_mode() callback */ if (dev->set_mode) { /* Legacy callback doesn't support new modes */ - if (mode > CLOCK_EVT_MODE_RESUME) + if (mode > CLOCK_EVT_MODE_ONESHOT) return -ENOSYS; dev->set_mode(mode, dev); return 0; @@ -133,13 +133,6 @@ static int __clockevents_set_mode(struct clock_event_device *dev, return -ENOSYS; return dev->set_mode_oneshot(dev); - case CLOCK_EVT_MODE_RESUME: - /* Optional callback */ - if (dev->set_mode_resume) - return dev->set_mode_resume(dev); - else - return 0; - default: return -ENOSYS; } @@ -184,6 +177,25 @@ void clockevents_shutdown(struct clock_event_device *dev) dev->next_event.tv64 = KTIME_MAX; } +/** + * clockevents_tick_resume - Resume the tick device before using it again + * @dev: device to resume + */ +int clockevents_tick_resume(struct clock_event_device *dev) +{ + int ret = 0; + + if (dev->set_mode) + dev->set_mode(CLOCK_EVT_MODE_RESUME, dev); + else if (dev->tick_resume) + ret = dev->tick_resume(dev); + + if (likely(!ret)) + dev->mode = CLOCK_EVT_MODE_RESUME; + + return ret; +} + #ifdef CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST /* Limit min_delta to a jiffie */ @@ -433,7 +445,7 @@ static int clockevents_sanity_check(struct clock_event_device *dev) if (dev->set_mode) { /* We shouldn't be supporting new modes now */ WARN_ON(dev->set_mode_periodic || dev->set_mode_oneshot || - dev->set_mode_shutdown || dev->set_mode_resume); + dev->set_mode_shutdown || dev->tick_resume); return 0; } diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 066f0ec05e48..542d5bb5c13d 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -464,7 +464,7 @@ int tick_resume_broadcast(void) bc = tick_broadcast_device.evtdev; if (bc) { - clockevents_set_mode(bc, CLOCK_EVT_MODE_RESUME); + clockevents_tick_resume(bc); switch (tick_broadcast_device.mode) { case TICKDEV_MODE_PERIODIC: diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index f7c515595b42..5c50664c21d7 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -384,7 +384,7 @@ void tick_resume(void) struct tick_device *td = this_cpu_ptr(&tick_cpu_device); int broadcast = tick_resume_broadcast(); - clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_RESUME); + clockevents_tick_resume(td->evtdev); if (!broadcast) { if (td->mode == TICKDEV_MODE_PERIODIC) diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 366aeb4f2c66..98700e4a2000 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -32,6 +32,7 @@ extern bool tick_check_replacement(struct clock_event_device *curdev, extern void tick_install_replacement(struct clock_event_device *dev); extern void clockevents_shutdown(struct clock_event_device *dev); +extern int clockevents_tick_resume(struct clock_event_device *dev); extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt); diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index 2cfd19485824..2b3e9393034d 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -251,9 +251,9 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu) SEQ_printf(m, "\n"); } - if (dev->set_mode_resume) { + if (dev->tick_resume) { SEQ_printf(m, " resume: "); - print_name_offset(m, dev->set_mode_resume); + print_name_offset(m, dev->tick_resume); SEQ_printf(m, "\n"); } } -- cgit v1.2.3 From 77e32c89a7117614ab3d66d20c1088de721abfaa Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Fri, 27 Feb 2015 17:21:33 +0530 Subject: clockevents: Manage device's state separately for the core 'enum clock_event_mode' is used for two purposes today: - to pass mode to the driver of clockevent device::set_mode(). - for managing state of the device for clockevents core. For supporting new modes/states we have moved away from the legacy set_mode() callback to new per-mode/state callbacks. New modes/states shouldn't be exposed to the legacy (now OBSOLOTE) callbacks and so we shouldn't add new states to 'enum clock_event_mode'. Lets have separate enums for the two use cases mentioned above. Keep using the earlier enum for legacy set_mode() callback and mark it OBSOLETE. And add another enum to clearly specify the possible states of a clockevent device. This also renames the newly added per-mode callbacks to reflect state changes. We haven't got rid of 'mode' member of 'struct clock_event_device' as it is used by some of the clockevent drivers and it would automatically die down once we migrate those drivers to the new interface. It ('mode') is only updated now for the drivers using the legacy interface. Suggested-by: Peter Zijlstra Suggested-by: Ingo Molnar Signed-off-by: Viresh Kumar Acked-by: Peter Zijlstra Cc: Daniel Lezcano Cc: Frederic Weisbecker Cc: Kevin Hilman Cc: Preeti U Murthy Cc: linaro-kernel@lists.linaro.org Cc: linaro-networking@linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/b6b0143a8a57bd58352ad35e08c25424c879c0cb.1425037853.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar --- arch/arm/common/bL_switcher.c | 8 ++-- include/linux/clockchips.h | 44 +++++++++++++------ kernel/time/clockevents.c | 99 +++++++++++++++++++++++-------------------- kernel/time/tick-broadcast.c | 20 ++++----- kernel/time/tick-common.c | 7 +-- kernel/time/tick-oneshot.c | 6 +-- kernel/time/timer_list.c | 12 +++--- 7 files changed, 111 insertions(+), 85 deletions(-) (limited to 'include') diff --git a/arch/arm/common/bL_switcher.c b/arch/arm/common/bL_switcher.c index 6eaddc47c43d..d4f970a4d255 100644 --- a/arch/arm/common/bL_switcher.c +++ b/arch/arm/common/bL_switcher.c @@ -152,7 +152,7 @@ static int bL_switch_to(unsigned int new_cluster_id) unsigned int ob_mpidr, ob_cpu, ob_cluster, ib_mpidr, ib_cpu, ib_cluster; struct completion inbound_alive; struct tick_device *tdev; - enum clock_event_mode tdev_mode; + enum clock_event_state tdev_state; long volatile *handshake_ptr; int ipi_nr, ret; @@ -223,8 +223,8 @@ static int bL_switch_to(unsigned int new_cluster_id) if (tdev && !cpumask_equal(tdev->evtdev->cpumask, cpumask_of(this_cpu))) tdev = NULL; if (tdev) { - tdev_mode = tdev->evtdev->mode; - clockevents_set_mode(tdev->evtdev, CLOCK_EVT_MODE_SHUTDOWN); + tdev_state = tdev->evtdev->state; + clockevents_set_state(tdev->evtdev, CLOCK_EVT_STATE_SHUTDOWN); } ret = cpu_pm_enter(); @@ -252,7 +252,7 @@ static int bL_switch_to(unsigned int new_cluster_id) ret = cpu_pm_exit(); if (tdev) { - clockevents_set_mode(tdev->evtdev, tdev_mode); + clockevents_set_state(tdev->evtdev, tdev_state); clockevents_program_event(tdev->evtdev, tdev->evtdev->next_event, 1); } diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index a41749543d48..e20232c3320a 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -32,15 +32,31 @@ enum clock_event_nofitiers { struct clock_event_device; struct module; -/* Clock event mode commands */ +/* Clock event mode commands for legacy ->set_mode(): OBSOLETE */ enum clock_event_mode { CLOCK_EVT_MODE_UNUSED = 0, CLOCK_EVT_MODE_SHUTDOWN, CLOCK_EVT_MODE_PERIODIC, CLOCK_EVT_MODE_ONESHOT, CLOCK_EVT_MODE_RESUME, +}; - /* Legacy ->set_mode() callback doesn't support below modes */ +/* + * Possible states of a clock event device. + * + * DETACHED: Device is not used by clockevents core. Initial state or can be + * reached from SHUTDOWN. + * SHUTDOWN: Device is powered-off. Can be reached from PERIODIC or ONESHOT. + * PERIODIC: Device is programmed to generate events periodically. Can be + * reached from DETACHED or SHUTDOWN. + * ONESHOT: Device is programmed to generate event only once. Can be reached + * from DETACHED or SHUTDOWN. + */ +enum clock_event_state { + CLOCK_EVT_STATE_DETACHED = 0, + CLOCK_EVT_STATE_SHUTDOWN, + CLOCK_EVT_STATE_PERIODIC, + CLOCK_EVT_STATE_ONESHOT, }; /* @@ -80,13 +96,14 @@ enum clock_event_mode { * @min_delta_ns: minimum delta value in ns * @mult: nanosecond to cycles multiplier * @shift: nanoseconds to cycles divisor (power of two) - * @mode: operating mode assigned by the management code + * @mode: operating mode, relevant only to ->set_mode(), OBSOLETE + * @state: current state of the device, assigned by the core code * @features: features * @retries: number of forced programming retries * @set_mode: legacy set mode function, only for modes <= CLOCK_EVT_MODE_RESUME. - * @set_mode_periodic: switch mode to periodic, if !set_mode - * @set_mode_oneshot: switch mode to oneshot, if !set_mode - * @set_mode_shutdown: switch mode to shutdown, if !set_mode + * @set_state_periodic: switch state to periodic, if !set_mode + * @set_state_oneshot: switch state to oneshot, if !set_mode + * @set_state_shutdown: switch state to shutdown, if !set_mode * @tick_resume: resume clkevt device, if !set_mode * @broadcast: function to broadcast events * @min_delta_ticks: minimum delta value in ticks stored for reconfiguration @@ -111,20 +128,21 @@ struct clock_event_device { u32 mult; u32 shift; enum clock_event_mode mode; + enum clock_event_state state; unsigned int features; unsigned long retries; /* - * Mode transition callback(s): Only one of the two groups should be + * State transition callback(s): Only one of the two groups should be * defined: * - set_mode(), only for modes <= CLOCK_EVT_MODE_RESUME. - * - set_mode_{shutdown|periodic|oneshot|resume}(). + * - set_state_{shutdown|periodic|oneshot}(), tick_resume(). */ void (*set_mode)(enum clock_event_mode mode, struct clock_event_device *); - int (*set_mode_periodic)(struct clock_event_device *); - int (*set_mode_oneshot)(struct clock_event_device *); - int (*set_mode_shutdown)(struct clock_event_device *); + int (*set_state_periodic)(struct clock_event_device *); + int (*set_state_oneshot)(struct clock_event_device *); + int (*set_state_shutdown)(struct clock_event_device *); int (*tick_resume)(struct clock_event_device *); void (*broadcast)(const struct cpumask *mask); @@ -177,8 +195,8 @@ extern int clockevents_update_freq(struct clock_event_device *ce, u32 freq); extern void clockevents_exchange_device(struct clock_event_device *old, struct clock_event_device *new); -extern void clockevents_set_mode(struct clock_event_device *dev, - enum clock_event_mode mode); +extern void clockevents_set_state(struct clock_event_device *dev, + enum clock_event_state state); extern int clockevents_program_event(struct clock_event_device *dev, ktime_t expires, bool force); diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 1b0ea63de69c..6e53e9a0c2e8 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -94,44 +94,49 @@ u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt) } EXPORT_SYMBOL_GPL(clockevent_delta2ns); -static int __clockevents_set_mode(struct clock_event_device *dev, - enum clock_event_mode mode) +static int __clockevents_set_state(struct clock_event_device *dev, + enum clock_event_state state) { /* Transition with legacy set_mode() callback */ if (dev->set_mode) { /* Legacy callback doesn't support new modes */ - if (mode > CLOCK_EVT_MODE_ONESHOT) + if (state > CLOCK_EVT_STATE_ONESHOT) return -ENOSYS; - dev->set_mode(mode, dev); + /* + * 'clock_event_state' and 'clock_event_mode' have 1-to-1 + * mapping until *_ONESHOT, and so a simple cast will work. + */ + dev->set_mode((enum clock_event_mode)state, dev); + dev->mode = (enum clock_event_mode)state; return 0; } if (dev->features & CLOCK_EVT_FEAT_DUMMY) return 0; - /* Transition with new mode-specific callbacks */ - switch (mode) { - case CLOCK_EVT_MODE_UNUSED: + /* Transition with new state-specific callbacks */ + switch (state) { + case CLOCK_EVT_STATE_DETACHED: /* * This is an internal state, which is guaranteed to go from - * SHUTDOWN to UNUSED. No driver interaction required. + * SHUTDOWN to DETACHED. No driver interaction required. */ return 0; - case CLOCK_EVT_MODE_SHUTDOWN: - return dev->set_mode_shutdown(dev); + case CLOCK_EVT_STATE_SHUTDOWN: + return dev->set_state_shutdown(dev); - case CLOCK_EVT_MODE_PERIODIC: + case CLOCK_EVT_STATE_PERIODIC: /* Core internal bug */ if (!(dev->features & CLOCK_EVT_FEAT_PERIODIC)) return -ENOSYS; - return dev->set_mode_periodic(dev); + return dev->set_state_periodic(dev); - case CLOCK_EVT_MODE_ONESHOT: + case CLOCK_EVT_STATE_ONESHOT: /* Core internal bug */ if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT)) return -ENOSYS; - return dev->set_mode_oneshot(dev); + return dev->set_state_oneshot(dev); default: return -ENOSYS; @@ -139,26 +144,26 @@ static int __clockevents_set_mode(struct clock_event_device *dev, } /** - * clockevents_set_mode - set the operating mode of a clock event device + * clockevents_set_state - set the operating state of a clock event device * @dev: device to modify - * @mode: new mode + * @state: new state * * Must be called with interrupts disabled ! */ -void clockevents_set_mode(struct clock_event_device *dev, - enum clock_event_mode mode) +void clockevents_set_state(struct clock_event_device *dev, + enum clock_event_state state) { - if (dev->mode != mode) { - if (__clockevents_set_mode(dev, mode)) + if (dev->state != state) { + if (__clockevents_set_state(dev, state)) return; - dev->mode = mode; + dev->state = state; /* * A nsec2cyc multiplicator of 0 is invalid and we'd crash * on it, so fix it up and emit a warning: */ - if (mode == CLOCK_EVT_MODE_ONESHOT) { + if (state == CLOCK_EVT_STATE_ONESHOT) { if (unlikely(!dev->mult)) { dev->mult = 1; WARN_ON(1); @@ -173,7 +178,7 @@ void clockevents_set_mode(struct clock_event_device *dev, */ void clockevents_shutdown(struct clock_event_device *dev) { - clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN); + clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN); dev->next_event.tv64 = KTIME_MAX; } @@ -185,13 +190,12 @@ int clockevents_tick_resume(struct clock_event_device *dev) { int ret = 0; - if (dev->set_mode) + if (dev->set_mode) { dev->set_mode(CLOCK_EVT_MODE_RESUME, dev); - else if (dev->tick_resume) - ret = dev->tick_resume(dev); - - if (likely(!ret)) dev->mode = CLOCK_EVT_MODE_RESUME; + } else if (dev->tick_resume) { + ret = dev->tick_resume(dev); + } return ret; } @@ -248,7 +252,7 @@ static int clockevents_program_min_delta(struct clock_event_device *dev) delta = dev->min_delta_ns; dev->next_event = ktime_add_ns(ktime_get(), delta); - if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN) + if (dev->state == CLOCK_EVT_STATE_SHUTDOWN) return 0; dev->retries++; @@ -285,7 +289,7 @@ static int clockevents_program_min_delta(struct clock_event_device *dev) delta = dev->min_delta_ns; dev->next_event = ktime_add_ns(ktime_get(), delta); - if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN) + if (dev->state == CLOCK_EVT_STATE_SHUTDOWN) return 0; dev->retries++; @@ -317,7 +321,7 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires, dev->next_event = expires; - if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN) + if (dev->state == CLOCK_EVT_STATE_SHUTDOWN) return 0; /* Shortcut for clockevent devices that can deal with ktime. */ @@ -362,7 +366,7 @@ static int clockevents_replace(struct clock_event_device *ced) struct clock_event_device *dev, *newdev = NULL; list_for_each_entry(dev, &clockevent_devices, list) { - if (dev == ced || dev->mode != CLOCK_EVT_MODE_UNUSED) + if (dev == ced || dev->state != CLOCK_EVT_STATE_DETACHED) continue; if (!tick_check_replacement(newdev, dev)) @@ -388,7 +392,7 @@ static int clockevents_replace(struct clock_event_device *ced) static int __clockevents_try_unbind(struct clock_event_device *ced, int cpu) { /* Fast track. Device is unused */ - if (ced->mode == CLOCK_EVT_MODE_UNUSED) { + if (ced->state == CLOCK_EVT_STATE_DETACHED) { list_del_init(&ced->list); return 0; } @@ -438,30 +442,30 @@ int clockevents_unbind_device(struct clock_event_device *ced, int cpu) } EXPORT_SYMBOL_GPL(clockevents_unbind); -/* Sanity check of mode transition callbacks */ +/* Sanity check of state transition callbacks */ static int clockevents_sanity_check(struct clock_event_device *dev) { /* Legacy set_mode() callback */ if (dev->set_mode) { /* We shouldn't be supporting new modes now */ - WARN_ON(dev->set_mode_periodic || dev->set_mode_oneshot || - dev->set_mode_shutdown || dev->tick_resume); + WARN_ON(dev->set_state_periodic || dev->set_state_oneshot || + dev->set_state_shutdown || dev->tick_resume); return 0; } if (dev->features & CLOCK_EVT_FEAT_DUMMY) return 0; - /* New mode-specific callbacks */ - if (!dev->set_mode_shutdown) + /* New state-specific callbacks */ + if (!dev->set_state_shutdown) return -EINVAL; if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) && - !dev->set_mode_periodic) + !dev->set_state_periodic) return -EINVAL; if ((dev->features & CLOCK_EVT_FEAT_ONESHOT) && - !dev->set_mode_oneshot) + !dev->set_state_oneshot) return -EINVAL; return 0; @@ -478,6 +482,9 @@ void clockevents_register_device(struct clock_event_device *dev) BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED); BUG_ON(clockevents_sanity_check(dev)); + /* Initialize state to DETACHED */ + dev->state = CLOCK_EVT_STATE_DETACHED; + if (!dev->cpumask) { WARN_ON(num_possible_cpus() > 1); dev->cpumask = cpumask_of(smp_processor_id()); @@ -541,11 +548,11 @@ int __clockevents_update_freq(struct clock_event_device *dev, u32 freq) { clockevents_config(dev, freq); - if (dev->mode == CLOCK_EVT_MODE_ONESHOT) + if (dev->state == CLOCK_EVT_STATE_ONESHOT) return clockevents_program_event(dev, dev->next_event, false); - if (dev->mode == CLOCK_EVT_MODE_PERIODIC) - return __clockevents_set_mode(dev, CLOCK_EVT_MODE_PERIODIC); + if (dev->state == CLOCK_EVT_STATE_PERIODIC) + return __clockevents_set_state(dev, CLOCK_EVT_STATE_PERIODIC); return 0; } @@ -601,13 +608,13 @@ void clockevents_exchange_device(struct clock_event_device *old, */ if (old) { module_put(old->owner); - clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED); + clockevents_set_state(old, CLOCK_EVT_STATE_DETACHED); list_del(&old->list); list_add(&old->list, &clockevents_released); } if (new) { - BUG_ON(new->mode != CLOCK_EVT_MODE_UNUSED); + BUG_ON(new->state != CLOCK_EVT_STATE_DETACHED); clockevents_shutdown(new); } local_irq_restore(flags); @@ -693,7 +700,7 @@ int clockevents_notify(unsigned long reason, void *arg) if (cpumask_test_cpu(cpu, dev->cpumask) && cpumask_weight(dev->cpumask) == 1 && !tick_is_broadcast_device(dev)) { - BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED); + BUG_ON(dev->state != CLOCK_EVT_STATE_DETACHED); list_del(&dev->list); } } diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 542d5bb5c13d..f0f8ee9dbc28 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -303,7 +303,7 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev) /* * The device is in periodic mode. No reprogramming necessary: */ - if (dev->mode == CLOCK_EVT_MODE_PERIODIC) + if (dev->state == CLOCK_EVT_STATE_PERIODIC) goto unlock; /* @@ -532,8 +532,8 @@ static int tick_broadcast_set_event(struct clock_event_device *bc, int cpu, { int ret; - if (bc->mode != CLOCK_EVT_MODE_ONESHOT) - clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT); + if (bc->state != CLOCK_EVT_STATE_ONESHOT) + clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT); ret = clockevents_program_event(bc, expires, force); if (!ret) @@ -543,7 +543,7 @@ static int tick_broadcast_set_event(struct clock_event_device *bc, int cpu, int tick_resume_broadcast_oneshot(struct clock_event_device *bc) { - clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT); + clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT); return 0; } @@ -562,8 +562,8 @@ void tick_check_oneshot_broadcast_this_cpu(void) * switched over, leave the device alone. */ if (td->mode == TICKDEV_MODE_ONESHOT) { - clockevents_set_mode(td->evtdev, - CLOCK_EVT_MODE_ONESHOT); + clockevents_set_state(td->evtdev, + CLOCK_EVT_STATE_ONESHOT); } } } @@ -666,7 +666,7 @@ static void broadcast_shutdown_local(struct clock_event_device *bc, if (dev->next_event.tv64 < bc->next_event.tv64) return; } - clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN); + clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN); } static void broadcast_move_bc(int deadcpu) @@ -741,7 +741,7 @@ int tick_broadcast_oneshot_control(unsigned long reason) cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); } else { if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) { - clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT); + clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT); /* * The cpu which was handling the broadcast * timer marked this cpu in the broadcast @@ -842,7 +842,7 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc) /* Set it up only once ! */ if (bc->event_handler != tick_handle_oneshot_broadcast) { - int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC; + int was_periodic = bc->state == CLOCK_EVT_STATE_PERIODIC; bc->event_handler = tick_handle_oneshot_broadcast; @@ -858,7 +858,7 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc) tick_broadcast_oneshot_mask, tmpmask); if (was_periodic && !cpumask_empty(tmpmask)) { - clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT); + clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT); tick_broadcast_init_next_event(tmpmask, tick_next_period); tick_broadcast_set_event(bc, cpu, tick_next_period, 1); diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 5c50664c21d7..a5b877130ae9 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -102,7 +102,7 @@ void tick_handle_periodic(struct clock_event_device *dev) tick_periodic(cpu); - if (dev->mode != CLOCK_EVT_MODE_ONESHOT) + if (dev->state != CLOCK_EVT_STATE_ONESHOT) return; for (;;) { /* @@ -140,7 +140,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) && !tick_broadcast_oneshot_active()) { - clockevents_set_mode(dev, CLOCK_EVT_MODE_PERIODIC); + clockevents_set_state(dev, CLOCK_EVT_STATE_PERIODIC); } else { unsigned long seq; ktime_t next; @@ -150,7 +150,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) next = tick_next_period; } while (read_seqretry(&jiffies_lock, seq)); - clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT); + clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT); for (;;) { if (!clockevents_program_event(dev, next, false)) @@ -365,6 +365,7 @@ void tick_shutdown(unsigned int *cpup) * Prevent that the clock events layer tries to call * the set mode function! */ + dev->state = CLOCK_EVT_STATE_DETACHED; dev->mode = CLOCK_EVT_MODE_UNUSED; clockevents_exchange_device(dev, NULL); dev->event_handler = clockevents_handle_noop; diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c index 7ce740e78e1b..67a64b1670bf 100644 --- a/kernel/time/tick-oneshot.c +++ b/kernel/time/tick-oneshot.c @@ -38,7 +38,7 @@ void tick_resume_oneshot(void) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); - clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT); + clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT); clockevents_program_event(dev, ktime_get(), true); } @@ -50,7 +50,7 @@ void tick_setup_oneshot(struct clock_event_device *newdev, ktime_t next_event) { newdev->event_handler = handler; - clockevents_set_mode(newdev, CLOCK_EVT_MODE_ONESHOT); + clockevents_set_state(newdev, CLOCK_EVT_STATE_ONESHOT); clockevents_program_event(newdev, next_event, true); } @@ -81,7 +81,7 @@ int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *)) td->mode = TICKDEV_MODE_ONESHOT; dev->event_handler = handler; - clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT); + clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT); tick_broadcast_switch_to_oneshot(); return 0; } diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index 2b3e9393034d..05aa5590106a 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -233,21 +233,21 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu) print_name_offset(m, dev->set_mode); SEQ_printf(m, "\n"); } else { - if (dev->set_mode_shutdown) { + if (dev->set_state_shutdown) { SEQ_printf(m, " shutdown: "); - print_name_offset(m, dev->set_mode_shutdown); + print_name_offset(m, dev->set_state_shutdown); SEQ_printf(m, "\n"); } - if (dev->set_mode_periodic) { + if (dev->set_state_periodic) { SEQ_printf(m, " periodic: "); - print_name_offset(m, dev->set_mode_periodic); + print_name_offset(m, dev->set_state_periodic); SEQ_printf(m, "\n"); } - if (dev->set_mode_oneshot) { + if (dev->set_state_oneshot) { SEQ_printf(m, " oneshot: "); - print_name_offset(m, dev->set_mode_oneshot); + print_name_offset(m, dev->set_state_oneshot); SEQ_printf(m, "\n"); } -- cgit v1.2.3 From 9f083b74df3a7eaa100b456f2dc195512daf728e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 25 Mar 2015 13:05:19 +0100 Subject: clockevents: Remove CONFIG_GENERIC_CLOCKEVENTS_BUILD This option was for simpler migration to the clock events code. Most architectures have been converted and the option has been disfunctional as a standalone option for quite some time. Remove it. Signed-off-by: Thomas Gleixner Signed-off-by: Rafael J. Wysocki Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/5021859.jl9OC1medj@vostro.rjw.lan Signed-off-by: Ingo Molnar --- include/linux/clockchips.h | 9 +++------ kernel/time/Kconfig | 6 ------ kernel/time/Makefile | 6 ++---- kernel/time/clockevents.c | 3 --- kernel/time/tick-internal.h | 4 ++-- 5 files changed, 7 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index e20232c3320a..57975131dac1 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -22,7 +22,7 @@ enum clock_event_nofitiers { CLOCK_EVT_NOTIFY_CPU_DEAD, }; -#ifdef CONFIG_GENERIC_CLOCKEVENTS_BUILD +#ifdef CONFIG_GENERIC_CLOCKEVENTS #include #include @@ -229,13 +229,9 @@ static inline int tick_check_broadcast_expired(void) { return 0; } static inline void tick_setup_hrtimer_broadcast(void) {}; #endif -#ifdef CONFIG_GENERIC_CLOCKEVENTS extern int clockevents_notify(unsigned long reason, void *arg); -#else -static inline int clockevents_notify(unsigned long reason, void *arg) { return 0; } -#endif -#else /* CONFIG_GENERIC_CLOCKEVENTS_BUILD */ +#else /* CONFIG_GENERIC_CLOCKEVENTS */ static inline void clockevents_suspend(void) {} static inline void clockevents_resume(void) {} @@ -243,6 +239,7 @@ static inline void clockevents_resume(void) {} static inline int clockevents_notify(unsigned long reason, void *arg) { return 0; } static inline int tick_check_broadcast_expired(void) { return 0; } static inline void tick_setup_hrtimer_broadcast(void) {}; +static inline int clockevents_notify(unsigned long reason, void *arg) { return 0; } #endif diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index d626dc98e8df..579ce1b929af 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -33,12 +33,6 @@ config ARCH_USES_GETTIMEOFFSET config GENERIC_CLOCKEVENTS bool -# Migration helper. Builds, but does not invoke -config GENERIC_CLOCKEVENTS_BUILD - bool - default y - depends on GENERIC_CLOCKEVENTS - # Architecture can handle broadcast in a driver-agnostic way config ARCH_HAS_TICK_BROADCAST bool diff --git a/kernel/time/Makefile b/kernel/time/Makefile index c09c07817d7a..01f0312419b3 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -2,15 +2,13 @@ obj-y += time.o timer.o hrtimer.o itimer.o posix-timers.o posix-cpu-timers.o obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o obj-y += timeconv.o timecounter.o posix-clock.o alarmtimer.o -obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD) += clockevents.o -obj-$(CONFIG_GENERIC_CLOCKEVENTS) += tick-common.o +obj-$(CONFIG_GENERIC_CLOCKEVENTS) += clockevents.o tick-common.o ifeq ($(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST),y) obj-y += tick-broadcast.o obj-$(CONFIG_TICK_ONESHOT) += tick-broadcast-hrtimer.o endif obj-$(CONFIG_GENERIC_SCHED_CLOCK) += sched_clock.o -obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o -obj-$(CONFIG_TICK_ONESHOT) += tick-sched.o +obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o tick-sched.o obj-$(CONFIG_TIMER_STATS) += timer_stats.o obj-$(CONFIG_DEBUG_FS) += timekeeping_debug.o obj-$(CONFIG_TEST_UDELAY) += test_udelay.o diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 73689df1e4b8..3531beecbe95 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -645,7 +645,6 @@ void clockevents_resume(void) dev->resume(dev); } -#ifdef CONFIG_GENERIC_CLOCKEVENTS /** * clockevents_notify - notification about relevant events * Returns 0 on success, any other value on error @@ -831,5 +830,3 @@ static int __init clockevents_init_sysfs(void) } device_initcall(clockevents_init_sysfs); #endif /* SYSFS */ - -#endif /* GENERIC_CLOCK_EVENTS */ diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 98700e4a2000..c7b75bec27f2 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -10,7 +10,7 @@ extern seqlock_t jiffies_lock; #define CS_NAME_LEN 32 -#ifdef CONFIG_GENERIC_CLOCKEVENTS_BUILD +#ifdef CONFIG_GENERIC_CLOCKEVENTS #define TICK_DO_TIMER_NONE -1 #define TICK_DO_TIMER_BOOT -2 @@ -167,7 +167,7 @@ static inline int tick_device_is_functional(struct clock_event_device *dev) int __clockevents_update_freq(struct clock_event_device *dev, u32 freq); -#endif +#endif /* GENERIC_CLOCKEVENTS */ extern void do_timer(unsigned long ticks); extern void update_wall_time(void); -- cgit v1.2.3 From c1797baf6880174f899ce3960d0598f5bbeeb7ff Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 25 Mar 2015 13:07:37 +0100 Subject: tick: Move core only declarations and functions to core No point to expose everything to the world. People just believe such functions can be abused for whatever purposes. Sigh. Signed-off-by: Thomas Gleixner [ Rebased on top of 4.0-rc5 ] Signed-off-by: Rafael J. Wysocki Cc: Nicolas Pitre Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/28017337.VbCUc39Gme@vostro.rjw.lan [ Merged to latest timers/core ] Signed-off-by: Ingo Molnar --- include/linux/clockchips.h | 15 ++--- include/linux/tick.h | 134 ++++++-------------------------------------- kernel/time/clocksource.c | 2 +- kernel/time/hrtimer.c | 2 +- kernel/time/tick-internal.h | 15 +++++ kernel/time/tick-sched.c | 7 ++- kernel/time/tick-sched.h | 64 +++++++++++++++++++++ kernel/time/timer_list.c | 2 +- 8 files changed, 112 insertions(+), 129 deletions(-) create mode 100644 kernel/time/tick-sched.h (limited to 'include') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 57975131dac1..bc3af821350b 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -193,15 +193,6 @@ extern void clockevents_config_and_register(struct clock_event_device *dev, extern int clockevents_update_freq(struct clock_event_device *ce, u32 freq); -extern void clockevents_exchange_device(struct clock_event_device *old, - struct clock_event_device *new); -extern void clockevents_set_state(struct clock_event_device *dev, - enum clock_event_state state); -extern int clockevents_program_event(struct clock_event_device *dev, - ktime_t expires, bool force); - -extern void clockevents_handle_noop(struct clock_event_device *dev); - static inline void clockevents_calc_mult_shift(struct clock_event_device *ce, u32 freq, u32 minsec) { @@ -209,6 +200,12 @@ clockevents_calc_mult_shift(struct clock_event_device *ce, u32 freq, u32 minsec) freq, minsec); } +/* Should be core only, but is abused by arm bl_switcher */ +extern void clockevents_set_state(struct clock_event_device *dev, + enum clock_event_state state); +extern int clockevents_program_event(struct clock_event_device *dev, + ktime_t expires, bool force); + extern void clockevents_suspend(void); extern void clockevents_resume(void); diff --git a/include/linux/tick.h b/include/linux/tick.h index 9c085dc12ae9..f9a2d2687a46 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -1,7 +1,5 @@ -/* linux/include/linux/tick.h - * - * This file contains the structure definitions for tick related functions - * +/* + * Tick related global functions */ #ifndef _LINUX_TICK_H #define _LINUX_TICK_H @@ -9,13 +7,12 @@ #include #include #include -#include #include #include #include +/* ARM BL switcher abuse support */ #ifdef CONFIG_GENERIC_CLOCKEVENTS - enum tick_device_mode { TICKDEV_MODE_PERIODIC, TICKDEV_MODE_ONESHOT, @@ -25,133 +22,38 @@ struct tick_device { struct clock_event_device *evtdev; enum tick_device_mode mode; }; - -enum tick_nohz_mode { - NOHZ_MODE_INACTIVE, - NOHZ_MODE_LOWRES, - NOHZ_MODE_HIGHRES, -}; - -/** - * struct tick_sched - sched tick emulation and no idle tick control/stats - * @sched_timer: hrtimer to schedule the periodic tick in high - * resolution mode - * @last_tick: Store the last tick expiry time when the tick - * timer is modified for nohz sleeps. This is necessary - * to resume the tick timer operation in the timeline - * when the CPU returns from nohz sleep. - * @tick_stopped: Indicator that the idle tick has been stopped - * @idle_jiffies: jiffies at the entry to idle for idle time accounting - * @idle_calls: Total number of idle calls - * @idle_sleeps: Number of idle calls, where the sched tick was stopped - * @idle_entrytime: Time when the idle call was entered - * @idle_waketime: Time when the idle was interrupted - * @idle_exittime: Time when the idle state was left - * @idle_sleeptime: Sum of the time slept in idle with sched tick stopped - * @iowait_sleeptime: Sum of the time slept in idle with sched tick stopped, with IO outstanding - * @sleep_length: Duration of the current idle sleep - * @do_timer_lst: CPU was the last one doing do_timer before going idle - */ -struct tick_sched { - struct hrtimer sched_timer; - unsigned long check_clocks; - enum tick_nohz_mode nohz_mode; - ktime_t last_tick; - int inidle; - int tick_stopped; - unsigned long idle_jiffies; - unsigned long idle_calls; - unsigned long idle_sleeps; - int idle_active; - ktime_t idle_entrytime; - ktime_t idle_waketime; - ktime_t idle_exittime; - ktime_t idle_sleeptime; - ktime_t iowait_sleeptime; - ktime_t sleep_length; - unsigned long last_jiffies; - unsigned long next_jiffies; - ktime_t idle_expires; - int do_timer_last; -}; - -extern void __init tick_init(void); -extern int tick_is_oneshot_available(void); extern struct tick_device *tick_get_device(int cpu); +#endif +#ifdef CONFIG_GENERIC_CLOCKEVENTS +extern void __init tick_init(void); extern void tick_freeze(void); extern void tick_unfreeze(void); +#else /* CONFIG_GENERIC_CLOCKEVENTS */ +static inline void tick_init(void) { } +static inline void tick_freeze(void) { } +static inline void tick_unfreeze(void) { } +#endif /* !CONFIG_GENERIC_CLOCKEVENTS */ -# ifdef CONFIG_HIGH_RES_TIMERS -extern int tick_init_highres(void); -extern int tick_program_event(ktime_t expires, int force); -extern void tick_setup_sched_timer(void); -# endif - -# if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS -extern void tick_cancel_sched_timer(int cpu); -# else -static inline void tick_cancel_sched_timer(int cpu) { } -# endif - -# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST -extern struct tick_device *tick_get_broadcast_device(void); -extern struct cpumask *tick_get_broadcast_mask(void); - -# ifdef CONFIG_TICK_ONESHOT -extern struct cpumask *tick_get_broadcast_oneshot_mask(void); -# endif - -# endif /* BROADCAST */ - -# ifdef CONFIG_TICK_ONESHOT -extern void tick_clock_notify(void); -extern int tick_check_oneshot_change(int allow_nohz); -extern struct tick_sched *tick_get_tick_sched(int cpu); +#ifdef CONFIG_TICK_ONESHOT extern void tick_irq_enter(void); -extern int tick_oneshot_mode_active(void); # ifndef arch_needs_cpu # define arch_needs_cpu() (0) # endif # else -static inline void tick_clock_notify(void) { } -static inline int tick_check_oneshot_change(int allow_nohz) { return 0; } -static inline void tick_irq_enter(void) { } -static inline int tick_oneshot_mode_active(void) { return 0; } -# endif - -#else /* CONFIG_GENERIC_CLOCKEVENTS */ -static inline void tick_init(void) { } -static inline void tick_freeze(void) { } -static inline void tick_unfreeze(void) { } -static inline void tick_cancel_sched_timer(int cpu) { } -static inline void tick_clock_notify(void) { } -static inline int tick_check_oneshot_change(int allow_nohz) { return 0; } static inline void tick_irq_enter(void) { } -static inline int tick_oneshot_mode_active(void) { return 0; } -#endif /* !CONFIG_GENERIC_CLOCKEVENTS */ - -# ifdef CONFIG_NO_HZ_COMMON -DECLARE_PER_CPU(struct tick_sched, tick_cpu_sched); - -static inline int tick_nohz_tick_stopped(void) -{ - return __this_cpu_read(tick_cpu_sched.tick_stopped); -} +#endif +#ifdef CONFIG_NO_HZ_COMMON +extern int tick_nohz_tick_stopped(void); extern void tick_nohz_idle_enter(void); extern void tick_nohz_idle_exit(void); extern void tick_nohz_irq_exit(void); extern ktime_t tick_nohz_get_sleep_length(void); extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time); extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time); - -# else /* !CONFIG_NO_HZ_COMMON */ -static inline int tick_nohz_tick_stopped(void) -{ - return 0; -} - +#else /* !CONFIG_NO_HZ_COMMON */ +static inline int tick_nohz_tick_stopped(void) { return 0; } static inline void tick_nohz_idle_enter(void) { } static inline void tick_nohz_idle_exit(void) { } @@ -163,7 +65,7 @@ static inline ktime_t tick_nohz_get_sleep_length(void) } static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; } static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } -# endif /* !CONFIG_NO_HZ_COMMON */ +#endif /* !CONFIG_NO_HZ_COMMON */ #ifdef CONFIG_NO_HZ_FULL extern bool tick_nohz_full_running; diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 8b4010f0b1b4..c3be3c71bbad 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -31,7 +31,7 @@ #include #include -#include "timekeeping.h" +#include "tick-internal.h" #include "timekeeping_internal.h" /** diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index bee0c1f78091..721d29b99d10 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -54,7 +54,7 @@ #include -#include "timekeeping.h" +#include "tick-internal.h" /* * The timer bases: diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index d86eb8d485e9..dd2c45d057b9 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -5,6 +5,7 @@ #include #include "timekeeping.h" +#include "tick-sched.h" #ifdef CONFIG_GENERIC_CLOCKEVENTS @@ -26,6 +27,7 @@ extern void tick_resume(void); extern bool tick_check_replacement(struct clock_event_device *curdev, struct clock_event_device *newdev); extern void tick_install_replacement(struct clock_event_device *dev); +extern int tick_is_oneshot_available(void); extern int clockevents_tick_resume(struct clock_event_device *dev); /* Check, if the device is functional or a dummy for broadcast */ @@ -35,6 +37,9 @@ static inline int tick_device_is_functional(struct clock_event_device *dev) } extern void clockevents_shutdown(struct clock_event_device *dev); +extern void clockevents_exchange_device(struct clock_event_device *old, + struct clock_event_device *new); +extern void clockevents_handle_noop(struct clock_event_device *dev); extern int __clockevents_update_freq(struct clock_event_device *dev, u32 freq); extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt); #endif /* GENERIC_CLOCKEVENTS */ @@ -49,6 +54,10 @@ extern void tick_oneshot_notify(void); extern int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *)); extern void tick_resume_oneshot(void); static inline bool tick_oneshot_possible(void) { return true; } +extern int tick_oneshot_mode_active(void); +extern void tick_clock_notify(void); +extern int tick_check_oneshot_change(int allow_nohz); +extern int tick_init_highres(void); #else /* !ONESHOT */ static inline void tick_setup_oneshot(struct clock_event_device *newdev, @@ -58,6 +67,9 @@ static inline void tick_resume_oneshot(void) { BUG(); } static inline int tick_program_event(ktime_t expires, int force) { return 0; } static inline void tick_oneshot_notify(void) { } static inline bool tick_oneshot_possible(void) { return false; } +static inline int tick_oneshot_mode_active(void) { return 0; } +static inline void tick_clock_notify(void) { } +static inline int tick_check_oneshot_change(int allow_nohz) { return 0; } #endif /* !TICK_ONESHOT */ /* Broadcasting support */ @@ -72,6 +84,8 @@ extern int tick_resume_broadcast(void); extern void tick_broadcast_init(void); extern void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast); extern int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq); +extern struct tick_device *tick_get_broadcast_device(void); +extern struct cpumask *tick_get_broadcast_mask(void); #else /* !BROADCAST */ static inline void tick_install_broadcast_device(struct clock_event_device *dev) { } static inline int tick_is_broadcast_device(struct clock_event_device *dev) { return 0; } @@ -101,6 +115,7 @@ extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc); extern int tick_broadcast_oneshot_active(void); extern void tick_check_oneshot_broadcast_this_cpu(void); bool tick_broadcast_oneshot_available(void); +extern struct cpumask *tick_get_broadcast_oneshot_mask(void); #else /* BROADCAST && ONESHOT */ static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); } static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index a4c4edac4528..914259128145 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -34,7 +34,7 @@ /* * Per cpu nohz control structure */ -DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched); +static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched); /* * The time, when the last jiffy update happened. Protected by jiffies_lock. @@ -416,6 +416,11 @@ static int __init setup_tick_nohz(char *str) __setup("nohz=", setup_tick_nohz); +int tick_nohz_tick_stopped(void) +{ + return __this_cpu_read(tick_cpu_sched.tick_stopped); +} + /** * tick_nohz_update_jiffies - update jiffies when idle was interrupted * diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h new file mode 100644 index 000000000000..930743249127 --- /dev/null +++ b/kernel/time/tick-sched.h @@ -0,0 +1,64 @@ +#ifndef _TICK_SCHED_H +#define _TICK_SCHED_H + +#include + +enum tick_nohz_mode { + NOHZ_MODE_INACTIVE, + NOHZ_MODE_LOWRES, + NOHZ_MODE_HIGHRES, +}; + +/** + * struct tick_sched - sched tick emulation and no idle tick control/stats + * @sched_timer: hrtimer to schedule the periodic tick in high + * resolution mode + * @last_tick: Store the last tick expiry time when the tick + * timer is modified for nohz sleeps. This is necessary + * to resume the tick timer operation in the timeline + * when the CPU returns from nohz sleep. + * @tick_stopped: Indicator that the idle tick has been stopped + * @idle_jiffies: jiffies at the entry to idle for idle time accounting + * @idle_calls: Total number of idle calls + * @idle_sleeps: Number of idle calls, where the sched tick was stopped + * @idle_entrytime: Time when the idle call was entered + * @idle_waketime: Time when the idle was interrupted + * @idle_exittime: Time when the idle state was left + * @idle_sleeptime: Sum of the time slept in idle with sched tick stopped + * @iowait_sleeptime: Sum of the time slept in idle with sched tick stopped, with IO outstanding + * @sleep_length: Duration of the current idle sleep + * @do_timer_lst: CPU was the last one doing do_timer before going idle + */ +struct tick_sched { + struct hrtimer sched_timer; + unsigned long check_clocks; + enum tick_nohz_mode nohz_mode; + ktime_t last_tick; + int inidle; + int tick_stopped; + unsigned long idle_jiffies; + unsigned long idle_calls; + unsigned long idle_sleeps; + int idle_active; + ktime_t idle_entrytime; + ktime_t idle_waketime; + ktime_t idle_exittime; + ktime_t idle_sleeptime; + ktime_t iowait_sleeptime; + ktime_t sleep_length; + unsigned long last_jiffies; + unsigned long next_jiffies; + ktime_t idle_expires; + int do_timer_last; +}; + +extern struct tick_sched *tick_get_tick_sched(int cpu); + +extern void tick_setup_sched_timer(void); +#if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS +extern void tick_cancel_sched_timer(int cpu); +#else +static inline void tick_cancel_sched_timer(int cpu) { } +#endif + +#endif diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index 05aa5590106a..e878c2e0ba45 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -16,10 +16,10 @@ #include #include #include -#include #include +#include "tick-internal.h" struct timer_list_iter { int cpu; -- cgit v1.2.3 From 4ffee521f36390c7720d493591b764ca35c8030b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 25 Mar 2015 13:09:16 +0100 Subject: clockevents: Make suspend/resume calls explicit clockevents_notify() is a leftover from the early design of the clockevents facility. It's really not a notification mechanism, it's a multiplex call. We are way better off to have explicit calls instead of this monstrosity. Split out the suspend/resume() calls and invoke them directly from the call sites. No locking required at this point because these calls happen with interrupts disabled and a single cpu online. Signed-off-by: Thomas Gleixner [ Rebased on top of 4.0-rc5. ] Signed-off-by: Rafael J. Wysocki Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/713674030.jVm1qaHuPf@vostro.rjw.lan [ Rebased on top of latest timers/core. ] Signed-off-by: Ingo Molnar --- arch/x86/xen/suspend.c | 11 ++++------- include/linux/clockchips.h | 2 -- include/linux/tick.h | 3 +++ kernel/time/clockevents.c | 9 --------- kernel/time/tick-common.c | 26 +++++++++++++++++++++++--- kernel/time/tick-internal.h | 3 ++- kernel/time/timekeeping.c | 6 ++---- 7 files changed, 34 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index c4df9dbd63b7..033e428581f4 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -1,5 +1,5 @@ #include -#include +#include #include #include @@ -81,17 +81,14 @@ void xen_arch_post_suspend(int cancelled) static void xen_vcpu_notify_restore(void *data) { - unsigned long reason = (unsigned long)data; - /* Boot processor notified via generic timekeeping_resume() */ - if ( smp_processor_id() == 0) + if (smp_processor_id() == 0) return; - clockevents_notify(reason, NULL); + tick_resume(); } void xen_arch_resume(void) { - on_each_cpu(xen_vcpu_notify_restore, - (void *)CLOCK_EVT_NOTIFY_RESUME, 1); + on_each_cpu(xen_vcpu_notify_restore, NULL, 1); } diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index bc3af821350b..50ce9750754f 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -16,8 +16,6 @@ enum clock_event_nofitiers { CLOCK_EVT_NOTIFY_BROADCAST_FORCE, CLOCK_EVT_NOTIFY_BROADCAST_ENTER, CLOCK_EVT_NOTIFY_BROADCAST_EXIT, - CLOCK_EVT_NOTIFY_SUSPEND, - CLOCK_EVT_NOTIFY_RESUME, CLOCK_EVT_NOTIFY_CPU_DYING, CLOCK_EVT_NOTIFY_CPU_DEAD, }; diff --git a/include/linux/tick.h b/include/linux/tick.h index f9a2d2687a46..7e07e0e3d898 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -29,10 +29,13 @@ extern struct tick_device *tick_get_device(int cpu); extern void __init tick_init(void); extern void tick_freeze(void); extern void tick_unfreeze(void); +/* Should be core only, but XEN resume magic abuses this interface */ +extern void tick_resume(void); #else /* CONFIG_GENERIC_CLOCKEVENTS */ static inline void tick_init(void) { } static inline void tick_freeze(void) { } static inline void tick_unfreeze(void) { } +static inline void tick_resume(void) { } #endif /* !CONFIG_GENERIC_CLOCKEVENTS */ #ifdef CONFIG_TICK_ONESHOT diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index b73002718536..7af614829da1 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -670,15 +670,6 @@ int clockevents_notify(unsigned long reason, void *arg) tick_handover_do_timer(arg); break; - case CLOCK_EVT_NOTIFY_SUSPEND: - tick_suspend(); - tick_suspend_broadcast(); - break; - - case CLOCK_EVT_NOTIFY_RESUME: - tick_resume(); - break; - case CLOCK_EVT_NOTIFY_CPU_DEAD: tick_shutdown_broadcast_oneshot(arg); tick_shutdown_broadcast(arg); diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index a5b877130ae9..1a60c2ae96a8 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -373,18 +373,39 @@ void tick_shutdown(unsigned int *cpup) } } +/** + * tick_suspend - Suspend the tick and the broadcast device + * + * Called from syscore_suspend() via timekeeping_suspend with only one + * CPU online and interrupts disabled or from tick_unfreeze() under + * tick_freeze_lock. + * + * No locks required. Nothing can change the per cpu device. + */ void tick_suspend(void) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); clockevents_shutdown(td->evtdev); + tick_suspend_broadcast(); } +/** + * tick_resume - Resume the tick and the broadcast device + * + * Called from syscore_resume() via timekeeping_resume with only one + * CPU online and interrupts disabled or from tick_unfreeze() under + * tick_freeze_lock. + * + * No locks required. Nothing can change the per cpu device. + */ void tick_resume(void) { - struct tick_device *td = this_cpu_ptr(&tick_cpu_device); - int broadcast = tick_resume_broadcast(); + struct tick_device *td; + int broadcast; + broadcast = tick_resume_broadcast(); + td = this_cpu_ptr(&tick_cpu_device); clockevents_tick_resume(td->evtdev); if (!broadcast) { @@ -416,7 +437,6 @@ void tick_freeze(void) timekeeping_suspend(); } else { tick_suspend(); - tick_suspend_broadcast(); } raw_spin_unlock(&tick_freeze_lock); diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index dd2c45d057b9..85a957195bf6 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -23,7 +23,6 @@ extern void tick_check_new_device(struct clock_event_device *dev); extern void tick_handover_do_timer(int *cpup); extern void tick_shutdown(unsigned int *cpup); extern void tick_suspend(void); -extern void tick_resume(void); extern bool tick_check_replacement(struct clock_event_device *curdev, struct clock_event_device *newdev); extern void tick_install_replacement(struct clock_event_device *dev); @@ -42,6 +41,8 @@ extern void clockevents_exchange_device(struct clock_event_device *old, extern void clockevents_handle_noop(struct clock_event_device *dev); extern int __clockevents_update_freq(struct clock_event_device *dev, u32 freq); extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt); +#else +static inline void tick_suspend(void) { } #endif /* GENERIC_CLOCKEVENTS */ /* Oneshot related functions */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index c3fcff06d30a..5b12292b343a 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1389,9 +1389,7 @@ void timekeeping_resume(void) touch_softlockup_watchdog(); - clockevents_notify(CLOCK_EVT_NOTIFY_RESUME, NULL); - - /* Resume hrtimers */ + tick_resume(); hrtimers_resume(); } @@ -1444,7 +1442,7 @@ int timekeeping_suspend(void) write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); - clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL); + tick_suspend(); clocksource_suspend(); clockevents_suspend(); -- cgit v1.2.3 From f46481d0a7cb942b84145acb80ad43bdb1ff8eb4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 25 Mar 2015 13:11:04 +0100 Subject: tick/xen: Provide and use tick_suspend_local() and tick_resume_local() Xen calls on every cpu into tick_resume() which is just wrong. tick_resume() is for the syscore global suspend/resume invocation. What XEN really wants is a per cpu local resume function. Provide a tick_resume_local() function and use it in XEN. Also provide a complementary tick_suspend_local() and modify tick_unfreeze() and tick_freeze(), respectively, to use the new local tick resume/suspend functions. Signed-off-by: Thomas Gleixner [ Combined two patches, rebased, modified subject/changelog. ] Signed-off-by: Rafael J. Wysocki Cc: Boris Ostrovsky Cc: David Vrabel Cc: Konrad Rzeszutek Wilk Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1698741.eezk9tnXtG@vostro.rjw.lan [ Merged to latest timers/core. ] Signed-off-by: Ingo Molnar --- arch/x86/xen/suspend.c | 2 +- include/linux/tick.h | 6 ++--- kernel/time/tick-broadcast.c | 24 +++++++++++++------ kernel/time/tick-common.c | 55 ++++++++++++++++++++++++++++++-------------- kernel/time/tick-internal.h | 8 +++++-- 5 files changed, 65 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index 033e428581f4..d9497698645a 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -85,7 +85,7 @@ static void xen_vcpu_notify_restore(void *data) if (smp_processor_id() == 0) return; - tick_resume(); + tick_resume_local(); } void xen_arch_resume(void) diff --git a/include/linux/tick.h b/include/linux/tick.h index 7e07e0e3d898..a3d4d2840e7f 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -29,13 +29,13 @@ extern struct tick_device *tick_get_device(int cpu); extern void __init tick_init(void); extern void tick_freeze(void); extern void tick_unfreeze(void); -/* Should be core only, but XEN resume magic abuses this interface */ -extern void tick_resume(void); +/* Should be core only, but XEN resume magic requires this */ +extern void tick_resume_local(void); #else /* CONFIG_GENERIC_CLOCKEVENTS */ static inline void tick_init(void) { } static inline void tick_freeze(void) { } static inline void tick_unfreeze(void) { } -static inline void tick_resume(void) { } +static inline void tick_resume_local(void) { } #endif /* !CONFIG_GENERIC_CLOCKEVENTS */ #ifdef CONFIG_TICK_ONESHOT diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 60e6c23ce1c7..19cfb381faa9 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -455,11 +455,26 @@ void tick_suspend_broadcast(void) raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } -int tick_resume_broadcast(void) +/* + * This is called from tick_resume_local() on a resuming CPU. That's + * called from the core resume function, tick_unfreeze() and the magic XEN + * resume hackery. + * + * In none of these cases the broadcast device mode can change and the + * bit of the resuming CPU in the broadcast mask is safe as well. + */ +bool tick_resume_check_broadcast(void) +{ + if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT) + return false; + else + return cpumask_test_cpu(smp_processor_id(), tick_broadcast_mask); +} + +void tick_resume_broadcast(void) { struct clock_event_device *bc; unsigned long flags; - int broadcast = 0; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); @@ -472,8 +487,6 @@ int tick_resume_broadcast(void) case TICKDEV_MODE_PERIODIC: if (!cpumask_empty(tick_broadcast_mask)) tick_broadcast_start_periodic(bc); - broadcast = cpumask_test_cpu(smp_processor_id(), - tick_broadcast_mask); break; case TICKDEV_MODE_ONESHOT: if (!cpumask_empty(tick_broadcast_mask)) @@ -482,11 +495,8 @@ int tick_resume_broadcast(void) } } raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); - - return broadcast; } - #ifdef CONFIG_TICK_ONESHOT static cpumask_var_t tick_broadcast_oneshot_mask; diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 1a60c2ae96a8..da796d65d1fb 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -374,40 +374,32 @@ void tick_shutdown(unsigned int *cpup) } /** - * tick_suspend - Suspend the tick and the broadcast device + * tick_suspend_local - Suspend the local tick device * - * Called from syscore_suspend() via timekeeping_suspend with only one - * CPU online and interrupts disabled or from tick_unfreeze() under - * tick_freeze_lock. + * Called from the local cpu for freeze with interrupts disabled. * * No locks required. Nothing can change the per cpu device. */ -void tick_suspend(void) +static void tick_suspend_local(void) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); clockevents_shutdown(td->evtdev); - tick_suspend_broadcast(); } /** - * tick_resume - Resume the tick and the broadcast device + * tick_resume_local - Resume the local tick device * - * Called from syscore_resume() via timekeeping_resume with only one - * CPU online and interrupts disabled or from tick_unfreeze() under - * tick_freeze_lock. + * Called from the local CPU for unfreeze or XEN resume magic. * * No locks required. Nothing can change the per cpu device. */ -void tick_resume(void) +void tick_resume_local(void) { - struct tick_device *td; - int broadcast; + struct tick_device *td = this_cpu_ptr(&tick_cpu_device); + bool broadcast = tick_resume_check_broadcast(); - broadcast = tick_resume_broadcast(); - td = this_cpu_ptr(&tick_cpu_device); clockevents_tick_resume(td->evtdev); - if (!broadcast) { if (td->mode == TICKDEV_MODE_PERIODIC) tick_setup_periodic(td->evtdev, 0); @@ -416,6 +408,35 @@ void tick_resume(void) } } +/** + * tick_suspend - Suspend the tick and the broadcast device + * + * Called from syscore_suspend() via timekeeping_suspend with only one + * CPU online and interrupts disabled or from tick_unfreeze() under + * tick_freeze_lock. + * + * No locks required. Nothing can change the per cpu device. + */ +void tick_suspend(void) +{ + tick_suspend_local(); + tick_suspend_broadcast(); +} + +/** + * tick_resume - Resume the tick and the broadcast device + * + * Called from syscore_resume() via timekeeping_resume with only one + * CPU online and interrupts disabled. + * + * No locks required. Nothing can change the per cpu device. + */ +void tick_resume(void) +{ + tick_resume_broadcast(); + tick_resume_local(); +} + static DEFINE_RAW_SPINLOCK(tick_freeze_lock); static unsigned int tick_freeze_depth; @@ -436,7 +457,7 @@ void tick_freeze(void) if (tick_freeze_depth == num_online_cpus()) { timekeeping_suspend(); } else { - tick_suspend(); + tick_suspend_local(); } raw_spin_unlock(&tick_freeze_lock); diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 5c9f0eec56b2..6ba7bce732f2 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -23,6 +23,7 @@ extern void tick_check_new_device(struct clock_event_device *dev); extern void tick_handover_do_timer(int *cpup); extern void tick_shutdown(unsigned int *cpup); extern void tick_suspend(void); +extern void tick_resume(void); extern bool tick_check_replacement(struct clock_event_device *curdev, struct clock_event_device *newdev); extern void tick_install_replacement(struct clock_event_device *dev); @@ -43,6 +44,7 @@ extern int __clockevents_update_freq(struct clock_event_device *dev, u32 freq); extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt); #else static inline void tick_suspend(void) { } +static inline void tick_resume(void) { } #endif /* GENERIC_CLOCKEVENTS */ /* Oneshot related functions */ @@ -81,7 +83,8 @@ extern int tick_is_broadcast_device(struct clock_event_device *dev); extern void tick_broadcast_on_off(unsigned long reason, int *oncpu); extern void tick_shutdown_broadcast(unsigned int *cpup); extern void tick_suspend_broadcast(void); -extern int tick_resume_broadcast(void); +extern void tick_resume_broadcast(void); +extern bool tick_resume_check_broadcast(void); extern void tick_broadcast_init(void); extern void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast); extern int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq); @@ -95,7 +98,8 @@ static inline void tick_do_periodic_broadcast(struct clock_event_device *d) { } static inline void tick_broadcast_on_off(unsigned long reason, int *oncpu) { } static inline void tick_shutdown_broadcast(unsigned int *cpup) { } static inline void tick_suspend_broadcast(void) { } -static inline int tick_resume_broadcast(void) { return 0; } +static inline void tick_resume_broadcast(void) { } +static inline bool tick_resume_check_broadcast(void) { return false; } static inline void tick_broadcast_init(void) { } static inline int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq) { return -ENODEV; } -- cgit v1.2.3 From 7270d11c56f594af4d166b2988421cd8ed933dc1 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 25 Mar 2015 13:11:52 +0100 Subject: arm/bL_switcher: Kill tick suspend hackery Use the new tick_suspend/resume_local() and get rid of the homebrewn implementation of these in the ARM bL switcher. The check for the cpumask is completely pointless. There is no harm to suspend a per cpu tick device unconditionally. If that's a real issue then we fix it proper at the core level and not with some completely undocumented hacks in some random core code. Move the tick internals to the core code, now that this nuisance is gone. Signed-off-by: Thomas Gleixner [ rjw: Rebase, changelog ] Signed-off-by: Rafael J. Wysocki Cc: Nicolas Pitre Cc: Peter Zijlstra Cc: Russell King Link: http://lkml.kernel.org/r/1655112.Ws17YsMfN7@vostro.rjw.lan Signed-off-by: Ingo Molnar --- arch/arm/common/bL_switcher.c | 16 ++-------------- include/linux/clockchips.h | 6 ------ include/linux/tick.h | 19 ++++--------------- kernel/time/tick-common.c | 2 +- kernel/time/tick-internal.h | 5 +++++ kernel/time/tick-sched.h | 10 ++++++++++ 6 files changed, 22 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/arch/arm/common/bL_switcher.c b/arch/arm/common/bL_switcher.c index d4f970a4d255..37dc0fe1093f 100644 --- a/arch/arm/common/bL_switcher.c +++ b/arch/arm/common/bL_switcher.c @@ -151,8 +151,6 @@ static int bL_switch_to(unsigned int new_cluster_id) unsigned int mpidr, this_cpu, that_cpu; unsigned int ob_mpidr, ob_cpu, ob_cluster, ib_mpidr, ib_cpu, ib_cluster; struct completion inbound_alive; - struct tick_device *tdev; - enum clock_event_state tdev_state; long volatile *handshake_ptr; int ipi_nr, ret; @@ -219,13 +217,7 @@ static int bL_switch_to(unsigned int new_cluster_id) /* redirect GIC's SGIs to our counterpart */ gic_migrate_target(bL_gic_id[ib_cpu][ib_cluster]); - tdev = tick_get_device(this_cpu); - if (tdev && !cpumask_equal(tdev->evtdev->cpumask, cpumask_of(this_cpu))) - tdev = NULL; - if (tdev) { - tdev_state = tdev->evtdev->state; - clockevents_set_state(tdev->evtdev, CLOCK_EVT_STATE_SHUTDOWN); - } + tick_suspend_local(); ret = cpu_pm_enter(); @@ -251,11 +243,7 @@ static int bL_switch_to(unsigned int new_cluster_id) ret = cpu_pm_exit(); - if (tdev) { - clockevents_set_state(tdev->evtdev, tdev_state); - clockevents_program_event(tdev->evtdev, - tdev->evtdev->next_event, 1); - } + tick_resume_local(); trace_cpu_migrate_finish(ktime_get_real_ns(), ib_mpidr); local_fiq_enable(); diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 50ce9750754f..3ac7e2d90374 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -198,12 +198,6 @@ clockevents_calc_mult_shift(struct clock_event_device *ce, u32 freq, u32 minsec) freq, minsec); } -/* Should be core only, but is abused by arm bl_switcher */ -extern void clockevents_set_state(struct clock_event_device *dev, - enum clock_event_state state); -extern int clockevents_program_event(struct clock_event_device *dev, - ktime_t expires, bool force); - extern void clockevents_suspend(void); extern void clockevents_resume(void); diff --git a/include/linux/tick.h b/include/linux/tick.h index a3d4d2840e7f..589868b09aff 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -11,30 +11,19 @@ #include #include -/* ARM BL switcher abuse support */ -#ifdef CONFIG_GENERIC_CLOCKEVENTS -enum tick_device_mode { - TICKDEV_MODE_PERIODIC, - TICKDEV_MODE_ONESHOT, -}; - -struct tick_device { - struct clock_event_device *evtdev; - enum tick_device_mode mode; -}; -extern struct tick_device *tick_get_device(int cpu); -#endif - #ifdef CONFIG_GENERIC_CLOCKEVENTS extern void __init tick_init(void); extern void tick_freeze(void); extern void tick_unfreeze(void); -/* Should be core only, but XEN resume magic requires this */ +/* Should be core only, but ARM BL switcher requires it */ +extern void tick_suspend_local(void); +/* Should be core only, but XEN resume magic and ARM BL switcher require it */ extern void tick_resume_local(void); #else /* CONFIG_GENERIC_CLOCKEVENTS */ static inline void tick_init(void) { } static inline void tick_freeze(void) { } static inline void tick_unfreeze(void) { } +static inline void tick_suspend_local(void) { } static inline void tick_resume_local(void) { } #endif /* !CONFIG_GENERIC_CLOCKEVENTS */ diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index da796d65d1fb..e28ba5c044c5 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -380,7 +380,7 @@ void tick_shutdown(unsigned int *cpup) * * No locks required. Nothing can change the per cpu device. */ -static void tick_suspend_local(void) +void tick_suspend_local(void) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 6ba7bce732f2..5fc2dafabd58 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -28,6 +28,7 @@ extern bool tick_check_replacement(struct clock_event_device *curdev, struct clock_event_device *newdev); extern void tick_install_replacement(struct clock_event_device *dev); extern int tick_is_oneshot_available(void); +extern struct tick_device *tick_get_device(int cpu); extern int clockevents_tick_resume(struct clock_event_device *dev); /* Check, if the device is functional or a dummy for broadcast */ @@ -39,6 +40,10 @@ static inline int tick_device_is_functional(struct clock_event_device *dev) extern void clockevents_shutdown(struct clock_event_device *dev); extern void clockevents_exchange_device(struct clock_event_device *old, struct clock_event_device *new); +extern void clockevents_set_state(struct clock_event_device *dev, + enum clock_event_state state); +extern int clockevents_program_event(struct clock_event_device *dev, + ktime_t expires, bool force); extern void clockevents_handle_noop(struct clock_event_device *dev); extern int __clockevents_update_freq(struct clock_event_device *dev, u32 freq); extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt); diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index 930743249127..28b5da3e1a17 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -3,6 +3,16 @@ #include +enum tick_device_mode { + TICKDEV_MODE_PERIODIC, + TICKDEV_MODE_ONESHOT, +}; + +struct tick_device { + struct clock_event_device *evtdev; + enum tick_device_mode mode; +}; + enum tick_nohz_mode { NOHZ_MODE_INACTIVE, NOHZ_MODE_LOWRES, -- cgit v1.2.3 From 9eed56e889d8a0bb7870e1216d8d4326dd63ec50 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 2 Apr 2015 11:26:23 +0200 Subject: clockevents: Clean up clockchips.h Do various cleanups on the clockchips.h file: - indent preprocessor blocks to make it more clear which block we are in, this also makes merge resolution easier - comment larger preprocessor blocks consistently, using the: #if FOO ... #else /* !FOO: */ ... #endif /* !FOO */ notation. - unbreak lines - etc. No change in functionality. Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/clockchips.h | 87 ++++++++++++++++++++++------------------------ 1 file changed, 41 insertions(+), 46 deletions(-) (limited to 'include') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 3ac7e2d90374..caeca76d7b32 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -22,17 +22,17 @@ enum clock_event_nofitiers { #ifdef CONFIG_GENERIC_CLOCKEVENTS -#include -#include -#include -#include +# include +# include +# include +# include struct clock_event_device; struct module; /* Clock event mode commands for legacy ->set_mode(): OBSOLETE */ enum clock_event_mode { - CLOCK_EVT_MODE_UNUSED = 0, + CLOCK_EVT_MODE_UNUSED, CLOCK_EVT_MODE_SHUTDOWN, CLOCK_EVT_MODE_PERIODIC, CLOCK_EVT_MODE_ONESHOT, @@ -51,7 +51,7 @@ enum clock_event_mode { * from DETACHED or SHUTDOWN. */ enum clock_event_state { - CLOCK_EVT_STATE_DETACHED = 0, + CLOCK_EVT_STATE_DETACHED, CLOCK_EVT_STATE_SHUTDOWN, CLOCK_EVT_STATE_PERIODIC, CLOCK_EVT_STATE_ONESHOT, @@ -60,28 +60,29 @@ enum clock_event_state { /* * Clock event features */ -#define CLOCK_EVT_FEAT_PERIODIC 0x000001 -#define CLOCK_EVT_FEAT_ONESHOT 0x000002 -#define CLOCK_EVT_FEAT_KTIME 0x000004 +# define CLOCK_EVT_FEAT_PERIODIC 0x000001 +# define CLOCK_EVT_FEAT_ONESHOT 0x000002 +# define CLOCK_EVT_FEAT_KTIME 0x000004 + /* - * x86(64) specific misfeatures: + * x86(64) specific (mis)features: * * - Clockevent source stops in C3 State and needs broadcast support. * - Local APIC timer is used as a dummy device. */ -#define CLOCK_EVT_FEAT_C3STOP 0x000008 -#define CLOCK_EVT_FEAT_DUMMY 0x000010 +# define CLOCK_EVT_FEAT_C3STOP 0x000008 +# define CLOCK_EVT_FEAT_DUMMY 0x000010 /* * Core shall set the interrupt affinity dynamically in broadcast mode */ -#define CLOCK_EVT_FEAT_DYNIRQ 0x000020 -#define CLOCK_EVT_FEAT_PERCPU 0x000040 +# define CLOCK_EVT_FEAT_DYNIRQ 0x000020 +# define CLOCK_EVT_FEAT_PERCPU 0x000040 /* * Clockevent device is based on a hrtimer for broadcast */ -#define CLOCK_EVT_FEAT_HRTIMER 0x000080 +# define CLOCK_EVT_FEAT_HRTIMER 0x000080 /** * struct clock_event_device - clock event device descriptor @@ -116,10 +117,8 @@ enum clock_event_state { */ struct clock_event_device { void (*event_handler)(struct clock_event_device *); - int (*set_next_event)(unsigned long evt, - struct clock_event_device *); - int (*set_next_ktime)(ktime_t expires, - struct clock_event_device *); + int (*set_next_event)(unsigned long evt, struct clock_event_device *); + int (*set_next_ktime)(ktime_t expires, struct clock_event_device *); ktime_t next_event; u64 max_delta_ns; u64 min_delta_ns; @@ -136,8 +135,7 @@ struct clock_event_device { * - set_mode(), only for modes <= CLOCK_EVT_MODE_RESUME. * - set_state_{shutdown|periodic|oneshot}(), tick_resume(). */ - void (*set_mode)(enum clock_event_mode mode, - struct clock_event_device *); + void (*set_mode)(enum clock_event_mode mode, struct clock_event_device *); int (*set_state_periodic)(struct clock_event_device *); int (*set_state_oneshot)(struct clock_event_device *); int (*set_state_shutdown)(struct clock_event_device *); @@ -169,18 +167,18 @@ struct clock_event_device { * * factor = (clock_ticks << shift) / nanoseconds */ -static inline unsigned long div_sc(unsigned long ticks, unsigned long nsec, - int shift) +static inline unsigned long +div_sc(unsigned long ticks, unsigned long nsec, int shift) { - uint64_t tmp = ((uint64_t)ticks) << shift; + u64 tmp = ((u64)ticks) << shift; do_div(tmp, nsec); + return (unsigned long) tmp; } /* Clock event layer functions */ -extern u64 clockevent_delta2ns(unsigned long latch, - struct clock_event_device *evt); +extern u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt); extern void clockevents_register_device(struct clock_event_device *dev); extern int clockevents_unbind_device(struct clock_event_device *ced, int cpu); @@ -194,42 +192,39 @@ extern int clockevents_update_freq(struct clock_event_device *ce, u32 freq); static inline void clockevents_calc_mult_shift(struct clock_event_device *ce, u32 freq, u32 minsec) { - return clocks_calc_mult_shift(&ce->mult, &ce->shift, NSEC_PER_SEC, - freq, minsec); + return clocks_calc_mult_shift(&ce->mult, &ce->shift, NSEC_PER_SEC, freq, minsec); } extern void clockevents_suspend(void); extern void clockevents_resume(void); -#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST -#ifdef CONFIG_ARCH_HAS_TICK_BROADCAST +# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +# ifdef CONFIG_ARCH_HAS_TICK_BROADCAST extern void tick_broadcast(const struct cpumask *mask); -#else -#define tick_broadcast NULL -#endif +# else +# define tick_broadcast NULL +# endif extern int tick_receive_broadcast(void); -#endif +# endif -#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT) +# if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT) extern void tick_setup_hrtimer_broadcast(void); extern int tick_check_broadcast_expired(void); -#else +# else static inline int tick_check_broadcast_expired(void) { return 0; } -static inline void tick_setup_hrtimer_broadcast(void) {}; -#endif +static inline void tick_setup_hrtimer_broadcast(void) { } +# endif extern int clockevents_notify(unsigned long reason, void *arg); -#else /* CONFIG_GENERIC_CLOCKEVENTS */ - -static inline void clockevents_suspend(void) {} -static inline void clockevents_resume(void) {} +#else /* !CONFIG_GENERIC_CLOCKEVENTS: */ +static inline void clockevents_suspend(void) { } +static inline void clockevents_resume(void) { } static inline int clockevents_notify(unsigned long reason, void *arg) { return 0; } static inline int tick_check_broadcast_expired(void) { return 0; } -static inline void tick_setup_hrtimer_broadcast(void) {}; -static inline int clockevents_notify(unsigned long reason, void *arg) { return 0; } +static inline void tick_setup_hrtimer_broadcast(void) { } -#endif +#endif /* !CONFIG_GENERIC_CLOCKEVENTS */ -#endif +#endif /* _LINUX_CLOCKCHIPS_H */ -- cgit v1.2.3 From 345527b1edce8df719e0884500c76832a18211c3 Mon Sep 17 00:00:00 2001 From: Preeti U Murthy Date: Mon, 30 Mar 2015 14:59:19 +0530 Subject: clockevents: Fix cpu_down() race for hrtimer based broadcasting It was found when doing a hotplug stress test on POWER, that the machine either hit softlockups or rcu_sched stall warnings. The issue was traced to commit: 7cba160ad789 ("powernv/cpuidle: Redesign idle states management") which exposed the cpu_down() race with hrtimer based broadcast mode: 5d1638acb9f6 ("tick: Introduce hrtimer based broadcast") The race is the following: Assume CPU1 is the CPU which holds the hrtimer broadcasting duty before it is taken down. CPU0 CPU1 cpu_down() take_cpu_down() disable_interrupts() cpu_die() while (CPU1 != CPU_DEAD) { msleep(100); switch_to_idle(); stop_cpu_timer(); schedule_broadcast(); } tick_cleanup_cpu_dead() take_over_broadcast() So after CPU1 disabled interrupts it cannot handle the broadcast hrtimer anymore, so CPU0 will be stuck forever. Fix this by explicitly taking over broadcast duty before cpu_die(). This is a temporary workaround. What we really want is a callback in the clockevent device which allows us to do that from the dying CPU by pushing the hrtimer onto a different cpu. That might involve an IPI and is definitely more complex than this immediate fix. Changelog was picked up from: https://lkml.org/lkml/2015/2/16/213 Suggested-by: Thomas Gleixner Tested-by: Nicolas Pitre Signed-off-by: Preeti U. Murthy Cc: linuxppc-dev@lists.ozlabs.org Cc: mpe@ellerman.id.au Cc: nicolas.pitre@linaro.org Cc: peterz@infradead.org Cc: rjw@rjwysocki.net Fixes: http://linuxppc.10917.n7.nabble.com/offlining-cpus-breakage-td88619.html Link: http://lkml.kernel.org/r/20150330092410.24979.59887.stgit@preeti.in.ibm.com [ Merged it to the latest timer tree, renamed the callback, tidied up the changelog. ] Signed-off-by: Ingo Molnar --- include/linux/tick.h | 6 ++++++ kernel/cpu.c | 2 ++ kernel/time/tick-broadcast.c | 19 +++++++++++-------- 3 files changed, 19 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/tick.h b/include/linux/tick.h index 589868b09aff..f9ff225d53c0 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -36,6 +36,12 @@ extern void tick_irq_enter(void); static inline void tick_irq_enter(void) { } #endif +#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT) +extern void hotplug_cpu__broadcast_tick_pull(int dead_cpu); +#else +static inline void hotplug_cpu__broadcast_tick_pull(int dead_cpu) { } +#endif + #ifdef CONFIG_NO_HZ_COMMON extern int tick_nohz_tick_stopped(void); extern void tick_nohz_idle_enter(void); diff --git a/kernel/cpu.c b/kernel/cpu.c index 1972b161c61e..af5db20e5803 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include "smpboot.h" @@ -411,6 +412,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) while (!idle_cpu(cpu)) cpu_relax(); + hotplug_cpu__broadcast_tick_pull(cpu); /* This actually kills the CPU. */ __cpu_die(cpu); diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 19cfb381faa9..f5e0fd5652dc 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -680,14 +680,19 @@ static void broadcast_shutdown_local(struct clock_event_device *bc, clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN); } -static void broadcast_move_bc(int deadcpu) +void hotplug_cpu__broadcast_tick_pull(int deadcpu) { - struct clock_event_device *bc = tick_broadcast_device.evtdev; + struct clock_event_device *bc; + unsigned long flags; - if (!bc || !broadcast_needs_cpu(bc, deadcpu)) - return; - /* This moves the broadcast assignment to this cpu */ - clockevents_program_event(bc, bc->next_event, 1); + raw_spin_lock_irqsave(&tick_broadcast_lock, flags); + bc = tick_broadcast_device.evtdev; + + if (bc && broadcast_needs_cpu(bc, deadcpu)) { + /* This moves the broadcast assignment to this CPU: */ + clockevents_program_event(bc, bc->next_event, 1); + } + raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } /* @@ -924,8 +929,6 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup) cpumask_clear_cpu(cpu, tick_broadcast_pending_mask); cpumask_clear_cpu(cpu, tick_broadcast_force_mask); - broadcast_move_bc(cpu); - raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } -- cgit v1.2.3 From 9a806ddbb9a18c510e4acdcc828b9a87f5fd3aef Mon Sep 17 00:00:00 2001 From: Xunlei Pang Date: Wed, 1 Apr 2015 20:34:21 -0700 Subject: time: Add y2038 safe read_boot_clock64() As part of addressing in-kernel y2038 issues, this patch adds read_boot_clock64() and replaces all the call sites of read_boot_clock() with this function. This is a __weak implementation, which simply calls the existing y2038 unsafe read_boot_clock(). This allows architecture specific implementations to be converted independently, and eventually the y2038 unsafe read_boot_clock() can be removed after all its architecture specific implementations have been converted to read_boot_clock64(). Suggested-by: Arnd Bergmann Signed-off-by: Xunlei Pang Signed-off-by: John Stultz Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1427945681-29972-2-git-send-email-john.stultz@linaro.org Signed-off-by: Ingo Molnar --- include/linux/timekeeping.h | 1 + kernel/time/timekeeping.c | 11 +++++++++-- 2 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 5047b83483d6..18d27a3f72ca 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -269,6 +269,7 @@ static inline bool has_persistent_clock(void) extern void read_persistent_clock(struct timespec *ts); extern void read_boot_clock(struct timespec *ts); +extern void read_boot_clock64(struct timespec64 *ts); extern int update_persistent_clock(struct timespec now); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 5b12292b343a..652e50a9c6ed 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1188,6 +1188,14 @@ void __weak read_boot_clock(struct timespec *ts) ts->tv_nsec = 0; } +void __weak read_boot_clock64(struct timespec64 *ts64) +{ + struct timespec ts; + + read_boot_clock(&ts); + *ts64 = timespec_to_timespec64(ts); +} + /* * timekeeping_init - Initializes the clocksource and common timekeeping values */ @@ -1209,8 +1217,7 @@ void __init timekeeping_init(void) } else if (now.tv_sec || now.tv_nsec) persistent_clock_exist = true; - read_boot_clock(&ts); - boot = timespec_to_timespec64(ts); + read_boot_clock64(&boot); if (!timespec64_valid_strict(&boot)) { pr_warn("WARNING: Boot clock returned invalid value!\n" " Check your CMOS/BIOS settings.\n"); -- cgit v1.2.3 From 2ee966320028ac846654eba5344540eeb4dc228d Mon Sep 17 00:00:00 2001 From: Xunlei Pang Date: Wed, 1 Apr 2015 20:34:22 -0700 Subject: time: Add y2038 safe read_persistent_clock64() As part of addressing in-kernel y2038 issues, this patch adds read_persistent_clock64() and replaces all the call sites of read_persistent_clock() with this function. This is a __weak implementation, which simply calls the existing y2038 unsafe read_persistent_clock(). This allows architecture specific implementations to be converted independently, and eventually the y2038 unsafe read_persistent_clock() can be removed after all its architecture specific implementations have been converted to read_persistent_clock64(). Suggested-by: Arnd Bergmann Signed-off-by: Xunlei Pang Signed-off-by: John Stultz Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1427945681-29972-3-git-send-email-john.stultz@linaro.org Signed-off-by: Ingo Molnar --- arch/mips/lasat/sysctl.c | 4 ++-- include/linux/timekeeping.h | 1 + kernel/time/timekeeping.c | 22 ++++++++++++---------- 3 files changed, 15 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/arch/mips/lasat/sysctl.c b/arch/mips/lasat/sysctl.c index 3b7f65cc4218..cf9b4633257e 100644 --- a/arch/mips/lasat/sysctl.c +++ b/arch/mips/lasat/sysctl.c @@ -75,11 +75,11 @@ static int rtctmp; int proc_dolasatrtc(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct timespec ts; + struct timespec64 ts; int r; if (!write) { - read_persistent_clock(&ts); + read_persistent_clock64(&ts); rtctmp = ts.tv_sec; /* check for time < 0 and set to 0 */ if (rtctmp < 0) diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 18d27a3f72ca..4c0f76f4616c 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -268,6 +268,7 @@ static inline bool has_persistent_clock(void) } extern void read_persistent_clock(struct timespec *ts); +extern void read_persistent_clock64(struct timespec64 *ts); extern void read_boot_clock(struct timespec *ts); extern void read_boot_clock64(struct timespec64 *ts); extern int update_persistent_clock(struct timespec now); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 652e50a9c6ed..b1dbfa573dce 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1173,6 +1173,14 @@ void __weak read_persistent_clock(struct timespec *ts) ts->tv_nsec = 0; } +void __weak read_persistent_clock64(struct timespec64 *ts64) +{ + struct timespec ts; + + read_persistent_clock(&ts); + *ts64 = timespec_to_timespec64(ts); +} + /** * read_boot_clock - Return time of the system start. * @@ -1205,10 +1213,8 @@ void __init timekeeping_init(void) struct clocksource *clock; unsigned long flags; struct timespec64 now, boot, tmp; - struct timespec ts; - read_persistent_clock(&ts); - now = timespec_to_timespec64(ts); + read_persistent_clock64(&now); if (!timespec64_valid_strict(&now)) { pr_warn("WARNING: Persistent clock returned invalid value!\n" " Check your CMOS/BIOS settings.\n"); @@ -1278,7 +1284,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, * timekeeping_inject_sleeptime64 - Adds suspend interval to timeekeeping values * @delta: pointer to a timespec64 delta value * - * This hook is for architectures that cannot support read_persistent_clock + * This hook is for architectures that cannot support read_persistent_clock64 * because their RTC/persistent clock is only accessible when irqs are enabled. * * This function should only be called by rtc_resume(), and allows @@ -1325,12 +1331,10 @@ void timekeeping_resume(void) struct clocksource *clock = tk->tkr_mono.clock; unsigned long flags; struct timespec64 ts_new, ts_delta; - struct timespec tmp; cycle_t cycle_now, cycle_delta; bool suspendtime_found = false; - read_persistent_clock(&tmp); - ts_new = timespec_to_timespec64(tmp); + read_persistent_clock64(&ts_new); clockevents_resume(); clocksource_resume(); @@ -1406,10 +1410,8 @@ int timekeeping_suspend(void) unsigned long flags; struct timespec64 delta, delta_delta; static struct timespec64 old_delta; - struct timespec tmp; - read_persistent_clock(&tmp); - timekeeping_suspend_time = timespec_to_timespec64(tmp); + read_persistent_clock64(&timekeeping_suspend_time); /* * On some systems the persistent_clock can not be detected at -- cgit v1.2.3 From 3c00a1fe8496ff29ab62764bb3f4ce4b48089004 Mon Sep 17 00:00:00 2001 From: Xunlei Pang Date: Wed, 1 Apr 2015 20:34:23 -0700 Subject: time: Add y2038 safe update_persistent_clock64() As part of addressing in-kernel y2038 issues, this patch adds update_persistent_clock64() and replaces all the call sites of update_persistent_clock() with this function. This is a __weak implementation, which simply calls the existing y2038 unsafe update_persistent_clock(). This allows architecture specific implementations to be converted independently, and eventually y2038-unsafe update_persistent_clock() can be removed after all its architecture specific implementations have been converted to update_persistent_clock64(). Suggested-by: Arnd Bergmann Signed-off-by: Xunlei Pang Signed-off-by: John Stultz Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1427945681-29972-4-git-send-email-john.stultz@linaro.org Signed-off-by: Ingo Molnar --- drivers/rtc/systohc.c | 2 +- include/linux/timekeeping.h | 1 + kernel/time/ntp.c | 13 ++++++++++++- 3 files changed, 14 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/rtc/systohc.c b/drivers/rtc/systohc.c index eb71872d0361..ef3c07a52c3a 100644 --- a/drivers/rtc/systohc.c +++ b/drivers/rtc/systohc.c @@ -11,7 +11,7 @@ * rtc_set_ntp_time - Save NTP synchronized time to the RTC * @now: Current time of day * - * Replacement for the NTP platform function update_persistent_clock + * Replacement for the NTP platform function update_persistent_clock64 * that stores time for later retrieval by rtc_hctosys. * * Returns 0 on successful RTC update, -ENODEV if a RTC update is not diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 4c0f76f4616c..7a2369d5b3f4 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -272,6 +272,7 @@ extern void read_persistent_clock64(struct timespec64 *ts); extern void read_boot_clock(struct timespec *ts); extern void read_boot_clock64(struct timespec64 *ts); extern int update_persistent_clock(struct timespec now); +extern int update_persistent_clock64(struct timespec64 now); #endif diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 9ad60d028508..7a681003001c 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -458,6 +458,16 @@ out: return leap; } +#ifdef CONFIG_GENERIC_CMOS_UPDATE +int __weak update_persistent_clock64(struct timespec64 now64) +{ + struct timespec now; + + now = timespec64_to_timespec(now64); + return update_persistent_clock(now); +} +#endif + #if defined(CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC) static void sync_cmos_clock(struct work_struct *work); @@ -493,8 +503,9 @@ static void sync_cmos_clock(struct work_struct *work) if (persistent_clock_is_local) adjust.tv_sec -= (sys_tz.tz_minuteswest * 60); #ifdef CONFIG_GENERIC_CMOS_UPDATE - fail = update_persistent_clock(timespec64_to_timespec(adjust)); + fail = update_persistent_clock64(adjust); #endif + #ifdef CONFIG_RTC_SYSTOHC if (fail == -ENODEV) fail = rtc_set_ntp_time(adjust); -- cgit v1.2.3 From 8e4ff1a81aa91d12856287c7103d0301ac91351a Mon Sep 17 00:00:00 2001 From: Xunlei Pang Date: Wed, 1 Apr 2015 20:34:27 -0700 Subject: drivers/rtc: Provide y2038 safe rtc_class_ops.set_mmss() replacement Currently the rtc_class_op's set_mmss() function takes a 32-bit second value (on 32-bit systems), which is problematic for dates past y2038. This patch provides a safe version named set_mmss64() using y2038 safe time64_t. After this patch, set_mmss() is deprecated and all its users will be fixed to use set_mmss64(), it can be removed when having no users. Signed-off-by: Xunlei Pang [jstultz: Add whitespace fix for checkpatch] Signed-off-by: John Stultz Acked-by: Alessandro Zummo Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1427945681-29972-8-git-send-email-john.stultz@linaro.org Signed-off-by: Ingo Molnar --- drivers/rtc/interface.c | 8 +++++++- drivers/rtc/systohc.c | 5 ++++- include/linux/rtc.h | 1 + 3 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index 37215cf983e9..d43ee409a5f2 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -72,7 +72,11 @@ int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm) err = -ENODEV; else if (rtc->ops->set_time) err = rtc->ops->set_time(rtc->dev.parent, tm); - else if (rtc->ops->set_mmss) { + else if (rtc->ops->set_mmss64) { + time64_t secs64 = rtc_tm_to_time64(tm); + + err = rtc->ops->set_mmss64(rtc->dev.parent, secs64); + } else if (rtc->ops->set_mmss) { time64_t secs64 = rtc_tm_to_time64(tm); err = rtc->ops->set_mmss(rtc->dev.parent, secs64); } else @@ -96,6 +100,8 @@ int rtc_set_mmss(struct rtc_device *rtc, unsigned long secs) if (!rtc->ops) err = -ENODEV; + else if (rtc->ops->set_mmss64) + err = rtc->ops->set_mmss64(rtc->dev.parent, secs); else if (rtc->ops->set_mmss) err = rtc->ops->set_mmss(rtc->dev.parent, secs); else if (rtc->ops->read_time && rtc->ops->set_time) { diff --git a/drivers/rtc/systohc.c b/drivers/rtc/systohc.c index ef3c07a52c3a..7728d5e32bf4 100644 --- a/drivers/rtc/systohc.c +++ b/drivers/rtc/systohc.c @@ -35,7 +35,10 @@ int rtc_set_ntp_time(struct timespec64 now) if (rtc) { /* rtc_hctosys exclusively uses UTC, so we call set_time here, * not set_mmss. */ - if (rtc->ops && (rtc->ops->set_time || rtc->ops->set_mmss)) + if (rtc->ops && + (rtc->ops->set_time || + rtc->ops->set_mmss64 || + rtc->ops->set_mmss)) err = rtc_set_time(rtc, &tm); rtc_class_close(rtc); } diff --git a/include/linux/rtc.h b/include/linux/rtc.h index dcad7ee0d746..8dcf6825fa88 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -77,6 +77,7 @@ struct rtc_class_ops { int (*read_alarm)(struct device *, struct rtc_wkalrm *); int (*set_alarm)(struct device *, struct rtc_wkalrm *); int (*proc)(struct device *, struct seq_file *); + int (*set_mmss64)(struct device *, time64_t secs); int (*set_mmss)(struct device *, unsigned long secs); int (*read_callback)(struct device *, int data); int (*alarm_irq_enable)(struct device *, unsigned int enabled); -- cgit v1.2.3 From 0fa88cb4b82b5cf7429bc1cef9db006ca035754e Mon Sep 17 00:00:00 2001 From: Xunlei Pang Date: Wed, 1 Apr 2015 20:34:38 -0700 Subject: time, drivers/rtc: Don't bother with rtc_resume() for the nonstop clocksource If a system does not provide a persistent_clock(), the time will be updated on resume by rtc_resume(). With the addition of the non-stop clocksources for suspend timing, those systems set the time on resume in timekeeping_resume(), but may not provide a valid persistent_clock(). This results in the rtc_resume() logic thinking no one has set the time and it then will over-write the suspend time again, which is not necessary and only increases clock error. So, fix this for rtc_resume(). This patch also improves the name of persistent_clock_exist to make it more grammatical. Signed-off-by: Xunlei Pang Signed-off-by: John Stultz Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1427945681-29972-19-git-send-email-john.stultz@linaro.org Signed-off-by: Ingo Molnar --- drivers/rtc/class.c | 4 +-- include/linux/timekeeping.h | 9 +++---- kernel/time/timekeeping.c | 66 +++++++++++++++++++++++++++++++++------------ 3 files changed, 54 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index d40760aa4553..c29ba7e14304 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -55,7 +55,7 @@ static int rtc_suspend(struct device *dev) struct timespec64 delta, delta_delta; int err; - if (has_persistent_clock()) + if (timekeeping_rtc_skipsuspend()) return 0; if (strcmp(dev_name(&rtc->dev), CONFIG_RTC_HCTOSYS_DEVICE) != 0) @@ -102,7 +102,7 @@ static int rtc_resume(struct device *dev) struct timespec64 sleep_time; int err; - if (has_persistent_clock()) + if (timekeeping_rtc_skipresume()) return 0; rtc_hctosys_ret = -ENODEV; diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 7a2369d5b3f4..99176af216af 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -248,6 +248,9 @@ static inline void timekeeping_clocktai(struct timespec *ts) /* * RTC specific */ +extern bool timekeeping_rtc_skipsuspend(void); +extern bool timekeeping_rtc_skipresume(void); + extern void timekeeping_inject_sleeptime64(struct timespec64 *delta); /* @@ -259,14 +262,8 @@ extern void getnstime_raw_and_real(struct timespec *ts_raw, /* * Persistent clock related interfaces */ -extern bool persistent_clock_exist; extern int persistent_clock_is_local; -static inline bool has_persistent_clock(void) -{ - return persistent_clock_exist; -} - extern void read_persistent_clock(struct timespec *ts); extern void read_persistent_clock64(struct timespec64 *ts); extern void read_boot_clock(struct timespec *ts); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index b7db4916415b..79b9bc6e7876 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -64,9 +64,6 @@ static struct tk_fast tk_fast_raw ____cacheline_aligned; /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; -/* Flag for if there is a persistent clock on this platform */ -bool __read_mostly persistent_clock_exist = false; - static inline void tk_normalize_xtime(struct timekeeper *tk) { while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) { @@ -1204,6 +1201,12 @@ void __weak read_boot_clock64(struct timespec64 *ts64) *ts64 = timespec_to_timespec64(ts); } +/* Flag for if timekeeping_resume() has injected sleeptime */ +static bool sleeptime_injected; + +/* Flag for if there is a persistent clock on this platform */ +static bool persistent_clock_exists; + /* * timekeeping_init - Initializes the clocksource and common timekeeping values */ @@ -1221,7 +1224,7 @@ void __init timekeeping_init(void) now.tv_sec = 0; now.tv_nsec = 0; } else if (now.tv_sec || now.tv_nsec) - persistent_clock_exist = true; + persistent_clock_exists = true; read_boot_clock64(&boot); if (!timespec64_valid_strict(&boot)) { @@ -1281,12 +1284,48 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, } #if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE) +/** + * We have three kinds of time sources to use for sleep time + * injection, the preference order is: + * 1) non-stop clocksource + * 2) persistent clock (ie: RTC accessible when irqs are off) + * 3) RTC + * + * 1) and 2) are used by timekeeping, 3) by RTC subsystem. + * If system has neither 1) nor 2), 3) will be used finally. + * + * + * If timekeeping has injected sleeptime via either 1) or 2), + * 3) becomes needless, so in this case we don't need to call + * rtc_resume(), and this is what timekeeping_rtc_skipresume() + * means. + */ +bool timekeeping_rtc_skipresume(void) +{ + return sleeptime_injected; +} + +/** + * 1) can be determined whether to use or not only when doing + * timekeeping_resume() which is invoked after rtc_suspend(), + * so we can't skip rtc_suspend() surely if system has 1). + * + * But if system has 2), 2) will definitely be used, so in this + * case we don't need to call rtc_suspend(), and this is what + * timekeeping_rtc_skipsuspend() means. + */ +bool timekeeping_rtc_skipsuspend(void) +{ + return persistent_clock_exists; +} + /** * timekeeping_inject_sleeptime64 - Adds suspend interval to timeekeeping values * @delta: pointer to a timespec64 delta value * * This hook is for architectures that cannot support read_persistent_clock64 * because their RTC/persistent clock is only accessible when irqs are enabled. + * and also don't have an effective nonstop clocksource. * * This function should only be called by rtc_resume(), and allows * a suspend offset to be injected into the timekeeping values. @@ -1296,13 +1335,6 @@ void timekeeping_inject_sleeptime64(struct timespec64 *delta) struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; - /* - * Make sure we don't set the clock twice, as timekeeping_resume() - * already did it - */ - if (has_persistent_clock()) - return; - raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); @@ -1334,8 +1366,8 @@ void timekeeping_resume(void) unsigned long flags; struct timespec64 ts_new, ts_delta; cycle_t cycle_now, cycle_delta; - bool suspendtime_found = false; + sleeptime_injected = false; read_persistent_clock64(&ts_new); clockevents_resume(); @@ -1381,13 +1413,13 @@ void timekeeping_resume(void) nsec += ((u64) cycle_delta * mult) >> shift; ts_delta = ns_to_timespec64(nsec); - suspendtime_found = true; + sleeptime_injected = true; } else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) { ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time); - suspendtime_found = true; + sleeptime_injected = true; } - if (suspendtime_found) + if (sleeptime_injected) __timekeeping_inject_sleeptime(tk, &ts_delta); /* Re-base the last cycle value */ @@ -1421,14 +1453,14 @@ int timekeeping_suspend(void) * value returned, update the persistent_clock_exists flag. */ if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec) - persistent_clock_exist = true; + persistent_clock_exists = true; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); timekeeping_suspended = 1; - if (has_persistent_clock()) { + if (persistent_clock_exists) { /* * To avoid drift caused by repeated suspend/resumes, * which each can add ~1 second drift error, -- cgit v1.2.3 From 592a438ff3fea61d303c5784c209b3f1fd3e16df Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 3 Apr 2015 02:01:10 +0200 Subject: clockevents: Provide explicit broadcast control functions clockevents_notify() is a leftover from the early design of the clockevents facility. It's really not a notification mechanism, it's a multiplex call. We are way better off to have explicit calls instead of this monstrosity. Split out the broadcast control into a separate function and provide inline helpers. Switch clockevents_notify() over. This will go away once all callers are converted. This also gets rid of the nested locking of clockevents_lock and broadcast_lock. The broadcast control functions do not require clockevents_lock. Only the managing functions (setup/shutdown/suspend/resume of the broadcast device require clockevents_lock. Signed-off-by: Thomas Gleixner Signed-off-by: Rafael J. Wysocki Cc: Daniel Lezcano Cc: Len Brown Cc: Peter Zijlstra Cc: Tony Lindgren Link: http://lkml.kernel.org/r/8086559.ttsuS0n1Xr@vostro.rjw.lan Signed-off-by: Ingo Molnar --- include/linux/tick.h | 25 ++++++++++++++++++ kernel/time/clockevents.c | 6 ++++- kernel/time/tick-broadcast.c | 62 +++++++++++++++++++------------------------- kernel/time/tick-internal.h | 2 -- 4 files changed, 57 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/include/linux/tick.h b/include/linux/tick.h index f9ff225d53c0..4bb236357b03 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -42,6 +42,31 @@ extern void hotplug_cpu__broadcast_tick_pull(int dead_cpu); static inline void hotplug_cpu__broadcast_tick_pull(int dead_cpu) { } #endif +enum tick_broadcast_mode { + TICK_BROADCAST_OFF, + TICK_BROADCAST_ON, + TICK_BROADCAST_FORCE, +}; + +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +extern void tick_broadcast_control(enum tick_broadcast_mode mode); +#else +static inline void tick_broadcast_control(enum tick_broadcast_mode mode) { } +#endif /* BROADCAST */ + +static inline void tick_broadcast_enable(void) +{ + tick_broadcast_control(TICK_BROADCAST_ON); +} +static inline void tick_broadcast_disable(void) +{ + tick_broadcast_control(TICK_BROADCAST_OFF); +} +static inline void tick_broadcast_force(void) +{ + tick_broadcast_control(TICK_BROADCAST_FORCE); +} + #ifdef CONFIG_NO_HZ_COMMON extern int tick_nohz_tick_stopped(void); extern void tick_nohz_idle_enter(void); diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 7af614829da1..599ff8d3fda5 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -656,9 +656,13 @@ int clockevents_notify(unsigned long reason, void *arg) switch (reason) { case CLOCK_EVT_NOTIFY_BROADCAST_ON: + tick_broadcast_enable(); + break; case CLOCK_EVT_NOTIFY_BROADCAST_OFF: + tick_broadcast_disable(); + break; case CLOCK_EVT_NOTIFY_BROADCAST_FORCE: - tick_broadcast_on_off(reason, arg); + tick_broadcast_force(); break; case CLOCK_EVT_NOTIFY_BROADCAST_ENTER: diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index f5e0fd5652dc..1a0bee04ef8c 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -33,7 +33,7 @@ static cpumask_var_t tick_broadcast_mask; static cpumask_var_t tick_broadcast_on; static cpumask_var_t tmpmask; static DEFINE_RAW_SPINLOCK(tick_broadcast_lock); -static int tick_broadcast_force; +static int tick_broadcast_forced; #ifdef CONFIG_TICK_ONESHOT static void tick_broadcast_clear_oneshot(int cpu); @@ -326,49 +326,54 @@ unlock: raw_spin_unlock(&tick_broadcast_lock); } -/* - * Powerstate information: The system enters/leaves a state, where - * affected devices might stop +/** + * tick_broadcast_control - Enable/disable or force broadcast mode + * @mode: The selected broadcast mode + * + * Called when the system enters a state where affected tick devices + * might stop. Note: TICK_BROADCAST_FORCE cannot be undone. + * + * Called with interrupts disabled, so clockevents_lock is not + * required here because the local clock event device cannot go away + * under us. */ -static void tick_do_broadcast_on_off(unsigned long *reason) +void tick_broadcast_control(enum tick_broadcast_mode mode) { struct clock_event_device *bc, *dev; struct tick_device *td; - unsigned long flags; int cpu, bc_stopped; - raw_spin_lock_irqsave(&tick_broadcast_lock, flags); - - cpu = smp_processor_id(); - td = &per_cpu(tick_cpu_device, cpu); + td = this_cpu_ptr(&tick_cpu_device); dev = td->evtdev; - bc = tick_broadcast_device.evtdev; /* * Is the device not affected by the powerstate ? */ if (!dev || !(dev->features & CLOCK_EVT_FEAT_C3STOP)) - goto out; + return; if (!tick_device_is_functional(dev)) - goto out; + return; + raw_spin_lock(&tick_broadcast_lock); + cpu = smp_processor_id(); + bc = tick_broadcast_device.evtdev; bc_stopped = cpumask_empty(tick_broadcast_mask); - switch (*reason) { - case CLOCK_EVT_NOTIFY_BROADCAST_ON: - case CLOCK_EVT_NOTIFY_BROADCAST_FORCE: + switch (mode) { + case TICK_BROADCAST_FORCE: + tick_broadcast_forced = 1; + case TICK_BROADCAST_ON: cpumask_set_cpu(cpu, tick_broadcast_on); if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) { if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) clockevents_shutdown(dev); } - if (*reason == CLOCK_EVT_NOTIFY_BROADCAST_FORCE) - tick_broadcast_force = 1; break; - case CLOCK_EVT_NOTIFY_BROADCAST_OFF: - if (tick_broadcast_force) + + case TICK_BROADCAST_OFF: + if (tick_broadcast_forced) break; cpumask_clear_cpu(cpu, tick_broadcast_on); if (!tick_device_is_functional(dev)) @@ -390,22 +395,9 @@ static void tick_do_broadcast_on_off(unsigned long *reason) else tick_broadcast_setup_oneshot(bc); } -out: - raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); -} - -/* - * Powerstate information: The system enters/leaves a state, where - * affected devices might stop. - */ -void tick_broadcast_on_off(unsigned long reason, int *oncpu) -{ - if (!cpumask_test_cpu(*oncpu, cpu_online_mask)) - printk(KERN_ERR "tick-broadcast: ignoring broadcast for " - "offline CPU #%d\n", *oncpu); - else - tick_do_broadcast_on_off(&reason); + raw_spin_unlock(&tick_broadcast_lock); } +EXPORT_SYMBOL_GPL(tick_broadcast_control); /* * Set the periodic handler depending on broadcast on/off diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index b6ba0a44e740..62e331d1bc76 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -53,7 +53,6 @@ extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt); extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu); extern void tick_install_broadcast_device(struct clock_event_device *dev); extern int tick_is_broadcast_device(struct clock_event_device *dev); -extern void tick_broadcast_on_off(unsigned long reason, int *oncpu); extern void tick_shutdown_broadcast(unsigned int *cpup); extern void tick_suspend_broadcast(void); extern void tick_resume_broadcast(void); @@ -68,7 +67,6 @@ static inline void tick_install_broadcast_device(struct clock_event_device *dev) static inline int tick_is_broadcast_device(struct clock_event_device *dev) { return 0; } static inline int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) { return 0; } static inline void tick_do_periodic_broadcast(struct clock_event_device *d) { } -static inline void tick_broadcast_on_off(unsigned long reason, int *oncpu) { } static inline void tick_shutdown_broadcast(unsigned int *cpup) { } static inline void tick_suspend_broadcast(void) { } static inline void tick_resume_broadcast(void) { } -- cgit v1.2.3 From 89feddbfe7023ccfb4a6d7f5e3f5161d91b28b18 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 3 Apr 2015 02:03:42 +0200 Subject: clockevents: Remove the broadcast control leftovers All users converted. Remove the notify leftovers. Signed-off-by: Thomas Gleixner Signed-off-by: Rafael J. Wysocki Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/2076318.76XJZ8QYP3@vostro.rjw.lan Signed-off-by: Ingo Molnar --- include/linux/clockchips.h | 3 --- kernel/time/clockevents.c | 10 ---------- 2 files changed, 13 deletions(-) (limited to 'include') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index caeca76d7b32..438fafa75067 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -11,9 +11,6 @@ /* Clock event notification values */ enum clock_event_nofitiers { CLOCK_EVT_NOTIFY_ADD, - CLOCK_EVT_NOTIFY_BROADCAST_ON, - CLOCK_EVT_NOTIFY_BROADCAST_OFF, - CLOCK_EVT_NOTIFY_BROADCAST_FORCE, CLOCK_EVT_NOTIFY_BROADCAST_ENTER, CLOCK_EVT_NOTIFY_BROADCAST_EXIT, CLOCK_EVT_NOTIFY_CPU_DYING, diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 599ff8d3fda5..dba0b83708b3 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -655,16 +655,6 @@ int clockevents_notify(unsigned long reason, void *arg) raw_spin_lock_irqsave(&clockevents_lock, flags); switch (reason) { - case CLOCK_EVT_NOTIFY_BROADCAST_ON: - tick_broadcast_enable(); - break; - case CLOCK_EVT_NOTIFY_BROADCAST_OFF: - tick_broadcast_disable(); - break; - case CLOCK_EVT_NOTIFY_BROADCAST_FORCE: - tick_broadcast_force(); - break; - case CLOCK_EVT_NOTIFY_BROADCAST_ENTER: case CLOCK_EVT_NOTIFY_BROADCAST_EXIT: ret = tick_broadcast_oneshot_control(reason); -- cgit v1.2.3 From 1fe5d5c3c9ba0c4ade18e3325cba0ffe35127941 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 3 Apr 2015 02:05:15 +0200 Subject: clockevents: Provide explicit broadcast oneshot control functions clockevents_notify() is a leftover from the early design of the clockevents facility. It's really not a notification mechanism, it's a multiplex call. We are way better off to have explicit calls instead of this monstrosity. Split out the broadcast oneshot control into a separate function and provide inline helpers. Switch clockevents_notify() over. This will go away once all callers are converted. This also gets rid of the nested locking of clockevents_lock and broadcast_lock. The broadcast oneshot control functions do not require clockevents_lock. Only the managing functions (setup/shutdown/suspend/resume of the broadcast device require clockevents_lock. Signed-off-by: Thomas Gleixner Signed-off-by: Rafael J. Wysocki Cc: Alexandre Courbot Cc: Daniel Lezcano Cc: Len Brown Cc: Peter Zijlstra Cc: Stephen Warren Cc: Thierry Reding Cc: Tony Lindgren Link: http://lkml.kernel.org/r/13000649.8qZuEDV0OA@vostro.rjw.lan Signed-off-by: Ingo Molnar --- include/linux/tick.h | 19 +++++++++++++++++++ kernel/time/clockevents.c | 4 +++- kernel/time/tick-broadcast.c | 28 +++++++++++++++++----------- kernel/time/tick-internal.h | 2 -- 4 files changed, 39 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/tick.h b/include/linux/tick.h index 4bb236357b03..6119321fc3be 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -48,12 +48,23 @@ enum tick_broadcast_mode { TICK_BROADCAST_FORCE, }; +enum tick_broadcast_state { + TICK_BROADCAST_EXIT, + TICK_BROADCAST_ENTER, +}; + #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST extern void tick_broadcast_control(enum tick_broadcast_mode mode); #else static inline void tick_broadcast_control(enum tick_broadcast_mode mode) { } #endif /* BROADCAST */ +#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT) +extern int tick_broadcast_oneshot_control(enum tick_broadcast_state state); +#else +static inline int tick_broadcast_oneshot_control(enum tick_broadcast_state state) { return 0; } +#endif + static inline void tick_broadcast_enable(void) { tick_broadcast_control(TICK_BROADCAST_ON); @@ -66,6 +77,14 @@ static inline void tick_broadcast_force(void) { tick_broadcast_control(TICK_BROADCAST_FORCE); } +static inline int tick_broadcast_enter(void) +{ + return tick_broadcast_oneshot_control(TICK_BROADCAST_ENTER); +} +static inline void tick_broadcast_exit(void) +{ + tick_broadcast_oneshot_control(TICK_BROADCAST_EXIT); +} #ifdef CONFIG_NO_HZ_COMMON extern int tick_nohz_tick_stopped(void); diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index dba0b83708b3..7791b1c94ef2 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -656,8 +656,10 @@ int clockevents_notify(unsigned long reason, void *arg) switch (reason) { case CLOCK_EVT_NOTIFY_BROADCAST_ENTER: + tick_broadcast_enter(); + break; case CLOCK_EVT_NOTIFY_BROADCAST_EXIT: - ret = tick_broadcast_oneshot_control(reason); + tick_broadcast_exit(); break; case CLOCK_EVT_NOTIFY_CPU_DYING: diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 1a0bee04ef8c..55e43f20987a 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -687,18 +687,23 @@ void hotplug_cpu__broadcast_tick_pull(int deadcpu) raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } -/* - * Powerstate information: The system enters/leaves a state, where - * affected devices might stop +/** + * tick_broadcast_oneshot_control - Enter/exit broadcast oneshot mode + * @state: The target state (enter/exit) + * + * The system enters/leaves a state, where affected devices might stop * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups. + * + * Called with interrupts disabled, so clockevents_lock is not + * required here because the local clock event device cannot go away + * under us. */ -int tick_broadcast_oneshot_control(unsigned long reason) +int tick_broadcast_oneshot_control(enum tick_broadcast_state state) { struct clock_event_device *bc, *dev; struct tick_device *td; - unsigned long flags; - ktime_t now; int cpu, ret = 0; + ktime_t now; /* * Periodic mode does not care about the enter/exit of power @@ -711,17 +716,17 @@ int tick_broadcast_oneshot_control(unsigned long reason) * We are called with preemtion disabled from the depth of the * idle code, so we can't be moved away. */ - cpu = smp_processor_id(); - td = &per_cpu(tick_cpu_device, cpu); + td = this_cpu_ptr(&tick_cpu_device); dev = td->evtdev; if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) return 0; + raw_spin_lock(&tick_broadcast_lock); bc = tick_broadcast_device.evtdev; + cpu = smp_processor_id(); - raw_spin_lock_irqsave(&tick_broadcast_lock, flags); - if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) { + if (state == TICK_BROADCAST_ENTER) { if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) { WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask)); broadcast_shutdown_local(bc, dev); @@ -813,9 +818,10 @@ int tick_broadcast_oneshot_control(unsigned long reason) } } out: - raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); + raw_spin_unlock(&tick_broadcast_lock); return ret; } +EXPORT_SYMBOL_GPL(tick_broadcast_oneshot_control); /* * Reset the one shot broadcast for a cpu diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 62e331d1bc76..0266f9dbd114 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -117,7 +117,6 @@ static inline int tick_check_oneshot_change(int allow_nohz) { return 0; } /* Functions related to oneshot broadcasting */ #if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT) extern void tick_broadcast_setup_oneshot(struct clock_event_device *bc); -extern int tick_broadcast_oneshot_control(unsigned long reason); extern void tick_broadcast_switch_to_oneshot(void); extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup); extern int tick_broadcast_oneshot_active(void); @@ -126,7 +125,6 @@ bool tick_broadcast_oneshot_available(void); extern struct cpumask *tick_get_broadcast_oneshot_mask(void); #else /* !(BROADCAST && ONESHOT): */ static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); } -static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; } static inline void tick_broadcast_switch_to_oneshot(void) { } static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { } static inline int tick_broadcast_oneshot_active(void) { return 0; } -- cgit v1.2.3 From ffa48c0d76803057ee89bf220305466d74256d7b Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 3 Apr 2015 02:36:10 +0200 Subject: clockevents: Remove broadcast oneshot control leftovers Now that all users are converted over to explicit calls into the clockevents state machine, remove the notification chain leftovers. Original-from: Thomas Gleixner Signed-off-by: Rafael J. Wysocki Cc: Peter Zijlstra Cc: Linus Torvalds Cc: Andrew Morton Cc: John Stultz Link: http://lkml.kernel.org/r/14018863.NQUzkFuafr@vostro.rjw.lan Signed-off-by: Ingo Molnar --- include/linux/clockchips.h | 2 -- kernel/time/clockevents.c | 7 ------- 2 files changed, 9 deletions(-) (limited to 'include') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 438fafa75067..f97f498a5d10 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -11,8 +11,6 @@ /* Clock event notification values */ enum clock_event_nofitiers { CLOCK_EVT_NOTIFY_ADD, - CLOCK_EVT_NOTIFY_BROADCAST_ENTER, - CLOCK_EVT_NOTIFY_BROADCAST_EXIT, CLOCK_EVT_NOTIFY_CPU_DYING, CLOCK_EVT_NOTIFY_CPU_DEAD, }; diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 7791b1c94ef2..be9abf32c0b9 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -655,13 +655,6 @@ int clockevents_notify(unsigned long reason, void *arg) raw_spin_lock_irqsave(&clockevents_lock, flags); switch (reason) { - case CLOCK_EVT_NOTIFY_BROADCAST_ENTER: - tick_broadcast_enter(); - break; - case CLOCK_EVT_NOTIFY_BROADCAST_EXIT: - tick_broadcast_exit(); - break; - case CLOCK_EVT_NOTIFY_CPU_DYING: tick_handover_do_timer(arg); break; -- cgit v1.2.3 From 52c063d1adbc16c76e70fffa20727fcd4e9343b3 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 3 Apr 2015 02:37:24 +0200 Subject: clockevents: Make tick handover explicit clockevents_notify() is a leftover from the early design of the clockevents facility. It's really not a notification mechanism, it's a multiplex call. We are way better off to have explicit calls instead of this monstrosity. Split out the tick_handover call and invoke it explicitely from the hotplug code. Temporary solution will be cleaned up in later patches. Signed-off-by: Thomas Gleixner [ Rebase ] Signed-off-by: Rafael J. Wysocki Cc: Peter Zijlstra Cc: John Stultz Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/1658173.RkEEILFiQZ@vostro.rjw.lan Signed-off-by: Ingo Molnar --- include/linux/clockchips.h | 1 - include/linux/tick.h | 2 ++ kernel/cpu.c | 2 ++ kernel/time/clockevents.c | 4 ---- kernel/time/hrtimer.c | 4 ---- kernel/time/tick-common.c | 9 ++++++--- kernel/time/tick-internal.h | 1 - 7 files changed, 10 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index f97f498a5d10..f4bde22f8a05 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -11,7 +11,6 @@ /* Clock event notification values */ enum clock_event_nofitiers { CLOCK_EVT_NOTIFY_ADD, - CLOCK_EVT_NOTIFY_CPU_DYING, CLOCK_EVT_NOTIFY_CPU_DEAD, }; diff --git a/include/linux/tick.h b/include/linux/tick.h index 6119321fc3be..2c68fa3b9436 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -19,12 +19,14 @@ extern void tick_unfreeze(void); extern void tick_suspend_local(void); /* Should be core only, but XEN resume magic and ARM BL switcher require it */ extern void tick_resume_local(void); +extern void tick_handover_do_timer(void); #else /* CONFIG_GENERIC_CLOCKEVENTS */ static inline void tick_init(void) { } static inline void tick_freeze(void) { } static inline void tick_unfreeze(void) { } static inline void tick_suspend_local(void) { } static inline void tick_resume_local(void) { } +static inline void tick_handover_do_timer(void) { } #endif /* !CONFIG_GENERIC_CLOCKEVENTS */ #ifdef CONFIG_TICK_ONESHOT diff --git a/kernel/cpu.c b/kernel/cpu.c index af5db20e5803..eba7eaa1341d 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -339,6 +339,8 @@ static int __ref take_cpu_down(void *_param) return err; cpu_notify(CPU_DYING | param->mod, param->hcpu); + /* Give up timekeeping duties */ + tick_handover_do_timer(); /* Park the stopper thread */ kthread_park(current); return 0; diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index be9abf32c0b9..88fb3b96c7cc 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -655,10 +655,6 @@ int clockevents_notify(unsigned long reason, void *arg) raw_spin_lock_irqsave(&clockevents_lock, flags); switch (reason) { - case CLOCK_EVT_NOTIFY_CPU_DYING: - tick_handover_do_timer(arg); - break; - case CLOCK_EVT_NOTIFY_CPU_DEAD: tick_shutdown_broadcast_oneshot(arg); tick_shutdown_broadcast(arg); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 721d29b99d10..6a7a64ec7d1b 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1707,10 +1707,6 @@ static int hrtimer_cpu_notify(struct notifier_block *self, break; #ifdef CONFIG_HOTPLUG_CPU - case CPU_DYING: - case CPU_DYING_FROZEN: - clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DYING, &scpu); - break; case CPU_DEAD: case CPU_DEAD_FROZEN: { diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index e28ba5c044c5..055c868f3ec9 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -332,20 +332,23 @@ out_bc: tick_install_broadcast_device(newdev); } +#ifdef CONFIG_HOTPLUG_CPU /* * Transfer the do_timer job away from a dying cpu. * - * Called with interrupts disabled. + * Called with interrupts disabled. Not locking required. If + * tick_do_timer_cpu is owned by this cpu, nothing can change it. */ -void tick_handover_do_timer(int *cpup) +void tick_handover_do_timer(void) { - if (*cpup == tick_do_timer_cpu) { + if (tick_do_timer_cpu == smp_processor_id()) { int cpu = cpumask_first(cpu_online_mask); tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu : TICK_DO_TIMER_NONE; } } +#endif /* * Shutdown an event device on a given cpu: diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 0266f9dbd114..aabcb5d00cf2 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -20,7 +20,6 @@ extern int tick_do_timer_cpu __read_mostly; extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast); extern void tick_handle_periodic(struct clock_event_device *dev); extern void tick_check_new_device(struct clock_event_device *dev); -extern void tick_handover_do_timer(int *cpup); extern void tick_shutdown(unsigned int *cpup); extern void tick_suspend(void); extern void tick_resume(void); -- cgit v1.2.3 From a49b116dcb1265f238f3169507424257b0519069 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 3 Apr 2015 02:38:05 +0200 Subject: clockevents: Cleanup dead cpu explicitely clockevents_notify() is a leftover from the early design of the clockevents facility. It's really not a notification mechanism, it's a multiplex call. We are way better off to have explicit calls instead of this monstrosity. Split out the cleanup function for a dead cpu and invoke it directly from the cpu down code. Make it conditional on CPU_HOTPLUG as well. Temporary change, will be refined in the future. Signed-off-by: Thomas Gleixner [ Rebased, added clockevents_notify() removal ] Signed-off-by: Rafael J. Wysocki Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1735025.raBZdQHM3m@vostro.rjw.lan Signed-off-by: Ingo Molnar --- include/linux/clockchips.h | 6 ------ include/linux/tick.h | 2 ++ kernel/cpu.c | 1 + kernel/time/clockevents.c | 51 ++++++++++++++++++-------------------------- kernel/time/hrtimer.c | 3 --- kernel/time/tick-broadcast.c | 39 ++++++++++++++++----------------- kernel/time/tick-common.c | 6 +++--- kernel/time/tick-internal.h | 10 ++++----- 8 files changed, 52 insertions(+), 66 deletions(-) (limited to 'include') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index f4bde22f8a05..96c280b2c263 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -8,12 +8,6 @@ #ifndef _LINUX_CLOCKCHIPS_H #define _LINUX_CLOCKCHIPS_H -/* Clock event notification values */ -enum clock_event_nofitiers { - CLOCK_EVT_NOTIFY_ADD, - CLOCK_EVT_NOTIFY_CPU_DEAD, -}; - #ifdef CONFIG_GENERIC_CLOCKEVENTS # include diff --git a/include/linux/tick.h b/include/linux/tick.h index 2c68fa3b9436..f8492da57ad3 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -20,6 +20,7 @@ extern void tick_suspend_local(void); /* Should be core only, but XEN resume magic and ARM BL switcher require it */ extern void tick_resume_local(void); extern void tick_handover_do_timer(void); +extern void tick_cleanup_dead_cpu(int cpu); #else /* CONFIG_GENERIC_CLOCKEVENTS */ static inline void tick_init(void) { } static inline void tick_freeze(void) { } @@ -27,6 +28,7 @@ static inline void tick_unfreeze(void) { } static inline void tick_suspend_local(void) { } static inline void tick_resume_local(void) { } static inline void tick_handover_do_timer(void) { } +static inline void tick_cleanup_dead_cpu(int cpu) { } #endif /* !CONFIG_GENERIC_CLOCKEVENTS */ #ifdef CONFIG_TICK_ONESHOT diff --git a/kernel/cpu.c b/kernel/cpu.c index eba7eaa1341d..82eea9c5af61 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -419,6 +419,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) __cpu_die(cpu); /* CPU is completely dead: tell everyone. Too late to complain. */ + tick_cleanup_dead_cpu(cpu); cpu_notify_nofail(CPU_DEAD | mod, hcpu); check_for_tasks(cpu); diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 88fb3b96c7cc..25d942d1da27 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -642,49 +642,40 @@ void clockevents_resume(void) dev->resume(dev); } +#ifdef CONFIG_HOTPLUG_CPU /** - * clockevents_notify - notification about relevant events - * Returns 0 on success, any other value on error + * tick_cleanup_dead_cpu - Cleanup the tick and clockevents of a dead cpu */ -int clockevents_notify(unsigned long reason, void *arg) +void tick_cleanup_dead_cpu(int cpu) { struct clock_event_device *dev, *tmp; unsigned long flags; - int cpu, ret = 0; raw_spin_lock_irqsave(&clockevents_lock, flags); - switch (reason) { - case CLOCK_EVT_NOTIFY_CPU_DEAD: - tick_shutdown_broadcast_oneshot(arg); - tick_shutdown_broadcast(arg); - tick_shutdown(arg); - /* - * Unregister the clock event devices which were - * released from the users in the notify chain. - */ - list_for_each_entry_safe(dev, tmp, &clockevents_released, list) + tick_shutdown_broadcast_oneshot(cpu); + tick_shutdown_broadcast(cpu); + tick_shutdown(cpu); + /* + * Unregister the clock event devices which were + * released from the users in the notify chain. + */ + list_for_each_entry_safe(dev, tmp, &clockevents_released, list) + list_del(&dev->list); + /* + * Now check whether the CPU has left unused per cpu devices + */ + list_for_each_entry_safe(dev, tmp, &clockevent_devices, list) { + if (cpumask_test_cpu(cpu, dev->cpumask) && + cpumask_weight(dev->cpumask) == 1 && + !tick_is_broadcast_device(dev)) { + BUG_ON(dev->state != CLOCK_EVT_STATE_DETACHED); list_del(&dev->list); - /* - * Now check whether the CPU has left unused per cpu devices - */ - cpu = *((int *)arg); - list_for_each_entry_safe(dev, tmp, &clockevent_devices, list) { - if (cpumask_test_cpu(cpu, dev->cpumask) && - cpumask_weight(dev->cpumask) == 1 && - !tick_is_broadcast_device(dev)) { - BUG_ON(dev->state != CLOCK_EVT_STATE_DETACHED); - list_del(&dev->list); - } } - break; - default: - break; } raw_spin_unlock_irqrestore(&clockevents_lock, flags); - return ret; } -EXPORT_SYMBOL_GPL(clockevents_notify); +#endif #ifdef CONFIG_SYSFS struct bus_type clockevents_subsys = { diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 6a7a64ec7d1b..76d4bd962b19 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1709,11 +1709,8 @@ static int hrtimer_cpu_notify(struct notifier_block *self, #ifdef CONFIG_HOTPLUG_CPU case CPU_DEAD: case CPU_DEAD_FROZEN: - { - clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &scpu); migrate_hrtimers(scpu); break; - } #endif default: diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 55e43f20987a..7e8ca4f448a8 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -410,14 +410,14 @@ void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast) dev->event_handler = tick_handle_periodic_broadcast; } +#ifdef CONFIG_HOTPLUG_CPU /* * Remove a CPU from broadcasting */ -void tick_shutdown_broadcast(unsigned int *cpup) +void tick_shutdown_broadcast(unsigned int cpu) { struct clock_event_device *bc; unsigned long flags; - unsigned int cpu = *cpup; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); @@ -432,6 +432,7 @@ void tick_shutdown_broadcast(unsigned int *cpup) raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } +#endif void tick_suspend_broadcast(void) { @@ -672,21 +673,6 @@ static void broadcast_shutdown_local(struct clock_event_device *bc, clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN); } -void hotplug_cpu__broadcast_tick_pull(int deadcpu) -{ - struct clock_event_device *bc; - unsigned long flags; - - raw_spin_lock_irqsave(&tick_broadcast_lock, flags); - bc = tick_broadcast_device.evtdev; - - if (bc && broadcast_needs_cpu(bc, deadcpu)) { - /* This moves the broadcast assignment to this CPU: */ - clockevents_program_event(bc, bc->next_event, 1); - } - raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); -} - /** * tick_broadcast_oneshot_control - Enter/exit broadcast oneshot mode * @state: The target state (enter/exit) @@ -908,14 +894,28 @@ void tick_broadcast_switch_to_oneshot(void) raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } +#ifdef CONFIG_HOTPLUG_CPU +void hotplug_cpu__broadcast_tick_pull(int deadcpu) +{ + struct clock_event_device *bc; + unsigned long flags; + + raw_spin_lock_irqsave(&tick_broadcast_lock, flags); + bc = tick_broadcast_device.evtdev; + + if (bc && broadcast_needs_cpu(bc, deadcpu)) { + /* This moves the broadcast assignment to this CPU: */ + clockevents_program_event(bc, bc->next_event, 1); + } + raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); +} /* * Remove a dead CPU from broadcasting */ -void tick_shutdown_broadcast_oneshot(unsigned int *cpup) +void tick_shutdown_broadcast_oneshot(unsigned int cpu) { unsigned long flags; - unsigned int cpu = *cpup; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); @@ -929,6 +929,7 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup) raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } +#endif /* * Check, whether the broadcast device is in one shot mode diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 055c868f3ec9..fac3e98fec49 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -348,7 +348,6 @@ void tick_handover_do_timer(void) TICK_DO_TIMER_NONE; } } -#endif /* * Shutdown an event device on a given cpu: @@ -357,9 +356,9 @@ void tick_handover_do_timer(void) * access the hardware device itself. * We just set the mode and remove it from the lists. */ -void tick_shutdown(unsigned int *cpup) +void tick_shutdown(unsigned int cpu) { - struct tick_device *td = &per_cpu(tick_cpu_device, *cpup); + struct tick_device *td = &per_cpu(tick_cpu_device, cpu); struct clock_event_device *dev = td->evtdev; td->mode = TICKDEV_MODE_PERIODIC; @@ -375,6 +374,7 @@ void tick_shutdown(unsigned int *cpup) td->evtdev = NULL; } } +#endif /** * tick_suspend_local - Suspend the local tick device diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index aabcb5d00cf2..b64fdd8054c5 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -20,7 +20,7 @@ extern int tick_do_timer_cpu __read_mostly; extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast); extern void tick_handle_periodic(struct clock_event_device *dev); extern void tick_check_new_device(struct clock_event_device *dev); -extern void tick_shutdown(unsigned int *cpup); +extern void tick_shutdown(unsigned int cpu); extern void tick_suspend(void); extern void tick_resume(void); extern bool tick_check_replacement(struct clock_event_device *curdev, @@ -52,7 +52,7 @@ extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt); extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu); extern void tick_install_broadcast_device(struct clock_event_device *dev); extern int tick_is_broadcast_device(struct clock_event_device *dev); -extern void tick_shutdown_broadcast(unsigned int *cpup); +extern void tick_shutdown_broadcast(unsigned int cpu); extern void tick_suspend_broadcast(void); extern void tick_resume_broadcast(void); extern bool tick_resume_check_broadcast(void); @@ -66,7 +66,7 @@ static inline void tick_install_broadcast_device(struct clock_event_device *dev) static inline int tick_is_broadcast_device(struct clock_event_device *dev) { return 0; } static inline int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) { return 0; } static inline void tick_do_periodic_broadcast(struct clock_event_device *d) { } -static inline void tick_shutdown_broadcast(unsigned int *cpup) { } +static inline void tick_shutdown_broadcast(unsigned int cpu) { } static inline void tick_suspend_broadcast(void) { } static inline void tick_resume_broadcast(void) { } static inline bool tick_resume_check_broadcast(void) { return false; } @@ -117,7 +117,7 @@ static inline int tick_check_oneshot_change(int allow_nohz) { return 0; } #if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT) extern void tick_broadcast_setup_oneshot(struct clock_event_device *bc); extern void tick_broadcast_switch_to_oneshot(void); -extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup); +extern void tick_shutdown_broadcast_oneshot(unsigned int cpu); extern int tick_broadcast_oneshot_active(void); extern void tick_check_oneshot_broadcast_this_cpu(void); bool tick_broadcast_oneshot_available(void); @@ -125,7 +125,7 @@ extern struct cpumask *tick_get_broadcast_oneshot_mask(void); #else /* !(BROADCAST && ONESHOT): */ static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); } static inline void tick_broadcast_switch_to_oneshot(void) { } -static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { } +static inline void tick_shutdown_broadcast_oneshot(unsigned int cpu) { } static inline int tick_broadcast_oneshot_active(void) { return 0; } static inline void tick_check_oneshot_broadcast_this_cpu(void) { } static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); } -- cgit v1.2.3