Merge branch 'master' into upstream

37 files changed, 4401 insertions, 931 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 14f4d45e0ae9..ac6b27abb1ad 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -47,6 +47,7 @@ obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
 obj-$(CONFIG_SECCOMP) += seccomp.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
 obj-$(CONFIG_RELAY) += relay.o
+obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
 obj-$(CONFIG_UTS_NS) += utsname.o
 obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
 obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
diff --git a/kernel/fork.c b/kernel/fork.c
index 0b6293d94d96..d154cc786489 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -858,7 +858,7 @@ static inline int copy_signal(unsigned long clone_flags, struct task_struct * ts
         init_sigpending(&sig->shared_pending);
         INIT_LIST_HEAD(&sig->posix_timers);
 
-        hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_REL);
+        hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
         sig->it_real_incr.tv64 = 0;
         sig->real_timer.function = it_real_fn;
         sig->tsk = tsk;
diff --git a/kernel/futex.c b/kernel/futex.c
index 5a737de857d3..e749e7df14b1 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1134,7 +1134,7 @@ static int futex_lock_pi(u32 __user *uaddr, int detect, unsigned long sec,
 
         if (sec != MAX_SCHEDULE_TIMEOUT) {
                 to = &timeout;
-                hrtimer_init(&to->timer, CLOCK_REALTIME, HRTIMER_ABS);
+                hrtimer_init(&to->timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
                 hrtimer_init_sleeper(to, current);
                 to->timer.expires = ktime_set(sec, nsec);
         }
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index f44e499e8fca..476cb0c0b4a4 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1,8 +1,9 @@
 /*
  *  linux/kernel/hrtimer.c
  *
- *  Copyright(C) 2005, Thomas Gleixner <tglx@linutronix.de>
- *  Copyright(C) 2005, Red Hat, Inc., Ingo Molnar
+ *  Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
+ *  Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
+ *  Copyright(C) 2006-2007  Timesys Corp., Thomas Gleixner
  *
  *  High-resolution kernel timers
  *
@@ -31,12 +32,17 @@
  */
 
 #include <linux/cpu.h>
+#include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/percpu.h>
 #include <linux/hrtimer.h>
 #include <linux/notifier.h>
 #include <linux/syscalls.h>
+#include <linux/kallsyms.h>
 #include <linux/interrupt.h>
+#include <linux/tick.h>
+#include <linux/seq_file.h>
+#include <linux/err.h>
 
 #include <asm/uaccess.h>
 
@@ -45,7 +51,7 @@
  *
  * returns the time in ktime_t format
  */
-static ktime_t ktime_get(void)
+ktime_t ktime_get(void)
 {
         struct timespec now;
 
@@ -59,7 +65,7 @@ static ktime_t ktime_get(void)
  *
  * returns the time in ktime_t format
  */
-static ktime_t ktime_get_real(void)
+ktime_t ktime_get_real(void)
 {
         struct timespec now;
 
@@ -79,21 +85,22 @@ EXPORT_SYMBOL_GPL(ktime_get_real);
  * This ensures that we capture erroneous accesses to these clock ids
  * rather than moving them into the range of valid clock id's.
  */
-
-#define MAX_HRTIMER_BASES 2
-
-static DEFINE_PER_CPU(struct hrtimer_base, hrtimer_bases[MAX_HRTIMER_BASES]) =
+DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 {
+
+        .clock_base =
         {
-                .index = CLOCK_REALTIME,
-                .get_time = &ktime_get_real,
-                .resolution = KTIME_REALTIME_RES,
-        },
-        {
-                .index = CLOCK_MONOTONIC,
-                .get_time = &ktime_get,
-                .resolution = KTIME_MONOTONIC_RES,
-        },
+                {
+                        .index = CLOCK_REALTIME,
+                        .get_time = &ktime_get_real,
+                        .resolution = KTIME_LOW_RES,
+                },
+                {
+                        .index = CLOCK_MONOTONIC,
+                        .get_time = &ktime_get,
+                        .resolution = KTIME_LOW_RES,
+                },
+        }
 };
 
 /**
@@ -125,20 +132,35 @@ EXPORT_SYMBOL_GPL(ktime_get_ts);
  * Get the coarse grained time at the softirq based on xtime and
  * wall_to_monotonic.
  */
-static void hrtimer_get_softirq_time(struct hrtimer_base *base)
+static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
 {
         ktime_t xtim, tomono;
+        struct timespec xts;
         unsigned long seq;
 
         do {
                 seq = read_seqbegin(&xtime_lock);
-                xtim = timespec_to_ktime(xtime);
-                tomono = timespec_to_ktime(wall_to_monotonic);
-
+#ifdef CONFIG_NO_HZ
+                getnstimeofday(&xts);
+#else
+                xts = xtime;
+#endif
         } while (read_seqretry(&xtime_lock, seq));
 
-        base[CLOCK_REALTIME].softirq_time = xtim;
-        base[CLOCK_MONOTONIC].softirq_time = ktime_add(xtim, tomono);
+        xtim = timespec_to_ktime(xts);
+        tomono = timespec_to_ktime(wall_to_monotonic);
+        base->clock_base[CLOCK_REALTIME].softirq_time = xtim;
+        base->clock_base[CLOCK_MONOTONIC].softirq_time =
+                ktime_add(xtim, tomono);
+}
+
+/*
+ * Helper function to check, whether the timer is running the callback
+ * function
+ */
+static inline int hrtimer_callback_running(struct hrtimer *timer)
+{
+        return timer->state & HRTIMER_STATE_CALLBACK;
 }
 
 /*
@@ -147,8 +169,6 @@ static void hrtimer_get_softirq_time(struct hrtimer_base *base)
  */
 #ifdef CONFIG_SMP
 
-#define set_curr_timer(b, t)            do { (b)->curr_timer = (t); } while (0)
-
 /*
  * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock
  * means that all timers which are tied to this base via timer->base are
@@ -161,19 +181,20 @@ static void hrtimer_get_softirq_time(struct hrtimer_base *base)
  * possible to set timer->base = NULL and drop the lock: the timer remains
  * locked.
  */
-static struct hrtimer_base *lock_hrtimer_base(const struct hrtimer *timer,
-                                              unsigned long *flags)
+static
+struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
+                                             unsigned long *flags)
 {
-        struct hrtimer_base *base;
+        struct hrtimer_clock_base *base;
 
         for (;;) {
                 base = timer->base;
                 if (likely(base != NULL)) {
-                        spin_lock_irqsave(&base->lock, *flags);
+                        spin_lock_irqsave(&base->cpu_base->lock, *flags);
                         if (likely(base == timer->base))
                                 return base;
                         /* The timer has migrated to another CPU: */
-                        spin_unlock_irqrestore(&base->lock, *flags);
+                        spin_unlock_irqrestore(&base->cpu_base->lock, *flags);
                 }
                 cpu_relax();
         }
@@ -182,12 +203,14 @@ static struct hrtimer_base *lock_hrtimer_base(const struct hrtimer *timer,
 /*
  * Switch the timer base to the current CPU when possible.
  */
-static inline struct hrtimer_base *
-switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_base *base)
+static inline struct hrtimer_clock_base *
+switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base)
 {
-        struct hrtimer_base *new_base;
+        struct hrtimer_clock_base *new_base;
+        struct hrtimer_cpu_base *new_cpu_base;
 
-        new_base = &__get_cpu_var(hrtimer_bases)[base->index];
+        new_cpu_base = &__get_cpu_var(hrtimer_bases);
+        new_base = &new_cpu_base->clock_base[base->index];
 
         if (base != new_base) {
                 /*
@@ -199,13 +222,13 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_base *base)
                  * completed. There is no conflict as we hold the lock until
                  * the timer is enqueued.
                  */
-                if (unlikely(base->curr_timer == timer))
+                if (unlikely(hrtimer_callback_running(timer)))
                         return base;
 
                 /* See the comment in lock_timer_base() */
                 timer->base = NULL;
-                spin_unlock(&base->lock);
-                spin_lock(&new_base->lock);
+                spin_unlock(&base->cpu_base->lock);
+                spin_lock(&new_base->cpu_base->lock);
                 timer->base = new_base;
         }
         return new_base;
@@ -213,19 +236,17 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_base *base)
 
 #else /* CONFIG_SMP */
 
-#define set_curr_timer(b, t)            do { } while (0)
-
-static inline struct hrtimer_base *
+static inline struct hrtimer_clock_base *
 lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
 {
-        struct hrtimer_base *base = timer->base;
+        struct hrtimer_clock_base *base = timer->base;
 
-        spin_lock_irqsave(&base->lock, *flags);
+        spin_lock_irqsave(&base->cpu_base->lock, *flags);
 
         return base;
 }
 
-#define switch_hrtimer_base(t, b)       (b)
+# define switch_hrtimer_base(t, b)      (b)
 
 #endif  /* !CONFIG_SMP */
 
@@ -256,15 +277,12 @@ ktime_t ktime_add_ns(const ktime_t kt, u64 nsec)
 
         return ktime_add(kt, tmp);
 }
-
-#else /* CONFIG_KTIME_SCALAR */
-
 # endif /* !CONFIG_KTIME_SCALAR */
 
 /*
  * Divide a ktime value by a nanosecond value
  */
-static unsigned long ktime_divns(const ktime_t kt, s64 div)
+unsigned long ktime_divns(const ktime_t kt, s64 div)
 {
         u64 dclc, inc, dns;
         int sft = 0;
@@ -281,18 +299,311 @@ static unsigned long ktime_divns(const ktime_t kt, s64 div)
 
         return (unsigned long) dclc;
 }
-
-#else /* BITS_PER_LONG < 64 */
-# define ktime_divns(kt, div)           (unsigned long)((kt).tv64 / (div))
 #endif /* BITS_PER_LONG >= 64 */
 
+/* High resolution timer related functions */
+#ifdef CONFIG_HIGH_RES_TIMERS
+
+/*
+ * High resolution timer enabled ?
+ */
+static int hrtimer_hres_enabled __read_mostly  = 1;
+
+/*
+ * Enable / Disable high resolution mode
+ */
+static int __init setup_hrtimer_hres(char *str)
+{
+        if (!strcmp(str, "off"))
+                hrtimer_hres_enabled = 0;
+        else if (!strcmp(str, "on"))
+                hrtimer_hres_enabled = 1;
+        else
+                return 0;
+        return 1;
+}
+
+__setup("highres=", setup_hrtimer_hres);
+
+/*
+ * hrtimer_high_res_enabled - query, if the highres mode is enabled
+ */
+static inline int hrtimer_is_hres_enabled(void)
+{
+        return hrtimer_hres_enabled;
+}
+
+/*
+ * Is the high resolution mode active ?
+ */
+static inline int hrtimer_hres_active(void)
+{
+        return __get_cpu_var(hrtimer_bases).hres_active;
+}
+
+/*
+ * Reprogram the event source with checking both queues for the
+ * next event
+ * Called with interrupts disabled and base->lock held
+ */
+static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base)
+{
+        int i;
+        struct hrtimer_clock_base *base = cpu_base->clock_base;
+        ktime_t expires;
+
+        cpu_base->expires_next.tv64 = KTIME_MAX;
+
+        for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
+                struct hrtimer *timer;
+
+                if (!base->first)
+                        continue;
+                timer = rb_entry(base->first, struct hrtimer, node);
+                expires = ktime_sub(timer->expires, base->offset);
+                if (expires.tv64 < cpu_base->expires_next.tv64)
+                        cpu_base->expires_next = expires;
+        }
+
+        if (cpu_base->expires_next.tv64 != KTIME_MAX)
+                tick_program_event(cpu_base->expires_next, 1);
+}
+
+/*
+ * Shared reprogramming for clock_realtime and clock_monotonic
+ *
+ * When a timer is enqueued and expires earlier than the already enqueued
+ * timers, we have to check, whether it expires earlier than the timer for
+ * which the clock event device was armed.
+ *
+ * Called with interrupts disabled and base->cpu_base.lock held
+ */
+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);
+        int res;
+
+        /*
+         * When the callback is running, we do not reprogram the clock event
+         * device. The timer callback is either running on a different CPU or
+         * the callback is executed in the hrtimer_interupt context. The
+         * reprogramming is handled either by the softirq, which called the
+         * callback or at the end of the hrtimer_interrupt.
+         */
+        if (hrtimer_callback_running(timer))
+                return 0;
+
+        if (expires.tv64 >= expires_next->tv64)
+                return 0;
+
+        /*
+         * Clockevents returns -ETIME, when the event was in the past.
+         */
+        res = tick_program_event(expires, 0);
+        if (!IS_ERR_VALUE(res))
+                *expires_next = expires;
+        return res;
+}
+
+
+/*
+ * Retrigger next event is called after clock was set
+ *
+ * Called with interrupts disabled via on_each_cpu()
+ */
+static void retrigger_next_event(void *arg)
+{
+        struct hrtimer_cpu_base *base;
+        struct timespec realtime_offset;
+        unsigned long seq;
+
+        if (!hrtimer_hres_active())
+                return;
+
+        do {
+                seq = read_seqbegin(&xtime_lock);
+                set_normalized_timespec(&realtime_offset,
+                                        -wall_to_monotonic.tv_sec,
+                                        -wall_to_monotonic.tv_nsec);
+        } while (read_seqretry(&xtime_lock, seq));
+
+        base = &__get_cpu_var(hrtimer_bases);
+
+        /* Adjust CLOCK_REALTIME offset */
+        spin_lock(&base->lock);
+        base->clock_base[CLOCK_REALTIME].offset =
+                timespec_to_ktime(realtime_offset);
+
+        hrtimer_force_reprogram(base);
+        spin_unlock(&base->lock);
+}
+
+/*
+ * Clock realtime was set
+ *
+ * Change the offset of the realtime clock vs. the monotonic
+ * clock.
+ *
+ * We might have to reprogram the high resolution timer interrupt. On
+ * SMP we call the architecture specific code to retrigger _all_ high
+ * resolution timer interrupts. On UP we just disable interrupts and
+ * call the high resolution interrupt code.
+ */
+void clock_was_set(void)
+{
+        /* Retrigger the CPU local events everywhere */
+        on_each_cpu(retrigger_next_event, NULL, 0, 1);
+}
+
+/*
+ * Check, whether the timer is on the callback pending list
+ */
+static inline int hrtimer_cb_pending(const struct hrtimer *timer)
+{
+        return timer->state & HRTIMER_STATE_PENDING;
+}
+
+/*
+ * Remove a timer from the callback pending list
+ */
+static inline void hrtimer_remove_cb_pending(struct hrtimer *timer)
+{
+        list_del_init(&timer->cb_entry);
+}
+
+/*
+ * Initialize the high resolution related parts of cpu_base
+ */
+static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base)
+{
+        base->expires_next.tv64 = KTIME_MAX;
+        base->hres_active = 0;
+        INIT_LIST_HEAD(&base->cb_pending);
+}
+
+/*
+ * Initialize the high resolution related parts of a hrtimer
+ */
+static inline void hrtimer_init_timer_hres(struct hrtimer *timer)
+{
+        INIT_LIST_HEAD(&timer->cb_entry);
+}
+
+/*
+ * When High resolution timers are active, try to reprogram. Note, that in case
+ * the state has HRTIMER_STATE_CALLBACK set, no reprogramming and no expiry
+ * check happens. The timer gets enqueued into the rbtree. The reprogramming
+ * and expiry check is done in the hrtimer_interrupt or in the softirq.
+ */
+static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
+                                            struct hrtimer_clock_base *base)
+{
+        if (base->cpu_base->hres_active && hrtimer_reprogram(timer, base)) {
+
+                /* Timer is expired, act upon the callback mode */
+                switch(timer->cb_mode) {
+                case HRTIMER_CB_IRQSAFE_NO_RESTART:
+                        /*
+                         * We can call the callback from here. No restart
+                         * happens, so no danger of recursion
+                         */
+                        BUG_ON(timer->function(timer) != HRTIMER_NORESTART);
+                        return 1;
+                case HRTIMER_CB_IRQSAFE_NO_SOFTIRQ:
+                        /*
+                         * This is solely for the sched tick emulation with
+                         * dynamic tick support to ensure that we do not
+                         * restart the tick right on the edge and end up with
+                         * the tick timer in the softirq ! The calling site
+                         * takes care of this.
+                         */
+                        return 1;
+                case HRTIMER_CB_IRQSAFE:
+                case HRTIMER_CB_SOFTIRQ:
+                        /*
+                         * Move everything else into the softirq pending list !
+                         */
+                        list_add_tail(&timer->cb_entry,
+                                      &base->cpu_base->cb_pending);
+                        timer->state = HRTIMER_STATE_PENDING;
+                        raise_softirq(HRTIMER_SOFTIRQ);
+                        return 1;
+                default:
+                        BUG();
+                }
+        }
+        return 0;
+}
+
+/*
+ * Switch to high resolution mode
+ */
+static void hrtimer_switch_to_hres(void)
+{
+        struct hrtimer_cpu_base *base = &__get_cpu_var(hrtimer_bases);
+        unsigned long flags;
+
+        if (base->hres_active)
+                return;
+
+        local_irq_save(flags);
+
+        if (tick_init_highres()) {
+                local_irq_restore(flags);
+                return;
+        }
+        base->hres_active = 1;
+        base->clock_base[CLOCK_REALTIME].resolution = KTIME_HIGH_RES;
+        base->clock_base[CLOCK_MONOTONIC].resolution = KTIME_HIGH_RES;
+
+        tick_setup_sched_timer();
+
+        /* "Retrigger" the interrupt to get things going */
+        retrigger_next_event(NULL);
+        local_irq_restore(flags);
+        printk(KERN_INFO "Switched to high resolution mode on CPU %d\n",
+               smp_processor_id());
+}
+
+#else
+
+static inline int hrtimer_hres_active(void) { return 0; }
+static inline int hrtimer_is_hres_enabled(void) { return 0; }
+static inline void hrtimer_switch_to_hres(void) { }
+static inline void hrtimer_force_reprogram(struct hrtimer_cpu_base *base) { }
+static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
+                                            struct hrtimer_clock_base *base)
+{
+        return 0;
+}
+static inline int hrtimer_cb_pending(struct hrtimer *timer) { return 0; }
+static inline void hrtimer_remove_cb_pending(struct hrtimer *timer) { }
+static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { }
+static inline void hrtimer_init_timer_hres(struct hrtimer *timer) { }
+
+#endif /* CONFIG_HIGH_RES_TIMERS */
+
+#ifdef CONFIG_TIMER_STATS
+void __timer_stats_hrtimer_set_start_info(struct hrtimer *timer, void *addr)
+{
+        if (timer->start_site)
+                return;
+
+        timer->start_site = addr;
+        memcpy(timer->start_comm, current->comm, TASK_COMM_LEN);
+        timer->start_pid = current->pid;
+}
+#endif
+
 /*
  * Counterpart to lock_timer_base above:
  */
 static inline
 void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
 {
-        spin_unlock_irqrestore(&timer->base->lock, *flags);
+        spin_unlock_irqrestore(&timer->base->cpu_base->lock, *flags);
 }
 
 /**
@@ -342,7 +653,8 @@ hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
  * The timer is inserted in expiry order. Insertion into the
  * red black tree is O(log(n)). Must hold the base lock.
  */
-static void enqueue_hrtimer(struct hrtimer *timer, struct hrtimer_base *base)
+static void enqueue_hrtimer(struct hrtimer *timer,
+                            struct hrtimer_clock_base *base, int reprogram)
 {
         struct rb_node **link = &base->active.rb_node;
         struct rb_node *parent = NULL;
@@ -368,39 +680,85 @@ static void enqueue_hrtimer(struct hrtimer *timer, struct hrtimer_base *base)
          * Insert the timer to the rbtree and check whether it
          * replaces the first pending timer
          */
-        rb_link_node(&timer->node, parent, link);
-        rb_insert_color(&timer->node, &base->active);
-
         if (!base->first || timer->expires.tv64 <
-            rb_entry(base->first, struct hrtimer, node)->expires.tv64)
+            rb_entry(base->first, struct hrtimer, node)->expires.tv64) {
+                /*
+                 * Reprogram the clock event device. When the timer is already
+                 * expired hrtimer_enqueue_reprogram has either called the
+                 * callback or added it to the pending list and raised the
+                 * softirq.
+                 *
+                 * This is a NOP for !HIGHRES
+                 */
+                if (reprogram && hrtimer_enqueue_reprogram(timer, base))
+                        return;
+
                 base->first = &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;
 }
 
 /*
  * __remove_hrtimer - internal function to remove a timer
  *
  * Caller must hold the base lock.
+ *
+ * High resolution timer mode reprograms the clock event device when the
+ * timer is the one which expires next. The caller can disable this by setting
+ * reprogram to zero. This is useful, when the context does a reprogramming
+ * anyway (e.g. timer interrupt)
  */
-static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_base *base)
+static void __remove_hrtimer(struct hrtimer *timer,
+                             struct hrtimer_clock_base *base,
+                             unsigned long newstate, int reprogram)
 {
-        /*
-         * 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);
-        rb_erase(&timer->node, &base->active);
-        rb_set_parent(&timer->node, &timer->node);
+        /* High res. callback list. NOP for !HIGHRES */
+        if (hrtimer_cb_pending(timer))
+                hrtimer_remove_cb_pending(timer);
+        else {
+                /*
+                 * 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);
+                        /* Reprogram the clock event device. if enabled */
+                        if (reprogram && hrtimer_hres_active())
+                                hrtimer_force_reprogram(base->cpu_base);
+                }
+                rb_erase(&timer->node, &base->active);
+        }
+        timer->state = newstate;
 }
 
 /*
  * remove hrtimer, called with base lock held
  */
 static inline int
-remove_hrtimer(struct hrtimer *timer, struct hrtimer_base *base)
+remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
 {
-        if (hrtimer_active(timer)) {
-                __remove_hrtimer(timer, base);
+        if (hrtimer_is_queued(timer)) {
+                int reprogram;
+
+                /*
+                 * Remove the timer and force reprogramming when high
+                 * resolution mode is active and the timer is on the current
+                 * CPU. If we remove a timer on another CPU, reprogramming is
+                 * skipped. The interrupt event on this CPU is fired and
+                 * reprogramming happens in the interrupt handler. This is a
+                 * rare case and less expensive than a smp call.
+                 */
+                timer_stats_hrtimer_clear_start_info(timer);
+                reprogram = base->cpu_base == &__get_cpu_var(hrtimer_bases);
+                __remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE,
+                                 reprogram);
                 return 1;
         }
         return 0;
@@ -419,7 +777,7 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_base *base)
 int
 hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
 {
-        struct hrtimer_base *base, *new_base;
+        struct hrtimer_clock_base *base, *new_base;
         unsigned long flags;
         int ret;
 
@@ -431,7 +789,7 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
         /* Switch the timer base, if necessary: */
         new_base = switch_hrtimer_base(timer, base);
 
-        if (mode == HRTIMER_REL) {
+        if (mode == HRTIMER_MODE_REL) {
                 tim = ktime_add(tim, new_base->get_time());
                 /*
                  * CONFIG_TIME_LOW_RES is a temporary way for architectures
@@ -446,7 +804,9 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
         }
         timer->expires = tim;
 
-        enqueue_hrtimer(timer, new_base);
+        timer_stats_hrtimer_set_start_info(timer);
+
+        enqueue_hrtimer(timer, new_base, base == new_base);
 
         unlock_hrtimer_base(timer, &flags);
 
@@ -466,13 +826,13 @@ EXPORT_SYMBOL_GPL(hrtimer_start);
  */
 int hrtimer_try_to_cancel(struct hrtimer *timer)
 {
-        struct hrtimer_base *base;
+        struct hrtimer_clock_base *base;
         unsigned long flags;
         int ret = -1;
 
         base = lock_hrtimer_base(timer, &flags);
 
-        if (base->curr_timer != timer)
+        if (!hrtimer_callback_running(timer))
                 ret = remove_hrtimer(timer, base);
 
         unlock_hrtimer_base(timer, &flags);
@@ -508,19 +868,19 @@ EXPORT_SYMBOL_GPL(hrtimer_cancel);
  */
 ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
 {
-        struct hrtimer_base *base;
+        struct hrtimer_clock_base *base;
         unsigned long flags;
         ktime_t rem;
 
         base = lock_hrtimer_base(timer, &flags);
-        rem = ktime_sub(timer->expires, timer->base->get_time());
+        rem = ktime_sub(timer->expires, base->get_time());
         unlock_hrtimer_base(timer, &flags);
 
         return rem;
 }
 EXPORT_SYMBOL_GPL(hrtimer_get_remaining);
 
-#ifdef CONFIG_NO_IDLE_HZ
+#if defined(CONFIG_NO_IDLE_HZ) || defined(CONFIG_NO_HZ)
 /**
  * hrtimer_get_next_event - get the time until next expiry event
  *
@@ -529,26 +889,31 @@ EXPORT_SYMBOL_GPL(hrtimer_get_remaining);
  */
 ktime_t hrtimer_get_next_event(void)
 {
-        struct hrtimer_base *base = __get_cpu_var(hrtimer_bases);
+        struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+        struct hrtimer_clock_base *base = cpu_base->clock_base;
         ktime_t delta, mindelta = { .tv64 = KTIME_MAX };
         unsigned long flags;
         int i;
 
-        for (i = 0; i < MAX_HRTIMER_BASES; i++, base++) {
-                struct hrtimer *timer;
+        spin_lock_irqsave(&cpu_base->lock, flags);
 
-                spin_lock_irqsave(&base->lock, flags);
-                if (!base->first) {
-                        spin_unlock_irqrestore(&base->lock, flags);
-                        continue;
+        if (!hrtimer_hres_active()) {
+                for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
+                        struct hrtimer *timer;
+
+                        if (!base->first)
+                                continue;
+
+                        timer = rb_entry(base->first, struct hrtimer, node);
+                        delta.tv64 = timer->expires.tv64;
+                        delta = ktime_sub(delta, base->get_time());
+                        if (delta.tv64 < mindelta.tv64)
+                                mindelta.tv64 = delta.tv64;
                 }
-                timer = rb_entry(base->first, struct hrtimer, node);
-                delta.tv64 = timer->expires.tv64;
-                spin_unlock_irqrestore(&base->lock, flags);
-                delta = ktime_sub(delta, base->get_time());
-                if (delta.tv64 < mindelta.tv64)
-                        mindelta.tv64 = delta.tv64;
         }
+
+        spin_unlock_irqrestore(&cpu_base->lock, flags);
+
         if (mindelta.tv64 < 0)
                 mindelta.tv64 = 0;
         return mindelta;
@@ -564,17 +929,23 @@ ktime_t hrtimer_get_next_event(void)
 void hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
                   enum hrtimer_mode mode)
 {
-        struct hrtimer_base *bases;
+        struct hrtimer_cpu_base *cpu_base;
 
         memset(timer, 0, sizeof(struct hrtimer));
 
-        bases = __raw_get_cpu_var(hrtimer_bases);
+        cpu_base = &__raw_get_cpu_var(hrtimer_bases);
 
-        if (clock_id == CLOCK_REALTIME && mode != HRTIMER_ABS)
+        if (clock_id == CLOCK_REALTIME && mode != HRTIMER_MODE_ABS)
                 clock_id = CLOCK_MONOTONIC;
 
-        timer->base = &bases[clock_id];
-        rb_set_parent(&timer->node, &timer->node);
+        timer->base = &cpu_base->clock_base[clock_id];
+        hrtimer_init_timer_hres(timer);
+
+#ifdef CONFIG_TIMER_STATS
+        timer->start_site = NULL;
+        timer->start_pid = -1;
+        memset(timer->start_comm, 0, TASK_COMM_LEN);
+#endif
 }
 EXPORT_SYMBOL_GPL(hrtimer_init);
 
@@ -588,21 +959,159 @@ EXPORT_SYMBOL_GPL(hrtimer_init);
  */
 int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
 {
-        struct hrtimer_base *bases;
+        struct hrtimer_cpu_base *cpu_base;
 
-        bases = __raw_get_cpu_var(hrtimer_bases);
-        *tp = ktime_to_timespec(bases[which_clock].resolution);
+        cpu_base = &__raw_get_cpu_var(hrtimer_bases);
+        *tp = ktime_to_timespec(cpu_base->clock_base[which_clock].resolution);
 
         return 0;
 }
 EXPORT_SYMBOL_GPL(hrtimer_get_res);
 
+#ifdef CONFIG_HIGH_RES_TIMERS
+
+/*
+ * High resolution timer interrupt
+ * Called with interrupts disabled
+ */
+void hrtimer_interrupt(struct clock_event_device *dev)
+{
+        struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+        struct hrtimer_clock_base *base;
+        ktime_t expires_next, now;
+        int i, raise = 0;
+
+        BUG_ON(!cpu_base->hres_active);
+        cpu_base->nr_events++;
+        dev->next_event.tv64 = KTIME_MAX;
+
+ retry:
+        now = ktime_get();
+
+        expires_next.tv64 = KTIME_MAX;
+
+        base = cpu_base->clock_base;
+
+        for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
+                ktime_t basenow;
+                struct rb_node *node;
+
+                spin_lock(&cpu_base->lock);
+
+                basenow = ktime_add(now, base->offset);
+
+                while ((node = base->first)) {
+                        struct hrtimer *timer;
+
+                        timer = rb_entry(node, struct hrtimer, node);
+
+                        if (basenow.tv64 < timer->expires.tv64) {
+                                ktime_t expires;
+
+                                expires = ktime_sub(timer->expires,
+                                                    base->offset);
+                                if (expires.tv64 < expires_next.tv64)
+                                        expires_next = expires;
+                                break;
+                        }
+
+                        /* Move softirq callbacks to the pending list */
+                        if (timer->cb_mode == HRTIMER_CB_SOFTIRQ) {
+                                __remove_hrtimer(timer, base,
+                                                 HRTIMER_STATE_PENDING, 0);
+                                list_add_tail(&timer->cb_entry,
+                                              &base->cpu_base->cb_pending);
+                                raise = 1;
+                                continue;
+                        }
+
+                        __remove_hrtimer(timer, base,
+                                         HRTIMER_STATE_CALLBACK, 0);
+                        timer_stats_account_hrtimer(timer);
+
+                        /*
+                         * Note: We clear the CALLBACK bit after
+                         * enqueue_hrtimer to avoid reprogramming of
+                         * the event hardware. This happens at the end
+                         * of this function anyway.
+                         */
+                        if (timer->function(timer) != HRTIMER_NORESTART) {
+                                BUG_ON(timer->state != HRTIMER_STATE_CALLBACK);
+                                enqueue_hrtimer(timer, base, 0);
+                        }
+                        timer->state &= ~HRTIMER_STATE_CALLBACK;
+                }
+                spin_unlock(&cpu_base->lock);
+                base++;
+        }
+
+        cpu_base->expires_next = expires_next;
+
+        /* Reprogramming necessary ? */
+        if (expires_next.tv64 != KTIME_MAX) {
+                if (tick_program_event(expires_next, 0))
+                        goto retry;
+        }
+
+        /* Raise softirq ? */
+        if (raise)
+                raise_softirq(HRTIMER_SOFTIRQ);
+}
+
+static void run_hrtimer_softirq(struct softirq_action *h)
+{
+        struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+
+        spin_lock_irq(&cpu_base->lock);
+
+        while (!list_empty(&cpu_base->cb_pending)) {
+                enum hrtimer_restart (*fn)(struct hrtimer *);
+                struct hrtimer *timer;
+                int restart;
+
+                timer = list_entry(cpu_base->cb_pending.next,
+                                   struct hrtimer, cb_entry);
+
+                timer_stats_account_hrtimer(timer);
+
+                fn = timer->function;
+                __remove_hrtimer(timer, timer->base, HRTIMER_STATE_CALLBACK, 0);
+                spin_unlock_irq(&cpu_base->lock);
+
+                restart = fn(timer);
+
+                spin_lock_irq(&cpu_base->lock);
+
+                timer->state &= ~HRTIMER_STATE_CALLBACK;
+                if (restart == HRTIMER_RESTART) {
+                        BUG_ON(hrtimer_active(timer));
+                        /*
+                         * Enqueue the timer, allow reprogramming of the event
+                         * device
+                         */
+                        enqueue_hrtimer(timer, timer->base, 1);
+                } else if (hrtimer_active(timer)) {
+                        /*
+                         * If the timer was rearmed on another CPU, reprogram
+                         * the event device.
+                         */
+                        if (timer->base->first == &timer->node)
+                                hrtimer_reprogram(timer, timer->base);
+                }
+        }
+        spin_unlock_irq(&cpu_base->lock);
+}
+
+#endif  /* CONFIG_HIGH_RES_TIMERS */
+
 /*
  * Expire the per base hrtimer-queue:
  */
-static inline void run_hrtimer_queue(struct hrtimer_base *base)
+static inline void run_hrtimer_queue(struct hrtimer_cpu_base *cpu_base,
+                                     int index)
 {
         struct rb_node *node;
+        struct hrtimer_clock_base *base = &cpu_base->clock_base[index];
 
         if (!base->first)
                 return;
@@ -610,53 +1119,72 @@ static inline void run_hrtimer_queue(struct hrtimer_base *base)
         if (base->get_softirq_time)
                 base->softirq_time = base->get_softirq_time();
 
-        spin_lock_irq(&base->lock);
+        spin_lock_irq(&cpu_base->lock);
 
         while ((node = base->first)) {
                 struct hrtimer *timer;
-                int (*fn)(struct hrtimer *);
+                enum hrtimer_restart (*fn)(struct hrtimer *);
                 int restart;
 
                 timer = rb_entry(node, struct hrtimer, node);
                 if (base->softirq_time.tv64 <= timer->expires.tv64)
                         break;
 
+                timer_stats_account_hrtimer(timer);
+
                 fn = timer->function;
-                set_curr_timer(base, timer);
-                __remove_hrtimer(timer, base);
-                spin_unlock_irq(&base->lock);
+                __remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0);
+                spin_unlock_irq(&cpu_base->lock);
 
                 restart = fn(timer);
 
-                spin_lock_irq(&base->lock);
+                spin_lock_irq(&cpu_base->lock);
 
+                timer->state &= ~HRTIMER_STATE_CALLBACK;
                 if (restart != HRTIMER_NORESTART) {
                         BUG_ON(hrtimer_active(timer));
-                        enqueue_hrtimer(timer, base);
+                        enqueue_hrtimer(timer, base, 0);
                 }
         }
-        set_curr_timer(base, NULL);
-        spin_unlock_irq(&base->lock);
+        spin_unlock_irq(&cpu_base->lock);
 }
 
 /*
  * Called from timer softirq every jiffy, expire hrtimers:
+ *
+ * For HRT its the fall back code to run the softirq in the timer
+ * softirq context in case the hrtimer initialization failed or has
+ * not been done yet.
  */
 void hrtimer_run_queues(void)
 {
-        struct hrtimer_base *base = __get_cpu_var(hrtimer_bases);
+        struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
         int i;
 
-        hrtimer_get_softirq_time(base);
+        if (hrtimer_hres_active())
+                return;
+
+        /*
+         * This _is_ ugly: We have to check in the softirq context,
+         * whether we can switch to highres and / or nohz mode. The
+         * clocksource switch happens in the timer interrupt with
+         * xtime_lock held. Notification from there only sets the
+         * check bit in the tick_oneshot code, otherwise we might
+         * deadlock vs. xtime_lock.
+         */
+        if (tick_check_oneshot_change(!hrtimer_is_hres_enabled()))
+                hrtimer_switch_to_hres();
 
-        for (i = 0; i < MAX_HRTIMER_BASES; i++)
-                run_hrtimer_queue(&base[i]);
+        hrtimer_get_softirq_time(cpu_base);
+
+        for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
+                run_hrtimer_queue(cpu_base, i);
 }
 
 /*
  * Sleep related functions:
  */
-static int hrtimer_wakeup(struct hrtimer *timer)
+static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer)
 {
         struct hrtimer_sleeper *t =
                 container_of(timer, struct hrtimer_sleeper, timer);
@@ -673,6 +1201,9 @@ void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task)
 {
         sl->timer.function = hrtimer_wakeup;
         sl->task = task;
+#ifdef CONFIG_HIGH_RES_TIMERS
+        sl->timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_RESTART;
+#endif
 }
 
 static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode)
@@ -683,10 +1214,11 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod
                 set_current_state(TASK_INTERRUPTIBLE);
                 hrtimer_start(&t->timer, t->timer.expires, mode);
 
-                schedule();
+                if (likely(t->task))
+                        schedule();
 
                 hrtimer_cancel(&t->timer);
-                mode = HRTIMER_ABS;
+                mode = HRTIMER_MODE_ABS;
 
         } while (t->task && !signal_pending(current));
 
@@ -702,10 +1234,10 @@ long __sched hrtimer_nanosleep_restart(struct restart_block *restart)
 
         restart->fn = do_no_restart_syscall;
 
-        hrtimer_init(&t.timer, restart->arg0, HRTIMER_ABS);
+        hrtimer_init(&t.timer, restart->arg0, HRTIMER_MODE_ABS);
         t.timer.expires.tv64 = ((u64)restart->arg3 << 32) | (u64) restart->arg2;
 
-        if (do_nanosleep(&t, HRTIMER_ABS))
+        if (do_nanosleep(&t, HRTIMER_MODE_ABS))
                 return 0;
 
         rmtp = (struct timespec __user *) restart->arg1;
@@ -738,7 +1270,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
                 return 0;
 
         /* Absolute timers do not update the rmtp value and restart: */
-        if (mode == HRTIMER_ABS)
+        if (mode == HRTIMER_MODE_ABS)
                 return -ERESTARTNOHAND;
 
         if (rmtp) {
@@ -771,7 +1303,7 @@ sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp)
         if (!timespec_valid(&tu))
                 return -EINVAL;
 
-        return hrtimer_nanosleep(&tu, rmtp, HRTIMER_REL, CLOCK_MONOTONIC);
+        return hrtimer_nanosleep(&tu, rmtp, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
 }
 
 /*
@@ -779,56 +1311,60 @@ sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp)
  */
 static void __devinit init_hrtimers_cpu(int cpu)
 {
-        struct hrtimer_base *base = per_cpu(hrtimer_bases, cpu);
+        struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
         int i;
 
-        for (i = 0; i < MAX_HRTIMER_BASES; i++, base++) {
-                spin_lock_init(&base->lock);
-                lockdep_set_class(&base->lock, &base->lock_key);
-        }
+        spin_lock_init(&cpu_base->lock);
+        lockdep_set_class(&cpu_base->lock, &cpu_base->lock_key);
+
+        for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
+                cpu_base->clock_base[i].cpu_base = cpu_base;
+
+        hrtimer_init_hres(cpu_base);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
 
-static void migrate_hrtimer_list(struct hrtimer_base *old_base,
-                                struct hrtimer_base *new_base)
+static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
+                                struct hrtimer_clock_base *new_base)
 {
         struct hrtimer *timer;
         struct rb_node *node;
 
         while ((node = rb_first(&old_base->active))) {
                 timer = rb_entry(node, struct hrtimer, node);
-                __remove_hrtimer(timer, old_base);
+                BUG_ON(hrtimer_callback_running(timer));
+                __remove_hrtimer(timer, old_base, HRTIMER_STATE_INACTIVE, 0);
                 timer->base = new_base;
-                enqueue_hrtimer(timer, new_base);
+                /*
+                 * Enqueue the timer. Allow reprogramming of the event device
+                 */
+                enqueue_hrtimer(timer, new_base, 1);
         }
 }
 
 static void migrate_hrtimers(int cpu)
 {
-        struct hrtimer_base *old_base, *new_base;
+        struct hrtimer_cpu_base *old_base, *new_base;
         int i;
 
         BUG_ON(cpu_online(cpu));
-        old_base = per_cpu(hrtimer_bases, cpu);
-        new_base = get_cpu_var(hrtimer_bases);
-
-        local_irq_disable();
+        old_base = &per_cpu(hrtimer_bases, cpu);
+        new_base = &get_cpu_var(hrtimer_bases);
 
-        for (i = 0; i < MAX_HRTIMER_BASES; i++) {
+        tick_cancel_sched_timer(cpu);
 
-                spin_lock(&new_base->lock);
-                spin_lock(&old_base->lock);
-
-                BUG_ON(old_base->curr_timer);
+        local_irq_disable();
 
-                migrate_hrtimer_list(old_base, new_base);
+        spin_lock(&new_base->lock);
+        spin_lock(&old_base->lock);
 
-                spin_unlock(&old_base->lock);
-                spin_unlock(&new_base->lock);
-                old_base++;
-                new_base++;
+        for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
+                migrate_hrtimer_list(&old_base->clock_base[i],
+                                     &new_base->clock_base[i]);
         }
+        spin_unlock(&old_base->lock);
+        spin_unlock(&new_base->lock);
 
         local_irq_enable();
         put_cpu_var(hrtimer_bases);
@@ -848,6 +1384,7 @@ static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self,
 
 #ifdef CONFIG_HOTPLUG_CPU
         case CPU_DEAD:
+                clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &cpu);
                 migrate_hrtimers(cpu);
                 break;
 #endif
@@ -868,5 +1405,8 @@ void __init hrtimers_init(void)
         hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
                           (void *)(long)smp_processor_id());
         register_cpu_notifier(&hrtimers_nb);
+#ifdef CONFIG_HIGH_RES_TIMERS
+        open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq, NULL);
+#endif
 }
 
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 475e8a71bcdc..0133f4f9e9f0 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -168,7 +168,7 @@ EXPORT_SYMBOL(set_irq_data);
 /**
  *      set_irq_data - set irq type data for an irq
  *      @irq:   Interrupt number
- *      @data:  Pointer to interrupt specific data
+ *      @entry: Pointer to MSI descriptor data
  *
  *      Set the hardware irq controller data for an irq
  */
@@ -230,10 +230,6 @@ static void default_enable(unsigned int irq)
  */
 static void default_disable(unsigned int irq)
 {
-        struct irq_desc *desc = irq_desc + irq;
-
-        if (!(desc->status & IRQ_DELAYED_DISABLE))
-                desc->chip->mask(irq);
 }
 
 /*
@@ -298,13 +294,18 @@ handle_simple_irq(unsigned int irq, struct irq_desc *desc)
 
         if (unlikely(desc->status & IRQ_INPROGRESS))
                 goto out_unlock;
-        desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
         kstat_cpu(cpu).irqs[irq]++;
 
         action = desc->action;
-        if (unlikely(!action || (desc->status & IRQ_DISABLED)))
+        if (unlikely(!action || (desc->status & IRQ_DISABLED))) {
+                if (desc->chip->mask)
+                        desc->chip->mask(irq);
+                desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
+                desc->status |= IRQ_PENDING;
                 goto out_unlock;
+        }
 
+        desc->status &= ~(IRQ_REPLAY | IRQ_WAITING | IRQ_PENDING);
         desc->status |= IRQ_INPROGRESS;
         spin_unlock(&desc->lock);
 
@@ -396,11 +397,13 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 
         /*
          * If its disabled or no action available
-         * keep it masked and get out of here
+         * then mask it and get out of here:
          */
         action = desc->action;
         if (unlikely(!action || (desc->status & IRQ_DISABLED))) {
                 desc->status |= IRQ_PENDING;
+                if (desc->chip->mask)
+                        desc->chip->mask(irq);
                 goto out;
         }
 
@@ -562,10 +565,8 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 
         /* Uninstall? */
         if (handle == handle_bad_irq) {
-                if (desc->chip != &no_irq_chip) {
-                        desc->chip->mask(irq);
-                        desc->chip->ack(irq);
-                }
+                if (desc->chip != &no_irq_chip)
+                        mask_ack_irq(desc, irq);
                 desc->status |= IRQ_DISABLED;
                 desc->depth = 1;
         }
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 7c85d69188ef..5597c157442a 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -38,6 +38,46 @@ void synchronize_irq(unsigned int irq)
 }
 EXPORT_SYMBOL(synchronize_irq);
 
+/**
+ *      irq_can_set_affinity - Check if the affinity of a given irq can be set
+ *      @irq:           Interrupt to check
+ *
+ */
+int irq_can_set_affinity(unsigned int irq)
+{
+        struct irq_desc *desc = irq_desc + irq;
+
+        if (CHECK_IRQ_PER_CPU(desc->status) || !desc->chip ||
+            !desc->chip->set_affinity)
+                return 0;
+
+        return 1;
+}
+
+/**
+ *      irq_set_affinity - Set the irq affinity of a given irq
+ *      @irq:           Interrupt to set affinity
+ *      @cpumask:       cpumask
+ *
+ */
+int irq_set_affinity(unsigned int irq, cpumask_t cpumask)
+{
+        struct irq_desc *desc = irq_desc + irq;
+
+        if (!desc->chip->set_affinity)
+                return -EINVAL;
+
+        set_balance_irq_affinity(irq, cpumask);
+
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+        set_pending_irq(irq, cpumask);
+#else
+        desc->affinity = cpumask;
+        desc->chip->set_affinity(irq, cpumask);
+#endif
+        return 0;
+}
+
 #endif
 
 /**
@@ -281,6 +321,10 @@ int setup_irq(unsigned int irq, struct irqaction *new)
         if (new->flags & IRQF_PERCPU)
                 desc->status |= IRQ_PER_CPU;
 #endif
+        /* Exclude IRQ from balancing */
+        if (new->flags & IRQF_NOBALANCING)
+                desc->status |= IRQ_NO_BALANCING;
+
         if (!shared) {
                 irq_chip_set_defaults(desc->chip);
 
@@ -461,7 +505,7 @@ int request_irq(unsigned int irq, irq_handler_t handler,
         /*
          * Lockdep wants atomic interrupt handlers:
          */
-        irqflags |= SA_INTERRUPT;
+        irqflags |= IRQF_DISABLED;
 #endif
         /*
          * Sanity-check: shared interrupts must pass in a real dev-ID,
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 6d3be06e8ce6..2db91eb54ad8 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -16,26 +16,6 @@ static struct proc_dir_entry *root_irq_dir;
 
 #ifdef CONFIG_SMP
 
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-void proc_set_irq_affinity(unsigned int irq, cpumask_t mask_val)
-{
-        set_balance_irq_affinity(irq, mask_val);
-
-        /*
-         * Save these away for later use. Re-progam when the
-         * interrupt is pending
-         */
-        set_pending_irq(irq, mask_val);
-}
-#else
-void proc_set_irq_affinity(unsigned int irq, cpumask_t mask_val)
-{
-        set_balance_irq_affinity(irq, mask_val);
-        irq_desc[irq].affinity = mask_val;
-        irq_desc[irq].chip->set_affinity(irq, mask_val);
-}
-#endif
-
 static int irq_affinity_read_proc(char *page, char **start, off_t off,
                                   int count, int *eof, void *data)
 {
@@ -55,7 +35,7 @@ static int irq_affinity_write_proc(struct file *file, const char __user *buffer,
         cpumask_t new_value, tmp;
 
         if (!irq_desc[irq].chip->set_affinity || no_irq_affinity ||
-                                CHECK_IRQ_PER_CPU(irq_desc[irq].status))
+            irq_balancing_disabled(irq))
                 return -EIO;
 
         err = cpumask_parse_user(buffer, count, new_value);
@@ -73,7 +53,7 @@ static int irq_affinity_write_proc(struct file *file, const char __user *buffer,
                    code to set default SMP affinity. */
                 return select_smp_affinity(irq) ? -EINVAL : full_count;
 
-        proc_set_irq_affinity(irq, new_value);
+        irq_set_affinity(irq, new_value);
 
         return full_count;
 }
diff --git a/kernel/itimer.c b/kernel/itimer.c
index 204ed7939e75..307c6a632ef6 100644
--- a/kernel/itimer.c
+++ b/kernel/itimer.c
@@ -128,18 +128,13 @@ asmlinkage long sys_getitimer(int which, struct itimerval __user *value)
 /*
  * The timer is automagically restarted, when interval != 0
  */
-int it_real_fn(struct hrtimer *timer)
+enum hrtimer_restart it_real_fn(struct hrtimer *timer)
 {
         struct signal_struct *sig =
             container_of(timer, struct signal_struct, real_timer);
 
         send_group_sig_info(SIGALRM, SEND_SIG_PRIV, sig->tsk);
 
-        if (sig->it_real_incr.tv64 != 0) {
-                hrtimer_forward(timer, timer->base->softirq_time,
-                                sig->it_real_incr);
-                return HRTIMER_RESTART;
-        }
         return HRTIMER_NORESTART;
 }
 
@@ -231,11 +226,14 @@ again:
                         spin_unlock_irq(&tsk->sighand->siglock);
                         goto again;
                 }
-                tsk->signal->it_real_incr =
-                        timeval_to_ktime(value->it_interval);
                 expires = timeval_to_ktime(value->it_value);
-                if (expires.tv64 != 0)
-                        hrtimer_start(timer, expires, HRTIMER_REL);
+                if (expires.tv64 != 0) {
+                        tsk->signal->it_real_incr =
+                                timeval_to_ktime(value->it_interval);
+                        hrtimer_start(timer, expires, HRTIMER_MODE_REL);
+                } else
+                        tsk->signal->it_real_incr.tv64 = 0;
+
                 spin_unlock_irq(&tsk->sighand->siglock);
                 break;
         case ITIMER_VIRTUAL:
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 3a7379aa31ca..796276141e51 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -217,7 +217,10 @@ static int wait_for_helper(void *data)
                         sub_info->retval = ret;
         }
 
-        complete(sub_info->complete);
+        if (sub_info->wait < 0)
+                kfree(sub_info);
+        else
+                complete(sub_info->complete);
         return 0;
 }
 
@@ -239,6 +242,9 @@ static void __call_usermodehelper(struct work_struct *work)
                 pid = kernel_thread(____call_usermodehelper, sub_info,
                                     CLONE_VFORK | SIGCHLD);
 
+        if (wait < 0)
+                return;
+
         if (pid < 0) {
                 sub_info->retval = pid;
                 complete(sub_info->complete);
@@ -253,6 +259,9 @@ static void __call_usermodehelper(struct work_struct *work)
  * @envp: null-terminated environment list
  * @session_keyring: session keyring for process (NULL for an empty keyring)
  * @wait: wait for the application to finish and return status.
+ *        when -1 don't wait at all, but you get no useful error back when
+ *        the program couldn't be exec'ed. This makes it safe to call
+ *        from interrupt context.
  *
  * Runs a user-space application.  The application is started
  * asynchronously if wait is not set, and runs as a child of keventd.
@@ -265,17 +274,8 @@ int call_usermodehelper_keys(char *path, char **argv, char **envp,
                              struct key *session_keyring, int wait)
 {
         DECLARE_COMPLETION_ONSTACK(done);
-        struct subprocess_info sub_info = {
-                .work           = __WORK_INITIALIZER(sub_info.work,
-                                                     __call_usermodehelper),
-                .complete       = &done,
-                .path           = path,
-                .argv           = argv,
-                .envp           = envp,
-                .ring           = session_keyring,
-                .wait           = wait,
-                .retval         = 0,
-        };
+        struct subprocess_info *sub_info;
+        int retval;
 
         if (!khelper_wq)
                 return -EBUSY;
@@ -283,9 +283,25 @@ int call_usermodehelper_keys(char *path, char **argv, char **envp,
         if (path[0] == '\0')
                 return 0;
 
-        queue_work(khelper_wq, &sub_info.work);
+        sub_info = kzalloc(sizeof(struct subprocess_info),  GFP_ATOMIC);
+        if (!sub_info)
+                return -ENOMEM;
+
+        INIT_WORK(&sub_info->work, __call_usermodehelper);
+        sub_info->complete = &done;
+        sub_info->path = path;
+        sub_info->argv = argv;
+        sub_info->envp = envp;
+        sub_info->ring = session_keyring;
+        sub_info->wait = wait;
+
+        queue_work(khelper_wq, &sub_info->work);
+        if (wait < 0) /* task has freed sub_info */
+                return 0;
         wait_for_completion(&done);
-        return sub_info.retval;
+        retval = sub_info->retval;
+        kfree(sub_info);
+        return retval;
 }
 EXPORT_SYMBOL(call_usermodehelper_keys);
 
diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c
index 88fc611b3ae9..58f35e586ee3 100644
--- a/kernel/lockdep_proc.c
+++ b/kernel/lockdep_proc.c
@@ -10,7 +10,6 @@
  * Code for /proc/lockdep and /proc/lockdep_stats:
  *
  */
-#include <linux/sched.h>
 #include <linux/module.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
diff --git a/kernel/mutex-debug.c b/kernel/mutex-debug.c
index 841539d72c55..d17436cdea1b 100644
--- a/kernel/mutex-debug.c
+++ b/kernel/mutex-debug.c
@@ -13,7 +13,6 @@
  *  Released under the General Public License (GPL).
  */
 #include <linux/mutex.h>
-#include <linux/sched.h>
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/poison.h>
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 7c3e1e6dfb5b..657f77697415 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -304,7 +304,7 @@ int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
                  * should be able to see it.
                  */
                 struct task_struct *p;
-                read_lock(&tasklist_lock);
+                rcu_read_lock();
                 p = find_task_by_pid(pid);
                 if (p) {
                         if (CPUCLOCK_PERTHREAD(which_clock)) {
@@ -312,12 +312,17 @@ int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
                                         error = cpu_clock_sample(which_clock,
                                                                  p, &rtn);
                                 }
-                        } else if (p->tgid == pid && p->signal) {
-                                error = cpu_clock_sample_group(which_clock,
-                                                               p, &rtn);
+                        } else {
+                                read_lock(&tasklist_lock);
+                                if (p->tgid == pid && p->signal) {
+                                        error =
+                                            cpu_clock_sample_group(which_clock,
+                                                                   p, &rtn);
+                                }
+                                read_unlock(&tasklist_lock);
                         }
                 }
-                read_unlock(&tasklist_lock);
+                rcu_read_unlock();
         }
 
         if (error)
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index a1bf61617839..44318ca71978 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -145,7 +145,7 @@ static int common_timer_set(struct k_itimer *, int,
                             struct itimerspec *, struct itimerspec *);
 static int common_timer_del(struct k_itimer *timer);
 
-static int posix_timer_fn(struct hrtimer *data);
+static enum hrtimer_restart posix_timer_fn(struct hrtimer *data);
 
 static struct k_itimer *lock_timer(timer_t timer_id, unsigned long *flags);
 
@@ -334,12 +334,12 @@ EXPORT_SYMBOL_GPL(posix_timer_event);
 
  * This code is for CLOCK_REALTIME* and CLOCK_MONOTONIC* timers.
  */
-static int posix_timer_fn(struct hrtimer *timer)
+static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
 {
         struct k_itimer *timr;
         unsigned long flags;
         int si_private = 0;
-        int ret = HRTIMER_NORESTART;
+        enum hrtimer_restart ret = HRTIMER_NORESTART;
 
         timr = container_of(timer, struct k_itimer, it.real.timer);
         spin_lock_irqsave(&timr->it_lock, flags);
@@ -356,7 +356,7 @@ static int posix_timer_fn(struct hrtimer *timer)
                 if (timr->it.real.interval.tv64 != 0) {
                         timr->it_overrun +=
                                 hrtimer_forward(timer,
-                                                timer->base->softirq_time,
+                                                hrtimer_cb_get_time(timer),
                                                 timr->it.real.interval);
                         ret = HRTIMER_RESTART;
                         ++timr->it_requeue_pending;
@@ -722,7 +722,7 @@ common_timer_set(struct k_itimer *timr, int flags,
         if (!new_setting->it_value.tv_sec && !new_setting->it_value.tv_nsec)
                 return 0;
 
-        mode = flags & TIMER_ABSTIME ? HRTIMER_ABS : HRTIMER_REL;
+        mode = flags & TIMER_ABSTIME ? HRTIMER_MODE_ABS : HRTIMER_MODE_REL;
         hrtimer_init(&timr->it.real.timer, timr->it_clock, mode);
         timr->it.real.timer.function = posix_timer_fn;
 
@@ -734,7 +734,7 @@ common_timer_set(struct k_itimer *timr, int flags,
         /* SIGEV_NONE timers are not queued ! See common_timer_get */
         if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) {
                 /* Setup correct expiry time for relative timers */
-                if (mode == HRTIMER_REL)
+                if (mode == HRTIMER_MODE_REL)
                         timer->expires = ktime_add(timer->expires,
                                                    timer->base->get_time());
                 return 0;
@@ -950,7 +950,8 @@ static int common_nsleep(const clockid_t which_clock, int flags,
                          struct timespec *tsave, struct timespec __user *rmtp)
 {
         return hrtimer_nanosleep(tsave, rmtp, flags & TIMER_ABSTIME ?
-                                 HRTIMER_ABS : HRTIMER_REL, which_clock);
+                                 HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
+                                 which_clock);
 }
 
 asmlinkage long
diff --git a/kernel/resource.c b/kernel/resource.c
index 2a3f88636580..bdb55a33f969 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -8,7 +8,6 @@
  */
 
 #include <linux/module.h>
-#include <linux/sched.h>
 #include <linux/errno.h>
 #include <linux/ioport.h>
 #include <linux/init.h>
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index 4ab17da46fd8..180978cb2f75 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -625,7 +625,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
         /* Setup the timer, when timeout != NULL */
         if (unlikely(timeout))
                 hrtimer_start(&timeout->timer, timeout->timer.expires,
-                              HRTIMER_ABS);
+                              HRTIMER_MODE_ABS);
 
         for (;;) {
                 /* Try to acquire the lock: */
diff --git a/kernel/sched.c b/kernel/sched.c
index 08f86178aa34..0dc757246d89 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1853,6 +1853,13 @@ context_switch(struct rq *rq, struct task_struct *prev,
         struct mm_struct *mm = next->mm;
         struct mm_struct *oldmm = prev->active_mm;
 
+        /*
+         * For paravirt, this is coupled with an exit in switch_to to
+         * combine the page table reload and the switch backend into
+         * one hypercall.
+         */
+        arch_enter_lazy_cpu_mode();
+
         if (!mm) {
                 next->active_mm = oldmm;
                 atomic_inc(&oldmm->mm_count);
diff --git a/kernel/signal.c b/kernel/signal.c
index 8072e568bbe0..e2a7d4bf7d57 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -456,26 +456,50 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask,
 int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
 {
         int signr = __dequeue_signal(&tsk->pending, mask, info);
-        if (!signr)
+        if (!signr) {
                 signr = __dequeue_signal(&tsk->signal->shared_pending,
                                          mask, info);
+                /*
+                 * itimer signal ?
+                 *
+                 * itimers are process shared and we restart periodic
+                 * itimers in the signal delivery path to prevent DoS
+                 * attacks in the high resolution timer case. This is
+                 * compliant with the old way of self restarting
+                 * itimers, as the SIGALRM is a legacy signal and only
+                 * queued once. Changing the restart behaviour to
+                 * restart the timer in the signal dequeue path is
+                 * reducing the timer noise on heavy loaded !highres
+                 * systems too.
+                 */
+                if (unlikely(signr == SIGALRM)) {
+                        struct hrtimer *tmr = &tsk->signal->real_timer;
+
+                        if (!hrtimer_is_queued(tmr) &&
+                            tsk->signal->it_real_incr.tv64 != 0) {
+                                hrtimer_forward(tmr, tmr->base->get_time(),
+                                                tsk->signal->it_real_incr);
+                                hrtimer_restart(tmr);
+                        }
+                }
+        }
         recalc_sigpending_tsk(tsk);
-        if (signr && unlikely(sig_kernel_stop(signr))) {
-                /*
-                 * Set a marker that we have dequeued a stop signal.  Our
-                 * caller might release the siglock and then the pending
-                 * stop signal it is about to process is no longer in the
-                 * pending bitmasks, but must still be cleared by a SIGCONT
-                 * (and overruled by a SIGKILL).  So those cases clear this
-                 * shared flag after we've set it.  Note that this flag may
-                 * remain set after the signal we return is ignored or
-                 * handled.  That doesn't matter because its only purpose
-                 * is to alert stop-signal processing code when another
-                 * processor has come along and cleared the flag.
-                 */
-                if (!(tsk->signal->flags & SIGNAL_GROUP_EXIT))
-                        tsk->signal->flags |= SIGNAL_STOP_DEQUEUED;
-        }
+        if (signr && unlikely(sig_kernel_stop(signr))) {
+                /*
+                 * Set a marker that we have dequeued a stop signal.  Our
+                 * caller might release the siglock and then the pending
+                 * stop signal it is about to process is no longer in the
+                 * pending bitmasks, but must still be cleared by a SIGCONT
+                 * (and overruled by a SIGKILL).  So those cases clear this
+                 * shared flag after we've set it.  Note that this flag may
+                 * remain set after the signal we return is ignored or
+                 * handled.  That doesn't matter because its only purpose
+                 * is to alert stop-signal processing code when another
+                 * processor has come along and cleared the flag.
+                 */
+                if (!(tsk->signal->flags & SIGNAL_GROUP_EXIT))
+                        tsk->signal->flags |= SIGNAL_STOP_DEQUEUED;
+        }
         if ( signr &&
              ((info->si_code & __SI_MASK) == __SI_TIMER) &&
              info->si_sys_private){
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 918e52df090e..8b75008e2bd8 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -17,6 +17,7 @@
 #include <linux/kthread.h>
 #include <linux/rcupdate.h>
 #include <linux/smp.h>
+#include <linux/tick.h>
 
 #include <asm/irq.h>
 /*
@@ -273,6 +274,18 @@ EXPORT_SYMBOL(do_softirq);
 
 #endif
 
+/*
+ * Enter an interrupt context.
+ */
+void irq_enter(void)
+{
+        __irq_enter();
+#ifdef CONFIG_NO_HZ
+        if (idle_cpu(smp_processor_id()))
+                tick_nohz_update_jiffies();
+#endif
+}
+
 #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED
 # define invoke_softirq()       __do_softirq()
 #else
@@ -289,6 +302,12 @@ void irq_exit(void)
         sub_preempt_count(IRQ_EXIT_OFFSET);
         if (!in_interrupt() && local_softirq_pending())
                 invoke_softirq();
+
+#ifdef CONFIG_NO_HZ
+        /* Make sure that timer wheel updates are propagated */
+        if (!in_interrupt() && idle_cpu(smp_processor_id()) && !need_resched())
+                tick_nohz_stop_sched_tick();
+#endif
         preempt_enable_no_resched();
 }
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index e0ac6cd79fcf..3ca1d5ff0319 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -90,12 +90,6 @@ extern char modprobe_path[];
 #ifdef CONFIG_CHR_DEV_SG
 extern int sg_big_buff;
 #endif
-#ifdef CONFIG_SYSVIPC
-static int proc_ipc_dointvec(ctl_table *table, int write, struct file *filp,
-                void __user *buffer, size_t *lenp, loff_t *ppos);
-static int proc_ipc_doulongvec_minmax(ctl_table *table, int write, struct file *filp,
-                void __user *buffer, size_t *lenp, loff_t *ppos);
-#endif
 
 #ifdef __sparc__
 extern char reboot_command [];
@@ -135,18 +129,6 @@ static int parse_table(int __user *, int, void __user *, size_t __user *,
                 void __user *, size_t, ctl_table *);
 #endif
 
-static int proc_do_uts_string(ctl_table *table, int write, struct file *filp,
-                  void __user *buffer, size_t *lenp, loff_t *ppos);
-
-static int sysctl_uts_string(ctl_table *table, int __user *name, int nlen,
-                  void __user *oldval, size_t __user *oldlenp,
-                  void __user *newval, size_t newlen);
-
-#ifdef CONFIG_SYSVIPC
-static int sysctl_ipc_data(ctl_table *table, int __user *name, int nlen,
-                  void __user *oldval, size_t __user *oldlenp,
-                  void __user *newval, size_t newlen);
-#endif
 
 #ifdef CONFIG_PROC_SYSCTL
 static int proc_do_cad_pid(ctl_table *table, int write, struct file *filp,
@@ -177,60 +159,6 @@ int sysctl_legacy_va_layout;
 #endif
 
 
-static void *get_uts(ctl_table *table, int write)
-{
-        char *which = table->data;
-#ifdef CONFIG_UTS_NS
-        struct uts_namespace *uts_ns = current->nsproxy->uts_ns;
-        which = (which - (char *)&init_uts_ns) + (char *)uts_ns;
-#endif
-        if (!write)
-                down_read(&uts_sem);
-        else
-                down_write(&uts_sem);
-        return which;
-}
-
-static void put_uts(ctl_table *table, int write, void *which)
-{
-        if (!write)
-                up_read(&uts_sem);
-        else
-                up_write(&uts_sem);
-}
-
-#ifdef CONFIG_SYSVIPC
-static void *get_ipc(ctl_table *table, int write)
-{
-        char *which = table->data;
-        struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
-        which = (which - (char *)&init_ipc_ns) + (char *)ipc_ns;
-        return which;
-}
-#else
-#define get_ipc(T,W) ((T)->data)
-#endif
-
-/* /proc declarations: */
-
-#ifdef CONFIG_PROC_SYSCTL
-
-static ssize_t proc_readsys(struct file *, char __user *, size_t, loff_t *);
-static ssize_t proc_writesys(struct file *, const char __user *, size_t, loff_t *);
-static int proc_opensys(struct inode *, struct file *);
-
-const struct file_operations proc_sys_file_operations = {
-        .open           = proc_opensys,
-        .read           = proc_readsys,
-        .write          = proc_writesys,
-};
-
-extern struct proc_dir_entry *proc_sys_root;
-
-static void register_proc_table(ctl_table *, struct proc_dir_entry *, void *);
-static void unregister_proc_table(ctl_table *, struct proc_dir_entry *);
-#endif
-
 /* The default sysctl tables: */
 
 static ctl_table root_table[] = {
@@ -278,51 +206,6 @@ static ctl_table root_table[] = {
 
 static ctl_table kern_table[] = {
         {
-                .ctl_name       = KERN_OSTYPE,
-                .procname       = "ostype",
-                .data           = init_uts_ns.name.sysname,
-                .maxlen         = sizeof(init_uts_ns.name.sysname),
-                .mode           = 0444,
-                .proc_handler   = &proc_do_uts_string,
-                .strategy       = &sysctl_uts_string,
-        },
-        {
-                .ctl_name       = KERN_OSRELEASE,
-                .procname       = "osrelease",
-                .data           = init_uts_ns.name.release,
-                .maxlen         = sizeof(init_uts_ns.name.release),
-                .mode           = 0444,
-                .proc_handler   = &proc_do_uts_string,
-                .strategy       = &sysctl_uts_string,
-        },
-        {
-                .ctl_name       = KERN_VERSION,
-                .procname       = "version",
-                .data           = init_uts_ns.name.version,
-                .maxlen         = sizeof(init_uts_ns.name.version),
-                .mode           = 0444,
-                .proc_handler   = &proc_do_uts_string,
-                .strategy       = &sysctl_uts_string,
-        },
-        {
-                .ctl_name       = KERN_NODENAME,
-                .procname       = "hostname",
-                .data           = init_uts_ns.name.nodename,
-                .maxlen         = sizeof(init_uts_ns.name.nodename),
-                .mode           = 0644,
-                .proc_handler   = &proc_do_uts_string,
-                .strategy       = &sysctl_uts_string,
-        },
-        {
-                .ctl_name       = KERN_DOMAINNAME,
-                .procname       = "domainname",
-                .data           = init_uts_ns.name.domainname,
-                .maxlen         = sizeof(init_uts_ns.name.domainname),
-                .mode           = 0644,
-                .proc_handler   = &proc_do_uts_string,
-                .strategy       = &sysctl_uts_string,
-        },
-        {
                 .ctl_name       = KERN_PANIC,
                 .procname       = "panic",
                 .data           = &panic_timeout,
@@ -478,71 +361,6 @@ static ctl_table kern_table[] = {
                 .proc_handler   = &proc_dointvec,
         },
 #endif
-#ifdef CONFIG_SYSVIPC
-        {
-                .ctl_name       = KERN_SHMMAX,
-                .procname       = "shmmax",
-                .data           = &init_ipc_ns.shm_ctlmax,
-                .maxlen         = sizeof (init_ipc_ns.shm_ctlmax),
-                .mode           = 0644,
-                .proc_handler   = &proc_ipc_doulongvec_minmax,
-                .strategy       = sysctl_ipc_data,
-        },
-        {
-                .ctl_name       = KERN_SHMALL,
-                .procname       = "shmall",
-                .data           = &init_ipc_ns.shm_ctlall,
-                .maxlen         = sizeof (init_ipc_ns.shm_ctlall),
-                .mode           = 0644,
-                .proc_handler   = &proc_ipc_doulongvec_minmax,
-                .strategy       = sysctl_ipc_data,
-        },
-        {
-                .ctl_name       = KERN_SHMMNI,
-                .procname       = "shmmni",
-                .data           = &init_ipc_ns.shm_ctlmni,
-                .maxlen         = sizeof (init_ipc_ns.shm_ctlmni),
-                .mode           = 0644,
-                .proc_handler   = &proc_ipc_dointvec,
-                .strategy       = sysctl_ipc_data,
-        },
-        {
-                .ctl_name       = KERN_MSGMAX,
-                .procname       = "msgmax",
-                .data           = &init_ipc_ns.msg_ctlmax,
-                .maxlen         = sizeof (init_ipc_ns.msg_ctlmax),
-                .mode           = 0644,
-                .proc_handler   = &proc_ipc_dointvec,
-                .strategy       = sysctl_ipc_data,
-        },
-        {
-                .ctl_name       = KERN_MSGMNI,
-                .procname       = "msgmni",
-                .data           = &init_ipc_ns.msg_ctlmni,
-                .maxlen         = sizeof (init_ipc_ns.msg_ctlmni),
-                .mode           = 0644,
-                .proc_handler   = &proc_ipc_dointvec,
-                .strategy       = sysctl_ipc_data,
-        },
-        {
-                .ctl_name       = KERN_MSGMNB,
-                .procname       =  "msgmnb",
-                .data           = &init_ipc_ns.msg_ctlmnb,
-                .maxlen         = sizeof (init_ipc_ns.msg_ctlmnb),
-                .mode           = 0644,
-                .proc_handler   = &proc_ipc_dointvec,
-                .strategy       = sysctl_ipc_data,
-        },
-        {
-                .ctl_name       = KERN_SEM,
-                .procname       = "sem",
-                .data           = &init_ipc_ns.sem_ctls,
-                .maxlen         = 4*sizeof (int),
-                .mode           = 0644,
-                .proc_handler   = &proc_ipc_dointvec,
-                .strategy       = sysctl_ipc_data,
-        },
-#endif
 #ifdef CONFIG_MAGIC_SYSRQ
         {
                 .ctl_name       = KERN_SYSRQ,
@@ -1043,6 +861,12 @@ static ctl_table vm_table[] = {
         { .ctl_name = 0 }
 };
 
+#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
+static ctl_table binfmt_misc_table[] = {
+        { .ctl_name = 0 }
+};
+#endif
+
 static ctl_table fs_table[] = {
         {
                 .ctl_name       = FS_NRINODE,
@@ -1166,6 +990,14 @@ static ctl_table fs_table[] = {
                 .mode           = 0644,
                 .proc_handler   = &proc_dointvec,
         },
+#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
+        {
+                .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "binfmt_misc",
+                .mode           = 0555,
+                .child          = binfmt_misc_table,
+        },
+#endif
         { .ctl_name = 0 }
 };
 
@@ -1177,8 +1009,6 @@ static ctl_table dev_table[] = {
         { .ctl_name = 0 }
 };
 
-extern void init_irq_proc (void);
-
 static DEFINE_SPINLOCK(sysctl_lock);
 
 /* called under sysctl_lock */
@@ -1220,19 +1050,47 @@ static void start_unregistering(struct ctl_table_header *p)
         list_del_init(&p->ctl_entry);
 }
 
-void __init sysctl_init(void)
+void sysctl_head_finish(struct ctl_table_header *head)
 {
-#ifdef CONFIG_PROC_SYSCTL
-        register_proc_table(root_table, proc_sys_root, &root_table_header);
-        init_irq_proc();
-#endif
+        if (!head)
+                return;
+        spin_lock(&sysctl_lock);
+        unuse_table(head);
+        spin_unlock(&sysctl_lock);
+}
+
+struct ctl_table_header *sysctl_head_next(struct ctl_table_header *prev)
+{
+        struct ctl_table_header *head;
+        struct list_head *tmp;
+        spin_lock(&sysctl_lock);
+        if (prev) {
+                tmp = &prev->ctl_entry;
+                unuse_table(prev);
+                goto next;
+        }
+        tmp = &root_table_header.ctl_entry;
+        for (;;) {
+                head = list_entry(tmp, struct ctl_table_header, ctl_entry);
+
+                if (!use_table(head))
+                        goto next;
+                spin_unlock(&sysctl_lock);
+                return head;
+        next:
+                tmp = tmp->next;
+                if (tmp == &root_table_header.ctl_entry)
+                        break;
+        }
+        spin_unlock(&sysctl_lock);
+        return NULL;
 }
 
 #ifdef CONFIG_SYSCTL_SYSCALL
 int do_sysctl(int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp,
                void __user *newval, size_t newlen)
 {
-        struct list_head *tmp;
+        struct ctl_table_header *head;
         int error = -ENOTDIR;
 
         if (nlen <= 0 || nlen >= CTL_MAXNAME)
@@ -1242,26 +1100,16 @@ int do_sysctl(int __user *name, int nlen, void __user *oldval, size_t __user *ol
                 if (!oldlenp || get_user(old_len, oldlenp))
                         return -EFAULT;
         }
-        spin_lock(&sysctl_lock);
-        tmp = &root_table_header.ctl_entry;
-        do {
-                struct ctl_table_header *head =
-                        list_entry(tmp, struct ctl_table_header, ctl_entry);
-
-                if (!use_table(head))
-                        continue;
-
-                spin_unlock(&sysctl_lock);
 
+        for (head = sysctl_head_next(NULL); head;
+                        head = sysctl_head_next(head)) {
                 error = parse_table(name, nlen, oldval, oldlenp, 
                                         newval, newlen, head->ctl_table);
-
-                spin_lock(&sysctl_lock);
-                unuse_table(head);
-                if (error != -ENOTDIR)
+                if (error != -ENOTDIR) {
+                        sysctl_head_finish(head);
                         break;
-        } while ((tmp = tmp->next) != &root_table_header.ctl_entry);
-        spin_unlock(&sysctl_lock);
+                }
+        }
         return error;
 }
 
@@ -1282,7 +1130,7 @@ asmlinkage long sys_sysctl(struct __sysctl_args __user *args)
 #endif /* CONFIG_SYSCTL_SYSCALL */
 
 /*
- * ctl_perm does NOT grant the superuser all rights automatically, because
+ * sysctl_perm does NOT grant the superuser all rights automatically, because
  * some sysctl variables are readonly even to root.
  */
 
@@ -1297,7 +1145,7 @@ static int test_perm(int mode, int op)
         return -EACCES;
 }
 
-static inline int ctl_perm(ctl_table *table, int op)
+int sysctl_perm(ctl_table *table, int op)
 {
         int error;
         error = security_sysctl(table, op);
@@ -1321,19 +1169,11 @@ repeat:
         for ( ; table->ctl_name || table->procname; table++) {
                 if (!table->ctl_name)
                         continue;
-                if (n == table->ctl_name || table->ctl_name == CTL_ANY) {
+                if (n == table->ctl_name) {
                         int error;
                         if (table->child) {
-                                if (ctl_perm(table, 001))
+                                if (sysctl_perm(table, 001))
                                         return -EPERM;
-                                if (table->strategy) {
-                                        error = table->strategy(
-                                                table, name, nlen,
-                                                oldval, oldlenp,
-                                                newval, newlen);
-                                        if (error)
-                                                return error;
-                                }
                                 name++;
                                 nlen--;
                                 table = table->child;
@@ -1361,7 +1201,7 @@ int do_sysctl_strategy (ctl_table *table,
                 op |= 004;
         if (newval) 
                 op |= 002;
-        if (ctl_perm(table, op))
+        if (sysctl_perm(table, op))
                 return -EPERM;
 
         if (table->strategy) {
@@ -1400,10 +1240,26 @@ int do_sysctl_strategy (ctl_table *table,
 }
 #endif /* CONFIG_SYSCTL_SYSCALL */
 
+static void sysctl_set_parent(struct ctl_table *parent, struct ctl_table *table)
+{
+        for (; table->ctl_name || table->procname; table++) {
+                table->parent = parent;
+                if (table->child)
+                        sysctl_set_parent(table, table->child);
+        }
+}
+
+static __init int sysctl_init(void)
+{
+        sysctl_set_parent(NULL, root_table);
+        return 0;
+}
+
+core_initcall(sysctl_init);
+
 /**
  * register_sysctl_table - register a sysctl hierarchy
  * @table: the top-level table structure
- * @insert_at_head: whether the entry should be inserted in front or at the end
  *
  * Register a sysctl table hierarchy. @table should be a filled in ctl_table
  * array. An entry with a ctl_name of 0 terminates the table. 
@@ -1469,8 +1325,7 @@ int do_sysctl_strategy (ctl_table *table,
  * This routine returns %NULL on a failure to register, and a pointer
  * to the table header on success.
  */
-struct ctl_table_header *register_sysctl_table(ctl_table * table, 
-                                               int insert_at_head)
+struct ctl_table_header *register_sysctl_table(ctl_table * table)
 {
         struct ctl_table_header *tmp;
         tmp = kmalloc(sizeof(struct ctl_table_header), GFP_KERNEL);
@@ -1480,15 +1335,10 @@ struct ctl_table_header *register_sysctl_table(ctl_table * table,
         INIT_LIST_HEAD(&tmp->ctl_entry);
         tmp->used = 0;
         tmp->unregistering = NULL;
+        sysctl_set_parent(NULL, table);
         spin_lock(&sysctl_lock);
-        if (insert_at_head)
-                list_add(&tmp->ctl_entry, &root_table_header.ctl_entry);
-        else
-                list_add_tail(&tmp->ctl_entry, &root_table_header.ctl_entry);
+        list_add_tail(&tmp->ctl_entry, &root_table_header.ctl_entry);
         spin_unlock(&sysctl_lock);
-#ifdef CONFIG_PROC_SYSCTL
-        register_proc_table(table, proc_sys_root, tmp);
-#endif
         return tmp;
 }
 
@@ -1504,9 +1354,6 @@ void unregister_sysctl_table(struct ctl_table_header * header)
         might_sleep();
         spin_lock(&sysctl_lock);
         start_unregistering(header);
-#ifdef CONFIG_PROC_SYSCTL
-        unregister_proc_table(header->ctl_table, proc_sys_root);
-#endif
         spin_unlock(&sysctl_lock);
         kfree(header);
 }
@@ -1530,155 +1377,6 @@ void unregister_sysctl_table(struct ctl_table_header * table)
 
 #ifdef CONFIG_PROC_SYSCTL
 
-/* Scan the sysctl entries in table and add them all into /proc */
-static void register_proc_table(ctl_table * table, struct proc_dir_entry *root, void *set)
-{
-        struct proc_dir_entry *de;
-        int len;
-        mode_t mode;
-        
-        for (; table->ctl_name || table->procname; table++) {
-                /* Can't do anything without a proc name. */
-                if (!table->procname)
-                        continue;
-                /* Maybe we can't do anything with it... */
-                if (!table->proc_handler && !table->child) {
-                        printk(KERN_WARNING "SYSCTL: Can't register %s\n",
-                                table->procname);
-                        continue;
-                }
-
-                len = strlen(table->procname);
-                mode = table->mode;
-
-                de = NULL;
-                if (table->proc_handler)
-                        mode |= S_IFREG;
-                else {
-                        mode |= S_IFDIR;
-                        for (de = root->subdir; de; de = de->next) {
-                                if (proc_match(len, table->procname, de))
-                                        break;
-                        }
-                        /* If the subdir exists already, de is non-NULL */
-                }
-
-                if (!de) {
-                        de = create_proc_entry(table->procname, mode, root);
-                        if (!de)
-                                continue;
-                        de->set = set;
-                        de->data = (void *) table;
-                        if (table->proc_handler)
-                                de->proc_fops = &proc_sys_file_operations;
-                }
-                table->de = de;
-                if (de->mode & S_IFDIR)
-                        register_proc_table(table->child, de, set);
-        }
-}
-
-/*
- * Unregister a /proc sysctl table and any subdirectories.
- */
-static void unregister_proc_table(ctl_table * table, struct proc_dir_entry *root)
-{
-        struct proc_dir_entry *de;
-        for (; table->ctl_name || table->procname; table++) {
-                if (!(de = table->de))
-                        continue;
-                if (de->mode & S_IFDIR) {
-                        if (!table->child) {
-                                printk (KERN_ALERT "Help - malformed sysctl tree on free\n");
-                                continue;
-                        }
-                        unregister_proc_table(table->child, de);
-
-                        /* Don't unregister directories which still have entries.. */
-                        if (de->subdir)
-                                continue;
-                }
-
-                /*
-                 * In any case, mark the entry as goner; we'll keep it
-                 * around if it's busy, but we'll know to do nothing with
-                 * its fields.  We are under sysctl_lock here.
-                 */
-                de->data = NULL;
-
-                /* Don't unregister proc entries that are still being used.. */
-                if (atomic_read(&de->count))
-                        continue;
-
-                table->de = NULL;
-                remove_proc_entry(table->procname, root);
-        }
-}
-
-static ssize_t do_rw_proc(int write, struct file * file, char __user * buf,
-                          size_t count, loff_t *ppos)
-{
-        int op;
-        struct proc_dir_entry *de = PDE(file->f_path.dentry->d_inode);
-        struct ctl_table *table;
-        size_t res;
-        ssize_t error = -ENOTDIR;
-        
-        spin_lock(&sysctl_lock);
-        if (de && de->data && use_table(de->set)) {
-                /*
-                 * at that point we know that sysctl was not unregistered
-                 * and won't be until we finish
-                 */
-                spin_unlock(&sysctl_lock);
-                table = (struct ctl_table *) de->data;
-                if (!table || !table->proc_handler)
-                        goto out;
-                error = -EPERM;
-                op = (write ? 002 : 004);
-                if (ctl_perm(table, op))
-                        goto out;
-                
-                /* careful: calling conventions are nasty here */
-                res = count;
-                error = (*table->proc_handler)(table, write, file,
-                                                buf, &res, ppos);
-                if (!error)
-                        error = res;
-        out:
-                spin_lock(&sysctl_lock);
-                unuse_table(de->set);
-        }
-        spin_unlock(&sysctl_lock);
-        return error;
-}
-
-static int proc_opensys(struct inode *inode, struct file *file)
-{
-        if (file->f_mode & FMODE_WRITE) {
-                /*
-                 * sysctl entries that are not writable,
-                 * are _NOT_ writable, capabilities or not.
-                 */
-                if (!(inode->i_mode & S_IWUSR))
-                        return -EPERM;
-        }
-
-        return 0;
-}
-
-static ssize_t proc_readsys(struct file * file, char __user * buf,
-                            size_t count, loff_t *ppos)
-{
-        return do_rw_proc(0, file, buf, count, ppos);
-}
-
-static ssize_t proc_writesys(struct file * file, const char __user * buf,
-                             size_t count, loff_t *ppos)
-{
-        return do_rw_proc(1, file, (char __user *) buf, count, ppos);
-}
-
 static int _proc_do_string(void* data, int maxlen, int write,
                            struct file *filp, void __user *buffer,
                            size_t *lenp, loff_t *ppos)
@@ -1762,21 +1460,6 @@ int proc_dostring(ctl_table *table, int write, struct file *filp,
                                buffer, lenp, ppos);
 }
 
-/*
- *      Special case of dostring for the UTS structure. This has locks
- *      to observe. Should this be in kernel/sys.c ????
- */
-
-static int proc_do_uts_string(ctl_table *table, int write, struct file *filp,
-                  void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-        int r;
-        void *which;
-        which = get_uts(table, write);
-        r = _proc_do_string(which, table->maxlen,write,filp,buffer,lenp, ppos);
-        put_uts(table, write, which);
-        return r;
-}
 
 static int do_proc_dointvec_conv(int *negp, unsigned long *lvalp,
                                  int *valp,
@@ -2362,27 +2045,6 @@ int proc_dointvec_ms_jiffies(ctl_table *table, int write, struct file *filp,
                                 do_proc_dointvec_ms_jiffies_conv, NULL);
 }
 
-#ifdef CONFIG_SYSVIPC
-static int proc_ipc_dointvec(ctl_table *table, int write, struct file *filp,
-        void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-        void *which;
-        which = get_ipc(table, write);
-        return __do_proc_dointvec(which, table, write, filp, buffer,
-                        lenp, ppos, NULL, NULL);
-}
-
-static int proc_ipc_doulongvec_minmax(ctl_table *table, int write,
-        struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-        void *which;
-        which = get_ipc(table, write);
-        return __do_proc_doulongvec_minmax(which, table, write, filp, buffer,
-                        lenp, ppos, 1l, 1l);
-}
-
-#endif
-
 static int proc_do_cad_pid(ctl_table *table, int write, struct file *filp,
                            void __user *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -2413,31 +2075,6 @@ int proc_dostring(ctl_table *table, int write, struct file *filp,
         return -ENOSYS;
 }
 
-static int proc_do_uts_string(ctl_table *table, int write, struct file *filp,
-                void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-        return -ENOSYS;
-}
-
-#ifdef CONFIG_SYSVIPC
-static int proc_do_ipc_string(ctl_table *table, int write, struct file *filp,
-                void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-        return -ENOSYS;
-}
-static int proc_ipc_dointvec(ctl_table *table, int write, struct file *filp,
-                void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-        return -ENOSYS;
-}
-static int proc_ipc_doulongvec_minmax(ctl_table *table, int write,
-                struct file *filp, void __user *buffer,
-                size_t *lenp, loff_t *ppos)
-{
-        return -ENOSYS;
-}
-#endif
-
 int proc_dointvec(ctl_table *table, int write, struct file *filp,
                   void __user *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -2648,62 +2285,6 @@ int sysctl_ms_jiffies(ctl_table *table, int __user *name, int nlen,
 }
 
 
-/* The generic string strategy routine: */
-static int sysctl_uts_string(ctl_table *table, int __user *name, int nlen,
-                  void __user *oldval, size_t __user *oldlenp,
-                  void __user *newval, size_t newlen)
-{
-        struct ctl_table uts_table;
-        int r, write;
-        write = newval && newlen;
-        memcpy(&uts_table, table, sizeof(uts_table));
-        uts_table.data = get_uts(table, write);
-        r = sysctl_string(&uts_table, name, nlen,
-                oldval, oldlenp, newval, newlen);
-        put_uts(table, write, uts_table.data);
-        return r;
-}
-
-#ifdef CONFIG_SYSVIPC
-/* The generic sysctl ipc data routine. */
-static int sysctl_ipc_data(ctl_table *table, int __user *name, int nlen,
-                void __user *oldval, size_t __user *oldlenp,
-                void __user *newval, size_t newlen)
-{
-        size_t len;
-        void *data;
-
-        /* Get out of I don't have a variable */
-        if (!table->data || !table->maxlen)
-                return -ENOTDIR;
-
-        data = get_ipc(table, 1);
-        if (!data)
-                return -ENOTDIR;
-
-        if (oldval && oldlenp) {
-                if (get_user(len, oldlenp))
-                        return -EFAULT;
-                if (len) {
-                        if (len > table->maxlen)
-                                len = table->maxlen;
-                        if (copy_to_user(oldval, data, len))
-                                return -EFAULT;
-                        if (put_user(len, oldlenp))
-                                return -EFAULT;
-                }
-        }
-
-        if (newval && newlen) {
-                if (newlen > table->maxlen)
-                        newlen = table->maxlen;
-
-                if (copy_from_user(data, newval, newlen))
-                        return -EFAULT;
-        }
-        return 1;
-}
-#endif
 
 #else /* CONFIG_SYSCTL_SYSCALL */
 
@@ -2769,20 +2350,6 @@ int sysctl_ms_jiffies(ctl_table *table, int __user *name, int nlen,
         return -ENOSYS;
 }
 
-static int sysctl_uts_string(ctl_table *table, int __user *name, int nlen,
-                  void __user *oldval, size_t __user *oldlenp,
-                  void __user *newval, size_t newlen)
-{
-        return -ENOSYS;
-}
-#ifdef CONFIG_SYSVIPC
-static int sysctl_ipc_data(ctl_table *table, int __user *name, int nlen,
-                void __user *oldval, size_t __user *oldlenp,
-                void __user *newval, size_t newlen)
-{
-        return -ENOSYS;
-}
-#endif
 #endif /* CONFIG_SYSCTL_SYSCALL */
 
 /*
diff --git a/kernel/time.c b/kernel/time.c
index 0e017bff4c19..c6c80ea5d0ea 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -470,6 +470,260 @@ struct timeval ns_to_timeval(const s64 nsec)
         return tv;
 }
 
+/*
+ * Convert jiffies to milliseconds and back.
+ *
+ * Avoid unnecessary multiplications/divisions in the
+ * two most common HZ cases:
+ */
+unsigned int jiffies_to_msecs(const unsigned long j)
+{
+#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
+        return (MSEC_PER_SEC / HZ) * j;
+#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
+        return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC);
+#else
+        return (j * MSEC_PER_SEC) / HZ;
+#endif
+}
+EXPORT_SYMBOL(jiffies_to_msecs);
+
+unsigned int jiffies_to_usecs(const unsigned long j)
+{
+#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ)
+        return (USEC_PER_SEC / HZ) * j;
+#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC)
+        return (j + (HZ / USEC_PER_SEC) - 1)/(HZ / USEC_PER_SEC);
+#else
+        return (j * USEC_PER_SEC) / HZ;
+#endif
+}
+EXPORT_SYMBOL(jiffies_to_usecs);
+
+/*
+ * When we convert to jiffies then we interpret incoming values
+ * the following way:
+ *
+ * - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET)
+ *
+ * - 'too large' values [that would result in larger than
+ *   MAX_JIFFY_OFFSET values] mean 'infinite timeout' too.
+ *
+ * - all other values are converted to jiffies by either multiplying
+ *   the input value by a factor or dividing it with a factor
+ *
+ * We must also be careful about 32-bit overflows.
+ */
+unsigned long msecs_to_jiffies(const unsigned int m)
+{
+        /*
+         * Negative value, means infinite timeout:
+         */
+        if ((int)m < 0)
+                return MAX_JIFFY_OFFSET;
+
+#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
+        /*
+         * HZ is equal to or smaller than 1000, and 1000 is a nice
+         * round multiple of HZ, divide with the factor between them,
+         * but round upwards:
+         */
+        return (m + (MSEC_PER_SEC / HZ) - 1) / (MSEC_PER_SEC / HZ);
+#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
+        /*
+         * HZ is larger than 1000, and HZ is a nice round multiple of
+         * 1000 - simply multiply with the factor between them.
+         *
+         * But first make sure the multiplication result cannot
+         * overflow:
+         */
+        if (m > jiffies_to_msecs(MAX_JIFFY_OFFSET))
+                return MAX_JIFFY_OFFSET;
+
+        return m * (HZ / MSEC_PER_SEC);
+#else
+        /*
+         * Generic case - multiply, round and divide. But first
+         * check that if we are doing a net multiplication, that
+         * we wouldnt overflow:
+         */
+        if (HZ > MSEC_PER_SEC && m > jiffies_to_msecs(MAX_JIFFY_OFFSET))
+                return MAX_JIFFY_OFFSET;
+
+        return (m * HZ + MSEC_PER_SEC - 1) / MSEC_PER_SEC;
+#endif
+}
+EXPORT_SYMBOL(msecs_to_jiffies);
+
+unsigned long usecs_to_jiffies(const unsigned int u)
+{
+        if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET))
+                return MAX_JIFFY_OFFSET;
+#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ)
+        return (u + (USEC_PER_SEC / HZ) - 1) / (USEC_PER_SEC / HZ);
+#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC)
+        return u * (HZ / USEC_PER_SEC);
+#else
+        return (u * HZ + USEC_PER_SEC - 1) / USEC_PER_SEC;
+#endif
+}
+EXPORT_SYMBOL(usecs_to_jiffies);
+
+/*
+ * The TICK_NSEC - 1 rounds up the value to the next resolution.  Note
+ * that a remainder subtract here would not do the right thing as the
+ * resolution values don't fall on second boundries.  I.e. the line:
+ * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding.
+ *
+ * Rather, we just shift the bits off the right.
+ *
+ * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec
+ * value to a scaled second value.
+ */
+unsigned long
+timespec_to_jiffies(const struct timespec *value)
+{
+        unsigned long sec = value->tv_sec;
+        long nsec = value->tv_nsec + TICK_NSEC - 1;
+
+        if (sec >= MAX_SEC_IN_JIFFIES){
+                sec = MAX_SEC_IN_JIFFIES;
+                nsec = 0;
+        }
+        return (((u64)sec * SEC_CONVERSION) +
+                (((u64)nsec * NSEC_CONVERSION) >>
+                 (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
+
+}
+EXPORT_SYMBOL(timespec_to_jiffies);
+
+void
+jiffies_to_timespec(const unsigned long jiffies, struct timespec *value)
+{
+        /*
+         * Convert jiffies to nanoseconds and separate with
+         * one divide.
+         */
+        u64 nsec = (u64)jiffies * TICK_NSEC;
+        value->tv_sec = div_long_long_rem(nsec, NSEC_PER_SEC, &value->tv_nsec);
+}
+EXPORT_SYMBOL(jiffies_to_timespec);
+
+/* Same for "timeval"
+ *
+ * Well, almost.  The problem here is that the real system resolution is
+ * in nanoseconds and the value being converted is in micro seconds.
+ * Also for some machines (those that use HZ = 1024, in-particular),
+ * there is a LARGE error in the tick size in microseconds.
+
+ * The solution we use is to do the rounding AFTER we convert the
+ * microsecond part.  Thus the USEC_ROUND, the bits to be shifted off.
+ * Instruction wise, this should cost only an additional add with carry
+ * instruction above the way it was done above.
+ */
+unsigned long
+timeval_to_jiffies(const struct timeval *value)
+{
+        unsigned long sec = value->tv_sec;
+        long usec = value->tv_usec;
+
+        if (sec >= MAX_SEC_IN_JIFFIES){
+                sec = MAX_SEC_IN_JIFFIES;
+                usec = 0;
+        }
+        return (((u64)sec * SEC_CONVERSION) +
+                (((u64)usec * USEC_CONVERSION + USEC_ROUND) >>
+                 (USEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
+}
+
+void jiffies_to_timeval(const unsigned long jiffies, struct timeval *value)
+{
+        /*
+         * Convert jiffies to nanoseconds and separate with
+         * one divide.
+         */
+        u64 nsec = (u64)jiffies * TICK_NSEC;
+        long tv_usec;
+
+        value->tv_sec = div_long_long_rem(nsec, NSEC_PER_SEC, &tv_usec);
+        tv_usec /= NSEC_PER_USEC;
+        value->tv_usec = tv_usec;
+}
+
+/*
+ * Convert jiffies/jiffies_64 to clock_t and back.
+ */
+clock_t jiffies_to_clock_t(long x)
+{
+#if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0
+        return x / (HZ / USER_HZ);
+#else
+        u64 tmp = (u64)x * TICK_NSEC;
+        do_div(tmp, (NSEC_PER_SEC / USER_HZ));
+        return (long)tmp;
+#endif
+}
+EXPORT_SYMBOL(jiffies_to_clock_t);
+
+unsigned long clock_t_to_jiffies(unsigned long x)
+{
+#if (HZ % USER_HZ)==0
+        if (x >= ~0UL / (HZ / USER_HZ))
+                return ~0UL;
+        return x * (HZ / USER_HZ);
+#else
+        u64 jif;
+
+        /* Don't worry about loss of precision here .. */
+        if (x >= ~0UL / HZ * USER_HZ)
+                return ~0UL;
+
+        /* .. but do try to contain it here */
+        jif = x * (u64) HZ;
+        do_div(jif, USER_HZ);
+        return jif;
+#endif
+}
+EXPORT_SYMBOL(clock_t_to_jiffies);
+
+u64 jiffies_64_to_clock_t(u64 x)
+{
+#if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0
+        do_div(x, HZ / USER_HZ);
+#else
+        /*
+         * There are better ways that don't overflow early,
+         * but even this doesn't overflow in hundreds of years
+         * in 64 bits, so..
+         */
+        x *= TICK_NSEC;
+        do_div(x, (NSEC_PER_SEC / USER_HZ));
+#endif
+        return x;
+}
+
+EXPORT_SYMBOL(jiffies_64_to_clock_t);
+
+u64 nsec_to_clock_t(u64 x)
+{
+#if (NSEC_PER_SEC % USER_HZ) == 0
+        do_div(x, (NSEC_PER_SEC / USER_HZ));
+#elif (USER_HZ % 512) == 0
+        x *= USER_HZ/512;
+        do_div(x, (NSEC_PER_SEC / 512));
+#else
+        /*
+         * max relative error 5.7e-8 (1.8s per year) for USER_HZ <= 1024,
+         * overflow after 64.99 years.
+         * exact for HZ=60, 72, 90, 120, 144, 180, 300, 600, 900, ...
+         */
+        x *= 9;
+        do_div(x, (unsigned long)((9ull * NSEC_PER_SEC + (USER_HZ/2)) /
+                                  USER_HZ));
+#endif
+        return x;
+}
+
 #if (BITS_PER_LONG < 64)
 u64 get_jiffies_64(void)
 {
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
new file mode 100644
index 000000000000..f66351126544
--- /dev/null
+++ b/kernel/time/Kconfig
@@ -0,0 +1,25 @@
+#
+# Timer subsystem related configuration options
+#
+config TICK_ONESHOT
+        bool
+        default n
+
+config NO_HZ
+        bool "Tickless System (Dynamic Ticks)"
+        depends on GENERIC_TIME && GENERIC_CLOCKEVENTS
+        select TICK_ONESHOT
+        help
+          This option enables a tickless system: timer interrupts will
+          only trigger on an as-needed basis both when the system is
+          busy and when the system is idle.
+
+config HIGH_RES_TIMERS
+        bool "High Resolution Timer Support"
+        depends on GENERIC_TIME && GENERIC_CLOCKEVENTS
+        select TICK_ONESHOT
+        help
+          This option enables high resolution timer support. If your
+          hardware is not capable then this option only increases
+          the size of the kernel image.
+
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 61a3907d16fb..93bccba1f265 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -1 +1,8 @@
-obj-y += ntp.o clocksource.o jiffies.o
+obj-y += ntp.o clocksource.o jiffies.o timer_list.o
+
+obj-$(CONFIG_GENERIC_CLOCKEVENTS)               += clockevents.o
+obj-$(CONFIG_GENERIC_CLOCKEVENTS)               += tick-common.o
+obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST)     += tick-broadcast.o
+obj-$(CONFIG_TICK_ONESHOT)                      += tick-oneshot.o
+obj-$(CONFIG_TICK_ONESHOT)                      += tick-sched.o
+obj-$(CONFIG_TIMER_STATS)                       += timer_stats.o
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
new file mode 100644
index 000000000000..67932ea78c17
--- /dev/null
+++ b/kernel/time/clockevents.c
@@ -0,0 +1,345 @@
+/*
+ * linux/kernel/time/clockevents.c
+ *
+ * This file contains functions which manage clock event devices.
+ *
+ * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
+ * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
+ * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
+ *
+ * This code is licenced under the GPL version 2. For details see
+ * kernel-base/COPYING.
+ */
+
+#include <linux/clockchips.h>
+#include <linux/hrtimer.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/notifier.h>
+#include <linux/smp.h>
+#include <linux/sysdev.h>
+
+/* The registered clock event devices */
+static LIST_HEAD(clockevent_devices);
+static LIST_HEAD(clockevents_released);
+
+/* Notification for clock events */
+static RAW_NOTIFIER_HEAD(clockevents_chain);
+
+/* Protection for the above */
+static DEFINE_SPINLOCK(clockevents_lock);
+
+/**
+ * clockevents_delta2ns - Convert a latch value (device ticks) to nanoseconds
+ * @latch:      value to convert
+ * @evt:        pointer to clock event device descriptor
+ *
+ * Math helper, returns latch value converted to nanoseconds (bound checked)
+ */
+unsigned long clockevent_delta2ns(unsigned long latch,
+                                  struct clock_event_device *evt)
+{
+        u64 clc = ((u64) latch << evt->shift);
+
+        do_div(clc, evt->mult);
+        if (clc < 1000)
+                clc = 1000;
+        if (clc > LONG_MAX)
+                clc = LONG_MAX;
+
+        return (unsigned long) clc;
+}
+
+/**
+ * clockevents_set_mode - set the operating mode of a clock event device
+ * @dev:        device to modify
+ * @mode:       new mode
+ *
+ * Must be called with interrupts disabled !
+ */
+void clockevents_set_mode(struct clock_event_device *dev,
+                                 enum clock_event_mode mode)
+{
+        if (dev->mode != mode) {
+                dev->set_mode(mode, dev);
+                dev->mode = mode;
+        }
+}
+
+/**
+ * clockevents_program_event - Reprogram the clock event device.
+ * @expires:    absolute expiry time (monotonic clock)
+ *
+ * Returns 0 on success, -ETIME when the event is in the past.
+ */
+int clockevents_program_event(struct clock_event_device *dev, ktime_t expires,
+                              ktime_t now)
+{
+        unsigned long long clc;
+        int64_t delta;
+
+        delta = ktime_to_ns(ktime_sub(expires, now));
+
+        if (delta <= 0)
+                return -ETIME;
+
+        dev->next_event = expires;
+
+        if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN)
+                return 0;
+
+        if (delta > dev->max_delta_ns)
+                delta = dev->max_delta_ns;
+        if (delta < dev->min_delta_ns)
+                delta = dev->min_delta_ns;
+
+        clc = delta * dev->mult;
+        clc >>= dev->shift;
+
+        return dev->set_next_event((unsigned long) clc, dev);
+}
+
+/**
+ * clockevents_register_notifier - register a clock events change listener
+ */
+int clockevents_register_notifier(struct notifier_block *nb)
+{
+        int ret;
+
+        spin_lock(&clockevents_lock);
+        ret = raw_notifier_chain_register(&clockevents_chain, nb);
+        spin_unlock(&clockevents_lock);
+
+        return ret;
+}
+
+/**
+ * clockevents_unregister_notifier - unregister a clock events change listener
+ */
+void clockevents_unregister_notifier(struct notifier_block *nb)
+{
+        spin_lock(&clockevents_lock);
+        raw_notifier_chain_unregister(&clockevents_chain, nb);
+        spin_unlock(&clockevents_lock);
+}
+
+/*
+ * Notify about a clock event change. Called with clockevents_lock
+ * held.
+ */
+static void clockevents_do_notify(unsigned long reason, void *dev)
+{
+        raw_notifier_call_chain(&clockevents_chain, reason, dev);
+}
+
+/*
+ * Called after a notify add to make devices availble which were
+ * released from the notifier call.
+ */
+static void clockevents_notify_released(void)
+{
+        struct clock_event_device *dev;
+
+        while (!list_empty(&clockevents_released)) {
+                dev = list_entry(clockevents_released.next,
+                                 struct clock_event_device, list);
+                list_del(&dev->list);
+                list_add(&dev->list, &clockevent_devices);
+                clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev);
+        }
+}
+
+/**
+ * clockevents_register_device - register a clock event device
+ * @dev:        device to register
+ */
+void clockevents_register_device(struct clock_event_device *dev)
+{
+        BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
+
+        spin_lock(&clockevents_lock);
+
+        list_add(&dev->list, &clockevent_devices);
+        clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev);
+        clockevents_notify_released();
+
+        spin_unlock(&clockevents_lock);
+}
+
+/*
+ * Noop handler when we shut down an event device
+ */
+static void clockevents_handle_noop(struct clock_event_device *dev)
+{
+}
+
+/**
+ * clockevents_exchange_device - release and request clock devices
+ * @old:        device to release (can be NULL)
+ * @new:        device to request (can be NULL)
+ *
+ * Called from the notifier chain. clockevents_lock is held already
+ */
+void clockevents_exchange_device(struct clock_event_device *old,
+                                 struct clock_event_device *new)
+{
+        unsigned long flags;
+
+        local_irq_save(flags);
+        /*
+         * Caller releases a clock event device. We queue it into the
+         * released list and do a notify add later.
+         */
+        if (old) {
+                old->event_handler = clockevents_handle_noop;
+                clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED);
+                list_del(&old->list);
+                list_add(&old->list, &clockevents_released);
+        }
+
+        if (new) {
+                BUG_ON(new->mode != CLOCK_EVT_MODE_UNUSED);
+                clockevents_set_mode(new, CLOCK_EVT_MODE_SHUTDOWN);
+        }
+        local_irq_restore(flags);
+}
+
+/**
+ * clockevents_request_device
+ */
+struct clock_event_device *clockevents_request_device(unsigned int features,
+                                                      cpumask_t cpumask)
+{
+        struct clock_event_device *cur, *dev = NULL;
+        struct list_head *tmp;
+
+        spin_lock(&clockevents_lock);
+
+        list_for_each(tmp, &clockevent_devices) {
+                cur = list_entry(tmp, struct clock_event_device, list);
+
+                if ((cur->features & features) == features &&
+                    cpus_equal(cpumask, cur->cpumask)) {
+                        if (!dev || dev->rating < cur->rating)
+                                dev = cur;
+                }
+        }
+
+        clockevents_exchange_device(NULL, dev);
+
+        spin_unlock(&clockevents_lock);
+
+        return dev;
+}
+
+/**
+ * clockevents_release_device
+ */
+void clockevents_release_device(struct clock_event_device *dev)
+{
+        spin_lock(&clockevents_lock);
+
+        clockevents_exchange_device(dev, NULL);
+        clockevents_notify_released();
+
+        spin_unlock(&clockevents_lock);
+}
+
+/**
+ * clockevents_notify - notification about relevant events
+ */
+void clockevents_notify(unsigned long reason, void *arg)
+{
+        spin_lock(&clockevents_lock);
+        clockevents_do_notify(reason, arg);
+
+        switch (reason) {
+        case CLOCK_EVT_NOTIFY_CPU_DEAD:
+                /*
+                 * Unregister the clock event devices which were
+                 * released from the users in the notify chain.
+                 */
+                while (!list_empty(&clockevents_released)) {
+                        struct clock_event_device *dev;
+
+                        dev = list_entry(clockevents_released.next,
+                                         struct clock_event_device, list);
+                        list_del(&dev->list);
+                }
+                break;
+        default:
+                break;
+        }
+        spin_unlock(&clockevents_lock);
+}
+EXPORT_SYMBOL_GPL(clockevents_notify);
+
+#ifdef CONFIG_SYSFS
+
+/**
+ * clockevents_show_registered - sysfs interface for listing clockevents
+ * @dev:        unused
+ * @buf:        char buffer to be filled with clock events list
+ *
+ * Provides sysfs interface for listing registered clock event devices
+ */
+static ssize_t clockevents_show_registered(struct sys_device *dev, char *buf)
+{
+        struct list_head *tmp;
+        char *p = buf;
+        int cpu;
+
+        spin_lock(&clockevents_lock);
+
+        list_for_each(tmp, &clockevent_devices) {
+                struct clock_event_device *ce;
+
+                ce = list_entry(tmp, struct clock_event_device, list);
+                p += sprintf(p, "%-20s F:%04x M:%d", ce->name,
+                             ce->features, ce->mode);
+                p += sprintf(p, " C:");
+                if (!cpus_equal(ce->cpumask, cpu_possible_map)) {
+                        for_each_cpu_mask(cpu, ce->cpumask)
+                                p += sprintf(p, " %d", cpu);
+                } else {
+                        /*
+                         * FIXME: Add the cpu which is handling this sucker
+                         */
+                }
+                p += sprintf(p, "\n");
+        }
+
+        spin_unlock(&clockevents_lock);
+
+        return p - buf;
+}
+
+/*
+ * Sysfs setup bits:
+ */
+static SYSDEV_ATTR(registered, 0600,
+                   clockevents_show_registered, NULL);
+
+static struct sysdev_class clockevents_sysclass = {
+        set_kset_name("clockevents"),
+};
+
+static struct sys_device clockevents_sys_device = {
+        .id     = 0,
+        .cls    = &clockevents_sysclass,
+};
+
+static int __init clockevents_sysfs_init(void)
+{
+        int error = sysdev_class_register(&clockevents_sysclass);
+
+        if (!error)
+                error = sysdev_register(&clockevents_sys_device);
+        if (!error)
+                error = sysdev_create_file(
+                                &clockevents_sys_device,
+                                &attr_registered);
+        return error;
+}
+device_initcall(clockevents_sysfs_init);
+#endif
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index d9ef176c4e09..193a0793af95 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -29,6 +29,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/sched.h> /* for spin_unlock_irq() using preempt_count() m68k */
+#include <linux/tick.h>
 
 /* XXX - Would like a better way for initializing curr_clocksource */
 extern struct clocksource clocksource_jiffies;
@@ -48,6 +49,7 @@ extern struct clocksource clocksource_jiffies;
  */
 static struct clocksource *curr_clocksource = &clocksource_jiffies;
 static struct clocksource *next_clocksource;
+static struct clocksource *clocksource_override;
 static LIST_HEAD(clocksource_list);
 static DEFINE_SPINLOCK(clocksource_lock);
 static char override_name[32];
@@ -62,9 +64,123 @@ static int __init clocksource_done_booting(void)
         finished_booting = 1;
         return 0;
 }
-
 late_initcall(clocksource_done_booting);
 
+#ifdef CONFIG_CLOCKSOURCE_WATCHDOG
+static LIST_HEAD(watchdog_list);
+static struct clocksource *watchdog;
+static struct timer_list watchdog_timer;
+static DEFINE_SPINLOCK(watchdog_lock);
+static cycle_t watchdog_last;
+/*
+ * Interval: 0.5sec Treshold: 0.0625s
+ */
+#define WATCHDOG_INTERVAL (HZ >> 1)
+#define WATCHDOG_TRESHOLD (NSEC_PER_SEC >> 4)
+
+static void clocksource_ratewd(struct clocksource *cs, int64_t delta)
+{
+        if (delta > -WATCHDOG_TRESHOLD && delta < WATCHDOG_TRESHOLD)
+                return;
+
+        printk(KERN_WARNING "Clocksource %s unstable (delta = %Ld ns)\n",
+               cs->name, delta);
+        cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG);
+        clocksource_change_rating(cs, 0);
+        cs->flags &= ~CLOCK_SOURCE_WATCHDOG;
+        list_del(&cs->wd_list);
+}
+
+static void clocksource_watchdog(unsigned long data)
+{
+        struct clocksource *cs, *tmp;
+        cycle_t csnow, wdnow;
+        int64_t wd_nsec, cs_nsec;
+
+        spin_lock(&watchdog_lock);
+
+        wdnow = watchdog->read();
+        wd_nsec = cyc2ns(watchdog, (wdnow - watchdog_last) & watchdog->mask);
+        watchdog_last = wdnow;
+
+        list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) {
+                csnow = cs->read();
+                /* Initialized ? */
+                if (!(cs->flags & CLOCK_SOURCE_WATCHDOG)) {
+                        if ((cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) &&
+                            (watchdog->flags & CLOCK_SOURCE_IS_CONTINUOUS)) {
+                                cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
+                                /*
+                                 * We just marked the clocksource as
+                                 * highres-capable, notify the rest of the
+                                 * system as well so that we transition
+                                 * into high-res mode:
+                                 */
+                                tick_clock_notify();
+                        }
+                        cs->flags |= CLOCK_SOURCE_WATCHDOG;
+                        cs->wd_last = csnow;
+                } else {
+                        cs_nsec = cyc2ns(cs, (csnow - cs->wd_last) & cs->mask);
+                        cs->wd_last = csnow;
+                        /* Check the delta. Might remove from the list ! */
+                        clocksource_ratewd(cs, cs_nsec - wd_nsec);
+                }
+        }
+
+        if (!list_empty(&watchdog_list)) {
+                __mod_timer(&watchdog_timer,
+                            watchdog_timer.expires + WATCHDOG_INTERVAL);
+        }
+        spin_unlock(&watchdog_lock);
+}
+static void clocksource_check_watchdog(struct clocksource *cs)
+{
+        struct clocksource *cse;
+        unsigned long flags;
+
+        spin_lock_irqsave(&watchdog_lock, flags);
+        if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
+                int started = !list_empty(&watchdog_list);
+
+                list_add(&cs->wd_list, &watchdog_list);
+                if (!started && watchdog) {
+                        watchdog_last = watchdog->read();
+                        watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL;
+                        add_timer(&watchdog_timer);
+                }
+        } else if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) {
+                        cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
+
+                if (!watchdog || cs->rating > watchdog->rating) {
+                        if (watchdog)
+                                del_timer(&watchdog_timer);
+                        watchdog = cs;
+                        init_timer(&watchdog_timer);
+                        watchdog_timer.function = clocksource_watchdog;
+
+                        /* Reset watchdog cycles */
+                        list_for_each_entry(cse, &watchdog_list, wd_list)
+                                cse->flags &= ~CLOCK_SOURCE_WATCHDOG;
+                        /* Start if list is not empty */
+                        if (!list_empty(&watchdog_list)) {
+                                watchdog_last = watchdog->read();
+                                watchdog_timer.expires =
+                                        jiffies + WATCHDOG_INTERVAL;
+                                add_timer(&watchdog_timer);
+                        }
+                }
+        }
+        spin_unlock_irqrestore(&watchdog_lock, flags);
+}
+#else
+static void clocksource_check_watchdog(struct clocksource *cs)
+{
+        if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
+                cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
+}
+#endif
+
 /**
  * clocksource_get_next - Returns the selected clocksource
  *
@@ -84,60 +200,54 @@ struct clocksource *clocksource_get_next(void)
 }
 
 /**
- * select_clocksource - Finds the best registered clocksource.
+ * select_clocksource - Selects the best registered clocksource.
  *
  * Private function. Must hold clocksource_lock when called.
  *
- * Looks through the list of registered clocksources, returning
- * the one with the highest rating value. If there is a clocksource
- * name that matches the override string, it returns that clocksource.
+ * Select the clocksource with the best rating, or the clocksource,
+ * which is selected by userspace override.
  */
 static struct clocksource *select_clocksource(void)
 {
-        struct clocksource *best = NULL;
-        struct list_head *tmp;
+        struct clocksource *next;
 
-        list_for_each(tmp, &clocksource_list) {
-                struct clocksource *src;
+        if (list_empty(&clocksource_list))
+                return NULL;
 
-                src = list_entry(tmp, struct clocksource, list);
-                if (!best)
-                        best = src;
-
-                /* check for override: */
-                if (strlen(src->name) == strlen(override_name) &&
-                    !strcmp(src->name, override_name)) {
-                        best = src;
-                        break;
-                }
-                /* pick the highest rating: */
-                if (src->rating > best->rating)
-                        best = src;
-        }
+        if (clocksource_override)
+                next = clocksource_override;
+        else
+                next = list_entry(clocksource_list.next, struct clocksource,
+                                  list);
+
+        if (next == curr_clocksource)
+                return NULL;
 
-        return best;
+        return next;
 }
 
-/**
- * is_registered_source - Checks if clocksource is registered
- * @c:          pointer to a clocksource
- *
- * Private helper function. Must hold clocksource_lock when called.
- *
- * Returns one if the clocksource is already registered, zero otherwise.
+/*
+ * Enqueue the clocksource sorted by rating
  */
-static int is_registered_source(struct clocksource *c)
+static int clocksource_enqueue(struct clocksource *c)
 {
-        int len = strlen(c->name);
-        struct list_head *tmp;
+        struct list_head *tmp, *entry = &clocksource_list;
 
         list_for_each(tmp, &clocksource_list) {
-                struct clocksource *src;
-
-                src = list_entry(tmp, struct clocksource, list);
-                if (strlen(src->name) == len && !strcmp(src->name, c->name))
-                        return 1;
+                struct clocksource *cs;
+
+                cs = list_entry(tmp, struct clocksource, list);
+                if (cs == c)
+                        return -EBUSY;
+                /* Keep track of the place, where to insert */
+                if (cs->rating >= c->rating)
+                        entry = tmp;
         }
+        list_add(&c->list, entry);
+
+        if (strlen(c->name) == strlen(override_name) &&
+            !strcmp(c->name, override_name))
+                clocksource_override = c;
 
         return 0;
 }
@@ -150,42 +260,35 @@ static int is_registered_source(struct clocksource *c)
  */
 int clocksource_register(struct clocksource *c)
 {
-        int ret = 0;
         unsigned long flags;
+        int ret;
 
         spin_lock_irqsave(&clocksource_lock, flags);
-        /* check if clocksource is already registered */
-        if (is_registered_source(c)) {
-                printk("register_clocksource: Cannot register %s. "
-                       "Already registered!", c->name);
-                ret = -EBUSY;
-        } else {
-                /* register it */
-                list_add(&c->list, &clocksource_list);
-                /* scan the registered clocksources, and pick the best one */
+        ret = clocksource_enqueue(c);
+        if (!ret)
                 next_clocksource = select_clocksource();
-        }
         spin_unlock_irqrestore(&clocksource_lock, flags);
+        if (!ret)
+                clocksource_check_watchdog(c);
         return ret;
 }
 EXPORT_SYMBOL(clocksource_register);
 
 /**
- * clocksource_reselect - Rescan list for next clocksource
+ * clocksource_change_rating - Change the rating of a registered clocksource
  *
- * A quick helper function to be used if a clocksource changes its
- * rating. Forces the clocksource list to be re-scanned for the best
- * clocksource.
  */
-void clocksource_reselect(void)
+void clocksource_change_rating(struct clocksource *cs, int rating)
 {
         unsigned long flags;
 
         spin_lock_irqsave(&clocksource_lock, flags);
+        list_del(&cs->list);
+        cs->rating = rating;
+        clocksource_enqueue(cs);
         next_clocksource = select_clocksource();
         spin_unlock_irqrestore(&clocksource_lock, flags);
 }
-EXPORT_SYMBOL(clocksource_reselect);
 
 #ifdef CONFIG_SYSFS
 /**
@@ -221,7 +324,11 @@ sysfs_show_current_clocksources(struct sys_device *dev, char *buf)
 static ssize_t sysfs_override_clocksource(struct sys_device *dev,
                                           const char *buf, size_t count)
 {
+        struct clocksource *ovr = NULL;
+        struct list_head *tmp;
         size_t ret = count;
+        int len;
+
         /* strings from sysfs write are not 0 terminated! */
         if (count >= sizeof(override_name))
                 return -EINVAL;
@@ -229,17 +336,32 @@ static ssize_t sysfs_override_clocksource(struct sys_device *dev,
         /* strip of \n: */
         if (buf[count-1] == '\n')
                 count--;
-        if (count < 1)
-                return -EINVAL;
 
         spin_lock_irq(&clocksource_lock);
 
-        /* copy the name given: */
-        memcpy(override_name, buf, count);
+        if (count > 0)
+                memcpy(override_name, buf, count);
         override_name[count] = 0;
 
-        /* try to select it: */
-        next_clocksource = select_clocksource();
+        len = strlen(override_name);
+        if (len) {
+                ovr = clocksource_override;
+                /* try to select it: */
+                list_for_each(tmp, &clocksource_list) {
+                        struct clocksource *cs;
+
+                        cs = list_entry(tmp, struct clocksource, list);
+                        if (strlen(cs->name) == len &&
+                            !strcmp(cs->name, override_name))
+                                ovr = cs;
+                }
+        }
+
+        /* Reselect, when the override name has changed */
+        if (ovr != clocksource_override) {
+                clocksource_override = ovr;
+                next_clocksource = select_clocksource();
+        }
 
         spin_unlock_irq(&clocksource_lock);
 
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index a99b2a6e6a07..3be8da8fed7e 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -62,7 +62,6 @@ struct clocksource clocksource_jiffies = {
         .mask           = 0xffffffff, /*32bits*/
         .mult           = NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */
         .shift          = JIFFIES_SHIFT,
-        .is_continuous  = 0, /* tick based, not free running */
 };
 
 static int __init init_jiffies_clocksource(void)
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 3afeaa3a73f9..eb12509e00bd 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -24,7 +24,7 @@ static u64 tick_length, tick_length_base;
 
 #define MAX_TICKADJ             500             /* microsecs */
 #define MAX_TICKADJ_SCALED      (((u64)(MAX_TICKADJ * NSEC_PER_USEC) << \
-                                  TICK_LENGTH_SHIFT) / HZ)
+                                  TICK_LENGTH_SHIFT) / NTP_INTERVAL_FREQ)
 
 /*
  * phase-lock loop variables
@@ -46,13 +46,17 @@ long time_adjust;
 
 static void ntp_update_frequency(void)
 {
-        tick_length_base = (u64)(tick_usec * NSEC_PER_USEC * USER_HZ) << TICK_LENGTH_SHIFT;
-        tick_length_base += (s64)CLOCK_TICK_ADJUST << TICK_LENGTH_SHIFT;
-        tick_length_base += (s64)time_freq << (TICK_LENGTH_SHIFT - SHIFT_NSEC);
+        u64 second_length = (u64)(tick_usec * NSEC_PER_USEC * USER_HZ)
+                                << TICK_LENGTH_SHIFT;
+        second_length += (s64)CLOCK_TICK_ADJUST << TICK_LENGTH_SHIFT;
+        second_length += (s64)time_freq << (TICK_LENGTH_SHIFT - SHIFT_NSEC);
 
-        do_div(tick_length_base, HZ);
+        tick_length_base = second_length;
 
-        tick_nsec = tick_length_base >> TICK_LENGTH_SHIFT;
+        do_div(second_length, HZ);
+        tick_nsec = second_length >> TICK_LENGTH_SHIFT;
+
+        do_div(tick_length_base, NTP_INTERVAL_FREQ);
 }
 
 /**
@@ -162,7 +166,7 @@ void second_overflow(void)
                         tick_length -= MAX_TICKADJ_SCALED;
                 } else {
                         tick_length += (s64)(time_adjust * NSEC_PER_USEC /
-                                             HZ) << TICK_LENGTH_SHIFT;
+                                        NTP_INTERVAL_FREQ) << TICK_LENGTH_SHIFT;
                         time_adjust = 0;
                 }
         }
@@ -239,7 +243,8 @@ int do_adjtimex(struct timex *txc)
                     result = -EINVAL;
                     goto leave;
                 }
-                time_freq = ((s64)txc->freq * NSEC_PER_USEC) >> (SHIFT_USEC - SHIFT_NSEC);
+                time_freq = ((s64)txc->freq * NSEC_PER_USEC)
+                                >> (SHIFT_USEC - SHIFT_NSEC);
             }
 
             if (txc->modes & ADJ_MAXERROR) {
@@ -309,7 +314,8 @@ int do_adjtimex(struct timex *txc)
                     freq_adj += time_freq;
                     freq_adj = min(freq_adj, (s64)MAXFREQ_NSEC);
                     time_freq = max(freq_adj, (s64)-MAXFREQ_NSEC);
-                    time_offset = (time_offset / HZ) << SHIFT_UPDATE;
+                    time_offset = (time_offset / NTP_INTERVAL_FREQ)
+                                        << SHIFT_UPDATE;
                 } /* STA_PLL */
             } /* txc->modes & ADJ_OFFSET */
             if (txc->modes & ADJ_TICK)
@@ -324,8 +330,10 @@ leave:	if ((time_status & (STA_UNSYNC|STA_CLOCKERR)) != 0)
         if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT)
             txc->offset    = save_adjust;
         else
-            txc->offset    = shift_right(time_offset, SHIFT_UPDATE) * HZ / 1000;
-        txc->freq          = (time_freq / NSEC_PER_USEC) << (SHIFT_USEC - SHIFT_NSEC);
+            txc->offset    = shift_right(time_offset, SHIFT_UPDATE)
+                                * NTP_INTERVAL_FREQ / 1000;
+        txc->freq          = (time_freq / NSEC_PER_USEC)
+                                << (SHIFT_USEC - SHIFT_NSEC);
         txc->maxerror      = time_maxerror;
         txc->esterror      = time_esterror;
         txc->status        = time_status;
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
new file mode 100644
index 000000000000..12b3efeb9f6f
--- /dev/null
+++ b/kernel/time/tick-broadcast.c
@@ -0,0 +1,480 @@
+/*
+ * linux/kernel/time/tick-broadcast.c
+ *
+ * This file contains functions which emulate a local clock-event
+ * device via a broadcast event source.
+ *
+ * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
+ * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
+ * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
+ *
+ * This code is licenced under the GPL version 2. For details see
+ * kernel-base/COPYING.
+ */
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/irq.h>
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/sched.h>
+#include <linux/tick.h>
+
+#include "tick-internal.h"
+
+/*
+ * Broadcast support for broken x86 hardware, where the local apic
+ * timer stops in C3 state.
+ */
+
+struct tick_device tick_broadcast_device;
+static cpumask_t tick_broadcast_mask;
+static DEFINE_SPINLOCK(tick_broadcast_lock);
+
+/*
+ * Debugging: see timer_list.c
+ */
+struct tick_device *tick_get_broadcast_device(void)
+{
+        return &tick_broadcast_device;
+}
+
+cpumask_t *tick_get_broadcast_mask(void)
+{
+        return &tick_broadcast_mask;
+}
+
+/*
+ * Start the device in periodic mode
+ */
+static void tick_broadcast_start_periodic(struct clock_event_device *bc)
+{
+        if (bc && bc->mode == CLOCK_EVT_MODE_SHUTDOWN)
+                tick_setup_periodic(bc, 1);
+}
+
+/*
+ * Check, if the device can be utilized as broadcast device:
+ */
+int tick_check_broadcast_device(struct clock_event_device *dev)
+{
+        if (tick_broadcast_device.evtdev ||
+            (dev->features & CLOCK_EVT_FEAT_C3STOP))
+                return 0;
+
+        clockevents_exchange_device(NULL, dev);
+        tick_broadcast_device.evtdev = dev;
+        if (!cpus_empty(tick_broadcast_mask))
+                tick_broadcast_start_periodic(dev);
+        return 1;
+}
+
+/*
+ * Check, if the device is the broadcast device
+ */
+int tick_is_broadcast_device(struct clock_event_device *dev)
+{
+        return (dev && tick_broadcast_device.evtdev == dev);
+}
+
+/*
+ * Check, if the device is disfunctional and a place holder, which
+ * needs to be handled by the broadcast device.
+ */
+int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
+{
+        unsigned long flags;
+        int ret = 0;
+
+        spin_lock_irqsave(&tick_broadcast_lock, flags);
+
+        /*
+         * Devices might be registered with both periodic and oneshot
+         * mode disabled. This signals, that the device needs to be
+         * operated from the broadcast device and is a placeholder for
+         * the cpu local device.
+         */
+        if (!tick_device_is_functional(dev)) {
+                dev->event_handler = tick_handle_periodic;
+                cpu_set(cpu, tick_broadcast_mask);
+                tick_broadcast_start_periodic(tick_broadcast_device.evtdev);
+                ret = 1;
+        }
+
+        spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+        return ret;
+}
+
+/*
+ * Broadcast the event to the cpus, which are set in the mask
+ */
+int tick_do_broadcast(cpumask_t mask)
+{
+        int ret = 0, cpu = smp_processor_id();
+        struct tick_device *td;
+
+        /*
+         * Check, if the current cpu is in the mask
+         */
+        if (cpu_isset(cpu, mask)) {
+                cpu_clear(cpu, mask);
+                td = &per_cpu(tick_cpu_device, cpu);
+                td->evtdev->event_handler(td->evtdev);
+                ret = 1;
+        }
+
+        if (!cpus_empty(mask)) {
+                /*
+                 * It might be necessary to actually check whether the devices
+                 * have different broadcast functions. For now, just use the
+                 * one of the first device. This works as long as we have this
+                 * misfeature only on x86 (lapic)
+                 */
+                cpu = first_cpu(mask);
+                td = &per_cpu(tick_cpu_device, cpu);
+                td->evtdev->broadcast(mask);
+                ret = 1;
+        }
+        return ret;
+}
+
+/*
+ * Periodic broadcast:
+ * - invoke the broadcast handlers
+ */
+static void tick_do_periodic_broadcast(void)
+{
+        cpumask_t mask;
+
+        spin_lock(&tick_broadcast_lock);
+
+        cpus_and(mask, cpu_online_map, tick_broadcast_mask);
+        tick_do_broadcast(mask);
+
+        spin_unlock(&tick_broadcast_lock);
+}
+
+/*
+ * Event handler for periodic broadcast ticks
+ */
+static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
+{
+        dev->next_event.tv64 = KTIME_MAX;
+
+        tick_do_periodic_broadcast();
+
+        /*
+         * The device is in periodic mode. No reprogramming necessary:
+         */
+        if (dev->mode == CLOCK_EVT_MODE_PERIODIC)
+                return;
+
+        /*
+         * Setup the next period for devices, which do not have
+         * periodic mode:
+         */
+        for (;;) {
+                ktime_t next = ktime_add(dev->next_event, tick_period);
+
+                if (!clockevents_program_event(dev, next, ktime_get()))
+                        return;
+                tick_do_periodic_broadcast();
+        }
+}
+
+/*
+ * Powerstate information: The system enters/leaves a state, where
+ * affected devices might stop
+ */
+static void tick_do_broadcast_on_off(void *why)
+{
+        struct clock_event_device *bc, *dev;
+        struct tick_device *td;
+        unsigned long flags, *reason = why;
+        int cpu;
+
+        spin_lock_irqsave(&tick_broadcast_lock, flags);
+
+        cpu = smp_processor_id();
+        td = &per_cpu(tick_cpu_device, cpu);
+        dev = td->evtdev;
+        bc = tick_broadcast_device.evtdev;
+
+        /*
+         * Is the device in broadcast mode forever or is it not
+         * affected by the powerstate ?
+         */
+        if (!dev || !tick_device_is_functional(dev) ||
+            !(dev->features & CLOCK_EVT_FEAT_C3STOP))
+                goto out;
+
+        if (*reason == CLOCK_EVT_NOTIFY_BROADCAST_ON) {
+                if (!cpu_isset(cpu, tick_broadcast_mask)) {
+                        cpu_set(cpu, tick_broadcast_mask);
+                        if (td->mode == TICKDEV_MODE_PERIODIC)
+                                clockevents_set_mode(dev,
+                                                     CLOCK_EVT_MODE_SHUTDOWN);
+                }
+        } else {
+                if (cpu_isset(cpu, tick_broadcast_mask)) {
+                        cpu_clear(cpu, tick_broadcast_mask);
+                        if (td->mode == TICKDEV_MODE_PERIODIC)
+                                tick_setup_periodic(dev, 0);
+                }
+        }
+
+        if (cpus_empty(tick_broadcast_mask))
+                clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
+        else {
+                if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
+                        tick_broadcast_start_periodic(bc);
+                else
+                        tick_broadcast_setup_oneshot(bc);
+        }
+out:
+        spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+}
+
+/*
+ * Powerstate information: The system enters/leaves a state, where
+ * affected devices might stop.
+ */
+void tick_broadcast_on_off(unsigned long reason, int *oncpu)
+{
+        int cpu = get_cpu();
+
+        if (cpu == *oncpu)
+                tick_do_broadcast_on_off(&reason);
+        else
+                smp_call_function_single(*oncpu, tick_do_broadcast_on_off,
+                                         &reason, 1, 1);
+        put_cpu();
+}
+
+/*
+ * Set the periodic handler depending on broadcast on/off
+ */
+void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast)
+{
+        if (!broadcast)
+                dev->event_handler = tick_handle_periodic;
+        else
+                dev->event_handler = tick_handle_periodic_broadcast;
+}
+
+/*
+ * Remove a CPU from broadcasting
+ */
+void tick_shutdown_broadcast(unsigned int *cpup)
+{
+        struct clock_event_device *bc;
+        unsigned long flags;
+        unsigned int cpu = *cpup;
+
+        spin_lock_irqsave(&tick_broadcast_lock, flags);
+
+        bc = tick_broadcast_device.evtdev;
+        cpu_clear(cpu, tick_broadcast_mask);
+
+        if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) {
+                if (bc && cpus_empty(tick_broadcast_mask))
+                        clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
+        }
+
+        spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+}
+
+#ifdef CONFIG_TICK_ONESHOT
+
+static cpumask_t tick_broadcast_oneshot_mask;
+
+/*
+ * Debugging: see timer_list.c
+ */
+cpumask_t *tick_get_broadcast_oneshot_mask(void)
+{
+        return &tick_broadcast_oneshot_mask;
+}
+
+static int tick_broadcast_set_event(ktime_t expires, int force)
+{
+        struct clock_event_device *bc = tick_broadcast_device.evtdev;
+        ktime_t now = ktime_get();
+        int res;
+
+        for(;;) {
+                res = clockevents_program_event(bc, expires, now);
+                if (!res || !force)
+                        return res;
+                now = ktime_get();
+                expires = ktime_add(now, ktime_set(0, bc->min_delta_ns));
+        }
+}
+
+/*
+ * Reprogram the broadcast device:
+ *
+ * Called with tick_broadcast_lock held and interrupts disabled.
+ */
+static int tick_broadcast_reprogram(void)
+{
+        ktime_t expires = { .tv64 = KTIME_MAX };
+        struct tick_device *td;
+        int cpu;
+
+        /*
+         * Find the event which expires next:
+         */
+        for (cpu = first_cpu(tick_broadcast_oneshot_mask); cpu != NR_CPUS;
+             cpu = next_cpu(cpu, tick_broadcast_oneshot_mask)) {
+                td = &per_cpu(tick_cpu_device, cpu);
+                if (td->evtdev->next_event.tv64 < expires.tv64)
+                        expires = td->evtdev->next_event;
+        }
+
+        if (expires.tv64 == KTIME_MAX)
+                return 0;
+
+        return tick_broadcast_set_event(expires, 0);
+}
+
+/*
+ * Handle oneshot mode broadcasting
+ */
+static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
+{
+        struct tick_device *td;
+        cpumask_t mask;
+        ktime_t now;
+        int cpu;
+
+        spin_lock(&tick_broadcast_lock);
+again:
+        dev->next_event.tv64 = KTIME_MAX;
+        mask = CPU_MASK_NONE;
+        now = ktime_get();
+        /* Find all expired events */
+        for (cpu = first_cpu(tick_broadcast_oneshot_mask); cpu != NR_CPUS;
+             cpu = next_cpu(cpu, tick_broadcast_oneshot_mask)) {
+                td = &per_cpu(tick_cpu_device, cpu);
+                if (td->evtdev->next_event.tv64 <= now.tv64)
+                        cpu_set(cpu, mask);
+        }
+
+        /*
+         * Wakeup the cpus which have an expired event. The broadcast
+         * device is reprogrammed in the return from idle code.
+         */
+        if (!tick_do_broadcast(mask)) {
+                /*
+                 * The global event did not expire any CPU local
+                 * events. This happens in dyntick mode, as the
+                 * maximum PIT delta is quite small.
+                 */
+                if (tick_broadcast_reprogram())
+                        goto again;
+        }
+        spin_unlock(&tick_broadcast_lock);
+}
+
+/*
+ * Powerstate information: The system enters/leaves a state, where
+ * affected devices might stop
+ */
+void tick_broadcast_oneshot_control(unsigned long reason)
+{
+        struct clock_event_device *bc, *dev;
+        struct tick_device *td;
+        unsigned long flags;
+        int cpu;
+
+        spin_lock_irqsave(&tick_broadcast_lock, flags);
+
+        /*
+         * Periodic mode does not care about the enter/exit of power
+         * states
+         */
+        if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
+                goto out;
+
+        bc = tick_broadcast_device.evtdev;
+        cpu = smp_processor_id();
+        td = &per_cpu(tick_cpu_device, cpu);
+        dev = td->evtdev;
+
+        if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
+                goto out;
+
+        if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) {
+                if (!cpu_isset(cpu, tick_broadcast_oneshot_mask)) {
+                        cpu_set(cpu, tick_broadcast_oneshot_mask);
+                        clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+                        if (dev->next_event.tv64 < bc->next_event.tv64)
+                                tick_broadcast_set_event(dev->next_event, 1);
+                }
+        } else {
+                if (cpu_isset(cpu, tick_broadcast_oneshot_mask)) {
+                        cpu_clear(cpu, tick_broadcast_oneshot_mask);
+                        clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
+                        if (dev->next_event.tv64 != KTIME_MAX)
+                                tick_program_event(dev->next_event, 1);
+                }
+        }
+
+out:
+        spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+}
+
+/**
+ * tick_broadcast_setup_highres - setup the broadcast device for highres
+ */
+void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
+{
+        if (bc->mode != CLOCK_EVT_MODE_ONESHOT) {
+                bc->event_handler = tick_handle_oneshot_broadcast;
+                clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
+                bc->next_event.tv64 = KTIME_MAX;
+        }
+}
+
+/*
+ * Select oneshot operating mode for the broadcast device
+ */
+void tick_broadcast_switch_to_oneshot(void)
+{
+        struct clock_event_device *bc;
+        unsigned long flags;
+
+        spin_lock_irqsave(&tick_broadcast_lock, flags);
+
+        tick_broadcast_device.mode = TICKDEV_MODE_ONESHOT;
+        bc = tick_broadcast_device.evtdev;
+        if (bc)
+                tick_broadcast_setup_oneshot(bc);
+        spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+}
+
+
+/*
+ * Remove a dead CPU from broadcasting
+ */
+void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
+{
+        struct clock_event_device *bc;
+        unsigned long flags;
+        unsigned int cpu = *cpup;
+
+        spin_lock_irqsave(&tick_broadcast_lock, flags);
+
+        bc = tick_broadcast_device.evtdev;
+        cpu_clear(cpu, tick_broadcast_oneshot_mask);
+
+        if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT) {
+                if (bc && cpus_empty(tick_broadcast_oneshot_mask))
+                        clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
+        }
+
+        spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+}
+
+#endif
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
new file mode 100644
index 000000000000..4500e347f1bb
--- /dev/null
+++ b/kernel/time/tick-common.c
@@ -0,0 +1,346 @@
+/*
+ * linux/kernel/time/tick-common.c
+ *
+ * This file contains the base functions to manage periodic tick
+ * related events.
+ *
+ * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
+ * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
+ * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
+ *
+ * This code is licenced under the GPL version 2. For details see
+ * kernel-base/COPYING.
+ */
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/irq.h>
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/sched.h>
+#include <linux/tick.h>
+
+#include "tick-internal.h"
+
+/*
+ * Tick devices
+ */
+DEFINE_PER_CPU(struct tick_device, tick_cpu_device);
+/*
+ * Tick next event: keeps track of the tick time
+ */
+ktime_t tick_next_period;
+ktime_t tick_period;
+static int tick_do_timer_cpu = -1;
+DEFINE_SPINLOCK(tick_device_lock);
+
+/*
+ * Debugging: see timer_list.c
+ */
+struct tick_device *tick_get_device(int cpu)
+{
+        return &per_cpu(tick_cpu_device, cpu);
+}
+
+/**
+ * tick_is_oneshot_available - check for a oneshot capable event device
+ */
+int tick_is_oneshot_available(void)
+{
+        struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
+
+        return dev && (dev->features & CLOCK_EVT_FEAT_ONESHOT);
+}
+
+/*
+ * Periodic tick
+ */
+static void tick_periodic(int cpu)
+{
+        if (tick_do_timer_cpu == cpu) {
+                write_seqlock(&xtime_lock);
+
+                /* Keep track of the next tick event */
+                tick_next_period = ktime_add(tick_next_period, tick_period);
+
+                do_timer(1);
+                write_sequnlock(&xtime_lock);
+        }
+
+        update_process_times(user_mode(get_irq_regs()));
+        profile_tick(CPU_PROFILING);
+}
+
+/*
+ * Event handler for periodic ticks
+ */
+void tick_handle_periodic(struct clock_event_device *dev)
+{
+        int cpu = smp_processor_id();
+
+        tick_periodic(cpu);
+
+        if (dev->mode != CLOCK_EVT_MODE_ONESHOT)
+                return;
+        /*
+         * Setup the next period for devices, which do not have
+         * periodic mode:
+         */
+        for (;;) {
+                ktime_t next = ktime_add(dev->next_event, tick_period);
+
+                if (!clockevents_program_event(dev, next, ktime_get()))
+                        return;
+                tick_periodic(cpu);
+        }
+}
+
+/*
+ * Setup the device for a periodic tick
+ */
+void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
+{
+        tick_set_periodic_handler(dev, broadcast);
+
+        /* Broadcast setup ? */
+        if (!tick_device_is_functional(dev))
+                return;
+
+        if (dev->features & CLOCK_EVT_FEAT_PERIODIC) {
+                clockevents_set_mode(dev, CLOCK_EVT_MODE_PERIODIC);
+        } else {
+                unsigned long seq;
+                ktime_t next;
+
+                do {
+                        seq = read_seqbegin(&xtime_lock);
+                        next = tick_next_period;
+                } while (read_seqretry(&xtime_lock, seq));
+
+                clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
+
+                for (;;) {
+                        if (!clockevents_program_event(dev, next, ktime_get()))
+                                return;
+                        next = ktime_add(next, tick_period);
+                }
+        }
+}
+
+/*
+ * Setup the tick device
+ */
+static void tick_setup_device(struct tick_device *td,
+                              struct clock_event_device *newdev, int cpu,
+                              cpumask_t cpumask)
+{
+        ktime_t next_event;
+        void (*handler)(struct clock_event_device *) = NULL;
+
+        /*
+         * First device setup ?
+         */
+        if (!td->evtdev) {
+                /*
+                 * If no cpu took the do_timer update, assign it to
+                 * this cpu:
+                 */
+                if (tick_do_timer_cpu == -1) {
+                        tick_do_timer_cpu = cpu;
+                        tick_next_period = ktime_get();
+                        tick_period = ktime_set(0, NSEC_PER_SEC / HZ);
+                }
+
+                /*
+                 * Startup in periodic mode first.
+                 */
+                td->mode = TICKDEV_MODE_PERIODIC;
+        } else {
+                handler = td->evtdev->event_handler;
+                next_event = td->evtdev->next_event;
+        }
+
+        td->evtdev = newdev;
+
+        /*
+         * When the device is not per cpu, pin the interrupt to the
+         * current cpu:
+         */
+        if (!cpus_equal(newdev->cpumask, cpumask))
+                irq_set_affinity(newdev->irq, cpumask);
+
+        /*
+         * When global broadcasting is active, check if the current
+         * device is registered as a placeholder for broadcast mode.
+         * This allows us to handle this x86 misfeature in a generic
+         * way.
+         */
+        if (tick_device_uses_broadcast(newdev, cpu))
+                return;
+
+        if (td->mode == TICKDEV_MODE_PERIODIC)
+                tick_setup_periodic(newdev, 0);
+        else
+                tick_setup_oneshot(newdev, handler, next_event);
+}
+
+/*
+ * Check, if the new registered device should be used.
+ */
+static int tick_check_new_device(struct clock_event_device *newdev)
+{
+        struct clock_event_device *curdev;
+        struct tick_device *td;
+        int cpu, ret = NOTIFY_OK;
+        unsigned long flags;
+        cpumask_t cpumask;
+
+        spin_lock_irqsave(&tick_device_lock, flags);
+
+        cpu = smp_processor_id();
+        if (!cpu_isset(cpu, newdev->cpumask))
+                goto out;
+
+        td = &per_cpu(tick_cpu_device, cpu);
+        curdev = td->evtdev;
+        cpumask = cpumask_of_cpu(cpu);
+
+        /* cpu local device ? */
+        if (!cpus_equal(newdev->cpumask, cpumask)) {
+
+                /*
+                 * If the cpu affinity of the device interrupt can not
+                 * be set, ignore it.
+                 */
+                if (!irq_can_set_affinity(newdev->irq))
+                        goto out_bc;
+
+                /*
+                 * If we have a cpu local device already, do not replace it
+                 * by a non cpu local device
+                 */
+                if (curdev && cpus_equal(curdev->cpumask, cpumask))
+                        goto out_bc;
+        }
+
+        /*
+         * If we have an active device, then check the rating and the oneshot
+         * feature.
+         */
+        if (curdev) {
+                /*
+                 * Prefer one shot capable devices !
+                 */
+                if ((curdev->features & CLOCK_EVT_FEAT_ONESHOT) &&
+                    !(newdev->features & CLOCK_EVT_FEAT_ONESHOT))
+                        goto out_bc;
+                /*
+                 * Check the rating
+                 */
+                if (curdev->rating >= newdev->rating)
+                        goto out_bc;
+        }
+
+        /*
+         * Replace the eventually existing device by the new
+         * device. If the current device is the broadcast device, do
+         * not give it back to the clockevents layer !
+         */
+        if (tick_is_broadcast_device(curdev)) {
+                clockevents_set_mode(curdev, CLOCK_EVT_MODE_SHUTDOWN);
+                curdev = NULL;
+        }
+        clockevents_exchange_device(curdev, newdev);
+        tick_setup_device(td, newdev, cpu, cpumask);
+        if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
+                tick_oneshot_notify();
+
+        spin_unlock_irqrestore(&tick_device_lock, flags);
+        return NOTIFY_STOP;
+
+out_bc:
+        /*
+         * Can the new device be used as a broadcast device ?
+         */
+        if (tick_check_broadcast_device(newdev))
+                ret = NOTIFY_STOP;
+out:
+        spin_unlock_irqrestore(&tick_device_lock, flags);
+
+        return ret;
+}
+
+/*
+ * Shutdown an event device on a given cpu:
+ *
+ * This is called on a life CPU, when a CPU is dead. So we cannot
+ * access the hardware device itself.
+ * We just set the mode and remove it from the lists.
+ */
+static void tick_shutdown(unsigned int *cpup)
+{
+        struct tick_device *td = &per_cpu(tick_cpu_device, *cpup);
+        struct clock_event_device *dev = td->evtdev;
+        unsigned long flags;
+
+        spin_lock_irqsave(&tick_device_lock, flags);
+        td->mode = TICKDEV_MODE_PERIODIC;
+        if (dev) {
+                /*
+                 * Prevent that the clock events layer tries to call
+                 * the set mode function!
+                 */
+                dev->mode = CLOCK_EVT_MODE_UNUSED;
+                clockevents_exchange_device(dev, NULL);
+                td->evtdev = NULL;
+        }
+        spin_unlock_irqrestore(&tick_device_lock, flags);
+}
+
+/*
+ * Notification about clock event devices
+ */
+static int tick_notify(struct notifier_block *nb, unsigned long reason,
+                               void *dev)
+{
+        switch (reason) {
+
+        case CLOCK_EVT_NOTIFY_ADD:
+                return tick_check_new_device(dev);
+
+        case CLOCK_EVT_NOTIFY_BROADCAST_ON:
+        case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
+                tick_broadcast_on_off(reason, dev);
+                break;
+
+        case CLOCK_EVT_NOTIFY_BROADCAST_ENTER:
+        case CLOCK_EVT_NOTIFY_BROADCAST_EXIT:
+                tick_broadcast_oneshot_control(reason);
+                break;
+
+        case CLOCK_EVT_NOTIFY_CPU_DEAD:
+                tick_shutdown_broadcast_oneshot(dev);
+                tick_shutdown_broadcast(dev);
+                tick_shutdown(dev);
+                break;
+
+        default:
+                break;
+        }
+
+        return NOTIFY_OK;
+}
+
+static struct notifier_block tick_notifier = {
+        .notifier_call = tick_notify,
+};
+
+/**
+ * tick_init - initialize the tick control
+ *
+ * Register the notifier with the clockevents framework
+ */
+void __init tick_init(void)
+{
+        clockevents_register_notifier(&tick_notifier);
+}
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
new file mode 100644
index 000000000000..54861a0f29ff
--- /dev/null
+++ b/kernel/time/tick-internal.h
@@ -0,0 +1,110 @@
+/*
+ * tick internal variable and functions used by low/high res code
+ */
+DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
+extern spinlock_t tick_device_lock;
+extern ktime_t tick_next_period;
+extern ktime_t tick_period;
+
+extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast);
+extern void tick_handle_periodic(struct clock_event_device *dev);
+
+/*
+ * NO_HZ / high resolution timer shared code
+ */
+#ifdef CONFIG_TICK_ONESHOT
+extern void tick_setup_oneshot(struct clock_event_device *newdev,
+                               void (*handler)(struct clock_event_device *),
+                               ktime_t nextevt);
+extern int tick_program_event(ktime_t expires, int force);
+extern void tick_oneshot_notify(void);
+extern int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *));
+
+# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+extern void tick_broadcast_setup_oneshot(struct clock_event_device *bc);
+extern void tick_broadcast_oneshot_control(unsigned long reason);
+extern void tick_broadcast_switch_to_oneshot(void);
+extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
+# else /* BROADCAST */
+static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
+{
+        BUG();
+}
+static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
+static inline void tick_broadcast_switch_to_oneshot(void) { }
+static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
+# endif /* !BROADCAST */
+
+#else /* !ONESHOT */
+static inline
+void tick_setup_oneshot(struct clock_event_device *newdev,
+                        void (*handler)(struct clock_event_device *),
+                        ktime_t nextevt)
+{
+        BUG();
+}
+static inline int tick_program_event(ktime_t expires, int force)
+{
+        return 0;
+}
+static inline void tick_oneshot_notify(void) { }
+static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
+{
+        BUG();
+}
+static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
+static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
+#endif /* !TICK_ONESHOT */
+
+/*
+ * Broadcasting support
+ */
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+extern int tick_do_broadcast(cpumask_t mask);
+
+extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu);
+extern int tick_check_broadcast_device(struct clock_event_device *dev);
+extern int tick_is_broadcast_device(struct clock_event_device *dev);
+extern void tick_broadcast_on_off(unsigned long reason, int *oncpu);
+extern void tick_shutdown_broadcast(unsigned int *cpup);
+
+extern void
+tick_set_periodic_handler(struct clock_event_device *dev, int broadcast);
+
+#else /* !BROADCAST */
+
+static inline int tick_check_broadcast_device(struct clock_event_device *dev)
+{
+        return 0;
+}
+
+static inline int tick_is_broadcast_device(struct clock_event_device *dev)
+{
+        return 0;
+}
+static inline int tick_device_uses_broadcast(struct clock_event_device *dev,
+                                             int cpu)
+{
+        return 0;
+}
+static inline void tick_do_periodic_broadcast(struct clock_event_device *d) { }
+static inline void tick_broadcast_on_off(unsigned long reason, int *oncpu) { }
+static inline void tick_shutdown_broadcast(unsigned int *cpup) { }
+
+/*
+ * Set the periodic handler in non broadcast mode
+ */
+static inline void tick_set_periodic_handler(struct clock_event_device *dev,
+                                             int broadcast)
+{
+        dev->event_handler = tick_handle_periodic;
+}
+#endif /* !BROADCAST */
+
+/*
+ * Check, if the device is functional or a dummy for broadcast
+ */
+static inline int tick_device_is_functional(struct clock_event_device *dev)
+{
+        return !(dev->features & CLOCK_EVT_FEAT_DUMMY);
+}
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
new file mode 100644
index 000000000000..2e8b7ff863cc
--- /dev/null
+++ b/kernel/time/tick-oneshot.c
@@ -0,0 +1,84 @@
+/*
+ * linux/kernel/time/tick-oneshot.c
+ *
+ * This file contains functions which manage high resolution tick
+ * related events.
+ *
+ * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
+ * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
+ * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
+ *
+ * This code is licenced under the GPL version 2. For details see
+ * kernel-base/COPYING.
+ */
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/irq.h>
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/sched.h>
+#include <linux/tick.h>
+
+#include "tick-internal.h"
+
+/**
+ * tick_program_event
+ */
+int tick_program_event(ktime_t expires, int force)
+{
+        struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
+        ktime_t now = ktime_get();
+
+        while (1) {
+                int ret = clockevents_program_event(dev, expires, now);
+
+                if (!ret || !force)
+                        return ret;
+                now = ktime_get();
+                expires = ktime_add(now, ktime_set(0, dev->min_delta_ns));
+        }
+}
+
+/**
+ * tick_setup_oneshot - setup the event device for oneshot mode (hres or nohz)
+ */
+void tick_setup_oneshot(struct clock_event_device *newdev,
+                        void (*handler)(struct clock_event_device *),
+                        ktime_t next_event)
+{
+        newdev->event_handler = handler;
+        clockevents_set_mode(newdev, CLOCK_EVT_MODE_ONESHOT);
+        clockevents_program_event(newdev, next_event, ktime_get());
+}
+
+/**
+ * tick_switch_to_oneshot - switch to oneshot mode
+ */
+int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *))
+{
+        struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+        struct clock_event_device *dev = td->evtdev;
+
+        if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT) ||
+            !tick_device_is_functional(dev))
+                return -EINVAL;
+
+        td->mode = TICKDEV_MODE_ONESHOT;
+        dev->event_handler = handler;
+        clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
+        tick_broadcast_switch_to_oneshot();
+        return 0;
+}
+
+#ifdef CONFIG_HIGH_RES_TIMERS
+/**
+ * tick_init_highres - switch to high resolution mode
+ *
+ * Called with interrupts disabled.
+ */
+int tick_init_highres(void)
+{
+        return tick_switch_to_oneshot(hrtimer_interrupt);
+}
+#endif
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
new file mode 100644
index 000000000000..95e41f7f850b
--- /dev/null
+++ b/kernel/time/tick-sched.c
@@ -0,0 +1,563 @@
+/*
+ *  linux/kernel/time/tick-sched.c
+ *
+ *  Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
+ *  Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
+ *  Copyright(C) 2006-2007  Timesys Corp., Thomas Gleixner
+ *
+ *  No idle tick implementation for low and high resolution timers
+ *
+ *  Started by: Thomas Gleixner and Ingo Molnar
+ *
+ *  For licencing details see kernel-base/COPYING
+ */
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
+#include <linux/kernel_stat.h>
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/sched.h>
+#include <linux/tick.h>
+
+#include "tick-internal.h"
+
+/*
+ * Per cpu nohz control structure
+ */
+static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched);
+
+/*
+ * The time, when the last jiffy update happened. Protected by xtime_lock.
+ */
+static ktime_t last_jiffies_update;
+
+struct tick_sched *tick_get_tick_sched(int cpu)
+{
+        return &per_cpu(tick_cpu_sched, cpu);
+}
+
+/*
+ * Must be called with interrupts disabled !
+ */
+static void tick_do_update_jiffies64(ktime_t now)
+{
+        unsigned long ticks = 0;
+        ktime_t delta;
+
+        /* Reevalute with xtime_lock held */
+        write_seqlock(&xtime_lock);
+
+        delta = ktime_sub(now, last_jiffies_update);
+        if (delta.tv64 >= tick_period.tv64) {
+
+                delta = ktime_sub(delta, tick_period);
+                last_jiffies_update = ktime_add(last_jiffies_update,
+                                                tick_period);
+
+                /* Slow path for long timeouts */
+                if (unlikely(delta.tv64 >= tick_period.tv64)) {
+                        s64 incr = ktime_to_ns(tick_period);
+
+                        ticks = ktime_divns(delta, incr);
+
+                        last_jiffies_update = ktime_add_ns(last_jiffies_update,
+                                                           incr * ticks);
+                }
+                do_timer(++ticks);
+        }
+        write_sequnlock(&xtime_lock);
+}
+
+/*
+ * Initialize and return retrieve the jiffies update.
+ */
+static ktime_t tick_init_jiffy_update(void)
+{
+        ktime_t period;
+
+        write_seqlock(&xtime_lock);
+        /* Did we start the jiffies update yet ? */
+        if (last_jiffies_update.tv64 == 0)
+                last_jiffies_update = tick_next_period;
+        period = last_jiffies_update;
+        write_sequnlock(&xtime_lock);
+        return period;
+}
+
+/*
+ * NOHZ - aka dynamic tick functionality
+ */
+#ifdef CONFIG_NO_HZ
+/*
+ * NO HZ enabled ?
+ */
+static int tick_nohz_enabled __read_mostly  = 1;
+
+/*
+ * Enable / Disable tickless mode
+ */
+static int __init setup_tick_nohz(char *str)
+{
+        if (!strcmp(str, "off"))
+                tick_nohz_enabled = 0;
+        else if (!strcmp(str, "on"))
+                tick_nohz_enabled = 1;
+        else
+                return 0;
+        return 1;
+}
+
+__setup("nohz=", setup_tick_nohz);
+
+/**
+ * tick_nohz_update_jiffies - update jiffies when idle was interrupted
+ *
+ * Called from interrupt entry when the CPU was idle
+ *
+ * In case the sched_tick was stopped on this CPU, we have to check if jiffies
+ * must be updated. Otherwise an interrupt handler could use a stale jiffy
+ * value. We do this unconditionally on any cpu, as we don't know whether the
+ * cpu, which has the update task assigned is in a long sleep.
+ */
+void tick_nohz_update_jiffies(void)
+{
+        int cpu = smp_processor_id();
+        struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+        unsigned long flags;
+        ktime_t now;
+
+        if (!ts->tick_stopped)
+                return;
+
+        cpu_clear(cpu, nohz_cpu_mask);
+        now = ktime_get();
+
+        local_irq_save(flags);
+        tick_do_update_jiffies64(now);
+        local_irq_restore(flags);
+}
+
+/**
+ * tick_nohz_stop_sched_tick - stop the idle tick from the idle task
+ *
+ * When the next event is more than a tick into the future, stop the idle tick
+ * Called either from the idle loop or from irq_exit() when an idle period was
+ * just interrupted by an interrupt which did not cause a reschedule.
+ */
+void tick_nohz_stop_sched_tick(void)
+{
+        unsigned long seq, last_jiffies, next_jiffies, delta_jiffies, flags;
+        struct tick_sched *ts;
+        ktime_t last_update, expires, now, delta;
+        int cpu;
+
+        local_irq_save(flags);
+
+        cpu = smp_processor_id();
+        ts = &per_cpu(tick_cpu_sched, cpu);
+
+        if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
+                goto end;
+
+        if (need_resched())
+                goto end;
+
+        cpu = smp_processor_id();
+        BUG_ON(local_softirq_pending());
+
+        now = ktime_get();
+        /*
+         * When called from irq_exit we need to account the idle sleep time
+         * correctly.
+         */
+        if (ts->tick_stopped) {
+                delta = ktime_sub(now, ts->idle_entrytime);
+                ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+        }
+
+        ts->idle_entrytime = now;
+        ts->idle_calls++;
+
+        /* Read jiffies and the time when jiffies were updated last */
+        do {
+                seq = read_seqbegin(&xtime_lock);
+                last_update = last_jiffies_update;
+                last_jiffies = jiffies;
+        } while (read_seqretry(&xtime_lock, seq));
+
+        /* Get the next timer wheel timer */
+        next_jiffies = get_next_timer_interrupt(last_jiffies);
+        delta_jiffies = next_jiffies - last_jiffies;
+
+        /*
+         * Do not stop the tick, if we are only one off
+         * or if the cpu is required for rcu
+         */
+        if (!ts->tick_stopped && (delta_jiffies == 1 || rcu_needs_cpu(cpu)))
+                goto out;
+
+        /* Schedule the tick, if we are at least one jiffie off */
+        if ((long)delta_jiffies >= 1) {
+
+                if (rcu_needs_cpu(cpu))
+                        delta_jiffies = 1;
+                else
+                        cpu_set(cpu, nohz_cpu_mask);
+                /*
+                 * nohz_stop_sched_tick can be called several times before
+                 * the nohz_restart_sched_tick is called. This happens when
+                 * interrupts arrive which do not cause a reschedule. In the
+                 * first call we save the current tick time, so we can restart
+                 * the scheduler tick in nohz_restart_sched_tick.
+                 */
+                if (!ts->tick_stopped) {
+                        ts->idle_tick = ts->sched_timer.expires;
+                        ts->tick_stopped = 1;
+                        ts->idle_jiffies = last_jiffies;
+                }
+                /*
+                 * calculate the expiry time for the next timer wheel
+                 * timer
+                 */
+                expires = ktime_add_ns(last_update, tick_period.tv64 *
+                                       delta_jiffies);
+                ts->idle_expires = expires;
+                ts->idle_sleeps++;
+
+                if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
+                        hrtimer_start(&ts->sched_timer, expires,
+                                      HRTIMER_MODE_ABS);
+                        /* Check, if the timer was already in the past */
+                        if (hrtimer_active(&ts->sched_timer))
+                                goto out;
+                } else if(!tick_program_event(expires, 0))
+                                goto out;
+                /*
+                 * We are past the event already. So we crossed a
+                 * jiffie boundary. Update jiffies and raise the
+                 * softirq.
+                 */
+                tick_do_update_jiffies64(ktime_get());
+                cpu_clear(cpu, nohz_cpu_mask);
+        }
+        raise_softirq_irqoff(TIMER_SOFTIRQ);
+out:
+        ts->next_jiffies = next_jiffies;
+        ts->last_jiffies = last_jiffies;
+end:
+        local_irq_restore(flags);
+}
+
+/**
+ * nohz_restart_sched_tick - restart the idle tick from the idle task
+ *
+ * Restart the idle tick when the CPU is woken up from idle
+ */
+void tick_nohz_restart_sched_tick(void)
+{
+        int cpu = smp_processor_id();
+        struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+        unsigned long ticks;
+        ktime_t now, delta;
+
+        if (!ts->tick_stopped)
+                return;
+
+        /* Update jiffies first */
+        now = ktime_get();
+
+        local_irq_disable();
+        tick_do_update_jiffies64(now);
+        cpu_clear(cpu, nohz_cpu_mask);
+
+        /* Account the idle time */
+        delta = ktime_sub(now, ts->idle_entrytime);
+        ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+
+        /*
+         * We stopped the tick in idle. Update process times would miss the
+         * time we slept as update_process_times does only a 1 tick
+         * accounting. Enforce that this is accounted to idle !
+         */
+        ticks = jiffies - ts->idle_jiffies;
+        /*
+         * We might be one off. Do not randomly account a huge number of ticks!
+         */
+        if (ticks && ticks < LONG_MAX) {
+                add_preempt_count(HARDIRQ_OFFSET);
+                account_system_time(current, HARDIRQ_OFFSET,
+                                    jiffies_to_cputime(ticks));
+                sub_preempt_count(HARDIRQ_OFFSET);
+        }
+
+        /*
+         * Cancel the scheduled timer and restore the tick
+         */
+        ts->tick_stopped  = 0;
+        hrtimer_cancel(&ts->sched_timer);
+        ts->sched_timer.expires = ts->idle_tick;
+
+        while (1) {
+                /* Forward the time to expire in the future */
+                hrtimer_forward(&ts->sched_timer, now, tick_period);
+
+                if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
+                        hrtimer_start(&ts->sched_timer,
+                                      ts->sched_timer.expires,
+                                      HRTIMER_MODE_ABS);
+                        /* Check, if the timer was already in the past */
+                        if (hrtimer_active(&ts->sched_timer))
+                                break;
+                } else {
+                        if (!tick_program_event(ts->sched_timer.expires, 0))
+                                break;
+                }
+                /* Update jiffies and reread time */
+                tick_do_update_jiffies64(now);
+                now = ktime_get();
+        }
+        local_irq_enable();
+}
+
+static int tick_nohz_reprogram(struct tick_sched *ts, ktime_t now)
+{
+        hrtimer_forward(&ts->sched_timer, now, tick_period);
+        return tick_program_event(ts->sched_timer.expires, 0);
+}
+
+/*
+ * The nohz low res interrupt handler
+ */
+static void tick_nohz_handler(struct clock_event_device *dev)
+{
+        struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+        struct pt_regs *regs = get_irq_regs();
+        ktime_t now = ktime_get();
+
+        dev->next_event.tv64 = KTIME_MAX;
+
+        /* Check, if the jiffies need an update */
+        tick_do_update_jiffies64(now);
+
+        /*
+         * When we are idle and the tick is stopped, we have to touch
+         * the watchdog as we might not schedule for a really long
+         * time. This happens on complete idle SMP systems while
+         * waiting on the login prompt. We also increment the "start
+         * of idle" jiffy stamp so the idle accounting adjustment we
+         * do when we go busy again does not account too much ticks.
+         */
+        if (ts->tick_stopped) {
+                touch_softlockup_watchdog();
+                ts->idle_jiffies++;
+        }
+
+        update_process_times(user_mode(regs));
+        profile_tick(CPU_PROFILING);
+
+        /* Do not restart, when we are in the idle loop */
+        if (ts->tick_stopped)
+                return;
+
+        while (tick_nohz_reprogram(ts, now)) {
+                now = ktime_get();
+                tick_do_update_jiffies64(now);
+        }
+}
+
+/**
+ * tick_nohz_switch_to_nohz - switch to nohz mode
+ */
+static void tick_nohz_switch_to_nohz(void)
+{
+        struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+        ktime_t next;
+
+        if (!tick_nohz_enabled)
+                return;
+
+        local_irq_disable();
+        if (tick_switch_to_oneshot(tick_nohz_handler)) {
+                local_irq_enable();
+                return;
+        }
+
+        ts->nohz_mode = NOHZ_MODE_LOWRES;
+
+        /*
+         * Recycle the hrtimer in ts, so we can share the
+         * hrtimer_forward with the highres code.
+         */
+        hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+        /* Get the next period */
+        next = tick_init_jiffy_update();
+
+        for (;;) {
+                ts->sched_timer.expires = next;
+                if (!tick_program_event(next, 0))
+                        break;
+                next = ktime_add(next, tick_period);
+        }
+        local_irq_enable();
+
+        printk(KERN_INFO "Switched to NOHz mode on CPU #%d\n",
+               smp_processor_id());
+}
+
+#else
+
+static inline void tick_nohz_switch_to_nohz(void) { }
+
+#endif /* NO_HZ */
+
+/*
+ * High resolution timer specific code
+ */
+#ifdef CONFIG_HIGH_RES_TIMERS
+/*
+ * We rearm the timer until we get disabled by the idle code
+ * Called with interrupts disabled and timer->base->cpu_base->lock held.
+ */
+static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
+{
+        struct tick_sched *ts =
+                container_of(timer, struct tick_sched, sched_timer);
+        struct hrtimer_cpu_base *base = timer->base->cpu_base;
+        struct pt_regs *regs = get_irq_regs();
+        ktime_t now = ktime_get();
+
+        /* Check, if the jiffies need an update */
+        tick_do_update_jiffies64(now);
+
+        /*
+         * Do not call, when we are not in irq context and have
+         * no valid regs pointer
+         */
+        if (regs) {
+                /*
+                 * When we are idle and the tick is stopped, we have to touch
+                 * the watchdog as we might not schedule for a really long
+                 * time. This happens on complete idle SMP systems while
+                 * waiting on the login prompt. We also increment the "start of
+                 * idle" jiffy stamp so the idle accounting adjustment we do
+                 * when we go busy again does not account too much ticks.
+                 */
+                if (ts->tick_stopped) {
+                        touch_softlockup_watchdog();
+                        ts->idle_jiffies++;
+                }
+                /*
+                 * update_process_times() might take tasklist_lock, hence
+                 * drop the base lock. sched-tick hrtimers are per-CPU and
+                 * never accessible by userspace APIs, so this is safe to do.
+                 */
+                spin_unlock(&base->lock);
+                update_process_times(user_mode(regs));
+                profile_tick(CPU_PROFILING);
+                spin_lock(&base->lock);
+        }
+
+        /* Do not restart, when we are in the idle loop */
+        if (ts->tick_stopped)
+                return HRTIMER_NORESTART;
+
+        hrtimer_forward(timer, now, tick_period);
+
+        return HRTIMER_RESTART;
+}
+
+/**
+ * tick_setup_sched_timer - setup the tick emulation timer
+ */
+void tick_setup_sched_timer(void)
+{
+        struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+        ktime_t now = ktime_get();
+
+        /*
+         * Emulate tick processing via per-CPU hrtimers:
+         */
+        hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+        ts->sched_timer.function = tick_sched_timer;
+        ts->sched_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ;
+
+        /* Get the next period */
+        ts->sched_timer.expires = tick_init_jiffy_update();
+
+        for (;;) {
+                hrtimer_forward(&ts->sched_timer, now, tick_period);
+                hrtimer_start(&ts->sched_timer, ts->sched_timer.expires,
+                              HRTIMER_MODE_ABS);
+                /* Check, if the timer was already in the past */
+                if (hrtimer_active(&ts->sched_timer))
+                        break;
+                now = ktime_get();
+        }
+
+#ifdef CONFIG_NO_HZ
+        if (tick_nohz_enabled)
+                ts->nohz_mode = NOHZ_MODE_HIGHRES;
+#endif
+}
+
+void tick_cancel_sched_timer(int cpu)
+{
+        struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+
+        if (ts->sched_timer.base)
+                hrtimer_cancel(&ts->sched_timer);
+        ts->tick_stopped = 0;
+        ts->nohz_mode = NOHZ_MODE_INACTIVE;
+}
+#endif /* HIGH_RES_TIMERS */
+
+/**
+ * Async notification about clocksource changes
+ */
+void tick_clock_notify(void)
+{
+        int cpu;
+
+        for_each_possible_cpu(cpu)
+                set_bit(0, &per_cpu(tick_cpu_sched, cpu).check_clocks);
+}
+
+/*
+ * Async notification about clock event changes
+ */
+void tick_oneshot_notify(void)
+{
+        struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+
+        set_bit(0, &ts->check_clocks);
+}
+
+/**
+ * Check, if a change happened, which makes oneshot possible.
+ *
+ * Called cyclic from the hrtimer softirq (driven by the timer
+ * softirq) allow_nohz signals, that we can switch into low-res nohz
+ * mode, because high resolution timers are disabled (either compile
+ * or runtime).
+ */
+int tick_check_oneshot_change(int allow_nohz)
+{
+        struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+
+        if (!test_and_clear_bit(0, &ts->check_clocks))
+                return 0;
+
+        if (ts->nohz_mode != NOHZ_MODE_INACTIVE)
+                return 0;
+
+        if (!timekeeping_is_continuous() || !tick_is_oneshot_available())
+                return 0;
+
+        if (!allow_nohz)
+                return 1;
+
+        tick_nohz_switch_to_nohz();
+        return 0;
+}
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
new file mode 100644
index 000000000000..f82c635c3d5c
--- /dev/null
+++ b/kernel/time/timer_list.c
@@ -0,0 +1,287 @@
+/*
+ * kernel/time/timer_list.c
+ *
+ * List pending timers
+ *
+ * Copyright(C) 2006, Red Hat, Inc., Ingo Molnar
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/proc_fs.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/kallsyms.h>
+#include <linux/tick.h>
+
+#include <asm/uaccess.h>
+
+typedef void (*print_fn_t)(struct seq_file *m, unsigned int *classes);
+
+DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases);
+
+/*
+ * This allows printing both to /proc/timer_list and
+ * to the console (on SysRq-Q):
+ */
+#define SEQ_printf(m, x...)                     \
+ do {                                           \
+        if (m)                                  \
+                seq_printf(m, x);               \
+        else                                    \
+                printk(x);                      \
+ } while (0)
+
+static void print_name_offset(struct seq_file *m, void *sym)
+{
+        unsigned long addr = (unsigned long)sym;
+        char namebuf[KSYM_NAME_LEN+1];
+        unsigned long size, offset;
+        const char *sym_name;
+        char *modname;
+
+        sym_name = kallsyms_lookup(addr, &size, &offset, &modname, namebuf);
+        if (sym_name)
+                SEQ_printf(m, "%s", sym_name);
+        else
+                SEQ_printf(m, "<%p>", sym);
+}
+
+static void
+print_timer(struct seq_file *m, struct hrtimer *timer, int idx, u64 now)
+{
+#ifdef CONFIG_TIMER_STATS
+        char tmp[TASK_COMM_LEN + 1];
+#endif
+        SEQ_printf(m, " #%d: ", idx);
+        print_name_offset(m, timer);
+        SEQ_printf(m, ", ");
+        print_name_offset(m, timer->function);
+        SEQ_printf(m, ", S:%02lx", timer->state);
+#ifdef CONFIG_TIMER_STATS
+        SEQ_printf(m, ", ");
+        print_name_offset(m, timer->start_site);
+        memcpy(tmp, timer->start_comm, TASK_COMM_LEN);
+        tmp[TASK_COMM_LEN] = 0;
+        SEQ_printf(m, ", %s/%d", tmp, timer->start_pid);
+#endif
+        SEQ_printf(m, "\n");
+        SEQ_printf(m, " # expires at %Ld nsecs [in %Ld nsecs]\n",
+                (unsigned long long)ktime_to_ns(timer->expires),
+                (unsigned long long)(ktime_to_ns(timer->expires) - now));
+}
+
+static void
+print_active_timers(struct seq_file *m, struct hrtimer_clock_base *base,
+                    u64 now)
+{
+        struct hrtimer *timer, tmp;
+        unsigned long next = 0, i;
+        struct rb_node *curr;
+        unsigned long flags;
+
+next_one:
+        i = 0;
+        spin_lock_irqsave(&base->cpu_base->lock, flags);
+
+        curr = base->first;
+        /*
+         * 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);
+                i++;
+        }
+
+        if (curr) {
+
+                timer = rb_entry(curr, struct hrtimer, node);
+                tmp = *timer;
+                spin_unlock_irqrestore(&base->cpu_base->lock, flags);
+
+                print_timer(m, &tmp, i, now);
+                next++;
+                goto next_one;
+        }
+        spin_unlock_irqrestore(&base->cpu_base->lock, flags);
+}
+
+static void
+print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now)
+{
+        SEQ_printf(m, "  .index:      %d\n",
+                        base->index);
+        SEQ_printf(m, "  .resolution: %Ld nsecs\n",
+                        (unsigned long long)ktime_to_ns(base->resolution));
+        SEQ_printf(m,   "  .get_time:   ");
+        print_name_offset(m, base->get_time);
+        SEQ_printf(m,   "\n");
+#ifdef CONFIG_HIGH_RES_TIMERS
+        SEQ_printf(m, "  .offset:     %Ld nsecs\n",
+                        ktime_to_ns(base->offset));
+#endif
+        SEQ_printf(m,   "active timers:\n");
+        print_active_timers(m, base, now);
+}
+
+static void print_cpu(struct seq_file *m, int cpu, u64 now)
+{
+        struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
+        int i;
+
+        SEQ_printf(m, "\ncpu: %d\n", cpu);
+        for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
+                SEQ_printf(m, " clock %d:\n", i);
+                print_base(m, cpu_base->clock_base + i, now);
+        }
+#define P(x) \
+        SEQ_printf(m, "  .%-15s: %Ld\n", #x, (u64)(cpu_base->x))
+#define P_ns(x) \
+        SEQ_printf(m, "  .%-15s: %Ld nsecs\n", #x, \
+                (u64)(ktime_to_ns(cpu_base->x)))
+
+#ifdef CONFIG_HIGH_RES_TIMERS
+        P_ns(expires_next);
+        P(hres_active);
+        P(nr_events);
+#endif
+#undef P
+#undef P_ns
+
+#ifdef CONFIG_TICK_ONESHOT
+# define P(x) \
+        SEQ_printf(m, "  .%-15s: %Ld\n", #x, (u64)(ts->x))
+# define P_ns(x) \
+        SEQ_printf(m, "  .%-15s: %Ld nsecs\n", #x, \
+                (u64)(ktime_to_ns(ts->x)))
+        {
+                struct tick_sched *ts = tick_get_tick_sched(cpu);
+                P(nohz_mode);
+                P_ns(idle_tick);
+                P(tick_stopped);
+                P(idle_jiffies);
+                P(idle_calls);
+                P(idle_sleeps);
+                P_ns(idle_entrytime);
+                P_ns(idle_sleeptime);
+                P(last_jiffies);
+                P(next_jiffies);
+                P_ns(idle_expires);
+                SEQ_printf(m, "jiffies: %Ld\n", (u64)jiffies);
+        }
+#endif
+
+#undef P
+#undef P_ns
+}
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
+static void
+print_tickdevice(struct seq_file *m, struct tick_device *td)
+{
+        struct clock_event_device *dev = td->evtdev;
+
+        SEQ_printf(m, "\nTick Device: mode:     %d\n", td->mode);
+
+        SEQ_printf(m, "Clock Event Device: ");
+        if (!dev) {
+                SEQ_printf(m, "<NULL>\n");
+                return;
+        }
+        SEQ_printf(m, "%s\n", dev->name);
+        SEQ_printf(m, " max_delta_ns:   %ld\n", dev->max_delta_ns);
+        SEQ_printf(m, " min_delta_ns:   %ld\n", dev->min_delta_ns);
+        SEQ_printf(m, " mult:           %ld\n", dev->mult);
+        SEQ_printf(m, " shift:          %d\n", dev->shift);
+        SEQ_printf(m, " mode:           %d\n", dev->mode);
+        SEQ_printf(m, " next_event:     %Ld nsecs\n",
+                   (unsigned long long) ktime_to_ns(dev->next_event));
+
+        SEQ_printf(m, " set_next_event: ");
+        print_name_offset(m, dev->set_next_event);
+        SEQ_printf(m, "\n");
+
+        SEQ_printf(m, " set_mode:       ");
+        print_name_offset(m, dev->set_mode);
+        SEQ_printf(m, "\n");
+
+        SEQ_printf(m, " event_handler:  ");
+        print_name_offset(m, dev->event_handler);
+        SEQ_printf(m, "\n");
+}
+
+static void timer_list_show_tickdevices(struct seq_file *m)
+{
+        int cpu;
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+        print_tickdevice(m, tick_get_broadcast_device());
+        SEQ_printf(m, "tick_broadcast_mask: %08lx\n",
+                   tick_get_broadcast_mask()->bits[0]);
+#ifdef CONFIG_TICK_ONESHOT
+        SEQ_printf(m, "tick_broadcast_oneshot_mask: %08lx\n",
+                   tick_get_broadcast_oneshot_mask()->bits[0]);
+#endif
+        SEQ_printf(m, "\n");
+#endif
+        for_each_online_cpu(cpu)
+                   print_tickdevice(m, tick_get_device(cpu));
+        SEQ_printf(m, "\n");
+}
+#else
+static void timer_list_show_tickdevices(struct seq_file *m) { }
+#endif
+
+static int timer_list_show(struct seq_file *m, void *v)
+{
+        u64 now = ktime_to_ns(ktime_get());
+        int cpu;
+
+        SEQ_printf(m, "Timer List Version: v0.3\n");
+        SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES);
+        SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now);
+
+        for_each_online_cpu(cpu)
+                print_cpu(m, cpu, now);
+
+        SEQ_printf(m, "\n");
+        timer_list_show_tickdevices(m);
+
+        return 0;
+}
+
+void sysrq_timer_list_show(void)
+{
+        timer_list_show(NULL, NULL);
+}
+
+static int timer_list_open(struct inode *inode, struct file *filp)
+{
+        return single_open(filp, timer_list_show, NULL);
+}
+
+static struct file_operations timer_list_fops = {
+        .open           = timer_list_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = seq_release,
+};
+
+static int __init init_timer_list_procfs(void)
+{
+        struct proc_dir_entry *pe;
+
+        pe = create_proc_entry("timer_list", 0644, NULL);
+        if (!pe)
+                return -ENOMEM;
+
+        pe->proc_fops = &timer_list_fops;
+
+        return 0;
+}
+__initcall(init_timer_list_procfs);
diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c
new file mode 100644
index 000000000000..1bc4882e28e0
--- /dev/null
+++ b/kernel/time/timer_stats.c
@@ -0,0 +1,411 @@
+/*
+ * kernel/time/timer_stats.c
+ *
+ * Collect timer usage statistics.
+ *
+ * Copyright(C) 2006, Red Hat, Inc., Ingo Molnar
+ * Copyright(C) 2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com>
+ *
+ * timer_stats is based on timer_top, a similar functionality which was part of
+ * Con Kolivas dyntick patch set. It was developed by Daniel Petrini at the
+ * Instituto Nokia de Tecnologia - INdT - Manaus. timer_top's design was based
+ * on dynamic allocation of the statistics entries and linear search based
+ * lookup combined with a global lock, rather than the static array, hash
+ * and per-CPU locking which is used by timer_stats. It was written for the
+ * pre hrtimer kernel code and therefore did not take hrtimers into account.
+ * Nevertheless it provided the base for the timer_stats implementation and
+ * was a helpful source of inspiration. Kudos to Daniel and the Nokia folks
+ * for this effort.
+ *
+ * timer_top.c is
+ *      Copyright (C) 2005 Instituto Nokia de Tecnologia - INdT - Manaus
+ *      Written by Daniel Petrini <d.pensator@gmail.com>
+ *      timer_top.c was released under the GNU General Public License version 2
+ *
+ * We export the addresses and counting of timer functions being called,
+ * the pid and cmdline from the owner process if applicable.
+ *
+ * Start/stop data collection:
+ * # echo 1[0] >/proc/timer_stats
+ *
+ * Display the information collected so far:
+ * # cat /proc/timer_stats
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/proc_fs.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/kallsyms.h>
+
+#include <asm/uaccess.h>
+
+/*
+ * This is our basic unit of interest: a timer expiry event identified
+ * by the timer, its start/expire functions and the PID of the task that
+ * started the timer. We count the number of times an event happens:
+ */
+struct entry {
+        /*
+         * Hash list:
+         */
+        struct entry            *next;
+
+        /*
+         * Hash keys:
+         */
+        void                    *timer;
+        void                    *start_func;
+        void                    *expire_func;
+        pid_t                   pid;
+
+        /*
+         * Number of timeout events:
+         */
+        unsigned long           count;
+
+        /*
+         * We save the command-line string to preserve
+         * this information past task exit:
+         */
+        char                    comm[TASK_COMM_LEN + 1];
+
+} ____cacheline_aligned_in_smp;
+
+/*
+ * Spinlock protecting the tables - not taken during lookup:
+ */
+static DEFINE_SPINLOCK(table_lock);
+
+/*
+ * Per-CPU lookup locks for fast hash lookup:
+ */
+static DEFINE_PER_CPU(spinlock_t, lookup_lock);
+
+/*
+ * Mutex to serialize state changes with show-stats activities:
+ */
+static DEFINE_MUTEX(show_mutex);
+
+/*
+ * Collection status, active/inactive:
+ */
+static int __read_mostly active;
+
+/*
+ * Beginning/end timestamps of measurement:
+ */
+static ktime_t time_start, time_stop;
+
+/*
+ * tstat entry structs only get allocated while collection is
+ * active and never freed during that time - this simplifies
+ * things quite a bit.
+ *
+ * They get freed when a new collection period is started.
+ */
+#define MAX_ENTRIES_BITS        10
+#define MAX_ENTRIES             (1UL << MAX_ENTRIES_BITS)
+
+static unsigned long nr_entries;
+static struct entry entries[MAX_ENTRIES];
+
+static atomic_t overflow_count;
+
+static void reset_entries(void)
+{
+        nr_entries = 0;
+        memset(entries, 0, sizeof(entries));
+        atomic_set(&overflow_count, 0);
+}
+
+static struct entry *alloc_entry(void)
+{
+        if (nr_entries >= MAX_ENTRIES)
+                return NULL;
+
+        return entries + nr_entries++;
+}
+
+/*
+ * The entries are in a hash-table, for fast lookup:
+ */
+#define TSTAT_HASH_BITS         (MAX_ENTRIES_BITS - 1)
+#define TSTAT_HASH_SIZE         (1UL << TSTAT_HASH_BITS)
+#define TSTAT_HASH_MASK         (TSTAT_HASH_SIZE - 1)
+
+#define __tstat_hashfn(entry)                                           \
+        (((unsigned long)(entry)->timer       ^                         \
+          (unsigned long)(entry)->start_func  ^                         \
+          (unsigned long)(entry)->expire_func ^                         \
+          (unsigned long)(entry)->pid           ) & TSTAT_HASH_MASK)
+
+#define tstat_hashentry(entry)  (tstat_hash_table + __tstat_hashfn(entry))
+
+static struct entry *tstat_hash_table[TSTAT_HASH_SIZE] __read_mostly;
+
+static int match_entries(struct entry *entry1, struct entry *entry2)
+{
+        return entry1->timer       == entry2->timer       &&
+               entry1->start_func  == entry2->start_func  &&
+               entry1->expire_func == entry2->expire_func &&
+               entry1->pid         == entry2->pid;
+}
+
+/*
+ * Look up whether an entry matching this item is present
+ * in the hash already. Must be called with irqs off and the
+ * lookup lock held:
+ */
+static struct entry *tstat_lookup(struct entry *entry, char *comm)
+{
+        struct entry **head, *curr, *prev;
+
+        head = tstat_hashentry(entry);
+        curr = *head;
+
+        /*
+         * The fastpath is when the entry is already hashed,
+         * we do this with the lookup lock held, but with the
+         * table lock not held:
+         */
+        while (curr) {
+                if (match_entries(curr, entry))
+                        return curr;
+
+                curr = curr->next;
+        }
+        /*
+         * Slowpath: allocate, set up and link a new hash entry:
+         */
+        prev = NULL;
+        curr = *head;
+
+        spin_lock(&table_lock);
+        /*
+         * Make sure we have not raced with another CPU:
+         */
+        while (curr) {
+                if (match_entries(curr, entry))
+                        goto out_unlock;
+
+                prev = curr;
+                curr = curr->next;
+        }
+
+        curr = alloc_entry();
+        if (curr) {
+                *curr = *entry;
+                curr->count = 0;
+                memcpy(curr->comm, comm, TASK_COMM_LEN);
+                if (prev)
+                        prev->next = curr;
+                else
+                        *head = curr;
+                curr->next = NULL;
+        }
+ out_unlock:
+        spin_unlock(&table_lock);
+
+        return curr;
+}
+
+/**
+ * timer_stats_update_stats - Update the statistics for a timer.
+ * @timer:      pointer to either a timer_list or a hrtimer
+ * @pid:        the pid of the task which set up the timer
+ * @startf:     pointer to the function which did the timer setup
+ * @timerf:     pointer to the timer callback function of the timer
+ * @comm:       name of the process which set up the timer
+ *
+ * When the timer is already registered, then the event counter is
+ * incremented. Otherwise the timer is registered in a free slot.
+ */
+void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
+                              void *timerf, char * comm)
+{
+        /*
+         * It doesnt matter which lock we take:
+         */
+        spinlock_t *lock = &per_cpu(lookup_lock, raw_smp_processor_id());
+        struct entry *entry, input;
+        unsigned long flags;
+
+        input.timer = timer;
+        input.start_func = startf;
+        input.expire_func = timerf;
+        input.pid = pid;
+
+        spin_lock_irqsave(lock, flags);
+        if (!active)
+                goto out_unlock;
+
+        entry = tstat_lookup(&input, comm);
+        if (likely(entry))
+                entry->count++;
+        else
+                atomic_inc(&overflow_count);
+
+ out_unlock:
+        spin_unlock_irqrestore(lock, flags);
+}
+
+static void print_name_offset(struct seq_file *m, unsigned long addr)
+{
+        char namebuf[KSYM_NAME_LEN+1];
+        unsigned long size, offset;
+        const char *sym_name;
+        char *modname;
+
+        sym_name = kallsyms_lookup(addr, &size, &offset, &modname, namebuf);
+        if (sym_name)
+                seq_printf(m, "%s", sym_name);
+        else
+                seq_printf(m, "<%p>", (void *)addr);
+}
+
+static int tstats_show(struct seq_file *m, void *v)
+{
+        struct timespec period;
+        struct entry *entry;
+        unsigned long ms;
+        long events = 0;
+        ktime_t time;
+        int i;
+
+        mutex_lock(&show_mutex);
+        /*
+         * If still active then calculate up to now:
+         */
+        if (active)
+                time_stop = ktime_get();
+
+        time = ktime_sub(time_stop, time_start);
+
+        period = ktime_to_timespec(time);
+        ms = period.tv_nsec / 1000000;
+
+        seq_puts(m, "Timer Stats Version: v0.1\n");
+        seq_printf(m, "Sample period: %ld.%03ld s\n", period.tv_sec, ms);
+        if (atomic_read(&overflow_count))
+                seq_printf(m, "Overflow: %d entries\n",
+                        atomic_read(&overflow_count));
+
+        for (i = 0; i < nr_entries; i++) {
+                entry = entries + i;
+                seq_printf(m, "%4lu, %5d %-16s ",
+                                entry->count, entry->pid, entry->comm);
+
+                print_name_offset(m, (unsigned long)entry->start_func);
+                seq_puts(m, " (");
+                print_name_offset(m, (unsigned long)entry->expire_func);
+                seq_puts(m, ")\n");
+
+                events += entry->count;
+        }
+
+        ms += period.tv_sec * 1000;
+        if (!ms)
+                ms = 1;
+
+        if (events && period.tv_sec)
+                seq_printf(m, "%ld total events, %ld.%ld events/sec\n", events,
+                           events / period.tv_sec, events * 1000 / ms);
+        else
+                seq_printf(m, "%ld total events\n", events);
+
+        mutex_unlock(&show_mutex);
+
+        return 0;
+}
+
+/*
+ * After a state change, make sure all concurrent lookup/update
+ * activities have stopped:
+ */
+static void sync_access(void)
+{
+        unsigned long flags;
+        int cpu;
+
+        for_each_online_cpu(cpu) {
+                spin_lock_irqsave(&per_cpu(lookup_lock, cpu), flags);
+                /* nothing */
+                spin_unlock_irqrestore(&per_cpu(lookup_lock, cpu), flags);
+        }
+}
+
+static ssize_t tstats_write(struct file *file, const char __user *buf,
+                            size_t count, loff_t *offs)
+{
+        char ctl[2];
+
+        if (count != 2 || *offs)
+                return -EINVAL;
+
+        if (copy_from_user(ctl, buf, count))
+                return -EFAULT;
+
+        mutex_lock(&show_mutex);
+        switch (ctl[0]) {
+        case '0':
+                if (active) {
+                        active = 0;
+                        time_stop = ktime_get();
+                        sync_access();
+                }
+                break;
+        case '1':
+                if (!active) {
+                        reset_entries();
+                        time_start = ktime_get();
+                        active = 1;
+                }
+                break;
+        default:
+                count = -EINVAL;
+        }
+        mutex_unlock(&show_mutex);
+
+        return count;
+}
+
+static int tstats_open(struct inode *inode, struct file *filp)
+{
+        return single_open(filp, tstats_show, NULL);
+}
+
+static struct file_operations tstats_fops = {
+        .open           = tstats_open,
+        .read           = seq_read,
+        .write          = tstats_write,
+        .llseek         = seq_lseek,
+        .release        = seq_release,
+};
+
+void __init init_timer_stats(void)
+{
+        int cpu;
+
+        for_each_possible_cpu(cpu)
+                spin_lock_init(&per_cpu(lookup_lock, cpu));
+}
+
+static int __init init_tstats_procfs(void)
+{
+        struct proc_dir_entry *pe;
+
+        pe = create_proc_entry("timer_stats", 0644, NULL);
+        if (!pe)
+                return -ENOMEM;
+
+        pe->proc_fops = &tstats_fops;
+
+        return 0;
+}
+__initcall(init_tstats_procfs);
diff --git a/kernel/timer.c b/kernel/timer.c
index 8533c3796082..cb1b86a9c52f 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -34,6 +34,8 @@
 #include <linux/cpu.h>
 #include <linux/syscalls.h>
 #include <linux/delay.h>
+#include <linux/tick.h>
+#include <linux/kallsyms.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -262,6 +264,18 @@ static void internal_add_timer(tvec_base_t *base, struct timer_list *timer)
         list_add_tail(&timer->entry, vec);
 }
 
+#ifdef CONFIG_TIMER_STATS
+void __timer_stats_timer_set_start_info(struct timer_list *timer, void *addr)
+{
+        if (timer->start_site)
+                return;
+
+        timer->start_site = addr;
+        memcpy(timer->start_comm, current->comm, TASK_COMM_LEN);
+        timer->start_pid = current->pid;
+}
+#endif
+
 /**
  * init_timer - initialize a timer.
  * @timer: the timer to be initialized
@@ -273,11 +287,16 @@ void fastcall init_timer(struct timer_list *timer)
 {
         timer->entry.next = NULL;
         timer->base = __raw_get_cpu_var(tvec_bases);
+#ifdef CONFIG_TIMER_STATS
+        timer->start_site = NULL;
+        timer->start_pid = -1;
+        memset(timer->start_comm, 0, TASK_COMM_LEN);
+#endif
 }
 EXPORT_SYMBOL(init_timer);
 
 static inline void detach_timer(struct timer_list *timer,
-                                        int clear_pending)
+                                int clear_pending)
 {
         struct list_head *entry = &timer->entry;
 
@@ -324,6 +343,7 @@ int __mod_timer(struct timer_list *timer, unsigned long expires)
         unsigned long flags;
         int ret = 0;
 
+        timer_stats_timer_set_start_info(timer);
         BUG_ON(!timer->function);
 
         base = lock_timer_base(timer, &flags);
@@ -374,6 +394,7 @@ void add_timer_on(struct timer_list *timer, int cpu)
         tvec_base_t *base = per_cpu(tvec_bases, cpu);
         unsigned long flags;
 
+        timer_stats_timer_set_start_info(timer);
         BUG_ON(timer_pending(timer) || !timer->function);
         spin_lock_irqsave(&base->lock, flags);
         timer->base = base;
@@ -406,6 +427,7 @@ int mod_timer(struct timer_list *timer, unsigned long expires)
 {
         BUG_ON(!timer->function);
 
+        timer_stats_timer_set_start_info(timer);
         /*
          * This is a common optimization triggered by the
          * networking code - if the timer is re-modified
@@ -436,6 +458,7 @@ int del_timer(struct timer_list *timer)
         unsigned long flags;
         int ret = 0;
 
+        timer_stats_timer_clear_start_info(timer);
         if (timer_pending(timer)) {
                 base = lock_timer_base(timer, &flags);
                 if (timer_pending(timer)) {
@@ -569,6 +592,8 @@ static inline void __run_timers(tvec_base_t *base)
                         fn = timer->function;
                         data = timer->data;
 
+                        timer_stats_account_timer(timer);
+
                         set_running_timer(base, timer);
                         detach_timer(timer, 1);
                         spin_unlock_irq(&base->lock);
@@ -591,105 +616,124 @@ static inline void __run_timers(tvec_base_t *base)
         spin_unlock_irq(&base->lock);
 }
 
-#ifdef CONFIG_NO_IDLE_HZ
+#if defined(CONFIG_NO_IDLE_HZ) || defined(CONFIG_NO_HZ)
 /*
  * Find out when the next timer event is due to happen. This
  * is used on S/390 to stop all activity when a cpus is idle.
  * This functions needs to be called disabled.
  */
-unsigned long next_timer_interrupt(void)
+static unsigned long __next_timer_interrupt(tvec_base_t *base)
 {
-        tvec_base_t *base;
-        struct list_head *list;
+        unsigned long timer_jiffies = base->timer_jiffies;
+        unsigned long expires = timer_jiffies + (LONG_MAX >> 1);
+        int index, slot, array, found = 0;
         struct timer_list *nte;
-        unsigned long expires;
-        unsigned long hr_expires = MAX_JIFFY_OFFSET;
-        ktime_t hr_delta;
         tvec_t *varray[4];
-        int i, j;
-
-        hr_delta = hrtimer_get_next_event();
-        if (hr_delta.tv64 != KTIME_MAX) {
-                struct timespec tsdelta;
-                tsdelta = ktime_to_timespec(hr_delta);
-                hr_expires = timespec_to_jiffies(&tsdelta);
-                if (hr_expires < 3)
-                        return hr_expires + jiffies;
-        }
-        hr_expires += jiffies;
-
-        base = __get_cpu_var(tvec_bases);
-        spin_lock(&base->lock);
-        expires = base->timer_jiffies + (LONG_MAX >> 1);
-        list = NULL;
 
         /* Look for timer events in tv1. */
-        j = base->timer_jiffies & TVR_MASK;
+        index = slot = timer_jiffies & TVR_MASK;
         do {
-                list_for_each_entry(nte, base->tv1.vec + j, entry) {
+                list_for_each_entry(nte, base->tv1.vec + slot, entry) {
+                        found = 1;
                         expires = nte->expires;
-                        if (j < (base->timer_jiffies & TVR_MASK))
-                                list = base->tv2.vec + (INDEX(0));
-                        goto found;
+                        /* Look at the cascade bucket(s)? */
+                        if (!index || slot < index)
+                                goto cascade;
+                        return expires;
                 }
-                j = (j + 1) & TVR_MASK;
-        } while (j != (base->timer_jiffies & TVR_MASK));
+                slot = (slot + 1) & TVR_MASK;
+        } while (slot != index);
+
+cascade:
+        /* Calculate the next cascade event */
+        if (index)
+                timer_jiffies += TVR_SIZE - index;
+        timer_jiffies >>= TVR_BITS;
 
         /* Check tv2-tv5. */
         varray[0] = &base->tv2;
         varray[1] = &base->tv3;
         varray[2] = &base->tv4;
         varray[3] = &base->tv5;
-        for (i = 0; i < 4; i++) {
-                j = INDEX(i);
+
+        for (array = 0; array < 4; array++) {
+                tvec_t *varp = varray[array];
+
+                index = slot = timer_jiffies & TVN_MASK;
                 do {
-                        if (list_empty(varray[i]->vec + j)) {
-                                j = (j + 1) & TVN_MASK;
-                                continue;
-                        }
-                        list_for_each_entry(nte, varray[i]->vec + j, entry)
+                        list_for_each_entry(nte, varp->vec + slot, entry) {
+                                found = 1;
                                 if (time_before(nte->expires, expires))
                                         expires = nte->expires;
-                        if (j < (INDEX(i)) && i < 3)
-                                list = varray[i + 1]->vec + (INDEX(i + 1));
-                        goto found;
-                } while (j != (INDEX(i)));
-        }
-found:
-        if (list) {
-                /*
-                 * The search wrapped. We need to look at the next list
-                 * from next tv element that would cascade into tv element
-                 * where we found the timer element.
-                 */
-                list_for_each_entry(nte, list, entry) {
-                        if (time_before(nte->expires, expires))
-                                expires = nte->expires;
-                }
+                        }
+                        /*
+                         * Do we still search for the first timer or are
+                         * we looking up the cascade buckets ?
+                         */
+                        if (found) {
+                                /* Look at the cascade bucket(s)? */
+                                if (!index || slot < index)
+                                        break;
+                                return expires;
+                        }
+                        slot = (slot + 1) & TVN_MASK;
+                } while (slot != index);
+
+                if (index)
+                        timer_jiffies += TVN_SIZE - index;
+                timer_jiffies >>= TVN_BITS;
         }
-        spin_unlock(&base->lock);
+        return expires;
+}
 
-        /*
-         * It can happen that other CPUs service timer IRQs and increment
-         * jiffies, but we have not yet got a local timer tick to process
-         * the timer wheels.  In that case, the expiry time can be before
-         * jiffies, but since the high-resolution timer here is relative to
-         * jiffies, the default expression when high-resolution timers are
-         * not active,
-         *
-         *   time_before(MAX_JIFFY_OFFSET + jiffies, expires)
-         *
-         * would falsely evaluate to true.  If that is the case, just
-         * return jiffies so that we can immediately fire the local timer
-         */
-        if (time_before(expires, jiffies))
-                return jiffies;
+/*
+ * Check, if the next hrtimer event is before the next timer wheel
+ * event:
+ */
+static unsigned long cmp_next_hrtimer_event(unsigned long now,
+                                            unsigned long expires)
+{
+        ktime_t hr_delta = hrtimer_get_next_event();
+        struct timespec tsdelta;
+
+        if (hr_delta.tv64 == KTIME_MAX)
+                return expires;
 
-        if (time_before(hr_expires, expires))
-                return hr_expires;
+        if (hr_delta.tv64 <= TICK_NSEC)
+                return now;
 
+        tsdelta = ktime_to_timespec(hr_delta);
+        now += timespec_to_jiffies(&tsdelta);
+        if (time_before(now, expires))
+                return now;
         return expires;
 }
+
+/**
+ * next_timer_interrupt - return the jiffy of the next pending timer
+ */
+unsigned long get_next_timer_interrupt(unsigned long now)
+{
+        tvec_base_t *base = __get_cpu_var(tvec_bases);
+        unsigned long expires;
+
+        spin_lock(&base->lock);
+        expires = __next_timer_interrupt(base);
+        spin_unlock(&base->lock);
+
+        if (time_before_eq(expires, now))
+                return now;
+
+        return cmp_next_hrtimer_event(now, expires);
+}
+
+#ifdef CONFIG_NO_IDLE_HZ
+unsigned long next_timer_interrupt(void)
+{
+        return get_next_timer_interrupt(jiffies);
+}
+#endif
+
 #endif
 
 /******************************************************************/
@@ -832,32 +876,35 @@ EXPORT_SYMBOL(do_settimeofday);
  *
  * Accumulates current time interval and initializes new clocksource
  */
-static int change_clocksource(void)
+static void change_clocksource(void)
 {
         struct clocksource *new;
         cycle_t now;
         u64 nsec;
+
         new = clocksource_get_next();
-        if (clock != new) {
-                now = clocksource_read(new);
-                nsec =  __get_nsec_offset();
-                timespec_add_ns(&xtime, nsec);
-
-                clock = new;
-                clock->cycle_last = now;
-                printk(KERN_INFO "Time: %s clocksource has been installed.\n",
-                       clock->name);
-                return 1;
-        } else if (clock->update_callback) {
-                return clock->update_callback();
-        }
-        return 0;
+
+        if (clock == new)
+                return;
+
+        now = clocksource_read(new);
+        nsec =  __get_nsec_offset();
+        timespec_add_ns(&xtime, nsec);
+
+        clock = new;
+        clock->cycle_last = now;
+
+        clock->error = 0;
+        clock->xtime_nsec = 0;
+        clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH);
+
+        tick_clock_notify();
+
+        printk(KERN_INFO "Time: %s clocksource has been installed.\n",
+               clock->name);
 }
 #else
-static inline int change_clocksource(void)
-{
-        return 0;
-}
+static inline void change_clocksource(void) { }
 #endif
 
 /**
@@ -871,33 +918,56 @@ int timekeeping_is_continuous(void)
         do {
                 seq = read_seqbegin(&xtime_lock);
 
-                ret = clock->is_continuous;
+                ret = clock->flags & CLOCK_SOURCE_VALID_FOR_HRES;
 
         } while (read_seqretry(&xtime_lock, seq));
 
         return ret;
 }
 
+/**
+ * read_persistent_clock -  Return time in seconds from the persistent clock.
+ *
+ * Weak dummy function for arches that do not yet support it.
+ * Returns seconds from epoch using the battery backed persistent clock.
+ * Returns zero if unsupported.
+ *
+ *  XXX - Do be sure to remove it once all arches implement it.
+ */
+unsigned long __attribute__((weak)) read_persistent_clock(void)
+{
+        return 0;
+}
+
 /*
  * timekeeping_init - Initializes the clocksource and common timekeeping values
  */
 void __init timekeeping_init(void)
 {
         unsigned long flags;
+        unsigned long sec = read_persistent_clock();
 
         write_seqlock_irqsave(&xtime_lock, flags);
 
         ntp_clear();
 
         clock = clocksource_get_next();
-        clocksource_calculate_interval(clock, tick_nsec);
+        clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH);
         clock->cycle_last = clocksource_read(clock);
 
+        xtime.tv_sec = sec;
+        xtime.tv_nsec = 0;
+        set_normalized_timespec(&wall_to_monotonic,
+                -xtime.tv_sec, -xtime.tv_nsec);
+
         write_sequnlock_irqrestore(&xtime_lock, flags);
 }
 
-
+/* flag for if timekeeping is suspended */
 static int timekeeping_suspended;
+/* time in seconds when suspend began */
+static unsigned long timekeeping_suspend_time;
+
 /**
  * timekeeping_resume - Resumes the generic timekeeping subsystem.
  * @dev:        unused
@@ -909,13 +979,26 @@ static int timekeeping_suspended;
 static int timekeeping_resume(struct sys_device *dev)
 {
         unsigned long flags;
+        unsigned long now = read_persistent_clock();
 
         write_seqlock_irqsave(&xtime_lock, flags);
-        /* restart the last cycle value */
+
+        if (now && (now > timekeeping_suspend_time)) {
+                unsigned long sleep_length = now - timekeeping_suspend_time;
+
+                xtime.tv_sec += sleep_length;
+                wall_to_monotonic.tv_sec -= sleep_length;
+        }
+        /* re-base the last cycle value */
         clock->cycle_last = clocksource_read(clock);
         clock->error = 0;
         timekeeping_suspended = 0;
         write_sequnlock_irqrestore(&xtime_lock, flags);
+
+        touch_softlockup_watchdog();
+        /* Resume hrtimers */
+        clock_was_set();
+
         return 0;
 }
 
@@ -925,6 +1008,7 @@ static int timekeeping_suspend(struct sys_device *dev, pm_message_t state)
 
         write_seqlock_irqsave(&xtime_lock, flags);
         timekeeping_suspended = 1;
+        timekeeping_suspend_time = read_persistent_clock();
         write_sequnlock_irqrestore(&xtime_lock, flags);
         return 0;
 }
@@ -1089,11 +1173,8 @@ static void update_wall_time(void)
         clock->xtime_nsec -= (s64)xtime.tv_nsec << clock->shift;
 
         /* check to see if there is a new clocksource to use */
-        if (change_clocksource()) {
-                clock->error = 0;
-                clock->xtime_nsec = 0;
-                clocksource_calculate_interval(clock, tick_nsec);
-        }
+        change_clocksource();
+        update_vsyscall(&xtime, clock);
 }
 
 /*
@@ -1162,11 +1243,9 @@ static inline void calc_load(unsigned long ticks)
  * This read-write spinlock protects us from races in SMP while
  * playing with xtime and avenrun.
  */
-#ifndef ARCH_HAVE_XTIME_LOCK
-__cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock);
+__attribute__((weak)) __cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock);
 
 EXPORT_SYMBOL(xtime_lock);
-#endif
 
 /*
  * This function runs timers and the timer-tq in bottom half context.
@@ -1175,7 +1254,8 @@ static void run_timer_softirq(struct softirq_action *h)
 {
         tvec_base_t *base = __get_cpu_var(tvec_bases);
 
-        hrtimer_run_queues();
+        hrtimer_run_queues();
+
         if (time_after_eq(jiffies, base->timer_jiffies))
                 __run_timers(base);
 }
@@ -1621,6 +1701,8 @@ void __init init_timers(void)
         int err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE,
                                 (void *)(long)smp_processor_id());
 
+        init_timer_stats();
+
         BUG_ON(err == NOTIFY_BAD);
         register_cpu_notifier(&timers_nb);
         open_softirq(TIMER_SOFTIRQ, run_timer_softirq, NULL);
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index baacc3691415..658f638c402c 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -22,8 +22,6 @@
 #include <linux/acct.h>
 #include <linux/jiffies.h>
 
-
-#define USEC_PER_TICK   (USEC_PER_SEC/HZ)
 /*
  * fill in basic accounting fields
  */
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
new file mode 100644
index 000000000000..f22b9dbd2a9c
--- /dev/null
+++ b/kernel/utsname_sysctl.c
@@ -0,0 +1,146 @@
+/*
+ *  Copyright (C) 2007
+ *
+ *  Author: Eric Biederman <ebiederm@xmision.com>
+ *
+ *  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, version 2 of the
+ *  License.
+ */
+
+#include <linux/module.h>
+#include <linux/uts.h>
+#include <linux/utsname.h>
+#include <linux/version.h>
+#include <linux/sysctl.h>
+
+static void *get_uts(ctl_table *table, int write)
+{
+        char *which = table->data;
+#ifdef CONFIG_UTS_NS
+        struct uts_namespace *uts_ns = current->nsproxy->uts_ns;
+        which = (which - (char *)&init_uts_ns) + (char *)uts_ns;
+#endif
+        if (!write)
+                down_read(&uts_sem);
+        else
+                down_write(&uts_sem);
+        return which;
+}
+
+static void put_uts(ctl_table *table, int write, void *which)
+{
+        if (!write)
+                up_read(&uts_sem);
+        else
+                up_write(&uts_sem);
+}
+
+#ifdef CONFIG_PROC_FS
+/*
+ *      Special case of dostring for the UTS structure. This has locks
+ *      to observe. Should this be in kernel/sys.c ????
+ */
+static int proc_do_uts_string(ctl_table *table, int write, struct file *filp,
+                  void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+        struct ctl_table uts_table;
+        int r;
+        memcpy(&uts_table, table, sizeof(uts_table));
+        uts_table.data = get_uts(table, write);
+        r = proc_dostring(&uts_table,write,filp,buffer,lenp, ppos);
+        put_uts(table, write, uts_table.data);
+        return r;
+}
+#else
+#define proc_do_uts_string NULL
+#endif
+
+
+#ifdef CONFIG_SYSCTL_SYSCALL
+/* The generic string strategy routine: */
+static int sysctl_uts_string(ctl_table *table, int __user *name, int nlen,
+                  void __user *oldval, size_t __user *oldlenp,
+                  void __user *newval, size_t newlen)
+{
+        struct ctl_table uts_table;
+        int r, write;
+        write = newval && newlen;
+        memcpy(&uts_table, table, sizeof(uts_table));
+        uts_table.data = get_uts(table, write);
+        r = sysctl_string(&uts_table, name, nlen,
+                oldval, oldlenp, newval, newlen);
+        put_uts(table, write, uts_table.data);
+        return r;
+}
+#else
+#define sysctl_uts_string NULL
+#endif
+
+static struct ctl_table uts_kern_table[] = {
+        {
+                .ctl_name       = KERN_OSTYPE,
+                .procname       = "ostype",
+                .data           = init_uts_ns.name.sysname,
+                .maxlen         = sizeof(init_uts_ns.name.sysname),
+                .mode           = 0444,
+                .proc_handler   = proc_do_uts_string,
+                .strategy       = sysctl_uts_string,
+        },
+        {
+                .ctl_name       = KERN_OSRELEASE,
+                .procname       = "osrelease",
+                .data           = init_uts_ns.name.release,
+                .maxlen         = sizeof(init_uts_ns.name.release),
+                .mode           = 0444,
+                .proc_handler   = proc_do_uts_string,
+                .strategy       = sysctl_uts_string,
+        },
+        {
+                .ctl_name       = KERN_VERSION,
+                .procname       = "version",
+                .data           = init_uts_ns.name.version,
+                .maxlen         = sizeof(init_uts_ns.name.version),
+                .mode           = 0444,
+                .proc_handler   = proc_do_uts_string,
+                .strategy       = sysctl_uts_string,
+        },
+        {
+                .ctl_name       = KERN_NODENAME,
+                .procname       = "hostname",
+                .data           = init_uts_ns.name.nodename,
+                .maxlen         = sizeof(init_uts_ns.name.nodename),
+                .mode           = 0644,
+                .proc_handler   = proc_do_uts_string,
+                .strategy       = sysctl_uts_string,
+        },
+        {
+                .ctl_name       = KERN_DOMAINNAME,
+                .procname       = "domainname",
+                .data           = init_uts_ns.name.domainname,
+                .maxlen         = sizeof(init_uts_ns.name.domainname),
+                .mode           = 0644,
+                .proc_handler   = proc_do_uts_string,
+                .strategy       = sysctl_uts_string,
+        },
+        {}
+};
+
+static struct ctl_table uts_root_table[] = {
+        {
+                .ctl_name       = CTL_KERN,
+                .procname       = "kernel",
+                .mode           = 0555,
+                .child          = uts_kern_table,
+        },
+        {}
+};
+
+static int __init utsname_sysctl_init(void)
+{
+        register_sysctl_table(uts_root_table);
+        return 0;
+}
+
+__initcall(utsname_sysctl_init);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 020d1fff57dc..b6fa5e63085d 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -218,7 +218,7 @@ int fastcall queue_work(struct workqueue_struct *wq, struct work_struct *work)
 }
 EXPORT_SYMBOL_GPL(queue_work);
 
-static void delayed_work_timer_fn(unsigned long __data)
+void delayed_work_timer_fn(unsigned long __data)
 {
         struct delayed_work *dwork = (struct delayed_work *)__data;
         struct workqueue_struct *wq = get_wq_data(&dwork->work);
@@ -245,6 +245,7 @@ int fastcall queue_delayed_work(struct workqueue_struct *wq,
         struct timer_list *timer = &dwork->timer;
         struct work_struct *work = &dwork->work;
 
+        timer_stats_timer_set_start_info(timer);
         if (delay == 0)
                 return queue_work(wq, work);
 
@@ -593,8 +594,10 @@ EXPORT_SYMBOL(schedule_work);
  * After waiting for a given time this puts a job in the kernel-global
  * workqueue.
  */
-int fastcall schedule_delayed_work(struct delayed_work *dwork, unsigned long delay)
+int fastcall schedule_delayed_work(struct delayed_work *dwork,
+                                        unsigned long delay)
 {
+        timer_stats_timer_set_start_info(&dwork->timer);
         return queue_delayed_work(keventd_wq, dwork, delay);
 }
 EXPORT_SYMBOL(schedule_delayed_work);