Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar:
"The main changes in this cycle were:
- Implement frequency/CPU invariance and OPP selection for
SCHED_DEADLINE (Juri Lelli)
- Tweak the task migration logic for better multi-tasking
workload scalability (Mel Gorman)
- Misc cleanups, fixes and improvements"
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/deadline: Make bandwidth enforcement scale-invariant
sched/cpufreq: Move arch_scale_{freq,cpu}_capacity() outside of #ifdef CONFIG_SMP
sched/cpufreq: Remove arch_scale_freq_capacity()'s 'sd' parameter
sched/cpufreq: Always consider all CPUs when deciding next freq
sched/cpufreq: Split utilization signals
sched/cpufreq: Change the worker kthread to SCHED_DEADLINE
sched/deadline: Move CPU frequency selection triggering points
sched/cpufreq: Use the DEADLINE utilization signal
sched/deadline: Implement "runtime overrun signal" support
sched/fair: Only immediately migrate tasks due to interrupts if prev and target CPUs share cache
sched/fair: Correct obsolete comment about cpufreq_update_util()
sched/fair: Remove impossible condition from find_idlest_group_cpu()
sched/cpufreq: Don't pass flags to sugov_set_iowait_boost()
sched/cpufreq: Initialize sg_cpu->flags to 0
sched/fair: Consider RT/IRQ pressure in capacity_spare_wake()
sched/fair: Use 'unsigned long' for utilization, consistently
sched/core: Rework and clarify prepare_lock_switch()
sched/fair: Remove unused 'curr' parameter from wakeup_gran
sched/headers: Constify object_is_on_stack()
This commit is contained in:
Linus Torvalds
commit
af8c5e2d60
|
|
@ -27,7 +27,7 @@ void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity);
|
|||
DECLARE_PER_CPU(unsigned long, freq_scale);
|
||||
|
||||
static inline
|
||||
unsigned long topology_get_freq_scale(struct sched_domain *sd, int cpu)
|
||||
unsigned long topology_get_freq_scale(int cpu)
|
||||
{
|
||||
return per_cpu(freq_scale, cpu);
|
||||
}
|
||||
|
|
|
|||
|
|
@ -472,11 +472,15 @@ struct sched_dl_entity {
|
|||
* has not been executed yet. This flag is useful to avoid race
|
||||
* conditions between the inactive timer handler and the wakeup
|
||||
* code.
|
||||
*
|
||||
* @dl_overrun tells if the task asked to be informed about runtime
|
||||
* overruns.
|
||||
*/
|
||||
unsigned int dl_throttled : 1;
|
||||
unsigned int dl_boosted : 1;
|
||||
unsigned int dl_yielded : 1;
|
||||
unsigned int dl_non_contending : 1;
|
||||
unsigned int dl_overrun : 1;
|
||||
|
||||
/*
|
||||
* Bandwidth enforcement timer. Each -deadline task has its
|
||||
|
|
@ -1427,6 +1431,7 @@ extern int idle_cpu(int cpu);
|
|||
extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *);
|
||||
extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *);
|
||||
extern int sched_setattr(struct task_struct *, const struct sched_attr *);
|
||||
extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *);
|
||||
extern struct task_struct *idle_task(int cpu);
|
||||
|
||||
/**
|
||||
|
|
|
|||
|
|
@ -12,8 +12,6 @@
|
|||
#define SCHED_CPUFREQ_DL (1U << 1)
|
||||
#define SCHED_CPUFREQ_IOWAIT (1U << 2)
|
||||
|
||||
#define SCHED_CPUFREQ_RT_DL (SCHED_CPUFREQ_RT | SCHED_CPUFREQ_DL)
|
||||
|
||||
#ifdef CONFIG_CPU_FREQ
|
||||
struct update_util_data {
|
||||
void (*func)(struct update_util_data *data, u64 time, unsigned int flags);
|
||||
|
|
|
|||
|
|
@ -78,7 +78,7 @@ static inline void put_task_stack(struct task_struct *tsk) {}
|
|||
#define task_stack_end_corrupted(task) \
|
||||
(*(end_of_stack(task)) != STACK_END_MAGIC)
|
||||
|
||||
static inline int object_is_on_stack(void *obj)
|
||||
static inline int object_is_on_stack(const void *obj)
|
||||
{
|
||||
void *stack = task_stack_page(current);
|
||||
|
||||
|
|
|
|||
|
|
@ -6,6 +6,12 @@
|
|||
|
||||
#include <linux/sched/idle.h>
|
||||
|
||||
/*
|
||||
* Increase resolution of cpu_capacity calculations
|
||||
*/
|
||||
#define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT
|
||||
#define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT)
|
||||
|
||||
/*
|
||||
* sched-domains (multiprocessor balancing) declarations:
|
||||
*/
|
||||
|
|
@ -27,12 +33,6 @@
|
|||
#define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */
|
||||
#define SD_NUMA 0x4000 /* cross-node balancing */
|
||||
|
||||
/*
|
||||
* Increase resolution of cpu_capacity calculations
|
||||
*/
|
||||
#define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT
|
||||
#define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT)
|
||||
|
||||
#ifdef CONFIG_SCHED_SMT
|
||||
static inline int cpu_smt_flags(void)
|
||||
{
|
||||
|
|
|
|||
|
|
@ -49,5 +49,10 @@
|
|||
*/
|
||||
#define SCHED_FLAG_RESET_ON_FORK 0x01
|
||||
#define SCHED_FLAG_RECLAIM 0x02
|
||||
#define SCHED_FLAG_DL_OVERRUN 0x04
|
||||
|
||||
#define SCHED_FLAG_ALL (SCHED_FLAG_RESET_ON_FORK | \
|
||||
SCHED_FLAG_RECLAIM | \
|
||||
SCHED_FLAG_DL_OVERRUN)
|
||||
|
||||
#endif /* _UAPI_LINUX_SCHED_H */
|
||||
|
|
|
|||
|
|
@ -2046,7 +2046,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
|
|||
* If the owning (remote) CPU is still in the middle of schedule() with
|
||||
* this task as prev, wait until its done referencing the task.
|
||||
*
|
||||
* Pairs with the smp_store_release() in finish_lock_switch().
|
||||
* Pairs with the smp_store_release() in finish_task().
|
||||
*
|
||||
* This ensures that tasks getting woken will be fully ordered against
|
||||
* their previous state and preserve Program Order.
|
||||
|
|
@ -2572,6 +2572,50 @@ fire_sched_out_preempt_notifiers(struct task_struct *curr,
|
|||
|
||||
#endif /* CONFIG_PREEMPT_NOTIFIERS */
|
||||
|
||||
static inline void prepare_task(struct task_struct *next)
|
||||
{
|
||||
#ifdef CONFIG_SMP
|
||||
/*
|
||||
* Claim the task as running, we do this before switching to it
|
||||
* such that any running task will have this set.
|
||||
*/
|
||||
next->on_cpu = 1;
|
||||
#endif
|
||||
}
|
||||
|
||||
static inline void finish_task(struct task_struct *prev)
|
||||
{
|
||||
#ifdef CONFIG_SMP
|
||||
/*
|
||||
* After ->on_cpu is cleared, the task can be moved to a different CPU.
|
||||
* We must ensure this doesn't happen until the switch is completely
|
||||
* finished.
|
||||
*
|
||||
* In particular, the load of prev->state in finish_task_switch() must
|
||||
* happen before this.
|
||||
*
|
||||
* Pairs with the smp_cond_load_acquire() in try_to_wake_up().
|
||||
*/
|
||||
smp_store_release(&prev->on_cpu, 0);
|
||||
#endif
|
||||
}
|
||||
|
||||
static inline void finish_lock_switch(struct rq *rq)
|
||||
{
|
||||
#ifdef CONFIG_DEBUG_SPINLOCK
|
||||
/* this is a valid case when another task releases the spinlock */
|
||||
rq->lock.owner = current;
|
||||
#endif
|
||||
/*
|
||||
* If we are tracking spinlock dependencies then we have to
|
||||
* fix up the runqueue lock - which gets 'carried over' from
|
||||
* prev into current:
|
||||
*/
|
||||
spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
|
||||
|
||||
raw_spin_unlock_irq(&rq->lock);
|
||||
}
|
||||
|
||||
/**
|
||||
* prepare_task_switch - prepare to switch tasks
|
||||
* @rq: the runqueue preparing to switch
|
||||
|
|
@ -2592,7 +2636,7 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
|
|||
sched_info_switch(rq, prev, next);
|
||||
perf_event_task_sched_out(prev, next);
|
||||
fire_sched_out_preempt_notifiers(prev, next);
|
||||
prepare_lock_switch(rq, next);
|
||||
prepare_task(next);
|
||||
prepare_arch_switch(next);
|
||||
}
|
||||
|
||||
|
|
@ -2647,7 +2691,7 @@ static struct rq *finish_task_switch(struct task_struct *prev)
|
|||
* the scheduled task must drop that reference.
|
||||
*
|
||||
* We must observe prev->state before clearing prev->on_cpu (in
|
||||
* finish_lock_switch), otherwise a concurrent wakeup can get prev
|
||||
* finish_task), otherwise a concurrent wakeup can get prev
|
||||
* running on another CPU and we could rave with its RUNNING -> DEAD
|
||||
* transition, resulting in a double drop.
|
||||
*/
|
||||
|
|
@ -2664,7 +2708,8 @@ static struct rq *finish_task_switch(struct task_struct *prev)
|
|||
* to use.
|
||||
*/
|
||||
smp_mb__after_unlock_lock();
|
||||
finish_lock_switch(rq, prev);
|
||||
finish_task(prev);
|
||||
finish_lock_switch(rq);
|
||||
finish_arch_post_lock_switch();
|
||||
|
||||
fire_sched_in_preempt_notifiers(current);
|
||||
|
|
@ -4041,8 +4086,7 @@ recheck:
|
|||
return -EINVAL;
|
||||
}
|
||||
|
||||
if (attr->sched_flags &
|
||||
~(SCHED_FLAG_RESET_ON_FORK | SCHED_FLAG_RECLAIM))
|
||||
if (attr->sched_flags & ~(SCHED_FLAG_ALL | SCHED_FLAG_SUGOV))
|
||||
return -EINVAL;
|
||||
|
||||
/*
|
||||
|
|
@ -4109,6 +4153,9 @@ recheck:
|
|||
}
|
||||
|
||||
if (user) {
|
||||
if (attr->sched_flags & SCHED_FLAG_SUGOV)
|
||||
return -EINVAL;
|
||||
|
||||
retval = security_task_setscheduler(p);
|
||||
if (retval)
|
||||
return retval;
|
||||
|
|
@ -4164,7 +4211,8 @@ change:
|
|||
}
|
||||
#endif
|
||||
#ifdef CONFIG_SMP
|
||||
if (dl_bandwidth_enabled() && dl_policy(policy)) {
|
||||
if (dl_bandwidth_enabled() && dl_policy(policy) &&
|
||||
!(attr->sched_flags & SCHED_FLAG_SUGOV)) {
|
||||
cpumask_t *span = rq->rd->span;
|
||||
|
||||
/*
|
||||
|
|
@ -4294,6 +4342,11 @@ int sched_setattr(struct task_struct *p, const struct sched_attr *attr)
|
|||
}
|
||||
EXPORT_SYMBOL_GPL(sched_setattr);
|
||||
|
||||
int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr)
|
||||
{
|
||||
return __sched_setscheduler(p, attr, false, true);
|
||||
}
|
||||
|
||||
/**
|
||||
* sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
|
||||
* @p: the task in question.
|
||||
|
|
|
|||
|
|
@ -60,7 +60,8 @@ struct sugov_cpu {
|
|||
u64 last_update;
|
||||
|
||||
/* The fields below are only needed when sharing a policy. */
|
||||
unsigned long util;
|
||||
unsigned long util_cfs;
|
||||
unsigned long util_dl;
|
||||
unsigned long max;
|
||||
unsigned int flags;
|
||||
|
||||
|
|
@ -176,21 +177,28 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
|
|||
return cpufreq_driver_resolve_freq(policy, freq);
|
||||
}
|
||||
|
||||
static void sugov_get_util(unsigned long *util, unsigned long *max, int cpu)
|
||||
static void sugov_get_util(struct sugov_cpu *sg_cpu)
|
||||
{
|
||||
struct rq *rq = cpu_rq(cpu);
|
||||
unsigned long cfs_max;
|
||||
struct rq *rq = cpu_rq(sg_cpu->cpu);
|
||||
|
||||
cfs_max = arch_scale_cpu_capacity(NULL, cpu);
|
||||
|
||||
*util = min(rq->cfs.avg.util_avg, cfs_max);
|
||||
*max = cfs_max;
|
||||
sg_cpu->max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
|
||||
sg_cpu->util_cfs = cpu_util_cfs(rq);
|
||||
sg_cpu->util_dl = cpu_util_dl(rq);
|
||||
}
|
||||
|
||||
static void sugov_set_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
|
||||
unsigned int flags)
|
||||
static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
|
||||
{
|
||||
if (flags & SCHED_CPUFREQ_IOWAIT) {
|
||||
/*
|
||||
* Ideally we would like to set util_dl as min/guaranteed freq and
|
||||
* util_cfs + util_dl as requested freq. However, cpufreq is not yet
|
||||
* ready for such an interface. So, we only do the latter for now.
|
||||
*/
|
||||
return min(sg_cpu->util_cfs + sg_cpu->util_dl, sg_cpu->max);
|
||||
}
|
||||
|
||||
static void sugov_set_iowait_boost(struct sugov_cpu *sg_cpu, u64 time)
|
||||
{
|
||||
if (sg_cpu->flags & SCHED_CPUFREQ_IOWAIT) {
|
||||
if (sg_cpu->iowait_boost_pending)
|
||||
return;
|
||||
|
||||
|
|
@ -264,7 +272,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
|
|||
unsigned int next_f;
|
||||
bool busy;
|
||||
|
||||
sugov_set_iowait_boost(sg_cpu, time, flags);
|
||||
sugov_set_iowait_boost(sg_cpu, time);
|
||||
sg_cpu->last_update = time;
|
||||
|
||||
if (!sugov_should_update_freq(sg_policy, time))
|
||||
|
|
@ -272,10 +280,12 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
|
|||
|
||||
busy = sugov_cpu_is_busy(sg_cpu);
|
||||
|
||||
if (flags & SCHED_CPUFREQ_RT_DL) {
|
||||
if (flags & SCHED_CPUFREQ_RT) {
|
||||
next_f = policy->cpuinfo.max_freq;
|
||||
} else {
|
||||
sugov_get_util(&util, &max, sg_cpu->cpu);
|
||||
sugov_get_util(sg_cpu);
|
||||
max = sg_cpu->max;
|
||||
util = sugov_aggregate_util(sg_cpu);
|
||||
sugov_iowait_boost(sg_cpu, &util, &max);
|
||||
next_f = get_next_freq(sg_policy, util, max);
|
||||
/*
|
||||
|
|
@ -305,23 +315,27 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
|
|||
s64 delta_ns;
|
||||
|
||||
/*
|
||||
* If the CPU utilization was last updated before the previous
|
||||
* frequency update and the time elapsed between the last update
|
||||
* of the CPU utilization and the last frequency update is long
|
||||
* enough, don't take the CPU into account as it probably is
|
||||
* idle now (and clear iowait_boost for it).
|
||||
* If the CFS CPU utilization was last updated before the
|
||||
* previous frequency update and the time elapsed between the
|
||||
* last update of the CPU utilization and the last frequency
|
||||
* update is long enough, reset iowait_boost and util_cfs, as
|
||||
* they are now probably stale. However, still consider the
|
||||
* CPU contribution if it has some DEADLINE utilization
|
||||
* (util_dl).
|
||||
*/
|
||||
delta_ns = time - j_sg_cpu->last_update;
|
||||
if (delta_ns > TICK_NSEC) {
|
||||
j_sg_cpu->iowait_boost = 0;
|
||||
j_sg_cpu->iowait_boost_pending = false;
|
||||
continue;
|
||||
j_sg_cpu->util_cfs = 0;
|
||||
if (j_sg_cpu->util_dl == 0)
|
||||
continue;
|
||||
}
|
||||
if (j_sg_cpu->flags & SCHED_CPUFREQ_RT_DL)
|
||||
if (j_sg_cpu->flags & SCHED_CPUFREQ_RT)
|
||||
return policy->cpuinfo.max_freq;
|
||||
|
||||
j_util = j_sg_cpu->util;
|
||||
j_max = j_sg_cpu->max;
|
||||
j_util = sugov_aggregate_util(j_sg_cpu);
|
||||
if (j_util * max > j_max * util) {
|
||||
util = j_util;
|
||||
max = j_max;
|
||||
|
|
@ -338,22 +352,18 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time,
|
|||
{
|
||||
struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
|
||||
struct sugov_policy *sg_policy = sg_cpu->sg_policy;
|
||||
unsigned long util, max;
|
||||
unsigned int next_f;
|
||||
|
||||
sugov_get_util(&util, &max, sg_cpu->cpu);
|
||||
|
||||
raw_spin_lock(&sg_policy->update_lock);
|
||||
|
||||
sg_cpu->util = util;
|
||||
sg_cpu->max = max;
|
||||
sugov_get_util(sg_cpu);
|
||||
sg_cpu->flags = flags;
|
||||
|
||||
sugov_set_iowait_boost(sg_cpu, time, flags);
|
||||
sugov_set_iowait_boost(sg_cpu, time);
|
||||
sg_cpu->last_update = time;
|
||||
|
||||
if (sugov_should_update_freq(sg_policy, time)) {
|
||||
if (flags & SCHED_CPUFREQ_RT_DL)
|
||||
if (flags & SCHED_CPUFREQ_RT)
|
||||
next_f = sg_policy->policy->cpuinfo.max_freq;
|
||||
else
|
||||
next_f = sugov_next_freq_shared(sg_cpu, time);
|
||||
|
|
@ -383,9 +393,9 @@ static void sugov_irq_work(struct irq_work *irq_work)
|
|||
sg_policy = container_of(irq_work, struct sugov_policy, irq_work);
|
||||
|
||||
/*
|
||||
* For RT and deadline tasks, the schedutil governor shoots the
|
||||
* frequency to maximum. Special care must be taken to ensure that this
|
||||
* kthread doesn't result in the same behavior.
|
||||
* For RT tasks, the schedutil governor shoots the frequency to maximum.
|
||||
* Special care must be taken to ensure that this kthread doesn't result
|
||||
* in the same behavior.
|
||||
*
|
||||
* This is (mostly) guaranteed by the work_in_progress flag. The flag is
|
||||
* updated only at the end of the sugov_work() function and before that
|
||||
|
|
@ -470,7 +480,20 @@ static void sugov_policy_free(struct sugov_policy *sg_policy)
|
|||
static int sugov_kthread_create(struct sugov_policy *sg_policy)
|
||||
{
|
||||
struct task_struct *thread;
|
||||
struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO / 2 };
|
||||
struct sched_attr attr = {
|
||||
.size = sizeof(struct sched_attr),
|
||||
.sched_policy = SCHED_DEADLINE,
|
||||
.sched_flags = SCHED_FLAG_SUGOV,
|
||||
.sched_nice = 0,
|
||||
.sched_priority = 0,
|
||||
/*
|
||||
* Fake (unused) bandwidth; workaround to "fix"
|
||||
* priority inheritance.
|
||||
*/
|
||||
.sched_runtime = 1000000,
|
||||
.sched_deadline = 10000000,
|
||||
.sched_period = 10000000,
|
||||
};
|
||||
struct cpufreq_policy *policy = sg_policy->policy;
|
||||
int ret;
|
||||
|
||||
|
|
@ -488,10 +511,10 @@ static int sugov_kthread_create(struct sugov_policy *sg_policy)
|
|||
return PTR_ERR(thread);
|
||||
}
|
||||
|
||||
ret = sched_setscheduler_nocheck(thread, SCHED_FIFO, ¶m);
|
||||
ret = sched_setattr_nocheck(thread, &attr);
|
||||
if (ret) {
|
||||
kthread_stop(thread);
|
||||
pr_warn("%s: failed to set SCHED_FIFO\n", __func__);
|
||||
pr_warn("%s: failed to set SCHED_DEADLINE\n", __func__);
|
||||
return ret;
|
||||
}
|
||||
|
||||
|
|
@ -655,7 +678,7 @@ static int sugov_start(struct cpufreq_policy *policy)
|
|||
memset(sg_cpu, 0, sizeof(*sg_cpu));
|
||||
sg_cpu->cpu = cpu;
|
||||
sg_cpu->sg_policy = sg_policy;
|
||||
sg_cpu->flags = SCHED_CPUFREQ_RT;
|
||||
sg_cpu->flags = 0;
|
||||
sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq;
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -78,7 +78,7 @@ static inline int dl_bw_cpus(int i)
|
|||
#endif
|
||||
|
||||
static inline
|
||||
void add_running_bw(u64 dl_bw, struct dl_rq *dl_rq)
|
||||
void __add_running_bw(u64 dl_bw, struct dl_rq *dl_rq)
|
||||
{
|
||||
u64 old = dl_rq->running_bw;
|
||||
|
||||
|
|
@ -86,10 +86,12 @@ void add_running_bw(u64 dl_bw, struct dl_rq *dl_rq)
|
|||
dl_rq->running_bw += dl_bw;
|
||||
SCHED_WARN_ON(dl_rq->running_bw < old); /* overflow */
|
||||
SCHED_WARN_ON(dl_rq->running_bw > dl_rq->this_bw);
|
||||
/* kick cpufreq (see the comment in kernel/sched/sched.h). */
|
||||
cpufreq_update_util(rq_of_dl_rq(dl_rq), SCHED_CPUFREQ_DL);
|
||||
}
|
||||
|
||||
static inline
|
||||
void sub_running_bw(u64 dl_bw, struct dl_rq *dl_rq)
|
||||
void __sub_running_bw(u64 dl_bw, struct dl_rq *dl_rq)
|
||||
{
|
||||
u64 old = dl_rq->running_bw;
|
||||
|
||||
|
|
@ -98,10 +100,12 @@ void sub_running_bw(u64 dl_bw, struct dl_rq *dl_rq)
|
|||
SCHED_WARN_ON(dl_rq->running_bw > old); /* underflow */
|
||||
if (dl_rq->running_bw > old)
|
||||
dl_rq->running_bw = 0;
|
||||
/* kick cpufreq (see the comment in kernel/sched/sched.h). */
|
||||
cpufreq_update_util(rq_of_dl_rq(dl_rq), SCHED_CPUFREQ_DL);
|
||||
}
|
||||
|
||||
static inline
|
||||
void add_rq_bw(u64 dl_bw, struct dl_rq *dl_rq)
|
||||
void __add_rq_bw(u64 dl_bw, struct dl_rq *dl_rq)
|
||||
{
|
||||
u64 old = dl_rq->this_bw;
|
||||
|
||||
|
|
@ -111,7 +115,7 @@ void add_rq_bw(u64 dl_bw, struct dl_rq *dl_rq)
|
|||
}
|
||||
|
||||
static inline
|
||||
void sub_rq_bw(u64 dl_bw, struct dl_rq *dl_rq)
|
||||
void __sub_rq_bw(u64 dl_bw, struct dl_rq *dl_rq)
|
||||
{
|
||||
u64 old = dl_rq->this_bw;
|
||||
|
||||
|
|
@ -123,16 +127,46 @@ void sub_rq_bw(u64 dl_bw, struct dl_rq *dl_rq)
|
|||
SCHED_WARN_ON(dl_rq->running_bw > dl_rq->this_bw);
|
||||
}
|
||||
|
||||
static inline
|
||||
void add_rq_bw(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
|
||||
{
|
||||
if (!dl_entity_is_special(dl_se))
|
||||
__add_rq_bw(dl_se->dl_bw, dl_rq);
|
||||
}
|
||||
|
||||
static inline
|
||||
void sub_rq_bw(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
|
||||
{
|
||||
if (!dl_entity_is_special(dl_se))
|
||||
__sub_rq_bw(dl_se->dl_bw, dl_rq);
|
||||
}
|
||||
|
||||
static inline
|
||||
void add_running_bw(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
|
||||
{
|
||||
if (!dl_entity_is_special(dl_se))
|
||||
__add_running_bw(dl_se->dl_bw, dl_rq);
|
||||
}
|
||||
|
||||
static inline
|
||||
void sub_running_bw(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
|
||||
{
|
||||
if (!dl_entity_is_special(dl_se))
|
||||
__sub_running_bw(dl_se->dl_bw, dl_rq);
|
||||
}
|
||||
|
||||
void dl_change_utilization(struct task_struct *p, u64 new_bw)
|
||||
{
|
||||
struct rq *rq;
|
||||
|
||||
BUG_ON(p->dl.flags & SCHED_FLAG_SUGOV);
|
||||
|
||||
if (task_on_rq_queued(p))
|
||||
return;
|
||||
|
||||
rq = task_rq(p);
|
||||
if (p->dl.dl_non_contending) {
|
||||
sub_running_bw(p->dl.dl_bw, &rq->dl);
|
||||
sub_running_bw(&p->dl, &rq->dl);
|
||||
p->dl.dl_non_contending = 0;
|
||||
/*
|
||||
* If the timer handler is currently running and the
|
||||
|
|
@ -144,8 +178,8 @@ void dl_change_utilization(struct task_struct *p, u64 new_bw)
|
|||
if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1)
|
||||
put_task_struct(p);
|
||||
}
|
||||
sub_rq_bw(p->dl.dl_bw, &rq->dl);
|
||||
add_rq_bw(new_bw, &rq->dl);
|
||||
__sub_rq_bw(p->dl.dl_bw, &rq->dl);
|
||||
__add_rq_bw(new_bw, &rq->dl);
|
||||
}
|
||||
|
||||
/*
|
||||
|
|
@ -217,6 +251,9 @@ static void task_non_contending(struct task_struct *p)
|
|||
if (dl_se->dl_runtime == 0)
|
||||
return;
|
||||
|
||||
if (dl_entity_is_special(dl_se))
|
||||
return;
|
||||
|
||||
WARN_ON(hrtimer_active(&dl_se->inactive_timer));
|
||||
WARN_ON(dl_se->dl_non_contending);
|
||||
|
||||
|
|
@ -236,12 +273,12 @@ static void task_non_contending(struct task_struct *p)
|
|||
*/
|
||||
if (zerolag_time < 0) {
|
||||
if (dl_task(p))
|
||||
sub_running_bw(dl_se->dl_bw, dl_rq);
|
||||
sub_running_bw(dl_se, dl_rq);
|
||||
if (!dl_task(p) || p->state == TASK_DEAD) {
|
||||
struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
|
||||
|
||||
if (p->state == TASK_DEAD)
|
||||
sub_rq_bw(p->dl.dl_bw, &rq->dl);
|
||||
sub_rq_bw(&p->dl, &rq->dl);
|
||||
raw_spin_lock(&dl_b->lock);
|
||||
__dl_sub(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p)));
|
||||
__dl_clear_params(p);
|
||||
|
|
@ -268,7 +305,7 @@ static void task_contending(struct sched_dl_entity *dl_se, int flags)
|
|||
return;
|
||||
|
||||
if (flags & ENQUEUE_MIGRATED)
|
||||
add_rq_bw(dl_se->dl_bw, dl_rq);
|
||||
add_rq_bw(dl_se, dl_rq);
|
||||
|
||||
if (dl_se->dl_non_contending) {
|
||||
dl_se->dl_non_contending = 0;
|
||||
|
|
@ -289,7 +326,7 @@ static void task_contending(struct sched_dl_entity *dl_se, int flags)
|
|||
* when the "inactive timer" fired).
|
||||
* So, add it back.
|
||||
*/
|
||||
add_running_bw(dl_se->dl_bw, dl_rq);
|
||||
add_running_bw(dl_se, dl_rq);
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -1114,7 +1151,8 @@ static void update_curr_dl(struct rq *rq)
|
|||
{
|
||||
struct task_struct *curr = rq->curr;
|
||||
struct sched_dl_entity *dl_se = &curr->dl;
|
||||
u64 delta_exec;
|
||||
u64 delta_exec, scaled_delta_exec;
|
||||
int cpu = cpu_of(rq);
|
||||
|
||||
if (!dl_task(curr) || !on_dl_rq(dl_se))
|
||||
return;
|
||||
|
|
@ -1134,9 +1172,6 @@ static void update_curr_dl(struct rq *rq)
|
|||
return;
|
||||
}
|
||||
|
||||
/* kick cpufreq (see the comment in kernel/sched/sched.h). */
|
||||
cpufreq_update_util(rq, SCHED_CPUFREQ_DL);
|
||||
|
||||
schedstat_set(curr->se.statistics.exec_max,
|
||||
max(curr->se.statistics.exec_max, delta_exec));
|
||||
|
||||
|
|
@ -1148,13 +1183,39 @@ static void update_curr_dl(struct rq *rq)
|
|||
|
||||
sched_rt_avg_update(rq, delta_exec);
|
||||
|
||||
if (unlikely(dl_se->flags & SCHED_FLAG_RECLAIM))
|
||||
delta_exec = grub_reclaim(delta_exec, rq, &curr->dl);
|
||||
dl_se->runtime -= delta_exec;
|
||||
if (dl_entity_is_special(dl_se))
|
||||
return;
|
||||
|
||||
/*
|
||||
* For tasks that participate in GRUB, we implement GRUB-PA: the
|
||||
* spare reclaimed bandwidth is used to clock down frequency.
|
||||
*
|
||||
* For the others, we still need to scale reservation parameters
|
||||
* according to current frequency and CPU maximum capacity.
|
||||
*/
|
||||
if (unlikely(dl_se->flags & SCHED_FLAG_RECLAIM)) {
|
||||
scaled_delta_exec = grub_reclaim(delta_exec,
|
||||
rq,
|
||||
&curr->dl);
|
||||
} else {
|
||||
unsigned long scale_freq = arch_scale_freq_capacity(cpu);
|
||||
unsigned long scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
|
||||
|
||||
scaled_delta_exec = cap_scale(delta_exec, scale_freq);
|
||||
scaled_delta_exec = cap_scale(scaled_delta_exec, scale_cpu);
|
||||
}
|
||||
|
||||
dl_se->runtime -= scaled_delta_exec;
|
||||
|
||||
throttle:
|
||||
if (dl_runtime_exceeded(dl_se) || dl_se->dl_yielded) {
|
||||
dl_se->dl_throttled = 1;
|
||||
|
||||
/* If requested, inform the user about runtime overruns. */
|
||||
if (dl_runtime_exceeded(dl_se) &&
|
||||
(dl_se->flags & SCHED_FLAG_DL_OVERRUN))
|
||||
dl_se->dl_overrun = 1;
|
||||
|
||||
__dequeue_task_dl(rq, curr, 0);
|
||||
if (unlikely(dl_se->dl_boosted || !start_dl_timer(curr)))
|
||||
enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH);
|
||||
|
|
@ -1204,8 +1265,8 @@ static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
|
|||
struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
|
||||
|
||||
if (p->state == TASK_DEAD && dl_se->dl_non_contending) {
|
||||
sub_running_bw(p->dl.dl_bw, dl_rq_of_se(&p->dl));
|
||||
sub_rq_bw(p->dl.dl_bw, dl_rq_of_se(&p->dl));
|
||||
sub_running_bw(&p->dl, dl_rq_of_se(&p->dl));
|
||||
sub_rq_bw(&p->dl, dl_rq_of_se(&p->dl));
|
||||
dl_se->dl_non_contending = 0;
|
||||
}
|
||||
|
||||
|
|
@ -1222,7 +1283,7 @@ static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
|
|||
sched_clock_tick();
|
||||
update_rq_clock(rq);
|
||||
|
||||
sub_running_bw(dl_se->dl_bw, &rq->dl);
|
||||
sub_running_bw(dl_se, &rq->dl);
|
||||
dl_se->dl_non_contending = 0;
|
||||
unlock:
|
||||
task_rq_unlock(rq, p, &rf);
|
||||
|
|
@ -1416,8 +1477,8 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
|
|||
dl_check_constrained_dl(&p->dl);
|
||||
|
||||
if (p->on_rq == TASK_ON_RQ_MIGRATING || flags & ENQUEUE_RESTORE) {
|
||||
add_rq_bw(p->dl.dl_bw, &rq->dl);
|
||||
add_running_bw(p->dl.dl_bw, &rq->dl);
|
||||
add_rq_bw(&p->dl, &rq->dl);
|
||||
add_running_bw(&p->dl, &rq->dl);
|
||||
}
|
||||
|
||||
/*
|
||||
|
|
@ -1457,8 +1518,8 @@ static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
|
|||
__dequeue_task_dl(rq, p, flags);
|
||||
|
||||
if (p->on_rq == TASK_ON_RQ_MIGRATING || flags & DEQUEUE_SAVE) {
|
||||
sub_running_bw(p->dl.dl_bw, &rq->dl);
|
||||
sub_rq_bw(p->dl.dl_bw, &rq->dl);
|
||||
sub_running_bw(&p->dl, &rq->dl);
|
||||
sub_rq_bw(&p->dl, &rq->dl);
|
||||
}
|
||||
|
||||
/*
|
||||
|
|
@ -1564,7 +1625,7 @@ static void migrate_task_rq_dl(struct task_struct *p)
|
|||
*/
|
||||
raw_spin_lock(&rq->lock);
|
||||
if (p->dl.dl_non_contending) {
|
||||
sub_running_bw(p->dl.dl_bw, &rq->dl);
|
||||
sub_running_bw(&p->dl, &rq->dl);
|
||||
p->dl.dl_non_contending = 0;
|
||||
/*
|
||||
* If the timer handler is currently running and the
|
||||
|
|
@ -1576,7 +1637,7 @@ static void migrate_task_rq_dl(struct task_struct *p)
|
|||
if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1)
|
||||
put_task_struct(p);
|
||||
}
|
||||
sub_rq_bw(p->dl.dl_bw, &rq->dl);
|
||||
sub_rq_bw(&p->dl, &rq->dl);
|
||||
raw_spin_unlock(&rq->lock);
|
||||
}
|
||||
|
||||
|
|
@ -2019,11 +2080,11 @@ retry:
|
|||
}
|
||||
|
||||
deactivate_task(rq, next_task, 0);
|
||||
sub_running_bw(next_task->dl.dl_bw, &rq->dl);
|
||||
sub_rq_bw(next_task->dl.dl_bw, &rq->dl);
|
||||
sub_running_bw(&next_task->dl, &rq->dl);
|
||||
sub_rq_bw(&next_task->dl, &rq->dl);
|
||||
set_task_cpu(next_task, later_rq->cpu);
|
||||
add_rq_bw(next_task->dl.dl_bw, &later_rq->dl);
|
||||
add_running_bw(next_task->dl.dl_bw, &later_rq->dl);
|
||||
add_rq_bw(&next_task->dl, &later_rq->dl);
|
||||
add_running_bw(&next_task->dl, &later_rq->dl);
|
||||
activate_task(later_rq, next_task, 0);
|
||||
ret = 1;
|
||||
|
||||
|
|
@ -2111,11 +2172,11 @@ static void pull_dl_task(struct rq *this_rq)
|
|||
resched = true;
|
||||
|
||||
deactivate_task(src_rq, p, 0);
|
||||
sub_running_bw(p->dl.dl_bw, &src_rq->dl);
|
||||
sub_rq_bw(p->dl.dl_bw, &src_rq->dl);
|
||||
sub_running_bw(&p->dl, &src_rq->dl);
|
||||
sub_rq_bw(&p->dl, &src_rq->dl);
|
||||
set_task_cpu(p, this_cpu);
|
||||
add_rq_bw(p->dl.dl_bw, &this_rq->dl);
|
||||
add_running_bw(p->dl.dl_bw, &this_rq->dl);
|
||||
add_rq_bw(&p->dl, &this_rq->dl);
|
||||
add_running_bw(&p->dl, &this_rq->dl);
|
||||
activate_task(this_rq, p, 0);
|
||||
dmin = p->dl.deadline;
|
||||
|
||||
|
|
@ -2224,7 +2285,7 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p)
|
|||
task_non_contending(p);
|
||||
|
||||
if (!task_on_rq_queued(p))
|
||||
sub_rq_bw(p->dl.dl_bw, &rq->dl);
|
||||
sub_rq_bw(&p->dl, &rq->dl);
|
||||
|
||||
/*
|
||||
* We cannot use inactive_task_timer() to invoke sub_running_bw()
|
||||
|
|
@ -2256,7 +2317,7 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
|
|||
|
||||
/* If p is not queued we will update its parameters at next wakeup. */
|
||||
if (!task_on_rq_queued(p)) {
|
||||
add_rq_bw(p->dl.dl_bw, &rq->dl);
|
||||
add_rq_bw(&p->dl, &rq->dl);
|
||||
|
||||
return;
|
||||
}
|
||||
|
|
@ -2435,6 +2496,9 @@ int sched_dl_overflow(struct task_struct *p, int policy,
|
|||
u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
|
||||
int cpus, err = -1;
|
||||
|
||||
if (attr->sched_flags & SCHED_FLAG_SUGOV)
|
||||
return 0;
|
||||
|
||||
/* !deadline task may carry old deadline bandwidth */
|
||||
if (new_bw == p->dl.dl_bw && task_has_dl_policy(p))
|
||||
return 0;
|
||||
|
|
@ -2521,6 +2585,10 @@ void __getparam_dl(struct task_struct *p, struct sched_attr *attr)
|
|||
*/
|
||||
bool __checkparam_dl(const struct sched_attr *attr)
|
||||
{
|
||||
/* special dl tasks don't actually use any parameter */
|
||||
if (attr->sched_flags & SCHED_FLAG_SUGOV)
|
||||
return true;
|
||||
|
||||
/* deadline != 0 */
|
||||
if (attr->sched_deadline == 0)
|
||||
return false;
|
||||
|
|
@ -2566,6 +2634,7 @@ void __dl_clear_params(struct task_struct *p)
|
|||
dl_se->dl_throttled = 0;
|
||||
dl_se->dl_yielded = 0;
|
||||
dl_se->dl_non_contending = 0;
|
||||
dl_se->dl_overrun = 0;
|
||||
}
|
||||
|
||||
bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
|
||||
|
|
|
|||
|
|
@ -3020,9 +3020,7 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
|
|||
/*
|
||||
* There are a few boundary cases this might miss but it should
|
||||
* get called often enough that that should (hopefully) not be
|
||||
* a real problem -- added to that it only calls on the local
|
||||
* CPU, so if we enqueue remotely we'll miss an update, but
|
||||
* the next tick/schedule should update.
|
||||
* a real problem.
|
||||
*
|
||||
* It will not get called when we go idle, because the idle
|
||||
* thread is a different class (!fair), nor will the utilization
|
||||
|
|
@ -3091,8 +3089,6 @@ static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3)
|
|||
return c1 + c2 + c3;
|
||||
}
|
||||
|
||||
#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
|
||||
|
||||
/*
|
||||
* Accumulate the three separate parts of the sum; d1 the remainder
|
||||
* of the last (incomplete) period, d2 the span of full periods and d3
|
||||
|
|
@ -3122,7 +3118,7 @@ accumulate_sum(u64 delta, int cpu, struct sched_avg *sa,
|
|||
u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */
|
||||
u64 periods;
|
||||
|
||||
scale_freq = arch_scale_freq_capacity(NULL, cpu);
|
||||
scale_freq = arch_scale_freq_capacity(cpu);
|
||||
scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
|
||||
|
||||
delta += sa->period_contrib;
|
||||
|
|
@ -5689,8 +5685,8 @@ static int wake_wide(struct task_struct *p)
|
|||
* soonest. For the purpose of speed we only consider the waking and previous
|
||||
* CPU.
|
||||
*
|
||||
* wake_affine_idle() - only considers 'now', it check if the waking CPU is (or
|
||||
* will be) idle.
|
||||
* wake_affine_idle() - only considers 'now', it check if the waking CPU is
|
||||
* cache-affine and is (or will be) idle.
|
||||
*
|
||||
* wake_affine_weight() - considers the weight to reflect the average
|
||||
* scheduling latency of the CPUs. This seems to work
|
||||
|
|
@ -5701,7 +5697,13 @@ static bool
|
|||
wake_affine_idle(struct sched_domain *sd, struct task_struct *p,
|
||||
int this_cpu, int prev_cpu, int sync)
|
||||
{
|
||||
if (idle_cpu(this_cpu))
|
||||
/*
|
||||
* If this_cpu is idle, it implies the wakeup is from interrupt
|
||||
* context. Only allow the move if cache is shared. Otherwise an
|
||||
* interrupt intensive workload could force all tasks onto one
|
||||
* node depending on the IO topology or IRQ affinity settings.
|
||||
*/
|
||||
if (idle_cpu(this_cpu) && cpus_share_cache(this_cpu, prev_cpu))
|
||||
return true;
|
||||
|
||||
if (sync && cpu_rq(this_cpu)->nr_running == 1)
|
||||
|
|
@ -5765,12 +5767,12 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
|
|||
return affine;
|
||||
}
|
||||
|
||||
static inline int task_util(struct task_struct *p);
|
||||
static int cpu_util_wake(int cpu, struct task_struct *p);
|
||||
static inline unsigned long task_util(struct task_struct *p);
|
||||
static unsigned long cpu_util_wake(int cpu, struct task_struct *p);
|
||||
|
||||
static unsigned long capacity_spare_wake(int cpu, struct task_struct *p)
|
||||
{
|
||||
return capacity_orig_of(cpu) - cpu_util_wake(cpu, p);
|
||||
return max_t(long, capacity_of(cpu) - cpu_util_wake(cpu, p), 0);
|
||||
}
|
||||
|
||||
/*
|
||||
|
|
@ -5950,7 +5952,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this
|
|||
}
|
||||
} else if (shallowest_idle_cpu == -1) {
|
||||
load = weighted_cpuload(cpu_rq(i));
|
||||
if (load < min_load || (load == min_load && i == this_cpu)) {
|
||||
if (load < min_load) {
|
||||
min_load = load;
|
||||
least_loaded_cpu = i;
|
||||
}
|
||||
|
|
@ -6247,7 +6249,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
|
|||
* capacity_orig) as it useful for predicting the capacity required after task
|
||||
* migrations (scheduler-driven DVFS).
|
||||
*/
|
||||
static int cpu_util(int cpu)
|
||||
static unsigned long cpu_util(int cpu)
|
||||
{
|
||||
unsigned long util = cpu_rq(cpu)->cfs.avg.util_avg;
|
||||
unsigned long capacity = capacity_orig_of(cpu);
|
||||
|
|
@ -6255,7 +6257,7 @@ static int cpu_util(int cpu)
|
|||
return (util >= capacity) ? capacity : util;
|
||||
}
|
||||
|
||||
static inline int task_util(struct task_struct *p)
|
||||
static inline unsigned long task_util(struct task_struct *p)
|
||||
{
|
||||
return p->se.avg.util_avg;
|
||||
}
|
||||
|
|
@ -6264,7 +6266,7 @@ static inline int task_util(struct task_struct *p)
|
|||
* cpu_util_wake: Compute cpu utilization with any contributions from
|
||||
* the waking task p removed.
|
||||
*/
|
||||
static int cpu_util_wake(int cpu, struct task_struct *p)
|
||||
static unsigned long cpu_util_wake(int cpu, struct task_struct *p)
|
||||
{
|
||||
unsigned long util, capacity;
|
||||
|
||||
|
|
@ -6449,8 +6451,7 @@ static void task_dead_fair(struct task_struct *p)
|
|||
}
|
||||
#endif /* CONFIG_SMP */
|
||||
|
||||
static unsigned long
|
||||
wakeup_gran(struct sched_entity *curr, struct sched_entity *se)
|
||||
static unsigned long wakeup_gran(struct sched_entity *se)
|
||||
{
|
||||
unsigned long gran = sysctl_sched_wakeup_granularity;
|
||||
|
||||
|
|
@ -6492,7 +6493,7 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
|
|||
if (vdiff <= 0)
|
||||
return -1;
|
||||
|
||||
gran = wakeup_gran(curr, se);
|
||||
gran = wakeup_gran(se);
|
||||
if (vdiff > gran)
|
||||
return 1;
|
||||
|
||||
|
|
|
|||
|
|
@ -156,13 +156,39 @@ static inline int task_has_dl_policy(struct task_struct *p)
|
|||
return dl_policy(p->policy);
|
||||
}
|
||||
|
||||
#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
|
||||
|
||||
/*
|
||||
* !! For sched_setattr_nocheck() (kernel) only !!
|
||||
*
|
||||
* This is actually gross. :(
|
||||
*
|
||||
* It is used to make schedutil kworker(s) higher priority than SCHED_DEADLINE
|
||||
* tasks, but still be able to sleep. We need this on platforms that cannot
|
||||
* atomically change clock frequency. Remove once fast switching will be
|
||||
* available on such platforms.
|
||||
*
|
||||
* SUGOV stands for SchedUtil GOVernor.
|
||||
*/
|
||||
#define SCHED_FLAG_SUGOV 0x10000000
|
||||
|
||||
static inline bool dl_entity_is_special(struct sched_dl_entity *dl_se)
|
||||
{
|
||||
#ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
|
||||
return unlikely(dl_se->flags & SCHED_FLAG_SUGOV);
|
||||
#else
|
||||
return false;
|
||||
#endif
|
||||
}
|
||||
|
||||
/*
|
||||
* Tells if entity @a should preempt entity @b.
|
||||
*/
|
||||
static inline bool
|
||||
dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b)
|
||||
{
|
||||
return dl_time_before(a->deadline, b->deadline);
|
||||
return dl_entity_is_special(a) ||
|
||||
dl_time_before(a->deadline, b->deadline);
|
||||
}
|
||||
|
||||
/*
|
||||
|
|
@ -1328,47 +1354,6 @@ static inline int task_on_rq_migrating(struct task_struct *p)
|
|||
# define finish_arch_post_lock_switch() do { } while (0)
|
||||
#endif
|
||||
|
||||
static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
|
||||
{
|
||||
#ifdef CONFIG_SMP
|
||||
/*
|
||||
* We can optimise this out completely for !SMP, because the
|
||||
* SMP rebalancing from interrupt is the only thing that cares
|
||||
* here.
|
||||
*/
|
||||
next->on_cpu = 1;
|
||||
#endif
|
||||
}
|
||||
|
||||
static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
|
||||
{
|
||||
#ifdef CONFIG_SMP
|
||||
/*
|
||||
* After ->on_cpu is cleared, the task can be moved to a different CPU.
|
||||
* We must ensure this doesn't happen until the switch is completely
|
||||
* finished.
|
||||
*
|
||||
* In particular, the load of prev->state in finish_task_switch() must
|
||||
* happen before this.
|
||||
*
|
||||
* Pairs with the smp_cond_load_acquire() in try_to_wake_up().
|
||||
*/
|
||||
smp_store_release(&prev->on_cpu, 0);
|
||||
#endif
|
||||
#ifdef CONFIG_DEBUG_SPINLOCK
|
||||
/* this is a valid case when another task releases the spinlock */
|
||||
rq->lock.owner = current;
|
||||
#endif
|
||||
/*
|
||||
* If we are tracking spinlock dependencies then we have to
|
||||
* fix up the runqueue lock - which gets 'carried over' from
|
||||
* prev into current:
|
||||
*/
|
||||
spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
|
||||
|
||||
raw_spin_unlock_irq(&rq->lock);
|
||||
}
|
||||
|
||||
/*
|
||||
* wake flags
|
||||
*/
|
||||
|
|
@ -1687,17 +1672,17 @@ static inline int hrtick_enabled(struct rq *rq)
|
|||
|
||||
#endif /* CONFIG_SCHED_HRTICK */
|
||||
|
||||
#ifdef CONFIG_SMP
|
||||
extern void sched_avg_update(struct rq *rq);
|
||||
|
||||
#ifndef arch_scale_freq_capacity
|
||||
static __always_inline
|
||||
unsigned long arch_scale_freq_capacity(struct sched_domain *sd, int cpu)
|
||||
unsigned long arch_scale_freq_capacity(int cpu)
|
||||
{
|
||||
return SCHED_CAPACITY_SCALE;
|
||||
}
|
||||
#endif
|
||||
|
||||
#ifdef CONFIG_SMP
|
||||
extern void sched_avg_update(struct rq *rq);
|
||||
|
||||
#ifndef arch_scale_cpu_capacity
|
||||
static __always_inline
|
||||
unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
|
||||
|
|
@ -1711,10 +1696,17 @@ unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
|
|||
|
||||
static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
|
||||
{
|
||||
rq->rt_avg += rt_delta * arch_scale_freq_capacity(NULL, cpu_of(rq));
|
||||
rq->rt_avg += rt_delta * arch_scale_freq_capacity(cpu_of(rq));
|
||||
sched_avg_update(rq);
|
||||
}
|
||||
#else
|
||||
#ifndef arch_scale_cpu_capacity
|
||||
static __always_inline
|
||||
unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu)
|
||||
{
|
||||
return SCHED_CAPACITY_SCALE;
|
||||
}
|
||||
#endif
|
||||
static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { }
|
||||
static inline void sched_avg_update(struct rq *rq) { }
|
||||
#endif
|
||||
|
|
@ -2096,14 +2088,14 @@ DECLARE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
|
|||
* The way cpufreq is currently arranged requires it to evaluate the CPU
|
||||
* performance state (frequency/voltage) on a regular basis to prevent it from
|
||||
* being stuck in a completely inadequate performance level for too long.
|
||||
* That is not guaranteed to happen if the updates are only triggered from CFS,
|
||||
* though, because they may not be coming in if RT or deadline tasks are active
|
||||
* all the time (or there are RT and DL tasks only).
|
||||
* That is not guaranteed to happen if the updates are only triggered from CFS
|
||||
* and DL, though, because they may not be coming in if only RT tasks are
|
||||
* active all the time (or there are RT tasks only).
|
||||
*
|
||||
* As a workaround for that issue, this function is called by the RT and DL
|
||||
* sched classes to trigger extra cpufreq updates to prevent it from stalling,
|
||||
* As a workaround for that issue, this function is called periodically by the
|
||||
* RT sched class to trigger extra cpufreq updates to prevent it from stalling,
|
||||
* but that really is a band-aid. Going forward it should be replaced with
|
||||
* solutions targeted more specifically at RT and DL tasks.
|
||||
* solutions targeted more specifically at RT tasks.
|
||||
*/
|
||||
static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
|
||||
{
|
||||
|
|
@ -2125,3 +2117,17 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
|
|||
#else /* arch_scale_freq_capacity */
|
||||
#define arch_scale_freq_invariant() (false)
|
||||
#endif
|
||||
|
||||
#ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
|
||||
|
||||
static inline unsigned long cpu_util_dl(struct rq *rq)
|
||||
{
|
||||
return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT;
|
||||
}
|
||||
|
||||
static inline unsigned long cpu_util_cfs(struct rq *rq)
|
||||
{
|
||||
return rq->cfs.avg.util_avg;
|
||||
}
|
||||
|
||||
#endif
|
||||
|
|
|
|||
|
|
@ -14,6 +14,7 @@
|
|||
#include <linux/tick.h>
|
||||
#include <linux/workqueue.h>
|
||||
#include <linux/compat.h>
|
||||
#include <linux/sched/deadline.h>
|
||||
|
||||
#include "posix-timers.h"
|
||||
|
||||
|
|
@ -791,6 +792,14 @@ check_timers_list(struct list_head *timers,
|
|||
return 0;
|
||||
}
|
||||
|
||||
static inline void check_dl_overrun(struct task_struct *tsk)
|
||||
{
|
||||
if (tsk->dl.dl_overrun) {
|
||||
tsk->dl.dl_overrun = 0;
|
||||
__group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Check for any per-thread CPU timers that have fired and move them off
|
||||
* the tsk->cpu_timers[N] list onto the firing list. Here we update the
|
||||
|
|
@ -804,6 +813,9 @@ static void check_thread_timers(struct task_struct *tsk,
|
|||
u64 expires;
|
||||
unsigned long soft;
|
||||
|
||||
if (dl_task(tsk))
|
||||
check_dl_overrun(tsk);
|
||||
|
||||
/*
|
||||
* If cputime_expires is zero, then there are no active
|
||||
* per thread CPU timers.
|
||||
|
|
@ -906,6 +918,9 @@ static void check_process_timers(struct task_struct *tsk,
|
|||
struct task_cputime cputime;
|
||||
unsigned long soft;
|
||||
|
||||
if (dl_task(tsk))
|
||||
check_dl_overrun(tsk);
|
||||
|
||||
/*
|
||||
* If cputimer is not running, then there are no active
|
||||
* process wide timers (POSIX 1.b, itimers, RLIMIT_CPU).
|
||||
|
|
@ -1111,6 +1126,9 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
|
|||
return 1;
|
||||
}
|
||||
|
||||
if (dl_task(tsk) && tsk->dl.dl_overrun)
|
||||
return 1;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue