Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched-fixes

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched-fixes:
  sched: default to n for GROUP_SCHED and FAIR_GROUP_SCHED
  sched: add optional support for CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
  sched, x86: add HAVE_UNSTABLE_SCHED_CLOCK
  sched: fix cpu clock
  sched: fair-group: fix a Div0 error of the fair group scheduler
  sched: fix missing locking in sched_domains code
  sched: make clock sync tunable by architecture code
  sched: fix debugging
  sched: fix sched_info_switch not being called according to documentation
  sched: fix hrtick_start_fair and CPU-Hotplug
  sched: fix SCHED_FAIR wake-idle logic error
  sched: fix RT task-wakeup logic
  sched: add statics, don't return void expressions
  sched: add debug checks to idle functions
  sched: remove old sched doc
  sched: make rt_sched_class, idle_sched_class static
  sched: optimize calc_delta_mine()
  sched: fix normalized sleeper

7 files changed, 380 insertions, 238 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 188c43223f52..1c9938addb9d 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -9,7 +9,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o profile.o \
             rcupdate.o extable.o params.o posix-timers.o \
             kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
             hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
-            notifier.o ksysfs.o pm_qos_params.o
+            notifier.o ksysfs.o pm_qos_params.o sched_clock.o
 
 obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o
 obj-$(CONFIG_STACKTRACE) += stacktrace.o
diff --git a/kernel/sched.c b/kernel/sched.c
index 34bcc5bc120e..58fb8af15776 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -75,16 +75,6 @@
 #include <asm/irq_regs.h>
 
 /*
- * Scheduler clock - returns current time in nanosec units.
- * This is default implementation.
- * Architectures and sub-architectures can override this.
- */
-unsigned long long __attribute__((weak)) sched_clock(void)
-{
-        return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
-}
-
-/*
  * Convert user-nice values [ -20 ... 0 ... 19 ]
  * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
  * and back.
@@ -242,6 +232,12 @@ static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b)
 }
 #endif
 
+/*
+ * sched_domains_mutex serializes calls to arch_init_sched_domains,
+ * detach_destroy_domains and partition_sched_domains.
+ */
+static DEFINE_MUTEX(sched_domains_mutex);
+
 #ifdef CONFIG_GROUP_SCHED
 
 #include <linux/cgroup.h>
@@ -308,9 +304,6 @@ static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;
  */
 static DEFINE_SPINLOCK(task_group_lock);
 
-/* doms_cur_mutex serializes access to doms_cur[] array */
-static DEFINE_MUTEX(doms_cur_mutex);
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
 #ifdef CONFIG_USER_SCHED
 # define INIT_TASK_GROUP_LOAD   (2*NICE_0_LOAD)
@@ -318,7 +311,13 @@ static DEFINE_MUTEX(doms_cur_mutex);
 # define INIT_TASK_GROUP_LOAD   NICE_0_LOAD
 #endif
 
+/*
+ * A weight of 0, 1 or ULONG_MAX can cause arithmetics problems.
+ * (The default weight is 1024 - so there's no practical
+ *  limitation from this.)
+ */
 #define MIN_SHARES      2
+#define MAX_SHARES      (ULONG_MAX - 1)
 
 static int init_task_group_load = INIT_TASK_GROUP_LOAD;
 #endif
@@ -358,21 +357,9 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
 #endif
 }
 
-static inline void lock_doms_cur(void)
-{
-        mutex_lock(&doms_cur_mutex);
-}
-
-static inline void unlock_doms_cur(void)
-{
-        mutex_unlock(&doms_cur_mutex);
-}
-
 #else
 
 static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { }
-static inline void lock_doms_cur(void) { }
-static inline void unlock_doms_cur(void) { }
 
 #endif  /* CONFIG_GROUP_SCHED */
 
@@ -560,13 +547,7 @@ struct rq {
         unsigned long next_balance;
         struct mm_struct *prev_mm;
 
-        u64 clock, prev_clock_raw;
-        s64 clock_max_delta;
-
-        unsigned int clock_warps, clock_overflows, clock_underflows;
-        u64 idle_clock;
-        unsigned int clock_deep_idle_events;
-        u64 tick_timestamp;
+        u64 clock;
 
         atomic_t nr_iowait;
 
@@ -631,82 +612,6 @@ static inline int cpu_of(struct rq *rq)
 #endif
 }
 
-#ifdef CONFIG_NO_HZ
-static inline bool nohz_on(int cpu)
-{
-        return tick_get_tick_sched(cpu)->nohz_mode != NOHZ_MODE_INACTIVE;
-}
-
-static inline u64 max_skipped_ticks(struct rq *rq)
-{
-        return nohz_on(cpu_of(rq)) ? jiffies - rq->last_tick_seen + 2 : 1;
-}
-
-static inline void update_last_tick_seen(struct rq *rq)
-{
-        rq->last_tick_seen = jiffies;
-}
-#else
-static inline u64 max_skipped_ticks(struct rq *rq)
-{
-        return 1;
-}
-
-static inline void update_last_tick_seen(struct rq *rq)
-{
-}
-#endif
-
-/*
- * Update the per-runqueue clock, as finegrained as the platform can give
- * us, but without assuming monotonicity, etc.:
- */
-static void __update_rq_clock(struct rq *rq)
-{
-        u64 prev_raw = rq->prev_clock_raw;
-        u64 now = sched_clock();
-        s64 delta = now - prev_raw;
-        u64 clock = rq->clock;
-
-#ifdef CONFIG_SCHED_DEBUG
-        WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
-#endif
-        /*
-         * Protect against sched_clock() occasionally going backwards:
-         */
-        if (unlikely(delta < 0)) {
-                clock++;
-                rq->clock_warps++;
-        } else {
-                /*
-                 * Catch too large forward jumps too:
-                 */
-                u64 max_jump = max_skipped_ticks(rq) * TICK_NSEC;
-                u64 max_time = rq->tick_timestamp + max_jump;
-
-                if (unlikely(clock + delta > max_time)) {
-                        if (clock < max_time)
-                                clock = max_time;
-                        else
-                                clock++;
-                        rq->clock_overflows++;
-                } else {
-                        if (unlikely(delta > rq->clock_max_delta))
-                                rq->clock_max_delta = delta;
-                        clock += delta;
-                }
-        }
-
-        rq->prev_clock_raw = now;
-        rq->clock = clock;
-}
-
-static void update_rq_clock(struct rq *rq)
-{
-        if (likely(smp_processor_id() == cpu_of(rq)))
-                __update_rq_clock(rq);
-}
-
 /*
  * The domain tree (rq->sd) is protected by RCU's quiescent state transition.
  * See detach_destroy_domains: synchronize_sched for details.
@@ -722,6 +627,11 @@ static void update_rq_clock(struct rq *rq)
 #define task_rq(p)              cpu_rq(task_cpu(p))
 #define cpu_curr(cpu)           (cpu_rq(cpu)->curr)
 
+static inline void update_rq_clock(struct rq *rq)
+{
+        rq->clock = sched_clock_cpu(cpu_of(rq));
+}
+
 /*
  * Tunables that become constants when CONFIG_SCHED_DEBUG is off:
  */
@@ -757,14 +667,14 @@ const_debug unsigned int sysctl_sched_features =
 #define SCHED_FEAT(name, enabled)       \
         #name ,
 
-__read_mostly char *sched_feat_names[] = {
+static __read_mostly char *sched_feat_names[] = {
 #include "sched_features.h"
         NULL
 };
 
 #undef SCHED_FEAT
 
-int sched_feat_open(struct inode *inode, struct file *filp)
+static int sched_feat_open(struct inode *inode, struct file *filp)
 {
         filp->private_data = inode->i_private;
         return 0;
@@ -899,7 +809,7 @@ static inline u64 global_rt_runtime(void)
         return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
 }
 
-static const unsigned long long time_sync_thresh = 100000;
+unsigned long long time_sync_thresh = 100000;
 
 static DEFINE_PER_CPU(unsigned long long, time_offset);
 static DEFINE_PER_CPU(unsigned long long, prev_cpu_time);
@@ -913,11 +823,14 @@ static DEFINE_PER_CPU(unsigned long long, prev_cpu_time);
 static DEFINE_SPINLOCK(time_sync_lock);
 static unsigned long long prev_global_time;
 
-static unsigned long long __sync_cpu_clock(cycles_t time, int cpu)
+static unsigned long long __sync_cpu_clock(unsigned long long time, int cpu)
 {
-        unsigned long flags;
-
-        spin_lock_irqsave(&time_sync_lock, flags);
+        /*
+         * We want this inlined, to not get tracer function calls
+         * in this critical section:
+         */
+        spin_acquire(&time_sync_lock.dep_map, 0, 0, _THIS_IP_);
+        __raw_spin_lock(&time_sync_lock.raw_lock);
 
         if (time < prev_global_time) {
                 per_cpu(time_offset, cpu) += prev_global_time - time;
@@ -926,7 +839,8 @@ static unsigned long long __sync_cpu_clock(cycles_t time, int cpu)
                 prev_global_time = time;
         }
 
-        spin_unlock_irqrestore(&time_sync_lock, flags);
+        __raw_spin_unlock(&time_sync_lock.raw_lock);
+        spin_release(&time_sync_lock.dep_map, 1, _THIS_IP_);
 
         return time;
 }
@@ -934,8 +848,6 @@ static unsigned long long __sync_cpu_clock(cycles_t time, int cpu)
 static unsigned long long __cpu_clock(int cpu)
 {
         unsigned long long now;
-        unsigned long flags;
-        struct rq *rq;
 
         /*
          * Only call sched_clock() if the scheduler has already been
@@ -944,11 +856,7 @@ static unsigned long long __cpu_clock(int cpu)
         if (unlikely(!scheduler_running))
                 return 0;
 
-        local_irq_save(flags);
-        rq = cpu_rq(cpu);
-        update_rq_clock(rq);
-        now = rq->clock;
-        local_irq_restore(flags);
+        now = sched_clock_cpu(cpu);
 
         return now;
 }
@@ -960,13 +868,18 @@ static unsigned long long __cpu_clock(int cpu)
 unsigned long long cpu_clock(int cpu)
 {
         unsigned long long prev_cpu_time, time, delta_time;
+        unsigned long flags;
 
+        local_irq_save(flags);
         prev_cpu_time = per_cpu(prev_cpu_time, cpu);
         time = __cpu_clock(cpu) + per_cpu(time_offset, cpu);
         delta_time = time-prev_cpu_time;
 
-        if (unlikely(delta_time > time_sync_thresh))
+        if (unlikely(delta_time > time_sync_thresh)) {
                 time = __sync_cpu_clock(time, cpu);
+                per_cpu(prev_cpu_time, cpu) = time;
+        }
+        local_irq_restore(flags);
 
         return time;
 }
@@ -1117,43 +1030,6 @@ static struct rq *this_rq_lock(void)
         return rq;
 }
 
-/*
- * We are going deep-idle (irqs are disabled):
- */
-void sched_clock_idle_sleep_event(void)
-{
-        struct rq *rq = cpu_rq(smp_processor_id());
-
-        spin_lock(&rq->lock);
-        __update_rq_clock(rq);
-        spin_unlock(&rq->lock);
-        rq->clock_deep_idle_events++;
-}
-EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event);
-
-/*
- * We just idled delta nanoseconds (called with irqs disabled):
- */
-void sched_clock_idle_wakeup_event(u64 delta_ns)
-{
-        struct rq *rq = cpu_rq(smp_processor_id());
-        u64 now = sched_clock();
-
-        rq->idle_clock += delta_ns;
-        /*
-         * Override the previous timestamp and ignore all
-         * sched_clock() deltas that occured while we idled,
-         * and use the PM-provided delta_ns to advance the
-         * rq clock:
-         */
-        spin_lock(&rq->lock);
-        rq->prev_clock_raw = now;
-        rq->clock += delta_ns;
-        spin_unlock(&rq->lock);
-        touch_softlockup_watchdog();
-}
-EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
-
 static void __resched_task(struct task_struct *p, int tif_bit);
 
 static inline void resched_task(struct task_struct *p)
@@ -1189,6 +1065,7 @@ static inline void resched_rq(struct rq *rq)
 enum {
         HRTICK_SET,             /* re-programm hrtick_timer */
         HRTICK_RESET,           /* not a new slice */
+        HRTICK_BLOCK,           /* stop hrtick operations */
 };
 
 /*
@@ -1200,6 +1077,8 @@ static inline int hrtick_enabled(struct rq *rq)
 {
         if (!sched_feat(HRTICK))
                 return 0;
+        if (unlikely(test_bit(HRTICK_BLOCK, &rq->hrtick_flags)))
+                return 0;
         return hrtimer_is_hres_active(&rq->hrtick_timer);
 }
 
@@ -1275,14 +1154,70 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer)
         WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
 
         spin_lock(&rq->lock);
-        __update_rq_clock(rq);
+        update_rq_clock(rq);
         rq->curr->sched_class->task_tick(rq, rq->curr, 1);
         spin_unlock(&rq->lock);
 
         return HRTIMER_NORESTART;
 }
 
-static inline void init_rq_hrtick(struct rq *rq)
+static void hotplug_hrtick_disable(int cpu)
+{
+        struct rq *rq = cpu_rq(cpu);
+        unsigned long flags;
+
+        spin_lock_irqsave(&rq->lock, flags);
+        rq->hrtick_flags = 0;
+        __set_bit(HRTICK_BLOCK, &rq->hrtick_flags);
+        spin_unlock_irqrestore(&rq->lock, flags);
+
+        hrtick_clear(rq);
+}
+
+static void hotplug_hrtick_enable(int cpu)
+{
+        struct rq *rq = cpu_rq(cpu);
+        unsigned long flags;
+
+        spin_lock_irqsave(&rq->lock, flags);
+        __clear_bit(HRTICK_BLOCK, &rq->hrtick_flags);
+        spin_unlock_irqrestore(&rq->lock, flags);
+}
+
+static int
+hotplug_hrtick(struct notifier_block *nfb, unsigned long action, void *hcpu)
+{
+        int cpu = (int)(long)hcpu;
+
+        switch (action) {
+        case CPU_UP_CANCELED:
+        case CPU_UP_CANCELED_FROZEN:
+        case CPU_DOWN_PREPARE:
+        case CPU_DOWN_PREPARE_FROZEN:
+        case CPU_DEAD:
+        case CPU_DEAD_FROZEN:
+                hotplug_hrtick_disable(cpu);
+                return NOTIFY_OK;
+
+        case CPU_UP_PREPARE:
+        case CPU_UP_PREPARE_FROZEN:
+        case CPU_DOWN_FAILED:
+        case CPU_DOWN_FAILED_FROZEN:
+        case CPU_ONLINE:
+        case CPU_ONLINE_FROZEN:
+                hotplug_hrtick_enable(cpu);
+                return NOTIFY_OK;
+        }
+
+        return NOTIFY_DONE;
+}
+
+static void init_hrtick(void)
+{
+        hotcpu_notifier(hotplug_hrtick, 0);
+}
+
+static void init_rq_hrtick(struct rq *rq)
 {
         rq->hrtick_flags = 0;
         hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
@@ -1319,6 +1254,10 @@ static inline void init_rq_hrtick(struct rq *rq)
 void hrtick_resched(void)
 {
 }
+
+static inline void init_hrtick(void)
+{
+}
 #endif
 
 /*
@@ -1438,8 +1377,8 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight,
 {
         u64 tmp;
 
-        if (unlikely(!lw->inv_weight))
-                lw->inv_weight = (WMULT_CONST-lw->weight/2) / (lw->weight+1);
+        if (!lw->inv_weight)
+                lw->inv_weight = 1 + (WMULT_CONST-lw->weight/2)/(lw->weight+1);
 
         tmp = (u64)delta_exec * weight;
         /*
@@ -1748,6 +1687,8 @@ __update_group_shares_cpu(struct task_group *tg, struct sched_domain *sd,
 
         if (shares < MIN_SHARES)
                 shares = MIN_SHARES;
+        else if (shares > MAX_SHARES)
+                shares = MAX_SHARES;
 
         __set_se_shares(tg->se[tcpu], shares);
 }
@@ -4339,8 +4280,10 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
         struct rq *rq = this_rq();
         cputime64_t tmp;
 
-        if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0))
-                return account_guest_time(p, cputime);
+        if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
+                account_guest_time(p, cputime);
+                return;
+        }
 
         p->stime = cputime_add(p->stime, cputime);
 
@@ -4404,19 +4347,11 @@ void scheduler_tick(void)
         int cpu = smp_processor_id();
         struct rq *rq = cpu_rq(cpu);
         struct task_struct *curr = rq->curr;
-        u64 next_tick = rq->tick_timestamp + TICK_NSEC;
+
+        sched_clock_tick();
 
         spin_lock(&rq->lock);
-        __update_rq_clock(rq);
-        /*
-         * Let rq->clock advance by at least TICK_NSEC:
-         */
-        if (unlikely(rq->clock < next_tick)) {
-                rq->clock = next_tick;
-                rq->clock_underflows++;
-        }
-        rq->tick_timestamp = rq->clock;
-        update_last_tick_seen(rq);
+        update_rq_clock(rq);
         update_cpu_load(rq);
         curr->sched_class->task_tick(rq, curr, 0);
         spin_unlock(&rq->lock);
@@ -4570,7 +4505,7 @@ need_resched_nonpreemptible:
          * Do the rq-clock update outside the rq lock:
          */
         local_irq_disable();
-        __update_rq_clock(rq);
+        update_rq_clock(rq);
         spin_lock(&rq->lock);
         clear_tsk_need_resched(prev);
 
@@ -4595,9 +4530,9 @@ need_resched_nonpreemptible:
         prev->sched_class->put_prev_task(rq, prev);
         next = pick_next_task(rq, prev);
 
-        sched_info_switch(prev, next);
-
         if (likely(prev != next)) {
+                sched_info_switch(prev, next);
+
                 rq->nr_switches++;
                 rq->curr = next;
                 ++*switch_count;
@@ -7755,7 +7690,7 @@ void partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
 {
         int i, j;
 
-        lock_doms_cur();
+        mutex_lock(&sched_domains_mutex);
 
         /* always unregister in case we don't destroy any domains */
         unregister_sched_domain_sysctl();
@@ -7804,7 +7739,7 @@ match2:
 
         register_sched_domain_sysctl();
 
-        unlock_doms_cur();
+        mutex_unlock(&sched_domains_mutex);
 }
 
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
@@ -7813,8 +7748,10 @@ int arch_reinit_sched_domains(void)
         int err;
 
         get_online_cpus();
+        mutex_lock(&sched_domains_mutex);
         detach_destroy_domains(&cpu_online_map);
         err = arch_init_sched_domains(&cpu_online_map);
+        mutex_unlock(&sched_domains_mutex);
         put_online_cpus();
 
         return err;
@@ -7932,13 +7869,16 @@ void __init sched_init_smp(void)
         BUG_ON(sched_group_nodes_bycpu == NULL);
 #endif
         get_online_cpus();
+        mutex_lock(&sched_domains_mutex);
         arch_init_sched_domains(&cpu_online_map);
         cpus_andnot(non_isolated_cpus, cpu_possible_map, cpu_isolated_map);
         if (cpus_empty(non_isolated_cpus))
                 cpu_set(smp_processor_id(), non_isolated_cpus);
+        mutex_unlock(&sched_domains_mutex);
         put_online_cpus();
         /* XXX: Theoretical race here - CPU may be hotplugged now */
         hotcpu_notifier(update_sched_domains, 0);
+        init_hrtick();
 
         /* Move init over to a non-isolated CPU */
         if (set_cpus_allowed_ptr(current, &non_isolated_cpus) < 0)
@@ -8025,7 +7965,7 @@ static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 
         se->my_q = cfs_rq;
         se->load.weight = tg->shares;
-        se->load.inv_weight = div64_u64(1ULL<<32, se->load.weight);
+        se->load.inv_weight = 0;
         se->parent = parent;
 }
 #endif
@@ -8149,8 +8089,6 @@ void __init sched_init(void)
                 spin_lock_init(&rq->lock);
                 lockdep_set_class(&rq->lock, &rq->rq_lock_key);
                 rq->nr_running = 0;
-                rq->clock = 1;
-                update_last_tick_seen(rq);
                 init_cfs_rq(&rq->cfs, rq);
                 init_rt_rq(&rq->rt, rq);
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -8294,6 +8232,7 @@ EXPORT_SYMBOL(__might_sleep);
 static void normalize_task(struct rq *rq, struct task_struct *p)
 {
         int on_rq;
+
         update_rq_clock(rq);
         on_rq = p->se.on_rq;
         if (on_rq)
@@ -8325,7 +8264,6 @@ void normalize_rt_tasks(void)
                 p->se.sleep_start               = 0;
                 p->se.block_start               = 0;
 #endif
-                task_rq(p)->clock               = 0;
 
                 if (!rt_task(p)) {
                         /*
@@ -8692,7 +8630,7 @@ static void __set_se_shares(struct sched_entity *se, unsigned long shares)
                 dequeue_entity(cfs_rq, se, 0);
 
         se->load.weight = shares;
-        se->load.inv_weight = div64_u64((1ULL<<32), shares);
+        se->load.inv_weight = 0;
 
         if (on_rq)
                 enqueue_entity(cfs_rq, se, 0);
@@ -8722,13 +8660,10 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
         if (!tg->se[0])
                 return -EINVAL;
 
-        /*
-         * A weight of 0 or 1 can cause arithmetics problems.
-         * (The default weight is 1024 - so there's no practical
-         *  limitation from this.)
-         */
         if (shares < MIN_SHARES)
                 shares = MIN_SHARES;
+        else if (shares > MAX_SHARES)
+                shares = MAX_SHARES;
 
         mutex_lock(&shares_mutex);
         if (tg->shares == shares)
@@ -8753,7 +8688,7 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
                  * force a rebalance
                  */
                 cfs_rq_set_shares(tg->cfs_rq[i], 0);
-                set_se_shares(tg->se[i], shares/nr_cpu_ids);
+                set_se_shares(tg->se[i], shares);
         }
 
         /*
diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
new file mode 100644
index 000000000000..9c597e37f7de
--- /dev/null
+++ b/kernel/sched_clock.c
@@ -0,0 +1,236 @@
+/*
+ * sched_clock for unstable cpu clocks
+ *
+ *  Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *
+ * Based on code by:
+ *   Ingo Molnar <mingo@redhat.com>
+ *   Guillaume Chazarain <guichaz@gmail.com>
+ *
+ * Create a semi stable clock from a mixture of other events, including:
+ *  - gtod
+ *  - jiffies
+ *  - sched_clock()
+ *  - explicit idle events
+ *
+ * We use gtod as base and the unstable clock deltas. The deltas are filtered,
+ * making it monotonic and keeping it within an expected window.  This window
+ * is set up using jiffies.
+ *
+ * Furthermore, explicit sleep and wakeup hooks allow us to account for time
+ * that is otherwise invisible (TSC gets stopped).
+ *
+ * The clock: sched_clock_cpu() is monotonic per cpu, and should be somewhat
+ * consistent between cpus (never more than 1 jiffies difference).
+ */
+#include <linux/sched.h>
+#include <linux/percpu.h>
+#include <linux/spinlock.h>
+#include <linux/ktime.h>
+#include <linux/module.h>
+
+
+#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+
+struct sched_clock_data {
+        /*
+         * Raw spinlock - this is a special case: this might be called
+         * from within instrumentation code so we dont want to do any
+         * instrumentation ourselves.
+         */
+        raw_spinlock_t          lock;
+
+        unsigned long           prev_jiffies;
+        u64                     prev_raw;
+        u64                     tick_raw;
+        u64                     tick_gtod;
+        u64                     clock;
+};
+
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
+
+static inline struct sched_clock_data *this_scd(void)
+{
+        return &__get_cpu_var(sched_clock_data);
+}
+
+static inline struct sched_clock_data *cpu_sdc(int cpu)
+{
+        return &per_cpu(sched_clock_data, cpu);
+}
+
+void sched_clock_init(void)
+{
+        u64 ktime_now = ktime_to_ns(ktime_get());
+        u64 now = 0;
+        int cpu;
+
+        for_each_possible_cpu(cpu) {
+                struct sched_clock_data *scd = cpu_sdc(cpu);
+
+                scd->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+                scd->prev_jiffies = jiffies;
+                scd->prev_raw = now;
+                scd->tick_raw = now;
+                scd->tick_gtod = ktime_now;
+                scd->clock = ktime_now;
+        }
+}
+
+/*
+ * update the percpu scd from the raw @now value
+ *
+ *  - filter out backward motion
+ *  - use jiffies to generate a min,max window to clip the raw values
+ */
+static void __update_sched_clock(struct sched_clock_data *scd, u64 now)
+{
+        unsigned long now_jiffies = jiffies;
+        long delta_jiffies = now_jiffies - scd->prev_jiffies;
+        u64 clock = scd->clock;
+        u64 min_clock, max_clock;
+        s64 delta = now - scd->prev_raw;
+
+        WARN_ON_ONCE(!irqs_disabled());
+        min_clock = scd->tick_gtod + delta_jiffies * TICK_NSEC;
+
+        if (unlikely(delta < 0)) {
+                clock++;
+                goto out;
+        }
+
+        max_clock = min_clock + TICK_NSEC;
+
+        if (unlikely(clock + delta > max_clock)) {
+                if (clock < max_clock)
+                        clock = max_clock;
+                else
+                        clock++;
+        } else {
+                clock += delta;
+        }
+
+ out:
+        if (unlikely(clock < min_clock))
+                clock = min_clock;
+
+        scd->prev_raw = now;
+        scd->prev_jiffies = now_jiffies;
+        scd->clock = clock;
+}
+
+static void lock_double_clock(struct sched_clock_data *data1,
+                                struct sched_clock_data *data2)
+{
+        if (data1 < data2) {
+                __raw_spin_lock(&data1->lock);
+                __raw_spin_lock(&data2->lock);
+        } else {
+                __raw_spin_lock(&data2->lock);
+                __raw_spin_lock(&data1->lock);
+        }
+}
+
+u64 sched_clock_cpu(int cpu)
+{
+        struct sched_clock_data *scd = cpu_sdc(cpu);
+        u64 now, clock;
+
+        WARN_ON_ONCE(!irqs_disabled());
+        now = sched_clock();
+
+        if (cpu != raw_smp_processor_id()) {
+                /*
+                 * in order to update a remote cpu's clock based on our
+                 * unstable raw time rebase it against:
+                 *   tick_raw           (offset between raw counters)
+                 *   tick_gotd          (tick offset between cpus)
+                 */
+                struct sched_clock_data *my_scd = this_scd();
+
+                lock_double_clock(scd, my_scd);
+
+                now -= my_scd->tick_raw;
+                now += scd->tick_raw;
+
+                now -= my_scd->tick_gtod;
+                now += scd->tick_gtod;
+
+                __raw_spin_unlock(&my_scd->lock);
+        } else {
+                __raw_spin_lock(&scd->lock);
+        }
+
+        __update_sched_clock(scd, now);
+        clock = scd->clock;
+
+        __raw_spin_unlock(&scd->lock);
+
+        return clock;
+}
+
+void sched_clock_tick(void)
+{
+        struct sched_clock_data *scd = this_scd();
+        u64 now, now_gtod;
+
+        WARN_ON_ONCE(!irqs_disabled());
+
+        now = sched_clock();
+        now_gtod = ktime_to_ns(ktime_get());
+
+        __raw_spin_lock(&scd->lock);
+        __update_sched_clock(scd, now);
+        /*
+         * update tick_gtod after __update_sched_clock() because that will
+         * already observe 1 new jiffy; adding a new tick_gtod to that would
+         * increase the clock 2 jiffies.
+         */
+        scd->tick_raw = now;
+        scd->tick_gtod = now_gtod;
+        __raw_spin_unlock(&scd->lock);
+}
+
+/*
+ * We are going deep-idle (irqs are disabled):
+ */
+void sched_clock_idle_sleep_event(void)
+{
+        sched_clock_cpu(smp_processor_id());
+}
+EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event);
+
+/*
+ * We just idled delta nanoseconds (called with irqs disabled):
+ */
+void sched_clock_idle_wakeup_event(u64 delta_ns)
+{
+        struct sched_clock_data *scd = this_scd();
+        u64 now = sched_clock();
+
+        /*
+         * Override the previous timestamp and ignore all
+         * sched_clock() deltas that occured while we idled,
+         * and use the PM-provided delta_ns to advance the
+         * rq clock:
+         */
+        __raw_spin_lock(&scd->lock);
+        scd->prev_raw = now;
+        scd->clock += delta_ns;
+        __raw_spin_unlock(&scd->lock);
+
+        touch_softlockup_watchdog();
+}
+EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
+
+#endif
+
+/*
+ * Scheduler clock - returns current time in nanosec units.
+ * This is default implementation.
+ * Architectures and sub-architectures can override this.
+ */
+unsigned long long __attribute__((weak)) sched_clock(void)
+{
+        return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
+}
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 6b4a12558e88..5f06118fbc31 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -204,13 +204,6 @@ static void print_cpu(struct seq_file *m, int cpu)
         PN(next_balance);
         P(curr->pid);
         PN(clock);
-        PN(idle_clock);
-        PN(prev_clock_raw);
-        P(clock_warps);
-        P(clock_overflows);
-        P(clock_underflows);
-        P(clock_deep_idle_events);
-        PN(clock_max_delta);
         P(cpu_load[0]);
         P(cpu_load[1]);
         P(cpu_load[2]);
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 89fa32b4edf2..c863663d204d 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -682,6 +682,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
          * Update run-time statistics of the 'current'.
          */
         update_curr(cfs_rq);
+        account_entity_enqueue(cfs_rq, se);
 
         if (wakeup) {
                 place_entity(cfs_rq, se, 0);
@@ -692,7 +693,6 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
         check_spread(cfs_rq, se);
         if (se != cfs_rq->curr)
                 __enqueue_entity(cfs_rq, se);
-        account_entity_enqueue(cfs_rq, se);
 }
 
 static void update_avg(u64 *avg, u64 sample)
@@ -841,8 +841,10 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
          * queued ticks are scheduled to match the slice, so don't bother
          * validating it and just reschedule.
          */
-        if (queued)
-                return resched_task(rq_of(cfs_rq)->curr);
+        if (queued) {
+                resched_task(rq_of(cfs_rq)->curr);
+                return;
+        }
         /*
          * don't let the period tick interfere with the hrtick preemption
          */
@@ -957,7 +959,7 @@ static void yield_task_fair(struct rq *rq)
                 return;
 
         if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) {
-                __update_rq_clock(rq);
+                update_rq_clock(rq);
                 /*
                  * Update run-time statistics of the 'current'.
                  */
@@ -1007,7 +1009,7 @@ static int wake_idle(int cpu, struct task_struct *p)
          * sibling runqueue info. This will avoid the checks and cache miss
          * penalities associated with that.
          */
-        if (idle_cpu(cpu) || cpu_rq(cpu)->nr_running > 1)
+        if (idle_cpu(cpu) || cpu_rq(cpu)->cfs.nr_running > 1)
                 return cpu;
 
         for_each_domain(cpu, sd) {
@@ -1611,30 +1613,6 @@ static const struct sched_class fair_sched_class = {
 };
 
 #ifdef CONFIG_SCHED_DEBUG
-static void
-print_cfs_rq_tasks(struct seq_file *m, struct cfs_rq *cfs_rq, int depth)
-{
-        struct sched_entity *se;
-
-        if (!cfs_rq)
-                return;
-
-        list_for_each_entry_rcu(se, &cfs_rq->tasks, group_node) {
-                int i;
-
-                for (i = depth; i; i--)
-                        seq_puts(m, "  ");
-
-                seq_printf(m, "%lu %s %lu\n",
-                                se->load.weight,
-                                entity_is_task(se) ? "T" : "G",
-                                calc_delta_weight(SCHED_LOAD_SCALE, se)
-                                );
-                if (!entity_is_task(se))
-                        print_cfs_rq_tasks(m, group_cfs_rq(se), depth + 1);
-        }
-}
-
 static void print_cfs_stats(struct seq_file *m, int cpu)
 {
         struct cfs_rq *cfs_rq;
@@ -1642,9 +1620,6 @@ static void print_cfs_stats(struct seq_file *m, int cpu)
         rcu_read_lock();
         for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
                 print_cfs_rq(m, cpu, cfs_rq);
-
-        seq_printf(m, "\nWeight tree:\n");
-        print_cfs_rq_tasks(m, &cpu_rq(cpu)->cfs, 1);
         rcu_read_unlock();
 }
 #endif
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index 2bcafa375633..3a4f92dbbe66 100644
--- a/kernel/sched_idletask.c
+++ b/kernel/sched_idletask.c
@@ -99,7 +99,7 @@ static void prio_changed_idle(struct rq *rq, struct task_struct *p,
 /*
  * Simple, special scheduling class for the per-CPU idle tasks:
  */
-const struct sched_class idle_sched_class = {
+static const struct sched_class idle_sched_class = {
         /* .next is NULL */
         /* no enqueue/yield_task for idle tasks */
 
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index c2730a5a4f05..060e87b0cb1c 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1098,11 +1098,14 @@ static void post_schedule_rt(struct rq *rq)
         }
 }
 
-
+/*
+ * If we are not running and we are not going to reschedule soon, we should
+ * try to push tasks away now
+ */
 static void task_wake_up_rt(struct rq *rq, struct task_struct *p)
 {
         if (!task_running(rq, p) &&
-            (p->prio >= rq->rt.highest_prio) &&
+            !test_tsk_need_resched(rq->curr) &&
             rq->rt.overloaded)
                 push_rt_tasks(rq);
 }
@@ -1309,7 +1312,7 @@ static void set_curr_task_rt(struct rq *rq)
         p->se.exec_start = rq->clock;
 }
 
-const struct sched_class rt_sched_class = {
+static const struct sched_class rt_sched_class = {
         .next                   = &fair_sched_class,
         .enqueue_task           = enqueue_task_rt,
         .dequeue_task           = dequeue_task_rt,