13 files changed, 289 insertions, 124 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index b1dda78a1e75..c5c7292daba0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2812,6 +2812,10 @@ M:	Thomas Gleixner <tglx@linutronix.de>
 S:      Maintained
 F:      Documentation/timers/
 F:      kernel/hrtimer.c
+F:      kernel/time/clockevents.c
+F:      kernel/time/tick*.*
+F:      kernel/time/timer_*.c
+F       include/linux/clockevents.h
 F:      include/linux/hrtimer.h
 
 HIGH-SPEED SCC DRIVER FOR AX.25
@@ -5142,6 +5146,18 @@ L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 S:      Supported
 F:      sound/soc/s3c24xx
 
+TIMEKEEPING, NTP
+M:      John Stultz <johnstul@us.ibm.com>
+M:      Thomas Gleixner <tglx@linutronix.de>
+S:      Supported
+F:      include/linux/clocksource.h
+F:      include/linux/time.h
+F:      include/linux/timex.h
+F:      include/linux/timekeeping.h
+F:      kernel/time/clocksource.c
+F:      kernel/time/time*.c
+F:      kernel/time/ntp.c
+
 TLG2300 VIDEO4LINUX-2 DRIVER
 M:      Huang Shijie <shijie8@gmail.com>
 M:      Kang Yong <kangyong@telegent.com>
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index fd0c1b857d3d..330586ffffbb 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -22,7 +22,7 @@
 #include <linux/wait.h>
 #include <linux/percpu.h>
 #include <linux/timer.h>
-
+#include <linux/timerqueue.h>
 
 struct hrtimer_clock_base;
 struct hrtimer_cpu_base;
@@ -79,8 +79,8 @@ enum hrtimer_restart {
 
 /**
  * struct hrtimer - the basic hrtimer structure
- * @node:       red black tree node for time ordered insertion
- * @_expires:   the absolute expiry time in the hrtimers internal
+ * @node:       timerqueue node, which also manages node.expires,
+ *              the absolute expiry time in the hrtimers internal
  *              representation. The time is related to the clock on
  *              which the timer is based. Is setup by adding
  *              slack to the _softexpires value. For non range timers
@@ -101,8 +101,7 @@ enum hrtimer_restart {
  * The hrtimer structure must be initialized by hrtimer_init()
  */
 struct hrtimer {
-        struct rb_node                  node;
-        ktime_t                         _expires;
+        struct timerqueue_node          node;
         ktime_t                         _softexpires;
         enum hrtimer_restart            (*function)(struct hrtimer *);
         struct hrtimer_clock_base       *base;
@@ -141,8 +140,7 @@ struct hrtimer_sleeper {
 struct hrtimer_clock_base {
         struct hrtimer_cpu_base *cpu_base;
         clockid_t               index;
-        struct rb_root          active;
-        struct rb_node          *first;
+        struct timerqueue_head  active;
         ktime_t                 resolution;
         ktime_t                 (*get_time)(void);
         ktime_t                 softirq_time;
@@ -158,7 +156,6 @@ struct hrtimer_clock_base {
  * @lock:               lock protecting the base and associated clock bases
  *                      and timers
  * @clock_base:         array of clock bases for this cpu
- * @curr_timer:         the timer which is executing a callback right now
  * @expires_next:       absolute time of the next event which was scheduled
  *                      via clock_set_next_event()
  * @hres_active:        State of high resolution mode
@@ -184,43 +181,43 @@ struct hrtimer_cpu_base {
 
 static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time)
 {
-        timer->_expires = time;
+        timer->node.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);
+        timer->node.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));
+        timer->node.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->node.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->node.expires = ktime_add_safe(timer->node.expires, time);
         timer->_softexpires = ktime_add_safe(timer->_softexpires, time);
 }
 
 static inline void hrtimer_add_expires_ns(struct hrtimer *timer, u64 ns)
 {
-        timer->_expires = ktime_add_ns(timer->_expires, ns);
+        timer->node.expires = ktime_add_ns(timer->node.expires, ns);
         timer->_softexpires = ktime_add_ns(timer->_softexpires, ns);
 }
 
 static inline ktime_t hrtimer_get_expires(const struct hrtimer *timer)
 {
-        return timer->_expires;
+        return timer->node.expires;
 }
 
 static inline ktime_t hrtimer_get_softexpires(const struct hrtimer *timer)
@@ -230,7 +227,7 @@ static inline ktime_t hrtimer_get_softexpires(const struct hrtimer *timer)
 
 static inline s64 hrtimer_get_expires_tv64(const struct hrtimer *timer)
 {
-        return timer->_expires.tv64;
+        return timer->node.expires.tv64;
 }
 static inline s64 hrtimer_get_softexpires_tv64(const struct hrtimer *timer)
 {
@@ -239,12 +236,12 @@ static inline s64 hrtimer_get_softexpires_tv64(const struct hrtimer *timer)
 
 static inline s64 hrtimer_get_expires_ns(const struct hrtimer *timer)
 {
-        return ktime_to_ns(timer->_expires);
+        return ktime_to_ns(timer->node.expires);
 }
 
 static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer)
 {
-    return ktime_sub(timer->_expires, timer->base->get_time());
+        return ktime_sub(timer->node.expires, timer->base->get_time());
 }
 
 #ifdef CONFIG_HIGH_RES_TIMERS
diff --git a/include/linux/timer.h b/include/linux/timer.h
index 38cf093ef62c..6abd9138beda 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -24,9 +24,9 @@ struct timer_list {
         int slack;
 
 #ifdef CONFIG_TIMER_STATS
+        int start_pid;
         void *start_site;
         char start_comm[16];
-        int start_pid;
 #endif
 #ifdef CONFIG_LOCKDEP
         struct lockdep_map lockdep_map;
@@ -48,12 +48,38 @@ extern struct tvec_base boot_tvec_bases;
 #define __TIMER_LOCKDEP_MAP_INITIALIZER(_kn)
 #endif
 
+/*
+ * Note that all tvec_bases are 2 byte aligned and lower bit of
+ * base in timer_list is guaranteed to be zero. Use the LSB to
+ * indicate whether the timer is deferrable.
+ *
+ * A deferrable timer will work normally when the system is busy, but
+ * will not cause a CPU to come out of idle just to service it; instead,
+ * the timer will be serviced when the CPU eventually wakes up with a
+ * subsequent non-deferrable timer.
+ */
+#define TBASE_DEFERRABLE_FLAG           (0x1)
+
 #define TIMER_INITIALIZER(_function, _expires, _data) {         \
                 .entry = { .prev = TIMER_ENTRY_STATIC },        \
                 .function = (_function),                        \
                 .expires = (_expires),                          \
                 .data = (_data),                                \
                 .base = &boot_tvec_bases,                       \
+                .slack = -1,                                    \
+                __TIMER_LOCKDEP_MAP_INITIALIZER(                \
+                        __FILE__ ":" __stringify(__LINE__))     \
+        }
+
+#define TBASE_MAKE_DEFERRED(ptr) ((struct tvec_base *)          \
+                  ((unsigned char *)(ptr) + TBASE_DEFERRABLE_FLAG))
+
+#define TIMER_DEFERRED_INITIALIZER(_function, _expires, _data) {\
+                .entry = { .prev = TIMER_ENTRY_STATIC },        \
+                .function = (_function),                        \
+                .expires = (_expires),                          \
+                .data = (_data),                                \
+                .base = TBASE_MAKE_DEFERRED(&boot_tvec_bases),  \
                 __TIMER_LOCKDEP_MAP_INITIALIZER(                \
                         __FILE__ ":" __stringify(__LINE__))     \
         }
@@ -248,11 +274,11 @@ static inline void timer_stats_timer_clear_start_info(struct timer_list *timer)
 
 extern void add_timer(struct timer_list *timer);
 
+extern int try_to_del_timer_sync(struct timer_list *timer);
+
 #ifdef CONFIG_SMP
-  extern int try_to_del_timer_sync(struct timer_list *timer);
   extern int del_timer_sync(struct timer_list *timer);
 #else
-# define try_to_del_timer_sync(t)       del_timer(t)
 # define del_timer_sync(t)              del_timer(t)
 #endif
 
diff --git a/include/linux/timerqueue.h b/include/linux/timerqueue.h
new file mode 100644
index 000000000000..d24aabaca474
--- /dev/null
+++ b/include/linux/timerqueue.h
@@ -0,0 +1,50 @@
+#ifndef _LINUX_TIMERQUEUE_H
+#define _LINUX_TIMERQUEUE_H
+
+#include <linux/rbtree.h>
+#include <linux/ktime.h>
+
+
+struct timerqueue_node {
+        struct rb_node node;
+        ktime_t expires;
+};
+
+struct timerqueue_head {
+        struct rb_root head;
+        struct timerqueue_node *next;
+};
+
+
+extern void timerqueue_add(struct timerqueue_head *head,
+                                struct timerqueue_node *node);
+extern void timerqueue_del(struct timerqueue_head *head,
+                                struct timerqueue_node *node);
+extern struct timerqueue_node *timerqueue_iterate_next(
+                                                struct timerqueue_node *node);
+
+/**
+ * timerqueue_getnext - Returns the timer with the earlies expiration time
+ *
+ * @head: head of timerqueue
+ *
+ * Returns a pointer to the timer node that has the
+ * earliest expiration time.
+ */
+static inline
+struct timerqueue_node *timerqueue_getnext(struct timerqueue_head *head)
+{
+        return head->next;
+}
+
+static inline void timerqueue_init(struct timerqueue_node *node)
+{
+        RB_CLEAR_NODE(&node->node);
+}
+
+static inline void timerqueue_init_head(struct timerqueue_head *head)
+{
+        head->head = RB_ROOT;
+        head->next = NULL;
+}
+#endif /* _LINUX_TIMERQUEUE_H */
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 0c0771f06bfa..bd257fee6031 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -127,12 +127,20 @@ struct execute_work {
         .timer = TIMER_INITIALIZER(NULL, 0, 0),                 \
         }
 
+#define __DEFERRED_WORK_INITIALIZER(n, f) {                     \
+        .work = __WORK_INITIALIZER((n).work, (f)),              \
+        .timer = TIMER_DEFERRED_INITIALIZER(NULL, 0, 0),        \
+        }
+
 #define DECLARE_WORK(n, f)                                      \
         struct work_struct n = __WORK_INITIALIZER(n, f)
 
 #define DECLARE_DELAYED_WORK(n, f)                              \
         struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f)
 
+#define DECLARE_DEFERRED_WORK(n, f)                             \
+        struct delayed_work n = __DEFERRED_WORK_INITIALIZER(n, f)
+
 /*
  * initialize a work item's function pointer
  */
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 72206cf5c6cf..f2429fc3438c 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -516,10 +516,13 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 
         for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
                 struct hrtimer *timer;
+                struct timerqueue_node *next;
 
-                if (!base->first)
+                next = timerqueue_getnext(&base->active);
+                if (!next)
                         continue;
-                timer = rb_entry(base->first, struct hrtimer, node);
+                timer = container_of(next, struct hrtimer, node);
+
                 expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
                 /*
                  * clock_was_set() has changed base->offset so the
@@ -840,48 +843,17 @@ EXPORT_SYMBOL_GPL(hrtimer_forward);
 static int enqueue_hrtimer(struct hrtimer *timer,
                            struct hrtimer_clock_base *base)
 {
-        struct rb_node **link = &base->active.rb_node;
-        struct rb_node *parent = NULL;
-        struct hrtimer *entry;
-        int leftmost = 1;
-
         debug_activate(timer);
 
-        /*
-         * Find the right place in the rbtree:
-         */
-        while (*link) {
-                parent = *link;
-                entry = rb_entry(parent, struct hrtimer, node);
-                /*
-                 * We dont care about collisions. Nodes with
-                 * the same expiry time stay together.
-                 */
-                if (hrtimer_get_expires_tv64(timer) <
-                                hrtimer_get_expires_tv64(entry)) {
-                        link = &(*link)->rb_left;
-                } else {
-                        link = &(*link)->rb_right;
-                        leftmost = 0;
-                }
-        }
-
-        /*
-         * Insert the timer to the rbtree and check whether it
-         * replaces the first pending timer
-         */
-        if (leftmost)
-                base->first = &timer->node;
+        timerqueue_add(&base->active, &timer->node);
 
-        rb_link_node(&timer->node, parent, link);
-        rb_insert_color(&timer->node, &base->active);
         /*
          * HRTIMER_STATE_ENQUEUED is or'ed to the current state to preserve the
          * state of a possibly running callback.
          */
         timer->state |= HRTIMER_STATE_ENQUEUED;
 
-        return leftmost;
+        return (&timer->node == base->active.next);
 }
 
 /*
@@ -901,12 +873,7 @@ static void __remove_hrtimer(struct hrtimer *timer,
         if (!(timer->state & HRTIMER_STATE_ENQUEUED))
                 goto out;
 
-        /*
-         * Remove the timer from the rbtree and replace the first
-         * entry pointer if necessary.
-         */
-        if (base->first == &timer->node) {
-                base->first = rb_next(&timer->node);
+        if (&timer->node == timerqueue_getnext(&base->active)) {
 #ifdef CONFIG_HIGH_RES_TIMERS
                 /* Reprogram the clock event device. if enabled */
                 if (reprogram && hrtimer_hres_active()) {
@@ -919,7 +886,7 @@ static void __remove_hrtimer(struct hrtimer *timer,
                 }
 #endif
         }
-        rb_erase(&timer->node, &base->active);
+        timerqueue_del(&base->active, &timer->node);
 out:
         timer->state = newstate;
 }
@@ -1128,11 +1095,13 @@ ktime_t hrtimer_get_next_event(void)
         if (!hrtimer_hres_active()) {
                 for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
                         struct hrtimer *timer;
+                        struct timerqueue_node *next;
 
-                        if (!base->first)
+                        next = timerqueue_getnext(&base->active);
+                        if (!next)
                                 continue;
 
-                        timer = rb_entry(base->first, struct hrtimer, node);
+                        timer = container_of(next, struct hrtimer, node);
                         delta.tv64 = hrtimer_get_expires_tv64(timer);
                         delta = ktime_sub(delta, base->get_time());
                         if (delta.tv64 < mindelta.tv64)
@@ -1162,6 +1131,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 
         timer->base = &cpu_base->clock_base[clock_id];
         hrtimer_init_timer_hres(timer);
+        timerqueue_init(&timer->node);
 
 #ifdef CONFIG_TIMER_STATS
         timer->start_site = NULL;
@@ -1278,14 +1248,14 @@ retry:
 
         for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
                 ktime_t basenow;
-                struct rb_node *node;
+                struct timerqueue_node *node;
 
                 basenow = ktime_add(now, base->offset);
 
-                while ((node = base->first)) {
+                while ((node = timerqueue_getnext(&base->active))) {
                         struct hrtimer *timer;
 
-                        timer = rb_entry(node, struct hrtimer, node);
+                        timer = container_of(node, struct hrtimer, node);
 
                         /*
                          * The immediate goal for using the softexpires is
@@ -1441,7 +1411,7 @@ void hrtimer_run_pending(void)
  */
 void hrtimer_run_queues(void)
 {
-        struct rb_node *node;
+        struct timerqueue_node *node;
         struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
         struct hrtimer_clock_base *base;
         int index, gettime = 1;
@@ -1451,8 +1421,7 @@ void hrtimer_run_queues(void)
 
         for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) {
                 base = &cpu_base->clock_base[index];
-
-                if (!base->first)
+                if (!timerqueue_getnext(&base->active))
                         continue;
 
                 if (gettime) {
@@ -1462,10 +1431,10 @@ void hrtimer_run_queues(void)
 
                 raw_spin_lock(&cpu_base->lock);
 
-                while ((node = base->first)) {
+                while ((node = timerqueue_getnext(&base->active))) {
                         struct hrtimer *timer;
 
-                        timer = rb_entry(node, struct hrtimer, node);
+                        timer = container_of(node, struct hrtimer, node);
                         if (base->softirq_time.tv64 <=
                                         hrtimer_get_expires_tv64(timer))
                                 break;
@@ -1630,8 +1599,10 @@ static void __cpuinit init_hrtimers_cpu(int cpu)
 
         raw_spin_lock_init(&cpu_base->lock);
 
-        for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
+        for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
                 cpu_base->clock_base[i].cpu_base = cpu_base;
+                timerqueue_init_head(&cpu_base->clock_base[i].active);
+        }
 
         hrtimer_init_hres(cpu_base);
 }
@@ -1642,10 +1613,10 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
                                 struct hrtimer_clock_base *new_base)
 {
         struct hrtimer *timer;
-        struct rb_node *node;
+        struct timerqueue_node *node;
 
-        while ((node = rb_first(&old_base->active))) {
-                timer = rb_entry(node, struct hrtimer, node);
+        while ((node = timerqueue_getnext(&old_base->active))) {
+                timer = container_of(node, struct hrtimer, node);
                 BUG_ON(hrtimer_callback_running(timer));
                 debug_deactivate(timer);
 
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 9ca4973f736d..93bd2eb2bc53 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -145,7 +145,13 @@ static int common_timer_del(struct k_itimer *timer);
 
 static enum hrtimer_restart posix_timer_fn(struct hrtimer *data);
 
-static struct k_itimer *lock_timer(timer_t timer_id, unsigned long *flags);
+static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags);
+
+#define lock_timer(tid, flags)                                             \
+({      struct k_itimer *__timr;                                           \
+        __cond_lock(&__timr->it_lock, __timr = __lock_timer(tid, flags));  \
+        __timr;                                                            \
+})
 
 static inline void unlock_timer(struct k_itimer *timr, unsigned long flags)
 {
@@ -619,7 +625,7 @@ out:
  * the find to the timer lock.  To avoid a dead lock, the timer id MUST
  * be release with out holding the timer lock.
  */
-static struct k_itimer *lock_timer(timer_t timer_id, unsigned long *flags)
+static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags)
 {
         struct k_itimer *timr;
         /*
diff --git a/kernel/time/timecompare.c b/kernel/time/timecompare.c
index ac38fbb176cc..a9ae369925ce 100644
--- a/kernel/time/timecompare.c
+++ b/kernel/time/timecompare.c
@@ -21,6 +21,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/math64.h>
+#include <linux/kernel.h>
 
 /*
  * fixed point arithmetic scale factor for skew
@@ -57,11 +58,11 @@ int timecompare_offset(struct timecompare *sync,
         int index;
         int num_samples = sync->num_samples;
 
-        if (num_samples > sizeof(buffer)/sizeof(buffer[0])) {
+        if (num_samples > ARRAY_SIZE(buffer)) {
                 samples = kmalloc(sizeof(*samples) * num_samples, GFP_ATOMIC);
                 if (!samples) {
                         samples = buffer;
-                        num_samples = sizeof(buffer)/sizeof(buffer[0]);
+                        num_samples = ARRAY_SIZE(buffer);
                 }
         } else {
                 samples = buffer;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 49010d822f72..5bb86da82003 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -32,6 +32,8 @@ struct timekeeper {
         cycle_t cycle_interval;
         /* Number of clock shifted nano seconds in one NTP interval. */
         u64     xtime_interval;
+        /* shifted nano seconds left over when rounding cycle_interval */
+        s64     xtime_remainder;
         /* Raw nano seconds accumulated per NTP interval. */
         u32     raw_interval;
 
@@ -62,7 +64,7 @@ struct timekeeper timekeeper;
 static void timekeeper_setup_internals(struct clocksource *clock)
 {
         cycle_t interval;
-        u64 tmp;
+        u64 tmp, ntpinterval;
 
         timekeeper.clock = clock;
         clock->cycle_last = clock->read(clock);
@@ -70,6 +72,7 @@ static void timekeeper_setup_internals(struct clocksource *clock)
         /* Do the ns -> cycle conversion first, using original mult */
         tmp = NTP_INTERVAL_LENGTH;
         tmp <<= clock->shift;
+        ntpinterval = tmp;
         tmp += clock->mult/2;
         do_div(tmp, clock->mult);
         if (tmp == 0)
@@ -80,6 +83,7 @@ static void timekeeper_setup_internals(struct clocksource *clock)
 
         /* Go back from cycles -> shifted ns */
         timekeeper.xtime_interval = (u64) interval * clock->mult;
+        timekeeper.xtime_remainder = ntpinterval - timekeeper.xtime_interval;
         timekeeper.raw_interval =
                 ((u64) interval * clock->mult) >> clock->shift;
 
@@ -719,7 +723,8 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
 
         /* Accumulate error between NTP and clock interval */
         timekeeper.ntp_error += tick_length << shift;
-        timekeeper.ntp_error -= timekeeper.xtime_interval <<
+        timekeeper.ntp_error -=
+            (timekeeper.xtime_interval + timekeeper.xtime_remainder) <<
                                 (timekeeper.ntp_error_shift + shift);
 
         return offset;
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index ab8f5e33fa92..32a19f9397fc 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -79,26 +79,26 @@ print_active_timers(struct seq_file *m, struct hrtimer_clock_base *base,
 {
         struct hrtimer *timer, tmp;
         unsigned long next = 0, i;
-        struct rb_node *curr;
+        struct timerqueue_node *curr;
         unsigned long flags;
 
 next_one:
         i = 0;
         raw_spin_lock_irqsave(&base->cpu_base->lock, flags);
 
-        curr = base->first;
+        curr = timerqueue_getnext(&base->active);
         /*
          * Crude but we have to do this O(N*N) thing, because
          * we have to unlock the base when printing:
          */
         while (curr && i < next) {
-                curr = rb_next(curr);
+                curr = timerqueue_iterate_next(curr);
                 i++;
         }
 
         if (curr) {
 
-                timer = rb_entry(curr, struct hrtimer, node);
+                timer = container_of(curr, struct hrtimer, node);
                 tmp = *timer;
                 raw_spin_unlock_irqrestore(&base->cpu_base->lock, flags);
 
diff --git a/kernel/timer.c b/kernel/timer.c
index 353b9227c2ec..43ca9936f2d0 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -88,18 +88,6 @@ struct tvec_base boot_tvec_bases;
 EXPORT_SYMBOL(boot_tvec_bases);
 static DEFINE_PER_CPU(struct tvec_base *, tvec_bases) = &boot_tvec_bases;
 
-/*
- * Note that all tvec_bases are 2 byte aligned and lower bit of
- * base in timer_list is guaranteed to be zero. Use the LSB to
- * indicate whether the timer is deferrable.
- *
- * A deferrable timer will work normally when the system is busy, but
- * will not cause a CPU to come out of idle just to service it; instead,
- * the timer will be serviced when the CPU eventually wakes up with a
- * subsequent non-deferrable timer.
- */
-#define TBASE_DEFERRABLE_FLAG           (0x1)
-
 /* Functions below help us manage 'deferrable' flag */
 static inline unsigned int tbase_get_deferrable(struct tvec_base *base)
 {
@@ -113,8 +101,7 @@ static inline struct tvec_base *tbase_get_base(struct tvec_base *base)
 
 static inline void timer_set_deferrable(struct timer_list *timer)
 {
-        timer->base = ((struct tvec_base *)((unsigned long)(timer->base) |
-                                       TBASE_DEFERRABLE_FLAG));
+        timer->base = TBASE_MAKE_DEFERRED(timer->base);
 }
 
 static inline void
@@ -343,15 +330,6 @@ void set_timer_slack(struct timer_list *timer, int slack_hz)
 }
 EXPORT_SYMBOL_GPL(set_timer_slack);
 
-
-static inline void set_running_timer(struct tvec_base *base,
-                                        struct timer_list *timer)
-{
-#ifdef CONFIG_SMP
-        base->running_timer = timer;
-#endif
-}
-
 static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
 {
         unsigned long expires = timer->expires;
@@ -936,15 +914,12 @@ int del_timer(struct timer_list *timer)
 }
 EXPORT_SYMBOL(del_timer);
 
-#ifdef CONFIG_SMP
 /**
  * try_to_del_timer_sync - Try to deactivate a timer
  * @timer: timer do del
  *
  * This function tries to deactivate a timer. Upon successful (ret >= 0)
  * exit the timer is not queued and the handler is not running on any CPU.
- *
- * It must not be called from interrupt contexts.
  */
 int try_to_del_timer_sync(struct timer_list *timer)
 {
@@ -973,6 +948,7 @@ out:
 }
 EXPORT_SYMBOL(try_to_del_timer_sync);
 
+#ifdef CONFIG_SMP
 /**
  * del_timer_sync - deactivate a timer and wait for the handler to finish.
  * @timer: the timer to be deactivated
@@ -983,7 +959,7 @@ EXPORT_SYMBOL(try_to_del_timer_sync);
  *
  * Synchronization rules: Callers must prevent restarting of the timer,
  * otherwise this function is meaningless. It must not be called from
- * interrupt contexts. The caller must not hold locks which would prevent
+ * hardirq contexts. The caller must not hold locks which would prevent
  * completion of the timer's handler. The timer's handler must not call
  * add_timer_on(). Upon exit the timer is not queued and the handler is
  * not running on any CPU.
@@ -993,14 +969,16 @@ EXPORT_SYMBOL(try_to_del_timer_sync);
 int del_timer_sync(struct timer_list *timer)
 {
 #ifdef CONFIG_LOCKDEP
-        unsigned long flags;
-
-        local_irq_save(flags);
+        local_bh_disable();
         lock_map_acquire(&timer->lockdep_map);
         lock_map_release(&timer->lockdep_map);
-        local_irq_restore(flags);
+        local_bh_enable();
 #endif
-
+        /*
+         * don't use it in hardirq context, because it
+         * could lead to deadlock.
+         */
+        WARN_ON(in_irq());
         for (;;) {
                 int ret = try_to_del_timer_sync(timer);
                 if (ret >= 0)
@@ -1111,7 +1089,7 @@ static inline void __run_timers(struct tvec_base *base)
 
                         timer_stats_account_timer(timer);
 
-                        set_running_timer(base, timer);
+                        base->running_timer = timer;
                         detach_timer(timer, 1);
 
                         spin_unlock_irq(&base->lock);
@@ -1119,7 +1097,7 @@ static inline void __run_timers(struct tvec_base *base)
                         spin_lock_irq(&base->lock);
                 }
         }
-        set_running_timer(base, NULL);
+        base->running_timer = NULL;
         spin_unlock_irq(&base->lock);
 }
 
@@ -1249,7 +1227,7 @@ static unsigned long cmp_next_hrtimer_event(unsigned long now,
  */
 unsigned long get_next_timer_interrupt(unsigned long now)
 {
-        struct tvec_base *base = __get_cpu_var(tvec_bases);
+        struct tvec_base *base = __this_cpu_read(tvec_bases);
         unsigned long expires;
 
         /*
@@ -1298,7 +1276,7 @@ void update_process_times(int user_tick)
  */
 static void run_timer_softirq(struct softirq_action *h)
 {
-        struct tvec_base *base = __get_cpu_var(tvec_bases);
+        struct tvec_base *base = __this_cpu_read(tvec_bases);
 
         hrtimer_run_pending();
 
diff --git a/lib/Makefile b/lib/Makefile
index e6a3763b8212..9e2db72d128e 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -8,7 +8,7 @@ KBUILD_CFLAGS = $(subst -pg,,$(ORIG_CFLAGS))
 endif
 
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
-         rbtree.o radix-tree.o dump_stack.o \
+         rbtree.o radix-tree.o dump_stack.o timerqueue.o\
          idr.o int_sqrt.o extable.o prio_tree.o \
          sha1.o irq_regs.o reciprocal_div.o argv_split.o \
          proportions.o prio_heap.o ratelimit.o show_mem.o \
diff --git a/lib/timerqueue.c b/lib/timerqueue.c
new file mode 100644
index 000000000000..e3a1050e6820
--- /dev/null
+++ b/lib/timerqueue.c
@@ -0,0 +1,107 @@
+/*
+ *  Generic Timer-queue
+ *
+ *  Manages a simple queue of timers, ordered by expiration time.
+ *  Uses rbtrees for quick list adds and expiration.
+ *
+ *  NOTE: All of the following functions need to be serialized
+ *  to avoid races. No locking is done by this libary code.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/timerqueue.h>
+#include <linux/rbtree.h>
+#include <linux/module.h>
+
+/**
+ * timerqueue_add - Adds timer to timerqueue.
+ *
+ * @head: head of timerqueue
+ * @node: timer node to be added
+ *
+ * Adds the timer node to the timerqueue, sorted by the
+ * node's expires value.
+ */
+void timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node)
+{
+        struct rb_node **p = &head->head.rb_node;
+        struct rb_node *parent = NULL;
+        struct timerqueue_node  *ptr;
+
+        /* Make sure we don't add nodes that are already added */
+        WARN_ON_ONCE(!RB_EMPTY_NODE(&node->node));
+
+        while (*p) {
+                parent = *p;
+                ptr = rb_entry(parent, struct timerqueue_node, node);
+                if (node->expires.tv64 < ptr->expires.tv64)
+                        p = &(*p)->rb_left;
+                else
+                        p = &(*p)->rb_right;
+        }
+        rb_link_node(&node->node, parent, p);
+        rb_insert_color(&node->node, &head->head);
+
+        if (!head->next || node->expires.tv64 < head->next->expires.tv64)
+                head->next = node;
+}
+EXPORT_SYMBOL_GPL(timerqueue_add);
+
+/**
+ * timerqueue_del - Removes a timer from the timerqueue.
+ *
+ * @head: head of timerqueue
+ * @node: timer node to be removed
+ *
+ * Removes the timer node from the timerqueue.
+ */
+void timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node)
+{
+        WARN_ON_ONCE(RB_EMPTY_NODE(&node->node));
+
+        /* update next pointer */
+        if (head->next == node) {
+                struct rb_node *rbn = rb_next(&node->node);
+
+                head->next = rbn ?
+                        rb_entry(rbn, struct timerqueue_node, node) : NULL;
+        }
+        rb_erase(&node->node, &head->head);
+        RB_CLEAR_NODE(&node->node);
+}
+EXPORT_SYMBOL_GPL(timerqueue_del);
+
+/**
+ * timerqueue_iterate_next - Returns the timer after the provided timer
+ *
+ * @node: Pointer to a timer.
+ *
+ * Provides the timer that is after the given node. This is used, when
+ * necessary, to iterate through the list of timers in a timer list
+ * without modifying the list.
+ */
+struct timerqueue_node *timerqueue_iterate_next(struct timerqueue_node *node)
+{
+        struct rb_node *next;
+
+        if (!node)
+                return NULL;
+        next = rb_next(&node->node);
+        if (!next)
+                return NULL;
+        return container_of(next, struct timerqueue_node, node);
+}
+EXPORT_SYMBOL_GPL(timerqueue_iterate_next);