linux/kernel/sched/stats.h
Peter Zijlstra c5895d3f06 sched: Simplify sched_info_on()
The situation around sched_info is somewhat complicated, it is used by
sched_stats and delayacct and, indirectly, kvm.

If SCHEDSTATS=Y (but disabled by default) sched_info_on() is
unconditionally true -- this is the case for all distro kernel configs
I checked.

If for some reason SCHEDSTATS=N, but TASK_DELAY_ACCT=Y, then
sched_info_on() can return false when delayacct is disabled,
presumably because there would be no other users left; except kvm is.

Instead of complicating matters further by accurately accounting
sched_stat and kvm state, simply unconditionally enable when
SCHED_INFO=Y, matching the common distro case.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lkml.kernel.org/r/20210505111525.121458839@infradead.org
2021-05-12 11:43:24 +02:00

246 lines
7.2 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifdef CONFIG_SCHEDSTATS
/*
* Expects runqueue lock to be held for atomicity of update
*/
static inline void
rq_sched_info_arrive(struct rq *rq, unsigned long long delta)
{
if (rq) {
rq->rq_sched_info.run_delay += delta;
rq->rq_sched_info.pcount++;
}
}
/*
* Expects runqueue lock to be held for atomicity of update
*/
static inline void
rq_sched_info_depart(struct rq *rq, unsigned long long delta)
{
if (rq)
rq->rq_cpu_time += delta;
}
static inline void
rq_sched_info_dequeue(struct rq *rq, unsigned long long delta)
{
if (rq)
rq->rq_sched_info.run_delay += delta;
}
#define schedstat_enabled() static_branch_unlikely(&sched_schedstats)
#define __schedstat_inc(var) do { var++; } while (0)
#define schedstat_inc(var) do { if (schedstat_enabled()) { var++; } } while (0)
#define __schedstat_add(var, amt) do { var += (amt); } while (0)
#define schedstat_add(var, amt) do { if (schedstat_enabled()) { var += (amt); } } while (0)
#define __schedstat_set(var, val) do { var = (val); } while (0)
#define schedstat_set(var, val) do { if (schedstat_enabled()) { var = (val); } } while (0)
#define schedstat_val(var) (var)
#define schedstat_val_or_zero(var) ((schedstat_enabled()) ? (var) : 0)
#else /* !CONFIG_SCHEDSTATS: */
static inline void rq_sched_info_arrive (struct rq *rq, unsigned long long delta) { }
static inline void rq_sched_info_dequeue(struct rq *rq, unsigned long long delta) { }
static inline void rq_sched_info_depart (struct rq *rq, unsigned long long delta) { }
# define schedstat_enabled() 0
# define __schedstat_inc(var) do { } while (0)
# define schedstat_inc(var) do { } while (0)
# define __schedstat_add(var, amt) do { } while (0)
# define schedstat_add(var, amt) do { } while (0)
# define __schedstat_set(var, val) do { } while (0)
# define schedstat_set(var, val) do { } while (0)
# define schedstat_val(var) 0
# define schedstat_val_or_zero(var) 0
#endif /* CONFIG_SCHEDSTATS */
#ifdef CONFIG_PSI
/*
* PSI tracks state that persists across sleeps, such as iowaits and
* memory stalls. As a result, it has to distinguish between sleeps,
* where a task's runnable state changes, and requeues, where a task
* and its state are being moved between CPUs and runqueues.
*/
static inline void psi_enqueue(struct task_struct *p, bool wakeup)
{
int clear = 0, set = TSK_RUNNING;
if (static_branch_likely(&psi_disabled))
return;
if (!wakeup || p->sched_psi_wake_requeue) {
if (p->in_memstall)
set |= TSK_MEMSTALL;
if (p->sched_psi_wake_requeue)
p->sched_psi_wake_requeue = 0;
} else {
if (p->in_iowait)
clear |= TSK_IOWAIT;
}
psi_task_change(p, clear, set);
}
static inline void psi_dequeue(struct task_struct *p, bool sleep)
{
int clear = TSK_RUNNING;
if (static_branch_likely(&psi_disabled))
return;
/*
* A voluntary sleep is a dequeue followed by a task switch. To
* avoid walking all ancestors twice, psi_task_switch() handles
* TSK_RUNNING and TSK_IOWAIT for us when it moves TSK_ONCPU.
* Do nothing here.
*/
if (sleep)
return;
if (p->in_memstall)
clear |= TSK_MEMSTALL;
psi_task_change(p, clear, 0);
}
static inline void psi_ttwu_dequeue(struct task_struct *p)
{
if (static_branch_likely(&psi_disabled))
return;
/*
* Is the task being migrated during a wakeup? Make sure to
* deregister its sleep-persistent psi states from the old
* queue, and let psi_enqueue() know it has to requeue.
*/
if (unlikely(p->in_iowait || p->in_memstall)) {
struct rq_flags rf;
struct rq *rq;
int clear = 0;
if (p->in_iowait)
clear |= TSK_IOWAIT;
if (p->in_memstall)
clear |= TSK_MEMSTALL;
rq = __task_rq_lock(p, &rf);
psi_task_change(p, clear, 0);
p->sched_psi_wake_requeue = 1;
__task_rq_unlock(rq, &rf);
}
}
static inline void psi_sched_switch(struct task_struct *prev,
struct task_struct *next,
bool sleep)
{
if (static_branch_likely(&psi_disabled))
return;
psi_task_switch(prev, next, sleep);
}
#else /* CONFIG_PSI */
static inline void psi_enqueue(struct task_struct *p, bool wakeup) {}
static inline void psi_dequeue(struct task_struct *p, bool sleep) {}
static inline void psi_ttwu_dequeue(struct task_struct *p) {}
static inline void psi_sched_switch(struct task_struct *prev,
struct task_struct *next,
bool sleep) {}
#endif /* CONFIG_PSI */
#ifdef CONFIG_SCHED_INFO
/*
* We are interested in knowing how long it was from the *first* time a
* task was queued to the time that it finally hit a CPU, we call this routine
* from dequeue_task() to account for possible rq->clock skew across CPUs. The
* delta taken on each CPU would annul the skew.
*/
static inline void sched_info_dequeue(struct rq *rq, struct task_struct *t)
{
unsigned long long delta = 0;
if (t->sched_info.last_queued) {
delta = rq_clock(rq) - t->sched_info.last_queued;
t->sched_info.last_queued = 0;
}
t->sched_info.run_delay += delta;
rq_sched_info_dequeue(rq, delta);
}
/*
* Called when a task finally hits the CPU. We can now calculate how
* long it was waiting to run. We also note when it began so that we
* can keep stats on how long its timeslice is.
*/
static void sched_info_arrive(struct rq *rq, struct task_struct *t)
{
unsigned long long now = rq_clock(rq), delta = 0;
if (t->sched_info.last_queued) {
delta = now - t->sched_info.last_queued;
t->sched_info.last_queued = 0;
}
t->sched_info.run_delay += delta;
t->sched_info.last_arrival = now;
t->sched_info.pcount++;
rq_sched_info_arrive(rq, delta);
}
/*
* This function is only called from enqueue_task(), but also only updates
* the timestamp if it is already not set. It's assumed that
* sched_info_dequeue() will clear that stamp when appropriate.
*/
static inline void sched_info_enqueue(struct rq *rq, struct task_struct *t)
{
if (!t->sched_info.last_queued)
t->sched_info.last_queued = rq_clock(rq);
}
/*
* Called when a process ceases being the active-running process involuntarily
* due, typically, to expiring its time slice (this may also be called when
* switching to the idle task). Now we can calculate how long we ran.
* Also, if the process is still in the TASK_RUNNING state, call
* sched_info_enqueue() to mark that it has now again started waiting on
* the runqueue.
*/
static inline void sched_info_depart(struct rq *rq, struct task_struct *t)
{
unsigned long long delta = rq_clock(rq) - t->sched_info.last_arrival;
rq_sched_info_depart(rq, delta);
if (t->state == TASK_RUNNING)
sched_info_enqueue(rq, t);
}
/*
* Called when tasks are switched involuntarily due, typically, to expiring
* their time slice. (This may also be called when switching to or from
* the idle task.) We are only called when prev != next.
*/
static inline void
sched_info_switch(struct rq *rq, struct task_struct *prev, struct task_struct *next)
{
/*
* prev now departs the CPU. It's not interesting to record
* stats about how efficient we were at scheduling the idle
* process, however.
*/
if (prev != rq->idle)
sched_info_depart(rq, prev);
if (next != rq->idle)
sched_info_arrive(rq, next);
}
#else /* !CONFIG_SCHED_INFO: */
# define sched_info_enqueue(rq, t) do { } while (0)
# define sched_info_dequeue(rq, t) do { } while (0)
# define sched_info_switch(rq, t, next) do { } while (0)
#endif /* CONFIG_SCHED_INFO */