From bbb138bdace76672ae8919887419e9f5f96bbeab Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Sat, 26 Sep 2015 18:19:54 +0100 Subject: [PATCH] ANDROID: sched: Update max cpu capacity in case of max frequency constraints Wakeup balancing uses cpu capacity awareness and needs to know the system-wide maximum cpu capacity. Patch "sched: Store system-wide maximum cpu capacity in root domain" finds the system-wide maximum cpu capacity during scheduler domain hierarchy setup. This is sufficient as long as maximum frequency invariance is not enabled. If it is enabled, the system-wide maximum cpu capacity can change between scheduler domain hierarchy setups due to frequency capping. The cpu capacity is changed in update_cpu_capacity() which is called in load balance on the lowest scheduler domain hierarchy level. To be able to know if a change in cpu capacity for a certain cpu also has an effect on the system-wide maximum cpu capacity it is normally necessary to iterate over all cpus. This would be way too costly. That's why this patch follows a different approach. The unsigned long max_cpu_capacity value in struct root_domain is replaced with a struct max_cpu_capacity, containing value (the max_cpu_capacity) and cpu (the cpu index of the cpu providing the maximum cpu_capacity). Changes to the system-wide maximum cpu capacity and the cpu index are made if: 1 System-wide maximum cpu capacity < cpu capacity 2 System-wide maximum cpu capacity > cpu capacity and cpu index == cpu There are no changes to the system-wide maximum cpu capacity in all other cases. Atomic read and write access to the pair (max_cpu_capacity.val, max_cpu_capacity.cpu) is enforced by max_cpu_capacity.lock. The access to max_cpu_capacity.val in task_fits_max() is still performed without taking the max_cpu_capacity.lock. The code to set max cpu capacity in build_sched_domains() has been removed because the whole functionality is now provided by update_cpu_capacity() instead. This approach can introduce errors temporarily, e.g. in case the cpu currently providing the max cpu capacity has its cpu capacity lowered due to frequency capping and calls update_cpu_capacity() before any cpu which might provide the max cpu now. There is also an outstanding question: Should the cpu capacity of a cpu going idle be set to a very small value? Signed-off-by: Dietmar Eggemann Signed-off-by: Andres Oportus --- kernel/sched/core.c | 12 ++---------- kernel/sched/fair.c | 32 +++++++++++++++++++++++++++++++- kernel/sched/sched.h | 11 ++++++++++- 3 files changed, 43 insertions(+), 12 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b231ed3e6c74..15a8e35f0198 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5885,6 +5885,8 @@ static int init_rootdomain(struct root_domain *rd) if (cpupri_init(&rd->cpupri) != 0) goto free_rto_mask; + + init_max_cpu_capacity(&rd->max_cpu_capacity); return 0; free_rto_mask: @@ -7131,20 +7133,10 @@ static int build_sched_domains(const struct cpumask *cpu_map, for_each_cpu(i, cpu_map) { rq = cpu_rq(i); sd = *per_cpu_ptr(d.sd, i); - - /* Use READ_ONCE()/WRITE_ONCE() to avoid load/store tearing: */ - if (rq->cpu_capacity_orig > READ_ONCE(d.rd->max_cpu_capacity)) - WRITE_ONCE(d.rd->max_cpu_capacity, rq->cpu_capacity_orig); - cpu_attach_domain(sd, d.rd, i); } rcu_read_unlock(); - if (rq && sched_debug_enabled) { - pr_info("span: %*pbl (max cpu_capacity = %lu)\n", - cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity); - } - ret = 0; error: __free_domain_allocs(&d, alloc_state, cpu_map); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 2672e7e6934a..bfd407869ef0 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5534,7 +5534,7 @@ static inline bool __task_fits(struct task_struct *p, int cpu, int util) static inline bool task_fits_max(struct task_struct *p, int cpu) { unsigned long capacity = capacity_of(cpu); - unsigned long max_capacity = cpu_rq(cpu)->rd->max_cpu_capacity; + unsigned long max_capacity = cpu_rq(cpu)->rd->max_cpu_capacity.val; if (capacity == max_capacity) return true; @@ -7246,13 +7246,43 @@ static unsigned long scale_rt_capacity(int cpu) return 1; } +void init_max_cpu_capacity(struct max_cpu_capacity *mcc) +{ + raw_spin_lock_init(&mcc->lock); + mcc->val = 0; + mcc->cpu = -1; +} + static void update_cpu_capacity(struct sched_domain *sd, int cpu) { unsigned long capacity = arch_scale_cpu_capacity(sd, cpu); struct sched_group *sdg = sd->groups; + struct max_cpu_capacity *mcc; + unsigned long max_capacity; + int max_cap_cpu; + unsigned long flags; cpu_rq(cpu)->cpu_capacity_orig = capacity; + mcc = &cpu_rq(cpu)->rd->max_cpu_capacity; + + raw_spin_lock_irqsave(&mcc->lock, flags); + max_capacity = mcc->val; + max_cap_cpu = mcc->cpu; + + if ((max_capacity > capacity && max_cap_cpu == cpu) || + (max_capacity < capacity)) { + mcc->val = capacity; + mcc->cpu = cpu; +#ifdef CONFIG_SCHED_DEBUG + raw_spin_unlock_irqrestore(&mcc->lock, flags); + pr_info("CPU%d: update max cpu_capacity %lu\n", cpu, capacity); + goto skip_unlock; +#endif + } + raw_spin_unlock_irqrestore(&mcc->lock, flags); + +skip_unlock: __attribute__ ((unused)); capacity *= scale_rt_capacity(cpu); capacity >>= SCHED_CAPACITY_SHIFT; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 86512afe0711..d08f3b054194 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -539,6 +539,12 @@ struct dl_rq { #ifdef CONFIG_SMP +struct max_cpu_capacity { + raw_spinlock_t lock; + unsigned long val; + int cpu; +}; + /* * We add the notion of a root-domain which will be used to define per-domain * variables. Each exclusive cpuset essentially defines an island domain by @@ -576,7 +582,8 @@ struct root_domain { cpumask_var_t rto_mask; struct cpupri cpupri; - unsigned long max_cpu_capacity; + /* Maximum cpu capacity in the system. */ + struct max_cpu_capacity max_cpu_capacity; }; extern struct root_domain def_root_domain; @@ -1414,6 +1421,8 @@ static inline void sched_update_tick_dependency(struct rq *rq) static inline void sched_update_tick_dependency(struct rq *rq) { } #endif +extern void init_max_cpu_capacity(struct max_cpu_capacity *mcc); + static inline void add_nr_running(struct rq *rq, unsigned count) { unsigned prev_nr = rq->nr_running;