vtime: Always scale generic vtime accounting results
authorFrederic Weisbecker <fweisbec@gmail.com>
Sat, 13 Jul 2013 15:24:20 +0000 (17:24 +0200)
committerFrederic Weisbecker <fweisbec@gmail.com>
Wed, 14 Aug 2013 15:14:55 +0000 (17:14 +0200)
commitb854fafa4e06c50a92e00b39d75ee62083d986d6
tree46dbf41c4842d237d9c93ad24ef2ad1d7373f60e
parentb04934061330a4a449cfce703c97d887c3e11cd7
vtime: Always scale generic vtime accounting results

The cputime accounting in full dynticks can be a subtle
mixup of CPUs using tick based accounting and others using
generic vtime.

As long as the tick can have a share on producing these stats, we
want to scale the result against CFS precise accounting as the tick
can miss some task hiding between the periodic interrupt.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
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>
Cc: Kevin Hilman <khilman@linaro.org>
kernel/sched/cputime.c