Merge branch 'v28-range-hrtimers-for-linus-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'v28-range-hrtimers-for-linus-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (37 commits)
  hrtimers: add missing docbook comments to struct hrtimer
  hrtimers: simplify hrtimer_peek_ahead_timers()
  hrtimers: fix docbook comments
  DECLARE_PER_CPU needs linux/percpu.h
  hrtimers: fix typo
  rangetimers: fix the bug reported by Ingo for real
  rangetimer: fix BUG_ON reported by Ingo
  rangetimer: fix x86 build failure for the !HRTIMERS case
  select: fix alpha OSF wrapper
  select: fix alpha OSF wrapper
  hrtimer: peek at the timer queue just before going idle
  hrtimer: make the futex() system call use the per process slack value
  hrtimer: make the nanosleep() syscall use the per process slack
  hrtimer: fix signed/unsigned bug in slack estimator
  hrtimer: show the timer ranges in /proc/timer_list
  hrtimer: incorporate feedback from Peter Zijlstra
  hrtimer: add a hrtimer_start_range() function
  hrtimer: another build fix
  hrtimer: fix build bug found by Ingo
  hrtimer: make select() and poll() use the hrtimer range feature
  ...

arch/alpha/kernel/osf_sys.c

@@ -983,10 +983,12 @@ asmlinkage int
 osf_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp,
 	   struct timeval32 __user *tvp)
 {
-	s64 timeout = MAX_SCHEDULE_TIMEOUT;
+	struct timespec end_time, *to = NULL;
 	if (tvp) {
 		time_t sec, usec;
 
+		to = &end_time;
+
 		if (!access_ok(VERIFY_READ, tvp, sizeof(*tvp))
 		    || __get_user(sec, &tvp->tv_sec)
 		    || __get_user(usec, &tvp->tv_usec)) {
@@ -996,14 +998,13 @@ osf_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp,
 		if (sec < 0 || usec < 0)
 			return -EINVAL;
 
-		if ((unsigned long) sec < MAX_SELECT_SECONDS) {
-			timeout = (usec + 1000000/HZ - 1) / (1000000/HZ);
-			timeout += sec * (unsigned long) HZ;
-		}
+		if (poll_select_set_timeout(to, sec, usec * NSEC_PER_USEC))
+			return -EINVAL;		
+
 	}
 
 	/* OSF does not copy back the remaining time.  */
-	return core_sys_select(n, inp, outp, exp, &timeout);
+	return core_sys_select(n, inp, outp, exp, to);
 }
 
 struct rusage32 {

arch/ia64/kvm/kvm-ia64.c

@@ -1114,7 +1114,7 @@ static void kvm_migrate_hlt_timer(struct kvm_vcpu *vcpu)
 	struct hrtimer *p_ht = &vcpu->arch.hlt_timer;
 
 	if (hrtimer_cancel(p_ht))
-		hrtimer_start(p_ht, p_ht->expires, HRTIMER_MODE_ABS);
+		hrtimer_start_expires(p_ht, HRTIMER_MODE_ABS);
 }
 
 static enum hrtimer_restart hlt_timer_fn(struct hrtimer *data)

arch/powerpc/oprofile/cell/spu_profiler.c

@@ -195,7 +195,7 @@ int start_spu_profiling(unsigned int cycles_reset)
 	pr_debug("timer resolution: %lu\n", TICK_NSEC);
 	kt = ktime_set(0, profiling_interval);
 	hrtimer_init(&timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	timer.expires = kt;
+	hrtimer_set_expires(&timer, kt);
 	timer.function = profile_spus;
 
 	/* Allocate arrays for collecting SPU PC samples */

arch/x86/kvm/i8254.c

@@ -204,10 +204,10 @@ static int __pit_timer_fn(struct kvm_kpit_state *ps)
 	if (vcpu0 && waitqueue_active(&vcpu0->wq))
 		wake_up_interruptible(&vcpu0->wq);
 
-	pt->timer.expires = ktime_add_ns(pt->timer.expires, pt->period);
-	pt->scheduled = ktime_to_ns(pt->timer.expires);
+	hrtimer_add_expires_ns(&pt->timer, pt->period);
+	pt->scheduled = hrtimer_get_expires_ns(&pt->timer);
 	if (pt->period)
-		ps->channels[0].count_load_time = pt->timer.expires;
+		ps->channels[0].count_load_time = hrtimer_get_expires(&pt->timer);
 
 	return (pt->period == 0 ? 0 : 1);
 }
@@ -257,7 +257,7 @@ void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu)
 
 	timer = &pit->pit_state.pit_timer.timer;
 	if (hrtimer_cancel(timer))
-		hrtimer_start(timer, timer->expires, HRTIMER_MODE_ABS);
+		hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
 }
 
 static void destroy_pit_timer(struct kvm_kpit_timer *pt)

arch/x86/kvm/lapic.c

@@ -946,9 +946,7 @@ static int __apic_timer_fn(struct kvm_lapic *apic)
 
 	if (apic_lvtt_period(apic)) {
 		result = 1;
-		apic->timer.dev.expires = ktime_add_ns(
-					apic->timer.dev.expires,
-					apic->timer.period);
+		hrtimer_add_expires_ns(&apic->timer.dev, apic->timer.period);
 	}
 	return result;
 }
@@ -1117,7 +1115,7 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu)
 
 	timer = &apic->timer.dev;
 	if (hrtimer_cancel(timer))
-		hrtimer_start(timer, timer->expires, HRTIMER_MODE_ABS);
+		hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
 }
 
 void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu)

drivers/cpuidle/cpuidle.c

@@ -16,6 +16,7 @@
 #include <linux/cpu.h>
 #include <linux/cpuidle.h>
 #include <linux/ktime.h>
+#include <linux/hrtimer.h>
 
 #include "cpuidle.h"
 
@@ -64,6 +65,12 @@ static void cpuidle_idle_call(void)
 		return;
 	}
 
+	/*
+	 * run any timers that can be run now, at this point
+	 * before calculating the idle duration etc.
+	 */
+	hrtimer_peek_ahead_timers();
+
 	/* ask the governor for the next state */
 	next_state = cpuidle_curr_governor->select(dev);
 	if (need_resched())

drivers/s390/crypto/ap_bus.c

@@ -659,9 +659,9 @@ static ssize_t poll_timeout_store(struct bus_type *bus, const char *buf,
 	hr_time = ktime_set(0, poll_timeout);
 
 	if (!hrtimer_is_queued(&ap_poll_timer) ||
-	    !hrtimer_forward(&ap_poll_timer, ap_poll_timer.expires, hr_time)) {
-		ap_poll_timer.expires = hr_time;
-		hrtimer_start(&ap_poll_timer, hr_time, HRTIMER_MODE_ABS);
+	    !hrtimer_forward(&ap_poll_timer, hrtimer_get_expires(&ap_poll_timer), hr_time)) {
+		hrtimer_set_expires(&ap_poll_timer, hr_time);
+		hrtimer_start_expires(&ap_poll_timer, HRTIMER_MODE_ABS);
 	}
 	return count;
 }

fs/compat.c

@@ -1469,6 +1469,57 @@ out_ret:
 
 #define __COMPAT_NFDBITS       (8 * sizeof(compat_ulong_t))
 
+static int poll_select_copy_remaining(struct timespec *end_time, void __user *p,
+				      int timeval, int ret)
+{
+	struct timespec ts;
+
+	if (!p)
+		return ret;
+
+	if (current->personality & STICKY_TIMEOUTS)
+		goto sticky;
+
+	/* No update for zero timeout */
+	if (!end_time->tv_sec && !end_time->tv_nsec)
+		return ret;
+
+	ktime_get_ts(&ts);
+	ts = timespec_sub(*end_time, ts);
+	if (ts.tv_sec < 0)
+		ts.tv_sec = ts.tv_nsec = 0;
+
+	if (timeval) {
+		struct compat_timeval rtv;
+
+		rtv.tv_sec = ts.tv_sec;
+		rtv.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
+
+		if (!copy_to_user(p, &rtv, sizeof(rtv)))
+			return ret;
+	} else {
+		struct compat_timespec rts;
+
+		rts.tv_sec = ts.tv_sec;
+		rts.tv_nsec = ts.tv_nsec;
+
+		if (!copy_to_user(p, &rts, sizeof(rts)))
+			return ret;
+	}
+	/*
+	 * If an application puts its timeval in read-only memory, we
+	 * don't want the Linux-specific update to the timeval to
+	 * cause a fault after the select has completed
+	 * successfully. However, because we're not updating the
+	 * timeval, we can't restart the system call.
+	 */
+
+sticky:
+	if (ret == -ERESTARTNOHAND)
+		ret = -EINTR;
+	return ret;
+}
+
 /*
  * Ooo, nasty.  We need here to frob 32-bit unsigned longs to
  * 64-bit unsigned longs.
@@ -1550,7 +1601,8 @@ int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset,
 	((unsigned long) (MAX_SCHEDULE_TIMEOUT / HZ)-1)
 
 int compat_core_sys_select(int n, compat_ulong_t __user *inp,
-	compat_ulong_t __user *outp, compat_ulong_t __user *exp, s64 *timeout)
+	compat_ulong_t __user *outp, compat_ulong_t __user *exp,
+	struct timespec *end_time)
 {
 	fd_set_bits fds;
 	void *bits;
@@ -1597,7 +1649,7 @@ int compat_core_sys_select(int n, compat_ulong_t __user *inp,
 	zero_fd_set(n, fds.res_out);
 	zero_fd_set(n, fds.res_ex);
 
-	ret = do_select(n, &fds, timeout);
+	ret = do_select(n, &fds, end_time);
 
 	if (ret < 0)
 		goto out;
@@ -1623,7 +1675,7 @@ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp,
 	compat_ulong_t __user *outp, compat_ulong_t __user *exp,
 	struct compat_timeval __user *tvp)
 {
-	s64 timeout = -1;
+	struct timespec end_time, *to = NULL;
 	struct compat_timeval tv;
 	int ret;
 
@@ -1631,43 +1683,14 @@ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp,
 		if (copy_from_user(&tv, tvp, sizeof(tv)))
 			return -EFAULT;
 
-		if (tv.tv_sec < 0 || tv.tv_usec < 0)
+		to = &end_time;
+		if (poll_select_set_timeout(to, tv.tv_sec,
+					    tv.tv_usec * NSEC_PER_USEC))
 			return -EINVAL;
-
-		/* Cast to u64 to make GCC stop complaining */
-		if ((u64)tv.tv_sec >= (u64)MAX_INT64_SECONDS)
-			timeout = -1;	/* infinite */
-		else {
-			timeout = DIV_ROUND_UP(tv.tv_usec, 1000000/HZ);
-			timeout += tv.tv_sec * HZ;
-		}
 	}
 
-	ret = compat_core_sys_select(n, inp, outp, exp, &timeout);
-
-	if (tvp) {
-		struct compat_timeval rtv;
-
-		if (current->personality & STICKY_TIMEOUTS)
-			goto sticky;
-		rtv.tv_usec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ));
-		rtv.tv_sec = timeout;
-		if (compat_timeval_compare(&rtv, &tv) >= 0)
-			rtv = tv;
-		if (copy_to_user(tvp, &rtv, sizeof(rtv))) {
-sticky:
-			/*
-			 * If an application puts its timeval in read-only
-			 * memory, we don't want the Linux-specific update to
-			 * the timeval to cause a fault after the select has
-			 * completed successfully. However, because we're not
-			 * updating the timeval, we can't restart the system
-			 * call.
-			 */
-			if (ret == -ERESTARTNOHAND)
-				ret = -EINTR;
-		}
-	}
+	ret = compat_core_sys_select(n, inp, outp, exp, to);
+	ret = poll_select_copy_remaining(&end_time, tvp, 1, ret);
 
 	return ret;
 }
@@ -1680,15 +1703,16 @@ asmlinkage long compat_sys_pselect7(int n, compat_ulong_t __user *inp,
 {
 	compat_sigset_t ss32;
 	sigset_t ksigmask, sigsaved;
-	s64 timeout = MAX_SCHEDULE_TIMEOUT;
 	struct compat_timespec ts;
+	struct timespec end_time, *to = NULL;
 	int ret;
 
 	if (tsp) {
 		if (copy_from_user(&ts, tsp, sizeof(ts)))
 			return -EFAULT;
 
-		if (ts.tv_sec < 0 || ts.tv_nsec < 0)
+		to = &end_time;
+		if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
 			return -EINVAL;
 	}
 
@@ -1703,51 +1727,8 @@ asmlinkage long compat_sys_pselect7(int n, compat_ulong_t __user *inp,
 		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
 	}
 
-	do {
-		if (tsp) {
-			if ((unsigned long)ts.tv_sec < MAX_SELECT_SECONDS) {
-				timeout = DIV_ROUND_UP(ts.tv_nsec, 1000000000/HZ);
-				timeout += ts.tv_sec * (unsigned long)HZ;
-				ts.tv_sec = 0;
-				ts.tv_nsec = 0;
-			} else {
-				ts.tv_sec -= MAX_SELECT_SECONDS;
-				timeout = MAX_SELECT_SECONDS * HZ;
-			}
-		}
-
-		ret = compat_core_sys_select(n, inp, outp, exp, &timeout);
-
-	} while (!ret && !timeout && tsp && (ts.tv_sec || ts.tv_nsec));
-
-	if (tsp) {
-		struct compat_timespec rts;
-
-		if (current->personality & STICKY_TIMEOUTS)
-			goto sticky;
-
-		rts.tv_sec = timeout / HZ;
-		rts.tv_nsec = (timeout % HZ) * (NSEC_PER_SEC/HZ);
-		if (rts.tv_nsec >= NSEC_PER_SEC) {
-			rts.tv_sec++;
-			rts.tv_nsec -= NSEC_PER_SEC;
-		}
-		if (compat_timespec_compare(&rts, &ts) >= 0)
-			rts = ts;
-		if (copy_to_user(tsp, &rts, sizeof(rts))) {
-sticky:
-			/*
-			 * If an application puts its timeval in read-only
-			 * memory, we don't want the Linux-specific update to
-			 * the timeval to cause a fault after the select has
-			 * completed successfully. However, because we're not
-			 * updating the timeval, we can't restart the system
-			 * call.
-			 */
-			if (ret == -ERESTARTNOHAND)
-				ret = -EINTR;
-		}
-	}
+	ret = compat_core_sys_select(n, inp, outp, exp, to);
+	ret = poll_select_copy_remaining(&end_time, tsp, 0, ret);
 
 	if (ret == -ERESTARTNOHAND) {
 		/*
@@ -1792,18 +1773,16 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds,
 	compat_sigset_t ss32;
 	sigset_t ksigmask, sigsaved;
 	struct compat_timespec ts;
-	s64 timeout = -1;
+	struct timespec end_time, *to = NULL;
 	int ret;
 
 	if (tsp) {
 		if (copy_from_user(&ts, tsp, sizeof(ts)))
 			return -EFAULT;
 
-		/* We assume that ts.tv_sec is always lower than
-		   the number of seconds that can be expressed in
-		   an s64. Otherwise the compiler bitches at us */
-		timeout = DIV_ROUND_UP(ts.tv_nsec, 1000000000/HZ);
-		timeout += ts.tv_sec * HZ;
+		to = &end_time;
+		if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
+			return -EINVAL;
 	}
 
 	if (sigmask) {
@@ -1817,7 +1796,7 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds,
 		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
 	}
 
-	ret = do_sys_poll(ufds, nfds, &timeout);
+	ret = do_sys_poll(ufds, nfds, to);
 
 	/* We can restart this syscall, usually */
 	if (ret == -EINTR) {
@@ -1835,31 +1814,7 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds,
 	} else if (sigmask)
 		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
 
-	if (tsp && timeout >= 0) {
-		struct compat_timespec rts;
-
-		if (current->personality & STICKY_TIMEOUTS)
-			goto sticky;
-		/* Yes, we know it's actually an s64, but it's also positive. */
-		rts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) *
-					1000;
-		rts.tv_sec = timeout;
-		if (compat_timespec_compare(&rts, &ts) >= 0)
-			rts = ts;
-		if (copy_to_user(tsp, &rts, sizeof(rts))) {
-sticky:
-			/*
-			 * If an application puts its timeval in read-only
-			 * memory, we don't want the Linux-specific update to
-			 * the timeval to cause a fault after the select has
-			 * completed successfully. However, because we're not
-			 * updating the timeval, we can't restart the system
-			 * call.
-			 */
-			if (ret == -ERESTARTNOHAND && timeout >= 0)
-				ret = -EINTR;
-		}
-	}
+	ret = poll_select_copy_remaining(&end_time, tsp, 0, ret);
 
 	return ret;
 }

fs/timerfd.c

@@ -52,11 +52,9 @@ static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr)
 
 static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx)
 {
-	ktime_t now, remaining;
-
-	now = ctx->tmr.base->get_time();
-	remaining = ktime_sub(ctx->tmr.expires, now);
+	ktime_t remaining;
 
+	remaining = hrtimer_expires_remaining(&ctx->tmr);
 	return remaining.tv64 < 0 ? ktime_set(0, 0): remaining;
 }
 
@@ -74,7 +72,7 @@ static void timerfd_setup(struct timerfd_ctx *ctx, int flags,
 	ctx->ticks = 0;
 	ctx->tintv = timespec_to_ktime(ktmr->it_interval);
 	hrtimer_init(&ctx->tmr, ctx->clockid, htmode);
-	ctx->tmr.expires = texp;
+	hrtimer_set_expires(&ctx->tmr, texp);
 	ctx->tmr.function = timerfd_tmrproc;
 	if (texp.tv64 != 0)
 		hrtimer_start(&ctx->tmr, texp, htmode);

include/linux/hrtimer.h

@@ -20,6 +20,8 @@
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/wait.h>
+#include <linux/percpu.h>
+
 
 struct hrtimer_clock_base;
 struct hrtimer_cpu_base;
@@ -101,9 +103,14 @@ enum hrtimer_cb_mode {
 /**
  * struct hrtimer - the basic hrtimer structure
  * @node:	red black tree node for time ordered insertion
- * @expires:	the absolute expiry time in the hrtimers internal
+ * @_expires:	the absolute expiry time in the hrtimers internal
  *		representation. The time is related to the clock on
- *		which the timer is based.
+ *		which the timer is based. Is setup by adding
+ *		slack to the _softexpires value. For non range timers
+ *		identical to _softexpires.
+ * @_softexpires: the absolute earliest expiry time of the hrtimer.
+ *		The time which was given as expiry time when the timer
+ *		was armed.
  * @function:	timer expiry callback function
  * @base:	pointer to the timer base (per cpu and per clock)
  * @state:	state information (See bit values above)
@@ -121,7 +128,8 @@ enum hrtimer_cb_mode {
  */
 struct hrtimer {
 	struct rb_node			node;
-	ktime_t				expires;
+	ktime_t				_expires;
+	ktime_t				_softexpires;
 	enum hrtimer_restart		(*function)(struct hrtimer *);
 	struct hrtimer_clock_base	*base;
 	unsigned long			state;
@@ -201,6 +209,71 @@ struct hrtimer_cpu_base {
 #endif
 };
 
+static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time)
+{
+	timer->_expires = time;
+	timer->_softexpires = time;
+}
+
+static inline void hrtimer_set_expires_range(struct hrtimer *timer, ktime_t time, ktime_t delta)
+{
+	timer->_softexpires = time;
+	timer->_expires = ktime_add_safe(time, delta);
+}
+
+static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, unsigned long delta)
+{
+	timer->_softexpires = time;
+	timer->_expires = ktime_add_safe(time, ns_to_ktime(delta));
+}
+
+static inline void hrtimer_set_expires_tv64(struct hrtimer *timer, s64 tv64)
+{
+	timer->_expires.tv64 = tv64;
+	timer->_softexpires.tv64 = tv64;
+}
+
+static inline void hrtimer_add_expires(struct hrtimer *timer, ktime_t time)
+{
+	timer->_expires = ktime_add_safe(timer->_expires, time);
+	timer->_softexpires = ktime_add_safe(timer->_softexpires, time);
+}
+
+static inline void hrtimer_add_expires_ns(struct hrtimer *timer, unsigned long ns)
+{
+	timer->_expires = ktime_add_ns(timer->_expires, ns);
+	timer->_softexpires = ktime_add_ns(timer->_softexpires, ns);
+}
+
+static inline ktime_t hrtimer_get_expires(const struct hrtimer *timer)
+{
+	return timer->_expires;
+}
+
+static inline ktime_t hrtimer_get_softexpires(const struct hrtimer *timer)
+{
+	return timer->_softexpires;
+}
+
+static inline s64 hrtimer_get_expires_tv64(const struct hrtimer *timer)
+{
+	return timer->_expires.tv64;
+}
+static inline s64 hrtimer_get_softexpires_tv64(const struct hrtimer *timer)
+{
+	return timer->_softexpires.tv64;
+}
+
+static inline s64 hrtimer_get_expires_ns(const struct hrtimer *timer)
+{
+	return ktime_to_ns(timer->_expires);
+}
+
+static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer)
+{
+    return ktime_sub(timer->_expires, timer->base->get_time());
+}
+
 #ifdef CONFIG_HIGH_RES_TIMERS
 struct clock_event_device;
 
@@ -221,6 +294,8 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer)
 	return timer->base->cpu_base->hres_active;
 }
 
+extern void hrtimer_peek_ahead_timers(void);
+
 /*
  * The resolution of the clocks. The resolution value is returned in
  * the clock_getres() system call to give application programmers an
@@ -243,6 +318,7 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer)
  * is expired in the next softirq when the clock was advanced.
  */
 static inline void clock_was_set(void) { }
+static inline void hrtimer_peek_ahead_timers(void) { }
 
 static inline void hres_timers_resume(void) { }
 
@@ -264,6 +340,10 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer)
 extern ktime_t ktime_get(void);
 extern ktime_t ktime_get_real(void);
 
+
+DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
+
+
 /* Exported timer functions: */
 
 /* Initialize timers: */
@@ -288,12 +368,25 @@ static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { }
 /* Basic timer operations: */
 extern int hrtimer_start(struct hrtimer *timer, ktime_t tim,
 			 const enum hrtimer_mode mode);
+extern int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+			unsigned long range_ns, const enum hrtimer_mode mode);
 extern int hrtimer_cancel(struct hrtimer *timer);
 extern int hrtimer_try_to_cancel(struct hrtimer *timer);
 
+static inline int hrtimer_start_expires(struct hrtimer *timer,
+						enum hrtimer_mode mode)
+{
+	unsigned long delta;
+	ktime_t soft, hard;
+	soft = hrtimer_get_softexpires(timer);
+	hard = hrtimer_get_expires(timer);
+	delta = ktime_to_ns(ktime_sub(hard, soft));
+	return hrtimer_start_range_ns(timer, soft, delta, mode);
+}
+
 static inline int hrtimer_restart(struct hrtimer *timer)
 {
-	return hrtimer_start(timer, timer->expires, HRTIMER_MODE_ABS);
+	return hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
 }
 
 /* Query timers: */
@@ -350,6 +443,10 @@ extern long hrtimer_nanosleep_restart(struct restart_block *restart_block);
 extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl,
 				 struct task_struct *tsk);
 
+extern int schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
+						const enum hrtimer_mode mode);
+extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode);
+
 /* Soft interrupt function to run the hrtimer queues: */
 extern void hrtimer_run_queues(void);
 extern void hrtimer_run_pending(void);

include/linux/init_task.h

@@ -170,6 +170,7 @@ extern struct group_info init_groups;
 	.cpu_timers	= INIT_CPU_TIMERS(tsk.cpu_timers),		\
 	.fs_excl	= ATOMIC_INIT(0),				\
 	.pi_lock	= __SPIN_LOCK_UNLOCKED(tsk.pi_lock),		\
+	.timer_slack_ns = 50000, /* 50 usec default slack */		\
 	.pids = {							\
 		[PIDTYPE_PID]  = INIT_PID_LINK(PIDTYPE_PID),		\
 		[PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID),		\

include/linux/poll.h

@@ -114,11 +114,13 @@ void zero_fd_set(unsigned long nr, unsigned long *fdset)
 
 #define MAX_INT64_SECONDS (((s64)(~((u64)0)>>1)/HZ)-1)
 
-extern int do_select(int n, fd_set_bits *fds, s64 *timeout);
+extern int do_select(int n, fd_set_bits *fds, struct timespec *end_time);
 extern int do_sys_poll(struct pollfd __user * ufds, unsigned int nfds,
-		       s64 *timeout);
+		       struct timespec *end_time);
 extern int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
-			   fd_set __user *exp, s64 *timeout);
+			   fd_set __user *exp, struct timespec *end_time);
+
+extern int poll_select_set_timeout(struct timespec *to, long sec, long nsec);
 
 #endif /* KERNEL */
 

include/linux/prctl.h

@@ -78,4 +78,11 @@
 #define PR_GET_SECUREBITS 27
 #define PR_SET_SECUREBITS 28
 
+/*
+ * Get/set the timerslack as used by poll/select/nanosleep
+ * A value of 0 means "use default"
+ */
+#define PR_SET_TIMERSLACK 29
+#define PR_GET_TIMERSLACK 30
+
 #endif /* _LINUX_PRCTL_H */

include/linux/sched.h

@@ -1345,6 +1345,12 @@ struct task_struct {
 	int latency_record_count;
 	struct latency_record latency_record[LT_SAVECOUNT];
 #endif
+	/*
+	 * time slack values; these are used to round up poll() and
+	 * select() etc timeout values. These are in nanoseconds.
+	 */
+	unsigned long timer_slack_ns;
+	unsigned long default_timer_slack_ns;
 };
 
 /*

include/linux/thread_info.h

@@ -38,6 +38,14 @@ struct restart_block {
 #endif
 			u64 expires;
 		} nanosleep;
+		/* For poll */
+		struct {
+			struct pollfd __user *ufds;
+			int nfds;
+			int has_timeout;
+			unsigned long tv_sec;
+			unsigned long tv_nsec;
+		} poll;
 	};
 };
 

include/linux/time.h

@@ -40,6 +40,8 @@ extern struct timezone sys_tz;
 #define NSEC_PER_SEC	1000000000L
 #define FSEC_PER_SEC	1000000000000000L
 
+#define TIME_T_MAX	(time_t)((1UL << ((sizeof(time_t) << 3) - 1)) - 1)
+
 static inline int timespec_equal(const struct timespec *a,
                                  const struct timespec *b)
 {
@@ -74,6 +76,8 @@ extern unsigned long mktime(const unsigned int year, const unsigned int mon,
 			    const unsigned int min, const unsigned int sec);
 
 extern void set_normalized_timespec(struct timespec *ts, time_t sec, long nsec);
+extern struct timespec timespec_add_safe(const struct timespec lhs,
+					 const struct timespec rhs);
 
 /*
  * sub = lhs - rhs, in normalized form

kernel/fork.c

@@ -1018,6 +1018,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->prev_utime = cputime_zero;
 	p->prev_stime = cputime_zero;
 
+	p->default_timer_slack_ns = current->timer_slack_ns;
+
 #ifdef CONFIG_DETECT_SOFTLOCKUP
 	p->last_switch_count = 0;
 	p->last_switch_timestamp = 0;

kernel/futex.c

@@ -1296,13 +1296,16 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 		if (!abs_time)
 			schedule();
 		else {
+			unsigned long slack;
+			slack = current->timer_slack_ns;
+			if (rt_task(current))
+				slack = 0;
 			hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC,
 						HRTIMER_MODE_ABS);
 			hrtimer_init_sleeper(&t, current);
-			t.timer.expires = *abs_time;
+			hrtimer_set_expires_range_ns(&t.timer, *abs_time, slack);
 
-			hrtimer_start(&t.timer, t.timer.expires,
-						HRTIMER_MODE_ABS);
+			hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS);
 			if (!hrtimer_active(&t.timer))
 				t.task = NULL;
 
@@ -1404,7 +1407,7 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 		hrtimer_init_on_stack(&to->timer, CLOCK_REALTIME,
 				      HRTIMER_MODE_ABS);
 		hrtimer_init_sleeper(to, current);
-		to->timer.expires = *time;
+		hrtimer_set_expires(&to->timer, *time);
 	}
 
 	q.pi_state = NULL;

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 hrtimer 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 hrtimer 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 +1383,30 @@ 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)
+{
+	struct tick_device *td;
+	unsigned long flags;
+
+	if (!hrtimer_hres_active())
+		return;
+
+	local_irq_save(flags);
+	td = &__get_cpu_var(tick_cpu_device);
+	if (td && td->evtdev)
+		hrtimer_interrupt(td->evtdev);
+	local_irq_restore(flags);
+}
+
 static void run_hrtimer_softirq(struct softirq_action *h)
 {
 	run_hrtimer_pending(&__get_cpu_var(hrtimer_bases));
@@ -1414,7 +1472,8 @@ 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) {
@@ -1462,7 +1521,7 @@ 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;
 
@@ -1484,7 +1543,7 @@ 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);
@@ -1503,7 +1562,7 @@ 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;
@@ -1528,9 +1587,14 @@ 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;
 
@@ -1550,7 +1614,7 @@ 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:
@@ -1752,3 +1816,103 @@ 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);