From d01d4827858cdc2e1c437c87ab65ec0a00fd40f8 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Mon, 21 Sep 2009 11:06:27 +0200
Subject: sched: Always show Cpus_allowed field in /proc/<pid>/status

The Cpus_allowed fields in /proc/<pid>/status is currently only
shown in case of CONFIG_CPUSETS. However their contents are also
useful for the !CONFIG_CPUSETS case.

So change the current behaviour and always show these fields.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20090921090627.GD4649@osiris.boeblingen.de.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 fs/proc/array.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'fs/proc')

diff --git a/fs/proc/array.c b/fs/proc/array.c
index 725a650bbbb8..762aea9c9c71 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -321,6 +321,16 @@ static inline void task_context_switch_counts(struct seq_file *m,
 			p->nivcsw);
 }
 
+static void task_cpus_allowed(struct seq_file *m, struct task_struct *task)
+{
+	seq_printf(m, "Cpus_allowed:\t");
+	seq_cpumask(m, &task->cpus_allowed);
+	seq_printf(m, "\n");
+	seq_printf(m, "Cpus_allowed_list:\t");
+	seq_cpumask_list(m, &task->cpus_allowed);
+	seq_printf(m, "\n");
+}
+
 int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
 			struct pid *pid, struct task_struct *task)
 {
@@ -335,6 +345,7 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
 	}
 	task_sig(m, task);
 	task_cap(m, task);
+	task_cpus_allowed(m, task);
 	cpuset_task_status_allowed(m, task);
 #if defined(CONFIG_S390)
 	task_show_regs(m, task);
-- 
cgit v1.2.3-59-g8ed1b


From ce0e7b28fb75cb003cfc8d0238613aaf1c55e797 Mon Sep 17 00:00:00 2001
From: Ryota Ozaki <ozaki.ryota@gmail.com>
Date: Sat, 24 Oct 2009 01:20:10 +0900
Subject: sched, cpuacct: Fix niced guest time accounting

CPU time of a guest is always accounted in 'user' time
without concern for the nice value of its counterpart
process although the guest is scheduled under the nice
value.

This patch fixes the defect and accounts cpu time of
a niced guest in 'nice' time as same as a niced process.

And also the patch adds 'guest_nice' to cpuacct. The
value provides niced guest cpu time which is like 'nice'
to 'user'.

The original discussions can be found here:

  http://www.mail-archive.com/kvm@vger.kernel.org/msg23982.html
  http://www.mail-archive.com/kvm@vger.kernel.org/msg23860.html

Signed-off-by: Ryota Ozaki <ozaki.ryota@gmail.com>
Acked-by: Avi Kivity <avi@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1256314810-7897-1-git-send-email-ozaki.ryota@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 Documentation/filesystems/proc.txt |  3 ++-
 fs/proc/stat.c                     | 19 +++++++++++++------
 include/linux/kernel_stat.h        |  1 +
 kernel/sched.c                     |  9 +++++++--
 4 files changed, 23 insertions(+), 9 deletions(-)

(limited to 'fs/proc')

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 2c48f945546b..4af0018533f2 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -1072,7 +1072,8 @@ second).  The meanings of the columns are as follows, from left to right:
 - irq: servicing interrupts
 - softirq: servicing softirqs
 - steal: involuntary wait
-- guest: running a guest
+- guest: running a normal guest
+- guest_nice: running a niced guest
 
 The "intr" line gives counts of interrupts  serviced since boot time, for each
 of the  possible system interrupts.   The first  column  is the  total of  all
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 7cc726c6d70a..b9b7aad2003d 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -27,7 +27,7 @@ static int show_stat(struct seq_file *p, void *v)
 	int i, j;
 	unsigned long jif;
 	cputime64_t user, nice, system, idle, iowait, irq, softirq, steal;
-	cputime64_t guest;
+	cputime64_t guest, guest_nice;
 	u64 sum = 0;
 	u64 sum_softirq = 0;
 	unsigned int per_softirq_sums[NR_SOFTIRQS] = {0};
@@ -36,7 +36,7 @@ static int show_stat(struct seq_file *p, void *v)
 
 	user = nice = system = idle = iowait =
 		irq = softirq = steal = cputime64_zero;
-	guest = cputime64_zero;
+	guest = guest_nice = cputime64_zero;
 	getboottime(&boottime);
 	jif = boottime.tv_sec;
 
@@ -51,6 +51,8 @@ static int show_stat(struct seq_file *p, void *v)
 		softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq);
 		steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal);
 		guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest);
+		guest_nice = cputime64_add(guest_nice,
+			kstat_cpu(i).cpustat.guest_nice);
 		for_each_irq_nr(j) {
 			sum += kstat_irqs_cpu(j, i);
 		}
@@ -65,7 +67,8 @@ static int show_stat(struct seq_file *p, void *v)
 	}
 	sum += arch_irq_stat();
 
-	seq_printf(p, "cpu  %llu %llu %llu %llu %llu %llu %llu %llu %llu\n",
+	seq_printf(p, "cpu  %llu %llu %llu %llu %llu %llu %llu %llu %llu "
+		"%llu\n",
 		(unsigned long long)cputime64_to_clock_t(user),
 		(unsigned long long)cputime64_to_clock_t(nice),
 		(unsigned long long)cputime64_to_clock_t(system),
@@ -74,7 +77,8 @@ static int show_stat(struct seq_file *p, void *v)
 		(unsigned long long)cputime64_to_clock_t(irq),
 		(unsigned long long)cputime64_to_clock_t(softirq),
 		(unsigned long long)cputime64_to_clock_t(steal),
-		(unsigned long long)cputime64_to_clock_t(guest));
+		(unsigned long long)cputime64_to_clock_t(guest),
+		(unsigned long long)cputime64_to_clock_t(guest_nice));
 	for_each_online_cpu(i) {
 
 		/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
@@ -88,8 +92,10 @@ static int show_stat(struct seq_file *p, void *v)
 		softirq = kstat_cpu(i).cpustat.softirq;
 		steal = kstat_cpu(i).cpustat.steal;
 		guest = kstat_cpu(i).cpustat.guest;
+		guest_nice = kstat_cpu(i).cpustat.guest_nice;
 		seq_printf(p,
-			"cpu%d %llu %llu %llu %llu %llu %llu %llu %llu %llu\n",
+			"cpu%d %llu %llu %llu %llu %llu %llu %llu %llu %llu "
+			"%llu\n",
 			i,
 			(unsigned long long)cputime64_to_clock_t(user),
 			(unsigned long long)cputime64_to_clock_t(nice),
@@ -99,7 +105,8 @@ static int show_stat(struct seq_file *p, void *v)
 			(unsigned long long)cputime64_to_clock_t(irq),
 			(unsigned long long)cputime64_to_clock_t(softirq),
 			(unsigned long long)cputime64_to_clock_t(steal),
-			(unsigned long long)cputime64_to_clock_t(guest));
+			(unsigned long long)cputime64_to_clock_t(guest),
+			(unsigned long long)cputime64_to_clock_t(guest_nice));
 	}
 	seq_printf(p, "intr %llu", (unsigned long long)sum);
 
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 348fa8874b52..c059044bc6dc 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -25,6 +25,7 @@ struct cpu_usage_stat {
 	cputime64_t iowait;
 	cputime64_t steal;
 	cputime64_t guest;
+	cputime64_t guest_nice;
 };
 
 struct kernel_stat {
diff --git a/kernel/sched.c b/kernel/sched.c
index e5205811c19e..67be4d0dddaa 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -5017,8 +5017,13 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime,
 	p->gtime = cputime_add(p->gtime, cputime);
 
 	/* Add guest time to cpustat. */
-	cpustat->user = cputime64_add(cpustat->user, tmp);
-	cpustat->guest = cputime64_add(cpustat->guest, tmp);
+	if (TASK_NICE(p) > 0) {
+		cpustat->nice = cputime64_add(cpustat->nice, tmp);
+		cpustat->guest_nice = cputime64_add(cpustat->guest_nice, tmp);
+	} else {
+		cpustat->user = cputime64_add(cpustat->user, tmp);
+		cpustat->guest = cputime64_add(cpustat->guest, tmp);
+	}
 }
 
 /*
-- 
cgit v1.2.3-59-g8ed1b


From d180c5bccec02612256fd8076ff3c1fac3429553 Mon Sep 17 00:00:00 2001
From: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Date: Thu, 26 Nov 2009 14:48:30 +0900
Subject: sched: Introduce task_times() to replace task_{u,s}time() pair

Functions task_{u,s}time() are called in pair in almost all
cases.  However task_stime() is implemented to call task_utime()
from its inside, so such paired calls run task_utime() twice.

It means we do heavy divisions (div_u64 + do_div) twice to get
utime and stime which can be obtained at same time by one set
of divisions.

This patch introduces a function task_times(*tsk, *utime,
*stime) to retrieve utime and stime at once in better, optimized
way.

Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
Cc: Spencer Candland <spencer@bluehost.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Americo Wang <xiyou.wangcong@gmail.com>
LKML-Reference: <4B0E16AE.906@jp.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 fs/proc/array.c       |  3 +--
 include/linux/sched.h |  1 +
 kernel/exit.c         |  7 +++++--
 kernel/sched.c        | 55 ++++++++++++++++++++++++++++++++-------------------
 kernel/sys.c          |  3 +--
 5 files changed, 43 insertions(+), 26 deletions(-)

(limited to 'fs/proc')

diff --git a/fs/proc/array.c b/fs/proc/array.c
index e209f64ab27b..330deda70d08 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -535,8 +535,7 @@ 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;
-		utime = task_utime(task);
-		stime = task_stime(task);
+		task_times(task, &utime, &stime);
 		gtime = task_gtime(task);
 	}
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 78ba664474f3..fe6ae1516640 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1723,6 +1723,7 @@ static inline void put_task_struct(struct task_struct *t)
 extern cputime_t task_utime(struct task_struct *p);
 extern cputime_t task_stime(struct task_struct *p);
 extern cputime_t task_gtime(struct task_struct *p);
+extern void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
 
 /*
  * Per process flags
diff --git a/kernel/exit.c b/kernel/exit.c
index f7864ac2ecc1..29068ab2670a 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -91,6 +91,8 @@ static void __exit_signal(struct task_struct *tsk)
 	if (atomic_dec_and_test(&sig->count))
 		posix_cpu_timers_exit_group(tsk);
 	else {
+		cputime_t utime, stime;
+
 		/*
 		 * If there is any task waiting for the group exit
 		 * then notify it:
@@ -110,8 +112,9 @@ 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 = cputime_add(sig->utime, task_utime(tsk));
-		sig->stime = cputime_add(sig->stime, task_stime(tsk));
+		task_times(tsk, &utime, &stime);
+		sig->utime = cputime_add(sig->utime, utime);
+		sig->stime = cputime_add(sig->stime, stime);
 		sig->gtime = cputime_add(sig->gtime, task_gtime(tsk));
 		sig->min_flt += tsk->min_flt;
 		sig->maj_flt += tsk->maj_flt;
diff --git a/kernel/sched.c b/kernel/sched.c
index 315ba4059f93..475a6f2b7158 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -5191,6 +5191,14 @@ cputime_t task_stime(struct task_struct *p)
 {
 	return p->stime;
 }
+
+void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+{
+	if (ut)
+		*ut = task_utime(p);
+	if (st)
+		*st = task_stime(p);
+}
 #else
 
 #ifndef nsecs_to_cputime
@@ -5198,41 +5206,48 @@ cputime_t task_stime(struct task_struct *p)
 	msecs_to_cputime(div_u64((__nsecs), NSEC_PER_MSEC))
 #endif
 
-cputime_t task_utime(struct task_struct *p)
+void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 {
-	cputime_t utime = p->utime, total = utime + p->stime;
-	u64 temp;
+	cputime_t rtime, utime = p->utime, total = utime + p->stime;
 
 	/*
 	 * Use CFS's precise accounting:
 	 */
-	temp = (u64)nsecs_to_cputime(p->se.sum_exec_runtime);
+	rtime = nsecs_to_cputime(p->se.sum_exec_runtime);
 
 	if (total) {
-		temp *= utime;
+		u64 temp;
+
+		temp = (u64)(rtime * utime);
 		do_div(temp, total);
-	}
-	utime = (cputime_t)temp;
+		utime = (cputime_t)temp;
+	} else
+		utime = rtime;
 
+	/*
+	 * Compare with previous values, to keep monotonicity:
+	 */
 	p->prev_utime = max(p->prev_utime, utime);
-	return p->prev_utime;
+	p->prev_stime = max(p->prev_stime, rtime - p->prev_utime);
+
+	if (ut)
+		*ut = p->prev_utime;
+	if (st)
+		*st = p->prev_stime;
+}
+
+cputime_t task_utime(struct task_struct *p)
+{
+	cputime_t utime;
+	task_times(p, &utime, NULL);
+	return utime;
 }
 
 cputime_t task_stime(struct task_struct *p)
 {
 	cputime_t stime;
-
-	/*
-	 * Use CFS's precise accounting. (we subtract utime from
-	 * the total, to make sure the total observed by userspace
-	 * grows monotonically - apps rely on that):
-	 */
-	stime = nsecs_to_cputime(p->se.sum_exec_runtime) - task_utime(p);
-
-	if (stime >= 0)
-		p->prev_stime = max(p->prev_stime, stime);
-
-	return p->prev_stime;
+	task_times(p, NULL, &stime);
+	return stime;
 }
 #endif
 
diff --git a/kernel/sys.c b/kernel/sys.c
index ce17760d9c51..bbdfce0d4347 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1346,8 +1346,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 	utime = stime = cputime_zero;
 
 	if (who == RUSAGE_THREAD) {
-		utime = task_utime(current);
-		stime = task_stime(current);
+		task_times(current, &utime, &stime);
 		accumulate_thread_rusage(p, r);
 		maxrss = p->signal->maxrss;
 		goto out;
-- 
cgit v1.2.3-59-g8ed1b


From d5b7c78e975302a1bab28263266c39ecb71acad4 Mon Sep 17 00:00:00 2001
From: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Date: Thu, 26 Nov 2009 14:49:05 +0900
Subject: sched: Remove task_{u,s,g}time()

Now all task_{u,s}time() pairs are replaced by task_times().
And task_gtime() is too simple to be an inline function.

Cleanup them all.

Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
Cc: Spencer Candland <spencer@bluehost.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Americo Wang <xiyou.wangcong@gmail.com>
LKML-Reference: <4B0E16D1.70902@jp.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 fs/proc/array.c       |  4 ++--
 include/linux/sched.h |  3 ---
 kernel/exit.c         |  2 +-
 kernel/sched.c        | 33 ++-------------------------------
 4 files changed, 5 insertions(+), 37 deletions(-)

(limited to 'fs/proc')

diff --git a/fs/proc/array.c b/fs/proc/array.c
index 330deda70d08..ca61a88aed66 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -511,7 +511,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 			do {
 				min_flt += t->min_flt;
 				maj_flt += t->maj_flt;
-				gtime = cputime_add(gtime, task_gtime(t));
+				gtime = cputime_add(gtime, t->gtime);
 				t = next_thread(t);
 			} while (t != task);
 
@@ -536,7 +536,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 		min_flt = task->min_flt;
 		maj_flt = task->maj_flt;
 		task_times(task, &utime, &stime);
-		gtime = task_gtime(task);
+		gtime = task->gtime;
 	}
 
 	/* scale priority and nice values from timeslices to -20..20 */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index fe6ae1516640..0395b0f4df3a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1720,9 +1720,6 @@ static inline void put_task_struct(struct task_struct *t)
 		__put_task_struct(t);
 }
 
-extern cputime_t task_utime(struct task_struct *p);
-extern cputime_t task_stime(struct task_struct *p);
-extern cputime_t task_gtime(struct task_struct *p);
 extern void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
 
 /*
diff --git a/kernel/exit.c b/kernel/exit.c
index 29068ab2670a..2eaf68b634e3 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -115,7 +115,7 @@ static void __exit_signal(struct task_struct *tsk)
 		task_times(tsk, &utime, &stime);
 		sig->utime = cputime_add(sig->utime, utime);
 		sig->stime = cputime_add(sig->stime, stime);
-		sig->gtime = cputime_add(sig->gtime, task_gtime(tsk));
+		sig->gtime = cputime_add(sig->gtime, tsk->gtime);
 		sig->min_flt += tsk->min_flt;
 		sig->maj_flt += tsk->maj_flt;
 		sig->nvcsw += tsk->nvcsw;
diff --git a/kernel/sched.c b/kernel/sched.c
index 475a6f2b7158..82251c21f785 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -5182,22 +5182,12 @@ void account_idle_ticks(unsigned long ticks)
  * Use precise platform statistics if available:
  */
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
-cputime_t task_utime(struct task_struct *p)
-{
-	return p->utime;
-}
-
-cputime_t task_stime(struct task_struct *p)
-{
-	return p->stime;
-}
-
 void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 {
 	if (ut)
-		*ut = task_utime(p);
+		*ut = p->utime;
 	if (st)
-		*st = task_stime(p);
+		*st = p->stime;
 }
 #else
 
@@ -5235,27 +5225,8 @@ void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 	if (st)
 		*st = p->prev_stime;
 }
-
-cputime_t task_utime(struct task_struct *p)
-{
-	cputime_t utime;
-	task_times(p, &utime, NULL);
-	return utime;
-}
-
-cputime_t task_stime(struct task_struct *p)
-{
-	cputime_t stime;
-	task_times(p, NULL, &stime);
-	return stime;
-}
 #endif
 
-inline cputime_t task_gtime(struct task_struct *p)
-{
-	return p->gtime;
-}
-
 /*
  * This function gets called by the timer code, with HZ frequency.
  * We call it with interrupts disabled.
-- 
cgit v1.2.3-59-g8ed1b


From 0cf55e1ec08bb5a22e068309e2d8ba1180ab4239 Mon Sep 17 00:00:00 2001
From: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Date: Wed, 2 Dec 2009 17:28:07 +0900
Subject: sched, cputime: Introduce thread_group_times()

This is a real fix for problem of utime/stime values decreasing
described in the thread:

   http://lkml.org/lkml/2009/11/3/522

Now cputime is accounted in the following way:

 - {u,s}time in task_struct are increased every time when the thread
   is interrupted by a tick (timer interrupt).

 - When a thread exits, its {u,s}time are added to signal->{u,s}time,
   after adjusted by task_times().

 - When all threads in a thread_group exits, accumulated {u,s}time
   (and also c{u,s}time) in signal struct are added to c{u,s}time
   in signal struct of the group's parent.

So {u,s}time in task struct are "raw" tick count, while
{u,s}time and c{u,s}time in signal struct are "adjusted" values.

And accounted values are used by:

 - task_times(), to get cputime of a thread:
   This function returns adjusted values that originates from raw
   {u,s}time and scaled by sum_exec_runtime that accounted by CFS.

 - thread_group_cputime(), to get cputime of a thread group:
   This function returns sum of all {u,s}time of living threads in
   the group, plus {u,s}time in the signal struct that is sum of
   adjusted cputimes of all exited threads belonged to the group.

The problem is the return value of thread_group_cputime(),
because it is mixed sum of "raw" value and "adjusted" value:

  group's {u,s}time = foreach(thread){{u,s}time} + exited({u,s}time)

This misbehavior can break {u,s}time monotonicity.
Assume that if there is a thread that have raw values greater
than adjusted values (e.g. interrupted by 1000Hz ticks 50 times
but only runs 45ms) and if it exits, cputime will decrease (e.g.
-5ms).

To fix this, we could do:

  group's {u,s}time = foreach(t){task_times(t)} + exited({u,s}time)

But task_times() contains hard divisions, so applying it for
every thread should be avoided.

This patch fixes the above problem in the following way:

 - Modify thread's exit (= __exit_signal()) not to use task_times().
   It means {u,s}time in signal struct accumulates raw values instead
   of adjusted values.  As the result it makes thread_group_cputime()
   to return pure sum of "raw" values.

 - Introduce a new function thread_group_times(*task, *utime, *stime)
   that converts "raw" values of thread_group_cputime() to "adjusted"
   values, in same calculation procedure as task_times().

 - Modify group's exit (= wait_task_zombie()) to use this introduced
   thread_group_times().  It make c{u,s}time in signal struct to
   have adjusted values like before this patch.

 - Replace some thread_group_cputime() by thread_group_times().
   This replacements are only applied where conveys the "adjusted"
   cputime to users, and where already uses task_times() near by it.
   (i.e. sys_times(), getrusage(), and /proc/<PID>/stat.)

This patch have a positive side effect:

 - Before this patch, if a group contains many short-life threads
   (e.g. runs 0.9ms and not interrupted by ticks), the group's
   cputime could be invisible since thread's cputime was accumulated
   after adjusted: imagine adjustment function as adj(ticks, runtime),
     {adj(0, 0.9) + adj(0, 0.9) + ....} = {0 + 0 + ....} = 0.
   After this patch it will not happen because the adjustment is
   applied after accumulated.

v2:
 - remove if()s, put new variables into signal_struct.

Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Spencer Candland <spencer@bluehost.com>
Cc: Americo Wang <xiyou.wangcong@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
LKML-Reference: <4B162517.8040909@jp.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 fs/proc/array.c       |  5 +----
 include/linux/sched.h |  4 ++++
 kernel/exit.c         | 23 ++++++++++++-----------
 kernel/fork.c         |  3 +++
 kernel/sched.c        | 41 +++++++++++++++++++++++++++++++++++++++++
 kernel/sys.c          | 18 ++++++++----------
 6 files changed, 69 insertions(+), 25 deletions(-)

(limited to 'fs/proc')

diff --git a/fs/proc/array.c b/fs/proc/array.c
index ca61a88aed66..2571da43c736 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -506,7 +506,6 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 
 		/* add up live thread stats at the group level */
 		if (whole) {
-			struct task_cputime cputime;
 			struct task_struct *t = task;
 			do {
 				min_flt += t->min_flt;
@@ -517,9 +516,7 @@ 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(task, &cputime);
-			utime = cputime.utime;
-			stime = cputime.stime;
+			thread_group_times(task, &utime, &stime);
 			gtime = cputime_add(gtime, sig->gtime);
 		}
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index dff85e58264e..34238bd10ebf 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -624,6 +624,9 @@ struct signal_struct {
 	cputime_t utime, stime, cutime, cstime;
 	cputime_t gtime;
 	cputime_t cgtime;
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+	cputime_t prev_utime, prev_stime;
+#endif
 	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
 	unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
 	unsigned long inblock, oublock, cinblock, coublock;
@@ -1723,6 +1726,7 @@ static inline void put_task_struct(struct task_struct *t)
 }
 
 extern void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
+extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
 
 /*
  * Per process flags
diff --git a/kernel/exit.c b/kernel/exit.c
index 2eaf68b634e3..b221ad65fd20 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -91,8 +91,6 @@ static void __exit_signal(struct task_struct *tsk)
 	if (atomic_dec_and_test(&sig->count))
 		posix_cpu_timers_exit_group(tsk);
 	else {
-		cputime_t utime, stime;
-
 		/*
 		 * If there is any task waiting for the group exit
 		 * then notify it:
@@ -112,9 +110,8 @@ 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.
 		 */
-		task_times(tsk, &utime, &stime);
-		sig->utime = cputime_add(sig->utime, utime);
-		sig->stime = cputime_add(sig->stime, stime);
+		sig->utime = cputime_add(sig->utime, tsk->utime);
+		sig->stime = cputime_add(sig->stime, tsk->stime);
 		sig->gtime = cputime_add(sig->gtime, tsk->gtime);
 		sig->min_flt += tsk->min_flt;
 		sig->maj_flt += tsk->maj_flt;
@@ -1208,6 +1205,7 @@ 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;
 
 		/*
 		 * The resource counters for the group leader are in its
@@ -1223,20 +1221,23 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		 * need to protect the access to parent->signal fields,
 		 * as other threads in the parent group can be right
 		 * here reaping other children at the same time.
+		 *
+		 * We use thread_group_times() to get times for the thread
+		 * group, which consolidates times for all threads in the
+		 * group including the group leader.
 		 */
+		thread_group_times(p, &tgutime, &tgstime);
 		spin_lock_irq(&p->real_parent->sighand->siglock);
 		psig = p->real_parent->signal;
 		sig = p->signal;
 		psig->cutime =
 			cputime_add(psig->cutime,
-			cputime_add(p->utime,
-			cputime_add(sig->utime,
-				    sig->cutime)));
+			cputime_add(tgutime,
+				    sig->cutime));
 		psig->cstime =
 			cputime_add(psig->cstime,
-			cputime_add(p->stime,
-			cputime_add(sig->stime,
-				    sig->cstime)));
+			cputime_add(tgstime,
+				    sig->cstime));
 		psig->cgtime =
 			cputime_add(psig->cgtime,
 			cputime_add(p->gtime,
diff --git a/kernel/fork.c b/kernel/fork.c
index ad7cb6d1193c..3d6f121bbe8a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -884,6 +884,9 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero;
 	sig->gtime = cputime_zero;
 	sig->cgtime = cputime_zero;
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+	sig->prev_utime = sig->prev_stime = cputime_zero;
+#endif
 	sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
 	sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
 	sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0;
diff --git a/kernel/sched.c b/kernel/sched.c
index 17e2c1db2bde..e6ba726941ae 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -5187,6 +5187,16 @@ void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 	*ut = p->utime;
 	*st = p->stime;
 }
+
+void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+{
+	struct task_cputime cputime;
+
+	thread_group_cputime(p, &cputime);
+
+	*ut = cputime.utime;
+	*st = cputime.stime;
+}
 #else
 
 #ifndef nsecs_to_cputime
@@ -5220,6 +5230,37 @@ void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 	*ut = p->prev_utime;
 	*st = p->prev_stime;
 }
+
+/*
+ * Must be called with siglock held.
+ */
+void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+{
+	struct signal_struct *sig = p->signal;
+	struct task_cputime cputime;
+	cputime_t rtime, utime, total;
+
+	thread_group_cputime(p, &cputime);
+
+	total = cputime_add(cputime.utime, cputime.stime);
+	rtime = nsecs_to_cputime(cputime.sum_exec_runtime);
+
+	if (total) {
+		u64 temp;
+
+		temp = (u64)(rtime * cputime.utime);
+		do_div(temp, total);
+		utime = (cputime_t)temp;
+	} else
+		utime = rtime;
+
+	sig->prev_utime = max(sig->prev_utime, utime);
+	sig->prev_stime = max(sig->prev_stime,
+			      cputime_sub(rtime, sig->prev_utime));
+
+	*ut = sig->prev_utime;
+	*st = sig->prev_stime;
+}
 #endif
 
 /*
diff --git a/kernel/sys.c b/kernel/sys.c
index bbdfce0d4347..9968c5fb55b9 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -911,16 +911,15 @@ change_okay:
 
 void do_sys_times(struct tms *tms)
 {
-	struct task_cputime cputime;
-	cputime_t cutime, cstime;
+	cputime_t tgutime, tgstime, cutime, cstime;
 
-	thread_group_cputime(current, &cputime);
 	spin_lock_irq(&current->sighand->siglock);
+	thread_group_times(current, &tgutime, &tgstime);
 	cutime = current->signal->cutime;
 	cstime = current->signal->cstime;
 	spin_unlock_irq(&current->sighand->siglock);
-	tms->tms_utime = cputime_to_clock_t(cputime.utime);
-	tms->tms_stime = cputime_to_clock_t(cputime.stime);
+	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);
 }
@@ -1338,8 +1337,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 {
 	struct task_struct *t;
 	unsigned long flags;
-	cputime_t utime, stime;
-	struct task_cputime cputime;
+	cputime_t tgutime, tgstime, utime, stime;
 	unsigned long maxrss = 0;
 
 	memset((char *) r, 0, sizeof *r);
@@ -1372,9 +1370,9 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 				break;
 
 		case RUSAGE_SELF:
-			thread_group_cputime(p, &cputime);
-			utime = cputime_add(utime, cputime.utime);
-			stime = cputime_add(stime, cputime.stime);
+			thread_group_times(p, &tgutime, &tgstime);
+			utime = cputime_add(utime, tgutime);
+			stime = cputime_add(stime, tgstime);
 			r->ru_nvcsw += p->signal->nvcsw;
 			r->ru_nivcsw += p->signal->nivcsw;
 			r->ru_minflt += p->signal->min_flt;
-- 
cgit v1.2.3-59-g8ed1b