From 6f9a22bc5775d231ab8fbe2c2f3c88e45e3e7c28 Mon Sep 17 00:00:00 2001 From: Michael Hernandez Date: Thu, 18 May 2017 10:47:47 -0700 Subject: PCI/MSI: Ignore affinity if pre/post vector count is more than min_vecs min_vecs is the minimum amount of vectors needed to operate in MSI-X mode which may just include the vectors that don't need affinity. Disabling affinity settings causes the qla2xxx driver scsi_add_host() to fail when blk_mq is enabled as the blk_mq_pci_map_queues() expects affinity masks on each vector. Fixes: dfef358bd1be ("PCI/MSI: Don't apply affinity if there aren't enough vectors left") Signed-off-by: Michael Hernandez Signed-off-by: Himanshu Madhani Signed-off-by: Bjorn Helgaas Reviewed-by: Christoph Hellwig Cc: stable@vger.kernel.org # v4.10+ --- include/linux/interrupt.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/interrupt.h') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index a6fba4804672..0991f973f8ca 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -291,7 +291,7 @@ extern int irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify); struct cpumask *irq_create_affinity_masks(int nvec, const struct irq_affinity *affd); -int irq_calc_affinity_vectors(int maxvec, const struct irq_affinity *affd); +int irq_calc_affinity_vectors(int minvec, int maxvec, const struct irq_affinity *affd); #else /* CONFIG_SMP */ @@ -331,7 +331,7 @@ irq_create_affinity_masks(int nvec, const struct irq_affinity *affd) } static inline int -irq_calc_affinity_vectors(int maxvec, const struct irq_affinity *affd) +irq_calc_affinity_vectors(int minvec, int maxvec, const struct irq_affinity *affd) { return maxvec; } -- cgit v1.2.3 From b2d3d61adb7b73cfe5f82404f7a130a76fc64232 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Fri, 23 Jun 2017 16:11:07 +0200 Subject: genirq/timings: Add infrastructure to track the interrupt timings The interrupt framework gives a lot of information about each interrupt. It does not keep track of when those interrupts occur though, which is a prerequisite for estimating the next interrupt arrival for power management purposes. Add a mechanism to record the timestamp for each interrupt occurrences in a per-CPU circular buffer to help with the prediction of the next occurrence using a statistical model. Each CPU can store up to IRQ_TIMINGS_SIZE events , the current value of IRQ_TIMINGS_SIZE is 32. Each event is encoded into a single u64, where the high 48 bits are used for the timestamp and the low 16 bits are for the irq number. A static key is introduced so when the irq prediction is switched off at runtime, the overhead is near to zero. It results in most of the code in internals.h for inline reasons and a very few in the new file timings.c. The latter will contain more in the next patch which will provide the statistical model for the next event prediction. Signed-off-by: Daniel Lezcano Signed-off-by: Thomas Gleixner Acked-by: Nicolas Pitre Cc: Jens Axboe Cc: Hannes Reinecke Cc: Vincent Guittot Cc: "Rafael J . Wysocki" Cc: Peter Zijlstra Cc: Bjorn Helgaas Link: http://lkml.kernel.org/r/1498227072-5980-1-git-send-email-daniel.lezcano@linaro.org --- include/linux/interrupt.h | 5 +++ kernel/irq/Kconfig | 3 ++ kernel/irq/Makefile | 1 + kernel/irq/handle.c | 2 ++ kernel/irq/internals.h | 90 +++++++++++++++++++++++++++++++++++++++++++++++ kernel/irq/manage.c | 3 ++ kernel/irq/timings.c | 30 ++++++++++++++++ 7 files changed, 134 insertions(+) create mode 100644 kernel/irq/timings.c (limited to 'include/linux/interrupt.h') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index a6fba4804672..9f617238a2f7 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -703,6 +703,11 @@ static inline void init_irq_proc(void) } #endif +#ifdef CONFIG_IRQ_TIMINGS +void irq_timings_enable(void); +void irq_timings_disable(void); +#endif + struct seq_file; int show_interrupts(struct seq_file *p, void *v); int arch_show_interrupts(struct seq_file *p, int prec); diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index fcbb1d6d51cb..27c4e774071c 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -85,6 +85,9 @@ config GENERIC_MSI_IRQ_DOMAIN config HANDLE_DOMAIN_IRQ bool +config IRQ_TIMINGS + bool + config IRQ_DOMAIN_DEBUG bool "Expose hardware/virtual IRQ mapping via debugfs" depends on IRQ_DOMAIN && DEBUG_FS diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index c61fc9c2d1f7..e4aef7351f2b 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -1,5 +1,6 @@ obj-y := irqdesc.o handle.o manage.o spurious.o resend.o chip.o dummychip.o devres.o +obj-$(CONFIG_IRQ_TIMINGS) += timings.o obj-$(CONFIG_GENERIC_IRQ_CHIP) += generic-chip.o obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o obj-$(CONFIG_IRQ_DOMAIN) += irqdomain.o diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index d3f24905852c..eb4d3e8945b8 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -138,6 +138,8 @@ irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags unsigned int irq = desc->irq_data.irq; struct irqaction *action; + record_irq_time(desc); + for_each_action_of_desc(desc, action) { irqreturn_t res; diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index a573e0771baf..b95b74920433 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -8,6 +8,7 @@ #include #include #include +#include #ifdef CONFIG_SPARSE_IRQ # define IRQ_BITMAP_BITS (NR_IRQS + 8196) @@ -57,6 +58,7 @@ enum { IRQS_WAITING = 0x00000080, IRQS_PENDING = 0x00000200, IRQS_SUSPENDED = 0x00000800, + IRQS_TIMINGS = 0x00001000, }; #include "debug.h" @@ -255,6 +257,94 @@ static inline void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action) { } #endif +#ifdef CONFIG_IRQ_TIMINGS + +#define IRQ_TIMINGS_SHIFT 5 +#define IRQ_TIMINGS_SIZE (1 << IRQ_TIMINGS_SHIFT) +#define IRQ_TIMINGS_MASK (IRQ_TIMINGS_SIZE - 1) + +/** + * struct irq_timings - irq timings storing structure + * @values: a circular buffer of u64 encoded values + * @count: the number of elements in the array + */ +struct irq_timings { + u64 values[IRQ_TIMINGS_SIZE]; + int count; +}; + +DECLARE_PER_CPU(struct irq_timings, irq_timings); + +static inline void irq_remove_timings(struct irq_desc *desc) +{ + desc->istate &= ~IRQS_TIMINGS; +} + +static inline void irq_setup_timings(struct irq_desc *desc, struct irqaction *act) +{ + /* + * We don't need the measurement because the idle code already + * knows the next expiry event. + */ + if (act->flags & __IRQF_TIMER) + return; + + desc->istate |= IRQS_TIMINGS; +} + +extern void irq_timings_enable(void); +extern void irq_timings_disable(void); + +DECLARE_STATIC_KEY_FALSE(irq_timing_enabled); + +/* + * The interrupt number and the timestamp are encoded into a single + * u64 variable to optimize the size. + * 48 bit time stamp and 16 bit IRQ number is way sufficient. + * Who cares an IRQ after 78 hours of idle time? + */ +static inline u64 irq_timing_encode(u64 timestamp, int irq) +{ + return (timestamp << 16) | irq; +} + +static inline int irq_timing_decode(u64 value, u64 *timestamp) +{ + *timestamp = value >> 16; + return value & U16_MAX; +} + +/* + * The function record_irq_time is only called in one place in the + * interrupts handler. We want this function always inline so the code + * inside is embedded in the function and the static key branching + * code can act at the higher level. Without the explicit + * __always_inline we can end up with a function call and a small + * overhead in the hotpath for nothing. + */ +static __always_inline void record_irq_time(struct irq_desc *desc) +{ + if (!static_branch_likely(&irq_timing_enabled)) + return; + + if (desc->istate & IRQS_TIMINGS) { + struct irq_timings *timings = this_cpu_ptr(&irq_timings); + + timings->values[timings->count & IRQ_TIMINGS_MASK] = + irq_timing_encode(local_clock(), + irq_desc_get_irq(desc)); + + timings->count++; + } +} +#else +static inline void irq_remove_timings(struct irq_desc *desc) {} +static inline void irq_setup_timings(struct irq_desc *desc, + struct irqaction *act) {}; +static inline void record_irq_time(struct irq_desc *desc) {} +#endif /* CONFIG_IRQ_TIMINGS */ + + #ifdef CONFIG_GENERIC_IRQ_CHIP void irq_init_generic_chip(struct irq_chip_generic *gc, const char *name, int num_ct, unsigned int irq_base, diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 3577c091ac7b..5c11c1730ba5 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1348,6 +1348,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) raw_spin_unlock_irqrestore(&desc->lock, flags); + irq_setup_timings(desc, new); + /* * Strictly no need to wake it up, but hung_task complains * when no hard interrupt wakes the thread up. @@ -1474,6 +1476,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) irq_settings_clr_disable_unlazy(desc); irq_shutdown(desc); irq_release_resources(desc); + irq_remove_timings(desc); } #ifdef CONFIG_SMP diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c new file mode 100644 index 000000000000..56cf6870fa26 --- /dev/null +++ b/kernel/irq/timings.c @@ -0,0 +1,30 @@ +/* + * linux/kernel/irq/timings.c + * + * Copyright (C) 2016, Linaro Ltd - Daniel Lezcano + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ +#include +#include +#include +#include + +#include "internals.h" + +DEFINE_STATIC_KEY_FALSE(irq_timing_enabled); + +DEFINE_PER_CPU(struct irq_timings, irq_timings); + +void irq_timings_enable(void) +{ + static_branch_enable(&irq_timing_enabled); +} + +void irq_timings_disable(void) +{ + static_branch_disable(&irq_timing_enabled); +} -- cgit v1.2.3 From e1c921495534002d727b15a76a2f8c20b6b108b5 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Fri, 23 Jun 2017 16:11:08 +0200 Subject: genirq/timings: Add infrastructure for estimating the next interrupt arrival time An interrupt behaves with a burst of activity with periodic interval of time followed by one or two peaks of longer interval. As the time intervals are periodic, statistically speaking they follow a normal distribution and each interrupts can be tracked individually. Add a mechanism to compute the statistics on all interrupts, except the timers which are deterministic from a prediction point of view, as their expiry time is known. The goal is to extract the periodicity for each interrupt, with the last timestamp and sum them, so the next event can be predicted to a certain extent. Taking the earliest prediction gives the expected wakeup on the system (assuming a timer won't expire before). Signed-off-by: Daniel Lezcano Signed-off-by: Thomas Gleixner Cc: Nicolas Pitre Cc: Jens Axboe Cc: Hannes Reinecke Cc: Vincent Guittot Cc: "Rafael J . Wysocki" Cc: Peter Zijlstra Cc: Bjorn Helgaas Link: http://lkml.kernel.org/r/1498227072-5980-2-git-send-email-daniel.lezcano@linaro.org --- include/linux/interrupt.h | 1 + kernel/irq/internals.h | 19 +++ kernel/irq/timings.c | 339 ++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 359 insertions(+) (limited to 'include/linux/interrupt.h') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 9f617238a2f7..37f8e354f564 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -706,6 +706,7 @@ static inline void init_irq_proc(void) #ifdef CONFIG_IRQ_TIMINGS void irq_timings_enable(void); void irq_timings_disable(void); +u64 irq_timings_next_event(u64 now); #endif struct seq_file; diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index b95b74920433..9da14d125df4 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -275,13 +275,21 @@ struct irq_timings { DECLARE_PER_CPU(struct irq_timings, irq_timings); +extern void irq_timings_free(int irq); +extern int irq_timings_alloc(int irq); + static inline void irq_remove_timings(struct irq_desc *desc) { desc->istate &= ~IRQS_TIMINGS; + + irq_timings_free(irq_desc_get_irq(desc)); } static inline void irq_setup_timings(struct irq_desc *desc, struct irqaction *act) { + int irq = irq_desc_get_irq(desc); + int ret; + /* * We don't need the measurement because the idle code already * knows the next expiry event. @@ -289,6 +297,17 @@ static inline void irq_setup_timings(struct irq_desc *desc, struct irqaction *ac if (act->flags & __IRQF_TIMER) return; + /* + * In case the timing allocation fails, we just want to warn, + * not fail, so letting the system boot anyway. + */ + ret = irq_timings_alloc(irq); + if (ret) { + pr_warn("Failed to allocate irq timing stats for irq%d (%d)", + irq, ret); + return; + } + desc->istate |= IRQS_TIMINGS; } diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c index 56cf6870fa26..c8c1d073fbf1 100644 --- a/kernel/irq/timings.c +++ b/kernel/irq/timings.c @@ -8,10 +8,16 @@ * published by the Free Software Foundation. * */ +#include #include +#include #include #include +#include #include +#include + +#include #include "internals.h" @@ -19,6 +25,18 @@ DEFINE_STATIC_KEY_FALSE(irq_timing_enabled); DEFINE_PER_CPU(struct irq_timings, irq_timings); +struct irqt_stat { + u64 next_evt; + u64 last_ts; + u64 variance; + u32 avg; + u32 nr_samples; + int anomalies; + int valid; +}; + +static DEFINE_IDR(irqt_stats); + void irq_timings_enable(void) { static_branch_enable(&irq_timing_enabled); @@ -28,3 +46,324 @@ void irq_timings_disable(void) { static_branch_disable(&irq_timing_enabled); } + +/** + * irqs_update - update the irq timing statistics with a new timestamp + * + * @irqs: an irqt_stat struct pointer + * @ts: the new timestamp + * + * The statistics are computed online, in other words, the code is + * designed to compute the statistics on a stream of values rather + * than doing multiple passes on the values to compute the average, + * then the variance. The integer division introduces a loss of + * precision but with an acceptable error margin regarding the results + * we would have with the double floating precision: we are dealing + * with nanosec, so big numbers, consequently the mantisse is + * negligeable, especially when converting the time in usec + * afterwards. + * + * The computation happens at idle time. When the CPU is not idle, the + * interrupts' timestamps are stored in the circular buffer, when the + * CPU goes idle and this routine is called, all the buffer's values + * are injected in the statistical model continuying to extend the + * statistics from the previous busy-idle cycle. + * + * The observations showed a device will trigger a burst of periodic + * interrupts followed by one or two peaks of longer time, for + * instance when a SD card device flushes its cache, then the periodic + * intervals occur again. A one second inactivity period resets the + * stats, that gives us the certitude the statistical values won't + * exceed 1x10^9, thus the computation won't overflow. + * + * Basically, the purpose of the algorithm is to watch the periodic + * interrupts and eliminate the peaks. + * + * An interrupt is considered periodically stable if the interval of + * its occurences follow the normal distribution, thus the values + * comply with: + * + * avg - 3 x stddev < value < avg + 3 x stddev + * + * Which can be simplified to: + * + * -3 x stddev < value - avg < 3 x stddev + * + * abs(value - avg) < 3 x stddev + * + * In order to save a costly square root computation, we use the + * variance. For the record, stddev = sqrt(variance). The equation + * above becomes: + * + * abs(value - avg) < 3 x sqrt(variance) + * + * And finally we square it: + * + * (value - avg) ^ 2 < (3 x sqrt(variance)) ^ 2 + * + * (value - avg) x (value - avg) < 9 x variance + * + * Statistically speaking, any values out of this interval is + * considered as an anomaly and is discarded. However, a normal + * distribution appears when the number of samples is 30 (it is the + * rule of thumb in statistics, cf. "30 samples" on Internet). When + * there are three consecutive anomalies, the statistics are resetted. + * + */ +static void irqs_update(struct irqt_stat *irqs, u64 ts) +{ + u64 old_ts = irqs->last_ts; + u64 variance = 0; + u64 interval; + s64 diff; + + /* + * The timestamps are absolute time values, we need to compute + * the timing interval between two interrupts. + */ + irqs->last_ts = ts; + + /* + * The interval type is u64 in order to deal with the same + * type in our computation, that prevent mindfuck issues with + * overflow, sign and division. + */ + interval = ts - old_ts; + + /* + * The interrupt triggered more than one second apart, that + * ends the sequence as predictible for our purpose. In this + * case, assume we have the beginning of a sequence and the + * timestamp is the first value. As it is impossible to + * predict anything at this point, return. + * + * Note the first timestamp of the sequence will always fall + * in this test because the old_ts is zero. That is what we + * want as we need another timestamp to compute an interval. + */ + if (interval >= NSEC_PER_SEC) { + memset(irqs, 0, sizeof(*irqs)); + irqs->last_ts = ts; + return; + } + + /* + * Pre-compute the delta with the average as the result is + * used several times in this function. + */ + diff = interval - irqs->avg; + + /* + * Increment the number of samples. + */ + irqs->nr_samples++; + + /* + * Online variance divided by the number of elements if there + * is more than one sample. Normally the formula is division + * by nr_samples - 1 but we assume the number of element will be + * more than 32 and dividing by 32 instead of 31 is enough + * precise. + */ + if (likely(irqs->nr_samples > 1)) + variance = irqs->variance >> IRQ_TIMINGS_SHIFT; + + /* + * The rule of thumb in statistics for the normal distribution + * is having at least 30 samples in order to have the model to + * apply. Values outside the interval are considered as an + * anomaly. + */ + if ((irqs->nr_samples >= 30) && ((diff * diff) > (9 * variance))) { + /* + * After three consecutive anomalies, we reset the + * stats as it is no longer stable enough. + */ + if (irqs->anomalies++ >= 3) { + memset(irqs, 0, sizeof(*irqs)); + irqs->last_ts = ts; + return; + } + } else { + /* + * The anomalies must be consecutives, so at this + * point, we reset the anomalies counter. + */ + irqs->anomalies = 0; + } + + /* + * The interrupt is considered stable enough to try to predict + * the next event on it. + */ + irqs->valid = 1; + + /* + * Online average algorithm: + * + * new_average = average + ((value - average) / count) + * + * The variance computation depends on the new average + * to be computed here first. + * + */ + irqs->avg = irqs->avg + (diff >> IRQ_TIMINGS_SHIFT); + + /* + * Online variance algorithm: + * + * new_variance = variance + (value - average) x (value - new_average) + * + * Warning: irqs->avg is updated with the line above, hence + * 'interval - irqs->avg' is no longer equal to 'diff' + */ + irqs->variance = irqs->variance + (diff * (interval - irqs->avg)); + + /* + * Update the next event + */ + irqs->next_evt = ts + irqs->avg; +} + +/** + * irq_timings_next_event - Return when the next event is supposed to arrive + * + * During the last busy cycle, the number of interrupts is incremented + * and stored in the irq_timings structure. This information is + * necessary to: + * + * - know if the index in the table wrapped up: + * + * If more than the array size interrupts happened during the + * last busy/idle cycle, the index wrapped up and we have to + * begin with the next element in the array which is the last one + * in the sequence, otherwise it is a the index 0. + * + * - have an indication of the interrupts activity on this CPU + * (eg. irq/sec) + * + * The values are 'consumed' after inserting in the statistical model, + * thus the count is reinitialized. + * + * The array of values **must** be browsed in the time direction, the + * timestamp must increase between an element and the next one. + * + * Returns a nanosec time based estimation of the earliest interrupt, + * U64_MAX otherwise. + */ +u64 irq_timings_next_event(u64 now) +{ + struct irq_timings *irqts = this_cpu_ptr(&irq_timings); + struct irqt_stat *irqs; + struct irqt_stat __percpu *s; + u64 ts, next_evt = U64_MAX; + int i, irq = 0; + + /* + * This function must be called with the local irq disabled in + * order to prevent the timings circular buffer to be updated + * while we are reading it. + */ + WARN_ON_ONCE(!irqs_disabled()); + + /* + * Number of elements in the circular buffer: If it happens it + * was flushed before, then the number of elements could be + * smaller than IRQ_TIMINGS_SIZE, so the count is used, + * otherwise the array size is used as we wrapped. The index + * begins from zero when we did not wrap. That could be done + * in a nicer way with the proper circular array structure + * type but with the cost of extra computation in the + * interrupt handler hot path. We choose efficiency. + * + * Inject measured irq/timestamp to the statistical model + * while decrementing the counter because we consume the data + * from our circular buffer. + */ + for (i = irqts->count & IRQ_TIMINGS_MASK, + irqts->count = min(IRQ_TIMINGS_SIZE, irqts->count); + irqts->count > 0; irqts->count--, i = (i + 1) & IRQ_TIMINGS_MASK) { + + irq = irq_timing_decode(irqts->values[i], &ts); + + s = idr_find(&irqt_stats, irq); + if (s) { + irqs = this_cpu_ptr(s); + irqs_update(irqs, ts); + } + } + + /* + * Look in the list of interrupts' statistics, the earliest + * next event. + */ + idr_for_each_entry(&irqt_stats, s, i) { + + irqs = this_cpu_ptr(s); + + if (!irqs->valid) + continue; + + if (irqs->next_evt <= now) { + irq = i; + next_evt = now; + + /* + * This interrupt mustn't use in the future + * until new events occur and update the + * statistics. + */ + irqs->valid = 0; + break; + } + + if (irqs->next_evt < next_evt) { + irq = i; + next_evt = irqs->next_evt; + } + } + + return next_evt; +} + +void irq_timings_free(int irq) +{ + struct irqt_stat __percpu *s; + + s = idr_find(&irqt_stats, irq); + if (s) { + free_percpu(s); + idr_remove(&irqt_stats, irq); + } +} + +int irq_timings_alloc(int irq) +{ + struct irqt_stat __percpu *s; + int id; + + /* + * Some platforms can have the same private interrupt per cpu, + * so this function may be be called several times with the + * same interrupt number. Just bail out in case the per cpu + * stat structure is already allocated. + */ + s = idr_find(&irqt_stats, irq); + if (s) + return 0; + + s = alloc_percpu(*s); + if (!s) + return -ENOMEM; + + idr_preload(GFP_KERNEL); + id = idr_alloc(&irqt_stats, s, irq, irq + 1, GFP_NOWAIT); + idr_preload_end(); + + if (id < 0) { + free_percpu(s); + return id; + } + + return 0; +} -- cgit v1.2.3 From c80081b9209713e0fe86d3def395a9fc66503c58 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 6 Jul 2017 14:29:04 +0200 Subject: genirq: Allow to pass the IRQF_TIMER flag with percpu irq request The irq timings infrastructure tracks when interrupts occur in order to statistically predict te next interrupt event. There is no point to track timer interrupts and try to predict them because the next expiration time is already known. This can be avoided via the IRQF_TIMER flag which is passed by timer drivers in request_irq(). It marks the interrupt as timer based which alloes to ignore these interrupts in the timings code. Per CPU interrupts which are requested via request_percpu_+irq() have no flag argument, so marking per cpu timer interrupts is not possible and they get tracked pointlessly. Add __request_percpu_irq() as a variant of request_percpu_irq() with a flags argument and make request_percpu_irq() an inline wrapper passing flags = 0. The flag parameter is restricted to IRQF_TIMER as all other IRQF_ flags make no sense for per cpu interrupts. The next step is to convert all existing users of request_percpu_irq() and then remove the wrapper and the underscores. [ tglx: Massaged changelog ] Signed-off-by: Daniel Lezcano Signed-off-by: Thomas Gleixner Cc: peterz@infradead.org Cc: nicolas.pitre@linaro.org Cc: vincent.guittot@linaro.org Cc: rafael@kernel.org Link: http://lkml.kernel.org/r/1499344144-3964-1-git-send-email-daniel.lezcano@linaro.org --- include/linux/interrupt.h | 11 ++++++++++- kernel/irq/manage.c | 15 ++++++++++----- 2 files changed, 20 insertions(+), 6 deletions(-) (limited to 'include/linux/interrupt.h') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 37f8e354f564..5ac6e238555e 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -152,8 +152,17 @@ request_any_context_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *name, void *dev_id); extern int __must_check +__request_percpu_irq(unsigned int irq, irq_handler_t handler, + unsigned long flags, const char *devname, + void __percpu *percpu_dev_id); + +static inline int __must_check request_percpu_irq(unsigned int irq, irq_handler_t handler, - const char *devname, void __percpu *percpu_dev_id); + const char *devname, void __percpu *percpu_dev_id) +{ + return __request_percpu_irq(irq, handler, 0, + devname, percpu_dev_id); +} extern const void *free_irq(unsigned int, void *); extern void free_percpu_irq(unsigned int, void __percpu *); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 91e1f2390752..5624b2dd6b58 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1950,9 +1950,10 @@ int setup_percpu_irq(unsigned int irq, struct irqaction *act) } /** - * request_percpu_irq - allocate a percpu interrupt line + * __request_percpu_irq - allocate a percpu interrupt line * @irq: Interrupt line to allocate * @handler: Function to be called when the IRQ occurs. + * @flags: Interrupt type flags (IRQF_TIMER only) * @devname: An ascii name for the claiming device * @dev_id: A percpu cookie passed back to the handler function * @@ -1965,8 +1966,9 @@ int setup_percpu_irq(unsigned int irq, struct irqaction *act) * the handler gets called with the interrupted CPU's instance of * that variable. */ -int request_percpu_irq(unsigned int irq, irq_handler_t handler, - const char *devname, void __percpu *dev_id) +int __request_percpu_irq(unsigned int irq, irq_handler_t handler, + unsigned long flags, const char *devname, + void __percpu *dev_id) { struct irqaction *action; struct irq_desc *desc; @@ -1980,12 +1982,15 @@ int request_percpu_irq(unsigned int irq, irq_handler_t handler, !irq_settings_is_per_cpu_devid(desc)) return -EINVAL; + if (flags && flags != IRQF_TIMER) + return -EINVAL; + action = kzalloc(sizeof(struct irqaction), GFP_KERNEL); if (!action) return -ENOMEM; action->handler = handler; - action->flags = IRQF_PERCPU | IRQF_NO_SUSPEND; + action->flags = flags | IRQF_PERCPU | IRQF_NO_SUSPEND; action->name = devname; action->percpu_dev_id = dev_id; @@ -2004,7 +2009,7 @@ int request_percpu_irq(unsigned int irq, irq_handler_t handler, return retval; } -EXPORT_SYMBOL_GPL(request_percpu_irq); +EXPORT_SYMBOL_GPL(__request_percpu_irq); /** * irq_get_irqchip_state - returns the irqchip state of a interrupt. -- cgit v1.2.3