sched/cputime: Introduce vtime accounting check for readers
authorFrederic Weisbecker <fweisbec@gmail.com>
Thu, 19 Nov 2015 15:47:33 +0000 (16:47 +0100)
committerIngo Molnar <mingo@kernel.org>
Fri, 4 Dec 2015 09:34:45 +0000 (10:34 +0100)
Readers need to know if vtime runs at all on some CPU somewhere, this
is a fast-path check to determine if we need to check further the need
to add up any tickless cputime delta.

This fast path check uses context tracking state because vtime is tied
to context tracking as of now. This check appears to be confusing though
so lets use a vtime function that deals with context tracking details
in vtime implementation instead.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Chris Metcalf <cmetcalf@ezchip.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Hiroshi Shimamoto <h-shimamoto@ct.jp.nec.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luiz Capitulino <lcapitulino@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul E . McKenney <paulmck@linux.vnet.ibm.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1447948054-28668-7-git-send-email-fweisbec@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
include/linux/vtime.h
kernel/sched/cputime.c

index ca23e8348f70f6a84cdf525307f1eca034c0fb21..fa2196990f84b2db9d77883b0bb7d7f329d0cc8e 100644 (file)
@@ -17,9 +17,20 @@ static inline bool vtime_accounting_cpu_enabled(void) { return true; }
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+/*
+ * Checks if vtime is enabled on some CPU. Cputime readers want to be careful
+ * in that case and compute the tickless cputime.
+ * For now vtime state is tied to context tracking. We might want to decouple
+ * those later if necessary.
+ */
+static inline bool vtime_accounting_enabled(void)
+{
+       return context_tracking_is_enabled();
+}
+
 static inline bool vtime_accounting_cpu_enabled(void)
 {
-       if (context_tracking_is_enabled()) {
+       if (vtime_accounting_enabled()) {
                if (context_tracking_cpu_is_enabled())
                        return true;
        }
index 572721756359da18f794dbcfa417754f1f57ad6d..9989c3f6172370916b7d062741f9b363fc1240dd 100644 (file)
@@ -788,7 +788,7 @@ cputime_t task_gtime(struct task_struct *t)
        unsigned int seq;
        cputime_t gtime;
 
-       if (!context_tracking_is_enabled())
+       if (!vtime_accounting_enabled())
                return t->gtime;
 
        do {
@@ -853,7 +853,7 @@ void task_cputime(struct task_struct *t, cputime_t *utime, cputime_t *stime)
 {
        cputime_t udelta, sdelta;
 
-       if (!context_tracking_is_enabled()) {
+       if (!vtime_accounting_enabled()) {
                if (utime)
                        *utime = t->utime;
                if (stime)
@@ -874,7 +874,7 @@ void task_cputime_scaled(struct task_struct *t,
 {
        cputime_t udelta, sdelta;
 
-       if (!context_tracking_is_enabled()) {
+       if (!vtime_accounting_enabled()) {
                if (utimescaled)
                        *utimescaled = t->utimescaled;
                if (stimescaled)
This page took 0.02946 seconds and 5 git commands to generate.