Commit 49048622 authored by Balbir Singh's avatar Balbir Singh Committed by Ingo Molnar
Browse files

sched: fix process time monotonicity 



Spencer reported a problem where utime and stime were going negative despite
the fixes in commit b27f03d4. The suspected
reason for the problem is that signal_struct maintains it's own utime and
stime (of exited tasks), these are not updated using the new task_utime()
routine, hence sig->utime can go backwards and cause the same problem
to occur (sig->utime, adds tsk->utime and not task_utime()). This patch
fixes the problem

TODO: using max(task->prev_utime, derived utime) works for now, but a more
generic solution is to implement cputime_max() and use the cputime_gt()
function for comparison.

Reported-by: default avatar <spencer@bluehost.com>
Signed-off-by: default avatarBalbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
parent 56c7426b

fs/proc/array.c

+0 −59
Original line number Diff line number Diff line
@@ -337,65 +337,6 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, 
	return 0;

}



/*

 * Use precise platform statistics if available:

 */

#ifdef CONFIG_VIRT_CPU_ACCOUNTING

static cputime_t task_utime(struct task_struct *p)

{

	return p->utime;

}



static cputime_t task_stime(struct task_struct *p)

{

	return p->stime;

}

#else

static cputime_t task_utime(struct task_struct *p)

{

	clock_t utime = cputime_to_clock_t(p->utime),

		total = utime + cputime_to_clock_t(p->stime);

	u64 temp;



	/*

	 * Use CFS's precise accounting:

	 */

	temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime);



	if (total) {

		temp *= utime;

		do_div(temp, total);

	}

	utime = (clock_t)temp;



	p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime));

	return p->prev_utime;

}



static cputime_t task_stime(struct task_struct *p)

{

	clock_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 = nsec_to_clock_t(p->se.sum_exec_runtime) -

			cputime_to_clock_t(task_utime(p));



	if (stime >= 0)

		p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime));



	return p->prev_stime;

}

#endif



static cputime_t task_gtime(struct task_struct *p)

{

	return p->gtime;

}



static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,

			struct pid *pid, struct task_struct *task, int whole)

{

include/linux/sched.h

+4 −0
Original line number Diff line number Diff line
@@ -1475,6 +1475,10 @@ 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);



/*

 * Per process flags

 */

kernel/exit.c

+3 −3
Original line number Diff line number Diff line
@@ -112,9 +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, tsk->utime);

		sig->stime = cputime_add(sig->stime, tsk->stime);

		sig->gtime = cputime_add(sig->gtime, tsk->gtime);

		sig->utime = cputime_add(sig->utime, task_utime(tsk));

		sig->stime = cputime_add(sig->stime, task_stime(tsk));

		sig->gtime = cputime_add(sig->gtime, task_gtime(tsk));

		sig->min_flt += tsk->min_flt;

		sig->maj_flt += tsk->maj_flt;

		sig->nvcsw += tsk->nvcsw;

kernel/sched.c

+59 −0
Original line number Diff line number Diff line
@@ -4178,6 +4178,65 @@ void account_steal_time(struct task_struct *p, cputime_t steal) 
		cpustat->steal = cputime64_add(cpustat->steal, tmp);

}



/*

 * 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;

}

#else

cputime_t task_utime(struct task_struct *p)

{

	clock_t utime = cputime_to_clock_t(p->utime),

		total = utime + cputime_to_clock_t(p->stime);

	u64 temp;



	/*

	 * Use CFS's precise accounting:

	 */

	temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime);



	if (total) {

		temp *= utime;

		do_div(temp, total);

	}

	utime = (clock_t)temp;



	p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime));

	return p->prev_utime;

}



cputime_t task_stime(struct task_struct *p)

{

	clock_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 = nsec_to_clock_t(p->se.sum_exec_runtime) -

			cputime_to_clock_t(task_utime(p));



	if (stime >= 0)

		p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime));



	return p->prev_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.

CRA Git | Maintained and supported by SUSTech CRA and CCSE