1 files changed, 191 insertions, 21 deletions

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index cdec83e722fa..51ee90bca2de 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -517,7 +517,7 @@ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base)
                 if (!base->first)
                         continue;
                 timer = rb_entry(base->first, struct hrtimer, node);
-                expires = ktime_sub(timer->expires, base->offset);
+                expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
                 if (expires.tv64 < cpu_base->expires_next.tv64)
                         cpu_base->expires_next = expires;
         }
@@ -539,10 +539,10 @@ static int hrtimer_reprogram(struct hrtimer *timer,
                              struct hrtimer_clock_base *base)
 {
         ktime_t *expires_next = &__get_cpu_var(hrtimer_bases).expires_next;
-        ktime_t expires = ktime_sub(timer->expires, base->offset);
+        ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
         int res;
 
-        WARN_ON_ONCE(timer->expires.tv64 < 0);
+        WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0);
 
         /*
          * When the callback is running, we do not reprogram the clock event
@@ -795,7 +795,7 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
         u64 orun = 1;
         ktime_t delta;
 
-        delta = ktime_sub(now, timer->expires);
+        delta = ktime_sub(now, hrtimer_get_expires(timer));
 
         if (delta.tv64 < 0)
                 return 0;
@@ -807,8 +807,8 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
                 s64 incr = ktime_to_ns(interval);
 
                 orun = ktime_divns(delta, incr);
-                timer->expires = ktime_add_ns(timer->expires, incr * orun);
-                if (timer->expires.tv64 > now.tv64)
+                hrtimer_add_expires_ns(timer, incr * orun);
+                if (hrtimer_get_expires_tv64(timer) > now.tv64)
                         return orun;
                 /*
                  * This (and the ktime_add() below) is the
@@ -816,7 +816,7 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
                  */
                 orun++;
         }
-        timer->expires = ktime_add_safe(timer->expires, interval);
+        hrtimer_add_expires(timer, interval);
 
         return orun;
 }
@@ -848,7 +848,8 @@ static void enqueue_hrtimer(struct hrtimer *timer,
                  * We dont care about collisions. Nodes with
                  * the same expiry time stay together.
                  */
-                if (timer->expires.tv64 < entry->expires.tv64) {
+                if (hrtimer_get_expires_tv64(timer) <
+                                hrtimer_get_expires_tv64(entry)) {
                         link = &(*link)->rb_left;
                 } else {
                         link = &(*link)->rb_right;
@@ -945,9 +946,10 @@ 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 +957,8 @@ 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 +986,7 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
 #endif
         }
 
-        timer->expires = tim;
+        hrtimer_set_expires_range_ns(timer, tim, delta_ns);
 
         timer_stats_hrtimer_set_start_info(timer);
 
@@ -1016,8 +1019,26 @@ 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
@@ -1077,7 +1098,7 @@ ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
         ktime_t rem;
 
         base = lock_hrtimer_base(timer, &flags);
-        rem = ktime_sub(timer->expires, base->get_time());
+        rem = hrtimer_expires_remaining(timer);
         unlock_hrtimer_base(timer, &flags);
 
         return rem;
@@ -1109,7 +1130,7 @@ ktime_t hrtimer_get_next_event(void)
                                 continue;
 
                         timer = rb_entry(base->first, struct hrtimer, node);
-                        delta.tv64 = timer->expires.tv64;
+                        delta.tv64 = hrtimer_get_expires_tv64(timer);
                         delta = ktime_sub(delta, base->get_time());
                         if (delta.tv64 < mindelta.tv64)
                                 mindelta.tv64 = delta.tv64;
@@ -1310,10 +1331,23 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 
                         timer = rb_entry(node, struct hrtimer, node);
 
-                        if (basenow.tv64 < timer->expires.tv64) {
+                        /*
+                         * 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(timer->expires,
+                                expires = ktime_sub(hrtimer_get_expires(timer),
                                                     base->offset);
                                 if (expires.tv64 < expires_next.tv64)
                                         expires_next = expires;
@@ -1349,6 +1383,36 @@ void hrtimer_interrupt(struct clock_event_device *dev)
                 raise_softirq(HRTIMER_SOFTIRQ);
 }
 
+/**
+ * hrtimer_peek_ahead_timers -- run soft-expired timers now
+ *
+ * hrtimer_peek_ahead_timers will peek at the timer queue of
+ * the current cpu and check if there are any timers for which
+ * the soft expires time has passed. If any such timers exist,
+ * they are run immediately and then removed from the timer queue.
+ *
+ */
+void hrtimer_peek_ahead_timers(void)
+{
+        unsigned long flags;
+        struct tick_device *td;
+        struct clock_event_device *dev;
+
+        if (!hrtimer_hres_active())
+                return;
+
+        local_irq_save(flags);
+        td = &__get_cpu_var(tick_cpu_device);
+        if (!td)
+                goto out;
+        dev = td->evtdev;
+        if (!dev)
+                goto out;
+        hrtimer_interrupt(dev);
+out:
+        local_irq_restore(flags);
+}
+
 static void run_hrtimer_softirq(struct softirq_action *h)
 {
         run_hrtimer_pending(&__get_cpu_var(hrtimer_bases));
@@ -1416,7 +1480,8 @@ void hrtimer_run_queues(void)
                         struct hrtimer *timer;
 
                         timer = rb_entry(node, struct hrtimer, node);
-                        if (base->softirq_time.tv64 <= timer->expires.tv64)
+                        if (base->softirq_time.tv64 <=
+                                        hrtimer_get_expires_tv64(timer))
                                 break;
 
                         if (timer->cb_mode == HRTIMER_CB_SOFTIRQ) {
@@ -1464,7 +1529,7 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod
 
         do {
                 set_current_state(TASK_INTERRUPTIBLE);
-                hrtimer_start(&t->timer, t->timer.expires, mode);
+                hrtimer_start_expires(&t->timer, mode);
                 if (!hrtimer_active(&t->timer))
                         t->task = NULL;
 
@@ -1486,7 +1551,7 @@ static int update_rmtp(struct hrtimer *timer, struct timespec __user *rmtp)
         struct timespec rmt;
         ktime_t rem;
 
-        rem = ktime_sub(timer->expires, timer->base->get_time());
+        rem = hrtimer_expires_remaining(timer);
         if (rem.tv64 <= 0)
                 return 0;
         rmt = ktime_to_timespec(rem);
@@ -1505,7 +1570,7 @@ long __sched hrtimer_nanosleep_restart(struct restart_block *restart)
 
         hrtimer_init_on_stack(&t.timer, restart->nanosleep.index,
                                 HRTIMER_MODE_ABS);
-        t.timer.expires.tv64 = restart->nanosleep.expires;
+        hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires);
 
         if (do_nanosleep(&t, HRTIMER_MODE_ABS))
                 goto out;
@@ -1530,9 +1595,14 @@ 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);
-        t.timer.expires = timespec_to_ktime(*rqtp);
+        hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack);
         if (do_nanosleep(&t, mode))
                 goto out;
 
@@ -1552,7 +1622,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
         restart->fn = hrtimer_nanosleep_restart;
         restart->nanosleep.index = t.timer.base->index;
         restart->nanosleep.rmtp = rmtp;
-        restart->nanosleep.expires = t.timer.expires.tv64;
+        restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer);
 
         ret = -ERESTART_RESTARTBLOCK;
 out:
@@ -1753,3 +1823,103 @@ void __init hrtimers_init(void)
 #endif
 }
 
+/**
+ * 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
+ * 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_range(ktime_t *expires, unsigned long delta,
+                               const enum hrtimer_mode mode)
+{
+        struct hrtimer_sleeper t;
+
+        /*
+         * Optimize when a zero timeout value is given. It does not
+         * matter whether this is an absolute or a relative time.
+         */
+        if (expires && !expires->tv64) {
+                __set_current_state(TASK_RUNNING);
+                return 0;
+        }
+
+        /*
+         * A NULL parameter means "inifinte"
+         */
+        if (!expires) {
+                schedule();
+                __set_current_state(TASK_RUNNING);
+                return -EINTR;
+        }
+
+        hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, mode);
+        hrtimer_set_expires_range_ns(&t.timer, *expires, delta);
+
+        hrtimer_init_sleeper(&t, current);
+
+        hrtimer_start_expires(&t.timer, mode);
+        if (!hrtimer_active(&t.timer))
+                t.task = NULL;
+
+        if (likely(t.task))
+                schedule();
+
+        hrtimer_cancel(&t.timer);
+        destroy_hrtimer_on_stack(&t.timer);
+
+        __set_current_state(TASK_RUNNING);
+
+        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);