[tip:sched/core] timers/itimer: Convert internal cputime_t units to nsec

From: tip-bot for Frederic Weisbecker
Date: Wed Feb 01 2017 - 05:00:59 EST

Commit-ID: 858cf3a8c59968e7c5f7c1a1192459a0d52d1ab4
Gitweb: http://git.kernel.org/tip/858cf3a8c59968e7c5f7c1a1192459a0d52d1ab4
Author: Frederic Weisbecker <fweisbec@xxxxxxxxx>
AuthorDate: Tue, 31 Jan 2017 04:09:35 +0100
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Wed, 1 Feb 2017 09:13:55 +0100

timers/itimer: Convert internal cputime_t units to nsec

Use the new nsec based cputime accessors as part of the whole cputime
conversion from cputime_t to nsecs.

Also convert itimers to use nsec based internal counters. This simplifies
it and removes the whole game with error/inc_error which served to deal
with cputime_t random granularity.

Signed-off-by: Frederic Weisbecker <fweisbec@xxxxxxxxx>
Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
Cc: Fenghua Yu <fenghua.yu@xxxxxxxxx>
Cc: Heiko Carstens <heiko.carstens@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Martin Schwidefsky <schwidefsky@xxxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Paul Mackerras <paulus@xxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Stanislaw Gruszka <sgruszka@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Tony Luck <tony.luck@xxxxxxxxx>
Cc: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>
Link: http://lkml.kernel.org/r/1485832191-26889-20-git-send-email-fweisbec@xxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
include/linux/posix-timers.h | 2 +-
include/linux/sched.h | 6 ++--
include/trace/events/timer.h | 26 ++++++++---------
kernel/time/itimer.c | 64 +++++++++++++++---------------------------
kernel/time/posix-cpu-timers.c | 43 +++++++++++-----------------
5 files changed, 55 insertions(+), 86 deletions(-)

diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 890de52..64aa189 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -119,7 +119,7 @@ void run_posix_cpu_timers(struct task_struct *task);
void posix_cpu_timers_exit(struct task_struct *task);
void posix_cpu_timers_exit_group(struct task_struct *task);
void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx,
- cputime_t *newval, cputime_t *oldval);
+ u64 *newval, u64 *oldval);

long clock_nanosleep_restart(struct restart_block *restart_block);

diff --git a/include/linux/sched.h b/include/linux/sched.h
index baa6a28..268fdd7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -568,10 +568,8 @@ struct pacct_struct {
};

struct cpu_itimer {
- cputime_t expires;
- cputime_t incr;
- u32 error;
- u32 incr_error;
+ u64 expires;
+ u64 incr;
};

/**
diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h
index 1448637..1bca99d 100644
--- a/include/trace/events/timer.h
+++ b/include/trace/events/timer.h
@@ -269,17 +269,17 @@ DEFINE_EVENT(hrtimer_class, hrtimer_cancel,
TRACE_EVENT(itimer_state,

TP_PROTO(int which, const struct itimerval *const value,
- cputime_t expires),
+ unsigned long long expires),

TP_ARGS(which, value, expires),

TP_STRUCT__entry(
- __field( int, which )
- __field( cputime_t, expires )
- __field( long, value_sec )
- __field( long, value_usec )
- __field( long, interval_sec )
- __field( long, interval_usec )
+ __field( int, which )
+ __field( unsigned long long, expires )
+ __field( long, value_sec )
+ __field( long, value_usec )
+ __field( long, interval_sec )
+ __field( long, interval_usec )
),

TP_fast_assign(
@@ -292,7 +292,7 @@ TRACE_EVENT(itimer_state,
),

TP_printk("which=%d expires=%llu it_value=%ld.%ld it_interval=%ld.%ld",
- __entry->which, (unsigned long long)__entry->expires,
+ __entry->which, __entry->expires,
__entry->value_sec, __entry->value_usec,
__entry->interval_sec, __entry->interval_usec)
);
@@ -305,14 +305,14 @@ TRACE_EVENT(itimer_state,
*/
TRACE_EVENT(itimer_expire,

- TP_PROTO(int which, struct pid *pid, cputime_t now),
+ TP_PROTO(int which, struct pid *pid, unsigned long long now),

TP_ARGS(which, pid, now),

TP_STRUCT__entry(
- __field( int , which )
- __field( pid_t, pid )
- __field( cputime_t, now )
+ __field( int , which )
+ __field( pid_t, pid )
+ __field( unsigned long long, now )
),

TP_fast_assign(
@@ -322,7 +322,7 @@ TRACE_EVENT(itimer_expire,
),

TP_printk("which=%d pid=%d now=%llu", __entry->which,
- (int) __entry->pid, (unsigned long long)__entry->now)
+ (int) __entry->pid, __entry->now)
);

#ifdef CONFIG_NO_HZ_COMMON
diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c
index bb01ff4..a95f13c 100644
--- a/kernel/time/itimer.c
+++ b/kernel/time/itimer.c
@@ -45,35 +45,35 @@ static struct timeval itimer_get_remtime(struct hrtimer *timer)
static void get_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
struct itimerval *const value)
{
- cputime_t cval, cinterval;
+ u64 val, interval;
struct cpu_itimer *it = &tsk->signal->it[clock_id];

spin_lock_irq(&tsk->sighand->siglock);

- cval = it->expires;
- cinterval = it->incr;
- if (cval) {
+ val = it->expires;
+ interval = it->incr;
+ if (val) {
struct task_cputime cputime;
- cputime_t t;
+ u64 t;

thread_group_cputimer(tsk, &cputime);
if (clock_id == CPUCLOCK_PROF)
- t = nsecs_to_cputime(cputime.utime + cputime.stime);
+ t = cputime.utime + cputime.stime;
else
/* CPUCLOCK_VIRT */
- t = nsecs_to_cputime(cputime.utime);
+ t = cputime.utime;

- if (cval < t)
+ if (val < t)
/* about to fire */
- cval = cputime_one_jiffy;
+ val = TICK_NSEC;
else
- cval = cval - t;
+ val -= t;
}

spin_unlock_irq(&tsk->sighand->siglock);

- cputime_to_timeval(cval, &value->it_value);
- cputime_to_timeval(cinterval, &value->it_interval);
+ value->it_value = ns_to_timeval(val);
+ value->it_interval = ns_to_timeval(interval);
}

int do_getitimer(int which, struct itimerval *value)
@@ -129,55 +129,35 @@ enum hrtimer_restart it_real_fn(struct hrtimer *timer)
return HRTIMER_NORESTART;
}

-static inline u32 cputime_sub_ns(cputime_t ct, s64 real_ns)
-{
- struct timespec ts;
- s64 cpu_ns;
-
- cputime_to_timespec(ct, &ts);
- cpu_ns = timespec_to_ns(&ts);
-
- return (cpu_ns <= real_ns) ? 0 : cpu_ns - real_ns;
-}
-
static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
const struct itimerval *const value,
struct itimerval *const ovalue)
{
- cputime_t cval, nval, cinterval, ninterval;
- s64 ns_ninterval, ns_nval;
- u32 error, incr_error;
+ u64 oval, nval, ointerval, ninterval;
struct cpu_itimer *it = &tsk->signal->it[clock_id];

- nval = timeval_to_cputime(&value->it_value);
- ns_nval = timeval_to_ns(&value->it_value);
- ninterval = timeval_to_cputime(&value->it_interval);
- ns_ninterval = timeval_to_ns(&value->it_interval);
-
- error = cputime_sub_ns(nval, ns_nval);
- incr_error = cputime_sub_ns(ninterval, ns_ninterval);
+ nval = timeval_to_ns(&value->it_value);
+ ninterval = timeval_to_ns(&value->it_interval);

spin_lock_irq(&tsk->sighand->siglock);

- cval = it->expires;
- cinterval = it->incr;
- if (cval || nval) {
+ oval = it->expires;
+ ointerval = it->incr;
+ if (oval || nval) {
if (nval > 0)
- nval += cputime_one_jiffy;
- set_process_cpu_timer(tsk, clock_id, &nval, &cval);
+ nval += TICK_NSEC;
+ set_process_cpu_timer(tsk, clock_id, &nval, &oval);
}
it->expires = nval;
it->incr = ninterval;
- it->error = error;
- it->incr_error = incr_error;
trace_itimer_state(clock_id == CPUCLOCK_VIRT ?
ITIMER_VIRTUAL : ITIMER_PROF, value, nval);

spin_unlock_irq(&tsk->sighand->siglock);

if (ovalue) {
- cputime_to_timeval(cval, &ovalue->it_value);
- cputime_to_timeval(cinterval, &ovalue->it_interval);
+ ovalue->it_value = ns_to_timeval(oval);
+ ovalue->it_interval = ns_to_timeval(ointerval);
}
}

diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 45be3ce..b4377a5 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -20,10 +20,10 @@
*/
void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new)
{
- cputime_t cputime = secs_to_cputime(rlim_new);
+ u64 nsecs = rlim_new * NSEC_PER_SEC;

spin_lock_irq(&task->sighand->siglock);
- set_process_cpu_timer(task, CPUCLOCK_PROF, &cputime, NULL);
+ set_process_cpu_timer(task, CPUCLOCK_PROF, &nsecs, NULL);
spin_unlock_irq(&task->sighand->siglock);
}

@@ -860,17 +860,11 @@ static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
if (!it->expires)
return;

- if (cur_time >= cputime_to_nsecs(it->expires)) {
- if (it->incr) {
+ if (cur_time >= it->expires) {
+ if (it->incr)
it->expires += it->incr;
- it->error += it->incr_error;
- if (it->error >= TICK_NSEC) {
- it->expires -= cputime_one_jiffy;
- it->error -= TICK_NSEC;
- }
- } else {
+ else
it->expires = 0;
- }

trace_itimer_expire(signo == SIGPROF ?
ITIMER_PROF : ITIMER_VIRTUAL,
@@ -878,9 +872,8 @@ static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
__group_send_sig_info(signo, SEND_SIG_PRIV, tsk);
}

- if (it->expires && (!*expires || cputime_to_nsecs(it->expires) < *expires)) {
- *expires = cputime_to_nsecs(it->expires);
- }
+ if (it->expires && (!*expires || it->expires < *expires))
+ *expires = it->expires;
}

/*
@@ -1174,9 +1167,9 @@ void run_posix_cpu_timers(struct task_struct *tsk)
* The tsk->sighand->siglock must be held by the caller.
*/
void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
- cputime_t *newval, cputime_t *oldval)
+ u64 *newval, u64 *oldval)
{
- u64 now, new;
+ u64 now;

WARN_ON_ONCE(clock_idx == CPUCLOCK_SCHED);
cpu_timer_sample_group(clock_idx, tsk, &now);
@@ -1188,33 +1181,31 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
* it to be absolute.
*/
if (*oldval) {
- if (cputime_to_nsecs(*oldval) <= now) {
+ if (*oldval <= now) {
/* Just about to fire. */
- *oldval = cputime_one_jiffy;
+ *oldval = TICK_NSEC;
} else {
- *oldval -= nsecs_to_cputime(now);
+ *oldval -= now;
}
}

if (!*newval)
return;
- *newval += nsecs_to_cputime(now);
+ *newval += now;
}

- new = cputime_to_nsecs(*newval);
-
/*
* Update expiration cache if we are the earliest timer, or eventually
* RLIMIT_CPU limit is earlier than prof_exp cpu timer expire.
*/
switch (clock_idx) {
case CPUCLOCK_PROF:
- if (expires_gt(tsk->signal->cputime_expires.prof_exp, new))
- tsk->signal->cputime_expires.prof_exp = new;
+ if (expires_gt(tsk->signal->cputime_expires.prof_exp, *newval))
+ tsk->signal->cputime_expires.prof_exp = *newval;
break;
case CPUCLOCK_VIRT:
- if (expires_gt(tsk->signal->cputime_expires.virt_exp, new))
- tsk->signal->cputime_expires.virt_exp = new;
+ if (expires_gt(tsk->signal->cputime_expires.virt_exp, *newval))
+ tsk->signal->cputime_expires.virt_exp = *newval;
break;
}