hrtimer: make the nanosleep() syscall use the per process slack

[linux-2.6-omap-h63xx.git] / kernel / hrtimer.c

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index ae307feec74c2435c62f0ab6214aeecd33e6eca6..9a4c901855668fd0daecdd398456a01f348d32ca 100644 (file)
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -945,9 +945,10 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
 }
 
 /**
- * hrtimer_start - (re)start an relative timer on the current CPU
+ * hrtimer_start_range_ns - (re)start an relative timer on the current CPU
  * @timer:     the timer to be added
  * @tim:       expiry time
+ * @delta_ns:  "slack" range for the timer
  * @mode:      expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL)
  *
  * Returns:
@@ -955,7 +956,8 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
  *  1 when the timer was active
  */
 int
-hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
+hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, unsigned long delta_ns,
+                       const enum hrtimer_mode mode)
 {
        struct hrtimer_clock_base *base, *new_base;
        unsigned long flags;
@@ -983,7 +985,7 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
 #endif
        }
 
-       hrtimer_set_expires(timer, tim);
+       hrtimer_set_expires_range_ns(timer, tim, delta_ns);
 
        timer_stats_hrtimer_set_start_info(timer);
 
@@ -1016,8 +1018,26 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
 
        return ret;
 }
+EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
+
+/**
+ * hrtimer_start - (re)start an relative timer on the current CPU
+ * @timer:     the timer to be added
+ * @tim:       expiry time
+ * @mode:      expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL)
+ *
+ * Returns:
+ *  0 on success
+ *  1 when the timer was active
+ */
+int
+hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
+{
+       return hrtimer_start_range_ns(timer, tim, 0, mode);
+}
 EXPORT_SYMBOL_GPL(hrtimer_start);
 
+
 /**
  * hrtimer_try_to_cancel - try to deactivate a timer
  * @timer:     hrtimer to stop
@@ -1309,7 +1329,20 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 
                        timer = rb_entry(node, struct hrtimer, node);
 
-                       if (basenow.tv64 < hrtimer_get_expires_tv64(timer)) {
+                       /*
+                        * The immediate goal for using the softexpires is
+                        * minimizing wakeups, not running timers at the
+                        * earliest interrupt after their soft expiration.
+                        * This allows us to avoid using a Priority Search
+                        * Tree, which can answer a stabbing querry for
+                        * overlapping intervals and instead use the simple
+                        * BST we already have.
+                        * We don't add extra wakeups by delaying timers that
+                        * are right-of a not yet expired timer, because that
+                        * timer will have to trigger a wakeup anyway.
+                        */
+
+                       if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) {
                                ktime_t expires;
 
                                expires = ktime_sub(hrtimer_get_expires(timer),
@@ -1530,9 +1563,14 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
        struct restart_block *restart;
        struct hrtimer_sleeper t;
        int ret = 0;
+       unsigned long slack;
+
+       slack = current->timer_slack_ns;
+       if (rt_task(current))
+               slack = 0;
 
        hrtimer_init_on_stack(&t.timer, clockid, mode);
-       hrtimer_set_expires(&t.timer, timespec_to_ktime(*rqtp));
+       hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack);
        if (do_nanosleep(&t, mode))
                goto out;
 
@@ -1681,14 +1719,20 @@ void __init hrtimers_init(void)
 }
 
 /**
- * schedule_hrtimeout - sleep until timeout
+ * schedule_hrtimeout_range - sleep until timeout
  * @expires:   timeout value (ktime_t)
+ * @delta:     slack in expires timeout (ktime_t)
  * @mode:      timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
  *
  * Make the current task sleep until the given expiry time has
  * elapsed. The routine will return immediately unless
  * the current task state has been set (see set_current_state()).
  *
+ * The @delta argument gives the kernel the freedom to schedule the
+ * actual wakeup to a time that is both power and performance friendly.
+ * The kernel give the normal best effort behavior for "@expires+@delta",
+ * but may decide to fire the timer earlier, but no earlier than @expires.
+ *
  * You can set the task state as follows -
  *
  * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
@@ -1702,7 +1746,7 @@ void __init hrtimers_init(void)
  *
  * Returns 0 when the timer has expired otherwise -EINTR
  */
-int __sched schedule_hrtimeout(ktime_t *expires,
+int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
                               const enum hrtimer_mode mode)
 {
        struct hrtimer_sleeper t;
@@ -1726,7 +1770,7 @@ int __sched schedule_hrtimeout(ktime_t *expires,
        }
 
        hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, mode);
-       hrtimer_set_expires(&t.timer, *expires);
+       hrtimer_set_expires_range_ns(&t.timer, *expires, delta);
 
        hrtimer_init_sleeper(&t, current);
 
@@ -1744,4 +1788,33 @@ int __sched schedule_hrtimeout(ktime_t *expires,
 
        return !t.task ? 0 : -EINTR;
 }
+EXPORT_SYMBOL_GPL(schedule_hrtimeout_range);
+
+/**
+ * schedule_hrtimeout - sleep until timeout
+ * @expires:   timeout value (ktime_t)
+ * @mode:      timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
+ *
+ * Make the current task sleep until the given expiry time has
+ * elapsed. The routine will return immediately unless
+ * the current task state has been set (see set_current_state()).
+ *
+ * You can set the task state as follows -
+ *
+ * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
+ * pass before the routine returns.
+ *
+ * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
+ * delivered to the current task.
+ *
+ * The current task state is guaranteed to be TASK_RUNNING when this
+ * routine returns.
+ *
+ * Returns 0 when the timer has expired otherwise -EINTR
+ */
+int __sched schedule_hrtimeout(ktime_t *expires,
+                              const enum hrtimer_mode mode)
+{
+       return schedule_hrtimeout_range(expires, 0, mode);
+}
 EXPORT_SYMBOL_GPL(schedule_hrtimeout);