posix_cpu_timer: Optimize fastpath_timer_check()
authorJason Low <jason.low2@hp.com>
Wed, 14 Oct 2015 19:07:53 +0000 (12:07 -0700)
committerThomas Gleixner <tglx@linutronix.de>
Thu, 15 Oct 2015 09:23:41 +0000 (11:23 +0200)
In fastpath_timer_check(), the task_cputime() function is always
called to compute the utime and stime values. However, this is not
necessary if there are no per-thread timers to check for. This patch
modifies the code such that we compute the task_cputime values only
when there are per-thread timers set.

Signed-off-by: Jason Low <jason.low2@hp.com>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Frederic Weisbecker <fweisbec@gmail.com>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Reviewed-by: George Spelvin <linux@horizon.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: hideaki.kimura@hpe.com
Cc: terry.rudd@hpe.com
Cc: scott.norton@hpe.com
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1444849677-29330-2-git-send-email-jason.low2@hp.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
kernel/time/posix-cpu-timers.c

index 892e3da..aa4b6f4 100644 (file)
@@ -1117,17 +1117,12 @@ 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 = utime,
-                       .stime = stime,
-                       .sum_exec_runtime = tsk->se.sum_exec_runtime
-               };
+               struct task_cputime task_sample;
 
+               task_cputime(tsk, &task_sample.utime, &task_sample.stime);
+               task_sample.sum_exec_runtime = tsk->se.sum_exec_runtime;
                if (task_cputime_expired(&task_sample, &tsk->cputime_expires))
                        return 1;
        }