[PATCH 6/7] cputime: Use accessors to read task cputime stats

From: Frederic Weisbecker
Date: Thu Jan 17 2013 - 08:25:31 EST


This is in preparation for the full dynticks feature. While
remotely reading the cputime of a task running in a full
dynticks CPU, we'll need to do some extra-computation. This
way we can account the time it spent tickless in userspace
since its last cputime snapshot.

Signed-off-by: Frederic Weisbecker <fweisbec@xxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Li Zhong <zhong@xxxxxxxxxxxxxxxxxx>
Cc: Namhyung Kim <namhyung.kim@xxxxxxx>
Cc: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
Cc: Paul Gortmaker <paul.gortmaker@xxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
---
arch/alpha/kernel/osf_sys.c | 6 +++-
arch/x86/kernel/apm_32.c | 11 +++++----
drivers/isdn/mISDN/stack.c | 7 +++++-
fs/binfmt_elf.c | 8 +++++-
fs/binfmt_elf_fdpic.c | 7 ++++-
include/linux/sched.h | 18 +++++++++++++++++
include/linux/tsacct_kern.h | 3 ++
kernel/acct.c | 6 +++-
kernel/cpu.c | 4 ++-
kernel/delayacct.c | 7 ++++-
kernel/exit.c | 6 +++-
kernel/posix-cpu-timers.c | 28 +++++++++++++++++++++-----
kernel/sched/cputime.c | 13 ++++++-----
kernel/signal.c | 12 +++++++---
kernel/tsacct.c | 44 +++++++++++++++++++++++++++++++++---------
15 files changed, 135 insertions(+), 45 deletions(-)

diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 14db93e..dbc1760 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -1139,6 +1139,7 @@ struct rusage32 {
SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru)
{
struct rusage32 r;
+ cputime_t utime, stime;

if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN)
return -EINVAL;
@@ -1146,8 +1147,9 @@ SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru)
memset(&r, 0, sizeof(r));
switch (who) {
case RUSAGE_SELF:
- jiffies_to_timeval32(current->utime, &r.ru_utime);
- jiffies_to_timeval32(current->stime, &r.ru_stime);
+ task_cputime(current, &utime, &stime);
+ jiffies_to_timeval32(utime, &r.ru_utime);
+ jiffies_to_timeval32(stime, &r.ru_stime);
r.ru_minflt = current->min_flt;
r.ru_majflt = current->maj_flt;
break;
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index d65464e..8d7012b 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -899,6 +899,7 @@ static void apm_cpu_idle(void)
static int use_apm_idle; /* = 0 */
static unsigned int last_jiffies; /* = 0 */
static unsigned int last_stime; /* = 0 */
+ cputime_t stime;

int apm_idle_done = 0;
unsigned int jiffies_since_last_check = jiffies - last_jiffies;
@@ -906,23 +907,23 @@ static void apm_cpu_idle(void)

WARN_ONCE(1, "deprecated apm_cpu_idle will be deleted in 2012");
recalc:
+ task_cputime(current, NULL, &stime);
if (jiffies_since_last_check > IDLE_CALC_LIMIT) {
use_apm_idle = 0;
- last_jiffies = jiffies;
- last_stime = current->stime;
} else if (jiffies_since_last_check > idle_period) {
unsigned int idle_percentage;

- idle_percentage = current->stime - last_stime;
+ idle_percentage = stime - last_stime;
idle_percentage *= 100;
idle_percentage /= jiffies_since_last_check;
use_apm_idle = (idle_percentage > idle_threshold);
if (apm_info.forbid_idle)
use_apm_idle = 0;
- last_jiffies = jiffies;
- last_stime = current->stime;
}

+ last_jiffies = jiffies;
+ last_stime = stime;
+
bucket = IDLE_LEAKY_MAX;

while (!need_resched()) {
diff --git a/drivers/isdn/mISDN/stack.c b/drivers/isdn/mISDN/stack.c
index 5f21f62..deda591 100644
--- a/drivers/isdn/mISDN/stack.c
+++ b/drivers/isdn/mISDN/stack.c
@@ -18,6 +18,7 @@
#include <linux/slab.h>
#include <linux/mISDNif.h>
#include <linux/kthread.h>
+#include <linux/sched.h>
#include "core.h"

static u_int *debug;
@@ -202,6 +203,9 @@ static int
mISDNStackd(void *data)
{
struct mISDNstack *st = data;
+#ifdef MISDN_MSG_STATS
+ cputime_t utime, stime;
+#endif
int err = 0;

sigfillset(&current->blocked);
@@ -303,9 +307,10 @@ mISDNStackd(void *data)
"msg %d sleep %d stopped\n",
dev_name(&st->dev->dev), st->msg_cnt, st->sleep_cnt,
st->stopped_cnt);
+ task_cputime(st->thread, &utime, &stime);
printk(KERN_DEBUG
"mISDNStackd daemon for %s utime(%ld) stime(%ld)\n",
- dev_name(&st->dev->dev), st->thread->utime, st->thread->stime);
+ dev_name(&st->dev->dev), utime, stime);
printk(KERN_DEBUG
"mISDNStackd daemon for %s nvcsw(%ld) nivcsw(%ld)\n",
dev_name(&st->dev->dev), st->thread->nvcsw, st->thread->nivcsw);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 0c42cdb..49d0b43 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -33,6 +33,7 @@
#include <linux/elf.h>
#include <linux/utsname.h>
#include <linux/coredump.h>
+#include <linux/sched.h>
#include <asm/uaccess.h>
#include <asm/param.h>
#include <asm/page.h>
@@ -1320,8 +1321,11 @@ static void fill_prstatus(struct elf_prstatus *prstatus,
cputime_to_timeval(cputime.utime, &prstatus->pr_utime);
cputime_to_timeval(cputime.stime, &prstatus->pr_stime);
} else {
- cputime_to_timeval(p->utime, &prstatus->pr_utime);
- cputime_to_timeval(p->stime, &prstatus->pr_stime);
+ cputime_t utime, stime;
+
+ task_cputime(p, &utime, &stime);
+ 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);
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index dc84732..cb240dd 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1375,8 +1375,11 @@ static void fill_prstatus(struct elf_prstatus *prstatus,
cputime_to_timeval(cputime.utime, &prstatus->pr_utime);
cputime_to_timeval(cputime.stime, &prstatus->pr_stime);
} else {
- cputime_to_timeval(p->utime, &prstatus->pr_utime);
- cputime_to_timeval(p->stime, &prstatus->pr_stime);
+ cputime_t utime, stime;
+
+ task_cputime(p, &utime, &stime);
+ 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);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 206bb08..e682d58 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1792,6 +1792,24 @@ static inline void put_task_struct(struct task_struct *t)
__put_task_struct(t);
}

+static inline void task_cputime(struct task_struct *t,
+ cputime_t *utime, cputime_t *stime)
+{
+ if (utime)
+ *utime = t->utime;
+ if (stime)
+ *stime = t->stime;
+}
+
+static inline void task_cputime_scaled(struct task_struct *t,
+ cputime_t *utimescaled,
+ cputime_t *stimescaled)
+{
+ if (utimescaled)
+ *utimescaled = t->utimescaled;
+ if (stimescaled)
+ *stimescaled = t->stimescaled;
+}
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);

diff --git a/include/linux/tsacct_kern.h b/include/linux/tsacct_kern.h
index 44893e5..3251965 100644
--- a/include/linux/tsacct_kern.h
+++ b/include/linux/tsacct_kern.h
@@ -23,12 +23,15 @@ static inline void bacct_add_tsk(struct user_namespace *user_ns,
#ifdef CONFIG_TASK_XACCT
extern void xacct_add_tsk(struct taskstats *stats, struct task_struct *p);
extern void acct_update_integrals(struct task_struct *tsk);
+extern void acct_account_cputime(struct task_struct *tsk);
extern void acct_clear_integrals(struct task_struct *tsk);
#else
static inline void xacct_add_tsk(struct taskstats *stats, struct task_struct *p)
{}
static inline void acct_update_integrals(struct task_struct *tsk)
{}
+static inline void acct_account_cputime(struct task_struct *tsk)
+{}
static inline void acct_clear_integrals(struct task_struct *tsk)
{}
#endif /* CONFIG_TASK_XACCT */
diff --git a/kernel/acct.c b/kernel/acct.c
index 051e071..e8b1627 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -566,6 +566,7 @@ out:
void acct_collect(long exitcode, int group_dead)
{
struct pacct_struct *pacct = &current->signal->pacct;
+ cputime_t utime, stime;
unsigned long vsize = 0;

if (group_dead && current->mm) {
@@ -593,8 +594,9 @@ void acct_collect(long exitcode, int group_dead)
pacct->ac_flag |= ACORE;
if (current->flags & PF_SIGNALED)
pacct->ac_flag |= AXSIG;
- pacct->ac_utime += current->utime;
- pacct->ac_stime += current->stime;
+ task_cputime(current, &utime, &stime);
+ pacct->ac_utime += utime;
+ pacct->ac_stime += stime;
pacct->ac_minflt += current->min_flt;
pacct->ac_majflt += current->maj_flt;
spin_unlock_irq(&current->sighand->siglock);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 3046a50..e5d5e8e 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -224,11 +224,13 @@ void clear_tasks_mm_cpumask(int cpu)
static inline void check_for_tasks(int cpu)
{
struct task_struct *p;
+ cputime_t utime, stime;

write_lock_irq(&tasklist_lock);
for_each_process(p) {
+ task_cputime(p, &utime, &stime);
if (task_cpu(p) == cpu && p->state == TASK_RUNNING &&
- (p->utime || p->stime))
+ (utime || stime))
printk(KERN_WARNING "Task %s (pid = %d) is on cpu %d "
"(state = %ld, flags = %x)\n",
p->comm, task_pid_nr(p), cpu,
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index 418b3f7..d473988 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -106,6 +106,7 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
unsigned long long t2, t3;
unsigned long flags;
struct timespec ts;
+ cputime_t utime, stime, stimescaled, utimescaled;

/* Though tsk->delays accessed later, early exit avoids
* unnecessary returning of other data
@@ -114,12 +115,14 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
goto done;

tmp = (s64)d->cpu_run_real_total;
- cputime_to_timespec(tsk->utime + tsk->stime, &ts);
+ task_cputime(tsk, &utime, &stime);
+ cputime_to_timespec(utime + stime, &ts);
tmp += timespec_to_ns(&ts);
d->cpu_run_real_total = (tmp < (s64)d->cpu_run_real_total) ? 0 : tmp;

tmp = (s64)d->cpu_scaled_run_real_total;
- cputime_to_timespec(tsk->utimescaled + tsk->stimescaled, &ts);
+ task_cputime_scaled(tsk, &utimescaled, &stimescaled);
+ cputime_to_timespec(utimescaled + stimescaled, &ts);
tmp += timespec_to_ns(&ts);
d->cpu_scaled_run_real_total =
(tmp < (s64)d->cpu_scaled_run_real_total) ? 0 : tmp;
diff --git a/kernel/exit.c b/kernel/exit.c
index b4df219..5d1b0ff 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -85,6 +85,7 @@ 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;

sighand = rcu_dereference_check(tsk->sighand,
lockdep_tasklist_lock_is_held());
@@ -123,8 +124,9 @@ static void __exit_signal(struct task_struct *tsk)
* We won't ever get here for the group leader, since it
* will have been the last reference on the signal_struct.
*/
- sig->utime += tsk->utime;
- sig->stime += tsk->stime;
+ task_cputime(tsk, &utime, &stime);
+ sig->utime += utime;
+ sig->stime += stime;
sig->gtime += tsk->gtime;
sig->min_flt += tsk->min_flt;
sig->maj_flt += tsk->maj_flt;
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index a278cad..165d476 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -155,11 +155,19 @@ static void bump_cpu_timer(struct k_itimer *timer,

static inline cputime_t prof_ticks(struct task_struct *p)
{
- return p->utime + p->stime;
+ cputime_t utime, stime;
+
+ task_cputime(p, &utime, &stime);
+
+ return utime + stime;
}
static inline cputime_t virt_ticks(struct task_struct *p)
{
- return p->utime;
+ cputime_t utime;
+
+ task_cputime(p, &utime, NULL);
+
+ return utime;
}

static int
@@ -471,18 +479,23 @@ static void cleanup_timers(struct list_head *head,
*/
void posix_cpu_timers_exit(struct task_struct *tsk)
{
+ cputime_t utime, stime;
+
add_device_randomness((const void*) &tsk->se.sum_exec_runtime,
sizeof(unsigned long long));
+ task_cputime(tsk, &utime, &stime);
cleanup_timers(tsk->cpu_timers,
- tsk->utime, tsk->stime, tsk->se.sum_exec_runtime);
+ utime, stime, tsk->se.sum_exec_runtime);

}
void posix_cpu_timers_exit_group(struct task_struct *tsk)
{
struct signal_struct *const sig = tsk->signal;
+ cputime_t utime, stime;

+ task_cputime(tsk, &utime, &stime);
cleanup_timers(tsk->signal->cpu_timers,
- tsk->utime + sig->utime, tsk->stime + sig->stime,
+ utime + sig->utime, stime + sig->stime,
tsk->se.sum_exec_runtime + sig->sum_sched_runtime);
}

@@ -1226,11 +1239,14 @@ static inline int task_cputime_expired(const struct task_cputime *sample,
static inline int fastpath_timer_check(struct task_struct *tsk)
{
struct signal_struct *sig;
+ cputime_t utime, stime;
+
+ task_cputime(tsk, &utime, &stime);

if (!task_cputime_zero(&tsk->cputime_expires)) {
struct task_cputime task_sample = {
- .utime = tsk->utime,
- .stime = tsk->stime,
+ .utime = utime,
+ .stime = stime,
.sum_exec_runtime = tsk->se.sum_exec_runtime
};

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 0dfc280..0745410 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -164,7 +164,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime,
task_group_account_field(p, index, (__force u64) cputime);

/* Account for user time used */
- acct_update_integrals(p);
+ acct_account_cputime(p);
}

/*
@@ -214,7 +214,7 @@ void __account_system_time(struct task_struct *p, cputime_t cputime,
task_group_account_field(p, index, (__force u64) cputime);

/* Account for system time used */
- acct_update_integrals(p);
+ acct_account_cputime(p);
}

/*
@@ -296,6 +296,7 @@ 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;
struct task_struct *t;

times->utime = sig->utime;
@@ -309,8 +310,9 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)

t = tsk;
do {
- times->utime += t->utime;
- times->stime += t->stime;
+ task_cputime(tsk, &utime, &stime);
+ times->utime += utime;
+ times->stime += stime;
times->sum_exec_runtime += task_sched_runtime(t);
} while_each_thread(tsk, t);
out:
@@ -584,11 +586,10 @@ static void cputime_adjust(struct task_cputime *curr,
void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
{
struct task_cputime cputime = {
- .utime = p->utime,
- .stime = p->stime,
.sum_exec_runtime = p->se.sum_exec_runtime,
};

+ task_cputime(p, &cputime.utime, &cputime.stime);
cputime_adjust(&cputime, &p->prev_cputime, ut, st);
}

diff --git a/kernel/signal.c b/kernel/signal.c
index 372771e..776a45a 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1638,6 +1638,7 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
unsigned long flags;
struct sighand_struct *psig;
bool autoreap = false;
+ cputime_t utime, stime;

BUG_ON(sig == -1);

@@ -1675,8 +1676,9 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
task_uid(tsk));
rcu_read_unlock();

- info.si_utime = cputime_to_clock_t(tsk->utime + tsk->signal->utime);
- info.si_stime = cputime_to_clock_t(tsk->stime + tsk->signal->stime);
+ task_cputime(tsk, &utime, &stime);
+ info.si_utime = cputime_to_clock_t(utime + tsk->signal->utime);
+ info.si_stime = cputime_to_clock_t(stime + tsk->signal->stime);

info.si_status = tsk->exit_code & 0x7f;
if (tsk->exit_code & 0x80)
@@ -1740,6 +1742,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk,
unsigned long flags;
struct task_struct *parent;
struct sighand_struct *sighand;
+ cputime_t utime, stime;

if (for_ptracer) {
parent = tsk->parent;
@@ -1758,8 +1761,9 @@ static void do_notify_parent_cldstop(struct task_struct *tsk,
info.si_uid = from_kuid_munged(task_cred_xxx(parent, user_ns), task_uid(tsk));
rcu_read_unlock();

- info.si_utime = cputime_to_clock_t(tsk->utime);
- info.si_stime = cputime_to_clock_t(tsk->stime);
+ task_cputime(tsk, &utime, &stime);
+ info.si_utime = cputime_to_clock_t(utime);
+ info.si_stime = cputime_to_clock_t(stime);

info.si_code = why;
switch (why) {
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index 625df0b..a1dd9a1 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -32,6 +32,7 @@ void bacct_add_tsk(struct user_namespace *user_ns,
{
const struct cred *tcred;
struct timespec uptime, ts;
+ cputime_t utime, stime, utimescaled, stimescaled;
u64 ac_etime;

BUILD_BUG_ON(TS_COMM_LEN < TASK_COMM_LEN);
@@ -65,10 +66,15 @@ void bacct_add_tsk(struct user_namespace *user_ns,
stats->ac_ppid = pid_alive(tsk) ?
task_tgid_nr_ns(rcu_dereference(tsk->real_parent), pid_ns) : 0;
rcu_read_unlock();
- stats->ac_utime = cputime_to_usecs(tsk->utime);
- stats->ac_stime = cputime_to_usecs(tsk->stime);
- stats->ac_utimescaled = cputime_to_usecs(tsk->utimescaled);
- stats->ac_stimescaled = cputime_to_usecs(tsk->stimescaled);
+
+ task_cputime(tsk, &utime, &stime);
+ stats->ac_utime = cputime_to_usecs(utime);
+ stats->ac_stime = cputime_to_usecs(stime);
+
+ task_cputime_scaled(tsk, &utimescaled, &stimescaled);
+ stats->ac_utimescaled = cputime_to_usecs(utimescaled);
+ stats->ac_stimescaled = cputime_to_usecs(stimescaled);
+
stats->ac_minflt = tsk->min_flt;
stats->ac_majflt = tsk->maj_flt;

@@ -115,11 +121,8 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p)
#undef KB
#undef MB

-/**
- * acct_update_integrals - update mm integral fields in task_struct
- * @tsk: task_struct for accounting
- */
-void acct_update_integrals(struct task_struct *tsk)
+static void __acct_update_integrals(struct task_struct *tsk,
+ cputime_t utime, cputime_t stime)
{
if (likely(tsk->mm)) {
cputime_t time, dtime;
@@ -128,7 +131,7 @@ void acct_update_integrals(struct task_struct *tsk)
u64 delta;

local_irq_save(flags);
- time = tsk->stime + tsk->utime;
+ time = stime + utime;
dtime = time - tsk->acct_timexpd;
jiffies_to_timeval(cputime_to_jiffies(dtime), &value);
delta = value.tv_sec;
@@ -145,6 +148,27 @@ void acct_update_integrals(struct task_struct *tsk)
}

/**
+ * acct_update_integrals - update mm integral fields in task_struct
+ * @tsk: task_struct for accounting
+ */
+void acct_update_integrals(struct task_struct *tsk)
+{
+ cputime_t utime, stime;
+
+ task_cputime(tsk, &utime, &stime);
+ __acct_update_integrals(tsk, utime, stime);
+}
+
+/**
+ * acct_account_cputime - update mm integral after cputime update
+ * @tsk: task_struct for accounting
+ */
+void acct_account_cputime(struct task_struct *tsk)
+{
+ __acct_update_integrals(tsk, tsk->utime, tsk->stime);
+}
+
+/**
* acct_clear_integrals - clear the mm integral fields in task_struct
* @tsk: task_struct whose accounting fields are cleared
*/
--
1.7.5.4

--
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/