[RFC PATCH 12/30] cputime: Convert task/group cputime to nsecs

From: Frederic Weisbecker
Date: Fri Nov 28 2014 - 13:29:21 EST

Now that most cputime readers use the transition API which return the
task cputime in old style cputime_t, we can safely store the cputime in
nsecs.

Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
Cc: Heiko Carstens <heiko.carstens@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Martin Schwidefsky <schwidefsky@xxxxxxxxxx>
Cc: Oleg Nesterov <oleg@xxxxxxxxxx>
Cc: Paul Mackerras <paulus@xxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Tony Luck <tony.luck@xxxxxxxxx>
Cc: Wu Fengguang <fengguang.wu@xxxxxxxxx>
Signed-off-by: Frederic Weisbecker <fweisbec@xxxxxxxxx>
---
arch/alpha/kernel/osf_sys.c | 4 +--
fs/binfmt_elf.c | 11 ++++++--
fs/binfmt_elf_fdpic.c | 4 +--
fs/proc/array.c | 9 +++++--
include/linux/cputime.h | 12 +++++++++
include/linux/sched.h | 51 ++++++++++++++++++++++++------------
kernel/exit.c | 4 +--
kernel/sched/cputime.c | 63 ++++++++++++++++++++++-----------------------
kernel/sys.c | 16 ++++++------
9 files changed, 107 insertions(+), 67 deletions(-)

diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 5451c10..a6e4491 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -1155,8 +1155,8 @@ SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru)
r.ru_majflt = current->maj_flt;
break;
case RUSAGE_CHILDREN:
- utime_jiffies = cputime_to_jiffies(current->signal->cutime);
- stime_jiffies = cputime_to_jiffies(current->signal->cstime);
+ utime_jiffies = nsecs_to_jiffies(current->signal->cutime);
+ stime_jiffies = nsecs_to_jiffies(current->signal->cstime);
jiffies_to_timeval32(utime_jiffies, &r.ru_utime);
jiffies_to_timeval32(stime_jiffies, &r.ru_stime);
r.ru_minflt = current->signal->cmin_flt;
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 84149e2..646cfc3 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1283,6 +1283,8 @@ static void fill_note(struct memelfnote *note, const char *name, int type,
static void fill_prstatus(struct elf_prstatus *prstatus,
struct task_struct *p, long signr)
{
+ struct timeval tv;
+
prstatus->pr_info.si_signo = prstatus->pr_cursig = signr;
prstatus->pr_sigpend = p->pending.signal.sig[0];
prstatus->pr_sighold = p->blocked.sig[0];
@@ -1309,8 +1311,13 @@ static void fill_prstatus(struct elf_prstatus *prstatus,
cputime_to_timeval(utime, &prstatus->pr_utime);
cputime_to_timeval(stime, &prstatus->pr_stime);
}
- cputime_to_timeval(p->signal->cutime, &prstatus->pr_cutime);
- cputime_to_timeval(p->signal->cstime, &prstatus->pr_cstime);
+ tv = ns_to_timeval(p->signal->cutime);
+ prstatus->pr_cutime.tv_sec = tv.tv_sec;
+ prstatus->pr_cutime.tv_usec = tv.tv_usec;
+
+ tv = ns_to_timeval(p->signal->cstime);
+ prstatus->pr_cstime.tv_sec = tv.tv_sec;
+ prstatus->pr_cstime.tv_usec = tv.tv_usec;
}

static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p,
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 3dc8e5d..fecdb6d 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1352,8 +1352,8 @@ static void fill_prstatus(struct elf_prstatus *prstatus,
cputime_to_timeval(utime, &prstatus->pr_utime);
cputime_to_timeval(stime, &prstatus->pr_stime);
}
- cputime_to_timeval(p->signal->cutime, &prstatus->pr_cutime);
- cputime_to_timeval(p->signal->cstime, &prstatus->pr_cstime);
+ prstatus->pr_cutime = ns_to_timeval(p->signal->cutime);
+ prstatus->pr_cstime = ns_to_timeval(p->signal->cstime);

prstatus->pr_exec_fdpic_loadmap = p->mm->context.exec_fdpic_loadmap;
prstatus->pr_interp_fdpic_loadmap = p->mm->context.interp_fdpic_loadmap;
diff --git a/fs/proc/array.c b/fs/proc/array.c
index e4a8ef1..de4fe51 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -385,6 +385,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
unsigned long min_flt = 0, maj_flt = 0;
cputime_t cutime, cstime, utime, stime;
u64 cgtime, gtime;
+ u64 nutime, nstime;
unsigned long rsslim = 0;
char tcomm[sizeof(task->comm)];
unsigned long flags;
@@ -439,7 +440,9 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,

min_flt += sig->min_flt;
maj_flt += sig->maj_flt;
- thread_group_cputime_adjusted(task, &utime, &stime);
+ thread_group_cputime_adjusted(task, &nutime, &nstime);
+ utime = nsecs_to_cputime(nutime);
+ stime = nsecs_to_cputime(nstime);
gtime += sig->gtime;
}

@@ -455,7 +458,9 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
if (!whole) {
min_flt = task->min_flt;
maj_flt = task->maj_flt;
- task_cputime_adjusted(task, &utime, &stime);
+ task_cputime_adjusted(task, &nutime, &nstime);
+ utime = nsecs_to_cputime(nutime);
+ stime = nsecs_to_cputime(nstime);
gtime = task_gtime(task);
}

diff --git a/include/linux/cputime.h b/include/linux/cputime.h
index a225ab9..ff843a9 100644
--- a/include/linux/cputime.h
+++ b/include/linux/cputime.h
@@ -23,4 +23,16 @@
((__force cputime64_t) nsecs_to_cputime(__nsecs))
#endif

+#ifndef nsecs_to_scaled
+static inline u64 nsecs_to_scaled(u64 nsecs)
+{
+ cputime_t cputime, scaled;
+
+ cputime = nsecs_to_cputime(nsecs);
+ scaled = cputime_to_scaled(cputime);
+
+ return cputime_to_nsecs(scaled);
+}
+#endif
+
#endif /* __LINUX_CPUTIME_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 83f77bf..3be3b0b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -488,8 +488,8 @@ struct cpu_itimer {
* Gathers a generic snapshot of user and system time.
*/
struct cputime {
- cputime_t utime;
- cputime_t stime;
+ u64 utime;
+ u64 stime;
};

/**
@@ -507,8 +507,8 @@ struct cputime {
* of them in parallel.
*/
struct task_cputime {
- cputime_t utime;
- cputime_t stime;
+ u64 utime;
+ u64 stime;
unsigned long long sum_exec_runtime;
};

@@ -663,7 +663,7 @@ struct signal_struct {
* in __exit_signal, except for the group leader.
*/
seqlock_t stats_lock;
- cputime_t utime, stime, cutime, cstime;
+ u64 utime, stime, cutime, cstime;
u64 gtime;
u64 cgtime;
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
@@ -1380,7 +1380,7 @@ struct task_struct {
int __user *set_child_tid; /* CLONE_CHILD_SETTID */
int __user *clear_child_tid; /* CLONE_CHILD_CLEARTID */

- cputime_t utime, stime, utimescaled, stimescaled;
+ u64 utime, stime, utimescaled, stimescaled;
u64 gtime;
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
struct cputime prev_cputime;
@@ -1878,13 +1878,13 @@ static inline void put_task_struct(struct task_struct *t)

#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
extern void task_cputime(struct task_struct *t,
- cputime_t *utime, cputime_t *stime);
+ u64 *utime, u64 *stime);
extern void task_cputime_scaled(struct task_struct *t,
- cputime_t *utimescaled, cputime_t *stimescaled);
+ u64 *utimescaled, u64 *stimescaled);
extern u64 task_gtime(struct task_struct *t);
#else
static inline void task_cputime(struct task_struct *t,
- cputime_t *utime, cputime_t *stime)
+ u64 *utime, u64 *stime)
{
if (utime)
*utime = t->utime;
@@ -1893,8 +1893,8 @@ static inline void task_cputime(struct task_struct *t,
}

static inline void task_cputime_scaled(struct task_struct *t,
- cputime_t *utimescaled,
- cputime_t *stimescaled)
+ u64 *utimescaled,
+ u64 *stimescaled)
{
if (utimescaled)
*utimescaled = t->utimescaled;
@@ -1911,18 +1911,30 @@ static inline u64 task_gtime(struct task_struct *t)
static inline void task_cputime_t(struct task_struct *t,
cputime_t *utime, cputime_t *stime)
{
- task_cputime(t, utime, stime);
+ u64 ut, st;
+
+ task_cputime(t, &ut, &st);
+ if (utime)
+ *utime = nsecs_to_cputime(ut);
+ if (stime)
+ *stime = nsecs_to_cputime(st);
}

static inline void task_cputime_t_scaled(struct task_struct *t,
cputime_t *utimescaled,
cputime_t *stimescaled)
{
- task_cputime_scaled(t, utimescaled, stimescaled);
+ u64 ut, st;
+
+ task_cputime_scaled(t, &ut, &st);
+ if (utimescaled)
+ *utimescaled = nsecs_to_cputime(ut);
+ if (stimescaled)
+ *stimescaled = nsecs_to_cputime(st);
}

-extern void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
-extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
+extern void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st);
+extern void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st);

/*
* Per process flags
@@ -2924,9 +2936,14 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times);
void thread_group_cputimer(struct task_struct *tsk, struct task_cputime_t *times);

static inline void thread_group_cputime_t(struct task_struct *tsk,
- struct task_cputime_t *times)
+ struct task_cputime_t *cputime)
{
- thread_group_cputime(tsk, (struct task_cputime *)times);
+ struct task_cputime times;
+
+ thread_group_cputime(tsk, &times);
+ cputime->utime = nsecs_to_cputime(times.utime);
+ cputime->stime = nsecs_to_cputime(times.stime);
+ cputime->sum_exec_runtime = times.sum_exec_runtime;
}

static inline void thread_group_cputime_init(struct signal_struct *sig)
diff --git a/kernel/exit.c b/kernel/exit.c
index 5d30019..9df0729 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -86,7 +86,7 @@ static void __exit_signal(struct task_struct *tsk)
bool group_dead = thread_group_leader(tsk);
struct sighand_struct *sighand;
struct tty_struct *uninitialized_var(tty);
- cputime_t utime, stime;
+ u64 utime, stime;

sighand = rcu_dereference_check(tsk->sighand,
lockdep_tasklist_lock_is_held());
@@ -1022,7 +1022,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
struct signal_struct *psig;
struct signal_struct *sig;
unsigned long maxrss;
- cputime_t tgutime, tgstime;
+ u64 tgutime, tgstime;

/*
* The resource counters for the group leader are in its
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index f3701ab..eefe1ec 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -138,8 +138,8 @@ void account_user_time(struct task_struct *p, cputime_t cputime,
int index;

/* Add user time to process. */
- p->utime += cputime;
- p->utimescaled += cputime_scaled;
+ p->utime += cputime_to_nsecs(cputime);
+ p->utimescaled += cputime_to_nsecs(cputime_scaled);
account_group_user_time(p, cputime);

index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
@@ -163,10 +163,10 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime,
u64 *cpustat = kcpustat_this_cpu->cpustat;

/* Add guest time to process. */
- p->utime += cputime;
- p->utimescaled += cputime_scaled;
+ p->utime += cputime_to_nsecs(cputime);
+ p->utimescaled += cputime_to_nsecs(cputime_scaled);
account_group_user_time(p, cputime);
- p->gtime += cptime_to_nsecs(cputime);
+ p->gtime += cputime_to_nsecs(cputime);

/* Add guest time to cpustat. */
if (task_nice(p) > 0) {
@@ -190,8 +190,8 @@ void __account_system_time(struct task_struct *p, cputime_t cputime,
cputime_t cputime_scaled, int index)
{
/* Add system time to process. */
- p->stime += cputime;
- p->stimescaled += cputime_scaled;
+ p->stime += cputime_to_nsecs(cputime);
+ p->stimescaled += cputime_to_nsecs(cputime_scaled);
account_group_system_time(p, cputime);

/* Add system time to cpustat. */
@@ -286,7 +286,7 @@ static __always_inline bool steal_account_process_tick(void)
void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
{
struct signal_struct *sig = tsk->signal;
- cputime_t utime, stime;
+ u64 utime, stime;
struct task_struct *t;
unsigned int seq, nextseq;
unsigned long flags;
@@ -440,13 +440,13 @@ EXPORT_SYMBOL_GPL(vtime_common_account_irq_enter);


#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
+void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
{
*ut = p->utime;
*st = p->stime;
}

-void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
+void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
{
struct task_cputime cputime;

@@ -515,7 +515,7 @@ void account_idle_ticks(unsigned long ticks)
* Perform (stime * rtime) / total, but avoid multiplication overflow by
* loosing precision when the numbers are big.
*/
-static cputime_t scale_stime(u64 stime, u64 rtime, u64 total)
+static u64 scale_stime(u64 stime, u64 rtime, u64 total)
{
u64 scaled;

@@ -552,7 +552,7 @@ drop_precision:
* followed by a 64/32->64 divide.
*/
scaled = div_u64((u64) (u32) stime * (u64) (u32) rtime, (u32)total);
- return (__force cputime_t) scaled;
+ return scaled;
}

/*
@@ -564,12 +564,12 @@ drop_precision:
* Normally a caller will only go through this loop once, or not
* at all in case a previous caller updated counter the same jiffy.
*/
-static void cputime_advance(cputime_t *counter, cputime_t new)
+static void cputime_advance(u64 *counter, u64 new)
{
- cputime_t old;
+ u64 old;

while (new > (old = ACCESS_ONCE(*counter)))
- cmpxchg_cputime(counter, old, new);
+ cmpxchg64(counter, old, new);
}

/*
@@ -578,9 +578,9 @@ static void cputime_advance(cputime_t *counter, cputime_t new)
*/
static void cputime_adjust(struct task_cputime *curr,
struct cputime *prev,
- cputime_t *ut, cputime_t *st)
+ u64 *ut, u64 *st)
{
- cputime_t rtime, stime, utime;
+ u64 rtime, stime, utime;

/*
* Tick based cputime accounting depend on random scheduling
@@ -592,7 +592,7 @@ static void cputime_adjust(struct task_cputime *curr,
* Fix this by scaling these tick based values against the total
* runtime accounted by the CFS scheduler.
*/
- rtime = nsecs_to_cputime(curr->sum_exec_runtime);
+ rtime = curr->sum_exec_runtime;

/*
* Update userspace visible utime/stime values only if actual execution
@@ -610,10 +610,9 @@ static void cputime_adjust(struct task_cputime *curr,
} else if (stime == 0) {
utime = rtime;
} else {
- cputime_t total = stime + utime;
+ u64 total = stime + utime;

- stime = scale_stime((__force u64)stime,
- (__force u64)rtime, (__force u64)total);
+ stime = scale_stime(stime, rtime, total);
utime = rtime - stime;
}

@@ -625,7 +624,7 @@ out:
*st = prev->stime;
}

-void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
+void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
{
struct task_cputime cputime = {
.sum_exec_runtime = p->se.sum_exec_runtime,
@@ -635,7 +634,7 @@ void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
cputime_adjust(&cputime, &p->prev_cputime, ut, st);
}

-void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
+void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
{
struct task_cputime cputime;

@@ -787,9 +786,9 @@ u64 task_gtime(struct task_struct *t)
*/
static void
fetch_task_cputime(struct task_struct *t,
- cputime_t *u_dst, cputime_t *s_dst,
- cputime_t *u_src, cputime_t *s_src,
- cputime_t *udelta, cputime_t *sdelta)
+ u64 *u_dst, u64 *s_dst,
+ u64 *u_src, u64 *s_src,
+ u64 *udelta, u64 *sdelta)
{
unsigned int seq;
unsigned long long delta;
@@ -826,9 +825,9 @@ fetch_task_cputime(struct task_struct *t,
}


-void task_cputime(struct task_struct *t, cputime_t *utime, cputime_t *stime)
+void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
{
- cputime_t udelta, sdelta;
+ u64 udelta, sdelta;

fetch_task_cputime(t, utime, stime, &t->utime,
&t->stime, &udelta, &sdelta);
@@ -839,15 +838,15 @@ void task_cputime(struct task_struct *t, cputime_t *utime, cputime_t *stime)
}

void task_cputime_scaled(struct task_struct *t,
- cputime_t *utimescaled, cputime_t *stimescaled)
+ u64 *utimescaled, u64 *stimescaled)
{
- cputime_t udelta, sdelta;
+ u64 udelta, sdelta;

fetch_task_cputime(t, utimescaled, stimescaled,
&t->utimescaled, &t->stimescaled, &udelta, &sdelta);
if (utimescaled)
- *utimescaled += cputime_to_scaled(udelta);
+ *utimescaled += nsecs_to_scaled(udelta);
if (stimescaled)
- *stimescaled += cputime_to_scaled(sdelta);
+ *stimescaled += nsecs_to_scaled(sdelta);
}
#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */
diff --git a/kernel/sys.c b/kernel/sys.c
index 1eaa2f0..aa9dab9 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -867,15 +867,15 @@ SYSCALL_DEFINE0(getegid)

void do_sys_times(struct tms *tms)
{
- cputime_t tgutime, tgstime, cutime, cstime;
+ u64 tgutime, tgstime, cutime, cstime;

thread_group_cputime_adjusted(current, &tgutime, &tgstime);
cutime = current->signal->cutime;
cstime = current->signal->cstime;
- tms->tms_utime = cputime_to_clock_t(tgutime);
- tms->tms_stime = cputime_to_clock_t(tgstime);
- tms->tms_cutime = cputime_to_clock_t(cutime);
- tms->tms_cstime = cputime_to_clock_t(cstime);
+ tms->tms_utime = nsec_to_clock_t(tgutime);
+ tms->tms_stime = nsec_to_clock_t(tgstime);
+ tms->tms_cutime = nsec_to_clock_t(cutime);
+ tms->tms_cstime = nsec_to_clock_t(cstime);
}

SYSCALL_DEFINE1(times, struct tms __user *, tbuf)
@@ -1528,7 +1528,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
{
struct task_struct *t;
unsigned long flags;
- cputime_t tgutime, tgstime, utime, stime;
+ u64 tgutime, tgstime, utime, stime;
unsigned long maxrss = 0;

memset((char *)r, 0, sizeof (*r));
@@ -1584,8 +1584,8 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
unlock_task_sighand(p, &flags);

out:
- cputime_to_timeval(utime, &r->ru_utime);
- cputime_to_timeval(stime, &r->ru_stime);
+ r->ru_utime = ns_to_timeval(utime);
+ r->ru_stime = ns_to_timeval(stime);

if (who != RUSAGE_CHILDREN) {
struct mm_struct *mm = get_task_mm(p);
--
2.1.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/