vtime: Use consistent clocks among nohz accounting

While computing the cputime delta of dynticks CPUs,
we are mixing up clocks of differents natures:

* local_clock() which takes care of unstable clock
sources and fix these if needed.

* sched_clock() which is the weaker version of
local_clock(). It doesn't compute any fixup in case
of unstable source.

If the clock source is stable, those two clocks are the
same and we can safely compute the difference against
two random points.

Otherwise it results in random deltas as sched_clock()
can randomly drift away, back or forward, from local_clock().

As a consequence, some strange behaviour with unstable tsc
has been observed such as non progressing constant zero cputime.
(The 'top' command showing no load).

Fix this by only using local_clock(), or its irq safe/remote
equivalent, in vtime code.

Reported-by: Mike Galbraith <efault@gmx.de>
Suggested-by: Mike Galbraith <efault@gmx.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Li Zhong <zhong@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index 71a5782d8c592fc027cd1e0ce7c4c5a99787c11f..b1dd2db80076d87d77236b76e9314557a185ae5c 100644 (file)
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -34,7 +34,7 @@ static inline void vtime_user_exit(struct task_struct *tsk)
 }
 extern void vtime_guest_enter(struct task_struct *tsk);
 extern void vtime_guest_exit(struct task_struct *tsk);
-extern void vtime_init_idle(struct task_struct *tsk);
+extern void vtime_init_idle(struct task_struct *tsk, int cpu);
 #else
 static inline void vtime_account_irq_exit(struct task_struct *tsk)
 {
@@ -45,7 +45,7 @@ static inline void vtime_user_enter(struct task_struct *tsk) { }
 static inline void vtime_user_exit(struct task_struct *tsk) { }
 static inline void vtime_guest_enter(struct task_struct *tsk) { }
 static inline void vtime_guest_exit(struct task_struct *tsk) { }
-static inline void vtime_init_idle(struct task_struct *tsk) { }
+static inline void vtime_init_idle(struct task_struct *tsk, int cpu) { }
 #endif
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 58453b8272fdbab9422bf6c040683397c269ba82..e1a27f91872377c2526d28aead495e8241b1e92d 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4745,7 +4745,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
         */
        idle->sched_class = &idle_sched_class;
        ftrace_graph_init_idle_task(idle, cpu);
-       vtime_init_idle(idle);
+       vtime_init_idle(idle, cpu);
 #if defined(CONFIG_SMP)
        sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
 #endif

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index cc2dc3eea8a3a55d7c86cc9896bfe9d235c18cab..b5ccba22603b51a92c2aa1f0ef647a878dd4e2c3 100644 (file)
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -747,17 +747,17 @@ void arch_vtime_task_switch(struct task_struct *prev)
 
        write_seqlock(&current->vtime_seqlock);
        current->vtime_snap_whence = VTIME_SYS;
-       current->vtime_snap = sched_clock();
+       current->vtime_snap = sched_clock_cpu(smp_processor_id());
        write_sequnlock(&current->vtime_seqlock);
 }
 
-void vtime_init_idle(struct task_struct *t)
+void vtime_init_idle(struct task_struct *t, int cpu)
 {
        unsigned long flags;
 
        write_seqlock_irqsave(&t->vtime_seqlock, flags);
        t->vtime_snap_whence = VTIME_SYS;
-       t->vtime_snap = sched_clock();
+       t->vtime_snap = sched_clock_cpu(cpu);
        write_sequnlock_irqrestore(&t->vtime_seqlock, flags);
 }