Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer updates from Thomas Gleixner:
 "Yet another big pile of changes:

   - More year 2038 work from Arnd slowly reaching the point where we
     need to think about the syscalls themself.

   - A new timer function which allows to conditionally (re)arm a timer
     only when it's either not running or the new expiry time is sooner
     than the armed expiry time. This allows to use a single timer for
     multiple timeout requirements w/o caring about the first expiry
     time at the call site.

   - A new NMI safe accessor to clock real time for the printk timestamp
     work. Can be used by tracing, perf as well if required.

   - A large number of timer setup conversions from Kees which got
     collected here because either maintainers requested so or they
     simply got ignored. As Kees pointed out already there are a few
     trivial merge conflicts and some redundant commits which was
     unavoidable due to the size of this conversion effort.

   - Avoid a redundant iteration in the timer wheel softirq processing.

   - Provide a mechanism to treat RTC implementations depending on their
     hardware properties, i.e. don't inflict the write at the 0.5
     seconds boundary which originates from the PC CMOS RTC to all RTCs.
     No functional change as drivers need to be updated separately.

   - The usual small updates to core code clocksource drivers. Nothing
     really exciting"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (111 commits)
  timers: Add a function to start/reduce a timer
  pstore: Use ktime_get_real_fast_ns() instead of __getnstimeofday()
  timer: Prepare to change all DEFINE_TIMER() callbacks
  netfilter: ipvs: Convert timers to use timer_setup()
  scsi: qla2xxx: Convert timers to use timer_setup()
  block/aoe: discover_timer: Convert timers to use timer_setup()
  ide: Convert timers to use timer_setup()
  drbd: Convert timers to use timer_setup()
  mailbox: Convert timers to use timer_setup()
  crypto: Convert timers to use timer_setup()
  drivers/pcmcia: omap1: Fix error in automated timer conversion
  ARM: footbridge: Fix typo in timer conversion
  drivers/sgi-xp: Convert timers to use timer_setup()
  drivers/pcmcia: Convert timers to use timer_setup()
  drivers/memstick: Convert timers to use timer_setup()
  drivers/macintosh: Convert timers to use timer_setup()
  hwrng/xgene-rng: Convert timers to use timer_setup()
  auxdisplay: Convert timers to use timer_setup()
  sparc/led: Convert timers to use timer_setup()
  mips: ip22/32: Convert timers to use timer_setup()
  ...

1 files changed, 64 insertions, 18 deletions

diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index f2674a0..af0b8ba 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -610,7 +610,7 @@ static bool timer_fixup_init(void *addr, enum debug_obj_state state)
 }
 
 /* Stub timer callback for improperly used timers. */
-static void stub_timer(unsigned long data)
+static void stub_timer(struct timer_list *unused)
 {
 	WARN_ON(1);
 }
@@ -626,7 +626,7 @@ static bool timer_fixup_activate(void *addr, enum debug_obj_state state)
 
 	switch (state) {
 	case ODEBUG_STATE_NOTAVAILABLE:
-		setup_timer(timer, stub_timer, 0);
+		timer_setup(timer, stub_timer, 0);
 		return true;
 
 	case ODEBUG_STATE_ACTIVE:
@@ -665,7 +665,7 @@ static bool timer_fixup_assert_init(void *addr, enum debug_obj_state state)
 
 	switch (state) {
 	case ODEBUG_STATE_NOTAVAILABLE:
-		setup_timer(timer, stub_timer, 0);
+		timer_setup(timer, stub_timer, 0);
 		return true;
 	default:
 		return false;
@@ -929,8 +929,11 @@ static struct timer_base *lock_timer_base(struct timer_list *timer,
 	}
 }
 
+#define MOD_TIMER_PENDING_ONLY		0x01
+#define MOD_TIMER_REDUCE		0x02
+
 static inline int
-__mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
+__mod_timer(struct timer_list *timer, unsigned long expires, unsigned int options)
 {
 	struct timer_base *base, *new_base;
 	unsigned int idx = UINT_MAX;
@@ -950,7 +953,11 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 		 * larger granularity than you would get from adding a new
 		 * timer with this expiry.
 		 */
-		if (timer->expires == expires)
+		long diff = timer->expires - expires;
+
+		if (!diff)
+			return 1;
+		if (options & MOD_TIMER_REDUCE && diff <= 0)
 			return 1;
 
 		/*
@@ -962,6 +969,12 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 		base = lock_timer_base(timer, &flags);
 		forward_timer_base(base);
 
+		if (timer_pending(timer) && (options & MOD_TIMER_REDUCE) &&
+		    time_before_eq(timer->expires, expires)) {
+			ret = 1;
+			goto out_unlock;
+		}
+
 		clk = base->clk;
 		idx = calc_wheel_index(expires, clk);
 
@@ -971,7 +984,10 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 		 * subsequent call will exit in the expires check above.
 		 */
 		if (idx == timer_get_idx(timer)) {
-			timer->expires = expires;
+			if (!(options & MOD_TIMER_REDUCE))
+				timer->expires = expires;
+			else if (time_after(timer->expires, expires))
+				timer->expires = expires;
 			ret = 1;
 			goto out_unlock;
 		}
@@ -981,7 +997,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 	}
 
 	ret = detach_if_pending(timer, base, false);
-	if (!ret && pending_only)
+	if (!ret && (options & MOD_TIMER_PENDING_ONLY))
 		goto out_unlock;
 
 	debug_activate(timer, expires);
@@ -1042,7 +1058,7 @@ out_unlock:
  */
 int mod_timer_pending(struct timer_list *timer, unsigned long expires)
 {
-	return __mod_timer(timer, expires, true);
+	return __mod_timer(timer, expires, MOD_TIMER_PENDING_ONLY);
 }
 EXPORT_SYMBOL(mod_timer_pending);
 
@@ -1068,11 +1084,26 @@ EXPORT_SYMBOL(mod_timer_pending);
  */
 int mod_timer(struct timer_list *timer, unsigned long expires)
 {
-	return __mod_timer(timer, expires, false);
+	return __mod_timer(timer, expires, 0);
 }
 EXPORT_SYMBOL(mod_timer);
 
 /**
+ * timer_reduce - Modify a timer's timeout if it would reduce the timeout
+ * @timer:	The timer to be modified
+ * @expires:	New timeout in jiffies
+ *
+ * timer_reduce() is very similar to mod_timer(), except that it will only
+ * modify a running timer if that would reduce the expiration time (it will
+ * start a timer that isn't running).
+ */
+int timer_reduce(struct timer_list *timer, unsigned long expires)
+{
+	return __mod_timer(timer, expires, MOD_TIMER_REDUCE);
+}
+EXPORT_SYMBOL(timer_reduce);
+
+/**
  * add_timer - start a timer
  * @timer: the timer to be added
  *
@@ -1560,8 +1591,11 @@ static int collect_expired_timers(struct timer_base *base,
 		 * jiffies, otherwise forward to the next expiry time:
 		 */
 		if (time_after(next, jiffies)) {
-			/* The call site will increment clock! */
-			base->clk = jiffies - 1;
+			/*
+			 * The call site will increment base->clk and then
+			 * terminate the expiry loop immediately.
+			 */
+			base->clk = jiffies;
 			return 0;
 		}
 		base->clk = next;
@@ -1668,9 +1702,20 @@ void run_local_timers(void)
 	raise_softirq(TIMER_SOFTIRQ);
 }
 
-static void process_timeout(unsigned long __data)
+/*
+ * Since schedule_timeout()'s timer is defined on the stack, it must store
+ * the target task on the stack as well.
+ */
+struct process_timer {
+	struct timer_list timer;
+	struct task_struct *task;
+};
+
+static void process_timeout(struct timer_list *t)
 {
-	wake_up_process((struct task_struct *)__data);
+	struct process_timer *timeout = from_timer(timeout, t, timer);
+
+	wake_up_process(timeout->task);
 }
 
 /**
@@ -1704,7 +1749,7 @@ static void process_timeout(unsigned long __data)
  */
 signed long __sched schedule_timeout(signed long timeout)
 {
-	struct timer_list timer;
+	struct process_timer timer;
 	unsigned long expire;
 
 	switch (timeout)
@@ -1738,13 +1783,14 @@ signed long __sched schedule_timeout(signed long timeout)
 
 	expire = timeout + jiffies;
 
-	setup_timer_on_stack(&timer, process_timeout, (unsigned long)current);
-	__mod_timer(&timer, expire, false);
+	timer.task = current;
+	timer_setup_on_stack(&timer.timer, process_timeout, 0);
+	__mod_timer(&timer.timer, expire, 0);
 	schedule();
-	del_singleshot_timer_sync(&timer);
+	del_singleshot_timer_sync(&timer.timer);
 
 	/* Remove the timer from the object tracker */
-	destroy_timer_on_stack(&timer);
+	destroy_timer_on_stack(&timer.timer);
 
 	timeout = expire - jiffies;