swait: Add idle variants which don't contribute to load average

There are cases where folks are using an interruptible swait when
using kthreads. This is rather confusing given you'd expect
interruptible waits to be -- interruptible, but kthreads are not
interruptible ! The reason for such practice though is to avoid
having these kthreads contribute to the system load average.

When systems are idle some kthreads may spend a lot of time blocking if
using swait_event_timeout(). This would contribute to the system load
average. On systems without preemption this would mean the load average
of an idle system is bumped to 2 instead of 0. On systems with PREEMPT=y
this would mean the load average of an idle system is bumped to 3
instead of 0.

This adds proper API using TASK_IDLE to make such goals explicit and
avoid confusion.

Suggested-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Tested-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

diff --git a/include/linux/swait.h b/include/linux/swait.h
index c1f9c62a8a507d1b4bfde42c0201cefabdef7675..4a4e180d0a3572fbb0719677db50d644a40c8f63 100644 (file)
--- a/include/linux/swait.h
+++ b/include/linux/swait.h
@@ -169,4 +169,59 @@ do {                                                                       \
        __ret;                                                          \
 })
 
+#define __swait_event_idle(wq, condition)                              \
+       (void)___swait_event(wq, condition, TASK_IDLE, 0, schedule())
+
+/**
+ * swait_event_idle - wait without system load contribution
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ *
+ * The process is put to sleep (TASK_IDLE) until the @condition evaluates to
+ * true. The @condition is checked each time the waitqueue @wq is woken up.
+ *
+ * This function is mostly used when a kthread or workqueue waits for some
+ * condition and doesn't want to contribute to system load. Signals are
+ * ignored.
+ */
+#define swait_event_idle(wq, condition)                                        \
+do {                                                                   \
+       if (condition)                                                  \
+               break;                                                  \
+       __swait_event_idle(wq, condition);                              \
+} while (0)
+
+#define __swait_event_idle_timeout(wq, condition, timeout)             \
+       ___swait_event(wq, ___wait_cond_timeout(condition),             \
+                      TASK_IDLE, timeout,                              \
+                      __ret = schedule_timeout(__ret))
+
+/**
+ * swait_event_idle_timeout - wait up to timeout without load contribution
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ * @timeout: timeout at which we'll give up in jiffies
+ *
+ * The process is put to sleep (TASK_IDLE) until the @condition evaluates to
+ * true. The @condition is checked each time the waitqueue @wq is woken up.
+ *
+ * This function is mostly used when a kthread or workqueue waits for some
+ * condition and doesn't want to contribute to system load. Signals are
+ * ignored.
+ *
+ * Returns:
+ * 0 if the @condition evaluated to %false after the @timeout elapsed,
+ * 1 if the @condition evaluated to %true after the @timeout elapsed,
+ * or the remaining jiffies (at least 1) if the @condition evaluated
+ * to %true before the @timeout elapsed.
+ */
+#define swait_event_idle_timeout(wq, condition, timeout)               \
+({                                                                     \
+       long __ret = timeout;                                           \
+       if (!___wait_cond_timeout(condition))                           \
+               __ret = __swait_event_idle_timeout(wq,                  \
+                                                  condition, timeout); \
+       __ret;                                                          \
+})
+
 #endif /* _LINUX_SWAIT_H */